From 9da3f2b74054406f87dff7101a569217ffceb29b Mon Sep 17 00:00:00 2001 From: Jann Horn Date: Tue, 28 Aug 2018 22:14:20 +0200 Subject: x86/fault: BUG() when uaccess helpers fault on kernel addresses There have been multiple kernel vulnerabilities that permitted userspace to pass completely unchecked pointers through to userspace accessors: - the waitid() bug - commit 96ca579a1ecc ("waitid(): Add missing access_ok() checks") - the sg/bsg read/write APIs - the infiniband read/write APIs These don't happen all that often, but when they do happen, it is hard to test for them properly; and it is probably also hard to discover them with fuzzing. Even when an unmapped kernel address is supplied to such buggy code, it just returns -EFAULT instead of doing a proper BUG() or at least WARN(). Try to make such misbehaving code a bit more visible by refusing to do a fixup in the pagefault handler code when a userspace accessor causes a #PF on a kernel address and the current context isn't whitelisted. Signed-off-by: Jann Horn Signed-off-by: Thomas Gleixner Tested-by: Kees Cook Cc: Andy Lutomirski Cc: kernel-hardening@lists.openwall.com Cc: dvyukov@google.com Cc: Masami Hiramatsu Cc: "Naveen N. Rao" Cc: Anil S Keshavamurthy Cc: "David S. Miller" Cc: Alexander Viro Cc: linux-fsdevel@vger.kernel.org Cc: Borislav Petkov Link: https://lkml.kernel.org/r/20180828201421.157735-7-jannh@google.com --- mm/maccess.c | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'mm') diff --git a/mm/maccess.c b/mm/maccess.c index ec00be51a24f..f3416632e5a4 100644 --- a/mm/maccess.c +++ b/mm/maccess.c @@ -30,8 +30,10 @@ long __probe_kernel_read(void *dst, const void *src, size_t size) set_fs(KERNEL_DS); pagefault_disable(); + current->kernel_uaccess_faults_ok++; ret = __copy_from_user_inatomic(dst, (__force const void __user *)src, size); + current->kernel_uaccess_faults_ok--; pagefault_enable(); set_fs(old_fs); @@ -58,7 +60,9 @@ long __probe_kernel_write(void *dst, const void *src, size_t size) set_fs(KERNEL_DS); pagefault_disable(); + current->kernel_uaccess_faults_ok++; ret = __copy_to_user_inatomic((__force void __user *)dst, src, size); + current->kernel_uaccess_faults_ok--; pagefault_enable(); set_fs(old_fs); @@ -94,11 +98,13 @@ long strncpy_from_unsafe(char *dst, const void *unsafe_addr, long count) set_fs(KERNEL_DS); pagefault_disable(); + current->kernel_uaccess_faults_ok++; do { ret = __get_user(*dst++, (const char __user __force *)src++); } while (dst[-1] && ret == 0 && src - unsafe_addr < count); + current->kernel_uaccess_faults_ok--; dst[-1] = '\0'; pagefault_enable(); set_fs(old_fs); -- cgit v1.2.3 From a6d60245d6d9b1caf66b0d94419988c4836980af Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Thu, 23 Aug 2018 21:01:46 +0100 Subject: asm-generic/tlb: Track which levels of the page tables have been cleared It is common for architectures with hugepage support to require only a single TLB invalidation operation per hugepage during unmap(), rather than iterating through the mapping at a PAGE_SIZE increment. Currently, however, the level in the page table where the unmap() operation occurs is not stored in the mmu_gather structure, therefore forcing architectures to issue additional TLB invalidation operations or to give up and over-invalidate by e.g. invalidating the entire TLB. Ideally, we could add an interval rbtree to the mmu_gather structure, which would allow us to associate the correct mapping granule with the various sub-mappings within the range being invalidated. However, this is costly in terms of book-keeping and memory management, so instead we approximate by keeping track of the page table levels that are cleared and provide a means to query the smallest granule required for invalidation. Acked-by: Peter Zijlstra (Intel) Acked-by: Nicholas Piggin Signed-off-by: Will Deacon --- include/asm-generic/tlb.h | 58 ++++++++++++++++++++++++++++++++++++++++------- mm/memory.c | 4 +++- 2 files changed, 53 insertions(+), 9 deletions(-) (limited to 'mm') diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h index 2b444ad94566..9791e98122a0 100644 --- a/include/asm-generic/tlb.h +++ b/include/asm-generic/tlb.h @@ -116,6 +116,14 @@ struct mmu_gather { */ unsigned int freed_tables : 1; + /* + * at which levels have we cleared entries? + */ + unsigned int cleared_ptes : 1; + unsigned int cleared_pmds : 1; + unsigned int cleared_puds : 1; + unsigned int cleared_p4ds : 1; + struct mmu_gather_batch *active; struct mmu_gather_batch local; struct page *__pages[MMU_GATHER_BUNDLE]; @@ -150,6 +158,10 @@ static inline void __tlb_reset_range(struct mmu_gather *tlb) tlb->end = 0; } tlb->freed_tables = 0; + tlb->cleared_ptes = 0; + tlb->cleared_pmds = 0; + tlb->cleared_puds = 0; + tlb->cleared_p4ds = 0; } static inline void tlb_flush_mmu_tlbonly(struct mmu_gather *tlb) @@ -199,6 +211,25 @@ static inline void tlb_remove_check_page_size_change(struct mmu_gather *tlb, } #endif +static inline unsigned long tlb_get_unmap_shift(struct mmu_gather *tlb) +{ + if (tlb->cleared_ptes) + return PAGE_SHIFT; + if (tlb->cleared_pmds) + return PMD_SHIFT; + if (tlb->cleared_puds) + return PUD_SHIFT; + if (tlb->cleared_p4ds) + return P4D_SHIFT; + + return PAGE_SHIFT; +} + +static inline unsigned long tlb_get_unmap_size(struct mmu_gather *tlb) +{ + return 1UL << tlb_get_unmap_shift(tlb); +} + /* * In the case of tlb vma handling, we can optimise these away in the * case where we're doing a full MM flush. When we're doing a munmap, @@ -232,13 +263,19 @@ static inline void tlb_remove_check_page_size_change(struct mmu_gather *tlb, #define tlb_remove_tlb_entry(tlb, ptep, address) \ do { \ __tlb_adjust_range(tlb, address, PAGE_SIZE); \ + tlb->cleared_ptes = 1; \ __tlb_remove_tlb_entry(tlb, ptep, address); \ } while (0) -#define tlb_remove_huge_tlb_entry(h, tlb, ptep, address) \ - do { \ - __tlb_adjust_range(tlb, address, huge_page_size(h)); \ - __tlb_remove_tlb_entry(tlb, ptep, address); \ +#define tlb_remove_huge_tlb_entry(h, tlb, ptep, address) \ + do { \ + unsigned long _sz = huge_page_size(h); \ + __tlb_adjust_range(tlb, address, _sz); \ + if (_sz == PMD_SIZE) \ + tlb->cleared_pmds = 1; \ + else if (_sz == PUD_SIZE) \ + tlb->cleared_puds = 1; \ + __tlb_remove_tlb_entry(tlb, ptep, address); \ } while (0) /** @@ -252,6 +289,7 @@ static inline void tlb_remove_check_page_size_change(struct mmu_gather *tlb, #define tlb_remove_pmd_tlb_entry(tlb, pmdp, address) \ do { \ __tlb_adjust_range(tlb, address, HPAGE_PMD_SIZE); \ + tlb->cleared_pmds = 1; \ __tlb_remove_pmd_tlb_entry(tlb, pmdp, address); \ } while (0) @@ -266,6 +304,7 @@ static inline void tlb_remove_check_page_size_change(struct mmu_gather *tlb, #define tlb_remove_pud_tlb_entry(tlb, pudp, address) \ do { \ __tlb_adjust_range(tlb, address, HPAGE_PUD_SIZE); \ + tlb->cleared_puds = 1; \ __tlb_remove_pud_tlb_entry(tlb, pudp, address); \ } while (0) @@ -291,7 +330,8 @@ static inline void tlb_remove_check_page_size_change(struct mmu_gather *tlb, #define pte_free_tlb(tlb, ptep, address) \ do { \ __tlb_adjust_range(tlb, address, PAGE_SIZE); \ - tlb->freed_tables = 1; \ + tlb->freed_tables = 1; \ + tlb->cleared_pmds = 1; \ __pte_free_tlb(tlb, ptep, address); \ } while (0) #endif @@ -300,7 +340,8 @@ static inline void tlb_remove_check_page_size_change(struct mmu_gather *tlb, #define pmd_free_tlb(tlb, pmdp, address) \ do { \ __tlb_adjust_range(tlb, address, PAGE_SIZE); \ - tlb->freed_tables = 1; \ + tlb->freed_tables = 1; \ + tlb->cleared_puds = 1; \ __pmd_free_tlb(tlb, pmdp, address); \ } while (0) #endif @@ -310,7 +351,8 @@ static inline void tlb_remove_check_page_size_change(struct mmu_gather *tlb, #define pud_free_tlb(tlb, pudp, address) \ do { \ __tlb_adjust_range(tlb, address, PAGE_SIZE); \ - tlb->freed_tables = 1; \ + tlb->freed_tables = 1; \ + tlb->cleared_p4ds = 1; \ __pud_free_tlb(tlb, pudp, address); \ } while (0) #endif @@ -321,7 +363,7 @@ static inline void tlb_remove_check_page_size_change(struct mmu_gather *tlb, #define p4d_free_tlb(tlb, pudp, address) \ do { \ __tlb_adjust_range(tlb, address, PAGE_SIZE); \ - tlb->freed_tables = 1; \ + tlb->freed_tables = 1; \ __p4d_free_tlb(tlb, pudp, address); \ } while (0) #endif diff --git a/mm/memory.c b/mm/memory.c index c467102a5cbc..9135f48e8d84 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -267,8 +267,10 @@ void arch_tlb_finish_mmu(struct mmu_gather *tlb, { struct mmu_gather_batch *batch, *next; - if (force) + if (force) { + __tlb_reset_range(tlb); __tlb_adjust_range(tlb, start, end - start); + } tlb_flush_mmu(tlb); -- cgit v1.2.3 From 196d9d8bb71deaa2d1c7170c88a2f1a318363047 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 3 Sep 2018 15:07:36 +0100 Subject: mm/memory: Move mmu_gather and TLB invalidation code into its own file In preparation for maintaining the mmu_gather code as its own entity, move the implementation out of memory.c and into its own file. Cc: "Kirill A. Shutemov" Cc: Andrew Morton Cc: Michal Hocko Signed-off-by: Peter Zijlstra Signed-off-by: Will Deacon --- include/asm-generic/tlb.h | 1 + mm/Makefile | 6 +- mm/memory.c | 249 ------------------------------------------- mm/mmu_gather.c | 261 ++++++++++++++++++++++++++++++++++++++++++++++ 4 files changed, 265 insertions(+), 252 deletions(-) create mode 100644 mm/mmu_gather.c (limited to 'mm') diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h index 9791e98122a0..6be86c1c5c58 100644 --- a/include/asm-generic/tlb.h +++ b/include/asm-generic/tlb.h @@ -138,6 +138,7 @@ void arch_tlb_gather_mmu(struct mmu_gather *tlb, void tlb_flush_mmu(struct mmu_gather *tlb); void arch_tlb_finish_mmu(struct mmu_gather *tlb, unsigned long start, unsigned long end, bool force); +void tlb_flush_mmu_free(struct mmu_gather *tlb); extern bool __tlb_remove_page_size(struct mmu_gather *tlb, struct page *page, int page_size); diff --git a/mm/Makefile b/mm/Makefile index 8716bdabe1e6..7c48e0d3d8ab 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -23,9 +23,9 @@ KCOV_INSTRUMENT_vmstat.o := n mmu-y := nommu.o mmu-$(CONFIG_MMU) := gup.o highmem.o memory.o mincore.o \ - mlock.o mmap.o mprotect.o mremap.o msync.o \ - page_vma_mapped.o pagewalk.o pgtable-generic.o \ - rmap.o vmalloc.o + mlock.o mmap.o mmu_gather.o mprotect.o mremap.o \ + msync.o page_vma_mapped.o pagewalk.o \ + pgtable-generic.o rmap.o vmalloc.o ifdef CONFIG_CROSS_MEMORY_ATTACH diff --git a/mm/memory.c b/mm/memory.c index 9135f48e8d84..21a5e6e4758b 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -186,255 +186,6 @@ static void check_sync_rss_stat(struct task_struct *task) #endif /* SPLIT_RSS_COUNTING */ -#ifdef HAVE_GENERIC_MMU_GATHER - -static bool tlb_next_batch(struct mmu_gather *tlb) -{ - struct mmu_gather_batch *batch; - - batch = tlb->active; - if (batch->next) { - tlb->active = batch->next; - return true; - } - - if (tlb->batch_count == MAX_GATHER_BATCH_COUNT) - return false; - - batch = (void *)__get_free_pages(GFP_NOWAIT | __GFP_NOWARN, 0); - if (!batch) - return false; - - tlb->batch_count++; - batch->next = NULL; - batch->nr = 0; - batch->max = MAX_GATHER_BATCH; - - tlb->active->next = batch; - tlb->active = batch; - - return true; -} - -void arch_tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, - unsigned long start, unsigned long end) -{ - tlb->mm = mm; - - /* Is it from 0 to ~0? */ - tlb->fullmm = !(start | (end+1)); - tlb->need_flush_all = 0; - tlb->local.next = NULL; - tlb->local.nr = 0; - tlb->local.max = ARRAY_SIZE(tlb->__pages); - tlb->active = &tlb->local; - tlb->batch_count = 0; - -#ifdef CONFIG_HAVE_RCU_TABLE_FREE - tlb->batch = NULL; -#endif - tlb->page_size = 0; - - __tlb_reset_range(tlb); -} - -static void tlb_flush_mmu_free(struct mmu_gather *tlb) -{ - struct mmu_gather_batch *batch; - -#ifdef CONFIG_HAVE_RCU_TABLE_FREE - tlb_table_flush(tlb); -#endif - for (batch = &tlb->local; batch && batch->nr; batch = batch->next) { - free_pages_and_swap_cache(batch->pages, batch->nr); - batch->nr = 0; - } - tlb->active = &tlb->local; -} - -void tlb_flush_mmu(struct mmu_gather *tlb) -{ - tlb_flush_mmu_tlbonly(tlb); - tlb_flush_mmu_free(tlb); -} - -/* tlb_finish_mmu - * Called at the end of the shootdown operation to free up any resources - * that were required. - */ -void arch_tlb_finish_mmu(struct mmu_gather *tlb, - unsigned long start, unsigned long end, bool force) -{ - struct mmu_gather_batch *batch, *next; - - if (force) { - __tlb_reset_range(tlb); - __tlb_adjust_range(tlb, start, end - start); - } - - tlb_flush_mmu(tlb); - - /* keep the page table cache within bounds */ - check_pgt_cache(); - - for (batch = tlb->local.next; batch; batch = next) { - next = batch->next; - free_pages((unsigned long)batch, 0); - } - tlb->local.next = NULL; -} - -/* __tlb_remove_page - * Must perform the equivalent to __free_pte(pte_get_and_clear(ptep)), while - * handling the additional races in SMP caused by other CPUs caching valid - * mappings in their TLBs. Returns the number of free page slots left. - * When out of page slots we must call tlb_flush_mmu(). - *returns true if the caller should flush. - */ -bool __tlb_remove_page_size(struct mmu_gather *tlb, struct page *page, int page_size) -{ - struct mmu_gather_batch *batch; - - VM_BUG_ON(!tlb->end); - VM_WARN_ON(tlb->page_size != page_size); - - batch = tlb->active; - /* - * Add the page and check if we are full. If so - * force a flush. - */ - batch->pages[batch->nr++] = page; - if (batch->nr == batch->max) { - if (!tlb_next_batch(tlb)) - return true; - batch = tlb->active; - } - VM_BUG_ON_PAGE(batch->nr > batch->max, page); - - return false; -} - -#endif /* HAVE_GENERIC_MMU_GATHER */ - -#ifdef CONFIG_HAVE_RCU_TABLE_FREE - -/* - * See the comment near struct mmu_table_batch. - */ - -/* - * If we want tlb_remove_table() to imply TLB invalidates. - */ -static inline void tlb_table_invalidate(struct mmu_gather *tlb) -{ -#ifdef CONFIG_HAVE_RCU_TABLE_INVALIDATE - /* - * Invalidate page-table caches used by hardware walkers. Then we still - * need to RCU-sched wait while freeing the pages because software - * walkers can still be in-flight. - */ - tlb_flush_mmu_tlbonly(tlb); -#endif -} - -static void tlb_remove_table_smp_sync(void *arg) -{ - /* Simply deliver the interrupt */ -} - -static void tlb_remove_table_one(void *table) -{ - /* - * This isn't an RCU grace period and hence the page-tables cannot be - * assumed to be actually RCU-freed. - * - * It is however sufficient for software page-table walkers that rely on - * IRQ disabling. See the comment near struct mmu_table_batch. - */ - smp_call_function(tlb_remove_table_smp_sync, NULL, 1); - __tlb_remove_table(table); -} - -static void tlb_remove_table_rcu(struct rcu_head *head) -{ - struct mmu_table_batch *batch; - int i; - - batch = container_of(head, struct mmu_table_batch, rcu); - - for (i = 0; i < batch->nr; i++) - __tlb_remove_table(batch->tables[i]); - - free_page((unsigned long)batch); -} - -void tlb_table_flush(struct mmu_gather *tlb) -{ - struct mmu_table_batch **batch = &tlb->batch; - - if (*batch) { - tlb_table_invalidate(tlb); - call_rcu_sched(&(*batch)->rcu, tlb_remove_table_rcu); - *batch = NULL; - } -} - -void tlb_remove_table(struct mmu_gather *tlb, void *table) -{ - struct mmu_table_batch **batch = &tlb->batch; - - if (*batch == NULL) { - *batch = (struct mmu_table_batch *)__get_free_page(GFP_NOWAIT | __GFP_NOWARN); - if (*batch == NULL) { - tlb_table_invalidate(tlb); - tlb_remove_table_one(table); - return; - } - (*batch)->nr = 0; - } - - (*batch)->tables[(*batch)->nr++] = table; - if ((*batch)->nr == MAX_TABLE_BATCH) - tlb_table_flush(tlb); -} - -#endif /* CONFIG_HAVE_RCU_TABLE_FREE */ - -/** - * tlb_gather_mmu - initialize an mmu_gather structure for page-table tear-down - * @tlb: the mmu_gather structure to initialize - * @mm: the mm_struct of the target address space - * @start: start of the region that will be removed from the page-table - * @end: end of the region that will be removed from the page-table - * - * Called to initialize an (on-stack) mmu_gather structure for page-table - * tear-down from @mm. The @start and @end are set to 0 and -1 - * respectively when @mm is without users and we're going to destroy - * the full address space (exit/execve). - */ -void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, - unsigned long start, unsigned long end) -{ - arch_tlb_gather_mmu(tlb, mm, start, end); - inc_tlb_flush_pending(tlb->mm); -} - -void tlb_finish_mmu(struct mmu_gather *tlb, - unsigned long start, unsigned long end) -{ - /* - * If there are parallel threads are doing PTE changes on same range - * under non-exclusive lock(e.g., mmap_sem read-side) but defer TLB - * flush by batching, a thread has stable TLB entry can fail to flush - * the TLB by observing pte_none|!pte_dirty, for example so flush TLB - * forcefully if we detect parallel PTE batching threads. - */ - bool force = mm_tlb_flush_nested(tlb->mm); - - arch_tlb_finish_mmu(tlb, start, end, force); - dec_tlb_flush_pending(tlb->mm); -} - /* * Note: this doesn't free the actual pages themselves. That * has been handled earlier when unmapping all the memory regions. diff --git a/mm/mmu_gather.c b/mm/mmu_gather.c new file mode 100644 index 000000000000..2a9fbc4a37d5 --- /dev/null +++ b/mm/mmu_gather.c @@ -0,0 +1,261 @@ +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include + +#ifdef HAVE_GENERIC_MMU_GATHER + +static bool tlb_next_batch(struct mmu_gather *tlb) +{ + struct mmu_gather_batch *batch; + + batch = tlb->active; + if (batch->next) { + tlb->active = batch->next; + return true; + } + + if (tlb->batch_count == MAX_GATHER_BATCH_COUNT) + return false; + + batch = (void *)__get_free_pages(GFP_NOWAIT | __GFP_NOWARN, 0); + if (!batch) + return false; + + tlb->batch_count++; + batch->next = NULL; + batch->nr = 0; + batch->max = MAX_GATHER_BATCH; + + tlb->active->next = batch; + tlb->active = batch; + + return true; +} + +void arch_tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, + unsigned long start, unsigned long end) +{ + tlb->mm = mm; + + /* Is it from 0 to ~0? */ + tlb->fullmm = !(start | (end+1)); + tlb->need_flush_all = 0; + tlb->local.next = NULL; + tlb->local.nr = 0; + tlb->local.max = ARRAY_SIZE(tlb->__pages); + tlb->active = &tlb->local; + tlb->batch_count = 0; + +#ifdef CONFIG_HAVE_RCU_TABLE_FREE + tlb->batch = NULL; +#endif + tlb->page_size = 0; + + __tlb_reset_range(tlb); +} + +void tlb_flush_mmu_free(struct mmu_gather *tlb) +{ + struct mmu_gather_batch *batch; + +#ifdef CONFIG_HAVE_RCU_TABLE_FREE + tlb_table_flush(tlb); +#endif + for (batch = &tlb->local; batch && batch->nr; batch = batch->next) { + free_pages_and_swap_cache(batch->pages, batch->nr); + batch->nr = 0; + } + tlb->active = &tlb->local; +} + +void tlb_flush_mmu(struct mmu_gather *tlb) +{ + tlb_flush_mmu_tlbonly(tlb); + tlb_flush_mmu_free(tlb); +} + +/* tlb_finish_mmu + * Called at the end of the shootdown operation to free up any resources + * that were required. + */ +void arch_tlb_finish_mmu(struct mmu_gather *tlb, + unsigned long start, unsigned long end, bool force) +{ + struct mmu_gather_batch *batch, *next; + + if (force) { + __tlb_reset_range(tlb); + __tlb_adjust_range(tlb, start, end - start); + } + + tlb_flush_mmu(tlb); + + /* keep the page table cache within bounds */ + check_pgt_cache(); + + for (batch = tlb->local.next; batch; batch = next) { + next = batch->next; + free_pages((unsigned long)batch, 0); + } + tlb->local.next = NULL; +} + +/* __tlb_remove_page + * Must perform the equivalent to __free_pte(pte_get_and_clear(ptep)), while + * handling the additional races in SMP caused by other CPUs caching valid + * mappings in their TLBs. Returns the number of free page slots left. + * When out of page slots we must call tlb_flush_mmu(). + *returns true if the caller should flush. + */ +bool __tlb_remove_page_size(struct mmu_gather *tlb, struct page *page, int page_size) +{ + struct mmu_gather_batch *batch; + + VM_BUG_ON(!tlb->end); + VM_WARN_ON(tlb->page_size != page_size); + + batch = tlb->active; + /* + * Add the page and check if we are full. If so + * force a flush. + */ + batch->pages[batch->nr++] = page; + if (batch->nr == batch->max) { + if (!tlb_next_batch(tlb)) + return true; + batch = tlb->active; + } + VM_BUG_ON_PAGE(batch->nr > batch->max, page); + + return false; +} + +#endif /* HAVE_GENERIC_MMU_GATHER */ + +#ifdef CONFIG_HAVE_RCU_TABLE_FREE + +/* + * See the comment near struct mmu_table_batch. + */ + +/* + * If we want tlb_remove_table() to imply TLB invalidates. + */ +static inline void tlb_table_invalidate(struct mmu_gather *tlb) +{ +#ifdef CONFIG_HAVE_RCU_TABLE_INVALIDATE + /* + * Invalidate page-table caches used by hardware walkers. Then we still + * need to RCU-sched wait while freeing the pages because software + * walkers can still be in-flight. + */ + tlb_flush_mmu_tlbonly(tlb); +#endif +} + +static void tlb_remove_table_smp_sync(void *arg) +{ + /* Simply deliver the interrupt */ +} + +static void tlb_remove_table_one(void *table) +{ + /* + * This isn't an RCU grace period and hence the page-tables cannot be + * assumed to be actually RCU-freed. + * + * It is however sufficient for software page-table walkers that rely on + * IRQ disabling. See the comment near struct mmu_table_batch. + */ + smp_call_function(tlb_remove_table_smp_sync, NULL, 1); + __tlb_remove_table(table); +} + +static void tlb_remove_table_rcu(struct rcu_head *head) +{ + struct mmu_table_batch *batch; + int i; + + batch = container_of(head, struct mmu_table_batch, rcu); + + for (i = 0; i < batch->nr; i++) + __tlb_remove_table(batch->tables[i]); + + free_page((unsigned long)batch); +} + +void tlb_table_flush(struct mmu_gather *tlb) +{ + struct mmu_table_batch **batch = &tlb->batch; + + if (*batch) { + tlb_table_invalidate(tlb); + call_rcu_sched(&(*batch)->rcu, tlb_remove_table_rcu); + *batch = NULL; + } +} + +void tlb_remove_table(struct mmu_gather *tlb, void *table) +{ + struct mmu_table_batch **batch = &tlb->batch; + + if (*batch == NULL) { + *batch = (struct mmu_table_batch *)__get_free_page(GFP_NOWAIT | __GFP_NOWARN); + if (*batch == NULL) { + tlb_table_invalidate(tlb); + tlb_remove_table_one(table); + return; + } + (*batch)->nr = 0; + } + + (*batch)->tables[(*batch)->nr++] = table; + if ((*batch)->nr == MAX_TABLE_BATCH) + tlb_table_flush(tlb); +} + +#endif /* CONFIG_HAVE_RCU_TABLE_FREE */ + +/** + * tlb_gather_mmu - initialize an mmu_gather structure for page-table tear-down + * @tlb: the mmu_gather structure to initialize + * @mm: the mm_struct of the target address space + * @start: start of the region that will be removed from the page-table + * @end: end of the region that will be removed from the page-table + * + * Called to initialize an (on-stack) mmu_gather structure for page-table + * tear-down from @mm. The @start and @end are set to 0 and -1 + * respectively when @mm is without users and we're going to destroy + * the full address space (exit/execve). + */ +void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, + unsigned long start, unsigned long end) +{ + arch_tlb_gather_mmu(tlb, mm, start, end); + inc_tlb_flush_pending(tlb->mm); +} + +void tlb_finish_mmu(struct mmu_gather *tlb, + unsigned long start, unsigned long end) +{ + /* + * If there are parallel threads are doing PTE changes on same range + * under non-exclusive lock(e.g., mmap_sem read-side) but defer TLB + * flush by batching, a thread has stable TLB entry can fail to flush + * the TLB by observing pte_none|!pte_dirty, for example so flush TLB + * forcefully if we detect parallel PTE batching threads. + */ + bool force = mm_tlb_flush_nested(tlb->mm); + + arch_tlb_finish_mmu(tlb, start, end, force); + dec_tlb_flush_pending(tlb->mm); +} -- cgit v1.2.3 From 079b22dc9be985c591589fcb94769b8e13518aa0 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Mon, 3 Sep 2018 10:32:52 +0200 Subject: signal: Use SEND_SIG_PRIV not SEND_SIG_FORCED with SIGKILL and SIGSTOP Now that siginfo is never allocated for SIGKILL and SIGSTOP there is no difference between SEND_SIG_PRIV and SEND_SIG_FORCED for SIGKILL and SIGSTOP. This makes SEND_SIG_FORCED unnecessary and redundant in the presence of SIGKILL and SIGSTOP. Therefore change users of SEND_SIG_FORCED that are sending SIGKILL or SIGSTOP to use SEND_SIG_PRIV instead. This removes the last users of SEND_SIG_FORCED. Reviewed-by: Thomas Gleixner Signed-off-by: "Eric W. Biederman" --- kernel/pid_namespace.c | 2 +- kernel/ptrace.c | 4 ++-- mm/oom_kill.c | 4 ++-- 3 files changed, 5 insertions(+), 5 deletions(-) (limited to 'mm') diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c index 2a2ac53d8b8b..c8d53397bbdd 100644 --- a/kernel/pid_namespace.c +++ b/kernel/pid_namespace.c @@ -216,7 +216,7 @@ void zap_pid_ns_processes(struct pid_namespace *pid_ns) idr_for_each_entry_continue(&pid_ns->idr, pid, nr) { task = pid_task(pid, PIDTYPE_PID); if (task && !__fatal_signal_pending(task)) - send_sig_info(SIGKILL, SEND_SIG_FORCED, task); + send_sig_info(SIGKILL, SEND_SIG_PRIV, task); } read_unlock(&tasklist_lock); rcu_read_unlock(); diff --git a/kernel/ptrace.c b/kernel/ptrace.c index 21fec73d45d4..45f77a1b9c97 100644 --- a/kernel/ptrace.c +++ b/kernel/ptrace.c @@ -396,7 +396,7 @@ static int ptrace_attach(struct task_struct *task, long request, /* SEIZE doesn't trap tracee on attach */ if (!seize) - send_sig_info(SIGSTOP, SEND_SIG_FORCED, task); + send_sig_info(SIGSTOP, SEND_SIG_PRIV, task); spin_lock(&task->sighand->siglock); @@ -563,7 +563,7 @@ void exit_ptrace(struct task_struct *tracer, struct list_head *dead) list_for_each_entry_safe(p, n, &tracer->ptraced, ptrace_entry) { if (unlikely(p->ptrace & PT_EXITKILL)) - send_sig_info(SIGKILL, SEND_SIG_FORCED, p); + send_sig_info(SIGKILL, SEND_SIG_PRIV, p); if (__ptrace_detach(tracer, p)) list_add(&p->ptrace_entry, dead); diff --git a/mm/oom_kill.c b/mm/oom_kill.c index b5b25e4dcbbb..3bcfeaaeed87 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -858,7 +858,7 @@ static void __oom_kill_process(struct task_struct *victim) * in order to prevent the OOM victim from depleting the memory * reserves from the user space under its control. */ - do_send_sig_info(SIGKILL, SEND_SIG_FORCED, victim, PIDTYPE_TGID); + do_send_sig_info(SIGKILL, SEND_SIG_PRIV, victim, PIDTYPE_TGID); mark_oom_victim(victim); pr_err("Killed process %d (%s) total-vm:%lukB, anon-rss:%lukB, file-rss:%lukB, shmem-rss:%lukB\n", task_pid_nr(victim), victim->comm, K(victim->mm->total_vm), @@ -896,7 +896,7 @@ static void __oom_kill_process(struct task_struct *victim) */ if (unlikely(p->flags & PF_KTHREAD)) continue; - do_send_sig_info(SIGKILL, SEND_SIG_FORCED, p, PIDTYPE_TGID); + do_send_sig_info(SIGKILL, SEND_SIG_PRIV, p, PIDTYPE_TGID); } rcu_read_unlock(); -- cgit v1.2.3 From 0b59c25f91002c1dec0d0d848e5aaefa5f213c85 Mon Sep 17 00:00:00 2001 From: Igor Stoppa Date: Fri, 31 Aug 2018 22:44:22 +0300 Subject: mm: percpu: remove unnecessary unlikely() WARN_ON() already contains an unlikely(), so it's not necessary to wrap it into another. Signed-off-by: Igor Stoppa Cc: Tejun Heo Cc: zijun_hu Cc: Christoph Lameter Cc: linux-mm@kvack.org Cc: linux-kernel@vger.kernel.org Signed-off-by: Dennis Zhou --- mm/percpu.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'mm') diff --git a/mm/percpu.c b/mm/percpu.c index a749d4d96e3e..f5c2796fe63e 100644 --- a/mm/percpu.c +++ b/mm/percpu.c @@ -2588,7 +2588,7 @@ int __init pcpu_page_first_chunk(size_t reserved_size, BUG_ON(ai->nr_groups != 1); upa = ai->alloc_size/ai->unit_size; nr_g0_units = roundup(num_possible_cpus(), upa); - if (unlikely(WARN_ON(ai->groups[0].nr_units != nr_g0_units))) { + if (WARN_ON(ai->groups[0].nr_units != nr_g0_units)) { pcpu_free_alloc_info(ai); return -EINVAL; } -- cgit v1.2.3 From 74b7c02a9bc124ee3df0d77880ee26db0a325516 Mon Sep 17 00:00:00 2001 From: "Dennis Zhou (Facebook)" Date: Tue, 11 Sep 2018 14:41:31 -0400 Subject: blkcg: associate a blkg for pages being evicted by swap A prior patch in this series added blkg association to bios issued by cgroups. There are two other paths that we want to attribute work back to the appropriate cgroup: swap and writeback. Here we modify the way swap tags bios to include the blkg. Writeback will be tackle in the next patch. Signed-off-by: Dennis Zhou Reviewed-by: Josef Bacik Acked-by: Tejun Heo Signed-off-by: Jens Axboe --- block/bio.c | 83 +++++++++++++++++++++++++++++++++++++---------------- include/linux/bio.h | 11 +++++-- mm/page_io.c | 2 +- 3 files changed, 68 insertions(+), 28 deletions(-) (limited to 'mm') diff --git a/block/bio.c b/block/bio.c index 80c948da061c..387480de6992 100644 --- a/block/bio.c +++ b/block/bio.c @@ -1956,30 +1956,6 @@ EXPORT_SYMBOL(bioset_init_from_src); #ifdef CONFIG_BLK_CGROUP -#ifdef CONFIG_MEMCG -/** - * bio_associate_blkcg_from_page - associate a bio with the page's blkcg - * @bio: target bio - * @page: the page to lookup the blkcg from - * - * Associate @bio with the blkcg from @page's owning memcg. This works like - * every other associate function wrt references. - */ -int bio_associate_blkcg_from_page(struct bio *bio, struct page *page) -{ - struct cgroup_subsys_state *blkcg_css; - - if (unlikely(bio->bi_css)) - return -EBUSY; - if (!page->mem_cgroup) - return 0; - blkcg_css = cgroup_get_e_css(page->mem_cgroup->css.cgroup, - &io_cgrp_subsys); - bio->bi_css = blkcg_css; - return 0; -} -#endif /* CONFIG_MEMCG */ - /** * bio_associate_blkcg - associate a bio with the specified blkcg * @bio: target bio @@ -2030,6 +2006,65 @@ int bio_associate_blkg(struct bio *bio, struct blkcg_gq *blkg) return 0; } +static int __bio_associate_blkg_from_css(struct bio *bio, + struct cgroup_subsys_state *css) +{ + struct blkcg_gq *blkg; + + rcu_read_lock(); + + blkg = blkg_lookup_create(css_to_blkcg(css), bio->bi_disk->queue); + + rcu_read_unlock(); + + return bio_associate_blkg(bio, blkg); +} + +/** + * bio_associate_blkg_from_css - associate a bio with a specified css + * @bio: target bio + * @css: target css + * + * Associate @bio with the blkg found by combining the css's blkg and the + * request_queue of the @bio. This takes a reference on the css that will + * be put upon freeing of @bio. + */ +int bio_associate_blkg_from_css(struct bio *bio, + struct cgroup_subsys_state *css) +{ + css_get(css); + bio->bi_css = css; + return __bio_associate_blkg_from_css(bio, css); +} +EXPORT_SYMBOL_GPL(bio_associate_blkg_from_css); + +#ifdef CONFIG_MEMCG +/** + * bio_associate_blkg_from_page - associate a bio with the page's blkg + * @bio: target bio + * @page: the page to lookup the blkcg from + * + * Associate @bio with the blkg from @page's owning memcg and the respective + * request_queue. This works like every other associate function wrt + * references. + * + * Note: this must be called after bio has an associated device. + */ +int bio_associate_blkg_from_page(struct bio *bio, struct page *page) +{ + struct cgroup_subsys_state *css; + + if (unlikely(bio->bi_css)) + return -EBUSY; + if (!page->mem_cgroup) + return 0; + css = cgroup_get_e_css(page->mem_cgroup->css.cgroup, &io_cgrp_subsys); + bio->bi_css = css; + + return __bio_associate_blkg_from_css(bio, css); +} +#endif /* CONFIG_MEMCG */ + /** * bio_associate_create_blkg - associate a bio with a blkg from q * @q: request_queue where bio is going diff --git a/include/linux/bio.h b/include/linux/bio.h index 829cd0bb407d..c73a870ebc0e 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -533,21 +533,26 @@ do { \ disk_devt((bio)->bi_disk) #if defined(CONFIG_MEMCG) && defined(CONFIG_BLK_CGROUP) -int bio_associate_blkcg_from_page(struct bio *bio, struct page *page); +int bio_associate_blkg_from_page(struct bio *bio, struct page *page); #else -static inline int bio_associate_blkcg_from_page(struct bio *bio, - struct page *page) { return 0; } +static inline int bio_associate_blkg_from_page(struct bio *bio, + struct page *page) { return 0; } #endif #ifdef CONFIG_BLK_CGROUP int bio_associate_blkcg(struct bio *bio, struct cgroup_subsys_state *blkcg_css); int bio_associate_blkg(struct bio *bio, struct blkcg_gq *blkg); +int bio_associate_blkg_from_css(struct bio *bio, + struct cgroup_subsys_state *css); int bio_associate_create_blkg(struct request_queue *q, struct bio *bio); void bio_disassociate_task(struct bio *bio); void bio_clone_blkcg_association(struct bio *dst, struct bio *src); #else /* CONFIG_BLK_CGROUP */ static inline int bio_associate_blkcg(struct bio *bio, struct cgroup_subsys_state *blkcg_css) { return 0; } +static inline int bio_associate_blkg_from_css(struct bio *bio, + struct cgroup_subsys_state *css) +{ return 0; } static inline int bio_associate_create_blkg(struct request_queue *q, struct bio *bio) { return 0; } static inline void bio_disassociate_task(struct bio *bio) { } diff --git a/mm/page_io.c b/mm/page_io.c index aafd19ec1db4..573d3663d846 100644 --- a/mm/page_io.c +++ b/mm/page_io.c @@ -339,7 +339,7 @@ int __swap_writepage(struct page *page, struct writeback_control *wbc, goto out; } bio->bi_opf = REQ_OP_WRITE | REQ_SWAP | wbc_to_write_flags(wbc); - bio_associate_blkcg_from_page(bio, page); + bio_associate_blkg_from_page(bio, page); count_swpout_vm_event(page); set_page_writeback(page); unlock_page(page); -- cgit v1.2.3 From 3159f943aafdbacb2f94c38fdaadabf2bbde2a14 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Fri, 3 Nov 2017 13:30:42 -0400 Subject: xarray: Replace exceptional entries Introduce xarray value entries and tagged pointers to replace radix tree exceptional entries. This is a slight change in encoding to allow the use of an extra bit (we can now store BITS_PER_LONG - 1 bits in a value entry). It is also a change in emphasis; exceptional entries are intimidating and different. As the comment explains, you can choose to store values or pointers in the xarray and they are both first-class citizens. Signed-off-by: Matthew Wilcox Reviewed-by: Josef Bacik --- arch/powerpc/include/asm/book3s/64/pgtable.h | 4 +- arch/powerpc/include/asm/nohash/64/pgtable.h | 4 +- drivers/gpu/drm/i915/i915_gem.c | 17 ++-- drivers/staging/erofs/utils.c | 18 ++--- fs/btrfs/compression.c | 2 +- fs/dax.c | 112 +++++++++++++-------------- fs/proc/task_mmu.c | 2 +- include/linux/radix-tree.h | 36 ++------- include/linux/swapops.h | 19 ++--- include/linux/xarray.h | 102 ++++++++++++++++++++++++ lib/idr.c | 60 ++++++-------- lib/radix-tree.c | 21 +++-- mm/filemap.c | 10 +-- mm/khugepaged.c | 2 +- mm/madvise.c | 2 +- mm/memcontrol.c | 2 +- mm/mincore.c | 2 +- mm/readahead.c | 2 +- mm/shmem.c | 10 +-- mm/swap.c | 2 +- mm/truncate.c | 12 +-- mm/workingset.c | 13 ++-- tools/testing/radix-tree/idr-test.c | 6 +- tools/testing/radix-tree/linux/radix-tree.h | 1 - tools/testing/radix-tree/multiorder.c | 47 ++++++----- tools/testing/radix-tree/test.c | 2 +- 26 files changed, 278 insertions(+), 232 deletions(-) (limited to 'mm') diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h index 2fdc865ca374..62039e557ac0 100644 --- a/arch/powerpc/include/asm/book3s/64/pgtable.h +++ b/arch/powerpc/include/asm/book3s/64/pgtable.h @@ -723,9 +723,7 @@ static inline bool pte_user(pte_t pte) BUILD_BUG_ON(_PAGE_HPTEFLAGS & (0x1f << _PAGE_BIT_SWAP_TYPE)); \ BUILD_BUG_ON(_PAGE_HPTEFLAGS & _PAGE_SWP_SOFT_DIRTY); \ } while (0) -/* - * on pte we don't need handle RADIX_TREE_EXCEPTIONAL_SHIFT; - */ + #define SWP_TYPE_BITS 5 #define __swp_type(x) (((x).val >> _PAGE_BIT_SWAP_TYPE) \ & ((1UL << SWP_TYPE_BITS) - 1)) diff --git a/arch/powerpc/include/asm/nohash/64/pgtable.h b/arch/powerpc/include/asm/nohash/64/pgtable.h index 7cd6809f4d33..05765c2d2c1f 100644 --- a/arch/powerpc/include/asm/nohash/64/pgtable.h +++ b/arch/powerpc/include/asm/nohash/64/pgtable.h @@ -313,9 +313,7 @@ static inline void __ptep_set_access_flags(struct vm_area_struct *vma, #define MAX_SWAPFILES_CHECK() do { \ BUILD_BUG_ON(MAX_SWAPFILES_SHIFT > SWP_TYPE_BITS); \ } while (0) -/* - * on pte we don't need handle RADIX_TREE_EXCEPTIONAL_SHIFT; - */ + #define SWP_TYPE_BITS 5 #define __swp_type(x) (((x).val >> _PAGE_BIT_SWAP_TYPE) \ & ((1UL << SWP_TYPE_BITS) - 1)) diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index fcc73a6ab503..316730b45f84 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -5996,7 +5996,8 @@ i915_gem_object_get_sg(struct drm_i915_gem_object *obj, count = __sg_page_count(sg); while (idx + count <= n) { - unsigned long exception, i; + void *entry; + unsigned long i; int ret; /* If we cannot allocate and insert this entry, or the @@ -6011,12 +6012,9 @@ i915_gem_object_get_sg(struct drm_i915_gem_object *obj, if (ret && ret != -EEXIST) goto scan; - exception = - RADIX_TREE_EXCEPTIONAL_ENTRY | - idx << RADIX_TREE_EXCEPTIONAL_SHIFT; + entry = xa_mk_value(idx); for (i = 1; i < count; i++) { - ret = radix_tree_insert(&iter->radix, idx + i, - (void *)exception); + ret = radix_tree_insert(&iter->radix, idx + i, entry); if (ret && ret != -EEXIST) goto scan; } @@ -6054,15 +6052,14 @@ lookup: GEM_BUG_ON(!sg); /* If this index is in the middle of multi-page sg entry, - * the radixtree will contain an exceptional entry that points + * the radix tree will contain a value entry that points * to the start of that range. We will return the pointer to * the base page and the offset of this page within the * sg entry's range. */ *offset = 0; - if (unlikely(radix_tree_exception(sg))) { - unsigned long base = - (unsigned long)sg >> RADIX_TREE_EXCEPTIONAL_SHIFT; + if (unlikely(xa_is_value(sg))) { + unsigned long base = xa_to_value(sg); sg = radix_tree_lookup(&iter->radix, base); GEM_BUG_ON(!sg); diff --git a/drivers/staging/erofs/utils.c b/drivers/staging/erofs/utils.c index 595cf90af9bb..bdee9bd09f11 100644 --- a/drivers/staging/erofs/utils.c +++ b/drivers/staging/erofs/utils.c @@ -35,7 +35,6 @@ static atomic_long_t erofs_global_shrink_cnt; #ifdef CONFIG_EROFS_FS_ZIP -/* radix_tree and the future XArray both don't use tagptr_t yet */ struct erofs_workgroup *erofs_find_workgroup( struct super_block *sb, pgoff_t index, bool *tag) { @@ -47,9 +46,8 @@ repeat: rcu_read_lock(); grp = radix_tree_lookup(&sbi->workstn_tree, index); if (grp != NULL) { - *tag = radix_tree_exceptional_entry(grp); - grp = (void *)((unsigned long)grp & - ~RADIX_TREE_EXCEPTIONAL_ENTRY); + *tag = xa_pointer_tag(grp); + grp = xa_untag_pointer(grp); if (erofs_workgroup_get(grp, &oldcount)) { /* prefer to relax rcu read side */ @@ -83,9 +81,7 @@ int erofs_register_workgroup(struct super_block *sb, sbi = EROFS_SB(sb); erofs_workstn_lock(sbi); - if (tag) - grp = (void *)((unsigned long)grp | - 1UL << RADIX_TREE_EXCEPTIONAL_SHIFT); + grp = xa_tag_pointer(grp, tag); err = radix_tree_insert(&sbi->workstn_tree, grp->index, grp); @@ -131,9 +127,7 @@ repeat: for (i = 0; i < found; ++i) { int cnt; - struct erofs_workgroup *grp = (void *) - ((unsigned long)batch[i] & - ~RADIX_TREE_EXCEPTIONAL_ENTRY); + struct erofs_workgroup *grp = xa_untag_pointer(batch[i]); first_index = grp->index + 1; @@ -150,8 +144,8 @@ repeat: #endif continue; - if (radix_tree_delete(&sbi->workstn_tree, - grp->index) != grp) { + if (xa_untag_pointer(radix_tree_delete(&sbi->workstn_tree, + grp->index)) != grp) { #ifdef EROFS_FS_HAS_MANAGED_CACHE skip: erofs_workgroup_unfreeze(grp, 1); diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c index 9bfa66592aa7..fd25e125303c 100644 --- a/fs/btrfs/compression.c +++ b/fs/btrfs/compression.c @@ -440,7 +440,7 @@ static noinline int add_ra_bio_pages(struct inode *inode, rcu_read_lock(); page = radix_tree_lookup(&mapping->i_pages, pg_index); rcu_read_unlock(); - if (page && !radix_tree_exceptional_entry(page)) { + if (page && !xa_is_value(page)) { misses++; if (misses > 4) break; diff --git a/fs/dax.c b/fs/dax.c index b68ce484e1be..ebcec36335eb 100644 --- a/fs/dax.c +++ b/fs/dax.c @@ -59,56 +59,57 @@ static int __init init_dax_wait_table(void) fs_initcall(init_dax_wait_table); /* - * We use lowest available bit in exceptional entry for locking, one bit for - * the entry size (PMD) and two more to tell us if the entry is a zero page or - * an empty entry that is just used for locking. In total four special bits. + * DAX pagecache entries use XArray value entries so they can't be mistaken + * for pages. We use one bit for locking, one bit for the entry size (PMD) + * and two more to tell us if the entry is a zero page or an empty entry that + * is just used for locking. In total four special bits. * * If the PMD bit isn't set the entry has size PAGE_SIZE, and if the ZERO_PAGE * and EMPTY bits aren't set the entry is a normal DAX entry with a filesystem * block allocation. */ -#define RADIX_DAX_SHIFT (RADIX_TREE_EXCEPTIONAL_SHIFT + 4) -#define RADIX_DAX_ENTRY_LOCK (1 << RADIX_TREE_EXCEPTIONAL_SHIFT) -#define RADIX_DAX_PMD (1 << (RADIX_TREE_EXCEPTIONAL_SHIFT + 1)) -#define RADIX_DAX_ZERO_PAGE (1 << (RADIX_TREE_EXCEPTIONAL_SHIFT + 2)) -#define RADIX_DAX_EMPTY (1 << (RADIX_TREE_EXCEPTIONAL_SHIFT + 3)) +#define DAX_SHIFT (4) +#define DAX_LOCKED (1UL << 0) +#define DAX_PMD (1UL << 1) +#define DAX_ZERO_PAGE (1UL << 2) +#define DAX_EMPTY (1UL << 3) static unsigned long dax_radix_pfn(void *entry) { - return (unsigned long)entry >> RADIX_DAX_SHIFT; + return xa_to_value(entry) >> DAX_SHIFT; } static void *dax_radix_locked_entry(unsigned long pfn, unsigned long flags) { - return (void *)(RADIX_TREE_EXCEPTIONAL_ENTRY | flags | - (pfn << RADIX_DAX_SHIFT) | RADIX_DAX_ENTRY_LOCK); + return xa_mk_value(flags | ((unsigned long)pfn << DAX_SHIFT) | + DAX_LOCKED); } static unsigned int dax_radix_order(void *entry) { - if ((unsigned long)entry & RADIX_DAX_PMD) + if (xa_to_value(entry) & DAX_PMD) return PMD_SHIFT - PAGE_SHIFT; return 0; } static int dax_is_pmd_entry(void *entry) { - return (unsigned long)entry & RADIX_DAX_PMD; + return xa_to_value(entry) & DAX_PMD; } static int dax_is_pte_entry(void *entry) { - return !((unsigned long)entry & RADIX_DAX_PMD); + return !(xa_to_value(entry) & DAX_PMD); } static int dax_is_zero_entry(void *entry) { - return (unsigned long)entry & RADIX_DAX_ZERO_PAGE; + return xa_to_value(entry) & DAX_ZERO_PAGE; } static int dax_is_empty_entry(void *entry) { - return (unsigned long)entry & RADIX_DAX_EMPTY; + return xa_to_value(entry) & DAX_EMPTY; } /* @@ -186,9 +187,9 @@ static void dax_wake_mapping_entry_waiter(struct address_space *mapping, */ static inline int slot_locked(struct address_space *mapping, void **slot) { - unsigned long entry = (unsigned long) - radix_tree_deref_slot_protected(slot, &mapping->i_pages.xa_lock); - return entry & RADIX_DAX_ENTRY_LOCK; + unsigned long entry = xa_to_value( + radix_tree_deref_slot_protected(slot, &mapping->i_pages.xa_lock)); + return entry & DAX_LOCKED; } /* @@ -196,12 +197,11 @@ static inline int slot_locked(struct address_space *mapping, void **slot) */ static inline void *lock_slot(struct address_space *mapping, void **slot) { - unsigned long entry = (unsigned long) - radix_tree_deref_slot_protected(slot, &mapping->i_pages.xa_lock); - - entry |= RADIX_DAX_ENTRY_LOCK; - radix_tree_replace_slot(&mapping->i_pages, slot, (void *)entry); - return (void *)entry; + unsigned long v = xa_to_value( + radix_tree_deref_slot_protected(slot, &mapping->i_pages.xa_lock)); + void *entry = xa_mk_value(v | DAX_LOCKED); + radix_tree_replace_slot(&mapping->i_pages, slot, entry); + return entry; } /* @@ -209,17 +209,16 @@ static inline void *lock_slot(struct address_space *mapping, void **slot) */ static inline void *unlock_slot(struct address_space *mapping, void **slot) { - unsigned long entry = (unsigned long) - radix_tree_deref_slot_protected(slot, &mapping->i_pages.xa_lock); - - entry &= ~(unsigned long)RADIX_DAX_ENTRY_LOCK; - radix_tree_replace_slot(&mapping->i_pages, slot, (void *)entry); - return (void *)entry; + unsigned long v = xa_to_value( + radix_tree_deref_slot_protected(slot, &mapping->i_pages.xa_lock)); + void *entry = xa_mk_value(v & ~DAX_LOCKED); + radix_tree_replace_slot(&mapping->i_pages, slot, entry); + return entry; } /* * Lookup entry in radix tree, wait for it to become unlocked if it is - * exceptional entry and return it. The caller must call + * a DAX entry and return it. The caller must call * put_unlocked_mapping_entry() when he decided not to lock the entry or * put_locked_mapping_entry() when he locked the entry and now wants to * unlock it. @@ -242,7 +241,7 @@ static void *__get_unlocked_mapping_entry(struct address_space *mapping, entry = __radix_tree_lookup(&mapping->i_pages, index, NULL, &slot); if (!entry || - WARN_ON_ONCE(!radix_tree_exceptional_entry(entry)) || + WARN_ON_ONCE(!xa_is_value(entry)) || !slot_locked(mapping, slot)) { if (slotp) *slotp = slot; @@ -283,7 +282,7 @@ static void unlock_mapping_entry(struct address_space *mapping, pgoff_t index) xa_lock_irq(&mapping->i_pages); entry = __radix_tree_lookup(&mapping->i_pages, index, NULL, &slot); - if (WARN_ON_ONCE(!entry || !radix_tree_exceptional_entry(entry) || + if (WARN_ON_ONCE(!entry || !xa_is_value(entry) || !slot_locked(mapping, slot))) { xa_unlock_irq(&mapping->i_pages); return; @@ -472,12 +471,11 @@ void dax_unlock_mapping_entry(struct page *page) } /* - * Find radix tree entry at given index. If it points to an exceptional entry, - * return it with the radix tree entry locked. If the radix tree doesn't - * contain given index, create an empty exceptional entry for the index and - * return with it locked. + * Find radix tree entry at given index. If it is a DAX entry, return it + * with the radix tree entry locked. If the radix tree doesn't contain the + * given index, create an empty entry for the index and return with it locked. * - * When requesting an entry with size RADIX_DAX_PMD, grab_mapping_entry() will + * When requesting an entry with size DAX_PMD, grab_mapping_entry() will * either return that locked entry or will return an error. This error will * happen if there are any 4k entries within the 2MiB range that we are * requesting. @@ -507,13 +505,13 @@ restart: xa_lock_irq(&mapping->i_pages); entry = get_unlocked_mapping_entry(mapping, index, &slot); - if (WARN_ON_ONCE(entry && !radix_tree_exceptional_entry(entry))) { + if (WARN_ON_ONCE(entry && !xa_is_value(entry))) { entry = ERR_PTR(-EIO); goto out_unlock; } if (entry) { - if (size_flag & RADIX_DAX_PMD) { + if (size_flag & DAX_PMD) { if (dax_is_pte_entry(entry)) { put_unlocked_mapping_entry(mapping, index, entry); @@ -584,7 +582,7 @@ restart: true); } - entry = dax_radix_locked_entry(0, size_flag | RADIX_DAX_EMPTY); + entry = dax_radix_locked_entry(0, size_flag | DAX_EMPTY); err = __radix_tree_insert(&mapping->i_pages, index, dax_radix_order(entry), entry); @@ -673,8 +671,7 @@ struct page *dax_layout_busy_page(struct address_space *mapping) if (index >= end) break; - if (WARN_ON_ONCE( - !radix_tree_exceptional_entry(pvec_ent))) + if (WARN_ON_ONCE(!xa_is_value(pvec_ent))) continue; xa_lock_irq(&mapping->i_pages); @@ -713,7 +710,7 @@ static int __dax_invalidate_mapping_entry(struct address_space *mapping, xa_lock_irq(pages); entry = get_unlocked_mapping_entry(mapping, index, NULL); - if (!entry || WARN_ON_ONCE(!radix_tree_exceptional_entry(entry))) + if (!entry || WARN_ON_ONCE(!xa_is_value(entry))) goto out; if (!trunc && (radix_tree_tag_get(pages, index, PAGECACHE_TAG_DIRTY) || @@ -729,8 +726,8 @@ out: return ret; } /* - * Delete exceptional DAX entry at @index from @mapping. Wait for radix tree - * entry to get unlocked before deleting it. + * Delete DAX entry at @index from @mapping. Wait for it + * to be unlocked before deleting it. */ int dax_delete_mapping_entry(struct address_space *mapping, pgoff_t index) { @@ -740,7 +737,7 @@ int dax_delete_mapping_entry(struct address_space *mapping, pgoff_t index) * This gets called from truncate / punch_hole path. As such, the caller * must hold locks protecting against concurrent modifications of the * radix tree (usually fs-private i_mmap_sem for writing). Since the - * caller has seen exceptional entry for this index, we better find it + * caller has seen a DAX entry for this index, we better find it * at that index as well... */ WARN_ON_ONCE(!ret); @@ -748,7 +745,7 @@ int dax_delete_mapping_entry(struct address_space *mapping, pgoff_t index) } /* - * Invalidate exceptional DAX entry if it is clean. + * Invalidate DAX entry if it is clean. */ int dax_invalidate_mapping_entry_sync(struct address_space *mapping, pgoff_t index) @@ -802,7 +799,7 @@ static void *dax_insert_mapping_entry(struct address_space *mapping, if (dirty) __mark_inode_dirty(mapping->host, I_DIRTY_PAGES); - if (dax_is_zero_entry(entry) && !(flags & RADIX_DAX_ZERO_PAGE)) { + if (dax_is_zero_entry(entry) && !(flags & DAX_ZERO_PAGE)) { /* we are replacing a zero page with block mapping */ if (dax_is_pmd_entry(entry)) unmap_mapping_pages(mapping, index & ~PG_PMD_COLOUR, @@ -940,13 +937,13 @@ static int dax_writeback_one(struct dax_device *dax_dev, * A page got tagged dirty in DAX mapping? Something is seriously * wrong. */ - if (WARN_ON(!radix_tree_exceptional_entry(entry))) + if (WARN_ON(!xa_is_value(entry))) return -EIO; xa_lock_irq(pages); entry2 = get_unlocked_mapping_entry(mapping, index, &slot); /* Entry got punched out / reallocated? */ - if (!entry2 || WARN_ON_ONCE(!radix_tree_exceptional_entry(entry2))) + if (!entry2 || WARN_ON_ONCE(!xa_is_value(entry2))) goto put_unlocked; /* * Entry got reallocated elsewhere? No need to writeback. We have to @@ -1123,8 +1120,9 @@ static vm_fault_t dax_load_hole(struct address_space *mapping, void *entry, pfn_t pfn = pfn_to_pfn_t(my_zero_pfn(vaddr)); vm_fault_t ret; - dax_insert_mapping_entry(mapping, vmf, entry, pfn, RADIX_DAX_ZERO_PAGE, - false); + dax_insert_mapping_entry(mapping, vmf, entry, pfn, + DAX_ZERO_PAGE, false); + ret = vmf_insert_mixed(vmf->vma, vaddr, pfn); trace_dax_load_hole(inode, vmf, ret); return ret; @@ -1514,7 +1512,7 @@ static vm_fault_t dax_pmd_load_hole(struct vm_fault *vmf, struct iomap *iomap, pfn = page_to_pfn_t(zero_page); ret = dax_insert_mapping_entry(mapping, vmf, entry, pfn, - RADIX_DAX_PMD | RADIX_DAX_ZERO_PAGE, false); + DAX_PMD | DAX_ZERO_PAGE, false); ptl = pmd_lock(vmf->vma->vm_mm, vmf->pmd); if (!pmd_none(*(vmf->pmd))) { @@ -1597,7 +1595,7 @@ static vm_fault_t dax_iomap_pmd_fault(struct vm_fault *vmf, pfn_t *pfnp, * is already in the tree, for instance), it will return -EEXIST and * we just fall back to 4k entries. */ - entry = grab_mapping_entry(mapping, pgoff, RADIX_DAX_PMD); + entry = grab_mapping_entry(mapping, pgoff, DAX_PMD); if (IS_ERR(entry)) goto fallback; @@ -1635,7 +1633,7 @@ static vm_fault_t dax_iomap_pmd_fault(struct vm_fault *vmf, pfn_t *pfnp, goto finish_iomap; entry = dax_insert_mapping_entry(mapping, vmf, entry, pfn, - RADIX_DAX_PMD, write && !sync); + DAX_PMD, write && !sync); /* * If we are doing synchronous page fault and inode needs fsync, diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 5ea1d64cb0b4..669abb617321 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -521,7 +521,7 @@ static void smaps_pte_entry(pte_t *pte, unsigned long addr, if (!page) return; - if (radix_tree_exceptional_entry(page)) + if (xa_is_value(page)) mss->swap += PAGE_SIZE; else put_page(page); diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h index 34149e8b5f73..e9e76ab4fbbf 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -28,34 +28,26 @@ #include #include #include +#include /* * The bottom two bits of the slot determine how the remaining bits in the * slot are interpreted: * * 00 - data pointer - * 01 - internal entry - * 10 - exceptional entry - * 11 - this bit combination is currently unused/reserved + * 10 - internal entry + * x1 - value entry * * The internal entry may be a pointer to the next level in the tree, a * sibling entry, or an indicator that the entry in this slot has been moved * to another location in the tree and the lookup should be restarted. While * NULL fits the 'data pointer' pattern, it means that there is no entry in * the tree for this index (no matter what level of the tree it is found at). - * This means that you cannot store NULL in the tree as a value for the index. + * This means that storing a NULL entry in the tree is the same as deleting + * the entry from the tree. */ #define RADIX_TREE_ENTRY_MASK 3UL -#define RADIX_TREE_INTERNAL_NODE 1UL - -/* - * Most users of the radix tree store pointers but shmem/tmpfs stores swap - * entries in the same tree. They are marked as exceptional entries to - * distinguish them from pointers to struct page. - * EXCEPTIONAL_ENTRY tests the bit, EXCEPTIONAL_SHIFT shifts content past it. - */ -#define RADIX_TREE_EXCEPTIONAL_ENTRY 2 -#define RADIX_TREE_EXCEPTIONAL_SHIFT 2 +#define RADIX_TREE_INTERNAL_NODE 2UL static inline bool radix_tree_is_internal_node(void *ptr) { @@ -83,11 +75,10 @@ static inline bool radix_tree_is_internal_node(void *ptr) /* * @count is the count of every non-NULL element in the ->slots array - * whether that is an exceptional entry, a retry entry, a user pointer, + * whether that is a value entry, a retry entry, a user pointer, * a sibling entry or a pointer to the next level of the tree. * @exceptional is the count of every element in ->slots which is - * either radix_tree_exceptional_entry() or is a sibling entry for an - * exceptional entry. + * either a value entry or a sibling of a value entry. */ struct radix_tree_node { unsigned char shift; /* Bits remaining in each slot */ @@ -268,17 +259,6 @@ static inline int radix_tree_deref_retry(void *arg) return unlikely(radix_tree_is_internal_node(arg)); } -/** - * radix_tree_exceptional_entry - radix_tree_deref_slot gave exceptional entry? - * @arg: value returned by radix_tree_deref_slot - * Returns: 0 if well-aligned pointer, non-0 if exceptional entry. - */ -static inline int radix_tree_exceptional_entry(void *arg) -{ - /* Not unlikely because radix_tree_exception often tested first */ - return (unsigned long)arg & RADIX_TREE_EXCEPTIONAL_ENTRY; -} - /** * radix_tree_exception - radix_tree_deref_slot returned either exception? * @arg: value returned by radix_tree_deref_slot diff --git a/include/linux/swapops.h b/include/linux/swapops.h index 22af9d8a84ae..4d961668e5fc 100644 --- a/include/linux/swapops.h +++ b/include/linux/swapops.h @@ -18,9 +18,8 @@ * * swp_entry_t's are *never* stored anywhere in their arch-dependent format. */ -#define SWP_TYPE_SHIFT(e) ((sizeof(e.val) * 8) - \ - (MAX_SWAPFILES_SHIFT + RADIX_TREE_EXCEPTIONAL_SHIFT)) -#define SWP_OFFSET_MASK(e) ((1UL << SWP_TYPE_SHIFT(e)) - 1) +#define SWP_TYPE_SHIFT (BITS_PER_XA_VALUE - MAX_SWAPFILES_SHIFT) +#define SWP_OFFSET_MASK ((1UL << SWP_TYPE_SHIFT) - 1) /* * Store a type+offset into a swp_entry_t in an arch-independent format @@ -29,8 +28,7 @@ static inline swp_entry_t swp_entry(unsigned long type, pgoff_t offset) { swp_entry_t ret; - ret.val = (type << SWP_TYPE_SHIFT(ret)) | - (offset & SWP_OFFSET_MASK(ret)); + ret.val = (type << SWP_TYPE_SHIFT) | (offset & SWP_OFFSET_MASK); return ret; } @@ -40,7 +38,7 @@ static inline swp_entry_t swp_entry(unsigned long type, pgoff_t offset) */ static inline unsigned swp_type(swp_entry_t entry) { - return (entry.val >> SWP_TYPE_SHIFT(entry)); + return (entry.val >> SWP_TYPE_SHIFT); } /* @@ -49,7 +47,7 @@ static inline unsigned swp_type(swp_entry_t entry) */ static inline pgoff_t swp_offset(swp_entry_t entry) { - return entry.val & SWP_OFFSET_MASK(entry); + return entry.val & SWP_OFFSET_MASK; } #ifdef CONFIG_MMU @@ -90,16 +88,13 @@ static inline swp_entry_t radix_to_swp_entry(void *arg) { swp_entry_t entry; - entry.val = (unsigned long)arg >> RADIX_TREE_EXCEPTIONAL_SHIFT; + entry.val = xa_to_value(arg); return entry; } static inline void *swp_to_radix_entry(swp_entry_t entry) { - unsigned long value; - - value = entry.val << RADIX_TREE_EXCEPTIONAL_SHIFT; - return (void *)(value | RADIX_TREE_EXCEPTIONAL_ENTRY); + return xa_mk_value(entry.val); } #if IS_ENABLED(CONFIG_DEVICE_PRIVATE) diff --git a/include/linux/xarray.h b/include/linux/xarray.h index 9e4c86853fa4..5c8acfc4ff55 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -5,9 +5,111 @@ * eXtensible Arrays * Copyright (c) 2017 Microsoft Corporation * Author: Matthew Wilcox + * + * See Documentation/core-api/xarray.rst for how to use the XArray. */ +#include #include +#include + +/* + * The bottom two bits of the entry determine how the XArray interprets + * the contents: + * + * 00: Pointer entry + * 10: Internal entry + * x1: Value entry or tagged pointer + * + * Attempting to store internal entries in the XArray is a bug. + */ + +#define BITS_PER_XA_VALUE (BITS_PER_LONG - 1) + +/** + * xa_mk_value() - Create an XArray entry from an integer. + * @v: Value to store in XArray. + * + * Context: Any context. + * Return: An entry suitable for storing in the XArray. + */ +static inline void *xa_mk_value(unsigned long v) +{ + WARN_ON((long)v < 0); + return (void *)((v << 1) | 1); +} + +/** + * xa_to_value() - Get value stored in an XArray entry. + * @entry: XArray entry. + * + * Context: Any context. + * Return: The value stored in the XArray entry. + */ +static inline unsigned long xa_to_value(const void *entry) +{ + return (unsigned long)entry >> 1; +} + +/** + * xa_is_value() - Determine if an entry is a value. + * @entry: XArray entry. + * + * Context: Any context. + * Return: True if the entry is a value, false if it is a pointer. + */ +static inline bool xa_is_value(const void *entry) +{ + return (unsigned long)entry & 1; +} + +/** + * xa_tag_pointer() - Create an XArray entry for a tagged pointer. + * @p: Plain pointer. + * @tag: Tag value (0, 1 or 3). + * + * If the user of the XArray prefers, they can tag their pointers instead + * of storing value entries. Three tags are available (0, 1 and 3). + * These are distinct from the xa_mark_t as they are not replicated up + * through the array and cannot be searched for. + * + * Context: Any context. + * Return: An XArray entry. + */ +static inline void *xa_tag_pointer(void *p, unsigned long tag) +{ + return (void *)((unsigned long)p | tag); +} + +/** + * xa_untag_pointer() - Turn an XArray entry into a plain pointer. + * @entry: XArray entry. + * + * If you have stored a tagged pointer in the XArray, call this function + * to get the untagged version of the pointer. + * + * Context: Any context. + * Return: A pointer. + */ +static inline void *xa_untag_pointer(void *entry) +{ + return (void *)((unsigned long)entry & ~3UL); +} + +/** + * xa_pointer_tag() - Get the tag stored in an XArray entry. + * @entry: XArray entry. + * + * If you have stored a tagged pointer in the XArray, call this function + * to get the tag of that pointer. + * + * Context: Any context. + * Return: A tag. + */ +static inline unsigned int xa_pointer_tag(void *entry) +{ + return (unsigned long)entry & 3UL; +} #define xa_trylock(xa) spin_trylock(&(xa)->xa_lock) #define xa_lock(xa) spin_lock(&(xa)->xa_lock) diff --git a/lib/idr.c b/lib/idr.c index 729e381e23b4..88419fbc5737 100644 --- a/lib/idr.c +++ b/lib/idr.c @@ -338,11 +338,8 @@ EXPORT_SYMBOL(idr_replace); * by the number of bits in the leaf bitmap before doing a radix tree lookup. * * As an optimisation, if there are only a few low bits set in any given - * leaf, instead of allocating a 128-byte bitmap, we use the 'exceptional - * entry' functionality of the radix tree to store BITS_PER_LONG - 2 bits - * directly in the entry. By being really tricksy, we could store - * BITS_PER_LONG - 1 bits, but there're diminishing returns after optimising - * for 0-3 allocated IDs. + * leaf, instead of allocating a 128-byte bitmap, we store the bits + * directly in the entry. * * We allow the radix tree 'exceptional' count to get out of date. Nothing * in the IDA nor the radix tree code checks it. If it becomes important @@ -366,12 +363,11 @@ static int ida_get_new_above(struct ida *ida, int start) struct radix_tree_iter iter; struct ida_bitmap *bitmap; unsigned long index; - unsigned bit, ebit; + unsigned bit; int new; index = start / IDA_BITMAP_BITS; bit = start % IDA_BITMAP_BITS; - ebit = bit + RADIX_TREE_EXCEPTIONAL_SHIFT; slot = radix_tree_iter_init(&iter, index); for (;;) { @@ -386,25 +382,23 @@ static int ida_get_new_above(struct ida *ida, int start) return PTR_ERR(slot); } } - if (iter.index > index) { + if (iter.index > index) bit = 0; - ebit = RADIX_TREE_EXCEPTIONAL_SHIFT; - } new = iter.index * IDA_BITMAP_BITS; bitmap = rcu_dereference_raw(*slot); - if (radix_tree_exception(bitmap)) { - unsigned long tmp = (unsigned long)bitmap; - ebit = find_next_zero_bit(&tmp, BITS_PER_LONG, ebit); - if (ebit < BITS_PER_LONG) { - tmp |= 1UL << ebit; - rcu_assign_pointer(*slot, (void *)tmp); - return new + ebit - - RADIX_TREE_EXCEPTIONAL_SHIFT; + if (xa_is_value(bitmap)) { + unsigned long tmp = xa_to_value(bitmap); + int vbit = find_next_zero_bit(&tmp, BITS_PER_XA_VALUE, + bit); + if (vbit < BITS_PER_XA_VALUE) { + tmp |= 1UL << vbit; + rcu_assign_pointer(*slot, xa_mk_value(tmp)); + return new + vbit; } bitmap = this_cpu_xchg(ida_bitmap, NULL); if (!bitmap) return -EAGAIN; - bitmap->bitmap[0] = tmp >> RADIX_TREE_EXCEPTIONAL_SHIFT; + bitmap->bitmap[0] = tmp; rcu_assign_pointer(*slot, bitmap); } @@ -425,17 +419,14 @@ static int ida_get_new_above(struct ida *ida, int start) new += bit; if (new < 0) return -ENOSPC; - if (ebit < BITS_PER_LONG) { - bitmap = (void *)((1UL << ebit) | - RADIX_TREE_EXCEPTIONAL_ENTRY); - radix_tree_iter_replace(root, &iter, slot, - bitmap); - return new; + if (bit < BITS_PER_XA_VALUE) { + bitmap = xa_mk_value(1UL << bit); + } else { + bitmap = this_cpu_xchg(ida_bitmap, NULL); + if (!bitmap) + return -EAGAIN; + __set_bit(bit, bitmap->bitmap); } - bitmap = this_cpu_xchg(ida_bitmap, NULL); - if (!bitmap) - return -EAGAIN; - __set_bit(bit, bitmap->bitmap); radix_tree_iter_replace(root, &iter, slot, bitmap); } @@ -457,9 +448,9 @@ static void ida_remove(struct ida *ida, int id) goto err; bitmap = rcu_dereference_raw(*slot); - if (radix_tree_exception(bitmap)) { + if (xa_is_value(bitmap)) { btmp = (unsigned long *)slot; - offset += RADIX_TREE_EXCEPTIONAL_SHIFT; + offset += 1; /* Intimate knowledge of the value encoding */ if (offset >= BITS_PER_LONG) goto err; } else { @@ -470,9 +461,8 @@ static void ida_remove(struct ida *ida, int id) __clear_bit(offset, btmp); radix_tree_iter_tag_set(&ida->ida_rt, &iter, IDR_FREE); - if (radix_tree_exception(bitmap)) { - if (rcu_dereference_raw(*slot) == - (void *)RADIX_TREE_EXCEPTIONAL_ENTRY) + if (xa_is_value(bitmap)) { + if (xa_to_value(rcu_dereference_raw(*slot)) == 0) radix_tree_iter_delete(&ida->ida_rt, &iter, slot); } else if (bitmap_empty(btmp, IDA_BITMAP_BITS)) { kfree(bitmap); @@ -503,7 +493,7 @@ void ida_destroy(struct ida *ida) xa_lock_irqsave(&ida->ida_rt, flags); radix_tree_for_each_slot(slot, &ida->ida_rt, &iter, 0) { struct ida_bitmap *bitmap = rcu_dereference_raw(*slot); - if (!radix_tree_exception(bitmap)) + if (!xa_is_value(bitmap)) kfree(bitmap); radix_tree_iter_delete(&ida->ida_rt, &iter, slot); } diff --git a/lib/radix-tree.c b/lib/radix-tree.c index a904a8ddd174..b6c0e7f3a894 100644 --- a/lib/radix-tree.c +++ b/lib/radix-tree.c @@ -340,14 +340,12 @@ static void dump_ida_node(void *entry, unsigned long index) for (i = 0; i < RADIX_TREE_MAP_SIZE; i++) dump_ida_node(node->slots[i], index | (i << node->shift)); - } else if (radix_tree_exceptional_entry(entry)) { + } else if (xa_is_value(entry)) { pr_debug("ida excp: %p offset %d indices %lu-%lu data %lx\n", entry, (int)(index & RADIX_TREE_MAP_MASK), index * IDA_BITMAP_BITS, - index * IDA_BITMAP_BITS + BITS_PER_LONG - - RADIX_TREE_EXCEPTIONAL_SHIFT, - (unsigned long)entry >> - RADIX_TREE_EXCEPTIONAL_SHIFT); + index * IDA_BITMAP_BITS + BITS_PER_XA_VALUE, + xa_to_value(entry)); } else { struct ida_bitmap *bitmap = entry; @@ -656,7 +654,7 @@ static int radix_tree_extend(struct radix_tree_root *root, gfp_t gfp, BUG_ON(shift > BITS_PER_LONG); if (radix_tree_is_internal_node(entry)) { entry_to_node(entry)->parent = node; - } else if (radix_tree_exceptional_entry(entry)) { + } else if (xa_is_value(entry)) { /* Moving an exceptional root->rnode to a node */ node->exceptional = 1; } @@ -955,12 +953,12 @@ static inline int insert_entries(struct radix_tree_node *node, !is_sibling_entry(node, old) && (old != RADIX_TREE_RETRY)) radix_tree_free_nodes(old); - if (radix_tree_exceptional_entry(old)) + if (xa_is_value(old)) node->exceptional--; } if (node) { node->count += n; - if (radix_tree_exceptional_entry(item)) + if (xa_is_value(item)) node->exceptional += n; } return n; @@ -974,7 +972,7 @@ static inline int insert_entries(struct radix_tree_node *node, rcu_assign_pointer(*slot, item); if (node) { node->count++; - if (radix_tree_exceptional_entry(item)) + if (xa_is_value(item)) node->exceptional++; } return 1; @@ -1190,8 +1188,7 @@ void __radix_tree_replace(struct radix_tree_root *root, radix_tree_update_node_t update_node) { void *old = rcu_dereference_raw(*slot); - int exceptional = !!radix_tree_exceptional_entry(item) - - !!radix_tree_exceptional_entry(old); + int exceptional = !!xa_is_value(item) - !!xa_is_value(old); int count = calculate_count(root, node, slot, item, old); /* @@ -1992,7 +1989,7 @@ static bool __radix_tree_delete(struct radix_tree_root *root, struct radix_tree_node *node, void __rcu **slot) { void *old = rcu_dereference_raw(*slot); - int exceptional = radix_tree_exceptional_entry(old) ? -1 : 0; + int exceptional = xa_is_value(old) ? -1 : 0; unsigned offset = get_slot_offset(node, slot); int tag; diff --git a/mm/filemap.c b/mm/filemap.c index 52517f28e6f4..4de14e75c4ec 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -127,7 +127,7 @@ static int page_cache_tree_insert(struct address_space *mapping, p = radix_tree_deref_slot_protected(slot, &mapping->i_pages.xa_lock); - if (!radix_tree_exceptional_entry(p)) + if (!xa_is_value(p)) return -EEXIST; mapping->nrexceptional--; @@ -336,7 +336,7 @@ page_cache_tree_delete_batch(struct address_space *mapping, break; page = radix_tree_deref_slot_protected(slot, &mapping->i_pages.xa_lock); - if (radix_tree_exceptional_entry(page)) + if (xa_is_value(page)) continue; if (!tail_pages) { /* @@ -1355,7 +1355,7 @@ pgoff_t page_cache_next_hole(struct address_space *mapping, struct page *page; page = radix_tree_lookup(&mapping->i_pages, index); - if (!page || radix_tree_exceptional_entry(page)) + if (!page || xa_is_value(page)) break; index++; if (index == 0) @@ -1396,7 +1396,7 @@ pgoff_t page_cache_prev_hole(struct address_space *mapping, struct page *page; page = radix_tree_lookup(&mapping->i_pages, index); - if (!page || radix_tree_exceptional_entry(page)) + if (!page || xa_is_value(page)) break; index--; if (index == ULONG_MAX) @@ -1539,7 +1539,7 @@ struct page *pagecache_get_page(struct address_space *mapping, pgoff_t offset, repeat: page = find_get_entry(mapping, offset); - if (radix_tree_exceptional_entry(page)) + if (xa_is_value(page)) page = NULL; if (!page) goto no_page; diff --git a/mm/khugepaged.c b/mm/khugepaged.c index a31d740e6cd1..4820e4adf853 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -1369,7 +1369,7 @@ static void collapse_shmem(struct mm_struct *mm, page = radix_tree_deref_slot_protected(slot, &mapping->i_pages.xa_lock); - if (radix_tree_exceptional_entry(page) || !PageUptodate(page)) { + if (xa_is_value(page) || !PageUptodate(page)) { xa_unlock_irq(&mapping->i_pages); /* swap in or instantiate fallocated page */ if (shmem_getpage(mapping->host, index, &page, diff --git a/mm/madvise.c b/mm/madvise.c index 972a9eaa898b..9d802566c494 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -251,7 +251,7 @@ static void force_shm_swapin_readahead(struct vm_area_struct *vma, index = ((start - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff; page = find_get_entry(mapping, index); - if (!radix_tree_exceptional_entry(page)) { + if (!xa_is_value(page)) { if (page) put_page(page); continue; diff --git a/mm/memcontrol.c b/mm/memcontrol.c index e79cb59552d9..29d9d1a69b36 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -4750,7 +4750,7 @@ static struct page *mc_handle_file_pte(struct vm_area_struct *vma, /* shmem/tmpfs may report page out on swap: account for that too. */ if (shmem_mapping(mapping)) { page = find_get_entry(mapping, pgoff); - if (radix_tree_exceptional_entry(page)) { + if (xa_is_value(page)) { swp_entry_t swp = radix_to_swp_entry(page); if (do_memsw_account()) *entry = swp; diff --git a/mm/mincore.c b/mm/mincore.c index fc37afe226e6..4985965aa20a 100644 --- a/mm/mincore.c +++ b/mm/mincore.c @@ -66,7 +66,7 @@ static unsigned char mincore_page(struct address_space *mapping, pgoff_t pgoff) * shmem/tmpfs may return swap: account for swapcache * page too. */ - if (radix_tree_exceptional_entry(page)) { + if (xa_is_value(page)) { swp_entry_t swp = radix_to_swp_entry(page); page = find_get_page(swap_address_space(swp), swp_offset(swp)); diff --git a/mm/readahead.c b/mm/readahead.c index 4e630143a0ba..de657077d41d 100644 --- a/mm/readahead.c +++ b/mm/readahead.c @@ -179,7 +179,7 @@ unsigned int __do_page_cache_readahead(struct address_space *mapping, rcu_read_lock(); page = radix_tree_lookup(&mapping->i_pages, page_offset); rcu_read_unlock(); - if (page && !radix_tree_exceptional_entry(page)) { + if (page && !xa_is_value(page)) { /* * Page already present? Kick off the current batch of * contiguous pages before continuing with the next diff --git a/mm/shmem.c b/mm/shmem.c index 446942677cd4..c1062760fe41 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -709,7 +709,7 @@ unsigned long shmem_partial_swap_usage(struct address_space *mapping, continue; } - if (radix_tree_exceptional_entry(page)) + if (xa_is_value(page)) swapped++; if (need_resched()) { @@ -824,7 +824,7 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend, if (index >= end) break; - if (radix_tree_exceptional_entry(page)) { + if (xa_is_value(page)) { if (unfalloc) continue; nr_swaps_freed += !shmem_free_swap(mapping, @@ -921,7 +921,7 @@ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend, if (index >= end) break; - if (radix_tree_exceptional_entry(page)) { + if (xa_is_value(page)) { if (unfalloc) continue; if (shmem_free_swap(mapping, index, page)) { @@ -1643,7 +1643,7 @@ static int shmem_getpage_gfp(struct inode *inode, pgoff_t index, repeat: swap.val = 0; page = find_lock_entry(mapping, index); - if (radix_tree_exceptional_entry(page)) { + if (xa_is_value(page)) { swap = radix_to_swp_entry(page); page = NULL; } @@ -2578,7 +2578,7 @@ static pgoff_t shmem_seek_hole_data(struct address_space *mapping, index = indices[i]; } page = pvec.pages[i]; - if (page && !radix_tree_exceptional_entry(page)) { + if (page && !xa_is_value(page)) { if (!PageUptodate(page)) page = NULL; } diff --git a/mm/swap.c b/mm/swap.c index 26fc9b5f1b6c..4c5c7fcc6e46 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -965,7 +965,7 @@ void pagevec_remove_exceptionals(struct pagevec *pvec) for (i = 0, j = 0; i < pagevec_count(pvec); i++) { struct page *page = pvec->pages[i]; - if (!radix_tree_exceptional_entry(page)) + if (!xa_is_value(page)) pvec->pages[j++] = page; } pvec->nr = j; diff --git a/mm/truncate.c b/mm/truncate.c index 1d2fb2dca96f..ed778555c9f3 100644 --- a/mm/truncate.c +++ b/mm/truncate.c @@ -70,7 +70,7 @@ static void truncate_exceptional_pvec_entries(struct address_space *mapping, return; for (j = 0; j < pagevec_count(pvec); j++) - if (radix_tree_exceptional_entry(pvec->pages[j])) + if (xa_is_value(pvec->pages[j])) break; if (j == pagevec_count(pvec)) @@ -85,7 +85,7 @@ static void truncate_exceptional_pvec_entries(struct address_space *mapping, struct page *page = pvec->pages[i]; pgoff_t index = indices[i]; - if (!radix_tree_exceptional_entry(page)) { + if (!xa_is_value(page)) { pvec->pages[j++] = page; continue; } @@ -347,7 +347,7 @@ void truncate_inode_pages_range(struct address_space *mapping, if (index >= end) break; - if (radix_tree_exceptional_entry(page)) + if (xa_is_value(page)) continue; if (!trylock_page(page)) @@ -442,7 +442,7 @@ void truncate_inode_pages_range(struct address_space *mapping, break; } - if (radix_tree_exceptional_entry(page)) + if (xa_is_value(page)) continue; lock_page(page); @@ -561,7 +561,7 @@ unsigned long invalidate_mapping_pages(struct address_space *mapping, if (index > end) break; - if (radix_tree_exceptional_entry(page)) { + if (xa_is_value(page)) { invalidate_exceptional_entry(mapping, index, page); continue; @@ -692,7 +692,7 @@ int invalidate_inode_pages2_range(struct address_space *mapping, if (index > end) break; - if (radix_tree_exceptional_entry(page)) { + if (xa_is_value(page)) { if (!invalidate_exceptional_entry2(mapping, index, page)) ret = -EBUSY; diff --git a/mm/workingset.c b/mm/workingset.c index 4516dd790129..bb109b3afac2 100644 --- a/mm/workingset.c +++ b/mm/workingset.c @@ -155,8 +155,8 @@ * refault distance will immediately activate the refaulting page. */ -#define EVICTION_SHIFT (RADIX_TREE_EXCEPTIONAL_ENTRY + \ - NODES_SHIFT + \ +#define EVICTION_SHIFT ((BITS_PER_LONG - BITS_PER_XA_VALUE) + \ + NODES_SHIFT + \ MEM_CGROUP_ID_SHIFT) #define EVICTION_MASK (~0UL >> EVICTION_SHIFT) @@ -173,20 +173,19 @@ static unsigned int bucket_order __read_mostly; static void *pack_shadow(int memcgid, pg_data_t *pgdat, unsigned long eviction) { eviction >>= bucket_order; + eviction &= EVICTION_MASK; eviction = (eviction << MEM_CGROUP_ID_SHIFT) | memcgid; eviction = (eviction << NODES_SHIFT) | pgdat->node_id; - eviction = (eviction << RADIX_TREE_EXCEPTIONAL_SHIFT); - return (void *)(eviction | RADIX_TREE_EXCEPTIONAL_ENTRY); + return xa_mk_value(eviction); } static void unpack_shadow(void *shadow, int *memcgidp, pg_data_t **pgdat, unsigned long *evictionp) { - unsigned long entry = (unsigned long)shadow; + unsigned long entry = xa_to_value(shadow); int memcgid, nid; - entry >>= RADIX_TREE_EXCEPTIONAL_SHIFT; nid = entry & ((1UL << NODES_SHIFT) - 1); entry >>= NODES_SHIFT; memcgid = entry & ((1UL << MEM_CGROUP_ID_SHIFT) - 1); @@ -453,7 +452,7 @@ static enum lru_status shadow_lru_isolate(struct list_head *item, goto out_invalid; for (i = 0; i < RADIX_TREE_MAP_SIZE; i++) { if (node->slots[i]) { - if (WARN_ON_ONCE(!radix_tree_exceptional_entry(node->slots[i]))) + if (WARN_ON_ONCE(!xa_is_value(node->slots[i]))) goto out_invalid; if (WARN_ON_ONCE(!node->exceptional)) goto out_invalid; diff --git a/tools/testing/radix-tree/idr-test.c b/tools/testing/radix-tree/idr-test.c index f620c831a4b5..a5a4494922a6 100644 --- a/tools/testing/radix-tree/idr-test.c +++ b/tools/testing/radix-tree/idr-test.c @@ -19,7 +19,7 @@ #include "test.h" -#define DUMMY_PTR ((void *)0x12) +#define DUMMY_PTR ((void *)0x10) int item_idr_free(int id, void *p, void *data) { @@ -411,11 +411,11 @@ void ida_check_conv_user(void) int id = ida_alloc(&ida, GFP_NOWAIT); if (id == -ENOMEM) { IDA_BUG_ON(&ida, (i % IDA_BITMAP_BITS) != - BITS_PER_LONG - 2); + BITS_PER_XA_VALUE); id = ida_alloc(&ida, GFP_KERNEL); } else { IDA_BUG_ON(&ida, (i % IDA_BITMAP_BITS) == - BITS_PER_LONG - 2); + BITS_PER_XA_VALUE); } IDA_BUG_ON(&ida, id != i); } diff --git a/tools/testing/radix-tree/linux/radix-tree.h b/tools/testing/radix-tree/linux/radix-tree.h index 24f13d27a8da..d1635a5bef02 100644 --- a/tools/testing/radix-tree/linux/radix-tree.h +++ b/tools/testing/radix-tree/linux/radix-tree.h @@ -2,7 +2,6 @@ #ifndef _TEST_RADIX_TREE_H #define _TEST_RADIX_TREE_H -#include "generated/map-shift.h" #include "../../../../include/linux/radix-tree.h" extern int kmalloc_verbose; diff --git a/tools/testing/radix-tree/multiorder.c b/tools/testing/radix-tree/multiorder.c index 7bf405638b0b..2b4f4dba1882 100644 --- a/tools/testing/radix-tree/multiorder.c +++ b/tools/testing/radix-tree/multiorder.c @@ -39,12 +39,11 @@ static void __multiorder_tag_test(int index, int order) /* * Verify we get collisions for covered indices. We try and fail to - * insert an exceptional entry so we don't leak memory via + * insert a value entry so we don't leak memory via * item_insert_order(). */ for_each_index(i, base, order) { - err = __radix_tree_insert(&tree, i, order, - (void *)(0xA0 | RADIX_TREE_EXCEPTIONAL_ENTRY)); + err = __radix_tree_insert(&tree, i, order, xa_mk_value(0xA0)); assert(err == -EEXIST); } @@ -380,8 +379,8 @@ static void multiorder_join1(unsigned long index, } /* - * Check that the accounting of exceptional entries is handled correctly - * by joining an exceptional entry to a normal pointer. + * Check that the accounting of value entries is handled correctly + * by joining a value entry to a normal pointer. */ static void multiorder_join2(unsigned order1, unsigned order2) { @@ -391,9 +390,9 @@ static void multiorder_join2(unsigned order1, unsigned order2) void *item2; item_insert_order(&tree, 0, order2); - radix_tree_insert(&tree, 1 << order2, (void *)0x12UL); + radix_tree_insert(&tree, 1 << order2, xa_mk_value(5)); item2 = __radix_tree_lookup(&tree, 1 << order2, &node, NULL); - assert(item2 == (void *)0x12UL); + assert(item2 == xa_mk_value(5)); assert(node->exceptional == 1); item2 = radix_tree_lookup(&tree, 0); @@ -407,7 +406,7 @@ static void multiorder_join2(unsigned order1, unsigned order2) } /* - * This test revealed an accounting bug for exceptional entries at one point. + * This test revealed an accounting bug for value entries at one point. * Nodes were being freed back into the pool with an elevated exception count * by radix_tree_join() and then radix_tree_split() was failing to zero the * count of exceptional entries. @@ -421,16 +420,16 @@ static void multiorder_join3(unsigned int order) unsigned long i; for (i = 0; i < (1 << order); i++) { - radix_tree_insert(&tree, i, (void *)0x12UL); + radix_tree_insert(&tree, i, xa_mk_value(5)); } - radix_tree_join(&tree, 0, order, (void *)0x16UL); + radix_tree_join(&tree, 0, order, xa_mk_value(7)); rcu_barrier(); radix_tree_split(&tree, 0, 0); radix_tree_for_each_slot(slot, &tree, &iter, 0) { - radix_tree_iter_replace(&tree, &iter, slot, (void *)0x12UL); + radix_tree_iter_replace(&tree, &iter, slot, xa_mk_value(5)); } __radix_tree_lookup(&tree, 0, &node, NULL); @@ -517,10 +516,10 @@ static void __multiorder_split2(int old_order, int new_order) struct radix_tree_node *node; void *item; - __radix_tree_insert(&tree, 0, old_order, (void *)0x12); + __radix_tree_insert(&tree, 0, old_order, xa_mk_value(5)); item = __radix_tree_lookup(&tree, 0, &node, NULL); - assert(item == (void *)0x12); + assert(item == xa_mk_value(5)); assert(node->exceptional > 0); radix_tree_split(&tree, 0, new_order); @@ -530,7 +529,7 @@ static void __multiorder_split2(int old_order, int new_order) } item = __radix_tree_lookup(&tree, 0, &node, NULL); - assert(item != (void *)0x12); + assert(item != xa_mk_value(5)); assert(node->exceptional == 0); item_kill_tree(&tree); @@ -544,40 +543,40 @@ static void __multiorder_split3(int old_order, int new_order) struct radix_tree_node *node; void *item; - __radix_tree_insert(&tree, 0, old_order, (void *)0x12); + __radix_tree_insert(&tree, 0, old_order, xa_mk_value(5)); item = __radix_tree_lookup(&tree, 0, &node, NULL); - assert(item == (void *)0x12); + assert(item == xa_mk_value(5)); assert(node->exceptional > 0); radix_tree_split(&tree, 0, new_order); radix_tree_for_each_slot(slot, &tree, &iter, 0) { - radix_tree_iter_replace(&tree, &iter, slot, (void *)0x16); + radix_tree_iter_replace(&tree, &iter, slot, xa_mk_value(7)); } item = __radix_tree_lookup(&tree, 0, &node, NULL); - assert(item == (void *)0x16); + assert(item == xa_mk_value(7)); assert(node->exceptional > 0); item_kill_tree(&tree); - __radix_tree_insert(&tree, 0, old_order, (void *)0x12); + __radix_tree_insert(&tree, 0, old_order, xa_mk_value(5)); item = __radix_tree_lookup(&tree, 0, &node, NULL); - assert(item == (void *)0x12); + assert(item == xa_mk_value(5)); assert(node->exceptional > 0); radix_tree_split(&tree, 0, new_order); radix_tree_for_each_slot(slot, &tree, &iter, 0) { if (iter.index == (1 << new_order)) radix_tree_iter_replace(&tree, &iter, slot, - (void *)0x16); + xa_mk_value(7)); else radix_tree_iter_replace(&tree, &iter, slot, NULL); } item = __radix_tree_lookup(&tree, 1 << new_order, &node, NULL); - assert(item == (void *)0x16); + assert(item == xa_mk_value(7)); assert(node->count == node->exceptional); do { node = node->parent; @@ -610,13 +609,13 @@ static void multiorder_account(void) item_insert_order(&tree, 0, 5); - __radix_tree_insert(&tree, 1 << 5, 5, (void *)0x12); + __radix_tree_insert(&tree, 1 << 5, 5, xa_mk_value(5)); __radix_tree_lookup(&tree, 0, &node, NULL); assert(node->count == node->exceptional * 2); radix_tree_delete(&tree, 1 << 5); assert(node->exceptional == 0); - __radix_tree_insert(&tree, 1 << 5, 5, (void *)0x12); + __radix_tree_insert(&tree, 1 << 5, 5, xa_mk_value(5)); __radix_tree_lookup(&tree, 1 << 5, &node, &slot); assert(node->count == node->exceptional * 2); __radix_tree_replace(&tree, node, slot, NULL, NULL); diff --git a/tools/testing/radix-tree/test.c b/tools/testing/radix-tree/test.c index def6015570b2..62de66c314b7 100644 --- a/tools/testing/radix-tree/test.c +++ b/tools/testing/radix-tree/test.c @@ -295,7 +295,7 @@ void item_kill_tree(struct radix_tree_root *root) int nfound; radix_tree_for_each_slot(slot, root, &iter, 0) { - if (radix_tree_exceptional_entry(*slot)) + if (xa_is_value(*slot)) radix_tree_delete(root, iter.index); } -- cgit v1.2.3 From 7534612123e0f5d020aba1076a6bb505db0e6bfe Mon Sep 17 00:00:00 2001 From: Srikar Dronamraju Date: Fri, 21 Sep 2018 23:19:00 +0530 Subject: mm/migrate: Use spin_trylock() while resetting rate limit Since this spinlock will only serialize the migrate rate limiting, convert the spin_lock() to a spin_trylock(). If another thread is updating, this task can move on. Specjbb2005 results (8 warehouses) Higher bops are better 2 Socket - 2 Node Haswell - X86 JVMS Prev Current %Change 4 205332 198512 -3.32145 1 319785 313559 -1.94693 2 Socket - 4 Node Power8 - PowerNV JVMS Prev Current %Change 8 74912 74761.9 -0.200368 1 206585 214874 4.01239 2 Socket - 2 Node Power9 - PowerNV JVMS Prev Current %Change 4 189162 180536 -4.56011 1 213760 210281 -1.62753 4 Socket - 4 Node Power7 - PowerVM JVMS Prev Current %Change 8 58736.8 56511.4 -3.78877 1 105419 104899 -0.49327 Avoiding stretching of window intervals may be the reason for the regression. Also code now uses READ_ONCE/WRITE_ONCE. That may also be hurting performance to some extent. Some events stats before and after applying the patch. perf stats 8th warehouse Multi JVM 2 Socket - 2 Node Haswell - X86 Event Before After cs 14,285,708 13,818,546 migrations 1,180,621 1,149,960 faults 339,114 385,583 cache-misses 55,205,631,894 55,259,546,768 sched:sched_move_numa 843 2,257 sched:sched_stick_numa 6 9 sched:sched_swap_numa 219 512 migrate:mm_migrate_pages 365 2,225 vmstat 8th warehouse Multi JVM 2 Socket - 2 Node Haswell - X86 Event Before After numa_hint_faults 26907 72692 numa_hint_faults_local 24279 62270 numa_hit 239771 238762 numa_huge_pte_updates 0 48 numa_interleave 68 75 numa_local 239688 238676 numa_other 83 86 numa_pages_migrated 363 2225 numa_pte_updates 27415 98557 perf stats 8th warehouse Single JVM 2 Socket - 2 Node Haswell - X86 Event Before After cs 3,202,779 3,173,490 migrations 37,186 36,966 faults 106,076 108,776 cache-misses 12,024,873,744 12,200,075,320 sched:sched_move_numa 931 1,264 sched:sched_stick_numa 0 0 sched:sched_swap_numa 1 0 migrate:mm_migrate_pages 637 899 vmstat 8th warehouse Single JVM 2 Socket - 2 Node Haswell - X86 Event Before After numa_hint_faults 17409 21109 numa_hint_faults_local 14367 17120 numa_hit 73953 72934 numa_huge_pte_updates 20 42 numa_interleave 25 33 numa_local 73892 72866 numa_other 61 68 numa_pages_migrated 668 915 numa_pte_updates 27276 42326 perf stats 8th warehouse Multi JVM 2 Socket - 2 Node Power9 - PowerNV Event Before After cs 8,474,013 8,312,022 migrations 254,934 231,705 faults 320,506 310,242 cache-misses 110,580,458 402,324,573 sched:sched_move_numa 725 193 sched:sched_stick_numa 0 0 sched:sched_swap_numa 7 3 migrate:mm_migrate_pages 145 93 vmstat 8th warehouse Multi JVM 2 Socket - 2 Node Power9 - PowerNV Event Before After numa_hint_faults 22797 11838 numa_hint_faults_local 21539 11216 numa_hit 89308 90689 numa_huge_pte_updates 0 0 numa_interleave 865 1579 numa_local 88955 89634 numa_other 353 1055 numa_pages_migrated 149 92 numa_pte_updates 22930 12109 perf stats 8th warehouse Single JVM 2 Socket - 2 Node Power9 - PowerNV Event Before After cs 2,195,628 2,170,481 migrations 11,179 10,126 faults 149,656 160,962 cache-misses 8,117,515 10,834,845 sched:sched_move_numa 49 10 sched:sched_stick_numa 0 0 sched:sched_swap_numa 0 0 migrate:mm_migrate_pages 5 2 vmstat 8th warehouse Single JVM 2 Socket - 2 Node Power9 - PowerNV Event Before After numa_hint_faults 3577 403 numa_hint_faults_local 3476 358 numa_hit 26142 25898 numa_huge_pte_updates 0 0 numa_interleave 358 207 numa_local 26042 25860 numa_other 100 38 numa_pages_migrated 5 2 numa_pte_updates 3587 400 perf stats 8th warehouse Multi JVM 4 Socket - 4 Node Power7 - PowerVM Event Before After cs 100,602,296 110,339,633 migrations 4,135,630 4,139,812 faults 789,256 863,622 cache-misses 226,160,621,058 231,838,045,660 sched:sched_move_numa 1,366 2,196 sched:sched_stick_numa 16 33 sched:sched_swap_numa 374 544 migrate:mm_migrate_pages 1,350 2,469 vmstat 8th warehouse Multi JVM 4 Socket - 4 Node Power7 - PowerVM Event Before After numa_hint_faults 47857 85748 numa_hint_faults_local 39768 66831 numa_hit 240165 242213 numa_huge_pte_updates 0 0 numa_interleave 0 0 numa_local 240165 242211 numa_other 0 2 numa_pages_migrated 1224 2376 numa_pte_updates 48354 86233 perf stats 8th warehouse Single JVM 4 Socket - 4 Node Power7 - PowerVM Event Before After cs 58,515,496 59,331,057 migrations 564,845 552,019 faults 245,807 266,586 cache-misses 73,603,757,976 73,796,312,990 sched:sched_move_numa 996 981 sched:sched_stick_numa 10 54 sched:sched_swap_numa 193 286 migrate:mm_migrate_pages 646 713 vmstat 8th warehouse Single JVM 4 Socket - 4 Node Power7 - PowerVM Event Before After numa_hint_faults 13422 14807 numa_hint_faults_local 5619 5738 numa_hit 36118 36230 numa_huge_pte_updates 0 0 numa_interleave 0 0 numa_local 36116 36228 numa_other 2 2 numa_pages_migrated 616 703 numa_pte_updates 13374 14742 Suggested-by: Peter Zijlstra Signed-off-by: Srikar Dronamraju Signed-off-by: Peter Zijlstra (Intel) Cc: Jirka Hladky Cc: Linus Torvalds Cc: Mel Gorman Cc: Mike Galbraith Cc: Rik van Riel Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/1537552141-27815-6-git-send-email-srikar@linux.vnet.ibm.com Signed-off-by: Ingo Molnar --- mm/migrate.c | 16 ++++++++++++---- 1 file changed, 12 insertions(+), 4 deletions(-) (limited to 'mm') diff --git a/mm/migrate.c b/mm/migrate.c index d6a2e89b086a..4f1d894835b5 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -1867,16 +1867,24 @@ static unsigned int ratelimit_pages __read_mostly = 128 << (20 - PAGE_SHIFT); static bool numamigrate_update_ratelimit(pg_data_t *pgdat, unsigned long nr_pages) { + unsigned long next_window, interval; + + next_window = READ_ONCE(pgdat->numabalancing_migrate_next_window); + interval = msecs_to_jiffies(migrate_interval_millisecs); + /* * Rate-limit the amount of data that is being migrated to a node. * Optimal placement is no good if the memory bus is saturated and * all the time is being spent migrating! */ - if (time_after(jiffies, pgdat->numabalancing_migrate_next_window)) { - spin_lock(&pgdat->numabalancing_migrate_lock); + if (time_after(jiffies, next_window) && + spin_trylock(&pgdat->numabalancing_migrate_lock)) { pgdat->numabalancing_migrate_nr_pages = 0; - pgdat->numabalancing_migrate_next_window = jiffies + - msecs_to_jiffies(migrate_interval_millisecs); + do { + next_window += interval; + } while (unlikely(time_after(jiffies, next_window))); + + WRITE_ONCE(pgdat->numabalancing_migrate_next_window, next_window); spin_unlock(&pgdat->numabalancing_migrate_lock); } if (pgdat->numabalancing_migrate_nr_pages > ratelimit_pages) { -- cgit v1.2.3 From efaffc5e40aeced0bcb497ed7a0a5b8c14abfcdf Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Mon, 1 Oct 2018 11:05:24 +0100 Subject: mm, sched/numa: Remove rate-limiting of automatic NUMA balancing migration Rate limiting of page migrations due to automatic NUMA balancing was introduced to mitigate the worst-case scenario of migrating at high frequency due to false sharing or slowly ping-ponging between nodes. Since then, a lot of effort was spent on correctly identifying these pages and avoiding unnecessary migrations and the safety net may no longer be required. Jirka Hladky reported a regression in 4.17 due to a scheduler patch that avoids spreading STREAM tasks wide prematurely. However, once the task was properly placed, it delayed migrating the memory due to rate limiting. Increasing the limit fixed the problem for him. Currently, the limit is hard-coded and does not account for the real capabilities of the hardware. Even if an estimate was attempted, it would not properly account for the number of memory controllers and it could not account for the amount of bandwidth used for normal accesses. Rather than fudging, this patch simply eliminates the rate limiting. However, Jirka reports that a STREAM configuration using multiple processes achieved similar performance to 4.16. In local tests, this patch improved performance of STREAM relative to the baseline but it is somewhat machine-dependent. Most workloads show little or not performance difference implying that there is not a heavily reliance on the throttling mechanism and it is safe to remove. STREAM on 2-socket machine 4.19.0-rc5 4.19.0-rc5 numab-v1r1 noratelimit-v1r1 MB/sec copy 43298.52 ( 0.00%) 44673.38 ( 3.18%) MB/sec scale 30115.06 ( 0.00%) 31293.06 ( 3.91%) MB/sec add 32825.12 ( 0.00%) 34883.62 ( 6.27%) MB/sec triad 32549.52 ( 0.00%) 34906.60 ( 7.24% Signed-off-by: Mel Gorman Reviewed-by: Rik van Riel Acked-by: Peter Zijlstra Cc: Jirka Hladky Cc: Linus Torvalds Cc: Linux-MM Cc: Srikar Dronamraju Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/20181001100525.29789-2-mgorman@techsingularity.net Signed-off-by: Ingo Molnar --- include/linux/mmzone.h | 6 ---- include/trace/events/migrate.h | 27 ------------------ mm/migrate.c | 65 ------------------------------------------ mm/page_alloc.c | 2 -- 4 files changed, 100 deletions(-) (limited to 'mm') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 1e22d96734e0..3f4c0b167333 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -671,12 +671,6 @@ typedef struct pglist_data { #ifdef CONFIG_NUMA_BALANCING /* Lock serializing the migrate rate limiting window */ spinlock_t numabalancing_migrate_lock; - - /* Rate limiting time interval */ - unsigned long numabalancing_migrate_next_window; - - /* Number of pages migrated during the rate limiting time interval */ - unsigned long numabalancing_migrate_nr_pages; #endif /* * This is a per-node reserve of pages that are not available diff --git a/include/trace/events/migrate.h b/include/trace/events/migrate.h index 711372845945..705b33d1e395 100644 --- a/include/trace/events/migrate.h +++ b/include/trace/events/migrate.h @@ -70,33 +70,6 @@ TRACE_EVENT(mm_migrate_pages, __print_symbolic(__entry->mode, MIGRATE_MODE), __print_symbolic(__entry->reason, MIGRATE_REASON)) ); - -TRACE_EVENT(mm_numa_migrate_ratelimit, - - TP_PROTO(struct task_struct *p, int dst_nid, unsigned long nr_pages), - - TP_ARGS(p, dst_nid, nr_pages), - - TP_STRUCT__entry( - __array( char, comm, TASK_COMM_LEN) - __field( pid_t, pid) - __field( int, dst_nid) - __field( unsigned long, nr_pages) - ), - - TP_fast_assign( - memcpy(__entry->comm, p->comm, TASK_COMM_LEN); - __entry->pid = p->pid; - __entry->dst_nid = dst_nid; - __entry->nr_pages = nr_pages; - ), - - TP_printk("comm=%s pid=%d dst_nid=%d nr_pages=%lu", - __entry->comm, - __entry->pid, - __entry->dst_nid, - __entry->nr_pages) -); #endif /* _TRACE_MIGRATE_H */ /* This part must be outside protection */ diff --git a/mm/migrate.c b/mm/migrate.c index 4f1d894835b5..5e285c1249a0 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -1855,54 +1855,6 @@ static struct page *alloc_misplaced_dst_page(struct page *page, return newpage; } -/* - * page migration rate limiting control. - * Do not migrate more than @pages_to_migrate in a @migrate_interval_millisecs - * window of time. Default here says do not migrate more than 1280M per second. - */ -static unsigned int migrate_interval_millisecs __read_mostly = 100; -static unsigned int ratelimit_pages __read_mostly = 128 << (20 - PAGE_SHIFT); - -/* Returns true if the node is migrate rate-limited after the update */ -static bool numamigrate_update_ratelimit(pg_data_t *pgdat, - unsigned long nr_pages) -{ - unsigned long next_window, interval; - - next_window = READ_ONCE(pgdat->numabalancing_migrate_next_window); - interval = msecs_to_jiffies(migrate_interval_millisecs); - - /* - * Rate-limit the amount of data that is being migrated to a node. - * Optimal placement is no good if the memory bus is saturated and - * all the time is being spent migrating! - */ - if (time_after(jiffies, next_window) && - spin_trylock(&pgdat->numabalancing_migrate_lock)) { - pgdat->numabalancing_migrate_nr_pages = 0; - do { - next_window += interval; - } while (unlikely(time_after(jiffies, next_window))); - - WRITE_ONCE(pgdat->numabalancing_migrate_next_window, next_window); - spin_unlock(&pgdat->numabalancing_migrate_lock); - } - if (pgdat->numabalancing_migrate_nr_pages > ratelimit_pages) { - trace_mm_numa_migrate_ratelimit(current, pgdat->node_id, - nr_pages); - return true; - } - - /* - * This is an unlocked non-atomic update so errors are possible. - * The consequences are failing to migrate when we potentiall should - * have which is not severe enough to warrant locking. If it is ever - * a problem, it can be converted to a per-cpu counter. - */ - pgdat->numabalancing_migrate_nr_pages += nr_pages; - return false; -} - static int numamigrate_isolate_page(pg_data_t *pgdat, struct page *page) { int page_lru; @@ -1975,14 +1927,6 @@ int migrate_misplaced_page(struct page *page, struct vm_area_struct *vma, if (page_is_file_cache(page) && PageDirty(page)) goto out; - /* - * Rate-limit the amount of data that is being migrated to a node. - * Optimal placement is no good if the memory bus is saturated and - * all the time is being spent migrating! - */ - if (numamigrate_update_ratelimit(pgdat, 1)) - goto out; - isolated = numamigrate_isolate_page(pgdat, page); if (!isolated) goto out; @@ -2029,14 +1973,6 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm, unsigned long mmun_start = address & HPAGE_PMD_MASK; unsigned long mmun_end = mmun_start + HPAGE_PMD_SIZE; - /* - * Rate-limit the amount of data that is being migrated to a node. - * Optimal placement is no good if the memory bus is saturated and - * all the time is being spent migrating! - */ - if (numamigrate_update_ratelimit(pgdat, HPAGE_PMD_NR)) - goto out_dropref; - new_page = alloc_pages_node(node, (GFP_TRANSHUGE_LIGHT | __GFP_THISNODE), HPAGE_PMD_ORDER); @@ -2133,7 +2069,6 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm, out_fail: count_vm_events(PGMIGRATE_FAIL, HPAGE_PMD_NR); -out_dropref: ptl = pmd_lock(mm, pmd); if (pmd_same(*pmd, entry)) { entry = pmd_modify(entry, vma->vm_page_prot); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 89d2a2ab3fe6..706a738c0aee 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -6197,8 +6197,6 @@ static unsigned long __init calc_memmap_size(unsigned long spanned_pages, static void pgdat_init_numabalancing(struct pglist_data *pgdat) { spin_lock_init(&pgdat->numabalancing_migrate_lock); - pgdat->numabalancing_migrate_nr_pages = 0; - pgdat->numabalancing_migrate_next_window = jiffies; } #else static void pgdat_init_numabalancing(struct pglist_data *pgdat) {} -- cgit v1.2.3 From 017b1660df89f5fb4bfe66c34e35f7d2031100c7 Mon Sep 17 00:00:00 2001 From: Mike Kravetz Date: Fri, 5 Oct 2018 15:51:29 -0700 Subject: mm: migration: fix migration of huge PMD shared pages The page migration code employs try_to_unmap() to try and unmap the source page. This is accomplished by using rmap_walk to find all vmas where the page is mapped. This search stops when page mapcount is zero. For shared PMD huge pages, the page map count is always 1 no matter the number of mappings. Shared mappings are tracked via the reference count of the PMD page. Therefore, try_to_unmap stops prematurely and does not completely unmap all mappings of the source page. This problem can result is data corruption as writes to the original source page can happen after contents of the page are copied to the target page. Hence, data is lost. This problem was originally seen as DB corruption of shared global areas after a huge page was soft offlined due to ECC memory errors. DB developers noticed they could reproduce the issue by (hotplug) offlining memory used to back huge pages. A simple testcase can reproduce the problem by creating a shared PMD mapping (note that this must be at least PUD_SIZE in size and PUD_SIZE aligned (1GB on x86)), and using migrate_pages() to migrate process pages between nodes while continually writing to the huge pages being migrated. To fix, have the try_to_unmap_one routine check for huge PMD sharing by calling huge_pmd_unshare for hugetlbfs huge pages. If it is a shared mapping it will be 'unshared' which removes the page table entry and drops the reference on the PMD page. After this, flush caches and TLB. mmu notifiers are called before locking page tables, but we can not be sure of PMD sharing until page tables are locked. Therefore, check for the possibility of PMD sharing before locking so that notifiers can prepare for the worst possible case. Link: http://lkml.kernel.org/r/20180823205917.16297-2-mike.kravetz@oracle.com [mike.kravetz@oracle.com: make _range_in_vma() a static inline] Link: http://lkml.kernel.org/r/6063f215-a5c8-2f0c-465a-2c515ddc952d@oracle.com Fixes: 39dde65c9940 ("shared page table for hugetlb page") Signed-off-by: Mike Kravetz Acked-by: Kirill A. Shutemov Reviewed-by: Naoya Horiguchi Acked-by: Michal Hocko Cc: Vlastimil Babka Cc: Davidlohr Bueso Cc: Jerome Glisse Cc: Mike Kravetz Cc: Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- include/linux/hugetlb.h | 14 ++++++++++++++ include/linux/mm.h | 6 ++++++ mm/hugetlb.c | 37 +++++++++++++++++++++++++++++++++++-- mm/rmap.c | 42 +++++++++++++++++++++++++++++++++++++++--- 4 files changed, 94 insertions(+), 5 deletions(-) (limited to 'mm') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 6b68e345f0ca..087fd5f48c91 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -140,6 +140,8 @@ pte_t *huge_pte_alloc(struct mm_struct *mm, pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr, unsigned long sz); int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep); +void adjust_range_if_pmd_sharing_possible(struct vm_area_struct *vma, + unsigned long *start, unsigned long *end); struct page *follow_huge_addr(struct mm_struct *mm, unsigned long address, int write); struct page *follow_huge_pd(struct vm_area_struct *vma, @@ -170,6 +172,18 @@ static inline unsigned long hugetlb_total_pages(void) return 0; } +static inline int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, + pte_t *ptep) +{ + return 0; +} + +static inline void adjust_range_if_pmd_sharing_possible( + struct vm_area_struct *vma, + unsigned long *start, unsigned long *end) +{ +} + #define follow_hugetlb_page(m,v,p,vs,a,b,i,w,n) ({ BUG(); 0; }) #define follow_huge_addr(mm, addr, write) ERR_PTR(-EINVAL) #define copy_hugetlb_page_range(src, dst, vma) ({ BUG(); 0; }) diff --git a/include/linux/mm.h b/include/linux/mm.h index a61ebe8ad4ca..0416a7204be3 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2455,6 +2455,12 @@ static inline struct vm_area_struct *find_exact_vma(struct mm_struct *mm, return vma; } +static inline bool range_in_vma(struct vm_area_struct *vma, + unsigned long start, unsigned long end) +{ + return (vma && vma->vm_start <= start && end <= vma->vm_end); +} + #ifdef CONFIG_MMU pgprot_t vm_get_page_prot(unsigned long vm_flags); void vma_set_page_prot(struct vm_area_struct *vma); diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 3c21775f196b..b903d746e132 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -4545,12 +4545,40 @@ static bool vma_shareable(struct vm_area_struct *vma, unsigned long addr) /* * check on proper vm_flags and page table alignment */ - if (vma->vm_flags & VM_MAYSHARE && - vma->vm_start <= base && end <= vma->vm_end) + if (vma->vm_flags & VM_MAYSHARE && range_in_vma(vma, base, end)) return true; return false; } +/* + * Determine if start,end range within vma could be mapped by shared pmd. + * If yes, adjust start and end to cover range associated with possible + * shared pmd mappings. + */ +void adjust_range_if_pmd_sharing_possible(struct vm_area_struct *vma, + unsigned long *start, unsigned long *end) +{ + unsigned long check_addr = *start; + + if (!(vma->vm_flags & VM_MAYSHARE)) + return; + + for (check_addr = *start; check_addr < *end; check_addr += PUD_SIZE) { + unsigned long a_start = check_addr & PUD_MASK; + unsigned long a_end = a_start + PUD_SIZE; + + /* + * If sharing is possible, adjust start/end if necessary. + */ + if (range_in_vma(vma, a_start, a_end)) { + if (a_start < *start) + *start = a_start; + if (a_end > *end) + *end = a_end; + } + } +} + /* * Search for a shareable pmd page for hugetlb. In any case calls pmd_alloc() * and returns the corresponding pte. While this is not necessary for the @@ -4648,6 +4676,11 @@ int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep) { return 0; } + +void adjust_range_if_pmd_sharing_possible(struct vm_area_struct *vma, + unsigned long *start, unsigned long *end) +{ +} #define want_pmd_share() (0) #endif /* CONFIG_ARCH_WANT_HUGE_PMD_SHARE */ diff --git a/mm/rmap.c b/mm/rmap.c index eb477809a5c0..1e79fac3186b 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -1362,11 +1362,21 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma, } /* - * We have to assume the worse case ie pmd for invalidation. Note that - * the page can not be free in this function as call of try_to_unmap() - * must hold a reference on the page. + * For THP, we have to assume the worse case ie pmd for invalidation. + * For hugetlb, it could be much worse if we need to do pud + * invalidation in the case of pmd sharing. + * + * Note that the page can not be free in this function as call of + * try_to_unmap() must hold a reference on the page. */ end = min(vma->vm_end, start + (PAGE_SIZE << compound_order(page))); + if (PageHuge(page)) { + /* + * If sharing is possible, start and end will be adjusted + * accordingly. + */ + adjust_range_if_pmd_sharing_possible(vma, &start, &end); + } mmu_notifier_invalidate_range_start(vma->vm_mm, start, end); while (page_vma_mapped_walk(&pvmw)) { @@ -1409,6 +1419,32 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma, subpage = page - page_to_pfn(page) + pte_pfn(*pvmw.pte); address = pvmw.address; + if (PageHuge(page)) { + if (huge_pmd_unshare(mm, &address, pvmw.pte)) { + /* + * huge_pmd_unshare unmapped an entire PMD + * page. There is no way of knowing exactly + * which PMDs may be cached for this mm, so + * we must flush them all. start/end were + * already adjusted above to cover this range. + */ + flush_cache_range(vma, start, end); + flush_tlb_range(vma, start, end); + mmu_notifier_invalidate_range(mm, start, end); + + /* + * The ref count of the PMD page was dropped + * which is part of the way map counting + * is done for shared PMDs. Return 'true' + * here. When there is no other sharing, + * huge_pmd_unshare returns false and we will + * unmap the actual page and drop map count + * to zero. + */ + page_vma_mapped_walk_done(&pvmw); + break; + } + } if (IS_ENABLED(CONFIG_MIGRATION) && (flags & TTU_MIGRATION) && -- cgit v1.2.3 From dff11abe280b47c21b804a8ace318e0638bb9a49 Mon Sep 17 00:00:00 2001 From: Mike Kravetz Date: Fri, 5 Oct 2018 15:51:33 -0700 Subject: hugetlb: take PMD sharing into account when flushing tlb/caches When fixing an issue with PMD sharing and migration, it was discovered via code inspection that other callers of huge_pmd_unshare potentially have an issue with cache and tlb flushing. Use the routine adjust_range_if_pmd_sharing_possible() to calculate worst case ranges for mmu notifiers. Ensure that this range is flushed if huge_pmd_unshare succeeds and unmaps a PUD_SUZE area. Link: http://lkml.kernel.org/r/20180823205917.16297-3-mike.kravetz@oracle.com Signed-off-by: Mike Kravetz Acked-by: Kirill A. Shutemov Reviewed-by: Naoya Horiguchi Cc: Vlastimil Babka Cc: Davidlohr Bueso Cc: Michal Hocko Cc: Jerome Glisse Cc: Mike Kravetz Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- mm/hugetlb.c | 53 ++++++++++++++++++++++++++++++++++++++++++++--------- 1 file changed, 44 insertions(+), 9 deletions(-) (limited to 'mm') diff --git a/mm/hugetlb.c b/mm/hugetlb.c index b903d746e132..5c390f5a5207 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -3326,8 +3326,8 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, struct page *page; struct hstate *h = hstate_vma(vma); unsigned long sz = huge_page_size(h); - const unsigned long mmun_start = start; /* For mmu_notifiers */ - const unsigned long mmun_end = end; /* For mmu_notifiers */ + unsigned long mmun_start = start; /* For mmu_notifiers */ + unsigned long mmun_end = end; /* For mmu_notifiers */ WARN_ON(!is_vm_hugetlb_page(vma)); BUG_ON(start & ~huge_page_mask(h)); @@ -3339,6 +3339,11 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, */ tlb_remove_check_page_size_change(tlb, sz); tlb_start_vma(tlb, vma); + + /* + * If sharing possible, alert mmu notifiers of worst case. + */ + adjust_range_if_pmd_sharing_possible(vma, &mmun_start, &mmun_end); mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end); address = start; for (; address < end; address += sz) { @@ -3349,6 +3354,10 @@ void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, ptl = huge_pte_lock(h, mm, ptep); if (huge_pmd_unshare(mm, &address, ptep)) { spin_unlock(ptl); + /* + * We just unmapped a page of PMDs by clearing a PUD. + * The caller's TLB flush range should cover this area. + */ continue; } @@ -3431,12 +3440,23 @@ void unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start, { struct mm_struct *mm; struct mmu_gather tlb; + unsigned long tlb_start = start; + unsigned long tlb_end = end; + + /* + * If shared PMDs were possibly used within this vma range, adjust + * start/end for worst case tlb flushing. + * Note that we can not be sure if PMDs are shared until we try to + * unmap pages. However, we want to make sure TLB flushing covers + * the largest possible range. + */ + adjust_range_if_pmd_sharing_possible(vma, &tlb_start, &tlb_end); mm = vma->vm_mm; - tlb_gather_mmu(&tlb, mm, start, end); + tlb_gather_mmu(&tlb, mm, tlb_start, tlb_end); __unmap_hugepage_range(&tlb, vma, start, end, ref_page); - tlb_finish_mmu(&tlb, start, end); + tlb_finish_mmu(&tlb, tlb_start, tlb_end); } /* @@ -4298,11 +4318,21 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma, pte_t pte; struct hstate *h = hstate_vma(vma); unsigned long pages = 0; + unsigned long f_start = start; + unsigned long f_end = end; + bool shared_pmd = false; + + /* + * In the case of shared PMDs, the area to flush could be beyond + * start/end. Set f_start/f_end to cover the maximum possible + * range if PMD sharing is possible. + */ + adjust_range_if_pmd_sharing_possible(vma, &f_start, &f_end); BUG_ON(address >= end); - flush_cache_range(vma, address, end); + flush_cache_range(vma, f_start, f_end); - mmu_notifier_invalidate_range_start(mm, start, end); + mmu_notifier_invalidate_range_start(mm, f_start, f_end); i_mmap_lock_write(vma->vm_file->f_mapping); for (; address < end; address += huge_page_size(h)) { spinlock_t *ptl; @@ -4313,6 +4343,7 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma, if (huge_pmd_unshare(mm, &address, ptep)) { pages++; spin_unlock(ptl); + shared_pmd = true; continue; } pte = huge_ptep_get(ptep); @@ -4348,9 +4379,13 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma, * Must flush TLB before releasing i_mmap_rwsem: x86's huge_pmd_unshare * may have cleared our pud entry and done put_page on the page table: * once we release i_mmap_rwsem, another task can do the final put_page - * and that page table be reused and filled with junk. + * and that page table be reused and filled with junk. If we actually + * did unshare a page of pmds, flush the range corresponding to the pud. */ - flush_hugetlb_tlb_range(vma, start, end); + if (shared_pmd) + flush_hugetlb_tlb_range(vma, f_start, f_end); + else + flush_hugetlb_tlb_range(vma, start, end); /* * No need to call mmu_notifier_invalidate_range() we are downgrading * page table protection not changing it to point to a new page. @@ -4358,7 +4393,7 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma, * See Documentation/vm/mmu_notifier.rst */ i_mmap_unlock_write(vma->vm_file->f_mapping); - mmu_notifier_invalidate_range_end(mm, start, end); + mmu_notifier_invalidate_range_end(mm, f_start, f_end); return pages << h->order; } -- cgit v1.2.3 From e125fe405abedc1dc8a5b2229b80ee91c1434015 Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Fri, 5 Oct 2018 15:51:41 -0700 Subject: mm, thp: fix mlocking THP page with migration enabled A transparent huge page is represented by a single entry on an LRU list. Therefore, we can only make unevictable an entire compound page, not individual subpages. If a user tries to mlock() part of a huge page, we want the rest of the page to be reclaimable. We handle this by keeping PTE-mapped huge pages on normal LRU lists: the PMD on border of VM_LOCKED VMA will be split into PTE table. Introduction of THP migration breaks[1] the rules around mlocking THP pages. If we had a single PMD mapping of the page in mlocked VMA, the page will get mlocked, regardless of PTE mappings of the page. For tmpfs/shmem it's easy to fix by checking PageDoubleMap() in remove_migration_pmd(). Anon THP pages can only be shared between processes via fork(). Mlocked page can only be shared if parent mlocked it before forking, otherwise CoW will be triggered on mlock(). For Anon-THP, we can fix the issue by munlocking the page on removing PTE migration entry for the page. PTEs for the page will always come after mlocked PMD: rmap walks VMAs from oldest to newest. Test-case: #include #include #include #include #include int main(void) { unsigned long nodemask = 4; void *addr; addr = mmap((void *)0x20000000UL, 2UL << 20, PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_ANONYMOUS | MAP_LOCKED, -1, 0); if (fork()) { wait(NULL); return 0; } mlock(addr, 4UL << 10); mbind(addr, 2UL << 20, MPOL_PREFERRED | MPOL_F_RELATIVE_NODES, &nodemask, 4, MPOL_MF_MOVE); return 0; } [1] https://lkml.kernel.org/r/CAOMGZ=G52R-30rZvhGxEbkTw7rLLwBGadVYeo--iizcD3upL3A@mail.gmail.com Link: http://lkml.kernel.org/r/20180917133816.43995-1-kirill.shutemov@linux.intel.com Fixes: 616b8371539a ("mm: thp: enable thp migration in generic path") Signed-off-by: Kirill A. Shutemov Reported-by: Vegard Nossum Reviewed-by: Zi Yan Cc: Naoya Horiguchi Cc: Vlastimil Babka Cc: Andrea Arcangeli Cc: [4.14+] Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- mm/huge_memory.c | 2 +- mm/migrate.c | 3 +++ 2 files changed, 4 insertions(+), 1 deletion(-) (limited to 'mm') diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 533f9b00147d..00704060b7f7 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2931,7 +2931,7 @@ void remove_migration_pmd(struct page_vma_mapped_walk *pvmw, struct page *new) else page_add_file_rmap(new, true); set_pmd_at(mm, mmun_start, pvmw->pmd, pmde); - if (vma->vm_flags & VM_LOCKED) + if ((vma->vm_flags & VM_LOCKED) && !PageDoubleMap(new)) mlock_vma_page(new); update_mmu_cache_pmd(vma, address, pvmw->pmd); } diff --git a/mm/migrate.c b/mm/migrate.c index d6a2e89b086a..9d374011c244 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -275,6 +275,9 @@ static bool remove_migration_pte(struct page *page, struct vm_area_struct *vma, if (vma->vm_flags & VM_LOCKED && !PageTransCompound(new)) mlock_vma_page(new); + if (PageTransHuge(page) && PageMlocked(page)) + clear_page_mlock(page); + /* No need to invalidate - it was non-present before */ update_mmu_cache(vma, pvmw.address, pvmw.pte); } -- cgit v1.2.3 From 51896864579d5a3349740847083f4db5c6487164 Mon Sep 17 00:00:00 2001 From: YueHaibing Date: Fri, 5 Oct 2018 15:51:44 -0700 Subject: mm/gup_benchmark: fix unsigned comparison to zero in __gup_benchmark_ioctl get_user_pages_fast() will return negative value if no pages were pinned, then be converted to a unsigned, which is compared to zero, giving the wrong result. Link: http://lkml.kernel.org/r/20180921095015.26088-1-yuehaibing@huawei.com Fixes: 09e35a4a1ca8 ("mm/gup_benchmark: handle gup failures") Signed-off-by: YueHaibing Reviewed-by: Andrew Morton Cc: Michael S. Tsirkin Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- mm/gup_benchmark.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'mm') diff --git a/mm/gup_benchmark.c b/mm/gup_benchmark.c index 6a473709e9b6..7405c9d89d65 100644 --- a/mm/gup_benchmark.c +++ b/mm/gup_benchmark.c @@ -19,7 +19,8 @@ static int __gup_benchmark_ioctl(unsigned int cmd, struct gup_benchmark *gup) { ktime_t start_time, end_time; - unsigned long i, nr, nr_pages, addr, next; + unsigned long i, nr_pages, addr, next; + int nr; struct page **pages; nr_pages = gup->size / PAGE_SIZE; -- cgit v1.2.3 From e6112fc300702f96374f34368513d57795fc6d23 Mon Sep 17 00:00:00 2001 From: Anshuman Khandual Date: Fri, 5 Oct 2018 15:51:51 -0700 Subject: mm/migrate.c: split only transparent huge pages when allocation fails split_huge_page_to_list() fails on HugeTLB pages. I was experimenting with moving 32MB contig HugeTLB pages on arm64 (with a debug patch applied) and hit the following stack trace when the kernel crashed. [ 3732.462797] Call trace: [ 3732.462835] split_huge_page_to_list+0x3b0/0x858 [ 3732.462913] migrate_pages+0x728/0xc20 [ 3732.462999] soft_offline_page+0x448/0x8b0 [ 3732.463097] __arm64_sys_madvise+0x724/0x850 [ 3732.463197] el0_svc_handler+0x74/0x110 [ 3732.463297] el0_svc+0x8/0xc [ 3732.463347] Code: d1000400 f90b0e60 f2fbd5a2 a94982a1 (f9000420) When unmap_and_move[_huge_page]() fails due to lack of memory, the splitting should happen only for transparent huge pages not for HugeTLB pages. PageTransHuge() returns true for both THP and HugeTLB pages. Hence the conditonal check should test PagesHuge() flag to make sure that given pages is not a HugeTLB one. Link: http://lkml.kernel.org/r/1537798495-4996-1-git-send-email-anshuman.khandual@arm.com Fixes: 94723aafb9 ("mm: unclutter THP migration") Signed-off-by: Anshuman Khandual Acked-by: Michal Hocko Acked-by: Naoya Horiguchi Cc: Kirill A. Shutemov Cc: Zi Yan Cc: Mike Kravetz Cc: Vlastimil Babka Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- mm/migrate.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'mm') diff --git a/mm/migrate.c b/mm/migrate.c index 9d374011c244..9ba72c2365e6 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -1414,7 +1414,7 @@ retry: * we encounter them after the rest of the list * is processed. */ - if (PageTransHuge(page)) { + if (PageTransHuge(page) && !PageHuge(page)) { lock_page(page); rc = split_huge_page_to_list(page, from); unlock_page(page); -- cgit v1.2.3 From 28e2c4bb99aa40f9d5f07ac130cbc4da0ea93079 Mon Sep 17 00:00:00 2001 From: Jann Horn Date: Fri, 5 Oct 2018 15:52:03 -0700 Subject: mm/vmstat.c: fix outdated vmstat_text 7a9cdebdcc17 ("mm: get rid of vmacache_flush_all() entirely") removed the VMACACHE_FULL_FLUSHES statistics, but didn't remove the corresponding entry in vmstat_text. This causes an out-of-bounds access in vmstat_show(). Luckily this only affects kernels with CONFIG_DEBUG_VM_VMACACHE=y, which is probably very rare. Link: http://lkml.kernel.org/r/20181001143138.95119-1-jannh@google.com Fixes: 7a9cdebdcc17 ("mm: get rid of vmacache_flush_all() entirely") Signed-off-by: Jann Horn Reviewed-by: Kees Cook Reviewed-by: Andrew Morton Acked-by: Michal Hocko Acked-by: Roman Gushchin Cc: Davidlohr Bueso Cc: Oleg Nesterov Cc: Christoph Lameter Cc: Kemi Wang Cc: Andy Lutomirski Cc: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- mm/vmstat.c | 1 - 1 file changed, 1 deletion(-) (limited to 'mm') diff --git a/mm/vmstat.c b/mm/vmstat.c index 8ba0870ecddd..4cea7b8f519d 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -1283,7 +1283,6 @@ const char * const vmstat_text[] = { #ifdef CONFIG_DEBUG_VM_VMACACHE "vmacache_find_calls", "vmacache_find_hits", - "vmacache_full_flushes", #endif #ifdef CONFIG_SWAP "swap_ra", -- cgit v1.2.3 From 58bc4c34d249bf1bc50730a9a209139347cfacfe Mon Sep 17 00:00:00 2001 From: Jann Horn Date: Fri, 5 Oct 2018 15:52:07 -0700 Subject: mm/vmstat.c: skip NR_TLB_REMOTE_FLUSH* properly 5dd0b16cdaff ("mm/vmstat: Make NR_TLB_REMOTE_FLUSH_RECEIVED available even on UP") made the availability of the NR_TLB_REMOTE_FLUSH* counters inside the kernel unconditional to reduce #ifdef soup, but (either to avoid showing dummy zero counters to userspace, or because that code was missed) didn't update the vmstat_array, meaning that all following counters would be shown with incorrect values. This only affects kernel builds with CONFIG_VM_EVENT_COUNTERS=y && CONFIG_DEBUG_TLBFLUSH=y && CONFIG_SMP=n. Link: http://lkml.kernel.org/r/20181001143138.95119-2-jannh@google.com Fixes: 5dd0b16cdaff ("mm/vmstat: Make NR_TLB_REMOTE_FLUSH_RECEIVED available even on UP") Signed-off-by: Jann Horn Reviewed-by: Kees Cook Reviewed-by: Andrew Morton Acked-by: Michal Hocko Acked-by: Roman Gushchin Cc: Davidlohr Bueso Cc: Oleg Nesterov Cc: Christoph Lameter Cc: Kemi Wang Cc: Andy Lutomirski Cc: Ingo Molnar Cc: Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- mm/vmstat.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'mm') diff --git a/mm/vmstat.c b/mm/vmstat.c index 4cea7b8f519d..7878da76abf2 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -1275,6 +1275,9 @@ const char * const vmstat_text[] = { #ifdef CONFIG_SMP "nr_tlb_remote_flush", "nr_tlb_remote_flush_received", +#else + "", /* nr_tlb_remote_flush */ + "", /* nr_tlb_remote_flush_received */ #endif /* CONFIG_SMP */ "nr_tlb_local_flush_all", "nr_tlb_local_flush_one", -- cgit v1.2.3 From b8e57efa2c98cc56c49461c4950cf026422c29e9 Mon Sep 17 00:00:00 2001 From: Kirill Tkhai Date: Fri, 5 Oct 2018 15:52:10 -0700 Subject: mm/vmscan.c: fix int overflow in callers of do_shrink_slab() do_shrink_slab() returns unsigned long value, and the placing into int variable cuts high bytes off. Then we compare ret and 0xfffffffe (since SHRINK_EMPTY is converted to ret type). Thus a large number of objects returned by do_shrink_slab() may be interpreted as SHRINK_EMPTY, if low bytes of their value are equal to 0xfffffffe. Fix that by declaration ret as unsigned long in these functions. Link: http://lkml.kernel.org/r/153813407177.17544.14888305435570723973.stgit@localhost.localdomain Signed-off-by: Kirill Tkhai Reported-by: Cyrill Gorcunov Acked-by: Cyrill Gorcunov Reviewed-by: Josef Bacik Cc: Michal Hocko Cc: Andrey Ryabinin Cc: Johannes Weiner Cc: Tetsuo Handa Cc: Shakeel Butt Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- mm/vmscan.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) (limited to 'mm') diff --git a/mm/vmscan.c b/mm/vmscan.c index c7ce2c161225..c5ef7240cbcb 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -580,8 +580,8 @@ static unsigned long shrink_slab_memcg(gfp_t gfp_mask, int nid, struct mem_cgroup *memcg, int priority) { struct memcg_shrinker_map *map; - unsigned long freed = 0; - int ret, i; + unsigned long ret, freed = 0; + int i; if (!memcg_kmem_enabled() || !mem_cgroup_online(memcg)) return 0; @@ -677,9 +677,8 @@ static unsigned long shrink_slab(gfp_t gfp_mask, int nid, struct mem_cgroup *memcg, int priority) { + unsigned long ret, freed = 0; struct shrinker *shrinker; - unsigned long freed = 0; - int ret; if (!mem_cgroup_is_root(memcg)) return shrink_slab_memcg(gfp_mask, nid, memcg, priority); -- cgit v1.2.3 From d41aa5252394c065d1f04d1ceea885b70d00c9c6 Mon Sep 17 00:00:00 2001 From: Daniel Black Date: Fri, 5 Oct 2018 15:52:19 -0700 Subject: mm: madvise(MADV_DODUMP): allow hugetlbfs pages Reproducer, assuming 2M of hugetlbfs available: Hugetlbfs mounted, size=2M and option user=testuser # mount | grep ^hugetlbfs hugetlbfs on /dev/hugepages type hugetlbfs (rw,pagesize=2M,user=dan) # sysctl vm.nr_hugepages=1 vm.nr_hugepages = 1 # grep Huge /proc/meminfo AnonHugePages: 0 kB ShmemHugePages: 0 kB HugePages_Total: 1 HugePages_Free: 1 HugePages_Rsvd: 0 HugePages_Surp: 0 Hugepagesize: 2048 kB Hugetlb: 2048 kB Code: #include #include #define SIZE 2*1024*1024 int main() { void *ptr; ptr = mmap(NULL, SIZE, PROT_READ | PROT_WRITE, MAP_PRIVATE | MAP_HUGETLB | MAP_ANONYMOUS, -1, 0); madvise(ptr, SIZE, MADV_DONTDUMP); madvise(ptr, SIZE, MADV_DODUMP); } Compile and strace: mmap(NULL, 2097152, PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_ANONYMOUS|MAP_HUGETLB, -1, 0) = 0x7ff7c9200000 madvise(0x7ff7c9200000, 2097152, MADV_DONTDUMP) = 0 madvise(0x7ff7c9200000, 2097152, MADV_DODUMP) = -1 EINVAL (Invalid argument) hugetlbfs pages have VM_DONTEXPAND in the VmFlags driver pages based on author testing with analysis from Florian Weimer[1]. The inclusion of VM_DONTEXPAND into the VM_SPECIAL defination was a consequence of the large useage of VM_DONTEXPAND in device drivers. A consequence of [2] is that VM_DONTEXPAND marked pages are unable to be marked DODUMP. A user could quite legitimately madvise(MADV_DONTDUMP) their hugetlbfs memory for a while and later request that madvise(MADV_DODUMP) on the same memory. We correct this omission by allowing madvice(MADV_DODUMP) on hugetlbfs pages. [1] https://stackoverflow.com/questions/52548260/madvisedodump-on-the-same-ptr-size-as-a-successful-madvisedontdump-fails-wit [2] commit 0103bd16fb90 ("mm: prepare VM_DONTDUMP for using in drivers") Link: http://lkml.kernel.org/r/20180930054629.29150-1-daniel@linux.ibm.com Link: https://lists.launchpad.net/maria-discuss/msg05245.html Fixes: 0103bd16fb90 ("mm: prepare VM_DONTDUMP for using in drivers") Reported-by: Kenneth Penza Signed-off-by: Daniel Black Reviewed-by: Mike Kravetz Cc: Konstantin Khlebnikov Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- mm/madvise.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'mm') diff --git a/mm/madvise.c b/mm/madvise.c index 972a9eaa898b..71d21df2a3f3 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -96,7 +96,7 @@ static long madvise_behavior(struct vm_area_struct *vma, new_flags |= VM_DONTDUMP; break; case MADV_DODUMP: - if (new_flags & VM_SPECIAL) { + if (!is_vm_hugetlb_page(vma) && new_flags & VM_SPECIAL) { error = -EINVAL; goto out; } -- cgit v1.2.3 From 6685b357363bfe295e3ae73665014db4aed62c58 Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Sun, 7 Oct 2018 11:31:51 +0300 Subject: percpu: stop leaking bitmap metadata blocks The commit ca460b3c9627 ("percpu: introduce bitmap metadata blocks") introduced bitmap metadata blocks. These metadata blocks are allocated whenever a new chunk is created, but they are never freed. Fix it. Fixes: ca460b3c9627 ("percpu: introduce bitmap metadata blocks") Signed-off-by: Mike Rapoport Cc: stable@vger.kernel.org Signed-off-by: Dennis Zhou --- mm/percpu.c | 1 + 1 file changed, 1 insertion(+) (limited to 'mm') diff --git a/mm/percpu.c b/mm/percpu.c index a749d4d96e3e..4b90682623e9 100644 --- a/mm/percpu.c +++ b/mm/percpu.c @@ -1212,6 +1212,7 @@ static void pcpu_free_chunk(struct pcpu_chunk *chunk) { if (!chunk) return; + pcpu_mem_free(chunk->md_blocks); pcpu_mem_free(chunk->bound_map); pcpu_mem_free(chunk->alloc_map); pcpu_mem_free(chunk); -- cgit v1.2.3 From e054637597ba36d3729ba6a3a3dd7aad8e2a3003 Mon Sep 17 00:00:00 2001 From: Srikar Dronamraju Date: Sat, 6 Oct 2018 16:53:19 +0530 Subject: mm, sched/numa: Remove remaining traces of NUMA rate-limiting Remove the leftover pglist_data::numabalancing_migrate_lock and its initialization, we stopped using this lock with: efaffc5e40ae ("mm, sched/numa: Remove rate-limiting of automatic NUMA balancing migration") [ mingo: Rewrote the changelog. ] Signed-off-by: Srikar Dronamraju Acked-by: Mel Gorman Cc: Linus Torvalds Cc: Linux-MM Cc: Peter Zijlstra Cc: Rik van Riel Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/1538824999-31230-1-git-send-email-srikar@linux.vnet.ibm.com Signed-off-by: Ingo Molnar --- include/linux/mmzone.h | 4 ---- mm/page_alloc.c | 10 ---------- 2 files changed, 14 deletions(-) (limited to 'mm') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 3f4c0b167333..d4b0c79d2924 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -667,10 +667,6 @@ typedef struct pglist_data { enum zone_type kcompactd_classzone_idx; wait_queue_head_t kcompactd_wait; struct task_struct *kcompactd; -#endif -#ifdef CONFIG_NUMA_BALANCING - /* Lock serializing the migrate rate limiting window */ - spinlock_t numabalancing_migrate_lock; #endif /* * This is a per-node reserve of pages that are not available diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 706a738c0aee..e2ef1c17942f 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -6193,15 +6193,6 @@ static unsigned long __init calc_memmap_size(unsigned long spanned_pages, return PAGE_ALIGN(pages * sizeof(struct page)) >> PAGE_SHIFT; } -#ifdef CONFIG_NUMA_BALANCING -static void pgdat_init_numabalancing(struct pglist_data *pgdat) -{ - spin_lock_init(&pgdat->numabalancing_migrate_lock); -} -#else -static void pgdat_init_numabalancing(struct pglist_data *pgdat) {} -#endif - #ifdef CONFIG_TRANSPARENT_HUGEPAGE static void pgdat_init_split_queue(struct pglist_data *pgdat) { @@ -6226,7 +6217,6 @@ static void __meminit pgdat_init_internals(struct pglist_data *pgdat) { pgdat_resize_init(pgdat); - pgdat_init_numabalancing(pgdat); pgdat_init_split_queue(pgdat); pgdat_init_kcompactd(pgdat); -- cgit v1.2.3 From a31acd3ee8f7dbc0370bdf4a4bfef7a8c13c7542 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Sun, 26 Aug 2018 12:56:48 +0200 Subject: x86/mm: Page size aware flush_tlb_mm_range() Use the new tlb_get_unmap_shift() to determine the stride of the INVLPG loop. Cc: Nick Piggin Cc: Will Deacon Cc: "Aneesh Kumar K.V" Cc: Andrew Morton Cc: Dave Hansen Signed-off-by: Peter Zijlstra (Intel) --- arch/x86/include/asm/tlb.h | 21 ++++++++++++++------- arch/x86/include/asm/tlbflush.h | 12 ++++++++---- arch/x86/kernel/ldt.c | 2 +- arch/x86/kernel/vm86_32.c | 2 +- arch/x86/mm/tlb.c | 17 ++++++++--------- mm/pgtable-generic.c | 1 + 6 files changed, 33 insertions(+), 22 deletions(-) (limited to 'mm') diff --git a/arch/x86/include/asm/tlb.h b/arch/x86/include/asm/tlb.h index cb0a1f470980..afbe7d1e68cf 100644 --- a/arch/x86/include/asm/tlb.h +++ b/arch/x86/include/asm/tlb.h @@ -6,16 +6,23 @@ #define tlb_end_vma(tlb, vma) do { } while (0) #define __tlb_remove_tlb_entry(tlb, ptep, address) do { } while (0) -#define tlb_flush(tlb) \ -{ \ - if (!tlb->fullmm && !tlb->need_flush_all) \ - flush_tlb_mm_range(tlb->mm, tlb->start, tlb->end, 0UL); \ - else \ - flush_tlb_mm_range(tlb->mm, 0UL, TLB_FLUSH_ALL, 0UL); \ -} +static inline void tlb_flush(struct mmu_gather *tlb); #include +static inline void tlb_flush(struct mmu_gather *tlb) +{ + unsigned long start = 0UL, end = TLB_FLUSH_ALL; + unsigned int stride_shift = tlb_get_unmap_shift(tlb); + + if (!tlb->fullmm && !tlb->need_flush_all) { + start = tlb->start; + end = tlb->end; + } + + flush_tlb_mm_range(tlb->mm, start, end, stride_shift); +} + /* * While x86 architecture in general requires an IPI to perform TLB * shootdown, enablement code for several hypervisors overrides diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h index 58ce5288878e..671f65309ce7 100644 --- a/arch/x86/include/asm/tlbflush.h +++ b/arch/x86/include/asm/tlbflush.h @@ -547,23 +547,27 @@ struct flush_tlb_info { unsigned long start; unsigned long end; u64 new_tlb_gen; + unsigned int stride_shift; }; #define local_flush_tlb() __flush_tlb() #define flush_tlb_mm(mm) flush_tlb_mm_range(mm, 0UL, TLB_FLUSH_ALL, 0UL) -#define flush_tlb_range(vma, start, end) \ - flush_tlb_mm_range(vma->vm_mm, start, end, vma->vm_flags) +#define flush_tlb_range(vma, start, end) \ + flush_tlb_mm_range((vma)->vm_mm, start, end, \ + ((vma)->vm_flags & VM_HUGETLB) \ + ? huge_page_shift(hstate_vma(vma)) \ + : PAGE_SHIFT) extern void flush_tlb_all(void); extern void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start, - unsigned long end, unsigned long vmflag); + unsigned long end, unsigned int stride_shift); extern void flush_tlb_kernel_range(unsigned long start, unsigned long end); static inline void flush_tlb_page(struct vm_area_struct *vma, unsigned long a) { - flush_tlb_mm_range(vma->vm_mm, a, a + PAGE_SIZE, VM_NONE); + flush_tlb_mm_range(vma->vm_mm, a, a + PAGE_SIZE, PAGE_SHIFT); } void native_flush_tlb_others(const struct cpumask *cpumask, diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c index 733e6ace0fa4..7fdb2414ca65 100644 --- a/arch/x86/kernel/ldt.c +++ b/arch/x86/kernel/ldt.c @@ -273,7 +273,7 @@ map_ldt_struct(struct mm_struct *mm, struct ldt_struct *ldt, int slot) map_ldt_struct_to_user(mm); va = (unsigned long)ldt_slot_va(slot); - flush_tlb_mm_range(mm, va, va + LDT_SLOT_STRIDE, 0); + flush_tlb_mm_range(mm, va, va + LDT_SLOT_STRIDE, PAGE_SHIFT); ldt->slot = slot; return 0; diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c index 1c03e4aa6474..52fed70f671e 100644 --- a/arch/x86/kernel/vm86_32.c +++ b/arch/x86/kernel/vm86_32.c @@ -199,7 +199,7 @@ static void mark_screen_rdonly(struct mm_struct *mm) pte_unmap_unlock(pte, ptl); out: up_write(&mm->mmap_sem); - flush_tlb_mm_range(mm, 0xA0000, 0xA0000 + 32*PAGE_SIZE, 0UL); + flush_tlb_mm_range(mm, 0xA0000, 0xA0000 + 32*PAGE_SIZE, PAGE_SHIFT); } diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c index e96b99eb800c..6aa195796dec 100644 --- a/arch/x86/mm/tlb.c +++ b/arch/x86/mm/tlb.c @@ -528,17 +528,16 @@ static void flush_tlb_func_common(const struct flush_tlb_info *f, f->new_tlb_gen == local_tlb_gen + 1 && f->new_tlb_gen == mm_tlb_gen) { /* Partial flush */ - unsigned long addr; - unsigned long nr_pages = (f->end - f->start) >> PAGE_SHIFT; + unsigned long nr_invalidate = (f->end - f->start) >> f->stride_shift; + unsigned long addr = f->start; - addr = f->start; while (addr < f->end) { __flush_tlb_one_user(addr); - addr += PAGE_SIZE; + addr += 1UL << f->stride_shift; } if (local) - count_vm_tlb_events(NR_TLB_LOCAL_FLUSH_ONE, nr_pages); - trace_tlb_flush(reason, nr_pages); + count_vm_tlb_events(NR_TLB_LOCAL_FLUSH_ONE, nr_invalidate); + trace_tlb_flush(reason, nr_invalidate); } else { /* Full flush. */ local_flush_tlb(); @@ -623,12 +622,13 @@ void native_flush_tlb_others(const struct cpumask *cpumask, static unsigned long tlb_single_page_flush_ceiling __read_mostly = 33; void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start, - unsigned long end, unsigned long vmflag) + unsigned long end, unsigned int stride_shift) { int cpu; struct flush_tlb_info info __aligned(SMP_CACHE_BYTES) = { .mm = mm, + .stride_shift = stride_shift, }; cpu = get_cpu(); @@ -638,8 +638,7 @@ void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start, /* Should we flush just the requested range? */ if ((end != TLB_FLUSH_ALL) && - !(vmflag & VM_HUGETLB) && - ((end - start) >> PAGE_SHIFT) <= tlb_single_page_flush_ceiling) { + ((end - start) >> stride_shift) <= tlb_single_page_flush_ceiling) { info.start = start; info.end = end; } else { diff --git a/mm/pgtable-generic.c b/mm/pgtable-generic.c index cf2af04b34b9..532c29276fce 100644 --- a/mm/pgtable-generic.c +++ b/mm/pgtable-generic.c @@ -8,6 +8,7 @@ */ #include +#include #include #include -- cgit v1.2.3 From 7aa867dd89526e9cfd9714d8b9b587c016eaea34 Mon Sep 17 00:00:00 2001 From: Jann Horn Date: Fri, 12 Oct 2018 21:34:32 -0700 Subject: mm/mmap.c: don't clobber partially overlapping VMA with MAP_FIXED_NOREPLACE Daniel Micay reports that attempting to use MAP_FIXED_NOREPLACE in an application causes that application to randomly crash. The existing check for handling MAP_FIXED_NOREPLACE looks up the first VMA that either overlaps or follows the requested region, and then bails out if that VMA overlaps *the start* of the requested region. It does not bail out if the VMA only overlaps another part of the requested region. Fix it by checking that the found VMA only starts at or after the end of the requested region, in which case there is no overlap. Test case: user@debian:~$ cat mmap_fixed_simple.c #include #include #include #include #include #ifndef MAP_FIXED_NOREPLACE #define MAP_FIXED_NOREPLACE 0x100000 #endif int main(void) { char *p; errno = 0; p = mmap((void*)0x10001000, 0x4000, PROT_NONE, MAP_PRIVATE|MAP_ANONYMOUS|MAP_FIXED_NOREPLACE, -1, 0); printf("p1=%p err=%m\n", p); errno = 0; p = mmap((void*)0x10000000, 0x2000, PROT_READ, MAP_PRIVATE|MAP_ANONYMOUS|MAP_FIXED_NOREPLACE, -1, 0); printf("p2=%p err=%m\n", p); char cmd[100]; sprintf(cmd, "cat /proc/%d/maps", getpid()); system(cmd); return 0; } user@debian:~$ gcc -o mmap_fixed_simple mmap_fixed_simple.c user@debian:~$ ./mmap_fixed_simple p1=0x10001000 err=Success p2=0x10000000 err=Success 10000000-10002000 r--p 00000000 00:00 0 10002000-10005000 ---p 00000000 00:00 0 564a9a06f000-564a9a070000 r-xp 00000000 fe:01 264004 /home/user/mmap_fixed_simple 564a9a26f000-564a9a270000 r--p 00000000 fe:01 264004 /home/user/mmap_fixed_simple 564a9a270000-564a9a271000 rw-p 00001000 fe:01 264004 /home/user/mmap_fixed_simple 564a9a54a000-564a9a56b000 rw-p 00000000 00:00 0 [heap] 7f8eba447000-7f8eba5dc000 r-xp 00000000 fe:01 405885 /lib/x86_64-linux-gnu/libc-2.24.so 7f8eba5dc000-7f8eba7dc000 ---p 00195000 fe:01 405885 /lib/x86_64-linux-gnu/libc-2.24.so 7f8eba7dc000-7f8eba7e0000 r--p 00195000 fe:01 405885 /lib/x86_64-linux-gnu/libc-2.24.so 7f8eba7e0000-7f8eba7e2000 rw-p 00199000 fe:01 405885 /lib/x86_64-linux-gnu/libc-2.24.so 7f8eba7e2000-7f8eba7e6000 rw-p 00000000 00:00 0 7f8eba7e6000-7f8eba809000 r-xp 00000000 fe:01 405876 /lib/x86_64-linux-gnu/ld-2.24.so 7f8eba9e9000-7f8eba9eb000 rw-p 00000000 00:00 0 7f8ebaa06000-7f8ebaa09000 rw-p 00000000 00:00 0 7f8ebaa09000-7f8ebaa0a000 r--p 00023000 fe:01 405876 /lib/x86_64-linux-gnu/ld-2.24.so 7f8ebaa0a000-7f8ebaa0b000 rw-p 00024000 fe:01 405876 /lib/x86_64-linux-gnu/ld-2.24.so 7f8ebaa0b000-7f8ebaa0c000 rw-p 00000000 00:00 0 7ffcc99fa000-7ffcc9a1b000 rw-p 00000000 00:00 0 [stack] 7ffcc9b44000-7ffcc9b47000 r--p 00000000 00:00 0 [vvar] 7ffcc9b47000-7ffcc9b49000 r-xp 00000000 00:00 0 [vdso] ffffffffff600000-ffffffffff601000 r-xp 00000000 00:00 0 [vsyscall] user@debian:~$ uname -a Linux debian 4.19.0-rc6+ #181 SMP Wed Oct 3 23:43:42 CEST 2018 x86_64 GNU/Linux user@debian:~$ As you can see, the first page of the mapping at 0x10001000 was clobbered. Link: http://lkml.kernel.org/r/20181010152736.99475-1-jannh@google.com Fixes: a4ff8e8620d3 ("mm: introduce MAP_FIXED_NOREPLACE") Signed-off-by: Jann Horn Reported-by: Daniel Micay Acked-by: Michal Hocko Acked-by: John Hubbard Acked-by: Kees Cook Acked-by: Vlastimil Babka Cc: Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- mm/mmap.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'mm') diff --git a/mm/mmap.c b/mm/mmap.c index 5f2b2b184c60..f7cd9cb966c0 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -1410,7 +1410,7 @@ unsigned long do_mmap(struct file *file, unsigned long addr, if (flags & MAP_FIXED_NOREPLACE) { struct vm_area_struct *vma = find_vma(mm, addr); - if (vma && vma->vm_start <= addr) + if (vma && vma->vm_start < addr + len) return -EEXIST; } -- cgit v1.2.3 From bfba8e5cf28f413aa05571af493871d74438979f Mon Sep 17 00:00:00 2001 From: Jérôme Glisse Date: Fri, 12 Oct 2018 21:34:36 -0700 Subject: mm/thp: fix call to mmu_notifier in set_pmd_migration_entry() v2 MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Inside set_pmd_migration_entry() we are holding page table locks and thus we can not sleep so we can not call invalidate_range_start/end() So remove call to mmu_notifier_invalidate_range_start/end() because they are call inside the function calling set_pmd_migration_entry() (see try_to_unmap_one()). Link: http://lkml.kernel.org/r/20181012181056.7864-1-jglisse@redhat.com Signed-off-by: Jérôme Glisse Reported-by: Andrea Arcangeli Reviewed-by: Zi Yan Acked-by: Michal Hocko Cc: Greg Kroah-Hartman Cc: Kirill A. Shutemov Cc: "H. Peter Anvin" Cc: Anshuman Khandual Cc: Dave Hansen Cc: David Nellans Cc: Ingo Molnar Cc: Mel Gorman Cc: Minchan Kim Cc: Naoya Horiguchi Cc: Thomas Gleixner Cc: Vlastimil Babka Cc: Signed-off-by: Andrew Morton Signed-off-by: Greg Kroah-Hartman --- mm/huge_memory.c | 6 ------ 1 file changed, 6 deletions(-) (limited to 'mm') diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 00704060b7f7..58269f8ba7c4 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2885,9 +2885,6 @@ void set_pmd_migration_entry(struct page_vma_mapped_walk *pvmw, if (!(pvmw->pmd && !pvmw->pte)) return; - mmu_notifier_invalidate_range_start(mm, address, - address + HPAGE_PMD_SIZE); - flush_cache_range(vma, address, address + HPAGE_PMD_SIZE); pmdval = *pvmw->pmd; pmdp_invalidate(vma, address, pvmw->pmd); @@ -2900,9 +2897,6 @@ void set_pmd_migration_entry(struct page_vma_mapped_walk *pvmw, set_pmd_at(mm, address, pvmw->pmd, pmdswp); page_remove_rmap(page, true); put_page(page); - - mmu_notifier_invalidate_range_end(mm, address, - address + HPAGE_PMD_SIZE); } void remove_migration_pmd(struct page_vma_mapped_walk *pvmw, struct page *new) -- cgit v1.2.3 From 59c3f82ad1d6ed83fde9d7608afb9fb221a211ab Mon Sep 17 00:00:00 2001 From: Bartosz Golaszewski Date: Sun, 14 Oct 2018 17:20:08 +0200 Subject: mm: move is_kernel_rodata() to asm-generic/sections.h Export this routine so that we can use it later in devm_kstrdup_const() and devm_kfree(). Signed-off-by: Bartosz Golaszewski Reviewed-by: Bjorn Andersson Acked-by: Mike Rapoport Acked-by: Rasmus Villemoes Reviewed-by: Geert Uytterhoeven Reviewed-by: Andy Shevchenko Signed-off-by: Greg Kroah-Hartman --- include/asm-generic/sections.h | 14 ++++++++++++++ mm/util.c | 7 ------- 2 files changed, 14 insertions(+), 7 deletions(-) (limited to 'mm') diff --git a/include/asm-generic/sections.h b/include/asm-generic/sections.h index 849cd8eb5ca0..d79abca81a52 100644 --- a/include/asm-generic/sections.h +++ b/include/asm-generic/sections.h @@ -141,4 +141,18 @@ static inline bool init_section_intersects(void *virt, size_t size) return memory_intersects(__init_begin, __init_end, virt, size); } +/** + * is_kernel_rodata - checks if the pointer address is located in the + * .rodata section + * + * @addr: address to check + * + * Returns: true if the address is located in .rodata, false otherwise. + */ +static inline bool is_kernel_rodata(unsigned long addr) +{ + return addr >= (unsigned long)__start_rodata && + addr < (unsigned long)__end_rodata; +} + #endif /* _ASM_GENERIC_SECTIONS_H_ */ diff --git a/mm/util.c b/mm/util.c index 9e3ebd2ef65f..470f5cd80b64 100644 --- a/mm/util.c +++ b/mm/util.c @@ -15,17 +15,10 @@ #include #include -#include #include #include "internal.h" -static inline int is_kernel_rodata(unsigned long addr) -{ - return addr >= (unsigned long)__start_rodata && - addr < (unsigned long)__end_rodata; -} - /** * kfree_const - conditionally free memory * @x: pointer to the memory -- cgit v1.2.3 From eb66ae030829605d61fbef1909ce310e29f78821 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Fri, 12 Oct 2018 15:22:59 -0700 Subject: mremap: properly flush TLB before releasing the page Jann Horn points out that our TLB flushing was subtly wrong for the mremap() case. What makes mremap() special is that we don't follow the usual "add page to list of pages to be freed, then flush tlb, and then free pages". No, mremap() obviously just _moves_ the page from one page table location to another. That matters, because mremap() thus doesn't directly control the lifetime of the moved page with a freelist: instead, the lifetime of the page is controlled by the page table locking, that serializes access to the entry. As a result, we need to flush the TLB not just before releasing the lock for the source location (to avoid any concurrent accesses to the entry), but also before we release the destination page table lock (to avoid the TLB being flushed after somebody else has already done something to that page). This also makes the whole "need_flush" logic unnecessary, since we now always end up flushing the TLB for every valid entry. Reported-and-tested-by: Jann Horn Acked-by: Will Deacon Tested-by: Ingo Molnar Acked-by: Peter Zijlstra (Intel) Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- include/linux/huge_mm.h | 2 +- mm/huge_memory.c | 10 ++++------ mm/mremap.c | 30 +++++++++++++----------------- 3 files changed, 18 insertions(+), 24 deletions(-) (limited to 'mm') diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index 99c19b06d9a4..fdcb45999b26 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -43,7 +43,7 @@ extern int mincore_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, unsigned char *vec); extern bool move_huge_pmd(struct vm_area_struct *vma, unsigned long old_addr, unsigned long new_addr, unsigned long old_end, - pmd_t *old_pmd, pmd_t *new_pmd, bool *need_flush); + pmd_t *old_pmd, pmd_t *new_pmd); extern int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, pgprot_t newprot, int prot_numa); diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 58269f8ba7c4..deed97fba979 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1780,7 +1780,7 @@ static pmd_t move_soft_dirty_pmd(pmd_t pmd) bool move_huge_pmd(struct vm_area_struct *vma, unsigned long old_addr, unsigned long new_addr, unsigned long old_end, - pmd_t *old_pmd, pmd_t *new_pmd, bool *need_flush) + pmd_t *old_pmd, pmd_t *new_pmd) { spinlock_t *old_ptl, *new_ptl; pmd_t pmd; @@ -1811,7 +1811,7 @@ bool move_huge_pmd(struct vm_area_struct *vma, unsigned long old_addr, if (new_ptl != old_ptl) spin_lock_nested(new_ptl, SINGLE_DEPTH_NESTING); pmd = pmdp_huge_get_and_clear(mm, old_addr, old_pmd); - if (pmd_present(pmd) && pmd_dirty(pmd)) + if (pmd_present(pmd)) force_flush = true; VM_BUG_ON(!pmd_none(*new_pmd)); @@ -1822,12 +1822,10 @@ bool move_huge_pmd(struct vm_area_struct *vma, unsigned long old_addr, } pmd = move_soft_dirty_pmd(pmd); set_pmd_at(mm, new_addr, new_pmd, pmd); - if (new_ptl != old_ptl) - spin_unlock(new_ptl); if (force_flush) flush_tlb_range(vma, old_addr, old_addr + PMD_SIZE); - else - *need_flush = true; + if (new_ptl != old_ptl) + spin_unlock(new_ptl); spin_unlock(old_ptl); return true; } diff --git a/mm/mremap.c b/mm/mremap.c index 5c2e18505f75..a9617e72e6b7 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -115,7 +115,7 @@ static pte_t move_soft_dirty_pte(pte_t pte) static void move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd, unsigned long old_addr, unsigned long old_end, struct vm_area_struct *new_vma, pmd_t *new_pmd, - unsigned long new_addr, bool need_rmap_locks, bool *need_flush) + unsigned long new_addr, bool need_rmap_locks) { struct mm_struct *mm = vma->vm_mm; pte_t *old_pte, *new_pte, pte; @@ -163,15 +163,17 @@ static void move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd, pte = ptep_get_and_clear(mm, old_addr, old_pte); /* - * If we are remapping a dirty PTE, make sure + * If we are remapping a valid PTE, make sure * to flush TLB before we drop the PTL for the - * old PTE or we may race with page_mkclean(). + * PTE. * - * This check has to be done after we removed the - * old PTE from page tables or another thread may - * dirty it after the check and before the removal. + * NOTE! Both old and new PTL matter: the old one + * for racing with page_mkclean(), the new one to + * make sure the physical page stays valid until + * the TLB entry for the old mapping has been + * flushed. */ - if (pte_present(pte) && pte_dirty(pte)) + if (pte_present(pte)) force_flush = true; pte = move_pte(pte, new_vma->vm_page_prot, old_addr, new_addr); pte = move_soft_dirty_pte(pte); @@ -179,13 +181,11 @@ static void move_ptes(struct vm_area_struct *vma, pmd_t *old_pmd, } arch_leave_lazy_mmu_mode(); + if (force_flush) + flush_tlb_range(vma, old_end - len, old_end); if (new_ptl != old_ptl) spin_unlock(new_ptl); pte_unmap(new_pte - 1); - if (force_flush) - flush_tlb_range(vma, old_end - len, old_end); - else - *need_flush = true; pte_unmap_unlock(old_pte - 1, old_ptl); if (need_rmap_locks) drop_rmap_locks(vma); @@ -198,7 +198,6 @@ unsigned long move_page_tables(struct vm_area_struct *vma, { unsigned long extent, next, old_end; pmd_t *old_pmd, *new_pmd; - bool need_flush = false; unsigned long mmun_start; /* For mmu_notifiers */ unsigned long mmun_end; /* For mmu_notifiers */ @@ -229,8 +228,7 @@ unsigned long move_page_tables(struct vm_area_struct *vma, if (need_rmap_locks) take_rmap_locks(vma); moved = move_huge_pmd(vma, old_addr, new_addr, - old_end, old_pmd, new_pmd, - &need_flush); + old_end, old_pmd, new_pmd); if (need_rmap_locks) drop_rmap_locks(vma); if (moved) @@ -246,10 +244,8 @@ unsigned long move_page_tables(struct vm_area_struct *vma, if (extent > next - new_addr) extent = next - new_addr; move_ptes(vma, old_pmd, old_addr, old_addr + extent, new_vma, - new_pmd, new_addr, need_rmap_locks, &need_flush); + new_pmd, new_addr, need_rmap_locks); } - if (need_flush) - flush_tlb_range(vma, old_end-len, old_addr); mmu_notifier_invalidate_range_end(vma->vm_mm, mmun_start, mmun_end); -- cgit v1.2.3 From 01959dfe771c6893365482ec78dc1d9cbbbe6de8 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Thu, 9 Nov 2017 09:23:56 -0500 Subject: xarray: Define struct xa_node This is a direct replacement for struct radix_tree_node. A couple of struct members have changed name, so convert those. Use a #define so that radix tree users continue to work without change. Signed-off-by: Matthew Wilcox Reviewed-by: Josef Bacik --- include/linux/radix-tree.h | 29 +++------------------ include/linux/xarray.h | 27 ++++++++++++++++++++ lib/radix-tree.c | 48 +++++++++++++++++------------------ mm/workingset.c | 16 ++++++------ tools/testing/radix-tree/multiorder.c | 30 +++++++++++----------- 5 files changed, 77 insertions(+), 73 deletions(-) (limited to 'mm') diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h index 0b080bd88ab7..15388b7e38b9 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -32,6 +32,7 @@ /* Keep unconverted code working */ #define radix_tree_root xarray +#define radix_tree_node xa_node /* * The bottom two bits of the slot determine how the remaining bits in the @@ -60,41 +61,17 @@ static inline bool radix_tree_is_internal_node(void *ptr) /*** radix-tree API starts here ***/ -#define RADIX_TREE_MAX_TAGS 3 - #define RADIX_TREE_MAP_SHIFT XA_CHUNK_SHIFT #define RADIX_TREE_MAP_SIZE (1UL << RADIX_TREE_MAP_SHIFT) #define RADIX_TREE_MAP_MASK (RADIX_TREE_MAP_SIZE-1) -#define RADIX_TREE_TAG_LONGS \ - ((RADIX_TREE_MAP_SIZE + BITS_PER_LONG - 1) / BITS_PER_LONG) +#define RADIX_TREE_MAX_TAGS XA_MAX_MARKS +#define RADIX_TREE_TAG_LONGS XA_MARK_LONGS #define RADIX_TREE_INDEX_BITS (8 /* CHAR_BIT */ * sizeof(unsigned long)) #define RADIX_TREE_MAX_PATH (DIV_ROUND_UP(RADIX_TREE_INDEX_BITS, \ RADIX_TREE_MAP_SHIFT)) -/* - * @count is the count of every non-NULL element in the ->slots array - * whether that is a value entry, a retry entry, a user pointer, - * a sibling entry or a pointer to the next level of the tree. - * @exceptional is the count of every element in ->slots which is - * either a value entry or a sibling of a value entry. - */ -struct radix_tree_node { - unsigned char shift; /* Bits remaining in each slot */ - unsigned char offset; /* Slot offset in parent */ - unsigned char count; /* Total entry count */ - unsigned char exceptional; /* Exceptional entry count */ - struct radix_tree_node *parent; /* Used when ascending tree */ - struct radix_tree_root *root; /* The tree we belong to */ - union { - struct list_head private_list; /* For tree user */ - struct rcu_head rcu_head; /* Used when freeing node */ - }; - void __rcu *slots[RADIX_TREE_MAP_SIZE]; - unsigned long tags[RADIX_TREE_MAX_TAGS][RADIX_TREE_TAG_LONGS]; -}; - /* The IDR tag is stored in the low bits of xa_flags */ #define ROOT_IS_IDR ((__force gfp_t)4) /* The top bits of xa_flags are used to store the root tags */ diff --git a/include/linux/xarray.h b/include/linux/xarray.h index 9122cf8bf52a..52141dfc5a90 100644 --- a/include/linux/xarray.h +++ b/include/linux/xarray.h @@ -252,6 +252,33 @@ static inline void xa_init(struct xarray *xa) #endif #define XA_CHUNK_SIZE (1UL << XA_CHUNK_SHIFT) #define XA_CHUNK_MASK (XA_CHUNK_SIZE - 1) +#define XA_MAX_MARKS 3 +#define XA_MARK_LONGS DIV_ROUND_UP(XA_CHUNK_SIZE, BITS_PER_LONG) + +/* + * @count is the count of every non-NULL element in the ->slots array + * whether that is a value entry, a retry entry, a user pointer, + * a sibling entry or a pointer to the next level of the tree. + * @nr_values is the count of every element in ->slots which is + * either a value entry or a sibling of a value entry. + */ +struct xa_node { + unsigned char shift; /* Bits remaining in each slot */ + unsigned char offset; /* Slot offset in parent */ + unsigned char count; /* Total entry count */ + unsigned char nr_values; /* Value entry count */ + struct xa_node __rcu *parent; /* NULL at top of tree */ + struct xarray *array; /* The array we belong to */ + union { + struct list_head private_list; /* For tree user */ + struct rcu_head rcu_head; /* Used when freeing node */ + }; + void __rcu *slots[XA_CHUNK_SIZE]; + union { + unsigned long tags[XA_MAX_MARKS][XA_MARK_LONGS]; + unsigned long marks[XA_MAX_MARKS][XA_MARK_LONGS]; + }; +}; /* Private */ static inline bool xa_is_node(const void *entry) diff --git a/lib/radix-tree.c b/lib/radix-tree.c index 299d4bdba109..8a568cea1237 100644 --- a/lib/radix-tree.c +++ b/lib/radix-tree.c @@ -260,11 +260,11 @@ static void dump_node(struct radix_tree_node *node, unsigned long index) { unsigned long i; - pr_debug("radix node: %p offset %d indices %lu-%lu parent %p tags %lx %lx %lx shift %d count %d exceptional %d\n", + pr_debug("radix node: %p offset %d indices %lu-%lu parent %p tags %lx %lx %lx shift %d count %d nr_values %d\n", node, node->offset, index, index | node_maxindex(node), node->parent, node->tags[0][0], node->tags[1][0], node->tags[2][0], - node->shift, node->count, node->exceptional); + node->shift, node->count, node->nr_values); for (i = 0; i < RADIX_TREE_MAP_SIZE; i++) { unsigned long first = index | (i << node->shift); @@ -354,7 +354,7 @@ static struct radix_tree_node * radix_tree_node_alloc(gfp_t gfp_mask, struct radix_tree_node *parent, struct radix_tree_root *root, unsigned int shift, unsigned int offset, - unsigned int count, unsigned int exceptional) + unsigned int count, unsigned int nr_values) { struct radix_tree_node *ret = NULL; @@ -401,9 +401,9 @@ out: ret->shift = shift; ret->offset = offset; ret->count = count; - ret->exceptional = exceptional; + ret->nr_values = nr_values; ret->parent = parent; - ret->root = root; + ret->array = root; } return ret; } @@ -633,8 +633,8 @@ static int radix_tree_extend(struct radix_tree_root *root, gfp_t gfp, if (radix_tree_is_internal_node(entry)) { entry_to_node(entry)->parent = node; } else if (xa_is_value(entry)) { - /* Moving an exceptional root->xa_head to a node */ - node->exceptional = 1; + /* Moving a value entry root->xa_head to a node */ + node->nr_values = 1; } /* * entry was already in the radix tree, so we do not need @@ -928,12 +928,12 @@ static inline int insert_entries(struct radix_tree_node *node, if (xa_is_node(old)) radix_tree_free_nodes(old); if (xa_is_value(old)) - node->exceptional--; + node->nr_values--; } if (node) { node->count += n; if (xa_is_value(item)) - node->exceptional += n; + node->nr_values += n; } return n; } @@ -947,7 +947,7 @@ static inline int insert_entries(struct radix_tree_node *node, if (node) { node->count++; if (xa_is_value(item)) - node->exceptional++; + node->nr_values++; } return 1; } @@ -1083,7 +1083,7 @@ void *radix_tree_lookup(const struct radix_tree_root *root, unsigned long index) EXPORT_SYMBOL(radix_tree_lookup); static inline void replace_sibling_entries(struct radix_tree_node *node, - void __rcu **slot, int count, int exceptional) + void __rcu **slot, int count, int values) { #ifdef CONFIG_RADIX_TREE_MULTIORDER unsigned offset = get_slot_offset(node, slot); @@ -1096,18 +1096,18 @@ static inline void replace_sibling_entries(struct radix_tree_node *node, node->slots[offset] = NULL; node->count--; } - node->exceptional += exceptional; + node->nr_values += values; } #endif } static void replace_slot(void __rcu **slot, void *item, - struct radix_tree_node *node, int count, int exceptional) + struct radix_tree_node *node, int count, int values) { - if (node && (count || exceptional)) { + if (node && (count || values)) { node->count += count; - node->exceptional += exceptional; - replace_sibling_entries(node, slot, count, exceptional); + node->nr_values += values; + replace_sibling_entries(node, slot, count, values); } rcu_assign_pointer(*slot, item); @@ -1161,17 +1161,17 @@ void __radix_tree_replace(struct radix_tree_root *root, radix_tree_update_node_t update_node) { void *old = rcu_dereference_raw(*slot); - int exceptional = !!xa_is_value(item) - !!xa_is_value(old); + int values = !!xa_is_value(item) - !!xa_is_value(old); int count = calculate_count(root, node, slot, item, old); /* - * This function supports replacing exceptional entries and + * This function supports replacing value entries and * deleting entries, but that needs accounting against the * node unless the slot is root->xa_head. */ WARN_ON_ONCE(!node && (slot != (void __rcu **)&root->xa_head) && - (count || exceptional)); - replace_slot(slot, item, node, count, exceptional); + (count || values)); + replace_slot(slot, item, node, count, values); if (!node) return; @@ -1193,7 +1193,7 @@ void __radix_tree_replace(struct radix_tree_root *root, * across slot lookup and replacement. * * NOTE: This cannot be used to switch between non-entries (empty slots), - * regular entries, and exceptional entries, as that requires accounting + * regular entries, and value entries, as that requires accounting * inside the radix tree node. When switching from one type of entry or * deleting, use __radix_tree_lookup() and __radix_tree_replace() or * radix_tree_iter_replace(). @@ -1301,7 +1301,7 @@ int radix_tree_split(struct radix_tree_root *root, unsigned long index, rcu_assign_pointer(parent->slots[end], RADIX_TREE_RETRY); } rcu_assign_pointer(parent->slots[offset], RADIX_TREE_RETRY); - parent->exceptional -= (end - offset); + parent->nr_values -= (end - offset); if (order == parent->shift) return 0; @@ -1961,7 +1961,7 @@ static bool __radix_tree_delete(struct radix_tree_root *root, struct radix_tree_node *node, void __rcu **slot) { void *old = rcu_dereference_raw(*slot); - int exceptional = xa_is_value(old) ? -1 : 0; + int values = xa_is_value(old) ? -1 : 0; unsigned offset = get_slot_offset(node, slot); int tag; @@ -1971,7 +1971,7 @@ static bool __radix_tree_delete(struct radix_tree_root *root, for (tag = 0; tag < RADIX_TREE_MAX_TAGS; tag++) node_tag_clear(root, node, tag, offset); - replace_slot(slot, NULL, node, -1, exceptional); + replace_slot(slot, NULL, node, -1, values); return node && delete_node(root, node, NULL); } diff --git a/mm/workingset.c b/mm/workingset.c index bb109b3afac2..c201cbb8c00f 100644 --- a/mm/workingset.c +++ b/mm/workingset.c @@ -349,7 +349,7 @@ void workingset_update_node(struct radix_tree_node *node) * already where they should be. The list_empty() test is safe * as node->private_list is protected by the i_pages lock. */ - if (node->count && node->count == node->exceptional) { + if (node->count && node->count == node->nr_values) { if (list_empty(&node->private_list)) list_lru_add(&shadow_nodes, &node->private_list); } else { @@ -428,8 +428,8 @@ static enum lru_status shadow_lru_isolate(struct list_head *item, * to reclaim, take the node off-LRU, and drop the lru_lock. */ - node = container_of(item, struct radix_tree_node, private_list); - mapping = container_of(node->root, struct address_space, i_pages); + node = container_of(item, struct xa_node, private_list); + mapping = container_of(node->array, struct address_space, i_pages); /* Coming from the list, invert the lock order */ if (!xa_trylock(&mapping->i_pages)) { @@ -446,25 +446,25 @@ static enum lru_status shadow_lru_isolate(struct list_head *item, * no pages, so we expect to be able to remove them all and * delete and free the empty node afterwards. */ - if (WARN_ON_ONCE(!node->exceptional)) + if (WARN_ON_ONCE(!node->nr_values)) goto out_invalid; - if (WARN_ON_ONCE(node->count != node->exceptional)) + if (WARN_ON_ONCE(node->count != node->nr_values)) goto out_invalid; for (i = 0; i < RADIX_TREE_MAP_SIZE; i++) { if (node->slots[i]) { if (WARN_ON_ONCE(!xa_is_value(node->slots[i]))) goto out_invalid; - if (WARN_ON_ONCE(!node->exceptional)) + if (WARN_ON_ONCE(!node->nr_values)) goto out_invalid; if (WARN_ON_ONCE(!mapping->nrexceptional)) goto out_invalid; node->slots[i] = NULL; - node->exceptional--; + node->nr_values--; node->count--; mapping->nrexceptional--; } } - if (WARN_ON_ONCE(node->exceptional)) + if (WARN_ON_ONCE(node->nr_values)) goto out_invalid; inc_lruvec_page_state(virt_to_page(node), WORKINGSET_NODERECLAIM); __radix_tree_delete_node(&mapping->i_pages, node, diff --git a/tools/testing/radix-tree/multiorder.c b/tools/testing/radix-tree/multiorder.c index 080aea450430..60786fa55302 100644 --- a/tools/testing/radix-tree/multiorder.c +++ b/tools/testing/radix-tree/multiorder.c @@ -393,7 +393,7 @@ static void multiorder_join2(unsigned order1, unsigned order2) radix_tree_insert(&tree, 1 << order2, xa_mk_value(5)); item2 = __radix_tree_lookup(&tree, 1 << order2, &node, NULL); assert(item2 == xa_mk_value(5)); - assert(node->exceptional == 1); + assert(node->nr_values == 1); item2 = radix_tree_lookup(&tree, 0); free(item2); @@ -401,7 +401,7 @@ static void multiorder_join2(unsigned order1, unsigned order2) radix_tree_join(&tree, 0, order1, item1); item2 = __radix_tree_lookup(&tree, 1 << order2, &node, NULL); assert(item2 == item1); - assert(node->exceptional == 0); + assert(node->nr_values == 0); item_kill_tree(&tree); } @@ -409,7 +409,7 @@ static void multiorder_join2(unsigned order1, unsigned order2) * This test revealed an accounting bug for value entries at one point. * Nodes were being freed back into the pool with an elevated exception count * by radix_tree_join() and then radix_tree_split() was failing to zero the - * count of exceptional entries. + * count of value entries. */ static void multiorder_join3(unsigned int order) { @@ -433,7 +433,7 @@ static void multiorder_join3(unsigned int order) } __radix_tree_lookup(&tree, 0, &node, NULL); - assert(node->exceptional == node->count); + assert(node->nr_values == node->count); item_kill_tree(&tree); } @@ -520,7 +520,7 @@ static void __multiorder_split2(int old_order, int new_order) item = __radix_tree_lookup(&tree, 0, &node, NULL); assert(item == xa_mk_value(5)); - assert(node->exceptional > 0); + assert(node->nr_values > 0); radix_tree_split(&tree, 0, new_order); radix_tree_for_each_slot(slot, &tree, &iter, 0) { @@ -530,7 +530,7 @@ static void __multiorder_split2(int old_order, int new_order) item = __radix_tree_lookup(&tree, 0, &node, NULL); assert(item != xa_mk_value(5)); - assert(node->exceptional == 0); + assert(node->nr_values == 0); item_kill_tree(&tree); } @@ -547,7 +547,7 @@ static void __multiorder_split3(int old_order, int new_order) item = __radix_tree_lookup(&tree, 0, &node, NULL); assert(item == xa_mk_value(5)); - assert(node->exceptional > 0); + assert(node->nr_values > 0); radix_tree_split(&tree, 0, new_order); radix_tree_for_each_slot(slot, &tree, &iter, 0) { @@ -556,7 +556,7 @@ static void __multiorder_split3(int old_order, int new_order) item = __radix_tree_lookup(&tree, 0, &node, NULL); assert(item == xa_mk_value(7)); - assert(node->exceptional > 0); + assert(node->nr_values > 0); item_kill_tree(&tree); @@ -564,7 +564,7 @@ static void __multiorder_split3(int old_order, int new_order) item = __radix_tree_lookup(&tree, 0, &node, NULL); assert(item == xa_mk_value(5)); - assert(node->exceptional > 0); + assert(node->nr_values > 0); radix_tree_split(&tree, 0, new_order); radix_tree_for_each_slot(slot, &tree, &iter, 0) { @@ -577,13 +577,13 @@ static void __multiorder_split3(int old_order, int new_order) item = __radix_tree_lookup(&tree, 1 << new_order, &node, NULL); assert(item == xa_mk_value(7)); - assert(node->count == node->exceptional); + assert(node->count == node->nr_values); do { node = node->parent; if (!node) break; assert(node->count == 1); - assert(node->exceptional == 0); + assert(node->nr_values == 0); } while (1); item_kill_tree(&tree); @@ -611,15 +611,15 @@ static void multiorder_account(void) __radix_tree_insert(&tree, 1 << 5, 5, xa_mk_value(5)); __radix_tree_lookup(&tree, 0, &node, NULL); - assert(node->count == node->exceptional * 2); + assert(node->count == node->nr_values * 2); radix_tree_delete(&tree, 1 << 5); - assert(node->exceptional == 0); + assert(node->nr_values == 0); __radix_tree_insert(&tree, 1 << 5, 5, xa_mk_value(5)); __radix_tree_lookup(&tree, 1 << 5, &node, &slot); - assert(node->count == node->exceptional * 2); + assert(node->count == node->nr_values * 2); __radix_tree_replace(&tree, node, slot, NULL, NULL); - assert(node->exceptional == 0); + assert(node->nr_values == 0); item_kill_tree(&tree); } -- cgit v1.2.3 From 0d3f92966629e536b0c5c2355c1ada8e21c245f6 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Tue, 21 Nov 2017 14:07:06 -0500 Subject: page cache: Convert hole search to XArray The page cache offers the ability to search for a miss in the previous or next N locations. Rather than teach the XArray about the page cache's definition of a miss, use xas_prev() and xas_next() to search the page array. This should be more efficient as it does not have to start the lookup from the top for each index. Signed-off-by: Matthew Wilcox --- fs/nfs/blocklayout/blocklayout.c | 2 +- include/linux/pagemap.h | 4 +- mm/filemap.c | 110 ++++++++++++++++++--------------------- mm/readahead.c | 4 +- 4 files changed, 55 insertions(+), 65 deletions(-) (limited to 'mm') diff --git a/fs/nfs/blocklayout/blocklayout.c b/fs/nfs/blocklayout/blocklayout.c index 06cb0c1d9aee..d3781cd983f6 100644 --- a/fs/nfs/blocklayout/blocklayout.c +++ b/fs/nfs/blocklayout/blocklayout.c @@ -896,7 +896,7 @@ static u64 pnfs_num_cont_bytes(struct inode *inode, pgoff_t idx) end = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE); if (end != inode->i_mapping->nrpages) { rcu_read_lock(); - end = page_cache_next_hole(mapping, idx + 1, ULONG_MAX); + end = page_cache_next_miss(mapping, idx + 1, ULONG_MAX); rcu_read_unlock(); } diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index b1bd2186e6d2..cf9ad413eee9 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -241,9 +241,9 @@ static inline gfp_t readahead_gfp_mask(struct address_space *x) typedef int filler_t(void *, struct page *); -pgoff_t page_cache_next_hole(struct address_space *mapping, +pgoff_t page_cache_next_miss(struct address_space *mapping, pgoff_t index, unsigned long max_scan); -pgoff_t page_cache_prev_hole(struct address_space *mapping, +pgoff_t page_cache_prev_miss(struct address_space *mapping, pgoff_t index, unsigned long max_scan); #define FGP_ACCESSED 0x00000001 diff --git a/mm/filemap.c b/mm/filemap.c index 4de14e75c4ec..714d3d0f60f5 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1326,86 +1326,76 @@ int __lock_page_or_retry(struct page *page, struct mm_struct *mm, } /** - * page_cache_next_hole - find the next hole (not-present entry) - * @mapping: mapping - * @index: index - * @max_scan: maximum range to search - * - * Search the set [index, min(index+max_scan-1, MAX_INDEX)] for the - * lowest indexed hole. - * - * Returns: the index of the hole if found, otherwise returns an index - * outside of the set specified (in which case 'return - index >= - * max_scan' will be true). In rare cases of index wrap-around, 0 will - * be returned. - * - * page_cache_next_hole may be called under rcu_read_lock. However, - * like radix_tree_gang_lookup, this will not atomically search a - * snapshot of the tree at a single point in time. For example, if a - * hole is created at index 5, then subsequently a hole is created at - * index 10, page_cache_next_hole covering both indexes may return 10 - * if called under rcu_read_lock. + * page_cache_next_miss() - Find the next gap in the page cache. + * @mapping: Mapping. + * @index: Index. + * @max_scan: Maximum range to search. + * + * Search the range [index, min(index + max_scan - 1, ULONG_MAX)] for the + * gap with the lowest index. + * + * This function may be called under the rcu_read_lock. However, this will + * not atomically search a snapshot of the cache at a single point in time. + * For example, if a gap is created at index 5, then subsequently a gap is + * created at index 10, page_cache_next_miss covering both indices may + * return 10 if called under the rcu_read_lock. + * + * Return: The index of the gap if found, otherwise an index outside the + * range specified (in which case 'return - index >= max_scan' will be true). + * In the rare case of index wrap-around, 0 will be returned. */ -pgoff_t page_cache_next_hole(struct address_space *mapping, +pgoff_t page_cache_next_miss(struct address_space *mapping, pgoff_t index, unsigned long max_scan) { - unsigned long i; + XA_STATE(xas, &mapping->i_pages, index); - for (i = 0; i < max_scan; i++) { - struct page *page; - - page = radix_tree_lookup(&mapping->i_pages, index); - if (!page || xa_is_value(page)) + while (max_scan--) { + void *entry = xas_next(&xas); + if (!entry || xa_is_value(entry)) break; - index++; - if (index == 0) + if (xas.xa_index == 0) break; } - return index; + return xas.xa_index; } -EXPORT_SYMBOL(page_cache_next_hole); +EXPORT_SYMBOL(page_cache_next_miss); /** - * page_cache_prev_hole - find the prev hole (not-present entry) - * @mapping: mapping - * @index: index - * @max_scan: maximum range to search - * - * Search backwards in the range [max(index-max_scan+1, 0), index] for - * the first hole. - * - * Returns: the index of the hole if found, otherwise returns an index - * outside of the set specified (in which case 'index - return >= - * max_scan' will be true). In rare cases of wrap-around, ULONG_MAX - * will be returned. - * - * page_cache_prev_hole may be called under rcu_read_lock. However, - * like radix_tree_gang_lookup, this will not atomically search a - * snapshot of the tree at a single point in time. For example, if a - * hole is created at index 10, then subsequently a hole is created at - * index 5, page_cache_prev_hole covering both indexes may return 5 if - * called under rcu_read_lock. + * page_cache_prev_miss() - Find the next gap in the page cache. + * @mapping: Mapping. + * @index: Index. + * @max_scan: Maximum range to search. + * + * Search the range [max(index - max_scan + 1, 0), index] for the + * gap with the highest index. + * + * This function may be called under the rcu_read_lock. However, this will + * not atomically search a snapshot of the cache at a single point in time. + * For example, if a gap is created at index 10, then subsequently a gap is + * created at index 5, page_cache_prev_miss() covering both indices may + * return 5 if called under the rcu_read_lock. + * + * Return: The index of the gap if found, otherwise an index outside the + * range specified (in which case 'index - return >= max_scan' will be true). + * In the rare case of wrap-around, ULONG_MAX will be returned. */ -pgoff_t page_cache_prev_hole(struct address_space *mapping, +pgoff_t page_cache_prev_miss(struct address_space *mapping, pgoff_t index, unsigned long max_scan) { - unsigned long i; - - for (i = 0; i < max_scan; i++) { - struct page *page; + XA_STATE(xas, &mapping->i_pages, index); - page = radix_tree_lookup(&mapping->i_pages, index); - if (!page || xa_is_value(page)) + while (max_scan--) { + void *entry = xas_prev(&xas); + if (!entry || xa_is_value(entry)) break; - index--; - if (index == ULONG_MAX) + if (xas.xa_index == ULONG_MAX) break; } - return index; + return xas.xa_index; } -EXPORT_SYMBOL(page_cache_prev_hole); +EXPORT_SYMBOL(page_cache_prev_miss); /** * find_get_entry - find and get a page cache entry diff --git a/mm/readahead.c b/mm/readahead.c index de657077d41d..fc4dd364b37a 100644 --- a/mm/readahead.c +++ b/mm/readahead.c @@ -336,7 +336,7 @@ static pgoff_t count_history_pages(struct address_space *mapping, pgoff_t head; rcu_read_lock(); - head = page_cache_prev_hole(mapping, offset - 1, max); + head = page_cache_prev_miss(mapping, offset - 1, max); rcu_read_unlock(); return offset - 1 - head; @@ -425,7 +425,7 @@ ondemand_readahead(struct address_space *mapping, pgoff_t start; rcu_read_lock(); - start = page_cache_next_hole(mapping, offset + 1, max_pages); + start = page_cache_next_miss(mapping, offset + 1, max_pages); rcu_read_unlock(); if (!start || start - offset > max_pages) -- cgit v1.2.3 From 74d609585d8bd6083bd9d75bc1fd2c0d3851bcc5 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Fri, 17 Nov 2017 10:01:45 -0500 Subject: page cache: Add and replace pages using the XArray Use the XArray APIs to add and replace pages in the page cache. This removes two uses of the radix tree preload API and is significantly shorter code. It also removes the last user of __radix_tree_create() outside radix-tree.c itself, so make it static. Signed-off-by: Matthew Wilcox --- include/linux/radix-tree.h | 3 - include/linux/swap.h | 8 ++- lib/radix-tree.c | 6 +- mm/filemap.c | 139 +++++++++++++++++++-------------------------- 4 files changed, 66 insertions(+), 90 deletions(-) (limited to 'mm') diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h index 15388b7e38b9..d55de428a589 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -231,9 +231,6 @@ static inline int radix_tree_exception(void *arg) return unlikely((unsigned long)arg & RADIX_TREE_ENTRY_MASK); } -int __radix_tree_create(struct radix_tree_root *, unsigned long index, - unsigned order, struct radix_tree_node **nodep, - void __rcu ***slotp); int __radix_tree_insert(struct radix_tree_root *, unsigned long index, unsigned order, void *); static inline int radix_tree_insert(struct radix_tree_root *root, diff --git a/include/linux/swap.h b/include/linux/swap.h index 8e2c11e692ba..6ea50cf41b4c 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -299,8 +299,12 @@ void *workingset_eviction(struct address_space *mapping, struct page *page); bool workingset_refault(void *shadow); void workingset_activation(struct page *page); -/* Do not use directly, use workingset_lookup_update */ -void workingset_update_node(struct radix_tree_node *node); +/* Only track the nodes of mappings with shadow entries */ +void workingset_update_node(struct xa_node *node); +#define mapping_set_update(xas, mapping) do { \ + if (!dax_mapping(mapping) && !shmem_mapping(mapping)) \ + xas_set_update(xas, workingset_update_node); \ +} while (0) /* Returns workingset_update_node() if the mapping has shadow entries. */ #define workingset_lookup_update(mapping) \ diff --git a/lib/radix-tree.c b/lib/radix-tree.c index 68702061464f..8a58051eb5b3 100644 --- a/lib/radix-tree.c +++ b/lib/radix-tree.c @@ -700,9 +700,9 @@ static bool delete_node(struct radix_tree_root *root, * * Returns -ENOMEM, or 0 for success. */ -int __radix_tree_create(struct radix_tree_root *root, unsigned long index, - unsigned order, struct radix_tree_node **nodep, - void __rcu ***slotp) +static int __radix_tree_create(struct radix_tree_root *root, + unsigned long index, unsigned order, + struct radix_tree_node **nodep, void __rcu ***slotp) { struct radix_tree_node *node = NULL, *child; void __rcu **slot = (void __rcu **)&root->xa_head; diff --git a/mm/filemap.c b/mm/filemap.c index 714d3d0f60f5..b63caebd1367 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -111,35 +111,6 @@ * ->tasklist_lock (memory_failure, collect_procs_ao) */ -static int page_cache_tree_insert(struct address_space *mapping, - struct page *page, void **shadowp) -{ - struct radix_tree_node *node; - void **slot; - int error; - - error = __radix_tree_create(&mapping->i_pages, page->index, 0, - &node, &slot); - if (error) - return error; - if (*slot) { - void *p; - - p = radix_tree_deref_slot_protected(slot, - &mapping->i_pages.xa_lock); - if (!xa_is_value(p)) - return -EEXIST; - - mapping->nrexceptional--; - if (shadowp) - *shadowp = p; - } - __radix_tree_replace(&mapping->i_pages, node, slot, page, - workingset_lookup_update(mapping)); - mapping->nrpages++; - return 0; -} - static void page_cache_tree_delete(struct address_space *mapping, struct page *page, void *shadow) { @@ -775,51 +746,44 @@ EXPORT_SYMBOL(file_write_and_wait_range); * locked. This function does not add the new page to the LRU, the * caller must do that. * - * The remove + add is atomic. The only way this function can fail is - * memory allocation failure. + * The remove + add is atomic. This function cannot fail. */ int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask) { - int error; + struct address_space *mapping = old->mapping; + void (*freepage)(struct page *) = mapping->a_ops->freepage; + pgoff_t offset = old->index; + XA_STATE(xas, &mapping->i_pages, offset); + unsigned long flags; VM_BUG_ON_PAGE(!PageLocked(old), old); VM_BUG_ON_PAGE(!PageLocked(new), new); VM_BUG_ON_PAGE(new->mapping, new); - error = radix_tree_preload(gfp_mask & GFP_RECLAIM_MASK); - if (!error) { - struct address_space *mapping = old->mapping; - void (*freepage)(struct page *); - unsigned long flags; - - pgoff_t offset = old->index; - freepage = mapping->a_ops->freepage; + get_page(new); + new->mapping = mapping; + new->index = offset; - get_page(new); - new->mapping = mapping; - new->index = offset; + xas_lock_irqsave(&xas, flags); + xas_store(&xas, new); - xa_lock_irqsave(&mapping->i_pages, flags); - __delete_from_page_cache(old, NULL); - error = page_cache_tree_insert(mapping, new, NULL); - BUG_ON(error); - - /* - * hugetlb pages do not participate in page cache accounting. - */ - if (!PageHuge(new)) - __inc_node_page_state(new, NR_FILE_PAGES); - if (PageSwapBacked(new)) - __inc_node_page_state(new, NR_SHMEM); - xa_unlock_irqrestore(&mapping->i_pages, flags); - mem_cgroup_migrate(old, new); - radix_tree_preload_end(); - if (freepage) - freepage(old); - put_page(old); - } + old->mapping = NULL; + /* hugetlb pages do not participate in page cache accounting. */ + if (!PageHuge(old)) + __dec_node_page_state(new, NR_FILE_PAGES); + if (!PageHuge(new)) + __inc_node_page_state(new, NR_FILE_PAGES); + if (PageSwapBacked(old)) + __dec_node_page_state(new, NR_SHMEM); + if (PageSwapBacked(new)) + __inc_node_page_state(new, NR_SHMEM); + xas_unlock_irqrestore(&xas, flags); + mem_cgroup_migrate(old, new); + if (freepage) + freepage(old); + put_page(old); - return error; + return 0; } EXPORT_SYMBOL_GPL(replace_page_cache_page); @@ -828,12 +792,15 @@ static int __add_to_page_cache_locked(struct page *page, pgoff_t offset, gfp_t gfp_mask, void **shadowp) { + XA_STATE(xas, &mapping->i_pages, offset); int huge = PageHuge(page); struct mem_cgroup *memcg; int error; + void *old; VM_BUG_ON_PAGE(!PageLocked(page), page); VM_BUG_ON_PAGE(PageSwapBacked(page), page); + mapping_set_update(&xas, mapping); if (!huge) { error = mem_cgroup_try_charge(page, current->mm, @@ -842,39 +809,47 @@ static int __add_to_page_cache_locked(struct page *page, return error; } - error = radix_tree_maybe_preload(gfp_mask & GFP_RECLAIM_MASK); - if (error) { - if (!huge) - mem_cgroup_cancel_charge(page, memcg, false); - return error; - } - get_page(page); page->mapping = mapping; page->index = offset; - xa_lock_irq(&mapping->i_pages); - error = page_cache_tree_insert(mapping, page, shadowp); - radix_tree_preload_end(); - if (unlikely(error)) - goto err_insert; + do { + xas_lock_irq(&xas); + old = xas_load(&xas); + if (old && !xa_is_value(old)) + xas_set_err(&xas, -EEXIST); + xas_store(&xas, page); + if (xas_error(&xas)) + goto unlock; + + if (xa_is_value(old)) { + mapping->nrexceptional--; + if (shadowp) + *shadowp = old; + } + mapping->nrpages++; + + /* hugetlb pages do not participate in page cache accounting */ + if (!huge) + __inc_node_page_state(page, NR_FILE_PAGES); +unlock: + xas_unlock_irq(&xas); + } while (xas_nomem(&xas, gfp_mask & GFP_RECLAIM_MASK)); + + if (xas_error(&xas)) + goto error; - /* hugetlb pages do not participate in page cache accounting. */ - if (!huge) - __inc_node_page_state(page, NR_FILE_PAGES); - xa_unlock_irq(&mapping->i_pages); if (!huge) mem_cgroup_commit_charge(page, memcg, false, false); trace_mm_filemap_add_to_page_cache(page); return 0; -err_insert: +error: page->mapping = NULL; /* Leave page->index set: truncation relies upon it */ - xa_unlock_irq(&mapping->i_pages); if (!huge) mem_cgroup_cancel_charge(page, memcg, false); put_page(page); - return error; + return xas_error(&xas); } /** -- cgit v1.2.3 From 5c024e6a4ebc1740db9f0f075aaa476210108a97 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Tue, 21 Nov 2017 09:17:59 -0500 Subject: page cache: Convert page deletion to XArray The code is slightly shorter and simpler. Signed-off-by: Matthew Wilcox --- mm/filemap.c | 31 +++++++++++++------------------ 1 file changed, 13 insertions(+), 18 deletions(-) (limited to 'mm') diff --git a/mm/filemap.c b/mm/filemap.c index b63caebd1367..414efbdc95df 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -111,31 +111,26 @@ * ->tasklist_lock (memory_failure, collect_procs_ao) */ -static void page_cache_tree_delete(struct address_space *mapping, +static void page_cache_delete(struct address_space *mapping, struct page *page, void *shadow) { - int i, nr; + XA_STATE(xas, &mapping->i_pages, page->index); + unsigned int nr = 1; - /* hugetlb pages are represented by one entry in the radix tree */ - nr = PageHuge(page) ? 1 : hpage_nr_pages(page); + mapping_set_update(&xas, mapping); + + /* hugetlb pages are represented by a single entry in the xarray */ + if (!PageHuge(page)) { + xas_set_order(&xas, page->index, compound_order(page)); + nr = 1U << compound_order(page); + } VM_BUG_ON_PAGE(!PageLocked(page), page); VM_BUG_ON_PAGE(PageTail(page), page); VM_BUG_ON_PAGE(nr != 1 && shadow, page); - for (i = 0; i < nr; i++) { - struct radix_tree_node *node; - void **slot; - - __radix_tree_lookup(&mapping->i_pages, page->index + i, - &node, &slot); - - VM_BUG_ON_PAGE(!node && nr != 1, page); - - radix_tree_clear_tags(&mapping->i_pages, node, slot); - __radix_tree_replace(&mapping->i_pages, node, slot, shadow, - workingset_lookup_update(mapping)); - } + xas_store(&xas, shadow); + xas_init_marks(&xas); page->mapping = NULL; /* Leave page->index set: truncation lookup relies upon it */ @@ -234,7 +229,7 @@ void __delete_from_page_cache(struct page *page, void *shadow) trace_mm_filemap_delete_from_page_cache(page); unaccount_page_cache_page(mapping, page); - page_cache_tree_delete(mapping, page, shadow); + page_cache_delete(mapping, page, shadow); } static void page_cache_free_page(struct address_space *mapping, -- cgit v1.2.3 From 4c7472c0df2f889df417a37571e622e02b5058fe Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Wed, 16 May 2018 16:12:50 -0400 Subject: page cache: Convert find_get_entry to XArray Slightly shorter and simpler code. Signed-off-by: Matthew Wilcox --- mm/filemap.c | 63 +++++++++++++++++++++++++++--------------------------------- 1 file changed, 28 insertions(+), 35 deletions(-) (limited to 'mm') diff --git a/mm/filemap.c b/mm/filemap.c index 414efbdc95df..2bf9f0742082 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1382,47 +1382,40 @@ EXPORT_SYMBOL(page_cache_prev_miss); */ struct page *find_get_entry(struct address_space *mapping, pgoff_t offset) { - void **pagep; + XA_STATE(xas, &mapping->i_pages, offset); struct page *head, *page; rcu_read_lock(); repeat: - page = NULL; - pagep = radix_tree_lookup_slot(&mapping->i_pages, offset); - if (pagep) { - page = radix_tree_deref_slot(pagep); - if (unlikely(!page)) - goto out; - if (radix_tree_exception(page)) { - if (radix_tree_deref_retry(page)) - goto repeat; - /* - * A shadow entry of a recently evicted page, - * or a swap entry from shmem/tmpfs. Return - * it without attempting to raise page count. - */ - goto out; - } + xas_reset(&xas); + page = xas_load(&xas); + if (xas_retry(&xas, page)) + goto repeat; + /* + * A shadow entry of a recently evicted page, or a swap entry from + * shmem/tmpfs. Return it without attempting to raise page count. + */ + if (!page || xa_is_value(page)) + goto out; - head = compound_head(page); - if (!page_cache_get_speculative(head)) - goto repeat; + head = compound_head(page); + if (!page_cache_get_speculative(head)) + goto repeat; - /* The page was split under us? */ - if (compound_head(page) != head) { - put_page(head); - goto repeat; - } + /* The page was split under us? */ + if (compound_head(page) != head) { + put_page(head); + goto repeat; + } - /* - * Has the page moved? - * This is part of the lockless pagecache protocol. See - * include/linux/pagemap.h for details. - */ - if (unlikely(page != *pagep)) { - put_page(head); - goto repeat; - } + /* + * Has the page moved? + * This is part of the lockless pagecache protocol. See + * include/linux/pagemap.h for details. + */ + if (unlikely(page != xas_reload(&xas))) { + put_page(head); + goto repeat; } out: rcu_read_unlock(); @@ -1453,7 +1446,7 @@ struct page *find_lock_entry(struct address_space *mapping, pgoff_t offset) repeat: page = find_get_entry(mapping, offset); - if (page && !radix_tree_exception(page)) { + if (page && !xa_is_value(page)) { lock_page(page); /* Has the page been truncated? */ if (unlikely(page_mapping(page) != mapping)) { -- cgit v1.2.3 From f280bf092d48ff2db12b4a01127cd855c9e0ffb0 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Wed, 16 May 2018 17:20:45 -0400 Subject: page cache: Convert find_get_entries to XArray Slightly shorter and simpler code. Signed-off-by: Matthew Wilcox --- mm/filemap.c | 51 +++++++++++++++++++++++---------------------------- 1 file changed, 23 insertions(+), 28 deletions(-) (limited to 'mm') diff --git a/mm/filemap.c b/mm/filemap.c index 2bf9f0742082..4707156b9fbd 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1578,53 +1578,48 @@ unsigned find_get_entries(struct address_space *mapping, pgoff_t start, unsigned int nr_entries, struct page **entries, pgoff_t *indices) { - void **slot; + XA_STATE(xas, &mapping->i_pages, start); + struct page *page; unsigned int ret = 0; - struct radix_tree_iter iter; if (!nr_entries) return 0; rcu_read_lock(); - radix_tree_for_each_slot(slot, &mapping->i_pages, &iter, start) { - struct page *head, *page; -repeat: - page = radix_tree_deref_slot(slot); - if (unlikely(!page)) + xas_for_each(&xas, page, ULONG_MAX) { + struct page *head; + if (xas_retry(&xas, page)) continue; - if (radix_tree_exception(page)) { - if (radix_tree_deref_retry(page)) { - slot = radix_tree_iter_retry(&iter); - continue; - } - /* - * A shadow entry of a recently evicted page, a swap - * entry from shmem/tmpfs or a DAX entry. Return it - * without attempting to raise page count. - */ + /* + * A shadow entry of a recently evicted page, a swap + * entry from shmem/tmpfs or a DAX entry. Return it + * without attempting to raise page count. + */ + if (xa_is_value(page)) goto export; - } head = compound_head(page); if (!page_cache_get_speculative(head)) - goto repeat; + goto retry; /* The page was split under us? */ - if (compound_head(page) != head) { - put_page(head); - goto repeat; - } + if (compound_head(page) != head) + goto put_page; /* Has the page moved? */ - if (unlikely(page != *slot)) { - put_page(head); - goto repeat; - } + if (unlikely(page != xas_reload(&xas))) + goto put_page; + export: - indices[ret] = iter.index; + indices[ret] = xas.xa_index; entries[ret] = page; if (++ret == nr_entries) break; + continue; +put_page: + put_page(head); +retry: + xas_reset(&xas); } rcu_read_unlock(); return ret; -- cgit v1.2.3 From fd1b3cee2a867868d39bb8cbcc4b00c36d07cc01 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Wed, 16 May 2018 17:38:56 -0400 Subject: page cache: Convert find_get_pages_range to XArray The 'end' parameter of the xas_for_each iterator avoids a useless iteration at the end of the range. Signed-off-by: Matthew Wilcox --- mm/filemap.c | 52 +++++++++++++++++++--------------------------------- 1 file changed, 19 insertions(+), 33 deletions(-) (limited to 'mm') diff --git a/mm/filemap.c b/mm/filemap.c index 4707156b9fbd..b72c39fe61c2 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1650,64 +1650,50 @@ unsigned find_get_pages_range(struct address_space *mapping, pgoff_t *start, pgoff_t end, unsigned int nr_pages, struct page **pages) { - struct radix_tree_iter iter; - void **slot; + XA_STATE(xas, &mapping->i_pages, *start); + struct page *page; unsigned ret = 0; if (unlikely(!nr_pages)) return 0; rcu_read_lock(); - radix_tree_for_each_slot(slot, &mapping->i_pages, &iter, *start) { - struct page *head, *page; - - if (iter.index > end) - break; -repeat: - page = radix_tree_deref_slot(slot); - if (unlikely(!page)) + xas_for_each(&xas, page, end) { + struct page *head; + if (xas_retry(&xas, page)) continue; - - if (radix_tree_exception(page)) { - if (radix_tree_deref_retry(page)) { - slot = radix_tree_iter_retry(&iter); - continue; - } - /* - * A shadow entry of a recently evicted page, - * or a swap entry from shmem/tmpfs. Skip - * over it. - */ + /* Skip over shadow, swap and DAX entries */ + if (xa_is_value(page)) continue; - } head = compound_head(page); if (!page_cache_get_speculative(head)) - goto repeat; + goto retry; /* The page was split under us? */ - if (compound_head(page) != head) { - put_page(head); - goto repeat; - } + if (compound_head(page) != head) + goto put_page; /* Has the page moved? */ - if (unlikely(page != *slot)) { - put_page(head); - goto repeat; - } + if (unlikely(page != xas_reload(&xas))) + goto put_page; pages[ret] = page; if (++ret == nr_pages) { - *start = pages[ret - 1]->index + 1; + *start = page->index + 1; goto out; } + continue; +put_page: + put_page(head); +retry: + xas_reset(&xas); } /* * We come here when there is no page beyond @end. We take care to not * overflow the index @start as it confuses some of the callers. This - * breaks the iteration when there is page at index -1 but that is + * breaks the iteration when there is a page at index -1 but that is * already broken anyway. */ if (end == (pgoff_t)-1) -- cgit v1.2.3 From 3ece58a270cd1e5026282abe778bd50db7a11d08 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Wed, 16 May 2018 18:00:33 -0400 Subject: page cache: Convert find_get_pages_contig to XArray There's no direct replacement for radix_tree_for_each_contig() in the XArray API as it's an unusual thing to do. Instead, open-code a loop using xas_next(). This removes the only user of radix_tree_for_each_contig() so delete the iterator from the API and the test suite code for it. Signed-off-by: Matthew Wilcox --- .clang-format | 1 - include/linux/radix-tree.h | 17 ----------- mm/filemap.c | 53 ++++++++++++++-------------------- tools/testing/radix-tree/regression3.c | 23 --------------- 4 files changed, 22 insertions(+), 72 deletions(-) (limited to 'mm') diff --git a/.clang-format b/.clang-format index 1d5da22e0ba5..e6080f5834a3 100644 --- a/.clang-format +++ b/.clang-format @@ -323,7 +323,6 @@ ForEachMacros: - 'protocol_for_each_card' - 'protocol_for_each_dev' - 'queue_for_each_hw_ctx' - - 'radix_tree_for_each_contig' - 'radix_tree_for_each_slot' - 'radix_tree_for_each_tagged' - 'rbtree_postorder_for_each_entry_safe' diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h index d55de428a589..023e888e1163 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -522,23 +522,6 @@ static __always_inline void __rcu **radix_tree_next_slot(void __rcu **slot, slot || (slot = radix_tree_next_chunk(root, iter, 0)) ; \ slot = radix_tree_next_slot(slot, iter, 0)) -/** - * radix_tree_for_each_contig - iterate over contiguous slots - * - * @slot: the void** variable for pointer to slot - * @root: the struct radix_tree_root pointer - * @iter: the struct radix_tree_iter pointer - * @start: iteration starting index - * - * @slot points to radix tree slot, @iter->index contains its index. - */ -#define radix_tree_for_each_contig(slot, root, iter, start) \ - for (slot = radix_tree_iter_init(iter, start) ; \ - slot || (slot = radix_tree_next_chunk(root, iter, \ - RADIX_TREE_ITER_CONTIG)) ; \ - slot = radix_tree_next_slot(slot, iter, \ - RADIX_TREE_ITER_CONTIG)) - /** * radix_tree_for_each_tagged - iterate over tagged slots * diff --git a/mm/filemap.c b/mm/filemap.c index b72c39fe61c2..089b67598100 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1721,57 +1721,43 @@ out: unsigned find_get_pages_contig(struct address_space *mapping, pgoff_t index, unsigned int nr_pages, struct page **pages) { - struct radix_tree_iter iter; - void **slot; + XA_STATE(xas, &mapping->i_pages, index); + struct page *page; unsigned int ret = 0; if (unlikely(!nr_pages)) return 0; rcu_read_lock(); - radix_tree_for_each_contig(slot, &mapping->i_pages, &iter, index) { - struct page *head, *page; -repeat: - page = radix_tree_deref_slot(slot); - /* The hole, there no reason to continue */ - if (unlikely(!page)) - break; - - if (radix_tree_exception(page)) { - if (radix_tree_deref_retry(page)) { - slot = radix_tree_iter_retry(&iter); - continue; - } - /* - * A shadow entry of a recently evicted page, - * or a swap entry from shmem/tmpfs. Stop - * looking for contiguous pages. - */ + for (page = xas_load(&xas); page; page = xas_next(&xas)) { + struct page *head; + if (xas_retry(&xas, page)) + continue; + /* + * If the entry has been swapped out, we can stop looking. + * No current caller is looking for DAX entries. + */ + if (xa_is_value(page)) break; - } head = compound_head(page); if (!page_cache_get_speculative(head)) - goto repeat; + goto retry; /* The page was split under us? */ - if (compound_head(page) != head) { - put_page(head); - goto repeat; - } + if (compound_head(page) != head) + goto put_page; /* Has the page moved? */ - if (unlikely(page != *slot)) { - put_page(head); - goto repeat; - } + if (unlikely(page != xas_reload(&xas))) + goto put_page; /* * must check mapping and index after taking the ref. * otherwise we can get both false positives and false * negatives, which is just confusing to the caller. */ - if (page->mapping == NULL || page_to_pgoff(page) != iter.index) { + if (!page->mapping || page_to_pgoff(page) != xas.xa_index) { put_page(page); break; } @@ -1779,6 +1765,11 @@ repeat: pages[ret] = page; if (++ret == nr_pages) break; + continue; +put_page: + put_page(head); +retry: + xas_reset(&xas); } rcu_read_unlock(); return ret; diff --git a/tools/testing/radix-tree/regression3.c b/tools/testing/radix-tree/regression3.c index ace2543c3eda..9f9a3b280f56 100644 --- a/tools/testing/radix-tree/regression3.c +++ b/tools/testing/radix-tree/regression3.c @@ -69,21 +69,6 @@ void regression3_test(void) continue; } } - radix_tree_delete(&root, 1); - - first = true; - radix_tree_for_each_contig(slot, &root, &iter, 0) { - printv(2, "contig %ld %p\n", iter.index, *slot); - if (first) { - radix_tree_insert(&root, 1, ptr); - first = false; - } - if (radix_tree_deref_retry(*slot)) { - printv(2, "retry at %ld\n", iter.index); - slot = radix_tree_iter_retry(&iter); - continue; - } - } radix_tree_for_each_slot(slot, &root, &iter, 0) { printv(2, "slot %ld %p\n", iter.index, *slot); @@ -93,14 +78,6 @@ void regression3_test(void) } } - radix_tree_for_each_contig(slot, &root, &iter, 0) { - printv(2, "contig %ld %p\n", iter.index, *slot); - if (!iter.index) { - printv(2, "next at %ld\n", iter.index); - slot = radix_tree_iter_resume(slot, &iter); - } - } - radix_tree_tag_set(&root, 0, 0); radix_tree_tag_set(&root, 1, 0); radix_tree_for_each_tagged(slot, &root, &iter, 0, 0) { -- cgit v1.2.3 From a6906972fe67fb6f73ba04088f7897227fd1cd8f Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Wed, 16 May 2018 18:12:54 -0400 Subject: page cache; Convert find_get_pages_range_tag to XArray The 'end' parameter of the xas_for_each iterator avoids a useless iteration at the end of the range. Signed-off-by: Matthew Wilcox --- include/linux/pagemap.h | 4 +-- mm/filemap.c | 68 +++++++++++++++++++------------------------------ 2 files changed, 28 insertions(+), 44 deletions(-) (limited to 'mm') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index cf9ad413eee9..c9bbb9a05764 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -363,10 +363,10 @@ static inline unsigned find_get_pages(struct address_space *mapping, unsigned find_get_pages_contig(struct address_space *mapping, pgoff_t start, unsigned int nr_pages, struct page **pages); unsigned find_get_pages_range_tag(struct address_space *mapping, pgoff_t *index, - pgoff_t end, int tag, unsigned int nr_pages, + pgoff_t end, xa_mark_t tag, unsigned int nr_pages, struct page **pages); static inline unsigned find_get_pages_tag(struct address_space *mapping, - pgoff_t *index, int tag, unsigned int nr_pages, + pgoff_t *index, xa_mark_t tag, unsigned int nr_pages, struct page **pages) { return find_get_pages_range_tag(mapping, index, (pgoff_t)-1, tag, diff --git a/mm/filemap.c b/mm/filemap.c index 089b67598100..0df28aa6411c 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1789,74 +1789,58 @@ EXPORT_SYMBOL(find_get_pages_contig); * @tag. We update @index to index the next page for the traversal. */ unsigned find_get_pages_range_tag(struct address_space *mapping, pgoff_t *index, - pgoff_t end, int tag, unsigned int nr_pages, + pgoff_t end, xa_mark_t tag, unsigned int nr_pages, struct page **pages) { - struct radix_tree_iter iter; - void **slot; + XA_STATE(xas, &mapping->i_pages, *index); + struct page *page; unsigned ret = 0; if (unlikely(!nr_pages)) return 0; rcu_read_lock(); - radix_tree_for_each_tagged(slot, &mapping->i_pages, &iter, *index, tag) { - struct page *head, *page; - - if (iter.index > end) - break; -repeat: - page = radix_tree_deref_slot(slot); - if (unlikely(!page)) + xas_for_each_marked(&xas, page, end, tag) { + struct page *head; + if (xas_retry(&xas, page)) continue; - - if (radix_tree_exception(page)) { - if (radix_tree_deref_retry(page)) { - slot = radix_tree_iter_retry(&iter); - continue; - } - /* - * A shadow entry of a recently evicted page. - * - * Those entries should never be tagged, but - * this tree walk is lockless and the tags are - * looked up in bulk, one radix tree node at a - * time, so there is a sizable window for page - * reclaim to evict a page we saw tagged. - * - * Skip over it. - */ + /* + * Shadow entries should never be tagged, but this iteration + * is lockless so there is a window for page reclaim to evict + * a page we saw tagged. Skip over it. + */ + if (xa_is_value(page)) continue; - } head = compound_head(page); if (!page_cache_get_speculative(head)) - goto repeat; + goto retry; /* The page was split under us? */ - if (compound_head(page) != head) { - put_page(head); - goto repeat; - } + if (compound_head(page) != head) + goto put_page; /* Has the page moved? */ - if (unlikely(page != *slot)) { - put_page(head); - goto repeat; - } + if (unlikely(page != xas_reload(&xas))) + goto put_page; pages[ret] = page; if (++ret == nr_pages) { - *index = pages[ret - 1]->index + 1; + *index = page->index + 1; goto out; } + continue; +put_page: + put_page(head); +retry: + xas_reset(&xas); } /* - * We come here when we got at @end. We take care to not overflow the + * We come here when we got to @end. We take care to not overflow the * index @index as it confuses some of the callers. This breaks the - * iteration when there is page at index -1 but that is already broken - * anyway. + * iteration when there is a page at index -1 but that is already + * broken anyway. */ if (end == (pgoff_t)-1) *index = (pgoff_t)-1; -- cgit v1.2.3 From c1901cd33cf407d77a181f8dd4ffff98041ef480 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Wed, 16 May 2018 23:56:04 -0400 Subject: page cache: Convert find_get_entries_tag to XArray Slightly shorter and simpler code. Signed-off-by: Matthew Wilcox --- include/linux/pagemap.h | 2 +- mm/filemap.c | 54 ++++++++++++++++++++++--------------------------- 2 files changed, 25 insertions(+), 31 deletions(-) (limited to 'mm') diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index c9bbb9a05764..226f96f0dee0 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -373,7 +373,7 @@ static inline unsigned find_get_pages_tag(struct address_space *mapping, nr_pages, pages); } unsigned find_get_entries_tag(struct address_space *mapping, pgoff_t start, - int tag, unsigned int nr_entries, + xa_mark_t tag, unsigned int nr_entries, struct page **entries, pgoff_t *indices); struct page *grab_cache_page_write_begin(struct address_space *mapping, diff --git a/mm/filemap.c b/mm/filemap.c index 0df28aa6411c..35ae011971e1 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1866,57 +1866,51 @@ EXPORT_SYMBOL(find_get_pages_range_tag); * @tag. */ unsigned find_get_entries_tag(struct address_space *mapping, pgoff_t start, - int tag, unsigned int nr_entries, + xa_mark_t tag, unsigned int nr_entries, struct page **entries, pgoff_t *indices) { - void **slot; + XA_STATE(xas, &mapping->i_pages, start); + struct page *page; unsigned int ret = 0; - struct radix_tree_iter iter; if (!nr_entries) return 0; rcu_read_lock(); - radix_tree_for_each_tagged(slot, &mapping->i_pages, &iter, start, tag) { - struct page *head, *page; -repeat: - page = radix_tree_deref_slot(slot); - if (unlikely(!page)) + xas_for_each_marked(&xas, page, ULONG_MAX, tag) { + struct page *head; + if (xas_retry(&xas, page)) continue; - if (radix_tree_exception(page)) { - if (radix_tree_deref_retry(page)) { - slot = radix_tree_iter_retry(&iter); - continue; - } - - /* - * A shadow entry of a recently evicted page, a swap - * entry from shmem/tmpfs or a DAX entry. Return it - * without attempting to raise page count. - */ + /* + * A shadow entry of a recently evicted page, a swap + * entry from shmem/tmpfs or a DAX entry. Return it + * without attempting to raise page count. + */ + if (xa_is_value(page)) goto export; - } head = compound_head(page); if (!page_cache_get_speculative(head)) - goto repeat; + goto retry; /* The page was split under us? */ - if (compound_head(page) != head) { - put_page(head); - goto repeat; - } + if (compound_head(page) != head) + goto put_page; /* Has the page moved? */ - if (unlikely(page != *slot)) { - put_page(head); - goto repeat; - } + if (unlikely(page != xas_reload(&xas))) + goto put_page; + export: - indices[ret] = iter.index; + indices[ret] = xas.xa_index; entries[ret] = page; if (++ret == nr_entries) break; + continue; +put_page: + put_page(head); +retry: + xas_reset(&xas); } rcu_read_unlock(); return ret; -- cgit v1.2.3 From 070e807c690bf9a648d4a878f3c68ea9f5f5ce14 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Thu, 17 May 2018 00:08:30 -0400 Subject: page cache: Convert filemap_map_pages to XArray Slight change of strategy here; if we have trouble getting hold of a page for whatever reason (eg a compound page is split underneath us), don't spin to stabilise the page, just continue the iteration, like we would if we failed to trylock the page. Since this is a speculative optimisation, it feels like we should allow the process to take an extra fault if it turns out to need this page instead of spending time to pin down a page it may not need. Signed-off-by: Matthew Wilcox --- mm/filemap.c | 42 +++++++++++++----------------------------- 1 file changed, 13 insertions(+), 29 deletions(-) (limited to 'mm') diff --git a/mm/filemap.c b/mm/filemap.c index 35ae011971e1..ae1fcaa24f97 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -2516,45 +2516,31 @@ EXPORT_SYMBOL(filemap_fault); void filemap_map_pages(struct vm_fault *vmf, pgoff_t start_pgoff, pgoff_t end_pgoff) { - struct radix_tree_iter iter; - void **slot; struct file *file = vmf->vma->vm_file; struct address_space *mapping = file->f_mapping; pgoff_t last_pgoff = start_pgoff; unsigned long max_idx; + XA_STATE(xas, &mapping->i_pages, start_pgoff); struct page *head, *page; rcu_read_lock(); - radix_tree_for_each_slot(slot, &mapping->i_pages, &iter, start_pgoff) { - if (iter.index > end_pgoff) - break; -repeat: - page = radix_tree_deref_slot(slot); - if (unlikely(!page)) - goto next; - if (radix_tree_exception(page)) { - if (radix_tree_deref_retry(page)) { - slot = radix_tree_iter_retry(&iter); - continue; - } + xas_for_each(&xas, page, end_pgoff) { + if (xas_retry(&xas, page)) + continue; + if (xa_is_value(page)) goto next; - } head = compound_head(page); if (!page_cache_get_speculative(head)) - goto repeat; + goto next; /* The page was split under us? */ - if (compound_head(page) != head) { - put_page(head); - goto repeat; - } + if (compound_head(page) != head) + goto skip; /* Has the page moved? */ - if (unlikely(page != *slot)) { - put_page(head); - goto repeat; - } + if (unlikely(page != xas_reload(&xas))) + goto skip; if (!PageUptodate(page) || PageReadahead(page) || @@ -2573,10 +2559,10 @@ repeat: if (file->f_ra.mmap_miss > 0) file->f_ra.mmap_miss--; - vmf->address += (iter.index - last_pgoff) << PAGE_SHIFT; + vmf->address += (xas.xa_index - last_pgoff) << PAGE_SHIFT; if (vmf->pte) - vmf->pte += iter.index - last_pgoff; - last_pgoff = iter.index; + vmf->pte += xas.xa_index - last_pgoff; + last_pgoff = xas.xa_index; if (alloc_set_pte(vmf, NULL, page)) goto unlock; unlock_page(page); @@ -2589,8 +2575,6 @@ next: /* Huge page is mapped? No need to proceed. */ if (pmd_trans_huge(*vmf->pmd)) break; - if (iter.index == end_pgoff) - break; } rcu_read_unlock(); } -- cgit v1.2.3 From ef8e5717db01bfa4f425d2cda551a6fccc85529d Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Mon, 4 Dec 2017 03:59:45 -0500 Subject: page cache: Convert delete_batch to XArray Rename the function from page_cache_tree_delete_batch to just page_cache_delete_batch. Signed-off-by: Matthew Wilcox --- mm/filemap.c | 28 +++++++++++++--------------- 1 file changed, 13 insertions(+), 15 deletions(-) (limited to 'mm') diff --git a/mm/filemap.c b/mm/filemap.c index ae1fcaa24f97..f7f9af1d98b0 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -272,7 +272,7 @@ void delete_from_page_cache(struct page *page) EXPORT_SYMBOL(delete_from_page_cache); /* - * page_cache_tree_delete_batch - delete several pages from page cache + * page_cache_delete_batch - delete several pages from page cache * @mapping: the mapping to which pages belong * @pvec: pagevec with pages to delete * @@ -285,23 +285,18 @@ EXPORT_SYMBOL(delete_from_page_cache); * * The function expects the i_pages lock to be held. */ -static void -page_cache_tree_delete_batch(struct address_space *mapping, +static void page_cache_delete_batch(struct address_space *mapping, struct pagevec *pvec) { - struct radix_tree_iter iter; - void **slot; + XA_STATE(xas, &mapping->i_pages, pvec->pages[0]->index); int total_pages = 0; int i = 0, tail_pages = 0; struct page *page; - pgoff_t start; - start = pvec->pages[0]->index; - radix_tree_for_each_slot(slot, &mapping->i_pages, &iter, start) { + mapping_set_update(&xas, mapping); + xas_for_each(&xas, page, ULONG_MAX) { if (i >= pagevec_count(pvec) && !tail_pages) break; - page = radix_tree_deref_slot_protected(slot, - &mapping->i_pages.xa_lock); if (xa_is_value(page)) continue; if (!tail_pages) { @@ -310,8 +305,11 @@ page_cache_tree_delete_batch(struct address_space *mapping, * have our pages locked so they are protected from * being removed. */ - if (page != pvec->pages[i]) + if (page != pvec->pages[i]) { + VM_BUG_ON_PAGE(page->index > + pvec->pages[i]->index, page); continue; + } WARN_ON_ONCE(!PageLocked(page)); if (PageTransHuge(page) && !PageHuge(page)) tail_pages = HPAGE_PMD_NR - 1; @@ -322,11 +320,11 @@ page_cache_tree_delete_batch(struct address_space *mapping, */ i++; } else { + VM_BUG_ON_PAGE(page->index + HPAGE_PMD_NR - tail_pages + != pvec->pages[i]->index, page); tail_pages--; } - radix_tree_clear_tags(&mapping->i_pages, iter.node, slot); - __radix_tree_replace(&mapping->i_pages, iter.node, slot, NULL, - workingset_lookup_update(mapping)); + xas_store(&xas, NULL); total_pages++; } mapping->nrpages -= total_pages; @@ -347,7 +345,7 @@ void delete_from_page_cache_batch(struct address_space *mapping, unaccount_page_cache_page(mapping, pvec->pages[i]); } - page_cache_tree_delete_batch(mapping, pvec); + page_cache_delete_batch(mapping, pvec); xa_unlock_irqrestore(&mapping->i_pages, flags); for (i = 0; i < pagevec_count(pvec); i++) -- cgit v1.2.3 From 22ecdb4f8b7dbfefa3deaf6b144093b5c4cd2aff Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Mon, 4 Dec 2017 04:02:00 -0500 Subject: page cache: Remove stray radix comment Signed-off-by: Matthew Wilcox --- mm/filemap.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'mm') diff --git a/mm/filemap.c b/mm/filemap.c index f7f9af1d98b0..bedd8680f789 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -2682,7 +2682,7 @@ repeat: put_page(page); if (err == -EEXIST) goto repeat; - /* Presumably ENOMEM for radix tree node */ + /* Presumably ENOMEM for xarray node */ return ERR_PTR(err); } -- cgit v1.2.3 From 8fa8e538e4be359e9042573737632dda35a8700d Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Tue, 16 Jan 2018 06:26:49 -0500 Subject: page cache: Convert filemap_range_has_page to XArray Instead of calling find_get_pages_range() and putting any reference, use xas_find() to iterate over any entries in the range, skipping the shadow/swap entries. Signed-off-by: Matthew Wilcox --- mm/filemap.c | 27 +++++++++++++++++++-------- 1 file changed, 19 insertions(+), 8 deletions(-) (limited to 'mm') diff --git a/mm/filemap.c b/mm/filemap.c index bedd8680f789..6b36516bc31d 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -455,20 +455,31 @@ EXPORT_SYMBOL(filemap_flush); bool filemap_range_has_page(struct address_space *mapping, loff_t start_byte, loff_t end_byte) { - pgoff_t index = start_byte >> PAGE_SHIFT; - pgoff_t end = end_byte >> PAGE_SHIFT; struct page *page; + XA_STATE(xas, &mapping->i_pages, start_byte >> PAGE_SHIFT); + pgoff_t max = end_byte >> PAGE_SHIFT; if (end_byte < start_byte) return false; - if (mapping->nrpages == 0) - return false; + rcu_read_lock(); + for (;;) { + page = xas_find(&xas, max); + if (xas_retry(&xas, page)) + continue; + /* Shadow entries don't count */ + if (xa_is_value(page)) + continue; + /* + * We don't need to try to pin this page; we're about to + * release the RCU lock anyway. It is enough to know that + * there was a page here recently. + */ + break; + } + rcu_read_unlock(); - if (!find_get_pages_range(mapping, &index, end, 1, &page)) - return false; - put_page(page); - return true; + return page != NULL; } EXPORT_SYMBOL(filemap_range_has_page); -- cgit v1.2.3 From ff9c745b81ff1e482167fd73558450e66ad43a33 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Wed, 22 Nov 2017 11:41:23 -0500 Subject: mm: Convert page-writeback to XArray Includes moving mapping_tagged() to fs.h as a static inline, and changing it to return bool. Signed-off-by: Matthew Wilcox --- include/linux/fs.h | 17 +++++++------ mm/page-writeback.c | 72 +++++++++++++++++++---------------------------------- 2 files changed, 36 insertions(+), 53 deletions(-) (limited to 'mm') diff --git a/include/linux/fs.h b/include/linux/fs.h index d126cad0f621..e10278e4db66 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -483,15 +483,18 @@ struct block_device { struct mutex bd_fsfreeze_mutex; } __randomize_layout; +/* XArray tags, for tagging dirty and writeback pages in the pagecache. */ +#define PAGECACHE_TAG_DIRTY XA_MARK_0 +#define PAGECACHE_TAG_WRITEBACK XA_MARK_1 +#define PAGECACHE_TAG_TOWRITE XA_MARK_2 + /* - * Radix-tree tags, for tagging dirty and writeback pages within the pagecache - * radix trees + * Returns true if any of the pages in the mapping are marked with the tag. */ -#define PAGECACHE_TAG_DIRTY 0 -#define PAGECACHE_TAG_WRITEBACK 1 -#define PAGECACHE_TAG_TOWRITE 2 - -int mapping_tagged(struct address_space *mapping, int tag); +static inline bool mapping_tagged(struct address_space *mapping, xa_mark_t tag) +{ + return xa_marked(&mapping->i_pages, tag); +} static inline void i_mmap_lock_write(struct address_space *mapping) { diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 84ae9bf5858a..fc6e5743b0bf 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -2097,34 +2097,25 @@ void __init page_writeback_init(void) * dirty pages in the file (thus it is important for this function to be quick * so that it can tag pages faster than a dirtying process can create them). */ -/* - * We tag pages in batches of WRITEBACK_TAG_BATCH to reduce the i_pages lock - * latency. - */ void tag_pages_for_writeback(struct address_space *mapping, pgoff_t start, pgoff_t end) { -#define WRITEBACK_TAG_BATCH 4096 - unsigned long tagged = 0; - struct radix_tree_iter iter; - void **slot; + XA_STATE(xas, &mapping->i_pages, start); + unsigned int tagged = 0; + void *page; - xa_lock_irq(&mapping->i_pages); - radix_tree_for_each_tagged(slot, &mapping->i_pages, &iter, start, - PAGECACHE_TAG_DIRTY) { - if (iter.index > end) - break; - radix_tree_iter_tag_set(&mapping->i_pages, &iter, - PAGECACHE_TAG_TOWRITE); - tagged++; - if ((tagged % WRITEBACK_TAG_BATCH) != 0) + xas_lock_irq(&xas); + xas_for_each_marked(&xas, page, end, PAGECACHE_TAG_DIRTY) { + xas_set_mark(&xas, PAGECACHE_TAG_TOWRITE); + if (++tagged % XA_CHECK_SCHED) continue; - slot = radix_tree_iter_resume(slot, &iter); - xa_unlock_irq(&mapping->i_pages); + + xas_pause(&xas); + xas_unlock_irq(&xas); cond_resched(); - xa_lock_irq(&mapping->i_pages); + xas_lock_irq(&xas); } - xa_unlock_irq(&mapping->i_pages); + xas_unlock_irq(&xas); } EXPORT_SYMBOL(tag_pages_for_writeback); @@ -2164,7 +2155,7 @@ int write_cache_pages(struct address_space *mapping, pgoff_t done_index; int cycled; int range_whole = 0; - int tag; + xa_mark_t tag; pagevec_init(&pvec); if (wbc->range_cyclic) { @@ -2445,7 +2436,7 @@ void account_page_cleaned(struct page *page, struct address_space *mapping, /* * For address_spaces which do not use buffers. Just tag the page as dirty in - * its radix tree. + * the xarray. * * This is also used when a single buffer is being dirtied: we want to set the * page dirty in that case, but not all the buffers. This is a "bottom-up" @@ -2471,7 +2462,7 @@ int __set_page_dirty_nobuffers(struct page *page) BUG_ON(page_mapping(page) != mapping); WARN_ON_ONCE(!PagePrivate(page) && !PageUptodate(page)); account_page_dirtied(page, mapping); - radix_tree_tag_set(&mapping->i_pages, page_index(page), + __xa_set_mark(&mapping->i_pages, page_index(page), PAGECACHE_TAG_DIRTY); xa_unlock_irqrestore(&mapping->i_pages, flags); unlock_page_memcg(page); @@ -2634,13 +2625,13 @@ EXPORT_SYMBOL(__cancel_dirty_page); * Returns true if the page was previously dirty. * * This is for preparing to put the page under writeout. We leave the page - * tagged as dirty in the radix tree so that a concurrent write-for-sync + * tagged as dirty in the xarray so that a concurrent write-for-sync * can discover it via a PAGECACHE_TAG_DIRTY walk. The ->writepage * implementation will run either set_page_writeback() or set_page_dirty(), - * at which stage we bring the page's dirty flag and radix-tree dirty tag + * at which stage we bring the page's dirty flag and xarray dirty tag * back into sync. * - * This incoherency between the page's dirty flag and radix-tree tag is + * This incoherency between the page's dirty flag and xarray tag is * unfortunate, but it only exists while the page is locked. */ int clear_page_dirty_for_io(struct page *page) @@ -2721,7 +2712,7 @@ int test_clear_page_writeback(struct page *page) xa_lock_irqsave(&mapping->i_pages, flags); ret = TestClearPageWriteback(page); if (ret) { - radix_tree_tag_clear(&mapping->i_pages, page_index(page), + __xa_clear_mark(&mapping->i_pages, page_index(page), PAGECACHE_TAG_WRITEBACK); if (bdi_cap_account_writeback(bdi)) { struct bdi_writeback *wb = inode_to_wb(inode); @@ -2761,11 +2752,13 @@ int __test_set_page_writeback(struct page *page, bool keep_write) lock_page_memcg(page); if (mapping && mapping_use_writeback_tags(mapping)) { + XA_STATE(xas, &mapping->i_pages, page_index(page)); struct inode *inode = mapping->host; struct backing_dev_info *bdi = inode_to_bdi(inode); unsigned long flags; - xa_lock_irqsave(&mapping->i_pages, flags); + xas_lock_irqsave(&xas, flags); + xas_load(&xas); ret = TestSetPageWriteback(page); if (!ret) { bool on_wblist; @@ -2773,8 +2766,7 @@ int __test_set_page_writeback(struct page *page, bool keep_write) on_wblist = mapping_tagged(mapping, PAGECACHE_TAG_WRITEBACK); - radix_tree_tag_set(&mapping->i_pages, page_index(page), - PAGECACHE_TAG_WRITEBACK); + xas_set_mark(&xas, PAGECACHE_TAG_WRITEBACK); if (bdi_cap_account_writeback(bdi)) inc_wb_stat(inode_to_wb(inode), WB_WRITEBACK); @@ -2787,12 +2779,10 @@ int __test_set_page_writeback(struct page *page, bool keep_write) sb_mark_inode_writeback(mapping->host); } if (!PageDirty(page)) - radix_tree_tag_clear(&mapping->i_pages, page_index(page), - PAGECACHE_TAG_DIRTY); + xas_clear_mark(&xas, PAGECACHE_TAG_DIRTY); if (!keep_write) - radix_tree_tag_clear(&mapping->i_pages, page_index(page), - PAGECACHE_TAG_TOWRITE); - xa_unlock_irqrestore(&mapping->i_pages, flags); + xas_clear_mark(&xas, PAGECACHE_TAG_TOWRITE); + xas_unlock_irqrestore(&xas, flags); } else { ret = TestSetPageWriteback(page); } @@ -2806,16 +2796,6 @@ int __test_set_page_writeback(struct page *page, bool keep_write) } EXPORT_SYMBOL(__test_set_page_writeback); -/* - * Return true if any of the pages in the mapping are marked with the - * passed tag. - */ -int mapping_tagged(struct address_space *mapping, int tag) -{ - return radix_tree_tagged(&mapping->i_pages, tag); -} -EXPORT_SYMBOL(mapping_tagged); - /** * wait_for_stable_page() - wait for writeback to finish, if necessary. * @page: The page to wait on. -- cgit v1.2.3 From a97e7904c0806309fd77103005bb7820c3f1c5e4 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Fri, 24 Nov 2017 14:24:59 -0500 Subject: mm: Convert workingset to XArray We construct an XA_STATE and use it to delete the node with xas_store() rather than adding a special function for this unique use case. Includes a test that simulates this usage for the test suite. Signed-off-by: Matthew Wilcox --- include/linux/swap.h | 9 -------- lib/test_xarray.c | 65 ++++++++++++++++++++++++++++++++++++++++++++++++++++ mm/workingset.c | 51 +++++++++++++++++------------------------ 3 files changed, 86 insertions(+), 39 deletions(-) (limited to 'mm') diff --git a/include/linux/swap.h b/include/linux/swap.h index 6ea50cf41b4c..112cebcf0402 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -306,15 +306,6 @@ void workingset_update_node(struct xa_node *node); xas_set_update(xas, workingset_update_node); \ } while (0) -/* Returns workingset_update_node() if the mapping has shadow entries. */ -#define workingset_lookup_update(mapping) \ -({ \ - radix_tree_update_node_t __helper = workingset_update_node; \ - if (dax_mapping(mapping) || shmem_mapping(mapping)) \ - __helper = NULL; \ - __helper; \ -}) - /* linux/mm/page_alloc.c */ extern unsigned long totalram_pages; extern unsigned long totalreserve_pages; diff --git a/lib/test_xarray.c b/lib/test_xarray.c index a752e6a37e6f..128c6489082f 100644 --- a/lib/test_xarray.c +++ b/lib/test_xarray.c @@ -863,6 +863,67 @@ static noinline void check_create_range(struct xarray *xa) check_create_range_3(); } +static LIST_HEAD(shadow_nodes); + +static void test_update_node(struct xa_node *node) +{ + if (node->count && node->count == node->nr_values) { + if (list_empty(&node->private_list)) + list_add(&shadow_nodes, &node->private_list); + } else { + if (!list_empty(&node->private_list)) + list_del_init(&node->private_list); + } +} + +static noinline void shadow_remove(struct xarray *xa) +{ + struct xa_node *node; + + xa_lock(xa); + while ((node = list_first_entry_or_null(&shadow_nodes, + struct xa_node, private_list))) { + XA_STATE(xas, node->array, 0); + XA_BUG_ON(xa, node->array != xa); + list_del_init(&node->private_list); + xas.xa_node = xa_parent_locked(node->array, node); + xas.xa_offset = node->offset; + xas.xa_shift = node->shift + XA_CHUNK_SHIFT; + xas_set_update(&xas, test_update_node); + xas_store(&xas, NULL); + } + xa_unlock(xa); +} + +static noinline void check_workingset(struct xarray *xa, unsigned long index) +{ + XA_STATE(xas, xa, index); + xas_set_update(&xas, test_update_node); + + do { + xas_lock(&xas); + xas_store(&xas, xa_mk_value(0)); + xas_next(&xas); + xas_store(&xas, xa_mk_value(1)); + xas_unlock(&xas); + } while (xas_nomem(&xas, GFP_KERNEL)); + + XA_BUG_ON(xa, list_empty(&shadow_nodes)); + + xas_lock(&xas); + xas_next(&xas); + xas_store(&xas, &xas); + XA_BUG_ON(xa, !list_empty(&shadow_nodes)); + + xas_store(&xas, xa_mk_value(2)); + xas_unlock(&xas); + XA_BUG_ON(xa, list_empty(&shadow_nodes)); + + shadow_remove(xa); + XA_BUG_ON(xa, !list_empty(&shadow_nodes)); + XA_BUG_ON(xa, !xa_empty(xa)); +} + static noinline void check_destroy(struct xarray *xa) { unsigned long index; @@ -916,6 +977,10 @@ static int xarray_checks(void) check_create_range(&array); check_store_iter(&array); + check_workingset(&array, 0); + check_workingset(&array, 64); + check_workingset(&array, 4096); + printk("XArray: %u of %u tests passed\n", tests_passed, tests_run); return (tests_run == tests_passed) ? 0 : -EINVAL; } diff --git a/mm/workingset.c b/mm/workingset.c index c201cbb8c00f..5cfb29ec3fd9 100644 --- a/mm/workingset.c +++ b/mm/workingset.c @@ -148,7 +148,7 @@ * and activations is maintained (node->inactive_age). * * On eviction, a snapshot of this counter (along with some bits to - * identify the node) is stored in the now empty page cache radix tree + * identify the node) is stored in the now empty page cache * slot of the evicted page. This is called a shadow entry. * * On cache misses for which there are shadow entries, an eligible @@ -162,7 +162,7 @@ /* * Eviction timestamps need to be able to cover the full range of - * actionable refaults. However, bits are tight in the radix tree + * actionable refaults. However, bits are tight in the xarray * entry, and after storing the identifier for the lruvec there might * not be enough left to represent every single actionable refault. In * that case, we have to sacrifice granularity for distance, and group @@ -339,7 +339,7 @@ out: static struct list_lru shadow_nodes; -void workingset_update_node(struct radix_tree_node *node) +void workingset_update_node(struct xa_node *node) { /* * Track non-empty nodes that contain only shadow entries; @@ -368,7 +368,7 @@ static unsigned long count_shadow_nodes(struct shrinker *shrinker, nodes = list_lru_shrink_count(&shadow_nodes, sc); /* - * Approximate a reasonable limit for the radix tree nodes + * Approximate a reasonable limit for the nodes * containing shadow entries. We don't need to keep more * shadow entries than possible pages on the active list, * since refault distances bigger than that are dismissed. @@ -383,11 +383,11 @@ static unsigned long count_shadow_nodes(struct shrinker *shrinker, * worst-case density of 1/8th. Below that, not all eligible * refaults can be detected anymore. * - * On 64-bit with 7 radix_tree_nodes per page and 64 slots + * On 64-bit with 7 xa_nodes per page and 64 slots * each, this will reclaim shadow entries when they consume * ~1.8% of available memory: * - * PAGE_SIZE / radix_tree_nodes / node_entries * 8 / PAGE_SIZE + * PAGE_SIZE / xa_nodes / node_entries * 8 / PAGE_SIZE */ if (sc->memcg) { cache = mem_cgroup_node_nr_lru_pages(sc->memcg, sc->nid, @@ -396,7 +396,7 @@ static unsigned long count_shadow_nodes(struct shrinker *shrinker, cache = node_page_state(NODE_DATA(sc->nid), NR_ACTIVE_FILE) + node_page_state(NODE_DATA(sc->nid), NR_INACTIVE_FILE); } - max_nodes = cache >> (RADIX_TREE_MAP_SHIFT - 3); + max_nodes = cache >> (XA_CHUNK_SHIFT - 3); if (!nodes) return SHRINK_EMPTY; @@ -409,11 +409,11 @@ static unsigned long count_shadow_nodes(struct shrinker *shrinker, static enum lru_status shadow_lru_isolate(struct list_head *item, struct list_lru_one *lru, spinlock_t *lru_lock, - void *arg) + void *arg) __must_hold(lru_lock) { + struct xa_node *node = container_of(item, struct xa_node, private_list); + XA_STATE(xas, node->array, 0); struct address_space *mapping; - struct radix_tree_node *node; - unsigned int i; int ret; /* @@ -421,14 +421,13 @@ static enum lru_status shadow_lru_isolate(struct list_head *item, * the shadow node LRU under the i_pages lock and the * lru_lock. Because the page cache tree is emptied before * the inode can be destroyed, holding the lru_lock pins any - * address_space that has radix tree nodes on the LRU. + * address_space that has nodes on the LRU. * * We can then safely transition to the i_pages lock to * pin only the address_space of the particular node we want * to reclaim, take the node off-LRU, and drop the lru_lock. */ - node = container_of(item, struct xa_node, private_list); mapping = container_of(node->array, struct address_space, i_pages); /* Coming from the list, invert the lock order */ @@ -450,25 +449,17 @@ static enum lru_status shadow_lru_isolate(struct list_head *item, goto out_invalid; if (WARN_ON_ONCE(node->count != node->nr_values)) goto out_invalid; - for (i = 0; i < RADIX_TREE_MAP_SIZE; i++) { - if (node->slots[i]) { - if (WARN_ON_ONCE(!xa_is_value(node->slots[i]))) - goto out_invalid; - if (WARN_ON_ONCE(!node->nr_values)) - goto out_invalid; - if (WARN_ON_ONCE(!mapping->nrexceptional)) - goto out_invalid; - node->slots[i] = NULL; - node->nr_values--; - node->count--; - mapping->nrexceptional--; - } - } - if (WARN_ON_ONCE(node->nr_values)) - goto out_invalid; + mapping->nrexceptional -= node->nr_values; + xas.xa_node = xa_parent_locked(&mapping->i_pages, node); + xas.xa_offset = node->offset; + xas.xa_shift = node->shift + XA_CHUNK_SHIFT; + xas_set_update(&xas, workingset_update_node); + /* + * We could store a shadow entry here which was the minimum of the + * shadow entries we were tracking ... + */ + xas_store(&xas, NULL); inc_lruvec_page_state(virt_to_page(node), WORKINGSET_NODERECLAIM); - __radix_tree_delete_node(&mapping->i_pages, node, - workingset_lookup_update(mapping)); out_invalid: xa_unlock_irq(&mapping->i_pages); -- cgit v1.2.3 From 69b6c1319b6588b65d853055d5336f662f6cb1a2 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Sat, 25 Nov 2017 22:52:46 -0500 Subject: mm: Convert truncate to XArray This is essentially xa_cmpxchg() with the locking handled above us, and it doesn't have to handle replacing a NULL entry. Signed-off-by: Matthew Wilcox --- mm/truncate.c | 15 ++++++--------- 1 file changed, 6 insertions(+), 9 deletions(-) (limited to 'mm') diff --git a/mm/truncate.c b/mm/truncate.c index ed778555c9f3..45d68e90b703 100644 --- a/mm/truncate.c +++ b/mm/truncate.c @@ -33,15 +33,12 @@ static inline void __clear_shadow_entry(struct address_space *mapping, pgoff_t index, void *entry) { - struct radix_tree_node *node; - void **slot; + XA_STATE(xas, &mapping->i_pages, index); - if (!__radix_tree_lookup(&mapping->i_pages, index, &node, &slot)) + xas_set_update(&xas, workingset_update_node); + if (xas_load(&xas) != entry) return; - if (*slot != entry) - return; - __radix_tree_replace(&mapping->i_pages, node, slot, NULL, - workingset_update_node); + xas_store(&xas, NULL); mapping->nrexceptional--; } @@ -738,10 +735,10 @@ int invalidate_inode_pages2_range(struct address_space *mapping, index++; } /* - * For DAX we invalidate page tables after invalidating radix tree. We + * For DAX we invalidate page tables after invalidating page cache. We * could invalidate page tables while invalidating each entry however * that would be expensive. And doing range unmapping before doesn't - * work as we have no cheap way to find whether radix tree entry didn't + * work as we have no cheap way to find whether page cache entry didn't * get remapped later. */ if (dax_mapping(mapping)) { -- cgit v1.2.3 From 8d93b41c09d1b74f376e3b9779eb3badeb550301 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Mon, 27 Nov 2017 15:46:54 -0500 Subject: mm: Convert add_to_swap_cache to XArray Combine __add_to_swap_cache and add_to_swap_cache into one function since there is no more need to preload. Signed-off-by: Matthew Wilcox --- mm/swap_state.c | 93 ++++++++++++++++++--------------------------------------- 1 file changed, 29 insertions(+), 64 deletions(-) (limited to 'mm') diff --git a/mm/swap_state.c b/mm/swap_state.c index ecee9c6c4cc1..850314c2c3ab 100644 --- a/mm/swap_state.c +++ b/mm/swap_state.c @@ -107,14 +107,15 @@ void show_swap_cache_info(void) } /* - * __add_to_swap_cache resembles add_to_page_cache_locked on swapper_space, + * add_to_swap_cache resembles add_to_page_cache_locked on swapper_space, * but sets SwapCache flag and private instead of mapping and index. */ -int __add_to_swap_cache(struct page *page, swp_entry_t entry) +int add_to_swap_cache(struct page *page, swp_entry_t entry, gfp_t gfp) { - int error, i, nr = hpage_nr_pages(page); - struct address_space *address_space; + struct address_space *address_space = swap_address_space(entry); pgoff_t idx = swp_offset(entry); + XA_STATE_ORDER(xas, &address_space->i_pages, idx, compound_order(page)); + unsigned long i, nr = 1UL << compound_order(page); VM_BUG_ON_PAGE(!PageLocked(page), page); VM_BUG_ON_PAGE(PageSwapCache(page), page); @@ -123,50 +124,30 @@ int __add_to_swap_cache(struct page *page, swp_entry_t entry) page_ref_add(page, nr); SetPageSwapCache(page); - address_space = swap_address_space(entry); - xa_lock_irq(&address_space->i_pages); - for (i = 0; i < nr; i++) { - set_page_private(page + i, entry.val + i); - error = radix_tree_insert(&address_space->i_pages, - idx + i, page + i); - if (unlikely(error)) - break; - } - if (likely(!error)) { + do { + xas_lock_irq(&xas); + xas_create_range(&xas); + if (xas_error(&xas)) + goto unlock; + for (i = 0; i < nr; i++) { + VM_BUG_ON_PAGE(xas.xa_index != idx + i, page); + set_page_private(page + i, entry.val + i); + xas_store(&xas, page + i); + xas_next(&xas); + } address_space->nrpages += nr; __mod_node_page_state(page_pgdat(page), NR_FILE_PAGES, nr); ADD_CACHE_INFO(add_total, nr); - } else { - /* - * Only the context which have set SWAP_HAS_CACHE flag - * would call add_to_swap_cache(). - * So add_to_swap_cache() doesn't returns -EEXIST. - */ - VM_BUG_ON(error == -EEXIST); - set_page_private(page + i, 0UL); - while (i--) { - radix_tree_delete(&address_space->i_pages, idx + i); - set_page_private(page + i, 0UL); - } - ClearPageSwapCache(page); - page_ref_sub(page, nr); - } - xa_unlock_irq(&address_space->i_pages); +unlock: + xas_unlock_irq(&xas); + } while (xas_nomem(&xas, gfp)); - return error; -} - - -int add_to_swap_cache(struct page *page, swp_entry_t entry, gfp_t gfp_mask) -{ - int error; + if (!xas_error(&xas)) + return 0; - error = radix_tree_maybe_preload_order(gfp_mask, compound_order(page)); - if (!error) { - error = __add_to_swap_cache(page, entry); - radix_tree_preload_end(); - } - return error; + ClearPageSwapCache(page); + page_ref_sub(page, nr); + return xas_error(&xas); } /* @@ -217,7 +198,7 @@ int add_to_swap(struct page *page) return 0; /* - * Radix-tree node allocations from PF_MEMALLOC contexts could + * XArray node allocations from PF_MEMALLOC contexts could * completely exhaust the page allocator. __GFP_NOMEMALLOC * stops emergency reserves from being allocated. * @@ -229,7 +210,6 @@ int add_to_swap(struct page *page) */ err = add_to_swap_cache(page, entry, __GFP_HIGH|__GFP_NOMEMALLOC|__GFP_NOWARN); - /* -ENOMEM radix-tree allocation failure */ if (err) /* * add_to_swap_cache() doesn't return -EEXIST, so we can safely @@ -413,19 +393,11 @@ struct page *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask, break; /* Out of memory */ } - /* - * call radix_tree_preload() while we can wait. - */ - err = radix_tree_maybe_preload(gfp_mask & GFP_KERNEL); - if (err) - break; - /* * Swap entry may have been freed since our caller observed it. */ err = swapcache_prepare(entry); if (err == -EEXIST) { - radix_tree_preload_end(); /* * We might race against get_swap_page() and stumble * across a SWAP_HAS_CACHE swap_map entry whose page @@ -433,26 +405,19 @@ struct page *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask, */ cond_resched(); continue; - } - if (err) { /* swp entry is obsolete ? */ - radix_tree_preload_end(); + } else if (err) /* swp entry is obsolete ? */ break; - } - /* May fail (-ENOMEM) if radix-tree node allocation failed. */ + /* May fail (-ENOMEM) if XArray node allocation failed. */ __SetPageLocked(new_page); __SetPageSwapBacked(new_page); - err = __add_to_swap_cache(new_page, entry); + err = add_to_swap_cache(new_page, entry, gfp_mask & GFP_KERNEL); if (likely(!err)) { - radix_tree_preload_end(); - /* - * Initiate read into locked page and return. - */ + /* Initiate read into locked page */ lru_cache_add_anon(new_page); *new_page_allocated = true; return new_page; } - radix_tree_preload_end(); __ClearPageLocked(new_page); /* * add_to_swap_cache() doesn't return -EEXIST, so we can safely -- cgit v1.2.3 From 4e17ec250fce0eba9b70a91c9622da2748a3ec50 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Wed, 29 Nov 2017 08:32:39 -0500 Subject: mm: Convert delete_from_swap_cache to XArray Both callers of __delete_from_swap_cache have the swp_entry_t already, so pass that in to make constructing the XA_STATE easier. Signed-off-by: Matthew Wilcox --- include/linux/swap.h | 5 +++-- mm/swap_state.c | 24 ++++++++++-------------- mm/vmscan.c | 2 +- 3 files changed, 14 insertions(+), 17 deletions(-) (limited to 'mm') diff --git a/include/linux/swap.h b/include/linux/swap.h index 112cebcf0402..cb479bf5842e 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -403,7 +403,7 @@ extern void show_swap_cache_info(void); extern int add_to_swap(struct page *page); extern int add_to_swap_cache(struct page *, swp_entry_t, gfp_t); extern int __add_to_swap_cache(struct page *page, swp_entry_t entry); -extern void __delete_from_swap_cache(struct page *); +extern void __delete_from_swap_cache(struct page *, swp_entry_t entry); extern void delete_from_swap_cache(struct page *); extern void free_page_and_swap_cache(struct page *); extern void free_pages_and_swap_cache(struct page **, int); @@ -557,7 +557,8 @@ static inline int add_to_swap_cache(struct page *page, swp_entry_t entry, return -1; } -static inline void __delete_from_swap_cache(struct page *page) +static inline void __delete_from_swap_cache(struct page *page, + swp_entry_t entry) { } diff --git a/mm/swap_state.c b/mm/swap_state.c index 850314c2c3ab..f393c994cc60 100644 --- a/mm/swap_state.c +++ b/mm/swap_state.c @@ -154,23 +154,22 @@ unlock: * This must be called only on pages that have * been verified to be in the swap cache. */ -void __delete_from_swap_cache(struct page *page) +void __delete_from_swap_cache(struct page *page, swp_entry_t entry) { - struct address_space *address_space; + struct address_space *address_space = swap_address_space(entry); int i, nr = hpage_nr_pages(page); - swp_entry_t entry; - pgoff_t idx; + pgoff_t idx = swp_offset(entry); + XA_STATE(xas, &address_space->i_pages, idx); VM_BUG_ON_PAGE(!PageLocked(page), page); VM_BUG_ON_PAGE(!PageSwapCache(page), page); VM_BUG_ON_PAGE(PageWriteback(page), page); - entry.val = page_private(page); - address_space = swap_address_space(entry); - idx = swp_offset(entry); for (i = 0; i < nr; i++) { - radix_tree_delete(&address_space->i_pages, idx + i); + void *entry = xas_store(&xas, NULL); + VM_BUG_ON_PAGE(entry != page + i, entry); set_page_private(page + i, 0); + xas_next(&xas); } ClearPageSwapCache(page); address_space->nrpages -= nr; @@ -243,14 +242,11 @@ fail: */ void delete_from_swap_cache(struct page *page) { - swp_entry_t entry; - struct address_space *address_space; - - entry.val = page_private(page); + swp_entry_t entry = { .val = page_private(page) }; + struct address_space *address_space = swap_address_space(entry); - address_space = swap_address_space(entry); xa_lock_irq(&address_space->i_pages); - __delete_from_swap_cache(page); + __delete_from_swap_cache(page, entry); xa_unlock_irq(&address_space->i_pages); put_swap_page(page, entry); diff --git a/mm/vmscan.c b/mm/vmscan.c index c7ce2c161225..80f731cf974e 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -923,7 +923,7 @@ static int __remove_mapping(struct address_space *mapping, struct page *page, if (PageSwapCache(page)) { swp_entry_t swap = { .val = page_private(page) }; mem_cgroup_swapout(page, swap); - __delete_from_swap_cache(page); + __delete_from_swap_cache(page, swap); xa_unlock_irqrestore(&mapping->i_pages, flags); put_swap_page(page, swap); } else { -- cgit v1.2.3 From 560d454bae08b5d5a132c5520177dede066334b7 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Mon, 4 Dec 2017 04:30:18 -0500 Subject: mm: Convert __do_page_cache_readahead to XArray This one is trivial. Signed-off-by: Matthew Wilcox --- mm/readahead.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'mm') diff --git a/mm/readahead.c b/mm/readahead.c index fc4dd364b37a..f3d6f9656a3c 100644 --- a/mm/readahead.c +++ b/mm/readahead.c @@ -176,9 +176,7 @@ unsigned int __do_page_cache_readahead(struct address_space *mapping, if (page_offset > end_index) break; - rcu_read_lock(); - page = radix_tree_lookup(&mapping->i_pages, page_offset); - rcu_read_unlock(); + page = xa_load(&mapping->i_pages, page_offset); if (page && !xa_is_value(page)) { /* * Page already present? Kick off the current batch of -- cgit v1.2.3 From 89eb946a7432be639b452fac295c0c2e5186c4a4 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Mon, 4 Dec 2017 04:35:16 -0500 Subject: mm: Convert page migration to XArray Signed-off-by: Matthew Wilcox --- mm/migrate.c | 48 ++++++++++++++++++------------------------------ 1 file changed, 18 insertions(+), 30 deletions(-) (limited to 'mm') diff --git a/mm/migrate.c b/mm/migrate.c index d6a2e89b086a..b3cde3fd094a 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -323,7 +323,7 @@ void __migration_entry_wait(struct mm_struct *mm, pte_t *ptep, page = migration_entry_to_page(entry); /* - * Once radix-tree replacement of page migration started, page_count + * Once page cache replacement of page migration started, page_count * *must* be zero. And, we don't want to call wait_on_page_locked() * against a page without get_page(). * So, we use get_page_unless_zero(), here. Even failed, page fault @@ -438,10 +438,10 @@ int migrate_page_move_mapping(struct address_space *mapping, struct buffer_head *head, enum migrate_mode mode, int extra_count) { + XA_STATE(xas, &mapping->i_pages, page_index(page)); struct zone *oldzone, *newzone; int dirty; int expected_count = 1 + extra_count; - void **pslot; /* * Device public or private pages have an extra refcount as they are @@ -467,21 +467,16 @@ int migrate_page_move_mapping(struct address_space *mapping, oldzone = page_zone(page); newzone = page_zone(newpage); - xa_lock_irq(&mapping->i_pages); - - pslot = radix_tree_lookup_slot(&mapping->i_pages, - page_index(page)); + xas_lock_irq(&xas); expected_count += hpage_nr_pages(page) + page_has_private(page); - if (page_count(page) != expected_count || - radix_tree_deref_slot_protected(pslot, - &mapping->i_pages.xa_lock) != page) { - xa_unlock_irq(&mapping->i_pages); + if (page_count(page) != expected_count || xas_load(&xas) != page) { + xas_unlock_irq(&xas); return -EAGAIN; } if (!page_ref_freeze(page, expected_count)) { - xa_unlock_irq(&mapping->i_pages); + xas_unlock_irq(&xas); return -EAGAIN; } @@ -495,7 +490,7 @@ int migrate_page_move_mapping(struct address_space *mapping, if (mode == MIGRATE_ASYNC && head && !buffer_migrate_lock_buffers(head, mode)) { page_ref_unfreeze(page, expected_count); - xa_unlock_irq(&mapping->i_pages); + xas_unlock_irq(&xas); return -EAGAIN; } @@ -523,16 +518,13 @@ int migrate_page_move_mapping(struct address_space *mapping, SetPageDirty(newpage); } - radix_tree_replace_slot(&mapping->i_pages, pslot, newpage); + xas_store(&xas, newpage); if (PageTransHuge(page)) { int i; - int index = page_index(page); for (i = 1; i < HPAGE_PMD_NR; i++) { - pslot = radix_tree_lookup_slot(&mapping->i_pages, - index + i); - radix_tree_replace_slot(&mapping->i_pages, pslot, - newpage + i); + xas_next(&xas); + xas_store(&xas, newpage + i); } } @@ -543,7 +535,7 @@ int migrate_page_move_mapping(struct address_space *mapping, */ page_ref_unfreeze(page, expected_count - hpage_nr_pages(page)); - xa_unlock(&mapping->i_pages); + xas_unlock(&xas); /* Leave irq disabled to prevent preemption while updating stats */ /* @@ -583,22 +575,18 @@ EXPORT_SYMBOL(migrate_page_move_mapping); int migrate_huge_page_move_mapping(struct address_space *mapping, struct page *newpage, struct page *page) { + XA_STATE(xas, &mapping->i_pages, page_index(page)); int expected_count; - void **pslot; - - xa_lock_irq(&mapping->i_pages); - - pslot = radix_tree_lookup_slot(&mapping->i_pages, page_index(page)); + xas_lock_irq(&xas); expected_count = 2 + page_has_private(page); - if (page_count(page) != expected_count || - radix_tree_deref_slot_protected(pslot, &mapping->i_pages.xa_lock) != page) { - xa_unlock_irq(&mapping->i_pages); + if (page_count(page) != expected_count || xas_load(&xas) != page) { + xas_unlock_irq(&xas); return -EAGAIN; } if (!page_ref_freeze(page, expected_count)) { - xa_unlock_irq(&mapping->i_pages); + xas_unlock_irq(&xas); return -EAGAIN; } @@ -607,11 +595,11 @@ int migrate_huge_page_move_mapping(struct address_space *mapping, get_page(newpage); - radix_tree_replace_slot(&mapping->i_pages, pslot, newpage); + xas_store(&xas, newpage); page_ref_unfreeze(page, expected_count - 1); - xa_unlock_irq(&mapping->i_pages); + xas_unlock_irq(&xas); return MIGRATEPAGE_SUCCESS; } -- cgit v1.2.3 From aa5dc07f70c50a3c56bf3fa07bde0b22a95aa381 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Mon, 4 Dec 2017 10:16:10 -0500 Subject: mm: Convert huge_memory to XArray Quite a straightforward conversion. Signed-off-by: Matthew Wilcox --- mm/huge_memory.c | 17 +++++++---------- 1 file changed, 7 insertions(+), 10 deletions(-) (limited to 'mm') diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 533f9b00147d..9eb79c384616 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2443,13 +2443,13 @@ static void __split_huge_page(struct page *page, struct list_head *list, ClearPageCompound(head); /* See comment in __split_huge_page_tail() */ if (PageAnon(head)) { - /* Additional pin to radix tree of swap cache */ + /* Additional pin to swap cache */ if (PageSwapCache(head)) page_ref_add(head, 2); else page_ref_inc(head); } else { - /* Additional pin to radix tree */ + /* Additional pin to page cache */ page_ref_add(head, 2); xa_unlock(&head->mapping->i_pages); } @@ -2561,7 +2561,7 @@ bool can_split_huge_page(struct page *page, int *pextra_pins) { int extra_pins; - /* Additional pins from radix tree */ + /* Additional pins from page cache */ if (PageAnon(page)) extra_pins = PageSwapCache(page) ? HPAGE_PMD_NR : 0; else @@ -2657,17 +2657,14 @@ int split_huge_page_to_list(struct page *page, struct list_head *list) spin_lock_irqsave(zone_lru_lock(page_zone(head)), flags); if (mapping) { - void **pslot; + XA_STATE(xas, &mapping->i_pages, page_index(head)); - xa_lock(&mapping->i_pages); - pslot = radix_tree_lookup_slot(&mapping->i_pages, - page_index(head)); /* - * Check if the head page is present in radix tree. + * Check if the head page is present in page cache. * We assume all tail are present too, if head is there. */ - if (radix_tree_deref_slot_protected(pslot, - &mapping->i_pages.xa_lock) != head) + xa_lock(&mapping->i_pages); + if (xas_load(&xas) != head) goto fail; } -- cgit v1.2.3 From 77da9389b9d5f07d54fda092d1ab56002ec0019a Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Mon, 4 Dec 2017 14:56:08 -0500 Subject: mm: Convert collapse_shmem to XArray I found another victim of the radix tree being hard to use. Because there was no call to radix_tree_preload(), khugepaged was allocating radix_tree_nodes using GFP_ATOMIC. I also converted a local_irq_save()/restore() pair to disable()/enable(). Signed-off-by: Matthew Wilcox --- mm/khugepaged.c | 159 +++++++++++++++++++++++--------------------------------- 1 file changed, 66 insertions(+), 93 deletions(-) (limited to 'mm') diff --git a/mm/khugepaged.c b/mm/khugepaged.c index 4820e4adf853..9610e8cba545 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -1288,17 +1288,17 @@ static void retract_page_tables(struct address_space *mapping, pgoff_t pgoff) * * Basic scheme is simple, details are more complex: * - allocate and freeze a new huge page; - * - scan over radix tree replacing old pages the new one + * - scan page cache replacing old pages with the new one * + swap in pages if necessary; * + fill in gaps; - * + keep old pages around in case if rollback is required; - * - if replacing succeed: + * + keep old pages around in case rollback is required; + * - if replacing succeeds: * + copy data over; * + free old pages; * + unfreeze huge page; * - if replacing failed; * + put all pages back and unfreeze them; - * + restore gaps in the radix-tree; + * + restore gaps in the page cache; * + free huge page; */ static void collapse_shmem(struct mm_struct *mm, @@ -1306,12 +1306,11 @@ static void collapse_shmem(struct mm_struct *mm, struct page **hpage, int node) { gfp_t gfp; - struct page *page, *new_page, *tmp; + struct page *new_page; struct mem_cgroup *memcg; pgoff_t index, end = start + HPAGE_PMD_NR; LIST_HEAD(pagelist); - struct radix_tree_iter iter; - void **slot; + XA_STATE_ORDER(xas, &mapping->i_pages, start, HPAGE_PMD_ORDER); int nr_none = 0, result = SCAN_SUCCEED; VM_BUG_ON(start & (HPAGE_PMD_NR - 1)); @@ -1336,48 +1335,49 @@ static void collapse_shmem(struct mm_struct *mm, __SetPageLocked(new_page); BUG_ON(!page_ref_freeze(new_page, 1)); - /* - * At this point the new_page is 'frozen' (page_count() is zero), locked - * and not up-to-date. It's safe to insert it into radix tree, because - * nobody would be able to map it or use it in other way until we - * unfreeze it. + * At this point the new_page is 'frozen' (page_count() is zero), + * locked and not up-to-date. It's safe to insert it into the page + * cache, because nobody would be able to map it or use it in other + * way until we unfreeze it. */ - index = start; - xa_lock_irq(&mapping->i_pages); - radix_tree_for_each_slot(slot, &mapping->i_pages, &iter, start) { - int n = min(iter.index, end) - index; - - /* - * Handle holes in the radix tree: charge it from shmem and - * insert relevant subpage of new_page into the radix-tree. - */ - if (n && !shmem_charge(mapping->host, n)) { - result = SCAN_FAIL; + /* This will be less messy when we use multi-index entries */ + do { + xas_lock_irq(&xas); + xas_create_range(&xas); + if (!xas_error(&xas)) break; - } - nr_none += n; - for (; index < min(iter.index, end); index++) { - radix_tree_insert(&mapping->i_pages, index, - new_page + (index % HPAGE_PMD_NR)); - } + xas_unlock_irq(&xas); + if (!xas_nomem(&xas, GFP_KERNEL)) + goto out; + } while (1); - /* We are done. */ - if (index >= end) - break; + xas_set(&xas, start); + for (index = start; index < end; index++) { + struct page *page = xas_next(&xas); + + VM_BUG_ON(index != xas.xa_index); + if (!page) { + if (!shmem_charge(mapping->host, 1)) { + result = SCAN_FAIL; + break; + } + xas_store(&xas, new_page + (index % HPAGE_PMD_NR)); + nr_none++; + continue; + } - page = radix_tree_deref_slot_protected(slot, - &mapping->i_pages.xa_lock); if (xa_is_value(page) || !PageUptodate(page)) { - xa_unlock_irq(&mapping->i_pages); + xas_unlock_irq(&xas); /* swap in or instantiate fallocated page */ if (shmem_getpage(mapping->host, index, &page, SGP_NOHUGE)) { result = SCAN_FAIL; - goto tree_unlocked; + goto xa_unlocked; } - xa_lock_irq(&mapping->i_pages); + xas_lock_irq(&xas); + xas_set(&xas, index); } else if (trylock_page(page)) { get_page(page); } else { @@ -1397,7 +1397,7 @@ static void collapse_shmem(struct mm_struct *mm, result = SCAN_TRUNCATED; goto out_unlock; } - xa_unlock_irq(&mapping->i_pages); + xas_unlock_irq(&xas); if (isolate_lru_page(page)) { result = SCAN_DEL_PAGE_LRU; @@ -1407,17 +1407,16 @@ static void collapse_shmem(struct mm_struct *mm, if (page_mapped(page)) unmap_mapping_pages(mapping, index, 1, false); - xa_lock_irq(&mapping->i_pages); + xas_lock_irq(&xas); + xas_set(&xas, index); - slot = radix_tree_lookup_slot(&mapping->i_pages, index); - VM_BUG_ON_PAGE(page != radix_tree_deref_slot_protected(slot, - &mapping->i_pages.xa_lock), page); + VM_BUG_ON_PAGE(page != xas_load(&xas), page); VM_BUG_ON_PAGE(page_mapped(page), page); /* * The page is expected to have page_count() == 3: * - we hold a pin on it; - * - one reference from radix tree; + * - one reference from page cache; * - one from isolate_lru_page; */ if (!page_ref_freeze(page, 3)) { @@ -1432,56 +1431,30 @@ static void collapse_shmem(struct mm_struct *mm, list_add_tail(&page->lru, &pagelist); /* Finally, replace with the new page. */ - radix_tree_replace_slot(&mapping->i_pages, slot, - new_page + (index % HPAGE_PMD_NR)); - - slot = radix_tree_iter_resume(slot, &iter); - index++; + xas_store(&xas, new_page + (index % HPAGE_PMD_NR)); continue; out_lru: - xa_unlock_irq(&mapping->i_pages); + xas_unlock_irq(&xas); putback_lru_page(page); out_isolate_failed: unlock_page(page); put_page(page); - goto tree_unlocked; + goto xa_unlocked; out_unlock: unlock_page(page); put_page(page); break; } + xas_unlock_irq(&xas); - /* - * Handle hole in radix tree at the end of the range. - * This code only triggers if there's nothing in radix tree - * beyond 'end'. - */ - if (result == SCAN_SUCCEED && index < end) { - int n = end - index; - - if (!shmem_charge(mapping->host, n)) { - result = SCAN_FAIL; - goto tree_locked; - } - - for (; index < end; index++) { - radix_tree_insert(&mapping->i_pages, index, - new_page + (index % HPAGE_PMD_NR)); - } - nr_none += n; - } - -tree_locked: - xa_unlock_irq(&mapping->i_pages); -tree_unlocked: - +xa_unlocked: if (result == SCAN_SUCCEED) { - unsigned long flags; + struct page *page, *tmp; struct zone *zone = page_zone(new_page); /* - * Replacing old pages with new one has succeed, now we need to - * copy the content and free old pages. + * Replacing old pages with new one has succeeded, now we + * need to copy the content and free the old pages. */ list_for_each_entry_safe(page, tmp, &pagelist, lru) { copy_highpage(new_page + (page->index % HPAGE_PMD_NR), @@ -1495,16 +1468,16 @@ tree_unlocked: put_page(page); } - local_irq_save(flags); + local_irq_disable(); __inc_node_page_state(new_page, NR_SHMEM_THPS); if (nr_none) { __mod_node_page_state(zone->zone_pgdat, NR_FILE_PAGES, nr_none); __mod_node_page_state(zone->zone_pgdat, NR_SHMEM, nr_none); } - local_irq_restore(flags); + local_irq_enable(); /* - * Remove pte page tables, so we can re-faulti + * Remove pte page tables, so we can re-fault * the page as huge. */ retract_page_tables(mapping, start); @@ -1521,37 +1494,37 @@ tree_unlocked: khugepaged_pages_collapsed++; } else { - /* Something went wrong: rollback changes to the radix-tree */ + struct page *page; + /* Something went wrong: roll back page cache changes */ shmem_uncharge(mapping->host, nr_none); - xa_lock_irq(&mapping->i_pages); - radix_tree_for_each_slot(slot, &mapping->i_pages, &iter, start) { - if (iter.index >= end) - break; + xas_lock_irq(&xas); + xas_set(&xas, start); + xas_for_each(&xas, page, end - 1) { page = list_first_entry_or_null(&pagelist, struct page, lru); - if (!page || iter.index < page->index) { + if (!page || xas.xa_index < page->index) { if (!nr_none) break; nr_none--; /* Put holes back where they were */ - radix_tree_delete(&mapping->i_pages, iter.index); + xas_store(&xas, NULL); continue; } - VM_BUG_ON_PAGE(page->index != iter.index, page); + VM_BUG_ON_PAGE(page->index != xas.xa_index, page); /* Unfreeze the page. */ list_del(&page->lru); page_ref_unfreeze(page, 2); - radix_tree_replace_slot(&mapping->i_pages, slot, page); - slot = radix_tree_iter_resume(slot, &iter); - xa_unlock_irq(&mapping->i_pages); + xas_store(&xas, page); + xas_pause(&xas); + xas_unlock_irq(&xas); putback_lru_page(page); unlock_page(page); - xa_lock_irq(&mapping->i_pages); + xas_lock_irq(&xas); } VM_BUG_ON(nr_none); - xa_unlock_irq(&mapping->i_pages); + xas_unlock_irq(&xas); /* Unfreeze new_page, caller would take care about freeing it */ page_ref_unfreeze(new_page, 1); -- cgit v1.2.3 From 85b392dbace77bf91050e6e07f3dd0f262e4babf Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Mon, 4 Dec 2017 15:06:23 -0500 Subject: mm: Convert khugepaged_scan_shmem to XArray Slightly shorter and easier to read code. Signed-off-by: Matthew Wilcox --- mm/khugepaged.c | 17 +++++------------ 1 file changed, 5 insertions(+), 12 deletions(-) (limited to 'mm') diff --git a/mm/khugepaged.c b/mm/khugepaged.c index 9610e8cba545..c13625c1ad5e 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -1542,8 +1542,7 @@ static void khugepaged_scan_shmem(struct mm_struct *mm, pgoff_t start, struct page **hpage) { struct page *page = NULL; - struct radix_tree_iter iter; - void **slot; + XA_STATE(xas, &mapping->i_pages, start); int present, swap; int node = NUMA_NO_NODE; int result = SCAN_SUCCEED; @@ -1552,17 +1551,11 @@ static void khugepaged_scan_shmem(struct mm_struct *mm, swap = 0; memset(khugepaged_node_load, 0, sizeof(khugepaged_node_load)); rcu_read_lock(); - radix_tree_for_each_slot(slot, &mapping->i_pages, &iter, start) { - if (iter.index >= start + HPAGE_PMD_NR) - break; - - page = radix_tree_deref_slot(slot); - if (radix_tree_deref_retry(page)) { - slot = radix_tree_iter_retry(&iter); + xas_for_each(&xas, page, start + HPAGE_PMD_NR - 1) { + if (xas_retry(&xas, page)) continue; - } - if (radix_tree_exception(page)) { + if (xa_is_value(page)) { if (++swap > khugepaged_max_ptes_swap) { result = SCAN_EXCEED_SWAP_PTE; break; @@ -1601,7 +1594,7 @@ static void khugepaged_scan_shmem(struct mm_struct *mm, present++; if (need_resched()) { - slot = radix_tree_iter_resume(slot, &iter); + xas_pause(&xas); cond_resched_rcu(); } } -- cgit v1.2.3 From 67891ffff2f5cf10e89e348207f687a05c8bd2d6 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Sun, 10 Jun 2018 07:34:39 -0400 Subject: mm: Convert is_page_cache_freeable to XArray This is just a variable rename and comment change. Signed-off-by: Matthew Wilcox --- mm/vmscan.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'mm') diff --git a/mm/vmscan.c b/mm/vmscan.c index 80f731cf974e..f9cc86e91812 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -742,12 +742,12 @@ static inline int is_page_cache_freeable(struct page *page) { /* * A freeable page cache page is referenced only by the caller - * that isolated the page, the page cache radix tree and - * optional buffer heads at page->private. + * that isolated the page, the page cache and optional buffer + * heads at page->private. */ - int radix_pins = PageTransHuge(page) && PageSwapCache(page) ? + int page_cache_pins = PageTransHuge(page) && PageSwapCache(page) ? HPAGE_PMD_NR : 1; - return page_count(page) - page_has_private(page) == 1 + radix_pins; + return page_count(page) - page_has_private(page) == 1 + page_cache_pins; } static int may_write_to_inode(struct inode *inode, struct scan_control *sc) -- cgit v1.2.3 From 10bbd235859bf483f9a8a4ebe95463d700bae394 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Tue, 5 Dec 2017 17:30:38 -0500 Subject: pagevec: Use xa_mark_t Removes sparse warnings. Signed-off-by: Matthew Wilcox --- fs/btrfs/extent_io.c | 4 ++-- fs/ext4/inode.c | 2 +- fs/f2fs/data.c | 2 +- fs/gfs2/aops.c | 2 +- include/linux/pagevec.h | 8 +++++--- mm/swap.c | 4 ++-- 6 files changed, 12 insertions(+), 10 deletions(-) (limited to 'mm') diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 4dd6faab02bb..fc7ca7d991ad 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -3778,7 +3778,7 @@ int btree_write_cache_pages(struct address_space *mapping, pgoff_t index; pgoff_t end; /* Inclusive */ int scanned = 0; - int tag; + xa_mark_t tag; pagevec_init(&pvec); if (wbc->range_cyclic) { @@ -3903,7 +3903,7 @@ static int extent_write_cache_pages(struct address_space *mapping, pgoff_t done_index; int range_whole = 0; int scanned = 0; - int tag; + xa_mark_t tag; /* * We have to hold onto the inode so that ordered extents can do their diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index d767e993591d..57bad3edfbed 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -2613,7 +2613,7 @@ static int mpage_prepare_extent_to_map(struct mpage_da_data *mpd) long left = mpd->wbc->nr_to_write; pgoff_t index = mpd->first_page; pgoff_t end = mpd->last_page; - int tag; + xa_mark_t tag; int i, err = 0; int blkbits = mpd->inode->i_blkbits; ext4_lblk_t lblk; diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c index 382c1ef9a9e4..5b760809eecc 100644 --- a/fs/f2fs/data.c +++ b/fs/f2fs/data.c @@ -2003,7 +2003,7 @@ static int f2fs_write_cache_pages(struct address_space *mapping, pgoff_t last_idx = ULONG_MAX; int cycled; int range_whole = 0; - int tag; + xa_mark_t tag; pagevec_init(&pvec); diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c index 31e8270d0b26..8afbb35559b9 100644 --- a/fs/gfs2/aops.c +++ b/fs/gfs2/aops.c @@ -366,7 +366,7 @@ static int gfs2_write_cache_jdata(struct address_space *mapping, pgoff_t done_index; int cycled; int range_whole = 0; - int tag; + xa_mark_t tag; pagevec_init(&pvec); if (wbc->range_cyclic) { diff --git a/include/linux/pagevec.h b/include/linux/pagevec.h index 6dc456ac6136..081d934eda64 100644 --- a/include/linux/pagevec.h +++ b/include/linux/pagevec.h @@ -9,6 +9,8 @@ #ifndef _LINUX_PAGEVEC_H #define _LINUX_PAGEVEC_H +#include + /* 15 pointers + header align the pagevec structure to a power of two */ #define PAGEVEC_SIZE 15 @@ -40,12 +42,12 @@ static inline unsigned pagevec_lookup(struct pagevec *pvec, unsigned pagevec_lookup_range_tag(struct pagevec *pvec, struct address_space *mapping, pgoff_t *index, pgoff_t end, - int tag); + xa_mark_t tag); unsigned pagevec_lookup_range_nr_tag(struct pagevec *pvec, struct address_space *mapping, pgoff_t *index, pgoff_t end, - int tag, unsigned max_pages); + xa_mark_t tag, unsigned max_pages); static inline unsigned pagevec_lookup_tag(struct pagevec *pvec, - struct address_space *mapping, pgoff_t *index, int tag) + struct address_space *mapping, pgoff_t *index, xa_mark_t tag) { return pagevec_lookup_range_tag(pvec, mapping, index, (pgoff_t)-1, tag); } diff --git a/mm/swap.c b/mm/swap.c index 4c5c7fcc6e46..6861f3140a13 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -1002,7 +1002,7 @@ EXPORT_SYMBOL(pagevec_lookup_range); unsigned pagevec_lookup_range_tag(struct pagevec *pvec, struct address_space *mapping, pgoff_t *index, pgoff_t end, - int tag) + xa_mark_t tag) { pvec->nr = find_get_pages_range_tag(mapping, index, end, tag, PAGEVEC_SIZE, pvec->pages); @@ -1012,7 +1012,7 @@ EXPORT_SYMBOL(pagevec_lookup_range_tag); unsigned pagevec_lookup_range_nr_tag(struct pagevec *pvec, struct address_space *mapping, pgoff_t *index, pgoff_t end, - int tag, unsigned max_pages) + xa_mark_t tag, unsigned max_pages) { pvec->nr = find_get_pages_range_tag(mapping, index, end, tag, min_t(unsigned int, max_pages, PAGEVEC_SIZE), pvec->pages); -- cgit v1.2.3 From 62f945b6a7b8cda6d1f35941eb374276f7b8749a Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Fri, 17 Nov 2017 10:22:37 -0500 Subject: shmem: Convert shmem_radix_tree_replace to XArray Rename shmem_radix_tree_replace() to shmem_replace_entry() and convert it to use the XArray API. Signed-off-by: Matthew Wilcox --- mm/shmem.c | 22 ++++++++-------------- 1 file changed, 8 insertions(+), 14 deletions(-) (limited to 'mm') diff --git a/mm/shmem.c b/mm/shmem.c index c1062760fe41..5697c8fecdfc 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -322,24 +322,20 @@ void shmem_uncharge(struct inode *inode, long pages) } /* - * Replace item expected in radix tree by a new item, while holding tree lock. + * Replace item expected in xarray by a new item, while holding xa_lock. */ -static int shmem_radix_tree_replace(struct address_space *mapping, +static int shmem_replace_entry(struct address_space *mapping, pgoff_t index, void *expected, void *replacement) { - struct radix_tree_node *node; - void __rcu **pslot; + XA_STATE(xas, &mapping->i_pages, index); void *item; VM_BUG_ON(!expected); VM_BUG_ON(!replacement); - item = __radix_tree_lookup(&mapping->i_pages, index, &node, &pslot); - if (!item) - return -ENOENT; + item = xas_load(&xas); if (item != expected) return -ENOENT; - __radix_tree_replace(&mapping->i_pages, node, pslot, - replacement, NULL); + xas_store(&xas, replacement); return 0; } @@ -624,8 +620,7 @@ static int shmem_add_to_page_cache(struct page *page, } else if (!expected) { error = radix_tree_insert(&mapping->i_pages, index, page); } else { - error = shmem_radix_tree_replace(mapping, index, expected, - page); + error = shmem_replace_entry(mapping, index, expected, page); } if (!error) { @@ -654,7 +649,7 @@ static void shmem_delete_from_page_cache(struct page *page, void *radswap) VM_BUG_ON_PAGE(PageCompound(page), page); xa_lock_irq(&mapping->i_pages); - error = shmem_radix_tree_replace(mapping, page->index, page, radswap); + error = shmem_replace_entry(mapping, page->index, page, radswap); page->mapping = NULL; mapping->nrpages--; __dec_node_page_state(page, NR_FILE_PAGES); @@ -1578,8 +1573,7 @@ static int shmem_replace_page(struct page **pagep, gfp_t gfp, * a nice clean interface for us to replace oldpage by newpage there. */ xa_lock_irq(&swap_mapping->i_pages); - error = shmem_radix_tree_replace(swap_mapping, swap_index, oldpage, - newpage); + error = shmem_replace_entry(swap_mapping, swap_index, oldpage, newpage); if (!error) { __inc_node_page_state(newpage, NR_FILE_PAGES); __dec_node_page_state(oldpage, NR_FILE_PAGES); -- cgit v1.2.3 From a12831bf4293d38518e41b80dd897af0122bb268 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Wed, 22 Nov 2017 08:34:58 -0500 Subject: shmem: Convert shmem_confirm_swap to XArray xa_load has its own RCU locking, so we can eliminate it here. Signed-off-by: Matthew Wilcox --- mm/shmem.c | 7 +------ 1 file changed, 1 insertion(+), 6 deletions(-) (limited to 'mm') diff --git a/mm/shmem.c b/mm/shmem.c index 5697c8fecdfc..ce91569426f3 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -349,12 +349,7 @@ static int shmem_replace_entry(struct address_space *mapping, static bool shmem_confirm_swap(struct address_space *mapping, pgoff_t index, swp_entry_t swap) { - void *item; - - rcu_read_lock(); - item = radix_tree_lookup(&mapping->i_pages, index); - rcu_read_unlock(); - return item == swp_to_radix_entry(swap); + return xa_load(&mapping->i_pages, index) == swp_to_radix_entry(swap); } /* -- cgit v1.2.3 From e21a29552fa3f44ea41c53488875015ae70fd7f8 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Wed, 22 Nov 2017 08:36:00 -0500 Subject: shmem: Convert find_swap_entry to XArray This is a 1:1 conversion. The major part of this patch is converting the test framework from userspace to kernel space and mirroring the algorithm now used in find_swap_entry(). Signed-off-by: Matthew Wilcox --- lib/test_xarray.c | 56 +++++++++++++++++++++++++++++++++++++ mm/shmem.c | 27 +++++++----------- tools/testing/radix-tree/main.c | 61 ----------------------------------------- tools/testing/radix-tree/test.c | 22 --------------- tools/testing/radix-tree/test.h | 1 - 5 files changed, 66 insertions(+), 101 deletions(-) (limited to 'mm') diff --git a/lib/test_xarray.c b/lib/test_xarray.c index 128c6489082f..815daffdd8c9 100644 --- a/lib/test_xarray.c +++ b/lib/test_xarray.c @@ -631,6 +631,61 @@ static noinline void check_find(struct xarray *xa) check_multi_find_2(xa); } +/* See find_swap_entry() in mm/shmem.c */ +static noinline unsigned long xa_find_entry(struct xarray *xa, void *item) +{ + XA_STATE(xas, xa, 0); + unsigned int checked = 0; + void *entry; + + rcu_read_lock(); + xas_for_each(&xas, entry, ULONG_MAX) { + if (xas_retry(&xas, entry)) + continue; + if (entry == item) + break; + checked++; + if ((checked % 4) != 0) + continue; + xas_pause(&xas); + } + rcu_read_unlock(); + + return entry ? xas.xa_index : -1; +} + +static noinline void check_find_entry(struct xarray *xa) +{ +#ifdef CONFIG_XARRAY_MULTI + unsigned int order; + unsigned long offset, index; + + for (order = 0; order < 20; order++) { + for (offset = 0; offset < (1UL << (order + 3)); + offset += (1UL << order)) { + for (index = 0; index < (1UL << (order + 5)); + index += (1UL << order)) { + xa_store_order(xa, index, order, + xa_mk_value(index), GFP_KERNEL); + XA_BUG_ON(xa, xa_load(xa, index) != + xa_mk_value(index)); + XA_BUG_ON(xa, xa_find_entry(xa, + xa_mk_value(index)) != index); + } + XA_BUG_ON(xa, xa_find_entry(xa, xa) != -1); + xa_destroy(xa); + } + } +#endif + + XA_BUG_ON(xa, xa_find_entry(xa, xa) != -1); + xa_store_index(xa, ULONG_MAX, GFP_KERNEL); + XA_BUG_ON(xa, xa_find_entry(xa, xa) != -1); + XA_BUG_ON(xa, xa_find_entry(xa, xa_mk_value(LONG_MAX)) != -1); + xa_erase_index(xa, ULONG_MAX); + XA_BUG_ON(xa, !xa_empty(xa)); +} + static noinline void check_move_small(struct xarray *xa, unsigned long idx) { XA_STATE(xas, xa, 0); @@ -972,6 +1027,7 @@ static int xarray_checks(void) check_multi_store(&array); check_xa_alloc(); check_find(&array); + check_find_entry(&array); check_destroy(&array); check_move(&array); check_create_range(&array); diff --git a/mm/shmem.c b/mm/shmem.c index ce91569426f3..a305529d6b89 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -1100,34 +1100,27 @@ static void shmem_evict_inode(struct inode *inode) clear_inode(inode); } -static unsigned long find_swap_entry(struct radix_tree_root *root, void *item) +static unsigned long find_swap_entry(struct xarray *xa, void *item) { - struct radix_tree_iter iter; - void __rcu **slot; - unsigned long found = -1; + XA_STATE(xas, xa, 0); unsigned int checked = 0; + void *entry; rcu_read_lock(); - radix_tree_for_each_slot(slot, root, &iter, 0) { - void *entry = radix_tree_deref_slot(slot); - - if (radix_tree_deref_retry(entry)) { - slot = radix_tree_iter_retry(&iter); + xas_for_each(&xas, entry, ULONG_MAX) { + if (xas_retry(&xas, entry)) continue; - } - if (entry == item) { - found = iter.index; + if (entry == item) break; - } checked++; - if ((checked % 4096) != 0) + if ((checked % XA_CHECK_SCHED) != 0) continue; - slot = radix_tree_iter_resume(slot, &iter); + xas_pause(&xas); cond_resched_rcu(); } - rcu_read_unlock(); - return found; + + return entry ? xas.xa_index : -1; } /* diff --git a/tools/testing/radix-tree/main.c b/tools/testing/radix-tree/main.c index 09deaf4f0959..79589ea570ab 100644 --- a/tools/testing/radix-tree/main.c +++ b/tools/testing/radix-tree/main.c @@ -236,63 +236,6 @@ void copy_tag_check(void) item_kill_tree(&tree); } -static void __locate_check(struct radix_tree_root *tree, unsigned long index, - unsigned order) -{ - struct item *item; - unsigned long index2; - - item_insert_order(tree, index, order); - item = item_lookup(tree, index); - index2 = find_item(tree, item); - if (index != index2) { - printv(2, "index %ld order %d inserted; found %ld\n", - index, order, index2); - abort(); - } -} - -static void __order_0_locate_check(void) -{ - RADIX_TREE(tree, GFP_KERNEL); - int i; - - for (i = 0; i < 50; i++) - __locate_check(&tree, rand() % INT_MAX, 0); - - item_kill_tree(&tree); -} - -static void locate_check(void) -{ - RADIX_TREE(tree, GFP_KERNEL); - unsigned order; - unsigned long offset, index; - - __order_0_locate_check(); - - for (order = 0; order < 20; order++) { - for (offset = 0; offset < (1 << (order + 3)); - offset += (1UL << order)) { - for (index = 0; index < (1UL << (order + 5)); - index += (1UL << order)) { - __locate_check(&tree, index + offset, order); - } - if (find_item(&tree, &tree) != -1) - abort(); - - item_kill_tree(&tree); - } - } - - if (find_item(&tree, &tree) != -1) - abort(); - __locate_check(&tree, -1, 0); - if (find_item(&tree, &tree) != -1) - abort(); - item_kill_tree(&tree); -} - static void single_thread_tests(bool long_run) { int i; @@ -303,10 +246,6 @@ static void single_thread_tests(bool long_run) rcu_barrier(); printv(2, "after multiorder_check: %d allocated, preempt %d\n", nr_allocated, preempt_count); - locate_check(); - rcu_barrier(); - printv(2, "after locate_check: %d allocated, preempt %d\n", - nr_allocated, preempt_count); tag_check(); rcu_barrier(); printv(2, "after tag_check: %d allocated, preempt %d\n", diff --git a/tools/testing/radix-tree/test.c b/tools/testing/radix-tree/test.c index 70ddf964d51c..470419bfd49d 100644 --- a/tools/testing/radix-tree/test.c +++ b/tools/testing/radix-tree/test.c @@ -209,28 +209,6 @@ int tag_tagged_items(struct radix_tree_root *root, pthread_mutex_t *lock, return tagged; } -/* Use the same pattern as find_swap_entry() in mm/shmem.c */ -unsigned long find_item(struct radix_tree_root *root, void *item) -{ - struct radix_tree_iter iter; - void **slot; - unsigned long found = -1; - unsigned long checked = 0; - - radix_tree_for_each_slot(slot, root, &iter, 0) { - if (*slot == item) { - found = iter.index; - break; - } - checked++; - if ((checked % 4) != 0) - continue; - slot = radix_tree_iter_resume(slot, &iter); - } - - return found; -} - static int verify_node(struct radix_tree_node *slot, unsigned int tag, int tagged) { diff --git a/tools/testing/radix-tree/test.h b/tools/testing/radix-tree/test.h index e3dc7a16f09b..9532c18c6cb1 100644 --- a/tools/testing/radix-tree/test.h +++ b/tools/testing/radix-tree/test.h @@ -32,7 +32,6 @@ void item_kill_tree(struct radix_tree_root *root); int tag_tagged_items(struct radix_tree_root *, pthread_mutex_t *, unsigned long start, unsigned long end, unsigned batch, unsigned iftag, unsigned thentag); -unsigned long find_item(struct radix_tree_root *, void *item); void xarray_tests(void); void tag_check(void); -- cgit v1.2.3 From 552446a4166189a8c2515571dd6e25fd64a2dc78 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Fri, 1 Dec 2017 13:25:14 -0500 Subject: shmem: Convert shmem_add_to_page_cache to XArray We can use xas_find_conflict() instead of radix_tree_gang_lookup_slot() to find any conflicting entry and combine the three paths through this function into one. Signed-off-by: Matthew Wilcox --- mm/shmem.c | 81 ++++++++++++++++++++++++++------------------------------------ 1 file changed, 34 insertions(+), 47 deletions(-) (limited to 'mm') diff --git a/mm/shmem.c b/mm/shmem.c index a305529d6b89..8633bd3dc433 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -577,9 +577,11 @@ static inline bool is_huge_enabled(struct shmem_sb_info *sbinfo) */ static int shmem_add_to_page_cache(struct page *page, struct address_space *mapping, - pgoff_t index, void *expected) + pgoff_t index, void *expected, gfp_t gfp) { - int error, nr = hpage_nr_pages(page); + XA_STATE_ORDER(xas, &mapping->i_pages, index, compound_order(page)); + unsigned long i = 0; + unsigned long nr = 1UL << compound_order(page); VM_BUG_ON_PAGE(PageTail(page), page); VM_BUG_ON_PAGE(index != round_down(index, nr), page); @@ -591,46 +593,39 @@ static int shmem_add_to_page_cache(struct page *page, page->mapping = mapping; page->index = index; - xa_lock_irq(&mapping->i_pages); - if (PageTransHuge(page)) { - void __rcu **results; - pgoff_t idx; - int i; - - error = 0; - if (radix_tree_gang_lookup_slot(&mapping->i_pages, - &results, &idx, index, 1) && - idx < index + HPAGE_PMD_NR) { - error = -EEXIST; + do { + void *entry; + xas_lock_irq(&xas); + entry = xas_find_conflict(&xas); + if (entry != expected) + xas_set_err(&xas, -EEXIST); + xas_create_range(&xas); + if (xas_error(&xas)) + goto unlock; +next: + xas_store(&xas, page + i); + if (++i < nr) { + xas_next(&xas); + goto next; } - - if (!error) { - for (i = 0; i < HPAGE_PMD_NR; i++) { - error = radix_tree_insert(&mapping->i_pages, - index + i, page + i); - VM_BUG_ON(error); - } + if (PageTransHuge(page)) { count_vm_event(THP_FILE_ALLOC); + __inc_node_page_state(page, NR_SHMEM_THPS); } - } else if (!expected) { - error = radix_tree_insert(&mapping->i_pages, index, page); - } else { - error = shmem_replace_entry(mapping, index, expected, page); - } - - if (!error) { mapping->nrpages += nr; - if (PageTransHuge(page)) - __inc_node_page_state(page, NR_SHMEM_THPS); __mod_node_page_state(page_pgdat(page), NR_FILE_PAGES, nr); __mod_node_page_state(page_pgdat(page), NR_SHMEM, nr); - xa_unlock_irq(&mapping->i_pages); - } else { +unlock: + xas_unlock_irq(&xas); + } while (xas_nomem(&xas, gfp)); + + if (xas_error(&xas)) { page->mapping = NULL; - xa_unlock_irq(&mapping->i_pages); page_ref_sub(page, nr); + return xas_error(&xas); } - return error; + + return 0; } /* @@ -1183,7 +1178,7 @@ static int shmem_unuse_inode(struct shmem_inode_info *info, */ if (!error) error = shmem_add_to_page_cache(*pagep, mapping, index, - radswap); + radswap, gfp); if (error != -ENOMEM) { /* * Truncation and eviction use free_swap_and_cache(), which @@ -1700,7 +1695,7 @@ repeat: false); if (!error) { error = shmem_add_to_page_cache(page, mapping, index, - swp_to_radix_entry(swap)); + swp_to_radix_entry(swap), gfp); /* * We already confirmed swap under page lock, and make * no memory allocation here, so usually no possibility @@ -1806,13 +1801,8 @@ alloc_nohuge: page = shmem_alloc_and_acct_page(gfp, inode, PageTransHuge(page)); if (error) goto unacct; - error = radix_tree_maybe_preload_order(gfp & GFP_RECLAIM_MASK, - compound_order(page)); - if (!error) { - error = shmem_add_to_page_cache(page, mapping, hindex, - NULL); - radix_tree_preload_end(); - } + error = shmem_add_to_page_cache(page, mapping, hindex, + NULL, gfp & GFP_RECLAIM_MASK); if (error) { mem_cgroup_cancel_charge(page, memcg, PageTransHuge(page)); @@ -2281,11 +2271,8 @@ static int shmem_mfill_atomic_pte(struct mm_struct *dst_mm, if (ret) goto out_release; - ret = radix_tree_maybe_preload(gfp & GFP_RECLAIM_MASK); - if (!ret) { - ret = shmem_add_to_page_cache(page, mapping, pgoff, NULL); - radix_tree_preload_end(); - } + ret = shmem_add_to_page_cache(page, mapping, pgoff, NULL, + gfp & GFP_RECLAIM_MASK); if (ret) goto out_release_uncharge; -- cgit v1.2.3 From 7b8d046fba91d62beb8a8f78244aaa3c23a60cdd Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Fri, 1 Dec 2017 22:13:06 -0500 Subject: shmem: Convert shmem_alloc_hugepage to XArray xa_find() is a slightly easier API to use than radix_tree_gang_lookup_slot() because it contains its own RCU locking. This commit removes the last user of radix_tree_gang_lookup_slot() so remove the function too. Signed-off-by: Matthew Wilcox --- include/linux/radix-tree.h | 6 +----- lib/radix-tree.c | 44 +------------------------------------------- mm/shmem.c | 14 ++++---------- 3 files changed, 6 insertions(+), 58 deletions(-) (limited to 'mm') diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h index 023e888e1163..8a4280bc350f 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -147,12 +147,11 @@ static inline unsigned int iter_shift(const struct radix_tree_iter *iter) * radix_tree_lookup_slot * radix_tree_tag_get * radix_tree_gang_lookup - * radix_tree_gang_lookup_slot * radix_tree_gang_lookup_tag * radix_tree_gang_lookup_tag_slot * radix_tree_tagged * - * The first 8 functions are able to be called locklessly, using RCU. The + * The first 7 functions are able to be called locklessly, using RCU. The * caller must ensure calls to these functions are made within rcu_read_lock() * regions. Other readers (lock-free or otherwise) and modifications may be * running concurrently. @@ -263,9 +262,6 @@ void radix_tree_clear_tags(struct radix_tree_root *, struct radix_tree_node *, unsigned int radix_tree_gang_lookup(const struct radix_tree_root *, void **results, unsigned long first_index, unsigned int max_items); -unsigned int radix_tree_gang_lookup_slot(const struct radix_tree_root *, - void __rcu ***results, unsigned long *indices, - unsigned long first_index, unsigned int max_items); int radix_tree_preload(gfp_t gfp_mask); int radix_tree_maybe_preload(gfp_t gfp_mask); int radix_tree_maybe_preload_order(gfp_t gfp_mask, int order); diff --git a/lib/radix-tree.c b/lib/radix-tree.c index 8a58051eb5b3..2f9c0e45eeb7 100644 --- a/lib/radix-tree.c +++ b/lib/radix-tree.c @@ -1097,7 +1097,7 @@ void __radix_tree_replace(struct radix_tree_root *root, * @slot: pointer to slot * @item: new item to store in the slot. * - * For use with radix_tree_lookup_slot(), radix_tree_gang_lookup_slot(), + * For use with radix_tree_lookup_slot() and * radix_tree_gang_lookup_tag_slot(). Caller must hold tree write locked * across slot lookup and replacement. * @@ -1731,48 +1731,6 @@ radix_tree_gang_lookup(const struct radix_tree_root *root, void **results, } EXPORT_SYMBOL(radix_tree_gang_lookup); -/** - * radix_tree_gang_lookup_slot - perform multiple slot lookup on radix tree - * @root: radix tree root - * @results: where the results of the lookup are placed - * @indices: where their indices should be placed (but usually NULL) - * @first_index: start the lookup from this key - * @max_items: place up to this many items at *results - * - * Performs an index-ascending scan of the tree for present items. Places - * their slots at *@results and returns the number of items which were - * placed at *@results. - * - * The implementation is naive. - * - * Like radix_tree_gang_lookup as far as RCU and locking goes. Slots must - * be dereferenced with radix_tree_deref_slot, and if using only RCU - * protection, radix_tree_deref_slot may fail requiring a retry. - */ -unsigned int -radix_tree_gang_lookup_slot(const struct radix_tree_root *root, - void __rcu ***results, unsigned long *indices, - unsigned long first_index, unsigned int max_items) -{ - struct radix_tree_iter iter; - void __rcu **slot; - unsigned int ret = 0; - - if (unlikely(!max_items)) - return 0; - - radix_tree_for_each_slot(slot, root, &iter, first_index) { - results[ret] = slot; - if (indices) - indices[ret] = iter.index; - if (++ret == max_items) - break; - } - - return ret; -} -EXPORT_SYMBOL(radix_tree_gang_lookup_slot); - /** * radix_tree_gang_lookup_tag - perform multiple lookup on a radix tree * based on a tag diff --git a/mm/shmem.c b/mm/shmem.c index 8633bd3dc433..608c9252248f 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -1431,23 +1431,17 @@ static struct page *shmem_alloc_hugepage(gfp_t gfp, struct shmem_inode_info *info, pgoff_t index) { struct vm_area_struct pvma; - struct inode *inode = &info->vfs_inode; - struct address_space *mapping = inode->i_mapping; - pgoff_t idx, hindex; - void __rcu **results; + struct address_space *mapping = info->vfs_inode.i_mapping; + pgoff_t hindex; struct page *page; if (!IS_ENABLED(CONFIG_TRANSPARENT_HUGE_PAGECACHE)) return NULL; hindex = round_down(index, HPAGE_PMD_NR); - rcu_read_lock(); - if (radix_tree_gang_lookup_slot(&mapping->i_pages, &results, &idx, - hindex, 1) && idx < hindex + HPAGE_PMD_NR) { - rcu_read_unlock(); + if (xa_find(&mapping->i_pages, &hindex, hindex + HPAGE_PMD_NR - 1, + XA_PRESENT)) return NULL; - } - rcu_read_unlock(); shmem_pseudo_vma_init(&pvma, info, hindex); page = alloc_pages_vma(gfp | __GFP_COMP | __GFP_NORETRY | __GFP_NOWARN, -- cgit v1.2.3 From c121d3bb717ee932caf031c6a7923547f7f83163 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Mon, 4 Dec 2017 03:13:54 -0500 Subject: shmem: Convert shmem_free_swap to XArray Since we are conditionally storing NULL in the XArray, we do not need to allocate memory and the GFP flags will be unused. Signed-off-by: Matthew Wilcox --- mm/shmem.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'mm') diff --git a/mm/shmem.c b/mm/shmem.c index 608c9252248f..8e9bbfb7ed15 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -650,7 +650,7 @@ static void shmem_delete_from_page_cache(struct page *page, void *radswap) } /* - * Remove swap entry from radix tree, free the swap and its page cache. + * Remove swap entry from page cache, free the swap and its page cache. */ static int shmem_free_swap(struct address_space *mapping, pgoff_t index, void *radswap) @@ -658,7 +658,7 @@ static int shmem_free_swap(struct address_space *mapping, void *old; xa_lock_irq(&mapping->i_pages); - old = radix_tree_delete_item(&mapping->i_pages, index, radswap); + old = __xa_cmpxchg(&mapping->i_pages, index, radswap, NULL, 0); xa_unlock_irq(&mapping->i_pages); if (old != radswap) return -ENOENT; -- cgit v1.2.3 From 7ae3424fb4b5587d9b2db12a4b1040c52073dd5c Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Mon, 4 Dec 2017 03:28:00 -0500 Subject: shmem: Convert shmem_partial_swap_usage to XArray Simpler code because the xarray takes care of things like the limit and dereferencing the slot. Signed-off-by: Matthew Wilcox --- mm/shmem.c | 18 ++++-------------- 1 file changed, 4 insertions(+), 14 deletions(-) (limited to 'mm') diff --git a/mm/shmem.c b/mm/shmem.c index 8e9bbfb7ed15..5588205f4259 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -676,29 +676,19 @@ static int shmem_free_swap(struct address_space *mapping, unsigned long shmem_partial_swap_usage(struct address_space *mapping, pgoff_t start, pgoff_t end) { - struct radix_tree_iter iter; - void __rcu **slot; + XA_STATE(xas, &mapping->i_pages, start); struct page *page; unsigned long swapped = 0; rcu_read_lock(); - - radix_tree_for_each_slot(slot, &mapping->i_pages, &iter, start) { - if (iter.index >= end) - break; - - page = radix_tree_deref_slot(slot); - - if (radix_tree_deref_retry(page)) { - slot = radix_tree_iter_retry(&iter); + xas_for_each(&xas, page, end - 1) { + if (xas_retry(&xas, page)) continue; - } - if (xa_is_value(page)) swapped++; if (need_resched()) { - slot = radix_tree_iter_resume(slot, &iter); + xas_pause(&xas); cond_resched_rcu(); } } -- cgit v1.2.3 From 2313216f861f955c2091f1593ea95d5dc88493f4 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Wed, 22 Nov 2017 11:11:31 -0500 Subject: memfd: Convert memfd_wait_for_pins to XArray Simplify the locking by taking the spinlock while we walk the tree on the assumption that many acquires and releases of the lock will be worse than holding the lock while we process an entire batch of pages. Signed-off-by: Matthew Wilcox Reviewed-by: Mike Kravetz --- mm/memfd.c | 61 +++++++++++++++++++++++++------------------------------------ 1 file changed, 25 insertions(+), 36 deletions(-) (limited to 'mm') diff --git a/mm/memfd.c b/mm/memfd.c index 2bb5e257080e..cf0ddd5fc859 100644 --- a/mm/memfd.c +++ b/mm/memfd.c @@ -21,7 +21,7 @@ #include /* - * We need a tag: a new tag would expand every radix_tree_node by 8 bytes, + * We need a tag: a new tag would expand every xa_node by 8 bytes, * so reuse a tag which we firmly believe is never set or cleared on tmpfs * or hugetlbfs because they are memory only filesystems. */ @@ -72,9 +72,7 @@ static void memfd_tag_pins(struct address_space *mapping) */ static int memfd_wait_for_pins(struct address_space *mapping) { - struct radix_tree_iter iter; - void __rcu **slot; - pgoff_t start; + XA_STATE(xas, &mapping->i_pages, 0); struct page *page; int error, scan; @@ -82,7 +80,9 @@ static int memfd_wait_for_pins(struct address_space *mapping) error = 0; for (scan = 0; scan <= LAST_SCAN; scan++) { - if (!radix_tree_tagged(&mapping->i_pages, MEMFD_TAG_PINNED)) + unsigned int tagged = 0; + + if (!xas_marked(&xas, MEMFD_TAG_PINNED)) break; if (!scan) @@ -90,45 +90,34 @@ static int memfd_wait_for_pins(struct address_space *mapping) else if (schedule_timeout_killable((HZ << scan) / 200)) scan = LAST_SCAN; - start = 0; - rcu_read_lock(); - radix_tree_for_each_tagged(slot, &mapping->i_pages, &iter, - start, MEMFD_TAG_PINNED) { - - page = radix_tree_deref_slot(slot); - if (radix_tree_exception(page)) { - if (radix_tree_deref_retry(page)) { - slot = radix_tree_iter_retry(&iter); - continue; - } - - page = NULL; - } - - if (page && - page_count(page) - page_mapcount(page) != 1) { - if (scan < LAST_SCAN) - goto continue_resched; - + xas_set(&xas, 0); + xas_lock_irq(&xas); + xas_for_each_marked(&xas, page, ULONG_MAX, MEMFD_TAG_PINNED) { + bool clear = true; + if (xa_is_value(page)) + continue; + if (page_count(page) - page_mapcount(page) != 1) { /* * On the last scan, we clean up all those tags * we inserted; but make a note that we still * found pages pinned. */ - error = -EBUSY; + if (scan == LAST_SCAN) + error = -EBUSY; + else + clear = false; } + if (clear) + xas_clear_mark(&xas, MEMFD_TAG_PINNED); + if (++tagged % XA_CHECK_SCHED) + continue; - xa_lock_irq(&mapping->i_pages); - radix_tree_tag_clear(&mapping->i_pages, - iter.index, MEMFD_TAG_PINNED); - xa_unlock_irq(&mapping->i_pages); -continue_resched: - if (need_resched()) { - slot = radix_tree_iter_resume(slot, &iter); - cond_resched_rcu(); - } + xas_pause(&xas); + xas_unlock_irq(&xas); + cond_resched(); + xas_lock_irq(&xas); } - rcu_read_unlock(); + xas_unlock_irq(&xas); } return error; -- cgit v1.2.3 From ef3038a573aa8bf2f3797b110f7244b55a0e519c Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Wed, 22 Nov 2017 08:37:38 -0500 Subject: memfd: Convert memfd_tag_pins to XArray Switch to a batch-processing model like memfd_wait_for_pins() and use the xa_state previously set up by memfd_wait_for_pins(). Signed-off-by: Matthew Wilcox Reviewed-by: Mike Kravetz --- mm/memfd.c | 44 ++++++++++++++++++-------------------------- 1 file changed, 18 insertions(+), 26 deletions(-) (limited to 'mm') diff --git a/mm/memfd.c b/mm/memfd.c index cf0ddd5fc859..97264c79d2cd 100644 --- a/mm/memfd.c +++ b/mm/memfd.c @@ -28,37 +28,29 @@ #define MEMFD_TAG_PINNED PAGECACHE_TAG_TOWRITE #define LAST_SCAN 4 /* about 150ms max */ -static void memfd_tag_pins(struct address_space *mapping) +static void memfd_tag_pins(struct xa_state *xas) { - struct radix_tree_iter iter; - void __rcu **slot; - pgoff_t start; struct page *page; + unsigned int tagged = 0; lru_add_drain(); - start = 0; - rcu_read_lock(); - - radix_tree_for_each_slot(slot, &mapping->i_pages, &iter, start) { - page = radix_tree_deref_slot(slot); - if (!page || radix_tree_exception(page)) { - if (radix_tree_deref_retry(page)) { - slot = radix_tree_iter_retry(&iter); - continue; - } - } else if (page_count(page) - page_mapcount(page) > 1) { - xa_lock_irq(&mapping->i_pages); - radix_tree_tag_set(&mapping->i_pages, iter.index, - MEMFD_TAG_PINNED); - xa_unlock_irq(&mapping->i_pages); - } - if (need_resched()) { - slot = radix_tree_iter_resume(slot, &iter); - cond_resched_rcu(); - } + xas_lock_irq(xas); + xas_for_each(xas, page, ULONG_MAX) { + if (xa_is_value(page)) + continue; + if (page_count(page) - page_mapcount(page) > 1) + xas_set_mark(xas, MEMFD_TAG_PINNED); + + if (++tagged % XA_CHECK_SCHED) + continue; + + xas_pause(xas); + xas_unlock_irq(xas); + cond_resched(); + xas_lock_irq(xas); } - rcu_read_unlock(); + xas_unlock_irq(xas); } /* @@ -76,7 +68,7 @@ static int memfd_wait_for_pins(struct address_space *mapping) struct page *page; int error, scan; - memfd_tag_pins(mapping); + memfd_tag_pins(&xas); error = 0; for (scan = 0; scan <= LAST_SCAN; scan++) { -- cgit v1.2.3 From 7f4446eefe9fbbe68e9543946c9a20f67897ff9b Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Mon, 4 Dec 2017 03:31:13 -0500 Subject: shmem: Comment fixups Remove the last mentions of radix tree from various comments. Signed-off-by: Matthew Wilcox --- mm/shmem.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-) (limited to 'mm') diff --git a/mm/shmem.c b/mm/shmem.c index 5588205f4259..56bf122e0bb4 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -763,7 +763,7 @@ void shmem_unlock_mapping(struct address_space *mapping) } /* - * Remove range of pages and swap entries from radix tree, and free them. + * Remove range of pages and swap entries from page cache, and free them. * If !unfalloc, truncate or punch hole; if unfalloc, undo failed fallocate. */ static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend, @@ -1143,10 +1143,10 @@ static int shmem_unuse_inode(struct shmem_inode_info *info, * We needed to drop mutex to make that restrictive page * allocation, but the inode might have been freed while we * dropped it: although a racing shmem_evict_inode() cannot - * complete without emptying the radix_tree, our page lock + * complete without emptying the page cache, our page lock * on this swapcache page is not enough to prevent that - * free_swap_and_cache() of our swap entry will only - * trylock_page(), removing swap from radix_tree whatever. + * trylock_page(), removing swap from page cache whatever. * * We must not proceed to shmem_add_to_page_cache() if the * inode has been freed, but of course we cannot rely on @@ -1212,7 +1212,7 @@ int shmem_unuse(swp_entry_t swap, struct page *page) &memcg, false); if (error) goto out; - /* No radix_tree_preload: swap entry keeps a place for page in tree */ + /* No memory allocation: swap entry occupies the slot for the page */ error = -EAGAIN; mutex_lock(&shmem_swaplist_mutex); @@ -1887,7 +1887,7 @@ unlock: spin_unlock_irq(&info->lock); goto repeat; } - if (error == -EEXIST) /* from above or from radix_tree_insert */ + if (error == -EEXIST) goto repeat; return error; } @@ -2501,7 +2501,7 @@ static ssize_t shmem_file_read_iter(struct kiocb *iocb, struct iov_iter *to) } /* - * llseek SEEK_DATA or SEEK_HOLE through the radix_tree. + * llseek SEEK_DATA or SEEK_HOLE through the page cache. */ static pgoff_t shmem_seek_hole_data(struct address_space *mapping, pgoff_t index, pgoff_t end, int whence) -- cgit v1.2.3 From a28334862993b5c6a8766f6963ee69048403817c Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Tue, 5 Dec 2017 19:04:20 -0500 Subject: page cache: Finish XArray conversion With no more radix tree API users left, we can drop the GFP flags and use xa_init() instead of INIT_RADIX_TREE(). Signed-off-by: Matthew Wilcox --- fs/inode.c | 2 +- mm/swap_state.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'mm') diff --git a/fs/inode.c b/fs/inode.c index 42f6d25f32a5..9b808986d440 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -349,7 +349,7 @@ EXPORT_SYMBOL(inc_nlink); static void __address_space_init_once(struct address_space *mapping) { - INIT_RADIX_TREE(&mapping->i_pages, GFP_ATOMIC | __GFP_ACCOUNT); + xa_init_flags(&mapping->i_pages, XA_FLAGS_LOCK_IRQ); init_rwsem(&mapping->i_mmap_rwsem); INIT_LIST_HEAD(&mapping->private_list); spin_lock_init(&mapping->private_lock); diff --git a/mm/swap_state.c b/mm/swap_state.c index f393c994cc60..31c45a25b2d3 100644 --- a/mm/swap_state.c +++ b/mm/swap_state.c @@ -586,7 +586,7 @@ int init_swap_address_space(unsigned int type, unsigned long nr_pages) return -ENOMEM; for (i = 0; i < nr; i++) { space = spaces + i; - INIT_RADIX_TREE(&space->i_pages, GFP_ATOMIC|__GFP_NOWARN); + xa_init_flags(&space->i_pages, XA_FLAGS_LOCK_IRQ); atomic_set(&space->i_mmap_writable, 0); space->a_ops = &swap_aops; /* swap cache doesn't use writeback related tags */ -- cgit v1.2.3 From 3a08cd52c37c793ffc199f6fc2ecfc368e284b2d Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Sat, 22 Sep 2018 16:14:30 -0400 Subject: radix tree: Remove multiorder support All users have now been converted to the XArray. Removing the support reduces code size and ensures new users will use the XArray instead. Signed-off-by: Matthew Wilcox --- include/linux/radix-tree.h | 40 +---- lib/Kconfig | 4 - lib/radix-tree.c | 215 ++------------------------ mm/Kconfig | 4 +- tools/testing/radix-tree/generated/autoconf.h | 1 - 5 files changed, 19 insertions(+), 245 deletions(-) (limited to 'mm') diff --git a/include/linux/radix-tree.h b/include/linux/radix-tree.h index 9a1460488163..06c4c7a6c09c 100644 --- a/include/linux/radix-tree.h +++ b/include/linux/radix-tree.h @@ -96,7 +96,6 @@ static inline bool radix_tree_empty(const struct radix_tree_root *root) * @next_index: one beyond the last index for this chunk * @tags: bit-mask for tag-iterating * @node: node that contains current slot - * @shift: shift for the node that holds our slots * * This radix tree iterator works in terms of "chunks" of slots. A chunk is a * subinterval of slots contained within one radix tree leaf node. It is @@ -110,20 +109,8 @@ struct radix_tree_iter { unsigned long next_index; unsigned long tags; struct radix_tree_node *node; -#ifdef CONFIG_RADIX_TREE_MULTIORDER - unsigned int shift; -#endif }; -static inline unsigned int iter_shift(const struct radix_tree_iter *iter) -{ -#ifdef CONFIG_RADIX_TREE_MULTIORDER - return iter->shift; -#else - return 0; -#endif -} - /** * Radix-tree synchronization * @@ -230,13 +217,8 @@ static inline int radix_tree_exception(void *arg) return unlikely((unsigned long)arg & RADIX_TREE_ENTRY_MASK); } -int __radix_tree_insert(struct radix_tree_root *, unsigned long index, - unsigned order, void *); -static inline int radix_tree_insert(struct radix_tree_root *root, - unsigned long index, void *entry) -{ - return __radix_tree_insert(root, index, 0, entry); -} +int radix_tree_insert(struct radix_tree_root *, unsigned long index, + void *); void *__radix_tree_lookup(const struct radix_tree_root *, unsigned long index, struct radix_tree_node **nodep, void __rcu ***slotp); void *radix_tree_lookup(const struct radix_tree_root *, unsigned long); @@ -384,7 +366,7 @@ void __rcu **radix_tree_iter_retry(struct radix_tree_iter *iter) static inline unsigned long __radix_tree_iter_add(struct radix_tree_iter *iter, unsigned long slots) { - return iter->index + (slots << iter_shift(iter)); + return iter->index + slots; } /** @@ -409,20 +391,8 @@ void __rcu **__must_check radix_tree_iter_resume(void __rcu **slot, static __always_inline long radix_tree_chunk_size(struct radix_tree_iter *iter) { - return (iter->next_index - iter->index) >> iter_shift(iter); -} - -#ifdef CONFIG_RADIX_TREE_MULTIORDER -void __rcu **__radix_tree_next_slot(void __rcu **slot, - struct radix_tree_iter *iter, unsigned flags); -#else -/* Can't happen without sibling entries, but the compiler can't tell that */ -static inline void __rcu **__radix_tree_next_slot(void __rcu **slot, - struct radix_tree_iter *iter, unsigned flags) -{ - return slot; + return iter->next_index - iter->index; } -#endif /** * radix_tree_next_slot - find next slot in chunk @@ -482,8 +452,6 @@ static __always_inline void __rcu **radix_tree_next_slot(void __rcu **slot, return NULL; found: - if (unlikely(radix_tree_is_internal_node(rcu_dereference_raw(*slot)))) - return __radix_tree_next_slot(slot, iter, flags); return slot; } diff --git a/lib/Kconfig b/lib/Kconfig index 40bfa6ccd294..a9965f4af4dd 100644 --- a/lib/Kconfig +++ b/lib/Kconfig @@ -405,10 +405,6 @@ config XARRAY_MULTI Support entries which occupy multiple consecutive indices in the XArray. -config RADIX_TREE_MULTIORDER - bool - select XARRAY_MULTI - config ASSOCIATIVE_ARRAY bool help diff --git a/lib/radix-tree.c b/lib/radix-tree.c index f107dd2698e3..1106bb6aa01e 100644 --- a/lib/radix-tree.c +++ b/lib/radix-tree.c @@ -110,11 +110,6 @@ static unsigned int radix_tree_descend(const struct radix_tree_node *parent, unsigned int offset = (index >> parent->shift) & RADIX_TREE_MAP_MASK; void __rcu **entry = rcu_dereference_raw(parent->slots[offset]); - if (xa_is_sibling(entry)) { - offset = xa_to_sibling(entry); - entry = rcu_dereference_raw(parent->slots[offset]); - } - *nodep = (void *)entry; return offset; } @@ -229,7 +224,7 @@ radix_tree_find_next_bit(struct radix_tree_node *node, unsigned int tag, static unsigned int iter_offset(const struct radix_tree_iter *iter) { - return (iter->index >> iter_shift(iter)) & RADIX_TREE_MAP_MASK; + return iter->index & RADIX_TREE_MAP_MASK; } /* @@ -506,16 +501,13 @@ static inline bool radix_tree_shrink(struct radix_tree_root *root) /* * The candidate node has more than one child, or its child - * is not at the leftmost slot, or the child is a multiorder - * entry, we cannot shrink. + * is not at the leftmost slot, we cannot shrink. */ if (node->count != 1) break; child = rcu_dereference_raw(node->slots[0]); if (!child) break; - if (!radix_tree_is_internal_node(child) && node->shift) - break; /* * For an IDR, we must not shrink entry 0 into the root in @@ -613,7 +605,6 @@ static bool delete_node(struct radix_tree_root *root, * __radix_tree_create - create a slot in a radix tree * @root: radix tree root * @index: index key - * @order: index occupies 2^order aligned slots * @nodep: returns node * @slotp: returns slot * @@ -627,21 +618,19 @@ static bool delete_node(struct radix_tree_root *root, * Returns -ENOMEM, or 0 for success. */ static int __radix_tree_create(struct radix_tree_root *root, - unsigned long index, unsigned order, - struct radix_tree_node **nodep, void __rcu ***slotp) + unsigned long index, struct radix_tree_node **nodep, + void __rcu ***slotp) { struct radix_tree_node *node = NULL, *child; void __rcu **slot = (void __rcu **)&root->xa_head; unsigned long maxindex; unsigned int shift, offset = 0; - unsigned long max = index | ((1UL << order) - 1); + unsigned long max = index; gfp_t gfp = root_gfp_mask(root); shift = radix_tree_load_root(root, &child, &maxindex); /* Make sure the tree is high enough. */ - if (order > 0 && max == ((1UL << order) - 1)) - max++; if (max > maxindex) { int error = radix_tree_extend(root, gfp, max, shift); if (error < 0) @@ -650,7 +639,7 @@ static int __radix_tree_create(struct radix_tree_root *root, child = rcu_dereference_raw(root->xa_head); } - while (shift > order) { + while (shift > 0) { shift -= RADIX_TREE_MAP_SHIFT; if (child == NULL) { /* Have to add a child node. */ @@ -711,70 +700,8 @@ static void radix_tree_free_nodes(struct radix_tree_node *node) } } -#ifdef CONFIG_RADIX_TREE_MULTIORDER -static inline int insert_entries(struct radix_tree_node *node, - void __rcu **slot, void *item, unsigned order, bool replace) -{ - void *sibling; - unsigned i, n, tag, offset, tags = 0; - - if (node) { - if (order > node->shift) - n = 1 << (order - node->shift); - else - n = 1; - offset = get_slot_offset(node, slot); - } else { - n = 1; - offset = 0; - } - - if (n > 1) { - offset = offset & ~(n - 1); - slot = &node->slots[offset]; - } - sibling = xa_mk_sibling(offset); - - for (i = 0; i < n; i++) { - if (slot[i]) { - if (replace) { - node->count--; - for (tag = 0; tag < RADIX_TREE_MAX_TAGS; tag++) - if (tag_get(node, tag, offset + i)) - tags |= 1 << tag; - } else - return -EEXIST; - } - } - - for (i = 0; i < n; i++) { - struct radix_tree_node *old = rcu_dereference_raw(slot[i]); - if (i) { - rcu_assign_pointer(slot[i], sibling); - for (tag = 0; tag < RADIX_TREE_MAX_TAGS; tag++) - if (tags & (1 << tag)) - tag_clear(node, tag, offset + i); - } else { - rcu_assign_pointer(slot[i], item); - for (tag = 0; tag < RADIX_TREE_MAX_TAGS; tag++) - if (tags & (1 << tag)) - tag_set(node, tag, offset); - } - if (xa_is_node(old)) - radix_tree_free_nodes(old); - if (xa_is_value(old)) - node->nr_values--; - } - if (node) { - node->count += n; - if (xa_is_value(item)) - node->nr_values += n; - } - return n; -} -#else static inline int insert_entries(struct radix_tree_node *node, - void __rcu **slot, void *item, unsigned order, bool replace) + void __rcu **slot, void *item, bool replace) { if (*slot) return -EEXIST; @@ -786,19 +713,17 @@ static inline int insert_entries(struct radix_tree_node *node, } return 1; } -#endif /** * __radix_tree_insert - insert into a radix tree * @root: radix tree root * @index: index key - * @order: key covers the 2^order indices around index * @item: item to insert * * Insert an item into the radix tree at position @index. */ -int __radix_tree_insert(struct radix_tree_root *root, unsigned long index, - unsigned order, void *item) +int radix_tree_insert(struct radix_tree_root *root, unsigned long index, + void *item) { struct radix_tree_node *node; void __rcu **slot; @@ -806,11 +731,11 @@ int __radix_tree_insert(struct radix_tree_root *root, unsigned long index, BUG_ON(radix_tree_is_internal_node(item)); - error = __radix_tree_create(root, index, order, &node, &slot); + error = __radix_tree_create(root, index, &node, &slot); if (error) return error; - error = insert_entries(node, slot, item, order, false); + error = insert_entries(node, slot, item, false); if (error < 0) return error; @@ -825,7 +750,7 @@ int __radix_tree_insert(struct radix_tree_root *root, unsigned long index, return 0; } -EXPORT_SYMBOL(__radix_tree_insert); +EXPORT_SYMBOL(radix_tree_insert); /** * __radix_tree_lookup - lookup an item in a radix tree @@ -917,32 +842,12 @@ void *radix_tree_lookup(const struct radix_tree_root *root, unsigned long index) } EXPORT_SYMBOL(radix_tree_lookup); -static inline void replace_sibling_entries(struct radix_tree_node *node, - void __rcu **slot, int count, int values) -{ -#ifdef CONFIG_RADIX_TREE_MULTIORDER - unsigned offset = get_slot_offset(node, slot); - void *ptr = xa_mk_sibling(offset); - - while (++offset < RADIX_TREE_MAP_SIZE) { - if (rcu_dereference_raw(node->slots[offset]) != ptr) - break; - if (count < 0) { - node->slots[offset] = NULL; - node->count--; - } - node->nr_values += values; - } -#endif -} - static void replace_slot(void __rcu **slot, void *item, struct radix_tree_node *node, int count, int values) { if (node && (count || values)) { node->count += count; node->nr_values += values; - replace_sibling_entries(node, slot, count, values); } rcu_assign_pointer(*slot, item); @@ -1223,14 +1128,6 @@ int radix_tree_tag_get(const struct radix_tree_root *root, } EXPORT_SYMBOL(radix_tree_tag_get); -static inline void __set_iter_shift(struct radix_tree_iter *iter, - unsigned int shift) -{ -#ifdef CONFIG_RADIX_TREE_MULTIORDER - iter->shift = shift; -#endif -} - /* Construct iter->tags bit-mask from node->tags[tag] array */ static void set_iter_tags(struct radix_tree_iter *iter, struct radix_tree_node *node, unsigned offset, @@ -1257,92 +1154,11 @@ static void set_iter_tags(struct radix_tree_iter *iter, } } -#ifdef CONFIG_RADIX_TREE_MULTIORDER -static void __rcu **skip_siblings(struct radix_tree_node **nodep, - void __rcu **slot, struct radix_tree_iter *iter) -{ - while (iter->index < iter->next_index) { - *nodep = rcu_dereference_raw(*slot); - if (*nodep && !xa_is_sibling(*nodep)) - return slot; - slot++; - iter->index = __radix_tree_iter_add(iter, 1); - iter->tags >>= 1; - } - - *nodep = NULL; - return NULL; -} - -void __rcu **__radix_tree_next_slot(void __rcu **slot, - struct radix_tree_iter *iter, unsigned flags) -{ - unsigned tag = flags & RADIX_TREE_ITER_TAG_MASK; - struct radix_tree_node *node; - - slot = skip_siblings(&node, slot, iter); - - while (radix_tree_is_internal_node(node)) { - unsigned offset; - unsigned long next_index; - - if (node == RADIX_TREE_RETRY) - return slot; - node = entry_to_node(node); - iter->node = node; - iter->shift = node->shift; - - if (flags & RADIX_TREE_ITER_TAGGED) { - offset = radix_tree_find_next_bit(node, tag, 0); - if (offset == RADIX_TREE_MAP_SIZE) - return NULL; - slot = &node->slots[offset]; - iter->index = __radix_tree_iter_add(iter, offset); - set_iter_tags(iter, node, offset, tag); - node = rcu_dereference_raw(*slot); - } else { - offset = 0; - slot = &node->slots[0]; - for (;;) { - node = rcu_dereference_raw(*slot); - if (node) - break; - slot++; - offset++; - if (offset == RADIX_TREE_MAP_SIZE) - return NULL; - } - iter->index = __radix_tree_iter_add(iter, offset); - } - if ((flags & RADIX_TREE_ITER_CONTIG) && (offset > 0)) - goto none; - next_index = (iter->index | shift_maxindex(iter->shift)) + 1; - if (next_index < iter->next_index) - iter->next_index = next_index; - } - - return slot; - none: - iter->next_index = 0; - return NULL; -} -EXPORT_SYMBOL(__radix_tree_next_slot); -#else -static void __rcu **skip_siblings(struct radix_tree_node **nodep, - void __rcu **slot, struct radix_tree_iter *iter) -{ - return slot; -} -#endif - void __rcu **radix_tree_iter_resume(void __rcu **slot, struct radix_tree_iter *iter) { - struct radix_tree_node *node; - slot++; iter->index = __radix_tree_iter_add(iter, 1); - skip_siblings(&node, slot, iter); iter->next_index = iter->index; iter->tags = 0; return NULL; @@ -1393,7 +1209,6 @@ void __rcu **radix_tree_next_chunk(const struct radix_tree_root *root, iter->next_index = maxindex + 1; iter->tags = 1; iter->node = NULL; - __set_iter_shift(iter, 0); return (void __rcu **)&root->xa_head; } @@ -1414,8 +1229,6 @@ void __rcu **radix_tree_next_chunk(const struct radix_tree_root *root, while (++offset < RADIX_TREE_MAP_SIZE) { void *slot = rcu_dereference_raw( node->slots[offset]); - if (xa_is_sibling(slot)) - continue; if (slot) break; } @@ -1436,10 +1249,9 @@ void __rcu **radix_tree_next_chunk(const struct radix_tree_root *root, } while (node->shift && radix_tree_is_internal_node(child)); /* Update the iterator state */ - iter->index = (index &~ node_maxindex(node)) | (offset << node->shift); + iter->index = (index &~ node_maxindex(node)) | offset; iter->next_index = (index | node_maxindex(node)) + 1; iter->node = node; - __set_iter_shift(iter, node->shift); if (flags & RADIX_TREE_ITER_TAGGED) set_iter_tags(iter, node, offset, tag); @@ -1750,7 +1562,6 @@ void __rcu **idr_get_free(struct radix_tree_root *root, else iter->next_index = 1; iter->node = node; - __set_iter_shift(iter, shift); set_iter_tags(iter, node, offset, IDR_FREE); return slot; diff --git a/mm/Kconfig b/mm/Kconfig index de64ea658716..02301a89089e 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -379,7 +379,7 @@ config TRANSPARENT_HUGEPAGE bool "Transparent Hugepage Support" depends on HAVE_ARCH_TRANSPARENT_HUGEPAGE select COMPACTION - select RADIX_TREE_MULTIORDER + select XARRAY_MULTI help Transparent Hugepages allows the kernel to use huge pages and huge tlb transparently to the applications whenever possible. @@ -671,7 +671,7 @@ config ZONE_DEVICE depends on MEMORY_HOTREMOVE depends on SPARSEMEM_VMEMMAP depends on ARCH_HAS_ZONE_DEVICE - select RADIX_TREE_MULTIORDER + select XARRAY_MULTI help Device memory hotplug support allows for establishing pmem, diff --git a/tools/testing/radix-tree/generated/autoconf.h b/tools/testing/radix-tree/generated/autoconf.h index ca8e03ad19ac..2218b3cc184e 100644 --- a/tools/testing/radix-tree/generated/autoconf.h +++ b/tools/testing/radix-tree/generated/autoconf.h @@ -1,2 +1 @@ -#define CONFIG_RADIX_TREE_MULTIORDER 1 #define CONFIG_XARRAY_MULTI 1 -- cgit v1.2.3 From 00e23707442a75b404392cef1405ab4fd498de6b Mon Sep 17 00:00:00 2001 From: David Howells Date: Mon, 22 Oct 2018 13:07:28 +0100 Subject: iov_iter: Use accessor function Use accessor functions to access an iterator's type and direction. This allows for the possibility of using some other method of determining the type of iterator than if-chains with bitwise-AND conditions. Signed-off-by: David Howells --- block/bio.c | 2 +- fs/block_dev.c | 2 +- fs/ceph/file.c | 2 +- fs/cifs/file.c | 4 ++-- fs/cifs/misc.c | 2 +- fs/cifs/smbdirect.c | 17 ++++++++++++---- fs/direct-io.c | 2 +- fs/fuse/file.c | 2 +- fs/iomap.c | 2 +- include/linux/uio.h | 48 +++++++++++++++++++++++++++++-------------- lib/iov_iter.c | 56 +++++++++++++++++++++++++-------------------------- mm/filemap.c | 2 +- net/9p/trans_virtio.c | 2 +- net/tls/tls_sw.c | 4 ++-- 14 files changed, 87 insertions(+), 60 deletions(-) (limited to 'mm') diff --git a/block/bio.c b/block/bio.c index 0093bed81c0e..c55f36bbe12a 100644 --- a/block/bio.c +++ b/block/bio.c @@ -1255,7 +1255,7 @@ struct bio *bio_copy_user_iov(struct request_queue *q, /* * success */ - if (((iter->type & WRITE) && (!map_data || !map_data->null_mapped)) || + if ((iov_iter_rw(iter) == WRITE && (!map_data || !map_data->null_mapped)) || (map_data && map_data->from_user)) { ret = bio_copy_from_iter(bio, iter); if (ret) diff --git a/fs/block_dev.c b/fs/block_dev.c index 38b8ce05cbc7..a80b4f0ee7c4 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -349,7 +349,7 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages) dio->size = 0; dio->multi_bio = false; - dio->should_dirty = is_read && (iter->type == ITER_IOVEC); + dio->should_dirty = is_read && iter_is_iovec(iter); blk_start_plug(&plug); for (;;) { diff --git a/fs/ceph/file.c b/fs/ceph/file.c index 92ab20433682..524ecc95b04d 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -658,7 +658,7 @@ static ssize_t ceph_sync_read(struct kiocb *iocb, struct iov_iter *to, if (ret < 0) return ret; - if (unlikely(to->type & ITER_PIPE)) { + if (unlikely(iov_iter_is_pipe(to))) { size_t page_off; ret = iov_iter_get_pages_alloc(to, &pages, len, &page_off); diff --git a/fs/cifs/file.c b/fs/cifs/file.c index 8d41ca7bfcf1..dcdbcb6f09f8 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -2990,7 +2990,7 @@ cifs_readdata_to_iov(struct cifs_readdata *rdata, struct iov_iter *iter) size_t copy = min_t(size_t, remaining, PAGE_SIZE); size_t written; - if (unlikely(iter->type & ITER_PIPE)) { + if (unlikely(iov_iter_is_pipe(iter))) { void *addr = kmap_atomic(page); written = copy_to_iter(addr, copy, iter); @@ -3302,7 +3302,7 @@ ssize_t cifs_user_readv(struct kiocb *iocb, struct iov_iter *to) if (!is_sync_kiocb(iocb)) ctx->iocb = iocb; - if (to->type == ITER_IOVEC) + if (iter_is_iovec(to)) ctx->should_dirty = true; rc = setup_aio_ctx_iter(ctx, to, READ); diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c index 6926685e513c..7b5b960a04b8 100644 --- a/fs/cifs/misc.c +++ b/fs/cifs/misc.c @@ -786,7 +786,7 @@ setup_aio_ctx_iter(struct cifs_aio_ctx *ctx, struct iov_iter *iter, int rw) struct page **pages = NULL; struct bio_vec *bv = NULL; - if (iter->type & ITER_KVEC) { + if (iov_iter_is_kvec(iter)) { memcpy(&ctx->iter, iter, sizeof(struct iov_iter)); ctx->len = count; iov_iter_advance(iter, count); diff --git a/fs/cifs/smbdirect.c b/fs/cifs/smbdirect.c index 5fdb9a509a97..5b05bf255268 100644 --- a/fs/cifs/smbdirect.c +++ b/fs/cifs/smbdirect.c @@ -2054,14 +2054,22 @@ int smbd_recv(struct smbd_connection *info, struct msghdr *msg) info->smbd_recv_pending++; - switch (msg->msg_iter.type) { - case READ | ITER_KVEC: + if (iov_iter_rw(&msg->msg_iter) == WRITE) { + /* It's a bug in upper layer to get there */ + cifs_dbg(VFS, "CIFS: invalid msg iter dir %u\n", + iov_iter_rw(&msg->msg_iter)); + rc = -EINVAL; + goto out; + } + + switch (iov_iter_type(&msg->msg_iter)) { + case ITER_KVEC: buf = msg->msg_iter.kvec->iov_base; to_read = msg->msg_iter.kvec->iov_len; rc = smbd_recv_buf(info, buf, to_read); break; - case READ | ITER_BVEC: + case ITER_BVEC: page = msg->msg_iter.bvec->bv_page; page_offset = msg->msg_iter.bvec->bv_offset; to_read = msg->msg_iter.bvec->bv_len; @@ -2071,10 +2079,11 @@ int smbd_recv(struct smbd_connection *info, struct msghdr *msg) default: /* It's a bug in upper layer to get there */ cifs_dbg(VFS, "CIFS: invalid msg type %d\n", - msg->msg_iter.type); + iov_iter_type(&msg->msg_iter)); rc = -EINVAL; } +out: info->smbd_recv_pending--; wake_up(&info->wait_smbd_recv_pending); diff --git a/fs/direct-io.c b/fs/direct-io.c index 093fb54cd316..722d17c88edb 100644 --- a/fs/direct-io.c +++ b/fs/direct-io.c @@ -1313,7 +1313,7 @@ do_blockdev_direct_IO(struct kiocb *iocb, struct inode *inode, spin_lock_init(&dio->bio_lock); dio->refcount = 1; - dio->should_dirty = (iter->type == ITER_IOVEC); + dio->should_dirty = iter_is_iovec(iter) && iov_iter_rw(iter) == READ; sdio.iter = iter; sdio.final_block_in_request = end >> blkbits; diff --git a/fs/fuse/file.c b/fs/fuse/file.c index 32d0b883e74f..c9ccd45156dc 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -1271,7 +1271,7 @@ static int fuse_get_user_pages(struct fuse_req *req, struct iov_iter *ii, ssize_t ret = 0; /* Special case for kernel I/O: can copy directly into the buffer */ - if (ii->type & ITER_KVEC) { + if (iov_iter_is_kvec(ii)) { unsigned long user_addr = fuse_get_user_addr(ii); size_t frag_size = fuse_get_frag_size(ii, *nbytesp); diff --git a/fs/iomap.c b/fs/iomap.c index ec15cf2ec696..2c53400aa802 100644 --- a/fs/iomap.c +++ b/fs/iomap.c @@ -1795,7 +1795,7 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, if (pos >= dio->i_size) goto out_free_dio; - if (iter->type == ITER_IOVEC) + if (iter_is_iovec(iter) && iov_iter_rw(iter) == READ) dio->flags |= IOMAP_DIO_DIRTY; } else { flags |= IOMAP_WRITE; diff --git a/include/linux/uio.h b/include/linux/uio.h index 422b1c01ee0d..fcabc959c794 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -21,7 +21,7 @@ struct kvec { size_t iov_len; }; -enum { +enum iter_type { ITER_IOVEC = 0, ITER_KVEC = 2, ITER_BVEC = 4, @@ -47,6 +47,36 @@ struct iov_iter { }; }; +static inline enum iter_type iov_iter_type(const struct iov_iter *i) +{ + return i->type & ~(READ | WRITE); +} + +static inline bool iter_is_iovec(const struct iov_iter *i) +{ + return iov_iter_type(i) == ITER_IOVEC; +} + +static inline bool iov_iter_is_kvec(const struct iov_iter *i) +{ + return iov_iter_type(i) == ITER_KVEC; +} + +static inline bool iov_iter_is_bvec(const struct iov_iter *i) +{ + return iov_iter_type(i) == ITER_BVEC; +} + +static inline bool iov_iter_is_pipe(const struct iov_iter *i) +{ + return iov_iter_type(i) == ITER_PIPE; +} + +static inline unsigned char iov_iter_rw(const struct iov_iter *i) +{ + return i->type & (READ | WRITE); +} + /* * Total number of bytes covered by an iovec. * @@ -74,7 +104,8 @@ static inline struct iovec iov_iter_iovec(const struct iov_iter *iter) } #define iov_for_each(iov, iter, start) \ - if (!((start).type & (ITER_BVEC | ITER_PIPE))) \ + if (iov_iter_type(start) == ITER_IOVEC || \ + iov_iter_type(start) == ITER_KVEC) \ for (iter = (start); \ (iter).count && \ ((iov = iov_iter_iovec(&(iter))), 1); \ @@ -202,19 +233,6 @@ static inline size_t iov_iter_count(const struct iov_iter *i) return i->count; } -static inline bool iter_is_iovec(const struct iov_iter *i) -{ - return !(i->type & (ITER_BVEC | ITER_KVEC | ITER_PIPE)); -} - -/* - * Get one of READ or WRITE out of iter->type without any other flags OR'd in - * with it. - * - * The ?: is just for type safety. - */ -#define iov_iter_rw(i) ((0 ? (struct iov_iter *)0 : (i))->type & (READ | WRITE)) - /* * Cap the iov_iter by given limit; note that the second argument is * *not* the new size - it's upper limit for such. Passing it a value diff --git a/lib/iov_iter.c b/lib/iov_iter.c index 8be175df3075..42d39116a556 100644 --- a/lib/iov_iter.c +++ b/lib/iov_iter.c @@ -558,7 +558,7 @@ static size_t copy_pipe_to_iter(const void *addr, size_t bytes, size_t _copy_to_iter(const void *addr, size_t bytes, struct iov_iter *i) { const char *from = addr; - if (unlikely(i->type & ITER_PIPE)) + if (unlikely(iov_iter_is_pipe(i))) return copy_pipe_to_iter(addr, bytes, i); if (iter_is_iovec(i)) might_fault(); @@ -658,7 +658,7 @@ size_t _copy_to_iter_mcsafe(const void *addr, size_t bytes, struct iov_iter *i) const char *from = addr; unsigned long rem, curr_addr, s_addr = (unsigned long) addr; - if (unlikely(i->type & ITER_PIPE)) + if (unlikely(iov_iter_is_pipe(i))) return copy_pipe_to_iter_mcsafe(addr, bytes, i); if (iter_is_iovec(i)) might_fault(); @@ -692,7 +692,7 @@ EXPORT_SYMBOL_GPL(_copy_to_iter_mcsafe); size_t _copy_from_iter(void *addr, size_t bytes, struct iov_iter *i) { char *to = addr; - if (unlikely(i->type & ITER_PIPE)) { + if (unlikely(iov_iter_is_pipe(i))) { WARN_ON(1); return 0; } @@ -712,7 +712,7 @@ EXPORT_SYMBOL(_copy_from_iter); bool _copy_from_iter_full(void *addr, size_t bytes, struct iov_iter *i) { char *to = addr; - if (unlikely(i->type & ITER_PIPE)) { + if (unlikely(iov_iter_is_pipe(i))) { WARN_ON(1); return false; } @@ -739,7 +739,7 @@ EXPORT_SYMBOL(_copy_from_iter_full); size_t _copy_from_iter_nocache(void *addr, size_t bytes, struct iov_iter *i) { char *to = addr; - if (unlikely(i->type & ITER_PIPE)) { + if (unlikely(iov_iter_is_pipe(i))) { WARN_ON(1); return 0; } @@ -773,7 +773,7 @@ EXPORT_SYMBOL(_copy_from_iter_nocache); size_t _copy_from_iter_flushcache(void *addr, size_t bytes, struct iov_iter *i) { char *to = addr; - if (unlikely(i->type & ITER_PIPE)) { + if (unlikely(iov_iter_is_pipe(i))) { WARN_ON(1); return 0; } @@ -794,7 +794,7 @@ EXPORT_SYMBOL_GPL(_copy_from_iter_flushcache); bool _copy_from_iter_full_nocache(void *addr, size_t bytes, struct iov_iter *i) { char *to = addr; - if (unlikely(i->type & ITER_PIPE)) { + if (unlikely(iov_iter_is_pipe(i))) { WARN_ON(1); return false; } @@ -836,7 +836,7 @@ size_t copy_page_to_iter(struct page *page, size_t offset, size_t bytes, size_t wanted = copy_to_iter(kaddr + offset, bytes, i); kunmap_atomic(kaddr); return wanted; - } else if (likely(!(i->type & ITER_PIPE))) + } else if (likely(!iov_iter_is_pipe(i))) return copy_page_to_iter_iovec(page, offset, bytes, i); else return copy_page_to_iter_pipe(page, offset, bytes, i); @@ -848,7 +848,7 @@ size_t copy_page_from_iter(struct page *page, size_t offset, size_t bytes, { if (unlikely(!page_copy_sane(page, offset, bytes))) return 0; - if (unlikely(i->type & ITER_PIPE)) { + if (unlikely(iov_iter_is_pipe(i))) { WARN_ON(1); return 0; } @@ -888,7 +888,7 @@ static size_t pipe_zero(size_t bytes, struct iov_iter *i) size_t iov_iter_zero(size_t bytes, struct iov_iter *i) { - if (unlikely(i->type & ITER_PIPE)) + if (unlikely(iov_iter_is_pipe(i))) return pipe_zero(bytes, i); iterate_and_advance(i, bytes, v, clear_user(v.iov_base, v.iov_len), @@ -908,7 +908,7 @@ size_t iov_iter_copy_from_user_atomic(struct page *page, kunmap_atomic(kaddr); return 0; } - if (unlikely(i->type & ITER_PIPE)) { + if (unlikely(iov_iter_is_pipe(i))) { kunmap_atomic(kaddr); WARN_ON(1); return 0; @@ -972,7 +972,7 @@ static void pipe_advance(struct iov_iter *i, size_t size) void iov_iter_advance(struct iov_iter *i, size_t size) { - if (unlikely(i->type & ITER_PIPE)) { + if (unlikely(iov_iter_is_pipe(i))) { pipe_advance(i, size); return; } @@ -987,7 +987,7 @@ void iov_iter_revert(struct iov_iter *i, size_t unroll) if (WARN_ON(unroll > MAX_RW_COUNT)) return; i->count += unroll; - if (unlikely(i->type & ITER_PIPE)) { + if (unlikely(iov_iter_is_pipe(i))) { struct pipe_inode_info *pipe = i->pipe; int idx = i->idx; size_t off = i->iov_offset; @@ -1016,7 +1016,7 @@ void iov_iter_revert(struct iov_iter *i, size_t unroll) return; } unroll -= i->iov_offset; - if (i->type & ITER_BVEC) { + if (iov_iter_is_bvec(i)) { const struct bio_vec *bvec = i->bvec; while (1) { size_t n = (--bvec)->bv_len; @@ -1049,11 +1049,11 @@ EXPORT_SYMBOL(iov_iter_revert); */ size_t iov_iter_single_seg_count(const struct iov_iter *i) { - if (unlikely(i->type & ITER_PIPE)) + if (unlikely(iov_iter_is_pipe(i))) return i->count; // it is a silly place, anyway if (i->nr_segs == 1) return i->count; - else if (i->type & ITER_BVEC) + else if (iov_iter_is_bvec(i)) return min(i->count, i->bvec->bv_len - i->iov_offset); else return min(i->count, i->iov->iov_len - i->iov_offset); @@ -1106,7 +1106,7 @@ unsigned long iov_iter_alignment(const struct iov_iter *i) unsigned long res = 0; size_t size = i->count; - if (unlikely(i->type & ITER_PIPE)) { + if (unlikely(iov_iter_is_pipe(i))) { if (size && i->iov_offset && allocated(&i->pipe->bufs[i->idx])) return size | i->iov_offset; return size; @@ -1125,7 +1125,7 @@ unsigned long iov_iter_gap_alignment(const struct iov_iter *i) unsigned long res = 0; size_t size = i->count; - if (unlikely(i->type & ITER_PIPE)) { + if (unlikely(iov_iter_is_pipe(i))) { WARN_ON(1); return ~0U; } @@ -1193,7 +1193,7 @@ ssize_t iov_iter_get_pages(struct iov_iter *i, if (maxsize > i->count) maxsize = i->count; - if (unlikely(i->type & ITER_PIPE)) + if (unlikely(iov_iter_is_pipe(i))) return pipe_get_pages(i, pages, maxsize, maxpages, start); iterate_all_kinds(i, maxsize, v, ({ unsigned long addr = (unsigned long)v.iov_base; @@ -1205,7 +1205,7 @@ ssize_t iov_iter_get_pages(struct iov_iter *i, len = maxpages * PAGE_SIZE; addr &= ~(PAGE_SIZE - 1); n = DIV_ROUND_UP(len, PAGE_SIZE); - res = get_user_pages_fast(addr, n, (i->type & WRITE) != WRITE, pages); + res = get_user_pages_fast(addr, n, iov_iter_rw(i) != WRITE, pages); if (unlikely(res < 0)) return res; return (res == n ? len : res * PAGE_SIZE) - *start; @@ -1270,7 +1270,7 @@ ssize_t iov_iter_get_pages_alloc(struct iov_iter *i, if (maxsize > i->count) maxsize = i->count; - if (unlikely(i->type & ITER_PIPE)) + if (unlikely(iov_iter_is_pipe(i))) return pipe_get_pages_alloc(i, pages, maxsize, start); iterate_all_kinds(i, maxsize, v, ({ unsigned long addr = (unsigned long)v.iov_base; @@ -1283,7 +1283,7 @@ ssize_t iov_iter_get_pages_alloc(struct iov_iter *i, p = get_pages_array(n); if (!p) return -ENOMEM; - res = get_user_pages_fast(addr, n, (i->type & WRITE) != WRITE, p); + res = get_user_pages_fast(addr, n, iov_iter_rw(i) != WRITE, p); if (unlikely(res < 0)) { kvfree(p); return res; @@ -1313,7 +1313,7 @@ size_t csum_and_copy_from_iter(void *addr, size_t bytes, __wsum *csum, __wsum sum, next; size_t off = 0; sum = *csum; - if (unlikely(i->type & ITER_PIPE)) { + if (unlikely(iov_iter_is_pipe(i))) { WARN_ON(1); return 0; } @@ -1355,7 +1355,7 @@ bool csum_and_copy_from_iter_full(void *addr, size_t bytes, __wsum *csum, __wsum sum, next; size_t off = 0; sum = *csum; - if (unlikely(i->type & ITER_PIPE)) { + if (unlikely(iov_iter_is_pipe(i))) { WARN_ON(1); return false; } @@ -1400,7 +1400,7 @@ size_t csum_and_copy_to_iter(const void *addr, size_t bytes, __wsum *csum, __wsum sum, next; size_t off = 0; sum = *csum; - if (unlikely(i->type & ITER_PIPE)) { + if (unlikely(iov_iter_is_pipe(i))) { WARN_ON(1); /* for now */ return 0; } @@ -1443,7 +1443,7 @@ int iov_iter_npages(const struct iov_iter *i, int maxpages) if (!size) return 0; - if (unlikely(i->type & ITER_PIPE)) { + if (unlikely(iov_iter_is_pipe(i))) { struct pipe_inode_info *pipe = i->pipe; size_t off; int idx; @@ -1481,11 +1481,11 @@ EXPORT_SYMBOL(iov_iter_npages); const void *dup_iter(struct iov_iter *new, struct iov_iter *old, gfp_t flags) { *new = *old; - if (unlikely(new->type & ITER_PIPE)) { + if (unlikely(iov_iter_is_pipe(new))) { WARN_ON(1); return NULL; } - if (new->type & ITER_BVEC) + if (iov_iter_is_bvec(new)) return new->bvec = kmemdup(new->bvec, new->nr_segs * sizeof(struct bio_vec), flags); diff --git a/mm/filemap.c b/mm/filemap.c index 52517f28e6f4..bdeee0168ea7 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -2122,7 +2122,7 @@ find_page: !mapping->a_ops->is_partially_uptodate) goto page_not_up_to_date; /* pipes can't handle partially uptodate pages */ - if (unlikely(iter->type & ITER_PIPE)) + if (unlikely(iov_iter_is_pipe(iter))) goto page_not_up_to_date; if (!trylock_page(page)) goto page_not_up_to_date; diff --git a/net/9p/trans_virtio.c b/net/9p/trans_virtio.c index 7728b0acde09..4d7d2070e9c8 100644 --- a/net/9p/trans_virtio.c +++ b/net/9p/trans_virtio.c @@ -322,7 +322,7 @@ static int p9_get_mapped_pages(struct virtio_chan *chan, if (!iov_iter_count(data)) return 0; - if (!(data->type & ITER_KVEC)) { + if (iov_iter_is_kvec(data)) { int n; /* * We allow only p9_max_pages pinned. We wait for the diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index a525fc4c2a4b..ad64b9c8b600 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -799,7 +799,7 @@ int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) struct crypto_tfm *tfm = crypto_aead_tfm(ctx->aead_send); bool async_capable = tfm->__crt_alg->cra_flags & CRYPTO_ALG_ASYNC; unsigned char record_type = TLS_RECORD_TYPE_DATA; - bool is_kvec = msg->msg_iter.type & ITER_KVEC; + bool is_kvec = iov_iter_is_kvec(&msg->msg_iter); bool eor = !(msg->msg_flags & MSG_MORE); size_t try_to_copy, copied = 0; struct sk_msg *msg_pl, *msg_en; @@ -1457,7 +1457,7 @@ int tls_sw_recvmsg(struct sock *sk, bool cmsg = false; int target, err = 0; long timeo; - bool is_kvec = msg->msg_iter.type & ITER_KVEC; + bool is_kvec = iov_iter_is_kvec(&msg->msg_iter); int num_async = 0; flags |= nonblock; -- cgit v1.2.3 From aa563d7bca6e882ec2bdae24603c8f016401a144 Mon Sep 17 00:00:00 2001 From: David Howells Date: Sat, 20 Oct 2018 00:57:56 +0100 Subject: iov_iter: Separate type from direction and use accessor functions In the iov_iter struct, separate the iterator type from the iterator direction and use accessor functions to access them in most places. Convert a bunch of places to use switch-statements to access them rather then chains of bitwise-AND statements. This makes it easier to add further iterator types. Also, this can be more efficient as to implement a switch of small contiguous integers, the compiler can use ~50% fewer compare instructions than it has to use bitwise-and instructions. Further, cease passing the iterator type into the iterator setup function. The iterator function can set that itself. Only the direction is required. Signed-off-by: David Howells --- drivers/block/drbd/drbd_main.c | 2 +- drivers/block/drbd/drbd_receiver.c | 2 +- drivers/block/loop.c | 9 ++++----- drivers/block/nbd.c | 12 +++++------- drivers/fsi/fsi-sbefifo.c | 4 ++-- drivers/isdn/mISDN/l1oip_core.c | 3 +-- drivers/misc/vmw_vmci/vmci_queue_pair.c | 6 +++--- drivers/nvme/target/io-cmd-file.c | 2 +- drivers/target/iscsi/iscsi_target_util.c | 6 ++---- drivers/target/target_core_file.c | 6 +++--- drivers/usb/usbip/usbip_common.c | 2 +- drivers/xen/pvcalls-back.c | 8 ++++---- fs/9p/vfs_addr.c | 4 ++-- fs/9p/vfs_dir.c | 2 +- fs/9p/xattr.c | 4 ++-- fs/afs/rxrpc.c | 15 +++++++-------- fs/ceph/file.c | 5 ++--- fs/cifs/connect.c | 4 ++-- fs/cifs/misc.c | 2 +- fs/cifs/smb2ops.c | 4 ++-- fs/cifs/transport.c | 8 +++----- fs/dlm/lowcomms.c | 2 +- fs/nfsd/vfs.c | 4 ++-- fs/ocfs2/cluster/tcp.c | 2 +- fs/orangefs/inode.c | 2 +- fs/splice.c | 7 +++---- include/linux/uio.h | 10 +++++----- lib/iov_iter.c | 28 +++++++++++++++------------- mm/page_io.c | 2 +- net/9p/client.c | 2 +- net/bluetooth/6lowpan.c | 2 +- net/bluetooth/a2mp.c | 2 +- net/bluetooth/smp.c | 2 +- net/ceph/messenger.c | 6 +++--- net/netfilter/ipvs/ip_vs_sync.c | 2 +- net/smc/smc_clc.c | 4 ++-- net/socket.c | 6 +++--- net/sunrpc/svcsock.c | 2 +- net/tipc/topsrv.c | 2 +- net/tls/tls_device.c | 4 ++-- 40 files changed, 96 insertions(+), 105 deletions(-) (limited to 'mm') diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c index ef8212a4b73e..ded9735d44af 100644 --- a/drivers/block/drbd/drbd_main.c +++ b/drivers/block/drbd/drbd_main.c @@ -1856,7 +1856,7 @@ int drbd_send(struct drbd_connection *connection, struct socket *sock, /* THINK if (signal_pending) return ... ? */ - iov_iter_kvec(&msg.msg_iter, WRITE | ITER_KVEC, &iov, 1, size); + iov_iter_kvec(&msg.msg_iter, WRITE, &iov, 1, size); if (sock == connection->data.socket) { rcu_read_lock(); diff --git a/drivers/block/drbd/drbd_receiver.c b/drivers/block/drbd/drbd_receiver.c index 75f6b47169e6..fcc70642b004 100644 --- a/drivers/block/drbd/drbd_receiver.c +++ b/drivers/block/drbd/drbd_receiver.c @@ -516,7 +516,7 @@ static int drbd_recv_short(struct socket *sock, void *buf, size_t size, int flag struct msghdr msg = { .msg_flags = (flags ? flags : MSG_WAITALL | MSG_NOSIGNAL) }; - iov_iter_kvec(&msg.msg_iter, READ | ITER_KVEC, &iov, 1, size); + iov_iter_kvec(&msg.msg_iter, READ, &iov, 1, size); return sock_recvmsg(sock, &msg, msg.msg_flags); } diff --git a/drivers/block/loop.c b/drivers/block/loop.c index ea9debf59b22..cb0cc8685076 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -268,7 +268,7 @@ static int lo_write_bvec(struct file *file, struct bio_vec *bvec, loff_t *ppos) struct iov_iter i; ssize_t bw; - iov_iter_bvec(&i, ITER_BVEC | WRITE, bvec, 1, bvec->bv_len); + iov_iter_bvec(&i, WRITE, bvec, 1, bvec->bv_len); file_start_write(file); bw = vfs_iter_write(file, &i, ppos, 0); @@ -346,7 +346,7 @@ static int lo_read_simple(struct loop_device *lo, struct request *rq, ssize_t len; rq_for_each_segment(bvec, rq, iter) { - iov_iter_bvec(&i, ITER_BVEC, &bvec, 1, bvec.bv_len); + iov_iter_bvec(&i, READ, &bvec, 1, bvec.bv_len); len = vfs_iter_read(lo->lo_backing_file, &i, &pos, 0); if (len < 0) return len; @@ -387,7 +387,7 @@ static int lo_read_transfer(struct loop_device *lo, struct request *rq, b.bv_offset = 0; b.bv_len = bvec.bv_len; - iov_iter_bvec(&i, ITER_BVEC, &b, 1, b.bv_len); + iov_iter_bvec(&i, READ, &b, 1, b.bv_len); len = vfs_iter_read(lo->lo_backing_file, &i, &pos, 0); if (len < 0) { ret = len; @@ -554,8 +554,7 @@ static int lo_rw_aio(struct loop_device *lo, struct loop_cmd *cmd, } atomic_set(&cmd->ref, 2); - iov_iter_bvec(&iter, ITER_BVEC | rw, bvec, - segments, blk_rq_bytes(rq)); + iov_iter_bvec(&iter, rw, bvec, segments, blk_rq_bytes(rq)); iter.iov_offset = offset; cmd->iocb.ki_pos = pos; diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index 14a51254c3db..4d4d6129ff66 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -473,7 +473,7 @@ static int nbd_send_cmd(struct nbd_device *nbd, struct nbd_cmd *cmd, int index) u32 nbd_cmd_flags = 0; int sent = nsock->sent, skip = 0; - iov_iter_kvec(&from, WRITE | ITER_KVEC, &iov, 1, sizeof(request)); + iov_iter_kvec(&from, WRITE, &iov, 1, sizeof(request)); switch (req_op(req)) { case REQ_OP_DISCARD: @@ -564,8 +564,7 @@ send_pages: dev_dbg(nbd_to_dev(nbd), "request %p: sending %d bytes data\n", req, bvec.bv_len); - iov_iter_bvec(&from, ITER_BVEC | WRITE, - &bvec, 1, bvec.bv_len); + iov_iter_bvec(&from, WRITE, &bvec, 1, bvec.bv_len); if (skip) { if (skip >= iov_iter_count(&from)) { skip -= iov_iter_count(&from); @@ -624,7 +623,7 @@ static struct nbd_cmd *nbd_read_stat(struct nbd_device *nbd, int index) int ret = 0; reply.magic = 0; - iov_iter_kvec(&to, READ | ITER_KVEC, &iov, 1, sizeof(reply)); + iov_iter_kvec(&to, READ, &iov, 1, sizeof(reply)); result = sock_xmit(nbd, index, 0, &to, MSG_WAITALL, NULL); if (result <= 0) { if (!nbd_disconnected(config)) @@ -678,8 +677,7 @@ static struct nbd_cmd *nbd_read_stat(struct nbd_device *nbd, int index) struct bio_vec bvec; rq_for_each_segment(bvec, req, iter) { - iov_iter_bvec(&to, ITER_BVEC | READ, - &bvec, 1, bvec.bv_len); + iov_iter_bvec(&to, READ, &bvec, 1, bvec.bv_len); result = sock_xmit(nbd, index, 0, &to, MSG_WAITALL, NULL); if (result <= 0) { dev_err(disk_to_dev(nbd->disk), "Receive data failed (result %d)\n", @@ -1073,7 +1071,7 @@ static void send_disconnects(struct nbd_device *nbd) for (i = 0; i < config->num_connections; i++) { struct nbd_sock *nsock = config->socks[i]; - iov_iter_kvec(&from, WRITE | ITER_KVEC, &iov, 1, sizeof(request)); + iov_iter_kvec(&from, WRITE, &iov, 1, sizeof(request)); mutex_lock(&nsock->tx_lock); ret = sock_xmit(nbd, i, 1, &from, 0, NULL); if (ret <= 0) diff --git a/drivers/fsi/fsi-sbefifo.c b/drivers/fsi/fsi-sbefifo.c index ae861342626e..d92f5b87c251 100644 --- a/drivers/fsi/fsi-sbefifo.c +++ b/drivers/fsi/fsi-sbefifo.c @@ -638,7 +638,7 @@ static void sbefifo_collect_async_ffdc(struct sbefifo *sbefifo) } ffdc_iov.iov_base = ffdc; ffdc_iov.iov_len = SBEFIFO_MAX_FFDC_SIZE; - iov_iter_kvec(&ffdc_iter, WRITE | ITER_KVEC, &ffdc_iov, 1, SBEFIFO_MAX_FFDC_SIZE); + iov_iter_kvec(&ffdc_iter, WRITE, &ffdc_iov, 1, SBEFIFO_MAX_FFDC_SIZE); cmd[0] = cpu_to_be32(2); cmd[1] = cpu_to_be32(SBEFIFO_CMD_GET_SBE_FFDC); rc = sbefifo_do_command(sbefifo, cmd, 2, &ffdc_iter); @@ -735,7 +735,7 @@ int sbefifo_submit(struct device *dev, const __be32 *command, size_t cmd_len, rbytes = (*resp_len) * sizeof(__be32); resp_iov.iov_base = response; resp_iov.iov_len = rbytes; - iov_iter_kvec(&resp_iter, WRITE | ITER_KVEC, &resp_iov, 1, rbytes); + iov_iter_kvec(&resp_iter, WRITE, &resp_iov, 1, rbytes); /* Perform the command */ mutex_lock(&sbefifo->lock); diff --git a/drivers/isdn/mISDN/l1oip_core.c b/drivers/isdn/mISDN/l1oip_core.c index b05022f94f18..072bb5e36c18 100644 --- a/drivers/isdn/mISDN/l1oip_core.c +++ b/drivers/isdn/mISDN/l1oip_core.c @@ -718,8 +718,7 @@ l1oip_socket_thread(void *data) printk(KERN_DEBUG "%s: socket created and open\n", __func__); while (!signal_pending(current)) { - iov_iter_kvec(&msg.msg_iter, READ | ITER_KVEC, &iov, 1, - recvbuf_size); + iov_iter_kvec(&msg.msg_iter, READ, &iov, 1, recvbuf_size); recvlen = sock_recvmsg(socket, &msg, 0); if (recvlen > 0) { l1oip_socket_parse(hc, &sin_rx, recvbuf, recvlen); diff --git a/drivers/misc/vmw_vmci/vmci_queue_pair.c b/drivers/misc/vmw_vmci/vmci_queue_pair.c index bd52f29b4a4e..264f4ed8eef2 100644 --- a/drivers/misc/vmw_vmci/vmci_queue_pair.c +++ b/drivers/misc/vmw_vmci/vmci_queue_pair.c @@ -3030,7 +3030,7 @@ ssize_t vmci_qpair_enqueue(struct vmci_qp *qpair, if (!qpair || !buf) return VMCI_ERROR_INVALID_ARGS; - iov_iter_kvec(&from, WRITE | ITER_KVEC, &v, 1, buf_size); + iov_iter_kvec(&from, WRITE, &v, 1, buf_size); qp_lock(qpair); @@ -3074,7 +3074,7 @@ ssize_t vmci_qpair_dequeue(struct vmci_qp *qpair, if (!qpair || !buf) return VMCI_ERROR_INVALID_ARGS; - iov_iter_kvec(&to, READ | ITER_KVEC, &v, 1, buf_size); + iov_iter_kvec(&to, READ, &v, 1, buf_size); qp_lock(qpair); @@ -3119,7 +3119,7 @@ ssize_t vmci_qpair_peek(struct vmci_qp *qpair, if (!qpair || !buf) return VMCI_ERROR_INVALID_ARGS; - iov_iter_kvec(&to, READ | ITER_KVEC, &v, 1, buf_size); + iov_iter_kvec(&to, READ, &v, 1, buf_size); qp_lock(qpair); diff --git a/drivers/nvme/target/io-cmd-file.c b/drivers/nvme/target/io-cmd-file.c index 81a9dc5290a8..97f282eca3c2 100644 --- a/drivers/nvme/target/io-cmd-file.c +++ b/drivers/nvme/target/io-cmd-file.c @@ -101,7 +101,7 @@ static ssize_t nvmet_file_submit_bvec(struct nvmet_req *req, loff_t pos, rw = READ; } - iov_iter_bvec(&iter, ITER_BVEC | rw, req->f.bvec, nr_segs, count); + iov_iter_bvec(&iter, rw, req->f.bvec, nr_segs, count); iocb->ki_pos = pos; iocb->ki_filp = req->ns->file; diff --git a/drivers/target/iscsi/iscsi_target_util.c b/drivers/target/iscsi/iscsi_target_util.c index 49be1e41290c..991482576417 100644 --- a/drivers/target/iscsi/iscsi_target_util.c +++ b/drivers/target/iscsi/iscsi_target_util.c @@ -1258,8 +1258,7 @@ static int iscsit_do_rx_data( return -1; memset(&msg, 0, sizeof(struct msghdr)); - iov_iter_kvec(&msg.msg_iter, READ | ITER_KVEC, - count->iov, count->iov_count, data); + iov_iter_kvec(&msg.msg_iter, READ, count->iov, count->iov_count, data); while (msg_data_left(&msg)) { rx_loop = sock_recvmsg(conn->sock, &msg, MSG_WAITALL); @@ -1315,8 +1314,7 @@ int tx_data( memset(&msg, 0, sizeof(struct msghdr)); - iov_iter_kvec(&msg.msg_iter, WRITE | ITER_KVEC, - iov, iov_count, data); + iov_iter_kvec(&msg.msg_iter, WRITE, iov, iov_count, data); while (msg_data_left(&msg)) { int tx_loop = sock_sendmsg(conn->sock, &msg); diff --git a/drivers/target/target_core_file.c b/drivers/target/target_core_file.c index 16751ae55d7b..49b110d1b972 100644 --- a/drivers/target/target_core_file.c +++ b/drivers/target/target_core_file.c @@ -303,7 +303,7 @@ fd_execute_rw_aio(struct se_cmd *cmd, struct scatterlist *sgl, u32 sgl_nents, len += sg->length; } - iov_iter_bvec(&iter, ITER_BVEC | is_write, bvec, sgl_nents, len); + iov_iter_bvec(&iter, is_write, bvec, sgl_nents, len); aio_cmd->cmd = cmd; aio_cmd->len = len; @@ -353,7 +353,7 @@ static int fd_do_rw(struct se_cmd *cmd, struct file *fd, len += sg->length; } - iov_iter_bvec(&iter, ITER_BVEC, bvec, sgl_nents, len); + iov_iter_bvec(&iter, READ, bvec, sgl_nents, len); if (is_write) ret = vfs_iter_write(fd, &iter, &pos, 0); else @@ -490,7 +490,7 @@ fd_execute_write_same(struct se_cmd *cmd) len += se_dev->dev_attrib.block_size; } - iov_iter_bvec(&iter, ITER_BVEC, bvec, nolb, len); + iov_iter_bvec(&iter, READ, bvec, nolb, len); ret = vfs_iter_write(fd_dev->fd_file, &iter, &pos, 0); kfree(bvec); diff --git a/drivers/usb/usbip/usbip_common.c b/drivers/usb/usbip/usbip_common.c index 9756752c0681..45da3e01c7b0 100644 --- a/drivers/usb/usbip/usbip_common.c +++ b/drivers/usb/usbip/usbip_common.c @@ -309,7 +309,7 @@ int usbip_recv(struct socket *sock, void *buf, int size) if (!sock || !buf || !size) return -EINVAL; - iov_iter_kvec(&msg.msg_iter, READ|ITER_KVEC, &iov, 1, size); + iov_iter_kvec(&msg.msg_iter, READ, &iov, 1, size); usbip_dbg_xmit("enter\n"); diff --git a/drivers/xen/pvcalls-back.c b/drivers/xen/pvcalls-back.c index b1092fbefa63..2e5d845b5091 100644 --- a/drivers/xen/pvcalls-back.c +++ b/drivers/xen/pvcalls-back.c @@ -137,13 +137,13 @@ static void pvcalls_conn_back_read(void *opaque) if (masked_prod < masked_cons) { vec[0].iov_base = data->in + masked_prod; vec[0].iov_len = wanted; - iov_iter_kvec(&msg.msg_iter, ITER_KVEC|WRITE, vec, 1, wanted); + iov_iter_kvec(&msg.msg_iter, WRITE, vec, 1, wanted); } else { vec[0].iov_base = data->in + masked_prod; vec[0].iov_len = array_size - masked_prod; vec[1].iov_base = data->in; vec[1].iov_len = wanted - vec[0].iov_len; - iov_iter_kvec(&msg.msg_iter, ITER_KVEC|WRITE, vec, 2, wanted); + iov_iter_kvec(&msg.msg_iter, WRITE, vec, 2, wanted); } atomic_set(&map->read, 0); @@ -195,13 +195,13 @@ static void pvcalls_conn_back_write(struct sock_mapping *map) if (pvcalls_mask(prod, array_size) > pvcalls_mask(cons, array_size)) { vec[0].iov_base = data->out + pvcalls_mask(cons, array_size); vec[0].iov_len = size; - iov_iter_kvec(&msg.msg_iter, ITER_KVEC|READ, vec, 1, size); + iov_iter_kvec(&msg.msg_iter, READ, vec, 1, size); } else { vec[0].iov_base = data->out + pvcalls_mask(cons, array_size); vec[0].iov_len = array_size - pvcalls_mask(cons, array_size); vec[1].iov_base = data->out; vec[1].iov_len = size - vec[0].iov_len; - iov_iter_kvec(&msg.msg_iter, ITER_KVEC|READ, vec, 2, size); + iov_iter_kvec(&msg.msg_iter, READ, vec, 2, size); } atomic_set(&map->write, 0); diff --git a/fs/9p/vfs_addr.c b/fs/9p/vfs_addr.c index e1cbdfdb7c68..0bcbcc20f769 100644 --- a/fs/9p/vfs_addr.c +++ b/fs/9p/vfs_addr.c @@ -65,7 +65,7 @@ static int v9fs_fid_readpage(struct p9_fid *fid, struct page *page) if (retval == 0) return retval; - iov_iter_bvec(&to, ITER_BVEC | READ, &bvec, 1, PAGE_SIZE); + iov_iter_bvec(&to, READ, &bvec, 1, PAGE_SIZE); retval = p9_client_read(fid, page_offset(page), &to, &err); if (err) { @@ -175,7 +175,7 @@ static int v9fs_vfs_writepage_locked(struct page *page) bvec.bv_page = page; bvec.bv_offset = 0; bvec.bv_len = len; - iov_iter_bvec(&from, ITER_BVEC | WRITE, &bvec, 1, len); + iov_iter_bvec(&from, WRITE, &bvec, 1, len); /* We should have writeback_fid always set */ BUG_ON(!v9inode->writeback_fid); diff --git a/fs/9p/vfs_dir.c b/fs/9p/vfs_dir.c index b0405d6aac85..d5db3c968a03 100644 --- a/fs/9p/vfs_dir.c +++ b/fs/9p/vfs_dir.c @@ -133,7 +133,7 @@ static int v9fs_dir_readdir(struct file *file, struct dir_context *ctx) if (rdir->tail == rdir->head) { struct iov_iter to; int n; - iov_iter_kvec(&to, READ | ITER_KVEC, &kvec, 1, buflen); + iov_iter_kvec(&to, READ, &kvec, 1, buflen); n = p9_client_read(file->private_data, ctx->pos, &to, &err); if (err) diff --git a/fs/9p/xattr.c b/fs/9p/xattr.c index 352abc39e891..ac8ff8ca4c11 100644 --- a/fs/9p/xattr.c +++ b/fs/9p/xattr.c @@ -32,7 +32,7 @@ ssize_t v9fs_fid_xattr_get(struct p9_fid *fid, const char *name, struct iov_iter to; int err; - iov_iter_kvec(&to, READ | ITER_KVEC, &kvec, 1, buffer_size); + iov_iter_kvec(&to, READ, &kvec, 1, buffer_size); attr_fid = p9_client_xattrwalk(fid, name, &attr_size); if (IS_ERR(attr_fid)) { @@ -107,7 +107,7 @@ int v9fs_fid_xattr_set(struct p9_fid *fid, const char *name, struct iov_iter from; int retval, err; - iov_iter_kvec(&from, WRITE | ITER_KVEC, &kvec, 1, value_len); + iov_iter_kvec(&from, WRITE, &kvec, 1, value_len); p9_debug(P9_DEBUG_VFS, "name = %s value_len = %zu flags = %d\n", name, value_len, flags); diff --git a/fs/afs/rxrpc.c b/fs/afs/rxrpc.c index 77a83790a31f..639c16882e93 100644 --- a/fs/afs/rxrpc.c +++ b/fs/afs/rxrpc.c @@ -286,7 +286,7 @@ static void afs_load_bvec(struct afs_call *call, struct msghdr *msg, offset = 0; } - iov_iter_bvec(&msg->msg_iter, WRITE | ITER_BVEC, bv, nr, bytes); + iov_iter_bvec(&msg->msg_iter, WRITE, bv, nr, bytes); } /* @@ -401,8 +401,7 @@ long afs_make_call(struct afs_addr_cursor *ac, struct afs_call *call, msg.msg_name = NULL; msg.msg_namelen = 0; - iov_iter_kvec(&msg.msg_iter, WRITE | ITER_KVEC, iov, 1, - call->request_size); + iov_iter_kvec(&msg.msg_iter, WRITE, iov, 1, call->request_size); msg.msg_control = NULL; msg.msg_controllen = 0; msg.msg_flags = MSG_WAITALL | (call->send_pages ? MSG_MORE : 0); @@ -432,7 +431,7 @@ error_do_abort: rxrpc_kernel_abort_call(call->net->socket, rxcall, RX_USER_ABORT, ret, "KSD"); } else { - iov_iter_kvec(&msg.msg_iter, READ | ITER_KVEC, NULL, 0, 0); + iov_iter_kvec(&msg.msg_iter, READ, NULL, 0, 0); rxrpc_kernel_recv_data(call->net->socket, rxcall, &msg.msg_iter, false, &call->abort_code, &call->service_id); @@ -468,7 +467,7 @@ static void afs_deliver_to_call(struct afs_call *call) if (state == AFS_CALL_SV_AWAIT_ACK) { struct iov_iter iter; - iov_iter_kvec(&iter, READ | ITER_KVEC, NULL, 0, 0); + iov_iter_kvec(&iter, READ, NULL, 0, 0); ret = rxrpc_kernel_recv_data(call->net->socket, call->rxcall, &iter, false, &remote_abort, @@ -825,7 +824,7 @@ void afs_send_empty_reply(struct afs_call *call) msg.msg_name = NULL; msg.msg_namelen = 0; - iov_iter_kvec(&msg.msg_iter, WRITE | ITER_KVEC, NULL, 0, 0); + iov_iter_kvec(&msg.msg_iter, WRITE, NULL, 0, 0); msg.msg_control = NULL; msg.msg_controllen = 0; msg.msg_flags = 0; @@ -864,7 +863,7 @@ void afs_send_simple_reply(struct afs_call *call, const void *buf, size_t len) iov[0].iov_len = len; msg.msg_name = NULL; msg.msg_namelen = 0; - iov_iter_kvec(&msg.msg_iter, WRITE | ITER_KVEC, iov, 1, len); + iov_iter_kvec(&msg.msg_iter, WRITE, iov, 1, len); msg.msg_control = NULL; msg.msg_controllen = 0; msg.msg_flags = 0; @@ -905,7 +904,7 @@ int afs_extract_data(struct afs_call *call, void *buf, size_t count, iov.iov_base = buf + call->offset; iov.iov_len = count - call->offset; - iov_iter_kvec(&iter, ITER_KVEC | READ, &iov, 1, count - call->offset); + iov_iter_kvec(&iter, READ, &iov, 1, count - call->offset); ret = rxrpc_kernel_recv_data(net->socket, call->rxcall, &iter, want_more, &remote_abort, diff --git a/fs/ceph/file.c b/fs/ceph/file.c index 524ecc95b04d..5dd433aa9b23 100644 --- a/fs/ceph/file.c +++ b/fs/ceph/file.c @@ -821,7 +821,7 @@ static void ceph_aio_complete_req(struct ceph_osd_request *req) aio_req->total_len = rc + zlen; } - iov_iter_bvec(&i, ITER_BVEC, osd_data->bvec_pos.bvecs, + iov_iter_bvec(&i, READ, osd_data->bvec_pos.bvecs, osd_data->num_bvecs, osd_data->bvec_pos.iter.bi_size); iov_iter_advance(&i, rc); @@ -1044,8 +1044,7 @@ ceph_direct_read_write(struct kiocb *iocb, struct iov_iter *iter, int zlen = min_t(size_t, len - ret, size - pos - ret); - iov_iter_bvec(&i, ITER_BVEC, bvecs, num_pages, - len); + iov_iter_bvec(&i, READ, bvecs, num_pages, len); iov_iter_advance(&i, ret); iov_iter_zero(zlen, &i); ret += zlen; diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index 52d71b64c0c6..11bcd2fb90b1 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -588,7 +588,7 @@ cifs_read_from_socket(struct TCP_Server_Info *server, char *buf, { struct msghdr smb_msg; struct kvec iov = {.iov_base = buf, .iov_len = to_read}; - iov_iter_kvec(&smb_msg.msg_iter, READ | ITER_KVEC, &iov, 1, to_read); + iov_iter_kvec(&smb_msg.msg_iter, READ, &iov, 1, to_read); return cifs_readv_from_socket(server, &smb_msg); } @@ -600,7 +600,7 @@ cifs_read_page_from_socket(struct TCP_Server_Info *server, struct page *page, struct msghdr smb_msg; struct bio_vec bv = { .bv_page = page, .bv_len = to_read, .bv_offset = page_offset}; - iov_iter_bvec(&smb_msg.msg_iter, READ | ITER_BVEC, &bv, 1, to_read); + iov_iter_bvec(&smb_msg.msg_iter, READ, &bv, 1, to_read); return cifs_readv_from_socket(server, &smb_msg); } diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c index 7b5b960a04b8..10cff44832d8 100644 --- a/fs/cifs/misc.c +++ b/fs/cifs/misc.c @@ -857,7 +857,7 @@ setup_aio_ctx_iter(struct cifs_aio_ctx *ctx, struct iov_iter *iter, int rw) ctx->bv = bv; ctx->len = saved_len - count; ctx->npages = npages; - iov_iter_bvec(&ctx->iter, ITER_BVEC | rw, ctx->bv, npages, ctx->len); + iov_iter_bvec(&ctx->iter, rw, ctx->bv, npages, ctx->len); return 0; } diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c index 89985a0a6819..26f8a65b8722 100644 --- a/fs/cifs/smb2ops.c +++ b/fs/cifs/smb2ops.c @@ -2962,13 +2962,13 @@ handle_read_data(struct TCP_Server_Info *server, struct mid_q_entry *mid, return 0; } - iov_iter_bvec(&iter, WRITE | ITER_BVEC, bvec, npages, data_len); + iov_iter_bvec(&iter, WRITE, bvec, npages, data_len); } else if (buf_len >= data_offset + data_len) { /* read response payload is in buf */ WARN_ONCE(npages > 0, "read data can be either in buf or in pages"); iov.iov_base = buf + data_offset; iov.iov_len = data_len; - iov_iter_kvec(&iter, WRITE | ITER_KVEC, &iov, 1, data_len); + iov_iter_kvec(&iter, WRITE, &iov, 1, data_len); } else { /* read response payload cannot be in both buf and pages */ WARN_ONCE(1, "buf can not contain only a part of read data"); diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c index b48f43963da6..146b618802a5 100644 --- a/fs/cifs/transport.c +++ b/fs/cifs/transport.c @@ -307,8 +307,7 @@ __smb_send_rqst(struct TCP_Server_Info *server, int num_rqst, .iov_base = &rfc1002_marker, .iov_len = 4 }; - iov_iter_kvec(&smb_msg.msg_iter, WRITE | ITER_KVEC, &hiov, - 1, 4); + iov_iter_kvec(&smb_msg.msg_iter, WRITE, &hiov, 1, 4); rc = smb_send_kvec(server, &smb_msg, &sent); if (rc < 0) goto uncork; @@ -329,8 +328,7 @@ __smb_send_rqst(struct TCP_Server_Info *server, int num_rqst, size += iov[i].iov_len; } - iov_iter_kvec(&smb_msg.msg_iter, WRITE | ITER_KVEC, - iov, n_vec, size); + iov_iter_kvec(&smb_msg.msg_iter, WRITE, iov, n_vec, size); rc = smb_send_kvec(server, &smb_msg, &sent); if (rc < 0) @@ -346,7 +344,7 @@ __smb_send_rqst(struct TCP_Server_Info *server, int num_rqst, rqst_page_get_length(&rqst[j], i, &bvec.bv_len, &bvec.bv_offset); - iov_iter_bvec(&smb_msg.msg_iter, WRITE | ITER_BVEC, + iov_iter_bvec(&smb_msg.msg_iter, WRITE, &bvec, 1, bvec.bv_len); rc = smb_send_kvec(server, &smb_msg, &sent); if (rc < 0) diff --git a/fs/dlm/lowcomms.c b/fs/dlm/lowcomms.c index a5e4a221435c..76976d6e50f9 100644 --- a/fs/dlm/lowcomms.c +++ b/fs/dlm/lowcomms.c @@ -674,7 +674,7 @@ static int receive_from_sock(struct connection *con) nvec = 2; } len = iov[0].iov_len + iov[1].iov_len; - iov_iter_kvec(&msg.msg_iter, READ | ITER_KVEC, iov, nvec, len); + iov_iter_kvec(&msg.msg_iter, READ, iov, nvec, len); r = ret = sock_recvmsg(con->sock, &msg, MSG_DONTWAIT | MSG_NOSIGNAL); if (ret <= 0) diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index b53e76391e52..8b90f5480904 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -923,7 +923,7 @@ __be32 nfsd_readv(struct svc_rqst *rqstp, struct svc_fh *fhp, int host_err; trace_nfsd_read_vector(rqstp, fhp, offset, *count); - iov_iter_kvec(&iter, READ | ITER_KVEC, vec, vlen, *count); + iov_iter_kvec(&iter, READ, vec, vlen, *count); host_err = vfs_iter_read(file, &iter, &offset, 0); return nfsd_finish_read(rqstp, fhp, file, offset, count, host_err); } @@ -999,7 +999,7 @@ nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file, if (stable && !use_wgather) flags |= RWF_SYNC; - iov_iter_kvec(&iter, WRITE | ITER_KVEC, vec, vlen, *cnt); + iov_iter_kvec(&iter, WRITE, vec, vlen, *cnt); host_err = vfs_iter_write(file, &iter, &pos, flags); if (host_err < 0) goto out_nfserr; diff --git a/fs/ocfs2/cluster/tcp.c b/fs/ocfs2/cluster/tcp.c index 7d9eea7d4a87..e9f236af1927 100644 --- a/fs/ocfs2/cluster/tcp.c +++ b/fs/ocfs2/cluster/tcp.c @@ -916,7 +916,7 @@ static int o2net_recv_tcp_msg(struct socket *sock, void *data, size_t len) { struct kvec vec = { .iov_len = len, .iov_base = data, }; struct msghdr msg = { .msg_flags = MSG_DONTWAIT, }; - iov_iter_kvec(&msg.msg_iter, READ | ITER_KVEC, &vec, 1, len); + iov_iter_kvec(&msg.msg_iter, READ, &vec, 1, len); return sock_recvmsg(sock, &msg, MSG_DONTWAIT); } diff --git a/fs/orangefs/inode.c b/fs/orangefs/inode.c index 31932879b716..136a8bdc1d91 100644 --- a/fs/orangefs/inode.c +++ b/fs/orangefs/inode.c @@ -25,7 +25,7 @@ static int read_one_page(struct page *page) struct iov_iter to; struct bio_vec bv = {.bv_page = page, .bv_len = PAGE_SIZE}; - iov_iter_bvec(&to, ITER_BVEC | READ, &bv, 1, PAGE_SIZE); + iov_iter_bvec(&to, READ, &bv, 1, PAGE_SIZE); gossip_debug(GOSSIP_INODE_DEBUG, "orangefs_readpage called with page %p\n", diff --git a/fs/splice.c b/fs/splice.c index b3daa971f597..3553f1956508 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -301,7 +301,7 @@ ssize_t generic_file_splice_read(struct file *in, loff_t *ppos, struct kiocb kiocb; int idx, ret; - iov_iter_pipe(&to, ITER_PIPE | READ, pipe, len); + iov_iter_pipe(&to, READ, pipe, len); idx = to.idx; init_sync_kiocb(&kiocb, in); kiocb.ki_pos = *ppos; @@ -386,7 +386,7 @@ static ssize_t default_file_splice_read(struct file *in, loff_t *ppos, */ offset = *ppos & ~PAGE_MASK; - iov_iter_pipe(&to, ITER_PIPE | READ, pipe, len + offset); + iov_iter_pipe(&to, READ, pipe, len + offset); res = iov_iter_get_pages_alloc(&to, &pages, len + offset, &base); if (res <= 0) @@ -745,8 +745,7 @@ iter_file_splice_write(struct pipe_inode_info *pipe, struct file *out, left -= this_len; } - iov_iter_bvec(&from, ITER_BVEC | WRITE, array, n, - sd.total_len - left); + iov_iter_bvec(&from, WRITE, array, n, sd.total_len - left); ret = vfs_iter_write(out, &from, &sd.pos, 0); if (ret <= 0) break; diff --git a/include/linux/uio.h b/include/linux/uio.h index fcabc959c794..3d8f1acc142c 100644 --- a/include/linux/uio.h +++ b/include/linux/uio.h @@ -29,7 +29,7 @@ enum iter_type { }; struct iov_iter { - int type; + unsigned int type; size_t iov_offset; size_t count; union { @@ -212,13 +212,13 @@ size_t copy_to_iter_mcsafe(void *addr, size_t bytes, struct iov_iter *i) size_t iov_iter_zero(size_t bytes, struct iov_iter *); unsigned long iov_iter_alignment(const struct iov_iter *i); unsigned long iov_iter_gap_alignment(const struct iov_iter *i); -void iov_iter_init(struct iov_iter *i, int direction, const struct iovec *iov, +void iov_iter_init(struct iov_iter *i, unsigned int direction, const struct iovec *iov, unsigned long nr_segs, size_t count); -void iov_iter_kvec(struct iov_iter *i, int direction, const struct kvec *kvec, +void iov_iter_kvec(struct iov_iter *i, unsigned int direction, const struct kvec *kvec, unsigned long nr_segs, size_t count); -void iov_iter_bvec(struct iov_iter *i, int direction, const struct bio_vec *bvec, +void iov_iter_bvec(struct iov_iter *i, unsigned int direction, const struct bio_vec *bvec, unsigned long nr_segs, size_t count); -void iov_iter_pipe(struct iov_iter *i, int direction, struct pipe_inode_info *pipe, +void iov_iter_pipe(struct iov_iter *i, unsigned int direction, struct pipe_inode_info *pipe, size_t count); ssize_t iov_iter_get_pages(struct iov_iter *i, struct page **pages, size_t maxsize, unsigned maxpages, size_t *start); diff --git a/lib/iov_iter.c b/lib/iov_iter.c index 42d39116a556..c42b928b15ef 100644 --- a/lib/iov_iter.c +++ b/lib/iov_iter.c @@ -428,17 +428,19 @@ int iov_iter_fault_in_readable(struct iov_iter *i, size_t bytes) } EXPORT_SYMBOL(iov_iter_fault_in_readable); -void iov_iter_init(struct iov_iter *i, int direction, +void iov_iter_init(struct iov_iter *i, unsigned int direction, const struct iovec *iov, unsigned long nr_segs, size_t count) { + WARN_ON(direction & ~(READ | WRITE)); + direction &= READ | WRITE; + /* It will get better. Eventually... */ if (uaccess_kernel()) { - direction |= ITER_KVEC; - i->type = direction; + i->type = ITER_KVEC | direction; i->kvec = (struct kvec *)iov; } else { - i->type = direction; + i->type = ITER_IOVEC | direction; i->iov = iov; } i->nr_segs = nr_segs; @@ -1060,12 +1062,12 @@ size_t iov_iter_single_seg_count(const struct iov_iter *i) } EXPORT_SYMBOL(iov_iter_single_seg_count); -void iov_iter_kvec(struct iov_iter *i, int direction, +void iov_iter_kvec(struct iov_iter *i, unsigned int direction, const struct kvec *kvec, unsigned long nr_segs, size_t count) { - BUG_ON(!(direction & ITER_KVEC)); - i->type = direction; + WARN_ON(direction & ~(READ | WRITE)); + i->type = ITER_KVEC | (direction & (READ | WRITE)); i->kvec = kvec; i->nr_segs = nr_segs; i->iov_offset = 0; @@ -1073,12 +1075,12 @@ void iov_iter_kvec(struct iov_iter *i, int direction, } EXPORT_SYMBOL(iov_iter_kvec); -void iov_iter_bvec(struct iov_iter *i, int direction, +void iov_iter_bvec(struct iov_iter *i, unsigned int direction, const struct bio_vec *bvec, unsigned long nr_segs, size_t count) { - BUG_ON(!(direction & ITER_BVEC)); - i->type = direction; + WARN_ON(direction & ~(READ | WRITE)); + i->type = ITER_BVEC | (direction & (READ | WRITE)); i->bvec = bvec; i->nr_segs = nr_segs; i->iov_offset = 0; @@ -1086,13 +1088,13 @@ void iov_iter_bvec(struct iov_iter *i, int direction, } EXPORT_SYMBOL(iov_iter_bvec); -void iov_iter_pipe(struct iov_iter *i, int direction, +void iov_iter_pipe(struct iov_iter *i, unsigned int direction, struct pipe_inode_info *pipe, size_t count) { - BUG_ON(direction != ITER_PIPE); + BUG_ON(direction != READ); WARN_ON(pipe->nrbufs == pipe->buffers); - i->type = direction; + i->type = ITER_PIPE | READ; i->pipe = pipe; i->idx = (pipe->curbuf + pipe->nrbufs) & (pipe->buffers - 1); i->iov_offset = 0; diff --git a/mm/page_io.c b/mm/page_io.c index aafd19ec1db4..86de453a60cf 100644 --- a/mm/page_io.c +++ b/mm/page_io.c @@ -294,7 +294,7 @@ int __swap_writepage(struct page *page, struct writeback_control *wbc, }; struct iov_iter from; - iov_iter_bvec(&from, ITER_BVEC | WRITE, &bv, 1, PAGE_SIZE); + iov_iter_bvec(&from, WRITE, &bv, 1, PAGE_SIZE); init_sync_kiocb(&kiocb, swap_file); kiocb.ki_pos = page_file_offset(page); diff --git a/net/9p/client.c b/net/9p/client.c index deae53a7dffc..a9cd1401bd09 100644 --- a/net/9p/client.c +++ b/net/9p/client.c @@ -2070,7 +2070,7 @@ int p9_client_readdir(struct p9_fid *fid, char *data, u32 count, u64 offset) struct kvec kv = {.iov_base = data, .iov_len = count}; struct iov_iter to; - iov_iter_kvec(&to, READ | ITER_KVEC, &kv, 1, count); + iov_iter_kvec(&to, READ, &kv, 1, count); p9_debug(P9_DEBUG_9P, ">>> TREADDIR fid %d offset %llu count %d\n", fid->fid, (unsigned long long) offset, count); diff --git a/net/bluetooth/6lowpan.c b/net/bluetooth/6lowpan.c index 4e2576fc0c59..828e87fe8027 100644 --- a/net/bluetooth/6lowpan.c +++ b/net/bluetooth/6lowpan.c @@ -467,7 +467,7 @@ static int send_pkt(struct l2cap_chan *chan, struct sk_buff *skb, iv.iov_len = skb->len; memset(&msg, 0, sizeof(msg)); - iov_iter_kvec(&msg.msg_iter, WRITE | ITER_KVEC, &iv, 1, skb->len); + iov_iter_kvec(&msg.msg_iter, WRITE, &iv, 1, skb->len); err = l2cap_chan_send(chan, &msg, skb->len); if (err > 0) { diff --git a/net/bluetooth/a2mp.c b/net/bluetooth/a2mp.c index 51c2cf2d8923..58fc6333d412 100644 --- a/net/bluetooth/a2mp.c +++ b/net/bluetooth/a2mp.c @@ -63,7 +63,7 @@ static void a2mp_send(struct amp_mgr *mgr, u8 code, u8 ident, u16 len, void *dat memset(&msg, 0, sizeof(msg)); - iov_iter_kvec(&msg.msg_iter, WRITE | ITER_KVEC, &iv, 1, total_len); + iov_iter_kvec(&msg.msg_iter, WRITE, &iv, 1, total_len); l2cap_chan_send(chan, &msg, total_len); diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c index a1c1b7e8a45c..c822e626761b 100644 --- a/net/bluetooth/smp.c +++ b/net/bluetooth/smp.c @@ -622,7 +622,7 @@ static void smp_send_cmd(struct l2cap_conn *conn, u8 code, u16 len, void *data) memset(&msg, 0, sizeof(msg)); - iov_iter_kvec(&msg.msg_iter, WRITE | ITER_KVEC, iv, 2, 1 + len); + iov_iter_kvec(&msg.msg_iter, WRITE, iv, 2, 1 + len); l2cap_chan_send(chan, &msg, 1 + len); diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index 0a187196aeed..e493ff77b378 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -526,7 +526,7 @@ static int ceph_tcp_recvmsg(struct socket *sock, void *buf, size_t len) if (!buf) msg.msg_flags |= MSG_TRUNC; - iov_iter_kvec(&msg.msg_iter, READ | ITER_KVEC, &iov, 1, len); + iov_iter_kvec(&msg.msg_iter, READ, &iov, 1, len); r = sock_recvmsg(sock, &msg, msg.msg_flags); if (r == -EAGAIN) r = 0; @@ -545,7 +545,7 @@ static int ceph_tcp_recvpage(struct socket *sock, struct page *page, int r; BUG_ON(page_offset + length > PAGE_SIZE); - iov_iter_bvec(&msg.msg_iter, READ | ITER_BVEC, &bvec, 1, length); + iov_iter_bvec(&msg.msg_iter, READ, &bvec, 1, length); r = sock_recvmsg(sock, &msg, msg.msg_flags); if (r == -EAGAIN) r = 0; @@ -607,7 +607,7 @@ static int ceph_tcp_sendpage(struct socket *sock, struct page *page, else msg.msg_flags |= MSG_EOR; /* superfluous, but what the hell */ - iov_iter_bvec(&msg.msg_iter, WRITE | ITER_BVEC, &bvec, 1, size); + iov_iter_bvec(&msg.msg_iter, WRITE, &bvec, 1, size); ret = sock_sendmsg(sock, &msg); if (ret == -EAGAIN) ret = 0; diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c index d4020c5e831d..2526be6b3d90 100644 --- a/net/netfilter/ipvs/ip_vs_sync.c +++ b/net/netfilter/ipvs/ip_vs_sync.c @@ -1616,7 +1616,7 @@ ip_vs_receive(struct socket *sock, char *buffer, const size_t buflen) EnterFunction(7); /* Receive a packet */ - iov_iter_kvec(&msg.msg_iter, READ | ITER_KVEC, &iov, 1, buflen); + iov_iter_kvec(&msg.msg_iter, READ, &iov, 1, buflen); len = sock_recvmsg(sock, &msg, MSG_DONTWAIT); if (len < 0) return len; diff --git a/net/smc/smc_clc.c b/net/smc/smc_clc.c index 52241d679cc9..89c3a8c7859a 100644 --- a/net/smc/smc_clc.c +++ b/net/smc/smc_clc.c @@ -286,7 +286,7 @@ int smc_clc_wait_msg(struct smc_sock *smc, void *buf, int buflen, */ krflags = MSG_PEEK | MSG_WAITALL; smc->clcsock->sk->sk_rcvtimeo = CLC_WAIT_TIME; - iov_iter_kvec(&msg.msg_iter, READ | ITER_KVEC, &vec, 1, + iov_iter_kvec(&msg.msg_iter, READ, &vec, 1, sizeof(struct smc_clc_msg_hdr)); len = sock_recvmsg(smc->clcsock, &msg, krflags); if (signal_pending(current)) { @@ -325,7 +325,7 @@ int smc_clc_wait_msg(struct smc_sock *smc, void *buf, int buflen, /* receive the complete CLC message */ memset(&msg, 0, sizeof(struct msghdr)); - iov_iter_kvec(&msg.msg_iter, READ | ITER_KVEC, &vec, 1, datlen); + iov_iter_kvec(&msg.msg_iter, READ, &vec, 1, datlen); krflags = MSG_WAITALL; len = sock_recvmsg(smc->clcsock, &msg, krflags); if (len < datlen || !smc_clc_msg_hdr_valid(clcm)) { diff --git a/net/socket.c b/net/socket.c index b68801c7d0ab..fae408abea54 100644 --- a/net/socket.c +++ b/net/socket.c @@ -635,7 +635,7 @@ EXPORT_SYMBOL(sock_sendmsg); int kernel_sendmsg(struct socket *sock, struct msghdr *msg, struct kvec *vec, size_t num, size_t size) { - iov_iter_kvec(&msg->msg_iter, WRITE | ITER_KVEC, vec, num, size); + iov_iter_kvec(&msg->msg_iter, WRITE, vec, num, size); return sock_sendmsg(sock, msg); } EXPORT_SYMBOL(kernel_sendmsg); @@ -648,7 +648,7 @@ int kernel_sendmsg_locked(struct sock *sk, struct msghdr *msg, if (!sock->ops->sendmsg_locked) return sock_no_sendmsg_locked(sk, msg, size); - iov_iter_kvec(&msg->msg_iter, WRITE | ITER_KVEC, vec, num, size); + iov_iter_kvec(&msg->msg_iter, WRITE, vec, num, size); return sock->ops->sendmsg_locked(sk, msg, msg_data_left(msg)); } @@ -823,7 +823,7 @@ int kernel_recvmsg(struct socket *sock, struct msghdr *msg, mm_segment_t oldfs = get_fs(); int result; - iov_iter_kvec(&msg->msg_iter, READ | ITER_KVEC, vec, num, size); + iov_iter_kvec(&msg->msg_iter, READ, vec, num, size); set_fs(KERNEL_DS); result = sock_recvmsg(sock, msg, flags); set_fs(oldfs); diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c index 5445145e639c..0b46ec0bf74e 100644 --- a/net/sunrpc/svcsock.c +++ b/net/sunrpc/svcsock.c @@ -338,7 +338,7 @@ static int svc_recvfrom(struct svc_rqst *rqstp, struct kvec *iov, int nr, rqstp->rq_xprt_hlen = 0; clear_bit(XPT_DATA, &svsk->sk_xprt.xpt_flags); - iov_iter_kvec(&msg.msg_iter, READ | ITER_KVEC, iov, nr, buflen); + iov_iter_kvec(&msg.msg_iter, READ, iov, nr, buflen); len = sock_recvmsg(svsk->sk_sock, &msg, msg.msg_flags); /* If we read a full record, then assume there may be more * data to read (stream based sockets only!) diff --git a/net/tipc/topsrv.c b/net/tipc/topsrv.c index d8956f7daac4..afa02eeec403 100644 --- a/net/tipc/topsrv.c +++ b/net/tipc/topsrv.c @@ -394,7 +394,7 @@ static int tipc_conn_rcv_from_sock(struct tipc_conn *con) iov.iov_base = &s; iov.iov_len = sizeof(s); msg.msg_name = NULL; - iov_iter_kvec(&msg.msg_iter, READ | ITER_KVEC, &iov, 1, iov.iov_len); + iov_iter_kvec(&msg.msg_iter, READ, &iov, 1, iov.iov_len); ret = sock_recvmsg(con->sock, &msg, MSG_DONTWAIT); if (ret == -EWOULDBLOCK) return -EWOULDBLOCK; diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c index 276edbc04f38..d753e362d2d9 100644 --- a/net/tls/tls_device.c +++ b/net/tls/tls_device.c @@ -489,7 +489,7 @@ int tls_device_sendpage(struct sock *sk, struct page *page, iov.iov_base = kaddr + offset; iov.iov_len = size; - iov_iter_kvec(&msg_iter, WRITE | ITER_KVEC, &iov, 1, size); + iov_iter_kvec(&msg_iter, WRITE, &iov, 1, size); rc = tls_push_data(sk, &msg_iter, size, flags, TLS_RECORD_TYPE_DATA); kunmap(page); @@ -538,7 +538,7 @@ static int tls_device_push_pending_record(struct sock *sk, int flags) { struct iov_iter msg_iter; - iov_iter_kvec(&msg_iter, WRITE | ITER_KVEC, NULL, 0, 0); + iov_iter_kvec(&msg_iter, WRITE, NULL, 0, 0); return tls_push_data(sk, &msg_iter, 0, flags, TLS_RECORD_TYPE_DATA); } -- cgit v1.2.3 From d95f58f4a6ca002126c36c530fb096519c94baef Mon Sep 17 00:00:00 2001 From: Wei Wang Date: Mon, 27 Aug 2018 09:32:18 +0800 Subject: mm/page_poison: expose page_poisoning_enabled to kernel modules In some usages, e.g. virtio-balloon, a kernel module needs to know if page poisoning is in use. This patch exposes the page_poisoning_enabled function to kernel modules. Signed-off-by: Wei Wang Cc: Andrew Morton Cc: Michal Hocko Cc: Michael S. Tsirkin Acked-by: Andrew Morton Signed-off-by: Michael S. Tsirkin --- mm/page_poison.c | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'mm') diff --git a/mm/page_poison.c b/mm/page_poison.c index aa2b3d34e8ea..830f60489b14 100644 --- a/mm/page_poison.c +++ b/mm/page_poison.c @@ -17,6 +17,11 @@ static int __init early_page_poison_param(char *buf) } early_param("page_poison", early_page_poison_param); +/** + * page_poisoning_enabled - check if page poisoning is enabled + * + * Return true if page poisoning is enabled, or false if not. + */ bool page_poisoning_enabled(void) { /* @@ -29,6 +34,7 @@ bool page_poisoning_enabled(void) (!IS_ENABLED(CONFIG_ARCH_SUPPORTS_DEBUG_PAGEALLOC) && debug_pagealloc_enabled())); } +EXPORT_SYMBOL_GPL(page_poisoning_enabled); static void poison_page(struct page *page) { -- cgit v1.2.3 From 0684e6526edfb4debf0a0a884834bb1a104085dc Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Fri, 26 Oct 2018 15:03:06 -0700 Subject: mm/slub.c: switch to bitmap_zalloc() Switch to bitmap_zalloc() to show clearly what we are allocating. Besides that it returns pointer of bitmap type instead of opaque void *. Link: http://lkml.kernel.org/r/20180830104301.61649-1-andriy.shevchenko@linux.intel.com Signed-off-by: Andy Shevchenko Acked-by: Christoph Lameter Reviewed-by: Andrew Morton Tested-by: David Rientjes Cc: Pekka Enberg Cc: Joonsoo Kim Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/slub.c | 20 +++++++------------- 1 file changed, 7 insertions(+), 13 deletions(-) (limited to 'mm') diff --git a/mm/slub.c b/mm/slub.c index 8da34a8af53d..37e82a0538aa 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -3621,9 +3621,7 @@ static void list_slab_objects(struct kmem_cache *s, struct page *page, #ifdef CONFIG_SLUB_DEBUG void *addr = page_address(page); void *p; - unsigned long *map = kcalloc(BITS_TO_LONGS(page->objects), - sizeof(long), - GFP_ATOMIC); + unsigned long *map = bitmap_zalloc(page->objects, GFP_ATOMIC); if (!map) return; slab_err(s, page, text, s->name); @@ -3638,7 +3636,7 @@ static void list_slab_objects(struct kmem_cache *s, struct page *page, } } slab_unlock(page); - kfree(map); + bitmap_free(map); #endif } @@ -4411,10 +4409,8 @@ static long validate_slab_cache(struct kmem_cache *s) { int node; unsigned long count = 0; - unsigned long *map = kmalloc_array(BITS_TO_LONGS(oo_objects(s->max)), - sizeof(unsigned long), - GFP_KERNEL); struct kmem_cache_node *n; + unsigned long *map = bitmap_alloc(oo_objects(s->max), GFP_KERNEL); if (!map) return -ENOMEM; @@ -4422,7 +4418,7 @@ static long validate_slab_cache(struct kmem_cache *s) flush_all(s); for_each_kmem_cache_node(s, node, n) count += validate_slab_node(s, n, map); - kfree(map); + bitmap_free(map); return count; } /* @@ -4573,14 +4569,12 @@ static int list_locations(struct kmem_cache *s, char *buf, unsigned long i; struct loc_track t = { 0, 0, NULL }; int node; - unsigned long *map = kmalloc_array(BITS_TO_LONGS(oo_objects(s->max)), - sizeof(unsigned long), - GFP_KERNEL); struct kmem_cache_node *n; + unsigned long *map = bitmap_alloc(oo_objects(s->max), GFP_KERNEL); if (!map || !alloc_loc_track(&t, PAGE_SIZE / sizeof(struct location), GFP_KERNEL)) { - kfree(map); + bitmap_free(map); return sprintf(buf, "Out of memory\n"); } /* Push back cpu slabs */ @@ -4646,7 +4640,7 @@ static int list_locations(struct kmem_cache *s, char *buf, } free_loc_track(&t); - kfree(map); + bitmap_free(map); if (!t.count) len += sprintf(buf, "No data\n"); return len; -- cgit v1.2.3 From 61448479a9f2c954cde0cfe778cb6bec5d0a748d Mon Sep 17 00:00:00 2001 From: Dmitry Vyukov Date: Fri, 26 Oct 2018 15:03:12 -0700 Subject: mm: don't warn about large allocations for slab Slub does not call kmalloc_slab() for sizes > KMALLOC_MAX_CACHE_SIZE, instead it falls back to kmalloc_large(). For slab KMALLOC_MAX_CACHE_SIZE == KMALLOC_MAX_SIZE and it calls kmalloc_slab() for all allocations relying on NULL return value for over-sized allocations. This inconsistency leads to unwanted warnings from kmalloc_slab() for over-sized allocations for slab. Returning NULL for failed allocations is the expected behavior. Make slub and slab code consistent by checking size > KMALLOC_MAX_CACHE_SIZE in slab before calling kmalloc_slab(). While we are here also fix the check in kmalloc_slab(). We should check against KMALLOC_MAX_CACHE_SIZE rather than KMALLOC_MAX_SIZE. It all kinda worked because for slab the constants are the same, and slub always checks the size against KMALLOC_MAX_CACHE_SIZE before kmalloc_slab(). But if we get there with size > KMALLOC_MAX_CACHE_SIZE anyhow bad things will happen. For example, in case of a newly introduced bug in slub code. Also move the check in kmalloc_slab() from function entry to the size > 192 case. This partially compensates for the additional check in slab code and makes slub code a bit faster (at least theoretically). Also drop __GFP_NOWARN in the warning check. This warning means a bug in slab code itself, user-passed flags have nothing to do with it. Nothing of this affects slob. Link: http://lkml.kernel.org/r/20180927171502.226522-1-dvyukov@gmail.com Signed-off-by: Dmitry Vyukov Reported-by: syzbot+87829a10073277282ad1@syzkaller.appspotmail.com Reported-by: syzbot+ef4e8fc3a06e9019bb40@syzkaller.appspotmail.com Reported-by: syzbot+6e438f4036df52cbb863@syzkaller.appspotmail.com Reported-by: syzbot+8574471d8734457d98aa@syzkaller.appspotmail.com Reported-by: syzbot+af1504df0807a083dbd9@syzkaller.appspotmail.com Acked-by: Christoph Lameter Acked-by: Vlastimil Babka Cc: Pekka Enberg Cc: David Rientjes Cc: Joonsoo Kim Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/slab.c | 4 ++++ mm/slab_common.c | 12 ++++++------ 2 files changed, 10 insertions(+), 6 deletions(-) (limited to 'mm') diff --git a/mm/slab.c b/mm/slab.c index aa76a70e087e..d73c7a4820a4 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -3675,6 +3675,8 @@ __do_kmalloc_node(size_t size, gfp_t flags, int node, unsigned long caller) struct kmem_cache *cachep; void *ret; + if (unlikely(size > KMALLOC_MAX_CACHE_SIZE)) + return NULL; cachep = kmalloc_slab(size, flags); if (unlikely(ZERO_OR_NULL_PTR(cachep))) return cachep; @@ -3710,6 +3712,8 @@ static __always_inline void *__do_kmalloc(size_t size, gfp_t flags, struct kmem_cache *cachep; void *ret; + if (unlikely(size > KMALLOC_MAX_CACHE_SIZE)) + return NULL; cachep = kmalloc_slab(size, flags); if (unlikely(ZERO_OR_NULL_PTR(cachep))) return cachep; diff --git a/mm/slab_common.c b/mm/slab_common.c index fea3376f9816..3a7ac4f15194 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -1027,18 +1027,18 @@ struct kmem_cache *kmalloc_slab(size_t size, gfp_t flags) { unsigned int index; - if (unlikely(size > KMALLOC_MAX_SIZE)) { - WARN_ON_ONCE(!(flags & __GFP_NOWARN)); - return NULL; - } - if (size <= 192) { if (!size) return ZERO_SIZE_PTR; index = size_index[size_index_elem(size)]; - } else + } else { + if (unlikely(size > KMALLOC_MAX_CACHE_SIZE)) { + WARN_ON(1); + return NULL; + } index = fls(size - 1); + } #ifdef CONFIG_ZONE_DMA if (unlikely((flags & GFP_DMA))) -- cgit v1.2.3 From c5fd3ca06b4699e251b4a1fb808c2d5124494101 Mon Sep 17 00:00:00 2001 From: Aaron Tomlin Date: Fri, 26 Oct 2018 15:03:15 -0700 Subject: slub: extend slub debug to handle multiple slabs Extend the slub_debug syntax to "slub_debug=[,]*", where may contain an asterisk at the end. For example, the following would poison all kmalloc slabs: slub_debug=P,kmalloc* and the following would apply the default flags to all kmalloc and all block IO slabs: slub_debug=,bio*,kmalloc* Please note that a similar patch was posted by Iliyan Malchev some time ago but was never merged: https://marc.info/?l=linux-mm&m=131283905330474&w=2 Link: http://lkml.kernel.org/r/20180928111139.27962-1-atomlin@redhat.com Signed-off-by: Aaron Tomlin Acked-by: Christoph Lameter Cc: Pekka Enberg Cc: David Rientjes Cc: Joonsoo Kim Cc: Iliyan Malchev Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/vm/slub.rst | 12 +++++++++--- mm/slub.c | 50 +++++++++++++++++++++++++++++++++++++++++------ 2 files changed, 53 insertions(+), 9 deletions(-) (limited to 'mm') diff --git a/Documentation/vm/slub.rst b/Documentation/vm/slub.rst index 3a775fd64e2d..195928808bac 100644 --- a/Documentation/vm/slub.rst +++ b/Documentation/vm/slub.rst @@ -36,9 +36,10 @@ debugging is enabled. Format: slub_debug= Enable options for all slabs -slub_debug=, - Enable options only for select slabs +slub_debug=,,,... + Enable options only for select slabs (no spaces + after a comma) Possible debug options are:: @@ -62,7 +63,12 @@ Trying to find an issue in the dentry cache? Try:: slub_debug=,dentry -to only enable debugging on the dentry cache. +to only enable debugging on the dentry cache. You may use an asterisk at the +end of the slab name, in order to cover all slabs with the same prefix. For +example, here's how you can poison the dentry cache as well as all kmalloc +slabs: + + slub_debug=P,kmalloc-*,dentry Red zoning and tracking may realign the slab. We can just apply sanity checks to the dentry cache with:: diff --git a/mm/slub.c b/mm/slub.c index 37e82a0538aa..18bd07daf4e4 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -1276,16 +1276,54 @@ out: __setup("slub_debug", setup_slub_debug); +/* + * kmem_cache_flags - apply debugging options to the cache + * @object_size: the size of an object without meta data + * @flags: flags to set + * @name: name of the cache + * @ctor: constructor function + * + * Debug option(s) are applied to @flags. In addition to the debug + * option(s), if a slab name (or multiple) is specified i.e. + * slub_debug=,, ... + * then only the select slabs will receive the debug option(s). + */ slab_flags_t kmem_cache_flags(unsigned int object_size, slab_flags_t flags, const char *name, void (*ctor)(void *)) { - /* - * Enable debugging if selected on the kernel commandline. - */ - if (slub_debug && (!slub_debug_slabs || (name && - !strncmp(slub_debug_slabs, name, strlen(slub_debug_slabs))))) - flags |= slub_debug; + char *iter; + size_t len; + + /* If slub_debug = 0, it folds into the if conditional. */ + if (!slub_debug_slabs) + return flags | slub_debug; + + len = strlen(name); + iter = slub_debug_slabs; + while (*iter) { + char *end, *glob; + size_t cmplen; + + end = strchr(iter, ','); + if (!end) + end = iter + strlen(iter); + + glob = strnchr(iter, end - iter, '*'); + if (glob) + cmplen = glob - iter; + else + cmplen = max_t(size_t, len, (end - iter)); + + if (!strncmp(name, iter, cmplen)) { + flags |= slub_debug; + break; + } + + if (!*end) + break; + iter = end + 1; + } return flags; } -- cgit v1.2.3 From 591edfb10a949d635ed770c6e85ec5286206c07e Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Fri, 26 Oct 2018 15:03:23 -0700 Subject: mm: drain memcg stocks on css offlining Memcg charge is batched using per-cpu stocks, so an offline memcg can be pinned by a cached charge up to a moment, when a process belonging to some other cgroup will charge some memory on the same cpu. In other words, cached charges can prevent a memory cgroup from being reclaimed for some time, without any clear need. Let's optimize it by explicit draining of all stocks on css offlining. As draining is performed asynchronously, and is skipped if any parallel draining is happening, it's cheap. Link: http://lkml.kernel.org/r/20180827162621.30187-2-guro@fb.com Signed-off-by: Roman Gushchin Reviewed-by: Shakeel Butt Acked-by: Michal Hocko Cc: Johannes Weiner Cc: Konstantin Khlebnikov Cc: Tejun Heo Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memcontrol.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'mm') diff --git a/mm/memcontrol.c b/mm/memcontrol.c index e79cb59552d9..fcec9b39e2a3 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -4573,6 +4573,8 @@ static void mem_cgroup_css_offline(struct cgroup_subsys_state *css) memcg_offline_kmem(memcg); wb_memcg_offline(memcg); + drain_all_stock(memcg); + mem_cgroup_id_put(memcg); } -- cgit v1.2.3 From 68600f623d69da428c6163275f97ca126e1a8ec5 Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Fri, 26 Oct 2018 15:03:27 -0700 Subject: mm: don't miss the last page because of round-off error I've noticed, that dying memory cgroups are often pinned in memory by a single pagecache page. Even under moderate memory pressure they sometimes stayed in such state for a long time. That looked strange. My investigation showed that the problem is caused by applying the LRU pressure balancing math: scan = div64_u64(scan * fraction[lru], denominator), where denominator = fraction[anon] + fraction[file] + 1. Because fraction[lru] is always less than denominator, if the initial scan size is 1, the result is always 0. This means the last page is not scanned and has no chances to be reclaimed. Fix this by rounding up the result of the division. In practice this change significantly improves the speed of dying cgroups reclaim. [guro@fb.com: prevent double calculation of DIV64_U64_ROUND_UP() arguments] Link: http://lkml.kernel.org/r/20180829213311.GA13501@castle Link: http://lkml.kernel.org/r/20180827162621.30187-3-guro@fb.com Signed-off-by: Roman Gushchin Reviewed-by: Andrew Morton Cc: Johannes Weiner Cc: Michal Hocko Cc: Tejun Heo Cc: Rik van Riel Cc: Konstantin Khlebnikov Cc: Matthew Wilcox Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/math64.h | 3 +++ mm/vmscan.c | 6 ++++-- 2 files changed, 7 insertions(+), 2 deletions(-) (limited to 'mm') diff --git a/include/linux/math64.h b/include/linux/math64.h index 837f2f2d1d34..bb2c84afb80c 100644 --- a/include/linux/math64.h +++ b/include/linux/math64.h @@ -281,4 +281,7 @@ static inline u64 mul_u64_u32_div(u64 a, u32 mul, u32 divisor) } #endif /* mul_u64_u32_div */ +#define DIV64_U64_ROUND_UP(ll, d) \ + ({ u64 _tmp = (d); div64_u64((ll) + _tmp - 1, _tmp); }) + #endif /* _LINUX_MATH64_H */ diff --git a/mm/vmscan.c b/mm/vmscan.c index c5ef7240cbcb..961401c46334 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -2456,9 +2456,11 @@ out: /* * Scan types proportional to swappiness and * their relative recent reclaim efficiency. + * Make sure we don't miss the last page + * because of a round-off error. */ - scan = div64_u64(scan * fraction[file], - denominator); + scan = DIV64_U64_ROUND_UP(scan * fraction[file], + denominator); break; case SCAN_FILE: case SCAN_ANON: -- cgit v1.2.3 From 15f570bf3d13aa94a97234538a5110d18df03aa3 Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Fri, 26 Oct 2018 15:03:31 -0700 Subject: mm,page_alloc: PF_WQ_WORKER threads must sleep at should_reclaim_retry() Tetsuo Handa has reported that it is possible to bypass the short sleep for PF_WQ_WORKER threads which was introduced by commit 373ccbe5927034b5 ("mm, vmstat: allow WQ concurrency to discover memory reclaim doesn't make any progress") and lock up the system if OOM. The primary reason is that WQ_MEM_RECLAIM WQs are not guaranteed to run even when they have a rescuer available. Those workers might be essential for reclaim to make a forward progress, however. If we are too unlucky all the allocations requests can get stuck waiting for a WQ_MEM_RECLAIM work item and the system is essentially stuck in an OOM condition without much hope to move on. Tetsuo has seen the reclaim stuck on drain_local_pages_wq or xlog_cil_push_work (xfs). There might be others. Since should_reclaim_retry() should be a natural reschedule point, let's do the short sleep for PF_WQ_WORKER threads unconditionally in order to guarantee that other pending work items are started. This will workaround this problem and it is less fragile than hunting down when the sleep is missed. Having a single sleeping point is more robust. [akpm@linux-foundation.org: reflow comment to 80 cols to save a couple of lines] Link: http://lkml.kernel.org/r/20180827135101.15700-1-mhocko@kernel.org Signed-off-by: Michal Hocko Debugged-by: Tetsuo Handa Reported-by: Tetsuo Handa Reviewed-by: Andrew Morton Cc: Roman Gushchin Cc: Johannes Weiner Cc: Vladimir Davydov Cc: David Rientjes Cc: Tejun Heo Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/page_alloc.c | 32 ++++++++++++++++---------------- 1 file changed, 16 insertions(+), 16 deletions(-) (limited to 'mm') diff --git a/mm/page_alloc.c b/mm/page_alloc.c index e2ef1c17942f..7e2fb6e38f34 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -3922,6 +3922,7 @@ should_reclaim_retry(gfp_t gfp_mask, unsigned order, { struct zone *zone; struct zoneref *z; + bool ret = false; /* * Costly allocations might have made a progress but this doesn't mean @@ -3985,25 +3986,24 @@ should_reclaim_retry(gfp_t gfp_mask, unsigned order, } } - /* - * Memory allocation/reclaim might be called from a WQ - * context and the current implementation of the WQ - * concurrency control doesn't recognize that - * a particular WQ is congested if the worker thread is - * looping without ever sleeping. Therefore we have to - * do a short sleep here rather than calling - * cond_resched(). - */ - if (current->flags & PF_WQ_WORKER) - schedule_timeout_uninterruptible(1); - else - cond_resched(); - - return true; + ret = true; + goto out; } } - return false; +out: + /* + * Memory allocation/reclaim might be called from a WQ context and the + * current implementation of the WQ concurrency control doesn't + * recognize that a particular WQ is congested if the worker thread is + * looping without ever sleeping. Therefore we have to do a short sleep + * here rather than calling cond_resched(). + */ + if (current->flags & PF_WQ_WORKER) + schedule_timeout_uninterruptible(1); + else + cond_resched(); + return ret; } static inline bool -- cgit v1.2.3 From 4e15a073a168b62311db911a55c4d4f1500c2821 Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Fri, 26 Oct 2018 15:03:39 -0700 Subject: Revert "mm, mmu_notifier: annotate mmu notifiers with blockable invalidate callbacks" Revert 5ff7091f5a2ca ("mm, mmu_notifier: annotate mmu notifiers with blockable invalidate callbacks"). MMU_INVALIDATE_DOES_NOT_BLOCK flags was the only one used and it is no longer needed since 93065ac753e4 ("mm, oom: distinguish blockable mode for mmu notifiers"). We now have a full support for per range !blocking behavior so we can drop the stop gap workaround which the per notifier flag was used for. Link: http://lkml.kernel.org/r/20180827112623.8992-4-mhocko@kernel.org Signed-off-by: Michal Hocko Cc: David Rientjes Cc: Boris Ostrovsky Cc: Jerome Glisse Cc: Juergen Gross Cc: Tetsuo Handa Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/infiniband/hw/hfi1/mmu_rb.c | 1 - drivers/iommu/amd_iommu_v2.c | 1 - drivers/iommu/intel-svm.c | 1 - drivers/misc/sgi-gru/grutlbpurge.c | 1 - include/linux/mmu_notifier.h | 23 ----------------------- mm/mmu_notifier.c | 31 ------------------------------- virt/kvm/kvm_main.c | 1 - 7 files changed, 59 deletions(-) (limited to 'mm') diff --git a/drivers/infiniband/hw/hfi1/mmu_rb.c b/drivers/infiniband/hw/hfi1/mmu_rb.c index e1c7996c018e..475b769e120c 100644 --- a/drivers/infiniband/hw/hfi1/mmu_rb.c +++ b/drivers/infiniband/hw/hfi1/mmu_rb.c @@ -77,7 +77,6 @@ static void do_remove(struct mmu_rb_handler *handler, static void handle_remove(struct work_struct *work); static const struct mmu_notifier_ops mn_opts = { - .flags = MMU_INVALIDATE_DOES_NOT_BLOCK, .invalidate_range_start = mmu_notifier_range_start, }; diff --git a/drivers/iommu/amd_iommu_v2.c b/drivers/iommu/amd_iommu_v2.c index 58da65df03f5..fd552235bd13 100644 --- a/drivers/iommu/amd_iommu_v2.c +++ b/drivers/iommu/amd_iommu_v2.c @@ -427,7 +427,6 @@ static void mn_release(struct mmu_notifier *mn, struct mm_struct *mm) } static const struct mmu_notifier_ops iommu_mn = { - .flags = MMU_INVALIDATE_DOES_NOT_BLOCK, .release = mn_release, .clear_flush_young = mn_clear_flush_young, .invalidate_range = mn_invalidate_range, diff --git a/drivers/iommu/intel-svm.c b/drivers/iommu/intel-svm.c index 4a03e5090952..db301efe126d 100644 --- a/drivers/iommu/intel-svm.c +++ b/drivers/iommu/intel-svm.c @@ -273,7 +273,6 @@ static void intel_mm_release(struct mmu_notifier *mn, struct mm_struct *mm) } static const struct mmu_notifier_ops intel_mmuops = { - .flags = MMU_INVALIDATE_DOES_NOT_BLOCK, .release = intel_mm_release, .change_pte = intel_change_pte, .invalidate_range = intel_invalidate_range, diff --git a/drivers/misc/sgi-gru/grutlbpurge.c b/drivers/misc/sgi-gru/grutlbpurge.c index be28f05bfafa..03b49d52092e 100644 --- a/drivers/misc/sgi-gru/grutlbpurge.c +++ b/drivers/misc/sgi-gru/grutlbpurge.c @@ -261,7 +261,6 @@ static void gru_release(struct mmu_notifier *mn, struct mm_struct *mm) static const struct mmu_notifier_ops gru_mmuops = { - .flags = MMU_INVALIDATE_DOES_NOT_BLOCK, .invalidate_range_start = gru_invalidate_range_start, .invalidate_range_end = gru_invalidate_range_end, .release = gru_release, diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h index 698e371aafe3..9893a6432adf 100644 --- a/include/linux/mmu_notifier.h +++ b/include/linux/mmu_notifier.h @@ -2,7 +2,6 @@ #ifndef _LINUX_MMU_NOTIFIER_H #define _LINUX_MMU_NOTIFIER_H -#include #include #include #include @@ -11,9 +10,6 @@ struct mmu_notifier; struct mmu_notifier_ops; -/* mmu_notifier_ops flags */ -#define MMU_INVALIDATE_DOES_NOT_BLOCK (0x01) - #ifdef CONFIG_MMU_NOTIFIER /* @@ -30,15 +26,6 @@ struct mmu_notifier_mm { }; struct mmu_notifier_ops { - /* - * Flags to specify behavior of callbacks for this MMU notifier. - * Used to determine which context an operation may be called. - * - * MMU_INVALIDATE_DOES_NOT_BLOCK: invalidate_range_* callbacks do not - * block - */ - int flags; - /* * Called either by mmu_notifier_unregister or when the mm is * being destroyed by exit_mmap, always before all pages are @@ -183,10 +170,6 @@ struct mmu_notifier_ops { * Note that this function might be called with just a sub-range * of what was passed to invalidate_range_start()/end(), if * called between those functions. - * - * If this callback cannot block, and invalidate_range_{start,end} - * cannot block, mmu_notifier_ops.flags should have - * MMU_INVALIDATE_DOES_NOT_BLOCK set. */ void (*invalidate_range)(struct mmu_notifier *mn, struct mm_struct *mm, unsigned long start, unsigned long end); @@ -241,7 +224,6 @@ extern void __mmu_notifier_invalidate_range_end(struct mm_struct *mm, bool only_end); extern void __mmu_notifier_invalidate_range(struct mm_struct *mm, unsigned long start, unsigned long end); -extern bool mm_has_blockable_invalidate_notifiers(struct mm_struct *mm); static inline void mmu_notifier_release(struct mm_struct *mm) { @@ -495,11 +477,6 @@ static inline void mmu_notifier_invalidate_range(struct mm_struct *mm, { } -static inline bool mm_has_blockable_invalidate_notifiers(struct mm_struct *mm) -{ - return false; -} - static inline void mmu_notifier_mm_init(struct mm_struct *mm) { } diff --git a/mm/mmu_notifier.c b/mm/mmu_notifier.c index 82bb1a939c0e..5119ff846769 100644 --- a/mm/mmu_notifier.c +++ b/mm/mmu_notifier.c @@ -247,37 +247,6 @@ void __mmu_notifier_invalidate_range(struct mm_struct *mm, } EXPORT_SYMBOL_GPL(__mmu_notifier_invalidate_range); -/* - * Must be called while holding mm->mmap_sem for either read or write. - * The result is guaranteed to be valid until mm->mmap_sem is dropped. - */ -bool mm_has_blockable_invalidate_notifiers(struct mm_struct *mm) -{ - struct mmu_notifier *mn; - int id; - bool ret = false; - - WARN_ON_ONCE(!rwsem_is_locked(&mm->mmap_sem)); - - if (!mm_has_notifiers(mm)) - return ret; - - id = srcu_read_lock(&srcu); - hlist_for_each_entry_rcu(mn, &mm->mmu_notifier_mm->list, hlist) { - if (!mn->ops->invalidate_range && - !mn->ops->invalidate_range_start && - !mn->ops->invalidate_range_end) - continue; - - if (!(mn->ops->flags & MMU_INVALIDATE_DOES_NOT_BLOCK)) { - ret = true; - break; - } - } - srcu_read_unlock(&srcu, id); - return ret; -} - static int do_mmu_notifier_register(struct mmu_notifier *mn, struct mm_struct *mm, int take_mmap_sem) diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 786ade1843a2..2679e476b6c3 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -497,7 +497,6 @@ static void kvm_mmu_notifier_release(struct mmu_notifier *mn, } static const struct mmu_notifier_ops kvm_mmu_notifier_ops = { - .flags = MMU_INVALIDATE_DOES_NOT_BLOCK, .invalidate_range_start = kvm_mmu_notifier_invalidate_range_start, .invalidate_range_end = kvm_mmu_notifier_invalidate_range_end, .clear_flush_young = kvm_mmu_notifier_clear_flush_young, -- cgit v1.2.3 From 154221c3e52083d9f54fa58b4e1090264969f6bc Mon Sep 17 00:00:00 2001 From: Vincent Whitchurch Date: Fri, 26 Oct 2018 15:03:42 -0700 Subject: kmemleak: add module param to print warnings to dmesg Currently, kmemleak only prints the number of suspected leaks to dmesg but requires the user to read a debugfs file to get the actual stack traces of the objects' allocation points. Add a module option to print the full object information to dmesg too. It can be enabled with kmemleak.verbose=1 on the kernel command line, or "echo 1 > /sys/module/kmemleak/parameters/verbose": This allows easier integration of kmemleak into test systems: We have automated test infrastructure to test our Linux systems. With this option, running our tests with kmemleak is as simple as enabling kmemleak and passing this command line option; the test infrastructure knows how to save kernel logs, which will now include kmemleak reports. Without this option, the test infrastructure needs to be specifically taught to read out the kmemleak debugfs file. Removing this need for special handling makes kmemleak more similar to other kernel debug options (slab debugging, debug objects, etc). Link: http://lkml.kernel.org/r/20180903144046.21023-1-vincent.whitchurch@axis.com Signed-off-by: Vincent Whitchurch Acked-by: Catalin Marinas Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/kmemleak.c | 42 +++++++++++++++++++++++++++++++++++------- 1 file changed, 35 insertions(+), 7 deletions(-) (limited to 'mm') diff --git a/mm/kmemleak.c b/mm/kmemleak.c index 17dd883198ae..4f7e4b5a2f08 100644 --- a/mm/kmemleak.c +++ b/mm/kmemleak.c @@ -86,6 +86,7 @@ #include #include #include +#include #include #include #include @@ -181,6 +182,7 @@ struct kmemleak_object { /* flag set to not scan the object */ #define OBJECT_NO_SCAN (1 << 2) +#define HEX_PREFIX " " /* number of bytes to print per line; must be 16 or 32 */ #define HEX_ROW_SIZE 16 /* number of bytes to print at a time (1, 2, 4, 8) */ @@ -235,6 +237,9 @@ static int kmemleak_skip_disable; /* If there are leaks that can be reported */ static bool kmemleak_found_leaks; +static bool kmemleak_verbose; +module_param_named(verbose, kmemleak_verbose, bool, 0600); + /* * Early object allocation/freeing logging. Kmemleak is initialized after the * kernel allocator. However, both the kernel allocator and kmemleak may @@ -299,6 +304,25 @@ static void kmemleak_disable(void); kmemleak_disable(); \ } while (0) +#define warn_or_seq_printf(seq, fmt, ...) do { \ + if (seq) \ + seq_printf(seq, fmt, ##__VA_ARGS__); \ + else \ + pr_warn(fmt, ##__VA_ARGS__); \ +} while (0) + +static void warn_or_seq_hex_dump(struct seq_file *seq, int prefix_type, + int rowsize, int groupsize, const void *buf, + size_t len, bool ascii) +{ + if (seq) + seq_hex_dump(seq, HEX_PREFIX, prefix_type, rowsize, groupsize, + buf, len, ascii); + else + print_hex_dump(KERN_WARNING, pr_fmt(HEX_PREFIX), prefix_type, + rowsize, groupsize, buf, len, ascii); +} + /* * Printing of the objects hex dump to the seq file. The number of lines to be * printed is limited to HEX_MAX_LINES to prevent seq file spamming. The @@ -314,10 +338,10 @@ static void hex_dump_object(struct seq_file *seq, /* limit the number of lines to HEX_MAX_LINES */ len = min_t(size_t, object->size, HEX_MAX_LINES * HEX_ROW_SIZE); - seq_printf(seq, " hex dump (first %zu bytes):\n", len); + warn_or_seq_printf(seq, " hex dump (first %zu bytes):\n", len); kasan_disable_current(); - seq_hex_dump(seq, " ", DUMP_PREFIX_NONE, HEX_ROW_SIZE, - HEX_GROUP_SIZE, ptr, len, HEX_ASCII); + warn_or_seq_hex_dump(seq, DUMP_PREFIX_NONE, HEX_ROW_SIZE, + HEX_GROUP_SIZE, ptr, len, HEX_ASCII); kasan_enable_current(); } @@ -365,17 +389,17 @@ static void print_unreferenced(struct seq_file *seq, int i; unsigned int msecs_age = jiffies_to_msecs(jiffies - object->jiffies); - seq_printf(seq, "unreferenced object 0x%08lx (size %zu):\n", + warn_or_seq_printf(seq, "unreferenced object 0x%08lx (size %zu):\n", object->pointer, object->size); - seq_printf(seq, " comm \"%s\", pid %d, jiffies %lu (age %d.%03ds)\n", + warn_or_seq_printf(seq, " comm \"%s\", pid %d, jiffies %lu (age %d.%03ds)\n", object->comm, object->pid, object->jiffies, msecs_age / 1000, msecs_age % 1000); hex_dump_object(seq, object); - seq_printf(seq, " backtrace:\n"); + warn_or_seq_printf(seq, " backtrace:\n"); for (i = 0; i < object->trace_len; i++) { void *ptr = (void *)object->trace[i]; - seq_printf(seq, " [<%p>] %pS\n", ptr, ptr); + warn_or_seq_printf(seq, " [<%p>] %pS\n", ptr, ptr); } } @@ -1598,6 +1622,10 @@ static void kmemleak_scan(void) if (unreferenced_object(object) && !(object->flags & OBJECT_REPORTED)) { object->flags |= OBJECT_REPORTED; + + if (kmemleak_verbose) + print_unreferenced(NULL, object); + new_leaks++; } spin_unlock_irqrestore(&object->lock, flags); -- cgit v1.2.3 From bcd49e86710b42f15c7512de594d23b3ae0b21d7 Mon Sep 17 00:00:00 2001 From: Huang Ying Date: Fri, 26 Oct 2018 15:03:46 -0700 Subject: mm/swapfile.c: use __try_to_reclaim_swap() in free_swap_and_cache() The code path to reclaim the swap entry in free_swap_and_cache() is almost same as that of __try_to_reclaim_swap(). The largest difference is just coding style. So the support to the additional requirement of free_swap_and_cache() is added into __try_to_reclaim_swap(). free_swap_and_cache() is changed to call __try_to_reclaim_swap(), and delete the duplicated code. This will improve code readability and reduce the potential bugs. There are 2 functionality differences between __try_to_reclaim_swap() and swap entry reclaim code of free_swap_and_cache(). - free_swap_and_cache() only reclaims the swap entry if the page is unmapped or swap is getting full. The support has been added into __try_to_reclaim_swap(). - try_to_free_swap() (called by __try_to_reclaim_swap()) checks pm_suspended_storage(), while free_swap_and_cache() not. I think this is OK. Because the page and the swap entry can be reclaimed later eventually. Link: http://lkml.kernel.org/r/20180827075535.17406-2-ying.huang@intel.com Signed-off-by: "Huang, Ying" Reviewed-by: Andrew Morton Cc: Dave Hansen Cc: Michal Hocko Cc: Johannes Weiner Cc: Shaohua Li Cc: Hugh Dickins Cc: Minchan Kim Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/swapfile.c | 57 +++++++++++++++++++++++++-------------------------------- 1 file changed, 25 insertions(+), 32 deletions(-) (limited to 'mm') diff --git a/mm/swapfile.c b/mm/swapfile.c index d954b71c4f9c..0d44179213ed 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -103,26 +103,39 @@ static inline unsigned char swap_count(unsigned char ent) return ent & ~SWAP_HAS_CACHE; /* may include COUNT_CONTINUED flag */ } +/* Reclaim the swap entry anyway if possible */ +#define TTRS_ANYWAY 0x1 +/* + * Reclaim the swap entry if there are no more mappings of the + * corresponding page + */ +#define TTRS_UNMAPPED 0x2 +/* Reclaim the swap entry if swap is getting full*/ +#define TTRS_FULL 0x4 + /* returns 1 if swap entry is freed */ -static int -__try_to_reclaim_swap(struct swap_info_struct *si, unsigned long offset) +static int __try_to_reclaim_swap(struct swap_info_struct *si, + unsigned long offset, unsigned long flags) { swp_entry_t entry = swp_entry(si->type, offset); struct page *page; int ret = 0; - page = find_get_page(swap_address_space(entry), swp_offset(entry)); + page = find_get_page(swap_address_space(entry), offset); if (!page) return 0; /* - * This function is called from scan_swap_map() and it's called - * by vmscan.c at reclaiming pages. So, we hold a lock on a page, here. - * We have to use trylock for avoiding deadlock. This is a special + * When this function is called from scan_swap_map_slots() and it's + * called by vmscan.c at reclaiming pages. So, we hold a lock on a page, + * here. We have to use trylock for avoiding deadlock. This is a special * case and you should use try_to_free_swap() with explicit lock_page() * in usual operations. */ if (trylock_page(page)) { - ret = try_to_free_swap(page); + if ((flags & TTRS_ANYWAY) || + ((flags & TTRS_UNMAPPED) && !page_mapped(page)) || + ((flags & TTRS_FULL) && mem_cgroup_swap_full(page))) + ret = try_to_free_swap(page); unlock_page(page); } put_page(page); @@ -780,7 +793,7 @@ checks: int swap_was_freed; unlock_cluster(ci); spin_unlock(&si->lock); - swap_was_freed = __try_to_reclaim_swap(si, offset); + swap_was_freed = __try_to_reclaim_swap(si, offset, TTRS_ANYWAY); spin_lock(&si->lock); /* entry was freed successfully, try to use this again */ if (swap_was_freed) @@ -1612,7 +1625,6 @@ int try_to_free_swap(struct page *page) int free_swap_and_cache(swp_entry_t entry) { struct swap_info_struct *p; - struct page *page = NULL; unsigned char count; if (non_swap_entry(entry)) @@ -1622,31 +1634,12 @@ int free_swap_and_cache(swp_entry_t entry) if (p) { count = __swap_entry_free(p, entry, 1); if (count == SWAP_HAS_CACHE && - !swap_page_trans_huge_swapped(p, entry)) { - page = find_get_page(swap_address_space(entry), - swp_offset(entry)); - if (page && !trylock_page(page)) { - put_page(page); - page = NULL; - } - } else if (!count) + !swap_page_trans_huge_swapped(p, entry)) + __try_to_reclaim_swap(p, swp_offset(entry), + TTRS_UNMAPPED | TTRS_FULL); + else if (!count) free_swap_slot(entry); } - if (page) { - /* - * Not mapped elsewhere, or swap space full? Free it! - * Also recheck PageSwapCache now page is locked (above). - */ - if (PageSwapCache(page) && !PageWriteback(page) && - (!page_mapped(page) || mem_cgroup_swap_full(page)) && - !swap_page_trans_huge_swapped(p, entry)) { - page = compound_head(page); - delete_from_swap_cache(page); - SetPageDirty(page); - } - unlock_page(page); - put_page(page); - } return p != NULL; } -- cgit v1.2.3 From 10e364da10d73ce4e3b61e1c53319ce93ee51c63 Mon Sep 17 00:00:00 2001 From: Huang Ying Date: Fri, 26 Oct 2018 15:03:49 -0700 Subject: mm/swapfile.c: call free_swap_slot() in __swap_entry_free() This is a code cleanup patch without functionality change. Originally, when __swap_entry_free() is called, and its return value is 0, free_swap_slot() will always be called to free the swap entry to the per-CPU pool. So move the call to free_swap_slot() to __swap_entry_free() to simplify the code. Link: http://lkml.kernel.org/r/20180827075535.17406-3-ying.huang@intel.com Signed-off-by: "Huang, Ying" Reviewed-by: Andrew Morton Cc: Dave Hansen Cc: Michal Hocko Cc: Johannes Weiner Cc: Shaohua Li Cc: Hugh Dickins Cc: Minchan Kim Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/swapfile.c | 10 ++++------ 1 file changed, 4 insertions(+), 6 deletions(-) (limited to 'mm') diff --git a/mm/swapfile.c b/mm/swapfile.c index 0d44179213ed..eaa5e2e55cab 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -1182,6 +1182,8 @@ static unsigned char __swap_entry_free(struct swap_info_struct *p, ci = lock_cluster_or_swap_info(p, offset); usage = __swap_entry_free_locked(p, offset, usage); unlock_cluster_or_swap_info(p, ci); + if (!usage) + free_swap_slot(entry); return usage; } @@ -1212,10 +1214,8 @@ void swap_free(swp_entry_t entry) struct swap_info_struct *p; p = _swap_info_get(entry); - if (p) { - if (!__swap_entry_free(p, entry, 1)) - free_swap_slot(entry); - } + if (p) + __swap_entry_free(p, entry, 1); } /* @@ -1637,8 +1637,6 @@ int free_swap_and_cache(swp_entry_t entry) !swap_page_trans_huge_swapped(p, entry)) __try_to_reclaim_swap(p, swp_offset(entry), TTRS_UNMAPPED | TTRS_FULL); - else if (!count) - free_swap_slot(entry); } return p != NULL; } -- cgit v1.2.3 From 979aafa5919b106a65646ac5f73f8354c0164e63 Mon Sep 17 00:00:00 2001 From: Huang Ying Date: Fri, 26 Oct 2018 15:03:53 -0700 Subject: mm/swapfile.c: clear si->swap_map[] in swap_free_cluster() si->swap_map[] of the swap entries in cluster needs to be cleared during freeing. Previously, this is done in the caller of swap_free_cluster(). This may cause code duplication (one user now, will add more users later) and lock/unlock cluster unnecessarily. In this patch, the clearing code is moved to swap_free_cluster() to avoid the downside. Link: http://lkml.kernel.org/r/20180827075535.17406-4-ying.huang@intel.com Signed-off-by: "Huang, Ying" Reviewed-by: Andrew Morton Cc: Dave Hansen Cc: Michal Hocko Cc: Johannes Weiner Cc: Shaohua Li Cc: Hugh Dickins Cc: Minchan Kim Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/swapfile.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'mm') diff --git a/mm/swapfile.c b/mm/swapfile.c index eaa5e2e55cab..2681e50592c5 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -932,6 +932,7 @@ static void swap_free_cluster(struct swap_info_struct *si, unsigned long idx) struct swap_cluster_info *ci; ci = lock_cluster(si, offset); + memset(si->swap_map + offset, 0, SWAPFILE_CLUSTER); cluster_set_count_flag(ci, 0, 0); free_cluster(si, idx); unlock_cluster(ci); @@ -1250,9 +1251,6 @@ void put_swap_page(struct page *page, swp_entry_t entry) if (free_entries == SWAPFILE_CLUSTER) { unlock_cluster_or_swap_info(si, ci); spin_lock(&si->lock); - ci = lock_cluster(si, offset); - memset(map, 0, SWAPFILE_CLUSTER); - unlock_cluster(ci); mem_cgroup_uncharge_swap(entry, SWAPFILE_CLUSTER); swap_free_cluster(si, idx); spin_unlock(&si->lock); -- cgit v1.2.3 From 7b0e0c0e35f5c7eca719404ca0e38bc964657330 Mon Sep 17 00:00:00 2001 From: Oscar Salvador Date: Fri, 26 Oct 2018 15:03:58 -0700 Subject: mm/page_alloc.c: clean up check_for_memory() check_for_memory() looks a bit confusing. First of all, we have this: if (N_MEMORY == N_NORMAL_MEMORY) return; Checking the ENUM declaration, looks like N_MEMORY canot be equal to N_NORMAL_MEMORY. I could not find where N_MEMORY is set to N_NORMAL_MEMORY, or the other way around either, so unless I am missing something, this condition will never evaluate to true. It makes sense to get rid of it. Moving forward, the operations within the loop look a bit confusing as well. We set N_HIGH_MEMORY unconditionally, and then we set N_NORMAL_MEMORY in case we have CONFIG_HIGHMEM (N_NORMAL_MEMORY != N_HIGH_MEMORY) and zone <= ZONE_NORMAL. (N_HIGH_MEMORY falls back to N_NORMAL_MEMORY on !CONFIG_HIGHMEM systems, and that is why we can just go ahead and set N_HIGH_MEMORY unconditionally) Although this works, it is a bit subtle. I think that this could be easier to follow: First, we should only set N_HIGH_MEMORY in case we have CONFIG_HIGHMEM. And then we should set N_NORMAL_MEMORY in case zone <= ZONE_NORMAL, without further checking whether we have CONFIG_HIGHMEM or not. Link: http://lkml.kernel.org/r/20180828210158.4617-1-osalvador@techadventures.net Signed-off-by: Oscar Salvador Reviewed-by: Andrew Morton Cc: Michael Hocko Cc: Vlastimil Babka Cc: Pavel Tatashin Cc: Joonsoo Kim Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/page_alloc.c | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-) (limited to 'mm') diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 7e2fb6e38f34..747031c2352d 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -6803,15 +6803,12 @@ static void check_for_memory(pg_data_t *pgdat, int nid) { enum zone_type zone_type; - if (N_MEMORY == N_NORMAL_MEMORY) - return; - for (zone_type = 0; zone_type <= ZONE_MOVABLE - 1; zone_type++) { struct zone *zone = &pgdat->node_zones[zone_type]; if (populated_zone(zone)) { - node_set_state(nid, N_HIGH_MEMORY); - if (N_NORMAL_MEMORY != N_HIGH_MEMORY && - zone_type <= ZONE_NORMAL) + if (IS_ENABLED(CONFIG_HIGHMEM)) + node_set_state(nid, N_HIGH_MEMORY); + if (zone_type <= ZONE_NORMAL) node_set_state(nid, N_NORMAL_MEMORY); break; } -- cgit v1.2.3 From 4b96a37d1c684f12468f436c0d79b5e6830d0b0b Mon Sep 17 00:00:00 2001 From: Souptick Joarder Date: Fri, 26 Oct 2018 15:04:03 -0700 Subject: mm: convert to use vm_fault_t As part of vm_fault_t conversion filemap_page_mkwrite() for the NOMMU case was missed. Now converted. Link: http://lkml.kernel.org/r/20180828174952.GA29229@jordon-HP-15-Notebook-PC Signed-off-by: Souptick Joarder Reviewed-by: Andrew Morton Cc: Matthew Wilcox Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/filemap.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'mm') diff --git a/mm/filemap.c b/mm/filemap.c index 52517f28e6f4..de6fed2a0815 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -2748,9 +2748,9 @@ int generic_file_readonly_mmap(struct file *file, struct vm_area_struct *vma) return generic_file_mmap(file, vma); } #else -int filemap_page_mkwrite(struct vm_fault *vmf) +vm_fault_t filemap_page_mkwrite(struct vm_fault *vmf) { - return -ENOSYS; + return VM_FAULT_SIGBUS; } int generic_file_mmap(struct file * file, struct vm_area_struct * vma) { -- cgit v1.2.3 From 5d7476374564645b1a2d299e242ad7b17b1104ee Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Fri, 26 Oct 2018 15:04:10 -0700 Subject: mm: remove vm_insert_mixed() All callers are now converted to vmf_insert_mixed() so convert vmf_insert_mixed() from being a compatibility wrapper into the real function. Link: http://lkml.kernel.org/r/20180828145728.11873-3-willy@infradead.org Signed-off-by: Matthew Wilcox Reviewed-by: Andrew Morton Cc: Nicolas Pitre Cc: Souptick Joarder Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 15 +-------------- mm/memory.c | 14 ++++++++++---- 2 files changed, 11 insertions(+), 18 deletions(-) (limited to 'mm') diff --git a/include/linux/mm.h b/include/linux/mm.h index daa2b8f1e9a8..ecc6f9347756 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2506,7 +2506,7 @@ int vm_insert_pfn(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn); int vm_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn, pgprot_t pgprot); -int vm_insert_mixed(struct vm_area_struct *vma, unsigned long addr, +vm_fault_t vmf_insert_mixed(struct vm_area_struct *vma, unsigned long addr, pfn_t pfn); vm_fault_t vmf_insert_mixed_mkwrite(struct vm_area_struct *vma, unsigned long addr, pfn_t pfn); @@ -2525,19 +2525,6 @@ static inline vm_fault_t vmf_insert_page(struct vm_area_struct *vma, return VM_FAULT_NOPAGE; } -static inline vm_fault_t vmf_insert_mixed(struct vm_area_struct *vma, - unsigned long addr, pfn_t pfn) -{ - int err = vm_insert_mixed(vma, addr, pfn); - - if (err == -ENOMEM) - return VM_FAULT_OOM; - if (err < 0 && err != -EBUSY) - return VM_FAULT_SIGBUS; - - return VM_FAULT_NOPAGE; -} - static inline vm_fault_t vmf_insert_pfn(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn) { diff --git a/mm/memory.c b/mm/memory.c index 21a5e6e4758b..200aaf291e98 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -1693,13 +1693,19 @@ static int __vm_insert_mixed(struct vm_area_struct *vma, unsigned long addr, return insert_pfn(vma, addr, pfn, pgprot, mkwrite); } -int vm_insert_mixed(struct vm_area_struct *vma, unsigned long addr, - pfn_t pfn) +vm_fault_t vmf_insert_mixed(struct vm_area_struct *vma, unsigned long addr, + pfn_t pfn) { - return __vm_insert_mixed(vma, addr, pfn, false); + int err = __vm_insert_mixed(vma, addr, pfn, false); + if (err == -ENOMEM) + return VM_FAULT_OOM; + if (err < 0 && err != -EBUSY) + return VM_FAULT_SIGBUS; + + return VM_FAULT_NOPAGE; } -EXPORT_SYMBOL(vm_insert_mixed); +EXPORT_SYMBOL(vmf_insert_mixed); /* * If the insertion of PTE failed because someone else already added a -- cgit v1.2.3 From f5e6d1d5f8f3080aa7a51acea1f77085f45abe9c Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Fri, 26 Oct 2018 15:04:13 -0700 Subject: mm: introduce vmf_insert_pfn_prot() Like vm_insert_pfn_prot(), but returns a vm_fault_t instead of an errno. Also unexport vm_insert_pfn_prot as it has no modular users. Link: http://lkml.kernel.org/r/20180828145728.11873-4-willy@infradead.org Signed-off-by: Matthew Wilcox Reviewed-by: Andrew Morton Cc: Nicolas Pitre Cc: Souptick Joarder Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 2 ++ mm/memory.c | 47 +++++++++++++++++++++++++++++++---------------- 2 files changed, 33 insertions(+), 16 deletions(-) (limited to 'mm') diff --git a/include/linux/mm.h b/include/linux/mm.h index ecc6f9347756..f1293bdc6de2 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2506,6 +2506,8 @@ int vm_insert_pfn(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn); int vm_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn, pgprot_t pgprot); +vm_fault_t vmf_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr, + unsigned long pfn, pgprot_t pgprot); vm_fault_t vmf_insert_mixed(struct vm_area_struct *vma, unsigned long addr, pfn_t pfn); vm_fault_t vmf_insert_mixed_mkwrite(struct vm_area_struct *vma, diff --git a/mm/memory.c b/mm/memory.c index 200aaf291e98..b3eecb3aa65f 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -1596,21 +1596,6 @@ int vm_insert_pfn(struct vm_area_struct *vma, unsigned long addr, } EXPORT_SYMBOL(vm_insert_pfn); -/** - * vm_insert_pfn_prot - insert single pfn into user vma with specified pgprot - * @vma: user vma to map to - * @addr: target user address of this page - * @pfn: source kernel pfn - * @pgprot: pgprot flags for the inserted page - * - * This is exactly like vm_insert_pfn, except that it allows drivers to - * to override pgprot on a per-page basis. - * - * This only makes sense for IO mappings, and it makes no sense for - * cow mappings. In general, using multiple vmas is preferable; - * vm_insert_pfn_prot should only be used if using multiple VMAs is - * impractical. - */ int vm_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn, pgprot_t pgprot) { @@ -1640,7 +1625,37 @@ int vm_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr, return ret; } -EXPORT_SYMBOL(vm_insert_pfn_prot); + +/** + * vmf_insert_pfn_prot - insert single pfn into user vma with specified pgprot + * @vma: user vma to map to + * @addr: target user address of this page + * @pfn: source kernel pfn + * @pgprot: pgprot flags for the inserted page + * + * This is exactly like vmf_insert_pfn(), except that it allows drivers to + * to override pgprot on a per-page basis. + * + * This only makes sense for IO mappings, and it makes no sense for + * COW mappings. In general, using multiple vmas is preferable; + * vm_insert_pfn_prot should only be used if using multiple VMAs is + * impractical. + * + * Return: vm_fault_t value. + */ +vm_fault_t vmf_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr, + unsigned long pfn, pgprot_t pgprot) +{ + int err = vm_insert_pfn_prot(vma, addr, pfn, pgprot); + + if (err == -ENOMEM) + return VM_FAULT_OOM; + if (err < 0 && err != -EBUSY) + return VM_FAULT_SIGBUS; + + return VM_FAULT_NOPAGE; +} +EXPORT_SYMBOL(vmf_insert_pfn_prot); static bool vm_mixed_ok(struct vm_area_struct *vma, pfn_t pfn) { -- cgit v1.2.3 From bc12e6ad9617831727e4201e7cbf5c3b868cc8fd Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Fri, 26 Oct 2018 15:04:21 -0700 Subject: mm: make vm_insert_pfn_prot() static Now this is no longer used outside mm/memory.c, make it static. Link: http://lkml.kernel.org/r/20180828145728.11873-6-willy@infradead.org Signed-off-by: Matthew Wilcox Reviewed-by: Andrew Morton Cc: Nicolas Pitre Cc: Souptick Joarder Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 2 -- mm/memory.c | 50 +++++++++++++++++++++++++------------------------- 2 files changed, 25 insertions(+), 27 deletions(-) (limited to 'mm') diff --git a/include/linux/mm.h b/include/linux/mm.h index f1293bdc6de2..0f5db0455e61 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2504,8 +2504,6 @@ int remap_pfn_range(struct vm_area_struct *, unsigned long addr, int vm_insert_page(struct vm_area_struct *, unsigned long addr, struct page *); int vm_insert_pfn(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn); -int vm_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr, - unsigned long pfn, pgprot_t pgprot); vm_fault_t vmf_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn, pgprot_t pgprot); vm_fault_t vmf_insert_mixed(struct vm_area_struct *vma, unsigned long addr, diff --git a/mm/memory.c b/mm/memory.c index b3eecb3aa65f..6365144f8267 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -1572,31 +1572,7 @@ out: return retval; } -/** - * vm_insert_pfn - insert single pfn into user vma - * @vma: user vma to map to - * @addr: target user address of this page - * @pfn: source kernel pfn - * - * Similar to vm_insert_page, this allows drivers to insert individual pages - * they've allocated into a user vma. Same comments apply. - * - * This function should only be called from a vm_ops->fault handler, and - * in that case the handler should return NULL. - * - * vma cannot be a COW mapping. - * - * As this is called only for pages that do not currently exist, we - * do not need to flush old virtual caches or the TLB. - */ -int vm_insert_pfn(struct vm_area_struct *vma, unsigned long addr, - unsigned long pfn) -{ - return vm_insert_pfn_prot(vma, addr, pfn, vma->vm_page_prot); -} -EXPORT_SYMBOL(vm_insert_pfn); - -int vm_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr, +static int vm_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn, pgprot_t pgprot) { int ret; @@ -1626,6 +1602,30 @@ int vm_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr, return ret; } +/** + * vm_insert_pfn - insert single pfn into user vma + * @vma: user vma to map to + * @addr: target user address of this page + * @pfn: source kernel pfn + * + * Similar to vm_insert_page, this allows drivers to insert individual pages + * they've allocated into a user vma. Same comments apply. + * + * This function should only be called from a vm_ops->fault handler, and + * in that case the handler should return NULL. + * + * vma cannot be a COW mapping. + * + * As this is called only for pages that do not currently exist, we + * do not need to flush old virtual caches or the TLB. + */ +int vm_insert_pfn(struct vm_area_struct *vma, unsigned long addr, + unsigned long pfn) +{ + return vm_insert_pfn_prot(vma, addr, pfn, vma->vm_page_prot); +} +EXPORT_SYMBOL(vm_insert_pfn); + /** * vmf_insert_pfn_prot - insert single pfn into user vma with specified pgprot * @vma: user vma to map to -- cgit v1.2.3 From ae2b01f37044c10e975d22116755df56252b09d8 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Fri, 26 Oct 2018 15:04:29 -0700 Subject: mm: remove vm_insert_pfn() All callers are now converted to vmf_insert_pfn() so convert vmf_insert_pfn() from being a compatibility wrapper around vm_insert_pfn() to being a compatibility wrapper around vmf_insert_pfn_prot(). Link: http://lkml.kernel.org/r/20180828145728.11873-8-willy@infradead.org Signed-off-by: Matthew Wilcox Reviewed-by: Andrew Morton Cc: Nicolas Pitre Cc: Souptick Joarder Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 15 +-------------- mm/memory.c | 54 +++++++++++++++++++++++++++++------------------------- 2 files changed, 30 insertions(+), 39 deletions(-) (limited to 'mm') diff --git a/include/linux/mm.h b/include/linux/mm.h index 0f5db0455e61..737279bb479c 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2502,7 +2502,7 @@ struct vm_area_struct *find_extend_vma(struct mm_struct *, unsigned long addr); int remap_pfn_range(struct vm_area_struct *, unsigned long addr, unsigned long pfn, unsigned long size, pgprot_t); int vm_insert_page(struct vm_area_struct *, unsigned long addr, struct page *); -int vm_insert_pfn(struct vm_area_struct *vma, unsigned long addr, +vm_fault_t vmf_insert_pfn(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn); vm_fault_t vmf_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn, pgprot_t pgprot); @@ -2525,19 +2525,6 @@ static inline vm_fault_t vmf_insert_page(struct vm_area_struct *vma, return VM_FAULT_NOPAGE; } -static inline vm_fault_t vmf_insert_pfn(struct vm_area_struct *vma, - unsigned long addr, unsigned long pfn) -{ - int err = vm_insert_pfn(vma, addr, pfn); - - if (err == -ENOMEM) - return VM_FAULT_OOM; - if (err < 0 && err != -EBUSY) - return VM_FAULT_SIGBUS; - - return VM_FAULT_NOPAGE; -} - static inline vm_fault_t vmf_error(int err) { if (err == -ENOMEM) diff --git a/mm/memory.c b/mm/memory.c index 6365144f8267..08653d0a795a 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -1602,30 +1602,6 @@ static int vm_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr, return ret; } -/** - * vm_insert_pfn - insert single pfn into user vma - * @vma: user vma to map to - * @addr: target user address of this page - * @pfn: source kernel pfn - * - * Similar to vm_insert_page, this allows drivers to insert individual pages - * they've allocated into a user vma. Same comments apply. - * - * This function should only be called from a vm_ops->fault handler, and - * in that case the handler should return NULL. - * - * vma cannot be a COW mapping. - * - * As this is called only for pages that do not currently exist, we - * do not need to flush old virtual caches or the TLB. - */ -int vm_insert_pfn(struct vm_area_struct *vma, unsigned long addr, - unsigned long pfn) -{ - return vm_insert_pfn_prot(vma, addr, pfn, vma->vm_page_prot); -} -EXPORT_SYMBOL(vm_insert_pfn); - /** * vmf_insert_pfn_prot - insert single pfn into user vma with specified pgprot * @vma: user vma to map to @@ -1638,9 +1614,10 @@ EXPORT_SYMBOL(vm_insert_pfn); * * This only makes sense for IO mappings, and it makes no sense for * COW mappings. In general, using multiple vmas is preferable; - * vm_insert_pfn_prot should only be used if using multiple VMAs is + * vmf_insert_pfn_prot should only be used if using multiple VMAs is * impractical. * + * Context: Process context. May allocate using %GFP_KERNEL. * Return: vm_fault_t value. */ vm_fault_t vmf_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr, @@ -1657,6 +1634,33 @@ vm_fault_t vmf_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr, } EXPORT_SYMBOL(vmf_insert_pfn_prot); +/** + * vmf_insert_pfn - insert single pfn into user vma + * @vma: user vma to map to + * @addr: target user address of this page + * @pfn: source kernel pfn + * + * Similar to vm_insert_page, this allows drivers to insert individual pages + * they've allocated into a user vma. Same comments apply. + * + * This function should only be called from a vm_ops->fault handler, and + * in that case the handler should return the result of this function. + * + * vma cannot be a COW mapping. + * + * As this is called only for pages that do not currently exist, we + * do not need to flush old virtual caches or the TLB. + * + * Context: Process context. May allocate using %GFP_KERNEL. + * Return: vm_fault_t value. + */ +vm_fault_t vmf_insert_pfn(struct vm_area_struct *vma, unsigned long addr, + unsigned long pfn) +{ + return vmf_insert_pfn_prot(vma, addr, pfn, vma->vm_page_prot); +} +EXPORT_SYMBOL(vmf_insert_pfn); + static bool vm_mixed_ok(struct vm_area_struct *vma, pfn_t pfn) { /* these checks mirror the abort conditions in vm_normal_page */ -- cgit v1.2.3 From 6d958546ff611c9ae09b181e628c1c5d5da5ebda Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Fri, 26 Oct 2018 15:04:33 -0700 Subject: mm: inline vm_insert_pfn_prot() into caller vm_insert_pfn_prot() is only called from vmf_insert_pfn_prot(), so inline it and convert some of the errnos into vm_fault codes earlier. Link: http://lkml.kernel.org/r/20180828145728.11873-9-willy@infradead.org Signed-off-by: Matthew Wilcox Reviewed-by: Andrew Morton Cc: Nicolas Pitre Cc: Souptick Joarder Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memory.c | 55 ++++++++++++++++++++++++------------------------------- 1 file changed, 24 insertions(+), 31 deletions(-) (limited to 'mm') diff --git a/mm/memory.c b/mm/memory.c index 08653d0a795a..40b692fa4b99 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -1572,36 +1572,6 @@ out: return retval; } -static int vm_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr, - unsigned long pfn, pgprot_t pgprot) -{ - int ret; - /* - * Technically, architectures with pte_special can avoid all these - * restrictions (same for remap_pfn_range). However we would like - * consistency in testing and feature parity among all, so we should - * try to keep these invariants in place for everybody. - */ - BUG_ON(!(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP))); - BUG_ON((vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)) == - (VM_PFNMAP|VM_MIXEDMAP)); - BUG_ON((vma->vm_flags & VM_PFNMAP) && is_cow_mapping(vma->vm_flags)); - BUG_ON((vma->vm_flags & VM_MIXEDMAP) && pfn_valid(pfn)); - - if (addr < vma->vm_start || addr >= vma->vm_end) - return -EFAULT; - - if (!pfn_modify_allowed(pfn, pgprot)) - return -EACCES; - - track_pfn_insert(vma, &pgprot, __pfn_to_pfn_t(pfn, PFN_DEV)); - - ret = insert_pfn(vma, addr, __pfn_to_pfn_t(pfn, PFN_DEV), pgprot, - false); - - return ret; -} - /** * vmf_insert_pfn_prot - insert single pfn into user vma with specified pgprot * @vma: user vma to map to @@ -1623,7 +1593,30 @@ static int vm_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr, vm_fault_t vmf_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn, pgprot_t pgprot) { - int err = vm_insert_pfn_prot(vma, addr, pfn, pgprot); + int err; + + /* + * Technically, architectures with pte_special can avoid all these + * restrictions (same for remap_pfn_range). However we would like + * consistency in testing and feature parity among all, so we should + * try to keep these invariants in place for everybody. + */ + BUG_ON(!(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP))); + BUG_ON((vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)) == + (VM_PFNMAP|VM_MIXEDMAP)); + BUG_ON((vma->vm_flags & VM_PFNMAP) && is_cow_mapping(vma->vm_flags)); + BUG_ON((vma->vm_flags & VM_MIXEDMAP) && pfn_valid(pfn)); + + if (addr < vma->vm_start || addr >= vma->vm_end) + return VM_FAULT_SIGBUS; + + if (!pfn_modify_allowed(pfn, pgprot)) + return VM_FAULT_SIGBUS; + + track_pfn_insert(vma, &pgprot, __pfn_to_pfn_t(pfn, PFN_DEV)); + + err = insert_pfn(vma, addr, __pfn_to_pfn_t(pfn, PFN_DEV), pgprot, + false); if (err == -ENOMEM) return VM_FAULT_OOM; -- cgit v1.2.3 From 79f3aa5ba989a1fa6e2ef189f2abdfcee25ba663 Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Fri, 26 Oct 2018 15:04:37 -0700 Subject: mm: convert __vm_insert_mixed() to vm_fault_t Both of its callers currently convert its errno return into a vm_fault_t, so move the conversion into __vm_insert_mixed(). Link: http://lkml.kernel.org/r/20180828145728.11873-10-willy@infradead.org Signed-off-by: Matthew Wilcox Reviewed-by: Andrew Morton Cc: Nicolas Pitre Cc: Souptick Joarder Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memory.c | 36 +++++++++++++++--------------------- 1 file changed, 15 insertions(+), 21 deletions(-) (limited to 'mm') diff --git a/mm/memory.c b/mm/memory.c index 40b692fa4b99..a016fd1198a9 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -1668,20 +1668,21 @@ static bool vm_mixed_ok(struct vm_area_struct *vma, pfn_t pfn) return false; } -static int __vm_insert_mixed(struct vm_area_struct *vma, unsigned long addr, - pfn_t pfn, bool mkwrite) +static vm_fault_t __vm_insert_mixed(struct vm_area_struct *vma, + unsigned long addr, pfn_t pfn, bool mkwrite) { pgprot_t pgprot = vma->vm_page_prot; + int err; BUG_ON(!vm_mixed_ok(vma, pfn)); if (addr < vma->vm_start || addr >= vma->vm_end) - return -EFAULT; + return VM_FAULT_SIGBUS; track_pfn_insert(vma, &pgprot, pfn); if (!pfn_modify_allowed(pfn_t_to_pfn(pfn), pgprot)) - return -EACCES; + return VM_FAULT_SIGBUS; /* * If we don't have pte special, then we have to use the pfn_valid() @@ -1700,15 +1701,10 @@ static int __vm_insert_mixed(struct vm_area_struct *vma, unsigned long addr, * result in pfn_t_has_page() == false. */ page = pfn_to_page(pfn_t_to_pfn(pfn)); - return insert_page(vma, addr, page, pgprot); + err = insert_page(vma, addr, page, pgprot); + } else { + err = insert_pfn(vma, addr, pfn, pgprot, mkwrite); } - return insert_pfn(vma, addr, pfn, pgprot, mkwrite); -} - -vm_fault_t vmf_insert_mixed(struct vm_area_struct *vma, unsigned long addr, - pfn_t pfn) -{ - int err = __vm_insert_mixed(vma, addr, pfn, false); if (err == -ENOMEM) return VM_FAULT_OOM; @@ -1717,6 +1713,12 @@ vm_fault_t vmf_insert_mixed(struct vm_area_struct *vma, unsigned long addr, return VM_FAULT_NOPAGE; } + +vm_fault_t vmf_insert_mixed(struct vm_area_struct *vma, unsigned long addr, + pfn_t pfn) +{ + return __vm_insert_mixed(vma, addr, pfn, false); +} EXPORT_SYMBOL(vmf_insert_mixed); /* @@ -1724,18 +1726,10 @@ EXPORT_SYMBOL(vmf_insert_mixed); * different entry in the mean time, we treat that as success as we assume * the same entry was actually inserted. */ - vm_fault_t vmf_insert_mixed_mkwrite(struct vm_area_struct *vma, unsigned long addr, pfn_t pfn) { - int err; - - err = __vm_insert_mixed(vma, addr, pfn, true); - if (err == -ENOMEM) - return VM_FAULT_OOM; - if (err < 0 && err != -EBUSY) - return VM_FAULT_SIGBUS; - return VM_FAULT_NOPAGE; + return __vm_insert_mixed(vma, addr, pfn, true); } EXPORT_SYMBOL(vmf_insert_mixed_mkwrite); -- cgit v1.2.3 From 9b5a8e00d479bb5e55f6902bf50877c080d9506d Mon Sep 17 00:00:00 2001 From: Matthew Wilcox Date: Fri, 26 Oct 2018 15:04:40 -0700 Subject: mm: convert insert_pfn() to vm_fault_t All callers convert its errno into a vm_fault_t, so convert it to return a vm_fault_t directly. Link: http://lkml.kernel.org/r/20180828145728.11873-11-willy@infradead.org Signed-off-by: Matthew Wilcox Reviewed-by: Andrew Morton Cc: Nicolas Pitre Cc: Souptick Joarder Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memory.c | 24 +++++------------------- 1 file changed, 5 insertions(+), 19 deletions(-) (limited to 'mm') diff --git a/mm/memory.c b/mm/memory.c index a016fd1198a9..6abc74f41bc0 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -1520,19 +1520,16 @@ int vm_insert_page(struct vm_area_struct *vma, unsigned long addr, } EXPORT_SYMBOL(vm_insert_page); -static int insert_pfn(struct vm_area_struct *vma, unsigned long addr, +static vm_fault_t insert_pfn(struct vm_area_struct *vma, unsigned long addr, pfn_t pfn, pgprot_t prot, bool mkwrite) { struct mm_struct *mm = vma->vm_mm; - int retval; pte_t *pte, entry; spinlock_t *ptl; - retval = -ENOMEM; pte = get_locked_pte(mm, addr, &ptl); if (!pte) - goto out; - retval = -EBUSY; + return VM_FAULT_OOM; if (!pte_none(*pte)) { if (mkwrite) { /* @@ -1565,11 +1562,9 @@ out_mkwrite: set_pte_at(mm, addr, pte, entry); update_mmu_cache(vma, addr, pte); /* XXX: why not for insert_page? */ - retval = 0; out_unlock: pte_unmap_unlock(pte, ptl); -out: - return retval; + return VM_FAULT_NOPAGE; } /** @@ -1593,8 +1588,6 @@ out: vm_fault_t vmf_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr, unsigned long pfn, pgprot_t pgprot) { - int err; - /* * Technically, architectures with pte_special can avoid all these * restrictions (same for remap_pfn_range). However we would like @@ -1615,15 +1608,8 @@ vm_fault_t vmf_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr, track_pfn_insert(vma, &pgprot, __pfn_to_pfn_t(pfn, PFN_DEV)); - err = insert_pfn(vma, addr, __pfn_to_pfn_t(pfn, PFN_DEV), pgprot, + return insert_pfn(vma, addr, __pfn_to_pfn_t(pfn, PFN_DEV), pgprot, false); - - if (err == -ENOMEM) - return VM_FAULT_OOM; - if (err < 0 && err != -EBUSY) - return VM_FAULT_SIGBUS; - - return VM_FAULT_NOPAGE; } EXPORT_SYMBOL(vmf_insert_pfn_prot); @@ -1703,7 +1689,7 @@ static vm_fault_t __vm_insert_mixed(struct vm_area_struct *vma, page = pfn_to_page(pfn_t_to_pfn(pfn)); err = insert_page(vma, addr, page, pgprot); } else { - err = insert_pfn(vma, addr, pfn, pgprot, mkwrite); + return insert_pfn(vma, addr, pfn, pgprot, mkwrite); } if (err == -ENOMEM) -- cgit v1.2.3 From 3b9aadf7278d16d7bed4d5d808501065f70898d8 Mon Sep 17 00:00:00 2001 From: Andrea Arcangeli Date: Fri, 26 Oct 2018 15:05:16 -0700 Subject: userfaultfd: allow get_mempolicy(MPOL_F_NODE|MPOL_F_ADDR) to trigger userfaults get_mempolicy(MPOL_F_NODE|MPOL_F_ADDR) called a get_user_pages that would not be waiting for userfaults before failing and it would hit on a SIGBUS instead. Using get_user_pages_locked/unlocked instead will allow get_mempolicy to allow userfaults to resolve the fault and fill the hole, before grabbing the node id of the page. If the user calls get_mempolicy() with MPOL_F_ADDR | MPOL_F_NODE for an address inside an area managed by uffd and there is no page at that address, the page allocation from within get_mempolicy() will fail because get_user_pages() does not allow for page fault retry required for uffd; the user will get SIGBUS. With this patch, the page fault will be resolved by the uffd and the get_mempolicy() will continue normally. Background: Via code review, previously the syscall would have returned -EFAULT (vm_fault_to_errno), now it will block and wait for an userfault (if it's waken before the fault is resolved it'll still -EFAULT). This way get_mempolicy will give a chance to an "unaware" app to be compliant with userfaults. The reason this visible change is that becoming "userfault compliant" cannot regress anything: all other syscalls including read(2)/write(2) had to become "userfault compliant" long time ago (that's one of the things userfaultfd can do that PROT_NONE and trapping segfaults can't). So this is just one more syscall that become "userfault compliant" like all other major ones already were. This has been happening on virtio-bridge dpdk process which just called get_mempolicy on the guest space post live migration, but before the memory had a chance to be migrated to destination. I didn't run an strace to be able to show the -EFAULT going away, but I've the confirmation of the below debug aid information (only visible with CONFIG_DEBUG_VM=y) going away with the patch: [20116.371461] FAULT_FLAG_ALLOW_RETRY missing 0 [20116.371464] CPU: 1 PID: 13381 Comm: vhost-events Not tainted 4.17.12-200.fc28.x86_64 #1 [20116.371465] Hardware name: LENOVO 20FAS2BN0A/20FAS2BN0A, BIOS N1CET54W (1.22 ) 02/10/2017 [20116.371466] Call Trace: [20116.371473] dump_stack+0x5c/0x80 [20116.371476] handle_userfault.cold.37+0x1b/0x22 [20116.371479] ? remove_wait_queue+0x20/0x60 [20116.371481] ? poll_freewait+0x45/0xa0 [20116.371483] ? do_sys_poll+0x31c/0x520 [20116.371485] ? radix_tree_lookup_slot+0x1e/0x50 [20116.371488] shmem_getpage_gfp+0xce7/0xe50 [20116.371491] ? page_add_file_rmap+0x1a/0x2c0 [20116.371493] shmem_fault+0x78/0x1e0 [20116.371495] ? filemap_map_pages+0x3a1/0x450 [20116.371498] __do_fault+0x1f/0xc0 [20116.371500] __handle_mm_fault+0xe2e/0x12f0 [20116.371502] handle_mm_fault+0xda/0x200 [20116.371504] __get_user_pages+0x238/0x790 [20116.371506] get_user_pages+0x3e/0x50 [20116.371510] kernel_get_mempolicy+0x40b/0x700 [20116.371512] ? vfs_write+0x170/0x1a0 [20116.371515] __x64_sys_get_mempolicy+0x21/0x30 [20116.371517] do_syscall_64+0x5b/0x160 [20116.371520] entry_SYSCALL_64_after_hwframe+0x44/0xa9 The above harmless debug message (not a kernel crash, just a dump_stack()) is shown with CONFIG_DEBUG_VM=y to more quickly identify and improve kernel spots that may have to become "userfaultfd compliant" like this one (without having to run an strace and search for syscall misbehavior). Spots like the above are more closer to a kernel bug for the non-cooperative usages that Mike focuses on, than for for dpdk qemu-cooperative usages that reproduced it, but it's still nicer to get this fixed for dpdk too. The part of the patch that caused me to think is only the implementation issue of mpol_get, but it looks like it should work safe no matter the kind of mempolicy structure that is (the default static policy also starts at 1 so it'll go to 2 and back to 1 without crashing everything at 0). [rppt@linux.vnet.ibm.com: changelog addition] http://lkml.kernel.org/r/20180904073718.GA26916@rapoport-lnx Link: http://lkml.kernel.org/r/20180831214848.23676-1-aarcange@redhat.com Signed-off-by: Andrea Arcangeli Reported-by: Maxime Coquelin Tested-by: Dr. David Alan Gilbert Reviewed-by: Mike Rapoport Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/mempolicy.c | 24 +++++++++++++++++++----- 1 file changed, 19 insertions(+), 5 deletions(-) (limited to 'mm') diff --git a/mm/mempolicy.c b/mm/mempolicy.c index da858f794eb6..2e76a8f65e94 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -797,16 +797,19 @@ static void get_policy_nodemask(struct mempolicy *p, nodemask_t *nodes) } } -static int lookup_node(unsigned long addr) +static int lookup_node(struct mm_struct *mm, unsigned long addr) { struct page *p; int err; - err = get_user_pages(addr & PAGE_MASK, 1, 0, &p, NULL); + int locked = 1; + err = get_user_pages_locked(addr & PAGE_MASK, 1, 0, &p, &locked); if (err >= 0) { err = page_to_nid(p); put_page(p); } + if (locked) + up_read(&mm->mmap_sem); return err; } @@ -817,7 +820,7 @@ static long do_get_mempolicy(int *policy, nodemask_t *nmask, int err; struct mm_struct *mm = current->mm; struct vm_area_struct *vma = NULL; - struct mempolicy *pol = current->mempolicy; + struct mempolicy *pol = current->mempolicy, *pol_refcount = NULL; if (flags & ~(unsigned long)(MPOL_F_NODE|MPOL_F_ADDR|MPOL_F_MEMS_ALLOWED)) @@ -857,7 +860,16 @@ static long do_get_mempolicy(int *policy, nodemask_t *nmask, if (flags & MPOL_F_NODE) { if (flags & MPOL_F_ADDR) { - err = lookup_node(addr); + /* + * Take a refcount on the mpol, lookup_node() + * wil drop the mmap_sem, so after calling + * lookup_node() only "pol" remains valid, "vma" + * is stale. + */ + pol_refcount = pol; + vma = NULL; + mpol_get(pol); + err = lookup_node(mm, addr); if (err < 0) goto out; *policy = err; @@ -892,7 +904,9 @@ static long do_get_mempolicy(int *policy, nodemask_t *nmask, out: mpol_cond_put(pol); if (vma) - up_read(¤t->mm->mmap_sem); + up_read(&mm->mmap_sem); + if (pol_refcount) + mpol_put(pol_refcount); return err; } -- cgit v1.2.3 From cc252eae85e09552f9c1e7ac0c3227f835efdf2d Mon Sep 17 00:00:00 2001 From: Vlastimil Babka Date: Fri, 26 Oct 2018 15:05:34 -0700 Subject: mm, slab: combine kmalloc_caches and kmalloc_dma_caches Patch series "kmalloc-reclaimable caches", v4. As discussed at LSF/MM [1] here's a patchset that introduces kmalloc-reclaimable caches (more details in the second patch) and uses them for dcache external names. That allows us to repurpose the NR_INDIRECTLY_RECLAIMABLE_BYTES counter later in the series. With patch 3/6, dcache external names are allocated from kmalloc-rcl-* caches, eliminating the need for manual accounting. More importantly, it also ensures the reclaimable kmalloc allocations are grouped in pages separate from the regular kmalloc allocations. The need for proper accounting of dcache external names has shown it's easy for misbehaving process to allocate lots of them, causing premature OOMs. Without the added grouping, it's likely that a similar workload can interleave the dcache external names allocations with regular kmalloc allocations (note: I haven't searched myself for an example of such regular kmalloc allocation, but I would be very surprised if there wasn't some). A pathological case would be e.g. one 64byte regular allocations with 63 external dcache names in a page (64x64=4096), which means the page is not freed even after reclaiming after all dcache names, and the process can thus "steal" the whole page with single 64byte allocation. If other kmalloc users similar to dcache external names become identified, they can also benefit from the new functionality simply by adding __GFP_RECLAIMABLE to the kmalloc calls. Side benefits of the patchset (that could be also merged separately) include removed branch for detecting __GFP_DMA kmalloc(), and shortening kmalloc cache names in /proc/slabinfo output. The latter is potentially an ABI break in case there are tools parsing the names and expecting the values to be in bytes. This is how /proc/slabinfo looks like after booting in virtme: ... kmalloc-rcl-4M 0 0 4194304 1 1024 : tunables 1 1 0 : slabdata 0 0 0 ... kmalloc-rcl-96 7 32 128 32 1 : tunables 120 60 8 : slabdata 1 1 0 kmalloc-rcl-64 25 128 64 64 1 : tunables 120 60 8 : slabdata 2 2 0 kmalloc-rcl-32 0 0 32 124 1 : tunables 120 60 8 : slabdata 0 0 0 kmalloc-4M 0 0 4194304 1 1024 : tunables 1 1 0 : slabdata 0 0 0 kmalloc-2M 0 0 2097152 1 512 : tunables 1 1 0 : slabdata 0 0 0 kmalloc-1M 0 0 1048576 1 256 : tunables 1 1 0 : slabdata 0 0 0 ... /proc/vmstat with renamed nr_indirectly_reclaimable_bytes counter: ... nr_slab_reclaimable 2817 nr_slab_unreclaimable 1781 ... nr_kernel_misc_reclaimable 0 ... /proc/meminfo with new KReclaimable counter: ... Shmem: 564 kB KReclaimable: 11260 kB Slab: 18368 kB SReclaimable: 11260 kB SUnreclaim: 7108 kB KernelStack: 1248 kB ... This patch (of 6): The kmalloc caches currently mainain separate (optional) array kmalloc_dma_caches for __GFP_DMA allocations. There are tests for __GFP_DMA in the allocation hotpaths. We can avoid the branches by combining kmalloc_caches and kmalloc_dma_caches into a single two-dimensional array where the outer dimension is cache "type". This will also allow to add kmalloc-reclaimable caches as a third type. Link: http://lkml.kernel.org/r/20180731090649.16028-2-vbabka@suse.cz Signed-off-by: Vlastimil Babka Acked-by: Mel Gorman Acked-by: Christoph Lameter Acked-by: Roman Gushchin Cc: Michal Hocko Cc: Johannes Weiner Cc: David Rientjes Cc: Joonsoo Kim Cc: Matthew Wilcox Cc: Laura Abbott Cc: Sumit Semwal Cc: Vijayanand Jitta Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/slab.h | 42 +++++++++++++++++++++++++++++++----------- mm/slab.c | 4 ++-- mm/slab_common.c | 31 ++++++++++++------------------- mm/slub.c | 13 +++++++------ 4 files changed, 52 insertions(+), 38 deletions(-) (limited to 'mm') diff --git a/include/linux/slab.h b/include/linux/slab.h index ed9cbddeb4a6..2a7137043e91 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -295,12 +295,29 @@ static inline void __check_heap_object(const void *ptr, unsigned long n, #define SLAB_OBJ_MIN_SIZE (KMALLOC_MIN_SIZE < 16 ? \ (KMALLOC_MIN_SIZE) : 16) +enum kmalloc_cache_type { + KMALLOC_NORMAL = 0, +#ifdef CONFIG_ZONE_DMA + KMALLOC_DMA, +#endif + NR_KMALLOC_TYPES +}; + #ifndef CONFIG_SLOB -extern struct kmem_cache *kmalloc_caches[KMALLOC_SHIFT_HIGH + 1]; +extern struct kmem_cache * +kmalloc_caches[NR_KMALLOC_TYPES][KMALLOC_SHIFT_HIGH + 1]; + +static __always_inline enum kmalloc_cache_type kmalloc_type(gfp_t flags) +{ + int is_dma = 0; + #ifdef CONFIG_ZONE_DMA -extern struct kmem_cache *kmalloc_dma_caches[KMALLOC_SHIFT_HIGH + 1]; + is_dma = !!(flags & __GFP_DMA); #endif + return is_dma; +} + /* * Figure out which kmalloc slab an allocation of a certain size * belongs to. @@ -501,18 +518,20 @@ static __always_inline void *kmalloc_large(size_t size, gfp_t flags) static __always_inline void *kmalloc(size_t size, gfp_t flags) { if (__builtin_constant_p(size)) { +#ifndef CONFIG_SLOB + unsigned int index; +#endif if (size > KMALLOC_MAX_CACHE_SIZE) return kmalloc_large(size, flags); #ifndef CONFIG_SLOB - if (!(flags & GFP_DMA)) { - unsigned int index = kmalloc_index(size); + index = kmalloc_index(size); - if (!index) - return ZERO_SIZE_PTR; + if (!index) + return ZERO_SIZE_PTR; - return kmem_cache_alloc_trace(kmalloc_caches[index], - flags, size); - } + return kmem_cache_alloc_trace( + kmalloc_caches[kmalloc_type(flags)][index], + flags, size); #endif } return __kmalloc(size, flags); @@ -542,13 +561,14 @@ static __always_inline void *kmalloc_node(size_t size, gfp_t flags, int node) { #ifndef CONFIG_SLOB if (__builtin_constant_p(size) && - size <= KMALLOC_MAX_CACHE_SIZE && !(flags & GFP_DMA)) { + size <= KMALLOC_MAX_CACHE_SIZE) { unsigned int i = kmalloc_index(size); if (!i) return ZERO_SIZE_PTR; - return kmem_cache_alloc_node_trace(kmalloc_caches[i], + return kmem_cache_alloc_node_trace( + kmalloc_caches[kmalloc_type(flags)][i], flags, node, size); } #endif diff --git a/mm/slab.c b/mm/slab.c index d73c7a4820a4..2a5654bb3b3f 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -1288,7 +1288,7 @@ void __init kmem_cache_init(void) * Initialize the caches that provide memory for the kmem_cache_node * structures first. Without this, further allocations will bug. */ - kmalloc_caches[INDEX_NODE] = create_kmalloc_cache( + kmalloc_caches[KMALLOC_NORMAL][INDEX_NODE] = create_kmalloc_cache( kmalloc_info[INDEX_NODE].name, kmalloc_size(INDEX_NODE), ARCH_KMALLOC_FLAGS, 0, kmalloc_size(INDEX_NODE)); @@ -1304,7 +1304,7 @@ void __init kmem_cache_init(void) for_each_online_node(nid) { init_list(kmem_cache, &init_kmem_cache_node[CACHE_CACHE + nid], nid); - init_list(kmalloc_caches[INDEX_NODE], + init_list(kmalloc_caches[KMALLOC_NORMAL][INDEX_NODE], &init_kmem_cache_node[SIZE_NODE + nid], nid); } } diff --git a/mm/slab_common.c b/mm/slab_common.c index 3a7ac4f15194..d880b2a3c81b 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -973,14 +973,10 @@ struct kmem_cache *__init create_kmalloc_cache(const char *name, return s; } -struct kmem_cache *kmalloc_caches[KMALLOC_SHIFT_HIGH + 1] __ro_after_init; +struct kmem_cache * +kmalloc_caches[NR_KMALLOC_TYPES][KMALLOC_SHIFT_HIGH + 1] __ro_after_init; EXPORT_SYMBOL(kmalloc_caches); -#ifdef CONFIG_ZONE_DMA -struct kmem_cache *kmalloc_dma_caches[KMALLOC_SHIFT_HIGH + 1] __ro_after_init; -EXPORT_SYMBOL(kmalloc_dma_caches); -#endif - /* * Conversion table for small slabs sizes / 8 to the index in the * kmalloc array. This is necessary for slabs < 192 since we have non power @@ -1040,12 +1036,7 @@ struct kmem_cache *kmalloc_slab(size_t size, gfp_t flags) index = fls(size - 1); } -#ifdef CONFIG_ZONE_DMA - if (unlikely((flags & GFP_DMA))) - return kmalloc_dma_caches[index]; - -#endif - return kmalloc_caches[index]; + return kmalloc_caches[kmalloc_type(flags)][index]; } /* @@ -1119,7 +1110,8 @@ void __init setup_kmalloc_cache_index_table(void) static void __init new_kmalloc_cache(int idx, slab_flags_t flags) { - kmalloc_caches[idx] = create_kmalloc_cache(kmalloc_info[idx].name, + kmalloc_caches[KMALLOC_NORMAL][idx] = create_kmalloc_cache( + kmalloc_info[idx].name, kmalloc_info[idx].size, flags, 0, kmalloc_info[idx].size); } @@ -1132,9 +1124,10 @@ static void __init new_kmalloc_cache(int idx, slab_flags_t flags) void __init create_kmalloc_caches(slab_flags_t flags) { int i; + int type = KMALLOC_NORMAL; for (i = KMALLOC_SHIFT_LOW; i <= KMALLOC_SHIFT_HIGH; i++) { - if (!kmalloc_caches[i]) + if (!kmalloc_caches[type][i]) new_kmalloc_cache(i, flags); /* @@ -1142,9 +1135,9 @@ void __init create_kmalloc_caches(slab_flags_t flags) * These have to be created immediately after the * earlier power of two caches */ - if (KMALLOC_MIN_SIZE <= 32 && !kmalloc_caches[1] && i == 6) + if (KMALLOC_MIN_SIZE <= 32 && !kmalloc_caches[type][1] && i == 6) new_kmalloc_cache(1, flags); - if (KMALLOC_MIN_SIZE <= 64 && !kmalloc_caches[2] && i == 7) + if (KMALLOC_MIN_SIZE <= 64 && !kmalloc_caches[type][2] && i == 7) new_kmalloc_cache(2, flags); } @@ -1153,7 +1146,7 @@ void __init create_kmalloc_caches(slab_flags_t flags) #ifdef CONFIG_ZONE_DMA for (i = 0; i <= KMALLOC_SHIFT_HIGH; i++) { - struct kmem_cache *s = kmalloc_caches[i]; + struct kmem_cache *s = kmalloc_caches[KMALLOC_NORMAL][i]; if (s) { unsigned int size = kmalloc_size(i); @@ -1161,8 +1154,8 @@ void __init create_kmalloc_caches(slab_flags_t flags) "dma-kmalloc-%u", size); BUG_ON(!n); - kmalloc_dma_caches[i] = create_kmalloc_cache(n, - size, SLAB_CACHE_DMA | flags, 0, 0); + kmalloc_caches[KMALLOC_DMA][i] = create_kmalloc_cache( + n, size, SLAB_CACHE_DMA | flags, 0, 0); } } #endif diff --git a/mm/slub.c b/mm/slub.c index 18bd07daf4e4..e3629cd7aff1 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -4689,6 +4689,7 @@ static int list_locations(struct kmem_cache *s, char *buf, static void __init resiliency_test(void) { u8 *p; + int type = KMALLOC_NORMAL; BUILD_BUG_ON(KMALLOC_MIN_SIZE > 16 || KMALLOC_SHIFT_HIGH < 10); @@ -4701,7 +4702,7 @@ static void __init resiliency_test(void) pr_err("\n1. kmalloc-16: Clobber Redzone/next pointer 0x12->0x%p\n\n", p + 16); - validate_slab_cache(kmalloc_caches[4]); + validate_slab_cache(kmalloc_caches[type][4]); /* Hmmm... The next two are dangerous */ p = kzalloc(32, GFP_KERNEL); @@ -4710,33 +4711,33 @@ static void __init resiliency_test(void) p); pr_err("If allocated object is overwritten then not detectable\n\n"); - validate_slab_cache(kmalloc_caches[5]); + validate_slab_cache(kmalloc_caches[type][5]); p = kzalloc(64, GFP_KERNEL); p += 64 + (get_cycles() & 0xff) * sizeof(void *); *p = 0x56; pr_err("\n3. kmalloc-64: corrupting random byte 0x56->0x%p\n", p); pr_err("If allocated object is overwritten then not detectable\n\n"); - validate_slab_cache(kmalloc_caches[6]); + validate_slab_cache(kmalloc_caches[type][6]); pr_err("\nB. Corruption after free\n"); p = kzalloc(128, GFP_KERNEL); kfree(p); *p = 0x78; pr_err("1. kmalloc-128: Clobber first word 0x78->0x%p\n\n", p); - validate_slab_cache(kmalloc_caches[7]); + validate_slab_cache(kmalloc_caches[type][7]); p = kzalloc(256, GFP_KERNEL); kfree(p); p[50] = 0x9a; pr_err("\n2. kmalloc-256: Clobber 50th byte 0x9a->0x%p\n\n", p); - validate_slab_cache(kmalloc_caches[8]); + validate_slab_cache(kmalloc_caches[type][8]); p = kzalloc(512, GFP_KERNEL); kfree(p); p[512] = 0xab; pr_err("\n3. kmalloc-512: Clobber redzone 0xab->0x%p\n\n", p); - validate_slab_cache(kmalloc_caches[9]); + validate_slab_cache(kmalloc_caches[type][9]); } #else #ifdef CONFIG_SYSFS -- cgit v1.2.3 From 1291523f2c1d631fea34102fd241fb54a4e8f7a0 Mon Sep 17 00:00:00 2001 From: Vlastimil Babka Date: Fri, 26 Oct 2018 15:05:38 -0700 Subject: mm, slab/slub: introduce kmalloc-reclaimable caches Kmem caches can be created with a SLAB_RECLAIM_ACCOUNT flag, which indicates they contain objects which can be reclaimed under memory pressure (typically through a shrinker). This makes the slab pages accounted as NR_SLAB_RECLAIMABLE in vmstat, which is reflected also the MemAvailable meminfo counter and in overcommit decisions. The slab pages are also allocated with __GFP_RECLAIMABLE, which is good for anti-fragmentation through grouping pages by mobility. The generic kmalloc-X caches are created without this flag, but sometimes are used also for objects that can be reclaimed, which due to varying size cannot have a dedicated kmem cache with SLAB_RECLAIM_ACCOUNT flag. A prominent example are dcache external names, which prompted the creation of a new, manually managed vmstat counter NR_INDIRECTLY_RECLAIMABLE_BYTES in commit f1782c9bc547 ("dcache: account external names as indirectly reclaimable memory"). To better handle this and any other similar cases, this patch introduces SLAB_RECLAIM_ACCOUNT variants of kmalloc caches, named kmalloc-rcl-X. They are used whenever the kmalloc() call passes __GFP_RECLAIMABLE among gfp flags. They are added to the kmalloc_caches array as a new type. Allocations with both __GFP_DMA and __GFP_RECLAIMABLE will use a dma type cache. This change only applies to SLAB and SLUB, not SLOB. This is fine, since SLOB's target are tiny system and this patch does add some overhead of kmem management objects. Link: http://lkml.kernel.org/r/20180731090649.16028-3-vbabka@suse.cz Signed-off-by: Vlastimil Babka Acked-by: Mel Gorman Acked-by: Christoph Lameter Acked-by: Roman Gushchin Cc: David Rientjes Cc: Johannes Weiner Cc: Joonsoo Kim Cc: Laura Abbott Cc: Matthew Wilcox Cc: Michal Hocko Cc: Sumit Semwal Cc: Vijayanand Jitta Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/slab.h | 16 +++++++++++++++- mm/slab_common.c | 48 +++++++++++++++++++++++++++++++----------------- 2 files changed, 46 insertions(+), 18 deletions(-) (limited to 'mm') diff --git a/include/linux/slab.h b/include/linux/slab.h index 2a7137043e91..918f374e7156 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -295,8 +295,13 @@ static inline void __check_heap_object(const void *ptr, unsigned long n, #define SLAB_OBJ_MIN_SIZE (KMALLOC_MIN_SIZE < 16 ? \ (KMALLOC_MIN_SIZE) : 16) +/* + * Whenever changing this, take care of that kmalloc_type() and + * create_kmalloc_caches() still work as intended. + */ enum kmalloc_cache_type { KMALLOC_NORMAL = 0, + KMALLOC_RECLAIM, #ifdef CONFIG_ZONE_DMA KMALLOC_DMA, #endif @@ -310,12 +315,21 @@ kmalloc_caches[NR_KMALLOC_TYPES][KMALLOC_SHIFT_HIGH + 1]; static __always_inline enum kmalloc_cache_type kmalloc_type(gfp_t flags) { int is_dma = 0; + int type_dma = 0; + int is_reclaimable; #ifdef CONFIG_ZONE_DMA is_dma = !!(flags & __GFP_DMA); + type_dma = is_dma * KMALLOC_DMA; #endif - return is_dma; + is_reclaimable = !!(flags & __GFP_RECLAIMABLE); + + /* + * If an allocation is both __GFP_DMA and __GFP_RECLAIMABLE, return + * KMALLOC_DMA and effectively ignore __GFP_RECLAIMABLE + */ + return type_dma + (is_reclaimable & !is_dma) * KMALLOC_RECLAIM; } /* diff --git a/mm/slab_common.c b/mm/slab_common.c index d880b2a3c81b..5b19439fd862 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -1108,10 +1108,21 @@ void __init setup_kmalloc_cache_index_table(void) } } -static void __init new_kmalloc_cache(int idx, slab_flags_t flags) +static void __init +new_kmalloc_cache(int idx, int type, slab_flags_t flags) { - kmalloc_caches[KMALLOC_NORMAL][idx] = create_kmalloc_cache( - kmalloc_info[idx].name, + const char *name; + + if (type == KMALLOC_RECLAIM) { + flags |= SLAB_RECLAIM_ACCOUNT; + name = kasprintf(GFP_NOWAIT, "kmalloc-rcl-%u", + kmalloc_info[idx].size); + BUG_ON(!name); + } else { + name = kmalloc_info[idx].name; + } + + kmalloc_caches[type][idx] = create_kmalloc_cache(name, kmalloc_info[idx].size, flags, 0, kmalloc_info[idx].size); } @@ -1123,22 +1134,25 @@ static void __init new_kmalloc_cache(int idx, slab_flags_t flags) */ void __init create_kmalloc_caches(slab_flags_t flags) { - int i; - int type = KMALLOC_NORMAL; + int i, type; - for (i = KMALLOC_SHIFT_LOW; i <= KMALLOC_SHIFT_HIGH; i++) { - if (!kmalloc_caches[type][i]) - new_kmalloc_cache(i, flags); + for (type = KMALLOC_NORMAL; type <= KMALLOC_RECLAIM; type++) { + for (i = KMALLOC_SHIFT_LOW; i <= KMALLOC_SHIFT_HIGH; i++) { + if (!kmalloc_caches[type][i]) + new_kmalloc_cache(i, type, flags); - /* - * Caches that are not of the two-to-the-power-of size. - * These have to be created immediately after the - * earlier power of two caches - */ - if (KMALLOC_MIN_SIZE <= 32 && !kmalloc_caches[type][1] && i == 6) - new_kmalloc_cache(1, flags); - if (KMALLOC_MIN_SIZE <= 64 && !kmalloc_caches[type][2] && i == 7) - new_kmalloc_cache(2, flags); + /* + * Caches that are not of the two-to-the-power-of size. + * These have to be created immediately after the + * earlier power of two caches + */ + if (KMALLOC_MIN_SIZE <= 32 && i == 6 && + !kmalloc_caches[type][1]) + new_kmalloc_cache(1, type, flags); + if (KMALLOC_MIN_SIZE <= 64 && i == 7 && + !kmalloc_caches[type][2]) + new_kmalloc_cache(2, type, flags); + } } /* Kmalloc array is now usable */ -- cgit v1.2.3 From b29940c1abd7a4c3abeb926df0a5ec84d6902d47 Mon Sep 17 00:00:00 2001 From: Vlastimil Babka Date: Fri, 26 Oct 2018 15:05:46 -0700 Subject: mm: rename and change semantics of nr_indirectly_reclaimable_bytes The vmstat counter NR_INDIRECTLY_RECLAIMABLE_BYTES was introduced by commit eb59254608bc ("mm: introduce NR_INDIRECTLY_RECLAIMABLE_BYTES") with the goal of accounting objects that can be reclaimed, but cannot be allocated via a SLAB_RECLAIM_ACCOUNT cache. This is now possible via kmalloc() with __GFP_RECLAIMABLE flag, and the dcache external names user is converted. The counter is however still useful for accounting direct page allocations (i.e. not slab) with a shrinker, such as the ION page pool. So keep it, and: - change granularity to pages to be more like other counters; sub-page allocations should be able to use kmalloc - rename the counter to NR_KERNEL_MISC_RECLAIMABLE - expose the counter again in vmstat as "nr_kernel_misc_reclaimable"; we can again remove the check for not printing "hidden" counters Link: http://lkml.kernel.org/r/20180731090649.16028-5-vbabka@suse.cz Signed-off-by: Vlastimil Babka Acked-by: Christoph Lameter Acked-by: Roman Gushchin Cc: Vijayanand Jitta Cc: Laura Abbott Cc: Sumit Semwal Cc: David Rientjes Cc: Johannes Weiner Cc: Joonsoo Kim Cc: Matthew Wilcox Cc: Mel Gorman Cc: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/staging/android/ion/ion_page_pool.c | 8 ++++---- include/linux/mmzone.h | 2 +- mm/page_alloc.c | 19 +++++++------------ mm/util.c | 3 +-- mm/vmstat.c | 6 +----- 5 files changed, 14 insertions(+), 24 deletions(-) (limited to 'mm') diff --git a/drivers/staging/android/ion/ion_page_pool.c b/drivers/staging/android/ion/ion_page_pool.c index 9bc56eb48d2a..0d2a95957ee8 100644 --- a/drivers/staging/android/ion/ion_page_pool.c +++ b/drivers/staging/android/ion/ion_page_pool.c @@ -33,8 +33,8 @@ static void ion_page_pool_add(struct ion_page_pool *pool, struct page *page) pool->low_count++; } - mod_node_page_state(page_pgdat(page), NR_INDIRECTLY_RECLAIMABLE_BYTES, - (1 << (PAGE_SHIFT + pool->order))); + mod_node_page_state(page_pgdat(page), NR_KERNEL_MISC_RECLAIMABLE, + 1 << pool->order); mutex_unlock(&pool->mutex); } @@ -53,8 +53,8 @@ static struct page *ion_page_pool_remove(struct ion_page_pool *pool, bool high) } list_del(&page->lru); - mod_node_page_state(page_pgdat(page), NR_INDIRECTLY_RECLAIMABLE_BYTES, - -(1 << (PAGE_SHIFT + pool->order))); + mod_node_page_state(page_pgdat(page), NR_KERNEL_MISC_RECLAIMABLE, + -(1 << pool->order)); return page; } diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index d4b0c79d2924..7bbeba21f6a3 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -180,7 +180,7 @@ enum node_stat_item { NR_VMSCAN_IMMEDIATE, /* Prioritise for reclaim when writeback ends */ NR_DIRTIED, /* page dirtyings since bootup */ NR_WRITTEN, /* page writings since bootup */ - NR_INDIRECTLY_RECLAIMABLE_BYTES, /* measured in bytes */ + NR_KERNEL_MISC_RECLAIMABLE, /* reclaimable non-slab kernel pages */ NR_VM_NODE_STAT_ITEMS }; diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 747031c2352d..20f25d06c00c 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -4701,6 +4701,7 @@ long si_mem_available(void) unsigned long pagecache; unsigned long wmark_low = 0; unsigned long pages[NR_LRU_LISTS]; + unsigned long reclaimable; struct zone *zone; int lru; @@ -4726,19 +4727,13 @@ long si_mem_available(void) available += pagecache; /* - * Part of the reclaimable slab consists of items that are in use, - * and cannot be freed. Cap this estimate at the low watermark. + * Part of the reclaimable slab and other kernel memory consists of + * items that are in use, and cannot be freed. Cap this estimate at the + * low watermark. */ - available += global_node_page_state(NR_SLAB_RECLAIMABLE) - - min(global_node_page_state(NR_SLAB_RECLAIMABLE) / 2, - wmark_low); - - /* - * Part of the kernel memory, which can be released under memory - * pressure. - */ - available += global_node_page_state(NR_INDIRECTLY_RECLAIMABLE_BYTES) >> - PAGE_SHIFT; + reclaimable = global_node_page_state(NR_SLAB_RECLAIMABLE) + + global_node_page_state(NR_KERNEL_MISC_RECLAIMABLE); + available += reclaimable - min(reclaimable / 2, wmark_low); if (available < 0) available = 0; diff --git a/mm/util.c b/mm/util.c index 470f5cd80b64..f740754f5012 100644 --- a/mm/util.c +++ b/mm/util.c @@ -678,8 +678,7 @@ int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin) * Part of the kernel memory, which can be released * under memory pressure. */ - free += global_node_page_state( - NR_INDIRECTLY_RECLAIMABLE_BYTES) >> PAGE_SHIFT; + free += global_node_page_state(NR_KERNEL_MISC_RECLAIMABLE); /* * Leave reserved pages. The pages are not for anonymous pages. diff --git a/mm/vmstat.c b/mm/vmstat.c index 7878da76abf2..2cec2fa4c8ae 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -1161,7 +1161,7 @@ const char * const vmstat_text[] = { "nr_vmscan_immediate_reclaim", "nr_dirtied", "nr_written", - "", /* nr_indirectly_reclaimable */ + "nr_kernel_misc_reclaimable", /* enum writeback_stat_item counters */ "nr_dirty_threshold", @@ -1706,10 +1706,6 @@ static int vmstat_show(struct seq_file *m, void *arg) unsigned long *l = arg; unsigned long off = l - (unsigned long *)m->private; - /* Skip hidden vmstat items. */ - if (*vmstat_text[off] == '\0') - return 0; - seq_puts(m, vmstat_text[off]); seq_put_decimal_ull(m, " ", *l); seq_putc(m, '\n'); -- cgit v1.2.3 From f0d77874143df90f9831f30254eb149fc4d76b40 Mon Sep 17 00:00:00 2001 From: Vlastimil Babka Date: Fri, 26 Oct 2018 15:05:55 -0700 Subject: mm, slab: shorten kmalloc cache names for large sizes Kmalloc cache names can get quite long for large object sizes, when the sizes are expressed in bytes. Use 'k' and 'M' prefixes to make the names as short as possible e.g. in /proc/slabinfo. This works, as we mostly use power-of-two sizes, with exceptions only below 1k. Example: 'kmalloc-4194304' becomes 'kmalloc-4M' Link: http://lkml.kernel.org/r/20180731090649.16028-7-vbabka@suse.cz Suggested-by: Matthew Wilcox Signed-off-by: Vlastimil Babka Acked-by: Mel Gorman Acked-by: Christoph Lameter Acked-by: Roman Gushchin Cc: David Rientjes Cc: Johannes Weiner Cc: Joonsoo Kim Cc: Laura Abbott Cc: Michal Hocko Cc: Sumit Semwal Cc: Vijayanand Jitta Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/slab_common.c | 38 ++++++++++++++++++++++++++------------ 1 file changed, 26 insertions(+), 12 deletions(-) (limited to 'mm') diff --git a/mm/slab_common.c b/mm/slab_common.c index 5b19439fd862..7eb8dc136c1c 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -1050,15 +1050,15 @@ const struct kmalloc_info_struct kmalloc_info[] __initconst = { {"kmalloc-16", 16}, {"kmalloc-32", 32}, {"kmalloc-64", 64}, {"kmalloc-128", 128}, {"kmalloc-256", 256}, {"kmalloc-512", 512}, - {"kmalloc-1024", 1024}, {"kmalloc-2048", 2048}, - {"kmalloc-4096", 4096}, {"kmalloc-8192", 8192}, - {"kmalloc-16384", 16384}, {"kmalloc-32768", 32768}, - {"kmalloc-65536", 65536}, {"kmalloc-131072", 131072}, - {"kmalloc-262144", 262144}, {"kmalloc-524288", 524288}, - {"kmalloc-1048576", 1048576}, {"kmalloc-2097152", 2097152}, - {"kmalloc-4194304", 4194304}, {"kmalloc-8388608", 8388608}, - {"kmalloc-16777216", 16777216}, {"kmalloc-33554432", 33554432}, - {"kmalloc-67108864", 67108864} + {"kmalloc-1k", 1024}, {"kmalloc-2k", 2048}, + {"kmalloc-4k", 4096}, {"kmalloc-8k", 8192}, + {"kmalloc-16k", 16384}, {"kmalloc-32k", 32768}, + {"kmalloc-64k", 65536}, {"kmalloc-128k", 131072}, + {"kmalloc-256k", 262144}, {"kmalloc-512k", 524288}, + {"kmalloc-1M", 1048576}, {"kmalloc-2M", 2097152}, + {"kmalloc-4M", 4194304}, {"kmalloc-8M", 8388608}, + {"kmalloc-16M", 16777216}, {"kmalloc-32M", 33554432}, + {"kmalloc-64M", 67108864} }; /* @@ -1108,6 +1108,21 @@ void __init setup_kmalloc_cache_index_table(void) } } +static const char * +kmalloc_cache_name(const char *prefix, unsigned int size) +{ + + static const char units[3] = "\0kM"; + int idx = 0; + + while (size >= 1024 && (size % 1024 == 0)) { + size /= 1024; + idx++; + } + + return kasprintf(GFP_NOWAIT, "%s-%u%c", prefix, size, units[idx]); +} + static void __init new_kmalloc_cache(int idx, int type, slab_flags_t flags) { @@ -1115,7 +1130,7 @@ new_kmalloc_cache(int idx, int type, slab_flags_t flags) if (type == KMALLOC_RECLAIM) { flags |= SLAB_RECLAIM_ACCOUNT; - name = kasprintf(GFP_NOWAIT, "kmalloc-rcl-%u", + name = kmalloc_cache_name("kmalloc-rcl", kmalloc_info[idx].size); BUG_ON(!name); } else { @@ -1164,8 +1179,7 @@ void __init create_kmalloc_caches(slab_flags_t flags) if (s) { unsigned int size = kmalloc_size(i); - char *n = kasprintf(GFP_NOWAIT, - "dma-kmalloc-%u", size); + const char *n = kmalloc_cache_name("dma-kmalloc", size); BUG_ON(!n); kmalloc_caches[KMALLOC_DMA][i] = create_kmalloc_cache( -- cgit v1.2.3 From 95f9ab2d596e8cbb388315e78c82b9a131bf2928 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Fri, 26 Oct 2018 15:05:59 -0700 Subject: mm: workingset: don't drop refault information prematurely Patch series "psi: pressure stall information for CPU, memory, and IO", v4. Overview PSI reports the overall wallclock time in which the tasks in a system (or cgroup) wait for (contended) hardware resources. This helps users understand the resource pressure their workloads are under, which allows them to rootcause and fix throughput and latency problems caused by overcommitting, underprovisioning, suboptimal job placement in a grid; as well as anticipate major disruptions like OOM. Real-world applications We're using the data collected by PSI (and its previous incarnation, memdelay) quite extensively at Facebook, and with several success stories. One usecase is avoiding OOM hangs/livelocks. The reason these happen is because the OOM killer is triggered by reclaim not being able to free pages, but with fast flash devices there is *always* some clean and uptodate cache to reclaim; the OOM killer never kicks in, even as tasks spend 90% of the time thrashing the cache pages of their own executables. There is no situation where this ever makes sense in practice. We wrote a <100 line POC python script to monitor memory pressure and kill stuff way before such pathological thrashing leads to full system losses that would require forcible hard resets. We've since extended and deployed this code into other places to guarantee latency and throughput SLAs, since they're usually violated way before the kernel OOM killer would ever kick in. It is available here: https://github.com/facebookincubator/oomd Eventually we probably want to trigger the in-kernel OOM killer based on extreme sustained pressure as well, so that Linux can avoid memory livelocks - which technically aren't deadlocks, but to the user indistinguishable from them - out of the box. We'd continue using OOMD as the first line of defense to ensure workload health and implement complex kill policies that are beyond the scope of the kernel. We also use PSI memory pressure for loadshedding. Our batch job infrastructure used to use heuristics based on various VM stats to anticipate OOM situations, with lackluster success. We switched it to PSI and managed to anticipate and avoid OOM kills and lockups fairly reliably. The reduction of OOM outages in the worker pool raised the pool's aggregate productivity, and we were able to switch that service to smaller machines. Lastly, we use cgroups to isolate a machine's main workload from maintenance crap like package upgrades, logging, configuration, as well as to prevent multiple workloads on a machine from stepping on each others' toes. We were not able to configure this properly without the pressure metrics; we would see latency or bandwidth drops, but it would often be hard to impossible to rootcause it post-mortem. We now log and graph pressure for the containers in our fleet and can trivially link latency spikes and throughput drops to shortages of specific resources after the fact, and fix the job config/scheduling. PSI has also received testing, feedback, and feature requests from Android and EndlessOS for the purpose of low-latency OOM killing, to intervene in pressure situations before the UI starts hanging. How do you use this feature? A kernel with CONFIG_PSI=y will create a /proc/pressure directory with 3 files: cpu, memory, and io. If using cgroup2, cgroups will also have cpu.pressure, memory.pressure and io.pressure files, which simply aggregate task stalls at the cgroup level instead of system-wide. The cpu file contains one line: some avg10=2.04 avg60=0.75 avg300=0.40 total=157656722 The averages give the percentage of walltime in which one or more tasks are delayed on the runqueue while another task has the CPU. They're recent averages over 10s, 1m, 5m windows, so you can tell short term trends from long term ones, similarly to the load average. The total= value gives the absolute stall time in microseconds. This allows detecting latency spikes that might be too short to sway the running averages. It also allows custom time averaging in case the 10s/1m/5m windows aren't adequate for the usecase (or are too coarse with future hardware). What to make of this "some" metric? If CPU utilization is at 100% and CPU pressure is 0, it means the system is perfectly utilized, with one runnable thread per CPU and nobody waiting. At two or more runnable tasks per CPU, the system is 100% overcommitted and the pressure average will indicate as much. From a utilization perspective this is a great state of course: no CPU cycles are being wasted, even when 50% of the threads were to go idle (as most workloads do vary). From the perspective of the individual job it's not great, however, and they would do better with more resources. Depending on what your priority and options are, raised "some" numbers may or may not require action. The memory file contains two lines: some avg10=70.24 avg60=68.52 avg300=69.91 total=3559632828 full avg10=57.59 avg60=58.06 avg300=60.38 total=3300487258 The some line is the same as for cpu, the time in which at least one task is stalled on the resource. In the case of memory, this includes waiting on swap-in, page cache refaults and page reclaim. The full line, however, indicates time in which *nobody* is using the CPU productively due to pressure: all non-idle tasks are waiting for memory in one form or another. Significant time spent in there is a good trigger for killing things, moving jobs to other machines, or dropping incoming requests, since neither the jobs nor the machine overall are making too much headway. The io file is similar to memory. Because the block layer doesn't have a concept of hardware contention right now (how much longer is my IO request taking due to other tasks?), it reports CPU potential lost on all IO delays, not just the potential lost due to competition. FAQ Q: How is PSI's CPU component different from the load average? A: There are several quirks in the load average that make it hard to impossible to tell how overcommitted the CPU really is. 1. The load average is reported as a raw number of active tasks. You need to know how many CPUs there are in the system, how many CPUs the workload is allowed to use, then think about what the proportion between load and the number of CPUs mean for the tasks trying to run. PSI reports the percentage of wallclock time in which tasks are waiting for a CPU to run on. It doesn't matter how many CPUs are present or usable. The number always tells the quality of life of tasks in the system or in a particular cgroup. 2. The shortest averaging window is 1m, which is extremely coarse, and it's sampled in 5s intervals. A *lot* can happen on a CPU in 5 seconds. This *may* be able to identify persistent long-term trends and very clear and obvious overloads, but it's unusable for latency spikes and more subtle overutilization. PSI's shortest window is 10s. It also exports the cumulative stall times (in microseconds) of synchronously recorded events. 3. On Linux, the load average for historical reasons includes all TASK_UNINTERRUPTIBLE tasks. This gives a broader sense of how busy the system is, but on the flipside it doesn't distinguish whether tasks are likely to contend over the CPU or IO - which obviously requires very different interventions from a sys admin or a job scheduler. PSI reports independent metrics for CPU and IO. You can tell which resource is making the tasks wait, but in conjunction still see how overloaded the system is overall. Q: What's the cost / performance impact of this feature? A: PSI's primary cost is in the scheduler, in particular task wakeups and sleeps. I benchmarked this code using Facebook's two most scheduling sensitive workloads: memcache and webserver. They handle a ton of small requests - lots of wakeups and sleeps with little actual work in between - so they tend to be canaries for scheduler regressions. In the tests, the boxes were handling live traffic over the course of several hours. Half the machines, the control, ran with CONFIG_PSI=n. For memcache I used eight machines total. They're 2-socket, 14 core, 56 thread boxes. The test runs for half the test period, flips the test and control kernels on the hardware to rule out HW factors, DC location etc., then runs the other half of the test. For the webservers, I used 32 machines total. They're single socket, 16 core, 32 thread machines. During the memcache test, CPU load was nopsi=78.05% psi=78.98% in the first half and nopsi=77.52% psi=78.25%, so PSI added between 0.7 and 0.9 percentage points to the CPU load, a difference of about 1%. UPDATE: I re-ran this test with the v3 version of this patch set and the CPU utilization was equivalent between test and control. UPDATE: v4 is on par with v3. As far as end-to-end request latency from the client perspective goes, we don't sample those finely enough to capture the requests going to those particular machines during the test, but we know the p50 turnaround time in this workload is 54us, and perf bench sched pipe on those machines show nopsi=5.232666 us/op and psi=5.587347 us/op, so this doesn't add much here either. The profile for the pipe benchmark shows: 0.87% sched-pipe [kernel.vmlinux] [k] psi_group_change 0.83% perf.real [kernel.vmlinux] [k] psi_group_change 0.82% perf.real [kernel.vmlinux] [k] psi_task_change 0.58% sched-pipe [kernel.vmlinux] [k] psi_task_change The webserver load is running inside 4 nested cgroup levels. The CPU load with both nopsi and psi kernels was indistinguishable at 81%. For comparison, we had to disable the cgroup cpu controller on the webservers because it added 4 percentage points to the CPU% during this same exact test. Versions of this accounting code now run on 80% of our fleet. None of our workloads have reported regressions during the rollout. Daniel Drake said: : I just retested the latest version at : http://git.cmpxchg.org/cgit.cgi/linux-psi.git (Linux 4.18) and the results : are great. : : Test setup: : Endless OS : GeminiLake N4200 low end laptop : 2GB RAM : swap (and zram swap) disabled : : Baseline test: open a handful of large-ish apps and several website : tabs in Google Chrome. : : Results: after a couple of minutes, system is excessively thrashing, mouse : cursor can barely be moved, UI is not responding to mouse clicks, so it's : impractical to recover from this situation as an ordinary user : : Add my simple killer: : https://gist.github.com/dsd/a8988bf0b81a6163475988120fe8d9cd : : Results: when the thrashing causes the UI to become sluggish, the killer : steps in and kills something (usually a chrome tab), and the system : remains usable. I repeatedly opened more apps and more websites over a 15 : minute period but I wasn't able to get the system to a point of UI : unresponsiveness. Suren said: : Backported to 4.9 and retested on ARMv8 8 code system running Android. : Signals behave as expected reacting to memory pressure, no jumps in : "total" counters that would indicate an overflow/underflow issues. Nicely : done! This patch (of 9): If we keep just enough refault information to match the *current* page cache during reclaim time, we could lose a lot of events when there is only a temporary spike in non-cache memory consumption that pushes out all the cache. Once cache comes back, we won't see those refaults. They might not be actionable for LRU aging, but we want to know about them for measuring memory pressure. [hannes@cmpxchg.org: switch to NUMA-aware lru and slab counters] Link: http://lkml.kernel.org/r/20181009184732.762-2-hannes@cmpxchg.org Link: http://lkml.kernel.org/r/20180828172258.3185-2-hannes@cmpxchg.org Signed-off-by: Johannes Weiner Acked-by: Peter Zijlstra (Intel) Reviewed-by: Rik van Riel Tested-by: Daniel Drake Tested-by: Suren Baghdasaryan Cc: Ingo Molnar Cc: Tejun Heo Cc: Vinayak Menon Cc: Christopher Lameter Cc: Peter Enderborg Cc: Shakeel Butt Cc: Mike Galbraith Cc: Randy Dunlap Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/workingset.c | 22 ++++++++++++++-------- 1 file changed, 14 insertions(+), 8 deletions(-) (limited to 'mm') diff --git a/mm/workingset.c b/mm/workingset.c index 4516dd790129..7d5fa0dd2b38 100644 --- a/mm/workingset.c +++ b/mm/workingset.c @@ -364,7 +364,7 @@ static unsigned long count_shadow_nodes(struct shrinker *shrinker, { unsigned long max_nodes; unsigned long nodes; - unsigned long cache; + unsigned long pages; nodes = list_lru_shrink_count(&shadow_nodes, sc); @@ -390,14 +390,20 @@ static unsigned long count_shadow_nodes(struct shrinker *shrinker, * * PAGE_SIZE / radix_tree_nodes / node_entries * 8 / PAGE_SIZE */ +#ifdef CONFIG_MEMCG if (sc->memcg) { - cache = mem_cgroup_node_nr_lru_pages(sc->memcg, sc->nid, - LRU_ALL_FILE); - } else { - cache = node_page_state(NODE_DATA(sc->nid), NR_ACTIVE_FILE) + - node_page_state(NODE_DATA(sc->nid), NR_INACTIVE_FILE); - } - max_nodes = cache >> (RADIX_TREE_MAP_SHIFT - 3); + struct lruvec *lruvec; + + pages = mem_cgroup_node_nr_lru_pages(sc->memcg, sc->nid, + LRU_ALL); + lruvec = mem_cgroup_lruvec(NODE_DATA(sc->nid), sc->memcg); + pages += lruvec_page_state(lruvec, NR_SLAB_RECLAIMABLE); + pages += lruvec_page_state(lruvec, NR_SLAB_UNRECLAIMABLE); + } else +#endif + pages = node_present_pages(sc->nid); + + max_nodes = pages >> (RADIX_TREE_MAP_SHIFT - 3); if (!nodes) return SHRINK_EMPTY; -- cgit v1.2.3 From 1899ad18c6072d689896badafb81267b0a1092a4 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Fri, 26 Oct 2018 15:06:04 -0700 Subject: mm: workingset: tell cache transitions from workingset thrashing Refaults happen during transitions between workingsets as well as in-place thrashing. Knowing the difference between the two has a range of applications, including measuring the impact of memory shortage on the system performance, as well as the ability to smarter balance pressure between the filesystem cache and the swap-backed workingset. During workingset transitions, inactive cache refaults and pushes out established active cache. When that active cache isn't stale, however, and also ends up refaulting, that's bonafide thrashing. Introduce a new page flag that tells on eviction whether the page has been active or not in its lifetime. This bit is then stored in the shadow entry, to classify refaults as transitioning or thrashing. How many page->flags does this leave us with on 32-bit? 20 bits are always page flags 21 if you have an MMU 23 with the zone bits for DMA, Normal, HighMem, Movable 29 with the sparsemem section bits 30 if PAE is enabled 31 with this patch. So on 32-bit PAE, that leaves 1 bit for distinguishing two NUMA nodes. If that's not enough, the system can switch to discontigmem and re-gain the 6 or 7 sparsemem section bits. Link: http://lkml.kernel.org/r/20180828172258.3185-3-hannes@cmpxchg.org Signed-off-by: Johannes Weiner Acked-by: Peter Zijlstra (Intel) Tested-by: Daniel Drake Tested-by: Suren Baghdasaryan Cc: Christopher Lameter Cc: Ingo Molnar Cc: Johannes Weiner Cc: Mike Galbraith Cc: Peter Enderborg Cc: Randy Dunlap Cc: Shakeel Butt Cc: Tejun Heo Cc: Vinayak Menon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 1 + include/linux/page-flags.h | 5 ++- include/linux/swap.h | 2 +- include/trace/events/mmflags.h | 1 + mm/filemap.c | 9 ++-- mm/huge_memory.c | 1 + mm/migrate.c | 2 + mm/swap_state.c | 1 + mm/vmscan.c | 1 + mm/vmstat.c | 1 + mm/workingset.c | 95 +++++++++++++++++++++++++++--------------- 11 files changed, 77 insertions(+), 42 deletions(-) (limited to 'mm') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 7bbeba21f6a3..ba51d5bf7af1 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -163,6 +163,7 @@ enum node_stat_item { NR_ISOLATED_FILE, /* Temporary isolated pages from file lru */ WORKINGSET_REFAULT, WORKINGSET_ACTIVATE, + WORKINGSET_RESTORE, WORKINGSET_NODERECLAIM, NR_ANON_MAPPED, /* Mapped anonymous pages */ NR_FILE_MAPPED, /* pagecache pages mapped into pagetables. diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 74bee8cecf4c..4d99504f6496 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -69,13 +69,14 @@ */ enum pageflags { PG_locked, /* Page is locked. Don't touch. */ - PG_error, PG_referenced, PG_uptodate, PG_dirty, PG_lru, PG_active, + PG_workingset, PG_waiters, /* Page has waiters, check its waitqueue. Must be bit #7 and in the same byte as "PG_locked" */ + PG_error, PG_slab, PG_owner_priv_1, /* Owner use. If pagecache, fs may use*/ PG_arch_1, @@ -280,6 +281,8 @@ PAGEFLAG(Dirty, dirty, PF_HEAD) TESTSCFLAG(Dirty, dirty, PF_HEAD) PAGEFLAG(LRU, lru, PF_HEAD) __CLEARPAGEFLAG(LRU, lru, PF_HEAD) PAGEFLAG(Active, active, PF_HEAD) __CLEARPAGEFLAG(Active, active, PF_HEAD) TESTCLEARFLAG(Active, active, PF_HEAD) +PAGEFLAG(Workingset, workingset, PF_HEAD) + TESTCLEARFLAG(Workingset, workingset, PF_HEAD) __PAGEFLAG(Slab, slab, PF_NO_TAIL) __PAGEFLAG(SlobFree, slob_free, PF_NO_TAIL) PAGEFLAG(Checked, checked, PF_NO_COMPOUND) /* Used by some filesystems */ diff --git a/include/linux/swap.h b/include/linux/swap.h index 8e2c11e692ba..b93740d72e78 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -296,7 +296,7 @@ struct vma_swap_readahead { /* linux/mm/workingset.c */ void *workingset_eviction(struct address_space *mapping, struct page *page); -bool workingset_refault(void *shadow); +void workingset_refault(struct page *page, void *shadow); void workingset_activation(struct page *page); /* Do not use directly, use workingset_lookup_update */ diff --git a/include/trace/events/mmflags.h b/include/trace/events/mmflags.h index a81cffb76d89..a1675d43777e 100644 --- a/include/trace/events/mmflags.h +++ b/include/trace/events/mmflags.h @@ -88,6 +88,7 @@ {1UL << PG_dirty, "dirty" }, \ {1UL << PG_lru, "lru" }, \ {1UL << PG_active, "active" }, \ + {1UL << PG_workingset, "workingset" }, \ {1UL << PG_slab, "slab" }, \ {1UL << PG_owner_priv_1, "owner_priv_1" }, \ {1UL << PG_arch_1, "arch_1" }, \ diff --git a/mm/filemap.c b/mm/filemap.c index de6fed2a0815..7997adce5a29 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -915,12 +915,9 @@ int add_to_page_cache_lru(struct page *page, struct address_space *mapping, * data from the working set, only to cache data that will * get overwritten with something else, is a waste of memory. */ - if (!(gfp_mask & __GFP_WRITE) && - shadow && workingset_refault(shadow)) { - SetPageActive(page); - workingset_activation(page); - } else - ClearPageActive(page); + WARN_ON_ONCE(PageActive(page)); + if (!(gfp_mask & __GFP_WRITE) && shadow) + workingset_refault(page, shadow); lru_cache_add(page); } return ret; diff --git a/mm/huge_memory.c b/mm/huge_memory.c index deed97fba979..8ea1b36bd452 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2369,6 +2369,7 @@ static void __split_huge_page_tail(struct page *head, int tail, (1L << PG_mlocked) | (1L << PG_uptodate) | (1L << PG_active) | + (1L << PG_workingset) | (1L << PG_locked) | (1L << PG_unevictable) | (1L << PG_dirty))); diff --git a/mm/migrate.c b/mm/migrate.c index 84381b55b2bd..1ea27b343ccd 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -685,6 +685,8 @@ void migrate_page_states(struct page *newpage, struct page *page) SetPageActive(newpage); } else if (TestClearPageUnevictable(page)) SetPageUnevictable(newpage); + if (PageWorkingset(page)) + SetPageWorkingset(newpage); if (PageChecked(page)) SetPageChecked(newpage); if (PageMappedToDisk(page)) diff --git a/mm/swap_state.c b/mm/swap_state.c index ecee9c6c4cc1..0d6a7f268d2e 100644 --- a/mm/swap_state.c +++ b/mm/swap_state.c @@ -448,6 +448,7 @@ struct page *__read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask, /* * Initiate read into locked page and return. */ + SetPageWorkingset(new_page); lru_cache_add_anon(new_page); *new_page_allocated = true; return new_page; diff --git a/mm/vmscan.c b/mm/vmscan.c index 961401c46334..87e9fef341d2 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -2145,6 +2145,7 @@ static void shrink_active_list(unsigned long nr_to_scan, } ClearPageActive(page); /* we are de-activating */ + SetPageWorkingset(page); list_add(&page->lru, &l_inactive); } diff --git a/mm/vmstat.c b/mm/vmstat.c index 2cec2fa4c8ae..d918f6192d15 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -1145,6 +1145,7 @@ const char * const vmstat_text[] = { "nr_isolated_file", "workingset_refault", "workingset_activate", + "workingset_restore", "workingset_nodereclaim", "nr_anon_pages", "nr_mapped", diff --git a/mm/workingset.c b/mm/workingset.c index 7d5fa0dd2b38..99b7f7c09b13 100644 --- a/mm/workingset.c +++ b/mm/workingset.c @@ -121,7 +121,7 @@ * the only thing eating into inactive list space is active pages. * * - * Activating refaulting pages + * Refaulting inactive pages * * All that is known about the active list is that the pages have been * accessed more than once in the past. This means that at any given @@ -134,6 +134,10 @@ * used less frequently than the refaulting page - or even not used at * all anymore. * + * That means if inactive cache is refaulting with a suitable refault + * distance, we assume the cache workingset is transitioning and put + * pressure on the current active list. + * * If this is wrong and demotion kicks in, the pages which are truly * used more frequently will be reactivated while the less frequently * used once will be evicted from memory. @@ -141,6 +145,14 @@ * But if this is right, the stale pages will be pushed out of memory * and the used pages get to stay in cache. * + * Refaulting active pages + * + * If on the other hand the refaulting pages have recently been + * deactivated, it means that the active list is no longer protecting + * actively used cache from reclaim. The cache is NOT transitioning to + * a different workingset; the existing workingset is thrashing in the + * space allocated to the page cache. + * * * Implementation * @@ -156,8 +168,7 @@ */ #define EVICTION_SHIFT (RADIX_TREE_EXCEPTIONAL_ENTRY + \ - NODES_SHIFT + \ - MEM_CGROUP_ID_SHIFT) + 1 + NODES_SHIFT + MEM_CGROUP_ID_SHIFT) #define EVICTION_MASK (~0UL >> EVICTION_SHIFT) /* @@ -170,23 +181,28 @@ */ static unsigned int bucket_order __read_mostly; -static void *pack_shadow(int memcgid, pg_data_t *pgdat, unsigned long eviction) +static void *pack_shadow(int memcgid, pg_data_t *pgdat, unsigned long eviction, + bool workingset) { eviction >>= bucket_order; eviction = (eviction << MEM_CGROUP_ID_SHIFT) | memcgid; eviction = (eviction << NODES_SHIFT) | pgdat->node_id; + eviction = (eviction << 1) | workingset; eviction = (eviction << RADIX_TREE_EXCEPTIONAL_SHIFT); return (void *)(eviction | RADIX_TREE_EXCEPTIONAL_ENTRY); } static void unpack_shadow(void *shadow, int *memcgidp, pg_data_t **pgdat, - unsigned long *evictionp) + unsigned long *evictionp, bool *workingsetp) { unsigned long entry = (unsigned long)shadow; int memcgid, nid; + bool workingset; entry >>= RADIX_TREE_EXCEPTIONAL_SHIFT; + workingset = entry & 1; + entry >>= 1; nid = entry & ((1UL << NODES_SHIFT) - 1); entry >>= NODES_SHIFT; memcgid = entry & ((1UL << MEM_CGROUP_ID_SHIFT) - 1); @@ -195,6 +211,7 @@ static void unpack_shadow(void *shadow, int *memcgidp, pg_data_t **pgdat, *memcgidp = memcgid; *pgdat = NODE_DATA(nid); *evictionp = entry << bucket_order; + *workingsetp = workingset; } /** @@ -207,8 +224,8 @@ static void unpack_shadow(void *shadow, int *memcgidp, pg_data_t **pgdat, */ void *workingset_eviction(struct address_space *mapping, struct page *page) { - struct mem_cgroup *memcg = page_memcg(page); struct pglist_data *pgdat = page_pgdat(page); + struct mem_cgroup *memcg = page_memcg(page); int memcgid = mem_cgroup_id(memcg); unsigned long eviction; struct lruvec *lruvec; @@ -220,30 +237,30 @@ void *workingset_eviction(struct address_space *mapping, struct page *page) lruvec = mem_cgroup_lruvec(pgdat, memcg); eviction = atomic_long_inc_return(&lruvec->inactive_age); - return pack_shadow(memcgid, pgdat, eviction); + return pack_shadow(memcgid, pgdat, eviction, PageWorkingset(page)); } /** * workingset_refault - evaluate the refault of a previously evicted page + * @page: the freshly allocated replacement page * @shadow: shadow entry of the evicted page * * Calculates and evaluates the refault distance of the previously * evicted page in the context of the node it was allocated in. - * - * Returns %true if the page should be activated, %false otherwise. */ -bool workingset_refault(void *shadow) +void workingset_refault(struct page *page, void *shadow) { unsigned long refault_distance; + struct pglist_data *pgdat; unsigned long active_file; struct mem_cgroup *memcg; unsigned long eviction; struct lruvec *lruvec; unsigned long refault; - struct pglist_data *pgdat; + bool workingset; int memcgid; - unpack_shadow(shadow, &memcgid, &pgdat, &eviction); + unpack_shadow(shadow, &memcgid, &pgdat, &eviction, &workingset); rcu_read_lock(); /* @@ -263,41 +280,51 @@ bool workingset_refault(void *shadow) * configurations instead. */ memcg = mem_cgroup_from_id(memcgid); - if (!mem_cgroup_disabled() && !memcg) { - rcu_read_unlock(); - return false; - } + if (!mem_cgroup_disabled() && !memcg) + goto out; lruvec = mem_cgroup_lruvec(pgdat, memcg); refault = atomic_long_read(&lruvec->inactive_age); active_file = lruvec_lru_size(lruvec, LRU_ACTIVE_FILE, MAX_NR_ZONES); /* - * The unsigned subtraction here gives an accurate distance - * across inactive_age overflows in most cases. + * Calculate the refault distance * - * There is a special case: usually, shadow entries have a - * short lifetime and are either refaulted or reclaimed along - * with the inode before they get too old. But it is not - * impossible for the inactive_age to lap a shadow entry in - * the field, which can then can result in a false small - * refault distance, leading to a false activation should this - * old entry actually refault again. However, earlier kernels - * used to deactivate unconditionally with *every* reclaim - * invocation for the longest time, so the occasional - * inappropriate activation leading to pressure on the active - * list is not a problem. + * The unsigned subtraction here gives an accurate distance + * across inactive_age overflows in most cases. There is a + * special case: usually, shadow entries have a short lifetime + * and are either refaulted or reclaimed along with the inode + * before they get too old. But it is not impossible for the + * inactive_age to lap a shadow entry in the field, which can + * then result in a false small refault distance, leading to a + * false activation should this old entry actually refault + * again. However, earlier kernels used to deactivate + * unconditionally with *every* reclaim invocation for the + * longest time, so the occasional inappropriate activation + * leading to pressure on the active list is not a problem. */ refault_distance = (refault - eviction) & EVICTION_MASK; inc_lruvec_state(lruvec, WORKINGSET_REFAULT); - if (refault_distance <= active_file) { - inc_lruvec_state(lruvec, WORKINGSET_ACTIVATE); - rcu_read_unlock(); - return true; + /* + * Compare the distance to the existing workingset size. We + * don't act on pages that couldn't stay resident even if all + * the memory was available to the page cache. + */ + if (refault_distance > active_file) + goto out; + + SetPageActive(page); + atomic_long_inc(&lruvec->inactive_age); + inc_lruvec_state(lruvec, WORKINGSET_ACTIVATE); + + /* Page was active prior to eviction */ + if (workingset) { + SetPageWorkingset(page); + inc_lruvec_state(lruvec, WORKINGSET_RESTORE); } +out: rcu_read_unlock(); - return false; } /** -- cgit v1.2.3 From b1d29ba82cf2bc784f4c963ddd6a2cf29e229b33 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Fri, 26 Oct 2018 15:06:08 -0700 Subject: delayacct: track delays from thrashing cache pages Delay accounting already measures the time a task spends in direct reclaim and waiting for swapin, but in low memory situations tasks spend can spend a significant amount of their time waiting on thrashing page cache. This isn't tracked right now. To know the full impact of memory contention on an individual task, measure the delay when waiting for a recently evicted active cache page to read back into memory. Also update tools/accounting/getdelays.c: [hannes@computer accounting]$ sudo ./getdelays -d -p 1 print delayacct stats ON PID 1 CPU count real total virtual total delay total delay average 50318 745000000 847346785 400533713 0.008ms IO count delay total delay average 435 122601218 0ms SWAP count delay total delay average 0 0 0ms RECLAIM count delay total delay average 0 0 0ms THRASHING count delay total delay average 19 12621439 0ms Link: http://lkml.kernel.org/r/20180828172258.3185-4-hannes@cmpxchg.org Signed-off-by: Johannes Weiner Acked-by: Peter Zijlstra (Intel) Tested-by: Daniel Drake Tested-by: Suren Baghdasaryan Cc: Christopher Lameter Cc: Ingo Molnar Cc: Johannes Weiner Cc: Mike Galbraith Cc: Peter Enderborg Cc: Randy Dunlap Cc: Shakeel Butt Cc: Tejun Heo Cc: Vinayak Menon Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/delayacct.h | 23 +++++++++++++++++++++++ include/uapi/linux/taskstats.h | 6 +++++- kernel/delayacct.c | 15 +++++++++++++++ mm/filemap.c | 11 +++++++++++ tools/accounting/getdelays.c | 8 +++++++- 5 files changed, 61 insertions(+), 2 deletions(-) (limited to 'mm') diff --git a/include/linux/delayacct.h b/include/linux/delayacct.h index 31c865d1842e..577d1b25fccd 100644 --- a/include/linux/delayacct.h +++ b/include/linux/delayacct.h @@ -57,7 +57,12 @@ struct task_delay_info { u64 freepages_start; u64 freepages_delay; /* wait for memory reclaim */ + + u64 thrashing_start; + u64 thrashing_delay; /* wait for thrashing page */ + u32 freepages_count; /* total count of memory reclaim */ + u32 thrashing_count; /* total count of thrash waits */ }; #endif @@ -76,6 +81,8 @@ extern int __delayacct_add_tsk(struct taskstats *, struct task_struct *); extern __u64 __delayacct_blkio_ticks(struct task_struct *); extern void __delayacct_freepages_start(void); extern void __delayacct_freepages_end(void); +extern void __delayacct_thrashing_start(void); +extern void __delayacct_thrashing_end(void); static inline int delayacct_is_task_waiting_on_io(struct task_struct *p) { @@ -156,6 +163,18 @@ static inline void delayacct_freepages_end(void) __delayacct_freepages_end(); } +static inline void delayacct_thrashing_start(void) +{ + if (current->delays) + __delayacct_thrashing_start(); +} + +static inline void delayacct_thrashing_end(void) +{ + if (current->delays) + __delayacct_thrashing_end(); +} + #else static inline void delayacct_set_flag(int flag) {} @@ -182,6 +201,10 @@ static inline void delayacct_freepages_start(void) {} static inline void delayacct_freepages_end(void) {} +static inline void delayacct_thrashing_start(void) +{} +static inline void delayacct_thrashing_end(void) +{} #endif /* CONFIG_TASK_DELAY_ACCT */ diff --git a/include/uapi/linux/taskstats.h b/include/uapi/linux/taskstats.h index b7aa7bb2349f..5e8ca16a9079 100644 --- a/include/uapi/linux/taskstats.h +++ b/include/uapi/linux/taskstats.h @@ -34,7 +34,7 @@ */ -#define TASKSTATS_VERSION 8 +#define TASKSTATS_VERSION 9 #define TS_COMM_LEN 32 /* should be >= TASK_COMM_LEN * in linux/sched.h */ @@ -164,6 +164,10 @@ struct taskstats { /* Delay waiting for memory reclaim */ __u64 freepages_count; __u64 freepages_delay_total; + + /* Delay waiting for thrashing page */ + __u64 thrashing_count; + __u64 thrashing_delay_total; }; diff --git a/kernel/delayacct.c b/kernel/delayacct.c index ca8ac2824f0b..2a12b988c717 100644 --- a/kernel/delayacct.c +++ b/kernel/delayacct.c @@ -135,9 +135,12 @@ int __delayacct_add_tsk(struct taskstats *d, struct task_struct *tsk) d->swapin_delay_total = (tmp < d->swapin_delay_total) ? 0 : tmp; tmp = d->freepages_delay_total + tsk->delays->freepages_delay; d->freepages_delay_total = (tmp < d->freepages_delay_total) ? 0 : tmp; + tmp = d->thrashing_delay_total + tsk->delays->thrashing_delay; + d->thrashing_delay_total = (tmp < d->thrashing_delay_total) ? 0 : tmp; d->blkio_count += tsk->delays->blkio_count; d->swapin_count += tsk->delays->swapin_count; d->freepages_count += tsk->delays->freepages_count; + d->thrashing_count += tsk->delays->thrashing_count; raw_spin_unlock_irqrestore(&tsk->delays->lock, flags); return 0; @@ -169,3 +172,15 @@ void __delayacct_freepages_end(void) ¤t->delays->freepages_count); } +void __delayacct_thrashing_start(void) +{ + current->delays->thrashing_start = ktime_get_ns(); +} + +void __delayacct_thrashing_end(void) +{ + delayacct_end(¤t->delays->lock, + ¤t->delays->thrashing_start, + ¤t->delays->thrashing_delay, + ¤t->delays->thrashing_count); +} diff --git a/mm/filemap.c b/mm/filemap.c index 7997adce5a29..01a841f17bf4 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -36,6 +36,7 @@ #include #include #include +#include #include "internal.h" #define CREATE_TRACE_POINTS @@ -1073,8 +1074,15 @@ static inline int wait_on_page_bit_common(wait_queue_head_t *q, { struct wait_page_queue wait_page; wait_queue_entry_t *wait = &wait_page.wait; + bool thrashing = false; int ret = 0; + if (bit_nr == PG_locked && !PageSwapBacked(page) && + !PageUptodate(page) && PageWorkingset(page)) { + delayacct_thrashing_start(); + thrashing = true; + } + init_wait(wait); wait->flags = lock ? WQ_FLAG_EXCLUSIVE : 0; wait->func = wake_page_function; @@ -1113,6 +1121,9 @@ static inline int wait_on_page_bit_common(wait_queue_head_t *q, finish_wait(q, wait); + if (thrashing) + delayacct_thrashing_end(); + /* * A signal could leave PageWaiters set. Clearing it here if * !waitqueue_active would be possible (by open-coding finish_wait), diff --git a/tools/accounting/getdelays.c b/tools/accounting/getdelays.c index 9f420d98b5fb..8cb504d30384 100644 --- a/tools/accounting/getdelays.c +++ b/tools/accounting/getdelays.c @@ -203,6 +203,8 @@ static void print_delayacct(struct taskstats *t) "SWAP %15s%15s%15s\n" " %15llu%15llu%15llums\n" "RECLAIM %12s%15s%15s\n" + " %15llu%15llu%15llums\n" + "THRASHING%12s%15s%15s\n" " %15llu%15llu%15llums\n", "count", "real total", "virtual total", "delay total", "delay average", @@ -222,7 +224,11 @@ static void print_delayacct(struct taskstats *t) "count", "delay total", "delay average", (unsigned long long)t->freepages_count, (unsigned long long)t->freepages_delay_total, - average_ms(t->freepages_delay_total, t->freepages_count)); + average_ms(t->freepages_delay_total, t->freepages_count), + "count", "delay total", "delay average", + (unsigned long long)t->thrashing_count, + (unsigned long long)t->thrashing_delay_total, + average_ms(t->thrashing_delay_total, t->thrashing_count)); } static void task_context_switch_counts(struct taskstats *t) -- cgit v1.2.3 From eb414681d5a07d28d2ff90dc05f69ec6b232ebd2 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Fri, 26 Oct 2018 15:06:27 -0700 Subject: psi: pressure stall information for CPU, memory, and IO When systems are overcommitted and resources become contended, it's hard to tell exactly the impact this has on workload productivity, or how close the system is to lockups and OOM kills. In particular, when machines work multiple jobs concurrently, the impact of overcommit in terms of latency and throughput on the individual job can be enormous. In order to maximize hardware utilization without sacrificing individual job health or risk complete machine lockups, this patch implements a way to quantify resource pressure in the system. A kernel built with CONFIG_PSI=y creates files in /proc/pressure/ that expose the percentage of time the system is stalled on CPU, memory, or IO, respectively. Stall states are aggregate versions of the per-task delay accounting delays: cpu: some tasks are runnable but not executing on a CPU memory: tasks are reclaiming, or waiting for swapin or thrashing cache io: tasks are waiting for io completions These percentages of walltime can be thought of as pressure percentages, and they give a general sense of system health and productivity loss incurred by resource overcommit. They can also indicate when the system is approaching lockup scenarios and OOMs. To do this, psi keeps track of the task states associated with each CPU and samples the time they spend in stall states. Every 2 seconds, the samples are averaged across CPUs - weighted by the CPUs' non-idle time to eliminate artifacts from unused CPUs - and translated into percentages of walltime. A running average of those percentages is maintained over 10s, 1m, and 5m periods (similar to the loadaverage). [hannes@cmpxchg.org: doc fixlet, per Randy] Link: http://lkml.kernel.org/r/20180828205625.GA14030@cmpxchg.org [hannes@cmpxchg.org: code optimization] Link: http://lkml.kernel.org/r/20180907175015.GA8479@cmpxchg.org [hannes@cmpxchg.org: rename psi_clock() to psi_update_work(), per Peter] Link: http://lkml.kernel.org/r/20180907145404.GB11088@cmpxchg.org [hannes@cmpxchg.org: fix build] Link: http://lkml.kernel.org/r/20180913014222.GA2370@cmpxchg.org Link: http://lkml.kernel.org/r/20180828172258.3185-9-hannes@cmpxchg.org Signed-off-by: Johannes Weiner Acked-by: Peter Zijlstra (Intel) Tested-by: Daniel Drake Tested-by: Suren Baghdasaryan Cc: Christopher Lameter Cc: Ingo Molnar Cc: Johannes Weiner Cc: Mike Galbraith Cc: Peter Enderborg Cc: Randy Dunlap Cc: Shakeel Butt Cc: Tejun Heo Cc: Vinayak Menon Cc: Randy Dunlap Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/accounting/psi.txt | 64 ++++ include/linux/psi.h | 28 ++ include/linux/psi_types.h | 92 ++++++ include/linux/sched.h | 10 + init/Kconfig | 15 + kernel/fork.c | 4 + kernel/sched/Makefile | 1 + kernel/sched/core.c | 12 +- kernel/sched/psi.c | 657 +++++++++++++++++++++++++++++++++++++++ kernel/sched/sched.h | 2 + kernel/sched/stats.h | 86 +++++ mm/compaction.c | 5 + mm/filemap.c | 15 +- mm/page_alloc.c | 9 + mm/vmscan.c | 9 + 15 files changed, 1003 insertions(+), 6 deletions(-) create mode 100644 Documentation/accounting/psi.txt create mode 100644 include/linux/psi.h create mode 100644 include/linux/psi_types.h create mode 100644 kernel/sched/psi.c (limited to 'mm') diff --git a/Documentation/accounting/psi.txt b/Documentation/accounting/psi.txt new file mode 100644 index 000000000000..3753a82f1cf5 --- /dev/null +++ b/Documentation/accounting/psi.txt @@ -0,0 +1,64 @@ +================================ +PSI - Pressure Stall Information +================================ + +:Date: April, 2018 +:Author: Johannes Weiner + +When CPU, memory or IO devices are contended, workloads experience +latency spikes, throughput losses, and run the risk of OOM kills. + +Without an accurate measure of such contention, users are forced to +either play it safe and under-utilize their hardware resources, or +roll the dice and frequently suffer the disruptions resulting from +excessive overcommit. + +The psi feature identifies and quantifies the disruptions caused by +such resource crunches and the time impact it has on complex workloads +or even entire systems. + +Having an accurate measure of productivity losses caused by resource +scarcity aids users in sizing workloads to hardware--or provisioning +hardware according to workload demand. + +As psi aggregates this information in realtime, systems can be managed +dynamically using techniques such as load shedding, migrating jobs to +other systems or data centers, or strategically pausing or killing low +priority or restartable batch jobs. + +This allows maximizing hardware utilization without sacrificing +workload health or risking major disruptions such as OOM kills. + +Pressure interface +================== + +Pressure information for each resource is exported through the +respective file in /proc/pressure/ -- cpu, memory, and io. + +The format for CPU is as such: + +some avg10=0.00 avg60=0.00 avg300=0.00 total=0 + +and for memory and IO: + +some avg10=0.00 avg60=0.00 avg300=0.00 total=0 +full avg10=0.00 avg60=0.00 avg300=0.00 total=0 + +The "some" line indicates the share of time in which at least some +tasks are stalled on a given resource. + +The "full" line indicates the share of time in which all non-idle +tasks are stalled on a given resource simultaneously. In this state +actual CPU cycles are going to waste, and a workload that spends +extended time in this state is considered to be thrashing. This has +severe impact on performance, and it's useful to distinguish this +situation from a state where some tasks are stalled but the CPU is +still doing productive work. As such, time spent in this subset of the +stall state is tracked separately and exported in the "full" averages. + +The ratios are tracked as recent trends over ten, sixty, and three +hundred second windows, which gives insight into short term events as +well as medium and long term trends. The total absolute stall time is +tracked and exported as well, to allow detection of latency spikes +which wouldn't necessarily make a dent in the time averages, or to +average trends over custom time frames. diff --git a/include/linux/psi.h b/include/linux/psi.h new file mode 100644 index 000000000000..b0daf050de58 --- /dev/null +++ b/include/linux/psi.h @@ -0,0 +1,28 @@ +#ifndef _LINUX_PSI_H +#define _LINUX_PSI_H + +#include +#include + +#ifdef CONFIG_PSI + +extern bool psi_disabled; + +void psi_init(void); + +void psi_task_change(struct task_struct *task, int clear, int set); + +void psi_memstall_tick(struct task_struct *task, int cpu); +void psi_memstall_enter(unsigned long *flags); +void psi_memstall_leave(unsigned long *flags); + +#else /* CONFIG_PSI */ + +static inline void psi_init(void) {} + +static inline void psi_memstall_enter(unsigned long *flags) {} +static inline void psi_memstall_leave(unsigned long *flags) {} + +#endif /* CONFIG_PSI */ + +#endif /* _LINUX_PSI_H */ diff --git a/include/linux/psi_types.h b/include/linux/psi_types.h new file mode 100644 index 000000000000..2cf422db5d18 --- /dev/null +++ b/include/linux/psi_types.h @@ -0,0 +1,92 @@ +#ifndef _LINUX_PSI_TYPES_H +#define _LINUX_PSI_TYPES_H + +#include +#include + +#ifdef CONFIG_PSI + +/* Tracked task states */ +enum psi_task_count { + NR_IOWAIT, + NR_MEMSTALL, + NR_RUNNING, + NR_PSI_TASK_COUNTS, +}; + +/* Task state bitmasks */ +#define TSK_IOWAIT (1 << NR_IOWAIT) +#define TSK_MEMSTALL (1 << NR_MEMSTALL) +#define TSK_RUNNING (1 << NR_RUNNING) + +/* Resources that workloads could be stalled on */ +enum psi_res { + PSI_IO, + PSI_MEM, + PSI_CPU, + NR_PSI_RESOURCES, +}; + +/* + * Pressure states for each resource: + * + * SOME: Stalled tasks & working tasks + * FULL: Stalled tasks & no working tasks + */ +enum psi_states { + PSI_IO_SOME, + PSI_IO_FULL, + PSI_MEM_SOME, + PSI_MEM_FULL, + PSI_CPU_SOME, + /* Only per-CPU, to weigh the CPU in the global average: */ + PSI_NONIDLE, + NR_PSI_STATES, +}; + +struct psi_group_cpu { + /* 1st cacheline updated by the scheduler */ + + /* Aggregator needs to know of concurrent changes */ + seqcount_t seq ____cacheline_aligned_in_smp; + + /* States of the tasks belonging to this group */ + unsigned int tasks[NR_PSI_TASK_COUNTS]; + + /* Period time sampling buckets for each state of interest (ns) */ + u32 times[NR_PSI_STATES]; + + /* Time of last task change in this group (rq_clock) */ + u64 state_start; + + /* 2nd cacheline updated by the aggregator */ + + /* Delta detection against the sampling buckets */ + u32 times_prev[NR_PSI_STATES] ____cacheline_aligned_in_smp; +}; + +struct psi_group { + /* Protects data updated during an aggregation */ + struct mutex stat_lock; + + /* Per-cpu task state & time tracking */ + struct psi_group_cpu __percpu *pcpu; + + /* Periodic aggregation state */ + u64 total_prev[NR_PSI_STATES - 1]; + u64 last_update; + u64 next_update; + struct delayed_work clock_work; + + /* Total stall times and sampled pressure averages */ + u64 total[NR_PSI_STATES - 1]; + unsigned long avg[NR_PSI_STATES - 1][3]; +}; + +#else /* CONFIG_PSI */ + +struct psi_group { }; + +#endif /* CONFIG_PSI */ + +#endif /* _LINUX_PSI_TYPES_H */ diff --git a/include/linux/sched.h b/include/linux/sched.h index adfb3f9a7597..b8fcc6b3080c 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -25,6 +25,7 @@ #include #include #include +#include #include #include #include @@ -706,6 +707,10 @@ struct task_struct { unsigned sched_contributes_to_load:1; unsigned sched_migrated:1; unsigned sched_remote_wakeup:1; +#ifdef CONFIG_PSI + unsigned sched_psi_wake_requeue:1; +#endif + /* Force alignment to the next boundary: */ unsigned :0; @@ -965,6 +970,10 @@ struct task_struct { kernel_siginfo_t *last_siginfo; struct task_io_accounting ioac; +#ifdef CONFIG_PSI + /* Pressure stall state */ + unsigned int psi_flags; +#endif #ifdef CONFIG_TASK_XACCT /* Accumulated RSS usage: */ u64 acct_rss_mem1; @@ -1391,6 +1400,7 @@ extern struct pid *cad_pid; #define PF_KTHREAD 0x00200000 /* I am a kernel thread */ #define PF_RANDOMIZE 0x00400000 /* Randomize virtual address space */ #define PF_SWAPWRITE 0x00800000 /* Allowed to write to swap */ +#define PF_MEMSTALL 0x01000000 /* Stalled due to lack of memory */ #define PF_NO_SETAFFINITY 0x04000000 /* Userland is not allowed to meddle with cpus_allowed */ #define PF_MCE_EARLY 0x08000000 /* Early kill for mce process policy */ #define PF_MUTEX_TESTER 0x20000000 /* Thread belongs to the rt mutex tester */ diff --git a/init/Kconfig b/init/Kconfig index 317d5ccb5191..26e639df5517 100644 --- a/init/Kconfig +++ b/init/Kconfig @@ -490,6 +490,21 @@ config TASK_IO_ACCOUNTING Say N if unsure. +config PSI + bool "Pressure stall information tracking" + help + Collect metrics that indicate how overcommitted the CPU, memory, + and IO capacity are in the system. + + If you say Y here, the kernel will create /proc/pressure/ with the + pressure statistics files cpu, memory, and io. These will indicate + the share of walltime in which some or all tasks in the system are + delayed due to contention of the respective resource. + + For more details see Documentation/accounting/psi.txt. + + Say N if unsure. + endmenu # "CPU/Task time and stats accounting" config CPU_ISOLATION diff --git a/kernel/fork.c b/kernel/fork.c index 3c719fec46c5..8f82a3bdcb8f 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1822,6 +1822,10 @@ static __latent_entropy struct task_struct *copy_process( p->default_timer_slack_ns = current->timer_slack_ns; +#ifdef CONFIG_PSI + p->psi_flags = 0; +#endif + task_io_accounting_init(&p->ioac); acct_clear_integrals(p); diff --git a/kernel/sched/Makefile b/kernel/sched/Makefile index 7fe183404c38..21fb5a5662b5 100644 --- a/kernel/sched/Makefile +++ b/kernel/sched/Makefile @@ -29,3 +29,4 @@ obj-$(CONFIG_CPU_FREQ) += cpufreq.o obj-$(CONFIG_CPU_FREQ_GOV_SCHEDUTIL) += cpufreq_schedutil.o obj-$(CONFIG_MEMBARRIER) += membarrier.o obj-$(CONFIG_CPU_ISOLATION) += isolation.o +obj-$(CONFIG_PSI) += psi.o diff --git a/kernel/sched/core.c b/kernel/sched/core.c index f3efef387797..fd2fce8a001b 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -722,8 +722,10 @@ static inline void enqueue_task(struct rq *rq, struct task_struct *p, int flags) if (!(flags & ENQUEUE_NOCLOCK)) update_rq_clock(rq); - if (!(flags & ENQUEUE_RESTORE)) + if (!(flags & ENQUEUE_RESTORE)) { sched_info_queued(rq, p); + psi_enqueue(p, flags & ENQUEUE_WAKEUP); + } p->sched_class->enqueue_task(rq, p, flags); } @@ -733,8 +735,10 @@ static inline void dequeue_task(struct rq *rq, struct task_struct *p, int flags) if (!(flags & DEQUEUE_NOCLOCK)) update_rq_clock(rq); - if (!(flags & DEQUEUE_SAVE)) + if (!(flags & DEQUEUE_SAVE)) { sched_info_dequeued(rq, p); + psi_dequeue(p, flags & DEQUEUE_SLEEP); + } p->sched_class->dequeue_task(rq, p, flags); } @@ -2037,6 +2041,7 @@ try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags) cpu = select_task_rq(p, p->wake_cpu, SD_BALANCE_WAKE, wake_flags); if (task_cpu(p) != cpu) { wake_flags |= WF_MIGRATED; + psi_ttwu_dequeue(p); set_task_cpu(p, cpu); } @@ -3051,6 +3056,7 @@ void scheduler_tick(void) curr->sched_class->task_tick(rq, curr, 0); cpu_load_update_active(rq); calc_global_load_tick(rq); + psi_task_tick(rq); rq_unlock(rq, &rf); @@ -6067,6 +6073,8 @@ void __init sched_init(void) init_schedstats(); + psi_init(); + scheduler_running = 1; } diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c new file mode 100644 index 000000000000..595414599b98 --- /dev/null +++ b/kernel/sched/psi.c @@ -0,0 +1,657 @@ +/* + * Pressure stall information for CPU, memory and IO + * + * Copyright (c) 2018 Facebook, Inc. + * Author: Johannes Weiner + * + * When CPU, memory and IO are contended, tasks experience delays that + * reduce throughput and introduce latencies into the workload. Memory + * and IO contention, in addition, can cause a full loss of forward + * progress in which the CPU goes idle. + * + * This code aggregates individual task delays into resource pressure + * metrics that indicate problems with both workload health and + * resource utilization. + * + * Model + * + * The time in which a task can execute on a CPU is our baseline for + * productivity. Pressure expresses the amount of time in which this + * potential cannot be realized due to resource contention. + * + * This concept of productivity has two components: the workload and + * the CPU. To measure the impact of pressure on both, we define two + * contention states for a resource: SOME and FULL. + * + * In the SOME state of a given resource, one or more tasks are + * delayed on that resource. This affects the workload's ability to + * perform work, but the CPU may still be executing other tasks. + * + * In the FULL state of a given resource, all non-idle tasks are + * delayed on that resource such that nobody is advancing and the CPU + * goes idle. This leaves both workload and CPU unproductive. + * + * (Naturally, the FULL state doesn't exist for the CPU resource.) + * + * SOME = nr_delayed_tasks != 0 + * FULL = nr_delayed_tasks != 0 && nr_running_tasks == 0 + * + * The percentage of wallclock time spent in those compound stall + * states gives pressure numbers between 0 and 100 for each resource, + * where the SOME percentage indicates workload slowdowns and the FULL + * percentage indicates reduced CPU utilization: + * + * %SOME = time(SOME) / period + * %FULL = time(FULL) / period + * + * Multiple CPUs + * + * The more tasks and available CPUs there are, the more work can be + * performed concurrently. This means that the potential that can go + * unrealized due to resource contention *also* scales with non-idle + * tasks and CPUs. + * + * Consider a scenario where 257 number crunching tasks are trying to + * run concurrently on 256 CPUs. If we simply aggregated the task + * states, we would have to conclude a CPU SOME pressure number of + * 100%, since *somebody* is waiting on a runqueue at all + * times. However, that is clearly not the amount of contention the + * workload is experiencing: only one out of 256 possible exceution + * threads will be contended at any given time, or about 0.4%. + * + * Conversely, consider a scenario of 4 tasks and 4 CPUs where at any + * given time *one* of the tasks is delayed due to a lack of memory. + * Again, looking purely at the task state would yield a memory FULL + * pressure number of 0%, since *somebody* is always making forward + * progress. But again this wouldn't capture the amount of execution + * potential lost, which is 1 out of 4 CPUs, or 25%. + * + * To calculate wasted potential (pressure) with multiple processors, + * we have to base our calculation on the number of non-idle tasks in + * conjunction with the number of available CPUs, which is the number + * of potential execution threads. SOME becomes then the proportion of + * delayed tasks to possibe threads, and FULL is the share of possible + * threads that are unproductive due to delays: + * + * threads = min(nr_nonidle_tasks, nr_cpus) + * SOME = min(nr_delayed_tasks / threads, 1) + * FULL = (threads - min(nr_running_tasks, threads)) / threads + * + * For the 257 number crunchers on 256 CPUs, this yields: + * + * threads = min(257, 256) + * SOME = min(1 / 256, 1) = 0.4% + * FULL = (256 - min(257, 256)) / 256 = 0% + * + * For the 1 out of 4 memory-delayed tasks, this yields: + * + * threads = min(4, 4) + * SOME = min(1 / 4, 1) = 25% + * FULL = (4 - min(3, 4)) / 4 = 25% + * + * [ Substitute nr_cpus with 1, and you can see that it's a natural + * extension of the single-CPU model. ] + * + * Implementation + * + * To assess the precise time spent in each such state, we would have + * to freeze the system on task changes and start/stop the state + * clocks accordingly. Obviously that doesn't scale in practice. + * + * Because the scheduler aims to distribute the compute load evenly + * among the available CPUs, we can track task state locally to each + * CPU and, at much lower frequency, extrapolate the global state for + * the cumulative stall times and the running averages. + * + * For each runqueue, we track: + * + * tSOME[cpu] = time(nr_delayed_tasks[cpu] != 0) + * tFULL[cpu] = time(nr_delayed_tasks[cpu] && !nr_running_tasks[cpu]) + * tNONIDLE[cpu] = time(nr_nonidle_tasks[cpu] != 0) + * + * and then periodically aggregate: + * + * tNONIDLE = sum(tNONIDLE[i]) + * + * tSOME = sum(tSOME[i] * tNONIDLE[i]) / tNONIDLE + * tFULL = sum(tFULL[i] * tNONIDLE[i]) / tNONIDLE + * + * %SOME = tSOME / period + * %FULL = tFULL / period + * + * This gives us an approximation of pressure that is practical + * cost-wise, yet way more sensitive and accurate than periodic + * sampling of the aggregate task states would be. + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include "sched.h" + +static int psi_bug __read_mostly; + +bool psi_disabled __read_mostly; +core_param(psi_disabled, psi_disabled, bool, 0644); + +/* Running averages - we need to be higher-res than loadavg */ +#define PSI_FREQ (2*HZ+1) /* 2 sec intervals */ +#define EXP_10s 1677 /* 1/exp(2s/10s) as fixed-point */ +#define EXP_60s 1981 /* 1/exp(2s/60s) */ +#define EXP_300s 2034 /* 1/exp(2s/300s) */ + +/* Sampling frequency in nanoseconds */ +static u64 psi_period __read_mostly; + +/* System-level pressure and stall tracking */ +static DEFINE_PER_CPU(struct psi_group_cpu, system_group_pcpu); +static struct psi_group psi_system = { + .pcpu = &system_group_pcpu, +}; + +static void psi_update_work(struct work_struct *work); + +static void group_init(struct psi_group *group) +{ + int cpu; + + for_each_possible_cpu(cpu) + seqcount_init(&per_cpu_ptr(group->pcpu, cpu)->seq); + group->next_update = sched_clock() + psi_period; + INIT_DELAYED_WORK(&group->clock_work, psi_update_work); + mutex_init(&group->stat_lock); +} + +void __init psi_init(void) +{ + if (psi_disabled) + return; + + psi_period = jiffies_to_nsecs(PSI_FREQ); + group_init(&psi_system); +} + +static bool test_state(unsigned int *tasks, enum psi_states state) +{ + switch (state) { + case PSI_IO_SOME: + return tasks[NR_IOWAIT]; + case PSI_IO_FULL: + return tasks[NR_IOWAIT] && !tasks[NR_RUNNING]; + case PSI_MEM_SOME: + return tasks[NR_MEMSTALL]; + case PSI_MEM_FULL: + return tasks[NR_MEMSTALL] && !tasks[NR_RUNNING]; + case PSI_CPU_SOME: + return tasks[NR_RUNNING] > 1; + case PSI_NONIDLE: + return tasks[NR_IOWAIT] || tasks[NR_MEMSTALL] || + tasks[NR_RUNNING]; + default: + return false; + } +} + +static void get_recent_times(struct psi_group *group, int cpu, u32 *times) +{ + struct psi_group_cpu *groupc = per_cpu_ptr(group->pcpu, cpu); + unsigned int tasks[NR_PSI_TASK_COUNTS]; + u64 now, state_start; + unsigned int seq; + int s; + + /* Snapshot a coherent view of the CPU state */ + do { + seq = read_seqcount_begin(&groupc->seq); + now = cpu_clock(cpu); + memcpy(times, groupc->times, sizeof(groupc->times)); + memcpy(tasks, groupc->tasks, sizeof(groupc->tasks)); + state_start = groupc->state_start; + } while (read_seqcount_retry(&groupc->seq, seq)); + + /* Calculate state time deltas against the previous snapshot */ + for (s = 0; s < NR_PSI_STATES; s++) { + u32 delta; + /* + * In addition to already concluded states, we also + * incorporate currently active states on the CPU, + * since states may last for many sampling periods. + * + * This way we keep our delta sampling buckets small + * (u32) and our reported pressure close to what's + * actually happening. + */ + if (test_state(tasks, s)) + times[s] += now - state_start; + + delta = times[s] - groupc->times_prev[s]; + groupc->times_prev[s] = times[s]; + + times[s] = delta; + } +} + +static void calc_avgs(unsigned long avg[3], int missed_periods, + u64 time, u64 period) +{ + unsigned long pct; + + /* Fill in zeroes for periods of no activity */ + if (missed_periods) { + avg[0] = calc_load_n(avg[0], EXP_10s, 0, missed_periods); + avg[1] = calc_load_n(avg[1], EXP_60s, 0, missed_periods); + avg[2] = calc_load_n(avg[2], EXP_300s, 0, missed_periods); + } + + /* Sample the most recent active period */ + pct = div_u64(time * 100, period); + pct *= FIXED_1; + avg[0] = calc_load(avg[0], EXP_10s, pct); + avg[1] = calc_load(avg[1], EXP_60s, pct); + avg[2] = calc_load(avg[2], EXP_300s, pct); +} + +static bool update_stats(struct psi_group *group) +{ + u64 deltas[NR_PSI_STATES - 1] = { 0, }; + unsigned long missed_periods = 0; + unsigned long nonidle_total = 0; + u64 now, expires, period; + int cpu; + int s; + + mutex_lock(&group->stat_lock); + + /* + * Collect the per-cpu time buckets and average them into a + * single time sample that is normalized to wallclock time. + * + * For averaging, each CPU is weighted by its non-idle time in + * the sampling period. This eliminates artifacts from uneven + * loading, or even entirely idle CPUs. + */ + for_each_possible_cpu(cpu) { + u32 times[NR_PSI_STATES]; + u32 nonidle; + + get_recent_times(group, cpu, times); + + nonidle = nsecs_to_jiffies(times[PSI_NONIDLE]); + nonidle_total += nonidle; + + for (s = 0; s < PSI_NONIDLE; s++) + deltas[s] += (u64)times[s] * nonidle; + } + + /* + * Integrate the sample into the running statistics that are + * reported to userspace: the cumulative stall times and the + * decaying averages. + * + * Pressure percentages are sampled at PSI_FREQ. We might be + * called more often when the user polls more frequently than + * that; we might be called less often when there is no task + * activity, thus no data, and clock ticks are sporadic. The + * below handles both. + */ + + /* total= */ + for (s = 0; s < NR_PSI_STATES - 1; s++) + group->total[s] += div_u64(deltas[s], max(nonidle_total, 1UL)); + + /* avgX= */ + now = sched_clock(); + expires = group->next_update; + if (now < expires) + goto out; + if (now - expires > psi_period) + missed_periods = div_u64(now - expires, psi_period); + + /* + * The periodic clock tick can get delayed for various + * reasons, especially on loaded systems. To avoid clock + * drift, we schedule the clock in fixed psi_period intervals. + * But the deltas we sample out of the per-cpu buckets above + * are based on the actual time elapsing between clock ticks. + */ + group->next_update = expires + ((1 + missed_periods) * psi_period); + period = now - (group->last_update + (missed_periods * psi_period)); + group->last_update = now; + + for (s = 0; s < NR_PSI_STATES - 1; s++) { + u32 sample; + + sample = group->total[s] - group->total_prev[s]; + /* + * Due to the lockless sampling of the time buckets, + * recorded time deltas can slip into the next period, + * which under full pressure can result in samples in + * excess of the period length. + * + * We don't want to report non-sensical pressures in + * excess of 100%, nor do we want to drop such events + * on the floor. Instead we punt any overage into the + * future until pressure subsides. By doing this we + * don't underreport the occurring pressure curve, we + * just report it delayed by one period length. + * + * The error isn't cumulative. As soon as another + * delta slips from a period P to P+1, by definition + * it frees up its time T in P. + */ + if (sample > period) + sample = period; + group->total_prev[s] += sample; + calc_avgs(group->avg[s], missed_periods, sample, period); + } +out: + mutex_unlock(&group->stat_lock); + return nonidle_total; +} + +static void psi_update_work(struct work_struct *work) +{ + struct delayed_work *dwork; + struct psi_group *group; + bool nonidle; + + dwork = to_delayed_work(work); + group = container_of(dwork, struct psi_group, clock_work); + + /* + * If there is task activity, periodically fold the per-cpu + * times and feed samples into the running averages. If things + * are idle and there is no data to process, stop the clock. + * Once restarted, we'll catch up the running averages in one + * go - see calc_avgs() and missed_periods. + */ + + nonidle = update_stats(group); + + if (nonidle) { + unsigned long delay = 0; + u64 now; + + now = sched_clock(); + if (group->next_update > now) + delay = nsecs_to_jiffies(group->next_update - now) + 1; + schedule_delayed_work(dwork, delay); + } +} + +static void record_times(struct psi_group_cpu *groupc, int cpu, + bool memstall_tick) +{ + u32 delta; + u64 now; + + now = cpu_clock(cpu); + delta = now - groupc->state_start; + groupc->state_start = now; + + if (test_state(groupc->tasks, PSI_IO_SOME)) { + groupc->times[PSI_IO_SOME] += delta; + if (test_state(groupc->tasks, PSI_IO_FULL)) + groupc->times[PSI_IO_FULL] += delta; + } + + if (test_state(groupc->tasks, PSI_MEM_SOME)) { + groupc->times[PSI_MEM_SOME] += delta; + if (test_state(groupc->tasks, PSI_MEM_FULL)) + groupc->times[PSI_MEM_FULL] += delta; + else if (memstall_tick) { + u32 sample; + /* + * Since we care about lost potential, a + * memstall is FULL when there are no other + * working tasks, but also when the CPU is + * actively reclaiming and nothing productive + * could run even if it were runnable. + * + * When the timer tick sees a reclaiming CPU, + * regardless of runnable tasks, sample a FULL + * tick (or less if it hasn't been a full tick + * since the last state change). + */ + sample = min(delta, (u32)jiffies_to_nsecs(1)); + groupc->times[PSI_MEM_FULL] += sample; + } + } + + if (test_state(groupc->tasks, PSI_CPU_SOME)) + groupc->times[PSI_CPU_SOME] += delta; + + if (test_state(groupc->tasks, PSI_NONIDLE)) + groupc->times[PSI_NONIDLE] += delta; +} + +static void psi_group_change(struct psi_group *group, int cpu, + unsigned int clear, unsigned int set) +{ + struct psi_group_cpu *groupc; + unsigned int t, m; + + groupc = per_cpu_ptr(group->pcpu, cpu); + + /* + * First we assess the aggregate resource states this CPU's + * tasks have been in since the last change, and account any + * SOME and FULL time these may have resulted in. + * + * Then we update the task counts according to the state + * change requested through the @clear and @set bits. + */ + write_seqcount_begin(&groupc->seq); + + record_times(groupc, cpu, false); + + for (t = 0, m = clear; m; m &= ~(1 << t), t++) { + if (!(m & (1 << t))) + continue; + if (groupc->tasks[t] == 0 && !psi_bug) { + printk_deferred(KERN_ERR "psi: task underflow! cpu=%d t=%d tasks=[%u %u %u] clear=%x set=%x\n", + cpu, t, groupc->tasks[0], + groupc->tasks[1], groupc->tasks[2], + clear, set); + psi_bug = 1; + } + groupc->tasks[t]--; + } + + for (t = 0; set; set &= ~(1 << t), t++) + if (set & (1 << t)) + groupc->tasks[t]++; + + write_seqcount_end(&groupc->seq); + + if (!delayed_work_pending(&group->clock_work)) + schedule_delayed_work(&group->clock_work, PSI_FREQ); +} + +void psi_task_change(struct task_struct *task, int clear, int set) +{ + int cpu = task_cpu(task); + + if (!task->pid) + return; + + if (((task->psi_flags & set) || + (task->psi_flags & clear) != clear) && + !psi_bug) { + printk_deferred(KERN_ERR "psi: inconsistent task state! task=%d:%s cpu=%d psi_flags=%x clear=%x set=%x\n", + task->pid, task->comm, cpu, + task->psi_flags, clear, set); + psi_bug = 1; + } + + task->psi_flags &= ~clear; + task->psi_flags |= set; + + psi_group_change(&psi_system, cpu, clear, set); +} + +void psi_memstall_tick(struct task_struct *task, int cpu) +{ + struct psi_group_cpu *groupc; + + groupc = per_cpu_ptr(psi_system.pcpu, cpu); + write_seqcount_begin(&groupc->seq); + record_times(groupc, cpu, true); + write_seqcount_end(&groupc->seq); +} + +/** + * psi_memstall_enter - mark the beginning of a memory stall section + * @flags: flags to handle nested sections + * + * Marks the calling task as being stalled due to a lack of memory, + * such as waiting for a refault or performing reclaim. + */ +void psi_memstall_enter(unsigned long *flags) +{ + struct rq_flags rf; + struct rq *rq; + + if (psi_disabled) + return; + + *flags = current->flags & PF_MEMSTALL; + if (*flags) + return; + /* + * PF_MEMSTALL setting & accounting needs to be atomic wrt + * changes to the task's scheduling state, otherwise we can + * race with CPU migration. + */ + rq = this_rq_lock_irq(&rf); + + current->flags |= PF_MEMSTALL; + psi_task_change(current, 0, TSK_MEMSTALL); + + rq_unlock_irq(rq, &rf); +} + +/** + * psi_memstall_leave - mark the end of an memory stall section + * @flags: flags to handle nested memdelay sections + * + * Marks the calling task as no longer stalled due to lack of memory. + */ +void psi_memstall_leave(unsigned long *flags) +{ + struct rq_flags rf; + struct rq *rq; + + if (psi_disabled) + return; + + if (*flags) + return; + /* + * PF_MEMSTALL clearing & accounting needs to be atomic wrt + * changes to the task's scheduling state, otherwise we could + * race with CPU migration. + */ + rq = this_rq_lock_irq(&rf); + + current->flags &= ~PF_MEMSTALL; + psi_task_change(current, TSK_MEMSTALL, 0); + + rq_unlock_irq(rq, &rf); +} + +static int psi_show(struct seq_file *m, struct psi_group *group, + enum psi_res res) +{ + int full; + + if (psi_disabled) + return -EOPNOTSUPP; + + update_stats(group); + + for (full = 0; full < 2 - (res == PSI_CPU); full++) { + unsigned long avg[3]; + u64 total; + int w; + + for (w = 0; w < 3; w++) + avg[w] = group->avg[res * 2 + full][w]; + total = div_u64(group->total[res * 2 + full], NSEC_PER_USEC); + + seq_printf(m, "%s avg10=%lu.%02lu avg60=%lu.%02lu avg300=%lu.%02lu total=%llu\n", + full ? "full" : "some", + LOAD_INT(avg[0]), LOAD_FRAC(avg[0]), + LOAD_INT(avg[1]), LOAD_FRAC(avg[1]), + LOAD_INT(avg[2]), LOAD_FRAC(avg[2]), + total); + } + + return 0; +} + +static int psi_io_show(struct seq_file *m, void *v) +{ + return psi_show(m, &psi_system, PSI_IO); +} + +static int psi_memory_show(struct seq_file *m, void *v) +{ + return psi_show(m, &psi_system, PSI_MEM); +} + +static int psi_cpu_show(struct seq_file *m, void *v) +{ + return psi_show(m, &psi_system, PSI_CPU); +} + +static int psi_io_open(struct inode *inode, struct file *file) +{ + return single_open(file, psi_io_show, NULL); +} + +static int psi_memory_open(struct inode *inode, struct file *file) +{ + return single_open(file, psi_memory_show, NULL); +} + +static int psi_cpu_open(struct inode *inode, struct file *file) +{ + return single_open(file, psi_cpu_show, NULL); +} + +static const struct file_operations psi_io_fops = { + .open = psi_io_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +static const struct file_operations psi_memory_fops = { + .open = psi_memory_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +static const struct file_operations psi_cpu_fops = { + .open = psi_cpu_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +static int __init psi_proc_init(void) +{ + proc_mkdir("pressure", NULL); + proc_create("pressure/io", 0, NULL, &psi_io_fops); + proc_create("pressure/memory", 0, NULL, &psi_memory_fops); + proc_create("pressure/cpu", 0, NULL, &psi_cpu_fops); + return 0; +} +module_init(psi_proc_init); diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 1de189bb9209..618577fc9aa8 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -54,6 +54,7 @@ #include #include #include +#include #include #include #include @@ -319,6 +320,7 @@ extern bool dl_cpu_busy(unsigned int cpu); #ifdef CONFIG_CGROUP_SCHED #include +#include struct cfs_rq; struct rt_rq; diff --git a/kernel/sched/stats.h b/kernel/sched/stats.h index 8aea199a39b4..4904c4677000 100644 --- a/kernel/sched/stats.h +++ b/kernel/sched/stats.h @@ -55,6 +55,92 @@ static inline void rq_sched_info_depart (struct rq *rq, unsigned long long delt # define schedstat_val_or_zero(var) 0 #endif /* CONFIG_SCHEDSTATS */ +#ifdef CONFIG_PSI +/* + * PSI tracks state that persists across sleeps, such as iowaits and + * memory stalls. As a result, it has to distinguish between sleeps, + * where a task's runnable state changes, and requeues, where a task + * and its state are being moved between CPUs and runqueues. + */ +static inline void psi_enqueue(struct task_struct *p, bool wakeup) +{ + int clear = 0, set = TSK_RUNNING; + + if (psi_disabled) + return; + + if (!wakeup || p->sched_psi_wake_requeue) { + if (p->flags & PF_MEMSTALL) + set |= TSK_MEMSTALL; + if (p->sched_psi_wake_requeue) + p->sched_psi_wake_requeue = 0; + } else { + if (p->in_iowait) + clear |= TSK_IOWAIT; + } + + psi_task_change(p, clear, set); +} + +static inline void psi_dequeue(struct task_struct *p, bool sleep) +{ + int clear = TSK_RUNNING, set = 0; + + if (psi_disabled) + return; + + if (!sleep) { + if (p->flags & PF_MEMSTALL) + clear |= TSK_MEMSTALL; + } else { + if (p->in_iowait) + set |= TSK_IOWAIT; + } + + psi_task_change(p, clear, set); +} + +static inline void psi_ttwu_dequeue(struct task_struct *p) +{ + if (psi_disabled) + return; + /* + * Is the task being migrated during a wakeup? Make sure to + * deregister its sleep-persistent psi states from the old + * queue, and let psi_enqueue() know it has to requeue. + */ + if (unlikely(p->in_iowait || (p->flags & PF_MEMSTALL))) { + struct rq_flags rf; + struct rq *rq; + int clear = 0; + + if (p->in_iowait) + clear |= TSK_IOWAIT; + if (p->flags & PF_MEMSTALL) + clear |= TSK_MEMSTALL; + + rq = __task_rq_lock(p, &rf); + psi_task_change(p, clear, 0); + p->sched_psi_wake_requeue = 1; + __task_rq_unlock(rq, &rf); + } +} + +static inline void psi_task_tick(struct rq *rq) +{ + if (psi_disabled) + return; + + if (unlikely(rq->curr->flags & PF_MEMSTALL)) + psi_memstall_tick(rq->curr, cpu_of(rq)); +} +#else /* CONFIG_PSI */ +static inline void psi_enqueue(struct task_struct *p, bool wakeup) {} +static inline void psi_dequeue(struct task_struct *p, bool sleep) {} +static inline void psi_ttwu_dequeue(struct task_struct *p) {} +static inline void psi_task_tick(struct rq *rq) {} +#endif /* CONFIG_PSI */ + #ifdef CONFIG_SCHED_INFO static inline void sched_info_reset_dequeued(struct task_struct *t) { diff --git a/mm/compaction.c b/mm/compaction.c index faca45ebe62d..7c607479de4a 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -22,6 +22,7 @@ #include #include #include +#include #include "internal.h" #ifdef CONFIG_COMPACTION @@ -2068,11 +2069,15 @@ static int kcompactd(void *p) pgdat->kcompactd_classzone_idx = pgdat->nr_zones - 1; while (!kthread_should_stop()) { + unsigned long pflags; + trace_mm_compaction_kcompactd_sleep(pgdat->node_id); wait_event_freezable(pgdat->kcompactd_wait, kcompactd_work_requested(pgdat)); + psi_memstall_enter(&pflags); kcompactd_do_work(pgdat); + psi_memstall_leave(&pflags); } return 0; diff --git a/mm/filemap.c b/mm/filemap.c index 01a841f17bf4..41586009fa42 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -37,6 +37,7 @@ #include #include #include +#include #include "internal.h" #define CREATE_TRACE_POINTS @@ -1075,11 +1076,14 @@ static inline int wait_on_page_bit_common(wait_queue_head_t *q, struct wait_page_queue wait_page; wait_queue_entry_t *wait = &wait_page.wait; bool thrashing = false; + unsigned long pflags; int ret = 0; - if (bit_nr == PG_locked && !PageSwapBacked(page) && + if (bit_nr == PG_locked && !PageUptodate(page) && PageWorkingset(page)) { - delayacct_thrashing_start(); + if (!PageSwapBacked(page)) + delayacct_thrashing_start(); + psi_memstall_enter(&pflags); thrashing = true; } @@ -1121,8 +1125,11 @@ static inline int wait_on_page_bit_common(wait_queue_head_t *q, finish_wait(q, wait); - if (thrashing) - delayacct_thrashing_end(); + if (thrashing) { + if (!PageSwapBacked(page)) + delayacct_thrashing_end(); + psi_memstall_leave(&pflags); + } /* * A signal could leave PageWaiters set. Clearing it here if diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 20f25d06c00c..f97b5a1700a4 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -66,6 +66,7 @@ #include #include #include +#include #include #include @@ -3549,15 +3550,20 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order, enum compact_priority prio, enum compact_result *compact_result) { struct page *page; + unsigned long pflags; unsigned int noreclaim_flag; if (!order) return NULL; + psi_memstall_enter(&pflags); noreclaim_flag = memalloc_noreclaim_save(); + *compact_result = try_to_compact_pages(gfp_mask, order, alloc_flags, ac, prio); + memalloc_noreclaim_restore(noreclaim_flag); + psi_memstall_leave(&pflags); if (*compact_result <= COMPACT_INACTIVE) return NULL; @@ -3756,11 +3762,13 @@ __perform_reclaim(gfp_t gfp_mask, unsigned int order, struct reclaim_state reclaim_state; int progress; unsigned int noreclaim_flag; + unsigned long pflags; cond_resched(); /* We now go into synchronous reclaim */ cpuset_memory_pressure_bump(); + psi_memstall_enter(&pflags); fs_reclaim_acquire(gfp_mask); noreclaim_flag = memalloc_noreclaim_save(); reclaim_state.reclaimed_slab = 0; @@ -3772,6 +3780,7 @@ __perform_reclaim(gfp_t gfp_mask, unsigned int order, current->reclaim_state = NULL; memalloc_noreclaim_restore(noreclaim_flag); fs_reclaim_release(gfp_mask); + psi_memstall_leave(&pflags); cond_resched(); diff --git a/mm/vmscan.c b/mm/vmscan.c index 87e9fef341d2..8ea87586925e 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -49,6 +49,7 @@ #include #include #include +#include #include #include @@ -3305,6 +3306,7 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg, { struct zonelist *zonelist; unsigned long nr_reclaimed; + unsigned long pflags; int nid; unsigned int noreclaim_flag; struct scan_control sc = { @@ -3333,9 +3335,13 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg, sc.gfp_mask, sc.reclaim_idx); + psi_memstall_enter(&pflags); noreclaim_flag = memalloc_noreclaim_save(); + nr_reclaimed = do_try_to_free_pages(zonelist, &sc); + memalloc_noreclaim_restore(noreclaim_flag); + psi_memstall_leave(&pflags); trace_mm_vmscan_memcg_reclaim_end(nr_reclaimed); @@ -3500,6 +3506,7 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int classzone_idx) int i; unsigned long nr_soft_reclaimed; unsigned long nr_soft_scanned; + unsigned long pflags; struct zone *zone; struct scan_control sc = { .gfp_mask = GFP_KERNEL, @@ -3510,6 +3517,7 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int classzone_idx) .may_swap = 1, }; + psi_memstall_enter(&pflags); __fs_reclaim_acquire(); count_vm_event(PAGEOUTRUN); @@ -3611,6 +3619,7 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int classzone_idx) out: snapshot_refaults(NULL, pgdat); __fs_reclaim_release(); + psi_memstall_leave(&pflags); /* * Return the order kswapd stopped reclaiming at as * prepare_kswapd_sleep() takes it into account. If another caller -- cgit v1.2.3 From 505802a53510e54ad5fbbd655a68893df83bfb91 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Fri, 26 Oct 2018 15:06:35 -0700 Subject: mm: workingset: use cheaper __inc_lruvec_state in irqsafe node reclaim No need to use the preemption-safe lruvec state function inside the reclaim region that has irqs disabled. Link: http://lkml.kernel.org/r/20181009184732.762-3-hannes@cmpxchg.org Signed-off-by: Johannes Weiner Reviewed-by: Andrew Morton Reviewed-by: Rik van Riel Acked-by: Peter Zijlstra (Intel) Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/workingset.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'mm') diff --git a/mm/workingset.c b/mm/workingset.c index 99b7f7c09b13..5a72c9d5e195 100644 --- a/mm/workingset.c +++ b/mm/workingset.c @@ -500,7 +500,7 @@ static enum lru_status shadow_lru_isolate(struct list_head *item, } if (WARN_ON_ONCE(node->exceptional)) goto out_invalid; - inc_lruvec_page_state(virt_to_page(node), WORKINGSET_NODERECLAIM); + __inc_lruvec_page_state(virt_to_page(node), WORKINGSET_NODERECLAIM); __radix_tree_delete_node(&mapping->i_pages, node, workingset_lookup_update(mapping)); -- cgit v1.2.3 From 68d48e6a2df575b935edd420396c3cb8b6aa6ad3 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Fri, 26 Oct 2018 15:06:39 -0700 Subject: mm: workingset: add vmstat counter for shadow nodes Make it easier to catch bugs in the shadow node shrinker by adding a counter for the shadow nodes in circulation. [akpm@linux-foundation.org: assert that irqs are disabled, for __inc_lruvec_page_state()] [akpm@linux-foundation.org: s/WARN_ON_ONCE/VM_WARN_ON_ONCE/, per Johannes] Link: http://lkml.kernel.org/r/20181009184732.762-4-hannes@cmpxchg.org Signed-off-by: Johannes Weiner Reviewed-by: Andrew Morton Acked-by: Peter Zijlstra (Intel) Cc: Rik van Riel Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 1 + mm/vmstat.c | 1 + mm/workingset.c | 14 ++++++++++++-- 3 files changed, 14 insertions(+), 2 deletions(-) (limited to 'mm') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index ba51d5bf7af1..9f0caccd5833 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -161,6 +161,7 @@ enum node_stat_item { NR_SLAB_UNRECLAIMABLE, NR_ISOLATED_ANON, /* Temporary isolated pages from anon lru */ NR_ISOLATED_FILE, /* Temporary isolated pages from file lru */ + WORKINGSET_NODES, WORKINGSET_REFAULT, WORKINGSET_ACTIVATE, WORKINGSET_RESTORE, diff --git a/mm/vmstat.c b/mm/vmstat.c index d918f6192d15..dab53430f63c 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -1143,6 +1143,7 @@ const char * const vmstat_text[] = { "nr_slab_unreclaimable", "nr_isolated_anon", "nr_isolated_file", + "workingset_nodes", "workingset_refault", "workingset_activate", "workingset_restore", diff --git a/mm/workingset.c b/mm/workingset.c index 5a72c9d5e195..7e6ef312cea5 100644 --- a/mm/workingset.c +++ b/mm/workingset.c @@ -377,12 +377,20 @@ void workingset_update_node(struct radix_tree_node *node) * already where they should be. The list_empty() test is safe * as node->private_list is protected by the i_pages lock. */ + VM_WARN_ON_ONCE(!irqs_disabled()); /* For __inc_lruvec_page_state */ + if (node->count && node->count == node->exceptional) { - if (list_empty(&node->private_list)) + if (list_empty(&node->private_list)) { list_lru_add(&shadow_nodes, &node->private_list); + __inc_lruvec_page_state(virt_to_page(node), + WORKINGSET_NODES); + } } else { - if (!list_empty(&node->private_list)) + if (!list_empty(&node->private_list)) { list_lru_del(&shadow_nodes, &node->private_list); + __dec_lruvec_page_state(virt_to_page(node), + WORKINGSET_NODES); + } } } @@ -473,6 +481,8 @@ static enum lru_status shadow_lru_isolate(struct list_head *item, } list_lru_isolate(lru, item); + __dec_lruvec_page_state(virt_to_page(node), WORKINGSET_NODES); + spin_unlock(lru_lock); /* -- cgit v1.2.3 From 4b85afbdacd290c7a22c96df40a6433fdcacb509 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Fri, 26 Oct 2018 15:06:42 -0700 Subject: mm: zero-seek shrinkers The page cache and most shrinkable slab caches hold data that has been read from disk, but there are some caches that only cache CPU work, such as the dentry and inode caches of procfs and sysfs, as well as the subset of radix tree nodes that track non-resident page cache. Currently, all these are shrunk at the same rate: using DEFAULT_SEEKS for the shrinker's seeks setting tells the reclaim algorithm that for every two page cache pages scanned it should scan one slab object. This is a bogus setting. A virtual inode that required no IO to create is not twice as valuable as a page cache page; shadow cache entries with eviction distances beyond the size of memory aren't either. In most cases, the behavior in practice is still fine. Such virtual caches don't tend to grow and assert themselves aggressively, and usually get picked up before they cause problems. But there are scenarios where that's not true. Our database workloads suffer from two of those. For one, their file workingset is several times bigger than available memory, which has the kernel aggressively create shadow page cache entries for the non-resident parts of it. The workingset code does tell the VM that most of these are expendable, but the VM ends up balancing them 2:1 to cache pages as per the seeks setting. This is a huge waste of memory. These workloads also deal with tens of thousands of open files and use /proc for introspection, which ends up growing the proc_inode_cache to absurdly large sizes - again at the cost of valuable cache space, which isn't a reasonable trade-off, given that proc inodes can be re-created without involving the disk. This patch implements a "zero-seek" setting for shrinkers that results in a target ratio of 0:1 between their objects and IO-backed caches. This allows such virtual caches to grow when memory is available (they do cache/avoid CPU work after all), but effectively disables them as soon as IO-backed objects are under pressure. It then switches the shrinkers for procfs and sysfs metadata, as well as excess page cache shadow nodes, to the new zero-seek setting. Link: http://lkml.kernel.org/r/20181009184732.762-5-hannes@cmpxchg.org Signed-off-by: Johannes Weiner Reported-by: Domas Mituzas Reviewed-by: Andrew Morton Reviewed-by: Rik van Riel Acked-by: Peter Zijlstra (Intel) Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/kernfs/mount.c | 3 +++ fs/proc/inode.c | 3 +++ mm/vmscan.c | 15 ++++++++++++--- mm/workingset.c | 2 +- 4 files changed, 19 insertions(+), 4 deletions(-) (limited to 'mm') diff --git a/fs/kernfs/mount.c b/fs/kernfs/mount.c index ff2716f9322e..fdf527b6d79c 100644 --- a/fs/kernfs/mount.c +++ b/fs/kernfs/mount.c @@ -236,6 +236,9 @@ static int kernfs_fill_super(struct super_block *sb, unsigned long magic) sb->s_export_op = &kernfs_export_ops; sb->s_time_gran = 1; + /* sysfs dentries and inodes don't require IO to create */ + sb->s_shrink.seeks = 0; + /* get root inode, initialize and unlock it */ mutex_lock(&kernfs_mutex); inode = kernfs_get_inode(sb, info->root->kn); diff --git a/fs/proc/inode.c b/fs/proc/inode.c index fc5306a31a1d..5792f9e39466 100644 --- a/fs/proc/inode.c +++ b/fs/proc/inode.c @@ -516,6 +516,9 @@ int proc_fill_super(struct super_block *s, void *data, int silent) */ s->s_stack_depth = FILESYSTEM_MAX_STACK_DEPTH; + /* procfs dentries and inodes don't require IO to create */ + s->s_shrink.seeks = 0; + pde_get(&proc_root); root_inode = proc_get_inode(s, &proc_root); if (!root_inode) { diff --git a/mm/vmscan.c b/mm/vmscan.c index 8ea87586925e..28c9ae5633b9 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -474,9 +474,18 @@ static unsigned long do_shrink_slab(struct shrink_control *shrinkctl, nr = atomic_long_xchg(&shrinker->nr_deferred[nid], 0); total_scan = nr; - delta = freeable >> priority; - delta *= 4; - do_div(delta, shrinker->seeks); + if (shrinker->seeks) { + delta = freeable >> priority; + delta *= 4; + do_div(delta, shrinker->seeks); + } else { + /* + * These objects don't require any IO to create. Trim + * them aggressively under memory pressure to keep + * them from causing refetches in the IO caches. + */ + delta = freeable / 2; + } /* * Make sure we apply some minimal pressure on default priority diff --git a/mm/workingset.c b/mm/workingset.c index 7e6ef312cea5..cbc13d4dfa79 100644 --- a/mm/workingset.c +++ b/mm/workingset.c @@ -534,7 +534,7 @@ static unsigned long scan_shadow_nodes(struct shrinker *shrinker, static struct shrinker workingset_shadow_shrinker = { .count_objects = count_shadow_nodes, .scan_objects = scan_shadow_nodes, - .seeks = DEFAULT_SEEKS, + .seeks = 0, /* ->count reports only fully expendable nodes */ .flags = SHRINKER_NUMA_AWARE | SHRINKER_MEMCG_AWARE, }; -- cgit v1.2.3 From e9b257ed150c1f43912bd66031185598451f68a9 Mon Sep 17 00:00:00 2001 From: Johannes Weiner Date: Fri, 26 Oct 2018 15:06:45 -0700 Subject: mm/memcontrol.c: fix memory.stat item ordering The refault stats go better with the page fault stats, and are of higher interest than the stats on LRU operations. In fact they used to be grouped together; when the LRU operation stats were added later on, they were wedged in between. Move them back together. Documentation/admin-guide/cgroup-v2.rst already lists them in the right order. Link: http://lkml.kernel.org/r/20181010140239.GA2527@cmpxchg.org Signed-off-by: Johannes Weiner Cc: Rik van Riel Cc: Michal Hocko Cc: Peter Zijlstra (Intel) Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memcontrol.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) (limited to 'mm') diff --git a/mm/memcontrol.c b/mm/memcontrol.c index fcec9b39e2a3..0e9ede617b89 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -5597,6 +5597,13 @@ static int memory_stat_show(struct seq_file *m, void *v) seq_printf(m, "pgfault %lu\n", acc.events[PGFAULT]); seq_printf(m, "pgmajfault %lu\n", acc.events[PGMAJFAULT]); + seq_printf(m, "workingset_refault %lu\n", + acc.stat[WORKINGSET_REFAULT]); + seq_printf(m, "workingset_activate %lu\n", + acc.stat[WORKINGSET_ACTIVATE]); + seq_printf(m, "workingset_nodereclaim %lu\n", + acc.stat[WORKINGSET_NODERECLAIM]); + seq_printf(m, "pgrefill %lu\n", acc.events[PGREFILL]); seq_printf(m, "pgscan %lu\n", acc.events[PGSCAN_KSWAPD] + acc.events[PGSCAN_DIRECT]); @@ -5607,13 +5614,6 @@ static int memory_stat_show(struct seq_file *m, void *v) seq_printf(m, "pglazyfree %lu\n", acc.events[PGLAZYFREE]); seq_printf(m, "pglazyfreed %lu\n", acc.events[PGLAZYFREED]); - seq_printf(m, "workingset_refault %lu\n", - acc.stat[WORKINGSET_REFAULT]); - seq_printf(m, "workingset_activate %lu\n", - acc.stat[WORKINGSET_ACTIVATE]); - seq_printf(m, "workingset_nodereclaim %lu\n", - acc.stat[WORKINGSET_NODERECLAIM]); - return 0; } -- cgit v1.2.3 From 2c029a1ea3aac296cd5b47584a579defcc4b4aa0 Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Fri, 26 Oct 2018 15:06:49 -0700 Subject: mm, page_alloc: drop should_suppress_show_mem should_suppress_show_mem() was introduced to reduce the overhead of show_mem on large NUMA systems. Things have changed since then though. Namely c78e93630d15 ("mm: do not walk all of system memory during show_mem") has reduced the overhead considerably. Moreover warn_alloc_show_mem clears SHOW_MEM_FILTER_NODES when called from the IRQ context already so we are not printing per node stats. Remove should_suppress_show_mem because we are losing potentially interesting information about allocation failures. We have seen a bug report where system gets unresponsive under memory pressure and there is only kernel: [2032243.696888] qlge 0000:8b:00.1 ql1: Could not get a page chunk, i=8, clean_idx =200 . kernel: [2032243.710725] swapper/7: page allocation failure: order:1, mode:0x1084120(GFP_ATOMIC|__GFP_COLD|__GFP_COMP) without an additional information for debugging. It would be great to see the state of the page allocator at the moment. Link: http://lkml.kernel.org/r/20180907114334.7088-1-mhocko@kernel.org Signed-off-by: Michal Hocko Acked-by: Vlastimil Babka Cc: David Rientjes Cc: Mel Gorman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/page_alloc.c | 16 +--------------- 1 file changed, 1 insertion(+), 15 deletions(-) (limited to 'mm') diff --git a/mm/page_alloc.c b/mm/page_alloc.c index f97b5a1700a4..eb6c50cc8880 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -3367,26 +3367,12 @@ try_this_zone: return NULL; } -/* - * Large machines with many possible nodes should not always dump per-node - * meminfo in irq context. - */ -static inline bool should_suppress_show_mem(void) -{ - bool ret = false; - -#if NODES_SHIFT > 8 - ret = in_interrupt(); -#endif - return ret; -} - static void warn_alloc_show_mem(gfp_t gfp_mask, nodemask_t *nodemask) { unsigned int filter = SHOW_MEM_FILTER_NODES; static DEFINE_RATELIMIT_STATE(show_mem_rs, HZ, 1); - if (should_suppress_show_mem() || !__ratelimit(&show_mem_rs)) + if (!__ratelimit(&show_mem_rs)) return; /* -- cgit v1.2.3 From c3df29d13044d885695067fa0b1386824942557a Mon Sep 17 00:00:00 2001 From: YueHaibing Date: Fri, 26 Oct 2018 15:06:53 -0700 Subject: mm/swap.c: remove duplicated include Remove duplicated include linux/memremap.h Link: http://lkml.kernel.org/r/20180917131308.16420-1-yuehaibing@huawei.com Signed-off-by: YueHaibing Reviewed-by: Andrew Morton Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/swap.c | 1 - 1 file changed, 1 deletion(-) (limited to 'mm') diff --git a/mm/swap.c b/mm/swap.c index 26fc9b5f1b6c..87a54c8dee34 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -29,7 +29,6 @@ #include #include #include -#include #include #include #include -- cgit v1.2.3 From dedf2c73b80b4566dfcae8ebe9ed46a38b63a1f9 Mon Sep 17 00:00:00 2001 From: zhong jiang Date: Fri, 26 Oct 2018 15:06:57 -0700 Subject: mm/mempolicy.c: use match_string() helper to simplify the code match_string() returns the index of an array for a matching string, which can be used intead of open coded implementation. Link: http://lkml.kernel.org/r/1536988365-50310-1-git-send-email-zhongjiang@huawei.com Signed-off-by: zhong jiang Reviewed-by: Andrew Morton Acked-by: Michal Hocko Cc: Vlastimil Babka Cc: Andrey Ryabinin Cc: Andrea Arcangeli Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/mempolicy.c | 11 +++-------- 1 file changed, 3 insertions(+), 8 deletions(-) (limited to 'mm') diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 2e76a8f65e94..cfd26d7e61a1 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -2711,12 +2711,11 @@ static const char * const policy_modes[] = int mpol_parse_str(char *str, struct mempolicy **mpol) { struct mempolicy *new = NULL; - unsigned short mode; unsigned short mode_flags; nodemask_t nodes; char *nodelist = strchr(str, ':'); char *flags = strchr(str, '='); - int err = 1; + int err = 1, mode; if (nodelist) { /* NUL-terminate mode or flags string */ @@ -2731,12 +2730,8 @@ int mpol_parse_str(char *str, struct mempolicy **mpol) if (flags) *flags++ = '\0'; /* terminate mode string */ - for (mode = 0; mode < MPOL_MAX; mode++) { - if (!strcmp(str, policy_modes[mode])) { - break; - } - } - if (mode >= MPOL_MAX) + mode = match_string(policy_modes, MPOL_MAX, str); + if (mode < 0) goto out; switch (mode) { -- cgit v1.2.3 From 52414d3302577bb60e4ba3c21b7957da7c7a8d21 Mon Sep 17 00:00:00 2001 From: Andrey Ryabinin Date: Fri, 26 Oct 2018 15:07:00 -0700 Subject: kvfree(): fix misleading comment vfree() might sleep if called not in interrupt context. So does kvfree() too. Fix misleading kvfree()'s comment about allowed context. Link: http://lkml.kernel.org/r/20180914130512.10394-1-aryabinin@virtuozzo.com Fixes: 04b8e946075d ("mm/util.c: improve kvfree() kerneldoc") Signed-off-by: Andrey Ryabinin Reviewed-by: Andrew Morton Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/util.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'mm') diff --git a/mm/util.c b/mm/util.c index f740754f5012..8bf08b5b5760 100644 --- a/mm/util.c +++ b/mm/util.c @@ -435,7 +435,7 @@ EXPORT_SYMBOL(kvmalloc_node); * It is slightly more efficient to use kfree() or vfree() if you are certain * that you know which one to use. * - * Context: Any context except NMI. + * Context: Either preemptible task context or not-NMI interrupt. */ void kvfree(const void *addr) { -- cgit v1.2.3 From 3ca4ea3a7a78a243ee9edf71a2736bc8fb26d70f Mon Sep 17 00:00:00 2001 From: Andrey Ryabinin Date: Fri, 26 Oct 2018 15:07:03 -0700 Subject: mm/vmalloc.c: improve vfree() kerneldoc vfree() might sleep if called not in interrupt context. Explain that in the comment. Link: http://lkml.kernel.org/r/20180914130512.10394-2-aryabinin@virtuozzo.com Signed-off-by: Andrey Ryabinin Reviewed-by: Andrew Morton Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/vmalloc.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'mm') diff --git a/mm/vmalloc.c b/mm/vmalloc.c index a728fc492557..d00d42d6bf79 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -1577,6 +1577,8 @@ void vfree_atomic(const void *addr) * have CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG, but making the calling * conventions for vfree() arch-depenedent would be a really bad idea) * + * May sleep if called *not* from interrupt context. + * * NOTE: assumes that the object at @addr has a size >= sizeof(llist_node) */ void vfree(const void *addr) -- cgit v1.2.3 From a8dda165ec34fac2b4119654330150e2c896e531 Mon Sep 17 00:00:00 2001 From: Andrey Ryabinin Date: Fri, 26 Oct 2018 15:07:07 -0700 Subject: vfree: add debug might_sleep() Add might_sleep() call to vfree() to catch potential sleep-in-atomic bugs earlier. [aryabinin@virtuozzo.com: drop might_sleep_if() from kvfree()] Link: http://lkml.kernel.org/r/7e19e4df-b1a6-29bd-9ae7-0266d50bef1d@virtuozzo.com Link: http://lkml.kernel.org/r/20180914130512.10394-3-aryabinin@virtuozzo.com Signed-off-by: Andrey Ryabinin Reviewed-by: Andrew Morton Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/vmalloc.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'mm') diff --git a/mm/vmalloc.c b/mm/vmalloc.c index d00d42d6bf79..97d4b25d0373 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -1587,6 +1587,8 @@ void vfree(const void *addr) kmemleak_free(addr); + might_sleep_if(!in_interrupt()); + if (!addr) return; if (unlikely(in_interrupt())) -- cgit v1.2.3 From dd2283f2605e3b3e9c61bcae844b34f2afa4813f Mon Sep 17 00:00:00 2001 From: Yang Shi Date: Fri, 26 Oct 2018 15:07:11 -0700 Subject: mm: mmap: zap pages with read mmap_sem in munmap Patch series "mm: zap pages with read mmap_sem in munmap for large mapping", v11. Background: Recently, when we ran some vm scalability tests on machines with large memory, we ran into a couple of mmap_sem scalability issues when unmapping large memory space, please refer to https://lkml.org/lkml/2017/12/14/733 and https://lkml.org/lkml/2018/2/20/576. History: Then akpm suggested to unmap large mapping section by section and drop mmap_sem at a time to mitigate it (see https://lkml.org/lkml/2018/3/6/784). V1 patch series was submitted to the mailing list per Andrew's suggestion (see https://lkml.org/lkml/2018/3/20/786). Then I received a lot great feedback and suggestions. Then this topic was discussed on LSFMM summit 2018. In the summit, Michal Hocko suggested (also in the v1 patches review) to try "two phases" approach. Zapping pages with read mmap_sem, then doing via cleanup with write mmap_sem (for discussion detail, see https://lwn.net/Articles/753269/) Approach: Zapping pages is the most time consuming part, according to the suggestion from Michal Hocko [1], zapping pages can be done with holding read mmap_sem, like what MADV_DONTNEED does. Then re-acquire write mmap_sem to cleanup vmas. But, we can't call MADV_DONTNEED directly, since there are two major drawbacks: * The unexpected state from PF if it wins the race in the middle of munmap. It may return zero page, instead of the content or SIGSEGV. * Can't handle VM_LOCKED | VM_HUGETLB | VM_PFNMAP and uprobe mappings, which is a showstopper from akpm But, some part may need write mmap_sem, for example, vma splitting. So, the design is as follows: acquire write mmap_sem lookup vmas (find and split vmas) deal with special mappings detach vmas downgrade_write zap pages free page tables release mmap_sem The vm events with read mmap_sem may come in during page zapping, but since vmas have been detached before, they, i.e. page fault, gup, etc, will not be able to find valid vma, then just return SIGSEGV or -EFAULT as expected. If the vma has VM_HUGETLB | VM_PFNMAP, they are considered as special mappings. They will be handled by falling back to regular do_munmap() with exclusive mmap_sem held in this patch since they may update vm flags. But, with the "detach vmas first" approach, the vmas have been detached when vm flags are updated, so it sounds safe to update vm flags with read mmap_sem for this specific case. So, VM_HUGETLB and VM_PFNMAP will be handled by using the optimized path in the following separate patches for bisectable sake. Unmapping uprobe areas may need update mm flags (MMF_RECALC_UPROBES). However it is fine to have false-positive MMF_RECALC_UPROBES according to uprobes developer. So, uprobe unmap will not be handled by the regular path. With the "detach vmas first" approach we don't have to re-acquire mmap_sem again to clean up vmas to avoid race window which might get the address space changed since downgrade_write() doesn't release the lock to lead regression, which simply downgrades to read lock. And, since the lock acquire/release cost is managed to the minimum and almost as same as before, the optimization could be extended to any size of mapping without incurring significant penalty to small mappings. For the time being, just do this in munmap syscall path. Other vm_munmap() or do_munmap() call sites (i.e mmap, mremap, etc) remain intact due to some implementation difficulties since they acquire write mmap_sem from very beginning and hold it until the end, do_munmap() might be called in the middle. But, the optimized do_munmap would like to be called without mmap_sem held so that we can do the optimization. So, if we want to do the similar optimization for mmap/mremap path, I'm afraid we would have to redesign them. mremap might be called on very large area depending on the usecases, the optimization to it will be considered in the future. This patch (of 3): When running some mmap/munmap scalability tests with large memory (i.e. > 300GB), the below hung task issue may happen occasionally. INFO: task ps:14018 blocked for more than 120 seconds. Tainted: G E 4.9.79-009.ali3000.alios7.x86_64 #1 "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. ps D 0 14018 1 0x00000004 ffff885582f84000 ffff885e8682f000 ffff880972943000 ffff885ebf499bc0 ffff8828ee120000 ffffc900349bfca8 ffffffff817154d0 0000000000000040 00ffffff812f872a ffff885ebf499bc0 024000d000948300 ffff880972943000 Call Trace: [] ? __schedule+0x250/0x730 [] schedule+0x36/0x80 [] rwsem_down_read_failed+0xf0/0x150 [] call_rwsem_down_read_failed+0x18/0x30 [] down_read+0x20/0x40 [] proc_pid_cmdline_read+0xd9/0x4e0 [] ? do_filp_open+0xa5/0x100 [] __vfs_read+0x37/0x150 [] ? security_file_permission+0x9b/0xc0 [] vfs_read+0x96/0x130 [] SyS_read+0x55/0xc0 [] entry_SYSCALL_64_fastpath+0x1a/0xc5 It is because munmap holds mmap_sem exclusively from very beginning to all the way down to the end, and doesn't release it in the middle. When unmapping large mapping, it may take long time (take ~18 seconds to unmap 320GB mapping with every single page mapped on an idle machine). Zapping pages is the most time consuming part, according to the suggestion from Michal Hocko [1], zapping pages can be done with holding read mmap_sem, like what MADV_DONTNEED does. Then re-acquire write mmap_sem to cleanup vmas. But, some part may need write mmap_sem, for example, vma splitting. So, the design is as follows: acquire write mmap_sem lookup vmas (find and split vmas) deal with special mappings detach vmas downgrade_write zap pages free page tables release mmap_sem The vm events with read mmap_sem may come in during page zapping, but since vmas have been detached before, they, i.e. page fault, gup, etc, will not be able to find valid vma, then just return SIGSEGV or -EFAULT as expected. If the vma has VM_HUGETLB | VM_PFNMAP, they are considered as special mappings. They will be handled by without downgrading mmap_sem in this patch since they may update vm flags. But, with the "detach vmas first" approach, the vmas have been detached when vm flags are updated, so it sounds safe to update vm flags with read mmap_sem for this specific case. So, VM_HUGETLB and VM_PFNMAP will be handled by using the optimized path in the following separate patches for bisectable sake. Unmapping uprobe areas may need update mm flags (MMF_RECALC_UPROBES). However it is fine to have false-positive MMF_RECALC_UPROBES according to uprobes developer. With the "detach vmas first" approach we don't have to re-acquire mmap_sem again to clean up vmas to avoid race window which might get the address space changed since downgrade_write() doesn't release the lock to lead regression, which simply downgrades to read lock. And, since the lock acquire/release cost is managed to the minimum and almost as same as before, the optimization could be extended to any size of mapping without incurring significant penalty to small mappings. For the time being, just do this in munmap syscall path. Other vm_munmap() or do_munmap() call sites (i.e mmap, mremap, etc) remain intact due to some implementation difficulties since they acquire write mmap_sem from very beginning and hold it until the end, do_munmap() might be called in the middle. But, the optimized do_munmap would like to be called without mmap_sem held so that we can do the optimization. So, if we want to do the similar optimization for mmap/mremap path, I'm afraid we would have to redesign them. mremap might be called on very large area depending on the usecases, the optimization to it will be considered in the future. With the patches, exclusive mmap_sem hold time when munmap a 80GB address space on a machine with 32 cores of E5-2680 @ 2.70GHz dropped to us level from second. munmap_test-15002 [008] 594.380138: funcgraph_entry: | __vm_munmap() { munmap_test-15002 [008] 594.380146: funcgraph_entry: !2485684 us | unmap_region(); munmap_test-15002 [008] 596.865836: funcgraph_exit: !2485692 us | } Here the execution time of unmap_region() is used to evaluate the time of holding read mmap_sem, then the remaining time is used with holding exclusive lock. [1] https://lwn.net/Articles/753269/ Link: http://lkml.kernel.org/r/1537376621-51150-2-git-send-email-yang.shi@linux.alibaba.com Signed-off-by: Yang Shi Suggested-by: Michal Hocko Suggested-by: Kirill A. Shutemov Suggested-by: Matthew Wilcox Reviewed-by: Matthew Wilcox Acked-by: Kirill A. Shutemov Acked-by: Vlastimil Babka Cc: Laurent Dufour Cc: Vlastimil Babka Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/mmap.c | 59 ++++++++++++++++++++++++++++++++++++++++++++++++----------- 1 file changed, 48 insertions(+), 11 deletions(-) (limited to 'mm') diff --git a/mm/mmap.c b/mm/mmap.c index f7cd9cb966c0..330f12c17fa1 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -2687,8 +2687,8 @@ int split_vma(struct mm_struct *mm, struct vm_area_struct *vma, * work. This now handles partial unmappings. * Jeremy Fitzhardinge */ -int do_munmap(struct mm_struct *mm, unsigned long start, size_t len, - struct list_head *uf) +static int __do_munmap(struct mm_struct *mm, unsigned long start, size_t len, + struct list_head *uf, bool downgrade) { unsigned long end; struct vm_area_struct *vma, *prev, *last; @@ -2770,25 +2770,47 @@ int do_munmap(struct mm_struct *mm, unsigned long start, size_t len, mm->locked_vm -= vma_pages(tmp); munlock_vma_pages_all(tmp); } + + /* + * Unmapping vmas, which have VM_HUGETLB or VM_PFNMAP, + * need get done with write mmap_sem held since they may + * update vm_flags. + */ + if (downgrade && + (tmp->vm_flags & (VM_HUGETLB | VM_PFNMAP))) + downgrade = false; + tmp = tmp->vm_next; } } - /* - * Remove the vma's, and unmap the actual pages - */ + /* Detach vmas from rbtree */ detach_vmas_to_be_unmapped(mm, vma, prev, end); - unmap_region(mm, vma, prev, start, end); + /* + * mpx unmap needs to be called with mmap_sem held for write. + * It is safe to call it before unmap_region(). + */ arch_unmap(mm, vma, start, end); + if (downgrade) + downgrade_write(&mm->mmap_sem); + + unmap_region(mm, vma, prev, start, end); + /* Fix up all other VM information */ remove_vma_list(mm, vma); - return 0; + return downgrade ? 1 : 0; } -int vm_munmap(unsigned long start, size_t len) +int do_munmap(struct mm_struct *mm, unsigned long start, size_t len, + struct list_head *uf) +{ + return __do_munmap(mm, start, len, uf, false); +} + +static int __vm_munmap(unsigned long start, size_t len, bool downgrade) { int ret; struct mm_struct *mm = current->mm; @@ -2797,17 +2819,32 @@ int vm_munmap(unsigned long start, size_t len) if (down_write_killable(&mm->mmap_sem)) return -EINTR; - ret = do_munmap(mm, start, len, &uf); - up_write(&mm->mmap_sem); + ret = __do_munmap(mm, start, len, &uf, downgrade); + /* + * Returning 1 indicates mmap_sem is downgraded. + * But 1 is not legal return value of vm_munmap() and munmap(), reset + * it to 0 before return. + */ + if (ret == 1) { + up_read(&mm->mmap_sem); + ret = 0; + } else + up_write(&mm->mmap_sem); + userfaultfd_unmap_complete(mm, &uf); return ret; } + +int vm_munmap(unsigned long start, size_t len) +{ + return __vm_munmap(start, len, false); +} EXPORT_SYMBOL(vm_munmap); SYSCALL_DEFINE2(munmap, unsigned long, addr, size_t, len) { profile_munmap(addr); - return vm_munmap(addr, len); + return __vm_munmap(addr, len, true); } -- cgit v1.2.3 From b4cefb36051244bcb5651026d862c332a6cac7df Mon Sep 17 00:00:00 2001 From: Yang Shi Date: Fri, 26 Oct 2018 15:07:15 -0700 Subject: mm: unmap VM_HUGETLB mappings with optimized path When unmapping VM_HUGETLB mappings, vm flags need to be updated. Since the vmas have been detached, so it sounds safe to update vm flags with read mmap_sem. Link: http://lkml.kernel.org/r/1537376621-51150-3-git-send-email-yang.shi@linux.alibaba.com Signed-off-by: Yang Shi Reviewed-by: Matthew Wilcox Acked-by: Kirill A. Shutemov Acked-by: Vlastimil Babka Cc: Michal Hocko Cc: Vlastimil Babka Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/mmap.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'mm') diff --git a/mm/mmap.c b/mm/mmap.c index 330f12c17fa1..ea3188bcc9b4 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -2777,7 +2777,7 @@ static int __do_munmap(struct mm_struct *mm, unsigned long start, size_t len, * update vm_flags. */ if (downgrade && - (tmp->vm_flags & (VM_HUGETLB | VM_PFNMAP))) + (tmp->vm_flags & VM_PFNMAP)) downgrade = false; tmp = tmp->vm_next; -- cgit v1.2.3 From cb4922496ae40a775a1b17025eaa1060e8991253 Mon Sep 17 00:00:00 2001 From: Yang Shi Date: Fri, 26 Oct 2018 15:07:18 -0700 Subject: mm: unmap VM_PFNMAP mappings with optimized path When unmapping VM_PFNMAP mappings, vm flags need to be updated. Since the vmas have been detached, so it sounds safe to update vm flags with read mmap_sem. Link: http://lkml.kernel.org/r/1537376621-51150-4-git-send-email-yang.shi@linux.alibaba.com Signed-off-by: Yang Shi Reviewed-by: Matthew Wilcox Acked-by: Kirill A. Shutemov Acked-by: Vlastimil Babka Cc: Michal Hocko Cc: Vlastimil Babka Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/mmap.c | 9 --------- 1 file changed, 9 deletions(-) (limited to 'mm') diff --git a/mm/mmap.c b/mm/mmap.c index ea3188bcc9b4..58e323c92c8e 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -2771,15 +2771,6 @@ static int __do_munmap(struct mm_struct *mm, unsigned long start, size_t len, munlock_vma_pages_all(tmp); } - /* - * Unmapping vmas, which have VM_HUGETLB or VM_PFNMAP, - * need get done with write mmap_sem held since they may - * update vm_flags. - */ - if (downgrade && - (tmp->vm_flags & VM_PFNMAP)) - downgrade = false; - tmp = tmp->vm_next; } } -- cgit v1.2.3 From 3cb7b121ff4dfbf202845b8ea27d9a437eae210f Mon Sep 17 00:00:00 2001 From: "haiqing.shq" Date: Fri, 26 Oct 2018 15:07:22 -0700 Subject: mm/filemap.c: Use existing variable Use the variable write_len instead of ov_iter_count(from). Link: http://lkml.kernel.org/r/1537375855-2088-1-git-send-email-leviathan0992@gmail.com Signed-off-by: haiqing.shq Reviewed-by: Andrew Morton Cc: Jan Kara Cc: Al Viro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/filemap.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'mm') diff --git a/mm/filemap.c b/mm/filemap.c index 41586009fa42..0b8c6de6d995 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -3027,7 +3027,7 @@ generic_file_direct_write(struct kiocb *iocb, struct iov_iter *from) if (iocb->ki_flags & IOCB_NOWAIT) { /* If there are pages to writeback, return */ if (filemap_range_has_page(inode->i_mapping, pos, - pos + iov_iter_count(from))) + pos + write_len)) return -EAGAIN; } else { written = filemap_write_and_wait_range(mapping, pos, -- cgit v1.2.3 From 83d83612d707c3709e030c745e3df8d4e17bbfa2 Mon Sep 17 00:00:00 2001 From: Oscar Salvador Date: Fri, 26 Oct 2018 15:07:25 -0700 Subject: mm/memory_hotplug.c: spare unnecessary calls to node_set_state In node_states_check_changes_online, we check if the node will have to be set for any of the N_*_MEMORY states after the pages have been onlined. Later on, we perform the activation in node_states_set_node. Currently, in node_states_set_node we set the node to N_MEMORY unconditionally. This means that we call node_set_state for N_MEMORY every time pages go online, but we only need to do it if the node has not yet been set for N_MEMORY. Fix this by checking status_change_nid. Link: http://lkml.kernel.org/r/20180919100819.25518-2-osalvador@techadventures.net Signed-off-by: Oscar Salvador Reviewed-by: Pavel Tatashin Cc: Michal Hocko Cc: Dan Williams Cc: David Hildenbrand Cc: Jonathan Cameron Cc: Cc: Mathieu Malaterre Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memory_hotplug.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'mm') diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 38d94b703e9d..63facfc57224 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -753,7 +753,8 @@ static void node_states_set_node(int node, struct memory_notify *arg) if (arg->status_change_nid_high >= 0) node_set_state(node, N_HIGH_MEMORY); - node_set_state(node, N_MEMORY); + if (arg->status_change_nid >= 0) + node_set_state(node, N_MEMORY); } static void __meminit resize_zone_range(struct zone *zone, unsigned long start_pfn, -- cgit v1.2.3 From cf01f6f5e398a74f00fa9ac490ec98c12e63e4b1 Mon Sep 17 00:00:00 2001 From: Oscar Salvador Date: Fri, 26 Oct 2018 15:07:28 -0700 Subject: mm/memory_hotplug.c: tidy up node_states_clear_node() node_states_clear has the following if statements: if ((N_MEMORY != N_NORMAL_MEMORY) && (arg->status_change_nid_high >= 0)) ... if ((N_MEMORY != N_HIGH_MEMORY) && (arg->status_change_nid >= 0)) ... N_MEMORY can never be equal to neither N_NORMAL_MEMORY nor N_HIGH_MEMORY. Similar problem was found in [1]. Since this is wrong, let us get rid of it. [1] https://patchwork.kernel.org/patch/10579155/ Link: http://lkml.kernel.org/r/20180919100819.25518-4-osalvador@techadventures.net Signed-off-by: Oscar Salvador Reviewed-by: Pavel Tatashin Cc: Dan Williams Cc: David Hildenbrand Cc: Jonathan Cameron Cc: Mathieu Malaterre Cc: Michal Hocko Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memory_hotplug.c | 6 ++---- 1 file changed, 2 insertions(+), 4 deletions(-) (limited to 'mm') diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 63facfc57224..561c44761f95 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1582,12 +1582,10 @@ static void node_states_clear_node(int node, struct memory_notify *arg) if (arg->status_change_nid_normal >= 0) node_clear_state(node, N_NORMAL_MEMORY); - if ((N_MEMORY != N_NORMAL_MEMORY) && - (arg->status_change_nid_high >= 0)) + if (arg->status_change_nid_high >= 0) node_clear_state(node, N_HIGH_MEMORY); - if ((N_MEMORY != N_HIGH_MEMORY) && - (arg->status_change_nid >= 0)) + if (arg->status_change_nid >= 0) node_clear_state(node, N_MEMORY); } -- cgit v1.2.3 From 8efe33f40f3e69ac6069ed46666d2d527ddc2c04 Mon Sep 17 00:00:00 2001 From: Oscar Salvador Date: Fri, 26 Oct 2018 15:07:34 -0700 Subject: mm/memory_hotplug.c: simplify node_states_check_changes_online While looking at node_states_check_changes_online, I stumbled upon some confusing things. Right after entering the function, we find this: if (N_MEMORY == N_NORMAL_MEMORY) zone_last = ZONE_MOVABLE; This is wrong. N_MEMORY cannot really be equal to N_NORMAL_MEMORY. My guess is that this wanted to be something like: if (N_NORMAL_MEMORY == N_HIGH_MEMORY) to check if we have CONFIG_HIGHMEM. Later on, in the CONFIG_HIGHMEM block, we have: if (N_MEMORY == N_HIGH_MEMORY) zone_last = ZONE_MOVABLE; Again, this is wrong, and will never be evaluated to true. Besides removing these wrong if statements, I simplified the function a bit. [osalvador@suse.de: address feedback from Pavel] Link: http://lkml.kernel.org/r/20180921132634.10103-4-osalvador@techadventures.net Link: http://lkml.kernel.org/r/20180919100819.25518-5-osalvador@techadventures.net Signed-off-by: Oscar Salvador Reviewed-by: Pavel Tatashin Cc: Dan Williams Cc: David Hildenbrand Cc: Jonathan Cameron Cc: Mathieu Malaterre Cc: Michal Hocko Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memory_hotplug.c | 57 +++++++---------------------------------------------- 1 file changed, 7 insertions(+), 50 deletions(-) (limited to 'mm') diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 561c44761f95..eadd149eb7bc 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -687,62 +687,19 @@ static void node_states_check_changes_online(unsigned long nr_pages, struct zone *zone, struct memory_notify *arg) { int nid = zone_to_nid(zone); - enum zone_type zone_last = ZONE_NORMAL; - /* - * If we have HIGHMEM or movable node, node_states[N_NORMAL_MEMORY] - * contains nodes which have zones of 0...ZONE_NORMAL, - * set zone_last to ZONE_NORMAL. - * - * If we don't have HIGHMEM nor movable node, - * node_states[N_NORMAL_MEMORY] contains nodes which have zones of - * 0...ZONE_MOVABLE, set zone_last to ZONE_MOVABLE. - */ - if (N_MEMORY == N_NORMAL_MEMORY) - zone_last = ZONE_MOVABLE; + arg->status_change_nid = -1; + arg->status_change_nid_normal = -1; + arg->status_change_nid_high = -1; - /* - * if the memory to be online is in a zone of 0...zone_last, and - * the zones of 0...zone_last don't have memory before online, we will - * need to set the node to node_states[N_NORMAL_MEMORY] after - * the memory is online. - */ - if (zone_idx(zone) <= zone_last && !node_state(nid, N_NORMAL_MEMORY)) + if (!node_state(nid, N_MEMORY)) + arg->status_change_nid = nid; + if (zone_idx(zone) <= ZONE_NORMAL && !node_state(nid, N_NORMAL_MEMORY)) arg->status_change_nid_normal = nid; - else - arg->status_change_nid_normal = -1; - #ifdef CONFIG_HIGHMEM - /* - * If we have movable node, node_states[N_HIGH_MEMORY] - * contains nodes which have zones of 0...ZONE_HIGHMEM, - * set zone_last to ZONE_HIGHMEM. - * - * If we don't have movable node, node_states[N_NORMAL_MEMORY] - * contains nodes which have zones of 0...ZONE_MOVABLE, - * set zone_last to ZONE_MOVABLE. - */ - zone_last = ZONE_HIGHMEM; - if (N_MEMORY == N_HIGH_MEMORY) - zone_last = ZONE_MOVABLE; - - if (zone_idx(zone) <= zone_last && !node_state(nid, N_HIGH_MEMORY)) + if (zone_idx(zone) <= N_HIGH_MEMORY && !node_state(nid, N_HIGH_MEMORY)) arg->status_change_nid_high = nid; - else - arg->status_change_nid_high = -1; -#else - arg->status_change_nid_high = arg->status_change_nid_normal; #endif - - /* - * if the node don't have memory befor online, we will need to - * set the node to node_states[N_MEMORY] after the memory - * is online. - */ - if (!node_state(nid, N_MEMORY)) - arg->status_change_nid = nid; - else - arg->status_change_nid = -1; } static void node_states_set_node(int node, struct memory_notify *arg) -- cgit v1.2.3 From 86b27beae59685a42f81bcda9d502b5aebddfab8 Mon Sep 17 00:00:00 2001 From: Oscar Salvador Date: Fri, 26 Oct 2018 15:07:38 -0700 Subject: mm/memory_hotplug.c: clean up node_states_check_changes_offline() This patch, as the previous one, gets rid of the wrong if statements. While at it, I realized that the comments are sometimes very confusing, to say the least, and wrong. For example: ___ zone_last = ZONE_MOVABLE; /* * check whether node_states[N_HIGH_MEMORY] will be changed * If we try to offline the last present @nr_pages from the node, * we can determind we will need to clear the node from * node_states[N_HIGH_MEMORY]. */ for (; zt <= zone_last; zt++) present_pages += pgdat->node_zones[zt].present_pages; if (nr_pages >= present_pages) arg->status_change_nid = zone_to_nid(zone); else arg->status_change_nid = -1; ___ In case the node gets empry, it must be removed from N_MEMORY. We already check N_HIGH_MEMORY a bit above within the CONFIG_HIGHMEM ifdef code. Not to say that status_change_nid is for N_MEMORY, and not for N_HIGH_MEMORY. So I re-wrote some of the comments to what I think is better. [osalvador@suse.de: address feedback from Pavel] Link: http://lkml.kernel.org/r/20180921132634.10103-5-osalvador@techadventures.net Link: http://lkml.kernel.org/r/20180919100819.25518-6-osalvador@techadventures.net Signed-off-by: Oscar Salvador Reviewed-by: Pavel Tatashin Cc: Michal Hocko Cc: Dan Williams Cc: David Hildenbrand Cc: Jonathan Cameron Cc: Cc: Mathieu Malaterre Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memory_hotplug.c | 80 +++++++++++++++++++---------------------------------- 1 file changed, 29 insertions(+), 51 deletions(-) (limited to 'mm') diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index eadd149eb7bc..7e6509a53d79 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1463,75 +1463,53 @@ static void node_states_check_changes_offline(unsigned long nr_pages, { struct pglist_data *pgdat = zone->zone_pgdat; unsigned long present_pages = 0; - enum zone_type zt, zone_last = ZONE_NORMAL; + enum zone_type zt; - /* - * If we have HIGHMEM or movable node, node_states[N_NORMAL_MEMORY] - * contains nodes which have zones of 0...ZONE_NORMAL, - * set zone_last to ZONE_NORMAL. - * - * If we don't have HIGHMEM nor movable node, - * node_states[N_NORMAL_MEMORY] contains nodes which have zones of - * 0...ZONE_MOVABLE, set zone_last to ZONE_MOVABLE. - */ - if (N_MEMORY == N_NORMAL_MEMORY) - zone_last = ZONE_MOVABLE; + arg->status_change_nid = -1; + arg->status_change_nid_normal = -1; + arg->status_change_nid_high = -1; /* - * check whether node_states[N_NORMAL_MEMORY] will be changed. - * If the memory to be offline is in a zone of 0...zone_last, - * and it is the last present memory, 0...zone_last will - * become empty after offline , thus we can determind we will - * need to clear the node from node_states[N_NORMAL_MEMORY]. + * Check whether node_states[N_NORMAL_MEMORY] will be changed. + * If the memory to be offline is within the range + * [0..ZONE_NORMAL], and it is the last present memory there, + * the zones in that range will become empty after the offlining, + * thus we can determine that we need to clear the node from + * node_states[N_NORMAL_MEMORY]. */ - for (zt = 0; zt <= zone_last; zt++) + for (zt = 0; zt <= ZONE_NORMAL; zt++) present_pages += pgdat->node_zones[zt].present_pages; - if (zone_idx(zone) <= zone_last && nr_pages >= present_pages) + if (zone_idx(zone) <= ZONE_NORMAL && nr_pages >= present_pages) arg->status_change_nid_normal = zone_to_nid(zone); - else - arg->status_change_nid_normal = -1; #ifdef CONFIG_HIGHMEM /* - * If we have movable node, node_states[N_HIGH_MEMORY] - * contains nodes which have zones of 0...ZONE_HIGHMEM, - * set zone_last to ZONE_HIGHMEM. - * - * If we don't have movable node, node_states[N_NORMAL_MEMORY] - * contains nodes which have zones of 0...ZONE_MOVABLE, - * set zone_last to ZONE_MOVABLE. + * node_states[N_HIGH_MEMORY] contains nodes which + * have normal memory or high memory. + * Here we add the present_pages belonging to ZONE_HIGHMEM. + * If the zone is within the range of [0..ZONE_HIGHMEM), and + * we determine that the zones in that range become empty, + * we need to clear the node for N_HIGH_MEMORY. */ - zone_last = ZONE_HIGHMEM; - if (N_MEMORY == N_HIGH_MEMORY) - zone_last = ZONE_MOVABLE; - - for (; zt <= zone_last; zt++) - present_pages += pgdat->node_zones[zt].present_pages; - if (zone_idx(zone) <= zone_last && nr_pages >= present_pages) + present_pages += pgdat->node_zones[ZONE_HIGHMEM].present_pages; + if (zone_idx(zone) <= ZONE_HIGHMEM && nr_pages >= present_pages) arg->status_change_nid_high = zone_to_nid(zone); - else - arg->status_change_nid_high = -1; -#else - arg->status_change_nid_high = arg->status_change_nid_normal; #endif /* - * node_states[N_HIGH_MEMORY] contains nodes which have 0...ZONE_MOVABLE + * We have accounted the pages from [0..ZONE_NORMAL), and + * in case of CONFIG_HIGHMEM the pages from ZONE_HIGHMEM + * as well. + * Here we count the possible pages from ZONE_MOVABLE. + * If after having accounted all the pages, we see that the nr_pages + * to be offlined is over or equal to the accounted pages, + * we know that the node will become empty, and so, we can clear + * it for N_MEMORY as well. */ - zone_last = ZONE_MOVABLE; + present_pages += pgdat->node_zones[ZONE_MOVABLE].present_pages; - /* - * check whether node_states[N_HIGH_MEMORY] will be changed - * If we try to offline the last present @nr_pages from the node, - * we can determind we will need to clear the node from - * node_states[N_HIGH_MEMORY]. - */ - for (; zt <= zone_last; zt++) - present_pages += pgdat->node_zones[zt].present_pages; if (nr_pages >= present_pages) arg->status_change_nid = zone_to_nid(zone); - else - arg->status_change_nid = -1; } static void node_states_clear_node(int node, struct memory_notify *arg) -- cgit v1.2.3 From 85cfb245060e45640fa3447f8b0bad5e8bd3bdaf Mon Sep 17 00:00:00 2001 From: Shakeel Butt Date: Fri, 26 Oct 2018 15:07:41 -0700 Subject: memcg: remove memcg_kmem_skip_account The flag memcg_kmem_skip_account was added during the era of opt-out kmem accounting. There is no need for such flag in the opt-in world as there aren't any __GFP_ACCOUNT allocations within memcg_create_cache_enqueue(). Link: http://lkml.kernel.org/r/20180919004501.178023-1-shakeelb@google.com Signed-off-by: Shakeel Butt Acked-by: Johannes Weiner Cc: Michal Hocko Cc: Vladimir Davydov Cc: Greg Thelen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sched.h | 3 --- mm/memcontrol.c | 24 +----------------------- 2 files changed, 1 insertion(+), 26 deletions(-) (limited to 'mm') diff --git a/include/linux/sched.h b/include/linux/sched.h index b8fcc6b3080c..8f8a5418b627 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -724,9 +724,6 @@ struct task_struct { #endif #ifdef CONFIG_MEMCG unsigned in_user_fault:1; -#ifdef CONFIG_MEMCG_KMEM - unsigned memcg_kmem_skip_account:1; -#endif #endif #ifdef CONFIG_COMPAT_BRK unsigned brk_randomized:1; diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 0e9ede617b89..645ede7ad1b2 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -2460,7 +2460,7 @@ static void memcg_kmem_cache_create_func(struct work_struct *w) /* * Enqueue the creation of a per-memcg kmem_cache. */ -static void __memcg_schedule_kmem_cache_create(struct mem_cgroup *memcg, +static void memcg_schedule_kmem_cache_create(struct mem_cgroup *memcg, struct kmem_cache *cachep) { struct memcg_kmem_cache_create_work *cw; @@ -2478,25 +2478,6 @@ static void __memcg_schedule_kmem_cache_create(struct mem_cgroup *memcg, queue_work(memcg_kmem_cache_wq, &cw->work); } -static void memcg_schedule_kmem_cache_create(struct mem_cgroup *memcg, - struct kmem_cache *cachep) -{ - /* - * We need to stop accounting when we kmalloc, because if the - * corresponding kmalloc cache is not yet created, the first allocation - * in __memcg_schedule_kmem_cache_create will recurse. - * - * However, it is better to enclose the whole function. Depending on - * the debugging options enabled, INIT_WORK(), for instance, can - * trigger an allocation. This too, will make us recurse. Because at - * this point we can't allow ourselves back into memcg_kmem_get_cache, - * the safest choice is to do it like this, wrapping the whole function. - */ - current->memcg_kmem_skip_account = 1; - __memcg_schedule_kmem_cache_create(memcg, cachep); - current->memcg_kmem_skip_account = 0; -} - static inline bool memcg_kmem_bypass(void) { if (in_interrupt() || !current->mm || (current->flags & PF_KTHREAD)) @@ -2531,9 +2512,6 @@ struct kmem_cache *memcg_kmem_get_cache(struct kmem_cache *cachep) if (memcg_kmem_bypass()) return cachep; - if (current->memcg_kmem_skip_account) - return cachep; - memcg = get_mem_cgroup_from_current(); kmemcg_id = READ_ONCE(memcg->kmemcg_id); if (kmemcg_id < 0) -- cgit v1.2.3 From f682a97a00591def7cefbb5003dc04045028e405 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Fri, 26 Oct 2018 15:07:45 -0700 Subject: mm: provide kernel parameter to allow disabling page init poisoning Patch series "Address issues slowing persistent memory initialization", v5. The main thing this patch set achieves is that it allows us to initialize each node worth of persistent memory independently. As a result we reduce page init time by about 2 minutes because instead of taking 30 to 40 seconds per node and going through each node one at a time, we process all 4 nodes in parallel in the case of a 12TB persistent memory setup spread evenly over 4 nodes. This patch (of 3): On systems with a large amount of memory it can take a significant amount of time to initialize all of the page structs with the PAGE_POISON_PATTERN value. I have seen it take over 2 minutes to initialize a system with over 12TB of RAM. In order to work around the issue I had to disable CONFIG_DEBUG_VM and then the boot time returned to something much more reasonable as the arch_add_memory call completed in milliseconds versus seconds. However in doing that I had to disable all of the other VM debugging on the system. In order to work around a kernel that might have CONFIG_DEBUG_VM enabled on a system that has a large amount of memory I have added a new kernel parameter named "vm_debug" that can be set to "-" in order to disable it. Link: http://lkml.kernel.org/r/20180925201921.3576.84239.stgit@localhost.localdomain Reviewed-by: Pavel Tatashin Signed-off-by: Alexander Duyck Cc: Dave Hansen Cc: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/admin-guide/kernel-parameters.txt | 12 +++++++ include/linux/page-flags.h | 8 +++++ mm/debug.c | 46 +++++++++++++++++++++++++ mm/memblock.c | 5 ++- mm/sparse.c | 4 +-- 5 files changed, 69 insertions(+), 6 deletions(-) (limited to 'mm') diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt index 8022d902e770..dcd082576e79 100644 --- a/Documentation/admin-guide/kernel-parameters.txt +++ b/Documentation/admin-guide/kernel-parameters.txt @@ -4839,6 +4839,18 @@ This is actually a boot loader parameter; the value is passed to the kernel using a special protocol. + vm_debug[=options] [KNL] Available with CONFIG_DEBUG_VM=y. + May slow down system boot speed, especially when + enabled on systems with a large amount of memory. + All options are enabled by default, and this + interface is meant to allow for selectively + enabling or disabling specific virtual memory + debugging features. + + Available options are: + P Enable page structure init time poisoning + - Disable all of the above options + vmalloc=nn[KMG] [KNL,BOOT] Forces the vmalloc area to have an exact size of . This can be used to increase the minimum size (128MB on x86). It can also be used to diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 4d99504f6496..934f91ef3f54 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -163,6 +163,14 @@ static inline int PagePoisoned(const struct page *page) return page->flags == PAGE_POISON_PATTERN; } +#ifdef CONFIG_DEBUG_VM +void page_init_poison(struct page *page, size_t size); +#else +static inline void page_init_poison(struct page *page, size_t size) +{ +} +#endif + /* * Page flags policies wrt compound pages * diff --git a/mm/debug.c b/mm/debug.c index bd10aad8539a..cdacba12e09a 100644 --- a/mm/debug.c +++ b/mm/debug.c @@ -13,6 +13,7 @@ #include #include #include +#include #include "internal.h" @@ -175,4 +176,49 @@ void dump_mm(const struct mm_struct *mm) ); } +static bool page_init_poisoning __read_mostly = true; + +static int __init setup_vm_debug(char *str) +{ + bool __page_init_poisoning = true; + + /* + * Calling vm_debug with no arguments is equivalent to requesting + * to enable all debugging options we can control. + */ + if (*str++ != '=' || !*str) + goto out; + + __page_init_poisoning = false; + if (*str == '-') + goto out; + + while (*str) { + switch (tolower(*str)) { + case'p': + __page_init_poisoning = true; + break; + default: + pr_err("vm_debug option '%c' unknown. skipped\n", + *str); + } + + str++; + } +out: + if (page_init_poisoning && !__page_init_poisoning) + pr_warn("Page struct poisoning disabled by kernel command line option 'vm_debug'\n"); + + page_init_poisoning = __page_init_poisoning; + + return 1; +} +__setup("vm_debug", setup_vm_debug); + +void page_init_poison(struct page *page, size_t size) +{ + if (page_init_poisoning) + memset(page, PAGE_POISON_PATTERN, size); +} +EXPORT_SYMBOL_GPL(page_init_poison); #endif /* CONFIG_DEBUG_VM */ diff --git a/mm/memblock.c b/mm/memblock.c index 237944479d25..a85315083b5a 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -1444,10 +1444,9 @@ void * __init memblock_virt_alloc_try_nid_raw( ptr = memblock_virt_alloc_internal(size, align, min_addr, max_addr, nid); -#ifdef CONFIG_DEBUG_VM if (ptr && size > 0) - memset(ptr, PAGE_POISON_PATTERN, size); -#endif + page_init_poison(ptr, size); + return ptr; } diff --git a/mm/sparse.c b/mm/sparse.c index 10b07eea9a6e..67ad061f7fb8 100644 --- a/mm/sparse.c +++ b/mm/sparse.c @@ -696,13 +696,11 @@ int __meminit sparse_add_one_section(struct pglist_data *pgdat, goto out; } -#ifdef CONFIG_DEBUG_VM /* * Poison uninitialized struct pages in order to catch invalid flags * combinations. */ - memset(memmap, PAGE_POISON_PATTERN, sizeof(struct page) * PAGES_PER_SECTION); -#endif + page_init_poison(memmap, sizeof(struct page) * PAGES_PER_SECTION); section_mark_present(ms); sparse_init_one_section(ms, section_nr, memmap, usemap); -- cgit v1.2.3 From d483da5bc78b86fe4200d2947f193a745f711713 Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Fri, 26 Oct 2018 15:07:48 -0700 Subject: mm: create non-atomic version of SetPageReserved for init use It doesn't make much sense to use the atomic SetPageReserved at init time when we are using memset to clear the memory and manipulating the page flags via simple "&=" and "|=" operations in __init_single_page. This patch adds a non-atomic version __SetPageReserved that can be used during page init and shows about a 10% improvement in initialization times on the systems I have available for testing. On those systems I saw initialization times drop from around 35 seconds to around 32 seconds to initialize a 3TB block of persistent memory. I believe the main advantage of this is that it allows for more compiler optimization as the __set_bit operation can be reordered whereas the atomic version cannot. I tried adding a bit of documentation based on f1dd2cd13c4 ("mm, memory_hotplug: do not associate hotadded memory to zones until online"). Ideally the reserved flag should be set earlier since there is a brief window where the page is initialization via __init_single_page and we have not set the PG_Reserved flag. I'm leaving that for a future patch set as that will require a more significant refactor. Link: http://lkml.kernel.org/r/20180925202018.3576.11607.stgit@localhost.localdomain Signed-off-by: Alexander Duyck Reviewed-by: Pavel Tatashin Acked-by: Michal Hocko Cc: Dave Hansen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/page-flags.h | 1 + mm/page_alloc.c | 9 +++++++-- 2 files changed, 8 insertions(+), 2 deletions(-) (limited to 'mm') diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h index 934f91ef3f54..50ce1bddaf56 100644 --- a/include/linux/page-flags.h +++ b/include/linux/page-flags.h @@ -303,6 +303,7 @@ PAGEFLAG(Foreign, foreign, PF_NO_COMPOUND); PAGEFLAG(Reserved, reserved, PF_NO_COMPOUND) __CLEARPAGEFLAG(Reserved, reserved, PF_NO_COMPOUND) + __SETPAGEFLAG(Reserved, reserved, PF_NO_COMPOUND) PAGEFLAG(SwapBacked, swapbacked, PF_NO_TAIL) __CLEARPAGEFLAG(SwapBacked, swapbacked, PF_NO_TAIL) __SETPAGEFLAG(SwapBacked, swapbacked, PF_NO_TAIL) diff --git a/mm/page_alloc.c b/mm/page_alloc.c index eb6c50cc8880..cee1abf85d72 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1232,7 +1232,12 @@ void __meminit reserve_bootmem_region(phys_addr_t start, phys_addr_t end) /* Avoid false-positive PageTail() */ INIT_LIST_HEAD(&page->lru); - SetPageReserved(page); + /* + * no need for atomic set_bit because the struct + * page is not visible yet so nobody should + * access it yet. + */ + __SetPageReserved(page); } } } @@ -5508,7 +5513,7 @@ not_early: page = pfn_to_page(pfn); __init_single_page(page, pfn, zone, nid); if (context == MEMMAP_HOTPLUG) - SetPageReserved(page); + __SetPageReserved(page); /* * Mark the block movable so that blocks are reserved for -- cgit v1.2.3 From 966cf44f637e6aeea7e3d01ba004bf8b5beac78f Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Fri, 26 Oct 2018 15:07:52 -0700 Subject: mm: defer ZONE_DEVICE page initialization to the point where we init pgmap The ZONE_DEVICE pages were being initialized in two locations. One was with the memory_hotplug lock held and another was outside of that lock. The problem with this is that it was nearly doubling the memory initialization time. Instead of doing this twice, once while holding a global lock and once without, I am opting to defer the initialization to the one outside of the lock. This allows us to avoid serializing the overhead for memory init and we can instead focus on per-node init times. One issue I encountered is that devm_memremap_pages and hmm_devmmem_pages_create were initializing only the pgmap field the same way. One wasn't initializing hmm_data, and the other was initializing it to a poison value. Since this is something that is exposed to the driver in the case of hmm I am opting for a third option and just initializing hmm_data to 0 since this is going to be exposed to unknown third party drivers. [alexander.h.duyck@linux.intel.com: fix reference count for pgmap in devm_memremap_pages] Link: http://lkml.kernel.org/r/20181008233404.1909.37302.stgit@localhost.localdomain Link: http://lkml.kernel.org/r/20180925202053.3576.66039.stgit@localhost.localdomain Signed-off-by: Alexander Duyck Reviewed-by: Pavel Tatashin Tested-by: Dan Williams Cc: Dave Hansen Cc: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 2 ++ kernel/memremap.c | 25 ++++++--------- mm/hmm.c | 12 ++++--- mm/page_alloc.c | 92 ++++++++++++++++++++++++++++++++++++++++++++++++++++-- 4 files changed, 108 insertions(+), 23 deletions(-) (limited to 'mm') diff --git a/include/linux/mm.h b/include/linux/mm.h index 737279bb479c..33228a49d7d2 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -848,6 +848,8 @@ static inline bool is_zone_device_page(const struct page *page) { return page_zonenum(page) == ZONE_DEVICE; } +extern void memmap_init_zone_device(struct zone *, unsigned long, + unsigned long, struct dev_pagemap *); #else static inline bool is_zone_device_page(const struct page *page) { diff --git a/kernel/memremap.c b/kernel/memremap.c index 5b8600d39931..620fc4d2559a 100644 --- a/kernel/memremap.c +++ b/kernel/memremap.c @@ -175,10 +175,10 @@ void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap) struct vmem_altmap *altmap = pgmap->altmap_valid ? &pgmap->altmap : NULL; struct resource *res = &pgmap->res; - unsigned long pfn, pgoff, order; + struct dev_pagemap *conflict_pgmap; pgprot_t pgprot = PAGE_KERNEL; + unsigned long pgoff, order; int error, nid, is_ram; - struct dev_pagemap *conflict_pgmap; align_start = res->start & ~(SECTION_SIZE - 1); align_size = ALIGN(res->start + resource_size(res), SECTION_SIZE) @@ -256,19 +256,14 @@ void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap) if (error) goto err_add_memory; - for_each_device_pfn(pfn, pgmap) { - struct page *page = pfn_to_page(pfn); - - /* - * ZONE_DEVICE pages union ->lru with a ->pgmap back - * pointer. It is a bug if a ZONE_DEVICE page is ever - * freed or placed on a driver-private list. Seed the - * storage with LIST_POISON* values. - */ - list_del(&page->lru); - page->pgmap = pgmap; - percpu_ref_get(pgmap->ref); - } + /* + * Initialization of the pages has been deferred until now in order + * to allow us to do the work while not holding the hotplug lock. + */ + memmap_init_zone_device(&NODE_DATA(nid)->node_zones[ZONE_DEVICE], + align_start >> PAGE_SHIFT, + align_size >> PAGE_SHIFT, pgmap); + percpu_ref_get_many(pgmap->ref, pfn_end(pgmap) - pfn_first(pgmap)); devm_add_action(dev, devm_memremap_pages_release, pgmap); diff --git a/mm/hmm.c b/mm/hmm.c index c968e49f7a0c..774d684fa2b4 100644 --- a/mm/hmm.c +++ b/mm/hmm.c @@ -1024,7 +1024,6 @@ static int hmm_devmem_pages_create(struct hmm_devmem *devmem) resource_size_t key, align_start, align_size, align_end; struct device *device = devmem->device; int ret, nid, is_ram; - unsigned long pfn; align_start = devmem->resource->start & ~(PA_SECTION_SIZE - 1); align_size = ALIGN(devmem->resource->start + @@ -1109,11 +1108,14 @@ static int hmm_devmem_pages_create(struct hmm_devmem *devmem) align_size >> PAGE_SHIFT, NULL); mem_hotplug_done(); - for (pfn = devmem->pfn_first; pfn < devmem->pfn_last; pfn++) { - struct page *page = pfn_to_page(pfn); + /* + * Initialization of the pages has been deferred until now in order + * to allow us to do the work while not holding the hotplug lock. + */ + memmap_init_zone_device(&NODE_DATA(nid)->node_zones[ZONE_DEVICE], + align_start >> PAGE_SHIFT, + align_size >> PAGE_SHIFT, &devmem->pagemap); - page->pgmap = &devmem->pagemap; - } return 0; error_add_memory: diff --git a/mm/page_alloc.c b/mm/page_alloc.c index cee1abf85d72..d73ff2188d72 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -5465,12 +5465,23 @@ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone, if (highest_memmap_pfn < end_pfn - 1) highest_memmap_pfn = end_pfn - 1; +#ifdef CONFIG_ZONE_DEVICE /* * Honor reservation requested by the driver for this ZONE_DEVICE - * memory + * memory. We limit the total number of pages to initialize to just + * those that might contain the memory mapping. We will defer the + * ZONE_DEVICE page initialization until after we have released + * the hotplug lock. */ - if (altmap && start_pfn == altmap->base_pfn) - start_pfn += altmap->reserve; + if (zone == ZONE_DEVICE) { + if (!altmap) + return; + + if (start_pfn == altmap->base_pfn) + start_pfn += altmap->reserve; + end_pfn = altmap->base_pfn + vmem_altmap_offset(altmap); + } +#endif for (pfn = start_pfn; pfn < end_pfn; pfn++) { /* @@ -5537,6 +5548,81 @@ not_early: } } +#ifdef CONFIG_ZONE_DEVICE +void __ref memmap_init_zone_device(struct zone *zone, + unsigned long start_pfn, + unsigned long size, + struct dev_pagemap *pgmap) +{ + unsigned long pfn, end_pfn = start_pfn + size; + struct pglist_data *pgdat = zone->zone_pgdat; + unsigned long zone_idx = zone_idx(zone); + unsigned long start = jiffies; + int nid = pgdat->node_id; + + if (WARN_ON_ONCE(!pgmap || !is_dev_zone(zone))) + return; + + /* + * The call to memmap_init_zone should have already taken care + * of the pages reserved for the memmap, so we can just jump to + * the end of that region and start processing the device pages. + */ + if (pgmap->altmap_valid) { + struct vmem_altmap *altmap = &pgmap->altmap; + + start_pfn = altmap->base_pfn + vmem_altmap_offset(altmap); + size = end_pfn - start_pfn; + } + + for (pfn = start_pfn; pfn < end_pfn; pfn++) { + struct page *page = pfn_to_page(pfn); + + __init_single_page(page, pfn, zone_idx, nid); + + /* + * Mark page reserved as it will need to wait for onlining + * phase for it to be fully associated with a zone. + * + * We can use the non-atomic __set_bit operation for setting + * the flag as we are still initializing the pages. + */ + __SetPageReserved(page); + + /* + * ZONE_DEVICE pages union ->lru with a ->pgmap back + * pointer and hmm_data. It is a bug if a ZONE_DEVICE + * page is ever freed or placed on a driver-private list. + */ + page->pgmap = pgmap; + page->hmm_data = 0; + + /* + * Mark the block movable so that blocks are reserved for + * movable at startup. This will force kernel allocations + * to reserve their blocks rather than leaking throughout + * the address space during boot when many long-lived + * kernel allocations are made. + * + * bitmap is created for zone's valid pfn range. but memmap + * can be created for invalid pages (for alignment) + * check here not to call set_pageblock_migratetype() against + * pfn out of zone. + * + * Please note that MEMMAP_HOTPLUG path doesn't clear memmap + * because this is done early in sparse_add_one_section + */ + if (!(pfn & (pageblock_nr_pages - 1))) { + set_pageblock_migratetype(page, MIGRATE_MOVABLE); + cond_resched(); + } + } + + pr_info("%s initialised, %lu pages in %ums\n", dev_name(pgmap->dev), + size, jiffies_to_msecs(jiffies - start)); +} + +#endif static void __meminit zone_init_free_lists(struct zone *zone) { unsigned int order, t; -- cgit v1.2.3 From d4faa40259b8524a09c1b0fcd38a446db0c0b770 Mon Sep 17 00:00:00 2001 From: Wei Yang Date: Fri, 26 Oct 2018 15:07:55 -0700 Subject: mm: remove unnecessary local variable addr in __get_user_pages_fast() The local variable `addr' in __get_user_pages_fast() is just a shadow of `start'. Since `start' never changes after assignment to `addr', it is fine to replace `start' with it. Also the meaning of [start, end] is more obvious than [addr, end] when passed to gup_pgd_range(). Link: http://lkml.kernel.org/r/20180925021448.20265-1-richard.weiyang@gmail.com Signed-off-by: Wei Yang Reviewed-by: Andrew Morton Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/gup.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'mm') diff --git a/mm/gup.c b/mm/gup.c index 1abc8b4afff6..08eb350e0f35 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -1780,12 +1780,11 @@ bool gup_fast_permitted(unsigned long start, int nr_pages, int write) int __get_user_pages_fast(unsigned long start, int nr_pages, int write, struct page **pages) { - unsigned long addr, len, end; + unsigned long len, end; unsigned long flags; int nr = 0; start &= PAGE_MASK; - addr = start; len = (unsigned long) nr_pages << PAGE_SHIFT; end = start + len; @@ -1807,7 +1806,7 @@ int __get_user_pages_fast(unsigned long start, int nr_pages, int write, if (gup_fast_permitted(start, nr_pages, write)) { local_irq_save(flags); - gup_pgd_range(addr, end, write, pages, &nr); + gup_pgd_range(start, end, write, pages, &nr); local_irq_restore(flags); } -- cgit v1.2.3 From 3c0513243a4a07ebad2d59f3d972bef483818ec6 Mon Sep 17 00:00:00 2001 From: Souptick Joarder Date: Fri, 26 Oct 2018 15:08:47 -0700 Subject: mm/filemap.c: use vmf_error() These codes can be replaced with new inline vmf_error(). Link: http://lkml.kernel.org/r/20180927171411.GA23331@jordon-HP-15-Notebook-PC Signed-off-by: Souptick Joarder Reviewed-by: Andrew Morton Reviewed-by: Jan Kara Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/filemap.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'mm') diff --git a/mm/filemap.c b/mm/filemap.c index 0b8c6de6d995..3968da1f7f5a 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -2596,9 +2596,7 @@ no_cached_page: * system is low on memory, or a problem occurs while trying * to schedule I/O. */ - if (error == -ENOMEM) - return VM_FAULT_OOM; - return VM_FAULT_SIGBUS; + return vmf_error(error); page_not_uptodate: /* -- cgit v1.2.3 From 85a06835f6f1ba79f0f00838ccd5ad840dd1eafb Mon Sep 17 00:00:00 2001 From: Yang Shi Date: Fri, 26 Oct 2018 15:08:50 -0700 Subject: mm: mremap: downgrade mmap_sem to read when shrinking Other than munmap, mremap might be used to shrink memory mapping too. So, it may hold write mmap_sem for long time when shrinking large mapping, as what commit ("mm: mmap: zap pages with read mmap_sem in munmap") described. The mremap() will not manipulate vmas anymore after __do_munmap() call for the mapping shrink use case, so it is safe to downgrade to read mmap_sem. So, the same optimization, which downgrades mmap_sem to read for zapping pages, is also feasible and reasonable to this case. The period of holding exclusive mmap_sem for shrinking large mapping would be reduced significantly with this optimization. MREMAP_FIXED and MREMAP_MAYMOVE are more complicated to adopt this optimization since they need manipulate vmas after do_munmap(), downgrading mmap_sem may create race window. Simple mapping shrink is the low hanging fruit, and it may cover the most cases of unmap with munmap together. [akpm@linux-foundation.org: tweak comment] [yang.shi@linux.alibaba.com: fix unsigned compare against 0 issue] Link: http://lkml.kernel.org/r/1538687672-17795-2-git-send-email-yang.shi@linux.alibaba.com Link: http://lkml.kernel.org/r/1538067582-60038-1-git-send-email-yang.shi@linux.alibaba.com Signed-off-by: Yang Shi Acked-by: Vlastimil Babka Acked-by: Kirill A. Shutemov Cc: Michal Hocko Cc: Matthew Wilcox Cc: Laurent Dufour Cc: Colin Ian King Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 2 ++ mm/mmap.c | 4 ++-- mm/mremap.c | 20 ++++++++++++++++---- 3 files changed, 20 insertions(+), 6 deletions(-) (limited to 'mm') diff --git a/include/linux/mm.h b/include/linux/mm.h index 33228a49d7d2..a023c5ce71fa 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2306,6 +2306,8 @@ extern unsigned long do_mmap(struct file *file, unsigned long addr, unsigned long len, unsigned long prot, unsigned long flags, vm_flags_t vm_flags, unsigned long pgoff, unsigned long *populate, struct list_head *uf); +extern int __do_munmap(struct mm_struct *, unsigned long, size_t, + struct list_head *uf, bool downgrade); extern int do_munmap(struct mm_struct *, unsigned long, size_t, struct list_head *uf); diff --git a/mm/mmap.c b/mm/mmap.c index 58e323c92c8e..1bfd12032664 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -2687,8 +2687,8 @@ int split_vma(struct mm_struct *mm, struct vm_area_struct *vma, * work. This now handles partial unmappings. * Jeremy Fitzhardinge */ -static int __do_munmap(struct mm_struct *mm, unsigned long start, size_t len, - struct list_head *uf, bool downgrade) +int __do_munmap(struct mm_struct *mm, unsigned long start, size_t len, + struct list_head *uf, bool downgrade) { unsigned long end; struct vm_area_struct *vma, *prev, *last; diff --git a/mm/mremap.c b/mm/mremap.c index a9617e72e6b7..7f9f9180e401 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -521,6 +521,7 @@ SYSCALL_DEFINE5(mremap, unsigned long, addr, unsigned long, old_len, unsigned long ret = -EINVAL; unsigned long charged = 0; bool locked = false; + bool downgraded = false; struct vm_userfaultfd_ctx uf = NULL_VM_UFFD_CTX; LIST_HEAD(uf_unmap_early); LIST_HEAD(uf_unmap); @@ -557,12 +558,20 @@ SYSCALL_DEFINE5(mremap, unsigned long, addr, unsigned long, old_len, /* * Always allow a shrinking remap: that just unmaps * the unnecessary pages.. - * do_munmap does all the needed commit accounting + * __do_munmap does all the needed commit accounting, and + * downgrades mmap_sem to read if so directed. */ if (old_len >= new_len) { - ret = do_munmap(mm, addr+new_len, old_len - new_len, &uf_unmap); - if (ret && old_len != new_len) + int retval; + + retval = __do_munmap(mm, addr+new_len, old_len - new_len, + &uf_unmap, true); + if (retval < 0 && old_len != new_len) { + ret = retval; goto out; + /* Returning 1 indicates mmap_sem is downgraded to read. */ + } else if (retval == 1) + downgraded = true; ret = addr; goto out; } @@ -627,7 +636,10 @@ out: vm_unacct_memory(charged); locked = 0; } - up_write(¤t->mm->mmap_sem); + if (downgraded) + up_read(¤t->mm->mmap_sem); + else + up_write(¤t->mm->mmap_sem); if (locked && new_len > old_len) mm_populate(new_addr + old_len, new_len - old_len); userfaultfd_unmap_complete(mm, &uf_unmap_early); -- cgit v1.2.3 From 9bc8039e715da3b53dbac89525323a9f2f69b7b5 Mon Sep 17 00:00:00 2001 From: Yang Shi Date: Fri, 26 Oct 2018 15:08:54 -0700 Subject: mm: brk: downgrade mmap_sem to read when shrinking brk might be used to shrink memory mapping too other than munmap(). So, it may hold write mmap_sem for long time when shrinking large mapping, as what commit ("mm: mmap: zap pages with read mmap_sem in munmap") described. The brk() will not manipulate vmas anymore after __do_munmap() call for the mapping shrink use case. But, it may set mm->brk after __do_munmap(), which needs hold write mmap_sem. However, a simple trick can workaround this by setting mm->brk before __do_munmap(). Then restore the original value if __do_munmap() fails. With this trick, it is safe to downgrade to read mmap_sem. So, the same optimization, which downgrades mmap_sem to read for zapping pages, is also feasible and reasonable to this case. The period of holding exclusive mmap_sem for shrinking large mapping would be reduced significantly with this optimization. [akpm@linux-foundation.org: tweak comment] [yang.shi@linux.alibaba.com: fix unsigned compare against 0 issue] Link: http://lkml.kernel.org/r/1538687672-17795-1-git-send-email-yang.shi@linux.alibaba.com Link: http://lkml.kernel.org/r/1538067582-60038-2-git-send-email-yang.shi@linux.alibaba.com Signed-off-by: Yang Shi Acked-by: Vlastimil Babka Acked-by: Kirill A. Shutemov Cc: Michal Hocko Cc: Matthew Wilcox Cc: Laurent Dufour Cc: Colin Ian King Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/mmap.c | 46 +++++++++++++++++++++++++++++++++++----------- 1 file changed, 35 insertions(+), 11 deletions(-) (limited to 'mm') diff --git a/mm/mmap.c b/mm/mmap.c index 1bfd12032664..6c04292e16a7 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -191,16 +191,19 @@ static int do_brk_flags(unsigned long addr, unsigned long request, unsigned long SYSCALL_DEFINE1(brk, unsigned long, brk) { unsigned long retval; - unsigned long newbrk, oldbrk; + unsigned long newbrk, oldbrk, origbrk; struct mm_struct *mm = current->mm; struct vm_area_struct *next; unsigned long min_brk; bool populate; + bool downgraded = false; LIST_HEAD(uf); if (down_write_killable(&mm->mmap_sem)) return -EINTR; + origbrk = mm->brk; + #ifdef CONFIG_COMPAT_BRK /* * CONFIG_COMPAT_BRK can still be overridden by setting @@ -229,14 +232,32 @@ SYSCALL_DEFINE1(brk, unsigned long, brk) newbrk = PAGE_ALIGN(brk); oldbrk = PAGE_ALIGN(mm->brk); - if (oldbrk == newbrk) - goto set_brk; + if (oldbrk == newbrk) { + mm->brk = brk; + goto success; + } - /* Always allow shrinking brk. */ + /* + * Always allow shrinking brk. + * __do_munmap() may downgrade mmap_sem to read. + */ if (brk <= mm->brk) { - if (!do_munmap(mm, newbrk, oldbrk-newbrk, &uf)) - goto set_brk; - goto out; + int ret; + + /* + * mm->brk must to be protected by write mmap_sem so update it + * before downgrading mmap_sem. When __do_munmap() fails, + * mm->brk will be restored from origbrk. + */ + mm->brk = brk; + ret = __do_munmap(mm, newbrk, oldbrk-newbrk, &uf, true); + if (ret < 0) { + mm->brk = origbrk; + goto out; + } else if (ret == 1) { + downgraded = true; + } + goto success; } /* Check against existing mmap mappings. */ @@ -247,18 +268,21 @@ SYSCALL_DEFINE1(brk, unsigned long, brk) /* Ok, looks good - let it rip. */ if (do_brk_flags(oldbrk, newbrk-oldbrk, 0, &uf) < 0) goto out; - -set_brk: mm->brk = brk; + +success: populate = newbrk > oldbrk && (mm->def_flags & VM_LOCKED) != 0; - up_write(&mm->mmap_sem); + if (downgraded) + up_read(&mm->mmap_sem); + else + up_write(&mm->mmap_sem); userfaultfd_unmap_complete(mm, &uf); if (populate) mm_populate(oldbrk, newbrk - oldbrk); return brk; out: - retval = mm->brk; + retval = origbrk; up_write(&mm->mmap_sem); return retval; } -- cgit v1.2.3 From ff09d7ec9786be4ad7589aa987d7dc66e2dd9160 Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" Date: Fri, 26 Oct 2018 15:09:01 -0700 Subject: mm/memory.c: recheck page table entry with page table lock held We clear the pte temporarily during read/modify/write update of the pte. If we take a page fault while the pte is cleared, the application can get SIGBUS. One such case is with remap_pfn_range without a backing vm_ops->fault callback. do_fault will return SIGBUS in that case. cpu 0 cpu1 mprotect() ptep_modify_prot_start()/pte cleared. . . page fault. . . prep_modify_prot_commit() Fix this by taking page table lock and rechecking for pte_none. [aneesh.kumar@linux.ibm.com: fix crash observed with syzkaller run] Link: http://lkml.kernel.org/r/87va6bwlfg.fsf@linux.ibm.com Link: http://lkml.kernel.org/r/20180926031858.9692-1-aneesh.kumar@linux.ibm.com Signed-off-by: Aneesh Kumar K.V Acked-by: Kirill A. Shutemov Cc: Willem de Bruijn Cc: Eric Dumazet Cc: Ido Schimmel Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memory.c | 34 ++++++++++++++++++++++++++++++---- 1 file changed, 30 insertions(+), 4 deletions(-) (limited to 'mm') diff --git a/mm/memory.c b/mm/memory.c index 6abc74f41bc0..072139579d89 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -3496,10 +3496,36 @@ static vm_fault_t do_fault(struct vm_fault *vmf) struct vm_area_struct *vma = vmf->vma; vm_fault_t ret; - /* The VMA was not fully populated on mmap() or missing VM_DONTEXPAND */ - if (!vma->vm_ops->fault) - ret = VM_FAULT_SIGBUS; - else if (!(vmf->flags & FAULT_FLAG_WRITE)) + /* + * The VMA was not fully populated on mmap() or missing VM_DONTEXPAND + */ + if (!vma->vm_ops->fault) { + /* + * If we find a migration pmd entry or a none pmd entry, which + * should never happen, return SIGBUS + */ + if (unlikely(!pmd_present(*vmf->pmd))) + ret = VM_FAULT_SIGBUS; + else { + vmf->pte = pte_offset_map_lock(vmf->vma->vm_mm, + vmf->pmd, + vmf->address, + &vmf->ptl); + /* + * Make sure this is not a temporary clearing of pte + * by holding ptl and checking again. A R/M/W update + * of pte involves: take ptl, clearing the pte so that + * we don't have concurrent modification by hardware + * followed by an update. + */ + if (unlikely(pte_none(*vmf->pte))) + ret = VM_FAULT_SIGBUS; + else + ret = VM_FAULT_NOPAGE; + + pte_unmap_unlock(vmf->pte, vmf->ptl); + } + } else if (!(vmf->flags & FAULT_FLAG_WRITE)) ret = do_read_fault(vmf); else if (!(vma->vm_flags & VM_SHARED)) ret = do_cow_fault(vmf); -- cgit v1.2.3 From f0ecf25a093fc0589f0a6bc4c1ea068bbb67d220 Mon Sep 17 00:00:00 2001 From: Jann Horn Date: Fri, 26 Oct 2018 15:09:05 -0700 Subject: mm/vmstat.c: assert that vmstat_text is in sync with stat_items_size Having two gigantic arrays that must manually be kept in sync, including ifdefs, isn't exactly robust. To make it easier to catch such issues in the future, add a BUILD_BUG_ON(). Link: http://lkml.kernel.org/r/20181001143138.95119-3-jannh@google.com Signed-off-by: Jann Horn Reviewed-by: Kees Cook Reviewed-by: Andrew Morton Acked-by: Roman Gushchin Acked-by: Michal Hocko Cc: Davidlohr Bueso Cc: Oleg Nesterov Cc: Christoph Lameter Cc: Kemi Wang Cc: Andy Lutomirski Cc: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/vmstat.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'mm') diff --git a/mm/vmstat.c b/mm/vmstat.c index dab53430f63c..6038ce593ce3 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -1665,6 +1665,8 @@ static void *vmstat_start(struct seq_file *m, loff_t *pos) stat_items_size += sizeof(struct vm_event_state); #endif + BUILD_BUG_ON(stat_items_size != + ARRAY_SIZE(vmstat_text) * sizeof(unsigned long)); v = kmalloc(stat_items_size, GFP_KERNEL); m->private = v; if (!v) -- cgit v1.2.3 From 61855f021c3ae2ccc244111e2a321690f9786aed Mon Sep 17 00:00:00 2001 From: "Gustavo A. R. Silva" Date: Fri, 26 Oct 2018 15:09:20 -0700 Subject: mm/zsmalloc.c: fix fall-through annotation Replace "fallthru" with a proper "fall through" annotation. This fix is part of the ongoing efforts to enabling -Wimplicit-fallthrough Link: http://lkml.kernel.org/r/20181003105114.GA24423@embeddedor.com Signed-off-by: Gustavo A. R. Silva Reviewed-by: Sergey Senozhatsky Cc: Minchan Kim Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/zsmalloc.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'mm') diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c index 9da65552e7ca..0787d33b80d8 100644 --- a/mm/zsmalloc.c +++ b/mm/zsmalloc.c @@ -418,7 +418,7 @@ static void *zs_zpool_map(void *pool, unsigned long handle, case ZPOOL_MM_WO: zs_mm = ZS_MM_WO; break; - case ZPOOL_MM_RW: /* fallthru */ + case ZPOOL_MM_RW: /* fall through */ default: zs_mm = ZS_MM_RW; break; -- cgit v1.2.3 From 4a222127f3631e6cdde228e3bb6b599f52b96d14 Mon Sep 17 00:00:00 2001 From: David Rientjes Date: Fri, 26 Oct 2018 15:09:24 -0700 Subject: mm/page_alloc.c: initialize num_movable in move_freepages() If move_freepages_block() returns 0 because !zone_spans_pfn(), *num_movable can hold the value from the stack because it does not get initialized in move_freepages(). Move the initialization to move_freepages_block() to guarantee the value actually makes sense. This currently doesn't affect its only caller where num_movable != NULL, so no bug fix, but just more robust. Link: http://lkml.kernel.org/r/alpine.DEB.2.21.1810051355490.212229@chino.kir.corp.google.com Signed-off-by: David Rientjes Reviewed-by: Andrew Morton Acked-by: Vlastimil Babka Cc: Greg Thelen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/page_alloc.c | 7 +++---- 1 file changed, 3 insertions(+), 4 deletions(-) (limited to 'mm') diff --git a/mm/page_alloc.c b/mm/page_alloc.c index d73ff2188d72..bdb7eb25acf8 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -2021,10 +2021,6 @@ static int move_freepages(struct zone *zone, pfn_valid(page_to_pfn(end_page)) && page_zone(start_page) != page_zone(end_page)); #endif - - if (num_movable) - *num_movable = 0; - for (page = start_page; page <= end_page;) { if (!pfn_valid_within(page_to_pfn(page))) { page++; @@ -2064,6 +2060,9 @@ int move_freepages_block(struct zone *zone, struct page *page, unsigned long start_pfn, end_pfn; struct page *start_page, *end_page; + if (num_movable) + *num_movable = 0; + start_pfn = page_to_pfn(page); start_pfn = start_pfn & ~(pageblock_nr_pages-1); start_page = pfn_to_page(start_pfn); -- cgit v1.2.3 From 1c2d479a119b84feacbe4de782016f1bf1ad16dc Mon Sep 17 00:00:00 2001 From: Kirill Tkhai Date: Fri, 26 Oct 2018 15:09:28 -0700 Subject: mm/memcontrol.c: convert mem_cgroup_id::ref to refcount_t type This will allow to use generic refcount_t interfaces to check counters overflow instead of currently existing VM_BUG_ON(). The only difference after the patch is VM_BUG_ON() may cause BUG(), while refcount_t fires with WARN(). But this seems not to be significant here, since such the problems are usually caught by syzbot with panic-on-warn enabled. Link: http://lkml.kernel.org/r/153910718919.7006.13400779039257185427.stgit@localhost.localdomain Signed-off-by: Kirill Tkhai Reviewed-by: Andrew Morton Acked-by: Michal Hocko Cc: Johannes Weiner Cc: Vladimir Davydov Cc: Andrea Parri Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 2 +- mm/memcontrol.c | 10 ++++------ 2 files changed, 5 insertions(+), 7 deletions(-) (limited to 'mm') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 4399cc3f00e4..7ab2120155a4 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -78,7 +78,7 @@ struct mem_cgroup_reclaim_cookie { struct mem_cgroup_id { int id; - atomic_t ref; + refcount_t ref; }; /* diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 645ede7ad1b2..92d38c88250f 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -4299,14 +4299,12 @@ static void mem_cgroup_id_remove(struct mem_cgroup *memcg) static void mem_cgroup_id_get_many(struct mem_cgroup *memcg, unsigned int n) { - VM_BUG_ON(atomic_read(&memcg->id.ref) <= 0); - atomic_add(n, &memcg->id.ref); + refcount_add(n, &memcg->id.ref); } static void mem_cgroup_id_put_many(struct mem_cgroup *memcg, unsigned int n) { - VM_BUG_ON(atomic_read(&memcg->id.ref) < n); - if (atomic_sub_and_test(n, &memcg->id.ref)) { + if (refcount_sub_and_test(n, &memcg->id.ref)) { mem_cgroup_id_remove(memcg); /* Memcg ID pins CSS */ @@ -4523,7 +4521,7 @@ static int mem_cgroup_css_online(struct cgroup_subsys_state *css) } /* Online state pins memcg ID, memcg ID pins CSS */ - atomic_set(&memcg->id.ref, 1); + refcount_set(&memcg->id.ref, 1); css_get(css); return 0; } @@ -6357,7 +6355,7 @@ subsys_initcall(mem_cgroup_init); #ifdef CONFIG_MEMCG_SWAP static struct mem_cgroup *mem_cgroup_id_get_online(struct mem_cgroup *memcg) { - while (!atomic_inc_not_zero(&memcg->id.ref)) { + while (!refcount_inc_not_zero(&memcg->id.ref)) { /* * The root cgroup cannot be destroyed, so it's refcount must * always be >= 1. -- cgit v1.2.3 From dfb3ccd00a06d71171961022019bb0f210d2cdc1 Mon Sep 17 00:00:00 2001 From: Pavel Tatashin Date: Fri, 26 Oct 2018 15:09:32 -0700 Subject: mm: make memmap_init a proper function MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit memmap_init is sometimes a macro sometimes a function based on __HAVE_ARCH_MEMMAP_INIT. It is only a function on ia64. Make memmap_init a weak function instead, and let ia64 redefine it. Link: http://lkml.kernel.org/r/20180724235520.10200-2-pasha.tatashin@oracle.com Signed-off-by: Pavel Tatashin Reviewed-by: Andrew Morton Reviewed-by: Oscar Salvador Cc: Steven Sistare Cc: Daniel Jordan Cc: Kirill A. Shutemov Cc: Michal Hocko Cc: Dan Williams Cc: Jan Kara Cc: Jérôme Glisse Cc: Souptick Joarder Cc: Baoquan He Cc: Greg Kroah-Hartman Cc: Vlastimil Babka Cc: Wei Yang Cc: Dave Hansen Cc: David Rientjes Cc: Ingo Molnar Cc: Pavel Tatashin Cc: Abdul Haleem Cc: Michael Ellerman Cc: Pasha Tatashin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/ia64/include/asm/pgtable.h | 1 - mm/page_alloc.c | 9 +++++---- 2 files changed, 5 insertions(+), 5 deletions(-) (limited to 'mm') diff --git a/arch/ia64/include/asm/pgtable.h b/arch/ia64/include/asm/pgtable.h index 165827774bea..b1e7468eb65a 100644 --- a/arch/ia64/include/asm/pgtable.h +++ b/arch/ia64/include/asm/pgtable.h @@ -544,7 +544,6 @@ extern struct page *zero_page_memmap_ptr; # ifdef CONFIG_VIRTUAL_MEM_MAP /* arch mem_map init routine is needed due to holes in a virtual mem_map */ -# define __HAVE_ARCH_MEMMAP_INIT extern void memmap_init (unsigned long size, int nid, unsigned long zone, unsigned long start_pfn); # endif /* CONFIG_VIRTUAL_MEM_MAP */ diff --git a/mm/page_alloc.c b/mm/page_alloc.c index bdb7eb25acf8..94725aea672f 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -5631,10 +5631,11 @@ static void __meminit zone_init_free_lists(struct zone *zone) } } -#ifndef __HAVE_ARCH_MEMMAP_INIT -#define memmap_init(size, nid, zone, start_pfn) \ - memmap_init_zone((size), (nid), (zone), (start_pfn), MEMMAP_EARLY, NULL) -#endif +void __meminit __weak memmap_init(unsigned long size, int nid, + unsigned long zone, unsigned long start_pfn) +{ + memmap_init_zone(size, nid, zone, start_pfn, MEMMAP_EARLY, NULL); +} static int zone_batchsize(struct zone *zone) { -- cgit v1.2.3 From d3035be4ce2345d98633a45f93a74e526e94b802 Mon Sep 17 00:00:00 2001 From: Pavel Tatashin Date: Fri, 26 Oct 2018 15:09:37 -0700 Subject: mm: calculate deferred pages after skipping mirrored memory MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit update_defer_init() should be called only when struct page is about to be initialized. Because it counts number of initialized struct pages, but there we may skip struct pages if there is some mirrored memory. So move, update_defer_init() after checking for mirrored memory. Also, rename update_defer_init() to defer_init() and reverse the return boolean to emphasize that this is a boolean function, that tells that the reset of memmap initialization should be deferred. Make this function self-contained: do not pass number of already initialized pages in this zone by using static counters. I found this bug by reading the code. The effect is that fewer than expected struct pages are initialized early in boot, and it is possible that in some corner cases we may fail to boot when mirrored pages are used. The deferred on demand code should somewhat mitigate this. But this still brings some inconsistencies compared to when booting without mirrored pages, so it is better to fix. [pasha.tatashin@oracle.com: add comment about defer_init's lack of locking] Link: http://lkml.kernel.org/r/20180726193509.3326-3-pasha.tatashin@oracle.com [akpm@linux-foundation.org: make defer_init non-inline, __meminit] Link: http://lkml.kernel.org/r/20180724235520.10200-3-pasha.tatashin@oracle.com Signed-off-by: Pavel Tatashin Reviewed-by: Oscar Salvador Cc: Abdul Haleem Cc: Baoquan He Cc: Daniel Jordan Cc: Dan Williams Cc: Dave Hansen Cc: David Rientjes Cc: Greg Kroah-Hartman Cc: Ingo Molnar Cc: Jan Kara Cc: Jérôme Glisse Cc: Kirill A. Shutemov Cc: Michael Ellerman Cc: Michal Hocko Cc: Souptick Joarder Cc: Steven Sistare Cc: Vlastimil Babka Cc: Wei Yang Cc: Pasha Tatashin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/page_alloc.c | 45 +++++++++++++++++++++++++-------------------- 1 file changed, 25 insertions(+), 20 deletions(-) (limited to 'mm') diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 94725aea672f..db1ff4ac0cc6 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -307,24 +307,33 @@ static inline bool __meminit early_page_uninitialised(unsigned long pfn) } /* - * Returns false when the remaining initialisation should be deferred until + * Returns true when the remaining initialisation should be deferred until * later in the boot cycle when it can be parallelised. */ -static inline bool update_defer_init(pg_data_t *pgdat, - unsigned long pfn, unsigned long zone_end, - unsigned long *nr_initialised) +static bool __meminit +defer_init(int nid, unsigned long pfn, unsigned long end_pfn) { + static unsigned long prev_end_pfn, nr_initialised; + + /* + * prev_end_pfn static that contains the end of previous zone + * No need to protect because called very early in boot before smp_init. + */ + if (prev_end_pfn != end_pfn) { + prev_end_pfn = end_pfn; + nr_initialised = 0; + } + /* Always populate low zones for address-constrained allocations */ - if (zone_end < pgdat_end_pfn(pgdat)) - return true; - (*nr_initialised)++; - if ((*nr_initialised > pgdat->static_init_pgcnt) && - (pfn & (PAGES_PER_SECTION - 1)) == 0) { - pgdat->first_deferred_pfn = pfn; + if (end_pfn < pgdat_end_pfn(NODE_DATA(nid))) return false; + nr_initialised++; + if ((nr_initialised > NODE_DATA(nid)->static_init_pgcnt) && + (pfn & (PAGES_PER_SECTION - 1)) == 0) { + NODE_DATA(nid)->first_deferred_pfn = pfn; + return true; } - - return true; + return false; } #else static inline bool early_page_uninitialised(unsigned long pfn) @@ -332,11 +341,9 @@ static inline bool early_page_uninitialised(unsigned long pfn) return false; } -static inline bool update_defer_init(pg_data_t *pgdat, - unsigned long pfn, unsigned long zone_end, - unsigned long *nr_initialised) +static inline bool defer_init(int nid, unsigned long pfn, unsigned long end_pfn) { - return true; + return false; } #endif @@ -5453,9 +5460,7 @@ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone, struct vmem_altmap *altmap) { unsigned long end_pfn = start_pfn + size; - pg_data_t *pgdat = NODE_DATA(nid); unsigned long pfn; - unsigned long nr_initialised = 0; struct page *page; #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP struct memblock_region *r = NULL, *tmp; @@ -5494,8 +5499,6 @@ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone, continue; if (!early_pfn_in_nid(pfn, nid)) continue; - if (!update_defer_init(pgdat, pfn, end_pfn, &nr_initialised)) - break; #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP /* @@ -5518,6 +5521,8 @@ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone, } } #endif + if (defer_init(nid, pfn, end_pfn)) + break; not_early: page = pfn_to_page(pfn); -- cgit v1.2.3 From a9a9e77fbf2784ae2694696eb772419c0a96159e Mon Sep 17 00:00:00 2001 From: Pavel Tatashin Date: Fri, 26 Oct 2018 15:09:40 -0700 Subject: mm: move mirrored memory specific code outside of memmap_init_zone MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit memmap_init_zone, is getting complex, because it is called from different contexts: hotplug, and during boot, and also because it must handle some architecture quirks. One of them is mirrored memory. Move the code that decides whether to skip mirrored memory outside of memmap_init_zone, into a separate function. [pasha.tatashin@oracle.com: uninline overlap_memmap_init()] Link: http://lkml.kernel.org/r/20180726193509.3326-4-pasha.tatashin@oracle.com Link: http://lkml.kernel.org/r/20180724235520.10200-4-pasha.tatashin@oracle.com Signed-off-by: Pavel Tatashin Reviewed-by: Oscar Salvador Cc: Pasha Tatashin Cc: Abdul Haleem Cc: Baoquan He Cc: Daniel Jordan Cc: Dan Williams Cc: Dave Hansen Cc: David Rientjes Cc: Greg Kroah-Hartman Cc: Ingo Molnar Cc: Jan Kara Cc: Jérôme Glisse Cc: Kirill A. Shutemov Cc: Michael Ellerman Cc: Michal Hocko Cc: Souptick Joarder Cc: Steven Sistare Cc: Vlastimil Babka Cc: Wei Yang Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/page_alloc.c | 71 +++++++++++++++++++++++++++------------------------------ 1 file changed, 33 insertions(+), 38 deletions(-) (limited to 'mm') diff --git a/mm/page_alloc.c b/mm/page_alloc.c index db1ff4ac0cc6..c26d3152f9ba 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -5450,6 +5450,30 @@ void __ref build_all_zonelists(pg_data_t *pgdat) #endif } +/* If zone is ZONE_MOVABLE but memory is mirrored, it is an overlapped init */ +static bool __meminit +overlap_memmap_init(unsigned long zone, unsigned long *pfn) +{ +#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP + static struct memblock_region *r; + + if (mirrored_kernelcore && zone == ZONE_MOVABLE) { + if (!r || *pfn >= memblock_region_memory_end_pfn(r)) { + for_each_memblock(memory, r) { + if (*pfn < memblock_region_memory_end_pfn(r)) + break; + } + } + if (*pfn >= memblock_region_memory_base_pfn(r) && + memblock_is_mirror(r)) { + *pfn = memblock_region_memory_end_pfn(r); + return true; + } + } +#endif + return false; +} + /* * Initially all pages are reserved - free ones are freed * up by free_all_bootmem() once the early boot process is @@ -5459,12 +5483,8 @@ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone, unsigned long start_pfn, enum memmap_context context, struct vmem_altmap *altmap) { - unsigned long end_pfn = start_pfn + size; - unsigned long pfn; + unsigned long pfn, end_pfn = start_pfn + size; struct page *page; -#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP - struct memblock_region *r = NULL, *tmp; -#endif if (highest_memmap_pfn < end_pfn - 1) highest_memmap_pfn = end_pfn - 1; @@ -5492,39 +5512,17 @@ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone, * There can be holes in boot-time mem_map[]s handed to this * function. They do not exist on hotplugged memory. */ - if (context != MEMMAP_EARLY) - goto not_early; - - if (!early_pfn_valid(pfn)) - continue; - if (!early_pfn_in_nid(pfn, nid)) - continue; - -#ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP - /* - * Check given memblock attribute by firmware which can affect - * kernel memory layout. If zone==ZONE_MOVABLE but memory is - * mirrored, it's an overlapped memmap init. skip it. - */ - if (mirrored_kernelcore && zone == ZONE_MOVABLE) { - if (!r || pfn >= memblock_region_memory_end_pfn(r)) { - for_each_memblock(memory, tmp) - if (pfn < memblock_region_memory_end_pfn(tmp)) - break; - r = tmp; - } - if (pfn >= memblock_region_memory_base_pfn(r) && - memblock_is_mirror(r)) { - /* already initialized as NORMAL */ - pfn = memblock_region_memory_end_pfn(r); + if (context == MEMMAP_EARLY) { + if (!early_pfn_valid(pfn)) continue; - } + if (!early_pfn_in_nid(pfn, nid)) + continue; + if (overlap_memmap_init(zone, &pfn)) + continue; + if (defer_init(nid, pfn, end_pfn)) + break; } -#endif - if (defer_init(nid, pfn, end_pfn)) - break; -not_early: page = pfn_to_page(pfn); __init_single_page(page, pfn, zone, nid); if (context == MEMMAP_HOTPLUG) @@ -5541,9 +5539,6 @@ not_early: * can be created for invalid pages (for alignment) * check here not to call set_pageblock_migratetype() against * pfn out of zone. - * - * Please note that MEMMAP_HOTPLUG path doesn't clear memmap - * because this is done early in sparse_add_one_section */ if (!(pfn & (pageblock_nr_pages - 1))) { set_pageblock_migratetype(page, MIGRATE_MOVABLE); -- cgit v1.2.3 From 64081362e8ff4587b4554087f3cfc73d3e0a4cd7 Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Fri, 26 Oct 2018 15:09:45 -0700 Subject: mm/page-writeback.c: fix range_cyclic writeback vs writepages deadlock We've recently seen a workload on XFS filesystems with a repeatable deadlock between background writeback and a multi-process application doing concurrent writes and fsyncs to a small range of a file. range_cyclic writeback Process 1 Process 2 xfs_vm_writepages write_cache_pages writeback_index = 2 cycled = 0 .... find page 2 dirty lock Page 2 ->writepage page 2 writeback page 2 clean page 2 added to bio no more pages write() locks page 1 dirties page 1 locks page 2 dirties page 1 fsync() .... xfs_vm_writepages write_cache_pages start index 0 find page 1 towrite lock Page 1 ->writepage page 1 writeback page 1 clean page 1 added to bio find page 2 towrite lock Page 2 page 2 is writeback write() locks page 1 dirties page 1 fsync() .... xfs_vm_writepages write_cache_pages start index 0 !done && !cycled sets index to 0, restarts lookup find page 1 dirty find page 1 towrite lock Page 1 page 1 is writeback lock Page 1 DEADLOCK because: - process 1 needs page 2 writeback to complete to make enough progress to issue IO pending for page 1 - writeback needs page 1 writeback to complete so process 2 can progress and unlock the page it is blocked on, then it can issue the IO pending for page 2 - process 2 can't make progress until process 1 issues IO for page 1 The underlying cause of the problem here is that range_cyclic writeback is processing pages in descending index order as we hold higher index pages in a structure controlled from above write_cache_pages(). The write_cache_pages() caller needs to be able to submit these pages for IO before write_cache_pages restarts writeback at mapping index 0 to avoid wcp inverting the page lock/writeback wait order. generic_writepages() is not susceptible to this bug as it has no private context held across write_cache_pages() - filesystems using this infrastructure always submit pages in ->writepage immediately and so there is no problem with range_cyclic going back to mapping index 0. However: mpage_writepages() has a private bio context, exofs_writepages() has page_collect fuse_writepages() has fuse_fill_wb_data nfs_writepages() has nfs_pageio_descriptor xfs_vm_writepages() has xfs_writepage_ctx All of these ->writepages implementations can hold pages under writeback in their private structures until write_cache_pages() returns, and hence they are all susceptible to this deadlock. Also worth noting is that ext4 has it's own bastardised version of write_cache_pages() and so it /may/ have an equivalent deadlock. I looked at the code long enough to understand that it has a similar retry loop for range_cyclic writeback reaching the end of the file and then promptly ran away before my eyes bled too much. I'll leave it for the ext4 developers to determine if their code is actually has this deadlock and how to fix it if it has. There's a few ways I can see avoid this deadlock. There's probably more, but these are the first I've though of: 1. get rid of range_cyclic altogether 2. range_cyclic always stops at EOF, and we start again from writeback index 0 on the next call into write_cache_pages() 2a. wcp also returns EAGAIN to ->writepages implementations to indicate range cyclic has hit EOF. writepages implementations can then flush the current context and call wpc again to continue. i.e. lift the retry into the ->writepages implementation 3. range_cyclic uses trylock_page() rather than lock_page(), and it skips pages it can't lock without blocking. It will already do this for pages under writeback, so this seems like a no-brainer 3a. all non-WB_SYNC_ALL writeback uses trylock_page() to avoid blocking as per pages under writeback. I don't think #1 is an option - range_cyclic prevents frequently dirtied lower file offset from starving background writeback of rarely touched higher file offsets. #2 is simple, and I don't think it will have any impact on performance as going back to the start of the file implies an immediate seek. We'll have exactly the same number of seeks if we switch writeback to another inode, and then come back to this one later and restart from index 0. #2a is pretty much "status quo without the deadlock". Moving the retry loop up into the wcp caller means we can issue IO on the pending pages before calling wcp again, and so avoid locking or waiting on pages in the wrong order. I'm not convinced we need to do this given that we get the same thing from #2 on the next writeback call from the writeback infrastructure. #3 is really just a band-aid - it doesn't fix the access/wait inversion problem, just prevents it from becoming a deadlock situation. I'd prefer we fix the inversion, not sweep it under the carpet like this. #3a is really an optimisation that just so happens to include the band-aid fix of #3. So it seems that the simplest way to fix this issue is to implement solution #2 Link: http://lkml.kernel.org/r/20181005054526.21507-1-david@fromorbit.com Signed-off-by: Dave Chinner Reviewed-by: Jan Kara Cc: Nicholas Piggin Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/page-writeback.c | 33 +++++++++++++++------------------ 1 file changed, 15 insertions(+), 18 deletions(-) (limited to 'mm') diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 84ae9bf5858a..439a304a6c92 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -2149,6 +2149,13 @@ EXPORT_SYMBOL(tag_pages_for_writeback); * not miss some pages (e.g., because some other process has cleared TOWRITE * tag we set). The rule we follow is that TOWRITE tag can be cleared only * by the process clearing the DIRTY tag (and submitting the page for IO). + * + * To avoid deadlocks between range_cyclic writeback and callers that hold + * pages in PageWriteback to aggregate IO until write_cache_pages() returns, + * we do not loop back to the start of the file. Doing so causes a page + * lock/page writeback access order inversion - we should only ever lock + * multiple pages in ascending page->index order, and looping back to the start + * of the file violates that rule and causes deadlocks. */ int write_cache_pages(struct address_space *mapping, struct writeback_control *wbc, writepage_t writepage, @@ -2162,7 +2169,6 @@ int write_cache_pages(struct address_space *mapping, pgoff_t index; pgoff_t end; /* Inclusive */ pgoff_t done_index; - int cycled; int range_whole = 0; int tag; @@ -2170,23 +2176,17 @@ int write_cache_pages(struct address_space *mapping, if (wbc->range_cyclic) { writeback_index = mapping->writeback_index; /* prev offset */ index = writeback_index; - if (index == 0) - cycled = 1; - else - cycled = 0; end = -1; } else { index = wbc->range_start >> PAGE_SHIFT; end = wbc->range_end >> PAGE_SHIFT; if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX) range_whole = 1; - cycled = 1; /* ignore range_cyclic tests */ } if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages) tag = PAGECACHE_TAG_TOWRITE; else tag = PAGECACHE_TAG_DIRTY; -retry: if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages) tag_pages_for_writeback(mapping, index, end); done_index = index; @@ -2272,17 +2272,14 @@ continue_unlock: pagevec_release(&pvec); cond_resched(); } - if (!cycled && !done) { - /* - * range_cyclic: - * We hit the last page and there is more work to be done: wrap - * back to the start of the file - */ - cycled = 1; - index = 0; - end = writeback_index - 1; - goto retry; - } + + /* + * If we hit the last page and there is more work to be done: wrap + * back the index back to the start of the file for the next + * time we are called. + */ + if (wbc->range_cyclic && !done) + done_index = 0; if (wbc->range_cyclic || (range_whole && wbc->nr_to_write > 0)) mapping->writeback_index = done_index; -- cgit v1.2.3 From 7a1adfddaf0d11a39fdcaf6e82a88e9c0586e08b Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Fri, 26 Oct 2018 15:09:48 -0700 Subject: mm: don't raise MEMCG_OOM event due to failed high-order allocation It was reported that on some of our machines containers were restarted with OOM symptoms without an obvious reason. Despite there were almost no memory pressure and plenty of page cache, MEMCG_OOM event was raised occasionally, causing the container management software to think, that OOM has happened. However, no tasks have been killed. The following investigation showed that the problem is caused by a failing attempt to charge a high-order page. In such case, the OOM killer is never invoked. As shown below, it can happen under conditions, which are very far from a real OOM: e.g. there is plenty of clean page cache and no memory pressure. There is no sense in raising an OOM event in this case, as it might confuse a user and lead to wrong and excessive actions (e.g. restart the workload, as in my case). Let's look at the charging path in try_charge(). If the memory usage is about memory.max, which is absolutely natural for most memory cgroups, we try to reclaim some pages. Even if we were able to reclaim enough memory for the allocation, the following check can fail due to a race with another concurrent allocation: if (mem_cgroup_margin(mem_over_limit) >= nr_pages) goto retry; For regular pages the following condition will save us from triggering the OOM: if (nr_reclaimed && nr_pages <= (1 << PAGE_ALLOC_COSTLY_ORDER)) goto retry; But for high-order allocation this condition will intentionally fail. The reason behind is that we'll likely fall to regular pages anyway, so it's ok and even preferred to return ENOMEM. In this case the idea of raising MEMCG_OOM looks dubious. Fix this by moving MEMCG_OOM raising to mem_cgroup_oom() after allocation order check, so that the event won't be raised for high order allocations. This change doesn't affect regular pages allocation and charging. Link: http://lkml.kernel.org/r/20181004214050.7417-1-guro@fb.com Signed-off-by: Roman Gushchin Acked-by: David Rientjes Acked-by: Michal Hocko Acked-by: Johannes Weiner Cc: Vladimir Davydov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/admin-guide/cgroup-v2.rst | 4 ++++ mm/memcontrol.c | 4 ++-- 2 files changed, 6 insertions(+), 2 deletions(-) (limited to 'mm') diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst index 8389d6f72a77..8384c681a4b2 100644 --- a/Documentation/admin-guide/cgroup-v2.rst +++ b/Documentation/admin-guide/cgroup-v2.rst @@ -1133,6 +1133,10 @@ PAGE_SIZE multiple when read back. disk readahead. For now OOM in memory cgroup kills tasks iff shortage has happened inside page fault. + This event is not raised if the OOM killer is not + considered as an option, e.g. for failed high-order + allocations. + oom_kill The number of processes belonging to this cgroup killed by any kind of OOM killer. diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 92d38c88250f..10a9b554d69f 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -1669,6 +1669,8 @@ static enum oom_status mem_cgroup_oom(struct mem_cgroup *memcg, gfp_t mask, int if (order > PAGE_ALLOC_COSTLY_ORDER) return OOM_SKIPPED; + memcg_memory_event(memcg, MEMCG_OOM); + /* * We are in the middle of the charge context here, so we * don't want to block when potentially sitting on a callstack @@ -2250,8 +2252,6 @@ retry: if (fatal_signal_pending(current)) goto force; - memcg_memory_event(mem_over_limit, MEMCG_OOM); - /* * keep retrying as long as the memcg oom killer is able to make * a forward progress or bypass the charge if the oom killer -- cgit v1.2.3 From 26db3d09d9e1963c9db77cb275bd2d36e56ef57a Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Fri, 26 Oct 2018 15:09:52 -0700 Subject: mm/gup_benchmark.c: time put_page() We'd like to measure time to unpin user pages, so this adds a second benchmark timer on put_page, separate from get_page. Adding the field breaks this ioctl ABI, but should be okay since this an in-tree kernel selftest. [akpm@linux-foundation.org: add expansion to struct gup_benchmark for future use] Link: http://lkml.kernel.org/r/20181010195605.10689-1-keith.busch@intel.com Signed-off-by: Keith Busch Acked-by: Kirill A. Shutemov Reviewed-by: Andrew Morton Cc: Dave Hansen Cc: Dan Williams Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/gup_benchmark.c | 9 +++++++-- tools/testing/selftests/vm/gup_benchmark.c | 6 ++++-- 2 files changed, 11 insertions(+), 4 deletions(-) (limited to 'mm') diff --git a/mm/gup_benchmark.c b/mm/gup_benchmark.c index 7405c9d89d65..e6aff102373b 100644 --- a/mm/gup_benchmark.c +++ b/mm/gup_benchmark.c @@ -8,11 +8,13 @@ #define GUP_FAST_BENCHMARK _IOWR('g', 1, struct gup_benchmark) struct gup_benchmark { - __u64 delta_usec; + __u64 get_delta_usec; + __u64 put_delta_usec; __u64 addr; __u64 size; __u32 nr_pages_per_call; __u32 flags; + __u64 expansion[10]; /* For future use */ }; static int __gup_benchmark_ioctl(unsigned int cmd, @@ -48,14 +50,17 @@ static int __gup_benchmark_ioctl(unsigned int cmd, } end_time = ktime_get(); - gup->delta_usec = ktime_us_delta(end_time, start_time); + gup->get_delta_usec = ktime_us_delta(end_time, start_time); gup->size = addr - gup->addr; + start_time = ktime_get(); for (i = 0; i < nr_pages; i++) { if (!pages[i]) break; put_page(pages[i]); } + end_time = ktime_get(); + gup->put_delta_usec = ktime_us_delta(end_time, start_time); kvfree(pages); return 0; diff --git a/tools/testing/selftests/vm/gup_benchmark.c b/tools/testing/selftests/vm/gup_benchmark.c index 36df55132036..bdcb97acd0ac 100644 --- a/tools/testing/selftests/vm/gup_benchmark.c +++ b/tools/testing/selftests/vm/gup_benchmark.c @@ -17,7 +17,8 @@ #define GUP_FAST_BENCHMARK _IOWR('g', 1, struct gup_benchmark) struct gup_benchmark { - __u64 delta_usec; + __u64 get_delta_usec; + __u64 put_delta_usec; __u64 addr; __u64 size; __u32 nr_pages_per_call; @@ -81,7 +82,8 @@ int main(int argc, char **argv) if (ioctl(fd, GUP_FAST_BENCHMARK, &gup)) perror("ioctl"), exit(1); - printf("Time: %lld us", gup.delta_usec); + printf("Time: get:%lld put:%lld us", gup.get_delta_usec, + gup.put_delta_usec); if (gup.size != size) printf(", truncated (size: %lld)", gup.size); printf("\n"); -- cgit v1.2.3 From 714a3a1ebafe6e23af55a5c694c308f4044a7e00 Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Fri, 26 Oct 2018 15:09:56 -0700 Subject: mm/gup_benchmark.c: add additional pinning methods Provide new gup benchmark ioctl commands to run different user page pinning methods, get_user_pages_longterm() and get_user_pages(), in addition to the existing get_user_pages_fast(). Link: http://lkml.kernel.org/r/20181010195605.10689-2-keith.busch@intel.com Signed-off-by: Keith Busch Acked-by: Kirill A. Shutemov Reviewed-by: Andrew Morton Cc: Dave Hansen Cc: Dan Williams Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/gup_benchmark.c | 28 ++++++++++++++++++++++++++-- tools/testing/selftests/vm/gup_benchmark.c | 13 +++++++++++-- 2 files changed, 37 insertions(+), 4 deletions(-) (limited to 'mm') diff --git a/mm/gup_benchmark.c b/mm/gup_benchmark.c index e6aff102373b..debf11388a60 100644 --- a/mm/gup_benchmark.c +++ b/mm/gup_benchmark.c @@ -6,6 +6,8 @@ #include #define GUP_FAST_BENCHMARK _IOWR('g', 1, struct gup_benchmark) +#define GUP_LONGTERM_BENCHMARK _IOWR('g', 2, struct gup_benchmark) +#define GUP_BENCHMARK _IOWR('g', 3, struct gup_benchmark) struct gup_benchmark { __u64 get_delta_usec; @@ -43,7 +45,23 @@ static int __gup_benchmark_ioctl(unsigned int cmd, nr = (next - addr) / PAGE_SIZE; } - nr = get_user_pages_fast(addr, nr, gup->flags & 1, pages + i); + switch (cmd) { + case GUP_FAST_BENCHMARK: + nr = get_user_pages_fast(addr, nr, gup->flags & 1, + pages + i); + break; + case GUP_LONGTERM_BENCHMARK: + nr = get_user_pages_longterm(addr, nr, gup->flags & 1, + pages + i, NULL); + break; + case GUP_BENCHMARK: + nr = get_user_pages(addr, nr, gup->flags & 1, pages + i, + NULL); + break; + default: + return -1; + } + if (nr <= 0) break; i += nr; @@ -72,8 +90,14 @@ static long gup_benchmark_ioctl(struct file *filep, unsigned int cmd, struct gup_benchmark gup; int ret; - if (cmd != GUP_FAST_BENCHMARK) + switch (cmd) { + case GUP_FAST_BENCHMARK: + case GUP_LONGTERM_BENCHMARK: + case GUP_BENCHMARK: + break; + default: return -EINVAL; + } if (copy_from_user(&gup, (void __user *)arg, sizeof(gup))) return -EFAULT; diff --git a/tools/testing/selftests/vm/gup_benchmark.c b/tools/testing/selftests/vm/gup_benchmark.c index bdcb97acd0ac..c2f785ded9b9 100644 --- a/tools/testing/selftests/vm/gup_benchmark.c +++ b/tools/testing/selftests/vm/gup_benchmark.c @@ -15,6 +15,8 @@ #define PAGE_SIZE sysconf(_SC_PAGESIZE) #define GUP_FAST_BENCHMARK _IOWR('g', 1, struct gup_benchmark) +#define GUP_LONGTERM_BENCHMARK _IOWR('g', 2, struct gup_benchmark) +#define GUP_BENCHMARK _IOWR('g', 3, struct gup_benchmark) struct gup_benchmark { __u64 get_delta_usec; @@ -30,9 +32,10 @@ int main(int argc, char **argv) struct gup_benchmark gup; unsigned long size = 128 * MB; int i, fd, opt, nr_pages = 1, thp = -1, repeats = 1, write = 0; + int cmd = GUP_FAST_BENCHMARK; char *p; - while ((opt = getopt(argc, argv, "m:r:n:tT")) != -1) { + while ((opt = getopt(argc, argv, "m:r:n:tTLU")) != -1) { switch (opt) { case 'm': size = atoi(optarg) * MB; @@ -49,6 +52,12 @@ int main(int argc, char **argv) case 'T': thp = 0; break; + case 'L': + cmd = GUP_LONGTERM_BENCHMARK; + break; + case 'U': + cmd = GUP_BENCHMARK; + break; case 'w': write = 1; default: @@ -79,7 +88,7 @@ int main(int argc, char **argv) for (i = 0; i < repeats; i++) { gup.size = size; - if (ioctl(fd, GUP_FAST_BENCHMARK, &gup)) + if (ioctl(fd, cmd, &gup)) perror("ioctl"), exit(1); printf("Time: get:%lld put:%lld us", gup.get_delta_usec, -- cgit v1.2.3 From 907ec5fca3dc38d37737de826f06f25b063aa08e Mon Sep 17 00:00:00 2001 From: Naoya Horiguchi Date: Fri, 26 Oct 2018 15:10:15 -0700 Subject: mm: zero remaining unavailable struct pages Patch series "mm: Fix for movable_node boot option", v3. This patch series contains a fix for the movable_node boot option issue which was introduced by commit 124049decbb1 ("x86/e820: put !E820_TYPE_RAM regions into memblock.reserved"). The commit breaks the option because it changed the memory gap range to reserved memblock. So, the node is marked as Normal zone even if the SRAT has Hot pluggable affinity. First and second patch fix the original issue which the commit tried to fix, then revert the commit. This patch (of 3): There is a kernel panic that is triggered when reading /proc/kpageflags on the kernel booted with kernel parameter 'memmap=nn[KMG]!ss[KMG]': BUG: unable to handle kernel paging request at fffffffffffffffe PGD 9b20e067 P4D 9b20e067 PUD 9b210067 PMD 0 Oops: 0000 [#1] SMP PTI CPU: 2 PID: 1728 Comm: page-types Not tainted 4.17.0-rc6-mm1-v4.17-rc6-180605-0816-00236-g2dfb086ef02c+ #160 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.11.0-2.fc28 04/01/2014 RIP: 0010:stable_page_flags+0x27/0x3c0 Code: 00 00 00 0f 1f 44 00 00 48 85 ff 0f 84 a0 03 00 00 41 54 55 49 89 fc 53 48 8b 57 08 48 8b 2f 48 8d 42 ff 83 e2 01 48 0f 44 c7 <48> 8b 00 f6 c4 01 0f 84 10 03 00 00 31 db 49 8b 54 24 08 4c 89 e7 RSP: 0018:ffffbbd44111fde0 EFLAGS: 00010202 RAX: fffffffffffffffe RBX: 00007fffffffeff9 RCX: 0000000000000000 RDX: 0000000000000001 RSI: 0000000000000202 RDI: ffffed1182fff5c0 RBP: ffffffffffffffff R08: 0000000000000001 R09: 0000000000000001 R10: ffffbbd44111fed8 R11: 0000000000000000 R12: ffffed1182fff5c0 R13: 00000000000bffd7 R14: 0000000002fff5c0 R15: ffffbbd44111ff10 FS: 00007efc4335a500(0000) GS:ffff93a5bfc00000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: fffffffffffffffe CR3: 00000000b2a58000 CR4: 00000000001406e0 Call Trace: kpageflags_read+0xc7/0x120 proc_reg_read+0x3c/0x60 __vfs_read+0x36/0x170 vfs_read+0x89/0x130 ksys_pread64+0x71/0x90 do_syscall_64+0x5b/0x160 entry_SYSCALL_64_after_hwframe+0x44/0xa9 RIP: 0033:0x7efc42e75e23 Code: 09 00 ba 9f 01 00 00 e8 ab 81 f4 ff 66 2e 0f 1f 84 00 00 00 00 00 90 83 3d 29 0a 2d 00 00 75 13 49 89 ca b8 11 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 34 c3 48 83 ec 08 e8 db d3 01 00 48 89 04 24 According to kernel bisection, this problem became visible due to commit f7f99100d8d9 which changes how struct pages are initialized. Memblock layout affects the pfn ranges covered by node/zone. Consider that we have a VM with 2 NUMA nodes and each node has 4GB memory, and the default (no memmap= given) memblock layout is like below: MEMBLOCK configuration: memory size = 0x00000001fff75c00 reserved size = 0x000000000300c000 memory.cnt = 0x4 memory[0x0] [0x0000000000001000-0x000000000009efff], 0x000000000009e000 bytes on node 0 flags: 0x0 memory[0x1] [0x0000000000100000-0x00000000bffd6fff], 0x00000000bfed7000 bytes on node 0 flags: 0x0 memory[0x2] [0x0000000100000000-0x000000013fffffff], 0x0000000040000000 bytes on node 0 flags: 0x0 memory[0x3] [0x0000000140000000-0x000000023fffffff], 0x0000000100000000 bytes on node 1 flags: 0x0 ... If you give memmap=1G!4G (so it just covers memory[0x2]), the range [0x100000000-0x13fffffff] is gone: MEMBLOCK configuration: memory size = 0x00000001bff75c00 reserved size = 0x000000000300c000 memory.cnt = 0x3 memory[0x0] [0x0000000000001000-0x000000000009efff], 0x000000000009e000 bytes on node 0 flags: 0x0 memory[0x1] [0x0000000000100000-0x00000000bffd6fff], 0x00000000bfed7000 bytes on node 0 flags: 0x0 memory[0x2] [0x0000000140000000-0x000000023fffffff], 0x0000000100000000 bytes on node 1 flags: 0x0 ... This causes shrinking node 0's pfn range because it is calculated by the address range of memblock.memory. So some of struct pages in the gap range are left uninitialized. We have a function zero_resv_unavail() which does zeroing the struct pages outside memblock.memory, but currently it covers only the reserved unavailable range (i.e. memblock.memory && !memblock.reserved). This patch extends it to cover all unavailable range, which fixes the reported issue. Link: http://lkml.kernel.org/r/20181002143821.5112-2-msys.mizuma@gmail.com Fixes: f7f99100d8d9 ("mm: stop zeroing memory during allocation in vmemmap") Signed-off-by: Naoya Horiguchi Signed-off-by-by: Masayoshi Mizuma Tested-by: Oscar Salvador Tested-by: Masayoshi Mizuma Reviewed-by: Pavel Tatashin Cc: Ingo Molnar Cc: Michal Hocko Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memblock.h | 15 --------------- mm/page_alloc.c | 36 +++++++++++++++++++++++++----------- 2 files changed, 25 insertions(+), 26 deletions(-) (limited to 'mm') diff --git a/include/linux/memblock.h b/include/linux/memblock.h index 516920549378..2acdd046df2d 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -265,21 +265,6 @@ void __next_mem_pfn_range(int *idx, int nid, unsigned long *out_start_pfn, for_each_mem_range_rev(i, &memblock.memory, &memblock.reserved, \ nid, flags, p_start, p_end, p_nid) -/** - * for_each_resv_unavail_range - iterate through reserved and unavailable memory - * @i: u64 used as loop variable - * @p_start: ptr to phys_addr_t for start address of the range, can be %NULL - * @p_end: ptr to phys_addr_t for end address of the range, can be %NULL - * - * Walks over unavailable but reserved (reserved && !memory) areas of memblock. - * Available as soon as memblock is initialized. - * Note: because this memory does not belong to any physical node, flags and - * nid arguments do not make sense and thus not exported as arguments. - */ -#define for_each_resv_unavail_range(i, p_start, p_end) \ - for_each_mem_range(i, &memblock.reserved, &memblock.memory, \ - NUMA_NO_NODE, MEMBLOCK_NONE, p_start, p_end, NULL) - static inline void memblock_set_region_flags(struct memblock_region *r, enum memblock_flags flags) { diff --git a/mm/page_alloc.c b/mm/page_alloc.c index c26d3152f9ba..6d863c5afa08 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -6515,29 +6515,42 @@ void __init free_area_init_node(int nid, unsigned long *zones_size, * struct pages which are reserved in memblock allocator and their fields * may be accessed (for example page_to_pfn() on some configuration accesses * flags). We must explicitly zero those struct pages. + * + * This function also addresses a similar issue where struct pages are left + * uninitialized because the physical address range is not covered by + * memblock.memory or memblock.reserved. That could happen when memblock + * layout is manually configured via memmap=. */ void __init zero_resv_unavail(void) { phys_addr_t start, end; unsigned long pfn; u64 i, pgcnt; + phys_addr_t next = 0; /* - * Loop through ranges that are reserved, but do not have reported - * physical memory backing. + * Loop through unavailable ranges not covered by memblock.memory. */ pgcnt = 0; - for_each_resv_unavail_range(i, &start, &end) { - for (pfn = PFN_DOWN(start); pfn < PFN_UP(end); pfn++) { - if (!pfn_valid(ALIGN_DOWN(pfn, pageblock_nr_pages))) { - pfn = ALIGN_DOWN(pfn, pageblock_nr_pages) - + pageblock_nr_pages - 1; - continue; + for_each_mem_range(i, &memblock.memory, NULL, + NUMA_NO_NODE, MEMBLOCK_NONE, &start, &end, NULL) { + if (next < start) { + for (pfn = PFN_DOWN(next); pfn < PFN_UP(start); pfn++) { + if (!pfn_valid(ALIGN_DOWN(pfn, pageblock_nr_pages))) + continue; + mm_zero_struct_page(pfn_to_page(pfn)); + pgcnt++; } - mm_zero_struct_page(pfn_to_page(pfn)); - pgcnt++; } + next = end; } + for (pfn = PFN_DOWN(next); pfn < max_pfn; pfn++) { + if (!pfn_valid(ALIGN_DOWN(pfn, pageblock_nr_pages))) + continue; + mm_zero_struct_page(pfn_to_page(pfn)); + pgcnt++; + } + /* * Struct pages that do not have backing memory. This could be because @@ -6547,7 +6560,8 @@ void __init zero_resv_unavail(void) * this code can be removed. */ if (pgcnt) - pr_info("Reserved but unavailable: %lld pages", pgcnt); + pr_info("Zeroed struct page in unavailable ranges: %lld pages", pgcnt); + } #endif /* CONFIG_HAVE_MEMBLOCK && !CONFIG_FLAT_NODE_MEM_MAP */ -- cgit v1.2.3 From ec393a0f014eaf688a3dbe8c8a4cbb52d7f535f9 Mon Sep 17 00:00:00 2001 From: Pavel Tatashin Date: Fri, 26 Oct 2018 15:10:21 -0700 Subject: mm: return zero_resv_unavail optimization When checking for valid pfns in zero_resv_unavail(), it is not necessary to verify that pfns within pageblock_nr_pages ranges are valid, only the first one needs to be checked. This is because memory for pages are allocated in contiguous chunks that contain pageblock_nr_pages struct pages. Link: http://lkml.kernel.org/r/20181002143821.5112-3-msys.mizuma@gmail.com Signed-off-by: Pavel Tatashin Signed-off-by: Masayoshi Mizuma Reviewed-by: Masayoshi Mizuma Acked-by: Naoya Horiguchi Reviewed-by: Oscar Salvador Cc: Ingo Molnar Cc: Michal Hocko Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/page_alloc.c | 46 ++++++++++++++++++++++++++-------------------- 1 file changed, 26 insertions(+), 20 deletions(-) (limited to 'mm') diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 6d863c5afa08..863d46da6586 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -6509,6 +6509,29 @@ void __init free_area_init_node(int nid, unsigned long *zones_size, } #if defined(CONFIG_HAVE_MEMBLOCK) && !defined(CONFIG_FLAT_NODE_MEM_MAP) + +/* + * Zero all valid struct pages in range [spfn, epfn), return number of struct + * pages zeroed + */ +static u64 zero_pfn_range(unsigned long spfn, unsigned long epfn) +{ + unsigned long pfn; + u64 pgcnt = 0; + + for (pfn = spfn; pfn < epfn; pfn++) { + if (!pfn_valid(ALIGN_DOWN(pfn, pageblock_nr_pages))) { + pfn = ALIGN_DOWN(pfn, pageblock_nr_pages) + + pageblock_nr_pages - 1; + continue; + } + mm_zero_struct_page(pfn_to_page(pfn)); + pgcnt++; + } + + return pgcnt; +} + /* * Only struct pages that are backed by physical memory are zeroed and * initialized by going through __init_single_page(). But, there are some @@ -6524,7 +6547,6 @@ void __init free_area_init_node(int nid, unsigned long *zones_size, void __init zero_resv_unavail(void) { phys_addr_t start, end; - unsigned long pfn; u64 i, pgcnt; phys_addr_t next = 0; @@ -6534,34 +6556,18 @@ void __init zero_resv_unavail(void) pgcnt = 0; for_each_mem_range(i, &memblock.memory, NULL, NUMA_NO_NODE, MEMBLOCK_NONE, &start, &end, NULL) { - if (next < start) { - for (pfn = PFN_DOWN(next); pfn < PFN_UP(start); pfn++) { - if (!pfn_valid(ALIGN_DOWN(pfn, pageblock_nr_pages))) - continue; - mm_zero_struct_page(pfn_to_page(pfn)); - pgcnt++; - } - } + if (next < start) + pgcnt += zero_pfn_range(PFN_DOWN(next), PFN_UP(start)); next = end; } - for (pfn = PFN_DOWN(next); pfn < max_pfn; pfn++) { - if (!pfn_valid(ALIGN_DOWN(pfn, pageblock_nr_pages))) - continue; - mm_zero_struct_page(pfn_to_page(pfn)); - pgcnt++; - } - + pgcnt += zero_pfn_range(PFN_DOWN(next), max_pfn); /* * Struct pages that do not have backing memory. This could be because * firmware is using some of this memory, or for some other reasons. - * Once memblock is changed so such behaviour is not allowed: i.e. - * list of "reserved" memory must be a subset of list of "memory", then - * this code can be removed. */ if (pgcnt) pr_info("Zeroed struct page in unavailable ranges: %lld pages", pgcnt); - } #endif /* CONFIG_HAVE_MEMBLOCK && !CONFIG_FLAT_NODE_MEM_MAP */ -- cgit v1.2.3 From df06b37ffe5a442503b7095b77b0a970df515459 Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Fri, 26 Oct 2018 15:10:28 -0700 Subject: mm/gup: cache dev_pagemap while pinning pages Getting pages from ZONE_DEVICE memory needs to check the backing device's live-ness, which is tracked in the device's dev_pagemap metadata. This metadata is stored in a radix tree and looking it up adds measurable software overhead. This patch avoids repeating this relatively costly operation when dev_pagemap is used by caching the last dev_pagemap while getting user pages. The gup_benchmark kernel self test reports this reduces time to get user pages to as low as 1/3 of the previous time. Link: http://lkml.kernel.org/r/20181012173040.15669-1-keith.busch@intel.com Signed-off-by: Keith Busch Reviewed-by: Dan Williams Acked-by: Kirill A. Shutemov Cc: Dave Hansen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/huge_mm.h | 8 ++-- include/linux/mm.h | 12 +----- mm/gup.c | 110 ++++++++++++++++++++++++++++-------------------- mm/huge_memory.c | 16 +++---- mm/nommu.c | 6 +-- 5 files changed, 79 insertions(+), 73 deletions(-) (limited to 'mm') diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index fdcb45999b26..4663ee96cf59 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -213,9 +213,9 @@ static inline int hpage_nr_pages(struct page *page) } struct page *follow_devmap_pmd(struct vm_area_struct *vma, unsigned long addr, - pmd_t *pmd, int flags); + pmd_t *pmd, int flags, struct dev_pagemap **pgmap); struct page *follow_devmap_pud(struct vm_area_struct *vma, unsigned long addr, - pud_t *pud, int flags); + pud_t *pud, int flags, struct dev_pagemap **pgmap); extern vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf, pmd_t orig_pmd); @@ -344,13 +344,13 @@ static inline void mm_put_huge_zero_page(struct mm_struct *mm) } static inline struct page *follow_devmap_pmd(struct vm_area_struct *vma, - unsigned long addr, pmd_t *pmd, int flags) + unsigned long addr, pmd_t *pmd, int flags, struct dev_pagemap **pgmap) { return NULL; } static inline struct page *follow_devmap_pud(struct vm_area_struct *vma, - unsigned long addr, pud_t *pud, int flags) + unsigned long addr, pud_t *pud, int flags, struct dev_pagemap **pgmap) { return NULL; } diff --git a/include/linux/mm.h b/include/linux/mm.h index a023c5ce71fa..1e52b8fd1685 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2536,16 +2536,8 @@ static inline vm_fault_t vmf_error(int err) return VM_FAULT_SIGBUS; } -struct page *follow_page_mask(struct vm_area_struct *vma, - unsigned long address, unsigned int foll_flags, - unsigned int *page_mask); - -static inline struct page *follow_page(struct vm_area_struct *vma, - unsigned long address, unsigned int foll_flags) -{ - unsigned int unused_page_mask; - return follow_page_mask(vma, address, foll_flags, &unused_page_mask); -} +struct page *follow_page(struct vm_area_struct *vma, unsigned long address, + unsigned int foll_flags); #define FOLL_WRITE 0x01 /* check pte is writable */ #define FOLL_TOUCH 0x02 /* mark page accessed */ diff --git a/mm/gup.c b/mm/gup.c index 08eb350e0f35..841d7ef53591 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -20,6 +20,11 @@ #include "internal.h" +struct follow_page_context { + struct dev_pagemap *pgmap; + unsigned int page_mask; +}; + static struct page *no_page_table(struct vm_area_struct *vma, unsigned int flags) { @@ -71,10 +76,10 @@ static inline bool can_follow_write_pte(pte_t pte, unsigned int flags) } static struct page *follow_page_pte(struct vm_area_struct *vma, - unsigned long address, pmd_t *pmd, unsigned int flags) + unsigned long address, pmd_t *pmd, unsigned int flags, + struct dev_pagemap **pgmap) { struct mm_struct *mm = vma->vm_mm; - struct dev_pagemap *pgmap = NULL; struct page *page; spinlock_t *ptl; pte_t *ptep, pte; @@ -116,8 +121,8 @@ retry: * Only return device mapping pages in the FOLL_GET case since * they are only valid while holding the pgmap reference. */ - pgmap = get_dev_pagemap(pte_pfn(pte), NULL); - if (pgmap) + *pgmap = get_dev_pagemap(pte_pfn(pte), *pgmap); + if (*pgmap) page = pte_page(pte); else goto no_page; @@ -152,15 +157,8 @@ retry: goto retry; } - if (flags & FOLL_GET) { + if (flags & FOLL_GET) get_page(page); - - /* drop the pgmap reference now that we hold the page */ - if (pgmap) { - put_dev_pagemap(pgmap); - pgmap = NULL; - } - } if (flags & FOLL_TOUCH) { if ((flags & FOLL_WRITE) && !pte_dirty(pte) && !PageDirty(page)) @@ -210,7 +208,8 @@ no_page: static struct page *follow_pmd_mask(struct vm_area_struct *vma, unsigned long address, pud_t *pudp, - unsigned int flags, unsigned int *page_mask) + unsigned int flags, + struct follow_page_context *ctx) { pmd_t *pmd, pmdval; spinlock_t *ptl; @@ -258,13 +257,13 @@ retry: } if (pmd_devmap(pmdval)) { ptl = pmd_lock(mm, pmd); - page = follow_devmap_pmd(vma, address, pmd, flags); + page = follow_devmap_pmd(vma, address, pmd, flags, &ctx->pgmap); spin_unlock(ptl); if (page) return page; } if (likely(!pmd_trans_huge(pmdval))) - return follow_page_pte(vma, address, pmd, flags); + return follow_page_pte(vma, address, pmd, flags, &ctx->pgmap); if ((flags & FOLL_NUMA) && pmd_protnone(pmdval)) return no_page_table(vma, flags); @@ -284,7 +283,7 @@ retry_locked: } if (unlikely(!pmd_trans_huge(*pmd))) { spin_unlock(ptl); - return follow_page_pte(vma, address, pmd, flags); + return follow_page_pte(vma, address, pmd, flags, &ctx->pgmap); } if (flags & FOLL_SPLIT) { int ret; @@ -307,18 +306,18 @@ retry_locked: } return ret ? ERR_PTR(ret) : - follow_page_pte(vma, address, pmd, flags); + follow_page_pte(vma, address, pmd, flags, &ctx->pgmap); } page = follow_trans_huge_pmd(vma, address, pmd, flags); spin_unlock(ptl); - *page_mask = HPAGE_PMD_NR - 1; + ctx->page_mask = HPAGE_PMD_NR - 1; return page; } - static struct page *follow_pud_mask(struct vm_area_struct *vma, unsigned long address, p4d_t *p4dp, - unsigned int flags, unsigned int *page_mask) + unsigned int flags, + struct follow_page_context *ctx) { pud_t *pud; spinlock_t *ptl; @@ -344,7 +343,7 @@ static struct page *follow_pud_mask(struct vm_area_struct *vma, } if (pud_devmap(*pud)) { ptl = pud_lock(mm, pud); - page = follow_devmap_pud(vma, address, pud, flags); + page = follow_devmap_pud(vma, address, pud, flags, &ctx->pgmap); spin_unlock(ptl); if (page) return page; @@ -352,13 +351,13 @@ static struct page *follow_pud_mask(struct vm_area_struct *vma, if (unlikely(pud_bad(*pud))) return no_page_table(vma, flags); - return follow_pmd_mask(vma, address, pud, flags, page_mask); + return follow_pmd_mask(vma, address, pud, flags, ctx); } - static struct page *follow_p4d_mask(struct vm_area_struct *vma, unsigned long address, pgd_t *pgdp, - unsigned int flags, unsigned int *page_mask) + unsigned int flags, + struct follow_page_context *ctx) { p4d_t *p4d; struct page *page; @@ -378,7 +377,7 @@ static struct page *follow_p4d_mask(struct vm_area_struct *vma, return page; return no_page_table(vma, flags); } - return follow_pud_mask(vma, address, p4d, flags, page_mask); + return follow_pud_mask(vma, address, p4d, flags, ctx); } /** @@ -396,13 +395,13 @@ static struct page *follow_p4d_mask(struct vm_area_struct *vma, */ struct page *follow_page_mask(struct vm_area_struct *vma, unsigned long address, unsigned int flags, - unsigned int *page_mask) + struct follow_page_context *ctx) { pgd_t *pgd; struct page *page; struct mm_struct *mm = vma->vm_mm; - *page_mask = 0; + ctx->page_mask = 0; /* make this handle hugepd */ page = follow_huge_addr(mm, address, flags & FOLL_WRITE); @@ -431,7 +430,19 @@ struct page *follow_page_mask(struct vm_area_struct *vma, return no_page_table(vma, flags); } - return follow_p4d_mask(vma, address, pgd, flags, page_mask); + return follow_p4d_mask(vma, address, pgd, flags, ctx); +} + +struct page *follow_page(struct vm_area_struct *vma, unsigned long address, + unsigned int foll_flags) +{ + struct follow_page_context ctx = { NULL }; + struct page *page; + + page = follow_page_mask(vma, address, foll_flags, &ctx); + if (ctx.pgmap) + put_dev_pagemap(ctx.pgmap); + return page; } static int get_gate_page(struct mm_struct *mm, unsigned long address, @@ -659,9 +670,9 @@ static long __get_user_pages(struct task_struct *tsk, struct mm_struct *mm, unsigned int gup_flags, struct page **pages, struct vm_area_struct **vmas, int *nonblocking) { - long i = 0; - unsigned int page_mask; + long ret = 0, i = 0; struct vm_area_struct *vma = NULL; + struct follow_page_context ctx = { NULL }; if (!nr_pages) return 0; @@ -691,12 +702,14 @@ static long __get_user_pages(struct task_struct *tsk, struct mm_struct *mm, pages ? &pages[i] : NULL); if (ret) return i ? : ret; - page_mask = 0; + ctx.page_mask = 0; goto next_page; } - if (!vma || check_vma_flags(vma, gup_flags)) - return i ? : -EFAULT; + if (!vma || check_vma_flags(vma, gup_flags)) { + ret = -EFAULT; + goto out; + } if (is_vm_hugetlb_page(vma)) { i = follow_hugetlb_page(mm, vma, pages, vmas, &start, &nr_pages, i, @@ -709,23 +722,26 @@ retry: * If we have a pending SIGKILL, don't keep faulting pages and * potentially allocating memory. */ - if (unlikely(fatal_signal_pending(current))) - return i ? i : -ERESTARTSYS; + if (unlikely(fatal_signal_pending(current))) { + ret = -ERESTARTSYS; + goto out; + } cond_resched(); - page = follow_page_mask(vma, start, foll_flags, &page_mask); + + page = follow_page_mask(vma, start, foll_flags, &ctx); if (!page) { - int ret; ret = faultin_page(tsk, vma, start, &foll_flags, nonblocking); switch (ret) { case 0: goto retry; + case -EBUSY: + ret = 0; + /* FALLTHRU */ case -EFAULT: case -ENOMEM: case -EHWPOISON: - return i ? i : ret; - case -EBUSY: - return i; + goto out; case -ENOENT: goto next_page; } @@ -737,27 +753,31 @@ retry: */ goto next_page; } else if (IS_ERR(page)) { - return i ? i : PTR_ERR(page); + ret = PTR_ERR(page); + goto out; } if (pages) { pages[i] = page; flush_anon_page(vma, page, start); flush_dcache_page(page); - page_mask = 0; + ctx.page_mask = 0; } next_page: if (vmas) { vmas[i] = vma; - page_mask = 0; + ctx.page_mask = 0; } - page_increm = 1 + (~(start >> PAGE_SHIFT) & page_mask); + page_increm = 1 + (~(start >> PAGE_SHIFT) & ctx.page_mask); if (page_increm > nr_pages) page_increm = nr_pages; i += page_increm; start += page_increm * PAGE_SIZE; nr_pages -= page_increm; } while (nr_pages); - return i; +out: + if (ctx.pgmap) + put_dev_pagemap(ctx.pgmap); + return i ? i : ret; } static bool vma_permits_fault(struct vm_area_struct *vma, diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 8ea1b36bd452..25c7d7509cf4 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -852,11 +852,10 @@ static void touch_pmd(struct vm_area_struct *vma, unsigned long addr, } struct page *follow_devmap_pmd(struct vm_area_struct *vma, unsigned long addr, - pmd_t *pmd, int flags) + pmd_t *pmd, int flags, struct dev_pagemap **pgmap) { unsigned long pfn = pmd_pfn(*pmd); struct mm_struct *mm = vma->vm_mm; - struct dev_pagemap *pgmap; struct page *page; assert_spin_locked(pmd_lockptr(mm, pmd)); @@ -886,12 +885,11 @@ struct page *follow_devmap_pmd(struct vm_area_struct *vma, unsigned long addr, return ERR_PTR(-EEXIST); pfn += (addr & ~PMD_MASK) >> PAGE_SHIFT; - pgmap = get_dev_pagemap(pfn, NULL); - if (!pgmap) + *pgmap = get_dev_pagemap(pfn, *pgmap); + if (!*pgmap) return ERR_PTR(-EFAULT); page = pfn_to_page(pfn); get_page(page); - put_dev_pagemap(pgmap); return page; } @@ -1000,11 +998,10 @@ static void touch_pud(struct vm_area_struct *vma, unsigned long addr, } struct page *follow_devmap_pud(struct vm_area_struct *vma, unsigned long addr, - pud_t *pud, int flags) + pud_t *pud, int flags, struct dev_pagemap **pgmap) { unsigned long pfn = pud_pfn(*pud); struct mm_struct *mm = vma->vm_mm; - struct dev_pagemap *pgmap; struct page *page; assert_spin_locked(pud_lockptr(mm, pud)); @@ -1028,12 +1025,11 @@ struct page *follow_devmap_pud(struct vm_area_struct *vma, unsigned long addr, return ERR_PTR(-EEXIST); pfn += (addr & ~PUD_MASK) >> PAGE_SHIFT; - pgmap = get_dev_pagemap(pfn, NULL); - if (!pgmap) + *pgmap = get_dev_pagemap(pfn, *pgmap); + if (!*pgmap) return ERR_PTR(-EFAULT); page = pfn_to_page(pfn); get_page(page); - put_dev_pagemap(pgmap); return page; } diff --git a/mm/nommu.c b/mm/nommu.c index e4aac33216ae..749276beb109 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -1709,11 +1709,9 @@ SYSCALL_DEFINE5(mremap, unsigned long, addr, unsigned long, old_len, return ret; } -struct page *follow_page_mask(struct vm_area_struct *vma, - unsigned long address, unsigned int flags, - unsigned int *page_mask) +struct page *follow_page(struct vm_area_struct *vma, unsigned long address, + unsigned int foll_flags) { - *page_mask = 0; return NULL; } -- cgit v1.2.3 From 026d1eaf5ef1a5d6258b46e4e411cd9f5ab8c41d Mon Sep 17 00:00:00 2001 From: Clark Williams Date: Fri, 26 Oct 2018 15:10:32 -0700 Subject: mm/kasan/quarantine.c: make quarantine_lock a raw_spinlock_t The static lock quarantine_lock is used in quarantine.c to protect the quarantine queue datastructures. It is taken inside quarantine queue manipulation routines (quarantine_put(), quarantine_reduce() and quarantine_remove_cache()), with IRQs disabled. This is not a problem on a stock kernel but is problematic on an RT kernel where spin locks are sleeping spinlocks, which can sleep and can not be acquired with disabled interrupts. Convert the quarantine_lock to a raw spinlock_t. The usage of quarantine_lock is confined to quarantine.c and the work performed while the lock is held is used for debug purpose. [bigeasy@linutronix.de: slightly altered the commit message] Link: http://lkml.kernel.org/r/20181010214945.5owshc3mlrh74z4b@linutronix.de Signed-off-by: Clark Williams Signed-off-by: Sebastian Andrzej Siewior Acked-by: Sebastian Andrzej Siewior Acked-by: Dmitry Vyukov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/kasan/quarantine.c | 18 +++++++++--------- 1 file changed, 9 insertions(+), 9 deletions(-) (limited to 'mm') diff --git a/mm/kasan/quarantine.c b/mm/kasan/quarantine.c index 3a8ddf8baf7d..b209dbaefde8 100644 --- a/mm/kasan/quarantine.c +++ b/mm/kasan/quarantine.c @@ -103,7 +103,7 @@ static int quarantine_head; static int quarantine_tail; /* Total size of all objects in global_quarantine across all batches. */ static unsigned long quarantine_size; -static DEFINE_SPINLOCK(quarantine_lock); +static DEFINE_RAW_SPINLOCK(quarantine_lock); DEFINE_STATIC_SRCU(remove_cache_srcu); /* Maximum size of the global queue. */ @@ -190,7 +190,7 @@ void quarantine_put(struct kasan_free_meta *info, struct kmem_cache *cache) if (unlikely(q->bytes > QUARANTINE_PERCPU_SIZE)) { qlist_move_all(q, &temp); - spin_lock(&quarantine_lock); + raw_spin_lock(&quarantine_lock); WRITE_ONCE(quarantine_size, quarantine_size + temp.bytes); qlist_move_all(&temp, &global_quarantine[quarantine_tail]); if (global_quarantine[quarantine_tail].bytes >= @@ -203,7 +203,7 @@ void quarantine_put(struct kasan_free_meta *info, struct kmem_cache *cache) if (new_tail != quarantine_head) quarantine_tail = new_tail; } - spin_unlock(&quarantine_lock); + raw_spin_unlock(&quarantine_lock); } local_irq_restore(flags); @@ -230,7 +230,7 @@ void quarantine_reduce(void) * expected case). */ srcu_idx = srcu_read_lock(&remove_cache_srcu); - spin_lock_irqsave(&quarantine_lock, flags); + raw_spin_lock_irqsave(&quarantine_lock, flags); /* * Update quarantine size in case of hotplug. Allocate a fraction of @@ -254,7 +254,7 @@ void quarantine_reduce(void) quarantine_head = 0; } - spin_unlock_irqrestore(&quarantine_lock, flags); + raw_spin_unlock_irqrestore(&quarantine_lock, flags); qlist_free_all(&to_free, NULL); srcu_read_unlock(&remove_cache_srcu, srcu_idx); @@ -310,17 +310,17 @@ void quarantine_remove_cache(struct kmem_cache *cache) */ on_each_cpu(per_cpu_remove_cache, cache, 1); - spin_lock_irqsave(&quarantine_lock, flags); + raw_spin_lock_irqsave(&quarantine_lock, flags); for (i = 0; i < QUARANTINE_BATCHES; i++) { if (qlist_empty(&global_quarantine[i])) continue; qlist_move_cache(&global_quarantine[i], &to_free, cache); /* Scanning whole quarantine can take a while. */ - spin_unlock_irqrestore(&quarantine_lock, flags); + raw_spin_unlock_irqrestore(&quarantine_lock, flags); cond_resched(); - spin_lock_irqsave(&quarantine_lock, flags); + raw_spin_lock_irqsave(&quarantine_lock, flags); } - spin_unlock_irqrestore(&quarantine_lock, flags); + raw_spin_unlock_irqrestore(&quarantine_lock, flags); qlist_free_all(&to_free, cache); -- cgit v1.2.3 From d7c3393413fe7e7dc54498ea200ea94742d61e18 Mon Sep 17 00:00:00 2001 From: Andrea Arcangeli Date: Fri, 26 Oct 2018 15:10:36 -0700 Subject: mm: thp: fix MADV_DONTNEED vs migrate_misplaced_transhuge_page race condition Patch series "migrate_misplaced_transhuge_page race conditions". Aaron found a new instance of the THP MADV_DONTNEED race against pmdp_clear_flush* variants, that was apparently left unfixed. While looking into the race found by Aaron, I may have found two more issues in migrate_misplaced_transhuge_page. These race conditions would not cause kernel instability, but they'd corrupt userland data or leave data non zero after MADV_DONTNEED. I did only minor testing, and I don't expect to be able to reproduce this (especially the lack of ->invalidate_range before migrate_page_copy, requires the latest iommu hardware or infiniband to reproduce). The last patch is noop for x86 and it needs further review from maintainers of archs that implement flush_cache_range() (not in CC yet). To avoid confusion, it's not the first patch that introduces the bug fixed in the second patch, even before removing the pmdp_huge_clear_flush_notify, that _notify suffix was called after migrate_page_copy already run. This patch (of 3): This is a corollary of ced108037c2aa ("thp: fix MADV_DONTNEED vs. numa balancing race"), 58ceeb6bec8 ("thp: fix MADV_DONTNEED vs. MADV_FREE race") and 5b7abeae3af8c ("thp: fix MADV_DONTNEED vs clear soft dirty race). When the above three fixes where posted Dave asked https://lkml.kernel.org/r/929b3844-aec2-0111-fef7-8002f9d4e2b9@intel.com but apparently this was missed. The pmdp_clear_flush* in migrate_misplaced_transhuge_page() was introduced in a54a407fbf7 ("mm: Close races between THP migration and PMD numa clearing"). The important part of such commit is only the part where the page lock is not released until the first do_huge_pmd_numa_page() finished disarming the pagenuma/protnone. The addition of pmdp_clear_flush() wasn't beneficial to such commit and there's no commentary about such an addition either. I guess the pmdp_clear_flush() in such commit was added just in case for safety, but it ended up introducing the MADV_DONTNEED race condition found by Aaron. At that point in time nobody thought of such kind of MADV_DONTNEED race conditions yet (they were fixed later) so the code may have looked more robust by adding the pmdp_clear_flush(). This specific race condition won't destabilize the kernel, but it can confuse userland because after MADV_DONTNEED the memory won't be zeroed out. This also optimizes the code and removes a superfluous TLB flush. [akpm@linux-foundation.org: reflow comment to 80 cols, fix grammar and typo (beacuse)] Link: http://lkml.kernel.org/r/20181013002430.698-2-aarcange@redhat.com Signed-off-by: Andrea Arcangeli Reported-by: Aaron Tomlin Acked-by: Mel Gorman Acked-by: Kirill A. Shutemov Cc: Jerome Glisse Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/migrate.c | 25 ++++++++++++++++++------- 1 file changed, 18 insertions(+), 7 deletions(-) (limited to 'mm') diff --git a/mm/migrate.c b/mm/migrate.c index 1ea27b343ccd..93d9a1e25aad 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -2031,15 +2031,26 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm, entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma); /* - * Clear the old entry under pagetable lock and establish the new PTE. - * Any parallel GUP will either observe the old page blocking on the - * page lock, block on the page table lock or observe the new page. - * The SetPageUptodate on the new page and page_add_new_anon_rmap - * guarantee the copy is visible before the pagetable update. + * Overwrite the old entry under pagetable lock and establish + * the new PTE. Any parallel GUP will either observe the old + * page blocking on the page lock, block on the page table + * lock or observe the new page. The SetPageUptodate on the + * new page and page_add_new_anon_rmap guarantee the copy is + * visible before the pagetable update. */ flush_cache_range(vma, mmun_start, mmun_end); page_add_anon_rmap(new_page, vma, mmun_start, true); - pmdp_huge_clear_flush_notify(vma, mmun_start, pmd); + /* + * At this point the pmd is numa/protnone (i.e. non present) and the TLB + * has already been flushed globally. So no TLB can be currently + * caching this non present pmd mapping. There's no need to clear the + * pmd before doing set_pmd_at(), nor to flush the TLB after + * set_pmd_at(). Clearing the pmd here would introduce a race + * condition against MADV_DONTNEED, because MADV_DONTNEED only holds the + * mmap_sem for reading. If the pmd is set to NULL at any given time, + * MADV_DONTNEED won't wait on the pmd lock and it'll skip clearing this + * pmd. + */ set_pmd_at(mm, mmun_start, pmd, entry); update_mmu_cache_pmd(vma, address, &entry); @@ -2053,7 +2064,7 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm, * No need to double call mmu_notifier->invalidate_range() callback as * the above pmdp_huge_clear_flush_notify() did already call it. */ - mmu_notifier_invalidate_range_only_end(mm, mmun_start, mmun_end); + mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end); /* Take an "isolate" reference and put new page on the LRU. */ get_page(new_page); -- cgit v1.2.3 From 7066f0f933a1fd707bb38781866657769cff7efc Mon Sep 17 00:00:00 2001 From: Andrea Arcangeli Date: Fri, 26 Oct 2018 15:10:40 -0700 Subject: mm: thp: fix mmu_notifier in migrate_misplaced_transhuge_page() change_huge_pmd() after arming the numa/protnone pmd doesn't flush the TLB right away. do_huge_pmd_numa_page() flushes the TLB before calling migrate_misplaced_transhuge_page(). By the time do_huge_pmd_numa_page() runs some CPU could still access the page through the TLB. change_huge_pmd() before arming the numa/protnone transhuge pmd calls mmu_notifier_invalidate_range_start(). So there's no need of mmu_notifier_invalidate_range_start()/mmu_notifier_invalidate_range_only_end() sequence in migrate_misplaced_transhuge_page() too, because by the time migrate_misplaced_transhuge_page() runs, the pmd mapping has already been invalidated in the secondary MMUs. It has to or if a secondary MMU can still write to the page, the migrate_page_copy() would lose data. However an explicit mmu_notifier_invalidate_range() is needed before migrate_misplaced_transhuge_page() starts copying the data of the transhuge page or the below can happen for MMU notifier users sharing the primary MMU pagetables and only implementing ->invalidate_range: CPU0 CPU1 GPU sharing linux pagetables using only ->invalidate_range ----------- ------------ --------- GPU secondary MMU writes to the page mapped by the transhuge pmd change_pmd_range() mmu..._range_start() ->invalidate_range_start() noop change_huge_pmd() set_pmd_at(numa/protnone) pmd_unlock() do_huge_pmd_numa_page() CPU TLB flush globally (1) CPU cannot write to page migrate_misplaced_transhuge_page() GPU writes to the page... migrate_page_copy() ...GPU stops writing to the page CPU TLB flush (2) mmu..._range_end() (3) ->invalidate_range_stop() noop ->invalidate_range() GPU secondary MMU is invalidated and cannot write to the page anymore (too late) Just like we need a CPU TLB flush (1) because the TLB flush (2) arrives too late, we also need a mmu_notifier_invalidate_range() before calling migrate_misplaced_transhuge_page(), because the ->invalidate_range() in (3) also arrives too late. This requirement is the result of the lazy optimization in change_huge_pmd() that releases the pmd_lock without first flushing the TLB and without first calling mmu_notifier_invalidate_range(). Even converting the removed mmu_notifier_invalidate_range_only_end() into a mmu_notifier_invalidate_range_end() would not have been enough to fix this, because it run after migrate_page_copy(). After the hugepage data copy is done migrate_misplaced_transhuge_page() can proceed and call set_pmd_at without having to flush the TLB nor any secondary MMUs because the secondary MMU invalidate, just like the CPU TLB flush, has to happen before the migrate_page_copy() is called or it would be a bug in the first place (and it was for drivers using ->invalidate_range()). KVM is unaffected because it doesn't implement ->invalidate_range(). The standard PAGE_SIZEd migrate_misplaced_page is less accelerated and uses the generic migrate_pages which transitions the pte from numa/protnone to a migration entry in try_to_unmap_one() and flushes TLBs and all mmu notifiers there before copying the page. Link: http://lkml.kernel.org/r/20181013002430.698-3-aarcange@redhat.com Signed-off-by: Andrea Arcangeli Acked-by: Mel Gorman Acked-by: Kirill A. Shutemov Reviewed-by: Aaron Tomlin Cc: Jerome Glisse Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/huge_memory.c | 14 +++++++++++++- mm/migrate.c | 19 ++++++------------- 2 files changed, 19 insertions(+), 14 deletions(-) (limited to 'mm') diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 25c7d7509cf4..25ef59b7ee34 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1558,8 +1558,20 @@ vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf, pmd_t pmd) * We are not sure a pending tlb flush here is for a huge page * mapping or not. Hence use the tlb range variant */ - if (mm_tlb_flush_pending(vma->vm_mm)) + if (mm_tlb_flush_pending(vma->vm_mm)) { flush_tlb_range(vma, haddr, haddr + HPAGE_PMD_SIZE); + /* + * change_huge_pmd() released the pmd lock before + * invalidating the secondary MMUs sharing the primary + * MMU pagetables (with ->invalidate_range()). The + * mmu_notifier_invalidate_range_end() (which + * internally calls ->invalidate_range()) in + * change_pmd_range() will run after us, so we can't + * rely on it here and we need an explicit invalidate. + */ + mmu_notifier_invalidate_range(vma->vm_mm, haddr, + haddr + HPAGE_PMD_SIZE); + } /* * Migrate the THP to the requested node, returns with page unlocked diff --git a/mm/migrate.c b/mm/migrate.c index 93d9a1e25aad..905c2264c788 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -1975,8 +1975,8 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm, int isolated = 0; struct page *new_page = NULL; int page_lru = page_is_file_cache(page); - unsigned long mmun_start = address & HPAGE_PMD_MASK; - unsigned long mmun_end = mmun_start + HPAGE_PMD_SIZE; + unsigned long start = address & HPAGE_PMD_MASK; + unsigned long end = start + HPAGE_PMD_SIZE; new_page = alloc_pages_node(node, (GFP_TRANSHUGE_LIGHT | __GFP_THISNODE), @@ -2003,11 +2003,9 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm, WARN_ON(PageLRU(new_page)); /* Recheck the target PMD */ - mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end); ptl = pmd_lock(mm, pmd); if (unlikely(!pmd_same(*pmd, entry) || !page_ref_freeze(page, 2))) { spin_unlock(ptl); - mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end); /* Reverse changes made by migrate_page_copy() */ if (TestClearPageActive(new_page)) @@ -2038,8 +2036,8 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm, * new page and page_add_new_anon_rmap guarantee the copy is * visible before the pagetable update. */ - flush_cache_range(vma, mmun_start, mmun_end); - page_add_anon_rmap(new_page, vma, mmun_start, true); + flush_cache_range(vma, start, end); + page_add_anon_rmap(new_page, vma, start, true); /* * At this point the pmd is numa/protnone (i.e. non present) and the TLB * has already been flushed globally. So no TLB can be currently @@ -2051,7 +2049,7 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm, * MADV_DONTNEED won't wait on the pmd lock and it'll skip clearing this * pmd. */ - set_pmd_at(mm, mmun_start, pmd, entry); + set_pmd_at(mm, start, pmd, entry); update_mmu_cache_pmd(vma, address, &entry); page_ref_unfreeze(page, 2); @@ -2060,11 +2058,6 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm, set_page_owner_migrate_reason(new_page, MR_NUMA_MISPLACED); spin_unlock(ptl); - /* - * No need to double call mmu_notifier->invalidate_range() callback as - * the above pmdp_huge_clear_flush_notify() did already call it. - */ - mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end); /* Take an "isolate" reference and put new page on the LRU. */ get_page(new_page); @@ -2088,7 +2081,7 @@ out_fail: ptl = pmd_lock(mm, pmd); if (pmd_same(*pmd, entry)) { entry = pmd_modify(entry, vma->vm_page_prot); - set_pmd_at(mm, mmun_start, pmd, entry); + set_pmd_at(mm, start, pmd, entry); update_mmu_cache_pmd(vma, address, &entry); } spin_unlock(ptl); -- cgit v1.2.3 From 7eef5f97c1f94c7b72520b42d372037e97a81b95 Mon Sep 17 00:00:00 2001 From: Andrea Arcangeli Date: Fri, 26 Oct 2018 15:10:43 -0700 Subject: mm: thp: relocate flush_cache_range() in migrate_misplaced_transhuge_page() There should be no cache left by the time we overwrite the old transhuge pmd with the new one. It's already too late to flush through the virtual address because we already copied the page data to the new physical address. So flush the cache before the data copy. Also delete the "end" variable to shutoff a "unused variable" warning on x86 where flush_cache_range() is a noop. Link: http://lkml.kernel.org/r/20181015202311.7209-1-aarcange@redhat.com Signed-off-by: Andrea Arcangeli Acked-by: Kirill A. Shutemov Cc: Aaron Tomlin Cc: Jerome Glisse Cc: Mel Gorman Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/migrate.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'mm') diff --git a/mm/migrate.c b/mm/migrate.c index 905c2264c788..b6700f2962f3 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -1976,7 +1976,6 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm, struct page *new_page = NULL; int page_lru = page_is_file_cache(page); unsigned long start = address & HPAGE_PMD_MASK; - unsigned long end = start + HPAGE_PMD_SIZE; new_page = alloc_pages_node(node, (GFP_TRANSHUGE_LIGHT | __GFP_THISNODE), @@ -1999,6 +1998,8 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm, /* anon mapping, we can simply copy page->mapping to the new page: */ new_page->mapping = page->mapping; new_page->index = page->index; + /* flush the cache before copying using the kernel virtual address */ + flush_cache_range(vma, start, start + HPAGE_PMD_SIZE); migrate_page_copy(new_page, page); WARN_ON(PageLRU(new_page)); @@ -2036,7 +2037,6 @@ int migrate_misplaced_transhuge_page(struct mm_struct *mm, * new page and page_add_new_anon_rmap guarantee the copy is * visible before the pagetable update. */ - flush_cache_range(vma, start, end); page_add_anon_rmap(new_page, vma, start, true); /* * At this point the pmd is numa/protnone (i.e. non present) and the TLB -- cgit v1.2.3 From bc4ae27d817a4e92071ef67cb6368120cfabe7ec Mon Sep 17 00:00:00 2001 From: Omar Sandoval Date: Fri, 26 Oct 2018 15:10:51 -0700 Subject: mm: split SWP_FILE into SWP_ACTIVATED and SWP_FS The SWP_FILE flag serves two purposes: to make swap_{read,write}page() go through the filesystem, and to make swapoff() call ->swap_deactivate(). For Btrfs, we want the latter but not the former, so split this flag into two. This makes us always call ->swap_deactivate() if ->swap_activate() succeeded, not just if it didn't add any swap extents itself. This also resolves the issue of the very misleading name of SWP_FILE, which is only used for swap files over NFS. Link: http://lkml.kernel.org/r/6d63d8668c4287a4f6d203d65696e96f80abdfc7.1536704650.git.osandov@fb.com Signed-off-by: Omar Sandoval Reviewed-by: Nikolay Borisov Reviewed-by: Andrew Morton Cc: Johannes Weiner Cc: David Sterba Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/swap.h | 13 +++++++------ mm/page_io.c | 6 +++--- mm/swapfile.c | 13 ++++++++----- 3 files changed, 18 insertions(+), 14 deletions(-) (limited to 'mm') diff --git a/include/linux/swap.h b/include/linux/swap.h index b93740d72e78..38195f5c96b1 100644 --- a/include/linux/swap.h +++ b/include/linux/swap.h @@ -167,13 +167,14 @@ enum { SWP_SOLIDSTATE = (1 << 4), /* blkdev seeks are cheap */ SWP_CONTINUED = (1 << 5), /* swap_map has count continuation */ SWP_BLKDEV = (1 << 6), /* its a block device */ - SWP_FILE = (1 << 7), /* set after swap_activate success */ - SWP_AREA_DISCARD = (1 << 8), /* single-time swap area discards */ - SWP_PAGE_DISCARD = (1 << 9), /* freed swap page-cluster discards */ - SWP_STABLE_WRITES = (1 << 10), /* no overwrite PG_writeback pages */ - SWP_SYNCHRONOUS_IO = (1 << 11), /* synchronous IO is efficient */ + SWP_ACTIVATED = (1 << 7), /* set after swap_activate success */ + SWP_FS = (1 << 8), /* swap file goes through fs */ + SWP_AREA_DISCARD = (1 << 9), /* single-time swap area discards */ + SWP_PAGE_DISCARD = (1 << 10), /* freed swap page-cluster discards */ + SWP_STABLE_WRITES = (1 << 11), /* no overwrite PG_writeback pages */ + SWP_SYNCHRONOUS_IO = (1 << 12), /* synchronous IO is efficient */ /* add others here before... */ - SWP_SCANNING = (1 << 12), /* refcount in scan_swap_map */ + SWP_SCANNING = (1 << 13), /* refcount in scan_swap_map */ }; #define SWAP_CLUSTER_MAX 32UL diff --git a/mm/page_io.c b/mm/page_io.c index 573d3663d846..a451ffa9491c 100644 --- a/mm/page_io.c +++ b/mm/page_io.c @@ -283,7 +283,7 @@ int __swap_writepage(struct page *page, struct writeback_control *wbc, struct swap_info_struct *sis = page_swap_info(page); VM_BUG_ON_PAGE(!PageSwapCache(page), page); - if (sis->flags & SWP_FILE) { + if (sis->flags & SWP_FS) { struct kiocb kiocb; struct file *swap_file = sis->swap_file; struct address_space *mapping = swap_file->f_mapping; @@ -365,7 +365,7 @@ int swap_readpage(struct page *page, bool synchronous) goto out; } - if (sis->flags & SWP_FILE) { + if (sis->flags & SWP_FS) { struct file *swap_file = sis->swap_file; struct address_space *mapping = swap_file->f_mapping; @@ -423,7 +423,7 @@ int swap_set_page_dirty(struct page *page) { struct swap_info_struct *sis = page_swap_info(page); - if (sis->flags & SWP_FILE) { + if (sis->flags & SWP_FS) { struct address_space *mapping = sis->swap_file->f_mapping; VM_BUG_ON_PAGE(!PageSwapCache(page), page); diff --git a/mm/swapfile.c b/mm/swapfile.c index 2681e50592c5..f0c7e4c11bab 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -1003,7 +1003,7 @@ start_over: goto nextsi; } if (size == SWAPFILE_CLUSTER) { - if (!(si->flags & SWP_FILE)) + if (!(si->flags & SWP_FS)) n_ret = swap_alloc_cluster(si, swp_entries); } else n_ret = scan_swap_map_slots(si, SWAP_HAS_CACHE, @@ -2299,12 +2299,13 @@ static void destroy_swap_extents(struct swap_info_struct *sis) kfree(se); } - if (sis->flags & SWP_FILE) { + if (sis->flags & SWP_ACTIVATED) { struct file *swap_file = sis->swap_file; struct address_space *mapping = swap_file->f_mapping; - sis->flags &= ~SWP_FILE; - mapping->a_ops->swap_deactivate(swap_file); + sis->flags &= ~SWP_ACTIVATED; + if (mapping->a_ops->swap_deactivate) + mapping->a_ops->swap_deactivate(swap_file); } } @@ -2400,8 +2401,10 @@ static int setup_swap_extents(struct swap_info_struct *sis, sector_t *span) if (mapping->a_ops->swap_activate) { ret = mapping->a_ops->swap_activate(sis, swap_file, span); + if (ret >= 0) + sis->flags |= SWP_ACTIVATED; if (!ret) { - sis->flags |= SWP_FILE; + sis->flags |= SWP_FS; ret = add_swap_extent(sis, 0, sis->max, 0); *span = sis->pages; } -- cgit v1.2.3 From aa8aa8a331d27fcef3e60dabb918eb8c5c9a2ad9 Mon Sep 17 00:00:00 2001 From: Omar Sandoval Date: Fri, 26 Oct 2018 15:10:55 -0700 Subject: mm: export add_swap_extent() Btrfs currently does not support swap files because swap's use of bmap does not work with copy-on-write and multiple devices. See 35054394c4b3 ("Btrfs: stop providing a bmap operation to avoid swapfile corruptions"). However, the swap code has a mechanism for the filesystem to manually add swap extents using add_swap_extent() from the ->swap_activate() aop. iomap has done this since 67482129cdab ("iomap: add a swapfile activation function"). Btrfs will do the same in a later patch, so export add_swap_extent(). Link: http://lkml.kernel.org/r/bb1208575e02829aae51b538709476964f97b1ea.1536704650.git.osandov@fb.com Signed-off-by: Omar Sandoval Reviewed-by: Andrew Morton Cc: David Sterba Cc: Johannes Weiner Cc: Nikolay Borisov Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/swapfile.c | 1 + 1 file changed, 1 insertion(+) (limited to 'mm') diff --git a/mm/swapfile.c b/mm/swapfile.c index f0c7e4c11bab..644f746e167a 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -2354,6 +2354,7 @@ add_swap_extent(struct swap_info_struct *sis, unsigned long start_page, list_add_tail(&new_se->list, &sis->first_swap_extent.list); return 1; } +EXPORT_SYMBOL_GPL(add_swap_extent); /* * A `swap extent' is a simple thing which maps a contiguous range of pages -- cgit v1.2.3 From 22146c3ce98962436e401f7b7016a6f664c9ffb5 Mon Sep 17 00:00:00 2001 From: Mike Kravetz Date: Fri, 26 Oct 2018 15:10:58 -0700 Subject: hugetlbfs: dirty pages as they are added to pagecache Some test systems were experiencing negative huge page reserve counts and incorrect file block counts. This was traced to /proc/sys/vm/drop_caches removing clean pages from hugetlbfs file pagecaches. When non-hugetlbfs explicit code removes the pages, the appropriate accounting is not performed. This can be recreated as follows: fallocate -l 2M /dev/hugepages/foo echo 1 > /proc/sys/vm/drop_caches fallocate -l 2M /dev/hugepages/foo grep -i huge /proc/meminfo AnonHugePages: 0 kB ShmemHugePages: 0 kB HugePages_Total: 2048 HugePages_Free: 2047 HugePages_Rsvd: 18446744073709551615 HugePages_Surp: 0 Hugepagesize: 2048 kB Hugetlb: 4194304 kB ls -lsh /dev/hugepages/foo 4.0M -rw-r--r--. 1 root root 2.0M Oct 17 20:05 /dev/hugepages/foo To address this issue, dirty pages as they are added to pagecache. This can easily be reproduced with fallocate as shown above. Read faulted pages will eventually end up being marked dirty. But there is a window where they are clean and could be impacted by code such as drop_caches. So, just dirty them all as they are added to the pagecache. Link: http://lkml.kernel.org/r/b5be45b8-5afe-56cd-9482-28384699a049@oracle.com Fixes: 6bda666a03f0 ("hugepages: fold find_or_alloc_pages into huge_no_page()") Signed-off-by: Mike Kravetz Acked-by: Mihcla Hocko Reviewed-by: Khalid Aziz Cc: Hugh Dickins Cc: Naoya Horiguchi Cc: "Aneesh Kumar K . V" Cc: Andrea Arcangeli Cc: "Kirill A . Shutemov" Cc: Davidlohr Bueso Cc: Alexander Viro Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/hugetlb.c | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'mm') diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 5c390f5a5207..7b5c0ad9a6bd 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -3690,6 +3690,12 @@ int huge_add_to_page_cache(struct page *page, struct address_space *mapping, return err; ClearPagePrivate(page); + /* + * set page dirty so that it will not be removed from cache/file + * by non-hugetlbfs specific code paths. + */ + set_page_dirty(page); + spin_lock(&inode->i_lock); inode->i_blocks += blocks_per_huge_page(h); spin_unlock(&inode->i_lock); -- cgit v1.2.3 From 1383a7ed67490fb00d793e36c7a4d599ff88a64d Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 30 Oct 2018 10:40:31 +1100 Subject: vfs: check file ranges before cloning files Move the file range checks from vfs_clone_file_prep into a separate generic_remap_checks function so that all the checks are collected in a central location. This forms the basis for adding more checks from generic_write_checks that will make cloning's input checking more consistent with write input checking. Signed-off-by: Darrick J. Wong Reviewed-by: Christoph Hellwig Reviewed-by: Amir Goldstein Signed-off-by: Dave Chinner --- fs/ocfs2/refcounttree.c | 2 +- fs/read_write.c | 55 ++++++++++----------------------------- fs/xfs/xfs_reflink.c | 2 +- include/linux/fs.h | 9 ++++--- mm/filemap.c | 69 +++++++++++++++++++++++++++++++++++++++++++++++++ 5 files changed, 90 insertions(+), 47 deletions(-) (limited to 'mm') diff --git a/fs/ocfs2/refcounttree.c b/fs/ocfs2/refcounttree.c index 7a5ee145c733..19e03936c5e1 100644 --- a/fs/ocfs2/refcounttree.c +++ b/fs/ocfs2/refcounttree.c @@ -4850,7 +4850,7 @@ int ocfs2_reflink_remap_range(struct file *file_in, (OCFS2_I(inode_out)->ip_flags & OCFS2_INODE_SYSTEM_FILE)) goto out_unlock; - ret = vfs_clone_file_prep_inodes(inode_in, pos_in, inode_out, pos_out, + ret = vfs_clone_file_prep(file_in, pos_in, file_out, pos_out, &len, is_dedupe); if (ret <= 0) goto out_unlock; diff --git a/fs/read_write.c b/fs/read_write.c index 260797b01851..d6e8e242a15f 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -1717,13 +1717,12 @@ static int clone_verify_area(struct file *file, loff_t pos, u64 len, bool write) * Returns: 0 for "nothing to clone", 1 for "something to clone", or * the usual negative error code. */ -int vfs_clone_file_prep_inodes(struct inode *inode_in, loff_t pos_in, - struct inode *inode_out, loff_t pos_out, - u64 *len, bool is_dedupe) +int vfs_clone_file_prep(struct file *file_in, loff_t pos_in, + struct file *file_out, loff_t pos_out, + u64 *len, bool is_dedupe) { - loff_t bs = inode_out->i_sb->s_blocksize; - loff_t blen; - loff_t isize; + struct inode *inode_in = file_inode(file_in); + struct inode *inode_out = file_inode(file_out); bool same_inode = (inode_in == inode_out); int ret; @@ -1740,10 +1739,10 @@ int vfs_clone_file_prep_inodes(struct inode *inode_in, loff_t pos_in, if (!S_ISREG(inode_in->i_mode) || !S_ISREG(inode_out->i_mode)) return -EINVAL; - isize = i_size_read(inode_in); - /* Zero length dedupe exits immediately; reflink goes to EOF. */ if (*len == 0) { + loff_t isize = i_size_read(inode_in); + if (is_dedupe || pos_in == isize) return 0; if (pos_in > isize) @@ -1751,36 +1750,11 @@ int vfs_clone_file_prep_inodes(struct inode *inode_in, loff_t pos_in, *len = isize - pos_in; } - /* Ensure offsets don't wrap and the input is inside i_size */ - if (pos_in + *len < pos_in || pos_out + *len < pos_out || - pos_in + *len > isize) - return -EINVAL; - - /* Don't allow dedupe past EOF in the dest file */ - if (is_dedupe) { - loff_t disize; - - disize = i_size_read(inode_out); - if (pos_out >= disize || pos_out + *len > disize) - return -EINVAL; - } - - /* If we're linking to EOF, continue to the block boundary. */ - if (pos_in + *len == isize) - blen = ALIGN(isize, bs) - pos_in; - else - blen = *len; - - /* Only reflink if we're aligned to block boundaries */ - if (!IS_ALIGNED(pos_in, bs) || !IS_ALIGNED(pos_in + blen, bs) || - !IS_ALIGNED(pos_out, bs) || !IS_ALIGNED(pos_out + blen, bs)) - return -EINVAL; - - /* Don't allow overlapped reflink within the same file */ - if (same_inode) { - if (pos_out + blen > pos_in && pos_out < pos_in + blen) - return -EINVAL; - } + /* Check that we don't violate system file offset limits. */ + ret = generic_remap_checks(file_in, pos_in, file_out, pos_out, len, + is_dedupe); + if (ret) + return ret; /* Wait for the completion of any pending IOs on both files */ inode_dio_wait(inode_in); @@ -1813,7 +1787,7 @@ int vfs_clone_file_prep_inodes(struct inode *inode_in, loff_t pos_in, return 1; } -EXPORT_SYMBOL(vfs_clone_file_prep_inodes); +EXPORT_SYMBOL(vfs_clone_file_prep); int do_clone_file_range(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, u64 len) @@ -1851,9 +1825,6 @@ int do_clone_file_range(struct file *file_in, loff_t pos_in, if (ret) return ret; - if (pos_in + len > i_size_read(inode_in)) - return -EINVAL; - ret = file_in->f_op->clone_file_range(file_in, pos_in, file_out, pos_out, len); if (!ret) { diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c index 42ea7bab9144..281d5f53f2ec 100644 --- a/fs/xfs/xfs_reflink.c +++ b/fs/xfs/xfs_reflink.c @@ -1326,7 +1326,7 @@ xfs_reflink_remap_prep( if (IS_DAX(inode_in) || IS_DAX(inode_out)) goto out_unlock; - ret = vfs_clone_file_prep_inodes(inode_in, pos_in, inode_out, pos_out, + ret = vfs_clone_file_prep(file_in, pos_in, file_out, pos_out, len, is_dedupe); if (ret <= 0) goto out_unlock; diff --git a/include/linux/fs.h b/include/linux/fs.h index 897eae8faee1..ba93a6e7dac4 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1825,9 +1825,9 @@ extern ssize_t vfs_readv(struct file *, const struct iovec __user *, unsigned long, loff_t *, rwf_t); extern ssize_t vfs_copy_file_range(struct file *, loff_t , struct file *, loff_t, size_t, unsigned int); -extern int vfs_clone_file_prep_inodes(struct inode *inode_in, loff_t pos_in, - struct inode *inode_out, loff_t pos_out, - u64 *len, bool is_dedupe); +extern int vfs_clone_file_prep(struct file *file_in, loff_t pos_in, + struct file *file_out, loff_t pos_out, + u64 *count, bool is_dedupe); extern int do_clone_file_range(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, u64 len); extern int vfs_clone_file_range(struct file *file_in, loff_t pos_in, @@ -2967,6 +2967,9 @@ extern int sb_min_blocksize(struct super_block *, int); extern int generic_file_mmap(struct file *, struct vm_area_struct *); extern int generic_file_readonly_mmap(struct file *, struct vm_area_struct *); extern ssize_t generic_write_checks(struct kiocb *, struct iov_iter *); +extern int generic_remap_checks(struct file *file_in, loff_t pos_in, + struct file *file_out, loff_t pos_out, + uint64_t *count, bool is_dedupe); extern ssize_t generic_file_read_iter(struct kiocb *, struct iov_iter *); extern ssize_t __generic_file_write_iter(struct kiocb *, struct iov_iter *); extern ssize_t generic_file_write_iter(struct kiocb *, struct iov_iter *); diff --git a/mm/filemap.c b/mm/filemap.c index 52517f28e6f4..47e6bfd45a91 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -2974,6 +2974,75 @@ inline ssize_t generic_write_checks(struct kiocb *iocb, struct iov_iter *from) } EXPORT_SYMBOL(generic_write_checks); +/* + * Performs necessary checks before doing a clone. + * + * Can adjust amount of bytes to clone. + * Returns appropriate error code that caller should return or + * zero in case the clone should be allowed. + */ +int generic_remap_checks(struct file *file_in, loff_t pos_in, + struct file *file_out, loff_t pos_out, + uint64_t *req_count, bool is_dedupe) +{ + struct inode *inode_in = file_in->f_mapping->host; + struct inode *inode_out = file_out->f_mapping->host; + uint64_t count = *req_count; + uint64_t bcount; + loff_t size_in, size_out; + loff_t bs = inode_out->i_sb->s_blocksize; + + /* The start of both ranges must be aligned to an fs block. */ + if (!IS_ALIGNED(pos_in, bs) || !IS_ALIGNED(pos_out, bs)) + return -EINVAL; + + /* Ensure offsets don't wrap. */ + if (pos_in + count < pos_in || pos_out + count < pos_out) + return -EINVAL; + + size_in = i_size_read(inode_in); + size_out = i_size_read(inode_out); + + /* Dedupe requires both ranges to be within EOF. */ + if (is_dedupe && + (pos_in >= size_in || pos_in + count > size_in || + pos_out >= size_out || pos_out + count > size_out)) + return -EINVAL; + + /* Ensure the infile range is within the infile. */ + if (pos_in >= size_in) + return -EINVAL; + count = min(count, size_in - (uint64_t)pos_in); + + /* + * If the user wanted us to link to the infile's EOF, round up to the + * next block boundary for this check. + * + * Otherwise, make sure the count is also block-aligned, having + * already confirmed the starting offsets' block alignment. + */ + if (pos_in + count == size_in) { + bcount = ALIGN(size_in, bs) - pos_in; + } else { + if (!IS_ALIGNED(count, bs)) + return -EINVAL; + + bcount = count; + } + + /* Don't allow overlapped cloning within the same file. */ + if (inode_in == inode_out && + pos_out + bcount > pos_in && + pos_out < pos_in + bcount) + return -EINVAL; + + /* For now we don't support changing the length. */ + if (*req_count != count) + return -EINVAL; + + return 0; +} + int pagecache_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned flags, struct page **pagep, void **fsdata) -- cgit v1.2.3 From 9fd91a90cb9837372af24a804853e15c11aed93e Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 30 Oct 2018 10:40:46 +1100 Subject: vfs: strengthen checking of file range inputs to generic_remap_checks File range remapping, if allowed to run past the destination file's EOF, is an optimization on a regular file write. Regular file writes that extend the file length are subject to various constraints which are not checked by range cloning. This is a correctness problem because we're never allowed to touch ranges that the page cache can't support (s_maxbytes); we're not supposed to deal with large offsets (MAX_NON_LFS) if O_LARGEFILE isn't set; and we must obey resource limits (RLIMIT_FSIZE). Therefore, add these checks to the new generic_remap_checks function so that we curtail unexpected behavior. Signed-off-by: Darrick J. Wong Reviewed-by: Amir Goldstein Reviewed-by: Christoph Hellwig Signed-off-by: Dave Chinner --- mm/filemap.c | 84 +++++++++++++++++++++++++++++++++++++----------------------- 1 file changed, 52 insertions(+), 32 deletions(-) (limited to 'mm') diff --git a/mm/filemap.c b/mm/filemap.c index 47e6bfd45a91..84b7301e41a0 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -2915,6 +2915,42 @@ struct page *read_cache_page_gfp(struct address_space *mapping, } EXPORT_SYMBOL(read_cache_page_gfp); +/* + * Don't operate on ranges the page cache doesn't support, and don't exceed the + * LFS limits. If pos is under the limit it becomes a short access. If it + * exceeds the limit we return -EFBIG. + */ +static int generic_access_check_limits(struct file *file, loff_t pos, + loff_t *count) +{ + struct inode *inode = file->f_mapping->host; + loff_t max_size = inode->i_sb->s_maxbytes; + + if (!(file->f_flags & O_LARGEFILE)) + max_size = MAX_NON_LFS; + + if (unlikely(pos >= max_size)) + return -EFBIG; + *count = min(*count, max_size - pos); + return 0; +} + +static int generic_write_check_limits(struct file *file, loff_t pos, + loff_t *count) +{ + loff_t limit = rlimit(RLIMIT_FSIZE); + + if (limit != RLIM_INFINITY) { + if (pos >= limit) { + send_sig(SIGXFSZ, current, 0); + return -EFBIG; + } + *count = min(*count, limit - pos); + } + + return generic_access_check_limits(file, pos, count); +} + /* * Performs necessary checks before doing a write * @@ -2926,8 +2962,8 @@ inline ssize_t generic_write_checks(struct kiocb *iocb, struct iov_iter *from) { struct file *file = iocb->ki_filp; struct inode *inode = file->f_mapping->host; - unsigned long limit = rlimit(RLIMIT_FSIZE); - loff_t pos; + loff_t count; + int ret; if (!iov_iter_count(from)) return 0; @@ -2936,40 +2972,15 @@ inline ssize_t generic_write_checks(struct kiocb *iocb, struct iov_iter *from) if (iocb->ki_flags & IOCB_APPEND) iocb->ki_pos = i_size_read(inode); - pos = iocb->ki_pos; - if ((iocb->ki_flags & IOCB_NOWAIT) && !(iocb->ki_flags & IOCB_DIRECT)) return -EINVAL; - if (limit != RLIM_INFINITY) { - if (iocb->ki_pos >= limit) { - send_sig(SIGXFSZ, current, 0); - return -EFBIG; - } - iov_iter_truncate(from, limit - (unsigned long)pos); - } - - /* - * LFS rule - */ - if (unlikely(pos + iov_iter_count(from) > MAX_NON_LFS && - !(file->f_flags & O_LARGEFILE))) { - if (pos >= MAX_NON_LFS) - return -EFBIG; - iov_iter_truncate(from, MAX_NON_LFS - (unsigned long)pos); - } - - /* - * Are we about to exceed the fs block limit ? - * - * If we have written data it becomes a short write. If we have - * exceeded without writing data we send a signal and return EFBIG. - * Linus frestrict idea will clean these up nicely.. - */ - if (unlikely(pos >= inode->i_sb->s_maxbytes)) - return -EFBIG; + count = iov_iter_count(from); + ret = generic_write_check_limits(file, iocb->ki_pos, &count); + if (ret) + return ret; - iov_iter_truncate(from, inode->i_sb->s_maxbytes - pos); + iov_iter_truncate(from, count); return iov_iter_count(from); } EXPORT_SYMBOL(generic_write_checks); @@ -2991,6 +3002,7 @@ int generic_remap_checks(struct file *file_in, loff_t pos_in, uint64_t bcount; loff_t size_in, size_out; loff_t bs = inode_out->i_sb->s_blocksize; + int ret; /* The start of both ranges must be aligned to an fs block. */ if (!IS_ALIGNED(pos_in, bs) || !IS_ALIGNED(pos_out, bs)) @@ -3014,6 +3026,14 @@ int generic_remap_checks(struct file *file_in, loff_t pos_in, return -EINVAL; count = min(count, size_in - (uint64_t)pos_in); + ret = generic_access_check_limits(file_in, pos_in, &count); + if (ret) + return ret; + + ret = generic_write_check_limits(file_out, pos_out, &count); + if (ret) + return ret; + /* * If the user wanted us to link to the infile's EOF, round up to the * next block boundary for this check. -- cgit v1.2.3 From 3d28193e1df043764deb7abdaba5e3a6660bc393 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 30 Oct 2018 10:41:34 +1100 Subject: vfs: pass remap flags to generic_remap_checks Pass the same remap flags to generic_remap_checks for consistency. Signed-off-by: Darrick J. Wong Reviewed-by: Amir Goldstein Reviewed-by: Christoph Hellwig Signed-off-by: Dave Chinner --- fs/read_write.c | 2 +- include/linux/fs.h | 2 +- mm/filemap.c | 4 ++-- 3 files changed, 4 insertions(+), 4 deletions(-) (limited to 'mm') diff --git a/fs/read_write.c b/fs/read_write.c index 201381689284..ebcbfc4f2907 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -1782,7 +1782,7 @@ int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in, /* Check that we don't violate system file offset limits. */ ret = generic_remap_checks(file_in, pos_in, file_out, pos_out, len, - (remap_flags & REMAP_FILE_DEDUP)); + remap_flags); if (ret) return ret; diff --git a/include/linux/fs.h b/include/linux/fs.h index 631c28ce1436..c5435ca81132 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2986,7 +2986,7 @@ extern int generic_file_readonly_mmap(struct file *, struct vm_area_struct *); extern ssize_t generic_write_checks(struct kiocb *, struct iov_iter *); extern int generic_remap_checks(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, - uint64_t *count, bool is_dedupe); + uint64_t *count, unsigned int remap_flags); extern ssize_t generic_file_read_iter(struct kiocb *, struct iov_iter *); extern ssize_t __generic_file_write_iter(struct kiocb *, struct iov_iter *); extern ssize_t generic_file_write_iter(struct kiocb *, struct iov_iter *); diff --git a/mm/filemap.c b/mm/filemap.c index 84b7301e41a0..410dc58f7b16 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -2994,7 +2994,7 @@ EXPORT_SYMBOL(generic_write_checks); */ int generic_remap_checks(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, - uint64_t *req_count, bool is_dedupe) + uint64_t *req_count, unsigned int remap_flags) { struct inode *inode_in = file_in->f_mapping->host; struct inode *inode_out = file_out->f_mapping->host; @@ -3016,7 +3016,7 @@ int generic_remap_checks(struct file *file_in, loff_t pos_in, size_out = i_size_read(inode_out); /* Dedupe requires both ranges to be within EOF. */ - if (is_dedupe && + if ((remap_flags & REMAP_FILE_DEDUP) && (pos_in >= size_in || pos_in + count > size_in || pos_out >= size_out || pos_out + count > size_out)) return -EINVAL; -- cgit v1.2.3 From 42ec3d4c02187a18e27ff94b409ec27234bf2ffd Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 30 Oct 2018 10:41:49 +1100 Subject: vfs: make remap_file_range functions take and return bytes completed Change the remap_file_range functions to take a number of bytes to operate upon and return the number of bytes they operated on. This is a requirement for allowing fs implementations to return short clone/dedupe results to the user, which will enable us to obey resource limits in a graceful manner. A subsequent patch will enable copy_file_range to signal to the ->clone_file_range implementation that it can handle a short length, which will be returned in the function's return value. For now the short return is not implemented anywhere so the behavior won't change -- either copy_file_range manages to clone the entire range or it tries an alternative. Neither clone ioctl can take advantage of this, alas. Signed-off-by: Darrick J. Wong Reviewed-by: Amir Goldstein Signed-off-by: Dave Chinner --- Documentation/filesystems/vfs.txt | 10 ++++---- fs/btrfs/ctree.h | 6 ++--- fs/btrfs/ioctl.c | 13 +++++++---- fs/cifs/cifsfs.c | 6 ++--- fs/ioctl.c | 10 +++++++- fs/nfs/nfs4file.c | 6 ++--- fs/nfsd/vfs.c | 8 +++++-- fs/ocfs2/file.c | 16 ++++++------- fs/ocfs2/refcounttree.c | 2 +- fs/ocfs2/refcounttree.h | 2 +- fs/overlayfs/copy_up.c | 6 ++--- fs/overlayfs/file.c | 12 +++++----- fs/read_write.c | 49 +++++++++++++++++++++------------------ fs/xfs/xfs_file.c | 9 ++++--- fs/xfs/xfs_reflink.c | 4 ++-- fs/xfs/xfs_reflink.h | 2 +- include/linux/fs.h | 27 +++++++++++---------- mm/filemap.c | 2 +- 18 files changed, 108 insertions(+), 82 deletions(-) (limited to 'mm') diff --git a/Documentation/filesystems/vfs.txt b/Documentation/filesystems/vfs.txt index 6f5babfee27b..1bd2919deaca 100644 --- a/Documentation/filesystems/vfs.txt +++ b/Documentation/filesystems/vfs.txt @@ -883,9 +883,9 @@ struct file_operations { unsigned (*mmap_capabilities)(struct file *); #endif ssize_t (*copy_file_range)(struct file *, loff_t, struct file *, loff_t, size_t, unsigned int); - int (*remap_file_range)(struct file *file_in, loff_t pos_in, - struct file *file_out, loff_t pos_out, - u64 len, unsigned int remap_flags); + loff_t (*remap_file_range)(struct file *file_in, loff_t pos_in, + struct file *file_out, loff_t pos_out, + loff_t len, unsigned int remap_flags); int (*fadvise)(struct file *, loff_t, loff_t, int); }; @@ -966,8 +966,8 @@ otherwise noted. implementation should remap len bytes at pos_in of the source file into the dest file at pos_out. Implementations must handle callers passing in len == 0; this means "remap to the end of the source file". The - return value should be zero if all bytes were remapped, or the usual - negative error code if the remapping did not succeed completely. + return value should the number of bytes remapped, or the usual + negative error code if errors occurred before any bytes were remapped. The remap_flags parameter accepts REMAP_FILE_* flags. If REMAP_FILE_DEDUP is set then the implementation must only remap if the requested file ranges have identical contents. diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 124a05662fc2..771a961d77ad 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -3247,9 +3247,9 @@ int btrfs_dirty_pages(struct inode *inode, struct page **pages, size_t num_pages, loff_t pos, size_t write_bytes, struct extent_state **cached); int btrfs_fdatawrite_range(struct inode *inode, loff_t start, loff_t end); -int btrfs_remap_file_range(struct file *file_in, loff_t pos_in, - struct file *file_out, loff_t pos_out, u64 len, - unsigned int remap_flags); +loff_t btrfs_remap_file_range(struct file *file_in, loff_t pos_in, + struct file *file_out, loff_t pos_out, + loff_t len, unsigned int remap_flags); /* tree-defrag.c */ int btrfs_defrag_leaves(struct btrfs_trans_handle *trans, diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index bfd99c66723e..b0c513e10977 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -4328,10 +4328,12 @@ out_unlock: return ret; } -int btrfs_remap_file_range(struct file *src_file, loff_t off, - struct file *dst_file, loff_t destoff, u64 len, +loff_t btrfs_remap_file_range(struct file *src_file, loff_t off, + struct file *dst_file, loff_t destoff, loff_t len, unsigned int remap_flags) { + int ret; + if (remap_flags & ~(REMAP_FILE_DEDUP | REMAP_FILE_ADVISORY)) return -EINVAL; @@ -4349,10 +4351,11 @@ int btrfs_remap_file_range(struct file *src_file, loff_t off, return -EINVAL; } - return btrfs_extent_same(src, off, len, dst, destoff); + ret = btrfs_extent_same(src, off, len, dst, destoff); + } else { + ret = btrfs_clone_files(dst_file, src_file, off, len, destoff); } - - return btrfs_clone_files(dst_file, src_file, off, len, destoff); + return ret < 0 ? ret : len; } static long btrfs_ioctl_default_subvol(struct file *file, void __user *argp) diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index e8144d0dcde2..5ca71c6c8be2 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -975,8 +975,8 @@ const struct inode_operations cifs_symlink_inode_ops = { .listxattr = cifs_listxattr, }; -static int cifs_remap_file_range(struct file *src_file, loff_t off, - struct file *dst_file, loff_t destoff, u64 len, +static loff_t cifs_remap_file_range(struct file *src_file, loff_t off, + struct file *dst_file, loff_t destoff, loff_t len, unsigned int remap_flags) { struct inode *src_inode = file_inode(src_file); @@ -1029,7 +1029,7 @@ static int cifs_remap_file_range(struct file *src_file, loff_t off, unlock_two_nondirectories(src_inode, target_inode); out: free_xid(xid); - return rc; + return rc < 0 ? rc : len; } ssize_t cifs_file_copychunk_range(unsigned int xid, diff --git a/fs/ioctl.c b/fs/ioctl.c index 2005529af560..72537b68c272 100644 --- a/fs/ioctl.c +++ b/fs/ioctl.c @@ -223,6 +223,7 @@ static long ioctl_file_clone(struct file *dst_file, unsigned long srcfd, u64 off, u64 olen, u64 destoff) { struct fd src_file = fdget(srcfd); + loff_t cloned; int ret; if (!src_file.file) @@ -230,7 +231,14 @@ static long ioctl_file_clone(struct file *dst_file, unsigned long srcfd, ret = -EXDEV; if (src_file.file->f_path.mnt != dst_file->f_path.mnt) goto fdput; - ret = vfs_clone_file_range(src_file.file, off, dst_file, destoff, olen); + cloned = vfs_clone_file_range(src_file.file, off, dst_file, destoff, + olen); + if (cloned < 0) + ret = cloned; + else if (olen && cloned != olen) + ret = -EINVAL; + else + ret = 0; fdput: fdput(src_file); return ret; diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c index ae5780ce41dc..46d691ba04bc 100644 --- a/fs/nfs/nfs4file.c +++ b/fs/nfs/nfs4file.c @@ -180,8 +180,8 @@ static long nfs42_fallocate(struct file *filep, int mode, loff_t offset, loff_t return nfs42_proc_allocate(filep, offset, len); } -static int nfs42_remap_file_range(struct file *src_file, loff_t src_off, - struct file *dst_file, loff_t dst_off, u64 count, +static loff_t nfs42_remap_file_range(struct file *src_file, loff_t src_off, + struct file *dst_file, loff_t dst_off, loff_t count, unsigned int remap_flags) { struct inode *dst_inode = file_inode(dst_file); @@ -244,7 +244,7 @@ out_unlock: inode_unlock(src_inode); } out: - return ret; + return ret < 0 ? ret : count; } #endif /* CONFIG_NFS_V4_2 */ diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index b53e76391e52..ac6cb6101cbe 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -541,8 +541,12 @@ __be32 nfsd4_set_nfs4_label(struct svc_rqst *rqstp, struct svc_fh *fhp, __be32 nfsd4_clone_file_range(struct file *src, u64 src_pos, struct file *dst, u64 dst_pos, u64 count) { - return nfserrno(vfs_clone_file_range(src, src_pos, dst, dst_pos, - count)); + loff_t cloned; + + cloned = vfs_clone_file_range(src, src_pos, dst, dst_pos, count); + if (count && cloned != count) + cloned = -EINVAL; + return nfserrno(cloned < 0 ? cloned : 0); } ssize_t nfsd_copy_file_range(struct file *src, u64 src_pos, struct file *dst, diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index 9809b0e5746f..fbaeafe44b5f 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -2527,18 +2527,18 @@ out: return offset; } -static int ocfs2_remap_file_range(struct file *file_in, - loff_t pos_in, - struct file *file_out, - loff_t pos_out, - u64 len, - unsigned int remap_flags) +static loff_t ocfs2_remap_file_range(struct file *file_in, loff_t pos_in, + struct file *file_out, loff_t pos_out, + loff_t len, unsigned int remap_flags) { + int ret; + if (remap_flags & ~(REMAP_FILE_DEDUP | REMAP_FILE_ADVISORY)) return -EINVAL; - return ocfs2_reflink_remap_range(file_in, pos_in, file_out, pos_out, - len, remap_flags); + ret = ocfs2_reflink_remap_range(file_in, pos_in, file_out, pos_out, + len, remap_flags); + return ret < 0 ? ret : len; } const struct inode_operations ocfs2_file_iops = { diff --git a/fs/ocfs2/refcounttree.c b/fs/ocfs2/refcounttree.c index df9781567ec0..6a42c04ac0ab 100644 --- a/fs/ocfs2/refcounttree.c +++ b/fs/ocfs2/refcounttree.c @@ -4824,7 +4824,7 @@ int ocfs2_reflink_remap_range(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, - u64 len, + loff_t len, unsigned int remap_flags) { struct inode *inode_in = file_inode(file_in); diff --git a/fs/ocfs2/refcounttree.h b/fs/ocfs2/refcounttree.h index d2c5f526edff..eb65c1d0843c 100644 --- a/fs/ocfs2/refcounttree.h +++ b/fs/ocfs2/refcounttree.h @@ -119,7 +119,7 @@ int ocfs2_reflink_remap_range(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, - u64 len, + loff_t len, unsigned int remap_flags); #endif /* OCFS2_REFCOUNTTREE_H */ diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c index 1cc797a08a5b..8750b7235516 100644 --- a/fs/overlayfs/copy_up.c +++ b/fs/overlayfs/copy_up.c @@ -125,6 +125,7 @@ static int ovl_copy_up_data(struct path *old, struct path *new, loff_t len) struct file *new_file; loff_t old_pos = 0; loff_t new_pos = 0; + loff_t cloned; int error = 0; if (len == 0) @@ -141,11 +142,10 @@ static int ovl_copy_up_data(struct path *old, struct path *new, loff_t len) } /* Try to use clone_file_range to clone up within the same fs */ - error = do_clone_file_range(old_file, 0, new_file, 0, len); - if (!error) + cloned = do_clone_file_range(old_file, 0, new_file, 0, len); + if (cloned == len) goto out; /* Couldn't clone, so now we try to copy the data */ - error = 0; /* FIXME: copy up sparse files efficiently */ while (len) { diff --git a/fs/overlayfs/file.c b/fs/overlayfs/file.c index fffb36fd5920..6c3fec6168e9 100644 --- a/fs/overlayfs/file.c +++ b/fs/overlayfs/file.c @@ -434,14 +434,14 @@ enum ovl_copyop { OVL_DEDUPE, }; -static ssize_t ovl_copyfile(struct file *file_in, loff_t pos_in, +static loff_t ovl_copyfile(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, - u64 len, unsigned int flags, enum ovl_copyop op) + loff_t len, unsigned int flags, enum ovl_copyop op) { struct inode *inode_out = file_inode(file_out); struct fd real_in, real_out; const struct cred *old_cred; - ssize_t ret; + loff_t ret; ret = ovl_real_fdget(file_out, &real_out); if (ret) @@ -489,9 +489,9 @@ static ssize_t ovl_copy_file_range(struct file *file_in, loff_t pos_in, OVL_COPY); } -static int ovl_remap_file_range(struct file *file_in, loff_t pos_in, - struct file *file_out, loff_t pos_out, - u64 len, unsigned int remap_flags) +static loff_t ovl_remap_file_range(struct file *file_in, loff_t pos_in, + struct file *file_out, loff_t pos_out, + loff_t len, unsigned int remap_flags) { enum ovl_copyop op; diff --git a/fs/read_write.c b/fs/read_write.c index b61bd3fc7154..356641afa487 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -1589,10 +1589,13 @@ ssize_t vfs_copy_file_range(struct file *file_in, loff_t pos_in, * more efficient if both clone and copy are supported (e.g. NFS). */ if (file_in->f_op->remap_file_range) { - ret = file_in->f_op->remap_file_range(file_in, pos_in, - file_out, pos_out, len, 0); - if (ret == 0) { - ret = len; + loff_t cloned; + + cloned = file_in->f_op->remap_file_range(file_in, pos_in, + file_out, pos_out, + min_t(loff_t, MAX_RW_COUNT, len), 0); + if (cloned > 0) { + ret = cloned; goto done; } } @@ -1686,11 +1689,12 @@ out2: return ret; } -static int remap_verify_area(struct file *file, loff_t pos, u64 len, bool write) +static int remap_verify_area(struct file *file, loff_t pos, loff_t len, + bool write) { struct inode *inode = file_inode(file); - if (unlikely(pos < 0)) + if (unlikely(pos < 0 || len < 0)) return -EINVAL; if (unlikely((loff_t) (pos + len) < 0)) @@ -1721,7 +1725,7 @@ static int remap_verify_area(struct file *file, loff_t pos, u64 len, bool write) static int generic_remap_check_len(struct inode *inode_in, struct inode *inode_out, loff_t pos_out, - u64 *len, + loff_t *len, unsigned int remap_flags) { u64 blkmask = i_blocksize(inode_in) - 1; @@ -1747,7 +1751,7 @@ static int generic_remap_check_len(struct inode *inode_in, */ int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, - u64 *len, unsigned int remap_flags) + loff_t *len, unsigned int remap_flags) { struct inode *inode_in = file_inode(file_in); struct inode *inode_out = file_inode(file_out); @@ -1843,12 +1847,12 @@ int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in, } EXPORT_SYMBOL(generic_remap_file_range_prep); -int do_clone_file_range(struct file *file_in, loff_t pos_in, - struct file *file_out, loff_t pos_out, u64 len) +loff_t do_clone_file_range(struct file *file_in, loff_t pos_in, + struct file *file_out, loff_t pos_out, loff_t len) { struct inode *inode_in = file_inode(file_in); struct inode *inode_out = file_inode(file_out); - int ret; + loff_t ret; if (S_ISDIR(inode_in->i_mode) || S_ISDIR(inode_out->i_mode)) return -EISDIR; @@ -1881,19 +1885,19 @@ int do_clone_file_range(struct file *file_in, loff_t pos_in, ret = file_in->f_op->remap_file_range(file_in, pos_in, file_out, pos_out, len, 0); - if (!ret) { - fsnotify_access(file_in); - fsnotify_modify(file_out); - } + if (ret < 0) + return ret; + fsnotify_access(file_in); + fsnotify_modify(file_out); return ret; } EXPORT_SYMBOL(do_clone_file_range); -int vfs_clone_file_range(struct file *file_in, loff_t pos_in, - struct file *file_out, loff_t pos_out, u64 len) +loff_t vfs_clone_file_range(struct file *file_in, loff_t pos_in, + struct file *file_out, loff_t pos_out, loff_t len) { - int ret; + loff_t ret; file_start_write(file_out); ret = do_clone_file_range(file_in, pos_in, file_out, pos_out, len); @@ -1999,10 +2003,11 @@ out_error: } EXPORT_SYMBOL(vfs_dedupe_file_range_compare); -int vfs_dedupe_file_range_one(struct file *src_file, loff_t src_pos, - struct file *dst_file, loff_t dst_pos, u64 len) +loff_t vfs_dedupe_file_range_one(struct file *src_file, loff_t src_pos, + struct file *dst_file, loff_t dst_pos, + loff_t len) { - s64 ret; + loff_t ret; ret = mnt_want_write_file(dst_file); if (ret) @@ -2051,7 +2056,7 @@ int vfs_dedupe_file_range(struct file *file, struct file_dedupe_range *same) int i; int ret; u16 count = same->dest_count; - int deduped; + loff_t deduped; if (!(file->f_mode & FMODE_READ)) return -EINVAL; diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index 20314eb4677a..38fde4e11714 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -919,20 +919,23 @@ out_unlock: return error; } -STATIC int +STATIC loff_t xfs_file_remap_range( struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, - u64 len, + loff_t len, unsigned int remap_flags) { + int ret; + if (remap_flags & ~(REMAP_FILE_DEDUP | REMAP_FILE_ADVISORY)) return -EINVAL; - return xfs_reflink_remap_range(file_in, pos_in, file_out, pos_out, + ret = xfs_reflink_remap_range(file_in, pos_in, file_out, pos_out, len, remap_flags); + return ret < 0 ? ret : len; } STATIC int diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c index 2d7dd8b28d7c..3dbe5fb7e9c0 100644 --- a/fs/xfs/xfs_reflink.c +++ b/fs/xfs/xfs_reflink.c @@ -1296,7 +1296,7 @@ xfs_reflink_remap_prep( loff_t pos_in, struct file *file_out, loff_t pos_out, - u64 *len, + loff_t *len, unsigned int remap_flags) { struct inode *inode_in = file_inode(file_in); @@ -1387,7 +1387,7 @@ xfs_reflink_remap_range( loff_t pos_in, struct file *file_out, loff_t pos_out, - u64 len, + loff_t len, unsigned int remap_flags) { struct inode *inode_in = file_inode(file_in); diff --git a/fs/xfs/xfs_reflink.h b/fs/xfs/xfs_reflink.h index 6f82d628bf17..c3c46c276fe1 100644 --- a/fs/xfs/xfs_reflink.h +++ b/fs/xfs/xfs_reflink.h @@ -28,7 +28,7 @@ extern int xfs_reflink_end_cow(struct xfs_inode *ip, xfs_off_t offset, xfs_off_t count); extern int xfs_reflink_recover_cow(struct xfs_mount *mp); extern int xfs_reflink_remap_range(struct file *file_in, loff_t pos_in, - struct file *file_out, loff_t pos_out, u64 len, + struct file *file_out, loff_t pos_out, loff_t len, unsigned int remap_flags); extern int xfs_reflink_inode_has_shared_extents(struct xfs_trans *tp, struct xfs_inode *ip, bool *has_shared); diff --git a/include/linux/fs.h b/include/linux/fs.h index c5435ca81132..c72d8c3c065a 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1777,9 +1777,9 @@ struct file_operations { #endif ssize_t (*copy_file_range)(struct file *, loff_t, struct file *, loff_t, size_t, unsigned int); - int (*remap_file_range)(struct file *file_in, loff_t pos_in, - struct file *file_out, loff_t pos_out, - u64 len, unsigned int remap_flags); + loff_t (*remap_file_range)(struct file *file_in, loff_t pos_in, + struct file *file_out, loff_t pos_out, + loff_t len, unsigned int remap_flags); int (*fadvise)(struct file *, loff_t, loff_t, int); } __randomize_layout; @@ -1844,19 +1844,22 @@ extern ssize_t vfs_copy_file_range(struct file *, loff_t , struct file *, loff_t, size_t, unsigned int); extern int generic_remap_file_range_prep(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, - u64 *count, unsigned int remap_flags); -extern int do_clone_file_range(struct file *file_in, loff_t pos_in, - struct file *file_out, loff_t pos_out, u64 len); -extern int vfs_clone_file_range(struct file *file_in, loff_t pos_in, - struct file *file_out, loff_t pos_out, u64 len); + loff_t *count, + unsigned int remap_flags); +extern loff_t do_clone_file_range(struct file *file_in, loff_t pos_in, + struct file *file_out, loff_t pos_out, + loff_t len); +extern loff_t vfs_clone_file_range(struct file *file_in, loff_t pos_in, + struct file *file_out, loff_t pos_out, + loff_t len); extern int vfs_dedupe_file_range_compare(struct inode *src, loff_t srcoff, struct inode *dest, loff_t destoff, loff_t len, bool *is_same); extern int vfs_dedupe_file_range(struct file *file, struct file_dedupe_range *same); -extern int vfs_dedupe_file_range_one(struct file *src_file, loff_t src_pos, - struct file *dst_file, loff_t dst_pos, - u64 len); +extern loff_t vfs_dedupe_file_range_one(struct file *src_file, loff_t src_pos, + struct file *dst_file, loff_t dst_pos, + loff_t len); struct super_operations { @@ -2986,7 +2989,7 @@ extern int generic_file_readonly_mmap(struct file *, struct vm_area_struct *); extern ssize_t generic_write_checks(struct kiocb *, struct iov_iter *); extern int generic_remap_checks(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, - uint64_t *count, unsigned int remap_flags); + loff_t *count, unsigned int remap_flags); extern ssize_t generic_file_read_iter(struct kiocb *, struct iov_iter *); extern ssize_t __generic_file_write_iter(struct kiocb *, struct iov_iter *); extern ssize_t generic_file_write_iter(struct kiocb *, struct iov_iter *); diff --git a/mm/filemap.c b/mm/filemap.c index 410dc58f7b16..e9091d731f84 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -2994,7 +2994,7 @@ EXPORT_SYMBOL(generic_write_checks); */ int generic_remap_checks(struct file *file_in, loff_t pos_in, struct file *file_out, loff_t pos_out, - uint64_t *req_count, unsigned int remap_flags) + loff_t *req_count, unsigned int remap_flags) { struct inode *inode_in = file_in->f_mapping->host; struct inode *inode_out = file_out->f_mapping->host; -- cgit v1.2.3 From eca3654e3cc7d93e9734d0fa96cfb15c7f356244 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 30 Oct 2018 10:42:10 +1100 Subject: vfs: enable remap callers that can handle short operations Plumb in a remap flag that enables the filesystem remap handler to shorten remapping requests for callers that can handle it. Now copy_file_range can report partial success (in case we run up against alignment problems, resource limits, etc.). We also enable CAN_SHORTEN for fideduperange to maintain existing userspace-visible behavior where xfs/btrfs shorten the dedupe range to avoid stale post-eof data exposure. Signed-off-by: Darrick J. Wong Reviewed-by: Amir Goldstein Signed-off-by: Dave Chinner --- Documentation/filesystems/vfs.txt | 4 +++- fs/read_write.c | 28 ++++++++++++++++++++-------- include/linux/fs.h | 5 +++-- mm/filemap.c | 11 +++++++---- 4 files changed, 33 insertions(+), 15 deletions(-) (limited to 'mm') diff --git a/Documentation/filesystems/vfs.txt b/Documentation/filesystems/vfs.txt index 1bd2919deaca..5f71a252e2e0 100644 --- a/Documentation/filesystems/vfs.txt +++ b/Documentation/filesystems/vfs.txt @@ -970,7 +970,9 @@ otherwise noted. negative error code if errors occurred before any bytes were remapped. The remap_flags parameter accepts REMAP_FILE_* flags. If REMAP_FILE_DEDUP is set then the implementation must only remap if the - requested file ranges have identical contents. + requested file ranges have identical contents. If REMAP_CAN_SHORTEN is + set, the caller is ok with the implementation shortening the request + length to satisfy alignment or EOF requirements (or any other reason). fadvise: possibly called by the fadvise64() system call. diff --git a/fs/read_write.c b/fs/read_write.c index ea30666013b0..c0bcc1a20650 100644 --- a/fs/read_write.c +++ b/fs/read_write.c @@ -1593,7 +1593,8 @@ ssize_t vfs_copy_file_range(struct file *file_in, loff_t pos_in, cloned = file_in->f_op->remap_file_range(file_in, pos_in, file_out, pos_out, - min_t(loff_t, MAX_RW_COUNT, len), 0); + min_t(loff_t, MAX_RW_COUNT, len), + REMAP_FILE_CAN_SHORTEN); if (cloned > 0) { ret = cloned; goto done; @@ -1721,6 +1722,8 @@ static int remap_verify_area(struct file *file, loff_t pos, loff_t len, * can't meaningfully compare post-EOF contents. * * For clone we only link a partial EOF block above the destination file's EOF. + * + * Shorten the request if possible. */ static int generic_remap_check_len(struct inode *inode_in, struct inode *inode_out, @@ -1729,16 +1732,24 @@ static int generic_remap_check_len(struct inode *inode_in, unsigned int remap_flags) { u64 blkmask = i_blocksize(inode_in) - 1; + loff_t new_len = *len; if ((*len & blkmask) == 0) return 0; - if (remap_flags & REMAP_FILE_DEDUP) - *len &= ~blkmask; - else if (pos_out + *len < i_size_read(inode_out)) - return -EINVAL; + if ((remap_flags & REMAP_FILE_DEDUP) || + pos_out + *len < i_size_read(inode_out)) + new_len &= ~blkmask; - return 0; + if (new_len == *len) + return 0; + + if (remap_flags & REMAP_FILE_CAN_SHORTEN) { + *len = new_len; + return 0; + } + + return (remap_flags & REMAP_FILE_DEDUP) ? -EBADE : -EINVAL; } /* @@ -2014,7 +2025,8 @@ loff_t vfs_dedupe_file_range_one(struct file *src_file, loff_t src_pos, { loff_t ret; - WARN_ON_ONCE(remap_flags & ~(REMAP_FILE_DEDUP)); + WARN_ON_ONCE(remap_flags & ~(REMAP_FILE_DEDUP | + REMAP_FILE_CAN_SHORTEN)); ret = mnt_want_write_file(dst_file); if (ret) @@ -2115,7 +2127,7 @@ int vfs_dedupe_file_range(struct file *file, struct file_dedupe_range *same) deduped = vfs_dedupe_file_range_one(file, off, dst_file, info->dest_offset, len, - 0); + REMAP_FILE_CAN_SHORTEN); if (deduped == -EBADE) info->status = FILE_DEDUPE_RANGE_DIFFERS; else if (deduped < 0) diff --git a/include/linux/fs.h b/include/linux/fs.h index 544ab5083b48..34c22d695011 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1727,8 +1727,10 @@ struct block_device_operations; * See Documentation/filesystems/vfs.txt for more details about this call. * * REMAP_FILE_DEDUP: only remap if contents identical (i.e. deduplicate) + * REMAP_FILE_CAN_SHORTEN: caller can handle a shortened request */ #define REMAP_FILE_DEDUP (1 << 0) +#define REMAP_FILE_CAN_SHORTEN (1 << 1) /* * These flags signal that the caller is ok with altering various aspects of @@ -1736,9 +1738,8 @@ struct block_device_operations; * implementation; the vfs remap helper functions can take advantage of them. * Flags in this category exist to preserve the quirky behavior of the hoisted * btrfs clone/dedupe ioctls. - * There are no flags yet, but subsequent commits will add some. */ -#define REMAP_FILE_ADVISORY (0) +#define REMAP_FILE_ADVISORY (REMAP_FILE_CAN_SHORTEN) struct iov_iter; diff --git a/mm/filemap.c b/mm/filemap.c index e9091d731f84..1775d4ad3317 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -3045,8 +3045,7 @@ int generic_remap_checks(struct file *file_in, loff_t pos_in, bcount = ALIGN(size_in, bs) - pos_in; } else { if (!IS_ALIGNED(count, bs)) - return -EINVAL; - + count = ALIGN_DOWN(count, bs); bcount = count; } @@ -3056,10 +3055,14 @@ int generic_remap_checks(struct file *file_in, loff_t pos_in, pos_out < pos_in + bcount) return -EINVAL; - /* For now we don't support changing the length. */ - if (*req_count != count) + /* + * We shortened the request but the caller can't deal with that, so + * bounce the request back to userspace. + */ + if (*req_count != count && !(remap_flags & REMAP_FILE_CAN_SHORTEN)) return -EINVAL; + *req_count = count; return 0; } -- cgit v1.2.3 From f813f21971b96f61a789dd48151f92220fdd2e0a Mon Sep 17 00:00:00 2001 From: Jérôme Glisse Date: Tue, 30 Oct 2018 15:04:06 -0700 Subject: mm/hmm: fix utf8 ... MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Patch series "HMM updates, improvements and fixes", v2 Few fixes that only affect HMM users. Improve the synchronization call back so that we match was other mmu_notifier listener do and add proper support to the new blockable flags in the process. For curious folks here are branches to leverage HMM in various existing device drivers: https://cgit.freedesktop.org/~glisse/linux/log/?h=hmm-nouveau-v01 https://cgit.freedesktop.org/~glisse/linux/log/?h=hmm-radeon-v00 https://cgit.freedesktop.org/~glisse/linux/log/?h=hmm-intel-v00 More to come (amd gpu, Mellanox, ...) I expect more of the preparatory work for nouveau will be merge in 4.20 (like we have been doing since 4.16) and i will wait until this patchset is upstream before pushing the patches that actualy make use of HMM (to avoid complex tree inter-dependency). This patch (of 6): Somehow utf=8 must have been broken. Link: http://lkml.kernel.org/r/20181019160442.18723-2-jglisse@redhat.com Signed-off-by: Jérôme Glisse Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hmm.h | 2 +- mm/hmm.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'mm') diff --git a/include/linux/hmm.h b/include/linux/hmm.h index dde947083d4e..42b1ae915915 100644 --- a/include/linux/hmm.h +++ b/include/linux/hmm.h @@ -11,7 +11,7 @@ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. * - * Authors: Jérôme Glisse + * Authors: Jérôme Glisse */ /* * Heterogeneous Memory Management (HMM) diff --git a/mm/hmm.c b/mm/hmm.c index 774d684fa2b4..de9840f60100 100644 --- a/mm/hmm.c +++ b/mm/hmm.c @@ -11,7 +11,7 @@ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. * - * Authors: Jérôme Glisse + * Authors: Jérôme Glisse */ /* * Refer to include/linux/hmm.h for information about heterogeneous memory -- cgit v1.2.3 From aab8d0520e6e7c2a61f71195e6ce7007a4843afb Mon Sep 17 00:00:00 2001 From: Ralph Campbell Date: Tue, 30 Oct 2018 15:04:11 -0700 Subject: mm/rmap: map_pte() was not handling private ZONE_DEVICE page properly MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Private ZONE_DEVICE pages use a special pte entry and thus are not present. Properly handle this case in map_pte(), it is already handled in check_pte(), the map_pte() part was lost in some rebase most probably. Without this patch the slow migration path can not migrate back to any private ZONE_DEVICE memory to regular memory. This was found after stress testing migration back to system memory. This ultimatly can lead to the CPU constantly page fault looping on the special swap entry. Link: http://lkml.kernel.org/r/20181019160442.18723-3-jglisse@redhat.com Signed-off-by: Ralph Campbell Signed-off-by: Jérôme Glisse Reviewed-by: Balbir Singh Cc: Andrew Morton Cc: Kirill A. Shutemov Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/page_vma_mapped.c | 24 +++++++++++++++++++++++- 1 file changed, 23 insertions(+), 1 deletion(-) (limited to 'mm') diff --git a/mm/page_vma_mapped.c b/mm/page_vma_mapped.c index ae3c2a35d61b..11df03e71288 100644 --- a/mm/page_vma_mapped.c +++ b/mm/page_vma_mapped.c @@ -21,7 +21,29 @@ static bool map_pte(struct page_vma_mapped_walk *pvmw) if (!is_swap_pte(*pvmw->pte)) return false; } else { - if (!pte_present(*pvmw->pte)) + /* + * We get here when we are trying to unmap a private + * device page from the process address space. Such + * page is not CPU accessible and thus is mapped as + * a special swap entry, nonetheless it still does + * count as a valid regular mapping for the page (and + * is accounted as such in page maps count). + * + * So handle this special case as if it was a normal + * page mapping ie lock CPU page table and returns + * true. + * + * For more details on device private memory see HMM + * (include/linux/hmm.h or mm/hmm.c). + */ + if (is_swap_pte(*pvmw->pte)) { + swp_entry_t entry; + + /* Handle un-addressable ZONE_DEVICE memory */ + entry = pte_to_swp_entry(*pvmw->pte); + if (!is_device_private_entry(entry)) + return false; + } else if (!pte_present(*pvmw->pte)) return false; } } -- cgit v1.2.3 From 86a2d59841ab0b147ffc1b7b3041af87927cf312 Mon Sep 17 00:00:00 2001 From: Ralph Campbell Date: Tue, 30 Oct 2018 15:04:14 -0700 Subject: mm/hmm: fix race between hmm_mirror_unregister() and mmu_notifier callback MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit In hmm_mirror_unregister(), mm->hmm is set to NULL and then mmu_notifier_unregister_no_release() is called. That creates a small window where mmu_notifier can call mmu_notifier_ops with mm->hmm equal to NULL. Fix this by first unregistering mmu notifier callbacks and then setting mm->hmm to NULL. Similarly in hmm_register(), set mm->hmm before registering mmu_notifier callbacks so callback functions always see mm->hmm set. Link: http://lkml.kernel.org/r/20181019160442.18723-4-jglisse@redhat.com Signed-off-by: Ralph Campbell Signed-off-by: Jérôme Glisse Reviewed-by: John Hubbard Reviewed-by: Jérôme Glisse Reviewed-by: Balbir Singh Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/hmm.c | 36 +++++++++++++++++++++--------------- 1 file changed, 21 insertions(+), 15 deletions(-) (limited to 'mm') diff --git a/mm/hmm.c b/mm/hmm.c index de9840f60100..63ca3b5be306 100644 --- a/mm/hmm.c +++ b/mm/hmm.c @@ -91,16 +91,6 @@ static struct hmm *hmm_register(struct mm_struct *mm) spin_lock_init(&hmm->lock); hmm->mm = mm; - /* - * We should only get here if hold the mmap_sem in write mode ie on - * registration of first mirror through hmm_mirror_register() - */ - hmm->mmu_notifier.ops = &hmm_mmu_notifier_ops; - if (__mmu_notifier_register(&hmm->mmu_notifier, mm)) { - kfree(hmm); - return NULL; - } - spin_lock(&mm->page_table_lock); if (!mm->hmm) mm->hmm = hmm; @@ -108,12 +98,27 @@ static struct hmm *hmm_register(struct mm_struct *mm) cleanup = true; spin_unlock(&mm->page_table_lock); - if (cleanup) { - mmu_notifier_unregister(&hmm->mmu_notifier, mm); - kfree(hmm); - } + if (cleanup) + goto error; + + /* + * We should only get here if hold the mmap_sem in write mode ie on + * registration of first mirror through hmm_mirror_register() + */ + hmm->mmu_notifier.ops = &hmm_mmu_notifier_ops; + if (__mmu_notifier_register(&hmm->mmu_notifier, mm)) + goto error_mm; return mm->hmm; + +error_mm: + spin_lock(&mm->page_table_lock); + if (mm->hmm == hmm) + mm->hmm = NULL; + spin_unlock(&mm->page_table_lock); +error: + kfree(hmm); + return NULL; } void hmm_mm_destroy(struct mm_struct *mm) @@ -278,12 +283,13 @@ void hmm_mirror_unregister(struct hmm_mirror *mirror) if (!should_unregister || mm == NULL) return; + mmu_notifier_unregister_no_release(&hmm->mmu_notifier, mm); + spin_lock(&mm->page_table_lock); if (mm->hmm == hmm) mm->hmm = NULL; spin_unlock(&mm->page_table_lock); - mmu_notifier_unregister_no_release(&hmm->mmu_notifier, mm); kfree(hmm); } EXPORT_SYMBOL(hmm_mirror_unregister); -- cgit v1.2.3 From d08faca018c4618068e54dfef4f1d71230feff38 Mon Sep 17 00:00:00 2001 From: Jérôme Glisse Date: Tue, 30 Oct 2018 15:04:20 -0700 Subject: mm/hmm: properly handle migration pmd MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Before this patch migration pmd entry (!pmd_present()) would have been treated as a bad entry (pmd_bad() returns true on migration pmd entry). The outcome was that device driver would believe that the range covered by the pmd was bad and would either SIGBUS or simply kill all the device's threads (each device driver decide how to react when the device tries to access poisonnous or invalid range of memory). This patch explicitly handle the case of migration pmd entry which are non present pmd entry and either wait for the migration to finish or report empty range (when device is just trying to pre- fill a range of virtual address and thus do not want to wait or trigger page fault). Link: http://lkml.kernel.org/r/20181019160442.18723-5-jglisse@redhat.com Signed-off-by: Aneesh Kumar K.V Signed-off-by: Jérôme Glisse Cc: Zi Yan Cc: Michal Hocko Cc: Ralph Campbell Cc: John Hubbard Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/hmm.c | 40 ++++++++++++++++++++++++++++++++++------ 1 file changed, 34 insertions(+), 6 deletions(-) (limited to 'mm') diff --git a/mm/hmm.c b/mm/hmm.c index 63ca3b5be306..a3d532ff7c3d 100644 --- a/mm/hmm.c +++ b/mm/hmm.c @@ -577,22 +577,42 @@ static int hmm_vma_walk_pmd(pmd_t *pmdp, { struct hmm_vma_walk *hmm_vma_walk = walk->private; struct hmm_range *range = hmm_vma_walk->range; + struct vm_area_struct *vma = walk->vma; uint64_t *pfns = range->pfns; unsigned long addr = start, i; pte_t *ptep; + pmd_t pmd; - i = (addr - range->start) >> PAGE_SHIFT; again: - if (pmd_none(*pmdp)) + pmd = READ_ONCE(*pmdp); + if (pmd_none(pmd)) return hmm_vma_walk_hole(start, end, walk); - if (pmd_huge(*pmdp) && (range->vma->vm_flags & VM_HUGETLB)) + if (pmd_huge(pmd) && (range->vma->vm_flags & VM_HUGETLB)) return hmm_pfns_bad(start, end, walk); - if (pmd_devmap(*pmdp) || pmd_trans_huge(*pmdp)) { - pmd_t pmd; + if (thp_migration_supported() && is_pmd_migration_entry(pmd)) { + bool fault, write_fault; + unsigned long npages; + uint64_t *pfns; + + i = (addr - range->start) >> PAGE_SHIFT; + npages = (end - addr) >> PAGE_SHIFT; + pfns = &range->pfns[i]; + + hmm_range_need_fault(hmm_vma_walk, pfns, npages, + 0, &fault, &write_fault); + if (fault || write_fault) { + hmm_vma_walk->last = addr; + pmd_migration_entry_wait(vma->vm_mm, pmdp); + return -EAGAIN; + } + return 0; + } else if (!pmd_present(pmd)) + return hmm_pfns_bad(start, end, walk); + if (pmd_devmap(pmd) || pmd_trans_huge(pmd)) { /* * No need to take pmd_lock here, even if some other threads * is splitting the huge pmd we will get that event through @@ -607,13 +627,21 @@ again: if (!pmd_devmap(pmd) && !pmd_trans_huge(pmd)) goto again; + i = (addr - range->start) >> PAGE_SHIFT; return hmm_vma_handle_pmd(walk, addr, end, &pfns[i], pmd); } - if (pmd_bad(*pmdp)) + /* + * We have handled all the valid case above ie either none, migration, + * huge or transparent huge. At this point either it is a valid pmd + * entry pointing to pte directory or it is a bad pmd that will not + * recover. + */ + if (pmd_bad(pmd)) return hmm_pfns_bad(start, end, walk); ptep = pte_offset_map(pmdp, addr); + i = (addr - range->start) >> PAGE_SHIFT; for (; addr < end; addr += PAGE_SIZE, ptep++, i++) { int r; -- cgit v1.2.3 From 44532d4c591c10d6907ac5030373bc306617d92b Mon Sep 17 00:00:00 2001 From: Jérôme Glisse Date: Tue, 30 Oct 2018 15:04:24 -0700 Subject: mm/hmm: use a structure for update callback parameters MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Use a structure to gather all the parameters for the update callback. This make it easier when adding new parameters by avoiding having to update all callback function signature. The hmm_update structure is always associated with a mmu_notifier callbacks so we are not planing on grouping multiple updates together. Nor do we care about page size for the range as range will over fully cover the page being invalidated (this is a mmu_notifier property). Link: http://lkml.kernel.org/r/20181019160442.18723-6-jglisse@redhat.com Signed-off-by: Jérôme Glisse Cc: Ralph Campbell Cc: John Hubbard Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hmm.h | 31 ++++++++++++++++++++++--------- mm/hmm.c | 33 ++++++++++++++++++++++----------- 2 files changed, 44 insertions(+), 20 deletions(-) (limited to 'mm') diff --git a/include/linux/hmm.h b/include/linux/hmm.h index 42b1ae915915..c6fb869a81c0 100644 --- a/include/linux/hmm.h +++ b/include/linux/hmm.h @@ -274,13 +274,28 @@ static inline uint64_t hmm_pfn_from_pfn(const struct hmm_range *range, struct hmm_mirror; /* - * enum hmm_update_type - type of update + * enum hmm_update_event - type of update * @HMM_UPDATE_INVALIDATE: invalidate range (no indication as to why) */ -enum hmm_update_type { +enum hmm_update_event { HMM_UPDATE_INVALIDATE, }; +/* + * struct hmm_update - HMM update informations for callback + * + * @start: virtual start address of the range to update + * @end: virtual end address of the range to update + * @event: event triggering the update (what is happening) + * @blockable: can the callback block/sleep ? + */ +struct hmm_update { + unsigned long start; + unsigned long end; + enum hmm_update_event event; + bool blockable; +}; + /* * struct hmm_mirror_ops - HMM mirror device operations callback * @@ -300,9 +315,9 @@ struct hmm_mirror_ops { /* sync_cpu_device_pagetables() - synchronize page tables * * @mirror: pointer to struct hmm_mirror - * @update_type: type of update that occurred to the CPU page table - * @start: virtual start address of the range to update - * @end: virtual end address of the range to update + * @update: update informations (see struct hmm_update) + * Returns: -EAGAIN if update.blockable false and callback need to + * block, 0 otherwise. * * This callback ultimately originates from mmu_notifiers when the CPU * page table is updated. The device driver must update its page table @@ -313,10 +328,8 @@ struct hmm_mirror_ops { * page tables are completely updated (TLBs flushed, etc); this is a * synchronous call. */ - void (*sync_cpu_device_pagetables)(struct hmm_mirror *mirror, - enum hmm_update_type update_type, - unsigned long start, - unsigned long end); + int (*sync_cpu_device_pagetables)(struct hmm_mirror *mirror, + const struct hmm_update *update); }; /* diff --git a/mm/hmm.c b/mm/hmm.c index a3d532ff7c3d..b4e9afdc2181 100644 --- a/mm/hmm.c +++ b/mm/hmm.c @@ -126,10 +126,8 @@ void hmm_mm_destroy(struct mm_struct *mm) kfree(mm->hmm); } -static void hmm_invalidate_range(struct hmm *hmm, - enum hmm_update_type action, - unsigned long start, - unsigned long end) +static int hmm_invalidate_range(struct hmm *hmm, + const struct hmm_update *update) { struct hmm_mirror *mirror; struct hmm_range *range; @@ -138,22 +136,30 @@ static void hmm_invalidate_range(struct hmm *hmm, list_for_each_entry(range, &hmm->ranges, list) { unsigned long addr, idx, npages; - if (end < range->start || start >= range->end) + if (update->end < range->start || update->start >= range->end) continue; range->valid = false; - addr = max(start, range->start); + addr = max(update->start, range->start); idx = (addr - range->start) >> PAGE_SHIFT; - npages = (min(range->end, end) - addr) >> PAGE_SHIFT; + npages = (min(range->end, update->end) - addr) >> PAGE_SHIFT; memset(&range->pfns[idx], 0, sizeof(*range->pfns) * npages); } spin_unlock(&hmm->lock); down_read(&hmm->mirrors_sem); - list_for_each_entry(mirror, &hmm->mirrors, list) - mirror->ops->sync_cpu_device_pagetables(mirror, action, - start, end); + list_for_each_entry(mirror, &hmm->mirrors, list) { + int ret; + + ret = mirror->ops->sync_cpu_device_pagetables(mirror, update); + if (!update->blockable && ret == -EAGAIN) { + up_read(&hmm->mirrors_sem); + return -EAGAIN; + } + } up_read(&hmm->mirrors_sem); + + return 0; } static void hmm_release(struct mmu_notifier *mn, struct mm_struct *mm) @@ -202,11 +208,16 @@ static void hmm_invalidate_range_end(struct mmu_notifier *mn, unsigned long start, unsigned long end) { + struct hmm_update update; struct hmm *hmm = mm->hmm; VM_BUG_ON(!hmm); - hmm_invalidate_range(mm->hmm, HMM_UPDATE_INVALIDATE, start, end); + update.start = start; + update.end = end; + update.event = HMM_UPDATE_INVALIDATE; + update.blockable = true; + hmm_invalidate_range(hmm, &update); } static const struct mmu_notifier_ops hmm_mmu_notifier_ops = { -- cgit v1.2.3 From ec131b2d7fa629edf88a1f51669d1b4a189cba44 Mon Sep 17 00:00:00 2001 From: Jérôme Glisse Date: Tue, 30 Oct 2018 15:04:28 -0700 Subject: mm/hmm: invalidate device page table at start of invalidation MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Invalidate device page table at start of invalidation and invalidate in progress CPU page table snapshooting at both start and end of any invalidation. This is helpful when device need to dirty page because the device page table report the page as dirty. Dirtying page must happen in the start mmu notifier callback and not in the end one. Link: http://lkml.kernel.org/r/20181019160442.18723-7-jglisse@redhat.com Signed-off-by: Jérôme Glisse Cc: Ralph Campbell Cc: John Hubbard Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/hmm.c | 27 +++++++++++++++------------ 1 file changed, 15 insertions(+), 12 deletions(-) (limited to 'mm') diff --git a/mm/hmm.c b/mm/hmm.c index b4e9afdc2181..90c34f3d1243 100644 --- a/mm/hmm.c +++ b/mm/hmm.c @@ -43,7 +43,6 @@ static const struct mmu_notifier_ops hmm_mmu_notifier_ops; * * @mm: mm struct this HMM struct is bound to * @lock: lock protecting ranges list - * @sequence: we track updates to the CPU page table with a sequence number * @ranges: list of range being snapshotted * @mirrors: list of mirrors for this mm * @mmu_notifier: mmu notifier to track updates to CPU page table @@ -52,7 +51,6 @@ static const struct mmu_notifier_ops hmm_mmu_notifier_ops; struct hmm { struct mm_struct *mm; spinlock_t lock; - atomic_t sequence; struct list_head ranges; struct list_head mirrors; struct mmu_notifier mmu_notifier; @@ -85,7 +83,6 @@ static struct hmm *hmm_register(struct mm_struct *mm) return NULL; INIT_LIST_HEAD(&hmm->mirrors); init_rwsem(&hmm->mirrors_sem); - atomic_set(&hmm->sequence, 0); hmm->mmu_notifier.ops = NULL; INIT_LIST_HEAD(&hmm->ranges); spin_lock_init(&hmm->lock); @@ -126,7 +123,7 @@ void hmm_mm_destroy(struct mm_struct *mm) kfree(mm->hmm); } -static int hmm_invalidate_range(struct hmm *hmm, +static int hmm_invalidate_range(struct hmm *hmm, bool device, const struct hmm_update *update) { struct hmm_mirror *mirror; @@ -147,6 +144,9 @@ static int hmm_invalidate_range(struct hmm *hmm, } spin_unlock(&hmm->lock); + if (!device) + return 0; + down_read(&hmm->mirrors_sem); list_for_each_entry(mirror, &hmm->mirrors, list) { int ret; @@ -189,18 +189,21 @@ static void hmm_release(struct mmu_notifier *mn, struct mm_struct *mm) } static int hmm_invalidate_range_start(struct mmu_notifier *mn, - struct mm_struct *mm, - unsigned long start, - unsigned long end, - bool blockable) + struct mm_struct *mm, + unsigned long start, + unsigned long end, + bool blockable) { + struct hmm_update update; struct hmm *hmm = mm->hmm; VM_BUG_ON(!hmm); - atomic_inc(&hmm->sequence); - - return 0; + update.start = start; + update.end = end; + update.event = HMM_UPDATE_INVALIDATE; + update.blockable = blockable; + return hmm_invalidate_range(hmm, true, &update); } static void hmm_invalidate_range_end(struct mmu_notifier *mn, @@ -217,7 +220,7 @@ static void hmm_invalidate_range_end(struct mmu_notifier *mn, update.end = end; update.event = HMM_UPDATE_INVALIDATE; update.blockable = true; - hmm_invalidate_range(hmm, &update); + hmm_invalidate_range(hmm, false, &update); } static const struct mmu_notifier_ops hmm_mmu_notifier_ops = { -- cgit v1.2.3 From 4b408c74ee5a0b74fc9265c2fe39b0e7dec7c056 Mon Sep 17 00:00:00 2001 From: Dan Carpenter Date: Tue, 30 Oct 2018 15:04:32 -0700 Subject: mm/gup_benchmark.c: prevent integer overflow in ioctl The concern here is that "gup->size" is a u64 and "nr_pages" is unsigned long. On 32 bit systems we could trick the kernel into allocating fewer pages than expected. Link: http://lkml.kernel.org/r/20181025061546.hnhkv33diogf2uis@kili.mountain Fixes: 64c349f4ae78 ("mm: add infrastructure for get_user_pages_fast() benchmarking") Signed-off-by: Dan Carpenter Acked-by: Kirill A. Shutemov Reviewed-by: Andrew Morton Cc: Stephen Rothwell Cc: Keith Busch Cc: "Michael S. Tsirkin" Cc: Kees Cook Cc: YueHaibing Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/gup_benchmark.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'mm') diff --git a/mm/gup_benchmark.c b/mm/gup_benchmark.c index debf11388a60..5b42d3d4b60a 100644 --- a/mm/gup_benchmark.c +++ b/mm/gup_benchmark.c @@ -27,6 +27,9 @@ static int __gup_benchmark_ioctl(unsigned int cmd, int nr; struct page **pages; + if (gup->size > ULONG_MAX) + return -EINVAL; + nr_pages = gup->size / PAGE_SIZE; pages = kvcalloc(nr_pages, sizeof(void *), GFP_KERNEL); if (!pages) -- cgit v1.2.3 From b4a991ec584b3ce333342c431c3cc4fef8a690d7 Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Tue, 30 Oct 2018 15:07:40 -0700 Subject: mm: remove CONFIG_NO_BOOTMEM All achitectures select NO_BOOTMEM which essentially becomes 'Y' for any kernel configuration and therefore it can be removed. [alexander.h.duyck@linux.intel.com: remove now defunct NO_BOOTMEM from depends list for deferred init] Link: http://lkml.kernel.org/r/20180925201814.3576.15105.stgit@localhost.localdomain Link: http://lkml.kernel.org/r/1536927045-23536-3-git-send-email-rppt@linux.vnet.ibm.com Signed-off-by: Mike Rapoport Signed-off-by: Alexander Duyck Acked-by: Michal Hocko Cc: Catalin Marinas Cc: Chris Zankel Cc: "David S. Miller" Cc: Geert Uytterhoeven Cc: Greentime Hu Cc: Greg Kroah-Hartman Cc: Guan Xuetao Cc: Ingo Molnar Cc: "James E.J. Bottomley" Cc: Jonas Bonn Cc: Jonathan Corbet Cc: Ley Foon Tan Cc: Mark Salter Cc: Martin Schwidefsky Cc: Matt Turner Cc: Michael Ellerman Cc: Michal Simek Cc: Palmer Dabbelt Cc: Paul Burton Cc: Richard Kuo Cc: Richard Weinberger Cc: Rich Felker Cc: Russell King Cc: Serge Semin Cc: Thomas Gleixner Cc: Tony Luck Cc: Vineet Gupta Cc: Yoshinori Sato Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/alpha/Kconfig | 1 - arch/arc/Kconfig | 1 - arch/arm/Kconfig | 1 - arch/arm64/Kconfig | 1 - arch/csky/Kconfig | 1 - arch/h8300/Kconfig | 1 - arch/hexagon/Kconfig | 1 - arch/ia64/Kconfig | 1 - arch/m68k/Kconfig | 1 - arch/microblaze/Kconfig | 1 - arch/mips/Kconfig | 1 - arch/nds32/Kconfig | 1 - arch/nios2/Kconfig | 1 - arch/openrisc/Kconfig | 1 - arch/parisc/Kconfig | 1 - arch/powerpc/Kconfig | 1 - arch/riscv/Kconfig | 1 - arch/s390/Kconfig | 1 - arch/sh/Kconfig | 1 - arch/sparc/Kconfig | 1 - arch/um/Kconfig | 1 - arch/unicore32/Kconfig | 1 - arch/x86/Kconfig | 3 --- arch/xtensa/Kconfig | 1 - include/linux/bootmem.h | 36 ++---------------------------------- include/linux/mmzone.h | 5 +---- mm/Kconfig | 4 ---- mm/Makefile | 7 +------ mm/memblock.c | 2 -- 29 files changed, 4 insertions(+), 76 deletions(-) (limited to 'mm') diff --git a/arch/alpha/Kconfig b/arch/alpha/Kconfig index 620b0a711ee4..04de6be101bc 100644 --- a/arch/alpha/Kconfig +++ b/arch/alpha/Kconfig @@ -32,7 +32,6 @@ config ALPHA select OLD_SIGSUSPEND select CPU_NO_EFFICIENT_FFS if !ALPHA_EV67 select HAVE_MEMBLOCK - select NO_BOOTMEM help The Alpha is a 64-bit general-purpose processor designed and marketed by the Digital Equipment Corporation of blessed memory, diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig index e98c6b8e6186..56995f356f69 100644 --- a/arch/arc/Kconfig +++ b/arch/arc/Kconfig @@ -44,7 +44,6 @@ config ARC select HANDLE_DOMAIN_IRQ select IRQ_DOMAIN select MODULES_USE_ELF_RELA - select NO_BOOTMEM select OF select OF_EARLY_FLATTREE select OF_RESERVED_MEM diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index b8c6062ca0c1..37d4c40f405a 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -100,7 +100,6 @@ config ARM select IRQ_FORCED_THREADING select MODULES_USE_ELF_REL select NEED_DMA_MAP_STATE - select NO_BOOTMEM select OF_EARLY_FLATTREE if OF select OF_RESERVED_MEM if OF select OLD_SIGACTION diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 964f682a2b7b..a8f36c7041ff 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -161,7 +161,6 @@ config ARM64 select MULTI_IRQ_HANDLER select NEED_DMA_MAP_STATE select NEED_SG_DMA_LENGTH - select NO_BOOTMEM select OF select OF_EARLY_FLATTREE select OF_RESERVED_MEM diff --git a/arch/csky/Kconfig b/arch/csky/Kconfig index 0a0558567eaa..46966f576249 100644 --- a/arch/csky/Kconfig +++ b/arch/csky/Kconfig @@ -39,7 +39,6 @@ config CSKY select HAVE_MEMBLOCK select MAY_HAVE_SPARSE_IRQ select MODULES_USE_ELF_RELA if MODULES - select NO_BOOTMEM select OF select OF_EARLY_FLATTREE select OF_RESERVED_MEM diff --git a/arch/h8300/Kconfig b/arch/h8300/Kconfig index 0b334b671e90..5e89d40be8cd 100644 --- a/arch/h8300/Kconfig +++ b/arch/h8300/Kconfig @@ -16,7 +16,6 @@ config H8300 select OF_IRQ select OF_EARLY_FLATTREE select HAVE_MEMBLOCK - select NO_BOOTMEM select TIMER_OF select H8300_TMR8 select HAVE_KERNEL_GZIP diff --git a/arch/hexagon/Kconfig b/arch/hexagon/Kconfig index 7b25d7c8fa49..7823f15e17b2 100644 --- a/arch/hexagon/Kconfig +++ b/arch/hexagon/Kconfig @@ -23,7 +23,6 @@ config HEXAGON select HAVE_ARCH_TRACEHOOK select HAVE_MEMBLOCK select ARCH_DISCARD_MEMBLOCK - select NO_BOOTMEM select NEED_SG_DMA_LENGTH select NO_IOPORT_MAP select GENERIC_IOMAP diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig index 8b4a0c1748c0..2bf4ef792f2c 100644 --- a/arch/ia64/Kconfig +++ b/arch/ia64/Kconfig @@ -28,7 +28,6 @@ config IA64 select HAVE_ARCH_TRACEHOOK select HAVE_MEMBLOCK select HAVE_MEMBLOCK_NODE_MAP - select NO_BOOTMEM select HAVE_VIRT_CPU_ACCOUNTING select ARCH_HAS_DMA_MARK_CLEAN select ARCH_HAS_SG_CHAIN diff --git a/arch/m68k/Kconfig b/arch/m68k/Kconfig index c7b2a8d60a41..26edf2542295 100644 --- a/arch/m68k/Kconfig +++ b/arch/m68k/Kconfig @@ -29,7 +29,6 @@ config M68K select DMA_DIRECT_OPS if HAS_DMA select HAVE_MEMBLOCK select ARCH_DISCARD_MEMBLOCK - select NO_BOOTMEM config CPU_BIG_ENDIAN def_bool y diff --git a/arch/microblaze/Kconfig b/arch/microblaze/Kconfig index 164a4857737a..5c2777bb5555 100644 --- a/arch/microblaze/Kconfig +++ b/arch/microblaze/Kconfig @@ -28,7 +28,6 @@ config MICROBLAZE select HAVE_FTRACE_MCOUNT_RECORD select HAVE_FUNCTION_GRAPH_TRACER select HAVE_FUNCTION_TRACER - select NO_BOOTMEM select HAVE_MEMBLOCK select HAVE_MEMBLOCK_NODE_MAP select HAVE_OPROFILE diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index 80778b40f8fa..366934157632 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -78,7 +78,6 @@ config MIPS select RTC_LIB select SYSCTL_EXCEPTION_TRACE select VIRT_TO_BUS - select NO_BOOTMEM menu "Machine selection" diff --git a/arch/nds32/Kconfig b/arch/nds32/Kconfig index 56992330026a..93c0b587ee23 100644 --- a/arch/nds32/Kconfig +++ b/arch/nds32/Kconfig @@ -36,7 +36,6 @@ config NDS32 select MODULES_USE_ELF_RELA select OF select OF_EARLY_FLATTREE - select NO_BOOTMEM select NO_IOPORT_MAP select RTC_LIB select THREAD_INFO_IN_TASK diff --git a/arch/nios2/Kconfig b/arch/nios2/Kconfig index 2df0c57f2833..b01febeb5ce3 100644 --- a/arch/nios2/Kconfig +++ b/arch/nios2/Kconfig @@ -25,7 +25,6 @@ config NIOS2 select CPU_NO_EFFICIENT_FFS select HAVE_MEMBLOCK select ARCH_DISCARD_MEMBLOCK - select NO_BOOTMEM config GENERIC_CSUM def_bool y diff --git a/arch/openrisc/Kconfig b/arch/openrisc/Kconfig index a655ae280637..cbfaf15f9d70 100644 --- a/arch/openrisc/Kconfig +++ b/arch/openrisc/Kconfig @@ -32,7 +32,6 @@ config OPENRISC select HAVE_DEBUG_STACKOVERFLOW select OR1K_PIC select CPU_NO_EFFICIENT_FFS if !OPENRISC_HAVE_INST_FF1 - select NO_BOOTMEM select ARCH_USE_QUEUED_SPINLOCKS select ARCH_USE_QUEUED_RWLOCKS select OMPIC if SMP diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig index f1cd12afd943..7418ebeeb4a4 100644 --- a/arch/parisc/Kconfig +++ b/arch/parisc/Kconfig @@ -16,7 +16,6 @@ config PARISC select RTC_DRV_GENERIC select INIT_ALL_POSSIBLE select HAVE_MEMBLOCK - select NO_BOOTMEM select BUG select BUILDTIME_EXTABLE_SORT select HAVE_PERF_EVENTS diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index e84943d24e5c..5798ffb1379b 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -231,7 +231,6 @@ config PPC select MODULES_USE_ELF_RELA select NEED_DMA_MAP_STATE if PPC64 || NOT_COHERENT_CACHE select NEED_SG_DMA_LENGTH - select NO_BOOTMEM select OF select OF_EARLY_FLATTREE select OF_RESERVED_MEM diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index fe451348ae57..f7c6b7cf124a 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -35,7 +35,6 @@ config RISCV select HAVE_GENERIC_DMA_COHERENT select HAVE_PERF_EVENTS select IRQ_DOMAIN - select NO_BOOTMEM select RISCV_ISA_A if SMP select SPARSE_IRQ select SYSCTL_EXCEPTION_TRACE diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index 8b25e1f45b27..c7af83a15b2d 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -175,7 +175,6 @@ config S390 select HAVE_SYSCALL_TRACEPOINTS select HAVE_VIRT_CPU_ACCOUNTING select MODULES_USE_ELF_RELA - select NO_BOOTMEM select OLD_SIGACTION select OLD_SIGSUSPEND3 select SPARSE_IRQ diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig index 475d786a65b0..7aaea9690e18 100644 --- a/arch/sh/Kconfig +++ b/arch/sh/Kconfig @@ -11,7 +11,6 @@ config SUPERH select HAVE_IDE if HAS_IOPORT_MAP select HAVE_MEMBLOCK select HAVE_MEMBLOCK_NODE_MAP - select NO_BOOTMEM select ARCH_DISCARD_MEMBLOCK select HAVE_OPROFILE select HAVE_GENERIC_DMA_COHERENT diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig index 7e2aa59fcc29..98c0996f3c2c 100644 --- a/arch/sparc/Kconfig +++ b/arch/sparc/Kconfig @@ -46,7 +46,6 @@ config SPARC select NEED_DMA_MAP_STATE select NEED_SG_DMA_LENGTH select HAVE_MEMBLOCK - select NO_BOOTMEM config SPARC32 def_bool !64BIT diff --git a/arch/um/Kconfig b/arch/um/Kconfig index 10c15b8853ae..ce3d56299b28 100644 --- a/arch/um/Kconfig +++ b/arch/um/Kconfig @@ -13,7 +13,6 @@ config UML select HAVE_FUTEX_CMPXCHG if FUTEX select HAVE_DEBUG_KMEMLEAK select HAVE_MEMBLOCK - select NO_BOOTMEM select GENERIC_IRQ_SHOW select GENERIC_CPU_DEVICES select GENERIC_CLOCKEVENTS diff --git a/arch/unicore32/Kconfig b/arch/unicore32/Kconfig index 0c5111b206bd..3a3b40f79558 100644 --- a/arch/unicore32/Kconfig +++ b/arch/unicore32/Kconfig @@ -6,7 +6,6 @@ config UNICORE32 select ARCH_MIGHT_HAVE_PC_SERIO select DMA_DIRECT_OPS select HAVE_MEMBLOCK - select NO_BOOTMEM select HAVE_GENERIC_DMA_COHERENT select HAVE_KERNEL_GZIP select HAVE_KERNEL_BZIP2 diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index ffebfc3f43c1..0354f52ef30e 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -834,9 +834,6 @@ config JAILHOUSE_GUEST endif #HYPERVISOR_GUEST -config NO_BOOTMEM - def_bool y - source "arch/x86/Kconfig.cpu" config HPET_TIMER diff --git a/arch/xtensa/Kconfig b/arch/xtensa/Kconfig index ea5d8d03e53b..df43d2e76842 100644 --- a/arch/xtensa/Kconfig +++ b/arch/xtensa/Kconfig @@ -34,7 +34,6 @@ config XTENSA select HAVE_STACKPROTECTOR select IRQ_DOMAIN select MODULES_USE_ELF_RELA - select NO_BOOTMEM select PERF_USE_VMALLOC select VIRT_TO_BUS help diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h index 42515195d7d8..1f005b5c1555 100644 --- a/include/linux/bootmem.h +++ b/include/linux/bootmem.h @@ -26,34 +26,6 @@ extern unsigned long max_pfn; */ extern unsigned long long max_possible_pfn; -#ifndef CONFIG_NO_BOOTMEM -/** - * struct bootmem_data - per-node information used by the bootmem allocator - * @node_min_pfn: the starting physical address of the node's memory - * @node_low_pfn: the end physical address of the directly addressable memory - * @node_bootmem_map: is a bitmap pointer - the bits represent all physical - * memory pages (including holes) on the node. - * @last_end_off: the offset within the page of the end of the last allocation; - * if 0, the page used is full - * @hint_idx: the PFN of the page used with the last allocation; - * together with using this with the @last_end_offset field, - * a test can be made to see if allocations can be merged - * with the page used for the last allocation rather than - * using up a full new page. - * @list: list entry in the linked list ordered by the memory addresses - */ -typedef struct bootmem_data { - unsigned long node_min_pfn; - unsigned long node_low_pfn; - void *node_bootmem_map; - unsigned long last_end_off; - unsigned long hint_idx; - struct list_head list; -} bootmem_data_t; - -extern bootmem_data_t bootmem_node_data[]; -#endif - extern unsigned long bootmem_bootmap_pages(unsigned long); extern unsigned long init_bootmem_node(pg_data_t *pgdat, @@ -125,12 +97,8 @@ extern void *__alloc_bootmem_low_node(pg_data_t *pgdat, unsigned long align, unsigned long goal) __malloc; -#ifdef CONFIG_NO_BOOTMEM /* We are using top down, so it is safe to use 0 here */ #define BOOTMEM_LOW_LIMIT 0 -#else -#define BOOTMEM_LOW_LIMIT __pa(MAX_DMA_ADDRESS) -#endif #ifndef ARCH_LOW_ADDRESS_LIMIT #define ARCH_LOW_ADDRESS_LIMIT 0xffffffffUL @@ -165,7 +133,7 @@ extern void *__alloc_bootmem_low_node(pg_data_t *pgdat, __alloc_bootmem_low_node(pgdat, x, PAGE_SIZE, 0) -#if defined(CONFIG_HAVE_MEMBLOCK) && defined(CONFIG_NO_BOOTMEM) +#if defined(CONFIG_HAVE_MEMBLOCK) /* FIXME: use MEMBLOCK_ALLOC_* variants here */ #define BOOTMEM_ALLOC_ACCESSIBLE 0 @@ -373,7 +341,7 @@ static inline void __init memblock_free_late( { free_bootmem_late(base, size); } -#endif /* defined(CONFIG_HAVE_MEMBLOCK) && defined(CONFIG_NO_BOOTMEM) */ +#endif /* defined(CONFIG_HAVE_MEMBLOCK) */ extern void *alloc_large_system_hash(const char *tablename, unsigned long bucketsize, diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 9f0caccd5833..847705a6d0ec 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -633,9 +633,6 @@ typedef struct pglist_data { struct page_ext *node_page_ext; #endif #endif -#ifndef CONFIG_NO_BOOTMEM - struct bootmem_data *bdata; -#endif #if defined(CONFIG_MEMORY_HOTPLUG) || defined(CONFIG_DEFERRED_STRUCT_PAGE_INIT) /* * Must be held any time you expect node_start_pfn, node_present_pages @@ -869,7 +866,7 @@ static inline int is_highmem_idx(enum zone_type idx) } /** - * is_highmem - helper function to quickly check if a struct zone is a + * is_highmem - helper function to quickly check if a struct zone is a * highmem zone or not. This is an attempt to keep references * to ZONE_{DMA/NORMAL/HIGHMEM/etc} in general code to a minimum. * @zone - pointer to struct zone variable diff --git a/mm/Kconfig b/mm/Kconfig index 02301a89089e..f7cb608f9ab2 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -142,9 +142,6 @@ config HAVE_GENERIC_GUP config ARCH_DISCARD_MEMBLOCK bool -config NO_BOOTMEM - bool - config MEMORY_ISOLATION bool @@ -634,7 +631,6 @@ config MAX_STACK_SIZE_MB config DEFERRED_STRUCT_PAGE_INIT bool "Defer initialisation of struct pages to kthreads" default n - depends on NO_BOOTMEM depends on SPARSEMEM depends on !NEED_PER_CPU_KM depends on 64BIT diff --git a/mm/Makefile b/mm/Makefile index 6485d5745dd7..ea5333886593 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -42,12 +42,7 @@ obj-y := filemap.o mempool.o oom_kill.o fadvise.o \ debug.o $(mmu-y) obj-y += init-mm.o - -ifdef CONFIG_NO_BOOTMEM - obj-y += nobootmem.o -else - obj-y += bootmem.o -endif +obj-y += nobootmem.o ifdef CONFIG_MMU obj-$(CONFIG_ADVISE_SYSCALLS) += madvise.o diff --git a/mm/memblock.c b/mm/memblock.c index a85315083b5a..d6897fbe021f 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -1318,7 +1318,6 @@ phys_addr_t __init memblock_alloc_try_nid(phys_addr_t size, phys_addr_t align, i return memblock_alloc_base(size, align, MEMBLOCK_ALLOC_ACCESSIBLE); } -#if defined(CONFIG_NO_BOOTMEM) /** * memblock_virt_alloc_internal - allocate boot memory block * @size: size of memory block to be allocated in bytes @@ -1524,7 +1523,6 @@ void * __init memblock_virt_alloc_try_nid( __func__, (u64)size, (u64)align, nid, &min_addr, &max_addr); return NULL; } -#endif /** * __memblock_free_early - free boot memory block -- cgit v1.2.3 From aca52c39838910605b1063a2243f553aa2a02d5c Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Tue, 30 Oct 2018 15:07:44 -0700 Subject: mm: remove CONFIG_HAVE_MEMBLOCK All architecures use memblock for early memory management. There is no need for the CONFIG_HAVE_MEMBLOCK configuration option. [rppt@linux.vnet.ibm.com: of/fdt: fixup #ifdefs] Link: http://lkml.kernel.org/r/20180919103457.GA20545@rapoport-lnx [rppt@linux.vnet.ibm.com: csky: fixups after bootmem removal] Link: http://lkml.kernel.org/r/20180926112744.GC4628@rapoport-lnx [rppt@linux.vnet.ibm.com: remove stale #else and the code it protects] Link: http://lkml.kernel.org/r/1538067825-24835-1-git-send-email-rppt@linux.vnet.ibm.com Link: http://lkml.kernel.org/r/1536927045-23536-4-git-send-email-rppt@linux.vnet.ibm.com Signed-off-by: Mike Rapoport Acked-by: Michal Hocko Tested-by: Jonathan Cameron Cc: Catalin Marinas Cc: Chris Zankel Cc: "David S. Miller" Cc: Geert Uytterhoeven Cc: Greentime Hu Cc: Greg Kroah-Hartman Cc: Guan Xuetao Cc: Ingo Molnar Cc: "James E.J. Bottomley" Cc: Jonas Bonn Cc: Jonathan Corbet Cc: Ley Foon Tan Cc: Mark Salter Cc: Martin Schwidefsky Cc: Matt Turner Cc: Michael Ellerman Cc: Michal Simek Cc: Palmer Dabbelt Cc: Paul Burton Cc: Richard Kuo Cc: Richard Weinberger Cc: Rich Felker Cc: Russell King Cc: Serge Semin Cc: Thomas Gleixner Cc: Tony Luck Cc: Vineet Gupta Cc: Yoshinori Sato Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/alpha/Kconfig | 1 - arch/arc/Kconfig | 1 - arch/arm/Kconfig | 1 - arch/arm64/Kconfig | 1 - arch/c6x/Kconfig | 1 - arch/csky/Kconfig | 1 - arch/csky/kernel/setup.c | 1 - arch/csky/mm/highmem.c | 4 +- arch/csky/mm/init.c | 3 +- arch/h8300/Kconfig | 1 - arch/hexagon/Kconfig | 1 - arch/ia64/Kconfig | 1 - arch/m68k/Kconfig | 1 - arch/microblaze/Kconfig | 1 - arch/mips/Kconfig | 1 - arch/nds32/Kconfig | 1 - arch/nios2/Kconfig | 1 - arch/openrisc/Kconfig | 1 - arch/parisc/Kconfig | 1 - arch/powerpc/Kconfig | 1 - arch/riscv/Kconfig | 1 - arch/s390/Kconfig | 1 - arch/sh/Kconfig | 1 - arch/sparc/Kconfig | 1 - arch/um/Kconfig | 1 - arch/unicore32/Kconfig | 1 - arch/x86/Kconfig | 1 - arch/xtensa/Kconfig | 1 - drivers/of/fdt.c | 21 ------- drivers/of/of_reserved_mem.c | 13 +---- drivers/staging/android/ion/Kconfig | 2 +- fs/pstore/Kconfig | 1 - include/linux/bootmem.h | 112 ------------------------------------ include/linux/memblock.h | 7 --- include/linux/mm.h | 2 +- lib/Kconfig.debug | 3 +- mm/Kconfig | 5 +- mm/Makefile | 2 +- mm/nobootmem.c | 4 -- mm/page_alloc.c | 5 +- 40 files changed, 11 insertions(+), 199 deletions(-) (limited to 'mm') diff --git a/arch/alpha/Kconfig b/arch/alpha/Kconfig index 04de6be101bc..5b4f88363453 100644 --- a/arch/alpha/Kconfig +++ b/arch/alpha/Kconfig @@ -31,7 +31,6 @@ config ALPHA select ODD_RT_SIGACTION select OLD_SIGSUSPEND select CPU_NO_EFFICIENT_FFS if !ALPHA_EV67 - select HAVE_MEMBLOCK help The Alpha is a 64-bit general-purpose processor designed and marketed by the Digital Equipment Corporation of blessed memory, diff --git a/arch/arc/Kconfig b/arch/arc/Kconfig index 56995f356f69..c9e2a1323536 100644 --- a/arch/arc/Kconfig +++ b/arch/arc/Kconfig @@ -37,7 +37,6 @@ config ARC select HAVE_KERNEL_LZMA select HAVE_KPROBES select HAVE_KRETPROBES - select HAVE_MEMBLOCK select HAVE_MOD_ARCH_SPECIFIC select HAVE_OPROFILE select HAVE_PERF_EVENTS diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig index 37d4c40f405a..91be74d8df65 100644 --- a/arch/arm/Kconfig +++ b/arch/arm/Kconfig @@ -82,7 +82,6 @@ config ARM select HAVE_KERNEL_XZ select HAVE_KPROBES if !XIP_KERNEL && !CPU_ENDIAN_BE32 && !CPU_V7M select HAVE_KRETPROBES if (HAVE_KPROBES) - select HAVE_MEMBLOCK select HAVE_MOD_ARCH_SPECIFIC select HAVE_NMI select HAVE_OPROFILE if (HAVE_PERF_EVENTS) diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index a8f36c7041ff..787d7850e064 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -139,7 +139,6 @@ config ARM64 select HAVE_GENERIC_DMA_COHERENT select HAVE_HW_BREAKPOINT if PERF_EVENTS select HAVE_IRQ_TIME_ACCOUNTING - select HAVE_MEMBLOCK select HAVE_MEMBLOCK_NODE_MAP if NUMA select HAVE_NMI select HAVE_PATA_PLATFORM diff --git a/arch/c6x/Kconfig b/arch/c6x/Kconfig index f65a084607fd..84420109113d 100644 --- a/arch/c6x/Kconfig +++ b/arch/c6x/Kconfig @@ -13,7 +13,6 @@ config C6X select GENERIC_ATOMIC64 select GENERIC_IRQ_SHOW select HAVE_ARCH_TRACEHOOK - select HAVE_MEMBLOCK select SPARSE_IRQ select IRQ_DOMAIN select OF diff --git a/arch/csky/Kconfig b/arch/csky/Kconfig index 46966f576249..cb64f8dacd08 100644 --- a/arch/csky/Kconfig +++ b/arch/csky/Kconfig @@ -36,7 +36,6 @@ config CSKY select HAVE_C_RECORDMCOUNT select HAVE_DMA_API_DEBUG select HAVE_DMA_CONTIGUOUS - select HAVE_MEMBLOCK select MAY_HAVE_SPARSE_IRQ select MODULES_USE_ELF_RELA if MODULES select OF diff --git a/arch/csky/kernel/setup.c b/arch/csky/kernel/setup.c index a5e3ab1d5360..dff8b89444ec 100644 --- a/arch/csky/kernel/setup.c +++ b/arch/csky/kernel/setup.c @@ -3,7 +3,6 @@ #include #include -#include #include #include #include diff --git a/arch/csky/mm/highmem.c b/arch/csky/mm/highmem.c index e168ac087ccb..53b1bfa4c462 100644 --- a/arch/csky/mm/highmem.c +++ b/arch/csky/mm/highmem.c @@ -4,7 +4,7 @@ #include #include #include -#include +#include #include #include #include @@ -140,7 +140,7 @@ static void __init fixrange_init(unsigned long start, unsigned long end, pmd = (pmd_t *)pud; for (; (k < PTRS_PER_PMD) && (vaddr != end); pmd++, k++) { if (pmd_none(*pmd)) { - pte = (pte_t *) alloc_bootmem_low_pages(PAGE_SIZE); + pte = (pte_t *) memblock_alloc_low(PAGE_SIZE, PAGE_SIZE); set_pmd(pmd, __pmd(__pa(pte))); BUG_ON(pte != pte_offset_kernel(pmd, 0)); } diff --git a/arch/csky/mm/init.c b/arch/csky/mm/init.c index ce2711e050ad..dc07c078f9b8 100644 --- a/arch/csky/mm/init.c +++ b/arch/csky/mm/init.c @@ -14,7 +14,6 @@ #include #include #include -#include #include #include #include @@ -47,7 +46,7 @@ void __init mem_init(void) #endif high_memory = (void *) __va(max_low_pfn << PAGE_SHIFT); - free_all_bootmem(); + memblock_free_all(); #ifdef CONFIG_HIGHMEM for (tmp = highstart_pfn; tmp < highend_pfn; tmp++) { diff --git a/arch/h8300/Kconfig b/arch/h8300/Kconfig index 5e89d40be8cd..d19c6b16cd5d 100644 --- a/arch/h8300/Kconfig +++ b/arch/h8300/Kconfig @@ -15,7 +15,6 @@ config H8300 select OF select OF_IRQ select OF_EARLY_FLATTREE - select HAVE_MEMBLOCK select TIMER_OF select H8300_TMR8 select HAVE_KERNEL_GZIP diff --git a/arch/hexagon/Kconfig b/arch/hexagon/Kconfig index 7823f15e17b2..2b688af379e6 100644 --- a/arch/hexagon/Kconfig +++ b/arch/hexagon/Kconfig @@ -21,7 +21,6 @@ config HEXAGON select GENERIC_IRQ_SHOW select HAVE_ARCH_KGDB select HAVE_ARCH_TRACEHOOK - select HAVE_MEMBLOCK select ARCH_DISCARD_MEMBLOCK select NEED_SG_DMA_LENGTH select NO_IOPORT_MAP diff --git a/arch/ia64/Kconfig b/arch/ia64/Kconfig index 2bf4ef792f2c..36773def6920 100644 --- a/arch/ia64/Kconfig +++ b/arch/ia64/Kconfig @@ -26,7 +26,6 @@ config IA64 select HAVE_FUNCTION_TRACER select TTY select HAVE_ARCH_TRACEHOOK - select HAVE_MEMBLOCK select HAVE_MEMBLOCK_NODE_MAP select HAVE_VIRT_CPU_ACCOUNTING select ARCH_HAS_DMA_MARK_CLEAN diff --git a/arch/m68k/Kconfig b/arch/m68k/Kconfig index 26edf2542295..1bc9f1ba759a 100644 --- a/arch/m68k/Kconfig +++ b/arch/m68k/Kconfig @@ -27,7 +27,6 @@ config M68K select OLD_SIGSUSPEND3 select OLD_SIGACTION select DMA_DIRECT_OPS if HAS_DMA - select HAVE_MEMBLOCK select ARCH_DISCARD_MEMBLOCK config CPU_BIG_ENDIAN diff --git a/arch/microblaze/Kconfig b/arch/microblaze/Kconfig index 5c2777bb5555..effed2efd306 100644 --- a/arch/microblaze/Kconfig +++ b/arch/microblaze/Kconfig @@ -28,7 +28,6 @@ config MICROBLAZE select HAVE_FTRACE_MCOUNT_RECORD select HAVE_FUNCTION_GRAPH_TRACER select HAVE_FUNCTION_TRACER - select HAVE_MEMBLOCK select HAVE_MEMBLOCK_NODE_MAP select HAVE_OPROFILE select IRQ_DOMAIN diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig index 366934157632..8272ea4c7264 100644 --- a/arch/mips/Kconfig +++ b/arch/mips/Kconfig @@ -60,7 +60,6 @@ config MIPS select HAVE_IRQ_TIME_ACCOUNTING select HAVE_KPROBES select HAVE_KRETPROBES - select HAVE_MEMBLOCK select HAVE_MEMBLOCK_NODE_MAP select HAVE_MOD_ARCH_SPECIFIC select HAVE_NMI diff --git a/arch/nds32/Kconfig b/arch/nds32/Kconfig index 93c0b587ee23..7a04adacb2f0 100644 --- a/arch/nds32/Kconfig +++ b/arch/nds32/Kconfig @@ -29,7 +29,6 @@ config NDS32 select HANDLE_DOMAIN_IRQ select HAVE_ARCH_TRACEHOOK select HAVE_DEBUG_KMEMLEAK - select HAVE_MEMBLOCK select HAVE_REGS_AND_STACK_ACCESS_API select IRQ_DOMAIN select LOCKDEP_SUPPORT diff --git a/arch/nios2/Kconfig b/arch/nios2/Kconfig index b01febeb5ce3..7e95506e957a 100644 --- a/arch/nios2/Kconfig +++ b/arch/nios2/Kconfig @@ -23,7 +23,6 @@ config NIOS2 select SPARSE_IRQ select USB_ARCH_HAS_HCD if USB_SUPPORT select CPU_NO_EFFICIENT_FFS - select HAVE_MEMBLOCK select ARCH_DISCARD_MEMBLOCK config GENERIC_CSUM diff --git a/arch/openrisc/Kconfig b/arch/openrisc/Kconfig index cbfaf15f9d70..285f7d05c8ed 100644 --- a/arch/openrisc/Kconfig +++ b/arch/openrisc/Kconfig @@ -12,7 +12,6 @@ config OPENRISC select OF_EARLY_FLATTREE select IRQ_DOMAIN select HANDLE_DOMAIN_IRQ - select HAVE_MEMBLOCK select GPIOLIB select HAVE_ARCH_TRACEHOOK select SPARSE_IRQ diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig index 7418ebeeb4a4..92a339ee28b3 100644 --- a/arch/parisc/Kconfig +++ b/arch/parisc/Kconfig @@ -15,7 +15,6 @@ config PARISC select RTC_CLASS select RTC_DRV_GENERIC select INIT_ALL_POSSIBLE - select HAVE_MEMBLOCK select BUG select BUILDTIME_EXTABLE_SORT select HAVE_PERF_EVENTS diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig index 5798ffb1379b..2d51b2bd4aa1 100644 --- a/arch/powerpc/Kconfig +++ b/arch/powerpc/Kconfig @@ -206,7 +206,6 @@ config PPC select HAVE_KRETPROBES select HAVE_LD_DEAD_CODE_DATA_ELIMINATION select HAVE_LIVEPATCH if HAVE_DYNAMIC_FTRACE_WITH_REGS - select HAVE_MEMBLOCK select HAVE_MEMBLOCK_NODE_MAP select HAVE_MOD_ARCH_SPECIFIC select HAVE_NMI if PERF_EVENTS || (PPC64 && PPC_BOOK3S) diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig index f7c6b7cf124a..d86842c21710 100644 --- a/arch/riscv/Kconfig +++ b/arch/riscv/Kconfig @@ -28,7 +28,6 @@ config RISCV select GENERIC_STRNLEN_USER select GENERIC_SMP_IDLE_THREAD select GENERIC_ATOMIC64 if !64BIT || !RISCV_ISA_A - select HAVE_MEMBLOCK select HAVE_MEMBLOCK_NODE_MAP select HAVE_DMA_CONTIGUOUS select HAVE_FUTEX_CMPXCHG if FUTEX diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index c7af83a15b2d..5173366af8f3 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -163,7 +163,6 @@ config S390 select HAVE_LIVEPATCH select HAVE_PERF_REGS select HAVE_PERF_USER_STACK_DUMP - select HAVE_MEMBLOCK select HAVE_MEMBLOCK_NODE_MAP select HAVE_MEMBLOCK_PHYS_MAP select HAVE_MOD_ARCH_SPECIFIC diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig index 7aaea9690e18..f82a4da7adf3 100644 --- a/arch/sh/Kconfig +++ b/arch/sh/Kconfig @@ -9,7 +9,6 @@ config SUPERH select CLKDEV_LOOKUP select DMA_DIRECT_OPS select HAVE_IDE if HAS_IOPORT_MAP - select HAVE_MEMBLOCK select HAVE_MEMBLOCK_NODE_MAP select ARCH_DISCARD_MEMBLOCK select HAVE_OPROFILE diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig index 98c0996f3c2c..490b2c95c212 100644 --- a/arch/sparc/Kconfig +++ b/arch/sparc/Kconfig @@ -45,7 +45,6 @@ config SPARC select LOCKDEP_SMALL if LOCKDEP select NEED_DMA_MAP_STATE select NEED_SG_DMA_LENGTH - select HAVE_MEMBLOCK config SPARC32 def_bool !64BIT diff --git a/arch/um/Kconfig b/arch/um/Kconfig index ce3d56299b28..6b9938919f0b 100644 --- a/arch/um/Kconfig +++ b/arch/um/Kconfig @@ -12,7 +12,6 @@ config UML select HAVE_UID16 select HAVE_FUTEX_CMPXCHG if FUTEX select HAVE_DEBUG_KMEMLEAK - select HAVE_MEMBLOCK select GENERIC_IRQ_SHOW select GENERIC_CPU_DEVICES select GENERIC_CLOCKEVENTS diff --git a/arch/unicore32/Kconfig b/arch/unicore32/Kconfig index 3a3b40f79558..a4c05159dca5 100644 --- a/arch/unicore32/Kconfig +++ b/arch/unicore32/Kconfig @@ -5,7 +5,6 @@ config UNICORE32 select ARCH_MIGHT_HAVE_PC_PARPORT select ARCH_MIGHT_HAVE_PC_SERIO select DMA_DIRECT_OPS - select HAVE_MEMBLOCK select HAVE_GENERIC_DMA_COHERENT select HAVE_KERNEL_GZIP select HAVE_KERNEL_BZIP2 diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 0354f52ef30e..c51c989c19c0 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -169,7 +169,6 @@ config X86 select HAVE_KRETPROBES select HAVE_KVM select HAVE_LIVEPATCH if X86_64 - select HAVE_MEMBLOCK select HAVE_MEMBLOCK_NODE_MAP select HAVE_MIXED_BREAKPOINTS_REGS select HAVE_MOD_ARCH_SPECIFIC diff --git a/arch/xtensa/Kconfig b/arch/xtensa/Kconfig index df43d2e76842..60c141af222b 100644 --- a/arch/xtensa/Kconfig +++ b/arch/xtensa/Kconfig @@ -28,7 +28,6 @@ config XTENSA select HAVE_FUTEX_CMPXCHG if !MMU select HAVE_HW_BREAKPOINT if PERF_EVENTS select HAVE_IRQ_TIME_ACCOUNTING - select HAVE_MEMBLOCK select HAVE_OPROFILE select HAVE_PERF_EVENTS select HAVE_STACKPROTECTOR diff --git a/drivers/of/fdt.c b/drivers/of/fdt.c index 76c83c1ffeda..4f915cea6f75 100644 --- a/drivers/of/fdt.c +++ b/drivers/of/fdt.c @@ -1115,7 +1115,6 @@ int __init early_init_dt_scan_chosen(unsigned long node, const char *uname, return 1; } -#ifdef CONFIG_HAVE_MEMBLOCK #ifndef MIN_MEMBLOCK_ADDR #define MIN_MEMBLOCK_ADDR __pa(PAGE_OFFSET) #endif @@ -1178,26 +1177,6 @@ int __init __weak early_init_dt_reserve_memory_arch(phys_addr_t base, return memblock_reserve(base, size); } -#else -void __init __weak early_init_dt_add_memory_arch(u64 base, u64 size) -{ - WARN_ON(1); -} - -int __init __weak early_init_dt_mark_hotplug_memory_arch(u64 base, u64 size) -{ - return -ENOSYS; -} - -int __init __weak early_init_dt_reserve_memory_arch(phys_addr_t base, - phys_addr_t size, bool nomap) -{ - pr_err("Reserved memory not supported, ignoring range %pa - %pa%s\n", - &base, &size, nomap ? " (nomap)" : ""); - return -ENOSYS; -} -#endif - static void * __init early_init_dt_alloc_memory_arch(u64 size, u64 align) { return memblock_virt_alloc(size, align); diff --git a/drivers/of/of_reserved_mem.c b/drivers/of/of_reserved_mem.c index 895c83e0c7b6..d6255c276a41 100644 --- a/drivers/of/of_reserved_mem.c +++ b/drivers/of/of_reserved_mem.c @@ -20,13 +20,12 @@ #include #include #include +#include #define MAX_RESERVED_REGIONS 32 static struct reserved_mem reserved_mem[MAX_RESERVED_REGIONS]; static int reserved_mem_count; -#if defined(CONFIG_HAVE_MEMBLOCK) -#include int __init __weak early_init_dt_alloc_reserved_memory_arch(phys_addr_t size, phys_addr_t align, phys_addr_t start, phys_addr_t end, bool nomap, phys_addr_t *res_base) @@ -54,16 +53,6 @@ int __init __weak early_init_dt_alloc_reserved_memory_arch(phys_addr_t size, return memblock_remove(base, size); return 0; } -#else -int __init __weak early_init_dt_alloc_reserved_memory_arch(phys_addr_t size, - phys_addr_t align, phys_addr_t start, phys_addr_t end, bool nomap, - phys_addr_t *res_base) -{ - pr_err("Reserved memory not supported, ignoring region 0x%llx%s\n", - size, nomap ? " (nomap)" : ""); - return -ENOSYS; -} -#endif /** * res_mem_save_node() - save fdt node for second pass initialization diff --git a/drivers/staging/android/ion/Kconfig b/drivers/staging/android/ion/Kconfig index c16dd16afe6a..0fdda6f62953 100644 --- a/drivers/staging/android/ion/Kconfig +++ b/drivers/staging/android/ion/Kconfig @@ -1,6 +1,6 @@ menuconfig ION bool "Ion Memory Manager" - depends on HAVE_MEMBLOCK && HAS_DMA && MMU + depends on HAS_DMA && MMU select GENERIC_ALLOCATOR select DMA_SHARED_BUFFER help diff --git a/fs/pstore/Kconfig b/fs/pstore/Kconfig index 503086f7f7c1..0d19d191ae70 100644 --- a/fs/pstore/Kconfig +++ b/fs/pstore/Kconfig @@ -141,7 +141,6 @@ config PSTORE_RAM tristate "Log panic/oops to a RAM buffer" depends on PSTORE depends on HAS_IOMEM - depends on HAVE_MEMBLOCK select REED_SOLOMON select REED_SOLOMON_ENC8 select REED_SOLOMON_DEC8 diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h index 1f005b5c1555..ee61ac355104 100644 --- a/include/linux/bootmem.h +++ b/include/linux/bootmem.h @@ -132,9 +132,6 @@ extern void *__alloc_bootmem_low_node(pg_data_t *pgdat, #define alloc_bootmem_low_pages_node(pgdat, x) \ __alloc_bootmem_low_node(pgdat, x, PAGE_SIZE, 0) - -#if defined(CONFIG_HAVE_MEMBLOCK) - /* FIXME: use MEMBLOCK_ALLOC_* variants here */ #define BOOTMEM_ALLOC_ACCESSIBLE 0 #define BOOTMEM_ALLOC_ANYWHERE (~(phys_addr_t)0) @@ -234,115 +231,6 @@ static inline void __init memblock_free_late( __memblock_free_late(base, size); } -#else - -#define BOOTMEM_ALLOC_ACCESSIBLE 0 - - -/* Fall back to all the existing bootmem APIs */ -static inline void * __init memblock_virt_alloc( - phys_addr_t size, phys_addr_t align) -{ - if (!align) - align = SMP_CACHE_BYTES; - return __alloc_bootmem(size, align, BOOTMEM_LOW_LIMIT); -} - -static inline void * __init memblock_virt_alloc_raw( - phys_addr_t size, phys_addr_t align) -{ - if (!align) - align = SMP_CACHE_BYTES; - return __alloc_bootmem_nopanic(size, align, BOOTMEM_LOW_LIMIT); -} - -static inline void * __init memblock_virt_alloc_nopanic( - phys_addr_t size, phys_addr_t align) -{ - if (!align) - align = SMP_CACHE_BYTES; - return __alloc_bootmem_nopanic(size, align, BOOTMEM_LOW_LIMIT); -} - -static inline void * __init memblock_virt_alloc_low( - phys_addr_t size, phys_addr_t align) -{ - if (!align) - align = SMP_CACHE_BYTES; - return __alloc_bootmem_low(size, align, 0); -} - -static inline void * __init memblock_virt_alloc_low_nopanic( - phys_addr_t size, phys_addr_t align) -{ - if (!align) - align = SMP_CACHE_BYTES; - return __alloc_bootmem_low_nopanic(size, align, 0); -} - -static inline void * __init memblock_virt_alloc_from_nopanic( - phys_addr_t size, phys_addr_t align, phys_addr_t min_addr) -{ - return __alloc_bootmem_nopanic(size, align, min_addr); -} - -static inline void * __init memblock_virt_alloc_node( - phys_addr_t size, int nid) -{ - return __alloc_bootmem_node(NODE_DATA(nid), size, SMP_CACHE_BYTES, - BOOTMEM_LOW_LIMIT); -} - -static inline void * __init memblock_virt_alloc_node_nopanic( - phys_addr_t size, int nid) -{ - return __alloc_bootmem_node_nopanic(NODE_DATA(nid), size, - SMP_CACHE_BYTES, - BOOTMEM_LOW_LIMIT); -} - -static inline void * __init memblock_virt_alloc_try_nid(phys_addr_t size, - phys_addr_t align, phys_addr_t min_addr, phys_addr_t max_addr, int nid) -{ - return __alloc_bootmem_node_high(NODE_DATA(nid), size, align, - min_addr); -} - -static inline void * __init memblock_virt_alloc_try_nid_raw( - phys_addr_t size, phys_addr_t align, - phys_addr_t min_addr, phys_addr_t max_addr, int nid) -{ - return ___alloc_bootmem_node_nopanic(NODE_DATA(nid), size, align, - min_addr, max_addr); -} - -static inline void * __init memblock_virt_alloc_try_nid_nopanic( - phys_addr_t size, phys_addr_t align, - phys_addr_t min_addr, phys_addr_t max_addr, int nid) -{ - return ___alloc_bootmem_node_nopanic(NODE_DATA(nid), size, align, - min_addr, max_addr); -} - -static inline void __init memblock_free_early( - phys_addr_t base, phys_addr_t size) -{ - free_bootmem(base, size); -} - -static inline void __init memblock_free_early_nid( - phys_addr_t base, phys_addr_t size, int nid) -{ - free_bootmem_node(NODE_DATA(nid), base, size); -} - -static inline void __init memblock_free_late( - phys_addr_t base, phys_addr_t size) -{ - free_bootmem_late(base, size); -} -#endif /* defined(CONFIG_HAVE_MEMBLOCK) */ - extern void *alloc_large_system_hash(const char *tablename, unsigned long bucketsize, unsigned long numentries, diff --git a/include/linux/memblock.h b/include/linux/memblock.h index 2acdd046df2d..224d27363cca 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -2,7 +2,6 @@ #define _LINUX_MEMBLOCK_H #ifdef __KERNEL__ -#ifdef CONFIG_HAVE_MEMBLOCK /* * Logical memory blocks. * @@ -440,12 +439,6 @@ static inline void early_memtest(phys_addr_t start, phys_addr_t end) { } #endif -#else -static inline phys_addr_t memblock_alloc(phys_addr_t size, phys_addr_t align) -{ - return 0; -} -#endif /* CONFIG_HAVE_MEMBLOCK */ #endif /* __KERNEL__ */ diff --git a/include/linux/mm.h b/include/linux/mm.h index 1e52b8fd1685..fcf9cc9d535f 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2163,7 +2163,7 @@ extern int __meminit __early_pfn_to_nid(unsigned long pfn, struct mminit_pfnnid_cache *state); #endif -#if defined(CONFIG_HAVE_MEMBLOCK) && !defined(CONFIG_FLAT_NODE_MEM_MAP) +#if !defined(CONFIG_FLAT_NODE_MEM_MAP) void zero_resv_unavail(void); #else static inline void zero_resv_unavail(void) {} diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index e0ba05e6f6bd..1af29b8224fd 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -1292,7 +1292,7 @@ config DEBUG_KOBJECT depends on DEBUG_KERNEL help If you say Y here, some extra kobject debugging messages will be sent - to the syslog. + to the syslog. config DEBUG_KOBJECT_RELEASE bool "kobject release debugging" @@ -1980,7 +1980,6 @@ endif # RUNTIME_TESTING_MENU config MEMTEST bool "Memtest" - depends on HAVE_MEMBLOCK ---help--- This option adds a kernel parameter 'memtest', which allows memtest to be set. diff --git a/mm/Kconfig b/mm/Kconfig index f7cb608f9ab2..d85e39da47ae 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -127,9 +127,6 @@ config SPARSEMEM_VMEMMAP pfn_to_page and page_to_pfn operations. This is the most efficient option when sufficient kernel resources are available. -config HAVE_MEMBLOCK - bool - config HAVE_MEMBLOCK_NODE_MAP bool @@ -478,7 +475,7 @@ config FRONTSWAP config CMA bool "Contiguous Memory Allocator" - depends on HAVE_MEMBLOCK && MMU + depends on MMU select MIGRATION select MEMORY_ISOLATION help diff --git a/mm/Makefile b/mm/Makefile index ea5333886593..ca3c844d7a56 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -43,11 +43,11 @@ obj-y := filemap.o mempool.o oom_kill.o fadvise.o \ obj-y += init-mm.o obj-y += nobootmem.o +obj-y += memblock.o ifdef CONFIG_MMU obj-$(CONFIG_ADVISE_SYSCALLS) += madvise.o endif -obj-$(CONFIG_HAVE_MEMBLOCK) += memblock.o obj-$(CONFIG_SWAP) += page_io.o swap_state.o swapfile.o swap_slots.o obj-$(CONFIG_FRONTSWAP) += frontswap.o diff --git a/mm/nobootmem.c b/mm/nobootmem.c index 439af3b765a7..d4d0cd474087 100644 --- a/mm/nobootmem.c +++ b/mm/nobootmem.c @@ -23,10 +23,6 @@ #include "internal.h" -#ifndef CONFIG_HAVE_MEMBLOCK -#error CONFIG_HAVE_MEMBLOCK not defined -#endif - #ifndef CONFIG_NEED_MULTIPLE_NODES struct pglist_data __refdata contig_page_data; EXPORT_SYMBOL(contig_page_data); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 863d46da6586..59d171f84445 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -6508,8 +6508,7 @@ void __init free_area_init_node(int nid, unsigned long *zones_size, free_area_init_core(pgdat); } -#if defined(CONFIG_HAVE_MEMBLOCK) && !defined(CONFIG_FLAT_NODE_MEM_MAP) - +#if !defined(CONFIG_FLAT_NODE_MEM_MAP) /* * Zero all valid struct pages in range [spfn, epfn), return number of struct * pages zeroed @@ -6569,7 +6568,7 @@ void __init zero_resv_unavail(void) if (pgcnt) pr_info("Zeroed struct page in unavailable ranges: %lld pages", pgcnt); } -#endif /* CONFIG_HAVE_MEMBLOCK && !CONFIG_FLAT_NODE_MEM_MAP */ +#endif /* !CONFIG_FLAT_NODE_MEM_MAP */ #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP -- cgit v1.2.3 From 355c45affca7114ab510e296a5b7012943aeea17 Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Tue, 30 Oct 2018 15:07:50 -0700 Subject: mm: remove bootmem allocator implementation. All architectures have been converted to use MEMBLOCK + NO_BOOTMEM. The bootmem allocator implementation can be removed. Link: http://lkml.kernel.org/r/1536927045-23536-5-git-send-email-rppt@linux.vnet.ibm.com Signed-off-by: Mike Rapoport Acked-by: Michal Hocko Cc: Catalin Marinas Cc: Chris Zankel Cc: "David S. Miller" Cc: Geert Uytterhoeven Cc: Greentime Hu Cc: Greg Kroah-Hartman Cc: Guan Xuetao Cc: Ingo Molnar Cc: "James E.J. Bottomley" Cc: Jonas Bonn Cc: Jonathan Corbet Cc: Ley Foon Tan Cc: Mark Salter Cc: Martin Schwidefsky Cc: Matt Turner Cc: Michael Ellerman Cc: Michal Simek Cc: Palmer Dabbelt Cc: Paul Burton Cc: Richard Kuo Cc: Richard Weinberger Cc: Rich Felker Cc: Russell King Cc: Serge Semin Cc: Thomas Gleixner Cc: Tony Luck Cc: Vineet Gupta Cc: Yoshinori Sato Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/bootmem.h | 16 - mm/bootmem.c | 811 ------------------------------------------------ 2 files changed, 827 deletions(-) delete mode 100644 mm/bootmem.c (limited to 'mm') diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h index ee61ac355104..fce6278a1724 100644 --- a/include/linux/bootmem.h +++ b/include/linux/bootmem.h @@ -26,14 +26,6 @@ extern unsigned long max_pfn; */ extern unsigned long long max_possible_pfn; -extern unsigned long bootmem_bootmap_pages(unsigned long); - -extern unsigned long init_bootmem_node(pg_data_t *pgdat, - unsigned long freepfn, - unsigned long startpfn, - unsigned long endpfn); -extern unsigned long init_bootmem(unsigned long addr, unsigned long memend); - extern unsigned long free_all_bootmem(void); extern void reset_node_managed_pages(pg_data_t *pgdat); extern void reset_all_zones_managed_pages(void); @@ -55,14 +47,6 @@ extern void free_bootmem_late(unsigned long physaddr, unsigned long size); #define BOOTMEM_DEFAULT 0 #define BOOTMEM_EXCLUSIVE (1<<0) -extern int reserve_bootmem(unsigned long addr, - unsigned long size, - int flags); -extern int reserve_bootmem_node(pg_data_t *pgdat, - unsigned long physaddr, - unsigned long size, - int flags); - extern void *__alloc_bootmem(unsigned long size, unsigned long align, unsigned long goal); diff --git a/mm/bootmem.c b/mm/bootmem.c deleted file mode 100644 index 97db0e8e362b..000000000000 --- a/mm/bootmem.c +++ /dev/null @@ -1,811 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * bootmem - A boot-time physical memory allocator and configurator - * - * Copyright (C) 1999 Ingo Molnar - * 1999 Kanoj Sarcar, SGI - * 2008 Johannes Weiner - * - * Access to this subsystem has to be serialized externally (which is true - * for the boot process anyway). - */ -#include -#include -#include -#include -#include -#include -#include -#include -#include - -#include "internal.h" - -/** - * DOC: bootmem overview - * - * Bootmem is a boot-time physical memory allocator and configurator. - * - * It is used early in the boot process before the page allocator is - * set up. - * - * Bootmem is based on the most basic of allocators, a First Fit - * allocator which uses a bitmap to represent memory. If a bit is 1, - * the page is allocated and 0 if unallocated. To satisfy allocations - * of sizes smaller than a page, the allocator records the Page Frame - * Number (PFN) of the last allocation and the offset the allocation - * ended at. Subsequent small allocations are merged together and - * stored on the same page. - * - * The information used by the bootmem allocator is represented by - * :c:type:`struct bootmem_data`. An array to hold up to %MAX_NUMNODES - * such structures is statically allocated and then it is discarded - * when the system initialization completes. Each entry in this array - * corresponds to a node with memory. For UMA systems only entry 0 is - * used. - * - * The bootmem allocator is initialized during early architecture - * specific setup. Each architecture is required to supply a - * :c:func:`setup_arch` function which, among other tasks, is - * responsible for acquiring the necessary parameters to initialise - * the boot memory allocator. These parameters define limits of usable - * physical memory: - * - * * @min_low_pfn - the lowest PFN that is available in the system - * * @max_low_pfn - the highest PFN that may be addressed by low - * memory (%ZONE_NORMAL) - * * @max_pfn - the last PFN available to the system. - * - * After those limits are determined, the :c:func:`init_bootmem` or - * :c:func:`init_bootmem_node` function should be called to initialize - * the bootmem allocator. The UMA case should use the `init_bootmem` - * function. It will initialize ``contig_page_data`` structure that - * represents the only memory node in the system. In the NUMA case the - * `init_bootmem_node` function should be called to initialize the - * bootmem allocator for each node. - * - * Once the allocator is set up, it is possible to use either single - * node or NUMA variant of the allocation APIs. - */ - -#ifndef CONFIG_NEED_MULTIPLE_NODES -struct pglist_data __refdata contig_page_data = { - .bdata = &bootmem_node_data[0] -}; -EXPORT_SYMBOL(contig_page_data); -#endif - -unsigned long max_low_pfn; -unsigned long min_low_pfn; -unsigned long max_pfn; -unsigned long long max_possible_pfn; - -bootmem_data_t bootmem_node_data[MAX_NUMNODES] __initdata; - -static struct list_head bdata_list __initdata = LIST_HEAD_INIT(bdata_list); - -static int bootmem_debug; - -static int __init bootmem_debug_setup(char *buf) -{ - bootmem_debug = 1; - return 0; -} -early_param("bootmem_debug", bootmem_debug_setup); - -#define bdebug(fmt, args...) ({ \ - if (unlikely(bootmem_debug)) \ - pr_info("bootmem::%s " fmt, \ - __func__, ## args); \ -}) - -static unsigned long __init bootmap_bytes(unsigned long pages) -{ - unsigned long bytes = DIV_ROUND_UP(pages, BITS_PER_BYTE); - - return ALIGN(bytes, sizeof(long)); -} - -/** - * bootmem_bootmap_pages - calculate bitmap size in pages - * @pages: number of pages the bitmap has to represent - * - * Return: the number of pages needed to hold the bitmap. - */ -unsigned long __init bootmem_bootmap_pages(unsigned long pages) -{ - unsigned long bytes = bootmap_bytes(pages); - - return PAGE_ALIGN(bytes) >> PAGE_SHIFT; -} - -/* - * link bdata in order - */ -static void __init link_bootmem(bootmem_data_t *bdata) -{ - bootmem_data_t *ent; - - list_for_each_entry(ent, &bdata_list, list) { - if (bdata->node_min_pfn < ent->node_min_pfn) { - list_add_tail(&bdata->list, &ent->list); - return; - } - } - - list_add_tail(&bdata->list, &bdata_list); -} - -/* - * Called once to set up the allocator itself. - */ -static unsigned long __init init_bootmem_core(bootmem_data_t *bdata, - unsigned long mapstart, unsigned long start, unsigned long end) -{ - unsigned long mapsize; - - mminit_validate_memmodel_limits(&start, &end); - bdata->node_bootmem_map = phys_to_virt(PFN_PHYS(mapstart)); - bdata->node_min_pfn = start; - bdata->node_low_pfn = end; - link_bootmem(bdata); - - /* - * Initially all pages are reserved - setup_arch() has to - * register free RAM areas explicitly. - */ - mapsize = bootmap_bytes(end - start); - memset(bdata->node_bootmem_map, 0xff, mapsize); - - bdebug("nid=%td start=%lx map=%lx end=%lx mapsize=%lx\n", - bdata - bootmem_node_data, start, mapstart, end, mapsize); - - return mapsize; -} - -/** - * init_bootmem_node - register a node as boot memory - * @pgdat: node to register - * @freepfn: pfn where the bitmap for this node is to be placed - * @startpfn: first pfn on the node - * @endpfn: first pfn after the node - * - * Return: the number of bytes needed to hold the bitmap for this node. - */ -unsigned long __init init_bootmem_node(pg_data_t *pgdat, unsigned long freepfn, - unsigned long startpfn, unsigned long endpfn) -{ - return init_bootmem_core(pgdat->bdata, freepfn, startpfn, endpfn); -} - -/** - * init_bootmem - register boot memory - * @start: pfn where the bitmap is to be placed - * @pages: number of available physical pages - * - * Return: the number of bytes needed to hold the bitmap. - */ -unsigned long __init init_bootmem(unsigned long start, unsigned long pages) -{ - max_low_pfn = pages; - min_low_pfn = start; - return init_bootmem_core(NODE_DATA(0)->bdata, start, 0, pages); -} - -void __init free_bootmem_late(unsigned long physaddr, unsigned long size) -{ - unsigned long cursor, end; - - kmemleak_free_part_phys(physaddr, size); - - cursor = PFN_UP(physaddr); - end = PFN_DOWN(physaddr + size); - - for (; cursor < end; cursor++) { - __free_pages_bootmem(pfn_to_page(cursor), cursor, 0); - totalram_pages++; - } -} - -static unsigned long __init free_all_bootmem_core(bootmem_data_t *bdata) -{ - struct page *page; - unsigned long *map, start, end, pages, cur, count = 0; - - if (!bdata->node_bootmem_map) - return 0; - - map = bdata->node_bootmem_map; - start = bdata->node_min_pfn; - end = bdata->node_low_pfn; - - bdebug("nid=%td start=%lx end=%lx\n", - bdata - bootmem_node_data, start, end); - - while (start < end) { - unsigned long idx, vec; - unsigned shift; - - idx = start - bdata->node_min_pfn; - shift = idx & (BITS_PER_LONG - 1); - /* - * vec holds at most BITS_PER_LONG map bits, - * bit 0 corresponds to start. - */ - vec = ~map[idx / BITS_PER_LONG]; - - if (shift) { - vec >>= shift; - if (end - start >= BITS_PER_LONG) - vec |= ~map[idx / BITS_PER_LONG + 1] << - (BITS_PER_LONG - shift); - } - /* - * If we have a properly aligned and fully unreserved - * BITS_PER_LONG block of pages in front of us, free - * it in one go. - */ - if (IS_ALIGNED(start, BITS_PER_LONG) && vec == ~0UL) { - int order = ilog2(BITS_PER_LONG); - - __free_pages_bootmem(pfn_to_page(start), start, order); - count += BITS_PER_LONG; - start += BITS_PER_LONG; - } else { - cur = start; - - start = ALIGN(start + 1, BITS_PER_LONG); - while (vec && cur != start) { - if (vec & 1) { - page = pfn_to_page(cur); - __free_pages_bootmem(page, cur, 0); - count++; - } - vec >>= 1; - ++cur; - } - } - } - - cur = bdata->node_min_pfn; - page = virt_to_page(bdata->node_bootmem_map); - pages = bdata->node_low_pfn - bdata->node_min_pfn; - pages = bootmem_bootmap_pages(pages); - count += pages; - while (pages--) - __free_pages_bootmem(page++, cur++, 0); - bdata->node_bootmem_map = NULL; - - bdebug("nid=%td released=%lx\n", bdata - bootmem_node_data, count); - - return count; -} - -static int reset_managed_pages_done __initdata; - -void reset_node_managed_pages(pg_data_t *pgdat) -{ - struct zone *z; - - for (z = pgdat->node_zones; z < pgdat->node_zones + MAX_NR_ZONES; z++) - z->managed_pages = 0; -} - -void __init reset_all_zones_managed_pages(void) -{ - struct pglist_data *pgdat; - - if (reset_managed_pages_done) - return; - - for_each_online_pgdat(pgdat) - reset_node_managed_pages(pgdat); - - reset_managed_pages_done = 1; -} - -unsigned long __init free_all_bootmem(void) -{ - unsigned long total_pages = 0; - bootmem_data_t *bdata; - - reset_all_zones_managed_pages(); - - list_for_each_entry(bdata, &bdata_list, list) - total_pages += free_all_bootmem_core(bdata); - - totalram_pages += total_pages; - - return total_pages; -} - -static void __init __free(bootmem_data_t *bdata, - unsigned long sidx, unsigned long eidx) -{ - unsigned long idx; - - bdebug("nid=%td start=%lx end=%lx\n", bdata - bootmem_node_data, - sidx + bdata->node_min_pfn, - eidx + bdata->node_min_pfn); - - if (WARN_ON(bdata->node_bootmem_map == NULL)) - return; - - if (bdata->hint_idx > sidx) - bdata->hint_idx = sidx; - - for (idx = sidx; idx < eidx; idx++) - if (!test_and_clear_bit(idx, bdata->node_bootmem_map)) - BUG(); -} - -static int __init __reserve(bootmem_data_t *bdata, unsigned long sidx, - unsigned long eidx, int flags) -{ - unsigned long idx; - int exclusive = flags & BOOTMEM_EXCLUSIVE; - - bdebug("nid=%td start=%lx end=%lx flags=%x\n", - bdata - bootmem_node_data, - sidx + bdata->node_min_pfn, - eidx + bdata->node_min_pfn, - flags); - - if (WARN_ON(bdata->node_bootmem_map == NULL)) - return 0; - - for (idx = sidx; idx < eidx; idx++) - if (test_and_set_bit(idx, bdata->node_bootmem_map)) { - if (exclusive) { - __free(bdata, sidx, idx); - return -EBUSY; - } - bdebug("silent double reserve of PFN %lx\n", - idx + bdata->node_min_pfn); - } - return 0; -} - -static int __init mark_bootmem_node(bootmem_data_t *bdata, - unsigned long start, unsigned long end, - int reserve, int flags) -{ - unsigned long sidx, eidx; - - bdebug("nid=%td start=%lx end=%lx reserve=%d flags=%x\n", - bdata - bootmem_node_data, start, end, reserve, flags); - - BUG_ON(start < bdata->node_min_pfn); - BUG_ON(end > bdata->node_low_pfn); - - sidx = start - bdata->node_min_pfn; - eidx = end - bdata->node_min_pfn; - - if (reserve) - return __reserve(bdata, sidx, eidx, flags); - else - __free(bdata, sidx, eidx); - return 0; -} - -static int __init mark_bootmem(unsigned long start, unsigned long end, - int reserve, int flags) -{ - unsigned long pos; - bootmem_data_t *bdata; - - pos = start; - list_for_each_entry(bdata, &bdata_list, list) { - int err; - unsigned long max; - - if (pos < bdata->node_min_pfn || - pos >= bdata->node_low_pfn) { - BUG_ON(pos != start); - continue; - } - - max = min(bdata->node_low_pfn, end); - - err = mark_bootmem_node(bdata, pos, max, reserve, flags); - if (reserve && err) { - mark_bootmem(start, pos, 0, 0); - return err; - } - - if (max == end) - return 0; - pos = bdata->node_low_pfn; - } - BUG(); -} - -void __init free_bootmem_node(pg_data_t *pgdat, unsigned long physaddr, - unsigned long size) -{ - unsigned long start, end; - - kmemleak_free_part_phys(physaddr, size); - - start = PFN_UP(physaddr); - end = PFN_DOWN(physaddr + size); - - mark_bootmem_node(pgdat->bdata, start, end, 0, 0); -} - -void __init free_bootmem(unsigned long physaddr, unsigned long size) -{ - unsigned long start, end; - - kmemleak_free_part_phys(physaddr, size); - - start = PFN_UP(physaddr); - end = PFN_DOWN(physaddr + size); - - mark_bootmem(start, end, 0, 0); -} - -/** - * reserve_bootmem_node - mark a page range as reserved - * @pgdat: node the range resides on - * @physaddr: starting address of the range - * @size: size of the range in bytes - * @flags: reservation flags (see linux/bootmem.h) - * - * Partial pages will be reserved. - * - * The range must reside completely on the specified node. - * - * Return: 0 on success, -errno on failure. - */ -int __init reserve_bootmem_node(pg_data_t *pgdat, unsigned long physaddr, - unsigned long size, int flags) -{ - unsigned long start, end; - - start = PFN_DOWN(physaddr); - end = PFN_UP(physaddr + size); - - return mark_bootmem_node(pgdat->bdata, start, end, 1, flags); -} - -/** - * reserve_bootmem - mark a page range as reserved - * @addr: starting address of the range - * @size: size of the range in bytes - * @flags: reservation flags (see linux/bootmem.h) - * - * Partial pages will be reserved. - * - * The range must be contiguous but may span node boundaries. - * - * Return: 0 on success, -errno on failure. - */ -int __init reserve_bootmem(unsigned long addr, unsigned long size, - int flags) -{ - unsigned long start, end; - - start = PFN_DOWN(addr); - end = PFN_UP(addr + size); - - return mark_bootmem(start, end, 1, flags); -} - -static unsigned long __init align_idx(struct bootmem_data *bdata, - unsigned long idx, unsigned long step) -{ - unsigned long base = bdata->node_min_pfn; - - /* - * Align the index with respect to the node start so that the - * combination of both satisfies the requested alignment. - */ - - return ALIGN(base + idx, step) - base; -} - -static unsigned long __init align_off(struct bootmem_data *bdata, - unsigned long off, unsigned long align) -{ - unsigned long base = PFN_PHYS(bdata->node_min_pfn); - - /* Same as align_idx for byte offsets */ - - return ALIGN(base + off, align) - base; -} - -static void * __init alloc_bootmem_bdata(struct bootmem_data *bdata, - unsigned long size, unsigned long align, - unsigned long goal, unsigned long limit) -{ - unsigned long fallback = 0; - unsigned long min, max, start, sidx, midx, step; - - bdebug("nid=%td size=%lx [%lu pages] align=%lx goal=%lx limit=%lx\n", - bdata - bootmem_node_data, size, PAGE_ALIGN(size) >> PAGE_SHIFT, - align, goal, limit); - - BUG_ON(!size); - BUG_ON(align & (align - 1)); - BUG_ON(limit && goal + size > limit); - - if (!bdata->node_bootmem_map) - return NULL; - - min = bdata->node_min_pfn; - max = bdata->node_low_pfn; - - goal >>= PAGE_SHIFT; - limit >>= PAGE_SHIFT; - - if (limit && max > limit) - max = limit; - if (max <= min) - return NULL; - - step = max(align >> PAGE_SHIFT, 1UL); - - if (goal && min < goal && goal < max) - start = ALIGN(goal, step); - else - start = ALIGN(min, step); - - sidx = start - bdata->node_min_pfn; - midx = max - bdata->node_min_pfn; - - if (bdata->hint_idx > sidx) { - /* - * Handle the valid case of sidx being zero and still - * catch the fallback below. - */ - fallback = sidx + 1; - sidx = align_idx(bdata, bdata->hint_idx, step); - } - - while (1) { - int merge; - void *region; - unsigned long eidx, i, start_off, end_off; -find_block: - sidx = find_next_zero_bit(bdata->node_bootmem_map, midx, sidx); - sidx = align_idx(bdata, sidx, step); - eidx = sidx + PFN_UP(size); - - if (sidx >= midx || eidx > midx) - break; - - for (i = sidx; i < eidx; i++) - if (test_bit(i, bdata->node_bootmem_map)) { - sidx = align_idx(bdata, i, step); - if (sidx == i) - sidx += step; - goto find_block; - } - - if (bdata->last_end_off & (PAGE_SIZE - 1) && - PFN_DOWN(bdata->last_end_off) + 1 == sidx) - start_off = align_off(bdata, bdata->last_end_off, align); - else - start_off = PFN_PHYS(sidx); - - merge = PFN_DOWN(start_off) < sidx; - end_off = start_off + size; - - bdata->last_end_off = end_off; - bdata->hint_idx = PFN_UP(end_off); - - /* - * Reserve the area now: - */ - if (__reserve(bdata, PFN_DOWN(start_off) + merge, - PFN_UP(end_off), BOOTMEM_EXCLUSIVE)) - BUG(); - - region = phys_to_virt(PFN_PHYS(bdata->node_min_pfn) + - start_off); - memset(region, 0, size); - /* - * The min_count is set to 0 so that bootmem allocated blocks - * are never reported as leaks. - */ - kmemleak_alloc(region, size, 0, 0); - return region; - } - - if (fallback) { - sidx = align_idx(bdata, fallback - 1, step); - fallback = 0; - goto find_block; - } - - return NULL; -} - -static void * __init alloc_bootmem_core(unsigned long size, - unsigned long align, - unsigned long goal, - unsigned long limit) -{ - bootmem_data_t *bdata; - void *region; - - if (WARN_ON_ONCE(slab_is_available())) - return kzalloc(size, GFP_NOWAIT); - - list_for_each_entry(bdata, &bdata_list, list) { - if (goal && bdata->node_low_pfn <= PFN_DOWN(goal)) - continue; - if (limit && bdata->node_min_pfn >= PFN_DOWN(limit)) - break; - - region = alloc_bootmem_bdata(bdata, size, align, goal, limit); - if (region) - return region; - } - - return NULL; -} - -static void * __init ___alloc_bootmem_nopanic(unsigned long size, - unsigned long align, - unsigned long goal, - unsigned long limit) -{ - void *ptr; - -restart: - ptr = alloc_bootmem_core(size, align, goal, limit); - if (ptr) - return ptr; - if (goal) { - goal = 0; - goto restart; - } - - return NULL; -} - -void * __init __alloc_bootmem_nopanic(unsigned long size, unsigned long align, - unsigned long goal) -{ - unsigned long limit = 0; - - return ___alloc_bootmem_nopanic(size, align, goal, limit); -} - -static void * __init ___alloc_bootmem(unsigned long size, unsigned long align, - unsigned long goal, unsigned long limit) -{ - void *mem = ___alloc_bootmem_nopanic(size, align, goal, limit); - - if (mem) - return mem; - /* - * Whoops, we cannot satisfy the allocation request. - */ - pr_alert("bootmem alloc of %lu bytes failed!\n", size); - panic("Out of memory"); - return NULL; -} - -void * __init __alloc_bootmem(unsigned long size, unsigned long align, - unsigned long goal) -{ - unsigned long limit = 0; - - return ___alloc_bootmem(size, align, goal, limit); -} - -void * __init ___alloc_bootmem_node_nopanic(pg_data_t *pgdat, - unsigned long size, unsigned long align, - unsigned long goal, unsigned long limit) -{ - void *ptr; - - if (WARN_ON_ONCE(slab_is_available())) - return kzalloc_node(size, GFP_NOWAIT, pgdat->node_id); -again: - - /* do not panic in alloc_bootmem_bdata() */ - if (limit && goal + size > limit) - limit = 0; - - ptr = alloc_bootmem_bdata(pgdat->bdata, size, align, goal, limit); - if (ptr) - return ptr; - - ptr = alloc_bootmem_core(size, align, goal, limit); - if (ptr) - return ptr; - - if (goal) { - goal = 0; - goto again; - } - - return NULL; -} - -void * __init __alloc_bootmem_node_nopanic(pg_data_t *pgdat, unsigned long size, - unsigned long align, unsigned long goal) -{ - return ___alloc_bootmem_node_nopanic(pgdat, size, align, goal, 0); -} - -void * __init ___alloc_bootmem_node(pg_data_t *pgdat, unsigned long size, - unsigned long align, unsigned long goal, - unsigned long limit) -{ - void *ptr; - - ptr = ___alloc_bootmem_node_nopanic(pgdat, size, align, goal, 0); - if (ptr) - return ptr; - - pr_alert("bootmem alloc of %lu bytes failed!\n", size); - panic("Out of memory"); - return NULL; -} - -void * __init __alloc_bootmem_node(pg_data_t *pgdat, unsigned long size, - unsigned long align, unsigned long goal) -{ - if (WARN_ON_ONCE(slab_is_available())) - return kzalloc_node(size, GFP_NOWAIT, pgdat->node_id); - - return ___alloc_bootmem_node(pgdat, size, align, goal, 0); -} - -void * __init __alloc_bootmem_node_high(pg_data_t *pgdat, unsigned long size, - unsigned long align, unsigned long goal) -{ -#ifdef MAX_DMA32_PFN - unsigned long end_pfn; - - if (WARN_ON_ONCE(slab_is_available())) - return kzalloc_node(size, GFP_NOWAIT, pgdat->node_id); - - /* update goal according ...MAX_DMA32_PFN */ - end_pfn = pgdat_end_pfn(pgdat); - - if (end_pfn > MAX_DMA32_PFN + (128 >> (20 - PAGE_SHIFT)) && - (goal >> PAGE_SHIFT) < MAX_DMA32_PFN) { - void *ptr; - unsigned long new_goal; - - new_goal = MAX_DMA32_PFN << PAGE_SHIFT; - ptr = alloc_bootmem_bdata(pgdat->bdata, size, align, - new_goal, 0); - if (ptr) - return ptr; - } -#endif - - return __alloc_bootmem_node(pgdat, size, align, goal); - -} - -void * __init __alloc_bootmem_low(unsigned long size, unsigned long align, - unsigned long goal) -{ - return ___alloc_bootmem(size, align, goal, ARCH_LOW_ADDRESS_LIMIT); -} - -void * __init __alloc_bootmem_low_nopanic(unsigned long size, - unsigned long align, - unsigned long goal) -{ - return ___alloc_bootmem_nopanic(size, align, goal, - ARCH_LOW_ADDRESS_LIMIT); -} - -void * __init __alloc_bootmem_low_node(pg_data_t *pgdat, unsigned long size, - unsigned long align, unsigned long goal) -{ - if (WARN_ON_ONCE(slab_is_available())) - return kzalloc_node(size, GFP_NOWAIT, pgdat->node_id); - - return ___alloc_bootmem_node(pgdat, size, align, - goal, ARCH_LOW_ADDRESS_LIMIT); -} -- cgit v1.2.3 From b146ada221c178a384fee2a8e2e5b2e8a04476b1 Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Tue, 30 Oct 2018 15:07:54 -0700 Subject: mm: nobootmem: remove dead code Several bootmem functions and macros are not used. Remove them. Link: http://lkml.kernel.org/r/1536927045-23536-6-git-send-email-rppt@linux.vnet.ibm.com Signed-off-by: Mike Rapoport Acked-by: Michal Hocko Cc: Catalin Marinas Cc: Chris Zankel Cc: "David S. Miller" Cc: Geert Uytterhoeven Cc: Greentime Hu Cc: Greg Kroah-Hartman Cc: Guan Xuetao Cc: Ingo Molnar Cc: "James E.J. Bottomley" Cc: Jonas Bonn Cc: Jonathan Corbet Cc: Ley Foon Tan Cc: Mark Salter Cc: Martin Schwidefsky Cc: Matt Turner Cc: Michael Ellerman Cc: Michal Simek Cc: Palmer Dabbelt Cc: Paul Burton Cc: Richard Kuo Cc: Richard Weinberger Cc: Rich Felker Cc: Russell King Cc: Serge Semin Cc: Thomas Gleixner Cc: Tony Luck Cc: Vineet Gupta Cc: Yoshinori Sato Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/bootmem.h | 26 -------------------------- mm/nobootmem.c | 35 ----------------------------------- 2 files changed, 61 deletions(-) (limited to 'mm') diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h index fce6278a1724..b74bafd110b9 100644 --- a/include/linux/bootmem.h +++ b/include/linux/bootmem.h @@ -36,17 +36,6 @@ extern void free_bootmem_node(pg_data_t *pgdat, extern void free_bootmem(unsigned long physaddr, unsigned long size); extern void free_bootmem_late(unsigned long physaddr, unsigned long size); -/* - * Flags for reserve_bootmem (also if CONFIG_HAVE_ARCH_BOOTMEM_NODE, - * the architecture-specific code should honor this). - * - * If flags is BOOTMEM_DEFAULT, then the return value is always 0 (success). - * If flags contains BOOTMEM_EXCLUSIVE, then -EBUSY is returned if the memory - * already was reserved. - */ -#define BOOTMEM_DEFAULT 0 -#define BOOTMEM_EXCLUSIVE (1<<0) - extern void *__alloc_bootmem(unsigned long size, unsigned long align, unsigned long goal); @@ -73,13 +62,6 @@ void *___alloc_bootmem_node_nopanic(pg_data_t *pgdat, extern void *__alloc_bootmem_low(unsigned long size, unsigned long align, unsigned long goal) __malloc; -void *__alloc_bootmem_low_nopanic(unsigned long size, - unsigned long align, - unsigned long goal) __malloc; -extern void *__alloc_bootmem_low_node(pg_data_t *pgdat, - unsigned long size, - unsigned long align, - unsigned long goal) __malloc; /* We are using top down, so it is safe to use 0 here */ #define BOOTMEM_LOW_LIMIT 0 @@ -92,8 +74,6 @@ extern void *__alloc_bootmem_low_node(pg_data_t *pgdat, __alloc_bootmem(x, SMP_CACHE_BYTES, BOOTMEM_LOW_LIMIT) #define alloc_bootmem_align(x, align) \ __alloc_bootmem(x, align, BOOTMEM_LOW_LIMIT) -#define alloc_bootmem_nopanic(x) \ - __alloc_bootmem_nopanic(x, SMP_CACHE_BYTES, BOOTMEM_LOW_LIMIT) #define alloc_bootmem_pages(x) \ __alloc_bootmem(x, PAGE_SIZE, BOOTMEM_LOW_LIMIT) #define alloc_bootmem_pages_nopanic(x) \ @@ -104,17 +84,11 @@ extern void *__alloc_bootmem_low_node(pg_data_t *pgdat, __alloc_bootmem_node_nopanic(pgdat, x, SMP_CACHE_BYTES, BOOTMEM_LOW_LIMIT) #define alloc_bootmem_pages_node(pgdat, x) \ __alloc_bootmem_node(pgdat, x, PAGE_SIZE, BOOTMEM_LOW_LIMIT) -#define alloc_bootmem_pages_node_nopanic(pgdat, x) \ - __alloc_bootmem_node_nopanic(pgdat, x, PAGE_SIZE, BOOTMEM_LOW_LIMIT) #define alloc_bootmem_low(x) \ __alloc_bootmem_low(x, SMP_CACHE_BYTES, 0) -#define alloc_bootmem_low_pages_nopanic(x) \ - __alloc_bootmem_low_nopanic(x, PAGE_SIZE, 0) #define alloc_bootmem_low_pages(x) \ __alloc_bootmem_low(x, PAGE_SIZE, 0) -#define alloc_bootmem_low_pages_node(pgdat, x) \ - __alloc_bootmem_low_node(pgdat, x, PAGE_SIZE, 0) /* FIXME: use MEMBLOCK_ALLOC_* variants here */ #define BOOTMEM_ALLOC_ACCESSIBLE 0 diff --git a/mm/nobootmem.c b/mm/nobootmem.c index d4d0cd474087..44ce7de1be8f 100644 --- a/mm/nobootmem.c +++ b/mm/nobootmem.c @@ -404,38 +404,3 @@ void * __init __alloc_bootmem_low(unsigned long size, unsigned long align, { return ___alloc_bootmem(size, align, goal, ARCH_LOW_ADDRESS_LIMIT); } - -void * __init __alloc_bootmem_low_nopanic(unsigned long size, - unsigned long align, - unsigned long goal) -{ - return ___alloc_bootmem_nopanic(size, align, goal, - ARCH_LOW_ADDRESS_LIMIT); -} - -/** - * __alloc_bootmem_low_node - allocate low boot memory from a specific node - * @pgdat: node to allocate from - * @size: size of the request in bytes - * @align: alignment of the region - * @goal: preferred starting address of the region - * - * The goal is dropped if it can not be satisfied and the allocation will - * fall back to memory below @goal. - * - * Allocation may fall back to any node in the system if the specified node - * can not hold the requested memory. - * - * The function panics if the request can not be satisfied. - * - * Return: address of the allocated region. - */ -void * __init __alloc_bootmem_low_node(pg_data_t *pgdat, unsigned long size, - unsigned long align, unsigned long goal) -{ - if (WARN_ON_ONCE(slab_is_available())) - return kzalloc_node(size, GFP_NOWAIT, pgdat->node_id); - - return ___alloc_bootmem_node(pgdat, size, align, goal, - ARCH_LOW_ADDRESS_LIMIT); -} -- cgit v1.2.3 From 9a8dd708d547268c899f1cb443c49bd4d8c84eb3 Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Tue, 30 Oct 2018 15:07:59 -0700 Subject: memblock: rename memblock_alloc{_nid,_try_nid} to memblock_phys_alloc* Make it explicit that the caller gets a physical address rather than a virtual one. This will also allow using meblock_alloc prefix for memblock allocations returning virtual address, which is done in the following patches. The conversion is done using the following semantic patch: @@ expression e1, e2, e3; @@ ( - memblock_alloc(e1, e2) + memblock_phys_alloc(e1, e2) | - memblock_alloc_nid(e1, e2, e3) + memblock_phys_alloc_nid(e1, e2, e3) | - memblock_alloc_try_nid(e1, e2, e3) + memblock_phys_alloc_try_nid(e1, e2, e3) ) Link: http://lkml.kernel.org/r/1536927045-23536-7-git-send-email-rppt@linux.vnet.ibm.com Signed-off-by: Mike Rapoport Acked-by: Michal Hocko Cc: Catalin Marinas Cc: Chris Zankel Cc: "David S. Miller" Cc: Geert Uytterhoeven Cc: Greentime Hu Cc: Greg Kroah-Hartman Cc: Guan Xuetao Cc: Ingo Molnar Cc: "James E.J. Bottomley" Cc: Jonas Bonn Cc: Jonathan Corbet Cc: Ley Foon Tan Cc: Mark Salter Cc: Martin Schwidefsky Cc: Matt Turner Cc: Michael Ellerman Cc: Michal Simek Cc: Palmer Dabbelt Cc: Paul Burton Cc: Richard Kuo Cc: Richard Weinberger Cc: Rich Felker Cc: Russell King Cc: Serge Semin Cc: Thomas Gleixner Cc: Tony Luck Cc: Vineet Gupta Cc: Yoshinori Sato Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/arm/mm/mmu.c | 2 +- arch/arm64/mm/mmu.c | 2 +- arch/arm64/mm/numa.c | 2 +- arch/c6x/mm/dma-coherent.c | 4 ++-- arch/nds32/mm/init.c | 8 ++++---- arch/openrisc/mm/init.c | 2 +- arch/openrisc/mm/ioremap.c | 2 +- arch/powerpc/kernel/dt_cpu_ftrs.c | 4 +--- arch/powerpc/kernel/paca.c | 2 +- arch/powerpc/kernel/prom.c | 2 +- arch/powerpc/kernel/setup-common.c | 3 +-- arch/powerpc/kernel/setup_32.c | 10 +++++----- arch/powerpc/mm/numa.c | 2 +- arch/powerpc/mm/pgtable_32.c | 2 +- arch/powerpc/mm/ppc_mmu_32.c | 2 +- arch/powerpc/platforms/pasemi/iommu.c | 2 +- arch/powerpc/platforms/powernv/opal.c | 2 +- arch/powerpc/sysdev/dart_iommu.c | 2 +- arch/s390/kernel/crash_dump.c | 2 +- arch/s390/kernel/setup.c | 3 ++- arch/s390/mm/vmem.c | 4 ++-- arch/s390/numa/numa.c | 2 +- arch/sparc/kernel/mdesc.c | 2 +- arch/sparc/kernel/prom_64.c | 2 +- arch/sparc/mm/init_64.c | 11 ++++++----- arch/unicore32/mm/mmu.c | 2 +- arch/x86/mm/numa.c | 2 +- drivers/firmware/efi/memmap.c | 2 +- include/linux/memblock.h | 6 +++--- mm/memblock.c | 8 ++++---- 30 files changed, 50 insertions(+), 51 deletions(-) (limited to 'mm') diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c index e46a6a446cdd..f5cc1ccfea3d 100644 --- a/arch/arm/mm/mmu.c +++ b/arch/arm/mm/mmu.c @@ -721,7 +721,7 @@ EXPORT_SYMBOL(phys_mem_access_prot); static void __init *early_alloc_aligned(unsigned long sz, unsigned long align) { - void *ptr = __va(memblock_alloc(sz, align)); + void *ptr = __va(memblock_phys_alloc(sz, align)); memset(ptr, 0, sz); return ptr; } diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c index 9498c15b847b..394b8d554def 100644 --- a/arch/arm64/mm/mmu.c +++ b/arch/arm64/mm/mmu.c @@ -101,7 +101,7 @@ static phys_addr_t __init early_pgtable_alloc(void) phys_addr_t phys; void *ptr; - phys = memblock_alloc(PAGE_SIZE, PAGE_SIZE); + phys = memblock_phys_alloc(PAGE_SIZE, PAGE_SIZE); /* * The FIX_{PGD,PUD,PMD} slots may be in active use, but the FIX_PTE diff --git a/arch/arm64/mm/numa.c b/arch/arm64/mm/numa.c index d7b66fc5e1c5..c7fb34efd23e 100644 --- a/arch/arm64/mm/numa.c +++ b/arch/arm64/mm/numa.c @@ -237,7 +237,7 @@ static void __init setup_node_data(int nid, u64 start_pfn, u64 end_pfn) if (start_pfn >= end_pfn) pr_info("Initmem setup node %d []\n", nid); - nd_pa = memblock_alloc_try_nid(nd_size, SMP_CACHE_BYTES, nid); + nd_pa = memblock_phys_alloc_try_nid(nd_size, SMP_CACHE_BYTES, nid); nd = __va(nd_pa); /* report and initialize */ diff --git a/arch/c6x/mm/dma-coherent.c b/arch/c6x/mm/dma-coherent.c index d0a8e0c4b27e..01305c787201 100644 --- a/arch/c6x/mm/dma-coherent.c +++ b/arch/c6x/mm/dma-coherent.c @@ -135,8 +135,8 @@ void __init coherent_mem_init(phys_addr_t start, u32 size) if (dma_size & (PAGE_SIZE - 1)) ++dma_pages; - bitmap_phys = memblock_alloc(BITS_TO_LONGS(dma_pages) * sizeof(long), - sizeof(long)); + bitmap_phys = memblock_phys_alloc(BITS_TO_LONGS(dma_pages) * sizeof(long), + sizeof(long)); dma_bitmap = phys_to_virt(bitmap_phys); memset(dma_bitmap, 0, dma_pages * PAGE_SIZE); diff --git a/arch/nds32/mm/init.c b/arch/nds32/mm/init.c index c713d2ad55dc..5af81b866aa5 100644 --- a/arch/nds32/mm/init.c +++ b/arch/nds32/mm/init.c @@ -81,7 +81,7 @@ static void __init map_ram(void) } /* Alloc one page for holding PTE's... */ - pte = (pte_t *) __va(memblock_alloc(PAGE_SIZE, PAGE_SIZE)); + pte = (pte_t *) __va(memblock_phys_alloc(PAGE_SIZE, PAGE_SIZE)); memset(pte, 0, PAGE_SIZE); set_pmd(pme, __pmd(__pa(pte) + _PAGE_KERNEL_TABLE)); @@ -114,7 +114,7 @@ static void __init fixedrange_init(void) pgd = swapper_pg_dir + pgd_index(vaddr); pud = pud_offset(pgd, vaddr); pmd = pmd_offset(pud, vaddr); - fixmap_pmd_p = (pmd_t *) __va(memblock_alloc(PAGE_SIZE, PAGE_SIZE)); + fixmap_pmd_p = (pmd_t *) __va(memblock_phys_alloc(PAGE_SIZE, PAGE_SIZE)); memset(fixmap_pmd_p, 0, PAGE_SIZE); set_pmd(pmd, __pmd(__pa(fixmap_pmd_p) + _PAGE_KERNEL_TABLE)); @@ -127,7 +127,7 @@ static void __init fixedrange_init(void) pgd = swapper_pg_dir + pgd_index(vaddr); pud = pud_offset(pgd, vaddr); pmd = pmd_offset(pud, vaddr); - pte = (pte_t *) __va(memblock_alloc(PAGE_SIZE, PAGE_SIZE)); + pte = (pte_t *) __va(memblock_phys_alloc(PAGE_SIZE, PAGE_SIZE)); memset(pte, 0, PAGE_SIZE); set_pmd(pmd, __pmd(__pa(pte) + _PAGE_KERNEL_TABLE)); pkmap_page_table = pte; @@ -153,7 +153,7 @@ void __init paging_init(void) fixedrange_init(); /* allocate space for empty_zero_page */ - zero_page = __va(memblock_alloc(PAGE_SIZE, PAGE_SIZE)); + zero_page = __va(memblock_phys_alloc(PAGE_SIZE, PAGE_SIZE)); memset(zero_page, 0, PAGE_SIZE); zone_sizes_init(); diff --git a/arch/openrisc/mm/init.c b/arch/openrisc/mm/init.c index 6972d5d6f23f..b7670de26c11 100644 --- a/arch/openrisc/mm/init.c +++ b/arch/openrisc/mm/init.c @@ -106,7 +106,7 @@ static void __init map_ram(void) } /* Alloc one page for holding PTE's... */ - pte = (pte_t *) __va(memblock_alloc(PAGE_SIZE, PAGE_SIZE)); + pte = (pte_t *) __va(memblock_phys_alloc(PAGE_SIZE, PAGE_SIZE)); set_pmd(pme, __pmd(_KERNPG_TABLE + __pa(pte))); /* Fill the newly allocated page with PTE'S */ diff --git a/arch/openrisc/mm/ioremap.c b/arch/openrisc/mm/ioremap.c index 2175e4bfd9fc..c9697529b3f0 100644 --- a/arch/openrisc/mm/ioremap.c +++ b/arch/openrisc/mm/ioremap.c @@ -126,7 +126,7 @@ pte_t __ref *pte_alloc_one_kernel(struct mm_struct *mm, if (likely(mem_init_done)) { pte = (pte_t *) __get_free_page(GFP_KERNEL); } else { - pte = (pte_t *) __va(memblock_alloc(PAGE_SIZE, PAGE_SIZE)); + pte = (pte_t *) __va(memblock_phys_alloc(PAGE_SIZE, PAGE_SIZE)); } if (pte) diff --git a/arch/powerpc/kernel/dt_cpu_ftrs.c b/arch/powerpc/kernel/dt_cpu_ftrs.c index f432054234a4..8be3721d9302 100644 --- a/arch/powerpc/kernel/dt_cpu_ftrs.c +++ b/arch/powerpc/kernel/dt_cpu_ftrs.c @@ -1008,9 +1008,7 @@ static int __init dt_cpu_ftrs_scan_callback(unsigned long node, const char /* Count and allocate space for cpu features */ of_scan_flat_dt_subnodes(node, count_cpufeatures_subnodes, &nr_dt_cpu_features); - dt_cpu_features = __va( - memblock_alloc(sizeof(struct dt_cpu_feature)* - nr_dt_cpu_features, PAGE_SIZE)); + dt_cpu_features = __va(memblock_phys_alloc(sizeof(struct dt_cpu_feature) * nr_dt_cpu_features, PAGE_SIZE)); cpufeatures_setup_start(isa); diff --git a/arch/powerpc/kernel/paca.c b/arch/powerpc/kernel/paca.c index 0ee3e6d50f28..f331a0054b3a 100644 --- a/arch/powerpc/kernel/paca.c +++ b/arch/powerpc/kernel/paca.c @@ -198,7 +198,7 @@ void __init allocate_paca_ptrs(void) paca_nr_cpu_ids = nr_cpu_ids; paca_ptrs_size = sizeof(struct paca_struct *) * nr_cpu_ids; - paca_ptrs = __va(memblock_alloc(paca_ptrs_size, 0)); + paca_ptrs = __va(memblock_phys_alloc(paca_ptrs_size, 0)); memset(paca_ptrs, 0x88, paca_ptrs_size); } diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c index c4d7078e5295..fe758cedb93f 100644 --- a/arch/powerpc/kernel/prom.c +++ b/arch/powerpc/kernel/prom.c @@ -126,7 +126,7 @@ static void __init move_device_tree(void) if ((memory_limit && (start + size) > PHYSICAL_START + memory_limit) || overlaps_crashkernel(start, size) || overlaps_initrd(start, size)) { - p = __va(memblock_alloc(size, PAGE_SIZE)); + p = __va(memblock_phys_alloc(size, PAGE_SIZE)); memcpy(p, initial_boot_params, size); initial_boot_params = p; DBG("Moved device tree to 0x%p\n", p); diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c index 9ca9db707bcb..2b56d1f30387 100644 --- a/arch/powerpc/kernel/setup-common.c +++ b/arch/powerpc/kernel/setup-common.c @@ -460,8 +460,7 @@ void __init smp_setup_cpu_maps(void) DBG("smp_setup_cpu_maps()\n"); - cpu_to_phys_id = __va(memblock_alloc(nr_cpu_ids * sizeof(u32), - __alignof__(u32))); + cpu_to_phys_id = __va(memblock_phys_alloc(nr_cpu_ids * sizeof(u32), __alignof__(u32))); memset(cpu_to_phys_id, 0, nr_cpu_ids * sizeof(u32)); for_each_node_by_type(dn, "cpu") { diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c index 8c507be12c3c..81909600013a 100644 --- a/arch/powerpc/kernel/setup_32.c +++ b/arch/powerpc/kernel/setup_32.c @@ -206,9 +206,9 @@ void __init irqstack_early_init(void) * as the memblock is limited to lowmem by default */ for_each_possible_cpu(i) { softirq_ctx[i] = (struct thread_info *) - __va(memblock_alloc(THREAD_SIZE, THREAD_SIZE)); + __va(memblock_phys_alloc(THREAD_SIZE, THREAD_SIZE)); hardirq_ctx[i] = (struct thread_info *) - __va(memblock_alloc(THREAD_SIZE, THREAD_SIZE)); + __va(memblock_phys_alloc(THREAD_SIZE, THREAD_SIZE)); } } @@ -227,12 +227,12 @@ void __init exc_lvl_early_init(void) #endif critirq_ctx[hw_cpu] = (struct thread_info *) - __va(memblock_alloc(THREAD_SIZE, THREAD_SIZE)); + __va(memblock_phys_alloc(THREAD_SIZE, THREAD_SIZE)); #ifdef CONFIG_BOOKE dbgirq_ctx[hw_cpu] = (struct thread_info *) - __va(memblock_alloc(THREAD_SIZE, THREAD_SIZE)); + __va(memblock_phys_alloc(THREAD_SIZE, THREAD_SIZE)); mcheckirq_ctx[hw_cpu] = (struct thread_info *) - __va(memblock_alloc(THREAD_SIZE, THREAD_SIZE)); + __va(memblock_phys_alloc(THREAD_SIZE, THREAD_SIZE)); #endif } } diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c index 693ae1c1acba..f04f15f9d232 100644 --- a/arch/powerpc/mm/numa.c +++ b/arch/powerpc/mm/numa.c @@ -788,7 +788,7 @@ static void __init setup_node_data(int nid, u64 start_pfn, u64 end_pfn) void *nd; int tnid; - nd_pa = memblock_alloc_try_nid(nd_size, SMP_CACHE_BYTES, nid); + nd_pa = memblock_phys_alloc_try_nid(nd_size, SMP_CACHE_BYTES, nid); nd = __va(nd_pa); /* report and initialize */ diff --git a/arch/powerpc/mm/pgtable_32.c b/arch/powerpc/mm/pgtable_32.c index 5877f5aa8f5d..bda3c6f1bd32 100644 --- a/arch/powerpc/mm/pgtable_32.c +++ b/arch/powerpc/mm/pgtable_32.c @@ -50,7 +50,7 @@ __ref pte_t *pte_alloc_one_kernel(struct mm_struct *mm, unsigned long address) if (slab_is_available()) { pte = (pte_t *)__get_free_page(GFP_KERNEL|__GFP_ZERO); } else { - pte = __va(memblock_alloc(PAGE_SIZE, PAGE_SIZE)); + pte = __va(memblock_phys_alloc(PAGE_SIZE, PAGE_SIZE)); if (pte) clear_page(pte); } diff --git a/arch/powerpc/mm/ppc_mmu_32.c b/arch/powerpc/mm/ppc_mmu_32.c index 38a793bfca37..f6f575bae3bc 100644 --- a/arch/powerpc/mm/ppc_mmu_32.c +++ b/arch/powerpc/mm/ppc_mmu_32.c @@ -224,7 +224,7 @@ void __init MMU_init_hw(void) * Find some memory for the hash table. */ if ( ppc_md.progress ) ppc_md.progress("hash:find piece", 0x322); - Hash = __va(memblock_alloc(Hash_size, Hash_size)); + Hash = __va(memblock_phys_alloc(Hash_size, Hash_size)); memset(Hash, 0, Hash_size); _SDR1 = __pa(Hash) | SDR1_LOW_BITS; diff --git a/arch/powerpc/platforms/pasemi/iommu.c b/arch/powerpc/platforms/pasemi/iommu.c index f06c83f321e6..f2971522fb4a 100644 --- a/arch/powerpc/platforms/pasemi/iommu.c +++ b/arch/powerpc/platforms/pasemi/iommu.c @@ -213,7 +213,7 @@ static int __init iob_init(struct device_node *dn) pr_info("IOBMAP L2 allocated at: %p\n", iob_l2_base); /* Allocate a spare page to map all invalid IOTLB pages. */ - tmp = memblock_alloc(IOBMAP_PAGE_SIZE, IOBMAP_PAGE_SIZE); + tmp = memblock_phys_alloc(IOBMAP_PAGE_SIZE, IOBMAP_PAGE_SIZE); if (!tmp) panic("IOBMAP: Cannot allocate spare page!"); /* Empty l1 is marked invalid */ diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c index a4641515956f..beed86f4224b 100644 --- a/arch/powerpc/platforms/powernv/opal.c +++ b/arch/powerpc/platforms/powernv/opal.c @@ -171,7 +171,7 @@ int __init early_init_dt_scan_recoverable_ranges(unsigned long node, /* * Allocate a buffer to hold the MC recoverable ranges. */ - mc_recoverable_range =__va(memblock_alloc(size, __alignof__(u64))); + mc_recoverable_range =__va(memblock_phys_alloc(size, __alignof__(u64))); memset(mc_recoverable_range, 0, size); for (i = 0; i < mc_recoverable_range_len; i++) { diff --git a/arch/powerpc/sysdev/dart_iommu.c b/arch/powerpc/sysdev/dart_iommu.c index 5ca3e22d0512..a5b40d1460f1 100644 --- a/arch/powerpc/sysdev/dart_iommu.c +++ b/arch/powerpc/sysdev/dart_iommu.c @@ -261,7 +261,7 @@ static void allocate_dart(void) * that to work around what looks like a problem with the HT bridge * prefetching into invalid pages and corrupting data */ - tmp = memblock_alloc(DART_PAGE_SIZE, DART_PAGE_SIZE); + tmp = memblock_phys_alloc(DART_PAGE_SIZE, DART_PAGE_SIZE); dart_emptyval = DARTMAP_VALID | ((tmp >> DART_PAGE_SHIFT) & DARTMAP_RPNMASK); diff --git a/arch/s390/kernel/crash_dump.c b/arch/s390/kernel/crash_dump.c index 376f6b6dfb3c..d17566a8c76f 100644 --- a/arch/s390/kernel/crash_dump.c +++ b/arch/s390/kernel/crash_dump.c @@ -61,7 +61,7 @@ struct save_area * __init save_area_alloc(bool is_boot_cpu) { struct save_area *sa; - sa = (void *) memblock_alloc(sizeof(*sa), 8); + sa = (void *) memblock_phys_alloc(sizeof(*sa), 8); if (is_boot_cpu) list_add(&sa->list, &dump_save_areas); else diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c index a2e952b66248..204ccfa54bf3 100644 --- a/arch/s390/kernel/setup.c +++ b/arch/s390/kernel/setup.c @@ -967,7 +967,8 @@ static void __init setup_randomness(void) { struct sysinfo_3_2_2 *vmms; - vmms = (struct sysinfo_3_2_2 *) memblock_alloc(PAGE_SIZE, PAGE_SIZE); + vmms = (struct sysinfo_3_2_2 *) memblock_phys_alloc(PAGE_SIZE, + PAGE_SIZE); if (stsi(vmms, 3, 2, 2) == 0 && vmms->count) add_device_randomness(&vmms->vm, sizeof(vmms->vm[0]) * vmms->count); memblock_free((unsigned long) vmms, PAGE_SIZE); diff --git a/arch/s390/mm/vmem.c b/arch/s390/mm/vmem.c index db55561c5981..04638b0b9ef1 100644 --- a/arch/s390/mm/vmem.c +++ b/arch/s390/mm/vmem.c @@ -36,7 +36,7 @@ static void __ref *vmem_alloc_pages(unsigned int order) if (slab_is_available()) return (void *)__get_free_pages(GFP_KERNEL, order); - return (void *) memblock_alloc(size, size); + return (void *) memblock_phys_alloc(size, size); } void *vmem_crst_alloc(unsigned long val) @@ -57,7 +57,7 @@ pte_t __ref *vmem_pte_alloc(void) if (slab_is_available()) pte = (pte_t *) page_table_alloc(&init_mm); else - pte = (pte_t *) memblock_alloc(size, size); + pte = (pte_t *) memblock_phys_alloc(size, size); if (!pte) return NULL; memset64((u64 *)pte, _PAGE_INVALID, PTRS_PER_PTE); diff --git a/arch/s390/numa/numa.c b/arch/s390/numa/numa.c index 5bd374491f94..297f5d8b0890 100644 --- a/arch/s390/numa/numa.c +++ b/arch/s390/numa/numa.c @@ -64,7 +64,7 @@ static __init pg_data_t *alloc_node_data(void) { pg_data_t *res; - res = (pg_data_t *) memblock_alloc(sizeof(pg_data_t), 8); + res = (pg_data_t *) memblock_phys_alloc(sizeof(pg_data_t), 8); memset(res, 0, sizeof(pg_data_t)); return res; } diff --git a/arch/sparc/kernel/mdesc.c b/arch/sparc/kernel/mdesc.c index 39a2503fa3e1..59131e72ee78 100644 --- a/arch/sparc/kernel/mdesc.c +++ b/arch/sparc/kernel/mdesc.c @@ -170,7 +170,7 @@ static struct mdesc_handle * __init mdesc_memblock_alloc(unsigned int mdesc_size mdesc_size); alloc_size = PAGE_ALIGN(handle_size); - paddr = memblock_alloc(alloc_size, PAGE_SIZE); + paddr = memblock_phys_alloc(alloc_size, PAGE_SIZE); hp = NULL; if (paddr) { diff --git a/arch/sparc/kernel/prom_64.c b/arch/sparc/kernel/prom_64.c index baeaeed64993..c37955d127fe 100644 --- a/arch/sparc/kernel/prom_64.c +++ b/arch/sparc/kernel/prom_64.c @@ -34,7 +34,7 @@ void * __init prom_early_alloc(unsigned long size) { - unsigned long paddr = memblock_alloc(size, SMP_CACHE_BYTES); + unsigned long paddr = memblock_phys_alloc(size, SMP_CACHE_BYTES); void *ret; if (!paddr) { diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c index 39822f611c01..b338f0440f6b 100644 --- a/arch/sparc/mm/init_64.c +++ b/arch/sparc/mm/init_64.c @@ -1092,7 +1092,8 @@ static void __init allocate_node_data(int nid) #ifdef CONFIG_NEED_MULTIPLE_NODES unsigned long paddr; - paddr = memblock_alloc_try_nid(sizeof(struct pglist_data), SMP_CACHE_BYTES, nid); + paddr = memblock_phys_alloc_try_nid(sizeof(struct pglist_data), + SMP_CACHE_BYTES, nid); if (!paddr) { prom_printf("Cannot allocate pglist_data for nid[%d]\n", nid); prom_halt(); @@ -1266,8 +1267,8 @@ static int __init grab_mlgroups(struct mdesc_handle *md) if (!count) return -ENOENT; - paddr = memblock_alloc(count * sizeof(struct mdesc_mlgroup), - SMP_CACHE_BYTES); + paddr = memblock_phys_alloc(count * sizeof(struct mdesc_mlgroup), + SMP_CACHE_BYTES); if (!paddr) return -ENOMEM; @@ -1307,8 +1308,8 @@ static int __init grab_mblocks(struct mdesc_handle *md) if (!count) return -ENOENT; - paddr = memblock_alloc(count * sizeof(struct mdesc_mblock), - SMP_CACHE_BYTES); + paddr = memblock_phys_alloc(count * sizeof(struct mdesc_mblock), + SMP_CACHE_BYTES); if (!paddr) return -ENOMEM; diff --git a/arch/unicore32/mm/mmu.c b/arch/unicore32/mm/mmu.c index 0c94b7b4514d..18b355a20f0b 100644 --- a/arch/unicore32/mm/mmu.c +++ b/arch/unicore32/mm/mmu.c @@ -144,7 +144,7 @@ static void __init build_mem_type_table(void) static void __init *early_alloc(unsigned long sz) { - void *ptr = __va(memblock_alloc(sz, sz)); + void *ptr = __va(memblock_phys_alloc(sz, sz)); memset(ptr, 0, sz); return ptr; } diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c index fa150855647c..16e37d712ffd 100644 --- a/arch/x86/mm/numa.c +++ b/arch/x86/mm/numa.c @@ -196,7 +196,7 @@ static void __init alloc_node_data(int nid) * Allocate node data. Try node-local memory and then any node. * Never allocate in DMA zone. */ - nd_pa = memblock_alloc_nid(nd_size, SMP_CACHE_BYTES, nid); + nd_pa = memblock_phys_alloc_nid(nd_size, SMP_CACHE_BYTES, nid); if (!nd_pa) { nd_pa = __memblock_alloc_base(nd_size, SMP_CACHE_BYTES, MEMBLOCK_ALLOC_ACCESSIBLE); diff --git a/drivers/firmware/efi/memmap.c b/drivers/firmware/efi/memmap.c index 5fc70520e04c..ef618bceb79a 100644 --- a/drivers/firmware/efi/memmap.c +++ b/drivers/firmware/efi/memmap.c @@ -15,7 +15,7 @@ static phys_addr_t __init __efi_memmap_alloc_early(unsigned long size) { - return memblock_alloc(size, 0); + return memblock_phys_alloc(size, 0); } static phys_addr_t __init __efi_memmap_alloc_late(unsigned long size) diff --git a/include/linux/memblock.h b/include/linux/memblock.h index 224d27363cca..9d46a7204975 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -300,10 +300,10 @@ static inline int memblock_get_region_node(const struct memblock_region *r) } #endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */ -phys_addr_t memblock_alloc_nid(phys_addr_t size, phys_addr_t align, int nid); -phys_addr_t memblock_alloc_try_nid(phys_addr_t size, phys_addr_t align, int nid); +phys_addr_t memblock_phys_alloc_nid(phys_addr_t size, phys_addr_t align, int nid); +phys_addr_t memblock_phys_alloc_try_nid(phys_addr_t size, phys_addr_t align, int nid); -phys_addr_t memblock_alloc(phys_addr_t size, phys_addr_t align); +phys_addr_t memblock_phys_alloc(phys_addr_t size, phys_addr_t align); /* * Set the allocation direction to bottom-up or top-down. diff --git a/mm/memblock.c b/mm/memblock.c index d6897fbe021f..20358374e8a8 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -1269,7 +1269,7 @@ phys_addr_t __init memblock_alloc_base_nid(phys_addr_t size, return memblock_alloc_range_nid(size, align, 0, max_addr, nid, flags); } -phys_addr_t __init memblock_alloc_nid(phys_addr_t size, phys_addr_t align, int nid) +phys_addr_t __init memblock_phys_alloc_nid(phys_addr_t size, phys_addr_t align, int nid) { enum memblock_flags flags = choose_memblock_flags(); phys_addr_t ret; @@ -1304,14 +1304,14 @@ phys_addr_t __init memblock_alloc_base(phys_addr_t size, phys_addr_t align, phys return alloc; } -phys_addr_t __init memblock_alloc(phys_addr_t size, phys_addr_t align) +phys_addr_t __init memblock_phys_alloc(phys_addr_t size, phys_addr_t align) { return memblock_alloc_base(size, align, MEMBLOCK_ALLOC_ACCESSIBLE); } -phys_addr_t __init memblock_alloc_try_nid(phys_addr_t size, phys_addr_t align, int nid) +phys_addr_t __init memblock_phys_alloc_try_nid(phys_addr_t size, phys_addr_t align, int nid) { - phys_addr_t res = memblock_alloc_nid(size, align, nid); + phys_addr_t res = memblock_phys_alloc_nid(size, align, nid); if (res) return res; -- cgit v1.2.3 From eb31d559f1e8390195372cd51cfb198da8bc84b9 Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Tue, 30 Oct 2018 15:08:04 -0700 Subject: memblock: remove _virt from APIs returning virtual address The conversion is done using sed -i 's@memblock_virt_alloc@memblock_alloc@g' \ $(git grep -l memblock_virt_alloc) Link: http://lkml.kernel.org/r/1536927045-23536-8-git-send-email-rppt@linux.vnet.ibm.com Signed-off-by: Mike Rapoport Cc: Catalin Marinas Cc: Chris Zankel Cc: "David S. Miller" Cc: Geert Uytterhoeven Cc: Greentime Hu Cc: Greg Kroah-Hartman Cc: Guan Xuetao Cc: Ingo Molnar Cc: "James E.J. Bottomley" Cc: Jonas Bonn Cc: Jonathan Corbet Cc: Ley Foon Tan Cc: Mark Salter Cc: Martin Schwidefsky Cc: Matt Turner Cc: Michael Ellerman Cc: Michal Hocko Cc: Michal Simek Cc: Palmer Dabbelt Cc: Paul Burton Cc: Richard Kuo Cc: Richard Weinberger Cc: Rich Felker Cc: Russell King Cc: Serge Semin Cc: Thomas Gleixner Cc: Tony Luck Cc: Vineet Gupta Cc: Yoshinori Sato Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/arm/kernel/setup.c | 4 ++-- arch/arm/mach-omap2/omap_hwmod.c | 6 ++--- arch/arm64/mm/kasan_init.c | 2 +- arch/arm64/mm/numa.c | 2 +- arch/mips/kernel/setup.c | 2 +- arch/powerpc/kernel/pci_32.c | 2 +- arch/powerpc/lib/alloc.c | 2 +- arch/powerpc/mm/mmu_context_nohash.c | 6 ++--- arch/powerpc/platforms/powermac/nvram.c | 2 +- arch/powerpc/platforms/powernv/pci-ioda.c | 6 ++--- arch/powerpc/platforms/ps3/setup.c | 2 +- arch/powerpc/sysdev/msi_bitmap.c | 2 +- arch/s390/kernel/setup.c | 8 +++---- arch/s390/kernel/smp.c | 2 +- arch/s390/kernel/topology.c | 4 ++-- arch/s390/numa/mode_emu.c | 2 +- arch/s390/numa/toptree.c | 2 +- arch/x86/mm/kasan_init_64.c | 4 ++-- arch/xtensa/mm/kasan_init.c | 2 +- drivers/clk/ti/clk.c | 2 +- drivers/firmware/memmap.c | 2 +- drivers/of/fdt.c | 2 +- drivers/of/unittest.c | 2 +- include/linux/bootmem.h | 38 +++++++++++++++---------------- init/main.c | 6 ++--- kernel/dma/swiotlb.c | 6 ++--- kernel/power/snapshot.c | 2 +- kernel/printk/printk.c | 4 ++-- lib/cpumask.c | 2 +- mm/hugetlb.c | 2 +- mm/kasan/kasan_init.c | 2 +- mm/memblock.c | 26 ++++++++++----------- mm/page_alloc.c | 8 +++---- mm/page_ext.c | 2 +- mm/percpu.c | 28 +++++++++++------------ mm/sparse-vmemmap.c | 2 +- mm/sparse.c | 12 +++++----- 37 files changed, 105 insertions(+), 105 deletions(-) (limited to 'mm') diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c index 4c249cb261f3..39e6090d23ac 100644 --- a/arch/arm/kernel/setup.c +++ b/arch/arm/kernel/setup.c @@ -857,7 +857,7 @@ static void __init request_standard_resources(const struct machine_desc *mdesc) */ boot_alias_start = phys_to_idmap(start); if (arm_has_idmap_alias() && boot_alias_start != IDMAP_INVALID_ADDR) { - res = memblock_virt_alloc(sizeof(*res), 0); + res = memblock_alloc(sizeof(*res), 0); res->name = "System RAM (boot alias)"; res->start = boot_alias_start; res->end = phys_to_idmap(end); @@ -865,7 +865,7 @@ static void __init request_standard_resources(const struct machine_desc *mdesc) request_resource(&iomem_resource, res); } - res = memblock_virt_alloc(sizeof(*res), 0); + res = memblock_alloc(sizeof(*res), 0); res->name = "System RAM"; res->start = start; res->end = end; diff --git a/arch/arm/mach-omap2/omap_hwmod.c b/arch/arm/mach-omap2/omap_hwmod.c index 56a1fe90d394..1f9b34a7eccd 100644 --- a/arch/arm/mach-omap2/omap_hwmod.c +++ b/arch/arm/mach-omap2/omap_hwmod.c @@ -726,7 +726,7 @@ static int __init _setup_clkctrl_provider(struct device_node *np) u64 size; int i; - provider = memblock_virt_alloc(sizeof(*provider), 0); + provider = memblock_alloc(sizeof(*provider), 0); if (!provider) return -ENOMEM; @@ -736,12 +736,12 @@ static int __init _setup_clkctrl_provider(struct device_node *np) of_property_count_elems_of_size(np, "reg", sizeof(u32)) / 2; provider->addr = - memblock_virt_alloc(sizeof(void *) * provider->num_addrs, 0); + memblock_alloc(sizeof(void *) * provider->num_addrs, 0); if (!provider->addr) return -ENOMEM; provider->size = - memblock_virt_alloc(sizeof(u32) * provider->num_addrs, 0); + memblock_alloc(sizeof(u32) * provider->num_addrs, 0); if (!provider->size) return -ENOMEM; diff --git a/arch/arm64/mm/kasan_init.c b/arch/arm64/mm/kasan_init.c index fccb1a6f8c6f..6a65a2912d36 100644 --- a/arch/arm64/mm/kasan_init.c +++ b/arch/arm64/mm/kasan_init.c @@ -38,7 +38,7 @@ static pgd_t tmp_pg_dir[PTRS_PER_PGD] __initdata __aligned(PGD_SIZE); static phys_addr_t __init kasan_alloc_zeroed_page(int node) { - void *p = memblock_virt_alloc_try_nid(PAGE_SIZE, PAGE_SIZE, + void *p = memblock_alloc_try_nid(PAGE_SIZE, PAGE_SIZE, __pa(MAX_DMA_ADDRESS), MEMBLOCK_ALLOC_ACCESSIBLE, node); return __pa(p); diff --git a/arch/arm64/mm/numa.c b/arch/arm64/mm/numa.c index c7fb34efd23e..0bff116c07a8 100644 --- a/arch/arm64/mm/numa.c +++ b/arch/arm64/mm/numa.c @@ -168,7 +168,7 @@ static void * __init pcpu_fc_alloc(unsigned int cpu, size_t size, { int nid = early_cpu_to_node(cpu); - return memblock_virt_alloc_try_nid(size, align, + return memblock_alloc_try_nid(size, align, __pa(MAX_DMA_ADDRESS), MEMBLOCK_ALLOC_ACCESSIBLE, nid); } diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c index 01a5ff4c41ff..0c997645e8f0 100644 --- a/arch/mips/kernel/setup.c +++ b/arch/mips/kernel/setup.c @@ -859,7 +859,7 @@ static void __init arch_mem_init(char **cmdline_p) * Prevent memblock from allocating high memory. * This cannot be done before max_low_pfn is detected, so up * to this point is possible to only reserve physical memory - * with memblock_reserve; memblock_virt_alloc* can be used + * with memblock_reserve; memblock_alloc* can be used * only after this point */ memblock_set_current_limit(PFN_PHYS(max_low_pfn)); diff --git a/arch/powerpc/kernel/pci_32.c b/arch/powerpc/kernel/pci_32.c index 4da8ed576229..d39ec3a4550a 100644 --- a/arch/powerpc/kernel/pci_32.c +++ b/arch/powerpc/kernel/pci_32.c @@ -203,7 +203,7 @@ pci_create_OF_bus_map(void) struct property* of_prop; struct device_node *dn; - of_prop = memblock_virt_alloc(sizeof(struct property) + 256, 0); + of_prop = memblock_alloc(sizeof(struct property) + 256, 0); dn = of_find_node_by_path("/"); if (dn) { memset(of_prop, -1, sizeof(struct property) + 256); diff --git a/arch/powerpc/lib/alloc.c b/arch/powerpc/lib/alloc.c index 06796dec01ea..bf87d6e13369 100644 --- a/arch/powerpc/lib/alloc.c +++ b/arch/powerpc/lib/alloc.c @@ -14,7 +14,7 @@ void * __ref zalloc_maybe_bootmem(size_t size, gfp_t mask) if (slab_is_available()) p = kzalloc(size, mask); else { - p = memblock_virt_alloc(size, 0); + p = memblock_alloc(size, 0); } return p; } diff --git a/arch/powerpc/mm/mmu_context_nohash.c b/arch/powerpc/mm/mmu_context_nohash.c index 4d80239ef83c..954f1986af4d 100644 --- a/arch/powerpc/mm/mmu_context_nohash.c +++ b/arch/powerpc/mm/mmu_context_nohash.c @@ -461,10 +461,10 @@ void __init mmu_context_init(void) /* * Allocate the maps used by context management */ - context_map = memblock_virt_alloc(CTX_MAP_SIZE, 0); - context_mm = memblock_virt_alloc(sizeof(void *) * (LAST_CONTEXT + 1), 0); + context_map = memblock_alloc(CTX_MAP_SIZE, 0); + context_mm = memblock_alloc(sizeof(void *) * (LAST_CONTEXT + 1), 0); #ifdef CONFIG_SMP - stale_map[boot_cpuid] = memblock_virt_alloc(CTX_MAP_SIZE, 0); + stale_map[boot_cpuid] = memblock_alloc(CTX_MAP_SIZE, 0); cpuhp_setup_state_nocalls(CPUHP_POWERPC_MMU_CTX_PREPARE, "powerpc/mmu/ctx:prepare", diff --git a/arch/powerpc/platforms/powermac/nvram.c b/arch/powerpc/platforms/powermac/nvram.c index 60b03a1703d1..f45b369177a4 100644 --- a/arch/powerpc/platforms/powermac/nvram.c +++ b/arch/powerpc/platforms/powermac/nvram.c @@ -513,7 +513,7 @@ static int __init core99_nvram_setup(struct device_node *dp, unsigned long addr) printk(KERN_ERR "nvram: no address\n"); return -EINVAL; } - nvram_image = memblock_virt_alloc(NVRAM_SIZE, 0); + nvram_image = memblock_alloc(NVRAM_SIZE, 0); nvram_data = ioremap(addr, NVRAM_SIZE*2); nvram_naddrs = 1; /* Make sure we get the correct case */ diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c index cde710297a4e..23a67b545b70 100644 --- a/arch/powerpc/platforms/powernv/pci-ioda.c +++ b/arch/powerpc/platforms/powernv/pci-ioda.c @@ -3770,7 +3770,7 @@ static void __init pnv_pci_init_ioda_phb(struct device_node *np, phb_id = be64_to_cpup(prop64); pr_debug(" PHB-ID : 0x%016llx\n", phb_id); - phb = memblock_virt_alloc(sizeof(*phb), 0); + phb = memblock_alloc(sizeof(*phb), 0); /* Allocate PCI controller */ phb->hose = hose = pcibios_alloc_controller(np); @@ -3816,7 +3816,7 @@ static void __init pnv_pci_init_ioda_phb(struct device_node *np, else phb->diag_data_size = PNV_PCI_DIAG_BUF_SIZE; - phb->diag_data = memblock_virt_alloc(phb->diag_data_size, 0); + phb->diag_data = memblock_alloc(phb->diag_data_size, 0); /* Parse 32-bit and IO ranges (if any) */ pci_process_bridge_OF_ranges(hose, np, !hose->global_number); @@ -3875,7 +3875,7 @@ static void __init pnv_pci_init_ioda_phb(struct device_node *np, } pemap_off = size; size += phb->ioda.total_pe_num * sizeof(struct pnv_ioda_pe); - aux = memblock_virt_alloc(size, 0); + aux = memblock_alloc(size, 0); phb->ioda.pe_alloc = aux; phb->ioda.m64_segmap = aux + m64map_off; phb->ioda.m32_segmap = aux + m32map_off; diff --git a/arch/powerpc/platforms/ps3/setup.c b/arch/powerpc/platforms/ps3/setup.c index 77a37520068d..12519857a33c 100644 --- a/arch/powerpc/platforms/ps3/setup.c +++ b/arch/powerpc/platforms/ps3/setup.c @@ -126,7 +126,7 @@ static void __init prealloc(struct ps3_prealloc *p) if (!p->size) return; - p->address = memblock_virt_alloc(p->size, p->align); + p->address = memblock_alloc(p->size, p->align); printk(KERN_INFO "%s: %lu bytes at %p\n", p->name, p->size, p->address); diff --git a/arch/powerpc/sysdev/msi_bitmap.c b/arch/powerpc/sysdev/msi_bitmap.c index e64a411d1a00..349a9ff6ca5b 100644 --- a/arch/powerpc/sysdev/msi_bitmap.c +++ b/arch/powerpc/sysdev/msi_bitmap.c @@ -128,7 +128,7 @@ int __ref msi_bitmap_alloc(struct msi_bitmap *bmp, unsigned int irq_count, if (bmp->bitmap_from_slab) bmp->bitmap = kzalloc(size, GFP_KERNEL); else { - bmp->bitmap = memblock_virt_alloc(size, 0); + bmp->bitmap = memblock_alloc(size, 0); /* the bitmap won't be freed from memblock allocator */ kmemleak_not_leak(bmp->bitmap); } diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c index 204ccfa54bf3..781c1053a773 100644 --- a/arch/s390/kernel/setup.c +++ b/arch/s390/kernel/setup.c @@ -378,7 +378,7 @@ static void __init setup_lowcore(void) * Setup lowcore for boot cpu */ BUILD_BUG_ON(sizeof(struct lowcore) != LC_PAGES * PAGE_SIZE); - lc = memblock_virt_alloc_low(sizeof(*lc), sizeof(*lc)); + lc = memblock_alloc_low(sizeof(*lc), sizeof(*lc)); lc->restart_psw.mask = PSW_KERNEL_BITS; lc->restart_psw.addr = (unsigned long) restart_int_handler; lc->external_new_psw.mask = PSW_KERNEL_BITS | @@ -422,7 +422,7 @@ static void __init setup_lowcore(void) * Allocate the global restart stack which is the same for * all CPUs in cast *one* of them does a PSW restart. */ - restart_stack = memblock_virt_alloc(THREAD_SIZE, THREAD_SIZE); + restart_stack = memblock_alloc(THREAD_SIZE, THREAD_SIZE); restart_stack += STACK_INIT_OFFSET; /* @@ -488,7 +488,7 @@ static void __init setup_resources(void) bss_resource.end = (unsigned long) __bss_stop - 1; for_each_memblock(memory, reg) { - res = memblock_virt_alloc(sizeof(*res), 8); + res = memblock_alloc(sizeof(*res), 8); res->flags = IORESOURCE_BUSY | IORESOURCE_SYSTEM_RAM; res->name = "System RAM"; @@ -502,7 +502,7 @@ static void __init setup_resources(void) std_res->start > res->end) continue; if (std_res->end > res->end) { - sub_res = memblock_virt_alloc(sizeof(*sub_res), 8); + sub_res = memblock_alloc(sizeof(*sub_res), 8); *sub_res = *std_res; sub_res->end = res->end; std_res->start = res->end + 1; diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c index 1b3188f57b58..44f9a7d6450b 100644 --- a/arch/s390/kernel/smp.c +++ b/arch/s390/kernel/smp.c @@ -761,7 +761,7 @@ void __init smp_detect_cpus(void) u16 address; /* Get CPU information */ - info = memblock_virt_alloc(sizeof(*info), 8); + info = memblock_alloc(sizeof(*info), 8); smp_get_core_info(info, 1); /* Find boot CPU type */ if (sclp.has_core_type) { diff --git a/arch/s390/kernel/topology.c b/arch/s390/kernel/topology.c index e8184a15578a..799a91882a76 100644 --- a/arch/s390/kernel/topology.c +++ b/arch/s390/kernel/topology.c @@ -519,7 +519,7 @@ static void __init alloc_masks(struct sysinfo_15_1_x *info, nr_masks *= info->mag[TOPOLOGY_NR_MAG - offset - 1 - i]; nr_masks = max(nr_masks, 1); for (i = 0; i < nr_masks; i++) { - mask->next = memblock_virt_alloc(sizeof(*mask->next), 8); + mask->next = memblock_alloc(sizeof(*mask->next), 8); mask = mask->next; } } @@ -537,7 +537,7 @@ void __init topology_init_early(void) } if (!MACHINE_HAS_TOPOLOGY) goto out; - tl_info = memblock_virt_alloc(PAGE_SIZE, PAGE_SIZE); + tl_info = memblock_alloc(PAGE_SIZE, PAGE_SIZE); info = tl_info; store_topology(info); pr_info("The CPU configuration topology of the machine is: %d %d %d %d %d %d / %d\n", diff --git a/arch/s390/numa/mode_emu.c b/arch/s390/numa/mode_emu.c index 83b222c57609..5a381fc8e958 100644 --- a/arch/s390/numa/mode_emu.c +++ b/arch/s390/numa/mode_emu.c @@ -313,7 +313,7 @@ static void __ref create_core_to_node_map(void) { int i; - emu_cores = memblock_virt_alloc(sizeof(*emu_cores), 8); + emu_cores = memblock_alloc(sizeof(*emu_cores), 8); for (i = 0; i < ARRAY_SIZE(emu_cores->to_node_id); i++) emu_cores->to_node_id[i] = NODE_ID_FREE; } diff --git a/arch/s390/numa/toptree.c b/arch/s390/numa/toptree.c index 21d1e8a1546d..7f61cc3fd4d1 100644 --- a/arch/s390/numa/toptree.c +++ b/arch/s390/numa/toptree.c @@ -34,7 +34,7 @@ struct toptree __ref *toptree_alloc(int level, int id) if (slab_is_available()) res = kzalloc(sizeof(*res), GFP_KERNEL); else - res = memblock_virt_alloc(sizeof(*res), 8); + res = memblock_alloc(sizeof(*res), 8); if (!res) return res; diff --git a/arch/x86/mm/kasan_init_64.c b/arch/x86/mm/kasan_init_64.c index e3e77527f8df..77b857cb036f 100644 --- a/arch/x86/mm/kasan_init_64.c +++ b/arch/x86/mm/kasan_init_64.c @@ -28,10 +28,10 @@ static p4d_t tmp_p4d_table[MAX_PTRS_PER_P4D] __initdata __aligned(PAGE_SIZE); static __init void *early_alloc(size_t size, int nid, bool panic) { if (panic) - return memblock_virt_alloc_try_nid(size, size, + return memblock_alloc_try_nid(size, size, __pa(MAX_DMA_ADDRESS), BOOTMEM_ALLOC_ACCESSIBLE, nid); else - return memblock_virt_alloc_try_nid_nopanic(size, size, + return memblock_alloc_try_nid_nopanic(size, size, __pa(MAX_DMA_ADDRESS), BOOTMEM_ALLOC_ACCESSIBLE, nid); } diff --git a/arch/xtensa/mm/kasan_init.c b/arch/xtensa/mm/kasan_init.c index 6b532b6bd785..1a30a258ccd0 100644 --- a/arch/xtensa/mm/kasan_init.c +++ b/arch/xtensa/mm/kasan_init.c @@ -43,7 +43,7 @@ static void __init populate(void *start, void *end) unsigned long vaddr = (unsigned long)start; pgd_t *pgd = pgd_offset_k(vaddr); pmd_t *pmd = pmd_offset(pgd, vaddr); - pte_t *pte = memblock_virt_alloc(n_pages * sizeof(pte_t), PAGE_SIZE); + pte_t *pte = memblock_alloc(n_pages * sizeof(pte_t), PAGE_SIZE); pr_debug("%s: %p - %p\n", __func__, start, end); diff --git a/drivers/clk/ti/clk.c b/drivers/clk/ti/clk.c index 7d22e1af2247..5c54d3734daf 100644 --- a/drivers/clk/ti/clk.c +++ b/drivers/clk/ti/clk.c @@ -342,7 +342,7 @@ void __init omap2_clk_legacy_provider_init(int index, void __iomem *mem) { struct clk_iomap *io; - io = memblock_virt_alloc(sizeof(*io), 0); + io = memblock_alloc(sizeof(*io), 0); io->mem = mem; diff --git a/drivers/firmware/memmap.c b/drivers/firmware/memmap.c index 5de3ed29282c..03cead6d5f97 100644 --- a/drivers/firmware/memmap.c +++ b/drivers/firmware/memmap.c @@ -333,7 +333,7 @@ int __init firmware_map_add_early(u64 start, u64 end, const char *type) { struct firmware_map_entry *entry; - entry = memblock_virt_alloc(sizeof(struct firmware_map_entry), 0); + entry = memblock_alloc(sizeof(struct firmware_map_entry), 0); if (WARN_ON(!entry)) return -ENOMEM; diff --git a/drivers/of/fdt.c b/drivers/of/fdt.c index 4f915cea6f75..ffe62a7ae19b 100644 --- a/drivers/of/fdt.c +++ b/drivers/of/fdt.c @@ -1179,7 +1179,7 @@ int __init __weak early_init_dt_reserve_memory_arch(phys_addr_t base, static void * __init early_init_dt_alloc_memory_arch(u64 size, u64 align) { - return memblock_virt_alloc(size, align); + return memblock_alloc(size, align); } bool __init early_init_dt_verify(void *params) diff --git a/drivers/of/unittest.c b/drivers/of/unittest.c index a3a6866765f2..01e23b85e798 100644 --- a/drivers/of/unittest.c +++ b/drivers/of/unittest.c @@ -2192,7 +2192,7 @@ static struct device_node *overlay_base_root; static void * __init dt_alloc_memory(u64 size, u64 align) { - return memblock_virt_alloc(size, align); + return memblock_alloc(size, align); } /* diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h index b74bafd110b9..7d91f0f5ee44 100644 --- a/include/linux/bootmem.h +++ b/include/linux/bootmem.h @@ -95,78 +95,78 @@ extern void *__alloc_bootmem_low(unsigned long size, #define BOOTMEM_ALLOC_ANYWHERE (~(phys_addr_t)0) /* FIXME: Move to memblock.h at a point where we remove nobootmem.c */ -void *memblock_virt_alloc_try_nid_raw(phys_addr_t size, phys_addr_t align, +void *memblock_alloc_try_nid_raw(phys_addr_t size, phys_addr_t align, phys_addr_t min_addr, phys_addr_t max_addr, int nid); -void *memblock_virt_alloc_try_nid_nopanic(phys_addr_t size, +void *memblock_alloc_try_nid_nopanic(phys_addr_t size, phys_addr_t align, phys_addr_t min_addr, phys_addr_t max_addr, int nid); -void *memblock_virt_alloc_try_nid(phys_addr_t size, phys_addr_t align, +void *memblock_alloc_try_nid(phys_addr_t size, phys_addr_t align, phys_addr_t min_addr, phys_addr_t max_addr, int nid); void __memblock_free_early(phys_addr_t base, phys_addr_t size); void __memblock_free_late(phys_addr_t base, phys_addr_t size); -static inline void * __init memblock_virt_alloc( +static inline void * __init memblock_alloc( phys_addr_t size, phys_addr_t align) { - return memblock_virt_alloc_try_nid(size, align, BOOTMEM_LOW_LIMIT, + return memblock_alloc_try_nid(size, align, BOOTMEM_LOW_LIMIT, BOOTMEM_ALLOC_ACCESSIBLE, NUMA_NO_NODE); } -static inline void * __init memblock_virt_alloc_raw( +static inline void * __init memblock_alloc_raw( phys_addr_t size, phys_addr_t align) { - return memblock_virt_alloc_try_nid_raw(size, align, BOOTMEM_LOW_LIMIT, + return memblock_alloc_try_nid_raw(size, align, BOOTMEM_LOW_LIMIT, BOOTMEM_ALLOC_ACCESSIBLE, NUMA_NO_NODE); } -static inline void * __init memblock_virt_alloc_nopanic( +static inline void * __init memblock_alloc_nopanic( phys_addr_t size, phys_addr_t align) { - return memblock_virt_alloc_try_nid_nopanic(size, align, + return memblock_alloc_try_nid_nopanic(size, align, BOOTMEM_LOW_LIMIT, BOOTMEM_ALLOC_ACCESSIBLE, NUMA_NO_NODE); } -static inline void * __init memblock_virt_alloc_low( +static inline void * __init memblock_alloc_low( phys_addr_t size, phys_addr_t align) { - return memblock_virt_alloc_try_nid(size, align, + return memblock_alloc_try_nid(size, align, BOOTMEM_LOW_LIMIT, ARCH_LOW_ADDRESS_LIMIT, NUMA_NO_NODE); } -static inline void * __init memblock_virt_alloc_low_nopanic( +static inline void * __init memblock_alloc_low_nopanic( phys_addr_t size, phys_addr_t align) { - return memblock_virt_alloc_try_nid_nopanic(size, align, + return memblock_alloc_try_nid_nopanic(size, align, BOOTMEM_LOW_LIMIT, ARCH_LOW_ADDRESS_LIMIT, NUMA_NO_NODE); } -static inline void * __init memblock_virt_alloc_from_nopanic( +static inline void * __init memblock_alloc_from_nopanic( phys_addr_t size, phys_addr_t align, phys_addr_t min_addr) { - return memblock_virt_alloc_try_nid_nopanic(size, align, min_addr, + return memblock_alloc_try_nid_nopanic(size, align, min_addr, BOOTMEM_ALLOC_ACCESSIBLE, NUMA_NO_NODE); } -static inline void * __init memblock_virt_alloc_node( +static inline void * __init memblock_alloc_node( phys_addr_t size, int nid) { - return memblock_virt_alloc_try_nid(size, 0, BOOTMEM_LOW_LIMIT, + return memblock_alloc_try_nid(size, 0, BOOTMEM_LOW_LIMIT, BOOTMEM_ALLOC_ACCESSIBLE, nid); } -static inline void * __init memblock_virt_alloc_node_nopanic( +static inline void * __init memblock_alloc_node_nopanic( phys_addr_t size, int nid) { - return memblock_virt_alloc_try_nid_nopanic(size, 0, BOOTMEM_LOW_LIMIT, + return memblock_alloc_try_nid_nopanic(size, 0, BOOTMEM_LOW_LIMIT, BOOTMEM_ALLOC_ACCESSIBLE, nid); } diff --git a/init/main.c b/init/main.c index 1c3f90264280..86b59cf3bec7 100644 --- a/init/main.c +++ b/init/main.c @@ -375,10 +375,10 @@ static inline void smp_prepare_cpus(unsigned int maxcpus) { } static void __init setup_command_line(char *command_line) { saved_command_line = - memblock_virt_alloc(strlen(boot_command_line) + 1, 0); + memblock_alloc(strlen(boot_command_line) + 1, 0); initcall_command_line = - memblock_virt_alloc(strlen(boot_command_line) + 1, 0); - static_command_line = memblock_virt_alloc(strlen(command_line) + 1, 0); + memblock_alloc(strlen(boot_command_line) + 1, 0); + static_command_line = memblock_alloc(strlen(command_line) + 1, 0); strcpy(saved_command_line, boot_command_line); strcpy(static_command_line, command_line); } diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c index ebecaf255ea2..801da67e957b 100644 --- a/kernel/dma/swiotlb.c +++ b/kernel/dma/swiotlb.c @@ -204,10 +204,10 @@ int __init swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose) * to find contiguous free memory regions of size up to IO_TLB_SEGSIZE * between io_tlb_start and io_tlb_end. */ - io_tlb_list = memblock_virt_alloc( + io_tlb_list = memblock_alloc( PAGE_ALIGN(io_tlb_nslabs * sizeof(int)), PAGE_SIZE); - io_tlb_orig_addr = memblock_virt_alloc( + io_tlb_orig_addr = memblock_alloc( PAGE_ALIGN(io_tlb_nslabs * sizeof(phys_addr_t)), PAGE_SIZE); for (i = 0; i < io_tlb_nslabs; i++) { @@ -242,7 +242,7 @@ swiotlb_init(int verbose) bytes = io_tlb_nslabs << IO_TLB_SHIFT; /* Get IO TLB memory from the low pages */ - vstart = memblock_virt_alloc_low_nopanic(PAGE_ALIGN(bytes), PAGE_SIZE); + vstart = memblock_alloc_low_nopanic(PAGE_ALIGN(bytes), PAGE_SIZE); if (vstart && !swiotlb_init_with_tbl(vstart, io_tlb_nslabs, verbose)) return; diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c index 3d37c279c090..34116a6097be 100644 --- a/kernel/power/snapshot.c +++ b/kernel/power/snapshot.c @@ -963,7 +963,7 @@ void __init __register_nosave_region(unsigned long start_pfn, BUG_ON(!region); } else { /* This allocation cannot fail */ - region = memblock_virt_alloc(sizeof(struct nosave_region), 0); + region = memblock_alloc(sizeof(struct nosave_region), 0); } region->start_pfn = start_pfn; region->end_pfn = end_pfn; diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index b77150ad1965..429e4a3833ca 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -1111,9 +1111,9 @@ void __init setup_log_buf(int early) if (early) { new_log_buf = - memblock_virt_alloc(new_log_buf_len, LOG_ALIGN); + memblock_alloc(new_log_buf_len, LOG_ALIGN); } else { - new_log_buf = memblock_virt_alloc_nopanic(new_log_buf_len, + new_log_buf = memblock_alloc_nopanic(new_log_buf_len, LOG_ALIGN); } diff --git a/lib/cpumask.c b/lib/cpumask.c index beca6244671a..1405cb22e6bc 100644 --- a/lib/cpumask.c +++ b/lib/cpumask.c @@ -163,7 +163,7 @@ EXPORT_SYMBOL(zalloc_cpumask_var); */ void __init alloc_bootmem_cpumask_var(cpumask_var_t *mask) { - *mask = memblock_virt_alloc(cpumask_size(), 0); + *mask = memblock_alloc(cpumask_size(), 0); } /** diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 7b5c0ad9a6bd..51e9f17dbd5c 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -2100,7 +2100,7 @@ int __alloc_bootmem_huge_page(struct hstate *h) for_each_node_mask_to_alloc(h, nr_nodes, node, &node_states[N_MEMORY]) { void *addr; - addr = memblock_virt_alloc_try_nid_raw( + addr = memblock_alloc_try_nid_raw( huge_page_size(h), huge_page_size(h), 0, BOOTMEM_ALLOC_ACCESSIBLE, node); if (addr) { diff --git a/mm/kasan/kasan_init.c b/mm/kasan/kasan_init.c index 7a2a2f13f86f..24d734bdff6b 100644 --- a/mm/kasan/kasan_init.c +++ b/mm/kasan/kasan_init.c @@ -83,7 +83,7 @@ static inline bool kasan_zero_page_entry(pte_t pte) static __init void *early_alloc(size_t size, int node) { - return memblock_virt_alloc_try_nid(size, size, __pa(MAX_DMA_ADDRESS), + return memblock_alloc_try_nid(size, size, __pa(MAX_DMA_ADDRESS), BOOTMEM_ALLOC_ACCESSIBLE, node); } diff --git a/mm/memblock.c b/mm/memblock.c index 20358374e8a8..58340de3ebc6 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -1319,7 +1319,7 @@ phys_addr_t __init memblock_phys_alloc_try_nid(phys_addr_t size, phys_addr_t ali } /** - * memblock_virt_alloc_internal - allocate boot memory block + * memblock_alloc_internal - allocate boot memory block * @size: size of memory block to be allocated in bytes * @align: alignment of the region and block's size * @min_addr: the lower bound of the memory region to allocate (phys address) @@ -1345,7 +1345,7 @@ phys_addr_t __init memblock_phys_alloc_try_nid(phys_addr_t size, phys_addr_t ali * Return: * Virtual address of allocated memory block on success, NULL on failure. */ -static void * __init memblock_virt_alloc_internal( +static void * __init memblock_alloc_internal( phys_addr_t size, phys_addr_t align, phys_addr_t min_addr, phys_addr_t max_addr, int nid) @@ -1412,7 +1412,7 @@ done: } /** - * memblock_virt_alloc_try_nid_raw - allocate boot memory block without zeroing + * memblock_alloc_try_nid_raw - allocate boot memory block without zeroing * memory and without panicking * @size: size of memory block to be allocated in bytes * @align: alignment of the region and block's size @@ -1430,7 +1430,7 @@ done: * Return: * Virtual address of allocated memory block on success, NULL on failure. */ -void * __init memblock_virt_alloc_try_nid_raw( +void * __init memblock_alloc_try_nid_raw( phys_addr_t size, phys_addr_t align, phys_addr_t min_addr, phys_addr_t max_addr, int nid) @@ -1441,7 +1441,7 @@ void * __init memblock_virt_alloc_try_nid_raw( __func__, (u64)size, (u64)align, nid, &min_addr, &max_addr, (void *)_RET_IP_); - ptr = memblock_virt_alloc_internal(size, align, + ptr = memblock_alloc_internal(size, align, min_addr, max_addr, nid); if (ptr && size > 0) page_init_poison(ptr, size); @@ -1450,7 +1450,7 @@ void * __init memblock_virt_alloc_try_nid_raw( } /** - * memblock_virt_alloc_try_nid_nopanic - allocate boot memory block + * memblock_alloc_try_nid_nopanic - allocate boot memory block * @size: size of memory block to be allocated in bytes * @align: alignment of the region and block's size * @min_addr: the lower bound of the memory region from where the allocation @@ -1466,7 +1466,7 @@ void * __init memblock_virt_alloc_try_nid_raw( * Return: * Virtual address of allocated memory block on success, NULL on failure. */ -void * __init memblock_virt_alloc_try_nid_nopanic( +void * __init memblock_alloc_try_nid_nopanic( phys_addr_t size, phys_addr_t align, phys_addr_t min_addr, phys_addr_t max_addr, int nid) @@ -1477,7 +1477,7 @@ void * __init memblock_virt_alloc_try_nid_nopanic( __func__, (u64)size, (u64)align, nid, &min_addr, &max_addr, (void *)_RET_IP_); - ptr = memblock_virt_alloc_internal(size, align, + ptr = memblock_alloc_internal(size, align, min_addr, max_addr, nid); if (ptr) memset(ptr, 0, size); @@ -1485,7 +1485,7 @@ void * __init memblock_virt_alloc_try_nid_nopanic( } /** - * memblock_virt_alloc_try_nid - allocate boot memory block with panicking + * memblock_alloc_try_nid - allocate boot memory block with panicking * @size: size of memory block to be allocated in bytes * @align: alignment of the region and block's size * @min_addr: the lower bound of the memory region from where the allocation @@ -1495,14 +1495,14 @@ void * __init memblock_virt_alloc_try_nid_nopanic( * allocate only from memory limited by memblock.current_limit value * @nid: nid of the free area to find, %NUMA_NO_NODE for any node * - * Public panicking version of memblock_virt_alloc_try_nid_nopanic() + * Public panicking version of memblock_alloc_try_nid_nopanic() * which provides debug information (including caller info), if enabled, * and panics if the request can not be satisfied. * * Return: * Virtual address of allocated memory block on success, NULL on failure. */ -void * __init memblock_virt_alloc_try_nid( +void * __init memblock_alloc_try_nid( phys_addr_t size, phys_addr_t align, phys_addr_t min_addr, phys_addr_t max_addr, int nid) @@ -1512,7 +1512,7 @@ void * __init memblock_virt_alloc_try_nid( memblock_dbg("%s: %llu bytes align=0x%llx nid=%d from=%pa max_addr=%pa %pF\n", __func__, (u64)size, (u64)align, nid, &min_addr, &max_addr, (void *)_RET_IP_); - ptr = memblock_virt_alloc_internal(size, align, + ptr = memblock_alloc_internal(size, align, min_addr, max_addr, nid); if (ptr) { memset(ptr, 0, size); @@ -1529,7 +1529,7 @@ void * __init memblock_virt_alloc_try_nid( * @base: phys starting address of the boot memory block * @size: size of the boot memory block in bytes * - * Free boot memory block previously allocated by memblock_virt_alloc_xx() API. + * Free boot memory block previously allocated by memblock_alloc_xx() API. * The freeing memory will not be released to the buddy allocator. */ void __init __memblock_free_early(phys_addr_t base, phys_addr_t size) diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 59d171f84445..8ca6954fdcdc 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -6209,7 +6209,7 @@ static void __ref setup_usemap(struct pglist_data *pgdat, zone->pageblock_flags = NULL; if (usemapsize) zone->pageblock_flags = - memblock_virt_alloc_node_nopanic(usemapsize, + memblock_alloc_node_nopanic(usemapsize, pgdat->node_id); } #else @@ -6439,7 +6439,7 @@ static void __ref alloc_node_mem_map(struct pglist_data *pgdat) end = pgdat_end_pfn(pgdat); end = ALIGN(end, MAX_ORDER_NR_PAGES); size = (end - start) * sizeof(struct page); - map = memblock_virt_alloc_node_nopanic(size, pgdat->node_id); + map = memblock_alloc_node_nopanic(size, pgdat->node_id); pgdat->node_mem_map = map + offset; } pr_debug("%s: node %d, pgdat %08lx, node_mem_map %08lx\n", @@ -7711,9 +7711,9 @@ void *__init alloc_large_system_hash(const char *tablename, size = bucketsize << log2qty; if (flags & HASH_EARLY) { if (flags & HASH_ZERO) - table = memblock_virt_alloc_nopanic(size, 0); + table = memblock_alloc_nopanic(size, 0); else - table = memblock_virt_alloc_raw(size, 0); + table = memblock_alloc_raw(size, 0); } else if (hashdist) { table = __vmalloc(size, gfp_flags, PAGE_KERNEL); } else { diff --git a/mm/page_ext.c b/mm/page_ext.c index a9826da84ccb..e77c0f031dd0 100644 --- a/mm/page_ext.c +++ b/mm/page_ext.c @@ -161,7 +161,7 @@ static int __init alloc_node_page_ext(int nid) table_size = get_entry_size() * nr_pages; - base = memblock_virt_alloc_try_nid_nopanic( + base = memblock_alloc_try_nid_nopanic( table_size, PAGE_SIZE, __pa(MAX_DMA_ADDRESS), BOOTMEM_ALLOC_ACCESSIBLE, nid); if (!base) diff --git a/mm/percpu.c b/mm/percpu.c index 4b90682623e9..3050c1d37d37 100644 --- a/mm/percpu.c +++ b/mm/percpu.c @@ -1101,7 +1101,7 @@ static struct pcpu_chunk * __init pcpu_alloc_first_chunk(unsigned long tmp_addr, region_size = ALIGN(start_offset + map_size, lcm_align); /* allocate chunk */ - chunk = memblock_virt_alloc(sizeof(struct pcpu_chunk) + + chunk = memblock_alloc(sizeof(struct pcpu_chunk) + BITS_TO_LONGS(region_size >> PAGE_SHIFT), 0); @@ -1114,11 +1114,11 @@ static struct pcpu_chunk * __init pcpu_alloc_first_chunk(unsigned long tmp_addr, chunk->nr_pages = region_size >> PAGE_SHIFT; region_bits = pcpu_chunk_map_bits(chunk); - chunk->alloc_map = memblock_virt_alloc(BITS_TO_LONGS(region_bits) * + chunk->alloc_map = memblock_alloc(BITS_TO_LONGS(region_bits) * sizeof(chunk->alloc_map[0]), 0); - chunk->bound_map = memblock_virt_alloc(BITS_TO_LONGS(region_bits + 1) * + chunk->bound_map = memblock_alloc(BITS_TO_LONGS(region_bits + 1) * sizeof(chunk->bound_map[0]), 0); - chunk->md_blocks = memblock_virt_alloc(pcpu_chunk_nr_blocks(chunk) * + chunk->md_blocks = memblock_alloc(pcpu_chunk_nr_blocks(chunk) * sizeof(chunk->md_blocks[0]), 0); pcpu_init_md_blocks(chunk); @@ -1888,7 +1888,7 @@ struct pcpu_alloc_info * __init pcpu_alloc_alloc_info(int nr_groups, __alignof__(ai->groups[0].cpu_map[0])); ai_size = base_size + nr_units * sizeof(ai->groups[0].cpu_map[0]); - ptr = memblock_virt_alloc_nopanic(PFN_ALIGN(ai_size), PAGE_SIZE); + ptr = memblock_alloc_nopanic(PFN_ALIGN(ai_size), PAGE_SIZE); if (!ptr) return NULL; ai = ptr; @@ -2075,12 +2075,12 @@ int __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai, PCPU_SETUP_BUG_ON(pcpu_verify_alloc_info(ai) < 0); /* process group information and build config tables accordingly */ - group_offsets = memblock_virt_alloc(ai->nr_groups * + group_offsets = memblock_alloc(ai->nr_groups * sizeof(group_offsets[0]), 0); - group_sizes = memblock_virt_alloc(ai->nr_groups * + group_sizes = memblock_alloc(ai->nr_groups * sizeof(group_sizes[0]), 0); - unit_map = memblock_virt_alloc(nr_cpu_ids * sizeof(unit_map[0]), 0); - unit_off = memblock_virt_alloc(nr_cpu_ids * sizeof(unit_off[0]), 0); + unit_map = memblock_alloc(nr_cpu_ids * sizeof(unit_map[0]), 0); + unit_off = memblock_alloc(nr_cpu_ids * sizeof(unit_off[0]), 0); for (cpu = 0; cpu < nr_cpu_ids; cpu++) unit_map[cpu] = UINT_MAX; @@ -2144,7 +2144,7 @@ int __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai, * empty chunks. */ pcpu_nr_slots = __pcpu_size_to_slot(pcpu_unit_size) + 2; - pcpu_slot = memblock_virt_alloc( + pcpu_slot = memblock_alloc( pcpu_nr_slots * sizeof(pcpu_slot[0]), 0); for (i = 0; i < pcpu_nr_slots; i++) INIT_LIST_HEAD(&pcpu_slot[i]); @@ -2458,7 +2458,7 @@ int __init pcpu_embed_first_chunk(size_t reserved_size, size_t dyn_size, size_sum = ai->static_size + ai->reserved_size + ai->dyn_size; areas_size = PFN_ALIGN(ai->nr_groups * sizeof(void *)); - areas = memblock_virt_alloc_nopanic(areas_size, 0); + areas = memblock_alloc_nopanic(areas_size, 0); if (!areas) { rc = -ENOMEM; goto out_free; @@ -2599,7 +2599,7 @@ int __init pcpu_page_first_chunk(size_t reserved_size, /* unaligned allocations can't be freed, round up to page size */ pages_size = PFN_ALIGN(unit_pages * num_possible_cpus() * sizeof(pages[0])); - pages = memblock_virt_alloc(pages_size, 0); + pages = memblock_alloc(pages_size, 0); /* allocate pages */ j = 0; @@ -2688,7 +2688,7 @@ EXPORT_SYMBOL(__per_cpu_offset); static void * __init pcpu_dfl_fc_alloc(unsigned int cpu, size_t size, size_t align) { - return memblock_virt_alloc_from_nopanic( + return memblock_alloc_from_nopanic( size, align, __pa(MAX_DMA_ADDRESS)); } @@ -2737,7 +2737,7 @@ void __init setup_per_cpu_areas(void) void *fc; ai = pcpu_alloc_alloc_info(1, 1); - fc = memblock_virt_alloc_from_nopanic(unit_size, + fc = memblock_alloc_from_nopanic(unit_size, PAGE_SIZE, __pa(MAX_DMA_ADDRESS)); if (!ai || !fc) diff --git a/mm/sparse-vmemmap.c b/mm/sparse-vmemmap.c index 8301293331a2..91c2c3d25827 100644 --- a/mm/sparse-vmemmap.c +++ b/mm/sparse-vmemmap.c @@ -42,7 +42,7 @@ static void * __ref __earlyonly_bootmem_alloc(int node, unsigned long align, unsigned long goal) { - return memblock_virt_alloc_try_nid_raw(size, align, goal, + return memblock_alloc_try_nid_raw(size, align, goal, BOOTMEM_ALLOC_ACCESSIBLE, node); } diff --git a/mm/sparse.c b/mm/sparse.c index 67ad061f7fb8..cb900dda7fd2 100644 --- a/mm/sparse.c +++ b/mm/sparse.c @@ -68,7 +68,7 @@ static noinline struct mem_section __ref *sparse_index_alloc(int nid) if (slab_is_available()) section = kzalloc_node(array_size, GFP_KERNEL, nid); else - section = memblock_virt_alloc_node(array_size, nid); + section = memblock_alloc_node(array_size, nid); return section; } @@ -216,7 +216,7 @@ void __init memory_present(int nid, unsigned long start, unsigned long end) size = sizeof(struct mem_section*) * NR_SECTION_ROOTS; align = 1 << (INTERNODE_CACHE_SHIFT); - mem_section = memblock_virt_alloc(size, align); + mem_section = memblock_alloc(size, align); } #endif @@ -306,7 +306,7 @@ sparse_early_usemaps_alloc_pgdat_section(struct pglist_data *pgdat, limit = goal + (1UL << PA_SECTION_SHIFT); nid = early_pfn_to_nid(goal >> PAGE_SHIFT); again: - p = memblock_virt_alloc_try_nid_nopanic(size, + p = memblock_alloc_try_nid_nopanic(size, SMP_CACHE_BYTES, goal, limit, nid); if (!p && limit) { @@ -362,7 +362,7 @@ static unsigned long * __init sparse_early_usemaps_alloc_pgdat_section(struct pglist_data *pgdat, unsigned long size) { - return memblock_virt_alloc_node_nopanic(size, pgdat->node_id); + return memblock_alloc_node_nopanic(size, pgdat->node_id); } static void __init check_usemap_section_nr(int nid, unsigned long *usemap) @@ -391,7 +391,7 @@ struct page __init *sparse_mem_map_populate(unsigned long pnum, int nid, if (map) return map; - map = memblock_virt_alloc_try_nid(size, + map = memblock_alloc_try_nid(size, PAGE_SIZE, __pa(MAX_DMA_ADDRESS), BOOTMEM_ALLOC_ACCESSIBLE, nid); return map; @@ -405,7 +405,7 @@ static void __init sparse_buffer_init(unsigned long size, int nid) { WARN_ON(sparsemap_buf); /* forgot to call sparse_buffer_fini()? */ sparsemap_buf = - memblock_virt_alloc_try_nid_raw(size, PAGE_SIZE, + memblock_alloc_try_nid_raw(size, PAGE_SIZE, __pa(MAX_DMA_ADDRESS), BOOTMEM_ALLOC_ACCESSIBLE, nid); sparsemap_buf_end = sparsemap_buf + size; -- cgit v1.2.3 From 3913c8f9f96bb75a062ad16ea10a1cdad48bb716 Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Tue, 30 Oct 2018 15:08:36 -0700 Subject: memblock: add align parameter to memblock_alloc_node() With the align parameter memblock_alloc_node() can be used as drop in replacement for alloc_bootmem_pages_node() and __alloc_bootmem_node(), which is done in the following patches. Link: http://lkml.kernel.org/r/1536927045-23536-15-git-send-email-rppt@linux.vnet.ibm.com Signed-off-by: Mike Rapoport Cc: Catalin Marinas Cc: Chris Zankel Cc: "David S. Miller" Cc: Geert Uytterhoeven Cc: Greentime Hu Cc: Greg Kroah-Hartman Cc: Guan Xuetao Cc: Ingo Molnar Cc: "James E.J. Bottomley" Cc: Jonas Bonn Cc: Jonathan Corbet Cc: Ley Foon Tan Cc: Mark Salter Cc: Martin Schwidefsky Cc: Matt Turner Cc: Michael Ellerman Cc: Michal Hocko Cc: Michal Simek Cc: Palmer Dabbelt Cc: Paul Burton Cc: Richard Kuo Cc: Richard Weinberger Cc: Rich Felker Cc: Russell King Cc: Serge Semin Cc: Thomas Gleixner Cc: Tony Luck Cc: Vineet Gupta Cc: Yoshinori Sato Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/bootmem.h | 4 ++-- mm/sparse.c | 2 +- 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'mm') diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h index 7d91f0f5ee44..3896af205303 100644 --- a/include/linux/bootmem.h +++ b/include/linux/bootmem.h @@ -157,9 +157,9 @@ static inline void * __init memblock_alloc_from_nopanic( } static inline void * __init memblock_alloc_node( - phys_addr_t size, int nid) + phys_addr_t size, phys_addr_t align, int nid) { - return memblock_alloc_try_nid(size, 0, BOOTMEM_LOW_LIMIT, + return memblock_alloc_try_nid(size, align, BOOTMEM_LOW_LIMIT, BOOTMEM_ALLOC_ACCESSIBLE, nid); } diff --git a/mm/sparse.c b/mm/sparse.c index cb900dda7fd2..d1296610562b 100644 --- a/mm/sparse.c +++ b/mm/sparse.c @@ -68,7 +68,7 @@ static noinline struct mem_section __ref *sparse_index_alloc(int nid) if (slab_is_available()) section = kzalloc_node(array_size, GFP_KERNEL, nid); else - section = memblock_alloc_node(array_size, nid); + section = memblock_alloc_node(array_size, 0, nid); return section; } -- cgit v1.2.3 From 6c7835f8d0d1839ca93bd3cf6faa15706f03d604 Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Tue, 30 Oct 2018 15:09:15 -0700 Subject: mm: nobootmem: remove bootmem allocation APIs The bootmem compatibility APIs are not used and can be removed. Link: http://lkml.kernel.org/r/1536927045-23536-23-git-send-email-rppt@linux.vnet.ibm.com Signed-off-by: Mike Rapoport Acked-by: Michal Hocko Cc: Catalin Marinas Cc: Chris Zankel Cc: "David S. Miller" Cc: Geert Uytterhoeven Cc: Greentime Hu Cc: Greg Kroah-Hartman Cc: Guan Xuetao Cc: Ingo Molnar Cc: "James E.J. Bottomley" Cc: Jonas Bonn Cc: Jonathan Corbet Cc: Ley Foon Tan Cc: Mark Salter Cc: Martin Schwidefsky Cc: Matt Turner Cc: Michael Ellerman Cc: Michal Simek Cc: Palmer Dabbelt Cc: Paul Burton Cc: Richard Kuo Cc: Richard Weinberger Cc: Rich Felker Cc: Russell King Cc: Serge Semin Cc: Thomas Gleixner Cc: Tony Luck Cc: Vineet Gupta Cc: Yoshinori Sato Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/bootmem.h | 47 ---------- mm/nobootmem.c | 224 ------------------------------------------------ 2 files changed, 271 deletions(-) (limited to 'mm') diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h index c97c105cfc67..73f1272fce20 100644 --- a/include/linux/bootmem.h +++ b/include/linux/bootmem.h @@ -36,33 +36,6 @@ extern void free_bootmem_node(pg_data_t *pgdat, extern void free_bootmem(unsigned long physaddr, unsigned long size); extern void free_bootmem_late(unsigned long physaddr, unsigned long size); -extern void *__alloc_bootmem(unsigned long size, - unsigned long align, - unsigned long goal); -extern void *__alloc_bootmem_nopanic(unsigned long size, - unsigned long align, - unsigned long goal) __malloc; -extern void *__alloc_bootmem_node(pg_data_t *pgdat, - unsigned long size, - unsigned long align, - unsigned long goal) __malloc; -void *__alloc_bootmem_node_high(pg_data_t *pgdat, - unsigned long size, - unsigned long align, - unsigned long goal) __malloc; -extern void *__alloc_bootmem_node_nopanic(pg_data_t *pgdat, - unsigned long size, - unsigned long align, - unsigned long goal) __malloc; -void *___alloc_bootmem_node_nopanic(pg_data_t *pgdat, - unsigned long size, - unsigned long align, - unsigned long goal, - unsigned long limit) __malloc; -extern void *__alloc_bootmem_low(unsigned long size, - unsigned long align, - unsigned long goal) __malloc; - /* We are using top down, so it is safe to use 0 here */ #define BOOTMEM_LOW_LIMIT 0 @@ -70,26 +43,6 @@ extern void *__alloc_bootmem_low(unsigned long size, #define ARCH_LOW_ADDRESS_LIMIT 0xffffffffUL #endif -#define alloc_bootmem(x) \ - __alloc_bootmem(x, SMP_CACHE_BYTES, BOOTMEM_LOW_LIMIT) -#define alloc_bootmem_align(x, align) \ - __alloc_bootmem(x, align, BOOTMEM_LOW_LIMIT) -#define alloc_bootmem_pages(x) \ - __alloc_bootmem(x, PAGE_SIZE, BOOTMEM_LOW_LIMIT) -#define alloc_bootmem_pages_nopanic(x) \ - __alloc_bootmem_nopanic(x, PAGE_SIZE, BOOTMEM_LOW_LIMIT) -#define alloc_bootmem_node(pgdat, x) \ - __alloc_bootmem_node(pgdat, x, SMP_CACHE_BYTES, BOOTMEM_LOW_LIMIT) -#define alloc_bootmem_node_nopanic(pgdat, x) \ - __alloc_bootmem_node_nopanic(pgdat, x, SMP_CACHE_BYTES, BOOTMEM_LOW_LIMIT) -#define alloc_bootmem_pages_node(pgdat, x) \ - __alloc_bootmem_node(pgdat, x, PAGE_SIZE, BOOTMEM_LOW_LIMIT) - -#define alloc_bootmem_low(x) \ - __alloc_bootmem_low(x, SMP_CACHE_BYTES, 0) -#define alloc_bootmem_low_pages(x) \ - __alloc_bootmem_low(x, PAGE_SIZE, 0) - /* FIXME: use MEMBLOCK_ALLOC_* variants here */ #define BOOTMEM_ALLOC_ACCESSIBLE 0 #define BOOTMEM_ALLOC_ANYWHERE (~(phys_addr_t)0) diff --git a/mm/nobootmem.c b/mm/nobootmem.c index 44ce7de1be8f..bc38e5673d31 100644 --- a/mm/nobootmem.c +++ b/mm/nobootmem.c @@ -33,41 +33,6 @@ unsigned long min_low_pfn; unsigned long max_pfn; unsigned long long max_possible_pfn; -static void * __init __alloc_memory_core_early(int nid, u64 size, u64 align, - u64 goal, u64 limit) -{ - void *ptr; - u64 addr; - enum memblock_flags flags = choose_memblock_flags(); - - if (limit > memblock.current_limit) - limit = memblock.current_limit; - -again: - addr = memblock_find_in_range_node(size, align, goal, limit, nid, - flags); - if (!addr && (flags & MEMBLOCK_MIRROR)) { - flags &= ~MEMBLOCK_MIRROR; - pr_warn("Could not allocate %pap bytes of mirrored memory\n", - &size); - goto again; - } - if (!addr) - return NULL; - - if (memblock_reserve(addr, size)) - return NULL; - - ptr = phys_to_virt(addr); - memset(ptr, 0, size); - /* - * The min_count is set to 0 so that bootmem allocated blocks - * are never reported as leaks. - */ - kmemleak_alloc(ptr, size, 0, 0); - return ptr; -} - /** * free_bootmem_late - free bootmem pages directly to page allocator * @addr: starting address of the range @@ -215,192 +180,3 @@ void __init free_bootmem(unsigned long addr, unsigned long size) { memblock_free(addr, size); } - -static void * __init ___alloc_bootmem_nopanic(unsigned long size, - unsigned long align, - unsigned long goal, - unsigned long limit) -{ - void *ptr; - - if (WARN_ON_ONCE(slab_is_available())) - return kzalloc(size, GFP_NOWAIT); - -restart: - - ptr = __alloc_memory_core_early(NUMA_NO_NODE, size, align, goal, limit); - - if (ptr) - return ptr; - - if (goal != 0) { - goal = 0; - goto restart; - } - - return NULL; -} - -/** - * __alloc_bootmem_nopanic - allocate boot memory without panicking - * @size: size of the request in bytes - * @align: alignment of the region - * @goal: preferred starting address of the region - * - * The goal is dropped if it can not be satisfied and the allocation will - * fall back to memory below @goal. - * - * Allocation may happen on any node in the system. - * - * Return: address of the allocated region or %NULL on failure. - */ -void * __init __alloc_bootmem_nopanic(unsigned long size, unsigned long align, - unsigned long goal) -{ - unsigned long limit = -1UL; - - return ___alloc_bootmem_nopanic(size, align, goal, limit); -} - -static void * __init ___alloc_bootmem(unsigned long size, unsigned long align, - unsigned long goal, unsigned long limit) -{ - void *mem = ___alloc_bootmem_nopanic(size, align, goal, limit); - - if (mem) - return mem; - /* - * Whoops, we cannot satisfy the allocation request. - */ - pr_alert("bootmem alloc of %lu bytes failed!\n", size); - panic("Out of memory"); - return NULL; -} - -/** - * __alloc_bootmem - allocate boot memory - * @size: size of the request in bytes - * @align: alignment of the region - * @goal: preferred starting address of the region - * - * The goal is dropped if it can not be satisfied and the allocation will - * fall back to memory below @goal. - * - * Allocation may happen on any node in the system. - * - * The function panics if the request can not be satisfied. - * - * Return: address of the allocated region. - */ -void * __init __alloc_bootmem(unsigned long size, unsigned long align, - unsigned long goal) -{ - unsigned long limit = -1UL; - - return ___alloc_bootmem(size, align, goal, limit); -} - -void * __init ___alloc_bootmem_node_nopanic(pg_data_t *pgdat, - unsigned long size, - unsigned long align, - unsigned long goal, - unsigned long limit) -{ - void *ptr; - -again: - ptr = __alloc_memory_core_early(pgdat->node_id, size, align, - goal, limit); - if (ptr) - return ptr; - - ptr = __alloc_memory_core_early(NUMA_NO_NODE, size, align, - goal, limit); - if (ptr) - return ptr; - - if (goal) { - goal = 0; - goto again; - } - - return NULL; -} - -void * __init __alloc_bootmem_node_nopanic(pg_data_t *pgdat, unsigned long size, - unsigned long align, unsigned long goal) -{ - if (WARN_ON_ONCE(slab_is_available())) - return kzalloc_node(size, GFP_NOWAIT, pgdat->node_id); - - return ___alloc_bootmem_node_nopanic(pgdat, size, align, goal, 0); -} - -static void * __init ___alloc_bootmem_node(pg_data_t *pgdat, unsigned long size, - unsigned long align, unsigned long goal, - unsigned long limit) -{ - void *ptr; - - ptr = ___alloc_bootmem_node_nopanic(pgdat, size, align, goal, limit); - if (ptr) - return ptr; - - pr_alert("bootmem alloc of %lu bytes failed!\n", size); - panic("Out of memory"); - return NULL; -} - -/** - * __alloc_bootmem_node - allocate boot memory from a specific node - * @pgdat: node to allocate from - * @size: size of the request in bytes - * @align: alignment of the region - * @goal: preferred starting address of the region - * - * The goal is dropped if it can not be satisfied and the allocation will - * fall back to memory below @goal. - * - * Allocation may fall back to any node in the system if the specified node - * can not hold the requested memory. - * - * The function panics if the request can not be satisfied. - * - * Return: address of the allocated region. - */ -void * __init __alloc_bootmem_node(pg_data_t *pgdat, unsigned long size, - unsigned long align, unsigned long goal) -{ - if (WARN_ON_ONCE(slab_is_available())) - return kzalloc_node(size, GFP_NOWAIT, pgdat->node_id); - - return ___alloc_bootmem_node(pgdat, size, align, goal, 0); -} - -void * __init __alloc_bootmem_node_high(pg_data_t *pgdat, unsigned long size, - unsigned long align, unsigned long goal) -{ - return __alloc_bootmem_node(pgdat, size, align, goal); -} - - -/** - * __alloc_bootmem_low - allocate low boot memory - * @size: size of the request in bytes - * @align: alignment of the region - * @goal: preferred starting address of the region - * - * The goal is dropped if it can not be satisfied and the allocation will - * fall back to memory below @goal. - * - * Allocation may happen on any node in the system. - * - * The function panics if the request can not be satisfied. - * - * Return: address of the allocated region. - */ -void * __init __alloc_bootmem_low(unsigned long size, unsigned long align, - unsigned long goal) -{ - return ___alloc_bootmem(size, align, goal, ARCH_LOW_ADDRESS_LIMIT); -} -- cgit v1.2.3 From 2013288f723887837d2f1cebef5fcf663b2319de Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Tue, 30 Oct 2018 15:09:21 -0700 Subject: memblock: replace free_bootmem{_node} with memblock_free The free_bootmem and free_bootmem_node are merely wrappers for memblock_free. Replace their usage with a call to memblock_free using the following semantic patch: @@ expression e1, e2, e3; @@ ( - free_bootmem(e1, e2) + memblock_free(e1, e2) | - free_bootmem_node(e1, e2, e3) + memblock_free(e2, e3) ) Link: http://lkml.kernel.org/r/1536927045-23536-24-git-send-email-rppt@linux.vnet.ibm.com Signed-off-by: Mike Rapoport Acked-by: Michal Hocko Cc: Catalin Marinas Cc: Chris Zankel Cc: "David S. Miller" Cc: Geert Uytterhoeven Cc: Greentime Hu Cc: Greg Kroah-Hartman Cc: Guan Xuetao Cc: Ingo Molnar Cc: "James E.J. Bottomley" Cc: Jonas Bonn Cc: Jonathan Corbet Cc: Ley Foon Tan Cc: Mark Salter Cc: Martin Schwidefsky Cc: Matt Turner Cc: Michael Ellerman Cc: Michal Simek Cc: Palmer Dabbelt Cc: Paul Burton Cc: Richard Kuo Cc: Richard Weinberger Cc: Rich Felker Cc: Russell King Cc: Serge Semin Cc: Thomas Gleixner Cc: Tony Luck Cc: Vineet Gupta Cc: Yoshinori Sato Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/alpha/kernel/core_irongate.c | 3 +-- arch/arm64/mm/init.c | 2 +- arch/mips/kernel/setup.c | 2 +- arch/powerpc/kernel/setup_64.c | 2 +- arch/sparc/kernel/smp_64.c | 2 +- arch/um/kernel/mem.c | 3 ++- arch/unicore32/mm/init.c | 2 +- arch/x86/kernel/setup_percpu.c | 3 ++- arch/x86/kernel/tce_64.c | 3 ++- arch/x86/xen/p2m.c | 3 ++- drivers/macintosh/smu.c | 2 +- drivers/usb/early/xhci-dbc.c | 11 ++++++----- drivers/xen/swiotlb-xen.c | 4 +++- include/linux/bootmem.h | 4 ---- mm/nobootmem.c | 30 ------------------------------ 15 files changed, 24 insertions(+), 52 deletions(-) (limited to 'mm') diff --git a/arch/alpha/kernel/core_irongate.c b/arch/alpha/kernel/core_irongate.c index f70986683fc6..35572be9deb5 100644 --- a/arch/alpha/kernel/core_irongate.c +++ b/arch/alpha/kernel/core_irongate.c @@ -234,8 +234,7 @@ albacore_init_arch(void) unsigned long size; size = initrd_end - initrd_start; - free_bootmem_node(NODE_DATA(0), __pa(initrd_start), - PAGE_ALIGN(size)); + memblock_free(__pa(initrd_start), PAGE_ALIGN(size)); if (!move_initrd(pci_mem)) printk("irongate_init_arch: initrd too big " "(%ldK)\ndisabling initrd\n", diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c index 3cf87341859f..2ddb1c5e988d 100644 --- a/arch/arm64/mm/init.c +++ b/arch/arm64/mm/init.c @@ -536,7 +536,7 @@ static inline void free_memmap(unsigned long start_pfn, unsigned long end_pfn) * memmap array. */ if (pg < pgend) - free_bootmem(pg, pgend - pg); + memblock_free(pg, pgend - pg); } /* diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c index c1f95359d298..31522d3bc8bf 100644 --- a/arch/mips/kernel/setup.c +++ b/arch/mips/kernel/setup.c @@ -561,7 +561,7 @@ static void __init bootmem_init(void) extern void show_kernel_relocation(const char *level); offset = __pa_symbol(_text) - __pa_symbol(VMLINUX_LOAD_ADDRESS); - free_bootmem(__pa_symbol(VMLINUX_LOAD_ADDRESS), offset); + memblock_free(__pa_symbol(VMLINUX_LOAD_ADDRESS), offset); #if defined(CONFIG_DEBUG_KERNEL) && defined(CONFIG_DEBUG_INFO) /* diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index 26d7c49a157b..f90ab3ea9af3 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -771,7 +771,7 @@ static void * __init pcpu_fc_alloc(unsigned int cpu, size_t size, size_t align) static void __init pcpu_fc_free(void *ptr, size_t size) { - free_bootmem(__pa(ptr), size); + memblock_free(__pa(ptr), size); } static int pcpu_cpu_distance(unsigned int from, unsigned int to) diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c index 337febdf94b8..a087a6a25f06 100644 --- a/arch/sparc/kernel/smp_64.c +++ b/arch/sparc/kernel/smp_64.c @@ -1607,7 +1607,7 @@ static void * __init pcpu_alloc_bootmem(unsigned int cpu, size_t size, static void __init pcpu_free_bootmem(void *ptr, size_t size) { - free_bootmem(__pa(ptr), size); + memblock_free(__pa(ptr), size); } static int __init pcpu_cpu_distance(unsigned int from, unsigned int to) diff --git a/arch/um/kernel/mem.c b/arch/um/kernel/mem.c index 185f6bb79269..3555c139389c 100644 --- a/arch/um/kernel/mem.c +++ b/arch/um/kernel/mem.c @@ -6,6 +6,7 @@ #include #include #include +#include #include #include #include @@ -46,7 +47,7 @@ void __init mem_init(void) */ brk_end = (unsigned long) UML_ROUND_UP(sbrk(0)); map_memory(brk_end, __pa(brk_end), uml_reserved - brk_end, 1, 1, 0); - free_bootmem(__pa(brk_end), uml_reserved - brk_end); + memblock_free(__pa(brk_end), uml_reserved - brk_end); uml_reserved = brk_end; /* this will put all low memory onto the freelists */ diff --git a/arch/unicore32/mm/init.c b/arch/unicore32/mm/init.c index 8f8699e62bd5..4ba51991c7de 100644 --- a/arch/unicore32/mm/init.c +++ b/arch/unicore32/mm/init.c @@ -238,7 +238,7 @@ free_memmap(unsigned long start_pfn, unsigned long end_pfn) * free the section of the memmap array. */ if (pg < pgend) - free_bootmem(pg, pgend - pg); + memblock_free(pg, pgend - pg); } /* diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c index 041663abc028..a006f1ba4c39 100644 --- a/arch/x86/kernel/setup_percpu.c +++ b/arch/x86/kernel/setup_percpu.c @@ -5,6 +5,7 @@ #include #include #include +#include #include #include #include @@ -135,7 +136,7 @@ static void * __init pcpu_fc_alloc(unsigned int cpu, size_t size, size_t align) static void __init pcpu_fc_free(void *ptr, size_t size) { - free_bootmem(__pa(ptr), size); + memblock_free(__pa(ptr), size); } static int __init pcpu_cpu_distance(unsigned int from, unsigned int to) diff --git a/arch/x86/kernel/tce_64.c b/arch/x86/kernel/tce_64.c index 54c9b5a696b1..75730ce01f8d 100644 --- a/arch/x86/kernel/tce_64.c +++ b/arch/x86/kernel/tce_64.c @@ -31,6 +31,7 @@ #include #include #include +#include #include #include #include @@ -186,5 +187,5 @@ void __init free_tce_table(void *tbl) size = table_size_to_number_of_entries(specified_table_size); size *= TCE_ENTRY_SIZE; - free_bootmem(__pa(tbl), size); + memblock_free(__pa(tbl), size); } diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c index 5de761b4cec8..b3e11afed25b 100644 --- a/arch/x86/xen/p2m.c +++ b/arch/x86/xen/p2m.c @@ -68,6 +68,7 @@ #include #include #include +#include #include #include @@ -190,7 +191,7 @@ static void * __ref alloc_p2m_page(void) static void __ref free_p2m_page(void *p) { if (unlikely(!slab_is_available())) { - free_bootmem((unsigned long)p, PAGE_SIZE); + memblock_free((unsigned long)p, PAGE_SIZE); return; } diff --git a/drivers/macintosh/smu.c b/drivers/macintosh/smu.c index 332fcca30944..0069f9084f9f 100644 --- a/drivers/macintosh/smu.c +++ b/drivers/macintosh/smu.c @@ -569,7 +569,7 @@ fail_msg_node: fail_db_node: of_node_put(smu->db_node); fail_bootmem: - free_bootmem(__pa(smu), sizeof(struct smu_device)); + memblock_free(__pa(smu), sizeof(struct smu_device)); smu = NULL; fail_np: of_node_put(np); diff --git a/drivers/usb/early/xhci-dbc.c b/drivers/usb/early/xhci-dbc.c index 21494c8973b6..ddc5fa88f268 100644 --- a/drivers/usb/early/xhci-dbc.c +++ b/drivers/usb/early/xhci-dbc.c @@ -13,6 +13,7 @@ #include #include #include +#include #include #include #include @@ -191,7 +192,7 @@ static void __init xdbc_free_ring(struct xdbc_ring *ring) if (!seg) return; - free_bootmem(seg->dma, PAGE_SIZE); + memblock_free(seg->dma, PAGE_SIZE); ring->segment = NULL; } @@ -675,10 +676,10 @@ int __init early_xdbc_setup_hardware(void) xdbc_free_ring(&xdbc.in_ring); if (xdbc.table_dma) - free_bootmem(xdbc.table_dma, PAGE_SIZE); + memblock_free(xdbc.table_dma, PAGE_SIZE); if (xdbc.out_dma) - free_bootmem(xdbc.out_dma, PAGE_SIZE); + memblock_free(xdbc.out_dma, PAGE_SIZE); xdbc.table_base = NULL; xdbc.out_buf = NULL; @@ -997,8 +998,8 @@ free_and_quit: xdbc_free_ring(&xdbc.evt_ring); xdbc_free_ring(&xdbc.out_ring); xdbc_free_ring(&xdbc.in_ring); - free_bootmem(xdbc.table_dma, PAGE_SIZE); - free_bootmem(xdbc.out_dma, PAGE_SIZE); + memblock_free(xdbc.table_dma, PAGE_SIZE); + memblock_free(xdbc.out_dma, PAGE_SIZE); writel(0, &xdbc.xdbc_reg->control); early_iounmap(xdbc.xhci_base, xdbc.xhci_length); diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c index 91a6208ec1a5..c5f26a87d238 100644 --- a/drivers/xen/swiotlb-xen.c +++ b/drivers/xen/swiotlb-xen.c @@ -36,6 +36,7 @@ #define pr_fmt(fmt) "xen:" KBUILD_MODNAME ": " fmt #include +#include #include #include #include @@ -248,7 +249,8 @@ retry: xen_io_tlb_nslabs); if (rc) { if (early) - free_bootmem(__pa(xen_io_tlb_start), PAGE_ALIGN(bytes)); + memblock_free(__pa(xen_io_tlb_start), + PAGE_ALIGN(bytes)); else { free_pages((unsigned long)xen_io_tlb_start, order); xen_io_tlb_start = NULL; diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h index 73f1272fce20..706cf8ef6678 100644 --- a/include/linux/bootmem.h +++ b/include/linux/bootmem.h @@ -30,10 +30,6 @@ extern unsigned long free_all_bootmem(void); extern void reset_node_managed_pages(pg_data_t *pgdat); extern void reset_all_zones_managed_pages(void); -extern void free_bootmem_node(pg_data_t *pgdat, - unsigned long addr, - unsigned long size); -extern void free_bootmem(unsigned long physaddr, unsigned long size); extern void free_bootmem_late(unsigned long physaddr, unsigned long size); /* We are using top down, so it is safe to use 0 here */ diff --git a/mm/nobootmem.c b/mm/nobootmem.c index bc38e5673d31..85e1822ce918 100644 --- a/mm/nobootmem.c +++ b/mm/nobootmem.c @@ -150,33 +150,3 @@ unsigned long __init free_all_bootmem(void) return pages; } - -/** - * free_bootmem_node - mark a page range as usable - * @pgdat: node the range resides on - * @physaddr: starting physical address of the range - * @size: size of the range in bytes - * - * Partial pages will be considered reserved and left as they are. - * - * The range must reside completely on the specified node. - */ -void __init free_bootmem_node(pg_data_t *pgdat, unsigned long physaddr, - unsigned long size) -{ - memblock_free(physaddr, size); -} - -/** - * free_bootmem - mark a page range as usable - * @addr: starting physical address of the range - * @size: size of the range in bytes - * - * Partial pages will be considered reserved and left as they are. - * - * The range must be contiguous but may span node boundaries. - */ -void __init free_bootmem(unsigned long addr, unsigned long size) -{ - memblock_free(addr, size); -} -- cgit v1.2.3 From 53ab85ebfd27cdf16c8ddc72781c072a63bef3cb Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Tue, 30 Oct 2018 15:09:25 -0700 Subject: memblock: replace free_bootmem_late with memblock_free_late The free_bootmem_late and memblock_free_late do exactly the same thing: they iterate over a range and give pages to the page allocator. Replace calls to free_bootmem_late with calls to memblock_free_late and remove the bootmem variant. Link: http://lkml.kernel.org/r/1536927045-23536-25-git-send-email-rppt@linux.vnet.ibm.com Signed-off-by: Mike Rapoport Acked-by: Michal Hocko Cc: Catalin Marinas Cc: Chris Zankel Cc: "David S. Miller" Cc: Geert Uytterhoeven Cc: Greentime Hu Cc: Greg Kroah-Hartman Cc: Guan Xuetao Cc: Ingo Molnar Cc: "James E.J. Bottomley" Cc: Jonas Bonn Cc: Jonathan Corbet Cc: Ley Foon Tan Cc: Mark Salter Cc: Martin Schwidefsky Cc: Matt Turner Cc: Michael Ellerman Cc: Michal Simek Cc: Palmer Dabbelt Cc: Paul Burton Cc: Richard Kuo Cc: Richard Weinberger Cc: Rich Felker Cc: Russell King Cc: Serge Semin Cc: Thomas Gleixner Cc: Tony Luck Cc: Vineet Gupta Cc: Yoshinori Sato Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/sparc/kernel/mdesc.c | 3 ++- arch/x86/platform/efi/quirks.c | 6 +++--- drivers/firmware/efi/apple-properties.c | 2 +- include/linux/bootmem.h | 2 -- mm/nobootmem.c | 24 ------------------------ 5 files changed, 6 insertions(+), 31 deletions(-) (limited to 'mm') diff --git a/arch/sparc/kernel/mdesc.c b/arch/sparc/kernel/mdesc.c index 59131e72ee78..a41526bd91e2 100644 --- a/arch/sparc/kernel/mdesc.c +++ b/arch/sparc/kernel/mdesc.c @@ -12,6 +12,7 @@ #include #include #include +#include #include #include @@ -190,7 +191,7 @@ static void __init mdesc_memblock_free(struct mdesc_handle *hp) alloc_size = PAGE_ALIGN(hp->handle_size); start = __pa(hp); - free_bootmem_late(start, alloc_size); + memblock_free_late(start, alloc_size); } static struct mdesc_mem_ops memblock_mdesc_ops = { diff --git a/arch/x86/platform/efi/quirks.c b/arch/x86/platform/efi/quirks.c index 669babcaf245..4b70d0f5a803 100644 --- a/arch/x86/platform/efi/quirks.c +++ b/arch/x86/platform/efi/quirks.c @@ -333,7 +333,7 @@ void __init efi_reserve_boot_services(void) /* * Because the following memblock_reserve() is paired - * with free_bootmem_late() for this region in + * with memblock_free_late() for this region in * efi_free_boot_services(), we must be extremely * careful not to reserve, and subsequently free, * critical regions of memory (like the kernel image) or @@ -364,7 +364,7 @@ void __init efi_reserve_boot_services(void) * doesn't make sense as far as the firmware is * concerned, but it does provide us with a way to tag * those regions that must not be paired with - * free_bootmem_late(). + * memblock_free_late(). */ md->attribute |= EFI_MEMORY_RUNTIME; } @@ -414,7 +414,7 @@ void __init efi_free_boot_services(void) size -= rm_size; } - free_bootmem_late(start, size); + memblock_free_late(start, size); } if (!num_entries) diff --git a/drivers/firmware/efi/apple-properties.c b/drivers/firmware/efi/apple-properties.c index 60a95719ecb8..2b675f788b61 100644 --- a/drivers/firmware/efi/apple-properties.c +++ b/drivers/firmware/efi/apple-properties.c @@ -235,7 +235,7 @@ static int __init map_properties(void) */ data->len = 0; memunmap(data); - free_bootmem_late(pa_data + sizeof(*data), data_len); + memblock_free_late(pa_data + sizeof(*data), data_len); return ret; } diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h index 706cf8ef6678..bcc7e2fcb6a6 100644 --- a/include/linux/bootmem.h +++ b/include/linux/bootmem.h @@ -30,8 +30,6 @@ extern unsigned long free_all_bootmem(void); extern void reset_node_managed_pages(pg_data_t *pgdat); extern void reset_all_zones_managed_pages(void); -extern void free_bootmem_late(unsigned long physaddr, unsigned long size); - /* We are using top down, so it is safe to use 0 here */ #define BOOTMEM_LOW_LIMIT 0 diff --git a/mm/nobootmem.c b/mm/nobootmem.c index 85e1822ce918..ee0f7fc37fd1 100644 --- a/mm/nobootmem.c +++ b/mm/nobootmem.c @@ -33,30 +33,6 @@ unsigned long min_low_pfn; unsigned long max_pfn; unsigned long long max_possible_pfn; -/** - * free_bootmem_late - free bootmem pages directly to page allocator - * @addr: starting address of the range - * @size: size of the range in bytes - * - * This is only useful when the bootmem allocator has already been torn - * down, but we are still initializing the system. Pages are given directly - * to the page allocator, no bootmem metadata is updated because it is gone. - */ -void __init free_bootmem_late(unsigned long addr, unsigned long size) -{ - unsigned long cursor, end; - - kmemleak_free_part_phys(addr, size); - - cursor = PFN_UP(addr); - end = PFN_DOWN(addr + size); - - for (; cursor < end; cursor++) { - __free_pages_bootmem(pfn_to_page(cursor), cursor, 0); - totalram_pages++; - } -} - static void __init __free_pages_memory(unsigned long start, unsigned long end) { int order; -- cgit v1.2.3 From c6ffc5ca8fb311a89cb6de5c31b6511308ddac8d Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Tue, 30 Oct 2018 15:09:30 -0700 Subject: memblock: rename free_all_bootmem to memblock_free_all The conversion is done using sed -i 's@free_all_bootmem@memblock_free_all@' \ $(git grep -l free_all_bootmem) Link: http://lkml.kernel.org/r/1536927045-23536-26-git-send-email-rppt@linux.vnet.ibm.com Signed-off-by: Mike Rapoport Acked-by: Michal Hocko Cc: Catalin Marinas Cc: Chris Zankel Cc: "David S. Miller" Cc: Geert Uytterhoeven Cc: Greentime Hu Cc: Greg Kroah-Hartman Cc: Guan Xuetao Cc: Ingo Molnar Cc: "James E.J. Bottomley" Cc: Jonas Bonn Cc: Jonathan Corbet Cc: Ley Foon Tan Cc: Mark Salter Cc: Martin Schwidefsky Cc: Matt Turner Cc: Michael Ellerman Cc: Michal Simek Cc: Palmer Dabbelt Cc: Paul Burton Cc: Richard Kuo Cc: Richard Weinberger Cc: Rich Felker Cc: Russell King Cc: Serge Semin Cc: Thomas Gleixner Cc: Tony Luck Cc: Vineet Gupta Cc: Yoshinori Sato Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/alpha/mm/init.c | 2 +- arch/arc/mm/init.c | 2 +- arch/arm/mm/init.c | 2 +- arch/arm64/mm/init.c | 2 +- arch/c6x/mm/init.c | 2 +- arch/h8300/mm/init.c | 2 +- arch/hexagon/mm/init.c | 2 +- arch/ia64/mm/init.c | 2 +- arch/m68k/mm/init.c | 2 +- arch/microblaze/mm/init.c | 2 +- arch/mips/loongson64/loongson-3/numa.c | 2 +- arch/mips/mm/init.c | 2 +- arch/mips/sgi-ip27/ip27-memory.c | 2 +- arch/nds32/mm/init.c | 2 +- arch/nios2/mm/init.c | 2 +- arch/openrisc/mm/init.c | 2 +- arch/parisc/mm/init.c | 2 +- arch/powerpc/mm/mem.c | 2 +- arch/riscv/mm/init.c | 2 +- arch/s390/mm/init.c | 2 +- arch/sh/mm/init.c | 2 +- arch/sparc/mm/init_32.c | 2 +- arch/sparc/mm/init_64.c | 4 ++-- arch/um/kernel/mem.c | 2 +- arch/unicore32/mm/init.c | 2 +- arch/x86/mm/highmem_32.c | 2 +- arch/x86/mm/init_32.c | 4 ++-- arch/x86/mm/init_64.c | 4 ++-- arch/x86/xen/mmu_pv.c | 2 +- arch/xtensa/mm/init.c | 2 +- include/linux/bootmem.h | 2 +- mm/memblock.c | 2 +- mm/nobootmem.c | 4 ++-- mm/page_alloc.c | 2 +- mm/page_poison.c | 2 +- 35 files changed, 39 insertions(+), 39 deletions(-) (limited to 'mm') diff --git a/arch/alpha/mm/init.c b/arch/alpha/mm/init.c index 9d74520298ab..853d15344934 100644 --- a/arch/alpha/mm/init.c +++ b/arch/alpha/mm/init.c @@ -282,7 +282,7 @@ mem_init(void) { set_max_mapnr(max_low_pfn); high_memory = (void *) __va(max_low_pfn * PAGE_SIZE); - free_all_bootmem(); + memblock_free_all(); mem_init_print_info(NULL); } diff --git a/arch/arc/mm/init.c b/arch/arc/mm/init.c index ba145065c579..0f29c6548779 100644 --- a/arch/arc/mm/init.c +++ b/arch/arc/mm/init.c @@ -218,7 +218,7 @@ void __init mem_init(void) free_highmem_page(pfn_to_page(tmp)); #endif - free_all_bootmem(); + memblock_free_all(); mem_init_print_info(NULL); } diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c index 0cc8e04295a4..d421a10c93a8 100644 --- a/arch/arm/mm/init.c +++ b/arch/arm/mm/init.c @@ -508,7 +508,7 @@ void __init mem_init(void) /* this will put all unused low memory onto the freelists */ free_unused_memmap(); - free_all_bootmem(); + memblock_free_all(); #ifdef CONFIG_SA1111 /* now that our DMA memory is actually so designated, we can free it */ diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c index 2ddb1c5e988d..d8d73073835f 100644 --- a/arch/arm64/mm/init.c +++ b/arch/arm64/mm/init.c @@ -599,7 +599,7 @@ void __init mem_init(void) free_unused_memmap(); #endif /* this will put all unused low memory onto the freelists */ - free_all_bootmem(); + memblock_free_all(); kexec_reserve_crashkres_pages(); diff --git a/arch/c6x/mm/init.c b/arch/c6x/mm/init.c index dc369ad8b0ba..3383df8b3508 100644 --- a/arch/c6x/mm/init.c +++ b/arch/c6x/mm/init.c @@ -62,7 +62,7 @@ void __init mem_init(void) high_memory = (void *)(memory_end & PAGE_MASK); /* this will put all memory onto the freelists */ - free_all_bootmem(); + memblock_free_all(); mem_init_print_info(NULL); } diff --git a/arch/h8300/mm/init.c b/arch/h8300/mm/init.c index 5d31ac9d7a8d..f2bf4487aabd 100644 --- a/arch/h8300/mm/init.c +++ b/arch/h8300/mm/init.c @@ -96,7 +96,7 @@ void __init mem_init(void) max_mapnr = MAP_NR(high_memory); /* this will put all low memory onto the freelists */ - free_all_bootmem(); + memblock_free_all(); mem_init_print_info(NULL); } diff --git a/arch/hexagon/mm/init.c b/arch/hexagon/mm/init.c index d789b9cc0189..88643faf3981 100644 --- a/arch/hexagon/mm/init.c +++ b/arch/hexagon/mm/init.c @@ -68,7 +68,7 @@ unsigned long long kmap_generation; void __init mem_init(void) { /* No idea where this is actually declared. Seems to evade LXR. */ - free_all_bootmem(); + memblock_free_all(); mem_init_print_info(NULL); /* diff --git a/arch/ia64/mm/init.c b/arch/ia64/mm/init.c index 2169ca52bdf4..43ea4a47163d 100644 --- a/arch/ia64/mm/init.c +++ b/arch/ia64/mm/init.c @@ -627,7 +627,7 @@ mem_init (void) set_max_mapnr(max_low_pfn); high_memory = __va(max_low_pfn * PAGE_SIZE); - free_all_bootmem(); + memblock_free_all(); mem_init_print_info(NULL); /* diff --git a/arch/m68k/mm/init.c b/arch/m68k/mm/init.c index 977363eda125..ae49ae4d3049 100644 --- a/arch/m68k/mm/init.c +++ b/arch/m68k/mm/init.c @@ -140,7 +140,7 @@ static inline void init_pointer_tables(void) void __init mem_init(void) { /* this will put all memory onto the freelists */ - free_all_bootmem(); + memblock_free_all(); init_pointer_tables(); mem_init_print_info(NULL); } diff --git a/arch/microblaze/mm/init.c b/arch/microblaze/mm/init.c index 8c7f074ec20f..9989740d397a 100644 --- a/arch/microblaze/mm/init.c +++ b/arch/microblaze/mm/init.c @@ -204,7 +204,7 @@ void __init mem_init(void) high_memory = (void *)__va(memory_start + lowmem_size - 1); /* this will put all memory onto the freelists */ - free_all_bootmem(); + memblock_free_all(); #ifdef CONFIG_HIGHMEM highmem_setup(); #endif diff --git a/arch/mips/loongson64/loongson-3/numa.c b/arch/mips/loongson64/loongson-3/numa.c index c1e6ec52c614..703ad4536fe0 100644 --- a/arch/mips/loongson64/loongson-3/numa.c +++ b/arch/mips/loongson64/loongson-3/numa.c @@ -272,7 +272,7 @@ void __init paging_init(void) void __init mem_init(void) { high_memory = (void *) __va(get_num_physpages() << PAGE_SHIFT); - free_all_bootmem(); + memblock_free_all(); setup_zero_pages(); /* This comes from node 0 */ mem_init_print_info(NULL); } diff --git a/arch/mips/mm/init.c b/arch/mips/mm/init.c index 842a49ef9909..0893b6136498 100644 --- a/arch/mips/mm/init.c +++ b/arch/mips/mm/init.c @@ -463,7 +463,7 @@ void __init mem_init(void) high_memory = (void *) __va(max_low_pfn << PAGE_SHIFT); maar_init(); - free_all_bootmem(); + memblock_free_all(); setup_zero_pages(); /* Setup zeroed pages. */ mem_init_free_highmem(); mem_init_print_info(NULL); diff --git a/arch/mips/sgi-ip27/ip27-memory.c b/arch/mips/sgi-ip27/ip27-memory.c index 6f7bef052b7f..cb1f1a6a166d 100644 --- a/arch/mips/sgi-ip27/ip27-memory.c +++ b/arch/mips/sgi-ip27/ip27-memory.c @@ -475,7 +475,7 @@ void __init paging_init(void) void __init mem_init(void) { high_memory = (void *) __va(get_num_physpages() << PAGE_SHIFT); - free_all_bootmem(); + memblock_free_all(); setup_zero_pages(); /* This comes from node 0 */ mem_init_print_info(NULL); } diff --git a/arch/nds32/mm/init.c b/arch/nds32/mm/init.c index 5af81b866aa5..66d3e9cf498d 100644 --- a/arch/nds32/mm/init.c +++ b/arch/nds32/mm/init.c @@ -192,7 +192,7 @@ void __init mem_init(void) free_highmem(); /* this will put all low memory onto the freelists */ - free_all_bootmem(); + memblock_free_all(); mem_init_print_info(NULL); pr_info("virtual kernel memory layout:\n" diff --git a/arch/nios2/mm/init.c b/arch/nios2/mm/init.c index c92fe4234009..12923501d94f 100644 --- a/arch/nios2/mm/init.c +++ b/arch/nios2/mm/init.c @@ -73,7 +73,7 @@ void __init mem_init(void) high_memory = __va(end_mem); /* this will put all memory onto the freelists */ - free_all_bootmem(); + memblock_free_all(); mem_init_print_info(NULL); } diff --git a/arch/openrisc/mm/init.c b/arch/openrisc/mm/init.c index b7670de26c11..91a6a9ab7598 100644 --- a/arch/openrisc/mm/init.c +++ b/arch/openrisc/mm/init.c @@ -213,7 +213,7 @@ void __init mem_init(void) memset((void *)empty_zero_page, 0, PAGE_SIZE); /* this will put all low memory onto the freelists */ - free_all_bootmem(); + memblock_free_all(); mem_init_print_info(NULL); diff --git a/arch/parisc/mm/init.c b/arch/parisc/mm/init.c index f88a52b8531c..7e7a3126c5e9 100644 --- a/arch/parisc/mm/init.c +++ b/arch/parisc/mm/init.c @@ -621,7 +621,7 @@ void __init mem_init(void) high_memory = __va((max_pfn << PAGE_SHIFT)); set_max_mapnr(page_to_pfn(virt_to_page(high_memory - 1)) + 1); - free_all_bootmem(); + memblock_free_all(); #ifdef CONFIG_PA11 if (boot_cpu_data.cpu_type == pcxl2 || boot_cpu_data.cpu_type == pcxl) { diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c index dd949d6649a2..b3fe79064a69 100644 --- a/arch/powerpc/mm/mem.c +++ b/arch/powerpc/mm/mem.c @@ -349,7 +349,7 @@ void __init mem_init(void) high_memory = (void *) __va(max_low_pfn * PAGE_SIZE); set_max_mapnr(max_pfn); - free_all_bootmem(); + memblock_free_all(); #ifdef CONFIG_HIGHMEM { diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index 58a522f9bcc3..d58c111099b3 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -55,7 +55,7 @@ void __init mem_init(void) #endif /* CONFIG_FLATMEM */ high_memory = (void *)(__va(PFN_PHYS(max_low_pfn))); - free_all_bootmem(); + memblock_free_all(); mem_init_print_info(NULL); } diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c index 92d7a153e72a..873f6ee1c46d 100644 --- a/arch/s390/mm/init.c +++ b/arch/s390/mm/init.c @@ -139,7 +139,7 @@ void __init mem_init(void) cmma_init(); /* this will put all low memory onto the freelists */ - free_all_bootmem(); + memblock_free_all(); setup_zero_pages(); /* Setup zeroed pages. */ cmma_init_nodat(); diff --git a/arch/sh/mm/init.c b/arch/sh/mm/init.c index c884b760e52f..21447f866415 100644 --- a/arch/sh/mm/init.c +++ b/arch/sh/mm/init.c @@ -350,7 +350,7 @@ void __init mem_init(void) high_memory = max_t(void *, high_memory, __va(pgdat_end_pfn(pgdat) << PAGE_SHIFT)); - free_all_bootmem(); + memblock_free_all(); /* Set this up early, so we can take care of the zero page */ cpu_cache_init(); diff --git a/arch/sparc/mm/init_32.c b/arch/sparc/mm/init_32.c index 885dd3881874..880714565c40 100644 --- a/arch/sparc/mm/init_32.c +++ b/arch/sparc/mm/init_32.c @@ -277,7 +277,7 @@ void __init mem_init(void) max_mapnr = last_valid_pfn - pfn_base; high_memory = __va(max_low_pfn << PAGE_SHIFT); - free_all_bootmem(); + memblock_free_all(); for (i = 0; sp_banks[i].num_bytes != 0; i++) { unsigned long start_pfn = sp_banks[i].base_addr >> PAGE_SHIFT; diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c index 6f965e6d01cc..a8c3453195e6 100644 --- a/arch/sparc/mm/init_64.c +++ b/arch/sparc/mm/init_64.c @@ -2545,12 +2545,12 @@ void __init mem_init(void) { high_memory = __va(last_valid_pfn << PAGE_SHIFT); - free_all_bootmem(); + memblock_free_all(); /* * Must be done after boot memory is put on freelist, because here we * might set fields in deferred struct pages that have not yet been - * initialized, and free_all_bootmem() initializes all the reserved + * initialized, and memblock_free_all() initializes all the reserved * deferred pages for us. */ register_page_bootmem_info(); diff --git a/arch/um/kernel/mem.c b/arch/um/kernel/mem.c index 3555c139389c..2c672a8f4571 100644 --- a/arch/um/kernel/mem.c +++ b/arch/um/kernel/mem.c @@ -51,7 +51,7 @@ void __init mem_init(void) uml_reserved = brk_end; /* this will put all low memory onto the freelists */ - free_all_bootmem(); + memblock_free_all(); max_low_pfn = totalram_pages; max_pfn = totalram_pages; mem_init_print_info(NULL); diff --git a/arch/unicore32/mm/init.c b/arch/unicore32/mm/init.c index 4ba51991c7de..44fd0e8fbe87 100644 --- a/arch/unicore32/mm/init.c +++ b/arch/unicore32/mm/init.c @@ -286,7 +286,7 @@ void __init mem_init(void) free_unused_memmap(&meminfo); /* this will put all unused low memory onto the freelists */ - free_all_bootmem(); + memblock_free_all(); mem_init_print_info(NULL); printk(KERN_NOTICE "Virtual kernel memory layout:\n" diff --git a/arch/x86/mm/highmem_32.c b/arch/x86/mm/highmem_32.c index 6d18b70ed5a9..62915a5e0fa2 100644 --- a/arch/x86/mm/highmem_32.c +++ b/arch/x86/mm/highmem_32.c @@ -111,7 +111,7 @@ void __init set_highmem_pages_init(void) /* * Explicitly reset zone->managed_pages because set_highmem_pages_init() - * is invoked before free_all_bootmem() + * is invoked before memblock_free_all() */ reset_all_zones_managed_pages(); for_each_zone(zone) { diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c index 142c7d9f89cc..3bbe5f58a67d 100644 --- a/arch/x86/mm/init_32.c +++ b/arch/x86/mm/init_32.c @@ -771,7 +771,7 @@ void __init mem_init(void) #endif /* * With CONFIG_DEBUG_PAGEALLOC initialization of highmem pages has to - * be done before free_all_bootmem(). Memblock use free low memory for + * be done before memblock_free_all(). Memblock use free low memory for * temporary data (see find_range_array()) and for this purpose can use * pages that was already passed to the buddy allocator, hence marked as * not accessible in the page tables when compiled with @@ -781,7 +781,7 @@ void __init mem_init(void) set_highmem_pages_init(); /* this will put all low memory onto the freelists */ - free_all_bootmem(); + memblock_free_all(); after_bootmem = 1; x86_init.hyper.init_after_bootmem(); diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index f39b51244fe2..bfb0bedc21d3 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -1188,14 +1188,14 @@ void __init mem_init(void) /* clear_bss() already clear the empty_zero_page */ /* this will put all memory onto the freelists */ - free_all_bootmem(); + memblock_free_all(); after_bootmem = 1; x86_init.hyper.init_after_bootmem(); /* * Must be done after boot memory is put on freelist, because here we * might set fields in deferred struct pages that have not yet been - * initialized, and free_all_bootmem() initializes all the reserved + * initialized, and memblock_free_all() initializes all the reserved * deferred pages for us. */ register_page_bootmem_info(); diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c index 70ea598a37d2..0d7b3ae4960b 100644 --- a/arch/x86/xen/mmu_pv.c +++ b/arch/x86/xen/mmu_pv.c @@ -864,7 +864,7 @@ static int __init xen_mark_pinned(struct mm_struct *mm, struct page *page, * The init_mm pagetable is really pinned as soon as its created, but * that's before we have page structures to store the bits. So do all * the book-keeping now once struct pages for allocated pages are - * initialized. This happens only after free_all_bootmem() is called. + * initialized. This happens only after memblock_free_all() is called. */ static void __init xen_after_bootmem(void) { diff --git a/arch/xtensa/mm/init.c b/arch/xtensa/mm/init.c index 34aead7dcb48..f7fbe6334939 100644 --- a/arch/xtensa/mm/init.c +++ b/arch/xtensa/mm/init.c @@ -152,7 +152,7 @@ void __init mem_init(void) max_mapnr = max_pfn - ARCH_PFN_OFFSET; high_memory = (void *)__va(max_low_pfn << PAGE_SHIFT); - free_all_bootmem(); + memblock_free_all(); mem_init_print_info(NULL); pr_info("virtual kernel memory layout:\n" diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h index bcc7e2fcb6a6..b58873a567b2 100644 --- a/include/linux/bootmem.h +++ b/include/linux/bootmem.h @@ -26,7 +26,7 @@ extern unsigned long max_pfn; */ extern unsigned long long max_possible_pfn; -extern unsigned long free_all_bootmem(void); +extern unsigned long memblock_free_all(void); extern void reset_node_managed_pages(pg_data_t *pgdat); extern void reset_all_zones_managed_pages(void); diff --git a/mm/memblock.c b/mm/memblock.c index 58340de3ebc6..e2f397174734 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -1360,7 +1360,7 @@ static void * __init memblock_alloc_internal( /* * Detect any accidental use of these APIs after slab is ready, as at * this moment memblock may be deinitialized already and its - * internal data may be destroyed (after execution of free_all_bootmem) + * internal data may be destroyed (after execution of memblock_free_all) */ if (WARN_ON_ONCE(slab_is_available())) return kzalloc_node(size, GFP_NOWAIT, nid); diff --git a/mm/nobootmem.c b/mm/nobootmem.c index ee0f7fc37fd1..bb64b09ca4d2 100644 --- a/mm/nobootmem.c +++ b/mm/nobootmem.c @@ -111,11 +111,11 @@ void __init reset_all_zones_managed_pages(void) } /** - * free_all_bootmem - release free pages to the buddy allocator + * memblock_free_all - release free pages to the buddy allocator * * Return: the number of pages actually released. */ -unsigned long __init free_all_bootmem(void) +unsigned long __init memblock_free_all(void) { unsigned long pages; diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 8ca6954fdcdc..6e9b8387a706 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -5476,7 +5476,7 @@ overlap_memmap_init(unsigned long zone, unsigned long *pfn) /* * Initially all pages are reserved - free ones are freed - * up by free_all_bootmem() once the early boot process is + * up by memblock_free_all() once the early boot process is * done. Non-atomic initialization, single-pass. */ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone, diff --git a/mm/page_poison.c b/mm/page_poison.c index aa2b3d34e8ea..f7e2a676365a 100644 --- a/mm/page_poison.c +++ b/mm/page_poison.c @@ -21,7 +21,7 @@ bool page_poisoning_enabled(void) { /* * Assumes that debug_pagealloc_enabled is set before - * free_all_bootmem. + * memblock_free_all. * Page poisoning is debug page alloc for some arches. If * either of those options are enabled, enable poisoning. */ -- cgit v1.2.3 From 7c2ee349cf79b6348e833dd7d8167c4004a72ecb Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Tue, 30 Oct 2018 15:09:36 -0700 Subject: memblock: rename __free_pages_bootmem to memblock_free_pages The conversion is done using sed -i 's@__free_pages_bootmem@memblock_free_pages@' \ $(git grep -l __free_pages_bootmem) Link: http://lkml.kernel.org/r/1536927045-23536-27-git-send-email-rppt@linux.vnet.ibm.com Signed-off-by: Mike Rapoport Acked-by: Michal Hocko Cc: Catalin Marinas Cc: Chris Zankel Cc: "David S. Miller" Cc: Geert Uytterhoeven Cc: Greentime Hu Cc: Greg Kroah-Hartman Cc: Guan Xuetao Cc: Ingo Molnar Cc: "James E.J. Bottomley" Cc: Jonas Bonn Cc: Jonathan Corbet Cc: Ley Foon Tan Cc: Mark Salter Cc: Martin Schwidefsky Cc: Matt Turner Cc: Michael Ellerman Cc: Michal Simek Cc: Palmer Dabbelt Cc: Paul Burton Cc: Richard Kuo Cc: Richard Weinberger Cc: Rich Felker Cc: Russell King Cc: Serge Semin Cc: Thomas Gleixner Cc: Tony Luck Cc: Vineet Gupta Cc: Yoshinori Sato Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/internal.h | 2 +- mm/memblock.c | 2 +- mm/nobootmem.c | 2 +- mm/page_alloc.c | 2 +- 4 files changed, 4 insertions(+), 4 deletions(-) (limited to 'mm') diff --git a/mm/internal.h b/mm/internal.h index 87256ae1bef8..291eb2b6d1d8 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -161,7 +161,7 @@ static inline struct page *pageblock_pfn_to_page(unsigned long start_pfn, } extern int __isolate_free_page(struct page *page, unsigned int order); -extern void __free_pages_bootmem(struct page *page, unsigned long pfn, +extern void memblock_free_pages(struct page *page, unsigned long pfn, unsigned int order); extern void prep_compound_page(struct page *page, unsigned int order); extern void post_alloc_hook(struct page *page, unsigned int order, diff --git a/mm/memblock.c b/mm/memblock.c index e2f397174734..8b63a04e8cca 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -1563,7 +1563,7 @@ void __init __memblock_free_late(phys_addr_t base, phys_addr_t size) end = PFN_DOWN(base + size); for (; cursor < end; cursor++) { - __free_pages_bootmem(pfn_to_page(cursor), cursor, 0); + memblock_free_pages(pfn_to_page(cursor), cursor, 0); totalram_pages++; } } diff --git a/mm/nobootmem.c b/mm/nobootmem.c index bb64b09ca4d2..9608bc581cd6 100644 --- a/mm/nobootmem.c +++ b/mm/nobootmem.c @@ -43,7 +43,7 @@ static void __init __free_pages_memory(unsigned long start, unsigned long end) while (start + (1UL << order) > end) order--; - __free_pages_bootmem(pfn_to_page(start), start, order); + memblock_free_pages(pfn_to_page(start), start, order); start += (1UL << order); } diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 6e9b8387a706..5f3291601945 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1339,7 +1339,7 @@ meminit_pfn_in_nid(unsigned long pfn, int node, #endif -void __init __free_pages_bootmem(struct page *page, unsigned long pfn, +void __init memblock_free_pages(struct page *page, unsigned long pfn, unsigned int order) { if (early_page_uninitialised(pfn)) -- cgit v1.2.3 From bda49a81164ab3e62f5348447345711586fd42e9 Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Tue, 30 Oct 2018 15:09:40 -0700 Subject: mm: remove nobootmem Move a few remaining functions from nobootmem.c to memblock.c and remove nobootmem Link: http://lkml.kernel.org/r/1536927045-23536-28-git-send-email-rppt@linux.vnet.ibm.com Signed-off-by: Mike Rapoport Acked-by: Michal Hocko Cc: Catalin Marinas Cc: Chris Zankel Cc: "David S. Miller" Cc: Geert Uytterhoeven Cc: Greentime Hu Cc: Greg Kroah-Hartman Cc: Guan Xuetao Cc: Ingo Molnar Cc: "James E.J. Bottomley" Cc: Jonas Bonn Cc: Jonathan Corbet Cc: Ley Foon Tan Cc: Mark Salter Cc: Martin Schwidefsky Cc: Matt Turner Cc: Michael Ellerman Cc: Michal Simek Cc: Palmer Dabbelt Cc: Paul Burton Cc: Richard Kuo Cc: Richard Weinberger Cc: Rich Felker Cc: Russell King Cc: Serge Semin Cc: Thomas Gleixner Cc: Tony Luck Cc: Vineet Gupta Cc: Yoshinori Sato Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/Makefile | 1 - mm/memblock.c | 104 ++++++++++++++++++++++++++++++++++++++++++++++ mm/nobootmem.c | 128 --------------------------------------------------------- 3 files changed, 104 insertions(+), 129 deletions(-) delete mode 100644 mm/nobootmem.c (limited to 'mm') diff --git a/mm/Makefile b/mm/Makefile index ca3c844d7a56..d210cc9d6f80 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -42,7 +42,6 @@ obj-y := filemap.o mempool.o oom_kill.o fadvise.o \ debug.o $(mmu-y) obj-y += init-mm.o -obj-y += nobootmem.o obj-y += memblock.o ifdef CONFIG_MMU diff --git a/mm/memblock.c b/mm/memblock.c index 8b63a04e8cca..3dd9cfef996c 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -82,6 +82,16 @@ * initialization compltes. */ +#ifndef CONFIG_NEED_MULTIPLE_NODES +struct pglist_data __refdata contig_page_data; +EXPORT_SYMBOL(contig_page_data); +#endif + +unsigned long max_low_pfn; +unsigned long min_low_pfn; +unsigned long max_pfn; +unsigned long long max_possible_pfn; + static struct memblock_region memblock_memory_init_regions[INIT_MEMBLOCK_REGIONS] __initdata_memblock; static struct memblock_region memblock_reserved_init_regions[INIT_MEMBLOCK_REGIONS] __initdata_memblock; #ifdef CONFIG_HAVE_MEMBLOCK_PHYS_MAP @@ -1877,6 +1887,100 @@ static int __init early_memblock(char *p) } early_param("memblock", early_memblock); +static void __init __free_pages_memory(unsigned long start, unsigned long end) +{ + int order; + + while (start < end) { + order = min(MAX_ORDER - 1UL, __ffs(start)); + + while (start + (1UL << order) > end) + order--; + + memblock_free_pages(pfn_to_page(start), start, order); + + start += (1UL << order); + } +} + +static unsigned long __init __free_memory_core(phys_addr_t start, + phys_addr_t end) +{ + unsigned long start_pfn = PFN_UP(start); + unsigned long end_pfn = min_t(unsigned long, + PFN_DOWN(end), max_low_pfn); + + if (start_pfn >= end_pfn) + return 0; + + __free_pages_memory(start_pfn, end_pfn); + + return end_pfn - start_pfn; +} + +static unsigned long __init free_low_memory_core_early(void) +{ + unsigned long count = 0; + phys_addr_t start, end; + u64 i; + + memblock_clear_hotplug(0, -1); + + for_each_reserved_mem_region(i, &start, &end) + reserve_bootmem_region(start, end); + + /* + * We need to use NUMA_NO_NODE instead of NODE_DATA(0)->node_id + * because in some case like Node0 doesn't have RAM installed + * low ram will be on Node1 + */ + for_each_free_mem_range(i, NUMA_NO_NODE, MEMBLOCK_NONE, &start, &end, + NULL) + count += __free_memory_core(start, end); + + return count; +} + +static int reset_managed_pages_done __initdata; + +void reset_node_managed_pages(pg_data_t *pgdat) +{ + struct zone *z; + + for (z = pgdat->node_zones; z < pgdat->node_zones + MAX_NR_ZONES; z++) + z->managed_pages = 0; +} + +void __init reset_all_zones_managed_pages(void) +{ + struct pglist_data *pgdat; + + if (reset_managed_pages_done) + return; + + for_each_online_pgdat(pgdat) + reset_node_managed_pages(pgdat); + + reset_managed_pages_done = 1; +} + +/** + * memblock_free_all - release free pages to the buddy allocator + * + * Return: the number of pages actually released. + */ +unsigned long __init memblock_free_all(void) +{ + unsigned long pages; + + reset_all_zones_managed_pages(); + + pages = free_low_memory_core_early(); + totalram_pages += pages; + + return pages; +} + #if defined(CONFIG_DEBUG_FS) && !defined(CONFIG_ARCH_DISCARD_MEMBLOCK) static int memblock_debug_show(struct seq_file *m, void *private) diff --git a/mm/nobootmem.c b/mm/nobootmem.c deleted file mode 100644 index 9608bc581cd6..000000000000 --- a/mm/nobootmem.c +++ /dev/null @@ -1,128 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * bootmem - A boot-time physical memory allocator and configurator - * - * Copyright (C) 1999 Ingo Molnar - * 1999 Kanoj Sarcar, SGI - * 2008 Johannes Weiner - * - * Access to this subsystem has to be serialized externally (which is true - * for the boot process anyway). - */ -#include -#include -#include -#include -#include -#include -#include -#include - -#include -#include - -#include "internal.h" - -#ifndef CONFIG_NEED_MULTIPLE_NODES -struct pglist_data __refdata contig_page_data; -EXPORT_SYMBOL(contig_page_data); -#endif - -unsigned long max_low_pfn; -unsigned long min_low_pfn; -unsigned long max_pfn; -unsigned long long max_possible_pfn; - -static void __init __free_pages_memory(unsigned long start, unsigned long end) -{ - int order; - - while (start < end) { - order = min(MAX_ORDER - 1UL, __ffs(start)); - - while (start + (1UL << order) > end) - order--; - - memblock_free_pages(pfn_to_page(start), start, order); - - start += (1UL << order); - } -} - -static unsigned long __init __free_memory_core(phys_addr_t start, - phys_addr_t end) -{ - unsigned long start_pfn = PFN_UP(start); - unsigned long end_pfn = min_t(unsigned long, - PFN_DOWN(end), max_low_pfn); - - if (start_pfn >= end_pfn) - return 0; - - __free_pages_memory(start_pfn, end_pfn); - - return end_pfn - start_pfn; -} - -static unsigned long __init free_low_memory_core_early(void) -{ - unsigned long count = 0; - phys_addr_t start, end; - u64 i; - - memblock_clear_hotplug(0, -1); - - for_each_reserved_mem_region(i, &start, &end) - reserve_bootmem_region(start, end); - - /* - * We need to use NUMA_NO_NODE instead of NODE_DATA(0)->node_id - * because in some case like Node0 doesn't have RAM installed - * low ram will be on Node1 - */ - for_each_free_mem_range(i, NUMA_NO_NODE, MEMBLOCK_NONE, &start, &end, - NULL) - count += __free_memory_core(start, end); - - return count; -} - -static int reset_managed_pages_done __initdata; - -void reset_node_managed_pages(pg_data_t *pgdat) -{ - struct zone *z; - - for (z = pgdat->node_zones; z < pgdat->node_zones + MAX_NR_ZONES; z++) - z->managed_pages = 0; -} - -void __init reset_all_zones_managed_pages(void) -{ - struct pglist_data *pgdat; - - if (reset_managed_pages_done) - return; - - for_each_online_pgdat(pgdat) - reset_node_managed_pages(pgdat); - - reset_managed_pages_done = 1; -} - -/** - * memblock_free_all - release free pages to the buddy allocator - * - * Return: the number of pages actually released. - */ -unsigned long __init memblock_free_all(void) -{ - unsigned long pages; - - reset_all_zones_managed_pages(); - - pages = free_low_memory_core_early(); - totalram_pages += pages; - - return pages; -} -- cgit v1.2.3 From 97ad1087efffed26cb00e310a927f9603332dfcb Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Tue, 30 Oct 2018 15:09:44 -0700 Subject: memblock: replace BOOTMEM_ALLOC_* with MEMBLOCK variants Drop BOOTMEM_ALLOC_ACCESSIBLE and BOOTMEM_ALLOC_ANYWHERE in favor of identical MEMBLOCK definitions. Link: http://lkml.kernel.org/r/1536927045-23536-29-git-send-email-rppt@linux.vnet.ibm.com Signed-off-by: Mike Rapoport Acked-by: Michal Hocko Cc: Catalin Marinas Cc: Chris Zankel Cc: "David S. Miller" Cc: Geert Uytterhoeven Cc: Greentime Hu Cc: Greg Kroah-Hartman Cc: Guan Xuetao Cc: Ingo Molnar Cc: "James E.J. Bottomley" Cc: Jonas Bonn Cc: Jonathan Corbet Cc: Ley Foon Tan Cc: Mark Salter Cc: Martin Schwidefsky Cc: Matt Turner Cc: Michael Ellerman Cc: Michal Simek Cc: Palmer Dabbelt Cc: Paul Burton Cc: Richard Kuo Cc: Richard Weinberger Cc: Rich Felker Cc: Russell King Cc: Serge Semin Cc: Thomas Gleixner Cc: Tony Luck Cc: Vineet Gupta Cc: Yoshinori Sato Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/ia64/mm/discontig.c | 2 +- arch/powerpc/kernel/setup_64.c | 2 +- arch/sparc/kernel/smp_64.c | 2 +- arch/x86/kernel/setup_percpu.c | 2 +- arch/x86/mm/kasan_init_64.c | 4 ++-- mm/hugetlb.c | 3 ++- mm/kasan/kasan_init.c | 2 +- mm/memblock.c | 8 ++++---- mm/page_ext.c | 2 +- mm/sparse-vmemmap.c | 3 ++- mm/sparse.c | 5 +++-- 11 files changed, 19 insertions(+), 16 deletions(-) (limited to 'mm') diff --git a/arch/ia64/mm/discontig.c b/arch/ia64/mm/discontig.c index 918dda972975..70609f823960 100644 --- a/arch/ia64/mm/discontig.c +++ b/arch/ia64/mm/discontig.c @@ -453,7 +453,7 @@ static void __init *memory_less_node_alloc(int nid, unsigned long pernodesize) ptr = memblock_alloc_try_nid(pernodesize, PERCPU_PAGE_SIZE, __pa(MAX_DMA_ADDRESS), - BOOTMEM_ALLOC_ACCESSIBLE, + MEMBLOCK_ALLOC_ACCESSIBLE, bestnode); return ptr; diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index f90ab3ea9af3..9216c3a7fcfc 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -764,7 +764,7 @@ void __init emergency_stack_init(void) static void * __init pcpu_fc_alloc(unsigned int cpu, size_t size, size_t align) { return memblock_alloc_try_nid(size, align, __pa(MAX_DMA_ADDRESS), - BOOTMEM_ALLOC_ACCESSIBLE, + MEMBLOCK_ALLOC_ACCESSIBLE, early_cpu_to_node(cpu)); } diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c index a087a6a25f06..6cc80d0f4b9f 100644 --- a/arch/sparc/kernel/smp_64.c +++ b/arch/sparc/kernel/smp_64.c @@ -1595,7 +1595,7 @@ static void * __init pcpu_alloc_bootmem(unsigned int cpu, size_t size, cpu, size, __pa(ptr)); } else { ptr = memblock_alloc_try_nid(size, align, goal, - BOOTMEM_ALLOC_ACCESSIBLE, node); + MEMBLOCK_ALLOC_ACCESSIBLE, node); pr_debug("per cpu data for cpu%d %lu bytes on node%d at " "%016lx\n", cpu, size, node, __pa(ptr)); } diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c index a006f1ba4c39..483412fb8a24 100644 --- a/arch/x86/kernel/setup_percpu.c +++ b/arch/x86/kernel/setup_percpu.c @@ -114,7 +114,7 @@ static void * __init pcpu_alloc_bootmem(unsigned int cpu, unsigned long size, cpu, size, __pa(ptr)); } else { ptr = memblock_alloc_try_nid_nopanic(size, align, goal, - BOOTMEM_ALLOC_ACCESSIBLE, + MEMBLOCK_ALLOC_ACCESSIBLE, node); pr_debug("per cpu data for cpu%d %lu bytes on node%d at %016lx\n", diff --git a/arch/x86/mm/kasan_init_64.c b/arch/x86/mm/kasan_init_64.c index 77b857cb036f..8f87499124b8 100644 --- a/arch/x86/mm/kasan_init_64.c +++ b/arch/x86/mm/kasan_init_64.c @@ -29,10 +29,10 @@ static __init void *early_alloc(size_t size, int nid, bool panic) { if (panic) return memblock_alloc_try_nid(size, size, - __pa(MAX_DMA_ADDRESS), BOOTMEM_ALLOC_ACCESSIBLE, nid); + __pa(MAX_DMA_ADDRESS), MEMBLOCK_ALLOC_ACCESSIBLE, nid); else return memblock_alloc_try_nid_nopanic(size, size, - __pa(MAX_DMA_ADDRESS), BOOTMEM_ALLOC_ACCESSIBLE, nid); + __pa(MAX_DMA_ADDRESS), MEMBLOCK_ALLOC_ACCESSIBLE, nid); } static void __init kasan_populate_pmd(pmd_t *pmd, unsigned long addr, diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 51e9f17dbd5c..e35d99844612 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -16,6 +16,7 @@ #include #include #include +#include #include #include #include @@ -2102,7 +2103,7 @@ int __alloc_bootmem_huge_page(struct hstate *h) addr = memblock_alloc_try_nid_raw( huge_page_size(h), huge_page_size(h), - 0, BOOTMEM_ALLOC_ACCESSIBLE, node); + 0, MEMBLOCK_ALLOC_ACCESSIBLE, node); if (addr) { /* * Use the beginning of the huge page to store the diff --git a/mm/kasan/kasan_init.c b/mm/kasan/kasan_init.c index 24d734bdff6b..785a9707786b 100644 --- a/mm/kasan/kasan_init.c +++ b/mm/kasan/kasan_init.c @@ -84,7 +84,7 @@ static inline bool kasan_zero_page_entry(pte_t pte) static __init void *early_alloc(size_t size, int node) { return memblock_alloc_try_nid(size, size, __pa(MAX_DMA_ADDRESS), - BOOTMEM_ALLOC_ACCESSIBLE, node); + MEMBLOCK_ALLOC_ACCESSIBLE, node); } static void __ref zero_pte_populate(pmd_t *pmd, unsigned long addr, diff --git a/mm/memblock.c b/mm/memblock.c index 3dd9cfef996c..2ed73245b5da 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -1342,7 +1342,7 @@ phys_addr_t __init memblock_phys_alloc_try_nid(phys_addr_t size, phys_addr_t ali * hold the requested memory. * * The allocation is performed from memory region limited by - * memblock.current_limit if @max_addr == %BOOTMEM_ALLOC_ACCESSIBLE. + * memblock.current_limit if @max_addr == %MEMBLOCK_ALLOC_ACCESSIBLE. * * The memory block is aligned on %SMP_CACHE_BYTES if @align == 0. * @@ -1429,7 +1429,7 @@ done: * @min_addr: the lower bound of the memory region from where the allocation * is preferred (phys address) * @max_addr: the upper bound of the memory region from where the allocation - * is preferred (phys address), or %BOOTMEM_ALLOC_ACCESSIBLE to + * is preferred (phys address), or %MEMBLOCK_ALLOC_ACCESSIBLE to * allocate only from memory limited by memblock.current_limit value * @nid: nid of the free area to find, %NUMA_NO_NODE for any node * @@ -1466,7 +1466,7 @@ void * __init memblock_alloc_try_nid_raw( * @min_addr: the lower bound of the memory region from where the allocation * is preferred (phys address) * @max_addr: the upper bound of the memory region from where the allocation - * is preferred (phys address), or %BOOTMEM_ALLOC_ACCESSIBLE to + * is preferred (phys address), or %MEMBLOCK_ALLOC_ACCESSIBLE to * allocate only from memory limited by memblock.current_limit value * @nid: nid of the free area to find, %NUMA_NO_NODE for any node * @@ -1501,7 +1501,7 @@ void * __init memblock_alloc_try_nid_nopanic( * @min_addr: the lower bound of the memory region from where the allocation * is preferred (phys address) * @max_addr: the upper bound of the memory region from where the allocation - * is preferred (phys address), or %BOOTMEM_ALLOC_ACCESSIBLE to + * is preferred (phys address), or %MEMBLOCK_ALLOC_ACCESSIBLE to * allocate only from memory limited by memblock.current_limit value * @nid: nid of the free area to find, %NUMA_NO_NODE for any node * diff --git a/mm/page_ext.c b/mm/page_ext.c index e77c0f031dd0..5323c2ade686 100644 --- a/mm/page_ext.c +++ b/mm/page_ext.c @@ -163,7 +163,7 @@ static int __init alloc_node_page_ext(int nid) base = memblock_alloc_try_nid_nopanic( table_size, PAGE_SIZE, __pa(MAX_DMA_ADDRESS), - BOOTMEM_ALLOC_ACCESSIBLE, nid); + MEMBLOCK_ALLOC_ACCESSIBLE, nid); if (!base) return -ENOMEM; NODE_DATA(nid)->node_page_ext = base; diff --git a/mm/sparse-vmemmap.c b/mm/sparse-vmemmap.c index 91c2c3d25827..7408cabed61a 100644 --- a/mm/sparse-vmemmap.c +++ b/mm/sparse-vmemmap.c @@ -21,6 +21,7 @@ #include #include #include +#include #include #include #include @@ -43,7 +44,7 @@ static void * __ref __earlyonly_bootmem_alloc(int node, unsigned long goal) { return memblock_alloc_try_nid_raw(size, align, goal, - BOOTMEM_ALLOC_ACCESSIBLE, node); + MEMBLOCK_ALLOC_ACCESSIBLE, node); } void * __meminit vmemmap_alloc_block(unsigned long size, int node) diff --git a/mm/sparse.c b/mm/sparse.c index d1296610562b..b139fbc61d10 100644 --- a/mm/sparse.c +++ b/mm/sparse.c @@ -6,6 +6,7 @@ #include #include #include +#include #include #include #include @@ -393,7 +394,7 @@ struct page __init *sparse_mem_map_populate(unsigned long pnum, int nid, map = memblock_alloc_try_nid(size, PAGE_SIZE, __pa(MAX_DMA_ADDRESS), - BOOTMEM_ALLOC_ACCESSIBLE, nid); + MEMBLOCK_ALLOC_ACCESSIBLE, nid); return map; } #endif /* !CONFIG_SPARSEMEM_VMEMMAP */ @@ -407,7 +408,7 @@ static void __init sparse_buffer_init(unsigned long size, int nid) sparsemap_buf = memblock_alloc_try_nid_raw(size, PAGE_SIZE, __pa(MAX_DMA_ADDRESS), - BOOTMEM_ALLOC_ACCESSIBLE, nid); + MEMBLOCK_ALLOC_ACCESSIBLE, nid); sparsemap_buf_end = sparsemap_buf + size; } -- cgit v1.2.3 From 57c8a661d95dff48dd9c2f2496139082bbaf241a Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Tue, 30 Oct 2018 15:09:49 -0700 Subject: mm: remove include/linux/bootmem.h Move remaining definitions and declarations from include/linux/bootmem.h into include/linux/memblock.h and remove the redundant header. The includes were replaced with the semantic patch below and then semi-automated removal of duplicated '#include @@ @@ - #include + #include [sfr@canb.auug.org.au: dma-direct: fix up for the removal of linux/bootmem.h] Link: http://lkml.kernel.org/r/20181002185342.133d1680@canb.auug.org.au [sfr@canb.auug.org.au: powerpc: fix up for removal of linux/bootmem.h] Link: http://lkml.kernel.org/r/20181005161406.73ef8727@canb.auug.org.au [sfr@canb.auug.org.au: x86/kaslr, ACPI/NUMA: fix for linux/bootmem.h removal] Link: http://lkml.kernel.org/r/20181008190341.5e396491@canb.auug.org.au Link: http://lkml.kernel.org/r/1536927045-23536-30-git-send-email-rppt@linux.vnet.ibm.com Signed-off-by: Mike Rapoport Signed-off-by: Stephen Rothwell Acked-by: Michal Hocko Cc: Catalin Marinas Cc: Chris Zankel Cc: "David S. Miller" Cc: Geert Uytterhoeven Cc: Greentime Hu Cc: Greg Kroah-Hartman Cc: Guan Xuetao Cc: Ingo Molnar Cc: "James E.J. Bottomley" Cc: Jonas Bonn Cc: Jonathan Corbet Cc: Ley Foon Tan Cc: Mark Salter Cc: Martin Schwidefsky Cc: Matt Turner Cc: Michael Ellerman Cc: Michal Simek Cc: Palmer Dabbelt Cc: Paul Burton Cc: Richard Kuo Cc: Richard Weinberger Cc: Rich Felker Cc: Russell King Cc: Serge Semin Cc: Thomas Gleixner Cc: Tony Luck Cc: Vineet Gupta Cc: Yoshinori Sato Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/alpha/kernel/core_cia.c | 2 +- arch/alpha/kernel/core_irongate.c | 1 - arch/alpha/kernel/core_marvel.c | 2 +- arch/alpha/kernel/core_titan.c | 2 +- arch/alpha/kernel/core_tsunami.c | 2 +- arch/alpha/kernel/pci-noop.c | 2 +- arch/alpha/kernel/pci.c | 2 +- arch/alpha/kernel/pci_iommu.c | 2 +- arch/alpha/kernel/setup.c | 1 - arch/alpha/kernel/sys_nautilus.c | 2 +- arch/alpha/mm/init.c | 2 +- arch/alpha/mm/numa.c | 1 - arch/arc/kernel/unwind.c | 2 +- arch/arc/mm/highmem.c | 2 +- arch/arc/mm/init.c | 1 - arch/arm/kernel/devtree.c | 1 - arch/arm/kernel/setup.c | 1 - arch/arm/mach-omap2/omap_hwmod.c | 2 +- arch/arm/mm/dma-mapping.c | 1 - arch/arm/mm/init.c | 1 - arch/arm/xen/mm.c | 1 - arch/arm/xen/p2m.c | 2 +- arch/arm64/kernel/acpi.c | 1 - arch/arm64/kernel/acpi_numa.c | 1 - arch/arm64/kernel/setup.c | 1 - arch/arm64/mm/dma-mapping.c | 2 +- arch/arm64/mm/init.c | 1 - arch/arm64/mm/kasan_init.c | 1 - arch/arm64/mm/numa.c | 1 - arch/c6x/kernel/setup.c | 1 - arch/c6x/mm/init.c | 2 +- arch/h8300/kernel/setup.c | 1 - arch/h8300/mm/init.c | 2 +- arch/hexagon/kernel/dma.c | 2 +- arch/hexagon/kernel/setup.c | 2 +- arch/hexagon/mm/init.c | 1 - arch/ia64/kernel/crash.c | 2 +- arch/ia64/kernel/efi.c | 2 +- arch/ia64/kernel/ia64_ksyms.c | 2 +- arch/ia64/kernel/iosapic.c | 2 +- arch/ia64/kernel/mca.c | 2 +- arch/ia64/kernel/mca_drv.c | 2 +- arch/ia64/kernel/setup.c | 1 - arch/ia64/kernel/smpboot.c | 2 +- arch/ia64/kernel/topology.c | 2 +- arch/ia64/kernel/unwind.c | 2 +- arch/ia64/mm/contig.c | 1 - arch/ia64/mm/discontig.c | 1 - arch/ia64/mm/init.c | 1 - arch/ia64/mm/numa.c | 2 +- arch/ia64/mm/tlb.c | 2 +- arch/ia64/pci/pci.c | 2 +- arch/ia64/sn/kernel/bte.c | 2 +- arch/ia64/sn/kernel/io_common.c | 2 +- arch/ia64/sn/kernel/setup.c | 2 +- arch/m68k/atari/stram.c | 2 +- arch/m68k/coldfire/m54xx.c | 2 +- arch/m68k/kernel/setup_mm.c | 1 - arch/m68k/kernel/setup_no.c | 1 - arch/m68k/kernel/uboot.c | 2 +- arch/m68k/mm/init.c | 2 +- arch/m68k/mm/mcfmmu.c | 1 - arch/m68k/mm/motorola.c | 1 - arch/m68k/mm/sun3mmu.c | 2 +- arch/m68k/sun3/config.c | 2 +- arch/m68k/sun3/dvma.c | 2 +- arch/m68k/sun3/mmu_emu.c | 2 +- arch/m68k/sun3/sun3dvma.c | 2 +- arch/m68k/sun3x/dvma.c | 2 +- arch/microblaze/mm/consistent.c | 2 +- arch/microblaze/mm/init.c | 3 +- arch/microblaze/pci/pci-common.c | 2 +- arch/mips/ar7/memory.c | 2 +- arch/mips/ath79/setup.c | 2 +- arch/mips/bcm63xx/prom.c | 2 +- arch/mips/bcm63xx/setup.c | 2 +- arch/mips/bmips/setup.c | 2 +- arch/mips/cavium-octeon/dma-octeon.c | 2 +- arch/mips/dec/prom/memory.c | 2 +- arch/mips/emma/common/prom.c | 2 +- arch/mips/fw/arc/memory.c | 2 +- arch/mips/jazz/jazzdma.c | 2 +- arch/mips/kernel/crash.c | 2 +- arch/mips/kernel/crash_dump.c | 2 +- arch/mips/kernel/prom.c | 2 +- arch/mips/kernel/setup.c | 1 - arch/mips/kernel/traps.c | 1 - arch/mips/kernel/vpe.c | 2 +- arch/mips/kvm/commpage.c | 2 +- arch/mips/kvm/dyntrans.c | 2 +- arch/mips/kvm/emulate.c | 2 +- arch/mips/kvm/interrupt.c | 2 +- arch/mips/kvm/mips.c | 2 +- arch/mips/lantiq/prom.c | 2 +- arch/mips/lasat/prom.c | 2 +- arch/mips/loongson64/common/init.c | 2 +- arch/mips/loongson64/loongson-3/numa.c | 1 - arch/mips/mm/init.c | 2 +- arch/mips/mm/pgtable-32.c | 2 +- arch/mips/mti-malta/malta-memory.c | 2 +- arch/mips/netlogic/xlp/dt.c | 2 +- arch/mips/pci/pci-legacy.c | 2 +- arch/mips/pci/pci.c | 2 +- arch/mips/ralink/of.c | 2 +- arch/mips/rb532/prom.c | 2 +- arch/mips/sgi-ip27/ip27-memory.c | 1 - arch/mips/sibyte/common/cfe.c | 2 +- arch/mips/sibyte/swarm/setup.c | 2 +- arch/mips/txx9/rbtx4938/prom.c | 2 +- arch/nds32/kernel/setup.c | 3 +- arch/nds32/mm/highmem.c | 2 +- arch/nds32/mm/init.c | 3 +- arch/nios2/kernel/prom.c | 2 +- arch/nios2/kernel/setup.c | 1 - arch/nios2/mm/init.c | 2 +- arch/openrisc/kernel/setup.c | 3 +- arch/openrisc/mm/init.c | 3 +- arch/parisc/mm/init.c | 1 - arch/powerpc/kernel/pci_32.c | 2 +- arch/powerpc/kernel/setup-common.c | 1 - arch/powerpc/kernel/setup_64.c | 3 +- arch/powerpc/lib/alloc.c | 2 +- arch/powerpc/mm/hugetlbpage.c | 1 - arch/powerpc/mm/mem.c | 3 +- arch/powerpc/mm/mmu_context_nohash.c | 2 +- arch/powerpc/mm/numa.c | 3 +- arch/powerpc/platforms/powermac/nvram.c | 2 +- arch/powerpc/platforms/powernv/pci-ioda.c | 3 +- arch/powerpc/platforms/ps3/setup.c | 2 +- arch/powerpc/sysdev/msi_bitmap.c | 2 +- arch/riscv/mm/init.c | 3 +- arch/s390/kernel/crash_dump.c | 3 +- arch/s390/kernel/setup.c | 1 - arch/s390/kernel/smp.c | 3 +- arch/s390/kernel/topology.c | 2 +- arch/s390/kernel/vdso.c | 2 +- arch/s390/mm/extmem.c | 2 +- arch/s390/mm/init.c | 3 +- arch/s390/mm/vmem.c | 3 +- arch/s390/numa/mode_emu.c | 1 - arch/s390/numa/numa.c | 1 - arch/s390/numa/toptree.c | 2 +- arch/sh/mm/init.c | 3 +- arch/sh/mm/ioremap_fixed.c | 2 +- arch/sparc/kernel/mdesc.c | 2 - arch/sparc/kernel/prom_32.c | 2 +- arch/sparc/kernel/setup_64.c | 2 +- arch/sparc/kernel/smp_64.c | 2 +- arch/sparc/mm/init_32.c | 1 - arch/sparc/mm/init_64.c | 3 +- arch/sparc/mm/srmmu.c | 2 +- arch/um/drivers/net_kern.c | 2 +- arch/um/drivers/vector_kern.c | 2 +- arch/um/kernel/initrd.c | 2 +- arch/um/kernel/mem.c | 1 - arch/um/kernel/physmem.c | 1 - arch/unicore32/kernel/hibernate.c | 2 +- arch/unicore32/kernel/setup.c | 3 +- arch/unicore32/mm/init.c | 3 +- arch/unicore32/mm/mmu.c | 1 - arch/x86/kernel/acpi/boot.c | 2 +- arch/x86/kernel/acpi/sleep.c | 1 - arch/x86/kernel/apic/apic.c | 2 +- arch/x86/kernel/apic/io_apic.c | 2 +- arch/x86/kernel/cpu/common.c | 2 +- arch/x86/kernel/e820.c | 3 +- arch/x86/kernel/mpparse.c | 1 - arch/x86/kernel/pci-dma.c | 2 +- arch/x86/kernel/pci-swiotlb.c | 2 +- arch/x86/kernel/pvclock.c | 2 +- arch/x86/kernel/setup.c | 1 - arch/x86/kernel/setup_percpu.c | 1 - arch/x86/kernel/smpboot.c | 2 +- arch/x86/kernel/tce_64.c | 1 - arch/x86/mm/amdtopology.c | 1 - arch/x86/mm/fault.c | 2 +- arch/x86/mm/highmem_32.c | 2 +- arch/x86/mm/init.c | 1 - arch/x86/mm/init_32.c | 1 - arch/x86/mm/init_64.c | 1 - arch/x86/mm/ioremap.c | 2 +- arch/x86/mm/kasan_init_64.c | 3 +- arch/x86/mm/kaslr.c | 1 + arch/x86/mm/numa.c | 1 - arch/x86/mm/numa_32.c | 1 - arch/x86/mm/numa_64.c | 2 +- arch/x86/mm/numa_emulation.c | 1 - arch/x86/mm/pageattr-test.c | 2 +- arch/x86/mm/pageattr.c | 2 +- arch/x86/mm/pat.c | 2 +- arch/x86/mm/physaddr.c | 2 +- arch/x86/pci/i386.c | 2 +- arch/x86/platform/efi/efi.c | 3 +- arch/x86/platform/efi/efi_64.c | 2 +- arch/x86/platform/efi/quirks.c | 1 - arch/x86/platform/olpc/olpc_dt.c | 2 +- arch/x86/power/hibernate_32.c | 2 +- arch/x86/xen/enlighten.c | 2 +- arch/x86/xen/enlighten_pv.c | 3 +- arch/x86/xen/p2m.c | 1 - arch/xtensa/kernel/pci.c | 2 +- arch/xtensa/mm/cache.c | 2 +- arch/xtensa/mm/init.c | 2 +- arch/xtensa/mm/kasan_init.c | 3 +- arch/xtensa/mm/mmu.c | 2 +- arch/xtensa/platforms/iss/network.c | 2 +- arch/xtensa/platforms/iss/setup.c | 2 +- block/blk-settings.c | 2 +- block/bounce.c | 2 +- drivers/acpi/numa.c | 1 - drivers/acpi/tables.c | 3 +- drivers/base/platform.c | 2 +- drivers/clk/ti/clk.c | 2 +- drivers/firmware/dmi_scan.c | 2 +- drivers/firmware/efi/apple-properties.c | 2 +- drivers/firmware/iscsi_ibft_find.c | 2 +- drivers/firmware/memmap.c | 2 +- drivers/iommu/mtk_iommu.c | 2 +- drivers/iommu/mtk_iommu_v1.c | 2 +- drivers/macintosh/smu.c | 3 +- drivers/mtd/ar7part.c | 2 +- drivers/net/arcnet/arc-rimi.c | 2 +- drivers/net/arcnet/com20020-isa.c | 2 +- drivers/net/arcnet/com90io.c | 2 +- drivers/of/fdt.c | 1 - drivers/of/unittest.c | 2 +- drivers/s390/char/fs3270.c | 2 +- drivers/s390/char/tty3270.c | 2 +- drivers/s390/cio/cmf.c | 2 +- drivers/s390/virtio/virtio_ccw.c | 2 +- drivers/sfi/sfi_core.c | 2 +- drivers/tty/serial/cpm_uart/cpm_uart_core.c | 2 +- drivers/tty/serial/cpm_uart/cpm_uart_cpm1.c | 2 +- drivers/tty/serial/cpm_uart/cpm_uart_cpm2.c | 2 +- drivers/usb/early/xhci-dbc.c | 1 - drivers/xen/balloon.c | 2 +- drivers/xen/events/events_base.c | 2 +- drivers/xen/grant-table.c | 2 +- drivers/xen/swiotlb-xen.c | 1 - drivers/xen/xen-selfballoon.c | 2 +- fs/dcache.c | 2 +- fs/inode.c | 2 +- fs/namespace.c | 2 +- fs/proc/kcore.c | 2 +- fs/proc/page.c | 2 +- fs/proc/vmcore.c | 2 +- include/linux/bootmem.h | 173 ---------------------------- include/linux/memblock.h | 151 +++++++++++++++++++++++- init/main.c | 2 +- kernel/dma/direct.c | 2 +- kernel/dma/swiotlb.c | 2 +- kernel/futex.c | 2 +- kernel/locking/qspinlock_paravirt.h | 2 +- kernel/pid.c | 2 +- kernel/power/snapshot.c | 2 +- kernel/printk/printk.c | 1 - kernel/profile.c | 2 +- lib/cpumask.c | 2 +- mm/hugetlb.c | 1 - mm/kasan/kasan_init.c | 3 +- mm/kmemleak.c | 2 +- mm/memblock.c | 1 - mm/memory_hotplug.c | 1 - mm/page_alloc.c | 1 - mm/page_ext.c | 2 +- mm/page_idle.c | 2 +- mm/page_owner.c | 2 +- mm/percpu.c | 2 +- mm/sparse-vmemmap.c | 1 - mm/sparse.c | 1 - net/ipv4/inet_hashtables.c | 2 +- net/ipv4/tcp.c | 2 +- net/ipv4/udp.c | 2 +- net/sctp/protocol.c | 2 +- net/xfrm/xfrm_hash.c | 2 +- 275 files changed, 353 insertions(+), 476 deletions(-) delete mode 100644 include/linux/bootmem.h (limited to 'mm') diff --git a/arch/alpha/kernel/core_cia.c b/arch/alpha/kernel/core_cia.c index 026ee955fd10..867e8730b0c5 100644 --- a/arch/alpha/kernel/core_cia.c +++ b/arch/alpha/kernel/core_cia.c @@ -21,7 +21,7 @@ #include #include #include -#include +#include #include #include diff --git a/arch/alpha/kernel/core_irongate.c b/arch/alpha/kernel/core_irongate.c index 35572be9deb5..a9fd133a7fb2 100644 --- a/arch/alpha/kernel/core_irongate.c +++ b/arch/alpha/kernel/core_irongate.c @@ -20,7 +20,6 @@ #include #include #include -#include #include #include diff --git a/arch/alpha/kernel/core_marvel.c b/arch/alpha/kernel/core_marvel.c index 1f00c9433b10..8a568c4d8e81 100644 --- a/arch/alpha/kernel/core_marvel.c +++ b/arch/alpha/kernel/core_marvel.c @@ -18,7 +18,7 @@ #include #include #include -#include +#include #include #include diff --git a/arch/alpha/kernel/core_titan.c b/arch/alpha/kernel/core_titan.c index 132b06bdf903..97551597581b 100644 --- a/arch/alpha/kernel/core_titan.c +++ b/arch/alpha/kernel/core_titan.c @@ -16,7 +16,7 @@ #include #include #include -#include +#include #include #include diff --git a/arch/alpha/kernel/core_tsunami.c b/arch/alpha/kernel/core_tsunami.c index e7c956ea46b6..f334b8928d72 100644 --- a/arch/alpha/kernel/core_tsunami.c +++ b/arch/alpha/kernel/core_tsunami.c @@ -17,7 +17,7 @@ #include #include #include -#include +#include #include #include diff --git a/arch/alpha/kernel/pci-noop.c b/arch/alpha/kernel/pci-noop.c index 59cbfc2bf2c5..a9378ee0c2f1 100644 --- a/arch/alpha/kernel/pci-noop.c +++ b/arch/alpha/kernel/pci-noop.c @@ -7,7 +7,7 @@ #include #include -#include +#include #include #include #include diff --git a/arch/alpha/kernel/pci.c b/arch/alpha/kernel/pci.c index 4cc3eb92f55b..13937e72d875 100644 --- a/arch/alpha/kernel/pci.c +++ b/arch/alpha/kernel/pci.c @@ -18,7 +18,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/arch/alpha/kernel/pci_iommu.c b/arch/alpha/kernel/pci_iommu.c index 5d178c7ba5b2..82cf950bda2a 100644 --- a/arch/alpha/kernel/pci_iommu.c +++ b/arch/alpha/kernel/pci_iommu.c @@ -7,7 +7,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/arch/alpha/kernel/setup.c b/arch/alpha/kernel/setup.c index 64c06a0adf3d..a37fd990bd55 100644 --- a/arch/alpha/kernel/setup.c +++ b/arch/alpha/kernel/setup.c @@ -29,7 +29,6 @@ #include #include #include -#include #include #include #include diff --git a/arch/alpha/kernel/sys_nautilus.c b/arch/alpha/kernel/sys_nautilus.c index ff4f54b86c7f..cd9a112d67ff 100644 --- a/arch/alpha/kernel/sys_nautilus.c +++ b/arch/alpha/kernel/sys_nautilus.c @@ -32,7 +32,7 @@ #include #include #include -#include +#include #include #include diff --git a/arch/alpha/mm/init.c b/arch/alpha/mm/init.c index 853d15344934..a42fc5c4db89 100644 --- a/arch/alpha/mm/init.c +++ b/arch/alpha/mm/init.c @@ -19,7 +19,7 @@ #include #include #include -#include /* max_low_pfn */ +#include /* max_low_pfn */ #include #include diff --git a/arch/alpha/mm/numa.c b/arch/alpha/mm/numa.c index 26cd925d19b1..74846553e3f1 100644 --- a/arch/alpha/mm/numa.c +++ b/arch/alpha/mm/numa.c @@ -10,7 +10,6 @@ #include #include #include -#include #include #include #include diff --git a/arch/arc/kernel/unwind.c b/arch/arc/kernel/unwind.c index 2a01dd1005f4..d34f69eb1a95 100644 --- a/arch/arc/kernel/unwind.c +++ b/arch/arc/kernel/unwind.c @@ -15,7 +15,7 @@ #include #include -#include +#include #include #include #include diff --git a/arch/arc/mm/highmem.c b/arch/arc/mm/highmem.c index f582dc8944c9..48e700151810 100644 --- a/arch/arc/mm/highmem.c +++ b/arch/arc/mm/highmem.c @@ -7,7 +7,7 @@ * */ -#include +#include #include #include #include diff --git a/arch/arc/mm/init.c b/arch/arc/mm/init.c index 0f29c6548779..f8fe5668b30f 100644 --- a/arch/arc/mm/init.c +++ b/arch/arc/mm/init.c @@ -8,7 +8,6 @@ #include #include -#include #include #ifdef CONFIG_BLK_DEV_INITRD #include diff --git a/arch/arm/kernel/devtree.c b/arch/arm/kernel/devtree.c index 13bcd3b867cb..e3057c1b55b9 100644 --- a/arch/arm/kernel/devtree.c +++ b/arch/arm/kernel/devtree.c @@ -12,7 +12,6 @@ #include #include #include -#include #include #include #include diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c index 39e6090d23ac..840a4adc69fc 100644 --- a/arch/arm/kernel/setup.c +++ b/arch/arm/kernel/setup.c @@ -16,7 +16,6 @@ #include #include #include -#include #include #include #include diff --git a/arch/arm/mach-omap2/omap_hwmod.c b/arch/arm/mach-omap2/omap_hwmod.c index 1f9b34a7eccd..cd5732ab0cdf 100644 --- a/arch/arm/mach-omap2/omap_hwmod.c +++ b/arch/arm/mach-omap2/omap_hwmod.c @@ -141,7 +141,7 @@ #include #include #include -#include +#include #include diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c index 66566472c153..661fe48ab78d 100644 --- a/arch/arm/mm/dma-mapping.c +++ b/arch/arm/mm/dma-mapping.c @@ -9,7 +9,6 @@ * * DMA uncached mapping support. */ -#include #include #include #include diff --git a/arch/arm/mm/init.c b/arch/arm/mm/init.c index d421a10c93a8..32e4845af2b6 100644 --- a/arch/arm/mm/init.c +++ b/arch/arm/mm/init.c @@ -11,7 +11,6 @@ #include #include #include -#include #include #include #include diff --git a/arch/arm/xen/mm.c b/arch/arm/xen/mm.c index 785d2a562a23..cb44aa290e73 100644 --- a/arch/arm/xen/mm.c +++ b/arch/arm/xen/mm.c @@ -1,6 +1,5 @@ #include #include -#include #include #include #include diff --git a/arch/arm/xen/p2m.c b/arch/arm/xen/p2m.c index 0641ba54ab62..e70a49fc8dcd 100644 --- a/arch/arm/xen/p2m.c +++ b/arch/arm/xen/p2m.c @@ -1,4 +1,4 @@ -#include +#include #include #include #include diff --git a/arch/arm64/kernel/acpi.c b/arch/arm64/kernel/acpi.c index ed46dc188b22..44e3c351e1ea 100644 --- a/arch/arm64/kernel/acpi.c +++ b/arch/arm64/kernel/acpi.c @@ -16,7 +16,6 @@ #define pr_fmt(fmt) "ACPI: " fmt #include -#include #include #include #include diff --git a/arch/arm64/kernel/acpi_numa.c b/arch/arm64/kernel/acpi_numa.c index 4f4f1815e047..eac1d0cc595c 100644 --- a/arch/arm64/kernel/acpi_numa.c +++ b/arch/arm64/kernel/acpi_numa.c @@ -18,7 +18,6 @@ #include #include -#include #include #include #include diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c index 3428427f6c93..7ce7306f1d75 100644 --- a/arch/arm64/kernel/setup.c +++ b/arch/arm64/kernel/setup.c @@ -26,7 +26,6 @@ #include #include #include -#include #include #include #include diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c index d190612b8f33..3a703e5d4e32 100644 --- a/arch/arm64/mm/dma-mapping.c +++ b/arch/arm64/mm/dma-mapping.c @@ -19,7 +19,7 @@ #include #include -#include +#include #include #include #include diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c index d8d73073835f..9d9582cac6c4 100644 --- a/arch/arm64/mm/init.c +++ b/arch/arm64/mm/init.c @@ -22,7 +22,6 @@ #include #include #include -#include #include #include #include diff --git a/arch/arm64/mm/kasan_init.c b/arch/arm64/mm/kasan_init.c index 6a65a2912d36..63527e585aac 100644 --- a/arch/arm64/mm/kasan_init.c +++ b/arch/arm64/mm/kasan_init.c @@ -11,7 +11,6 @@ */ #define pr_fmt(fmt) "kasan: " fmt -#include #include #include #include diff --git a/arch/arm64/mm/numa.c b/arch/arm64/mm/numa.c index 0bff116c07a8..27a31efd9e8e 100644 --- a/arch/arm64/mm/numa.c +++ b/arch/arm64/mm/numa.c @@ -20,7 +20,6 @@ #define pr_fmt(fmt) "NUMA: " fmt #include -#include #include #include #include diff --git a/arch/c6x/kernel/setup.c b/arch/c6x/kernel/setup.c index 05d96a9541b5..2e1c0ea22eb0 100644 --- a/arch/c6x/kernel/setup.c +++ b/arch/c6x/kernel/setup.c @@ -11,7 +11,6 @@ #include #include #include -#include #include #include #include diff --git a/arch/c6x/mm/init.c b/arch/c6x/mm/init.c index 3383df8b3508..af5ada0520be 100644 --- a/arch/c6x/mm/init.c +++ b/arch/c6x/mm/init.c @@ -11,7 +11,7 @@ #include #include #include -#include +#include #ifdef CONFIG_BLK_DEV_RAM #include #endif diff --git a/arch/h8300/kernel/setup.c b/arch/h8300/kernel/setup.c index 34e2df5c0d6d..b32bfa1fe99e 100644 --- a/arch/h8300/kernel/setup.c +++ b/arch/h8300/kernel/setup.c @@ -18,7 +18,6 @@ #include #include #include -#include #include #include #include diff --git a/arch/h8300/mm/init.c b/arch/h8300/mm/init.c index f2bf4487aabd..6519252ac4db 100644 --- a/arch/h8300/mm/init.c +++ b/arch/h8300/mm/init.c @@ -30,7 +30,7 @@ #include #include #include -#include +#include #include #include diff --git a/arch/hexagon/kernel/dma.c b/arch/hexagon/kernel/dma.c index 706699374444..38eaa7b703e7 100644 --- a/arch/hexagon/kernel/dma.c +++ b/arch/hexagon/kernel/dma.c @@ -19,7 +19,7 @@ */ #include -#include +#include #include #include #include diff --git a/arch/hexagon/kernel/setup.c b/arch/hexagon/kernel/setup.c index dc8c7e75b5d1..b3c3e04d4e57 100644 --- a/arch/hexagon/kernel/setup.c +++ b/arch/hexagon/kernel/setup.c @@ -20,7 +20,7 @@ #include #include -#include +#include #include #include #include diff --git a/arch/hexagon/mm/init.c b/arch/hexagon/mm/init.c index 88643faf3981..1719ede9e9bd 100644 --- a/arch/hexagon/mm/init.c +++ b/arch/hexagon/mm/init.c @@ -20,7 +20,6 @@ #include #include -#include #include #include #include diff --git a/arch/ia64/kernel/crash.c b/arch/ia64/kernel/crash.c index 39f4433a6f0e..bec762a9b418 100644 --- a/arch/ia64/kernel/crash.c +++ b/arch/ia64/kernel/crash.c @@ -12,7 +12,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/arch/ia64/kernel/efi.c b/arch/ia64/kernel/efi.c index f77d80edddfe..8f106638913c 100644 --- a/arch/ia64/kernel/efi.c +++ b/arch/ia64/kernel/efi.c @@ -23,7 +23,7 @@ * Skip non-WB memory and ignore empty memory ranges. */ #include -#include +#include #include #include #include diff --git a/arch/ia64/kernel/ia64_ksyms.c b/arch/ia64/kernel/ia64_ksyms.c index 6b51c88e3578..b49fe6f618ed 100644 --- a/arch/ia64/kernel/ia64_ksyms.c +++ b/arch/ia64/kernel/ia64_ksyms.c @@ -6,7 +6,7 @@ #ifdef CONFIG_VIRTUAL_MEM_MAP #include #include -#include +#include EXPORT_SYMBOL(min_low_pfn); /* defined by bootmem.c, but not exported by generic code */ EXPORT_SYMBOL(max_low_pfn); /* defined by bootmem.c, but not exported by generic code */ #endif diff --git a/arch/ia64/kernel/iosapic.c b/arch/ia64/kernel/iosapic.c index 550243a94b5d..fe6e4946672e 100644 --- a/arch/ia64/kernel/iosapic.c +++ b/arch/ia64/kernel/iosapic.c @@ -90,7 +90,7 @@ #include #include #include -#include +#include #include #include diff --git a/arch/ia64/kernel/mca.c b/arch/ia64/kernel/mca.c index 71209766c47f..9a6603f8e409 100644 --- a/arch/ia64/kernel/mca.c +++ b/arch/ia64/kernel/mca.c @@ -77,7 +77,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/arch/ia64/kernel/mca_drv.c b/arch/ia64/kernel/mca_drv.c index dfe40cbdf3b3..45f956ad715a 100644 --- a/arch/ia64/kernel/mca_drv.c +++ b/arch/ia64/kernel/mca_drv.c @@ -14,7 +14,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/arch/ia64/kernel/setup.c b/arch/ia64/kernel/setup.c index 0e6c2d9fb498..583a3746d70b 100644 --- a/arch/ia64/kernel/setup.c +++ b/arch/ia64/kernel/setup.c @@ -27,7 +27,6 @@ #include #include -#include #include #include #include diff --git a/arch/ia64/kernel/smpboot.c b/arch/ia64/kernel/smpboot.c index 74fe317477e6..51ec944b036c 100644 --- a/arch/ia64/kernel/smpboot.c +++ b/arch/ia64/kernel/smpboot.c @@ -24,7 +24,7 @@ #include #include -#include +#include #include #include #include diff --git a/arch/ia64/kernel/topology.c b/arch/ia64/kernel/topology.c index 9b820f7a6a98..e311ee13e61d 100644 --- a/arch/ia64/kernel/topology.c +++ b/arch/ia64/kernel/topology.c @@ -19,7 +19,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/arch/ia64/kernel/unwind.c b/arch/ia64/kernel/unwind.c index e04efa088902..7601fe0622d2 100644 --- a/arch/ia64/kernel/unwind.c +++ b/arch/ia64/kernel/unwind.c @@ -28,7 +28,7 @@ * acquired, then the read-write lock must be acquired first. */ #include -#include +#include #include #include #include diff --git a/arch/ia64/mm/contig.c b/arch/ia64/mm/contig.c index 9e5c23a6b8b4..6e447234205c 100644 --- a/arch/ia64/mm/contig.c +++ b/arch/ia64/mm/contig.c @@ -14,7 +14,6 @@ * Routines used by ia64 machines with contiguous (or virtually contiguous) * memory. */ -#include #include #include #include diff --git a/arch/ia64/mm/discontig.c b/arch/ia64/mm/discontig.c index 70609f823960..8a965784340c 100644 --- a/arch/ia64/mm/discontig.c +++ b/arch/ia64/mm/discontig.c @@ -19,7 +19,6 @@ #include #include #include -#include #include #include #include diff --git a/arch/ia64/mm/init.c b/arch/ia64/mm/init.c index 43ea4a47163d..d5e12ff1d73c 100644 --- a/arch/ia64/mm/init.c +++ b/arch/ia64/mm/init.c @@ -8,7 +8,6 @@ #include #include -#include #include #include #include diff --git a/arch/ia64/mm/numa.c b/arch/ia64/mm/numa.c index aa19b7ac8222..3861d6e32d5f 100644 --- a/arch/ia64/mm/numa.c +++ b/arch/ia64/mm/numa.c @@ -15,7 +15,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/arch/ia64/mm/tlb.c b/arch/ia64/mm/tlb.c index 5554863b4c9b..ab545daff7c3 100644 --- a/arch/ia64/mm/tlb.c +++ b/arch/ia64/mm/tlb.c @@ -21,7 +21,7 @@ #include #include #include -#include +#include #include #include diff --git a/arch/ia64/pci/pci.c b/arch/ia64/pci/pci.c index 5d71800df431..196a0dd7ff97 100644 --- a/arch/ia64/pci/pci.c +++ b/arch/ia64/pci/pci.c @@ -20,7 +20,7 @@ #include #include #include -#include +#include #include #include diff --git a/arch/ia64/sn/kernel/bte.c b/arch/ia64/sn/kernel/bte.c index 9146192b86f5..9900e6d4add6 100644 --- a/arch/ia64/sn/kernel/bte.c +++ b/arch/ia64/sn/kernel/bte.c @@ -16,7 +16,7 @@ #include #include -#include +#include #include #include #include diff --git a/arch/ia64/sn/kernel/io_common.c b/arch/ia64/sn/kernel/io_common.c index 8b05d5581615..98f55220c67d 100644 --- a/arch/ia64/sn/kernel/io_common.c +++ b/arch/ia64/sn/kernel/io_common.c @@ -6,7 +6,7 @@ * Copyright (C) 2006 Silicon Graphics, Inc. All rights reserved. */ -#include +#include #include #include #include diff --git a/arch/ia64/sn/kernel/setup.c b/arch/ia64/sn/kernel/setup.c index ab2564f95199..71ad6b0ccab4 100644 --- a/arch/ia64/sn/kernel/setup.c +++ b/arch/ia64/sn/kernel/setup.c @@ -20,7 +20,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/arch/m68k/atari/stram.c b/arch/m68k/atari/stram.c index 1089d67df315..6ffc204eb07d 100644 --- a/arch/m68k/atari/stram.c +++ b/arch/m68k/atari/stram.c @@ -17,7 +17,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/arch/m68k/coldfire/m54xx.c b/arch/m68k/coldfire/m54xx.c index adad03ca6e11..360c723c0ae6 100644 --- a/arch/m68k/coldfire/m54xx.c +++ b/arch/m68k/coldfire/m54xx.c @@ -16,7 +16,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/arch/m68k/kernel/setup_mm.c b/arch/m68k/kernel/setup_mm.c index 5d3596c180f9..a1a3eaeaf58c 100644 --- a/arch/m68k/kernel/setup_mm.c +++ b/arch/m68k/kernel/setup_mm.c @@ -20,7 +20,6 @@ #include #include #include -#include #include #include #include diff --git a/arch/m68k/kernel/setup_no.c b/arch/m68k/kernel/setup_no.c index cfd5475bfc31..3c5def10d486 100644 --- a/arch/m68k/kernel/setup_no.c +++ b/arch/m68k/kernel/setup_no.c @@ -27,7 +27,6 @@ #include #include #include -#include #include #include #include diff --git a/arch/m68k/kernel/uboot.c b/arch/m68k/kernel/uboot.c index 107082877064..1b4c562753da 100644 --- a/arch/m68k/kernel/uboot.c +++ b/arch/m68k/kernel/uboot.c @@ -16,7 +16,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/arch/m68k/mm/init.c b/arch/m68k/mm/init.c index ae49ae4d3049..933c33e76a48 100644 --- a/arch/m68k/mm/init.c +++ b/arch/m68k/mm/init.c @@ -17,7 +17,7 @@ #include #include #include -#include +#include #include #include diff --git a/arch/m68k/mm/mcfmmu.c b/arch/m68k/mm/mcfmmu.c index 38a1d92dd555..0de4999a3810 100644 --- a/arch/m68k/mm/mcfmmu.c +++ b/arch/m68k/mm/mcfmmu.c @@ -13,7 +13,6 @@ #include #include #include -#include #include #include diff --git a/arch/m68k/mm/motorola.c b/arch/m68k/mm/motorola.c index 2113eec8dbf9..7497cf30bf1c 100644 --- a/arch/m68k/mm/motorola.c +++ b/arch/m68k/mm/motorola.c @@ -18,7 +18,6 @@ #include #include #include -#include #include #include diff --git a/arch/m68k/mm/sun3mmu.c b/arch/m68k/mm/sun3mmu.c index 19c05ab9824d..f736db48a2e1 100644 --- a/arch/m68k/mm/sun3mmu.c +++ b/arch/m68k/mm/sun3mmu.c @@ -16,7 +16,7 @@ #include #include #include -#include +#include #include #include diff --git a/arch/m68k/sun3/config.c b/arch/m68k/sun3/config.c index 79a2bb857906..542c4404861c 100644 --- a/arch/m68k/sun3/config.c +++ b/arch/m68k/sun3/config.c @@ -15,7 +15,7 @@ #include #include #include -#include +#include #include #include diff --git a/arch/m68k/sun3/dvma.c b/arch/m68k/sun3/dvma.c index 5f92c72b05c3..a2c1c9304895 100644 --- a/arch/m68k/sun3/dvma.c +++ b/arch/m68k/sun3/dvma.c @@ -11,7 +11,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/arch/m68k/sun3/mmu_emu.c b/arch/m68k/sun3/mmu_emu.c index d30da12a1702..582a1284059a 100644 --- a/arch/m68k/sun3/mmu_emu.c +++ b/arch/m68k/sun3/mmu_emu.c @@ -13,7 +13,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/arch/m68k/sun3/sun3dvma.c b/arch/m68k/sun3/sun3dvma.c index 72d94585b52e..8be8b750c629 100644 --- a/arch/m68k/sun3/sun3dvma.c +++ b/arch/m68k/sun3/sun3dvma.c @@ -7,7 +7,7 @@ * Contains common routines for sun3/sun3x DVMA management. */ -#include +#include #include #include #include diff --git a/arch/m68k/sun3x/dvma.c b/arch/m68k/sun3x/dvma.c index b2acbc862f60..89e630e66555 100644 --- a/arch/m68k/sun3x/dvma.c +++ b/arch/m68k/sun3x/dvma.c @@ -15,7 +15,7 @@ #include #include #include -#include +#include #include #include diff --git a/arch/microblaze/mm/consistent.c b/arch/microblaze/mm/consistent.c index d801cc5f5b95..45e0a1aa9357 100644 --- a/arch/microblaze/mm/consistent.c +++ b/arch/microblaze/mm/consistent.c @@ -28,7 +28,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/arch/microblaze/mm/init.c b/arch/microblaze/mm/init.c index 9989740d397a..8c14988f52f2 100644 --- a/arch/microblaze/mm/init.c +++ b/arch/microblaze/mm/init.c @@ -7,10 +7,9 @@ * for more details. */ -#include +#include #include #include -#include #include /* mem_init */ #include #include diff --git a/arch/microblaze/pci/pci-common.c b/arch/microblaze/pci/pci-common.c index 2ffd171af8b6..6b89a66ec1a5 100644 --- a/arch/microblaze/pci/pci-common.c +++ b/arch/microblaze/pci/pci-common.c @@ -20,7 +20,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/arch/mips/ar7/memory.c b/arch/mips/ar7/memory.c index 0332f0514d05..80390a9ec264 100644 --- a/arch/mips/ar7/memory.c +++ b/arch/mips/ar7/memory.c @@ -16,7 +16,7 @@ * along with this program; if not, write to the Free Software * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA */ -#include +#include #include #include #include diff --git a/arch/mips/ath79/setup.c b/arch/mips/ath79/setup.c index 4c7a93f4039a..9728abcb18fa 100644 --- a/arch/mips/ath79/setup.c +++ b/arch/mips/ath79/setup.c @@ -14,7 +14,7 @@ #include #include -#include +#include #include #include #include diff --git a/arch/mips/bcm63xx/prom.c b/arch/mips/bcm63xx/prom.c index 7019e2967009..77a836e661c9 100644 --- a/arch/mips/bcm63xx/prom.c +++ b/arch/mips/bcm63xx/prom.c @@ -7,7 +7,7 @@ */ #include -#include +#include #include #include #include diff --git a/arch/mips/bcm63xx/setup.c b/arch/mips/bcm63xx/setup.c index 2be9caaa2085..e28ee9a7cc7e 100644 --- a/arch/mips/bcm63xx/setup.c +++ b/arch/mips/bcm63xx/setup.c @@ -9,7 +9,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/arch/mips/bmips/setup.c b/arch/mips/bmips/setup.c index 6329c5f780d6..1738a06396f9 100644 --- a/arch/mips/bmips/setup.c +++ b/arch/mips/bmips/setup.c @@ -9,7 +9,7 @@ #include #include -#include +#include #include #include #include diff --git a/arch/mips/cavium-octeon/dma-octeon.c b/arch/mips/cavium-octeon/dma-octeon.c index c44c1a654471..e8eb60ed99f2 100644 --- a/arch/mips/cavium-octeon/dma-octeon.c +++ b/arch/mips/cavium-octeon/dma-octeon.c @@ -11,7 +11,7 @@ * Copyright (C) 2010 Cavium Networks, Inc. */ #include -#include +#include #include #include #include diff --git a/arch/mips/dec/prom/memory.c b/arch/mips/dec/prom/memory.c index a2acc6454cf3..5073d2ed78bb 100644 --- a/arch/mips/dec/prom/memory.c +++ b/arch/mips/dec/prom/memory.c @@ -8,7 +8,7 @@ #include #include #include -#include +#include #include #include diff --git a/arch/mips/emma/common/prom.c b/arch/mips/emma/common/prom.c index cae42259d6da..675337b8a4a0 100644 --- a/arch/mips/emma/common/prom.c +++ b/arch/mips/emma/common/prom.c @@ -22,7 +22,7 @@ #include #include #include -#include +#include #include #include diff --git a/arch/mips/fw/arc/memory.c b/arch/mips/fw/arc/memory.c index dd9496f26e6a..429b7f8d2aeb 100644 --- a/arch/mips/fw/arc/memory.c +++ b/arch/mips/fw/arc/memory.c @@ -17,7 +17,7 @@ #include #include #include -#include +#include #include #include diff --git a/arch/mips/jazz/jazzdma.c b/arch/mips/jazz/jazzdma.c index 0a0aaf39fd16..4c41ed0a637e 100644 --- a/arch/mips/jazz/jazzdma.c +++ b/arch/mips/jazz/jazzdma.c @@ -13,7 +13,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/arch/mips/kernel/crash.c b/arch/mips/kernel/crash.c index 2c7288041a99..81845ba04835 100644 --- a/arch/mips/kernel/crash.c +++ b/arch/mips/kernel/crash.c @@ -3,7 +3,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/arch/mips/kernel/crash_dump.c b/arch/mips/kernel/crash_dump.c index a8657d29c62e..01b2bd95ba1f 100644 --- a/arch/mips/kernel/crash_dump.c +++ b/arch/mips/kernel/crash_dump.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #include -#include +#include #include #include #include diff --git a/arch/mips/kernel/prom.c b/arch/mips/kernel/prom.c index 89950b7bf536..93b8e0b4332f 100644 --- a/arch/mips/kernel/prom.c +++ b/arch/mips/kernel/prom.c @@ -12,7 +12,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c index 31522d3bc8bf..41c1683761bb 100644 --- a/arch/mips/kernel/setup.c +++ b/arch/mips/kernel/setup.c @@ -15,7 +15,6 @@ #include #include #include -#include #include #include #include diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c index 623dc18f7f2f..0f852e1b5891 100644 --- a/arch/mips/kernel/traps.c +++ b/arch/mips/kernel/traps.c @@ -28,7 +28,6 @@ #include #include #include -#include #include #include #include diff --git a/arch/mips/kernel/vpe.c b/arch/mips/kernel/vpe.c index 0bef238d2c0c..6176b9acba95 100644 --- a/arch/mips/kernel/vpe.c +++ b/arch/mips/kernel/vpe.c @@ -26,7 +26,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/arch/mips/kvm/commpage.c b/arch/mips/kvm/commpage.c index f43629979a0e..5812e6145801 100644 --- a/arch/mips/kvm/commpage.c +++ b/arch/mips/kvm/commpage.c @@ -14,7 +14,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/arch/mips/kvm/dyntrans.c b/arch/mips/kvm/dyntrans.c index f8e772564d74..d77b61b3d6ee 100644 --- a/arch/mips/kvm/dyntrans.c +++ b/arch/mips/kvm/dyntrans.c @@ -16,7 +16,7 @@ #include #include #include -#include +#include #include #include "commpage.h" diff --git a/arch/mips/kvm/emulate.c b/arch/mips/kvm/emulate.c index 4144bfaef137..ec9ed23bca7f 100644 --- a/arch/mips/kvm/emulate.c +++ b/arch/mips/kvm/emulate.c @@ -15,7 +15,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/arch/mips/kvm/interrupt.c b/arch/mips/kvm/interrupt.c index aa0a1a00faf6..7257e8b6f5a9 100644 --- a/arch/mips/kvm/interrupt.c +++ b/arch/mips/kvm/interrupt.c @@ -13,7 +13,7 @@ #include #include #include -#include +#include #include #include diff --git a/arch/mips/kvm/mips.c b/arch/mips/kvm/mips.c index f7ea8e21656b..1fcc4d149054 100644 --- a/arch/mips/kvm/mips.c +++ b/arch/mips/kvm/mips.c @@ -18,7 +18,7 @@ #include #include #include -#include +#include #include #include diff --git a/arch/mips/lantiq/prom.c b/arch/mips/lantiq/prom.c index d984bd5c2ec5..14d4c5e2b42f 100644 --- a/arch/mips/lantiq/prom.c +++ b/arch/mips/lantiq/prom.c @@ -8,7 +8,7 @@ #include #include -#include +#include #include #include diff --git a/arch/mips/lasat/prom.c b/arch/mips/lasat/prom.c index 37b8fc5b9ac9..5ce1407de2d5 100644 --- a/arch/mips/lasat/prom.c +++ b/arch/mips/lasat/prom.c @@ -8,7 +8,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/arch/mips/loongson64/common/init.c b/arch/mips/loongson64/common/init.c index 6ef17120722f..c073fbcb9805 100644 --- a/arch/mips/loongson64/common/init.c +++ b/arch/mips/loongson64/common/init.c @@ -8,7 +8,7 @@ * option) any later version. */ -#include +#include #include #include #include diff --git a/arch/mips/loongson64/loongson-3/numa.c b/arch/mips/loongson64/loongson-3/numa.c index 703ad4536fe0..622761878cd1 100644 --- a/arch/mips/loongson64/loongson-3/numa.c +++ b/arch/mips/loongson64/loongson-3/numa.c @@ -18,7 +18,6 @@ #include #include #include -#include #include #include #include diff --git a/arch/mips/mm/init.c b/arch/mips/mm/init.c index 0893b6136498..b521d8e2d359 100644 --- a/arch/mips/mm/init.c +++ b/arch/mips/mm/init.c @@ -22,7 +22,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/arch/mips/mm/pgtable-32.c b/arch/mips/mm/pgtable-32.c index b19a3c506b1e..e2a33adc0f29 100644 --- a/arch/mips/mm/pgtable-32.c +++ b/arch/mips/mm/pgtable-32.c @@ -7,7 +7,7 @@ */ #include #include -#include +#include #include #include #include diff --git a/arch/mips/mti-malta/malta-memory.c b/arch/mips/mti-malta/malta-memory.c index a47556723b85..868921adef1d 100644 --- a/arch/mips/mti-malta/malta-memory.c +++ b/arch/mips/mti-malta/malta-memory.c @@ -12,7 +12,7 @@ * Steven J. Hill */ #include -#include +#include #include #include diff --git a/arch/mips/netlogic/xlp/dt.c b/arch/mips/netlogic/xlp/dt.c index b5ba83f4c646..c856f2a3ea42 100644 --- a/arch/mips/netlogic/xlp/dt.c +++ b/arch/mips/netlogic/xlp/dt.c @@ -33,7 +33,7 @@ */ #include -#include +#include #include #include diff --git a/arch/mips/pci/pci-legacy.c b/arch/mips/pci/pci-legacy.c index 3c3b1e6abb53..687513880fbf 100644 --- a/arch/mips/pci/pci-legacy.c +++ b/arch/mips/pci/pci-legacy.c @@ -11,7 +11,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/arch/mips/pci/pci.c b/arch/mips/pci/pci.c index c2e94cf5ecda..e68b44b27c0d 100644 --- a/arch/mips/pci/pci.c +++ b/arch/mips/pci/pci.c @@ -11,7 +11,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/arch/mips/ralink/of.c b/arch/mips/ralink/of.c index 1ada8492733b..d544e7b07f7a 100644 --- a/arch/mips/ralink/of.c +++ b/arch/mips/ralink/of.c @@ -14,7 +14,7 @@ #include #include #include -#include +#include #include #include diff --git a/arch/mips/rb532/prom.c b/arch/mips/rb532/prom.c index 6484e4a4597b..361a690facbf 100644 --- a/arch/mips/rb532/prom.c +++ b/arch/mips/rb532/prom.c @@ -29,7 +29,7 @@ #include #include #include -#include +#include #include #include diff --git a/arch/mips/sgi-ip27/ip27-memory.c b/arch/mips/sgi-ip27/ip27-memory.c index cb1f1a6a166d..d8b8444d6795 100644 --- a/arch/mips/sgi-ip27/ip27-memory.c +++ b/arch/mips/sgi-ip27/ip27-memory.c @@ -18,7 +18,6 @@ #include #include #include -#include #include #include #include diff --git a/arch/mips/sibyte/common/cfe.c b/arch/mips/sibyte/common/cfe.c index 092fb2a6ec4a..12a780f251e1 100644 --- a/arch/mips/sibyte/common/cfe.c +++ b/arch/mips/sibyte/common/cfe.c @@ -21,7 +21,7 @@ #include #include #include -#include +#include #include #include diff --git a/arch/mips/sibyte/swarm/setup.c b/arch/mips/sibyte/swarm/setup.c index 152ca71cc2d7..3b034b7178d6 100644 --- a/arch/mips/sibyte/swarm/setup.c +++ b/arch/mips/sibyte/swarm/setup.c @@ -23,7 +23,7 @@ #include #include -#include +#include #include #include #include diff --git a/arch/mips/txx9/rbtx4938/prom.c b/arch/mips/txx9/rbtx4938/prom.c index bcb469247e8c..2b36a2ee744c 100644 --- a/arch/mips/txx9/rbtx4938/prom.c +++ b/arch/mips/txx9/rbtx4938/prom.c @@ -11,7 +11,7 @@ */ #include -#include +#include #include #include #include diff --git a/arch/nds32/kernel/setup.c b/arch/nds32/kernel/setup.c index 63a1a5ef5219..eacc79024879 100644 --- a/arch/nds32/kernel/setup.c +++ b/arch/nds32/kernel/setup.c @@ -2,9 +2,8 @@ // Copyright (C) 2005-2017 Andes Technology Corporation #include -#include -#include #include +#include #include #include #include diff --git a/arch/nds32/mm/highmem.c b/arch/nds32/mm/highmem.c index e17cb8a69315..022779af6148 100644 --- a/arch/nds32/mm/highmem.c +++ b/arch/nds32/mm/highmem.c @@ -6,7 +6,7 @@ #include #include #include -#include +#include #include #include diff --git a/arch/nds32/mm/init.c b/arch/nds32/mm/init.c index 66d3e9cf498d..131104bd2538 100644 --- a/arch/nds32/mm/init.c +++ b/arch/nds32/mm/init.c @@ -7,12 +7,11 @@ #include #include #include -#include +#include #include #include #include #include -#include #include #include diff --git a/arch/nios2/kernel/prom.c b/arch/nios2/kernel/prom.c index a6d4f7530247..232a36b511aa 100644 --- a/arch/nios2/kernel/prom.c +++ b/arch/nios2/kernel/prom.c @@ -25,7 +25,7 @@ #include #include -#include +#include #include #include #include diff --git a/arch/nios2/kernel/setup.c b/arch/nios2/kernel/setup.c index 2d0011ddd4d5..6bbd4ae2beb0 100644 --- a/arch/nios2/kernel/setup.c +++ b/arch/nios2/kernel/setup.c @@ -16,7 +16,6 @@ #include #include #include -#include #include #include #include diff --git a/arch/nios2/mm/init.c b/arch/nios2/mm/init.c index 12923501d94f..16cea5776b87 100644 --- a/arch/nios2/mm/init.c +++ b/arch/nios2/mm/init.c @@ -23,7 +23,7 @@ #include #include #include -#include +#include #include #include diff --git a/arch/openrisc/kernel/setup.c b/arch/openrisc/kernel/setup.c index e17fcd83120f..c605bdad1746 100644 --- a/arch/openrisc/kernel/setup.c +++ b/arch/openrisc/kernel/setup.c @@ -30,13 +30,12 @@ #include #include #include -#include +#include #include #include #include #include #include -#include #include #include diff --git a/arch/openrisc/mm/init.c b/arch/openrisc/mm/init.c index 91a6a9ab7598..d157310eb377 100644 --- a/arch/openrisc/mm/init.c +++ b/arch/openrisc/mm/init.c @@ -26,12 +26,11 @@ #include #include #include -#include +#include #include #include #include /* for initrd_* */ #include -#include #include #include diff --git a/arch/parisc/mm/init.c b/arch/parisc/mm/init.c index 7e7a3126c5e9..2d7cffcaa476 100644 --- a/arch/parisc/mm/init.c +++ b/arch/parisc/mm/init.c @@ -14,7 +14,6 @@ #include #include -#include #include #include #include diff --git a/arch/powerpc/kernel/pci_32.c b/arch/powerpc/kernel/pci_32.c index d39ec3a4550a..274bd1442dd9 100644 --- a/arch/powerpc/kernel/pci_32.c +++ b/arch/powerpc/kernel/pci_32.c @@ -10,7 +10,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c index 2b56d1f30387..93ee3703b42f 100644 --- a/arch/powerpc/kernel/setup-common.c +++ b/arch/powerpc/kernel/setup-common.c @@ -33,7 +33,6 @@ #include #include #include -#include #include #include #include diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c index 9216c3a7fcfc..2a51e4cc8246 100644 --- a/arch/powerpc/kernel/setup_64.c +++ b/arch/powerpc/kernel/setup_64.c @@ -29,10 +29,9 @@ #include #include #include -#include +#include #include #include -#include #include #include diff --git a/arch/powerpc/lib/alloc.c b/arch/powerpc/lib/alloc.c index bf87d6e13369..5b61704447c1 100644 --- a/arch/powerpc/lib/alloc.c +++ b/arch/powerpc/lib/alloc.c @@ -2,7 +2,7 @@ #include #include #include -#include +#include #include #include diff --git a/arch/powerpc/mm/hugetlbpage.c b/arch/powerpc/mm/hugetlbpage.c index a7226ed9cae6..8cf035e68378 100644 --- a/arch/powerpc/mm/hugetlbpage.c +++ b/arch/powerpc/mm/hugetlbpage.c @@ -15,7 +15,6 @@ #include #include #include -#include #include #include #include diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c index b3fe79064a69..0a64fffabee1 100644 --- a/arch/powerpc/mm/mem.c +++ b/arch/powerpc/mm/mem.c @@ -27,12 +27,11 @@ #include #include #include -#include +#include #include #include #include #include -#include #include #include #include diff --git a/arch/powerpc/mm/mmu_context_nohash.c b/arch/powerpc/mm/mmu_context_nohash.c index 954f1986af4d..67b9d7b669a1 100644 --- a/arch/powerpc/mm/mmu_context_nohash.c +++ b/arch/powerpc/mm/mmu_context_nohash.c @@ -44,7 +44,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c index f04f15f9d232..3a048e98a132 100644 --- a/arch/powerpc/mm/numa.c +++ b/arch/powerpc/mm/numa.c @@ -11,7 +11,7 @@ #define pr_fmt(fmt) "numa: " fmt #include -#include +#include #include #include #include @@ -19,7 +19,6 @@ #include #include #include -#include #include #include #include diff --git a/arch/powerpc/platforms/powermac/nvram.c b/arch/powerpc/platforms/powermac/nvram.c index f45b369177a4..f3391be7c762 100644 --- a/arch/powerpc/platforms/powermac/nvram.c +++ b/arch/powerpc/platforms/powermac/nvram.c @@ -18,7 +18,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c index 23a67b545b70..aba81cbf0b36 100644 --- a/arch/powerpc/platforms/powernv/pci-ioda.c +++ b/arch/powerpc/platforms/powernv/pci-ioda.c @@ -17,11 +17,10 @@ #include #include #include -#include +#include #include #include #include -#include #include #include #include diff --git a/arch/powerpc/platforms/ps3/setup.c b/arch/powerpc/platforms/ps3/setup.c index 12519857a33c..658bfab3350b 100644 --- a/arch/powerpc/platforms/ps3/setup.c +++ b/arch/powerpc/platforms/ps3/setup.c @@ -24,7 +24,7 @@ #include #include #include -#include +#include #include #include diff --git a/arch/powerpc/sysdev/msi_bitmap.c b/arch/powerpc/sysdev/msi_bitmap.c index 349a9ff6ca5b..2444feda831f 100644 --- a/arch/powerpc/sysdev/msi_bitmap.c +++ b/arch/powerpc/sysdev/msi_bitmap.c @@ -12,7 +12,7 @@ #include #include #include -#include +#include #include #include diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index d58c111099b3..1d9bfaff60bc 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -13,9 +13,8 @@ #include #include -#include -#include #include +#include #include #include diff --git a/arch/s390/kernel/crash_dump.c b/arch/s390/kernel/crash_dump.c index d17566a8c76f..97eae3871868 100644 --- a/arch/s390/kernel/crash_dump.c +++ b/arch/s390/kernel/crash_dump.c @@ -13,10 +13,9 @@ #include #include #include -#include +#include #include #include -#include #include #include #include diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c index 781c1053a773..72dd23ef771b 100644 --- a/arch/s390/kernel/setup.c +++ b/arch/s390/kernel/setup.c @@ -34,7 +34,6 @@ #include #include #include -#include #include #include #include diff --git a/arch/s390/kernel/smp.c b/arch/s390/kernel/smp.c index 44f9a7d6450b..f82b3d3c36e2 100644 --- a/arch/s390/kernel/smp.c +++ b/arch/s390/kernel/smp.c @@ -20,7 +20,7 @@ #define pr_fmt(fmt) KMSG_COMPONENT ": " fmt #include -#include +#include #include #include #include @@ -35,7 +35,6 @@ #include #include #include -#include #include #include #include diff --git a/arch/s390/kernel/topology.c b/arch/s390/kernel/topology.c index 799a91882a76..8992b04c0ade 100644 --- a/arch/s390/kernel/topology.c +++ b/arch/s390/kernel/topology.c @@ -8,7 +8,7 @@ #define pr_fmt(fmt) KMSG_COMPONENT ": " fmt #include -#include +#include #include #include #include diff --git a/arch/s390/kernel/vdso.c b/arch/s390/kernel/vdso.c index ec31b48a42a5..ebe748a9f472 100644 --- a/arch/s390/kernel/vdso.c +++ b/arch/s390/kernel/vdso.c @@ -18,7 +18,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/arch/s390/mm/extmem.c b/arch/s390/mm/extmem.c index 84111a43ea29..eba2def3414d 100644 --- a/arch/s390/mm/extmem.c +++ b/arch/s390/mm/extmem.c @@ -16,7 +16,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c index 873f6ee1c46d..76d0708438e9 100644 --- a/arch/s390/mm/init.c +++ b/arch/s390/mm/init.c @@ -21,7 +21,7 @@ #include #include #include -#include +#include #include #include #include @@ -29,7 +29,6 @@ #include #include #include -#include #include #include #include diff --git a/arch/s390/mm/vmem.c b/arch/s390/mm/vmem.c index 04638b0b9ef1..0472e27febdf 100644 --- a/arch/s390/mm/vmem.c +++ b/arch/s390/mm/vmem.c @@ -4,14 +4,13 @@ * Author(s): Heiko Carstens */ -#include +#include #include #include #include #include #include #include -#include #include #include #include diff --git a/arch/s390/numa/mode_emu.c b/arch/s390/numa/mode_emu.c index 5a381fc8e958..bfba273c32c0 100644 --- a/arch/s390/numa/mode_emu.c +++ b/arch/s390/numa/mode_emu.c @@ -22,7 +22,6 @@ #include #include #include -#include #include #include #include diff --git a/arch/s390/numa/numa.c b/arch/s390/numa/numa.c index 297f5d8b0890..ae0d9e889534 100644 --- a/arch/s390/numa/numa.c +++ b/arch/s390/numa/numa.c @@ -13,7 +13,6 @@ #include #include #include -#include #include #include #include diff --git a/arch/s390/numa/toptree.c b/arch/s390/numa/toptree.c index 7f61cc3fd4d1..71a608cd4f61 100644 --- a/arch/s390/numa/toptree.c +++ b/arch/s390/numa/toptree.c @@ -8,7 +8,7 @@ */ #include -#include +#include #include #include #include diff --git a/arch/sh/mm/init.c b/arch/sh/mm/init.c index 21447f866415..c8c13c777162 100644 --- a/arch/sh/mm/init.c +++ b/arch/sh/mm/init.c @@ -11,12 +11,11 @@ #include #include #include -#include +#include #include #include #include #include -#include #include #include #include diff --git a/arch/sh/mm/ioremap_fixed.c b/arch/sh/mm/ioremap_fixed.c index 927a1294c465..07e744d75fa0 100644 --- a/arch/sh/mm/ioremap_fixed.c +++ b/arch/sh/mm/ioremap_fixed.c @@ -14,7 +14,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/arch/sparc/kernel/mdesc.c b/arch/sparc/kernel/mdesc.c index a41526bd91e2..9a26b442f820 100644 --- a/arch/sparc/kernel/mdesc.c +++ b/arch/sparc/kernel/mdesc.c @@ -5,13 +5,11 @@ */ #include #include -#include #include #include #include #include #include -#include #include #include #include diff --git a/arch/sparc/kernel/prom_32.c b/arch/sparc/kernel/prom_32.c index 4389944735c6..d41e2a749c5d 100644 --- a/arch/sparc/kernel/prom_32.c +++ b/arch/sparc/kernel/prom_32.c @@ -19,7 +19,7 @@ #include #include #include -#include +#include #include #include diff --git a/arch/sparc/kernel/setup_64.c b/arch/sparc/kernel/setup_64.c index de7c87b153fe..cd2825cb8420 100644 --- a/arch/sparc/kernel/setup_64.c +++ b/arch/sparc/kernel/setup_64.c @@ -32,7 +32,7 @@ #include #include #include -#include +#include #include #include diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c index 6cc80d0f4b9f..4792e08ad36b 100644 --- a/arch/sparc/kernel/smp_64.c +++ b/arch/sparc/kernel/smp_64.c @@ -22,7 +22,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/arch/sparc/mm/init_32.c b/arch/sparc/mm/init_32.c index 880714565c40..d900952bfc5f 100644 --- a/arch/sparc/mm/init_32.c +++ b/arch/sparc/mm/init_32.c @@ -22,7 +22,6 @@ #include #include #include -#include #include #include #include diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c index a8c3453195e6..3c8aac21f426 100644 --- a/arch/sparc/mm/init_64.c +++ b/arch/sparc/mm/init_64.c @@ -11,7 +11,7 @@ #include #include #include -#include +#include #include #include #include @@ -25,7 +25,6 @@ #include #include #include -#include #include #include diff --git a/arch/sparc/mm/srmmu.c b/arch/sparc/mm/srmmu.c index b48fea5ad9ef..a6142c5abf61 100644 --- a/arch/sparc/mm/srmmu.c +++ b/arch/sparc/mm/srmmu.c @@ -11,7 +11,7 @@ #include #include -#include +#include #include #include #include diff --git a/arch/um/drivers/net_kern.c b/arch/um/drivers/net_kern.c index ef19a391214f..673816880cce 100644 --- a/arch/um/drivers/net_kern.c +++ b/arch/um/drivers/net_kern.c @@ -6,7 +6,7 @@ * Licensed under the GPL. */ -#include +#include #include #include #include diff --git a/arch/um/drivers/vector_kern.c b/arch/um/drivers/vector_kern.c index 20442d20bd09..2b4dded11a7a 100644 --- a/arch/um/drivers/vector_kern.c +++ b/arch/um/drivers/vector_kern.c @@ -9,7 +9,7 @@ */ #include -#include +#include #include #include #include diff --git a/arch/um/kernel/initrd.c b/arch/um/kernel/initrd.c index 844056cf313e..3678f5b05e42 100644 --- a/arch/um/kernel/initrd.c +++ b/arch/um/kernel/initrd.c @@ -4,7 +4,7 @@ */ #include -#include +#include #include #include #include diff --git a/arch/um/kernel/mem.c b/arch/um/kernel/mem.c index 2c672a8f4571..1067469ba2ea 100644 --- a/arch/um/kernel/mem.c +++ b/arch/um/kernel/mem.c @@ -5,7 +5,6 @@ #include #include -#include #include #include #include diff --git a/arch/um/kernel/physmem.c b/arch/um/kernel/physmem.c index 296a91a04598..5bf56af4d5b9 100644 --- a/arch/um/kernel/physmem.c +++ b/arch/um/kernel/physmem.c @@ -4,7 +4,6 @@ */ #include -#include #include #include #include diff --git a/arch/unicore32/kernel/hibernate.c b/arch/unicore32/kernel/hibernate.c index 9969ec374abb..29b71c68eb7c 100644 --- a/arch/unicore32/kernel/hibernate.c +++ b/arch/unicore32/kernel/hibernate.c @@ -13,7 +13,7 @@ #include #include -#include +#include #include #include diff --git a/arch/unicore32/kernel/setup.c b/arch/unicore32/kernel/setup.c index 9f163f976315..b2c38b32ea57 100644 --- a/arch/unicore32/kernel/setup.c +++ b/arch/unicore32/kernel/setup.c @@ -17,7 +17,7 @@ #include #include #include -#include +#include #include #include #include @@ -27,7 +27,6 @@ #include #include #include -#include #include #include diff --git a/arch/unicore32/mm/init.c b/arch/unicore32/mm/init.c index 44fd0e8fbe87..cf4eb9481fd6 100644 --- a/arch/unicore32/mm/init.c +++ b/arch/unicore32/mm/init.c @@ -11,13 +11,12 @@ #include #include #include -#include +#include #include #include #include #include #include -#include #include #include #include diff --git a/arch/unicore32/mm/mmu.c b/arch/unicore32/mm/mmu.c index 18b355a20f0b..040a8c279761 100644 --- a/arch/unicore32/mm/mmu.c +++ b/arch/unicore32/mm/mmu.c @@ -17,7 +17,6 @@ #include #include #include -#include #include #include diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index f5ea6415b778..7f5d212551d4 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -32,7 +32,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c index f1915b744052..ca13851f0570 100644 --- a/arch/x86/kernel/acpi/sleep.c +++ b/arch/x86/kernel/acpi/sleep.c @@ -7,7 +7,6 @@ */ #include -#include #include #include #include diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index ab731ab09f06..32b2b7a41ef5 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -20,7 +20,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index 8c7450900e0e..5fbc57e4b0b9 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -47,7 +47,7 @@ #include #include /* time_after() */ #include -#include +#include #include #include diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 660d0b22e962..cbbd57ae06ee 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -1,7 +1,7 @@ /* cpu_feature_enabled() cannot be used this early */ #define USE_EARLY_PGTABLE_L5 -#include +#include #include #include #include diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index a0ec4c37265a..68ff62bffbab 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -9,11 +9,10 @@ * allocation code routines via a platform independent interface (memblock, etc.). */ #include -#include +#include #include #include #include -#include #include #include diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c index f1c5eb99d445..3482460d984d 100644 --- a/arch/x86/kernel/mpparse.c +++ b/arch/x86/kernel/mpparse.c @@ -11,7 +11,6 @@ #include #include #include -#include #include #include #include diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c index 7ba73fe0d917..f4562fcec681 100644 --- a/arch/x86/kernel/pci-dma.c +++ b/arch/x86/kernel/pci-dma.c @@ -3,7 +3,7 @@ #include #include #include -#include +#include #include #include diff --git a/arch/x86/kernel/pci-swiotlb.c b/arch/x86/kernel/pci-swiotlb.c index 71c0b01d93b1..bd08b9e1c9e2 100644 --- a/arch/x86/kernel/pci-swiotlb.c +++ b/arch/x86/kernel/pci-swiotlb.c @@ -5,7 +5,7 @@ #include #include #include -#include +#include #include #include diff --git a/arch/x86/kernel/pvclock.c b/arch/x86/kernel/pvclock.c index 637982efecd8..9b158b4716d2 100644 --- a/arch/x86/kernel/pvclock.c +++ b/arch/x86/kernel/pvclock.c @@ -20,7 +20,7 @@ #include #include #include -#include +#include #include #include diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 7005f89bf3b2..b74e7bfed6ab 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -30,7 +30,6 @@ #include #include #include -#include #include #include #include diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c index 483412fb8a24..e8796fcd7e5a 100644 --- a/arch/x86/kernel/setup_percpu.c +++ b/arch/x86/kernel/setup_percpu.c @@ -4,7 +4,6 @@ #include #include #include -#include #include #include #include diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 5369d7fac797..a9134d1910b9 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -49,7 +49,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/arch/x86/kernel/tce_64.c b/arch/x86/kernel/tce_64.c index 75730ce01f8d..285aaa62d153 100644 --- a/arch/x86/kernel/tce_64.c +++ b/arch/x86/kernel/tce_64.c @@ -30,7 +30,6 @@ #include #include #include -#include #include #include #include diff --git a/arch/x86/mm/amdtopology.c b/arch/x86/mm/amdtopology.c index 048c761d97b0..058b2f36b3a6 100644 --- a/arch/x86/mm/amdtopology.c +++ b/arch/x86/mm/amdtopology.c @@ -12,7 +12,6 @@ #include #include #include -#include #include #include diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index b24eb4eb9984..71d4b9d4d43f 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -8,7 +8,7 @@ #include /* task_stack_*(), ... */ #include /* oops_begin/end, ... */ #include /* search_exception_tables */ -#include /* max_low_pfn */ +#include /* max_low_pfn */ #include /* NOKPROBE_SYMBOL, ... */ #include /* kmmio_handler, ... */ #include /* perf_sw_event */ diff --git a/arch/x86/mm/highmem_32.c b/arch/x86/mm/highmem_32.c index 62915a5e0fa2..0d4bdcb84da5 100644 --- a/arch/x86/mm/highmem_32.c +++ b/arch/x86/mm/highmem_32.c @@ -1,7 +1,7 @@ #include #include #include /* for totalram_pages */ -#include +#include void *kmap(struct page *page) { diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index faca978ebf9d..ef99f3892e1f 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -3,7 +3,6 @@ #include #include #include -#include /* for max_low_pfn */ #include #include diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c index 3bbe5f58a67d..49ecf5ecf6d3 100644 --- a/arch/x86/mm/init_32.c +++ b/arch/x86/mm/init_32.c @@ -23,7 +23,6 @@ #include #include #include -#include #include #include #include diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index bfb0bedc21d3..5fab264948c2 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -20,7 +20,6 @@ #include #include #include -#include #include #include #include diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c index 24e0920a9b25..5378d10f1d31 100644 --- a/arch/x86/mm/ioremap.c +++ b/arch/x86/mm/ioremap.c @@ -6,7 +6,7 @@ * (C) Copyright 1995 1996 Linus Torvalds */ -#include +#include #include #include #include diff --git a/arch/x86/mm/kasan_init_64.c b/arch/x86/mm/kasan_init_64.c index 8f87499124b8..04a9cf6b034f 100644 --- a/arch/x86/mm/kasan_init_64.c +++ b/arch/x86/mm/kasan_init_64.c @@ -5,10 +5,9 @@ /* cpu_feature_enabled() cannot be used this early */ #define USE_EARLY_PGTABLE_L5 -#include +#include #include #include -#include #include #include #include diff --git a/arch/x86/mm/kaslr.c b/arch/x86/mm/kaslr.c index 61db77b0eda9..3f452ffed7e9 100644 --- a/arch/x86/mm/kaslr.c +++ b/arch/x86/mm/kaslr.c @@ -23,6 +23,7 @@ #include #include #include +#include #include #include diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c index 16e37d712ffd..1308f5408bf7 100644 --- a/arch/x86/mm/numa.c +++ b/arch/x86/mm/numa.c @@ -4,7 +4,6 @@ #include #include #include -#include #include #include #include diff --git a/arch/x86/mm/numa_32.c b/arch/x86/mm/numa_32.c index e8a4a09e20f1..f2bd3d61e16b 100644 --- a/arch/x86/mm/numa_32.c +++ b/arch/x86/mm/numa_32.c @@ -22,7 +22,6 @@ * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. */ -#include #include #include diff --git a/arch/x86/mm/numa_64.c b/arch/x86/mm/numa_64.c index 066f3511d5f1..59d80160fa5a 100644 --- a/arch/x86/mm/numa_64.c +++ b/arch/x86/mm/numa_64.c @@ -3,7 +3,7 @@ * Generic VM initialization for x86-64 NUMA setups. * Copyright 2002,2003 Andi Kleen, SuSE Labs. */ -#include +#include #include "numa_internal.h" diff --git a/arch/x86/mm/numa_emulation.c b/arch/x86/mm/numa_emulation.c index b54d52a2d00a..a80fdd7fb40f 100644 --- a/arch/x86/mm/numa_emulation.c +++ b/arch/x86/mm/numa_emulation.c @@ -6,7 +6,6 @@ #include #include #include -#include #include #include "numa_internal.h" diff --git a/arch/x86/mm/pageattr-test.c b/arch/x86/mm/pageattr-test.c index a25588ad75ef..08f8f76a4852 100644 --- a/arch/x86/mm/pageattr-test.c +++ b/arch/x86/mm/pageattr-test.c @@ -5,7 +5,7 @@ * Clears the a test pte bit on random pages in the direct mapping, * then reverts and compares page tables forwards and afterwards. */ -#include +#include #include #include #include diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c index 62bb30b4bd2a..f799076e3d57 100644 --- a/arch/x86/mm/pageattr.c +++ b/arch/x86/mm/pageattr.c @@ -3,7 +3,7 @@ * Thanks to Ben LaHaise for precious feedback. */ #include -#include +#include #include #include #include diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c index 3d0c83ef6aab..08013524fba1 100644 --- a/arch/x86/mm/pat.c +++ b/arch/x86/mm/pat.c @@ -8,7 +8,7 @@ */ #include -#include +#include #include #include #include diff --git a/arch/x86/mm/physaddr.c b/arch/x86/mm/physaddr.c index 7f9acb68324c..bdc98150d4db 100644 --- a/arch/x86/mm/physaddr.c +++ b/arch/x86/mm/physaddr.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -#include +#include #include #include #include diff --git a/arch/x86/pci/i386.c b/arch/x86/pci/i386.c index ed4ac215305d..8cd66152cdb0 100644 --- a/arch/x86/pci/i386.c +++ b/arch/x86/pci/i386.c @@ -32,7 +32,7 @@ #include #include #include -#include +#include #include #include diff --git a/arch/x86/platform/efi/efi.c b/arch/x86/platform/efi/efi.c index 9061babfbc83..7ae939e353cd 100644 --- a/arch/x86/platform/efi/efi.c +++ b/arch/x86/platform/efi/efi.c @@ -36,9 +36,8 @@ #include #include #include -#include -#include #include +#include #include #include #include diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c index e8da7f492970..cf0347f61b21 100644 --- a/arch/x86/platform/efi/efi_64.c +++ b/arch/x86/platform/efi/efi_64.c @@ -23,7 +23,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/arch/x86/platform/efi/quirks.c b/arch/x86/platform/efi/quirks.c index 4b70d0f5a803..95e77a667ba5 100644 --- a/arch/x86/platform/efi/quirks.c +++ b/arch/x86/platform/efi/quirks.c @@ -8,7 +8,6 @@ #include #include #include -#include #include #include diff --git a/arch/x86/platform/olpc/olpc_dt.c b/arch/x86/platform/olpc/olpc_dt.c index 140cd76ee897..115c8e4173bb 100644 --- a/arch/x86/platform/olpc/olpc_dt.c +++ b/arch/x86/platform/olpc/olpc_dt.c @@ -17,7 +17,7 @@ */ #include -#include +#include #include #include #include diff --git a/arch/x86/power/hibernate_32.c b/arch/x86/power/hibernate_32.c index 15695e30f982..be15bdcb20df 100644 --- a/arch/x86/power/hibernate_32.c +++ b/arch/x86/power/hibernate_32.c @@ -8,7 +8,7 @@ #include #include -#include +#include #include #include diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index 67b2f31a1265..e996e8e744cb 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #ifdef CONFIG_XEN_BALLOON_MEMORY_HOTPLUG -#include +#include #endif #include #include diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c index ec7a4209f310..2f6787fc7106 100644 --- a/arch/x86/xen/enlighten_pv.c +++ b/arch/x86/xen/enlighten_pv.c @@ -23,7 +23,7 @@ #include #include #include -#include +#include #include #include #include @@ -31,7 +31,6 @@ #include #include #include -#include #include #include diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c index b3e11afed25b..b06731705529 100644 --- a/arch/x86/xen/p2m.c +++ b/arch/x86/xen/p2m.c @@ -67,7 +67,6 @@ #include #include #include -#include #include #include #include diff --git a/arch/xtensa/kernel/pci.c b/arch/xtensa/kernel/pci.c index 21f13e9aabe1..5ca440a74316 100644 --- a/arch/xtensa/kernel/pci.c +++ b/arch/xtensa/kernel/pci.c @@ -24,7 +24,7 @@ #include #include #include -#include +#include #include #include diff --git a/arch/xtensa/mm/cache.c b/arch/xtensa/mm/cache.c index 9220dcde7520..b27359e2a464 100644 --- a/arch/xtensa/mm/cache.c +++ b/arch/xtensa/mm/cache.c @@ -21,7 +21,7 @@ #include #include #include -#include +#include #include #include diff --git a/arch/xtensa/mm/init.c b/arch/xtensa/mm/init.c index f7fbe6334939..9750a48f491b 100644 --- a/arch/xtensa/mm/init.c +++ b/arch/xtensa/mm/init.c @@ -18,7 +18,7 @@ #include #include -#include +#include #include #include #include diff --git a/arch/xtensa/mm/kasan_init.c b/arch/xtensa/mm/kasan_init.c index 1a30a258ccd0..6b95ca43aec0 100644 --- a/arch/xtensa/mm/kasan_init.c +++ b/arch/xtensa/mm/kasan_init.c @@ -8,11 +8,10 @@ * Copyright (C) 2017 Cadence Design Systems Inc. */ -#include +#include #include #include #include -#include #include #include #include diff --git a/arch/xtensa/mm/mmu.c b/arch/xtensa/mm/mmu.c index f33a1ff2662a..a4dcfd39bc5c 100644 --- a/arch/xtensa/mm/mmu.c +++ b/arch/xtensa/mm/mmu.c @@ -4,7 +4,7 @@ * * Extracted from init.c */ -#include +#include #include #include #include diff --git a/arch/xtensa/platforms/iss/network.c b/arch/xtensa/platforms/iss/network.c index 206b9d4591e8..190846dddc67 100644 --- a/arch/xtensa/platforms/iss/network.c +++ b/arch/xtensa/platforms/iss/network.c @@ -30,7 +30,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/arch/xtensa/platforms/iss/setup.c b/arch/xtensa/platforms/iss/setup.c index 58709e89a8ed..c14cc673976c 100644 --- a/arch/xtensa/platforms/iss/setup.c +++ b/arch/xtensa/platforms/iss/setup.c @@ -16,7 +16,7 @@ * option) any later version. * */ -#include +#include #include #include #include diff --git a/block/blk-settings.c b/block/blk-settings.c index ffd459969689..696c04c1ab6c 100644 --- a/block/blk-settings.c +++ b/block/blk-settings.c @@ -6,7 +6,7 @@ #include #include #include -#include /* for max_pfn/max_low_pfn */ +#include /* for max_pfn/max_low_pfn */ #include #include #include diff --git a/block/bounce.c b/block/bounce.c index ec0d99995f5f..cf49fe02f65c 100644 --- a/block/bounce.c +++ b/block/bounce.c @@ -18,7 +18,7 @@ #include #include #include -#include +#include #include #include diff --git a/drivers/acpi/numa.c b/drivers/acpi/numa.c index 85167603b9c9..274699463b4f 100644 --- a/drivers/acpi/numa.c +++ b/drivers/acpi/numa.c @@ -27,7 +27,6 @@ #include #include #include -#include #include #include #include diff --git a/drivers/acpi/tables.c b/drivers/acpi/tables.c index a3d012b08fc5..61203eebf3a1 100644 --- a/drivers/acpi/tables.c +++ b/drivers/acpi/tables.c @@ -31,9 +31,8 @@ #include #include #include -#include -#include #include +#include #include #include "internal.h" diff --git a/drivers/base/platform.c b/drivers/base/platform.c index 23cf4427f425..41b91af95afb 100644 --- a/drivers/base/platform.c +++ b/drivers/base/platform.c @@ -16,7 +16,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/drivers/clk/ti/clk.c b/drivers/clk/ti/clk.c index 5c54d3734daf..5b2867a33b98 100644 --- a/drivers/clk/ti/clk.c +++ b/drivers/clk/ti/clk.c @@ -23,7 +23,7 @@ #include #include #include -#include +#include #include #include "clock.h" diff --git a/drivers/firmware/dmi_scan.c b/drivers/firmware/dmi_scan.c index f2483548cde9..099d83e4e910 100644 --- a/drivers/firmware/dmi_scan.c +++ b/drivers/firmware/dmi_scan.c @@ -5,7 +5,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/drivers/firmware/efi/apple-properties.c b/drivers/firmware/efi/apple-properties.c index 2b675f788b61..ac1654f74dc7 100644 --- a/drivers/firmware/efi/apple-properties.c +++ b/drivers/firmware/efi/apple-properties.c @@ -20,7 +20,7 @@ #define pr_fmt(fmt) "apple-properties: " fmt -#include +#include #include #include #include diff --git a/drivers/firmware/iscsi_ibft_find.c b/drivers/firmware/iscsi_ibft_find.c index 2224f1dc074b..72d9ea18270b 100644 --- a/drivers/firmware/iscsi_ibft_find.c +++ b/drivers/firmware/iscsi_ibft_find.c @@ -18,7 +18,7 @@ * GNU General Public License for more details. */ -#include +#include #include #include #include diff --git a/drivers/firmware/memmap.c b/drivers/firmware/memmap.c index 03cead6d5f97..2a23453f005a 100644 --- a/drivers/firmware/memmap.c +++ b/drivers/firmware/memmap.c @@ -19,7 +19,7 @@ #include #include #include -#include +#include #include #include diff --git a/drivers/iommu/mtk_iommu.c b/drivers/iommu/mtk_iommu.c index f9f69f7111a9..44bd5b9166bb 100644 --- a/drivers/iommu/mtk_iommu.c +++ b/drivers/iommu/mtk_iommu.c @@ -11,7 +11,7 @@ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. */ -#include +#include #include #include #include diff --git a/drivers/iommu/mtk_iommu_v1.c b/drivers/iommu/mtk_iommu_v1.c index 676c029494e4..0e780848f59b 100644 --- a/drivers/iommu/mtk_iommu_v1.c +++ b/drivers/iommu/mtk_iommu_v1.c @@ -13,7 +13,7 @@ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the * GNU General Public License for more details. */ -#include +#include #include #include #include diff --git a/drivers/macintosh/smu.c b/drivers/macintosh/smu.c index 0069f9084f9f..880a81c82b7a 100644 --- a/drivers/macintosh/smu.c +++ b/drivers/macintosh/smu.c @@ -23,7 +23,7 @@ #include #include #include -#include +#include #include #include #include @@ -38,7 +38,6 @@ #include #include #include -#include #include #include diff --git a/drivers/mtd/ar7part.c b/drivers/mtd/ar7part.c index fc15ec58230a..0d33cf0842ad 100644 --- a/drivers/mtd/ar7part.c +++ b/drivers/mtd/ar7part.c @@ -25,7 +25,7 @@ #include #include -#include +#include #include #include diff --git a/drivers/net/arcnet/arc-rimi.c b/drivers/net/arcnet/arc-rimi.c index a07e24970be4..11c5bad95226 100644 --- a/drivers/net/arcnet/arc-rimi.c +++ b/drivers/net/arcnet/arc-rimi.c @@ -33,7 +33,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/drivers/net/arcnet/com20020-isa.c b/drivers/net/arcnet/com20020-isa.c index 38fa60ddaf2e..28510e33924f 100644 --- a/drivers/net/arcnet/com20020-isa.c +++ b/drivers/net/arcnet/com20020-isa.c @@ -38,7 +38,7 @@ #include #include #include -#include +#include #include #include "arcdevice.h" diff --git a/drivers/net/arcnet/com90io.c b/drivers/net/arcnet/com90io.c index 4e56aaf2b984..2c546013a980 100644 --- a/drivers/net/arcnet/com90io.c +++ b/drivers/net/arcnet/com90io.c @@ -34,7 +34,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/drivers/of/fdt.c b/drivers/of/fdt.c index ffe62a7ae19b..bb532aae0d92 100644 --- a/drivers/of/fdt.c +++ b/drivers/of/fdt.c @@ -11,7 +11,6 @@ #include #include #include -#include #include #include #include diff --git a/drivers/of/unittest.c b/drivers/of/unittest.c index 01e23b85e798..49ae2aa744d6 100644 --- a/drivers/of/unittest.c +++ b/drivers/of/unittest.c @@ -5,7 +5,7 @@ #define pr_fmt(fmt) "### dt-test ### " fmt -#include +#include #include #include #include diff --git a/drivers/s390/char/fs3270.c b/drivers/s390/char/fs3270.c index 16a4e8528bbc..8f3a2eeb28dc 100644 --- a/drivers/s390/char/fs3270.c +++ b/drivers/s390/char/fs3270.c @@ -8,7 +8,7 @@ * Copyright IBM Corp. 2003, 2009 */ -#include +#include #include #include #include diff --git a/drivers/s390/char/tty3270.c b/drivers/s390/char/tty3270.c index 5b8af2782282..2b0c36c2c568 100644 --- a/drivers/s390/char/tty3270.c +++ b/drivers/s390/char/tty3270.c @@ -19,7 +19,7 @@ #include #include -#include +#include #include #include diff --git a/drivers/s390/cio/cmf.c b/drivers/s390/cio/cmf.c index 8af4948dae80..72dd2471ec1e 100644 --- a/drivers/s390/cio/cmf.c +++ b/drivers/s390/cio/cmf.c @@ -13,7 +13,7 @@ #define KMSG_COMPONENT "cio" #define pr_fmt(fmt) KMSG_COMPONENT ": " fmt -#include +#include #include #include #include diff --git a/drivers/s390/virtio/virtio_ccw.c b/drivers/s390/virtio/virtio_ccw.c index 8f5c1d7f751a..97b6f197f007 100644 --- a/drivers/s390/virtio/virtio_ccw.c +++ b/drivers/s390/virtio/virtio_ccw.c @@ -9,7 +9,7 @@ #include #include -#include +#include #include #include #include diff --git a/drivers/sfi/sfi_core.c b/drivers/sfi/sfi_core.c index 153b3f3cc795..a5136901dd8a 100644 --- a/drivers/sfi/sfi_core.c +++ b/drivers/sfi/sfi_core.c @@ -59,7 +59,7 @@ #define KMSG_COMPONENT "SFI" #define pr_fmt(fmt) KMSG_COMPONENT ": " fmt -#include +#include #include #include #include diff --git a/drivers/tty/serial/cpm_uart/cpm_uart_core.c b/drivers/tty/serial/cpm_uart/cpm_uart_core.c index 79ad30d34949..b929c7ae3a27 100644 --- a/drivers/tty/serial/cpm_uart/cpm_uart_core.c +++ b/drivers/tty/serial/cpm_uart/cpm_uart_core.c @@ -24,7 +24,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/drivers/tty/serial/cpm_uart/cpm_uart_cpm1.c b/drivers/tty/serial/cpm_uart/cpm_uart_cpm1.c index 4eba17f3d293..56fc527015cb 100644 --- a/drivers/tty/serial/cpm_uart/cpm_uart_cpm1.c +++ b/drivers/tty/serial/cpm_uart/cpm_uart_cpm1.c @@ -19,7 +19,7 @@ #include #include #include -#include +#include #include #include diff --git a/drivers/tty/serial/cpm_uart/cpm_uart_cpm2.c b/drivers/tty/serial/cpm_uart/cpm_uart_cpm2.c index e3bff068dc3c..6a1cd03bfe39 100644 --- a/drivers/tty/serial/cpm_uart/cpm_uart_cpm2.c +++ b/drivers/tty/serial/cpm_uart/cpm_uart_cpm2.c @@ -19,7 +19,7 @@ #include #include #include -#include +#include #include #include diff --git a/drivers/usb/early/xhci-dbc.c b/drivers/usb/early/xhci-dbc.c index ddc5fa88f268..d2652dccc699 100644 --- a/drivers/usb/early/xhci-dbc.c +++ b/drivers/usb/early/xhci-dbc.c @@ -12,7 +12,6 @@ #include #include #include -#include #include #include #include diff --git a/drivers/xen/balloon.c b/drivers/xen/balloon.c index e12bb256036f..a3f5cbfcd4a1 100644 --- a/drivers/xen/balloon.c +++ b/drivers/xen/balloon.c @@ -44,7 +44,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/drivers/xen/events/events_base.c b/drivers/xen/events/events_base.c index e6c1934734b7..93194f3e7540 100644 --- a/drivers/xen/events/events_base.c +++ b/drivers/xen/events/events_base.c @@ -28,7 +28,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/drivers/xen/grant-table.c b/drivers/xen/grant-table.c index 84575baceebc..f15f89df1f36 100644 --- a/drivers/xen/grant-table.c +++ b/drivers/xen/grant-table.c @@ -33,7 +33,7 @@ #define pr_fmt(fmt) "xen:" KBUILD_MODNAME ": " fmt -#include +#include #include #include #include diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c index c5f26a87d238..2a7f545bd0b5 100644 --- a/drivers/xen/swiotlb-xen.c +++ b/drivers/xen/swiotlb-xen.c @@ -35,7 +35,6 @@ #define pr_fmt(fmt) "xen:" KBUILD_MODNAME ": " fmt -#include #include #include #include diff --git a/drivers/xen/xen-selfballoon.c b/drivers/xen/xen-selfballoon.c index 55988b8418ee..5165aa82bf7d 100644 --- a/drivers/xen/xen-selfballoon.c +++ b/drivers/xen/xen-selfballoon.c @@ -68,7 +68,7 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include -#include +#include #include #include #include diff --git a/fs/dcache.c b/fs/dcache.c index c2e443fb76ae..2593153471cf 100644 --- a/fs/dcache.c +++ b/fs/dcache.c @@ -26,7 +26,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/fs/inode.c b/fs/inode.c index 9b808986d440..9e198f00b64c 100644 --- a/fs/inode.c +++ b/fs/inode.c @@ -10,7 +10,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/fs/namespace.c b/fs/namespace.c index d86830c86ce8..98d27da43304 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -23,7 +23,7 @@ #include #include #include -#include +#include #include #include diff --git a/fs/proc/kcore.c b/fs/proc/kcore.c index d297fe4472a9..bbcc185062bb 100644 --- a/fs/proc/kcore.c +++ b/fs/proc/kcore.c @@ -22,7 +22,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/fs/proc/page.c b/fs/proc/page.c index 792c78a49174..6c517b11acf8 100644 --- a/fs/proc/page.c +++ b/fs/proc/page.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -#include +#include #include #include #include diff --git a/fs/proc/vmcore.c b/fs/proc/vmcore.c index 0377a104495b..3fe90443c1bb 100644 --- a/fs/proc/vmcore.c +++ b/fs/proc/vmcore.c @@ -16,7 +16,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h deleted file mode 100644 index b58873a567b2..000000000000 --- a/include/linux/bootmem.h +++ /dev/null @@ -1,173 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * Discontiguous memory support, Kanoj Sarcar, SGI, Nov 1999 - */ -#ifndef _LINUX_BOOTMEM_H -#define _LINUX_BOOTMEM_H - -#include -#include -#include -#include - -/* - * simple boot-time physical memory area allocator. - */ - -extern unsigned long max_low_pfn; -extern unsigned long min_low_pfn; - -/* - * highest page - */ -extern unsigned long max_pfn; -/* - * highest possible page - */ -extern unsigned long long max_possible_pfn; - -extern unsigned long memblock_free_all(void); -extern void reset_node_managed_pages(pg_data_t *pgdat); -extern void reset_all_zones_managed_pages(void); - -/* We are using top down, so it is safe to use 0 here */ -#define BOOTMEM_LOW_LIMIT 0 - -#ifndef ARCH_LOW_ADDRESS_LIMIT -#define ARCH_LOW_ADDRESS_LIMIT 0xffffffffUL -#endif - -/* FIXME: use MEMBLOCK_ALLOC_* variants here */ -#define BOOTMEM_ALLOC_ACCESSIBLE 0 -#define BOOTMEM_ALLOC_ANYWHERE (~(phys_addr_t)0) - -/* FIXME: Move to memblock.h at a point where we remove nobootmem.c */ -void *memblock_alloc_try_nid_raw(phys_addr_t size, phys_addr_t align, - phys_addr_t min_addr, - phys_addr_t max_addr, int nid); -void *memblock_alloc_try_nid_nopanic(phys_addr_t size, - phys_addr_t align, phys_addr_t min_addr, - phys_addr_t max_addr, int nid); -void *memblock_alloc_try_nid(phys_addr_t size, phys_addr_t align, - phys_addr_t min_addr, phys_addr_t max_addr, int nid); -void __memblock_free_early(phys_addr_t base, phys_addr_t size); -void __memblock_free_late(phys_addr_t base, phys_addr_t size); - -static inline void * __init memblock_alloc( - phys_addr_t size, phys_addr_t align) -{ - return memblock_alloc_try_nid(size, align, BOOTMEM_LOW_LIMIT, - BOOTMEM_ALLOC_ACCESSIBLE, - NUMA_NO_NODE); -} - -static inline void * __init memblock_alloc_raw( - phys_addr_t size, phys_addr_t align) -{ - return memblock_alloc_try_nid_raw(size, align, BOOTMEM_LOW_LIMIT, - BOOTMEM_ALLOC_ACCESSIBLE, - NUMA_NO_NODE); -} - -static inline void * __init memblock_alloc_from( - phys_addr_t size, phys_addr_t align, phys_addr_t min_addr) -{ - return memblock_alloc_try_nid(size, align, min_addr, - BOOTMEM_ALLOC_ACCESSIBLE, - NUMA_NO_NODE); -} - -static inline void * __init memblock_alloc_nopanic( - phys_addr_t size, phys_addr_t align) -{ - return memblock_alloc_try_nid_nopanic(size, align, - BOOTMEM_LOW_LIMIT, - BOOTMEM_ALLOC_ACCESSIBLE, - NUMA_NO_NODE); -} - -static inline void * __init memblock_alloc_low( - phys_addr_t size, phys_addr_t align) -{ - return memblock_alloc_try_nid(size, align, - BOOTMEM_LOW_LIMIT, - ARCH_LOW_ADDRESS_LIMIT, - NUMA_NO_NODE); -} -static inline void * __init memblock_alloc_low_nopanic( - phys_addr_t size, phys_addr_t align) -{ - return memblock_alloc_try_nid_nopanic(size, align, - BOOTMEM_LOW_LIMIT, - ARCH_LOW_ADDRESS_LIMIT, - NUMA_NO_NODE); -} - -static inline void * __init memblock_alloc_from_nopanic( - phys_addr_t size, phys_addr_t align, phys_addr_t min_addr) -{ - return memblock_alloc_try_nid_nopanic(size, align, min_addr, - BOOTMEM_ALLOC_ACCESSIBLE, - NUMA_NO_NODE); -} - -static inline void * __init memblock_alloc_node( - phys_addr_t size, phys_addr_t align, int nid) -{ - return memblock_alloc_try_nid(size, align, BOOTMEM_LOW_LIMIT, - BOOTMEM_ALLOC_ACCESSIBLE, nid); -} - -static inline void * __init memblock_alloc_node_nopanic( - phys_addr_t size, int nid) -{ - return memblock_alloc_try_nid_nopanic(size, 0, BOOTMEM_LOW_LIMIT, - BOOTMEM_ALLOC_ACCESSIBLE, - nid); -} - -static inline void __init memblock_free_early( - phys_addr_t base, phys_addr_t size) -{ - __memblock_free_early(base, size); -} - -static inline void __init memblock_free_early_nid( - phys_addr_t base, phys_addr_t size, int nid) -{ - __memblock_free_early(base, size); -} - -static inline void __init memblock_free_late( - phys_addr_t base, phys_addr_t size) -{ - __memblock_free_late(base, size); -} - -extern void *alloc_large_system_hash(const char *tablename, - unsigned long bucketsize, - unsigned long numentries, - int scale, - int flags, - unsigned int *_hash_shift, - unsigned int *_hash_mask, - unsigned long low_limit, - unsigned long high_limit); - -#define HASH_EARLY 0x00000001 /* Allocating during early boot? */ -#define HASH_SMALL 0x00000002 /* sub-page allocation allowed, min - * shift passed via *_hash_shift */ -#define HASH_ZERO 0x00000004 /* Zero allocated hash table */ - -/* Only NUMA needs hash distribution. 64bit NUMA architectures have - * sufficient vmalloc space. - */ -#ifdef CONFIG_NUMA -#define HASHDIST_DEFAULT IS_ENABLED(CONFIG_64BIT) -extern int hashdist; /* Distribute hashes across NUMA nodes? */ -#else -#define hashdist (0) -#endif - - -#endif /* _LINUX_BOOTMEM_H */ diff --git a/include/linux/memblock.h b/include/linux/memblock.h index 9d46a7204975..1b4d85879cbe 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -15,6 +15,19 @@ #include #include +#include + +extern unsigned long max_low_pfn; +extern unsigned long min_low_pfn; + +/* + * highest page + */ +extern unsigned long max_pfn; +/* + * highest possible page + */ +extern unsigned long long max_possible_pfn; #define INIT_MEMBLOCK_REGIONS 128 #define INIT_PHYSMEM_REGIONS 4 @@ -119,6 +132,10 @@ int memblock_mark_nomap(phys_addr_t base, phys_addr_t size); int memblock_clear_nomap(phys_addr_t base, phys_addr_t size); enum memblock_flags choose_memblock_flags(void); +unsigned long memblock_free_all(void); +void reset_node_managed_pages(pg_data_t *pgdat); +void reset_all_zones_managed_pages(void); + /* Low level functions */ int memblock_add_range(struct memblock_type *type, phys_addr_t base, phys_addr_t size, @@ -300,11 +317,116 @@ static inline int memblock_get_region_node(const struct memblock_region *r) } #endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */ +/* Flags for memblock allocation APIs */ +#define MEMBLOCK_ALLOC_ANYWHERE (~(phys_addr_t)0) +#define MEMBLOCK_ALLOC_ACCESSIBLE 0 + +/* We are using top down, so it is safe to use 0 here */ +#define MEMBLOCK_LOW_LIMIT 0 + +#ifndef ARCH_LOW_ADDRESS_LIMIT +#define ARCH_LOW_ADDRESS_LIMIT 0xffffffffUL +#endif + phys_addr_t memblock_phys_alloc_nid(phys_addr_t size, phys_addr_t align, int nid); phys_addr_t memblock_phys_alloc_try_nid(phys_addr_t size, phys_addr_t align, int nid); phys_addr_t memblock_phys_alloc(phys_addr_t size, phys_addr_t align); +void *memblock_alloc_try_nid_raw(phys_addr_t size, phys_addr_t align, + phys_addr_t min_addr, phys_addr_t max_addr, + int nid); +void *memblock_alloc_try_nid_nopanic(phys_addr_t size, phys_addr_t align, + phys_addr_t min_addr, phys_addr_t max_addr, + int nid); +void *memblock_alloc_try_nid(phys_addr_t size, phys_addr_t align, + phys_addr_t min_addr, phys_addr_t max_addr, + int nid); + +static inline void * __init memblock_alloc(phys_addr_t size, phys_addr_t align) +{ + return memblock_alloc_try_nid(size, align, MEMBLOCK_LOW_LIMIT, + MEMBLOCK_ALLOC_ACCESSIBLE, NUMA_NO_NODE); +} + +static inline void * __init memblock_alloc_raw(phys_addr_t size, + phys_addr_t align) +{ + return memblock_alloc_try_nid_raw(size, align, MEMBLOCK_LOW_LIMIT, + MEMBLOCK_ALLOC_ACCESSIBLE, + NUMA_NO_NODE); +} + +static inline void * __init memblock_alloc_from(phys_addr_t size, + phys_addr_t align, + phys_addr_t min_addr) +{ + return memblock_alloc_try_nid(size, align, min_addr, + MEMBLOCK_ALLOC_ACCESSIBLE, NUMA_NO_NODE); +} + +static inline void * __init memblock_alloc_nopanic(phys_addr_t size, + phys_addr_t align) +{ + return memblock_alloc_try_nid_nopanic(size, align, MEMBLOCK_LOW_LIMIT, + MEMBLOCK_ALLOC_ACCESSIBLE, + NUMA_NO_NODE); +} + +static inline void * __init memblock_alloc_low(phys_addr_t size, + phys_addr_t align) +{ + return memblock_alloc_try_nid(size, align, MEMBLOCK_LOW_LIMIT, + ARCH_LOW_ADDRESS_LIMIT, NUMA_NO_NODE); +} +static inline void * __init memblock_alloc_low_nopanic(phys_addr_t size, + phys_addr_t align) +{ + return memblock_alloc_try_nid_nopanic(size, align, MEMBLOCK_LOW_LIMIT, + ARCH_LOW_ADDRESS_LIMIT, + NUMA_NO_NODE); +} + +static inline void * __init memblock_alloc_from_nopanic(phys_addr_t size, + phys_addr_t align, + phys_addr_t min_addr) +{ + return memblock_alloc_try_nid_nopanic(size, align, min_addr, + MEMBLOCK_ALLOC_ACCESSIBLE, + NUMA_NO_NODE); +} + +static inline void * __init memblock_alloc_node(phys_addr_t size, + phys_addr_t align, int nid) +{ + return memblock_alloc_try_nid(size, align, MEMBLOCK_LOW_LIMIT, + MEMBLOCK_ALLOC_ACCESSIBLE, nid); +} + +static inline void * __init memblock_alloc_node_nopanic(phys_addr_t size, + int nid) +{ + return memblock_alloc_try_nid_nopanic(size, 0, MEMBLOCK_LOW_LIMIT, + MEMBLOCK_ALLOC_ACCESSIBLE, nid); +} + +static inline void __init memblock_free_early(phys_addr_t base, + phys_addr_t size) +{ + __memblock_free_early(base, size); +} + +static inline void __init memblock_free_early_nid(phys_addr_t base, + phys_addr_t size, int nid) +{ + __memblock_free_early(base, size); +} + +static inline void __init memblock_free_late(phys_addr_t base, phys_addr_t size) +{ + __memblock_free_late(base, size); +} + /* * Set the allocation direction to bottom-up or top-down. */ @@ -323,10 +445,6 @@ static inline bool memblock_bottom_up(void) return memblock.bottom_up; } -/* Flags for memblock_alloc_base() amd __memblock_alloc_base() */ -#define MEMBLOCK_ALLOC_ANYWHERE (~(phys_addr_t)0) -#define MEMBLOCK_ALLOC_ACCESSIBLE 0 - phys_addr_t __init memblock_alloc_range(phys_addr_t size, phys_addr_t align, phys_addr_t start, phys_addr_t end, enum memblock_flags flags); @@ -432,6 +550,31 @@ static inline unsigned long memblock_region_reserved_end_pfn(const struct memblo i < memblock_type->cnt; \ i++, rgn = &memblock_type->regions[i]) +extern void *alloc_large_system_hash(const char *tablename, + unsigned long bucketsize, + unsigned long numentries, + int scale, + int flags, + unsigned int *_hash_shift, + unsigned int *_hash_mask, + unsigned long low_limit, + unsigned long high_limit); + +#define HASH_EARLY 0x00000001 /* Allocating during early boot? */ +#define HASH_SMALL 0x00000002 /* sub-page allocation allowed, min + * shift passed via *_hash_shift */ +#define HASH_ZERO 0x00000004 /* Zero allocated hash table */ + +/* Only NUMA needs hash distribution. 64bit NUMA architectures have + * sufficient vmalloc space. + */ +#ifdef CONFIG_NUMA +#define HASHDIST_DEFAULT IS_ENABLED(CONFIG_64BIT) +extern int hashdist; /* Distribute hashes across NUMA nodes? */ +#else +#define hashdist (0) +#endif + #ifdef CONFIG_MEMTEST extern void early_memtest(phys_addr_t start, phys_addr_t end); #else diff --git a/init/main.c b/init/main.c index 8cef69c61389..51b8e7b8ae5b 100644 --- a/init/main.c +++ b/init/main.c @@ -25,7 +25,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c index f14c376937e5..22a12ab5a5e9 100644 --- a/kernel/dma/direct.c +++ b/kernel/dma/direct.c @@ -4,7 +4,7 @@ * * DMA operations that map physical memory directly without using an IOMMU. */ -#include /* for max_pfn */ +#include /* for max_pfn */ #include #include #include diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c index 801da67e957b..5731daa09a32 100644 --- a/kernel/dma/swiotlb.c +++ b/kernel/dma/swiotlb.c @@ -40,7 +40,7 @@ #include #include -#include +#include #include #define CREATE_TRACE_POINTS diff --git a/kernel/futex.c b/kernel/futex.c index 3e2de8fc1891..f423f9b6577e 100644 --- a/kernel/futex.c +++ b/kernel/futex.c @@ -65,7 +65,7 @@ #include #include #include -#include +#include #include #include diff --git a/kernel/locking/qspinlock_paravirt.h b/kernel/locking/qspinlock_paravirt.h index 0130e488ebfe..8f36c27c1794 100644 --- a/kernel/locking/qspinlock_paravirt.h +++ b/kernel/locking/qspinlock_paravirt.h @@ -4,7 +4,7 @@ #endif #include -#include +#include #include /* diff --git a/kernel/pid.c b/kernel/pid.c index cdf63e53a014..b2f6c506035d 100644 --- a/kernel/pid.c +++ b/kernel/pid.c @@ -31,7 +31,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c index 34116a6097be..3c9e365438ad 100644 --- a/kernel/power/snapshot.c +++ b/kernel/power/snapshot.c @@ -23,7 +23,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c index 429e4a3833ca..1b2a029360b7 100644 --- a/kernel/printk/printk.c +++ b/kernel/printk/printk.c @@ -31,7 +31,6 @@ #include #include #include -#include #include #include #include diff --git a/kernel/profile.c b/kernel/profile.c index 9aa2a4445b0d..9c08a2c7cb1d 100644 --- a/kernel/profile.c +++ b/kernel/profile.c @@ -16,7 +16,7 @@ #include #include -#include +#include #include #include #include diff --git a/lib/cpumask.c b/lib/cpumask.c index 1405cb22e6bc..75b5e7672c4c 100644 --- a/lib/cpumask.c +++ b/lib/cpumask.c @@ -4,7 +4,7 @@ #include #include #include -#include +#include /** * cpumask_next - get the next cpu in a cpumask diff --git a/mm/hugetlb.c b/mm/hugetlb.c index e35d99844612..c007fb5fb8d5 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -15,7 +15,6 @@ #include #include #include -#include #include #include #include diff --git a/mm/kasan/kasan_init.c b/mm/kasan/kasan_init.c index 785a9707786b..c7550eb65922 100644 --- a/mm/kasan/kasan_init.c +++ b/mm/kasan/kasan_init.c @@ -10,11 +10,10 @@ * */ -#include +#include #include #include #include -#include #include #include #include diff --git a/mm/kmemleak.c b/mm/kmemleak.c index 4f7e4b5a2f08..877de4fa0720 100644 --- a/mm/kmemleak.c +++ b/mm/kmemleak.c @@ -92,7 +92,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/mm/memblock.c b/mm/memblock.c index 2ed73245b5da..c655342569f8 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -20,7 +20,6 @@ #include #include #include -#include #include #include diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 7e6509a53d79..41e326472ef9 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -33,7 +33,6 @@ #include #include #include -#include #include #include diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 5f3291601945..ef289fadec0e 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -20,7 +20,6 @@ #include #include #include -#include #include #include #include diff --git a/mm/page_ext.c b/mm/page_ext.c index 5323c2ade686..ae44f7adbe07 100644 --- a/mm/page_ext.c +++ b/mm/page_ext.c @@ -1,7 +1,7 @@ // SPDX-License-Identifier: GPL-2.0 #include #include -#include +#include #include #include #include diff --git a/mm/page_idle.c b/mm/page_idle.c index 6302bc62c27d..b9e4b42b33ab 100644 --- a/mm/page_idle.c +++ b/mm/page_idle.c @@ -1,6 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 #include -#include +#include #include #include #include diff --git a/mm/page_owner.c b/mm/page_owner.c index d80adfe702d3..87bc0dfdb52b 100644 --- a/mm/page_owner.c +++ b/mm/page_owner.c @@ -3,7 +3,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/mm/percpu.c b/mm/percpu.c index 3050c1d37d37..61cdbb3b3736 100644 --- a/mm/percpu.c +++ b/mm/percpu.c @@ -65,7 +65,7 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include -#include +#include #include #include #include diff --git a/mm/sparse-vmemmap.c b/mm/sparse-vmemmap.c index 7408cabed61a..7fec05796796 100644 --- a/mm/sparse-vmemmap.c +++ b/mm/sparse-vmemmap.c @@ -20,7 +20,6 @@ */ #include #include -#include #include #include #include diff --git a/mm/sparse.c b/mm/sparse.c index b139fbc61d10..ab2ac45e0440 100644 --- a/mm/sparse.c +++ b/mm/sparse.c @@ -5,7 +5,6 @@ #include #include #include -#include #include #include #include diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index f5c9ef2586de..411dd7a90046 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -19,7 +19,7 @@ #include #include #include -#include +#include #include #include diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 1834818ed07b..9e6bc4d6daa7 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -262,7 +262,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index ca3ed931f2a9..1976fddb9e00 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -81,7 +81,7 @@ #include #include -#include +#include #include #include #include diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index e948db29ab53..9b277bd36d1a 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -46,7 +46,7 @@ #include #include #include -#include +#include #include #include #include diff --git a/net/xfrm/xfrm_hash.c b/net/xfrm/xfrm_hash.c index 2ad33ce1ea17..eca8d84d99bf 100644 --- a/net/xfrm/xfrm_hash.c +++ b/net/xfrm/xfrm_hash.c @@ -6,7 +6,7 @@ #include #include -#include +#include #include #include #include -- cgit v1.2.3 From 7e1c4e27928e5f87b9b1eaf06dc31773b2f1e7f1 Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Tue, 30 Oct 2018 15:09:57 -0700 Subject: memblock: stop using implicit alignment to SMP_CACHE_BYTES When a memblock allocation APIs are called with align = 0, the alignment is implicitly set to SMP_CACHE_BYTES. Implicit alignment is done deep in the memblock allocator and it can come as a surprise. Not that such an alignment would be wrong even when used incorrectly but it is better to be explicit for the sake of clarity and the prinicple of the least surprise. Replace all such uses of memblock APIs with the 'align' parameter explicitly set to SMP_CACHE_BYTES and stop implicit alignment assignment in the memblock internal allocation functions. For the case when memblock APIs are used via helper functions, e.g. like iommu_arena_new_node() in Alpha, the helper functions were detected with Coccinelle's help and then manually examined and updated where appropriate. The direct memblock APIs users were updated using the semantic patch below: @@ expression size, min_addr, max_addr, nid; @@ ( | - memblock_alloc_try_nid_raw(size, 0, min_addr, max_addr, nid) + memblock_alloc_try_nid_raw(size, SMP_CACHE_BYTES, min_addr, max_addr, nid) | - memblock_alloc_try_nid_nopanic(size, 0, min_addr, max_addr, nid) + memblock_alloc_try_nid_nopanic(size, SMP_CACHE_BYTES, min_addr, max_addr, nid) | - memblock_alloc_try_nid(size, 0, min_addr, max_addr, nid) + memblock_alloc_try_nid(size, SMP_CACHE_BYTES, min_addr, max_addr, nid) | - memblock_alloc(size, 0) + memblock_alloc(size, SMP_CACHE_BYTES) | - memblock_alloc_raw(size, 0) + memblock_alloc_raw(size, SMP_CACHE_BYTES) | - memblock_alloc_from(size, 0, min_addr) + memblock_alloc_from(size, SMP_CACHE_BYTES, min_addr) | - memblock_alloc_nopanic(size, 0) + memblock_alloc_nopanic(size, SMP_CACHE_BYTES) | - memblock_alloc_low(size, 0) + memblock_alloc_low(size, SMP_CACHE_BYTES) | - memblock_alloc_low_nopanic(size, 0) + memblock_alloc_low_nopanic(size, SMP_CACHE_BYTES) | - memblock_alloc_from_nopanic(size, 0, min_addr) + memblock_alloc_from_nopanic(size, SMP_CACHE_BYTES, min_addr) | - memblock_alloc_node(size, 0, nid) + memblock_alloc_node(size, SMP_CACHE_BYTES, nid) ) [mhocko@suse.com: changelog update] [akpm@linux-foundation.org: coding-style fixes] [rppt@linux.ibm.com: fix missed uses of implicit alignment] Link: http://lkml.kernel.org/r/20181016133656.GA10925@rapoport-lnx Link: http://lkml.kernel.org/r/1538687224-17535-1-git-send-email-rppt@linux.vnet.ibm.com Signed-off-by: Mike Rapoport Suggested-by: Michal Hocko Acked-by: Paul Burton [MIPS] Acked-by: Michael Ellerman [powerpc] Acked-by: Michal Hocko Cc: Catalin Marinas Cc: Chris Zankel Cc: Geert Uytterhoeven Cc: Guan Xuetao Cc: Ingo Molnar Cc: Matt Turner Cc: Michal Simek Cc: Richard Weinberger Cc: Russell King Cc: Thomas Gleixner Cc: Tony Luck Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/alpha/kernel/core_apecs.c | 3 ++- arch/alpha/kernel/core_lca.c | 3 ++- arch/alpha/kernel/core_marvel.c | 4 ++-- arch/alpha/kernel/core_mcpcia.c | 6 +++-- arch/alpha/kernel/core_t2.c | 2 +- arch/alpha/kernel/core_titan.c | 6 +++-- arch/alpha/kernel/core_tsunami.c | 6 +++-- arch/alpha/kernel/core_wildfire.c | 6 +++-- arch/alpha/kernel/pci-noop.c | 4 ++-- arch/alpha/kernel/pci.c | 4 ++-- arch/alpha/kernel/pci_iommu.c | 4 ++-- arch/arm/kernel/setup.c | 4 ++-- arch/arm/mach-omap2/omap_hwmod.c | 8 ++++--- arch/arm64/kernel/setup.c | 2 +- arch/ia64/kernel/mca.c | 4 ++-- arch/ia64/mm/tlb.c | 6 +++-- arch/ia64/sn/kernel/io_common.c | 4 +++- arch/ia64/sn/kernel/setup.c | 5 ++-- arch/m68k/sun3/sun3dvma.c | 2 +- arch/microblaze/mm/init.c | 2 +- arch/mips/kernel/setup.c | 2 +- arch/powerpc/kernel/paca.c | 2 +- arch/powerpc/kernel/pci_32.c | 3 ++- arch/powerpc/lib/alloc.c | 2 +- arch/powerpc/mm/mmu_context_nohash.c | 7 +++--- arch/powerpc/platforms/powermac/nvram.c | 2 +- arch/powerpc/platforms/powernv/pci-ioda.c | 6 ++--- arch/powerpc/sysdev/msi_bitmap.c | 2 +- arch/um/drivers/net_kern.c | 2 +- arch/um/drivers/vector_kern.c | 2 +- arch/um/kernel/initrd.c | 2 +- arch/unicore32/kernel/setup.c | 2 +- arch/x86/kernel/acpi/boot.c | 2 +- arch/x86/kernel/apic/io_apic.c | 2 +- arch/x86/kernel/e820.c | 3 ++- arch/x86/platform/olpc/olpc_dt.c | 2 +- arch/xtensa/platforms/iss/network.c | 2 +- drivers/clk/ti/clk.c | 2 +- drivers/firmware/efi/memmap.c | 2 +- drivers/firmware/memmap.c | 3 ++- drivers/macintosh/smu.c | 2 +- drivers/of/of_reserved_mem.c | 1 + include/linux/memblock.h | 3 ++- init/main.c | 13 +++++++---- kernel/power/snapshot.c | 3 ++- lib/cpumask.c | 2 +- mm/memblock.c | 8 ------- mm/page_alloc.c | 6 +++-- mm/percpu.c | 38 ++++++++++++++++--------------- mm/sparse.c | 3 ++- 50 files changed, 120 insertions(+), 96 deletions(-) (limited to 'mm') diff --git a/arch/alpha/kernel/core_apecs.c b/arch/alpha/kernel/core_apecs.c index 1bf3eef34c22..6df765ff2b10 100644 --- a/arch/alpha/kernel/core_apecs.c +++ b/arch/alpha/kernel/core_apecs.c @@ -346,7 +346,8 @@ apecs_init_arch(void) * Window 1 is direct access 1GB at 1GB * Window 2 is scatter-gather 8MB at 8MB (for isa) */ - hose->sg_isa = iommu_arena_new(hose, 0x00800000, 0x00800000, 0); + hose->sg_isa = iommu_arena_new(hose, 0x00800000, 0x00800000, + SMP_CACHE_BYTES); hose->sg_pci = NULL; __direct_map_base = 0x40000000; __direct_map_size = 0x40000000; diff --git a/arch/alpha/kernel/core_lca.c b/arch/alpha/kernel/core_lca.c index 81c0c43635b0..57e0750419f2 100644 --- a/arch/alpha/kernel/core_lca.c +++ b/arch/alpha/kernel/core_lca.c @@ -275,7 +275,8 @@ lca_init_arch(void) * Note that we do not try to save any of the DMA window CSRs * before setting them, since we cannot read those CSRs on LCA. */ - hose->sg_isa = iommu_arena_new(hose, 0x00800000, 0x00800000, 0); + hose->sg_isa = iommu_arena_new(hose, 0x00800000, 0x00800000, + SMP_CACHE_BYTES); hose->sg_pci = NULL; __direct_map_base = 0x40000000; __direct_map_size = 0x40000000; diff --git a/arch/alpha/kernel/core_marvel.c b/arch/alpha/kernel/core_marvel.c index 8a568c4d8e81..c1d0c18c71ca 100644 --- a/arch/alpha/kernel/core_marvel.c +++ b/arch/alpha/kernel/core_marvel.c @@ -82,7 +82,7 @@ mk_resource_name(int pe, int port, char *str) char *name; sprintf(tmp, "PCI %s PE %d PORT %d", str, pe, port); - name = memblock_alloc(strlen(tmp) + 1, 0); + name = memblock_alloc(strlen(tmp) + 1, SMP_CACHE_BYTES); strcpy(name, tmp); return name; @@ -117,7 +117,7 @@ alloc_io7(unsigned int pe) return NULL; } - io7 = memblock_alloc(sizeof(*io7), 0); + io7 = memblock_alloc(sizeof(*io7), SMP_CACHE_BYTES); io7->pe = pe; raw_spin_lock_init(&io7->irq_lock); diff --git a/arch/alpha/kernel/core_mcpcia.c b/arch/alpha/kernel/core_mcpcia.c index b1549db54260..74b1d018124c 100644 --- a/arch/alpha/kernel/core_mcpcia.c +++ b/arch/alpha/kernel/core_mcpcia.c @@ -364,9 +364,11 @@ mcpcia_startup_hose(struct pci_controller *hose) * Window 1 is scatter-gather (up to) 1GB at 1GB (for pci) * Window 2 is direct access 2GB at 2GB */ - hose->sg_isa = iommu_arena_new(hose, 0x00800000, 0x00800000, 0); + hose->sg_isa = iommu_arena_new(hose, 0x00800000, 0x00800000, + SMP_CACHE_BYTES); hose->sg_pci = iommu_arena_new(hose, 0x40000000, - size_for_memory(0x40000000), 0); + size_for_memory(0x40000000), + SMP_CACHE_BYTES); __direct_map_base = 0x80000000; __direct_map_size = 0x80000000; diff --git a/arch/alpha/kernel/core_t2.c b/arch/alpha/kernel/core_t2.c index 2c00b61ca379..98d5b6ff8a76 100644 --- a/arch/alpha/kernel/core_t2.c +++ b/arch/alpha/kernel/core_t2.c @@ -351,7 +351,7 @@ t2_sg_map_window2(struct pci_controller *hose, /* Note we can only do 1 SG window, as the other is for direct, so do an ISA SG area, especially for the floppy. */ - hose->sg_isa = iommu_arena_new(hose, base, length, 0); + hose->sg_isa = iommu_arena_new(hose, base, length, SMP_CACHE_BYTES); hose->sg_pci = NULL; temp = (base & 0xfff00000UL) | ((base + length - 1) >> 20); diff --git a/arch/alpha/kernel/core_titan.c b/arch/alpha/kernel/core_titan.c index 97551597581b..2a2820fb1be6 100644 --- a/arch/alpha/kernel/core_titan.c +++ b/arch/alpha/kernel/core_titan.c @@ -316,10 +316,12 @@ titan_init_one_pachip_port(titan_pachip_port *port, int index) * Window 1 is direct access 1GB at 2GB * Window 2 is scatter-gather 1GB at 3GB */ - hose->sg_isa = iommu_arena_new(hose, 0x00800000, 0x00800000, 0); + hose->sg_isa = iommu_arena_new(hose, 0x00800000, 0x00800000, + SMP_CACHE_BYTES); hose->sg_isa->align_entry = 8; /* 64KB for ISA */ - hose->sg_pci = iommu_arena_new(hose, 0xc0000000, 0x40000000, 0); + hose->sg_pci = iommu_arena_new(hose, 0xc0000000, 0x40000000, + SMP_CACHE_BYTES); hose->sg_pci->align_entry = 4; /* Titan caches 4 PTEs at a time */ port->wsba[0].csr = hose->sg_isa->dma_base | 3; diff --git a/arch/alpha/kernel/core_tsunami.c b/arch/alpha/kernel/core_tsunami.c index f334b8928d72..fc1ab73f23de 100644 --- a/arch/alpha/kernel/core_tsunami.c +++ b/arch/alpha/kernel/core_tsunami.c @@ -319,12 +319,14 @@ tsunami_init_one_pchip(tsunami_pchip *pchip, int index) * NOTE: we need the align_entry settings for Acer devices on ES40, * specifically floppy and IDE when memory is larger than 2GB. */ - hose->sg_isa = iommu_arena_new(hose, 0x00800000, 0x00800000, 0); + hose->sg_isa = iommu_arena_new(hose, 0x00800000, 0x00800000, + SMP_CACHE_BYTES); /* Initially set for 4 PTEs, but will be overridden to 64K for ISA. */ hose->sg_isa->align_entry = 4; hose->sg_pci = iommu_arena_new(hose, 0x40000000, - size_for_memory(0x40000000), 0); + size_for_memory(0x40000000), + SMP_CACHE_BYTES); hose->sg_pci->align_entry = 4; /* Tsunami caches 4 PTEs at a time */ __direct_map_base = 0x80000000; diff --git a/arch/alpha/kernel/core_wildfire.c b/arch/alpha/kernel/core_wildfire.c index cad36fc6ed7d..353c03d15442 100644 --- a/arch/alpha/kernel/core_wildfire.c +++ b/arch/alpha/kernel/core_wildfire.c @@ -111,8 +111,10 @@ wildfire_init_hose(int qbbno, int hoseno) * ??? We ought to scale window 3 memory. * */ - hose->sg_isa = iommu_arena_new(hose, 0x00800000, 0x00800000, 0); - hose->sg_pci = iommu_arena_new(hose, 0xc0000000, 0x08000000, 0); + hose->sg_isa = iommu_arena_new(hose, 0x00800000, 0x00800000, + SMP_CACHE_BYTES); + hose->sg_pci = iommu_arena_new(hose, 0xc0000000, 0x08000000, + SMP_CACHE_BYTES); pci = WILDFIRE_pci(qbbno, hoseno); diff --git a/arch/alpha/kernel/pci-noop.c b/arch/alpha/kernel/pci-noop.c index a9378ee0c2f1..091cff3c68fd 100644 --- a/arch/alpha/kernel/pci-noop.c +++ b/arch/alpha/kernel/pci-noop.c @@ -33,7 +33,7 @@ alloc_pci_controller(void) { struct pci_controller *hose; - hose = memblock_alloc(sizeof(*hose), 0); + hose = memblock_alloc(sizeof(*hose), SMP_CACHE_BYTES); *hose_tail = hose; hose_tail = &hose->next; @@ -44,7 +44,7 @@ alloc_pci_controller(void) struct resource * __init alloc_resource(void) { - return memblock_alloc(sizeof(struct resource), 0); + return memblock_alloc(sizeof(struct resource), SMP_CACHE_BYTES); } SYSCALL_DEFINE3(pciconfig_iobase, long, which, unsigned long, bus, diff --git a/arch/alpha/kernel/pci.c b/arch/alpha/kernel/pci.c index 13937e72d875..97098127df83 100644 --- a/arch/alpha/kernel/pci.c +++ b/arch/alpha/kernel/pci.c @@ -392,7 +392,7 @@ alloc_pci_controller(void) { struct pci_controller *hose; - hose = memblock_alloc(sizeof(*hose), 0); + hose = memblock_alloc(sizeof(*hose), SMP_CACHE_BYTES); *hose_tail = hose; hose_tail = &hose->next; @@ -403,7 +403,7 @@ alloc_pci_controller(void) struct resource * __init alloc_resource(void) { - return memblock_alloc(sizeof(struct resource), 0); + return memblock_alloc(sizeof(struct resource), SMP_CACHE_BYTES); } diff --git a/arch/alpha/kernel/pci_iommu.c b/arch/alpha/kernel/pci_iommu.c index 82cf950bda2a..46e08e0d9181 100644 --- a/arch/alpha/kernel/pci_iommu.c +++ b/arch/alpha/kernel/pci_iommu.c @@ -79,7 +79,7 @@ iommu_arena_new_node(int nid, struct pci_controller *hose, dma_addr_t base, printk("%s: couldn't allocate arena from node %d\n" " falling back to system-wide allocation\n", __func__, nid); - arena = memblock_alloc(sizeof(*arena), 0); + arena = memblock_alloc(sizeof(*arena), SMP_CACHE_BYTES); } arena->ptes = memblock_alloc_node(sizeof(*arena), align, nid); @@ -92,7 +92,7 @@ iommu_arena_new_node(int nid, struct pci_controller *hose, dma_addr_t base, #else /* CONFIG_DISCONTIGMEM */ - arena = memblock_alloc(sizeof(*arena), 0); + arena = memblock_alloc(sizeof(*arena), SMP_CACHE_BYTES); arena->ptes = memblock_alloc_from(mem_size, align, 0); #endif /* CONFIG_DISCONTIGMEM */ diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c index 840a4adc69fc..ac7e08886863 100644 --- a/arch/arm/kernel/setup.c +++ b/arch/arm/kernel/setup.c @@ -856,7 +856,7 @@ static void __init request_standard_resources(const struct machine_desc *mdesc) */ boot_alias_start = phys_to_idmap(start); if (arm_has_idmap_alias() && boot_alias_start != IDMAP_INVALID_ADDR) { - res = memblock_alloc(sizeof(*res), 0); + res = memblock_alloc(sizeof(*res), SMP_CACHE_BYTES); res->name = "System RAM (boot alias)"; res->start = boot_alias_start; res->end = phys_to_idmap(end); @@ -864,7 +864,7 @@ static void __init request_standard_resources(const struct machine_desc *mdesc) request_resource(&iomem_resource, res); } - res = memblock_alloc(sizeof(*res), 0); + res = memblock_alloc(sizeof(*res), SMP_CACHE_BYTES); res->name = "System RAM"; res->start = start; res->end = end; diff --git a/arch/arm/mach-omap2/omap_hwmod.c b/arch/arm/mach-omap2/omap_hwmod.c index cd5732ab0cdf..083dcd9942ce 100644 --- a/arch/arm/mach-omap2/omap_hwmod.c +++ b/arch/arm/mach-omap2/omap_hwmod.c @@ -726,7 +726,7 @@ static int __init _setup_clkctrl_provider(struct device_node *np) u64 size; int i; - provider = memblock_alloc(sizeof(*provider), 0); + provider = memblock_alloc(sizeof(*provider), SMP_CACHE_BYTES); if (!provider) return -ENOMEM; @@ -736,12 +736,14 @@ static int __init _setup_clkctrl_provider(struct device_node *np) of_property_count_elems_of_size(np, "reg", sizeof(u32)) / 2; provider->addr = - memblock_alloc(sizeof(void *) * provider->num_addrs, 0); + memblock_alloc(sizeof(void *) * provider->num_addrs, + SMP_CACHE_BYTES); if (!provider->addr) return -ENOMEM; provider->size = - memblock_alloc(sizeof(u32) * provider->num_addrs, 0); + memblock_alloc(sizeof(u32) * provider->num_addrs, + SMP_CACHE_BYTES); if (!provider->size) return -ENOMEM; diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c index 7ce7306f1d75..953e316521fc 100644 --- a/arch/arm64/kernel/setup.c +++ b/arch/arm64/kernel/setup.c @@ -218,7 +218,7 @@ static void __init request_standard_resources(void) num_standard_resources = memblock.memory.cnt; standard_resources = memblock_alloc_low(num_standard_resources * sizeof(*standard_resources), - 0); + SMP_CACHE_BYTES); for_each_memblock(memory, region) { res = &standard_resources[i++]; diff --git a/arch/ia64/kernel/mca.c b/arch/ia64/kernel/mca.c index 9a6603f8e409..91bd1e129379 100644 --- a/arch/ia64/kernel/mca.c +++ b/arch/ia64/kernel/mca.c @@ -361,9 +361,9 @@ static ia64_state_log_t ia64_state_log[IA64_MAX_LOG_TYPES]; #define IA64_LOG_ALLOCATE(it, size) \ {ia64_state_log[it].isl_log[IA64_LOG_CURR_INDEX(it)] = \ - (ia64_err_rec_t *)memblock_alloc(size, 0); \ + (ia64_err_rec_t *)memblock_alloc(size, SMP_CACHE_BYTES); \ ia64_state_log[it].isl_log[IA64_LOG_NEXT_INDEX(it)] = \ - (ia64_err_rec_t *)memblock_alloc(size, 0);} + (ia64_err_rec_t *)memblock_alloc(size, SMP_CACHE_BYTES);} #define IA64_LOG_LOCK_INIT(it) spin_lock_init(&ia64_state_log[it].isl_lock) #define IA64_LOG_LOCK(it) spin_lock_irqsave(&ia64_state_log[it].isl_lock, s) #define IA64_LOG_UNLOCK(it) spin_unlock_irqrestore(&ia64_state_log[it].isl_lock,s) diff --git a/arch/ia64/mm/tlb.c b/arch/ia64/mm/tlb.c index ab545daff7c3..9340bcb4f29c 100644 --- a/arch/ia64/mm/tlb.c +++ b/arch/ia64/mm/tlb.c @@ -59,8 +59,10 @@ struct ia64_tr_entry *ia64_idtrs[NR_CPUS]; void __init mmu_context_init (void) { - ia64_ctx.bitmap = memblock_alloc((ia64_ctx.max_ctx + 1) >> 3, 0); - ia64_ctx.flushmap = memblock_alloc((ia64_ctx.max_ctx + 1) >> 3, 0); + ia64_ctx.bitmap = memblock_alloc((ia64_ctx.max_ctx + 1) >> 3, + SMP_CACHE_BYTES); + ia64_ctx.flushmap = memblock_alloc((ia64_ctx.max_ctx + 1) >> 3, + SMP_CACHE_BYTES); } /* diff --git a/arch/ia64/sn/kernel/io_common.c b/arch/ia64/sn/kernel/io_common.c index 98f55220c67d..8df13d0d96fa 100644 --- a/arch/ia64/sn/kernel/io_common.c +++ b/arch/ia64/sn/kernel/io_common.c @@ -391,7 +391,9 @@ void __init hubdev_init_node(nodepda_t * npda, cnodeid_t node) if (node >= num_online_nodes()) /* Headless/memless IO nodes */ node = 0; - hubdev_info = (struct hubdev_info *)memblock_alloc_node(size, 0, node); + hubdev_info = (struct hubdev_info *)memblock_alloc_node(size, + SMP_CACHE_BYTES, + node); npda->pdinfo = (void *)hubdev_info; } diff --git a/arch/ia64/sn/kernel/setup.c b/arch/ia64/sn/kernel/setup.c index 71ad6b0ccab4..a6d40a2c5bff 100644 --- a/arch/ia64/sn/kernel/setup.c +++ b/arch/ia64/sn/kernel/setup.c @@ -511,7 +511,8 @@ static void __init sn_init_pdas(char **cmdline_p) */ for_each_online_node(cnode) { nodepdaindr[cnode] = - memblock_alloc_node(sizeof(nodepda_t), 0, cnode); + memblock_alloc_node(sizeof(nodepda_t), SMP_CACHE_BYTES, + cnode); memset(nodepdaindr[cnode]->phys_cpuid, -1, sizeof(nodepdaindr[cnode]->phys_cpuid)); spin_lock_init(&nodepdaindr[cnode]->ptc_lock); @@ -522,7 +523,7 @@ static void __init sn_init_pdas(char **cmdline_p) */ for (cnode = num_online_nodes(); cnode < num_cnodes; cnode++) nodepdaindr[cnode] = - memblock_alloc_node(sizeof(nodepda_t), 0, 0); + memblock_alloc_node(sizeof(nodepda_t), SMP_CACHE_BYTES, 0); /* * Now copy the array of nodepda pointers to each nodepda. diff --git a/arch/m68k/sun3/sun3dvma.c b/arch/m68k/sun3/sun3dvma.c index 8be8b750c629..4d64711d3d47 100644 --- a/arch/m68k/sun3/sun3dvma.c +++ b/arch/m68k/sun3/sun3dvma.c @@ -268,7 +268,7 @@ void __init dvma_init(void) list_add(&(hole->list), &hole_list); iommu_use = memblock_alloc(IOMMU_TOTAL_ENTRIES * sizeof(unsigned long), - 0); + SMP_CACHE_BYTES); dvma_unmap_iommu(DVMA_START, DVMA_SIZE); diff --git a/arch/microblaze/mm/init.c b/arch/microblaze/mm/init.c index 8c14988f52f2..b17fd8aafd64 100644 --- a/arch/microblaze/mm/init.c +++ b/arch/microblaze/mm/init.c @@ -376,7 +376,7 @@ void * __ref zalloc_maybe_bootmem(size_t size, gfp_t mask) if (mem_init_done) p = kzalloc(size, mask); else { - p = memblock_alloc(size, 0); + p = memblock_alloc(size, SMP_CACHE_BYTES); if (p) memset(p, 0, size); } diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c index 41c1683761bb..ea09ed6a80a9 100644 --- a/arch/mips/kernel/setup.c +++ b/arch/mips/kernel/setup.c @@ -916,7 +916,7 @@ static void __init resource_init(void) if (end >= HIGHMEM_START) end = HIGHMEM_START - 1; - res = memblock_alloc(sizeof(struct resource), 0); + res = memblock_alloc(sizeof(struct resource), SMP_CACHE_BYTES); res->start = start; res->end = end; diff --git a/arch/powerpc/kernel/paca.c b/arch/powerpc/kernel/paca.c index f331a0054b3a..913bfca09c4f 100644 --- a/arch/powerpc/kernel/paca.c +++ b/arch/powerpc/kernel/paca.c @@ -198,7 +198,7 @@ void __init allocate_paca_ptrs(void) paca_nr_cpu_ids = nr_cpu_ids; paca_ptrs_size = sizeof(struct paca_struct *) * nr_cpu_ids; - paca_ptrs = __va(memblock_phys_alloc(paca_ptrs_size, 0)); + paca_ptrs = __va(memblock_phys_alloc(paca_ptrs_size, SMP_CACHE_BYTES)); memset(paca_ptrs, 0x88, paca_ptrs_size); } diff --git a/arch/powerpc/kernel/pci_32.c b/arch/powerpc/kernel/pci_32.c index 274bd1442dd9..d3f04f2d8249 100644 --- a/arch/powerpc/kernel/pci_32.c +++ b/arch/powerpc/kernel/pci_32.c @@ -203,7 +203,8 @@ pci_create_OF_bus_map(void) struct property* of_prop; struct device_node *dn; - of_prop = memblock_alloc(sizeof(struct property) + 256, 0); + of_prop = memblock_alloc(sizeof(struct property) + 256, + SMP_CACHE_BYTES); dn = of_find_node_by_path("/"); if (dn) { memset(of_prop, -1, sizeof(struct property) + 256); diff --git a/arch/powerpc/lib/alloc.c b/arch/powerpc/lib/alloc.c index 5b61704447c1..dedf88a76f58 100644 --- a/arch/powerpc/lib/alloc.c +++ b/arch/powerpc/lib/alloc.c @@ -14,7 +14,7 @@ void * __ref zalloc_maybe_bootmem(size_t size, gfp_t mask) if (slab_is_available()) p = kzalloc(size, mask); else { - p = memblock_alloc(size, 0); + p = memblock_alloc(size, SMP_CACHE_BYTES); } return p; } diff --git a/arch/powerpc/mm/mmu_context_nohash.c b/arch/powerpc/mm/mmu_context_nohash.c index 67b9d7b669a1..2faca46ad720 100644 --- a/arch/powerpc/mm/mmu_context_nohash.c +++ b/arch/powerpc/mm/mmu_context_nohash.c @@ -461,10 +461,11 @@ void __init mmu_context_init(void) /* * Allocate the maps used by context management */ - context_map = memblock_alloc(CTX_MAP_SIZE, 0); - context_mm = memblock_alloc(sizeof(void *) * (LAST_CONTEXT + 1), 0); + context_map = memblock_alloc(CTX_MAP_SIZE, SMP_CACHE_BYTES); + context_mm = memblock_alloc(sizeof(void *) * (LAST_CONTEXT + 1), + SMP_CACHE_BYTES); #ifdef CONFIG_SMP - stale_map[boot_cpuid] = memblock_alloc(CTX_MAP_SIZE, 0); + stale_map[boot_cpuid] = memblock_alloc(CTX_MAP_SIZE, SMP_CACHE_BYTES); cpuhp_setup_state_nocalls(CPUHP_POWERPC_MMU_CTX_PREPARE, "powerpc/mmu/ctx:prepare", diff --git a/arch/powerpc/platforms/powermac/nvram.c b/arch/powerpc/platforms/powermac/nvram.c index f3391be7c762..ae54d7fe68f3 100644 --- a/arch/powerpc/platforms/powermac/nvram.c +++ b/arch/powerpc/platforms/powermac/nvram.c @@ -513,7 +513,7 @@ static int __init core99_nvram_setup(struct device_node *dp, unsigned long addr) printk(KERN_ERR "nvram: no address\n"); return -EINVAL; } - nvram_image = memblock_alloc(NVRAM_SIZE, 0); + nvram_image = memblock_alloc(NVRAM_SIZE, SMP_CACHE_BYTES); nvram_data = ioremap(addr, NVRAM_SIZE*2); nvram_naddrs = 1; /* Make sure we get the correct case */ diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c index aba81cbf0b36..dd807446801e 100644 --- a/arch/powerpc/platforms/powernv/pci-ioda.c +++ b/arch/powerpc/platforms/powernv/pci-ioda.c @@ -3769,7 +3769,7 @@ static void __init pnv_pci_init_ioda_phb(struct device_node *np, phb_id = be64_to_cpup(prop64); pr_debug(" PHB-ID : 0x%016llx\n", phb_id); - phb = memblock_alloc(sizeof(*phb), 0); + phb = memblock_alloc(sizeof(*phb), SMP_CACHE_BYTES); /* Allocate PCI controller */ phb->hose = hose = pcibios_alloc_controller(np); @@ -3815,7 +3815,7 @@ static void __init pnv_pci_init_ioda_phb(struct device_node *np, else phb->diag_data_size = PNV_PCI_DIAG_BUF_SIZE; - phb->diag_data = memblock_alloc(phb->diag_data_size, 0); + phb->diag_data = memblock_alloc(phb->diag_data_size, SMP_CACHE_BYTES); /* Parse 32-bit and IO ranges (if any) */ pci_process_bridge_OF_ranges(hose, np, !hose->global_number); @@ -3874,7 +3874,7 @@ static void __init pnv_pci_init_ioda_phb(struct device_node *np, } pemap_off = size; size += phb->ioda.total_pe_num * sizeof(struct pnv_ioda_pe); - aux = memblock_alloc(size, 0); + aux = memblock_alloc(size, SMP_CACHE_BYTES); phb->ioda.pe_alloc = aux; phb->ioda.m64_segmap = aux + m64map_off; phb->ioda.m32_segmap = aux + m32map_off; diff --git a/arch/powerpc/sysdev/msi_bitmap.c b/arch/powerpc/sysdev/msi_bitmap.c index 2444feda831f..d45450f6666a 100644 --- a/arch/powerpc/sysdev/msi_bitmap.c +++ b/arch/powerpc/sysdev/msi_bitmap.c @@ -128,7 +128,7 @@ int __ref msi_bitmap_alloc(struct msi_bitmap *bmp, unsigned int irq_count, if (bmp->bitmap_from_slab) bmp->bitmap = kzalloc(size, GFP_KERNEL); else { - bmp->bitmap = memblock_alloc(size, 0); + bmp->bitmap = memblock_alloc(size, SMP_CACHE_BYTES); /* the bitmap won't be freed from memblock allocator */ kmemleak_not_leak(bmp->bitmap); } diff --git a/arch/um/drivers/net_kern.c b/arch/um/drivers/net_kern.c index 673816880cce..624cb47cc9cd 100644 --- a/arch/um/drivers/net_kern.c +++ b/arch/um/drivers/net_kern.c @@ -650,7 +650,7 @@ static int __init eth_setup(char *str) return 1; } - new = memblock_alloc(sizeof(*new), 0); + new = memblock_alloc(sizeof(*new), SMP_CACHE_BYTES); INIT_LIST_HEAD(&new->list); new->index = n; diff --git a/arch/um/drivers/vector_kern.c b/arch/um/drivers/vector_kern.c index 2b4dded11a7a..10d8d20eb9ec 100644 --- a/arch/um/drivers/vector_kern.c +++ b/arch/um/drivers/vector_kern.c @@ -1580,7 +1580,7 @@ static int __init vector_setup(char *str) str, error); return 1; } - new = memblock_alloc(sizeof(*new), 0); + new = memblock_alloc(sizeof(*new), SMP_CACHE_BYTES); INIT_LIST_HEAD(&new->list); new->unit = n; new->arguments = str; diff --git a/arch/um/kernel/initrd.c b/arch/um/kernel/initrd.c index 3678f5b05e42..ce169ea87e61 100644 --- a/arch/um/kernel/initrd.c +++ b/arch/um/kernel/initrd.c @@ -36,7 +36,7 @@ int __init read_initrd(void) return 0; } - area = memblock_alloc(size, 0); + area = memblock_alloc(size, SMP_CACHE_BYTES); if (load_initrd(initrd, area, size) == -1) return 0; diff --git a/arch/unicore32/kernel/setup.c b/arch/unicore32/kernel/setup.c index b2c38b32ea57..4b0cb68c355a 100644 --- a/arch/unicore32/kernel/setup.c +++ b/arch/unicore32/kernel/setup.c @@ -206,7 +206,7 @@ request_standard_resources(struct meminfo *mi) if (mi->bank[i].size == 0) continue; - res = memblock_alloc_low(sizeof(*res), 0); + res = memblock_alloc_low(sizeof(*res), SMP_CACHE_BYTES); res->name = "System RAM"; res->start = mi->bank[i].start; res->end = mi->bank[i].start + mi->bank[i].size - 1; diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c index 7f5d212551d4..92c76bf97ad8 100644 --- a/arch/x86/kernel/acpi/boot.c +++ b/arch/x86/kernel/acpi/boot.c @@ -934,7 +934,7 @@ static int __init acpi_parse_hpet(struct acpi_table_header *table) */ #define HPET_RESOURCE_NAME_SIZE 9 hpet_res = memblock_alloc(sizeof(*hpet_res) + HPET_RESOURCE_NAME_SIZE, - 0); + SMP_CACHE_BYTES); hpet_res->name = (void *)&hpet_res[1]; hpet_res->flags = IORESOURCE_MEM; diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index 5fbc57e4b0b9..2953bbf05c08 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -2578,7 +2578,7 @@ static struct resource * __init ioapic_setup_resources(void) n = IOAPIC_RESOURCE_NAME_SIZE + sizeof(struct resource); n *= nr_ioapics; - mem = memblock_alloc(n, 0); + mem = memblock_alloc(n, SMP_CACHE_BYTES); res = (void *)mem; mem += sizeof(struct resource) * nr_ioapics; diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index 68ff62bffbab..50895c2f937d 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -1093,7 +1093,8 @@ void __init e820__reserve_resources(void) struct resource *res; u64 end; - res = memblock_alloc(sizeof(*res) * e820_table->nr_entries, 0); + res = memblock_alloc(sizeof(*res) * e820_table->nr_entries, + SMP_CACHE_BYTES); e820_res = res; for (i = 0; i < e820_table->nr_entries; i++) { diff --git a/arch/x86/platform/olpc/olpc_dt.c b/arch/x86/platform/olpc/olpc_dt.c index 115c8e4173bb..24d2175a9480 100644 --- a/arch/x86/platform/olpc/olpc_dt.c +++ b/arch/x86/platform/olpc/olpc_dt.c @@ -141,7 +141,7 @@ void * __init prom_early_alloc(unsigned long size) * fast enough on the platforms we care about while minimizing * wasted bootmem) and hand off chunks of it to callers. */ - res = memblock_alloc(chunk_size, 0); + res = memblock_alloc(chunk_size, SMP_CACHE_BYTES); BUG_ON(!res); prom_early_allocated += chunk_size; memset(res, 0, chunk_size); diff --git a/arch/xtensa/platforms/iss/network.c b/arch/xtensa/platforms/iss/network.c index 190846dddc67..d052712373b6 100644 --- a/arch/xtensa/platforms/iss/network.c +++ b/arch/xtensa/platforms/iss/network.c @@ -646,7 +646,7 @@ static int __init iss_net_setup(char *str) return 1; } - new = memblock_alloc(sizeof(*new), 0); + new = memblock_alloc(sizeof(*new), SMP_CACHE_BYTES); if (new == NULL) { pr_err("Alloc_bootmem failed\n"); return 1; diff --git a/drivers/clk/ti/clk.c b/drivers/clk/ti/clk.c index 5b2867a33b98..e205af814582 100644 --- a/drivers/clk/ti/clk.c +++ b/drivers/clk/ti/clk.c @@ -342,7 +342,7 @@ void __init omap2_clk_legacy_provider_init(int index, void __iomem *mem) { struct clk_iomap *io; - io = memblock_alloc(sizeof(*io), 0); + io = memblock_alloc(sizeof(*io), SMP_CACHE_BYTES); io->mem = mem; diff --git a/drivers/firmware/efi/memmap.c b/drivers/firmware/efi/memmap.c index ef618bceb79a..fa2904fb841f 100644 --- a/drivers/firmware/efi/memmap.c +++ b/drivers/firmware/efi/memmap.c @@ -15,7 +15,7 @@ static phys_addr_t __init __efi_memmap_alloc_early(unsigned long size) { - return memblock_phys_alloc(size, 0); + return memblock_phys_alloc(size, SMP_CACHE_BYTES); } static phys_addr_t __init __efi_memmap_alloc_late(unsigned long size) diff --git a/drivers/firmware/memmap.c b/drivers/firmware/memmap.c index 2a23453f005a..d168c87c7d30 100644 --- a/drivers/firmware/memmap.c +++ b/drivers/firmware/memmap.c @@ -333,7 +333,8 @@ int __init firmware_map_add_early(u64 start, u64 end, const char *type) { struct firmware_map_entry *entry; - entry = memblock_alloc(sizeof(struct firmware_map_entry), 0); + entry = memblock_alloc(sizeof(struct firmware_map_entry), + SMP_CACHE_BYTES); if (WARN_ON(!entry)) return -ENOMEM; diff --git a/drivers/macintosh/smu.c b/drivers/macintosh/smu.c index 880a81c82b7a..0a0b8e1f4236 100644 --- a/drivers/macintosh/smu.c +++ b/drivers/macintosh/smu.c @@ -492,7 +492,7 @@ int __init smu_init (void) goto fail_np; } - smu = memblock_alloc(sizeof(struct smu_device), 0); + smu = memblock_alloc(sizeof(struct smu_device), SMP_CACHE_BYTES); spin_lock_init(&smu->lock); INIT_LIST_HEAD(&smu->cmd_list); diff --git a/drivers/of/of_reserved_mem.c b/drivers/of/of_reserved_mem.c index d6255c276a41..1977ee0adcb1 100644 --- a/drivers/of/of_reserved_mem.c +++ b/drivers/of/of_reserved_mem.c @@ -36,6 +36,7 @@ int __init __weak early_init_dt_alloc_reserved_memory_arch(phys_addr_t size, * panic()s on allocation failure. */ end = !end ? MEMBLOCK_ALLOC_ANYWHERE : end; + align = !align ? SMP_CACHE_BYTES : align; base = __memblock_alloc_base(size, align, end); if (!base) return -ENOMEM; diff --git a/include/linux/memblock.h b/include/linux/memblock.h index 1b4d85879cbe..aee299a6aa76 100644 --- a/include/linux/memblock.h +++ b/include/linux/memblock.h @@ -406,7 +406,8 @@ static inline void * __init memblock_alloc_node(phys_addr_t size, static inline void * __init memblock_alloc_node_nopanic(phys_addr_t size, int nid) { - return memblock_alloc_try_nid_nopanic(size, 0, MEMBLOCK_LOW_LIMIT, + return memblock_alloc_try_nid_nopanic(size, SMP_CACHE_BYTES, + MEMBLOCK_LOW_LIMIT, MEMBLOCK_ALLOC_ACCESSIBLE, nid); } diff --git a/init/main.c b/init/main.c index 51b8e7b8ae5b..ee147103ba1b 100644 --- a/init/main.c +++ b/init/main.c @@ -375,10 +375,11 @@ static inline void smp_prepare_cpus(unsigned int maxcpus) { } static void __init setup_command_line(char *command_line) { saved_command_line = - memblock_alloc(strlen(boot_command_line) + 1, 0); + memblock_alloc(strlen(boot_command_line) + 1, SMP_CACHE_BYTES); initcall_command_line = - memblock_alloc(strlen(boot_command_line) + 1, 0); - static_command_line = memblock_alloc(strlen(command_line) + 1, 0); + memblock_alloc(strlen(boot_command_line) + 1, SMP_CACHE_BYTES); + static_command_line = memblock_alloc(strlen(command_line) + 1, + SMP_CACHE_BYTES); strcpy(saved_command_line, boot_command_line); strcpy(static_command_line, command_line); } @@ -773,8 +774,10 @@ static int __init initcall_blacklist(char *str) str_entry = strsep(&str, ","); if (str_entry) { pr_debug("blacklisting initcall %s\n", str_entry); - entry = memblock_alloc(sizeof(*entry), 0); - entry->buf = memblock_alloc(strlen(str_entry) + 1, 0); + entry = memblock_alloc(sizeof(*entry), + SMP_CACHE_BYTES); + entry->buf = memblock_alloc(strlen(str_entry) + 1, + SMP_CACHE_BYTES); strcpy(entry->buf, str_entry); list_add(&entry->next, &blacklisted_initcalls); } diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c index 3c9e365438ad..b0308a2c6000 100644 --- a/kernel/power/snapshot.c +++ b/kernel/power/snapshot.c @@ -963,7 +963,8 @@ void __init __register_nosave_region(unsigned long start_pfn, BUG_ON(!region); } else { /* This allocation cannot fail */ - region = memblock_alloc(sizeof(struct nosave_region), 0); + region = memblock_alloc(sizeof(struct nosave_region), + SMP_CACHE_BYTES); } region->start_pfn = start_pfn; region->end_pfn = end_pfn; diff --git a/lib/cpumask.c b/lib/cpumask.c index 75b5e7672c4c..8d666ab84b5c 100644 --- a/lib/cpumask.c +++ b/lib/cpumask.c @@ -163,7 +163,7 @@ EXPORT_SYMBOL(zalloc_cpumask_var); */ void __init alloc_bootmem_cpumask_var(cpumask_var_t *mask) { - *mask = memblock_alloc(cpumask_size(), 0); + *mask = memblock_alloc(cpumask_size(), SMP_CACHE_BYTES); } /** diff --git a/mm/memblock.c b/mm/memblock.c index c655342569f8..839531133816 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -1247,9 +1247,6 @@ static phys_addr_t __init memblock_alloc_range_nid(phys_addr_t size, { phys_addr_t found; - if (!align) - align = SMP_CACHE_BYTES; - found = memblock_find_in_range_node(size, align, start, end, nid, flags); if (found && !memblock_reserve(found, size)) { @@ -1343,8 +1340,6 @@ phys_addr_t __init memblock_phys_alloc_try_nid(phys_addr_t size, phys_addr_t ali * The allocation is performed from memory region limited by * memblock.current_limit if @max_addr == %MEMBLOCK_ALLOC_ACCESSIBLE. * - * The memory block is aligned on %SMP_CACHE_BYTES if @align == 0. - * * The phys address of allocated boot memory block is converted to virtual and * allocated memory is reset to 0. * @@ -1374,9 +1369,6 @@ static void * __init memblock_alloc_internal( if (WARN_ON_ONCE(slab_is_available())) return kzalloc_node(size, GFP_NOWAIT, nid); - if (!align) - align = SMP_CACHE_BYTES; - if (max_addr > memblock.current_limit) max_addr = memblock.current_limit; again: diff --git a/mm/page_alloc.c b/mm/page_alloc.c index ef289fadec0e..a919ba5cb3c8 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -7710,9 +7710,11 @@ void *__init alloc_large_system_hash(const char *tablename, size = bucketsize << log2qty; if (flags & HASH_EARLY) { if (flags & HASH_ZERO) - table = memblock_alloc_nopanic(size, 0); + table = memblock_alloc_nopanic(size, + SMP_CACHE_BYTES); else - table = memblock_alloc_raw(size, 0); + table = memblock_alloc_raw(size, + SMP_CACHE_BYTES); } else if (hashdist) { table = __vmalloc(size, gfp_flags, PAGE_KERNEL); } else { diff --git a/mm/percpu.c b/mm/percpu.c index 61cdbb3b3736..a6b74c6fe0be 100644 --- a/mm/percpu.c +++ b/mm/percpu.c @@ -1102,8 +1102,8 @@ static struct pcpu_chunk * __init pcpu_alloc_first_chunk(unsigned long tmp_addr, /* allocate chunk */ chunk = memblock_alloc(sizeof(struct pcpu_chunk) + - BITS_TO_LONGS(region_size >> PAGE_SHIFT), - 0); + BITS_TO_LONGS(region_size >> PAGE_SHIFT), + SMP_CACHE_BYTES); INIT_LIST_HEAD(&chunk->list); @@ -1114,12 +1114,12 @@ static struct pcpu_chunk * __init pcpu_alloc_first_chunk(unsigned long tmp_addr, chunk->nr_pages = region_size >> PAGE_SHIFT; region_bits = pcpu_chunk_map_bits(chunk); - chunk->alloc_map = memblock_alloc(BITS_TO_LONGS(region_bits) * - sizeof(chunk->alloc_map[0]), 0); - chunk->bound_map = memblock_alloc(BITS_TO_LONGS(region_bits + 1) * - sizeof(chunk->bound_map[0]), 0); - chunk->md_blocks = memblock_alloc(pcpu_chunk_nr_blocks(chunk) * - sizeof(chunk->md_blocks[0]), 0); + chunk->alloc_map = memblock_alloc(BITS_TO_LONGS(region_bits) * sizeof(chunk->alloc_map[0]), + SMP_CACHE_BYTES); + chunk->bound_map = memblock_alloc(BITS_TO_LONGS(region_bits + 1) * sizeof(chunk->bound_map[0]), + SMP_CACHE_BYTES); + chunk->md_blocks = memblock_alloc(pcpu_chunk_nr_blocks(chunk) * sizeof(chunk->md_blocks[0]), + SMP_CACHE_BYTES); pcpu_init_md_blocks(chunk); /* manage populated page bitmap */ @@ -2075,12 +2075,14 @@ int __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai, PCPU_SETUP_BUG_ON(pcpu_verify_alloc_info(ai) < 0); /* process group information and build config tables accordingly */ - group_offsets = memblock_alloc(ai->nr_groups * - sizeof(group_offsets[0]), 0); - group_sizes = memblock_alloc(ai->nr_groups * - sizeof(group_sizes[0]), 0); - unit_map = memblock_alloc(nr_cpu_ids * sizeof(unit_map[0]), 0); - unit_off = memblock_alloc(nr_cpu_ids * sizeof(unit_off[0]), 0); + group_offsets = memblock_alloc(ai->nr_groups * sizeof(group_offsets[0]), + SMP_CACHE_BYTES); + group_sizes = memblock_alloc(ai->nr_groups * sizeof(group_sizes[0]), + SMP_CACHE_BYTES); + unit_map = memblock_alloc(nr_cpu_ids * sizeof(unit_map[0]), + SMP_CACHE_BYTES); + unit_off = memblock_alloc(nr_cpu_ids * sizeof(unit_off[0]), + SMP_CACHE_BYTES); for (cpu = 0; cpu < nr_cpu_ids; cpu++) unit_map[cpu] = UINT_MAX; @@ -2144,8 +2146,8 @@ int __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai, * empty chunks. */ pcpu_nr_slots = __pcpu_size_to_slot(pcpu_unit_size) + 2; - pcpu_slot = memblock_alloc( - pcpu_nr_slots * sizeof(pcpu_slot[0]), 0); + pcpu_slot = memblock_alloc(pcpu_nr_slots * sizeof(pcpu_slot[0]), + SMP_CACHE_BYTES); for (i = 0; i < pcpu_nr_slots; i++) INIT_LIST_HEAD(&pcpu_slot[i]); @@ -2458,7 +2460,7 @@ int __init pcpu_embed_first_chunk(size_t reserved_size, size_t dyn_size, size_sum = ai->static_size + ai->reserved_size + ai->dyn_size; areas_size = PFN_ALIGN(ai->nr_groups * sizeof(void *)); - areas = memblock_alloc_nopanic(areas_size, 0); + areas = memblock_alloc_nopanic(areas_size, SMP_CACHE_BYTES); if (!areas) { rc = -ENOMEM; goto out_free; @@ -2599,7 +2601,7 @@ int __init pcpu_page_first_chunk(size_t reserved_size, /* unaligned allocations can't be freed, round up to page size */ pages_size = PFN_ALIGN(unit_pages * num_possible_cpus() * sizeof(pages[0])); - pages = memblock_alloc(pages_size, 0); + pages = memblock_alloc(pages_size, SMP_CACHE_BYTES); /* allocate pages */ j = 0; diff --git a/mm/sparse.c b/mm/sparse.c index ab2ac45e0440..33307fc05c4d 100644 --- a/mm/sparse.c +++ b/mm/sparse.c @@ -68,7 +68,8 @@ static noinline struct mem_section __ref *sparse_index_alloc(int nid) if (slab_is_available()) section = kzalloc_node(array_size, GFP_KERNEL, nid); else - section = memblock_alloc_node(array_size, 0, nid); + section = memblock_alloc_node(array_size, SMP_CACHE_BYTES, + nid); return section; } -- cgit v1.2.3 From 2f770806fd2c3db9616965e57ba60d80f43c827d Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Tue, 30 Oct 2018 15:10:01 -0700 Subject: mm/memblock.c: warn if zero alignment was requested After updating all memblock users to explicitly specify SMP_CACHE_BYTES alignment rather than use 0, it is still possible that uncovered users may sneak in. Add a WARN_ON_ONCE for such cases. [sfr@canb.auug.org.au: use dump_stack() instead of WARN_ON_ONCE for the alignment checks] Link: http://lkml.kernel.org/r/20181016131927.6ceba6ab@canb.auug.org.au [akpm@linux-foundation.org: add apologetic comment] Link: http://lkml.kernel.org/r/20181011060850.GA19822@rapoport-lnx Signed-off-by: Mike Rapoport Signed-off-by: Stephen Rothwell Reviewed-by: Andrew Morton Acked-by: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memblock.c | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'mm') diff --git a/mm/memblock.c b/mm/memblock.c index 839531133816..7df468c8ebc8 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -1247,6 +1247,12 @@ static phys_addr_t __init memblock_alloc_range_nid(phys_addr_t size, { phys_addr_t found; + if (!align) { + /* Can't use WARNs this early in boot on powerpc */ + dump_stack(); + align = SMP_CACHE_BYTES; + } + found = memblock_find_in_range_node(size, align, start, end, nid, flags); if (found && !memblock_reserve(found, size)) { @@ -1369,6 +1375,11 @@ static void * __init memblock_alloc_internal( if (WARN_ON_ONCE(slab_is_available())) return kzalloc_node(size, GFP_NOWAIT, nid); + if (!align) { + dump_stack(); + align = SMP_CACHE_BYTES; + } + if (max_addr > memblock.current_limit) max_addr = memblock.current_limit; again: -- cgit v1.2.3 From d15e59260f62bd5e0f625cf5f5240f6ffac78ab6 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Tue, 30 Oct 2018 15:10:18 -0700 Subject: mm/memory_hotplug: make remove_memory() take the device_hotplug_lock Patch series "mm: online/offline_pages called w.o. mem_hotplug_lock", v3. Reading through the code and studying how mem_hotplug_lock is to be used, I noticed that there are two places where we can end up calling device_online()/device_offline() - online_pages()/offline_pages() without the mem_hotplug_lock. And there are other places where we call device_online()/device_offline() without the device_hotplug_lock. While e.g. echo "online" > /sys/devices/system/memory/memory9/state is fine, e.g. echo 1 > /sys/devices/system/memory/memory9/online Will not take the mem_hotplug_lock. However the device_lock() and device_hotplug_lock. E.g. via memory_probe_store(), we can end up calling add_memory()->online_pages() without the device_hotplug_lock. So we can have concurrent callers in online_pages(). We e.g. touch in online_pages() basically unprotected zone->present_pages then. Looks like there is a longer history to that (see Patch #2 for details), and fixing it to work the way it was intended is not really possible. We would e.g. have to take the mem_hotplug_lock in device/base/core.c, which sounds wrong. Summary: We had a lock inversion on mem_hotplug_lock and device_lock(). More details can be found in patch 3 and patch 6. I propose the general rules (documentation added in patch 6): 1. add_memory/add_memory_resource() must only be called with device_hotplug_lock. 2. remove_memory() must only be called with device_hotplug_lock. This is already documented and holds for all callers. 3. device_online()/device_offline() must only be called with device_hotplug_lock. This is already documented and true for now in core code. Other callers (related to memory hotplug) have to be fixed up. 4. mem_hotplug_lock is taken inside of add_memory/remove_memory/ online_pages/offline_pages. To me, this looks way cleaner than what we have right now (and easier to verify). And looking at the documentation of remove_memory, using lock_device_hotplug also for add_memory() feels natural. This patch (of 6): remove_memory() is exported right now but requires the device_hotplug_lock, which is not exported. So let's provide a variant that takes the lock and only export that one. The lock is already held in arch/powerpc/platforms/pseries/hotplug-memory.c drivers/acpi/acpi_memhotplug.c arch/powerpc/platforms/powernv/memtrace.c Apart from that, there are not other users in the tree. Link: http://lkml.kernel.org/r/20180925091457.28651-2-david@redhat.com Signed-off-by: David Hildenbrand Reviewed-by: Pavel Tatashin Reviewed-by: Rafael J. Wysocki Reviewed-by: Rashmica Gupta Reviewed-by: Oscar Salvador Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Michael Ellerman Cc: "Rafael J. Wysocki" Cc: Len Brown Cc: Rashmica Gupta Cc: Michael Neuling Cc: Balbir Singh Cc: Nathan Fontenot Cc: John Allen Cc: Michal Hocko Cc: Dan Williams Cc: Joonsoo Kim Cc: Vlastimil Babka Cc: Greg Kroah-Hartman Cc: YASUAKI ISHIMATSU Cc: Mathieu Malaterre Cc: Boris Ostrovsky Cc: Haiyang Zhang Cc: Heiko Carstens Cc: Jonathan Corbet Cc: Juergen Gross Cc: Kate Stewart Cc: "K. Y. Srinivasan" Cc: Martin Schwidefsky Cc: Philippe Ombredanne Cc: Stephen Hemminger Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/powerpc/platforms/powernv/memtrace.c | 2 +- arch/powerpc/platforms/pseries/hotplug-memory.c | 6 +++--- drivers/acpi/acpi_memhotplug.c | 2 +- include/linux/memory_hotplug.h | 3 ++- mm/memory_hotplug.c | 9 ++++++++- 5 files changed, 15 insertions(+), 7 deletions(-) (limited to 'mm') diff --git a/arch/powerpc/platforms/powernv/memtrace.c b/arch/powerpc/platforms/powernv/memtrace.c index a29fdf8a2e56..773623f6bfb1 100644 --- a/arch/powerpc/platforms/powernv/memtrace.c +++ b/arch/powerpc/platforms/powernv/memtrace.c @@ -121,7 +121,7 @@ static u64 memtrace_alloc_node(u32 nid, u64 size) lock_device_hotplug(); end_pfn = base_pfn + nr_pages; for (pfn = base_pfn; pfn < end_pfn; pfn += bytes>> PAGE_SHIFT) { - remove_memory(nid, pfn << PAGE_SHIFT, bytes); + __remove_memory(nid, pfn << PAGE_SHIFT, bytes); } unlock_device_hotplug(); return base_pfn << PAGE_SHIFT; diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c index 2b796da822c2..d79b31e7a6cf 100644 --- a/arch/powerpc/platforms/pseries/hotplug-memory.c +++ b/arch/powerpc/platforms/pseries/hotplug-memory.c @@ -300,7 +300,7 @@ static int pseries_remove_memblock(unsigned long base, unsigned int memblock_siz nid = memory_add_physaddr_to_nid(base); for (i = 0; i < sections_per_block; i++) { - remove_memory(nid, base, MIN_MEMORY_BLOCK_SIZE); + __remove_memory(nid, base, MIN_MEMORY_BLOCK_SIZE); base += MIN_MEMORY_BLOCK_SIZE; } @@ -389,7 +389,7 @@ static int dlpar_remove_lmb(struct drmem_lmb *lmb) block_sz = pseries_memory_block_size(); nid = memory_add_physaddr_to_nid(lmb->base_addr); - remove_memory(nid, lmb->base_addr, block_sz); + __remove_memory(nid, lmb->base_addr, block_sz); /* Update memory regions for memory remove */ memblock_remove(lmb->base_addr, block_sz); @@ -676,7 +676,7 @@ static int dlpar_add_lmb(struct drmem_lmb *lmb) rc = dlpar_online_lmb(lmb); if (rc) { - remove_memory(nid, lmb->base_addr, block_sz); + __remove_memory(nid, lmb->base_addr, block_sz); invalidate_lmb_associativity_index(lmb); } else { lmb->flags |= DRCONF_MEM_ASSIGNED; diff --git a/drivers/acpi/acpi_memhotplug.c b/drivers/acpi/acpi_memhotplug.c index 6b0d3ef7309c..811148415993 100644 --- a/drivers/acpi/acpi_memhotplug.c +++ b/drivers/acpi/acpi_memhotplug.c @@ -282,7 +282,7 @@ static void acpi_memory_remove_memory(struct acpi_memory_device *mem_device) nid = memory_add_physaddr_to_nid(info->start_addr); acpi_unbind_memory_blocks(info); - remove_memory(nid, info->start_addr, info->length); + __remove_memory(nid, info->start_addr, info->length); list_del(&info->list); kfree(info); } diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 34a28227068d..1f096852f479 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -301,6 +301,7 @@ extern bool is_mem_section_removable(unsigned long pfn, unsigned long nr_pages); extern void try_offline_node(int nid); extern int offline_pages(unsigned long start_pfn, unsigned long nr_pages); extern void remove_memory(int nid, u64 start, u64 size); +extern void __remove_memory(int nid, u64 start, u64 size); #else static inline bool is_mem_section_removable(unsigned long pfn, @@ -317,6 +318,7 @@ static inline int offline_pages(unsigned long start_pfn, unsigned long nr_pages) } static inline void remove_memory(int nid, u64 start, u64 size) {} +static inline void __remove_memory(int nid, u64 start, u64 size) {} #endif /* CONFIG_MEMORY_HOTREMOVE */ extern void __ref free_area_init_core_hotplug(int nid); @@ -330,7 +332,6 @@ extern void move_pfn_range_to_zone(struct zone *zone, unsigned long start_pfn, unsigned long nr_pages, struct vmem_altmap *altmap); extern int offline_pages(unsigned long start_pfn, unsigned long nr_pages); extern bool is_memblock_offlined(struct memory_block *mem); -extern void remove_memory(int nid, u64 start, u64 size); extern int sparse_add_one_section(struct pglist_data *pgdat, unsigned long start_pfn, struct vmem_altmap *altmap); extern void sparse_remove_one_section(struct zone *zone, struct mem_section *ms, diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 41e326472ef9..8f38e689da25 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1806,7 +1806,7 @@ EXPORT_SYMBOL(try_offline_node); * and online/offline operations before this call, as required by * try_offline_node(). */ -void __ref remove_memory(int nid, u64 start, u64 size) +void __ref __remove_memory(int nid, u64 start, u64 size) { int ret; @@ -1835,5 +1835,12 @@ void __ref remove_memory(int nid, u64 start, u64 size) mem_hotplug_done(); } + +void remove_memory(int nid, u64 start, u64 size) +{ + lock_device_hotplug(); + __remove_memory(nid, start, size); + unlock_device_hotplug(); +} EXPORT_SYMBOL_GPL(remove_memory); #endif /* CONFIG_MEMORY_HOTREMOVE */ -- cgit v1.2.3 From 8df1d0e4a265f25dc1e7e7624ccdbcb4a6630c89 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Tue, 30 Oct 2018 15:10:24 -0700 Subject: mm/memory_hotplug: make add_memory() take the device_hotplug_lock add_memory() currently does not take the device_hotplug_lock, however is aleady called under the lock from arch/powerpc/platforms/pseries/hotplug-memory.c drivers/acpi/acpi_memhotplug.c to synchronize against CPU hot-remove and similar. In general, we should hold the device_hotplug_lock when adding memory to synchronize against online/offline request (e.g. from user space) - which already resulted in lock inversions due to device_lock() and mem_hotplug_lock - see 30467e0b3be ("mm, hotplug: fix concurrent memory hot-add deadlock"). add_memory()/add_memory_resource() will create memory block devices, so this really feels like the right thing to do. Holding the device_hotplug_lock makes sure that a memory block device can really only be accessed (e.g. via .online/.state) from user space, once the memory has been fully added to the system. The lock is not held yet in drivers/xen/balloon.c arch/powerpc/platforms/powernv/memtrace.c drivers/s390/char/sclp_cmd.c drivers/hv/hv_balloon.c So, let's either use the locked variants or take the lock. Don't export add_memory_resource(), as it once was exported to be used by XEN, which is never built as a module. If somebody requires it, we also have to export a locked variant (as device_hotplug_lock is never exported). Link: http://lkml.kernel.org/r/20180925091457.28651-3-david@redhat.com Signed-off-by: David Hildenbrand Reviewed-by: Pavel Tatashin Reviewed-by: Rafael J. Wysocki Reviewed-by: Rashmica Gupta Reviewed-by: Oscar Salvador Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Michael Ellerman Cc: "Rafael J. Wysocki" Cc: Len Brown Cc: Greg Kroah-Hartman Cc: Boris Ostrovsky Cc: Juergen Gross Cc: Nathan Fontenot Cc: John Allen Cc: Michal Hocko Cc: Dan Williams Cc: Joonsoo Kim Cc: Vlastimil Babka Cc: Mathieu Malaterre Cc: Pavel Tatashin Cc: YASUAKI ISHIMATSU Cc: Balbir Singh Cc: Haiyang Zhang Cc: Heiko Carstens Cc: Jonathan Corbet Cc: Kate Stewart Cc: "K. Y. Srinivasan" Cc: Martin Schwidefsky Cc: Michael Neuling Cc: Philippe Ombredanne Cc: Stephen Hemminger Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/powerpc/platforms/pseries/hotplug-memory.c | 2 +- drivers/acpi/acpi_memhotplug.c | 2 +- drivers/base/memory.c | 9 +++++++-- drivers/xen/balloon.c | 3 +++ include/linux/memory_hotplug.h | 1 + mm/memory_hotplug.c | 22 +++++++++++++++++++--- 6 files changed, 32 insertions(+), 7 deletions(-) (limited to 'mm') diff --git a/arch/powerpc/platforms/pseries/hotplug-memory.c b/arch/powerpc/platforms/pseries/hotplug-memory.c index d79b31e7a6cf..2a983b5a52e1 100644 --- a/arch/powerpc/platforms/pseries/hotplug-memory.c +++ b/arch/powerpc/platforms/pseries/hotplug-memory.c @@ -668,7 +668,7 @@ static int dlpar_add_lmb(struct drmem_lmb *lmb) nid = memory_add_physaddr_to_nid(lmb->base_addr); /* Add the memory */ - rc = add_memory(nid, lmb->base_addr, block_sz); + rc = __add_memory(nid, lmb->base_addr, block_sz); if (rc) { invalidate_lmb_associativity_index(lmb); return rc; diff --git a/drivers/acpi/acpi_memhotplug.c b/drivers/acpi/acpi_memhotplug.c index 811148415993..8fe0960ea572 100644 --- a/drivers/acpi/acpi_memhotplug.c +++ b/drivers/acpi/acpi_memhotplug.c @@ -228,7 +228,7 @@ static int acpi_memory_enable_device(struct acpi_memory_device *mem_device) if (node < 0) node = memory_add_physaddr_to_nid(info->start_addr); - result = add_memory(node, info->start_addr, info->length); + result = __add_memory(node, info->start_addr, info->length); /* * If the memory block has been used by the kernel, add_memory() diff --git a/drivers/base/memory.c b/drivers/base/memory.c index 817320c7c4c1..40cac122ec73 100644 --- a/drivers/base/memory.c +++ b/drivers/base/memory.c @@ -519,15 +519,20 @@ memory_probe_store(struct device *dev, struct device_attribute *attr, if (phys_addr & ((pages_per_block << PAGE_SHIFT) - 1)) return -EINVAL; + ret = lock_device_hotplug_sysfs(); + if (ret) + goto out; + nid = memory_add_physaddr_to_nid(phys_addr); - ret = add_memory(nid, phys_addr, - MIN_MEMORY_BLOCK_SIZE * sections_per_block); + ret = __add_memory(nid, phys_addr, + MIN_MEMORY_BLOCK_SIZE * sections_per_block); if (ret) goto out; ret = count; out: + unlock_device_hotplug(); return ret; } diff --git a/drivers/xen/balloon.c b/drivers/xen/balloon.c index a3f5cbfcd4a1..fdfc64f5acea 100644 --- a/drivers/xen/balloon.c +++ b/drivers/xen/balloon.c @@ -395,7 +395,10 @@ static enum bp_state reserve_additional_memory(void) * callers drop the mutex before trying again. */ mutex_unlock(&balloon_mutex); + /* add_memory_resource() requires the device_hotplug lock */ + lock_device_hotplug(); rc = add_memory_resource(nid, resource, memhp_auto_online); + unlock_device_hotplug(); mutex_lock(&balloon_mutex); if (rc) { diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h index 1f096852f479..ffd9cd10fcf3 100644 --- a/include/linux/memory_hotplug.h +++ b/include/linux/memory_hotplug.h @@ -324,6 +324,7 @@ static inline void __remove_memory(int nid, u64 start, u64 size) {} extern void __ref free_area_init_core_hotplug(int nid); extern int walk_memory_range(unsigned long start_pfn, unsigned long end_pfn, void *arg, int (*func)(struct memory_block *, void *)); +extern int __add_memory(int nid, u64 start, u64 size); extern int add_memory(int nid, u64 start, u64 size); extern int add_memory_resource(int nid, struct resource *resource, bool online); extern int arch_add_memory(int nid, u64 start, u64 size, diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 8f38e689da25..39cc887bbdcc 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1068,7 +1068,12 @@ static int online_memory_block(struct memory_block *mem, void *arg) return device_online(&mem->dev); } -/* we are OK calling __meminit stuff here - we have CONFIG_MEMORY_HOTPLUG */ +/* + * NOTE: The caller must call lock_device_hotplug() to serialize hotplug + * and online/offline operations (triggered e.g. by sysfs). + * + * we are OK calling __meminit stuff here - we have CONFIG_MEMORY_HOTPLUG + */ int __ref add_memory_resource(int nid, struct resource *res, bool online) { u64 start, size; @@ -1137,9 +1142,9 @@ out: mem_hotplug_done(); return ret; } -EXPORT_SYMBOL_GPL(add_memory_resource); -int __ref add_memory(int nid, u64 start, u64 size) +/* requires device_hotplug_lock, see add_memory_resource() */ +int __ref __add_memory(int nid, u64 start, u64 size) { struct resource *res; int ret; @@ -1153,6 +1158,17 @@ int __ref add_memory(int nid, u64 start, u64 size) release_memory_resource(res); return ret; } + +int add_memory(int nid, u64 start, u64 size) +{ + int rc; + + lock_device_hotplug(); + rc = __add_memory(nid, start, size); + unlock_device_hotplug(); + + return rc; +} EXPORT_SYMBOL_GPL(add_memory); #ifdef CONFIG_MEMORY_HOTREMOVE -- cgit v1.2.3 From 381eab4a6ee81266f8dddc62e57376c7e584e5b8 Mon Sep 17 00:00:00 2001 From: David Hildenbrand Date: Tue, 30 Oct 2018 15:10:29 -0700 Subject: mm/memory_hotplug: fix online/offline_pages called w.o. mem_hotplug_lock There seem to be some problems as result of 30467e0b3be ("mm, hotplug: fix concurrent memory hot-add deadlock"), which tried to fix a possible lock inversion reported and discussed in [1] due to the two locks a) device_lock() b) mem_hotplug_lock While add_memory() first takes b), followed by a) during bus_probe_device(), onlining of memory from user space first took a), followed by b), exposing a possible deadlock. In [1], and it was decided to not make use of device_hotplug_lock, but rather to enforce a locking order. The problems I spotted related to this: 1. Memory block device attributes: While .state first calls mem_hotplug_begin() and the calls device_online() - which takes device_lock() - .online does no longer call mem_hotplug_begin(), so effectively calls online_pages() without mem_hotplug_lock. 2. device_online() should be called under device_hotplug_lock, however onlining memory during add_memory() does not take care of that. In addition, I think there is also something wrong about the locking in 3. arch/powerpc/platforms/powernv/memtrace.c calls offline_pages() without locks. This was introduced after 30467e0b3be. And skimming over the code, I assume it could need some more care in regards to locking (e.g. device_online() called without device_hotplug_lock. This will be addressed in the following patches. Now that we hold the device_hotplug_lock when - adding memory (e.g. via add_memory()/add_memory_resource()) - removing memory (e.g. via remove_memory()) - device_online()/device_offline() We can move mem_hotplug_lock usage back into online_pages()/offline_pages(). Why is mem_hotplug_lock still needed? Essentially to make get_online_mems()/put_online_mems() be very fast (relying on device_hotplug_lock would be very slow), and to serialize against addition of memory that does not create memory block devices (hmm). [1] http://driverdev.linuxdriverproject.org/pipermail/ driverdev-devel/ 2015-February/065324.html This patch is partly based on a patch by Vitaly Kuznetsov. Link: http://lkml.kernel.org/r/20180925091457.28651-4-david@redhat.com Signed-off-by: David Hildenbrand Reviewed-by: Pavel Tatashin Reviewed-by: Rashmica Gupta Reviewed-by: Oscar Salvador Cc: Benjamin Herrenschmidt Cc: Paul Mackerras Cc: Michael Ellerman Cc: "Rafael J. Wysocki" Cc: Len Brown Cc: Greg Kroah-Hartman Cc: "K. Y. Srinivasan" Cc: Haiyang Zhang Cc: Stephen Hemminger Cc: Martin Schwidefsky Cc: Heiko Carstens Cc: Boris Ostrovsky Cc: Juergen Gross Cc: Rashmica Gupta Cc: Michael Neuling Cc: Balbir Singh Cc: Kate Stewart Cc: Thomas Gleixner Cc: Philippe Ombredanne Cc: Pavel Tatashin Cc: Vlastimil Babka Cc: Dan Williams Cc: Oscar Salvador Cc: YASUAKI ISHIMATSU Cc: Mathieu Malaterre Cc: John Allen Cc: Jonathan Corbet Cc: Joonsoo Kim Cc: Nathan Fontenot Cc: Rafael J. Wysocki Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- drivers/base/memory.c | 13 +------------ mm/memory_hotplug.c | 28 ++++++++++++++++++++-------- 2 files changed, 21 insertions(+), 20 deletions(-) (limited to 'mm') diff --git a/drivers/base/memory.c b/drivers/base/memory.c index 40cac122ec73..0e5985682642 100644 --- a/drivers/base/memory.c +++ b/drivers/base/memory.c @@ -228,7 +228,6 @@ static bool pages_correctly_probed(unsigned long start_pfn) /* * MEMORY_HOTPLUG depends on SPARSEMEM in mm/Kconfig, so it is * OK to have direct references to sparsemem variables in here. - * Must already be protected by mem_hotplug_begin(). */ static int memory_block_action(unsigned long phys_index, unsigned long action, int online_type) @@ -294,7 +293,6 @@ static int memory_subsys_online(struct device *dev) if (mem->online_type < 0) mem->online_type = MMOP_ONLINE_KEEP; - /* Already under protection of mem_hotplug_begin() */ ret = memory_block_change_state(mem, MEM_ONLINE, MEM_OFFLINE); /* clear online_type */ @@ -341,19 +339,11 @@ store_mem_state(struct device *dev, goto err; } - /* - * Memory hotplug needs to hold mem_hotplug_begin() for probe to find - * the correct memory block to online before doing device_online(dev), - * which will take dev->mutex. Take the lock early to prevent an - * inversion, memory_subsys_online() callbacks will be implemented by - * assuming it's already protected. - */ - mem_hotplug_begin(); - switch (online_type) { case MMOP_ONLINE_KERNEL: case MMOP_ONLINE_MOVABLE: case MMOP_ONLINE_KEEP: + /* mem->online_type is protected by device_hotplug_lock */ mem->online_type = online_type; ret = device_online(&mem->dev); break; @@ -364,7 +354,6 @@ store_mem_state(struct device *dev, ret = -EINVAL; /* should never happen */ } - mem_hotplug_done(); err: unlock_device_hotplug(); diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 39cc887bbdcc..61972da38d93 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -838,7 +838,6 @@ static struct zone * __meminit move_pfn_range(int online_type, int nid, return zone; } -/* Must be protected by mem_hotplug_begin() or a device_lock */ int __ref online_pages(unsigned long pfn, unsigned long nr_pages, int online_type) { unsigned long flags; @@ -850,6 +849,8 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages, int online_typ struct memory_notify arg; struct memory_block *mem; + mem_hotplug_begin(); + /* * We can't use pfn_to_nid() because nid might be stored in struct page * which is not yet initialized. Instead, we find nid from memory block. @@ -914,6 +915,7 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages, int online_typ if (onlined_pages) memory_notify(MEM_ONLINE, &arg); + mem_hotplug_done(); return 0; failed_addition: @@ -921,6 +923,7 @@ failed_addition: (unsigned long long) pfn << PAGE_SHIFT, (((unsigned long long) pfn + nr_pages) << PAGE_SHIFT) - 1); memory_notify(MEM_CANCEL_ONLINE, &arg); + mem_hotplug_done(); return ret; } #endif /* CONFIG_MEMORY_HOTPLUG_SPARSE */ @@ -1125,20 +1128,20 @@ int __ref add_memory_resource(int nid, struct resource *res, bool online) /* create new memmap entry */ firmware_map_add_hotplug(start, start + size, "System RAM"); + /* device_online() will take the lock when calling online_pages() */ + mem_hotplug_done(); + /* online pages if requested */ if (online) walk_memory_range(PFN_DOWN(start), PFN_UP(start + size - 1), NULL, online_memory_block); - goto out; - + return ret; error: /* rollback pgdat allocation and others */ if (new_node) rollback_node_hotadd(nid); memblock_remove(start, size); - -out: mem_hotplug_done(); return ret; } @@ -1555,10 +1558,16 @@ static int __ref __offline_pages(unsigned long start_pfn, return -EINVAL; if (!IS_ALIGNED(end_pfn, pageblock_nr_pages)) return -EINVAL; + + mem_hotplug_begin(); + /* This makes hotplug much easier...and readable. we assume this for now. .*/ - if (!test_pages_in_a_zone(start_pfn, end_pfn, &valid_start, &valid_end)) + if (!test_pages_in_a_zone(start_pfn, end_pfn, &valid_start, + &valid_end)) { + mem_hotplug_done(); return -EINVAL; + } zone = page_zone(pfn_to_page(valid_start)); node = zone_to_nid(zone); @@ -1567,8 +1576,10 @@ static int __ref __offline_pages(unsigned long start_pfn, /* set above range as isolated */ ret = start_isolate_page_range(start_pfn, end_pfn, MIGRATE_MOVABLE, true); - if (ret) + if (ret) { + mem_hotplug_done(); return ret; + } arg.start_pfn = start_pfn; arg.nr_pages = nr_pages; @@ -1639,6 +1650,7 @@ repeat: writeback_set_ratelimit(); memory_notify(MEM_OFFLINE, &arg); + mem_hotplug_done(); return 0; failed_removal: @@ -1648,10 +1660,10 @@ failed_removal: memory_notify(MEM_CANCEL_OFFLINE, &arg); /* pushback to free area */ undo_isolate_page_range(start_pfn, end_pfn, MIGRATE_MOVABLE); + mem_hotplug_done(); return ret; } -/* Must be protected by mem_hotplug_begin() or a device_lock */ int offline_pages(unsigned long start_pfn, unsigned long nr_pages) { return __offline_pages(start_pfn, start_pfn + nr_pages); -- cgit v1.2.3 From f2c57d91b0d96aa13ccff4e3b178038f17b00658 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Tue, 30 Oct 2018 15:10:47 -0700 Subject: mm: Fix warning in insert_pfn() In DAX mode a write pagefault can race with write(2) in the following way: CPU0 CPU1 write fault for mapped zero page (hole) dax_iomap_rw() iomap_apply() xfs_file_iomap_begin() - allocates blocks dax_iomap_actor() invalidate_inode_pages2_range() - invalidates radix tree entries in given range dax_iomap_pte_fault() grab_mapping_entry() - no entry found, creates empty ... xfs_file_iomap_begin() - finds already allocated block ... vmf_insert_mixed_mkwrite() - WARNs and does nothing because there is still zero page mapped in PTE unmap_mapping_pages() This race results in WARN_ON from insert_pfn() and is occasionally triggered by fstest generic/344. Note that the race is otherwise harmless as before write(2) on CPU0 is finished, we will invalidate page tables properly and thus user of mmap will see modified data from write(2) from that point on. So just restrict the warning only to the case when the PFN in PTE is not zero page. Link: http://lkml.kernel.org/r/20180824154542.26872-1-jack@suse.cz Signed-off-by: Jan Kara Reviewed-by: Andrew Morton Cc: Ross Zwisler Cc: Dan Williams Cc: Dave Jiang Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memory.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) (limited to 'mm') diff --git a/mm/memory.c b/mm/memory.c index 072139579d89..4ad2d293ddc2 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -1537,10 +1537,15 @@ static vm_fault_t insert_pfn(struct vm_area_struct *vma, unsigned long addr, * in may not match the PFN we have mapped if the * mapped PFN is a writeable COW page. In the mkwrite * case we are creating a writable PTE for a shared - * mapping and we expect the PFNs to match. + * mapping and we expect the PFNs to match. If they + * don't match, we are likely racing with block + * allocation and mapping invalidation so just skip the + * update. */ - if (WARN_ON_ONCE(pte_pfn(*pte) != pfn_t_to_pfn(pfn))) + if (pte_pfn(*pte) != pfn_t_to_pfn(pfn)) { + WARN_ON_ONCE(!is_zero_pfn(pte_pfn(*pte))); goto out_unlock; + } entry = *pte; goto out_mkwrite; } else -- cgit v1.2.3 From 2ebe82288b3278b8e538ee8adce4142dbdedd8f6 Mon Sep 17 00:00:00 2001 From: Fengguang Wu Date: Tue, 30 Oct 2018 15:10:51 -0700 Subject: mm/gup.c: fix __get_user_pages_fast() comment mmu_gather_tlb() no longer exists. Replace with mmu_table_batch(). Link: http://lkml.kernel.org/r/20180928053441.rpzwafzlsnp74mkl@wfg-t540p.sh.intel.com Signed-off-by: Fengguang Wu Reviewed-by: Andrew Morton Cc: Jiri Kosina Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/gup.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'mm') diff --git a/mm/gup.c b/mm/gup.c index 841d7ef53591..f76e77a2d34b 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -1817,8 +1817,8 @@ int __get_user_pages_fast(unsigned long start, int nr_pages, int write, * interrupts disabled by get_futex_key. * * With interrupts disabled, we block page table pages from being - * freed from under us. See mmu_gather_tlb in asm-generic/tlb.h - * for more details. + * freed from under us. See struct mmu_table_batch comments in + * include/asm-generic/tlb.h for more details. * * We do not adopt an rcu_read_lock(.) here as we also want to * block IPIs that come from THPs splitting. -- cgit v1.2.3 From b5f2954d30c77649bce9c27e7a0a94299d9cfdf8 Mon Sep 17 00:00:00 2001 From: Dennis Zhou Date: Thu, 1 Nov 2018 17:24:10 -0400 Subject: blkcg: revert blkcg cleanups series This reverts a series committed earlier due to null pointer exception bug report in [1]. It seems there are edge case interactions that I did not consider and will need some time to understand what causes the adverse interactions. The original series can be found in [2] with a follow up series in [3]. [1] https://www.spinics.net/lists/cgroups/msg20719.html [2] https://lore.kernel.org/lkml/20180911184137.35897-1-dennisszhou@gmail.com/ [3] https://lore.kernel.org/lkml/20181020185612.51587-1-dennis@kernel.org/ This reverts the following commits: d459d853c2ed, b2c3fa546705, 101246ec02b5, b3b9f24f5fcc, e2b0989954ae, f0fcb3ec89f3, c839e7a03f92, bdc2491708c4, 74b7c02a9bc1, 5bf9a1f3b4ef, a7b39b4e961c, 07b05bcc3213, 49f4c2dc2b50, 27e6fa996c53 Signed-off-by: Dennis Zhou Signed-off-by: Jens Axboe --- Documentation/admin-guide/cgroup-v2.rst | 8 +- block/bfq-cgroup.c | 4 +- block/bfq-iosched.c | 2 +- block/bio.c | 174 +++++++++----------------------- block/blk-cgroup.c | 123 +++++++--------------- block/blk-core.c | 1 - block/blk-iolatency.c | 26 ++++- block/blk-throttle.c | 13 ++- block/bounce.c | 4 +- block/cfq-iosched.c | 4 +- drivers/block/loop.c | 5 +- drivers/md/raid0.c | 2 +- fs/buffer.c | 10 +- fs/ext4/page-io.c | 2 +- include/linux/bio.h | 26 ++--- include/linux/blk-cgroup.h | 145 +++++++++----------------- include/linux/blk_types.h | 1 + include/linux/cgroup.h | 2 - include/linux/writeback.h | 5 +- kernel/cgroup/cgroup.c | 48 ++------- kernel/trace/blktrace.c | 4 +- mm/page_io.c | 2 +- 22 files changed, 208 insertions(+), 403 deletions(-) (limited to 'mm') diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst index caf36105a1c7..184193bcb262 100644 --- a/Documentation/admin-guide/cgroup-v2.rst +++ b/Documentation/admin-guide/cgroup-v2.rst @@ -1857,10 +1857,8 @@ following two functions. wbc_init_bio(@wbc, @bio) Should be called for each bio carrying writeback data and - associates the bio with the inode's owner cgroup and the - corresponding request queue. This must be called after - a queue (device) has been associated with the bio and - before submission. + associates the bio with the inode's owner cgroup. Can be + called anytime between bio allocation and submission. wbc_account_io(@wbc, @page, @bytes) Should be called for each data segment being written out. @@ -1879,7 +1877,7 @@ the configuration, the bio may be executed at a lower priority and if the writeback session is holding shared resources, e.g. a journal entry, may lead to priority inversion. There is no one easy solution for the problem. Filesystems can try to work around specific problem -cases by skipping wbc_init_bio() or using bio_associate_create_blkg() +cases by skipping wbc_init_bio() or using bio_associate_blkcg() directly. diff --git a/block/bfq-cgroup.c b/block/bfq-cgroup.c index d9a7916ff0ab..9fe5952d117d 100644 --- a/block/bfq-cgroup.c +++ b/block/bfq-cgroup.c @@ -642,7 +642,7 @@ void bfq_bic_update_cgroup(struct bfq_io_cq *bic, struct bio *bio) uint64_t serial_nr; rcu_read_lock(); - serial_nr = __bio_blkcg(bio)->css.serial_nr; + serial_nr = bio_blkcg(bio)->css.serial_nr; /* * Check whether blkcg has changed. The condition may trigger @@ -651,7 +651,7 @@ void bfq_bic_update_cgroup(struct bfq_io_cq *bic, struct bio *bio) if (unlikely(!bfqd) || likely(bic->blkcg_serial_nr == serial_nr)) goto out; - bfqg = __bfq_bic_change_cgroup(bfqd, bic, __bio_blkcg(bio)); + bfqg = __bfq_bic_change_cgroup(bfqd, bic, bio_blkcg(bio)); /* * Update blkg_path for bfq_log_* functions. We cache this * path, and update it here, for the following diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c index 6075100f03a5..3a27d31fcda6 100644 --- a/block/bfq-iosched.c +++ b/block/bfq-iosched.c @@ -4384,7 +4384,7 @@ static struct bfq_queue *bfq_get_queue(struct bfq_data *bfqd, rcu_read_lock(); - bfqg = bfq_find_set_group(bfqd, __bio_blkcg(bio)); + bfqg = bfq_find_set_group(bfqd, bio_blkcg(bio)); if (!bfqg) { bfqq = &bfqd->oom_bfqq; goto out; diff --git a/block/bio.c b/block/bio.c index bbfeb4ee2892..4a5a036268fb 100644 --- a/block/bio.c +++ b/block/bio.c @@ -609,9 +609,7 @@ void __bio_clone_fast(struct bio *bio, struct bio *bio_src) bio->bi_iter = bio_src->bi_iter; bio->bi_io_vec = bio_src->bi_io_vec; - bio_clone_blkg_association(bio, bio_src); - - blkcg_bio_issue_init(bio); + bio_clone_blkcg_association(bio, bio_src); } EXPORT_SYMBOL(__bio_clone_fast); @@ -1956,151 +1954,69 @@ EXPORT_SYMBOL(bioset_init_from_src); #ifdef CONFIG_BLK_CGROUP -/** - * bio_associate_blkg - associate a bio with the a blkg - * @bio: target bio - * @blkg: the blkg to associate - * - * This tries to associate @bio with the specified blkg. Association failure - * is handled by walking up the blkg tree. Therefore, the blkg associated can - * be anything between @blkg and the root_blkg. This situation only happens - * when a cgroup is dying and then the remaining bios will spill to the closest - * alive blkg. - * - * A reference will be taken on the @blkg and will be released when @bio is - * freed. - */ -int bio_associate_blkg(struct bio *bio, struct blkcg_gq *blkg) -{ - if (unlikely(bio->bi_blkg)) - return -EBUSY; - bio->bi_blkg = blkg_tryget_closest(blkg); - return 0; -} - -/** - * __bio_associate_blkg_from_css - internal blkg association function - * - * This in the core association function that all association paths rely on. - * A blkg reference is taken which is released upon freeing of the bio. - */ -static int __bio_associate_blkg_from_css(struct bio *bio, - struct cgroup_subsys_state *css) -{ - struct request_queue *q = bio->bi_disk->queue; - struct blkcg_gq *blkg; - int ret; - - rcu_read_lock(); - - if (!css || !css->parent) - blkg = q->root_blkg; - else - blkg = blkg_lookup_create(css_to_blkcg(css), q); - - ret = bio_associate_blkg(bio, blkg); - - rcu_read_unlock(); - return ret; -} - -/** - * bio_associate_blkg_from_css - associate a bio with a specified css - * @bio: target bio - * @css: target css - * - * Associate @bio with the blkg found by combining the css's blkg and the - * request_queue of the @bio. This falls back to the queue's root_blkg if - * the association fails with the css. - */ -int bio_associate_blkg_from_css(struct bio *bio, - struct cgroup_subsys_state *css) -{ - if (unlikely(bio->bi_blkg)) - return -EBUSY; - return __bio_associate_blkg_from_css(bio, css); -} -EXPORT_SYMBOL_GPL(bio_associate_blkg_from_css); - #ifdef CONFIG_MEMCG /** - * bio_associate_blkg_from_page - associate a bio with the page's blkg + * bio_associate_blkcg_from_page - associate a bio with the page's blkcg * @bio: target bio * @page: the page to lookup the blkcg from * - * Associate @bio with the blkg from @page's owning memcg and the respective - * request_queue. If cgroup_e_css returns NULL, fall back to the queue's - * root_blkg. - * - * Note: this must be called after bio has an associated device. + * Associate @bio with the blkcg from @page's owning memcg. This works like + * every other associate function wrt references. */ -int bio_associate_blkg_from_page(struct bio *bio, struct page *page) +int bio_associate_blkcg_from_page(struct bio *bio, struct page *page) { - struct cgroup_subsys_state *css; - int ret; + struct cgroup_subsys_state *blkcg_css; - if (unlikely(bio->bi_blkg)) + if (unlikely(bio->bi_css)) return -EBUSY; if (!page->mem_cgroup) return 0; - - rcu_read_lock(); - - css = cgroup_e_css(page->mem_cgroup->css.cgroup, &io_cgrp_subsys); - - ret = __bio_associate_blkg_from_css(bio, css); - - rcu_read_unlock(); - return ret; + blkcg_css = cgroup_get_e_css(page->mem_cgroup->css.cgroup, + &io_cgrp_subsys); + bio->bi_css = blkcg_css; + return 0; } #endif /* CONFIG_MEMCG */ /** - * bio_associate_create_blkg - associate a bio with a blkg from q - * @q: request_queue where bio is going + * bio_associate_blkcg - associate a bio with the specified blkcg * @bio: target bio + * @blkcg_css: css of the blkcg to associate + * + * Associate @bio with the blkcg specified by @blkcg_css. Block layer will + * treat @bio as if it were issued by a task which belongs to the blkcg. * - * Associate @bio with the blkg found from the bio's css and the request_queue. - * If one is not found, bio_lookup_blkg creates the blkg. This falls back to - * the queue's root_blkg if association fails. + * This function takes an extra reference of @blkcg_css which will be put + * when @bio is released. The caller must own @bio and is responsible for + * synchronizing calls to this function. */ -int bio_associate_create_blkg(struct request_queue *q, struct bio *bio) +int bio_associate_blkcg(struct bio *bio, struct cgroup_subsys_state *blkcg_css) { - struct cgroup_subsys_state *css; - int ret = 0; - - /* someone has already associated this bio with a blkg */ - if (bio->bi_blkg) - return ret; - - rcu_read_lock(); - - css = blkcg_css(); - - ret = __bio_associate_blkg_from_css(bio, css); - - rcu_read_unlock(); - return ret; + if (unlikely(bio->bi_css)) + return -EBUSY; + css_get(blkcg_css); + bio->bi_css = blkcg_css; + return 0; } +EXPORT_SYMBOL_GPL(bio_associate_blkcg); /** - * bio_reassociate_blkg - reassociate a bio with a blkg from q - * @q: request_queue where bio is going + * bio_associate_blkg - associate a bio with the specified blkg * @bio: target bio + * @blkg: the blkg to associate * - * When submitting a bio, multiple recursive calls to make_request() may occur. - * This causes the initial associate done in blkcg_bio_issue_check() to be - * incorrect and reference the prior request_queue. This performs reassociation - * when this situation happens. + * Associate @bio with the blkg specified by @blkg. This is the queue specific + * blkcg information associated with the @bio, a reference will be taken on the + * @blkg and will be freed when the bio is freed. */ -int bio_reassociate_blkg(struct request_queue *q, struct bio *bio) +int bio_associate_blkg(struct bio *bio, struct blkcg_gq *blkg) { - if (bio->bi_blkg) { - blkg_put(bio->bi_blkg); - bio->bi_blkg = NULL; - } - - return bio_associate_create_blkg(q, bio); + if (unlikely(bio->bi_blkg)) + return -EBUSY; + if (!blkg_try_get(blkg)) + return -ENODEV; + bio->bi_blkg = blkg; + return 0; } /** @@ -2113,6 +2029,10 @@ void bio_disassociate_task(struct bio *bio) put_io_context(bio->bi_ioc); bio->bi_ioc = NULL; } + if (bio->bi_css) { + css_put(bio->bi_css); + bio->bi_css = NULL; + } if (bio->bi_blkg) { blkg_put(bio->bi_blkg); bio->bi_blkg = NULL; @@ -2120,16 +2040,16 @@ void bio_disassociate_task(struct bio *bio) } /** - * bio_clone_blkg_association - clone blkg association from src to dst bio + * bio_clone_blkcg_association - clone blkcg association from src to dst bio * @dst: destination bio * @src: source bio */ -void bio_clone_blkg_association(struct bio *dst, struct bio *src) +void bio_clone_blkcg_association(struct bio *dst, struct bio *src) { - if (src->bi_blkg) - bio_associate_blkg(dst, src->bi_blkg); + if (src->bi_css) + WARN_ON(bio_associate_blkcg(dst, src->bi_css)); } -EXPORT_SYMBOL_GPL(bio_clone_blkg_association); +EXPORT_SYMBOL_GPL(bio_clone_blkcg_association); #endif /* CONFIG_BLK_CGROUP */ static void __init biovec_init_slabs(void) diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index 992da5592c6e..c630e02836a8 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -84,37 +84,6 @@ static void blkg_free(struct blkcg_gq *blkg) kfree(blkg); } -static void __blkg_release(struct rcu_head *rcu) -{ - struct blkcg_gq *blkg = container_of(rcu, struct blkcg_gq, rcu_head); - - percpu_ref_exit(&blkg->refcnt); - - /* release the blkcg and parent blkg refs this blkg has been holding */ - css_put(&blkg->blkcg->css); - if (blkg->parent) - blkg_put(blkg->parent); - - wb_congested_put(blkg->wb_congested); - - blkg_free(blkg); -} - -/* - * A group is RCU protected, but having an rcu lock does not mean that one - * can access all the fields of blkg and assume these are valid. For - * example, don't try to follow throtl_data and request queue links. - * - * Having a reference to blkg under an rcu allows accesses to only values - * local to groups like group stats and group rate limits. - */ -static void blkg_release(struct percpu_ref *ref) -{ - struct blkcg_gq *blkg = container_of(ref, struct blkcg_gq, refcnt); - - call_rcu(&blkg->rcu_head, __blkg_release); -} - /** * blkg_alloc - allocate a blkg * @blkcg: block cgroup the new blkg is associated with @@ -141,6 +110,7 @@ static struct blkcg_gq *blkg_alloc(struct blkcg *blkcg, struct request_queue *q, blkg->q = q; INIT_LIST_HEAD(&blkg->q_node); blkg->blkcg = blkcg; + atomic_set(&blkg->refcnt, 1); /* root blkg uses @q->root_rl, init rl only for !root blkgs */ if (blkcg != &blkcg_root) { @@ -247,11 +217,6 @@ static struct blkcg_gq *blkg_create(struct blkcg *blkcg, blkg_get(blkg->parent); } - ret = percpu_ref_init(&blkg->refcnt, blkg_release, 0, - GFP_NOWAIT | __GFP_NOWARN); - if (ret) - goto err_cancel_ref; - /* invoke per-policy init */ for (i = 0; i < BLKCG_MAX_POLS; i++) { struct blkcg_policy *pol = blkcg_policy[i]; @@ -284,8 +249,6 @@ static struct blkcg_gq *blkg_create(struct blkcg *blkcg, blkg_put(blkg); return ERR_PTR(ret); -err_cancel_ref: - percpu_ref_exit(&blkg->refcnt); err_put_congested: wb_congested_put(wb_congested); err_put_css: @@ -296,7 +259,7 @@ err_free_blkg: } /** - * __blkg_lookup_create - lookup blkg, try to create one if not there + * blkg_lookup_create - lookup blkg, try to create one if not there * @blkcg: blkcg of interest * @q: request_queue of interest * @@ -305,11 +268,12 @@ err_free_blkg: * that all non-root blkg's have access to the parent blkg. This function * should be called under RCU read lock and @q->queue_lock. * - * Returns the blkg or the closest blkg if blkg_create fails as it walks - * down from root. + * Returns pointer to the looked up or created blkg on success, ERR_PTR() + * value on error. If @q is dead, returns ERR_PTR(-EINVAL). If @q is not + * dead and bypassing, returns ERR_PTR(-EBUSY). */ -struct blkcg_gq *__blkg_lookup_create(struct blkcg *blkcg, - struct request_queue *q) +struct blkcg_gq *blkg_lookup_create(struct blkcg *blkcg, + struct request_queue *q) { struct blkcg_gq *blkg; @@ -321,7 +285,7 @@ struct blkcg_gq *__blkg_lookup_create(struct blkcg *blkcg, * we shouldn't allow anything to go through for a bypassing queue. */ if (unlikely(blk_queue_bypass(q))) - return q->root_blkg; + return ERR_PTR(blk_queue_dying(q) ? -ENODEV : -EBUSY); blkg = __blkg_lookup(blkcg, q, true); if (blkg) @@ -329,58 +293,23 @@ struct blkcg_gq *__blkg_lookup_create(struct blkcg *blkcg, /* * Create blkgs walking down from blkcg_root to @blkcg, so that all - * non-root blkgs have access to their parents. Returns the closest - * blkg to the intended blkg should blkg_create() fail. + * non-root blkgs have access to their parents. */ while (true) { struct blkcg *pos = blkcg; struct blkcg *parent = blkcg_parent(blkcg); - struct blkcg_gq *ret_blkg = q->root_blkg; - - while (parent) { - blkg = __blkg_lookup(parent, q, false); - if (blkg) { - /* remember closest blkg */ - ret_blkg = blkg; - break; - } + + while (parent && !__blkg_lookup(parent, q, false)) { pos = parent; parent = blkcg_parent(parent); } blkg = blkg_create(pos, q, NULL); - if (IS_ERR(blkg)) - return ret_blkg; - if (pos == blkcg) + if (pos == blkcg || IS_ERR(blkg)) return blkg; } } -/** - * blkg_lookup_create - find or create a blkg - * @blkcg: target block cgroup - * @q: target request_queue - * - * This looks up or creates the blkg representing the unique pair - * of the blkcg and the request_queue. - */ -struct blkcg_gq *blkg_lookup_create(struct blkcg *blkcg, - struct request_queue *q) -{ - struct blkcg_gq *blkg = blkg_lookup(blkcg, q); - unsigned long flags; - - if (unlikely(!blkg)) { - spin_lock_irqsave(q->queue_lock, flags); - - blkg = __blkg_lookup_create(blkcg, q); - - spin_unlock_irqrestore(q->queue_lock, flags); - } - - return blkg; -} - static void blkg_destroy(struct blkcg_gq *blkg) { struct blkcg *blkcg = blkg->blkcg; @@ -424,7 +353,7 @@ static void blkg_destroy(struct blkcg_gq *blkg) * Put the reference taken at the time of creation so that when all * queues are gone, group can be destroyed. */ - percpu_ref_kill(&blkg->refcnt); + blkg_put(blkg); } /** @@ -451,6 +380,29 @@ static void blkg_destroy_all(struct request_queue *q) q->root_rl.blkg = NULL; } +/* + * A group is RCU protected, but having an rcu lock does not mean that one + * can access all the fields of blkg and assume these are valid. For + * example, don't try to follow throtl_data and request queue links. + * + * Having a reference to blkg under an rcu allows accesses to only values + * local to groups like group stats and group rate limits. + */ +void __blkg_release_rcu(struct rcu_head *rcu_head) +{ + struct blkcg_gq *blkg = container_of(rcu_head, struct blkcg_gq, rcu_head); + + /* release the blkcg and parent blkg refs this blkg has been holding */ + css_put(&blkg->blkcg->css); + if (blkg->parent) + blkg_put(blkg->parent); + + wb_congested_put(blkg->wb_congested); + + blkg_free(blkg); +} +EXPORT_SYMBOL_GPL(__blkg_release_rcu); + /* * The next function used by blk_queue_for_each_rl(). It's a bit tricky * because the root blkg uses @q->root_rl instead of its own rl. @@ -1796,7 +1748,8 @@ void blkcg_maybe_throttle_current(void) blkg = blkg_lookup(blkcg, q); if (!blkg) goto out; - if (!blkg_tryget(blkg)) + blkg = blkg_try_get(blkg); + if (!blkg) goto out; rcu_read_unlock(); diff --git a/block/blk-core.c b/block/blk-core.c index 26a5dac80ed9..ce12515f9b9b 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -2435,7 +2435,6 @@ blk_qc_t generic_make_request(struct bio *bio) if (q) blk_queue_exit(q); q = bio->bi_disk->queue; - bio_reassociate_blkg(q, bio); flags = 0; if (bio->bi_opf & REQ_NOWAIT) flags = BLK_MQ_REQ_NOWAIT; diff --git a/block/blk-iolatency.c b/block/blk-iolatency.c index 35c48d7b8f78..bb240a0c1309 100644 --- a/block/blk-iolatency.c +++ b/block/blk-iolatency.c @@ -480,12 +480,34 @@ static void blkcg_iolatency_throttle(struct rq_qos *rqos, struct bio *bio, spinlock_t *lock) { struct blk_iolatency *blkiolat = BLKIOLATENCY(rqos); - struct blkcg_gq *blkg = bio->bi_blkg; + struct blkcg *blkcg; + struct blkcg_gq *blkg; + struct request_queue *q = rqos->q; bool issue_as_root = bio_issue_as_root_blkg(bio); if (!blk_iolatency_enabled(blkiolat)) return; + rcu_read_lock(); + blkcg = bio_blkcg(bio); + bio_associate_blkcg(bio, &blkcg->css); + blkg = blkg_lookup(blkcg, q); + if (unlikely(!blkg)) { + if (!lock) + spin_lock_irq(q->queue_lock); + blkg = blkg_lookup_create(blkcg, q); + if (IS_ERR(blkg)) + blkg = NULL; + if (!lock) + spin_unlock_irq(q->queue_lock); + } + if (!blkg) + goto out; + + bio_issue_init(&bio->bi_issue, bio_sectors(bio)); + bio_associate_blkg(bio, blkg); +out: + rcu_read_unlock(); while (blkg && blkg->parent) { struct iolatency_grp *iolat = blkg_to_lat(blkg); if (!iolat) { @@ -706,7 +728,7 @@ static void blkiolatency_timer_fn(struct timer_list *t) * We could be exiting, don't access the pd unless we have a * ref on the blkg. */ - if (!blkg_tryget(blkg)) + if (!blkg_try_get(blkg)) continue; iolat = blkg_to_lat(blkg); diff --git a/block/blk-throttle.c b/block/blk-throttle.c index 4bda70e8db48..db1a3a2ae006 100644 --- a/block/blk-throttle.c +++ b/block/blk-throttle.c @@ -2115,11 +2115,21 @@ static inline void throtl_update_latency_buckets(struct throtl_data *td) } #endif +static void blk_throtl_assoc_bio(struct throtl_grp *tg, struct bio *bio) +{ +#ifdef CONFIG_BLK_DEV_THROTTLING_LOW + /* fallback to root_blkg if we fail to get a blkg ref */ + if (bio->bi_css && (bio_associate_blkg(bio, tg_to_blkg(tg)) == -ENODEV)) + bio_associate_blkg(bio, bio->bi_disk->queue->root_blkg); + bio_issue_init(&bio->bi_issue, bio_sectors(bio)); +#endif +} + bool blk_throtl_bio(struct request_queue *q, struct blkcg_gq *blkg, struct bio *bio) { struct throtl_qnode *qn = NULL; - struct throtl_grp *tg = blkg_to_tg(blkg); + struct throtl_grp *tg = blkg_to_tg(blkg ?: q->root_blkg); struct throtl_service_queue *sq; bool rw = bio_data_dir(bio); bool throttled = false; @@ -2138,6 +2148,7 @@ bool blk_throtl_bio(struct request_queue *q, struct blkcg_gq *blkg, if (unlikely(blk_queue_bypass(q))) goto out_unlock; + blk_throtl_assoc_bio(tg, bio); blk_throtl_update_idletime(tg); sq = &tg->service_queue; diff --git a/block/bounce.c b/block/bounce.c index ec0d99995f5f..418677dcec60 100644 --- a/block/bounce.c +++ b/block/bounce.c @@ -276,9 +276,7 @@ static struct bio *bounce_clone_bio(struct bio *bio_src, gfp_t gfp_mask, } } - bio_clone_blkg_association(bio, bio_src); - - blkcg_bio_issue_init(bio); + bio_clone_blkcg_association(bio, bio_src); return bio; } diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c index 6a3d87dd3c1a..ed41aa978c4a 100644 --- a/block/cfq-iosched.c +++ b/block/cfq-iosched.c @@ -3759,7 +3759,7 @@ static void check_blkcg_changed(struct cfq_io_cq *cic, struct bio *bio) uint64_t serial_nr; rcu_read_lock(); - serial_nr = __bio_blkcg(bio)->css.serial_nr; + serial_nr = bio_blkcg(bio)->css.serial_nr; rcu_read_unlock(); /* @@ -3824,7 +3824,7 @@ cfq_get_queue(struct cfq_data *cfqd, bool is_sync, struct cfq_io_cq *cic, struct cfq_group *cfqg; rcu_read_lock(); - cfqg = cfq_lookup_cfqg(cfqd, __bio_blkcg(bio)); + cfqg = cfq_lookup_cfqg(cfqd, bio_blkcg(bio)); if (!cfqg) { cfqq = &cfqd->oom_cfqq; goto out; diff --git a/drivers/block/loop.c b/drivers/block/loop.c index abad6d15f956..ea9debf59b22 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -77,7 +77,6 @@ #include #include #include -#include #include "loop.h" @@ -1761,8 +1760,8 @@ static blk_status_t loop_queue_rq(struct blk_mq_hw_ctx *hctx, /* always use the first bio's css */ #ifdef CONFIG_BLK_CGROUP - if (cmd->use_aio && rq->bio && rq->bio->bi_blkg) { - cmd->css = &bio_blkcg(rq->bio)->css; + if (cmd->use_aio && rq->bio && rq->bio->bi_css) { + cmd->css = rq->bio->bi_css; css_get(cmd->css); } else #endif diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c index f3fb5bb8c82a..ac1cffd2a09b 100644 --- a/drivers/md/raid0.c +++ b/drivers/md/raid0.c @@ -542,7 +542,7 @@ static void raid0_handle_discard(struct mddev *mddev, struct bio *bio) !discard_bio) continue; bio_chain(discard_bio, bio); - bio_clone_blkg_association(discard_bio, bio); + bio_clone_blkcg_association(discard_bio, bio); if (mddev->gendisk) trace_block_bio_remap(bdev_get_queue(rdev->bdev), discard_bio, disk_devt(mddev->gendisk), diff --git a/fs/buffer.c b/fs/buffer.c index 109f55196866..6f1ae3ac9789 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -3060,6 +3060,11 @@ static int submit_bh_wbc(int op, int op_flags, struct buffer_head *bh, */ bio = bio_alloc(GFP_NOIO, 1); + if (wbc) { + wbc_init_bio(wbc, bio); + wbc_account_io(wbc, bh->b_page, bh->b_size); + } + bio->bi_iter.bi_sector = bh->b_blocknr * (bh->b_size >> 9); bio_set_dev(bio, bh->b_bdev); bio->bi_write_hint = write_hint; @@ -3079,11 +3084,6 @@ static int submit_bh_wbc(int op, int op_flags, struct buffer_head *bh, op_flags |= REQ_PRIO; bio_set_op_attrs(bio, op, op_flags); - if (wbc) { - wbc_init_bio(wbc, bio); - wbc_account_io(wbc, bh->b_page, bh->b_size); - } - submit_bio(bio); return 0; } diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c index 2aa62d58d8dd..db7590178dfc 100644 --- a/fs/ext4/page-io.c +++ b/fs/ext4/page-io.c @@ -374,13 +374,13 @@ static int io_submit_init_bio(struct ext4_io_submit *io, bio = bio_alloc(GFP_NOIO, BIO_MAX_PAGES); if (!bio) return -ENOMEM; + wbc_init_bio(io->io_wbc, bio); bio->bi_iter.bi_sector = bh->b_blocknr * (bh->b_size >> 9); bio_set_dev(bio, bh->b_bdev); bio->bi_end_io = ext4_end_bio; bio->bi_private = ext4_get_io_end(io->io_end); io->io_bio = bio; io->io_next_block = bh->b_blocknr; - wbc_init_bio(io->io_wbc, bio); return 0; } diff --git a/include/linux/bio.h b/include/linux/bio.h index b47c7f716731..056fb627edb3 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -503,31 +503,23 @@ do { \ disk_devt((bio)->bi_disk) #if defined(CONFIG_MEMCG) && defined(CONFIG_BLK_CGROUP) -int bio_associate_blkg_from_page(struct bio *bio, struct page *page); +int bio_associate_blkcg_from_page(struct bio *bio, struct page *page); #else -static inline int bio_associate_blkg_from_page(struct bio *bio, - struct page *page) { return 0; } +static inline int bio_associate_blkcg_from_page(struct bio *bio, + struct page *page) { return 0; } #endif #ifdef CONFIG_BLK_CGROUP +int bio_associate_blkcg(struct bio *bio, struct cgroup_subsys_state *blkcg_css); int bio_associate_blkg(struct bio *bio, struct blkcg_gq *blkg); -int bio_associate_blkg_from_css(struct bio *bio, - struct cgroup_subsys_state *css); -int bio_associate_create_blkg(struct request_queue *q, struct bio *bio); -int bio_reassociate_blkg(struct request_queue *q, struct bio *bio); void bio_disassociate_task(struct bio *bio); -void bio_clone_blkg_association(struct bio *dst, struct bio *src); +void bio_clone_blkcg_association(struct bio *dst, struct bio *src); #else /* CONFIG_BLK_CGROUP */ -static inline int bio_associate_blkg_from_css(struct bio *bio, - struct cgroup_subsys_state *css) -{ return 0; } -static inline int bio_associate_create_blkg(struct request_queue *q, - struct bio *bio) { return 0; } -static inline int bio_reassociate_blkg(struct request_queue *q, struct bio *bio) -{ return 0; } +static inline int bio_associate_blkcg(struct bio *bio, + struct cgroup_subsys_state *blkcg_css) { return 0; } static inline void bio_disassociate_task(struct bio *bio) { } -static inline void bio_clone_blkg_association(struct bio *dst, - struct bio *src) { } +static inline void bio_clone_blkcg_association(struct bio *dst, + struct bio *src) { } #endif /* CONFIG_BLK_CGROUP */ #ifdef CONFIG_HIGHMEM diff --git a/include/linux/blk-cgroup.h b/include/linux/blk-cgroup.h index 1e76ceebeb5d..6d766a19f2bb 100644 --- a/include/linux/blk-cgroup.h +++ b/include/linux/blk-cgroup.h @@ -126,7 +126,7 @@ struct blkcg_gq { struct request_list rl; /* reference count */ - struct percpu_ref refcnt; + atomic_t refcnt; /* is this blkg online? protected by both blkcg and q locks */ bool online; @@ -184,8 +184,6 @@ extern struct cgroup_subsys_state * const blkcg_root_css; struct blkcg_gq *blkg_lookup_slowpath(struct blkcg *blkcg, struct request_queue *q, bool update_hint); -struct blkcg_gq *__blkg_lookup_create(struct blkcg *blkcg, - struct request_queue *q); struct blkcg_gq *blkg_lookup_create(struct blkcg *blkcg, struct request_queue *q); int blkcg_init_queue(struct request_queue *q); @@ -232,59 +230,22 @@ int blkg_conf_prep(struct blkcg *blkcg, const struct blkcg_policy *pol, char *input, struct blkg_conf_ctx *ctx); void blkg_conf_finish(struct blkg_conf_ctx *ctx); -/** - * blkcg_css - find the current css - * - * Find the css associated with either the kthread or the current task. - * This may return a dying css, so it is up to the caller to use tryget logic - * to confirm it is alive and well. - */ -static inline struct cgroup_subsys_state *blkcg_css(void) -{ - struct cgroup_subsys_state *css; - - css = kthread_blkcg(); - if (css) - return css; - return task_css(current, io_cgrp_id); -} static inline struct blkcg *css_to_blkcg(struct cgroup_subsys_state *css) { return css ? container_of(css, struct blkcg, css) : NULL; } -/** - * __bio_blkcg - internal version of bio_blkcg for bfq and cfq - * - * DO NOT USE. - * There is a flaw using this version of the function. In particular, this was - * used in a broken paradigm where association was called on the given css. It - * is possible though that the returned css from task_css() is in the process - * of dying due to migration of the current task. So it is improper to assume - * *_get() is going to succeed. Both BFQ and CFQ rely on this logic and will - * take additional work to handle more gracefully. - */ -static inline struct blkcg *__bio_blkcg(struct bio *bio) -{ - if (bio && bio->bi_blkg) - return bio->bi_blkg->blkcg; - return css_to_blkcg(blkcg_css()); -} - -/** - * bio_blkcg - grab the blkcg associated with a bio - * @bio: target bio - * - * This returns the blkcg associated with a bio, NULL if not associated. - * Callers are expected to either handle NULL or know association has been - * done prior to calling this. - */ static inline struct blkcg *bio_blkcg(struct bio *bio) { - if (bio && bio->bi_blkg) - return bio->bi_blkg->blkcg; - return NULL; + struct cgroup_subsys_state *css; + + if (bio && bio->bi_css) + return css_to_blkcg(bio->bi_css); + css = kthread_blkcg(); + if (css) + return css_to_blkcg(css); + return css_to_blkcg(task_css(current, io_cgrp_id)); } static inline bool blk_cgroup_congested(void) @@ -490,35 +451,26 @@ static inline int blkg_path(struct blkcg_gq *blkg, char *buf, int buflen) */ static inline void blkg_get(struct blkcg_gq *blkg) { - percpu_ref_get(&blkg->refcnt); + WARN_ON_ONCE(atomic_read(&blkg->refcnt) <= 0); + atomic_inc(&blkg->refcnt); } /** - * blkg_tryget - try and get a blkg reference + * blkg_try_get - try and get a blkg reference * @blkg: blkg to get * * This is for use when doing an RCU lookup of the blkg. We may be in the midst * of freeing this blkg, so we can only use it if the refcnt is not zero. */ -static inline bool blkg_tryget(struct blkcg_gq *blkg) +static inline struct blkcg_gq *blkg_try_get(struct blkcg_gq *blkg) { - return percpu_ref_tryget(&blkg->refcnt); + if (atomic_inc_not_zero(&blkg->refcnt)) + return blkg; + return NULL; } -/** - * blkg_tryget_closest - try and get a blkg ref on the closet blkg - * @blkg: blkg to get - * - * This walks up the blkg tree to find the closest non-dying blkg and returns - * the blkg that it did association with as it may not be the passed in blkg. - */ -static inline struct blkcg_gq *blkg_tryget_closest(struct blkcg_gq *blkg) -{ - while (!percpu_ref_tryget(&blkg->refcnt)) - blkg = blkg->parent; - return blkg; -} +void __blkg_release_rcu(struct rcu_head *rcu); /** * blkg_put - put a blkg reference @@ -526,7 +478,9 @@ static inline struct blkcg_gq *blkg_tryget_closest(struct blkcg_gq *blkg) */ static inline void blkg_put(struct blkcg_gq *blkg) { - percpu_ref_put(&blkg->refcnt); + WARN_ON_ONCE(atomic_read(&blkg->refcnt) <= 0); + if (atomic_dec_and_test(&blkg->refcnt)) + call_rcu(&blkg->rcu_head, __blkg_release_rcu); } /** @@ -579,36 +533,25 @@ static inline struct request_list *blk_get_rl(struct request_queue *q, rcu_read_lock(); - if (bio && bio->bi_blkg) { - blkcg = bio->bi_blkg->blkcg; - if (blkcg == &blkcg_root) - goto rl_use_root; - - blkg_get(bio->bi_blkg); - rcu_read_unlock(); - return &bio->bi_blkg->rl; - } + blkcg = bio_blkcg(bio); - blkcg = css_to_blkcg(blkcg_css()); + /* bypass blkg lookup and use @q->root_rl directly for root */ if (blkcg == &blkcg_root) - goto rl_use_root; + goto root_rl; + /* + * Try to use blkg->rl. blkg lookup may fail under memory pressure + * or if either the blkcg or queue is going away. Fall back to + * root_rl in such cases. + */ blkg = blkg_lookup(blkcg, q); if (unlikely(!blkg)) - blkg = __blkg_lookup_create(blkcg, q); - - if (blkg->blkcg == &blkcg_root || !blkg_tryget(blkg)) - goto rl_use_root; + goto root_rl; + blkg_get(blkg); rcu_read_unlock(); return &blkg->rl; - - /* - * Each blkg has its own request_list, however, the root blkcg - * uses the request_queue's root_rl. This is to avoid most - * overhead for the root blkcg. - */ -rl_use_root: +root_rl: rcu_read_unlock(); return &q->root_rl; } @@ -854,26 +797,32 @@ static inline bool blk_throtl_bio(struct request_queue *q, struct blkcg_gq *blkg struct bio *bio) { return false; } #endif - -static inline void blkcg_bio_issue_init(struct bio *bio) -{ - bio_issue_init(&bio->bi_issue, bio_sectors(bio)); -} - static inline bool blkcg_bio_issue_check(struct request_queue *q, struct bio *bio) { + struct blkcg *blkcg; struct blkcg_gq *blkg; bool throtl = false; rcu_read_lock(); + blkcg = bio_blkcg(bio); + + /* associate blkcg if bio hasn't attached one */ + bio_associate_blkcg(bio, &blkcg->css); - bio_associate_create_blkg(q, bio); - blkg = bio->bi_blkg; + blkg = blkg_lookup(blkcg, q); + if (unlikely(!blkg)) { + spin_lock_irq(q->queue_lock); + blkg = blkg_lookup_create(blkcg, q); + if (IS_ERR(blkg)) + blkg = NULL; + spin_unlock_irq(q->queue_lock); + } throtl = blk_throtl_bio(q, blkg, bio); if (!throtl) { + blkg = blkg ?: q->root_blkg; /* * If the bio is flagged with BIO_QUEUE_ENTERED it means this * is a split bio and we would have already accounted for the @@ -885,8 +834,6 @@ static inline bool blkcg_bio_issue_check(struct request_queue *q, blkg_rwstat_add(&blkg->stat_ios, bio->bi_opf, 1); } - blkcg_bio_issue_init(bio); - rcu_read_unlock(); return !throtl; } @@ -983,7 +930,6 @@ static inline int blkcg_activate_policy(struct request_queue *q, static inline void blkcg_deactivate_policy(struct request_queue *q, const struct blkcg_policy *pol) { } -static inline struct blkcg *__bio_blkcg(struct bio *bio) { return NULL; } static inline struct blkcg *bio_blkcg(struct bio *bio) { return NULL; } static inline struct blkg_policy_data *blkg_to_pd(struct blkcg_gq *blkg, @@ -999,7 +945,6 @@ static inline void blk_put_rl(struct request_list *rl) { } static inline void blk_rq_set_rl(struct request *rq, struct request_list *rl) { } static inline struct request_list *blk_rq_rl(struct request *rq) { return &rq->q->root_rl; } -static inline void blkcg_bio_issue_init(struct bio *bio) { } static inline bool blkcg_bio_issue_check(struct request_queue *q, struct bio *bio) { return true; } diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 093a818c5b68..1dcf652ba0aa 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -178,6 +178,7 @@ struct bio { * release. Read comment on top of bio_associate_current(). */ struct io_context *bi_ioc; + struct cgroup_subsys_state *bi_css; struct blkcg_gq *bi_blkg; struct bio_issue bi_issue; #endif diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h index b8bcbdeb2eac..32c553556bbd 100644 --- a/include/linux/cgroup.h +++ b/include/linux/cgroup.h @@ -93,8 +93,6 @@ extern struct css_set init_css_set; bool css_has_online_children(struct cgroup_subsys_state *css); struct cgroup_subsys_state *css_from_id(int id, struct cgroup_subsys *ss); -struct cgroup_subsys_state *cgroup_e_css(struct cgroup *cgroup, - struct cgroup_subsys *ss); struct cgroup_subsys_state *cgroup_get_e_css(struct cgroup *cgroup, struct cgroup_subsys *ss); struct cgroup_subsys_state *css_tryget_online_from_dir(struct dentry *dentry, diff --git a/include/linux/writeback.h b/include/linux/writeback.h index 738a0c24874f..fdfd04e348f6 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -246,8 +246,7 @@ static inline void wbc_attach_fdatawrite_inode(struct writeback_control *wbc, * * @bio is a part of the writeback in progress controlled by @wbc. Perform * writeback specific initialization. This is used to apply the cgroup - * writeback context. Must be called after the bio has been associated with - * a device. + * writeback context. */ static inline void wbc_init_bio(struct writeback_control *wbc, struct bio *bio) { @@ -258,7 +257,7 @@ static inline void wbc_init_bio(struct writeback_control *wbc, struct bio *bio) * regular writeback instead of writing things out itself. */ if (wbc->wb) - bio_associate_blkg_from_css(bio, wbc->wb->blkcg_css); + bio_associate_blkcg(bio, wbc->wb->blkcg_css); } #else /* CONFIG_CGROUP_WRITEBACK */ diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 4c1cf0969a80..4a3dae2a8283 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -492,7 +492,7 @@ static struct cgroup_subsys_state *cgroup_tryget_css(struct cgroup *cgrp, } /** - * cgroup_e_css_by_mask - obtain a cgroup's effective css for the specified ss + * cgroup_e_css - obtain a cgroup's effective css for the specified subsystem * @cgrp: the cgroup of interest * @ss: the subsystem of interest (%NULL returns @cgrp->self) * @@ -501,8 +501,8 @@ static struct cgroup_subsys_state *cgroup_tryget_css(struct cgroup *cgrp, * enabled. If @ss is associated with the hierarchy @cgrp is on, this * function is guaranteed to return non-NULL css. */ -static struct cgroup_subsys_state *cgroup_e_css_by_mask(struct cgroup *cgrp, - struct cgroup_subsys *ss) +static struct cgroup_subsys_state *cgroup_e_css(struct cgroup *cgrp, + struct cgroup_subsys *ss) { lockdep_assert_held(&cgroup_mutex); @@ -522,35 +522,6 @@ static struct cgroup_subsys_state *cgroup_e_css_by_mask(struct cgroup *cgrp, return cgroup_css(cgrp, ss); } -/** - * cgroup_e_css - obtain a cgroup's effective css for the specified subsystem - * @cgrp: the cgroup of interest - * @ss: the subsystem of interest - * - * Find and get the effective css of @cgrp for @ss. The effective css is - * defined as the matching css of the nearest ancestor including self which - * has @ss enabled. If @ss is not mounted on the hierarchy @cgrp is on, - * the root css is returned, so this function always returns a valid css. - * - * The returned css is not guaranteed to be online, and therefore it is the - * callers responsiblity to tryget a reference for it. - */ -struct cgroup_subsys_state *cgroup_e_css(struct cgroup *cgrp, - struct cgroup_subsys *ss) -{ - struct cgroup_subsys_state *css; - - do { - css = cgroup_css(cgrp, ss); - - if (css) - return css; - cgrp = cgroup_parent(cgrp); - } while (cgrp); - - return init_css_set.subsys[ss->id]; -} - /** * cgroup_get_e_css - get a cgroup's effective css for the specified subsystem * @cgrp: the cgroup of interest @@ -633,11 +604,10 @@ EXPORT_SYMBOL_GPL(of_css); * * Should be called under cgroup_[tree_]mutex. */ -#define for_each_e_css(css, ssid, cgrp) \ - for ((ssid) = 0; (ssid) < CGROUP_SUBSYS_COUNT; (ssid)++) \ - if (!((css) = cgroup_e_css_by_mask(cgrp, \ - cgroup_subsys[(ssid)]))) \ - ; \ +#define for_each_e_css(css, ssid, cgrp) \ + for ((ssid) = 0; (ssid) < CGROUP_SUBSYS_COUNT; (ssid)++) \ + if (!((css) = cgroup_e_css(cgrp, cgroup_subsys[(ssid)]))) \ + ; \ else /** @@ -1036,7 +1006,7 @@ static struct css_set *find_existing_css_set(struct css_set *old_cset, * @ss is in this hierarchy, so we want the * effective css from @cgrp. */ - template[i] = cgroup_e_css_by_mask(cgrp, ss); + template[i] = cgroup_e_css(cgrp, ss); } else { /* * @ss is not in this hierarchy, so we don't want @@ -3053,7 +3023,7 @@ static int cgroup_apply_control(struct cgroup *cgrp) return ret; /* - * At this point, cgroup_e_css_by_mask() results reflect the new csses + * At this point, cgroup_e_css() results reflect the new csses * making the following cgroup_update_dfl_csses() properly update * css associations of all tasks in the subtree. */ diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index fac0ddf8a8e2..2868d85f1fb1 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -764,9 +764,9 @@ blk_trace_bio_get_cgid(struct request_queue *q, struct bio *bio) if (!bt || !(blk_tracer_flags.val & TRACE_BLK_OPT_CGROUP)) return NULL; - if (!bio->bi_blkg) + if (!bio->bi_css) return NULL; - return cgroup_get_kernfs_id(bio_blkcg(bio)->css.cgroup); + return cgroup_get_kernfs_id(bio->bi_css->cgroup); } #else static union kernfs_node_id * diff --git a/mm/page_io.c b/mm/page_io.c index 573d3663d846..aafd19ec1db4 100644 --- a/mm/page_io.c +++ b/mm/page_io.c @@ -339,7 +339,7 @@ int __swap_writepage(struct page *page, struct writeback_control *wbc, goto out; } bio->bi_opf = REQ_OP_WRITE | REQ_SWAP | wbc_to_write_flags(wbc); - bio_associate_blkg_from_page(bio, page); + bio_associate_blkcg_from_page(bio, page); count_swpout_vm_event(page); set_page_writeback(page); unlock_page(page); -- cgit v1.2.3 From e68599a3c3ad0f3171a7cb4e48aa6f9a69381902 Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Fri, 2 Nov 2018 15:47:49 -0700 Subject: mm: handle no memcg case in memcg_kmem_charge() properly Mike Galbraith reported a regression caused by the commit 9b6f7e163cd0 ("mm: rework memcg kernel stack accounting") on a system with "cgroup_disable=memory" boot option: the system panics with the following stack trace: BUG: unable to handle kernel NULL pointer dereference at 00000000000000f8 PGD 0 P4D 0 Oops: 0002 [#1] PREEMPT SMP PTI CPU: 0 PID: 1 Comm: systemd Not tainted 4.19.0-preempt+ #410 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS ?-20180531_142017-buildhw-08.phx2.fed4 RIP: 0010:page_counter_try_charge+0x22/0xc0 Code: 41 5d c3 c3 0f 1f 40 00 0f 1f 44 00 00 48 85 ff 0f 84 a7 00 00 00 41 56 48 89 f8 49 89 fe 49 Call Trace: try_charge+0xcb/0x780 memcg_kmem_charge_memcg+0x28/0x80 memcg_kmem_charge+0x8b/0x1d0 copy_process.part.41+0x1ca/0x2070 _do_fork+0xd7/0x3d0 do_syscall_64+0x5a/0x180 entry_SYSCALL_64_after_hwframe+0x49/0xbe The problem occurs because get_mem_cgroup_from_current() returns the NULL pointer if memory controller is disabled. Let's check if this is a case at the beginning of memcg_kmem_charge() and just return 0 if mem_cgroup_disabled() returns true. This is how we handle this case in many other places in the memory controller code. Link: http://lkml.kernel.org/r/20181029215123.17830-1-guro@fb.com Fixes: 9b6f7e163cd0 ("mm: rework memcg kernel stack accounting") Signed-off-by: Roman Gushchin Reported-by: Mike Galbraith Acked-by: Rik van Riel Acked-by: Michal Hocko Cc: Johannes Weiner Cc: Vladimir Davydov Cc: Shakeel Butt Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memcontrol.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'mm') diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 54920cbc46bf..6e1469b80cb7 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -2593,7 +2593,7 @@ int memcg_kmem_charge(struct page *page, gfp_t gfp, int order) struct mem_cgroup *memcg; int ret = 0; - if (memcg_kmem_bypass()) + if (mem_cgroup_disabled() || memcg_kmem_bypass()) return 0; memcg = get_mem_cgroup_from_current(); -- cgit v1.2.3 From ac5b2c18911ffe95c08d69273917f90212cf5659 Mon Sep 17 00:00:00 2001 From: Andrea Arcangeli Date: Fri, 2 Nov 2018 15:47:59 -0700 Subject: mm: thp: relax __GFP_THISNODE for MADV_HUGEPAGE mappings THP allocation might be really disruptive when allocated on NUMA system with the local node full or hard to reclaim. Stefan has posted an allocation stall report on 4.12 based SLES kernel which suggests the same issue: kvm: page allocation stalls for 194572ms, order:9, mode:0x4740ca(__GFP_HIGHMEM|__GFP_IO|__GFP_FS|__GFP_COMP|__GFP_NOMEMALLOC|__GFP_HARDWALL|__GFP_THISNODE|__GFP_MOVABLE|__GFP_DIRECT_RECLAIM), nodemask=(null) kvm cpuset=/ mems_allowed=0-1 CPU: 10 PID: 84752 Comm: kvm Tainted: G W 4.12.0+98-ph 0000001 SLE15 (unreleased) Hardware name: Supermicro SYS-1029P-WTRT/X11DDW-NT, BIOS 2.0 12/05/2017 Call Trace: dump_stack+0x5c/0x84 warn_alloc+0xe0/0x180 __alloc_pages_slowpath+0x820/0xc90 __alloc_pages_nodemask+0x1cc/0x210 alloc_pages_vma+0x1e5/0x280 do_huge_pmd_wp_page+0x83f/0xf00 __handle_mm_fault+0x93d/0x1060 handle_mm_fault+0xc6/0x1b0 __do_page_fault+0x230/0x430 do_page_fault+0x2a/0x70 page_fault+0x7b/0x80 [...] Mem-Info: active_anon:126315487 inactive_anon:1612476 isolated_anon:5 active_file:60183 inactive_file:245285 isolated_file:0 unevictable:15657 dirty:286 writeback:1 unstable:0 slab_reclaimable:75543 slab_unreclaimable:2509111 mapped:81814 shmem:31764 pagetables:370616 bounce:0 free:32294031 free_pcp:6233 free_cma:0 Node 0 active_anon:254680388kB inactive_anon:1112760kB active_file:240648kB inactive_file:981168kB unevictable:13368kB isolated(anon):0kB isolated(file):0kB mapped:280240kB dirty:1144kB writeback:0kB shmem:95832kB shmem_thp: 0kB shmem_pmdmapped: 0kB anon_thp: 81225728kB writeback_tmp:0kB unstable:0kB all_unreclaimable? no Node 1 active_anon:250583072kB inactive_anon:5337144kB active_file:84kB inactive_file:0kB unevictable:49260kB isolated(anon):20kB isolated(file):0kB mapped:47016kB dirty:0kB writeback:4kB shmem:31224kB shmem_thp: 0kB shmem_pmdmapped: 0kB anon_thp: 31897600kB writeback_tmp:0kB unstable:0kB all_unreclaimable? no The defrag mode is "madvise" and from the above report it is clear that the THP has been allocated for MADV_HUGEPAGA vma. Andrea has identified that the main source of the problem is __GFP_THISNODE usage: : The problem is that direct compaction combined with the NUMA : __GFP_THISNODE logic in mempolicy.c is telling reclaim to swap very : hard the local node, instead of failing the allocation if there's no : THP available in the local node. : : Such logic was ok until __GFP_THISNODE was added to the THP allocation : path even with MPOL_DEFAULT. : : The idea behind the __GFP_THISNODE addition, is that it is better to : provide local memory in PAGE_SIZE units than to use remote NUMA THP : backed memory. That largely depends on the remote latency though, on : threadrippers for example the overhead is relatively low in my : experience. : : The combination of __GFP_THISNODE and __GFP_DIRECT_RECLAIM results in : extremely slow qemu startup with vfio, if the VM is larger than the : size of one host NUMA node. This is because it will try very hard to : unsuccessfully swapout get_user_pages pinned pages as result of the : __GFP_THISNODE being set, instead of falling back to PAGE_SIZE : allocations and instead of trying to allocate THP on other nodes (it : would be even worse without vfio type1 GUP pins of course, except it'd : be swapping heavily instead). Fix this by removing __GFP_THISNODE for THP requests which are requesting the direct reclaim. This effectivelly reverts 5265047ac301 on the grounds that the zone/node reclaim was known to be disruptive due to premature reclaim when there was memory free. While it made sense at the time for HPC workloads without NUMA awareness on rare machines, it was ultimately harmful in the majority of cases. The existing behaviour is similar, if not as widespare as it applies to a corner case but crucially, it cannot be tuned around like zone_reclaim_mode can. The default behaviour should always be to cause the least harm for the common case. If there are specialised use cases out there that want zone_reclaim_mode in specific cases, then it can be built on top. Longterm we should consider a memory policy which allows for the node reclaim like behavior for the specific memory ranges which would allow a [1] http://lkml.kernel.org/r/20180820032204.9591-1-aarcange@redhat.com Mel said: : Both patches look correct to me but I'm responding to this one because : it's the fix. The change makes sense and moves further away from the : severe stalling behaviour we used to see with both THP and zone reclaim : mode. : : I put together a basic experiment with usemem configured to reference a : buffer multiple times that is 80% the size of main memory on a 2-socket : box with symmetric node sizes and defrag set to "always". The defrag : setting is not the default but it would be functionally similar to : accessing a buffer with madvise(MADV_HUGEPAGE). Usemem is configured to : reference the buffer multiple times and while it's not an interesting : workload, it would be expected to complete reasonably quickly as it fits : within memory. The results were; : : usemem : vanilla noreclaim-v1 : Amean Elapsd-1 42.78 ( 0.00%) 26.87 ( 37.18%) : Amean Elapsd-3 27.55 ( 0.00%) 7.44 ( 73.00%) : Amean Elapsd-4 5.72 ( 0.00%) 5.69 ( 0.45%) : : This shows the elapsed time in seconds for 1 thread, 3 threads and 4 : threads referencing buffers 80% the size of memory. With the patches : applied, it's 37.18% faster for the single thread and 73% faster with two : threads. Note that 4 threads showing little difference does not indicate : the problem is related to thread counts. It's simply the case that 4 : threads gets spread so their workload mostly fits in one node. : : The overall view from /proc/vmstats is more startling : : 4.19.0-rc1 4.19.0-rc1 : vanillanoreclaim-v1r1 : Minor Faults 35593425 708164 : Major Faults 484088 36 : Swap Ins 3772837 0 : Swap Outs 3932295 0 : : Massive amounts of swap in/out without the patch : : Direct pages scanned 6013214 0 : Kswapd pages scanned 0 0 : Kswapd pages reclaimed 0 0 : Direct pages reclaimed 4033009 0 : : Lots of reclaim activity without the patch : : Kswapd efficiency 100% 100% : Kswapd velocity 0.000 0.000 : Direct efficiency 67% 100% : Direct velocity 11191.956 0.000 : : Mostly from direct reclaim context as you'd expect without the patch. : : Page writes by reclaim 3932314.000 0.000 : Page writes file 19 0 : Page writes anon 3932295 0 : Page reclaim immediate 42336 0 : : Writes from reclaim context is never good but the patch eliminates it. : : We should never have default behaviour to thrash the system for such a : basic workload. If zone reclaim mode behaviour is ever desired but on a : single task instead of a global basis then the sensible option is to build : a mempolicy that enforces that behaviour. This was a severe regression compared to previous kernels that made important workloads unusable and it starts when __GFP_THISNODE was added to THP allocations under MADV_HUGEPAGE. It is not a significant risk to go to the previous behavior before __GFP_THISNODE was added, it worked like that for years. This was simply an optimization to some lucky workloads that can fit in a single node, but it ended up breaking the VM for others that can't possibly fit in a single node, so going back is safe. [mhocko@suse.com: rewrote the changelog based on the one from Andrea] Link: http://lkml.kernel.org/r/20180925120326.24392-2-mhocko@kernel.org Fixes: 5265047ac301 ("mm, thp: really limit transparent hugepage allocation to local node") Signed-off-by: Andrea Arcangeli Signed-off-by: Michal Hocko Reported-by: Stefan Priebe Debugged-by: Andrea Arcangeli Reported-by: Alex Williamson Reviewed-by: Mel Gorman Tested-by: Mel Gorman Cc: Zi Yan Cc: Vlastimil Babka Cc: David Rientjes Cc: "Kirill A. Shutemov" Cc: [4.1+] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/mempolicy.c | 32 ++++++++++++++++++++++++++++++-- 1 file changed, 30 insertions(+), 2 deletions(-) (limited to 'mm') diff --git a/mm/mempolicy.c b/mm/mempolicy.c index cfd26d7e61a1..58fb833fce0c 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -2060,8 +2060,36 @@ alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma, nmask = policy_nodemask(gfp, pol); if (!nmask || node_isset(hpage_node, *nmask)) { mpol_cond_put(pol); - page = __alloc_pages_node(hpage_node, - gfp | __GFP_THISNODE, order); + /* + * We cannot invoke reclaim if __GFP_THISNODE + * is set. Invoking reclaim with + * __GFP_THISNODE set, would cause THP + * allocations to trigger heavy swapping + * despite there may be tons of free memory + * (including potentially plenty of THP + * already available in the buddy) on all the + * other NUMA nodes. + * + * At most we could invoke compaction when + * __GFP_THISNODE is set (but we would need to + * refrain from invoking reclaim even if + * compaction returned COMPACT_SKIPPED because + * there wasn't not enough memory to succeed + * compaction). For now just avoid + * __GFP_THISNODE instead of limiting the + * allocation path to a strict and single + * compaction invocation. + * + * Supposedly if direct reclaim was enabled by + * the caller, the app prefers THP regardless + * of the node it comes from so this would be + * more desiderable behavior than only + * providing THP originated from the local + * node in such case. + */ + if (!(gfp & __GFP_DIRECT_RECLAIM)) + gfp |= __GFP_THISNODE; + page = __alloc_pages_node(hpage_node, gfp, order); goto out; } } -- cgit v1.2.3 From 89c83fb539f95491be80cdd5158e6f0ce329e317 Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Fri, 2 Nov 2018 15:48:31 -0700 Subject: mm, thp: consolidate THP gfp handling into alloc_hugepage_direct_gfpmask THP allocation mode is quite complex and it depends on the defrag mode. This complexity is hidden in alloc_hugepage_direct_gfpmask from a large part currently. The NUMA special casing (namely __GFP_THISNODE) is however independent and placed in alloc_pages_vma currently. This both adds an unnecessary branch to all vma based page allocation requests and it makes the code more complex unnecessarily as well. Not to mention that e.g. shmem THP used to do the node reclaiming unconditionally regardless of the defrag mode until recently. This was not only unexpected behavior but it was also hardly a good default behavior and I strongly suspect it was just a side effect of the code sharing more than a deliberate decision which suggests that such a layering is wrong. Get rid of the thp special casing from alloc_pages_vma and move the logic to alloc_hugepage_direct_gfpmask. __GFP_THISNODE is applied to the resulting gfp mask only when the direct reclaim is not requested and when there is no explicit numa binding to preserve the current logic. Please note that there's also a slight difference wrt MPOL_BIND now. The previous code would avoid using __GFP_THISNODE if the local node was outside of policy_nodemask(). After this patch __GFP_THISNODE is avoided for all MPOL_BIND policies. So there's a difference that if local node is actually allowed by the bind policy's nodemask, previously __GFP_THISNODE would be added, but now it won't be. From the behavior POV this is still correct because the policy nodemask is used. Link: http://lkml.kernel.org/r/20180925120326.24392-3-mhocko@kernel.org Signed-off-by: Michal Hocko Acked-by: Vlastimil Babka Cc: Alex Williamson Cc: Andrea Arcangeli Cc: David Rientjes Cc: "Kirill A. Shutemov" Cc: Mel Gorman Cc: Stefan Priebe - Profihost AG Cc: Zi Yan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/gfp.h | 12 +++------ include/linux/mempolicy.h | 2 ++ mm/huge_memory.c | 38 +++++++++++++++++++++------- mm/mempolicy.c | 63 +++-------------------------------------------- mm/shmem.c | 2 +- 5 files changed, 40 insertions(+), 77 deletions(-) (limited to 'mm') diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 24bcc5eec6b4..76f8db0b0e71 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -510,22 +510,18 @@ alloc_pages(gfp_t gfp_mask, unsigned int order) } extern struct page *alloc_pages_vma(gfp_t gfp_mask, int order, struct vm_area_struct *vma, unsigned long addr, - int node, bool hugepage); -#define alloc_hugepage_vma(gfp_mask, vma, addr, order) \ - alloc_pages_vma(gfp_mask, order, vma, addr, numa_node_id(), true) + int node); #else #define alloc_pages(gfp_mask, order) \ alloc_pages_node(numa_node_id(), gfp_mask, order) -#define alloc_pages_vma(gfp_mask, order, vma, addr, node, false)\ - alloc_pages(gfp_mask, order) -#define alloc_hugepage_vma(gfp_mask, vma, addr, order) \ +#define alloc_pages_vma(gfp_mask, order, vma, addr, node)\ alloc_pages(gfp_mask, order) #endif #define alloc_page(gfp_mask) alloc_pages(gfp_mask, 0) #define alloc_page_vma(gfp_mask, vma, addr) \ - alloc_pages_vma(gfp_mask, 0, vma, addr, numa_node_id(), false) + alloc_pages_vma(gfp_mask, 0, vma, addr, numa_node_id()) #define alloc_page_vma_node(gfp_mask, vma, addr, node) \ - alloc_pages_vma(gfp_mask, 0, vma, addr, node, false) + alloc_pages_vma(gfp_mask, 0, vma, addr, node) extern unsigned long __get_free_pages(gfp_t gfp_mask, unsigned int order); extern unsigned long get_zeroed_page(gfp_t gfp_mask); diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h index 5228c62af416..bac395f1d00a 100644 --- a/include/linux/mempolicy.h +++ b/include/linux/mempolicy.h @@ -139,6 +139,8 @@ struct mempolicy *mpol_shared_policy_lookup(struct shared_policy *sp, struct mempolicy *get_task_policy(struct task_struct *p); struct mempolicy *__get_vma_policy(struct vm_area_struct *vma, unsigned long addr); +struct mempolicy *get_vma_policy(struct vm_area_struct *vma, + unsigned long addr); bool vma_policy_mof(struct vm_area_struct *vma); extern void numa_default_policy(void); diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 4e4ef8fa479d..55478ab3c83b 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -629,21 +629,40 @@ release: * available * never: never stall for any thp allocation */ -static inline gfp_t alloc_hugepage_direct_gfpmask(struct vm_area_struct *vma) +static inline gfp_t alloc_hugepage_direct_gfpmask(struct vm_area_struct *vma, unsigned long addr) { const bool vma_madvised = !!(vma->vm_flags & VM_HUGEPAGE); + gfp_t this_node = 0; + +#ifdef CONFIG_NUMA + struct mempolicy *pol; + /* + * __GFP_THISNODE is used only when __GFP_DIRECT_RECLAIM is not + * specified, to express a general desire to stay on the current + * node for optimistic allocation attempts. If the defrag mode + * and/or madvise hint requires the direct reclaim then we prefer + * to fallback to other node rather than node reclaim because that + * can lead to excessive reclaim even though there is free memory + * on other nodes. We expect that NUMA preferences are specified + * by memory policies. + */ + pol = get_vma_policy(vma, addr); + if (pol->mode != MPOL_BIND) + this_node = __GFP_THISNODE; + mpol_cond_put(pol); +#endif if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags)) return GFP_TRANSHUGE | (vma_madvised ? 0 : __GFP_NORETRY); if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags)) - return GFP_TRANSHUGE_LIGHT | __GFP_KSWAPD_RECLAIM; + return GFP_TRANSHUGE_LIGHT | __GFP_KSWAPD_RECLAIM | this_node; if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags)) return GFP_TRANSHUGE_LIGHT | (vma_madvised ? __GFP_DIRECT_RECLAIM : - __GFP_KSWAPD_RECLAIM); + __GFP_KSWAPD_RECLAIM | this_node); if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags)) return GFP_TRANSHUGE_LIGHT | (vma_madvised ? __GFP_DIRECT_RECLAIM : - 0); - return GFP_TRANSHUGE_LIGHT; + this_node); + return GFP_TRANSHUGE_LIGHT | this_node; } /* Caller must hold page table lock. */ @@ -715,8 +734,8 @@ vm_fault_t do_huge_pmd_anonymous_page(struct vm_fault *vmf) pte_free(vma->vm_mm, pgtable); return ret; } - gfp = alloc_hugepage_direct_gfpmask(vma); - page = alloc_hugepage_vma(gfp, vma, haddr, HPAGE_PMD_ORDER); + gfp = alloc_hugepage_direct_gfpmask(vma, haddr); + page = alloc_pages_vma(gfp, HPAGE_PMD_ORDER, vma, haddr, numa_node_id()); if (unlikely(!page)) { count_vm_event(THP_FAULT_FALLBACK); return VM_FAULT_FALLBACK; @@ -1286,8 +1305,9 @@ vm_fault_t do_huge_pmd_wp_page(struct vm_fault *vmf, pmd_t orig_pmd) alloc: if (transparent_hugepage_enabled(vma) && !transparent_hugepage_debug_cow()) { - huge_gfp = alloc_hugepage_direct_gfpmask(vma); - new_page = alloc_hugepage_vma(huge_gfp, vma, haddr, HPAGE_PMD_ORDER); + huge_gfp = alloc_hugepage_direct_gfpmask(vma, haddr); + new_page = alloc_pages_vma(huge_gfp, HPAGE_PMD_ORDER, vma, + haddr, numa_node_id()); } else new_page = NULL; diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 58fb833fce0c..5837a067124d 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -1116,8 +1116,8 @@ static struct page *new_page(struct page *page, unsigned long start) } else if (PageTransHuge(page)) { struct page *thp; - thp = alloc_hugepage_vma(GFP_TRANSHUGE, vma, address, - HPAGE_PMD_ORDER); + thp = alloc_pages_vma(GFP_TRANSHUGE, HPAGE_PMD_ORDER, vma, + address, numa_node_id()); if (!thp) return NULL; prep_transhuge_page(thp); @@ -1662,7 +1662,7 @@ struct mempolicy *__get_vma_policy(struct vm_area_struct *vma, * freeing by another task. It is the caller's responsibility to free the * extra reference for shared policies. */ -static struct mempolicy *get_vma_policy(struct vm_area_struct *vma, +struct mempolicy *get_vma_policy(struct vm_area_struct *vma, unsigned long addr) { struct mempolicy *pol = __get_vma_policy(vma, addr); @@ -2011,7 +2011,6 @@ static struct page *alloc_page_interleave(gfp_t gfp, unsigned order, * @vma: Pointer to VMA or NULL if not available. * @addr: Virtual Address of the allocation. Must be inside the VMA. * @node: Which node to prefer for allocation (modulo policy). - * @hugepage: for hugepages try only the preferred node if possible * * This function allocates a page from the kernel page pool and applies * a NUMA policy associated with the VMA or the current process. @@ -2022,7 +2021,7 @@ static struct page *alloc_page_interleave(gfp_t gfp, unsigned order, */ struct page * alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma, - unsigned long addr, int node, bool hugepage) + unsigned long addr, int node) { struct mempolicy *pol; struct page *page; @@ -2040,60 +2039,6 @@ alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma, goto out; } - if (unlikely(IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) && hugepage)) { - int hpage_node = node; - - /* - * For hugepage allocation and non-interleave policy which - * allows the current node (or other explicitly preferred - * node) we only try to allocate from the current/preferred - * node and don't fall back to other nodes, as the cost of - * remote accesses would likely offset THP benefits. - * - * If the policy is interleave, or does not allow the current - * node in its nodemask, we allocate the standard way. - */ - if (pol->mode == MPOL_PREFERRED && - !(pol->flags & MPOL_F_LOCAL)) - hpage_node = pol->v.preferred_node; - - nmask = policy_nodemask(gfp, pol); - if (!nmask || node_isset(hpage_node, *nmask)) { - mpol_cond_put(pol); - /* - * We cannot invoke reclaim if __GFP_THISNODE - * is set. Invoking reclaim with - * __GFP_THISNODE set, would cause THP - * allocations to trigger heavy swapping - * despite there may be tons of free memory - * (including potentially plenty of THP - * already available in the buddy) on all the - * other NUMA nodes. - * - * At most we could invoke compaction when - * __GFP_THISNODE is set (but we would need to - * refrain from invoking reclaim even if - * compaction returned COMPACT_SKIPPED because - * there wasn't not enough memory to succeed - * compaction). For now just avoid - * __GFP_THISNODE instead of limiting the - * allocation path to a strict and single - * compaction invocation. - * - * Supposedly if direct reclaim was enabled by - * the caller, the app prefers THP regardless - * of the node it comes from so this would be - * more desiderable behavior than only - * providing THP originated from the local - * node in such case. - */ - if (!(gfp & __GFP_DIRECT_RECLAIM)) - gfp |= __GFP_THISNODE; - page = __alloc_pages_node(hpage_node, gfp, order); - goto out; - } - } - nmask = policy_nodemask(gfp, pol); preferred_nid = policy_node(gfp, pol, node); page = __alloc_pages_nodemask(gfp, order, preferred_nid, nmask); diff --git a/mm/shmem.c b/mm/shmem.c index 56bf122e0bb4..ea26d7a0342d 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -1435,7 +1435,7 @@ static struct page *shmem_alloc_hugepage(gfp_t gfp, shmem_pseudo_vma_init(&pvma, info, hindex); page = alloc_pages_vma(gfp | __GFP_COMP | __GFP_NORETRY | __GFP_NOWARN, - HPAGE_PMD_ORDER, &pvma, 0, numa_node_id(), true); + HPAGE_PMD_ORDER, &pvma, 0, numa_node_id()); shmem_pseudo_vma_destroy(&pvma); if (page) prep_transhuge_page(page); -- cgit v1.2.3 From dd33ad7b251f900481701b2a82d25de583867708 Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Fri, 2 Nov 2018 15:48:46 -0700 Subject: memory_hotplug: cond_resched in __remove_pages We have received a bug report that unbinding a large pmem (>1TB) can result in a soft lockup: NMI watchdog: BUG: soft lockup - CPU#9 stuck for 23s! [ndctl:4365] [...] Supported: Yes CPU: 9 PID: 4365 Comm: ndctl Not tainted 4.12.14-94.40-default #1 SLE12-SP4 Hardware name: Intel Corporation S2600WFD/S2600WFD, BIOS SE5C620.86B.01.00.0833.051120182255 05/11/2018 task: ffff9cce7d4410c0 task.stack: ffffbe9eb1bc4000 RIP: 0010:__put_page+0x62/0x80 Call Trace: devm_memremap_pages_release+0x152/0x260 release_nodes+0x18d/0x1d0 device_release_driver_internal+0x160/0x210 unbind_store+0xb3/0xe0 kernfs_fop_write+0x102/0x180 __vfs_write+0x26/0x150 vfs_write+0xad/0x1a0 SyS_write+0x42/0x90 do_syscall_64+0x74/0x150 entry_SYSCALL_64_after_hwframe+0x3d/0xa2 RIP: 0033:0x7fd13166b3d0 It has been reported on an older (4.12) kernel but the current upstream code doesn't cond_resched in the hot remove code at all and the given range to remove might be really large. Fix the issue by calling cond_resched once per memory section. Link: http://lkml.kernel.org/r/20181031125840.23982-1-mhocko@kernel.org Signed-off-by: Michal Hocko Acked-by: Johannes Thumshirn Cc: Dan Williams Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memory_hotplug.c | 1 + 1 file changed, 1 insertion(+) (limited to 'mm') diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 61972da38d93..2b2b3ccbbfb5 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -586,6 +586,7 @@ int __remove_pages(struct zone *zone, unsigned long phys_start_pfn, for (i = 0; i < sections_to_remove; i++) { unsigned long pfn = phys_start_pfn + i*PAGES_PER_SECTION; + cond_resched(); ret = __remove_section(zone, __pfn_to_section(pfn), map_offset, altmap); map_offset = 0; -- cgit v1.2.3 From ca0246bb97c23da9d267c2107c07fb77e38205c9 Mon Sep 17 00:00:00 2001 From: Vitaly Wool Date: Fri, 16 Nov 2018 15:07:56 -0800 Subject: z3fold: fix possible reclaim races Reclaim and free can race on an object which is basically fine but in order for reclaim to be able to map "freed" object we need to encode object length in the handle. handle_to_chunks() is then introduced to extract object length from a handle and use it during mapping. Moreover, to avoid racing on a z3fold "headless" page release, we should not try to free that page in z3fold_free() if the reclaim bit is set. Also, in the unlikely case of trying to reclaim a page being freed, we should not proceed with that page. While at it, fix the page accounting in reclaim function. This patch supersedes "[PATCH] z3fold: fix reclaim lock-ups". Link: http://lkml.kernel.org/r/20181105162225.74e8837d03583a9b707cf559@gmail.com Signed-off-by: Vitaly Wool Signed-off-by: Jongseok Kim Reported-by-by: Jongseok Kim Reviewed-by: Snild Dolkow Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/z3fold.c | 101 +++++++++++++++++++++++++++++++++++++----------------------- 1 file changed, 62 insertions(+), 39 deletions(-) (limited to 'mm') diff --git a/mm/z3fold.c b/mm/z3fold.c index 4b366d181f35..aee9b0b8d907 100644 --- a/mm/z3fold.c +++ b/mm/z3fold.c @@ -99,6 +99,7 @@ struct z3fold_header { #define NCHUNKS ((PAGE_SIZE - ZHDR_SIZE_ALIGNED) >> CHUNK_SHIFT) #define BUDDY_MASK (0x3) +#define BUDDY_SHIFT 2 /** * struct z3fold_pool - stores metadata for each z3fold pool @@ -145,7 +146,7 @@ enum z3fold_page_flags { MIDDLE_CHUNK_MAPPED, NEEDS_COMPACTING, PAGE_STALE, - UNDER_RECLAIM + PAGE_CLAIMED, /* by either reclaim or free */ }; /***************** @@ -174,7 +175,7 @@ static struct z3fold_header *init_z3fold_page(struct page *page, clear_bit(MIDDLE_CHUNK_MAPPED, &page->private); clear_bit(NEEDS_COMPACTING, &page->private); clear_bit(PAGE_STALE, &page->private); - clear_bit(UNDER_RECLAIM, &page->private); + clear_bit(PAGE_CLAIMED, &page->private); spin_lock_init(&zhdr->page_lock); kref_init(&zhdr->refcount); @@ -223,8 +224,11 @@ static unsigned long encode_handle(struct z3fold_header *zhdr, enum buddy bud) unsigned long handle; handle = (unsigned long)zhdr; - if (bud != HEADLESS) - handle += (bud + zhdr->first_num) & BUDDY_MASK; + if (bud != HEADLESS) { + handle |= (bud + zhdr->first_num) & BUDDY_MASK; + if (bud == LAST) + handle |= (zhdr->last_chunks << BUDDY_SHIFT); + } return handle; } @@ -234,6 +238,12 @@ static struct z3fold_header *handle_to_z3fold_header(unsigned long handle) return (struct z3fold_header *)(handle & PAGE_MASK); } +/* only for LAST bud, returns zero otherwise */ +static unsigned short handle_to_chunks(unsigned long handle) +{ + return (handle & ~PAGE_MASK) >> BUDDY_SHIFT; +} + /* * (handle & BUDDY_MASK) < zhdr->first_num is possible in encode_handle * but that doesn't matter. because the masking will result in the @@ -720,37 +730,39 @@ static void z3fold_free(struct z3fold_pool *pool, unsigned long handle) page = virt_to_page(zhdr); if (test_bit(PAGE_HEADLESS, &page->private)) { - /* HEADLESS page stored */ - bud = HEADLESS; - } else { - z3fold_page_lock(zhdr); - bud = handle_to_buddy(handle); - - switch (bud) { - case FIRST: - zhdr->first_chunks = 0; - break; - case MIDDLE: - zhdr->middle_chunks = 0; - zhdr->start_middle = 0; - break; - case LAST: - zhdr->last_chunks = 0; - break; - default: - pr_err("%s: unknown bud %d\n", __func__, bud); - WARN_ON(1); - z3fold_page_unlock(zhdr); - return; + /* if a headless page is under reclaim, just leave. + * NB: we use test_and_set_bit for a reason: if the bit + * has not been set before, we release this page + * immediately so we don't care about its value any more. + */ + if (!test_and_set_bit(PAGE_CLAIMED, &page->private)) { + spin_lock(&pool->lock); + list_del(&page->lru); + spin_unlock(&pool->lock); + free_z3fold_page(page); + atomic64_dec(&pool->pages_nr); } + return; } - if (bud == HEADLESS) { - spin_lock(&pool->lock); - list_del(&page->lru); - spin_unlock(&pool->lock); - free_z3fold_page(page); - atomic64_dec(&pool->pages_nr); + /* Non-headless case */ + z3fold_page_lock(zhdr); + bud = handle_to_buddy(handle); + + switch (bud) { + case FIRST: + zhdr->first_chunks = 0; + break; + case MIDDLE: + zhdr->middle_chunks = 0; + break; + case LAST: + zhdr->last_chunks = 0; + break; + default: + pr_err("%s: unknown bud %d\n", __func__, bud); + WARN_ON(1); + z3fold_page_unlock(zhdr); return; } @@ -758,7 +770,7 @@ static void z3fold_free(struct z3fold_pool *pool, unsigned long handle) atomic64_dec(&pool->pages_nr); return; } - if (test_bit(UNDER_RECLAIM, &page->private)) { + if (test_bit(PAGE_CLAIMED, &page->private)) { z3fold_page_unlock(zhdr); return; } @@ -836,20 +848,30 @@ static int z3fold_reclaim_page(struct z3fold_pool *pool, unsigned int retries) } list_for_each_prev(pos, &pool->lru) { page = list_entry(pos, struct page, lru); + + /* this bit could have been set by free, in which case + * we pass over to the next page in the pool. + */ + if (test_and_set_bit(PAGE_CLAIMED, &page->private)) + continue; + + zhdr = page_address(page); if (test_bit(PAGE_HEADLESS, &page->private)) - /* candidate found */ break; - zhdr = page_address(page); - if (!z3fold_page_trylock(zhdr)) + if (!z3fold_page_trylock(zhdr)) { + zhdr = NULL; continue; /* can't evict at this point */ + } kref_get(&zhdr->refcount); list_del_init(&zhdr->buddy); zhdr->cpu = -1; - set_bit(UNDER_RECLAIM, &page->private); break; } + if (!zhdr) + break; + list_del_init(&page->lru); spin_unlock(&pool->lock); @@ -898,6 +920,7 @@ next: if (test_bit(PAGE_HEADLESS, &page->private)) { if (ret == 0) { free_z3fold_page(page); + atomic64_dec(&pool->pages_nr); return 0; } spin_lock(&pool->lock); @@ -905,7 +928,7 @@ next: spin_unlock(&pool->lock); } else { z3fold_page_lock(zhdr); - clear_bit(UNDER_RECLAIM, &page->private); + clear_bit(PAGE_CLAIMED, &page->private); if (kref_put(&zhdr->refcount, release_z3fold_page_locked)) { atomic64_dec(&pool->pages_nr); @@ -964,7 +987,7 @@ static void *z3fold_map(struct z3fold_pool *pool, unsigned long handle) set_bit(MIDDLE_CHUNK_MAPPED, &page->private); break; case LAST: - addr += PAGE_SIZE - (zhdr->last_chunks << CHUNK_SHIFT); + addr += PAGE_SIZE - (handle_to_chunks(handle) << CHUNK_SHIFT); break; default: pr_err("unknown buddy id %d\n", buddy); -- cgit v1.2.3 From 5e41540c8a0f0e98c337dda8b391e5dda0cde7cf Mon Sep 17 00:00:00 2001 From: Mike Kravetz Date: Fri, 16 Nov 2018 15:08:04 -0800 Subject: hugetlbfs: fix kernel BUG at fs/hugetlbfs/inode.c:444! This bug has been experienced several times by the Oracle DB team. The BUG is in remove_inode_hugepages() as follows: /* * If page is mapped, it was faulted in after being * unmapped in caller. Unmap (again) now after taking * the fault mutex. The mutex will prevent faults * until we finish removing the page. * * This race can only happen in the hole punch case. * Getting here in a truncate operation is a bug. */ if (unlikely(page_mapped(page))) { BUG_ON(truncate_op); In this case, the elevated map count is not the result of a race. Rather it was incorrectly incremented as the result of a bug in the huge pmd sharing code. Consider the following: - Process A maps a hugetlbfs file of sufficient size and alignment (PUD_SIZE) that a pmd page could be shared. - Process B maps the same hugetlbfs file with the same size and alignment such that a pmd page is shared. - Process B then calls mprotect() to change protections for the mapping with the shared pmd. As a result, the pmd is 'unshared'. - Process B then calls mprotect() again to chage protections for the mapping back to their original value. pmd remains unshared. - Process B then forks and process C is created. During the fork process, we do dup_mm -> dup_mmap -> copy_page_range to copy page tables. Copying page tables for hugetlb mappings is done in the routine copy_hugetlb_page_range. In copy_hugetlb_page_range(), the destination pte is obtained by: dst_pte = huge_pte_alloc(dst, addr, sz); If pmd sharing is possible, the returned pointer will be to a pte in an existing page table. In the situation above, process C could share with either process A or process B. Since process A is first in the list, the returned pte is a pointer to a pte in process A's page table. However, the check for pmd sharing in copy_hugetlb_page_range is: /* If the pagetables are shared don't copy or take references */ if (dst_pte == src_pte) continue; Since process C is sharing with process A instead of process B, the above test fails. The code in copy_hugetlb_page_range which follows assumes dst_pte points to a huge_pte_none pte. It copies the pte entry from src_pte to dst_pte and increments this map count of the associated page. This is how we end up with an elevated map count. To solve, check the dst_pte entry for huge_pte_none. If !none, this implies PMD sharing so do not copy. Link: http://lkml.kernel.org/r/20181105212315.14125-1-mike.kravetz@oracle.com Fixes: c5c99429fa57 ("fix hugepages leak due to pagetable page sharing") Signed-off-by: Mike Kravetz Reviewed-by: Naoya Horiguchi Cc: Michal Hocko Cc: Hugh Dickins Cc: Andrea Arcangeli Cc: "Kirill A . Shutemov" Cc: Davidlohr Bueso Cc: Prakash Sangappa Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/hugetlb.c | 23 +++++++++++++++++++---- 1 file changed, 19 insertions(+), 4 deletions(-) (limited to 'mm') diff --git a/mm/hugetlb.c b/mm/hugetlb.c index c007fb5fb8d5..7f2a28ab46d5 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -3233,7 +3233,7 @@ static int is_hugetlb_entry_hwpoisoned(pte_t pte) int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src, struct vm_area_struct *vma) { - pte_t *src_pte, *dst_pte, entry; + pte_t *src_pte, *dst_pte, entry, dst_entry; struct page *ptepage; unsigned long addr; int cow; @@ -3261,15 +3261,30 @@ int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src, break; } - /* If the pagetables are shared don't copy or take references */ - if (dst_pte == src_pte) + /* + * If the pagetables are shared don't copy or take references. + * dst_pte == src_pte is the common case of src/dest sharing. + * + * However, src could have 'unshared' and dst shares with + * another vma. If dst_pte !none, this implies sharing. + * Check here before taking page table lock, and once again + * after taking the lock below. + */ + dst_entry = huge_ptep_get(dst_pte); + if ((dst_pte == src_pte) || !huge_pte_none(dst_entry)) continue; dst_ptl = huge_pte_lock(h, dst, dst_pte); src_ptl = huge_pte_lockptr(h, src, src_pte); spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING); entry = huge_ptep_get(src_pte); - if (huge_pte_none(entry)) { /* skip none entry */ + dst_entry = huge_ptep_get(dst_pte); + if (huge_pte_none(entry) || !huge_pte_none(dst_entry)) { + /* + * Skip if src entry none. Also, skip in the + * unlikely case dst entry !none as this implies + * sharing with another vma. + */ ; } else if (unlikely(is_hugetlb_entry_migration(entry) || is_hugetlb_entry_hwpoisoned(entry))) { -- cgit v1.2.3 From 873d7bcfd066663e3e50113dc4a0de19289b6354 Mon Sep 17 00:00:00 2001 From: Vasily Averin Date: Fri, 16 Nov 2018 15:08:11 -0800 Subject: mm/swapfile.c: use kvzalloc for swap_info_struct allocation Commit a2468cc9bfdf ("swap: choose swap device according to numa node") changed 'avail_lists' field of 'struct swap_info_struct' to an array. In popular linux distros it increased size of swap_info_struct up to 40 Kbytes and now swap_info_struct allocation requires order-4 page. Switch to kvzmalloc allows to avoid unexpected allocation failures. Link: http://lkml.kernel.org/r/fc23172d-3c75-21e2-d551-8b1808cbe593@virtuozzo.com Fixes: a2468cc9bfdf ("swap: choose swap device according to numa node") Signed-off-by: Vasily Averin Acked-by: Aaron Lu Acked-by: Michal Hocko Reviewed-by: Andrew Morton Cc: Huang Ying Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/swapfile.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'mm') diff --git a/mm/swapfile.c b/mm/swapfile.c index 644f746e167a..8688ae65ef58 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -2813,7 +2813,7 @@ static struct swap_info_struct *alloc_swap_info(void) unsigned int type; int i; - p = kzalloc(sizeof(*p), GFP_KERNEL); + p = kvzalloc(sizeof(*p), GFP_KERNEL); if (!p) return ERR_PTR(-ENOMEM); @@ -2824,7 +2824,7 @@ static struct swap_info_struct *alloc_swap_info(void) } if (type >= MAX_SWAPFILES) { spin_unlock(&swap_lock); - kfree(p); + kvfree(p); return ERR_PTR(-EPERM); } if (type >= nr_swapfiles) { @@ -2838,7 +2838,7 @@ static struct swap_info_struct *alloc_swap_info(void) smp_wmb(); nr_swapfiles++; } else { - kfree(p); + kvfree(p); p = swap_info[type]; /* * Do not memset this entry: a racing procfs swap_next() -- cgit v1.2.3 From 9d7899999c62c1a81129b76d2a6ecbc4655e1597 Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Fri, 16 Nov 2018 15:08:15 -0800 Subject: mm, memory_hotplug: check zone_movable in has_unmovable_pages Page state checks are racy. Under a heavy memory workload (e.g. stress -m 200 -t 2h) it is quite easy to hit a race window when the page is allocated but its state is not fully populated yet. A debugging patch to dump the struct page state shows has_unmovable_pages: pfn:0x10dfec00, found:0x1, count:0x0 page:ffffea0437fb0000 count:1 mapcount:1 mapping:ffff880e05239841 index:0x7f26e5000 compound_mapcount: 1 flags: 0x5fffffc0090034(uptodate|lru|active|head|swapbacked) Note that the state has been checked for both PageLRU and PageSwapBacked already. Closing this race completely would require some sort of retry logic. This can be tricky and error prone (think of potential endless or long taking loops). Workaround this problem for movable zones at least. Such a zone should only contain movable pages. Commit 15c30bc09085 ("mm, memory_hotplug: make has_unmovable_pages more robust") has told us that this is not strictly true though. Bootmem pages should be marked reserved though so we can move the original check after the PageReserved check. Pages from other zones are still prone to races but we even do not pretend that memory hotremove works for those so pre-mature failure doesn't hurt that much. Link: http://lkml.kernel.org/r/20181106095524.14629-1-mhocko@kernel.org Fixes: 15c30bc09085 ("mm, memory_hotplug: make has_unmovable_pages more robust") Signed-off-by: Michal Hocko Reported-by: Baoquan He Tested-by: Baoquan He Acked-by: Baoquan He Reviewed-by: Oscar Salvador Acked-by: Balbir Singh Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/page_alloc.c | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'mm') diff --git a/mm/page_alloc.c b/mm/page_alloc.c index a919ba5cb3c8..a0e5ec0addd2 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -7788,6 +7788,14 @@ bool has_unmovable_pages(struct zone *zone, struct page *page, int count, if (PageReserved(page)) goto unmovable; + /* + * If the zone is movable and we have ruled out all reserved + * pages then it should be reasonably safe to assume the rest + * is movable. + */ + if (zone_idx(zone) == ZONE_MOVABLE) + continue; + /* * Hugepages are not in LRU lists, but they're movable. * We need not scan over tail pages bacause we don't -- cgit v1.2.3 From 78179556e7605ba07fd3ddba6ab8891fa457b93e Mon Sep 17 00:00:00 2001 From: Mike Rapoport Date: Fri, 16 Nov 2018 15:08:29 -0800 Subject: mm/gup.c: fix follow_page_mask() kerneldoc comment Commit df06b37ffe5a ("mm/gup: cache dev_pagemap while pinning pages") modified the signature of follow_page_mask() but left the parameter description behind. Update the description to make the code and comments agree again. While at it, update formatting of the return value description to match Documentation/doc-guide/kernel-doc.rst guidelines. Link: http://lkml.kernel.org/r/1541603316-27832-1-git-send-email-rppt@linux.ibm.com Signed-off-by: Mike Rapoport Reviewed-by: Andrew Morton Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/gup.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) (limited to 'mm') diff --git a/mm/gup.c b/mm/gup.c index f76e77a2d34b..aa43620a3270 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -385,11 +385,17 @@ static struct page *follow_p4d_mask(struct vm_area_struct *vma, * @vma: vm_area_struct mapping @address * @address: virtual address to look up * @flags: flags modifying lookup behaviour - * @page_mask: on output, *page_mask is set according to the size of the page + * @ctx: contains dev_pagemap for %ZONE_DEVICE memory pinning and a + * pointer to output page_mask * * @flags can have FOLL_ flags set, defined in * - * Returns the mapped (struct page *), %NULL if no mapping exists, or + * When getting pages from ZONE_DEVICE memory, the @ctx->pgmap caches + * the device's dev_pagemap metadata to avoid repeating expensive lookups. + * + * On output, the @ctx->page_mask is set according to the size of the page. + * + * Return: the mapped (struct page *), %NULL if no mapping exists, or * an error pointer if there is a mapping to something not represented * by a page descriptor (see also vm_normal_page()). */ -- cgit v1.2.3 From 13c9aaf7fa01cc7600c61981609feadeef3354ec Mon Sep 17 00:00:00 2001 From: Janne Huttunen Date: Fri, 16 Nov 2018 15:08:32 -0800 Subject: mm/vmstat.c: fix NUMA statistics updates Scan through the whole array to see if an update is needed. While we're at it, use sizeof() to be safe against any possible type changes in the future. The bug here is that we wouldn't sync per-cpu counters into global ones if there was an update of numa_stats for higher cpus. Highly theoretical one though because it is much more probable that zone_stats are updated so we would refresh anyway. So I wouldn't bother to mark this for stable, yet something nice to fix. [mhocko@suse.com: changelog enhancement] Link: http://lkml.kernel.org/r/1541601517-17282-1-git-send-email-janne.huttunen@nokia.com Fixes: 1d90ca897cb0 ("mm: update NUMA counter threshold size") Signed-off-by: Janne Huttunen Acked-by: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/vmstat.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'mm') diff --git a/mm/vmstat.c b/mm/vmstat.c index 6038ce593ce3..9c624595e904 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -1827,12 +1827,13 @@ static bool need_update(int cpu) /* * The fast way of checking if there are any vmstat diffs. - * This works because the diffs are byte sized items. */ - if (memchr_inv(p->vm_stat_diff, 0, NR_VM_ZONE_STAT_ITEMS)) + if (memchr_inv(p->vm_stat_diff, 0, NR_VM_ZONE_STAT_ITEMS * + sizeof(p->vm_stat_diff[0]))) return true; #ifdef CONFIG_NUMA - if (memchr_inv(p->vm_numa_stat_diff, 0, NR_VM_NUMA_STAT_ITEMS)) + if (memchr_inv(p->vm_numa_stat_diff, 0, NR_VM_NUMA_STAT_ITEMS * + sizeof(p->vm_numa_stat_diff[0]))) return true; #endif } -- cgit v1.2.3 From 1a413646931cb14442065cfc17561e50f5b5bb44 Mon Sep 17 00:00:00 2001 From: Yufen Yu Date: Fri, 16 Nov 2018 15:08:39 -0800 Subject: tmpfs: make lseek(SEEK_DATA/SEK_HOLE) return ENXIO with a negative offset Other filesystems such as ext4, f2fs and ubifs all return ENXIO when lseek (SEEK_DATA or SEEK_HOLE) requests a negative offset. man 2 lseek says : EINVAL whence is not valid. Or: the resulting file offset would be : negative, or beyond the end of a seekable device. : : ENXIO whence is SEEK_DATA or SEEK_HOLE, and the file offset is beyond : the end of the file. Make tmpfs return ENXIO under these circumstances as well. After this, tmpfs also passes xfstests's generic/448. [akpm@linux-foundation.org: rewrite changelog] Link: http://lkml.kernel.org/r/1540434176-14349-1-git-send-email-yuyufen@huawei.com Signed-off-by: Yufen Yu Reviewed-by: Andrew Morton Cc: Al Viro Cc: Hugh Dickins Cc: William Kucharski Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/shmem.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'mm') diff --git a/mm/shmem.c b/mm/shmem.c index ea26d7a0342d..d44991ea5ed4 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -2563,9 +2563,7 @@ static loff_t shmem_file_llseek(struct file *file, loff_t offset, int whence) inode_lock(inode); /* We're holding i_mutex so we can access i_size directly */ - if (offset < 0) - offset = -EINVAL; - else if (offset >= inode->i_size) + if (offset < 0 || offset >= inode->i_size) offset = -ENXIO; else { start = offset >> PAGE_SHIFT; -- cgit v1.2.3 From c63ae43ba53bc432b414fd73dd5f4b01fcb1ab43 Mon Sep 17 00:00:00 2001 From: Michal Hocko Date: Fri, 16 Nov 2018 15:08:53 -0800 Subject: mm, page_alloc: check for max order in hot path Konstantin has noticed that kvmalloc might trigger the following warning: WARNING: CPU: 0 PID: 6676 at mm/vmstat.c:986 __fragmentation_index+0x54/0x60 [...] Call Trace: fragmentation_index+0x76/0x90 compaction_suitable+0x4f/0xf0 shrink_node+0x295/0x310 node_reclaim+0x205/0x250 get_page_from_freelist+0x649/0xad0 __alloc_pages_nodemask+0x12a/0x2a0 kmalloc_large_node+0x47/0x90 __kmalloc_node+0x22b/0x2e0 kvmalloc_node+0x3e/0x70 xt_alloc_table_info+0x3a/0x80 [x_tables] do_ip6t_set_ctl+0xcd/0x1c0 [ip6_tables] nf_setsockopt+0x44/0x60 SyS_setsockopt+0x6f/0xc0 do_syscall_64+0x67/0x120 entry_SYSCALL_64_after_hwframe+0x3d/0xa2 the problem is that we only check for an out of bound order in the slow path and the node reclaim might happen from the fast path already. This is fixable by making sure that kvmalloc doesn't ever use kmalloc for requests that are larger than KMALLOC_MAX_SIZE but this also shows that the code is rather fragile. A recent UBSAN report just underlines that by the following report UBSAN: Undefined behaviour in mm/page_alloc.c:3117:19 shift exponent 51 is too large for 32-bit type 'int' CPU: 0 PID: 6520 Comm: syz-executor1 Not tainted 4.19.0-rc2 #1 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Bochs 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0xd2/0x148 lib/dump_stack.c:113 ubsan_epilogue+0x12/0x94 lib/ubsan.c:159 __ubsan_handle_shift_out_of_bounds+0x2b6/0x30b lib/ubsan.c:425 __zone_watermark_ok+0x2c7/0x400 mm/page_alloc.c:3117 zone_watermark_fast mm/page_alloc.c:3216 [inline] get_page_from_freelist+0xc49/0x44c0 mm/page_alloc.c:3300 __alloc_pages_nodemask+0x21e/0x640 mm/page_alloc.c:4370 alloc_pages_current+0xcc/0x210 mm/mempolicy.c:2093 alloc_pages include/linux/gfp.h:509 [inline] __get_free_pages+0x12/0x60 mm/page_alloc.c:4414 dma_mem_alloc+0x36/0x50 arch/x86/include/asm/floppy.h:156 raw_cmd_copyin drivers/block/floppy.c:3159 [inline] raw_cmd_ioctl drivers/block/floppy.c:3206 [inline] fd_locked_ioctl+0xa00/0x2c10 drivers/block/floppy.c:3544 fd_ioctl+0x40/0x60 drivers/block/floppy.c:3571 __blkdev_driver_ioctl block/ioctl.c:303 [inline] blkdev_ioctl+0xb3c/0x1a30 block/ioctl.c:601 block_ioctl+0x105/0x150 fs/block_dev.c:1883 vfs_ioctl fs/ioctl.c:46 [inline] do_vfs_ioctl+0x1c0/0x1150 fs/ioctl.c:687 ksys_ioctl+0x9e/0xb0 fs/ioctl.c:702 __do_sys_ioctl fs/ioctl.c:709 [inline] __se_sys_ioctl fs/ioctl.c:707 [inline] __x64_sys_ioctl+0x7e/0xc0 fs/ioctl.c:707 do_syscall_64+0xc4/0x510 arch/x86/entry/common.c:290 entry_SYSCALL_64_after_hwframe+0x49/0xbe Note that this is not a kvmalloc path. It is just that the fast path really depends on having sanitzed order as well. Therefore move the order check to the fast path. Link: http://lkml.kernel.org/r/20181113094305.GM15120@dhcp22.suse.cz Signed-off-by: Michal Hocko Reported-by: Konstantin Khlebnikov Reported-by: Kyungtae Kim Acked-by: Vlastimil Babka Cc: Balbir Singh Cc: Mel Gorman Cc: Pavel Tatashin Cc: Oscar Salvador Cc: Mike Rapoport Cc: Aaron Lu Cc: Joonsoo Kim Cc: Byoungyoung Lee Cc: "Dae R. Jeong" Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/page_alloc.c | 20 +++++++++----------- 1 file changed, 9 insertions(+), 11 deletions(-) (limited to 'mm') diff --git a/mm/page_alloc.c b/mm/page_alloc.c index a0e5ec0addd2..6847177dc4a1 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -4060,17 +4060,6 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order, unsigned int cpuset_mems_cookie; int reserve_flags; - /* - * In the slowpath, we sanity check order to avoid ever trying to - * reclaim >= MAX_ORDER areas which will never succeed. Callers may - * be using allocators in order of preference for an area that is - * too large. - */ - if (order >= MAX_ORDER) { - WARN_ON_ONCE(!(gfp_mask & __GFP_NOWARN)); - return NULL; - } - /* * We also sanity check to catch abuse of atomic reserves being used by * callers that are not in atomic context. @@ -4364,6 +4353,15 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order, int preferred_nid, gfp_t alloc_mask; /* The gfp_t that was actually used for allocation */ struct alloc_context ac = { }; + /* + * There are several places where we assume that the order value is sane + * so bail out early if the request is out of bound. + */ + if (unlikely(order >= MAX_ORDER)) { + WARN_ON_ONCE(!(gfp_mask & __GFP_NOWARN)); + return NULL; + } + gfp_mask &= gfp_allowed_mask; alloc_mask = gfp_mask; if (!prepare_alloc_pages(gfp_mask, order, preferred_nid, nodemask, &ac, &alloc_mask, &alloc_flags)) -- cgit v1.2.3 From 45e79815b89149dc6698e71b587c86ffaf4062aa Mon Sep 17 00:00:00 2001 From: Chen Chang Date: Fri, 16 Nov 2018 15:08:57 -0800 Subject: mm/memblock.c: fix a typo in __next_mem_pfn_range() comments Link: http://lkml.kernel.org/r/20181107100247.13359-1-rainccrun@gmail.com Signed-off-by: Chen Chang Acked-by: Michal Hocko Acked-by: Mike Rapoport Reviewed-by: Andrew Morton Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- mm/memblock.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'mm') diff --git a/mm/memblock.c b/mm/memblock.c index 7df468c8ebc8..9a2d5ae81ae1 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -1179,7 +1179,7 @@ void __init_memblock __next_mem_range_rev(u64 *idx, int nid, #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP /* - * Common iterator interface used to define for_each_mem_range(). + * Common iterator interface used to define for_each_mem_pfn_range(). */ void __init_memblock __next_mem_pfn_range(int *idx, int nid, unsigned long *out_start_pfn, -- cgit v1.2.3