From 60115fa54ad7b913b7cb5844e6b7ffeb842d55f2 Mon Sep 17 00:00:00 2001 From: Kefeng Wang <wangkefeng.wang@huawei.com> Date: Fri, 14 Jan 2022 14:04:11 -0800 Subject: mm: defer kmemleak object creation of module_alloc() Yongqiang reports a kmemleak panic when module insmod/rmmod with KASAN enabled(without KASAN_VMALLOC) on x86[1]. When the module area allocates memory, it's kmemleak_object is created successfully, but the KASAN shadow memory of module allocation is not ready, so when kmemleak scan the module's pointer, it will panic due to no shadow memory with KASAN check. module_alloc __vmalloc_node_range kmemleak_vmalloc kmemleak_scan update_checksum kasan_module_alloc kmemleak_ignore Note, there is no problem if KASAN_VMALLOC enabled, the modules area entire shadow memory is preallocated. Thus, the bug only exits on ARCH which supports dynamic allocation of module area per module load, for now, only x86/arm64/s390 are involved. Add a VM_DEFER_KMEMLEAK flags, defer vmalloc'ed object register of kmemleak in module_alloc() to fix this issue. [1] https://lore.kernel.org/all/6d41e2b9-4692-5ec4-b1cd-cbe29ae89739@huawei.com/ [wangkefeng.wang@huawei.com: fix build] Link: https://lkml.kernel.org/r/20211125080307.27225-1-wangkefeng.wang@huawei.com [akpm@linux-foundation.org: simplify ifdefs, per Andrey] Link: https://lkml.kernel.org/r/CA+fCnZcnwJHUQq34VuRxpdoY6_XbJCDJ-jopksS5Eia4PijPzw@mail.gmail.com Link: https://lkml.kernel.org/r/20211124142034.192078-1-wangkefeng.wang@huawei.com Fixes: 793213a82de4 ("s390/kasan: dynamic shadow mem allocation for modules") Fixes: 39d114ddc682 ("arm64: add KASAN support") Fixes: bebf56a1b176 ("kasan: enable instrumentation of global variables") Signed-off-by: Kefeng Wang <wangkefeng.wang@huawei.com> Reported-by: Yongqiang Liu <liuyongqiang13@huawei.com> Cc: Andrey Konovalov <andreyknvl@gmail.com> Cc: Andrey Ryabinin <ryabinin.a.a@gmail.com> Cc: Dmitry Vyukov <dvyukov@google.com> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Will Deacon <will@kernel.org> Cc: Heiko Carstens <hca@linux.ibm.com> Cc: Vasily Gorbik <gor@linux.ibm.com> Cc: Christian Borntraeger <borntraeger@linux.ibm.com> Cc: Alexander Gordeev <agordeev@linux.ibm.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@redhat.com> Cc: Borislav Petkov <bp@alien8.de> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: Alexander Potapenko <glider@google.com> Cc: Kefeng Wang <wangkefeng.wang@huawei.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> --- arch/x86/kernel/module.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c index 169fb6f4cd2e..95fa745e310a 100644 --- a/arch/x86/kernel/module.c +++ b/arch/x86/kernel/module.c @@ -67,6 +67,7 @@ static unsigned long int get_module_load_offset(void) void *module_alloc(unsigned long size) { + gfp_t gfp_mask = GFP_KERNEL; void *p; if (PAGE_ALIGN(size) > MODULES_LEN) @@ -74,10 +75,10 @@ void *module_alloc(unsigned long size) p = __vmalloc_node_range(size, MODULE_ALIGN, MODULES_VADDR + get_module_load_offset(), - MODULES_END, GFP_KERNEL, - PAGE_KERNEL, 0, NUMA_NO_NODE, + MODULES_END, gfp_mask, + PAGE_KERNEL, VM_DEFER_KMEMLEAK, NUMA_NO_NODE, __builtin_return_address(0)); - if (p && (kasan_module_alloc(p, size) < 0)) { + if (p && (kasan_module_alloc(p, size, gfp_mask) < 0)) { vfree(p); return NULL; } -- cgit v1.2.3 From 36ef159f4408b08eae7f2af6d62bedd3f4343758 Mon Sep 17 00:00:00 2001 From: Qi Zheng <zhengqi.arch@bytedance.com> Date: Fri, 14 Jan 2022 14:05:51 -0800 Subject: mm: remove redundant check about FAULT_FLAG_ALLOW_RETRY bit Since commit 4064b9827063 ("mm: allow VM_FAULT_RETRY for multiple times") allowed VM_FAULT_RETRY for multiple times, the FAULT_FLAG_ALLOW_RETRY bit of fault_flag will not be changed in the page fault path, so the following check is no longer needed: flags & FAULT_FLAG_ALLOW_RETRY So just remove it. [akpm@linux-foundation.org: coding style fixes] Link: https://lkml.kernel.org/r/20211110123358.36511-1-zhengqi.arch@bytedance.com Signed-off-by: Qi Zheng <zhengqi.arch@bytedance.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: David Hildenbrand <david@redhat.com> Cc: Kirill Shutemov <kirill@shutemov.name> Cc: Peter Xu <peterx@redhat.com> Cc: Muchun Song <songmuchun@bytedance.com> Cc: Chengming Zhou <zhouchengming@bytedance.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> --- arch/alpha/mm/fault.c | 16 +++++++--------- arch/arc/mm/fault.c | 3 +-- arch/arm/mm/fault.c | 2 +- arch/arm64/mm/fault.c | 6 ++---- arch/hexagon/mm/vm_fault.c | 8 +++----- arch/ia64/mm/fault.c | 16 +++++++--------- arch/m68k/mm/fault.c | 22 ++++++++++------------ arch/microblaze/mm/fault.c | 22 ++++++++++------------ arch/mips/mm/fault.c | 19 +++++++++---------- arch/nds32/mm/fault.c | 18 ++++++++---------- arch/nios2/mm/fault.c | 18 ++++++++---------- arch/openrisc/mm/fault.c | 18 ++++++++---------- arch/parisc/mm/fault.c | 18 ++++++++---------- arch/powerpc/mm/fault.c | 6 ++---- arch/riscv/mm/fault.c | 2 +- arch/s390/mm/fault.c | 28 ++++++++++++++-------------- arch/sh/mm/fault.c | 20 +++++++++----------- arch/sparc/mm/fault_32.c | 16 +++++++--------- arch/sparc/mm/fault_64.c | 16 +++++++--------- arch/um/kernel/trap.c | 8 +++----- arch/x86/mm/fault.c | 3 +-- arch/xtensa/mm/fault.c | 17 ++++++++--------- 22 files changed, 134 insertions(+), 168 deletions(-) (limited to 'arch/x86') diff --git a/arch/alpha/mm/fault.c b/arch/alpha/mm/fault.c index eee5102c3d88..6c0a277388dd 100644 --- a/arch/alpha/mm/fault.c +++ b/arch/alpha/mm/fault.c @@ -165,17 +165,15 @@ retry: BUG(); } - if (flags & FAULT_FLAG_ALLOW_RETRY) { - if (fault & VM_FAULT_RETRY) { - flags |= FAULT_FLAG_TRIED; + if (fault & VM_FAULT_RETRY) { + flags |= FAULT_FLAG_TRIED; - /* No need to mmap_read_unlock(mm) as we would - * have already released it in __lock_page_or_retry - * in mm/filemap.c. - */ + /* No need to mmap_read_unlock(mm) as we would + * have already released it in __lock_page_or_retry + * in mm/filemap.c. + */ - goto retry; - } + goto retry; } mmap_read_unlock(mm); diff --git a/arch/arc/mm/fault.c b/arch/arc/mm/fault.c index 5787c261c9a4..dad27e4d69ff 100644 --- a/arch/arc/mm/fault.c +++ b/arch/arc/mm/fault.c @@ -149,8 +149,7 @@ retry: /* * Fault retry nuances, mmap_lock already relinquished by core mm */ - if (unlikely((fault & VM_FAULT_RETRY) && - (flags & FAULT_FLAG_ALLOW_RETRY))) { + if (unlikely(fault & VM_FAULT_RETRY)) { flags |= FAULT_FLAG_TRIED; goto retry; } diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c index bc8779d54a64..c7326a521a69 100644 --- a/arch/arm/mm/fault.c +++ b/arch/arm/mm/fault.c @@ -312,7 +312,7 @@ retry: return 0; } - if (!(fault & VM_FAULT_ERROR) && flags & FAULT_FLAG_ALLOW_RETRY) { + if (!(fault & VM_FAULT_ERROR)) { if (fault & VM_FAULT_RETRY) { flags |= FAULT_FLAG_TRIED; goto retry; diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c index 9ae24e3b72be..a8fb54fccde0 100644 --- a/arch/arm64/mm/fault.c +++ b/arch/arm64/mm/fault.c @@ -606,10 +606,8 @@ retry: } if (fault & VM_FAULT_RETRY) { - if (mm_flags & FAULT_FLAG_ALLOW_RETRY) { - mm_flags |= FAULT_FLAG_TRIED; - goto retry; - } + mm_flags |= FAULT_FLAG_TRIED; + goto retry; } mmap_read_unlock(mm); diff --git a/arch/hexagon/mm/vm_fault.c b/arch/hexagon/mm/vm_fault.c index ef32c5a84ff3..4fac4b9eb316 100644 --- a/arch/hexagon/mm/vm_fault.c +++ b/arch/hexagon/mm/vm_fault.c @@ -98,11 +98,9 @@ good_area: /* The most common case -- we are done. */ if (likely(!(fault & VM_FAULT_ERROR))) { - if (flags & FAULT_FLAG_ALLOW_RETRY) { - if (fault & VM_FAULT_RETRY) { - flags |= FAULT_FLAG_TRIED; - goto retry; - } + if (fault & VM_FAULT_RETRY) { + flags |= FAULT_FLAG_TRIED; + goto retry; } mmap_read_unlock(mm); diff --git a/arch/ia64/mm/fault.c b/arch/ia64/mm/fault.c index 02de2e70c587..32417f49ad2f 100644 --- a/arch/ia64/mm/fault.c +++ b/arch/ia64/mm/fault.c @@ -156,17 +156,15 @@ retry: BUG(); } - if (flags & FAULT_FLAG_ALLOW_RETRY) { - if (fault & VM_FAULT_RETRY) { - flags |= FAULT_FLAG_TRIED; + if (fault & VM_FAULT_RETRY) { + flags |= FAULT_FLAG_TRIED; - /* No need to mmap_read_unlock(mm) as we would - * have already released it in __lock_page_or_retry - * in mm/filemap.c. - */ + /* No need to mmap_read_unlock(mm) as we would + * have already released it in __lock_page_or_retry + * in mm/filemap.c. + */ - goto retry; - } + goto retry; } mmap_read_unlock(mm); diff --git a/arch/m68k/mm/fault.c b/arch/m68k/mm/fault.c index ef46e77e97a5..53cfb9bc1066 100644 --- a/arch/m68k/mm/fault.c +++ b/arch/m68k/mm/fault.c @@ -153,18 +153,16 @@ good_area: BUG(); } - if (flags & FAULT_FLAG_ALLOW_RETRY) { - if (fault & VM_FAULT_RETRY) { - flags |= FAULT_FLAG_TRIED; - - /* - * No need to mmap_read_unlock(mm) as we would - * have already released it in __lock_page_or_retry - * in mm/filemap.c. - */ - - goto retry; - } + if (fault & VM_FAULT_RETRY) { + flags |= FAULT_FLAG_TRIED; + + /* + * No need to mmap_read_unlock(mm) as we would + * have already released it in __lock_page_or_retry + * in mm/filemap.c. + */ + + goto retry; } mmap_read_unlock(mm); diff --git a/arch/microblaze/mm/fault.c b/arch/microblaze/mm/fault.c index b3fed2cecf84..a9626e6a68af 100644 --- a/arch/microblaze/mm/fault.c +++ b/arch/microblaze/mm/fault.c @@ -232,18 +232,16 @@ good_area: BUG(); } - if (flags & FAULT_FLAG_ALLOW_RETRY) { - if (fault & VM_FAULT_RETRY) { - flags |= FAULT_FLAG_TRIED; - - /* - * No need to mmap_read_unlock(mm) as we would - * have already released it in __lock_page_or_retry - * in mm/filemap.c. - */ - - goto retry; - } + if (fault & VM_FAULT_RETRY) { + flags |= FAULT_FLAG_TRIED; + + /* + * No need to mmap_read_unlock(mm) as we would + * have already released it in __lock_page_or_retry + * in mm/filemap.c. + */ + + goto retry; } mmap_read_unlock(mm); diff --git a/arch/mips/mm/fault.c b/arch/mips/mm/fault.c index e7abda9c013f..44f98100e84e 100644 --- a/arch/mips/mm/fault.c +++ b/arch/mips/mm/fault.c @@ -171,18 +171,17 @@ good_area: goto do_sigbus; BUG(); } - if (flags & FAULT_FLAG_ALLOW_RETRY) { - if (fault & VM_FAULT_RETRY) { - flags |= FAULT_FLAG_TRIED; - /* - * No need to mmap_read_unlock(mm) as we would - * have already released it in __lock_page_or_retry - * in mm/filemap.c. - */ + if (fault & VM_FAULT_RETRY) { + flags |= FAULT_FLAG_TRIED; - goto retry; - } + /* + * No need to mmap_read_unlock(mm) as we would + * have already released it in __lock_page_or_retry + * in mm/filemap.c. + */ + + goto retry; } mmap_read_unlock(mm); diff --git a/arch/nds32/mm/fault.c b/arch/nds32/mm/fault.c index 1d139b117168..636977a1c8b9 100644 --- a/arch/nds32/mm/fault.c +++ b/arch/nds32/mm/fault.c @@ -230,16 +230,14 @@ good_area: goto bad_area; } - if (flags & FAULT_FLAG_ALLOW_RETRY) { - if (fault & VM_FAULT_RETRY) { - flags |= FAULT_FLAG_TRIED; - - /* No need to mmap_read_unlock(mm) as we would - * have already released it in __lock_page_or_retry - * in mm/filemap.c. - */ - goto retry; - } + if (fault & VM_FAULT_RETRY) { + flags |= FAULT_FLAG_TRIED; + + /* No need to mmap_read_unlock(mm) as we would + * have already released it in __lock_page_or_retry + * in mm/filemap.c. + */ + goto retry; } mmap_read_unlock(mm); diff --git a/arch/nios2/mm/fault.c b/arch/nios2/mm/fault.c index 9476feecf512..a32f14cd72f2 100644 --- a/arch/nios2/mm/fault.c +++ b/arch/nios2/mm/fault.c @@ -149,18 +149,16 @@ good_area: BUG(); } - if (flags & FAULT_FLAG_ALLOW_RETRY) { - if (fault & VM_FAULT_RETRY) { - flags |= FAULT_FLAG_TRIED; + if (fault & VM_FAULT_RETRY) { + flags |= FAULT_FLAG_TRIED; - /* - * No need to mmap_read_unlock(mm) as we would - * have already released it in __lock_page_or_retry - * in mm/filemap.c. - */ + /* + * No need to mmap_read_unlock(mm) as we would + * have already released it in __lock_page_or_retry + * in mm/filemap.c. + */ - goto retry; - } + goto retry; } mmap_read_unlock(mm); diff --git a/arch/openrisc/mm/fault.c b/arch/openrisc/mm/fault.c index f0fa6394a58e..80bb66ad42f6 100644 --- a/arch/openrisc/mm/fault.c +++ b/arch/openrisc/mm/fault.c @@ -177,18 +177,16 @@ good_area: BUG(); } - if (flags & FAULT_FLAG_ALLOW_RETRY) { - /*RGD modeled on Cris */ - if (fault & VM_FAULT_RETRY) { - flags |= FAULT_FLAG_TRIED; + /*RGD modeled on Cris */ + if (fault & VM_FAULT_RETRY) { + flags |= FAULT_FLAG_TRIED; - /* No need to mmap_read_unlock(mm) as we would - * have already released it in __lock_page_or_retry - * in mm/filemap.c. - */ + /* No need to mmap_read_unlock(mm) as we would + * have already released it in __lock_page_or_retry + * in mm/filemap.c. + */ - goto retry; - } + goto retry; } mmap_read_unlock(mm); diff --git a/arch/parisc/mm/fault.c b/arch/parisc/mm/fault.c index 4a6221b869fd..360b627645cc 100644 --- a/arch/parisc/mm/fault.c +++ b/arch/parisc/mm/fault.c @@ -324,16 +324,14 @@ good_area: goto bad_area; BUG(); } - if (flags & FAULT_FLAG_ALLOW_RETRY) { - if (fault & VM_FAULT_RETRY) { - /* - * No need to mmap_read_unlock(mm) as we would - * have already released it in __lock_page_or_retry - * in mm/filemap.c. - */ - flags |= FAULT_FLAG_TRIED; - goto retry; - } + if (fault & VM_FAULT_RETRY) { + /* + * No need to mmap_read_unlock(mm) as we would + * have already released it in __lock_page_or_retry + * in mm/filemap.c. + */ + flags |= FAULT_FLAG_TRIED; + goto retry; } mmap_read_unlock(mm); return; diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c index a8d0ce85d39a..ebcc61e47d62 100644 --- a/arch/powerpc/mm/fault.c +++ b/arch/powerpc/mm/fault.c @@ -516,10 +516,8 @@ retry: * case. */ if (unlikely(fault & VM_FAULT_RETRY)) { - if (flags & FAULT_FLAG_ALLOW_RETRY) { - flags |= FAULT_FLAG_TRIED; - goto retry; - } + flags |= FAULT_FLAG_TRIED; + goto retry; } mmap_read_unlock(current->mm); diff --git a/arch/riscv/mm/fault.c b/arch/riscv/mm/fault.c index aa08dd2f8fae..cae4b6363607 100644 --- a/arch/riscv/mm/fault.c +++ b/arch/riscv/mm/fault.c @@ -330,7 +330,7 @@ good_area: if (fault_signal_pending(fault, regs)) return; - if (unlikely((fault & VM_FAULT_RETRY) && (flags & FAULT_FLAG_ALLOW_RETRY))) { + if (unlikely(fault & VM_FAULT_RETRY)) { flags |= FAULT_FLAG_TRIED; /* diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c index d30f5986fa85..d7d6be283d94 100644 --- a/arch/s390/mm/fault.c +++ b/arch/s390/mm/fault.c @@ -452,21 +452,21 @@ retry: if (unlikely(fault & VM_FAULT_ERROR)) goto out_up; - if (flags & FAULT_FLAG_ALLOW_RETRY) { - if (fault & VM_FAULT_RETRY) { - if (IS_ENABLED(CONFIG_PGSTE) && gmap && - (flags & FAULT_FLAG_RETRY_NOWAIT)) { - /* FAULT_FLAG_RETRY_NOWAIT has been set, - * mmap_lock has not been released */ - current->thread.gmap_pfault = 1; - fault = VM_FAULT_PFAULT; - goto out_up; - } - flags &= ~FAULT_FLAG_RETRY_NOWAIT; - flags |= FAULT_FLAG_TRIED; - mmap_read_lock(mm); - goto retry; + if (fault & VM_FAULT_RETRY) { + if (IS_ENABLED(CONFIG_PGSTE) && gmap && + (flags & FAULT_FLAG_RETRY_NOWAIT)) { + /* + * FAULT_FLAG_RETRY_NOWAIT has been set, mmap_lock has + * not been released + */ + current->thread.gmap_pfault = 1; + fault = VM_FAULT_PFAULT; + goto out_up; } + flags &= ~FAULT_FLAG_RETRY_NOWAIT; + flags |= FAULT_FLAG_TRIED; + mmap_read_lock(mm); + goto retry; } if (IS_ENABLED(CONFIG_PGSTE) && gmap) { address = __gmap_link(gmap, current->thread.gmap_addr, diff --git a/arch/sh/mm/fault.c b/arch/sh/mm/fault.c index 1e1aa75df3ca..e175667b1363 100644 --- a/arch/sh/mm/fault.c +++ b/arch/sh/mm/fault.c @@ -485,17 +485,15 @@ good_area: if (mm_fault_error(regs, error_code, address, fault)) return; - if (flags & FAULT_FLAG_ALLOW_RETRY) { - if (fault & VM_FAULT_RETRY) { - flags |= FAULT_FLAG_TRIED; - - /* - * No need to mmap_read_unlock(mm) as we would - * have already released it in __lock_page_or_retry - * in mm/filemap.c. - */ - goto retry; - } + if (fault & VM_FAULT_RETRY) { + flags |= FAULT_FLAG_TRIED; + + /* + * No need to mmap_read_unlock(mm) as we would + * have already released it in __lock_page_or_retry + * in mm/filemap.c. + */ + goto retry; } mmap_read_unlock(mm); diff --git a/arch/sparc/mm/fault_32.c b/arch/sparc/mm/fault_32.c index 90dc4ae315c8..ad569d9bd124 100644 --- a/arch/sparc/mm/fault_32.c +++ b/arch/sparc/mm/fault_32.c @@ -200,17 +200,15 @@ good_area: BUG(); } - if (flags & FAULT_FLAG_ALLOW_RETRY) { - if (fault & VM_FAULT_RETRY) { - flags |= FAULT_FLAG_TRIED; + if (fault & VM_FAULT_RETRY) { + flags |= FAULT_FLAG_TRIED; - /* No need to mmap_read_unlock(mm) as we would - * have already released it in __lock_page_or_retry - * in mm/filemap.c. - */ + /* No need to mmap_read_unlock(mm) as we would + * have already released it in __lock_page_or_retry + * in mm/filemap.c. + */ - goto retry; - } + goto retry; } mmap_read_unlock(mm); diff --git a/arch/sparc/mm/fault_64.c b/arch/sparc/mm/fault_64.c index 9a9652a15fed..253e07043298 100644 --- a/arch/sparc/mm/fault_64.c +++ b/arch/sparc/mm/fault_64.c @@ -437,17 +437,15 @@ good_area: BUG(); } - if (flags & FAULT_FLAG_ALLOW_RETRY) { - if (fault & VM_FAULT_RETRY) { - flags |= FAULT_FLAG_TRIED; + if (fault & VM_FAULT_RETRY) { + flags |= FAULT_FLAG_TRIED; - /* No need to mmap_read_unlock(mm) as we would - * have already released it in __lock_page_or_retry - * in mm/filemap.c. - */ + /* No need to mmap_read_unlock(mm) as we would + * have already released it in __lock_page_or_retry + * in mm/filemap.c. + */ - goto retry; - } + goto retry; } mmap_read_unlock(mm); diff --git a/arch/um/kernel/trap.c b/arch/um/kernel/trap.c index c32efb09db21..193503484af5 100644 --- a/arch/um/kernel/trap.c +++ b/arch/um/kernel/trap.c @@ -87,12 +87,10 @@ good_area: } BUG(); } - if (flags & FAULT_FLAG_ALLOW_RETRY) { - if (fault & VM_FAULT_RETRY) { - flags |= FAULT_FLAG_TRIED; + if (fault & VM_FAULT_RETRY) { + flags |= FAULT_FLAG_TRIED; - goto retry; - } + goto retry; } pmd = pmd_off(mm, address); diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index 4bfed53e210e..d0074c6ed31a 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -1413,8 +1413,7 @@ good_area: * and if there is a fatal signal pending there is no guarantee * that we made any progress. Handle this case first. */ - if (unlikely((fault & VM_FAULT_RETRY) && - (flags & FAULT_FLAG_ALLOW_RETRY))) { + if (unlikely(fault & VM_FAULT_RETRY)) { flags |= FAULT_FLAG_TRIED; goto retry; } diff --git a/arch/xtensa/mm/fault.c b/arch/xtensa/mm/fault.c index fd6a70635962..06d0973a0d74 100644 --- a/arch/xtensa/mm/fault.c +++ b/arch/xtensa/mm/fault.c @@ -127,17 +127,16 @@ good_area: goto do_sigbus; BUG(); } - if (flags & FAULT_FLAG_ALLOW_RETRY) { - if (fault & VM_FAULT_RETRY) { - flags |= FAULT_FLAG_TRIED; - /* No need to mmap_read_unlock(mm) as we would - * have already released it in __lock_page_or_retry - * in mm/filemap.c. - */ + if (fault & VM_FAULT_RETRY) { + flags |= FAULT_FLAG_TRIED; - goto retry; - } + /* No need to mmap_read_unlock(mm) as we would + * have already released it in __lock_page_or_retry + * in mm/filemap.c. + */ + + goto retry; } mmap_read_unlock(mm); -- cgit v1.2.3 From 36090def7bad06a6346f86a7cfdbfda2d138cb64 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann <arnd@arndb.de> Date: Fri, 14 Jan 2022 14:06:10 -0800 Subject: mm: move tlb_flush_pending inline helpers to mm_inline.h linux/mm_types.h should only define structure definitions, to make it cheap to include elsewhere. The atomic_t helper function definitions are particularly large, so it's better to move the helpers using those into the existing linux/mm_inline.h and only include that where needed. As a follow-up, we may want to go through all the indirect includes in mm_types.h and reduce them as much as possible. Link: https://lkml.kernel.org/r/20211207125710.2503446-2-arnd@kernel.org Signed-off-by: Arnd Bergmann <arnd@arndb.de> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Stephen Rothwell <sfr@canb.auug.org.au> Cc: Suren Baghdasaryan <surenb@google.com> Cc: Colin Cross <ccross@google.com> Cc: Kees Cook <keescook@chromium.org> Cc: Peter Xu <peterx@redhat.com> Cc: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Yu Zhao <yuzhao@google.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Eric Biederman <ebiederm@xmission.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> --- arch/x86/include/asm/pgtable.h | 2 +- include/linux/mm.h | 45 -------------- include/linux/mm_inline.h | 86 +++++++++++++++++++++++++++ include/linux/mm_types.h | 129 ++++++++++++++--------------------------- mm/ksm.c | 1 + mm/mapping_dirty_helpers.c | 1 + mm/memory.c | 1 + mm/mmu_gather.c | 1 + mm/pgtable-generic.c | 1 + 9 files changed, 137 insertions(+), 130 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index 448cd01eb3ec..5196958aa6ac 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -752,7 +752,7 @@ static inline bool pte_accessible(struct mm_struct *mm, pte_t a) return true; if ((pte_flags(a) & _PAGE_PROTNONE) && - mm_tlb_flush_pending(mm)) + atomic_read(&mm->tlb_flush_pending)) return true; return false; diff --git a/include/linux/mm.h b/include/linux/mm.h index 7000442984b9..c17e5cfc1e47 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -424,51 +424,6 @@ extern unsigned int kobjsize(const void *objp); */ extern pgprot_t protection_map[16]; -/** - * enum fault_flag - Fault flag definitions. - * @FAULT_FLAG_WRITE: Fault was a write fault. - * @FAULT_FLAG_MKWRITE: Fault was mkwrite of existing PTE. - * @FAULT_FLAG_ALLOW_RETRY: Allow to retry the fault if blocked. - * @FAULT_FLAG_RETRY_NOWAIT: Don't drop mmap_lock and wait when retrying. - * @FAULT_FLAG_KILLABLE: The fault task is in SIGKILL killable region. - * @FAULT_FLAG_TRIED: The fault has been tried once. - * @FAULT_FLAG_USER: The fault originated in userspace. - * @FAULT_FLAG_REMOTE: The fault is not for current task/mm. - * @FAULT_FLAG_INSTRUCTION: The fault was during an instruction fetch. - * @FAULT_FLAG_INTERRUPTIBLE: The fault can be interrupted by non-fatal signals. - * - * About @FAULT_FLAG_ALLOW_RETRY and @FAULT_FLAG_TRIED: we can specify - * whether we would allow page faults to retry by specifying these two - * fault flags correctly. Currently there can be three legal combinations: - * - * (a) ALLOW_RETRY and !TRIED: this means the page fault allows retry, and - * this is the first try - * - * (b) ALLOW_RETRY and TRIED: this means the page fault allows retry, and - * we've already tried at least once - * - * (c) !ALLOW_RETRY and !TRIED: this means the page fault does not allow retry - * - * The unlisted combination (!ALLOW_RETRY && TRIED) is illegal and should never - * be used. Note that page faults can be allowed to retry for multiple times, - * in which case we'll have an initial fault with flags (a) then later on - * continuous faults with flags (b). We should always try to detect pending - * signals before a retry to make sure the continuous page faults can still be - * interrupted if necessary. - */ -enum fault_flag { - FAULT_FLAG_WRITE = 1 << 0, - FAULT_FLAG_MKWRITE = 1 << 1, - FAULT_FLAG_ALLOW_RETRY = 1 << 2, - FAULT_FLAG_RETRY_NOWAIT = 1 << 3, - FAULT_FLAG_KILLABLE = 1 << 4, - FAULT_FLAG_TRIED = 1 << 5, - FAULT_FLAG_USER = 1 << 6, - FAULT_FLAG_REMOTE = 1 << 7, - FAULT_FLAG_INSTRUCTION = 1 << 8, - FAULT_FLAG_INTERRUPTIBLE = 1 << 9, -}; - /* * The default fault flags that should be used by most of the * arch-specific page fault handlers. diff --git a/include/linux/mm_inline.h b/include/linux/mm_inline.h index 47d96d2647ca..b725839dfe71 100644 --- a/include/linux/mm_inline.h +++ b/include/linux/mm_inline.h @@ -2,6 +2,7 @@ #ifndef LINUX_MM_INLINE_H #define LINUX_MM_INLINE_H +#include <linux/atomic.h> #include <linux/huge_mm.h> #include <linux/swap.h> #include <linux/string.h> @@ -185,4 +186,89 @@ static inline bool is_same_vma_anon_name(struct vm_area_struct *vma, } #endif /* CONFIG_ANON_VMA_NAME */ +static inline void init_tlb_flush_pending(struct mm_struct *mm) +{ + atomic_set(&mm->tlb_flush_pending, 0); +} + +static inline void inc_tlb_flush_pending(struct mm_struct *mm) +{ + atomic_inc(&mm->tlb_flush_pending); + /* + * The only time this value is relevant is when there are indeed pages + * to flush. And we'll only flush pages after changing them, which + * requires the PTL. + * + * So the ordering here is: + * + * atomic_inc(&mm->tlb_flush_pending); + * spin_lock(&ptl); + * ... + * set_pte_at(); + * spin_unlock(&ptl); + * + * spin_lock(&ptl) + * mm_tlb_flush_pending(); + * .... + * spin_unlock(&ptl); + * + * flush_tlb_range(); + * atomic_dec(&mm->tlb_flush_pending); + * + * Where the increment if constrained by the PTL unlock, it thus + * ensures that the increment is visible if the PTE modification is + * visible. After all, if there is no PTE modification, nobody cares + * about TLB flushes either. + * + * This very much relies on users (mm_tlb_flush_pending() and + * mm_tlb_flush_nested()) only caring about _specific_ PTEs (and + * therefore specific PTLs), because with SPLIT_PTE_PTLOCKS and RCpc + * locks (PPC) the unlock of one doesn't order against the lock of + * another PTL. + * + * The decrement is ordered by the flush_tlb_range(), such that + * mm_tlb_flush_pending() will not return false unless all flushes have + * completed. + */ +} + +static inline void dec_tlb_flush_pending(struct mm_struct *mm) +{ + /* + * See inc_tlb_flush_pending(). + * + * This cannot be smp_mb__before_atomic() because smp_mb() simply does + * not order against TLB invalidate completion, which is what we need. + * + * Therefore we must rely on tlb_flush_*() to guarantee order. + */ + atomic_dec(&mm->tlb_flush_pending); +} + +static inline bool mm_tlb_flush_pending(struct mm_struct *mm) +{ + /* + * Must be called after having acquired the PTL; orders against that + * PTLs release and therefore ensures that if we observe the modified + * PTE we must also observe the increment from inc_tlb_flush_pending(). + * + * That is, it only guarantees to return true if there is a flush + * pending for _this_ PTL. + */ + return atomic_read(&mm->tlb_flush_pending); +} + +static inline bool mm_tlb_flush_nested(struct mm_struct *mm) +{ + /* + * Similar to mm_tlb_flush_pending(), we must have acquired the PTL + * for which there is a TLB flush pending in order to guarantee + * we've seen both that PTE modification and the increment. + * + * (no requirement on actually still holding the PTL, that is irrelevant) + */ + return atomic_read(&mm->tlb_flush_pending) > 1; +} + + #endif diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 4d5fb84eed5e..6a89f128c990 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -692,90 +692,6 @@ extern void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm); extern void tlb_gather_mmu_fullmm(struct mmu_gather *tlb, struct mm_struct *mm); extern void tlb_finish_mmu(struct mmu_gather *tlb); -static inline void init_tlb_flush_pending(struct mm_struct *mm) -{ - atomic_set(&mm->tlb_flush_pending, 0); -} - -static inline void inc_tlb_flush_pending(struct mm_struct *mm) -{ - atomic_inc(&mm->tlb_flush_pending); - /* - * The only time this value is relevant is when there are indeed pages - * to flush. And we'll only flush pages after changing them, which - * requires the PTL. - * - * So the ordering here is: - * - * atomic_inc(&mm->tlb_flush_pending); - * spin_lock(&ptl); - * ... - * set_pte_at(); - * spin_unlock(&ptl); - * - * spin_lock(&ptl) - * mm_tlb_flush_pending(); - * .... - * spin_unlock(&ptl); - * - * flush_tlb_range(); - * atomic_dec(&mm->tlb_flush_pending); - * - * Where the increment if constrained by the PTL unlock, it thus - * ensures that the increment is visible if the PTE modification is - * visible. After all, if there is no PTE modification, nobody cares - * about TLB flushes either. - * - * This very much relies on users (mm_tlb_flush_pending() and - * mm_tlb_flush_nested()) only caring about _specific_ PTEs (and - * therefore specific PTLs), because with SPLIT_PTE_PTLOCKS and RCpc - * locks (PPC) the unlock of one doesn't order against the lock of - * another PTL. - * - * The decrement is ordered by the flush_tlb_range(), such that - * mm_tlb_flush_pending() will not return false unless all flushes have - * completed. - */ -} - -static inline void dec_tlb_flush_pending(struct mm_struct *mm) -{ - /* - * See inc_tlb_flush_pending(). - * - * This cannot be smp_mb__before_atomic() because smp_mb() simply does - * not order against TLB invalidate completion, which is what we need. - * - * Therefore we must rely on tlb_flush_*() to guarantee order. - */ - atomic_dec(&mm->tlb_flush_pending); -} - -static inline bool mm_tlb_flush_pending(struct mm_struct *mm) -{ - /* - * Must be called after having acquired the PTL; orders against that - * PTLs release and therefore ensures that if we observe the modified - * PTE we must also observe the increment from inc_tlb_flush_pending(). - * - * That is, it only guarantees to return true if there is a flush - * pending for _this_ PTL. - */ - return atomic_read(&mm->tlb_flush_pending); -} - -static inline bool mm_tlb_flush_nested(struct mm_struct *mm) -{ - /* - * Similar to mm_tlb_flush_pending(), we must have acquired the PTL - * for which there is a TLB flush pending in order to guarantee - * we've seen both that PTE modification and the increment. - * - * (no requirement on actually still holding the PTL, that is irrelevant) - */ - return atomic_read(&mm->tlb_flush_pending) > 1; -} - struct vm_fault; /** @@ -890,4 +806,49 @@ typedef struct { unsigned long val; } swp_entry_t; +/** + * enum fault_flag - Fault flag definitions. + * @FAULT_FLAG_WRITE: Fault was a write fault. + * @FAULT_FLAG_MKWRITE: Fault was mkwrite of existing PTE. + * @FAULT_FLAG_ALLOW_RETRY: Allow to retry the fault if blocked. + * @FAULT_FLAG_RETRY_NOWAIT: Don't drop mmap_lock and wait when retrying. + * @FAULT_FLAG_KILLABLE: The fault task is in SIGKILL killable region. + * @FAULT_FLAG_TRIED: The fault has been tried once. + * @FAULT_FLAG_USER: The fault originated in userspace. + * @FAULT_FLAG_REMOTE: The fault is not for current task/mm. + * @FAULT_FLAG_INSTRUCTION: The fault was during an instruction fetch. + * @FAULT_FLAG_INTERRUPTIBLE: The fault can be interrupted by non-fatal signals. + * + * About @FAULT_FLAG_ALLOW_RETRY and @FAULT_FLAG_TRIED: we can specify + * whether we would allow page faults to retry by specifying these two + * fault flags correctly. Currently there can be three legal combinations: + * + * (a) ALLOW_RETRY and !TRIED: this means the page fault allows retry, and + * this is the first try + * + * (b) ALLOW_RETRY and TRIED: this means the page fault allows retry, and + * we've already tried at least once + * + * (c) !ALLOW_RETRY and !TRIED: this means the page fault does not allow retry + * + * The unlisted combination (!ALLOW_RETRY && TRIED) is illegal and should never + * be used. Note that page faults can be allowed to retry for multiple times, + * in which case we'll have an initial fault with flags (a) then later on + * continuous faults with flags (b). We should always try to detect pending + * signals before a retry to make sure the continuous page faults can still be + * interrupted if necessary. + */ +enum fault_flag { + FAULT_FLAG_WRITE = 1 << 0, + FAULT_FLAG_MKWRITE = 1 << 1, + FAULT_FLAG_ALLOW_RETRY = 1 << 2, + FAULT_FLAG_RETRY_NOWAIT = 1 << 3, + FAULT_FLAG_KILLABLE = 1 << 4, + FAULT_FLAG_TRIED = 1 << 5, + FAULT_FLAG_USER = 1 << 6, + FAULT_FLAG_REMOTE = 1 << 7, + FAULT_FLAG_INSTRUCTION = 1 << 8, + FAULT_FLAG_INTERRUPTIBLE = 1 << 9, +}; + #endif /* _LINUX_MM_TYPES_H */ diff --git a/mm/ksm.c b/mm/ksm.c index 0662093237e4..f34476ac0a41 100644 --- a/mm/ksm.c +++ b/mm/ksm.c @@ -15,6 +15,7 @@ #include <linux/errno.h> #include <linux/mm.h> +#include <linux/mm_inline.h> #include <linux/fs.h> #include <linux/mman.h> #include <linux/sched.h> diff --git a/mm/mapping_dirty_helpers.c b/mm/mapping_dirty_helpers.c index ea734f248fce..1b0ab8fcfd8b 100644 --- a/mm/mapping_dirty_helpers.c +++ b/mm/mapping_dirty_helpers.c @@ -3,6 +3,7 @@ #include <linux/hugetlb.h> #include <linux/bitops.h> #include <linux/mmu_notifier.h> +#include <linux/mm_inline.h> #include <asm/cacheflush.h> #include <asm/tlbflush.h> diff --git a/mm/memory.c b/mm/memory.c index 8f1de811a1dc..bc80d4effac9 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -41,6 +41,7 @@ #include <linux/kernel_stat.h> #include <linux/mm.h> +#include <linux/mm_inline.h> #include <linux/sched/mm.h> #include <linux/sched/coredump.h> #include <linux/sched/numa_balancing.h> diff --git a/mm/mmu_gather.c b/mm/mmu_gather.c index 1b9837419bf9..afb7185ffdc4 100644 --- a/mm/mmu_gather.c +++ b/mm/mmu_gather.c @@ -3,6 +3,7 @@ #include <linux/kernel.h> #include <linux/mmdebug.h> #include <linux/mm_types.h> +#include <linux/mm_inline.h> #include <linux/pagemap.h> #include <linux/rcupdate.h> #include <linux/smp.h> diff --git a/mm/pgtable-generic.c b/mm/pgtable-generic.c index 4e640baf9794..6523fda274e5 100644 --- a/mm/pgtable-generic.c +++ b/mm/pgtable-generic.c @@ -10,6 +10,7 @@ #include <linux/pagemap.h> #include <linux/hugetlb.h> #include <linux/pgtable.h> +#include <linux/mm_inline.h> #include <asm/tlb.h> /* -- cgit v1.2.3 From d283d422c6c4f0264fe8ecf5ae80036bf73f4594 Mon Sep 17 00:00:00 2001 From: Pasha Tatashin <pasha.tatashin@soleen.com> Date: Fri, 14 Jan 2022 14:06:41 -0800 Subject: x86: mm: add x86_64 support for page table check Add page table check hooks into routines that modify user page tables. Link: https://lkml.kernel.org/r/20211221154650.1047963-5-pasha.tatashin@soleen.com Signed-off-by: Pasha Tatashin <pasha.tatashin@soleen.com> Cc: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: David Rientjes <rientjes@google.com> Cc: Frederic Weisbecker <frederic@kernel.org> Cc: Greg Thelen <gthelen@google.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Hugh Dickins <hughd@google.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Slaby <jirislaby@kernel.org> Cc: Jonathan Corbet <corbet@lwn.net> Cc: Kees Cook <keescook@chromium.org> Cc: Masahiro Yamada <masahiroy@kernel.org> Cc: Mike Rapoport <rppt@kernel.org> Cc: Muchun Song <songmuchun@bytedance.com> Cc: Paul Turner <pjt@google.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Sami Tolvanen <samitolvanen@google.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Wei Xu <weixugc@google.com> Cc: Will Deacon <will@kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> --- arch/x86/Kconfig | 1 + arch/x86/include/asm/pgtable.h | 29 +++++++++++++++++++++++++++-- 2 files changed, 28 insertions(+), 2 deletions(-) (limited to 'arch/x86') diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 5c2ccb85f2ef..d0628415b93e 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -104,6 +104,7 @@ config X86 select ARCH_SUPPORTS_ACPI select ARCH_SUPPORTS_ATOMIC_RMW select ARCH_SUPPORTS_DEBUG_PAGEALLOC + select ARCH_SUPPORTS_PAGE_TABLE_CHECK if X86_64 select ARCH_SUPPORTS_NUMA_BALANCING if X86_64 select ARCH_SUPPORTS_KMAP_LOCAL_FORCE_MAP if NR_CPUS <= 4096 select ARCH_SUPPORTS_LTO_CLANG diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index 5196958aa6ac..d7d287ac1018 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -26,6 +26,7 @@ #include <asm/pkru.h> #include <asm/fpu/api.h> #include <asm-generic/pgtable_uffd.h> +#include <linux/page_table_check.h> extern pgd_t early_top_pgt[PTRS_PER_PGD]; bool __init __early_make_pgtable(unsigned long address, pmdval_t pmd); @@ -1006,18 +1007,21 @@ static inline pud_t native_local_pudp_get_and_clear(pud_t *pudp) static inline void set_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte) { + page_table_check_pte_set(mm, addr, ptep, pte); set_pte(ptep, pte); } static inline void set_pmd_at(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp, pmd_t pmd) { + page_table_check_pmd_set(mm, addr, pmdp, pmd); set_pmd(pmdp, pmd); } static inline void set_pud_at(struct mm_struct *mm, unsigned long addr, pud_t *pudp, pud_t pud) { + page_table_check_pud_set(mm, addr, pudp, pud); native_set_pud(pudp, pud); } @@ -1048,6 +1052,7 @@ static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { pte_t pte = native_ptep_get_and_clear(ptep); + page_table_check_pte_clear(mm, addr, pte); return pte; } @@ -1063,12 +1068,23 @@ static inline pte_t ptep_get_and_clear_full(struct mm_struct *mm, * care about updates and native needs no locking */ pte = native_local_ptep_get_and_clear(ptep); + page_table_check_pte_clear(mm, addr, pte); } else { pte = ptep_get_and_clear(mm, addr, ptep); } return pte; } +#define __HAVE_ARCH_PTEP_CLEAR +static inline void ptep_clear(struct mm_struct *mm, unsigned long addr, + pte_t *ptep) +{ + if (IS_ENABLED(CONFIG_PAGE_TABLE_CHECK)) + ptep_get_and_clear(mm, addr, ptep); + else + pte_clear(mm, addr, ptep); +} + #define __HAVE_ARCH_PTEP_SET_WRPROTECT static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, pte_t *ptep) @@ -1109,14 +1125,22 @@ static inline int pmd_write(pmd_t pmd) static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp) { - return native_pmdp_get_and_clear(pmdp); + pmd_t pmd = native_pmdp_get_and_clear(pmdp); + + page_table_check_pmd_clear(mm, addr, pmd); + + return pmd; } #define __HAVE_ARCH_PUDP_HUGE_GET_AND_CLEAR static inline pud_t pudp_huge_get_and_clear(struct mm_struct *mm, unsigned long addr, pud_t *pudp) { - return native_pudp_get_and_clear(pudp); + pud_t pud = native_pudp_get_and_clear(pudp); + + page_table_check_pud_clear(mm, addr, pud); + + return pud; } #define __HAVE_ARCH_PMDP_SET_WRPROTECT @@ -1137,6 +1161,7 @@ static inline int pud_write(pud_t pud) static inline pmd_t pmdp_establish(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp, pmd_t pmd) { + page_table_check_pmd_set(vma->vm_mm, address, pmdp, pmd); if (IS_ENABLED(CONFIG_SMP)) { return xchg(pmdp, pmd); } else { -- cgit v1.2.3 From 21b084fdf2a49ca1634e8e360e9ab6f9ff0dee11 Mon Sep 17 00:00:00 2001 From: "Aneesh Kumar K.V" <aneesh.kumar@linux.ibm.com> Date: Fri, 14 Jan 2022 14:08:21 -0800 Subject: mm/mempolicy: wire up syscall set_mempolicy_home_node Link: https://lkml.kernel.org/r/20211202123810.267175-4-aneesh.kumar@linux.ibm.com Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com> Cc: Ben Widawsky <ben.widawsky@intel.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: Feng Tang <feng.tang@intel.com> Cc: Michal Hocko <mhocko@kernel.org> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Mel Gorman <mgorman@techsingularity.net> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: Randy Dunlap <rdunlap@infradead.org> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Andi Kleen <ak@linux.intel.com> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Huang Ying <ying.huang@intel.com> Cc: <linux-api@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> --- arch/alpha/kernel/syscalls/syscall.tbl | 1 + arch/arm/tools/syscall.tbl | 1 + arch/arm64/include/asm/unistd.h | 2 +- arch/arm64/include/asm/unistd32.h | 2 ++ arch/ia64/kernel/syscalls/syscall.tbl | 1 + arch/m68k/kernel/syscalls/syscall.tbl | 1 + arch/microblaze/kernel/syscalls/syscall.tbl | 1 + arch/mips/kernel/syscalls/syscall_n32.tbl | 1 + arch/mips/kernel/syscalls/syscall_n64.tbl | 1 + arch/mips/kernel/syscalls/syscall_o32.tbl | 1 + arch/parisc/kernel/syscalls/syscall.tbl | 1 + arch/powerpc/kernel/syscalls/syscall.tbl | 1 + arch/s390/kernel/syscalls/syscall.tbl | 1 + arch/sh/kernel/syscalls/syscall.tbl | 1 + arch/sparc/kernel/syscalls/syscall.tbl | 1 + arch/x86/entry/syscalls/syscall_32.tbl | 1 + arch/x86/entry/syscalls/syscall_64.tbl | 1 + arch/xtensa/kernel/syscalls/syscall.tbl | 1 + include/linux/syscalls.h | 3 +++ include/uapi/asm-generic/unistd.h | 5 ++++- kernel/sys_ni.c | 1 + 21 files changed, 27 insertions(+), 2 deletions(-) (limited to 'arch/x86') diff --git a/arch/alpha/kernel/syscalls/syscall.tbl b/arch/alpha/kernel/syscalls/syscall.tbl index ca5a32228cd6..3515bc4f16a4 100644 --- a/arch/alpha/kernel/syscalls/syscall.tbl +++ b/arch/alpha/kernel/syscalls/syscall.tbl @@ -489,3 +489,4 @@ # 557 reserved for memfd_secret 558 common process_mrelease sys_process_mrelease 559 common futex_waitv sys_futex_waitv +560 common set_mempolicy_home_node sys_ni_syscall diff --git a/arch/arm/tools/syscall.tbl b/arch/arm/tools/syscall.tbl index 543100151f2b..ac964612d8b0 100644 --- a/arch/arm/tools/syscall.tbl +++ b/arch/arm/tools/syscall.tbl @@ -463,3 +463,4 @@ # 447 reserved for memfd_secret 448 common process_mrelease sys_process_mrelease 449 common futex_waitv sys_futex_waitv +450 common set_mempolicy_home_node sys_set_mempolicy_home_node diff --git a/arch/arm64/include/asm/unistd.h b/arch/arm64/include/asm/unistd.h index 6bdb5f5db438..4e65da3445c7 100644 --- a/arch/arm64/include/asm/unistd.h +++ b/arch/arm64/include/asm/unistd.h @@ -38,7 +38,7 @@ #define __ARM_NR_compat_set_tls (__ARM_NR_COMPAT_BASE + 5) #define __ARM_NR_COMPAT_END (__ARM_NR_COMPAT_BASE + 0x800) -#define __NR_compat_syscalls 450 +#define __NR_compat_syscalls 451 #endif #define __ARCH_WANT_SYS_CLONE diff --git a/arch/arm64/include/asm/unistd32.h b/arch/arm64/include/asm/unistd32.h index 41ea1195e44b..604a2053d006 100644 --- a/arch/arm64/include/asm/unistd32.h +++ b/arch/arm64/include/asm/unistd32.h @@ -905,6 +905,8 @@ __SYSCALL(__NR_landlock_restrict_self, sys_landlock_restrict_self) __SYSCALL(__NR_process_mrelease, sys_process_mrelease) #define __NR_futex_waitv 449 __SYSCALL(__NR_futex_waitv, sys_futex_waitv) +#define __NR_set_mempolicy_home_node 450 +__SYSCALL(__NR_set_mempolicy_home_node, sys_set_mempolicy_home_node) /* * Please add new compat syscalls above this comment and update diff --git a/arch/ia64/kernel/syscalls/syscall.tbl b/arch/ia64/kernel/syscalls/syscall.tbl index 707ae121f6d3..78b1d03e86e1 100644 --- a/arch/ia64/kernel/syscalls/syscall.tbl +++ b/arch/ia64/kernel/syscalls/syscall.tbl @@ -370,3 +370,4 @@ # 447 reserved for memfd_secret 448 common process_mrelease sys_process_mrelease 449 common futex_waitv sys_futex_waitv +450 common set_mempolicy_home_node sys_set_mempolicy_home_node diff --git a/arch/m68k/kernel/syscalls/syscall.tbl b/arch/m68k/kernel/syscalls/syscall.tbl index 45bc32a41b90..b1f3940bc298 100644 --- a/arch/m68k/kernel/syscalls/syscall.tbl +++ b/arch/m68k/kernel/syscalls/syscall.tbl @@ -449,3 +449,4 @@ # 447 reserved for memfd_secret 448 common process_mrelease sys_process_mrelease 449 common futex_waitv sys_futex_waitv +450 common set_mempolicy_home_node sys_set_mempolicy_home_node diff --git a/arch/microblaze/kernel/syscalls/syscall.tbl b/arch/microblaze/kernel/syscalls/syscall.tbl index 2204bde3ce4a..820145e47350 100644 --- a/arch/microblaze/kernel/syscalls/syscall.tbl +++ b/arch/microblaze/kernel/syscalls/syscall.tbl @@ -455,3 +455,4 @@ # 447 reserved for memfd_secret 448 common process_mrelease sys_process_mrelease 449 common futex_waitv sys_futex_waitv +450 common set_mempolicy_home_node sys_set_mempolicy_home_node diff --git a/arch/mips/kernel/syscalls/syscall_n32.tbl b/arch/mips/kernel/syscalls/syscall_n32.tbl index 72d02d363f36..253ff994ed2e 100644 --- a/arch/mips/kernel/syscalls/syscall_n32.tbl +++ b/arch/mips/kernel/syscalls/syscall_n32.tbl @@ -388,3 +388,4 @@ # 447 reserved for memfd_secret 448 n32 process_mrelease sys_process_mrelease 449 n32 futex_waitv sys_futex_waitv +450 n32 set_mempolicy_home_node sys_set_mempolicy_home_node diff --git a/arch/mips/kernel/syscalls/syscall_n64.tbl b/arch/mips/kernel/syscalls/syscall_n64.tbl index e2c481fcede6..3f1886ad9d80 100644 --- a/arch/mips/kernel/syscalls/syscall_n64.tbl +++ b/arch/mips/kernel/syscalls/syscall_n64.tbl @@ -364,3 +364,4 @@ # 447 reserved for memfd_secret 448 n64 process_mrelease sys_process_mrelease 449 n64 futex_waitv sys_futex_waitv +450 common set_mempolicy_home_node sys_set_mempolicy_home_node diff --git a/arch/mips/kernel/syscalls/syscall_o32.tbl b/arch/mips/kernel/syscalls/syscall_o32.tbl index 3714c97b2643..8f243e35a7b2 100644 --- a/arch/mips/kernel/syscalls/syscall_o32.tbl +++ b/arch/mips/kernel/syscalls/syscall_o32.tbl @@ -437,3 +437,4 @@ # 447 reserved for memfd_secret 448 o32 process_mrelease sys_process_mrelease 449 o32 futex_waitv sys_futex_waitv +450 o32 set_mempolicy_home_node sys_set_mempolicy_home_node diff --git a/arch/parisc/kernel/syscalls/syscall.tbl b/arch/parisc/kernel/syscalls/syscall.tbl index 358c00000755..68b46fe2f17c 100644 --- a/arch/parisc/kernel/syscalls/syscall.tbl +++ b/arch/parisc/kernel/syscalls/syscall.tbl @@ -447,3 +447,4 @@ # 447 reserved for memfd_secret 448 common process_mrelease sys_process_mrelease 449 common futex_waitv sys_futex_waitv +450 common set_mempolicy_home_node sys_set_mempolicy_home_node diff --git a/arch/powerpc/kernel/syscalls/syscall.tbl b/arch/powerpc/kernel/syscalls/syscall.tbl index 15109af9d075..2600b4237292 100644 --- a/arch/powerpc/kernel/syscalls/syscall.tbl +++ b/arch/powerpc/kernel/syscalls/syscall.tbl @@ -529,3 +529,4 @@ # 447 reserved for memfd_secret 448 common process_mrelease sys_process_mrelease 449 common futex_waitv sys_futex_waitv +450 nospu set_mempolicy_home_node sys_set_mempolicy_home_node diff --git a/arch/s390/kernel/syscalls/syscall.tbl b/arch/s390/kernel/syscalls/syscall.tbl index ed9c5c2eafad..799147658dee 100644 --- a/arch/s390/kernel/syscalls/syscall.tbl +++ b/arch/s390/kernel/syscalls/syscall.tbl @@ -452,3 +452,4 @@ # 447 reserved for memfd_secret 448 common process_mrelease sys_process_mrelease sys_process_mrelease 449 common futex_waitv sys_futex_waitv sys_futex_waitv +450 common set_mempolicy_home_node sys_set_mempolicy_home_node sys_set_mempolicy_home_node diff --git a/arch/sh/kernel/syscalls/syscall.tbl b/arch/sh/kernel/syscalls/syscall.tbl index d9539d28bdaa..2de85c977f54 100644 --- a/arch/sh/kernel/syscalls/syscall.tbl +++ b/arch/sh/kernel/syscalls/syscall.tbl @@ -452,3 +452,4 @@ # 447 reserved for memfd_secret 448 common process_mrelease sys_process_mrelease 449 common futex_waitv sys_futex_waitv +450 common set_mempolicy_home_node sys_set_mempolicy_home_node diff --git a/arch/sparc/kernel/syscalls/syscall.tbl b/arch/sparc/kernel/syscalls/syscall.tbl index 46adabcb1720..4398cc6fb68d 100644 --- a/arch/sparc/kernel/syscalls/syscall.tbl +++ b/arch/sparc/kernel/syscalls/syscall.tbl @@ -495,3 +495,4 @@ # 447 reserved for memfd_secret 448 common process_mrelease sys_process_mrelease 449 common futex_waitv sys_futex_waitv +450 common set_mempolicy_home_node sys_set_mempolicy_home_node diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl index 7e25543693de..320480a8db4f 100644 --- a/arch/x86/entry/syscalls/syscall_32.tbl +++ b/arch/x86/entry/syscalls/syscall_32.tbl @@ -454,3 +454,4 @@ 447 i386 memfd_secret sys_memfd_secret 448 i386 process_mrelease sys_process_mrelease 449 i386 futex_waitv sys_futex_waitv +450 i386 set_mempolicy_home_node sys_set_mempolicy_home_node diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl index fe8f8dd157b4..c84d12608cd2 100644 --- a/arch/x86/entry/syscalls/syscall_64.tbl +++ b/arch/x86/entry/syscalls/syscall_64.tbl @@ -371,6 +371,7 @@ 447 common memfd_secret sys_memfd_secret 448 common process_mrelease sys_process_mrelease 449 common futex_waitv sys_futex_waitv +450 common set_mempolicy_home_node sys_set_mempolicy_home_node # # Due to a historical design error, certain syscalls are numbered differently diff --git a/arch/xtensa/kernel/syscalls/syscall.tbl b/arch/xtensa/kernel/syscalls/syscall.tbl index 3e3e1a506bed..52c94ab5c205 100644 --- a/arch/xtensa/kernel/syscalls/syscall.tbl +++ b/arch/xtensa/kernel/syscalls/syscall.tbl @@ -420,3 +420,4 @@ # 447 reserved for memfd_secret 448 common process_mrelease sys_process_mrelease 449 common futex_waitv sys_futex_waitv +450 common set_mempolicy_home_node sys_set_mempolicy_home_node diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 528a478dbda8..819c0cb00b6d 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -1057,6 +1057,9 @@ asmlinkage long sys_landlock_add_rule(int ruleset_fd, enum landlock_rule_type ru const void __user *rule_attr, __u32 flags); asmlinkage long sys_landlock_restrict_self(int ruleset_fd, __u32 flags); asmlinkage long sys_memfd_secret(unsigned int flags); +asmlinkage long sys_set_mempolicy_home_node(unsigned long start, unsigned long len, + unsigned long home_node, + unsigned long flags); /* * Architecture-specific system calls diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h index 4557a8b6086f..1c48b0ae3ba3 100644 --- a/include/uapi/asm-generic/unistd.h +++ b/include/uapi/asm-generic/unistd.h @@ -883,8 +883,11 @@ __SYSCALL(__NR_process_mrelease, sys_process_mrelease) #define __NR_futex_waitv 449 __SYSCALL(__NR_futex_waitv, sys_futex_waitv) +#define __NR_set_mempolicy_home_node 450 +__SYSCALL(__NR_set_mempolicy_home_node, sys_set_mempolicy_home_node) + #undef __NR_syscalls -#define __NR_syscalls 450 +#define __NR_syscalls 451 /* * 32 bit systems traditionally used different diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c index d1944258cfc0..a492f159624f 100644 --- a/kernel/sys_ni.c +++ b/kernel/sys_ni.c @@ -297,6 +297,7 @@ COND_SYSCALL(get_mempolicy); COND_SYSCALL(set_mempolicy); COND_SYSCALL(migrate_pages); COND_SYSCALL(move_pages); +COND_SYSCALL(set_mempolicy_home_node); COND_SYSCALL(perf_event_open); COND_SYSCALL(accept4); -- cgit v1.2.3