From dd63fdcc63f0f853b116b52e56200a0e0227cf5f Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Fri, 13 Mar 2009 03:20:49 +0100 Subject: x86: unify kmap_atomic_pfn() and iomap_atomic_prot_pfn(), fix Impact: build fix Move kmap_atomic_prot_pfn() to iomap_32.c. It is used on all 32-bit kernels, while highmem_32.c is only built on highmem kernels. ( Note: the debug_kmap_atomic_prot() check is removed for now, that problem is handled via another patch. ) Reported-by: Thomas Gleixner Cc: Akinobu Mita LKML-Reference: <20090311143317.GA22244@localhost.localdomain> Signed-off-by: Ingo Molnar --- arch/x86/mm/highmem_32.c | 20 ++------------------ arch/x86/mm/iomap_32.c | 18 +++++++++++++++++- 2 files changed, 19 insertions(+), 19 deletions(-) (limited to 'arch/x86/mm') diff --git a/arch/x86/mm/highmem_32.c b/arch/x86/mm/highmem_32.c index f256e73542d7..522db5e3d0bf 100644 --- a/arch/x86/mm/highmem_32.c +++ b/arch/x86/mm/highmem_32.c @@ -121,24 +121,8 @@ void kunmap_atomic(void *kvaddr, enum km_type type) pagefault_enable(); } -void *kmap_atomic_prot_pfn(unsigned long pfn, enum km_type type, pgprot_t prot) -{ - enum fixed_addresses idx; - unsigned long vaddr; - - pagefault_disable(); - - debug_kmap_atomic_prot(type); - - idx = type + KM_TYPE_NR * smp_processor_id(); - vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx); - set_pte(kmap_pte - idx, pfn_pte(pfn, prot)); - arch_flush_lazy_mmu_mode(); - - return (void*) vaddr; -} - -/* This is the same as kmap_atomic() but can map memory that doesn't +/* + * This is the same as kmap_atomic() but can map memory that doesn't * have a struct page associated with it. */ void *kmap_atomic_pfn(unsigned long pfn, enum km_type type) diff --git a/arch/x86/mm/iomap_32.c b/arch/x86/mm/iomap_32.c index 592984e5496b..6e60ba698cee 100644 --- a/arch/x86/mm/iomap_32.c +++ b/arch/x86/mm/iomap_32.c @@ -32,7 +32,23 @@ int is_io_mapping_possible(resource_size_t base, unsigned long size) } EXPORT_SYMBOL_GPL(is_io_mapping_possible); -/* Map 'pfn' using fixed map 'type' and protections 'prot' +void *kmap_atomic_prot_pfn(unsigned long pfn, enum km_type type, pgprot_t prot) +{ + enum fixed_addresses idx; + unsigned long vaddr; + + pagefault_disable(); + + idx = type + KM_TYPE_NR * smp_processor_id(); + vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx); + set_pte(kmap_pte - idx, pfn_pte(pfn, prot)); + arch_flush_lazy_mmu_mode(); + + return (void *)vaddr; +} + +/* + * Map 'pfn' using fixed map 'type' and protections 'prot' */ void * iomap_atomic_prot_pfn(unsigned long pfn, enum km_type type, pgprot_t prot) -- cgit v1.2.3 From 13c6c53282d99c82e79b02477efd2c1e30a991ef Mon Sep 17 00:00:00 2001 From: Jan Beulich Date: Thu, 12 Mar 2009 12:37:34 +0000 Subject: x86, 32-bit: also use cpuinfo_x86's x86_{phys,virt}_bits members Impact: 32/64-bit consolidation In a first step, this allows fixing phys_addr_valid() for PAE (which until now reported all addresses to be valid). Subsequently, this will also allow simplifying some MTRR handling code. Signed-off-by: Jan Beulich LKML-Reference: <49B9101E.76E4.0078.0@novell.com> Signed-off-by: Ingo Molnar --- arch/x86/include/asm/processor.h | 2 +- arch/x86/kernel/cpu/common.c | 12 +++++++++++- arch/x86/kernel/cpu/intel.c | 5 +++++ arch/x86/mm/ioremap.c | 17 ++++++++--------- 4 files changed, 25 insertions(+), 11 deletions(-) (limited to 'arch/x86/mm') diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 76139506c3e4..bd3406db1d68 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -75,9 +75,9 @@ struct cpuinfo_x86 { #else /* Number of 4K pages in DTLB/ITLB combined(in pages): */ int x86_tlbsize; +#endif __u8 x86_virt_bits; __u8 x86_phys_bits; -#endif /* CPUID returned core id bits: */ __u8 x86_coreid_bits; /* Max extended CPUID function supported: */ diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 826d5c876278..a95e9480bb9c 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -549,13 +549,15 @@ static void __cpuinit get_cpu_cap(struct cpuinfo_x86 *c) } } -#ifdef CONFIG_X86_64 if (c->extended_cpuid_level >= 0x80000008) { u32 eax = cpuid_eax(0x80000008); c->x86_virt_bits = (eax >> 8) & 0xff; c->x86_phys_bits = eax & 0xff; } +#ifdef CONFIG_X86_32 + else if (cpu_has(c, X86_FEATURE_PAE) || cpu_has(c, X86_FEATURE_PSE36)) + c->x86_phys_bits = 36; #endif if (c->extended_cpuid_level >= 0x80000007) @@ -602,8 +604,12 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c) { #ifdef CONFIG_X86_64 c->x86_clflush_size = 64; + c->x86_phys_bits = 36; + c->x86_virt_bits = 48; #else c->x86_clflush_size = 32; + c->x86_phys_bits = 32; + c->x86_virt_bits = 32; #endif c->x86_cache_alignment = c->x86_clflush_size; @@ -726,9 +732,13 @@ static void __cpuinit identify_cpu(struct cpuinfo_x86 *c) c->x86_coreid_bits = 0; #ifdef CONFIG_X86_64 c->x86_clflush_size = 64; + c->x86_phys_bits = 36; + c->x86_virt_bits = 48; #else c->cpuid_level = -1; /* CPUID not detected */ c->x86_clflush_size = 32; + c->x86_phys_bits = 32; + c->x86_virt_bits = 32; #endif c->x86_cache_alignment = c->x86_clflush_size; memset(&c->x86_capability, 0, sizeof c->x86_capability); diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index 191117f1ad51..ae769471042e 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -54,6 +54,11 @@ static void __cpuinit early_init_intel(struct cpuinfo_x86 *c) c->x86_cache_alignment = 128; #endif + /* CPUID workaround for 0F33/0F34 CPU */ + if (c->x86 == 0xF && c->x86_model == 0x3 + && (c->x86_mask == 0x3 || c->x86_mask == 0x4)) + c->x86_phys_bits = 36; + /* * c->x86_power is 8000_0007 edx. Bit 8 is TSC runs at constant rate * with P/T states and does not stop in deep C-states diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c index aca924a30ee6..83ed74affba9 100644 --- a/arch/x86/mm/ioremap.c +++ b/arch/x86/mm/ioremap.c @@ -22,13 +22,17 @@ #include #include -#ifdef CONFIG_X86_64 - -static inline int phys_addr_valid(unsigned long addr) +static inline int phys_addr_valid(resource_size_t addr) { - return addr < (1UL << boot_cpu_data.x86_phys_bits); +#ifdef CONFIG_PHYS_ADDR_T_64BIT + return !(addr >> boot_cpu_data.x86_phys_bits); +#else + return 1; +#endif } +#ifdef CONFIG_X86_64 + unsigned long __phys_addr(unsigned long x) { if (x >= __START_KERNEL_map) { @@ -65,11 +69,6 @@ EXPORT_SYMBOL(__virt_addr_valid); #else -static inline int phys_addr_valid(unsigned long addr) -{ - return 1; -} - #ifdef CONFIG_DEBUG_VIRTUAL unsigned long __phys_addr(unsigned long x) { -- cgit v1.2.3 From dc9dd5cc854cde110d2421f3a11fec7597e059c1 Mon Sep 17 00:00:00 2001 From: Jan Beulich Date: Thu, 12 Mar 2009 12:40:06 +0000 Subject: x86: move save_mr() into .meminit.text Impact: cleanup, save memory The function is only being called from boot or memory hotplug paths. Signed-off-by: Jan Beulich LKML-Reference: <49B910B6.76E4.0078.0@novell.com> Signed-off-by: Ingo Molnar --- arch/x86/mm/init.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'arch/x86/mm') diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c index 15219e0d1243..fd3da1dda1c9 100644 --- a/arch/x86/mm/init.c +++ b/arch/x86/mm/init.c @@ -94,9 +94,9 @@ struct map_range { #define NR_RANGE_MR 5 #endif -static int save_mr(struct map_range *mr, int nr_range, - unsigned long start_pfn, unsigned long end_pfn, - unsigned long page_size_mask) +static int __meminit save_mr(struct map_range *mr, int nr_range, + unsigned long start_pfn, unsigned long end_pfn, + unsigned long page_size_mask) { if (start_pfn < end_pfn) { if (nr_range >= NR_RANGE_MR) -- cgit v1.2.3 From 698609bdcd35d0641f4c6622c83680ab1a6d67cb Mon Sep 17 00:00:00 2001 From: Jan Beulich Date: Thu, 12 Mar 2009 13:11:50 +0000 Subject: x86: create a non-zero sized bm_pte only when needed Impact: kernel image size reduction Since in most configurations the pmd page needed maps the same range of virtual addresses which is also mapped by the earlier inserted one for covering FIX_DBGP_BASE, that page (and its insertion in the page tables) can be avoided altogether by detecting the condition at compile time. Signed-off-by: Jan Beulich LKML-Reference: <49B91826.76E4.0078.0@novell.com> Signed-off-by: Ingo Molnar --- arch/x86/mm/ioremap.c | 19 ++++++++++++++++--- 1 file changed, 16 insertions(+), 3 deletions(-) (limited to 'arch/x86/mm') diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c index 83ed74affba9..55e127f71ed9 100644 --- a/arch/x86/mm/ioremap.c +++ b/arch/x86/mm/ioremap.c @@ -487,7 +487,12 @@ static int __init early_ioremap_debug_setup(char *str) early_param("early_ioremap_debug", early_ioremap_debug_setup); static __initdata int after_paging_init; -static pte_t bm_pte[PAGE_SIZE/sizeof(pte_t)] __page_aligned_bss; +#define __FIXADDR_TOP (-PAGE_SIZE) +static pte_t bm_pte[(__fix_to_virt(FIX_DBGP_BASE) + ^ __fix_to_virt(FIX_BTMAP_BEGIN)) >> PMD_SHIFT + ? PAGE_SIZE / sizeof(pte_t) : 0] __page_aligned_bss; +#undef __FIXADDR_TOP +static __initdata pte_t *bm_ptep; static inline pmd_t * __init early_ioremap_pmd(unsigned long addr) { @@ -502,6 +507,8 @@ static inline pmd_t * __init early_ioremap_pmd(unsigned long addr) static inline pte_t * __init early_ioremap_pte(unsigned long addr) { + if (!sizeof(bm_pte)) + return &bm_ptep[pte_index(addr)]; return &bm_pte[pte_index(addr)]; } @@ -519,8 +526,14 @@ void __init early_ioremap_init(void) slot_virt[i] = fix_to_virt(FIX_BTMAP_BEGIN - NR_FIX_BTMAPS*i); pmd = early_ioremap_pmd(fix_to_virt(FIX_BTMAP_BEGIN)); - memset(bm_pte, 0, sizeof(bm_pte)); - pmd_populate_kernel(&init_mm, pmd, bm_pte); + if (sizeof(bm_pte)) { + memset(bm_pte, 0, sizeof(bm_pte)); + pmd_populate_kernel(&init_mm, pmd, bm_pte); + } else { + bm_ptep = pte_offset_kernel(pmd, 0); + if (early_ioremap_debug) + printk(KERN_INFO "bm_ptep=%p\n", bm_ptep); + } /* * The boot-ioremap range spans multiple pmds, for which -- cgit v1.2.3 From 4bb9c5c02153dfc89a6c73a6f32091413805ad7d Mon Sep 17 00:00:00 2001 From: "Pallipadi, Venkatesh" Date: Thu, 12 Mar 2009 17:45:27 -0700 Subject: VM, x86, PAT: Change is_linear_pfn_mapping to not use vm_pgoff Impact: fix false positive PAT warnings - also fix VirtalBox hang Use of vma->vm_pgoff to identify the pfnmaps that are fully mapped at mmap time is broken. vm_pgoff is set by generic mmap code even for cases where drivers are setting up the mappings at the fault time. The problem was originally reported here: http://marc.info/?l=linux-kernel&m=123383810628583&w=2 Change is_linear_pfn_mapping logic to overload VM_INSERTPAGE flag along with VM_PFNMAP to mean full PFNMAP setup at mmap time. Problem also tracked at: http://bugzilla.kernel.org/show_bug.cgi?id=12800 Reported-by: Thomas Hellstrom Tested-by: Frans Pop Signed-off-by: Venkatesh Pallipadi Signed-off-by: Suresh Siddha @intel.com> Cc: Nick Piggin Cc: "ebiederm@xmission.com" Cc: # only for 2.6.29.1, not .28 LKML-Reference: <20090313004527.GA7176@linux-os.sc.intel.com> Signed-off-by: Ingo Molnar --- arch/x86/mm/pat.c | 5 +++-- include/linux/mm.h | 15 +++++++++++++-- mm/memory.c | 6 ++++-- 3 files changed, 20 insertions(+), 6 deletions(-) (limited to 'arch/x86/mm') diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c index e0ab173b6974..21bc1f787ae2 100644 --- a/arch/x86/mm/pat.c +++ b/arch/x86/mm/pat.c @@ -641,10 +641,11 @@ static int reserve_pfn_range(u64 paddr, unsigned long size, pgprot_t *vma_prot, is_ram = pat_pagerange_is_ram(paddr, paddr + size); /* - * reserve_pfn_range() doesn't support RAM pages. + * reserve_pfn_range() doesn't support RAM pages. Maintain the current + * behavior with RAM pages by returning success. */ if (is_ram != 0) - return -EINVAL; + return 0; ret = reserve_memtype(paddr, paddr + size, want_flags, &flags); if (ret) diff --git a/include/linux/mm.h b/include/linux/mm.h index 065cdf8c09fb..3daa05feed9f 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -98,7 +98,7 @@ extern unsigned int kobjsize(const void *objp); #define VM_HUGETLB 0x00400000 /* Huge TLB Page VM */ #define VM_NONLINEAR 0x00800000 /* Is non-linear (remap_file_pages) */ #define VM_MAPPED_COPY 0x01000000 /* T if mapped copy of data (nommu mmap) */ -#define VM_INSERTPAGE 0x02000000 /* The vma has had "vm_insert_page()" done on it */ +#define VM_INSERTPAGE 0x02000000 /* The vma has had "vm_insert_page()" done on it. Refer note in VM_PFNMAP_AT_MMAP below */ #define VM_ALWAYSDUMP 0x04000000 /* Always include in core dumps */ #define VM_CAN_NONLINEAR 0x08000000 /* Has ->fault & does nonlinear pages */ @@ -126,6 +126,17 @@ extern unsigned int kobjsize(const void *objp); */ #define VM_SPECIAL (VM_IO | VM_DONTEXPAND | VM_RESERVED | VM_PFNMAP) +/* + * pfnmap vmas that are fully mapped at mmap time (not mapped on fault). + * Used by x86 PAT to identify such PFNMAP mappings and optimize their handling. + * Note VM_INSERTPAGE flag is overloaded here. i.e, + * VM_INSERTPAGE && !VM_PFNMAP implies + * The vma has had "vm_insert_page()" done on it + * VM_INSERTPAGE && VM_PFNMAP implies + * The vma is PFNMAP with full mapping at mmap time + */ +#define VM_PFNMAP_AT_MMAP (VM_INSERTPAGE | VM_PFNMAP) + /* * mapping from the currently active vm_flags protection bits (the * low four bits) to a page protection mask.. @@ -145,7 +156,7 @@ extern pgprot_t protection_map[16]; */ static inline int is_linear_pfn_mapping(struct vm_area_struct *vma) { - return ((vma->vm_flags & VM_PFNMAP) && vma->vm_pgoff); + return ((vma->vm_flags & VM_PFNMAP_AT_MMAP) == VM_PFNMAP_AT_MMAP); } static inline int is_pfn_mapping(struct vm_area_struct *vma) diff --git a/mm/memory.c b/mm/memory.c index baa999e87cd2..d7df5babcba9 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -1665,9 +1665,10 @@ int remap_pfn_range(struct vm_area_struct *vma, unsigned long addr, * behaviour that some programs depend on. We mark the "original" * un-COW'ed pages by matching them up with "vma->vm_pgoff". */ - if (addr == vma->vm_start && end == vma->vm_end) + if (addr == vma->vm_start && end == vma->vm_end) { vma->vm_pgoff = pfn; - else if (is_cow_mapping(vma->vm_flags)) + vma->vm_flags |= VM_PFNMAP_AT_MMAP; + } else if (is_cow_mapping(vma->vm_flags)) return -EINVAL; vma->vm_flags |= VM_IO | VM_RESERVED | VM_PFNMAP; @@ -1679,6 +1680,7 @@ int remap_pfn_range(struct vm_area_struct *vma, unsigned long addr, * needed from higher level routine calling unmap_vmas */ vma->vm_flags &= ~(VM_IO | VM_RESERVED | VM_PFNMAP); + vma->vm_flags &= ~VM_PFNMAP_AT_MMAP; return -EINVAL; } -- cgit v1.2.3