From 64141da587241301ce8638cc945f8b67853156ec Mon Sep 17 00:00:00 2001 From: Jeremy Fitzhardinge Date: Thu, 2 Dec 2010 14:31:18 -0800 Subject: vmalloc: eagerly clear ptes on vunmap On stock 2.6.37-rc4, running: # mount lilith:/export /mnt/lilith # find /mnt/lilith/ -type f -print0 | xargs -0 file crashes the machine fairly quickly under Xen. Often it results in oops messages, but the couple of times I tried just now, it just hung quietly and made Xen print some rude messages: (XEN) mm.c:2389:d80 Bad type (saw 7400000000000001 != exp 3000000000000000) for mfn 1d7058 (pfn 18fa7) (XEN) mm.c:964:d80 Attempt to create linear p.t. with write perms (XEN) mm.c:2389:d80 Bad type (saw 7400000000000010 != exp 1000000000000000) for mfn 1d2e04 (pfn 1d1fb) (XEN) mm.c:2965:d80 Error while pinning mfn 1d2e04 Which means the domain tried to map a pagetable page RW, which would allow it to map arbitrary memory, so Xen stopped it. This is because vm_unmap_ram() left some pages mapped in the vmalloc area after NFS had finished with them, and those pages got recycled as pagetable pages while still having these RW aliases. Removing those mappings immediately removes the Xen-visible aliases, and so it has no problem with those pages being reused as pagetable pages. Deferring the TLB flush doesn't upset Xen because it can flush the TLB itself as needed to maintain its invariants. When unmapping a region in the vmalloc space, clear the ptes immediately. There's no point in deferring this because there's no amortization benefit. The TLBs are left dirty, and they are flushed lazily to amortize the cost of the IPIs. This specific motivation for this patch is an oops-causing regression since 2.6.36 when using NFS under Xen, triggered by the NFS client's use of vm_map_ram() introduced in 56e4ebf877b60 ("NFS: readdir with vmapped pages") . XFS also uses vm_map_ram() and could cause similar problems. Signed-off-by: Jeremy Fitzhardinge Cc: Nick Piggin Cc: Bryan Schumaker Cc: Trond Myklebust Cc: Alex Elder Cc: Dave Chinner Cc: Christoph Hellwig Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/vmalloc.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux/vmalloc.h') diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index a03dcf62ca9d..44b54f619ac6 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -7,8 +7,6 @@ struct vm_area_struct; /* vma defining user mapping in mm_types.h */ -extern bool vmap_lazy_unmap; - /* bits in flags of vmalloc's vm_struct below */ #define VM_IOREMAP 0x00000001 /* ioremap() and friends */ #define VM_ALLOC 0x00000002 /* vmalloc() */ -- cgit v1.2.3 From e5a5623b28198aa91ea71ee5d3846757fc76bc87 Mon Sep 17 00:00:00 2001 From: David Rientjes Date: Thu, 13 Jan 2011 15:46:00 -0800 Subject: mm: remove unused get_vm_area_node get_vm_area_node() is unused in the kernel and can thus be removed. Signed-off-by: David Rientjes Cc: Christoph Lameter Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/vmalloc.h | 3 --- mm/vmalloc.c | 7 ------- 2 files changed, 10 deletions(-) (limited to 'include/linux/vmalloc.h') diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index 44b54f619ac6..cb73c755fac8 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -90,9 +90,6 @@ extern struct vm_struct *__get_vm_area_caller(unsigned long size, unsigned long flags, unsigned long start, unsigned long end, void *caller); -extern struct vm_struct *get_vm_area_node(unsigned long size, - unsigned long flags, int node, - gfp_t gfp_mask); extern struct vm_struct *remove_vm_area(const void *addr); extern int map_vm_area(struct vm_struct *area, pgprot_t prot, diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 48245af07b10..78ec9d8bc57c 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -1315,13 +1315,6 @@ struct vm_struct *get_vm_area_caller(unsigned long size, unsigned long flags, -1, GFP_KERNEL, caller); } -struct vm_struct *get_vm_area_node(unsigned long size, unsigned long flags, - int node, gfp_t gfp_mask) -{ - return __get_vm_area_node(size, 1, flags, VMALLOC_START, VMALLOC_END, - node, gfp_mask, __builtin_return_address(0)); -} - static struct vm_struct *find_vm_area(const void *addr) { struct vmap_area *va; -- cgit v1.2.3 From ec3f64fc9c196a304c4b7db3e1ff56d640628509 Mon Sep 17 00:00:00 2001 From: David Rientjes Date: Thu, 13 Jan 2011 15:46:01 -0800 Subject: mm: remove gfp mask from pcpu_get_vm_areas pcpu_get_vm_areas() only uses GFP_KERNEL allocations, so remove the gfp_t formal and use the mask internally. Signed-off-by: David Rientjes Cc: Christoph Lameter Cc: Tejun Heo Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/vmalloc.h | 2 +- mm/percpu-vm.c | 2 +- mm/vmalloc.c | 21 +++++++++------------ 3 files changed, 11 insertions(+), 14 deletions(-) (limited to 'include/linux/vmalloc.h') diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index cb73c755fac8..c7348b8d0a81 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -117,7 +117,7 @@ extern __init void vm_area_register_early(struct vm_struct *vm, size_t align); #ifdef CONFIG_SMP struct vm_struct **pcpu_get_vm_areas(const unsigned long *offsets, const size_t *sizes, int nr_vms, - size_t align, gfp_t gfp_mask); + size_t align); void pcpu_free_vm_areas(struct vm_struct **vms, int nr_vms); #endif diff --git a/mm/percpu-vm.c b/mm/percpu-vm.c index 7d9c1d0ebd3f..ea534960a04b 100644 --- a/mm/percpu-vm.c +++ b/mm/percpu-vm.c @@ -421,7 +421,7 @@ static struct pcpu_chunk *pcpu_create_chunk(void) return NULL; vms = pcpu_get_vm_areas(pcpu_group_offsets, pcpu_group_sizes, - pcpu_nr_groups, pcpu_atom_size, GFP_KERNEL); + pcpu_nr_groups, pcpu_atom_size); if (!vms) { pcpu_free_chunk(chunk); return NULL; diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 78ec9d8bc57c..f67546636322 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -2196,17 +2196,16 @@ static unsigned long pvm_determine_end(struct vmap_area **pnext, * @sizes: array containing size of each area * @nr_vms: the number of areas to allocate * @align: alignment, all entries in @offsets and @sizes must be aligned to this - * @gfp_mask: allocation mask * * Returns: kmalloc'd vm_struct pointer array pointing to allocated * vm_structs on success, %NULL on failure * * Percpu allocator wants to use congruent vm areas so that it can * maintain the offsets among percpu areas. This function allocates - * congruent vmalloc areas for it. These areas tend to be scattered - * pretty far, distance between two areas easily going up to - * gigabytes. To avoid interacting with regular vmallocs, these areas - * are allocated from top. + * congruent vmalloc areas for it with GFP_KERNEL. These areas tend to + * be scattered pretty far, distance between two areas easily going up + * to gigabytes. To avoid interacting with regular vmallocs, these + * areas are allocated from top. * * Despite its complicated look, this allocator is rather simple. It * does everything top-down and scans areas from the end looking for @@ -2217,7 +2216,7 @@ static unsigned long pvm_determine_end(struct vmap_area **pnext, */ struct vm_struct **pcpu_get_vm_areas(const unsigned long *offsets, const size_t *sizes, int nr_vms, - size_t align, gfp_t gfp_mask) + size_t align) { const unsigned long vmalloc_start = ALIGN(VMALLOC_START, align); const unsigned long vmalloc_end = VMALLOC_END & ~(align - 1); @@ -2227,8 +2226,6 @@ struct vm_struct **pcpu_get_vm_areas(const unsigned long *offsets, unsigned long base, start, end, last_end; bool purged = false; - gfp_mask &= GFP_RECLAIM_MASK; - /* verify parameters and allocate data structures */ BUG_ON(align & ~PAGE_MASK || !is_power_of_2(align)); for (last_area = 0, area = 0; area < nr_vms; area++) { @@ -2261,14 +2258,14 @@ struct vm_struct **pcpu_get_vm_areas(const unsigned long *offsets, return NULL; } - vms = kzalloc(sizeof(vms[0]) * nr_vms, gfp_mask); - vas = kzalloc(sizeof(vas[0]) * nr_vms, gfp_mask); + vms = kzalloc(sizeof(vms[0]) * nr_vms, GFP_KERNEL); + vas = kzalloc(sizeof(vas[0]) * nr_vms, GFP_KERNEL); if (!vas || !vms) goto err_free; for (area = 0; area < nr_vms; area++) { - vas[area] = kzalloc(sizeof(struct vmap_area), gfp_mask); - vms[area] = kzalloc(sizeof(struct vm_struct), gfp_mask); + vas[area] = kzalloc(sizeof(struct vmap_area), GFP_KERNEL); + vms[area] = kzalloc(sizeof(struct vm_struct), GFP_KERNEL); if (!vas[area] || !vms[area]) goto err_free; } -- cgit v1.2.3 From d0a21265dfb5fa8ae54e90d0fb6d1c215b10a28a Mon Sep 17 00:00:00 2001 From: David Rientjes Date: Thu, 13 Jan 2011 15:46:02 -0800 Subject: mm: unify module_alloc code for vmalloc Four architectures (arm, mips, sparc, x86) use __vmalloc_area() for module_init(). Much of the code is duplicated and can be generalized in a globally accessible function, __vmalloc_node_range(). __vmalloc_node() now calls into __vmalloc_node_range() with a range of [VMALLOC_START, VMALLOC_END) for functionally equivalent behavior. Each architecture may then use __vmalloc_node_range() directly to remove the duplication of code. Signed-off-by: David Rientjes Cc: Christoph Lameter Cc: Russell King Cc: Ralf Baechle Cc: "David S. Miller" Cc: Ingo Molnar Cc: "H. Peter Anvin" Cc: Thomas Gleixner Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/arm/kernel/module.c | 14 +++---------- arch/mips/kernel/module.c | 14 +++---------- arch/sparc/kernel/module.c | 14 ++++--------- arch/x86/kernel/module.c | 17 ++++------------ include/linux/vmalloc.h | 5 +++-- mm/vmalloc.c | 50 +++++++++++++++++++++++++++------------------- 6 files changed, 46 insertions(+), 68 deletions(-) (limited to 'include/linux/vmalloc.h') diff --git a/arch/arm/kernel/module.c b/arch/arm/kernel/module.c index 0c1bb68ff4a8..2cfe8161b478 100644 --- a/arch/arm/kernel/module.c +++ b/arch/arm/kernel/module.c @@ -38,17 +38,9 @@ #ifdef CONFIG_MMU void *module_alloc(unsigned long size) { - struct vm_struct *area; - - size = PAGE_ALIGN(size); - if (!size) - return NULL; - - area = __get_vm_area(size, VM_ALLOC, MODULES_VADDR, MODULES_END); - if (!area) - return NULL; - - return __vmalloc_area(area, GFP_KERNEL, PAGE_KERNEL_EXEC); + return __vmalloc_node_range(size, 1, MODULES_VADDR, MODULES_END, + GFP_KERNEL, PAGE_KERNEL_EXEC, -1, + __builtin_return_address(0)); } #else /* CONFIG_MMU */ void *module_alloc(unsigned long size) diff --git a/arch/mips/kernel/module.c b/arch/mips/kernel/module.c index 6f51dda87fce..d87a72e9fac7 100644 --- a/arch/mips/kernel/module.c +++ b/arch/mips/kernel/module.c @@ -46,17 +46,9 @@ static DEFINE_SPINLOCK(dbe_lock); void *module_alloc(unsigned long size) { #ifdef MODULE_START - struct vm_struct *area; - - size = PAGE_ALIGN(size); - if (!size) - return NULL; - - area = __get_vm_area(size, VM_ALLOC, MODULE_START, MODULE_END); - if (!area) - return NULL; - - return __vmalloc_area(area, GFP_KERNEL, PAGE_KERNEL); + return __vmalloc_node_range(size, 1, MODULE_START, MODULE_END, + GFP_KERNEL, PAGE_KERNEL, -1, + __builtin_return_address(0)); #else if (size == 0) return NULL; diff --git a/arch/sparc/kernel/module.c b/arch/sparc/kernel/module.c index ee3c7dde8d9f..8d348c474a2f 100644 --- a/arch/sparc/kernel/module.c +++ b/arch/sparc/kernel/module.c @@ -23,17 +23,11 @@ static void *module_map(unsigned long size) { - struct vm_struct *area; - - size = PAGE_ALIGN(size); - if (!size || size > MODULES_LEN) - return NULL; - - area = __get_vm_area(size, VM_ALLOC, MODULES_VADDR, MODULES_END); - if (!area) + if (PAGE_ALIGN(size) > MODULES_LEN) return NULL; - - return __vmalloc_area(area, GFP_KERNEL, PAGE_KERNEL); + return __vmalloc_node_range(size, 1, MODULES_VADDR, MODULES_END, + GFP_KERNEL, PAGE_KERNEL, -1, + __builtin_return_address(0)); } static char *dot2underscore(char *name) diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c index 8f2956091735..ab23f1ad4bf1 100644 --- a/arch/x86/kernel/module.c +++ b/arch/x86/kernel/module.c @@ -37,20 +37,11 @@ void *module_alloc(unsigned long size) { - struct vm_struct *area; - - if (!size) - return NULL; - size = PAGE_ALIGN(size); - if (size > MODULES_LEN) + if (PAGE_ALIGN(size) > MODULES_LEN) return NULL; - - area = __get_vm_area(size, VM_ALLOC, MODULES_VADDR, MODULES_END); - if (!area) - return NULL; - - return __vmalloc_area(area, GFP_KERNEL | __GFP_HIGHMEM, - PAGE_KERNEL_EXEC); + return __vmalloc_node_range(size, 1, MODULES_VADDR, MODULES_END, + GFP_KERNEL | __GFP_HIGHMEM, PAGE_KERNEL_EXEC, + -1, __builtin_return_address(0)); } /* Free memory returned from module_alloc */ diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h index c7348b8d0a81..4ed6fcd6b726 100644 --- a/include/linux/vmalloc.h +++ b/include/linux/vmalloc.h @@ -59,8 +59,9 @@ extern void *vmalloc_exec(unsigned long size); extern void *vmalloc_32(unsigned long size); extern void *vmalloc_32_user(unsigned long size); extern void *__vmalloc(unsigned long size, gfp_t gfp_mask, pgprot_t prot); -extern void *__vmalloc_area(struct vm_struct *area, gfp_t gfp_mask, - pgprot_t prot); +extern void *__vmalloc_node_range(unsigned long size, unsigned long align, + unsigned long start, unsigned long end, gfp_t gfp_mask, + pgprot_t prot, int node, void *caller); extern void vfree(const void *addr); extern void *vmap(struct page **pages, unsigned int count, diff --git a/mm/vmalloc.c b/mm/vmalloc.c index f67546636322..284346ee0e91 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -1530,25 +1530,12 @@ fail: return NULL; } -void *__vmalloc_area(struct vm_struct *area, gfp_t gfp_mask, pgprot_t prot) -{ - void *addr = __vmalloc_area_node(area, gfp_mask, prot, -1, - __builtin_return_address(0)); - - /* - * A ref_count = 3 is needed because the vm_struct and vmap_area - * structures allocated in the __get_vm_area_node() function contain - * references to the virtual address of the vmalloc'ed block. - */ - kmemleak_alloc(addr, area->size - PAGE_SIZE, 3, gfp_mask); - - return addr; -} - /** - * __vmalloc_node - allocate virtually contiguous memory + * __vmalloc_node_range - allocate virtually contiguous memory * @size: allocation size * @align: desired alignment + * @start: vm area range start + * @end: vm area range end * @gfp_mask: flags for the page level allocator * @prot: protection mask for the allocated pages * @node: node to use for allocation or -1 @@ -1558,9 +1545,9 @@ void *__vmalloc_area(struct vm_struct *area, gfp_t gfp_mask, pgprot_t prot) * allocator with @gfp_mask flags. Map them into contiguous * kernel virtual space, using a pagetable protection of @prot. */ -static void *__vmalloc_node(unsigned long size, unsigned long align, - gfp_t gfp_mask, pgprot_t prot, - int node, void *caller) +void *__vmalloc_node_range(unsigned long size, unsigned long align, + unsigned long start, unsigned long end, gfp_t gfp_mask, + pgprot_t prot, int node, void *caller) { struct vm_struct *area; void *addr; @@ -1570,8 +1557,8 @@ static void *__vmalloc_node(unsigned long size, unsigned long align, if (!size || (size >> PAGE_SHIFT) > totalram_pages) return NULL; - area = __get_vm_area_node(size, align, VM_ALLOC, VMALLOC_START, - VMALLOC_END, node, gfp_mask, caller); + area = __get_vm_area_node(size, align, VM_ALLOC, start, end, node, + gfp_mask, caller); if (!area) return NULL; @@ -1588,6 +1575,27 @@ static void *__vmalloc_node(unsigned long size, unsigned long align, return addr; } +/** + * __vmalloc_node - allocate virtually contiguous memory + * @size: allocation size + * @align: desired alignment + * @gfp_mask: flags for the page level allocator + * @prot: protection mask for the allocated pages + * @node: node to use for allocation or -1 + * @caller: caller's return address + * + * Allocate enough pages to cover @size from the page level + * allocator with @gfp_mask flags. Map them into contiguous + * kernel virtual space, using a pagetable protection of @prot. + */ +static void *__vmalloc_node(unsigned long size, unsigned long align, + gfp_t gfp_mask, pgprot_t prot, + int node, void *caller) +{ + return __vmalloc_node_range(size, align, VMALLOC_START, VMALLOC_END, + gfp_mask, prot, node, caller); +} + void *__vmalloc(unsigned long size, gfp_t gfp_mask, pgprot_t prot) { return __vmalloc_node(size, 1, gfp_mask, prot, -1, -- cgit v1.2.3