linux/mm/util.c

642 lines
16 KiB
C
Raw Normal View History

#include <linux/mm.h>
#include <linux/slab.h>
#include <linux/string.h>
#include <linux/compiler.h>
#include <linux/export.h>
#include <linux/err.h>
#include <linux/sched.h>
#include <linux/security.h>
#include <linux/swap.h>
#include <linux/swapops.h>
#include <linux/mman.h>
#include <linux/hugetlb.h>
#include <linux/vmalloc.h>
mm/util: add kstrdup_const kstrdup() is often used to duplicate strings where neither source neither destination will be ever modified. In such case we can just reuse the source instead of duplicating it. The problem is that we must be sure that the source is non-modifiable and its life-time is long enough. I suspect the good candidates for such strings are strings located in kernel .rodata section, they cannot be modifed because the section is read-only and their life-time is equal to kernel life-time. This small patchset proposes alternative version of kstrdup - kstrdup_const, which returns source string if it is located in .rodata otherwise it fallbacks to kstrdup. To verify if the source is in .rodata function checks if the address is between sentinels __start_rodata, __end_rodata. I guess it should work with all architectures. The main patch is accompanied by four patches constifying kstrdup for cases where situtation described above happens frequently. I have tested the patchset on mobile platform (exynos4210-trats) and it saves 3272 string allocations. Since minimal allocation is 32 or 64 bytes depending on Kconfig options the patchset saves respectively about 100KB or 200KB of memory. Stats from tested platform show that the main offender is sysfs: By caller: 2260 __kernfs_new_node 631 clk_register+0xc8/0x1b8 318 clk_register+0x34/0x1b8 51 kmem_cache_create 12 alloc_vfsmnt By string (with count >= 5): 883 power 876 subsystem 135 parameters 132 device 61 iommu_group ... This patch (of 5): Add an alternative version of kstrdup which returns pointer to constant char array. The function checks if input string is in persistent and read-only memory section, if yes it returns the input string, otherwise it fallbacks to kstrdup. kstrdup_const is accompanied by kfree_const performing conditional memory deallocation of the string. Signed-off-by: Andrzej Hajda <a.hajda@samsung.com> Cc: Marek Szyprowski <m.szyprowski@samsung.com> Cc: Kyungmin Park <kyungmin.park@samsung.com> Cc: Mike Turquette <mturquette@linaro.org> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Christoph Lameter <cl@linux.com> Cc: Pekka Enberg <penberg@kernel.org> Cc: David Rientjes <rientjes@google.com> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Tejun Heo <tj@kernel.org> Cc: Greg KH <greg@kroah.com> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-02-13 22:36:24 +00:00
#include <asm/sections.h>
#include <asm/uaccess.h>
mm: nommu: sort mm->mmap list properly When I was reading nommu code, I found that it handles the vma list/tree in an unusual way. IIUC, because there can be more than one identical/overrapped vmas in the list/tree, it sorts the tree more strictly and does a linear search on the tree. But it doesn't applied to the list (i.e. the list could be constructed in a different order than the tree so that we can't use the list when finding the first vma in that order). Since inserting/sorting a vma in the tree and link is done at the same time, we can easily construct both of them in the same order. And linear searching on the tree could be more costly than doing it on the list, it can be converted to use the list. Also, after the commit 297c5eee3724 ("mm: make the vma list be doubly linked") made the list be doubly linked, there were a couple of code need to be fixed to construct the list properly. Patch 1/6 is a preparation. It maintains the list sorted same as the tree and construct doubly-linked list properly. Patch 2/6 is a simple optimization for the vma deletion. Patch 3/6 and 4/6 convert tree traversal to list traversal and the rest are simple fixes and cleanups. This patch: @vma added into @mm should be sorted by start addr, end addr and VMA struct addr in that order because we may get identical VMAs in the @mm. However this was true only for the rbtree, not for the list. This patch fixes this by remembering 'rb_prev' during the tree traversal like find_vma_prepare() does and linking the @vma via __vma_link_list(). After this patch, we can iterate the whole VMAs in correct order simply by using @mm->mmap list. [akpm@linux-foundation.org: avoid duplicating __vma_link_list()] Signed-off-by: Namhyung Kim <namhyung@gmail.com> Acked-by: Greg Ungerer <gerg@uclinux.org> Cc: David Howells <dhowells@redhat.com> Cc: Paul Mundt <lethal@linux-sh.org> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-05-25 00:11:22 +00:00
#include "internal.h"
mm/util: add kstrdup_const kstrdup() is often used to duplicate strings where neither source neither destination will be ever modified. In such case we can just reuse the source instead of duplicating it. The problem is that we must be sure that the source is non-modifiable and its life-time is long enough. I suspect the good candidates for such strings are strings located in kernel .rodata section, they cannot be modifed because the section is read-only and their life-time is equal to kernel life-time. This small patchset proposes alternative version of kstrdup - kstrdup_const, which returns source string if it is located in .rodata otherwise it fallbacks to kstrdup. To verify if the source is in .rodata function checks if the address is between sentinels __start_rodata, __end_rodata. I guess it should work with all architectures. The main patch is accompanied by four patches constifying kstrdup for cases where situtation described above happens frequently. I have tested the patchset on mobile platform (exynos4210-trats) and it saves 3272 string allocations. Since minimal allocation is 32 or 64 bytes depending on Kconfig options the patchset saves respectively about 100KB or 200KB of memory. Stats from tested platform show that the main offender is sysfs: By caller: 2260 __kernfs_new_node 631 clk_register+0xc8/0x1b8 318 clk_register+0x34/0x1b8 51 kmem_cache_create 12 alloc_vfsmnt By string (with count >= 5): 883 power 876 subsystem 135 parameters 132 device 61 iommu_group ... This patch (of 5): Add an alternative version of kstrdup which returns pointer to constant char array. The function checks if input string is in persistent and read-only memory section, if yes it returns the input string, otherwise it fallbacks to kstrdup. kstrdup_const is accompanied by kfree_const performing conditional memory deallocation of the string. Signed-off-by: Andrzej Hajda <a.hajda@samsung.com> Cc: Marek Szyprowski <m.szyprowski@samsung.com> Cc: Kyungmin Park <kyungmin.park@samsung.com> Cc: Mike Turquette <mturquette@linaro.org> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Christoph Lameter <cl@linux.com> Cc: Pekka Enberg <penberg@kernel.org> Cc: David Rientjes <rientjes@google.com> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Tejun Heo <tj@kernel.org> Cc: Greg KH <greg@kroah.com> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-02-13 22:36:24 +00:00
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
*
* Function calls kfree only if @x is not in .rodata section.
*/
void kfree_const(const void *x)
{
if (!is_kernel_rodata((unsigned long)x))
kfree(x);
}
EXPORT_SYMBOL(kfree_const);
/**
* kstrdup - allocate space for and copy an existing string
* @s: the string to duplicate
* @gfp: the GFP mask used in the kmalloc() call when allocating memory
*/
char *kstrdup(const char *s, gfp_t gfp)
{
size_t len;
char *buf;
if (!s)
return NULL;
len = strlen(s) + 1;
buf = kmalloc_track_caller(len, gfp);
if (buf)
memcpy(buf, s, len);
return buf;
}
EXPORT_SYMBOL(kstrdup);
mm/util: add kstrdup_const kstrdup() is often used to duplicate strings where neither source neither destination will be ever modified. In such case we can just reuse the source instead of duplicating it. The problem is that we must be sure that the source is non-modifiable and its life-time is long enough. I suspect the good candidates for such strings are strings located in kernel .rodata section, they cannot be modifed because the section is read-only and their life-time is equal to kernel life-time. This small patchset proposes alternative version of kstrdup - kstrdup_const, which returns source string if it is located in .rodata otherwise it fallbacks to kstrdup. To verify if the source is in .rodata function checks if the address is between sentinels __start_rodata, __end_rodata. I guess it should work with all architectures. The main patch is accompanied by four patches constifying kstrdup for cases where situtation described above happens frequently. I have tested the patchset on mobile platform (exynos4210-trats) and it saves 3272 string allocations. Since minimal allocation is 32 or 64 bytes depending on Kconfig options the patchset saves respectively about 100KB or 200KB of memory. Stats from tested platform show that the main offender is sysfs: By caller: 2260 __kernfs_new_node 631 clk_register+0xc8/0x1b8 318 clk_register+0x34/0x1b8 51 kmem_cache_create 12 alloc_vfsmnt By string (with count >= 5): 883 power 876 subsystem 135 parameters 132 device 61 iommu_group ... This patch (of 5): Add an alternative version of kstrdup which returns pointer to constant char array. The function checks if input string is in persistent and read-only memory section, if yes it returns the input string, otherwise it fallbacks to kstrdup. kstrdup_const is accompanied by kfree_const performing conditional memory deallocation of the string. Signed-off-by: Andrzej Hajda <a.hajda@samsung.com> Cc: Marek Szyprowski <m.szyprowski@samsung.com> Cc: Kyungmin Park <kyungmin.park@samsung.com> Cc: Mike Turquette <mturquette@linaro.org> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Christoph Lameter <cl@linux.com> Cc: Pekka Enberg <penberg@kernel.org> Cc: David Rientjes <rientjes@google.com> Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Tejun Heo <tj@kernel.org> Cc: Greg KH <greg@kroah.com> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2015-02-13 22:36:24 +00:00
/**
* kstrdup_const - conditionally duplicate an existing const string
* @s: the string to duplicate
* @gfp: the GFP mask used in the kmalloc() call when allocating memory
*
* Function returns source string if it is in .rodata section otherwise it
* fallbacks to kstrdup.
* Strings allocated by kstrdup_const should be freed by kfree_const.
*/
const char *kstrdup_const(const char *s, gfp_t gfp)
{
if (is_kernel_rodata((unsigned long)s))
return s;
return kstrdup(s, gfp);
}
EXPORT_SYMBOL(kstrdup_const);
/**
* kstrndup - allocate space for and copy an existing string
* @s: the string to duplicate
* @max: read at most @max chars from @s
* @gfp: the GFP mask used in the kmalloc() call when allocating memory
*/
char *kstrndup(const char *s, size_t max, gfp_t gfp)
{
size_t len;
char *buf;
if (!s)
return NULL;
len = strnlen(s, max);
buf = kmalloc_track_caller(len+1, gfp);
if (buf) {
memcpy(buf, s, len);
buf[len] = '\0';
}
return buf;
}
EXPORT_SYMBOL(kstrndup);
/**
* kmemdup - duplicate region of memory
*
* @src: memory region to duplicate
* @len: memory region length
* @gfp: GFP mask to use
*/
void *kmemdup(const void *src, size_t len, gfp_t gfp)
{
void *p;
p = kmalloc_track_caller(len, gfp);
if (p)
memcpy(p, src, len);
return p;
}
EXPORT_SYMBOL(kmemdup);
/**
* memdup_user - duplicate memory region from user space
*
* @src: source address in user space
* @len: number of bytes to copy
*
* Returns an ERR_PTR() on failure.
*/
void *memdup_user(const void __user *src, size_t len)
{
void *p;
/*
* Always use GFP_KERNEL, since copy_from_user() can sleep and
* cause pagefault, which makes it pointless to use GFP_NOFS
* or GFP_ATOMIC.
*/
p = kmalloc_track_caller(len, GFP_KERNEL);
if (!p)
return ERR_PTR(-ENOMEM);
if (copy_from_user(p, src, len)) {
kfree(p);
return ERR_PTR(-EFAULT);
}
return p;
}
EXPORT_SYMBOL(memdup_user);
/*
* strndup_user - duplicate an existing string from user space
* @s: The string to duplicate
* @n: Maximum number of bytes to copy, including the trailing NUL.
*/
char *strndup_user(const char __user *s, long n)
{
char *p;
long length;
length = strnlen_user(s, n);
if (!length)
return ERR_PTR(-EFAULT);
if (length > n)
return ERR_PTR(-EINVAL);
p = memdup_user(s, length);
if (IS_ERR(p))
return p;
p[length - 1] = '\0';
return p;
}
EXPORT_SYMBOL(strndup_user);
/**
* memdup_user_nul - duplicate memory region from user space and NUL-terminate
*
* @src: source address in user space
* @len: number of bytes to copy
*
* Returns an ERR_PTR() on failure.
*/
void *memdup_user_nul(const void __user *src, size_t len)
{
char *p;
/*
* Always use GFP_KERNEL, since copy_from_user() can sleep and
* cause pagefault, which makes it pointless to use GFP_NOFS
* or GFP_ATOMIC.
*/
p = kmalloc_track_caller(len + 1, GFP_KERNEL);
if (!p)
return ERR_PTR(-ENOMEM);
if (copy_from_user(p, src, len)) {
kfree(p);
return ERR_PTR(-EFAULT);
}
p[len] = '\0';
return p;
}
EXPORT_SYMBOL(memdup_user_nul);
mm: nommu: sort mm->mmap list properly When I was reading nommu code, I found that it handles the vma list/tree in an unusual way. IIUC, because there can be more than one identical/overrapped vmas in the list/tree, it sorts the tree more strictly and does a linear search on the tree. But it doesn't applied to the list (i.e. the list could be constructed in a different order than the tree so that we can't use the list when finding the first vma in that order). Since inserting/sorting a vma in the tree and link is done at the same time, we can easily construct both of them in the same order. And linear searching on the tree could be more costly than doing it on the list, it can be converted to use the list. Also, after the commit 297c5eee3724 ("mm: make the vma list be doubly linked") made the list be doubly linked, there were a couple of code need to be fixed to construct the list properly. Patch 1/6 is a preparation. It maintains the list sorted same as the tree and construct doubly-linked list properly. Patch 2/6 is a simple optimization for the vma deletion. Patch 3/6 and 4/6 convert tree traversal to list traversal and the rest are simple fixes and cleanups. This patch: @vma added into @mm should be sorted by start addr, end addr and VMA struct addr in that order because we may get identical VMAs in the @mm. However this was true only for the rbtree, not for the list. This patch fixes this by remembering 'rb_prev' during the tree traversal like find_vma_prepare() does and linking the @vma via __vma_link_list(). After this patch, we can iterate the whole VMAs in correct order simply by using @mm->mmap list. [akpm@linux-foundation.org: avoid duplicating __vma_link_list()] Signed-off-by: Namhyung Kim <namhyung@gmail.com> Acked-by: Greg Ungerer <gerg@uclinux.org> Cc: David Howells <dhowells@redhat.com> Cc: Paul Mundt <lethal@linux-sh.org> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2011-05-25 00:11:22 +00:00
void __vma_link_list(struct mm_struct *mm, struct vm_area_struct *vma,
struct vm_area_struct *prev, struct rb_node *rb_parent)
{
struct vm_area_struct *next;
vma->vm_prev = prev;
if (prev) {
next = prev->vm_next;
prev->vm_next = vma;
} else {
mm->mmap = vma;
if (rb_parent)
next = rb_entry(rb_parent,
struct vm_area_struct, vm_rb);
else
next = NULL;
}
vma->vm_next = next;
if (next)
next->vm_prev = vma;
}
procfs: mark thread stack correctly in proc/<pid>/maps Stack for a new thread is mapped by userspace code and passed via sys_clone. This memory is currently seen as anonymous in /proc/<pid>/maps, which makes it difficult to ascertain which mappings are being used for thread stacks. This patch uses the individual task stack pointers to determine which vmas are actually thread stacks. For a multithreaded program like the following: #include <pthread.h> void *thread_main(void *foo) { while(1); } int main() { pthread_t t; pthread_create(&t, NULL, thread_main, NULL); pthread_join(t, NULL); } proc/PID/maps looks like the following: 00400000-00401000 r-xp 00000000 fd:0a 3671804 /home/siddhesh/a.out 00600000-00601000 rw-p 00000000 fd:0a 3671804 /home/siddhesh/a.out 019ef000-01a10000 rw-p 00000000 00:00 0 [heap] 7f8a44491000-7f8a44492000 ---p 00000000 00:00 0 7f8a44492000-7f8a44c92000 rw-p 00000000 00:00 0 7f8a44c92000-7f8a44e3d000 r-xp 00000000 fd:00 2097482 /lib64/libc-2.14.90.so 7f8a44e3d000-7f8a4503d000 ---p 001ab000 fd:00 2097482 /lib64/libc-2.14.90.so 7f8a4503d000-7f8a45041000 r--p 001ab000 fd:00 2097482 /lib64/libc-2.14.90.so 7f8a45041000-7f8a45043000 rw-p 001af000 fd:00 2097482 /lib64/libc-2.14.90.so 7f8a45043000-7f8a45048000 rw-p 00000000 00:00 0 7f8a45048000-7f8a4505f000 r-xp 00000000 fd:00 2099938 /lib64/libpthread-2.14.90.so 7f8a4505f000-7f8a4525e000 ---p 00017000 fd:00 2099938 /lib64/libpthread-2.14.90.so 7f8a4525e000-7f8a4525f000 r--p 00016000 fd:00 2099938 /lib64/libpthread-2.14.90.so 7f8a4525f000-7f8a45260000 rw-p 00017000 fd:00 2099938 /lib64/libpthread-2.14.90.so 7f8a45260000-7f8a45264000 rw-p 00000000 00:00 0 7f8a45264000-7f8a45286000 r-xp 00000000 fd:00 2097348 /lib64/ld-2.14.90.so 7f8a45457000-7f8a4545a000 rw-p 00000000 00:00 0 7f8a45484000-7f8a45485000 rw-p 00000000 00:00 0 7f8a45485000-7f8a45486000 r--p 00021000 fd:00 2097348 /lib64/ld-2.14.90.so 7f8a45486000-7f8a45487000 rw-p 00022000 fd:00 2097348 /lib64/ld-2.14.90.so 7f8a45487000-7f8a45488000 rw-p 00000000 00:00 0 7fff6273b000-7fff6275c000 rw-p 00000000 00:00 0 [stack] 7fff627ff000-7fff62800000 r-xp 00000000 00:00 0 [vdso] ffffffffff600000-ffffffffff601000 r-xp 00000000 00:00 0 [vsyscall] Here, one could guess that 7f8a44492000-7f8a44c92000 is a stack since the earlier vma that has no permissions (7f8a44e3d000-7f8a4503d000) but that is not always a reliable way to find out which vma is a thread stack. Also, /proc/PID/maps and /proc/PID/task/TID/maps has the same content. With this patch in place, /proc/PID/task/TID/maps are treated as 'maps as the task would see it' and hence, only the vma that that task uses as stack is marked as [stack]. All other 'stack' vmas are marked as anonymous memory. /proc/PID/maps acts as a thread group level view, where all thread stack vmas are marked as [stack:TID] where TID is the process ID of the task that uses that vma as stack, while the process stack is marked as [stack]. So /proc/PID/maps will look like this: 00400000-00401000 r-xp 00000000 fd:0a 3671804 /home/siddhesh/a.out 00600000-00601000 rw-p 00000000 fd:0a 3671804 /home/siddhesh/a.out 019ef000-01a10000 rw-p 00000000 00:00 0 [heap] 7f8a44491000-7f8a44492000 ---p 00000000 00:00 0 7f8a44492000-7f8a44c92000 rw-p 00000000 00:00 0 [stack:1442] 7f8a44c92000-7f8a44e3d000 r-xp 00000000 fd:00 2097482 /lib64/libc-2.14.90.so 7f8a44e3d000-7f8a4503d000 ---p 001ab000 fd:00 2097482 /lib64/libc-2.14.90.so 7f8a4503d000-7f8a45041000 r--p 001ab000 fd:00 2097482 /lib64/libc-2.14.90.so 7f8a45041000-7f8a45043000 rw-p 001af000 fd:00 2097482 /lib64/libc-2.14.90.so 7f8a45043000-7f8a45048000 rw-p 00000000 00:00 0 7f8a45048000-7f8a4505f000 r-xp 00000000 fd:00 2099938 /lib64/libpthread-2.14.90.so 7f8a4505f000-7f8a4525e000 ---p 00017000 fd:00 2099938 /lib64/libpthread-2.14.90.so 7f8a4525e000-7f8a4525f000 r--p 00016000 fd:00 2099938 /lib64/libpthread-2.14.90.so 7f8a4525f000-7f8a45260000 rw-p 00017000 fd:00 2099938 /lib64/libpthread-2.14.90.so 7f8a45260000-7f8a45264000 rw-p 00000000 00:00 0 7f8a45264000-7f8a45286000 r-xp 00000000 fd:00 2097348 /lib64/ld-2.14.90.so 7f8a45457000-7f8a4545a000 rw-p 00000000 00:00 0 7f8a45484000-7f8a45485000 rw-p 00000000 00:00 0 7f8a45485000-7f8a45486000 r--p 00021000 fd:00 2097348 /lib64/ld-2.14.90.so 7f8a45486000-7f8a45487000 rw-p 00022000 fd:00 2097348 /lib64/ld-2.14.90.so 7f8a45487000-7f8a45488000 rw-p 00000000 00:00 0 7fff6273b000-7fff6275c000 rw-p 00000000 00:00 0 [stack] 7fff627ff000-7fff62800000 r-xp 00000000 00:00 0 [vdso] ffffffffff600000-ffffffffff601000 r-xp 00000000 00:00 0 [vsyscall] Thus marking all vmas that are used as stacks by the threads in the thread group along with the process stack. The task level maps will however like this: 00400000-00401000 r-xp 00000000 fd:0a 3671804 /home/siddhesh/a.out 00600000-00601000 rw-p 00000000 fd:0a 3671804 /home/siddhesh/a.out 019ef000-01a10000 rw-p 00000000 00:00 0 [heap] 7f8a44491000-7f8a44492000 ---p 00000000 00:00 0 7f8a44492000-7f8a44c92000 rw-p 00000000 00:00 0 [stack] 7f8a44c92000-7f8a44e3d000 r-xp 00000000 fd:00 2097482 /lib64/libc-2.14.90.so 7f8a44e3d000-7f8a4503d000 ---p 001ab000 fd:00 2097482 /lib64/libc-2.14.90.so 7f8a4503d000-7f8a45041000 r--p 001ab000 fd:00 2097482 /lib64/libc-2.14.90.so 7f8a45041000-7f8a45043000 rw-p 001af000 fd:00 2097482 /lib64/libc-2.14.90.so 7f8a45043000-7f8a45048000 rw-p 00000000 00:00 0 7f8a45048000-7f8a4505f000 r-xp 00000000 fd:00 2099938 /lib64/libpthread-2.14.90.so 7f8a4505f000-7f8a4525e000 ---p 00017000 fd:00 2099938 /lib64/libpthread-2.14.90.so 7f8a4525e000-7f8a4525f000 r--p 00016000 fd:00 2099938 /lib64/libpthread-2.14.90.so 7f8a4525f000-7f8a45260000 rw-p 00017000 fd:00 2099938 /lib64/libpthread-2.14.90.so 7f8a45260000-7f8a45264000 rw-p 00000000 00:00 0 7f8a45264000-7f8a45286000 r-xp 00000000 fd:00 2097348 /lib64/ld-2.14.90.so 7f8a45457000-7f8a4545a000 rw-p 00000000 00:00 0 7f8a45484000-7f8a45485000 rw-p 00000000 00:00 0 7f8a45485000-7f8a45486000 r--p 00021000 fd:00 2097348 /lib64/ld-2.14.90.so 7f8a45486000-7f8a45487000 rw-p 00022000 fd:00 2097348 /lib64/ld-2.14.90.so 7f8a45487000-7f8a45488000 rw-p 00000000 00:00 0 7fff6273b000-7fff6275c000 rw-p 00000000 00:00 0 7fff627ff000-7fff62800000 r-xp 00000000 00:00 0 [vdso] ffffffffff600000-ffffffffff601000 r-xp 00000000 00:00 0 [vsyscall] where only the vma that is being used as a stack by *that* task is marked as [stack]. Analogous changes have been made to /proc/PID/smaps, /proc/PID/numa_maps, /proc/PID/task/TID/smaps and /proc/PID/task/TID/numa_maps. Relevant snippets from smaps and numa_maps: [siddhesh@localhost ~ ]$ pgrep a.out 1441 [siddhesh@localhost ~ ]$ cat /proc/1441/smaps | grep "\[stack" 7f8a44492000-7f8a44c92000 rw-p 00000000 00:00 0 [stack:1442] 7fff6273b000-7fff6275c000 rw-p 00000000 00:00 0 [stack] [siddhesh@localhost ~ ]$ cat /proc/1441/task/1442/smaps | grep "\[stack" 7f8a44492000-7f8a44c92000 rw-p 00000000 00:00 0 [stack] [siddhesh@localhost ~ ]$ cat /proc/1441/task/1441/smaps | grep "\[stack" 7fff6273b000-7fff6275c000 rw-p 00000000 00:00 0 [stack] [siddhesh@localhost ~ ]$ cat /proc/1441/numa_maps | grep "stack" 7f8a44492000 default stack:1442 anon=2 dirty=2 N0=2 7fff6273a000 default stack anon=3 dirty=3 N0=3 [siddhesh@localhost ~ ]$ cat /proc/1441/task/1442/numa_maps | grep "stack" 7f8a44492000 default stack anon=2 dirty=2 N0=2 [siddhesh@localhost ~ ]$ cat /proc/1441/task/1441/numa_maps | grep "stack" 7fff6273a000 default stack anon=3 dirty=3 N0=3 [akpm@linux-foundation.org: checkpatch fixes] [akpm@linux-foundation.org: fix build] Signed-off-by: Siddhesh Poyarekar <siddhesh.poyarekar@gmail.com> Cc: KOSAKI Motohiro <kosaki.motohiro@gmail.com> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Jamie Lokier <jamie@shareable.org> Cc: Mike Frysinger <vapier@gentoo.org> Cc: Alexey Dobriyan <adobriyan@gmail.com> Cc: Matt Mackall <mpm@selenic.com> Cc: Oleg Nesterov <oleg@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-03-21 23:34:04 +00:00
/* Check if the vma is being used as a stack by this task */
proc: revert /proc/<pid>/maps [stack:TID] annotation Commit b76437579d13 ("procfs: mark thread stack correctly in proc/<pid>/maps") added [stack:TID] annotation to /proc/<pid>/maps. Finding the task of a stack VMA requires walking the entire thread list, turning this into quadratic behavior: a thousand threads means a thousand stacks, so the rendering of /proc/<pid>/maps needs to look at a million combinations. The cost is not in proportion to the usefulness as described in the patch. Drop the [stack:TID] annotation to make /proc/<pid>/maps (and /proc/<pid>/numa_maps) usable again for higher thread counts. The [stack] annotation inside /proc/<pid>/task/<tid>/maps is retained, as identifying the stack VMA there is an O(1) operation. Siddesh said: "The end users needed a way to identify thread stacks programmatically and there wasn't a way to do that. I'm afraid I no longer remember (or have access to the resources that would aid my memory since I changed employers) the details of their requirement. However, I did do this on my own time because I thought it was an interesting project for me and nobody really gave any feedback then as to its utility, so as far as I am concerned you could roll back the main thread maps information since the information is available in the thread-specific files" Signed-off-by: Johannes Weiner <hannes@cmpxchg.org> Cc: "Kirill A. Shutemov" <kirill@shutemov.name> Cc: Siddhesh Poyarekar <siddhesh.poyarekar@gmail.com> Cc: Shaohua Li <shli@fb.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2016-02-03 00:57:29 +00:00
int vma_is_stack_for_task(struct vm_area_struct *vma, struct task_struct *t)
procfs: mark thread stack correctly in proc/<pid>/maps Stack for a new thread is mapped by userspace code and passed via sys_clone. This memory is currently seen as anonymous in /proc/<pid>/maps, which makes it difficult to ascertain which mappings are being used for thread stacks. This patch uses the individual task stack pointers to determine which vmas are actually thread stacks. For a multithreaded program like the following: #include <pthread.h> void *thread_main(void *foo) { while(1); } int main() { pthread_t t; pthread_create(&t, NULL, thread_main, NULL); pthread_join(t, NULL); } proc/PID/maps looks like the following: 00400000-00401000 r-xp 00000000 fd:0a 3671804 /home/siddhesh/a.out 00600000-00601000 rw-p 00000000 fd:0a 3671804 /home/siddhesh/a.out 019ef000-01a10000 rw-p 00000000 00:00 0 [heap] 7f8a44491000-7f8a44492000 ---p 00000000 00:00 0 7f8a44492000-7f8a44c92000 rw-p 00000000 00:00 0 7f8a44c92000-7f8a44e3d000 r-xp 00000000 fd:00 2097482 /lib64/libc-2.14.90.so 7f8a44e3d000-7f8a4503d000 ---p 001ab000 fd:00 2097482 /lib64/libc-2.14.90.so 7f8a4503d000-7f8a45041000 r--p 001ab000 fd:00 2097482 /lib64/libc-2.14.90.so 7f8a45041000-7f8a45043000 rw-p 001af000 fd:00 2097482 /lib64/libc-2.14.90.so 7f8a45043000-7f8a45048000 rw-p 00000000 00:00 0 7f8a45048000-7f8a4505f000 r-xp 00000000 fd:00 2099938 /lib64/libpthread-2.14.90.so 7f8a4505f000-7f8a4525e000 ---p 00017000 fd:00 2099938 /lib64/libpthread-2.14.90.so 7f8a4525e000-7f8a4525f000 r--p 00016000 fd:00 2099938 /lib64/libpthread-2.14.90.so 7f8a4525f000-7f8a45260000 rw-p 00017000 fd:00 2099938 /lib64/libpthread-2.14.90.so 7f8a45260000-7f8a45264000 rw-p 00000000 00:00 0 7f8a45264000-7f8a45286000 r-xp 00000000 fd:00 2097348 /lib64/ld-2.14.90.so 7f8a45457000-7f8a4545a000 rw-p 00000000 00:00 0 7f8a45484000-7f8a45485000 rw-p 00000000 00:00 0 7f8a45485000-7f8a45486000 r--p 00021000 fd:00 2097348 /lib64/ld-2.14.90.so 7f8a45486000-7f8a45487000 rw-p 00022000 fd:00 2097348 /lib64/ld-2.14.90.so 7f8a45487000-7f8a45488000 rw-p 00000000 00:00 0 7fff6273b000-7fff6275c000 rw-p 00000000 00:00 0 [stack] 7fff627ff000-7fff62800000 r-xp 00000000 00:00 0 [vdso] ffffffffff600000-ffffffffff601000 r-xp 00000000 00:00 0 [vsyscall] Here, one could guess that 7f8a44492000-7f8a44c92000 is a stack since the earlier vma that has no permissions (7f8a44e3d000-7f8a4503d000) but that is not always a reliable way to find out which vma is a thread stack. Also, /proc/PID/maps and /proc/PID/task/TID/maps has the same content. With this patch in place, /proc/PID/task/TID/maps are treated as 'maps as the task would see it' and hence, only the vma that that task uses as stack is marked as [stack]. All other 'stack' vmas are marked as anonymous memory. /proc/PID/maps acts as a thread group level view, where all thread stack vmas are marked as [stack:TID] where TID is the process ID of the task that uses that vma as stack, while the process stack is marked as [stack]. So /proc/PID/maps will look like this: 00400000-00401000 r-xp 00000000 fd:0a 3671804 /home/siddhesh/a.out 00600000-00601000 rw-p 00000000 fd:0a 3671804 /home/siddhesh/a.out 019ef000-01a10000 rw-p 00000000 00:00 0 [heap] 7f8a44491000-7f8a44492000 ---p 00000000 00:00 0 7f8a44492000-7f8a44c92000 rw-p 00000000 00:00 0 [stack:1442] 7f8a44c92000-7f8a44e3d000 r-xp 00000000 fd:00 2097482 /lib64/libc-2.14.90.so 7f8a44e3d000-7f8a4503d000 ---p 001ab000 fd:00 2097482 /lib64/libc-2.14.90.so 7f8a4503d000-7f8a45041000 r--p 001ab000 fd:00 2097482 /lib64/libc-2.14.90.so 7f8a45041000-7f8a45043000 rw-p 001af000 fd:00 2097482 /lib64/libc-2.14.90.so 7f8a45043000-7f8a45048000 rw-p 00000000 00:00 0 7f8a45048000-7f8a4505f000 r-xp 00000000 fd:00 2099938 /lib64/libpthread-2.14.90.so 7f8a4505f000-7f8a4525e000 ---p 00017000 fd:00 2099938 /lib64/libpthread-2.14.90.so 7f8a4525e000-7f8a4525f000 r--p 00016000 fd:00 2099938 /lib64/libpthread-2.14.90.so 7f8a4525f000-7f8a45260000 rw-p 00017000 fd:00 2099938 /lib64/libpthread-2.14.90.so 7f8a45260000-7f8a45264000 rw-p 00000000 00:00 0 7f8a45264000-7f8a45286000 r-xp 00000000 fd:00 2097348 /lib64/ld-2.14.90.so 7f8a45457000-7f8a4545a000 rw-p 00000000 00:00 0 7f8a45484000-7f8a45485000 rw-p 00000000 00:00 0 7f8a45485000-7f8a45486000 r--p 00021000 fd:00 2097348 /lib64/ld-2.14.90.so 7f8a45486000-7f8a45487000 rw-p 00022000 fd:00 2097348 /lib64/ld-2.14.90.so 7f8a45487000-7f8a45488000 rw-p 00000000 00:00 0 7fff6273b000-7fff6275c000 rw-p 00000000 00:00 0 [stack] 7fff627ff000-7fff62800000 r-xp 00000000 00:00 0 [vdso] ffffffffff600000-ffffffffff601000 r-xp 00000000 00:00 0 [vsyscall] Thus marking all vmas that are used as stacks by the threads in the thread group along with the process stack. The task level maps will however like this: 00400000-00401000 r-xp 00000000 fd:0a 3671804 /home/siddhesh/a.out 00600000-00601000 rw-p 00000000 fd:0a 3671804 /home/siddhesh/a.out 019ef000-01a10000 rw-p 00000000 00:00 0 [heap] 7f8a44491000-7f8a44492000 ---p 00000000 00:00 0 7f8a44492000-7f8a44c92000 rw-p 00000000 00:00 0 [stack] 7f8a44c92000-7f8a44e3d000 r-xp 00000000 fd:00 2097482 /lib64/libc-2.14.90.so 7f8a44e3d000-7f8a4503d000 ---p 001ab000 fd:00 2097482 /lib64/libc-2.14.90.so 7f8a4503d000-7f8a45041000 r--p 001ab000 fd:00 2097482 /lib64/libc-2.14.90.so 7f8a45041000-7f8a45043000 rw-p 001af000 fd:00 2097482 /lib64/libc-2.14.90.so 7f8a45043000-7f8a45048000 rw-p 00000000 00:00 0 7f8a45048000-7f8a4505f000 r-xp 00000000 fd:00 2099938 /lib64/libpthread-2.14.90.so 7f8a4505f000-7f8a4525e000 ---p 00017000 fd:00 2099938 /lib64/libpthread-2.14.90.so 7f8a4525e000-7f8a4525f000 r--p 00016000 fd:00 2099938 /lib64/libpthread-2.14.90.so 7f8a4525f000-7f8a45260000 rw-p 00017000 fd:00 2099938 /lib64/libpthread-2.14.90.so 7f8a45260000-7f8a45264000 rw-p 00000000 00:00 0 7f8a45264000-7f8a45286000 r-xp 00000000 fd:00 2097348 /lib64/ld-2.14.90.so 7f8a45457000-7f8a4545a000 rw-p 00000000 00:00 0 7f8a45484000-7f8a45485000 rw-p 00000000 00:00 0 7f8a45485000-7f8a45486000 r--p 00021000 fd:00 2097348 /lib64/ld-2.14.90.so 7f8a45486000-7f8a45487000 rw-p 00022000 fd:00 2097348 /lib64/ld-2.14.90.so 7f8a45487000-7f8a45488000 rw-p 00000000 00:00 0 7fff6273b000-7fff6275c000 rw-p 00000000 00:00 0 7fff627ff000-7fff62800000 r-xp 00000000 00:00 0 [vdso] ffffffffff600000-ffffffffff601000 r-xp 00000000 00:00 0 [vsyscall] where only the vma that is being used as a stack by *that* task is marked as [stack]. Analogous changes have been made to /proc/PID/smaps, /proc/PID/numa_maps, /proc/PID/task/TID/smaps and /proc/PID/task/TID/numa_maps. Relevant snippets from smaps and numa_maps: [siddhesh@localhost ~ ]$ pgrep a.out 1441 [siddhesh@localhost ~ ]$ cat /proc/1441/smaps | grep "\[stack" 7f8a44492000-7f8a44c92000 rw-p 00000000 00:00 0 [stack:1442] 7fff6273b000-7fff6275c000 rw-p 00000000 00:00 0 [stack] [siddhesh@localhost ~ ]$ cat /proc/1441/task/1442/smaps | grep "\[stack" 7f8a44492000-7f8a44c92000 rw-p 00000000 00:00 0 [stack] [siddhesh@localhost ~ ]$ cat /proc/1441/task/1441/smaps | grep "\[stack" 7fff6273b000-7fff6275c000 rw-p 00000000 00:00 0 [stack] [siddhesh@localhost ~ ]$ cat /proc/1441/numa_maps | grep "stack" 7f8a44492000 default stack:1442 anon=2 dirty=2 N0=2 7fff6273a000 default stack anon=3 dirty=3 N0=3 [siddhesh@localhost ~ ]$ cat /proc/1441/task/1442/numa_maps | grep "stack" 7f8a44492000 default stack anon=2 dirty=2 N0=2 [siddhesh@localhost ~ ]$ cat /proc/1441/task/1441/numa_maps | grep "stack" 7fff6273a000 default stack anon=3 dirty=3 N0=3 [akpm@linux-foundation.org: checkpatch fixes] [akpm@linux-foundation.org: fix build] Signed-off-by: Siddhesh Poyarekar <siddhesh.poyarekar@gmail.com> Cc: KOSAKI Motohiro <kosaki.motohiro@gmail.com> Cc: Alexander Viro <viro@zeniv.linux.org.uk> Cc: Jamie Lokier <jamie@shareable.org> Cc: Mike Frysinger <vapier@gentoo.org> Cc: Alexey Dobriyan <adobriyan@gmail.com> Cc: Matt Mackall <mpm@selenic.com> Cc: Oleg Nesterov <oleg@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-03-21 23:34:04 +00:00
{
return (vma->vm_start <= KSTK_ESP(t) && vma->vm_end >= KSTK_ESP(t));
}
#if defined(CONFIG_MMU) && !defined(HAVE_ARCH_PICK_MMAP_LAYOUT)
void arch_pick_mmap_layout(struct mm_struct *mm)
{
mm->mmap_base = TASK_UNMAPPED_BASE;
mm->get_unmapped_area = arch_get_unmapped_area;
}
#endif
/*
* Like get_user_pages_fast() except its IRQ-safe in that it won't fall
* back to the regular GUP.
* If the architecture not support this function, simply return with no
* page pinned
*/
int __weak __get_user_pages_fast(unsigned long start,
int nr_pages, int write, struct page **pages)
{
return 0;
}
EXPORT_SYMBOL_GPL(__get_user_pages_fast);
/**
* get_user_pages_fast() - pin user pages in memory
* @start: starting user address
* @nr_pages: number of pages from start to pin
* @write: whether pages will be written to
* @pages: array that receives pointers to the pages pinned.
* Should be at least nr_pages long.
*
* Returns number of pages pinned. This may be fewer than the number
* requested. If nr_pages is 0 or negative, returns 0. If no pages
* were pinned, returns -errno.
*
* get_user_pages_fast provides equivalent functionality to get_user_pages,
* operating on current and current->mm, with force=0 and vma=NULL. However
* unlike get_user_pages, it must be called without mmap_sem held.
*
* get_user_pages_fast may take mmap_sem and page table locks, so no
* assumptions can be made about lack of locking. get_user_pages_fast is to be
* implemented in a way that is advantageous (vs get_user_pages()) when the
* user memory area is already faulted in and present in ptes. However if the
* pages have to be faulted in, it may turn out to be slightly slower so
* callers need to carefully consider what to use. On many architectures,
* get_user_pages_fast simply falls back to get_user_pages.
*/
int __weak get_user_pages_fast(unsigned long start,
int nr_pages, int write, struct page **pages)
{
mm/gup: Overload get_user_pages() functions The concept here was a suggestion from Ingo. The implementation horrors are all mine. This allows get_user_pages(), get_user_pages_unlocked(), and get_user_pages_locked() to be called with or without the leading tsk/mm arguments. We will give a compile-time warning about the old style being __deprecated and we will also WARN_ON() if the non-remote version is used for a remote-style access. Doing this, folks will get nice warnings and will not break the build. This should be nice for -next and will hopefully let developers fix up their own code instead of maintainers needing to do it at merge time. The way we do this is hideous. It uses the __VA_ARGS__ macro functionality to call different functions based on the number of arguments passed to the macro. There's an additional hack to ensure that our EXPORT_SYMBOL() of the deprecated symbols doesn't trigger a warning. We should be able to remove this mess as soon as -rc1 hits in the release after this is merged. Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Alexander Kuleshov <kuleshovmail@gmail.com> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Dan Williams <dan.j.williams@intel.com> Cc: Dave Hansen <dave@sr71.net> Cc: Dominik Dingel <dingel@linux.vnet.ibm.com> Cc: Geliang Tang <geliangtang@163.com> Cc: Jan Kara <jack@suse.cz> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Konstantin Khlebnikov <koct9i@gmail.com> Cc: Leon Romanovsky <leon@leon.nu> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Masahiro Yamada <yamada.masahiro@socionext.com> Cc: Mateusz Guzik <mguzik@redhat.com> Cc: Maxime Coquelin <mcoquelin.stm32@gmail.com> Cc: Michal Hocko <mhocko@suse.com> Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Paul Gortmaker <paul.gortmaker@windriver.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Vladimir Davydov <vdavydov@virtuozzo.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Xie XiuQi <xiexiuqi@huawei.com> Cc: linux-kernel@vger.kernel.org Cc: linux-mm@kvack.org Link: http://lkml.kernel.org/r/20160212210155.73222EE1@viggo.jf.intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2016-02-12 21:01:55 +00:00
return get_user_pages_unlocked(start, nr_pages, write, 0, pages);
}
EXPORT_SYMBOL_GPL(get_user_pages_fast);
unsigned long vm_mmap_pgoff(struct file *file, unsigned long addr,
unsigned long len, unsigned long prot,
unsigned long flag, unsigned long pgoff)
{
unsigned long ret;
struct mm_struct *mm = current->mm;
unsigned long populate;
ret = security_mmap_file(file, prot, flag);
if (!ret) {
if (down_write_killable(&mm->mmap_sem))
return -EINTR;
ret = do_mmap_pgoff(file, addr, len, prot, flag, pgoff,
&populate);
up_write(&mm->mmap_sem);
if (populate)
mm_populate(ret, populate);
}
return ret;
}
unsigned long vm_mmap(struct file *file, unsigned long addr,
unsigned long len, unsigned long prot,
unsigned long flag, unsigned long offset)
{
if (unlikely(offset + PAGE_ALIGN(len) < offset))
return -EINVAL;
if (unlikely(offset_in_page(offset)))
return -EINVAL;
return vm_mmap_pgoff(file, addr, len, prot, flag, offset >> PAGE_SHIFT);
}
EXPORT_SYMBOL(vm_mmap);
void kvfree(const void *addr)
{
if (is_vmalloc_addr(addr))
vfree(addr);
else
kfree(addr);
}
EXPORT_SYMBOL(kvfree);
static inline void *__page_rmapping(struct page *page)
{
unsigned long mapping;
mapping = (unsigned long)page->mapping;
mapping &= ~PAGE_MAPPING_FLAGS;
return (void *)mapping;
}
/* Neutral page->mapping pointer to address_space or anon_vma or other */
void *page_rmapping(struct page *page)
{
page = compound_head(page);
return __page_rmapping(page);
}
/*
* Return true if this page is mapped into pagetables.
* For compound page it returns true if any subpage of compound page is mapped.
*/
bool page_mapped(struct page *page)
{
int i;
if (likely(!PageCompound(page)))
return atomic_read(&page->_mapcount) >= 0;
page = compound_head(page);
if (atomic_read(compound_mapcount_ptr(page)) >= 0)
return true;
if (PageHuge(page))
return false;
for (i = 0; i < hpage_nr_pages(page); i++) {
if (atomic_read(&page[i]._mapcount) >= 0)
return true;
}
return false;
}
EXPORT_SYMBOL(page_mapped);
struct anon_vma *page_anon_vma(struct page *page)
{
unsigned long mapping;
page = compound_head(page);
mapping = (unsigned long)page->mapping;
if ((mapping & PAGE_MAPPING_FLAGS) != PAGE_MAPPING_ANON)
return NULL;
return __page_rmapping(page);
}
struct address_space *page_mapping(struct page *page)
{
struct address_space *mapping;
page = compound_head(page);
mm: fix crash when using XFS on loopback Commit 8456a648cf44 ("slab: use struct page for slab management") causes a crash in the LVM2 testsuite on PA-RISC (the crashing test is fsadm.sh). The testsuite doesn't crash on 3.12, crashes on 3.13-rc1 and later. Bad Address (null pointer deref?): Code=15 regs=000000413edd89a0 (Addr=000006202224647d) CPU: 3 PID: 24008 Comm: loop0 Not tainted 3.13.0-rc6 #5 task: 00000001bf3c0048 ti: 000000413edd8000 task.ti: 000000413edd8000 YZrvWESTHLNXBCVMcbcbcbcbOGFRQPDI PSW: 00001000000001101111100100001110 Not tainted r00-03 000000ff0806f90e 00000000405c8de0 000000004013e6c0 000000413edd83f0 r04-07 00000000405a95e0 0000000000000200 00000001414735f0 00000001bf349e40 r08-11 0000000010fe3d10 0000000000000001 00000040829c7778 000000413efd9000 r12-15 0000000000000000 000000004060d800 0000000010fe3000 0000000010fe3000 r16-19 000000413edd82a0 00000041078ddbc0 0000000000000010 0000000000000001 r20-23 0008f3d0d83a8000 0000000000000000 00000040829c7778 0000000000000080 r24-27 00000001bf349e40 00000001bf349e40 202d66202224640d 00000000405a95e0 r28-31 202d662022246465 000000413edd88f0 000000413edd89a0 0000000000000001 sr00-03 000000000532c000 0000000000000000 0000000000000000 000000000532c000 sr04-07 0000000000000000 0000000000000000 0000000000000000 0000000000000000 IASQ: 0000000000000000 0000000000000000 IAOQ: 00000000401fe42c 00000000401fe430 IIR: 539c0030 ISR: 00000000202d6000 IOR: 000006202224647d CPU: 3 CR30: 000000413edd8000 CR31: 0000000000000000 ORIG_R28: 00000000405a95e0 IAOQ[0]: vma_interval_tree_iter_first+0x14/0x48 IAOQ[1]: vma_interval_tree_iter_first+0x18/0x48 RP(r2): flush_dcache_page+0x128/0x388 Backtrace: flush_dcache_page+0x128/0x388 lo_splice_actor+0x90/0x148 [loop] splice_from_pipe_feed+0xc0/0x1d0 __splice_from_pipe+0xac/0xc0 lo_direct_splice_actor+0x1c/0x70 [loop] splice_direct_to_actor+0xec/0x228 lo_receive+0xe4/0x298 [loop] loop_thread+0x478/0x640 [loop] kthread+0x134/0x168 end_fault_vector+0x20/0x28 xfs_setsize_buftarg+0x0/0x90 [xfs] Kernel panic - not syncing: Bad Address (null pointer deref?) Commit 8456a648cf44 changes the page structure so that the slab subsystem reuses the page->mapping field. The crash happens in the following way: * XFS allocates some memory from slab and issues a bio to read data into it. * the bio is sent to the loopback device. * lo_receive creates an actor and calls splice_direct_to_actor. * lo_splice_actor copies data to the target page. * lo_splice_actor calls flush_dcache_page because the page may be mapped by userspace. In that case we need to flush the kernel cache. * flush_dcache_page asks for the list of userspace mappings, however that page->mapping field is reused by the slab subsystem for a different purpose. This causes the crash. Note that other architectures without coherent caches (sparc, arm, mips) also call page_mapping from flush_dcache_page, so they may crash in the same way. This patch fixes this bug by testing if the page is a slab page in page_mapping and returning NULL if it is. The patch also fixes VM_BUG_ON(PageSlab(page)) that could happen in earlier kernels in the same scenario on architectures without cache coherence when CONFIG_DEBUG_VM is enabled - so it should be backported to stable kernels. In the old kernels, the function page_mapping is placed in include/linux/mm.h, so you should modify the patch accordingly when backporting it. Signed-off-by: Mikulas Patocka <mpatocka@redhat.com> Cc: John David Anglin <dave.anglin@bell.net>] Cc: Andi Kleen <ak@linux.intel.com> Cc: Christoph Lameter <cl@linux.com> Acked-by: Pekka Enberg <penberg@kernel.org> Reviewed-by: Joonsoo Kim <iamjoonsoo.kim@lge.com> Cc: Helge Deller <deller@gmx.de> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2014-01-15 01:56:40 +00:00
/* This happens if someone calls flush_dcache_page on slab page */
if (unlikely(PageSlab(page)))
return NULL;
if (unlikely(PageSwapCache(page))) {
swp_entry_t entry;
entry.val = page_private(page);
return swap_address_space(entry);
}
mapping = page->mapping;
if ((unsigned long)mapping & PAGE_MAPPING_FLAGS)
return NULL;
return mapping;
}
/* Slow path of page_mapcount() for compound pages */
int __page_mapcount(struct page *page)
{
int ret;
ret = atomic_read(&page->_mapcount) + 1;
page = compound_head(page);
ret += atomic_read(compound_mapcount_ptr(page)) + 1;
if (PageDoubleMap(page))
ret--;
return ret;
}
EXPORT_SYMBOL_GPL(__page_mapcount);
int sysctl_overcommit_memory __read_mostly = OVERCOMMIT_GUESS;
int sysctl_overcommit_ratio __read_mostly = 50;
unsigned long sysctl_overcommit_kbytes __read_mostly;
int sysctl_max_map_count __read_mostly = DEFAULT_MAX_MAP_COUNT;
unsigned long sysctl_user_reserve_kbytes __read_mostly = 1UL << 17; /* 128MB */
unsigned long sysctl_admin_reserve_kbytes __read_mostly = 1UL << 13; /* 8MB */
int overcommit_ratio_handler(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp,
loff_t *ppos)
{
int ret;
ret = proc_dointvec(table, write, buffer, lenp, ppos);
if (ret == 0 && write)
sysctl_overcommit_kbytes = 0;
return ret;
}
int overcommit_kbytes_handler(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp,
loff_t *ppos)
{
int ret;
ret = proc_doulongvec_minmax(table, write, buffer, lenp, ppos);
if (ret == 0 && write)
sysctl_overcommit_ratio = 0;
return ret;
}
/*
* Committed memory limit enforced when OVERCOMMIT_NEVER policy is used
*/
unsigned long vm_commit_limit(void)
{
unsigned long allowed;
if (sysctl_overcommit_kbytes)
allowed = sysctl_overcommit_kbytes >> (PAGE_SHIFT - 10);
else
allowed = ((totalram_pages - hugetlb_total_pages())
* sysctl_overcommit_ratio / 100);
allowed += total_swap_pages;
return allowed;
}
/*
* Make sure vm_committed_as in one cacheline and not cacheline shared with
* other variables. It can be updated by several CPUs frequently.
*/
struct percpu_counter vm_committed_as ____cacheline_aligned_in_smp;
/*
* The global memory commitment made in the system can be a metric
* that can be used to drive ballooning decisions when Linux is hosted
* as a guest. On Hyper-V, the host implements a policy engine for dynamically
* balancing memory across competing virtual machines that are hosted.
* Several metrics drive this policy engine including the guest reported
* memory commitment.
*/
unsigned long vm_memory_committed(void)
{
return percpu_counter_read_positive(&vm_committed_as);
}
EXPORT_SYMBOL_GPL(vm_memory_committed);
/*
* Check that a process has enough memory to allocate a new virtual
* mapping. 0 means there is enough memory for the allocation to
* succeed and -ENOMEM implies there is not.
*
* We currently support three overcommit policies, which are set via the
* vm.overcommit_memory sysctl. See Documentation/vm/overcommit-accounting
*
* Strict overcommit modes added 2002 Feb 26 by Alan Cox.
* Additional code 2002 Jul 20 by Robert Love.
*
* cap_sys_admin is 1 if the process has admin privileges, 0 otherwise.
*
* Note this is a helper function intended to be used by LSMs which
* wish to use this logic.
*/
int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin)
{
long free, allowed, reserve;
VM_WARN_ONCE(percpu_counter_read(&vm_committed_as) <
-(s64)vm_committed_as_batch * num_online_cpus(),
"memory commitment underflow");
vm_acct_memory(pages);
/*
* Sometimes we want to use more memory than we have
*/
if (sysctl_overcommit_memory == OVERCOMMIT_ALWAYS)
return 0;
if (sysctl_overcommit_memory == OVERCOMMIT_GUESS) {
free = global_page_state(NR_FREE_PAGES);
free += global_page_state(NR_FILE_PAGES);
/*
* shmem pages shouldn't be counted as free in this
* case, they can't be purged, only swapped out, and
* that won't affect the overall amount of available
* memory in the system.
*/
free -= global_page_state(NR_SHMEM);
free += get_nr_swap_pages();
/*
* Any slabs which are created with the
* SLAB_RECLAIM_ACCOUNT flag claim to have contents
* which are reclaimable, under pressure. The dentry
* cache and most inode caches should fall into this
*/
free += global_page_state(NR_SLAB_RECLAIMABLE);
/*
* Leave reserved pages. The pages are not for anonymous pages.
*/
if (free <= totalreserve_pages)
goto error;
else
free -= totalreserve_pages;
/*
* Reserve some for root
*/
if (!cap_sys_admin)
free -= sysctl_admin_reserve_kbytes >> (PAGE_SHIFT - 10);
if (free > pages)
return 0;
goto error;
}
allowed = vm_commit_limit();
/*
* Reserve some for root
*/
if (!cap_sys_admin)
allowed -= sysctl_admin_reserve_kbytes >> (PAGE_SHIFT - 10);
/*
* Don't let a single process grow so big a user can't recover
*/
if (mm) {
reserve = sysctl_user_reserve_kbytes >> (PAGE_SHIFT - 10);
allowed -= min_t(long, mm->total_vm / 32, reserve);
}
if (percpu_counter_read_positive(&vm_committed_as) < allowed)
return 0;
error:
vm_unacct_memory(pages);
return -ENOMEM;
}
/**
* get_cmdline() - copy the cmdline value to a buffer.
* @task: the task whose cmdline value to copy.
* @buffer: the buffer to copy to.
* @buflen: the length of the buffer. Larger cmdline values are truncated
* to this length.
* Returns the size of the cmdline field copied. Note that the copy does
* not guarantee an ending NULL byte.
*/
int get_cmdline(struct task_struct *task, char *buffer, int buflen)
{
int res = 0;
unsigned int len;
struct mm_struct *mm = get_task_mm(task);
unsigned long arg_start, arg_end, env_start, env_end;
if (!mm)
goto out;
if (!mm->arg_end)
goto out_mm; /* Shh! No looking before we're done */
down_read(&mm->mmap_sem);
arg_start = mm->arg_start;
arg_end = mm->arg_end;
env_start = mm->env_start;
env_end = mm->env_end;
up_read(&mm->mmap_sem);
len = arg_end - arg_start;
if (len > buflen)
len = buflen;
res = access_process_vm(task, arg_start, buffer, len, 0);
/*
* If the nul at the end of args has been overwritten, then
* assume application is using setproctitle(3).
*/
if (res > 0 && buffer[res-1] != '\0' && len < buflen) {
len = strnlen(buffer, res);
if (len < res) {
res = len;
} else {
len = env_end - env_start;
if (len > buflen - res)
len = buflen - res;
res += access_process_vm(task, env_start,
buffer+res, len, 0);
res = strnlen(buffer, res);
}
}
out_mm:
mmput(mm);
out:
return res;
}