Techwizz/kernel-fxtec-pro1x
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

ANDROID: mm: add a field to store names for private anonymous memory

Browse source 
Userspace processes often have multiple allocators that each do
anonymous mmaps to get memory.  When examining memory usage of
individual processes or systems as a whole, it is useful to be
able to break down the various heaps that were allocated by
each layer and examine their size, RSS, and physical memory
usage.

This patch adds a user pointer to the shared union in
vm_area_struct that points to a null terminated string inside
the user process containing a name for the vma.  vmas that
point to the same address will be merged, but vmas that
point to equivalent strings at different addresses will
not be merged.

Userspace can set the name for a region of memory by calling
prctl(PR_SET_VMA, PR_SET_VMA_ANON_NAME, start, len, (unsigned long)name);
Setting the name to NULL clears it.

The names of named anonymous vmas are shown in /proc/pid/maps
as [anon:<name>] and in /proc/pid/smaps in a new "Name" field
that is only present for named vmas.  If the userspace pointer
is no longer valid all or part of the name will be replaced
with "<fault>".

The idea to store a userspace pointer to reduce the complexity
within mm (at the expense of the complexity of reading
/proc/pid/mem) came from Dave Hansen.  This results in no
runtime overhead in the mm subsystem other than comparing
the anon_name pointers when considering vma merging.  The pointer
is stored in a union with fieds that are only used on file-backed
mappings, so it does not increase memory usage.

Includes fix from Jed Davis <jld@mozilla.com> for typo in
prctl_set_vma_anon_name, which could attempt to set the name
across two vmas at the same time due to a typo, which might
corrupt the vma list.  Fix it to use tmp instead of end to limit
the name setting to a single vma at a time.

Change-Id: I9aa7b6b5ef536cd780599ba4e2fba8ceebe8b59f
Signed-off-by: Dmitry Shmidt <dimitrysh@google.com>

[AmitP: Fix get_user_pages_remote() call to align with upstream commit
        5b56d49fc3 ("mm: add locked parameter to get_user_pages_remote()")]
Signed-off-by: Amit Pundir <amit.pundir@linaro.org>
This commit is contained in:
Colin Cross 2015-10-27 16:42:08 -07:00 committed by Amit Pundir
parent d7b0c0bd50
commit 62dd4637d6
12 changed files with 280 additions and 28 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

6
Documentation/filesystems/proc.txt
View file

@ -398,6 +398,8 @@ is not associated with a file:
[stack] = the stack of the main process
[vdso] = the "virtual dynamic shared object",
the kernel system call handler
[anon:<name>] = an anonymous mapping that has been
named by userspace
or if empty, the mapping is anonymous.
@ -426,6 +428,7 @@ KernelPageSize: 4 kB
MMUPageSize: 4 kB
Locked: 0 kB
VmFlags: rd ex mr mw me dw
Name: name from userspace
the first of these lines shows the same information as is displayed for the
mapping in /proc/PID/maps. The remaining lines show the size of the mapping
@ -498,6 +501,9 @@ Note that there is no guarantee that every flag and associated mnemonic will
be present in all further kernel releases. Things get changed, the flags may
be vanished or the reverse -- new added.
The "Name" field will only be present on a mapping that has been named by
userspace, and will show the name passed in by userspace.
This file is only present if the CONFIG_MMU kernel configuration option is
enabled.

64
fs/proc/task_mmu.c
View file

@ -123,6 +123,56 @@ static void release_task_mempolicy(struct proc_maps_private *priv)
}
#endif
static void seq_print_vma_name(struct seq_file *m, struct vm_area_struct *vma)
{
const char __user *name = vma_get_anon_name(vma);
struct mm_struct *mm = vma->vm_mm;
unsigned long page_start_vaddr;
unsigned long page_offset;
unsigned long num_pages;
unsigned long max_len = NAME_MAX;
int i;
page_start_vaddr = (unsigned long)name & PAGE_MASK;
page_offset = (unsigned long)name - page_start_vaddr;
num_pages = DIV_ROUND_UP(page_offset + max_len, PAGE_SIZE);
seq_puts(m, "[anon:");
for (i = 0; i < num_pages; i++) {
int len;
int write_len;
const char *kaddr;
long pages_pinned;
struct page *page;
pages_pinned = get_user_pages_remote(current, mm,
page_start_vaddr, 1, 0, &page, NULL, NULL);
if (pages_pinned < 1) {
seq_puts(m, "<fault>]");
return;
}
kaddr = (const char *)kmap(page);
len = min(max_len, PAGE_SIZE - page_offset);
write_len = strnlen(kaddr + page_offset, len);
seq_write(m, kaddr + page_offset, write_len);
kunmap(page);
put_page(page);
/* if strnlen hit a null terminator then we're done */
if (write_len != len)
break;
max_len -= len;
page_offset = 0;
page_start_vaddr += PAGE_SIZE;
}
seq_putc(m, ']');
}
static void vma_stop(struct proc_maps_private *priv)
{
struct mm_struct *mm = priv->mm;
@ -344,8 +394,15 @@ show_map_vma(struct seq_file *m, struct vm_area_struct *vma)
goto done;
}
if (is_stack(vma))
if (is_stack(vma)) {
name = "[stack]";
goto done;
}
if (vma_get_anon_name(vma)) {
seq_pad(m, ' ');
seq_print_vma_name(m, vma);
}
}
done:
@ -780,6 +837,11 @@ static int show_smap(struct seq_file *m, void *v)
smap_gather_stats(vma, &mss);
show_map_vma(m, vma);
if (vma_get_anon_name(vma)) {
seq_puts(m, "Name: ");
seq_print_vma_name(m, vma);
seq_putc(m, '\n');
}
SEQ_PUT_DEC("Size: ", vma->vm_end - vma->vm_start);
SEQ_PUT_DEC(" kB\nKernelPageSize: ", vma_kernel_pagesize(vma));

9
fs/userfaultfd.c
View file

@ -890,7 +890,8 @@ static int userfaultfd_release(struct inode *inode, struct file *file)
new_flags, vma->anon_vma,
vma->vm_file, vma->vm_pgoff,
vma_policy(vma),
NULL_VM_UFFD_CTX);
NULL_VM_UFFD_CTX,
vma_get_anon_name(vma));
if (prev)
vma = prev;
else
@ -1423,7 +1424,8 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx,
prev = vma_merge(mm, prev, start, vma_end, new_flags,
vma->anon_vma, vma->vm_file, vma->vm_pgoff,
vma_policy(vma),
((struct vm_userfaultfd_ctx){ ctx }));
((struct vm_userfaultfd_ctx){ ctx }),
vma_get_anon_name(vma));
if (prev) {
vma = prev;
goto next;
@ -1581,7 +1583,8 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx,
prev = vma_merge(mm, prev, start, vma_end, new_flags,
vma->anon_vma, vma->vm_file, vma->vm_pgoff,
vma_policy(vma),
NULL_VM_UFFD_CTX);
NULL_VM_UFFD_CTX,
vma_get_anon_name(vma));
if (prev) {
vma = prev;
goto next;

2
include/linux/mm.h
View file

@ -2227,7 +2227,7 @@ static inline int vma_adjust(struct vm_area_struct *vma, unsigned long start,
extern struct vm_area_struct *vma_merge(struct mm_struct *,
struct vm_area_struct *prev, unsigned long addr, unsigned long end,
unsigned long vm_flags, struct anon_vma *, struct file *, pgoff_t,
struct mempolicy *, struct vm_userfaultfd_ctx);
struct mempolicy *, struct vm_userfaultfd_ctx, const char __user *);
extern struct anon_vma *find_mergeable_anon_vma(struct vm_area_struct *);
extern int __split_vma(struct mm_struct *, struct vm_area_struct *,
unsigned long addr, int new_below);

16
include/linux/mm_types.h
View file

@ -290,11 +290,18 @@ struct vm_area_struct {
/*
* For areas with an address space and backing store,
* linkage into the address_space->i_mmap interval tree.
*
* For private anonymous mappings, a pointer to a null terminated string
* in the user process containing the name given to the vma, or NULL
* if unnamed.
*/
union {
struct {
struct rb_node rb;
unsigned long rb_subtree_last;
} shared;
const char __user *anon_name;
};
/*
* A file's MAP_PRIVATE vma can be in both i_mmap tree and anon_vma
@ -649,4 +656,13 @@ typedef struct {
unsigned long val;
} swp_entry_t;
/* Return the name for an anonymous mapping or NULL for a file-backed mapping */
static inline const char __user *vma_get_anon_name(struct vm_area_struct *vma)
{
if (vma->vm_file)
return NULL;
return vma->anon_name;
}
#endif /* _LINUX_MM_TYPES_H */

3
include/uapi/linux/prctl.h
View file

@ -219,4 +219,7 @@ struct prctl_mm_map {
# define PR_SPEC_DISABLE (1UL << 2)
# define PR_SPEC_FORCE_DISABLE (1UL << 3)
#define PR_SET_VMA 0x53564d41
# define PR_SET_VMA_ANON_NAME 0
#endif /* _LINUX_PRCTL_H */

152
kernel/sys.c
View file

@ -42,6 +42,8 @@
#include <linux/syscore_ops.h>
#include <linux/version.h>
#include <linux/ctype.h>
#include <linux/mm.h>
#include <linux/mempolicy.h>
#include <linux/compat.h>
#include <linux/syscalls.h>
@ -2261,6 +2263,153 @@ int __weak arch_prctl_spec_ctrl_set(struct task_struct *t, unsigned long which,
return -EINVAL;
}
#ifdef CONFIG_MMU
static int prctl_update_vma_anon_name(struct vm_area_struct *vma,
struct vm_area_struct **prev,
unsigned long start, unsigned long end,
const char __user *name_addr)
{
struct mm_struct *mm = vma->vm_mm;
int error = 0;
pgoff_t pgoff;
if (name_addr == vma_get_anon_name(vma)) {
*prev = vma;
goto out;
}
pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT);
*prev = vma_merge(mm, *prev, start, end, vma->vm_flags, vma->anon_vma,
vma->vm_file, pgoff, vma_policy(vma),
vma->vm_userfaultfd_ctx, name_addr);
if (*prev) {
vma = *prev;
goto success;
}
*prev = vma;
if (start != vma->vm_start) {
error = split_vma(mm, vma, start, 1);
if (error)
goto out;
}
if (end != vma->vm_end) {
error = split_vma(mm, vma, end, 0);
if (error)
goto out;
}
success:
if (!vma->vm_file)
vma->anon_name = name_addr;
out:
if (error == -ENOMEM)
error = -EAGAIN;
return error;
}
static int prctl_set_vma_anon_name(unsigned long start, unsigned long end,
unsigned long arg)
{
unsigned long tmp;
struct vm_area_struct *vma, *prev;
int unmapped_error = 0;
int error = -EINVAL;
/*
* If the interval [start,end) covers some unmapped address
* ranges, just ignore them, but return -ENOMEM at the end.
* - this matches the handling in madvise.
*/
vma = find_vma_prev(current->mm, start, &prev);
if (vma && start > vma->vm_start)
prev = vma;
for (;;) {
/* Still start < end. */
error = -ENOMEM;
if (!vma)
return error;
/* Here start < (end|vma->vm_end). */
if (start < vma->vm_start) {
unmapped_error = -ENOMEM;
start = vma->vm_start;
if (start >= end)
return error;
}
/* Here vma->vm_start <= start < (end|vma->vm_end) */
tmp = vma->vm_end;
if (end < tmp)
tmp = end;
/* Here vma->vm_start <= start < tmp <= (end|vma->vm_end). */
error = prctl_update_vma_anon_name(vma, &prev, start, tmp,
(const char __user *)arg);
if (error)
return error;
start = tmp;
if (prev && start < prev->vm_end)
start = prev->vm_end;
error = unmapped_error;
if (start >= end)
return error;
if (prev)
vma = prev->vm_next;
else /* madvise_remove dropped mmap_sem */
vma = find_vma(current->mm, start);
}
}
static int prctl_set_vma(unsigned long opt, unsigned long start,
unsigned long len_in, unsigned long arg)
{
struct mm_struct *mm = current->mm;
int error;
unsigned long len;
unsigned long end;
if (start & ~PAGE_MASK)
return -EINVAL;
len = (len_in + ~PAGE_MASK) & PAGE_MASK;
/* Check to see whether len was rounded up from small -ve to zero */
if (len_in && !len)
return -EINVAL;
end = start + len;
if (end < start)
return -EINVAL;
if (end == start)
return 0;
down_write(&mm->mmap_sem);
switch (opt) {
case PR_SET_VMA_ANON_NAME:
error = prctl_set_vma_anon_name(start, end, arg);
break;
default:
error = -EINVAL;
}
up_write(&mm->mmap_sem);
return error;
}
#else /* CONFIG_MMU */
static int prctl_set_vma(unsigned long opt, unsigned long start,
unsigned long len_in, unsigned long arg)
{
return -EINVAL;
}
#endif
SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
unsigned long, arg4, unsigned long, arg5)
{
@ -2479,6 +2628,9 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
return -EINVAL;
error = arch_prctl_spec_ctrl_set(me, arg2, arg3);
break;
case PR_SET_VMA:
error = prctl_set_vma(arg2, arg3, arg4, arg5);
break;
default:
error = -EINVAL;
break;

2
mm/madvise.c
View file

@ -138,7 +138,7 @@ static long madvise_behavior(struct vm_area_struct *vma,
pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT);
*prev = vma_merge(mm, *prev, start, end, new_flags, vma->anon_vma,
vma->vm_file, pgoff, vma_policy(vma),
vma->vm_userfaultfd_ctx);
vma->vm_userfaultfd_ctx, vma_get_anon_name(vma));
if (*prev) {
vma = *prev;
goto success;

3
mm/mempolicy.c
View file

@ -705,7 +705,8 @@ static int mbind_range(struct mm_struct *mm, unsigned long start,
((vmstart - vma->vm_start) >> PAGE_SHIFT);
prev = vma_merge(mm, prev, vmstart, vmend, vma->vm_flags,
vma->anon_vma, vma->vm_file, pgoff,
new_pol, vma->vm_userfaultfd_ctx);
new_pol, vma->vm_userfaultfd_ctx,
vma_get_anon_name(vma));
if (prev) {
vma = prev;
next = vma->vm_next;

2
mm/mlock.c
View file

@ -535,7 +535,7 @@ static int mlock_fixup(struct vm_area_struct *vma, struct vm_area_struct **prev,
pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT);
*prev = vma_merge(mm, *prev, start, end, newflags, vma->anon_vma,
vma->vm_file, pgoff, vma_policy(vma),
vma->vm_userfaultfd_ctx);
vma->vm_userfaultfd_ctx, vma_get_anon_name(vma));
if (*prev) {
vma = *prev;
goto success;

39
mm/mmap.c
View file

@ -982,7 +982,8 @@ int __vma_adjust(struct vm_area_struct *vma, unsigned long start,
*/
static inline int is_mergeable_vma(struct vm_area_struct *vma,
struct file *file, unsigned long vm_flags,
struct vm_userfaultfd_ctx vm_userfaultfd_ctx)
struct vm_userfaultfd_ctx vm_userfaultfd_ctx,
const char __user *anon_name)
{
/*
* VM_SOFTDIRTY should not prevent from VMA merging, if we
@ -1000,6 +1001,8 @@ static inline int is_mergeable_vma(struct vm_area_struct *vma,
return 0;
if (!is_mergeable_vm_userfaultfd_ctx(vma, vm_userfaultfd_ctx))
return 0;
if (vma_get_anon_name(vma) != anon_name)
return 0;
return 1;
}
@ -1032,9 +1035,10 @@ static int
can_vma_merge_before(struct vm_area_struct *vma, unsigned long vm_flags,
struct anon_vma *anon_vma, struct file *file,
pgoff_t vm_pgoff,
struct vm_userfaultfd_ctx vm_userfaultfd_ctx)
struct vm_userfaultfd_ctx vm_userfaultfd_ctx,
const char __user *anon_name)
{
if (is_mergeable_vma(vma, file, vm_flags, vm_userfaultfd_ctx) &&
if (is_mergeable_vma(vma, file, vm_flags, vm_userfaultfd_ctx, anon_name) &&
is_mergeable_anon_vma(anon_vma, vma->anon_vma, vma)) {
if (vma->vm_pgoff == vm_pgoff)
return 1;
@ -1053,9 +1057,10 @@ static int
can_vma_merge_after(struct vm_area_struct *vma, unsigned long vm_flags,
struct anon_vma *anon_vma, struct file *file,
pgoff_t vm_pgoff,
struct vm_userfaultfd_ctx vm_userfaultfd_ctx)
struct vm_userfaultfd_ctx vm_userfaultfd_ctx,
const char __user *anon_name)
{
if (is_mergeable_vma(vma, file, vm_flags, vm_userfaultfd_ctx) &&
if (is_mergeable_vma(vma, file, vm_flags, vm_userfaultfd_ctx, anon_name) &&
is_mergeable_anon_vma(anon_vma, vma->anon_vma, vma)) {
pgoff_t vm_pglen;
vm_pglen = vma_pages(vma);
@ -1066,9 +1071,9 @@ can_vma_merge_after(struct vm_area_struct *vma, unsigned long vm_flags,
}
/*
* Given a mapping request (addr,end,vm_flags,file,pgoff), figure out
* whether that can be merged with its predecessor or its successor.
* Or both (it neatly fills a hole).
* Given a mapping request (addr,end,vm_flags,file,pgoff,anon_name),
* figure out whether that can be merged with its predecessor or its
* successor. Or both (it neatly fills a hole).
*
* In most cases - when called for mmap, brk or mremap - [addr,end) is
* certain not to be mapped by the time vma_merge is called; but when
@ -1110,7 +1115,8 @@ struct vm_area_struct *vma_merge(struct mm_struct *mm,
unsigned long end, unsigned long vm_flags,
struct anon_vma *anon_vma, struct file *file,
pgoff_t pgoff, struct mempolicy *policy,
struct vm_userfaultfd_ctx vm_userfaultfd_ctx)
struct vm_userfaultfd_ctx vm_userfaultfd_ctx,
const char __user *anon_name)
{
pgoff_t pglen = (end - addr) >> PAGE_SHIFT;
struct vm_area_struct *area, *next;
@ -1143,7 +1149,8 @@ struct vm_area_struct *vma_merge(struct mm_struct *mm,
mpol_equal(vma_policy(prev), policy) &&
can_vma_merge_after(prev, vm_flags,
anon_vma, file, pgoff,
vm_userfaultfd_ctx)) {
vm_userfaultfd_ctx,
anon_name)) {
/*
* OK, it can. Can we now merge in the successor as well?
*/
@ -1152,7 +1159,8 @@ struct vm_area_struct *vma_merge(struct mm_struct *mm,
can_vma_merge_before(next, vm_flags,
anon_vma, file,
pgoff+pglen,
vm_userfaultfd_ctx) &&
vm_userfaultfd_ctx,
anon_name) &&
is_mergeable_anon_vma(prev->anon_vma,
next->anon_vma, NULL)) {
/* cases 1, 6 */
@ -1175,7 +1183,8 @@ struct vm_area_struct *vma_merge(struct mm_struct *mm,
mpol_equal(policy, vma_policy(next)) &&
can_vma_merge_before(next, vm_flags,
anon_vma, file, pgoff+pglen,
vm_userfaultfd_ctx)) {
vm_userfaultfd_ctx,
anon_name)) {
if (prev && addr < prev->vm_end) /* case 4 */
err = __vma_adjust(prev, prev->vm_start,
addr, prev->vm_pgoff, NULL, next);
@ -1720,7 +1729,7 @@ unsigned long mmap_region(struct file *file, unsigned long addr,
* Can we just expand an old mapping?
*/
vma = vma_merge(mm, prev, addr, addr + len, vm_flags,
NULL, file, pgoff, NULL, NULL_VM_UFFD_CTX);
NULL, file, pgoff, NULL, NULL_VM_UFFD_CTX, NULL);
if (vma)
goto out;
@ -2973,7 +2982,7 @@ static int do_brk_flags(unsigned long addr, unsigned long len, unsigned long fla
/* Can we just expand an old private anonymous mapping? */
vma = vma_merge(mm, prev, addr, addr + len, flags,
NULL, NULL, pgoff, NULL, NULL_VM_UFFD_CTX);
NULL, NULL, pgoff, NULL, NULL_VM_UFFD_CTX, NULL);
if (vma)
goto out;
@ -3171,7 +3180,7 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap,
return NULL; /* should never get here */
new_vma = vma_merge(mm, prev, addr, addr + len, vma->vm_flags,
vma->anon_vma, vma->vm_file, pgoff, vma_policy(vma),
vma->vm_userfaultfd_ctx);
vma->vm_userfaultfd_ctx, vma_get_anon_name(vma));
if (new_vma) {
/*
* Source vma may have been merged into new_vma

2
mm/mprotect.c
View file

@ -398,7 +398,7 @@ mprotect_fixup(struct vm_area_struct *vma, struct vm_area_struct **pprev,
pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT);
*pprev = vma_merge(mm, *pprev, start, end, newflags,
vma->anon_vma, vma->vm_file, pgoff, vma_policy(vma),
vma->vm_userfaultfd_ctx);
vma->vm_userfaultfd_ctx, vma_get_anon_name(vma));
if (*pprev) {
vma = *pprev;
VM_WARN_ON((vma->vm_flags ^ newflags) & ~VM_SOFTDIRTY);