mm: add a field to store names for private anonymous memory
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is no longer valid all or part of the name will be replaced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.
Change-Id: Ie2ffc0967d4ffe7ee4c70781313c7b00cf7e3092
Signed-off-by: Colin Cross <ccross@android.com>
diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt
index b7413cb..87fb3e9 100644
--- a/Documentation/filesystems/proc.txt
+++ b/Documentation/filesystems/proc.txt
@@ -360,6 +360,8 @@
[stack:1001] = the stack of the thread with tid 1001
[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.
@@ -409,6 +411,7 @@
KernelPageSize: 4 kB
MMUPageSize: 4 kB
Locked: 374 kB
+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
@@ -424,6 +427,9 @@
"Swap" shows how much would-be-anonymous memory is also used, but out on
swap.
+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.
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 8df7fd2..b9416ec 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -90,6 +90,56 @@
seq_printf(m, "%*c", len, ' ');
}
+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(current, mm, page_start_vaddr,
+ 1, 0, 0, &page, 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 vm_area_struct *vma)
{
if (vma && vma != priv->tail_vma) {
@@ -289,6 +339,12 @@
pad_len_spaces(m, len);
seq_printf(m, "[stack:%d]", tid);
}
+ goto done;
+ }
+
+ if (vma_get_anon_name(vma)) {
+ pad_len_spaces(m, len);
+ seq_print_vma_name(m, vma);
}
}
@@ -521,6 +577,12 @@
(vma->vm_flags & VM_LOCKED) ?
(unsigned long)(mss.pss >> (10 + PSS_SHIFT)) : 0);
+ if (vma_get_anon_name(vma)) {
+ seq_puts(m, "Name: ");
+ seq_print_vma_name(m, vma);
+ seq_putc(m, '\n');
+ }
+
if (m->count < m->size) /* vma is copied successfully */
m->version = (vma != get_gate_vma(task->mm))
? vma->vm_start : 0;
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 304728d..b64a652 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1370,7 +1370,7 @@
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 mempolicy *, 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);
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 696b7d8..5788ad6 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -226,6 +226,10 @@
* linkage into the address_space->i_mmap prio tree, or
* linkage to the list of like vmas hanging off its node, or
* linkage of vma in the address_space->i_mmap_nonlinear list.
+ *
+ * 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 {
@@ -235,6 +239,7 @@
} vm_set;
struct raw_prio_tree_node prio_tree_node;
+ const char __user *anon_name;
} shared;
/*
@@ -402,4 +407,14 @@
return mm->cpu_vm_mask_var;
}
+
+/* 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->shared.anon_name;
+}
+
#endif /* _LINUX_MM_TYPES_H */
diff --git a/include/linux/prctl.h b/include/linux/prctl.h
index e0cfec2..2f51340 100644
--- a/include/linux/prctl.h
+++ b/include/linux/prctl.h
@@ -124,4 +124,7 @@
#define PR_SET_CHILD_SUBREAPER 36
#define PR_GET_CHILD_SUBREAPER 37
+#define PR_SET_VMA 0x53564d41
+# define PR_SET_VMA_ANON_NAME 0
+
#endif /* _LINUX_PRCTL_H */
diff --git a/kernel/sys.c b/kernel/sys.c
index 3449d26..864611c 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -40,6 +40,8 @@
#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>
@@ -1846,6 +1848,146 @@
}
#endif
+
+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),
+ 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->shared.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, end,
+ (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;
+}
+
SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3,
unsigned long, arg4, unsigned long, arg5)
{
@@ -2006,6 +2148,9 @@
error = put_user(me->signal->is_child_subreaper,
(int __user *) arg2);
break;
+ case PR_SET_VMA:
+ error = prctl_set_vma(arg2, arg3, arg4, arg5);
+ break;
default:
error = -EINVAL;
break;
diff --git a/mm/madvise.c b/mm/madvise.c
index 55f645c..b075d1d 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -93,7 +93,8 @@
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_file, pgoff, vma_policy(vma),
+ vma_get_anon_name(vma));
if (*prev) {
vma = *prev;
goto success;
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 82f1b02..46cb63b 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -675,7 +675,7 @@
((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);
+ new_pol, vma_get_anon_name(name));
if (prev) {
vma = prev;
next = vma->vm_next;
diff --git a/mm/mlock.c b/mm/mlock.c
index 38c77ab..029f234 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -333,7 +333,8 @@
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_file, pgoff, vma_policy(vma),
+ vma_get_anon_name(vma));
if (*prev) {
vma = *prev;
goto success;
diff --git a/mm/mmap.c b/mm/mmap.c
index 60dca27..e0e4ebf 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -678,7 +678,8 @@
* per-vma resources, so we don't attempt to merge those.
*/
static inline int is_mergeable_vma(struct vm_area_struct *vma,
- struct file *file, unsigned long vm_flags)
+ struct file *file, unsigned long vm_flags,
+ const char __user *anon_name)
{
/* VM_CAN_NONLINEAR may get set later by f_op->mmap() */
if ((vma->vm_flags ^ vm_flags) & ~VM_CAN_NONLINEAR)
@@ -687,6 +688,8 @@
return 0;
if (vma->vm_ops && vma->vm_ops->close)
return 0;
+ if (vma_get_anon_name(vma) != anon_name)
+ return 0;
return 1;
}
@@ -717,9 +720,10 @@
*/
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 anon_vma *anon_vma, struct file *file, pgoff_t vm_pgoff,
+ const char __user *anon_name)
{
- if (is_mergeable_vma(vma, file, vm_flags) &&
+ if (is_mergeable_vma(vma, file, vm_flags, anon_name) &&
is_mergeable_anon_vma(anon_vma, vma->anon_vma, vma)) {
if (vma->vm_pgoff == vm_pgoff)
return 1;
@@ -736,9 +740,10 @@
*/
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 anon_vma *anon_vma, struct file *file, pgoff_t vm_pgoff,
+ const char __user *anon_name)
{
- if (is_mergeable_vma(vma, file, vm_flags) &&
+ if (is_mergeable_vma(vma, file, vm_flags, anon_name) &&
is_mergeable_anon_vma(anon_vma, vma->anon_vma, vma)) {
pgoff_t vm_pglen;
vm_pglen = (vma->vm_end - vma->vm_start) >> PAGE_SHIFT;
@@ -749,9 +754,9 @@
}
/*
- * 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
@@ -781,7 +786,8 @@
struct vm_area_struct *prev, unsigned long addr,
unsigned long end, unsigned long vm_flags,
struct anon_vma *anon_vma, struct file *file,
- pgoff_t pgoff, struct mempolicy *policy)
+ pgoff_t pgoff, struct mempolicy *policy,
+ const char __user *anon_name)
{
pgoff_t pglen = (end - addr) >> PAGE_SHIFT;
struct vm_area_struct *area, *next;
@@ -807,15 +813,15 @@
*/
if (prev && prev->vm_end == addr &&
mpol_equal(vma_policy(prev), policy) &&
- can_vma_merge_after(prev, vm_flags,
- anon_vma, file, pgoff)) {
+ can_vma_merge_after(prev, vm_flags, anon_vma,
+ file, pgoff, anon_name)) {
/*
* OK, it can. Can we now merge in the successor as well?
*/
if (next && end == next->vm_start &&
mpol_equal(policy, vma_policy(next)) &&
- can_vma_merge_before(next, vm_flags,
- anon_vma, file, pgoff+pglen) &&
+ can_vma_merge_before(next, vm_flags, anon_vma,
+ file, pgoff+pglen, anon_name) &&
is_mergeable_anon_vma(prev->anon_vma,
next->anon_vma, NULL)) {
/* cases 1, 6 */
@@ -835,8 +841,8 @@
*/
if (next && end == next->vm_start &&
mpol_equal(policy, vma_policy(next)) &&
- can_vma_merge_before(next, vm_flags,
- anon_vma, file, pgoff+pglen)) {
+ can_vma_merge_before(next, vm_flags, anon_vma,
+ file, pgoff+pglen, anon_name)) {
if (prev && addr < prev->vm_end) /* case 4 */
err = vma_adjust(prev, prev->vm_start,
addr, prev->vm_pgoff, NULL);
@@ -1328,7 +1334,8 @@
/*
* Can we just expand an old mapping?
*/
- vma = vma_merge(mm, prev, addr, addr + len, vm_flags, NULL, file, pgoff, NULL);
+ vma = vma_merge(mm, prev, addr, addr + len, vm_flags, NULL, file, pgoff,
+ NULL, NULL);
if (vma)
goto out;
@@ -2305,7 +2312,7 @@
/* Can we just expand an old private anonymous mapping? */
vma = vma_merge(mm, prev, addr, addr + len, flags,
- NULL, NULL, pgoff, NULL);
+ NULL, NULL, pgoff, NULL, NULL);
if (vma)
goto out;
@@ -2455,7 +2462,8 @@
find_vma_prepare(mm, addr, &prev, &rb_link, &rb_parent);
new_vma = vma_merge(mm, prev, addr, addr + len, vma->vm_flags,
- vma->anon_vma, vma->vm_file, pgoff, vma_policy(vma));
+ vma->anon_vma, vma->vm_file, pgoff, vma_policy(vma),
+ vma_get_anon_name(vma));
if (new_vma) {
/*
* Source vma may have been merged into new_vma
diff --git a/mm/mprotect.c b/mm/mprotect.c
index a409926..10add6b 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -179,7 +179,8 @@
*/
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->anon_vma, vma->vm_file, pgoff, vma_policy(vma),
+ vma_get_anon_name(vma));
if (*pprev) {
vma = *pprev;
goto success;