From 0fa571fe6091b184f50b63373b48f44b247d4d44 Mon Sep 17 00:00:00 2001 From: Colin Cross Date: Wed, 26 Jun 2013 17:26:01 -0700 Subject: [PATCH] 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:] 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 If the userspace pointer is no longer valid all or part of the name will be replaced with "". 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 --- Documentation/filesystems/proc.txt | 6 ++ fs/proc/task_mmu.c | 62 ++++++++++++ include/linux/mm.h | 2 +- include/linux/mm_types.h | 15 +++ include/linux/prctl.h | 3 + kernel/sys.c | 145 +++++++++++++++++++++++++++++ mm/madvise.c | 3 +- mm/mempolicy.c | 2 +- mm/mlock.c | 3 +- mm/mmap.c | 44 +++++---- mm/mprotect.c | 3 +- 11 files changed, 265 insertions(+), 23 deletions(-) diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt index b7413cb46dcb..87fb3e9ccd73 100644 --- a/Documentation/filesystems/proc.txt +++ b/Documentation/filesystems/proc.txt @@ -360,6 +360,8 @@ is not associated with a file: [stack:1001] = the stack of the thread with tid 1001 [vdso] = the "virtual dynamic shared object", the kernel system call handler + [anon:] = an anonymous mapping that has been + named by userspace or if empty, the mapping is anonymous. @@ -409,6 +411,7 @@ Swap: 0 kB 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 @@ and a page is modified, the file page is replaced by a private anonymous copy. "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 1030a716d155..a789934737e2 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -90,6 +90,56 @@ static void pad_len_spaces(struct seq_file *m, int len) 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, "]"); + 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 @@ show_map_vma(struct seq_file *m, struct vm_area_struct *vma, int is_pid) 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 @@ static int show_smap(struct seq_file *m, void *v, int is_pid) (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 ddfb7c5dd515..fd1baead0d8f 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1369,7 +1369,7 @@ extern 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 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 3cc3062b3767..9035d0a71a87 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -216,6 +216,10 @@ struct vm_area_struct { * 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 { @@ -225,6 +229,7 @@ struct vm_area_struct { } vm_set; struct raw_prio_tree_node prio_tree_node; + const char __user *anon_name; } shared; /* @@ -403,4 +408,14 @@ static inline cpumask_t *mm_cpumask(struct mm_struct *mm) 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 e0cfec2490aa..2f513409fabf 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 6e08068f3591..ce7e1e638dea 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -40,6 +40,8 @@ #include #include #include +#include +#include #include #include @@ -1821,6 +1823,146 @@ static int prctl_set_mm(int opt, unsigned long addr, } #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) { @@ -1981,6 +2123,9 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3, 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 55f645c85a35..b075d1d1f6c8 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -93,7 +93,8 @@ 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_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 b19569137529..a78698098f50 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -660,7 +660,7 @@ 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); + 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 ef726e8aa8e9..263e49dd1ba9 100644 --- a/mm/mlock.c +++ b/mm/mlock.c @@ -329,7 +329,8 @@ 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_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 848ef52d9603..ded6fe9f144d 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -649,7 +649,8 @@ again: remove_next = 1 + (end > next->vm_end); * 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) @@ -658,6 +659,8 @@ static inline int is_mergeable_vma(struct vm_area_struct *vma, return 0; if (vma->vm_ops && vma->vm_ops->close) return 0; + if (vma_get_anon_name(vma) != anon_name) + return 0; return 1; } @@ -688,9 +691,10 @@ static inline int is_mergeable_anon_vma(struct anon_vma *anon_vma1, */ 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; @@ -707,9 +711,10 @@ can_vma_merge_before(struct vm_area_struct *vma, unsigned long vm_flags, */ 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; @@ -720,9 +725,9 @@ 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 @@ -752,7 +757,8 @@ struct vm_area_struct *vma_merge(struct mm_struct *mm, 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; @@ -778,15 +784,15 @@ struct vm_area_struct *vma_merge(struct mm_struct *mm, */ 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 */ @@ -806,8 +812,8 @@ struct vm_area_struct *vma_merge(struct mm_struct *mm, */ 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); @@ -1282,7 +1288,8 @@ munmap_back: /* * 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; @@ -2232,7 +2239,7 @@ static unsigned long do_brk(unsigned long addr, unsigned long len) /* 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; @@ -2382,7 +2389,8 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap, 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 a40992610ab6..10add6b44c55 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -179,7 +179,8 @@ 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->anon_vma, vma->vm_file, pgoff, vma_policy(vma), + vma_get_anon_name(vma)); if (*pprev) { vma = *pprev; goto success;