diff options
| -rw-r--r-- | Documentation/filesystems/proc.rst | 6 | ||||
| -rw-r--r-- | fs/proc/task_mmu.c | 64 | ||||
| -rw-r--r-- | fs/userfaultfd.c | 9 | ||||
| -rw-r--r-- | include/linux/mm.h | 2 | ||||
| -rw-r--r-- | include/linux/mm_types.h | 24 | ||||
| -rw-r--r-- | include/uapi/linux/prctl.h | 2 | ||||
| -rw-r--r-- | kernel/sys.c | 152 | ||||
| -rw-r--r-- | mm/madvise.c | 2 | ||||
| -rw-r--r-- | mm/mempolicy.c | 3 | ||||
| -rw-r--r-- | mm/mlock.c | 2 | ||||
| -rw-r--r-- | mm/mmap.c | 41 | ||||
| -rw-r--r-- | mm/mprotect.c | 2 |
12 files changed, 280 insertions, 29 deletions
diff --git a/Documentation/filesystems/proc.rst b/Documentation/filesystems/proc.rst index 2fa69f710e2a..49f65d8c29ff 100644 --- a/Documentation/filesystems/proc.rst +++ b/Documentation/filesystems/proc.rst @@ -431,6 +431,8 @@ 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. @@ -464,6 +466,7 @@ Memory Area, or VMA) there is a series of lines such as the following:: Locked: 0 kB THPeligible: 0 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. Following lines show the size of the mapping @@ -557,6 +560,9 @@ be vanished or the reverse -- new added. Interpretation of their meaning might change in future as well. So each consumer of these flags has to follow each specific kernel version for the exact semantic. +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 602e3a52884d..d4c728cae659 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -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(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 *m_start(struct seq_file *m, loff_t *ppos) { struct proc_maps_private *priv = m->private; @@ -319,8 +369,15 @@ 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: @@ -820,6 +877,11 @@ static int show_smap(struct seq_file *m, void *v) smap_gather_stats(vma, &mss, 0); 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)); diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index 894cc28142e7..4a113ffadf88 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -876,7 +876,8 @@ 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 @@ -1424,7 +1425,8 @@ 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; @@ -1594,7 +1596,8 @@ 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; diff --git a/include/linux/mm.h b/include/linux/mm.h index ecdf8a8cd6ae..d9f6f49c65da 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2516,7 +2516,7 @@ 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); diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 07d9acb5b19c..911c40ee4472 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -334,11 +334,18 @@ 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. */ - struct { - struct rb_node rb; - unsigned long rb_subtree_last; - } shared; + 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 @@ -791,4 +798,13 @@ 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 */ diff --git a/include/uapi/linux/prctl.h b/include/uapi/linux/prctl.h index 90deb41c8a34..b3e82f3eff84 100644 --- a/include/uapi/linux/prctl.h +++ b/include/uapi/linux/prctl.h @@ -251,5 +251,7 @@ struct prctl_mm_map { #define PR_SET_SYSCALL_USER_DISPATCH 59 # define PR_SYS_DISPATCH_OFF 0 # define PR_SYS_DISPATCH_ON 1 +#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 51f00fe20e4d..e063072ee439 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -43,6 +43,8 @@ #include <linux/version.h> #include <linux/ctype.h> #include <linux/syscall_user_dispatch.h> +#include <linux/mm.h> +#include <linux/mempolicy.h> #include <linux/compat.h> #include <linux/syscalls.h> @@ -2279,6 +2281,153 @@ 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; + + mmap_write_lock(mm); + + switch (opt) { + case PR_SET_VMA_ANON_NAME: + error = prctl_set_vma_anon_name(start, end, arg); + break; + default: + error = -EINVAL; + } + + mmap_write_unlock(mm); + + 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 + #define PR_IO_FLUSHER (PF_MEMALLOC_NOIO | PF_LOCAL_THROTTLE) SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3, @@ -2493,6 +2642,9 @@ 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; case PR_PAC_RESET_KEYS: if (arg3 || arg4 || arg5) return -EINVAL; diff --git a/mm/madvise.c b/mm/madvise.c index 6a660858784b..297c10f020c9 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -136,7 +136,7 @@ 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; diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 2c3a86502053..bc6d14fd67da 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -829,7 +829,8 @@ 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; diff --git a/mm/mlock.c b/mm/mlock.c index 55b3b3672977..2285045beb11 100644 --- a/mm/mlock.c +++ b/mm/mlock.c @@ -511,7 +511,7 @@ 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; diff --git a/mm/mmap.c b/mm/mmap.c index dc7206032387..251afa5e0759 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -1028,7 +1028,8 @@ again: */ 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 @@ -1046,6 +1047,8 @@ 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; } @@ -1078,9 +1081,10 @@ 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; @@ -1099,9 +1103,10 @@ 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); @@ -1112,9 +1117,9 @@ 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 @@ -1159,7 +1164,8 @@ 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; @@ -1189,7 +1195,8 @@ 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? */ @@ -1198,7 +1205,8 @@ 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 */ @@ -1221,7 +1229,8 @@ 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); @@ -1765,7 +1774,7 @@ 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; @@ -1824,7 +1833,7 @@ unsigned long mmap_region(struct file *file, unsigned long addr, */ if (unlikely(vm_flags != vma->vm_flags && prev)) { merge = vma_merge(mm, prev, vma->vm_start, vma->vm_end, vma->vm_flags, - NULL, vma->vm_file, vma->vm_pgoff, NULL, NULL_VM_UFFD_CTX); + NULL, vma->vm_file, vma->vm_pgoff, NULL, NULL_VM_UFFD_CTX, vma_get_anon_name(vma)); if (merge) { /* ->mmap() can change vma->vm_file and fput the original file. So * fput the vma->vm_file here or we would add an extra fput for file @@ -3100,7 +3109,7 @@ 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; @@ -3299,7 +3308,7 @@ 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 diff --git a/mm/mprotect.c b/mm/mprotect.c index ab709023e9aa..d8c39370017d 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -454,7 +454,7 @@ 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); |