mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-08-23 09:19:51 +00:00
![Colin Cross](/assets/img/avatar_default.png)
In many userspace applications, and especially in VM based applications like Android uses heavily, there are multiple different allocators in use. At a minimum there is libc malloc and the stack, and in many cases there are libc malloc, the stack, direct syscalls to mmap anonymous memory, and multiple VM heaps (one for small objects, one for big objects, etc.). Each of these layers usually has its own tools to inspect its usage; malloc by compiling a debug version, the VM through heap inspection tools, and for direct syscalls there is usually no way to track them. On Android we heavily use a set of tools that use an extended version of the logic covered in Documentation/vm/pagemap.txt to walk all pages mapped in userspace and slice their usage by process, shared (COW) vs. unique mappings, backing, etc. This can account for real physical memory usage even in cases like fork without exec (which Android uses heavily to share as many private COW pages as possible between processes), Kernel SamePage Merging, and clean zero pages. It produces a measurement of the pages that only exist in that process (USS, for unique), and a measurement of the physical memory usage of that process with the cost of shared pages being evenly split between processes that share them (PSS). If all anonymous memory is indistinguishable then figuring out the real physical memory usage (PSS) of each heap requires either a pagemap walking tool that can understand the heap debugging of every layer, or for every layer's heap debugging tools to implement the pagemap walking logic, in which case it is hard to get a consistent view of memory across the whole system. Tracking the information in userspace leads to all sorts of problems. It either needs to be stored inside the process, which means every process has to have an API to export its current heap information upon request, or it has to be stored externally in a filesystem that somebody needs to clean up on crashes. It needs to be readable while the process is still running, so it has to have some sort of synchronization with every layer of userspace. Efficiently tracking the ranges requires reimplementing something like the kernel vma trees, and linking to it from every layer of userspace. It requires more memory, more syscalls, more runtime cost, and more complexity to separately track regions that the kernel is already tracking. This patch adds a field to /proc/pid/maps and /proc/pid/smaps to show a userspace-provided name for anonymous vmas. The names of named anonymous vmas are shown in /proc/pid/maps and /proc/pid/smaps as [anon:<name>]. 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 name length limit is 80 bytes including NUL-terminator and is checked to contain only printable ascii characters (including space), except '[',']','\','$' and '`'. Ascii strings are being used to have a descriptive identifiers for vmas, which can be understood by the users reading /proc/pid/maps or /proc/pid/smaps. Names can be standardized for a given system and they can include some variable parts such as the name of the allocator or a library, tid of the thread using it, etc. The name is stored in a pointer in the shared union in vm_area_struct that points to a null terminated string. Anonymous vmas with the same name (equivalent strings) and are otherwise mergeable will be merged. The name pointers are not shared between vmas even if they contain the same name. The name pointer is stored in a union with fields that are only used on file-backed mappings, so it does not increase memory usage. CONFIG_ANON_VMA_NAME kernel configuration is introduced to enable this feature. It keeps the feature disabled by default to prevent any additional memory overhead and to avoid confusing procfs parsers on systems which are not ready to support named anonymous vmas. The patch is based on the original patch developed by Colin Cross, more specifically on its latest version [1] posted upstream by Sumit Semwal. It used a userspace pointer to store vma names. In that design, name pointers could be shared between vmas. However during the last upstreaming attempt, Kees Cook raised concerns [2] about this approach and suggested to copy the name into kernel memory space, perform validity checks [3] and store as a string referenced from vm_area_struct. One big concern is about fork() performance which would need to strdup anonymous vma names. Dave Hansen suggested experimenting with worst-case scenario of forking a process with 64k vmas having longest possible names [4]. I ran this experiment on an ARM64 Android device and recorded a worst-case regression of almost 40% when forking such a process. This regression is addressed in the followup patch which replaces the pointer to a name with a refcounted structure that allows sharing the name pointer between vmas of the same name. Instead of duplicating the string during fork() or when splitting a vma it increments the refcount. [1] https://lore.kernel.org/linux-mm/20200901161459.11772-4-sumit.semwal@linaro.org/ [2] https://lore.kernel.org/linux-mm/202009031031.D32EF57ED@keescook/ [3] https://lore.kernel.org/linux-mm/202009031022.3834F692@keescook/ [4] https://lore.kernel.org/linux-mm/5d0358ab-8c47-2f5f-8e43-23b89d6a8e95@intel.com/ Changes for prctl(2) manual page (in the options section): PR_SET_VMA Sets an attribute specified in arg2 for virtual memory areas starting from the address specified in arg3 and spanning the size specified in arg4. arg5 specifies the value of the attribute to be set. Note that assigning an attribute to a virtual memory area might prevent it from being merged with adjacent virtual memory areas due to the difference in that attribute's value. Currently, arg2 must be one of: PR_SET_VMA_ANON_NAME Set a name for anonymous virtual memory areas. arg5 should be a pointer to a null-terminated string containing the name. The name length including null byte cannot exceed 80 bytes. If arg5 is NULL, the name of the appropriate anonymous virtual memory areas will be reset. The name can contain only printable ascii characters (including space), except '[',']','\','$' and '`'. This feature is available only if the kernel is built with the CONFIG_ANON_VMA_NAME option enabled. [surenb@google.com: docs: proc.rst: /proc/PID/maps: fix malformed table] Link: https://lkml.kernel.org/r/20211123185928.2513763-1-surenb@google.com [surenb: rebased over v5.15-rc6, replaced userpointer with a kernel copy, added input sanitization and CONFIG_ANON_VMA_NAME config. The bulk of the work here was done by Colin Cross, therefore, with his permission, keeping him as the author] Link: https://lkml.kernel.org/r/20211019215511.3771969-2-surenb@google.com Signed-off-by: Colin Cross <ccross@google.com> Signed-off-by: Suren Baghdasaryan <surenb@google.com> Reviewed-by: Kees Cook <keescook@chromium.org> Cc: Stephen Rothwell <sfr@canb.auug.org.au> Cc: Al Viro <viro@zeniv.linux.org.uk> Cc: Cyrill Gorcunov <gorcunov@openvz.org> Cc: Dave Hansen <dave.hansen@intel.com> Cc: David Rientjes <rientjes@google.com> Cc: "Eric W. Biederman" <ebiederm@xmission.com> Cc: Hugh Dickins <hughd@google.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jan Glauber <jan.glauber@gmail.com> Cc: Johannes Weiner <hannes@cmpxchg.org> Cc: John Stultz <john.stultz@linaro.org> Cc: Mel Gorman <mgorman@suse.de> Cc: Minchan Kim <minchan@kernel.org> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Pekka Enberg <penberg@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Rob Landley <rob@landley.net> Cc: "Serge E. Hallyn" <serge.hallyn@ubuntu.com> Cc: Shaohua Li <shli@fusionio.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
721 lines
18 KiB
C
721 lines
18 KiB
C
// SPDX-License-Identifier: GPL-2.0
|
|
/*
|
|
* mm/mprotect.c
|
|
*
|
|
* (C) Copyright 1994 Linus Torvalds
|
|
* (C) Copyright 2002 Christoph Hellwig
|
|
*
|
|
* Address space accounting code <alan@lxorguk.ukuu.org.uk>
|
|
* (C) Copyright 2002 Red Hat Inc, All Rights Reserved
|
|
*/
|
|
|
|
#include <linux/pagewalk.h>
|
|
#include <linux/hugetlb.h>
|
|
#include <linux/shm.h>
|
|
#include <linux/mman.h>
|
|
#include <linux/fs.h>
|
|
#include <linux/highmem.h>
|
|
#include <linux/security.h>
|
|
#include <linux/mempolicy.h>
|
|
#include <linux/personality.h>
|
|
#include <linux/syscalls.h>
|
|
#include <linux/swap.h>
|
|
#include <linux/swapops.h>
|
|
#include <linux/mmu_notifier.h>
|
|
#include <linux/migrate.h>
|
|
#include <linux/perf_event.h>
|
|
#include <linux/pkeys.h>
|
|
#include <linux/ksm.h>
|
|
#include <linux/uaccess.h>
|
|
#include <linux/mm_inline.h>
|
|
#include <linux/pgtable.h>
|
|
#include <asm/cacheflush.h>
|
|
#include <asm/mmu_context.h>
|
|
#include <asm/tlbflush.h>
|
|
|
|
#include "internal.h"
|
|
|
|
static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
|
|
unsigned long addr, unsigned long end, pgprot_t newprot,
|
|
unsigned long cp_flags)
|
|
{
|
|
pte_t *pte, oldpte;
|
|
spinlock_t *ptl;
|
|
unsigned long pages = 0;
|
|
int target_node = NUMA_NO_NODE;
|
|
bool dirty_accountable = cp_flags & MM_CP_DIRTY_ACCT;
|
|
bool prot_numa = cp_flags & MM_CP_PROT_NUMA;
|
|
bool uffd_wp = cp_flags & MM_CP_UFFD_WP;
|
|
bool uffd_wp_resolve = cp_flags & MM_CP_UFFD_WP_RESOLVE;
|
|
|
|
/*
|
|
* Can be called with only the mmap_lock for reading by
|
|
* prot_numa so we must check the pmd isn't constantly
|
|
* changing from under us from pmd_none to pmd_trans_huge
|
|
* and/or the other way around.
|
|
*/
|
|
if (pmd_trans_unstable(pmd))
|
|
return 0;
|
|
|
|
/*
|
|
* The pmd points to a regular pte so the pmd can't change
|
|
* from under us even if the mmap_lock is only hold for
|
|
* reading.
|
|
*/
|
|
pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
|
|
|
|
/* Get target node for single threaded private VMAs */
|
|
if (prot_numa && !(vma->vm_flags & VM_SHARED) &&
|
|
atomic_read(&vma->vm_mm->mm_users) == 1)
|
|
target_node = numa_node_id();
|
|
|
|
flush_tlb_batched_pending(vma->vm_mm);
|
|
arch_enter_lazy_mmu_mode();
|
|
do {
|
|
oldpte = *pte;
|
|
if (pte_present(oldpte)) {
|
|
pte_t ptent;
|
|
bool preserve_write = prot_numa && pte_write(oldpte);
|
|
|
|
/*
|
|
* Avoid trapping faults against the zero or KSM
|
|
* pages. See similar comment in change_huge_pmd.
|
|
*/
|
|
if (prot_numa) {
|
|
struct page *page;
|
|
|
|
/* Avoid TLB flush if possible */
|
|
if (pte_protnone(oldpte))
|
|
continue;
|
|
|
|
page = vm_normal_page(vma, addr, oldpte);
|
|
if (!page || PageKsm(page))
|
|
continue;
|
|
|
|
/* Also skip shared copy-on-write pages */
|
|
if (is_cow_mapping(vma->vm_flags) &&
|
|
page_mapcount(page) != 1)
|
|
continue;
|
|
|
|
/*
|
|
* While migration can move some dirty pages,
|
|
* it cannot move them all from MIGRATE_ASYNC
|
|
* context.
|
|
*/
|
|
if (page_is_file_lru(page) && PageDirty(page))
|
|
continue;
|
|
|
|
/*
|
|
* Don't mess with PTEs if page is already on the node
|
|
* a single-threaded process is running on.
|
|
*/
|
|
if (target_node == page_to_nid(page))
|
|
continue;
|
|
}
|
|
|
|
oldpte = ptep_modify_prot_start(vma, addr, pte);
|
|
ptent = pte_modify(oldpte, newprot);
|
|
if (preserve_write)
|
|
ptent = pte_mk_savedwrite(ptent);
|
|
|
|
if (uffd_wp) {
|
|
ptent = pte_wrprotect(ptent);
|
|
ptent = pte_mkuffd_wp(ptent);
|
|
} else if (uffd_wp_resolve) {
|
|
/*
|
|
* Leave the write bit to be handled
|
|
* by PF interrupt handler, then
|
|
* things like COW could be properly
|
|
* handled.
|
|
*/
|
|
ptent = pte_clear_uffd_wp(ptent);
|
|
}
|
|
|
|
/* Avoid taking write faults for known dirty pages */
|
|
if (dirty_accountable && pte_dirty(ptent) &&
|
|
(pte_soft_dirty(ptent) ||
|
|
!(vma->vm_flags & VM_SOFTDIRTY))) {
|
|
ptent = pte_mkwrite(ptent);
|
|
}
|
|
ptep_modify_prot_commit(vma, addr, pte, oldpte, ptent);
|
|
pages++;
|
|
} else if (is_swap_pte(oldpte)) {
|
|
swp_entry_t entry = pte_to_swp_entry(oldpte);
|
|
pte_t newpte;
|
|
|
|
if (is_writable_migration_entry(entry)) {
|
|
/*
|
|
* A protection check is difficult so
|
|
* just be safe and disable write
|
|
*/
|
|
entry = make_readable_migration_entry(
|
|
swp_offset(entry));
|
|
newpte = swp_entry_to_pte(entry);
|
|
if (pte_swp_soft_dirty(oldpte))
|
|
newpte = pte_swp_mksoft_dirty(newpte);
|
|
if (pte_swp_uffd_wp(oldpte))
|
|
newpte = pte_swp_mkuffd_wp(newpte);
|
|
} else if (is_writable_device_private_entry(entry)) {
|
|
/*
|
|
* We do not preserve soft-dirtiness. See
|
|
* copy_one_pte() for explanation.
|
|
*/
|
|
entry = make_readable_device_private_entry(
|
|
swp_offset(entry));
|
|
newpte = swp_entry_to_pte(entry);
|
|
if (pte_swp_uffd_wp(oldpte))
|
|
newpte = pte_swp_mkuffd_wp(newpte);
|
|
} else if (is_writable_device_exclusive_entry(entry)) {
|
|
entry = make_readable_device_exclusive_entry(
|
|
swp_offset(entry));
|
|
newpte = swp_entry_to_pte(entry);
|
|
if (pte_swp_soft_dirty(oldpte))
|
|
newpte = pte_swp_mksoft_dirty(newpte);
|
|
if (pte_swp_uffd_wp(oldpte))
|
|
newpte = pte_swp_mkuffd_wp(newpte);
|
|
} else {
|
|
newpte = oldpte;
|
|
}
|
|
|
|
if (uffd_wp)
|
|
newpte = pte_swp_mkuffd_wp(newpte);
|
|
else if (uffd_wp_resolve)
|
|
newpte = pte_swp_clear_uffd_wp(newpte);
|
|
|
|
if (!pte_same(oldpte, newpte)) {
|
|
set_pte_at(vma->vm_mm, addr, pte, newpte);
|
|
pages++;
|
|
}
|
|
}
|
|
} while (pte++, addr += PAGE_SIZE, addr != end);
|
|
arch_leave_lazy_mmu_mode();
|
|
pte_unmap_unlock(pte - 1, ptl);
|
|
|
|
return pages;
|
|
}
|
|
|
|
/*
|
|
* Used when setting automatic NUMA hinting protection where it is
|
|
* critical that a numa hinting PMD is not confused with a bad PMD.
|
|
*/
|
|
static inline int pmd_none_or_clear_bad_unless_trans_huge(pmd_t *pmd)
|
|
{
|
|
pmd_t pmdval = pmd_read_atomic(pmd);
|
|
|
|
/* See pmd_none_or_trans_huge_or_clear_bad for info on barrier */
|
|
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
|
|
barrier();
|
|
#endif
|
|
|
|
if (pmd_none(pmdval))
|
|
return 1;
|
|
if (pmd_trans_huge(pmdval))
|
|
return 0;
|
|
if (unlikely(pmd_bad(pmdval))) {
|
|
pmd_clear_bad(pmd);
|
|
return 1;
|
|
}
|
|
|
|
return 0;
|
|
}
|
|
|
|
static inline unsigned long change_pmd_range(struct vm_area_struct *vma,
|
|
pud_t *pud, unsigned long addr, unsigned long end,
|
|
pgprot_t newprot, unsigned long cp_flags)
|
|
{
|
|
pmd_t *pmd;
|
|
unsigned long next;
|
|
unsigned long pages = 0;
|
|
unsigned long nr_huge_updates = 0;
|
|
struct mmu_notifier_range range;
|
|
|
|
range.start = 0;
|
|
|
|
pmd = pmd_offset(pud, addr);
|
|
do {
|
|
unsigned long this_pages;
|
|
|
|
next = pmd_addr_end(addr, end);
|
|
|
|
/*
|
|
* Automatic NUMA balancing walks the tables with mmap_lock
|
|
* held for read. It's possible a parallel update to occur
|
|
* between pmd_trans_huge() and a pmd_none_or_clear_bad()
|
|
* check leading to a false positive and clearing.
|
|
* Hence, it's necessary to atomically read the PMD value
|
|
* for all the checks.
|
|
*/
|
|
if (!is_swap_pmd(*pmd) && !pmd_devmap(*pmd) &&
|
|
pmd_none_or_clear_bad_unless_trans_huge(pmd))
|
|
goto next;
|
|
|
|
/* invoke the mmu notifier if the pmd is populated */
|
|
if (!range.start) {
|
|
mmu_notifier_range_init(&range,
|
|
MMU_NOTIFY_PROTECTION_VMA, 0,
|
|
vma, vma->vm_mm, addr, end);
|
|
mmu_notifier_invalidate_range_start(&range);
|
|
}
|
|
|
|
if (is_swap_pmd(*pmd) || pmd_trans_huge(*pmd) || pmd_devmap(*pmd)) {
|
|
if (next - addr != HPAGE_PMD_SIZE) {
|
|
__split_huge_pmd(vma, pmd, addr, false, NULL);
|
|
} else {
|
|
int nr_ptes = change_huge_pmd(vma, pmd, addr,
|
|
newprot, cp_flags);
|
|
|
|
if (nr_ptes) {
|
|
if (nr_ptes == HPAGE_PMD_NR) {
|
|
pages += HPAGE_PMD_NR;
|
|
nr_huge_updates++;
|
|
}
|
|
|
|
/* huge pmd was handled */
|
|
goto next;
|
|
}
|
|
}
|
|
/* fall through, the trans huge pmd just split */
|
|
}
|
|
this_pages = change_pte_range(vma, pmd, addr, next, newprot,
|
|
cp_flags);
|
|
pages += this_pages;
|
|
next:
|
|
cond_resched();
|
|
} while (pmd++, addr = next, addr != end);
|
|
|
|
if (range.start)
|
|
mmu_notifier_invalidate_range_end(&range);
|
|
|
|
if (nr_huge_updates)
|
|
count_vm_numa_events(NUMA_HUGE_PTE_UPDATES, nr_huge_updates);
|
|
return pages;
|
|
}
|
|
|
|
static inline unsigned long change_pud_range(struct vm_area_struct *vma,
|
|
p4d_t *p4d, unsigned long addr, unsigned long end,
|
|
pgprot_t newprot, unsigned long cp_flags)
|
|
{
|
|
pud_t *pud;
|
|
unsigned long next;
|
|
unsigned long pages = 0;
|
|
|
|
pud = pud_offset(p4d, addr);
|
|
do {
|
|
next = pud_addr_end(addr, end);
|
|
if (pud_none_or_clear_bad(pud))
|
|
continue;
|
|
pages += change_pmd_range(vma, pud, addr, next, newprot,
|
|
cp_flags);
|
|
} while (pud++, addr = next, addr != end);
|
|
|
|
return pages;
|
|
}
|
|
|
|
static inline unsigned long change_p4d_range(struct vm_area_struct *vma,
|
|
pgd_t *pgd, unsigned long addr, unsigned long end,
|
|
pgprot_t newprot, unsigned long cp_flags)
|
|
{
|
|
p4d_t *p4d;
|
|
unsigned long next;
|
|
unsigned long pages = 0;
|
|
|
|
p4d = p4d_offset(pgd, addr);
|
|
do {
|
|
next = p4d_addr_end(addr, end);
|
|
if (p4d_none_or_clear_bad(p4d))
|
|
continue;
|
|
pages += change_pud_range(vma, p4d, addr, next, newprot,
|
|
cp_flags);
|
|
} while (p4d++, addr = next, addr != end);
|
|
|
|
return pages;
|
|
}
|
|
|
|
static unsigned long change_protection_range(struct vm_area_struct *vma,
|
|
unsigned long addr, unsigned long end, pgprot_t newprot,
|
|
unsigned long cp_flags)
|
|
{
|
|
struct mm_struct *mm = vma->vm_mm;
|
|
pgd_t *pgd;
|
|
unsigned long next;
|
|
unsigned long start = addr;
|
|
unsigned long pages = 0;
|
|
|
|
BUG_ON(addr >= end);
|
|
pgd = pgd_offset(mm, addr);
|
|
flush_cache_range(vma, addr, end);
|
|
inc_tlb_flush_pending(mm);
|
|
do {
|
|
next = pgd_addr_end(addr, end);
|
|
if (pgd_none_or_clear_bad(pgd))
|
|
continue;
|
|
pages += change_p4d_range(vma, pgd, addr, next, newprot,
|
|
cp_flags);
|
|
} while (pgd++, addr = next, addr != end);
|
|
|
|
/* Only flush the TLB if we actually modified any entries: */
|
|
if (pages)
|
|
flush_tlb_range(vma, start, end);
|
|
dec_tlb_flush_pending(mm);
|
|
|
|
return pages;
|
|
}
|
|
|
|
unsigned long change_protection(struct vm_area_struct *vma, unsigned long start,
|
|
unsigned long end, pgprot_t newprot,
|
|
unsigned long cp_flags)
|
|
{
|
|
unsigned long pages;
|
|
|
|
BUG_ON((cp_flags & MM_CP_UFFD_WP_ALL) == MM_CP_UFFD_WP_ALL);
|
|
|
|
if (is_vm_hugetlb_page(vma))
|
|
pages = hugetlb_change_protection(vma, start, end, newprot);
|
|
else
|
|
pages = change_protection_range(vma, start, end, newprot,
|
|
cp_flags);
|
|
|
|
return pages;
|
|
}
|
|
|
|
static int prot_none_pte_entry(pte_t *pte, unsigned long addr,
|
|
unsigned long next, struct mm_walk *walk)
|
|
{
|
|
return pfn_modify_allowed(pte_pfn(*pte), *(pgprot_t *)(walk->private)) ?
|
|
0 : -EACCES;
|
|
}
|
|
|
|
static int prot_none_hugetlb_entry(pte_t *pte, unsigned long hmask,
|
|
unsigned long addr, unsigned long next,
|
|
struct mm_walk *walk)
|
|
{
|
|
return pfn_modify_allowed(pte_pfn(*pte), *(pgprot_t *)(walk->private)) ?
|
|
0 : -EACCES;
|
|
}
|
|
|
|
static int prot_none_test(unsigned long addr, unsigned long next,
|
|
struct mm_walk *walk)
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
static const struct mm_walk_ops prot_none_walk_ops = {
|
|
.pte_entry = prot_none_pte_entry,
|
|
.hugetlb_entry = prot_none_hugetlb_entry,
|
|
.test_walk = prot_none_test,
|
|
};
|
|
|
|
int
|
|
mprotect_fixup(struct vm_area_struct *vma, struct vm_area_struct **pprev,
|
|
unsigned long start, unsigned long end, unsigned long newflags)
|
|
{
|
|
struct mm_struct *mm = vma->vm_mm;
|
|
unsigned long oldflags = vma->vm_flags;
|
|
long nrpages = (end - start) >> PAGE_SHIFT;
|
|
unsigned long charged = 0;
|
|
pgoff_t pgoff;
|
|
int error;
|
|
int dirty_accountable = 0;
|
|
|
|
if (newflags == oldflags) {
|
|
*pprev = vma;
|
|
return 0;
|
|
}
|
|
|
|
/*
|
|
* Do PROT_NONE PFN permission checks here when we can still
|
|
* bail out without undoing a lot of state. This is a rather
|
|
* uncommon case, so doesn't need to be very optimized.
|
|
*/
|
|
if (arch_has_pfn_modify_check() &&
|
|
(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)) &&
|
|
(newflags & VM_ACCESS_FLAGS) == 0) {
|
|
pgprot_t new_pgprot = vm_get_page_prot(newflags);
|
|
|
|
error = walk_page_range(current->mm, start, end,
|
|
&prot_none_walk_ops, &new_pgprot);
|
|
if (error)
|
|
return error;
|
|
}
|
|
|
|
/*
|
|
* If we make a private mapping writable we increase our commit;
|
|
* but (without finer accounting) cannot reduce our commit if we
|
|
* make it unwritable again. hugetlb mapping were accounted for
|
|
* even if read-only so there is no need to account for them here
|
|
*/
|
|
if (newflags & VM_WRITE) {
|
|
/* Check space limits when area turns into data. */
|
|
if (!may_expand_vm(mm, newflags, nrpages) &&
|
|
may_expand_vm(mm, oldflags, nrpages))
|
|
return -ENOMEM;
|
|
if (!(oldflags & (VM_ACCOUNT|VM_WRITE|VM_HUGETLB|
|
|
VM_SHARED|VM_NORESERVE))) {
|
|
charged = nrpages;
|
|
if (security_vm_enough_memory_mm(mm, charged))
|
|
return -ENOMEM;
|
|
newflags |= VM_ACCOUNT;
|
|
}
|
|
}
|
|
|
|
/*
|
|
* First try to merge with previous and/or next vma.
|
|
*/
|
|
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_anon_name(vma));
|
|
if (*pprev) {
|
|
vma = *pprev;
|
|
VM_WARN_ON((vma->vm_flags ^ newflags) & ~VM_SOFTDIRTY);
|
|
goto success;
|
|
}
|
|
|
|
*pprev = vma;
|
|
|
|
if (start != vma->vm_start) {
|
|
error = split_vma(mm, vma, start, 1);
|
|
if (error)
|
|
goto fail;
|
|
}
|
|
|
|
if (end != vma->vm_end) {
|
|
error = split_vma(mm, vma, end, 0);
|
|
if (error)
|
|
goto fail;
|
|
}
|
|
|
|
success:
|
|
/*
|
|
* vm_flags and vm_page_prot are protected by the mmap_lock
|
|
* held in write mode.
|
|
*/
|
|
vma->vm_flags = newflags;
|
|
dirty_accountable = vma_wants_writenotify(vma, vma->vm_page_prot);
|
|
vma_set_page_prot(vma);
|
|
|
|
change_protection(vma, start, end, vma->vm_page_prot,
|
|
dirty_accountable ? MM_CP_DIRTY_ACCT : 0);
|
|
|
|
/*
|
|
* Private VM_LOCKED VMA becoming writable: trigger COW to avoid major
|
|
* fault on access.
|
|
*/
|
|
if ((oldflags & (VM_WRITE | VM_SHARED | VM_LOCKED)) == VM_LOCKED &&
|
|
(newflags & VM_WRITE)) {
|
|
populate_vma_page_range(vma, start, end, NULL);
|
|
}
|
|
|
|
vm_stat_account(mm, oldflags, -nrpages);
|
|
vm_stat_account(mm, newflags, nrpages);
|
|
perf_event_mmap(vma);
|
|
return 0;
|
|
|
|
fail:
|
|
vm_unacct_memory(charged);
|
|
return error;
|
|
}
|
|
|
|
/*
|
|
* pkey==-1 when doing a legacy mprotect()
|
|
*/
|
|
static int do_mprotect_pkey(unsigned long start, size_t len,
|
|
unsigned long prot, int pkey)
|
|
{
|
|
unsigned long nstart, end, tmp, reqprot;
|
|
struct vm_area_struct *vma, *prev;
|
|
int error = -EINVAL;
|
|
const int grows = prot & (PROT_GROWSDOWN|PROT_GROWSUP);
|
|
const bool rier = (current->personality & READ_IMPLIES_EXEC) &&
|
|
(prot & PROT_READ);
|
|
|
|
start = untagged_addr(start);
|
|
|
|
prot &= ~(PROT_GROWSDOWN|PROT_GROWSUP);
|
|
if (grows == (PROT_GROWSDOWN|PROT_GROWSUP)) /* can't be both */
|
|
return -EINVAL;
|
|
|
|
if (start & ~PAGE_MASK)
|
|
return -EINVAL;
|
|
if (!len)
|
|
return 0;
|
|
len = PAGE_ALIGN(len);
|
|
end = start + len;
|
|
if (end <= start)
|
|
return -ENOMEM;
|
|
if (!arch_validate_prot(prot, start))
|
|
return -EINVAL;
|
|
|
|
reqprot = prot;
|
|
|
|
if (mmap_write_lock_killable(current->mm))
|
|
return -EINTR;
|
|
|
|
/*
|
|
* If userspace did not allocate the pkey, do not let
|
|
* them use it here.
|
|
*/
|
|
error = -EINVAL;
|
|
if ((pkey != -1) && !mm_pkey_is_allocated(current->mm, pkey))
|
|
goto out;
|
|
|
|
vma = find_vma(current->mm, start);
|
|
error = -ENOMEM;
|
|
if (!vma)
|
|
goto out;
|
|
|
|
if (unlikely(grows & PROT_GROWSDOWN)) {
|
|
if (vma->vm_start >= end)
|
|
goto out;
|
|
start = vma->vm_start;
|
|
error = -EINVAL;
|
|
if (!(vma->vm_flags & VM_GROWSDOWN))
|
|
goto out;
|
|
} else {
|
|
if (vma->vm_start > start)
|
|
goto out;
|
|
if (unlikely(grows & PROT_GROWSUP)) {
|
|
end = vma->vm_end;
|
|
error = -EINVAL;
|
|
if (!(vma->vm_flags & VM_GROWSUP))
|
|
goto out;
|
|
}
|
|
}
|
|
|
|
if (start > vma->vm_start)
|
|
prev = vma;
|
|
else
|
|
prev = vma->vm_prev;
|
|
|
|
for (nstart = start ; ; ) {
|
|
unsigned long mask_off_old_flags;
|
|
unsigned long newflags;
|
|
int new_vma_pkey;
|
|
|
|
/* Here we know that vma->vm_start <= nstart < vma->vm_end. */
|
|
|
|
/* Does the application expect PROT_READ to imply PROT_EXEC */
|
|
if (rier && (vma->vm_flags & VM_MAYEXEC))
|
|
prot |= PROT_EXEC;
|
|
|
|
/*
|
|
* Each mprotect() call explicitly passes r/w/x permissions.
|
|
* If a permission is not passed to mprotect(), it must be
|
|
* cleared from the VMA.
|
|
*/
|
|
mask_off_old_flags = VM_READ | VM_WRITE | VM_EXEC |
|
|
VM_FLAGS_CLEAR;
|
|
|
|
new_vma_pkey = arch_override_mprotect_pkey(vma, prot, pkey);
|
|
newflags = calc_vm_prot_bits(prot, new_vma_pkey);
|
|
newflags |= (vma->vm_flags & ~mask_off_old_flags);
|
|
|
|
/* newflags >> 4 shift VM_MAY% in place of VM_% */
|
|
if ((newflags & ~(newflags >> 4)) & VM_ACCESS_FLAGS) {
|
|
error = -EACCES;
|
|
goto out;
|
|
}
|
|
|
|
/* Allow architectures to sanity-check the new flags */
|
|
if (!arch_validate_flags(newflags)) {
|
|
error = -EINVAL;
|
|
goto out;
|
|
}
|
|
|
|
error = security_file_mprotect(vma, reqprot, prot);
|
|
if (error)
|
|
goto out;
|
|
|
|
tmp = vma->vm_end;
|
|
if (tmp > end)
|
|
tmp = end;
|
|
|
|
if (vma->vm_ops && vma->vm_ops->mprotect) {
|
|
error = vma->vm_ops->mprotect(vma, nstart, tmp, newflags);
|
|
if (error)
|
|
goto out;
|
|
}
|
|
|
|
error = mprotect_fixup(vma, &prev, nstart, tmp, newflags);
|
|
if (error)
|
|
goto out;
|
|
|
|
nstart = tmp;
|
|
|
|
if (nstart < prev->vm_end)
|
|
nstart = prev->vm_end;
|
|
if (nstart >= end)
|
|
goto out;
|
|
|
|
vma = prev->vm_next;
|
|
if (!vma || vma->vm_start != nstart) {
|
|
error = -ENOMEM;
|
|
goto out;
|
|
}
|
|
prot = reqprot;
|
|
}
|
|
out:
|
|
mmap_write_unlock(current->mm);
|
|
return error;
|
|
}
|
|
|
|
SYSCALL_DEFINE3(mprotect, unsigned long, start, size_t, len,
|
|
unsigned long, prot)
|
|
{
|
|
return do_mprotect_pkey(start, len, prot, -1);
|
|
}
|
|
|
|
#ifdef CONFIG_ARCH_HAS_PKEYS
|
|
|
|
SYSCALL_DEFINE4(pkey_mprotect, unsigned long, start, size_t, len,
|
|
unsigned long, prot, int, pkey)
|
|
{
|
|
return do_mprotect_pkey(start, len, prot, pkey);
|
|
}
|
|
|
|
SYSCALL_DEFINE2(pkey_alloc, unsigned long, flags, unsigned long, init_val)
|
|
{
|
|
int pkey;
|
|
int ret;
|
|
|
|
/* No flags supported yet. */
|
|
if (flags)
|
|
return -EINVAL;
|
|
/* check for unsupported init values */
|
|
if (init_val & ~PKEY_ACCESS_MASK)
|
|
return -EINVAL;
|
|
|
|
mmap_write_lock(current->mm);
|
|
pkey = mm_pkey_alloc(current->mm);
|
|
|
|
ret = -ENOSPC;
|
|
if (pkey == -1)
|
|
goto out;
|
|
|
|
ret = arch_set_user_pkey_access(current, pkey, init_val);
|
|
if (ret) {
|
|
mm_pkey_free(current->mm, pkey);
|
|
goto out;
|
|
}
|
|
ret = pkey;
|
|
out:
|
|
mmap_write_unlock(current->mm);
|
|
return ret;
|
|
}
|
|
|
|
SYSCALL_DEFINE1(pkey_free, int, pkey)
|
|
{
|
|
int ret;
|
|
|
|
mmap_write_lock(current->mm);
|
|
ret = mm_pkey_free(current->mm, pkey);
|
|
mmap_write_unlock(current->mm);
|
|
|
|
/*
|
|
* We could provide warnings or errors if any VMA still
|
|
* has the pkey set here.
|
|
*/
|
|
return ret;
|
|
}
|
|
|
|
#endif /* CONFIG_ARCH_HAS_PKEYS */
|