From 102a0743326a03cd1a1202ceda21e175b7d3575c Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Tue, 20 Feb 2024 01:20:52 +0000
Subject: [PATCH] add new system file
---
kernel/mm/util.c | 480 ++++++++++++++++++++++++++++++++++++++++++++---------------
1 files changed, 355 insertions(+), 125 deletions(-)
diff --git a/kernel/mm/util.c b/kernel/mm/util.c
index 65b4ea6..6ed9861 100644
--- a/kernel/mm/util.c
+++ b/kernel/mm/util.c
@@ -1,3 +1,4 @@
+// SPDX-License-Identifier: GPL-2.0-only
#include <linux/mm.h>
#include <linux/slab.h>
#include <linux/string.h>
@@ -6,6 +7,7 @@
#include <linux/err.h>
#include <linux/sched.h>
#include <linux/sched/mm.h>
+#include <linux/sched/signal.h>
#include <linux/sched/task_stack.h>
#include <linux/security.h>
#include <linux/swap.h>
@@ -14,17 +16,21 @@
#include <linux/hugetlb.h>
#include <linux/vmalloc.h>
#include <linux/userfaultfd_k.h>
+#include <linux/elf.h>
+#include <linux/elf-randomize.h>
+#include <linux/personality.h>
+#include <linux/random.h>
+#include <linux/processor.h>
+#include <linux/sizes.h>
+#include <linux/compat.h>
-#include <asm/sections.h>
#include <linux/uaccess.h>
#include "internal.h"
-
-static inline int is_kernel_rodata(unsigned long addr)
-{
- return addr >= (unsigned long)__start_rodata &&
- addr < (unsigned long)__end_rodata;
-}
+#ifndef __GENKSYMS__
+#include <trace/hooks/syscall_check.h>
+#include <trace/hooks/mm.h>
+#endif
/**
* kfree_const - conditionally free memory
@@ -43,6 +49,8 @@
* kstrdup - allocate space for and copy an existing string
* @s: the string to duplicate
* @gfp: the GFP mask used in the kmalloc() call when allocating memory
+ *
+ * Return: newly allocated copy of @s or %NULL in case of error
*/
char *kstrdup(const char *s, gfp_t gfp)
{
@@ -65,9 +73,11 @@
* @s: the string to duplicate
* @gfp: the GFP mask used in the kmalloc() call when allocating memory
*
- * Function returns source string if it is in .rodata section otherwise it
- * fallbacks to kstrdup.
- * Strings allocated by kstrdup_const should be freed by kfree_const.
+ * Note: Strings allocated by kstrdup_const should be freed by kfree_const and
+ * must not be passed to krealloc().
+ *
+ * Return: source string if it is in .rodata section otherwise
+ * fallback to kstrdup.
*/
const char *kstrdup_const(const char *s, gfp_t gfp)
{
@@ -85,6 +95,8 @@
* @gfp: the GFP mask used in the kmalloc() call when allocating memory
*
* Note: Use kmemdup_nul() instead if the size is known exactly.
+ *
+ * Return: newly allocated copy of @s or %NULL in case of error
*/
char *kstrndup(const char *s, size_t max, gfp_t gfp)
{
@@ -110,6 +122,8 @@
* @src: memory region to duplicate
* @len: memory region length
* @gfp: GFP mask to use
+ *
+ * Return: newly allocated copy of @src or %NULL in case of error
*/
void *kmemdup(const void *src, size_t len, gfp_t gfp)
{
@@ -127,6 +141,9 @@
* @s: The data to stringify
* @len: The size of the data
* @gfp: the GFP mask used in the kmalloc() call when allocating memory
+ *
+ * Return: newly allocated copy of @s with NUL-termination or %NULL in
+ * case of error
*/
char *kmemdup_nul(const char *s, size_t len, gfp_t gfp)
{
@@ -150,14 +167,14 @@
* @src: source address in user space
* @len: number of bytes to copy
*
- * Returns an ERR_PTR() on failure. Result is physically
+ * Return: an ERR_PTR() on failure. Result is physically
* contiguous, to be freed by kfree().
*/
void *memdup_user(const void __user *src, size_t len)
{
void *p;
- p = kmalloc_track_caller(len, GFP_USER);
+ p = kmalloc_track_caller(len, GFP_USER | __GFP_NOWARN);
if (!p)
return ERR_PTR(-ENOMEM);
@@ -176,7 +193,7 @@
* @src: source address in user space
* @len: number of bytes to copy
*
- * Returns an ERR_PTR() on failure. Result may be not
+ * Return: an ERR_PTR() on failure. Result may be not
* physically contiguous. Use kvfree() to free.
*/
void *vmemdup_user(const void __user *src, size_t len)
@@ -200,6 +217,8 @@
* strndup_user - duplicate an existing string from user space
* @s: The string to duplicate
* @n: Maximum number of bytes to copy, including the trailing NUL.
+ *
+ * Return: newly allocated copy of @s or an ERR_PTR() in case of error
*/
char *strndup_user(const char __user *s, long n)
{
@@ -231,7 +250,7 @@
* @src: source address in user space
* @len: number of bytes to copy
*
- * Returns an ERR_PTR() on failure.
+ * Return: an ERR_PTR() on failure.
*/
void *memdup_user_nul(const void __user *src, size_t len)
{
@@ -257,7 +276,7 @@
EXPORT_SYMBOL(memdup_user_nul);
void __vma_link_list(struct mm_struct *mm, struct vm_area_struct *vma,
- struct vm_area_struct *prev, struct rb_node *rb_parent)
+ struct vm_area_struct *prev)
{
struct vm_area_struct *next;
@@ -266,16 +285,26 @@
next = prev->vm_next;
prev->vm_next = vma;
} else {
+ next = mm->mmap;
mm->mmap = vma;
- if (rb_parent)
- next = rb_entry(rb_parent,
- struct vm_area_struct, vm_rb);
- else
- next = NULL;
}
vma->vm_next = next;
if (next)
next->vm_prev = vma;
+}
+
+void __vma_unlink_list(struct mm_struct *mm, struct vm_area_struct *vma)
+{
+ struct vm_area_struct *prev, *next;
+
+ next = vma->vm_next;
+ prev = vma->vm_prev;
+ if (prev)
+ prev->vm_next = next;
+ else
+ mm->mmap = next;
+ if (next)
+ next->vm_prev = prev;
}
/* Check if the vma is being used as a stack by this task */
@@ -286,7 +315,138 @@
return (vma->vm_start <= KSTK_ESP(t) && vma->vm_end >= KSTK_ESP(t));
}
-#if defined(CONFIG_MMU) && !defined(HAVE_ARCH_PICK_MMAP_LAYOUT)
+#ifndef STACK_RND_MASK
+#define STACK_RND_MASK (0x7ff >> (PAGE_SHIFT - 12)) /* 8MB of VA */
+#endif
+
+unsigned long randomize_stack_top(unsigned long stack_top)
+{
+ unsigned long random_variable = 0;
+
+ if (current->flags & PF_RANDOMIZE) {
+ random_variable = get_random_long();
+ random_variable &= STACK_RND_MASK;
+ random_variable <<= PAGE_SHIFT;
+ }
+#ifdef CONFIG_STACK_GROWSUP
+ return PAGE_ALIGN(stack_top) + random_variable;
+#else
+ return PAGE_ALIGN(stack_top) - random_variable;
+#endif
+}
+
+/**
+ * randomize_page - Generate a random, page aligned address
+ * @start: The smallest acceptable address the caller will take.
+ * @range: The size of the area, starting at @start, within which the
+ * random address must fall.
+ *
+ * If @start + @range would overflow, @range is capped.
+ *
+ * NOTE: Historical use of randomize_range, which this replaces, presumed that
+ * @start was already page aligned. We now align it regardless.
+ *
+ * Return: A page aligned address within [start, start + range). On error,
+ * @start is returned.
+ */
+unsigned long randomize_page(unsigned long start, unsigned long range)
+{
+ if (!PAGE_ALIGNED(start)) {
+ range -= PAGE_ALIGN(start) - start;
+ start = PAGE_ALIGN(start);
+ }
+
+ if (start > ULONG_MAX - range)
+ range = ULONG_MAX - start;
+
+ range >>= PAGE_SHIFT;
+
+ if (range == 0)
+ return start;
+
+ return start + (get_random_long() % range << PAGE_SHIFT);
+}
+
+#ifdef CONFIG_ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT
+unsigned long arch_randomize_brk(struct mm_struct *mm)
+{
+ /* Is the current task 32bit ? */
+ if (!IS_ENABLED(CONFIG_64BIT) || is_compat_task())
+ return randomize_page(mm->brk, SZ_32M);
+
+ return randomize_page(mm->brk, SZ_1G);
+}
+
+unsigned long arch_mmap_rnd(void)
+{
+ unsigned long rnd;
+
+#ifdef CONFIG_HAVE_ARCH_MMAP_RND_COMPAT_BITS
+ if (is_compat_task())
+ rnd = get_random_long() & ((1UL << mmap_rnd_compat_bits) - 1);
+ else
+#endif /* CONFIG_HAVE_ARCH_MMAP_RND_COMPAT_BITS */
+ rnd = get_random_long() & ((1UL << mmap_rnd_bits) - 1);
+
+ return rnd << PAGE_SHIFT;
+}
+EXPORT_SYMBOL_GPL(arch_mmap_rnd);
+
+static int mmap_is_legacy(struct rlimit *rlim_stack)
+{
+ if (current->personality & ADDR_COMPAT_LAYOUT)
+ return 1;
+
+ if (rlim_stack->rlim_cur == RLIM_INFINITY)
+ return 1;
+
+ return sysctl_legacy_va_layout;
+}
+
+/*
+ * Leave enough space between the mmap area and the stack to honour ulimit in
+ * the face of randomisation.
+ */
+#define MIN_GAP (SZ_128M)
+#define MAX_GAP (STACK_TOP / 6 * 5)
+
+static unsigned long mmap_base(unsigned long rnd, struct rlimit *rlim_stack)
+{
+ unsigned long gap = rlim_stack->rlim_cur;
+ unsigned long pad = stack_guard_gap;
+
+ /* Account for stack randomization if necessary */
+ if (current->flags & PF_RANDOMIZE)
+ pad += (STACK_RND_MASK << PAGE_SHIFT);
+
+ /* Values close to RLIM_INFINITY can overflow. */
+ if (gap + pad > gap)
+ gap += pad;
+
+ if (gap < MIN_GAP)
+ gap = MIN_GAP;
+ else if (gap > MAX_GAP)
+ gap = MAX_GAP;
+
+ return PAGE_ALIGN(STACK_TOP - gap - rnd);
+}
+
+void arch_pick_mmap_layout(struct mm_struct *mm, struct rlimit *rlim_stack)
+{
+ unsigned long random_factor = 0UL;
+
+ if (current->flags & PF_RANDOMIZE)
+ random_factor = arch_mmap_rnd();
+
+ if (mmap_is_legacy(rlim_stack)) {
+ mm->mmap_base = TASK_UNMAPPED_BASE + random_factor;
+ mm->get_unmapped_area = arch_get_unmapped_area;
+ } else {
+ mm->mmap_base = mmap_base(random_factor, rlim_stack);
+ mm->get_unmapped_area = arch_get_unmapped_area_topdown;
+ }
+}
+#elif defined(CONFIG_MMU) && !defined(HAVE_ARCH_PICK_MMAP_LAYOUT)
void arch_pick_mmap_layout(struct mm_struct *mm, struct rlimit *rlim_stack)
{
mm->mmap_base = TASK_UNMAPPED_BASE;
@@ -294,52 +454,79 @@
}
#endif
-/*
- * Like get_user_pages_fast() except its IRQ-safe in that it won't fall
- * back to the regular GUP.
- * Note a difference with get_user_pages_fast: this always returns the
- * number of pages pinned, 0 if no pages were pinned.
- * If the architecture does not support this function, simply return with no
- * pages pinned.
+/**
+ * __account_locked_vm - account locked pages to an mm's locked_vm
+ * @mm: mm to account against
+ * @pages: number of pages to account
+ * @inc: %true if @pages should be considered positive, %false if not
+ * @task: task used to check RLIMIT_MEMLOCK
+ * @bypass_rlim: %true if checking RLIMIT_MEMLOCK should be skipped
+ *
+ * Assumes @task and @mm are valid (i.e. at least one reference on each), and
+ * that mmap_lock is held as writer.
+ *
+ * Return:
+ * * 0 on success
+ * * -ENOMEM if RLIMIT_MEMLOCK would be exceeded.
*/
-int __weak __get_user_pages_fast(unsigned long start,
- int nr_pages, int write, struct page **pages)
+int __account_locked_vm(struct mm_struct *mm, unsigned long pages, bool inc,
+ struct task_struct *task, bool bypass_rlim)
{
- return 0;
+ unsigned long locked_vm, limit;
+ int ret = 0;
+
+ mmap_assert_write_locked(mm);
+
+ locked_vm = mm->locked_vm;
+ if (inc) {
+ if (!bypass_rlim) {
+ limit = task_rlimit(task, RLIMIT_MEMLOCK) >> PAGE_SHIFT;
+ if (locked_vm + pages > limit)
+ ret = -ENOMEM;
+ }
+ if (!ret)
+ mm->locked_vm = locked_vm + pages;
+ } else {
+ WARN_ON_ONCE(pages > locked_vm);
+ mm->locked_vm = locked_vm - pages;
+ }
+
+ pr_debug("%s: [%d] caller %ps %c%lu %lu/%lu%s\n", __func__, task->pid,
+ (void *)_RET_IP_, (inc) ? '+' : '-', pages << PAGE_SHIFT,
+ locked_vm << PAGE_SHIFT, task_rlimit(task, RLIMIT_MEMLOCK),
+ ret ? " - exceeded" : "");
+
+ return ret;
}
-EXPORT_SYMBOL_GPL(__get_user_pages_fast);
+EXPORT_SYMBOL_GPL(__account_locked_vm);
/**
- * get_user_pages_fast() - pin user pages in memory
- * @start: starting user address
- * @nr_pages: number of pages from start to pin
- * @write: whether pages will be written to
- * @pages: array that receives pointers to the pages pinned.
- * Should be at least nr_pages long.
+ * account_locked_vm - account locked pages to an mm's locked_vm
+ * @mm: mm to account against, may be NULL
+ * @pages: number of pages to account
+ * @inc: %true if @pages should be considered positive, %false if not
*
- * Returns number of pages pinned. This may be fewer than the number
- * requested. If nr_pages is 0 or negative, returns 0. If no pages
- * were pinned, returns -errno.
+ * Assumes a non-NULL @mm is valid (i.e. at least one reference on it).
*
- * get_user_pages_fast provides equivalent functionality to get_user_pages,
- * operating on current and current->mm, with force=0 and vma=NULL. However
- * unlike get_user_pages, it must be called without mmap_sem held.
- *
- * get_user_pages_fast may take mmap_sem and page table locks, so no
- * assumptions can be made about lack of locking. get_user_pages_fast is to be
- * implemented in a way that is advantageous (vs get_user_pages()) when the
- * user memory area is already faulted in and present in ptes. However if the
- * pages have to be faulted in, it may turn out to be slightly slower so
- * callers need to carefully consider what to use. On many architectures,
- * get_user_pages_fast simply falls back to get_user_pages.
+ * Return:
+ * * 0 on success, or if mm is NULL
+ * * -ENOMEM if RLIMIT_MEMLOCK would be exceeded.
*/
-int __weak get_user_pages_fast(unsigned long start,
- int nr_pages, int write, struct page **pages)
+int account_locked_vm(struct mm_struct *mm, unsigned long pages, bool inc)
{
- return get_user_pages_unlocked(start, nr_pages, pages,
- write ? FOLL_WRITE : 0);
+ int ret;
+
+ if (pages == 0 || !mm)
+ return 0;
+
+ mmap_write_lock(mm);
+ ret = __account_locked_vm(mm, pages, inc, current,
+ capable(CAP_IPC_LOCK));
+ mmap_write_unlock(mm);
+
+ return ret;
}
-EXPORT_SYMBOL_GPL(get_user_pages_fast);
+EXPORT_SYMBOL_GPL(account_locked_vm);
unsigned long vm_mmap_pgoff(struct file *file, unsigned long addr,
unsigned long len, unsigned long prot,
@@ -352,15 +539,16 @@
ret = security_mmap_file(file, prot, flag);
if (!ret) {
- if (down_write_killable(&mm->mmap_sem))
+ if (mmap_write_lock_killable(mm))
return -EINTR;
- ret = do_mmap_pgoff(file, addr, len, prot, flag, pgoff,
- &populate, &uf);
- up_write(&mm->mmap_sem);
+ ret = do_mmap(file, addr, len, prot, flag, pgoff, &populate,
+ &uf);
+ mmap_write_unlock(mm);
userfaultfd_unmap_complete(mm, &uf);
if (populate)
mm_populate(ret, populate);
}
+ trace_android_vh_check_mmap_file(file, prot, flag, ret);
return ret;
}
@@ -393,11 +581,14 @@
*
* Please note that any use of gfp flags outside of GFP_KERNEL is careful to not
* fall back to vmalloc.
+ *
+ * Return: pointer to the allocated memory of %NULL in case of failure
*/
void *kvmalloc_node(size_t size, gfp_t flags, int node)
{
gfp_t kmalloc_flags = flags;
void *ret;
+ bool use_vmalloc = false;
/*
* vmalloc uses GFP_KERNEL for some internal allocations (e.g page tables)
@@ -405,6 +596,10 @@
*/
if ((flags & GFP_KERNEL) != GFP_KERNEL)
return kmalloc_node(size, flags, node);
+
+ trace_android_vh_kvmalloc_node_use_vmalloc(size, &kmalloc_flags, &use_vmalloc);
+ if (use_vmalloc)
+ goto use_vmalloc_node;
/*
* We want to attempt a large physically contiguous block first because
@@ -429,7 +624,14 @@
if (ret || size <= PAGE_SIZE)
return ret;
- return __vmalloc_node_flags_caller(size, node, flags,
+ /* Don't even allow crazy sizes */
+ if (unlikely(size > INT_MAX)) {
+ WARN_ON_ONCE(!(flags & __GFP_NOWARN));
+ return NULL;
+ }
+
+use_vmalloc_node:
+ return __vmalloc_node(size, 1, flags, node,
__builtin_return_address(0));
}
EXPORT_SYMBOL(kvmalloc_node);
@@ -442,7 +644,7 @@
* It is slightly more efficient to use kfree() or vfree() if you are certain
* that you know which one to use.
*
- * Context: Any context except NMI.
+ * Context: Either preemptible task context or not-NMI interrupt.
*/
void kvfree(const void *addr)
{
@@ -470,6 +672,21 @@
}
}
EXPORT_SYMBOL(kvfree_sensitive);
+
+void *kvrealloc(const void *p, size_t oldsize, size_t newsize, gfp_t flags)
+{
+ void *newp;
+
+ if (oldsize >= newsize)
+ return (void *)p;
+ newp = kvmalloc(newsize, flags);
+ if (!newp)
+ return NULL;
+ memcpy(newp, p, oldsize);
+ kvfree(p);
+ return newp;
+}
+EXPORT_SYMBOL(kvrealloc);
static inline void *__page_rmapping(struct page *page)
{
@@ -503,7 +720,7 @@
return true;
if (PageHuge(page))
return false;
- for (i = 0; i < (1 << compound_order(page)); i++) {
+ for (i = 0; i < compound_nr(page); i++) {
if (atomic_read(&page[i]._mapcount) >= 0)
return true;
}
@@ -584,9 +801,8 @@
unsigned long sysctl_user_reserve_kbytes __read_mostly = 1UL << 17; /* 128MB */
unsigned long sysctl_admin_reserve_kbytes __read_mostly = 1UL << 13; /* 8MB */
-int overcommit_ratio_handler(struct ctl_table *table, int write,
- void __user *buffer, size_t *lenp,
- loff_t *ppos)
+int overcommit_ratio_handler(struct ctl_table *table, int write, void *buffer,
+ size_t *lenp, loff_t *ppos)
{
int ret;
@@ -596,9 +812,49 @@
return ret;
}
-int overcommit_kbytes_handler(struct ctl_table *table, int write,
- void __user *buffer, size_t *lenp,
- loff_t *ppos)
+static void sync_overcommit_as(struct work_struct *dummy)
+{
+ percpu_counter_sync(&vm_committed_as);
+}
+
+int overcommit_policy_handler(struct ctl_table *table, int write, void *buffer,
+ size_t *lenp, loff_t *ppos)
+{
+ struct ctl_table t;
+ int new_policy = -1;
+ int ret;
+
+ /*
+ * The deviation of sync_overcommit_as could be big with loose policy
+ * like OVERCOMMIT_ALWAYS/OVERCOMMIT_GUESS. When changing policy to
+ * strict OVERCOMMIT_NEVER, we need to reduce the deviation to comply
+ * with the strict "NEVER", and to avoid possible race condtion (even
+ * though user usually won't too frequently do the switching to policy
+ * OVERCOMMIT_NEVER), the switch is done in the following order:
+ * 1. changing the batch
+ * 2. sync percpu count on each CPU
+ * 3. switch the policy
+ */
+ if (write) {
+ t = *table;
+ t.data = &new_policy;
+ ret = proc_dointvec_minmax(&t, write, buffer, lenp, ppos);
+ if (ret || new_policy == -1)
+ return ret;
+
+ mm_compute_batch(new_policy);
+ if (new_policy == OVERCOMMIT_NEVER)
+ schedule_on_each_cpu(sync_overcommit_as);
+ sysctl_overcommit_memory = new_policy;
+ } else {
+ ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
+ }
+
+ return ret;
+}
+
+int overcommit_kbytes_handler(struct ctl_table *table, int write, void *buffer,
+ size_t *lenp, loff_t *ppos)
{
int ret;
@@ -618,7 +874,7 @@
if (sysctl_overcommit_kbytes)
allowed = sysctl_overcommit_kbytes >> (PAGE_SHIFT - 10);
else
- allowed = ((totalram_pages - hugetlb_total_pages())
+ allowed = ((totalram_pages() - hugetlb_total_pages())
* sysctl_overcommit_ratio / 100);
allowed += total_swap_pages;
@@ -638,10 +894,15 @@
* balancing memory across competing virtual machines that are hosted.
* Several metrics drive this policy engine including the guest reported
* memory commitment.
+ *
+ * The time cost of this is very low for small platforms, and for big
+ * platform like a 2S/36C/72T Skylake server, in worst case where
+ * vm_committed_as's spinlock is under severe contention, the time cost
+ * could be about 30~40 microseconds.
*/
unsigned long vm_memory_committed(void)
{
- return percpu_counter_read_positive(&vm_committed_as);
+ return percpu_counter_sum_positive(&vm_committed_as);
}
EXPORT_SYMBOL_GPL(vm_memory_committed);
@@ -663,11 +924,7 @@
*/
int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin)
{
- long free, allowed, reserve;
-
- VM_WARN_ONCE(percpu_counter_read(&vm_committed_as) <
- -(s64)vm_committed_as_batch * num_online_cpus(),
- "memory commitment underflow");
+ long allowed;
vm_acct_memory(pages);
@@ -678,51 +935,9 @@
return 0;
if (sysctl_overcommit_memory == OVERCOMMIT_GUESS) {
- free = global_zone_page_state(NR_FREE_PAGES);
- free += global_node_page_state(NR_FILE_PAGES);
-
- /*
- * shmem pages shouldn't be counted as free in this
- * case, they can't be purged, only swapped out, and
- * that won't affect the overall amount of available
- * memory in the system.
- */
- free -= global_node_page_state(NR_SHMEM);
-
- free += get_nr_swap_pages();
-
- /*
- * Any slabs which are created with the
- * SLAB_RECLAIM_ACCOUNT flag claim to have contents
- * which are reclaimable, under pressure. The dentry
- * cache and most inode caches should fall into this
- */
- free += global_node_page_state(NR_SLAB_RECLAIMABLE);
-
- /*
- * Part of the kernel memory, which can be released
- * under memory pressure.
- */
- free += global_node_page_state(NR_KERNEL_MISC_RECLAIMABLE);
-
- /*
- * Leave reserved pages. The pages are not for anonymous pages.
- */
- if (free <= totalreserve_pages)
+ if (pages > totalram_pages() + total_swap_pages)
goto error;
- else
- free -= totalreserve_pages;
-
- /*
- * Reserve some for root
- */
- if (!cap_sys_admin)
- free -= sysctl_admin_reserve_kbytes >> (PAGE_SHIFT - 10);
-
- if (free > pages)
- return 0;
-
- goto error;
+ return 0;
}
allowed = vm_commit_limit();
@@ -736,7 +951,8 @@
* Don't let a single process grow so big a user can't recover
*/
if (mm) {
- reserve = sysctl_user_reserve_kbytes >> (PAGE_SHIFT - 10);
+ long reserve = sysctl_user_reserve_kbytes >> (PAGE_SHIFT - 10);
+
allowed -= min_t(long, mm->total_vm / 32, reserve);
}
@@ -754,7 +970,8 @@
* @buffer: the buffer to copy to.
* @buflen: the length of the buffer. Larger cmdline values are truncated
* to this length.
- * Returns the size of the cmdline field copied. Note that the copy does
+ *
+ * Return: the size of the cmdline field copied. Note that the copy does
* not guarantee an ending NULL byte.
*/
int get_cmdline(struct task_struct *task, char *buffer, int buflen)
@@ -768,12 +985,12 @@
if (!mm->arg_end)
goto out_mm; /* Shh! No looking before we're done */
- down_read(&mm->mmap_sem);
+ spin_lock(&mm->arg_lock);
arg_start = mm->arg_start;
arg_end = mm->arg_end;
env_start = mm->env_start;
env_end = mm->env_end;
- up_read(&mm->mmap_sem);
+ spin_unlock(&mm->arg_lock);
len = arg_end - arg_start;
@@ -805,3 +1022,16 @@
out:
return res;
}
+
+int __weak memcmp_pages(struct page *page1, struct page *page2)
+{
+ char *addr1, *addr2;
+ int ret;
+
+ addr1 = kmap_atomic(page1);
+ addr2 = kmap_atomic(page2);
+ ret = memcmp(addr1, addr2, PAGE_SIZE);
+ kunmap_atomic(addr2);
+ kunmap_atomic(addr1);
+ return ret;
+}
--
Gitblit v1.6.2