aboutsummaryrefslogtreecommitdiffstats
path: root/fs/proc
diff options
context:
space:
mode:
Diffstat (limited to 'fs/proc')
-rw-r--r--fs/proc/array.c2
-rw-r--r--fs/proc/base.c34
-rw-r--r--fs/proc/inode.c3
-rw-r--r--fs/proc/kcore.c4
-rw-r--r--fs/proc/meminfo.c5
-rw-r--r--fs/proc/namespaces.c4
-rw-r--r--fs/proc/page.c4
-rw-r--r--fs/proc/self.c4
-rw-r--r--fs/proc/task_mmu.c137
-rw-r--r--fs/proc/thread_self.c4
10 files changed, 143 insertions, 58 deletions
diff --git a/fs/proc/array.c b/fs/proc/array.c
index d73291f5f0fc..b6c00ce0e29e 100644
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -395,7 +395,7 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns,
state = *get_task_state(task);
vsize = eip = esp = 0;
- permitted = ptrace_may_access(task, PTRACE_MODE_READ | PTRACE_MODE_NOAUDIT);
+ permitted = ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS | PTRACE_MODE_NOAUDIT);
mm = get_task_mm(task);
if (mm) {
vsize = task_vsize(mm);
diff --git a/fs/proc/base.c b/fs/proc/base.c
index 2cf5d7e37375..4f764c2ac1a5 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -403,7 +403,7 @@ static const struct file_operations proc_pid_cmdline_ops = {
static int proc_pid_auxv(struct seq_file *m, struct pid_namespace *ns,
struct pid *pid, struct task_struct *task)
{
- struct mm_struct *mm = mm_access(task, PTRACE_MODE_READ);
+ struct mm_struct *mm = mm_access(task, PTRACE_MODE_READ_FSCREDS);
if (mm && !IS_ERR(mm)) {
unsigned int nwords = 0;
do {
@@ -430,7 +430,8 @@ static int proc_pid_wchan(struct seq_file *m, struct pid_namespace *ns,
wchan = get_wchan(task);
- if (wchan && ptrace_may_access(task, PTRACE_MODE_READ) && !lookup_symbol_name(wchan, symname))
+ if (wchan && ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS)
+ && !lookup_symbol_name(wchan, symname))
seq_printf(m, "%s", symname);
else
seq_putc(m, '0');
@@ -444,7 +445,7 @@ static int lock_trace(struct task_struct *task)
int err = mutex_lock_killable(&task->signal->cred_guard_mutex);
if (err)
return err;
- if (!ptrace_may_access(task, PTRACE_MODE_ATTACH)) {
+ if (!ptrace_may_access(task, PTRACE_MODE_ATTACH_FSCREDS)) {
mutex_unlock(&task->signal->cred_guard_mutex);
return -EPERM;
}
@@ -697,7 +698,7 @@ static int proc_fd_access_allowed(struct inode *inode)
*/
task = get_proc_task(inode);
if (task) {
- allowed = ptrace_may_access(task, PTRACE_MODE_READ);
+ allowed = ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS);
put_task_struct(task);
}
return allowed;
@@ -732,7 +733,7 @@ static bool has_pid_permissions(struct pid_namespace *pid,
return true;
if (in_group_p(pid->pid_gid))
return true;
- return ptrace_may_access(task, PTRACE_MODE_READ);
+ return ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS);
}
@@ -809,7 +810,7 @@ struct mm_struct *proc_mem_open(struct inode *inode, unsigned int mode)
struct mm_struct *mm = ERR_PTR(-ESRCH);
if (task) {
- mm = mm_access(task, mode);
+ mm = mm_access(task, mode | PTRACE_MODE_FSCREDS);
put_task_struct(task);
if (!IS_ERR_OR_NULL(mm)) {
@@ -952,6 +953,7 @@ static ssize_t environ_read(struct file *file, char __user *buf,
unsigned long src = *ppos;
int ret = 0;
struct mm_struct *mm = file->private_data;
+ unsigned long env_start, env_end;
if (!mm)
return 0;
@@ -963,19 +965,25 @@ static ssize_t environ_read(struct file *file, char __user *buf,
ret = 0;
if (!atomic_inc_not_zero(&mm->mm_users))
goto free;
+
+ down_read(&mm->mmap_sem);
+ env_start = mm->env_start;
+ env_end = mm->env_end;
+ up_read(&mm->mmap_sem);
+
while (count > 0) {
size_t this_len, max_len;
int retval;
- if (src >= (mm->env_end - mm->env_start))
+ if (src >= (env_end - env_start))
break;
- this_len = mm->env_end - (mm->env_start + src);
+ this_len = env_end - (env_start + src);
max_len = min_t(size_t, PAGE_SIZE, count);
this_len = min(max_len, this_len);
- retval = access_remote_vm(mm, (mm->env_start + src),
+ retval = access_remote_vm(mm, (env_start + src),
page, this_len, 0);
if (retval <= 0) {
@@ -1860,7 +1868,7 @@ static int map_files_d_revalidate(struct dentry *dentry, unsigned int flags)
if (!task)
goto out_notask;
- mm = mm_access(task, PTRACE_MODE_READ);
+ mm = mm_access(task, PTRACE_MODE_READ_FSCREDS);
if (IS_ERR_OR_NULL(mm))
goto out;
@@ -2013,7 +2021,7 @@ static struct dentry *proc_map_files_lookup(struct inode *dir,
goto out;
result = -EACCES;
- if (!ptrace_may_access(task, PTRACE_MODE_READ))
+ if (!ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS))
goto out_put_task;
result = -ENOENT;
@@ -2066,7 +2074,7 @@ proc_map_files_readdir(struct file *file, struct dir_context *ctx)
goto out;
ret = -EACCES;
- if (!ptrace_may_access(task, PTRACE_MODE_READ))
+ if (!ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS))
goto out_put_task;
ret = 0;
@@ -2533,7 +2541,7 @@ static int do_io_accounting(struct task_struct *task, struct seq_file *m, int wh
if (result)
return result;
- if (!ptrace_may_access(task, PTRACE_MODE_READ)) {
+ if (!ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS)) {
result = -EACCES;
goto out_unlock;
}
diff --git a/fs/proc/inode.c b/fs/proc/inode.c
index d0e9b9b6223e..42305ddcbaa0 100644
--- a/fs/proc/inode.c
+++ b/fs/proc/inode.c
@@ -95,7 +95,8 @@ void __init proc_init_inodecache(void)
proc_inode_cachep = kmem_cache_create("proc_inode_cache",
sizeof(struct proc_inode),
0, (SLAB_RECLAIM_ACCOUNT|
- SLAB_MEM_SPREAD|SLAB_PANIC),
+ SLAB_MEM_SPREAD|SLAB_ACCOUNT|
+ SLAB_PANIC),
init_once);
}
diff --git a/fs/proc/kcore.c b/fs/proc/kcore.c
index 92e6726f6e37..a939f5ed7f89 100644
--- a/fs/proc/kcore.c
+++ b/fs/proc/kcore.c
@@ -552,9 +552,9 @@ static int open_kcore(struct inode *inode, struct file *filp)
if (kcore_need_update)
kcore_update_ram();
if (i_size_read(inode) != proc_root_kcore->size) {
- mutex_lock(&inode->i_mutex);
+ inode_lock(inode);
i_size_write(inode, proc_root_kcore->size);
- mutex_unlock(&inode->i_mutex);
+ inode_unlock(inode);
}
return 0;
}
diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c
index 9155a5a0d3b9..df4661abadc4 100644
--- a/fs/proc/meminfo.c
+++ b/fs/proc/meminfo.c
@@ -57,11 +57,8 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
/*
* Estimate the amount of memory available for userspace allocations,
* without causing swapping.
- *
- * Free memory cannot be taken below the low watermark, before the
- * system starts swapping.
*/
- available = i.freeram - wmark_low;
+ available = i.freeram - totalreserve_pages;
/*
* Not all the page cache can be freed, otherwise the system will
diff --git a/fs/proc/namespaces.c b/fs/proc/namespaces.c
index 1dece8781f91..276f12431dbf 100644
--- a/fs/proc/namespaces.c
+++ b/fs/proc/namespaces.c
@@ -46,7 +46,7 @@ static const char *proc_ns_get_link(struct dentry *dentry,
if (!task)
return error;
- if (ptrace_may_access(task, PTRACE_MODE_READ)) {
+ if (ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS)) {
error = ns_get_path(&ns_path, task, ns_ops);
if (!error)
nd_jump_link(&ns_path);
@@ -67,7 +67,7 @@ static int proc_ns_readlink(struct dentry *dentry, char __user *buffer, int bufl
if (!task)
return res;
- if (ptrace_may_access(task, PTRACE_MODE_READ)) {
+ if (ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS)) {
res = ns_get_name(name, sizeof(name), task, ns_ops);
if (res >= 0)
res = readlink_copy(buffer, buflen, name);
diff --git a/fs/proc/page.c b/fs/proc/page.c
index 93484034a03d..b2855eea5405 100644
--- a/fs/proc/page.c
+++ b/fs/proc/page.c
@@ -103,9 +103,9 @@ u64 stable_page_flags(struct page *page)
* pseudo flags for the well known (anonymous) memory mapped pages
*
* Note that page->_mapcount is overloaded in SLOB/SLUB/SLQB, so the
- * simple test in page_mapped() is not enough.
+ * simple test in page_mapcount() is not enough.
*/
- if (!PageSlab(page) && page_mapped(page))
+ if (!PageSlab(page) && page_mapcount(page))
u |= 1 << KPF_MMAP;
if (PageAnon(page))
u |= 1 << KPF_ANON;
diff --git a/fs/proc/self.c b/fs/proc/self.c
index 67e8db442cf0..b6a8d3529fea 100644
--- a/fs/proc/self.c
+++ b/fs/proc/self.c
@@ -50,7 +50,7 @@ int proc_setup_self(struct super_block *s)
struct pid_namespace *ns = s->s_fs_info;
struct dentry *self;
- mutex_lock(&root_inode->i_mutex);
+ inode_lock(root_inode);
self = d_alloc_name(s->s_root, "self");
if (self) {
struct inode *inode = new_inode_pseudo(s);
@@ -69,7 +69,7 @@ int proc_setup_self(struct super_block *s)
} else {
self = ERR_PTR(-ENOMEM);
}
- mutex_unlock(&root_inode->i_mutex);
+ inode_unlock(root_inode);
if (IS_ERR(self)) {
pr_err("proc_fill_super: can't allocate /proc/self\n");
return PTR_ERR(self);
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 187b3b5f242e..85d16c67c33e 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -14,6 +14,7 @@
#include <linux/swapops.h>
#include <linux/mmu_notifier.h>
#include <linux/page_idle.h>
+#include <linux/shmem_fs.h>
#include <asm/elf.h>
#include <asm/uaccess.h>
@@ -22,9 +23,13 @@
void task_mem(struct seq_file *m, struct mm_struct *mm)
{
- unsigned long data, text, lib, swap, ptes, pmds;
+ unsigned long text, lib, swap, ptes, pmds, anon, file, shmem;
unsigned long hiwater_vm, total_vm, hiwater_rss, total_rss;
+ anon = get_mm_counter(mm, MM_ANONPAGES);
+ file = get_mm_counter(mm, MM_FILEPAGES);
+ shmem = get_mm_counter(mm, MM_SHMEMPAGES);
+
/*
* Note: to minimize their overhead, mm maintains hiwater_vm and
* hiwater_rss only when about to *lower* total_vm or rss. Any
@@ -35,11 +40,10 @@ void task_mem(struct seq_file *m, struct mm_struct *mm)
hiwater_vm = total_vm = mm->total_vm;
if (hiwater_vm < mm->hiwater_vm)
hiwater_vm = mm->hiwater_vm;
- hiwater_rss = total_rss = get_mm_rss(mm);
+ hiwater_rss = total_rss = anon + file + shmem;
if (hiwater_rss < mm->hiwater_rss)
hiwater_rss = mm->hiwater_rss;
- data = mm->total_vm - mm->shared_vm - mm->stack_vm;
text = (PAGE_ALIGN(mm->end_code) - (mm->start_code & PAGE_MASK)) >> 10;
lib = (mm->exec_vm << (PAGE_SHIFT-10)) - text;
swap = get_mm_counter(mm, MM_SWAPENTS);
@@ -52,6 +56,9 @@ void task_mem(struct seq_file *m, struct mm_struct *mm)
"VmPin:\t%8lu kB\n"
"VmHWM:\t%8lu kB\n"
"VmRSS:\t%8lu kB\n"
+ "RssAnon:\t%8lu kB\n"
+ "RssFile:\t%8lu kB\n"
+ "RssShmem:\t%8lu kB\n"
"VmData:\t%8lu kB\n"
"VmStk:\t%8lu kB\n"
"VmExe:\t%8lu kB\n"
@@ -65,7 +72,10 @@ void task_mem(struct seq_file *m, struct mm_struct *mm)
mm->pinned_vm << (PAGE_SHIFT-10),
hiwater_rss << (PAGE_SHIFT-10),
total_rss << (PAGE_SHIFT-10),
- data << (PAGE_SHIFT-10),
+ anon << (PAGE_SHIFT-10),
+ file << (PAGE_SHIFT-10),
+ shmem << (PAGE_SHIFT-10),
+ mm->data_vm << (PAGE_SHIFT-10),
mm->stack_vm << (PAGE_SHIFT-10), text, lib,
ptes >> 10,
pmds >> 10,
@@ -82,10 +92,11 @@ unsigned long task_statm(struct mm_struct *mm,
unsigned long *shared, unsigned long *text,
unsigned long *data, unsigned long *resident)
{
- *shared = get_mm_counter(mm, MM_FILEPAGES);
+ *shared = get_mm_counter(mm, MM_FILEPAGES) +
+ get_mm_counter(mm, MM_SHMEMPAGES);
*text = (PAGE_ALIGN(mm->end_code) - (mm->start_code & PAGE_MASK))
>> PAGE_SHIFT;
- *data = mm->total_vm - mm->shared_vm;
+ *data = mm->data_vm + mm->stack_vm;
*resident = *shared + get_mm_counter(mm, MM_ANONPAGES);
return mm->total_vm;
}
@@ -451,12 +462,14 @@ struct mem_size_stats {
unsigned long private_hugetlb;
u64 pss;
u64 swap_pss;
+ bool check_shmem_swap;
};
static void smaps_account(struct mem_size_stats *mss, struct page *page,
- unsigned long size, bool young, bool dirty)
+ bool compound, bool young, bool dirty)
{
- int mapcount;
+ int i, nr = compound ? 1 << compound_order(page) : 1;
+ unsigned long size = nr * PAGE_SIZE;
if (PageAnon(page))
mss->anonymous += size;
@@ -465,26 +478,53 @@ static void smaps_account(struct mem_size_stats *mss, struct page *page,
/* Accumulate the size in pages that have been accessed. */
if (young || page_is_young(page) || PageReferenced(page))
mss->referenced += size;
- mapcount = page_mapcount(page);
- if (mapcount >= 2) {
- u64 pss_delta;
- if (dirty || PageDirty(page))
- mss->shared_dirty += size;
- else
- mss->shared_clean += size;
- pss_delta = (u64)size << PSS_SHIFT;
- do_div(pss_delta, mapcount);
- mss->pss += pss_delta;
- } else {
+ /*
+ * page_count(page) == 1 guarantees the page is mapped exactly once.
+ * If any subpage of the compound page mapped with PTE it would elevate
+ * page_count().
+ */
+ if (page_count(page) == 1) {
if (dirty || PageDirty(page))
mss->private_dirty += size;
else
mss->private_clean += size;
mss->pss += (u64)size << PSS_SHIFT;
+ return;
+ }
+
+ for (i = 0; i < nr; i++, page++) {
+ int mapcount = page_mapcount(page);
+
+ if (mapcount >= 2) {
+ if (dirty || PageDirty(page))
+ mss->shared_dirty += PAGE_SIZE;
+ else
+ mss->shared_clean += PAGE_SIZE;
+ mss->pss += (PAGE_SIZE << PSS_SHIFT) / mapcount;
+ } else {
+ if (dirty || PageDirty(page))
+ mss->private_dirty += PAGE_SIZE;
+ else
+ mss->private_clean += PAGE_SIZE;
+ mss->pss += PAGE_SIZE << PSS_SHIFT;
+ }
}
}
+#ifdef CONFIG_SHMEM
+static int smaps_pte_hole(unsigned long addr, unsigned long end,
+ struct mm_walk *walk)
+{
+ struct mem_size_stats *mss = walk->private;
+
+ mss->swap += shmem_partial_swap_usage(
+ walk->vma->vm_file->f_mapping, addr, end);
+
+ return 0;
+}
+#endif
+
static void smaps_pte_entry(pte_t *pte, unsigned long addr,
struct mm_walk *walk)
{
@@ -512,11 +552,25 @@ static void smaps_pte_entry(pte_t *pte, unsigned long addr,
}
} else if (is_migration_entry(swpent))
page = migration_entry_to_page(swpent);
+ } else if (unlikely(IS_ENABLED(CONFIG_SHMEM) && mss->check_shmem_swap
+ && pte_none(*pte))) {
+ page = find_get_entry(vma->vm_file->f_mapping,
+ linear_page_index(vma, addr));
+ if (!page)
+ return;
+
+ if (radix_tree_exceptional_entry(page))
+ mss->swap += PAGE_SIZE;
+ else
+ page_cache_release(page);
+
+ return;
}
if (!page)
return;
- smaps_account(mss, page, PAGE_SIZE, pte_young(*pte), pte_dirty(*pte));
+
+ smaps_account(mss, page, false, pte_young(*pte), pte_dirty(*pte));
}
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
@@ -532,8 +586,7 @@ static void smaps_pmd_entry(pmd_t *pmd, unsigned long addr,
if (IS_ERR_OR_NULL(page))
return;
mss->anonymous_thp += HPAGE_PMD_SIZE;
- smaps_account(mss, page, HPAGE_PMD_SIZE,
- pmd_young(*pmd), pmd_dirty(*pmd));
+ smaps_account(mss, page, true, pmd_young(*pmd), pmd_dirty(*pmd));
}
#else
static void smaps_pmd_entry(pmd_t *pmd, unsigned long addr,
@@ -549,7 +602,8 @@ static int smaps_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
pte_t *pte;
spinlock_t *ptl;
- if (pmd_trans_huge_lock(pmd, vma, &ptl) == 1) {
+ ptl = pmd_trans_huge_lock(pmd, vma);
+ if (ptl) {
smaps_pmd_entry(pmd, addr, walk);
spin_unlock(ptl);
return 0;
@@ -671,6 +725,31 @@ static int show_smap(struct seq_file *m, void *v, int is_pid)
};
memset(&mss, 0, sizeof mss);
+
+#ifdef CONFIG_SHMEM
+ if (vma->vm_file && shmem_mapping(vma->vm_file->f_mapping)) {
+ /*
+ * For shared or readonly shmem mappings we know that all
+ * swapped out pages belong to the shmem object, and we can
+ * obtain the swap value much more efficiently. For private
+ * writable mappings, we might have COW pages that are
+ * not affected by the parent swapped out pages of the shmem
+ * object, so we have to distinguish them during the page walk.
+ * Unless we know that the shmem object (or the part mapped by
+ * our VMA) has no swapped out pages at all.
+ */
+ unsigned long shmem_swapped = shmem_swap_usage(vma);
+
+ if (!shmem_swapped || (vma->vm_flags & VM_SHARED) ||
+ !(vma->vm_flags & VM_WRITE)) {
+ mss.swap = shmem_swapped;
+ } else {
+ mss.check_shmem_swap = true;
+ smaps_walk.pte_hole = smaps_pte_hole;
+ }
+ }
+#endif
+
/* mmap_sem is held in m_start */
walk_page_vma(vma, &smaps_walk);
@@ -817,9 +896,6 @@ static inline void clear_soft_dirty_pmd(struct vm_area_struct *vma,
pmd = pmd_wrprotect(pmd);
pmd = pmd_clear_soft_dirty(pmd);
- if (vma->vm_flags & VM_SOFTDIRTY)
- vma->vm_flags &= ~VM_SOFTDIRTY;
-
set_pmd_at(vma->vm_mm, addr, pmdp, pmd);
}
#else
@@ -838,7 +914,8 @@ static int clear_refs_pte_range(pmd_t *pmd, unsigned long addr,
spinlock_t *ptl;
struct page *page;
- if (pmd_trans_huge_lock(pmd, vma, &ptl) == 1) {
+ ptl = pmd_trans_huge_lock(pmd, vma);
+ if (ptl) {
if (cp->type == CLEAR_REFS_SOFT_DIRTY) {
clear_soft_dirty_pmd(vma, addr, pmd);
goto out;
@@ -1112,7 +1189,8 @@ static int pagemap_pmd_range(pmd_t *pmdp, unsigned long addr, unsigned long end,
int err = 0;
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
- if (pmd_trans_huge_lock(pmdp, vma, &ptl) == 1) {
+ ptl = pmd_trans_huge_lock(pmdp, vma);
+ if (ptl) {
u64 flags = 0, frame = 0;
pmd_t pmd = *pmdp;
@@ -1444,7 +1522,8 @@ static int gather_pte_stats(pmd_t *pmd, unsigned long addr,
pte_t *orig_pte;
pte_t *pte;
- if (pmd_trans_huge_lock(pmd, vma, &ptl) == 1) {
+ ptl = pmd_trans_huge_lock(pmd, vma);
+ if (ptl) {
pte_t huge_pte = *(pte_t *)pmd;
struct page *page;
diff --git a/fs/proc/thread_self.c b/fs/proc/thread_self.c
index 9eacd59e0360..e58a31e8fb2a 100644
--- a/fs/proc/thread_self.c
+++ b/fs/proc/thread_self.c
@@ -52,7 +52,7 @@ int proc_setup_thread_self(struct super_block *s)
struct pid_namespace *ns = s->s_fs_info;
struct dentry *thread_self;
- mutex_lock(&root_inode->i_mutex);
+ inode_lock(root_inode);
thread_self = d_alloc_name(s->s_root, "thread-self");
if (thread_self) {
struct inode *inode = new_inode_pseudo(s);
@@ -71,7 +71,7 @@ int proc_setup_thread_self(struct super_block *s)
} else {
thread_self = ERR_PTR(-ENOMEM);
}
- mutex_unlock(&root_inode->i_mutex);
+ inode_unlock(root_inode);
if (IS_ERR(thread_self)) {
pr_err("proc_fill_super: can't allocate /proc/thread_self\n");
return PTR_ERR(thread_self);
Copyright © 1996 – 2023 Jason A. Donenfeld. All Rights Reverse Engineered.