summaryrefslogtreecommitdiffstats
path: root/fs/proc
diff options
context:
space:
mode:
Diffstat (limited to 'fs/proc')
-rw-r--r--fs/proc/array.c47
-rw-r--r--fs/proc/base.c3
-rw-r--r--fs/proc/generic.c163
-rw-r--r--fs/proc/internal.h11
-rw-r--r--fs/proc/proc_net.c1
-rw-r--r--fs/proc/root.c1
-rw-r--r--fs/proc/task_mmu.c107
7 files changed, 208 insertions, 125 deletions
diff --git a/fs/proc/array.c b/fs/proc/array.c
index cd3653e..bd117d0 100644
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -157,20 +157,29 @@ static inline void task_state(struct seq_file *m, struct pid_namespace *ns,
struct user_namespace *user_ns = seq_user_ns(m);
struct group_info *group_info;
int g;
- struct fdtable *fdt = NULL;
+ struct task_struct *tracer;
const struct cred *cred;
- pid_t ppid, tpid;
+ pid_t ppid, tpid = 0, tgid, ngid;
+ unsigned int max_fds = 0;
rcu_read_lock();
ppid = pid_alive(p) ?
task_tgid_nr_ns(rcu_dereference(p->real_parent), ns) : 0;
- tpid = 0;
- if (pid_alive(p)) {
- struct task_struct *tracer = ptrace_parent(p);
- if (tracer)
- tpid = task_pid_nr_ns(tracer, ns);
- }
+
+ tracer = ptrace_parent(p);
+ if (tracer)
+ tpid = task_pid_nr_ns(tracer, ns);
+
+ tgid = task_tgid_nr_ns(p, ns);
+ ngid = task_numa_group_id(p);
cred = get_task_cred(p);
+
+ task_lock(p);
+ if (p->files)
+ max_fds = files_fdtable(p->files)->max_fds;
+ task_unlock(p);
+ rcu_read_unlock();
+
seq_printf(m,
"State:\t%s\n"
"Tgid:\t%d\n"
@@ -179,12 +188,10 @@ static inline void task_state(struct seq_file *m, struct pid_namespace *ns,
"PPid:\t%d\n"
"TracerPid:\t%d\n"
"Uid:\t%d\t%d\t%d\t%d\n"
- "Gid:\t%d\t%d\t%d\t%d\n",
+ "Gid:\t%d\t%d\t%d\t%d\n"
+ "FDSize:\t%d\nGroups:\t",
get_task_state(p),
- task_tgid_nr_ns(p, ns),
- task_numa_group_id(p),
- pid_nr_ns(pid, ns),
- ppid, tpid,
+ tgid, ngid, pid_nr_ns(pid, ns), ppid, tpid,
from_kuid_munged(user_ns, cred->uid),
from_kuid_munged(user_ns, cred->euid),
from_kuid_munged(user_ns, cred->suid),
@@ -192,20 +199,10 @@ static inline void task_state(struct seq_file *m, struct pid_namespace *ns,
from_kgid_munged(user_ns, cred->gid),
from_kgid_munged(user_ns, cred->egid),
from_kgid_munged(user_ns, cred->sgid),
- from_kgid_munged(user_ns, cred->fsgid));
-
- task_lock(p);
- if (p->files)
- fdt = files_fdtable(p->files);
- seq_printf(m,
- "FDSize:\t%d\n"
- "Groups:\t",
- fdt ? fdt->max_fds : 0);
- rcu_read_unlock();
+ from_kgid_munged(user_ns, cred->fsgid),
+ max_fds);
group_info = cred->group_info;
- task_unlock(p);
-
for (g = 0; g < group_info->ngroups; g++)
seq_printf(m, "%d ",
from_kgid_munged(user_ns, GROUP_AT(group_info, g)));
diff --git a/fs/proc/base.c b/fs/proc/base.c
index 64891f3..590aeda 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -2618,6 +2618,9 @@ static void proc_flush_task_mnt(struct vfsmount *mnt, pid_t pid, pid_t tgid)
dput(dentry);
}
+ if (pid == tgid)
+ return;
+
name.name = buf;
name.len = snprintf(buf, sizeof(buf), "%d", tgid);
leader = d_hash_and_lookup(mnt->mnt_root, &name);
diff --git a/fs/proc/generic.c b/fs/proc/generic.c
index 317b726..7fea132 100644
--- a/fs/proc/generic.c
+++ b/fs/proc/generic.c
@@ -31,9 +31,73 @@ static DEFINE_SPINLOCK(proc_subdir_lock);
static int proc_match(unsigned int len, const char *name, struct proc_dir_entry *de)
{
- if (de->namelen != len)
- return 0;
- return !memcmp(name, de->name, len);
+ if (len < de->namelen)
+ return -1;
+ if (len > de->namelen)
+ return 1;
+
+ return memcmp(name, de->name, len);
+}
+
+static struct proc_dir_entry *pde_subdir_first(struct proc_dir_entry *dir)
+{
+ return rb_entry_safe(rb_first(&dir->subdir), struct proc_dir_entry,
+ subdir_node);
+}
+
+static struct proc_dir_entry *pde_subdir_next(struct proc_dir_entry *dir)
+{
+ return rb_entry_safe(rb_next(&dir->subdir_node), struct proc_dir_entry,
+ subdir_node);
+}
+
+static struct proc_dir_entry *pde_subdir_find(struct proc_dir_entry *dir,
+ const char *name,
+ unsigned int len)
+{
+ struct rb_node *node = dir->subdir.rb_node;
+
+ while (node) {
+ struct proc_dir_entry *de = container_of(node,
+ struct proc_dir_entry,
+ subdir_node);
+ int result = proc_match(len, name, de);
+
+ if (result < 0)
+ node = node->rb_left;
+ else if (result > 0)
+ node = node->rb_right;
+ else
+ return de;
+ }
+ return NULL;
+}
+
+static bool pde_subdir_insert(struct proc_dir_entry *dir,
+ struct proc_dir_entry *de)
+{
+ struct rb_root *root = &dir->subdir;
+ struct rb_node **new = &root->rb_node, *parent = NULL;
+
+ /* Figure out where to put new node */
+ while (*new) {
+ struct proc_dir_entry *this =
+ container_of(*new, struct proc_dir_entry, subdir_node);
+ int result = proc_match(de->namelen, de->name, this);
+
+ parent = *new;
+ if (result < 0)
+ new = &(*new)->rb_left;
+ else if (result > 0)
+ new = &(*new)->rb_right;
+ else
+ return false;
+ }
+
+ /* Add new node and rebalance tree. */
+ rb_link_node(&de->subdir_node, parent, new);
+ rb_insert_color(&de->subdir_node, root);
+ return true;
}
static int proc_notify_change(struct dentry *dentry, struct iattr *iattr)
@@ -92,10 +156,7 @@ static int __xlate_proc_name(const char *name, struct proc_dir_entry **ret,
break;
len = next - cp;
- for (de = de->subdir; de ; de = de->next) {
- if (proc_match(len, cp, de))
- break;
- }
+ de = pde_subdir_find(de, cp, len);
if (!de) {
WARN(1, "name '%s'\n", name);
return -ENOENT;
@@ -183,19 +244,16 @@ struct dentry *proc_lookup_de(struct proc_dir_entry *de, struct inode *dir,
struct inode *inode;
spin_lock(&proc_subdir_lock);
- for (de = de->subdir; de ; de = de->next) {
- if (de->namelen != dentry->d_name.len)
- continue;
- if (!memcmp(dentry->d_name.name, de->name, de->namelen)) {
- pde_get(de);
- spin_unlock(&proc_subdir_lock);
- inode = proc_get_inode(dir->i_sb, de);
- if (!inode)
- return ERR_PTR(-ENOMEM);
- d_set_d_op(dentry, &simple_dentry_operations);
- d_add(dentry, inode);
- return NULL;
- }
+ de = pde_subdir_find(de, dentry->d_name.name, dentry->d_name.len);
+ if (de) {
+ pde_get(de);
+ spin_unlock(&proc_subdir_lock);
+ inode = proc_get_inode(dir->i_sb, de);
+ if (!inode)
+ return ERR_PTR(-ENOMEM);
+ d_set_d_op(dentry, &simple_dentry_operations);
+ d_add(dentry, inode);
+ return NULL;
}
spin_unlock(&proc_subdir_lock);
return ERR_PTR(-ENOENT);
@@ -225,7 +283,7 @@ int proc_readdir_de(struct proc_dir_entry *de, struct file *file,
return 0;
spin_lock(&proc_subdir_lock);
- de = de->subdir;
+ de = pde_subdir_first(de);
i = ctx->pos - 2;
for (;;) {
if (!de) {
@@ -234,7 +292,7 @@ int proc_readdir_de(struct proc_dir_entry *de, struct file *file,
}
if (!i)
break;
- de = de->next;
+ de = pde_subdir_next(de);
i--;
}
@@ -249,7 +307,7 @@ int proc_readdir_de(struct proc_dir_entry *de, struct file *file,
}
spin_lock(&proc_subdir_lock);
ctx->pos++;
- next = de->next;
+ next = pde_subdir_next(de);
pde_put(de);
de = next;
} while (de);
@@ -286,9 +344,8 @@ static const struct inode_operations proc_dir_inode_operations = {
static int proc_register(struct proc_dir_entry * dir, struct proc_dir_entry * dp)
{
- struct proc_dir_entry *tmp;
int ret;
-
+
ret = proc_alloc_inum(&dp->low_ino);
if (ret)
return ret;
@@ -304,21 +361,21 @@ static int proc_register(struct proc_dir_entry * dir, struct proc_dir_entry * dp
dp->proc_iops = &proc_file_inode_operations;
} else {
WARN_ON(1);
+ proc_free_inum(dp->low_ino);
return -EINVAL;
}
spin_lock(&proc_subdir_lock);
-
- for (tmp = dir->subdir; tmp; tmp = tmp->next)
- if (strcmp(tmp->name, dp->name) == 0) {
- WARN(1, "proc_dir_entry '%s/%s' already registered\n",
- dir->name, dp->name);
- break;
- }
-
- dp->next = dir->subdir;
dp->parent = dir;
- dir->subdir = dp;
+ if (pde_subdir_insert(dir, dp) == false) {
+ WARN(1, "proc_dir_entry '%s/%s' already registered\n",
+ dir->name, dp->name);
+ spin_unlock(&proc_subdir_lock);
+ if (S_ISDIR(dp->mode))
+ dir->nlink--;
+ proc_free_inum(dp->low_ino);
+ return -EEXIST;
+ }
spin_unlock(&proc_subdir_lock);
return 0;
@@ -354,6 +411,7 @@ static struct proc_dir_entry *__proc_create(struct proc_dir_entry **parent,
ent->namelen = qstr.len;
ent->mode = mode;
ent->nlink = nlink;
+ ent->subdir = RB_ROOT;
atomic_set(&ent->count, 1);
spin_lock_init(&ent->pde_unload_lock);
INIT_LIST_HEAD(&ent->pde_openers);
@@ -485,7 +543,6 @@ void pde_put(struct proc_dir_entry *pde)
*/
void remove_proc_entry(const char *name, struct proc_dir_entry *parent)
{
- struct proc_dir_entry **p;
struct proc_dir_entry *de = NULL;
const char *fn = name;
unsigned int len;
@@ -497,14 +554,9 @@ void remove_proc_entry(const char *name, struct proc_dir_entry *parent)
}
len = strlen(fn);
- for (p = &parent->subdir; *p; p=&(*p)->next ) {
- if (proc_match(len, fn, *p)) {
- de = *p;
- *p = de->next;
- de->next = NULL;
- break;
- }
- }
+ de = pde_subdir_find(parent, fn, len);
+ if (de)
+ rb_erase(&de->subdir_node, &parent->subdir);
spin_unlock(&proc_subdir_lock);
if (!de) {
WARN(1, "name '%s'\n", name);
@@ -516,16 +568,15 @@ void remove_proc_entry(const char *name, struct proc_dir_entry *parent)
if (S_ISDIR(de->mode))
parent->nlink--;
de->nlink = 0;
- WARN(de->subdir, "%s: removing non-empty directory "
- "'%s/%s', leaking at least '%s'\n", __func__,
- de->parent->name, de->name, de->subdir->name);
+ WARN(pde_subdir_first(de),
+ "%s: removing non-empty directory '%s/%s', leaking at least '%s'\n",
+ __func__, de->parent->name, de->name, pde_subdir_first(de)->name);
pde_put(de);
}
EXPORT_SYMBOL(remove_proc_entry);
int remove_proc_subtree(const char *name, struct proc_dir_entry *parent)
{
- struct proc_dir_entry **p;
struct proc_dir_entry *root = NULL, *de, *next;
const char *fn = name;
unsigned int len;
@@ -537,24 +588,18 @@ int remove_proc_subtree(const char *name, struct proc_dir_entry *parent)
}
len = strlen(fn);
- for (p = &parent->subdir; *p; p=&(*p)->next ) {
- if (proc_match(len, fn, *p)) {
- root = *p;
- *p = root->next;
- root->next = NULL;
- break;
- }
- }
+ root = pde_subdir_find(parent, fn, len);
if (!root) {
spin_unlock(&proc_subdir_lock);
return -ENOENT;
}
+ rb_erase(&root->subdir_node, &parent->subdir);
+
de = root;
while (1) {
- next = de->subdir;
+ next = pde_subdir_first(de);
if (next) {
- de->subdir = next->next;
- next->next = NULL;
+ rb_erase(&next->subdir_node, &de->subdir);
de = next;
continue;
}
diff --git a/fs/proc/internal.h b/fs/proc/internal.h
index d689fd6..6fcdba5 100644
--- a/fs/proc/internal.h
+++ b/fs/proc/internal.h
@@ -24,10 +24,9 @@ struct mempolicy;
* tree) of these proc_dir_entries, so that we can dynamically
* add new files to /proc.
*
- * The "next" pointer creates a linked list of one /proc directory,
- * while parent/subdir create the directory structure (every
- * /proc file has a parent, but "subdir" is NULL for all
- * non-directory entries).
+ * parent/subdir are used for the directory structure (every /proc file has a
+ * parent, but "subdir" is empty for all non-directory entries).
+ * subdir_node is used to build the rb tree "subdir" of the parent.
*/
struct proc_dir_entry {
unsigned int low_ino;
@@ -38,7 +37,9 @@ struct proc_dir_entry {
loff_t size;
const struct inode_operations *proc_iops;
const struct file_operations *proc_fops;
- struct proc_dir_entry *next, *parent, *subdir;
+ struct proc_dir_entry *parent;
+ struct rb_root subdir;
+ struct rb_node subdir_node;
void *data;
atomic_t count; /* use count */
atomic_t in_use; /* number of callers into module in progress; */
diff --git a/fs/proc/proc_net.c b/fs/proc/proc_net.c
index a63af3e..1bde894 100644
--- a/fs/proc/proc_net.c
+++ b/fs/proc/proc_net.c
@@ -192,6 +192,7 @@ static __net_init int proc_net_ns_init(struct net *net)
if (!netd)
goto out;
+ netd->subdir = RB_ROOT;
netd->data = net;
netd->nlink = 2;
netd->namelen = 3;
diff --git a/fs/proc/root.c b/fs/proc/root.c
index 094e44d..e74ac9f 100644
--- a/fs/proc/root.c
+++ b/fs/proc/root.c
@@ -251,6 +251,7 @@ struct proc_dir_entry proc_root = {
.proc_iops = &proc_root_inode_operations,
.proc_fops = &proc_root_operations,
.parent = &proc_root,
+ .subdir = RB_ROOT,
.name = "/proc",
};
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 4e0388c..246eae8 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -447,59 +447,92 @@ struct mem_size_stats {
u64 pss;
};
+static void smaps_account(struct mem_size_stats *mss, struct page *page,
+ unsigned long size, bool young, bool dirty)
+{
+ int mapcount;
+
+ if (PageAnon(page))
+ mss->anonymous += size;
-static void smaps_pte_entry(pte_t ptent, unsigned long addr,
- unsigned long ptent_size, struct mm_walk *walk)
+ mss->resident += size;
+ /* Accumulate the size in pages that have been accessed. */
+ if (young || 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 {
+ if (dirty || PageDirty(page))
+ mss->private_dirty += size;
+ else
+ mss->private_clean += size;
+ mss->pss += (u64)size << PSS_SHIFT;
+ }
+}
+
+static void smaps_pte_entry(pte_t *pte, unsigned long addr,
+ struct mm_walk *walk)
{
struct mem_size_stats *mss = walk->private;
struct vm_area_struct *vma = mss->vma;
pgoff_t pgoff = linear_page_index(vma, addr);
struct page *page = NULL;
- int mapcount;
- if (pte_present(ptent)) {
- page = vm_normal_page(vma, addr, ptent);
- } else if (is_swap_pte(ptent)) {
- swp_entry_t swpent = pte_to_swp_entry(ptent);
+ if (pte_present(*pte)) {
+ page = vm_normal_page(vma, addr, *pte);
+ } else if (is_swap_pte(*pte)) {
+ swp_entry_t swpent = pte_to_swp_entry(*pte);
if (!non_swap_entry(swpent))
- mss->swap += ptent_size;
+ mss->swap += PAGE_SIZE;
else if (is_migration_entry(swpent))
page = migration_entry_to_page(swpent);
- } else if (pte_file(ptent)) {
- if (pte_to_pgoff(ptent) != pgoff)
- mss->nonlinear += ptent_size;
+ } else if (pte_file(*pte)) {
+ if (pte_to_pgoff(*pte) != pgoff)
+ mss->nonlinear += PAGE_SIZE;
}
if (!page)
return;
- if (PageAnon(page))
- mss->anonymous += ptent_size;
-
if (page->index != pgoff)
- mss->nonlinear += ptent_size;
+ mss->nonlinear += PAGE_SIZE;
- mss->resident += ptent_size;
- /* Accumulate the size in pages that have been accessed. */
- if (pte_young(ptent) || PageReferenced(page))
- mss->referenced += ptent_size;
- mapcount = page_mapcount(page);
- if (mapcount >= 2) {
- if (pte_dirty(ptent) || PageDirty(page))
- mss->shared_dirty += ptent_size;
- else
- mss->shared_clean += ptent_size;
- mss->pss += (ptent_size << PSS_SHIFT) / mapcount;
- } else {
- if (pte_dirty(ptent) || PageDirty(page))
- mss->private_dirty += ptent_size;
- else
- mss->private_clean += ptent_size;
- mss->pss += (ptent_size << PSS_SHIFT);
- }
+ smaps_account(mss, page, PAGE_SIZE, pte_young(*pte), pte_dirty(*pte));
}
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+static void smaps_pmd_entry(pmd_t *pmd, unsigned long addr,
+ struct mm_walk *walk)
+{
+ struct mem_size_stats *mss = walk->private;
+ struct vm_area_struct *vma = mss->vma;
+ struct page *page;
+
+ /* FOLL_DUMP will return -EFAULT on huge zero page */
+ page = follow_trans_huge_pmd(vma, addr, pmd, FOLL_DUMP);
+ 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));
+}
+#else
+static void smaps_pmd_entry(pmd_t *pmd, unsigned long addr,
+ struct mm_walk *walk)
+{
+}
+#endif
+
static int smaps_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
struct mm_walk *walk)
{
@@ -509,9 +542,8 @@ static int smaps_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
spinlock_t *ptl;
if (pmd_trans_huge_lock(pmd, vma, &ptl) == 1) {
- smaps_pte_entry(*(pte_t *)pmd, addr, HPAGE_PMD_SIZE, walk);
+ smaps_pmd_entry(pmd, addr, walk);
spin_unlock(ptl);
- mss->anonymous_thp += HPAGE_PMD_SIZE;
return 0;
}
@@ -524,7 +556,7 @@ static int smaps_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
*/
pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
for (; addr != end; pte++, addr += PAGE_SIZE)
- smaps_pte_entry(*pte, addr, PAGE_SIZE, walk);
+ smaps_pte_entry(pte, addr, walk);
pte_unmap_unlock(pte - 1, ptl);
cond_resched();
return 0;
@@ -552,6 +584,9 @@ static void show_smap_vma_flags(struct seq_file *m, struct vm_area_struct *vma)
[ilog2(VM_GROWSDOWN)] = "gd",
[ilog2(VM_PFNMAP)] = "pf",
[ilog2(VM_DENYWRITE)] = "dw",
+#ifdef CONFIG_X86_INTEL_MPX
+ [ilog2(VM_MPX)] = "mp",
+#endif
[ilog2(VM_LOCKED)] = "lo",
[ilog2(VM_IO)] = "io",
[ilog2(VM_SEQ_READ)] = "sr",
OpenPOWER on IntegriCloud