aboutsummaryrefslogtreecommitdiff
path: root/fs/proc
diff options
context:
space:
mode:
Diffstat (limited to 'fs/proc')
-rw-r--r--fs/proc/array.c13
-rw-r--r--fs/proc/base.c40
-rw-r--r--fs/proc/stat.c4
-rw-r--r--fs/proc/task_mmu.c28
-rw-r--r--fs/proc/uptime.c14
-rw-r--r--fs/proc/vmcore.c109
6 files changed, 130 insertions, 78 deletions
diff --git a/fs/proc/array.c b/fs/proc/array.c
index 49be8c8ef555..ff869a66b34e 100644
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -408,9 +408,9 @@ static void task_cpus_allowed(struct seq_file *m, struct task_struct *task)
cpumask_pr_args(&task->cpus_mask));
}
-static inline void task_core_dumping(struct seq_file *m, struct mm_struct *mm)
+static inline void task_core_dumping(struct seq_file *m, struct task_struct *task)
{
- seq_put_decimal_ull(m, "CoreDumping:\t", !!mm->core_state);
+ seq_put_decimal_ull(m, "CoreDumping:\t", !!task->signal->core_state);
seq_putc(m, '\n');
}
@@ -436,7 +436,7 @@ int proc_pid_status(struct seq_file *m, struct pid_namespace *ns,
if (mm) {
task_mem(m, mm);
- task_core_dumping(m, mm);
+ task_core_dumping(m, task);
task_thp_status(m, mm);
mmput(mm);
}
@@ -541,7 +541,7 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns,
}
if (permitted && (!whole || num_threads < 2))
- wchan = get_wchan(task);
+ wchan = !task_is_running(task);
if (!whole) {
min_flt = task->min_flt;
maj_flt = task->maj_flt;
@@ -606,10 +606,7 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns,
*
* This works with older implementations of procps as well.
*/
- if (wchan)
- seq_puts(m, " 1");
- else
- seq_puts(m, " 0");
+ seq_put_decimal_ull(m, " ", wchan);
seq_put_decimal_ull(m, " ", 0);
seq_put_decimal_ull(m, " ", 0);
diff --git a/fs/proc/base.c b/fs/proc/base.c
index 533d5836eb9a..13eda8de2998 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -67,6 +67,7 @@
#include <linux/mm.h>
#include <linux/swap.h>
#include <linux/rcupdate.h>
+#include <linux/kallsyms.h>
#include <linux/stacktrace.h>
#include <linux/resource.h>
#include <linux/module.h>
@@ -386,17 +387,19 @@ static int proc_pid_wchan(struct seq_file *m, struct pid_namespace *ns,
struct pid *pid, struct task_struct *task)
{
unsigned long wchan;
+ char symname[KSYM_NAME_LEN];
- if (ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS))
- wchan = get_wchan(task);
- else
- wchan = 0;
+ if (!ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS))
+ goto print0;
- if (wchan)
- seq_printf(m, "%ps", (void *) wchan);
- else
- seq_putc(m, '0');
+ wchan = get_wchan(task);
+ if (wchan && !lookup_symbol_name(wchan, symname)) {
+ seq_puts(m, symname);
+ return 0;
+ }
+print0:
+ seq_putc(m, '0');
return 0;
}
#endif /* CONFIG_KALLSYMS */
@@ -1979,19 +1982,21 @@ static int pid_revalidate(struct dentry *dentry, unsigned int flags)
{
struct inode *inode;
struct task_struct *task;
+ int ret = 0;
- if (flags & LOOKUP_RCU)
- return -ECHILD;
-
- inode = d_inode(dentry);
- task = get_proc_task(inode);
+ rcu_read_lock();
+ inode = d_inode_rcu(dentry);
+ if (!inode)
+ goto out;
+ task = pid_task(proc_pid(inode), PIDTYPE_PID);
if (task) {
pid_update_inode(task, inode);
- put_task_struct(task);
- return 1;
+ ret = 1;
}
- return 0;
+out:
+ rcu_read_unlock();
+ return ret;
}
static inline bool proc_inode_is_dead(struct inode *inode)
@@ -3799,7 +3804,10 @@ static int proc_task_readdir(struct file *file, struct dir_context *ctx)
task = next_tid(task), ctx->pos++) {
char name[10 + 1];
unsigned int len;
+
tid = task_pid_nr_ns(task, ns);
+ if (!tid)
+ continue; /* The task has just exited. */
len = snprintf(name, sizeof(name), "%u", tid);
if (!proc_fill_cache(file, ctx, name, len,
proc_task_instantiate, task, NULL)) {
diff --git a/fs/proc/stat.c b/fs/proc/stat.c
index 6561a06ef905..4fb8729a68d4 100644
--- a/fs/proc/stat.c
+++ b/fs/proc/stat.c
@@ -24,7 +24,7 @@
#ifdef arch_idle_time
-static u64 get_idle_time(struct kernel_cpustat *kcs, int cpu)
+u64 get_idle_time(struct kernel_cpustat *kcs, int cpu)
{
u64 idle;
@@ -46,7 +46,7 @@ static u64 get_iowait_time(struct kernel_cpustat *kcs, int cpu)
#else
-static u64 get_idle_time(struct kernel_cpustat *kcs, int cpu)
+u64 get_idle_time(struct kernel_cpustat *kcs, int cpu)
{
u64 idle, idle_usecs = -1ULL;
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index cf25be3e0321..ad667dbc96f5 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -397,7 +397,6 @@ struct mem_size_stats {
u64 pss_shmem;
u64 pss_locked;
u64 swap_pss;
- bool check_shmem_swap;
};
static void smaps_page_accumulate(struct mem_size_stats *mss,
@@ -478,9 +477,11 @@ static int smaps_pte_hole(unsigned long addr, unsigned long end,
__always_unused int depth, struct mm_walk *walk)
{
struct mem_size_stats *mss = walk->private;
+ struct vm_area_struct *vma = walk->vma;
- mss->swap += shmem_partial_swap_usage(
- walk->vma->vm_file->f_mapping, addr, end);
+ mss->swap += shmem_partial_swap_usage(walk->vma->vm_file->f_mapping,
+ linear_page_index(vma, addr),
+ linear_page_index(vma, end));
return 0;
}
@@ -488,6 +489,16 @@ static int smaps_pte_hole(unsigned long addr, unsigned long end,
#define smaps_pte_hole NULL
#endif /* CONFIG_SHMEM */
+static void smaps_pte_hole_lookup(unsigned long addr, struct mm_walk *walk)
+{
+#ifdef CONFIG_SHMEM
+ if (walk->ops->pte_hole) {
+ /* depth is not used */
+ smaps_pte_hole(addr, addr + PAGE_SIZE, 0, walk);
+ }
+#endif
+}
+
static void smaps_pte_entry(pte_t *pte, unsigned long addr,
struct mm_walk *walk)
{
@@ -516,12 +527,8 @@ static void smaps_pte_entry(pte_t *pte, unsigned long addr,
}
} else if (is_pfn_swap_entry(swpent))
page = pfn_swap_entry_to_page(swpent);
- } else if (unlikely(IS_ENABLED(CONFIG_SHMEM) && mss->check_shmem_swap
- && pte_none(*pte))) {
- page = xa_load(&vma->vm_file->f_mapping->i_pages,
- linear_page_index(vma, addr));
- if (xa_is_value(page))
- mss->swap += PAGE_SIZE;
+ } else {
+ smaps_pte_hole_lookup(addr, walk);
return;
}
@@ -735,8 +742,6 @@ static void smap_gather_stats(struct vm_area_struct *vma,
return;
#ifdef CONFIG_SHMEM
- /* In case of smaps_rollup, reset the value from previous vma */
- mss->check_shmem_swap = false;
if (vma->vm_file && shmem_mapping(vma->vm_file->f_mapping)) {
/*
* For shared or readonly shmem mappings we know that all
@@ -754,7 +759,6 @@ static void smap_gather_stats(struct vm_area_struct *vma,
!(vma->vm_flags & VM_WRITE))) {
mss->swap += shmem_swapped;
} else {
- mss->check_shmem_swap = true;
ops = &smaps_shmem_walk_ops;
}
}
diff --git a/fs/proc/uptime.c b/fs/proc/uptime.c
index 5a1b228964fb..deb99bc9b7e6 100644
--- a/fs/proc/uptime.c
+++ b/fs/proc/uptime.c
@@ -12,18 +12,22 @@ static int uptime_proc_show(struct seq_file *m, void *v)
{
struct timespec64 uptime;
struct timespec64 idle;
- u64 nsec;
+ u64 idle_nsec;
u32 rem;
int i;
- nsec = 0;
- for_each_possible_cpu(i)
- nsec += (__force u64) kcpustat_cpu(i).cpustat[CPUTIME_IDLE];
+ idle_nsec = 0;
+ for_each_possible_cpu(i) {
+ struct kernel_cpustat kcs;
+
+ kcpustat_cpu_fetch(&kcs, i);
+ idle_nsec += get_idle_time(&kcs, i);
+ }
ktime_get_boottime_ts64(&uptime);
timens_add_boottime(&uptime);
- idle.tv_sec = div_u64_rem(nsec, NSEC_PER_SEC, &rem);
+ idle.tv_sec = div_u64_rem(idle_nsec, NSEC_PER_SEC, &rem);
idle.tv_nsec = rem;
seq_printf(m, "%lu.%02lu %lu.%02lu\n",
(unsigned long) uptime.tv_sec,
diff --git a/fs/proc/vmcore.c b/fs/proc/vmcore.c
index 9a15334da208..30a3b66f475a 100644
--- a/fs/proc/vmcore.c
+++ b/fs/proc/vmcore.c
@@ -26,7 +26,7 @@
#include <linux/vmalloc.h>
#include <linux/pagemap.h>
#include <linux/uaccess.h>
-#include <linux/mem_encrypt.h>
+#include <linux/cc_platform.h>
#include <asm/io.h>
#include "internal.h"
@@ -62,46 +62,75 @@ core_param(novmcoredd, vmcoredd_disabled, bool, 0);
/* Device Dump Size */
static size_t vmcoredd_orig_sz;
-/*
- * Returns > 0 for RAM pages, 0 for non-RAM pages, < 0 on error
- * The called function has to take care of module refcounting.
- */
-static int (*oldmem_pfn_is_ram)(unsigned long pfn);
+static DECLARE_RWSEM(vmcore_cb_rwsem);
+/* List of registered vmcore callbacks. */
+static LIST_HEAD(vmcore_cb_list);
+/* Whether we had a surprise unregistration of a callback. */
+static bool vmcore_cb_unstable;
+/* Whether the vmcore has been opened once. */
+static bool vmcore_opened;
-int register_oldmem_pfn_is_ram(int (*fn)(unsigned long pfn))
+void register_vmcore_cb(struct vmcore_cb *cb)
{
- if (oldmem_pfn_is_ram)
- return -EBUSY;
- oldmem_pfn_is_ram = fn;
- return 0;
+ down_write(&vmcore_cb_rwsem);
+ INIT_LIST_HEAD(&cb->next);
+ list_add_tail(&cb->next, &vmcore_cb_list);
+ /*
+ * Registering a vmcore callback after the vmcore was opened is
+ * very unusual (e.g., manual driver loading).
+ */
+ if (vmcore_opened)
+ pr_warn_once("Unexpected vmcore callback registration\n");
+ up_write(&vmcore_cb_rwsem);
}
-EXPORT_SYMBOL_GPL(register_oldmem_pfn_is_ram);
+EXPORT_SYMBOL_GPL(register_vmcore_cb);
-void unregister_oldmem_pfn_is_ram(void)
+void unregister_vmcore_cb(struct vmcore_cb *cb)
{
- oldmem_pfn_is_ram = NULL;
- wmb();
+ down_write(&vmcore_cb_rwsem);
+ list_del(&cb->next);
+ /*
+ * Unregistering a vmcore callback after the vmcore was opened is
+ * very unusual (e.g., forced driver removal), but we cannot stop
+ * unregistering.
+ */
+ if (vmcore_opened) {
+ pr_warn_once("Unexpected vmcore callback unregistration\n");
+ vmcore_cb_unstable = true;
+ }
+ up_write(&vmcore_cb_rwsem);
}
-EXPORT_SYMBOL_GPL(unregister_oldmem_pfn_is_ram);
+EXPORT_SYMBOL_GPL(unregister_vmcore_cb);
-static int pfn_is_ram(unsigned long pfn)
+static bool pfn_is_ram(unsigned long pfn)
{
- int (*fn)(unsigned long pfn);
- /* pfn is ram unless fn() checks pagetype */
- int ret = 1;
+ struct vmcore_cb *cb;
+ bool ret = true;
- /*
- * Ask hypervisor if the pfn is really ram.
- * A ballooned page contains no data and reading from such a page
- * will cause high load in the hypervisor.
- */
- fn = oldmem_pfn_is_ram;
- if (fn)
- ret = fn(pfn);
+ lockdep_assert_held_read(&vmcore_cb_rwsem);
+ if (unlikely(vmcore_cb_unstable))
+ return false;
+
+ list_for_each_entry(cb, &vmcore_cb_list, next) {
+ if (unlikely(!cb->pfn_is_ram))
+ continue;
+ ret = cb->pfn_is_ram(cb, pfn);
+ if (!ret)
+ break;
+ }
return ret;
}
+static int open_vmcore(struct inode *inode, struct file *file)
+{
+ down_read(&vmcore_cb_rwsem);
+ vmcore_opened = true;
+ up_read(&vmcore_cb_rwsem);
+
+ return 0;
+}
+
/* Reads a page from the oldmem device from given offset. */
ssize_t read_from_oldmem(char *buf, size_t count,
u64 *ppos, int userbuf,
@@ -117,6 +146,7 @@ ssize_t read_from_oldmem(char *buf, size_t count,
offset = (unsigned long)(*ppos % PAGE_SIZE);
pfn = (unsigned long)(*ppos / PAGE_SIZE);
+ down_read(&vmcore_cb_rwsem);
do {
if (count > (PAGE_SIZE - offset))
nr_bytes = PAGE_SIZE - offset;
@@ -124,7 +154,7 @@ ssize_t read_from_oldmem(char *buf, size_t count,
nr_bytes = count;
/* If pfn is not ram, return zeros for sparse dump files */
- if (pfn_is_ram(pfn) == 0)
+ if (!pfn_is_ram(pfn))
memset(buf, 0, nr_bytes);
else {
if (encrypted)
@@ -136,8 +166,10 @@ ssize_t read_from_oldmem(char *buf, size_t count,
tmp = copy_oldmem_page(pfn, buf, nr_bytes,
offset, userbuf);
- if (tmp < 0)
+ if (tmp < 0) {
+ up_read(&vmcore_cb_rwsem);
return tmp;
+ }
}
*ppos += nr_bytes;
count -= nr_bytes;
@@ -147,6 +179,7 @@ ssize_t read_from_oldmem(char *buf, size_t count,
offset = 0;
} while (count);
+ up_read(&vmcore_cb_rwsem);
return read;
}
@@ -177,7 +210,7 @@ ssize_t __weak elfcorehdr_read(char *buf, size_t count, u64 *ppos)
*/
ssize_t __weak elfcorehdr_read_notes(char *buf, size_t count, u64 *ppos)
{
- return read_from_oldmem(buf, count, ppos, 0, mem_encrypt_active());
+ return read_from_oldmem(buf, count, ppos, 0, cc_platform_has(CC_ATTR_MEM_ENCRYPT));
}
/*
@@ -378,7 +411,7 @@ static ssize_t __read_vmcore(char *buffer, size_t buflen, loff_t *fpos,
buflen);
start = m->paddr + *fpos - m->offset;
tmp = read_from_oldmem(buffer, tsz, &start,
- userbuf, mem_encrypt_active());
+ userbuf, cc_platform_has(CC_ATTR_MEM_ENCRYPT));
if (tmp < 0)
return tmp;
buflen -= tsz;
@@ -537,14 +570,19 @@ static int vmcore_remap_oldmem_pfn(struct vm_area_struct *vma,
unsigned long from, unsigned long pfn,
unsigned long size, pgprot_t prot)
{
+ int ret;
+
/*
* Check if oldmem_pfn_is_ram was registered to avoid
* looping over all pages without a reason.
*/
- if (oldmem_pfn_is_ram)
- return remap_oldmem_pfn_checked(vma, from, pfn, size, prot);
+ down_read(&vmcore_cb_rwsem);
+ if (!list_empty(&vmcore_cb_list) || vmcore_cb_unstable)
+ ret = remap_oldmem_pfn_checked(vma, from, pfn, size, prot);
else
- return remap_oldmem_pfn_range(vma, from, pfn, size, prot);
+ ret = remap_oldmem_pfn_range(vma, from, pfn, size, prot);
+ up_read(&vmcore_cb_rwsem);
+ return ret;
}
static int mmap_vmcore(struct file *file, struct vm_area_struct *vma)
@@ -668,6 +706,7 @@ static int mmap_vmcore(struct file *file, struct vm_area_struct *vma)
#endif
static const struct proc_ops vmcore_proc_ops = {
+ .proc_open = open_vmcore,
.proc_read = read_vmcore,
.proc_lseek = default_llseek,
.proc_mmap = mmap_vmcore,
Powered by cgit, Gruvboxed by Blaster4385.