summaryrefslogtreecommitdiffstats
path: root/fs/proc
diff options
context:
space:
mode:
Diffstat (limited to 'fs/proc')
-rw-r--r--fs/proc/Kconfig4
-rw-r--r--fs/proc/array.c2
-rw-r--r--fs/proc/consoles.c10
-rw-r--r--fs/proc/fd.c2
-rw-r--r--fs/proc/generic.c18
-rw-r--r--fs/proc/inode.c24
-rw-r--r--fs/proc/kcore.c3
-rw-r--r--fs/proc/meminfo.c13
-rw-r--r--fs/proc/namespaces.c8
-rw-r--r--fs/proc/nommu.c12
-rw-r--r--fs/proc/proc_devtree.c3
-rw-r--r--fs/proc/root.c6
-rw-r--r--fs/proc/self.c10
-rw-r--r--fs/proc/task_mmu.c97
-rw-r--r--fs/proc/task_nommu.c19
-rw-r--r--fs/proc/vmcore.c154
16 files changed, 253 insertions, 132 deletions
diff --git a/fs/proc/Kconfig b/fs/proc/Kconfig
index 15af6222f8a4..2183fcf41d59 100644
--- a/fs/proc/Kconfig
+++ b/fs/proc/Kconfig
@@ -31,6 +31,10 @@ config PROC_FS
config PROC_KCORE
bool "/proc/kcore support" if !ARM
depends on PROC_FS && MMU
+ help
+ Provides a virtual ELF core file of the live kernel. This can
+ be read with gdb and other ELF tools. No modifications can be
+ made using this mechanism.
config PROC_VMCORE
bool "/proc/vmcore support"
diff --git a/fs/proc/array.c b/fs/proc/array.c
index cbd0f1b324b9..1bd2077187fd 100644
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -183,6 +183,7 @@ static inline void task_state(struct seq_file *m, struct pid_namespace *ns,
seq_printf(m,
"State:\t%s\n"
"Tgid:\t%d\n"
+ "Ngid:\t%d\n"
"Pid:\t%d\n"
"PPid:\t%d\n"
"TracerPid:\t%d\n"
@@ -190,6 +191,7 @@ static inline void task_state(struct seq_file *m, struct pid_namespace *ns,
"Gid:\t%d\t%d\t%d\t%d\n",
get_task_state(p),
task_tgid_nr_ns(p, ns),
+ task_numa_group_id(p),
pid_nr_ns(pid, ns),
ppid, tpid,
from_kuid_munged(user_ns, cred->uid),
diff --git a/fs/proc/consoles.c b/fs/proc/consoles.c
index b701eaa482bf..51942d5abcec 100644
--- a/fs/proc/consoles.c
+++ b/fs/proc/consoles.c
@@ -29,7 +29,6 @@ static int show_console_dev(struct seq_file *m, void *v)
char flags[ARRAY_SIZE(con_flags) + 1];
struct console *con = v;
unsigned int a;
- int len;
dev_t dev = 0;
if (con->device) {
@@ -47,11 +46,10 @@ static int show_console_dev(struct seq_file *m, void *v)
con_flags[a].name : ' ';
flags[a] = 0;
- seq_printf(m, "%s%d%n", con->name, con->index, &len);
- len = 21 - len;
- if (len < 1)
- len = 1;
- seq_printf(m, "%*c%c%c%c (%s)", len, ' ', con->read ? 'R' : '-',
+ seq_setwidth(m, 21 - 1);
+ seq_printf(m, "%s%d", con->name, con->index);
+ seq_pad(m, ' ');
+ seq_printf(m, "%c%c%c (%s)", con->read ? 'R' : '-',
con->write ? 'W' : '-', con->unblank ? 'U' : '-',
flags);
if (dev)
diff --git a/fs/proc/fd.c b/fs/proc/fd.c
index 0ff80f9b930f..985ea881b5bc 100644
--- a/fs/proc/fd.c
+++ b/fs/proc/fd.c
@@ -286,7 +286,7 @@ int proc_fd_permission(struct inode *inode, int mask)
int rv = generic_permission(inode, mask);
if (rv == 0)
return 0;
- if (task_pid(current) == proc_pid(inode))
+ if (task_tgid(current) == proc_pid(inode))
rv = 0;
return rv;
}
diff --git a/fs/proc/generic.c b/fs/proc/generic.c
index 737e15615b04..cca93b6fb9a9 100644
--- a/fs/proc/generic.c
+++ b/fs/proc/generic.c
@@ -175,22 +175,6 @@ static const struct inode_operations proc_link_inode_operations = {
};
/*
- * As some entries in /proc are volatile, we want to
- * get rid of unused dentries. This could be made
- * smarter: we could keep a "volatile" flag in the
- * inode to indicate which ones to keep.
- */
-static int proc_delete_dentry(const struct dentry * dentry)
-{
- return 1;
-}
-
-static const struct dentry_operations proc_dentry_operations =
-{
- .d_delete = proc_delete_dentry,
-};
-
-/*
* Don't create negative dentries here, return -ENOENT by hand
* instead.
*/
@@ -209,7 +193,7 @@ struct dentry *proc_lookup_de(struct proc_dir_entry *de, struct inode *dir,
inode = proc_get_inode(dir->i_sb, de);
if (!inode)
return ERR_PTR(-ENOMEM);
- d_set_d_op(dentry, &proc_dentry_operations);
+ d_set_d_op(dentry, &simple_dentry_operations);
d_add(dentry, inode);
return NULL;
}
diff --git a/fs/proc/inode.c b/fs/proc/inode.c
index 073aea60cf8f..28955d4b7218 100644
--- a/fs/proc/inode.c
+++ b/fs/proc/inode.c
@@ -285,6 +285,28 @@ static int proc_reg_mmap(struct file *file, struct vm_area_struct *vma)
return rv;
}
+static unsigned long
+proc_reg_get_unmapped_area(struct file *file, unsigned long orig_addr,
+ unsigned long len, unsigned long pgoff,
+ unsigned long flags)
+{
+ struct proc_dir_entry *pde = PDE(file_inode(file));
+ unsigned long rv = -EIO;
+ unsigned long (*get_area)(struct file *, unsigned long, unsigned long,
+ unsigned long, unsigned long) = NULL;
+ if (use_pde(pde)) {
+#ifdef CONFIG_MMU
+ get_area = current->mm->get_unmapped_area;
+#endif
+ if (pde->proc_fops->get_unmapped_area)
+ get_area = pde->proc_fops->get_unmapped_area;
+ if (get_area)
+ rv = get_area(file, orig_addr, len, pgoff, flags);
+ unuse_pde(pde);
+ }
+ return rv;
+}
+
static int proc_reg_open(struct inode *inode, struct file *file)
{
struct proc_dir_entry *pde = PDE(inode);
@@ -356,6 +378,7 @@ static const struct file_operations proc_reg_file_ops = {
.compat_ioctl = proc_reg_compat_ioctl,
#endif
.mmap = proc_reg_mmap,
+ .get_unmapped_area = proc_reg_get_unmapped_area,
.open = proc_reg_open,
.release = proc_reg_release,
};
@@ -368,6 +391,7 @@ static const struct file_operations proc_reg_file_ops_no_compat = {
.poll = proc_reg_poll,
.unlocked_ioctl = proc_reg_unlocked_ioctl,
.mmap = proc_reg_mmap,
+ .get_unmapped_area = proc_reg_get_unmapped_area,
.open = proc_reg_open,
.release = proc_reg_release,
};
diff --git a/fs/proc/kcore.c b/fs/proc/kcore.c
index 06ea155e1a59..5ed0e52d6aa0 100644
--- a/fs/proc/kcore.c
+++ b/fs/proc/kcore.c
@@ -255,8 +255,7 @@ static int kcore_update_ram(void)
end_pfn = 0;
for_each_node_state(nid, N_MEMORY) {
unsigned long node_end;
- node_end = NODE_DATA(nid)->node_start_pfn +
- NODE_DATA(nid)->node_spanned_pages;
+ node_end = node_end_pfn(nid);
if (end_pfn < node_end)
end_pfn = node_end;
}
diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c
index 5aa847a603c0..a77d2b299199 100644
--- a/fs/proc/meminfo.c
+++ b/fs/proc/meminfo.c
@@ -1,8 +1,8 @@
#include <linux/fs.h>
-#include <linux/hugetlb.h>
#include <linux/init.h>
#include <linux/kernel.h>
#include <linux/mm.h>
+#include <linux/hugetlb.h>
#include <linux/mman.h>
#include <linux/mmzone.h>
#include <linux/proc_fs.h>
@@ -24,7 +24,6 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
{
struct sysinfo i;
unsigned long committed;
- unsigned long allowed;
struct vmalloc_info vmi;
long cached;
unsigned long pages[NR_LRU_LISTS];
@@ -37,8 +36,6 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
si_meminfo(&i);
si_swapinfo(&i);
committed = percpu_counter_read_positive(&vm_committed_as);
- allowed = ((totalram_pages - hugetlb_total_pages())
- * sysctl_overcommit_ratio / 100) + total_swap_pages;
cached = global_page_state(NR_FILE_PAGES) -
total_swapcache_pages() - i.bufferram;
@@ -132,13 +129,7 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
K(i.freeswap),
K(global_page_state(NR_FILE_DIRTY)),
K(global_page_state(NR_WRITEBACK)),
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
- K(global_page_state(NR_ANON_PAGES)
- + global_page_state(NR_ANON_TRANSPARENT_HUGEPAGES) *
- HPAGE_PMD_NR),
-#else
K(global_page_state(NR_ANON_PAGES)),
-#endif
K(global_page_state(NR_FILE_MAPPED)),
K(global_page_state(NR_SHMEM)),
K(global_page_state(NR_SLAB_RECLAIMABLE) +
@@ -153,7 +144,7 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
K(global_page_state(NR_UNSTABLE_NFS)),
K(global_page_state(NR_BOUNCE)),
K(global_page_state(NR_WRITEBACK_TEMP)),
- K(allowed),
+ K(vm_commit_limit()),
K(committed),
(unsigned long)VMALLOC_TOTAL >> 10,
vmi.used >> 10,
diff --git a/fs/proc/namespaces.c b/fs/proc/namespaces.c
index 49a7fff2e83a..9ae46b87470d 100644
--- a/fs/proc/namespaces.c
+++ b/fs/proc/namespaces.c
@@ -42,12 +42,6 @@ static const struct inode_operations ns_inode_operations = {
.setattr = proc_setattr,
};
-static int ns_delete_dentry(const struct dentry *dentry)
-{
- /* Don't cache namespace inodes when not in use */
- return 1;
-}
-
static char *ns_dname(struct dentry *dentry, char *buffer, int buflen)
{
struct inode *inode = dentry->d_inode;
@@ -59,7 +53,7 @@ static char *ns_dname(struct dentry *dentry, char *buffer, int buflen)
const struct dentry_operations ns_dentry_operations =
{
- .d_delete = ns_delete_dentry,
+ .d_delete = always_delete_dentry,
.d_dname = ns_dname,
};
diff --git a/fs/proc/nommu.c b/fs/proc/nommu.c
index ccfd99bd1c5a..5f9bc8a746c9 100644
--- a/fs/proc/nommu.c
+++ b/fs/proc/nommu.c
@@ -39,7 +39,7 @@ static int nommu_region_show(struct seq_file *m, struct vm_region *region)
unsigned long ino = 0;
struct file *file;
dev_t dev = 0;
- int flags, len;
+ int flags;
flags = region->vm_flags;
file = region->vm_file;
@@ -50,8 +50,9 @@ static int nommu_region_show(struct seq_file *m, struct vm_region *region)
ino = inode->i_ino;
}
+ seq_setwidth(m, 25 + sizeof(void *) * 6 - 1);
seq_printf(m,
- "%08lx-%08lx %c%c%c%c %08llx %02x:%02x %lu %n",
+ "%08lx-%08lx %c%c%c%c %08llx %02x:%02x %lu ",
region->vm_start,
region->vm_end,
flags & VM_READ ? 'r' : '-',
@@ -59,13 +60,10 @@ static int nommu_region_show(struct seq_file *m, struct vm_region *region)
flags & VM_EXEC ? 'x' : '-',
flags & VM_MAYSHARE ? flags & VM_SHARED ? 'S' : 's' : 'p',
((loff_t)region->vm_pgoff) << PAGE_SHIFT,
- MAJOR(dev), MINOR(dev), ino, &len);
+ MAJOR(dev), MINOR(dev), ino);
if (file) {
- len = 25 + sizeof(void *) * 6 - len;
- if (len < 1)
- len = 1;
- seq_printf(m, "%*c", len, ' ');
+ seq_pad(m, ' ');
seq_path(m, &file->f_path, "");
}
diff --git a/fs/proc/proc_devtree.c b/fs/proc/proc_devtree.c
index 106a83570630..70779b2fc209 100644
--- a/fs/proc/proc_devtree.c
+++ b/fs/proc/proc_devtree.c
@@ -14,16 +14,13 @@
#include <linux/of.h>
#include <linux/export.h>
#include <linux/slab.h>
-#include <asm/prom.h>
#include <asm/uaccess.h>
#include "internal.h"
static inline void set_node_proc_entry(struct device_node *np,
struct proc_dir_entry *de)
{
-#ifdef HAVE_ARCH_DEVTREE_FIXUPS
np->pde = de;
-#endif
}
static struct proc_dir_entry *proc_device_tree;
diff --git a/fs/proc/root.c b/fs/proc/root.c
index e0a790da726d..87dbcbef7fe4 100644
--- a/fs/proc/root.c
+++ b/fs/proc/root.c
@@ -110,7 +110,11 @@ static struct dentry *proc_mount(struct file_system_type *fs_type,
ns = task_active_pid_ns(current);
options = data;
- if (!current_user_ns()->may_mount_proc)
+ if (!capable(CAP_SYS_ADMIN) && !fs_fully_visible(fs_type))
+ return ERR_PTR(-EPERM);
+
+ /* Does the mounter have privilege over the pid namespace? */
+ if (!ns_capable(ns->user_ns, CAP_SYS_ADMIN))
return ERR_PTR(-EPERM);
}
diff --git a/fs/proc/self.c b/fs/proc/self.c
index 6b6a993b5c25..ffeb202ec942 100644
--- a/fs/proc/self.c
+++ b/fs/proc/self.c
@@ -36,18 +36,10 @@ static void *proc_self_follow_link(struct dentry *dentry, struct nameidata *nd)
return NULL;
}
-static void proc_self_put_link(struct dentry *dentry, struct nameidata *nd,
- void *cookie)
-{
- char *s = nd_get_link(nd);
- if (!IS_ERR(s))
- kfree(s);
-}
-
static const struct inode_operations proc_self_inode_operations = {
.readlink = proc_self_readlink,
.follow_link = proc_self_follow_link,
- .put_link = proc_self_put_link,
+ .put_link = kfree_put_link,
};
static unsigned self_inum;
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 107d026f5d6e..fb52b548080d 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -62,7 +62,8 @@ void task_mem(struct seq_file *m, struct mm_struct *mm)
total_rss << (PAGE_SHIFT-10),
data << (PAGE_SHIFT-10),
mm->stack_vm << (PAGE_SHIFT-10), text, lib,
- (PTRS_PER_PTE*sizeof(pte_t)*mm->nr_ptes) >> 10,
+ (PTRS_PER_PTE * sizeof(pte_t) *
+ atomic_long_read(&mm->nr_ptes)) >> 10,
swap << (PAGE_SHIFT-10));
}
@@ -83,14 +84,6 @@ unsigned long task_statm(struct mm_struct *mm,
return mm->total_vm;
}
-static void pad_len_spaces(struct seq_file *m, int len)
-{
- len = 25 + sizeof(void*) * 6 - len;
- if (len < 1)
- len = 1;
- seq_printf(m, "%*c", len, ' ');
-}
-
#ifdef CONFIG_NUMA
/*
* These functions are for numa_maps but called in generic **maps seq_file
@@ -268,7 +261,6 @@ show_map_vma(struct seq_file *m, struct vm_area_struct *vma, int is_pid)
unsigned long long pgoff = 0;
unsigned long start, end;
dev_t dev = 0;
- int len;
const char *name = NULL;
if (file) {
@@ -286,7 +278,8 @@ show_map_vma(struct seq_file *m, struct vm_area_struct *vma, int is_pid)
if (stack_guard_page_end(vma, end))
end -= PAGE_SIZE;
- seq_printf(m, "%08lx-%08lx %c%c%c%c %08llx %02x:%02x %lu %n",
+ seq_setwidth(m, 25 + sizeof(void *) * 6 - 1);
+ seq_printf(m, "%08lx-%08lx %c%c%c%c %08llx %02x:%02x %lu ",
start,
end,
flags & VM_READ ? 'r' : '-',
@@ -294,14 +287,14 @@ show_map_vma(struct seq_file *m, struct vm_area_struct *vma, int is_pid)
flags & VM_EXEC ? 'x' : '-',
flags & VM_MAYSHARE ? 's' : 'p',
pgoff,
- MAJOR(dev), MINOR(dev), ino, &len);
+ MAJOR(dev), MINOR(dev), ino);
/*
* Print the dentry name for named mappings, and a
* special [heap] marker for the heap:
*/
if (file) {
- pad_len_spaces(m, len);
+ seq_pad(m, ' ');
seq_path(m, &file->f_path, "\n");
goto done;
}
@@ -333,7 +326,7 @@ show_map_vma(struct seq_file *m, struct vm_area_struct *vma, int is_pid)
name = "[stack]";
} else {
/* Thread stack in /proc/PID/maps */
- pad_len_spaces(m, len);
+ seq_pad(m, ' ');
seq_printf(m, "[stack:%d]", tid);
}
}
@@ -341,7 +334,7 @@ show_map_vma(struct seq_file *m, struct vm_area_struct *vma, int is_pid)
done:
if (name) {
- pad_len_spaces(m, len);
+ seq_pad(m, ' ');
seq_puts(m, name);
}
seq_putc(m, '\n');
@@ -505,9 +498,9 @@ 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) == 1) {
+ if (pmd_trans_huge_lock(pmd, vma, &ptl) == 1) {
smaps_pte_entry(*(pte_t *)pmd, addr, HPAGE_PMD_SIZE, walk);
- spin_unlock(&walk->mm->page_table_lock);
+ spin_unlock(ptl);
mss->anonymous_thp += HPAGE_PMD_SIZE;
return 0;
}
@@ -561,6 +554,9 @@ static void show_smap_vma_flags(struct seq_file *m, struct vm_area_struct *vma)
[ilog2(VM_NONLINEAR)] = "nl",
[ilog2(VM_ARCH_1)] = "ar",
[ilog2(VM_DONTDUMP)] = "dd",
+#ifdef CONFIG_MEM_SOFT_DIRTY
+ [ilog2(VM_SOFTDIRTY)] = "sd",
+#endif
[ilog2(VM_MIXEDMAP)] = "mm",
[ilog2(VM_HUGEPAGE)] = "hg",
[ilog2(VM_NOHUGEPAGE)] = "nh",
@@ -740,6 +736,9 @@ static inline void clear_soft_dirty(struct vm_area_struct *vma,
ptent = pte_file_clear_soft_dirty(ptent);
}
+ if (vma->vm_flags & VM_SOFTDIRTY)
+ vma->vm_flags &= ~VM_SOFTDIRTY;
+
set_pte_at(vma->vm_mm, addr, pte, ptent);
#endif
}
@@ -938,6 +937,8 @@ static void pte_to_pagemap_entry(pagemap_entry_t *pme, struct pagemapread *pm,
frame = pte_pfn(pte);
flags = PM_PRESENT;
page = vm_normal_page(vma, addr, pte);
+ if (pte_soft_dirty(pte))
+ flags2 |= __PM_SOFT_DIRTY;
} else if (is_swap_pte(pte)) {
swp_entry_t entry;
if (pte_swp_soft_dirty(pte))
@@ -949,13 +950,15 @@ static void pte_to_pagemap_entry(pagemap_entry_t *pme, struct pagemapread *pm,
if (is_migration_entry(entry))
page = migration_entry_to_page(entry);
} else {
- *pme = make_pme(PM_NOT_PRESENT(pm->v2));
+ if (vma->vm_flags & VM_SOFTDIRTY)
+ flags2 |= __PM_SOFT_DIRTY;
+ *pme = make_pme(PM_NOT_PRESENT(pm->v2) | PM_STATUS2(pm->v2, flags2));
return;
}
if (page && !PageAnon(page))
flags |= PM_FILE;
- if (pte_soft_dirty(pte))
+ if ((vma->vm_flags & VM_SOFTDIRTY))
flags2 |= __PM_SOFT_DIRTY;
*pme = make_pme(PM_PFRAME(frame) | PM_STATUS2(pm->v2, flags2) | flags);
@@ -974,7 +977,7 @@ static void thp_pmd_to_pagemap_entry(pagemap_entry_t *pme, struct pagemapread *p
*pme = make_pme(PM_PFRAME(pmd_pfn(pmd) + offset)
| PM_STATUS2(pm->v2, pmd_flags2) | PM_PRESENT);
else
- *pme = make_pme(PM_NOT_PRESENT(pm->v2));
+ *pme = make_pme(PM_NOT_PRESENT(pm->v2) | PM_STATUS2(pm->v2, pmd_flags2));
}
#else
static inline void thp_pmd_to_pagemap_entry(pagemap_entry_t *pme, struct pagemapread *pm,
@@ -988,16 +991,21 @@ static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
{
struct vm_area_struct *vma;
struct pagemapread *pm = walk->private;
+ spinlock_t *ptl;
pte_t *pte;
int err = 0;
pagemap_entry_t pme = make_pme(PM_NOT_PRESENT(pm->v2));
/* find the first VMA at or above 'addr' */
vma = find_vma(walk->mm, addr);
- if (vma && pmd_trans_huge_lock(pmd, vma) == 1) {
+ if (vma && pmd_trans_huge_lock(pmd, vma, &ptl) == 1) {
int pmd_flags2;
- pmd_flags2 = (pmd_soft_dirty(*pmd) ? __PM_SOFT_DIRTY : 0);
+ if ((vma->vm_flags & VM_SOFTDIRTY) || pmd_soft_dirty(*pmd))
+ pmd_flags2 = __PM_SOFT_DIRTY;
+ else
+ pmd_flags2 = 0;
+
for (; addr != end; addr += PAGE_SIZE) {
unsigned long offset;
@@ -1008,19 +1016,24 @@ static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
if (err)
break;
}
- spin_unlock(&walk->mm->page_table_lock);
+ spin_unlock(ptl);
return err;
}
if (pmd_trans_unstable(pmd))
return 0;
for (; addr != end; addr += PAGE_SIZE) {
+ int flags2;
/* check to see if we've left 'vma' behind
* and need a new, higher one */
if (vma && (addr >= vma->vm_end)) {
vma = find_vma(walk->mm, addr);
- pme = make_pme(PM_NOT_PRESENT(pm->v2));
+ if (vma && (vma->vm_flags & VM_SOFTDIRTY))
+ flags2 = __PM_SOFT_DIRTY;
+ else
+ flags2 = 0;
+ pme = make_pme(PM_NOT_PRESENT(pm->v2) | PM_STATUS2(pm->v2, flags2));
}
/* check that 'vma' actually covers this address,
@@ -1044,13 +1057,15 @@ static int pagemap_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
#ifdef CONFIG_HUGETLB_PAGE
static void huge_pte_to_pagemap_entry(pagemap_entry_t *pme, struct pagemapread *pm,
- pte_t pte, int offset)
+ pte_t pte, int offset, int flags2)
{
if (pte_present(pte))
- *pme = make_pme(PM_PFRAME(pte_pfn(pte) + offset)
- | PM_STATUS2(pm->v2, 0) | PM_PRESENT);
+ *pme = make_pme(PM_PFRAME(pte_pfn(pte) + offset) |
+ PM_STATUS2(pm->v2, flags2) |
+ PM_PRESENT);
else
- *pme = make_pme(PM_NOT_PRESENT(pm->v2));
+ *pme = make_pme(PM_NOT_PRESENT(pm->v2) |
+ PM_STATUS2(pm->v2, flags2));
}
/* This function walks within one hugetlb entry in the single call */
@@ -1059,12 +1074,22 @@ static int pagemap_hugetlb_range(pte_t *pte, unsigned long hmask,
struct mm_walk *walk)
{
struct pagemapread *pm = walk->private;
+ struct vm_area_struct *vma;
int err = 0;
+ int flags2;
pagemap_entry_t pme;
+ vma = find_vma(walk->mm, addr);
+ WARN_ON_ONCE(!vma);
+
+ if (vma && (vma->vm_flags & VM_SOFTDIRTY))
+ flags2 = __PM_SOFT_DIRTY;
+ else
+ flags2 = 0;
+
for (; addr != end; addr += PAGE_SIZE) {
int offset = (addr & ~hmask) >> PAGE_SHIFT;
- huge_pte_to_pagemap_entry(&pme, pm, *pte, offset);
+ huge_pte_to_pagemap_entry(&pme, pm, *pte, offset, flags2);
err = add_to_pagemap(addr, &pme, pm);
if (err)
return err;
@@ -1293,7 +1318,7 @@ static int gather_pte_stats(pmd_t *pmd, unsigned long addr,
md = walk->private;
- if (pmd_trans_huge_lock(pmd, md->vma) == 1) {
+ if (pmd_trans_huge_lock(pmd, md->vma, &ptl) == 1) {
pte_t huge_pte = *(pte_t *)pmd;
struct page *page;
@@ -1301,7 +1326,7 @@ static int gather_pte_stats(pmd_t *pmd, unsigned long addr,
if (page)
gather_stats(page, md, pte_dirty(huge_pte),
HPAGE_PMD_SIZE/PAGE_SIZE);
- spin_unlock(&walk->mm->page_table_lock);
+ spin_unlock(ptl);
return 0;
}
@@ -1359,8 +1384,8 @@ static int show_numa_map(struct seq_file *m, void *v, int is_pid)
struct mm_struct *mm = vma->vm_mm;
struct mm_walk walk = {};
struct mempolicy *pol;
- int n;
- char buffer[50];
+ char buffer[64];
+ int nid;
if (!mm)
return 0;
@@ -1430,9 +1455,9 @@ static int show_numa_map(struct seq_file *m, void *v, int is_pid)
if (md->writeback)
seq_printf(m, " writeback=%lu", md->writeback);
- for_each_node_state(n, N_MEMORY)
- if (md->node[n])
- seq_printf(m, " N%d=%lu", n, md->node[n]);
+ for_each_node_state(nid, N_MEMORY)
+ if (md->node[nid])
+ seq_printf(m, " N%d=%lu", nid, md->node[nid]);
out:
seq_putc(m, '\n');
diff --git a/fs/proc/task_nommu.c b/fs/proc/task_nommu.c
index 56123a6f462e..678455d2d683 100644
--- a/fs/proc/task_nommu.c
+++ b/fs/proc/task_nommu.c
@@ -123,14 +123,6 @@ unsigned long task_statm(struct mm_struct *mm,
return size;
}
-static void pad_len_spaces(struct seq_file *m, int len)
-{
- len = 25 + sizeof(void*) * 6 - len;
- if (len < 1)
- len = 1;
- seq_printf(m, "%*c", len, ' ');
-}
-
/*
* display a single VMA to a sequenced file
*/
@@ -142,7 +134,7 @@ static int nommu_vma_show(struct seq_file *m, struct vm_area_struct *vma,
unsigned long ino = 0;
struct file *file;
dev_t dev = 0;
- int flags, len;
+ int flags;
unsigned long long pgoff = 0;
flags = vma->vm_flags;
@@ -155,8 +147,9 @@ static int nommu_vma_show(struct seq_file *m, struct vm_area_struct *vma,
pgoff = (loff_t)vma->vm_pgoff << PAGE_SHIFT;
}
+ seq_setwidth(m, 25 + sizeof(void *) * 6 - 1);
seq_printf(m,
- "%08lx-%08lx %c%c%c%c %08llx %02x:%02x %lu %n",
+ "%08lx-%08lx %c%c%c%c %08llx %02x:%02x %lu ",
vma->vm_start,
vma->vm_end,
flags & VM_READ ? 'r' : '-',
@@ -164,16 +157,16 @@ static int nommu_vma_show(struct seq_file *m, struct vm_area_struct *vma,
flags & VM_EXEC ? 'x' : '-',
flags & VM_MAYSHARE ? flags & VM_SHARED ? 'S' : 's' : 'p',
pgoff,
- MAJOR(dev), MINOR(dev), ino, &len);
+ MAJOR(dev), MINOR(dev), ino);
if (file) {
- pad_len_spaces(m, len);
+ seq_pad(m, ' ');
seq_path(m, &file->f_path, "");
} else if (mm) {
pid_t tid = vm_is_stack(priv->task, vma, is_pid);
if (tid != 0) {
- pad_len_spaces(m, len);
+ seq_pad(m, ' ');
/*
* Thread stack in /proc/PID/task/TID/maps or
* the main process stack.
diff --git a/fs/proc/vmcore.c b/fs/proc/vmcore.c
index a1a16eb97c7b..9100d6959886 100644
--- a/fs/proc/vmcore.c
+++ b/fs/proc/vmcore.c
@@ -21,6 +21,7 @@
#include <linux/crash_dump.h>
#include <linux/list.h>
#include <linux/vmalloc.h>
+#include <linux/pagemap.h>
#include <asm/uaccess.h>
#include <asm/io.h>
#include "internal.h"
@@ -123,11 +124,65 @@ static ssize_t read_from_oldmem(char *buf, size_t count,
return read;
}
+/*
+ * Architectures may override this function to allocate ELF header in 2nd kernel
+ */
+int __weak elfcorehdr_alloc(unsigned long long *addr, unsigned long long *size)
+{
+ return 0;
+}
+
+/*
+ * Architectures may override this function to free header
+ */
+void __weak elfcorehdr_free(unsigned long long addr)
+{}
+
+/*
+ * Architectures may override this function to read from ELF header
+ */
+ssize_t __weak elfcorehdr_read(char *buf, size_t count, u64 *ppos)
+{
+ return read_from_oldmem(buf, count, ppos, 0);
+}
+
+/*
+ * Architectures may override this function to read from notes sections
+ */
+ssize_t __weak elfcorehdr_read_notes(char *buf, size_t count, u64 *ppos)
+{
+ return read_from_oldmem(buf, count, ppos, 0);
+}
+
+/*
+ * Architectures may override this function to map oldmem
+ */
+int __weak remap_oldmem_pfn_range(struct vm_area_struct *vma,
+ unsigned long from, unsigned long pfn,
+ unsigned long size, pgprot_t prot)
+{
+ return remap_pfn_range(vma, from, pfn, size, prot);
+}
+
+/*
+ * Copy to either kernel or user space
+ */
+static int copy_to(void *target, void *src, size_t size, int userbuf)
+{
+ if (userbuf) {
+ if (copy_to_user((char __user *) target, src, size))
+ return -EFAULT;
+ } else {
+ memcpy(target, src, size);
+ }
+ return 0;
+}
+
/* Read from the ELF header and then the crash dump. On error, negative value is
* returned otherwise number of bytes read are returned.
*/
-static ssize_t read_vmcore(struct file *file, char __user *buffer,
- size_t buflen, loff_t *fpos)
+static ssize_t __read_vmcore(char *buffer, size_t buflen, loff_t *fpos,
+ int userbuf)
{
ssize_t acc = 0, tmp;
size_t tsz;
@@ -144,7 +199,7 @@ static ssize_t read_vmcore(struct file *file, char __user *buffer,
/* Read ELF core header */
if (*fpos < elfcorebuf_sz) {
tsz = min(elfcorebuf_sz - (size_t)*fpos, buflen);
- if (copy_to_user(buffer, elfcorebuf + *fpos, tsz))
+ if (copy_to(buffer, elfcorebuf + *fpos, tsz, userbuf))
return -EFAULT;
buflen -= tsz;
*fpos += tsz;
@@ -162,7 +217,7 @@ static ssize_t read_vmcore(struct file *file, char __user *buffer,
tsz = min(elfcorebuf_sz + elfnotes_sz - (size_t)*fpos, buflen);
kaddr = elfnotes_buf + *fpos - elfcorebuf_sz;
- if (copy_to_user(buffer, kaddr, tsz))
+ if (copy_to(buffer, kaddr, tsz, userbuf))
return -EFAULT;
buflen -= tsz;
*fpos += tsz;
@@ -178,7 +233,7 @@ static ssize_t read_vmcore(struct file *file, char __user *buffer,
if (*fpos < m->offset + m->size) {
tsz = min_t(size_t, m->offset + m->size - *fpos, buflen);
start = m->paddr + *fpos - m->offset;
- tmp = read_from_oldmem(buffer, tsz, &start, 1);
+ tmp = read_from_oldmem(buffer, tsz, &start, userbuf);
if (tmp < 0)
return tmp;
buflen -= tsz;
@@ -195,6 +250,55 @@ static ssize_t read_vmcore(struct file *file, char __user *buffer,
return acc;
}
+static ssize_t read_vmcore(struct file *file, char __user *buffer,
+ size_t buflen, loff_t *fpos)
+{
+ return __read_vmcore((__force char *) buffer, buflen, fpos, 1);
+}
+
+/*
+ * The vmcore fault handler uses the page cache and fills data using the
+ * standard __vmcore_read() function.
+ *
+ * On s390 the fault handler is used for memory regions that can't be mapped
+ * directly with remap_pfn_range().
+ */
+static int mmap_vmcore_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
+{
+#ifdef CONFIG_S390
+ struct address_space *mapping = vma->vm_file->f_mapping;
+ pgoff_t index = vmf->pgoff;
+ struct page *page;
+ loff_t offset;
+ char *buf;
+ int rc;
+
+ page = find_or_create_page(mapping, index, GFP_KERNEL);
+ if (!page)
+ return VM_FAULT_OOM;
+ if (!PageUptodate(page)) {
+ offset = (loff_t) index << PAGE_CACHE_SHIFT;
+ buf = __va((page_to_pfn(page) << PAGE_SHIFT));
+ rc = __read_vmcore(buf, PAGE_SIZE, &offset, 0);
+ if (rc < 0) {
+ unlock_page(page);
+ page_cache_release(page);
+ return (rc == -ENOMEM) ? VM_FAULT_OOM : VM_FAULT_SIGBUS;
+ }
+ SetPageUptodate(page);
+ }
+ unlock_page(page);
+ vmf->page = page;
+ return 0;
+#else
+ return VM_FAULT_SIGBUS;
+#endif
+}
+
+static const struct vm_operations_struct vmcore_mmap_ops = {
+ .fault = mmap_vmcore_fault,
+};
+
/**
* alloc_elfnotes_buf - allocate buffer for ELF note segment in
* vmalloc memory
@@ -223,7 +327,7 @@ static inline char *alloc_elfnotes_buf(size_t notes_sz)
* regions in the 1st kernel pointed to by PT_LOAD entries) into
* virtually contiguous user-space in ELF layout.
*/
-#if defined(CONFIG_MMU) && !defined(CONFIG_S390)
+#ifdef CONFIG_MMU
static int mmap_vmcore(struct file *file, struct vm_area_struct *vma)
{
size_t size = vma->vm_end - vma->vm_start;
@@ -241,6 +345,7 @@ static int mmap_vmcore(struct file *file, struct vm_area_struct *vma)
vma->vm_flags &= ~(VM_MAYWRITE | VM_MAYEXEC);
vma->vm_flags |= VM_MIXEDMAP;
+ vma->vm_ops = &vmcore_mmap_ops;
len = 0;
@@ -282,9 +387,9 @@ static int mmap_vmcore(struct file *file, struct vm_area_struct *vma)
tsz = min_t(size_t, m->offset + m->size - start, size);
paddr = m->paddr + start - m->offset;
- if (remap_pfn_range(vma, vma->vm_start + len,
- paddr >> PAGE_SHIFT, tsz,
- vma->vm_page_prot))
+ if (remap_oldmem_pfn_range(vma, vma->vm_start + len,
+ paddr >> PAGE_SHIFT, tsz,
+ vma->vm_page_prot))
goto fail;
size -= tsz;
start += tsz;
@@ -357,7 +462,7 @@ static int __init update_note_header_size_elf64(const Elf64_Ehdr *ehdr_ptr)
notes_section = kmalloc(max_sz, GFP_KERNEL);
if (!notes_section)
return -ENOMEM;
- rc = read_from_oldmem(notes_section, max_sz, &offset, 0);
+ rc = elfcorehdr_read_notes(notes_section, max_sz, &offset);
if (rc < 0) {
kfree(notes_section);
return rc;
@@ -444,7 +549,8 @@ static int __init copy_notes_elf64(const Elf64_Ehdr *ehdr_ptr, char *notes_buf)
if (phdr_ptr->p_type != PT_NOTE)
continue;
offset = phdr_ptr->p_offset;
- rc = read_from_oldmem(notes_buf, phdr_ptr->p_memsz, &offset, 0);
+ rc = elfcorehdr_read_notes(notes_buf, phdr_ptr->p_memsz,
+ &offset);
if (rc < 0)
return rc;
notes_buf += phdr_ptr->p_memsz;
@@ -536,7 +642,7 @@ static int __init update_note_header_size_elf32(const Elf32_Ehdr *ehdr_ptr)
notes_section = kmalloc(max_sz, GFP_KERNEL);
if (!notes_section)
return -ENOMEM;
- rc = read_from_oldmem(notes_section, max_sz, &offset, 0);
+ rc = elfcorehdr_read_notes(notes_section, max_sz, &offset);
if (rc < 0) {
kfree(notes_section);
return rc;
@@ -623,7 +729,8 @@ static int __init copy_notes_elf32(const Elf32_Ehdr *ehdr_ptr, char *notes_buf)
if (phdr_ptr->p_type != PT_NOTE)
continue;
offset = phdr_ptr->p_offset;
- rc = read_from_oldmem(notes_buf, phdr_ptr->p_memsz, &offset, 0);
+ rc = elfcorehdr_read_notes(notes_buf, phdr_ptr->p_memsz,
+ &offset);
if (rc < 0)
return rc;
notes_buf += phdr_ptr->p_memsz;
@@ -810,7 +917,7 @@ static int __init parse_crash_elf64_headers(void)
addr = elfcorehdr_addr;
/* Read Elf header */
- rc = read_from_oldmem((char*)&ehdr, sizeof(Elf64_Ehdr), &addr, 0);
+ rc = elfcorehdr_read((char *)&ehdr, sizeof(Elf64_Ehdr), &addr);
if (rc < 0)
return rc;
@@ -837,7 +944,7 @@ static int __init parse_crash_elf64_headers(void)
if (!elfcorebuf)
return -ENOMEM;
addr = elfcorehdr_addr;
- rc = read_from_oldmem(elfcorebuf, elfcorebuf_sz_orig, &addr, 0);
+ rc = elfcorehdr_read(elfcorebuf, elfcorebuf_sz_orig, &addr);
if (rc < 0)
goto fail;
@@ -866,7 +973,7 @@ static int __init parse_crash_elf32_headers(void)
addr = elfcorehdr_addr;
/* Read Elf header */
- rc = read_from_oldmem((char*)&ehdr, sizeof(Elf32_Ehdr), &addr, 0);
+ rc = elfcorehdr_read((char *)&ehdr, sizeof(Elf32_Ehdr), &addr);
if (rc < 0)
return rc;
@@ -892,7 +999,7 @@ static int __init parse_crash_elf32_headers(void)
if (!elfcorebuf)
return -ENOMEM;
addr = elfcorehdr_addr;
- rc = read_from_oldmem(elfcorebuf, elfcorebuf_sz_orig, &addr, 0);
+ rc = elfcorehdr_read(elfcorebuf, elfcorebuf_sz_orig, &addr);
if (rc < 0)
goto fail;
@@ -919,7 +1026,7 @@ static int __init parse_crash_elf_headers(void)
int rc=0;
addr = elfcorehdr_addr;
- rc = read_from_oldmem(e_ident, EI_NIDENT, &addr, 0);
+ rc = elfcorehdr_read(e_ident, EI_NIDENT, &addr);
if (rc < 0)
return rc;
if (memcmp(e_ident, ELFMAG, SELFMAG) != 0) {
@@ -952,7 +1059,14 @@ static int __init vmcore_init(void)
{
int rc = 0;
- /* If elfcorehdr= has been passed in cmdline, then capture the dump.*/
+ /* Allow architectures to allocate ELF header in 2nd kernel */
+ rc = elfcorehdr_alloc(&elfcorehdr_addr, &elfcorehdr_size);
+ if (rc)
+ return rc;
+ /*
+ * If elfcorehdr= has been passed in cmdline or created in 2nd kernel,
+ * then capture the dump.
+ */
if (!(is_vmcore_usable()))
return rc;
rc = parse_crash_elf_headers();
@@ -960,6 +1074,8 @@ static int __init vmcore_init(void)
pr_warn("Kdump: vmcore not initialized\n");
return rc;
}
+ elfcorehdr_free(elfcorehdr_addr);
+ elfcorehdr_addr = ELFCORE_ADDR_ERR;
proc_vmcore = proc_create("vmcore", S_IRUSR, NULL, &proc_vmcore_operations);
if (proc_vmcore)
generated by cgit v1.2.3 (git 2.25.1) at 2025-01-27 03:01:33 +0000