* 'hwpoison' of git://git.kernel.org/pub/scm/linux/kernel/git/ak/linux-mce-2.6: (21 commits)
HWPOISON: Enable error_remove_page on btrfs
HWPOISON: Add simple debugfs interface to inject hwpoison on arbitary PFNs
HWPOISON: Add madvise() based injector for hardware poisoned pages v4
HWPOISON: Enable error_remove_page for NFS
HWPOISON: Enable .remove_error_page for migration aware file systems
HWPOISON: The high level memory error handler in the VM v7
HWPOISON: Add PR_MCE_KILL prctl to control early kill behaviour per process
HWPOISON: shmem: call set_page_dirty() with locked page
HWPOISON: Define a new error_remove_page address space op for async truncation
HWPOISON: Add invalidate_inode_page
HWPOISON: Refactor truncate to allow direct truncating of page v2
HWPOISON: check and isolate corrupted free pages v2
HWPOISON: Handle hardware poisoned pages in try_to_unmap
HWPOISON: Use bitmask/action code for try_to_unmap behaviour
HWPOISON: x86: Add VM_FAULT_HWPOISON handling to x86 page fault handler v2
HWPOISON: Add poison check to page fault handling
HWPOISON: Add basic support for poisoned pages in fault handler v3
HWPOISON: Add new SIGBUS error codes for hardware poison signals
HWPOISON: Add support for poison swap entries v2
HWPOISON: Export some rmap vma locking to outside world
...
- legacy_va_layout
- lowmem_reserve_ratio
- max_map_count
+ - memory_failure_early_kill
+ - memory_failure_recovery
- min_free_kbytes
- min_slab_ratio
- min_unmapped_ratio
- vfs_cache_pressure
- zone_reclaim_mode
-
==============================================================
block_dump
The default value is 65536.
+ =============================================================
+
+ memory_failure_early_kill:
+
+ Control how to kill processes when uncorrected memory error (typically
+ a 2bit error in a memory module) is detected in the background by hardware
+ that cannot be handled by the kernel. In some cases (like the page
+ still having a valid copy on disk) the kernel will handle the failure
+ transparently without affecting any applications. But if there is
+ no other uptodate copy of the data it will kill to prevent any data
+ corruptions from propagating.
+
+ 1: Kill all processes that have the corrupted and not reloadable page mapped
+ as soon as the corruption is detected. Note this is not supported
+ for a few types of pages, like kernel internally allocated data or
+ the swap cache, but works for the majority of user pages.
+
+ 0: Only unmap the corrupted page from all processes and only kill a process
+ who tries to access it.
+
+ The kill is done using a catchable SIGBUS with BUS_MCEERR_AO, so processes can
+ handle this if they want to.
+
+ This is only active on architectures/platforms with advanced machine
+ check handling and depends on the hardware capabilities.
+
+ Applications can override this setting individually with the PR_MCE_KILL prctl
+
+ ==============================================================
+
+ memory_failure_recovery
+
+ Enable memory failure recovery (when supported by the platform)
+
+ 1: Attempt recovery.
+
+ 0: Always panic on a memory failure.
+
==============================================================
min_free_kbytes:
At the default value of vfs_cache_pressure=100 the kernel will attempt to
reclaim dentries and inodes at a "fair" rate with respect to pagecache and
swapcache reclaim. Decreasing vfs_cache_pressure causes the kernel to prefer
-to retain dentry and inode caches. Increasing vfs_cache_pressure beyond 100
+to retain dentry and inode caches. When vfs_cache_pressure=0, the kernel will
+never reclaim dentries and inodes due to memory pressure and this can easily
+lead to out-of-memory conditions. Increasing vfs_cache_pressure beyond 100
causes the kernel to prefer to reclaim dentries and inodes.
==============================================================
#include <linux/bootmem.h> /* max_low_pfn */
#include <linux/kprobes.h> /* __kprobes, ... */
#include <linux/mmiotrace.h> /* kmmio_handler, ... */
-#include <linux/perf_counter.h> /* perf_swcounter_event */
+#include <linux/perf_event.h> /* perf_sw_event */
#include <asm/traps.h> /* dotraplinkage, ... */
#include <asm/pgalloc.h> /* pgd_*(), ... */
info.si_errno = 0;
info.si_code = si_code;
info.si_addr = (void __user *)address;
+ info.si_addr_lsb = si_code == BUS_MCEERR_AR ? PAGE_SHIFT : 0;
force_sig_info(si_signo, &info, tsk);
}
}
static void
- do_sigbus(struct pt_regs *regs, unsigned long error_code, unsigned long address)
+ do_sigbus(struct pt_regs *regs, unsigned long error_code, unsigned long address,
+ unsigned int fault)
{
struct task_struct *tsk = current;
struct mm_struct *mm = tsk->mm;
+ int code = BUS_ADRERR;
up_read(&mm->mmap_sem);
tsk->thread.error_code = error_code;
tsk->thread.trap_no = 14;
- force_sig_info_fault(SIGBUS, BUS_ADRERR, address, tsk);
+ #ifdef CONFIG_MEMORY_FAILURE
+ if (fault & VM_FAULT_HWPOISON) {
+ printk(KERN_ERR
+ "MCE: Killing %s:%d due to hardware memory corruption fault at %lx\n",
+ tsk->comm, tsk->pid, address);
+ code = BUS_MCEERR_AR;
+ }
+ #endif
+ force_sig_info_fault(SIGBUS, code, address, tsk);
}
static noinline void
if (fault & VM_FAULT_OOM) {
out_of_memory(regs, error_code, address);
} else {
- if (fault & VM_FAULT_SIGBUS)
- do_sigbus(regs, error_code, address);
+ if (fault & (VM_FAULT_SIGBUS|VM_FAULT_HWPOISON))
+ do_sigbus(regs, error_code, address, fault);
else
BUG();
}
if (unlikely(error_code & PF_RSVD))
pgtable_bad(regs, error_code, address);
- perf_swcounter_event(PERF_COUNT_SW_PAGE_FAULTS, 1, 0, regs, address);
+ perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, 0, regs, address);
/*
* If we're in an interrupt, have no user context or are running
if (fault & VM_FAULT_MAJOR) {
tsk->maj_flt++;
- perf_swcounter_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, 0,
+ perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MAJ, 1, 0,
regs, address);
} else {
tsk->min_flt++;
- perf_swcounter_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, 0,
+ perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS_MIN, 1, 0,
regs, address);
}
struct btrfs_root *root;
};
-static struct inode_operations btrfs_dir_inode_operations;
-static struct inode_operations btrfs_symlink_inode_operations;
-static struct inode_operations btrfs_dir_ro_inode_operations;
-static struct inode_operations btrfs_special_inode_operations;
-static struct inode_operations btrfs_file_inode_operations;
-static struct address_space_operations btrfs_aops;
-static struct address_space_operations btrfs_symlink_aops;
+static const struct inode_operations btrfs_dir_inode_operations;
+static const struct inode_operations btrfs_symlink_inode_operations;
+static const struct inode_operations btrfs_dir_ro_inode_operations;
+static const struct inode_operations btrfs_special_inode_operations;
+static const struct inode_operations btrfs_file_inode_operations;
+static const struct address_space_operations btrfs_aops;
+static const struct address_space_operations btrfs_symlink_aops;
static struct file_operations btrfs_dir_file_operations;
static struct extent_io_ops btrfs_extent_io_ops;
return generic_permission(inode, mask, btrfs_check_acl);
}
-static struct inode_operations btrfs_dir_inode_operations = {
+static const struct inode_operations btrfs_dir_inode_operations = {
.getattr = btrfs_getattr,
.lookup = btrfs_lookup,
.create = btrfs_create,
.removexattr = btrfs_removexattr,
.permission = btrfs_permission,
};
-static struct inode_operations btrfs_dir_ro_inode_operations = {
+static const struct inode_operations btrfs_dir_ro_inode_operations = {
.lookup = btrfs_lookup,
.permission = btrfs_permission,
};
*
* For now we're avoiding this by dropping bmap.
*/
-static struct address_space_operations btrfs_aops = {
+static const struct address_space_operations btrfs_aops = {
.readpage = btrfs_readpage,
.writepage = btrfs_writepage,
.writepages = btrfs_writepages,
.invalidatepage = btrfs_invalidatepage,
.releasepage = btrfs_releasepage,
.set_page_dirty = btrfs_set_page_dirty,
+ .error_remove_page = generic_error_remove_page,
};
-static struct address_space_operations btrfs_symlink_aops = {
+static const struct address_space_operations btrfs_symlink_aops = {
.readpage = btrfs_readpage,
.writepage = btrfs_writepage,
.invalidatepage = btrfs_invalidatepage,
.releasepage = btrfs_releasepage,
};
-static struct inode_operations btrfs_file_inode_operations = {
+static const struct inode_operations btrfs_file_inode_operations = {
.truncate = btrfs_truncate,
.getattr = btrfs_getattr,
.setattr = btrfs_setattr,
.fallocate = btrfs_fallocate,
.fiemap = btrfs_fiemap,
};
-static struct inode_operations btrfs_special_inode_operations = {
+static const struct inode_operations btrfs_special_inode_operations = {
.getattr = btrfs_getattr,
.setattr = btrfs_setattr,
.permission = btrfs_permission,
.listxattr = btrfs_listxattr,
.removexattr = btrfs_removexattr,
};
-static struct inode_operations btrfs_symlink_inode_operations = {
+static const struct inode_operations btrfs_symlink_inode_operations = {
.readlink = generic_readlink,
.follow_link = page_follow_link_light,
.put_link = page_put_link,
* so before we call here everything must be consistently dirtied against
* this transaction.
*/
-static int ext3_journal_test_restart(handle_t *handle, struct inode *inode)
+static int truncate_restart_transaction(handle_t *handle, struct inode *inode)
{
+ int ret;
+
jbd_debug(2, "restarting handle %p\n", handle);
- return ext3_journal_restart(handle, blocks_for_truncate(inode));
+ /*
+ * Drop truncate_mutex to avoid deadlock with ext3_get_blocks_handle
+ * At this moment, get_block can be called only for blocks inside
+ * i_size since page cache has been already dropped and writes are
+ * blocked by i_mutex. So we can safely drop the truncate_mutex.
+ */
+ mutex_unlock(&EXT3_I(inode)->truncate_mutex);
+ ret = ext3_journal_restart(handle, blocks_for_truncate(inode));
+ mutex_lock(&EXT3_I(inode)->truncate_mutex);
+ return ret;
}
/*
.direct_IO = ext3_direct_IO,
.migratepage = buffer_migrate_page,
.is_partially_uptodate = block_is_partially_uptodate,
+ .error_remove_page = generic_error_remove_page,
};
static const struct address_space_operations ext3_writeback_aops = {
.direct_IO = ext3_direct_IO,
.migratepage = buffer_migrate_page,
.is_partially_uptodate = block_is_partially_uptodate,
+ .error_remove_page = generic_error_remove_page,
};
static const struct address_space_operations ext3_journalled_aops = {
.invalidatepage = ext3_invalidatepage,
.releasepage = ext3_releasepage,
.is_partially_uptodate = block_is_partially_uptodate,
+ .error_remove_page = generic_error_remove_page,
};
void ext3_set_aops(struct inode *inode)
ext3_journal_dirty_metadata(handle, bh);
}
ext3_mark_inode_dirty(handle, inode);
- ext3_journal_test_restart(handle, inode);
+ truncate_restart_transaction(handle, inode);
if (bh) {
BUFFER_TRACE(bh, "retaking write access");
ext3_journal_get_write_access(handle, bh);
return;
if (try_to_extend_transaction(handle, inode)) {
ext3_mark_inode_dirty(handle, inode);
- ext3_journal_test_restart(handle, inode);
+ truncate_restart_transaction(handle, inode);
}
ext3_free_blocks(handle, inode, nr, 1);
struct buffer_head *bh = iloc->bh;
int err = 0, rc, block;
+again:
+ /* we can't allow multiple procs in here at once, its a bit racey */
+ lock_buffer(bh);
+
/* For fields not not tracking in the in-memory inode,
* initialise them to zero for new inodes. */
if (ei->i_state & EXT3_STATE_NEW)
/* If this is the first large file
* created, add a flag to the superblock.
*/
+ unlock_buffer(bh);
err = ext3_journal_get_write_access(handle,
EXT3_SB(sb)->s_sbh);
if (err)
goto out_brelse;
+
ext3_update_dynamic_rev(sb);
EXT3_SET_RO_COMPAT_FEATURE(sb,
EXT3_FEATURE_RO_COMPAT_LARGE_FILE);
handle->h_sync = 1;
err = ext3_journal_dirty_metadata(handle,
EXT3_SB(sb)->s_sbh);
+ /* get our lock and start over */
+ goto again;
}
}
}
raw_inode->i_extra_isize = cpu_to_le16(ei->i_extra_isize);
BUFFER_TRACE(bh, "call ext3_journal_dirty_metadata");
+ unlock_buffer(bh);
rc = ext3_journal_dirty_metadata(handle, bh);
if (!err)
err = rc;
* so before we call here everything must be consistently dirtied against
* this transaction.
*/
-static int ext4_journal_test_restart(handle_t *handle, struct inode *inode)
+ int ext4_truncate_restart_trans(handle_t *handle, struct inode *inode,
+ int nblocks)
{
+ int ret;
+
+ /*
+ * Drop i_data_sem to avoid deadlock with ext4_get_blocks At this
+ * moment, get_block can be called only for blocks inside i_size since
+ * page cache has been already dropped and writes are blocked by
+ * i_mutex. So we can safely drop the i_data_sem here.
+ */
BUG_ON(EXT4_JOURNAL(inode) == NULL);
jbd_debug(2, "restarting handle %p\n", handle);
- return ext4_journal_restart(handle, blocks_for_truncate(inode));
+ up_write(&EXT4_I(inode)->i_data_sem);
+ ret = ext4_journal_restart(handle, blocks_for_truncate(inode));
+ down_write(&EXT4_I(inode)->i_data_sem);
+
+ return ret;
}
/*
int n = 0;
int final = 0;
- if (i_block < 0) {
- ext4_warning(inode->i_sb, "ext4_block_to_path", "block < 0");
- } else if (i_block < direct_blocks) {
+ if (i_block < direct_blocks) {
offsets[n++] = i_block;
final = direct_blocks;
} else if ((i_block -= direct_blocks) < indirect_blocks) {
*
* Normally this function find the preferred place for block allocation,
* returns it.
+ * Because this is only used for non-extent files, we limit the block nr
+ * to 32 bits.
*/
static ext4_fsblk_t ext4_find_goal(struct inode *inode, ext4_lblk_t block,
Indirect *partial)
{
+ ext4_fsblk_t goal;
+
/*
* XXX need to get goal block from mballoc's data structures
*/
- return ext4_find_near(inode, partial);
+ goal = ext4_find_near(inode, partial);
+ goal = goal & EXT4_MAX_BLOCK_FILE_PHYS;
+ return goal;
}
/**
if (*err)
goto failed_out;
+ BUG_ON(current_block + count > EXT4_MAX_BLOCK_FILE_PHYS);
+
target -= count;
/* allocate blocks for indirect blocks */
while (index < indirect_blks && count) {
ar.flags = EXT4_MB_HINT_DATA;
current_block = ext4_mb_new_blocks(handle, &ar, err);
+ BUG_ON(current_block + ar.len > EXT4_MAX_BLOCK_FILE_PHYS);
if (*err && (target == blks)) {
/*
BUFFER_TRACE(bh, "call get_create_access");
err = ext4_journal_get_create_access(handle, bh);
if (err) {
+ /* Don't brelse(bh) here; it's done in
+ * ext4_journal_forget() below */
unlock_buffer(bh);
- brelse(bh);
goto failed;
}
ext4_discard_preallocations(inode);
}
-static int check_block_validity(struct inode *inode, sector_t logical,
- sector_t phys, int len)
+static int check_block_validity(struct inode *inode, const char *msg,
+ sector_t logical, sector_t phys, int len)
{
if (!ext4_data_block_valid(EXT4_SB(inode->i_sb), phys, len)) {
- ext4_error(inode->i_sb, "check_block_validity",
+ ext4_error(inode->i_sb, msg,
"inode #%lu logical block %llu mapped to %llu "
"(size %d)", inode->i_ino,
(unsigned long long) logical,
(unsigned long long) phys, len);
- WARN_ON(1);
return -EIO;
}
return 0;
up_read((&EXT4_I(inode)->i_data_sem));
if (retval > 0 && buffer_mapped(bh)) {
- int ret = check_block_validity(inode, block,
- bh->b_blocknr, retval);
+ int ret = check_block_validity(inode, "file system corruption",
+ block, bh->b_blocknr, retval);
if (ret != 0)
return ret;
}
* i_data's format changing. Force the migrate
* to fail by clearing migrate flags
*/
- EXT4_I(inode)->i_flags = EXT4_I(inode)->i_flags &
- ~EXT4_EXT_MIGRATE;
+ EXT4_I(inode)->i_state &= ~EXT4_STATE_EXT_MIGRATE;
}
}
up_write((&EXT4_I(inode)->i_data_sem));
if (retval > 0 && buffer_mapped(bh)) {
- int ret = check_block_validity(inode, block,
- bh->b_blocknr, retval);
+ int ret = check_block_validity(inode, "file system "
+ "corruption after allocation",
+ block, bh->b_blocknr, retval);
if (ret != 0)
return ret;
}
* Delayed allocation stuff
*/
-struct mpage_da_data {
- struct inode *inode;
- sector_t b_blocknr; /* start block number of extent */
- size_t b_size; /* size of extent */
- unsigned long b_state; /* state of the extent */
- unsigned long first_page, next_page; /* extent of pages */
- struct writeback_control *wbc;
- int io_done;
- int pages_written;
- int retval;
-};
-
/*
* mpage_da_submit_io - walks through extent of pages and try to write
* them with writepage() call back
/*
* Rest of the page in the page_vec
* redirty then and skip then. We will
- * try to to write them again after
+ * try to write them again after
* starting a new transaction
*/
redirty_page_for_writepage(wbc, page);
long pages_skipped;
int range_cyclic, cycled = 1, io_done = 0;
int needed_blocks, ret = 0, nr_to_writebump = 0;
+ loff_t range_start = wbc->range_start;
struct ext4_sb_info *sbi = EXT4_SB(mapping->host->i_sb);
trace_ext4_da_writepages(inode, wbc);
mpd.io_done = 1;
ret = MPAGE_DA_EXTENT_TAIL;
}
+ trace_ext4_da_write_pages(inode, &mpd);
wbc->nr_to_write -= mpd.pages_written;
ext4_journal_stop(handle);
if (!no_nrwrite_index_update)
wbc->no_nrwrite_index_update = 0;
wbc->nr_to_write -= nr_to_writebump;
+ wbc->range_start = range_start;
trace_ext4_da_writepages_result(inode, wbc, ret, pages_written);
return ret;
}
*/
int ext4_alloc_da_blocks(struct inode *inode)
{
+ trace_ext4_alloc_da_blocks(inode);
+
if (!EXT4_I(inode)->i_reserved_data_blocks &&
!EXT4_I(inode)->i_reserved_meta_blocks)
return 0;
.direct_IO = ext4_direct_IO,
.migratepage = buffer_migrate_page,
.is_partially_uptodate = block_is_partially_uptodate,
+ .error_remove_page = generic_error_remove_page,
};
static const struct address_space_operations ext4_writeback_aops = {
.direct_IO = ext4_direct_IO,
.migratepage = buffer_migrate_page,
.is_partially_uptodate = block_is_partially_uptodate,
+ .error_remove_page = generic_error_remove_page,
};
static const struct address_space_operations ext4_journalled_aops = {
.invalidatepage = ext4_invalidatepage,
.releasepage = ext4_releasepage,
.is_partially_uptodate = block_is_partially_uptodate,
+ .error_remove_page = generic_error_remove_page,
};
static const struct address_space_operations ext4_da_aops = {
.direct_IO = ext4_direct_IO,
.migratepage = buffer_migrate_page,
.is_partially_uptodate = block_is_partially_uptodate,
+ .error_remove_page = generic_error_remove_page,
};
void ext4_set_aops(struct inode *inode)
ext4_handle_dirty_metadata(handle, inode, bh);
}
ext4_mark_inode_dirty(handle, inode);
- ext4_journal_test_restart(handle, inode);
+ ext4_truncate_restart_trans(handle, inode,
+ blocks_for_truncate(inode));
if (bh) {
BUFFER_TRACE(bh, "retaking write access");
ext4_journal_get_write_access(handle, bh);
return;
if (try_to_extend_transaction(handle, inode)) {
ext4_mark_inode_dirty(handle, inode);
- ext4_journal_test_restart(handle, inode);
+ ext4_truncate_restart_trans(handle, inode,
+ blocks_for_truncate(inode));
}
ext4_free_blocks(handle, inode, nr, 1, 1);
if (!ext4_can_truncate(inode))
return;
- if (ei->i_disksize && inode->i_size == 0 &&
- !test_opt(inode->i_sb, NO_AUTO_DA_ALLOC))
+ if (inode->i_size == 0 && !test_opt(inode->i_sb, NO_AUTO_DA_ALLOC))
ei->i_state |= EXT4_STATE_DA_ALLOC_CLOSE;
if (EXT4_I(inode)->i_flags & EXT4_EXTENTS_FL) {
*/
static int ext4_do_update_inode(handle_t *handle,
struct inode *inode,
- struct ext4_iloc *iloc)
+ struct ext4_iloc *iloc,
+ int do_sync)
{
struct ext4_inode *raw_inode = ext4_raw_inode(iloc);
struct ext4_inode_info *ei = EXT4_I(inode);
if (ext4_inode_blocks_set(handle, raw_inode, ei))
goto out_brelse;
raw_inode->i_dtime = cpu_to_le32(ei->i_dtime);
- /* clear the migrate flag in the raw_inode */
- raw_inode->i_flags = cpu_to_le32(ei->i_flags & ~EXT4_EXT_MIGRATE);
+ raw_inode->i_flags = cpu_to_le32(ei->i_flags);
if (EXT4_SB(inode->i_sb)->s_es->s_creator_os !=
cpu_to_le32(EXT4_OS_HURD))
raw_inode->i_file_acl_high =
raw_inode->i_extra_isize = cpu_to_le16(ei->i_extra_isize);
}
- BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata");
- rc = ext4_handle_dirty_metadata(handle, inode, bh);
- if (!err)
- err = rc;
+ /*
+ * If we're not using a journal and we were called from
+ * ext4_write_inode() to sync the inode (making do_sync true),
+ * we can just use sync_dirty_buffer() directly to do our dirty
+ * work. Testing s_journal here is a bit redundant but it's
+ * worth it to avoid potential future trouble.
+ */
+ if (EXT4_SB(inode->i_sb)->s_journal == NULL && do_sync) {
+ BUFFER_TRACE(bh, "call sync_dirty_buffer");
+ sync_dirty_buffer(bh);
+ } else {
+ BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata");
+ rc = ext4_handle_dirty_metadata(handle, inode, bh);
+ if (!err)
+ err = rc;
+ }
ei->i_state &= ~EXT4_STATE_NEW;
out_brelse:
*/
int ext4_write_inode(struct inode *inode, int wait)
{
+ int err;
+
if (current->flags & PF_MEMALLOC)
return 0;
- if (ext4_journal_current_handle()) {
- jbd_debug(1, "called recursively, non-PF_MEMALLOC!\n");
- dump_stack();
- return -EIO;
- }
+ if (EXT4_SB(inode->i_sb)->s_journal) {
+ if (ext4_journal_current_handle()) {
+ jbd_debug(1, "called recursively, non-PF_MEMALLOC!\n");
+ dump_stack();
+ return -EIO;
+ }
- if (!wait)
- return 0;
+ if (!wait)
+ return 0;
+
+ err = ext4_force_commit(inode->i_sb);
+ } else {
+ struct ext4_iloc iloc;
- return ext4_force_commit(inode->i_sb);
+ err = ext4_get_inode_loc(inode, &iloc);
+ if (err)
+ return err;
+ err = ext4_do_update_inode(EXT4_NOJOURNAL_HANDLE,
+ inode, &iloc, wait);
+ }
+ return err;
}
/*
get_bh(iloc->bh);
/* ext4_do_update_inode() does jbd2_journal_dirty_metadata */
- err = ext4_do_update_inode(handle, inode, iloc);
+ err = ext4_do_update_inode(handle, inode, iloc, 0);
put_bh(iloc->bh);
return err;
}
else
len = PAGE_CACHE_SIZE;
+ lock_page(page);
+ /*
+ * return if we have all the buffers mapped. This avoid
+ * the need to call write_begin/write_end which does a
+ * journal_start/journal_stop which can block and take
+ * long time
+ */
if (page_has_buffers(page)) {
- /* return if we have all the buffers mapped */
if (!walk_page_buffers(NULL, page_buffers(page), 0, len, NULL,
- ext4_bh_unmapped))
+ ext4_bh_unmapped)) {
+ unlock_page(page);
goto out_unlock;
+ }
}
+ unlock_page(page);
/*
* OK, we need to fill the hole... Do write_begin write_end
* to do block allocation/reservation.We are not holding
#include "suballoc.h"
#include "super.h"
#include "symlink.h"
+#include "refcounttree.h"
#include "buffer_head_io.h"
return err;
}
-static int ocfs2_get_block(struct inode *inode, sector_t iblock,
- struct buffer_head *bh_result, int create)
+int ocfs2_get_block(struct inode *inode, sector_t iblock,
+ struct buffer_head *bh_result, int create)
{
int err = 0;
unsigned int ext_flags;
goto bail;
}
+ /* We should already CoW the refcounted extent. */
+ BUG_ON(ext_flags & OCFS2_EXT_REFCOUNTED);
/*
* get_more_blocks() expects us to describe a hole by clearing
* the mapped bit on bh_result().
if (OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL)
return 0;
+ /* Fallback to buffered I/O if we are appending. */
+ if (i_size_read(inode) <= offset)
+ return 0;
+
ret = blockdev_direct_IO_no_locking(rw, iocb, inode,
inode->i_sb->s_bdev, iov, offset,
nr_segs,
goto out;
}
} else if (unwritten) {
- ocfs2_init_dinode_extent_tree(&et, inode, wc->w_di_bh);
+ ocfs2_init_dinode_extent_tree(&et, INODE_CACHE(inode),
+ wc->w_di_bh);
ret = ocfs2_mark_extent_written(inode, &et,
wc->w_handle, cpos, 1, phys,
meta_ac, &wc->w_dealloc);
goto out;
}
+ /* We should already CoW the refcountd extent. */
+ BUG_ON(ext_flags & OCFS2_EXT_REFCOUNTED);
+
/*
* Assume worst case - that we're writing in
* the middle of the extent.
goto out;
}
- ret = ocfs2_journal_access_di(handle, inode, wc->w_di_bh,
+ ret = ocfs2_journal_access_di(handle, INODE_CACHE(inode), wc->w_di_bh,
OCFS2_JOURNAL_ACCESS_WRITE);
if (ret) {
ocfs2_commit_trans(osb, handle);
goto out;
}
+ ret = ocfs2_check_range_for_refcount(inode, pos, len);
+ if (ret < 0) {
+ mlog_errno(ret);
+ goto out;
+ } else if (ret == 1) {
+ ret = ocfs2_refcount_cow(inode, di_bh,
+ wc->w_cpos, wc->w_clen, UINT_MAX);
+ if (ret) {
+ mlog_errno(ret);
+ goto out;
+ }
+ }
+
ret = ocfs2_populate_write_desc(inode, wc, &clusters_to_alloc,
&extents_to_split);
if (ret) {
(long long)i_size_read(inode), le32_to_cpu(di->i_clusters),
clusters_to_alloc, extents_to_split);
- ocfs2_init_dinode_extent_tree(&et, inode, wc->w_di_bh);
+ ocfs2_init_dinode_extent_tree(&et, INODE_CACHE(inode),
+ wc->w_di_bh);
ret = ocfs2_lock_allocators(inode, &et,
clusters_to_alloc, extents_to_split,
&data_ac, &meta_ac);
* We don't want this to fail in ocfs2_write_end(), so do it
* here.
*/
- ret = ocfs2_journal_access_di(handle, inode, wc->w_di_bh,
+ ret = ocfs2_journal_access_di(handle, INODE_CACHE(inode), wc->w_di_bh,
OCFS2_JOURNAL_ACCESS_WRITE);
if (ret) {
mlog_errno(ret);
.releasepage = ocfs2_releasepage,
.migratepage = buffer_migrate_page,
.is_partially_uptodate = block_is_partially_uptodate,
+ .error_remove_page = generic_error_remove_page,
};
"Writeback: %8lu kB\n"
"AnonPages: %8lu kB\n"
"Mapped: %8lu kB\n"
+ "Shmem: %8lu kB\n"
"Slab: %8lu kB\n"
"SReclaimable: %8lu kB\n"
"SUnreclaim: %8lu kB\n"
+ "KernelStack: %8lu kB\n"
"PageTables: %8lu kB\n"
#ifdef CONFIG_QUICKLIST
"Quicklists: %8lu kB\n"
"Committed_AS: %8lu kB\n"
"VmallocTotal: %8lu kB\n"
"VmallocUsed: %8lu kB\n"
- "VmallocChunk: %8lu kB\n",
+ "VmallocChunk: %8lu kB\n"
+ #ifdef CONFIG_MEMORY_FAILURE
+ "HardwareCorrupted: %8lu kB\n"
+ #endif
+ ,
K(i.totalram),
K(i.freeram),
K(i.bufferram),
K(global_page_state(NR_WRITEBACK)),
K(global_page_state(NR_ANON_PAGES)),
K(global_page_state(NR_FILE_MAPPED)),
+ K(global_page_state(NR_SHMEM)),
K(global_page_state(NR_SLAB_RECLAIMABLE) +
global_page_state(NR_SLAB_UNRECLAIMABLE)),
K(global_page_state(NR_SLAB_RECLAIMABLE)),
K(global_page_state(NR_SLAB_UNRECLAIMABLE)),
+ global_page_state(NR_KERNEL_STACK) * THREAD_SIZE / 1024,
K(global_page_state(NR_PAGETABLE)),
#ifdef CONFIG_QUICKLIST
K(quicklist_total_size()),
(unsigned long)VMALLOC_TOTAL >> 10,
vmi.used >> 10,
vmi.largest_chunk >> 10
+ #ifdef CONFIG_MEMORY_FAILURE
+ ,atomic_long_read(&mce_bad_pages) << (PAGE_SHIFT - 10)
+ #endif
);
hugetlb_report_meminfo(m);
if (ip->i_d.di_size < isize) {
ip->i_d.di_size = isize;
ip->i_update_core = 1;
- ip->i_update_size = 1;
xfs_mark_inode_dirty_sync(ip);
}
.direct_IO = xfs_vm_direct_IO,
.migratepage = buffer_migrate_page,
.is_partially_uptodate = block_is_partially_uptodate,
+ .error_remove_page = generic_error_remove_page,
};
#define MADV_REMOVE 9 /* remove these pages & resources */
#define MADV_DONTFORK 10 /* don't inherit across fork */
#define MADV_DOFORK 11 /* do inherit across fork */
+ #define MADV_HWPOISON 100 /* poison a page for testing */
+#define MADV_MERGEABLE 12 /* KSM may merge identical pages */
+#define MADV_UNMERGEABLE 13 /* KSM may not merge identical pages */
+
/* compatibility flags */
#define MAP_FILE 0
int (*launder_page) (struct page *);
int (*is_partially_uptodate) (struct page *, read_descriptor_t *,
unsigned long);
+ int (*error_remove_page)(struct address_space *, struct page *);
};
/*
int bd_invalidated;
struct gendisk * bd_disk;
struct list_head bd_list;
- struct backing_dev_info *bd_inode_backing_dev_info;
/*
* Private data. You must have bd_claim'ed the block_device
* to use this. NOTE: bd_claim allows an owner to claim
struct fasync_struct * fl_fasync; /* for lease break notifications */
unsigned long fl_break_time; /* for nonblocking lease breaks */
- struct file_lock_operations *fl_ops; /* Callbacks for filesystems */
- struct lock_manager_operations *fl_lmops; /* Callbacks for lockmanagers */
+ const struct file_lock_operations *fl_ops; /* Callbacks for filesystems */
+ const struct lock_manager_operations *fl_lmops; /* Callbacks for lockmanagers */
union {
struct nfs_lock_info nfs_fl;
struct nfs4_lock_info nfs4_fl;
unsigned long long s_maxbytes; /* Max file size */
struct file_system_type *s_type;
const struct super_operations *s_op;
- struct dquot_operations *dq_op;
- struct quotactl_ops *s_qcop;
+ const struct dquot_operations *dq_op;
+ const struct quotactl_ops *s_qcop;
const struct export_operations *s_export_op;
unsigned long s_flags;
unsigned long s_magic;
int s_nr_dentry_unused; /* # of dentry on lru */
struct block_device *s_bdev;
+ struct backing_dev_info *s_bdi;
struct mtd_info *s_mtd;
struct list_head s_instances;
struct quota_info s_dquot; /* Diskquota specific options */
size_t len, loff_t *ppos);
struct ctl_table;
-int proc_nr_files(struct ctl_table *table, int write, struct file *filp,
+int proc_nr_files(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos);
int __init get_filesystem_list(char *buf);
#endif
extern unsigned long num_physpages;
+extern unsigned long totalram_pages;
extern void * high_memory;
extern int page_cluster;
#define VM_MIXEDMAP 0x10000000 /* Can contain "struct page" and pure PFN pages */
#define VM_SAO 0x20000000 /* Strong Access Ordering (powerpc) */
#define VM_PFN_AT_MMAP 0x40000000 /* PFNMAP vma that is fully mapped at mmap time */
+#define VM_MERGEABLE 0x80000000 /* KSM may merge identical pages */
#ifndef VM_STACK_DEFAULT_FLAGS /* arch can override this */
#define VM_STACK_DEFAULT_FLAGS VM_DATA_DEFAULT_FLAGS
return 0;
#endif
}
+#ifdef CONFIG_MMU
+extern int is_vmalloc_or_module_addr(const void *x);
+#else
+static int is_vmalloc_or_module_addr(const void *x)
+{
+ return 0;
+}
+#endif
static inline struct page *compound_head(struct page *page)
{
#define VM_FAULT_SIGBUS 0x0002
#define VM_FAULT_MAJOR 0x0004
#define VM_FAULT_WRITE 0x0008 /* Special case for get_user_pages */
+ #define VM_FAULT_HWPOISON 0x0010 /* Hit poisoned page */
#define VM_FAULT_NOPAGE 0x0100 /* ->fault installed the pte, not return page */
#define VM_FAULT_LOCKED 0x0200 /* ->fault locked the returned page */
- #define VM_FAULT_ERROR (VM_FAULT_OOM | VM_FAULT_SIGBUS)
+ #define VM_FAULT_ERROR (VM_FAULT_OOM | VM_FAULT_SIGBUS | VM_FAULT_HWPOISON)
/*
* Can be called by the pagefault handler when it gets a VM_FAULT_OOM.
extern void show_free_areas(void);
-#ifdef CONFIG_SHMEM
-extern int shmem_lock(struct file *file, int lock, struct user_struct *user);
-#else
-static inline int shmem_lock(struct file *file, int lock,
- struct user_struct *user)
-{
- return 0;
-}
-#endif
+int shmem_lock(struct file *file, int lock, struct user_struct *user);
struct file *shmem_file_setup(const char *name, loff_t size, unsigned long flags);
-
int shmem_zero_setup(struct vm_area_struct *);
#ifndef CONFIG_MMU
extern int vmtruncate(struct inode * inode, loff_t offset);
extern int vmtruncate_range(struct inode * inode, loff_t offset, loff_t end);
+ int truncate_inode_page(struct address_space *mapping, struct page *page);
+ int generic_error_remove_page(struct address_space *mapping, struct page *page);
+
+ int invalidate_inode_page(struct page *page);
+
#ifdef CONFIG_MMU
extern int handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma,
unsigned long address, unsigned int flags);
struct page **pages, struct vm_area_struct **vmas);
int get_user_pages_fast(unsigned long start, int nr_pages, int write,
struct page **pages);
+struct page *get_dump_page(unsigned long addr);
extern int try_to_release_page(struct page * page, gfp_t gfp_mask);
extern void do_invalidatepage(struct page *page, unsigned long offset);
static inline void setup_per_cpu_pageset(void) {}
#endif
+extern void zone_pcp_update(struct zone *zone);
+
/* nommu.c */
extern atomic_long_t mmap_pages_allocated;
#define FOLL_WRITE 0x01 /* check pte is writable */
#define FOLL_TOUCH 0x02 /* mark page accessed */
#define FOLL_GET 0x04 /* do get_page on page */
-#define FOLL_ANON 0x08 /* give ZERO_PAGE if no pgtable */
+#define FOLL_DUMP 0x08 /* give error on hole if it would be zero */
+#define FOLL_FORCE 0x10 /* get_user_pages read/write w/o permission */
typedef int (*pte_fn_t)(pte_t *pte, pgtable_t token, unsigned long addr,
void *data);
#define in_gate_area(task, addr) ({(void)task; in_gate_area_no_task(addr);})
#endif /* __HAVE_ARCH_GATE_AREA */
-int drop_caches_sysctl_handler(struct ctl_table *, int, struct file *,
+int drop_caches_sysctl_handler(struct ctl_table *, int,
void __user *, size_t *, loff_t *);
unsigned long shrink_slab(unsigned long scanned, gfp_t gfp_mask,
unsigned long lru_pages);
extern int account_locked_memory(struct mm_struct *mm, struct rlimit *rlim,
size_t size);
extern void refund_locked_memory(struct mm_struct *mm, size_t size);
+
+ extern void memory_failure(unsigned long pfn, int trapno);
+ extern int __memory_failure(unsigned long pfn, int trapno, int ref);
+ extern int sysctl_memory_failure_early_kill;
+ extern int sysctl_memory_failure_recovery;
+ extern atomic_long_t mce_bad_pages;
+
#endif /* __KERNEL__ */
#endif /* _LINUX_MM_H */
* PG_buddy is set to indicate that the page is free and in the buddy system
* (see mm/page_alloc.c).
*
+ * PG_hwpoison indicates that a page got corrupted in hardware and contains
+ * data with incorrect ECC bits that triggered a machine check. Accessing is
+ * not safe since it may cause another machine check. Don't touch!
*/
/*
#endif
#ifdef CONFIG_ARCH_USES_PG_UNCACHED
PG_uncached, /* Page has been mapped as uncached */
+ #endif
+ #ifdef CONFIG_MEMORY_FAILURE
+ PG_hwpoison, /* hardware poisoned page. Don't touch */
#endif
__NR_PAGEFLAGS,
static inline int TestClearPage##uname(struct page *page) \
{ return test_and_clear_bit(PG_##lname, &page->flags); }
+#define __TESTCLEARFLAG(uname, lname) \
+static inline int __TestClearPage##uname(struct page *page) \
+ { return __test_and_clear_bit(PG_##lname, &page->flags); }
#define PAGEFLAG(uname, lname) TESTPAGEFLAG(uname, lname) \
SETPAGEFLAG(uname, lname) CLEARPAGEFLAG(uname, lname)
#define TESTCLEARFLAG_FALSE(uname) \
static inline int TestClearPage##uname(struct page *page) { return 0; }
+#define __TESTCLEARFLAG_FALSE(uname) \
+static inline int __TestClearPage##uname(struct page *page) { return 0; }
+
struct page; /* forward declaration */
TESTPAGEFLAG(Locked, locked) TESTSETFLAG(Locked, locked)
#ifdef CONFIG_HAVE_MLOCKED_PAGE_BIT
#define MLOCK_PAGES 1
PAGEFLAG(Mlocked, mlocked) __CLEARPAGEFLAG(Mlocked, mlocked)
- TESTSCFLAG(Mlocked, mlocked)
+ TESTSCFLAG(Mlocked, mlocked) __TESTCLEARFLAG(Mlocked, mlocked)
#else
#define MLOCK_PAGES 0
-PAGEFLAG_FALSE(Mlocked)
- SETPAGEFLAG_NOOP(Mlocked) TESTCLEARFLAG_FALSE(Mlocked)
+PAGEFLAG_FALSE(Mlocked) SETPAGEFLAG_NOOP(Mlocked)
+ TESTCLEARFLAG_FALSE(Mlocked) __TESTCLEARFLAG_FALSE(Mlocked)
#endif
#ifdef CONFIG_ARCH_USES_PG_UNCACHED
PAGEFLAG_FALSE(Uncached)
#endif
+ #ifdef CONFIG_MEMORY_FAILURE
+ PAGEFLAG(HWPoison, hwpoison)
+ TESTSETFLAG(HWPoison, hwpoison)
+ #define __PG_HWPOISON (1UL << PG_hwpoison)
+ #else
+ PAGEFLAG_FALSE(HWPoison)
+ #define __PG_HWPOISON 0
+ #endif
+
static inline int PageUptodate(struct page *page)
{
int ret = test_bit(PG_uptodate, &(page)->flags);
1 << PG_private | 1 << PG_private_2 | \
1 << PG_buddy | 1 << PG_writeback | 1 << PG_reserved | \
1 << PG_slab | 1 << PG_swapcache | 1 << PG_active | \
- 1 << PG_unevictable | __PG_MLOCKED)
+ 1 << PG_unevictable | __PG_MLOCKED | __PG_HWPOISON)
/*
* Flags checked when a page is prepped for return by the page allocator.
*/
#define PAGE_FLAGS_CHECK_AT_PREP ((1 << NR_PAGEFLAGS) - 1)
-#endif /* !__GENERATING_BOUNDS_H */
-
+#define PAGE_FLAGS_PRIVATE \
+ (1 << PG_private | 1 << PG_private_2)
/**
* page_has_private - Determine if page has private stuff
* @page: The page to be checked
* Determine if a page has private stuff, indicating that release routines
* should be invoked upon it.
*/
-#define page_has_private(page) \
- ((page)->flags & ((1 << PG_private) | \
- (1 << PG_private_2)))
+static inline int page_has_private(struct page *page)
+{
+ return !!(page->flags & PAGE_FLAGS_PRIVATE);
+}
+
+#endif /* !__GENERATING_BOUNDS_H */
#endif /* PAGE_FLAGS_H */
#define PR_SET_TIMERSLACK 29
#define PR_GET_TIMERSLACK 30
-#define PR_TASK_PERF_COUNTERS_DISABLE 31
-#define PR_TASK_PERF_COUNTERS_ENABLE 32
+#define PR_TASK_PERF_EVENTS_DISABLE 31
+#define PR_TASK_PERF_EVENTS_ENABLE 32
+ #define PR_MCE_KILL 33
+
#endif /* _LINUX_PRCTL_H */
void page_add_file_rmap(struct page *);
void page_remove_rmap(struct page *);
-#ifdef CONFIG_DEBUG_VM
-void page_dup_rmap(struct page *page, struct vm_area_struct *vma, unsigned long address);
-#else
-static inline void page_dup_rmap(struct page *page, struct vm_area_struct *vma, unsigned long address)
+static inline void page_dup_rmap(struct page *page)
{
atomic_inc(&page->_mapcount);
}
-#endif
/*
* Called from mm/vmscan.c to handle paging out
*/
int page_referenced(struct page *, int is_locked,
struct mem_cgroup *cnt, unsigned long *vm_flags);
- int try_to_unmap(struct page *, int ignore_refs);
+ enum ttu_flags {
+ TTU_UNMAP = 0, /* unmap mode */
+ TTU_MIGRATION = 1, /* migration mode */
+ TTU_MUNLOCK = 2, /* munlock mode */
+ TTU_ACTION_MASK = 0xff,
+
+ TTU_IGNORE_MLOCK = (1 << 8), /* ignore mlock */
+ TTU_IGNORE_ACCESS = (1 << 9), /* don't age */
+ TTU_IGNORE_HWPOISON = (1 << 10),/* corrupted page is recoverable */
+ };
+ #define TTU_ACTION(x) ((x) & TTU_ACTION_MASK)
+
+ int try_to_unmap(struct page *, enum ttu_flags flags);
/*
* Called from mm/filemap_xip.c to unmap empty zero page
*/
int try_to_munlock(struct page *);
+ /*
+ * Called by memory-failure.c to kill processes.
+ */
+ struct anon_vma *page_lock_anon_vma(struct page *page);
+ void page_unlock_anon_vma(struct anon_vma *anon_vma);
+ int page_mapped_in_vma(struct page *page, struct vm_area_struct *vma);
+
#else /* !CONFIG_MMU */
#define anon_vma_init() do {} while (0)
struct bio;
struct fs_struct;
struct bts_context;
-struct perf_counter_context;
+struct perf_event_context;
/*
* List of flags we want to share for kernel threads,
extern unsigned long nr_running(void);
extern unsigned long nr_uninterruptible(void);
extern unsigned long nr_iowait(void);
+extern unsigned long nr_iowait_cpu(void);
+extern unsigned long this_cpu_load(void);
+
+
extern void calc_global_load(void);
extern u64 cpu_nr_migrations(int cpu);
/* in tsk->state again */
#define TASK_DEAD 64
#define TASK_WAKEKILL 128
+#define TASK_WAKING 256
/* Convenience macros for the sake of set_task_state */
#define TASK_KILLABLE (TASK_WAKEKILL | TASK_UNINTERRUPTIBLE)
extern void init_idle(struct task_struct *idle, int cpu);
extern void init_idle_bootup_task(struct task_struct *idle);
-extern int runqueue_is_locked(void);
+extern int runqueue_is_locked(int cpu);
extern void task_rq_unlock_wait(struct task_struct *p);
extern cpumask_var_t nohz_cpu_mask;
extern void touch_softlockup_watchdog(void);
extern void touch_all_softlockup_watchdogs(void);
extern int proc_dosoftlockup_thresh(struct ctl_table *table, int write,
- struct file *filp, void __user *buffer,
+ void __user *buffer,
size_t *lenp, loff_t *ppos);
extern unsigned int softlockup_panic;
extern int softlockup_thresh;
extern unsigned long sysctl_hung_task_timeout_secs;
extern unsigned long sysctl_hung_task_warnings;
extern int proc_dohung_task_timeout_secs(struct ctl_table *table, int write,
- struct file *filp, void __user *buffer,
+ void __user *buffer,
size_t *lenp, loff_t *ppos);
#endif
return max(mm->hiwater_rss, get_mm_rss(mm));
}
+static inline void setmax_mm_hiwater_rss(unsigned long *maxrss,
+ struct mm_struct *mm)
+{
+ unsigned long hiwater_rss = get_mm_hiwater_rss(mm);
+
+ if (*maxrss < hiwater_rss)
+ *maxrss = hiwater_rss;
+}
+
static inline unsigned long get_mm_hiwater_vm(struct mm_struct *mm)
{
return max(mm->hiwater_vm, mm->total_vm);
/* dumpable bits */
#define MMF_DUMPABLE 0 /* core dump is permitted */
#define MMF_DUMP_SECURELY 1 /* core file is readable only by root */
+
#define MMF_DUMPABLE_BITS 2
+#define MMF_DUMPABLE_MASK ((1 << MMF_DUMPABLE_BITS) - 1)
/* coredump filter bits */
#define MMF_DUMP_ANON_PRIVATE 2
#define MMF_DUMP_ELF_HEADERS 6
#define MMF_DUMP_HUGETLB_PRIVATE 7
#define MMF_DUMP_HUGETLB_SHARED 8
+
#define MMF_DUMP_FILTER_SHIFT MMF_DUMPABLE_BITS
#define MMF_DUMP_FILTER_BITS 7
#define MMF_DUMP_FILTER_MASK \
#else
# define MMF_DUMP_MASK_DEFAULT_ELF 0
#endif
+ /* leave room for more dump flags */
+#define MMF_VM_MERGEABLE 16 /* KSM may merge identical pages */
+
+#define MMF_INIT_MASK (MMF_DUMPABLE_MASK | MMF_DUMP_FILTER_MASK)
struct sighand_struct {
atomic_t count;
unsigned long ac_minflt, ac_majflt;
};
+struct cpu_itimer {
+ cputime_t expires;
+ cputime_t incr;
+ u32 error;
+ u32 incr_error;
+};
+
/**
* struct task_cputime - collected CPU time counts
* @utime: time spent in user mode, in &cputime_t units
struct pid *leader_pid;
ktime_t it_real_incr;
- /* ITIMER_PROF and ITIMER_VIRTUAL timers for the process */
- cputime_t it_prof_expires, it_virt_expires;
- cputime_t it_prof_incr, it_virt_incr;
+ /*
+ * ITIMER_PROF and ITIMER_VIRTUAL timers for the process, we use
+ * CPUCLOCK_PROF and CPUCLOCK_VIRT for indexing array as these
+ * values are defined to 0 and 1 respectively
+ */
+ struct cpu_itimer it[2];
/*
* Thread group totals for process CPU timers.
unsigned long nvcsw, nivcsw, cnvcsw, cnivcsw;
unsigned long min_flt, maj_flt, cmin_flt, cmaj_flt;
unsigned long inblock, oublock, cinblock, coublock;
+ unsigned long maxrss, cmaxrss;
struct task_io_accounting ioac;
/*
unsigned audit_tty;
struct tty_audit_buf *tty_audit_buf;
#endif
+
+ int oom_adj; /* OOM kill score adjustment (bit shift) */
};
/* Context switch must be unlocked if interrupts are to be enabled */
#endif
#endif
-#ifdef CONFIG_PERF_COUNTERS
+#ifdef CONFIG_PERF_EVENTS
atomic_long_t locked_vm;
#endif
};
#define SD_BALANCE_NEWIDLE 0x0002 /* Balance when about to become idle */
#define SD_BALANCE_EXEC 0x0004 /* Balance on exec */
#define SD_BALANCE_FORK 0x0008 /* Balance on fork, clone */
-#define SD_WAKE_IDLE 0x0010 /* Wake to idle CPU on task wakeup */
+#define SD_BALANCE_WAKE 0x0010 /* Balance on wakeup */
#define SD_WAKE_AFFINE 0x0020 /* Wake task to waking CPU */
-#define SD_WAKE_BALANCE 0x0040 /* Perform balancing at task wakeup */
+#define SD_PREFER_LOCAL 0x0040 /* Prefer to keep tasks local to this domain */
#define SD_SHARE_CPUPOWER 0x0080 /* Domain members share cpu power */
#define SD_POWERSAVINGS_BALANCE 0x0100 /* Balance for power savings */
#define SD_SHARE_PKG_RESOURCES 0x0200 /* Domain members share cpu pkg resources */
#define SD_SERIALIZE 0x0400 /* Only a single load balancing instance */
-#define SD_WAKE_IDLE_FAR 0x0800 /* Gain latency sacrificing cache hit */
+
#define SD_PREFER_SIBLING 0x1000 /* Prefer to place tasks in a sibling domain */
enum powersavings_balance_level {
return 0;
}
+unsigned long default_scale_freq_power(struct sched_domain *sd, int cpu);
+unsigned long default_scale_smt_power(struct sched_domain *sd, int cpu);
+
#else /* CONFIG_SMP */
struct sched_domain_attr;
}
#endif /* !CONFIG_SMP */
+
struct io_context; /* See blkdev.h */
struct rq;
struct sched_domain;
+/*
+ * wake flags
+ */
+#define WF_SYNC 0x01 /* waker goes to sleep after wakup */
+#define WF_FORK 0x02 /* child wakeup after fork */
+
struct sched_class {
const struct sched_class *next;
void (*dequeue_task) (struct rq *rq, struct task_struct *p, int sleep);
void (*yield_task) (struct rq *rq);
- void (*check_preempt_curr) (struct rq *rq, struct task_struct *p, int sync);
+ void (*check_preempt_curr) (struct rq *rq, struct task_struct *p, int flags);
struct task_struct * (*pick_next_task) (struct rq *rq);
void (*put_prev_task) (struct rq *rq, struct task_struct *p);
#ifdef CONFIG_SMP
- int (*select_task_rq)(struct task_struct *p, int sync);
+ int (*select_task_rq)(struct task_struct *p, int sd_flag, int flags);
unsigned long (*load_balance) (struct rq *this_rq, int this_cpu,
struct rq *busiest, unsigned long max_load_move,
void (*prio_changed) (struct rq *this_rq, struct task_struct *task,
int oldprio, int running);
+ unsigned int (*get_rr_interval) (struct task_struct *task);
+
#ifdef CONFIG_FAIR_GROUP_SCHED
void (*moved_group) (struct task_struct *p);
#endif
u64 start_runtime;
u64 avg_wakeup;
+ u64 avg_running;
+
#ifdef CONFIG_SCHEDSTATS
u64 wait_start;
u64 wait_max;
* a short time
*/
unsigned char fpu_counter;
- s8 oomkilladj; /* OOM kill score adjustment (bit shift). */
#ifdef CONFIG_BLK_DEV_IO_TRACE
unsigned int btrace_seq;
#endif
struct mm_struct *mm, *active_mm;
/* task state */
- struct linux_binfmt *binfmt;
int exit_state;
int exit_code, exit_signal;
int pdeath_signal; /* The signal sent when the parent dies */
struct list_head pi_state_list;
struct futex_pi_state *pi_state_cache;
#endif
-#ifdef CONFIG_PERF_COUNTERS
- struct perf_counter_context *perf_counter_ctxp;
- struct mutex perf_counter_mutex;
- struct list_head perf_counter_list;
+#ifdef CONFIG_PERF_EVENTS
+ struct perf_event_context *perf_event_ctxp;
+ struct mutex perf_event_mutex;
+ struct list_head perf_event_list;
#endif
#ifdef CONFIG_NUMA
struct mempolicy *mempolicy; /* Protected by alloc_lock */
/* bitmask of trace recursion */
unsigned long trace_recursion;
#endif /* CONFIG_TRACING */
+ unsigned long stack_start;
};
/* Future-safe accessor for struct task_struct's cpus_allowed. */
#define PF_EXITPIDONE 0x00000008 /* pi exit done on shut down */
#define PF_VCPU 0x00000010 /* I'm a virtual CPU */
#define PF_FORKNOEXEC 0x00000040 /* forked but didn't exec */
+ #define PF_MCE_PROCESS 0x00000080 /* process policy on mce errors */
#define PF_SUPERPRIV 0x00000100 /* used super-user privileges */
#define PF_DUMPCORE 0x00000200 /* dumped core */
#define PF_SIGNALED 0x00000400 /* killed by a signal */
#define PF_FROZEN 0x00010000 /* frozen for system suspend */
#define PF_FSTRANS 0x00020000 /* inside a filesystem transaction */
#define PF_KSWAPD 0x00040000 /* I am kswapd */
-#define PF_SWAPOFF 0x00080000 /* I am in swapoff */
+#define PF_OOM_ORIGIN 0x00080000 /* Allocating much memory to others */
#define PF_LESS_THROTTLE 0x00100000 /* Throttle me less: I clean memory */
#define PF_KTHREAD 0x00200000 /* I am a kernel thread */
#define PF_RANDOMIZE 0x00400000 /* randomize virtual address space */
#define PF_SPREAD_PAGE 0x01000000 /* Spread page cache over cpuset */
#define PF_SPREAD_SLAB 0x02000000 /* Spread some slab caches over cpuset */
#define PF_THREAD_BOUND 0x04000000 /* Thread bound to specific cpu */
+ #define PF_MCE_EARLY 0x08000000 /* Early kill for mce process policy */
#define PF_MEMPOLICY 0x10000000 /* Non-default NUMA mempolicy */
#define PF_MUTEX_TESTER 0x20000000 /* Thread belongs to the rt mutex tester */
#define PF_FREEZER_SKIP 0x40000000 /* Freezer should not count it as freezeable */
#define RCU_READ_UNLOCK_BLOCKED (1 << 0) /* blocked while in RCU read-side. */
#define RCU_READ_UNLOCK_NEED_QS (1 << 1) /* RCU core needs CPU response. */
-#define RCU_READ_UNLOCK_GOT_QS (1 << 2) /* CPU has responded to RCU core. */
static inline void rcu_copy_process(struct task_struct *p)
{
return 0;
}
#endif
+
+#ifndef CONFIG_CPUMASK_OFFSTACK
static inline int set_cpus_allowed(struct task_struct *p, cpumask_t new_mask)
{
return set_cpus_allowed_ptr(p, &new_mask);
}
+#endif
/*
* Architectures can set this to 1 if they have specified
extern unsigned int sysctl_timer_migration;
int sched_nr_latency_handler(struct ctl_table *table, int write,
- struct file *file, void __user *buffer, size_t *length,
+ void __user *buffer, size_t *length,
loff_t *ppos);
#endif
#ifdef CONFIG_SCHED_DEBUG
extern int sysctl_sched_rt_runtime;
int sched_rt_handler(struct ctl_table *table, int write,
- struct file *filp, void __user *buffer, size_t *lenp,
+ void __user *buffer, size_t *lenp,
loff_t *ppos);
extern unsigned int sysctl_sched_compat_yield;
extern int kill_pid(struct pid *pid, int sig, int priv);
extern int kill_proc_info(int, struct siginfo *, pid_t);
extern int do_notify_parent(struct task_struct *, int);
+extern void __wake_up_parent(struct task_struct *p, struct task_struct *parent);
extern void force_sig(int, struct task_struct *);
extern void force_sig_specific(int, struct task_struct *);
extern int send_sig(int, struct task_struct *, int);
return unlikely(test_tsk_thread_flag(p,TIF_SIGPENDING));
}
-extern int __fatal_signal_pending(struct task_struct *p);
+static inline int __fatal_signal_pending(struct task_struct *p)
+{
+ return unlikely(sigismember(&p->pending.signal, SIGKILL));
+}
static inline int fatal_signal_pending(struct task_struct *p)
{
* the type/offset into the pte as 5/27 as well.
*/
#define MAX_SWAPFILES_SHIFT 5
- #ifndef CONFIG_MIGRATION
- #define MAX_SWAPFILES (1 << MAX_SWAPFILES_SHIFT)
+
+ /*
+ * Use some of the swap files numbers for other purposes. This
+ * is a convenient way to hook into the VM to trigger special
+ * actions on faults.
+ */
+
+ /*
+ * NUMA node memory migration support
+ */
+ #ifdef CONFIG_MIGRATION
+ #define SWP_MIGRATION_NUM 2
+ #define SWP_MIGRATION_READ (MAX_SWAPFILES + SWP_HWPOISON_NUM)
+ #define SWP_MIGRATION_WRITE (MAX_SWAPFILES + SWP_HWPOISON_NUM + 1)
#else
- /* Use last two entries for page migration swap entries */
- #define MAX_SWAPFILES ((1 << MAX_SWAPFILES_SHIFT)-2)
- #define SWP_MIGRATION_READ MAX_SWAPFILES
- #define SWP_MIGRATION_WRITE (MAX_SWAPFILES + 1)
+ #define SWP_MIGRATION_NUM 0
#endif
+ /*
+ * Handling of hardware poisoned pages with memory corruption.
+ */
+ #ifdef CONFIG_MEMORY_FAILURE
+ #define SWP_HWPOISON_NUM 1
+ #define SWP_HWPOISON MAX_SWAPFILES
+ #else
+ #define SWP_HWPOISON_NUM 0
+ #endif
+
+ #define MAX_SWAPFILES \
+ ((1 << MAX_SWAPFILES_SHIFT) - SWP_MIGRATION_NUM - SWP_HWPOISON_NUM)
+
/*
* Magic header for a swap area. The first part of the union is
* what the swap magic looks like for the old (limited to 128MB)
extern unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *mem,
gfp_t gfp_mask, bool noswap,
unsigned int swappiness);
+extern unsigned long mem_cgroup_shrink_node_zone(struct mem_cgroup *mem,
+ gfp_t gfp_mask, bool noswap,
+ unsigned int swappiness,
+ struct zone *zone,
+ int nid);
extern int __isolate_lru_page(struct page *page, int mode, int file);
extern unsigned long shrink_all_memory(unsigned long nr_pages);
extern int vm_swappiness;
extern void scan_mapping_unevictable_pages(struct address_space *);
extern unsigned long scan_unevictable_pages;
-extern int scan_unevictable_handler(struct ctl_table *, int, struct file *,
+extern int scan_unevictable_handler(struct ctl_table *, int,
void __user *, size_t *, loff_t *);
extern int scan_unevictable_register_node(struct node *node);
extern void scan_unevictable_unregister_node(struct node *node);
}
/* linux/mm/thrash.c */
-#define put_swap_token(mm) do { } while (0)
-#define grab_swap_token(mm) do { } while (0)
-#define has_swap_token(mm) 0
-#define disable_swap_token() do { } while (0)
+static inline void put_swap_token(struct mm_struct *mm)
+{
+}
+
+static inline void grab_swap_token(struct mm_struct *mm)
+{
+}
+
+static inline int has_swap_token(struct mm_struct *mm)
+{
+ return 0;
+}
+
+static inline void disable_swap_token(void)
+{
+}
static inline void
mem_cgroup_uncharge_swapcache(struct page *page, swp_entry_t ent)
#include <linux/prctl.h>
#include <linux/highuid.h>
#include <linux/fs.h>
-#include <linux/perf_counter.h>
+#include <linux/perf_event.h>
#include <linux/resource.h>
#include <linux/kernel.h>
#include <linux/kexec.h>
unsigned long flags;
cputime_t utime, stime;
struct task_cputime cputime;
+ unsigned long maxrss = 0;
memset((char *) r, 0, sizeof *r);
utime = stime = cputime_zero;
utime = task_utime(current);
stime = task_stime(current);
accumulate_thread_rusage(p, r);
+ maxrss = p->signal->maxrss;
goto out;
}
r->ru_majflt = p->signal->cmaj_flt;
r->ru_inblock = p->signal->cinblock;
r->ru_oublock = p->signal->coublock;
+ maxrss = p->signal->cmaxrss;
if (who == RUSAGE_CHILDREN)
break;
r->ru_majflt += p->signal->maj_flt;
r->ru_inblock += p->signal->inblock;
r->ru_oublock += p->signal->oublock;
+ if (maxrss < p->signal->maxrss)
+ maxrss = p->signal->maxrss;
t = p;
do {
accumulate_thread_rusage(t, r);
out:
cputime_to_timeval(utime, &r->ru_utime);
cputime_to_timeval(stime, &r->ru_stime);
+
+ if (who != RUSAGE_CHILDREN) {
+ struct mm_struct *mm = get_task_mm(p);
+ if (mm) {
+ setmax_mm_hiwater_rss(&maxrss, mm);
+ mmput(mm);
+ }
+ }
+ r->ru_maxrss = maxrss * (PAGE_SIZE / 1024); /* convert pages to KBs */
}
int getrusage(struct task_struct *p, int who, struct rusage __user *ru)
case PR_SET_TSC:
error = SET_TSC_CTL(arg2);
break;
- case PR_TASK_PERF_COUNTERS_DISABLE:
- error = perf_counter_task_disable();
+ case PR_TASK_PERF_EVENTS_DISABLE:
+ error = perf_event_task_disable();
break;
- case PR_TASK_PERF_COUNTERS_ENABLE:
- error = perf_counter_task_enable();
+ case PR_TASK_PERF_EVENTS_ENABLE:
+ error = perf_event_task_enable();
break;
case PR_GET_TIMERSLACK:
error = current->timer_slack_ns;
current->timer_slack_ns = arg2;
error = 0;
break;
+ case PR_MCE_KILL:
+ if (arg4 | arg5)
+ return -EINVAL;
+ switch (arg2) {
+ case 0:
+ if (arg3 != 0)
+ return -EINVAL;
+ current->flags &= ~PF_MCE_PROCESS;
+ break;
+ case 1:
+ current->flags |= PF_MCE_PROCESS;
+ if (arg3 != 0)
+ current->flags |= PF_MCE_EARLY;
+ else
+ current->flags &= ~PF_MCE_EARLY;
+ break;
+ default:
+ return -EINVAL;
+ }
+ error = 0;
+ break;
+
default:
error = -EINVAL;
break;
#include <linux/proc_fs.h>
#include <linux/security.h>
#include <linux/ctype.h>
-#include <linux/utsname.h>
#include <linux/kmemcheck.h>
#include <linux/smp_lock.h>
#include <linux/fs.h>
#include <linux/reboot.h>
#include <linux/ftrace.h>
#include <linux/slow-work.h>
-#include <linux/perf_counter.h>
+#include <linux/perf_event.h>
#include <asm/uaccess.h>
#include <asm/processor.h>
extern int core_uses_pid;
extern int suid_dumpable;
extern char core_pattern[];
+extern unsigned int core_pipe_limit;
extern int pid_max;
extern int min_free_kbytes;
extern int pid_max_min, pid_max_max;
#ifdef CONFIG_RCU_TORTURE_TEST
extern int rcutorture_runnable;
#endif /* #ifdef CONFIG_RCU_TORTURE_TEST */
+#ifdef CONFIG_BLOCK
extern int blk_iopoll_enabled;
+#endif
/* Constants used for minimum and maximum */
#ifdef CONFIG_DETECT_SOFTLOCKUP
static int __maybe_unused two = 2;
static unsigned long one_ul = 1;
static int one_hundred = 100;
+#ifdef CONFIG_PRINTK
+static int ten_thousand = 10000;
+#endif
/* this is needed for the proc_doulongvec_minmax of vm_dirty_bytes */
static unsigned long dirty_bytes_min = 2 * PAGE_SIZE;
#endif
#ifdef CONFIG_PROC_SYSCTL
-static int proc_do_cad_pid(struct ctl_table *table, int write, struct file *filp,
+static int proc_do_cad_pid(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos);
-static int proc_taint(struct ctl_table *table, int write, struct file *filp,
+static int proc_taint(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos);
#endif
.proc_handler = &proc_dostring,
.strategy = &sysctl_string,
},
+ {
+ .ctl_name = CTL_UNNUMBERED,
+ .procname = "core_pipe_limit",
+ .data = &core_pipe_limit,
+ .maxlen = sizeof(unsigned int),
+ .mode = 0644,
+ .proc_handler = &proc_dointvec,
+ },
#ifdef CONFIG_PROC_SYSCTL
{
.procname = "tainted",
.mode = 0644,
.proc_handler = &proc_dointvec,
},
+ {
+ .ctl_name = CTL_UNNUMBERED,
+ .procname = "printk_delay",
+ .data = &printk_delay_msec,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = &proc_dointvec_minmax,
+ .strategy = &sysctl_intvec,
+ .extra1 = &zero,
+ .extra2 = &ten_thousand,
+ },
#endif
{
.ctl_name = KERN_NGROUPS_MAX,
.child = slow_work_sysctls,
},
#endif
-#ifdef CONFIG_PERF_COUNTERS
+#ifdef CONFIG_PERF_EVENTS
{
.ctl_name = CTL_UNNUMBERED,
- .procname = "perf_counter_paranoid",
- .data = &sysctl_perf_counter_paranoid,
- .maxlen = sizeof(sysctl_perf_counter_paranoid),
+ .procname = "perf_event_paranoid",
+ .data = &sysctl_perf_event_paranoid,
+ .maxlen = sizeof(sysctl_perf_event_paranoid),
.mode = 0644,
.proc_handler = &proc_dointvec,
},
{
.ctl_name = CTL_UNNUMBERED,
- .procname = "perf_counter_mlock_kb",
- .data = &sysctl_perf_counter_mlock,
- .maxlen = sizeof(sysctl_perf_counter_mlock),
+ .procname = "perf_event_mlock_kb",
+ .data = &sysctl_perf_event_mlock,
+ .maxlen = sizeof(sysctl_perf_event_mlock),
.mode = 0644,
.proc_handler = &proc_dointvec,
},
{
.ctl_name = CTL_UNNUMBERED,
- .procname = "perf_counter_max_sample_rate",
- .data = &sysctl_perf_counter_sample_rate,
- .maxlen = sizeof(sysctl_perf_counter_sample_rate),
+ .procname = "perf_event_max_sample_rate",
+ .data = &sysctl_perf_event_sample_rate,
+ .maxlen = sizeof(sysctl_perf_event_sample_rate),
.mode = 0644,
.proc_handler = &proc_dointvec,
},
.proc_handler = &proc_dointvec,
},
#endif
+#ifdef CONFIG_BLOCK
{
.ctl_name = CTL_UNNUMBERED,
.procname = "blk_iopoll",
.mode = 0644,
.proc_handler = &proc_dointvec,
},
+#endif
/*
* NOTE: do not add new entries to this table unless you have read
* Documentation/sysctl/ctl_unnumbered.txt
.mode = 0644,
.proc_handler = &scan_unevictable_handler,
},
+ #ifdef CONFIG_MEMORY_FAILURE
+ {
+ .ctl_name = CTL_UNNUMBERED,
+ .procname = "memory_failure_early_kill",
+ .data = &sysctl_memory_failure_early_kill,
+ .maxlen = sizeof(sysctl_memory_failure_early_kill),
+ .mode = 0644,
+ .proc_handler = &proc_dointvec_minmax,
+ .strategy = &sysctl_intvec,
+ .extra1 = &zero,
+ .extra2 = &one,
+ },
+ {
+ .ctl_name = CTL_UNNUMBERED,
+ .procname = "memory_failure_recovery",
+ .data = &sysctl_memory_failure_recovery,
+ .maxlen = sizeof(sysctl_memory_failure_recovery),
+ .mode = 0644,
+ .proc_handler = &proc_dointvec_minmax,
+ .strategy = &sysctl_intvec,
+ .extra1 = &zero,
+ .extra2 = &one,
+ },
+ #endif
+
/*
* NOTE: do not add new entries to this table unless you have read
* Documentation/sysctl/ctl_unnumbered.txt
#ifdef CONFIG_PROC_SYSCTL
static int _proc_do_string(void* data, int maxlen, int write,
- struct file *filp, void __user *buffer,
+ void __user *buffer,
size_t *lenp, loff_t *ppos)
{
size_t len;
* proc_dostring - read a string sysctl
* @table: the sysctl table
* @write: %TRUE if this is a write to the sysctl file
- * @filp: the file structure
* @buffer: the user buffer
* @lenp: the size of the user buffer
* @ppos: file position
*
* Returns 0 on success.
*/
-int proc_dostring(struct ctl_table *table, int write, struct file *filp,
+int proc_dostring(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
- return _proc_do_string(table->data, table->maxlen, write, filp,
+ return _proc_do_string(table->data, table->maxlen, write,
buffer, lenp, ppos);
}
}
static int __do_proc_dointvec(void *tbl_data, struct ctl_table *table,
- int write, struct file *filp, void __user *buffer,
+ int write, void __user *buffer,
size_t *lenp, loff_t *ppos,
int (*conv)(int *negp, unsigned long *lvalp, int *valp,
int write, void *data),
#undef TMPBUFLEN
}
-static int do_proc_dointvec(struct ctl_table *table, int write, struct file *filp,
+static int do_proc_dointvec(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos,
int (*conv)(int *negp, unsigned long *lvalp, int *valp,
int write, void *data),
void *data)
{
- return __do_proc_dointvec(table->data, table, write, filp,
+ return __do_proc_dointvec(table->data, table, write,
buffer, lenp, ppos, conv, data);
}
* proc_dointvec - read a vector of integers
* @table: the sysctl table
* @write: %TRUE if this is a write to the sysctl file
- * @filp: the file structure
* @buffer: the user buffer
* @lenp: the size of the user buffer
* @ppos: file position
*
* Returns 0 on success.
*/
-int proc_dointvec(struct ctl_table *table, int write, struct file *filp,
+int proc_dointvec(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
- return do_proc_dointvec(table,write,filp,buffer,lenp,ppos,
+ return do_proc_dointvec(table,write,buffer,lenp,ppos,
NULL,NULL);
}
* Taint values can only be increased
* This means we can safely use a temporary.
*/
-static int proc_taint(struct ctl_table *table, int write, struct file *filp,
+static int proc_taint(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
struct ctl_table t;
t = *table;
t.data = &tmptaint;
- err = proc_doulongvec_minmax(&t, write, filp, buffer, lenp, ppos);
+ err = proc_doulongvec_minmax(&t, write, buffer, lenp, ppos);
if (err < 0)
return err;
* proc_dointvec_minmax - read a vector of integers with min/max values
* @table: the sysctl table
* @write: %TRUE if this is a write to the sysctl file
- * @filp: the file structure
* @buffer: the user buffer
* @lenp: the size of the user buffer
* @ppos: file position
*
* Returns 0 on success.
*/
-int proc_dointvec_minmax(struct ctl_table *table, int write, struct file *filp,
+int proc_dointvec_minmax(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
struct do_proc_dointvec_minmax_conv_param param = {
.min = (int *) table->extra1,
.max = (int *) table->extra2,
};
- return do_proc_dointvec(table, write, filp, buffer, lenp, ppos,
+ return do_proc_dointvec(table, write, buffer, lenp, ppos,
do_proc_dointvec_minmax_conv, ¶m);
}
static int __do_proc_doulongvec_minmax(void *data, struct ctl_table *table, int write,
- struct file *filp,
void __user *buffer,
size_t *lenp, loff_t *ppos,
unsigned long convmul,
}
static int do_proc_doulongvec_minmax(struct ctl_table *table, int write,
- struct file *filp,
void __user *buffer,
size_t *lenp, loff_t *ppos,
unsigned long convmul,
unsigned long convdiv)
{
return __do_proc_doulongvec_minmax(table->data, table, write,
- filp, buffer, lenp, ppos, convmul, convdiv);
+ buffer, lenp, ppos, convmul, convdiv);
}
/**
* proc_doulongvec_minmax - read a vector of long integers with min/max values
* @table: the sysctl table
* @write: %TRUE if this is a write to the sysctl file
- * @filp: the file structure
* @buffer: the user buffer
* @lenp: the size of the user buffer
* @ppos: file position
*
* Returns 0 on success.
*/
-int proc_doulongvec_minmax(struct ctl_table *table, int write, struct file *filp,
+int proc_doulongvec_minmax(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
- return do_proc_doulongvec_minmax(table, write, filp, buffer, lenp, ppos, 1l, 1l);
+ return do_proc_doulongvec_minmax(table, write, buffer, lenp, ppos, 1l, 1l);
}
/**
* proc_doulongvec_ms_jiffies_minmax - read a vector of millisecond values with min/max values
* @table: the sysctl table
* @write: %TRUE if this is a write to the sysctl file
- * @filp: the file structure
* @buffer: the user buffer
* @lenp: the size of the user buffer
* @ppos: file position
* Returns 0 on success.
*/
int proc_doulongvec_ms_jiffies_minmax(struct ctl_table *table, int write,
- struct file *filp,
void __user *buffer,
size_t *lenp, loff_t *ppos)
{
- return do_proc_doulongvec_minmax(table, write, filp, buffer,
+ return do_proc_doulongvec_minmax(table, write, buffer,
lenp, ppos, HZ, 1000l);
}
* proc_dointvec_jiffies - read a vector of integers as seconds
* @table: the sysctl table
* @write: %TRUE if this is a write to the sysctl file
- * @filp: the file structure
* @buffer: the user buffer
* @lenp: the size of the user buffer
* @ppos: file position
*
* Returns 0 on success.
*/
-int proc_dointvec_jiffies(struct ctl_table *table, int write, struct file *filp,
+int proc_dointvec_jiffies(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
- return do_proc_dointvec(table,write,filp,buffer,lenp,ppos,
+ return do_proc_dointvec(table,write,buffer,lenp,ppos,
do_proc_dointvec_jiffies_conv,NULL);
}
* proc_dointvec_userhz_jiffies - read a vector of integers as 1/USER_HZ seconds
* @table: the sysctl table
* @write: %TRUE if this is a write to the sysctl file
- * @filp: the file structure
* @buffer: the user buffer
* @lenp: the size of the user buffer
* @ppos: pointer to the file position
*
* Returns 0 on success.
*/
-int proc_dointvec_userhz_jiffies(struct ctl_table *table, int write, struct file *filp,
+int proc_dointvec_userhz_jiffies(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
- return do_proc_dointvec(table,write,filp,buffer,lenp,ppos,
+ return do_proc_dointvec(table,write,buffer,lenp,ppos,
do_proc_dointvec_userhz_jiffies_conv,NULL);
}
* proc_dointvec_ms_jiffies - read a vector of integers as 1 milliseconds
* @table: the sysctl table
* @write: %TRUE if this is a write to the sysctl file
- * @filp: the file structure
* @buffer: the user buffer
* @lenp: the size of the user buffer
* @ppos: file position
*
* Returns 0 on success.
*/
-int proc_dointvec_ms_jiffies(struct ctl_table *table, int write, struct file *filp,
+int proc_dointvec_ms_jiffies(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
- return do_proc_dointvec(table, write, filp, buffer, lenp, ppos,
+ return do_proc_dointvec(table, write, buffer, lenp, ppos,
do_proc_dointvec_ms_jiffies_conv, NULL);
}
-static int proc_do_cad_pid(struct ctl_table *table, int write, struct file *filp,
+static int proc_do_cad_pid(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
struct pid *new_pid;
tmp = pid_vnr(cad_pid);
- r = __do_proc_dointvec(&tmp, table, write, filp, buffer,
+ r = __do_proc_dointvec(&tmp, table, write, buffer,
lenp, ppos, NULL, NULL);
if (r || !write)
return r;
#else /* CONFIG_PROC_FS */
-int proc_dostring(struct ctl_table *table, int write, struct file *filp,
+int proc_dostring(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
return -ENOSYS;
}
-int proc_dointvec(struct ctl_table *table, int write, struct file *filp,
+int proc_dointvec(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
return -ENOSYS;
}
-int proc_dointvec_minmax(struct ctl_table *table, int write, struct file *filp,
+int proc_dointvec_minmax(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
return -ENOSYS;
}
-int proc_dointvec_jiffies(struct ctl_table *table, int write, struct file *filp,
+int proc_dointvec_jiffies(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
return -ENOSYS;
}
-int proc_dointvec_userhz_jiffies(struct ctl_table *table, int write, struct file *filp,
+int proc_dointvec_userhz_jiffies(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
return -ENOSYS;
}
-int proc_dointvec_ms_jiffies(struct ctl_table *table, int write, struct file *filp,
+int proc_dointvec_ms_jiffies(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
return -ENOSYS;
}
-int proc_doulongvec_minmax(struct ctl_table *table, int write, struct file *filp,
+int proc_doulongvec_minmax(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
return -ENOSYS;
}
int proc_doulongvec_ms_jiffies_minmax(struct ctl_table *table, int write,
- struct file *filp,
void __user *buffer,
size_t *lenp, loff_t *ppos)
{
config MMU_NOTIFIER
bool
+config KSM
+ bool "Enable KSM for page merging"
+ depends on MMU
+ help
+ Enable Kernel Samepage Merging: KSM periodically scans those areas
+ of an application's address space that an app has advised may be
+ mergeable. When it finds pages of identical content, it replaces
+ the many instances by a single resident page with that content, so
+ saving memory until one or another app needs to modify the content.
+ Recommended for use with KVM, or with other duplicative applications.
+ See Documentation/vm/ksm.txt for more information.
+
config DEFAULT_MMAP_MIN_ADDR
int "Low address space to protect from user allocation"
default 4096
/proc/sys/vm/mmap_min_addr tunable.
+ config MEMORY_FAILURE
+ depends on MMU
+ depends on X86_MCE
+ bool "Enable recovery from hardware memory errors"
+ help
+ Enables code to recover from some memory failures on systems
+ with MCA recovery. This allows a system to continue running
+ even when some of its memory has uncorrected errors. This requires
+ special hardware support and typically ECC memory.
+
+ config HWPOISON_INJECT
+ tristate "Poison pages injector"
+ depends on MEMORY_FAILURE && DEBUG_KERNEL
+
config NOMMU_INITIAL_TRIM_EXCESS
int "Turn on mmap() excess space trimming before booting"
depends on !MMU
maccess.o page_alloc.o page-writeback.o \
readahead.o swap.o truncate.o vmscan.o shmem.o \
prio_tree.o util.o mmzone.o vmstat.o backing-dev.o \
- page_isolation.o mm_init.o $(mmu-y)
+ page_isolation.o mm_init.o mmu_context.o \
+ pagewalk.o $(mmu-y)
obj-y += init-mm.o
-obj-$(CONFIG_PROC_PAGE_MONITOR) += pagewalk.o
obj-$(CONFIG_BOUNCE) += bounce.o
obj-$(CONFIG_SWAP) += page_io.o swap_state.o swapfile.o thrash.o
obj-$(CONFIG_HAS_DMA) += dmapool.o
obj-$(CONFIG_TMPFS_POSIX_ACL) += shmem_acl.o
obj-$(CONFIG_SLOB) += slob.o
obj-$(CONFIG_MMU_NOTIFIER) += mmu_notifier.o
+obj-$(CONFIG_KSM) += ksm.o
obj-$(CONFIG_PAGE_POISONING) += debug-pagealloc.o
obj-$(CONFIG_SLAB) += slab.o
obj-$(CONFIG_SLUB) += slub.o
endif
obj-$(CONFIG_QUICKLIST) += quicklist.o
obj-$(CONFIG_CGROUP_MEM_RES_CTLR) += memcontrol.o page_cgroup.o
+ obj-$(CONFIG_MEMORY_FAILURE) += memory-failure.o
+ obj-$(CONFIG_HWPOISON_INJECT) += hwpoison-inject.o
obj-$(CONFIG_DEBUG_KMEMLEAK) += kmemleak.o
obj-$(CONFIG_DEBUG_KMEMLEAK_TEST) += kmemleak-test.o
*
* ->task->proc_lock
* ->dcache_lock (proc_pid_lookup)
+ *
+ * (code doesn't rely on that order, so you could switch it around)
+ * ->tasklist_lock (memory_failure, collect_procs_ao)
+ * ->i_mmap_lock
*/
/*
page->mapping = NULL;
mapping->nrpages--;
__dec_zone_page_state(page, NR_FILE_PAGES);
+ if (PageSwapBacked(page))
+ __dec_zone_page_state(page, NR_SHMEM);
BUG_ON(page_mapped(page));
/*
if (likely(!error)) {
mapping->nrpages++;
__inc_zone_page_state(page, NR_FILE_PAGES);
+ if (PageSwapBacked(page))
+ __inc_zone_page_state(page, NR_SHMEM);
spin_unlock_irq(&mapping->tree_lock);
} else {
page->mapping = NULL;
#include <linux/mempolicy.h>
#include <linux/hugetlb.h>
#include <linux/sched.h>
+#include <linux/ksm.h>
/*
* Any behaviour which results in changes to the vma->vm_flags needs to
struct mm_struct * mm = vma->vm_mm;
int error = 0;
pgoff_t pgoff;
- int new_flags = vma->vm_flags;
+ unsigned long new_flags = vma->vm_flags;
switch (behavior) {
case MADV_NORMAL:
new_flags |= VM_DONTCOPY;
break;
case MADV_DOFORK:
+ if (vma->vm_flags & VM_IO) {
+ error = -EINVAL;
+ goto out;
+ }
new_flags &= ~VM_DONTCOPY;
break;
+ case MADV_MERGEABLE:
+ case MADV_UNMERGEABLE:
+ error = ksm_madvise(vma, start, end, behavior, &new_flags);
+ if (error)
+ goto out;
+ break;
}
if (new_flags == vma->vm_flags) {
return error;
}
+ #ifdef CONFIG_MEMORY_FAILURE
+ /*
+ * Error injection support for memory error handling.
+ */
+ static int madvise_hwpoison(unsigned long start, unsigned long end)
+ {
+ int ret = 0;
+
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+ for (; start < end; start += PAGE_SIZE) {
+ struct page *p;
+ int ret = get_user_pages(current, current->mm, start, 1,
+ 0, 0, &p, NULL);
+ if (ret != 1)
+ return ret;
+ printk(KERN_INFO "Injecting memory failure for page %lx at %lx\n",
+ page_to_pfn(p), start);
+ /* Ignore return value for now */
+ __memory_failure(page_to_pfn(p), 0, 1);
+ put_page(p);
+ }
+ return ret;
+ }
+ #endif
+
static long
madvise_vma(struct vm_area_struct *vma, struct vm_area_struct **prev,
unsigned long start, unsigned long end, int behavior)
{
- long error;
-
switch (behavior) {
- case MADV_DOFORK:
- if (vma->vm_flags & VM_IO) {
- error = -EINVAL;
- break;
- }
- case MADV_DONTFORK:
- case MADV_NORMAL:
- case MADV_SEQUENTIAL:
- case MADV_RANDOM:
- error = madvise_behavior(vma, prev, start, end, behavior);
- break;
case MADV_REMOVE:
- error = madvise_remove(vma, prev, start, end);
- break;
-
+ return madvise_remove(vma, prev, start, end);
case MADV_WILLNEED:
- error = madvise_willneed(vma, prev, start, end);
- break;
-
+ return madvise_willneed(vma, prev, start, end);
case MADV_DONTNEED:
- error = madvise_dontneed(vma, prev, start, end);
- break;
-
+ return madvise_dontneed(vma, prev, start, end);
default:
- BUG();
- break;
+ return madvise_behavior(vma, prev, start, end, behavior);
}
- return error;
}
static int
case MADV_REMOVE:
case MADV_WILLNEED:
case MADV_DONTNEED:
+#ifdef CONFIG_KSM
+ case MADV_MERGEABLE:
+ case MADV_UNMERGEABLE:
+#endif
return 1;
default:
return 0;
}
}
+
/*
* The madvise(2) system call.
*
* so the kernel can free resources associated with it.
* MADV_REMOVE - the application wants to free up the given range of
* pages and associated backing store.
+ * MADV_DONTFORK - omit this area from child's address space when forking:
+ * typically, to avoid COWing pages pinned by get_user_pages().
+ * MADV_DOFORK - cancel MADV_DONTFORK: no longer omit this area when forking.
+ * MADV_MERGEABLE - the application recommends that KSM try to merge pages in
+ * this area with pages of identical content from other such areas.
+ * MADV_UNMERGEABLE- cancel MADV_MERGEABLE: no longer merge pages with others.
*
* return values:
* zero - success
int write;
size_t len;
+ #ifdef CONFIG_MEMORY_FAILURE
+ if (behavior == MADV_HWPOISON)
+ return madvise_hwpoison(start, start+len_in);
+ #endif
if (!madvise_behavior_valid(behavior))
return error;
#include <linux/swap.h>
#include <linux/highmem.h>
#include <linux/pagemap.h>
+#include <linux/ksm.h>
#include <linux/rmap.h>
#include <linux/module.h>
#include <linux/delayacct.h>
#include <linux/swapops.h>
#include <linux/elf.h>
+#include <asm/io.h>
#include <asm/pgalloc.h>
#include <asm/uaccess.h>
#include <asm/tlb.h>
}
__setup("norandmaps", disable_randmaps);
+unsigned long zero_pfn __read_mostly;
+unsigned long highest_memmap_pfn __read_mostly;
+
+/*
+ * CONFIG_MMU architectures set up ZERO_PAGE in their paging_init()
+ */
+static int __init init_zero_pfn(void)
+{
+ zero_pfn = page_to_pfn(ZERO_PAGE(0));
+ return 0;
+}
+core_initcall(init_zero_pfn);
/*
* If a p?d_bad entry is found while walking page tables, report
return (flags & (VM_SHARED | VM_MAYWRITE)) == VM_MAYWRITE;
}
+#ifndef is_zero_pfn
+static inline int is_zero_pfn(unsigned long pfn)
+{
+ return pfn == zero_pfn;
+}
+#endif
+
+#ifndef my_zero_pfn
+static inline unsigned long my_zero_pfn(unsigned long addr)
+{
+ return zero_pfn;
+}
+#endif
+
/*
* vm_normal_page -- This function gets the "struct page" associated with a pte.
*
if (HAVE_PTE_SPECIAL) {
if (likely(!pte_special(pte)))
goto check_pfn;
- if (!(vma->vm_flags & (VM_PFNMAP | VM_MIXEDMAP)))
+ if (vma->vm_flags & (VM_PFNMAP | VM_MIXEDMAP))
+ return NULL;
+ if (!is_zero_pfn(pfn))
print_bad_pte(vma, addr, pte, NULL);
return NULL;
}
}
}
+ if (is_zero_pfn(pfn))
+ return NULL;
check_pfn:
if (unlikely(pfn > highest_memmap_pfn)) {
print_bad_pte(vma, addr, pte, NULL);
page = vm_normal_page(vma, addr, pte);
if (page) {
get_page(page);
- page_dup_rmap(page, vma, addr);
- rss[!!PageAnon(page)]++;
+ page_dup_rmap(page);
+ rss[PageAnon(page)]++;
}
out_set_pte:
goto no_page;
if ((flags & FOLL_WRITE) && !pte_write(pte))
goto unlock;
+
page = vm_normal_page(vma, address, pte);
- if (unlikely(!page))
- goto bad_page;
+ if (unlikely(!page)) {
+ if ((flags & FOLL_DUMP) ||
+ !is_zero_pfn(pte_pfn(pte)))
+ goto bad_page;
+ page = pte_page(pte);
+ }
if (flags & FOLL_GET)
get_page(page);
pte_unmap_unlock(ptep, ptl);
if (!pte_none(pte))
return page;
- /* Fall through to ZERO_PAGE handling */
+
no_page_table:
/*
* When core dumping an enormous anonymous area that nobody
- * has touched so far, we don't want to allocate page tables.
+ * has touched so far, we don't want to allocate unnecessary pages or
+ * page tables. Return error instead of NULL to skip handle_mm_fault,
+ * then get_dump_page() will return NULL to leave a hole in the dump.
+ * But we can only make this optimization where a hole would surely
+ * be zero-filled if handle_mm_fault() actually did handle it.
*/
- if (flags & FOLL_ANON) {
- page = ZERO_PAGE(0);
- if (flags & FOLL_GET)
- get_page(page);
- BUG_ON(flags & FOLL_WRITE);
- }
+ if ((flags & FOLL_DUMP) &&
+ (!vma->vm_ops || !vma->vm_ops->fault))
+ return ERR_PTR(-EFAULT);
return page;
}
-/* Can we do the FOLL_ANON optimization? */
-static inline int use_zero_page(struct vm_area_struct *vma)
-{
- /*
- * We don't want to optimize FOLL_ANON for make_pages_present()
- * when it tries to page in a VM_LOCKED region. As to VM_SHARED,
- * we want to get the page from the page tables to make sure
- * that we serialize and update with any other user of that
- * mapping.
- */
- if (vma->vm_flags & (VM_LOCKED | VM_SHARED))
- return 0;
- /*
- * And if we have a fault routine, it's not an anonymous region.
- */
- return !vma->vm_ops || !vma->vm_ops->fault;
-}
-
-
-
int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
- unsigned long start, int nr_pages, int flags,
+ unsigned long start, int nr_pages, unsigned int gup_flags,
struct page **pages, struct vm_area_struct **vmas)
{
int i;
- unsigned int vm_flags = 0;
- int write = !!(flags & GUP_FLAGS_WRITE);
- int force = !!(flags & GUP_FLAGS_FORCE);
- int ignore = !!(flags & GUP_FLAGS_IGNORE_VMA_PERMISSIONS);
- int ignore_sigkill = !!(flags & GUP_FLAGS_IGNORE_SIGKILL);
+ unsigned long vm_flags;
if (nr_pages <= 0)
return 0;
+
+ VM_BUG_ON(!!pages != !!(gup_flags & FOLL_GET));
+
/*
* Require read or write permissions.
- * If 'force' is set, we only require the "MAY" flags.
+ * If FOLL_FORCE is set, we only require the "MAY" flags.
*/
- vm_flags = write ? (VM_WRITE | VM_MAYWRITE) : (VM_READ | VM_MAYREAD);
- vm_flags &= force ? (VM_MAYREAD | VM_MAYWRITE) : (VM_READ | VM_WRITE);
+ vm_flags = (gup_flags & FOLL_WRITE) ?
+ (VM_WRITE | VM_MAYWRITE) : (VM_READ | VM_MAYREAD);
+ vm_flags &= (gup_flags & FOLL_FORCE) ?
+ (VM_MAYREAD | VM_MAYWRITE) : (VM_READ | VM_WRITE);
i = 0;
do {
struct vm_area_struct *vma;
- unsigned int foll_flags;
vma = find_extend_vma(mm, start);
if (!vma && in_gate_area(tsk, start)) {
pte_t *pte;
/* user gate pages are read-only */
- if (!ignore && write)
+ if (gup_flags & FOLL_WRITE)
return i ? : -EFAULT;
if (pg > TASK_SIZE)
pgd = pgd_offset_k(pg);
if (!vma ||
(vma->vm_flags & (VM_IO | VM_PFNMAP)) ||
- (!ignore && !(vm_flags & vma->vm_flags)))
+ !(vm_flags & vma->vm_flags))
return i ? : -EFAULT;
if (is_vm_hugetlb_page(vma)) {
i = follow_hugetlb_page(mm, vma, pages, vmas,
- &start, &nr_pages, i, write);
+ &start, &nr_pages, i, gup_flags);
continue;
}
- foll_flags = FOLL_TOUCH;
- if (pages)
- foll_flags |= FOLL_GET;
- if (!write && use_zero_page(vma))
- foll_flags |= FOLL_ANON;
-
do {
struct page *page;
+ unsigned int foll_flags = gup_flags;
/*
* If we have a pending SIGKILL, don't keep faulting
- * pages and potentially allocating memory, unless
- * current is handling munlock--e.g., on exit. In
- * that case, we are not allocating memory. Rather,
- * we're only unlocking already resident/mapped pages.
+ * pages and potentially allocating memory.
*/
- if (unlikely(!ignore_sigkill &&
- fatal_signal_pending(current)))
+ if (unlikely(fatal_signal_pending(current)))
return i ? i : -ERESTARTSYS;
- if (write)
- foll_flags |= FOLL_WRITE;
-
cond_resched();
while (!(page = follow_page(vma, start, foll_flags))) {
int ret;
if (ret & VM_FAULT_ERROR) {
if (ret & VM_FAULT_OOM)
return i ? i : -ENOMEM;
- else if (ret & VM_FAULT_SIGBUS)
+ if (ret &
+ (VM_FAULT_HWPOISON|VM_FAULT_SIGBUS))
return i ? i : -EFAULT;
BUG();
}
unsigned long start, int nr_pages, int write, int force,
struct page **pages, struct vm_area_struct **vmas)
{
- int flags = 0;
+ int flags = FOLL_TOUCH;
+ if (pages)
+ flags |= FOLL_GET;
if (write)
- flags |= GUP_FLAGS_WRITE;
+ flags |= FOLL_WRITE;
if (force)
- flags |= GUP_FLAGS_FORCE;
+ flags |= FOLL_FORCE;
return __get_user_pages(tsk, mm, start, nr_pages, flags, pages, vmas);
}
-
EXPORT_SYMBOL(get_user_pages);
+/**
+ * get_dump_page() - pin user page in memory while writing it to core dump
+ * @addr: user address
+ *
+ * Returns struct page pointer of user page pinned for dump,
+ * to be freed afterwards by page_cache_release() or put_page().
+ *
+ * Returns NULL on any kind of failure - a hole must then be inserted into
+ * the corefile, to preserve alignment with its headers; and also returns
+ * NULL wherever the ZERO_PAGE, or an anonymous pte_none, has been found -
+ * allowing a hole to be left in the corefile to save diskspace.
+ *
+ * Called without mmap_sem, but after all other threads have been killed.
+ */
+#ifdef CONFIG_ELF_CORE
+struct page *get_dump_page(unsigned long addr)
+{
+ struct vm_area_struct *vma;
+ struct page *page;
+
+ if (__get_user_pages(current, current->mm, addr, 1,
+ FOLL_FORCE | FOLL_DUMP | FOLL_GET, &page, &vma) < 1)
+ return NULL;
+ flush_cache_page(vma, addr, page_to_pfn(page));
+ return page;
+}
+#endif /* CONFIG_ELF_CORE */
+
pte_t *get_locked_pte(struct mm_struct *mm, unsigned long addr,
spinlock_t **ptl)
{
* If we don't have pte special, then we have to use the pfn_valid()
* based VM_MIXEDMAP scheme (see vm_normal_page), and thus we *must*
* refcount the page if pfn_valid is true (hence insert_page rather
- * than insert_pfn).
+ * than insert_pfn). If a zero_pfn were inserted into a VM_MIXEDMAP
+ * without pte special, it would there be refcounted as a normal page.
*/
if (!HAVE_PTE_SPECIAL && pfn_valid(pfn)) {
struct page *page;
* Take out anonymous pages first, anonymous shared vmas are
* not dirty accountable.
*/
- if (PageAnon(old_page)) {
+ if (PageAnon(old_page) && !PageKsm(old_page)) {
if (!trylock_page(old_page)) {
page_cache_get(old_page);
pte_unmap_unlock(page_table, ptl);
if (unlikely(anon_vma_prepare(vma)))
goto oom;
- VM_BUG_ON(old_page == ZERO_PAGE(0));
- new_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, address);
- if (!new_page)
- goto oom;
+
+ if (is_zero_pfn(pte_pfn(orig_pte))) {
+ new_page = alloc_zeroed_user_highpage_movable(vma, address);
+ if (!new_page)
+ goto oom;
+ } else {
+ new_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, address);
+ if (!new_page)
+ goto oom;
+ cow_user_page(new_page, old_page, address, vma);
+ }
+ __SetPageUptodate(new_page);
+
/*
* Don't let another task, with possibly unlocked vma,
* keep the mlocked page.
clear_page_mlock(old_page);
unlock_page(old_page);
}
- cow_user_page(new_page, old_page, address, vma);
- __SetPageUptodate(new_page);
if (mem_cgroup_newpage_charge(new_page, mm, GFP_KERNEL))
goto oom_free_new;
* seen in the presence of one thread doing SMC and another
* thread doing COW.
*/
- ptep_clear_flush_notify(vma, address, page_table);
+ ptep_clear_flush(vma, address, page_table);
page_add_new_anon_rmap(new_page, vma, address);
- set_pte_at(mm, address, page_table, entry);
+ /*
+ * We call the notify macro here because, when using secondary
+ * mmu page tables (such as kvm shadow page tables), we want the
+ * new page to be mapped directly into the secondary page table.
+ */
+ set_pte_at_notify(mm, address, page_table, entry);
update_mmu_cache(vma, address, entry);
if (old_page) {
/*
goto out;
entry = pte_to_swp_entry(orig_pte);
- if (is_migration_entry(entry)) {
- migration_entry_wait(mm, pmd, address);
+ if (unlikely(non_swap_entry(entry))) {
+ if (is_migration_entry(entry)) {
+ migration_entry_wait(mm, pmd, address);
+ } else if (is_hwpoison_entry(entry)) {
+ ret = VM_FAULT_HWPOISON;
+ } else {
+ print_bad_pte(vma, address, orig_pte, NULL);
+ ret = VM_FAULT_OOM;
+ }
goto out;
}
delayacct_set_flag(DELAYACCT_PF_SWAPIN);
/* Had to read the page from swap area: Major fault */
ret = VM_FAULT_MAJOR;
count_vm_event(PGMAJFAULT);
+ } else if (PageHWPoison(page)) {
+ ret = VM_FAULT_HWPOISON;
+ delayacct_clear_flag(DELAYACCT_PF_SWAPIN);
+ goto out;
}
lock_page(page);
spinlock_t *ptl;
pte_t entry;
+ if (!(flags & FAULT_FLAG_WRITE)) {
+ entry = pte_mkspecial(pfn_pte(my_zero_pfn(address),
+ vma->vm_page_prot));
+ ptl = pte_lockptr(mm, pmd);
+ spin_lock(ptl);
+ if (!pte_none(*page_table))
+ goto unlock;
+ goto setpte;
+ }
+
/* Allocate our own private page. */
pte_unmap(page_table);
goto oom_free_page;
entry = mk_pte(page, vma->vm_page_prot);
- entry = maybe_mkwrite(pte_mkdirty(entry), vma);
+ if (vma->vm_flags & VM_WRITE)
+ entry = pte_mkwrite(pte_mkdirty(entry));
page_table = pte_offset_map_lock(mm, pmd, address, &ptl);
if (!pte_none(*page_table))
goto release;
+
inc_mm_counter(mm, anon_rss);
page_add_new_anon_rmap(page, vma, address);
+setpte:
set_pte_at(mm, address, page_table, entry);
/* No need to invalidate - it was non-present before */
if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE)))
return ret;
+ if (unlikely(PageHWPoison(vmf.page))) {
+ if (ret & VM_FAULT_LOCKED)
+ unlock_page(vmf.page);
+ return VM_FAULT_HWPOISON;
+ }
+
/*
* For consistency in subsequent calls, make the faulted page always
* locked.
list_for_each_entry_safe(page, page2, l, lru) {
list_del(&page->lru);
+ dec_zone_page_state(page, NR_ISOLATED_ANON +
+ page_is_file_cache(page));
putback_lru_page(page);
count++;
}
static void remove_file_migration_ptes(struct page *old, struct page *new)
{
struct vm_area_struct *vma;
- struct address_space *mapping = page_mapping(new);
+ struct address_space *mapping = new->mapping;
struct prio_tree_iter iter;
pgoff_t pgoff = new->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT);
pslot = radix_tree_lookup_slot(&mapping->page_tree,
page_index(page));
- expected_count = 2 + !!page_has_private(page);
+ expected_count = 2 + page_has_private(page);
if (page_count(page) != expected_count ||
(struct page *)radix_tree_deref_slot(pslot) != page) {
spin_unlock_irq(&mapping->tree_lock);
*/
__dec_zone_page_state(page, NR_FILE_PAGES);
__inc_zone_page_state(newpage, NR_FILE_PAGES);
-
+ if (PageSwapBacked(page)) {
+ __dec_zone_page_state(page, NR_SHMEM);
+ __inc_zone_page_state(newpage, NR_SHMEM);
+ }
spin_unlock_irq(&mapping->tree_lock);
return 0;
* needs to be effective.
*/
try_to_free_buffers(page);
+ goto rcu_unlock;
}
- goto rcu_unlock;
+ goto skip_unmap;
}
/* Establish migration ptes or remove ptes */
- try_to_unmap(page, 1);
+ try_to_unmap(page, TTU_MIGRATION|TTU_IGNORE_MLOCK|TTU_IGNORE_ACCESS);
+skip_unmap:
if (!page_mapped(page))
rc = move_to_new_page(newpage, page);
* restored.
*/
list_del(&page->lru);
+ dec_zone_page_state(page, NR_ISOLATED_ANON +
+ page_is_file_cache(page));
putback_lru_page(page);
}
struct page *page2;
int swapwrite = current->flags & PF_SWAPWRITE;
int rc;
+ unsigned long flags;
+
+ local_irq_save(flags);
+ list_for_each_entry(page, from, lru)
+ __inc_zone_page_state(page, NR_ISOLATED_ANON +
+ page_is_file_cache(page));
+ local_irq_restore(flags);
if (!swapwrite)
current->flags |= PF_SWAPWRITE;
}
int dirty_background_ratio_handler(struct ctl_table *table, int write,
- struct file *filp, void __user *buffer, size_t *lenp,
+ void __user *buffer, size_t *lenp,
loff_t *ppos)
{
int ret;
- ret = proc_dointvec_minmax(table, write, filp, buffer, lenp, ppos);
+ ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
if (ret == 0 && write)
dirty_background_bytes = 0;
return ret;
}
int dirty_background_bytes_handler(struct ctl_table *table, int write,
- struct file *filp, void __user *buffer, size_t *lenp,
+ void __user *buffer, size_t *lenp,
loff_t *ppos)
{
int ret;
- ret = proc_doulongvec_minmax(table, write, filp, buffer, lenp, ppos);
+ ret = proc_doulongvec_minmax(table, write, buffer, lenp, ppos);
if (ret == 0 && write)
dirty_background_ratio = 0;
return ret;
}
int dirty_ratio_handler(struct ctl_table *table, int write,
- struct file *filp, void __user *buffer, size_t *lenp,
+ void __user *buffer, size_t *lenp,
loff_t *ppos)
{
int old_ratio = vm_dirty_ratio;
int ret;
- ret = proc_dointvec_minmax(table, write, filp, buffer, lenp, ppos);
+ ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos);
if (ret == 0 && write && vm_dirty_ratio != old_ratio) {
update_completion_period();
vm_dirty_bytes = 0;
int dirty_bytes_handler(struct ctl_table *table, int write,
- struct file *filp, void __user *buffer, size_t *lenp,
+ void __user *buffer, size_t *lenp,
loff_t *ppos)
{
unsigned long old_bytes = vm_dirty_bytes;
int ret;
- ret = proc_doulongvec_minmax(table, write, filp, buffer, lenp, ppos);
+ ret = proc_doulongvec_minmax(table, write, buffer, lenp, ppos);
if (ret == 0 && write && vm_dirty_bytes != old_bytes) {
update_completion_period();
vm_dirty_ratio = 0;
{
int ret = 0;
- spin_lock(&bdi_lock);
+ spin_lock_bh(&bdi_lock);
if (min_ratio > bdi->max_ratio) {
ret = -EINVAL;
} else {
ret = -EINVAL;
}
}
- spin_unlock(&bdi_lock);
+ spin_unlock_bh(&bdi_lock);
return ret;
}
if (max_ratio > 100)
return -EINVAL;
- spin_lock(&bdi_lock);
+ spin_lock_bh(&bdi_lock);
if (bdi->min_ratio > max_ratio) {
ret = -EINVAL;
} else {
bdi->max_ratio = max_ratio;
bdi->max_prop_frac = (PROP_FRAC_BASE * max_ratio) / 100;
}
- spin_unlock(&bdi_lock);
+ spin_unlock_bh(&bdi_lock);
return ret;
}
struct zone *z =
&NODE_DATA(node)->node_zones[ZONE_HIGHMEM];
- x += zone_page_state(z, NR_FREE_PAGES) + zone_lru_pages(z);
+ x += zone_page_state(z, NR_FREE_PAGES) +
+ zone_reclaimable_pages(z);
}
/*
* Make sure that the number of highmem pages is never larger
{
unsigned long x;
- x = global_page_state(NR_FREE_PAGES) + global_lru_pages();
+ x = global_page_state(NR_FREE_PAGES) + global_reclaimable_pages();
if (!vm_highmem_is_dirtyable)
x -= highmem_dirtyable_memory(x);
unsigned long bdi_thresh;
unsigned long pages_written = 0;
unsigned long write_chunk = sync_writeback_pages();
+ unsigned long pause = 1;
struct backing_dev_info *bdi = mapping->backing_dev_info;
if (pages_written >= write_chunk)
break; /* We've done our duty */
- schedule_timeout(1);
+ schedule_timeout_interruptible(pause);
+
+ /*
+ * Increase the delay for each loop, up to our previous
+ * default of taking a 100ms nap.
+ */
+ pause <<= 1;
+ if (pause > HZ / 10)
+ pause = HZ / 10;
}
if (bdi_nr_reclaimable + bdi_nr_writeback < bdi_thresh &&
if ((laptop_mode && pages_written) ||
(!laptop_mode && ((nr_writeback = global_page_state(NR_FILE_DIRTY)
+ global_page_state(NR_UNSTABLE_NFS))
- > background_thresh))) {
- struct writeback_control wbc = {
- .bdi = bdi,
- .sync_mode = WB_SYNC_NONE,
- .nr_to_write = nr_writeback,
- };
-
-
- bdi_start_writeback(&wbc);
- }
+ > background_thresh)))
+ bdi_start_writeback(bdi, nr_writeback);
}
void set_page_dirty_balance(struct page *page, int page_mkwrite)
* sysctl handler for /proc/sys/vm/dirty_writeback_centisecs
*/
int dirty_writeback_centisecs_handler(ctl_table *table, int write,
- struct file *file, void __user *buffer, size_t *length, loff_t *ppos)
+ void __user *buffer, size_t *length, loff_t *ppos)
{
- proc_dointvec(table, write, file, buffer, length, ppos);
+ proc_dointvec(table, write, buffer, length, ppos);
return 0;
}
if (wbc->nr_to_write <= 0)
return 0;
- wbc->for_writepages = 1;
if (mapping->a_ops->writepages)
ret = mapping->a_ops->writepages(mapping, wbc);
else
ret = generic_writepages(mapping, wbc);
- wbc->for_writepages = 0;
return ret;
}
EXPORT_SYMBOL(redirty_page_for_writepage);
/*
+ * Dirty a page.
+ *
+ * For pages with a mapping this should be done under the page lock
+ * for the benefit of asynchronous memory errors who prefer a consistent
+ * dirty state. This rule can be broken in some special cases,
+ * but should be better not to.
+ *
* If the mapping doesn't provide a set_page_dirty a_op, then
* just fall through and assume that it wants buffer_heads.
*/
#include <linux/page_cgroup.h>
#include <linux/debugobjects.h>
#include <linux/kmemleak.h>
+#include <trace/events/kmem.h>
#include <asm/tlbflush.h>
#include <asm/div64.h>
unsigned long totalram_pages __read_mostly;
unsigned long totalreserve_pages __read_mostly;
-unsigned long highest_memmap_pfn __read_mostly;
int percpu_pagelist_fraction;
gfp_t gfp_allowed_mask __read_mostly = GFP_BOOT_MASK;
int min_free_kbytes = 1024;
-unsigned long __meminitdata nr_kernel_pages;
-unsigned long __meminitdata nr_all_pages;
+static unsigned long __meminitdata nr_kernel_pages;
+static unsigned long __meminitdata nr_all_pages;
static unsigned long __meminitdata dma_reserve;
#ifdef CONFIG_ARCH_POPULATES_NODE_MAP
static unsigned long nr_shown;
static unsigned long nr_unshown;
+ /* Don't complain about poisoned pages */
+ if (PageHWPoison(page)) {
+ __ClearPageBuddy(page);
+ return;
+ }
+
/*
* Allow a burst of 60 reports, then keep quiet for that minute;
* or allow a steady drip of one report per second.
}
/*
- * Frees a list of pages.
+ * Frees a number of pages from the PCP lists
* Assumes all pages on list are in same zone, and of same order.
* count is the number of pages to free.
*
* And clear the zone's pages_scanned counter, to hold off the "all pages are
* pinned" detection logic.
*/
-static void free_pages_bulk(struct zone *zone, int count,
- struct list_head *list, int order)
+static void free_pcppages_bulk(struct zone *zone, int count,
+ struct per_cpu_pages *pcp)
{
+ int migratetype = 0;
+ int batch_free = 0;
+
spin_lock(&zone->lock);
zone_clear_flag(zone, ZONE_ALL_UNRECLAIMABLE);
zone->pages_scanned = 0;
- __mod_zone_page_state(zone, NR_FREE_PAGES, count << order);
- while (count--) {
+ __mod_zone_page_state(zone, NR_FREE_PAGES, count);
+ while (count) {
struct page *page;
+ struct list_head *list;
- VM_BUG_ON(list_empty(list));
- page = list_entry(list->prev, struct page, lru);
- /* have to delete it as __free_one_page list manipulates */
- list_del(&page->lru);
- __free_one_page(page, zone, order, page_private(page));
+ /*
+ * Remove pages from lists in a round-robin fashion. A
+ * batch_free count is maintained that is incremented when an
+ * empty list is encountered. This is so more pages are freed
+ * off fuller lists instead of spinning excessively around empty
+ * lists
+ */
+ do {
+ batch_free++;
+ if (++migratetype == MIGRATE_PCPTYPES)
+ migratetype = 0;
+ list = &pcp->lists[migratetype];
+ } while (list_empty(list));
+
+ do {
+ page = list_entry(list->prev, struct page, lru);
+ /* must delete as __free_one_page list manipulates */
+ list_del(&page->lru);
+ __free_one_page(page, zone, 0, migratetype);
+ trace_mm_page_pcpu_drain(page, 0, migratetype);
+ } while (--count && --batch_free && !list_empty(list));
}
spin_unlock(&zone->lock);
}
unsigned long flags;
int i;
int bad = 0;
- int wasMlocked = TestClearPageMlocked(page);
+ int wasMlocked = __TestClearPageMlocked(page);
kmemcheck_free_shadow(page, order);
/*
* This page is about to be returned from the page allocator
*/
- static int prep_new_page(struct page *page, int order, gfp_t gfp_flags)
+ static inline int check_new_page(struct page *page)
{
if (unlikely(page_mapcount(page) |
(page->mapping != NULL) |
bad_page(page);
return 1;
}
+ return 0;
+ }
+
+ static int prep_new_page(struct page *page, int order, gfp_t gfp_flags)
+ {
+ int i;
+
+ for (i = 0; i < (1 << order); i++) {
+ struct page *p = page + i;
+ if (unlikely(check_new_page(p)))
+ return 1;
+ }
set_page_private(page, 0);
set_page_refcounted(page);
return move_freepages(zone, start_page, end_page, migratetype);
}
+static void change_pageblock_range(struct page *pageblock_page,
+ int start_order, int migratetype)
+{
+ int nr_pageblocks = 1 << (start_order - pageblock_order);
+
+ while (nr_pageblocks--) {
+ set_pageblock_migratetype(pageblock_page, migratetype);
+ pageblock_page += pageblock_nr_pages;
+ }
+}
+
/* Remove an element from the buddy allocator from the fallback list */
static inline struct page *
__rmqueue_fallback(struct zone *zone, int order, int start_migratetype)
list_del(&page->lru);
rmv_page_order(page);
- if (current_order == pageblock_order)
- set_pageblock_migratetype(page,
+ /* Take ownership for orders >= pageblock_order */
+ if (current_order >= pageblock_order)
+ change_pageblock_range(page, current_order,
start_migratetype);
expand(zone, page, order, current_order, area, migratetype);
+
+ trace_mm_page_alloc_extfrag(page, order, current_order,
+ start_migratetype, migratetype);
+
return page;
}
}
}
}
+ trace_mm_page_alloc_zone_locked(page, order, migratetype);
return page;
}
to_drain = pcp->batch;
else
to_drain = pcp->count;
- free_pages_bulk(zone, to_drain, &pcp->list, 0);
+ free_pcppages_bulk(zone, to_drain, pcp);
pcp->count -= to_drain;
local_irq_restore(flags);
}
pcp = &pset->pcp;
local_irq_save(flags);
- free_pages_bulk(zone, pcp->count, &pcp->list, 0);
+ free_pcppages_bulk(zone, pcp->count, pcp);
pcp->count = 0;
local_irq_restore(flags);
}
struct zone *zone = page_zone(page);
struct per_cpu_pages *pcp;
unsigned long flags;
- int wasMlocked = TestClearPageMlocked(page);
+ int migratetype;
+ int wasMlocked = __TestClearPageMlocked(page);
kmemcheck_free_shadow(page, 0);
kernel_map_pages(page, 1, 0);
pcp = &zone_pcp(zone, get_cpu())->pcp;
- set_page_private(page, get_pageblock_migratetype(page));
+ migratetype = get_pageblock_migratetype(page);
+ set_page_private(page, migratetype);
local_irq_save(flags);
if (unlikely(wasMlocked))
free_page_mlock(page);
__count_vm_event(PGFREE);
+ /*
+ * We only track unmovable, reclaimable and movable on pcp lists.
+ * Free ISOLATE pages back to the allocator because they are being
+ * offlined but treat RESERVE as movable pages so we can get those
+ * areas back if necessary. Otherwise, we may have to free
+ * excessively into the page allocator
+ */
+ if (migratetype >= MIGRATE_PCPTYPES) {
+ if (unlikely(migratetype == MIGRATE_ISOLATE)) {
+ free_one_page(zone, page, 0, migratetype);
+ goto out;
+ }
+ migratetype = MIGRATE_MOVABLE;
+ }
+
if (cold)
- list_add_tail(&page->lru, &pcp->list);
+ list_add_tail(&page->lru, &pcp->lists[migratetype]);
else
- list_add(&page->lru, &pcp->list);
+ list_add(&page->lru, &pcp->lists[migratetype]);
pcp->count++;
if (pcp->count >= pcp->high) {
- free_pages_bulk(zone, pcp->batch, &pcp->list, 0);
+ free_pcppages_bulk(zone, pcp->batch, pcp);
pcp->count -= pcp->batch;
}
+
+out:
local_irq_restore(flags);
put_cpu();
}
void free_hot_page(struct page *page)
{
+ trace_mm_page_free_direct(page, 0);
free_hot_cold_page(page, 0);
}
-void free_cold_page(struct page *page)
-{
- free_hot_cold_page(page, 1);
-}
-
/*
* split_page takes a non-compound higher-order page, and splits it into
* n (1<<order) sub-pages: page[0..n]
cpu = get_cpu();
if (likely(order == 0)) {
struct per_cpu_pages *pcp;
+ struct list_head *list;
pcp = &zone_pcp(zone, cpu)->pcp;
+ list = &pcp->lists[migratetype];
local_irq_save(flags);
- if (!pcp->count) {
- pcp->count = rmqueue_bulk(zone, 0,
- pcp->batch, &pcp->list,
+ if (list_empty(list)) {
+ pcp->count += rmqueue_bulk(zone, 0,
+ pcp->batch, list,
migratetype, cold);
- if (unlikely(!pcp->count))
+ if (unlikely(list_empty(list)))
goto failed;
}
- /* Find a page of the appropriate migrate type */
- if (cold) {
- list_for_each_entry_reverse(page, &pcp->list, lru)
- if (page_private(page) == migratetype)
- break;
- } else {
- list_for_each_entry(page, &pcp->list, lru)
- if (page_private(page) == migratetype)
- break;
- }
-
- /* Allocate more to the pcp list if necessary */
- if (unlikely(&page->lru == &pcp->list)) {
- pcp->count += rmqueue_bulk(zone, 0,
- pcp->batch, &pcp->list,
- migratetype, cold);
- page = list_entry(pcp->list.next, struct page, lru);
- }
+ if (cold)
+ page = list_entry(list->prev, struct page, lru);
+ else
+ page = list_entry(list->next, struct page, lru);
list_del(&page->lru);
pcp->count--;
/* We now go into synchronous reclaim */
cpuset_memory_pressure_bump();
-
- /*
- * The task's cpuset might have expanded its set of allowable nodes
- */
p->flags |= PF_MEMALLOC;
lockdep_set_current_reclaim_state(gfp_mask);
reclaim_state.reclaimed_slab = 0;
wake_all_kswapd(order, zonelist, high_zoneidx);
+restart:
/*
* OK, we're below the kswapd watermark and have kicked background
* reclaim. Now things get more complex, so set up alloc_flags according
*/
alloc_flags = gfp_to_alloc_flags(gfp_mask);
-restart:
/* This is the last chance, in general, before the goto nopage. */
page = get_page_from_freelist(gfp_mask, nodemask, order, zonelist,
high_zoneidx, alloc_flags & ~ALLOC_NO_WATERMARKS,
zonelist, high_zoneidx, nodemask,
preferred_zone, migratetype);
+ trace_mm_page_alloc(page, order, gfp_mask, migratetype);
return page;
}
EXPORT_SYMBOL(__alloc_pages_nodemask);
*/
unsigned long __get_free_pages(gfp_t gfp_mask, unsigned int order)
{
- struct page * page;
+ struct page *page;
+
+ /*
+ * __get_free_pages() returns a 32-bit address, which cannot represent
+ * a highmem page
+ */
+ VM_BUG_ON((gfp_mask & __GFP_HIGHMEM) != 0);
+
page = alloc_pages(gfp_mask, order);
if (!page)
return 0;
return (unsigned long) page_address(page);
}
-
EXPORT_SYMBOL(__get_free_pages);
unsigned long get_zeroed_page(gfp_t gfp_mask)
{
- struct page * page;
-
- /*
- * get_zeroed_page() returns a 32-bit address, which cannot represent
- * a highmem page
- */
- VM_BUG_ON((gfp_mask & __GFP_HIGHMEM) != 0);
-
- page = alloc_pages(gfp_mask | __GFP_ZERO, 0);
- if (page)
- return (unsigned long) page_address(page);
- return 0;
+ return __get_free_pages(gfp_mask | __GFP_ZERO, 0);
}
-
EXPORT_SYMBOL(get_zeroed_page);
void __pagevec_free(struct pagevec *pvec)
{
int i = pagevec_count(pvec);
- while (--i >= 0)
+ while (--i >= 0) {
+ trace_mm_pagevec_free(pvec->pages[i], pvec->cold);
free_hot_cold_page(pvec->pages[i], pvec->cold);
+ }
}
void __free_pages(struct page *page, unsigned int order)
{
if (put_page_testzero(page)) {
+ trace_mm_page_free_direct(page, order);
if (order == 0)
free_hot_page(page);
else
}
}
- printk("Active_anon:%lu active_file:%lu inactive_anon:%lu\n"
- " inactive_file:%lu"
+ printk("active_anon:%lu inactive_anon:%lu isolated_anon:%lu\n"
+ " active_file:%lu inactive_file:%lu isolated_file:%lu\n"
" unevictable:%lu"
- " dirty:%lu writeback:%lu unstable:%lu\n"
- " free:%lu slab:%lu mapped:%lu pagetables:%lu bounce:%lu\n",
+ " dirty:%lu writeback:%lu unstable:%lu buffer:%lu\n"
+ " free:%lu slab_reclaimable:%lu slab_unreclaimable:%lu\n"
+ " mapped:%lu shmem:%lu pagetables:%lu bounce:%lu\n",
global_page_state(NR_ACTIVE_ANON),
- global_page_state(NR_ACTIVE_FILE),
global_page_state(NR_INACTIVE_ANON),
+ global_page_state(NR_ISOLATED_ANON),
+ global_page_state(NR_ACTIVE_FILE),
global_page_state(NR_INACTIVE_FILE),
+ global_page_state(NR_ISOLATED_FILE),
global_page_state(NR_UNEVICTABLE),
global_page_state(NR_FILE_DIRTY),
global_page_state(NR_WRITEBACK),
global_page_state(NR_UNSTABLE_NFS),
+ nr_blockdev_pages(),
global_page_state(NR_FREE_PAGES),
- global_page_state(NR_SLAB_RECLAIMABLE) +
- global_page_state(NR_SLAB_UNRECLAIMABLE),
+ global_page_state(NR_SLAB_RECLAIMABLE),
+ global_page_state(NR_SLAB_UNRECLAIMABLE),
global_page_state(NR_FILE_MAPPED),
+ global_page_state(NR_SHMEM),
global_page_state(NR_PAGETABLE),
global_page_state(NR_BOUNCE));
" active_file:%lukB"
" inactive_file:%lukB"
" unevictable:%lukB"
+ " isolated(anon):%lukB"
+ " isolated(file):%lukB"
" present:%lukB"
+ " mlocked:%lukB"
+ " dirty:%lukB"
+ " writeback:%lukB"
+ " mapped:%lukB"
+ " shmem:%lukB"
+ " slab_reclaimable:%lukB"
+ " slab_unreclaimable:%lukB"
+ " kernel_stack:%lukB"
+ " pagetables:%lukB"
+ " unstable:%lukB"
+ " bounce:%lukB"
+ " writeback_tmp:%lukB"
" pages_scanned:%lu"
" all_unreclaimable? %s"
"\n",
K(zone_page_state(zone, NR_ACTIVE_FILE)),
K(zone_page_state(zone, NR_INACTIVE_FILE)),
K(zone_page_state(zone, NR_UNEVICTABLE)),
+ K(zone_page_state(zone, NR_ISOLATED_ANON)),
+ K(zone_page_state(zone, NR_ISOLATED_FILE)),
K(zone->present_pages),
+ K(zone_page_state(zone, NR_MLOCK)),
+ K(zone_page_state(zone, NR_FILE_DIRTY)),
+ K(zone_page_state(zone, NR_WRITEBACK)),
+ K(zone_page_state(zone, NR_FILE_MAPPED)),
+ K(zone_page_state(zone, NR_SHMEM)),
+ K(zone_page_state(zone, NR_SLAB_RECLAIMABLE)),
+ K(zone_page_state(zone, NR_SLAB_UNRECLAIMABLE)),
+ zone_page_state(zone, NR_KERNEL_STACK) *
+ THREAD_SIZE / 1024,
+ K(zone_page_state(zone, NR_PAGETABLE)),
+ K(zone_page_state(zone, NR_UNSTABLE_NFS)),
+ K(zone_page_state(zone, NR_BOUNCE)),
+ K(zone_page_state(zone, NR_WRITEBACK_TEMP)),
zone->pages_scanned,
(zone_is_all_unreclaimable(zone) ? "yes" : "no")
);
* sysctl handler for numa_zonelist_order
*/
int numa_zonelist_order_handler(ctl_table *table, int write,
- struct file *file, void __user *buffer, size_t *length,
+ void __user *buffer, size_t *length,
loff_t *ppos)
{
char saved_string[NUMA_ZONELIST_ORDER_LEN];
if (write)
strncpy(saved_string, (char*)table->data,
NUMA_ZONELIST_ORDER_LEN);
- ret = proc_dostring(table, write, file, buffer, length, ppos);
+ ret = proc_dostring(table, write, buffer, length, ppos);
if (ret)
return ret;
if (write) {
{
unsigned long start_pfn, pfn, end_pfn;
struct page *page;
- unsigned long reserve, block_migratetype;
+ unsigned long block_migratetype;
+ int reserve;
/* Get the start pfn, end pfn and the number of blocks to reserve */
start_pfn = zone->zone_start_pfn;
reserve = roundup(min_wmark_pages(zone), pageblock_nr_pages) >>
pageblock_order;
+ /*
+ * Reserve blocks are generally in place to help high-order atomic
+ * allocations that are short-lived. A min_free_kbytes value that
+ * would result in more than 2 reserve blocks for atomic allocations
+ * is assumed to be in place to help anti-fragmentation for the
+ * future allocation of hugepages at runtime.
+ */
+ reserve = min(2, reserve);
+
for (pfn = start_pfn; pfn < end_pfn; pfn += pageblock_nr_pages) {
if (!pfn_valid(pfn))
continue;
static void setup_pageset(struct per_cpu_pageset *p, unsigned long batch)
{
struct per_cpu_pages *pcp;
+ int migratetype;
memset(p, 0, sizeof(*p));
pcp->count = 0;
pcp->high = 6 * batch;
pcp->batch = max(1UL, 1 * batch);
- INIT_LIST_HEAD(&pcp->list);
+ for (migratetype = 0; migratetype < MIGRATE_PCPTYPES; migratetype++)
+ INIT_LIST_HEAD(&pcp->lists[migratetype]);
}
/*
return 0;
}
+static int __zone_pcp_update(void *data)
+{
+ struct zone *zone = data;
+ int cpu;
+ unsigned long batch = zone_batchsize(zone), flags;
+
+ for (cpu = 0; cpu < NR_CPUS; cpu++) {
+ struct per_cpu_pageset *pset;
+ struct per_cpu_pages *pcp;
+
+ pset = zone_pcp(zone, cpu);
+ pcp = &pset->pcp;
+
+ local_irq_save(flags);
+ free_pcppages_bulk(zone, pcp->count, pcp);
+ setup_pageset(pset, batch);
+ local_irq_restore(flags);
+ }
+ return 0;
+}
+
+void zone_pcp_update(struct zone *zone)
+{
+ stop_machine(__zone_pcp_update, zone, NULL);
+}
+
static __meminit void zone_pcp_init(struct zone *zone)
{
int cpu;
zone_pcp_init(zone);
for_each_lru(l) {
INIT_LIST_HEAD(&zone->lru[l].list);
- zone->lru[l].nr_saved_scan = 0;
+ zone->reclaim_stat.nr_saved_scan[l] = 0;
}
zone->reclaim_stat.recent_rotated[0] = 0;
zone->reclaim_stat.recent_rotated[1] = 0;
calculate_totalreserve_pages();
}
-/**
+/*
* The inactive anon list should be small enough that the VM never has to
* do too much work, but large enough that each inactive page has a chance
* to be referenced again before it is swapped out.
* changes.
*/
int min_free_kbytes_sysctl_handler(ctl_table *table, int write,
- struct file *file, void __user *buffer, size_t *length, loff_t *ppos)
+ void __user *buffer, size_t *length, loff_t *ppos)
{
- proc_dointvec(table, write, file, buffer, length, ppos);
+ proc_dointvec(table, write, buffer, length, ppos);
if (write)
setup_per_zone_wmarks();
return 0;
#ifdef CONFIG_NUMA
int sysctl_min_unmapped_ratio_sysctl_handler(ctl_table *table, int write,
- struct file *file, void __user *buffer, size_t *length, loff_t *ppos)
+ void __user *buffer, size_t *length, loff_t *ppos)
{
struct zone *zone;
int rc;
- rc = proc_dointvec_minmax(table, write, file, buffer, length, ppos);
+ rc = proc_dointvec_minmax(table, write, buffer, length, ppos);
if (rc)
return rc;
}
int sysctl_min_slab_ratio_sysctl_handler(ctl_table *table, int write,
- struct file *file, void __user *buffer, size_t *length, loff_t *ppos)
+ void __user *buffer, size_t *length, loff_t *ppos)
{
struct zone *zone;
int rc;
- rc = proc_dointvec_minmax(table, write, file, buffer, length, ppos);
+ rc = proc_dointvec_minmax(table, write, buffer, length, ppos);
if (rc)
return rc;
* if in function of the boot time zone sizes.
*/
int lowmem_reserve_ratio_sysctl_handler(ctl_table *table, int write,
- struct file *file, void __user *buffer, size_t *length, loff_t *ppos)
+ void __user *buffer, size_t *length, loff_t *ppos)
{
- proc_dointvec_minmax(table, write, file, buffer, length, ppos);
+ proc_dointvec_minmax(table, write, buffer, length, ppos);
setup_per_zone_lowmem_reserve();
return 0;
}
*/
int percpu_pagelist_fraction_sysctl_handler(ctl_table *table, int write,
- struct file *file, void __user *buffer, size_t *length, loff_t *ppos)
+ void __user *buffer, size_t *length, loff_t *ppos)
{
struct zone *zone;
unsigned int cpu;
int ret;
- ret = proc_dointvec_minmax(table, write, file, buffer, length, ppos);
+ ret = proc_dointvec_minmax(table, write, buffer, length, ppos);
if (!write || (ret == -EINVAL))
return ret;
for_each_populated_zone(zone) {
numentries <<= (PAGE_SHIFT - scale);
/* Make sure we've got at least a 0-order allocation.. */
- if (unlikely((numentries * bucketsize) < PAGE_SIZE))
+ if (unlikely(flags & HASH_SMALL)) {
+ /* Makes no sense without HASH_EARLY */
+ WARN_ON(!(flags & HASH_EARLY));
+ if (!(numentries >> *_hash_shift)) {
+ numentries = 1UL << *_hash_shift;
+ BUG_ON(!numentries);
+ }
+ } else if (unlikely((numentries * bucketsize) < PAGE_SIZE))
numentries = PAGE_SIZE / bucketsize;
}
numentries = roundup_pow_of_two(numentries);
struct zone *zone;
unsigned long flags;
int ret = -EBUSY;
+ int zone_idx;
zone = page_zone(page);
+ zone_idx = zone_idx(zone);
spin_lock_irqsave(&zone->lock, flags);
/*
* In future, more migrate types will be able to be isolation target.
*/
- if (get_pageblock_migratetype(page) != MIGRATE_MOVABLE)
+ if (get_pageblock_migratetype(page) != MIGRATE_MOVABLE &&
+ zone_idx != ZONE_MOVABLE)
goto out;
set_pageblock_migratetype(page, MIGRATE_ISOLATE);
move_freepages_block(zone, page, MIGRATE_ISOLATE);
* mapping->tree_lock (widely used, in set_page_dirty,
* in arch-dependent flush_dcache_mmap_lock,
* within inode_lock in __sync_single_inode)
+ *
+ * (code doesn't rely on that order so it could be switched around)
+ * ->tasklist_lock
+ * anon_vma->lock (memory_failure, collect_procs_anon)
+ * pte map lock
*/
#include <linux/mm.h>
* Getting a lock on a stable anon_vma from a page off the LRU is
* tricky: page_lock_anon_vma rely on RCU to guard against the races.
*/
- static struct anon_vma *page_lock_anon_vma(struct page *page)
+ struct anon_vma *page_lock_anon_vma(struct page *page)
{
struct anon_vma *anon_vma;
unsigned long anon_mapping;
return NULL;
}
- static void page_unlock_anon_vma(struct anon_vma *anon_vma)
+ void page_unlock_anon_vma(struct anon_vma *anon_vma)
{
spin_unlock(&anon_vma->lock);
rcu_read_unlock();
* if the page is not mapped into the page tables of this VMA. Only
* valid for normal file or anonymous VMAs.
*/
- static int page_mapped_in_vma(struct page *page, struct vm_area_struct *vma)
+ int page_mapped_in_vma(struct page *page, struct vm_area_struct *vma)
{
unsigned long address;
pte_t *pte;
}
}
-#ifdef CONFIG_DEBUG_VM
-/**
- * page_dup_rmap - duplicate pte mapping to a page
- * @page: the page to add the mapping to
- * @vma: the vm area being duplicated
- * @address: the user virtual address mapped
- *
- * For copy_page_range only: minimal extract from page_add_file_rmap /
- * page_add_anon_rmap, avoiding unnecessary tests (already checked) so it's
- * quicker.
- *
- * The caller needs to hold the pte lock.
- */
-void page_dup_rmap(struct page *page, struct vm_area_struct *vma, unsigned long address)
-{
- if (PageAnon(page))
- __page_check_anon_rmap(page, vma, address);
- atomic_inc(&page->_mapcount);
-}
-#endif
-
/**
* page_remove_rmap - take down pte mapping from a page
* @page: page to remove mapping from
*/
void page_remove_rmap(struct page *page)
{
- if (atomic_add_negative(-1, &page->_mapcount)) {
- /*
- * Now that the last pte has gone, s390 must transfer dirty
- * flag from storage key to struct page. We can usually skip
- * this if the page is anon, so about to be freed; but perhaps
- * not if it's in swapcache - there might be another pte slot
- * containing the swap entry, but page not yet written to swap.
- */
- if ((!PageAnon(page) || PageSwapCache(page)) &&
- page_test_dirty(page)) {
- page_clear_dirty(page);
- set_page_dirty(page);
- }
- if (PageAnon(page))
- mem_cgroup_uncharge_page(page);
- __dec_zone_page_state(page,
- PageAnon(page) ? NR_ANON_PAGES : NR_FILE_MAPPED);
- mem_cgroup_update_mapped_file_stat(page, -1);
- /*
- * It would be tidy to reset the PageAnon mapping here,
- * but that might overwrite a racing page_add_anon_rmap
- * which increments mapcount after us but sets mapping
- * before us: so leave the reset to free_hot_cold_page,
- * and remember that it's only reliable while mapped.
- * Leaving it set also helps swapoff to reinstate ptes
- * faster for those pages still in swapcache.
- */
+ /* page still mapped by someone else? */
+ if (!atomic_add_negative(-1, &page->_mapcount))
+ return;
+
+ /*
+ * Now that the last pte has gone, s390 must transfer dirty
+ * flag from storage key to struct page. We can usually skip
+ * this if the page is anon, so about to be freed; but perhaps
+ * not if it's in swapcache - there might be another pte slot
+ * containing the swap entry, but page not yet written to swap.
+ */
+ if ((!PageAnon(page) || PageSwapCache(page)) && page_test_dirty(page)) {
+ page_clear_dirty(page);
+ set_page_dirty(page);
+ }
+ if (PageAnon(page)) {
+ mem_cgroup_uncharge_page(page);
+ __dec_zone_page_state(page, NR_ANON_PAGES);
+ } else {
+ __dec_zone_page_state(page, NR_FILE_MAPPED);
}
+ mem_cgroup_update_mapped_file_stat(page, -1);
+ /*
+ * It would be tidy to reset the PageAnon mapping here,
+ * but that might overwrite a racing page_add_anon_rmap
+ * which increments mapcount after us but sets mapping
+ * before us: so leave the reset to free_hot_cold_page,
+ * and remember that it's only reliable while mapped.
+ * Leaving it set also helps swapoff to reinstate ptes
+ * faster for those pages still in swapcache.
+ */
}
/*
* repeatedly from either try_to_unmap_anon or try_to_unmap_file.
*/
static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
- int migration)
+ enum ttu_flags flags)
{
struct mm_struct *mm = vma->vm_mm;
unsigned long address;
* If it's recently referenced (perhaps page_referenced
* skipped over this mm) then we should reactivate it.
*/
- if (!migration) {
+ if (!(flags & TTU_IGNORE_MLOCK)) {
if (vma->vm_flags & VM_LOCKED) {
ret = SWAP_MLOCK;
goto out_unmap;
}
+ }
+ if (!(flags & TTU_IGNORE_ACCESS)) {
if (ptep_clear_flush_young_notify(vma, address, pte)) {
ret = SWAP_FAIL;
goto out_unmap;
/* Update high watermark before we lower rss */
update_hiwater_rss(mm);
- if (PageAnon(page)) {
+ if (PageHWPoison(page) && !(flags & TTU_IGNORE_HWPOISON)) {
+ if (PageAnon(page))
+ dec_mm_counter(mm, anon_rss);
+ else
+ dec_mm_counter(mm, file_rss);
+ set_pte_at(mm, address, pte,
+ swp_entry_to_pte(make_hwpoison_entry(page)));
+ } else if (PageAnon(page)) {
swp_entry_t entry = { .val = page_private(page) };
if (PageSwapCache(page)) {
* pte. do_swap_page() will wait until the migration
* pte is removed and then restart fault handling.
*/
- BUG_ON(!migration);
+ BUG_ON(TTU_ACTION(flags) != TTU_MIGRATION);
entry = make_migration_entry(page, pte_write(pteval));
}
set_pte_at(mm, address, pte, swp_entry_to_pte(entry));
BUG_ON(pte_file(*pte));
- } else if (PAGE_MIGRATION && migration) {
+ } else if (PAGE_MIGRATION && (TTU_ACTION(flags) == TTU_MIGRATION)) {
/* Establish migration entry for a file page */
swp_entry_t entry;
entry = make_migration_entry(page, pte_write(pteval));
* vm_flags for that VMA. That should be OK, because that vma shouldn't be
* 'LOCKED.
*/
- static int try_to_unmap_anon(struct page *page, int unlock, int migration)
+ static int try_to_unmap_anon(struct page *page, enum ttu_flags flags)
{
struct anon_vma *anon_vma;
struct vm_area_struct *vma;
unsigned int mlocked = 0;
int ret = SWAP_AGAIN;
+ int unlock = TTU_ACTION(flags) == TTU_MUNLOCK;
if (MLOCK_PAGES && unlikely(unlock))
ret = SWAP_SUCCESS; /* default for try_to_munlock() */
continue; /* must visit all unlocked vmas */
ret = SWAP_MLOCK; /* saw at least one mlocked vma */
} else {
- ret = try_to_unmap_one(page, vma, migration);
+ ret = try_to_unmap_one(page, vma, flags);
if (ret == SWAP_FAIL || !page_mapped(page))
break;
}
/**
* try_to_unmap_file - unmap/unlock file page using the object-based rmap method
* @page: the page to unmap/unlock
- * @unlock: request for unlock rather than unmap [unlikely]
- * @migration: unmapping for migration - ignored if @unlock
+ * @flags: action and flags
*
* Find all the mappings of a page using the mapping pointer and the vma chains
* contained in the address_space struct it points to.
* vm_flags for that VMA. That should be OK, because that vma shouldn't be
* 'LOCKED.
*/
- static int try_to_unmap_file(struct page *page, int unlock, int migration)
+ static int try_to_unmap_file(struct page *page, enum ttu_flags flags)
{
struct address_space *mapping = page->mapping;
pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT);
unsigned long max_nl_size = 0;
unsigned int mapcount;
unsigned int mlocked = 0;
+ int unlock = TTU_ACTION(flags) == TTU_MUNLOCK;
if (MLOCK_PAGES && unlikely(unlock))
ret = SWAP_SUCCESS; /* default for try_to_munlock() */
continue; /* must visit all vmas */
ret = SWAP_MLOCK;
} else {
- ret = try_to_unmap_one(page, vma, migration);
+ ret = try_to_unmap_one(page, vma, flags);
if (ret == SWAP_FAIL || !page_mapped(page))
goto out;
}
ret = SWAP_MLOCK; /* leave mlocked == 0 */
goto out; /* no need to look further */
}
- if (!MLOCK_PAGES && !migration && (vma->vm_flags & VM_LOCKED))
+ if (!MLOCK_PAGES && !(flags & TTU_IGNORE_MLOCK) &&
+ (vma->vm_flags & VM_LOCKED))
continue;
cursor = (unsigned long) vma->vm_private_data;
if (cursor > max_nl_cursor)
do {
list_for_each_entry(vma, &mapping->i_mmap_nonlinear,
shared.vm_set.list) {
- if (!MLOCK_PAGES && !migration &&
+ if (!MLOCK_PAGES && !(flags & TTU_IGNORE_MLOCK) &&
(vma->vm_flags & VM_LOCKED))
continue;
cursor = (unsigned long) vma->vm_private_data;
/**
* try_to_unmap - try to remove all page table mappings to a page
* @page: the page to get unmapped
- * @migration: migration flag
+ * @flags: action and flags
*
* Tries to remove all the page table entries which are mapping this
* page, used in the pageout path. Caller must hold the page lock.
* SWAP_FAIL - the page is unswappable
* SWAP_MLOCK - page is mlocked.
*/
- int try_to_unmap(struct page *page, int migration)
+ int try_to_unmap(struct page *page, enum ttu_flags flags)
{
int ret;
BUG_ON(!PageLocked(page));
if (PageAnon(page))
- ret = try_to_unmap_anon(page, 0, migration);
+ ret = try_to_unmap_anon(page, flags);
else
- ret = try_to_unmap_file(page, 0, migration);
+ ret = try_to_unmap_file(page, flags);
if (ret != SWAP_MLOCK && !page_mapped(page))
ret = SWAP_SUCCESS;
return ret;
VM_BUG_ON(!PageLocked(page) || PageLRU(page));
if (PageAnon(page))
- return try_to_unmap_anon(page, 1, 0);
+ return try_to_unmap_anon(page, TTU_MUNLOCK);
else
- return try_to_unmap_file(page, 1, 0);
+ return try_to_unmap_file(page, TTU_MUNLOCK);
}
#include <linux/backing-dev.h>
#include <linux/shmem_fs.h>
#include <linux/writeback.h>
-#include <linux/vfs.h>
#include <linux/blkdev.h>
#include <linux/security.h>
#include <linux/swapops.h>
shmem_swp_unmap(entry);
unlock:
spin_unlock(&info->lock);
+ /*
+ * add_to_swap_cache() doesn't return -EEXIST, so we can safely
+ * clear SWAP_HAS_CACHE flag.
+ */
swapcache_free(swap, NULL);
redirty:
set_page_dirty(page);
if (pos + copied > inode->i_size)
i_size_write(inode, pos + copied);
- unlock_page(page);
set_page_dirty(page);
+ unlock_page(page);
page_cache_release(page);
return copied;
iput(inode);
return error;
}
- unlock_page(page);
inode->i_mapping->a_ops = &shmem_aops;
inode->i_op = &shmem_symlink_inode_operations;
kaddr = kmap_atomic(page, KM_USER0);
memcpy(kaddr, symname, len);
kunmap_atomic(kaddr, KM_USER0);
set_page_dirty(page);
+ unlock_page(page);
page_cache_release(page);
}
if (dir->i_mode & S_ISGID)
sb->s_fs_info = NULL;
}
-static int shmem_fill_super(struct super_block *sb,
- void *data, int silent)
+int shmem_fill_super(struct super_block *sb, void *data, int silent)
{
struct inode *inode;
struct dentry *root;
int err = -ENOMEM;
/* Round up to L1_CACHE_BYTES to resist false sharing */
- sbinfo = kmalloc(max((int)sizeof(struct shmem_sb_info),
+ sbinfo = kzalloc(max((int)sizeof(struct shmem_sb_info),
L1_CACHE_BYTES), GFP_KERNEL);
if (!sbinfo)
return -ENOMEM;
- sbinfo->max_blocks = 0;
- sbinfo->max_inodes = 0;
sbinfo->mode = S_IRWXUGO | S_ISVTX;
sbinfo->uid = current_fsuid();
sbinfo->gid = current_fsgid();
- sbinfo->mpol = NULL;
sb->s_fs_info = sbinfo;
#ifdef CONFIG_TMPFS
.write_end = shmem_write_end,
#endif
.migratepage = migrate_page,
+ .error_remove_page = generic_error_remove_page,
};
static const struct file_operations shmem_file_operations = {
.kill_sb = kill_litter_super,
};
-static int __init init_tmpfs(void)
+int __init init_tmpfs(void)
{
int error;
.kill_sb = kill_litter_super,
};
-static int __init init_tmpfs(void)
+int __init init_tmpfs(void)
{
BUG_ON(register_filesystem(&tmpfs_fs_type) != 0);
return 0;
}
+int shmem_lock(struct file *file, int lock, struct user_struct *user)
+{
+ return 0;
+}
+
#define shmem_vm_ops generic_file_vm_ops
#define shmem_file_operations ramfs_file_operations
#define shmem_get_inode(sb, mode, dev, flags) ramfs_get_inode(sb, mode, dev)
vma->vm_ops = &shmem_vm_ops;
return 0;
}
-
-module_init(init_tmpfs)
struct swap_info_struct *p;
struct page *page = NULL;
- if (is_migration_entry(entry))
+ if (non_swap_entry(entry))
return 1;
p = swap_info_get(entry);
p->flags &= ~SWP_WRITEOK;
spin_unlock(&swap_lock);
- current->flags |= PF_SWAPOFF;
+ current->flags |= PF_OOM_ORIGIN;
err = try_to_unuse(type);
- current->flags &= ~PF_SWAPOFF;
+ current->flags &= ~PF_OOM_ORIGIN;
if (err) {
/* re-insert swap space back into swap_list */
int count;
bool has_cache;
- if (is_migration_entry(entry))
+ if (non_swap_entry(entry))
return -EINVAL;
type = swp_type(entry);
return &zone->reclaim_stat;
}
-static unsigned long zone_nr_pages(struct zone *zone, struct scan_control *sc,
- enum lru_list lru)
+static unsigned long zone_nr_lru_pages(struct zone *zone,
+ struct scan_control *sc, enum lru_list lru)
{
if (!scanning_global_lru(sc))
return mem_cgroup_zone_nr_pages(sc->mem_cgroup, zone, lru);
static inline int is_page_cache_freeable(struct page *page)
{
- return page_count(page) - !!page_has_private(page) == 2;
+ /*
+ * A freeable page cache page is referenced only by the caller
+ * that isolated the page, the page cache radix tree and
+ * optional buffer heads at page->private.
+ */
+ return page_count(page) - page_has_private(page) == 2;
}
static int may_write_to_queue(struct backing_dev_info *bdi)
* block, for some throttling. This happens by accident, because
* swap_backing_dev_info is bust: it doesn't reflect the
* congestion state of the swapdevs. Easy to fix, if needed.
- * See swapfile.c:page_queue_congested().
*/
if (!is_page_cache_freeable(page))
return PAGE_KEEP;
* unevictable page on [in]active list.
* We know how to handle that.
*/
- lru = active + page_is_file_cache(page);
+ lru = active + page_lru_base_type(page);
lru_cache_add_lru(page, lru);
} else {
/*
* processes. Try to unmap it here.
*/
if (page_mapped(page) && mapping) {
- switch (try_to_unmap(page, 0)) {
+ switch (try_to_unmap(page, TTU_UNMAP)) {
case SWAP_FAIL:
goto activate_locked;
case SWAP_AGAIN:
if (mode != ISOLATE_BOTH && (!PageActive(page) != !mode))
return ret;
- if (mode != ISOLATE_BOTH && (!page_is_file_cache(page) != !file))
+ if (mode != ISOLATE_BOTH && page_is_file_cache(page) != file)
return ret;
/*
/* Check that we have not crossed a zone boundary. */
if (unlikely(page_zone_id(cursor_page) != zone_id))
continue;
+
+ /*
+ * If we don't have enough swap space, reclaiming of
+ * anon page which don't already have a swap slot is
+ * pointless.
+ */
+ if (nr_swap_pages <= 0 && PageAnon(cursor_page) &&
+ !PageSwapCache(cursor_page))
+ continue;
+
if (__isolate_lru_page(cursor_page, mode, file) == 0) {
list_move(&cursor_page->lru, dst);
mem_cgroup_del_lru(cursor_page);
if (file)
lru += LRU_FILE;
return isolate_lru_pages(nr, &z->lru[lru].list, dst, scanned, order,
- mode, !!file);
+ mode, file);
}
/*
struct page *page;
list_for_each_entry(page, page_list, lru) {
- lru = page_is_file_cache(page);
+ lru = page_lru_base_type(page);
if (PageActive(page)) {
lru += LRU_ACTIVE;
ClearPageActive(page);
return ret;
}
+/*
+ * Are there way too many processes in the direct reclaim path already?
+ */
+static int too_many_isolated(struct zone *zone, int file,
+ struct scan_control *sc)
+{
+ unsigned long inactive, isolated;
+
+ if (current_is_kswapd())
+ return 0;
+
+ if (!scanning_global_lru(sc))
+ return 0;
+
+ if (file) {
+ inactive = zone_page_state(zone, NR_INACTIVE_FILE);
+ isolated = zone_page_state(zone, NR_ISOLATED_FILE);
+ } else {
+ inactive = zone_page_state(zone, NR_INACTIVE_ANON);
+ isolated = zone_page_state(zone, NR_ISOLATED_ANON);
+ }
+
+ return isolated > inactive;
+}
+
/*
* shrink_inactive_list() is a helper for shrink_zone(). It returns the number
* of reclaimed pages
struct zone_reclaim_stat *reclaim_stat = get_reclaim_stat(zone, sc);
int lumpy_reclaim = 0;
+ while (unlikely(too_many_isolated(zone, file, sc))) {
+ congestion_wait(WRITE, HZ/10);
+
+ /* We are about to die and free our memory. Return now. */
+ if (fatal_signal_pending(current))
+ return SWAP_CLUSTER_MAX;
+ }
+
/*
* If we need a large contiguous chunk of memory, or have
* trouble getting a small set of contiguous pages, we
unsigned long nr_active;
unsigned int count[NR_LRU_LISTS] = { 0, };
int mode = lumpy_reclaim ? ISOLATE_BOTH : ISOLATE_INACTIVE;
+ unsigned long nr_anon;
+ unsigned long nr_file;
nr_taken = sc->isolate_pages(sc->swap_cluster_max,
&page_list, &nr_scan, sc->order, mode,
zone, sc->mem_cgroup, 0, file);
+
+ if (scanning_global_lru(sc)) {
+ zone->pages_scanned += nr_scan;
+ if (current_is_kswapd())
+ __count_zone_vm_events(PGSCAN_KSWAPD, zone,
+ nr_scan);
+ else
+ __count_zone_vm_events(PGSCAN_DIRECT, zone,
+ nr_scan);
+ }
+
+ if (nr_taken == 0)
+ goto done;
+
nr_active = clear_active_flags(&page_list, count);
__count_vm_events(PGDEACTIVATE, nr_active);
__mod_zone_page_state(zone, NR_INACTIVE_ANON,
-count[LRU_INACTIVE_ANON]);
- if (scanning_global_lru(sc))
- zone->pages_scanned += nr_scan;
+ nr_anon = count[LRU_ACTIVE_ANON] + count[LRU_INACTIVE_ANON];
+ nr_file = count[LRU_ACTIVE_FILE] + count[LRU_INACTIVE_FILE];
+ __mod_zone_page_state(zone, NR_ISOLATED_ANON, nr_anon);
+ __mod_zone_page_state(zone, NR_ISOLATED_FILE, nr_file);
reclaim_stat->recent_scanned[0] += count[LRU_INACTIVE_ANON];
reclaim_stat->recent_scanned[0] += count[LRU_ACTIVE_ANON];
}
nr_reclaimed += nr_freed;
+
local_irq_disable();
- if (current_is_kswapd()) {
- __count_zone_vm_events(PGSCAN_KSWAPD, zone, nr_scan);
+ if (current_is_kswapd())
__count_vm_events(KSWAPD_STEAL, nr_freed);
- } else if (scanning_global_lru(sc))
- __count_zone_vm_events(PGSCAN_DIRECT, zone, nr_scan);
-
__count_zone_vm_events(PGSTEAL, zone, nr_freed);
- if (nr_taken == 0)
- goto done;
-
spin_lock(&zone->lru_lock);
/*
* Put back any unfreeable pages.
SetPageLRU(page);
lru = page_lru(page);
add_page_to_lru_list(zone, page, lru);
- if (PageActive(page)) {
- int file = !!page_is_file_cache(page);
+ if (is_active_lru(lru)) {
+ int file = is_file_lru(lru);
reclaim_stat->recent_rotated[file]++;
}
if (!pagevec_add(&pvec, page)) {
spin_lock_irq(&zone->lru_lock);
}
}
+ __mod_zone_page_state(zone, NR_ISOLATED_ANON, -nr_anon);
+ __mod_zone_page_state(zone, NR_ISOLATED_FILE, -nr_file);
+
} while (nr_scanned < max_scan);
- spin_unlock(&zone->lru_lock);
+
done:
- local_irq_enable();
+ spin_unlock_irq(&zone->lru_lock);
pagevec_release(&pvec);
return nr_reclaimed;
}
while (!list_empty(list)) {
page = lru_to_page(list);
- prefetchw_prev_lru_page(page, list, flags);
VM_BUG_ON(PageLRU(page));
SetPageLRU(page);
- VM_BUG_ON(!PageActive(page));
- if (!is_active_lru(lru))
- ClearPageActive(page); /* we are de-activating */
-
list_move(&page->lru, &zone->lru[lru].list);
mem_cgroup_add_lru_list(page, lru);
pgmoved++;
static void shrink_active_list(unsigned long nr_pages, struct zone *zone,
struct scan_control *sc, int priority, int file)
{
- unsigned long pgmoved;
+ unsigned long nr_taken;
unsigned long pgscanned;
unsigned long vm_flags;
LIST_HEAD(l_hold); /* The pages which were snipped off */
LIST_HEAD(l_inactive);
struct page *page;
struct zone_reclaim_stat *reclaim_stat = get_reclaim_stat(zone, sc);
+ unsigned long nr_rotated = 0;
lru_add_drain();
spin_lock_irq(&zone->lru_lock);
- pgmoved = sc->isolate_pages(nr_pages, &l_hold, &pgscanned, sc->order,
+ nr_taken = sc->isolate_pages(nr_pages, &l_hold, &pgscanned, sc->order,
ISOLATE_ACTIVE, zone,
sc->mem_cgroup, 1, file);
/*
if (scanning_global_lru(sc)) {
zone->pages_scanned += pgscanned;
}
- reclaim_stat->recent_scanned[!!file] += pgmoved;
+ reclaim_stat->recent_scanned[file] += nr_taken;
__count_zone_vm_events(PGREFILL, zone, pgscanned);
if (file)
- __mod_zone_page_state(zone, NR_ACTIVE_FILE, -pgmoved);
+ __mod_zone_page_state(zone, NR_ACTIVE_FILE, -nr_taken);
else
- __mod_zone_page_state(zone, NR_ACTIVE_ANON, -pgmoved);
+ __mod_zone_page_state(zone, NR_ACTIVE_ANON, -nr_taken);
+ __mod_zone_page_state(zone, NR_ISOLATED_ANON + file, nr_taken);
spin_unlock_irq(&zone->lru_lock);
- pgmoved = 0; /* count referenced (mapping) mapped pages */
while (!list_empty(&l_hold)) {
cond_resched();
page = lru_to_page(&l_hold);
/* page_referenced clears PageReferenced */
if (page_mapping_inuse(page) &&
page_referenced(page, 0, sc->mem_cgroup, &vm_flags)) {
- pgmoved++;
+ nr_rotated++;
/*
* Identify referenced, file-backed active pages and
* give them one more trip around the active list. So
}
}
+ ClearPageActive(page); /* we are de-activating */
list_add(&page->lru, &l_inactive);
}
* helps balance scan pressure between file and anonymous pages in
* get_scan_ratio.
*/
- reclaim_stat->recent_rotated[!!file] += pgmoved;
+ reclaim_stat->recent_rotated[file] += nr_rotated;
move_active_pages_to_lru(zone, &l_active,
LRU_ACTIVE + file * LRU_FILE);
move_active_pages_to_lru(zone, &l_inactive,
LRU_BASE + file * LRU_FILE);
-
+ __mod_zone_page_state(zone, NR_ISOLATED_ANON + file, -nr_taken);
spin_unlock_irq(&zone->lru_lock);
}
unsigned long ap, fp;
struct zone_reclaim_stat *reclaim_stat = get_reclaim_stat(zone, sc);
- anon = zone_nr_pages(zone, sc, LRU_ACTIVE_ANON) +
- zone_nr_pages(zone, sc, LRU_INACTIVE_ANON);
- file = zone_nr_pages(zone, sc, LRU_ACTIVE_FILE) +
- zone_nr_pages(zone, sc, LRU_INACTIVE_FILE);
+ anon = zone_nr_lru_pages(zone, sc, LRU_ACTIVE_ANON) +
+ zone_nr_lru_pages(zone, sc, LRU_INACTIVE_ANON);
+ file = zone_nr_lru_pages(zone, sc, LRU_ACTIVE_FILE) +
+ zone_nr_lru_pages(zone, sc, LRU_INACTIVE_FILE);
if (scanning_global_lru(sc)) {
free = zone_page_state(zone, NR_FREE_PAGES);
enum lru_list l;
unsigned long nr_reclaimed = sc->nr_reclaimed;
unsigned long swap_cluster_max = sc->swap_cluster_max;
+ struct zone_reclaim_stat *reclaim_stat = get_reclaim_stat(zone, sc);
int noswap = 0;
/* If we have no swap space, do not bother scanning anon pages. */
int file = is_file_lru(l);
unsigned long scan;
- scan = zone_nr_pages(zone, sc, l);
+ scan = zone_nr_lru_pages(zone, sc, l);
if (priority || noswap) {
scan >>= priority;
scan = (scan * percent[file]) / 100;
}
- if (scanning_global_lru(sc))
- nr[l] = nr_scan_try_batch(scan,
- &zone->lru[l].nr_saved_scan,
- swap_cluster_max);
- else
- nr[l] = scan;
+ nr[l] = nr_scan_try_batch(scan,
+ &reclaim_stat->nr_saved_scan[l],
+ swap_cluster_max);
}
while (nr[LRU_INACTIVE_ANON] || nr[LRU_ACTIVE_FILE] ||
if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL))
continue;
- lru_pages += zone_lru_pages(zone);
+ lru_pages += zone_reclaimable_pages(zone);
}
}
#ifdef CONFIG_CGROUP_MEM_RES_CTLR
+unsigned long mem_cgroup_shrink_node_zone(struct mem_cgroup *mem,
+ gfp_t gfp_mask, bool noswap,
+ unsigned int swappiness,
+ struct zone *zone, int nid)
+{
+ struct scan_control sc = {
+ .may_writepage = !laptop_mode,
+ .may_unmap = 1,
+ .may_swap = !noswap,
+ .swap_cluster_max = SWAP_CLUSTER_MAX,
+ .swappiness = swappiness,
+ .order = 0,
+ .mem_cgroup = mem,
+ .isolate_pages = mem_cgroup_isolate_pages,
+ };
+ nodemask_t nm = nodemask_of_node(nid);
+
+ sc.gfp_mask = (gfp_mask & GFP_RECLAIM_MASK) |
+ (GFP_HIGHUSER_MOVABLE & ~GFP_RECLAIM_MASK);
+ sc.nodemask = &nm;
+ sc.nr_reclaimed = 0;
+ sc.nr_scanned = 0;
+ /*
+ * NOTE: Although we can get the priority field, using it
+ * here is not a good idea, since it limits the pages we can scan.
+ * if we don't reclaim here, the shrink_zone from balance_pgdat
+ * will pick up pages from other mem cgroup's as well. We hack
+ * the priority and make it zero.
+ */
+ shrink_zone(0, zone, &sc);
+ return sc.nr_reclaimed;
+}
+
unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *mem_cont,
gfp_t gfp_mask,
bool noswap,
unsigned int swappiness)
{
+ struct zonelist *zonelist;
struct scan_control sc = {
.may_writepage = !laptop_mode,
.may_unmap = 1,
.isolate_pages = mem_cgroup_isolate_pages,
.nodemask = NULL, /* we don't care the placement */
};
- struct zonelist *zonelist;
sc.gfp_mask = (gfp_mask & GFP_RECLAIM_MASK) |
(GFP_HIGHUSER_MOVABLE & ~GFP_RECLAIM_MASK);
for (i = 0; i <= end_zone; i++) {
struct zone *zone = pgdat->node_zones + i;
- lru_pages += zone_lru_pages(zone);
+ lru_pages += zone_reclaimable_pages(zone);
}
/*
for (i = 0; i <= end_zone; i++) {
struct zone *zone = pgdat->node_zones + i;
int nr_slab;
+ int nid, zid;
if (!populated_zone(zone))
continue;
temp_priority[i] = priority;
sc.nr_scanned = 0;
note_zone_scanning_priority(zone, priority);
+
+ nid = pgdat->node_id;
+ zid = zone_idx(zone);
+ /*
+ * Call soft limit reclaim before calling shrink_zone.
+ * For now we ignore the return value
+ */
+ mem_cgroup_soft_limit_reclaim(zone, order, sc.gfp_mask,
+ nid, zid);
/*
* We put equal pressure on every zone, unless one
* zone has way too many pages free already.
if (zone_is_all_unreclaimable(zone))
continue;
if (nr_slab == 0 && zone->pages_scanned >=
- (zone_lru_pages(zone) * 6))
+ (zone_reclaimable_pages(zone) * 6))
zone_set_flag(zone,
ZONE_ALL_UNRECLAIMABLE);
/*
wake_up_interruptible(&pgdat->kswapd_wait);
}
-unsigned long global_lru_pages(void)
+/*
+ * The reclaimable count would be mostly accurate.
+ * The less reclaimable pages may be
+ * - mlocked pages, which will be moved to unevictable list when encountered
+ * - mapped pages, which may require several travels to be reclaimed
+ * - dirty pages, which is not "instantly" reclaimable
+ */
+unsigned long global_reclaimable_pages(void)
+{
+ int nr;
+
+ nr = global_page_state(NR_ACTIVE_FILE) +
+ global_page_state(NR_INACTIVE_FILE);
+
+ if (nr_swap_pages > 0)
+ nr += global_page_state(NR_ACTIVE_ANON) +
+ global_page_state(NR_INACTIVE_ANON);
+
+ return nr;
+}
+
+unsigned long zone_reclaimable_pages(struct zone *zone)
{
- return global_page_state(NR_ACTIVE_ANON)
- + global_page_state(NR_ACTIVE_FILE)
- + global_page_state(NR_INACTIVE_ANON)
- + global_page_state(NR_INACTIVE_FILE);
+ int nr;
+
+ nr = zone_page_state(zone, NR_ACTIVE_FILE) +
+ zone_page_state(zone, NR_INACTIVE_FILE);
+
+ if (nr_swap_pages > 0)
+ nr += zone_page_state(zone, NR_ACTIVE_ANON) +
+ zone_page_state(zone, NR_INACTIVE_ANON);
+
+ return nr;
}
#ifdef CONFIG_HIBERNATION
{
struct zone *zone;
unsigned long nr_reclaimed = 0;
+ struct zone_reclaim_stat *reclaim_stat;
for_each_populated_zone(zone) {
enum lru_list l;
l == LRU_ACTIVE_FILE))
continue;
- zone->lru[l].nr_saved_scan += (lru_pages >> prio) + 1;
- if (zone->lru[l].nr_saved_scan >= nr_pages || pass > 3) {
+ reclaim_stat = get_reclaim_stat(zone, sc);
+ reclaim_stat->nr_saved_scan[l] +=
+ (lru_pages >> prio) + 1;
+ if (reclaim_stat->nr_saved_scan[l]
+ >= nr_pages || pass > 3) {
unsigned long nr_to_scan;
- zone->lru[l].nr_saved_scan = 0;
+ reclaim_stat->nr_saved_scan[l] = 0;
nr_to_scan = min(nr_pages, lru_pages);
nr_reclaimed += shrink_list(l, nr_to_scan, zone,
sc, prio);
current->reclaim_state = &reclaim_state;
- lru_pages = global_lru_pages();
+ lru_pages = global_reclaimable_pages();
nr_slab = global_page_state(NR_SLAB_RECLAIMABLE);
/* If slab caches are huge, it's better to hit them first */
while (nr_slab >= lru_pages) {
reclaim_state.reclaimed_slab = 0;
shrink_slab(sc.nr_scanned, sc.gfp_mask,
- global_lru_pages());
+ global_reclaimable_pages());
sc.nr_reclaimed += reclaim_state.reclaimed_slab;
if (sc.nr_reclaimed >= nr_pages)
goto out;
if (!sc.nr_reclaimed) {
do {
reclaim_state.reclaimed_slab = 0;
- shrink_slab(nr_pages, sc.gfp_mask, global_lru_pages());
+ shrink_slab(nr_pages, sc.gfp_mask,
+ global_reclaimable_pages());
sc.nr_reclaimed += reclaim_state.reclaimed_slab;
} while (sc.nr_reclaimed < nr_pages &&
reclaim_state.reclaimed_slab > 0);
retry:
ClearPageUnevictable(page);
if (page_evictable(page, NULL)) {
- enum lru_list l = LRU_INACTIVE_ANON + page_is_file_cache(page);
+ enum lru_list l = page_lru_base_type(page);
__dec_zone_state(zone, NR_UNEVICTABLE);
list_move(&page->lru, &zone->lru[l].list);
unsigned long scan_unevictable_pages;
int scan_unevictable_handler(struct ctl_table *table, int write,
- struct file *file, void __user *buffer,
+ void __user *buffer,
size_t *length, loff_t *ppos)
{
- proc_doulongvec_minmax(table, write, file, buffer, length, ppos);
+ proc_doulongvec_minmax(table, write, buffer, length, ppos);
if (write && *(unsigned long *)table->data)
scan_all_zones_unevictable_pages();