summaryrefslogtreecommitdiff
path: root/Documentation
diff options
context:
space:
mode:
authorIngo Molnar <mingo@elte.hu>2011-01-05 14:14:42 +0100
committerIngo Molnar <mingo@elte.hu>2011-01-05 14:14:46 +0100
commit27066fd484a32c80630136aa2b91c980f3198f9d (patch)
tree78ddabdedbfd7525d13ecd62a745525843f1d0e8 /Documentation
parent101e5f77bf35679809586e250b6c62193d2ed179 (diff)
parent3c0eee3fe6a3a1c745379547c7e7c904aa64f6d5 (diff)
Merge commit 'v2.6.37' into sched/core
Merge reason: Merge the final .37 tree. Signed-off-by: Ingo Molnar <mingo@elte.hu>
Diffstat (limited to 'Documentation')
-rw-r--r--Documentation/accounting/getdelays.c1
-rw-r--r--Documentation/filesystems/Locking212
-rw-r--r--Documentation/kernel-parameters.txt7
-rw-r--r--Documentation/power/runtime_pm.txt4
-rw-r--r--Documentation/scsi/scsi_mid_low_api.txt59
-rw-r--r--Documentation/trace/postprocess/trace-vmscan-postprocess.pl11
6 files changed, 145 insertions, 149 deletions
diff --git a/Documentation/accounting/getdelays.c b/Documentation/accounting/getdelays.c
index a2976a6de033..e9c77788a39d 100644
--- a/Documentation/accounting/getdelays.c
+++ b/Documentation/accounting/getdelays.c
@@ -516,6 +516,7 @@ int main(int argc, char *argv[])
default:
fprintf(stderr, "Unknown nla_type %d\n",
na->nla_type);
+ case TASKSTATS_TYPE_NULL:
break;
}
na = (struct nlattr *) (GENLMSG_DATA(&msg) + len);
diff --git a/Documentation/filesystems/Locking b/Documentation/filesystems/Locking
index b6426f15b4ae..33fa3e5d38fd 100644
--- a/Documentation/filesystems/Locking
+++ b/Documentation/filesystems/Locking
@@ -18,7 +18,6 @@ prototypes:
char *(*d_dname)((struct dentry *dentry, char *buffer, int buflen);
locking rules:
- none have BKL
dcache_lock rename_lock ->d_lock may block
d_revalidate: no no no yes
d_hash no no no yes
@@ -42,18 +41,23 @@ ata *);
int (*rename) (struct inode *, struct dentry *,
struct inode *, struct dentry *);
int (*readlink) (struct dentry *, char __user *,int);
- int (*follow_link) (struct dentry *, struct nameidata *);
+ void * (*follow_link) (struct dentry *, struct nameidata *);
+ void (*put_link) (struct dentry *, struct nameidata *, void *);
void (*truncate) (struct inode *);
int (*permission) (struct inode *, int, struct nameidata *);
+ int (*check_acl)(struct inode *, int);
int (*setattr) (struct dentry *, struct iattr *);
int (*getattr) (struct vfsmount *, struct dentry *, struct kstat *);
int (*setxattr) (struct dentry *, const char *,const void *,size_t,int);
ssize_t (*getxattr) (struct dentry *, const char *, void *, size_t);
ssize_t (*listxattr) (struct dentry *, char *, size_t);
int (*removexattr) (struct dentry *, const char *);
+ void (*truncate_range)(struct inode *, loff_t, loff_t);
+ long (*fallocate)(struct inode *inode, int mode, loff_t offset, loff_t len);
+ int (*fiemap)(struct inode *, struct fiemap_extent_info *, u64 start, u64 len);
locking rules:
- all may block, none have BKL
+ all may block
i_mutex(inode)
lookup: yes
create: yes
@@ -66,19 +70,24 @@ rmdir: yes (both) (see below)
rename: yes (all) (see below)
readlink: no
follow_link: no
+put_link: no
truncate: yes (see below)
setattr: yes
permission: no
+check_acl: no
getattr: no
setxattr: yes
getxattr: no
listxattr: no
removexattr: yes
+truncate_range: yes
+fallocate: no
+fiemap: no
Additionally, ->rmdir(), ->unlink() and ->rename() have ->i_mutex on
victim.
cross-directory ->rename() has (per-superblock) ->s_vfs_rename_sem.
->truncate() is never called directly - it's a callback, not a
-method. It's called by vmtruncate() - library function normally used by
+method. It's called by vmtruncate() - deprecated library function used by
->setattr(). Locking information above applies to that call (i.e. is
inherited from ->setattr() - vmtruncate() is used when ATTR_SIZE had been
passed).
@@ -91,7 +100,7 @@ prototypes:
struct inode *(*alloc_inode)(struct super_block *sb);
void (*destroy_inode)(struct inode *);
void (*dirty_inode) (struct inode *);
- int (*write_inode) (struct inode *, int);
+ int (*write_inode) (struct inode *, struct writeback_control *wbc);
int (*drop_inode) (struct inode *);
void (*evict_inode) (struct inode *);
void (*put_super) (struct super_block *);
@@ -105,10 +114,10 @@ prototypes:
int (*show_options)(struct seq_file *, struct vfsmount *);
ssize_t (*quota_read)(struct super_block *, int, char *, size_t, loff_t);
ssize_t (*quota_write)(struct super_block *, int, const char *, size_t, loff_t);
+ int (*bdev_try_to_free_page)(struct super_block*, struct page*, gfp_t);
locking rules:
All may block [not true, see below]
- None have BKL
s_umount
alloc_inode:
destroy_inode:
@@ -127,6 +136,7 @@ umount_begin: no
show_options: no (namespace_sem)
quota_read: no (see below)
quota_write: no (see below)
+bdev_try_to_free_page: no (see below)
->statfs() has s_umount (shared) when called by ustat(2) (native or
compat), but that's an accident of bad API; s_umount is used to pin
@@ -139,19 +149,25 @@ be the only ones operating on the quota file by the quota code (via
dqio_sem) (unless an admin really wants to screw up something and
writes to quota files with quotas on). For other details about locking
see also dquot_operations section.
+->bdev_try_to_free_page is called from the ->releasepage handler of
+the block device inode. See there for more details.
--------------------------- file_system_type ---------------------------
prototypes:
int (*get_sb) (struct file_system_type *, int,
const char *, void *, struct vfsmount *);
+ struct dentry *(*mount) (struct file_system_type *, int,
+ const char *, void *);
void (*kill_sb) (struct super_block *);
locking rules:
- may block BKL
-get_sb yes no
-kill_sb yes no
+ may block
+get_sb yes
+mount yes
+kill_sb yes
->get_sb() returns error or 0 with locked superblock attached to the vfsmount
(exclusive on ->s_umount).
+->mount() returns ERR_PTR or the root dentry.
->kill_sb() takes a write-locked superblock, does all shutdown work on it,
unlocks and drops the reference.
@@ -176,27 +192,35 @@ prototypes:
void (*freepage)(struct page *);
int (*direct_IO)(int, struct kiocb *, const struct iovec *iov,
loff_t offset, unsigned long nr_segs);
- int (*launder_page) (struct page *);
+ int (*get_xip_mem)(struct address_space *, pgoff_t, int, void **,
+ unsigned long *);
+ int (*migratepage)(struct address_space *, struct page *, struct page *);
+ 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 *);
locking rules:
All except set_page_dirty and freepage may block
- BKL PageLocked(page) i_mutex
-writepage: no yes, unlocks (see below)
-readpage: no yes, unlocks
-sync_page: no maybe
-writepages: no
-set_page_dirty no no
-readpages: no
-write_begin: no locks the page yes
-write_end: no yes, unlocks yes
-perform_write: no n/a yes
-bmap: no
-invalidatepage: no yes
-releasepage: no yes
-freepage: no yes
-direct_IO: no
-launder_page: no yes
+ PageLocked(page) i_mutex
+writepage: yes, unlocks (see below)
+readpage: yes, unlocks
+sync_page: maybe
+writepages:
+set_page_dirty no
+readpages:
+write_begin: locks the page yes
+write_end: yes, unlocks yes
+bmap:
+invalidatepage: yes
+releasepage: yes
+freepage: yes
+direct_IO:
+get_xip_mem: maybe
+migratepage: yes (both)
+launder_page: yes
+is_partially_uptodate: yes
+error_remove_page: yes
->write_begin(), ->write_end(), ->sync_page() and ->readpage()
may be called from the request handler (/dev/loop).
@@ -276,9 +300,8 @@ under spinlock (it cannot block) and is sometimes called with the page
not locked.
->bmap() is currently used by legacy ioctl() (FIBMAP) provided by some
-filesystems and by the swapper. The latter will eventually go away. All
-instances do not actually need the BKL. Please, keep it that way and don't
-breed new callers.
+filesystems and by the swapper. The latter will eventually go away. Please,
+keep it that way and don't breed new callers.
->invalidatepage() is called when the filesystem must attempt to drop
some or all of the buffers from the page when it is being truncated. It
@@ -299,47 +322,37 @@ cleaned, or an error value if not. Note that in order to prevent the page
getting mapped back in and redirtied, it needs to be kept locked
across the entire operation.
- Note: currently almost all instances of address_space methods are
-using BKL for internal serialization and that's one of the worst sources
-of contention. Normally they are calling library functions (in fs/buffer.c)
-and pass foo_get_block() as a callback (on local block-based filesystems,
-indeed). BKL is not needed for library stuff and is usually taken by
-foo_get_block(). It's an overkill, since block bitmaps can be protected by
-internal fs locking and real critical areas are much smaller than the areas
-filesystems protect now.
-
----------------------- file_lock_operations ------------------------------
prototypes:
- void (*fl_insert)(struct file_lock *); /* lock insertion callback */
- void (*fl_remove)(struct file_lock *); /* lock removal callback */
void (*fl_copy_lock)(struct file_lock *, struct file_lock *);
void (*fl_release_private)(struct file_lock *);
locking rules:
- BKL may block
-fl_insert: yes no
-fl_remove: yes no
-fl_copy_lock: yes no
-fl_release_private: yes yes
+ file_lock_lock may block
+fl_copy_lock: yes no
+fl_release_private: maybe no
----------------------- lock_manager_operations ---------------------------
prototypes:
int (*fl_compare_owner)(struct file_lock *, struct file_lock *);
void (*fl_notify)(struct file_lock *); /* unblock callback */
+ int (*fl_grant)(struct file_lock *, struct file_lock *, int);
void (*fl_release_private)(struct file_lock *);
void (*fl_break)(struct file_lock *); /* break_lease callback */
+ int (*fl_mylease)(struct file_lock *, struct file_lock *);
+ int (*fl_change)(struct file_lock **, int);
locking rules:
- BKL may block
-fl_compare_owner: yes no
-fl_notify: yes no
-fl_release_private: yes yes
-fl_break: yes no
-
- Currently only NFSD and NLM provide instances of this class. None of the
-them block. If you have out-of-tree instances - please, show up. Locking
-in that area will change.
+ file_lock_lock may block
+fl_compare_owner: yes no
+fl_notify: yes no
+fl_grant: no no
+fl_release_private: maybe no
+fl_break: yes no
+fl_mylease: yes no
+fl_change yes no
+
--------------------------- buffer_head -----------------------------------
prototypes:
void (*b_end_io)(struct buffer_head *bh, int uptodate);
@@ -364,17 +377,17 @@ prototypes:
void (*swap_slot_free_notify) (struct block_device *, unsigned long);
locking rules:
- BKL bd_mutex
-open: no yes
-release: no yes
-ioctl: no no
-compat_ioctl: no no
-direct_access: no no
-media_changed: no no
-unlock_native_capacity: no no
-revalidate_disk: no no
-getgeo: no no
-swap_slot_free_notify: no no (see below)
+ bd_mutex
+open: yes
+release: yes
+ioctl: no
+compat_ioctl: no
+direct_access: no
+media_changed: no
+unlock_native_capacity: no
+revalidate_disk: no
+getgeo: no
+swap_slot_free_notify: no (see below)
media_changed, unlock_native_capacity and revalidate_disk are called only from
check_disk_change().
@@ -413,34 +426,21 @@ prototypes:
unsigned long (*get_unmapped_area)(struct file *, unsigned long,
unsigned long, unsigned long, unsigned long);
int (*check_flags)(int);
+ int (*flock) (struct file *, int, struct file_lock *);
+ ssize_t (*splice_write)(struct pipe_inode_info *, struct file *, loff_t *,
+ size_t, unsigned int);
+ ssize_t (*splice_read)(struct file *, loff_t *, struct pipe_inode_info *,
+ size_t, unsigned int);
+ int (*setlease)(struct file *, long, struct file_lock **);
};
locking rules:
- All may block.
- BKL
-llseek: no (see below)
-read: no
-aio_read: no
-write: no
-aio_write: no
-readdir: no
-poll: no
-unlocked_ioctl: no
-compat_ioctl: no
-mmap: no
-open: no
-flush: no
-release: no
-fsync: no (see below)
-aio_fsync: no
-fasync: no
-lock: yes
-readv: no
-writev: no
-sendfile: no
-sendpage: no
-get_unmapped_area: no
-check_flags: no
+ All may block except for ->setlease.
+ No VFS locks held on entry except for ->fsync and ->setlease.
+
+->fsync() has i_mutex on inode.
+
+->setlease has the file_list_lock held and must not sleep.
->llseek() locking has moved from llseek to the individual llseek
implementations. If your fs is not using generic_file_llseek, you
@@ -450,17 +450,10 @@ mutex or just to use i_size_read() instead.
Note: this does not protect the file->f_pos against concurrent modifications
since this is something the userspace has to take care about.
-Note: ext2_release() was *the* source of contention on fs-intensive
-loads and dropping BKL on ->release() helps to get rid of that (we still
-grab BKL for cases when we close a file that had been opened r/w, but that
-can and should be done using the internal locking with smaller critical areas).
-Current worst offender is ext2_get_block()...
-
-->fasync() is called without BKL protection, and is responsible for
-maintaining the FASYNC bit in filp->f_flags. Most instances call
-fasync_helper(), which does that maintenance, so it's not normally
-something one needs to worry about. Return values > 0 will be mapped to
-zero in the VFS layer.
+->fasync() is responsible for maintaining the FASYNC bit in filp->f_flags.
+Most instances call fasync_helper(), which does that maintenance, so it's
+not normally something one needs to worry about. Return values > 0 will be
+mapped to zero in the VFS layer.
->readdir() and ->ioctl() on directories must be changed. Ideally we would
move ->readdir() to inode_operations and use a separate method for directory
@@ -471,8 +464,6 @@ components. And there are other reasons why the current interface is a mess...
->read on directories probably must go away - we should just enforce -EISDIR
in sys_read() and friends.
-->fsync() has i_mutex on inode.
-
--------------------------- dquot_operations -------------------------------
prototypes:
int (*write_dquot) (struct dquot *);
@@ -507,12 +498,12 @@ prototypes:
int (*access)(struct vm_area_struct *, unsigned long, void*, int, int);
locking rules:
- BKL mmap_sem PageLocked(page)
-open: no yes
-close: no yes
-fault: no yes can return with page locked
-page_mkwrite: no yes can return with page locked
-access: no yes
+ mmap_sem PageLocked(page)
+open: yes
+close: yes
+fault: yes can return with page locked
+page_mkwrite: yes can return with page locked
+access: yes
->fault() is called when a previously not present pte is about
to be faulted in. The filesystem must find and return the page associated
@@ -539,6 +530,3 @@ VM_IO | VM_PFNMAP VMAs.
(if you break something or notice that it is broken and do not fix it yourself
- at least put it here)
-
-ipc/shm.c::shm_delete() - may need BKL.
-->read() and ->write() in many drivers are (probably) missing BKL.
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index b79a8fbf0dd7..1031923f5254 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -1761,7 +1761,7 @@ and is between 256 and 4096 characters. It is defined in the file
nousb [USB] Disable the USB subsystem
- nowatchdog [KNL] Disable the lockup detector.
+ nowatchdog [KNL] Disable the lockup detector (NMI watchdog).
nowb [ARM]
@@ -2177,11 +2177,6 @@ and is between 256 and 4096 characters. It is defined in the file
reset_devices [KNL] Force drivers to reset the underlying device
during initialization.
- resource_alloc_from_bottom
- Allocate new resources from the beginning of available
- space, not the end. If you need to use this, please
- report a bug.
-
resume= [SWSUSP]
Specify the partition device for software suspend
diff --git a/Documentation/power/runtime_pm.txt b/Documentation/power/runtime_pm.txt
index 489e9bacd165..41cc7b30d7dd 100644
--- a/Documentation/power/runtime_pm.txt
+++ b/Documentation/power/runtime_pm.txt
@@ -379,8 +379,8 @@ drivers/base/power/runtime.c and include/linux/pm_runtime.h:
zero)
bool pm_runtime_suspended(struct device *dev);
- - return true if the device's runtime PM status is 'suspended', or false
- otherwise
+ - return true if the device's runtime PM status is 'suspended' and its
+ 'power.disable_depth' field is equal to zero, or false otherwise
void pm_runtime_allow(struct device *dev);
- set the power.runtime_auto flag for the device and decrease its usage
diff --git a/Documentation/scsi/scsi_mid_low_api.txt b/Documentation/scsi/scsi_mid_low_api.txt
index 570ef2b3d79b..df322c103466 100644
--- a/Documentation/scsi/scsi_mid_low_api.txt
+++ b/Documentation/scsi/scsi_mid_low_api.txt
@@ -1044,9 +1044,9 @@ Details:
/**
- * queuecommand - queue scsi command, invoke 'done' on completion
+ * queuecommand - queue scsi command, invoke scp->scsi_done on completion
+ * @shost: pointer to the scsi host object
* @scp: pointer to scsi command object
- * @done: function pointer to be invoked on completion
*
* Returns 0 on success.
*
@@ -1074,42 +1074,45 @@ Details:
*
* Other types of errors that are detected immediately may be
* flagged by setting scp->result to an appropriate value,
- * invoking the 'done' callback, and then returning 0 from this
- * function. If the command is not performed immediately (and the
- * LLD is starting (or will start) the given command) then this
- * function should place 0 in scp->result and return 0.
+ * invoking the scp->scsi_done callback, and then returning 0
+ * from this function. If the command is not performed
+ * immediately (and the LLD is starting (or will start) the given
+ * command) then this function should place 0 in scp->result and
+ * return 0.
*
* Command ownership. If the driver returns zero, it owns the
- * command and must take responsibility for ensuring the 'done'
- * callback is executed. Note: the driver may call done before
- * returning zero, but after it has called done, it may not
- * return any value other than zero. If the driver makes a
- * non-zero return, it must not execute the command's done
- * callback at any time.
- *
- * Locks: struct Scsi_Host::host_lock held on entry (with "irqsave")
- * and is expected to be held on return.
+ * command and must take responsibility for ensuring the
+ * scp->scsi_done callback is executed. Note: the driver may
+ * call scp->scsi_done before returning zero, but after it has
+ * called scp->scsi_done, it may not return any value other than
+ * zero. If the driver makes a non-zero return, it must not
+ * execute the command's scsi_done callback at any time.
+ *
+ * Locks: up to and including 2.6.36, struct Scsi_Host::host_lock
+ * held on entry (with "irqsave") and is expected to be
+ * held on return. From 2.6.37 onwards, queuecommand is
+ * called without any locks held.
*
* Calling context: in interrupt (soft irq) or process context
*
- * Notes: This function should be relatively fast. Normally it will
- * not wait for IO to complete. Hence the 'done' callback is invoked
- * (often directly from an interrupt service routine) some time after
- * this function has returned. In some cases (e.g. pseudo adapter
- * drivers that manufacture the response to a SCSI INQUIRY)
- * the 'done' callback may be invoked before this function returns.
- * If the 'done' callback is not invoked within a certain period
- * the SCSI mid level will commence error processing.
- * If a status of CHECK CONDITION is placed in "result" when the
- * 'done' callback is invoked, then the LLD driver should
- * perform autosense and fill in the struct scsi_cmnd::sense_buffer
+ * Notes: This function should be relatively fast. Normally it
+ * will not wait for IO to complete. Hence the scp->scsi_done
+ * callback is invoked (often directly from an interrupt service
+ * routine) some time after this function has returned. In some
+ * cases (e.g. pseudo adapter drivers that manufacture the
+ * response to a SCSI INQUIRY) the scp->scsi_done callback may be
+ * invoked before this function returns. If the scp->scsi_done
+ * callback is not invoked within a certain period the SCSI mid
+ * level will commence error processing. If a status of CHECK
+ * CONDITION is placed in "result" when the scp->scsi_done
+ * callback is invoked, then the LLD driver should perform
+ * autosense and fill in the struct scsi_cmnd::sense_buffer
* array. The scsi_cmnd::sense_buffer array is zeroed prior to
* the mid level queuing a command to an LLD.
*
* Defined in: LLD
**/
- int queuecommand(struct scsi_cmnd * scp,
- void (*done)(struct scsi_cmnd *))
+ int queuecommand(struct Scsi_Host *shost, struct scsi_cmnd * scp)
/**
diff --git a/Documentation/trace/postprocess/trace-vmscan-postprocess.pl b/Documentation/trace/postprocess/trace-vmscan-postprocess.pl
index b3e73ddb1567..12cecc83cd91 100644
--- a/Documentation/trace/postprocess/trace-vmscan-postprocess.pl
+++ b/Documentation/trace/postprocess/trace-vmscan-postprocess.pl
@@ -373,9 +373,18 @@ EVENT_PROCESS:
print " $regex_lru_isolate/o\n";
next;
}
+ my $isolate_mode = $1;
my $nr_scanned = $4;
my $nr_contig_dirty = $7;
- $perprocesspid{$process_pid}->{HIGH_NR_SCANNED} += $nr_scanned;
+
+ # To closer match vmstat scanning statistics, only count isolate_both
+ # and isolate_inactive as scanning. isolate_active is rotation
+ # isolate_inactive == 0
+ # isolate_active == 1
+ # isolate_both == 2
+ if ($isolate_mode != 1) {
+ $perprocesspid{$process_pid}->{HIGH_NR_SCANNED} += $nr_scanned;
+ }
$perprocesspid{$process_pid}->{HIGH_NR_CONTIG_DIRTY} += $nr_contig_dirty;
} elsif ($tracepoint eq "mm_vmscan_lru_shrink_inactive") {
$details = $5;