summaryrefslogtreecommitdiffstats
path: root/fs/btrfs/reada.c
diff options
context:
space:
mode:
authorJames Bottomley <JBottomley@Parallels.com>2012-05-21 12:17:30 +0100
committerJames Bottomley <JBottomley@Parallels.com>2012-05-21 12:17:30 +0100
commite34693336564f02b3e2cc09d8b872aef22a154e9 (patch)
tree09f51f10f9406042f9176e39b4dc8de850ba712e /fs/btrfs/reada.c
parent76b311fdbdd2e16e5d39cd496a67aa1a1b948914 (diff)
parentde2eb4d5c5c25e8fb75d1e19092f24b83cb7d8d5 (diff)
downloadlinux-e34693336564f02b3e2cc09d8b872aef22a154e9.tar.bz2
Merge tag 'isci-for-3.5' into misc
isci update for 3.5 1/ Rework remote-node-context (RNC) handling for proper management of the silicon state machine in error handling and hot-plug conditions. Further details below, suffice to say if the RNC is mismanaged the silicon state machines may lock up. 2/ Refactor the initialization code to be reused for suspend/resume support 3/ Miscellaneous bug fixes to address discovery issues and hardware compatibility. RNC rework details from Jeff Skirvin: In the controller, devices as they appear on a SAS domain (or direct-attached SATA devices) are represented by memory structures known as "Remote Node Contexts" (RNCs). These structures are transferred from main memory to the controller using a set of register commands; these commands include setting up the context ("posting"), removing the context ("invalidating"), and commands to control the scheduling of commands and connections to that remote device ("suspensions" and "resumptions"). There is a similar path to control RNC scheduling from the protocol engine, which interprets the results of command and data transmission and reception. In general, the controller chooses among non-suspended RNCs to find one that has work requiring scheduling the transmission of command and data frames to a target. Likewise, when a target tries to return data back to the initiator, the state of the RNC is used by the controller to determine how to treat the incoming request. As an example, if the RNC is in the state "TX/RX Suspended", incoming SSP connection requests from the target will be rejected by the controller hardware. When an RNC is "TX Suspended", it will not be selected by the controller hardware to start outgoing command or data operations (with certain priority-based exceptions). As mentioned above, there are two sources for management of the RNC states: commands from driver software, and the result of transmission and reception conditions of commands and data signaled by the controller hardware. As an example of the latter, if an outgoing SSP command ends with a OPEN_REJECT(BAD_DESTINATION) status, the RNC state will transition to the "TX Suspended" state, and this is signaled by the controller hardware in the status to the completion of the pending command as well as signaled in a controller hardware event. Examples of the former are included in the patch changelogs. Driver software is required to suspend the RNC in a "TX/RX Suspended" condition before any outstanding commands can be terminated. Failure to guarantee this can lead to a complete hardware hang condition. Earlier versions of the driver software did not guarantee that an RNC was correctly managed before I/O termination, and so operated in an unsafe way. Further, the driver performed unnecessary contortions to preserve the remote device command state and so was more complicated than it needed to be. A simplifying driver assumption is that once an I/O has entered the error handler path without having completed in the target, the requirement on the driver is that all use of the sas_task must end. Beyond that, recovery of operation is dependent on libsas and other components to reset, rediscover and reconfigure the device before normal operation can restart. In the driver, this simplifying assumption meant that the RNC management could be reduced to entry into the suspended state, terminating the targeted I/O request, and resuming the RNC as needed for device-specific management such as an SSP Abort Task or LUN Reset Management request.
Diffstat (limited to 'fs/btrfs/reada.c')
-rw-r--r--fs/btrfs/reada.c48
1 files changed, 29 insertions, 19 deletions
diff --git a/fs/btrfs/reada.c b/fs/btrfs/reada.c
index dc5d33146fdb..ac5d01085884 100644
--- a/fs/btrfs/reada.c
+++ b/fs/btrfs/reada.c
@@ -250,14 +250,12 @@ static struct reada_zone *reada_find_zone(struct btrfs_fs_info *fs_info,
struct btrfs_bio *bbio)
{
int ret;
- int looped = 0;
struct reada_zone *zone;
struct btrfs_block_group_cache *cache = NULL;
u64 start;
u64 end;
int i;
-again:
zone = NULL;
spin_lock(&fs_info->reada_lock);
ret = radix_tree_gang_lookup(&dev->reada_zones, (void **)&zone,
@@ -274,9 +272,6 @@ again:
spin_unlock(&fs_info->reada_lock);
}
- if (looped)
- return NULL;
-
cache = btrfs_lookup_block_group(fs_info, logical);
if (!cache)
return NULL;
@@ -307,13 +302,15 @@ again:
ret = radix_tree_insert(&dev->reada_zones,
(unsigned long)(zone->end >> PAGE_CACHE_SHIFT),
zone);
- spin_unlock(&fs_info->reada_lock);
- if (ret) {
+ if (ret == -EEXIST) {
kfree(zone);
- looped = 1;
- goto again;
+ ret = radix_tree_gang_lookup(&dev->reada_zones, (void **)&zone,
+ logical >> PAGE_CACHE_SHIFT, 1);
+ if (ret == 1)
+ kref_get(&zone->refcnt);
}
+ spin_unlock(&fs_info->reada_lock);
return zone;
}
@@ -323,26 +320,26 @@ static struct reada_extent *reada_find_extent(struct btrfs_root *root,
struct btrfs_key *top, int level)
{
int ret;
- int looped = 0;
struct reada_extent *re = NULL;
+ struct reada_extent *re_exist = NULL;
struct btrfs_fs_info *fs_info = root->fs_info;
struct btrfs_mapping_tree *map_tree = &fs_info->mapping_tree;
struct btrfs_bio *bbio = NULL;
struct btrfs_device *dev;
+ struct btrfs_device *prev_dev;
u32 blocksize;
u64 length;
int nzones = 0;
int i;
unsigned long index = logical >> PAGE_CACHE_SHIFT;
-again:
spin_lock(&fs_info->reada_lock);
re = radix_tree_lookup(&fs_info->reada_tree, index);
if (re)
kref_get(&re->refcnt);
spin_unlock(&fs_info->reada_lock);
- if (re || looped)
+ if (re)
return re;
re = kzalloc(sizeof(*re), GFP_NOFS);
@@ -398,16 +395,31 @@ again:
/* insert extent in reada_tree + all per-device trees, all or nothing */
spin_lock(&fs_info->reada_lock);
ret = radix_tree_insert(&fs_info->reada_tree, index, re);
+ if (ret == -EEXIST) {
+ re_exist = radix_tree_lookup(&fs_info->reada_tree, index);
+ BUG_ON(!re_exist);
+ kref_get(&re_exist->refcnt);
+ spin_unlock(&fs_info->reada_lock);
+ goto error;
+ }
if (ret) {
spin_unlock(&fs_info->reada_lock);
- if (ret != -ENOMEM) {
- /* someone inserted the extent in the meantime */
- looped = 1;
- }
goto error;
}
+ prev_dev = NULL;
for (i = 0; i < nzones; ++i) {
dev = bbio->stripes[i].dev;
+ if (dev == prev_dev) {
+ /*
+ * in case of DUP, just add the first zone. As both
+ * are on the same device, there's nothing to gain
+ * from adding both.
+ * Also, it wouldn't work, as the tree is per device
+ * and adding would fail with EEXIST
+ */
+ continue;
+ }
+ prev_dev = dev;
ret = radix_tree_insert(&dev->reada_extents, index, re);
if (ret) {
while (--i >= 0) {
@@ -450,9 +462,7 @@ error:
}
kfree(bbio);
kfree(re);
- if (looped)
- goto again;
- return NULL;
+ return re_exist;
}
static void reada_kref_dummy(struct kref *kr)