From 5151412dd4338b273afdb107c3772528e9e67d92 Mon Sep 17 00:00:00 2001 From: Mike Snitzer Date: Wed, 23 Nov 2011 10:59:13 +0100 Subject: block: initialize request_queue's numa node during struct request_queue is allocated with __GFP_ZERO so its "node" field is zero before initialization. This causes an oops if node 0 is offline in the page allocator because its zonelists are not initialized. From Dave Young's dmesg: SRAT: Node 1 PXM 2 0-d0000000 SRAT: Node 1 PXM 2 100000000-330000000 SRAT: Node 0 PXM 1 330000000-630000000 Initmem setup node 1 0000000000000000-000000000affb000 ... Built 1 zonelists in Node order, mobility grouping on. ... BUG: unable to handle kernel paging request at 0000000000001c08 IP: [] __alloc_pages_nodemask+0xb5/0x870 and __alloc_pages_nodemask+0xb5 translates to a NULL pointer on zonelist->_zonerefs. The fix is to initialize q->node at the time of allocation so the correct node is passed to the slab allocator later. Since blk_init_allocated_queue_node() is no longer needed, merge it with blk_init_allocated_queue(). [rientjes@google.com: changelog, initializing q->node] Cc: stable@vger.kernel.org [2.6.37+] Reported-by: Dave Young Signed-off-by: Mike Snitzer Signed-off-by: David Rientjes Tested-by: Dave Young Signed-off-by: Jens Axboe --- block/blk-core.c | 14 +++----------- 1 file changed, 3 insertions(+), 11 deletions(-) (limited to 'block') diff --git a/block/blk-core.c b/block/blk-core.c index ea70e6c80cd3..20d69f6beb6b 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -467,6 +467,7 @@ struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id) q->backing_dev_info.state = 0; q->backing_dev_info.capabilities = BDI_CAP_MAP_COPY; q->backing_dev_info.name = "block"; + q->node = node_id; err = bdi_init(&q->backing_dev_info); if (err) { @@ -551,7 +552,7 @@ blk_init_queue_node(request_fn_proc *rfn, spinlock_t *lock, int node_id) if (!uninit_q) return NULL; - q = blk_init_allocated_queue_node(uninit_q, rfn, lock, node_id); + q = blk_init_allocated_queue(uninit_q, rfn, lock); if (!q) blk_cleanup_queue(uninit_q); @@ -562,19 +563,10 @@ EXPORT_SYMBOL(blk_init_queue_node); struct request_queue * blk_init_allocated_queue(struct request_queue *q, request_fn_proc *rfn, spinlock_t *lock) -{ - return blk_init_allocated_queue_node(q, rfn, lock, -1); -} -EXPORT_SYMBOL(blk_init_allocated_queue); - -struct request_queue * -blk_init_allocated_queue_node(struct request_queue *q, request_fn_proc *rfn, - spinlock_t *lock, int node_id) { if (!q) return NULL; - q->node = node_id; if (blk_init_free_list(q)) return NULL; @@ -604,7 +596,7 @@ blk_init_allocated_queue_node(struct request_queue *q, request_fn_proc *rfn, return NULL; } -EXPORT_SYMBOL(blk_init_allocated_queue_node); +EXPORT_SYMBOL(blk_init_allocated_queue); int blk_get_queue(struct request_queue *q) { -- cgit v1.2.3 From 2984ff38ccf6cbc02a7a996a36c7d6f69f3c6146 Mon Sep 17 00:00:00 2001 From: majianpeng Date: Wed, 30 Nov 2011 15:47:48 +0100 Subject: cfq-iosched: free cic_index if blkio_alloc_blkg_stats fails If we fail allocating the blkpg stats, we free cfqd and cfgq. But we need to free the IDA cfqd->cic_index as well. Signed-off-by: majianpeng Cc: stable@kernel.org Signed-off-by: Jens Axboe --- block/cfq-iosched.c | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'block') diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c index 16ace89613bc..3beed83437a3 100644 --- a/block/cfq-iosched.c +++ b/block/cfq-iosched.c @@ -4036,6 +4036,11 @@ static void *cfq_init_queue(struct request_queue *q) if (blkio_alloc_blkg_stats(&cfqg->blkg)) { kfree(cfqg); + + spin_lock(&cic_index_lock); + ida_remove(&cic_index_ida, cfqd->cic_index); + spin_unlock(&cic_index_lock); + kfree(cfqd); return NULL; } -- cgit v1.2.3 From 5eb46851de3904cd1be9192fdacb8d34deadc1fc Mon Sep 17 00:00:00 2001 From: Yasuaki Ishimatsu Date: Fri, 2 Dec 2011 10:07:07 +0100 Subject: cfq-iosched: fix cfq_cic_link() race confition cfq_cic_link() has race condition. When some processes which shared ioc issue I/O to same block device simultaneously, cfq_cic_link() returns -EEXIST sometimes. The race condition might stop I/O by following steps: step 1: Process A: Issue an I/O to /dev/sda step 2: Process A: Get an ioc (iocA here) in get_io_context() which does not linked with a cic for the device step 3: Process A: Get a new cic for the device (cicA here) in cfq_alloc_io_context() step 4: Process B: Issue an I/O to /dev/sda step 5: Process B: Get iocA in get_io_context() since process A and B share the same ioc step 6: Process B: Get a new cic for the device (cicB here) in cfq_alloc_io_context() since iocA has not been linked with a cic for the device yet step 7: Process A: Link cicA to iocA in cfq_cic_link() step 8: Process A: Dispatch I/O to driver and finish it step 9: Process B: Try to link cicB to iocA in cfq_cic_link() But it fails with showing "cfq: cic link failed!" kernel message, since iocA has already linked with cicA at step 7. step 10: Process B: Wait for finishig I/O in get_request_wait() The function does not wake up, when there is no I/O to the device. When cfq_cic_link() returns -EEXIST, it means ioc has already linked with cic. So when cfq_cic_link() return -EEXIST, retry cfq_cic_lookup(). Signed-off-by: Yasuaki Ishimatsu Cc: stable@kernel.org Signed-off-by: Jens Axboe --- block/cfq-iosched.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) (limited to 'block') diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c index 3beed83437a3..4c12869fcf77 100644 --- a/block/cfq-iosched.c +++ b/block/cfq-iosched.c @@ -3184,7 +3184,7 @@ static int cfq_cic_link(struct cfq_data *cfqd, struct io_context *ioc, } } - if (ret) + if (ret && ret != -EEXIST) printk(KERN_ERR "cfq: cic link failed!\n"); return ret; @@ -3200,6 +3200,7 @@ cfq_get_io_context(struct cfq_data *cfqd, gfp_t gfp_mask) { struct io_context *ioc = NULL; struct cfq_io_context *cic; + int ret; might_sleep_if(gfp_mask & __GFP_WAIT); @@ -3207,6 +3208,7 @@ cfq_get_io_context(struct cfq_data *cfqd, gfp_t gfp_mask) if (!ioc) return NULL; +retry: cic = cfq_cic_lookup(cfqd, ioc); if (cic) goto out; @@ -3215,7 +3217,12 @@ cfq_get_io_context(struct cfq_data *cfqd, gfp_t gfp_mask) if (cic == NULL) goto err; - if (cfq_cic_link(cfqd, ioc, cic, gfp_mask)) + ret = cfq_cic_link(cfqd, ioc, cic, gfp_mask); + if (ret == -EEXIST) { + /* someone has linked cic to ioc already */ + cfq_cic_free(cic); + goto retry; + } else if (ret) goto err_free; out: -- cgit v1.2.3 From 4eabc941259f9d8c8fb71746d3f30c87e1d9e49b Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 15 Dec 2011 20:03:04 +0100 Subject: block: don't kick empty queue in blk_drain_queue() While probing, fd sets up queue, probes hardware and tears down the queue if probing fails. In the process, blk_drain_queue() kicks the queue which failed to finish initialization and fd is unhappy about that. floppy0: no floppy controllers found ------------[ cut here ]------------ WARNING: at drivers/block/floppy.c:2929 do_fd_request+0xbf/0xd0() Hardware name: To Be Filled By O.E.M. VFS: do_fd_request called on non-open device Modules linked in: Pid: 1, comm: swapper Not tainted 3.2.0-rc4-00077-g5983fe2 #2 Call Trace: [] warn_slowpath_common+0x7a/0xb0 [] warn_slowpath_fmt+0x41/0x50 [] do_fd_request+0xbf/0xd0 [] blk_drain_queue+0x65/0x80 [] blk_cleanup_queue+0xe3/0x1a0 [] floppy_init+0xdeb/0xe28 [] ? daring+0x6b/0x6b [] do_one_initcall+0x3f/0x170 [] kernel_init+0x9d/0x11e [] ? schedule_tail+0x22/0xa0 [] kernel_thread_helper+0x4/0x10 [] ? start_kernel+0x2be/0x2be [] ? gs_change+0xb/0xb Avoid it by making blk_drain_queue() kick queue iff dispatch queue has something on it. Signed-off-by: Tejun Heo Reported-by: Ralf Hildebrandt Reported-by: Wu Fengguang Tested-by: Sergei Trofimovich Signed-off-by: Jens Axboe --- block/blk-core.c | 9 ++++++++- 1 file changed, 8 insertions(+), 1 deletion(-) (limited to 'block') diff --git a/block/blk-core.c b/block/blk-core.c index 20d69f6beb6b..15de223c7f93 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -366,7 +366,14 @@ void blk_drain_queue(struct request_queue *q, bool drain_all) if (drain_all) blk_throtl_drain(q); - __blk_run_queue(q); + /* + * This function might be called on a queue which failed + * driver init after queue creation. Some drivers + * (e.g. fd) get unhappy in such cases. Kick queue iff + * dispatch queue has something on it. + */ + if (!list_empty(&q->queue_head)) + __blk_run_queue(q); if (drain_all) nr_rqs = q->rq.count[0] + q->rq.count[1]; -- cgit v1.2.3