From 8c9ce606a60e4a0cb447bdc082ce383b96b227b4 Mon Sep 17 00:00:00 2001 From: Konrad Rzeszutek Wilk Date: Fri, 25 May 2012 16:11:09 -0400 Subject: xen/blkback: Copy id field when doing BLKIF_DISCARD. We weren't copying the id field so when we sent the response back to the frontend (especially with a 64-bit host and 32-bit guest), we ended up using a random value. This lead to the frontend crashing as it would try to pass to __blk_end_request_all a NULL 'struct request' (b/c it would use the 'id' to find the proper 'struct request' in its shadow array) and end up crashing: BUG: unable to handle kernel NULL pointer dereference at 000000e4 IP: [] __blk_end_request_all+0xc/0x40 .. snip.. EIP is at __blk_end_request_all+0xc/0x40 .. snip.. [] blkif_interrupt+0x172/0x330 [xen_blkfront] This fixes the bug by passing in the proper id for the response. Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=824641 CC: stable@kernel.org Tested-by: William Dauchy Acked-by: Stefano Stabellini Signed-off-by: Konrad Rzeszutek Wilk --- drivers/block/xen-blkback/common.h | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/block/xen-blkback/common.h b/drivers/block/xen-blkback/common.h index 773cf27dc23f..9ad3b5ec1dc1 100644 --- a/drivers/block/xen-blkback/common.h +++ b/drivers/block/xen-blkback/common.h @@ -257,6 +257,7 @@ static inline void blkif_get_x86_32_req(struct blkif_request *dst, break; case BLKIF_OP_DISCARD: dst->u.discard.flag = src->u.discard.flag; + dst->u.discard.id = src->u.discard.id; dst->u.discard.sector_number = src->u.discard.sector_number; dst->u.discard.nr_sectors = src->u.discard.nr_sectors; break; @@ -287,6 +288,7 @@ static inline void blkif_get_x86_64_req(struct blkif_request *dst, break; case BLKIF_OP_DISCARD: dst->u.discard.flag = src->u.discard.flag; + dst->u.discard.id = src->u.discard.id; dst->u.discard.sector_number = src->u.discard.sector_number; dst->u.discard.nr_sectors = src->u.discard.nr_sectors; break; -- cgit v1.2.3 From 87c9ea76a242c2f9063e2a8f3e90846c932c61a7 Mon Sep 17 00:00:00 2001 From: Sachin Kamat Date: Sun, 3 Jun 2012 21:56:21 +0530 Subject: mtip32xx: Remove version.h header file inclusion version.h header file inclusion is no longer required. Signed-off-by: Sachin Kamat --- drivers/block/mtip32xx/mtip32xx.h | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/block/mtip32xx/mtip32xx.h b/drivers/block/mtip32xx/mtip32xx.h index b2c88da26b2a..adb1aae3b752 100644 --- a/drivers/block/mtip32xx/mtip32xx.h +++ b/drivers/block/mtip32xx/mtip32xx.h @@ -26,7 +26,6 @@ #include #include #include -#include /* Offset of Subsystem Device ID in pci confoguration space */ #define PCI_SUBSYSTEM_DEVICEID 0x2E -- cgit v1.2.3 From fd7949564ced88385ca7758a4c1f47c274233dd5 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 4 Jun 2012 10:01:38 +0200 Subject: block: fix return value on cfq_init() failure cfq_init() would return zero after kmem cache creation failure. Fix so that it returns -ENOMEM. Signed-off-by: Tejun Heo Signed-off-by: Jens Axboe --- block/cfq-iosched.c | 1 + 1 file changed, 1 insertion(+) diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c index 673c977cc2bf..ae5113d3ebae 100644 --- a/block/cfq-iosched.c +++ b/block/cfq-iosched.c @@ -4202,6 +4202,7 @@ static int __init cfq_init(void) if (ret) return ret; + ret = -ENOMEM; cfq_pool = KMEM_CACHE(cfq_queue, 0); if (!cfq_pool) goto err_pol_unreg; -- cgit v1.2.3 From ffea73fc723a12fdde4c9fb3fcce5d154d1104a1 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 4 Jun 2012 10:02:29 +0200 Subject: block: blkcg_policy_cfq shouldn't be used if !CONFIG_CFQ_GROUP_IOSCHED cfq may be built w/ or w/o blkcg support depending on CONFIG_CFQ_CGROUP_IOSCHED. If blkcg support is disabled, most of related code is ifdef'd out but some part is left dangling - blkcg_policy_cfq is left zero-filled and blkcg_policy_[un]register() calls are made on it. Feeding zero filled policy to blkcg_policy_register() is incorrect and triggers the following WARN_ON() if CONFIG_BLK_CGROUP && !CONFIG_CFQ_GROUP_IOSCHED. ------------[ cut here ]------------ WARNING: at block/blk-cgroup.c:867 Modules linked in: Modules linked in: CPU: 3 Not tainted 3.4.0-09547-gfb21aff #1 Process swapper/0 (pid: 1, task: 000000003ff80000, ksp: 000000003ff7f8b8) Krnl PSW : 0704100180000000 00000000003d76ca (blkcg_policy_register+0xca/0xe0) R:0 T:1 IO:1 EX:1 Key:0 M:1 W:0 P:0 AS:0 CC:1 PM:0 EA:3 Krnl GPRS: 0000000000000000 00000000014b85ec 00000000014b85b0 0000000000000000 000000000096fb60 0000000000000000 00000000009a8e78 0000000000000048 000000000099c070 0000000000b6f000 0000000000000000 000000000099c0b8 00000000014b85b0 0000000000667580 000000003ff7fd98 000000003ff7fd70 Krnl Code: 00000000003d76be: a7280001 lhi %r2,1 00000000003d76c2: a7f4ffdf brc 15,3d7680 #00000000003d76c6: a7f40001 brc 15,3d76c8 >00000000003d76ca: a7c8ffea lhi %r12,-22 00000000003d76ce: a7f4ffce brc 15,3d766a 00000000003d76d2: a7f40001 brc 15,3d76d4 00000000003d76d6: a7c80000 lhi %r12,0 00000000003d76da: a7f4ffc2 brc 15,3d765e Call Trace: ([<0000000000b6f000>] initcall_debug+0x0/0x4) [<0000000000989e8a>] cfq_init+0x62/0xd4 [<00000000001000ba>] do_one_initcall+0x3a/0x170 [<000000000096fb60>] kernel_init+0x214/0x2bc [<0000000000623202>] kernel_thread_starter+0x6/0xc [<00000000006231fc>] kernel_thread_starter+0x0/0xc no locks held by swapper/0/1. Last Breaking-Event-Address: [<00000000003d76c6>] blkcg_policy_register+0xc6/0xe0 ---[ end trace b8ef4903fcbf9dd3 ]--- This patch fixes the problem by ensuring all blkcg support code is inside CONFIG_CFQ_GROUP_IOSCHED. * blkcg_policy_cfq declaration and blkg_to_cfqg() definition are moved inside the first CONFIG_CFQ_GROUP_IOSCHED block. __maybe_unused is dropped from blkcg_policy_cfq decl. * blkcg_deactivate_poilcy() invocation is moved inside ifdef. This also makes the activation logic match cfq_init_queue(). * All blkcg_policy_[un]register() invocations are moved inside ifdef. Signed-off-by: Tejun Heo Reported-by: Heiko Carstens LKML-Reference: <20120601112954.GC3535@osiris.boeblingen.de.ibm.com> Signed-off-by: Jens Axboe --- block/cfq-iosched.c | 29 +++++++++++++++++------------ 1 file changed, 17 insertions(+), 12 deletions(-) diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c index ae5113d3ebae..fb52df9744f5 100644 --- a/block/cfq-iosched.c +++ b/block/cfq-iosched.c @@ -17,8 +17,6 @@ #include "blk.h" #include "blk-cgroup.h" -static struct blkcg_policy blkcg_policy_cfq __maybe_unused; - /* * tunables */ @@ -418,11 +416,6 @@ static inline struct cfq_group *pd_to_cfqg(struct blkg_policy_data *pd) return pd ? container_of(pd, struct cfq_group, pd) : NULL; } -static inline struct cfq_group *blkg_to_cfqg(struct blkcg_gq *blkg) -{ - return pd_to_cfqg(blkg_to_pd(blkg, &blkcg_policy_cfq)); -} - static inline struct blkcg_gq *cfqg_to_blkg(struct cfq_group *cfqg) { return pd_to_blkg(&cfqg->pd); @@ -572,6 +565,13 @@ static inline void cfqg_stats_update_avg_queue_size(struct cfq_group *cfqg) { } #ifdef CONFIG_CFQ_GROUP_IOSCHED +static struct blkcg_policy blkcg_policy_cfq; + +static inline struct cfq_group *blkg_to_cfqg(struct blkcg_gq *blkg) +{ + return pd_to_cfqg(blkg_to_pd(blkg, &blkcg_policy_cfq)); +} + static inline void cfqg_get(struct cfq_group *cfqg) { return blkg_get(cfqg_to_blkg(cfqg)); @@ -3951,10 +3951,11 @@ static void cfq_exit_queue(struct elevator_queue *e) cfq_shutdown_timer_wq(cfqd); -#ifndef CONFIG_CFQ_GROUP_IOSCHED +#ifdef CONFIG_CFQ_GROUP_IOSCHED + blkcg_deactivate_policy(q, &blkcg_policy_cfq); +#else kfree(cfqd->root_group); #endif - blkcg_deactivate_policy(q, &blkcg_policy_cfq); kfree(cfqd); } @@ -4194,13 +4195,13 @@ static int __init cfq_init(void) #ifdef CONFIG_CFQ_GROUP_IOSCHED if (!cfq_group_idle) cfq_group_idle = 1; -#else - cfq_group_idle = 0; -#endif ret = blkcg_policy_register(&blkcg_policy_cfq); if (ret) return ret; +#else + cfq_group_idle = 0; +#endif ret = -ENOMEM; cfq_pool = KMEM_CACHE(cfq_queue, 0); @@ -4216,13 +4217,17 @@ static int __init cfq_init(void) err_free_pool: kmem_cache_destroy(cfq_pool); err_pol_unreg: +#ifdef CONFIG_CFQ_GROUP_IOSCHED blkcg_policy_unregister(&blkcg_policy_cfq); +#endif return ret; } static void __exit cfq_exit(void) { +#ifdef CONFIG_CFQ_GROUP_IOSCHED blkcg_policy_unregister(&blkcg_policy_cfq); +#endif elv_unregister(&iosched_cfq); kmem_cache_destroy(cfq_pool); } -- cgit v1.2.3 From 9b2ea86bc9e940950a088e9795ab28f006e73276 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 4 Jun 2012 15:21:00 +0900 Subject: blkcg: fix blkg_alloc() failure path When policy data allocation fails in the middle, blkg_alloc() invokes blkg_free() to destroy the half constructed blkg. This ends up calling pd_exit_fn() on policy datas which didn't go through pd_init_fn(). Fix it by making blkg_alloc() call pd_init_fn() immediately after each policy data allocation. Signed-off-by: Tejun Heo Acked-by: Vivek Goyal Signed-off-by: Jens Axboe --- block/blk-cgroup.c | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index 02cf6335e9bd..4ab7420ba465 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -125,12 +125,8 @@ static struct blkcg_gq *blkg_alloc(struct blkcg *blkcg, struct request_queue *q) blkg->pd[i] = pd; pd->blkg = blkg; - } - - /* invoke per-policy init */ - for (i = 0; i < BLKCG_MAX_POLS; i++) { - struct blkcg_policy *pol = blkcg_policy[i]; + /* invoke per-policy init */ if (blkcg_policy_enabled(blkg->q, pol)) pol->pd_init_fn(blkg); } -- cgit v1.2.3 From 7412ff139d73f5561492478e89a22aede7252b7b Mon Sep 17 00:00:00 2001 From: Asai Thambi S P Date: Mon, 4 Jun 2012 12:43:03 -0700 Subject: mtip32xx: Remove 'registers' and 'flags' from sysfs This patch removes entries 'registers' and 'flags' from sysfs. Updated ABI file to reflect this change. Reported-by: Greg Kroah-Hartman Signed-off-by: Asai Thambi S P Signed-off-by: Jens Axboe --- Documentation/ABI/testing/sysfs-block-rssd | 21 ------- drivers/block/mtip32xx/mtip32xx.c | 92 +----------------------------- 2 files changed, 1 insertion(+), 112 deletions(-) diff --git a/Documentation/ABI/testing/sysfs-block-rssd b/Documentation/ABI/testing/sysfs-block-rssd index 679ce3543122..beef30c046b0 100644 --- a/Documentation/ABI/testing/sysfs-block-rssd +++ b/Documentation/ABI/testing/sysfs-block-rssd @@ -1,26 +1,5 @@ -What: /sys/block/rssd*/registers -Date: March 2012 -KernelVersion: 3.3 -Contact: Asai Thambi S P -Description: This is a read-only file. Dumps below driver information and - hardware registers. - - S ACTive - - Command Issue - - Completed - - PORT IRQ STAT - - HOST IRQ STAT - - Allocated - - Commands in Q - What: /sys/block/rssd*/status Date: April 2012 KernelVersion: 3.4 Contact: Asai Thambi S P Description: This is a read-only file. Indicates the status of the device. - -What: /sys/block/rssd*/flags -Date: May 2012 -KernelVersion: 3.5 -Contact: Asai Thambi S P -Description: This is a read-only file. Dumps the flags in port and driver - data structure diff --git a/drivers/block/mtip32xx/mtip32xx.c b/drivers/block/mtip32xx/mtip32xx.c index 264bc77dcb91..b6e95b911b8c 100644 --- a/drivers/block/mtip32xx/mtip32xx.c +++ b/drivers/block/mtip32xx/mtip32xx.c @@ -2546,7 +2546,7 @@ static struct scatterlist *mtip_hw_get_scatterlist(struct driver_data *dd, } /* - * Sysfs register/status dump. + * Sysfs status dump. * * @dev Pointer to the device structure, passed by the kernrel. * @attr Pointer to the device_attribute structure passed by the kernel. @@ -2555,71 +2555,6 @@ static struct scatterlist *mtip_hw_get_scatterlist(struct driver_data *dd, * return value * The size, in bytes, of the data copied into buf. */ -static ssize_t mtip_hw_show_registers(struct device *dev, - struct device_attribute *attr, - char *buf) -{ - u32 group_allocated; - struct driver_data *dd = dev_to_disk(dev)->private_data; - int size = 0; - int n; - - size += sprintf(&buf[size], "Hardware\n--------\n"); - size += sprintf(&buf[size], "S ACTive : [ 0x"); - - for (n = dd->slot_groups-1; n >= 0; n--) - size += sprintf(&buf[size], "%08X ", - readl(dd->port->s_active[n])); - - size += sprintf(&buf[size], "]\n"); - size += sprintf(&buf[size], "Command Issue : [ 0x"); - - for (n = dd->slot_groups-1; n >= 0; n--) - size += sprintf(&buf[size], "%08X ", - readl(dd->port->cmd_issue[n])); - - size += sprintf(&buf[size], "]\n"); - size += sprintf(&buf[size], "Completed : [ 0x"); - - for (n = dd->slot_groups-1; n >= 0; n--) - size += sprintf(&buf[size], "%08X ", - readl(dd->port->completed[n])); - - size += sprintf(&buf[size], "]\n"); - size += sprintf(&buf[size], "PORT IRQ STAT : [ 0x%08X ]\n", - readl(dd->port->mmio + PORT_IRQ_STAT)); - size += sprintf(&buf[size], "HOST IRQ STAT : [ 0x%08X ]\n", - readl(dd->mmio + HOST_IRQ_STAT)); - size += sprintf(&buf[size], "\n"); - - size += sprintf(&buf[size], "Local\n-----\n"); - size += sprintf(&buf[size], "Allocated : [ 0x"); - - for (n = dd->slot_groups-1; n >= 0; n--) { - if (sizeof(long) > sizeof(u32)) - group_allocated = - dd->port->allocated[n/2] >> (32*(n&1)); - else - group_allocated = dd->port->allocated[n]; - size += sprintf(&buf[size], "%08X ", group_allocated); - } - size += sprintf(&buf[size], "]\n"); - - size += sprintf(&buf[size], "Commands in Q: [ 0x"); - - for (n = dd->slot_groups-1; n >= 0; n--) { - if (sizeof(long) > sizeof(u32)) - group_allocated = - dd->port->cmds_to_issue[n/2] >> (32*(n&1)); - else - group_allocated = dd->port->cmds_to_issue[n]; - size += sprintf(&buf[size], "%08X ", group_allocated); - } - size += sprintf(&buf[size], "]\n"); - - return size; -} - static ssize_t mtip_hw_show_status(struct device *dev, struct device_attribute *attr, char *buf) @@ -2637,24 +2572,7 @@ static ssize_t mtip_hw_show_status(struct device *dev, return size; } -static ssize_t mtip_hw_show_flags(struct device *dev, - struct device_attribute *attr, - char *buf) -{ - struct driver_data *dd = dev_to_disk(dev)->private_data; - int size = 0; - - size += sprintf(&buf[size], "Flag in port struct : [ %08lX ]\n", - dd->port->flags); - size += sprintf(&buf[size], "Flag in dd struct : [ %08lX ]\n", - dd->dd_flag); - - return size; -} - -static DEVICE_ATTR(registers, S_IRUGO, mtip_hw_show_registers, NULL); static DEVICE_ATTR(status, S_IRUGO, mtip_hw_show_status, NULL); -static DEVICE_ATTR(flags, S_IRUGO, mtip_hw_show_flags, NULL); /* * Create the sysfs related attributes. @@ -2671,15 +2589,9 @@ static int mtip_hw_sysfs_init(struct driver_data *dd, struct kobject *kobj) if (!kobj || !dd) return -EINVAL; - if (sysfs_create_file(kobj, &dev_attr_registers.attr)) - dev_warn(&dd->pdev->dev, - "Error creating 'registers' sysfs entry\n"); if (sysfs_create_file(kobj, &dev_attr_status.attr)) dev_warn(&dd->pdev->dev, "Error creating 'status' sysfs entry\n"); - if (sysfs_create_file(kobj, &dev_attr_flags.attr)) - dev_warn(&dd->pdev->dev, - "Error creating 'flags' sysfs entry\n"); return 0; } @@ -2698,9 +2610,7 @@ static int mtip_hw_sysfs_exit(struct driver_data *dd, struct kobject *kobj) if (!kobj || !dd) return -EINVAL; - sysfs_remove_file(kobj, &dev_attr_registers.attr); sysfs_remove_file(kobj, &dev_attr_status.attr); - sysfs_remove_file(kobj, &dev_attr_flags.attr); return 0; } -- cgit v1.2.3 From 7b421d24eac79800ee68905f732300a291f72f00 Mon Sep 17 00:00:00 2001 From: Asai Thambi S P Date: Mon, 4 Jun 2012 12:44:02 -0700 Subject: mtip32xx: Create debugfs entries for troubleshooting On module load, creates a debugfs parent 'rssd' in debugfs root. Then for each device, create a new node with corresponding disk name. Under the new node, two entries 'registers' and 'flags' are created. NOTE: These entries were removed from sysfs in the previous patch Signed-off-by: Asai Thambi S P Signed-off-by: Jens Axboe --- drivers/block/mtip32xx/mtip32xx.c | 162 +++++++++++++++++++++++++++++++++++++- drivers/block/mtip32xx/mtip32xx.h | 4 + 2 files changed, 165 insertions(+), 1 deletion(-) diff --git a/drivers/block/mtip32xx/mtip32xx.c b/drivers/block/mtip32xx/mtip32xx.c index b6e95b911b8c..a8fddeb3d638 100644 --- a/drivers/block/mtip32xx/mtip32xx.c +++ b/drivers/block/mtip32xx/mtip32xx.c @@ -37,6 +37,7 @@ #include #include <../drivers/ata/ahci.h> #include +#include #include "mtip32xx.h" #define HW_CMD_SLOT_SZ (MTIP_MAX_COMMAND_SLOTS * 32) @@ -85,6 +86,7 @@ static int instance; * allocated in mtip_init(). */ static int mtip_major; +static struct dentry *dfs_parent; static DEFINE_SPINLOCK(rssd_index_lock); static DEFINE_IDA(rssd_index_ida); @@ -2574,6 +2576,120 @@ static ssize_t mtip_hw_show_status(struct device *dev, static DEVICE_ATTR(status, S_IRUGO, mtip_hw_show_status, NULL); +static ssize_t mtip_hw_read_registers(struct file *f, char __user *ubuf, + size_t len, loff_t *offset) +{ + struct driver_data *dd = (struct driver_data *)f->private_data; + char buf[MTIP_DFS_MAX_BUF_SIZE]; + u32 group_allocated; + int size = *offset; + int n; + + if (!len || size) + return 0; + + if (size < 0) + return -EINVAL; + + size += sprintf(&buf[size], "H/ S ACTive : [ 0x"); + + for (n = dd->slot_groups-1; n >= 0; n--) + size += sprintf(&buf[size], "%08X ", + readl(dd->port->s_active[n])); + + size += sprintf(&buf[size], "]\n"); + size += sprintf(&buf[size], "H/ Command Issue : [ 0x"); + + for (n = dd->slot_groups-1; n >= 0; n--) + size += sprintf(&buf[size], "%08X ", + readl(dd->port->cmd_issue[n])); + + size += sprintf(&buf[size], "]\n"); + size += sprintf(&buf[size], "H/ Completed : [ 0x"); + + for (n = dd->slot_groups-1; n >= 0; n--) + size += sprintf(&buf[size], "%08X ", + readl(dd->port->completed[n])); + + size += sprintf(&buf[size], "]\n"); + size += sprintf(&buf[size], "H/ PORT IRQ STAT : [ 0x%08X ]\n", + readl(dd->port->mmio + PORT_IRQ_STAT)); + size += sprintf(&buf[size], "H/ HOST IRQ STAT : [ 0x%08X ]\n", + readl(dd->mmio + HOST_IRQ_STAT)); + size += sprintf(&buf[size], "\n"); + + size += sprintf(&buf[size], "L/ Allocated : [ 0x"); + + for (n = dd->slot_groups-1; n >= 0; n--) { + if (sizeof(long) > sizeof(u32)) + group_allocated = + dd->port->allocated[n/2] >> (32*(n&1)); + else + group_allocated = dd->port->allocated[n]; + size += sprintf(&buf[size], "%08X ", group_allocated); + } + size += sprintf(&buf[size], "]\n"); + + size += sprintf(&buf[size], "L/ Commands in Q : [ 0x"); + + for (n = dd->slot_groups-1; n >= 0; n--) { + if (sizeof(long) > sizeof(u32)) + group_allocated = + dd->port->cmds_to_issue[n/2] >> (32*(n&1)); + else + group_allocated = dd->port->cmds_to_issue[n]; + size += sprintf(&buf[size], "%08X ", group_allocated); + } + size += sprintf(&buf[size], "]\n"); + + *offset = size <= len ? size : len; + size = copy_to_user(ubuf, buf, *offset); + if (size) + return -EFAULT; + + return *offset; +} + +static ssize_t mtip_hw_read_flags(struct file *f, char __user *ubuf, + size_t len, loff_t *offset) +{ + struct driver_data *dd = (struct driver_data *)f->private_data; + char buf[MTIP_DFS_MAX_BUF_SIZE]; + int size = *offset; + + if (!len || size) + return 0; + + if (size < 0) + return -EINVAL; + + size += sprintf(&buf[size], "Flag-port : [ %08lX ]\n", + dd->port->flags); + size += sprintf(&buf[size], "Flag-dd : [ %08lX ]\n", + dd->dd_flag); + + *offset = size <= len ? size : len; + size = copy_to_user(ubuf, buf, *offset); + if (size) + return -EFAULT; + + return *offset; +} + +static const struct file_operations mtip_regs_fops = { + .owner = THIS_MODULE, + .open = simple_open, + .read = mtip_hw_read_registers, + .llseek = no_llseek, +}; + +static const struct file_operations mtip_flags_fops = { + .owner = THIS_MODULE, + .open = simple_open, + .read = mtip_hw_read_flags, + .llseek = no_llseek, +}; + /* * Create the sysfs related attributes. * @@ -2615,6 +2731,34 @@ static int mtip_hw_sysfs_exit(struct driver_data *dd, struct kobject *kobj) return 0; } +static int mtip_hw_debugfs_init(struct driver_data *dd) +{ + if (!dfs_parent) + return -1; + + dd->dfs_node = debugfs_create_dir(dd->disk->disk_name, dfs_parent); + if (IS_ERR_OR_NULL(dd->dfs_node)) { + dev_warn(&dd->pdev->dev, + "Error creating node %s under debugfs\n", + dd->disk->disk_name); + dd->dfs_node = NULL; + return -1; + } + + debugfs_create_file("flags", S_IRUGO, dd->dfs_node, dd, + &mtip_flags_fops); + debugfs_create_file("registers", S_IRUGO, dd->dfs_node, dd, + &mtip_regs_fops); + + return 0; +} + +static void mtip_hw_debugfs_exit(struct driver_data *dd) +{ + debugfs_remove_recursive(dd->dfs_node); +} + + /* * Perform any init/resume time hardware setup * @@ -3640,6 +3784,7 @@ skip_create_disk: mtip_hw_sysfs_init(dd, kobj); kobject_put(kobj); } + mtip_hw_debugfs_init(dd); if (dd->mtip_svc_handler) { set_bit(MTIP_DDF_INIT_DONE_BIT, &dd->dd_flag); @@ -3665,6 +3810,8 @@ start_service_thread: return rv; kthread_run_error: + mtip_hw_debugfs_exit(dd); + /* Delete our gendisk. This also removes the device from /dev */ del_gendisk(dd->disk); @@ -3715,6 +3862,7 @@ static int mtip_block_remove(struct driver_data *dd) kobject_put(kobj); } } + mtip_hw_debugfs_exit(dd); /* * Delete our gendisk structure. This also removes the device @@ -4062,10 +4210,20 @@ static int __init mtip_init(void) } mtip_major = error; + if (!dfs_parent) { + dfs_parent = debugfs_create_dir("rssd", NULL); + if (IS_ERR_OR_NULL(dfs_parent)) { + printk(KERN_WARNING "Error creating debugfs parent\n"); + dfs_parent = NULL; + } + } + /* Register our PCI operations. */ error = pci_register_driver(&mtip_pci_driver); - if (error) + if (error) { + debugfs_remove(dfs_parent); unregister_blkdev(mtip_major, MTIP_DRV_NAME); + } return error; } @@ -4082,6 +4240,8 @@ static int __init mtip_init(void) */ static void __exit mtip_exit(void) { + debugfs_remove_recursive(dfs_parent); + /* Release the allocated major block device number. */ unregister_blkdev(mtip_major, MTIP_DRV_NAME); diff --git a/drivers/block/mtip32xx/mtip32xx.h b/drivers/block/mtip32xx/mtip32xx.h index adb1aae3b752..f51fc23d17bb 100644 --- a/drivers/block/mtip32xx/mtip32xx.h +++ b/drivers/block/mtip32xx/mtip32xx.h @@ -110,6 +110,8 @@ #define dbg_printk(format, arg...) #endif +#define MTIP_DFS_MAX_BUF_SIZE 1024 + #define __force_bit2int (unsigned int __force) enum { @@ -446,6 +448,8 @@ struct driver_data { unsigned long dd_flag; /* NOTE: use atomic bit operations on this */ struct task_struct *mtip_svc_handler; /* task_struct of svc thd */ + + struct dentry *dfs_node; }; #endif -- cgit v1.2.3 From 27e1f9d1cc87be4e53c6eb7158cafc21c4b85a14 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Tue, 5 Jun 2012 13:36:44 +0200 Subject: blkcg: drop local variable @q from blkg_destroy() blkg_destroy() caches @blkg->q in local variable @q. While there are two places which needs @blkg->q, only lockdep_assert_held() used the local variable leading to unused local variable warning if lockdep is configured out. Drop the local variable and just use @blkg->q directly. Signed-off-by: Tejun Heo Reported-by: Rakesh Iyer Signed-off-by: Jens Axboe --- block/blk-cgroup.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index 4ab7420ba465..e7dee617358e 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -241,10 +241,9 @@ EXPORT_SYMBOL_GPL(blkg_lookup_create); static void blkg_destroy(struct blkcg_gq *blkg) { - struct request_queue *q = blkg->q; struct blkcg *blkcg = blkg->blkcg; - lockdep_assert_held(q->queue_lock); + lockdep_assert_held(blkg->q->queue_lock); lockdep_assert_held(&blkcg->lock); /* Something wrong if we are trying to remove same group twice */ -- cgit v1.2.3 From 6878c32e5cc0e40980abe51d1f02fb453e27493e Mon Sep 17 00:00:00 2001 From: Konrad Rzeszutek Wilk Date: Fri, 25 May 2012 17:34:51 -0400 Subject: xen/blkfront: Add WARN to deal with misbehaving backends. Part of the ring structure is the 'id' field which is under control of the frontend. The frontend stamps it with "some" value (this some in this implementation being a value less than BLK_RING_SIZE), and when it gets a response expects said value to be in the response structure. We have a check for the id field when spolling new requests but not when de-spolling responses. We also add an extra check in add_id_to_freelist to make sure that the 'struct request' was not NULL - as we cannot pass a NULL to __blk_end_request_all, otherwise that crashes (and all the operations that the response is dealing with end up with __blk_end_request_all). Lastly we also print the name of the operation that failed. [v1: s/BUG/WARN/ suggested by Stefano] [v2: Add extra check in add_id_to_freelist] [v3: Redid op_name per Jan's suggestion] [v4: add const * and add WARN on failure returns] Acked-by: Jan Beulich Acked-by: Stefano Stabellini Signed-off-by: Konrad Rzeszutek Wilk --- drivers/block/xen-blkfront.c | 58 +++++++++++++++++++++++++++++++++++--------- 1 file changed, 46 insertions(+), 12 deletions(-) diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c index 60eed4bdd2e4..e4fb3374dcd2 100644 --- a/drivers/block/xen-blkfront.c +++ b/drivers/block/xen-blkfront.c @@ -141,14 +141,36 @@ static int get_id_from_freelist(struct blkfront_info *info) return free; } -static void add_id_to_freelist(struct blkfront_info *info, +static int add_id_to_freelist(struct blkfront_info *info, unsigned long id) { + if (info->shadow[id].req.u.rw.id != id) + return -EINVAL; + if (info->shadow[id].request == NULL) + return -EINVAL; info->shadow[id].req.u.rw.id = info->shadow_free; info->shadow[id].request = NULL; info->shadow_free = id; + return 0; } +static const char *op_name(int op) +{ + static const char *const names[] = { + [BLKIF_OP_READ] = "read", + [BLKIF_OP_WRITE] = "write", + [BLKIF_OP_WRITE_BARRIER] = "barrier", + [BLKIF_OP_FLUSH_DISKCACHE] = "flush", + [BLKIF_OP_DISCARD] = "discard" }; + + if (op < 0 || op >= ARRAY_SIZE(names)) + return "unknown"; + + if (!names[op]) + return "reserved"; + + return names[op]; +} static int xlbd_reserve_minors(unsigned int minor, unsigned int nr) { unsigned int end = minor + nr; @@ -746,20 +768,36 @@ static irqreturn_t blkif_interrupt(int irq, void *dev_id) bret = RING_GET_RESPONSE(&info->ring, i); id = bret->id; + /* + * The backend has messed up and given us an id that we would + * never have given to it (we stamp it up to BLK_RING_SIZE - + * look in get_id_from_freelist. + */ + if (id >= BLK_RING_SIZE) { + WARN(1, "%s: response to %s has incorrect id (%ld)\n", + info->gd->disk_name, op_name(bret->operation), id); + /* We can't safely get the 'struct request' as + * the id is busted. */ + continue; + } req = info->shadow[id].request; if (bret->operation != BLKIF_OP_DISCARD) blkif_completion(&info->shadow[id]); - add_id_to_freelist(info, id); + if (add_id_to_freelist(info, id)) { + WARN(1, "%s: response to %s (id %ld) couldn't be recycled!\n", + info->gd->disk_name, op_name(bret->operation), id); + continue; + } error = (bret->status == BLKIF_RSP_OKAY) ? 0 : -EIO; switch (bret->operation) { case BLKIF_OP_DISCARD: if (unlikely(bret->status == BLKIF_RSP_EOPNOTSUPP)) { struct request_queue *rq = info->rq; - printk(KERN_WARNING "blkfront: %s: discard op failed\n", - info->gd->disk_name); + printk(KERN_WARNING "blkfront: %s: %s op failed\n", + info->gd->disk_name, op_name(bret->operation)); error = -EOPNOTSUPP; info->feature_discard = 0; info->feature_secdiscard = 0; @@ -771,18 +809,14 @@ static irqreturn_t blkif_interrupt(int irq, void *dev_id) case BLKIF_OP_FLUSH_DISKCACHE: case BLKIF_OP_WRITE_BARRIER: if (unlikely(bret->status == BLKIF_RSP_EOPNOTSUPP)) { - printk(KERN_WARNING "blkfront: %s: write %s op failed\n", - info->flush_op == BLKIF_OP_WRITE_BARRIER ? - "barrier" : "flush disk cache", - info->gd->disk_name); + printk(KERN_WARNING "blkfront: %s: %s op failed\n", + info->gd->disk_name, op_name(bret->operation)); error = -EOPNOTSUPP; } if (unlikely(bret->status == BLKIF_RSP_ERROR && info->shadow[id].req.u.rw.nr_segments == 0)) { - printk(KERN_WARNING "blkfront: %s: empty write %s op failed\n", - info->flush_op == BLKIF_OP_WRITE_BARRIER ? - "barrier" : "flush disk cache", - info->gd->disk_name); + printk(KERN_WARNING "blkfront: %s: empty %s op failed\n", + info->gd->disk_name, op_name(bret->operation)); error = -EOPNOTSUPP; } if (unlikely(error)) { -- cgit v1.2.3 From 4eccc579795290a58e2262fa4e9d083d7672e699 Mon Sep 17 00:00:00 2001 From: Lars Ellenberg Date: Fri, 8 Jun 2012 13:18:51 +0200 Subject: drbd: fix access of unallocated pages and kernel panic BUG: unable to handle kernel NULL pointer dereference at (null) ... [] ? _drbd_bm_set_bits+0x151/0x240 [drbd] [] ? receive_bitmap+0x4f8/0xbc0 [drbd] This fixes an off-by-one error in the receive_bitmap() path, if run-length encoded bitmap transfer is enabled. If the bitmap is an exact multiple of PAGE_SIZE, which means the visible capacity of the drbd device is an exact multiple of 128 MiB (for 4k page size), and bitmap compression (use-rle) is enabled (which became default with 8.4), and the very last bit is dirty and reported in an rle comressed bitmap packet, we ended up trying to kmap_atomic a page pointer that does not exist (bitmap->bm_pages[last index + 1]). bug introduced by: Date: Fri Jul 24 15:33:24 2009 +0200 set bits: optimize for complete last word, fix off-by-one-word corner case made effective by: Date: Thu Dec 16 00:32:38 2010 +0100 drbd: get rid of unused debug code Long time ago, we had paranoia code in the bitmap that allocated one extra word, assigned a magic value, and checked on every occasion that the magic value was still unchanged. That debug code is unused, the extra long word complicates code a bit. Get rid of it. No-one triggered this bug in the last few years, because a large subset of our userbase is unaffected: * typically the last few blocks of a device are not modified frequently, and remain unset * use-rle was disabled by default in drbd < 8.4 * those with slightly "odd" device sizes, or * drbd internal meta data (which will skew the device size slightly, thus makes it harder to have a bug relevant device size) Signed-off-by: Philipp Reisner Signed-off-by: Lars Ellenberg --- drivers/block/drbd/drbd_bitmap.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) diff --git a/drivers/block/drbd/drbd_bitmap.c b/drivers/block/drbd/drbd_bitmap.c index b5c5ff53cb57..fcb956bb4b4c 100644 --- a/drivers/block/drbd/drbd_bitmap.c +++ b/drivers/block/drbd/drbd_bitmap.c @@ -1475,10 +1475,17 @@ void _drbd_bm_set_bits(struct drbd_conf *mdev, const unsigned long s, const unsi first_word = 0; spin_lock_irq(&b->bm_lock); } - /* last page (respectively only page, for first page == last page) */ last_word = MLPP(el >> LN2_BPL); - bm_set_full_words_within_one_page(mdev->bitmap, last_page, first_word, last_word); + + /* consider bitmap->bm_bits = 32768, bitmap->bm_number_of_pages = 1. (or multiples). + * ==> e = 32767, el = 32768, last_page = 2, + * and now last_word = 0. + * We do not want to touch last_page in this case, + * as we did not allocate it, it is not present in bitmap->bm_pages. + */ + if (last_word) + bm_set_full_words_within_one_page(mdev->bitmap, last_page, first_word, last_word); /* possibly trailing bits. * example: (e & 63) == 63, el will be e+1. -- cgit v1.2.3 From 1ed25b269e3dd5ecc64f17beef9ea21745c39ca6 Mon Sep 17 00:00:00 2001 From: Lars Ellenberg Date: Fri, 8 Jun 2012 14:09:54 +0200 Subject: drbd: fix list corruption by failing but already aborted reads If a read is aborted due to force-detach of a supposedly unresponsive local backing device, and retried on the peer, it can happen that the local request later still completes (hopefully with an error). As it may already have been completed to upper layers meanwhile, it must not be retried again now. Signed-off-by: Philipp Reisner Signed-off-by: Lars Ellenberg --- drivers/block/drbd/drbd_req.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/drivers/block/drbd/drbd_req.c b/drivers/block/drbd/drbd_req.c index 9c5c84946b05..773f4e2d3c1b 100644 --- a/drivers/block/drbd/drbd_req.c +++ b/drivers/block/drbd/drbd_req.c @@ -472,12 +472,17 @@ int __req_mod(struct drbd_request *req, enum drbd_req_event what, req->rq_state |= RQ_LOCAL_COMPLETED; req->rq_state &= ~RQ_LOCAL_PENDING; - D_ASSERT(!(req->rq_state & RQ_NET_MASK)); + if (req->rq_state & RQ_LOCAL_ABORTED) { + _req_may_be_done(req, m); + break; + } __drbd_chk_io_error(mdev, false); goto_queue_for_net_read: + D_ASSERT(!(req->rq_state & RQ_NET_MASK)); + /* no point in retrying if there is no good remote data, * or we have no connection. */ if (mdev->state.pdsk != D_UP_TO_DATE) { -- cgit v1.2.3 From 0d5934e3c258fc5decc4103600c597086fd95a52 Mon Sep 17 00:00:00 2001 From: Lars Ellenberg Date: Fri, 8 Jun 2012 14:17:36 +0200 Subject: drbd: fix null pointer dereference with on-congestion policy when diskless We must not look at mdev->actlog, unless we have a get_ldev() reference. It also does not make much sense to try to disconnect or pull-ahead of the peer, if we don't have good local data. Only even consider congestion policies, if our local disk is D_UP_TO_DATE. Signed-off-by: Philipp Reisner Signed-off-by: Lars Ellenberg --- drivers/block/drbd/drbd_req.c | 59 ++++++++++++++++++++++++++----------------- 1 file changed, 36 insertions(+), 23 deletions(-) diff --git a/drivers/block/drbd/drbd_req.c b/drivers/block/drbd/drbd_req.c index 773f4e2d3c1b..8e93a6ac9bb6 100644 --- a/drivers/block/drbd/drbd_req.c +++ b/drivers/block/drbd/drbd_req.c @@ -770,6 +770,40 @@ static int drbd_may_do_local_read(struct drbd_conf *mdev, sector_t sector, int s return 0 == drbd_bm_count_bits(mdev, sbnr, ebnr); } +static void maybe_pull_ahead(struct drbd_conf *mdev) +{ + int congested = 0; + + /* If I don't even have good local storage, we can not reasonably try + * to pull ahead of the peer. We also need the local reference to make + * sure mdev->act_log is there. + * Note: caller has to make sure that net_conf is there. + */ + if (!get_ldev_if_state(mdev, D_UP_TO_DATE)) + return; + + if (mdev->net_conf->cong_fill && + atomic_read(&mdev->ap_in_flight) >= mdev->net_conf->cong_fill) { + dev_info(DEV, "Congestion-fill threshold reached\n"); + congested = 1; + } + + if (mdev->act_log->used >= mdev->net_conf->cong_extents) { + dev_info(DEV, "Congestion-extents threshold reached\n"); + congested = 1; + } + + if (congested) { + queue_barrier(mdev); /* last barrier, after mirrored writes */ + + if (mdev->net_conf->on_congestion == OC_PULL_AHEAD) + _drbd_set_state(_NS(mdev, conn, C_AHEAD), 0, NULL); + else /*mdev->net_conf->on_congestion == OC_DISCONNECT */ + _drbd_set_state(_NS(mdev, conn, C_DISCONNECTING), 0, NULL); + } + put_ldev(mdev); +} + static int drbd_make_request_common(struct drbd_conf *mdev, struct bio *bio, unsigned long start_time) { const int rw = bio_rw(bio); @@ -977,29 +1011,8 @@ allocate_barrier: _req_mod(req, queue_for_send_oos); if (remote && - mdev->net_conf->on_congestion != OC_BLOCK && mdev->agreed_pro_version >= 96) { - int congested = 0; - - if (mdev->net_conf->cong_fill && - atomic_read(&mdev->ap_in_flight) >= mdev->net_conf->cong_fill) { - dev_info(DEV, "Congestion-fill threshold reached\n"); - congested = 1; - } - - if (mdev->act_log->used >= mdev->net_conf->cong_extents) { - dev_info(DEV, "Congestion-extents threshold reached\n"); - congested = 1; - } - - if (congested) { - queue_barrier(mdev); /* last barrier, after mirrored writes */ - - if (mdev->net_conf->on_congestion == OC_PULL_AHEAD) - _drbd_set_state(_NS(mdev, conn, C_AHEAD), 0, NULL); - else /*mdev->net_conf->on_congestion == OC_DISCONNECT */ - _drbd_set_state(_NS(mdev, conn, C_DISCONNECTING), 0, NULL); - } - } + mdev->net_conf->on_congestion != OC_BLOCK && mdev->agreed_pro_version >= 96) + maybe_pull_ahead(mdev); spin_unlock_irq(&mdev->req_lock); kfree(b); /* if someone else has beaten us to it... */ -- cgit v1.2.3 From 047fe3605235888f3ebcda0c728cb31937eadfe6 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 12 Jun 2012 15:24:40 +0200 Subject: splice: fix racy pipe->buffers uses Dave Jones reported a kernel BUG at mm/slub.c:3474! triggered by splice_shrink_spd() called from vmsplice_to_pipe() commit 35f3d14dbbc5 (pipe: add support for shrinking and growing pipes) added capability to adjust pipe->buffers. Problem is some paths don't hold pipe mutex and assume pipe->buffers doesn't change for their duration. Fix this by adding nr_pages_max field in struct splice_pipe_desc, and use it in place of pipe->buffers where appropriate. splice_shrink_spd() loses its struct pipe_inode_info argument. Reported-by: Dave Jones Signed-off-by: Eric Dumazet Cc: Jens Axboe Cc: Alexander Viro Cc: Tom Herbert Cc: stable # 2.6.35 Tested-by: Dave Jones Signed-off-by: Jens Axboe --- fs/splice.c | 35 ++++++++++++++++++++--------------- include/linux/splice.h | 8 ++++---- kernel/relay.c | 5 +++-- kernel/trace/trace.c | 6 ++++-- mm/shmem.c | 3 ++- net/core/skbuff.c | 1 + 6 files changed, 34 insertions(+), 24 deletions(-) diff --git a/fs/splice.c b/fs/splice.c index c9f1318a3b82..7bf08fa22ec9 100644 --- a/fs/splice.c +++ b/fs/splice.c @@ -273,13 +273,16 @@ void spd_release_page(struct splice_pipe_desc *spd, unsigned int i) * Check if we need to grow the arrays holding pages and partial page * descriptions. */ -int splice_grow_spd(struct pipe_inode_info *pipe, struct splice_pipe_desc *spd) +int splice_grow_spd(const struct pipe_inode_info *pipe, struct splice_pipe_desc *spd) { - if (pipe->buffers <= PIPE_DEF_BUFFERS) + unsigned int buffers = ACCESS_ONCE(pipe->buffers); + + spd->nr_pages_max = buffers; + if (buffers <= PIPE_DEF_BUFFERS) return 0; - spd->pages = kmalloc(pipe->buffers * sizeof(struct page *), GFP_KERNEL); - spd->partial = kmalloc(pipe->buffers * sizeof(struct partial_page), GFP_KERNEL); + spd->pages = kmalloc(buffers * sizeof(struct page *), GFP_KERNEL); + spd->partial = kmalloc(buffers * sizeof(struct partial_page), GFP_KERNEL); if (spd->pages && spd->partial) return 0; @@ -289,10 +292,9 @@ int splice_grow_spd(struct pipe_inode_info *pipe, struct splice_pipe_desc *spd) return -ENOMEM; } -void splice_shrink_spd(struct pipe_inode_info *pipe, - struct splice_pipe_desc *spd) +void splice_shrink_spd(struct splice_pipe_desc *spd) { - if (pipe->buffers <= PIPE_DEF_BUFFERS) + if (spd->nr_pages_max <= PIPE_DEF_BUFFERS) return; kfree(spd->pages); @@ -315,6 +317,7 @@ __generic_file_splice_read(struct file *in, loff_t *ppos, struct splice_pipe_desc spd = { .pages = pages, .partial = partial, + .nr_pages_max = PIPE_DEF_BUFFERS, .flags = flags, .ops = &page_cache_pipe_buf_ops, .spd_release = spd_release_page, @@ -326,7 +329,7 @@ __generic_file_splice_read(struct file *in, loff_t *ppos, index = *ppos >> PAGE_CACHE_SHIFT; loff = *ppos & ~PAGE_CACHE_MASK; req_pages = (len + loff + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT; - nr_pages = min(req_pages, pipe->buffers); + nr_pages = min(req_pages, spd.nr_pages_max); /* * Lookup the (hopefully) full range of pages we need. @@ -497,7 +500,7 @@ fill_it: if (spd.nr_pages) error = splice_to_pipe(pipe, &spd); - splice_shrink_spd(pipe, &spd); + splice_shrink_spd(&spd); return error; } @@ -598,6 +601,7 @@ ssize_t default_file_splice_read(struct file *in, loff_t *ppos, struct splice_pipe_desc spd = { .pages = pages, .partial = partial, + .nr_pages_max = PIPE_DEF_BUFFERS, .flags = flags, .ops = &default_pipe_buf_ops, .spd_release = spd_release_page, @@ -608,8 +612,8 @@ ssize_t default_file_splice_read(struct file *in, loff_t *ppos, res = -ENOMEM; vec = __vec; - if (pipe->buffers > PIPE_DEF_BUFFERS) { - vec = kmalloc(pipe->buffers * sizeof(struct iovec), GFP_KERNEL); + if (spd.nr_pages_max > PIPE_DEF_BUFFERS) { + vec = kmalloc(spd.nr_pages_max * sizeof(struct iovec), GFP_KERNEL); if (!vec) goto shrink_ret; } @@ -617,7 +621,7 @@ ssize_t default_file_splice_read(struct file *in, loff_t *ppos, offset = *ppos & ~PAGE_CACHE_MASK; nr_pages = (len + offset + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT; - for (i = 0; i < nr_pages && i < pipe->buffers && len; i++) { + for (i = 0; i < nr_pages && i < spd.nr_pages_max && len; i++) { struct page *page; page = alloc_page(GFP_USER); @@ -665,7 +669,7 @@ ssize_t default_file_splice_read(struct file *in, loff_t *ppos, shrink_ret: if (vec != __vec) kfree(vec); - splice_shrink_spd(pipe, &spd); + splice_shrink_spd(&spd); return res; err: @@ -1614,6 +1618,7 @@ static long vmsplice_to_pipe(struct file *file, const struct iovec __user *iov, struct splice_pipe_desc spd = { .pages = pages, .partial = partial, + .nr_pages_max = PIPE_DEF_BUFFERS, .flags = flags, .ops = &user_page_pipe_buf_ops, .spd_release = spd_release_page, @@ -1629,13 +1634,13 @@ static long vmsplice_to_pipe(struct file *file, const struct iovec __user *iov, spd.nr_pages = get_iovec_page_array(iov, nr_segs, spd.pages, spd.partial, false, - pipe->buffers); + spd.nr_pages_max); if (spd.nr_pages <= 0) ret = spd.nr_pages; else ret = splice_to_pipe(pipe, &spd); - splice_shrink_spd(pipe, &spd); + splice_shrink_spd(&spd); return ret; } diff --git a/include/linux/splice.h b/include/linux/splice.h index 26e5b613deda..09a545a7dfa3 100644 --- a/include/linux/splice.h +++ b/include/linux/splice.h @@ -51,7 +51,8 @@ struct partial_page { struct splice_pipe_desc { struct page **pages; /* page map */ struct partial_page *partial; /* pages[] may not be contig */ - int nr_pages; /* number of pages in map */ + int nr_pages; /* number of populated pages in map */ + unsigned int nr_pages_max; /* pages[] & partial[] arrays size */ unsigned int flags; /* splice flags */ const struct pipe_buf_operations *ops;/* ops associated with output pipe */ void (*spd_release)(struct splice_pipe_desc *, unsigned int); @@ -85,9 +86,8 @@ extern ssize_t splice_direct_to_actor(struct file *, struct splice_desc *, /* * for dynamic pipe sizing */ -extern int splice_grow_spd(struct pipe_inode_info *, struct splice_pipe_desc *); -extern void splice_shrink_spd(struct pipe_inode_info *, - struct splice_pipe_desc *); +extern int splice_grow_spd(const struct pipe_inode_info *, struct splice_pipe_desc *); +extern void splice_shrink_spd(struct splice_pipe_desc *); extern void spd_release_page(struct splice_pipe_desc *, unsigned int); extern const struct pipe_buf_operations page_cache_pipe_buf_ops; diff --git a/kernel/relay.c b/kernel/relay.c index ab56a1764d4d..e8cd2027abbd 100644 --- a/kernel/relay.c +++ b/kernel/relay.c @@ -1235,6 +1235,7 @@ static ssize_t subbuf_splice_actor(struct file *in, struct splice_pipe_desc spd = { .pages = pages, .nr_pages = 0, + .nr_pages_max = PIPE_DEF_BUFFERS, .partial = partial, .flags = flags, .ops = &relay_pipe_buf_ops, @@ -1302,8 +1303,8 @@ static ssize_t subbuf_splice_actor(struct file *in, ret += padding; out: - splice_shrink_spd(pipe, &spd); - return ret; + splice_shrink_spd(&spd); + return ret; } static ssize_t relay_file_splice_read(struct file *in, diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 68032c6177db..288488082224 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -3609,6 +3609,7 @@ static ssize_t tracing_splice_read_pipe(struct file *filp, .pages = pages_def, .partial = partial_def, .nr_pages = 0, /* This gets updated below. */ + .nr_pages_max = PIPE_DEF_BUFFERS, .flags = flags, .ops = &tracing_pipe_buf_ops, .spd_release = tracing_spd_release_pipe, @@ -3680,7 +3681,7 @@ static ssize_t tracing_splice_read_pipe(struct file *filp, ret = splice_to_pipe(pipe, &spd); out: - splice_shrink_spd(pipe, &spd); + splice_shrink_spd(&spd); return ret; out_err: @@ -4231,6 +4232,7 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos, struct splice_pipe_desc spd = { .pages = pages_def, .partial = partial_def, + .nr_pages_max = PIPE_DEF_BUFFERS, .flags = flags, .ops = &buffer_pipe_buf_ops, .spd_release = buffer_spd_release, @@ -4318,7 +4320,7 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos, } ret = splice_to_pipe(pipe, &spd); - splice_shrink_spd(pipe, &spd); + splice_shrink_spd(&spd); out: return ret; } diff --git a/mm/shmem.c b/mm/shmem.c index 585bd220a21e..c244e93a70fa 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -1577,6 +1577,7 @@ static ssize_t shmem_file_splice_read(struct file *in, loff_t *ppos, struct splice_pipe_desc spd = { .pages = pages, .partial = partial, + .nr_pages_max = PIPE_DEF_BUFFERS, .flags = flags, .ops = &page_cache_pipe_buf_ops, .spd_release = spd_release_page, @@ -1665,7 +1666,7 @@ static ssize_t shmem_file_splice_read(struct file *in, loff_t *ppos, if (spd.nr_pages) error = splice_to_pipe(pipe, &spd); - splice_shrink_spd(pipe, &spd); + splice_shrink_spd(&spd); if (error > 0) { *ppos += error; diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 016694d62484..bac3c5756d63 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -1755,6 +1755,7 @@ int skb_splice_bits(struct sk_buff *skb, unsigned int offset, struct splice_pipe_desc spd = { .pages = pages, .partial = partial, + .nr_pages_max = MAX_SKB_FRAGS, .flags = flags, .ops = &sock_pipe_buf_ops, .spd_release = sock_spd_release, -- cgit v1.2.3 From 32587371ad3db2f9d335de10dbd8cffd4fff5669 Mon Sep 17 00:00:00 2001 From: Tao Guo Date: Wed, 13 Jun 2012 21:17:21 +0200 Subject: umem: fix up unplugging Fix a regression introduced by 7eaceaccab5f40 ("block: remove per-queue plugging"). In that patch, Jens removed the whole mm_unplug_device() function, which used to be the trigger to make umem start to work. We need to implement unplugging to make umem start to work, or I/O will never be triggered. Signed-off-by: Tao Guo Cc: Neil Brown Cc: Jens Axboe Cc: Shaohua Li Cc: Acked-by: NeilBrown Signed-off-by: Jens Axboe --- drivers/block/umem.c | 40 ++++++++++++++++++++++++++++++++++++++++ 1 file changed, 40 insertions(+) diff --git a/drivers/block/umem.c b/drivers/block/umem.c index aa2712060bfb..9a72277a31df 100644 --- a/drivers/block/umem.c +++ b/drivers/block/umem.c @@ -513,6 +513,44 @@ static void process_page(unsigned long data) } } +struct mm_plug_cb { + struct blk_plug_cb cb; + struct cardinfo *card; +}; + +static void mm_unplug(struct blk_plug_cb *cb) +{ + struct mm_plug_cb *mmcb = container_of(cb, struct mm_plug_cb, cb); + + spin_lock_irq(&mmcb->card->lock); + activate(mmcb->card); + spin_unlock_irq(&mmcb->card->lock); + kfree(mmcb); +} + +static int mm_check_plugged(struct cardinfo *card) +{ + struct blk_plug *plug = current->plug; + struct mm_plug_cb *mmcb; + + if (!plug) + return 0; + + list_for_each_entry(mmcb, &plug->cb_list, cb.list) { + if (mmcb->cb.callback == mm_unplug && mmcb->card == card) + return 1; + } + /* Not currently on the callback list */ + mmcb = kmalloc(sizeof(*mmcb), GFP_ATOMIC); + if (!mmcb) + return 0; + + mmcb->card = card; + mmcb->cb.callback = mm_unplug; + list_add(&mmcb->cb.list, &plug->cb_list); + return 1; +} + static void mm_make_request(struct request_queue *q, struct bio *bio) { struct cardinfo *card = q->queuedata; @@ -523,6 +561,8 @@ static void mm_make_request(struct request_queue *q, struct bio *bio) *card->biotail = bio; bio->bi_next = NULL; card->biotail = &bio->bi_next; + if (bio->bi_rw & REQ_SYNC || !mm_check_plugged(card)) + activate(card); spin_unlock_irq(&card->lock); return; -- cgit v1.2.3 From 458f27a9823a0841acb4ca59e0e7f33e181f85e2 Mon Sep 17 00:00:00 2001 From: Asias He Date: Fri, 15 Jun 2012 08:45:25 +0200 Subject: block: Avoid missed wakeup in request waitqueue After hot-unplug a stressed disk, I found that rl->wait[] is not empty while rl->count[] is empty and there are theads still sleeping on get_request after the queue cleanup. With simple debug code, I found there are exactly nr_sleep - nr_wakeup of theads in D state. So there are missed wakeup. $ dmesg | grep nr_sleep [ 52.917115] ---> nr_sleep=1046, nr_wakeup=873, delta=173 $ vmstat 1 1 173 0 712640 24292 96172 0 0 0 0 419 757 0 0 0 100 0 To quote Tejun: Ah, okay, freed_request() wakes up single waiter with the assumption that after the wakeup there will at least be one successful allocation which in turn will continue the wakeup chain until the wait list is empty - ie. waiter wakeup is dependent on successful request allocation happening after each wakeup. With queue marked dead, any woken up waiter fails the allocation path, so the wakeup chaining is lost and we're left with hung waiters. What we need is wake_up_all() after drain completion. This patch fixes the missed wakeup by waking up all the theads which are sleeping on wait queue after queue drain. Changes in v2: Drop waitqueue_active() optimization Acked-by: Tejun Heo Signed-off-by: Asias He Fixed a bug by me, where stacked devices would oops on calling blk_drain_queue() since ->rq.wait[] do not get initialized unless it's a full queue setup. Signed-off-by: Jens Axboe --- block/blk-core.c | 15 ++++++++++++++- 1 file changed, 14 insertions(+), 1 deletion(-) diff --git a/block/blk-core.c b/block/blk-core.c index 3c923a7aeb56..ce7fbf8d85a6 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -361,9 +361,10 @@ EXPORT_SYMBOL(blk_put_queue); */ void blk_drain_queue(struct request_queue *q, bool drain_all) { + int i; + while (true) { bool drain = false; - int i; spin_lock_irq(q->queue_lock); @@ -408,6 +409,18 @@ void blk_drain_queue(struct request_queue *q, bool drain_all) break; msleep(10); } + + /* + * With queue marked dead, any woken up waiter will fail the + * allocation path, so the wakeup chaining is lost and we're + * left with hung waiters. We need to wake up those waiters. + */ + if (q->request_fn) { + spin_lock_irq(q->queue_lock); + for (i = 0; i < ARRAY_SIZE(q->rq.wait); i++) + wake_up_all(&q->rq.wait[i]); + spin_unlock_irq(q->queue_lock); + } } /** -- cgit v1.2.3 From 5e5cfac0c622d42eff4fa308e91b3c9c1884b4f0 Mon Sep 17 00:00:00 2001 From: Asias He Date: Thu, 24 May 2012 23:28:52 +0800 Subject: block: Mitigate lock unbalance caused by lock switching Commit 777eb1bf15b8532c396821774bf6451e563438f5 disconnects externally supplied queue_lock before blk_drain_queue(). Switching the lock would introduce lock unbalance because theads which have taken the external lock might unlock the internal lock in the during the queue drain. This patch mitigate this by disconnecting the lock after the queue draining since queue draining makes a lot of request_queue users go away. However, please note, this patch only makes the problem less likely to happen. Anyone who still holds a ref might try to issue a new request on a dead queue after the blk_cleanup_queue() finishes draining, the lock unbalance might still happen in this case. ===================================== [ BUG: bad unlock balance detected! ] 3.4.0+ #288 Not tainted ------------------------------------- fio/17706 is trying to release lock (&(&q->__queue_lock)->rlock) at: [] blk_queue_bio+0x2a2/0x380 but there are no more locks to release! other info that might help us debug this: 1 lock held by fio/17706: #0: (&(&vblk->lock)->rlock){......}, at: [] get_request_wait+0x19a/0x250 stack backtrace: Pid: 17706, comm: fio Not tainted 3.4.0+ #288 Call Trace: [] ? blk_queue_bio+0x2a2/0x380 [] print_unlock_inbalance_bug+0xf9/0x100 [] lock_release_non_nested+0x1df/0x330 [] ? dio_bio_end_aio+0x34/0xc0 [] ? bio_check_pages_dirty+0x85/0xe0 [] ? dio_bio_end_aio+0xb1/0xc0 [] ? blk_queue_bio+0x2a2/0x380 [] ? blk_queue_bio+0x2a2/0x380 [] lock_release+0xd9/0x250 [] _raw_spin_unlock_irq+0x23/0x40 [] blk_queue_bio+0x2a2/0x380 [] generic_make_request+0xca/0x100 [] submit_bio+0x76/0xf0 [] ? set_page_dirty_lock+0x3c/0x60 [] ? bio_set_pages_dirty+0x51/0x70 [] do_blockdev_direct_IO+0xbf8/0xee0 [] ? blkdev_get_block+0x80/0x80 [] __blockdev_direct_IO+0x55/0x60 [] ? blkdev_get_block+0x80/0x80 [] blkdev_direct_IO+0x57/0x60 [] ? blkdev_get_block+0x80/0x80 [] generic_file_aio_read+0x70e/0x760 [] ? __lock_acquire+0x215/0x5a0 [] ? aio_run_iocb+0x54/0x1a0 [] ? grab_cache_page_nowait+0xc0/0xc0 [] aio_rw_vect_retry+0x7c/0x1e0 [] ? aio_fsync+0x30/0x30 [] aio_run_iocb+0x66/0x1a0 [] do_io_submit+0x6f0/0xb80 [] ? trace_hardirqs_on_thunk+0x3a/0x3f [] sys_io_submit+0x10/0x20 [] system_call_fastpath+0x16/0x1b Changes since v2: Update commit log to explain how the code is still broken even if we delay the lock switching after the drain. Changes since v1: Update commit log as Tejun suggested. Acked-by: Tejun Heo Signed-off-by: Asias He Signed-off-by: Jens Axboe --- block/blk-core.c | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) diff --git a/block/blk-core.c b/block/blk-core.c index ce7fbf8d85a6..93eb3e4f88ce 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -480,7 +480,6 @@ void blk_cleanup_queue(struct request_queue *q) /* mark @q DEAD, no new request or merges will be allowed afterwards */ mutex_lock(&q->sysfs_lock); queue_flag_set_unlocked(QUEUE_FLAG_DEAD, q); - spin_lock_irq(lock); /* @@ -498,10 +497,6 @@ void blk_cleanup_queue(struct request_queue *q) queue_flag_set(QUEUE_FLAG_NOMERGES, q); queue_flag_set(QUEUE_FLAG_NOXMERGES, q); queue_flag_set(QUEUE_FLAG_DEAD, q); - - if (q->queue_lock != &q->__queue_lock) - q->queue_lock = &q->__queue_lock; - spin_unlock_irq(lock); mutex_unlock(&q->sysfs_lock); @@ -512,6 +507,11 @@ void blk_cleanup_queue(struct request_queue *q) del_timer_sync(&q->backing_dev_info.laptop_mode_wb_timer); blk_sync_queue(q); + spin_lock_irq(lock); + if (q->queue_lock != &q->__queue_lock) + q->queue_lock = &q->__queue_lock; + spin_unlock_irq(lock); + /* @q is and will stay empty, shutdown and put */ blk_put_queue(q); } -- cgit v1.2.3 From 76aaa5101fffaef12b45b4c01ed0d0528f23dedf Mon Sep 17 00:00:00 2001 From: Asias He Date: Thu, 14 Jun 2012 09:04:07 +0200 Subject: block: Drop dead function blk_abort_queue() This function was only used by btrfs code in btrfs_abort_devices() (seems in a wrong way). It was removed in commit d07eb9117050c9ed3f78296ebcc06128b52693be, So, Let's remove the dead code to avoid any confusion. Changes in v2: update commit log, btrfs_abort_devices() was removed already. Cc: Jens Axboe Cc: linux-kernel@vger.kernel.org Cc: Chris Mason Cc: linux-btrfs@vger.kernel.org Cc: David Sterba Signed-off-by: Asias He Signed-off-by: Jens Axboe --- block/blk-timeout.c | 41 ----------------------------------------- include/linux/blkdev.h | 1 - 2 files changed, 42 deletions(-) diff --git a/block/blk-timeout.c b/block/blk-timeout.c index 780354888958..6e4744cbfb56 100644 --- a/block/blk-timeout.c +++ b/block/blk-timeout.c @@ -197,44 +197,3 @@ void blk_add_timer(struct request *req) mod_timer(&q->timeout, expiry); } -/** - * blk_abort_queue -- Abort all request on given queue - * @queue: pointer to queue - * - */ -void blk_abort_queue(struct request_queue *q) -{ - unsigned long flags; - struct request *rq, *tmp; - LIST_HEAD(list); - - /* - * Not a request based block device, nothing to abort - */ - if (!q->request_fn) - return; - - spin_lock_irqsave(q->queue_lock, flags); - - elv_abort_queue(q); - - /* - * Splice entries to local list, to avoid deadlocking if entries - * get readded to the timeout list by error handling - */ - list_splice_init(&q->timeout_list, &list); - - list_for_each_entry_safe(rq, tmp, &list, timeout_list) - blk_abort_request(rq); - - /* - * Occasionally, blk_abort_request() will return without - * deleting the element from the list. Make sure we add those back - * instead of leaving them on the local stack list. - */ - list_splice(&list, &q->timeout_list); - - spin_unlock_irqrestore(q->queue_lock, flags); - -} -EXPORT_SYMBOL_GPL(blk_abort_queue); diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index ba43f408baa3..07954b05b86c 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -827,7 +827,6 @@ extern bool __blk_end_request_err(struct request *rq, int error); extern void blk_complete_request(struct request *); extern void __blk_complete_request(struct request *); extern void blk_abort_request(struct request *); -extern void blk_abort_queue(struct request_queue *); extern void blk_unprep_request(struct request *); /* -- cgit v1.2.3 From 6d9359280753d2955f86d6411047516a9431eb51 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Fri, 15 Jun 2012 12:52:46 +0200 Subject: scsi: Silence unnecessary warnings about ioctl to partition Sometimes, warnings about ioctls to partition happen often enough that they form majority of the warnings in the kernel log and users complain. In some cases warnings are about ioctls such as SG_IO so it's not good to get rid of the warnings completely as they can ease debugging of userspace problems when ioctl is refused. Since I have seen warnings from lots of commands, including some proprietary userspace applications, I don't think disallowing the ioctls for processes with CAP_SYS_RAWIO will happen in the near future if ever. So lets just stop warning for processes with CAP_SYS_RAWIO for which ioctl is allowed. CC: Paolo Bonzini CC: James Bottomley CC: linux-scsi@vger.kernel.org Acked-by: Paolo Bonzini Signed-off-by: Jan Kara Signed-off-by: Jens Axboe --- block/scsi_ioctl.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/block/scsi_ioctl.c b/block/scsi_ioctl.c index 260fa80ef575..9a87daa6f4fb 100644 --- a/block/scsi_ioctl.c +++ b/block/scsi_ioctl.c @@ -721,11 +721,14 @@ int scsi_verify_blk_ioctl(struct block_device *bd, unsigned int cmd) break; } + if (capable(CAP_SYS_RAWIO)) + return 0; + /* In particular, rule out all resets and host-specific ioctls. */ printk_ratelimited(KERN_WARNING "%s: sending ioctl %x to a partition!\n", current->comm, cmd); - return capable(CAP_SYS_RAWIO) ? 0 : -ENOIOCTLCMD; + return -ENOIOCTLCMD; } EXPORT_SYMBOL(scsi_verify_blk_ioctl); -- cgit v1.2.3