From f5944daa0a72316077435c18a6571e73ed338332 Mon Sep 17 00:00:00 2001 From: Anton Blanchard Date: Thu, 8 Aug 2013 17:47:34 +1000 Subject: [PATCH 1/5] [SCSI] lpfc: Don't force CONFIG_GENERIC_CSUM on We want ppc64 to be able to select between optimised assembly checksum routines in big endian and the generic lib/checksum.c routines in little endian. The lpfc driver is forcing CONFIG_GENERIC_CSUM on which means we are unable to make the decision to enable it in the arch Kconfig. If the option exists it is always forced on. This got introduced in 3.10 via commit 6a7252fdb0c3 ([SCSI] lpfc: fix up Kconfig dependencies). I spoke to Randy about it and the original issue was with CRC_T10DIF not being defined. As such, remove the select of CONFIG_GENERIC_CSUM. Signed-off-by: Anton Blanchard Cc: # 3.10 Signed-off-by: James Bottomley --- drivers/scsi/Kconfig | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/scsi/Kconfig b/drivers/scsi/Kconfig index 48b2918e0d65..92ff027746f2 100644 --- a/drivers/scsi/Kconfig +++ b/drivers/scsi/Kconfig @@ -1353,7 +1353,6 @@ config SCSI_LPFC tristate "Emulex LightPulse Fibre Channel Support" depends on PCI && SCSI select SCSI_FC_ATTRS - select GENERIC_CSUM select CRC_T10DIF help This lpfc driver supports the Emulex LightPulse From 35dc248383bbab0a7203fca4d722875bc81ef091 Mon Sep 17 00:00:00 2001 From: Roland Dreier Date: Mon, 5 Aug 2013 17:55:01 -0700 Subject: [PATCH 2/5] [SCSI] sg: Fix user memory corruption when SG_IO is interrupted by a signal There is a nasty bug in the SCSI SG_IO ioctl that in some circumstances leads to one process writing data into the address space of some other random unrelated process if the ioctl is interrupted by a signal. What happens is the following: - A process issues an SG_IO ioctl with direction DXFER_FROM_DEV (ie the underlying SCSI command will transfer data from the SCSI device to the buffer provided in the ioctl) - Before the command finishes, a signal is sent to the process waiting in the ioctl. This will end up waking up the sg_ioctl() code: result = wait_event_interruptible(sfp->read_wait, (srp_done(sfp, srp) || sdp->detached)); but neither srp_done() nor sdp->detached is true, so we end up just setting srp->orphan and returning to userspace: srp->orphan = 1; write_unlock_irq(&sfp->rq_list_lock); return result; /* -ERESTARTSYS because signal hit process */ At this point the original process is done with the ioctl and blithely goes ahead handling the signal, reissuing the ioctl, etc. - Eventually, the SCSI command issued by the first ioctl finishes and ends up in sg_rq_end_io(). At the end of that function, we run through: write_lock_irqsave(&sfp->rq_list_lock, iflags); if (unlikely(srp->orphan)) { if (sfp->keep_orphan) srp->sg_io_owned = 0; else done = 0; } srp->done = done; write_unlock_irqrestore(&sfp->rq_list_lock, iflags); if (likely(done)) { /* Now wake up any sg_read() that is waiting for this * packet. */ wake_up_interruptible(&sfp->read_wait); kill_fasync(&sfp->async_qp, SIGPOLL, POLL_IN); kref_put(&sfp->f_ref, sg_remove_sfp); } else { INIT_WORK(&srp->ew.work, sg_rq_end_io_usercontext); schedule_work(&srp->ew.work); } Since srp->orphan *is* set, we set done to 0 (assuming the userspace app has not set keep_orphan via an SG_SET_KEEP_ORPHAN ioctl), and therefore we end up scheduling sg_rq_end_io_usercontext() to run in a workqueue. - In workqueue context we go through sg_rq_end_io_usercontext() -> sg_finish_rem_req() -> blk_rq_unmap_user() -> ... -> bio_uncopy_user() -> __bio_copy_iov() -> copy_to_user(). The key point here is that we are doing copy_to_user() on a workqueue -- that is, we're on a kernel thread with current->mm equal to whatever random previous user process was scheduled before this kernel thread. So we end up copying whatever data the SCSI command returned to the virtual address of the buffer passed into the original ioctl, but it's quite likely we do this copying into a different address space! As suggested by James Bottomley , add a check for current->mm (which is NULL if we're on a kernel thread without a real userspace address space) in bio_uncopy_user(), and skip the copy if we're on a kernel thread. There's no reason that I can think of for any caller of bio_uncopy_user() to want to do copying on a kernel thread with a random active userspace address space. Huge thanks to Costa Sapuntzakis for the original pointer to this bug in the sg code. Signed-off-by: Roland Dreier Tested-by: David Milburn Cc: Jens Axboe Cc: Signed-off-by: James Bottomley --- fs/bio.c | 20 +++++++++++++++----- 1 file changed, 15 insertions(+), 5 deletions(-) diff --git a/fs/bio.c b/fs/bio.c index 94bbc04dba77..c5eae7251490 100644 --- a/fs/bio.c +++ b/fs/bio.c @@ -1045,12 +1045,22 @@ static int __bio_copy_iov(struct bio *bio, struct bio_vec *iovecs, int bio_uncopy_user(struct bio *bio) { struct bio_map_data *bmd = bio->bi_private; - int ret = 0; + struct bio_vec *bvec; + int ret = 0, i; - if (!bio_flagged(bio, BIO_NULL_MAPPED)) - ret = __bio_copy_iov(bio, bmd->iovecs, bmd->sgvecs, - bmd->nr_sgvecs, bio_data_dir(bio) == READ, - 0, bmd->is_our_pages); + if (!bio_flagged(bio, BIO_NULL_MAPPED)) { + /* + * if we're in a workqueue, the request is orphaned, so + * don't copy into a random user address space, just free. + */ + if (current->mm) + ret = __bio_copy_iov(bio, bmd->iovecs, bmd->sgvecs, + bmd->nr_sgvecs, bio_data_dir(bio) == READ, + 0, bmd->is_our_pages); + else if (bmd->is_our_pages) + bio_for_each_segment_all(bvec, bio, i) + __free_page(bvec->bv_page); + } bio_free_map_data(bmd); bio_put(bio); return ret; From d79ff142624e1be080ad8d09101f7004d79c36e1 Mon Sep 17 00:00:00 2001 From: Martin Peschke Date: Thu, 22 Aug 2013 17:45:36 +0200 Subject: [PATCH 3/5] [SCSI] zfcp: fix lock imbalance by reworking request queue locking This patch adds wait_event_interruptible_lock_irq_timeout(), which is a straight-forward descendant of wait_event_interruptible_timeout() and wait_event_interruptible_lock_irq(). The zfcp driver used to call wait_event_interruptible_timeout() in combination with some intricate and error-prone locking. Using wait_event_interruptible_lock_irq_timeout() as a replacement nicely cleans up that locking. This rework removes a situation that resulted in a locking imbalance in zfcp_qdio_sbal_get(): BUG: workqueue leaked lock or atomic: events/1/0xffffff00/10 last function: zfcp_fc_wka_port_offline+0x0/0xa0 [zfcp] It was introduced by commit c2af7545aaff3495d9bf9a7608c52f0af86fb194 "[SCSI] zfcp: Do not wait for SBALs on stopped queue", which had a new code path related to ZFCP_STATUS_ADAPTER_QDIOUP that took an early exit without a required lock being held. The problem occured when a special, non-SCSI I/O request was being submitted in process context, when the adapter's queues had been torn down. In this case the bug surfaced when the Fibre Channel port connection for a well-known address was closed during a concurrent adapter shut-down procedure, which is a rare constellation. This patch also fixes these warnings from the sparse tool (make C=1): drivers/s390/scsi/zfcp_qdio.c:224:12: warning: context imbalance in 'zfcp_qdio_sbal_check' - wrong count at exit drivers/s390/scsi/zfcp_qdio.c:244:5: warning: context imbalance in 'zfcp_qdio_sbal_get' - unexpected unlock Last but not least, we get rid of that crappy lock-unlock-lock sequence at the beginning of the critical section. It is okay to call zfcp_erp_adapter_reopen() with req_q_lock held. Reported-by: Mikulas Patocka Reported-by: Heiko Carstens Signed-off-by: Martin Peschke Cc: stable@vger.kernel.org #2.6.35+ Signed-off-by: Steffen Maier Signed-off-by: James Bottomley --- drivers/s390/scsi/zfcp_qdio.c | 8 ++--- include/linux/wait.h | 57 +++++++++++++++++++++++++++++++++++ 2 files changed, 59 insertions(+), 6 deletions(-) diff --git a/drivers/s390/scsi/zfcp_qdio.c b/drivers/s390/scsi/zfcp_qdio.c index 665e3cfaaf85..de0598eaacd2 100644 --- a/drivers/s390/scsi/zfcp_qdio.c +++ b/drivers/s390/scsi/zfcp_qdio.c @@ -224,11 +224,9 @@ int zfcp_qdio_sbals_from_sg(struct zfcp_qdio *qdio, struct zfcp_qdio_req *q_req, static int zfcp_qdio_sbal_check(struct zfcp_qdio *qdio) { - spin_lock_irq(&qdio->req_q_lock); if (atomic_read(&qdio->req_q_free) || !(atomic_read(&qdio->adapter->status) & ZFCP_STATUS_ADAPTER_QDIOUP)) return 1; - spin_unlock_irq(&qdio->req_q_lock); return 0; } @@ -246,9 +244,8 @@ int zfcp_qdio_sbal_get(struct zfcp_qdio *qdio) { long ret; - spin_unlock_irq(&qdio->req_q_lock); - ret = wait_event_interruptible_timeout(qdio->req_q_wq, - zfcp_qdio_sbal_check(qdio), 5 * HZ); + ret = wait_event_interruptible_lock_irq_timeout(qdio->req_q_wq, + zfcp_qdio_sbal_check(qdio), qdio->req_q_lock, 5 * HZ); if (!(atomic_read(&qdio->adapter->status) & ZFCP_STATUS_ADAPTER_QDIOUP)) return -EIO; @@ -262,7 +259,6 @@ int zfcp_qdio_sbal_get(struct zfcp_qdio *qdio) zfcp_erp_adapter_reopen(qdio->adapter, 0, "qdsbg_1"); } - spin_lock_irq(&qdio->req_q_lock); return -EIO; } diff --git a/include/linux/wait.h b/include/linux/wait.h index f487a4750b7f..a67fc1635592 100644 --- a/include/linux/wait.h +++ b/include/linux/wait.h @@ -811,6 +811,63 @@ do { \ __ret; \ }) +#define __wait_event_interruptible_lock_irq_timeout(wq, condition, \ + lock, ret) \ +do { \ + DEFINE_WAIT(__wait); \ + \ + for (;;) { \ + prepare_to_wait(&wq, &__wait, TASK_INTERRUPTIBLE); \ + if (condition) \ + break; \ + if (signal_pending(current)) { \ + ret = -ERESTARTSYS; \ + break; \ + } \ + spin_unlock_irq(&lock); \ + ret = schedule_timeout(ret); \ + spin_lock_irq(&lock); \ + if (!ret) \ + break; \ + } \ + finish_wait(&wq, &__wait); \ +} while (0) + +/** + * wait_event_interruptible_lock_irq_timeout - sleep until a condition gets true or a timeout elapses. + * The condition is checked under the lock. This is expected + * to be called with the lock taken. + * @wq: the waitqueue to wait on + * @condition: a C expression for the event to wait for + * @lock: a locked spinlock_t, which will be released before schedule() + * and reacquired afterwards. + * @timeout: timeout, in jiffies + * + * The process is put to sleep (TASK_INTERRUPTIBLE) until the + * @condition evaluates to true or signal is received. The @condition is + * checked each time the waitqueue @wq is woken up. + * + * wake_up() has to be called after changing any variable that could + * change the result of the wait condition. + * + * This is supposed to be called while holding the lock. The lock is + * dropped before going to sleep and is reacquired afterwards. + * + * The function returns 0 if the @timeout elapsed, -ERESTARTSYS if it + * was interrupted by a signal, and the remaining jiffies otherwise + * if the condition evaluated to true before the timeout elapsed. + */ +#define wait_event_interruptible_lock_irq_timeout(wq, condition, lock, \ + timeout) \ +({ \ + int __ret = timeout; \ + \ + if (!(condition)) \ + __wait_event_interruptible_lock_irq_timeout( \ + wq, condition, lock, __ret); \ + __ret; \ +}) + /* * These are the old interfaces to sleep waiting for an event. From 924dd584b198a58aa7cb3efefd8a03326550ce8f Mon Sep 17 00:00:00 2001 From: Martin Peschke Date: Thu, 22 Aug 2013 17:45:37 +0200 Subject: [PATCH 4/5] [SCSI] zfcp: fix schedule-inside-lock in scsi_device list loops BUG: sleeping function called from invalid context at kernel/workqueue.c:2752 in_atomic(): 1, irqs_disabled(): 1, pid: 360, name: zfcperp0.0.1700 CPU: 1 Not tainted 3.9.3+ #69 Process zfcperp0.0.1700 (pid: 360, task: 0000000075b7e080, ksp: 000000007476bc30) Call Trace: ([<00000000001165de>] show_trace+0x106/0x154) [<00000000001166a0>] show_stack+0x74/0xf4 [<00000000006ff646>] dump_stack+0xc6/0xd4 [<000000000017f3a0>] __might_sleep+0x128/0x148 [<000000000015ece8>] flush_work+0x54/0x1f8 [<00000000001630de>] __cancel_work_timer+0xc6/0x128 [<00000000005067ac>] scsi_device_dev_release_usercontext+0x164/0x23c [<0000000000161816>] execute_in_process_context+0x96/0xa8 [<00000000004d33d8>] device_release+0x60/0xc0 [<000000000048af48>] kobject_release+0xa8/0x1c4 [<00000000004f4bf2>] __scsi_iterate_devices+0xfa/0x130 [<000003ff801b307a>] zfcp_erp_strategy+0x4da/0x1014 [zfcp] [<000003ff801b3caa>] zfcp_erp_thread+0xf6/0x2b0 [zfcp] [<000000000016b75a>] kthread+0xf2/0xfc [<000000000070c9de>] kernel_thread_starter+0x6/0xc [<000000000070c9d8>] kernel_thread_starter+0x0/0xc Apparently, the ref_count for some scsi_device drops down to zero, triggering device removal through execute_in_process_context(), while the lldd error recovery thread iterates through a scsi device list. Unfortunately, execute_in_process_context() decides to immediately execute that device removal function, instead of scheduling asynchronous execution, since it detects process context and thinks it is safe to do so. But almost all calls to shost_for_each_device() in our lldd are inside spin_lock_irq, even in thread context. Obviously, schedule() inside spin_lock_irq sections is a bad idea. Change the lldd to use the proper iterator function, __shost_for_each_device(), in combination with required locking. Occurences that need to be changed include all calls in zfcp_erp.c, since those might be executed in zfcp error recovery thread context with a lock held. Other occurences of shost_for_each_device() in zfcp_fsf.c do not need to be changed (no process context, no surrounding locking). The problem was introduced in Linux 2.6.37 by commit b62a8d9b45b971a67a0f8413338c230e3117dff5 "[SCSI] zfcp: Use SCSI device data zfcp_scsi_dev instead of zfcp_unit". Reported-by: Christian Borntraeger Signed-off-by: Martin Peschke Cc: stable@vger.kernel.org #2.6.37+ Signed-off-by: Steffen Maier Signed-off-by: James Bottomley --- drivers/s390/scsi/zfcp_erp.c | 29 ++++++++++++++++++++++------- 1 file changed, 22 insertions(+), 7 deletions(-) diff --git a/drivers/s390/scsi/zfcp_erp.c b/drivers/s390/scsi/zfcp_erp.c index 1d4c8fe72752..c82fe65c4128 100644 --- a/drivers/s390/scsi/zfcp_erp.c +++ b/drivers/s390/scsi/zfcp_erp.c @@ -102,10 +102,13 @@ static void zfcp_erp_action_dismiss_port(struct zfcp_port *port) if (atomic_read(&port->status) & ZFCP_STATUS_COMMON_ERP_INUSE) zfcp_erp_action_dismiss(&port->erp_action); - else - shost_for_each_device(sdev, port->adapter->scsi_host) + else { + spin_lock(port->adapter->scsi_host->host_lock); + __shost_for_each_device(sdev, port->adapter->scsi_host) if (sdev_to_zfcp(sdev)->port == port) zfcp_erp_action_dismiss_lun(sdev); + spin_unlock(port->adapter->scsi_host->host_lock); + } } static void zfcp_erp_action_dismiss_adapter(struct zfcp_adapter *adapter) @@ -592,9 +595,11 @@ static void _zfcp_erp_lun_reopen_all(struct zfcp_port *port, int clear, { struct scsi_device *sdev; - shost_for_each_device(sdev, port->adapter->scsi_host) + spin_lock(port->adapter->scsi_host->host_lock); + __shost_for_each_device(sdev, port->adapter->scsi_host) if (sdev_to_zfcp(sdev)->port == port) _zfcp_erp_lun_reopen(sdev, clear, id, 0); + spin_unlock(port->adapter->scsi_host->host_lock); } static void zfcp_erp_strategy_followup_failed(struct zfcp_erp_action *act) @@ -1434,8 +1439,10 @@ void zfcp_erp_set_adapter_status(struct zfcp_adapter *adapter, u32 mask) atomic_set_mask(common_mask, &port->status); read_unlock_irqrestore(&adapter->port_list_lock, flags); - shost_for_each_device(sdev, adapter->scsi_host) + spin_lock_irqsave(adapter->scsi_host->host_lock, flags); + __shost_for_each_device(sdev, adapter->scsi_host) atomic_set_mask(common_mask, &sdev_to_zfcp(sdev)->status); + spin_unlock_irqrestore(adapter->scsi_host->host_lock, flags); } /** @@ -1469,11 +1476,13 @@ void zfcp_erp_clear_adapter_status(struct zfcp_adapter *adapter, u32 mask) } read_unlock_irqrestore(&adapter->port_list_lock, flags); - shost_for_each_device(sdev, adapter->scsi_host) { + spin_lock_irqsave(adapter->scsi_host->host_lock, flags); + __shost_for_each_device(sdev, adapter->scsi_host) { atomic_clear_mask(common_mask, &sdev_to_zfcp(sdev)->status); if (clear_counter) atomic_set(&sdev_to_zfcp(sdev)->erp_counter, 0); } + spin_unlock_irqrestore(adapter->scsi_host->host_lock, flags); } /** @@ -1487,16 +1496,19 @@ void zfcp_erp_set_port_status(struct zfcp_port *port, u32 mask) { struct scsi_device *sdev; u32 common_mask = mask & ZFCP_COMMON_FLAGS; + unsigned long flags; atomic_set_mask(mask, &port->status); if (!common_mask) return; - shost_for_each_device(sdev, port->adapter->scsi_host) + spin_lock_irqsave(port->adapter->scsi_host->host_lock, flags); + __shost_for_each_device(sdev, port->adapter->scsi_host) if (sdev_to_zfcp(sdev)->port == port) atomic_set_mask(common_mask, &sdev_to_zfcp(sdev)->status); + spin_unlock_irqrestore(port->adapter->scsi_host->host_lock, flags); } /** @@ -1511,6 +1523,7 @@ void zfcp_erp_clear_port_status(struct zfcp_port *port, u32 mask) struct scsi_device *sdev; u32 common_mask = mask & ZFCP_COMMON_FLAGS; u32 clear_counter = mask & ZFCP_STATUS_COMMON_ERP_FAILED; + unsigned long flags; atomic_clear_mask(mask, &port->status); @@ -1520,13 +1533,15 @@ void zfcp_erp_clear_port_status(struct zfcp_port *port, u32 mask) if (clear_counter) atomic_set(&port->erp_counter, 0); - shost_for_each_device(sdev, port->adapter->scsi_host) + spin_lock_irqsave(port->adapter->scsi_host->host_lock, flags); + __shost_for_each_device(sdev, port->adapter->scsi_host) if (sdev_to_zfcp(sdev)->port == port) { atomic_clear_mask(common_mask, &sdev_to_zfcp(sdev)->status); if (clear_counter) atomic_set(&sdev_to_zfcp(sdev)->erp_counter, 0); } + spin_unlock_irqrestore(port->adapter->scsi_host->host_lock, flags); } /** From b5dc3c4800cc5c2c0b3c93a97eb4c7afa0aae49a Mon Sep 17 00:00:00 2001 From: Martin Peschke Date: Thu, 22 Aug 2013 17:45:38 +0200 Subject: [PATCH 5/5] [SCSI] zfcp: remove access control tables interface (keep sysfs files) By popular demand, this patch brings back a couple of sysfs attributes removed by commit 663e0890e31cb85f0cca5ac1faaee0d2d52880b5 "[SCSI] zfcp: remove access control tables interface". The content has been irrelevant for years, but the files must be there forever for whatever user space tools that may rely on them. Since these files always return a constant value, a new stripped down show-macro was required. Otherwise build warnings would have been introduced. Signed-off-by: Martin Peschke Signed-off-by: Steffen Maier Signed-off-by: James Bottomley --- drivers/s390/scsi/zfcp_sysfs.c | 14 ++++++++++++++ 1 file changed, 14 insertions(+) diff --git a/drivers/s390/scsi/zfcp_sysfs.c b/drivers/s390/scsi/zfcp_sysfs.c index 3f01bbf0609f..890639274bcf 100644 --- a/drivers/s390/scsi/zfcp_sysfs.c +++ b/drivers/s390/scsi/zfcp_sysfs.c @@ -27,6 +27,16 @@ static ssize_t zfcp_sysfs_##_feat##_##_name##_show(struct device *dev, \ static ZFCP_DEV_ATTR(_feat, _name, S_IRUGO, \ zfcp_sysfs_##_feat##_##_name##_show, NULL); +#define ZFCP_DEFINE_ATTR_CONST(_feat, _name, _format, _value) \ +static ssize_t zfcp_sysfs_##_feat##_##_name##_show(struct device *dev, \ + struct device_attribute *at,\ + char *buf) \ +{ \ + return sprintf(buf, _format, _value); \ +} \ +static ZFCP_DEV_ATTR(_feat, _name, S_IRUGO, \ + zfcp_sysfs_##_feat##_##_name##_show, NULL); + #define ZFCP_DEFINE_A_ATTR(_name, _format, _value) \ static ssize_t zfcp_sysfs_adapter_##_name##_show(struct device *dev, \ struct device_attribute *at,\ @@ -75,6 +85,8 @@ ZFCP_DEFINE_ATTR(zfcp_unit, unit, in_recovery, "%d\n", ZFCP_DEFINE_ATTR(zfcp_unit, unit, access_denied, "%d\n", (zfcp_unit_sdev_status(unit) & ZFCP_STATUS_COMMON_ACCESS_DENIED) != 0); +ZFCP_DEFINE_ATTR_CONST(unit, access_shared, "%d\n", 0); +ZFCP_DEFINE_ATTR_CONST(unit, access_readonly, "%d\n", 0); static ssize_t zfcp_sysfs_port_failed_show(struct device *dev, struct device_attribute *attr, @@ -347,6 +359,8 @@ static struct attribute *zfcp_unit_attrs[] = { &dev_attr_unit_in_recovery.attr, &dev_attr_unit_status.attr, &dev_attr_unit_access_denied.attr, + &dev_attr_unit_access_shared.attr, + &dev_attr_unit_access_readonly.attr, NULL }; static struct attribute_group zfcp_unit_attr_group = {