diff options
65 files changed, 676 insertions, 278 deletions
diff --git a/Documentation/block/null_blk.txt b/Documentation/block/null_blk.txt new file mode 100644 index 000000000000..b2830b435895 --- /dev/null +++ b/Documentation/block/null_blk.txt @@ -0,0 +1,72 @@ +Null block device driver +================================================================================ + +I. Overview + +The null block device (/dev/nullb*) is used for benchmarking the various +block-layer implementations. It emulates a block device of X gigabytes in size. +The following instances are possible: + + Single-queue block-layer + - Request-based. + - Single submission queue per device. + - Implements IO scheduling algorithms (CFQ, Deadline, noop). + Multi-queue block-layer + - Request-based. + - Configurable submission queues per device. + No block-layer (Known as bio-based) + - Bio-based. IO requests are submitted directly to the device driver. + - Directly accepts bio data structure and returns them. + +All of them have a completion queue for each core in the system. + +II. Module parameters applicable for all instances: + +queue_mode=[0-2]: Default: 2-Multi-queue + Selects which block-layer the module should instantiate with. + + 0: Bio-based. + 1: Single-queue. + 2: Multi-queue. + +home_node=[0--nr_nodes]: Default: NUMA_NO_NODE + Selects what CPU node the data structures are allocated from. + +gb=[Size in GB]: Default: 250GB + The size of the device reported to the system. + +bs=[Block size (in bytes)]: Default: 512 bytes + The block size reported to the system. + +nr_devices=[Number of devices]: Default: 2 + Number of block devices instantiated. They are instantiated as /dev/nullb0, + etc. + +irq_mode=[0-2]: Default: 1-Soft-irq + The completion mode used for completing IOs to the block-layer. + + 0: None. + 1: Soft-irq. Uses IPI to complete IOs across CPU nodes. Simulates the overhead + when IOs are issued from another CPU node than the home the device is + connected to. + 2: Timer: Waits a specific period (completion_nsec) for each IO before + completion. + +completion_nsec=[ns]: Default: 10.000ns + Combined with irq_mode=2 (timer). The time each completion event must wait. + +submit_queues=[0..nr_cpus]: + The number of submission queues attached to the device driver. If unset, it + defaults to 1 on single-queue and bio-based instances. For multi-queue, + it is ignored when use_per_node_hctx module parameter is 1. + +hw_queue_depth=[0..qdepth]: Default: 64 + The hardware queue depth of the device. + +III: Multi-queue specific parameters + +use_per_node_hctx=[0/1]: Default: 0 + 0: The number of submit queues are set to the value of the submit_queues + parameter. + 1: The multi-queue block layer is instantiated with a hardware dispatch + queue for each CPU node in the system. diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index 50680a59a2ff..b9e9bd854298 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -1529,6 +1529,8 @@ bytes respectively. Such letter suffixes can also be entirely omitted. * atapi_dmadir: Enable ATAPI DMADIR bridge support + * disable: Disable this device. + If there are multiple matching configurations changing the same attribute, the last one is used. diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c index dc1ec0dff939..ea04b342c026 100644 --- a/arch/x86/kernel/cpu/intel.c +++ b/arch/x86/kernel/cpu/intel.c @@ -387,7 +387,8 @@ static void init_intel(struct cpuinfo_x86 *c) set_cpu_cap(c, X86_FEATURE_PEBS); } - if (c->x86 == 6 && c->x86_model == 29 && cpu_has_clflush) + if (c->x86 == 6 && cpu_has_clflush && + (c->x86_model == 29 || c->x86_model == 46 || c->x86_model == 47)) set_cpu_cap(c, X86_FEATURE_CLFLUSH_MONITOR); #ifdef CONFIG_X86_64 diff --git a/block/blk-mq-sysfs.c b/block/blk-mq-sysfs.c index ba6cf8e9aa0a..b91ce75bd35d 100644 --- a/block/blk-mq-sysfs.c +++ b/block/blk-mq-sysfs.c @@ -335,9 +335,22 @@ static struct kobj_type blk_mq_hw_ktype = { void blk_mq_unregister_disk(struct gendisk *disk) { struct request_queue *q = disk->queue; + struct blk_mq_hw_ctx *hctx; + struct blk_mq_ctx *ctx; + int i, j; + + queue_for_each_hw_ctx(q, hctx, i) { + hctx_for_each_ctx(hctx, ctx, j) { + kobject_del(&ctx->kobj); + kobject_put(&ctx->kobj); + } + kobject_del(&hctx->kobj); + kobject_put(&hctx->kobj); + } kobject_uevent(&q->mq_kobj, KOBJ_REMOVE); kobject_del(&q->mq_kobj); + kobject_put(&q->mq_kobj); kobject_put(&disk_to_dev(disk)->kobj); } diff --git a/drivers/acpi/Kconfig b/drivers/acpi/Kconfig index 5d9248526d78..4770de5707b9 100644 --- a/drivers/acpi/Kconfig +++ b/drivers/acpi/Kconfig @@ -348,7 +348,6 @@ source "drivers/acpi/apei/Kconfig" config ACPI_EXTLOG tristate "Extended Error Log support" depends on X86_MCE && X86_LOCAL_APIC - select EFI select UEFI_CPER default n help diff --git a/drivers/acpi/acpi_lpss.c b/drivers/acpi/acpi_lpss.c index 6745fe137b9e..e60390597372 100644 --- a/drivers/acpi/acpi_lpss.c +++ b/drivers/acpi/acpi_lpss.c @@ -162,6 +162,7 @@ static const struct acpi_device_id acpi_lpss_device_ids[] = { { "80860F14", (unsigned long)&byt_sdio_dev_desc }, { "80860F41", (unsigned long)&byt_i2c_dev_desc }, { "INT33B2", }, + { "INT33FC", }, { "INT3430", (unsigned long)&lpt_dev_desc }, { "INT3431", (unsigned long)&lpt_dev_desc }, diff --git a/drivers/acpi/apei/Kconfig b/drivers/acpi/apei/Kconfig index 786294bb682c..3650b2183227 100644 --- a/drivers/acpi/apei/Kconfig +++ b/drivers/acpi/apei/Kconfig @@ -2,7 +2,6 @@ config ACPI_APEI bool "ACPI Platform Error Interface (APEI)" select MISC_FILESYSTEMS select PSTORE - select EFI select UEFI_CPER depends on X86 help diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c index 14f1e9506338..c0ed4f273cf2 100644 --- a/drivers/ata/ahci.c +++ b/drivers/ata/ahci.c @@ -1238,15 +1238,6 @@ static int ahci_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) if (rc) return rc; - /* AHCI controllers often implement SFF compatible interface. - * Grab all PCI BARs just in case. - */ - rc = pcim_iomap_regions_request_all(pdev, 1 << ahci_pci_bar, DRV_NAME); - if (rc == -EBUSY) - pcim_pin_device(pdev); - if (rc) - return rc; - if (pdev->vendor == PCI_VENDOR_ID_INTEL && (pdev->device == 0x2652 || pdev->device == 0x2653)) { u8 map; @@ -1263,6 +1254,15 @@ static int ahci_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) } } + /* AHCI controllers often implement SFF compatible interface. + * Grab all PCI BARs just in case. + */ + rc = pcim_iomap_regions_request_all(pdev, 1 << ahci_pci_bar, DRV_NAME); + if (rc == -EBUSY) + pcim_pin_device(pdev); + if (rc) + return rc; + hpriv = devm_kzalloc(dev, sizeof(*hpriv), GFP_KERNEL); if (!hpriv) return -ENOMEM; diff --git a/drivers/ata/ahci_imx.c b/drivers/ata/ahci_imx.c index ae2d73fe321e..3e23e9941dad 100644 --- a/drivers/ata/ahci_imx.c +++ b/drivers/ata/ahci_imx.c @@ -113,7 +113,7 @@ static int imx6q_sata_init(struct device *dev, void __iomem *mmio) /* * set PHY Paremeters, two steps to configure the GPR13, * one write for rest of parameters, mask of first write - * is 0x07fffffd, and the other one write for setting + * is 0x07ffffff, and the other one write for setting * the mpll_clk_en. */ regmap_update_bits(imxpriv->gpr, 0x34, IMX6Q_GPR13_SATA_RX_EQ_VAL_MASK @@ -124,6 +124,7 @@ static int imx6q_sata_init(struct device *dev, void __iomem *mmio) | IMX6Q_GPR13_SATA_TX_ATTEN_MASK | IMX6Q_GPR13_SATA_TX_BOOST_MASK | IMX6Q_GPR13_SATA_TX_LVL_MASK + | IMX6Q_GPR13_SATA_MPLL_CLK_EN | IMX6Q_GPR13_SATA_TX_EDGE_RATE , IMX6Q_GPR13_SATA_RX_EQ_VAL_3_0_DB | IMX6Q_GPR13_SATA_RX_LOS_LVL_SATA2M diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c index 75b93678bbcd..1393a5890ed5 100644 --- a/drivers/ata/libata-core.c +++ b/drivers/ata/libata-core.c @@ -2149,9 +2149,16 @@ static int ata_dev_config_ncq(struct ata_device *dev, "failed to get NCQ Send/Recv Log Emask 0x%x\n", err_mask); } else { + u8 *cmds = dev->ncq_send_recv_cmds; + dev->flags |= ATA_DFLAG_NCQ_SEND_RECV; - memcpy(dev->ncq_send_recv_cmds, ap->sector_buf, - ATA_LOG_NCQ_SEND_RECV_SIZE); + memcpy(cmds, ap->sector_buf, ATA_LOG_NCQ_SEND_RECV_SIZE); + + if (dev->horkage & ATA_HORKAGE_NO_NCQ_TRIM) { + ata_dev_dbg(dev, "disabling queued TRIM support\n"); + cmds[ATA_LOG_NCQ_SEND_RECV_DSM_OFFSET] &= + ~ATA_LOG_NCQ_SEND_RECV_DSM_TRIM; + } } } @@ -4156,6 +4163,9 @@ static const struct ata_blacklist_entry ata_device_blacklist [] = { { "ST3320[68]13AS", "SD1[5-9]", ATA_HORKAGE_NONCQ | ATA_HORKAGE_FIRMWARE_WARN }, + /* Seagate Momentus SpinPoint M8 seem to have FPMDA_AA issues */ + { "ST1000LM024 HN-M101MBB", "2AR10001", ATA_HORKAGE_BROKEN_FPDMA_AA }, + /* Blacklist entries taken from Silicon Image 3124/3132 Windows driver .inf file - also several Linux problem reports */ { "HTS541060G9SA00", "MB3OC60D", ATA_HORKAGE_NONCQ, }, @@ -4202,6 +4212,10 @@ static const struct ata_blacklist_entry ata_device_blacklist [] = { { "PIONEER DVD-RW DVR-212D", NULL, ATA_HORKAGE_NOSETXFER }, { "PIONEER DVD-RW DVR-216D", NULL, ATA_HORKAGE_NOSETXFER }, + /* devices that don't properly handle queued TRIM commands */ + { "Micron_M500*", NULL, ATA_HORKAGE_NO_NCQ_TRIM, }, + { "Crucial_CT???M500SSD1", NULL, ATA_HORKAGE_NO_NCQ_TRIM, }, + /* End Marker */ { } }; @@ -6519,6 +6533,7 @@ static int __init ata_parse_force_one(char **cur, { "norst", .lflags = ATA_LFLAG_NO_HRST | ATA_LFLAG_NO_SRST }, { "rstonce", .lflags = ATA_LFLAG_RST_ONCE }, { "atapi_dmadir", .horkage_on = ATA_HORKAGE_ATAPI_DMADIR }, + { "disable", .horkage_on = ATA_HORKAGE_DISABLE }, }; char *start = *cur, *p = *cur; char *id, *val, *endp; diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c index ab58556d347c..377eb889f555 100644 --- a/drivers/ata/libata-scsi.c +++ b/drivers/ata/libata-scsi.c @@ -3872,6 +3872,27 @@ void ata_scsi_hotplug(struct work_struct *work) return; } + /* + * XXX - UGLY HACK + * + * The block layer suspend/resume path is fundamentally broken due + * to freezable kthreads and workqueue and may deadlock if a block + * device gets removed while resume is in progress. I don't know + * what the solution is short of removing freezable kthreads and + * workqueues altogether. + * + * The following is an ugly hack to avoid kicking off device + * removal while freezer is active. This is a joke but does avoid + * this particular deadlock scenario. + * + * https://bugzilla.kernel.org/show_bug.cgi?id=62801 + * http://marc.info/?l=linux-kernel&m=138695698516487 + */ +#ifdef CONFIG_FREEZER + while (pm_freezing) + msleep(10); +#endif + DPRINTK("ENTER\n"); mutex_lock(&ap->scsi_scan_mutex); diff --git a/drivers/block/null_blk.c b/drivers/block/null_blk.c index f370fc13aea5..a2e69d26266d 100644 --- a/drivers/block/null_blk.c +++ b/drivers/block/null_blk.c @@ -1,4 +1,5 @@ #include <linux/module.h> + #include <linux/moduleparam.h> #include <linux/sched.h> #include <linux/fs.h> @@ -65,7 +66,7 @@ enum { NULL_Q_MQ = 2, }; -static int submit_queues = 1; +static int submit_queues; module_param(submit_queues, int, S_IRUGO); MODULE_PARM_DESC(submit_queues, "Number of submission queues"); @@ -101,9 +102,9 @@ static int hw_queue_depth = 64; module_param(hw_queue_depth, int, S_IRUGO); MODULE_PARM_DESC(hw_queue_depth, "Queue depth for each hardware queue. Default: 64"); -static bool use_per_node_hctx = true; +static bool use_per_node_hctx = false; module_param(use_per_node_hctx, bool, S_IRUGO); -MODULE_PARM_DESC(use_per_node_hctx, "Use per-node allocation for hardware context queues. Default: true"); +MODULE_PARM_DESC(use_per_node_hctx, "Use per-node allocation for hardware context queues. Default: false"); static void put_tag(struct nullb_queue *nq, unsigned int tag) { @@ -346,8 +347,37 @@ static int null_queue_rq(struct blk_mq_hw_ctx *hctx, struct request *rq) static struct blk_mq_hw_ctx *null_alloc_hctx(struct blk_mq_reg *reg, unsigned int hctx_index) { - return kzalloc_node(sizeof(struct blk_mq_hw_ctx), GFP_KERNEL, - hctx_index); + int b_size = DIV_ROUND_UP(reg->nr_hw_queues, nr_online_nodes); + int tip = (reg->nr_hw_queues % nr_online_nodes); + int node = 0, i, n; + + /* + * Split submit queues evenly wrt to the number of nodes. If uneven, + * fill the first buckets with one extra, until the rest is filled with + * no extra. + */ + for (i = 0, n = 1; i < hctx_index; i++, n++) { + if (n % b_size == 0) { + n = 0; + node++; + + tip--; + if (!tip) + b_size = reg->nr_hw_queues / nr_online_nodes; + } + } + + /* + * A node might not be online, therefore map the relative node id to the + * real node id. + */ + for_each_online_node(n) { + if (!node) + break; + node--; + } + + return kzalloc_node(sizeof(struct blk_mq_hw_ctx), GFP_KERNEL, n); } static void null_free_hctx(struct blk_mq_hw_ctx *hctx, unsigned int hctx_index) @@ -355,16 +385,24 @@ static void null_free_hctx(struct blk_mq_hw_ctx *hctx, unsigned int hctx_index) kfree(hctx); } +static void null_init_queue(struct nullb *nullb, struct nullb_queue *nq) +{ + BUG_ON(!nullb); + BUG_ON(!nq); + + init_waitqueue_head(&nq->wait); + nq->queue_depth = nullb->queue_depth; +} + static int null_init_hctx(struct blk_mq_hw_ctx *hctx, void *data, unsigned int index) { struct nullb *nullb = data; struct nullb_queue *nq = &nullb->queues[index]; - init_waitqueue_head(&nq->wait); - nq->queue_depth = nullb->queue_depth; - nullb->nr_queues++; hctx->driver_data = nq; + null_init_queue(nullb, nq); + nullb->nr_queues++; return 0; } @@ -417,13 +455,13 @@ static int setup_commands(struct nullb_queue *nq) nq->cmds = kzalloc(nq->queue_depth * sizeof(*cmd), GFP_KERNEL); if (!nq->cmds) - return 1; + return -ENOMEM; tag_size = ALIGN(nq->queue_depth, BITS_PER_LONG) / BITS_PER_LONG; nq->tag_map = kzalloc(tag_size * sizeof(unsigned long), GFP_KERNEL); if (!nq->tag_map) { kfree(nq->cmds); - return 1; + return -ENOMEM; } for (i = 0; i < nq->queue_depth; i++) { @@ -454,33 +492,37 @@ static void cleanup_queues(struct nullb *nullb) static int setup_queues(struct nullb *nullb) { - struct nullb_queue *nq; - int i; - - nullb->queues = kzalloc(submit_queues * sizeof(*nq), GFP_KERNEL); + nullb->queues = kzalloc(submit_queues * sizeof(struct nullb_queue), + GFP_KERNEL); if (!nullb->queues) - return 1; + return -ENOMEM; nullb->nr_queues = 0; nullb->queue_depth = hw_queue_depth; - if (queue_mode == NULL_Q_MQ) - return 0; + return 0; +} + +static int init_driver_queues(struct nullb *nullb) +{ + struct nullb_queue *nq; + int i, ret = 0; for (i = 0; i < submit_queues; i++) { nq = &nullb->queues[i]; - init_waitqueue_head(&nq->wait); - nq->queue_depth = hw_queue_depth; - if (setup_commands(nq)) - break; + + null_init_queue(nullb, nq); + + ret = setup_commands(nq); + if (ret) + goto err_queue; nullb->nr_queues++; } - if (i == submit_queues) - return 0; - + return 0; +err_queue: cleanup_queues(nullb); - return 1; + return ret; } static int null_add_dev(void) @@ -518,11 +560,13 @@ static int null_add_dev(void) } else if (queue_mode == NULL_Q_BIO) { nullb->q = blk_alloc_queue_node(GFP_KERNEL, home_node); blk_queue_make_request(nullb->q, null_queue_bio); + init_driver_queues(nullb); } else { nullb->q = blk_init_queue_node(null_request_fn, &nullb->lock, home_node); blk_queue_prep_rq(nullb->q, null_rq_prep_fn); if (nullb->q) blk_queue_softirq_done(nullb->q, null_softirq_done_fn); + init_driver_queues(nullb); } if (!nullb->q) @@ -579,7 +623,13 @@ static int __init null_init(void) } #endif - if (submit_queues > nr_cpu_ids) + if (queue_mode == NULL_Q_MQ && use_per_node_hctx) { + if (submit_queues < nr_online_nodes) { + pr_warn("null_blk: submit_queues param is set to %u.", + nr_online_nodes); + submit_queues = nr_online_nodes; + } + } else if (submit_queues > nr_cpu_ids) submit_queues = nr_cpu_ids; else if (!submit_queues) submit_queues = 1; diff --git a/drivers/block/skd_main.c b/drivers/block/skd_main.c index 9199c93be926..eb6e1e0e8db2 100644 --- a/drivers/block/skd_main.c +++ b/drivers/block/skd_main.c @@ -5269,7 +5269,7 @@ const char *skd_skdev_state_to_str(enum skd_drvr_state state) } } -const char *skd_skmsg_state_to_str(enum skd_fit_msg_state state) +static const char *skd_skmsg_state_to_str(enum skd_fit_msg_state state) { switch (state) { case SKD_MSG_STATE_IDLE: @@ -5281,7 +5281,7 @@ const char *skd_skmsg_state_to_str(enum skd_fit_msg_state state) } } -const char *skd_skreq_state_to_str(enum skd_req_state state) +static const char *skd_skreq_state_to_str(enum skd_req_state state) { switch (state) { case SKD_REQ_STATE_IDLE: diff --git a/drivers/cpufreq/cpufreq.c b/drivers/cpufreq/cpufreq.c index 02d534da22dd..16d7b4ac94be 100644 --- a/drivers/cpufreq/cpufreq.c +++ b/drivers/cpufreq/cpufreq.c @@ -828,6 +828,12 @@ static void cpufreq_init_policy(struct cpufreq_policy *policy) int ret = 0; memcpy(&new_policy, policy, sizeof(*policy)); + + /* Use the default policy if its valid. */ + if (cpufreq_driver->setpolicy) + cpufreq_parse_governor(policy->governor->name, + &new_policy.policy, NULL); + /* assure that the starting sequence is run in cpufreq_set_policy */ policy->governor = NULL; @@ -845,8 +851,7 @@ static void cpufreq_init_policy(struct cpufreq_policy *policy) #ifdef CONFIG_HOTPLUG_CPU static int cpufreq_add_policy_cpu(struct cpufreq_policy *policy, - unsigned int cpu, struct device *dev, - bool frozen) + unsigned int cpu, struct device *dev) { int ret = 0; unsigned long flags; @@ -877,11 +882,7 @@ static int cpufreq_add_policy_cpu(struct cpufreq_policy *policy, } } - /* Don't touch sysfs links during light-weight init */ - if (!frozen) - ret = sysfs_create_link(&dev->kobj, &policy->kobj, "cpufreq"); - - return ret; + return sysfs_create_link(&dev->kobj, &policy->kobj, "cpufreq"); } #endif @@ -926,6 +927,27 @@ err_free_policy: return NULL; } +static void cpufreq_policy_put_kobj(struct cpufreq_policy *policy) +{ + struct kobject *kobj; + struct completion *cmp; + + down_read(&policy->rwsem); + kobj = &policy->kobj; + cmp = &policy->kobj_unregister; + up_read(&policy->rwsem); + kobject_put(kobj); + + /* + * We need to make sure that the underlying kobj is + * actually not referenced anymore by anybody before we + * proceed with unloading. + */ + pr_debug("waiting for dropping of refcount\n"); + wait_for_completion(cmp); + pr_debug("wait complete\n"); +} + static void cpufreq_policy_free(struct cpufreq_policy *policy) { free_cpumask_var(policy->related_cpus); @@ -986,7 +1008,7 @@ static int __cpufreq_add_dev(struct device *dev, struct subsys_interface *sif, list_for_each_entry(tpolicy, &cpufreq_policy_list, policy_list) { if (cpumask_test_cpu(cpu, tpolicy->related_cpus)) { read_unlock_irqrestore(&cpufreq_driver_lock, flags); - ret = cpufreq_add_policy_cpu(tpolicy, cpu, dev, frozen); + ret = cpufreq_add_policy_cpu(tpolicy, cpu, dev); up_read(&cpufreq_rwsem); return ret; } @@ -1096,7 +1118,10 @@ err_get_freq: if (cpufreq_driver->exit) cpufreq_driver->exit(policy); err_set_policy_cpu: + if (frozen) + cpufreq_policy_put_kobj(policy); cpufreq_policy_free(policy); + nomem_out: up_read(&cpufreq_rwsem); @@ -1118,7 +1143,7 @@ static int cpufreq_add_dev(struct device *dev, struct subsys_interface *sif) } static int cpufreq_nominate_new_policy_cpu(struct cpufreq_policy *policy, - unsigned int old_cpu, bool frozen) + unsigned int old_cpu) { struct device *cpu_dev; int ret; @@ -1126,10 +1151,6 @@ static int cpufreq_nominate_new_policy_cpu(struct cpufreq_policy *policy, /* first sibling now owns the new sysfs dir */ cpu_dev = get_cpu_device(cpumask_any_but(policy->cpus, old_cpu)); - /* Don't touch sysfs files during light-weight tear-down */ - if (frozen) - return cpu_dev->id; - sysfs_remove_link(&cpu_dev->kobj, "cpufreq"); ret = kobject_move(&policy->kobj, &cpu_dev->kobj); if (ret) { @@ -1196,7 +1217,7 @@ static int __cpufreq_remove_dev_prepare(struct device *dev, if (!frozen) sysfs_remove_link(&dev->kobj, "cpufreq"); } else if (cpus > 1) { - new_cpu = cpufreq_nominate_new_policy_cpu(policy, cpu, frozen); + new_cpu = cpufreq_nominate_new_policy_cpu(policy, cpu); if (new_cpu >= 0) { update_policy_cpu(policy, new_cpu); @@ -1218,8 +1239,6 @@ static int __cpufreq_remove_dev_finish(struct device *dev, int ret; unsigned long flags; struct cpufreq_policy *policy; - struct kobject *kobj; - struct completion *cmp; read_lock_irqsave(&cpufreq_driver_lock, flags); policy = per_cpu(cpufreq_cpu_data, cpu); @@ -1249,22 +1268,8 @@ static int __cpufreq_remove_dev_finish(struct device *dev, } } - if (!frozen) { - down_read(&policy->rwsem); - kobj = &policy->kobj; - cmp = &policy->kobj_unregister; - up_read(&policy->rwsem); - kobject_put(kobj); - - /* - * We need to make sure that the underlying kobj is - * actually not referenced anymore by anybody before we - * proceed with unloading. - */ - pr_debug("waiting for dropping of refcount\n"); - wait_for_completion(cmp); - pr_debug("wait complete\n"); - } + if (!frozen) + cpufreq_policy_put_kobj(policy); /* * Perform the ->exit() even during light-weight tear-down, diff --git a/drivers/firmware/Makefile b/drivers/firmware/Makefile index 299fad6b5867..5373dc5b6011 100644 --- a/drivers/firmware/Makefile +++ b/drivers/firmware/Makefile @@ -14,3 +14,4 @@ obj-$(CONFIG_FIRMWARE_MEMMAP) += memmap.o obj-$(CONFIG_GOOGLE_FIRMWARE) += google/ obj-$(CONFIG_EFI) += efi/ +obj-$(CONFIG_UEFI_CPER) += efi/ diff --git a/drivers/firmware/efi/Kconfig b/drivers/firmware/efi/Kconfig index 3150aa4874e8..6aecbc86ec94 100644 --- a/drivers/firmware/efi/Kconfig +++ b/drivers/firmware/efi/Kconfig @@ -36,7 +36,7 @@ config EFI_VARS_PSTORE_DEFAULT_DISABLE backend for pstore by default. This setting can be overridden using the efivars module's pstore_disable parameter. -config UEFI_CPER - def_bool n - endmenu + +config UEFI_CPER + bool diff --git a/drivers/firmware/efi/Makefile b/drivers/firmware/efi/Makefile index 9ba156d3c775..6c2a41ec21ba 100644 --- a/drivers/firmware/efi/Makefile +++ b/drivers/firmware/efi/Makefile @@ -1,7 +1,7 @@ # # Makefile for linux kernel # -obj-y += efi.o vars.o +obj-$(CONFIG_EFI) += efi.o vars.o obj-$(CONFIG_EFI_VARS) += efivars.o obj-$(CONFIG_EFI_VARS_PSTORE) += efi-pstore.o obj-$(CONFIG_UEFI_CPER) += cper.o diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index 621c7c67a643..76d3d1ab73c6 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -2343,15 +2343,24 @@ static void i915_gem_free_request(struct drm_i915_gem_request *request) kfree(request); } -static void i915_gem_reset_ring_lists(struct drm_i915_private *dev_priv, - struct intel_ring_buffer *ring) +static void i915_gem_reset_ring_status(struct drm_i915_private *dev_priv, + struct intel_ring_buffer *ring) { - u32 completed_seqno; - u32 acthd; + u32 completed_seqno = ring->get_seqno(ring, false); + u32 acthd = intel_ring_get_active_head(ring); + struct drm_i915_gem_request *request; + + list_for_each_entry(request, &ring->request_list, list) { + if (i915_seqno_passed(completed_seqno, request->seqno)) + continue; - acthd = intel_ring_get_active_head(ring); - completed_seqno = ring->get_seqno(ring, false); + i915_set_reset_status(ring, request, acthd); + } +} +static void i915_gem_reset_ring_cleanup(struct drm_i915_private *dev_priv, + struct intel_ring_buffer *ring) +{ while (!list_empty(&ring->request_list)) { struct drm_i915_gem_request *request; @@ -2359,9 +2368,6 @@ static void i915_gem_reset_ring_lists(struct drm_i915_private *dev_priv, struct drm_i915_gem_request, list); - if (request->seqno > completed_seqno) - i915_set_reset_status(ring, request, acthd); - i915_gem_free_request(request); } @@ -2403,8 +2409,16 @@ void i915_gem_reset(struct drm_device *dev) struct intel_ring_buffer *ring; int i; + /* + * Before we free the objects from the requests, we need to inspect + * them for finding the guilty party. As the requests only borrow + * their reference to the objects, the inspection must be done first. + */ + for_each_ring(ring, dev_priv, i) + i915_gem_reset_ring_status(dev_priv, ring); + for_each_ring(ring, dev_priv, i) - i915_gem_reset_ring_lists(dev_priv, ring); + i915_gem_reset_ring_cleanup(dev_priv, ring); i915_gem_cleanup_ringbuffer(dev); diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c index b7e787fb4649..a3ba9a8cd687 100644 --- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c +++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c @@ -93,7 +93,7 @@ eb_lookup_vmas(struct eb_vmas *eb, { struct drm_i915_gem_object *obj; struct list_head objects; - int i, ret = 0; + int i, ret; INIT_LIST_HEAD(&objects); spin_lock(&file->table_lock); @@ -106,7 +106,7 @@ eb_lookup_vmas(struct eb_vmas *eb, DRM_DEBUG("Invalid object handle %d at index %d\n", exec[i].handle, i); ret = -ENOENT; - goto out; + goto err; } if (!list_empty(&obj->obj_exec_link)) { @@ -114,7 +114,7 @@ eb_lookup_vmas(struct eb_vmas *eb, DRM_DEBUG("Object %p [handle %d, index %d] appears more than once in object list\n", obj, exec[i].handle, i); ret = -EINVAL; - goto out; + goto err; } drm_gem_object_reference(&obj->base); @@ -123,9 +123,13 @@ eb_lookup_vmas(struct eb_vmas *eb, spin_unlock(&file->table_lock); i = 0; - list_for_each_entry(obj, &objects, obj_exec_link) { + while (!list_empty(&objects)) { struct i915_vma *vma; + obj = list_first_entry(&objects, + struct drm_i915_gem_object, + obj_exec_link); + /* * NOTE: We can leak any vmas created here when something fails * later on. But that's no issue since vma_unbind can deal with @@ -138,10 +142,12 @@ eb_lookup_vmas(struct eb_vmas *eb, if (IS_ERR(vma)) { DRM_DEBUG("Failed to lookup VMA\n"); ret = PTR_ERR(vma); - goto out; + goto err; } + /* Transfer ownership from the objects list to the vmas list. */ list_add_tail(&vma->exec_list, &eb->vmas); + list_del_init(&obj->obj_exec_link); vma->exec_entry = &exec[i]; if (eb->and < 0) { @@ -155,16 +161,22 @@ eb_lookup_vmas(struct eb_vmas *eb, ++i; } + return 0; + -out: +err: while (!list_empty(&objects)) { obj = list_first_entry(&objects, struct drm_i915_gem_object, obj_exec_link); list_del_init(&obj->obj_exec_link); - if (ret) - drm_gem_object_unreference(&obj->base); + drm_gem_object_unreference(&obj->base); } + /* + * Objects already transfered to the vmas list will be unreferenced by + * eb_destroy. + */ + return ret; } diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c index 8b8bde7dce53..54e82a80cf50 100644 --- a/drivers/gpu/drm/i915/intel_display.c +++ b/drivers/gpu/drm/i915/intel_display.c @@ -6303,7 +6303,7 @@ static void assert_can_disable_lcpll(struct drm_i915_private *dev_priv) uint32_t val; list_for_each_entry(crtc, &dev->mode_config.crtc_list, base.head) - WARN(crtc->base.enabled, "CRTC for pipe %c enabled\n", + WARN(crtc->active, "CRTC for pipe %c enabled\n", pipe_name(crtc->pipe)); WARN(I915_READ(HSW_PWR_WELL_DRIVER), "Power well on\n"); @@ -11126,14 +11126,15 @@ void intel_connector_attach_encoder(struct intel_connector *connector, int intel_modeset_vga_set_state(struct drm_device *dev, bool state) { struct drm_i915_private *dev_priv = dev->dev_private; + unsigned reg = INTEL_INFO(dev)->gen >= 6 ? SNB_GMCH_CTRL : INTEL_GMCH_CTRL; u16 gmch_ctrl; - pci_read_config_word(dev_priv->bridge_dev, INTEL_GMCH_CTRL, &gmch_ctrl); + pci_read_config_word(dev_priv->bridge_dev, reg, &gmch_ctrl); if (state) gmch_ctrl &= ~INTEL_GMCH_VGA_DISABLE; else gmch_ctrl |= INTEL_GMCH_VGA_DISABLE; - pci_write_config_word(dev_priv->bridge_dev, INTEL_GMCH_CTRL, gmch_ctrl); + pci_write_config_word(dev_priv->bridge_dev, reg, gmch_ctrl); return 0; } diff --git a/drivers/gpu/drm/i915/intel_pm.c b/drivers/gpu/drm/i915/intel_pm.c index 3657ab43c8fd..26c29c173221 100644 --- a/drivers/gpu/drm/i915/intel_pm.c +++ b/drivers/gpu/drm/i915/intel_pm.c @@ -5688,6 +5688,8 @@ static void __intel_set_power_well(struct drm_device *dev, bool enable) unsigned long irqflags; uint32_t tmp; + WARN_ON(dev_priv->pc8.enabled); + tmp = I915_READ(HSW_PWR_WELL_DRIVER); is_enabled = tmp & HSW_PWR_WELL_STATE_ENABLED; enable_requested = tmp & HSW_PWR_WELL_ENABLE_REQUEST; @@ -5747,16 +5749,24 @@ static void __intel_set_power_well(struct drm_device *dev, bool enable) static void __intel_power_well_get(struct drm_device *dev, struct i915_power_well *power_well) { - if (!power_well->count++) + struct drm_i915_private *dev_priv = dev->dev_private; + + if (!power_well->count++) { + hsw_disable_package_c8(dev_priv); __intel_set_power_well(dev, true); + } } static void __intel_power_well_put(struct drm_device *dev, struct i915_power_well *power_well) { + struct drm_i915_private *dev_priv = dev->dev_private; + WARN_ON(!power_well->count); - if (!--power_well->count && i915_disable_power_well) + if (!--power_well->count && i915_disable_power_well) { __intel_set_power_well(dev, false); + hsw_enable_package_c8(dev_priv); + } } void intel_display_power_get(struct drm_device *dev, diff --git a/drivers/gpu/drm/qxl/Kconfig b/drivers/gpu/drm/qxl/Kconfig index 037d324bf58f..66ac0ff95f5a 100644 --- a/drivers/gpu/drm/qxl/Kconfig +++ b/drivers/gpu/drm/qxl/Kconfig @@ -8,5 +8,6 @@ config DRM_QXL select DRM_KMS_HELPER select DRM_KMS_FB_HELPER select DRM_TTM + select CRC32 help QXL virtual GPU for Spice virtualization desktop integration. Do not enable this driver unless your distro ships a corresponding X.org QXL driver that can handle kernel modesetting. diff --git a/drivers/gpu/drm/qxl/qxl_display.c b/drivers/gpu/drm/qxl/qxl_display.c index 5e827c29d194..d70aafb83307 100644 --- a/drivers/gpu/drm/qxl/qxl_display.c +++ b/drivers/gpu/drm/qxl/qxl_display.c @@ -24,7 +24,7 @@ */ -#include "linux/crc32.h" +#include <linux/crc32.h> #include "qxl_drv.h" #include "qxl_object.h" diff --git a/drivers/gpu/drm/radeon/dce6_afmt.c b/drivers/gpu/drm/radeon/dce6_afmt.c index de86493cbc44..713a5d359901 100644 --- a/drivers/gpu/drm/radeon/dce6_afmt.c +++ b/drivers/gpu/drm/radeon/dce6_afmt.c @@ -174,7 +174,7 @@ void dce6_afmt_write_speaker_allocation(struct drm_encoder *encoder) } sad_count = drm_edid_to_speaker_allocation(radeon_connector->edid, &sadb); - if (sad_count < 0) { + if (sad_count <= 0) { DRM_ERROR("Couldn't read Speaker Allocation Data Block: %d\n", sad_count); return; } @@ -235,7 +235,7 @@ void dce6_afmt_write_sad_regs(struct drm_encoder *encoder) } sad_count = drm_edid_to_sad(radeon_connector->edid, &sads); - if (sad_count < 0) { + if (sad_count <= 0) { DRM_ERROR("Couldn't read SADs: %d\n", sad_count); return; } @@ -308,7 +308,9 @@ int dce6_audio_init(struct radeon_device *rdev) rdev->audio.enabled = true; if (ASIC_IS_DCE8(rdev)) - rdev->audio.num_pins = 7; + rdev->audio.num_pins = 6; + else if (ASIC_IS_DCE61(rdev)) + rdev->audio.num_pins = 4; else rdev->audio.num_pins = 6; diff --git a/drivers/gpu/drm/radeon/evergreen_hdmi.c b/drivers/gpu/drm/radeon/evergreen_hdmi.c index aa695c4feb3d..0c6d5cef4cf1 100644 --- a/drivers/gpu/drm/radeon/evergreen_hdmi.c +++ b/drivers/gpu/drm/radeon/evergreen_hdmi.c @@ -118,7 +118,7 @@ static void dce4_afmt_write_speaker_allocation(struct drm_encoder *encoder) } sad_count = drm_edid_to_speaker_allocation(radeon_connector->edid, &sadb); - if (sad_count < 0) { + if (sad_count <= 0) { DRM_ERROR("Couldn't read Speaker Allocation Data Block: %d\n", sad_count); return; } @@ -173,7 +173,7 @@ static void evergreen_hdmi_write_sad_regs(struct drm_encoder *encoder) } sad_count = drm_edid_to_sad(radeon_connector->edid, &sads); - if (sad_count < 0) { + if (sad_count <= 0) { DRM_ERROR("Couldn't read SADs: %d\n", sad_count); return; } diff --git a/drivers/gpu/drm/radeon/ni.c b/drivers/gpu/drm/radeon/ni.c index 11aab2ab54ce..f59a9e9fccf8 100644 --- a/drivers/gpu/drm/radeon/ni.c +++ b/drivers/gpu/drm/radeon/ni.c @@ -895,6 +895,10 @@ static void cayman_gpu_init(struct radeon_device *rdev) (rdev->pdev->device == 0x999C)) { rdev->config.cayman.max_simds_per_se = 6; rdev->config.cayman.max_backends_per_se = 2; + rdev->config.cayman.max_hw_contexts = 8; + rdev->config.cayman.sx_max_export_size = 256; + rdev->config.cayman.sx_max_export_pos_size = 64; + rdev->config.cayman.sx_max_export_smx_size = 192; } else if ((rdev->pdev->device == 0x9903) || (rdev->pdev->device == 0x9904) || (rdev->pdev->device == 0x990A) || @@ -905,6 +909,10 @@ static void cayman_gpu_init(struct radeon_device *rdev) (rdev->pdev->device == 0x999D)) { rdev->config.cayman.max_simds_per_se = 4; rdev->config.cayman.max_backends_per_se = 2; + rdev->config.cayman.max_hw_contexts = 8; + rdev->config.cayman.sx_max_export_size = 256; + rdev->config.cayman.sx_max_export_pos_size = 64; + rdev->config.cayman.sx_max_export_smx_size = 192; } else if ((rdev->pdev->device == 0x9919) || (rdev->pdev->device == 0x9990) || (rdev->pdev->device == 0x9991) || @@ -915,9 +923,17 @@ static void cayman_gpu_init(struct radeon_device *rdev) (rdev->pdev->device == 0x99A0)) { rdev->config.cayman.max_simds_per_se = 3; rdev->config.cayman.max_backends_per_se = 1; + rdev->config.cayman.max_hw_contexts = 4; + rdev->config.cayman.sx_max_export_size = 128; + rdev->config.cayman.sx_max_export_pos_size = 32; + rdev->config.cayman.sx_max_export_smx_size = 96; } else { rdev->config.cayman.max_simds_per_se = 2; rdev->config.cayman.max_backends_per_se = 1; + rdev->config.cayman.max_hw_contexts = 4; + rdev->config.cayman.sx_max_export_size = 128; + rdev->config.cayman.sx_max_export_pos_size = 32; + rdev->config.cayman.sx_max_export_smx_size = 96; } rdev->config.cayman.max_texture_channel_caches = 2; rdev->config.cayman.max_gprs = 256; @@ -925,10 +941,6 @@ static void cayman_gpu_init(struct radeon_device *rdev) rdev->config.cayman.max_gs_threads = 32; rdev->config.cayman.max_stack_entries = 512; rdev->config.cayman.sx_num_of_sets = 8; - rdev->config.cayman.sx_max_export_size = 256; - rdev->config.cayman.sx_max_export_pos_size = 64; - rdev->config.cayman.sx_max_export_smx_size = 192; - rdev->config.cayman.max_hw_contexts = 8; rdev->config.cayman.sq_num_cf_insts = 2; rdev->config.cayman.sc_prim_fifo_size = 0x40; diff --git a/drivers/gpu/drm/radeon/rv770_dpm.c b/drivers/gpu/drm/radeon/rv770_dpm.c index 913b025ae9b3..374499db20c7 100644 --- a/drivers/gpu/drm/radeon/rv770_dpm.c +++ b/drivers/gpu/drm/radeon/rv770_dpm.c @@ -2328,6 +2328,12 @@ void rv770_get_engine_memory_ss(struct radeon_device *rdev) pi->mclk_ss = radeon_atombios_get_asic_ss_info(rdev, &ss, ASIC_INTERNAL_MEMORY_SS, 0); + /* disable ss, causes hangs on some cayman boards */ + if (rdev->family == CHIP_CAYMAN) { + pi->sclk_ss = false; + pi->mclk_ss = false; + } + if (pi->sclk_ss || pi->mclk_ss) pi->dynamic_ss = true; else diff --git a/drivers/gpu/drm/ttm/ttm_bo_util.c b/drivers/gpu/drm/ttm/ttm_bo_util.c index 15b86a94949d..406152152315 100644 --- a/drivers/gpu/drm/ttm/ttm_bo_util.c +++ b/drivers/gpu/drm/ttm/ttm_bo_util.c @@ -353,7 +353,8 @@ int ttm_bo_move_memcpy(struct ttm_buffer_object *bo, * Don't move nonexistent data. Clear destination instead. */ if (old_iomap == NULL && - (ttm == NULL || ttm->state == tt_unpopulated)) { + (ttm == NULL || (ttm->state == tt_unpopulated && + !(ttm->page_flags & TTM_PAGE_FLAG_SWAPPED)))) { memset_io(new_iomap, 0, new_mem->num_pages*PAGE_SIZE); goto out2; } diff --git a/drivers/idle/intel_idle.c b/drivers/idle/intel_idle.c index 92d1206482a6..f80b700f821c 100644 --- a/drivers/idle/intel_idle.c +++ b/drivers/idle/intel_idle.c @@ -377,6 +377,9 @@ static int intel_idle(struct cpuidle_device *dev, if (!current_set_polling_and_test()) { + if (this_cpu_has(X86_FEATURE_CLFLUSH_MONITOR)) + clflush((void *)¤t_thread_info()->flags); + __monitor((void *)¤t_thread_info()->flags, 0, 0); smp_mb(); if (!need_resched()) diff --git a/drivers/infiniband/core/iwcm.c b/drivers/infiniband/core/iwcm.c index c47c2034ca71..0717940ec3b5 100644 --- a/drivers/infiniband/core/iwcm.c +++ b/drivers/infiniband/core/iwcm.c @@ -181,9 +181,16 @@ static void add_ref(struct iw_cm_id *cm_id) static void rem_ref(struct iw_cm_id *cm_id) { struct iwcm_id_private *cm_id_priv; + int cb_destroy; + cm_id_priv = container_of(cm_id, struct iwcm_id_private, id); - if (iwcm_deref_id(cm_id_priv) && - test_bit(IWCM_F_CALLBACK_DESTROY, &cm_id_priv->flags)) { + + /* + * Test bit before deref in case the cm_id gets freed on another + * thread. + */ + cb_destroy = test_bit(IWCM_F_CALLBACK_DESTROY, &cm_id_priv->flags); + if (iwcm_deref_id(cm_id_priv) && cb_destroy) { BUG_ON(!list_empty(&cm_id_priv->work_list)); free_cm_id(cm_id_priv); } diff --git a/drivers/infiniband/core/uverbs.h b/drivers/infiniband/core/uverbs.h index bdc842e9faef..a283274a5a09 100644 --- a/drivers/infiniband/core/uverbs.h +++ b/drivers/infiniband/core/uverbs.h @@ -49,12 +49,20 @@ #define INIT_UDATA(udata, ibuf, obuf, ilen, olen) \ do { \ - (udata)->inbuf = (void __user *) (ibuf); \ + (udata)->inbuf = (const void __user *) (ibuf); \ (udata)->outbuf = (void __user *) (obuf); \ (udata)->inlen = (ilen); \ (udata)->outlen = (olen); \ } while (0) +#define INIT_UDATA_BUF_OR_NULL(udata, ibuf, obuf, ilen, olen) \ + do { \ + (udata)->inbuf = (ilen) ? (const void __user *) (ibuf) : NULL; \ + (udata)->outbuf = (olen) ? (void __user *) (obuf) : NULL; \ + (udata)->inlen = (ilen); \ + (udata)->outlen = (olen); \ + } while (0) + /* * Our lifetime rules for these structs are the following: * diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c index 65f6e7dc380c..f1cc83855af6 100644 --- a/drivers/infiniband/core/uverbs_cmd.c +++ b/drivers/infiniband/core/uverbs_cmd.c @@ -2593,6 +2593,9 @@ out_put: static int kern_spec_to_ib_spec(struct ib_uverbs_flow_spec *kern_spec, union ib_flow_spec *ib_spec) { + if (kern_spec->reserved) + return -EINVAL; + ib_spec->type = kern_spec->type; switch (ib_spec->type) { @@ -2646,6 +2649,9 @@ int ib_uverbs_ex_create_flow(struct ib_uverbs_file *file, void *ib_spec; int i; + if (ucore->inlen < sizeof(cmd)) + return -EINVAL; + if (ucore->outlen < sizeof(resp)) return -ENOSPC; @@ -2671,6 +2677,10 @@ int ib_uverbs_ex_create_flow(struct ib_uverbs_file *file, (cmd.flow_attr.num_of_specs * sizeof(struct ib_uverbs_flow_spec))) return -EINVAL; + if (cmd.flow_attr.reserved[0] || + cmd.flow_attr.reserved[1]) + return -EINVAL; + if (cmd.flow_attr.num_of_specs) { kern_flow_attr = kmalloc(sizeof(*kern_flow_attr) + cmd.flow_attr.size, GFP_KERNEL); @@ -2731,6 +2741,7 @@ int ib_uverbs_ex_create_flow(struct ib_uverbs_file *file, if (cmd.flow_attr.size || (i != flow_attr->num_of_specs)) { pr_warn("create flow failed, flow %d: %d bytes left from uverb cmd\n", i, cmd.flow_attr.size); + err = -EINVAL; goto err_free; } flow_id = ib_create_flow(qp, flow_attr, IB_FLOW_DOMAIN_USER); @@ -2791,10 +2802,16 @@ int ib_uverbs_ex_destroy_flow(struct ib_uverbs_file *file, struct ib_uobject *uobj; int ret; + if (ucore->inlen < sizeof(cmd)) + return -EINVAL; + ret = ib_copy_from_udata(&cmd, ucore, sizeof(cmd)); if (ret) return ret; + if (cmd.comp_mask) + return -EINVAL; + uobj = idr_write_uobj(&ib_uverbs_rule_idr, cmd.flow_handle, file->ucontext); if (!uobj) diff --git a/drivers/infiniband/core/uverbs_main.c b/drivers/infiniband/core/uverbs_main.c index 34386943ebcf..08219fb3338b 100644 --- a/drivers/infiniband/core/uverbs_main.c +++ b/drivers/infiniband/core/uverbs_main.c @@ -668,25 +668,30 @@ static ssize_t ib_uverbs_write(struct file *filp, const char __user *buf, if ((hdr.in_words + ex_hdr.provider_in_words) * 8 != count) return -EINVAL; + if (ex_hdr.cmd_hdr_reserved) + return -EINVAL; + if (ex_hdr.response) { if (!hdr.out_words && !ex_hdr.provider_out_words) return -EINVAL; + + if (!access_ok(VERIFY_WRITE, + (void __user *) (unsigned long) ex_hdr.response, + (hdr.out_words + ex_hdr.provider_out_words) * 8)) + return -EFAULT; } else { if (hdr.out_words || ex_hdr.provider_out_words) return -EINVAL; } - INIT_UDATA(&ucore, - (hdr.in_words) ? buf : 0, - (unsigned long)ex_hdr.response, - hdr.in_words * 8, - hdr.out_words * 8); - - INIT_UDATA(&uhw, - (ex_hdr.provider_in_words) ? buf + ucore.inlen : 0, - (ex_hdr.provider_out_words) ? (unsigned long)ex_hdr.response + ucore.outlen : 0, - ex_hdr.provider_in_words * 8, - ex_hdr.provider_out_words * 8); + INIT_UDATA_BUF_OR_NULL(&ucore, buf, (unsigned long) ex_hdr.response, + hdr.in_words * 8, hdr.out_words * 8); + + INIT_UDATA_BUF_OR_NULL(&uhw, + buf + ucore.inlen, + (unsigned long) ex_hdr.response + ucore.outlen, + ex_hdr.provider_in_words * 8, + ex_hdr.provider_out_words * 8); err = uverbs_ex_cmd_table[command](file, &ucore, diff --git a/drivers/infiniband/hw/cxgb4/mem.c b/drivers/infiniband/hw/cxgb4/mem.c index 4cb8eb24497c..84e45006451c 100644 --- a/drivers/infiniband/hw/cxgb4/mem.c +++ b/drivers/infiniband/hw/cxgb4/mem.c @@ -173,7 +173,7 @@ static int _c4iw_write_mem_inline(struct c4iw_rdev *rdev, u32 addr, u32 len, return ret; } -int _c4iw_write_mem_dma(struct c4iw_rdev *rdev, u32 addr, u32 len, void *data) +static int _c4iw_write_mem_dma(struct c4iw_rdev *rdev, u32 addr, u32 len, void *data) { u32 remain = len; u32 dmalen; diff --git a/drivers/md/bcache/alloc.c b/drivers/md/bcache/alloc.c index 2b46bf1d7e40..4c9852d92b0a 100644 --- a/drivers/md/bcache/alloc.c +++ b/drivers/md/bcache/alloc.c @@ -421,9 +421,11 @@ out: if (watermark <= WATERMARK_METADATA) { SET_GC_MARK(b, GC_MARK_METADATA); + SET_GC_MOVE(b, 0); b->prio = BTREE_PRIO; } else { SET_GC_MARK(b, GC_MARK_RECLAIMABLE); + SET_GC_MOVE(b, 0); b->prio = INITIAL_PRIO; } diff --git a/drivers/md/bcache/bcache.h b/drivers/md/bcache/bcache.h index 4beb55a0ff30..754f43177483 100644 --- a/drivers/md/bcache/bcache.h +++ b/drivers/md/bcache/bcache.h @@ -197,7 +197,7 @@ struct bucket { uint8_t disk_gen; uint8_t last_gc; /* Most out of date gen in the btree */ uint8_t gc_gen; - uint16_t gc_mark; + uint16_t gc_mark; /* Bitfield used by GC. See below for field */ }; /* @@ -209,7 +209,8 @@ BITMASK(GC_MARK, struct bucket, gc_mark, 0, 2); #define GC_MARK_RECLAIMABLE 0 #define GC_MARK_DIRTY 1 #define GC_MARK_METADATA 2 -BITMASK(GC_SECTORS_USED, struct bucket, gc_mark, 2, 14); +BITMASK(GC_SECTORS_USED, struct bucket, gc_mark, 2, 13); +BITMASK(GC_MOVE, struct bucket, gc_mark, 15, 1); #include "journal.h" #include "stats.h" @@ -372,14 +373,14 @@ struct cached_dev { unsigned char writeback_percent; unsigned writeback_delay; - int writeback_rate_change; - int64_t writeback_rate_derivative; uint64_t writeback_rate_target; + int64_t writeback_rate_proportional; + int64_t writeback_rate_derivative; + int64_t writeback_rate_change; unsigned writeback_rate_update_seconds; unsigned writeback_rate_d_term; unsigned writeback_rate_p_term_inverse; - unsigned writeback_rate_d_smooth; }; enum alloc_watermarks { @@ -445,7 +446,6 @@ struct cache { * call prio_write() to keep gens from wrapping. */ uint8_t need_save_prio; - unsigned gc_move_threshold; /* * If nonzero, we know we aren't going to find any buckets to invalidate diff --git a/drivers/md/bcache/btree.c b/drivers/md/bcache/btree.c index 5e2765aadce1..31bb53fcc67a 100644 --- a/drivers/md/bcache/btree.c +++ b/drivers/md/bcache/btree.c @@ -1561,6 +1561,28 @@ size_t bch_btree_gc_finish(struct cache_set *c) SET_GC_MARK(PTR_BUCKET(c, &c->uuid_bucket, i), GC_MARK_METADATA); + /* don't reclaim buckets to which writeback keys point */ + rcu_read_lock(); + for (i = 0; i < c->nr_uuids; i++) { + struct bcache_device *d = c->devices[i]; + struct cached_dev *dc; + struct keybuf_key *w, *n; + unsigned j; + + if (!d || UUID_FLASH_ONLY(&c->uuids[i])) + continue; + dc = container_of(d, struct cached_dev, disk); + + spin_lock(&dc->writeback_keys.lock); + rbtree_postorder_for_each_entry_safe(w, n, + &dc->writeback_keys.keys, node) + for (j = 0; j < KEY_PTRS(&w->key); j++) + SET_GC_MARK(PTR_BUCKET(c, &w->key, j), + GC_MARK_DIRTY); + spin_unlock(&dc->writeback_keys.lock); + } + rcu_read_unlock(); + for_each_cache(ca, c, i) { uint64_t *i; @@ -1817,7 +1839,8 @@ static bool fix_overlapping_extents(struct btree *b, struct bkey *insert, if (KEY_START(k) > KEY_START(insert) + sectors_found) goto check_failed; - if (KEY_PTRS(replace_key) != KEY_PTRS(k)) + if (KEY_PTRS(k) != KEY_PTRS(replace_key) || + KEY_DIRTY(k) != KEY_DIRTY(replace_key)) goto check_failed; /* skip past gen */ @@ -2217,7 +2240,7 @@ struct btree_insert_op { struct bkey *replace_key; }; -int btree_insert_fn(struct btree_op *b_op, struct btree *b) +static int btree_insert_fn(struct btree_op *b_op, struct btree *b) { struct btree_insert_op *op = container_of(b_op, struct btree_insert_op, op); diff --git a/drivers/md/bcache/movinggc.c b/drivers/md/bcache/movinggc.c index 7c1275e66025..f2f0998c4a91 100644 --- a/drivers/md/bcache/movinggc.c +++ b/drivers/md/bcache/movinggc.c @@ -25,10 +25,9 @@ static bool moving_pred(struct keybuf *buf, struct bkey *k) unsigned i; for (i = 0; i < KEY_PTRS(k); i++) { - struct cache *ca = PTR_CACHE(c, k, i); struct bucket *g = PTR_BUCKET(c, k, i); - if (GC_SECTORS_USED(g) < ca->gc_move_threshold) + if (GC_MOVE(g)) return true; } @@ -65,11 +64,16 @@ static void write_moving_finish(struct closure *cl) static void read_moving_endio(struct bio *bio, int error) { + struct bbio *b = container_of(bio, struct bbio, bio); struct moving_io *io = container_of(bio->bi_private, struct moving_io, cl); if (error) io->op.error = error; + else if (!KEY_DIRTY(&b->key) && + ptr_stale(io->op.c, &b->key, 0)) { + io->op.error = -EINTR; + } bch_bbio_endio(io->op.c, bio, error, "reading data to move"); } @@ -141,6 +145,11 @@ static void read_moving(struct cache_set *c) if (!w) break; + if (ptr_stale(c, &w->key, 0)) { + bch_keybuf_del(&c->moving_gc_keys, w); + continue; + } + io = kzalloc(sizeof(struct moving_io) + sizeof(struct bio_vec) * DIV_ROUND_UP(KEY_SIZE(&w->key), PAGE_SECTORS), GFP_KERNEL); @@ -184,7 +193,8 @@ static bool bucket_cmp(struct bucket *l, struct bucket *r) static unsigned bucket_heap_top(struct cache *ca) { - return GC_SECTORS_USED(heap_peek(&ca->heap)); + struct bucket *b; + return (b = heap_peek(&ca->heap)) ? GC_SECTORS_USED(b) : 0; } void bch_moving_gc(struct cache_set *c) @@ -226,9 +236,8 @@ void bch_moving_gc(struct cache_set *c) sectors_to_move -= GC_SECTORS_USED(b); } - ca->gc_move_threshold = bucket_heap_top(ca); - - pr_debug("threshold %u", ca->gc_move_threshold); + while (heap_pop(&ca->heap, b, bucket_cmp)) + SET_GC_MOVE(b, 1); } mutex_unlock(&c->bucket_lock); diff --git a/drivers/md/bcache/super.c b/drivers/md/bcache/super.c index dec15cd2d797..c57bfa071a57 100644 --- a/drivers/md/bcache/super.c +++ b/drivers/md/bcache/super.c @@ -1676,7 +1676,7 @@ err: static bool can_attach_cache(struct cache *ca, struct cache_set *c) { return ca->sb.block_size == c->sb.block_size && - ca->sb.bucket_size == c->sb.block_size && + ca->sb.bucket_size == c->sb.bucket_size && ca->sb.nr_in_set == c->sb.nr_in_set; } diff --git a/drivers/md/bcache/sysfs.c b/drivers/md/bcache/sysfs.c index 80d4c2bee18a..a1f85612f0b3 100644 --- a/drivers/md/bcache/sysfs.c +++ b/drivers/md/bcache/sysfs.c @@ -83,7 +83,6 @@ rw_attribute(writeback_rate); rw_attribute(writeback_rate_update_seconds); rw_attribute(writeback_rate_d_term); rw_attribute(writeback_rate_p_term_inverse); -rw_attribute(writeback_rate_d_smooth); read_attribute(writeback_rate_debug); read_attribute(stripe_size); @@ -129,31 +128,41 @@ SHOW(__bch_cached_dev) var_printf(writeback_running, "%i"); var_print(writeback_delay); var_print(writeback_percent); - sysfs_print(writeback_rate, dc->writeback_rate.rate); + sysfs_hprint(writeback_rate, dc->writeback_rate.rate << 9); var_print(writeback_rate_update_seconds); var_print(writeback_rate_d_term); var_print(writeback_rate_p_term_inverse); - var_print(writeback_rate_d_smooth); if (attr == &sysfs_writeback_rate_debug) { + char rate[20]; char dirty[20]; - char derivative[20]; char target[20]; - bch_hprint(dirty, - bcache_dev_sectors_dirty(&dc->disk) << 9); - bch_hprint(derivative, dc->writeback_rate_derivative << 9); + char proportional[20]; + char derivative[20]; + char change[20]; + s64 next_io; + + bch_hprint(rate, dc->writeback_rate.rate << 9); + bch_hprint(dirty, bcache_dev_sectors_dirty(&dc->disk) << 9); bch_hprint(target, dc->writeback_rate_target << 9); + bch_hprint(proportional,dc->writeback_rate_proportional << 9); + bch_hprint(derivative, dc->writeback_rate_derivative << 9); + bch_hprint(change, dc->writeback_rate_change << 9); + + next_io = div64_s64(dc->writeback_rate.next - local_clock(), + NSEC_PER_MSEC); return sprintf(buf, - "rate:\t\t%u\n" - "change:\t\t%i\n" + "rate:\t\t%s/sec\n" "dirty:\t\t%s\n" + "target:\t\t%s\n" + "proportional:\t%s\n" "derivative:\t%s\n" - "target:\t\t%s\n", - dc->writeback_rate.rate, - dc->writeback_rate_change, - dirty, derivative, target); + "change:\t\t%s/sec\n" + "next io:\t%llims\n", + rate, dirty, target, proportional, + derivative, change, next_io); } sysfs_hprint(dirty_data, @@ -189,6 +198,7 @@ STORE(__cached_dev) struct kobj_uevent_env *env; #define d_strtoul(var) sysfs_strtoul(var, dc->var) +#define d_strtoul_nonzero(var) sysfs_strtoul_clamp(var, dc->var, 1, INT_MAX) #define d_strtoi_h(var) sysfs_hatoi(var, dc->var) sysfs_strtoul(data_csum, dc->disk.data_csum); @@ -197,16 +207,15 @@ STORE(__cached_dev) d_strtoul(writeback_metadata); d_strtoul(writeback_running); d_strtoul(writeback_delay); - sysfs_strtoul_clamp(writeback_rate, - dc->writeback_rate.rate, 1, 1000000); + sysfs_strtoul_clamp(writeback_percent, dc->writeback_percent, 0, 40); - d_strtoul(writeback_rate_update_seconds); + sysfs_strtoul_clamp(writeback_rate, + dc->writeback_rate.rate, 1, INT_MAX); + + d_strtoul_nonzero(writeback_rate_update_seconds); d_strtoul(writeback_rate_d_term); - d_strtoul(writeback_rate_p_term_inverse); - sysfs_strtoul_clamp(writeback_rate_p_term_inverse, - dc->writeback_rate_p_term_inverse, 1, INT_MAX); - d_strtoul(writeback_rate_d_smooth); + d_strtoul_nonzero(writeback_rate_p_term_inverse); d_strtoi_h(sequential_cutoff); d_strtoi_h(readahead); @@ -313,7 +322,6 @@ static struct attribute *bch_cached_dev_files[] = { &sysfs_writeback_rate_update_seconds, &sysfs_writeback_rate_d_term, &sysfs_writeback_rate_p_term_inverse, - &sysfs_writeback_rate_d_smooth, &sysfs_writeback_rate_debug, &sysfs_dirty_data, &sysfs_stripe_size, diff --git a/drivers/md/bcache/util.c b/drivers/md/bcache/util.c index 462214eeacbe..bb37618e7664 100644 --- a/drivers/md/bcache/util.c +++ b/drivers/md/bcache/util.c @@ -209,7 +209,13 @@ uint64_t bch_next_delay(struct bch_ratelimit *d, uint64_t done) { uint64_t now = local_clock(); - d->next += div_u64(done, d->rate); + d->next += div_u64(done * NSEC_PER_SEC, d->rate); + + if (time_before64(now + NSEC_PER_SEC, d->next)) + d->next = now + NSEC_PER_SEC; + + if (time_after64(now - NSEC_PER_SEC * 2, d->next)) + d->next = now - NSEC_PER_SEC * 2; return time_after64(d->next, now) ? div_u64(d->next - now, NSEC_PER_SEC / HZ) diff --git a/drivers/md/bcache/util.h b/drivers/md/bcache/util.h index 362c4b3f8b4a..1030c6020e98 100644 --- a/drivers/md/bcache/util.h +++ b/drivers/md/bcache/util.h @@ -110,7 +110,7 @@ do { \ _r; \ }) -#define heap_peek(h) ((h)->size ? (h)->data[0] : NULL) +#define heap_peek(h) ((h)->used ? (h)->data[0] : NULL) #define heap_full(h) ((h)->used == (h)->size) diff --git a/drivers/md/bcache/writeback.c b/drivers/md/bcache/writeback.c index 99053b1251be..6c44fe059c27 100644 --- a/drivers/md/bcache/writeback.c +++ b/drivers/md/bcache/writeback.c @@ -30,38 +30,40 @@ static void __update_writeback_rate(struct cached_dev *dc) /* PD controller */ - int change = 0; - int64_t error; int64_t dirty = bcache_dev_sectors_dirty(&dc->disk); int64_t derivative = dirty - dc->disk.sectors_dirty_last; + int64_t proportional = dirty - target; + int64_t change; dc->disk.sectors_dirty_last = dirty; - derivative *= dc->writeback_rate_d_term; - derivative = clamp(derivative, -dirty, dirty); + /* Scale to sectors per second */ - derivative = ewma_add(dc->disk.sectors_dirty_derivative, derivative, - dc->writeback_rate_d_smooth, 0); + proportional *= dc->writeback_rate_update_seconds; + proportional = div_s64(proportional, dc->writeback_rate_p_term_inverse); - /* Avoid divide by zero */ - if (!target) - goto out; + derivative = div_s64(derivative, dc->writeback_rate_update_seconds); - error = div64_s64((dirty + derivative - target) << 8, target); + derivative = ewma_add(dc->disk.sectors_dirty_derivative, derivative, + (dc->writeback_rate_d_term / + dc->writeback_rate_update_seconds) ?: 1, 0); + + derivative *= dc->writeback_rate_d_term; + derivative = div_s64(derivative, dc->writeback_rate_p_term_inverse); - change = div_s64((dc->writeback_rate.rate * error) >> 8, - dc->writeback_rate_p_term_inverse); + change = proportional + derivative; /* Don't increase writeback rate if the device isn't keeping up */ if (change > 0 && time_after64(local_clock(), - dc->writeback_rate.next + 10 * NSEC_PER_MSEC)) + dc->writeback_rate.next + NSEC_PER_MSEC)) change = 0; dc->writeback_rate.rate = - clamp_t(int64_t, dc->writeback_rate.rate + change, + clamp_t(int64_t, (int64_t) dc->writeback_rate.rate + change, 1, NSEC_PER_MSEC); -out: + + dc->writeback_rate_proportional = proportional; dc->writeback_rate_derivative = derivative; dc->writeback_rate_change = change; dc->writeback_rate_target = target; @@ -87,15 +89,11 @@ static void update_writeback_rate(struct work_struct *work) static unsigned writeback_delay(struct cached_dev *dc, unsigned sectors) { - uint64_t ret; - if (test_bit(BCACHE_DEV_DETACHING, &dc->disk.flags) || !dc->writeback_percent) return 0; - ret = bch_next_delay(&dc->writeback_rate, sectors * 10000000ULL); - - return min_t(uint64_t, ret, HZ); + return bch_next_delay(&dc->writeback_rate, sectors); } struct dirty_io { @@ -241,7 +239,7 @@ static void read_dirty(struct cached_dev *dc) if (KEY_START(&w->key) != dc->last_read || jiffies_to_msecs(delay) > 50) while (!kthread_should_stop() && delay) - delay = schedule_timeout_interruptible(delay); + delay = schedule_timeout_uninterruptible(delay); dc->last_read = KEY_OFFSET(&w->key); @@ -438,7 +436,7 @@ static int bch_writeback_thread(void *arg) while (delay && !kthread_should_stop() && !test_bit(BCACHE_DEV_DETACHING, &dc->disk.flags)) - delay = schedule_timeout_interruptible(delay); + delay = schedule_timeout_uninterruptible(delay); } } @@ -476,6 +474,8 @@ void bch_sectors_dirty_init(struct cached_dev *dc) bch_btree_map_keys(&op.op, dc->disk.c, &KEY(op.inode, 0, 0), sectors_dirty_init_fn, 0); + + dc->disk.sectors_dirty_last = bcache_dev_sectors_dirty(&dc->disk); } int bch_cached_dev_writeback_init(struct cached_dev *dc) @@ -490,18 +490,15 @@ int bch_cached_dev_writeback_init(struct cached_dev *dc) dc->writeback_delay = 30; dc->writeback_rate.rate = 1024; - dc->writeback_rate_update_seconds = 30; - dc->writeback_rate_d_term = 16; - dc->writeback_rate_p_term_inverse = 64; - dc->writeback_rate_d_smooth = 8; + dc->writeback_rate_update_seconds = 5; + dc->writeback_rate_d_term = 30; + dc->writeback_rate_p_term_inverse = 6000; dc->writeback_thread = kthread_create(bch_writeback_thread, dc, "bcache_writeback"); if (IS_ERR(dc->writeback_thread)) return PTR_ERR(dc->writeback_thread); - set_task_state(dc->writeback_thread, TASK_INTERRUPTIBLE); - INIT_DELAYED_WORK(&dc->writeback_rate_update, update_writeback_rate); schedule_delayed_work(&dc->writeback_rate_update, dc->writeback_rate_update_seconds * HZ); diff --git a/drivers/pinctrl/pinctrl-baytrail.c b/drivers/pinctrl/pinctrl-baytrail.c index 2832576d8b12..114f5ef4b73a 100644 --- a/drivers/pinctrl/pinctrl-baytrail.c +++ b/drivers/pinctrl/pinctrl-baytrail.c @@ -512,6 +512,7 @@ static const struct dev_pm_ops byt_gpio_pm_ops = { static const struct acpi_device_id byt_gpio_acpi_match[] = { { "INT33B2", 0 }, + { "INT33FC", 0 }, { } }; MODULE_DEVICE_TABLE(acpi, byt_gpio_acpi_match); diff --git a/drivers/powercap/intel_rapl.c b/drivers/powercap/intel_rapl.c index 2a786c504460..3c6768378a94 100644 --- a/drivers/powercap/intel_rapl.c +++ b/drivers/powercap/intel_rapl.c @@ -833,6 +833,11 @@ static int rapl_write_data_raw(struct rapl_domain *rd, return 0; } +static const struct x86_cpu_id energy_unit_quirk_ids[] = { + { X86_VENDOR_INTEL, 6, 0x37},/* VLV */ + {} +}; + static int rapl_check_unit(struct rapl_package *rp, int cpu) { u64 msr_val; @@ -853,8 +858,11 @@ static int rapl_check_unit(struct rapl_package *rp, int cpu) * time unit: 1/time_unit_divisor Seconds */ value = (msr_val & ENERGY_UNIT_MASK) >> ENERGY_UNIT_OFFSET; - rp->energy_unit_divisor = 1 << value; - + /* some CPUs have different way to calculate energy unit */ + if (x86_match_cpu(energy_unit_quirk_ids)) + rp->energy_unit_divisor = 1000000 / (1 << value); + else + rp->energy_unit_divisor = 1 << value; value = (msr_val & POWER_UNIT_MASK) >> POWER_UNIT_OFFSET; rp->power_unit_divisor = 1 << value; @@ -941,6 +949,7 @@ static void package_power_limit_irq_restore(int package_id) static const struct x86_cpu_id rapl_ids[] = { { X86_VENDOR_INTEL, 6, 0x2a},/* SNB */ { X86_VENDOR_INTEL, 6, 0x2d},/* SNB EP */ + { X86_VENDOR_INTEL, 6, 0x37},/* VLV */ { X86_VENDOR_INTEL, 6, 0x3a},/* IVB */ { X86_VENDOR_INTEL, 6, 0x45},/* HSW */ /* TODO: Add more CPU IDs after testing */ diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c index c444654fc33f..5c4a95b516cf 100644 --- a/drivers/virtio/virtio_balloon.c +++ b/drivers/virtio/virtio_balloon.c @@ -285,7 +285,7 @@ static void update_balloon_size(struct virtio_balloon *vb) { __le32 actual = cpu_to_le32(vb->num_pages); - virtio_cwrite(vb->vdev, struct virtio_balloon_config, num_pages, + virtio_cwrite(vb->vdev, struct virtio_balloon_config, actual, &actual); } diff --git a/fs/ext2/super.c b/fs/ext2/super.c index 288534920fe5..20d6697bd638 100644 --- a/fs/ext2/super.c +++ b/fs/ext2/super.c @@ -1493,6 +1493,7 @@ static ssize_t ext2_quota_write(struct super_block *sb, int type, sb->s_blocksize - offset : towrite; tmp_bh.b_state = 0; + tmp_bh.b_size = sb->s_blocksize; err = ext2_get_block(inode, blk, &tmp_bh, 1); if (err < 0) goto out; diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index e6185031c1cc..ece55565b9cd 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -268,6 +268,16 @@ struct ext4_io_submit { /* Translate # of blks to # of clusters */ #define EXT4_NUM_B2C(sbi, blks) (((blks) + (sbi)->s_cluster_ratio - 1) >> \ (sbi)->s_cluster_bits) +/* Mask out the low bits to get the starting block of the cluster */ +#define EXT4_PBLK_CMASK(s, pblk) ((pblk) & \ + ~((ext4_fsblk_t) (s)->s_cluster_ratio - 1)) +#define EXT4_LBLK_CMASK(s, lblk) ((lblk) & \ + ~((ext4_lblk_t) (s)->s_cluster_ratio - 1)) +/* Get the cluster offset */ +#define EXT4_PBLK_COFF(s, pblk) ((pblk) & \ + ((ext4_fsblk_t) (s)->s_cluster_ratio - 1)) +#define EXT4_LBLK_COFF(s, lblk) ((lblk) & \ + ((ext4_lblk_t) (s)->s_cluster_ratio - 1)) /* * Structure of a blocks group descriptor diff --git a/fs/ext4/ext4_jbd2.c b/fs/ext4/ext4_jbd2.c index 17ac112ab101..3fe29de832c8 100644 --- a/fs/ext4/ext4_jbd2.c +++ b/fs/ext4/ext4_jbd2.c @@ -259,6 +259,15 @@ int __ext4_handle_dirty_metadata(const char *where, unsigned int line, if (WARN_ON_ONCE(err)) { ext4_journal_abort_handle(where, line, __func__, bh, handle, err); + ext4_error_inode(inode, where, line, + bh->b_blocknr, + "journal_dirty_metadata failed: " + "handle type %u started at line %u, " + "credits %u/%u, errcode %d", + handle->h_type, + handle->h_line_no, + handle->h_requested_credits, + handle->h_buffer_credits, err); } } else { if (inode) diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c index 35f65cf4f318..4410cc3d6ee2 100644 --- a/fs/ext4/extents.c +++ b/fs/ext4/extents.c @@ -360,8 +360,10 @@ static int ext4_valid_extent(struct inode *inode, struct ext4_extent *ext) { ext4_fsblk_t block = ext4_ext_pblock(ext); int len = ext4_ext_get_actual_len(ext); + ext4_lblk_t lblock = le32_to_cpu(ext->ee_block); + ext4_lblk_t last = lblock + len - 1; - if (len == 0) + if (lblock > last) return 0; return ext4_data_block_valid(EXT4_SB(inode->i_sb), block, len); } @@ -387,11 +389,26 @@ static int ext4_valid_extent_entries(struct inode *inode, if (depth == 0) { /* leaf entries */ struct ext4_extent *ext = EXT_FIRST_EXTENT(eh); + struct ext4_super_block *es = EXT4_SB(inode->i_sb)->s_es; + ext4_fsblk_t pblock = 0; + ext4_lblk_t lblock = 0; + ext4_lblk_t prev = 0; + int len = 0; while (entries) { if (!ext4_valid_extent(inode, ext)) return 0; + + /* Check for overlapping extents */ + lblock = le32_to_cpu(ext->ee_block); + len = ext4_ext_get_actual_len(ext); + if ((lblock <= prev) && prev) { + pblock = ext4_ext_pblock(ext); + es->s_last_error_block = cpu_to_le64(pblock); + return 0; + } ext++; entries--; + prev = lblock + len - 1; } } else { struct ext4_extent_idx *ext_idx = EXT_FIRST_INDEX(eh); @@ -1834,8 +1851,7 @@ static unsigned int ext4_ext_check_overlap(struct ext4_sb_info *sbi, depth = ext_depth(inode); if (!path[depth].p_ext) goto out; - b2 = le32_to_cpu(path[depth].p_ext->ee_block); - b2 &= ~(sbi->s_cluster_ratio - 1); + b2 = EXT4_LBLK_CMASK(sbi, le32_to_cpu(path[depth].p_ext->ee_block)); /* * get the next allocated block if the extent in the path @@ -1845,7 +1861,7 @@ static unsigned int ext4_ext_check_overlap(struct ext4_sb_info *sbi, b2 = ext4_ext_next_allocated_block(path); if (b2 == EXT_MAX_BLOCKS) goto out; - b2 &= ~(sbi->s_cluster_ratio - 1); + b2 = EXT4_LBLK_CMASK(sbi, b2); } /* check for wrap through zero on extent logical start block*/ @@ -2504,7 +2520,7 @@ static int ext4_remove_blocks(handle_t *handle, struct inode *inode, * extent, we have to mark the cluster as used (store negative * cluster number in partial_cluster). */ - unaligned = pblk & (sbi->s_cluster_ratio - 1); + unaligned = EXT4_PBLK_COFF(sbi, pblk); if (unaligned && (ee_len == num) && (*partial_cluster != -((long long)EXT4_B2C(sbi, pblk)))) *partial_cluster = EXT4_B2C(sbi, pblk); @@ -2598,7 +2614,7 @@ ext4_ext_rm_leaf(handle_t *handle, struct inode *inode, * accidentally freeing it later on */ pblk = ext4_ext_pblock(ex); - if (pblk & (sbi->s_cluster_ratio - 1)) + if (EXT4_PBLK_COFF(sbi, pblk)) *partial_cluster = -((long long)EXT4_B2C(sbi, pblk)); ex--; @@ -3753,7 +3769,7 @@ int ext4_find_delalloc_cluster(struct inode *inode, ext4_lblk_t lblk) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); ext4_lblk_t lblk_start, lblk_end; - lblk_start = lblk & (~(sbi->s_cluster_ratio - 1)); + lblk_start = EXT4_LBLK_CMASK(sbi, lblk); lblk_end = lblk_start + sbi->s_cluster_ratio - 1; return ext4_find_delalloc_range(inode, lblk_start, lblk_end); @@ -3812,9 +3828,9 @@ get_reserved_cluster_alloc(struct inode *inode, ext4_lblk_t lblk_start, trace_ext4_get_reserved_cluster_alloc(inode, lblk_start, num_blks); /* Check towards left side */ - c_offset = lblk_start & (sbi->s_cluster_ratio - 1); + c_offset = EXT4_LBLK_COFF(sbi, lblk_start); if (c_offset) { - lblk_from = lblk_start & (~(sbi->s_cluster_ratio - 1)); + lblk_from = EXT4_LBLK_CMASK(sbi, lblk_start); lblk_to = lblk_from + c_offset - 1; if (ext4_find_delalloc_range(inode, lblk_from, lblk_to)) @@ -3822,7 +3838,7 @@ get_reserved_cluster_alloc(struct inode *inode, ext4_lblk_t lblk_start, } /* Now check towards right. */ - c_offset = (lblk_start + num_blks) & (sbi->s_cluster_ratio - 1); + c_offset = EXT4_LBLK_COFF(sbi, lblk_start + num_blks); if (allocated_clusters && c_offset) { lblk_from = lblk_start + num_blks; lblk_to = lblk_from + (sbi->s_cluster_ratio - c_offset) - 1; @@ -4030,7 +4046,7 @@ static int get_implied_cluster_alloc(struct super_block *sb, struct ext4_ext_path *path) { struct ext4_sb_info *sbi = EXT4_SB(sb); - ext4_lblk_t c_offset = map->m_lblk & (sbi->s_cluster_ratio-1); + ext4_lblk_t c_offset = EXT4_LBLK_COFF(sbi, map->m_lblk); ext4_lblk_t ex_cluster_start, ex_cluster_end; ext4_lblk_t rr_cluster_start; ext4_lblk_t ee_block = le32_to_cpu(ex->ee_block); @@ -4048,8 +4064,7 @@ static int get_implied_cluster_alloc(struct super_block *sb, (rr_cluster_start == ex_cluster_start)) { if (rr_cluster_start == ex_cluster_end) ee_start += ee_len - 1; - map->m_pblk = (ee_start & ~(sbi->s_cluster_ratio - 1)) + - c_offset; + map->m_pblk = EXT4_PBLK_CMASK(sbi, ee_start) + c_offset; map->m_len = min(map->m_len, (unsigned) sbi->s_cluster_ratio - c_offset); /* @@ -4203,7 +4218,7 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode, */ map->m_flags &= ~EXT4_MAP_FROM_CLUSTER; newex.ee_block = cpu_to_le32(map->m_lblk); - cluster_offset = map->m_lblk & (sbi->s_cluster_ratio-1); + cluster_offset = EXT4_LBLK_CMASK(sbi, map->m_lblk); /* * If we are doing bigalloc, check to see if the extent returned @@ -4271,7 +4286,7 @@ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode, * needed so that future calls to get_implied_cluster_alloc() * work correctly. */ - offset = map->m_lblk & (sbi->s_cluster_ratio - 1); + offset = EXT4_LBLK_COFF(sbi, map->m_lblk); ar.len = EXT4_NUM_B2C(sbi, offset+allocated); ar.goal -= offset; ar.logical -= offset; diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index 075763474118..61d49ff22c81 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -1206,7 +1206,6 @@ static int ext4_journalled_write_end(struct file *file, */ static int ext4_da_reserve_metadata(struct inode *inode, ext4_lblk_t lblock) { - int retries = 0; struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); struct ext4_inode_info *ei = EXT4_I(inode); unsigned int md_needed; @@ -1218,7 +1217,6 @@ static int ext4_da_reserve_metadata(struct inode *inode, ext4_lblk_t lblock) * in order to allocate nrblocks * worse case is one extent per block */ -repeat: spin_lock(&ei->i_block_reservation_lock); /* * ext4_calc_metadata_amount() has side effects, which we have @@ -1238,10 +1236,6 @@ repeat: ei->i_da_metadata_calc_len = save_len; ei->i_da_metadata_calc_last_lblock = save_last_lblock; spin_unlock(&ei->i_block_reservation_lock); - if (ext4_should_retry_alloc(inode->i_sb, &retries)) { - cond_resched(); - goto repeat; - } return -ENOSPC; } ei->i_reserved_meta_blocks += md_needed; @@ -1255,7 +1249,6 @@ repeat: */ static int ext4_da_reserve_space(struct inode *inode, ext4_lblk_t lblock) { - int retries = 0; struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); struct ext4_inode_info *ei = EXT4_I(inode); unsigned int md_needed; @@ -1277,7 +1270,6 @@ static int ext4_da_reserve_space(struct inode *inode, ext4_lblk_t lblock) * in order to allocate nrblocks * worse case is one extent per block */ -repeat: spin_lock(&ei->i_block_reservation_lock); /* * ext4_calc_metadata_amount() has side effects, which we have @@ -1297,10 +1289,6 @@ repeat: ei->i_da_metadata_calc_len = save_len; ei->i_da_metadata_calc_last_lblock = save_last_lblock; spin_unlock(&ei->i_block_reservation_lock); - if (ext4_should_retry_alloc(inode->i_sb, &retries)) { - cond_resched(); - goto repeat; - } dquot_release_reservation_block(inode, EXT4_C2B(sbi, 1)); return -ENOSPC; } diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c index 4d113efa024c..04a5c7504be9 100644 --- a/fs/ext4/mballoc.c +++ b/fs/ext4/mballoc.c @@ -3442,6 +3442,9 @@ static void ext4_mb_pa_callback(struct rcu_head *head) { struct ext4_prealloc_space *pa; pa = container_of(head, struct ext4_prealloc_space, u.pa_rcu); + + BUG_ON(atomic_read(&pa->pa_count)); + BUG_ON(pa->pa_deleted == 0); kmem_cache_free(ext4_pspace_cachep, pa); } @@ -3455,11 +3458,13 @@ static void ext4_mb_put_pa(struct ext4_allocation_context *ac, ext4_group_t grp; ext4_fsblk_t grp_blk; - if (!atomic_dec_and_test(&pa->pa_count) || pa->pa_free != 0) - return; - /* in this short window concurrent discard can set pa_deleted */ spin_lock(&pa->pa_lock); + if (!atomic_dec_and_test(&pa->pa_count) || pa->pa_free != 0) { + spin_unlock(&pa->pa_lock); + return; + } + if (pa->pa_deleted == 1) { spin_unlock(&pa->pa_lock); return; @@ -4121,7 +4126,7 @@ ext4_mb_initialize_context(struct ext4_allocation_context *ac, ext4_get_group_no_and_offset(sb, goal, &group, &block); /* set up allocation goals */ - ac->ac_b_ex.fe_logical = ar->logical & ~(sbi->s_cluster_ratio - 1); + ac->ac_b_ex.fe_logical = EXT4_LBLK_CMASK(sbi, ar->logical); ac->ac_status = AC_STATUS_CONTINUE; ac->ac_sb = sb; ac->ac_inode = ar->inode; @@ -4663,7 +4668,7 @@ void ext4_free_blocks(handle_t *handle, struct inode *inode, * blocks at the beginning or the end unless we are explicitly * requested to avoid doing so. */ - overflow = block & (sbi->s_cluster_ratio - 1); + overflow = EXT4_PBLK_COFF(sbi, block); if (overflow) { if (flags & EXT4_FREE_BLOCKS_NOFREE_FIRST_CLUSTER) { overflow = sbi->s_cluster_ratio - overflow; @@ -4677,7 +4682,7 @@ void ext4_free_blocks(handle_t *handle, struct inode *inode, count += overflow; } } - overflow = count & (sbi->s_cluster_ratio - 1); + overflow = EXT4_LBLK_COFF(sbi, count); if (overflow) { if (flags & EXT4_FREE_BLOCKS_NOFREE_LAST_CLUSTER) { if (count > overflow) diff --git a/fs/ext4/super.c b/fs/ext4/super.c index c977f4e4e63b..1f7784de05b6 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -792,7 +792,7 @@ static void ext4_put_super(struct super_block *sb) } ext4_es_unregister_shrinker(sbi); - del_timer(&sbi->s_err_report); + del_timer_sync(&sbi->s_err_report); ext4_release_system_zone(sb); ext4_mb_release(sb); ext4_ext_release(sb); @@ -3316,11 +3316,19 @@ int ext4_calculate_overhead(struct super_block *sb) } -static ext4_fsblk_t ext4_calculate_resv_clusters(struct ext4_sb_info *sbi) +static ext4_fsblk_t ext4_calculate_resv_clusters(struct super_block *sb) { ext4_fsblk_t resv_clusters; /* + * There's no need to reserve anything when we aren't using extents. + * The space estimates are exact, there are no unwritten extents, + * hole punching doesn't need new metadata... This is needed especially + * to keep ext2/3 backward compatibility. + */ + if (!EXT4_HAS_INCOMPAT_FEATURE(sb, EXT4_FEATURE_INCOMPAT_EXTENTS)) + return 0; + /* * By default we reserve 2% or 4096 clusters, whichever is smaller. * This should cover the situations where we can not afford to run * out of space like for example punch hole, or converting @@ -3328,7 +3336,8 @@ static ext4_fsblk_t ext4_calculate_resv_clusters(struct ext4_sb_info *sbi) * allocation would require 1, or 2 blocks, higher numbers are * very rare. */ - resv_clusters = ext4_blocks_count(sbi->s_es) >> sbi->s_cluster_bits; + resv_clusters = ext4_blocks_count(EXT4_SB(sb)->s_es) >> + EXT4_SB(sb)->s_cluster_bits; do_div(resv_clusters, 50); resv_clusters = min_t(ext4_fsblk_t, resv_clusters, 4096); @@ -4071,10 +4080,10 @@ no_journal: "available"); } - err = ext4_reserve_clusters(sbi, ext4_calculate_resv_clusters(sbi)); + err = ext4_reserve_clusters(sbi, ext4_calculate_resv_clusters(sb)); if (err) { ext4_msg(sb, KERN_ERR, "failed to reserve %llu clusters for " - "reserved pool", ext4_calculate_resv_clusters(sbi)); + "reserved pool", ext4_calculate_resv_clusters(sb)); goto failed_mount4a; } @@ -4184,7 +4193,7 @@ failed_mount_wq: } failed_mount3: ext4_es_unregister_shrinker(sbi); - del_timer(&sbi->s_err_report); + del_timer_sync(&sbi->s_err_report); if (sbi->s_flex_groups) ext4_kvfree(sbi->s_flex_groups); percpu_counter_destroy(&sbi->s_freeclusters_counter); diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c index 52032647dd4a..5fa344afb49a 100644 --- a/fs/jbd2/journal.c +++ b/fs/jbd2/journal.c @@ -702,7 +702,7 @@ int jbd2_log_wait_commit(journal_t *journal, tid_t tid) read_lock(&journal->j_state_lock); #ifdef CONFIG_JBD2_DEBUG if (!tid_geq(journal->j_commit_request, tid)) { - printk(KERN_EMERG + printk(KERN_ERR "%s: error: j_commit_request=%d, tid=%d\n", __func__, journal->j_commit_request, tid); } @@ -718,10 +718,8 @@ int jbd2_log_wait_commit(journal_t *journal, tid_t tid) } read_unlock(&journal->j_state_lock); - if (unlikely(is_journal_aborted(journal))) { - printk(KERN_EMERG "journal commit I/O error\n"); + if (unlikely(is_journal_aborted(journal))) err = -EIO; - } return err; } @@ -1527,13 +1525,13 @@ static int journal_get_superblock(journal_t *journal) if (JBD2_HAS_COMPAT_FEATURE(journal, JBD2_FEATURE_COMPAT_CHECKSUM) && JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V2)) { /* Can't have checksum v1 and v2 on at the same time! */ - printk(KERN_ERR "JBD: Can't enable checksumming v1 and v2 " + printk(KERN_ERR "JBD2: Can't enable checksumming v1 and v2 " "at the same time!\n"); goto out; } if (!jbd2_verify_csum_type(journal, sb)) { - printk(KERN_ERR "JBD: Unknown checksum type\n"); + printk(KERN_ERR "JBD2: Unknown checksum type\n"); goto out; } @@ -1541,7 +1539,7 @@ static int journal_get_superblock(journal_t *journal) if (JBD2_HAS_INCOMPAT_FEATURE(journal, JBD2_FEATURE_INCOMPAT_CSUM_V2)) { journal->j_chksum_driver = crypto_alloc_shash("crc32c", 0, 0); if (IS_ERR(journal->j_chksum_driver)) { - printk(KERN_ERR "JBD: Cannot load crc32c driver.\n"); + printk(KERN_ERR "JBD2: Cannot load crc32c driver.\n"); err = PTR_ERR(journal->j_chksum_driver); journal->j_chksum_driver = NULL; goto out; @@ -1550,7 +1548,7 @@ static int journal_get_superblock(journal_t *journal) /* Check superblock checksum */ if (!jbd2_superblock_csum_verify(journal, sb)) { - printk(KERN_ERR "JBD: journal checksum error\n"); + printk(KERN_ERR "JBD2: journal checksum error\n"); goto out; } @@ -1836,7 +1834,7 @@ int jbd2_journal_set_features (journal_t *journal, unsigned long compat, journal->j_chksum_driver = crypto_alloc_shash("crc32c", 0, 0); if (IS_ERR(journal->j_chksum_driver)) { - printk(KERN_ERR "JBD: Cannot load crc32c " + printk(KERN_ERR "JBD2: Cannot load crc32c " "driver.\n"); journal->j_chksum_driver = NULL; return 0; @@ -2645,7 +2643,7 @@ static void __exit journal_exit(void) #ifdef CONFIG_JBD2_DEBUG int n = atomic_read(&nr_journal_heads); if (n) - printk(KERN_EMERG "JBD2: leaked %d journal_heads!\n", n); + printk(KERN_ERR "JBD2: leaked %d journal_heads!\n", n); #endif jbd2_remove_jbd_stats_proc_entry(); jbd2_journal_destroy_caches(); diff --git a/fs/jbd2/recovery.c b/fs/jbd2/recovery.c index 3929c50428b1..3b6bb19d60b1 100644 --- a/fs/jbd2/recovery.c +++ b/fs/jbd2/recovery.c @@ -594,7 +594,7 @@ static int do_one_pass(journal_t *journal, be32_to_cpu(tmp->h_sequence))) { brelse(obh); success = -EIO; - printk(KERN_ERR "JBD: Invalid " + printk(KERN_ERR "JBD2: Invalid " "checksum recovering " "block %llu in log\n", blocknr); diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c index 7aa9a32573bb..8360674c85bc 100644 --- a/fs/jbd2/transaction.c +++ b/fs/jbd2/transaction.c @@ -932,7 +932,7 @@ repeat: jbd2_alloc(jh2bh(jh)->b_size, GFP_NOFS); if (!frozen_buffer) { - printk(KERN_EMERG + printk(KERN_ERR "%s: OOM for frozen_buffer\n", __func__); JBUFFER_TRACE(jh, "oom!"); @@ -1166,7 +1166,7 @@ repeat: if (!jh->b_committed_data) { committed_data = jbd2_alloc(jh2bh(jh)->b_size, GFP_NOFS); if (!committed_data) { - printk(KERN_EMERG "%s: No memory for committed data\n", + printk(KERN_ERR "%s: No memory for committed data\n", __func__); err = -ENOMEM; goto out; @@ -1290,7 +1290,10 @@ int jbd2_journal_dirty_metadata(handle_t *handle, struct buffer_head *bh) * once a transaction -bzzz */ jh->b_modified = 1; - J_ASSERT_JH(jh, handle->h_buffer_credits > 0); + if (handle->h_buffer_credits <= 0) { + ret = -ENOSPC; + goto out_unlock_bh; + } handle->h_buffer_credits--; } @@ -1305,7 +1308,7 @@ int jbd2_journal_dirty_metadata(handle_t *handle, struct buffer_head *bh) JBUFFER_TRACE(jh, "fastpath"); if (unlikely(jh->b_transaction != journal->j_running_transaction)) { - printk(KERN_EMERG "JBD: %s: " + printk(KERN_ERR "JBD2: %s: " "jh->b_transaction (%llu, %p, %u) != " "journal->j_running_transaction (%p, %u)", journal->j_devname, @@ -1332,7 +1335,7 @@ int jbd2_journal_dirty_metadata(handle_t *handle, struct buffer_head *bh) JBUFFER_TRACE(jh, "already on other transaction"); if (unlikely(jh->b_transaction != journal->j_committing_transaction)) { - printk(KERN_EMERG "JBD: %s: " + printk(KERN_ERR "JBD2: %s: " "jh->b_transaction (%llu, %p, %u) != " "journal->j_committing_transaction (%p, %u)", journal->j_devname, @@ -1345,7 +1348,7 @@ int jbd2_journal_dirty_metadata(handle_t *handle, struct buffer_head *bh) ret = -EINVAL; } if (unlikely(jh->b_next_transaction != transaction)) { - printk(KERN_EMERG "JBD: %s: " + printk(KERN_ERR "JBD2: %s: " "jh->b_next_transaction (%llu, %p, %u) != " "transaction (%p, %u)", journal->j_devname, @@ -1373,7 +1376,6 @@ out_unlock_bh: jbd2_journal_put_journal_head(jh); out: JBUFFER_TRACE(jh, "exit"); - WARN_ON(ret); /* All errors are bugs, so dump the stack */ return ret; } diff --git a/include/linux/auxvec.h b/include/linux/auxvec.h index 669fef5c745a..3e0fbe441763 100644 --- a/include/linux/auxvec.h +++ b/include/linux/auxvec.h @@ -3,6 +3,6 @@ #include <uapi/linux/auxvec.h> -#define AT_VECTOR_SIZE_BASE 19 /* NEW_AUX_ENT entries in auxiliary table */ +#define AT_VECTOR_SIZE_BASE 20 /* NEW_AUX_ENT entries in auxiliary table */ /* number of "#define AT_.*" above, minus {AT_NULL, AT_IGNORE, AT_NOTELF} */ #endif /* _LINUX_AUXVEC_H */ diff --git a/include/linux/libata.h b/include/linux/libata.h index 0e23c26485f4..9b503376738f 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -418,6 +418,7 @@ enum { ATA_HORKAGE_DUMP_ID = (1 << 16), /* dump IDENTIFY data */ ATA_HORKAGE_MAX_SEC_LBA48 = (1 << 17), /* Set max sects to 65535 */ ATA_HORKAGE_ATAPI_DMADIR = (1 << 18), /* device requires dmadir */ + ATA_HORKAGE_NO_NCQ_TRIM = (1 << 19), /* don't use queued TRIM */ /* DMA mask for user DMA control: User visible values; DO NOT renumber */ diff --git a/include/linux/percpu-defs.h b/include/linux/percpu-defs.h index 57e890abe1f0..a5fc7d01aad6 100644 --- a/include/linux/percpu-defs.h +++ b/include/linux/percpu-defs.h @@ -69,6 +69,7 @@ __PCPU_DUMMY_ATTRS char __pcpu_scope_##name; \ extern __PCPU_DUMMY_ATTRS char __pcpu_unique_##name; \ __PCPU_DUMMY_ATTRS char __pcpu_unique_##name; \ + extern __PCPU_ATTRS(sec) __typeof__(type) name; \ __PCPU_ATTRS(sec) PER_CPU_DEF_ATTRIBUTES __weak \ __typeof__(type) name #else diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index 979874c627ee..61e1935c91b1 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -978,7 +978,7 @@ struct ib_uobject { }; struct ib_udata { - void __user *inbuf; + const void __user *inbuf; void __user *outbuf; size_t inlen; size_t outlen; diff --git a/kernel/cgroup.c b/kernel/cgroup.c index 8b729c278b64..bc1dcabe9217 100644 --- a/kernel/cgroup.c +++ b/kernel/cgroup.c @@ -890,6 +890,16 @@ static void cgroup_diput(struct dentry *dentry, struct inode *inode) struct cgroup *cgrp = dentry->d_fsdata; BUG_ON(!(cgroup_is_dead(cgrp))); + + /* + * XXX: cgrp->id is only used to look up css's. As cgroup + * and css's lifetimes will be decoupled, it should be made + * per-subsystem and moved to css->id so that lookups are + * successful until the target css is released. + */ + idr_remove(&cgrp->root->cgroup_idr, cgrp->id); + cgrp->id = -1; + call_rcu(&cgrp->rcu_head, cgroup_free_rcu); } else { struct cfent *cfe = __d_cfe(dentry); @@ -4268,6 +4278,7 @@ static void css_release(struct percpu_ref *ref) struct cgroup_subsys_state *css = container_of(ref, struct cgroup_subsys_state, refcnt); + rcu_assign_pointer(css->cgroup->subsys[css->ss->subsys_id], NULL); call_rcu(&css->rcu_head, css_free_rcu_fn); } @@ -4426,14 +4437,6 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry, list_add_tail_rcu(&cgrp->sibling, &cgrp->parent->children); root->number_of_cgroups++; - /* each css holds a ref to the cgroup's dentry and the parent css */ - for_each_root_subsys(root, ss) { - struct cgroup_subsys_state *css = css_ar[ss->subsys_id]; - - dget(dentry); - css_get(css->parent); - } - /* hold a ref to the parent's dentry */ dget(parent->dentry); @@ -4445,6 +4448,13 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry, if (err) goto err_destroy; + /* each css holds a ref to the cgroup's dentry and parent css */ + dget(dentry); + css_get(css->parent); + + /* mark it consumed for error path */ + css_ar[ss->subsys_id] = NULL; + if (ss->broken_hierarchy && !ss->warned_broken_hierarchy && parent->parent) { pr_warning("cgroup: %s (%d) created nested cgroup for controller \"%s\" which has incomplete hierarchy support. Nested cgroups may change behavior in the future.\n", @@ -4491,6 +4501,14 @@ err_free_cgrp: return err; err_destroy: + for_each_root_subsys(root, ss) { + struct cgroup_subsys_state *css = css_ar[ss->subsys_id]; + + if (css) { + percpu_ref_cancel_init(&css->refcnt); + ss->css_free(css); + } + } cgroup_destroy_locked(cgrp); mutex_unlock(&cgroup_mutex); mutex_unlock(&dentry->d_inode->i_mutex); @@ -4652,8 +4670,12 @@ static int cgroup_destroy_locked(struct cgroup *cgrp) * will be invoked to perform the rest of destruction once the * percpu refs of all css's are confirmed to be killed. */ - for_each_root_subsys(cgrp->root, ss) - kill_css(cgroup_css(cgrp, ss)); + for_each_root_subsys(cgrp->root, ss) { + struct cgroup_subsys_state *css = cgroup_css(cgrp, ss); + + if (css) + kill_css(css); + } /* * Mark @cgrp dead. This prevents further task migration and child @@ -4722,14 +4744,6 @@ static void cgroup_destroy_css_killed(struct cgroup *cgrp) /* delete this cgroup from parent->children */ list_del_rcu(&cgrp->sibling); - /* - * We should remove the cgroup object from idr before its grace - * period starts, so we won't be looking up a cgroup while the - * cgroup is being freed. - */ - idr_remove(&cgrp->root->cgroup_idr, cgrp->id); - cgrp->id = -1; - dput(d); set_bit(CGRP_RELEASABLE, &parent->flags); diff --git a/kernel/freezer.c b/kernel/freezer.c index b462fa197517..aa6a8aadb911 100644 --- a/kernel/freezer.c +++ b/kernel/freezer.c @@ -19,6 +19,12 @@ EXPORT_SYMBOL(system_freezing_cnt); bool pm_freezing; bool pm_nosig_freezing; +/* + * Temporary export for the deadlock workaround in ata_scsi_hotplug(). + * Remove once the hack becomes unnecessary. + */ +EXPORT_SYMBOL_GPL(pm_freezing); + /* protects freezing and frozen transitions */ static DEFINE_SPINLOCK(freezer_lock); diff --git a/kernel/power/console.c b/kernel/power/console.c index 463aa6736751..eacb8bd8cab4 100644 --- a/kernel/power/console.c +++ b/kernel/power/console.c @@ -81,6 +81,7 @@ void pm_vt_switch_unregister(struct device *dev) list_for_each_entry(tmp, &pm_vt_switch_list, head) { if (tmp->dev == dev) { list_del(&tmp->head); + kfree(tmp); break; } } diff --git a/scripts/link-vmlinux.sh b/scripts/link-vmlinux.sh index 32b10f53d0b4..2dcb37736d84 100644 --- a/scripts/link-vmlinux.sh +++ b/scripts/link-vmlinux.sh @@ -82,7 +82,9 @@ kallsyms() kallsymopt="${kallsymopt} --all-symbols" fi - kallsymopt="${kallsymopt} --page-offset=$CONFIG_PAGE_OFFSET" + if [ -n "${CONFIG_ARM}" ] && [ -n "${CONFIG_PAGE_OFFSET}" ]; then + kallsymopt="${kallsymopt} --page-offset=$CONFIG_PAGE_OFFSET" + fi local aflags="${KBUILD_AFLAGS} ${KBUILD_AFLAGS_KERNEL} \ ${NOSTDINC_FLAGS} ${LINUXINCLUDE} ${KBUILD_CPPFLAGS}" diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index 419491d8e7d2..6625699f497c 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -4334,8 +4334,10 @@ static int selinux_socket_sock_rcv_skb(struct sock *sk, struct sk_buff *skb) } err = avc_has_perm(sk_sid, peer_sid, SECCLASS_PEER, PEER__RECV, &ad); - if (err) + if (err) { selinux_netlbl_err(skb, err, 0); + return err; + } } if (secmark_active) { @@ -5586,11 +5588,11 @@ static int selinux_setprocattr(struct task_struct *p, /* Check for ptracing, and update the task SID if ok. Otherwise, leave SID unchanged and fail. */ ptsid = 0; - task_lock(p); + rcu_read_lock(); tracer = ptrace_parent(p); if (tracer) ptsid = task_sid(tracer); - task_unlock(p); + rcu_read_unlock(); if (tracer) { error = avc_has_perm(ptsid, sid, SECCLASS_PROCESS, |