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 00000000000..b2830b43589 --- /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 50680a59a2f..b9e9bd85429 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 dc1ec0dff93..ea04b342c02 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 ba6cf8e9aa0..b91ce75bd35 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 5d9248526d7..4770de5707b 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 6745fe137b9..e6039059737 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 786294bb682..3650b218322 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 14f1e950633..c0ed4f273cf 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 ae2d73fe321..3e23e9941da 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 75b93678bbc..1393a5890ed 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 ab58556d347..377eb889f55 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 f370fc13aea..a2e69d26266 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 9199c93be92..eb6e1e0e8db 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 02d534da22d..16d7b4ac94b 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)); +</ |