diff options
98 files changed, 1991 insertions, 499 deletions
diff --git a/Documentation/block/cfq-iosched.txt b/Documentation/block/cfq-iosched.txt index e578fee..6d670f5 100644 --- a/Documentation/block/cfq-iosched.txt +++ b/Documentation/block/cfq-iosched.txt @@ -43,3 +43,74 @@ If one sets slice_idle=0 and if storage supports NCQ, CFQ internally switches to IOPS mode and starts providing fairness in terms of number of requests dispatched. Note that this mode switching takes effect only for group scheduling. For non-cgroup users nothing should change. + +CFQ IO scheduler Idling Theory +=============================== +Idling on a queue is primarily about waiting for the next request to come +on same queue after completion of a request. In this process CFQ will not +dispatch requests from other cfq queues even if requests are pending there. + +The rationale behind idling is that it can cut down on number of seeks +on rotational media. For example, if a process is doing dependent +sequential reads (next read will come on only after completion of previous +one), then not dispatching request from other queue should help as we +did not move the disk head and kept on dispatching sequential IO from +one queue. + +CFQ has following service trees and various queues are put on these trees. + + sync-idle sync-noidle async + +All cfq queues doing synchronous sequential IO go on to sync-idle tree. +On this tree we idle on each queue individually. + +All synchronous non-sequential queues go on sync-noidle tree. Also any +request which are marked with REQ_NOIDLE go on this service tree. On this +tree we do not idle on individual queues instead idle on the whole group +of queues or the tree. So if there are 4 queues waiting for IO to dispatch +we will idle only once last queue has dispatched the IO and there is +no more IO on this service tree. + +All async writes go on async service tree. There is no idling on async +queues. + +CFQ has some optimizations for SSDs and if it detects a non-rotational +media which can support higher queue depth (multiple requests at in +flight at a time), then it cuts down on idling of individual queues and +all the queues move to sync-noidle tree and only tree idle remains. This +tree idling provides isolation with buffered write queues on async tree. + +FAQ +=== +Q1. Why to idle at all on queues marked with REQ_NOIDLE. + +A1. We only do tree idle (all queues on sync-noidle tree) on queues marked + with REQ_NOIDLE. This helps in providing isolation with all the sync-idle + queues. Otherwise in presence of many sequential readers, other + synchronous IO might not get fair share of disk. + + For example, if there are 10 sequential readers doing IO and they get + 100ms each. If a REQ_NOIDLE request comes in, it will be scheduled + roughly after 1 second. If after completion of REQ_NOIDLE request we + do not idle, and after a couple of milli seconds a another REQ_NOIDLE + request comes in, again it will be scheduled after 1second. Repeat it + and notice how a workload can lose its disk share and suffer due to + multiple sequential readers. + + fsync can generate dependent IO where bunch of data is written in the + context of fsync, and later some journaling data is written. Journaling + data comes in only after fsync has finished its IO (atleast for ext4 + that seemed to be the case). Now if one decides not to idle on fsync + thread due to REQ_NOIDLE, then next journaling write will not get + scheduled for another second. A process doing small fsync, will suffer + badly in presence of multiple sequential readers. + + Hence doing tree idling on threads using REQ_NOIDLE flag on requests + provides isolation from multiple sequential readers and at the same + time we do not idle on individual threads. + +Q2. When to specify REQ_NOIDLE +A2. I would think whenever one is doing synchronous write and not expecting + more writes to be dispatched from same context soon, should be able + to specify REQ_NOIDLE on writes and that probably should work well for + most of the cases. diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index 6ca1f5c..614d038 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -1350,9 +1350,12 @@ bytes respectively. Such letter suffixes can also be entirely omitted. it is equivalent to "nosmp", which also disables the IO APIC. - max_loop= [LOOP] Maximum number of loopback devices that can - be mounted - Format: <1-256> + max_loop= [LOOP] The number of loop block devices that get + (loop.max_loop) unconditionally pre-created at init time. The default + number is configured by BLK_DEV_LOOP_MIN_COUNT. Instead + of statically allocating a predefined number, loop + devices can be requested on-demand with the + /dev/loop-control interface. mcatest= [IA-64] diff --git a/arch/sparc/kernel/pcic.c b/arch/sparc/kernel/pcic.c index a19f041..1aaf8c1 100644 --- a/arch/sparc/kernel/pcic.c +++ b/arch/sparc/kernel/pcic.c @@ -352,8 +352,8 @@ int __init pcic_probe(void) strcpy(pbm->prom_name, namebuf); { - extern volatile int t_nmi[1]; - extern int pcic_nmi_trap_patch[1]; + extern volatile int t_nmi[4]; + extern int pcic_nmi_trap_patch[4]; t_nmi[0] = pcic_nmi_trap_patch[0]; t_nmi[1] = pcic_nmi_trap_patch[1]; diff --git a/arch/x86/include/asm/xen/page.h b/arch/x86/include/asm/xen/page.h index 64a619d..7ff4669 100644 --- a/arch/x86/include/asm/xen/page.h +++ b/arch/x86/include/asm/xen/page.h @@ -39,7 +39,7 @@ typedef struct xpaddr { ((unsigned long)((u64)CONFIG_XEN_MAX_DOMAIN_MEMORY * 1024 * 1024 * 1024 / PAGE_SIZE)) extern unsigned long *machine_to_phys_mapping; -extern unsigned int machine_to_phys_order; +extern unsigned long machine_to_phys_nr; extern unsigned long get_phys_to_machine(unsigned long pfn); extern bool set_phys_to_machine(unsigned long pfn, unsigned long mfn); @@ -87,7 +87,7 @@ static inline unsigned long mfn_to_pfn(unsigned long mfn) if (xen_feature(XENFEAT_auto_translated_physmap)) return mfn; - if (unlikely((mfn >> machine_to_phys_order) != 0)) { + if (unlikely(mfn >= machine_to_phys_nr)) { pfn = ~0; goto try_override; } diff --git a/arch/x86/pci/acpi.c b/arch/x86/pci/acpi.c index ae3cb23..c953302 100644 --- a/arch/x86/pci/acpi.c +++ b/arch/x86/pci/acpi.c @@ -360,6 +360,15 @@ struct pci_bus * __devinit pci_acpi_scan_root(struct acpi_pci_root *root) } } + /* After the PCI-E bus has been walked and all devices discovered, + * configure any settings of the fabric that might be necessary. + */ + if (bus) { + struct pci_bus *child; + list_for_each_entry(child, &bus->children, node) + pcie_bus_configure_settings(child, child->self->pcie_mpss); + } + if (!bus) kfree(sd); diff --git a/arch/x86/xen/Makefile b/arch/x86/xen/Makefile index 3326204..add2c2d 100644 --- a/arch/x86/xen/Makefile +++ b/arch/x86/xen/Makefile @@ -15,7 +15,7 @@ obj-y := enlighten.o setup.o multicalls.o mmu.o irq.o \ grant-table.o suspend.o platform-pci-unplug.o \ p2m.o -obj-$(CONFIG_FTRACE) += trace.o +obj-$(CONFIG_EVENT_TRACING) += trace.o obj-$(CONFIG_SMP) += smp.o obj-$(CONFIG_PARAVIRT_SPINLOCKS)+= spinlock.o diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index e2345af..2d69617 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -77,8 +77,8 @@ EXPORT_SYMBOL_GPL(xen_domain_type); unsigned long *machine_to_phys_mapping = (void *)MACH2PHYS_VIRT_START; EXPORT_SYMBOL(machine_to_phys_mapping); -unsigned int machine_to_phys_order; -EXPORT_SYMBOL(machine_to_phys_order); +unsigned long machine_to_phys_nr; +EXPORT_SYMBOL(machine_to_phys_nr); struct start_info *xen_start_info; EXPORT_SYMBOL_GPL(xen_start_info); diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c index 8cce339..20a6142 100644 --- a/arch/x86/xen/mmu.c +++ b/arch/x86/xen/mmu.c @@ -1713,15 +1713,19 @@ static void __init xen_map_identity_early(pmd_t *pmd, unsigned long max_pfn) void __init xen_setup_machphys_mapping(void) { struct xen_machphys_mapping mapping; - unsigned long machine_to_phys_nr_ents; if (HYPERVISOR_memory_op(XENMEM_machphys_mapping, &mapping) == 0) { machine_to_phys_mapping = (unsigned long *)mapping.v_start; - machine_to_phys_nr_ents = mapping.max_mfn + 1; + machine_to_phys_nr = mapping.max_mfn + 1; } else { - machine_to_phys_nr_ents = MACH2PHYS_NR_ENTRIES; + machine_to_phys_nr = MACH2PHYS_NR_ENTRIES; } - machine_to_phys_order = fls(machine_to_phys_nr_ents - 1); +#ifdef CONFIG_X86_32 + if ((machine_to_phys_mapping + machine_to_phys_nr) + < machine_to_phys_mapping) + machine_to_phys_nr = (unsigned long *)NULL + - machine_to_phys_mapping; +#endif } #ifdef CONFIG_X86_64 diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c index b4533a8..e79dbb9 100644 --- a/arch/x86/xen/smp.c +++ b/arch/x86/xen/smp.c @@ -521,8 +521,6 @@ static void __init xen_hvm_smp_prepare_cpus(unsigned int max_cpus) native_smp_prepare_cpus(max_cpus); WARN_ON(xen_smp_intr_init(0)); - if (!xen_have_vector_callback) - return; xen_init_lock_cpu(0); xen_init_spinlocks(); } @@ -546,6 +544,8 @@ static void xen_hvm_cpu_die(unsigned int cpu) void __init xen_hvm_smp_init(void) { + if (!xen_have_vector_callback) + return; smp_ops.smp_prepare_cpus = xen_hvm_smp_prepare_cpus; smp_ops.smp_send_reschedule = xen_smp_send_reschedule; smp_ops.cpu_up = xen_hvm_cpu_up; diff --git a/block/Kconfig b/block/Kconfig index 60be1e0..e97934e 100644 --- a/block/Kconfig +++ b/block/Kconfig @@ -65,6 +65,16 @@ config BLK_DEV_BSG If unsure, say Y. +config BLK_DEV_BSGLIB + bool "Block layer SG support v4 helper lib" + default n + select BLK_DEV_BSG + help + Subsystems will normally enable this if needed. Users will not + normally need to manually enable this. + + If unsure, say N. + config BLK_DEV_INTEGRITY bool "Block layer data integrity support" ---help--- diff --git a/block/Makefile b/block/Makefile index 0fec4b3..514c6e4 100644 --- a/block/Makefile +++ b/block/Makefile @@ -8,6 +8,7 @@ obj-$(CONFIG_BLOCK) := elevator.o blk-core.o blk-tag.o blk-sysfs.o \ blk-iopoll.o blk-lib.o ioctl.o genhd.o scsi_ioctl.o obj-$(CONFIG_BLK_DEV_BSG) += bsg.o +obj-$(CONFIG_BLK_DEV_BSGLIB) += bsg-lib.o obj-$(CONFIG_BLK_CGROUP) += blk-cgroup.o obj-$(CONFIG_BLK_DEV_THROTTLING) += blk-throttle.o obj-$(CONFIG_IOSCHED_NOOP) += noop-iosched.o diff --git a/block/blk-core.c b/block/blk-core.c index b627558..90e1ffd 100644 --- a/block/blk-core.c +++ b/block/blk-core.c @@ -1702,6 +1702,7 @@ EXPORT_SYMBOL_GPL(blk_rq_check_limits); int blk_insert_cloned_request(struct request_queue *q, struct request *rq) { unsigned long flags; + int where = ELEVATOR_INSERT_BACK; if (blk_rq_check_limits(q, rq)) return -EIO; @@ -1718,7 +1719,10 @@ int blk_insert_cloned_request(struct request_queue *q, struct request *rq) */ BUG_ON(blk_queued_rq(rq)); - add_acct_request(q, rq, ELEVATOR_INSERT_BACK); + if (rq->cmd_flags & (REQ_FLUSH|REQ_FUA)) + where = ELEVATOR_INSERT_FLUSH; + + add_acct_request(q, rq, where); spin_unlock_irqrestore(q->queue_lock, flags); return 0; @@ -2275,7 +2279,7 @@ static bool blk_end_bidi_request(struct request *rq, int error, * %false - we are done with this request * %true - still buffers pending for this request **/ -static bool __blk_end_bidi_request(struct request *rq, int error, +bool __blk_end_bidi_request(struct request *rq, int error, unsigned int nr_bytes, unsigned int bidi_bytes) { if (blk_update_bidi_request(rq, error, nr_bytes, bidi_bytes)) diff --git a/block/blk-flush.c b/block/blk-flush.c index bb21e4c..491eb30 100644 --- a/block/blk-flush.c +++ b/block/blk-flush.c @@ -95,11 +95,12 @@ static unsigned int blk_flush_policy(unsigned int fflags, struct request *rq) { unsigned int policy = 0; + if (blk_rq_sectors(rq)) + policy |= REQ_FSEQ_DATA; + if (fflags & REQ_FLUSH) { if (rq->cmd_flags & REQ_FLUSH) policy |= REQ_FSEQ_PREFLUSH; - if (blk_rq_sectors(rq)) - policy |= REQ_FSEQ_DATA; if (!(fflags & REQ_FUA) && (rq->cmd_flags & REQ_FUA)) policy |= REQ_FSEQ_POSTFLUSH; } @@ -122,7 +123,7 @@ static void blk_flush_restore_request(struct request *rq) /* make @rq a normal request */ rq->cmd_flags &= ~REQ_FLUSH_SEQ; - rq->end_io = NULL; + rq->end_io = rq->flush.saved_end_io; } /** @@ -300,9 +301,6 @@ void blk_insert_flush(struct request *rq) unsigned int fflags = q->flush_flags; /* may change, cache */ unsigned int policy = blk_flush_policy(fflags, rq); - BUG_ON(rq->end_io); - BUG_ON(!rq->bio || rq->bio != rq->biotail); - /* * @policy now records what operations need to be done. Adjust * REQ_FLUSH and FUA for the driver. @@ -312,6 +310,19 @@ void blk_insert_flush(struct request *rq) rq->cmd_flags &= ~REQ_FUA; /* + * An empty flush handed down from a stacking driver may + * translate into nothing if the underlying device does not + * advertise a write-back cache. In this case, simply + * complete the request. + */ + if (!policy) { + __blk_end_bidi_request(rq, 0, 0, 0); + return; + } + + BUG_ON(!rq->bio || rq->bio != rq->biotail); + + /* * If there's data but flush is not necessary, the request can be * processed directly without going through flush machinery. Queue * for normal execution. @@ -319,6 +330,7 @@ void blk_insert_flush(struct request *rq) if ((policy & REQ_FSEQ_DATA) && !(policy & (REQ_FSEQ_PREFLUSH | REQ_FSEQ_POSTFLUSH))) { list_add_tail(&rq->queuelist, &q->queue_head); + blk_run_queue_async(q); return; } @@ -329,6 +341,7 @@ void blk_insert_flush(struct request *rq) memset(&rq->flush, 0, sizeof(rq->flush)); INIT_LIST_HEAD(&rq->flush.list); rq->cmd_flags |= REQ_FLUSH_SEQ; + rq->flush.saved_end_io = rq->end_io; /* Usually NULL */ rq->end_io = flush_data_end_io; blk_flush_complete_seq(rq, REQ_FSEQ_ACTIONS & ~policy, 0); diff --git a/block/blk-softirq.c b/block/blk-softirq.c index 475fab8..58340d0 100644 --- a/block/blk-softirq.c +++ b/block/blk-softirq.c @@ -124,6 +124,14 @@ void __blk_complete_request(struct request *req) } else ccpu = cpu; + /* + * If current CPU and requested CPU are in the same group, running + * softirq in current CPU. One might concern this is just like + * QUEUE_FLAG_SAME_FORCE, but actually not. blk_complete_request() is + * running in interrupt handler, and currently I/O controller doesn't + * support multiple interrupts, so current CPU is unique actually. This + * avoids IPI sending from current CPU to the first CPU of a group. + */ if (ccpu == cpu || ccpu == group_cpu) { struct list_head *list; do_local: diff --git a/block/blk-throttle.c b/block/blk-throttle.c index f6a7941..a19f58c 100644 --- a/block/blk-throttle.c +++ b/block/blk-throttle.c @@ -746,7 +746,7 @@ static bool tg_may_dispatch(struct throtl_data *td, struct throtl_grp *tg, static void throtl_charge_bio(struct throtl_grp *tg, struct bio *bio) { bool rw = bio_data_dir(bio); - bool sync = bio->bi_rw & REQ_SYNC; + bool sync = rw_is_sync(bio->bi_rw); /* Charge the bio to the group */ tg->bytes_disp[rw] += bio->bi_size; @@ -1150,7 +1150,7 @@ int blk_throtl_bio(struct request_queue *q, struct bio **biop) if (tg_no_rule_group(tg, rw)) { blkiocg_update_dispatch_stats(&tg->blkg, bio->bi_size, - rw, bio->bi_rw & REQ_SYNC); + rw, rw_is_sync(bio->bi_rw)); rcu_read_unlock(); return 0; } diff --git a/block/blk.h b/block/blk.h index d658628..20b900a 100644 --- a/block/blk.h +++ b/block/blk.h @@ -17,6 +17,8 @@ int blk_rq_append_bio(struct request_queue *q, struct request *rq, struct bio *bio); void blk_dequeue_request(struct request *rq); void __blk_queue_free_tags(struct request_queue *q); +bool __blk_end_bidi_request(struct request *rq, int error, + unsigned int nr_bytes, unsigned int bidi_bytes); void blk_rq_timed_out_timer(unsigned long data); void blk_delete_timer(struct request *); diff --git a/block/bsg-lib.c b/block/bsg-lib.c new file mode 100644 index 0000000..6690e6e --- /dev/null +++ b/block/bsg-lib.c @@ -0,0 +1,298 @@ +/* + * BSG helper library + * + * Copyright (C) 2008 James Smart, Emulex Corporation + * Copyright (C) 2011 Red Hat, Inc. All rights reserved. + * Copyright (C) 2011 Mike Christie + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + * + */ +#include <linux/slab.h> +#include <linux/blkdev.h> +#include <linux/delay.h> +#include <linux/scatterlist.h> +#include <linux/bsg-lib.h> +#include <linux/module.h> +#include <scsi/scsi_cmnd.h> + +/** + * bsg_destroy_job - routine to teardown/delete a bsg job + * @job: bsg_job that is to be torn down + */ +static void bsg_destroy_job(struct bsg_job *job) +{ + put_device(job->dev); /* release reference for the request */ + + kfree(job->request_payload.sg_list); + kfree(job->reply_payload.sg_list); + kfree(job); +} + +/** + * bsg_job_done - completion routine for bsg requests + * @job: bsg_job that is complete + * @result: job reply result + * @reply_payload_rcv_len: length of payload recvd + * + * The LLD should call this when the bsg job has completed. + */ +void bsg_job_done(struct bsg_job *job, int result, + unsigned int reply_payload_rcv_len) +{ + struct request *req = job->req; + struct request *rsp = req->next_rq; + int err; + + err = job->req->errors = result; + if (err < 0) + /* we're only returning the result field in the reply */ + job->req->sense_len = sizeof(u32); + else + job->req->sense_len = job->reply_len; + /* we assume all request payload was transferred, residual == 0 */ + req->resid_len = 0; + + if (rsp) { + WARN_ON(reply_payload_rcv_len > rsp->resid_len); + + /* set reply (bidi) residual */ + rsp->resid_len -= min(reply_payload_rcv_len, rsp->resid_len); + } + blk_complete_request(req); +} +EXPORT_SYMBOL_GPL(bsg_job_done); + +/** + * bsg_softirq_done - softirq done routine for destroying the bsg requests + * @rq: BSG request that holds the job to be destroyed + */ +static void bsg_softirq_done(struct request *rq) +{ + struct bsg_job *job = rq->special; + + blk_end_request_all(rq, rq->errors); + bsg_destroy_job(job); +} + +static int bsg_map_buffer(struct bsg_buffer *buf, struct request *req) +{ + size_t sz = (sizeof(struct scatterlist) * req->nr_phys_segments); + + BUG_ON(!req->nr_phys_segments); + + buf->sg_list = kzalloc(sz, GFP_KERNEL); + if (!buf->sg_list) + return -ENOMEM; + sg_init_table(buf->sg_list, req->nr_phys_segments); + buf->sg_cnt = blk_rq_map_sg(req->q, req, buf->sg_list); + buf->payload_len = blk_rq_bytes(req); + return 0; +} + +/** + * bsg_create_job - create the bsg_job structure for the bsg request + * @dev: device that is being sent the bsg request + * @req: BSG request that needs a job structure + */ +static int bsg_create_job(struct device *dev, struct request *req) +{ + struct request *rsp = req->next_rq; + struct request_queue *q = req->q; + struct bsg_job *job; + int ret; + + BUG_ON(req->special); + + job = kzalloc(sizeof(struct bsg_job) + q->bsg_job_size, GFP_KERNEL); + if (!job) + return -ENOMEM; + + req->special = job; + job->req = req; + if (q->bsg_job_size) + job->dd_data = (void *)&job[1]; + job->request = req->cmd; + job->request_len = req->cmd_len; + job->reply = req->sense; + job->reply_len = SCSI_SENSE_BUFFERSIZE; /* Size of sense buffer + * allocated */ + if (req->bio) { + ret = bsg_map_buffer(&job->request_payload, req); + if (ret) + goto failjob_rls_job; + } + if (rsp && rsp->bio) { + ret = bsg_map_buffer(&job->reply_payload, rsp); + if (ret) + goto failjob_rls_rqst_payload; + } + job->dev = dev; + /* take a reference for the request */ + get_device(job->dev); + return 0; + +failjob_rls_rqst_payload: + kfree(job->request_payload.sg_list); +failjob_rls_job: + kfree(job); + return -ENOMEM; +} + +/* + * bsg_goose_queue - restart queue in case it was stopped + * @q: request q to be restarted + */ +void bsg_goose_queue(struct request_queue *q) +{ + if (!q) + return; + + blk_run_queue_async(q); +} +EXPORT_SYMBOL_GPL(bsg_goose_queue); + +/** + * bsg_request_fn - generic handler for bsg requests + * @q: request queue to manage + * + * On error the create_bsg_job function should return a -Exyz error value + * that will be set to the req->errors. + * + * Drivers/subsys should pass this to the queue init function. + */ +void bsg_request_fn(struct request_queue *q) +{ + struct device *dev = q->queuedata; + struct request *req; + struct bsg_job *job; + int ret; + + if (!get_device(dev)) + return; + + while (1) { + req = blk_fetch_request(q); + if (!req) + break; + spin_unlock_irq(q->queue_lock); + + ret = bsg_create_job(dev, req); + if (ret) { + req->errors = ret; + blk_end_request_all(req, ret); + spin_lock_irq(q->queue_lock); + continue; + } + + job = req->special; + ret = q->bsg_job_fn(job); + spin_lock_irq(q->queue_lock); + if (ret) + break; + } + + spin_unlock_irq(q->queue_lock); + put_device(dev); + spin_lock_irq(q->queue_lock); +} +EXPORT_SYMBOL_GPL(bsg_request_fn); + +/** + * bsg_setup_queue - Create and add the bsg hooks so we can receive requests + * @dev: device to attach bsg device to + * @q: request queue setup by caller + * @name: device to give bsg device + * @job_fn: bsg job handler + * @dd_job_size: size of LLD data needed for each job + * + * The caller should have setup the reuqest queue with bsg_request_fn + * as the request_fn. + */ +int bsg_setup_queue(struct device *dev, struct request_queue *q, + char *name, bsg_job_fn *job_fn, int dd_job_size) +{ + int ret; + + q->queuedata = dev; + q->bsg_job_size = dd_job_size; + q->bsg_job_fn = job_fn; + queue_flag_set_unlocked(QUEUE_FLAG_BIDI, q); + blk_queue_softirq_done(q, bsg_softirq_done); + blk_queue_rq_timeout(q, BLK_DEFAULT_SG_TIMEOUT); + + ret = bsg_register_queue(q, dev, name, NULL); + if (ret) { + printk(KERN_ERR "%s: bsg interface failed to " + "initialize - register queue\n", dev->kobj.name); + return ret; + } + + return 0; +} +EXPORT_SYMBOL_GPL(bsg_setup_queue); + +/** + * bsg_remove_queue - Deletes the bsg dev from the q + * @q: the request_queue that is to be torn down. + * + * Notes: + * Before unregistering the queue empty any requests that are blocked + */ +void bsg_remove_queue(struct request_queue *q) +{ + struct request *req; /* block request */ + int counts; /* totals for request_list count and starved */ + + if (!q) + return; + + /* Stop taking in new requests */ + spin_lock_irq(q->queue_lock); + blk_stop_queue(q); + + /* drain all requests in the queue */ + while (1) { + /* need the lock to fetch a request + * this may fetch the same reqeust as the previous pass + */ + req = blk_fetch_request(q); + /* save requests in use and starved */ + counts = q->rq.count[0] + q->rq.count[1] + + q->rq.starved[0] + q->rq.starved[1]; + spin_unlock_irq(q->queue_lock); + /* any requests still outstanding? */ + if (counts == 0) + break; + + /* This may be the same req as the previous iteration, + * always send the blk_end_request_all after a prefetch. + * It is not okay to not end the request because the + * prefetch started the request. + */ + if (req) { + /* return -ENXIO to indicate that this queue is + * going away + */ + req->errors = -ENXIO; + blk_end_request_all(req, -ENXIO); + } + + msleep(200); /* allow bsg to possibly finish */ + spin_lock_irq(q->queue_lock); + } + bsg_unregister_queue(q); +} +EXPORT_SYMBOL_GPL(bsg_remove_queue); diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c index 1f96ad6..a33bd43 100644 --- a/block/cfq-iosched.c +++ b/block/cfq-iosched.c @@ -130,6 +130,8 @@ struct cfq_queue { unsigned long slice_end; long slice_resid; + /* pending metadata requests */ + int meta_pending; /* number of requests that are on the dispatch list or inside driver */ int dispatched; @@ -682,6 +684,9 @@ cfq_choose_req(struct cfq_data *cfqd, struct request *rq1, struct request *rq2, if (rq_is_sync(rq1) != rq_is_sync(rq2)) return rq_is_sync(rq1) ? rq1 : rq2; + if ((rq1->cmd_flags ^ rq2->cmd_flags) & REQ_META) + return rq1->cmd_flags & REQ_META ? rq1 : rq2; + s1 = blk_rq_pos(rq1); s2 = blk_rq_pos(rq2); @@ -1209,6 +1214,9 @@ static void cfq_destroy_cfqg(struct cfq_data *cfqd, struct cfq_group *cfqg) hlist_del_init(&cfqg->cfqd_node); + BUG_ON(cfqd->nr_blkcg_linked_grps <= 0); + cfqd->nr_blkcg_linked_grps--; + /* * Put the reference taken at the time of creation so that when all * queues are gone, group can be destroyed. @@ -1604,6 +1612,10 @@ static void cfq_remove_request(struct request *rq) cfqq->cfqd->rq_queued--; cfq_blkiocg_update_io_remove_stats(&(RQ_CFQG(rq))->blkg, rq_data_dir(rq), rq_is_sync(rq)); + if (rq->cmd_flags & REQ_META) { + WARN_ON(!cfqq->meta_pending); + cfqq->meta_pending--; + } } static int cfq_merge(struct request_queue *q, struct request **req, @@ -3357,6 +3369,13 @@ cfq_should_preempt(struct cfq_data *cfqd, struct cfq_queue *new_cfqq, return true; /* + * So both queues are sync. Let the new request get disk time if + * it's a metadata request and the current queue is doing regular IO. + */ + if ((rq->cmd_flags & REQ_META) && !cfqq->meta_pending) + return true; + + /* * Allow an RT request to pre-empt an ongoing non-RT cfqq timeslice. */ if (cfq_class_rt(new_cfqq) && !cfq_class_rt(cfqq)) @@ -3420,6 +3439,8 @@ cfq_rq_enqueued(struct cfq_data *cfqd, struct cfq_queue *cfqq, struct cfq_io_context *cic = RQ_CIC(rq); cfqd->rq_queued++; + if (rq->cmd_flags & REQ_META) + cfqq->meta_pending++; cfq_update_io_thinktime(cfqd, cfqq, cic); cfq_update_io_seektime(cfqd, cfqq, rq); diff --git a/block/genhd.c b/block/genhd.c index 5cb51c5..e2f6790 100644 --- a/block/genhd.c +++ b/block/genhd.c @@ -1146,17 +1146,17 @@ static int diskstats_show(struct seq_file *seqf, void *v) cpu = part_stat_lock(); part_round_stats(cpu, hd); part_stat_unlock(); - seq_printf(seqf, "%4d %7d %s %lu %lu %llu " - "%u %lu %lu %llu %u %u %u %u\n", + seq_printf(seqf, "%4d %7d %s %lu %lu %lu " + "%u %lu %lu %lu %u %u %u %u\n", MAJOR(part_devt(hd)), MINOR(part_devt(hd)), disk_name(gp, hd->partno, buf), part_stat_read(hd, ios[READ]), part_stat_read(hd, merges[READ]), - (unsigned long long)part_stat_read(hd, sectors[READ]), + part_stat_read(hd, sectors[READ]), jiffies_to_msecs(part_stat_read(hd, ticks[READ])), part_stat_read(hd, ios[WRITE]), part_stat_read(hd, merges[WRITE]), - (unsigned long long)part_stat_read(hd, sectors[WRITE]), + part_stat_read(hd, sectors[WRITE]), jiffies_to_msecs(part_stat_read(hd, ticks[WRITE])), part_in_flight(hd), jiffies_to_msecs(part_stat_read(hd, io_ticks)), diff --git a/drivers/ata/Kconfig b/drivers/ata/Kconfig index ca3e6be..5987e0b 100644 --- a/drivers/ata/Kconfig +++ b/drivers/ata/Kconfig @@ -468,6 +468,15 @@ config PATA_ICSIDE interface card. This is not required for ICS partition support. If you are unsure, say N to this. +config PATA_IMX + tristate "PATA support for Freescale iMX" + depends on ARCH_MXC + help + This option enables support for the PATA host available on Freescale + iMX SoCs. + + If unsure, say N. + config PATA_IT8213 tristate "IT8213 PATA support (Experimental)" depends on PCI && EXPERIMENTAL diff --git a/drivers/ata/Makefile b/drivers/ata/Makefile index 8ac64e1..9550d69 100644 --- a/drivers/ata/Makefile +++ b/drivers/ata/Makefile @@ -48,6 +48,7 @@ obj-$(CONFIG_PATA_HPT37X) += pata_hpt37x.o obj-$(CONFIG_PATA_HPT3X2N) += pata_hpt3x2n.o obj-$(CONFIG_PATA_HPT3X3) += pata_hpt3x3.o obj-$(CONFIG_PATA_ICSIDE) += pata_icside.o +obj-$(CONFIG_PATA_IMX) += pata_imx.o obj-$(CONFIG_PATA_IT8213) += pata_it8213.o obj-$(CONFIG_PATA_IT821X) += pata_it821x.o obj-$(CONFIG_PATA_JMICRON) += pata_jmicron.o diff --git a/drivers/ata/pata_imx.c b/drivers/ata/pata_imx.c new file mode 100644 index 0000000..ca9d9ca --- /dev/null +++ b/drivers/ata/pata_imx.c @@ -0,0 +1,253 @@ +/* + * Freescale iMX PATA driver + * + * Copyright (C) 2011 Arnaud Patard <arnaud.patard@rtp-net.org> + * + * Based on pata_platform - Copyright (C) 2006 - 2007 Paul Mundt + * + * This file is subject to the terms and conditions of the GNU General Public + * License. See the file "COPYING" in the main directory of this archive + * for more details. + * + * TODO: + * - dmaengine support + * - check if timing stuff needed + */ +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/init.h> +#include <linux/blkdev.h> +#include <scsi/scsi_host.h> +#include <linux/ata.h> +#include <linux/libata.h> +#include <linux/platform_device.h> +#include <linux/clk.h> + +#define DRV_NAME "pata_imx" + +#define PATA_IMX_ATA_CONTROL 0x24 +#define PATA_IMX_ATA_CTRL_FIFO_RST_B (1<<7) +#define PATA_IMX_ATA_CTRL_ATA_RST_B (1<<6) +#define PATA_IMX_ATA_CTRL_IORDY_EN (1<<0) +#define PATA_IMX_ATA_INT_EN 0x2C +#define PATA_IMX_ATA_INTR_ATA_INTRQ2 (1<<3) +#define PATA_IMX_DRIVE_DATA 0xA0 +#define PATA_IMX_DRIVE_CONTROL 0xD8 + +struct pata_imx_priv { + struct clk *clk; + /* timings/interrupt/control regs */ + u8 *host_regs; + u32 ata_ctl; +}; + +static int pata_imx_set_mode(struct ata_link *link, struct ata_device **unused) +{ + struct ata_device *dev; + struct ata_port *ap = link->ap; + struct pata_imx_priv *priv = ap->host->private_data; + u32 val; + + ata_for_each_dev(dev, link, ENABLED) { + dev->pio_mode = dev->xfer_mode = XFER_PIO_0; + dev->xfer_shift = ATA_SHIFT_PIO; + dev->flags |= ATA_DFLAG_PIO; + + val = __raw_readl(priv->host_regs + PATA_IMX_ATA_CONTROL); + if (ata_pio_need_iordy(dev)) + val |= PATA_IMX_ATA_CTRL_IORDY_EN; + else + val &= ~PATA_IMX_ATA_CTRL_IORDY_EN; + __raw_writel(val, priv->host_regs + PATA_IMX_ATA_CONTROL); + + ata_dev_printk(dev, KERN_INFO, "configured for PIO\n"); + } + return 0; +} + +static struct scsi_host_template pata_imx_sht = { + ATA_PIO_SHT(DRV_NAME), +}; + +static struct ata_port_operations pata_imx_port_ops = { + .inherits = &ata_sff_port_ops, + .sff_data_xfer = ata_sff_data_xfer_noirq, + .cable_detect = ata_cable_unknown, + .set_mode = pata_imx_set_mode, +}; + +static void pata_imx_setup_port(struct ata_ioports *ioaddr) +{ + /* Fixup the port shift for platforms that need it */ + ioaddr->data_addr = ioaddr->cmd_addr + (ATA_REG_DATA << 2); + ioaddr->error_addr = ioaddr->cmd_addr + (ATA_REG_ERR << 2); + ioaddr->feature_addr = ioaddr->cmd_addr + (ATA_REG_FEATURE << 2); + ioaddr->nsect_addr = ioaddr->cmd_addr + (ATA_REG_NSECT << 2); + ioaddr->lbal_addr = ioaddr->cmd_addr + (ATA_REG_LBAL << 2); + ioaddr->lbam_addr = ioaddr->cmd_addr + (ATA_REG_LBAM << 2); + ioaddr->lbah_addr = ioaddr->cmd_addr + (ATA_REG_LBAH << 2); + ioaddr->device_addr = ioaddr->cmd_addr + (ATA_REG_DEVICE << 2); + ioaddr->status_addr = ioaddr->cmd_addr + (ATA_REG_STATUS << 2); + ioaddr->command_addr = ioaddr->cmd_addr + (ATA_REG_CMD << 2); +} + +static int __devinit pata_imx_probe(struct platform_device *pdev) +{ + struct ata_host *host; + struct ata_port *ap; + struct pata_imx_priv *priv; + int irq = 0; + struct resource *io_res; + + io_res = platform_get_resource(pdev, IORESOURCE_MEM, 0); + if (io_res == NULL) + return -EINVAL; + + irq = platform_get_irq(pdev, 0); + if (irq <= 0) + return -EINVAL; + + priv = devm_kzalloc(&pdev->dev, + sizeof(struct pata_imx_priv), GFP_KERNEL); + if (!priv) + return -ENOMEM; + + priv->clk = clk_get(&pdev->dev, NULL); + if (IS_ERR(priv->clk)) { + dev_err(&pdev->dev, "Failed to get clock\n"); + return PTR_ERR(priv->clk); + } + + clk_enable(priv->clk); + + host = ata_host_alloc(&pdev->dev, 1); + if (!host) + goto free_priv; + + host->private_data = priv; + ap = host->ports[0]; + + ap->ops = &pata_imx_port_ops; + ap->pio_mask = ATA_PIO0; + ap->flags |= ATA_FLAG_SLAVE_POSS; + + priv->host_regs = devm_ioremap(&pdev->dev, io_res->start, + resource_size(io_res)); + if (!priv->host_regs) { + dev_err(&pdev->dev, "failed to map IO/CTL base\n"); + goto free_priv; + } + + ap->ioaddr.cmd_addr = priv->host_regs + PATA_IMX_DRIVE_DATA; + ap->ioaddr.ctl_addr = priv->host_regs + PATA_IMX_DRIVE_CONTROL; + + ap->ioaddr.altstatus_addr = ap->ioaddr.ctl_addr; + + pata_imx_setup_port(&ap->ioaddr); + + ata_port_desc(ap, "cmd 0x%llx ctl 0x%llx", + (unsigned long long)io_res->start + PATA_IMX_DRIVE_DATA, + (unsigned long long)io_res->start + PATA_IMX_DRIVE_CONTROL); + + /* deassert resets */ + __raw_writel(PATA_IMX_ATA_CTRL_FIFO_RST_B | + PATA_IMX_ATA_CTRL_ATA_RST_B, + priv->host_regs + PATA_IMX_ATA_CONTROL); + /* enable interrupts */ + __raw_writel(PATA_IMX_ATA_INTR_ATA_INTRQ2, + priv->host_regs + PATA_IMX_ATA_INT_EN); + + /* activate */ + return ata_host_activate(host, irq, ata_sff_interrupt, 0, + &pata_imx_sht); + +free_priv: + clk_disable(priv->clk); + clk_put(priv->clk); + return -ENOMEM; +} + +static int __devexit pata_imx_remove(struct platform_device *pdev) +{ + struct ata_host *host = dev_get_drvdata(&pdev->dev); + struct pata_imx_priv *priv = host->private_data; + + ata_host_detach(host); + + __raw_writel(0, priv->host_regs + PATA_IMX_ATA_INT_EN); + + clk_disable(priv->clk); + clk_put(priv->clk); + + return 0; +} + +#ifdef CONFIG_PM +static int pata_imx_suspend(struct device *dev) +{ + struct ata_host *host = dev_get_drvdata(dev); + struct pata_imx_priv *priv = host->private_data; + int ret; + + ret = ata_host_suspend(host, PMSG_SUSPEND); + if (!ret) { + __raw_writel(0, priv->host_regs + PATA_IMX_ATA_INT_EN); + priv->ata_ctl = + __raw_readl(priv->host_regs + PATA_IMX_ATA_CONTROL); + clk_disable(priv->clk); + } + + return ret; +} + +static int pata_imx_resume(struct device *dev) +{ + struct ata_host *host = dev_get_drvdata(dev); + struct pata_imx_priv *priv = host->private_data; + + clk_enable(priv->clk); + + __raw_writel(priv->ata_ctl, priv->host_regs + PATA_IMX_ATA_CONTROL); + + __raw_writel(PATA_IMX_ATA_INTR_ATA_INTRQ2, + priv->host_regs + PATA_IMX_ATA_INT_EN); + + ata_host_resume(host); + + return 0; +} + +static const struct dev_pm_ops pata_imx_pm_ops = { + .suspend = pata_imx_suspend, + .resume = pata_imx_resume, +}; +#endif + +static struct platform_driver pata_imx_driver = { + .probe = pata_imx_probe, + .remove = __devexit_p(pata_imx_remove), + .driver = { + .name = DRV_NAME, + .owner = THIS_MODULE, +#ifdef CONFIG_PM + .pm = &pata_imx_pm_ops, +#endif + }, +}; + +static int __init pata_imx_init(void) +{ + return platform_driver_register(&pata_imx_driver); +} + +static void __exit pata_imx_exit(void) +{ + platform_driver_unregister(&pata_imx_driver); +} +module_init(pata_imx_init); +module_exit(pata_imx_exit); + +MODULE_AUTHOR("Arnaud Patard <arnaud.patard@rtp-net.org>"); +MODULE_DESCRIPTION("low-level driver for iMX PATA"); +MODULE_LICENSE("GPL"); +MODULE_ALIAS("platform:" DRV_NAME); diff --git a/drivers/ata/pata_via.c b/drivers/ata/pata_via.c index 65e4be6..8e9f504 100644 --- a/drivers/ata/pata_via.c +++ b/drivers/ata/pata_via.c @@ -124,6 +124,17 @@ static const struct via_isa_bridge { { NULL } }; +static const struct dmi_system_id no_atapi_dma_dmi_table[] = { + { + .ident = "AVERATEC 3200", + .matches = { + DMI_MATCH(DMI_BOARD_VENDOR, "AVERATEC"), + DMI_MATCH(DMI_BOARD_NAME, "3200"), + }, + }, + { } +}; + struct via_port { u8 cached_device; }; @@ -355,6 +366,13 @@ static unsigned long via_mode_filter(struct ata_device *dev, unsigned long mask) mask &= ~ ATA_MASK_UDMA; } } + + if (dev->class == ATA_DEV_ATAPI && + dmi_check_system(no_atapi_dma_dmi_table)) { + ata_dev_warn(dev, "controller locks up on ATAPI DMA, forcing PIO\n"); + mask &= ATA_MASK_PIO; + } + return mask; } diff --git a/drivers/ata/sata_dwc_460ex.c b/drivers/ata/sata_dwc_460ex.c index 0a9a774..5c42374 100644 --- a/drivers/ata/sata_dwc_460ex.c +++ b/drivers/ata/sata_dwc_460ex.c @@ -1329,7 +1329,7 @@ static int sata_dwc_port_start(struct ata_port *ap) dev_err(ap->dev, "%s: dma_alloc_coherent failed\n", __func__); err = -ENOMEM; - goto CLEANUP; + goto CLEANUP_ALLOC; } } @@ -1349,15 +1349,13 @@ static int sata_dwc_port_start(struct ata_port *ap) /* Clear any error bits before libata starts issuing commands */ clear_serror(); ap->private_data = hsdevp; + dev_dbg(ap->dev, "%s: done\n", __func__); + return 0; +CLEANUP_ALLOC: + kfree(hsdevp); CLEANUP: - if (err) { - sata_dwc_port_stop(ap); - dev_dbg(ap->dev, "%s: fail\n", __func__); - } else { - dev_dbg(ap->dev, "%s: done\n", __func__); - } - + dev_dbg(ap->dev, "%s: fail. ap->id = %d\n", __func__, ap->print_id); return err; } diff --git a/drivers/ata/sata_sil.c b/drivers/ata/sata_sil.c index 98c1d78..9dfb40b 100644 --- a/drivers/ata/sata_sil.c +++ b/drivers/ata/sata_sil.c @@ -438,7 +438,7 @@ static void sil_host_intr(struct ata_port *ap, u32 bmdma2) u8 status; if (unlikely(bmdma2 & SIL_DMA_SATA_IRQ)) { - u32 serror; + u32 serror = 0xffffffff; /* SIEN doesn't mask SATA IRQs on some 3112s. Those * controllers continue to assert IRQ as long as diff --git a/drivers/base/power/domain.c b/drivers/base/power/domain.c index e18566a..1c37457 100644 --- a/drivers/base/power/domain.c +++ b/drivers/base/power/domain.c @@ -460,6 +460,21 @@ static int pm_genpd_runtime_resume(struct device *dev) return 0; } +/** + * pm_genpd_poweroff_unused - Power off all PM domains with no devices in use. + */ +void pm_genpd_poweroff_unused(void) +{ + struct generic_pm_domain *genpd; + + mutex_lock(&gpd_list_lock); + + list_for_each_entry(genpd, &gpd_list, gpd_list_node) + genpd_queue_power_off_work(genpd); + + mutex_unlock(&gpd_list_lock); +} + #else static inline void genpd_power_off_work_fn(struct work_struct *work) {} @@ -1255,18 +1270,3 @@ void pm_genpd_init(struct generic_pm_domain *genpd, list_add(&genpd->gpd_list_node, &gpd_list); mutex_unlock(&gpd_list_lock); } - -/** - * pm_genpd_poweroff_unused - Power off all PM domains with no devices in use. - */ -void pm_genpd_poweroff_unused(void) -{ - struct generic_pm_domain *genpd; - - mutex_lock(&gpd_list_lock); - - list_for_each_entry(genpd, &gpd_list, gpd_list_node) - genpd_queue_power_off_work(genpd); - - mutex_unlock(&gpd_list_lock); -} diff --git a/drivers/block/Kconfig b/drivers/block/Kconfig index 717d6e4..6f07ec1 100644 --- a/drivers/block/Kconfig +++ b/drivers/block/Kconfig @@ -256,6 +256,21 @@ config BLK_DEV_LOOP Most users will answer N here. +config BLK_DEV_LOOP_MIN_COUNT + int "Number of loop devices to pre-create at init time" + depends on BLK_DEV_LOOP + default 8 + help + Static number of loop devices to be unconditionally pre-created + at init time. + + This default value can be overwritten on the kernel command + line or with module-parameter loop.max_loop. + + The historic default is 8. If a late 2011 version of losetup(8) + is used, it can be set to 0, since needed loop devices can be + dynamically allocated with the /dev/loop-control interface. + config BLK_DEV_CRYPTOLOOP tristate "Cryptoloop Support" select CRYPTO @@ -471,7 +486,7 @@ config XEN_BLKDEV_FRONTEND in another domain which drives the actual block device. config XEN_BLKDEV_BACKEND - tristate "Block-device backend driver" + tristate "Xen block-device backend driver" depends on XEN_BACKEND help The block-device backend driver allows the kernel to export its diff --git a/drivers/block/drbd/drbd_nl.c b/drivers/block/drbd/drbd_nl.c index 515bcd9..0feab26 100644 --- a/drivers/block/drbd/drbd_nl.c +++ b/drivers/block/drbd/drbd_nl.c @@ -1829,10 +1829,10 @@ static int drbd_nl_syncer_conf(struct drbd_conf *mdev, struct drbd_nl_cfg_req *n /* silently ignore cpu mask on UP kernel */ if (nr_cpu_ids > 1 && sc.cpu_mask[0] != 0) { - err = __bitmap_parse(sc.cpu_mask, 32, 0, + err = bitmap_parse(sc.cpu_mask, 32, cpumask_bits(new_cpu_mask), nr_cpu_ids); if (err) { - dev_warn(DEV, "__bitmap_parse() failed with %d\n", err); + dev_warn(DEV, "bitmap_parse() failed with %d\n", err); retcode = ERR_CPU_MASK_PARSE; goto fail; } diff --git a/drivers/block/loop.c b/drivers/block/loop.c index 76c8da7..4720c7a 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -75,11 +75,11 @@ #include <linux/kthread.h> #include <linux/splice.h> #include <linux/sysfs.h> - +#include <linux/miscdevice.h> #include <asm/uaccess.h> -static LIST_HEAD(loop_devices); -static DEFINE_MUTEX(loop_devices_mutex); +static DEFINE_IDR(loop_index_idr); +static DEFINE_MUTEX(loop_index_mutex); static int max_part; static int part_shift; @@ -722,17 +722,10 @@ static inline int is_loop_device(struct file *file) static ssize_t loop_attr_show(struct device *dev, char *page, ssize_t (*callback)(struct loop_device *, char *)) { - struct loop_device *l, *lo = NULL; - - mutex_lock(&loop_devices_mutex); - list_for_each_entry(l, &loop_devices, lo_list) - if (disk_to_dev(l->lo_disk) == dev) { - lo = l; - break; - } - mutex_unlock(&loop_devices_mutex); + struct gendisk *disk = dev_to_disk(dev); + struct loop_device *lo = disk->private_data; - return lo ? callback(lo, page) : -EIO; + return callback(lo, page); } #define LOOP_ATTR_RO(_name) \ @@ -750,10 +743,10 @@ static ssize_t loop_attr_backing_file_show(struct loop_device *lo, char *buf) ssize_t ret; char *p = NULL; - mutex_lock(&lo->lo_ctl_mutex); + spin_lock_irq(&lo->lo_lock); if (lo->lo_backing_file) p = d_path(&lo->lo_backing_file->f_path, buf, PAGE_SIZE - 1); - mutex_unlock(&lo->lo_ctl_mutex); + spin_unlock_irq(&lo->lo_lock); if (IS_ERR_OR_NULL(p)) ret = PTR_ERR(p); @@ -1007,7 +1000,9 @@ static int loop_clr_fd(struct loop_device *lo, struct block_device *bdev) kthread_stop(lo->lo_thread); + spin_lock_irq(&lo->lo_lock); lo->lo_backing_file = NULL; + spin_unlock_irq(&lo->lo_lock); loop_release_xfer(lo); lo->transfer = NULL; @@ -1485,13 +1480,22 @@ static int lo_compat_ioctl(struct block_device *bdev, fmode_t mode, static int lo_open(struct block_device *bdev, fmode_t mode) { - struct loop_device *lo = bdev->bd_disk->private_data; + struct loop_device *lo; + int err = 0; + + mutex_lock(&loop_index_mutex); + lo = bdev->bd_disk->private_data; + if (!lo) { + err = -ENXIO; + goto out; + } mutex_lock(&lo->lo_ctl_mutex); lo->lo_refcnt++; mutex_unlock(&lo->lo_ctl_mutex); - - return 0; +out: + mutex_unlock(&loop_index_mutex); + return err; } static int lo_release(struct gendisk *disk, fmode_t mode) @@ -1557,40 +1561,71 @@ int loop_register_transfer(struct loop_func_table *funcs) return 0; } +static int unregister_transfer_cb(int id, void *ptr, void *data) +{ + struct loop_device *lo = ptr; + struct loop_func_table *xfer = data; + + mutex_lock(&lo->lo_ctl_mutex); + if (lo->lo_encryption == xfer) + loop_release_xfer(lo); + mutex_unlock(&lo->lo_ctl_mutex); + return 0; +} + int loop_unregister_transfer(int number) { unsigned int n = number; - struct loop_device *lo; struct loop_func_table *xfer; if (n == 0 || n >= MAX_LO_CRYPT || (xfer = xfer_funcs[n]) == NULL) return -EINVAL; xfer_funcs[n] = NULL; - - list_for_each_entry(lo, &loop_devices, lo_list) { - mutex_lock(&lo->lo_ctl_mutex); - - if (lo->lo_encryption == xfer) - loop_release_xfer(lo); - - mutex_unlock(&lo->lo_ctl_mutex); - } - + idr_for_each(&loop_index_idr, &unregister_transfer_cb, xfer); return 0; } EXPORT_SYMBOL(loop_register_transfer); EXPORT_SYMBOL(loop_unregister_transfer); -static struct loop_device *loop_alloc(int i) +static int loop_add(struct loop_device **l, int i) { struct loop_device *lo; struct gendisk *disk; + int err; lo = kzalloc(sizeof(*lo), GFP_KERNEL); - if (!lo) + if (!lo) { + err = -ENOMEM; goto out; + } + + err = idr_pre_get(&loop_index_idr, GFP_KERNEL); + if (err < 0) + goto out_free_dev; + + if (i >= 0) { + int m; + + /* create specific i in the index */ + err = idr_get_new_above(&loop_index_idr, lo, i, &m); + if (err >= 0 && i != m) { + idr_remove(&loop_index_idr, m); + err = -EEXIST; + } + } else if (i == -1) { + int m; + + /* get next free nr */ + err = idr_get_new(&loop_index_idr, lo, &m); + if (err >= 0) + i = m; + } else { + err = -EINVAL; + } + if (err < 0) + goto out_free_dev; lo->lo_queue = blk_alloc_queue(GFP_KERNEL); if (!lo->lo_queue) @@ -1611,81 +1646,158 @@ static struct loop_device *loop_alloc(int i) disk->private_data = lo; disk->queue = lo->lo_queue; sprintf(disk->disk_name, "loop%d", i); - return lo; + add_disk(disk); + *l = lo; + return lo->lo_number; out_free_queue: blk_cleanup_queue(lo->lo_queue); out_free_dev: kfree(lo); out: - return NULL; + return err; } -static void loop_free(struct loop_device *lo) +static void loop_remove(struct loop_device *lo) { + del_gendisk(lo->lo_disk); blk_cleanup_queue(lo->lo_queue); put_disk(lo->lo_disk); - list_del(&lo->lo_list); kfree(lo); } -static struct loop_device *loop_init_one(int i) +static int find_free_cb(int id, void *ptr, void *data) +{ + struct loop_device *lo = ptr; + struct loop_device **l = data; + + if (lo->lo_state == Lo_unbound) { + *l = lo; + return 1; + } + return 0; +} + +static int loop_lookup(struct loop_device **l, int i) { struct loop_device *lo; + int ret = -ENODEV; - list_for_each_entry(lo, &loop_devices, lo_list) { - if (lo->lo_number == i) - return lo; + if (i < 0) { + int err; + + err = idr_for_each(&loop_index_idr, &find_free_cb, &lo); + if (err == 1) { + *l = lo; + ret = lo->lo_number; + } + goto out; } - lo = loop_alloc(i); + /* lookup and return a specific i */ + lo = idr_find(&loop_index_idr, i); if (lo) { - add_disk(lo->lo_disk); - list_add_tail(&lo->lo_list, &loop_devices); + *l = lo; + ret = lo->lo_number; } - return lo; -} - -static void loop_del_one(struct loop_device *lo) -{ - del_gendisk(lo->lo_disk); - loop_free(lo); +out: + return ret; } static struct kobject *loop_probe(dev_t dev, int *part, void *data) { struct loop_device *lo; struct kobject *kobj; + int err; - mutex_lock(&loop_devices_mutex); - lo = loop_init_one(MINOR(dev) >> part_shift); - kobj = lo ? get_disk(lo->lo_disk) : ERR_PTR(-ENOMEM); - mutex_unlock(&loop_devices_mutex); + mutex_lock(&loop_index_mutex); + err = loop_lookup(&lo, MINOR(dev) >> part_shift); + if (err < 0) + err = loop_add(&lo, MINOR(dev) >> part_shift); + if (err < 0) + kobj = ERR_PTR(err); + else + kobj = get_disk(lo->lo_disk); + mutex_unlock(&loop_index_mutex); *part = 0; return kobj; } +static long loop_control_ioctl(struct file *file, unsigned int cmd, + unsigned long parm) +{ + struct loop_device *lo; + int ret = -ENOSYS; + + mutex_lock(&loop_index_mutex); + switch (cmd) { + case LOOP_CTL_ADD: + ret = loop_lookup(&lo, parm); + if (ret >= 0) { + ret = -EEXIST; + break; + } + ret = loop_add(&lo, parm); + break; + case LOOP_CTL_REMOVE: + ret = loop_lookup(&lo, parm); + if (ret < 0) + break; + mutex_lock(&lo->lo_ctl_mutex); + if (lo->lo_state != Lo_unbound) { + ret = -EBUSY; + mutex_unlock(&lo->lo_ctl_mutex); + break; + } + if (lo->lo_refcnt > 0) { + ret = -EBUSY; + mutex_unlock(&lo->lo_ctl_mutex); + break; + } + lo->lo_disk->private_data = NULL; + mutex_unlock(&lo->lo_ctl_mutex); + idr_remove(&loop_index_idr, lo->lo_number); + loop_remove(lo); + break; + case LOOP_CTL_GET_FREE: + ret = loop_lookup(&lo, -1); + if (ret >= 0) + break; + ret = loop_add(&lo, -1); + } + mutex_unlock(&loop_index_mutex); + + return ret; +} + +static const struct file_operations loop_ctl_fops = { + .open = nonseekable_open, + .unlocked_ioctl = loop_control_ioctl, + .compat_ioctl = loop_control_ioctl, + .owner = THIS_MODULE, + .llseek = noop_llseek, +}; + +static struct miscdevice loop_misc = { + .minor = LOOP_CTRL_MINOR, + .name = "loop-control", + .fops = &loop_ctl_fops, +}; + +MODULE_ALIAS_MISCDEV(LOOP_CTRL_MINOR); +MODULE_ALIAS("devname:loop-control"); + static int __init loop_init(void) { int i, nr; unsigned long range; - struct loop_device *lo, *next; + struct loop_device *lo; + int err; - /* - * loop module now has a feature to instantiate underlying device - * structure on-demand, provided that there is an access dev node. - * However, this will not work well with user space tool that doesn't - * know about such "feature". In order to not break any existing - * tool, we do the following: - * - * (1) if max_loop is specified, create that many upfront, and this - * also becomes a hard limit. - * (2) if max_loop is not specified, create 8 loop device on module - * load, user can further extend loop device by create dev node - * themselves and have kernel automatically instantiate actual - * device on-demand. - */ + err = misc_register(&loop_misc); + if (err < 0) + return err; part_shift = 0; if (max_part > 0) { @@ -1708,57 +1820,60 @@ static int __init loop_init(void) if (max_loop > 1UL << (MINORBITS - part_shift)) return -EINVAL; + /* + * If max_loop is specified, create that many devices upfront. + * This also becomes a hard limit. If max_loop is not specified, + * create CONFIG_BLK_DEV_LOOP_MIN_COUNT loop devices at module + * init time. Loop devices can be requested on-demand with the + * /dev/loop-control interface, or be instantiated by accessing + * a 'dead' device node. + */ if (max_loop) { nr = max_loop; range = max_loop << part_shift; } else { - nr = 8; + nr = CONFIG_BLK_DEV_LOOP_MIN_COUNT; range = 1UL << MINORBITS; } if (register_blkdev(LOOP_MAJOR, "loop")) return -EIO; - for (i = 0; i < nr; i++) { - lo = loop_alloc(i); - if (!lo) - goto Enomem; - list_add_tail(&lo->lo_list, &loop_devices); - } - - /* point of no return */ - - list_for_each_entry(lo, &loop_devices, lo_list) - add_disk(lo->lo_disk); - blk_register_region(MKDEV(LOOP_MAJOR, 0), range, THIS_MODULE, loop_probe, NULL, NULL); + /* pre-create number of devices given by config or max_loop */ + mutex_lock(&loop_index_mutex); + for (i = 0; i < nr; i++) + loop_add(&lo, i); + mutex_unlock(&loop_index_mutex); + printk(KERN_INFO "loop: module loaded\n"); return 0; +} -Enomem: - printk(KERN_INFO "loop: out of memory\n"); - - list_for_each_entry_safe(lo, next, &loop_devices, lo_list) - loop_free(lo); +static int loop_exit_cb(int id, void *ptr, void *data) +{ + struct loop_device *lo = ptr; - unregister_blkdev(LOOP_MAJOR, "loop"); - return -ENOMEM; + loop_remove(lo); + return 0; } static void __exit loop_exit(void) { unsigned long range; - struct loop_device *lo, *next; range = max_loop ? max_loop << part_shift : 1UL << MINORBITS; - list_for_each_entry_safe(lo, next, &loop_devices, lo_list) - loop_del_one(lo); + idr_for_each(&loop_index_idr, &loop_exit_cb, NULL); + idr_remove_all(&loop_index_idr); + idr_destroy(&loop_index_idr); blk_unregister_region(MKDEV(LOOP_MAJOR, 0), range); unregister_blkdev(LOOP_MAJOR, "loop"); + + misc_deregister(&loop_misc); } module_init(loop_init); diff --git a/drivers/block/swim3.c b/drivers/block/swim3.c index 773bfa7..ae3e167 100644 --- a/drivers/block/swim3.c +++ b/drivers/block/swim3.c @@ -1184,6 +1184,7 @@ static struct of_device_id swim3_match[] = { .compatible = "swim3" }, + { /* end of list */ } }; static struct macio_driver swim3_driver = diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c index b536a9c..9ea8c25 100644 --- a/drivers/block/xen-blkfront.c +++ b/drivers/block/xen-blkfront.c @@ -123,8 +123,8 @@ static DEFINE_SPINLOCK(minor_lock); #define BLKIF_MINOR_EXT(dev) ((dev)&(~EXTENDED)) #define EMULATED_HD_DISK_MINOR_OFFSET (0) #define EMULATED_HD_DISK_NAME_OFFSET (EMULATED_HD_DISK_MINOR_OFFSET / 256) -#define EMULATED_SD_DISK_MINOR_OFFSET (EMULATED_HD_DISK_MINOR_OFFSET + (4 * 16)) -#define EMULATED_SD_DISK_NAME_OFFSET (EMULATED_HD_DISK_NAME_OFFSET + 4) +#define EMULATED_SD_DISK_MINOR_OFFSET (0) +#define EMULATED_SD_DISK_NAME_OFFSET (EMULATED_SD_DISK_MINOR_OFFSET / 256) #define DEV_NAME "xvd" /* name in /dev */ @@ -529,7 +529,7 @@ static int xlvbd_alloc_gendisk(blkif_sector_t capacity, minor = BLKIF_MINOR_EXT(info->vdevice); nr_parts = PARTS_PER_EXT_DISK; offset = minor / nr_parts; - if (xen_hvm_domain() && offset <= EMULATED_HD_DISK_NAME_OFFSET + 4) + if (xen_hvm_domain() && offset < EMULATED_HD_DISK_NAME_OFFSET + 4) printk(KERN_WARNING "blkfront: vdevice 0x%x might conflict with " "emulated IDE disks,\n\t choose an xvd device name" "from xvde on\n", info->vdevice); diff --git a/drivers/cdrom/cdrom.c b/drivers/cdrom/cdrom.c index 75fb965..f997c27 100644 --- a/drivers/cdrom/cdrom.c +++ b/drivers/cdrom/cdrom.c @@ -1929,11 +1929,17 @@ static int dvd_read_manufact(struct cdrom_device_info *cdi, dvd_struct *s, goto out; s->manufact.len = buf[0] << 8 | buf[1]; - if (s->manufact.len < 0 || s->manufact.len > 2048) { + if (s->manufact.len < 0) { cdinfo(CD_WARNING, "Received invalid manufacture info length" " (%d)\n", s->manufact.len); ret = -EIO; } else { + if (s->manufact.len > 2048) { + cdinfo(CD_WARNING, "Received invalid manufacture info " + "length (%d): truncating to 2048\n", + s->manufact.len); + s->manufact.len = 2048; + } memcpy(s->manufact.value, &buf[4], s->manufact.len); } diff --git a/drivers/edac/i7core_edac.c b/drivers/edac/i7core_edac.c index 04f1e7c..f6cf448 100644 --- a/drivers/edac/i7core_edac.c +++ b/drivers/edac/i7core_edac.c @@ -1670,7 +1670,7 @@ static void i7core_mce_output_error(struct mem_ctl_info *mci, char *type, *optype, *err, *msg; unsigned long error = m->status & 0x1ff0000l; u32 optypenum = (m->status >> 4) & 0x07; - u32 core_err_cnt = (m->status >> 38) && 0x7fff; + u32 core_err_cnt = (m->status >> 38) & 0x7fff; u32 dimm = (m->misc >> 16) & 0x3; u32 channel = (m->misc >> 18) & 0x3; u32 syndrome = m->misc >> 32; diff --git a/drivers/firewire/core-device.c b/drivers/firewire/core-device.c index 8ba7f79..f3b890d 100644 --- a/drivers/firewire/core-device.c +++ b/drivers/firewire/core-device.c @@ -455,15 +455,20 @@ static struct device_attribute fw_device_attributes[] = { static int read_rom(struct fw_device *device, int generation, int index, u32 *data) { - int rcode; + u64 offset = (CSR_REGISTER_BASE | CSR_CONFIG_ROM) + index * 4; + int i, rcode; /* device->node_id, accessed below, must not be older than generation */ smp_rmb(); - rcode = fw_run_transaction(device->card, TCODE_READ_QUADLET_REQUEST, - device->node_id, generation, device->max_speed, - (CSR_REGISTER_BASE | CSR_CONFIG_ROM) + index * 4, - data, 4); + for (i = 10; i < 100; i += 10) { + rcode = fw_run_transaction(device->card, + TCODE_READ_QUADLET_REQUEST, device->node_id, + generation, device->max_speed, offset, data, 4); + if (rcode != RCODE_BUSY) + break; + msleep(i); + } be32_to_cpus(data); return rcode; diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h index 5baaef4..542453f 100644 --- a/drivers/gpu/drm/i915/i915_reg.h +++ b/drivers/gpu/drm/i915/i915_reg.h @@ -375,6 +375,7 @@ # define MI_FLUSH_ENABLE (1 << 11) #define GFX_MODE 0x02520 +#define GFX_MODE_GEN7 0x0229c #define GFX_RUN_LIST_ENABLE (1<<15) #define GFX_TLB_INVALIDATE_ALWAYS (1<<13) #define GFX_SURFACE_FAULT_ENABLE (1<<12) @@ -382,6 +383,9 @@ #define GFX_PSMI_GRANULARITY (1<<10) #define GFX_PPGTT_ENABLE (1<<9) +#define GFX_MODE_ENABLE(bit) (((bit) << 16) | (bit)) +#define GFX_MODE_DISABLE(bit) (((bit) << 16) | (0)) + #define SCPD0 0x0209c /* 915+ only */ #define IER 0x020a0 #define IIR 0x020a4 diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c index 47b9b27..c30626e 100644 --- a/drivers/gpu/drm/i915/intel_ringbuffer.c +++ b/drivers/gpu/drm/i915/intel_ringbuffer.c @@ -290,6 +290,10 @@ static int init_render_ring(struct intel_ring_buffer *ring) if (IS_GEN6(dev) || IS_GEN7(dev)) mode |= MI_FLUSH_ENABLE << 16 | MI_FLUSH_ENABLE; I915_WRITE(MI_MODE, mode); + if (IS_GEN7(dev)) + I915_WRITE(GFX_MODE_GEN7, + GFX_MODE_DISABLE(GFX_TLB_INVALIDATE_ALWAYS) | + GFX_MODE_ENABLE(GFX_REPLAY_MODE)); } if (INTEL_INFO(dev)->gen >= 6) { diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c b/drivers/infiniband/ulp/ipoib/ipoib_main.c index 43f89ba..fe89c46 100644 --- a/drivers/infiniband/ulp/ipoib/ipoib_main.c +++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c @@ -717,11 +717,13 @@ static int ipoib_start_xmit(struct sk_buff *skb, struct net_device *dev) { struct ipoib_dev_priv *priv = netdev_priv(dev); struct ipoib_neigh *neigh; - struct neighbour *n; + struct neighbour *n = NULL; unsigned long flags; - n = dst_get_neighbour(skb_dst(skb)); - if (likely(skb_dst(skb) && n)) { + if (likely(skb_dst(skb))) + n = dst_get_neighbour(skb_dst(skb)); + + if (likely(n)) { if (unlikely(!*to_ipoib_neigh(n))) { ipoib_path_lookup(skb, dev); return NETDEV_TX_OK; diff --git a/drivers/infiniband/ulp/iser/iscsi_iser.c b/drivers/infiniband/ulp/iser/iscsi_iser.c index 8db008d..9c61b9c 100644 --- a/drivers/infiniband/ulp/iser/iscsi_iser.c +++ b/drivers/infiniband/ulp/iser/iscsi_iser.c @@ -101,13 +101,17 @@ iscsi_iser_recv(struct iscsi_conn *conn, /* verify PDU length */ datalen = ntoh24(hdr->dlength); - if (datalen != rx_data_len) { - printk(KERN_ERR "iscsi_iser: datalen %d (hdr) != %d (IB) \n", - datalen, rx_data_len); + if (datalen > rx_data_len || (datalen + 4) < rx_data_len) { + iser_err("wrong datalen %d (hdr), %d (IB)\n", + datalen, rx_data_len); rc = ISCSI_ERR_DATALEN; goto error; } + if (datalen != rx_data_len) + iser_dbg("aligned datalen (%d) hdr, %d (IB)\n", + datalen, rx_data_len); + /* read AHS */ ahslen = hdr->hlength * 4; diff --git a/drivers/infiniband/ulp/iser/iscsi_iser.h b/drivers/infiniband/ulp/iser/iscsi_iser.h index 342cbc1..db6f3ce 100644 --- a/drivers/infiniband/ulp/iser/iscsi_iser.h +++ b/drivers/infiniband/ulp/iser/iscsi_iser.h @@ -89,7 +89,7 @@ } while (0) #define SHIFT_4K 12 -#define SIZE_4K (1UL << SHIFT_4K) +#define SIZE_4K (1ULL << SHIFT_4K) #define MASK_4K (~(SIZE_4K-1)) /* support up to 512KB in one RDMA */ diff --git a/drivers/infiniband/ulp/iser/iser_initiator.c b/drivers/infiniband/ulp/iser/iser_initiator.c index 5745b7f..f299de6 100644 --- a/drivers/infiniband/ulp/iser/iser_initiator.c +++ b/drivers/infiniband/ulp/iser/iser_initiator.c @@ -412,7 +412,7 @@ int iser_send_control(struct iscsi_conn *conn, memcpy(iser_conn->ib_conn->login_buf, task->data, task->data_count); tx_dsg->addr = iser_conn->ib_conn->login_dma; - tx_dsg->length = data_seg_len; + tx_dsg->length = task->data_count; tx_dsg->lkey = device->mr->lkey; mdesc->num_sge = 2; } diff --git a/drivers/pci/hotplug/pcihp_slot.c b/drivers/pci/hotplug/pcihp_slot.c index 749fdf0..753b21a 100644 --- a/drivers/pci/hotplug/pcihp_slot.c +++ b/drivers/pci/hotplug/pcihp_slot.c @@ -158,47 +158,6 @@ static void program_hpp_type2(struct pci_dev *dev, struct hpp_type2 *hpp) */ } -/* Program PCIE MaxPayload setting on device: ensure parent maxpayload <= device */ -static int pci_set_payload(struct pci_dev *dev) -{ - int pos, ppos; - u16 pctl, psz; - u16 dctl, dsz, dcap, dmax; - struct pci_dev *parent; - - parent = dev->bus->self; - pos = pci_find_capability(dev, PCI_CAP_ID_EXP); - if (!pos) - return 0; - - /* Read Device MaxPayload capability and setting */ - pci_read_config_word(dev, pos + PCI_EXP_DEVCTL, &dctl); - pci_read_config_word(dev, pos + PCI_EXP_DEVCAP, &dcap); - dsz = (dctl & PCI_EXP_DEVCTL_PAYLOAD) >> 5; - dmax = (dcap & PCI_EXP_DEVCAP_PAYLOAD); - - /* Read Parent MaxPayload setting */ - ppos = pci_find_capability(parent, PCI_CAP_ID_EXP); - if (!ppos) - return 0; - pci_read_config_word(parent, ppos + PCI_EXP_DEVCTL, &pctl); - psz = (pctl & PCI_EXP_DEVCTL_PAYLOAD) >> 5; - - /* If parent payload > device max payload -> error - * If parent payload > device payload -> set speed - * If parent payload <= device payload -> do nothing - */ - if (psz > dmax) - return -1; - else if (psz > dsz) { - dev_info(&dev->dev, "Setting MaxPayload to %d\n", 128 << psz); - pci_write_config_word(dev, pos + PCI_EXP_DEVCTL, - (dctl & ~PCI_EXP_DEVCTL_PAYLOAD) + - (psz << 5)); - } - return 0; -} - void pci_configure_slot(struct pci_dev *dev) { struct pci_dev *cdev; @@ -210,9 +169,7 @@ void pci_configure_slot(struct pci_dev *dev) (dev->class >> 8) == PCI_CLASS_BRIDGE_PCI))) return; - ret = pci_set_payload(dev); - if (ret) - dev_warn(&dev->dev, "could not set device max payload\n"); + pcie_bus_configure_settings(dev->bus, dev->bus->self->pcie_mpss); memset(&hpp, 0, sizeof(hpp)); ret = pci_get_hp_params(dev, &hpp); diff --git a/drivers/pci/of.c b/drivers/pci/of.c index c94d37e..f092993 100644 --- a/drivers/pci/of.c +++ b/drivers/pci/of.c @@ -55,7 +55,7 @@ struct device_node * __weak pcibios_get_phb_of_node(struct pci_bus *bus) */ if (bus->bridge->of_node) return of_node_get(bus->bridge->of_node); - if (bus->bridge->parent->of_node) + if (bus->bridge->parent && bus->bridge->parent->of_node) return of_node_get(bus->bridge->parent->of_node); return NULL; } diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index 08a95b3..0ce6742 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -77,6 +77,8 @@ unsigned long pci_cardbus_mem_size = DEFAULT_CARDBUS_MEM_SIZE; unsigned long pci_hotplug_io_size = DEFAULT_HOTPLUG_IO_SIZE; unsigned long pci_hotplug_mem_size = DEFAULT_HOTPLUG_MEM_SIZE; +enum pcie_bus_config_types pcie_bus_config = PCIE_BUS_PERFORMANCE; + /* * The default CLS is used if arch didn't set CLS explicitly and not * all pci devices agree on the same value. Arch can override either @@ -3223,6 +3225,67 @@ out: EXPORT_SYMBOL(pcie_set_readrq); /** + * pcie_get_mps - get PCI Express maximum payload size + * @dev: PCI device to query + * + * Returns maximum payload size in bytes + * or appropriate error value. + */ +int pcie_get_mps(struct pci_dev *dev) +{ + int ret, cap; + u16 ctl; + + cap = pci_pcie_cap(dev); + if (!cap) + return -EINVAL; + + ret = pci_read_config_word(dev, cap + PCI_EXP_DEVCTL, &ctl); + if (!ret) + ret = 128 << ((ctl & PCI_EXP_DEVCTL_PAYLOAD) >> 5); + + return ret; +} + +/** + * pcie_set_mps - set PCI Express maximum payload size + * @dev: PCI device to query + * @mps: maximum payload size in bytes + * valid values are 128, 256, 512, 1024, 2048, 4096 + * + * If possible sets maximum payload size + */ +int pcie_set_mps(struct pci_dev *dev, int mps) +{ + int cap, err = -EINVAL; + u16 ctl, v; + + if (mps < 128 || mps > 4096 || !is_power_of_2(mps)) + goto out; + + v = ffs(mps) - 8; + if (v > dev->pcie_mpss) + goto out; + v <<= 5; + + cap = pci_pcie_cap(dev); + if (!cap) + goto out; + + err = pci_read_config_word(dev, cap + PCI_EXP_DEVCTL, &ctl); + if (err) + goto out; + + if ((ctl & PCI_EXP_DEVCTL_PAYLOAD) != v) { + ctl &= ~PCI_EXP_DEVCTL_PAYLOAD; + ctl |= v; + err = pci_write_config_word(dev, cap + PCI_EXP_DEVCTL, ctl); + } +out: + return err; +} + +/** * pci_select_bars - Make BAR mask from the type of resource * @dev: the PCI device for which BAR mask is made * @flags: resource type mask to be selected @@ -3505,6 +3568,10 @@ static int __init pci_setup(char *str) pci_hotplug_io_size = memparse(str + 9, &str); } else if (!strncmp(str, "hpmemsize=", 10)) { pci_hotplug_mem_size = memparse(str + 10, &str); + } else if (!strncmp(str, "pcie_bus_safe", 13)) { + pcie_bus_config = PCIE_BUS_SAFE; + } else if (!strncmp(str, "pcie_bus_perf", 13)) { + pcie_bus_config = PCIE_BUS_PERFORMANCE; } else { printk(KERN_ERR "PCI: Unknown option `%s'\n", str); diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h index c8cee76..b74084e 100644 --- a/drivers/pci/pci.h +++ b/drivers/pci/pci.h @@ -283,6 +283,8 @@ static inline int pci_iov_bus_range(struct pci_bus *bus) #endif /* CONFIG_PCI_IOV */ +extern unsigned long pci_cardbus_resource_alignment(struct resource *); + static inline resource_size_t pci_resource_alignment(struct pci_dev *dev, struct resource *res) { @@ -292,6 +294,8 @@ static inline resource_size_t pci_resource_alignment(struct pci_dev *dev, if (resno >= PCI_IOV_RESOURCES && resno <= PCI_IOV_RESOURCE_END) return pci_sriov_resource_alignment(dev, resno); #endif + if (dev->class >> 8 == PCI_CLASS_BRIDGE_CARDBUS) + return pci_cardbus_resource_alignment(res); return resource_alignment(res); } diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c index 795c902..8473727 100644 --- a/drivers/pci/probe.c +++ b/drivers/pci/probe.c @@ -856,6 +856,8 @@ void set_pcie_port_type(struct pci_dev *pdev) pdev->pcie_cap = pos; pci_read_config_word(pdev, pos + PCI_EXP_FLAGS, ®16); pdev->pcie_type = (reg16 & PCI_EXP_FLAGS_TYPE) >> 4; + pci_read_config_word(pdev, pos + PCI_EXP_DEVCAP, ®16); + pdev->pcie_mpss = reg16 & PCI_EXP_DEVCAP_PAYLOAD; } void set_pcie_hotplug_bridge(struct pci_dev *pdev) @@ -1326,6 +1328,150 @@ int pci_scan_slot(struct pci_bus *bus, int devfn) return nr; } +static int pcie_find_smpss(struct pci_dev *dev, void *data) +{ + u8 *smpss = data; + + if (!pci_is_pcie(dev)) + return 0; + + /* For PCIE hotplug enabled slots not connected directly to a + * PCI-E root port, there can be problems when hotplugging + * devices. This is due to the possibility of hotplugging a + * device into the fabric with a smaller MPS that the devices + * currently running have configured. Modifying the MPS on the + * running devices could cause a fatal bus error due to an + * incoming frame being larger than the newly configured MPS. + * To work around this, the MPS for the entire fabric must be + * set to the minimum size. Any devices hotplugged into this + * fabric will have the minimum MPS set. If the PCI hotplug + * slot is directly connected to the root port and there are not + * other devices on the fabric (which seems to be the most + * common case), then this is not an issue and MPS discovery + * will occur as normal. + */ + if (dev->is_hotplug_bridge && (!list_is_singular(&dev->bus->devices) || + dev->bus->self->pcie_type != PCI_EXP_TYPE_ROOT_PORT)) + *smpss = 0; + + if (*smpss > dev->pcie_mpss) + *smpss = dev->pcie_mpss; + + return 0; +} + +static void pcie_write_mps(struct pci_dev *dev, int mps) +{ + int rc, dev_mpss; + + dev_mpss = 128 << dev->pcie_mpss; + + if (pcie_bus_config == PCIE_BUS_PERFORMANCE) { + if (dev->bus->self) { + dev_dbg(&dev->bus->dev, "Bus MPSS %d\n", + 128 << dev->bus->self->pcie_mpss); + + /* For "MPS Force Max", the assumption is made that + * downstream communication will never be larger than + * the MRRS. So, the MPS only needs to be configured + * for the upstream communication. This being the case, + * walk from the top down and set the MPS of the child + * to that of the parent bus. + */ + mps = 128 << dev->bus->self->pcie_mpss; + if (mps > dev_mpss) + dev_warn(&dev->dev, "MPS configured higher than" + " maximum supported by the device. If" + " a bus issue occurs, try running with" + " pci=pcie_bus_safe.\n"); + } + + dev->pcie_mpss = ffs(mps) - 8; + } + + rc = pcie_set_mps(dev, mps); + if (rc) + dev_err(&dev->dev, "Failed attempting to set the MPS\n"); +} + +static void pcie_write_mrrs(struct pci_dev *dev, int mps) +{ + int rc, mrrs; + + if (pcie_bus_config == PCIE_BUS_PERFORMANCE) { + int dev_mpss = 128 << dev->pcie_mpss; + + /* For Max performance, the MRRS must be set to the largest + * supported value. However, it cannot be configured larger + * than the MPS the device or the bus can support. This assumes + * that the largest MRRS available on the device cannot be + * smaller than the device MPSS. + */ + mrrs = mps < dev_mpss ? mps : dev_mpss; + } else + /* In the "safe" case, configure the MRRS for fairness on the + * bus by making all devices have the same size + */ + mrrs = mps; + + + /* MRRS is a R/W register. Invalid values can be written, but a + * subsiquent read will verify if the value is acceptable or not. + * If the MRRS value provided is not acceptable (e.g., too large), + * shrink the value until it is acceptable to the HW. + */ + while (mrrs != pcie_get_readrq(dev) && mrrs >= 128) { + rc = pcie_set_readrq(dev, mrrs); + if (rc) + dev_err(&dev->dev, "Failed attempting to set the MRRS\n"); + + mrrs /= 2; + } +} + +static int pcie_bus_configure_set(struct pci_dev *dev, void *data) +{ + int mps = 128 << *(u8 *)data; + + if (!pci_is_pcie(dev)) + return 0; + + dev_info(&dev->dev, "Dev MPS %d MPSS %d MRRS %d\n", + pcie_get_mps(dev), 128<<dev->pcie_mpss, pcie_get_readrq(dev)); + + pcie_write_mps(dev, mps); + pcie_write_mrrs(dev, mps); + + dev_info(&dev->dev, "Dev MPS %d MPSS %d MRRS %d\n", + pcie_get_mps(dev), 128<<dev->pcie_mpss, pcie_get_readrq(dev)); + + return 0; +} + +/* pcie_bus_configure_mps requires that pci_walk_bus work in a top-down, + * parents then children fashion. If this changes, then this code will not + * work as designed. + */ +void pcie_bus_configure_settings(struct pci_bus *bus, u8 mpss) +{ + u8 smpss = mpss; + + if (!bus->self) + return; + + if (!pci_is_pcie(bus->self)) + return; + + if (pcie_bus_config == PCIE_BUS_SAFE) { + pcie_find_smpss(bus->self, &smpss); + pci_walk_bus(bus, pcie_find_smpss, &smpss); + } + + pcie_bus_configure_set(bus->self, &smpss); + pci_walk_bus(bus, pcie_bus_configure_set, &smpss); +} +EXPORT_SYMBOL_GPL(pcie_bus_configure_settings); + unsigned int __devinit pci_scan_child_bus(struct pci_bus *bus) { unsigned int devfn, pass, max = bus->secondary; diff --git a/drivers/pci/setup-bus.c b/drivers/pci/setup-bus.c index 8a1d3c7..784da9d 100644 --- a/drivers/pci/setup-bus.c +++ b/drivers/pci/setup-bus.c @@ -34,6 +34,7 @@ struct resource_list_x { resource_size_t start; resource_size_t end; resource_size_t add_size; + resource_size_t min_align; unsigned long flags; }; @@ -65,7 +66,7 @@ void pci_realloc(void) */ static void add_to_list(struct resource_list_x *head, struct pci_dev *dev, struct resource *res, - resource_size_t add_size) + resource_size_t add_size, resource_size_t min_align) { struct resource_list_x *list = head; struct resource_list_x *ln = list->next; @@ -84,13 +85,16 @@ static void add_to_list(struct resource_list_x *head, tmp->end = res->end; tmp->flags = res->flags; tmp->add_size = add_size; + tmp->min_align = min_align; list->next = tmp; } static void add_to_failed_list(struct resource_list_x *head, struct pci_dev *dev, struct resource *res) { - add_to_list(head, dev, res, 0); + add_to_list(head, dev, res, + 0 /* dont care */, + 0 /* dont care */); } static void __dev_sort_resources(struct pci_dev *dev, @@ -121,18 +125,18 @@ static inline void reset_resource(struct resource *res) } /** - * adjust_resources_sorted() - satisfy any additional resource requests + * reassign_resources_sorted() - satisfy any additional resource requests * - * @add_head : head of the list tracking requests requiring additional + * @realloc_head : head of the list tracking requests requiring additional * resources * @head : head of the list tracking requests with allocated * resources * - * Walk through each element of the add_head and try to procure + * Walk through each element of the realloc_head and try to procure * additional resources for the element, provided the element * is in the head list. */ -static void adjust_resources_sorted(struct resource_list_x *add_head, +static void reassign_resources_sorted(struct resource_list_x *realloc_head, struct resource_list *head) { struct resource *res; @@ -141,8 +145,8 @@ static void adjust_resources_sorted(struct resource_list_x *add_head, resource_size_t add_size; int idx; - prev = add_head; - for (list = add_head->next; list;) { + prev = realloc_head; + for (list = realloc_head->next; list;) { res = list->res; /* skip resource that has been reset */ if (!res->flags) @@ -159,13 +163,17 @@ static void adjust_resources_sorted(struct resource_list_x *add_head, idx = res - &list->dev->resource[0]; add_size=list->add_size; - if (!resource_size(res) && add_size) { - res->end = res->start + add_size - 1; - if(pci_assign_resource(list->dev, idx)) + if (!resource_size(res)) { + res->start = list->start; + res->end = res->start + add_size - 1; + if(pci_assign_resource(list->dev, idx)) reset_resource(res); - } else if (add_size) { - adjust_resource(res, res->start, - resource_size(res) + add_size); + } else { + resource_size_t align = list->min_align; + res->flags |= list->flags & (IORESOURCE_STARTALIGN|IORESOURCE_SIZEALIGN); + if (pci_reassign_resource(list->dev, idx, add_size, align)) + dev_printk(KERN_DEBUG, &list->dev->dev, "failed to add optional resources res=%pR\n", + res); } out: tmp = list; @@ -210,16 +218,16 @@ static void assign_requested_resources_sorted(struct resource_list *head, } static void __assign_resources_sorted(struct resource_list *head, - struct resource_list_x *add_head, + struct resource_list_x *realloc_head, struct resource_list_x *fail_head) { /* Satisfy the must-have resource requests */ assign_requested_resources_sorted(head, fail_head); - /* Try to satisfy any additional nice-to-have resource + /* Try to satisfy any additional optional resource requests */ - if (add_head) - adjust_resources_sorted(add_head, head); + if (realloc_head) + reassign_resources_sorted(realloc_head, head); free_list(resource_list, head); } @@ -235,7 +243,7 @@ static void pdev_assign_resources_sorted(struct pci_dev *dev, } static void pbus_assign_resources_sorted(const struct pci_bus *bus, - struct resource_list_x *add_head, + struct resource_list_x *realloc_head, struct resource_list_x *fail_head) { struct pci_dev *dev; @@ -245,7 +253,7 @@ static void pbus_assign_resources_sorted(const struct pci_bus *bus, list_for_each_entry(dev, &bus->devices, bus_list) __dev_sort_resources(dev, &head); - __assign_resources_sorted(&head, add_head, fail_head); + __assign_resources_sorted(&head, realloc_head, fail_head); } void pci_setup_cardbus(struct pci_bus *bus) @@ -540,13 +548,27 @@ static resource_size_t calculate_memsize(resource_size_t size, return size; } +static resource_size_t get_res_add_size(struct resource_list_x *realloc_head, + struct resource *res) +{ + struct resource_list_x *list; + + /* check if it is in realloc_head list */ + for (list = realloc_head->next; list && list->res != res; + list = list->next); + if (list) + return list->add_size; + + return 0; +} + /** * pbus_size_io() - size the io window of a given bus * * @bus : the bus * @min_size : the minimum io window that must to be allocated * @add_size : additional optional io window - * @add_head : track the additional io window on this list + * @realloc_head : track the additional io window on this list * * Sizing the IO windows of the PCI-PCI bridge is trivial, * since these windows have 4K granularity and the IO ranges @@ -554,11 +576,12 @@ static resource_size_t calculate_memsize(resource_size_t size, * We must be careful with the ISA aliasing though. */ static void pbus_size_io(struct pci_bus *bus, resource_size_t min_size, - resource_size_t add_size, struct resource_list_x *add_head) + resource_size_t add_size, struct resource_list_x *realloc_head) { struct pci_dev *dev; struct resource *b_res = find_free_bus_resource(bus, IORESOURCE_IO); unsigned long size = 0, size0 = 0, size1 = 0; + resource_size_t children_add_size = 0; if (!b_res) return; @@ -579,11 +602,16 @@ static void pbus_size_io(struct pci_bus *bus, resource_size_t min_size, size += r_size; else size1 += r_size; + + if (realloc_head) + children_add_size += get_res_add_size(realloc_head, r); } } size0 = calculate_iosize(size, min_size, size1, resource_size(b_res), 4096); - size1 = (!add_head || (add_head && !add_size)) ? size0 : + if (children_add_size > add_size) + add_size = children_add_size; + size1 = (!realloc_head || (realloc_head && !add_size)) ? size0 : calculate_iosize(size, min_size+add_size, size1, resource_size(b_res), 4096); if (!size0 && !size1) { @@ -598,8 +626,8 @@ static void pbus_size_io(struct pci_bus *bus, resource_size_t min_size, b_res->start = 4096; b_res->end = b_res->start + size0 - 1; b_res->flags |= IORESOURCE_STARTALIGN; - if (size1 > size0 && add_head) - add_to_list(add_head, bus->self, b_res, size1-size0); + if (size1 > size0 && realloc_head) + add_to_list(realloc_head, bus->self, b_res, size1-size0, 4096); } /** @@ -608,7 +636,7 @@ static void pbus_size_io(struct pci_bus *bus, resource_size_t min_size, * @bus : the bus * @min_size : the minimum memory window that must to be allocated * @add_size : additional optional memory window - * @add_head : track the additional memory window on this list + * @realloc_head : track the additional memory window on this list * * Calculate the size of the bus and minimal alignment which * guarantees that all child resources fit in this size. @@ -616,7 +644,7 @@ static void pbus_size_io(struct pci_bus *bus, resource_size_t min_size, static int pbus_size_mem(struct pci_bus *bus, unsigned long mask, unsigned long type, resource_size_t min_size, resource_size_t add_size, - struct resource_list_x *add_head) + struct resource_list_x *realloc_head) { struct pci_dev *dev; resource_size_t min_align, align, size, size0, size1; @@ -624,6 +652,7 @@ static int pbus_size_mem(struct pci_bus *bus, unsigned long mask, int order, max_order; struct resource *b_res = find_free_bus_resource(bus, type); unsigned int mem64_mask = 0; + resource_size_t children_add_size = 0; if (!b_res) return 0; @@ -645,6 +674,16 @@ static int pbus_size_mem(struct pci_bus *bus, unsigned long mask, if (r->parent || (r->flags & mask) != type) continue; r_size = resource_size(r); +#ifdef CONFIG_PCI_IOV + /* put SRIOV requested res to the optional list */ + if (realloc_head && i >= PCI_IOV_RESOURCES && + i <= PCI_IOV_RESOURCE_END) { + r->end = r->start - 1; + add_to_list(realloc_head, dev, r, r_size, 0/* dont' care */); + children_add_size += r_size; + continue; + } +#endif /* For bridges size != alignment */ align = pci_resource_alignment(dev, r); order = __ffs(align) - 20; @@ -665,6 +704,9 @@ static int pbus_size_mem(struct pci_bus *bus, unsigned long mask, if (order > max_order) max_order = order; mem64_mask &= r->flags & IORESOURCE_MEM_64; + + if (realloc_head) + children_add_size += get_res_add_size(realloc_head, r); } } align = 0; @@ -681,7 +723,9 @@ static int pbus_size_mem(struct pci_bus *bus, unsigned long mask, align += aligns[order]; } size0 = calculate_memsize(size, min_size, 0, resource_size(b_res), min_align); - size1 = (!add_head || (add_head && !add_size)) ? size0 : + if (children_add_size > add_size) + add_size = children_add_size; + size1 = (!realloc_head || (realloc_head && !add_size)) ? size0 : calculate_memsize(size, min_size+add_size, 0, resource_size(b_res), min_align); if (!size0 && !size1) { @@ -695,12 +739,22 @@ static int pbus_size_mem(struct pci_bus *bus, unsigned long mask, b_res->start = min_align; b_res->end = size0 + min_align - 1; b_res->flags |= IORESOURCE_STARTALIGN | mem64_mask; - if (size1 > size0 && add_head) - add_to_list(add_head, bus->self, b_res, size1-size0); + if (size1 > size0 && realloc_head) + add_to_list(realloc_head, bus->self, b_res, size1-size0, min_align); return 1; } -static void pci_bus_size_cardbus(struct pci_bus *bus) +unsigned long pci_cardbus_resource_alignment(struct resource *res) +{ + if (res->flags & IORESOURCE_IO) + return pci_cardbus_io_size; + if (res->flags & IORESOURCE_MEM) + return pci_cardbus_mem_size; + return 0; +} + +static void pci_bus_size_cardbus(struct pci_bus *bus, + struct resource_list_x *realloc_head) { struct pci_dev *bridge = bus->self; struct resource *b_res = &bridge->resource[PCI_BRIDGE_RESOURCES]; @@ -711,12 +765,14 @@ static void pci_bus_size_cardbus(struct pci_bus *bus) * a fixed amount of bus space for CardBus bridges. */ b_res[0].start = 0; - b_res[0].end = pci_cardbus_io_size - 1; b_res[0].flags |= IORESOURCE_IO | IORESOURCE_SIZEALIGN; + if (realloc_head) + add_to_list(realloc_head, bridge, b_res, pci_cardbus_io_size, 0 /* dont care */); b_res[1].start = 0; - b_res[1].end = pci_cardbus_io_size - 1; b_res[1].flags |= IORESOURCE_IO | IORESOURCE_SIZEALIGN; + if (realloc_head) + add_to_list(realloc_head, bridge, b_res+1, pci_cardbus_io_size, 0 /* dont care */); /* * Check whether prefetchable memory is supported @@ -736,21 +792,31 @@ static void pci_bus_size_cardbus(struct pci_bus *bus) */ if (ctrl & PCI_CB_BRIDGE_CTL_PREFETCH_MEM0) { b_res[2].start = 0; - b_res[2].end = pci_cardbus_mem_size - 1; b_res[2].flags |= IORESOURCE_MEM | IORESOURCE_PREFETCH | IORESOURCE_SIZEALIGN; + if (realloc_head) + add_to_list(realloc_head, bridge, b_res+2, pci_cardbus_mem_size, 0 /* dont care */); b_res[3].start = 0; - b_res[3].end = pci_cardbus_mem_size - 1; b_res[3].flags |= IORESOURCE_MEM | IORESOURCE_SIZEALIGN; + if (realloc_head) + add_to_list(realloc_head, bridge, b_res+3, pci_cardbus_mem_size, 0 /* dont care */); } else { b_res[3].start = 0; - b_res[3].end = pci_cardbus_mem_size * 2 - 1; b_res[3].flags |= IORESOURCE_MEM | IORESOURCE_SIZEALIGN; + if (realloc_head) + add_to_list(realloc_head, bridge, b_res+3, pci_cardbus_mem_size * 2, 0 /* dont care */); } + + /* set the size of the resource to zero, so that the resource does not + * get assigned during required-resource allocation cycle but gets assigned + * during the optional-resource allocation cycle. + */ + b_res[0].start = b_res[1].start = b_res[2].start = b_res[3].start = 1; + b_res[0].end = b_res[1].end = b_res[2].end = b_res[3].end = 0; } void __ref __pci_bus_size_bridges(struct pci_bus *bus, - struct resource_list_x *add_head) + struct resource_list_x *realloc_head) { struct pci_dev *dev; unsigned long mask, prefmask; @@ -763,12 +829,12 @@ void __ref __pci_bus_size_bridges(struct pci_bus *bus, switch (dev->class >> 8) { case PCI_CLASS_BRIDGE_CARDBUS: - pci_bus_size_cardbus(b); + pci_bus_size_cardbus(b, realloc_head); break; case PCI_CLASS_BRIDGE_PCI: default: - __pci_bus_size_bridges(b, add_head); + __pci_bus_size_bridges(b, realloc_head); break; } } @@ -792,7 +858,7 @@ void __ref __pci_bus_size_bridges(struct pci_bus *bus, * Follow thru */ default: - pbus_size_io(bus, 0, additional_io_size, add_head); + pbus_size_io(bus, 0, additional_io_size, realloc_head); /* If the bridge supports prefetchable range, size it separately. If it doesn't, or its prefetchable window has already been allocated by arch code, try @@ -800,11 +866,11 @@ void __ref __pci_bus_size_bridges(struct pci_bus *bus, resources. */ mask = IORESOURCE_MEM; prefmask = IORESOURCE_MEM | IORESOURCE_PREFETCH; - if (pbus_size_mem(bus, prefmask, prefmask, 0, additional_mem_size, add_head)) + if (pbus_size_mem(bus, prefmask, prefmask, 0, additional_mem_size, realloc_head)) mask = prefmask; /* Success, size non-prefetch only. */ else additional_mem_size += additional_mem_size; - pbus_size_mem(bus, mask, IORESOURCE_MEM, 0, additional_mem_size, add_head); + pbus_size_mem(bus, mask, IORESOURCE_MEM, 0, additional_mem_size, realloc_head); break; } } @@ -816,20 +882,20 @@ void __ref pci_bus_size_bridges(struct pci_bus *bus) EXPORT_SYMBOL(pci_bus_size_bridges); static void __ref __pci_bus_assign_resources(const struct pci_bus *bus, - struct resource_list_x *add_head, + struct resource_list_x *realloc_head, struct resource_list_x *fail_head) { struct pci_bus *b; struct pci_dev *dev; - pbus_assign_resources_sorted(bus, add_head, fail_head); + pbus_assign_resources_sorted(bus, realloc_head, fail_head); list_for_each_entry(dev, &bus->devices, bus_list) { b = dev->subordinate; if (!b) continue; - __pci_bus_assign_resources(b, add_head, fail_head); + __pci_bus_assign_resources(b, realloc_head, fail_head); switch (dev->class >> 8) { case PCI_CLASS_BRIDGE_PCI: @@ -1039,7 +1105,7 @@ void __init pci_assign_unassigned_resources(void) { struct pci_bus *bus; - struct resource_list_x add_list; /* list of resources that + struct resource_list_x realloc_list; /* list of resources that want additional resources */ int tried_times = 0; enum release_type rel_type = leaf_only; @@ -1052,7 +1118,7 @@ pci_assign_unassigned_resources(void) head.next = NULL; - add_list.next = NULL; + realloc_list.next = NULL; pci_try_num = max_depth + 1; printk(KERN_DEBUG "PCI: max bus depth: %d pci_try_num: %d\n", @@ -1062,12 +1128,12 @@ again: /* Depth first, calculate sizes and alignments of all subordinate buses. */ list_for_each_entry(bus, &pci_root_buses, node) - __pci_bus_size_bridges(bus, &add_list); + __pci_bus_size_bridges(bus, &realloc_list); /* Depth last, allocate resources and update the hardware. */ list_for_each_entry(bus, &pci_root_buses, node) - __pci_bus_assign_resources(bus, &add_list, &head); - BUG_ON(add_list.next); + __pci_bus_assign_resources(bus, &realloc_list, &head); + BUG_ON(realloc_list.next); tried_times++; /* any device complain? */ diff --git a/drivers/pci/setup-res.c b/drivers/pci/setup-res.c index 319f359..51a9095 100644 --- a/drivers/pci/setup-res.c +++ b/drivers/pci/setup-res.c @@ -128,16 +128,16 @@ void pci_disable_bridge_window(struct pci_dev *dev) } #endif /* CONFIG_PCI_QUIRKS */ + + static int __pci_assign_resource(struct pci_bus *bus, struct pci_dev *dev, - int resno) + int resno, resource_size_t size, resource_size_t align) { struct resource *res = dev->resource + resno; - resource_size_t size, min, align; + resource_size_t min; int ret; - size = resource_size(res); min = (res->flags & IORESOURCE_IO) ? PCIBIOS_MIN_IO : PCIBIOS_MIN_MEM; - align = pci_resource_alignment(dev, res); /* First, try exact prefetching match.. */ ret = pci_bus_alloc_resource(bus, res, size, align, min, @@ -154,56 +154,101 @@ static int __pci_assign_resource(struct pci_bus *bus, struct pci_dev *dev, ret = pci_bus_alloc_resource(bus, res, size, align, min, 0, pcibios_align_resource, dev); } + return ret; +} - if (ret < 0 && dev->fw_addr[resno]) { - struct resource *root, *conflict; - resource_size_t start, end; +static int pci_revert_fw_address(struct resource *res, struct pci_dev *dev, + int resno, resource_size_t size) +{ + struct resource *root, *conflict; + resource_size_t start, end; + int ret = 0; - /* - * If we failed to assign anything, let's try the address - * where firmware left it. That at least has a chance of - * working, which is better than just leaving it disabled. - */ + if (res->flags & IORESOURCE_IO) + root = &ioport_resource; + else + root = &iomem_resource; + + start = res->start; + end = res->end; + res->start = dev->fw_addr[resno]; + res->end = res->start + size - 1; + dev_info(&dev->dev, "BAR %d: trying firmware assignment %pR\n", + resno, res); + conflict = request_resource_conflict(root, res); + if (conflict) { + dev_info(&dev->dev, + "BAR %d: %pR conflicts with %s %pR\n", resno, + res, conflict->name, conflict); + res->start = start; + res->end = end; + ret = 1; + } + return ret; +} + +static int _pci_assign_resource(struct pci_dev *dev, int resno, int size, resource_size_t min_align) +{ + struct resource *res = dev->resource + resno; + struct pci_bus *bus; + int ret; + char *type; - if (res->flags & IORESOURCE_IO) - root = &ioport_resource; + bus = dev->bus; + while ((ret = __pci_assign_resource(bus, dev, resno, size, min_align))) { + if (!bus->parent || !bus->self->transparent) + break; + bus = bus->parent; + } + + if (ret) { + if (res->flags & IORESOURCE_MEM) + if (res->flags & IORESOURCE_PREFETCH) + type = "mem pref"; + else + type = "mem"; + else if (res->flags & IORESOURCE_IO) + type = "io"; else - root = &iomem_resource; - - start = res->start; - end = res->end; - res->start = dev->fw_addr[resno]; - res->end = res->start + size - 1; - dev_info(&dev->dev, "BAR %d: trying firmware assignment %pR\n", - resno, res); - conflict = request_resource_conflict(root, res); - if (conflict) { - dev_info(&dev->dev, - "BAR %d: %pR conflicts with %s %pR\n", resno, - res, conflict->name, conflict); - res->start = start; - res->end = end; - } else - ret = 0; + type = "unknown"; + dev_info(&dev->dev, + "BAR %d: can't assign %s (size %#llx)\n", + resno, type, (unsigned long long) resource_size(res)); } + return ret; +} + +int pci_reassign_resource(struct pci_dev *dev, int resno, resource_size_t addsize, + resource_size_t min_align) +{ + struct resource *res = dev->resource + resno; + resource_size_t new_size; + int ret; + + if (!res->parent) { + dev_info(&dev->dev, "BAR %d: can't reassign an unassigned resouce %pR " + "\n", resno, res); + return -EINVAL; + } + + new_size = resource_size(res) + addsize + min_align; + ret = _pci_assign_resource(dev, resno, new_size, min_align); if (!ret) { res->flags &= ~IORESOURCE_STARTALIGN; dev_info(&dev->dev, "BAR %d: assigned %pR\n", resno, res); if (resno < PCI_BRIDGE_RESOURCES) pci_update_resource(dev, resno); } - return ret; } int pci_assign_resource(struct pci_dev *dev, int resno) { struct resource *res = dev->resource + resno; - resource_size_t align; + resource_size_t align, size; struct pci_bus *bus; int ret; - char *type; align = pci_resource_alignment(dev, res); if (!align) { @@ -213,34 +258,27 @@ int pci_assign_resource(struct pci_dev *dev, int resno) } bus = dev->bus; - while ((ret = __pci_assign_resource(bus, dev, resno))) { - if (bus->parent && bus->self->transparent) - bus = bus->parent; - else - bus = NULL; - if (bus) - continue; - break; - } + size = resource_size(res); + ret = _pci_assign_resource(dev, resno, size, align); - if (ret) { - if (res->flags & IORESOURCE_MEM) - if (res->flags & IORESOURCE_PREFETCH) - type = "mem pref"; - else - type = "mem"; - else if (res->flags & IORESOURCE_IO) - type = "io"; - else - type = "unknown"; - dev_info(&dev->dev, - "BAR %d: can't assign %s (size %#llx)\n", - resno, type, (unsigned long long) resource_size(res)); - } + /* + * If we failed to assign anything, let's try the address + * where firmware left it. That at least has a chance of + * working, which is better than just leaving it disabled. + */ + if (ret < 0 && dev->fw_addr[resno]) + ret = pci_revert_fw_address(res, dev, resno, size); + if (!ret) { + res->flags &= ~IORESOURCE_STARTALIGN; + dev_info(&dev->dev, "BAR %d: assigned %pR\n", resno, res); + if (resno < PCI_BRIDGE_RESOURCES) + pci_update_resource(dev, resno); + } return ret; } + /* Sort resources by alignment */ void pdev_sort_resources(struct pci_dev *dev, struct resource_list *head) { diff --git a/fs/befs/linuxvfs.c b/fs/befs/linuxvfs.c index 54b8c28..720d885 100644 --- a/fs/befs/linuxvfs.c +++ b/fs/befs/linuxvfs.c @@ -474,17 +474,22 @@ befs_follow_link(struct dentry *dentry, struct nameidata *nd) befs_data_stream *data = &befs_ino->i_data.ds; befs_off_t len = data->size; - befs_debug(sb, "Follow long symlink"); - - link = kmalloc(len, GFP_NOFS); - if (!link) { - link = ERR_PTR(-ENOMEM); - } else if (befs_read_lsymlink(sb, data, link, len) != len) { - kfree(link); - befs_error(sb, "Failed to read entire long symlink"); + if (len == 0) { + befs_error(sb, "Long symlink with illegal length"); link = ERR_PTR(-EIO); } else { - link[len - 1] = '\0'; + befs_debug(sb, "Follow long symlink"); + + link = kmalloc(len, GFP_NOFS); + if (!link) { + link = ERR_PTR(-ENOMEM); + } else if (befs_read_lsymlink(sb, data, link, len) != len) { + kfree(link); + befs_error(sb, "Failed to read entire long symlink"); + link = ERR_PTR(-EIO); + } else { + link[len - 1] = '\0'; + } } } else { link = befs_ino->i_data.symlink; diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index 0469263..03912c5 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -1415,17 +1415,15 @@ void btrfs_set_##name(struct extent_buffer *eb, type *s, u##bits val); #define BTRFS_SETGET_HEADER_FUNCS(name, type, member, bits) \ static inline u##bits btrfs_##name(struct extent_buffer *eb) \ { \ - type *p = kmap_atomic(eb->first_page, KM_USER0); \ + type *p = page_address(eb->first_page); \ u##bits res = le##bits##_to_cpu(p->member); \ - kunmap_atomic(p, KM_USER0); \ return res; \ } \ static inline void btrfs_set_##name(struct extent_buffer *eb, \ u##bits val) \ { \ - type *p = kmap_atomic(eb->first_page, KM_USER0); \ + type *p = page_address(eb->first_page); \ p->member = cpu_to_le##bits(val); \ - kunmap_atomic(p, KM_USER0); \ } #define BTRFS_SETGET_STACK_FUNCS(name, type, member, bits) \ @@ -2367,8 +2365,8 @@ static inline int btrfs_insert_empty_item(struct btrfs_trans_handle *trans, int btrfs_next_leaf(struct btrfs_root *root, struct btrfs_path *path); int btrfs_prev_leaf(struct btrfs_root *root, struct btrfs_path *path); int btrfs_leaf_free_space(struct btrfs_root *root, struct extent_buffer *leaf); -int btrfs_drop_snapshot(struct btrfs_root *root, - struct btrfs_block_rsv *block_rsv, int update_ref); +void btrfs_drop_snapshot(struct btrfs_root *root, + struct btrfs_block_rsv *block_rsv, int update_ref); int btrfs_drop_subtree(struct btrfs_trans_handle *trans, struct btrfs_root *root, struct extent_buffer *node, diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index 66bac22..f5be06a 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -1782,6 +1782,9 @@ static int btrfs_discard_extent(struct btrfs_root *root, u64 bytenr, for (i = 0; i < multi->num_stripes; i++, stripe++) { + if (!stripe->dev->can_discard) + continue; + ret = btrfs_issue_discard(stripe->dev->bdev, stripe->physical, stripe->length); @@ -1789,11 +1792,16 @@ static int btrfs_discard_extent(struct btrfs_root *root, u64 bytenr, discarded_bytes += stripe->length; else if (ret != -EOPNOTSUPP) break; + + /* + * Just in case we get back EOPNOTSUPP for some reason, + * just ignore the return value so we don't screw up + * people calling discard_extent. + */ + ret = 0; } kfree(multi); } - if (discarded_bytes && ret == -EOPNOTSUPP) - ret = 0; if (actual_bytes) *actual_bytes = discarded_bytes; @@ -6269,8 +6277,8 @@ static noinline int walk_up_tree(struct btrfs_trans_handle *trans, * also make sure backrefs for the shared block and all lower level * blocks are properly updated. */ -int btrfs_drop_snapshot(struct btrfs_root *root, - struct btrfs_block_rsv *block_rsv, int update_ref) +void btrfs_drop_snapshot(struct btrfs_root *root, + struct btrfs_block_rsv *block_rsv, int update_ref) { struct btrfs_path *path; struct btrfs_trans_handle *trans; @@ -6283,13 +6291,16 @@ int btrfs_drop_snapshot(struct btrfs_root *root, int level; path = btrfs_alloc_path(); - if (!path) - return -ENOMEM; + if (!path) { + err = -ENOMEM; + goto out; + } wc = kzalloc(sizeof(*wc), GFP_NOFS); if (!wc) { btrfs_free_path(path); - return -ENOMEM; + err = -ENOMEM; + goto out; } trans = btrfs_start_transaction(tree_root, 0); @@ -6318,7 +6329,7 @@ int btrfs_drop_snapshot(struct btrfs_root *root, path->lowest_level = 0; if (ret < 0) { err = ret; - goto out; + goto out_free; } WARN_ON(ret > 0); @@ -6425,11 +6436,14 @@ int btrfs_drop_snapshot(struct btrfs_root *root, free_extent_buffer(root->commit_root); kfree(root); } -out: +out_free: btrfs_end_transaction_throttle(trans, tree_root); kfree(wc); btrfs_free_path(path); - return err; +out: + if (err) + btrfs_std_error(root->fs_info, err); + return; } /* @@ -6720,6 +6734,10 @@ int btrfs_can_relocate(struct btrfs_root *root, u64 bytenr) struct btrfs_space_info *space_info; struct btrfs_fs_devices *fs_devices = root->fs_info->fs_devices; struct btrfs_device *device; + u64 min_free; + u64 dev_min = 1; + u64 dev_nr = 0; + int index; int full = 0; int ret = 0; @@ -6729,8 +6747,10 @@ int btrfs_can_relocate(struct btrfs_root *root, u64 bytenr) if (!block_group) return -1; + min_free = btrfs_block_group_used(&block_group->item); + /* no bytes used, we're good */ - if (!btrfs_block_group_used(&block_group->item)) + if (!min_free) goto out; space_info = block_group->space_info; @@ -6746,10 +6766,9 @@ int btrfs_can_relocate(struct btrfs_root *root, u64 bytenr) * all of the extents from this block group. If we can, we're good */ if ((space_info->total_bytes != block_group->key.offset) && - (space_info->bytes_used + space_info->bytes_reserved + - space_info->bytes_pinned + space_info->bytes_readonly + - btrfs_block_group_used(&block_group->item) < - space_info->total_bytes)) { + (space_info->bytes_used + space_info->bytes_reserved + + space_info->bytes_pinned + space_info->bytes_readonly + + min_free < space_info->total_bytes)) { spin_unlock(&space_info->lock); goto out; } @@ -6766,9 +6785,31 @@ int btrfs_can_relocate(struct btrfs_root *root, u64 bytenr) if (full) goto out; + /* + * index: + * 0: raid10 + * 1: raid1 + * 2: dup + * 3: raid0 + * 4: single + */ + index = get_block_group_index(block_group); + if (index == 0) { + dev_min = 4; + /* Divide by 2 */ + min_free >>= 1; + } else if (index == 1) { + dev_min = 2; + } else if (index == 2) { + /* Multiply by 2 */ + min_free <<= 1; + } else if (index == 3) { + dev_min = fs_devices->rw_devices; + do_div(min_free, dev_min); + } + mutex_lock(&root->fs_info->chunk_mutex); list_for_each_entry(device, &fs_devices->alloc_list, dev_alloc_list) { - u64 min_free = btrfs_block_group_used(&block_group->item); u64 dev_offset; /* @@ -6779,7 +6820,11 @@ int btrfs_can_relocate(struct btrfs_root *root, u64 bytenr) ret = find_free_dev_extent(NULL, device, min_free, &dev_offset, NULL); if (!ret) + dev_nr++; + + if (dev_nr >= dev_min) break; + ret = -1; } } diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 658d669..e7872e4 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -150,6 +150,8 @@ int btrfs_add_inode_defrag(struct btrfs_trans_handle *trans, spin_lock(&root->fs_info->defrag_inodes_lock); if (!BTRFS_I(inode)->in_defrag) __btrfs_add_inode_defrag(inode, defrag); + else + kfree(defrag); spin_unlock(&root->fs_info->defrag_inodes_lock); return 0; } @@ -1638,11 +1640,15 @@ static long btrfs_fallocate(struct file *file, int mode, cur_offset = alloc_start; while (1) { + u64 actual_end; + em = btrfs_get_extent(inode, NULL, 0, cur_offset, alloc_end - cur_offset, 0); BUG_ON(IS_ERR_OR_NULL(em)); last_byte = min(extent_map_end(em), alloc_end); + actual_end = min_t(u64, extent_map_end(em), offset + len); last_byte = (last_byte + mask) & ~mask; + if (em->block_start == EXTENT_MAP_HOLE || (cur_offset >= inode->i_size && !test_bit(EXTENT_FLAG_PREALLOC, &em->flags))) { @@ -1655,6 +1661,16 @@ static long btrfs_fallocate(struct file *file, int mode, free_extent_map(em); break; } + } else if (actual_end > inode->i_size && + !(mode & FALLOC_FL_KEEP_SIZE)) { + /* + * We didn't need to allocate any more space, but we + * still extended the size of the file so we need to + * update i_size. + */ + inode->i_ctime = CURRENT_TIME; + i_size_write(inode, actual_end); + btrfs_ordered_update_i_size(inode, actual_end, NULL); } free_extent_map(em); @@ -1804,10 +1820,14 @@ static loff_t btrfs_file_llseek(struct file *file, loff_t offset, int origin) } } - if (offset < 0 && !(file->f_mode & FMODE_UNSIGNED_OFFSET)) - return -EINVAL; - if (offset > inode->i_sb->s_maxbytes) - return -EINVAL; + if (offset < 0 && !(file->f_mode & FMODE_UNSIGNED_OFFSET)) { + ret = -EINVAL; + goto out; + } + if (offset > inode->i_sb->s_maxbytes) { + ret = -EINVAL; + goto out; + } /* Special lock needed here? */ if (offset != file->f_pos) { diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c index 6377713..6a265b9 100644 --- a/fs/btrfs/free-space-cache.c +++ b/fs/btrfs/free-space-cache.c @@ -1168,9 +1168,9 @@ static void recalculate_thresholds(struct btrfs_free_space_ctl *ctl) div64_u64(extent_bytes, (sizeof(struct btrfs_free_space))); } -static void bitmap_clear_bits(struct btrfs_free_space_ctl *ctl, - struct btrfs_free_space *info, u64 offset, - u64 bytes) +static inline void __bitmap_clear_bits(struct btrfs_free_space_ctl *ctl, + struct btrfs_free_space *info, + u64 offset, u64 bytes) { unsigned long start, count; @@ -1181,6 +1181,13 @@ static void bitmap_clear_bits(struct btrfs_free_space_ctl *ctl, bitmap_clear(info->bitmap, start, count); info->bytes -= bytes; +} + +static void bitmap_clear_bits(struct btrfs_free_space_ctl *ctl, + struct btrfs_free_space *info, u64 offset, + u64 bytes) +{ + __bitmap_clear_bits(ctl, info, offset, bytes); ctl->free_space -= bytes; } @@ -1984,7 +1991,7 @@ static u64 btrfs_alloc_from_bitmap(struct btrfs_block_group_cache *block_group, return 0; ret = search_start; - bitmap_clear_bits(ctl, entry, ret, bytes); + __bitmap_clear_bits(ctl, entry, ret, bytes); return ret; } @@ -2039,7 +2046,6 @@ u64 btrfs_alloc_from_cluster(struct btrfs_block_group_cache *block_group, continue; } } else { - ret = entry->offset; entry->offset += bytes; diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index 15fceef..0ccc743 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -7354,11 +7354,15 @@ static int btrfs_set_page_dirty(struct page *page) static int btrfs_permission(struct inode *inode, int mask) { struct btrfs_root *root = BTRFS_I(inode)->root; + umode_t mode = inode->i_mode; - if (btrfs_root_readonly(root) && (mask & MAY_WRITE)) - return -EROFS; - if ((BTRFS_I(inode)->flags & BTRFS_INODE_READONLY) && (mask & MAY_WRITE)) - return -EACCES; + if (mask & MAY_WRITE && + (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode))) { + if (btrfs_root_readonly(root)) + return -EROFS; + if (BTRFS_I(inode)->flags & BTRFS_INODE_READONLY) + return -EACCES; + } return generic_permission(inode, mask); } diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index 7cf0133..970977a 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -2236,6 +2236,10 @@ static noinline long btrfs_ioctl_clone(struct file *file, unsigned long srcfd, btrfs_wait_ordered_range(src, off, len); } + /* truncate page cache pages from target inode range */ + truncate_inode_pages_range(&inode->i_data, off, + ALIGN(off + len, PAGE_CACHE_SIZE) - 1); + /* clone data */ key.objectid = btrfs_ino(src); key.type = BTRFS_EXTENT_DATA_KEY; diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c index babee65..786639f 100644 --- a/fs/btrfs/tree-log.c +++ b/fs/btrfs/tree-log.c @@ -799,14 +799,15 @@ static noinline int add_inode_ref(struct btrfs_trans_handle *trans, struct extent_buffer *eb, int slot, struct btrfs_key *key) { - struct inode *dir; - int ret; struct btrfs_inode_ref *ref; + struct btrfs_dir_item *di; + struct inode *dir; struct inode *inode; - char *name; - int namelen; unsigned long ref_ptr; unsigned long ref_end; + char *name; + int namelen; + int ret; int search_done = 0; /* @@ -909,6 +910,25 @@ again: } btrfs_release_path(path); + /* look for a conflicting sequence number */ + di = btrfs_lookup_dir_index_item(trans, root, path, btrfs_ino(dir), + btrfs_inode_ref_index(eb, ref), + name, namelen, 0); + if (di && !IS_ERR(di)) { + ret = drop_one_dir_item(trans, root, path, dir, di); + BUG_ON(ret); + } + btrfs_release_path(path); + + /* look for a conflicing name */ + di = btrfs_lookup_dir_item(trans, root, path, btrfs_ino(dir), + name, namelen, 0); + if (di && !IS_ERR(di)) { + ret = drop_one_dir_item(trans, root, path, dir, di); + BUG_ON(ret); + } + btrfs_release_path(path); + insert: /* insert our name */ ret = btrfs_add_link(trans, dir, inode, name, namelen, 0, diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 53875ae73..f2a4cc7 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -142,6 +142,7 @@ static noinline int run_scheduled_bios(struct btrfs_device *device) unsigned long limit; unsigned long last_waited = 0; int force_reg = 0; + int sync_pending = 0; struct blk_plug plug; /* @@ -229,6 +230,22 @@ loop_lock: BUG_ON(atomic_read(&cur->bi_cnt) == 0); + /* + * if we're doing the sync list, record that our + * plug has some sync requests on it + * + * If we're doing the regular list and there are + * sync requests sitting around, unplug before + * we add more + */ + if (pending_bios == &device->pending_sync_bios) { + sync_pending = 1; + } else if (sync_pending) { + blk_finish_plug(&plug); + blk_start_plug(&plug); + sync_pending = 0; + } + submit_bio(cur->bi_rw, cur); num_run++; batch_run++; @@ -500,6 +517,9 @@ static int __btrfs_close_devices(struct btrfs_fs_devices *fs_devices) fs_devices->rw_devices--; } + if (device->can_discard) + fs_devices->num_can_discard--; + new_device = kmalloc(sizeof(*new_device), GFP_NOFS); BUG_ON(!new_device); memcpy(new_device, device, sizeof(*new_device)); @@ -508,6 +528,7 @@ static int __btrfs_close_devices(struct btrfs_fs_devices *fs_devices) new_device->bdev = NULL; new_device->writeable = 0; new_device->in_fs_metadata = 0; + new_device->can_discard = 0; list_replace_rcu(&device->dev_list, &new_device->dev_list); call_rcu(&device->rcu, free_device); @@ -547,6 +568,7 @@ int btrfs_close_devices(struct btrfs_fs_devices *fs_devices) static int __btrfs_open_devices(struct btrfs_fs_devices *fs_devices, fmode_t flags, void *holder) { + struct request_queue *q; struct block_device *bdev; struct list_head *head = &fs_devices->devices; struct btrfs_device *device; @@ -603,6 +625,12 @@ static int __btrfs_open_devices(struct btrfs_fs_devices *fs_devices, seeding = 0; } + q = bdev_get_queue(bdev); + if (blk_queue_discard(q)) { + device->can_discard = 1; + fs_devices->num_can_discard++; + } + device->bdev = bdev; device->in_fs_metadata = 0; device->mode = flags; @@ -835,6 +863,7 @@ int find_free_dev_extent(struct btrfs_trans_handle *trans, max_hole_start = search_start; max_hole_size = 0; + hole_size = 0; if (search_start >= search_end) { ret = -ENOSPC; @@ -917,7 +946,14 @@ next: cond_resched(); } - hole_size = search_end- search_start; + /* + * At this point, search_start should be the end of + * allocated dev extents, and when shrinking the device, + * search_end may be smaller than search_start. + */ + if (search_end > search_start) + hole_size = search_end - search_start; + if (hole_size > max_hole_size) { max_hole_start = search_start; max_hole_size = hole_size; @@ -1543,6 +1579,7 @@ error: int btrfs_init_new_device(struct btrfs_root *root, char *device_path) { + struct request_queue *q; struct btrfs_trans_handle *trans; struct btrfs_device *device; struct block_device *bdev; @@ -1612,6 +1649,9 @@ int btrfs_init_new_device(struct btrfs_root *root, char *device_path) lock_chunks(root); + q = bdev_get_queue(bdev); + if (blk_queue_discard(q)) + device->can_discard = 1; device->writeable = 1; device->work.func = pending_bios_fn; generate_random_uuid(device->uuid); @@ -1647,6 +1687,8 @@ int btrfs_init_new_device(struct btrfs_root *root, char *device_path) root->fs_info->fs_devices->num_devices++; root->fs_info->fs_devices->open_devices++; root->fs_info->fs_devices->rw_devices++; + if (device->can_discard) + root->fs_info->fs_devices->num_can_discard++; root->fs_info->fs_devices->total_rw_bytes += device->total_bytes; if (!blk_queue_nonrot(bdev_get_queue(bdev))) @@ -2413,9 +2455,10 @@ static int __btrfs_alloc_chunk(struct btrfs_trans_handle *trans, total_avail = device->total_bytes - device->bytes_used; else total_avail = 0; - /* avail is off by max(alloc_start, 1MB), but that is the same - * for all devices, so it doesn't hurt the sorting later on - */ + + /* If there is no space on this device, skip it. */ + if (total_avail == 0) + continue; ret = find_free_dev_extent(trans, device, max_stripe_size * dev_stripes, diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h index 7c12d61..6d866db 100644 --- a/fs/btrfs/volumes.h +++ b/fs/btrfs/volumes.h @@ -48,6 +48,7 @@ struct btrfs_device { int writeable; int in_fs_metadata; int missing; + int can_discard; spinlock_t io_lock; @@ -104,6 +105,7 @@ struct btrfs_fs_devices { u64 rw_devices; u64 missing_devices; u64 total_rw_bytes; + u64 num_can_discard; struct block_device *latest_bdev; /* all of the devices in the FS, protected by a mutex diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h index cb71dc1..95da802 100644 --- a/fs/cifs/cifsfs.h +++ b/fs/cifs/cifsfs.h @@ -125,5 +125,5 @@ extern long cifs_ioctl(struct file *filep, unsigned int cmd, unsigned long arg); extern const struct export_operations cifs_export_ops; #endif /* CIFS_NFSD_EXPORT */ -#define CIFS_VERSION "1.74" +#define CIFS_VERSION "1.75" #endif /* _CIFSFS_H */ diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index 80c2e3a..633c246 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -2878,7 +2878,8 @@ cleanup_volume_info_contents(struct smb_vol *volume_info) kfree(volume_info->username); kzfree(volume_info->password); kfree(volume_info->UNC); - kfree(volume_info->UNCip); + if (volume_info->UNCip != volume_info->UNC + 2) + kfree(volume_info->UNCip); kfree(volume_info->domainname); kfree(volume_info->iocharset); kfree(volume_info->prepath); diff --git a/fs/cifs/dir.c b/fs/cifs/dir.c index ae576fb..72d448b 100644 --- a/fs/cifs/dir.c +++ b/fs/cifs/dir.c @@ -105,8 +105,8 @@ cifs_bp_rename_retry: } rcu_read_unlock(); if (namelen != dfsplen || read_seqretry(&rename_lock, seq)) { - cERROR(1, "did not end path lookup where expected namelen is %d", - namelen); + cFYI(1, "did not end path lookup where expected. namelen=%d " + "dfsplen=%d", namelen, dfsplen); /* presumably this is only possible if racing with a rename of one of the parent directories (we can not lock the dentries above us to prevent this, but retrying should be harmless) */ diff --git a/fs/ext4/ext4_jbd2.h b/fs/ext4/ext4_jbd2.h index bb85757..5802fa1 100644 --- a/fs/ext4/ext4_jbd2.h +++ b/fs/ext4/ext4_jbd2.h @@ -289,10 +289,10 @@ static inline int ext4_should_order_data(struct inode *inode) static inline int ext4_should_writeback_data(struct inode *inode) { - if (!S_ISREG(inode->i_mode)) - return 0; if (EXT4_JOURNAL(inode) == NULL) return 1; + if (!S_ISREG(inode->i_mode)) + return 0; if (ext4_test_inode_flag(inode, EXT4_INODE_JOURNAL_DATA)) return 0; if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_WRITEBACK_DATA) diff --git a/fs/ext4/indirect.c b/fs/ext4/indirect.c index b8602cd..0962642 100644 --- a/fs/ext4/indirect.c +++ b/fs/ext4/indirect.c @@ -800,12 +800,17 @@ ssize_t ext4_ind_direct_IO(int rw, struct kiocb *iocb, } retry: - if (rw == READ && ext4_should_dioread_nolock(inode)) + if (rw == READ && ext4_should_dioread_nolock(inode)) { + if (unlikely(!list_empty(&ei->i_completed_io_list))) { + mutex_lock(&inode->i_mutex); + ext4_flush_completed_IO(inode); + mutex_unlock(&inode->i_mutex); + } ret = __blockdev_direct_IO(rw, iocb, inode, inode->i_sb->s_bdev, iov, offset, nr_segs, ext4_get_block, NULL, NULL, 0); - else { + } else { ret = blockdev_direct_IO(rw, iocb, inode, iov, offset, nr_segs, ext4_get_block); diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c index d47264c..c4da98a 100644 --- a/fs/ext4/inode.c +++ b/fs/ext4/inode.c @@ -120,6 +120,12 @@ void ext4_evict_inode(struct inode *inode) int err; trace_ext4_evict_inode(inode); + + mutex_lock(&inode->i_mutex); + ext4_flush_completed_IO(inode); + mutex_unlock(&inode->i_mutex); + ext4_ioend_wait(inode); + if (inode->i_nlink) { /* * When journalling data dirty buffers are tracked only in the @@ -983,6 +989,8 @@ static int ext4_journalled_write_end(struct file *file, from = pos & (PAGE_CACHE_SIZE - 1); to = from + len; + BUG_ON(!ext4_handle_valid(handle)); + if (copied < len) { if (!PageUptodate(page)) copied = 0; @@ -1283,7 +1291,12 @@ static int mpage_da_submit_io(struct mpage_da_data *mpd, else if (test_opt(inode->i_sb, MBLK_IO_SUBMIT)) err = ext4_bio_write_page(&io_submit, page, len, mpd->wbc); - else + else if (buffer_uninit(page_bufs)) { + ext4_set_bh_endio(page_bufs, inode); + err = block_write_full_page_endio(page, + noalloc_get_block_write, + mpd->wbc, ext4_end_io_buffer_write); + } else err = block_write_full_page(page, noalloc_get_block_write, mpd->wbc); @@ -1699,6 +1712,8 @@ static int __ext4_journalled_writepage(struct page *page, goto out; } + BUG_ON(!ext4_handle_valid(handle)); + ret = walk_page_buffers(handle, page_bufs, 0, len, NULL, do_journal_get_write_access); @@ -2668,8 +2683,15 @@ static void ext4_end_io_buffer_write(struct buffer_head *bh, int uptodate) goto out; } - io_end->flag = EXT4_IO_END_UNWRITTEN; + /* + * It may be over-defensive here to check EXT4_IO_END_UNWRITTEN now, + * but being more careful is always safe for the future change. + */ inode = io_end->inode; + if (!(io_end->flag & EXT4_IO_END_UNWRITTEN)) { + io_end->flag |= EXT4_IO_END_UNWRITTEN; + atomic_inc(&EXT4_I(inode)->i_aiodio_unwritten); + } /* Add the io_end to per-inode completed io list*/ spin_lock_irqsave(&EXT4_I(inode)->i_completed_io_lock, flags); diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c index 430c401..78839af 100644 --- a/fs/ext4/page-io.c +++ b/fs/ext4/page-io.c @@ -334,8 +334,10 @@ submit_and_retry: if ((io_end->num_io_pages >= MAX_IO_PAGES) && (io_end->pages[io_end->num_io_pages-1] != io_page)) goto submit_and_retry; - if (buffer_uninit(bh)) - io->io_end->flag |= EXT4_IO_END_UNWRITTEN; + if (buffer_uninit(bh) && !(io_end->flag & EXT4_IO_END_UNWRITTEN)) { + io_end->flag |= EXT4_IO_END_UNWRITTEN; + atomic_inc(&EXT4_I(inode)->i_aiodio_unwritten); + } io->io_end->size += bh->b_size; io->io_next_block++; ret = bio_add_page(io->io_bio, bh->b_page, bh->b_size, bh_offset(bh)); diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 4687fea..44d0c8d 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -919,7 +919,6 @@ static void ext4_i_callback(struct rcu_head *head) static void ext4_destroy_inode(struct inode *inode) { - ext4_ioend_wait(inode); if (!list_empty(&(EXT4_I(inode)->i_orphan))) { ext4_msg(inode->i_sb, KERN_ERR, "Inode %lu (%p): orphan list check failed!", diff --git a/fs/fat/dir.c b/fs/fat/dir.c index 4ad6473..5efbd5d 100644 --- a/fs/fat/dir.c +++ b/fs/fat/dir.c @@ -1231,7 +1231,7 @@ int fat_add_entries(struct inode *dir, void *slots, int nr_slots, struct super_block *sb = dir->i_sb; struct msdos_sb_info *sbi = MSDOS_SB(sb); struct buffer_head *bh, *prev, *bhs[3]; /* 32*slots (672bytes) */ - struct msdos_dir_entry *de; + struct msdos_dir_entry *uninitialized_var(de); int err, free_slots, i, nr_bhs; loff_t pos, i_pos; diff --git a/fs/fat/inode.c b/fs/fat/inode.c index 5942fec..1726d73 100644 --- a/fs/fat/inode.c +++ b/fs/fat/inode.c @@ -1188,9 +1188,9 @@ static int parse_options(struct super_block *sb, char *options, int is_vfat, out: /* UTF-8 doesn't provide FAT semantics */ if (!strcmp(opts->iocharset, "utf8")) { - fat_msg(sb, KERN_ERR, "utf8 is not a recommended IO charset" + fat_msg(sb, KERN_WARNING, "utf8 is not a recommended IO charset" " for FAT filesystems, filesystem will be " - "case sensitive!\n"); + "case sensitive!"); } /* If user doesn't specify allow_utime, it's initialized from dmask. */ @@ -1367,6 +1367,7 @@ int fat_fill_super(struct super_block *sb, void *data, int silent, int isvfat, sbi->free_clusters = -1; /* Don't know yet */ sbi->free_clus_valid = 0; sbi->prev_free = FAT_START_ENT; + sb->s_maxbytes = 0xffffffff; if (!sbi->fat_length && b->fat32_length) { struct fat_boot_fsinfo *fsinfo; @@ -1377,8 +1378,6 @@ int fat_fill_super(struct super_block *sb, void *data, int silent, int isvfat, sbi->fat_length = le32_to_cpu(b->fat32_length); sbi->root_cluster = le32_to_cpu(b->root_cluster); - sb->s_maxbytes = 0xffffffff; - /* MC - if info_sector is 0, don't multiply by 0 */ sbi->fsinfo_sector = le16_to_cpu(b->info_sector); if (sbi->fsinfo_sector == 0) diff --git a/fs/nfs/blocklayout/blocklayout.c b/fs/nfs/blocklayout/blocklayout.c index e56564d..9561c8f 100644 --- a/fs/nfs/blocklayout/blocklayout.c +++ b/fs/nfs/blocklayout/blocklayout.c @@ -36,6 +36,7 @@ #include <linux/namei.h> #include <linux/bio.h> /* struct bio */ #include <linux/buffer_head.h> /* various write calls */ +#include <linux/prefetch.h> #include "blocklayout.h" diff --git a/fs/nfs/callback.h b/fs/nfs/callback.h index b257383..07df5f1 100644 --- a/fs/nfs/callback.h +++ b/fs/nfs/callback.h @@ -38,6 +38,7 @@ enum nfs4_callback_opnum { struct cb_process_state { __be32 drc_status; struct nfs_client *clp; + int slotid; }; struct cb_compound_hdr_arg { @@ -166,7 +167,6 @@ extern unsigned nfs4_callback_layoutrecall( void *dummy, struct cb_process_state *cps); extern void nfs4_check_drain_bc_complete(struct nfs4_session *ses); -extern void nfs4_cb_take_slot(struct nfs_client *clp); struct cb_devicenotifyitem { uint32_t cbd_notify_type; diff --git a/fs/nfs/callback_proc.c b/fs/nfs/callback_proc.c index 74780f9..43926ad 100644 --- a/fs/nfs/callback_proc.c +++ b/fs/nfs/callback_proc.c @@ -348,7 +348,7 @@ validate_seqid(struct nfs4_slot_table *tbl, struct cb_sequenceargs * args) /* Normal */ if (likely(args->csa_sequenceid == slot->seq_nr + 1)) { slot->seq_nr++; - return htonl(NFS4_OK); + goto out_ok; } /* Replay */ @@ -367,11 +367,14 @@ validate_seqid(struct nfs4_slot_table *tbl, struct cb_sequenceargs * args) /* Wraparound */ if (args->csa_sequenceid == 1 && (slot->seq_nr + 1) == 0) { slot->seq_nr = 1; - return htonl(NFS4_OK); + goto out_ok; } /* Misordered request */ return htonl(NFS4ERR_SEQ_MISORDERED); +out_ok: + tbl->highest_used_slotid = args->csa_slotid; + return htonl(NFS4_OK); } /* @@ -433,26 +436,37 @@ __be32 nfs4_callback_sequence(struct cb_sequenceargs *args, struct cb_sequenceres *res, struct cb_process_state *cps) { + struct nfs4_slot_table *tbl; struct nfs_client *clp; int i; __be32 status = htonl(NFS4ERR_BADSESSION); - cps->clp = NULL; - clp = nfs4_find_client_sessionid(args->csa_addr, &args->csa_sessionid); if (clp == NULL) goto out; + tbl = &clp->cl_session->bc_slot_table; + + spin_lock(&tbl->slot_tbl_lock); /* state manager is resetting the session */ if (test_bit(NFS4_SESSION_DRAINING, &clp->cl_session->session_state)) { - status = NFS4ERR_DELAY; + spin_unlock(&tbl->slot_tbl_lock); + status = htonl(NFS4ERR_DELAY); + /* Return NFS4ERR_BADSESSION if we're draining the session + * in order to reset it. + */ + if (test_bit(NFS4CLNT_SESSION_RESET, &clp->cl_state)) + status = htonl(NFS4ERR_BADSESSION); goto out; } status = validate_seqid(&clp->cl_session->bc_slot_table, args); + spin_unlock(&tbl->slot_tbl_lock); if (status) goto out; + cps->slotid = args->csa_slotid; + /* * Check for pending referring calls. If a match is found, a * related callback was received before the response to the original @@ -469,7 +483,6 @@ __be32 nfs4_callback_sequence(struct cb_sequenceargs *args, res->csr_slotid = args->csa_slotid; res->csr_highestslotid = NFS41_BC_MAX_CALLBACKS - 1; res->csr_target_highestslotid = NFS41_BC_MAX_CALLBACKS - 1; - nfs4_cb_take_slot(clp); out: cps->clp = clp; /* put in nfs4_callback_compound */ diff --git a/fs/nfs/callback_xdr.c b/fs/nfs/callback_xdr.c index c6c86a7..918ad64 100644 --- a/fs/nfs/callback_xdr.c +++ b/fs/nfs/callback_xdr.c @@ -754,26 +754,15 @@ static void nfs4_callback_free_slot(struct nfs4_session *session) * Let the state manager know callback processing done. * A single slot, so highest used slotid is either 0 or -1 */ - tbl->highest_used_slotid--; + tbl->highest_used_slotid = -1; nfs4_check_drain_bc_complete(session); spin_unlock(&tbl->slot_tbl_lock); } -static void nfs4_cb_free_slot(struct nfs_client *clp) +static void nfs4_cb_free_slot(struct cb_process_state *cps) { - if (clp && clp->cl_session) - nfs4_callback_free_slot(clp->cl_session); -} - -/* A single slot, so highest used slotid is either 0 or -1 */ -void nfs4_cb_take_slot(struct nfs_client *clp) -{ - struct nfs4_slot_table *tbl = &clp->cl_session->bc_slot_table; - - spin_lock(&tbl->slot_tbl_lock); - tbl->highest_used_slotid++; - BUG_ON(tbl->highest_used_slotid != 0); - spin_unlock(&tbl->slot_tbl_lock); + if (cps->slotid != -1) + nfs4_callback_free_slot(cps->clp->cl_session); } #else /* CONFIG_NFS_V4_1 */ @@ -784,7 +773,7 @@ preprocess_nfs41_op(int nop, unsigned int op_nr, struct callback_op **op) return htonl(NFS4ERR_MINOR_VERS_MISMATCH); } -static void nfs4_cb_free_slot(struct nfs_client *clp) +static void nfs4_cb_free_slot(struct cb_process_state *cps) { } #endif /* CONFIG_NFS_V4_1 */ @@ -866,6 +855,7 @@ static __be32 nfs4_callback_compound(struct svc_rqst *rqstp, void *argp, void *r struct cb_process_state cps = { .drc_status = 0, .clp = NULL, + .slotid = -1, }; unsigned int nops = 0; @@ -906,7 +896,7 @@ static __be32 nfs4_callback_compound(struct svc_rqst *rqstp, void *argp, void *r *hdr_res.status = status; *hdr_res.nops = htonl(nops); - nfs4_cb_free_slot(cps.clp); + nfs4_cb_free_slot(&cps); nfs_put_client(cps.clp); dprintk("%s: done, status = %u\n", __func__, ntohl(status)); return rpc_success; diff --git a/fs/nfs/objlayout/objio_osd.c b/fs/nfs/objlayout/objio_osd.c index 9383ca7..d0cda12 100644 --- a/fs/nfs/objlayout/objio_osd.c +++ b/fs/nfs/objlayout/objio_osd.c @@ -479,7 +479,6 @@ static int _io_check(struct objio_state *ios, bool is_write) for (i = 0; i < ios->numdevs; i++) { struct osd_sense_info osi; struct osd_request *or = ios->per_dev[i].or; - unsigned dev; int ret; if (!or) @@ -500,9 +499,8 @@ static int _io_check(struct objio_state *ios, bool is_write) continue; /* we recovered */ } - dev = ios->per_dev[i].dev; - objlayout_io_set_result(&ios->ol_state, dev, - &ios->layout->comps[dev].oc_object_id, + objlayout_io_set_result(&ios->ol_state, i, + &ios->layout->comps[i].oc_object_id, osd_pri_2_pnfs_err(osi.osd_err_pri), ios->per_dev[i].offset, ios->per_dev[i].length, @@ -589,22 +587,19 @@ static void _calc_stripe_info(struct objio_state *ios, u64 file_offset, } static int _add_stripe_unit(struct objio_state *ios, unsigned *cur_pg, - unsigned pgbase, struct _objio_per_comp *per_dev, int cur_len, + unsigned pgbase, struct _objio_per_comp *per_dev, int len, gfp_t gfp_flags) { unsigned pg = *cur_pg; + int cur_len = len; struct request_queue *q = osd_request_queue(_io_od(ios, per_dev->dev)); - per_dev->length += cur_len; - if (per_dev->bio == NULL) { - unsigned stripes = ios->layout->num_comps / - ios->layout->mirrors_p1; - unsigned pages_in_stripe = stripes * + unsigned pages_in_stripe = ios->layout->group_width * (ios->layout->stripe_unit / PAGE_SIZE); unsigned bio_size = (ios->ol_state.nr_pages + pages_in_stripe) / - stripes; + ios->layout->group_width; if (BIO_MAX_PAGES_KMALLOC < bio_size) bio_size = BIO_MAX_PAGES_KMALLOC; @@ -632,6 +627,7 @@ static int _add_stripe_unit(struct objio_state *ios, unsigned *cur_pg, } BUG_ON(cur_len); + per_dev->length += len; *cur_pg = pg; return 0; } @@ -650,7 +646,7 @@ static int _prepare_one_group(struct objio_state *ios, u64 length, int ret = 0; while (length) { - struct _objio_per_comp *per_dev = &ios->per_dev[dev]; + struct _objio_per_comp *per_dev = &ios->per_dev[dev - first_dev]; unsigned cur_len, page_off = 0; if (!per_dev->length) { @@ -670,8 +666,8 @@ static int _prepare_one_group(struct objio_state *ios, u64 length, cur_len = stripe_unit; } - if (max_comp < dev) - max_comp = dev; + if (max_comp < dev - first_dev) + max_comp = dev - first_dev; } else { cur_len = stripe_unit; } @@ -806,7 +802,7 @@ static int _read_mirrors(struct objio_state *ios, unsigned cur_comp) struct _objio_per_comp *per_dev = &ios->per_dev[cur_comp]; unsigned dev = per_dev->dev; struct pnfs_osd_object_cred *cred = - &ios->layout->comps[dev]; + &ios->layout->comps[cur_comp]; struct osd_obj_id obj = { .partition = cred->oc_object_id.oid_partition_id, .id = cred->oc_object_id.oid_object_id, @@ -904,7 +900,7 @@ static int _write_mirrors(struct objio_state *ios, unsigned cur_comp) for (; cur_comp < last_comp; ++cur_comp, ++dev) { struct osd_request *or = NULL; struct pnfs_osd_object_cred *cred = - &ios->layout->comps[dev]; + &ios->layout->comps[cur_comp]; struct osd_obj_id obj = { .partition = cred->oc_object_id.oid_partition_id, .id = cred->oc_object_id.oid_object_id, diff --git a/fs/nfs/objlayout/pnfs_osd_xdr_cli.c b/fs/nfs/objlayout/pnfs_osd_xdr_cli.c index 16fc758..b3918f7 100644 --- a/fs/nfs/objlayout/pnfs_osd_xdr_cli.c +++ b/fs/nfs/objlayout/pnfs_osd_xdr_cli.c @@ -170,6 +170,9 @@ int pnfs_osd_xdr_decode_layout_map(struct pnfs_osd_layout *layout, p = _osd_xdr_decode_data_map(p, &layout->olo_map); layout->olo_comps_index = be32_to_cpup(p++); layout->olo_num_comps = be32_to_cpup(p++); + dprintk("%s: olo_comps_index=%d olo_num_comps=%d\n", __func__, + layout->olo_comps_index, layout->olo_num_comps); + iter->total_comps = layout->olo_num_comps; return 0; } diff --git a/include/asm-generic/memory_model.h b/include/asm-generic/memory_model.h index fb2d63f..aea9e45 100644 --- a/include/asm-generic/memory_model.h +++ b/include/asm-generic/memory_model.h @@ -39,7 +39,7 @@ }) #define __page_to_pfn(pg) \ -({ struct page *__pg = (pg); \ +({ const struct page *__pg = (pg); \ struct pglist_data *__pgdat = NODE_DATA(page_to_nid(__pg)); \ (unsigned long)(__pg - __pgdat->node_mem_map) + \ __pgdat->node_start_pfn; \ @@ -57,7 +57,7 @@ * section[i].section_mem_map == mem_map's address - start_pfn; */ #define __page_to_pfn(pg) \ -({ struct page *__pg = (pg); \ +({ const struct page *__pg = (pg); \ int __sec = page_to_section(__pg); \ (unsigned long)(__pg - __section_mem_map_addr(__nr_to_section(__sec))); \ }) diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 6395692..32f0076 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -125,7 +125,11 @@ enum rq_flag_bits { __REQ_SYNC, /* request is sync (sync write or read) */ __REQ_META, /* metadata io request */ __REQ_DISCARD, /* request to discard sectors */ + __REQ_SECURE, /* secure discard (used with __REQ_DISCARD) */ + __REQ_NOIDLE, /* don't anticipate more IO after this one */ + __REQ_FUA, /* forced unit access */ + __REQ_FLUSH, /* request for cache flush */ /* bio only flags */ __REQ_RAHEAD, /* read ahead, can fail anytime */ @@ -135,7 +139,6 @@ enum rq_flag_bits { /* request only flags */ __REQ_SORTED, /* elevator knows about this request */ __REQ_SOFTBARRIER, /* may not be passed by ioscheduler */ - __REQ_FUA, /* forced unit access */ __REQ_NOMERGE, /* don't touch this for merging */ __REQ_STARTED, /* drive already may have started this one */ __REQ_DONTPREP, /* don't call prep for this one */ @@ -146,11 +149,9 @@ enum rq_flag_bits { __REQ_PREEMPT, /* set for "ide_preempt" requests */ __REQ_ALLOCED, /* request came from our alloc pool */ __REQ_COPY_USER, /* contains copies of user pages */ - __REQ_FLUSH, /* request for cache flush */ __REQ_FLUSH_SEQ, /* request for flush sequence */ __REQ_IO_STAT, /* account I/O stat */ __REQ_MIXED_MERGE, /* merge of different types, fail separately */ - __REQ_SECURE, /* secure discard (used with __REQ_DISCARD) */ __REQ_NR_BITS, /* stops here */ }; diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 0e67c45..84b15d5 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -30,6 +30,7 @@ struct request_pm_state; struct blk_trace; struct request; struct sg_io_hdr; +struct bsg_job; #define BLKDEV_MIN_RQ 4 #define BLKDEV_MAX_RQ 128 /* Default maximum */ @@ -117,6 +118,7 @@ struct request { struct { unsigned int seq; struct list_head list; + rq_end_io_fn *saved_end_io; } flush; }; @@ -209,6 +211,7 @@ typedef int (merge_bvec_fn) (struct request_queue *, struct bvec_merge_data *, typedef void (softirq_done_fn)(struct request *); typedef int (dma_drain_needed_fn)(struct request *); typedef int (lld_busy_fn) (struct request_queue *q); +typedef int (bsg_job_fn) (struct bsg_job *); enum blk_eh_timer_return { BLK_EH_NOT_HANDLED, @@ -375,6 +378,8 @@ struct request_queue { struct mutex sysfs_lock; #if defined(CONFIG_BLK_DEV_BSG) + bsg_job_fn *bsg_job_fn; + int bsg_job_size; struct bsg_class_device bsg_dev; #endif diff --git a/include/linux/blktrace_api.h b/include/linux/blktrace_api.h index 8c7c2de..8e9e4bc 100644 --- a/include/linux/blktrace_api.h +++ b/include/linux/blktrace_api.h @@ -14,7 +14,7 @@ enum blktrace_cat { BLK_TC_READ = 1 << 0, /* reads */ BLK_TC_WRITE = 1 << 1, /* writes */ - BLK_TC_BARRIER = 1 << 2, /* barrier */ + BLK_TC_FLUSH = 1 << 2, /* flush */ BLK_TC_SYNC = 1 << 3, /* sync IO */ BLK_TC_SYNCIO = BLK_TC_SYNC, BLK_TC_QUEUE = 1 << 4, /* queueing/merging */ @@ -28,8 +28,9 @@ enum blktrace_cat { BLK_TC_META = 1 << 12, /* metadata */ BLK_TC_DISCARD = 1 << 13, /* discard requests */ BLK_TC_DRV_DATA = 1 << 14, /* binary per-driver data */ + BLK_TC_FUA = 1 << 15, /* fua requests */ - BLK_TC_END = 1 << 15, /* only 16-bits, reminder */ + BLK_TC_END = 1 << 15, /* we've run out of bits! */ }; #define BLK_TC_SHIFT (16) diff --git a/include/linux/bsg-lib.h b/include/linux/bsg-lib.h new file mode 100644 index 0000000..f55ab8c --- /dev/null +++ b/include/linux/bsg-lib.h @@ -0,0 +1,73 @@ +/* + * BSG helper library + * + * Copyright (C) 2008 James Smart, Emulex Corporation + * Copyright (C) 2011 Red Hat, Inc. All rights reserved. + * Copyright (C) 2011 Mike Christie + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + * + */ +#ifndef _BLK_BSG_ +#define _BLK_BSG_ + +#include <linux/blkdev.h> + +struct request; +struct device; +struct scatterlist; +struct request_queue; + +struct bsg_buffer { + unsigned int payload_len; + int sg_cnt; + struct scatterlist *sg_list; +}; + +struct bsg_job { + struct device *dev; + struct request *req; + + /* Transport/driver specific request/reply structs */ + void *request; + void *reply; + + unsigned int request_len; + unsigned int reply_len; + /* + * On entry : reply_len indicates the buffer size allocated for + * the reply. + * + * Upon completion : the message handler must set reply_len + * to indicates the size of the reply to be returned to the + * caller. + */ + + /* DMA payloads for the request/response */ + struct bsg_buffer request_payload; + struct bsg_buffer reply_payload; + + void *dd_data; /* Used for driver-specific storage */ +}; + +void bsg_job_done(struct bsg_job *job, int result, + unsigned int reply_payload_rcv_len); +int bsg_setup_queue(struct device *dev, struct request_queue *q, char *name, + bsg_job_fn *job_fn, int dd_job_size); +void bsg_request_fn(struct request_queue *q); +void bsg_remove_queue(struct request_queue *q); +void bsg_goose_queue(struct request_queue *q); + +#endif diff --git a/include/linux/hash.h b/include/linux/hash.h index 06d25c1..b80506b 100644 --- a/include/linux/hash.h +++ b/include/linux/hash.h @@ -63,7 +63,7 @@ static inline u32 hash_32(u32 val, unsigned int bits) return hash >> (32 - bits); } -static inline unsigned long hash_ptr(void *ptr, unsigned int bits) +static inline unsigned long hash_ptr(const void *ptr, unsigned int bits) { return hash_long((unsigned long)ptr, bits); } diff --git a/include/linux/loop.h b/include/linux/loop.h index 66c194e..683d698 100644 --- a/include/linux/loop.h +++ b/include/linux/loop.h @@ -64,7 +64,6 @@ struct loop_device { struct request_queue *lo_queue; struct gendisk *lo_disk; - struct list_head lo_list; }; #endif /* __KERNEL__ */ @@ -161,4 +160,8 @@ int loop_unregister_transfer(int number); #define LOOP_CHANGE_FD 0x4C06 #define LOOP_SET_CAPACITY 0x4C07 +/* /dev/loop-control interface */ +#define LOOP_CTL_ADD 0x4C80 +#define LOOP_CTL_REMOVE 0x4C81 +#define LOOP_CTL_GET_FREE 0x4C82 #endif diff --git a/include/linux/miscdevice.h b/include/linux/miscdevice.h index 18fd130..c309b1e 100644 --- a/include/linux/miscdevice.h +++ b/include/linux/miscdevice.h @@ -40,6 +40,7 @@ #define BTRFS_MINOR 234 #define AUTOFS_MINOR 235 #define MAPPER_CTRL_MINOR 236 +#define LOOP_CTRL_MINOR 237 #define MISC_DYNAMIC_MINOR 255 struct device; diff --git a/include/linux/mm.h b/include/linux/mm.h index fd599f4..7438071 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -685,7 +685,7 @@ static inline void set_page_section(struct page *page, unsigned long section) page->flags |= (section & SECTIONS_MASK) << SECTIONS_PGSHIFT; } -static inline unsigned long page_to_section(struct page *page) +static inline unsigned long page_to_section(const struct page *page) { return (page->flags >> SECTIONS_PGSHIFT) & SECTIONS_MASK; } @@ -720,7 +720,7 @@ static inline void set_page_links(struct page *page, enum zone_type zone, static __always_inline void *lowmem_page_address(const struct page *page) { - return __va(PFN_PHYS(page_to_pfn((struct page *)page))); + return __va(PFN_PHYS(page_to_pfn(page))); } #if defined(CONFIG_HIGHMEM) && !defined(WANT_PAGE_VIRTUAL) @@ -737,7 +737,7 @@ static __always_inline void *lowmem_page_address(const struct page *page) #endif #if defined(HASHED_PAGE_VIRTUAL) -void *page_address(struct page *page); +void *page_address(const struct page *page); void set_page_address(struct page *page, void *virtual); void page_address_init(void); #endif diff --git a/include/linux/pci.h b/include/linux/pci.h index f27893b..8c230cb 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -251,7 +251,8 @@ struct pci_dev { u8 revision; /* PCI revision, low byte of class word */ u8 hdr_type; /* PCI header type (`multi' flag masked out) */ u8 pcie_cap; /* PCI-E capability offset */ - u8 pcie_type; /* PCI-E device/port type */ + u8 pcie_type:4; /* PCI-E device/port type */ + u8 pcie_mpss:3; /* PCI-E Max Payload Size Supported */ u8 rom_base_reg; /* which config register controls the ROM */ u8 pin; /* which interrupt pin this device uses */ @@ -617,6 +618,16 @@ struct pci_driver { /* these external functions are only available when PCI support is enabled */ #ifdef CONFIG_PCI +extern void pcie_bus_configure_settings(struct pci_bus *bus, u8 smpss); + +enum pcie_bus_config_types { + PCIE_BUS_PERFORMANCE, + PCIE_BUS_SAFE, + PCIE_BUS_PEER2PEER, +}; + +extern enum pcie_bus_config_types pcie_bus_config; + extern struct bus_type pci_bus_type; /* Do NOT directly access these two variables, unless you are arch specific pci @@ -796,10 +807,13 @@ int pcix_get_mmrbc(struct pci_dev *dev); int pcix_set_mmrbc(struct pci_dev *dev, int mmrbc); int pcie_get_readrq(struct pci_dev *dev); int pcie_set_readrq(struct pci_dev *dev, int rq); +int pcie_get_mps(struct pci_dev *dev); +int pcie_set_mps(struct pci_dev *dev, int mps); int __pci_reset_function(struct pci_dev *dev); int pci_reset_function(struct pci_dev *dev); void pci_update_resource(struct pci_dev *dev, int resno); int __must_check pci_assign_resource(struct pci_dev *dev, int i); +int __must_check pci_reassign_resource(struct pci_dev *dev, int i, resource_size_t add_size, resource_size_t align); int pci_select_bars(struct pci_dev *dev, unsigned long flags); /* ROM control related routines */ diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h index 21097cb..f9ec173 100644 --- a/include/linux/pm_domain.h +++ b/include/linux/pm_domain.h @@ -72,8 +72,6 @@ extern int pm_genpd_remove_subdomain(struct generic_pm_domain *genpd, extern void pm_genpd_init(struct generic_pm_domain *genpd, struct dev_power_governor *gov, bool is_off); extern int pm_genpd_poweron(struct generic_pm_domain *genpd); -extern void pm_genpd_poweroff_unused(void); -extern void genpd_queue_power_off_work(struct generic_pm_domain *genpd); #else static inline int pm_genpd_add_device(struct generic_pm_domain *genpd, struct device *dev) @@ -101,8 +99,14 @@ static inline int pm_genpd_poweron(struct generic_pm_domain *genpd) { return -ENOSYS; } -static inline void pm_genpd_poweroff_unused(void) {} +#endif + +#ifdef CONFIG_PM_GENERIC_DOMAINS_RUNTIME +extern void genpd_queue_power_off_work(struct generic_pm_domain *genpd); +extern void pm_genpd_poweroff_unused(void); +#else static inline void genpd_queue_power_off_work(struct generic_pm_domain *gpd) {} +static inline void pm_genpd_poweroff_unused(void) {} #endif #endif /* _LINUX_PM_DOMAIN_H */ diff --git a/include/trace/events/block.h b/include/trace/events/block.h index bf36654..05c5e61 100644 --- a/include/trace/events/block.h +++ b/include/trace/events/block.h @@ -8,6 +8,8 @@ #include <linux/blkdev.h> #include <linux/tracepoint.h> +#define RWBS_LEN 8 + DECLARE_EVENT_CLASS(block_rq_with_error, TP_PROTO(struct request_queue *q, struct request *rq), @@ -19,7 +21,7 @@ DECLARE_EVENT_CLASS(block_rq_with_error, __field( sector_t, sector ) __field( unsigned int, nr_sector ) __field( int, errors ) - __array( char, rwbs, 6 ) + __array( char, rwbs, RWBS_LEN ) __dynamic_array( char, cmd, blk_cmd_buf_len(rq) ) ), @@ -104,7 +106,7 @@ DECLARE_EVENT_CLASS(block_rq, __field( sector_t, sector ) __field( unsigned int, nr_sector ) __field( unsigned int, bytes ) - __array( char, rwbs, 6 ) + __array( char, rwbs, RWBS_LEN ) __array( char, comm, TASK_COMM_LEN ) __dynamic_array( char, cmd, blk_cmd_buf_len(rq) ) ), @@ -183,7 +185,7 @@ TRACE_EVENT(block_bio_bounce, __field( dev_t, dev ) __field( sector_t, sector ) __field( unsigned int, nr_sector ) - __array( char, rwbs, 6 ) + __array( char, rwbs, RWBS_LEN ) __array( char, comm, TASK_COMM_LEN ) ), @@ -222,7 +224,7 @@ TRACE_EVENT(block_bio_complete, __field( sector_t, sector ) __field( unsigned, nr_sector ) __field( int, error ) - __array( char, rwbs, 6 ) + __array( char, rwbs, RWBS_LEN) ), TP_fast_assign( @@ -249,7 +251,7 @@ DECLARE_EVENT_CLASS(block_bio, __field( dev_t, dev ) __field( sector_t, sector ) __field( unsigned int, nr_sector ) - __array( char, rwbs, 6 ) + __array( char, rwbs, RWBS_LEN ) __array( char, comm, TASK_COMM_LEN ) ), @@ -321,7 +323,7 @@ DECLARE_EVENT_CLASS(block_get_rq, __field( dev_t, dev ) __field( sector_t, sector ) __field( unsigned int, nr_sector ) - __array( char, rwbs, 6 ) + __array( char, rwbs, RWBS_LEN ) __array( char, comm, TASK_COMM_LEN ) ), @@ -456,7 +458,7 @@ TRACE_EVENT(block_split, __field( dev_t, dev ) __field( sector_t, sector ) __field( sector_t, new_sector ) - __array( char, rwbs, 6 ) + __array( char, rwbs, RWBS_LEN ) __array( char, comm, TASK_COMM_LEN ) ), @@ -498,7 +500,7 @@ TRACE_EVENT(block_bio_remap, __field( unsigned int, nr_sector ) __field( dev_t, old_dev ) __field( sector_t, old_sector ) - __array( char, rwbs, 6 ) + __array( char, rwbs, RWBS_LEN) ), TP_fast_assign( @@ -542,7 +544,7 @@ TRACE_EVENT(block_rq_remap, __field( unsigned int, nr_sector ) __field( dev_t, old_dev ) __field( sector_t, old_sector ) - __array( char, rwbs, 6 ) + __array( char, rwbs, RWBS_LEN) ), TP_fast_assign( diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c index cb65d03..039b889 100644 --- a/kernel/irq/irqdesc.c +++ b/kernel/irq/irqdesc.c @@ -344,6 +344,7 @@ EXPORT_SYMBOL_GPL(irq_free_descs); * @from: Start the search from this irq number * @cnt: Number of consecutive irqs to allocate. * @node: Preferred node on which the irq descriptor should be allocated + * @owner: Owning module (can be NULL) * * Returns the first irq number or error code */ diff --git a/kernel/power/Kconfig b/kernel/power/Kconfig index b1914cb9..3744c59 100644 --- a/kernel/power/Kconfig +++ b/kernel/power/Kconfig @@ -231,3 +231,7 @@ config PM_CLK config PM_GENERIC_DOMAINS bool depends on PM + +config PM_GENERIC_DOMAINS_RUNTIME + def_bool y + depends on PM_RUNTIME && PM_GENERIC_DOMAINS diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index 6957aa2..7c910a5 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -206,6 +206,8 @@ static void __blk_add_trace(struct blk_trace *bt, sector_t sector, int bytes, what |= MASK_TC_BIT(rw, RAHEAD); what |= MASK_TC_BIT(rw, META); what |= MASK_TC_BIT(rw, DISCARD); + what |= MASK_TC_BIT(rw, FLUSH); + what |= MASK_TC_BIT(rw, FUA); pid = tsk->pid; if (act_log_check(bt, what, sector, pid)) @@ -1054,6 +1056,9 @@ static void fill_rwbs(char *rwbs, const struct blk_io_trace *t) goto out; } + if (tc & BLK_TC_FLUSH) + rwbs[i++] = 'F'; + if (tc & BLK_TC_DISCARD) rwbs[i++] = 'D'; else if (tc & BLK_TC_WRITE) @@ -1063,10 +1068,10 @@ static void fill_rwbs(char *rwbs, const struct blk_io_trace *t) else rwbs[i++] = 'N'; + if (tc & BLK_TC_FUA) + rwbs[i++] = 'F'; if (tc & BLK_TC_AHEAD) rwbs[i++] = 'A'; - if (tc & BLK_TC_BARRIER) - rwbs[i++] = 'B'; if (tc & BLK_TC_SYNC) rwbs[i++] = 'S'; if (tc & BLK_TC_META) @@ -1132,7 +1137,7 @@ typedef int (blk_log_action_t) (struct trace_iterator *iter, const char *act); static int blk_log_action_classic(struct trace_iterator *iter, const char *act) { - char rwbs[6]; + char rwbs[RWBS_LEN]; unsigned long long ts = iter->ts; unsigned long nsec_rem = do_div(ts, NSEC_PER_SEC); unsigned secs = (unsigned long)ts; @@ -1148,7 +1153,7 @@ static int blk_log_action_classic(struct trace_iterator *iter, const char *act) static int blk_log_action(struct trace_iterator *iter, const char *act) { - char rwbs[6]; + char rwbs[RWBS_LEN]; const struct blk_io_trace *t = te_blk_io_trace(iter->ent); fill_rwbs(rwbs, t); @@ -1561,7 +1566,7 @@ static const struct { } mask_maps[] = { { BLK_TC_READ, "read" }, { BLK_TC_WRITE, "write" }, - { BLK_TC_BARRIER, "barrier" }, + { BLK_TC_FLUSH, "flush" }, { BLK_TC_SYNC, "sync" }, { BLK_TC_QUEUE, "queue" }, { BLK_TC_REQUEUE, "requeue" }, @@ -1573,6 +1578,7 @@ static const struct { { BLK_TC_META, "meta" }, { BLK_TC_DISCARD, "discard" }, { BLK_TC_DRV_DATA, "drv_data" }, + { BLK_TC_FUA, "fua" }, }; static int blk_trace_str2mask(const char *str) @@ -1788,6 +1794,9 @@ void blk_fill_rwbs(char *rwbs, u32 rw, int bytes) { int i = 0; + if (rw & REQ_FLUSH) + rwbs[i++] = 'F'; + if (rw & WRITE) rwbs[i++] = 'W'; else if (rw & REQ_DISCARD) @@ -1797,6 +1806,8 @@ void blk_fill_rwbs(char *rwbs, u32 rw, int bytes) else rwbs[i++] = 'N'; + if (rw & REQ_FUA) + rwbs[i++] = 'F'; if (rw & REQ_RAHEAD) rwbs[i++] = 'A'; if (rw & REQ_SYNC) diff --git a/mm/highmem.c b/mm/highmem.c index 693394d..5ef672c 100644 --- a/mm/highmem.c +++ b/mm/highmem.c @@ -326,7 +326,7 @@ static struct page_address_slot { spinlock_t lock; /* Protect this bucket's list */ } ____cacheline_aligned_in_smp page_address_htable[1<<PA_HASH_ORDER]; -static struct page_address_slot *page_slot(struct page *page) +static struct page_address_slot *page_slot(const struct page *page) { return &page_address_htable[hash_ptr(page, PA_HASH_ORDER)]; } @@ -337,7 +337,7 @@ static struct page_address_slot *page_slot(struct page *page) * * Returns the page's virtual address. */ -void *page_address(struct page *page) +void *page_address(const struct page *page) { unsigned long flags; void *ret; diff --git a/sound/aoa/fabrics/layout.c b/sound/aoa/fabrics/layout.c index 3fd1a7e..552b97a 100644 --- a/sound/aoa/fabrics/layout.c +++ b/sound/aoa/fabrics/layout.c @@ -1073,10 +1073,10 @@ static int aoa_fabric_layout_probe(struct soundbus_dev *sdev) sdev->pcmid = -1; list_del(&ldev->list); layouts_list_items--; + kfree(ldev); outnodev: of_node_put(sound); layout_device = NULL; - kfree(ldev); return -ENODEV; } diff --git a/sound/pci/ac97/ac97_patch.c b/sound/pci/ac97/ac97_patch.c index 200c9a1..a872d0a 100644 --- a/sound/pci/ac97/ac97_patch.c +++ b/sound/pci/ac97/ac97_patch.c @@ -1909,6 +1909,7 @@ static unsigned int ad1981_jacks_whitelist[] = { 0x103c0944, /* HP nc6220 */ 0x103c0934, /* HP nc8220 */ 0x103c006d, /* HP nx9105 */ + 0x103c300d, /* HP Compaq dc5100 SFF(PT003AW) */ 0x17340088, /* FSC Scenic-W */ 0 /* end */ }; diff --git a/sound/pci/hda/alc268_quirks.c b/sound/pci/hda/alc268_quirks.c index be58bf2..2e5876c 100644 --- a/sound/pci/hda/alc268_quirks.c +++ b/sound/pci/hda/alc268_quirks.c @@ -476,8 +476,8 @@ static const struct snd_pci_quirk alc268_ssid_cfg_tbl[] = { static const struct alc_config_preset alc268_presets[] = { [ALC267_QUANTA_IL1] = { - .mixers = { alc267_quanta_il1_mixer, alc268_beep_mixer, - alc268_capture_nosrc_mixer }, + .mixers = { alc267_quanta_il1_mixer, alc268_beep_mixer }, + .cap_mixer = alc268_capture_nosrc_mixer, .init_verbs = { alc268_base_init_verbs, alc268_eapd_verbs, alc267_quanta_il1_verbs }, .num_dacs = ARRAY_SIZE(alc268_dac_nids), @@ -492,8 +492,8 @@ static const struct alc_config_preset alc268_presets[] = { .init_hook = alc_inithook, }, [ALC268_3ST] = { - .mixers = { alc268_base_mixer, alc268_capture_alt_mixer, - alc268_beep_mixer }, + .mixers = { alc268_base_mixer, alc268_beep_mixer }, + .cap_mixer = alc268_capture_alt_mixer, .init_verbs = { alc268_base_init_verbs }, .num_dacs = ARRAY_SIZE(alc268_dac_nids), .dac_nids = alc268_dac_nids, @@ -507,8 +507,8 @@ static const struct alc_config_preset alc268_presets[] = { .input_mux = &alc268_capture_source, }, [ALC268_TOSHIBA] = { - .mixers = { alc268_toshiba_mixer, alc268_capture_alt_mixer, - alc268_beep_mixer }, + .mixers = { alc268_toshiba_mixer, alc268_beep_mixer }, + .cap_mixer = alc268_capture_alt_mixer, .init_verbs = { alc268_base_init_verbs, alc268_eapd_verbs, alc268_toshiba_verbs }, .num_dacs = ARRAY_SIZE(alc268_dac_nids), @@ -525,8 +525,8 @@ static const struct alc_config_preset alc268_presets[] = { .init_hook = alc_inithook, }, [ALC268_ACER] = { - .mixers = { alc268_acer_mixer, alc268_capture_alt_mixer, - alc268_beep_mixer }, + .mixers = { alc268_acer_mixer, alc268_beep_mixer }, + .cap_mixer = alc268_capture_alt_mixer, .init_verbs = { alc268_base_init_verbs, alc268_eapd_verbs, alc268_acer_verbs }, .num_dacs = ARRAY_SIZE(alc268_dac_nids), @@ -543,8 +543,8 @@ static const struct alc_config_preset alc268_presets[] = { .init_hook = alc_inithook, }, [ALC268_ACER_DMIC] = { - .mixers = { alc268_acer_dmic_mixer, alc268_capture_alt_mixer, - alc268_beep_mixer }, + .mixers = { alc268_acer_dmic_mixer, alc268_beep_mixer }, + .cap_mixer = alc268_capture_alt_mixer, .init_verbs = { alc268_base_init_verbs, alc268_eapd_verbs, alc268_acer_verbs }, .num_dacs = ARRAY_SIZE(alc268_dac_nids), @@ -561,9 +561,8 @@ static const struct alc_config_preset alc268_presets[] = { .init_hook = alc_inithook, }, [ALC268_ACER_ASPIRE_ONE] = { - .mixers = { alc268_acer_aspire_one_mixer, - alc268_beep_mixer, - alc268_capture_nosrc_mixer }, + .mixers = { alc268_acer_aspire_one_mixer, alc268_beep_mixer}, + .cap_mixer = alc268_capture_nosrc_mixer, .init_verbs = { alc268_base_init_verbs, alc268_eapd_verbs, alc268_acer_aspire_one_verbs }, .num_dacs = ARRAY_SIZE(alc268_dac_nids), @@ -579,8 +578,8 @@ static const struct alc_config_preset alc268_presets[] = { .init_hook = alc_inithook, }, [ALC268_DELL] = { - .mixers = { alc268_dell_mixer, alc268_beep_mixer, - alc268_capture_nosrc_mixer }, + .mixers = { alc268_dell_mixer, alc268_beep_mixer}, + .cap_mixer = alc268_capture_nosrc_mixer, .init_verbs = { alc268_base_init_verbs, alc268_eapd_verbs, alc268_dell_verbs }, .num_dacs = ARRAY_SIZE(alc268_dac_nids), @@ -596,8 +595,8 @@ static const struct alc_config_preset alc268_presets[] = { .init_hook = alc_inithook, }, [ALC268_ZEPTO] = { - .mixers = { alc268_base_mixer, alc268_capture_alt_mixer, - alc268_beep_mixer }, + .mixers = { alc268_base_mixer, alc268_beep_mixer }, + .cap_mixer = alc268_capture_alt_mixer, .init_verbs = { alc268_base_init_verbs, alc268_eapd_verbs, alc268_toshiba_verbs }, .num_dacs = ARRAY_SIZE(alc268_dac_nids), @@ -616,7 +615,8 @@ static const struct alc_config_preset alc268_presets[] = { }, #ifdef CONFIG_SND_DEBUG [ALC268_TEST] = { - .mixers = { alc268_test_mixer, alc268_capture_mixer }, + .mixers = { alc268_test_mixer }, + .cap_mixer = alc268_capture_mixer, .init_verbs = { alc268_base_init_verbs, alc268_eapd_verbs, alc268_volume_init_verbs, alc268_beep_init_verbs }, diff --git a/sound/pci/hda/hda_eld.c b/sound/pci/hda/hda_eld.c index 28ce17d..c34f730 100644 --- a/sound/pci/hda/hda_eld.c +++ b/sound/pci/hda/hda_eld.c @@ -144,25 +144,17 @@ static int cea_sampling_frequencies[8] = { SNDRV_PCM_RATE_192000, /* 7: 192000Hz */ }; -static unsigned char hdmi_get_eld_byte(struct hda_codec *codec, hda_nid_t nid, +static unsigned int hdmi_get_eld_data(struct hda_codec *codec, hda_nid_t nid, int byte_index) { unsigned int val; val = snd_hda_codec_read(codec, nid, 0, AC_VERB_GET_HDMI_ELDD, byte_index); - #ifdef BE_PARANOID printk(KERN_INFO "HDMI: ELD data byte %d: 0x%x\n", byte_index, val); #endif - - if ((val & AC_ELDD_ELD_VALID) == 0) { - snd_printd(KERN_INFO "HDMI: invalid ELD data byte %d\n", - byte_index); - val = 0; - } - - return val & AC_ELDD_ELD_DATA; + return val; } #define GRAB_BITS(buf, byte, lowbit, bits) \ @@ -344,11 +336,26 @@ int snd_hdmi_get_eld(struct hdmi_eld *eld, if (!buf) return -ENOMEM; - for (i = 0; i < size; i++) - buf[i] = hdmi_get_eld_byte(codec, nid, i); + for (i = 0; i < size; i++) { + unsigned int val = hdmi_get_eld_data(codec, nid, i); + if (!(val & AC_ELDD_ELD_VALID)) { + if (!i) { + snd_printd(KERN_INFO + "HDMI: invalid ELD data\n"); + ret = -EINVAL; + goto error; + } + snd_printd(KERN_INFO + "HDMI: invalid ELD data byte %d\n", i); + val = 0; + } else + val &= AC_ELDD_ELD_DATA; + buf[i] = val; + } ret = hdmi_update_eld(eld, buf, size); +error: kfree(buf); return ret; } diff --git a/sound/pci/hda/patch_cirrus.c b/sound/pci/hda/patch_cirrus.c index 47d6ffc..d6c93d9 100644 --- a/sound/pci/hda/patch_cirrus.c +++ b/sound/pci/hda/patch_cirrus.c @@ -375,7 +375,7 @@ static int is_ext_mic(struct hda_codec *codec, unsigned int idx) static hda_nid_t get_adc(struct hda_codec *codec, hda_nid_t pin, unsigned int *idxp) { - int i; + int i, idx; hda_nid_t nid; nid = codec->start_nid; @@ -384,9 +384,11 @@ static hda_nid_t get_adc(struct hda_codec *codec, hda_nid_t pin, type = get_wcaps_type(get_wcaps(codec, nid)); if (type != AC_WID_AUD_IN) continue; - *idxp = snd_hda_get_conn_index(codec, nid, pin, false); - if (*idxp >= 0) + idx = snd_hda_get_conn_index(codec, nid, pin, false); + if (idx >= 0) { + *idxp = idx; return nid; + } } return 0; } diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c index 9a1aa09..fcb11af 100644 --- a/sound/pci/hda/patch_realtek.c +++ b/sound/pci/hda/patch_realtek.c @@ -1784,6 +1784,7 @@ static const char * const alc_slave_vols[] = { "Speaker Playback Volume", "Mono Playback Volume", "Line-Out Playback Volume", + "PCM Playback Volume", NULL, }; @@ -1798,6 +1799,7 @@ static const char * const alc_slave_sws[] = { "Mono Playback Switch", "IEC958 Playback Switch", "Line-Out Playback Switch", + "PCM Playback Switch", NULL, }; diff --git a/sound/usb/caiaq/audio.c b/sound/usb/caiaq/audio.c index aa52b3e..2cf87f5 100644 --- a/sound/usb/caiaq/audio.c +++ b/sound/usb/caiaq/audio.c @@ -139,8 +139,12 @@ static void stream_stop(struct snd_usb_caiaqdev *dev) for (i = 0; i < N_URBS; i++) { usb_kill_urb(dev->data_urbs_in[i]); - usb_kill_urb(dev->data_urbs_out[i]); + + if (test_bit(i, &dev->outurb_active_mask)) + usb_kill_urb(dev->data_urbs_out[i]); } + + dev->outurb_active_mask = 0; } static int snd_usb_caiaq_substream_open(struct snd_pcm_substream *substream) @@ -612,8 +616,8 @@ static void read_completed(struct urb *urb) { struct snd_usb_caiaq_cb_info *info = urb->context; struct snd_usb_caiaqdev *dev; - struct urb *out; - int frame, len, send_it = 0, outframe = 0; + struct urb *out = NULL; + int i, frame, len, send_it = 0, outframe = 0; size_t offset = 0; if (urb->status || !info) @@ -624,7 +628,17 @@ static void read_completed(struct urb *urb) if (!dev->streaming) return; - out = dev->data_urbs_out[info->index]; + /* find an unused output urb that is unused */ + for (i = 0; i < N_URBS; i++) + if (test_and_set_bit(i, &dev->outurb_active_mask) == 0) { + out = dev->data_urbs_out[i]; + break; + } + + if (!out) { + log("Unable to find an output urb to use\n"); + goto requeue; + } /* read the recently received packet and send back one which has * the same layout */ @@ -655,8 +669,12 @@ static void read_completed(struct urb *urb) out->number_of_packets = outframe; out->transfer_flags = URB_ISO_ASAP; usb_submit_urb(out, GFP_ATOMIC); + } else { + struct snd_usb_caiaq_cb_info *oinfo = out->context; + clear_bit(oinfo->index, &dev->outurb_active_mask); } +requeue: /* re-submit inbound urb */ for (frame = 0; frame < FRAMES_PER_URB; frame++) { urb->iso_frame_desc[frame].offset = BYTES_PER_FRAME * frame; @@ -678,6 +696,8 @@ static void write_completed(struct urb *urb) dev->output_running = 1; wake_up(&dev->prepare_wait_queue); } + + clear_bit(info->index, &dev->outurb_active_mask); } static struct urb **alloc_urbs(struct snd_usb_caiaqdev *dev, int dir, int *ret) @@ -829,6 +849,9 @@ int snd_usb_caiaq_audio_init(struct snd_usb_caiaqdev *dev) if (!dev->data_cb_info) return -ENOMEM; + dev->outurb_active_mask = 0; + BUILD_BUG_ON(N_URBS > (sizeof(dev->outurb_active_mask) * 8)); + for (i = 0; i < N_URBS; i++) { dev->data_cb_info[i].dev = dev; dev->data_cb_info[i].index = i; diff --git a/sound/usb/caiaq/device.h b/sound/usb/caiaq/device.h index b2b3101..3f9c633 100644 --- a/sound/usb/caiaq/device.h +++ b/sound/usb/caiaq/device.h @@ -96,6 +96,7 @@ struct snd_usb_caiaqdev { int input_panic, output_panic, warned; char *audio_in_buf, *audio_out_buf; unsigned int samplerates, bpp; + unsigned long outurb_active_mask; struct snd_pcm_substream *sub_playback[MAX_STREAMS]; struct snd_pcm_substream *sub_capture[MAX_STREAMS]; diff --git a/sound/usb/mixer.c b/sound/usb/mixer.c index c04d7c7..cdd19d7 100644 --- a/sound/usb/mixer.c +++ b/sound/usb/mixer.c @@ -152,6 +152,7 @@ static inline void check_mapped_dB(const struct usbmix_name_map *p, if (p && p->dB) { cval->dBmin = p->dB->min; cval->dBmax = p->dB->max; + cval->initialized = 1; } } @@ -1092,7 +1093,7 @@ static void build_feature_ctl(struct mixer_build *state, void *raw_desc, " Switch" : " Volume"); if (control == UAC_FU_VOLUME) { check_mapped_dB(map, cval); - if (cval->dBmin < cval->dBmax) { + if (cval->dBmin < cval->dBmax || !cval->initialized) { kctl->tlv.c = mixer_vol_tlv; kctl->vd[0].access |= SNDRV_CTL_ELEM_ACCESS_TLV_READ | |