---

yaml
---
r: 263186
b: refs/heads/master
c: 8f6544e
h: refs/heads/master
v: v3

[refs]

@@ -1,2 +1,2 @@
 ---
-refs/heads/master: fe4c51b22080691792d3e28d86acb4d4ccb7e8e8
+refs/heads/master: 8f6544edb2c7a7464fbbce1d86a4de414dc0cf95

trunk/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.

trunk/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]
 

trunk/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];

trunk/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;
 	}

trunk/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);
 

trunk/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

trunk/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);

trunk/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

trunk/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;

trunk/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---

trunk/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

trunk/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))

trunk/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.
@@ -311,6 +309,19 @@ void blk_insert_flush(struct request *rq)
 	if (!(fflags & REQ_FUA))
 		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
@@ -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);

trunk/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:

trunk/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;
 		}

trunk/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 *);