Merge branch 'for-linus' of git://git.kernel.dk/data/git/linux-2.6-block

* 'for-linus' of git://git.kernel.dk/data/git/linux-2.6-block: (63 commits) Fix memory leak in dm-crypt SPARC64: sg chaining support SPARC: sg chaining support PPC: sg chaining support PS3: sg chaining support IA64: sg chaining support x86-64: enable sg chaining x86-64: update pci-gart iommu to sg helpers x86-64: update nommu to sg helpers x86-64: update calgary iommu to sg helpers swiotlb: sg chaining support i386: enable sg chaining i386 dma_map_sg: convert to using sg helpers mmc: need to zero sglist on init Panic in blk_rq_map_sg() from CCISS driver remove sglist_len remove blk_queue_max_phys_segments in libata revert sg segment size ifdefs Fixup u14-34f ENABLE_SG_CHAINING qla1280: enable use_sg_chaining option ...
mna · Oct 16, 2007 · 92d15c2 · 92d15c2
2 parents f20bf61 + 644bd2f
commit 92d15c2
Show file tree

Hide file tree

Showing 142 changed files with 1,186 additions and 1,115 deletions.
diff --git a/Documentation/DMA-mapping.txt b/Documentation/DMA-mapping.txt
@@ -514,7 +514,7 @@ With scatterlists, you map a region gathered from several regions by:
 	int i, count = pci_map_sg(dev, sglist, nents, direction);
 	struct scatterlist *sg;
 
-	for (i = 0, sg = sglist; i < count; i++, sg++) {
+	for_each_sg(sglist, sg, count, i) {
 		hw_address[i] = sg_dma_address(sg);
 		hw_len[i] = sg_dma_len(sg);
 	}
@@ -782,5 +782,5 @@ following people:
 	Jay Estabrook <[email protected]>
 	Thomas Sailer <[email protected]>
 	Andrea Arcangeli <[email protected]>
-	Jens Axboe <axboe@suse.de>
+	Jens Axboe <jens.axboe@oracle.com>
 	David Mosberger-Tang <[email protected]>
diff --git a/Documentation/HOWTO b/Documentation/HOWTO
@@ -330,7 +330,7 @@ Here is a list of some of the different kernel trees available:
     - ACPI development tree, Len Brown <[email protected]>
 	git.kernel.org:/pub/scm/linux/kernel/git/lenb/linux-acpi-2.6.git
 
-    - Block development tree, Jens Axboe <axboe@suse.de>
+    - Block development tree, Jens Axboe <jens.axboe@oracle.com>
 	git.kernel.org:/pub/scm/linux/kernel/git/axboe/linux-2.6-block.git
 
     - DRM development tree, Dave Airlie <[email protected]>

diff --git a/Documentation/block/00-INDEX b/Documentation/block/00-INDEX
@@ -0,0 +1,20 @@
+00-INDEX
+	- This file
+as-iosched.txt
+	- Anticipatory IO scheduler
+barrier.txt
+	- I/O Barriers
+biodoc.txt
+	- Notes on the Generic Block Layer Rewrite in Linux 2.5
+capability.txt
+	- Generic Block Device Capability (/sys/block/<disk>/capability)
+deadline-iosched.txt
+	- Deadline IO scheduler tunables
+ioprio.txt
+	- Block io priorities (in CFQ scheduler)
+request.txt
+	- The members of struct request (in include/linux/blkdev.h)
+stat.txt
+	- Block layer statistics in /sys/block/<dev>/stat
+switching-sched.txt
+	- Switching I/O schedulers at runtime
diff --git a/Documentation/block/as-iosched.txt b/Documentation/block/as-iosched.txt
@@ -20,15 +20,10 @@ actually has a head for each physical device in the logical RAID device.
 However, setting the antic_expire (see tunable parameters below) produces
 very similar behavior to the deadline IO scheduler.
 
-
 Selecting IO schedulers
 -----------------------
-To choose IO schedulers at boot time, use the argument 'elevator=deadline'.
-'noop', 'as' and 'cfq' (the default) are also available. IO schedulers are
-assigned globally at boot time only presently. It's also possible to change
-the IO scheduler for a determined device on the fly, as described in
-Documentation/block/switching-sched.txt.
-
+Refer to Documentation/block/switching-sched.txt for information on
+selecting an io scheduler on a per-device basis.
 
 Anticipatory IO scheduler Policies
 ----------------------------------
@@ -115,7 +110,7 @@ statistics (average think time, average seek distance) on the process
 that submitted the just completed request are examined.  If it seems
 likely that that process will submit another request soon, and that
 request is likely to be near the just completed request, then the IO
-scheduler will stop dispatching more read requests for up time (antic_expire)
+scheduler will stop dispatching more read requests for up to (antic_expire)
 milliseconds, hoping that process will submit a new request near the one
 that just completed.  If such a request is made, then it is dispatched
 immediately.  If the antic_expire wait time expires, then the IO scheduler
@@ -165,3 +160,13 @@ The parameters are:
     for big seek time devices though not a linear correspondence - most
     processes have only a few ms thinktime.
 
+In addition to the tunables above there is a read-only file named est_time
+which, when read, will show:
+
+    - The probability of a task exiting without a cooperating task
+      submitting an anticipated IO.
+
+    - The current mean think time.
+
+    - The seek distance used to determine if an incoming IO is better.
+
diff --git a/Documentation/block/biodoc.txt b/Documentation/block/biodoc.txt
@@ -2,7 +2,7 @@
 	=====================================================
 
 Notes Written on Jan 15, 2002:
-	Jens Axboe <axboe@suse.de>
+	Jens Axboe <jens.axboe@oracle.com>
 	Suparna Bhattacharya <[email protected]>
 
 Last Updated May 2, 2002
@@ -21,7 +21,7 @@ Credits:
 ---------
 
 2.5 bio rewrite:
-	Jens Axboe <axboe@suse.de>
+	Jens Axboe <jens.axboe@oracle.com>
 
 Many aspects of the generic block layer redesign were driven by and evolved
 over discussions, prior patches and the collective experience of several

diff --git a/Documentation/block/deadline-iosched.txt b/Documentation/block/deadline-iosched.txt
@@ -5,16 +5,10 @@ This little file attempts to document how the deadline io scheduler works.
 In particular, it will clarify the meaning of the exposed tunables that may be
 of interest to power users.
 
-Each io queue has a set of io scheduler tunables associated with it. These
-tunables control how the io scheduler works. You can find these entries
-in:
-
-/sys/block/<device>/queue/iosched
-
-assuming that you have sysfs mounted on /sys. If you don't have sysfs mounted,
-you can do so by typing:
-
-# mount none /sys -t sysfs
+Selecting IO schedulers
+-----------------------
+Refer to Documentation/block/switching-sched.txt for information on
+selecting an io scheduler on a per-device basis.
 
 
 ********************************************************************************
@@ -41,14 +35,11 @@ fifo_batch
 
 When a read request expires its deadline, we must move some requests from
 the sorted io scheduler list to the block device dispatch queue. fifo_batch
-controls how many requests we move, based on the cost of each request. A
-request is either qualified as a seek or a stream. The io scheduler knows
-the last request that was serviced by the drive (or will be serviced right
-before this one). See seek_cost and stream_unit.
+controls how many requests we move.
 
 
-write_starved	(number of dispatches)
--------------
+writes_starved	(number of dispatches)
+--------------
 
 When we have to move requests from the io scheduler queue to the block
 device dispatch queue, we always give a preference to reads. However, we
@@ -73,6 +64,6 @@ that comes at basically 0 cost we leave that on. We simply disable the
 rbtree front sector lookup when the io scheduler merge function is called.
 
 
-Nov 11 2002, Jens Axboe <axboe@suse.de>
+Nov 11 2002, Jens Axboe <jens.axboe@oracle.com>
 
 
diff --git a/Documentation/block/ioprio.txt b/Documentation/block/ioprio.txt
@@ -180,4 +180,4 @@ int main(int argc, char *argv[])
 ---> snip ionice.c tool <---
 
 
-March 11 2005, Jens Axboe <axboe@suse.de>
+March 11 2005, Jens Axboe <jens.axboe@oracle.com>
diff --git a/Documentation/block/request.txt b/Documentation/block/request.txt
@@ -1,7 +1,7 @@
 
 struct request documentation
 
-Jens Axboe <axboe@suse.de> 27/05/02
+Jens Axboe <jens.axboe@oracle.com> 27/05/02
 
 1.0
 Index

diff --git a/Documentation/block/switching-sched.txt b/Documentation/block/switching-sched.txt
@@ -1,3 +1,18 @@
+To choose IO schedulers at boot time, use the argument 'elevator=deadline'.
+'noop', 'as' and 'cfq' (the default) are also available. IO schedulers are
+assigned globally at boot time only presently.
+
+Each io queue has a set of io scheduler tunables associated with it. These
+tunables control how the io scheduler works. You can find these entries
+in:
+
+/sys/block/<device>/queue/iosched
+
+assuming that you have sysfs mounted on /sys. If you don't have sysfs mounted,
+you can do so by typing:
+
+# mount none /sys -t sysfs
+
 As of the Linux 2.6.10 kernel, it is now possible to change the
 IO scheduler for a given block device on the fly (thus making it possible,
 for instance, to set the CFQ scheduler for the system default, but
@@ -20,3 +35,9 @@ noop anticipatory deadline [cfq]
 # echo anticipatory > /sys/block/hda/queue/scheduler
 # cat /sys/block/hda/queue/scheduler
 noop [anticipatory] deadline cfq
+
+Each io queue has a set of io scheduler tunables associated with it. These
+tunables control how the io scheduler works. You can find these entries
+in:
+
+/sys/block/<device>/queue/iosched
diff --git a/arch/ia64/hp/common/sba_iommu.c b/arch/ia64/hp/common/sba_iommu.c
@@ -396,7 +396,7 @@ sba_dump_sg( struct ioc *ioc, struct scatterlist *startsg, int nents)
 		printk(KERN_DEBUG " %d : DMA %08lx/%05x CPU %p\n", nents,
 		       startsg->dma_address, startsg->dma_length,
 		       sba_sg_address(startsg));
-		startsg++;
+		startsg = sg_next(startsg);
 	}
 }
 
@@ -409,7 +409,7 @@ sba_check_sg( struct ioc *ioc, struct scatterlist *startsg, int nents)
 	while (the_nents-- > 0) {
 		if (sba_sg_address(the_sg) == 0x0UL)
 			sba_dump_sg(NULL, startsg, nents);
-		the_sg++;
+		the_sg = sg_next(the_sg);
 	}
 }
 
@@ -1201,7 +1201,7 @@ sba_fill_pdir(
 			u32 pide = startsg->dma_address & ~PIDE_FLAG;
 			dma_offset = (unsigned long) pide & ~iovp_mask;
 			startsg->dma_address = 0;
-			dma_sg++;
+			dma_sg = sg_next(dma_sg);
 			dma_sg->dma_address = pide | ioc->ibase;
 			pdirp = &(ioc->pdir_base[pide >> iovp_shift]);
 			n_mappings++;
@@ -1228,7 +1228,7 @@ sba_fill_pdir(
 				pdirp++;
 			} while (cnt > 0);
 		}
-		startsg++;
+		startsg = sg_next(startsg);
 	}
 	/* force pdir update */
 	wmb();
@@ -1297,7 +1297,7 @@ sba_coalesce_chunks( struct ioc *ioc,
 		while (--nents > 0) {
 			unsigned long vaddr;	/* tmp */
 
-			startsg++;
+			startsg = sg_next(startsg);
 
 			/* PARANOID */
 			startsg->dma_address = startsg->dma_length = 0;
@@ -1407,7 +1407,7 @@ int sba_map_sg(struct device *dev, struct scatterlist *sglist, int nents, int di
 #ifdef ALLOW_IOV_BYPASS_SG
 	ASSERT(to_pci_dev(dev)->dma_mask);
 	if (likely((ioc->dma_mask & ~to_pci_dev(dev)->dma_mask) == 0)) {
-		for (sg = sglist ; filled < nents ; filled++, sg++){
+		for_each_sg(sglist, sg, nents, filled) {
 			sg->dma_length = sg->length;
 			sg->dma_address = virt_to_phys(sba_sg_address(sg));
 		}
@@ -1501,7 +1501,7 @@ void sba_unmap_sg (struct device *dev, struct scatterlist *sglist, int nents, in
 	while (nents && sglist->dma_length) {
 
 		sba_unmap_single(dev, sglist->dma_address, sglist->dma_length, dir);
-		sglist++;
+		sglist = sg_next(sglist);
 		nents--;
 	}
 

diff --git a/arch/ia64/hp/sim/simscsi.c b/arch/ia64/hp/sim/simscsi.c
@@ -360,6 +360,7 @@ static struct scsi_host_template driver_template = {
 	.max_sectors		= 1024,
 	.cmd_per_lun		= SIMSCSI_REQ_QUEUE_LEN,
 	.use_clustering		= DISABLE_CLUSTERING,
+	.use_sg_chaining	= ENABLE_SG_CHAINING,
 };
 
 static int __init

diff --git a/arch/ia64/sn/pci/pci_dma.c b/arch/ia64/sn/pci/pci_dma.c
@@ -218,16 +218,17 @@ EXPORT_SYMBOL(sn_dma_unmap_single);
  *
  * Unmap a set of streaming mode DMA translations.
  */
-void sn_dma_unmap_sg(struct device *dev, struct scatterlist *sg,
+void sn_dma_unmap_sg(struct device *dev, struct scatterlist *sgl,
 		     int nhwentries, int direction)
 {
 	int i;
 	struct pci_dev *pdev = to_pci_dev(dev);
 	struct sn_pcibus_provider *provider = SN_PCIDEV_BUSPROVIDER(pdev);
+	struct scatterlist *sg;
 
 	BUG_ON(dev->bus != &pci_bus_type);
 
-	for (i = 0; i < nhwentries; i++, sg++) {
+	for_each_sg(sgl, sg, nhwentries, i) {
 		provider->dma_unmap(pdev, sg->dma_address, direction);
 		sg->dma_address = (dma_addr_t) NULL;
 		sg->dma_length = 0;
@@ -244,11 +245,11 @@ EXPORT_SYMBOL(sn_dma_unmap_sg);
  *
  * Maps each entry of @sg for DMA.
  */
-int sn_dma_map_sg(struct device *dev, struct scatterlist *sg, int nhwentries,
+int sn_dma_map_sg(struct device *dev, struct scatterlist *sgl, int nhwentries,
 		  int direction)
 {
 	unsigned long phys_addr;
-	struct scatterlist *saved_sg = sg;
+	struct scatterlist *saved_sg = sgl, *sg;
 	struct pci_dev *pdev = to_pci_dev(dev);
 	struct sn_pcibus_provider *provider = SN_PCIDEV_BUSPROVIDER(pdev);
 	int i;
@@ -258,7 +259,7 @@ int sn_dma_map_sg(struct device *dev, struct scatterlist *sg, int nhwentries,
 	/*
 	 * Setup a DMA address for each entry in the scatterlist.
 	 */
-	for (i = 0; i < nhwentries; i++, sg++) {
+	for_each_sg(sgl, sg, nhwentries, i) {
 		phys_addr = SG_ENT_PHYS_ADDRESS(sg);
 		sg->dma_address = provider->dma_map(pdev,
 						    phys_addr, sg->length,

diff --git a/arch/powerpc/kernel/dma_64.c b/arch/powerpc/kernel/dma_64.c
@@ -154,12 +154,13 @@ static void dma_direct_unmap_single(struct device *dev, dma_addr_t dma_addr,
 {
 }
 
-static int dma_direct_map_sg(struct device *dev, struct scatterlist *sg,
+static int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl,
 			     int nents, enum dma_data_direction direction)
 {
+	struct scatterlist *sg;
 	int i;
 
-	for (i = 0; i < nents; i++, sg++) {
+	for_each_sg(sgl, sg, nents, i) {
 		sg->dma_address = (page_to_phys(sg->page) + sg->offset) |
 			dma_direct_offset;
 		sg->dma_length = sg->length;

diff --git a/arch/powerpc/kernel/ibmebus.c b/arch/powerpc/kernel/ibmebus.c
@@ -87,15 +87,16 @@ static void ibmebus_unmap_single(struct device *dev,
 }
 
 static int ibmebus_map_sg(struct device *dev,
-			  struct scatterlist *sg,
+			  struct scatterlist *sgl,
 			  int nents, enum dma_data_direction direction)
 {
+	struct scatterlist *sg;
 	int i;
 
-	for (i = 0; i < nents; i++) {
-		sg[i].dma_address = (dma_addr_t)page_address(sg[i].page)
-			+ sg[i].offset;
-		sg[i].dma_length = sg[i].length;
+	for_each_sg(sgl, sg, nents, i) {
+		sg->dma_address = (dma_addr_t)page_address(sg->page)
+			+ sg->offset;
+		sg->dma_length = sg->length;
 	}
 
 	return nents;
Original file line number	Diff line number	Diff line change
Expand Up		@@ -180,4 +180,4 @@ int main(int argc, char *argv[])
		---> snip ionice.c tool <---


		March 11 2005, Jens Axboe <axboe@suse.de>
		March 11 2005, Jens Axboe <jens.axboe@oracle.com>