---

yaml
---
r: 12168
b: refs/heads/master
c: 9dc2d0f
h: refs/heads/master
v: v3

[refs]

@@ -1,2 +1,2 @@
 ---
-refs/heads/master: 3a7142371efdc95f4c5b5ffc188b18efdc4e64dd
+refs/heads/master: 9dc2d0f55fb693ae6d50c8dd3d934fe3133ca183

trunk/arch/ia64/Kconfig

@@ -26,10 +26,6 @@ config MMU
 	bool
 	default y
 
-config SWIOTLB
-       bool
-       default y
-
 config RWSEM_XCHGADD_ALGORITHM
 	bool
 	default y

trunk/arch/ia64/lib/Makefile

@@ -9,7 +9,7 @@ lib-y := __divsi3.o __udivsi3.o __modsi3.o __umodsi3.o			\
 	bitop.o checksum.o clear_page.o csum_partial_copy.o		\
 	clear_user.o strncpy_from_user.o strlen_user.o strnlen_user.o	\
 	flush.o ip_fast_csum.o do_csum.o				\
-	memset.o strlen.o
+	memset.o strlen.o swiotlb.o
 
 lib-$(CONFIG_ITANIUM)	+= copy_page.o copy_user.o memcpy.o
 lib-$(CONFIG_MCKINLEY)	+= copy_page_mck.o memcpy_mck.o

trunk/lib/swiotlb.c → trunk/arch/ia64/lib/swiotlb.c

@@ -1,7 +1,7 @@
 /*
  * Dynamic DMA mapping support.
  *
- * This implementation is for IA-64 and EM64T platforms that do not support
+ * This implementation is for IA-64 platforms that do not support
  * I/O TLBs (aka DMA address translation hardware).
  * Copyright (C) 2000 Asit Mallick <Asit.K.Mallick@intel.com>
  * Copyright (C) 2000 Goutham Rao <goutham.rao@intel.com>
@@ -11,23 +11,21 @@
  * 03/05/07 davidm	Switch from PCI-DMA to generic device DMA API.
  * 00/12/13 davidm	Rename to swiotlb.c and add mark_clean() to avoid
  *			unnecessary i-cache flushing.
- * 04/07/.. ak		Better overflow handling. Assorted fixes.
- * 05/09/10 linville	Add support for syncing ranges, support syncing for
- *			DMA_BIDIRECTIONAL mappings, miscellaneous cleanup.
+ * 04/07/.. ak          Better overflow handling. Assorted fixes.
  */
 
 #include <linux/cache.h>
-#include <linux/dma-mapping.h>
 #include <linux/mm.h>
 #include <linux/module.h>
+#include <linux/pci.h>
 #include <linux/spinlock.h>
 #include <linux/string.h>
 #include <linux/types.h>
 #include <linux/ctype.h>
 
 #include <asm/io.h>
+#include <asm/pci.h>
 #include <asm/dma.h>
-#include <asm/scatterlist.h>
 
 #include <linux/init.h>
 #include <linux/bootmem.h>
@@ -60,14 +58,6 @@
  */
 #define IO_TLB_MIN_SLABS ((1<<20) >> IO_TLB_SHIFT)
 
-/*
- * Enumeration for sync targets
- */
-enum dma_sync_target {
-	SYNC_FOR_CPU = 0,
-	SYNC_FOR_DEVICE = 1,
-};
-
 int swiotlb_force;
 
 /*
@@ -127,7 +117,7 @@ __setup("swiotlb=", setup_io_tlb_npages);
 
 /*
  * Statically reserve bounce buffer space and initialize bounce buffer data
- * structures for the software IO TLB used to implement the DMA API.
+ * structures for the software IO TLB used to implement the PCI DMA API.
  */
 void
 swiotlb_init_with_default_size (size_t default_size)
@@ -407,28 +397,21 @@ unmap_single(struct device *hwdev, char *dma_addr, size_t size, int dir)
 }
 
 static void
-sync_single(struct device *hwdev, char *dma_addr, size_t size,
-	    int dir, int target)
+sync_single(struct device *hwdev, char *dma_addr, size_t size, int dir)
 {
 	int index = (dma_addr - io_tlb_start) >> IO_TLB_SHIFT;
 	char *buffer = io_tlb_orig_addr[index];
 
-	switch (target) {
-	case SYNC_FOR_CPU:
-		if (likely(dir == DMA_FROM_DEVICE || dir == DMA_BIDIRECTIONAL))
-			memcpy(buffer, dma_addr, size);
-		else if (dir != DMA_TO_DEVICE)
-			BUG();
-		break;
-	case SYNC_FOR_DEVICE:
-		if (likely(dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL))
-			memcpy(dma_addr, buffer, size);
-		else if (dir != DMA_FROM_DEVICE)
-			BUG();
-		break;
-	default:
+	/*
+	 * bounce... copy the data back into/from the original buffer
+	 * XXX How do you handle DMA_BIDIRECTIONAL here ?
+	 */
+	if (dir == DMA_FROM_DEVICE)
+		memcpy(buffer, dma_addr, size);
+	else if (dir == DMA_TO_DEVICE)
+		memcpy(dma_addr, buffer, size);
+	else
 		BUG();
-	}
 }
 
 void *
@@ -502,24 +485,24 @@ swiotlb_full(struct device *dev, size_t size, int dir, int do_panic)
 	/*
 	 * Ran out of IOMMU space for this operation. This is very bad.
 	 * Unfortunately the drivers cannot handle this operation properly.
-	 * unless they check for dma_mapping_error (most don't)
+	 * unless they check for pci_dma_mapping_error (most don't)
 	 * When the mapping is small enough return a static buffer to limit
 	 * the damage, or panic when the transfer is too big.
 	 */
-	printk(KERN_ERR "DMA: Out of SW-IOMMU space for %lu bytes at "
+	printk(KERN_ERR "PCI-DMA: Out of SW-IOMMU space for %lu bytes at "
 	       "device %s\n", size, dev ? dev->bus_id : "?");
 
 	if (size > io_tlb_overflow && do_panic) {
-		if (dir == DMA_FROM_DEVICE || dir == DMA_BIDIRECTIONAL)
-			panic("DMA: Memory would be corrupted\n");
-		if (dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL)
-			panic("DMA: Random memory would be DMAed\n");
+		if (dir == PCI_DMA_FROMDEVICE || dir == PCI_DMA_BIDIRECTIONAL)
+			panic("PCI-DMA: Memory would be corrupted\n");
+		if (dir == PCI_DMA_TODEVICE || dir == PCI_DMA_BIDIRECTIONAL)
+			panic("PCI-DMA: Random memory would be DMAed\n");
 	}
 }
 
 /*
  * Map a single buffer of the indicated size for DMA in streaming mode.  The
- * physical address to use is returned.
+ * PCI address to use is returned.
  *
  * Once the device is given the dma address, the device owns this memory until
  * either swiotlb_unmap_single or swiotlb_dma_sync_single is performed.
@@ -606,73 +589,39 @@ swiotlb_unmap_single(struct device *hwdev, dma_addr_t dev_addr, size_t size,
  * after a transfer.
  *
  * If you perform a swiotlb_map_single() but wish to interrogate the buffer
- * using the cpu, yet do not wish to teardown the dma mapping, you must
- * call this function before doing so.  At the next point you give the dma
+ * using the cpu, yet do not wish to teardown the PCI dma mapping, you must
+ * call this function before doing so.  At the next point you give the PCI dma
  * address back to the card, you must first perform a
  * swiotlb_dma_sync_for_device, and then the device again owns the buffer
  */
-static inline void
-swiotlb_sync_single(struct device *hwdev, dma_addr_t dev_addr,
-		    size_t size, int dir, int target)
+void
+swiotlb_sync_single_for_cpu(struct device *hwdev, dma_addr_t dev_addr,
+			    size_t size, int dir)
 {
 	char *dma_addr = phys_to_virt(dev_addr);
 
 	if (dir == DMA_NONE)
 		BUG();
 	if (dma_addr >= io_tlb_start && dma_addr < io_tlb_end)
-		sync_single(hwdev, dma_addr, size, dir, target);
+		sync_single(hwdev, dma_addr, size, dir);
 	else if (dir == DMA_FROM_DEVICE)
 		mark_clean(dma_addr, size);
 }
 
-void
-swiotlb_sync_single_for_cpu(struct device *hwdev, dma_addr_t dev_addr,
-			    size_t size, int dir)
-{
-	swiotlb_sync_single(hwdev, dev_addr, size, dir, SYNC_FOR_CPU);
-}
-
 void
 swiotlb_sync_single_for_device(struct device *hwdev, dma_addr_t dev_addr,
 			       size_t size, int dir)
 {
-	swiotlb_sync_single(hwdev, dev_addr, size, dir, SYNC_FOR_DEVICE);
-}
-
-/*
- * Same as above, but for a sub-range of the mapping.
- */
-static inline void
-swiotlb_sync_single_range(struct device *hwdev, dma_addr_t dev_addr,
-			  unsigned long offset, size_t size,
-			  int dir, int target)
-{
-	char *dma_addr = phys_to_virt(dev_addr) + offset;
+	char *dma_addr = phys_to_virt(dev_addr);
 
 	if (dir == DMA_NONE)
 		BUG();
 	if (dma_addr >= io_tlb_start && dma_addr < io_tlb_end)
-		sync_single(hwdev, dma_addr, size, dir, target);
+		sync_single(hwdev, dma_addr, size, dir);
 	else if (dir == DMA_FROM_DEVICE)
 		mark_clean(dma_addr, size);
 }
 
-void
-swiotlb_sync_single_range_for_cpu(struct device *hwdev, dma_addr_t dev_addr,
-				  unsigned long offset, size_t size, int dir)
-{
-	swiotlb_sync_single_range(hwdev, dev_addr, offset, size, dir,
-				  SYNC_FOR_CPU);
-}
-
-void
-swiotlb_sync_single_range_for_device(struct device *hwdev, dma_addr_t dev_addr,
-				     unsigned long offset, size_t size, int dir)
-{
-	swiotlb_sync_single_range(hwdev, dev_addr, offset, size, dir,
-				  SYNC_FOR_DEVICE);
-}
-
 /*
  * Map a set of buffers described by scatterlist in streaming mode for DMA.
  * This is the scatter-gather version of the above swiotlb_map_single
@@ -747,9 +696,9 @@ swiotlb_unmap_sg(struct device *hwdev, struct scatterlist *sg, int nelems,
  * The same as swiotlb_sync_single_* but for a scatter-gather list, same rules
  * and usage.
  */
-static inline void
-swiotlb_sync_sg(struct device *hwdev, struct scatterlist *sg,
-		int nelems, int dir, int target)
+void
+swiotlb_sync_sg_for_cpu(struct device *hwdev, struct scatterlist *sg,
+			int nelems, int dir)
 {
 	int i;
 
@@ -759,21 +708,22 @@ swiotlb_sync_sg(struct device *hwdev, struct scatterlist *sg,
 	for (i = 0; i < nelems; i++, sg++)
 		if (sg->dma_address != SG_ENT_PHYS_ADDRESS(sg))
 			sync_single(hwdev, (void *) sg->dma_address,
-				    sg->dma_length, dir, target);
-}
-
-void
-swiotlb_sync_sg_for_cpu(struct device *hwdev, struct scatterlist *sg,
-			int nelems, int dir)
-{
-	swiotlb_sync_sg(hwdev, sg, nelems, dir, SYNC_FOR_CPU);
+				    sg->dma_length, dir);
 }
 
 void
 swiotlb_sync_sg_for_device(struct device *hwdev, struct scatterlist *sg,
 			   int nelems, int dir)
 {
-	swiotlb_sync_sg(hwdev, sg, nelems, dir, SYNC_FOR_DEVICE);
+	int i;
+
+	if (dir == DMA_NONE)
+		BUG();
+
+	for (i = 0; i < nelems; i++, sg++)
+		if (sg->dma_address != SG_ENT_PHYS_ADDRESS(sg))
+			sync_single(hwdev, (void *) sg->dma_address,
+				    sg->dma_length, dir);
 }
 
 int
@@ -783,9 +733,9 @@ swiotlb_dma_mapping_error(dma_addr_t dma_addr)
 }
 
 /*
- * Return whether the given device DMA address mask can be supported
+ * Return whether the given PCI device DMA address mask can be supported
  * properly.  For example, if your device can only drive the low 24-bits
- * during bus mastering, then you would pass 0x00ffffff as the mask to
+ * during PCI bus mastering, then you would pass 0x00ffffff as the mask to
  * this function.
  */
 int
@@ -801,8 +751,6 @@ EXPORT_SYMBOL(swiotlb_map_sg);
 EXPORT_SYMBOL(swiotlb_unmap_sg);
 EXPORT_SYMBOL(swiotlb_sync_single_for_cpu);
 EXPORT_SYMBOL(swiotlb_sync_single_for_device);
-EXPORT_SYMBOL_GPL(swiotlb_sync_single_range_for_cpu);
-EXPORT_SYMBOL_GPL(swiotlb_sync_single_range_for_device);
 EXPORT_SYMBOL(swiotlb_sync_sg_for_cpu);
 EXPORT_SYMBOL(swiotlb_sync_sg_for_device);
 EXPORT_SYMBOL(swiotlb_dma_mapping_error);

trunk/arch/x86_64/kernel/Makefile

@@ -27,6 +27,7 @@ obj-$(CONFIG_CPU_FREQ)		+= cpufreq/
 obj-$(CONFIG_EARLY_PRINTK)	+= early_printk.o
 obj-$(CONFIG_GART_IOMMU)	+= pci-gart.o aperture.o
 obj-$(CONFIG_DUMMY_IOMMU)	+= pci-nommu.o pci-dma.o
+obj-$(CONFIG_SWIOTLB)		+= swiotlb.o
 obj-$(CONFIG_KPROBES)		+= kprobes.o
 obj-$(CONFIG_X86_PM_TIMER)	+= pmtimer.o
 
@@ -40,6 +41,7 @@ CFLAGS_vsyscall.o		:= $(PROFILING) -g0
 bootflag-y			+= ../../i386/kernel/bootflag.o
 cpuid-$(subst m,y,$(CONFIG_X86_CPUID))  += ../../i386/kernel/cpuid.o
 topology-y                     += ../../i386/mach-default/topology.o
+swiotlb-$(CONFIG_SWIOTLB)      += ../../ia64/lib/swiotlb.o
 microcode-$(subst m,y,$(CONFIG_MICROCODE))  += ../../i386/kernel/microcode.o
 intel_cacheinfo-y		+= ../../i386/kernel/cpu/intel_cacheinfo.o
 quirks-y			+= ../../i386/kernel/quirks.o

trunk/drivers/block/aoe/aoecmd.c

@@ -468,11 +468,16 @@ aoecmd_ata_rsp(struct sk_buff *skb)
 			unsigned long duration = jiffies - buf->start_time;
 			unsigned long n_sect = buf->bio->bi_size >> 9;
 			struct gendisk *disk = d->gd;
-			const int rw = bio_data_dir(buf->bio);
 
-			disk_stat_inc(disk, ios[rw]);
-			disk_stat_add(disk, ticks[rw], duration);
-			disk_stat_add(disk, sectors[rw], n_sect);
+			if (bio_data_dir(buf->bio) == WRITE) {
+				disk_stat_inc(disk, writes);
+				disk_stat_add(disk, write_ticks, duration);
+				disk_stat_add(disk, write_sectors, n_sect);
+			} else {
+				disk_stat_inc(disk, reads);
+				disk_stat_add(disk, read_ticks, duration);
+				disk_stat_add(disk, read_sectors, n_sect);
+			}
 			disk_stat_add(disk, io_ticks, duration);
 			n = (buf->flags & BUFFL_FAIL) ? -EIO : 0;
 			bio_endio(buf->bio, buf->bio->bi_size, n);

trunk/drivers/block/genhd.c

@@ -391,12 +391,13 @@ static ssize_t disk_stats_read(struct gendisk * disk, char *page)
 		"%8u %8u %8llu %8u "
 		"%8u %8u %8u"
 		"\n",
-		disk_stat_read(disk, ios[0]), disk_stat_read(disk, merges[0]),
-		(unsigned long long)disk_stat_read(disk, sectors[0]),
-		jiffies_to_msecs(disk_stat_read(disk, ticks[0])),
-		disk_stat_read(disk, ios[1]), disk_stat_read(disk, merges[1]),
-		(unsigned long long)disk_stat_read(disk, sectors[1]),
-		jiffies_to_msecs(disk_stat_read(disk, ticks[1])),
+		disk_stat_read(disk, reads), disk_stat_read(disk, read_merges),
+		(unsigned long long)disk_stat_read(disk, read_sectors),
+		jiffies_to_msecs(disk_stat_read(disk, read_ticks)),
+		disk_stat_read(disk, writes), 
+		disk_stat_read(disk, write_merges),
+		(unsigned long long)disk_stat_read(disk, write_sectors),
+		jiffies_to_msecs(disk_stat_read(disk, write_ticks)),
 		disk->in_flight,
 		jiffies_to_msecs(disk_stat_read(disk, io_ticks)),
 		jiffies_to_msecs(disk_stat_read(disk, time_in_queue)));
@@ -582,12 +583,12 @@ static int diskstats_show(struct seq_file *s, void *v)
 	preempt_enable();
 	seq_printf(s, "%4d %4d %s %u %u %llu %u %u %u %llu %u %u %u %u\n",
 		gp->major, n + gp->first_minor, disk_name(gp, n, buf),
-		disk_stat_read(gp, ios[0]), disk_stat_read(gp, merges[0]),
-		(unsigned long long)disk_stat_read(gp, sectors[0]),
-		jiffies_to_msecs(disk_stat_read(gp, ticks[0])),
-		disk_stat_read(gp, ios[1]), disk_stat_read(gp, merges[1]),
-		(unsigned long long)disk_stat_read(gp, sectors[1]),
-		jiffies_to_msecs(disk_stat_read(gp, ticks[1])),
+		disk_stat_read(gp, reads), disk_stat_read(gp, read_merges),
+		(unsigned long long)disk_stat_read(gp, read_sectors),
+		jiffies_to_msecs(disk_stat_read(gp, read_ticks)),
+		disk_stat_read(gp, writes), disk_stat_read(gp, write_merges),
+		(unsigned long long)disk_stat_read(gp, write_sectors),
+		jiffies_to_msecs(disk_stat_read(gp, write_ticks)),
 		gp->in_flight,
 		jiffies_to_msecs(disk_stat_read(gp, io_ticks)),
 		jiffies_to_msecs(disk_stat_read(gp, time_in_queue)));
@@ -600,8 +601,8 @@ static int diskstats_show(struct seq_file *s, void *v)
 			seq_printf(s, "%4d %4d %s %u %u %u %u\n",
 				gp->major, n + gp->first_minor + 1,
 				disk_name(gp, n + 1, buf),
-				hd->ios[0], hd->sectors[0],
-				hd->ios[1], hd->sectors[1]);
+				hd->reads, hd->read_sectors,
+				hd->writes, hd->write_sectors);
 	}
 
 	return 0;