Merge tag 'dmaengine-3.17' of git://git.kernel.org/pub/scm/linux/kern…

…el/git/djbw/dmaengine

Pull dmaengine updates from Dan Williams:
 "Even though this has fixes marked for -stable, given the size and the
  needed conflict resolutions this is 3.18-rc1/merge-window material.

  These patches have been languishing in my tree for a long while.  The
  fact that I do not have the time to do proper/prompt maintenance of
  this tree is a primary factor in the decision to step down as
  dmaengine maintainer.  That and the fact that the bulk of drivers/dma/
  activity is going through Vinod these days.

  The net_dma removal has not been in -next.  It has developed simple
  conflicts against mainline and net-next (for-3.18).

  Continuing thanks to Vinod for staying on top of drivers/dma/.

  Summary:

   1/ Step down as dmaengine maintainer see commit 08223d8
      "dmaengine maintainer update"

   2/ Removal of net_dma, as it has been marked 'broken' since 3.13
      (commit 7787380 "net_dma: mark broken"), without reports of
      performance regression.

   3/ Miscellaneous fixes"

* tag 'dmaengine-3.17' of git://git.kernel.org/pub/scm/linux/kernel/git/djbw/dmaengine:
  net: make tcp_cleanup_rbuf private
  net_dma: revert 'copied_early'
  net_dma: simple removal
  dmaengine maintainer update
  dmatest: prevent memory leakage on error path in thread
  ioat: Use time_before_jiffies()
  dmaengine: fix xor sources continuation
  dma: mv_xor: Rename __mv_xor_slot_cleanup() to mv_xor_slot_cleanup()
  dma: mv_xor: Remove all callers of mv_xor_slot_cleanup()
  dma: mv_xor: Remove unneeded mv_xor_clean_completed_slots() call
  ioat: Use pci_enable_msix_exact() instead of pci_enable_msix()
  drivers: dma: Include appropriate header file in dca.c
  drivers: dma: Mark functions as static in dma_v3.c
  dma: mv_xor: Add DMA API error checks
  ioat/dca: Use dev_is_pci() to check whether it is pci device

Documentation/ABI/removed/net_dma

@@ -0,0 +1,8 @@
+What:		tcp_dma_copybreak sysctl
+Date:		Removed in kernel v3.13
+Contact:	Dan Williams <[email protected]>
+Description:
+	Formerly the lower limit, in bytes, of the size of socket reads
+	that will be offloaded to a DMA copy engine.  Removed due to
+	coherency issues of the cpu potentially touching the buffers
+	while dma is in flight.

Documentation/networking/ip-sysctl.txt

@@ -580,12 +580,6 @@ tcp_workaround_signed_windows - BOOLEAN
 	not receive a window scaling option from them.
 	Default: 0
 
-tcp_dma_copybreak - INTEGER
-	Lower limit, in bytes, of the size of socket reads that will be
-	offloaded to a DMA copy engine, if one is present in the system
-	and CONFIG_NET_DMA is enabled.
-	Default: 4096
-
 tcp_thin_linear_timeouts - BOOLEAN
 	Enable dynamic triggering of linear timeouts for thin streams.
 	If set, a check is performed upon retransmission by timeout to

MAINTAINERS

@@ -1025,24 +1025,20 @@ F:	arch/arm/mach-pxa/colibri-pxa270-income.c
 
 ARM/INTEL IOP32X ARM ARCHITECTURE
 M:	Lennert Buytenhek <[email protected]>
-M:	Dan Williams <[email protected]>
 L:	[email protected] (moderated for non-subscribers)
 S:	Maintained
 
 ARM/INTEL IOP33X ARM ARCHITECTURE
-M:	Dan Williams <[email protected]>
 L:	[email protected] (moderated for non-subscribers)
-S:	Maintained
+S:	Orphan
 
 ARM/INTEL IOP13XX ARM ARCHITECTURE
 M:	Lennert Buytenhek <[email protected]>
-M:	Dan Williams <[email protected]>
 L:	[email protected] (moderated for non-subscribers)
 S:	Maintained
 
 ARM/INTEL IQ81342EX MACHINE SUPPORT
 M:	Lennert Buytenhek <[email protected]>
-M:	Dan Williams <[email protected]>
 L:	[email protected] (moderated for non-subscribers)
 S:	Maintained
 
@@ -1067,7 +1063,6 @@ F:	drivers/pcmcia/pxa2xx_stargate2.c
 
 ARM/INTEL XSC3 (MANZANO) ARM CORE
 M:	Lennert Buytenhek <[email protected]>
-M:	Dan Williams <[email protected]>
 L:	[email protected] (moderated for non-subscribers)
 S:	Maintained
 
@@ -1562,9 +1557,9 @@ F:	drivers/platform/x86/asus*.c
 F:	drivers/platform/x86/eeepc*.c
 
 ASYNCHRONOUS TRANSFERS/TRANSFORMS (IOAT) API
-M:	Dan Williams <[email protected]>
+R:	Dan Williams <[email protected]>
 W:	http://sourceforge.net/projects/xscaleiop
-S:	Maintained
+S:	Odd fixes
 F:	Documentation/crypto/async-tx-api.txt
 F:	crypto/async_tx/
 F:	drivers/dma/
@@ -2995,13 +2990,11 @@ T:	git git://git.linaro.org/people/sumitsemwal/linux-dma-buf.git
 
 DMA GENERIC OFFLOAD ENGINE SUBSYSTEM
 M:	Vinod Koul <[email protected]>
-M:	Dan Williams <[email protected]>
 L:	[email protected]
 Q:	https://patchwork.kernel.org/project/linux-dmaengine/list/
-S:	Supported
+S:	Maintained
 F:	drivers/dma/
 F:	include/linux/dma*
-T:	git git://git.kernel.org/pub/scm/linux/kernel/git/djbw/async_tx.git
 T:	git git://git.infradead.org/users/vkoul/slave-dma.git (slave-dma)
 
 DME1737 HARDWARE MONITOR DRIVER
@@ -4754,8 +4747,8 @@ F:	arch/x86/kernel/cpu/microcode/core*
 F:	arch/x86/kernel/cpu/microcode/intel*
 
 INTEL I/OAT DMA DRIVER
-M:	Dan Williams <[email protected]>
 M:	Dave Jiang <[email protected]>
+R:	Dan Williams <[email protected]>
 L:	[email protected]
 Q:	https://patchwork.kernel.org/project/linux-dmaengine/list/
 S:	Supported
@@ -4770,7 +4763,7 @@ F:	drivers/iommu/intel-iommu.c
 F:	include/linux/intel-iommu.h
 
 INTEL IOP-ADMA DMA DRIVER
-M:	Dan Williams <[email protected]>
+R:	Dan Williams <[email protected]>
 S:	Odd fixes
 F:	drivers/dma/iop-adma.c
 

crypto/async_tx/async_xor.c

@@ -78,8 +78,6 @@ do_async_xor(struct dma_chan *chan, struct dmaengine_unmap_data *unmap,
 		tx = dma->device_prep_dma_xor(chan, dma_dest, src_list,
 					      xor_src_cnt, unmap->len,
 					      dma_flags);
-		src_list[0] = tmp;
-
 
 		if (unlikely(!tx))
 			async_tx_quiesce(&submit->depend_tx);
@@ -92,6 +90,7 @@ do_async_xor(struct dma_chan *chan, struct dmaengine_unmap_data *unmap,
 						      xor_src_cnt, unmap->len,
 						      dma_flags);
 		}
+		src_list[0] = tmp;
 
 		dma_set_unmap(tx, unmap);
 		async_tx_submit(chan, tx, submit);

drivers/dma/Kconfig

@@ -427,18 +427,6 @@ config DMA_OF
 comment "DMA Clients"
 	depends on DMA_ENGINE
 
-config NET_DMA
-	bool "Network: TCP receive copy offload"
-	depends on DMA_ENGINE && NET
-	default (INTEL_IOATDMA || FSL_DMA)
-	depends on BROKEN
-	help
-	  This enables the use of DMA engines in the network stack to
-	  offload receive copy-to-user operations, freeing CPU cycles.
-
-	  Say Y here if you enabled INTEL_IOATDMA or FSL_DMA, otherwise
-	  say N.
-
 config ASYNC_TX_DMA
 	bool "Async_tx: Offload support for the async_tx api"
 	depends on DMA_ENGINE

drivers/dma/Makefile

@@ -6,7 +6,6 @@ obj-$(CONFIG_DMA_VIRTUAL_CHANNELS) += virt-dma.o
 obj-$(CONFIG_DMA_ACPI) += acpi-dma.o
 obj-$(CONFIG_DMA_OF) += of-dma.o
 
-obj-$(CONFIG_NET_DMA) += iovlock.o
 obj-$(CONFIG_INTEL_MID_DMAC) += intel_mid_dma.o
 obj-$(CONFIG_DMATEST) += dmatest.o
 obj-$(CONFIG_INTEL_IOATDMA) += ioat/

drivers/dma/dmaengine.c

@@ -1081,110 +1081,6 @@ dmaengine_get_unmap_data(struct device *dev, int nr, gfp_t flags)
 }
 EXPORT_SYMBOL(dmaengine_get_unmap_data);
 
-/**
- * dma_async_memcpy_pg_to_pg - offloaded copy from page to page
- * @chan: DMA channel to offload copy to
- * @dest_pg: destination page
- * @dest_off: offset in page to copy to
- * @src_pg: source page
- * @src_off: offset in page to copy from
- * @len: length
- *
- * Both @dest_page/@dest_off and @src_page/@src_off must be mappable to a bus
- * address according to the DMA mapping API rules for streaming mappings.
- * Both @dest_page/@dest_off and @src_page/@src_off must stay memory resident
- * (kernel memory or locked user space pages).
- */
-dma_cookie_t
-dma_async_memcpy_pg_to_pg(struct dma_chan *chan, struct page *dest_pg,
-	unsigned int dest_off, struct page *src_pg, unsigned int src_off,
-	size_t len)
-{
-	struct dma_device *dev = chan->device;
-	struct dma_async_tx_descriptor *tx;
-	struct dmaengine_unmap_data *unmap;
-	dma_cookie_t cookie;
-	unsigned long flags;
-
-	unmap = dmaengine_get_unmap_data(dev->dev, 2, GFP_NOWAIT);
-	if (!unmap)
-		return -ENOMEM;
-
-	unmap->to_cnt = 1;
-	unmap->from_cnt = 1;
-	unmap->addr[0] = dma_map_page(dev->dev, src_pg, src_off, len,
-				      DMA_TO_DEVICE);
-	unmap->addr[1] = dma_map_page(dev->dev, dest_pg, dest_off, len,
-				      DMA_FROM_DEVICE);
-	unmap->len = len;
-	flags = DMA_CTRL_ACK;
-	tx = dev->device_prep_dma_memcpy(chan, unmap->addr[1], unmap->addr[0],
-					 len, flags);
-
-	if (!tx) {
-		dmaengine_unmap_put(unmap);
-		return -ENOMEM;
-	}
-
-	dma_set_unmap(tx, unmap);
-	cookie = tx->tx_submit(tx);
-	dmaengine_unmap_put(unmap);
-
-	preempt_disable();
-	__this_cpu_add(chan->local->bytes_transferred, len);
-	__this_cpu_inc(chan->local->memcpy_count);
-	preempt_enable();
-
-	return cookie;
-}
-EXPORT_SYMBOL(dma_async_memcpy_pg_to_pg);
-
-/**
- * dma_async_memcpy_buf_to_buf - offloaded copy between virtual addresses
- * @chan: DMA channel to offload copy to
- * @dest: destination address (virtual)
- * @src: source address (virtual)
- * @len: length
- *
- * Both @dest and @src must be mappable to a bus address according to the
- * DMA mapping API rules for streaming mappings.
- * Both @dest and @src must stay memory resident (kernel memory or locked
- * user space pages).
- */
-dma_cookie_t
-dma_async_memcpy_buf_to_buf(struct dma_chan *chan, void *dest,
-			    void *src, size_t len)
-{
-	return dma_async_memcpy_pg_to_pg(chan, virt_to_page(dest),
-					 (unsigned long) dest & ~PAGE_MASK,
-					 virt_to_page(src),
-					 (unsigned long) src & ~PAGE_MASK, len);
-}
-EXPORT_SYMBOL(dma_async_memcpy_buf_to_buf);
-
-/**
- * dma_async_memcpy_buf_to_pg - offloaded copy from address to page
- * @chan: DMA channel to offload copy to
- * @page: destination page
- * @offset: offset in page to copy to
- * @kdata: source address (virtual)
- * @len: length
- *
- * Both @page/@offset and @kdata must be mappable to a bus address according
- * to the DMA mapping API rules for streaming mappings.
- * Both @page/@offset and @kdata must stay memory resident (kernel memory or
- * locked user space pages)
- */
-dma_cookie_t
-dma_async_memcpy_buf_to_pg(struct dma_chan *chan, struct page *page,
-			   unsigned int offset, void *kdata, size_t len)
-{
-	return dma_async_memcpy_pg_to_pg(chan, page, offset,
-					 virt_to_page(kdata),
-					 (unsigned long) kdata & ~PAGE_MASK, len);
-}
-EXPORT_SYMBOL(dma_async_memcpy_buf_to_pg);
-
 void dma_async_tx_descriptor_init(struct dma_async_tx_descriptor *tx,
 	struct dma_chan *chan)
 {

drivers/dma/dmatest.c

@@ -688,14 +688,14 @@ static int dmatest_func(void *data)
 	runtime = ktime_us_delta(ktime_get(), ktime);
 
 	ret = 0;
+err_dstbuf:
 	for (i = 0; thread->dsts[i]; i++)
 		kfree(thread->dsts[i]);
-err_dstbuf:
 	kfree(thread->dsts);
 err_dsts:
+err_srcbuf:
 	for (i = 0; thread->srcs[i]; i++)
 		kfree(thread->srcs[i]);
-err_srcbuf:
 	kfree(thread->srcs);
 err_srcs:
 	kfree(pq_coefs);

drivers/dma/ioat/dca.c

@@ -35,6 +35,7 @@
 
 #include "dma.h"
 #include "registers.h"
+#include "dma_v2.h"
 
 /*
  * Bit 7 of a tag map entry is the "valid" bit, if it is set then bits 0:6
@@ -147,7 +148,7 @@ static int ioat_dca_add_requester(struct dca_provider *dca, struct device *dev)
 	u16 id;
 
 	/* This implementation only supports PCI-Express */
-	if (dev->bus != &pci_bus_type)
+	if (!dev_is_pci(dev))
 		return -ENODEV;
 	pdev = to_pci_dev(dev);
 	id = dcaid_from_pcidev(pdev);
@@ -179,7 +180,7 @@ static int ioat_dca_remove_requester(struct dca_provider *dca,
 	int i;
 
 	/* This implementation only supports PCI-Express */
-	if (dev->bus != &pci_bus_type)
+	if (!dev_is_pci(dev))
 		return -ENODEV;
 	pdev = to_pci_dev(dev);
 
@@ -320,7 +321,7 @@ static int ioat2_dca_add_requester(struct dca_provider *dca, struct device *dev)
 	u16 global_req_table;
 
 	/* This implementation only supports PCI-Express */
-	if (dev->bus != &pci_bus_type)
+	if (!dev_is_pci(dev))
 		return -ENODEV;
 	pdev = to_pci_dev(dev);
 	id = dcaid_from_pcidev(pdev);
@@ -354,7 +355,7 @@ static int ioat2_dca_remove_requester(struct dca_provider *dca,
 	u16 global_req_table;
 
 	/* This implementation only supports PCI-Express */
-	if (dev->bus != &pci_bus_type)
+	if (!dev_is_pci(dev))
 		return -ENODEV;
 	pdev = to_pci_dev(dev);
 
@@ -496,7 +497,7 @@ static int ioat3_dca_add_requester(struct dca_provider *dca, struct device *dev)
 	u16 global_req_table;
 
 	/* This implementation only supports PCI-Express */
-	if (dev->bus != &pci_bus_type)
+	if (!dev_is_pci(dev))
 		return -ENODEV;
 	pdev = to_pci_dev(dev);
 	id = dcaid_from_pcidev(pdev);
@@ -530,7 +531,7 @@ static int ioat3_dca_remove_requester(struct dca_provider *dca,
 	u16 global_req_table;
 
 	/* This implementation only supports PCI-Express */
-	if (dev->bus != &pci_bus_type)
+	if (!dev_is_pci(dev))
 		return -ENODEV;
 	pdev = to_pci_dev(dev);
 

drivers/dma/ioat/dma.c

@@ -947,7 +947,7 @@ int ioat_dma_setup_interrupts(struct ioatdma_device *device)
 	for (i = 0; i < msixcnt; i++)
 		device->msix_entries[i].entry = i;
 
-	err = pci_enable_msix(pdev, device->msix_entries, msixcnt);
+	err = pci_enable_msix_exact(pdev, device->msix_entries, msixcnt);
 	if (err)
 		goto msi;
 
@@ -1222,7 +1222,6 @@ int ioat1_dma_probe(struct ioatdma_device *device, int dca)
 	err = ioat_probe(device);
 	if (err)
 		return err;
-	ioat_set_tcp_copy_break(4096);
 	err = ioat_register(device);
 	if (err)
 		return err;

drivers/dma/ioat/dma.h

@@ -214,13 +214,6 @@ __dump_desc_dbg(struct ioat_chan_common *chan, struct ioat_dma_descriptor *hw,
 #define dump_desc_dbg(c, d) \
 	({ if (d) __dump_desc_dbg(&c->base, d->hw, &d->txd, desc_id(d)); 0; })
 
-static inline void ioat_set_tcp_copy_break(unsigned long copybreak)
-{
-	#ifdef CONFIG_NET_DMA
-	sysctl_tcp_dma_copybreak = copybreak;
-	#endif
-}
-
 static inline struct ioat_chan_common *
 ioat_chan_by_index(struct ioatdma_device *device, int index)
 {

drivers/dma/ioat/dma_v2.c

@@ -735,7 +735,8 @@ int ioat2_check_space_lock(struct ioat2_dma_chan *ioat, int num_descs)
 	 * called under bh_disabled so we need to trigger the timer
 	 * event directly
 	 */
-	if (jiffies > chan->timer.expires && timer_pending(&chan->timer)) {
+	if (time_is_before_jiffies(chan->timer.expires)
+	    && timer_pending(&chan->timer)) {
 		struct ioatdma_device *device = chan->device;
 
 		mod_timer(&chan->timer, jiffies + COMPLETION_TIMEOUT);
@@ -899,7 +900,6 @@ int ioat2_dma_probe(struct ioatdma_device *device, int dca)
 	err = ioat_probe(device);
 	if (err)
 		return err;
-	ioat_set_tcp_copy_break(2048);
 
 	list_for_each_entry(c, &dma->channels, device_node) {
 		chan = to_chan_common(c);