Merge tag 'dmaengine-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/djbw/dmaengine

Pull dmaengine fixes from Dan Williams:

1/ regression fix for Xen as it now trips over a broken assumption
   about the dma address size on 32-bit builds

2/ new quirk for netdma to ignore dma channels that cannot meet
   netdma alignment requirements

3/ fixes for two long standing issues in ioatdma (ring size overflow)
   and iop-adma (potential stack corruption)

* tag 'dmaengine-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/djbw/dmaengine:
  netdma: adding alignment check for NETDMA ops
  ioatdma: DMA copy alignment needed to address IOAT DMA silicon errata
  ioat: ring size variables need to be 32bit to avoid overflow
  iop-adma: Corrected array overflow in RAID6 Xscale(R) test.
  ioat: fix size of 'completion' for Xen

drivers/dma/dmaengine.c

@@ -332,6 +332,20 @@ struct dma_chan *dma_find_channel(enum dma_transaction_type tx_type)
 }
 EXPORT_SYMBOL(dma_find_channel);
 
+/*
+ * net_dma_find_channel - find a channel for net_dma
+ * net_dma has alignment requirements
+ */
+struct dma_chan *net_dma_find_channel(void)
+{
+	struct dma_chan *chan = dma_find_channel(DMA_MEMCPY);
+	if (chan && !is_dma_copy_aligned(chan->device, 1, 1, 1))
+		return NULL;
+
+	return chan;
+}
+EXPORT_SYMBOL(net_dma_find_channel);
+
 /**
  * dma_issue_pending_all - flush all pending operations across all channels
  */

drivers/dma/ioat/dma.c

@@ -546,9 +546,9 @@ void ioat_dma_unmap(struct ioat_chan_common *chan, enum dma_ctrl_flags flags,
 			   PCI_DMA_TODEVICE, flags, 0);
 }
 
-unsigned long ioat_get_current_completion(struct ioat_chan_common *chan)
+dma_addr_t ioat_get_current_completion(struct ioat_chan_common *chan)
 {
-	unsigned long phys_complete;
+	dma_addr_t phys_complete;
 	u64 completion;
 
 	completion = *chan->completion;
@@ -569,7 +569,7 @@ unsigned long ioat_get_current_completion(struct ioat_chan_common *chan)
 }
 
 bool ioat_cleanup_preamble(struct ioat_chan_common *chan,
-			   unsigned long *phys_complete)
+			   dma_addr_t *phys_complete)
 {
 	*phys_complete = ioat_get_current_completion(chan);
 	if (*phys_complete == chan->last_completion)
@@ -580,14 +580,14 @@ bool ioat_cleanup_preamble(struct ioat_chan_common *chan,
 	return true;
 }
 
-static void __cleanup(struct ioat_dma_chan *ioat, unsigned long phys_complete)
+static void __cleanup(struct ioat_dma_chan *ioat, dma_addr_t phys_complete)
 {
 	struct ioat_chan_common *chan = &ioat->base;
 	struct list_head *_desc, *n;
 	struct dma_async_tx_descriptor *tx;
 
-	dev_dbg(to_dev(chan), "%s: phys_complete: %lx\n",
-		 __func__, phys_complete);
+	dev_dbg(to_dev(chan), "%s: phys_complete: %llx\n",
+		 __func__, (unsigned long long) phys_complete);
 	list_for_each_safe(_desc, n, &ioat->used_desc) {
 		struct ioat_desc_sw *desc;
 
@@ -652,7 +652,7 @@ static void __cleanup(struct ioat_dma_chan *ioat, unsigned long phys_complete)
 static void ioat1_cleanup(struct ioat_dma_chan *ioat)
 {
 	struct ioat_chan_common *chan = &ioat->base;
-	unsigned long phys_complete;
+	dma_addr_t phys_complete;
 
 	prefetch(chan->completion);
 
@@ -698,7 +698,7 @@ static void ioat1_timer_event(unsigned long data)
 		mod_timer(&chan->timer, jiffies + COMPLETION_TIMEOUT);
 		spin_unlock_bh(&ioat->desc_lock);
 	} else if (test_bit(IOAT_COMPLETION_PENDING, &chan->state)) {
-		unsigned long phys_complete;
+		dma_addr_t phys_complete;
 
 		spin_lock_bh(&ioat->desc_lock);
 		/* if we haven't made progress and we have already

drivers/dma/ioat/dma.h

@@ -88,7 +88,7 @@ struct ioatdma_device {
 struct ioat_chan_common {
 	struct dma_chan common;
 	void __iomem *reg_base;
-	unsigned long last_completion;
+	dma_addr_t last_completion;
 	spinlock_t cleanup_lock;
 	unsigned long state;
 	#define IOAT_COMPLETION_PENDING 0
@@ -310,7 +310,7 @@ int __devinit ioat_dma_self_test(struct ioatdma_device *device);
 void __devexit ioat_dma_remove(struct ioatdma_device *device);
 struct dca_provider * __devinit ioat_dca_init(struct pci_dev *pdev,
 					      void __iomem *iobase);
-unsigned long ioat_get_current_completion(struct ioat_chan_common *chan);
+dma_addr_t ioat_get_current_completion(struct ioat_chan_common *chan);
 void ioat_init_channel(struct ioatdma_device *device,
 		       struct ioat_chan_common *chan, int idx);
 enum dma_status ioat_dma_tx_status(struct dma_chan *c, dma_cookie_t cookie,
@@ -318,7 +318,7 @@ enum dma_status ioat_dma_tx_status(struct dma_chan *c, dma_cookie_t cookie,
 void ioat_dma_unmap(struct ioat_chan_common *chan, enum dma_ctrl_flags flags,
 		    size_t len, struct ioat_dma_descriptor *hw);
 bool ioat_cleanup_preamble(struct ioat_chan_common *chan,
-			   unsigned long *phys_complete);
+			   dma_addr_t *phys_complete);
 void ioat_kobject_add(struct ioatdma_device *device, struct kobj_type *type);
 void ioat_kobject_del(struct ioatdma_device *device);
 extern const struct sysfs_ops ioat_sysfs_ops;

drivers/dma/ioat/dma_v2.c

@@ -128,7 +128,7 @@ static void ioat2_start_null_desc(struct ioat2_dma_chan *ioat)
 	spin_unlock_bh(&ioat->prep_lock);
 }
 
-static void __cleanup(struct ioat2_dma_chan *ioat, unsigned long phys_complete)
+static void __cleanup(struct ioat2_dma_chan *ioat, dma_addr_t phys_complete)
 {
 	struct ioat_chan_common *chan = &ioat->base;
 	struct dma_async_tx_descriptor *tx;
@@ -179,7 +179,7 @@ static void __cleanup(struct ioat2_dma_chan *ioat, unsigned long phys_complete)
 static void ioat2_cleanup(struct ioat2_dma_chan *ioat)
 {
 	struct ioat_chan_common *chan = &ioat->base;
-	unsigned long phys_complete;
+	dma_addr_t phys_complete;
 
 	spin_lock_bh(&chan->cleanup_lock);
 	if (ioat_cleanup_preamble(chan, &phys_complete))
@@ -260,7 +260,7 @@ int ioat2_reset_sync(struct ioat_chan_common *chan, unsigned long tmo)
 static void ioat2_restart_channel(struct ioat2_dma_chan *ioat)
 {
 	struct ioat_chan_common *chan = &ioat->base;
-	unsigned long phys_complete;
+	dma_addr_t phys_complete;
 
 	ioat2_quiesce(chan, 0);
 	if (ioat_cleanup_preamble(chan, &phys_complete))
@@ -275,7 +275,7 @@ void ioat2_timer_event(unsigned long data)
 	struct ioat_chan_common *chan = &ioat->base;
 
 	if (test_bit(IOAT_COMPLETION_PENDING, &chan->state)) {
-		unsigned long phys_complete;
+		dma_addr_t phys_complete;
 		u64 status;
 
 		status = ioat_chansts(chan);
@@ -572,9 +572,9 @@ bool reshape_ring(struct ioat2_dma_chan *ioat, int order)
 	 */
 	struct ioat_chan_common *chan = &ioat->base;
 	struct dma_chan *c = &chan->common;
-	const u16 curr_size = ioat2_ring_size(ioat);
+	const u32 curr_size = ioat2_ring_size(ioat);
 	const u16 active = ioat2_ring_active(ioat);
-	const u16 new_size = 1 << order;
+	const u32 new_size = 1 << order;
 	struct ioat_ring_ent **ring;
 	u16 i;
 

drivers/dma/ioat/dma_v2.h

@@ -74,7 +74,7 @@ static inline struct ioat2_dma_chan *to_ioat2_chan(struct dma_chan *c)
 	return container_of(chan, struct ioat2_dma_chan, base);
 }
 
-static inline u16 ioat2_ring_size(struct ioat2_dma_chan *ioat)
+static inline u32 ioat2_ring_size(struct ioat2_dma_chan *ioat)
 {
 	return 1 << ioat->alloc_order;
 }
@@ -91,7 +91,7 @@ static inline u16 ioat2_ring_pending(struct ioat2_dma_chan *ioat)
 	return CIRC_CNT(ioat->head, ioat->issued, ioat2_ring_size(ioat));
 }
 
-static inline u16 ioat2_ring_space(struct ioat2_dma_chan *ioat)
+static inline u32 ioat2_ring_space(struct ioat2_dma_chan *ioat)
 {
 	return ioat2_ring_size(ioat) - ioat2_ring_active(ioat);
 }

drivers/dma/ioat/dma_v3.c

@@ -257,7 +257,7 @@ static bool desc_has_ext(struct ioat_ring_ent *desc)
  * The difference from the dma_v2.c __cleanup() is that this routine
  * handles extended descriptors and dma-unmapping raid operations.
  */
-static void __cleanup(struct ioat2_dma_chan *ioat, unsigned long phys_complete)
+static void __cleanup(struct ioat2_dma_chan *ioat, dma_addr_t phys_complete)
 {
 	struct ioat_chan_common *chan = &ioat->base;
 	struct ioat_ring_ent *desc;
@@ -314,7 +314,7 @@ static void __cleanup(struct ioat2_dma_chan *ioat, unsigned long phys_complete)
 static void ioat3_cleanup(struct ioat2_dma_chan *ioat)
 {
 	struct ioat_chan_common *chan = &ioat->base;
-	unsigned long phys_complete;
+	dma_addr_t phys_complete;
 
 	spin_lock_bh(&chan->cleanup_lock);
 	if (ioat_cleanup_preamble(chan, &phys_complete))
@@ -333,7 +333,7 @@ static void ioat3_cleanup_event(unsigned long data)
 static void ioat3_restart_channel(struct ioat2_dma_chan *ioat)
 {
 	struct ioat_chan_common *chan = &ioat->base;
-	unsigned long phys_complete;
+	dma_addr_t phys_complete;
 
 	ioat2_quiesce(chan, 0);
 	if (ioat_cleanup_preamble(chan, &phys_complete))
@@ -348,7 +348,7 @@ static void ioat3_timer_event(unsigned long data)
 	struct ioat_chan_common *chan = &ioat->base;
 
 	if (test_bit(IOAT_COMPLETION_PENDING, &chan->state)) {
-		unsigned long phys_complete;
+		dma_addr_t phys_complete;
 		u64 status;
 
 		status = ioat_chansts(chan);
@@ -1149,6 +1149,44 @@ static int ioat3_reset_hw(struct ioat_chan_common *chan)
 	return ioat2_reset_sync(chan, msecs_to_jiffies(200));
 }
 
+static bool is_jf_ioat(struct pci_dev *pdev)
+{
+	switch (pdev->device) {
+	case PCI_DEVICE_ID_INTEL_IOAT_JSF0:
+	case PCI_DEVICE_ID_INTEL_IOAT_JSF1:
+	case PCI_DEVICE_ID_INTEL_IOAT_JSF2:
+	case PCI_DEVICE_ID_INTEL_IOAT_JSF3:
+	case PCI_DEVICE_ID_INTEL_IOAT_JSF4:
+	case PCI_DEVICE_ID_INTEL_IOAT_JSF5:
+	case PCI_DEVICE_ID_INTEL_IOAT_JSF6:
+	case PCI_DEVICE_ID_INTEL_IOAT_JSF7:
+	case PCI_DEVICE_ID_INTEL_IOAT_JSF8:
+	case PCI_DEVICE_ID_INTEL_IOAT_JSF9:
+		return true;
+	default:
+		return false;
+	}
+}
+
+static bool is_snb_ioat(struct pci_dev *pdev)
+{
+	switch (pdev->device) {
+	case PCI_DEVICE_ID_INTEL_IOAT_SNB0:
+	case PCI_DEVICE_ID_INTEL_IOAT_SNB1:
+	case PCI_DEVICE_ID_INTEL_IOAT_SNB2:
+	case PCI_DEVICE_ID_INTEL_IOAT_SNB3:
+	case PCI_DEVICE_ID_INTEL_IOAT_SNB4:
+	case PCI_DEVICE_ID_INTEL_IOAT_SNB5:
+	case PCI_DEVICE_ID_INTEL_IOAT_SNB6:
+	case PCI_DEVICE_ID_INTEL_IOAT_SNB7:
+	case PCI_DEVICE_ID_INTEL_IOAT_SNB8:
+	case PCI_DEVICE_ID_INTEL_IOAT_SNB9:
+		return true;
+	default:
+		return false;
+	}
+}
+
 int __devinit ioat3_dma_probe(struct ioatdma_device *device, int dca)
 {
 	struct pci_dev *pdev = device->pdev;
@@ -1169,6 +1207,9 @@ int __devinit ioat3_dma_probe(struct ioatdma_device *device, int dca)
 	dma->device_alloc_chan_resources = ioat2_alloc_chan_resources;
 	dma->device_free_chan_resources = ioat2_free_chan_resources;
 
+	if (is_jf_ioat(pdev) || is_snb_ioat(pdev))
+		dma->copy_align = 6;
+
 	dma_cap_set(DMA_INTERRUPT, dma->cap_mask);
 	dma->device_prep_dma_interrupt = ioat3_prep_interrupt_lock;
 

drivers/dma/iop-adma.c

@@ -1252,8 +1252,8 @@ iop_adma_pq_zero_sum_self_test(struct iop_adma_device *device)
 	struct page **pq_hw = &pq[IOP_ADMA_NUM_SRC_TEST+2];
 	/* address conversion buffers (dma_map / page_address) */
 	void *pq_sw[IOP_ADMA_NUM_SRC_TEST+2];
-	dma_addr_t pq_src[IOP_ADMA_NUM_SRC_TEST];
-	dma_addr_t pq_dest[2];
+	dma_addr_t pq_src[IOP_ADMA_NUM_SRC_TEST+2];
+	dma_addr_t *pq_dest = &pq_src[IOP_ADMA_NUM_SRC_TEST];
 
 	int i;
 	struct dma_async_tx_descriptor *tx;

include/linux/dmaengine.h

@@ -974,6 +974,7 @@ int dma_async_device_register(struct dma_device *device);
 void dma_async_device_unregister(struct dma_device *device);
 void dma_run_dependencies(struct dma_async_tx_descriptor *tx);
 struct dma_chan *dma_find_channel(enum dma_transaction_type tx_type);
+struct dma_chan *net_dma_find_channel(void);
 #define dma_request_channel(mask, x, y) __dma_request_channel(&(mask), x, y)
 
 /* --- Helper iov-locking functions --- */

net/ipv4/tcp.c

@@ -1452,7 +1452,7 @@ int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 		if ((available < target) &&
 		    (len > sysctl_tcp_dma_copybreak) && !(flags & MSG_PEEK) &&
 		    !sysctl_tcp_low_latency &&
-		    dma_find_channel(DMA_MEMCPY)) {
+		    net_dma_find_channel()) {
 			preempt_enable_no_resched();
 			tp->ucopy.pinned_list =
 					dma_pin_iovec_pages(msg->msg_iov, len);
@@ -1667,7 +1667,7 @@ do_prequeue:
 		if (!(flags & MSG_TRUNC)) {
 #ifdef CONFIG_NET_DMA
 			if (!tp->ucopy.dma_chan && tp->ucopy.pinned_list)
-				tp->ucopy.dma_chan = dma_find_channel(DMA_MEMCPY);
+				tp->ucopy.dma_chan = net_dma_find_channel();
 
 			if (tp->ucopy.dma_chan) {
 				tp->ucopy.dma_cookie = dma_skb_copy_datagram_iovec(

net/ipv4/tcp_input.c

@@ -5225,7 +5225,7 @@ static int tcp_dma_try_early_copy(struct sock *sk, struct sk_buff *skb,
 		return 0;
 
 	if (!tp->ucopy.dma_chan && tp->ucopy.pinned_list)
-		tp->ucopy.dma_chan = dma_find_channel(DMA_MEMCPY);
+		tp->ucopy.dma_chan = net_dma_find_channel();
 
 	if (tp->ucopy.dma_chan && skb_csum_unnecessary(skb)) {
 

net/ipv4/tcp_ipv4.c

@@ -1730,7 +1730,7 @@ process:
 #ifdef CONFIG_NET_DMA
 		struct tcp_sock *tp = tcp_sk(sk);
 		if (!tp->ucopy.dma_chan && tp->ucopy.pinned_list)
-			tp->ucopy.dma_chan = dma_find_channel(DMA_MEMCPY);
+			tp->ucopy.dma_chan = net_dma_find_channel();
 		if (tp->ucopy.dma_chan)
 			ret = tcp_v4_do_rcv(sk, skb);
 		else

net/ipv6/tcp_ipv6.c

@@ -1645,7 +1645,7 @@ process:
 #ifdef CONFIG_NET_DMA
 		struct tcp_sock *tp = tcp_sk(sk);
 		if (!tp->ucopy.dma_chan && tp->ucopy.pinned_list)
-			tp->ucopy.dma_chan = dma_find_channel(DMA_MEMCPY);
+			tp->ucopy.dma_chan = net_dma_find_channel();
 		if (tp->ucopy.dma_chan)
 			ret = tcp_v6_do_rcv(sk, skb);
 		else