Merge branch 'ioat-md-accel-for-linus' of git://lost.foo-projects.org/~dwillia2/git/iop

* 'ioat-md-accel-for-linus' of git://lost.foo-projects.org/~dwillia2/git/iop: (28 commits)
  ioatdma: add the unisys "i/oat" pci vendor/device id
  ARM: Add drivers/dma to arch/arm/Kconfig
  iop3xx: surface the iop3xx DMA and AAU units to the iop-adma driver
  iop13xx: surface the iop13xx adma units to the iop-adma driver
  dmaengine: driver for the iop32x, iop33x, and iop13xx raid engines
  md: remove raid5 compute_block and compute_parity5
  md: handle_stripe5 - request io processing in raid5_run_ops
  md: handle_stripe5 - add request/completion logic for async expand ops
  md: handle_stripe5 - add request/completion logic for async read ops
  md: handle_stripe5 - add request/completion logic for async check ops
  md: handle_stripe5 - add request/completion logic for async compute ops
  md: handle_stripe5 - add request/completion logic for async write ops
  md: common infrastructure for running operations with raid5_run_ops
  md: raid5_run_ops - run stripe operations outside sh->lock
  raid5: replace custom debug PRINTKs with standard pr_debug
  raid5: refactor handle_stripe5 and handle_stripe6 (v3)
  async_tx: add the async_tx api
  xor: make 'xor_blocks' a library routine for use with async_tx
  dmaengine: make clients responsible for managing channels
  dmaengine: refactor dmaengine around dma_async_tx_descriptor
  ...

1 files changed, 78 insertions, 34 deletions

diff --git a/net/core/dev.c b/net/core/dev.c
index 4221dcda88d7..96443055324e 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -151,9 +151,22 @@ static struct list_head ptype_base[16] __read_mostly;	/* 16 way hashed list */
 static struct list_head ptype_all __read_mostly;        /* Taps */
 
 #ifdef CONFIG_NET_DMA
-static struct dma_client *net_dma_client;
-static unsigned int net_dma_count;
-static spinlock_t net_dma_event_lock;
+struct net_dma {
+        struct dma_client client;
+        spinlock_t lock;
+        cpumask_t channel_mask;
+        struct dma_chan *channels[NR_CPUS];
+};
+
+static enum dma_state_client
+netdev_dma_event(struct dma_client *client, struct dma_chan *chan,
+        enum dma_state state);
+
+static struct net_dma net_dma = {
+        .client = {
+                .event_callback = netdev_dma_event,
+        },
+};
 #endif
 
 /*
@@ -2022,12 +2035,13 @@ out:
          * There may not be any more sk_buffs coming right now, so push
          * any pending DMA copies to hardware
          */
-        if (net_dma_client) {
-                struct dma_chan *chan;
-                rcu_read_lock();
-                list_for_each_entry_rcu(chan, &net_dma_client->channels, client_node)
-                        dma_async_memcpy_issue_pending(chan);
-                rcu_read_unlock();
+        if (!cpus_empty(net_dma.channel_mask)) {
+                int chan_idx;
+                for_each_cpu_mask(chan_idx, net_dma.channel_mask) {
+                        struct dma_chan *chan = net_dma.channels[chan_idx];
+                        if (chan)
+                                dma_async_memcpy_issue_pending(chan);
+                }
         }
 #endif
         return;
@@ -3775,12 +3789,13 @@ static int dev_cpu_callback(struct notifier_block *nfb,
  * This is called when the number of channels allocated to the net_dma_client
  * changes.  The net_dma_client tries to have one DMA channel per CPU.
  */
-static void net_dma_rebalance(void)
+
+static void net_dma_rebalance(struct net_dma *net_dma)
 {
-        unsigned int cpu, i, n;
+        unsigned int cpu, i, n, chan_idx;
         struct dma_chan *chan;
 
-        if (net_dma_count == 0) {
+        if (cpus_empty(net_dma->channel_mask)) {
                 for_each_online_cpu(cpu)
                         rcu_assign_pointer(per_cpu(softnet_data, cpu).net_dma, NULL);
                 return;
@@ -3789,10 +3804,12 @@ static void net_dma_rebalance(void)
         i = 0;
         cpu = first_cpu(cpu_online_map);
 
-        rcu_read_lock();
-        list_for_each_entry(chan, &net_dma_client->channels, client_node) {
-                n = ((num_online_cpus() / net_dma_count)
-                   + (i < (num_online_cpus() % net_dma_count) ? 1 : 0));
+        for_each_cpu_mask(chan_idx, net_dma->channel_mask) {
+                chan = net_dma->channels[chan_idx];
+
+                n = ((num_online_cpus() / cpus_weight(net_dma->channel_mask))
+                   + (i < (num_online_cpus() %
+                        cpus_weight(net_dma->channel_mask)) ? 1 : 0));
 
                 while(n) {
                         per_cpu(softnet_data, cpu).net_dma = chan;
@@ -3801,7 +3818,6 @@ static void net_dma_rebalance(void)
                 }
                 i++;
         }
-        rcu_read_unlock();
 }
 
 /**
@@ -3810,23 +3826,53 @@ static void net_dma_rebalance(void)
  * @chan: DMA channel for the event
  * @event: event type
  */
-static void netdev_dma_event(struct dma_client *client, struct dma_chan *chan,
-        enum dma_event event)
-{
-        spin_lock(&net_dma_event_lock);
-        switch (event) {
-        case DMA_RESOURCE_ADDED:
-                net_dma_count++;
-                net_dma_rebalance();
+static enum dma_state_client
+netdev_dma_event(struct dma_client *client, struct dma_chan *chan,
+        enum dma_state state)
+{
+        int i, found = 0, pos = -1;
+        struct net_dma *net_dma =
+                container_of(client, struct net_dma, client);
+        enum dma_state_client ack = DMA_DUP; /* default: take no action */
+
+        spin_lock(&net_dma->lock);
+        switch (state) {
+        case DMA_RESOURCE_AVAILABLE:
+                for (i = 0; i < NR_CPUS; i++)
+                        if (net_dma->channels[i] == chan) {
+                                found = 1;
+                                break;
+                        } else if (net_dma->channels[i] == NULL && pos < 0)
+                                pos = i;
+
+                if (!found && pos >= 0) {
+                        ack = DMA_ACK;
+                        net_dma->channels[pos] = chan;
+                        cpu_set(pos, net_dma->channel_mask);
+                        net_dma_rebalance(net_dma);
+                }
                 break;
         case DMA_RESOURCE_REMOVED:
-                net_dma_count--;
-                net_dma_rebalance();
+                for (i = 0; i < NR_CPUS; i++)
+                        if (net_dma->channels[i] == chan) {
+                                found = 1;
+                                pos = i;
+                                break;
+                        }
+
+                if (found) {
+                        ack = DMA_ACK;
+                        cpu_clear(pos, net_dma->channel_mask);
+                        net_dma->channels[i] = NULL;
+                        net_dma_rebalance(net_dma);
+                }
                 break;
         default:
                 break;
         }
-        spin_unlock(&net_dma_event_lock);
+        spin_unlock(&net_dma->lock);
+
+        return ack;
 }
 
 /**
@@ -3834,12 +3880,10 @@ static void netdev_dma_event(struct dma_client *client, struct dma_chan *chan,
  */
 static int __init netdev_dma_register(void)
 {
-        spin_lock_init(&net_dma_event_lock);
-        net_dma_client = dma_async_client_register(netdev_dma_event);
-        if (net_dma_client == NULL)
-                return -ENOMEM;
-
-        dma_async_client_chan_request(net_dma_client, num_online_cpus());
+        spin_lock_init(&net_dma.lock);
+        dma_cap_set(DMA_MEMCPY, net_dma.client.cap_mask);
+        dma_async_client_register(&net_dma.client);
+        dma_async_client_chan_request(&net_dma.client);
         return 0;
 }