ixgbe: setup per CPU PCI pool for FCoE DDP

Currently single PCI pool used across all CPUs and that
doesn't scales up as number of CPU increases, so this
patch adds per CPU PCI pool to setup udl and that aligns
well from FCoE stack as that already has per CPU exch locking.

Adds per CPU PCI alloc setup and free in
ixgbe_fcoe_ddp_pools_alloc and ixgbe_fcoe_ddp_pools_free,
use CPU specific pool during DDP setup.

Re-arranged ixgbe_fcoe struct to have fewer holes
along with adding pools ptr using pahole.

Signed-off-by: Vasu Dev <[e-mail]>
Tested-by: Ross Brattain <[e-mail]>
Signed-off-by: Jeff Kirsher <[e-mail]>

drivers/net/ixgbe/ixgbe_fcoe.c

···
 	if (ddp->sgl)
 		pci_unmap_sg(adapter->pdev, ddp->sgl, ddp->sgc,
 			     DMA_FROM_DEVICE);
-	pci_pool_free(fcoe->pool, ddp->udl, ddp->udp);
+	if (ddp->pool) {
+		pci_pool_free(ddp->pool, ddp->udl, ddp->udp);
+		ddp->pool = NULL;
+	}
+
 	ixgbe_fcoe_clear_ddp(ddp);
 
 out_ddp_put:
···
 	unsigned int thislen = 0;
 	u32 fcbuff, fcdmarw, fcfltrw, fcrxctl;
 	dma_addr_t addr = 0;
+	struct pci_pool *pool;
 
 	if (!netdev || !sgl)
 		return 0;
···
 		return 0;
 	}
 
-	/* alloc the udl from our ddp pool */
-	ddp->udl = pci_pool_alloc(fcoe->pool, GFP_ATOMIC, &ddp->udp);
+	/* alloc the udl from per cpu ddp pool */
+	pool = *per_cpu_ptr(fcoe->pool, get_cpu());
+	ddp->udl = pci_pool_alloc(pool, GFP_ATOMIC, &ddp->udp);
 	if (!ddp->udl) {
 		e_err(drv, "failed allocated ddp context\n");
 		goto out_noddp_unmap;
 	}
+	ddp->pool = pool;
 	ddp->sgl = sgl;
 	ddp->sgc = sgc;
 
···
 		j++;
 		lastsize = 1;
 	}
+	put_cpu();
 
 	fcbuff = (IXGBE_FCBUFF_4KB << IXGBE_FCBUFF_BUFFSIZE_SHIFT);
 	fcbuff |= ((j & 0xff) << IXGBE_FCBUFF_BUFFCNT_SHIFT);
···
 	return 1;
 
 out_noddp_free:
-	pci_pool_free(fcoe->pool, ddp->udl, ddp->udp);
+	pci_pool_free(pool, ddp->udl, ddp->udp);
 	ixgbe_fcoe_clear_ddp(ddp);
 
 out_noddp_unmap:
 	pci_unmap_sg(adapter->pdev, sgl, sgc, DMA_FROM_DEVICE);
+	put_cpu();
 	return 0;
 }
 
···
 	return skb_is_gso(skb);
 }
 
+static void ixgbe_fcoe_ddp_pools_free(struct ixgbe_fcoe *fcoe)
+{
+	unsigned int cpu;
+	struct pci_pool **pool;
+
+	for_each_possible_cpu(cpu) {
+		pool = per_cpu_ptr(fcoe->pool, cpu);
+		if (*pool)
+			pci_pool_destroy(*pool);
+	}
+	free_percpu(fcoe->pool);
+	fcoe->pool = NULL;
+}
+
+static void ixgbe_fcoe_ddp_pools_alloc(struct ixgbe_adapter *adapter)
+{
+	struct ixgbe_fcoe *fcoe = &adapter->fcoe;
+	unsigned int cpu;
+	struct pci_pool **pool;
+	char pool_name[32];
+
+	fcoe->pool = alloc_percpu(struct pci_pool *);
+	if (!fcoe->pool)
+		return;
+
+	/* allocate pci pool for each cpu */
+	for_each_possible_cpu(cpu) {
+		snprintf(pool_name, 32, "ixgbe_fcoe_ddp_%d", cpu);
+		pool = per_cpu_ptr(fcoe->pool, cpu);
+		*pool = pci_pool_create(pool_name,
+					adapter->pdev, IXGBE_FCPTR_MAX,
+					IXGBE_FCPTR_ALIGN, PAGE_SIZE);
+		if (!*pool) {
+			e_err(drv, "failed to alloc DDP pool on cpu:%d\n", cpu);
+			ixgbe_fcoe_ddp_pools_free(fcoe);
+			return;
+		}
+	}
+}
+
 /**
  * ixgbe_configure_fcoe - configures registers for fcoe at start
  * @adapter: ptr to ixgbe adapter
···
 	u32 up2tc;
 #endif
 
-	/* create the pool for ddp if not created yet */
 	if (!fcoe->pool) {
-		/* allocate ddp pool */
-		fcoe->pool = pci_pool_create("ixgbe_fcoe_ddp",
-					     adapter->pdev, IXGBE_FCPTR_MAX,
-					     IXGBE_FCPTR_ALIGN, PAGE_SIZE);
-		if (!fcoe->pool)
-			e_err(drv, "failed to allocated FCoE DDP pool\n");
-
 		spin_lock_init(&fcoe->lock);
+
+		ixgbe_fcoe_ddp_pools_alloc(adapter);
+		if (!fcoe->pool) {
+			e_err(drv, "failed to alloc percpu fcoe DDP pools\n");
+			return;
+		}
 
 		/* Extra buffer to be shared by all DDPs for HW work around */
 		fcoe->extra_ddp_buffer = kmalloc(IXGBE_FCBUFF_MIN, GFP_ATOMIC);
 		if (fcoe->extra_ddp_buffer == NULL) {
 			e_err(drv, "failed to allocated extra DDP buffer\n");
-			goto out_extra_ddp_buffer_alloc;
+			goto out_ddp_pools;
 		}
 
 		fcoe->extra_ddp_buffer_dma =
···
 		if (dma_mapping_error(&adapter->pdev->dev,
 				      fcoe->extra_ddp_buffer_dma)) {
 			e_err(drv, "failed to map extra DDP buffer\n");
-			goto out_extra_ddp_buffer_dma;
+			goto out_extra_ddp_buffer;
 		}
 	}
 
···
 
 	return;
 
-out_extra_ddp_buffer_dma:
+out_extra_ddp_buffer:
 	kfree(fcoe->extra_ddp_buffer);
-out_extra_ddp_buffer_alloc:
-	pci_pool_destroy(fcoe->pool);
-	fcoe->pool = NULL;
+out_ddp_pools:
+	ixgbe_fcoe_ddp_pools_free(fcoe);
 }
 
 /**
···
 	int i;
 	struct ixgbe_fcoe *fcoe = &adapter->fcoe;
 
-	/* release ddp resource */
-	if (fcoe->pool) {
-		for (i = 0; i < IXGBE_FCOE_DDP_MAX; i++)
-			ixgbe_fcoe_ddp_put(adapter->netdev, i);
-		dma_unmap_single(&adapter->pdev->dev,
-				 fcoe->extra_ddp_buffer_dma,
-				 IXGBE_FCBUFF_MIN,
-				 DMA_FROM_DEVICE);
-		kfree(fcoe->extra_ddp_buffer);
-		pci_pool_destroy(fcoe->pool);
-		fcoe->pool = NULL;
-	}
+	if (!fcoe->pool)
+		return;
+
+	for (i = 0; i < IXGBE_FCOE_DDP_MAX; i++)
+		ixgbe_fcoe_ddp_put(adapter->netdev, i);
+	dma_unmap_single(&adapter->pdev->dev,
+			 fcoe->extra_ddp_buffer_dma,
+			 IXGBE_FCBUFF_MIN,
+			 DMA_FROM_DEVICE);
+	kfree(fcoe->extra_ddp_buffer);
+	ixgbe_fcoe_ddp_pools_free(fcoe);
 }
 
 /**

drivers/net/ixgbe/ixgbe_fcoe.h

···
 	struct scatterlist *sgl;
 	dma_addr_t udp;
 	u64 *udl;
+	struct pci_pool *pool;
 };
 
 struct ixgbe_fcoe {
+	struct pci_pool **pool;
+	atomic_t refcnt;
+	spinlock_t lock;
+	struct ixgbe_fcoe_ddp ddp[IXGBE_FCOE_DDP_MAX];
+	unsigned char *extra_ddp_buffer;
+	dma_addr_t extra_ddp_buffer_dma;
+	unsigned long mode;
 #ifdef CONFIG_IXGBE_DCB
 	u8 tc;
 	u8 up;
 #endif
-	unsigned long mode;
-	atomic_t refcnt;
-	spinlock_t lock;
-	struct pci_pool *pool;
-	struct ixgbe_fcoe_ddp ddp[IXGBE_FCOE_DDP_MAX];
-	unsigned char *extra_ddp_buffer;
-	dma_addr_t extra_ddp_buffer_dma;
 };
 
 #endif /* _IXGBE_FCOE_H */