summaryrefslogtreecommitdiffstats
path: root/drivers/net/mlx4
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/net/mlx4')
-rw-r--r--drivers/net/mlx4/catas.c106
-rw-r--r--drivers/net/mlx4/cmd.c14
-rw-r--r--drivers/net/mlx4/cq.c2
-rw-r--r--drivers/net/mlx4/eq.c69
-rw-r--r--drivers/net/mlx4/fw.c2
-rw-r--r--drivers/net/mlx4/icm.c134
-rw-r--r--drivers/net/mlx4/icm.h9
-rw-r--r--drivers/net/mlx4/intf.c2
-rw-r--r--drivers/net/mlx4/main.c154
-rw-r--r--drivers/net/mlx4/mcg.c2
-rw-r--r--drivers/net/mlx4/mlx4.h23
-rw-r--r--drivers/net/mlx4/mr.c257
-rw-r--r--drivers/net/mlx4/pd.c2
-rw-r--r--drivers/net/mlx4/qp.c5
-rw-r--r--drivers/net/mlx4/reset.c3
-rw-r--r--drivers/net/mlx4/srq.c4
16 files changed, 551 insertions, 237 deletions
diff --git a/drivers/net/mlx4/catas.c b/drivers/net/mlx4/catas.c
index 1bb088aeaf71..6b32ec94b3a8 100644
--- a/drivers/net/mlx4/catas.c
+++ b/drivers/net/mlx4/catas.c
@@ -30,41 +30,133 @@
* SOFTWARE.
*/
+#include <linux/workqueue.h>
+
#include "mlx4.h"
-void mlx4_handle_catas_err(struct mlx4_dev *dev)
+enum {
+ MLX4_CATAS_POLL_INTERVAL = 5 * HZ,
+};
+
+static DEFINE_SPINLOCK(catas_lock);
+
+static LIST_HEAD(catas_list);
+static struct workqueue_struct *catas_wq;
+static struct work_struct catas_work;
+
+static int internal_err_reset = 1;
+module_param(internal_err_reset, int, 0644);
+MODULE_PARM_DESC(internal_err_reset,
+ "Reset device on internal errors if non-zero (default 1)");
+
+static void dump_err_buf(struct mlx4_dev *dev)
{
struct mlx4_priv *priv = mlx4_priv(dev);
int i;
- mlx4_err(dev, "Catastrophic error detected:\n");
+ mlx4_err(dev, "Internal error detected:\n");
for (i = 0; i < priv->fw.catas_size; ++i)
mlx4_err(dev, " buf[%02x]: %08x\n",
i, swab32(readl(priv->catas_err.map + i)));
+}
- mlx4_dispatch_event(dev, MLX4_EVENT_TYPE_LOCAL_CATAS_ERROR, 0, 0);
+static void poll_catas(unsigned long dev_ptr)
+{
+ struct mlx4_dev *dev = (struct mlx4_dev *) dev_ptr;
+ struct mlx4_priv *priv = mlx4_priv(dev);
+
+ if (readl(priv->catas_err.map)) {
+ dump_err_buf(dev);
+
+ mlx4_dispatch_event(dev, MLX4_EVENT_TYPE_LOCAL_CATAS_ERROR, 0, 0);
+
+ if (internal_err_reset) {
+ spin_lock(&catas_lock);
+ list_add(&priv->catas_err.list, &catas_list);
+ spin_unlock(&catas_lock);
+
+ queue_work(catas_wq, &catas_work);
+ }
+ } else
+ mod_timer(&priv->catas_err.timer,
+ round_jiffies(jiffies + MLX4_CATAS_POLL_INTERVAL));
}
-void mlx4_map_catas_buf(struct mlx4_dev *dev)
+static void catas_reset(struct work_struct *work)
+{
+ struct mlx4_priv *priv, *tmppriv;
+ struct mlx4_dev *dev;
+
+ LIST_HEAD(tlist);
+ int ret;
+
+ spin_lock_irq(&catas_lock);
+ list_splice_init(&catas_list, &tlist);
+ spin_unlock_irq(&catas_lock);
+
+ list_for_each_entry_safe(priv, tmppriv, &tlist, catas_err.list) {
+ ret = mlx4_restart_one(priv->dev.pdev);
+ dev = &priv->dev;
+ if (ret)
+ mlx4_err(dev, "Reset failed (%d)\n", ret);
+ else
+ mlx4_dbg(dev, "Reset succeeded\n");
+ }
+}
+
+void mlx4_start_catas_poll(struct mlx4_dev *dev)
{
struct mlx4_priv *priv = mlx4_priv(dev);
unsigned long addr;
+ INIT_LIST_HEAD(&priv->catas_err.list);
+ init_timer(&priv->catas_err.timer);
+ priv->catas_err.map = NULL;
+
addr = pci_resource_start(dev->pdev, priv->fw.catas_bar) +
priv->fw.catas_offset;
priv->catas_err.map = ioremap(addr, priv->fw.catas_size * 4);
- if (!priv->catas_err.map)
- mlx4_warn(dev, "Failed to map catastrophic error buffer at 0x%lx\n",
+ if (!priv->catas_err.map) {
+ mlx4_warn(dev, "Failed to map internal error buffer at 0x%lx\n",
addr);
+ return;
+ }
+ priv->catas_err.timer.data = (unsigned long) dev;
+ priv->catas_err.timer.function = poll_catas;
+ priv->catas_err.timer.expires =
+ round_jiffies(jiffies + MLX4_CATAS_POLL_INTERVAL);
+ add_timer(&priv->catas_err.timer);
}
-void mlx4_unmap_catas_buf(struct mlx4_dev *dev)
+void mlx4_stop_catas_poll(struct mlx4_dev *dev)
{
struct mlx4_priv *priv = mlx4_priv(dev);
+ del_timer_sync(&priv->catas_err.timer);
+
if (priv->catas_err.map)
iounmap(priv->catas_err.map);
+
+ spin_lock_irq(&catas_lock);
+ list_del(&priv->catas_err.list);
+ spin_unlock_irq(&catas_lock);
+}
+
+int __init mlx4_catas_init(void)
+{
+ INIT_WORK(&catas_work, catas_reset);
+
+ catas_wq = create_singlethread_workqueue("mlx4_err");
+ if (!catas_wq)
+ return -ENOMEM;
+
+ return 0;
+}
+
+void mlx4_catas_cleanup(void)
+{
+ destroy_workqueue(catas_wq);
}
diff --git a/drivers/net/mlx4/cmd.c b/drivers/net/mlx4/cmd.c
index c1f81a993f5d..db49051b97b1 100644
--- a/drivers/net/mlx4/cmd.c
+++ b/drivers/net/mlx4/cmd.c
@@ -95,7 +95,7 @@ enum {
};
enum {
- GO_BIT_TIMEOUT = 10000
+ GO_BIT_TIMEOUT_MSECS = 10000
};
struct mlx4_cmd_context {
@@ -155,7 +155,7 @@ static int mlx4_cmd_post(struct mlx4_dev *dev, u64 in_param, u64 out_param,
end = jiffies;
if (event)
- end += HZ * 10;
+ end += msecs_to_jiffies(GO_BIT_TIMEOUT_MSECS);
while (cmd_pending(dev)) {
if (time_after_eq(jiffies, end))
@@ -184,6 +184,13 @@ static int mlx4_cmd_post(struct mlx4_dev *dev, u64 in_param, u64 out_param,
(event ? (1 << HCR_E_BIT) : 0) |
(op_modifier << HCR_OPMOD_SHIFT) |
op), hcr + 6);
+
+ /*
+ * Make sure that our HCR writes don't get mixed in with
+ * writes from another CPU starting a FW command.
+ */
+ mmiowb();
+
cmd->toggle = cmd->toggle ^ 1;
ret = 0;
@@ -246,8 +253,6 @@ void mlx4_cmd_event(struct mlx4_dev *dev, u16 token, u8 status, u64 out_param)
context->result = mlx4_status_to_errno(status);
context->out_param = out_param;
- context->token += priv->cmd.token_mask + 1;
-
complete(&context->done);
}
@@ -264,6 +269,7 @@ static int mlx4_cmd_wait(struct mlx4_dev *dev, u64 in_param, u64 *out_param,
spin_lock(&cmd->context_lock);
BUG_ON(cmd->free_head < 0);
context = &cmd->context[cmd->free_head];
+ context->token += cmd->token_mask + 1;
cmd->free_head = context->next;
spin_unlock(&cmd->context_lock);
diff --git a/drivers/net/mlx4/cq.c b/drivers/net/mlx4/cq.c
index 39253d0c1590..d4441fee3d80 100644
--- a/drivers/net/mlx4/cq.c
+++ b/drivers/net/mlx4/cq.c
@@ -231,7 +231,7 @@ void mlx4_cq_free(struct mlx4_dev *dev, struct mlx4_cq *cq)
}
EXPORT_SYMBOL_GPL(mlx4_cq_free);
-int __devinit mlx4_init_cq_table(struct mlx4_dev *dev)
+int mlx4_init_cq_table(struct mlx4_dev *dev)
{
struct mlx4_cq_table *cq_table = &mlx4_priv(dev)->cq_table;
int err;
diff --git a/drivers/net/mlx4/eq.c b/drivers/net/mlx4/eq.c
index 27a82cecd693..9c36c2034030 100644
--- a/drivers/net/mlx4/eq.c
+++ b/drivers/net/mlx4/eq.c
@@ -89,14 +89,12 @@ struct mlx4_eq_context {
(1ull << MLX4_EVENT_TYPE_PATH_MIG_FAILED) | \
(1ull << MLX4_EVENT_TYPE_WQ_INVAL_REQ_ERROR) | \
(1ull << MLX4_EVENT_TYPE_WQ_ACCESS_ERROR) | \
- (1ull << MLX4_EVENT_TYPE_LOCAL_CATAS_ERROR) | \
(1ull << MLX4_EVENT_TYPE_PORT_CHANGE) | \
(1ull << MLX4_EVENT_TYPE_ECC_DETECT) | \
(1ull << MLX4_EVENT_TYPE_SRQ_CATAS_ERROR) | \
(1ull << MLX4_EVENT_TYPE_SRQ_QP_LAST_WQE) | \
(1ull << MLX4_EVENT_TYPE_SRQ_LIMIT) | \
(1ull << MLX4_EVENT_TYPE_CMD))
-#define MLX4_CATAS_EVENT_MASK (1ull << MLX4_EVENT_TYPE_LOCAL_CATAS_ERROR)
struct mlx4_eqe {
u8 reserved1;
@@ -264,7 +262,7 @@ static irqreturn_t mlx4_interrupt(int irq, void *dev_ptr)
writel(priv->eq_table.clr_mask, priv->eq_table.clr_int);
- for (i = 0; i < MLX4_EQ_CATAS; ++i)
+ for (i = 0; i < MLX4_NUM_EQ; ++i)
work |= mlx4_eq_int(dev, &priv->eq_table.eq[i]);
return IRQ_RETVAL(work);
@@ -281,14 +279,6 @@ static irqreturn_t mlx4_msi_x_interrupt(int irq, void *eq_ptr)
return IRQ_HANDLED;
}
-static irqreturn_t mlx4_catas_interrupt(int irq, void *dev_ptr)
-{
- mlx4_handle_catas_err(dev_ptr);
-
- /* MSI-X vectors always belong to us */
- return IRQ_HANDLED;
-}
-
static int mlx4_MAP_EQ(struct mlx4_dev *dev, u64 event_mask, int unmap,
int eq_num)
{
@@ -310,8 +300,7 @@ static int mlx4_HW2SW_EQ(struct mlx4_dev *dev, struct mlx4_cmd_mailbox *mailbox,
MLX4_CMD_TIME_CLASS_A);
}
-static void __devinit __iomem *mlx4_get_eq_uar(struct mlx4_dev *dev,
- struct mlx4_eq *eq)
+static void __iomem *mlx4_get_eq_uar(struct mlx4_dev *dev, struct mlx4_eq *eq)
{
struct mlx4_priv *priv = mlx4_priv(dev);
int index;
@@ -333,8 +322,8 @@ static void __devinit __iomem *mlx4_get_eq_uar(struct mlx4_dev *dev,
return priv->eq_table.uar_map[index] + 0x800 + 8 * (eq->eqn % 4);
}
-static int __devinit mlx4_create_eq(struct mlx4_dev *dev, int nent,
- u8 intr, struct mlx4_eq *eq)
+static int mlx4_create_eq(struct mlx4_dev *dev, int nent,
+ u8 intr, struct mlx4_eq *eq)
{
struct mlx4_priv *priv = mlx4_priv(dev);
struct mlx4_cmd_mailbox *mailbox;
@@ -490,14 +479,12 @@ static void mlx4_free_irqs(struct mlx4_dev *dev)
if (eq_table->have_irq)
free_irq(dev->pdev->irq, dev);
- for (i = 0; i < MLX4_EQ_CATAS; ++i)
+ for (i = 0; i < MLX4_NUM_EQ; ++i)
if (eq_table->eq[i].have_irq)
free_irq(eq_table->eq[i].irq, eq_table->eq + i);
- if (eq_table->eq[MLX4_EQ_CATAS].have_irq)
- free_irq(eq_table->eq[MLX4_EQ_CATAS].irq, dev);
}
-static int __devinit mlx4_map_clr_int(struct mlx4_dev *dev)
+static int mlx4_map_clr_int(struct mlx4_dev *dev)
{
struct mlx4_priv *priv = mlx4_priv(dev);
@@ -518,7 +505,7 @@ static void mlx4_unmap_clr_int(struct mlx4_dev *dev)
iounmap(priv->clr_base);
}
-int __devinit mlx4_map_eq_icm(struct mlx4_dev *dev, u64 icm_virt)
+int mlx4_map_eq_icm(struct mlx4_dev *dev, u64 icm_virt)
{
struct mlx4_priv *priv = mlx4_priv(dev);
int ret;
@@ -560,7 +547,7 @@ void mlx4_unmap_eq_icm(struct mlx4_dev *dev)
__free_page(priv->eq_table.icm_page);
}
-int __devinit mlx4_init_eq_table(struct mlx4_dev *dev)
+int mlx4_init_eq_table(struct mlx4_dev *dev)
{
struct mlx4_priv *priv = mlx4_priv(dev);
int err;
@@ -598,32 +585,19 @@ int __devinit mlx4_init_eq_table(struct mlx4_dev *dev)
if (dev->flags & MLX4_FLAG_MSI_X) {
static const char *eq_name[] = {
[MLX4_EQ_COMP] = DRV_NAME " (comp)",
- [MLX4_EQ_ASYNC] = DRV_NAME " (async)",
- [MLX4_EQ_CATAS] = DRV_NAME " (catas)"
+ [MLX4_EQ_ASYNC] = DRV_NAME " (async)"
};
- err = mlx4_create_eq(dev, 1, MLX4_EQ_CATAS,
- &priv->eq_table.eq[MLX4_EQ_CATAS]);
- if (err)
- goto err_out_async;
-
- for (i = 0; i < MLX4_EQ_CATAS; ++i) {
+ for (i = 0; i < MLX4_NUM_EQ; ++i) {
err = request_irq(priv->eq_table.eq[i].irq,
mlx4_msi_x_interrupt,
0, eq_name[i], priv->eq_table.eq + i);
if (err)
- goto err_out_catas;
+ goto err_out_async;
priv->eq_table.eq[i].have_irq = 1;
}
- err = request_irq(priv->eq_table.eq[MLX4_EQ_CATAS].irq,
- mlx4_catas_interrupt, 0,
- eq_name[MLX4_EQ_CATAS], dev);
- if (err)
- goto err_out_catas;
-
- priv->eq_table.eq[MLX4_EQ_CATAS].have_irq = 1;
} else {
err = request_irq(dev->pdev->irq, mlx4_interrupt,
IRQF_SHARED, DRV_NAME, dev);
@@ -639,22 +613,11 @@ int __devinit mlx4_init_eq_table(struct mlx4_dev *dev)
mlx4_warn(dev, "MAP_EQ for async EQ %d failed (%d)\n",
priv->eq_table.eq[MLX4_EQ_ASYNC].eqn, err);
- for (i = 0; i < MLX4_EQ_CATAS; ++i)
+ for (i = 0; i < MLX4_NUM_EQ; ++i)
eq_set_ci(&priv->eq_table.eq[i], 1);
- if (dev->flags & MLX4_FLAG_MSI_X) {
- err = mlx4_MAP_EQ(dev, MLX4_CATAS_EVENT_MASK, 0,
- priv->eq_table.eq[MLX4_EQ_CATAS].eqn);
- if (err)
- mlx4_warn(dev, "MAP_EQ for catas EQ %d failed (%d)\n",
- priv->eq_table.eq[MLX4_EQ_CATAS].eqn, err);
- }
-
return 0;
-err_out_catas:
- mlx4_free_eq(dev, &priv->eq_table.eq[MLX4_EQ_CATAS]);
-
err_out_async:
mlx4_free_eq(dev, &priv->eq_table.eq[MLX4_EQ_ASYNC]);
@@ -675,19 +638,13 @@ void mlx4_cleanup_eq_table(struct mlx4_dev *dev)
struct mlx4_priv *priv = mlx4_priv(dev);
int i;
- if (dev->flags & MLX4_FLAG_MSI_X)
- mlx4_MAP_EQ(dev, MLX4_CATAS_EVENT_MASK, 1,
- priv->eq_table.eq[MLX4_EQ_CATAS].eqn);
-
mlx4_MAP_EQ(dev, MLX4_ASYNC_EVENT_MASK, 1,
priv->eq_table.eq[MLX4_EQ_ASYNC].eqn);
mlx4_free_irqs(dev);
- for (i = 0; i < MLX4_EQ_CATAS; ++i)
+ for (i = 0; i < MLX4_NUM_EQ; ++i)
mlx4_free_eq(dev, &priv->eq_table.eq[i]);
- if (dev->flags & MLX4_FLAG_MSI_X)
- mlx4_free_eq(dev, &priv->eq_table.eq[MLX4_EQ_CATAS]);
mlx4_unmap_clr_int(dev);
diff --git a/drivers/net/mlx4/fw.c b/drivers/net/mlx4/fw.c
index c45cbe43a0c4..6471d33afb7d 100644
--- a/drivers/net/mlx4/fw.c
+++ b/drivers/net/mlx4/fw.c
@@ -76,7 +76,7 @@ static void dump_dev_cap_flags(struct mlx4_dev *dev, u32 flags)
[ 0] = "RC transport",
[ 1] = "UC transport",
[ 2] = "UD transport",
- [ 3] = "SRC transport",
+ [ 3] = "XRC transport",
[ 4] = "reliable multicast",
[ 5] = "FCoIB support",
[ 6] = "SRQ support",
diff --git a/drivers/net/mlx4/icm.c b/drivers/net/mlx4/icm.c
index b7a4aa8476fb..4b3c109d5eae 100644
--- a/drivers/net/mlx4/icm.c
+++ b/drivers/net/mlx4/icm.c
@@ -34,6 +34,7 @@
#include <linux/init.h>
#include <linux/errno.h>
#include <linux/mm.h>
+#include <linux/scatterlist.h>
#include <linux/mlx4/cmd.h>
@@ -50,19 +51,41 @@ enum {
MLX4_TABLE_CHUNK_SIZE = 1 << 18
};
-void mlx4_free_icm(struct mlx4_dev *dev, struct mlx4_icm *icm)
+static void mlx4_free_icm_pages(struct mlx4_dev *dev, struct mlx4_icm_chunk *chunk)
{
- struct mlx4_icm_chunk *chunk, *tmp;
int i;
- list_for_each_entry_safe(chunk, tmp, &icm->chunk_list, list) {
- if (chunk->nsg > 0)
- pci_unmap_sg(dev->pdev, chunk->mem, chunk->npages,
- PCI_DMA_BIDIRECTIONAL);
+ if (chunk->nsg > 0)
+ pci_unmap_sg(dev->pdev, chunk->mem, chunk->npages,
+ PCI_DMA_BIDIRECTIONAL);
+
+ for (i = 0; i < chunk->npages; ++i)
+ __free_pages(chunk->mem[i].page,
+ get_order(chunk->mem[i].length));
+}
+
+static void mlx4_free_icm_coherent(struct mlx4_dev *dev, struct mlx4_icm_chunk *chunk)
+{
+ int i;
+
+ for (i = 0; i < chunk->npages; ++i)
+ dma_free_coherent(&dev->pdev->dev, chunk->mem[i].length,
+ lowmem_page_address(chunk->mem[i].page),
+ sg_dma_address(&chunk->mem[i]));
+}
+
+void mlx4_free_icm(struct mlx4_dev *dev, struct mlx4_icm *icm, int coherent)
+{
+ struct mlx4_icm_chunk *chunk, *tmp;
- for (i = 0; i < chunk->npages; ++i)
- __free_pages(chunk->mem[i].page,
- get_order(chunk->mem[i].length));
+ if (!icm)
+ return;
+
+ list_for_each_entry_safe(chunk, tmp, &icm->chunk_list, list) {
+ if (coherent)
+ mlx4_free_icm_coherent(dev, chunk);
+ else
+ mlx4_free_icm_pages(dev, chunk);
kfree(chunk);
}
@@ -70,16 +93,45 @@ void mlx4_free_icm(struct mlx4_dev *dev, struct mlx4_icm *icm)
kfree(icm);
}
+static int mlx4_alloc_icm_pages(struct scatterlist *mem, int order, gfp_t gfp_mask)
+{
+ mem->page = alloc_pages(gfp_mask, order);
+ if (!mem->page)
+ return -ENOMEM;
+
+ mem->length = PAGE_SIZE << order;
+ mem->offset = 0;
+ return 0;
+}
+
+static int mlx4_alloc_icm_coherent(struct device *dev, struct scatterlist *mem,
+ int order, gfp_t gfp_mask)
+{
+ void *buf = dma_alloc_coherent(dev, PAGE_SIZE << order,
+ &sg_dma_address(mem), gfp_mask);
+ if (!buf)
+ return -ENOMEM;
+
+ sg_set_buf(mem, buf, PAGE_SIZE << order);
+ BUG_ON(mem->offset);
+ sg_dma_len(mem) = PAGE_SIZE << order;
+ return 0;
+}
+
struct mlx4_icm *mlx4_alloc_icm(struct mlx4_dev *dev, int npages,
- gfp_t gfp_mask)
+ gfp_t gfp_mask, int coherent)
{
struct mlx4_icm *icm;
struct mlx4_icm_chunk *chunk = NULL;
int cur_order;
+ int ret;
+
+ /* We use sg_set_buf for coherent allocs, which assumes low memory */
+ BUG_ON(coherent && (gfp_mask & __GFP_HIGHMEM));
icm = kmalloc(sizeof *icm, gfp_mask & ~(__GFP_HIGHMEM | __GFP_NOWARN));
if (!icm)
- return icm;
+ return NULL;
icm->refcount = 0;
INIT_LIST_HEAD(&icm->chunk_list);
@@ -101,12 +153,20 @@ struct mlx4_icm *mlx4_alloc_icm(struct mlx4_dev *dev, int npages,
while (1 << cur_order > npages)
--cur_order;
- chunk->mem[chunk->npages].page = alloc_pages(gfp_mask, cur_order);
- if (chunk->mem[chunk->npages].page) {
- chunk->mem[chunk->npages].length = PAGE_SIZE << cur_order;
- chunk->mem[chunk->npages].offset = 0;
+ if (coherent)
+ ret = mlx4_alloc_icm_coherent(&dev->pdev->dev,
+ &chunk->mem[chunk->npages],
+ cur_order, gfp_mask);
+ else
+ ret = mlx4_alloc_icm_pages(&chunk->mem[chunk->npages],
+ cur_order, gfp_mask);
+
+ if (!ret) {
+ ++chunk->npages;
- if (++chunk->npages == MLX4_ICM_CHUNK_LEN) {
+ if (coherent)
+ ++chunk->nsg;
+ else if (chunk->npages == MLX4_ICM_CHUNK_LEN) {
chunk->nsg = pci_map_sg(dev->pdev, chunk->mem,
chunk->npages,
PCI_DMA_BIDIRECTIONAL);
@@ -125,7 +185,7 @@ struct mlx4_icm *mlx4_alloc_icm(struct mlx4_dev *dev, int npages,
}
}
- if (chunk) {
+ if (!coherent && chunk) {
chunk->nsg = pci_map_sg(dev->pdev, chunk->mem,
chunk->npages,
PCI_DMA_BIDIRECTIONAL);
@@ -137,7 +197,7 @@ struct mlx4_icm *mlx4_alloc_icm(struct mlx4_dev *dev, int npages,
return icm;
fail:
- mlx4_free_icm(dev, icm);
+ mlx4_free_icm(dev, icm, coherent);
return NULL;
}
@@ -202,7 +262,7 @@ int mlx4_table_get(struct mlx4_dev *dev, struct mlx4_icm_table *table, int obj)
table->icm[i] = mlx4_alloc_icm(dev, MLX4_TABLE_CHUNK_SIZE >> PAGE_SHIFT,
(table->lowmem ? GFP_KERNEL : GFP_HIGHUSER) |
- __GFP_NOWARN);
+ __GFP_NOWARN, table->coherent);
if (!table->icm[i]) {
ret = -ENOMEM;
goto out;
@@ -210,7 +270,7 @@ int mlx4_table_get(struct mlx4_dev *dev, struct mlx4_icm_table *table, int obj)
if (mlx4_MAP_ICM(dev, table->icm[i], table->virt +
(u64) i * MLX4_TABLE_CHUNK_SIZE)) {
- mlx4_free_icm(dev, table->icm[i]);
+ mlx4_free_icm(dev, table->icm[i], table->coherent);
table->icm[i] = NULL;
ret = -ENOMEM;
goto out;
@@ -234,16 +294,16 @@ void mlx4_table_put(struct mlx4_dev *dev, struct mlx4_icm_table *table, int obj)
if (--table->icm[i]->refcount == 0) {
mlx4_UNMAP_ICM(dev, table->virt + i * MLX4_TABLE_CHUNK_SIZE,
MLX4_TABLE_CHUNK_SIZE / MLX4_ICM_PAGE_SIZE);
- mlx4_free_icm(dev, table->icm[i]);
+ mlx4_free_icm(dev, table->icm[i], table->coherent);
table->icm[i] = NULL;
}
mutex_unlock(&table->mutex);
}
-void *mlx4_table_find(struct mlx4_icm_table *table, int obj)
+void *mlx4_table_find(struct mlx4_icm_table *table, int obj, dma_addr_t *dma_handle)
{
- int idx, offset, i;
+ int idx, offset, dma_offset, i;
struct mlx4_icm_chunk *chunk;
struct mlx4_icm *icm;
struct page *page = NULL;
@@ -253,15 +313,26 @@ void *mlx4_table_find(struct mlx4_icm_table *table, int obj)
mutex_lock(&table->mutex);
- idx = obj & (table->num_obj - 1);
- icm = table->icm[idx / (MLX4_TABLE_CHUNK_SIZE / table->obj_size)];
- offset = idx % (MLX4_TABLE_CHUNK_SIZE / table->obj_size);
+ idx = (obj & (table->num_obj - 1)) * table->obj_size;
+ icm = table->icm[idx / MLX4_TABLE_CHUNK_SIZE];
+ dma_offset = offset = idx % MLX4_TABLE_CHUNK_SIZE;
if (!icm)
goto out;
list_for_each_entry(chunk, &icm->chunk_list, list) {
for (i = 0; i < chunk->npages; ++i) {
+ if (dma_handle && dma_offset >= 0) {
+ if (sg_dma_len(&chunk->mem[i]) > dma_offset)
+ *dma_handle = sg_dma_address(&chunk->mem[i]) +
+ dma_offset;
+ dma_offset -= sg_dma_len(&chunk->mem[i]);
+ }
+ /*
+ * DMA mapping can merge pages but not split them,
+ * so if we found the page, dma_handle has already
+ * been assigned to.
+ */
if (chunk->mem[i].length > offset) {
page = chunk->mem[i].page;
goto out;
@@ -309,7 +380,7 @@ void mlx4_table_put_range(struct mlx4_dev *dev, struct mlx4_icm_table *table,
int mlx4_init_icm_table(struct mlx4_dev *dev, struct mlx4_icm_table *table,
u64 virt, int obj_size, int nobj, int reserved,
- int use_lowmem)
+ int use_lowmem, int use_coherent)
{
int obj_per_chunk;
int num_icm;
@@ -327,6 +398,7 @@ int mlx4_init_icm_table(struct mlx4_dev *dev, struct mlx4_icm_table *table,
table->num_obj = nobj;
table->obj_size = obj_size;
table->lowmem = use_lowmem;
+ table->coherent = use_coherent;
mutex_init(&table->mutex);
for (i = 0; i * MLX4_TABLE_CHUNK_SIZE < reserved * obj_size; ++i) {
@@ -336,11 +408,11 @@ int mlx4_init_icm_table(struct mlx4_dev *dev, struct mlx4_icm_table *table,
table->icm[i] = mlx4_alloc_icm(dev, chunk_size >> PAGE_SHIFT,
(use_lowmem ? GFP_KERNEL : GFP_HIGHUSER) |
- __GFP_NOWARN);
+ __GFP_NOWARN, use_coherent);
if (!table->icm[i])
goto err;
if (mlx4_MAP_ICM(dev, table->icm[i], virt + i * MLX4_TABLE_CHUNK_SIZE)) {
- mlx4_free_icm(dev, table->icm[i]);
+ mlx4_free_icm(dev, table->icm[i], use_coherent);
table->icm[i] = NULL;
goto err;
}
@@ -359,7 +431,7 @@ err:
if (table->icm[i]) {
mlx4_UNMAP_ICM(dev, virt + i * MLX4_TABLE_CHUNK_SIZE,
MLX4_TABLE_CHUNK_SIZE / MLX4_ICM_PAGE_SIZE);
- mlx4_free_icm(dev, table->icm[i]);
+ mlx4_free_icm(dev, table->icm[i], use_coherent);
}
return -ENOMEM;
@@ -373,7 +445,7 @@ void mlx4_cleanup_icm_table(struct mlx4_dev *dev, struct mlx4_icm_table *table)
if (table->icm[i]) {
mlx4_UNMAP_ICM(dev, table->virt + i * MLX4_TABLE_CHUNK_SIZE,
MLX4_TABLE_CHUNK_SIZE / MLX4_ICM_PAGE_SIZE);
- mlx4_free_icm(dev, table->icm[i]);
+ mlx4_free_icm(dev, table->icm[i], table->coherent);
}
kfree(table->icm);
diff --git a/drivers/net/mlx4/icm.h b/drivers/net/mlx4/icm.h
index bea223d879a5..6c44edf35847 100644
--- a/drivers/net/mlx4/icm.h
+++ b/drivers/net/mlx4/icm.h
@@ -67,8 +67,9 @@ struct mlx4_icm_iter {
struct mlx4_dev;
-struct mlx4_icm *mlx4_alloc_icm(struct mlx4_dev *dev, int npages, gfp_t gfp_mask);
-void mlx4_free_icm(struct mlx4_dev *dev, struct mlx4_icm *icm);
+struct mlx4_icm *mlx4_alloc_icm(struct mlx4_dev *dev, int npages,
+ gfp_t gfp_mask, int coherent);
+void mlx4_free_icm(struct mlx4_dev *dev, struct mlx4_icm *icm, int coherent);
int mlx4_table_get(struct mlx4_dev *dev, struct mlx4_icm_table *table, int obj);
void mlx4_table_put(struct mlx4_dev *dev, struct mlx4_icm_table *table, int obj);
@@ -78,11 +79,11 @@ void mlx4_table_put_range(struct mlx4_dev *dev, struct mlx4_icm_table *table,
int start, int end);
int mlx4_init_icm_table(struct mlx4_dev *dev, struct mlx4_icm_table *table,
u64 virt, int obj_size, int nobj, int reserved,
- int use_lowmem);
+ int use_lowmem, int use_coherent);
void mlx4_cleanup_icm_table(struct mlx4_dev *dev, struct mlx4_icm_table *table);
int mlx4_table_get(struct mlx4_dev *dev, struct mlx4_icm_table *table, int obj);
void mlx4_table_put(struct mlx4_dev *dev, struct mlx4_icm_table *table, int obj);
-void *mlx4_table_find(struct mlx4_icm_table *table, int obj);
+void *mlx4_table_find(struct mlx4_icm_table *table, int obj, dma_addr_t *dma_handle);
int mlx4_table_get_range(struct mlx4_dev *dev, struct mlx4_icm_table *table,
int start, int end);
void mlx4_table_put_range(struct mlx4_dev *dev, struct mlx4_icm_table *table,
diff --git a/drivers/net/mlx4/intf.c b/drivers/net/mlx4/intf.c
index 9ae951bf6aa6..be5d9e90ccf2 100644
--- a/drivers/net/mlx4/intf.c
+++ b/drivers/net/mlx4/intf.c
@@ -142,6 +142,7 @@ int mlx4_register_device(struct mlx4_dev *dev)
mlx4_add_device(intf, priv);
mutex_unlock(&intf_mutex);
+ mlx4_start_catas_poll(dev);
return 0;
}
@@ -151,6 +152,7 @@ void mlx4_unregister_device(struct mlx4_dev *dev)
struct mlx4_priv *priv = mlx4_priv(dev);
struct mlx4_interface *intf;
+ mlx4_stop_catas_poll(dev);
mutex_lock(&intf_mutex);
list_for_each_entry(intf, &intf_list, list)
diff --git a/drivers/net/mlx4/main.c b/drivers/net/mlx4/main.c
index a4f2e0475a71..e029b8afbd37 100644
--- a/drivers/net/mlx4/main.c
+++ b/drivers/net/mlx4/main.c
@@ -61,7 +61,7 @@ MODULE_PARM_DESC(debug_level, "Enable debug tracing if > 0");
#ifdef CONFIG_PCI_MSI
-static int msi_x;
+static int msi_x = 1;
module_param(msi_x, int, 0444);
MODULE_PARM_DESC(msi_x, "attempt to use MSI-X if nonzero");
@@ -78,14 +78,14 @@ static const char mlx4_version[] __devinitdata =
static struct mlx4_profile default_profile = {
.num_qp = 1 << 16,
.num_srq = 1 << 16,
- .rdmarc_per_qp = 4,
+ .rdmarc_per_qp = 1 << 4,
.num_cq = 1 << 16,
.num_mcg = 1 << 13,
.num_mpt = 1 << 17,
.num_mtt = 1 << 20,
};
-static int __devinit mlx4_dev_cap(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
+static int mlx4_dev_cap(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
{
int err;
int i;
@@ -149,7 +149,8 @@ static int __devinit mlx4_dev_cap(struct mlx4_dev *dev, struct mlx4_dev_cap *dev
dev->caps.max_cqes = dev_cap->max_cq_sz - 1;
dev->caps.reserved_cqs = dev_cap->reserved_cqs;
dev->caps.reserved_eqs = dev_cap->reserved_eqs;
- dev->caps.reserved_mtts = dev_cap->reserved_mtts;
+ dev->caps.reserved_mtts = DIV_ROUND_UP(dev_cap->reserved_mtts,
+ MLX4_MTT_ENTRY_PER_SEG);
dev->caps.reserved_mrws = dev_cap->reserved_mrws;
dev->caps.reserved_uars = dev_cap->reserved_uars;
dev->caps.reserved_pds = dev_cap->reserved_pds;
@@ -168,7 +169,7 @@ static int __devinit mlx4_load_fw(struct mlx4_dev *dev)
int err;
priv->fw.fw_icm = mlx4_alloc_icm(dev, priv->fw.fw_pages,
- GFP_HIGHUSER | __GFP_NOWARN);
+ GFP_HIGHUSER | __GFP_NOWARN, 0);
if (!priv->fw.fw_icm) {
mlx4_err(dev, "Couldn't allocate FW area, aborting.\n");
return -ENOMEM;
@@ -192,7 +193,7 @@ err_unmap_fa:
mlx4_UNMAP_FA(dev);
err_free:
- mlx4_free_icm(dev, priv->fw.fw_icm);
+ mlx4_free_icm(dev, priv->fw.fw_icm, 0);
return err;
}
@@ -207,7 +208,7 @@ static int __devinit mlx4_init_cmpt_table(struct mlx4_dev *dev, u64 cmpt_base,
((u64) (MLX4_CMPT_TYPE_QP *
cmpt_entry_sz) << MLX4_CMPT_SHIFT),
cmpt_entry_sz, dev->caps.num_qps,
- dev->caps.reserved_qps, 0);
+ dev->caps.reserved_qps, 0, 0);
if (err)
goto err;
@@ -216,7 +217,7 @@ static int __devinit mlx4_init_cmpt_table(struct mlx4_dev *dev, u64 cmpt_base,
((u64) (MLX4_CMPT_TYPE_SRQ *
cmpt_entry_sz) << MLX4_CMPT_SHIFT),
cmpt_entry_sz, dev->caps.num_srqs,
- dev->caps.reserved_srqs, 0);
+ dev->caps.reserved_srqs, 0, 0);
if (err)
goto err_qp;
@@ -225,7 +226,7 @@ static int __devinit mlx4_init_cmpt_table(struct mlx4_dev *dev, u64 cmpt_base,
((u64) (MLX4_CMPT_TYPE_CQ *
cmpt_entry_sz) << MLX4_CMPT_SHIFT),
cmpt_entry_sz, dev->caps.num_cqs,
- dev->caps.reserved_cqs, 0);
+ dev->caps.reserved_cqs, 0, 0);
if (err)
goto err_srq;
@@ -236,7 +237,7 @@ static int __devinit mlx4_init_cmpt_table(struct mlx4_dev *dev, u64 cmpt_base,
cmpt_entry_sz,
roundup_pow_of_two(MLX4_NUM_EQ +
dev->caps.reserved_eqs),
- MLX4_NUM_EQ + dev->caps.reserved_eqs, 0);
+ MLX4_NUM_EQ + dev->caps.reserved_eqs, 0, 0);
if (err)
goto err_cq;
@@ -255,10 +256,8 @@ err:
return err;
}
-static int __devinit mlx4_init_icm(struct mlx4_dev *dev,
- struct mlx4_dev_cap *dev_cap,
- struct mlx4_init_hca_param *init_hca,
- u64 icm_size)
+static int mlx4_init_icm(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap,
+ struct mlx4_init_hca_param *init_hca, u64 icm_size)
{
struct mlx4_priv *priv = mlx4_priv(dev);
u64 aux_pages;
@@ -275,7 +274,7 @@ static int __devinit mlx4_init_icm(struct mlx4_dev *dev,
(unsigned long long) aux_pages << 2);
priv->fw.aux_icm = mlx4_alloc_icm(dev, aux_pages,
- GFP_HIGHUSER | __GFP_NOWARN);
+ GFP_HIGHUSER | __GFP_NOWARN, 0);
if (!priv->fw.aux_icm) {
mlx4_err(dev, "Couldn't allocate aux memory, aborting.\n");
return -ENOMEM;
@@ -299,11 +298,22 @@ static int __devinit mlx4_init_icm(struct mlx4_dev *dev,
goto err_unmap_cmpt;
}
+ /*
+ * Reserved MTT entries must be aligned up to a cacheline
+ * boundary, since the FW will write to them, while the driver
+ * writes to all other MTT entries. (The variable
+ * dev->caps.mtt_entry_sz below is really the MTT segment
+ * size, not the raw entry size)
+ */
+ dev->caps.reserved_mtts =
+ ALIGN(dev->caps.reserved_mtts * dev->caps.mtt_entry_sz,
+ dma_get_cache_alignment()) / dev->caps.mtt_entry_sz;
+
err = mlx4_init_icm_table(dev, &priv->mr_table.mtt_table,
init_hca->mtt_base,
dev->caps.mtt_entry_sz,
dev->caps.num_mtt_segs,
- dev->caps.reserved_mtts, 1);
+ dev->caps.reserved_mtts, 1, 0);
if (err) {
mlx4_err(dev, "Failed to map MTT context memory, aborting.\n");
goto err_unmap_eq;
@@ -313,7 +323,7 @@ static int __devinit mlx4_init_icm(struct mlx4_dev *dev,
init_hca->dmpt_base,
dev_cap->dmpt_entry_sz,
dev->caps.num_mpts,
- dev->caps.reserved_mrws, 1);
+ dev->caps.reserved_mrws, 1, 1);
if (err) {
mlx4_err(dev, "Failed to map dMPT context memory, aborting.\n");
goto err_unmap_mtt;
@@ -323,7 +333,7 @@ static int __devinit mlx4_init_icm(struct mlx4_dev *dev,
init_hca->qpc_base,
dev_cap->qpc_entry_sz,
dev->caps.num_qps,
- dev->caps.reserved_qps, 0);
+ dev->caps.reserved_qps, 0, 0);
if (err) {
mlx4_err(dev, "Failed to map QP context memory, aborting.\n");
goto err_unmap_dmpt;
@@ -333,7 +343,7 @@ static int __devinit mlx4_init_icm(struct mlx4_dev *dev,
init_hca->auxc_base,
dev_cap->aux_entry_sz,
dev->caps.num_qps,
- dev->caps.reserved_qps, 0);
+ dev->caps.reserved_qps, 0, 0);
if (err) {
mlx4_err(dev, "Failed to map AUXC context memory, aborting.\n");
goto err_unmap_qp;
@@ -343,7 +353,7 @@ static int __devinit mlx4_init_icm(struct mlx4_dev *dev,
init_hca->altc_base,
dev_cap->altc_entry_sz,
dev->caps.num_qps,
- dev->caps.reserved_qps, 0);
+ dev->caps.reserved_qps, 0, 0);
if (err) {
mlx4_err(dev, "Failed to map ALTC context memory, aborting.\n");
goto err_unmap_auxc;
@@ -353,7 +363,7 @@ static int __devinit mlx4_init_icm(struct mlx4_dev *dev,
init_hca->rdmarc_base,
dev_cap->rdmarc_entry_sz << priv->qp_table.rdmarc_shift,
dev->caps.num_qps,
- dev->caps.reserved_qps, 0);
+ dev->caps.reserved_qps, 0, 0);
if (err) {
mlx4_err(dev, "Failed to map RDMARC context memory, aborting\n");
goto err_unmap_altc;
@@ -363,7 +373,7 @@ static int __devinit mlx4_init_icm(struct mlx4_dev *dev,
init_hca->cqc_base,
dev_cap->cqc_entry_sz,
dev->caps.num_cqs,
- dev->caps.reserved_cqs, 0);
+ dev->caps.reserved_cqs, 0, 0);
if (err) {
mlx4_err(dev, "Failed to map CQ context memory, aborting.\n");
goto err_unmap_rdmarc;
@@ -373,7 +383,7 @@ static int __devinit mlx4_init_icm(struct mlx4_dev *dev,
init_hca->srqc_base,
dev_cap->srq_entry_sz,
dev->caps.num_srqs,
- dev->caps.reserved_srqs, 0);
+ dev->caps.reserved_srqs, 0, 0);
if (err) {
mlx4_err(dev, "Failed to map SRQ context memory, aborting.\n");
goto err_unmap_cq;
@@ -388,7 +398,7 @@ static int __devinit mlx4_init_icm(struct mlx4_dev *dev,
init_hca->mc_base, MLX4_MGM_ENTRY_SIZE,
dev->caps.num_mgms + dev->caps.num_amgms,
dev->caps.num_mgms + dev->caps.num_amgms,
- 0);
+ 0, 0);
if (err) {
mlx4_err(dev, "Failed to map MCG context memory, aborting.\n");
goto err_unmap_srq;
@@ -433,7 +443,7 @@ err_unmap_aux:
mlx4_UNMAP_ICM_AUX(dev);
err_free_aux:
- mlx4_free_icm(dev, priv->fw.aux_icm);
+ mlx4_free_icm(dev, priv->fw.aux_icm, 0);
return err;
}
@@ -458,7 +468,7 @@ static void mlx4_free_icms(struct mlx4_dev *dev)
mlx4_unmap_eq_icm(dev);
mlx4_UNMAP_ICM_AUX(dev);
- mlx4_free_icm(dev, priv->fw.aux_icm);
+ mlx4_free_icm(dev, priv->fw.aux_icm, 0);
}
static void mlx4_close_hca(struct mlx4_dev *dev)
@@ -466,10 +476,10 @@ static void mlx4_close_hca(struct mlx4_dev *dev)
mlx4_CLOSE_HCA(dev, 0);
mlx4_free_icms(dev);
mlx4_UNMAP_FA(dev);
- mlx4_free_icm(dev, mlx4_priv(dev)->fw.fw_icm);
+ mlx4_free_icm(dev, mlx4_priv(dev)->fw.fw_icm, 0);
}
-static int __devinit mlx4_init_hca(struct mlx4_dev *dev)
+static int mlx4_init_hca(struct mlx4_dev *dev)
{
struct mlx4_priv *priv = mlx4_priv(dev);
struct mlx4_adapter adapter;
@@ -524,8 +534,8 @@ static int __devinit mlx4_init_hca(struct mlx4_dev *dev)
}
priv->eq_table.inta_pin = adapter.inta_pin;
- priv->rev_id = adapter.revision_id;
- memcpy(priv->board_id, adapter.board_id, sizeof priv->board_id);
+ dev->rev_id = adapter.revision_id;
+ memcpy(dev->board_id, adapter.board_id, sizeof dev->board_id);
return 0;
@@ -537,12 +547,12 @@ err_free_icm:
err_stop_fw:
mlx4_UNMAP_FA(dev);
- mlx4_free_icm(dev, priv->fw.fw_icm);
+ mlx4_free_icm(dev, priv->fw.fw_icm, 0);
return err;
}
-static int __devinit mlx4_setup_hca(struct mlx4_dev *dev)
+static int mlx4_setup_hca(struct mlx4_dev *dev)
{
struct mlx4_priv *priv = mlx4_priv(dev);
int err;
@@ -583,13 +593,11 @@ static int __devinit mlx4_setup_hca(struct mlx4_dev *dev)
goto err_pd_table_free;
}
- mlx4_map_catas_buf(dev);
-
err = mlx4_init_eq_table(dev);
if (err) {
mlx4_err(dev, "Failed to initialize "
"event queue table, aborting.\n");
- goto err_catas_buf;
+ goto err_mr_table_free;
}
err = mlx4_cmd_use_events(dev);
@@ -601,13 +609,17 @@ static int __devinit mlx4_setup_hca(struct mlx4_dev *dev)
err = mlx4_NOP(dev);
if (err) {
- mlx4_err(dev, "NOP command failed to generate interrupt "
- "(IRQ %d), aborting.\n",
- priv->eq_table.eq[MLX4_EQ_ASYNC].irq);
- if (dev->flags & MLX4_FLAG_MSI_X)
- mlx4_err(dev, "Try again with MSI-X disabled.\n");
- else
+ if (dev->flags & MLX4_FLAG_MSI_X) {
+ mlx4_warn(dev, "NOP command failed to generate MSI-X "
+ "interrupt IRQ %d).\n",
+ priv->eq_table.eq[MLX4_EQ_ASYNC].irq);
+ mlx4_warn(dev, "Trying again without MSI-X.\n");
+ } else {
+ mlx4_err(dev, "NOP command failed to generate interrupt "
+ "(IRQ %d), aborting.\n",
+ priv->eq_table.eq[MLX4_EQ_ASYNC].irq);
mlx4_err(dev, "BIOS or ACPI interrupt routing problem?\n");
+ }
goto err_cmd_poll;
}
@@ -659,8 +671,7 @@ err_cmd_poll:
err_eq_table_free:
mlx4_cleanup_eq_table(dev);
-err_catas_buf:
- mlx4_unmap_catas_buf(dev);
+err_mr_table_free:
mlx4_cleanup_mr_table(dev);
err_pd_table_free:
@@ -708,19 +719,12 @@ no_msi:
priv->eq_table.eq[i].irq = dev->pdev->irq;
}
-static int __devinit mlx4_init_one(struct pci_dev *pdev,
- const struct pci_device_id *id)
+static int __mlx4_init_one(struct pci_dev *pdev, const struct pci_device_id *id)
{
- static int mlx4_version_printed;
struct mlx4_priv *priv;
struct mlx4_dev *dev;
int err;
- if (!mlx4_version_printed) {
- printk(KERN_INFO "%s", mlx4_version);
- ++mlx4_version_printed;
- }
-
printk(KERN_INFO PFX "Initializing %s\n",
pci_name(pdev));
@@ -806,8 +810,6 @@ static int __devinit mlx4_init_one(struct pci_dev *pdev,
goto err_free_dev;
}
- mlx4_enable_msi_x(dev);
-
if (mlx4_cmd_init(dev)) {
mlx4_err(dev, "Failed to init command interface, aborting.\n");
goto err_free_dev;
@@ -817,7 +819,15 @@ static int __devinit mlx4_init_one(struct pci_dev *pdev,
if (err)
goto err_cmd;
+ mlx4_enable_msi_x(dev);
+
err = mlx4_setup_hca(dev);
+ if (err == -EBUSY && (dev->flags & MLX4_FLAG_MSI_X)) {
+ dev->flags &= ~MLX4_FLAG_MSI_X;
+ pci_disable_msix(pdev);
+ err = mlx4_setup_hca(dev);
+ }
+
if (err)
goto err_close;
@@ -836,23 +846,20 @@ err_cleanup:
mlx4_cleanup_cq_table(dev);
mlx4_cmd_use_polling(dev);
mlx4_cleanup_eq_table(dev);
-
- mlx4_unmap_catas_buf(dev);
-
mlx4_cleanup_mr_table(dev);
mlx4_cleanup_pd_table(dev);
mlx4_cleanup_uar_table(dev);
err_close:
+ if (dev->flags & MLX4_FLAG_MSI_X)
+ pci_disable_msix(pdev);
+
mlx4_close_hca(dev);
err_cmd:
mlx4_cmd_cleanup(dev);
err_free_dev:
- if (dev->flags & MLX4_FLAG_MSI_X)
- pci_disable_msix(pdev);
-
kfree(priv);
err_release_bar2:
@@ -867,7 +874,20 @@ err_disable_pdev:
return err;
}
-static void __devexit mlx4_remove_one(struct pci_dev *pdev)
+static int __devinit mlx4_init_one(struct pci_dev *pdev,
+ const struct pci_device_id *id)
+{
+ static int mlx4_version_printed;
+
+ if (!mlx4_version_printed) {
+ printk(KERN_INFO "%s", mlx4_version);
+ ++mlx4_version_printed;
+ }
+
+ return mlx4_init_one(pdev, id);
+}
+
+static void mlx4_remove_one(struct pci_dev *pdev)
{
struct mlx4_dev *dev = pci_get_drvdata(pdev);
struct mlx4_priv *priv = mlx4_priv(dev);
@@ -885,9 +905,6 @@ static void __devexit mlx4_remove_one(struct pci_dev *pdev)
mlx4_cleanup_cq_table(dev);
mlx4_cmd_use_polling(dev);
mlx4_cleanup_eq_table(dev);
-
- mlx4_unmap_catas_buf(dev);
-
mlx4_cleanup_mr_table(dev);
mlx4_cleanup_pd_table(dev);
@@ -908,6 +925,12 @@ static void __devexit mlx4_remove_one(struct pci_dev *pdev)
}
}
+int mlx4_restart_one(struct pci_dev *pdev)
+{
+ mlx4_remove_one(pdev);
+ return __mlx4_init_one(pdev, NULL);
+}
+
static struct pci_device_id mlx4_pci_table[] = {
{ PCI_VDEVICE(MELLANOX, 0x6340) }, /* MT25408 "Hermon" SDR */
{ PCI_VDEVICE(MELLANOX, 0x634a) }, /* MT25408 "Hermon" DDR */
@@ -930,6 +953,10 @@ static int __init mlx4_init(void)
{
int ret;
+ ret = mlx4_catas_init();
+ if (ret)
+ return ret;
+
ret = pci_register_driver(&mlx4_driver);
return ret < 0 ? ret : 0;
}
@@ -937,6 +964,7 @@ static int __init mlx4_init(void)
static void __exit mlx4_cleanup(void)
{
pci_unregister_driver(&mlx4_driver);
+ mlx4_catas_cleanup();
}
module_init(mlx4_init);
diff --git a/drivers/net/mlx4/mcg.c b/drivers/net/mlx4/mcg.c
index 672024a0ee71..a99e7729d333 100644
--- a/drivers/net/mlx4/mcg.c
+++ b/drivers/net/mlx4/mcg.c
@@ -359,7 +359,7 @@ out:
}
EXPORT_SYMBOL_GPL(mlx4_multicast_detach);
-int __devinit mlx4_init_mcg_table(struct mlx4_dev *dev)
+int mlx4_init_mcg_table(struct mlx4_dev *dev)
{
struct mlx4_priv *priv = mlx4_priv(dev);
int err;
diff --git a/drivers/net/mlx4/mlx4.h b/drivers/net/mlx4/mlx4.h
index d9c91a71fc87..53a1cdddfc13 100644
--- a/drivers/net/mlx4/mlx4.h
+++ b/drivers/net/mlx4/mlx4.h
@@ -39,6 +39,7 @@
#include <linux/mutex.h>
#include <linux/radix-tree.h>
+#include <linux/timer.h>
#include <linux/mlx4/device.h>
#include <linux/mlx4/doorbell.h>
@@ -55,11 +56,7 @@ enum {
};
enum {
- MLX4_BOARD_ID_LEN = 64
-};
-
-enum {
- MLX4_MGM_ENTRY_SIZE = 0x40,
+ MLX4_MGM_ENTRY_SIZE = 0x100,
MLX4_QP_PER_MGM = 4 * (MLX4_MGM_ENTRY_SIZE / 16 - 2),
MLX4_MTT_ENTRY_PER_SEG = 8
};
@@ -67,7 +64,6 @@ enum {
enum {
MLX4_EQ_ASYNC,
MLX4_EQ_COMP,
- MLX4_EQ_CATAS,
MLX4_NUM_EQ
};
@@ -133,6 +129,7 @@ struct mlx4_icm_table {
int num_obj;
int obj_size;
int lowmem;
+ int coherent;
struct mutex mutex;
struct mlx4_icm **icm;
};
@@ -248,7 +245,8 @@ struct mlx4_mcg_table {
struct mlx4_catas_err {
u32 __iomem *map;
- int size;
+ struct timer_list timer;
+ struct list_head list;
};
struct mlx4_priv {
@@ -276,9 +274,6 @@ struct mlx4_priv {
struct mlx4_uar driver_uar;
void __iomem *kar;
-
- u32 rev_id;
- char board_id[MLX4_BOARD_ID_LEN];
};
static inline struct mlx4_priv *mlx4_priv(struct mlx4_dev *dev)
@@ -311,9 +306,11 @@ void mlx4_cleanup_qp_table(struct mlx4_dev *dev);
void mlx4_cleanup_srq_table(struct mlx4_dev *dev);
void mlx4_cleanup_mcg_table(struct mlx4_dev *dev);
-void mlx4_map_catas_buf(struct mlx4_dev *dev);
-void mlx4_unmap_catas_buf(struct mlx4_dev *dev);
-
+void mlx4_start_catas_poll(struct mlx4_dev *dev);
+void mlx4_stop_catas_poll(struct mlx4_dev *dev);
+int mlx4_catas_init(void);
+void mlx4_catas_cleanup(void);
+int mlx4_restart_one(struct pci_dev *pdev);
int mlx4_register_device(struct mlx4_dev *dev);
void mlx4_unregister_device(struct mlx4_dev *dev);
void mlx4_dispatch_event(struct mlx4_dev *dev, enum mlx4_event type,
diff --git a/drivers/net/mlx4/mr.c b/drivers/net/mlx4/mr.c
index d0808fa3ec82..0c05a10bae3b 100644
--- a/drivers/net/mlx4/mr.c
+++ b/drivers/net/mlx4/mr.c
@@ -68,6 +68,9 @@ struct mlx4_mpt_entry {
#define MLX4_MTT_FLAG_PRESENT 1
+#define MLX4_MPT_STATUS_SW 0xF0
+#define MLX4_MPT_STATUS_HW 0x00
+
static u32 mlx4_buddy_alloc(struct mlx4_buddy *buddy, int order)
{
int o;
@@ -255,10 +258,8 @@ int mlx4_mr_alloc(struct mlx4_dev *dev, u32 pd, u64 iova, u64 size, u32 access,
int err;
index = mlx4_bitmap_alloc(&priv->mr_table.mpt_bitmap);
- if (index == -1) {
- err = -ENOMEM;
- goto err;
- }
+ if (index == -1)
+ return -ENOMEM;
mr->iova = iova;
mr->size = size;
@@ -269,15 +270,8 @@ int mlx4_mr_alloc(struct mlx4_dev *dev, u32 pd, u64 iova, u64 size, u32 access,
err = mlx4_mtt_init(dev, npages, page_shift, &mr->mtt);
if (err)
- goto err_index;
-
- return 0;
-
-err_index:
- mlx4_bitmap_free(&priv->mr_table.mpt_bitmap, index);
+ mlx4_bitmap_free(&priv->mr_table.mpt_bitmap, index);
-err:
- kfree(mr);
return err;
}
EXPORT_SYMBOL_GPL(mlx4_mr_alloc);
@@ -358,58 +352,57 @@ err_table:
}
EXPORT_SYMBOL_GPL(mlx4_mr_enable);
-static int mlx4_WRITE_MTT(struct mlx4_dev *dev, struct mlx4_cmd_mailbox *mailbox,
- int num_mtt)
+static int mlx4_write_mtt_chunk(struct mlx4_dev *dev, struct mlx4_mtt *mtt,
+ int start_index, int npages, u64 *page_list)
{
- return mlx4_cmd(dev, mailbox->dma, num_mtt, 0, MLX4_CMD_WRITE_MTT,
- MLX4_CMD_TIME_CLASS_B);
+ struct mlx4_priv *priv = mlx4_priv(dev);
+ __be64 *mtts;
+ dma_addr_t dma_handle;
+ int i;
+ int s = start_index * sizeof (u64);
+
+ /* All MTTs must fit in the same page */
+ if (start_index / (PAGE_SIZE / sizeof (u64)) !=
+ (start_index + npages - 1) / (PAGE_SIZE / sizeof (u64)))
+ return -EINVAL;
+
+ if (start_index & (MLX4_MTT_ENTRY_PER_SEG - 1))
+ return -EINVAL;
+
+ mtts = mlx4_table_find(&priv->mr_table.mtt_table, mtt->first_seg +
+ s / dev->caps.mtt_entry_sz, &dma_handle);
+ if (!mtts)
+ return -ENOMEM;
+
+ for (i = 0; i < npages; ++i)
+ mtts[i] = cpu_to_be64(page_list[i] | MLX4_MTT_FLAG_PRESENT);
+
+ dma_sync_single(&dev->pdev->dev, dma_handle, npages * sizeof (u64), DMA_TO_DEVICE);
+
+ return 0;
}
int mlx4_write_mtt(struct mlx4_dev *dev, struct mlx4_mtt *mtt,
int start_index, int npages, u64 *page_list)
{
- struct mlx4_cmd_mailbox *mailbox;
- __be64 *mtt_entry;
- int i;
- int err = 0;
+ int chunk;
+ int err;
if (mtt->order < 0)
return -EINVAL;
- mailbox = mlx4_alloc_cmd_mailbox(dev);
- if (IS_ERR(mailbox))
- return PTR_ERR(mailbox);
-
- mtt_entry = mailbox->buf;
-
while (npages > 0) {
- mtt_entry[0] = cpu_to_be64(mlx4_mtt_addr(dev, mtt) + start_index * 8);
- mtt_entry[1] = 0;
-
- for (i = 0; i < npages && i < MLX4_MAILBOX_SIZE / 8 - 2; ++i)
- mtt_entry[i + 2] = cpu_to_be64(page_list[i] |
- MLX4_MTT_FLAG_PRESENT);
-
- /*
- * If we have an odd number of entries to write, add
- * one more dummy entry for firmware efficiency.
- */
- if (i & 1)
- mtt_entry[i + 2] = 0;
-
- err = mlx4_WRITE_MTT(dev, mailbox, (i + 1) & ~1);
+ chunk = min_t(int, PAGE_SIZE / sizeof(u64), npages);
+ err = mlx4_write_mtt_chunk(dev, mtt, start_index, chunk, page_list);
if (err)
- goto out;
+ return err;
- npages -= i;
- start_index += i;
- page_list += i;
+ npages -= chunk;
+ start_index += chunk;
+ page_list += chunk;
}
-out:
- mlx4_free_cmd_mailbox(dev, mailbox);
-
- return err;
+ return 0;
}
EXPORT_SYMBOL_GPL(mlx4_write_mtt);
@@ -437,7 +430,7 @@ int mlx4_buf_write_mtt(struct mlx4_dev *dev, struct mlx4_mtt *mtt,
}
EXPORT_SYMBOL_GPL(mlx4_buf_write_mtt);
-int __devinit mlx4_init_mr_table(struct mlx4_dev *dev)
+int mlx4_init_mr_table(struct mlx4_dev *dev)
{
struct mlx4_mr_table *mr_table = &mlx4_priv(dev)->mr_table;
int err;
@@ -453,7 +446,7 @@ int __devinit mlx4_init_mr_table(struct mlx4_dev *dev)
goto err_buddy;
if (dev->caps.reserved_mtts) {
- if (mlx4_alloc_mtt_range(dev, ilog2(dev->caps.reserved_mtts)) == -1) {
+ if (mlx4_alloc_mtt_range(dev, fls(dev->caps.reserved_mtts - 1)) == -1) {
mlx4_warn(dev, "MTT table of order %d is too small.\n",
mr_table->mtt_buddy.max_order);
err = -ENOMEM;
@@ -479,3 +472,165 @@ void mlx4_cleanup_mr_table(struct mlx4_dev *dev)
mlx4_buddy_cleanup(&mr_table->mtt_buddy);
mlx4_bitmap_cleanup(&mr_table->mpt_bitmap);
}
+
+static inline int mlx4_check_fmr(struct mlx4_fmr *fmr, u64 *page_list,
+ int npages, u64 iova)
+{
+ int i, page_mask;
+
+ if (npages > fmr->max_pages)
+ return -EINVAL;
+
+ page_mask = (1 << fmr->page_shift) - 1;
+
+ /* We are getting page lists, so va must be page aligned. */
+ if (iova & page_mask)
+ return -EINVAL;
+
+ /* Trust the user not to pass misaligned data in page_list */
+ if (0)
+ for (i = 0; i < npages; ++i) {
+ if (page_list[i] & ~page_mask)
+ return -EINVAL;
+ }
+
+ if (fmr->maps >= fmr->max_maps)
+ return -EINVAL;
+
+ return 0;
+}
+
+int mlx4_map_phys_fmr(struct mlx4_dev *dev, struct mlx4_fmr *fmr, u64 *page_list,
+ int npages, u64 iova, u32 *lkey, u32 *rkey)
+{
+ u32 key;
+ int i, err;
+
+ err = mlx4_check_fmr(fmr, page_list, npages, iova);
+ if (err)
+ return err;
+
+ ++fmr->maps;
+
+ key = key_to_hw_index(fmr->mr.key);
+ key += dev->caps.num_mpts;
+ *lkey = *rkey = fmr->mr.key = hw_index_to_key(key);
+
+ *(u8 *) fmr->mpt = MLX4_MPT_STATUS_SW;
+
+ /* Make sure MPT status is visible before writing MTT entries */
+ wmb();
+
+ for (i = 0; i < npages; ++i)
+ fmr->mtts[i] = cpu_to_be64(page_list[i] | MLX4_MTT_FLAG_PRESENT);
+
+ dma_sync_single(&dev->pdev->dev, fmr->dma_handle,
+ npages * sizeof(u64), DMA_TO_DEVICE);
+
+ fmr->mpt->key = cpu_to_be32(key);
+ fmr->mpt->lkey = cpu_to_be32(key);
+ fmr->mpt->length = cpu_to_be64(npages * (1ull << fmr->page_shift));
+ fmr->mpt->start = cpu_to_be64(iova);
+
+ /* Make MTT entries are visible before setting MPT status */
+ wmb();
+
+ *(u8 *) fmr->mpt = MLX4_MPT_STATUS_HW;
+
+ /* Make sure MPT status is visible before consumer can use FMR */
+ wmb();
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(mlx4_map_phys_fmr);
+
+int mlx4_fmr_alloc(struct mlx4_dev *dev, u32 pd, u32 access, int max_pages,
+ int max_maps, u8 page_shift, struct mlx4_fmr *fmr)
+{
+ struct mlx4_priv *priv = mlx4_priv(dev);
+ u64 mtt_seg;
+ int err = -ENOMEM;
+
+ if (page_shift < 12 || page_shift >= 32)
+ return -EINVAL;
+
+ /* All MTTs must fit in the same page */
+ if (max_pages * sizeof *fmr->mtts > PAGE_SIZE)
+ return -EINVAL;
+
+ fmr->page_shift = page_shift;
+ fmr->max_pages = max_pages;
+ fmr->max_maps = max_maps;
+ fmr->maps = 0;
+
+ err = mlx4_mr_alloc(dev, pd, 0, 0, access, max_pages,
+ page_shift, &fmr->mr);
+ if (err)
+ return err;
+
+ mtt_seg = fmr->mr.mtt.first_seg * dev->caps.mtt_entry_sz;
+
+ fmr->mtts = mlx4_table_find(&priv->mr_table.mtt_table,
+ fmr->mr.mtt.first_seg,
+ &fmr->dma_handle);
+ if (!fmr->mtts) {
+ err = -ENOMEM;
+ goto err_free;
+ }
+
+ fmr->mpt = mlx4_table_find(&priv->mr_table.dmpt_table,
+ key_to_hw_index(fmr->mr.key), NULL);
+ if (!fmr->mpt) {
+ err = -ENOMEM;
+ goto err_free;
+ }
+
+ return 0;
+
+err_free:
+ mlx4_mr_free(dev, &fmr->mr);
+ return err;
+}
+EXPORT_SYMBOL_GPL(mlx4_fmr_alloc);
+
+int mlx4_fmr_enable(struct mlx4_dev *dev, struct mlx4_fmr *fmr)
+{
+ return mlx4_mr_enable(dev, &fmr->mr);
+}
+EXPORT_SYMBOL_GPL(mlx4_fmr_enable);
+
+void mlx4_fmr_unmap(struct mlx4_dev *dev, struct mlx4_fmr *fmr,
+ u32 *lkey, u32 *rkey)
+{
+ u32 key;
+
+ if (!fmr->maps)
+ return;
+
+ key = key_to_hw_index(fmr->mr.key);
+ key &= dev->caps.num_mpts - 1;
+ *lkey = *rkey = fmr->mr.key = hw_index_to_key(key);
+
+ fmr->maps = 0;
+
+ *(u8 *) fmr->mpt = MLX4_MPT_STATUS_SW;
+}
+EXPORT_SYMBOL_GPL(mlx4_fmr_unmap);
+
+int mlx4_fmr_free(struct mlx4_dev *dev, struct mlx4_fmr *fmr)
+{
+ if (fmr->maps)
+ return -EBUSY;
+
+ fmr->mr.enabled = 0;
+ mlx4_mr_free(dev, &fmr->mr);
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(mlx4_fmr_free);
+
+int mlx4_SYNC_TPT(struct mlx4_dev *dev)
+{
+ return mlx4_cmd(dev, 0, 0, 0, MLX4_CMD_SYNC_TPT, 1000);
+}
+EXPORT_SYMBOL_GPL(mlx4_SYNC_TPT);
diff --git a/drivers/net/mlx4/pd.c b/drivers/net/mlx4/pd.c
index 23dea1ee7750..3a93c5f0f7ab 100644
--- a/drivers/net/mlx4/pd.c
+++ b/drivers/net/mlx4/pd.c
@@ -57,7 +57,7 @@ void mlx4_pd_free(struct mlx4_dev *dev, u32 pdn)
}
EXPORT_SYMBOL_GPL(mlx4_pd_free);
-int __devinit mlx4_init_pd_table(struct mlx4_dev *dev)
+int mlx4_init_pd_table(struct mlx4_dev *dev)
{
struct mlx4_priv *priv = mlx4_priv(dev);
diff --git a/drivers/net/mlx4/qp.c b/drivers/net/mlx4/qp.c
index 19b48c71cf7f..cc4b1be18219 100644
--- a/drivers/net/mlx4/qp.c
+++ b/drivers/net/mlx4/qp.c
@@ -240,7 +240,8 @@ void mlx4_qp_free(struct mlx4_dev *dev, struct mlx4_qp *qp)
mlx4_table_put(dev, &qp_table->auxc_table, qp->qpn);
mlx4_table_put(dev, &qp_table->qp_table, qp->qpn);
- mlx4_bitmap_free(&qp_table->bitmap, qp->qpn);
+ if (qp->qpn < dev->caps.sqp_start + 8)
+ mlx4_bitmap_free(&qp_table->bitmap, qp->qpn);
}
EXPORT_SYMBOL_GPL(mlx4_qp_free);
@@ -250,7 +251,7 @@ static int mlx4_CONF_SPECIAL_QP(struct mlx4_dev *dev, u32 base_qpn)
MLX4_CMD_TIME_CLASS_B);
}
-int __devinit mlx4_init_qp_table(struct mlx4_dev *dev)
+int mlx4_init_qp_table(struct mlx4_dev *dev)
{
struct mlx4_qp_table *qp_table = &mlx4_priv(dev)->qp_table;
int err;
diff --git a/drivers/net/mlx4/reset.c b/drivers/net/mlx4/reset.c
index e4dfd4b11a4a..e199715fabd0 100644
--- a/drivers/net/mlx4/reset.c
+++ b/drivers/net/mlx4/reset.c
@@ -119,6 +119,9 @@ int mlx4_reset(struct mlx4_dev *dev)
writel(MLX4_RESET_VALUE, reset + MLX4_RESET_OFFSET);
iounmap(reset);
+ /* Docs say to wait one second before accessing device */
+ msleep(1000);
+
end = jiffies + MLX4_RESET_TIMEOUT_JIFFIES;
do {
if (!pci_read_config_word(dev->pdev, PCI_VENDOR_ID, &vendor) &&
diff --git a/drivers/net/mlx4/srq.c b/drivers/net/mlx4/srq.c
index b061c86d6839..d23f46d692ef 100644
--- a/drivers/net/mlx4/srq.c
+++ b/drivers/net/mlx4/srq.c
@@ -227,7 +227,7 @@ int mlx4_srq_query(struct mlx4_dev *dev, struct mlx4_srq *srq, int *limit_waterm
err = mlx4_QUERY_SRQ(dev, mailbox, srq->srqn);
if (err)
goto err_out;
- *limit_watermark = srq_context->limit_watermark;
+ *limit_watermark = be16_to_cpu(srq_context->limit_watermark);
err_out:
mlx4_free_cmd_mailbox(dev, mailbox);
@@ -235,7 +235,7 @@ err_out:
}
EXPORT_SYMBOL_GPL(mlx4_srq_query);
-int __devinit mlx4_init_srq_table(struct mlx4_dev *dev)
+int mlx4_init_srq_table(struct mlx4_dev *dev)
{
struct mlx4_srq_table *srq_table = &mlx4_priv(dev)->srq_table;
int err;
generated by cgit v1.2.3 (git 2.39.1) at 2024-12-30 04:11:42 +0100