IB/mthca: Write FW commands through doorbell page
This patch is checks whether the HCA supports posting FW commands
through a doorbell page (user access region 0, or "UAR0"). If this is
supported, the driver maps UAR0 and uses it for FW commands. This can
be controlled by the value of a writable module parameter
fw_cmd_doorbell. When the parameter is 0, the commands are posted
through HCR using the old method; otherwise if HCA is capable commands
go through UAR0.
This use of UAR0 to post commands eliminates the need for polling the
"go" bit prior to posting a new command. Since reading from a PCI
device is much more expensive then issuing a posted write, it is
expected that issuing FW commands this way will provide better CPU
utilization.
Signed-off-by: Eli Cohen <eli@mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>
diff --git a/drivers/infiniband/hw/mthca/mthca_cmd.c b/drivers/infiniband/hw/mthca/mthca_cmd.c
index 890c060..d1e7ecb 100644
--- a/drivers/infiniband/hw/mthca/mthca_cmd.c
+++ b/drivers/infiniband/hw/mthca/mthca_cmd.c
@@ -182,25 +182,58 @@
u8 status;
};
+static int fw_cmd_doorbell = 1;
+module_param(fw_cmd_doorbell, int, 0644);
+MODULE_PARM_DESC(fw_cmd_doorbell, "post FW commands through doorbell page if nonzero "
+ "(and supported by FW)");
+
static inline int go_bit(struct mthca_dev *dev)
{
return readl(dev->hcr + HCR_STATUS_OFFSET) &
swab32(1 << HCR_GO_BIT);
}
-static int mthca_cmd_post(struct mthca_dev *dev,
- u64 in_param,
- u64 out_param,
- u32 in_modifier,
- u8 op_modifier,
- u16 op,
- u16 token,
- int event)
+static void mthca_cmd_post_dbell(struct mthca_dev *dev,
+ u64 in_param,
+ u64 out_param,
+ u32 in_modifier,
+ u8 op_modifier,
+ u16 op,
+ u16 token)
{
- int err = 0;
+ void __iomem *ptr = dev->cmd.dbell_map;
+ u16 *offs = dev->cmd.dbell_offsets;
- mutex_lock(&dev->cmd.hcr_mutex);
+ __raw_writel((__force u32) cpu_to_be32(in_param >> 32), ptr + offs[0]);
+ wmb();
+ __raw_writel((__force u32) cpu_to_be32(in_param & 0xfffffffful), ptr + offs[1]);
+ wmb();
+ __raw_writel((__force u32) cpu_to_be32(in_modifier), ptr + offs[2]);
+ wmb();
+ __raw_writel((__force u32) cpu_to_be32(out_param >> 32), ptr + offs[3]);
+ wmb();
+ __raw_writel((__force u32) cpu_to_be32(out_param & 0xfffffffful), ptr + offs[4]);
+ wmb();
+ __raw_writel((__force u32) cpu_to_be32(token << 16), ptr + offs[5]);
+ wmb();
+ __raw_writel((__force u32) cpu_to_be32((1 << HCR_GO_BIT) |
+ (1 << HCA_E_BIT) |
+ (op_modifier << HCR_OPMOD_SHIFT) |
+ op), ptr + offs[6]);
+ wmb();
+ __raw_writel((__force u32) 0, ptr + offs[7]);
+ wmb();
+}
+static int mthca_cmd_post_hcr(struct mthca_dev *dev,
+ u64 in_param,
+ u64 out_param,
+ u32 in_modifier,
+ u8 op_modifier,
+ u16 op,
+ u16 token,
+ int event)
+{
if (event) {
unsigned long end = jiffies + GO_BIT_TIMEOUT;
@@ -210,10 +243,8 @@
}
}
- if (go_bit(dev)) {
- err = -EAGAIN;
- goto out;
- }
+ if (go_bit(dev))
+ return -EAGAIN;
/*
* We use writel (instead of something like memcpy_toio)
@@ -236,7 +267,29 @@
(op_modifier << HCR_OPMOD_SHIFT) |
op), dev->hcr + 6 * 4);
-out:
+ return 0;
+}
+
+static int mthca_cmd_post(struct mthca_dev *dev,
+ u64 in_param,
+ u64 out_param,
+ u32 in_modifier,
+ u8 op_modifier,
+ u16 op,
+ u16 token,
+ int event)
+{
+ int err = 0;
+
+ mutex_lock(&dev->cmd.hcr_mutex);
+
+ if (event && dev->cmd.flags & MTHCA_CMD_POST_DOORBELLS && fw_cmd_doorbell)
+ mthca_cmd_post_dbell(dev, in_param, out_param, in_modifier,
+ op_modifier, op, token);
+ else
+ err = mthca_cmd_post_hcr(dev, in_param, out_param, in_modifier,
+ op_modifier, op, token, event);
+
mutex_unlock(&dev->cmd.hcr_mutex);
return err;
}
@@ -386,7 +439,7 @@
unsigned long timeout,
u8 *status)
{
- if (dev->cmd.use_events)
+ if (dev->cmd.flags & MTHCA_CMD_USE_EVENTS)
return mthca_cmd_wait(dev, in_param, &out_param, 0,
in_modifier, op_modifier, op,
timeout, status);
@@ -423,7 +476,7 @@
unsigned long timeout,
u8 *status)
{
- if (dev->cmd.use_events)
+ if (dev->cmd.flags & MTHCA_CMD_USE_EVENTS)
return mthca_cmd_wait(dev, in_param, out_param, 1,
in_modifier, op_modifier, op,
timeout, status);
@@ -437,7 +490,7 @@
{
mutex_init(&dev->cmd.hcr_mutex);
sema_init(&dev->cmd.poll_sem, 1);
- dev->cmd.use_events = 0;
+ dev->cmd.flags = 0;
dev->hcr = ioremap(pci_resource_start(dev->pdev, 0) + MTHCA_HCR_BASE,
MTHCA_HCR_SIZE);
@@ -461,6 +514,8 @@
{
pci_pool_destroy(dev->cmd.pool);
iounmap(dev->hcr);
+ if (dev->cmd.flags & MTHCA_CMD_POST_DOORBELLS)
+ iounmap(dev->cmd.dbell_map);
}
/*
@@ -498,7 +553,8 @@
; /* nothing */
--dev->cmd.token_mask;
- dev->cmd.use_events = 1;
+ dev->cmd.flags |= MTHCA_CMD_USE_EVENTS;
+
down(&dev->cmd.poll_sem);
return 0;
@@ -511,7 +567,7 @@
{
int i;
- dev->cmd.use_events = 0;
+ dev->cmd.flags &= ~MTHCA_CMD_USE_EVENTS;
for (i = 0; i < dev->cmd.max_cmds; ++i)
down(&dev->cmd.event_sem);
@@ -661,12 +717,41 @@
return mthca_cmd(dev, 0, 0, 0, CMD_RUN_FW, CMD_TIME_CLASS_A, status);
}
+static void mthca_setup_cmd_doorbells(struct mthca_dev *dev, u64 base)
+{
+ unsigned long addr;
+ u16 max_off = 0;
+ int i;
+
+ for (i = 0; i < 8; ++i)
+ max_off = max(max_off, dev->cmd.dbell_offsets[i]);
+
+ if ((base & PAGE_MASK) != ((base + max_off) & PAGE_MASK)) {
+ mthca_warn(dev, "Firmware doorbell region at 0x%016llx, "
+ "length 0x%x crosses a page boundary\n",
+ (unsigned long long) base, max_off);
+ return;
+ }
+
+ addr = pci_resource_start(dev->pdev, 2) +
+ ((pci_resource_len(dev->pdev, 2) - 1) & base);
+ dev->cmd.dbell_map = ioremap(addr, max_off + sizeof(u32));
+ if (!dev->cmd.dbell_map)
+ return;
+
+ dev->cmd.flags |= MTHCA_CMD_POST_DOORBELLS;
+ mthca_dbg(dev, "Mapped doorbell page for posting FW commands\n");
+}
+
int mthca_QUERY_FW(struct mthca_dev *dev, u8 *status)
{
struct mthca_mailbox *mailbox;
u32 *outbox;
+ u64 base;
+ u32 tmp;
int err = 0;
u8 lg;
+ int i;
#define QUERY_FW_OUT_SIZE 0x100
#define QUERY_FW_VER_OFFSET 0x00
@@ -674,6 +759,10 @@
#define QUERY_FW_ERR_START_OFFSET 0x30
#define QUERY_FW_ERR_SIZE_OFFSET 0x38
+#define QUERY_FW_CMD_DB_EN_OFFSET 0x10
+#define QUERY_FW_CMD_DB_OFFSET 0x50
+#define QUERY_FW_CMD_DB_BASE 0x60
+
#define QUERY_FW_START_OFFSET 0x20
#define QUERY_FW_END_OFFSET 0x28
@@ -702,16 +791,29 @@
((dev->fw_ver & 0xffff0000ull) >> 16) |
((dev->fw_ver & 0x0000ffffull) << 16);
+ mthca_dbg(dev, "FW version %012llx, max commands %d\n",
+ (unsigned long long) dev->fw_ver, dev->cmd.max_cmds);
+
MTHCA_GET(lg, outbox, QUERY_FW_MAX_CMD_OFFSET);
dev->cmd.max_cmds = 1 << lg;
MTHCA_GET(dev->catas_err.addr, outbox, QUERY_FW_ERR_START_OFFSET);
MTHCA_GET(dev->catas_err.size, outbox, QUERY_FW_ERR_SIZE_OFFSET);
- mthca_dbg(dev, "FW version %012llx, max commands %d\n",
- (unsigned long long) dev->fw_ver, dev->cmd.max_cmds);
mthca_dbg(dev, "Catastrophic error buffer at 0x%llx, size 0x%x\n",
(unsigned long long) dev->catas_err.addr, dev->catas_err.size);
+ MTHCA_GET(tmp, outbox, QUERY_FW_CMD_DB_EN_OFFSET);
+ if (tmp & 0x1) {
+ mthca_dbg(dev, "FW supports commands through doorbells\n");
+
+ MTHCA_GET(base, outbox, QUERY_FW_CMD_DB_BASE);
+ for (i = 0; i < MTHCA_CMD_NUM_DBELL_DWORDS; ++i)
+ MTHCA_GET(dev->cmd.dbell_offsets[i], outbox,
+ QUERY_FW_CMD_DB_OFFSET + (i << 1));
+
+ mthca_setup_cmd_doorbells(dev, base);
+ }
+
if (mthca_is_memfree(dev)) {
MTHCA_GET(dev->fw.arbel.fw_pages, outbox, QUERY_FW_SIZE_OFFSET);
MTHCA_GET(dev->fw.arbel.clr_int_base, outbox, QUERY_FW_CLR_INT_BASE_OFFSET);