[PATCH 6/6] esp_scsi: Optimize PIO loops

From: Finn Thain
Date: Fri Oct 12 2018 - 21:12:27 EST


Avoid function calls in the inner PIO loops. On a Centris 660av this
improves throughput for sequential read transfers by about 40% and
sequential write by about 10%.

Unfortunately it is not possible to have method calls like esp_write8()
placed inline so this is always going to be slow (even with LTO).

Tested-by: Stan Johnson <userm57@xxxxxxxxx>
Signed-off-by: Finn Thain <fthain@xxxxxxxxxxxxxxxxxxx>
---
drivers/scsi/esp_scsi.c | 14 +++++++-------
1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/drivers/scsi/esp_scsi.c b/drivers/scsi/esp_scsi.c
index 646701fc22a4..9f0e68cd0e99 100644
--- a/drivers/scsi/esp_scsi.c
+++ b/drivers/scsi/esp_scsi.c
@@ -2788,7 +2788,7 @@ static inline unsigned int esp_wait_for_fifo(struct esp *esp)
if (fbytes)
return fbytes;

- udelay(2);
+ udelay(1);
} while (--i);

pr_err("FIFO is empty (sreg %02x)\n", esp_read8(ESP_STATUS));
@@ -2804,7 +2804,7 @@ static inline int esp_wait_for_intr(struct esp *esp)
if (esp->sreg & ESP_STAT_INTR)
return 0;

- udelay(2);
+ udelay(1);
} while (--i);

pr_err("IRQ timeout (sreg %02x)\n", esp->sreg);
@@ -2831,7 +2831,7 @@ void esp_send_pio_cmd(struct esp *esp, u32 addr, u32 esp_count,
if (!esp_wait_for_fifo(esp))
break;

- *dst++ = esp_read8(ESP_FDATA);
+ *dst++ = readb(esp->fifo_reg);
--esp_count;

if (!esp_count)
@@ -2852,15 +2852,15 @@ void esp_send_pio_cmd(struct esp *esp, u32 addr, u32 esp_count,
}

if (phase == ESP_MIP)
- scsi_esp_cmd(esp, ESP_CMD_MOK);
+ esp_write8(ESP_CMD_MOK, ESP_CMD);

- scsi_esp_cmd(esp, ESP_CMD_TI);
+ esp_write8(ESP_CMD_TI, ESP_CMD);
}
} else {
unsigned int n = ESP_FIFO_SIZE;
u8 *src = (u8 *)addr;

- scsi_esp_cmd(esp, ESP_CMD_FLUSH);
+ esp_write8(ESP_CMD_FLUSH, ESP_CMD);

if (n > esp_count)
n = esp_count;
@@ -2894,7 +2894,7 @@ void esp_send_pio_cmd(struct esp *esp, u32 addr, u32 esp_count,
src += n;
esp_count -= n;

- scsi_esp_cmd(esp, ESP_CMD_TI);
+ esp_write8(ESP_CMD_TI, ESP_CMD);
}
}

--
2.16.4