linux-kernel - [PATCH 6/6] esp_scsi: Optimize PIO loops

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date:   Sat, 13 Oct 2018 11:51:16 +1100
From:   Finn Thain <fthain@...egraphics.com.au>
To:     "James E.J. Bottomley" <jejb@...ux.vnet.ibm.com>,
        "Martin K. Petersen" <martin.petersen@...cle.com>
Cc:     Michael Schmitz <schmitzmic@...il.com>,
        Hannes Reinecke <hare@...e.de>, linux-scsi@...r.kernel.org,
        linux-m68k@...ts.linux-m68k.org, linux-kernel@...r.kernel.org
Subject: [PATCH 6/6] esp_scsi: Optimize PIO loops

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@...oo.com>
Signed-off-by: Finn Thain <fthain@...egraphics.com.au>
---
 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