[PATCH] pcnet_cs.c: IRQ handler optimization

During some performance diagnostics I stumbled on this slightly wasteful
code in pcnet_cs.c which I made the patch included at the bottom for (two
minor comment fixes included).

Improvement:
instead of *always* calculating
lea    0x2c0(%edx),%ebx
and then additionally doing the
mov    %edx,0xc0(%ebx)
addition *if we need it*,

we now do the *whole* calculation of
mov    %edx,0x380(%ebx)
*only* if we need it.
This even manages to save us a whole 16-byte alignment buffer loss
in this compilation case.

Result: slightly improves IRQ handler performance in both shared and
non-shared IRQ case, which should make my rusty P3/700 a slight bit happier.

Thank you for your support,

Andreas Mohr

old asm result (using gcc 3.3.5):

000015a0 <ei_irq_wrapper>:
    15a0:       55                      push   %ebp
    15a1:       89 e5                   mov    %esp,%ebp
    15a3:       53                      push   %ebx
    15a4:       8d 9a c0 02 00 00       lea    0x2c0(%edx),%ebx
    15aa:       e8 fc ff ff ff          call   15ab <ei_irq_wrapper+0xb>
    15af:       83 f8 01                cmp    $0x1,%eax
    15b2:       74 03                   je     15b7 <ei_irq_wrapper+0x17>
    15b4:       5b                      pop    %ebx
    15b5:       5d                      pop    %ebp
    15b6:       c3                      ret
    15b7:       31 d2                   xor    %edx,%edx
    15b9:       89 93 c0 00 00 00       mov    %edx,0xc0(%ebx)
    15bf:       eb f3                   jmp    15b4 <ei_irq_wrapper+0x14>
    15c1:       eb 0d                   jmp    15d0 <ei_watchdog>
    15c3:       90                      nop
    15c4:       90                      nop
    15c5:       90                      nop
    15c6:       90                      nop
    15c7:       90                      nop
    15c8:       90                      nop
    15c9:       90                      nop
    15ca:       90                      nop
    15cb:       90                      nop
    15cc:       90                      nop
    15cd:       90                      nop
    15ce:       90                      nop
    15cf:       90                      nop

000015d0 <ei_watchdog>:

new asm result:

000015a0 <ei_irq_wrapper>:
    15a0:       55                      push   %ebp
    15a1:       89 e5                   mov    %esp,%ebp
    15a3:       53                      push   %ebx
    15a4:       89 d3                   mov    %edx,%ebx
    15a6:       e8 fc ff ff ff          call   15a7 <ei_irq_wrapper+0x7>
    15ab:       83 f8 01                cmp    $0x1,%eax
    15ae:       74 03                   je     15b3 <ei_irq_wrapper+0x13>
    15b0:       5b                      pop    %ebx
    15b1:       5d                      pop    %ebp
    15b2:       c3                      ret
    15b3:       31 d2                   xor    %edx,%edx
    15b5:       89 93 80 03 00 00       mov    %edx,0x380(%ebx)
    15bb:       eb f3                   jmp    15b0 <ei_irq_wrapper+0x10>
    15bd:       8d 76 00                lea    0x0(%esi),%esi

000015c0 <ei_watchdog>:

Signed-off-by: Andrew Morton <akpm@osdl.org>

diff --git a/drivers/net/pcmcia/pcnet_cs.c b/drivers/net/pcmcia/pcnet_cs.c
index 181b6ed550036852196bb0d67ae6ef753be5c78b..f3ea4a9f2bf196a0b884cde3d44a2cec27f9db13 100644 (file)
--- a/drivers/net/pcmcia/pcnet_cs.c
+++ b/drivers/net/pcmcia/pcnet_cs.c
@@ -1155,11 +1155,13 @@ static int set_config(struct net_device *dev, struct ifmap *map)
 static irqreturn_t ei_irq_wrapper(int irq, void *dev_id, struct pt_regs *regs)
 {
     struct net_device *dev = dev_id;
-    pcnet_dev_t *info = PRIV(dev);
+    pcnet_dev_t *info;
     irqreturn_t ret = ei_interrupt(irq, dev_id, regs);
 
-    if (ret == IRQ_HANDLED)
+    if (ret == IRQ_HANDLED) {
+           info = PRIV(dev);
            info->stale = 0;
+    }
     return ret;
 }
 
@@ -1350,7 +1352,7 @@ static void dma_block_input(struct net_device *dev, int count,
     if (count & 0x01)
        buf[count-1] = inb(nic_base + PCNET_DATAPORT), xfer_count++;
 
-    /* This was for the ALPHA version only, but enough people have
+    /* This was for the ALPHA version only, but enough people have been
        encountering problems that it is still here. */
 #ifdef PCMCIA_DEBUG
     if (ei_debug > 4) {                /* DMA termination address check... */
@@ -1424,7 +1426,7 @@ static void dma_block_output(struct net_device *dev, int count,
     dma_start = jiffies;
 
 #ifdef PCMCIA_DEBUG
-    /* This was for the ALPHA version only, but enough people have
+    /* This was for the ALPHA version only, but enough people have been
        encountering problems that it is still here. */
     if (ei_debug > 4) {        /* DMA termination address check... */
        int addr, tries = 20;