* Re: Instability
2005-04-19 14:50 Instability Frank Henkel
@ 2005-04-20 2:30 ` Albert Lee
0 siblings, 0 replies; 2+ messages in thread
From: Albert Lee @ 2005-04-20 2:30 UTC (permalink / raw)
To: fhenkel; +Cc: Jeff Garzik, linux-ide
[-- Attachment #1: Type: text/plain, Size: 1746 bytes --]
Frank Henkel wrote:
>
> Dear Jeff,
>
> we have a stability problem under x86_64 Linux using the
> sata_sil driver for the SiI 3512A dual port SATA onboard
> controller (BIOS Version 4.3.47) of the MSI MS-9145 Dual
> Opteron (So940) MoBo.
>
> The proprietary drivers from SiI don't match our kernel
> versions, so we rely on the sata_sil alternative.
>
> What Linux distros I have tested:
>
> Distro Kernel sata_sil Version
> - -------------------------------------------------------
> SuSE 9.3 x86_64 2.6.11.4-20a-smp 0.8
> - -------------------------------------------------------
> Scientific Linux CERN 3.0.4
> 2.4.21-27.0.2.EL.cernsmp
> 0.54
> - -------------------------------------------------------
> RHEL WS3 U4 2.4.X (server crashed before information
> was saved)
> - -------------------------------------------------------
>
> The problem is, that I a lot of console messages like
>
> ata1: status=0x51 { DriveReady SeekComplete Error }
> ata1: error=0x04 { DriveStatus Error }
>
> appear when data is written to disk. And, suddenly, I/O
> errors are reported and the system hangs. In the case of
> RHEL WS3 U4 I lost the complete installation, because
> fsck couldn't catch up all errors in the FS.
>
> Do you know problems with this specific SATA controller?
> Do you have a solution (2.4 kernel)?
> Can I help you with more information to enhance the driver?
>
Hi Frank,
Since you are running x86-64, I guess the problem might be similar to
the sg_dma_len() problem seen on ppc64:
http://marc.theaimsgroup.com/?l=linux-ide&m=111113103410355&w=2
Could you please try the attached patch, thanks.
Albert
[-- Attachment #2: sg_dma_len2.diff --]
[-- Type: text/plain, Size: 4351 bytes --]
--- linux-2.6.5-SLES9_SP2_BRANCH_20050418161416/drivers/scsi/libata-core.c.ori 2005-04-19 15:34:14.000000000 +0800
+++ linux-2.6.5-SLES9_SP2_BRANCH_20050418161416/drivers/scsi/libata-core.c 2005-04-19 16:39:25.000000000 +0800
@@ -1054,6 +1054,7 @@
}
qc->waiting = &wait;
+ qc->private_data = &status;
qc->complete_fn = ata_qc_complete_noop;
spin_lock_irqsave(&ap->host_set->lock, flags);
@@ -1065,7 +1066,6 @@
else
wait_for_completion(&wait);
- status = ata_chk_status(ap);
if (status & ATA_ERR) {
/*
* arg! EDD works for all test cases, but seems to return
@@ -1918,6 +1918,7 @@
struct ata_queued_cmd *qc;
int rc;
unsigned long flags;
+ u8 status;
/* set up set-features taskfile */
DPRINTK("set features - xfer mode\n");
@@ -1932,6 +1933,7 @@
qc->tf.nsect = dev->xfer_mode;
qc->waiting = &wait;
+ qc->private_data = &status;
qc->complete_fn = ata_qc_complete_noop;
spin_lock_irqsave(&ap->host_set->lock, flags);
@@ -2071,7 +2073,7 @@
sg = qc->sg;
sg->page = virt_to_page(buf);
sg->offset = (unsigned long) buf & ~PAGE_MASK;
- sg_dma_len(sg) = buflen;
+ sg->length = buflen;
}
void ata_sg_init(struct ata_queued_cmd *qc, struct scatterlist *sg,
@@ -2101,11 +2103,12 @@
dma_addr_t dma_address;
dma_address = dma_map_single(ap->host_set->dev, qc->buf_virt,
- sg_dma_len(sg), dir);
+ sg->length, dir);
if (dma_mapping_error(dma_address))
return -1;
sg_dma_address(sg) = dma_address;
+ sg_dma_len(sg) = sg->length;
DPRINTK("mapped buffer of %d bytes for %s\n", sg_dma_len(sg),
qc->tf.flags & ATA_TFLAG_WRITE ? "write" : "read");
@@ -2310,7 +2313,7 @@
qc->cursect++;
qc->cursg_ofs++;
- if ((qc->cursg_ofs * ATA_SECT_SIZE) == sg_dma_len(&sg[qc->cursg])) {
+ if ((qc->cursg_ofs * ATA_SECT_SIZE) == (&sg[qc->cursg])->length) {
qc->cursg++;
qc->cursg_ofs = 0;
}
@@ -2333,13 +2336,29 @@
unsigned char *buf;
unsigned int offset, count;
- if (qc->curbytes == qc->nbytes - bytes)
+ if (qc->curbytes + bytes >= qc->nbytes)
ap->pio_task_state = PIO_ST_LAST;
next_sg:
+ /* check whether qc->sg is full */
+ if (unlikely(qc->cursg >= qc->n_elem)) {
+ unsigned char pad_buf[2];
+ unsigned int words = (bytes+1) >> 1; /* pad to word boundary */
+ unsigned int i;
+
+ DPRINTK("ata%u: padding %u bytes\n", ap->id, bytes);
+
+ memset(&pad_buf, 0, sizeof(pad_buf));
+ for (i = 0; i < words; i++) {
+ ata_data_xfer(ap, pad_buf, sizeof(pad_buf), do_write);
+ }
+
+ ap->pio_task_state = PIO_ST_LAST;
+ return;
+ }
+
sg = &qc->sg[qc->cursg];
-next_page:
page = sg->page;
offset = sg->offset + qc->cursg_ofs;
@@ -2347,18 +2366,25 @@
page = nth_page(page, (offset >> PAGE_SHIFT));
offset %= PAGE_SIZE;
- count = min(sg_dma_len(sg) - qc->cursg_ofs, bytes);
+ /* don't overrun current sg */
+ count = min(sg->length - qc->cursg_ofs, bytes);
/* don't cross page boundaries */
count = min(count, (unsigned int)PAGE_SIZE - offset);
+ /* handle the odd condition */
+ if (unlikely(count & 0x01)) {
+ printk(KERN_WARNING "ata%u: odd count %u rounded: qc->nbytes %u, bytes %u\n",
+ ap->id, count, qc->nbytes, bytes);
+ count++;
+ }
+
buf = kmap(page) + offset;
- bytes -= count;
qc->curbytes += count;
qc->cursg_ofs += count;
- if (qc->cursg_ofs == sg_dma_len(sg)) {
+ if (qc->cursg_ofs >= sg->length) {
qc->cursg++;
qc->cursg_ofs = 0;
}
@@ -2370,9 +2396,9 @@
kunmap(page);
- if (bytes) {
- if (qc->cursg_ofs < sg_dma_len(sg))
- goto next_page;
+ if (bytes > count) {
+ bytes -= count;
+
goto next_sg;
}
}
@@ -2475,8 +2501,7 @@
assert(qc != NULL);
drv_stat = ata_chk_status(ap);
- printk(KERN_WARNING "ata%u: PIO error, drv_stat 0x%x\n",
- ap->id, drv_stat);
+ DPRINTK("ata%u: PIO error, drv_stat 0x%x\n", ap->id, drv_stat);
ap->pio_task_state = PIO_ST_IDLE;
@@ -2527,6 +2552,7 @@
struct ata_queued_cmd *qc;
unsigned long flags;
int rc;
+ u8 status;
DPRINTK("ATAPI request sense\n");
@@ -2552,6 +2578,7 @@
qc->nbytes = SCSI_SENSE_BUFFERSIZE;
qc->waiting = &wait;
+ qc->private_data = &status;
qc->complete_fn = ata_qc_complete_noop;
spin_lock_irqsave(&ap->host_set->lock, flags);
@@ -2745,6 +2772,7 @@
static int ata_qc_complete_noop(struct ata_queued_cmd *qc, u8 drv_stat)
{
+ *((u8*)qc->private_data) = drv_stat;
return 0;
}
^ permalink raw reply [flat|nested] 2+ messages in thread