Commit 459ad688 authored by Tejun Heo's avatar Tejun Heo Committed by Jeff Garzik

libata: kill spurious NCQ completion detection

Spurious NCQ completion detection implemented in ahci was incorrect.
On AHCI receving and processing FISes and raising interrupts are not
interlocked and spurious interrupts are expected.

For example, if an interrupt occurs while interrupt handler is running
and the running interrupt handler handles the event the new IRQ
indicated, after IRQ handler finishes, it will be executed again
because IRQ pending bit is set by the new interrupt but there won't be
anything to process.

Please read the following message for more information.

  http://article.gmane.org/gmane.linux.ide/26012

This patch...

* Removes all spurious IRQ whining from ahci.  Spurious NCQ completion
  detection was completely wrong.  Spurious D2H Register FIS taught us
  that some early drives send spurious D2H Register FIS with I bit set
  while NCQ commands are in progress but none of recent drives does
  that and even the ones which show such behavior can do NCQ fine.

* Kills all NCQ blacklist entries which were added because of spurious
  NCQ completions.  I tracked down each commit and verified all
  removed ones are actually added because of spurious completions.

  WD740ADFD-00NLR1 wasn't deleted but moved upward because the drive
  not only had spurious NCQ completions but also is slow on sequential
  data transfers if NCQ is enabled.

  Maxtor 7V300F0 was added by 0e3dbc01
  from Alan Cox.  I can only find evidences that the drive only had
  troubles with spuruious completions by searching the mailing list.
  This entry needs to be verified and removed if it doesn't have other
  NCQ related problems.
Signed-off-by: default avatarTejun Heo <htejun@gmail.com>
Cc: Alan Cox <alan@lxorguk.ukuu.org.uk>
Signed-off-by: default avatarJeff Garzik <jeff@garzik.org>
parent c4f7792c
......@@ -1640,7 +1640,7 @@ static void ahci_port_intr(struct ata_port *ap)
struct ahci_host_priv *hpriv = ap->host->private_data;
int resetting = !!(ap->pflags & ATA_PFLAG_RESETTING);
u32 status, qc_active;
int rc, known_irq = 0;
int rc;
status = readl(port_mmio + PORT_IRQ_STAT);
writel(status, port_mmio + PORT_IRQ_STAT);
......@@ -1698,80 +1698,12 @@ static void ahci_port_intr(struct ata_port *ap)
rc = ata_qc_complete_multiple(ap, qc_active, NULL);
/* If resetting, spurious or invalid completions are expected,
* return unconditionally.
*/
if (resetting)
return;
if (rc > 0)
return;
if (rc < 0) {
ehi->err_mask |= AC_ERR_HSM;
ehi->action |= ATA_EH_SOFTRESET;
ata_port_freeze(ap);
return;
}
/* hmmm... a spurious interrupt */
/* if !NCQ, ignore. No modern ATA device has broken HSM
* implementation for non-NCQ commands.
*/
if (!ap->link.sactive)
return;
if (status & PORT_IRQ_D2H_REG_FIS) {
if (!pp->ncq_saw_d2h)
ata_port_printk(ap, KERN_INFO,
"D2H reg with I during NCQ, "
"this message won't be printed again\n");
pp->ncq_saw_d2h = 1;
known_irq = 1;
}
if (status & PORT_IRQ_DMAS_FIS) {
if (!pp->ncq_saw_dmas)
ata_port_printk(ap, KERN_INFO,
"DMAS FIS during NCQ, "
"this message won't be printed again\n");
pp->ncq_saw_dmas = 1;
known_irq = 1;
}
if (status & PORT_IRQ_SDB_FIS) {
const __le32 *f = pp->rx_fis + RX_FIS_SDB;
if (le32_to_cpu(f[1])) {
/* SDB FIS containing spurious completions
* might be dangerous, whine and fail commands
* with HSM violation. EH will turn off NCQ
* after several such failures.
*/
ata_ehi_push_desc(ehi,
"spurious completions during NCQ "
"issue=0x%x SAct=0x%x FIS=%08x:%08x",
readl(port_mmio + PORT_CMD_ISSUE),
readl(port_mmio + PORT_SCR_ACT),
le32_to_cpu(f[0]), le32_to_cpu(f[1]));
/* while resetting, invalid completions are expected */
if (unlikely(rc < 0 && !resetting)) {
ehi->err_mask |= AC_ERR_HSM;
ehi->action |= ATA_EH_SOFTRESET;
ata_port_freeze(ap);
} else {
if (!pp->ncq_saw_sdb)
ata_port_printk(ap, KERN_INFO,
"spurious SDB FIS %08x:%08x during NCQ, "
"this message won't be printed again\n",
le32_to_cpu(f[0]), le32_to_cpu(f[1]));
pp->ncq_saw_sdb = 1;
}
known_irq = 1;
}
if (!known_irq)
ata_port_printk(ap, KERN_INFO, "spurious interrupt "
"(irq_stat 0x%x active_tag 0x%x sactive 0x%x)\n",
status, ap->link.active_tag, ap->link.sactive);
}
static void ahci_irq_clear(struct ata_port *ap)
......
......@@ -4140,6 +4140,7 @@ static const struct ata_blacklist_entry ata_device_blacklist [] = {
/* Devices where NCQ should be avoided */
/* NCQ is slow */
{ "WDC WD740ADFD-00", NULL, ATA_HORKAGE_NONCQ },
{ "WDC WD740ADFD-00NLR1", NULL, ATA_HORKAGE_NONCQ, },
/* http://thread.gmane.org/gmane.linux.ide/14907 */
{ "FUJITSU MHT2060BH", NULL, ATA_HORKAGE_NONCQ },
/* NCQ is broken */
......@@ -4154,23 +4155,6 @@ static const struct ata_blacklist_entry ata_device_blacklist [] = {
{ "HTS541060G9SA00", "MB3OC60D", ATA_HORKAGE_NONCQ, },
{ "HTS541080G9SA00", "MB4OC60D", ATA_HORKAGE_NONCQ, },
{ "HTS541010G9SA00", "MBZOC60D", ATA_HORKAGE_NONCQ, },
/* Drives which do spurious command completion */
{ "HTS541680J9SA00", "SB2IC7EP", ATA_HORKAGE_NONCQ, },
{ "HTS541612J9SA00", "SBDIC7JP", ATA_HORKAGE_NONCQ, },
{ "HDT722516DLA380", "V43OA96A", ATA_HORKAGE_NONCQ, },
{ "Hitachi HTS541616J9SA00", "SB4OC70P", ATA_HORKAGE_NONCQ, },
{ "Hitachi HTS542525K9SA00", "BBFOC31P", ATA_HORKAGE_NONCQ, },
{ "WDC WD740ADFD-00NLR1", NULL, ATA_HORKAGE_NONCQ, },
{ "WDC WD3200AAJS-00RYA0", "12.01B01", ATA_HORKAGE_NONCQ, },
{ "FUJITSU MHV2080BH", "00840028", ATA_HORKAGE_NONCQ, },
{ "ST9120822AS", "3.CLF", ATA_HORKAGE_NONCQ, },
{ "ST9160821AS", "3.CLF", ATA_HORKAGE_NONCQ, },
{ "ST9160821AS", "3.ALD", ATA_HORKAGE_NONCQ, },
{ "ST9160821AS", "3.CCD", ATA_HORKAGE_NONCQ, },
{ "ST3160812AS", "3.ADJ", ATA_HORKAGE_NONCQ, },
{ "ST980813AS", "3.ADB", ATA_HORKAGE_NONCQ, },
{ "SAMSUNG HD401LJ", "ZZ100-15", ATA_HORKAGE_NONCQ, },
{ "Maxtor 7V300F0", "VA111900", ATA_HORKAGE_NONCQ, },
/* devices which puke on READ_NATIVE_MAX */
{ "HDS724040KLSA80", "KFAOA20N", ATA_HORKAGE_BROKEN_HPA, },
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment