aboutsummaryrefslogtreecommitdiff
path: root/drivers/infiniband/hw/ipath/ipath_iba6110.c
diff options
context:
space:
mode:
authorBryan O'Sullivan <bos@pathscale.com>2007-03-15 14:45:07 -0700
committerRoland Dreier <rolandd@cisco.com>2007-04-18 20:20:58 -0700
commit9783ab405844202b452ac673677e6c8f8c9a6a99 (patch)
tree32aac9ac3ff1089a7ecb05c4ef0b825a95227694 /drivers/infiniband/hw/ipath/ipath_iba6110.c
parent820054b7ca7a54ba94d89db4b3c53a24d2d66633 (diff)
IB/ipath: Improve handling and reporting of parity errors
Mostly cleanup. Signed-off-by: Dave Olson <dave.olson@qlogic.com> Signed-off-by: Bryan O'Sullivan <bryan.osullivan@qlogic.com> Signed-off-by: Roland Dreier <rolandd@cisco.com>
Diffstat (limited to 'drivers/infiniband/hw/ipath/ipath_iba6110.c')
-rw-r--r--drivers/infiniband/hw/ipath/ipath_iba6110.c138
1 files changed, 83 insertions, 55 deletions
diff --git a/drivers/infiniband/hw/ipath/ipath_iba6110.c b/drivers/infiniband/hw/ipath/ipath_iba6110.c
index b50436c5663..8e0794d316f 100644
--- a/drivers/infiniband/hw/ipath/ipath_iba6110.c
+++ b/drivers/infiniband/hw/ipath/ipath_iba6110.c
@@ -284,6 +284,14 @@ static const struct ipath_cregs ipath_ht_cregs = {
#define INFINIPATH_EXTS_MEMBIST_ENDTEST 0x0000000000004000
#define INFINIPATH_EXTS_MEMBIST_CORRECT 0x0000000000008000
+
+/* TID entries (memory), HT-only */
+#define INFINIPATH_RT_ADDR_MASK 0xFFFFFFFFFFULL /* 40 bits valid */
+#define INFINIPATH_RT_VALID 0x8000000000000000ULL
+#define INFINIPATH_RT_ADDR_SHIFT 0
+#define INFINIPATH_RT_BUFSIZE_MASK 0x3FFFULL
+#define INFINIPATH_RT_BUFSIZE_SHIFT 48
+
/*
* masks and bits that are different in different chips, or present only
* in one
@@ -402,6 +410,14 @@ static const struct ipath_hwerror_msgs ipath_6110_hwerror_msgs[] = {
INFINIPATH_HWE_MSG(SERDESPLLFAILED, "SerDes PLL"),
};
+#define TXE_PIO_PARITY ((INFINIPATH_HWE_TXEMEMPARITYERR_PIOBUF | \
+ INFINIPATH_HWE_TXEMEMPARITYERR_PIOPBC) \
+ << INFINIPATH_HWE_TXEMEMPARITYERR_SHIFT)
+#define RXE_EAGER_PARITY (INFINIPATH_HWE_RXEMEMPARITYERR_EAGERTID \
+ << INFINIPATH_HWE_RXEMEMPARITYERR_SHIFT)
+
+static int ipath_ht_txe_recover(struct ipath_devdata *);
+
/**
* ipath_ht_handle_hwerrors - display hardware errors.
* @dd: the infinipath device
@@ -450,13 +466,12 @@ static void ipath_ht_handle_hwerrors(struct ipath_devdata *dd, char *msg,
/*
* make sure we get this much out, unless told to be quiet,
+ * it's a parity error we may recover from,
* or it's occurred within the last 5 seconds
*/
- if ((hwerrs & ~(dd->ipath_lasthwerror |
- ((INFINIPATH_HWE_TXEMEMPARITYERR_PIOBUF |
- INFINIPATH_HWE_TXEMEMPARITYERR_PIOPBC)
- << INFINIPATH_HWE_TXEMEMPARITYERR_SHIFT))) ||
- (ipath_debug & __IPATH_VERBDBG))
+ if ((hwerrs & ~(dd->ipath_lasthwerror | TXE_PIO_PARITY |
+ RXE_EAGER_PARITY)) ||
+ (ipath_debug & __IPATH_VERBDBG))
dev_info(&dd->pcidev->dev, "Hardware error: hwerr=0x%llx "
"(cleared)\n", (unsigned long long) hwerrs);
dd->ipath_lasthwerror |= hwerrs;
@@ -467,7 +482,7 @@ static void ipath_ht_handle_hwerrors(struct ipath_devdata *dd, char *msg,
(hwerrs & ~dd->ipath_hwe_bitsextant));
ctrl = ipath_read_kreg32(dd, dd->ipath_kregs->kr_control);
- if (ctrl & INFINIPATH_C_FREEZEMODE) {
+ if ((ctrl & INFINIPATH_C_FREEZEMODE) && !ipath_diag_inuse) {
/*
* parity errors in send memory are recoverable,
* just cancel the send (if indicated in * sendbuffererror),
@@ -476,50 +491,14 @@ static void ipath_ht_handle_hwerrors(struct ipath_devdata *dd, char *msg,
* occur if a processor speculative read is done to the PIO
* buffer while we are sending a packet, for example.
*/
- if (hwerrs & ((INFINIPATH_HWE_TXEMEMPARITYERR_PIOBUF |
- INFINIPATH_HWE_TXEMEMPARITYERR_PIOPBC)
- << INFINIPATH_HWE_TXEMEMPARITYERR_SHIFT)) {
- ipath_stats.sps_txeparity++;
- ipath_dbg("Recovering from TXE parity error (%llu), "
- "hwerrstatus=%llx\n",
- (unsigned long long) ipath_stats.sps_txeparity,
- (unsigned long long) hwerrs);
- ipath_disarm_senderrbufs(dd);
- hwerrs &= ~((INFINIPATH_HWE_TXEMEMPARITYERR_PIOBUF |
- INFINIPATH_HWE_TXEMEMPARITYERR_PIOPBC)
- << INFINIPATH_HWE_TXEMEMPARITYERR_SHIFT);
- if (!hwerrs) { /* else leave in freeze mode */
- ipath_write_kreg(dd,
- dd->ipath_kregs->kr_control,
- dd->ipath_control);
- return;
- }
- }
- if (hwerrs) {
- /*
- * if any set that we aren't ignoring; only
- * make the complaint once, in case it's stuck
- * or recurring, and we get here multiple
- * times.
- */
- if (dd->ipath_flags & IPATH_INITTED) {
- ipath_dev_err(dd, "Fatal Hardware Error (freeze "
- "mode), no longer usable, SN %.16s\n",
- dd->ipath_serial);
- isfatal = 1;
- }
- *dd->ipath_statusp &= ~IPATH_STATUS_IB_READY;
- /* mark as having had error */
- *dd->ipath_statusp |= IPATH_STATUS_HWERROR;
- /*
- * mark as not usable, at a minimum until driver
- * is reloaded, probably until reboot, since no
- * other reset is possible.
- */
- dd->ipath_flags &= ~IPATH_INITTED;
- } else {
- ipath_dbg("Clearing freezemode on ignored hardware "
- "error\n");
+ if ((hwerrs & TXE_PIO_PARITY) && ipath_ht_txe_recover(dd))
+ hwerrs &= ~TXE_PIO_PARITY;
+ if (hwerrs & RXE_EAGER_PARITY)
+ ipath_dev_err(dd, "RXE parity, Eager TID error is not "
+ "recoverable\n");
+ if (!hwerrs) {
+ ipath_dbg("Clearing freezemode on ignored or "
+ "recovered hardware error\n");
ctrl &= ~INFINIPATH_C_FREEZEMODE;
ipath_write_kreg(dd, dd->ipath_kregs->kr_control,
ctrl);
@@ -587,7 +566,32 @@ static void ipath_ht_handle_hwerrors(struct ipath_devdata *dd, char *msg,
dd->ipath_hwerrmask);
}
- ipath_dev_err(dd, "%s hardware error\n", msg);
+ if (hwerrs) {
+ /*
+ * if any set that we aren't ignoring; only
+ * make the complaint once, in case it's stuck
+ * or recurring, and we get here multiple
+ * times.
+ */
+ ipath_dev_err(dd, "%s hardware error\n", msg);
+ if (dd->ipath_flags & IPATH_INITTED) {
+ ipath_dev_err(dd, "Fatal Hardware Error (freeze "
+ "mode), no longer usable, SN %.16s\n",
+ dd->ipath_serial);
+ isfatal = 1;
+ }
+ *dd->ipath_statusp &= ~IPATH_STATUS_IB_READY;
+ /* mark as having had error */
+ *dd->ipath_statusp |= IPATH_STATUS_HWERROR;
+ /*
+ * mark as not usable, at a minimum until driver
+ * is reloaded, probably until reboot, since no
+ * other reset is possible.
+ */
+ dd->ipath_flags &= ~IPATH_INITTED;
+ }
+ else
+ *msg = 0; /* recovered from all of them */
if (isfatal && !ipath_diag_inuse && dd->ipath_freezemsg)
/*
* for status file; if no trailing brace is copied,
@@ -658,7 +662,8 @@ static int ipath_ht_boardname(struct ipath_devdata *dd, char *name,
if (n)
snprintf(name, namelen, "%s", n);
- if (dd->ipath_majrev != 3 || (dd->ipath_minrev < 2 || dd->ipath_minrev > 3)) {
+ if (dd->ipath_majrev != 3 || (dd->ipath_minrev < 2 ||
+ dd->ipath_minrev > 3)) {
/*
* This version of the driver only supports Rev 3.2 and 3.3
*/
@@ -1163,6 +1168,8 @@ static void ipath_ht_init_hwerrors(struct ipath_devdata *dd)
if (!(extsval & INFINIPATH_EXTS_MEMBIST_ENDTEST))
ipath_dev_err(dd, "MemBIST did not complete!\n");
+ if (extsval & INFINIPATH_EXTS_MEMBIST_CORRECT)
+ ipath_dbg("MemBIST corrected\n");
ipath_check_htlink(dd);
@@ -1366,6 +1373,9 @@ static void ipath_ht_put_tid(struct ipath_devdata *dd,
u64 __iomem *tidptr, u32 type,
unsigned long pa)
{
+ if (!dd->ipath_kregbase)
+ return;
+
if (pa != dd->ipath_tidinvalid) {
if (unlikely((pa & ~INFINIPATH_RT_ADDR_MASK))) {
dev_info(&dd->pcidev->dev,
@@ -1382,10 +1392,10 @@ static void ipath_ht_put_tid(struct ipath_devdata *dd,
pa |= lenvalid | INFINIPATH_RT_VALID;
}
}
- if (dd->ipath_kregbase)
- writeq(pa, tidptr);
+ writeq(pa, tidptr);
}
+
/**
* ipath_ht_clear_tid - clear all TID entries for a port, expected and eager
* @dd: the infinipath device
@@ -1515,7 +1525,7 @@ static int ipath_ht_early_init(struct ipath_devdata *dd)
INFINIPATH_S_ABORT);
ipath_get_eeprom_info(dd);
- if(dd->ipath_boardrev == 5 && dd->ipath_serial[0] == '1' &&
+ if (dd->ipath_boardrev == 5 && dd->ipath_serial[0] == '1' &&
dd->ipath_serial[1] == '2' && dd->ipath_serial[2] == '8') {
/*
* Later production QHT7040 has same changes as QHT7140, so
@@ -1528,6 +1538,24 @@ static int ipath_ht_early_init(struct ipath_devdata *dd)
return 0;
}
+
+static int ipath_ht_txe_recover(struct ipath_devdata *dd)
+{
+ int cnt = ++ipath_stats.sps_txeparity;
+ if (cnt >= IPATH_MAX_PARITY_ATTEMPTS) {
+ if (cnt == IPATH_MAX_PARITY_ATTEMPTS)
+ ipath_dev_err(dd,
+ "Too many attempts to recover from "
+ "TXE parity, giving up\n");
+ return 0;
+ }
+ dev_info(&dd->pcidev->dev,
+ "Recovering from TXE PIO parity error\n");
+ ipath_disarm_senderrbufs(dd, 1);
+ return 1;
+}
+
+
/**
* ipath_init_ht_get_base_info - set chip-specific flags for user code
* @dd: the infinipath device