diff options
author | Vipin K Parashar <vipin@linux.vnet.ibm.com> | 2016-07-20 19:22:28 +0530 |
---|---|---|
committer | Stewart Smith <stewart@linux.vnet.ibm.com> | 2016-07-21 11:51:21 +1000 |
commit | 3ca77982a3c43e2a320eee742af9ff4dd8b0596f (patch) | |
tree | c4f74ddb0a57b43122644f23a1cf2d55a41a701f | |
parent | 4ae024ed5b9b5e475783c9f930183506ab32a0d9 (diff) | |
download | skiboot-3ca77982a3c43e2a320eee742af9ff4dd8b0596f.zip skiboot-3ca77982a3c43e2a320eee742af9ff4dd8b0596f.tar.gz skiboot-3ca77982a3c43e2a320eee742af9ff4dd8b0596f.tar.bz2 |
hw/xscom: Reset XSCOM engine after finite number of retries when busy
OPAL retries XSCOM read/write operations forever till it succeeds.
This can cause XSCOM ops to hang forever when XSCOM engine remains
busy for some reason. Changed it to retry XSCOM operations only
XSCOM_BUSY_MAX_RETRIES number of times instead of retrying forever.
Also added logic to reset XSCOM engine after XSCOM_BUSY_RESET_THRESHOLD
number of retries to unblock it when it remains busy.
Cc: stable # 9c2d82394fd2 ("xscom: Return OPAL_WRONG_STATE on XSCOM ops..")
Signed-off-by: Vipin K Parashar <vipin@linux.vnet.ibm.com>
Signed-off-by: Vaidyanathan Srinivasan <svaidy@linux.vnet.ibm.com>
Signed-off-by: Stewart Smith <stewart@linux.vnet.ibm.com>
(cherry picked from commit e761222593a1ae932cddbc81239b6a7cd98ddb70)
Signed-off-by: Vipin K Parashar <vipin@linux.vnet.ibm.com>
Signed-off-by: Stewart Smith <stewart@linux.vnet.ibm.com>
-rw-r--r-- | hw/xscom.c | 74 | ||||
-rw-r--r-- | include/errorlog.h | 1 | ||||
-rw-r--r-- | include/xscom.h | 6 |
3 files changed, 64 insertions, 17 deletions
@@ -23,6 +23,7 @@ #include <centaur.h> #include <errorlog.h> #include <opal-api.h> +#include <timebase.h> /* Mask of bits to clear in HMER before an access */ #define HMER_CLR_MASK (~(SPR_HMER_XSCOM_FAIL | \ @@ -41,6 +42,10 @@ DEFINE_LOG_ENTRY(OPAL_RC_XSCOM_RESET, OPAL_PLATFORM_ERR_EVT, OPAL_XSCOM, OPAL_CEC_HARDWARE, OPAL_PREDICTIVE_ERR_GENERAL, OPAL_NA); +DEFINE_LOG_ENTRY(OPAL_RC_XSCOM_BUSY, OPAL_PLATFORM_ERR_EVT, OPAL_XSCOM, + OPAL_CEC_HARDWARE, OPAL_PREDICTIVE_ERR_GENERAL, + OPAL_NA); + /* xscom details to trigger xstop */ static struct { uint64_t addr; @@ -118,18 +123,49 @@ static void xscom_reset(uint32_t gcid) */ } -static int xscom_handle_error(uint64_t hmer, uint32_t gcid, uint32_t pcb_addr, - bool is_write) +static int64_t xscom_handle_error(uint64_t hmer, uint32_t gcid, uint32_t pcb_addr, + bool is_write, int64_t retries) { + struct timespec ts; unsigned int stat = GETFIELD(SPR_HMER_XSCOM_STATUS, hmer); /* XXX Figure out error codes from doc and error * recovery procedures */ switch(stat) { - /* XSCOM blocked, just retry */ + /* + * XSCOM engine is blocked, need to retry. Reset XSCOM engine + * after crossing retry threshold before retrying again. + */ case 1: + if (retries && !(retries % XSCOM_BUSY_RESET_THRESHOLD)) { + prlog(PR_NOTICE, "XSCOM: Busy even after %d retries, " + "resetting XSCOM now. Total retries = %lld\n", + XSCOM_BUSY_RESET_THRESHOLD, retries); + xscom_reset(gcid); + + /* + * Its observed that sometimes immediate retry of + * XSCOM operation returns wrong data. Adding a + * delay for XSCOM reset to be effective. Delay of + * 10 ms is found to be working fine experimentally. + * FIXME: Replace 10ms delay by exact delay needed + * or other alternate method to confirm XSCOM reset + * completion, after checking from HW folks. + */ + ts.tv_sec = 0; + ts.tv_nsec = 10 * 1000; + nanosleep_nopoll(&ts, NULL); + } + + /* Log error if we have retried enough and its still busy */ + if (retries == XSCOM_BUSY_MAX_RETRIES) + log_simple_error(&e_info(OPAL_RC_XSCOM_BUSY), + "XSCOM: %s-busy error gcid=0x%x pcb_addr=0x%x " + "stat=0x%x\n", is_write ? "write" : "read", + gcid, pcb_addr, stat); return OPAL_BUSY; + /* CPU is asleep, don't retry */ case 2: return OPAL_WRONG_STATE; @@ -178,14 +214,14 @@ static bool xscom_gcid_ok(uint32_t gcid) static int __xscom_read(uint32_t gcid, uint32_t pcb_addr, uint64_t *val) { uint64_t hmer; - int64_t ret; + int64_t ret, retries; if (!xscom_gcid_ok(gcid)) { prerror("%s: invalid XSCOM gcid 0x%x\n", __func__, gcid); return OPAL_PARAMETER; } - for (;;) { + for (retries = 0; retries <= XSCOM_BUSY_MAX_RETRIES; retries++) { /* Clear status bits in HMER (HMER is special * writing to it *ands* bits */ @@ -199,27 +235,29 @@ static int __xscom_read(uint32_t gcid, uint32_t pcb_addr, uint64_t *val) /* Check for error */ if (!(hmer & SPR_HMER_XSCOM_FAIL)) - break; + return OPAL_SUCCESS; /* Handle error and possibly eventually retry */ - ret = xscom_handle_error(hmer, gcid, pcb_addr, false); - if (ret == OPAL_HARDWARE || ret == OPAL_WRONG_STATE) - return ret; + ret = xscom_handle_error(hmer, gcid, pcb_addr, false, retries); + if (ret != OPAL_BUSY) + break; } - return OPAL_SUCCESS; + + prerror("XSCOM: Read failed, ret = %lld\n", ret); + return ret; } static int __xscom_write(uint32_t gcid, uint32_t pcb_addr, uint64_t val) { uint64_t hmer; - int64_t ret; + int64_t ret, retries = 0; if (!xscom_gcid_ok(gcid)) { prerror("%s: invalid XSCOM gcid 0x%x\n", __func__, gcid); return OPAL_PARAMETER; } - for (;;) { + for (retries = 0; retries <= XSCOM_BUSY_MAX_RETRIES; retries++) { /* Clear status bits in HMER (HMER is special * writing to it *ands* bits */ @@ -233,14 +271,16 @@ static int __xscom_write(uint32_t gcid, uint32_t pcb_addr, uint64_t val) /* Check for error */ if (!(hmer & SPR_HMER_XSCOM_FAIL)) - break; + return OPAL_SUCCESS; /* Handle error and possibly eventually retry */ - ret = xscom_handle_error(hmer, gcid, pcb_addr, true); - if (ret == OPAL_HARDWARE || ret == OPAL_WRONG_STATE) - return ret; + ret = xscom_handle_error(hmer, gcid, pcb_addr, true, retries); + if (ret != OPAL_BUSY) + break; } - return OPAL_SUCCESS; + + prerror("XSCOM: Write failed, ret = %lld\n", ret); + return ret; } /* diff --git a/include/errorlog.h b/include/errorlog.h index ed90dab..214aed2 100644 --- a/include/errorlog.h +++ b/include/errorlog.h @@ -275,6 +275,7 @@ enum opal_reasoncode { OPAL_RC_XSCOM_RW = OPAL_XS | 0x10, OPAL_RC_XSCOM_INDIRECT_RW = OPAL_XS | 0x11, OPAL_RC_XSCOM_RESET = OPAL_XS | 0x12, + OPAL_RC_XSCOM_BUSY = OPAL_XS | 0x13, /* PCI */ OPAL_RC_PCI_INIT_SLOT = OPAL_PC | 0x10, OPAL_RC_PCI_ADD_SLOT = OPAL_PC | 0x11, diff --git a/include/xscom.h b/include/xscom.h index 933af6a..1aee40e 100644 --- a/include/xscom.h +++ b/include/xscom.h @@ -167,6 +167,12 @@ /* HB folks say: try 10 time for now */ #define XSCOM_IND_MAX_RETRIES 10 +/* Max number of retries when XSCOM remains busy */ +#define XSCOM_BUSY_MAX_RETRIES 3000 + +/* Retry count after which to reset XSCOM, if still busy */ +#define XSCOM_BUSY_RESET_THRESHOLD 1000 + /* * Error handling: * |