[PATCH 20/21] amd64_edac: Remove polling mechanism

From: Borislav Petkov
Date: Thu Jul 01 2010 - 11:55:52 EST


From: Borislav Petkov <borislav.petkov@xxxxxxx>

Switch to reusing the mcheck core's machine check polling mechanism
instead of duplicating functionality by using the EDAC polling routine.

Correct formatting while at it.

Signed-off-by: Borislav Petkov <borislav.petkov@xxxxxxx>
---
drivers/edac/amd64_edac.c | 118 -------------------------------------------
drivers/edac/edac_mce_amd.c | 16 +++---
2 files changed, 8 insertions(+), 126 deletions(-)

diff --git a/drivers/edac/amd64_edac.c b/drivers/edac/amd64_edac.c
index cf17dbb..df47daf 100644
--- a/drivers/edac/amd64_edac.c
+++ b/drivers/edac/amd64_edac.c
@@ -1975,107 +1975,6 @@ static int get_channel_from_ecc_syndrome(struct mem_ctl_info *mci, u16 syndrome)
}

/*
- * Check for valid error in the NB Status High register. If so, proceed to read
- * NB Status Low, NB Address Low and NB Address High registers and store data
- * into error structure.
- *
- * Returns:
- * - 1: if hardware regs contains valid error info
- * - 0: if no valid error is indicated
- */
-static int amd64_get_error_info_regs(struct mem_ctl_info *mci,
- struct err_regs *regs)
-{
- struct amd64_pvt *pvt;
- struct pci_dev *misc_f3_ctl;
-
- pvt = mci->pvt_info;
- misc_f3_ctl = pvt->misc_f3_ctl;
-
- if (amd64_read_pci_cfg(misc_f3_ctl, K8_NBSH, &regs->nbsh))
- return 0;
-
- if (!(regs->nbsh & K8_NBSH_VALID_BIT))
- return 0;
-
- /* valid error, read remaining error information registers */
- if (amd64_read_pci_cfg(misc_f3_ctl, K8_NBSL, &regs->nbsl) ||
- amd64_read_pci_cfg(misc_f3_ctl, K8_NBEAL, &regs->nbeal) ||
- amd64_read_pci_cfg(misc_f3_ctl, K8_NBEAH, &regs->nbeah) ||
- amd64_read_pci_cfg(misc_f3_ctl, K8_NBCFG, &regs->nbcfg))
- return 0;
-
- return 1;
-}
-
-/*
- * This function is called to retrieve the error data from hardware and store it
- * in the info structure.
- *
- * Returns:
- * - 1: if a valid error is found
- * - 0: if no error is found
- */
-static int amd64_get_error_info(struct mem_ctl_info *mci,
- struct err_regs *info)
-{
- struct amd64_pvt *pvt;
- struct err_regs regs;
-
- pvt = mci->pvt_info;
-
- if (!amd64_get_error_info_regs(mci, info))
- return 0;
-
- /*
- * Here's the problem with the K8's EDAC reporting: There are four
- * registers which report pieces of error information. They are shared
- * between CEs and UEs. Furthermore, contrary to what is stated in the
- * BKDG, the overflow bit is never used! Every error always updates the
- * reporting registers.
- *
- * Can you see the race condition? All four error reporting registers
- * must be read before a new error updates them! There is no way to read
- * all four registers atomically. The best than can be done is to detect
- * that a race has occured and then report the error without any kind of
- * precision.
- *
- * What is still positive is that errors are still reported and thus
- * problems can still be detected - just not localized because the
- * syndrome and address are spread out across registers.
- *
- * Grrrrr!!!!! Here's hoping that AMD fixes this in some future K8 rev.
- * UEs and CEs should have separate register sets with proper overflow
- * bits that are used! At very least the problem can be fixed by
- * honoring the ErrValid bit in 'nbsh' and not updating registers - just
- * set the overflow bit - unless the current error is CE and the new
- * error is UE which would be the only situation for overwriting the
- * current values.
- */
-
- regs = *info;
-
- /* Use info from the second read - most current */
- if (unlikely(!amd64_get_error_info_regs(mci, info)))
- return 0;
-
- /* clear the error bits in hardware */
- pci_write_bits32(pvt->misc_f3_ctl, K8_NBSH, 0, K8_NBSH_VALID_BIT);
-
- /* Check for the possible race condition */
- if ((regs.nbsh != info->nbsh) ||
- (regs.nbsl != info->nbsl) ||
- (regs.nbeah != info->nbeah) ||
- (regs.nbeal != info->nbeal)) {
- amd64_mc_printk(mci, KERN_WARNING,
- "hardware STATUS read access race condition "
- "detected!\n");
- return 0;
- }
- return 1;
-}
-
-/*
* Handle any Correctable Errors (CEs) that have occurred. Check for valid ERROR
* ADDRESS and process.
*/
@@ -2199,20 +2098,6 @@ void amd64_decode_bus_error(int node_id, struct err_regs *regs)
}

/*
- * The main polling 'check' function, called FROM the edac core to perform the
- * error checking and if an error is encountered, error processing.
- */
-static void amd64_check(struct mem_ctl_info *mci)
-{
- struct err_regs regs;
-
- if (amd64_get_error_info(mci, &regs)) {
- struct amd64_pvt *pvt = mci->pvt_info;
- amd_decode_nb_mce(pvt->mc_node_id, &regs, 1);
- }
-}
-
-/*
* Input:
* 1) struct amd64_pvt which contains pvt->dram_f2_ctl pointer
* 2) AMD Family index value
@@ -2739,9 +2624,6 @@ static void amd64_setup_mci_misc_attributes(struct mem_ctl_info *mci)
mci->dev_name = pci_name(pvt->dram_f2_ctl);
mci->ctl_page_to_phys = NULL;

- /* IMPORTANT: Set the polling 'check' function in this module */
- mci->edac_check = amd64_check;
-
/* memory scrubber interface */
mci->set_sdram_scrub_rate = amd64_set_scrub_rate;
mci->get_sdram_scrub_rate = amd64_get_scrub_rate;
diff --git a/drivers/edac/edac_mce_amd.c b/drivers/edac/edac_mce_amd.c
index 97e64bc..bae9351 100644
--- a/drivers/edac/edac_mce_amd.c
+++ b/drivers/edac/edac_mce_amd.c
@@ -133,7 +133,7 @@ static void amd_decode_dc_mce(u64 mc0_status)
u32 ec = mc0_status & 0xffff;
u32 xec = (mc0_status >> 16) & 0xf;

- pr_emerg(" Data Cache Error");
+ pr_emerg("Data Cache Error");

if (xec == 1 && TLB_ERROR(ec))
pr_cont(": %s TLB multimatch.\n", LL_MSG(ec));
@@ -176,7 +176,7 @@ static void amd_decode_ic_mce(u64 mc1_status)
u32 ec = mc1_status & 0xffff;
u32 xec = (mc1_status >> 16) & 0xf;

- pr_emerg(" Instruction Cache Error");
+ pr_emerg("Instruction Cache Error");

if (xec == 1 && TLB_ERROR(ec))
pr_cont(": %s TLB multimatch.\n", LL_MSG(ec));
@@ -233,7 +233,7 @@ static void amd_decode_bu_mce(u64 mc2_status)
u32 ec = mc2_status & 0xffff;
u32 xec = (mc2_status >> 16) & 0xf;

- pr_emerg(" Bus Unit Error");
+ pr_emerg("Bus Unit Error");

if (xec == 0x1)
pr_cont(" in the write data buffers.\n");
@@ -275,7 +275,7 @@ static void amd_decode_ls_mce(u64 mc3_status)
u32 ec = mc3_status & 0xffff;
u32 xec = (mc3_status >> 16) & 0xf;

- pr_emerg(" Load Store Error");
+ pr_emerg("Load Store Error");

if (xec == 0x0) {
u8 rrrr = (ec >> 4) & 0xf;
@@ -304,7 +304,7 @@ void amd_decode_nb_mce(int node_id, struct err_regs *regs, int handle_errors)
if (TLB_ERROR(ec) && !report_gart_errors)
return;

- pr_emerg(" Northbridge Error, node %d", node_id);
+ pr_emerg("Northbridge Error, node %d", node_id);

/*
* F10h, revD can disable ErrCpu[3:0] so check that first and also the
@@ -342,13 +342,13 @@ static void amd_decode_fr_mce(u64 mc5_status)
static inline void amd_decode_err_code(unsigned int ec)
{
if (TLB_ERROR(ec)) {
- pr_emerg(" Transaction: %s, Cache Level %s\n",
+ pr_emerg("Transaction: %s, Cache Level %s\n",
TT_MSG(ec), LL_MSG(ec));
} else if (MEM_ERROR(ec)) {
- pr_emerg(" Transaction: %s, Type: %s, Cache Level: %s",
+ pr_emerg("Transaction: %s, Type: %s, Cache Level: %s",
RRRR_MSG(ec), TT_MSG(ec), LL_MSG(ec));
} else if (BUS_ERROR(ec)) {
- pr_emerg(" Transaction type: %s(%s), %s, Cache Level: %s, "
+ pr_emerg("Transaction type: %s(%s), %s, Cache Level: %s, "
"Participating Processor: %s\n",
RRRR_MSG(ec), II_MSG(ec), TO_MSG(ec), LL_MSG(ec),
PP_MSG(ec));
--
1.7.1

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/