There are a number of generic and vendor-specific status checks in
machine_check_poll(). These are used to determine if an error should be
skipped.
Move these into helper functions. Future vendor-specific checks will be
added to the helpers.
Reviewed-by: Qiuxu Zhuo <qiuxu.zhuo@xxxxxxxxx>
Tested-by: Tony Luck <tony.luck@xxxxxxxxx>
Reviewed-by: Tony Luck <tony.luck@xxxxxxxxx>
Signed-off-by: Yazen Ghannam <yazen.ghannam@xxxxxxx>
---
Notes:
Link:
https://lore.kernel.org/r/20250415-wip-mca-updates-v3-11-8ffd9eb4aa56@xxxxxxx
v3->v4:
* No change.
v2->v3:
* Add tags from Qiuxu and Tony.
v1->v2:
* Change log_poll_error() to should_log_poll_error().
* Keep code comment.
arch/x86/kernel/cpu/mce/core.c | 88 +++++++++++++++++++++++-------------------
1 file changed, 48 insertions(+), 40 deletions(-)
diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c
index 4f6af060a395..bed059c6c808 100644
--- a/arch/x86/kernel/cpu/mce/core.c
+++ b/arch/x86/kernel/cpu/mce/core.c
@@ -714,6 +714,52 @@ static noinstr void mce_read_aux(struct mce_hw_err *err, int i)
DEFINE_PER_CPU(unsigned, mce_poll_count);
+/*
+ * Newer Intel systems that support software error
+ * recovery need to make additional checks. Other
+ * CPUs should skip over uncorrected errors, but log
+ * everything else.
+ */
+static bool ser_should_log_poll_error(struct mce *m)
+{
+ /* Log "not enabled" (speculative) errors */
+ if (!(m->status & MCI_STATUS_EN))
+ return true;
+
+ /*
+ * Log UCNA (SDM: 15.6.3 "UCR Error Classification")
+ * UC == 1 && PCC == 0 && S == 0
+ */
+ if (!(m->status & MCI_STATUS_PCC) && !(m->status & MCI_STATUS_S))
+ return true;
+
+ return false;
+}
+
+static bool should_log_poll_error(enum mcp_flags flags, struct mce_hw_err *err)
+{
+ struct mce *m = &err->m;
+
+ /* If this entry is not valid, ignore it. */
+ if (!(m->status & MCI_STATUS_VAL))
+ return false;
+
+ /*
+ * If we are logging everything (at CPU online) or this
+ * is a corrected error, then we must log it.
+ */
+ if ((flags & MCP_UC) || !(m->status & MCI_STATUS_UC))
+ return true;
+
+ if (mca_cfg.ser)
+ return ser_should_log_poll_error(m);
+
+ if (m->status & MCI_STATUS_UC)
+ return false;
+
+ return true;
+}
+
/*
* Poll for corrected events or events that happened before reset.
* Those are just logged through /dev/mcelog.
@@ -765,48 +811,10 @@ void machine_check_poll(enum mcp_flags flags, mce_banks_t *b)
if (!mca_cfg.cmci_disabled)
mce_track_storm(m);
- /* If this entry is not valid, ignore it */
- if (!(m->status & MCI_STATUS_VAL))
+ /* Verify that the error should be logged based on hardware conditions. */
+ if (!should_log_poll_error(flags, &err))
continue;
- /*
- * If we are logging everything (at CPU online) or this
- * is a corrected error, then we must log it.
- */
- if ((flags & MCP_UC) || !(m->status & MCI_STATUS_UC))
- goto log_it;
-
- /*
- * Newer Intel systems that support software error
- * recovery need to make additional checks. Other
- * CPUs should skip over uncorrected errors, but log
- * everything else.
- */
- if (!mca_cfg.ser) {
- if (m->status & MCI_STATUS_UC)
- continue;
- goto log_it;
- }
-
- /* Log "not enabled" (speculative) errors */
- if (!(m->status & MCI_STATUS_EN))
- goto log_it;
-
- /*
- * Log UCNA (SDM: 15.6.3 "UCR Error Classification")
- * UC == 1 && PCC == 0 && S == 0
- */
- if (!(m->status & MCI_STATUS_PCC) && !(m->status & MCI_STATUS_S))
- goto log_it;
-
- /*
- * Skip anything else. Presumption is that our read of this
- * bank is racing with a machine check. Leave the log alone
- * for do_machine_check() to deal with it.
- */
- continue;
-
-log_it:
mce_read_aux(&err, i);
m->severity = mce_severity(m, NULL, NULL, false);
/*
--
2.49.0
