aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2018-06-24 19:22:19 +0800
committerLinus Torvalds <torvalds@linux-foundation.org>2018-06-24 19:22:19 +0800
commita43de489934cadcbc4cc08a6590fdcc833768461 (patch)
tree61b688a0017e696bd1133d48a7c302d66bfa8ae2
parent6242258b6b472f8fdd8ed9b735cc1190c185d16d (diff)
parent40c36e2741d7fe1e66d6ec55477ba5fd19c9c5d2 (diff)
downloadlinux-stericsson-a43de489934cadcbc4cc08a6590fdcc833768461.tar.gz
Merge branch 'ras-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull ras fixes from Thomas Gleixner: "A set of fixes for RAS/MCE: - Improve the error message when the kernel cannot recover from a MCE so the maximum amount of information gets provided. - Individually check MCE recovery features on SkyLake CPUs instead of assuming none when the CAPID0 register does not advertise the general ability for recovery. - Prevent MCE to output inconsistent messages which first show an error location and then claim that the source is unknown. - Prevent overwriting MCi_STATUS in the attempt to gather more information when a fatal MCE has alreay been detected. This leads to empty status values in the printout and failing to react promptly on the fatal event" * 'ras-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: x86/mce: Fix incorrect "Machine check from unknown source" message x86/mce: Do not overwrite MCi_STATUS in mce_no_way_out() x86/mce: Check for alternate indication of machine check recovery on Skylake x86/mce: Improve error message when kernel cannot recover
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce-severity.c5
-rw-r--r--arch/x86/kernel/cpu/mcheck/mce.c44
-rw-r--r--arch/x86/kernel/quirks.c11
3 files changed, 42 insertions, 18 deletions
diff --git a/arch/x86/kernel/cpu/mcheck/mce-severity.c b/arch/x86/kernel/cpu/mcheck/mce-severity.c
index 5bbd06f38ff6..f34d89c01edc 100644
--- a/arch/x86/kernel/cpu/mcheck/mce-severity.c
+++ b/arch/x86/kernel/cpu/mcheck/mce-severity.c
@@ -160,6 +160,11 @@ static struct severity {
SER, MASK(MCI_STATUS_OVER|MCI_UC_SAR|MCI_ADDR|MCACOD, MCI_UC_SAR|MCI_ADDR|MCACOD_INSTR),
USER
),
+ MCESEV(
+ PANIC, "Data load in unrecoverable area of kernel",
+ SER, MASK(MCI_STATUS_OVER|MCI_UC_SAR|MCI_ADDR|MCACOD, MCI_UC_SAR|MCI_ADDR|MCACOD_DATA),
+ KERNEL
+ ),
#endif
MCESEV(
PANIC, "Action required: unknown MCACOD",
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index e4cf6ff1c2e1..c102ad51025e 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -772,23 +772,25 @@ EXPORT_SYMBOL_GPL(machine_check_poll);
static int mce_no_way_out(struct mce *m, char **msg, unsigned long *validp,
struct pt_regs *regs)
{
- int i, ret = 0;
char *tmp;
+ int i;
for (i = 0; i < mca_cfg.banks; i++) {
m->status = mce_rdmsrl(msr_ops.status(i));
- if (m->status & MCI_STATUS_VAL) {
- __set_bit(i, validp);
- if (quirk_no_way_out)
- quirk_no_way_out(i, m, regs);
- }
+ if (!(m->status & MCI_STATUS_VAL))
+ continue;
+
+ __set_bit(i, validp);
+ if (quirk_no_way_out)
+ quirk_no_way_out(i, m, regs);
if (mce_severity(m, mca_cfg.tolerant, &tmp, true) >= MCE_PANIC_SEVERITY) {
+ mce_read_aux(m, i);
*msg = tmp;
- ret = 1;
+ return 1;
}
}
- return ret;
+ return 0;
}
/*
@@ -1205,13 +1207,18 @@ void do_machine_check(struct pt_regs *regs, long error_code)
lmce = m.mcgstatus & MCG_STATUS_LMCES;
/*
+ * Local machine check may already know that we have to panic.
+ * Broadcast machine check begins rendezvous in mce_start()
* Go through all banks in exclusion of the other CPUs. This way we
* don't report duplicated events on shared banks because the first one
- * to see it will clear it. If this is a Local MCE, then no need to
- * perform rendezvous.
+ * to see it will clear it.
*/
- if (!lmce)
+ if (lmce) {
+ if (no_way_out)
+ mce_panic("Fatal local machine check", &m, msg);
+ } else {
order = mce_start(&no_way_out);
+ }
for (i = 0; i < cfg->banks; i++) {
__clear_bit(i, toclear);
@@ -1287,12 +1294,17 @@ void do_machine_check(struct pt_regs *regs, long error_code)
no_way_out = worst >= MCE_PANIC_SEVERITY;
} else {
/*
- * Local MCE skipped calling mce_reign()
- * If we found a fatal error, we need to panic here.
+ * If there was a fatal machine check we should have
+ * already called mce_panic earlier in this function.
+ * Since we re-read the banks, we might have found
+ * something new. Check again to see if we found a
+ * fatal error. We call "mce_severity()" again to
+ * make sure we have the right "msg".
*/
- if (worst >= MCE_PANIC_SEVERITY && mca_cfg.tolerant < 3)
- mce_panic("Machine check from unknown source",
- NULL, NULL);
+ if (worst >= MCE_PANIC_SEVERITY && mca_cfg.tolerant < 3) {
+ mce_severity(&m, cfg->tolerant, &msg, true);
+ mce_panic("Local fatal machine check!", &m, msg);
+ }
}
/*
diff --git a/arch/x86/kernel/quirks.c b/arch/x86/kernel/quirks.c
index 697a4ce04308..736348ead421 100644
--- a/arch/x86/kernel/quirks.c
+++ b/arch/x86/kernel/quirks.c
@@ -645,12 +645,19 @@ static void quirk_intel_brickland_xeon_ras_cap(struct pci_dev *pdev)
/* Skylake */
static void quirk_intel_purley_xeon_ras_cap(struct pci_dev *pdev)
{
- u32 capid0;
+ u32 capid0, capid5;
pci_read_config_dword(pdev, 0x84, &capid0);
+ pci_read_config_dword(pdev, 0x98, &capid5);
- if ((capid0 & 0xc0) == 0xc0)
+ /*
+ * CAPID0{7:6} indicate whether this is an advanced RAS SKU
+ * CAPID5{8:5} indicate that various NVDIMM usage modes are
+ * enabled, so memory machine check recovery is also enabled.
+ */
+ if ((capid0 & 0xc0) == 0xc0 || (capid5 & 0x1e0))
static_branch_inc(&mcsafe_key);
+
}
DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x0ec3, quirk_intel_brickland_xeon_ras_cap);
DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x2fc0, quirk_intel_brickland_xeon_ras_cap);