x86/mce: Check for alternate indication of machine check recovery on Skylake

aegl · KAGA-KOKO · commit 4c5717da1d02 · 2018-06-07T22:22:12.000+02:00
Currently we just check the "CAPID0" register to see whether the CPU can recover from machine checks. But there are also some special SKUs which do not have all advanced RAS features, but do enable machine check recovery for use with NVDIMMs. Add a check for any of bits {8:5} in the "CAPID5" register (each reports some NVDIMM mode available, if any of them are set, then the system supports memory machine check recovery). Signed-off-by: Tony Luck <tony.luck@intel.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Cc: Qiuxu Zhuo <qiuxu.zhuo@intel.com> Cc: Ashok Raj <ashok.raj@intel.com> Cc: stable@vger.kernel.org # 4.9 Cc: Dan Williams <dan.j.williams@intel.com> Cc: Borislav Petkov <bp@suse.de> Link: https://lkml.kernel.org/r/03cbed6e99ddafb51c2eadf9a3b7c8d7a0cc204e.1527283897.git.tony.luck@intel.com
diff --git 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);
