x86/mce: Add PCI quirks to identify Xeons with machine check recovery

Each Xeon includes a number of capability registers in PCI space that
describe some features not enumerated by CPUID.

Use these to determine that we are running on a model that can recover from
machine checks. Hooks for Ivybridge ... Skylake provided.

Signed-off-by: Tony Luck <tony.luck@intel.com>
Acked-by: Borislav Petkov <bp@suse.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Boris Petkov <bp@suse.de>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/abf331dc4a3e2a2d17444129bc51127437bcf4ba.1472754711.git.tony.luck@intel.com
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

arch/x86/include/asm/string_64.h

@@ -2,6 +2,7 @@
 #define _ASM_X86_STRING_64_H
 
 #ifdef __KERNEL__
+#include <linux/jump_label.h>
 
 /* Written 2002 by Andi Kleen */
 
@@ -78,6 +79,8 @@ int strcmp(const char *cs, const char *ct);
 #define memset(s, c, n) __memset(s, c, n)
 #endif
 
+DECLARE_STATIC_KEY_FALSE(mcsafe_key);
+
 /**
  * memcpy_mcsafe - copy memory with indication if a machine check happened
  *

arch/x86/kernel/cpu/mcheck/mce.c

@@ -41,6 +41,7 @@
 #include <linux/debugfs.h>
 #include <linux/irq_work.h>
 #include <linux/export.h>
+#include <linux/jump_label.h>
 
 #include <asm/processor.h>
 #include <asm/traps.h>
@@ -2080,6 +2081,7 @@ void mce_disable_bank(int bank)
  * mce=bootlog Log MCEs from before booting. Disabled by default on AMD.
  * mce=nobootlog Don't log MCEs from before booting.
  * mce=bios_cmci_threshold Don't program the CMCI threshold
+ * mce=recovery force enable memcpy_mcsafe()
  */
 static int __init mcheck_enable(char *str)
 {
@@ -2676,8 +2678,14 @@ static int __init mcheck_debugfs_init(void)
 static int __init mcheck_debugfs_init(void) { return -EINVAL; }
 #endif
 
+DEFINE_STATIC_KEY_FALSE(mcsafe_key);
+EXPORT_SYMBOL_GPL(mcsafe_key);
+
 static int __init mcheck_late_init(void)
 {
+	if (mca_cfg.recovery)
+		static_branch_inc(&mcsafe_key);
+
 	mcheck_debugfs_init();
 
 	/*

arch/x86/kernel/quirks.c

@@ -626,3 +626,34 @@ DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_16H_NB_F3,
 			amd_disable_seq_and_redirect_scrub);
 
 #endif
+
+#if defined(CONFIG_X86_64) && defined(CONFIG_X86_MCE)
+#include <linux/jump_label.h>
+#include <asm/string_64.h>
+
+/* Ivy Bridge, Haswell, Broadwell */
+static void quirk_intel_brickland_xeon_ras_cap(struct pci_dev *pdev)
+{
+	u32 capid0;
+
+	pci_read_config_dword(pdev, 0x84, &capid0);
+
+	if (capid0 & 0x10)
+		static_branch_inc(&mcsafe_key);
+}
+
+/* Skylake */
+static void quirk_intel_purley_xeon_ras_cap(struct pci_dev *pdev)
+{
+	u32 capid0;
+
+	pci_read_config_dword(pdev, 0x84, &capid0);
+
+	if ((capid0 & 0xc0) == 0xc0)
+		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);
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x6fc0, quirk_intel_brickland_xeon_ras_cap);
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x2083, quirk_intel_purley_xeon_ras_cap);
+#endif