x86/mce/amd: Introduce deferred error interrupt handler

Deferred errors indicate error conditions that were not corrected, but
require no action from S/W (or action is optional).These errors provide
info about a latent UC MCE that can occur when a poisoned data is
consumed by the processor.

Processors that report these errors can be configured to generate APIC
interrupts to notify OS about the error.

Provide an interrupt handler in this patch so that OS can catch these
errors as and when they happen. Currently, we simply log the errors and
exit the handler as S/W action is not mandated.

Signed-off-by: Aravind Gopalakrishnan <Aravind.Gopalakrishnan@amd.com>
Cc: Tony Luck <tony.luck@intel.com>
Cc: x86-ml <x86@kernel.org>
Cc: linux-edac <linux-edac@vger.kernel.org>
Link: http://lkml.kernel.org/r/1430913538-1415-5-git-send-email-Aravind.Gopalakrishnan@amd.com
Signed-off-by: Borislav Petkov <bp@suse.de>

1 files changed, 93 insertions, 0 deletions

diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c
index 607075726e10..2e7ebe7e1e80 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_amd.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c
@@ -12,6 +12,8 @@
  *     - added support for AMD Family 0x10 processors
  *  May 2012
  *     - major scrubbing
+ *  May 2015
+ *     - add support for deferred error interrupts (Aravind Gopalakrishnan)
  *
  *  All MC4_MISCi registers are shared between multi-cores
  */
@@ -32,6 +34,7 @@
 #include <asm/idle.h>
 #include <asm/mce.h>
 #include <asm/msr.h>
+#include <asm/trace/irq_vectors.h>
 
 #define NR_BLOCKS         9
 #define THRESHOLD_MAX     0xFFF
@@ -47,6 +50,13 @@
 #define MASK_BLKPTR_LO    0xFF000000
 #define MCG_XBLK_ADDR     0xC0000400
 
+/* Deferred error settings */
+#define MSR_CU_DEF_ERR		0xC0000410
+#define MASK_DEF_LVTOFF		0x000000F0
+#define MASK_DEF_INT_TYPE	0x00000006
+#define DEF_LVT_OFF		0x2
+#define DEF_INT_TYPE_APIC	0x2
+
 static const char * const th_names[] = {
 	"load_store",
 	"insn_fetch",
@@ -60,6 +70,13 @@ static DEFINE_PER_CPU(struct threshold_bank **, threshold_banks);
 static DEFINE_PER_CPU(unsigned char, bank_map);	/* see which banks are on */
 
 static void amd_threshold_interrupt(void);
+static void amd_deferred_error_interrupt(void);
+
+static void default_deferred_error_interrupt(void)
+{
+	pr_err("Unexpected deferred interrupt at vector %x\n", DEFERRED_ERROR_VECTOR);
+}
+void (*deferred_error_int_vector)(void) = default_deferred_error_interrupt;
 
 /*
  * CPU Initialization
@@ -205,6 +222,39 @@ static int setup_APIC_mce(int reserved, int new)
 	return reserved;
 }
 
+static int setup_APIC_deferred_error(int reserved, int new)
+{
+	if (reserved < 0 && !setup_APIC_eilvt(new, DEFERRED_ERROR_VECTOR,
+					      APIC_EILVT_MSG_FIX, 0))
+		return new;
+
+	return reserved;
+}
+
+static void deferred_error_interrupt_enable(struct cpuinfo_x86 *c)
+{
+	u32 low = 0, high = 0;
+	int def_offset = -1, def_new;
+
+	if (rdmsr_safe(MSR_CU_DEF_ERR, &low, &high))
+		return;
+
+	def_new = (low & MASK_DEF_LVTOFF) >> 4;
+	if (!(low & MASK_DEF_LVTOFF)) {
+		pr_err(FW_BUG "Your BIOS is not setting up LVT offset 0x2 for deferred error IRQs correctly.\n");
+		def_new = DEF_LVT_OFF;
+		low = (low & ~MASK_DEF_LVTOFF) | (DEF_LVT_OFF << 4);
+	}
+
+	def_offset = setup_APIC_deferred_error(def_offset, def_new);
+	if ((def_offset == def_new) &&
+	    (deferred_error_int_vector != amd_deferred_error_interrupt))
+		deferred_error_int_vector = amd_deferred_error_interrupt;
+
+	low = (low & ~MASK_DEF_INT_TYPE) | DEF_INT_TYPE_APIC;
+	wrmsr(MSR_CU_DEF_ERR, low, high);
+}
+
 /* cpu init entry point, called from mce.c with preempt off */
 void mce_amd_feature_init(struct cpuinfo_x86 *c)
 {
@@ -262,6 +312,9 @@ init:
 			mce_threshold_block_init(&b, offset);
 		}
 	}
+
+	if (mce_flags.succor)
+		deferred_error_interrupt_enable(c);
 }
 
 static void __log_error(unsigned int bank, bool threshold_err, u64 misc)
@@ -288,6 +341,46 @@ static void __log_error(unsigned int bank, bool threshold_err, u64 misc)
 	wrmsrl(MSR_IA32_MCx_STATUS(bank), 0);
 }
 
+static inline void __smp_deferred_error_interrupt(void)
+{
+	inc_irq_stat(irq_deferred_error_count);
+	deferred_error_int_vector();
+}
+
+asmlinkage __visible void smp_deferred_error_interrupt(void)
+{
+	entering_irq();
+	__smp_deferred_error_interrupt();
+	exiting_ack_irq();
+}
+
+asmlinkage __visible void smp_trace_deferred_error_interrupt(void)
+{
+	entering_irq();
+	trace_deferred_error_apic_entry(DEFERRED_ERROR_VECTOR);
+	__smp_deferred_error_interrupt();
+	trace_deferred_error_apic_exit(DEFERRED_ERROR_VECTOR);
+	exiting_ack_irq();
+}
+
+/* APIC interrupt handler for deferred errors */
+static void amd_deferred_error_interrupt(void)
+{
+	u64 status;
+	unsigned int bank;
+
+	for (bank = 0; bank < mca_cfg.banks; ++bank) {
+		rdmsrl(MSR_IA32_MCx_STATUS(bank), status);
+
+		if (!(status & MCI_STATUS_VAL) ||
+		    !(status & MCI_STATUS_DEFERRED))
+			continue;
+
+		__log_error(bank, false, 0);
+		break;
+	}
+}
+
 /*
  * APIC Interrupt Handler
  */