[tip:ras/core] x86/mce/AMD: Use saved threshold block info in interrupt handler

[tip-bot for Yazen Ghannam]

Commit-ID:  17ef4af0ec0f97b369f304dc04d61722f3591c4b
Gitweb:     http://git.kernel.org/tip/17ef4af0ec0f97b369f304dc04d61722f3591c4b
Author:     Yazen Ghannam <yazen.ghannam@xxxxxxx>
AuthorDate: Tue, 13 Jun 2017 18:28:29 +0200
Committer:  Ingo Molnar <mingo@xxxxxxxxxx>
CommitDate: Wed, 14 Jun 2017 07:32:06 +0200

x86/mce/AMD: Use saved threshold block info in interrupt handler

In the amd_threshold_interrupt() handler, we loop through every possible
block in each bank and rediscover the block's address and if it's valid,
e.g. valid, counter present and not locked.

However, we already have the address saved in the threshold blocks list
for each CPU and bank. The list only contains blocks that have passed
all the valid checks.

Besides the redundancy, there's also a smp_call_function* in
get_block_address() which causes a warning when servicing the interrupt:

 WARNING: CPU: 0 PID: 0 at kernel/smp.c:281 smp_call_function_single+0xdd/0xf0
 ...
 Call Trace:
  <IRQ>
  rdmsr_safe_on_cpu()
  get_block_address.isra.2()
  amd_threshold_interrupt()
  smp_threshold_interrupt()
  threshold_interrupt()

because we do get called in an interrupt handler *with* interrupts
disabled, which can result in a deadlock.

Drop the redundant valid checks and move the overflow check, logging and
block reset into a separate function.

Check the first block then iterate over the rest. This procedure is
needed since the first block is used as the head of the list.

Signed-off-by: Yazen Ghannam <yazen.ghannam@xxxxxxx>
Signed-off-by: Borislav Petkov <bp@xxxxxxx>
Cc: Borislav Petkov <bp@xxxxxxxxx>
Cc: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: Tony Luck <tony.luck@xxxxxxxxx>
Cc: linux-edac <linux-edac@xxxxxxxxxxxxxxx>
Link: http://lkml.kernel.org/r/20170613162835.30750-3-bp@xxxxxxxxx
Signed-off-by: Ingo Molnar <mingo@xxxxxxxxxx>
---
 arch/x86/kernel/cpu/mcheck/mce_amd.c | 66 +++++++++++++++++++-----------------
 1 file changed, 35 insertions(+), 31 deletions(-)

diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c
index d11f94e..9e314bc 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_amd.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c
@@ -867,49 +867,53 @@ static void log_error_thresholding(unsigned int bank, u64 misc)
 	_log_error_bank(bank, msr_ops.status(bank), msr_ops.addr(bank), misc);
 }
 
+static void log_and_reset_block(struct threshold_block *block)
+{
+	struct thresh_restart tr;
+	u32 low = 0, high = 0;
+
+	if (!block)
+		return;
+
+	if (rdmsr_safe(block->address, &low, &high))
+		return;
+
+	if (!(high & MASK_OVERFLOW_HI))
+		return;
+
+	/* Log the MCE which caused the threshold event. */
+	log_error_thresholding(block->bank, ((u64)high << 32) | low);
+
+	/* Reset threshold block after logging error. */
+	memset(&tr, 0, sizeof(tr));
+	tr.b = block;
+	threshold_restart_bank(&tr);
+}
+
 /*
  * Threshold interrupt handler will service THRESHOLD_APIC_VECTOR. The interrupt
  * goes off when error_count reaches threshold_limit.
  */
 static void amd_threshold_interrupt(void)
 {
-	u32 low = 0, high = 0, address = 0;
-	unsigned int bank, block, cpu = smp_processor_id();
-	struct thresh_restart tr;
+	struct threshold_block *first_block = NULL, *block = NULL, *tmp = NULL;
+	unsigned int bank, cpu = smp_processor_id();
 
 	for (bank = 0; bank < mca_cfg.banks; ++bank) {
 		if (!(per_cpu(bank_map, cpu) & (1 << bank)))
 			continue;
-		for (block = 0; block < NR_BLOCKS; ++block) {
-			address = get_block_address(cpu, address, low, high, bank, block);
-			if (!address)
-				break;
-
-			if (rdmsr_safe(address, &low, &high))
-				break;
-
-			if (!(high & MASK_VALID_HI)) {
-				if (block)
-					continue;
-				else
-					break;
-			}
-
-			if (!(high & MASK_CNTP_HI)  ||
-			     (high & MASK_LOCKED_HI))
-				continue;
-
-			if (!(high & MASK_OVERFLOW_HI))
-				continue;
 
-			/* Log the MCE which caused the threshold event. */
-			log_error_thresholding(bank, ((u64)high << 32) | low);
+		first_block = per_cpu(threshold_banks, cpu)[bank]->blocks;
+		if (!first_block)
+			continue;
 
-			/* Reset threshold block after logging error. */
-			memset(&tr, 0, sizeof(tr));
-			tr.b = &per_cpu(threshold_banks, cpu)[bank]->blocks[block];
-			threshold_restart_bank(&tr);
-		}
+		/*
+		 * The first block is also the head of the list. Check it first
+		 * before iterating over the rest.
+		 */
+		log_and_reset_block(first_block);
+		list_for_each_entry_safe(block, tmp, &first_block->miscj, miscj)
+			log_and_reset_block(block);
 	}
 }