[v6,1/4] x86/mce: Cleanup bank processing on init

Commit Message

Yazen Ghannam Dec. 6, 2022, 5:36 p.m. UTC

From: Borislav Petkov <[e-mail]>

Unify the bank preparation into __mcheck_cpu_init_clear_banks(), rename
that function to what it does now - prepares banks. Do this so that
generic and vendor banks init goes first so that settings done during
that init can take effect before the first bank polling takes place.

Move __mcheck_cpu_check_banks() into __mcheck_cpu_init_prepare_banks()
as it already loops over the banks.

Signed-off-by: Borislav Petkov <[e-mail]>
Reviewed-by: Yazen Ghannam <[e-mail]>
---

Link:
https://lore.kernel.org/r/Ylb3/[e-mail]

v6:
	New. Added Yazen's Reviewed-by.

 arch/x86/include/asm/mce.h     |  3 +-
 arch/x86/kernel/cpu/mce/core.c | 64 ++++++++++------------------------
 2 files changed, 19 insertions(+), 48 deletions(-)

Comments

Borislav Petkov Dec. 23, 2022, 1:23 p.m. UTC | #1

On Tue, Dec 06, 2022 at 11:36:04AM -0600, Yazen Ghannam wrote:
> -static void __mcheck_cpu_init_clear_banks(void)
> +static void __mcheck_cpu_init_prepare_banks(void)
>  {
>  	struct mce_bank *mce_banks = this_cpu_ptr(mce_banks_array);
> +	mce_banks_t all_banks;
> +	u64 msrval;
>  	int i;
>  
> -	for (i = 0; i < this_cpu_read(mce_num_banks); i++) {
> -		struct mce_bank *b = &mce_banks[i];
> -
> -		if (!b->init)
> -			continue;
> -		wrmsrl(mca_msr_reg(i, MCA_CTL), b->ctl);
> -		wrmsrl(mca_msr_reg(i, MCA_STATUS), 0);
> +	/*
> +	 * Log the machine checks left over from the previous reset. Log them
> +	 * only, do not start processing them. That will happen in mcheck_late_init()
> +	 * when all consumers have been registered on the notifier chain.
> +	 */
> +	if (mca_cfg.bootlog) {
> +		bitmap_fill(all_banks, MAX_NR_BANKS);
> +		machine_check_poll(MCP_UC | MCP_QUEUE_LOG, &all_banks);
>  	}

Yeah, just a nit ontop - lemme move all_banks into the if branch so that
it is closer and obvious:

---
diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c
index 5f406d135d32..a90d3eb6fcd8 100644
--- a/arch/x86/kernel/cpu/mce/core.c
+++ b/arch/x86/kernel/cpu/mce/core.c
@@ -1755,7 +1755,6 @@ static void __mcheck_cpu_init_generic(void)
 static void __mcheck_cpu_init_prepare_banks(void)
 {
 	struct mce_bank *mce_banks = this_cpu_ptr(mce_banks_array);
-	mce_banks_t all_banks;
 	u64 msrval;
 	int i;
 
@@ -1765,6 +1764,8 @@ static void __mcheck_cpu_init_prepare_banks(void)
 	 * when all consumers have been registered on the notifier chain.
 	 */
 	if (mca_cfg.bootlog) {
+		mce_banks_t all_banks;
+
 		bitmap_fill(all_banks, MAX_NR_BANKS);
 		machine_check_poll(MCP_UC | MCP_QUEUE_LOG, &all_banks);
 	}

Patch

diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h
index 6e986088817d..0dd7752345ec 100644
--- a/arch/x86/include/asm/mce.h
+++ b/arch/x86/include/asm/mce.h
@@ -253,8 +253,7 @@  DECLARE_PER_CPU(mce_banks_t, mce_poll_banks);
 enum mcp_flags {
 	MCP_TIMESTAMP	= BIT(0),	/* log time stamp */
 	MCP_UC		= BIT(1),	/* log uncorrected errors */
-	MCP_DONTLOG	= BIT(2),	/* only clear, don't log */
-	MCP_QUEUE_LOG	= BIT(3),	/* only queue to genpool */
+	MCP_QUEUE_LOG	= BIT(2),	/* only queue to genpool */
 };
 bool machine_check_poll(enum mcp_flags flags, mce_banks_t *b);
 
diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c
index 2c8ec5c71712..5f406d135d32 100644
--- a/arch/x86/kernel/cpu/mce/core.c
+++ b/arch/x86/kernel/cpu/mce/core.c
@@ -738,9 +738,6 @@  bool machine_check_poll(enum mcp_flags flags, mce_banks_t *b)
 log_it:
 		error_seen = true;
 
-		if (flags & MCP_DONTLOG)
-			goto clear_it;
-
 		mce_read_aux(&m, i);
 		m.severity = mce_severity(&m, NULL, NULL, false);
 		/*
@@ -1707,7 +1704,7 @@  static void __mcheck_cpu_mce_banks_init(void)
 		/*
 		 * Init them all, __mcheck_cpu_apply_quirks() is going to apply
 		 * the required vendor quirks before
-		 * __mcheck_cpu_init_clear_banks() does the final bank setup.
+		 * __mcheck_cpu_init_prepare_banks() does the final bank setup.
 		 */
 		b->ctl = -1ULL;
 		b->init = true;
@@ -1746,21 +1743,8 @@  static void __mcheck_cpu_cap_init(void)
 
 static void __mcheck_cpu_init_generic(void)
 {
-	enum mcp_flags m_fl = 0;
-	mce_banks_t all_banks;
 	u64 cap;
 
-	if (!mca_cfg.bootlog)
-		m_fl = MCP_DONTLOG;
-
-	/*
-	 * Log the machine checks left over from the previous reset. Log them
-	 * only, do not start processing them. That will happen in mcheck_late_init()
-	 * when all consumers have been registered on the notifier chain.
-	 */
-	bitmap_fill(all_banks, MAX_NR_BANKS);
-	machine_check_poll(MCP_UC | MCP_QUEUE_LOG | m_fl, &all_banks);
-
 	cr4_set_bits(X86_CR4_MCE);
 
 	rdmsrl(MSR_IA32_MCG_CAP, cap);
@@ -1768,36 +1752,22 @@  static void __mcheck_cpu_init_generic(void)
 		wrmsr(MSR_IA32_MCG_CTL, 0xffffffff, 0xffffffff);
 }
 
-static void __mcheck_cpu_init_clear_banks(void)
+static void __mcheck_cpu_init_prepare_banks(void)
 {
 	struct mce_bank *mce_banks = this_cpu_ptr(mce_banks_array);
+	mce_banks_t all_banks;
+	u64 msrval;
 	int i;
 
-	for (i = 0; i < this_cpu_read(mce_num_banks); i++) {
-		struct mce_bank *b = &mce_banks[i];
-
-		if (!b->init)
-			continue;
-		wrmsrl(mca_msr_reg(i, MCA_CTL), b->ctl);
-		wrmsrl(mca_msr_reg(i, MCA_STATUS), 0);
+	/*
+	 * Log the machine checks left over from the previous reset. Log them
+	 * only, do not start processing them. That will happen in mcheck_late_init()
+	 * when all consumers have been registered on the notifier chain.
+	 */
+	if (mca_cfg.bootlog) {
+		bitmap_fill(all_banks, MAX_NR_BANKS);
+		machine_check_poll(MCP_UC | MCP_QUEUE_LOG, &all_banks);
 	}
-}
-
-/*
- * Do a final check to see if there are any unused/RAZ banks.
- *
- * This must be done after the banks have been initialized and any quirks have
- * been applied.
- *
- * Do not call this from any user-initiated flows, e.g. CPU hotplug or sysfs.
- * Otherwise, a user who disables a bank will not be able to re-enable it
- * without a system reboot.
- */
-static void __mcheck_cpu_check_banks(void)
-{
-	struct mce_bank *mce_banks = this_cpu_ptr(mce_banks_array);
-	u64 msrval;
-	int i;
 
 	for (i = 0; i < this_cpu_read(mce_num_banks); i++) {
 		struct mce_bank *b = &mce_banks[i];
@@ -1805,6 +1775,9 @@  static void __mcheck_cpu_check_banks(void)
 		if (!b->init)
 			continue;
 
+		wrmsrl(mca_msr_reg(i, MCA_CTL), b->ctl);
+		wrmsrl(mca_msr_reg(i, MCA_STATUS), 0);
+
 		rdmsrl(mca_msr_reg(i, MCA_CTL), msrval);
 		b->init = !!msrval;
 	}
@@ -2169,8 +2142,7 @@  void mcheck_cpu_init(struct cpuinfo_x86 *c)
 	__mcheck_cpu_init_early(c);
 	__mcheck_cpu_init_generic();
 	__mcheck_cpu_init_vendor(c);
-	__mcheck_cpu_init_clear_banks();
-	__mcheck_cpu_check_banks();
+	__mcheck_cpu_init_prepare_banks();
 	__mcheck_cpu_setup_timer();
 }
 
@@ -2338,7 +2310,7 @@  static void mce_syscore_resume(void)
 {
 	__mcheck_cpu_init_generic();
 	__mcheck_cpu_init_vendor(raw_cpu_ptr(&cpu_info));
-	__mcheck_cpu_init_clear_banks();
+	__mcheck_cpu_init_prepare_banks();
 }
 
 static struct syscore_ops mce_syscore_ops = {
@@ -2356,7 +2328,7 @@  static void mce_cpu_restart(void *data)
 	if (!mce_available(raw_cpu_ptr(&cpu_info)))
 		return;
 	__mcheck_cpu_init_generic();
-	__mcheck_cpu_init_clear_banks();
+	__mcheck_cpu_init_prepare_banks();
 	__mcheck_cpu_init_timer();
 }