Re: [PATCH v5 2/2] x86/mce: Add support for Extended Physical Address MCA changes

[Borislav Petkov]

On Wed, Apr 13, 2022 at 02:10:30PM +0000, Yazen Ghannam wrote:
> This function gets called from __mcheck_cpu_init_early() so that the info is
> available before the MCA banks are polled in __mcheck_cpu_init_generic().

Would that work?

I've moved first bank polling into __mcheck_cpu_init_clear_banks()
because, well, this function is clearing the banks so it might as well
poll them first. First bank polling in a init_generic function doesn't
make too much sense anyway.

And __mcheck_cpu_check_banks() functionality is moved into
__mcheck_cpu_init_clear_banks() because, well, silly.

On a quick scan, I don't see problems with such move but the devil is in
the detail.

Hmm?

---

diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c
index 99e3ff9607a3..345e068215c4 100644
--- a/arch/x86/kernel/cpu/mce/core.c
+++ b/arch/x86/kernel/cpu/mce/core.c
@@ -1732,21 +1732,8 @@ 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);
@@ -1757,33 +1744,21 @@ static void __mcheck_cpu_init_generic(void)
 static void __mcheck_cpu_init_clear_banks(void)
 {
 	struct mce_bank *mce_banks = this_cpu_ptr(mce_banks_array);
+	enum mcp_flags m_fl = 0;
+	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);
-	}
-}
+	if (!mca_cfg.bootlog)
+		m_fl = MCP_DONTLOG;
 
-/*
- * 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;
+	/*
+	 * 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);
 
 	for (i = 0; i < this_cpu_read(mce_num_banks); i++) {
 		struct mce_bank *b = &mce_banks[i];
@@ -1791,6 +1766,9 @@ 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;
 	}
@@ -2159,7 +2137,6 @@ void mcheck_cpu_init(struct cpuinfo_x86 *c)
 	__mcheck_cpu_init_generic();
 	__mcheck_cpu_init_vendor(c);
 	__mcheck_cpu_init_clear_banks();
-	__mcheck_cpu_check_banks();
 	__mcheck_cpu_setup_timer();
 }
 
-- 
Regards/Gruss,
    Boris.

https://people.kernel.org/tglx/notes-about-netiquette