lists.openwall.net   lists  /  announce  owl-users  owl-dev  john-users  john-dev  passwdqc-users  yescrypt  popa3d-users  /  oss-security  kernel-hardening  musl  sabotage  tlsify  passwords  /  crypt-dev  xvendor  /  Bugtraq  Full-Disclosure  linux-kernel  linux-netdev  linux-ext4  linux-hardening  linux-cve-announce  PHC 
Open Source and information security mailing list archives
 
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <ZxLBwO4HkkJG4WYn@agluck-desk3.sc.intel.com>
Date: Fri, 18 Oct 2024 13:14:56 -0700
From: Tony Luck <tony.luck@...el.com>
To: Sohil Mehta <sohil.mehta@...el.com>
Cc: Qiuxu Zhuo <qiuxu.zhuo@...el.com>, bp@...en8.de, tglx@...utronix.de,
	dave.hansen@...ux.intel.com, mingo@...hat.com, hpa@...or.com,
	x86@...nel.org, linux-edac@...r.kernel.org,
	linux-kernel@...r.kernel.org
Subject: Re: [PATCH v2 06/10] x86/mce: Convert multiple if () statements into
 a switch() statement

On Fri, Oct 18, 2024 at 12:44:00PM -0700, Sohil Mehta wrote:
> > diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c
> > index 725c1d6fb1e5..40672fe0991a 100644
> > --- a/arch/x86/kernel/cpu/mce/core.c
> > +++ b/arch/x86/kernel/cpu/mce/core.c
> > @@ -1892,7 +1892,8 @@ static int __mcheck_cpu_apply_quirks(struct cpuinfo_x86 *c)
> >  	}
> >  
> >  	/* This should be disabled by the BIOS, but isn't always */
> 
> This comment is specific to the AMD and placing it before the switch
> makes it seem generic to the entire switch statement. It should probably
> be moved inside the AMD case just above the disable GART TLB check.
> 
> > -	if (c->x86_vendor == X86_VENDOR_AMD) {
> > +	switch (c->x86_vendor) {
> > +	case X86_VENDOR_AMD:
> >  		if (c->x86 == 15 && this_cpu_read(mce_num_banks) > 4) {
> >  			/*
> >  			 * disable GART TBL walk error reporting, which
> > @@ -1925,9 +1926,9 @@ static int __mcheck_cpu_apply_quirks(struct cpuinfo_x86 *c)
> >  		if (c->x86 >= 0x17 && c->x86 <= 0x1A)
> >  			mce_flags.zen_ifu_quirk = 1;
> >  
> > -	}
> > +		break;
> >  
> 
> 
> Also, why not include the unknown vendor check (right above) inside the
> switch case as well?
> 
> if (c->x86_vendor == X86_VENDOR_UNKNOWN) {
> 	pr_info("unknown CPU type - not enabling MCE support\n");
> 	return -EOPNOTSUPP;
> }
> 
> This seems to follow the same pattern as others and can be the first
> case inside the switch.

The vendor specific bits are large enough to warrant their own
static functions (as we do elsewhere in this file).

How about this (only compile-tested) patch?

-Tony


>From 967d8637ac90823f28f4612cbbac305c421b4853 Mon Sep 17 00:00:00 2001
From: Tony Luck <tony.luck@...el.com>
Date: Fri, 18 Oct 2024 13:01:02 -0700
Subject: [PATCH] x86/mce: Break up __mcheck_cpu_apply_quirks()

Split each vendor specific part into its own helper function.

Signed-off-by: Tony Luck <tony.luck@...el.com>
---
 arch/x86/kernel/cpu/mce/core.c | 172 ++++++++++++++++++---------------
 1 file changed, 96 insertions(+), 76 deletions(-)

diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c
index 2a938f429c4d..f51fb393d369 100644
--- a/arch/x86/kernel/cpu/mce/core.c
+++ b/arch/x86/kernel/cpu/mce/core.c
@@ -1880,101 +1880,121 @@ static void __mcheck_cpu_check_banks(void)
 	}
 }
 
-/* Add per CPU specific workarounds here */
-static int __mcheck_cpu_apply_quirks(struct cpuinfo_x86 *c)
+static void apply_quirks_amd(struct cpuinfo_x86 *c)
 {
 	struct mce_bank *mce_banks = this_cpu_ptr(mce_banks_array);
 	struct mca_config *cfg = &mca_cfg;
 
-	if (c->x86_vendor == X86_VENDOR_UNKNOWN) {
-		pr_info("unknown CPU type - not enabling MCE support\n");
-		return -EOPNOTSUPP;
-	}
-
 	/* This should be disabled by the BIOS, but isn't always */
-	if (c->x86_vendor == X86_VENDOR_AMD) {
-		if (c->x86 == 15 && this_cpu_read(mce_num_banks) > 4) {
-			/*
-			 * disable GART TBL walk error reporting, which
-			 * trips off incorrectly with the IOMMU & 3ware
-			 * & Cerberus:
-			 */
-			clear_bit(10, (unsigned long *)&mce_banks[4].ctl);
-		}
-		if (c->x86 < 0x11 && cfg->bootlog < 0) {
-			/*
-			 * Lots of broken BIOS around that don't clear them
-			 * by default and leave crap in there. Don't log:
-			 */
-			cfg->bootlog = 0;
-		}
+	if (c->x86 == 15 && this_cpu_read(mce_num_banks) > 4) {
 		/*
-		 * Various K7s with broken bank 0 around. Always disable
-		 * by default.
+		 * disable GART TBL walk error reporting, which
+		 * trips off incorrectly with the IOMMU & 3ware
+		 * & Cerberus:
 		 */
-		if (c->x86 == 6 && this_cpu_read(mce_num_banks) > 0)
-			mce_banks[0].ctl = 0;
-
+		clear_bit(10, (unsigned long *)&mce_banks[4].ctl);
+	}
+	if (c->x86 < 0x11 && cfg->bootlog < 0) {
 		/*
-		 * overflow_recov is supported for F15h Models 00h-0fh
-		 * even though we don't have a CPUID bit for it.
+		 * Lots of broken BIOS around that don't clear them
+		 * by default and leave crap in there. Don't log:
 		 */
-		if (c->x86 == 0x15 && c->x86_model <= 0xf)
-			mce_flags.overflow_recov = 1;
+		cfg->bootlog = 0;
+	}
+	/*
+	 * Various K7s with broken bank 0 around. Always disable
+	 * by default.
+	 */
+	if (c->x86 == 6 && this_cpu_read(mce_num_banks) > 0)
+		mce_banks[0].ctl = 0;
 
-		if (c->x86 >= 0x17 && c->x86 <= 0x1A)
-			mce_flags.zen_ifu_quirk = 1;
+	/*
+	 * overflow_recov is supported for F15h Models 00h-0fh
+	 * even though we don't have a CPUID bit for it.
+	 */
+	if (c->x86 == 0x15 && c->x86_model <= 0xf)
+		mce_flags.overflow_recov = 1;
 
-	}
+	if (c->x86 >= 0x17 && c->x86 <= 0x1A)
+		mce_flags.zen_ifu_quirk = 1;
+}
 
-	if (c->x86_vendor == X86_VENDOR_INTEL) {
-		/*
-		 * SDM documents that on family 6 bank 0 should not be written
-		 * because it aliases to another special BIOS controlled
-		 * register.
-		 * But it's not aliased anymore on model 0x1a+
-		 * Don't ignore bank 0 completely because there could be a
-		 * valid event later, merely don't write CTL0.
-		 */
+static void apply_quirks_intel(struct cpuinfo_x86 *c)
+{
+	struct mce_bank *mce_banks = this_cpu_ptr(mce_banks_array);
+	struct mca_config *cfg = &mca_cfg;
 
-		if (c->x86 == 6 && c->x86_model < 0x1A && this_cpu_read(mce_num_banks) > 0)
-			mce_banks[0].init = false;
+	/*
+	 * SDM documents that on family 6 bank 0 should not be written
+	 * because it aliases to another special BIOS controlled
+	 * register.
+	 * But it's not aliased anymore on model 0x1a+
+	 * Don't ignore bank 0 completely because there could be a
+	 * valid event later, merely don't write CTL0.
+	 */
 
-		/*
-		 * All newer Intel systems support MCE broadcasting. Enable
-		 * synchronization with a one second timeout.
-		 */
-		if ((c->x86 > 6 || (c->x86 == 6 && c->x86_model >= 0xe)) &&
-			cfg->monarch_timeout < 0)
-			cfg->monarch_timeout = USEC_PER_SEC;
+	if (c->x86 == 6 && c->x86_model < 0x1A && this_cpu_read(mce_num_banks) > 0)
+		mce_banks[0].init = false;
 
-		/*
-		 * There are also broken BIOSes on some Pentium M and
-		 * earlier systems:
-		 */
-		if (c->x86 == 6 && c->x86_model <= 13 && cfg->bootlog < 0)
-			cfg->bootlog = 0;
+	/*
+	 * All newer Intel systems support MCE broadcasting. Enable
+	 * synchronization with a one second timeout.
+	 */
+	if ((c->x86 > 6 || (c->x86 == 6 && c->x86_model >= 0xe)) &&
+	    cfg->monarch_timeout < 0)
+		cfg->monarch_timeout = USEC_PER_SEC;
 
-		if (c->x86_vfm == INTEL_SANDYBRIDGE_X)
-			mce_flags.snb_ifu_quirk = 1;
+	/*
+	 * There are also broken BIOSes on some Pentium M and
+	 * earlier systems:
+	 */
+	if (c->x86 == 6 && c->x86_model <= 13 && cfg->bootlog < 0)
+		cfg->bootlog = 0;
 
-		/*
-		 * Skylake, Cascacde Lake and Cooper Lake require a quirk on
-		 * rep movs.
-		 */
-		if (c->x86_vfm == INTEL_SKYLAKE_X)
-			mce_flags.skx_repmov_quirk = 1;
+	if (c->x86_vfm == INTEL_SANDYBRIDGE_X)
+		mce_flags.snb_ifu_quirk = 1;
+
+	/*
+	 * Skylake, Cascacde Lake and Cooper Lake require a quirk on
+	 * rep movs.
+	 */
+	if (c->x86_vfm == INTEL_SKYLAKE_X)
+		mce_flags.skx_repmov_quirk = 1;
+}
+
+static void apply_quirks_zhaoxin(struct cpuinfo_x86 *c)
+{
+	struct mca_config *cfg = &mca_cfg;
+
+	/*
+	 * All newer Zhaoxin CPUs support MCE broadcasting. Enable
+	 * synchronization with a one second timeout.
+	 */
+	if (c->x86 > 6 || (c->x86_model == 0x19 || c->x86_model == 0x1f)) {
+		if (cfg->monarch_timeout < 0)
+			cfg->monarch_timeout = USEC_PER_SEC;
 	}
+}
 
-	if (c->x86_vendor == X86_VENDOR_ZHAOXIN) {
-		/*
-		 * All newer Zhaoxin CPUs support MCE broadcasting. Enable
-		 * synchronization with a one second timeout.
-		 */
-		if (c->x86 > 6 || (c->x86_model == 0x19 || c->x86_model == 0x1f)) {
-			if (cfg->monarch_timeout < 0)
-				cfg->monarch_timeout = USEC_PER_SEC;
-		}
+/* Add per CPU specific workarounds here */
+static int __mcheck_cpu_apply_quirks(struct cpuinfo_x86 *c)
+{
+	struct mca_config *cfg = &mca_cfg;
+
+	switch (c->x86_vendor) {
+	case X86_VENDOR_UNKNOWN:
+		pr_info("unknown CPU type - not enabling MCE support\n");
+		return -EOPNOTSUPP;
+
+	case X86_VENDOR_AMD:
+		apply_quirks_amd(c);
+		break;
+	case X86_VENDOR_INTEL:
+		apply_quirks_intel(c);
+		break;
+	case X86_VENDOR_ZHAOXIN:
+		apply_quirks_zhaoxin(c);
+		break;
 	}
 
 	if (cfg->monarch_timeout < 0)
-- 
2.47.0

> 

Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ