linux-kernel - [PATCH] x86/mce/AMD: Allow any CPU to initialize smca

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]

Date:   Thu, 29 Jun 2017 13:08:28 -0500
From:   Yazen Ghannam <Yazen.Ghannam@....com>
To:     linux-edac@...r.kernel.org
Cc:     Borislav Petkov <bp@...e.de>, Tony Luck <tony.luck@...el.com>,
        x86@...nel.org, linux-kernel@...r.kernel.org, jack@...ezen.org,
        Yazen Ghannam <yazen.ghannam@....com>
Subject: [PATCH] x86/mce/AMD: Allow any CPU to initialize smca_banks array

From: Yazen Ghannam <yazen.ghannam@....com>

Current SMCA implementations have the same banks on each CPU with the
non-core banks only visible to a "master thread" on each Die. Practically,
this means the smca_banks array, which describes the banks, only needs to
be populated once by a single master thread.

CPU0 seemed like a good candidate to do the populating. However, it's
possible that CPU0 is not enabled in which case the smca_banks array won't
be populated.

Rather than try to figure out another master thread to do the populating,
we should just allow any CPU to populate the array.

Drop the CPU0 check and return early if the bank was already initialized.
Also, drop the WARNing about an already initialized bank, since this will
be a common, expected occurrence.

The smca_banks array is only populated at boot time and CPUs are brought
online sequentially. So there's no need for locking around the array.

If the first CPU up is a master thread, then it will populate the array
with all banks, core and non-core. Every CPU afterwards will return early.

If the first CPU up is not a master thread, then it will populate the array
with all core banks. The first CPU afterwards that is a master thread will
skip populating the core banks and continue populating the non-core banks.
Every CPU afterwards will then return early.

Signed-off-by: Yazen Ghannam <yazen.ghannam@....com>
---
 arch/x86/kernel/cpu/mcheck/mce_amd.c | 9 ++-------
 1 file changed, 2 insertions(+), 7 deletions(-)

diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd.c b/arch/x86/kernel/cpu/mcheck/mce_amd.c
index b41466723f71..37dc43f820b4 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_amd.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_amd.c
@@ -214,8 +214,8 @@ static void smca_configure(unsigned int bank, unsigned int cpu)
 		wrmsr(smca_config, low, high);
 	}

-	/* Collect bank_info using CPU 0 for now. */
-	if (cpu)
+	/* Return early if this bank was already initialized. */
+	if (smca_banks[bank].hwid)
 		return;

 	if (rdmsr_safe_on_cpu(cpu, MSR_AMD64_SMCA_MCx_IPID(bank), &low, &high)) {
@@ -229,11 +229,6 @@ static void smca_configure(unsigned int bank, unsigned int cpu)
 	for (i = 0; i < ARRAY_SIZE(smca_hwid_mcatypes); i++) {
 		s_hwid = &smca_hwid_mcatypes[i];
 		if (hwid_mcatype == s_hwid->hwid_mcatype) {
-
-			WARN(smca_banks[bank].hwid,
-			     "Bank %s already initialized!\n",
-			     smca_get_name(s_hwid->bank_type));
-
 			smca_banks[bank].hwid = s_hwid;
 			smca_banks[bank].id = low;
 			smca_banks[bank].sysfs_id = s_hwid->count++;
-- 
2.7.4