Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
Received-SPF: Pass (protection.outlook.com: domain of amd.com designates
 165.204.84.17 as permitted sender) receiver=protection.outlook.com;
 client-ip=165.204.84.17; helo=SATLEXMB04.amd.com; pr=C
From:   Smita Koralahalli <Smita.KoralahalliChannabasappa@amd.com>
To:     Borislav Petkov <bp@alien8.de>
CC:     <x86@kernel.org>, <linux-edac@vger.kernel.org>,
        <linux-kernel@vger.kernel.org>, Tony Luck <tony.luck@intel.com>,
        "H . Peter Anvin" <hpa@zytor.com>,
        Yazen Ghannam <yazen.ghannam@amd.com>,
        "Smita Koralahalli" <Smita.KoralahalliChannabasappa@amd.com>,
        Borislav Petkov <bp@suse.de>
Subject: [PATCH] x86/mce: Check whether writes to MCA_STATUS are getting ignored
Date:   Mon, 27 Jun 2022 20:56:46 +0000
Message-ID: <20220627205646.4692-1-Smita.KoralahalliChannabasappa@amd.com>
MIME-Version: 1.0
Content-Type: text/plain
X-MS-Exchange-CrossTenant-OriginalArrivalTime: 27 Jun 2022 20:57:07.9803
 (UTC)
X-MS-Exchange-CrossTenant-Network-Message-Id: 5b72edb1-1096-49e4-f368-08da587f992e
X-MS-Exchange-CrossTenant-Id: 3dd8961f-e488-4e60-8e11-a82d994e183d
X-MS-Exchange-CrossTenant-OriginalAttributedTenantConnectingIp: TenantId=3dd8961f-e488-4e60-8e11-a82d994e183d;Ip=[165.204.84.17];Helo=[SATLEXMB04.amd.com]
X-MS-Exchange-CrossTenant-AuthSource: BN8NAM11FT057.eop-nam11.prod.protection.outlook.com
X-MS-Exchange-CrossTenant-AuthAs: Anonymous
X-MS-Exchange-CrossTenant-FromEntityHeader: HybridOnPrem
X-MS-Exchange-Transport-CrossTenantHeadersStamped: BY5PR12MB3649
X-Spam-Status: No, score=-2.1 required=5.0 tests=BAYES_00,DKIM_SIGNED,
        DKIM_VALID,DKIM_VALID_AU,DKIM_VALID_EF,RCVD_IN_DNSWL_NONE,
        RCVD_IN_MSPIKE_H2,SPF_HELO_PASS,SPF_PASS,T_SCC_BODY_TEXT_LINE
        autolearn=ham autolearn_force=no version=3.4.6
X-Spam-Checker-Version: SpamAssassin 3.4.6 (2021-04-09) on
        lindbergh.monkeyblade.net
Precedence: bulk
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org

The platform can sometimes - depending on its settings - cause writes
to MCA_STATUS MSRs to get ignored, regardless of HWCR[McStatusWrEn]'s
value.

For further info see

  PPR for AMD Family 19h, Model 01h, Revision B1 Processors, doc ID 55898

at https://bugzilla.kernel.org/show_bug.cgi?id=206537.

Therefore, probe for ignored writes to MCA_STATUS to determine if hardware
error injection is at all possible.

  [ bp: Heavily massage commit message and patch. ]

Signed-off-by: Smita Koralahalli <Smita.KoralahalliChannabasappa@amd.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Link: https://lore.kernel.org/r/20220214233640.70510-2-Smita.KoralahalliChannabasappa@amd.com
---
 arch/x86/kernel/cpu/mce/inject.c   | 47 ++++++++++++++++++++++++++++++
 arch/x86/kernel/cpu/mce/internal.h |  2 +-
 2 files changed, 48 insertions(+), 1 deletion(-)

diff --git a/arch/x86/kernel/cpu/mce/inject.c b/arch/x86/kernel/cpu/mce/inject.c
index 5fbd7ffb3233..12cf2e7ca33c 100644
--- a/arch/x86/kernel/cpu/mce/inject.c
+++ b/arch/x86/kernel/cpu/mce/inject.c
@@ -33,6 +33,8 @@
 
 #include "internal.h"
 
+static bool hw_injection_possible = true;
+
 /*
  * Collect all the MCi_XXX settings
  */
@@ -339,6 +341,8 @@ static int __set_inj(const char *buf)
 
 	for (i = 0; i < N_INJ_TYPES; i++) {
 		if (!strncmp(flags_options[i], buf, strlen(flags_options[i]))) {
+			if (i > SW_INJ && !hw_injection_possible)
+				continue;
 			inj_type = i;
 			return 0;
 		}
@@ -717,11 +721,54 @@ static void __init debugfs_init(void)
 				    &i_mce, dfs_fls[i].fops);
 }
 
+static void check_hw_inj_possible(void)
+{
+	int cpu;
+	u8 bank;
+
+	/*
+	 * This behavior exists only on SMCA systems though its not directly
+	 * related to SMCA.
+	 */
+	if (!cpu_feature_enabled(X86_FEATURE_SMCA))
+		return;
+
+	cpu = get_cpu();
+
+	for (bank = 0; bank < MAX_NR_BANKS; ++bank) {
+		u64 status = MCI_STATUS_VAL, ipid;
+
+		/* Check whether bank is populated */
+		rdmsrl(MSR_AMD64_SMCA_MCx_IPID(bank), ipid);
+		if (!ipid)
+			continue;
+
+		toggle_hw_mce_inject(cpu, true);
+
+		wrmsrl_safe(mca_msr_reg(bank, MCA_STATUS), status);
+		rdmsrl_safe(mca_msr_reg(bank, MCA_STATUS), &status);
+
+		if (!status) {
+			hw_injection_possible = false;
+			pr_warn("Platform does not allow *hardware* error injection."
+				"Try using APEI EINJ instead.\n");
+		}
+
+		toggle_hw_mce_inject(cpu, false);
+
+		break;
+	}
+
+	put_cpu();
+}
+
 static int __init inject_init(void)
 {
 	if (!alloc_cpumask_var(&mce_inject_cpumask, GFP_KERNEL))
 		return -ENOMEM;
 
+	check_hw_inj_possible();
+
 	debugfs_init();
 
 	register_nmi_handler(NMI_LOCAL, mce_raise_notify, 0, "mce_notify");
diff --git a/arch/x86/kernel/cpu/mce/internal.h b/arch/x86/kernel/cpu/mce/internal.h
index 4ae0e603f7fa..7e03f5b7f6bd 100644
--- a/arch/x86/kernel/cpu/mce/internal.h
+++ b/arch/x86/kernel/cpu/mce/internal.h
@@ -211,7 +211,7 @@ noinstr u64 mce_rdmsrl(u32 msr);
 
 static __always_inline u32 mca_msr_reg(int bank, enum mca_msr reg)
 {
-	if (mce_flags.smca) {
+	if (cpu_feature_enabled(X86_FEATURE_SMCA)) {
 		switch (reg) {
 		case MCA_CTL:	 return MSR_AMD64_SMCA_MCx_CTL(bank);
 		case MCA_ADDR:	 return MSR_AMD64_SMCA_MCx_ADDR(bank);
-- 
2.17.1