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;
From:   Smita Koralahalli <Smita.KoralahalliChannabasappa@amd.com>
To:     <x86@kernel.org>, <linux-edac@vger.kernel.org>,
        <linux-kernel@vger.kernel.org>
CC:     Tony Luck <tony.luck@intel.com>, "H . Peter Anvin" <hpa@zytor.com>,
        "Yazen Ghannam" <yazen.ghannam@amd.com>,
        Smita Koralahalli <Smita.KoralahalliChannabasappa@amd.com>
Subject: [PATCH v4 1/2] x86/mce: Check for writes ignored in MCA_STATUS register
Date:   Mon, 14 Feb 2022 17:36:39 -0600
Message-ID: <20220214233640.70510-2-Smita.KoralahalliChannabasappa@amd.com>
In-Reply-To: <20220214233640.70510-1-Smita.KoralahalliChannabasappa@amd.com>
References: <20220214233640.70510-1-Smita.KoralahalliChannabasappa@amd.com>
MIME-Version: 1.0
Content-Type: text/plain
X-MS-Exchange-CrossTenant-OriginalArrivalTime: 14 Feb 2022 23:36:54.8806
 (UTC)
X-MS-Exchange-CrossTenant-Network-Message-Id: 692f7fd8-d758-407d-ef21-08d9f012e292
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: CO1NAM11FT007.eop-nam11.prod.protection.outlook.com
X-MS-Exchange-CrossTenant-AuthAs: Anonymous
X-MS-Exchange-CrossTenant-FromEntityHeader: HybridOnPrem
X-MS-Exchange-Transport-CrossTenantHeadersStamped: CH2PR12MB4970
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

According to Section 2.1.16.3 under HWCR[McStatusWrEn] in "PPR for AMD
Family 19h, Model 01h, Revision B1 Processors - 55898 Rev 0.35 - Feb 5,
2021", the status register may sometimes enforce write ignored behavior
independent of the value of HWCR[McStatusWrEn] depending on the platform
settings.

Hence, evaluate for writes ignored for MCA_STATUS before doing error
injection. If true, return the appropriate error code to userspace.

Make mca_msr_reg exportable in order to be accessible from mce-inject
module.

Link: https://bugzilla.kernel.org/show_bug.cgi?id=206537
Signed-off-by: Smita Koralahalli <Smita.KoralahalliChannabasappa@amd.com>
Reviewed-by: Yazen Ghannam <yazen.ghannam@amd.com>
---
Link:
https://lkml.kernel.org/r/20211104215846.254012-1-Smita.KoralahalliChannabasappa@amd.com

v2:
	msr_ops -> mca_msr_reg().
	simulation -> injection.
	pr_info() -> pr_err().
	Aligned on ",".
v3:
	Removed "x86/mce: Use mca_msr_reg() in prepare_msrs()" patch.
	and made changes on the existing MCx_{STATUS, ADDR, MISC} macros.
v4:
	Simplified the code by just checking for writes ignored behavior in
	MCA_STATUS register.
	Introduced prepare_mca_status() and performed writes ignored checks
	inside the function.
	Rephrased error message.
---
 arch/x86/kernel/cpu/mce/core.c   |  1 +
 arch/x86/kernel/cpu/mce/inject.c | 37 +++++++++++++++++++++++++++++---
 2 files changed, 35 insertions(+), 3 deletions(-)

diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c
index 4f1e825033ce..4ddad8082989 100644
--- a/arch/x86/kernel/cpu/mce/core.c
+++ b/arch/x86/kernel/cpu/mce/core.c
@@ -188,6 +188,7 @@ u32 mca_msr_reg(int bank, enum mca_msr reg)
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(mca_msr_reg);
 
 static void __print_mce(struct mce *m)
 {
diff --git a/arch/x86/kernel/cpu/mce/inject.c b/arch/x86/kernel/cpu/mce/inject.c
index 5fbd7ffb3233..43ba63b7dc73 100644
--- a/arch/x86/kernel/cpu/mce/inject.c
+++ b/arch/x86/kernel/cpu/mce/inject.c
@@ -470,11 +470,36 @@ static void toggle_nb_mca_mst_cpu(u16 nid)
 		       __func__, PCI_FUNC(F3->devfn), NBCFG);
 }
 
+struct mce_err_handler {
+	struct mce *mce;
+	int err;
+};
+
+static struct mce_err_handler mce_err;
+
+static bool prepare_mca_status(struct mce *m)
+{
+	u32 status_reg = mca_msr_reg(m->bank, MCA_STATUS);
+	u64 status_val = m->status;
+
+	wrmsrl(status_reg, status_val);
+	rdmsrl(status_reg, status_val);
+
+	return status_val;
+}
+
 static void prepare_msrs(void *info)
 {
-	struct mce m = *(struct mce *)info;
+	struct mce_err_handler *i_mce_err = ((struct mce_err_handler *)info);
+	struct mce m = *i_mce_err->mce;
 	u8 b = m.bank;
 
+	if (!prepare_mca_status(&m)) {
+		pr_err("Platform does not allow error injection, try using APEI EINJ instead.\n");
+		i_mce_err->err = -EINVAL;
+		return;
+	}
+
 	wrmsrl(MSR_IA32_MCG_STATUS, m.mcgstatus);
 
 	if (boot_cpu_has(X86_FEATURE_SMCA)) {
@@ -501,6 +526,9 @@ static void do_inject(void)
 	unsigned int cpu = i_mce.extcpu;
 	u8 b = i_mce.bank;
 
+	mce_err.mce = &i_mce;
+	mce_err.err = 0;
+
 	i_mce.tsc = rdtsc_ordered();
 
 	i_mce.status |= MCI_STATUS_VAL;
@@ -552,10 +580,13 @@ static void do_inject(void)
 
 	i_mce.mcgstatus = mcg_status;
 	i_mce.inject_flags = inj_type;
-	smp_call_function_single(cpu, prepare_msrs, &i_mce, 0);
+	smp_call_function_single(cpu, prepare_msrs, &mce_err, 0);
 
 	toggle_hw_mce_inject(cpu, false);
 
+	if (mce_err.err)
+		goto err;
+
 	switch (inj_type) {
 	case DFR_INT_INJ:
 		smp_call_function_single(cpu, trigger_dfr_int, NULL, 0);
@@ -624,7 +655,7 @@ static int inj_bank_set(void *data, u64 val)
 	/* Reset injection struct */
 	setup_inj_struct(&i_mce);
 
-	return 0;
+	return mce_err.err;
 }
 
 MCE_INJECT_GET(bank);
-- 
2.17.1