Received-SPF: pass (google.com: domain of linux-kernel+bounces-187753-linux.lists.archive=gmail.com@vger.kernel.org designates 2604:1380:4601:e00::3 as permitted sender) client-ip=2604:1380:4601:e00::3;
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: Yazen Ghannam <yazen.ghannam@amd.com>
To: <linux-edac@vger.kernel.org>
CC: <linux-kernel@vger.kernel.org>, <tony.luck@intel.com>, <x86@kernel.org>,
	<avadhut.naik@amd.com>, <john.allen@amd.com>, Yazen Ghannam
	<yazen.ghannam@amd.com>
Subject: [PATCH 4/9] x86/mce: Move machine_check_poll() status checks to helper functions
Date: Thu, 23 May 2024 10:56:36 -0500
Message-ID: <20240523155641.2805411-5-yazen.ghannam@amd.com>
In-Reply-To: <20240523155641.2805411-1-yazen.ghannam@amd.com>
References: <20240523155641.2805411-1-yazen.ghannam@amd.com>
Precedence: bulk
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Content-Type: text/plain
X-MS-Exchange-CrossTenant-OriginalArrivalTime: 23 May 2024 15:57:01.7323
 (UTC)
X-MS-Exchange-CrossTenant-Network-Message-Id: 7950d509-007b-451e-2cc3-08dc7b40fc1f
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:
	BN1PEPF00004680.namprd03.prod.outlook.com
X-MS-Exchange-CrossTenant-AuthAs: Anonymous
X-MS-Exchange-CrossTenant-FromEntityHeader: HybridOnPrem
X-MS-Exchange-Transport-CrossTenantHeadersStamped: IA0PR12MB8302

There are a number of generic and vendor-specific status checks in
machine_check_poll(). These are used to determine if an error should be
skipped.

Move these into helper functions. Future vendor-specific checks will be
added to the helpers.

Signed-off-by: Yazen Ghannam <yazen.ghannam@amd.com>
---
 arch/x86/kernel/cpu/mce/core.c | 79 +++++++++++++++++-----------------
 1 file changed, 39 insertions(+), 40 deletions(-)

diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c
index 70c8df1a766a..704e651203b4 100644
--- a/arch/x86/kernel/cpu/mce/core.c
+++ b/arch/x86/kernel/cpu/mce/core.c
@@ -662,6 +662,44 @@ static noinstr void mce_read_aux(struct mce *m, int i)
 
 DEFINE_PER_CPU(unsigned, mce_poll_count);
 
+static bool ser_log_poll_error(struct mce *m)
+{
+	/* Log "not enabled" (speculative) errors */
+	if (!(m->status & MCI_STATUS_EN))
+		return true;
+
+	/*
+	 * Log UCNA (SDM: 15.6.3 "UCR Error Classification")
+	 * UC == 1 && PCC == 0 && S == 0
+	 */
+	if (!(m->status & MCI_STATUS_PCC) && !(m->status & MCI_STATUS_S))
+		return true;
+
+	return false;
+}
+
+static bool log_poll_error(enum mcp_flags flags, struct mce *m)
+{
+	/* If this entry is not valid, ignore it. */
+	if (!(m->status & MCI_STATUS_VAL))
+		return false;
+
+	/*
+	 * If we are logging everything (at CPU online) or this
+	 * is a corrected error, then we must log it.
+	 */
+	if ((flags & MCP_UC) || !(m->status & MCI_STATUS_UC))
+		return true;
+
+	if (mca_cfg.ser)
+		return ser_log_poll_error(m);
+
+	if (m->status & MCI_STATUS_UC)
+		return false;
+
+	return true;
+}
+
 /*
  * Poll for corrected events or events that happened before reset.
  * Those are just logged through /dev/mcelog.
@@ -709,48 +747,9 @@ void machine_check_poll(enum mcp_flags flags, mce_banks_t *b)
 		if (!mca_cfg.cmci_disabled)
 			mce_track_storm(&m);
 
-		/* If this entry is not valid, ignore it */
-		if (!(m.status & MCI_STATUS_VAL))
+		if (!log_poll_error(flags, &m))
 			continue;
 
-		/*
-		 * If we are logging everything (at CPU online) or this
-		 * is a corrected error, then we must log it.
-		 */
-		if ((flags & MCP_UC) || !(m.status & MCI_STATUS_UC))
-			goto log_it;
-
-		/*
-		 * Newer Intel systems that support software error
-		 * recovery need to make additional checks. Other
-		 * CPUs should skip over uncorrected errors, but log
-		 * everything else.
-		 */
-		if (!mca_cfg.ser) {
-			if (m.status & MCI_STATUS_UC)
-				continue;
-			goto log_it;
-		}
-
-		/* Log "not enabled" (speculative) errors */
-		if (!(m.status & MCI_STATUS_EN))
-			goto log_it;
-
-		/*
-		 * Log UCNA (SDM: 15.6.3 "UCR Error Classification")
-		 * UC == 1 && PCC == 0 && S == 0
-		 */
-		if (!(m.status & MCI_STATUS_PCC) && !(m.status & MCI_STATUS_S))
-			goto log_it;
-
-		/*
-		 * Skip anything else. Presumption is that our read of this
-		 * bank is racing with a machine check. Leave the log alone
-		 * for do_machine_check() to deal with it.
-		 */
-		continue;
-
-log_it:
 		if (flags & MCP_DONTLOG)
 			goto clear_it;
 
-- 
2.34.1