linux-kernel - [PATCH] iommu/amd: Enhance "Completion-wait Time-out" error message

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>] [day] [month] [year] [list]

Message-ID: <20251016150809.5465-1-dheerajkumar.srivastava@amd.com>
Date: Thu, 16 Oct 2025 20:38:09 +0530
From: Dheeraj Kumar Srivastava <dheerajkumar.srivastava@....com>
To: <joro@...tes.org>, <will@...nel.org>, <robin.murphy@....com>,
	<iommu@...ts.linux.dev>, <linux-kernel@...r.kernel.org>
CC: <suravee.suthikulpanit@....com>, <Vasant.Hegde@....com>,
	<Santosh.Shukla@....com>, Dheeraj Kumar Srivastava
	<dheerajkumar.srivastava@....com>
Subject: [PATCH] iommu/amd: Enhance "Completion-wait Time-out" error message

Current IOMMU driver prints "Completion-wait Time-out" error message with
insufficient information to further debug the issue.

Enhancing the error message as following:
1. Log IOMMU PCI device ID in the error message.
2. Also dump the command and offset of the command prior to the
   COMPLETION_WAIT command to figure out for what IOMMU is waiting.
3. With "amd_iommu_dump=1" kernel command line option, dump entire
   command buffer entries including Head and Tail offset.

Signed-off-by: Dheeraj Kumar Srivastava <dheerajkumar.srivastava@....com>
---
 drivers/iommu/amd/amd_iommu_types.h |  4 ++++
 drivers/iommu/amd/iommu.c           | 31 +++++++++++++++++++++++++++--
 2 files changed, 33 insertions(+), 2 deletions(-)

diff --git a/drivers/iommu/amd/amd_iommu_types.h b/drivers/iommu/amd/amd_iommu_types.h
index 95f63c5f6159..7576814f944d 100644
--- a/drivers/iommu/amd/amd_iommu_types.h
+++ b/drivers/iommu/amd/amd_iommu_types.h
@@ -247,6 +247,10 @@
 #define CMD_BUFFER_ENTRIES 512
 #define MMIO_CMD_SIZE_SHIFT 56
 #define MMIO_CMD_SIZE_512 (0x9ULL << MMIO_CMD_SIZE_SHIFT)
+#define MMIO_CMD_HEAD_MASK	GENMASK_ULL(18, 4)
+#define MMIO_CMD_BUFFER_HEAD(x) FIELD_GET(MMIO_CMD_HEAD_MASK, (x))
+#define MMIO_CMD_TAIL_MASK	GENMASK_ULL(18, 4)
+#define MMIO_CMD_BUFFER_TAIL(x) FIELD_GET(MMIO_CMD_TAIL_MASK, (x))
 
 /* constants for event buffer handling */
 #define EVT_BUFFER_SIZE		8192 /* 512 entries */
diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c
index eb348c63a8d0..e1b4b0ea0990 100644
--- a/drivers/iommu/amd/iommu.c
+++ b/drivers/iommu/amd/iommu.c
@@ -1158,7 +1158,8 @@ irqreturn_t amd_iommu_int_handler(int irq, void *data)
 
 static int wait_on_sem(struct amd_iommu *iommu, u64 data)
 {
-	int i = 0;
+	struct iommu_cmd *cmd;
+	int i = 0, j;
 
 	while (*iommu->cmd_sem != data && i < LOOP_TIMEOUT) {
 		udelay(1);
@@ -1166,7 +1167,33 @@ static int wait_on_sem(struct amd_iommu *iommu, u64 data)
 	}
 
 	if (i == LOOP_TIMEOUT) {
-		pr_alert("Completion-Wait loop timed out\n");
+		int head, tail;
+
+		head = readl(iommu->mmio_base + MMIO_CMD_HEAD_OFFSET);
+		tail = readl(iommu->mmio_base + MMIO_CMD_TAIL_OFFSET);
+
+		pr_alert("IOMMU %04x:%02x:%02x.%01x: Completion-Wait loop timed out\n",
+			 iommu->pci_seg->id, PCI_BUS_NUM(iommu->devid),
+			 PCI_SLOT(iommu->devid), PCI_FUNC(iommu->devid));
+		if (!amd_iommu_dump) {
+			/*
+			 * On command buffer completion timeout, step back by 2 commands
+			 * to locate the actual command that is causing the issue.
+			 */
+			tail = (MMIO_CMD_BUFFER_TAIL(tail) - 2) & (CMD_BUFFER_ENTRIES - 1);
+			cmd = (struct iommu_cmd *)(iommu->cmd_buf + tail * sizeof(*cmd));
+			dump_command(iommu_virt_to_phys(cmd));
+		} else {
+			/* Dump entire command buffer along with head and tail indices */
+			pr_alert("CMD Buffer head=%d tail=%d\n", (int)(MMIO_CMD_BUFFER_HEAD(head)),
+				 (int)(MMIO_CMD_BUFFER_TAIL(tail)));
+			for (j = 0; j < CMD_BUFFER_ENTRIES; j++) {
+				cmd = (struct iommu_cmd *)(iommu->cmd_buf + j * sizeof(*cmd));
+				pr_err("%3d: %08x %08x %08x %08x\n", j, cmd->data[0], cmd->data[1],
+				       cmd->data[2], cmd->data[3]);
+			}
+		}
+
 		return -EIO;
 	}
 
-- 
2.25.1