mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Dheeraj Kumar Srivastava <dheerajkumar.srivastava@amd.com>
To: <joro@8bytes.org>, <will@kernel.org>, <robin.murphy@arm.com>,
	<iommu@lists.linux.dev>, <linux-kernel@vger.kernel.org>
Cc: <suravee.suthikulpanit@amd.com>, <Vasant.Hegde@amd.com>,
	<Santosh.Shukla@amd.com>,
	Dheeraj Kumar Srivastava <dheerajkumar.srivastava@amd.com>,
	Ankit Soni <Ankit.Soni@amd.com>
Subject: [PATCH v5] iommu/amd: Enhance "Completion-wait Time-out" error message
Date: Thu, 13 Nov 2025 02:43:50 +0530	[thread overview]
Message-ID: <20251112211350.894-1-dheerajkumar.srivastava@amd.com> (raw)

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. With "amd_iommu_dump=1" kernel command line option, dump entire
   command buffer entries including Head and Tail offset.

Dump the entire command buffer only on the first 'Completion-wait Time-out'
to avoid dmesg spam.

Signed-off-by: Dheeraj Kumar Srivastava <dheerajkumar.srivastava@amd.com>
Reviewed-by: Ankit Soni <Ankit.Soni@amd.com>
---
Changes since v4:
-> Changed head and tail variables from int to u32 in dump_command_buffer()
   to match readl() return type and updated pr_err() format specifiers from
   %d to %u accordingly for head and tail. (Ankit)

Changes since v3:
-> Dump the entire command buffer only on the first 'Completion-wait Time-out'
   when amd_iommu_dump=1, instead of dumping it on every occurrence.

 drivers/iommu/amd/amd_iommu_types.h |  4 ++++
 drivers/iommu/amd/iommu.c           | 28 +++++++++++++++++++++++++++-
 2 files changed, 31 insertions(+), 1 deletion(-)

diff --git a/drivers/iommu/amd/amd_iommu_types.h b/drivers/iommu/amd/amd_iommu_types.h
index 95f63c5f6159..c20798fc644d 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)	/* Command buffer head ptr field [18:4] */
+#define MMIO_CMD_BUFFER_HEAD(x) FIELD_GET(MMIO_CMD_HEAD_MASK, (x))
+#define MMIO_CMD_TAIL_MASK	GENMASK_ULL(18, 4)	/* Command buffer tail ptr field [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..c68b0fdc5433 100644
--- a/drivers/iommu/amd/iommu.c
+++ b/drivers/iommu/amd/iommu.c
@@ -1156,6 +1156,25 @@ irqreturn_t amd_iommu_int_handler(int irq, void *data)
  *
  ****************************************************************************/
 
+static void dump_command_buffer(struct amd_iommu *iommu)
+{
+	struct iommu_cmd *cmd;
+	u32 head, tail;
+	int i;
+
+	head = readl(iommu->mmio_base + MMIO_CMD_HEAD_OFFSET);
+	tail = readl(iommu->mmio_base + MMIO_CMD_TAIL_OFFSET);
+
+	pr_err("CMD Buffer head=%llu tail=%llu\n", MMIO_CMD_BUFFER_HEAD(head),
+	       MMIO_CMD_BUFFER_TAIL(tail));
+
+	for (i = 0; i < CMD_BUFFER_ENTRIES; i++) {
+		cmd = (struct iommu_cmd *)(iommu->cmd_buf + i * sizeof(*cmd));
+		pr_err("%3d: %08x %08x %08x %08x\n", i, cmd->data[0], cmd->data[1], cmd->data[2],
+		       cmd->data[3]);
+	}
+}
+
 static int wait_on_sem(struct amd_iommu *iommu, u64 data)
 {
 	int i = 0;
@@ -1166,7 +1185,14 @@ static int wait_on_sem(struct amd_iommu *iommu, u64 data)
 	}
 
 	if (i == LOOP_TIMEOUT) {
-		pr_alert("Completion-Wait loop timed out\n");
+
+		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)
+			DO_ONCE_LITE(dump_command_buffer, iommu);
+
 		return -EIO;
 	}
 
-- 
2.25.1


             reply	other threads:[~2025-11-12 21:14 UTC|newest]

Thread overview: 3+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-11-12 21:13 Dheeraj Kumar Srivastava [this message]
2025-11-13 11:34 ` Vasant Hegde
2025-11-13 15:13 ` Jörg Rödel

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20251112211350.894-1-dheerajkumar.srivastava@amd.com \
    --to=dheerajkumar.srivastava@amd.com \
    --cc=Ankit.Soni@amd.com \
    --cc=Santosh.Shukla@amd.com \
    --cc=Vasant.Hegde@amd.com \
    --cc=iommu@lists.linux.dev \
    --cc=joro@8bytes.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=robin.murphy@arm.com \
    --cc=suravee.suthikulpanit@amd.com \
    --cc=will@kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox

all inboxes | Powered by JetHome®