iommu/amd: Add debugfs support to dump IOMMU command buffer

IOMMU driver sends command to IOMMU hardware via command buffer. In cases
where IOMMU hardware fails to process commands in command buffer, dumping
it is a valuable input to debug the issue.

IOMMU hardware processes command buffer entry at offset equals to the head
pointer. Dumping just the entry at the head pointer may not always be
useful. The current head may not be pointing to the entry of the command
buffer which is causing the issue. IOMMU Hardware may have processed the
entry and updated the head pointer. So dumping the entire command buffer
gives a broad understanding of what hardware was/is doing. The command
buffer dump will have all entries from start to end of the command buffer.
Along with that, it will have a head and tail command buffer pointer
register dump to facilitate where the IOMMU driver and hardware are in
the command buffer for injecting and processing the entries respectively.

Command buffer is a per IOMMU data structure. So dumping on per IOMMU
basis.
eg.
-> To get command buffer dump for iommu<x> (say, iommu00)
   #cat /sys/kernel/debug/iommu/amd/iommu00/cmdbuf

Signed-off-by: Dheeraj Kumar Srivastava <dheerajkumar.srivastava@amd.com>
Reviewed-by: Vasant Hegde <vasant.hegde@amd.com>
Link: https://lore.kernel.org/r/20250702093804.849-5-dheerajkumar.srivastava@amd.com
Signed-off-by: Will Deacon <will@kernel.org>

drivers/iommu/amd/amd_iommu_types.h

@@ -897,6 +897,13 @@ struct dev_table_entry {
 	};
 };
 
+/*
+ * Structure defining one entry in the command buffer
+ */
+struct iommu_cmd {
+	u32 data[4];
+};
+
 /*
  * Structure to sture persistent DTE flags from IVHD
  */

drivers/iommu/amd/debugfs.c

@@ -107,6 +107,30 @@ static int iommu_capability_show(struct seq_file *m, void *unused)
 }
 DEFINE_SHOW_STORE_ATTRIBUTE(iommu_capability);
 
+static int iommu_cmdbuf_show(struct seq_file *m, void *unused)
+{
+	struct amd_iommu *iommu = m->private;
+	struct iommu_cmd *cmd;
+	unsigned long flag;
+	u32 head, tail;
+	int i;
+
+	raw_spin_lock_irqsave(&iommu->lock, flag);
+	head = readl(iommu->mmio_base + MMIO_CMD_HEAD_OFFSET);
+	tail = readl(iommu->mmio_base + MMIO_CMD_TAIL_OFFSET);
+	seq_printf(m, "CMD Buffer Head Offset:%d Tail Offset:%d\n",
+		   (head >> 4) & 0x7fff, (tail >> 4) & 0x7fff);
+	for (i = 0; i < CMD_BUFFER_ENTRIES; i++) {
+		cmd = (struct iommu_cmd *)(iommu->cmd_buf + i * sizeof(*cmd));
+		seq_printf(m, "%3d: %08x %08x %08x %08x\n", i, cmd->data[0],
+			   cmd->data[1], cmd->data[2], cmd->data[3]);
+	}
+	raw_spin_unlock_irqrestore(&iommu->lock, flag);
+
+	return 0;
+}
+DEFINE_SHOW_ATTRIBUTE(iommu_cmdbuf);
+
 void amd_iommu_debugfs_setup(void)
 {
 	struct amd_iommu *iommu;
@@ -125,5 +149,7 @@ void amd_iommu_debugfs_setup(void)
 				    &iommu_mmio_fops);
 		debugfs_create_file("capability", 0644, iommu->debugfs, iommu,
 				    &iommu_capability_fops);
+		debugfs_create_file("cmdbuf", 0444, iommu->debugfs, iommu,
+				    &iommu_cmdbuf_fops);
 	}
 }

drivers/iommu/amd/iommu.c

@@ -62,13 +62,6 @@ static const struct iommu_dirty_ops amd_dirty_ops;
 
 int amd_iommu_max_glx_val = -1;
 
-/*
- * general struct to manage commands send to an IOMMU
- */
-struct iommu_cmd {
-	u32 data[4];
-};
-
 /*
  * AMD IOMMU allows up to 2^16 different protection domains. This is a bitmap
  * to know which ones are already in use.