[v2,3/3] RAS/AMD/FMPM: Add debugfs interface to print record entries

Message ID 20240301143748.854090-4-yazen.ghannam@amd.com
State New
Headers
Series FMPM Debug Updates |

Commit Message

Yazen Ghannam March 1, 2024, 2:37 p.m. UTC
  It is helpful to see the saved record entries during run time in
human-readable format. This is useful for testing during module
development. And it can be used by system admins to quickly and easily
see the state of the system.

Provide a sequential file in debugfs to print fields of interest from
the FRU records and their entries.

Don't fail to load the module if the debugfs interface is not available.
This is a convenience feature which does not affect other module
functionality.

The new interface reads the record entries and should hold the mutex.
Expand the mutex code comment to clarify when it should be held.

Signed-off-by: Yazen Ghannam <yazen.ghannam@amd.com>
---
Link:
https://lore.kernel.org/r/20240226152941.2615007-4-yazen.ghannam@amd.com

v1->v2:
* Update based on patch 1 and 2 changes.

 drivers/ras/amd/fmpm.c | 131 +++++++++++++++++++++++++++++++++++++++++
 1 file changed, 131 insertions(+)
  

Patch

diff --git a/drivers/ras/amd/fmpm.c b/drivers/ras/amd/fmpm.c
index a7bb36eb60cb..d670aa11aef4 100644
--- a/drivers/ras/amd/fmpm.c
+++ b/drivers/ras/amd/fmpm.c
@@ -54,6 +54,8 @@ 
 #include <asm/cpu_device_id.h>
 #include <asm/mce.h>
 
+#include "../debugfs.h"
+
 #define INVALID_CPU			UINT_MAX
 
 /* Validation Bits */
@@ -116,6 +118,9 @@  static u64 *spa_entries;
 
 #define INVALID_SPA	~0ULL
 
+static struct dentry *fmpm_dfs_dir;
+static struct dentry *fmpm_dfs_entries;
+
 #define CPER_CREATOR_FMP						\
 	GUID_INIT(0xcd5c2993, 0xf4b2, 0x41b2, 0xb5, 0xd4, 0xf9, 0xc3,	\
 		  0xa0, 0x33, 0x08, 0x75)
@@ -152,6 +157,11 @@  static unsigned int spa_nr_entries;
  * Protect the local records cache in fru_records and prevent concurrent
  * writes to storage. This is only needed after init once notifier block
  * registration is done.
+ *
+ * The majority of a record is fixed at module init and will not change
+ * during run time. The entries within a record will be updated as new
+ * errors are reported. The mutex should be held whenever the entries are
+ * accessed during run time.
  */
 static DEFINE_MUTEX(fmpm_update_mutex);
 
@@ -813,6 +823,124 @@  static int allocate_records(void)
 	return ret;
 }
 
+static void *fmpm_start(struct seq_file *f, loff_t *pos)
+{
+	if (*pos >= (spa_nr_entries + 1))
+		return NULL;
+	return pos;
+}
+
+static void *fmpm_next(struct seq_file *f, void *data, loff_t *pos)
+{
+	if (++(*pos) >= (spa_nr_entries + 1))
+		return NULL;
+	return pos;
+}
+
+static void fmpm_stop(struct seq_file *f, void *data)
+{
+}
+
+#define SHORT_WIDTH	8
+#define U64_WIDTH	18
+#define TIMESTAMP_WIDTH	19
+#define LONG_WIDTH	24
+#define U64_PAD		(LONG_WIDTH - U64_WIDTH)
+#define TS_PAD		(LONG_WIDTH - TIMESTAMP_WIDTH)
+static int fmpm_show(struct seq_file *f, void *data)
+{
+	unsigned int fru_idx, entry, spa_entry, line;
+	struct cper_fru_poison_desc *fpd;
+	struct fru_rec *rec;
+
+	line = *(loff_t *)data;
+	if (line == 0) {
+		seq_printf(f, "%-*s", SHORT_WIDTH, "fru_idx");
+		seq_printf(f, "%-*s", LONG_WIDTH,  "fru_id");
+		seq_printf(f, "%-*s", SHORT_WIDTH, "entry");
+		seq_printf(f, "%-*s", LONG_WIDTH,  "timestamp");
+		seq_printf(f, "%-*s", LONG_WIDTH,  "hw_id");
+		seq_printf(f, "%-*s", LONG_WIDTH,  "addr");
+		seq_printf(f, "%-*s", LONG_WIDTH,  "spa");
+		goto out_newline;
+	}
+
+	spa_entry = line - 1;
+	fru_idx	  = spa_entry / max_nr_entries;
+	entry	  = spa_entry % max_nr_entries;
+
+	rec = fru_records[fru_idx];
+	if (!rec)
+		goto out;
+
+	seq_printf(f, "%-*u",		SHORT_WIDTH, fru_idx);
+	seq_printf(f, "0x%016llx%-*s",	rec->fmp.fru_id, U64_PAD, "");
+	seq_printf(f, "%-*u",		SHORT_WIDTH, entry);
+
+	mutex_lock(&fmpm_update_mutex);
+
+	if (entry >= rec->fmp.nr_entries) {
+		seq_printf(f, "%-*s", LONG_WIDTH, "*");
+		seq_printf(f, "%-*s", LONG_WIDTH, "*");
+		seq_printf(f, "%-*s", LONG_WIDTH, "*");
+		seq_printf(f, "%-*s", LONG_WIDTH, "*");
+		goto out_unlock;
+	}
+
+	fpd = &rec->entries[entry];
+
+	seq_printf(f, "%ptT%-*s",	&fpd->timestamp, TS_PAD,  "");
+	seq_printf(f, "0x%016llx%-*s",	fpd->hw_id,	 U64_PAD, "");
+	seq_printf(f, "0x%016llx%-*s",	fpd->addr,	 U64_PAD, "");
+
+	if (spa_entries[spa_entry] == INVALID_SPA)
+		seq_printf(f, "%-*s", LONG_WIDTH, "*");
+	else
+		seq_printf(f, "0x%016llx%-*s", spa_entries[spa_entry], U64_PAD, "");
+
+out_unlock:
+	mutex_unlock(&fmpm_update_mutex);
+out_newline:
+	seq_putc(f, '\n');
+out:
+	return 0;
+}
+
+static const struct seq_operations fmpm_seq_ops = {
+	.start	= fmpm_start,
+	.next	= fmpm_next,
+	.stop	= fmpm_stop,
+	.show	= fmpm_show,
+};
+
+static int fmpm_open(struct inode *inode, struct file *file)
+{
+	return seq_open(file, &fmpm_seq_ops);
+}
+
+static const struct file_operations fmpm_fops = {
+	.open		= fmpm_open,
+	.release	= seq_release,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+};
+
+static void setup_debugfs(void)
+{
+	struct dentry *dfs = ras_get_debugfs_root();
+
+	if (!dfs)
+		return;
+
+	fmpm_dfs_dir = debugfs_create_dir("fmpm", dfs);
+	if (!fmpm_dfs_dir)
+		return;
+
+	fmpm_dfs_entries = debugfs_create_file("entries", 0400, fmpm_dfs_dir, NULL, &fmpm_fops);
+	if (!fmpm_dfs_entries)
+		debugfs_remove(fmpm_dfs_dir);
+}
+
 static const struct x86_cpu_id fmpm_cpuids[] = {
 	X86_MATCH_VENDOR_FAM(AMD, 0x19, NULL),
 	{ }
@@ -854,6 +982,8 @@  static int __init fru_mem_poison_init(void)
 	if (ret)
 		goto out_free;
 
+	setup_debugfs();
+
 	retire_mem_records();
 
 	mce_register_decode_chain(&fru_mem_poison_nb);
@@ -870,6 +1000,7 @@  static int __init fru_mem_poison_init(void)
 static void __exit fru_mem_poison_exit(void)
 {
 	mce_unregister_decode_chain(&fru_mem_poison_nb);
+	debugfs_remove(fmpm_dfs_dir);
 	free_records();
 }