grub2/0001-ieee1275-ofdisk-retry-on-open-and-read-failure.patch

From b99c45820f228ff5b881700eda95a017abf2e198 Mon Sep 17 00:00:00 2001
From: Mukesh Kumar Chaurasiya <mchauras@linux.vnet.ibm.com>
Date: Wed, 1 Mar 2023 15:08:05 +0530
Subject: [PATCH] ieee1275/ofdisk: retry on open and read failure

Sometimes, when booting from a very busy SAN, the access to the
disk can fail and then grub will eventually drop to grub prompt.
This scenario is more frequent when deploying many machines at
the same time using the same SAN.
This patch aims to force the ofdisk module to retry the open or
read function after it fails. We use MAX_RETRIES to specify the
amount of times it will try to access the disk before it
definitely fails.

Signed-off-by: Mukesh Kumar Chaurasiya <mchauras@linux.vnet.ibm.com>
---
 grub-core/disk/ieee1275/ofdisk.c | 65 +++++++++++++++++++++++++++++++-
 1 file changed, 63 insertions(+), 2 deletions(-)

--- a/grub-core/disk/ieee1275/ofdisk.c
+++ b/grub-core/disk/ieee1275/ofdisk.c
@@ -24,6 +24,9 @@
 #include <grub/ieee1275/ofdisk.h>
 #include <grub/i18n.h>
 #include <grub/time.h>
+#include <grub/env.h>
+
+#define RETRY_DEFAULT_TIMEOUT 15000
 
 static char *last_devpath;
 static grub_ieee1275_ihandle_t last_ihandle;
@@ -783,7 +786,7 @@
 }
 
 static grub_err_t
-grub_ofdisk_open (const char *name, grub_disk_t disk)
+grub_ofdisk_open_real (const char *name, grub_disk_t disk)
 {
   grub_ieee1275_phandle_t dev;
   char *devpath;
@@ -879,6 +882,41 @@
   return 0;
 }
 
+static grub_uint64_t
+grub_ofdisk_disk_timeout(void)
+{
+   if(grub_env_get("ofdisk_retry_timeout") != NULL)
+     {
+	grub_uint64_t retry = grub_strtoul(grub_env_get("ofdisk_retry_timeout"), 0, 10);
+	if(retry)
+	  return retry;
+     }
+
+   return RETRY_DEFAULT_TIMEOUT;
+}
+
+static grub_err_t
+grub_ofdisk_open (const char *name, grub_disk_t disk)
+{
+  grub_err_t err;
+  grub_uint64_t timeout = grub_get_time_ms () + grub_ofdisk_disk_timeout();
+
+ retry:
+  err = grub_ofdisk_open_real (name, disk);
+
+  if (err == GRUB_ERR_UNKNOWN_DEVICE)
+    {
+      if (grub_get_time_ms () < timeout)
+        {
+          grub_dprintf ("ofdisk","Failed to open disk %s. Retrying...\n", name);
+          grub_errno = GRUB_ERR_NONE;
+          goto retry;
+	}
+    }
+
+  return err;
+}
+
 static void
 grub_ofdisk_close (grub_disk_t disk)
 {
@@ -915,7 +953,7 @@
 }
 
 static grub_err_t
-grub_ofdisk_read (grub_disk_t disk, grub_disk_addr_t sector,
+grub_ofdisk_read_real (grub_disk_t disk, grub_disk_addr_t sector,
 		  grub_size_t size, char *buf)
 {
   grub_err_t err;
@@ -935,6 +973,29 @@
 }
 
 static grub_err_t
+grub_ofdisk_read (grub_disk_t disk, grub_disk_addr_t sector,
+		  grub_size_t size, char *buf)
+{
+  grub_err_t err;
+  grub_uint64_t timeout = grub_get_time_ms () + grub_ofdisk_disk_timeout();
+
+ retry:
+  err = grub_ofdisk_read_real (disk, sector, size, buf);
+
+  if (err == GRUB_ERR_READ_ERROR)
+    {
+      if (grub_get_time_ms () < timeout)
+        {
+          grub_dprintf ("ofdisk","Failed to read disk %s. Retrying...\n", (char*)disk->data);
+          grub_errno = GRUB_ERR_NONE;
+          goto retry;
+	}
+    }
+
+  return err;
+}
+
+static grub_err_t
 grub_ofdisk_write (grub_disk_t disk, grub_disk_addr_t sector,
 		   grub_size_t size, const char *buf)
 {