[PULL 1/4] file-posix: probe discard alignment on Linux block devices

[Kevin Wolf <kwolf@redhat.com>]

From: Stefan Hajnoczi <stefanha@redhat.com>

Populate the pdiscard_alignment block limit so the block layer is able
align discard requests correctly.

Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
Message-ID: <20250417150528.76470-2-stefanha@redhat.com>
Reviewed-by: Kevin Wolf <kwolf@redhat.com>
Signed-off-by: Kevin Wolf <kwolf@redhat.com>
---
 block/file-posix.c | 67 +++++++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 66 insertions(+), 1 deletion(-)

diff --git a/block/file-posix.c b/block/file-posix.c
index 56d1972d15..0d6e12f880 100644
--- a/block/file-posix.c
+++ b/block/file-posix.c
@@ -1276,10 +1276,10 @@ static int get_sysfs_zoned_model(struct stat *st, BlockZoneModel *zoned)
 }
 #endif /* defined(CONFIG_BLKZONED) */
 
+#ifdef CONFIG_LINUX
 /*
  * Get a sysfs attribute value as a long integer.
  */
-#ifdef CONFIG_LINUX
 static long get_sysfs_long_val(struct stat *st, const char *attribute)
 {
     g_autofree char *str = NULL;
@@ -1299,6 +1299,30 @@ static long get_sysfs_long_val(struct stat *st, const char *attribute)
     }
     return ret;
 }
+
+/*
+ * Get a sysfs attribute value as a uint32_t.
+ */
+static int get_sysfs_u32_val(struct stat *st, const char *attribute,
+                             uint32_t *u32)
+{
+    g_autofree char *str = NULL;
+    const char *end;
+    unsigned int val;
+    int ret;
+
+    ret = get_sysfs_str_val(st, attribute, &str);
+    if (ret < 0) {
+        return ret;
+    }
+
+    /* The file is ended with '\n', pass 'end' to accept that. */
+    ret = qemu_strtoui(str, &end, 10, &val);
+    if (ret == 0 && end && *end == '\0') {
+        *u32 = val;
+    }
+    return ret;
+}
 #endif
 
 static int hdev_get_max_segments(int fd, struct stat *st)
@@ -1318,6 +1342,23 @@ static int hdev_get_max_segments(int fd, struct stat *st)
 #endif
 }
 
+/*
+ * Fills in *dalign with the discard alignment and returns 0 on success,
+ * -errno otherwise.
+ */
+static int hdev_get_pdiscard_alignment(struct stat *st, uint32_t *dalign)
+{
+#ifdef CONFIG_LINUX
+    /*
+     * Note that Linux "discard_granularity" is QEMU "discard_alignment". Linux
+     * "discard_alignment" is something else.
+     */
+    return get_sysfs_u32_val(st, "discard_granularity", dalign);
+#else
+    return -ENOTSUP;
+#endif
+}
+
 #if defined(CONFIG_BLKZONED)
 /*
  * If the reset_all flag is true, then the wps of zone whose state is
@@ -1527,6 +1568,30 @@ static void raw_refresh_limits(BlockDriverState *bs, Error **errp)
         }
     }
 
+    if (S_ISBLK(st.st_mode)) {
+        uint32_t dalign = 0;
+        int ret;
+
+        ret = hdev_get_pdiscard_alignment(&st, &dalign);
+        if (ret == 0) {
+            uint32_t ralign = bs->bl.request_alignment;
+
+            /* Probably never happens, but handle it just in case */
+            if (dalign < ralign && (ralign % dalign == 0)) {
+                dalign = ralign;
+            }
+
+            /* The block layer requires a multiple of request_alignment */
+            if (dalign % ralign != 0) {
+                error_setg(errp, "Invalid pdiscard_alignment limit %u is not a "
+                        "multiple of request_alignment %u", dalign, ralign);
+                return;
+            }
+
+            bs->bl.pdiscard_alignment = dalign;
+        }
+    }
+
     raw_refresh_zoned_limits(bs, &st, errp);
 }
 
-- 
2.49.0