Re: [PULL v2 02/16] block/file-posix: introduce helper functions for sysfs attributes

[Matthew Rosato]

On 5/15/23 12:04 PM, Stefan Hajnoczi wrote:
> From: Sam Li <faithilikerun@gmail.com>
> 
> Use get_sysfs_str_val() to get the string value of device
> zoned model. Then get_sysfs_zoned_model() can convert it to
> BlockZoneModel type of QEMU.
> 
> Use get_sysfs_long_val() to get the long value of zoned device
> information.

Hi Stefan, Sam,

I am having an issue on s390x using virtio-blk-{pci,ccw} backed by an NVMe 
partition, and I've bisected the root cause to this commit. 

I noticed that tests which use the partition e.g. /dev/nvme0n1p1 as a backing 
device would fail, but those that use the namespace e.g. /dev/nvme0n1 would 
still succeed.  The root issue appears to be that the block device associated 
with the partition does not have a "max_segments" attribute, and prior to this 
patch hdev_get_max_segment() would return -ENOENT in this case.  After this 
patch, however, QEMU is instead crashing.  It looks like g_file_get_contents is 
returning 0 with a len == 0 if the specified sysfs path does not exist.  The 
following diff on top seems to resolve the issue for me:


diff --git a/block/file-posix.c b/block/file-posix.c
index 0ab158efba2..eeb0247c74e 100644
--- a/block/file-posix.c
+++ b/block/file-posix.c
@@ -1243,7 +1243,7 @@ static int get_sysfs_str_val(struct stat *st, const char 
*attribute,
                                 major(st->st_rdev), minor(st->st_rdev),
                                 attribute);
     ret = g_file_get_contents(sysfspath, val, &len, NULL);
-    if (ret == -1) {
+    if (ret == -1 || len == 0) {
         return -ENOENT;
     }
 



> 
> Signed-off-by: Sam Li <faithilikerun@gmail.com>
> Reviewed-by: Hannes Reinecke <hare@suse.de>
> Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
> Reviewed-by: Damien Le Moal <damien.lemoal@opensource.wdc.com>
> Reviewed-by: Dmitry Fomichev <dmitry.fomichev@wdc.com>
> Acked-by: Kevin Wolf <kwolf@redhat.com>
> Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
> Message-id: 20230508045533.175575-3-faithilikerun@gmail.com
> Message-id: 20230324090605.28361-3-faithilikerun@gmail.com
> [Adjust commit message prefix as suggested by Philippe Mathieu-Daudé
> <philmd@linaro.org>.
> --Stefan]
> Signed-off-by: Stefan Hajnoczi <stefanha@redhat.com>
> ---
>  include/block/block_int-common.h |   3 +
>  block/file-posix.c               | 135 ++++++++++++++++++++++---------
>  2 files changed, 100 insertions(+), 38 deletions(-)
> 
> diff --git a/include/block/block_int-common.h 
> b/include/block/block_int-common.h
> index 4909876756..c7ca5a83e9 100644
> --- a/include/block/block_int-common.h
> +++ b/include/block/block_int-common.h
> @@ -862,6 +862,9 @@ typedef struct BlockLimits {
>       * an explicit monitor command to load the disk inside the guest).
>       */
>      bool has_variable_length;
> +
> +    /* device zone model */
> +    BlockZoneModel zoned;
>  } BlockLimits;
>  
>  typedef struct BdrvOpBlocker BdrvOpBlocker;
> diff --git a/block/file-posix.c b/block/file-posix.c
> index c7b723368e..97c597a2a0 100644
> --- a/block/file-posix.c
> +++ b/block/file-posix.c
> @@ -1202,15 +1202,89 @@ static int hdev_get_max_hw_transfer(int fd, struct 
> stat *st)
>  #endif
>  }
>  
> -static int hdev_get_max_segments(int fd, struct stat *st)
> +/*
> + * Get a sysfs attribute value as character string.
> + */
> +#ifdef CONFIG_LINUX
> +static int get_sysfs_str_val(struct stat *st, const char *attribute,
> +                             char **val) {
> +    g_autofree char *sysfspath = NULL;
> +    int ret;
> +    size_t len;
> +
> +    if (!S_ISBLK(st->st_mode)) {
> +        return -ENOTSUP;
> +    }
> +
> +    sysfspath = g_strdup_printf("/sys/dev/block/%u:%u/queue/%s",
> +                                major(st->st_rdev), minor(st->st_rdev),
> +                                attribute);
> +    ret = g_file_get_contents(sysfspath, val, &len, NULL);
> +    if (ret == -1) {
> +        return -ENOENT;
> +    }
> +
> +    /* The file is ended with '\n' */
> +    char *p;
> +    p = *val;
> +    if (*(p + len - 1) == '\n') {
> +        *(p + len - 1) = '\0';
> +    }
> +    return ret;
> +}
> +#endif
> +
> +static int get_sysfs_zoned_model(struct stat *st, BlockZoneModel *zoned)
>  {
> +    g_autofree char *val = NULL;
> +    int ret;
> +
> +    ret = get_sysfs_str_val(st, "zoned", &val);
> +    if (ret < 0) {
> +        return ret;
> +    }
> +
> +    if (strcmp(val, "host-managed") == 0) {
> +        *zoned = BLK_Z_HM;
> +    } else if (strcmp(val, "host-aware") == 0) {
> +        *zoned = BLK_Z_HA;
> +    } else if (strcmp(val, "none") == 0) {
> +        *zoned = BLK_Z_NONE;
> +    } else {
> +        return -ENOTSUP;
> +    }
> +    return 0;
> +}
> +
> +/*
> + * Get a sysfs attribute value as a long integer.
> + */
>  #ifdef CONFIG_LINUX
> -    char buf[32];
> +static long get_sysfs_long_val(struct stat *st, const char *attribute)
> +{
> +    g_autofree char *str = NULL;
>      const char *end;
> -    char *sysfspath = NULL;
> +    long 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_strtol(str, &end, 10, &val);
> +    if (ret == 0 && end && *end == '\0') {
> +        ret = val;
> +    }
> +    return ret;
> +}
> +#endif
> +
> +static int hdev_get_max_segments(int fd, struct stat *st)
> +{
> +#ifdef CONFIG_LINUX
>      int ret;
> -    int sysfd = -1;
> -    long max_segments;
>  
>      if (S_ISCHR(st->st_mode)) {
>          if (ioctl(fd, SG_GET_SG_TABLESIZE, &ret) == 0) {
> @@ -1218,44 +1292,27 @@ static int hdev_get_max_segments(int fd, struct stat 
> *st)
>          }
>          return -ENOTSUP;
>      }
> -
> -    if (!S_ISBLK(st->st_mode)) {
> -        return -ENOTSUP;
> -    }
> -
> -    sysfspath = g_strdup_printf("/sys/dev/block/%u:%u/queue/max_segments",
> -                                major(st->st_rdev), minor(st->st_rdev));
> -    sysfd = open(sysfspath, O_RDONLY);
> -    if (sysfd == -1) {
> -        ret = -errno;
> -        goto out;
> -    }
> -    ret = RETRY_ON_EINTR(read(sysfd, buf, sizeof(buf) - 1));
> -    if (ret < 0) {
> -        ret = -errno;
> -        goto out;
> -    } else if (ret == 0) {
> -        ret = -EIO;
> -        goto out;
> -    }
> -    buf[ret] = 0;
> -    /* The file is ended with '\n', pass 'end' to accept that. */
> -    ret = qemu_strtol(buf, &end, 10, &max_segments);
> -    if (ret == 0 && end && *end == '\n') {
> -        ret = max_segments;
> -    }
> -
> -out:
> -    if (sysfd != -1) {
> -        close(sysfd);
> -    }
> -    g_free(sysfspath);
> -    return ret;
> +    return get_sysfs_long_val(st, "max_segments");
>  #else
>      return -ENOTSUP;
>  #endif
>  }
>  
> +static void raw_refresh_zoned_limits(BlockDriverState *bs, struct stat *st,
> +                                     Error **errp)
> +{
> +    BlockZoneModel zoned;
> +    int ret;
> +
> +    bs->bl.zoned = BLK_Z_NONE;
> +
> +    ret = get_sysfs_zoned_model(st, &zoned);
> +    if (ret < 0 || zoned == BLK_Z_NONE) {
> +        return;
> +    }
> +    bs->bl.zoned = zoned;
> +}
> +
>  static void raw_refresh_limits(BlockDriverState *bs, Error **errp)
>  {
>      BDRVRawState *s = bs->opaque;
> @@ -1297,6 +1354,8 @@ static void raw_refresh_limits(BlockDriverState *bs, 
> Error **errp)
>              bs->bl.max_hw_iov = ret;
>          }
>      }
> +
> +    raw_refresh_zoned_limits(bs, &st, errp);
>  }
>  
>  static int check_for_dasd(int fd)