Re: [PATCH v15 08/11] fw_cfg: handle fw_cfg_read_blob() error

From: Michael S. Tsirkin
Date: Wed Feb 28 2018 - 10:33:35 EST


On Wed, Feb 28, 2018 at 12:49:35PM +0100, Marc-André Lureau wrote:
> Hi
>
> On Tue, Feb 27, 2018 at 1:20 AM, Michael S. Tsirkin <mst@xxxxxxxxxx> wrote:
> > On Thu, Feb 15, 2018 at 10:33:09PM +0100, Marc-André Lureau wrote:
> >> fw_cfg_read_blob() may fail, but does not return error. This may lead
> >> to undefined behaviours, such as a memcmp(sig, "QEMU") on uninitilized
> >> memory.
> >
> > I don't think that's true - there's a memset there that
> > will initialize the memory. probe is likely the only
> > case where it returns a slightly incorrect data.
>
> Right, I'll update the commit message.
>
> >> Return an error if ACPI locking failed. Also, the following
> >> DMA read/write extension will add more error paths that should be
> >> handled appropriately.
> >>
> >> Signed-off-by: Marc-André Lureau <marcandre.lureau@xxxxxxxxxx>
> >> ---
> >> drivers/firmware/qemu_fw_cfg.c | 32 ++++++++++++++++++++++----------
> >> 1 file changed, 22 insertions(+), 10 deletions(-)
> >>
> >> diff --git a/drivers/firmware/qemu_fw_cfg.c b/drivers/firmware/qemu_fw_cfg.c
> >> index f6f90bef604c..5e6e5ac71dab 100644
> >> --- a/drivers/firmware/qemu_fw_cfg.c
> >> +++ b/drivers/firmware/qemu_fw_cfg.c
> >> @@ -59,8 +59,8 @@ static void fw_cfg_sel_endianness(u16 key)
> >> }
> >>
> >> /* read chunk of given fw_cfg blob (caller responsible for sanity-check) */
> >> -static void fw_cfg_read_blob(u16 key,
> >> - void *buf, loff_t pos, size_t count)
> >> +static ssize_t fw_cfg_read_blob(u16 key,
> >> + void *buf, loff_t pos, size_t count)
> >> {
> >> u32 glk = -1U;
> >> acpi_status status;
> >> @@ -73,7 +73,7 @@ static void fw_cfg_read_blob(u16 key,
> >> /* Should never get here */
> >> WARN(1, "fw_cfg_read_blob: Failed to lock ACPI!\n");
> >> memset(buf, 0, count);
> >> - return;
> >> + return -EINVAL;
> >> }
> >>
> >> mutex_lock(&fw_cfg_dev_lock);
> >
> > Wouldn't something like -EBUSY be more appropriate?
>
> In theory, it would be a general failure right? I don't think we want
> the caller to retry. I think in EINVAL fits better, but I don't think
> it matters much this or EBUSY.
>
> >> @@ -84,6 +84,7 @@ static void fw_cfg_read_blob(u16 key,
> >> mutex_unlock(&fw_cfg_dev_lock);
> >>
> >> acpi_release_global_lock(glk);
> >> + return count;
> >> }
> >>
> >> /* clean up fw_cfg device i/o */
> >> @@ -165,8 +166,9 @@ static int fw_cfg_do_platform_probe(struct platform_device *pdev)
> >> }
> >>
> >> /* verify fw_cfg device signature */
> >> - fw_cfg_read_blob(FW_CFG_SIGNATURE, sig, 0, FW_CFG_SIG_SIZE);
> >> - if (memcmp(sig, "QEMU", FW_CFG_SIG_SIZE) != 0) {
> >> + if (fw_cfg_read_blob(FW_CFG_SIGNATURE, sig,
> >> + 0, FW_CFG_SIG_SIZE) < 0 ||
> >> + memcmp(sig, "QEMU", FW_CFG_SIG_SIZE) != 0) {
> >> fw_cfg_io_cleanup();
> >> return -ENODEV;
> >> }
> >> @@ -326,8 +328,7 @@ static ssize_t fw_cfg_sysfs_read_raw(struct file *filp, struct kobject *kobj,
> >> if (count > entry->size - pos)
> >> count = entry->size - pos;
> >>
> >> - fw_cfg_read_blob(entry->select, buf, pos, count);
> >> - return count;
> >> + return fw_cfg_read_blob(entry->select, buf, pos, count);
> >> }
> >>
> >> static struct bin_attribute fw_cfg_sysfs_attr_raw = {
> >> @@ -483,7 +484,11 @@ static int fw_cfg_register_dir_entries(void)
> >> struct fw_cfg_file *dir;
> >> size_t dir_size;
> >>
> >> - fw_cfg_read_blob(FW_CFG_FILE_DIR, &files_count, 0, sizeof(files_count));
> >> + ret = fw_cfg_read_blob(FW_CFG_FILE_DIR, &files_count,
> >> + 0, sizeof(files_count));
> >> + if (ret < 0)
> >> + return ret;
> >> +
> >> count = be32_to_cpu(files_count);
> >> dir_size = count * sizeof(struct fw_cfg_file);
> >>
> >> @@ -491,7 +496,10 @@ static int fw_cfg_register_dir_entries(void)
> >> if (!dir)
> >> return -ENOMEM;
> >>
> >> - fw_cfg_read_blob(FW_CFG_FILE_DIR, dir, sizeof(files_count), dir_size);
> >> + ret = fw_cfg_read_blob(FW_CFG_FILE_DIR, dir,
> >> + sizeof(files_count), dir_size);
> >> + if (ret < 0)
> >> + goto end;
> >>
> >> for (i = 0; i < count; i++) {
> >> ret = fw_cfg_register_file(&dir[i]);
> >> @@ -499,6 +507,7 @@ static int fw_cfg_register_dir_entries(void)
> >> break;
> >> }
> >>
> >> +end:
> >> kfree(dir);
> >> return ret;
> >> }
> >> @@ -539,7 +548,10 @@ static int fw_cfg_sysfs_probe(struct platform_device *pdev)
> >> goto err_probe;
> >>
> >> /* get revision number, add matching top-level attribute */
> >> - fw_cfg_read_blob(FW_CFG_ID, &rev, 0, sizeof(rev));
> >> + err = fw_cfg_read_blob(FW_CFG_ID, &rev, 0, sizeof(rev));
> >> + if (err < 0)
> >> + goto err_probe;
> >> +
> >> fw_cfg_rev = le32_to_cpu(rev);
> >> err = sysfs_create_file(fw_cfg_top_ko, &fw_cfg_rev_attr.attr);
> >> if (err)
> >
> > I think that this is the only case where it's not doing the right thing right now in
> > that it shows 0 as the revision to the users. Is it worth failing probe
> > here? We could just skip the attribute, could we not?
>
> I think it's best to fail the probe if we have a read failure at that time.

I'd rather we just dropped this attribute completely.
Why is it there?
Does any userspace actually need it?
Gabriel?

> --
> Marc-André Lureau