Drivers: hv: vmbus: Compute ring byte counts from a caller-held snapshot

hv_get_ringbuffer_availbytes() reads the indices directly, so a caller
that also wants the index values has to read them a second time. The
host can change them in between, resulting in the byte counts and the
indices reflecting two different states of the ring.

Replace it with hv_ringbuffer_avail_write() and
hv_ringbuffer_avail_read(), which take the indices as arguments and
return a single count. They are separate because most callers want only
one of the two values. Use them in hv_ringbuffer_write() in place of the
open-coded equivalent. hv_get_bytes_to_read(), hv_get_bytes_to_write()
and hv_pkt_iter_avail() duplicated the same arithmetic, so put the
helpers in include/linux/hyperv.h and use them there too.

Add a hv_ringbuffer_indices_invalid() helper that bounds checks a pair
of read and write indices, and use it for the check in
hv_ringbuffer_write(). Convert the remaining callers to use a single
snapshot:

  - hv_ringbuffer_get_debuginfo() now reports the indices and the
    computed byte counts from the same snapshot.

  - hv_pkt_iter_close() computes the free space from priv_read_index
    instead of re-reading the shared read index. The two agree unless a
    misbehaving host has rewritten the value.

No functional change intended for a well-behaved host.

Signed-off-by: Kameron Carr <kameroncarr@linux.microsoft.com>
Reviewed-by: Michael Kelley <mhklinux@outlook.com>
Signed-off-by: Wei Liu <wei.liu@kernel.org>
This commit is contained in:
Kameron Carr 2026-10-19 16:09:48 -07:00 committed by Wei Liu
parent 10e2eba7cc
commit a8e60890cb
2 changed files with 61 additions and 57 deletions

View File

@ -107,35 +107,12 @@ static u32 hv_copyto_ringbuffer(
return start_write_offset;
}
/*
*
* hv_get_ringbuffer_availbytes()
*
* Get number of bytes available to read and to write to
* for the specified ring buffer
*/
static void
hv_get_ringbuffer_availbytes(const struct hv_ring_buffer_info *rbi,
u32 *read, u32 *write)
{
u32 read_loc, write_loc, dsize;
/* Capture the read/write indices before they changed */
read_loc = READ_ONCE(rbi->ring_buffer->read_index);
write_loc = READ_ONCE(rbi->ring_buffer->write_index);
dsize = rbi->ring_datasize;
*write = write_loc >= read_loc ? dsize - (write_loc - read_loc) :
read_loc - write_loc;
*read = dsize - *write;
}
/* Get various debug metrics for the specified ring buffer. */
int hv_ringbuffer_get_debuginfo(struct hv_ring_buffer_info *ring_info,
struct hv_ring_buffer_debug_info *debug_info)
{
u32 bytes_avail_towrite;
u32 bytes_avail_toread;
u32 read_index;
u32 write_index;
mutex_lock(&ring_info->ring_buffer_mutex);
@ -144,13 +121,14 @@ int hv_ringbuffer_get_debuginfo(struct hv_ring_buffer_info *ring_info,
return -EINVAL;
}
hv_get_ringbuffer_availbytes(ring_info,
&bytes_avail_toread,
&bytes_avail_towrite);
debug_info->bytes_avail_toread = bytes_avail_toread;
debug_info->bytes_avail_towrite = bytes_avail_towrite;
debug_info->current_read_index = ring_info->ring_buffer->read_index;
debug_info->current_write_index = ring_info->ring_buffer->write_index;
read_index = READ_ONCE(ring_info->ring_buffer->read_index);
write_index = READ_ONCE(ring_info->ring_buffer->write_index);
debug_info->bytes_avail_toread =
hv_ringbuffer_avail_read(ring_info, read_index, write_index);
debug_info->bytes_avail_towrite =
hv_ringbuffer_avail_write(ring_info, read_index, write_index);
debug_info->current_read_index = read_index;
debug_info->current_write_index = write_index;
debug_info->current_interrupt_mask
= ring_info->ring_buffer->interrupt_mask;
mutex_unlock(&ring_info->ring_buffer_mutex);
@ -282,8 +260,8 @@ int hv_ringbuffer_write(struct vmbus_channel *channel,
read_index = READ_ONCE(outring_info->ring_buffer->read_index);
old_write = READ_ONCE(outring_info->ring_buffer->write_index);
if (unlikely(read_index >= outring_info->ring_datasize ||
old_write >= outring_info->ring_datasize)) {
if (unlikely(hv_ringbuffer_indices_invalid(outring_info, read_index,
old_write))) {
spin_unlock_irqrestore(&outring_info->ring_lock, flags);
pr_err_ratelimited("outbound ring indices out of range: relid %u read %u write %u size %u\n",
channel->offermsg.child_relid, read_index,
@ -291,9 +269,8 @@ int hv_ringbuffer_write(struct vmbus_channel *channel,
return -EIO;
}
bytes_avail_towrite = old_write >= read_index ?
outring_info->ring_datasize - (old_write - read_index) :
read_index - old_write;
bytes_avail_towrite = hv_ringbuffer_avail_write(outring_info, read_index,
old_write);
/*
* If there is only room for the packet, assume it is full.
@ -445,10 +422,7 @@ static u32 hv_pkt_iter_avail(const struct hv_ring_buffer_info *rbi)
*/
write_loc = virt_load_acquire(&rbi->ring_buffer->write_index);
if (write_loc >= priv_read_loc)
return write_loc - priv_read_loc;
else
return (rbi->ring_datasize - priv_read_loc) + write_loc;
return hv_ringbuffer_avail_read(rbi, priv_read_loc, write_loc);
}
/*
@ -568,6 +542,7 @@ void hv_pkt_iter_close(struct vmbus_channel *channel)
{
struct hv_ring_buffer_info *rbi = &channel->inbound;
u32 curr_write_sz, pending_sz, bytes_read, start_read_index;
u32 write_index;
/*
* Make sure all reads are done before we update the read index since
@ -607,11 +582,13 @@ void hv_pkt_iter_close(struct vmbus_channel *channel)
return;
/*
* Ensure the read of write_index in hv_get_bytes_to_write()
* happens after the read of pending_send_sz.
* Ensure the read of write_index happens after the read of
* pending_send_sz.
*/
virt_rmb();
curr_write_sz = hv_get_bytes_to_write(rbi);
write_index = READ_ONCE(rbi->ring_buffer->write_index);
curr_write_sz = hv_ringbuffer_avail_write(rbi, rbi->priv_read_index,
write_index);
bytes_read = hv_pkt_iter_bytes_read(rbi, start_read_index);
/*
@ -627,8 +604,7 @@ void hv_pkt_iter_close(struct vmbus_channel *channel)
* Exactly filling the ring buffer is treated as "not enough
* space". The ring buffer always must have at least one byte
* empty so the empty and full conditions are distinguishable.
* hv_get_bytes_to_write() doesn't fully tell the truth in
* this regard.
* curr_write_sz doesn't fully tell the truth in this regard.
*
* So first check if we were in the "enough free space" state
* before we began the iteration. If so, the host was not

View File

@ -209,31 +209,59 @@ struct hv_ring_buffer_info {
};
/*
* The indices live in memory shared with the untrusted host, so check a
* snapshot of them before using it as an offset or to compute a byte count.
*/
static inline bool
hv_ringbuffer_indices_invalid(const struct hv_ring_buffer_info *rbi,
u32 read_loc, u32 write_loc)
{
return read_loc >= rbi->ring_datasize ||
write_loc >= rbi->ring_datasize;
}
/*
* Byte counts for a caller-supplied snapshot of the indices, so that the
* counts and the indices the caller goes on to use describe one state of the
* ring.
*/
static inline u32
hv_ringbuffer_avail_write(const struct hv_ring_buffer_info *rbi,
u32 read_loc, u32 write_loc)
{
u32 dsize = rbi->ring_datasize;
return write_loc >= read_loc ? dsize - (write_loc - read_loc) :
read_loc - write_loc;
}
static inline u32
hv_ringbuffer_avail_read(const struct hv_ring_buffer_info *rbi,
u32 read_loc, u32 write_loc)
{
return rbi->ring_datasize -
hv_ringbuffer_avail_write(rbi, read_loc, write_loc);
}
static inline u32 hv_get_bytes_to_read(const struct hv_ring_buffer_info *rbi)
{
u32 read_loc, write_loc, dsize, read;
u32 read_loc, write_loc;
dsize = rbi->ring_datasize;
read_loc = READ_ONCE(rbi->ring_buffer->read_index);
write_loc = READ_ONCE(rbi->ring_buffer->write_index);
read = write_loc >= read_loc ? (write_loc - read_loc) :
(dsize - read_loc) + write_loc;
return read;
return hv_ringbuffer_avail_read(rbi, read_loc, write_loc);
}
static inline u32 hv_get_bytes_to_write(const struct hv_ring_buffer_info *rbi)
{
u32 read_loc, write_loc, dsize, write;
u32 read_loc, write_loc;
dsize = rbi->ring_datasize;
read_loc = READ_ONCE(rbi->ring_buffer->read_index);
write_loc = READ_ONCE(rbi->ring_buffer->write_index);
write = write_loc >= read_loc ? dsize - (write_loc - read_loc) :
read_loc - write_loc;
return write;
return hv_ringbuffer_avail_write(rbi, read_loc, write_loc);
}
static inline u32 hv_get_avail_to_write_percent(