mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-08-24 01:41:39 +00:00
![Kees Cook](/assets/img/avatar_default.png)
The kzalloc() function has a 2-factor argument form, kcalloc(). This patch replaces cases of: kzalloc(a * b, gfp) with: kcalloc(a * b, gfp) as well as handling cases of: kzalloc(a * b * c, gfp) with: kzalloc(array3_size(a, b, c), gfp) as it's slightly less ugly than: kzalloc_array(array_size(a, b), c, gfp) This does, however, attempt to ignore constant size factors like: kzalloc(4 * 1024, gfp) though any constants defined via macros get caught up in the conversion. Any factors with a sizeof() of "unsigned char", "char", and "u8" were dropped, since they're redundant. The Coccinelle script used for this was: // Fix redundant parens around sizeof(). @@ type TYPE; expression THING, E; @@ ( kzalloc( - (sizeof(TYPE)) * E + sizeof(TYPE) * E , ...) | kzalloc( - (sizeof(THING)) * E + sizeof(THING) * E , ...) ) // Drop single-byte sizes and redundant parens. @@ expression COUNT; typedef u8; typedef __u8; @@ ( kzalloc( - sizeof(u8) * (COUNT) + COUNT , ...) | kzalloc( - sizeof(__u8) * (COUNT) + COUNT , ...) | kzalloc( - sizeof(char) * (COUNT) + COUNT , ...) | kzalloc( - sizeof(unsigned char) * (COUNT) + COUNT , ...) | kzalloc( - sizeof(u8) * COUNT + COUNT , ...) | kzalloc( - sizeof(__u8) * COUNT + COUNT , ...) | kzalloc( - sizeof(char) * COUNT + COUNT , ...) | kzalloc( - sizeof(unsigned char) * COUNT + COUNT , ...) ) // 2-factor product with sizeof(type/expression) and identifier or constant. @@ type TYPE; expression THING; identifier COUNT_ID; constant COUNT_CONST; @@ ( - kzalloc + kcalloc ( - sizeof(TYPE) * (COUNT_ID) + COUNT_ID, sizeof(TYPE) , ...) | - kzalloc + kcalloc ( - sizeof(TYPE) * COUNT_ID + COUNT_ID, sizeof(TYPE) , ...) | - kzalloc + kcalloc ( - sizeof(TYPE) * (COUNT_CONST) + COUNT_CONST, sizeof(TYPE) , ...) | - kzalloc + kcalloc ( - sizeof(TYPE) * COUNT_CONST + COUNT_CONST, sizeof(TYPE) , ...) | - kzalloc + kcalloc ( - sizeof(THING) * (COUNT_ID) + COUNT_ID, sizeof(THING) , ...) | - kzalloc + kcalloc ( - sizeof(THING) * COUNT_ID + COUNT_ID, sizeof(THING) , ...) | - kzalloc + kcalloc ( - sizeof(THING) * (COUNT_CONST) + COUNT_CONST, sizeof(THING) , ...) | - kzalloc + kcalloc ( - sizeof(THING) * COUNT_CONST + COUNT_CONST, sizeof(THING) , ...) ) // 2-factor product, only identifiers. @@ identifier SIZE, COUNT; @@ - kzalloc + kcalloc ( - SIZE * COUNT + COUNT, SIZE , ...) // 3-factor product with 1 sizeof(type) or sizeof(expression), with // redundant parens removed. @@ expression THING; identifier STRIDE, COUNT; type TYPE; @@ ( kzalloc( - sizeof(TYPE) * (COUNT) * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kzalloc( - sizeof(TYPE) * (COUNT) * STRIDE + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kzalloc( - sizeof(TYPE) * COUNT * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kzalloc( - sizeof(TYPE) * COUNT * STRIDE + array3_size(COUNT, STRIDE, sizeof(TYPE)) , ...) | kzalloc( - sizeof(THING) * (COUNT) * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) | kzalloc( - sizeof(THING) * (COUNT) * STRIDE + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) | kzalloc( - sizeof(THING) * COUNT * (STRIDE) + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) | kzalloc( - sizeof(THING) * COUNT * STRIDE + array3_size(COUNT, STRIDE, sizeof(THING)) , ...) ) // 3-factor product with 2 sizeof(variable), with redundant parens removed. @@ expression THING1, THING2; identifier COUNT; type TYPE1, TYPE2; @@ ( kzalloc( - sizeof(TYPE1) * sizeof(TYPE2) * COUNT + array3_size(COUNT, sizeof(TYPE1), sizeof(TYPE2)) , ...) | kzalloc( - sizeof(TYPE1) * sizeof(THING2) * (COUNT) + array3_size(COUNT, sizeof(TYPE1), sizeof(TYPE2)) , ...) | kzalloc( - sizeof(THING1) * sizeof(THING2) * COUNT + array3_size(COUNT, sizeof(THING1), sizeof(THING2)) , ...) | kzalloc( - sizeof(THING1) * sizeof(THING2) * (COUNT) + array3_size(COUNT, sizeof(THING1), sizeof(THING2)) , ...) | kzalloc( - sizeof(TYPE1) * sizeof(THING2) * COUNT + array3_size(COUNT, sizeof(TYPE1), sizeof(THING2)) , ...) | kzalloc( - sizeof(TYPE1) * sizeof(THING2) * (COUNT) + array3_size(COUNT, sizeof(TYPE1), sizeof(THING2)) , ...) ) // 3-factor product, only identifiers, with redundant parens removed. @@ identifier STRIDE, SIZE, COUNT; @@ ( kzalloc( - (COUNT) * STRIDE * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - COUNT * (STRIDE) * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - COUNT * STRIDE * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - (COUNT) * (STRIDE) * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - COUNT * (STRIDE) * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - (COUNT) * STRIDE * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - (COUNT) * (STRIDE) * (SIZE) + array3_size(COUNT, STRIDE, SIZE) , ...) | kzalloc( - COUNT * STRIDE * SIZE + array3_size(COUNT, STRIDE, SIZE) , ...) ) // Any remaining multi-factor products, first at least 3-factor products, // when they're not all constants... @@ expression E1, E2, E3; constant C1, C2, C3; @@ ( kzalloc(C1 * C2 * C3, ...) | kzalloc( - (E1) * E2 * E3 + array3_size(E1, E2, E3) , ...) | kzalloc( - (E1) * (E2) * E3 + array3_size(E1, E2, E3) , ...) | kzalloc( - (E1) * (E2) * (E3) + array3_size(E1, E2, E3) , ...) | kzalloc( - E1 * E2 * E3 + array3_size(E1, E2, E3) , ...) ) // And then all remaining 2 factors products when they're not all constants, // keeping sizeof() as the second factor argument. @@ expression THING, E1, E2; type TYPE; constant C1, C2, C3; @@ ( kzalloc(sizeof(THING) * C2, ...) | kzalloc(sizeof(TYPE) * C2, ...) | kzalloc(C1 * C2 * C3, ...) | kzalloc(C1 * C2, ...) | - kzalloc + kcalloc ( - sizeof(TYPE) * (E2) + E2, sizeof(TYPE) , ...) | - kzalloc + kcalloc ( - sizeof(TYPE) * E2 + E2, sizeof(TYPE) , ...) | - kzalloc + kcalloc ( - sizeof(THING) * (E2) + E2, sizeof(THING) , ...) | - kzalloc + kcalloc ( - sizeof(THING) * E2 + E2, sizeof(THING) , ...) | - kzalloc + kcalloc ( - (E1) * E2 + E1, E2 , ...) | - kzalloc + kcalloc ( - (E1) * (E2) + E1, E2 , ...) | - kzalloc + kcalloc ( - E1 * E2 + E1, E2 , ...) ) Signed-off-by: Kees Cook <keescook@chromium.org>
492 lines
14 KiB
C
492 lines
14 KiB
C
/*
|
|
*
|
|
* Copyright (c) 2009, Microsoft Corporation.
|
|
*
|
|
* This program is free software; you can redistribute it and/or modify it
|
|
* under the terms and conditions of the GNU General Public License,
|
|
* version 2, as published by the Free Software Foundation.
|
|
*
|
|
* This program is distributed in the hope it will be useful, but WITHOUT
|
|
* ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
|
|
* FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
|
|
* more details.
|
|
*
|
|
* You should have received a copy of the GNU General Public License along with
|
|
* this program; if not, write to the Free Software Foundation, Inc., 59 Temple
|
|
* Place - Suite 330, Boston, MA 02111-1307 USA.
|
|
*
|
|
* Authors:
|
|
* Haiyang Zhang <haiyangz@microsoft.com>
|
|
* Hank Janssen <hjanssen@microsoft.com>
|
|
* K. Y. Srinivasan <kys@microsoft.com>
|
|
*
|
|
*/
|
|
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
|
|
|
|
#include <linux/kernel.h>
|
|
#include <linux/mm.h>
|
|
#include <linux/hyperv.h>
|
|
#include <linux/uio.h>
|
|
#include <linux/vmalloc.h>
|
|
#include <linux/slab.h>
|
|
#include <linux/prefetch.h>
|
|
|
|
#include "hyperv_vmbus.h"
|
|
|
|
#define VMBUS_PKT_TRAILER 8
|
|
|
|
/*
|
|
* When we write to the ring buffer, check if the host needs to
|
|
* be signaled. Here is the details of this protocol:
|
|
*
|
|
* 1. The host guarantees that while it is draining the
|
|
* ring buffer, it will set the interrupt_mask to
|
|
* indicate it does not need to be interrupted when
|
|
* new data is placed.
|
|
*
|
|
* 2. The host guarantees that it will completely drain
|
|
* the ring buffer before exiting the read loop. Further,
|
|
* once the ring buffer is empty, it will clear the
|
|
* interrupt_mask and re-check to see if new data has
|
|
* arrived.
|
|
*
|
|
* KYS: Oct. 30, 2016:
|
|
* It looks like Windows hosts have logic to deal with DOS attacks that
|
|
* can be triggered if it receives interrupts when it is not expecting
|
|
* the interrupt. The host expects interrupts only when the ring
|
|
* transitions from empty to non-empty (or full to non full on the guest
|
|
* to host ring).
|
|
* So, base the signaling decision solely on the ring state until the
|
|
* host logic is fixed.
|
|
*/
|
|
|
|
static void hv_signal_on_write(u32 old_write, struct vmbus_channel *channel)
|
|
{
|
|
struct hv_ring_buffer_info *rbi = &channel->outbound;
|
|
|
|
virt_mb();
|
|
if (READ_ONCE(rbi->ring_buffer->interrupt_mask))
|
|
return;
|
|
|
|
/* check interrupt_mask before read_index */
|
|
virt_rmb();
|
|
/*
|
|
* This is the only case we need to signal when the
|
|
* ring transitions from being empty to non-empty.
|
|
*/
|
|
if (old_write == READ_ONCE(rbi->ring_buffer->read_index))
|
|
vmbus_setevent(channel);
|
|
}
|
|
|
|
/* Get the next write location for the specified ring buffer. */
|
|
static inline u32
|
|
hv_get_next_write_location(struct hv_ring_buffer_info *ring_info)
|
|
{
|
|
u32 next = ring_info->ring_buffer->write_index;
|
|
|
|
return next;
|
|
}
|
|
|
|
/* Set the next write location for the specified ring buffer. */
|
|
static inline void
|
|
hv_set_next_write_location(struct hv_ring_buffer_info *ring_info,
|
|
u32 next_write_location)
|
|
{
|
|
ring_info->ring_buffer->write_index = next_write_location;
|
|
}
|
|
|
|
/* Set the next read location for the specified ring buffer. */
|
|
static inline void
|
|
hv_set_next_read_location(struct hv_ring_buffer_info *ring_info,
|
|
u32 next_read_location)
|
|
{
|
|
ring_info->ring_buffer->read_index = next_read_location;
|
|
ring_info->priv_read_index = next_read_location;
|
|
}
|
|
|
|
/* Get the size of the ring buffer. */
|
|
static inline u32
|
|
hv_get_ring_buffersize(const struct hv_ring_buffer_info *ring_info)
|
|
{
|
|
return ring_info->ring_datasize;
|
|
}
|
|
|
|
/* Get the read and write indices as u64 of the specified ring buffer. */
|
|
static inline u64
|
|
hv_get_ring_bufferindices(struct hv_ring_buffer_info *ring_info)
|
|
{
|
|
return (u64)ring_info->ring_buffer->write_index << 32;
|
|
}
|
|
|
|
/*
|
|
* Helper routine to copy from source to ring buffer.
|
|
* Assume there is enough room. Handles wrap-around in dest case only!!
|
|
*/
|
|
static u32 hv_copyto_ringbuffer(
|
|
struct hv_ring_buffer_info *ring_info,
|
|
u32 start_write_offset,
|
|
const void *src,
|
|
u32 srclen)
|
|
{
|
|
void *ring_buffer = hv_get_ring_buffer(ring_info);
|
|
u32 ring_buffer_size = hv_get_ring_buffersize(ring_info);
|
|
|
|
memcpy(ring_buffer + start_write_offset, src, srclen);
|
|
|
|
start_write_offset += srclen;
|
|
if (start_write_offset >= ring_buffer_size)
|
|
start_write_offset -= ring_buffer_size;
|
|
|
|
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. */
|
|
void hv_ringbuffer_get_debuginfo(const struct hv_ring_buffer_info *ring_info,
|
|
struct hv_ring_buffer_debug_info *debug_info)
|
|
{
|
|
u32 bytes_avail_towrite;
|
|
u32 bytes_avail_toread;
|
|
|
|
if (ring_info->ring_buffer) {
|
|
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;
|
|
debug_info->current_interrupt_mask =
|
|
ring_info->ring_buffer->interrupt_mask;
|
|
}
|
|
}
|
|
EXPORT_SYMBOL_GPL(hv_ringbuffer_get_debuginfo);
|
|
|
|
/* Initialize the ring buffer. */
|
|
int hv_ringbuffer_init(struct hv_ring_buffer_info *ring_info,
|
|
struct page *pages, u32 page_cnt)
|
|
{
|
|
int i;
|
|
struct page **pages_wraparound;
|
|
|
|
BUILD_BUG_ON((sizeof(struct hv_ring_buffer) != PAGE_SIZE));
|
|
|
|
memset(ring_info, 0, sizeof(struct hv_ring_buffer_info));
|
|
|
|
/*
|
|
* First page holds struct hv_ring_buffer, do wraparound mapping for
|
|
* the rest.
|
|
*/
|
|
pages_wraparound = kcalloc(page_cnt * 2 - 1, sizeof(struct page *),
|
|
GFP_KERNEL);
|
|
if (!pages_wraparound)
|
|
return -ENOMEM;
|
|
|
|
pages_wraparound[0] = pages;
|
|
for (i = 0; i < 2 * (page_cnt - 1); i++)
|
|
pages_wraparound[i + 1] = &pages[i % (page_cnt - 1) + 1];
|
|
|
|
ring_info->ring_buffer = (struct hv_ring_buffer *)
|
|
vmap(pages_wraparound, page_cnt * 2 - 1, VM_MAP, PAGE_KERNEL);
|
|
|
|
kfree(pages_wraparound);
|
|
|
|
|
|
if (!ring_info->ring_buffer)
|
|
return -ENOMEM;
|
|
|
|
ring_info->ring_buffer->read_index =
|
|
ring_info->ring_buffer->write_index = 0;
|
|
|
|
/* Set the feature bit for enabling flow control. */
|
|
ring_info->ring_buffer->feature_bits.value = 1;
|
|
|
|
ring_info->ring_size = page_cnt << PAGE_SHIFT;
|
|
ring_info->ring_size_div10_reciprocal =
|
|
reciprocal_value(ring_info->ring_size / 10);
|
|
ring_info->ring_datasize = ring_info->ring_size -
|
|
sizeof(struct hv_ring_buffer);
|
|
|
|
spin_lock_init(&ring_info->ring_lock);
|
|
|
|
return 0;
|
|
}
|
|
|
|
/* Cleanup the ring buffer. */
|
|
void hv_ringbuffer_cleanup(struct hv_ring_buffer_info *ring_info)
|
|
{
|
|
vunmap(ring_info->ring_buffer);
|
|
}
|
|
|
|
/* Write to the ring buffer. */
|
|
int hv_ringbuffer_write(struct vmbus_channel *channel,
|
|
const struct kvec *kv_list, u32 kv_count)
|
|
{
|
|
int i;
|
|
u32 bytes_avail_towrite;
|
|
u32 totalbytes_towrite = sizeof(u64);
|
|
u32 next_write_location;
|
|
u32 old_write;
|
|
u64 prev_indices;
|
|
unsigned long flags;
|
|
struct hv_ring_buffer_info *outring_info = &channel->outbound;
|
|
|
|
if (channel->rescind)
|
|
return -ENODEV;
|
|
|
|
for (i = 0; i < kv_count; i++)
|
|
totalbytes_towrite += kv_list[i].iov_len;
|
|
|
|
spin_lock_irqsave(&outring_info->ring_lock, flags);
|
|
|
|
bytes_avail_towrite = hv_get_bytes_to_write(outring_info);
|
|
|
|
/*
|
|
* If there is only room for the packet, assume it is full.
|
|
* Otherwise, the next time around, we think the ring buffer
|
|
* is empty since the read index == write index.
|
|
*/
|
|
if (bytes_avail_towrite <= totalbytes_towrite) {
|
|
spin_unlock_irqrestore(&outring_info->ring_lock, flags);
|
|
return -EAGAIN;
|
|
}
|
|
|
|
/* Write to the ring buffer */
|
|
next_write_location = hv_get_next_write_location(outring_info);
|
|
|
|
old_write = next_write_location;
|
|
|
|
for (i = 0; i < kv_count; i++) {
|
|
next_write_location = hv_copyto_ringbuffer(outring_info,
|
|
next_write_location,
|
|
kv_list[i].iov_base,
|
|
kv_list[i].iov_len);
|
|
}
|
|
|
|
/* Set previous packet start */
|
|
prev_indices = hv_get_ring_bufferindices(outring_info);
|
|
|
|
next_write_location = hv_copyto_ringbuffer(outring_info,
|
|
next_write_location,
|
|
&prev_indices,
|
|
sizeof(u64));
|
|
|
|
/* Issue a full memory barrier before updating the write index */
|
|
virt_mb();
|
|
|
|
/* Now, update the write location */
|
|
hv_set_next_write_location(outring_info, next_write_location);
|
|
|
|
|
|
spin_unlock_irqrestore(&outring_info->ring_lock, flags);
|
|
|
|
hv_signal_on_write(old_write, channel);
|
|
|
|
if (channel->rescind)
|
|
return -ENODEV;
|
|
|
|
return 0;
|
|
}
|
|
|
|
int hv_ringbuffer_read(struct vmbus_channel *channel,
|
|
void *buffer, u32 buflen, u32 *buffer_actual_len,
|
|
u64 *requestid, bool raw)
|
|
{
|
|
struct vmpacket_descriptor *desc;
|
|
u32 packetlen, offset;
|
|
|
|
if (unlikely(buflen == 0))
|
|
return -EINVAL;
|
|
|
|
*buffer_actual_len = 0;
|
|
*requestid = 0;
|
|
|
|
/* Make sure there is something to read */
|
|
desc = hv_pkt_iter_first(channel);
|
|
if (desc == NULL) {
|
|
/*
|
|
* No error is set when there is even no header, drivers are
|
|
* supposed to analyze buffer_actual_len.
|
|
*/
|
|
return 0;
|
|
}
|
|
|
|
offset = raw ? 0 : (desc->offset8 << 3);
|
|
packetlen = (desc->len8 << 3) - offset;
|
|
*buffer_actual_len = packetlen;
|
|
*requestid = desc->trans_id;
|
|
|
|
if (unlikely(packetlen > buflen))
|
|
return -ENOBUFS;
|
|
|
|
/* since ring is double mapped, only one copy is necessary */
|
|
memcpy(buffer, (const char *)desc + offset, packetlen);
|
|
|
|
/* Advance ring index to next packet descriptor */
|
|
__hv_pkt_iter_next(channel, desc);
|
|
|
|
/* Notify host of update */
|
|
hv_pkt_iter_close(channel);
|
|
|
|
return 0;
|
|
}
|
|
|
|
/*
|
|
* Determine number of bytes available in ring buffer after
|
|
* the current iterator (priv_read_index) location.
|
|
*
|
|
* This is similar to hv_get_bytes_to_read but with private
|
|
* read index instead.
|
|
*/
|
|
static u32 hv_pkt_iter_avail(const struct hv_ring_buffer_info *rbi)
|
|
{
|
|
u32 priv_read_loc = rbi->priv_read_index;
|
|
u32 write_loc = READ_ONCE(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;
|
|
}
|
|
|
|
/*
|
|
* Get first vmbus packet from ring buffer after read_index
|
|
*
|
|
* If ring buffer is empty, returns NULL and no other action needed.
|
|
*/
|
|
struct vmpacket_descriptor *hv_pkt_iter_first(struct vmbus_channel *channel)
|
|
{
|
|
struct hv_ring_buffer_info *rbi = &channel->inbound;
|
|
struct vmpacket_descriptor *desc;
|
|
|
|
if (hv_pkt_iter_avail(rbi) < sizeof(struct vmpacket_descriptor))
|
|
return NULL;
|
|
|
|
desc = hv_get_ring_buffer(rbi) + rbi->priv_read_index;
|
|
if (desc)
|
|
prefetch((char *)desc + (desc->len8 << 3));
|
|
|
|
return desc;
|
|
}
|
|
EXPORT_SYMBOL_GPL(hv_pkt_iter_first);
|
|
|
|
/*
|
|
* Get next vmbus packet from ring buffer.
|
|
*
|
|
* Advances the current location (priv_read_index) and checks for more
|
|
* data. If the end of the ring buffer is reached, then return NULL.
|
|
*/
|
|
struct vmpacket_descriptor *
|
|
__hv_pkt_iter_next(struct vmbus_channel *channel,
|
|
const struct vmpacket_descriptor *desc)
|
|
{
|
|
struct hv_ring_buffer_info *rbi = &channel->inbound;
|
|
u32 packetlen = desc->len8 << 3;
|
|
u32 dsize = rbi->ring_datasize;
|
|
|
|
/* bump offset to next potential packet */
|
|
rbi->priv_read_index += packetlen + VMBUS_PKT_TRAILER;
|
|
if (rbi->priv_read_index >= dsize)
|
|
rbi->priv_read_index -= dsize;
|
|
|
|
/* more data? */
|
|
return hv_pkt_iter_first(channel);
|
|
}
|
|
EXPORT_SYMBOL_GPL(__hv_pkt_iter_next);
|
|
|
|
/* How many bytes were read in this iterator cycle */
|
|
static u32 hv_pkt_iter_bytes_read(const struct hv_ring_buffer_info *rbi,
|
|
u32 start_read_index)
|
|
{
|
|
if (rbi->priv_read_index >= start_read_index)
|
|
return rbi->priv_read_index - start_read_index;
|
|
else
|
|
return rbi->ring_datasize - start_read_index +
|
|
rbi->priv_read_index;
|
|
}
|
|
|
|
/*
|
|
* Update host ring buffer after iterating over packets.
|
|
*/
|
|
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;
|
|
|
|
/*
|
|
* Make sure all reads are done before we update the read index since
|
|
* the writer may start writing to the read area once the read index
|
|
* is updated.
|
|
*/
|
|
virt_rmb();
|
|
start_read_index = rbi->ring_buffer->read_index;
|
|
rbi->ring_buffer->read_index = rbi->priv_read_index;
|
|
|
|
if (!rbi->ring_buffer->feature_bits.feat_pending_send_sz)
|
|
return;
|
|
|
|
/*
|
|
* Issue a full memory barrier before making the signaling decision.
|
|
* Here is the reason for having this barrier:
|
|
* If the reading of the pend_sz (in this function)
|
|
* were to be reordered and read before we commit the new read
|
|
* index (in the calling function) we could
|
|
* have a problem. If the host were to set the pending_sz after we
|
|
* have sampled pending_sz and go to sleep before we commit the
|
|
* read index, we could miss sending the interrupt. Issue a full
|
|
* memory barrier to address this.
|
|
*/
|
|
virt_mb();
|
|
|
|
pending_sz = READ_ONCE(rbi->ring_buffer->pending_send_sz);
|
|
if (!pending_sz)
|
|
return;
|
|
|
|
/*
|
|
* Ensure the read of write_index in hv_get_bytes_to_write()
|
|
* happens after the read of pending_send_sz.
|
|
*/
|
|
virt_rmb();
|
|
curr_write_sz = hv_get_bytes_to_write(rbi);
|
|
bytes_read = hv_pkt_iter_bytes_read(rbi, start_read_index);
|
|
|
|
/*
|
|
* If there was space before we began iteration,
|
|
* then host was not blocked.
|
|
*/
|
|
|
|
if (curr_write_sz - bytes_read > pending_sz)
|
|
return;
|
|
|
|
/* If pending write will not fit, don't give false hope. */
|
|
if (curr_write_sz <= pending_sz)
|
|
return;
|
|
|
|
vmbus_setevent(channel);
|
|
}
|
|
EXPORT_SYMBOL_GPL(hv_pkt_iter_close);
|