The number of slots per page being 511 (i.e. not a power of two) means
that the (32-bit) read and write indexes going beyond 2^32 will likely
disturb operation. The hypervisor side gets I/O req server creation
extended so we can indicate that we're using suitable atomic accesses
where needed, allowing it to atomically canonicalize both pointers when
both have gone through at least one cycle.
The Xen side counterpart (which is not a functional prereq to this
change, albeit the intention is for Xen to assume default servers
always use suitable atomic accesses) went in already (commit
b7007bc6f9).
Signed-off-by: Jan Beulich <jbeul...@suse.com>
---
v2: Adjust description.
--- a/i386-dm/helper2.c
+++ b/i386-dm/helper2.c
@@ -493,10 +493,19 @@ static int __handle_buffered_iopage(CPUS
memset(&req, 0x00, sizeof(req));
- while (buffered_io_page->read_pointer !=
- buffered_io_page->write_pointer) {
- buf_req = &buffered_io_page->buf_ioreq[
- buffered_io_page->read_pointer % IOREQ_BUFFER_SLOT_NUM];
+ for (;;) {
+ uint32_t rdptr = buffered_io_page->read_pointer, wrptr;
+
+ xen_rmb();
+ wrptr = buffered_io_page->write_pointer;
+ xen_rmb();
+ if (rdptr != buffered_io_page->read_pointer) {
+ continue;
+ }
+ if (rdptr == wrptr) {
+ break;
+ }
+ buf_req = &buffered_io_page->buf_ioreq[rdptr % IOREQ_BUFFER_SLOT_NUM];
req.size = 1UL << buf_req->size;
req.count = 1;
req.addr = buf_req->addr;
@@ -508,15 +517,14 @@ static int __handle_buffered_iopage(CPUS
req.data_is_ptr = 0;
qw = (req.size == 8);
if (qw) {
- buf_req = &buffered_io_page->buf_ioreq[
- (buffered_io_page->read_pointer+1) % IOREQ_BUFFER_SLOT_NUM];
+ buf_req = &buffered_io_page->buf_ioreq[(rdptr + 1) %
+ IOREQ_BUFFER_SLOT_NUM];
req.data |= ((uint64_t)buf_req->data) << 32;
}
__handle_ioreq(env, &req);
- xen_mb();
- buffered_io_page->read_pointer += qw ? 2 : 1;
+ __sync_fetch_and_add(&buffered_io_page->read_pointer, qw + 1);
}
return req.count;
HVM: atomically access pointers in bufioreq handling
The number of slots per page being 511 (i.e. not a power of two) means
that the (32-bit) read and write indexes going beyond 2^32 will likely
disturb operation. The hypervisor side gets I/O req server creation
extended so we can indicate that we're using suitable atomic accesses
where needed, allowing it to atomically canonicalize both pointers when
both have gone through at least one cycle.
The Xen side counterpart (which is not a functional prereq to this
change, albeit the intention is for Xen to assume default servers
always use suitable atomic accesses) went in already (commit
b7007bc6f9).
Signed-off-by: Jan Beulich <jbeul...@suse.com>
---
v2: Adjust description.
--- a/i386-dm/helper2.c
+++ b/i386-dm/helper2.c
@@ -493,10 +493,19 @@ static int __handle_buffered_iopage(CPUS
memset(&req, 0x00, sizeof(req));
- while (buffered_io_page->read_pointer !=
- buffered_io_page->write_pointer) {
- buf_req = &buffered_io_page->buf_ioreq[
- buffered_io_page->read_pointer % IOREQ_BUFFER_SLOT_NUM];
+ for (;;) {
+ uint32_t rdptr = buffered_io_page->read_pointer, wrptr;
+
+ xen_rmb();
+ wrptr = buffered_io_page->write_pointer;
+ xen_rmb();
+ if (rdptr != buffered_io_page->read_pointer) {
+ continue;
+ }
+ if (rdptr == wrptr) {
+ break;
+ }
+ buf_req = &buffered_io_page->buf_ioreq[rdptr % IOREQ_BUFFER_SLOT_NUM];
req.size = 1UL << buf_req->size;
req.count = 1;
req.addr = buf_req->addr;
@@ -508,15 +517,14 @@ static int __handle_buffered_iopage(CPUS
req.data_is_ptr = 0;
qw = (req.size == 8);
if (qw) {
- buf_req = &buffered_io_page->buf_ioreq[
- (buffered_io_page->read_pointer+1) % IOREQ_BUFFER_SLOT_NUM];
+ buf_req = &buffered_io_page->buf_ioreq[(rdptr + 1) %
+ IOREQ_BUFFER_SLOT_NUM];
req.data |= ((uint64_t)buf_req->data) << 32;
}
__handle_ioreq(env, &req);
- xen_mb();
- buffered_io_page->read_pointer += qw ? 2 : 1;
+ __sync_fetch_and_add(&buffered_io_page->read_pointer, qw + 1);
}
return req.count;
_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xen.org
http://lists.xen.org/xen-devel
