From d8b441a3fbfd075c48ab2a519d779d926624ed79 Mon Sep 17 00:00:00 2001
From: Jan Beulich <JBeulich@suse.com>
Date: Fri, 24 Jul 2015 03:38:28 -0600
Subject: [PATCH] xen/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 a build one) went in already (commit b7007bc6f9).

Signed-off-by: Jan Beulich <jbeulich@suse.com>
Signed-off-by: Stefano Stabellini <stefano.stabellini@eu.citrix.com>
---
 configure                   | 27 +++++++++++++++++++++++++++
 include/hw/xen/xen_common.h | 12 +++++++++++-
 xen-hvm.c                   | 26 ++++++++++++++++++--------
 3 files changed, 56 insertions(+), 9 deletions(-)

diff --git a/configure b/configure
index d854936682..5618bf1bc0 100755
--- a/configure
+++ b/configure
@@ -1881,6 +1881,33 @@ EOF
 #if !defined(HVM_MAX_VCPUS)
 # error HVM_MAX_VCPUS not defined
 #endif
+int main(void) {
+  xc_interface *xc;
+  xs_daemon_open();
+  xc = xc_interface_open(0, 0, 0);
+  xc_hvm_set_mem_type(0, 0, HVMMEM_ram_ro, 0, 0);
+  xc_gnttab_open(NULL, 0);
+  xc_domain_add_to_physmap(0, 0, XENMAPSPACE_gmfn, 0, 0);
+  xc_hvm_inject_msi(xc, 0, 0xf0000000, 0x00000000);
+  xc_hvm_create_ioreq_server(xc, 0, HVM_IOREQSRV_BUFIOREQ_ATOMIC, NULL);
+  return 0;
+}
+EOF
+      compile_prog "" "$xen_libs"
+    then
+    xen_ctrl_version=460
+    xen=yes
+
+  # Xen 4.5
+  elif
+      cat > $TMPC <<EOF &&
+#include <xenctrl.h>
+#include <xenstore.h>
+#include <stdint.h>
+#include <xen/hvm/hvm_info_table.h>
+#if !defined(HVM_MAX_VCPUS)
+# error HVM_MAX_VCPUS not defined
+#endif
 int main(void) {
   xc_interface *xc;
   xs_daemon_open();
diff --git a/include/hw/xen/xen_common.h b/include/hw/xen/xen_common.h
index ed5fd3e1a2..19d0bca14e 100644
--- a/include/hw/xen/xen_common.h
+++ b/include/hw/xen/xen_common.h
@@ -186,6 +186,15 @@ static inline int xen_get_vmport_regs_pfn(XenXC xc, domid_t dom,
 }
 #endif
 
+/* Xen before 4.6 */
+#if CONFIG_XEN_CTRL_INTERFACE_VERSION < 460
+
+#ifndef HVM_IOREQSRV_BUFIOREQ_ATOMIC
+#define HVM_IOREQSRV_BUFIOREQ_ATOMIC 2
+#endif
+
+#endif
+
 /* Xen before 4.5 */
 #if CONFIG_XEN_CTRL_INTERFACE_VERSION < 450
 
@@ -370,7 +379,8 @@ static inline void xen_unmap_pcidev(XenXC xc, domid_t dom,
 static inline int xen_create_ioreq_server(XenXC xc, domid_t dom,
                                           ioservid_t *ioservid)
 {
-    int rc = xc_hvm_create_ioreq_server(xc, dom, 1, ioservid);
+    int rc = xc_hvm_create_ioreq_server(xc, dom, HVM_IOREQSRV_BUFIOREQ_ATOMIC,
+                                        ioservid);
 
     if (rc == 0) {
         trace_xen_ioreq_server_create(*ioservid);
diff --git a/xen-hvm.c b/xen-hvm.c
index 0f81f7fd9c..cbd0a79afd 100644
--- a/xen-hvm.c
+++ b/xen-hvm.c
@@ -984,19 +984,30 @@ static void handle_ioreq(XenIOState *state, ioreq_t *req)
 
 static int handle_buffered_iopage(XenIOState *state)
 {
+    buffered_iopage_t *buf_page = state->buffered_io_page;
     buf_ioreq_t *buf_req = NULL;
     ioreq_t req;
     int qw;
 
-    if (!state->buffered_io_page) {
+    if (!buf_page) {
         return 0;
     }
 
     memset(&req, 0x00, sizeof(req));
 
-    while (state->buffered_io_page->read_pointer != state->buffered_io_page->write_pointer) {
-        buf_req = &state->buffered_io_page->buf_ioreq[
-            state->buffered_io_page->read_pointer % IOREQ_BUFFER_SLOT_NUM];
+    for (;;) {
+        uint32_t rdptr = buf_page->read_pointer, wrptr;
+
+        xen_rmb();
+        wrptr = buf_page->write_pointer;
+        xen_rmb();
+        if (rdptr != buf_page->read_pointer) {
+            continue;
+        }
+        if (rdptr == wrptr) {
+            break;
+        }
+        buf_req = &buf_page->buf_ioreq[rdptr % IOREQ_BUFFER_SLOT_NUM];
         req.size = 1UL << buf_req->size;
         req.count = 1;
         req.addr = buf_req->addr;
@@ -1008,15 +1019,14 @@ static int handle_buffered_iopage(XenIOState *state)
         req.data_is_ptr = 0;
         qw = (req.size == 8);
         if (qw) {
-            buf_req = &state->buffered_io_page->buf_ioreq[
-                (state->buffered_io_page->read_pointer + 1) % IOREQ_BUFFER_SLOT_NUM];
+            buf_req = &buf_page->buf_ioreq[(rdptr + 1) %
+                                           IOREQ_BUFFER_SLOT_NUM];
             req.data |= ((uint64_t)buf_req->data) << 32;
         }
 
         handle_ioreq(state, &req);
 
-        xen_mb();
-        state->buffered_io_page->read_pointer += qw ? 2 : 1;
+        atomic_add(&buf_page->read_pointer, qw + 1);
     }
 
     return req.count;
-- 
2.39.5