The atomic_cmpxchg() loop is broken because we occasionally end up with
old and _old having different values (a legit compiler can generate code
that accessed *ind_addr again to pick up a value for _old instead of
using the value of old that was already fetched according to the
rules of the abstract machine). This means the underlying CS instruction
may use a different old (_old) than the one we intended to use if
atomic_cmpxchg() performed the xchg part.

Let us use volatile to force the rules of the abstract machine for
accesses to *ind_addr. Let us also rewrite the loop so, we that the
new old is used to compute the new desired value if the xchg part
is not performed.

Signed-off-by: Halil Pasic <pasic@linux.ibm.com>
Fixes: 8cba80c3a0 ("s390: Add PCI bus support")
Reported-by: Christian Borntraeger <borntraeger@de.ibm.com>
---
 hw/s390x/s390-pci-bus.c | 16 +++++++++-------
 1 file changed, 9 insertions(+), 7 deletions(-)

diff --git a/hw/s390x/s390-pci-bus.c b/hw/s390x/s390-pci-bus.c
index c4a4259f0c..80eb957a91 100644
--- a/hw/s390x/s390-pci-bus.c
+++ b/hw/s390x/s390-pci-bus.c
@@ -637,22 +637,24 @@ static AddressSpace *s390_pci_dma_iommu(PCIBus *bus, void *opaque, int devfn)
 
 static uint8_t set_ind_atomic(uint64_t ind_loc, uint8_t to_be_set)
 {
-    uint8_t ind_old, ind_new;
+    uint8_t expected, actual;
     hwaddr len = 1;
-    uint8_t *ind_addr;
+    /* avoid  multiple fetches */
+    uint8_t volatile *ind_addr;
 
     ind_addr = cpu_physical_memory_map(ind_loc, &len, true);
     if (!ind_addr) {
         s390_pci_generate_error_event(ERR_EVENT_AIRERR, 0, 0, 0, 0);
         return -1;
     }
+    actual = *ind_addr;
     do {
-        ind_old = *ind_addr;
-        ind_new = ind_old | to_be_set;
-    } while (atomic_cmpxchg(ind_addr, ind_old, ind_new) != ind_old);
-    cpu_physical_memory_unmap(ind_addr, len, 1, len);
+        expected = actual;
+        actual = atomic_cmpxchg(ind_addr, expected, expected | to_be_set);
+    } while (actual != expected);
+    cpu_physical_memory_unmap((void *)ind_addr, len, 1, len);
 
-    return ind_old;
+    return actual;
 }
 
 static void s390_msi_ctrl_write(void *opaque, hwaddr addr, uint64_t data,
-- 
2.17.1

On 16.06.20 06:50, Halil Pasic wrote:
> The atomic_cmpxchg() loop is broken because we occasionally end up with
> old and _old having different values (a legit compiler can generate code
> that accessed *ind_addr again to pick up a value for _old instead of
> using the value of old that was already fetched according to the
> rules of the abstract machine). This means the underlying CS instruction
> may use a different old (_old) than the one we intended to use if
> atomic_cmpxchg() performed the xchg part.
> 
> Let us use volatile to force the rules of the abstract machine for
> accesses to *ind_addr. Let us also rewrite the loop so, we that the
> new old is used to compute the new desired value if the xchg part
> is not performed.
> 
> Signed-off-by: Halil Pasic <pasic@linux.ibm.com>
> Fixes: 8cba80c3a0 ("s390: Add PCI bus support")
> Reported-by: Christian Borntraeger <borntraeger@de.ibm.com>

Reviewed-by: Christian Borntraeger <borntraeger@de.ibm.com>

> ---
>  hw/s390x/s390-pci-bus.c | 16 +++++++++-------
>  1 file changed, 9 insertions(+), 7 deletions(-)
> 
> diff --git a/hw/s390x/s390-pci-bus.c b/hw/s390x/s390-pci-bus.c
> index c4a4259f0c..80eb957a91 100644
> --- a/hw/s390x/s390-pci-bus.c
> +++ b/hw/s390x/s390-pci-bus.c
> @@ -637,22 +637,24 @@ static AddressSpace *s390_pci_dma_iommu(PCIBus *bus, void *opaque, int devfn)
>  
>  static uint8_t set_ind_atomic(uint64_t ind_loc, uint8_t to_be_set)
>  {
> -    uint8_t ind_old, ind_new;
> +    uint8_t expected, actual;
>      hwaddr len = 1;
> -    uint8_t *ind_addr;
> +    /* avoid  multiple fetches */
> +    uint8_t volatile *ind_addr;
>  
>      ind_addr = cpu_physical_memory_map(ind_loc, &len, true);
>      if (!ind_addr) {
>          s390_pci_generate_error_event(ERR_EVENT_AIRERR, 0, 0, 0, 0);
>          return -1;
>      }
> +    actual = *ind_addr;
>      do {
> -        ind_old = *ind_addr;
> -        ind_new = ind_old | to_be_set;
> -    } while (atomic_cmpxchg(ind_addr, ind_old, ind_new) != ind_old);
> -    cpu_physical_memory_unmap(ind_addr, len, 1, len);
> +        expected = actual;
> +        actual = atomic_cmpxchg(ind_addr, expected, expected | to_be_set);
> +    } while (actual != expected);
> +    cpu_physical_memory_unmap((void *)ind_addr, len, 1, len);
>  
> -    return ind_old;
> +    return actual;
>  }
>  
>  static void s390_msi_ctrl_write(void *opaque, hwaddr addr, uint64_t data,
>