memory: prevent dma-reentracy issues

Add a flag to the DeviceState, when a device is engaged in PIO/MMIO/DMA.
This flag is set/checked prior to calling a device's MemoryRegion
handlers, and set when device code initiates DMA.  The purpose of this
flag is to prevent two types of DMA-based reentrancy issues:

1.) mmio -> dma -> mmio case
2.) bh -> dma write -> mmio case

These issues have led to problems such as stack-exhaustion and
use-after-frees.

Summary of the problem from Peter Maydell:
https://lore.kernel.org/qemu-devel/CAFEAcA_23vc7hE3iaM-JVA6W38LK4hJoWae5KcknhPRD5fPBZA@mail.gmail.com

Resolves: qemu-project/qemu#62
Resolves: qemu-project/qemu#540
Resolves: qemu-project/qemu#541
Resolves: qemu-project/qemu#556
Resolves: qemu-project/qemu#557
Resolves: qemu-project/qemu#827
Resolves: qemu-project/qemu#1282



Signed-off-by: Alexander Bulekov <alxndr@bu.edu>
Reviewed-by: Darren Kenny <darren.kenny@oracle.com>
Reviewed-by: Stefan Hajnoczi <stefanha@redhat.com>
Acked-by: Peter Xu <peterx@redhat.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Message-Id: <20230205040737.3567731-2-alxndr@bu.edu>
Signed-off-by: Thomas Huth <thuth@redhat.com>

include/hw/qdev-core.h

@@ -162,6 +162,10 @@ struct NamedClockList {
     QLIST_ENTRY(NamedClockList) node;
 };
 
+typedef struct {
+    bool engaged_in_io;
+} MemReentrancyGuard;
+
 /**
  * DeviceState:
  * @realized: Indicates whether the device has been fully constructed.
@@ -194,6 +198,9 @@ struct DeviceState {
     int alias_required_for_version;
     ResettableState reset;
     GSList *unplug_blockers;
+
+    /* Is the device currently in mmio/pio/dma? Used to prevent re-entrancy */
+    MemReentrancyGuard mem_reentrancy_guard;
 };
 
 struct DeviceListener {

softmmu/memory.c

@@ -533,6 +533,7 @@ static MemTxResult access_with_adjusted_size(hwaddr addr,
     uint64_t access_mask;
     unsigned access_size;
     unsigned i;
+    DeviceState *dev = NULL;
     MemTxResult r = MEMTX_OK;
 
     if (!access_size_min) {
@@ -542,6 +543,19 @@ static MemTxResult access_with_adjusted_size(hwaddr addr,
         access_size_max = 4;
     }
 
+    /* Do not allow more than one simultanous access to a device's IO Regions */
+    if (mr->owner &&
+        !mr->ram_device && !mr->ram && !mr->rom_device && !mr->readonly) {
+        dev = (DeviceState *) object_dynamic_cast(mr->owner, TYPE_DEVICE);
+        if (dev) {
+            if (dev->mem_reentrancy_guard.engaged_in_io) {
+                trace_memory_region_reentrant_io(get_cpu_index(), mr, addr, size);
+                return MEMTX_ERROR;
+            }
+            dev->mem_reentrancy_guard.engaged_in_io = true;
+        }
+    }
+
     /* FIXME: support unaligned access? */
     access_size = MAX(MIN(size, access_size_max), access_size_min);
     access_mask = MAKE_64BIT_MASK(0, access_size * 8);
@@ -556,6 +570,9 @@ static MemTxResult access_with_adjusted_size(hwaddr addr,
                         access_mask, attrs);
         }
     }
+    if (dev) {
+        dev->mem_reentrancy_guard.engaged_in_io = false;
+    }
     return r;
 }
 

softmmu/trace-events

@@ -13,6 +13,7 @@ memory_region_ops_read(int cpu_index, void *mr, uint64_t addr, uint64_t value, u
 memory_region_ops_write(int cpu_index, void *mr, uint64_t addr, uint64_t value, unsigned size, const char *name) "cpu %d mr %p addr 0x%"PRIx64" value 0x%"PRIx64" size %u name '%s'"
 memory_region_subpage_read(int cpu_index, void *mr, uint64_t offset, uint64_t value, unsigned size) "cpu %d mr %p offset 0x%"PRIx64" value 0x%"PRIx64" size %u"
 memory_region_subpage_write(int cpu_index, void *mr, uint64_t offset, uint64_t value, unsigned size) "cpu %d mr %p offset 0x%"PRIx64" value 0x%"PRIx64" size %u"
+memory_region_reentrant_io(int cpu_index, void *mr, uint64_t offset, unsigned size) "cpu %d mr %p offset 0x%"PRIx64" size %u"
 memory_region_ram_device_read(int cpu_index, void *mr, uint64_t addr, uint64_t value, unsigned size) "cpu %d mr %p addr 0x%"PRIx64" value 0x%"PRIx64" size %u"
 memory_region_ram_device_write(int cpu_index, void *mr, uint64_t addr, uint64_t value, unsigned size) "cpu %d mr %p addr 0x%"PRIx64" value 0x%"PRIx64" size %u"
 memory_region_sync_dirty(const char *mr, const char *listener, int global) "mr '%s' listener '%s' synced (global=%d)"