Hi Alex, Generally, this looks good, but I do have a comment below...
On Thursday, 2023-01-19 at 02:00:02 -05, Alexander Bulekov wrote: > 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-jva6w38lk4hjowae5kcknhprd5fp...@mail.gmail.com > > Resolves: https://gitlab.com/qemu-project/qemu/-/issues/62 > Resolves: https://gitlab.com/qemu-project/qemu/-/issues/540 > Resolves: https://gitlab.com/qemu-project/qemu/-/issues/541 > Resolves: https://gitlab.com/qemu-project/qemu/-/issues/556 > Resolves: https://gitlab.com/qemu-project/qemu/-/issues/557 > Resolves: https://gitlab.com/qemu-project/qemu/-/issues/827 > Signed-off-by: Alexander Bulekov <alx...@bu.edu> > --- > include/hw/qdev-core.h | 7 +++++++ > softmmu/memory.c | 15 +++++++++++++++ > softmmu/trace-events | 1 + > 3 files changed, 23 insertions(+) > > diff --git a/include/hw/qdev-core.h b/include/hw/qdev-core.h > index 35fddb19a6..8858195262 100644 > --- a/include/hw/qdev-core.h > +++ b/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 { > diff --git a/softmmu/memory.c b/softmmu/memory.c > index e05332d07f..90ffaaa4f5 100644 > --- a/softmmu/memory.c > +++ b/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 +543,17 @@ 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); I don't know how likely this is to happen, but according to: - https://qemu-project.gitlab.io/qemu/devel/qom.html#c.object_dynamic_cast it is possible for the object_dynamic_cast() function to return NULL, so it might make sense to wrap the subsequent calls in a test of dev != NULL. Thanks, Darren. > + 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 +568,9 @@ static MemTxResult access_with_adjusted_size(hwaddr addr, > access_mask, attrs); > } > } > + if (dev) { > + dev->mem_reentrancy_guard.engaged_in_io = false; > + } > return r; > } > > diff --git a/softmmu/trace-events b/softmmu/trace-events > index 22606dc27b..62d04ea9a7 100644 > --- a/softmmu/trace-events > +++ b/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)" > -- > 2.39.0
