Re: [PATCH v2] memory: prevent dma-reentracy issues

[Alexander Bulekov]

On 220609 0958, 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-JVA6W38LK4hJoWae5KcknhPRD5fPBZA@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 <alxndr@bu.edu>
> ---
>  include/hw/pci/pci.h   | 13 +++++++++++--
>  include/hw/qdev-core.h |  3 +++
>  softmmu/dma-helpers.c  | 12 ++++++++++++
>  softmmu/memory.c       | 15 +++++++++++++++
>  softmmu/trace-events   |  1 +
>  5 files changed, 42 insertions(+), 2 deletions(-)
> 
> diff --git a/include/hw/pci/pci.h b/include/hw/pci/pci.h
> index 44dacfa224..ab1ad0f7a8 100644
> --- a/include/hw/pci/pci.h
> +++ b/include/hw/pci/pci.h
> @@ -834,8 +834,17 @@ static inline MemTxResult pci_dma_rw(PCIDevice *dev, 
> dma_addr_t addr,
>                                       void *buf, dma_addr_t len,
>                                       DMADirection dir, MemTxAttrs attrs)
>  {
> -    return dma_memory_rw(pci_get_address_space(dev), addr, buf, len,
> -                         dir, attrs);
> +    bool prior_engaged_state;
> +    MemTxResult result;
> +
> +    prior_engaged_state = dev->qdev.engaged_in_io;
> +
> +    dev->qdev.engaged_in_io = true;
> +    result = dma_memory_rw(pci_get_address_space(dev), addr, buf, len,
> +                           dir, attrs);
> +    dev->qdev.engaged_in_io = prior_engaged_state;
> +
> +    return result;
>  }
>  
>  /**
> diff --git a/include/hw/qdev-core.h b/include/hw/qdev-core.h
> index 92c3d65208..6474dc51fa 100644
> --- a/include/hw/qdev-core.h
> +++ b/include/hw/qdev-core.h
> @@ -193,6 +193,9 @@ struct DeviceState {
>      int instance_id_alias;
>      int alias_required_for_version;
>      ResettableState reset;
> +
> +    /* Is the device currently in mmio/pio/dma? Used to prevent re-entrancy 
> */
> +    int engaged_in_io;
>  };
>  
>  struct DeviceListener {
> diff --git a/softmmu/dma-helpers.c b/softmmu/dma-helpers.c
> index 7820fec54c..7a4f1fb9b3 100644
> --- a/softmmu/dma-helpers.c
> +++ b/softmmu/dma-helpers.c
> @@ -288,8 +288,16 @@ static MemTxResult dma_buf_rw(void *buf, dma_addr_t len, 
> dma_addr_t *residual,
>      uint8_t *ptr = buf;
>      dma_addr_t xresidual;
>      int sg_cur_index;
> +    DeviceState *dev;
> +    bool prior_engaged_state;
>      MemTxResult res = MEMTX_OK;
>  
> +    dev = sg->dev;
> +    if (dev) {
> +        prior_engaged_state = dev->engaged_in_io;
> +        dev->engaged_in_io = true;
> +    }
> +
>      xresidual = sg->size;
>      sg_cur_index = 0;
>      len = MIN(len, xresidual);
> @@ -302,6 +310,10 @@ static MemTxResult dma_buf_rw(void *buf, dma_addr_t len, 
> dma_addr_t *residual,
>          xresidual -= xfer;
>      }
>  
> +    if (dev) {
> +        dev->engaged_in_io = prior_engaged_state;
> +    }
> +
>      if (residual) {
>          *residual = xresidual;
>      }
> diff --git a/softmmu/memory.c b/softmmu/memory.c
> index 7ba2048836..44a14bb4f5 100644
> --- a/softmmu/memory.c
> +++ b/softmmu/memory.c
> @@ -532,6 +532,7 @@ 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) {
> @@ -541,6 +542,17 @@ 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);
> +        if (dev->engaged_in_io) {
> +            trace_memory_region_reentrant_io(get_cpu_index(), mr, addr, 
> size);
> +            return MEMTX_ERROR;
> +        }
> +        dev->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);
> @@ -555,6 +567,9 @@ static MemTxResult access_with_adjusted_size(hwaddr addr,
>                          access_mask, attrs);
>          }
>      }
> +    if (dev) {
> +        dev->engaged_in_io = false;
> +    }
>      return r;
>  }
>  
> diff --git a/softmmu/trace-events b/softmmu/trace-events
> index 9c88887b3c..d7228316db 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)"
> -- 
> 2.33.0
> 

ping