[pve-devel] [PATCH qemu] add patch fixing DMA reentrancy issues

Fiona Ebner f.ebner at proxmox.com
Tue Feb 21 10:08:59 CET 2023


that could lead to use-after-frees and stack overflows with a
malicious (or buggy) guest. See [0] for a good summary:

[0]: https://lore.kernel.org/qemu-devel/CAFEAcA_23vc7hE3iaM-JVA6W38LK4hJoWae5KcknhPRD5fPBZA@mail.gmail.com

Signed-off-by: Fiona Ebner <f.ebner at proxmox.com>
---
 ...-memory-prevent-dma-reentracy-issues.patch | 118 ++++++++++++++++++
 debian/patches/series                         |   1 +
 2 files changed, 119 insertions(+)
 create mode 100644 debian/patches/extra/0008-memory-prevent-dma-reentracy-issues.patch

diff --git a/debian/patches/extra/0008-memory-prevent-dma-reentracy-issues.patch b/debian/patches/extra/0008-memory-prevent-dma-reentracy-issues.patch
new file mode 100644
index 0000000..4f3af9a
--- /dev/null
+++ b/debian/patches/extra/0008-memory-prevent-dma-reentracy-issues.patch
@@ -0,0 +1,118 @@
+From 0000000000000000000000000000000000000000 Mon Sep 17 00:00:00 2001
+From: Alexander Bulekov <alxndr at bu.edu>
+Date: Sat, 4 Feb 2023 23:07:34 -0500
+Subject: [PATCH] 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: 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
+Resolves: https://gitlab.com/qemu-project/qemu/-/issues/1282
+
+Reviewed-by: Darren Kenny <darren.kenny at oracle.com>
+Reviewed-by: Stefan Hajnoczi <stefanha at redhat.com>
+Signed-off-by: Alexander Bulekov <alxndr at bu.edu>
+Acked-by: Peter Xu <peterx at redhat.com>
+(picked-up from https://lists.nongnu.org/archive/html/qemu-devel/2023-02/msg01142.html)
+Signed-off-by: Fiona Ebner <f.ebner at proxmox.com>
+---
+ include/hw/qdev-core.h |  7 +++++++
+ softmmu/memory.c       | 17 +++++++++++++++++
+ softmmu/trace-events   |  1 +
+ 3 files changed, 25 insertions(+)
+
+diff --git a/include/hw/qdev-core.h b/include/hw/qdev-core.h
+index 785dd5a56e..886f6bb79e 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 bc0be3f62c..7dcb3347aa 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 +543,19 @@ 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;
+ }
+ 
+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)"
diff --git a/debian/patches/series b/debian/patches/series
index 06c775f..3ecc9d9 100644
--- a/debian/patches/series
+++ b/debian/patches/series
@@ -5,6 +5,7 @@ extra/0004-virtio-mem-Fix-the-iterator-variable-in-a-vmem-rdl_l.patch
 extra/0005-vhost-fix-vq-dirty-bitmap-syncing-when-vIOMMU-is-ena.patch
 extra/0006-virtio-rng-pci-fix-migration-compat-for-vectors.patch
 extra/0007-block-fix-detect-zeroes-with-BDRV_REQ_REGISTERED_BUF.patch
+extra/0008-memory-prevent-dma-reentracy-issues.patch
 bitmap-mirror/0001-drive-mirror-add-support-for-sync-bitmap-mode-never.patch
 bitmap-mirror/0002-drive-mirror-add-support-for-conditional-and-always-.patch
 bitmap-mirror/0003-mirror-add-check-for-bitmap-mode-without-bitmap.patch
-- 
2.30.2






More information about the pve-devel mailing list