qemu-kvm/kvm-memory-prevent-dma-reentracy-issues.patch

From e0c811c2d13f995fe1b095f48637316be5978b0e Mon Sep 17 00:00:00 2001
From: Jon Maloy <jmaloy@redhat.com>
Date: Tue, 9 May 2023 10:29:03 -0400
Subject: [PATCH 01/15] memory: prevent dma-reentracy issues

RH-Author: Jon Maloy <jmaloy@redhat.com>
RH-MergeRequest: 277: memory: prevent dma-reentracy issues
RH-Bugzilla: 1999236
RH-Acked-by: Thomas Huth <thuth@redhat.com>
RH-Acked-by: Miroslav Rezanina <mrezanin@redhat.com>
RH-Commit: [1/12] 8fced41b4b2105343e8f0250286b771bcb43c81f (redhat/rhel/src/qemu-kvm/jons-qemu-kvm-2)

Bugzilla: https://bugzilla.redhat.com/show_bug.cgi?id=1999236
Upstream: Merged
CVE: CVE-2021-3750
CVE: CVE-2023-0330

commit a2e1753b8054344f32cf94f31c6399a58794a380
Author: Alexander Bulekov <alxndr@bu.edu>
Date:   Thu Apr 27 17:10:06 2023 -0400

    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
    Resolves: CVE-2023-0330

    Signed-off-by: Alexander Bulekov <alxndr@bu.edu>
    Reviewed-by: Thomas Huth <thuth@redhat.com>
    Message-Id: <20230427211013.2994127-2-alxndr@bu.edu>
    [thuth: Replace warn_report() with warn_report_once()]
    Signed-off-by: Thomas Huth <thuth@redhat.com>

Signed-off-by: Jon Maloy <jmaloy@redhat.com>
---
 include/exec/memory.h  |  5 +++++
 include/hw/qdev-core.h |  7 +++++++
 softmmu/memory.c       | 16 ++++++++++++++++
 3 files changed, 28 insertions(+)

diff --git a/include/exec/memory.h b/include/exec/memory.h
index 20f1b27377..e089f90f9b 100644
--- a/include/exec/memory.h
+++ b/include/exec/memory.h
@@ -734,6 +734,8 @@ struct MemoryRegion {
     bool is_iommu;
     RAMBlock *ram_block;
     Object *owner;
+    /* owner as TYPE_DEVICE. Used for re-entrancy checks in MR access hotpath */
+    DeviceState *dev;
 
     const MemoryRegionOps *ops;
     void *opaque;
@@ -757,6 +759,9 @@ struct MemoryRegion {
     unsigned ioeventfd_nb;
     MemoryRegionIoeventfd *ioeventfds;
     RamDiscardManager *rdm; /* Only for RAM */
+
+    /* For devices designed to perform re-entrant IO into their own IO MRs */
+    bool disable_reentrancy_guard;
 };
 
 struct IOMMUMemoryRegion {
diff --git a/include/hw/qdev-core.h b/include/hw/qdev-core.h
index 20d3066595..14226f860d 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.
@@ -193,6 +197,9 @@ 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 */
+    MemReentrancyGuard mem_reentrancy_guard;
 };
 
 struct DeviceListener {
diff --git a/softmmu/memory.c b/softmmu/memory.c
index 7340e19ff5..102f0a4248 100644
--- a/softmmu/memory.c
+++ b/softmmu/memory.c
@@ -541,6 +541,18 @@ static MemTxResult access_with_adjusted_size(hwaddr addr,
         access_size_max = 4;
     }
 
+    /* Do not allow more than one simultaneous access to a device's IO Regions */
+    if (mr->dev && !mr->disable_reentrancy_guard &&
+        !mr->ram_device && !mr->ram && !mr->rom_device && !mr->readonly) {
+        if (mr->dev->mem_reentrancy_guard.engaged_in_io) {
+            warn_report_once("Blocked re-entrant IO on MemoryRegion: "
+                             "%s at addr: 0x%" HWADDR_PRIX,
+                             memory_region_name(mr), addr);
+            return MEMTX_ACCESS_ERROR;
+        }
+        mr->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);
@@ -555,6 +567,9 @@ static MemTxResult access_with_adjusted_size(hwaddr addr,
                         access_mask, attrs);
         }
     }
+    if (mr->dev) {
+        mr->dev->mem_reentrancy_guard.engaged_in_io = false;
+    }
     return r;
 }
 
@@ -1169,6 +1184,7 @@ static void memory_region_do_init(MemoryRegion *mr,
     }
     mr->name = g_strdup(name);
     mr->owner = owner;
+    mr->dev = (DeviceState *) object_dynamic_cast(mr->owner, TYPE_DEVICE);
     mr->ram_block = NULL;
 
     if (name) {
-- 
2.37.3