dmaengine: fix use-after-free in dma_chan_put() and dma_release_channel()grafted

When dma_device_put() drops the last reference on chan->device->ref,
dma_device_release() runs and may free the dma_device along with its
channels.

dma_chan_put() then still reads chan->device->owner via
dma_chan_to_owner() for the trailing module_put(). KASAN catches it:

	slab-use-after-free in dma_chan_put+0x3e6/0x4c0
	Read of size 8 by task insmod/6319
	Freed by task 6319:
	  kfree+0x225/0x470
	  dma_chan_put+0x395/0x4c0
	  dmaengine_put+0xf8/0x160

Cache the module owner in dma_chan_put() before the put so the trailing
module_put() does not need chan->device.

Fixes: 8ad342a86359 ("dmaengine: Add reference counting to dma_device struct")
Suggested-by: Sashiko <sashiko-bot@kernel.org>
Link: https://sashiko.dev/#/patchset/20260518-dmaengine-kref-fix-v1-1-4d6125048fb7@amd.com
Reviewed-by: Frank Li <Frank.Li@nxp.com>
Reviewed-by: Logan Gunthorpe <logang@deltatee.com>
Signed-off-by: Shivank Garg <shivankg@amd.com>
Link: https://patch.msgid.link/20260822-dmaengine-kref-fix-v5-3-d4a4ee47d927@amd.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>

1 files changed, 148 insertions, 0 deletions

diff --git a/tools/memory-model/linux-kernel.def b/tools/memory-model/linux-kernel.def
new file mode 100644
index 000000000..49e402782
--- /dev/null
+++ b/tools/memory-model/linux-kernel.def
@@ -0,0 +1,148 @@
+// SPDX-License-Identifier: GPL-2.0+
+//
+// An earlier version of this file appeared in the companion webpage for
+// "Frightening small children and disconcerting grown-ups: Concurrency
+// in the Linux kernel" by Alglave, Maranget, McKenney, Parri, and Stern,
+// which appeared in ASPLOS 2018.
+
+// ONCE
+READ_ONCE(X) __load{ONCE}(X)
+WRITE_ONCE(X,V) { __store{ONCE}(X,V); }
+
+// Release Acquire and friends
+smp_store_release(X,V) { __store{RELEASE}(*X,V); }
+smp_load_acquire(X) __load{ACQUIRE}(*X)
+rcu_assign_pointer(X,V) { __store{RELEASE}(X,V); }
+rcu_dereference(X) __load{ONCE}(X)
+smp_store_mb(X,V) { __store{ONCE}(X,V); __fence{MB}; }
+
+// Fences
+smp_mb() { __fence{MB}; }
+smp_rmb() { __fence{rmb}; }
+smp_wmb() { __fence{wmb}; }
+smp_mb__before_atomic() { __fence{before-atomic}; }
+smp_mb__after_atomic() { __fence{after-atomic}; }
+smp_mb__after_spinlock() { __fence{after-spinlock}; }
+smp_mb__after_unlock_lock() { __fence{after-unlock-lock}; }
+smp_mb__after_srcu_read_unlock() { __fence{after-srcu-read-unlock}; }
+barrier() { __fence{barrier}; }
+
+// Exchange
+xchg(X,V)  __xchg{MB}(X,V)
+xchg_relaxed(X,V) __xchg{ONCE}(X,V)
+xchg_release(X,V) __xchg{RELEASE}(X,V)
+xchg_acquire(X,V) __xchg{ACQUIRE}(X,V)
+cmpxchg(X,V,W) __cmpxchg{MB}(X,V,W)
+cmpxchg_relaxed(X,V,W) __cmpxchg{ONCE}(X,V,W)
+cmpxchg_acquire(X,V,W) __cmpxchg{ACQUIRE}(X,V,W)
+cmpxchg_release(X,V,W) __cmpxchg{RELEASE}(X,V,W)
+
+// Spinlocks
+spin_lock(X) { __lock(X); }
+spin_unlock(X) { __unlock(X); }
+spin_trylock(X) __trylock(X)
+spin_is_locked(X) __islocked(X)
+
+// RCU
+rcu_read_lock() { __fence{rcu-lock}; }
+rcu_read_unlock() { __fence{rcu-unlock}; }
+synchronize_rcu() { __fence{sync-rcu}; }
+synchronize_rcu_expedited() { __fence{sync-rcu}; }
+
+// SRCU
+srcu_read_lock(X) __load{srcu-lock}(*X)
+srcu_read_unlock(X,Y) { __store{srcu-unlock}(*X,Y); }
+srcu_down_read(X) __load{srcu-lock}(*X)
+srcu_up_read(X,Y) { __store{srcu-unlock}(*X,Y); }
+synchronize_srcu(X)  { __srcu{sync-srcu}(X); }
+synchronize_srcu_expedited(X)  { __srcu{sync-srcu}(X); }
+
+// Atomic
+atomic_read(X) READ_ONCE(*X)
+atomic_set(X,V) { WRITE_ONCE(*X,V); }
+atomic_read_acquire(X) smp_load_acquire(X)
+atomic_set_release(X,V) { smp_store_release(X,V); }
+
+atomic_add(V,X) { __atomic_op{NORETURN}(X,+,V); }
+atomic_sub(V,X) { __atomic_op{NORETURN}(X,-,V); }
+atomic_and(V,X) { __atomic_op{NORETURN}(X,&,V); }
+atomic_or(V,X)  { __atomic_op{NORETURN}(X,|,V); }
+atomic_xor(V,X) { __atomic_op{NORETURN}(X,^,V); }
+atomic_inc(X)   { __atomic_op{NORETURN}(X,+,1); }
+atomic_dec(X)   { __atomic_op{NORETURN}(X,-,1); }
+atomic_andnot(V,X) { __atomic_op{NORETURN}(X,&~,V); }
+
+atomic_add_return(V,X) __atomic_op_return{MB}(X,+,V)
+atomic_add_return_relaxed(V,X) __atomic_op_return{ONCE}(X,+,V)
+atomic_add_return_acquire(V,X) __atomic_op_return{ACQUIRE}(X,+,V)
+atomic_add_return_release(V,X) __atomic_op_return{RELEASE}(X,+,V)
+atomic_fetch_add(V,X) __atomic_fetch_op{MB}(X,+,V)
+atomic_fetch_add_relaxed(V,X) __atomic_fetch_op{ONCE}(X,+,V)
+atomic_fetch_add_acquire(V,X) __atomic_fetch_op{ACQUIRE}(X,+,V)
+atomic_fetch_add_release(V,X) __atomic_fetch_op{RELEASE}(X,+,V)
+
+atomic_fetch_and(V,X) __atomic_fetch_op{MB}(X,&,V)
+atomic_fetch_and_relaxed(V,X) __atomic_fetch_op{ONCE}(X,&,V)
+atomic_fetch_and_acquire(V,X) __atomic_fetch_op{ACQUIRE}(X,&,V)
+atomic_fetch_and_release(V,X) __atomic_fetch_op{RELEASE}(X,&,V)
+
+atomic_fetch_or(V,X) __atomic_fetch_op{MB}(X,|,V)
+atomic_fetch_or_relaxed(V,X) __atomic_fetch_op{ONCE}(X,|,V)
+atomic_fetch_or_acquire(V,X) __atomic_fetch_op{ACQUIRE}(X,|,V)
+atomic_fetch_or_release(V,X) __atomic_fetch_op{RELEASE}(X,|,V)
+
+atomic_fetch_xor(V,X) __atomic_fetch_op{MB}(X,^,V)
+atomic_fetch_xor_relaxed(V,X) __atomic_fetch_op{ONCE}(X,^,V)
+atomic_fetch_xor_acquire(V,X) __atomic_fetch_op{ACQUIRE}(X,^,V)
+atomic_fetch_xor_release(V,X) __atomic_fetch_op{RELEASE}(X,^,V)
+
+atomic_inc_return(X) __atomic_op_return{MB}(X,+,1)
+atomic_inc_return_relaxed(X) __atomic_op_return{ONCE}(X,+,1)
+atomic_inc_return_acquire(X) __atomic_op_return{ACQUIRE}(X,+,1)
+atomic_inc_return_release(X) __atomic_op_return{RELEASE}(X,+,1)
+atomic_fetch_inc(X) __atomic_fetch_op{MB}(X,+,1)
+atomic_fetch_inc_relaxed(X) __atomic_fetch_op{ONCE}(X,+,1)
+atomic_fetch_inc_acquire(X) __atomic_fetch_op{ACQUIRE}(X,+,1)
+atomic_fetch_inc_release(X) __atomic_fetch_op{RELEASE}(X,+,1)
+
+atomic_sub_return(V,X) __atomic_op_return{MB}(X,-,V)
+atomic_sub_return_relaxed(V,X) __atomic_op_return{ONCE}(X,-,V)
+atomic_sub_return_acquire(V,X) __atomic_op_return{ACQUIRE}(X,-,V)
+atomic_sub_return_release(V,X) __atomic_op_return{RELEASE}(X,-,V)
+atomic_fetch_sub(V,X) __atomic_fetch_op{MB}(X,-,V)
+atomic_fetch_sub_relaxed(V,X) __atomic_fetch_op{ONCE}(X,-,V)
+atomic_fetch_sub_acquire(V,X) __atomic_fetch_op{ACQUIRE}(X,-,V)
+atomic_fetch_sub_release(V,X) __atomic_fetch_op{RELEASE}(X,-,V)
+
+atomic_dec_return(X) __atomic_op_return{MB}(X,-,1)
+atomic_dec_return_relaxed(X) __atomic_op_return{ONCE}(X,-,1)
+atomic_dec_return_acquire(X) __atomic_op_return{ACQUIRE}(X,-,1)
+atomic_dec_return_release(X) __atomic_op_return{RELEASE}(X,-,1)
+atomic_fetch_dec(X) __atomic_fetch_op{MB}(X,-,1)
+atomic_fetch_dec_relaxed(X) __atomic_fetch_op{ONCE}(X,-,1)
+atomic_fetch_dec_acquire(X) __atomic_fetch_op{ACQUIRE}(X,-,1)
+atomic_fetch_dec_release(X) __atomic_fetch_op{RELEASE}(X,-,1)
+
+atomic_xchg(X,V) __xchg{MB}(X,V)
+atomic_xchg_relaxed(X,V) __xchg{ONCE}(X,V)
+atomic_xchg_release(X,V) __xchg{RELEASE}(X,V)
+atomic_xchg_acquire(X,V) __xchg{ACQUIRE}(X,V)
+atomic_cmpxchg(X,V,W) __cmpxchg{MB}(X,V,W)
+atomic_cmpxchg_relaxed(X,V,W) __cmpxchg{ONCE}(X,V,W)
+atomic_cmpxchg_acquire(X,V,W) __cmpxchg{ACQUIRE}(X,V,W)
+atomic_cmpxchg_release(X,V,W) __cmpxchg{RELEASE}(X,V,W)
+
+atomic_sub_and_test(V,X) __atomic_op_return{MB}(X,-,V) == 0
+atomic_dec_and_test(X)  __atomic_op_return{MB}(X,-,1) == 0
+atomic_inc_and_test(X)  __atomic_op_return{MB}(X,+,1) == 0
+atomic_add_negative(V,X) __atomic_op_return{MB}(X,+,V) < 0
+atomic_add_negative_relaxed(V,X) __atomic_op_return{ONCE}(X,+,V) < 0
+atomic_add_negative_acquire(V,X) __atomic_op_return{ACQUIRE}(X,+,V) < 0
+atomic_add_negative_release(V,X) __atomic_op_return{RELEASE}(X,+,V) < 0
+
+atomic_fetch_andnot(V,X) __atomic_fetch_op{MB}(X,&~,V)
+atomic_fetch_andnot_acquire(V,X) __atomic_fetch_op{ACQUIRE}(X,&~,V)
+atomic_fetch_andnot_release(V,X) __atomic_fetch_op{RELEASE}(X,&~,V)
+atomic_fetch_andnot_relaxed(V,X) __atomic_fetch_op{ONCE}(X,&~,V)
+
+atomic_add_unless(X,V,W) __atomic_add_unless{MB}(X,V,W)