summaryrefslogtreecommitdiffstats
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2022-01-11 18:51:26 +0100
committerLinus Torvalds <torvalds@linux-foundation.org>2022-01-11 18:51:26 +0100
commit1be5bdf8cd5a194d981e65687367b0828c839c37 (patch)
treed6560826c211fd7a4ddcc1d45040dab123271df8
parentMerge tag 'lkmm.2022.01.09a' of git://git.kernel.org/pub/scm/linux/kernel/git... (diff)
parentkcsan: Only test clear_bit_unlock_is_negative_byte if arch defines it (diff)
downloadlinux-1be5bdf8cd5a194d981e65687367b0828c839c37.tar.xz
linux-1be5bdf8cd5a194d981e65687367b0828c839c37.zip
Merge tag 'kcsan.2022.01.09a' of git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu
Pull KCSAN updates from Paul McKenney: "This provides KCSAN fixes and also the ability to take memory barriers into account for weakly-ordered systems. This last can increase the probability of detecting certain types of data races" * tag 'kcsan.2022.01.09a' of git://git.kernel.org/pub/scm/linux/kernel/git/paulmck/linux-rcu: (29 commits) kcsan: Only test clear_bit_unlock_is_negative_byte if arch defines it kcsan: Avoid nested contexts reading inconsistent reorder_access kcsan: Turn barrier instrumentation into macros kcsan: Make barrier tests compatible with lockdep kcsan: Support WEAK_MEMORY with Clang where no objtool support exists compiler_attributes.h: Add __disable_sanitizer_instrumentation objtool, kcsan: Remove memory barrier instrumentation from noinstr objtool, kcsan: Add memory barrier instrumentation to whitelist sched, kcsan: Enable memory barrier instrumentation mm, kcsan: Enable barrier instrumentation x86/qspinlock, kcsan: Instrument barrier of pv_queued_spin_unlock() x86/barriers, kcsan: Use generic instrumentation for non-smp barriers asm-generic/bitops, kcsan: Add instrumentation for barriers locking/atomics, kcsan: Add instrumentation for barriers locking/barriers, kcsan: Support generic instrumentation locking/barriers, kcsan: Add instrumentation for barriers kcsan: selftest: Add test case to check memory barrier instrumentation kcsan: Ignore GCC 11+ warnings about TSan runtime support kcsan: test: Add test cases for memory barrier instrumentation kcsan: test: Match reordered or normal accesses ...
-rw-r--r--Documentation/dev-tools/kcsan.rst76
-rw-r--r--arch/x86/include/asm/barrier.h10
-rw-r--r--arch/x86/include/asm/qspinlock.h1
-rw-r--r--include/asm-generic/barrier.h54
-rw-r--r--include/asm-generic/bitops/instrumented-atomic.h3
-rw-r--r--include/asm-generic/bitops/instrumented-lock.h3
-rw-r--r--include/linux/atomic/atomic-instrumented.h135
-rw-r--r--include/linux/compiler_attributes.h18
-rw-r--r--include/linux/compiler_types.h13
-rw-r--r--include/linux/kcsan-checks.h83
-rw-r--r--include/linux/kcsan.h11
-rw-r--r--include/linux/sched.h3
-rw-r--r--include/linux/spinlock.h2
-rw-r--r--init/init_task.c5
-rw-r--r--kernel/kcsan/Makefile2
-rw-r--r--kernel/kcsan/core.c347
-rw-r--r--kernel/kcsan/kcsan_test.c426
-rw-r--r--kernel/kcsan/report.c51
-rw-r--r--kernel/kcsan/selftest.c143
-rw-r--r--kernel/sched/Makefile7
-rw-r--r--lib/Kconfig.kcsan20
-rw-r--r--mm/Makefile2
-rw-r--r--scripts/Makefile.kcsan15
-rw-r--r--scripts/Makefile.lib5
-rwxr-xr-xscripts/atomic/gen-atomic-instrumented.sh41
-rw-r--r--tools/objtool/check.c41
-rw-r--r--tools/objtool/include/objtool/elf.h2
27 files changed, 1347 insertions, 172 deletions
diff --git a/Documentation/dev-tools/kcsan.rst b/Documentation/dev-tools/kcsan.rst
index 7db43c7c09b8..3ae866dcc924 100644
--- a/Documentation/dev-tools/kcsan.rst
+++ b/Documentation/dev-tools/kcsan.rst
@@ -204,17 +204,17 @@ Ultimately this allows to determine the possible executions of concurrent code,
and if that code is free from data races.
KCSAN is aware of *marked atomic operations* (``READ_ONCE``, ``WRITE_ONCE``,
-``atomic_*``, etc.), but is oblivious of any ordering guarantees and simply
-assumes that memory barriers are placed correctly. In other words, KCSAN
-assumes that as long as a plain access is not observed to race with another
-conflicting access, memory operations are correctly ordered.
-
-This means that KCSAN will not report *potential* data races due to missing
-memory ordering. Developers should therefore carefully consider the required
-memory ordering requirements that remain unchecked. If, however, missing
-memory ordering (that is observable with a particular compiler and
-architecture) leads to an observable data race (e.g. entering a critical
-section erroneously), KCSAN would report the resulting data race.
+``atomic_*``, etc.), and a subset of ordering guarantees implied by memory
+barriers. With ``CONFIG_KCSAN_WEAK_MEMORY=y``, KCSAN models load or store
+buffering, and can detect missing ``smp_mb()``, ``smp_wmb()``, ``smp_rmb()``,
+``smp_store_release()``, and all ``atomic_*`` operations with equivalent
+implied barriers.
+
+Note, KCSAN will not report all data races due to missing memory ordering,
+specifically where a memory barrier would be required to prohibit subsequent
+memory operation from reordering before the barrier. Developers should
+therefore carefully consider the required memory ordering requirements that
+remain unchecked.
Race Detection Beyond Data Races
--------------------------------
@@ -268,6 +268,56 @@ marked operations, if all accesses to a variable that is accessed concurrently
are properly marked, KCSAN will never trigger a watchpoint and therefore never
report the accesses.
+Modeling Weak Memory
+~~~~~~~~~~~~~~~~~~~~
+
+KCSAN's approach to detecting data races due to missing memory barriers is
+based on modeling access reordering (with ``CONFIG_KCSAN_WEAK_MEMORY=y``).
+Each plain memory access for which a watchpoint is set up, is also selected for
+simulated reordering within the scope of its function (at most 1 in-flight
+access).
+
+Once an access has been selected for reordering, it is checked along every
+other access until the end of the function scope. If an appropriate memory
+barrier is encountered, the access will no longer be considered for simulated
+reordering.
+
+When the result of a memory operation should be ordered by a barrier, KCSAN can
+then detect data races where the conflict only occurs as a result of a missing
+barrier. Consider the example::
+
+ int x, flag;
+ void T1(void)
+ {
+ x = 1; // data race!
+ WRITE_ONCE(flag, 1); // correct: smp_store_release(&flag, 1)
+ }
+ void T2(void)
+ {
+ while (!READ_ONCE(flag)); // correct: smp_load_acquire(&flag)
+ ... = x; // data race!
+ }
+
+When weak memory modeling is enabled, KCSAN can consider ``x`` in ``T1`` for
+simulated reordering. After the write of ``flag``, ``x`` is again checked for
+concurrent accesses: because ``T2`` is able to proceed after the write of
+``flag``, a data race is detected. With the correct barriers in place, ``x``
+would not be considered for reordering after the proper release of ``flag``,
+and no data race would be detected.
+
+Deliberate trade-offs in complexity but also practical limitations mean only a
+subset of data races due to missing memory barriers can be detected. With
+currently available compiler support, the implementation is limited to modeling
+the effects of "buffering" (delaying accesses), since the runtime cannot
+"prefetch" accesses. Also recall that watchpoints are only set up for plain
+accesses, and the only access type for which KCSAN simulates reordering. This
+means reordering of marked accesses is not modeled.
+
+A consequence of the above is that acquire operations do not require barrier
+instrumentation (no prefetching). Furthermore, marked accesses introducing
+address or control dependencies do not require special handling (the marked
+access cannot be reordered, later dependent accesses cannot be prefetched).
+
Key Properties
~~~~~~~~~~~~~~
@@ -290,8 +340,8 @@ Key Properties
4. **Detects Racy Writes from Devices:** Due to checking data values upon
setting up watchpoints, racy writes from devices can also be detected.
-5. **Memory Ordering:** KCSAN is *not* explicitly aware of the LKMM's ordering
- rules; this may result in missed data races (false negatives).
+5. **Memory Ordering:** KCSAN is aware of only a subset of LKMM ordering rules;
+ this may result in missed data races (false negatives).
6. **Analysis Accuracy:** For observed executions, due to using a sampling
strategy, the analysis is *unsound* (false negatives possible), but aims to
diff --git a/arch/x86/include/asm/barrier.h b/arch/x86/include/asm/barrier.h
index 3ba772a69cc8..35389b2af88e 100644
--- a/arch/x86/include/asm/barrier.h
+++ b/arch/x86/include/asm/barrier.h
@@ -19,9 +19,9 @@
#define wmb() asm volatile(ALTERNATIVE("lock; addl $0,-4(%%esp)", "sfence", \
X86_FEATURE_XMM2) ::: "memory", "cc")
#else
-#define mb() asm volatile("mfence":::"memory")
-#define rmb() asm volatile("lfence":::"memory")
-#define wmb() asm volatile("sfence" ::: "memory")
+#define __mb() asm volatile("mfence":::"memory")
+#define __rmb() asm volatile("lfence":::"memory")
+#define __wmb() asm volatile("sfence" ::: "memory")
#endif
/**
@@ -51,8 +51,8 @@ static inline unsigned long array_index_mask_nospec(unsigned long index,
/* Prevent speculative execution past this barrier. */
#define barrier_nospec() alternative("", "lfence", X86_FEATURE_LFENCE_RDTSC)
-#define dma_rmb() barrier()
-#define dma_wmb() barrier()
+#define __dma_rmb() barrier()
+#define __dma_wmb() barrier()
#define __smp_mb() asm volatile("lock; addl $0,-4(%%" _ASM_SP ")" ::: "memory", "cc")
diff --git a/arch/x86/include/asm/qspinlock.h b/arch/x86/include/asm/qspinlock.h
index d86ab942219c..d87451df480b 100644
--- a/arch/x86/include/asm/qspinlock.h
+++ b/arch/x86/include/asm/qspinlock.h
@@ -53,6 +53,7 @@ static inline void queued_spin_lock_slowpath(struct qspinlock *lock, u32 val)
static inline void queued_spin_unlock(struct qspinlock *lock)
{
+ kcsan_release();
pv_queued_spin_unlock(lock);
}
diff --git a/include/asm-generic/barrier.h b/include/asm-generic/barrier.h
index 4c2c1b830344..3d503e74037f 100644
--- a/include/asm-generic/barrier.h
+++ b/include/asm-generic/barrier.h
@@ -14,6 +14,7 @@
#ifndef __ASSEMBLY__
#include <linux/compiler.h>
+#include <linux/kcsan-checks.h>
#include <asm/rwonce.h>
#ifndef nop
@@ -21,6 +22,31 @@
#endif
/*
+ * Architectures that want generic instrumentation can define __ prefixed
+ * variants of all barriers.
+ */
+
+#ifdef __mb
+#define mb() do { kcsan_mb(); __mb(); } while (0)
+#endif
+
+#ifdef __rmb
+#define rmb() do { kcsan_rmb(); __rmb(); } while (0)
+#endif
+
+#ifdef __wmb
+#define wmb() do { kcsan_wmb(); __wmb(); } while (0)
+#endif
+
+#ifdef __dma_rmb
+#define dma_rmb() do { kcsan_rmb(); __dma_rmb(); } while (0)
+#endif
+
+#ifdef __dma_wmb
+#define dma_wmb() do { kcsan_wmb(); __dma_wmb(); } while (0)
+#endif
+
+/*
* Force strict CPU ordering. And yes, this is required on UP too when we're
* talking to devices.
*
@@ -62,15 +88,15 @@
#ifdef CONFIG_SMP
#ifndef smp_mb
-#define smp_mb() __smp_mb()
+#define smp_mb() do { kcsan_mb(); __smp_mb(); } while (0)
#endif
#ifndef smp_rmb
-#define smp_rmb() __smp_rmb()
+#define smp_rmb() do { kcsan_rmb(); __smp_rmb(); } while (0)
#endif
#ifndef smp_wmb
-#define smp_wmb() __smp_wmb()
+#define smp_wmb() do { kcsan_wmb(); __smp_wmb(); } while (0)
#endif
#else /* !CONFIG_SMP */
@@ -123,19 +149,19 @@ do { \
#ifdef CONFIG_SMP
#ifndef smp_store_mb
-#define smp_store_mb(var, value) __smp_store_mb(var, value)
+#define smp_store_mb(var, value) do { kcsan_mb(); __smp_store_mb(var, value); } while (0)
#endif
#ifndef smp_mb__before_atomic
-#define smp_mb__before_atomic() __smp_mb__before_atomic()
+#define smp_mb__before_atomic() do { kcsan_mb(); __smp_mb__before_atomic(); } while (0)
#endif
#ifndef smp_mb__after_atomic
-#define smp_mb__after_atomic() __smp_mb__after_atomic()
+#define smp_mb__after_atomic() do { kcsan_mb(); __smp_mb__after_atomic(); } while (0)
#endif
#ifndef smp_store_release
-#define smp_store_release(p, v) __smp_store_release(p, v)
+#define smp_store_release(p, v) do { kcsan_release(); __smp_store_release(p, v); } while (0)
#endif
#ifndef smp_load_acquire
@@ -178,13 +204,13 @@ do { \
#endif /* CONFIG_SMP */
/* Barriers for virtual machine guests when talking to an SMP host */
-#define virt_mb() __smp_mb()
-#define virt_rmb() __smp_rmb()
-#define virt_wmb() __smp_wmb()
-#define virt_store_mb(var, value) __smp_store_mb(var, value)
-#define virt_mb__before_atomic() __smp_mb__before_atomic()
-#define virt_mb__after_atomic() __smp_mb__after_atomic()
-#define virt_store_release(p, v) __smp_store_release(p, v)
+#define virt_mb() do { kcsan_mb(); __smp_mb(); } while (0)
+#define virt_rmb() do { kcsan_rmb(); __smp_rmb(); } while (0)
+#define virt_wmb() do { kcsan_wmb(); __smp_wmb(); } while (0)
+#define virt_store_mb(var, value) do { kcsan_mb(); __smp_store_mb(var, value); } while (0)
+#define virt_mb__before_atomic() do { kcsan_mb(); __smp_mb__before_atomic(); } while (0)
+#define virt_mb__after_atomic() do { kcsan_mb(); __smp_mb__after_atomic(); } while (0)
+#define virt_store_release(p, v) do { kcsan_release(); __smp_store_release(p, v); } while (0)
#define virt_load_acquire(p) __smp_load_acquire(p)
/**
diff --git a/include/asm-generic/bitops/instrumented-atomic.h b/include/asm-generic/bitops/instrumented-atomic.h
index 81915dcd4b4e..c90192b1c755 100644
--- a/include/asm-generic/bitops/instrumented-atomic.h
+++ b/include/asm-generic/bitops/instrumented-atomic.h
@@ -67,6 +67,7 @@ static inline void change_bit(long nr, volatile unsigned long *addr)
*/
static inline bool test_and_set_bit(long nr, volatile unsigned long *addr)
{
+ kcsan_mb();
instrument_atomic_read_write(addr + BIT_WORD(nr), sizeof(long));
return arch_test_and_set_bit(nr, addr);
}
@@ -80,6 +81,7 @@ static inline bool test_and_set_bit(long nr, volatile unsigned long *addr)
*/
static inline bool test_and_clear_bit(long nr, volatile unsigned long *addr)
{
+ kcsan_mb();
instrument_atomic_read_write(addr + BIT_WORD(nr), sizeof(long));
return arch_test_and_clear_bit(nr, addr);
}
@@ -93,6 +95,7 @@ static inline bool test_and_clear_bit(long nr, volatile unsigned long *addr)
*/
static inline bool test_and_change_bit(long nr, volatile unsigned long *addr)
{
+ kcsan_mb();
instrument_atomic_read_write(addr + BIT_WORD(nr), sizeof(long));
return arch_test_and_change_bit(nr, addr);
}
diff --git a/include/asm-generic/bitops/instrumented-lock.h b/include/asm-generic/bitops/instrumented-lock.h
index 75ef606f7145..eb64bd4f11f3 100644
--- a/include/asm-generic/bitops/instrumented-lock.h
+++ b/include/asm-generic/bitops/instrumented-lock.h
@@ -22,6 +22,7 @@
*/
static inline void clear_bit_unlock(long nr, volatile unsigned long *addr)
{
+ kcsan_release();
instrument_atomic_write(addr + BIT_WORD(nr), sizeof(long));
arch_clear_bit_unlock(nr, addr);
}
@@ -37,6 +38,7 @@ static inline void clear_bit_unlock(long nr, volatile unsigned long *addr)
*/
static inline void __clear_bit_unlock(long nr, volatile unsigned long *addr)
{
+ kcsan_release();
instrument_write(addr + BIT_WORD(nr), sizeof(long));
arch___clear_bit_unlock(nr, addr);
}
@@ -71,6 +73,7 @@ static inline bool test_and_set_bit_lock(long nr, volatile unsigned long *addr)
static inline bool
clear_bit_unlock_is_negative_byte(long nr, volatile unsigned long *addr)
{
+ kcsan_release();
instrument_atomic_write(addr + BIT_WORD(nr), sizeof(long));
return arch_clear_bit_unlock_is_negative_byte(nr, addr);
}
diff --git a/include/linux/atomic/atomic-instrumented.h b/include/linux/atomic/atomic-instrumented.h
index a0f654370da3..5d69b143c28e 100644
--- a/include/linux/atomic/atomic-instrumented.h
+++ b/include/linux/atomic/atomic-instrumented.h
@@ -45,6 +45,7 @@ atomic_set(atomic_t *v, int i)
static __always_inline void
atomic_set_release(atomic_t *v, int i)
{
+ kcsan_release();
instrument_atomic_write(v, sizeof(*v));
arch_atomic_set_release(v, i);
}
@@ -59,6 +60,7 @@ atomic_add(int i, atomic_t *v)
static __always_inline int
atomic_add_return(int i, atomic_t *v)
{
+ kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return arch_atomic_add_return(i, v);
}
@@ -73,6 +75,7 @@ atomic_add_return_acquire(int i, atomic_t *v)
static __always_inline int
atomic_add_return_release(int i, atomic_t *v)
{
+ kcsan_release();
instrument_atomic_read_write(v, sizeof(*v));
return arch_atomic_add_return_release(i, v);
}
@@ -87,6 +90,7 @@ atomic_add_return_relaxed(int i, atomic_t *v)
static __always_inline int
atomic_fetch_add(int i, atomic_t *v)
{
+ kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return arch_atomic_fetch_add(i, v);
}
@@ -101,6 +105,7 @@ atomic_fetch_add_acquire(int i, atomic_t *v)
static __always_inline int
atomic_fetch_add_release(int i, atomic_t *v)
{
+ kcsan_release();
instrument_atomic_read_write(v, sizeof(*v));
return arch_atomic_fetch_add_release(i, v);
}
@@ -122,6 +127,7 @@ atomic_sub(int i, atomic_t *v)
static __always_inline int
atomic_sub_return(int i, atomic_t *v)
{
+ kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return arch_atomic_sub_return(i, v);
}
@@ -136,6 +142,7 @@ atomic_sub_return_acquire(int i, atomic_t *v)
static __always_inline int
atomic_sub_return_release(int i, atomic_t *v)
{
+ kcsan_release();
instrument_atomic_read_write(v, sizeof(*v));
return arch_atomic_sub_return_release(i, v);
}
@@ -150,6 +157,7 @@ atomic_sub_return_relaxed(int i, atomic_t *v)
static __always_inline int
atomic_fetch_sub(int i, atomic_t *v)
{
+ kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return arch_atomic_fetch_sub(i, v);
}
@@ -164,6 +172,7 @@ atomic_fetch_sub_acquire(int i, atomic_t *v)
static __always_inline int
atomic_fetch_sub_release(int i, atomic_t *v)
{
+ kcsan_release();
instrument_atomic_read_write(v, sizeof(*v));
return arch_atomic_fetch_sub_release(i, v);
}
@@ -185,6 +194,7 @@ atomic_inc(atomic_t *v)
static __always_inline int
atomic_inc_return(atomic_t *v)
{
+ kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return arch_atomic_inc_return(v);
}
@@ -199,6 +209,7 @@ atomic_inc_return_acquire(atomic_t *v)
static __always_inline int
atomic_inc_return_release(atomic_t *v)
{
+ kcsan_release();
instrument_atomic_read_write(v, sizeof(*v));
return arch_atomic_inc_return_release(v);
}
@@ -213,6 +224,7 @@ atomic_inc_return_relaxed(atomic_t *v)
static __always_inline int
atomic_fetch_inc(atomic_t *v)
{
+ kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return arch_atomic_fetch_inc(v);
}
@@ -227,6 +239,7 @@ atomic_fetch_inc_acquire(atomic_t *v)
static __always_inline int
atomic_fetch_inc_release(atomic_t *v)
{
+ kcsan_release();
instrument_atomic_read_write(v, sizeof(*v));
return arch_atomic_fetch_inc_release(v);
}
@@ -248,6 +261,7 @@ atomic_dec(atomic_t *v)
static __always_inline int
atomic_dec_return(atomic_t *v)
{
+ kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return arch_atomic_dec_return(v);
}
@@ -262,6 +276,7 @@ atomic_dec_return_acquire(atomic_t *v)
static __always_inline int
atomic_dec_return_release(atomic_t *v)
{
+ kcsan_release();
instrument_atomic_read_write(v, sizeof(*v));
return arch_atomic_dec_return_release(v);
}
@@ -276,6 +291,7 @@ atomic_dec_return_relaxed(atomic_t *v)
static __always_inline int
atomic_fetch_dec(atomic_t *v)
{
+ kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return arch_atomic_fetch_dec(v);
}
@@ -290,6 +306,7 @@ atomic_fetch_dec_acquire(atomic_t *v)
static __always_inline int
atomic_fetch_dec_release(atomic_t *v)
{
+ kcsan_release();
instrument_atomic_read_write(v, sizeof(*v));
return arch_atomic_fetch_dec_release(v);
}
@@ -311,6 +328,7 @@ atomic_and(int i, atomic_t *v)
static __always_inline int
atomic_fetch_and(int i, atomic_t *v)
{
+ kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return arch_atomic_fetch_and(i, v);
}
@@ -325,6 +343,7 @@ atomic_fetch_and_acquire(int i, atomic_t *v)
static __always_inline int
atomic_fetch_and_release(int i, atomic_t *v)
{
+ kcsan_release();
instrument_atomic_read_write(v, sizeof(*v));
return arch_atomic_fetch_and_release(i, v);
}
@@ -346,6 +365,7 @@ atomic_andnot(int i, atomic_t *v)
static __always_inline int
atomic_fetch_andnot(int i, atomic_t *v)
{
+ kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return arch_atomic_fetch_andnot(i, v);
}
@@ -360,6 +380,7 @@ atomic_fetch_andnot_acquire(int i, atomic_t *v)
static __always_inline int
atomic_fetch_andnot_release(int i, atomic_t *v)
{
+ kcsan_release();
instrument_atomic_read_write(v, sizeof(*v));
return arch_atomic_fetch_andnot_release(i, v);
}
@@ -381,6 +402,7 @@ atomic_or(int i, atomic_t *v)
static __always_inline int
atomic_fetch_or(int i, atomic_t *v)
{
+ kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return arch_atomic_fetch_or(i, v);
}
@@ -395,6 +417,7 @@ atomic_fetch_or_acquire(int i, atomic_t *v)
static __always_inline int
atomic_fetch_or_release(int i, atomic_t *v)
{
+ kcsan_release();
instrument_atomic_read_write(v, sizeof(*v));
return arch_atomic_fetch_or_release(i, v);
}
@@ -416,6 +439,7 @@ atomic_xor(int i, atomic_t *v)
static __always_inline int
atomic_fetch_xor(int i, atomic_t *v)
{
+ kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return arch_atomic_fetch_xor(i, v);
}
@@ -430,6 +454,7 @@ atomic_fetch_xor_acquire(int i, atomic_t *v)
static __always_inline int
atomic_fetch_xor_release(int i, atomic_t *v)
{
+ kcsan_release();
instrument_atomic_read_write(v, sizeof(*v));
return arch_atomic_fetch_xor_release(i, v);
}
@@ -444,6 +469,7 @@ atomic_fetch_xor_relaxed(int i, atomic_t *v)
static __always_inline int
atomic_xchg(atomic_t *v, int i)
{
+ kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return arch_atomic_xchg(v, i);
}
@@ -458,6 +484,7 @@ atomic_xchg_acquire(atomic_t *v, int i)
static __always_inline int
atomic_xchg_release(atomic_t *v, int i)
{
+ kcsan_release();
instrument_atomic_read_write(v, sizeof(*v));
return arch_atomic_xchg_release(v, i);
}
@@ -472,6 +499,7 @@ atomic_xchg_relaxed(atomic_t *v, int i)
static __always_inline int
atomic_cmpxchg(atomic_t *v, int old, int new)
{
+ kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return arch_atomic_cmpxchg(v, old, new);
}
@@ -486,6 +514,7 @@ atomic_cmpxchg_acquire(atomic_t *v, int old, int new)
static __always_inline int
atomic_cmpxchg_release(atomic_t *v, int old, int new)
{
+ kcsan_release();
instrument_atomic_read_write(v, sizeof(*v));
return arch_atomic_cmpxchg_release(v, old, new);
}
@@ -500,6 +529,7 @@ atomic_cmpxchg_relaxed(atomic_t *v, int old, int new)
static __always_inline bool
atomic_try_cmpxchg(atomic_t *v, int *old, int new)
{
+ kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
instrument_atomic_read_write(old, sizeof(*old));
return arch_atomic_try_cmpxchg(v, old, new);
@@ -516,6 +546,7 @@ atomic_try_cmpxchg_acquire(atomic_t *v, int *old, int new)
static __always_inline bool
atomic_try_cmpxchg_release(atomic_t *v, int *old, int new)
{
+ kcsan_release();
instrument_atomic_read_write(v, sizeof(*v));
instrument_atomic_read_write(old, sizeof(*old));
return arch_atomic_try_cmpxchg_release(v, old, new);
@@ -532,6 +563,7 @@ atomic_try_cmpxchg_relaxed(atomic_t *v, int *old, int new)
static __always_inline bool
atomic_sub_and_test(int i, atomic_t *v)
{
+ kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return arch_atomic_sub_and_test(i, v);
}
@@ -539,6 +571,7 @@ atomic_sub_and_test(int i, atomic_t *v)
static __always_inline bool
atomic_dec_and_test(atomic_t *v)
{
+ kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return arch_atomic_dec_and_test(v);
}
@@ -546,6 +579,7 @@ atomic_dec_and_test(atomic_t *v)
static __always_inline bool
atomic_inc_and_test(atomic_t *v)
{
+ kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return arch_atomic_inc_and_test(v);
}
@@ -553,6 +587,7 @@ atomic_inc_and_test(atomic_t *v)
static __always_inline bool
atomic_add_negative(int i, atomic_t *v)
{
+ kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return arch_atomic_add_negative(i, v);
}
@@ -560,6 +595,7 @@ atomic_add_negative(int i, atomic_t *v)
static __always_inline int
atomic_fetch_add_unless(atomic_t *v, int a, int u)
{
+ kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return arch_atomic_fetch_add_unless(v, a, u);
}
@@ -567,6 +603,7 @@ atomic_fetch_add_unless(atomic_t *v, int a, int u)
static __always_inline bool
atomic_add_unless(atomic_t *v, int a, int u)
{
+ kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return arch_atomic_add_unless(v, a, u);
}
@@ -574,6 +611,7 @@ atomic_add_unless(atomic_t *v, int a, int u)
static __always_inline bool
atomic_inc_not_zero(atomic_t *v)
{
+ kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return arch_atomic_inc_not_zero(v);
}
@@ -581,6 +619,7 @@ atomic_inc_not_zero(atomic_t *v)
static __always_inline bool
atomic_inc_unless_negative(atomic_t *v)
{
+ kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return arch_atomic_inc_unless_negative(v);
}
@@ -588,6 +627,7 @@ atomic_inc_unless_negative(atomic_t *v)
static __always_inline bool
atomic_dec_unless_positive(atomic_t *v)
{
+ kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return arch_atomic_dec_unless_positive(v);
}
@@ -595,6 +635,7 @@ atomic_dec_unless_positive(atomic_t *v)
static __always_inline int
atomic_dec_if_positive(atomic_t *v)
{
+ kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return arch_atomic_dec_if_positive(v);
}
@@ -623,6 +664,7 @@ atomic64_set(atomic64_t *v, s64 i)
static __always_inline void
atomic64_set_release(atomic64_t *v, s64 i)
{
+ kcsan_release();
instrument_atomic_write(v, sizeof(*v));
arch_atomic64_set_release(v, i);
}
@@ -637,6 +679,7 @@ atomic64_add(s64 i, atomic64_t *v)
static __always_inline s64
atomic64_add_return(s64 i, atomic64_t *v)
{
+ kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return arch_atomic64_add_return(i, v);
}
@@ -651,6 +694,7 @@ atomic64_add_return_acquire(s64 i, atomic64_t *v)
static __always_inline s64
atomic64_add_return_release(s64 i, atomic64_t *v)
{
+ kcsan_release();
instrument_atomic_read_write(v, sizeof(*v));
return arch_atomic64_add_return_release(i, v);
}
@@ -665,6 +709,7 @@ atomic64_add_return_relaxed(s64 i, atomic64_t *v)
static __always_inline s64
atomic64_fetch_add(s64 i, atomic64_t *v)
{
+ kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return arch_atomic64_fetch_add(i, v);
}
@@ -679,6 +724,7 @@ atomic64_fetch_add_acquire(s64 i, atomic64_t *v)
static __always_inline s64
atomic64_fetch_add_release(s64 i, atomic64_t *v)
{
+ kcsan_release();
instrument_atomic_read_write(v, sizeof(*v));
return arch_atomic64_fetch_add_release(i, v);
}
@@ -700,6 +746,7 @@ atomic64_sub(s64 i, atomic64_t *v)
static __always_inline s64
atomic64_sub_return(s64 i, atomic64_t *v)
{
+ kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return arch_atomic64_sub_return(i, v);
}
@@ -714,6 +761,7 @@ atomic64_sub_return_acquire(s64 i, atomic64_t *v)
static __always_inline s64
atomic64_sub_return_release(s64 i, atomic64_t *v)
{
+ kcsan_release();
instrument_atomic_read_write(v, sizeof(*v));
return arch_atomic64_sub_return_release(i, v);
}
@@ -728,6 +776,7 @@ atomic64_sub_return_relaxed(s64 i, atomic64_t *v)
static __always_inline s64
atomic64_fetch_sub(s64 i, atomic64_t *v)
{
+ kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return arch_atomic64_fetch_sub(i, v);
}
@@ -742,6 +791,7 @@ atomic64_fetch_sub_acquire(s64 i, atomic64_t *v)
static __always_inline s64
atomic64_fetch_sub_release(s64 i, atomic64_t *v)
{
+ kcsan_release();
instrument_atomic_read_write(v, sizeof(*v));
return arch_atomic64_fetch_sub_release(i, v);
}
@@ -763,6 +813,7 @@ atomic64_inc(atomic64_t *v)
static __always_inline s64
atomic64_inc_return(atomic64_t *v)
{
+ kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return arch_atomic64_inc_return(v);
}
@@ -777,6 +828,7 @@ atomic64_inc_return_acquire(atomic64_t *v)
static __always_inline s64
atomic64_inc_return_release(atomic64_t *v)
{
+ kcsan_release();
instrument_atomic_read_write(v, sizeof(*v));
return arch_atomic64_inc_return_release(v);
}
@@ -791,6 +843,7 @@ atomic64_inc_return_relaxed(atomic64_t *v)
static __always_inline s64
atomic64_fetch_inc(atomic64_t *v)
{
+ kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return arch_atomic64_fetch_inc(v);
}
@@ -805,6 +858,7 @@ atomic64_fetch_inc_acquire(atomic64_t *v)
static __always_inline s64
atomic64_fetch_inc_release(atomic64_t *v)
{
+ kcsan_release();
instrument_atomic_read_write(v, sizeof(*v));
return arch_atomic64_fetch_inc_release(v);
}
@@ -826,6 +880,7 @@ atomic64_dec(atomic64_t *v)
static __always_inline s64
atomic64_dec_return(atomic64_t *v)
{
+ kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return arch_atomic64_dec_return(v);
}
@@ -840,6 +895,7 @@ atomic64_dec_return_acquire(atomic64_t *v)
static __always_inline s64
atomic64_dec_return_release(atomic64_t *v)
{
+ kcsan_release();
instrument_atomic_read_write(v, sizeof(*v));
return arch_atomic64_dec_return_release(v);
}
@@ -854,6 +910,7 @@ atomic64_dec_return_relaxed(atomic64_t *v)
static __always_inline s64
atomic64_fetch_dec(atomic64_t *v)
{
+ kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return arch_atomic64_fetch_dec(v);
}
@@ -868,6 +925,7 @@ atomic64_fetch_dec_acquire(atomic64_t *v)
static __always_inline s64
atomic64_fetch_dec_release(atomic64_t *v)
{
+ kcsan_release();
instrument_atomic_read_write(v, sizeof(*v));
return arch_atomic64_fetch_dec_release(v);
}
@@ -889,6 +947,7 @@ atomic64_and(s64 i, atomic64_t *v)
static __always_inline s64
atomic64_fetch_and(s64 i, atomic64_t *v)
{
+ kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return arch_atomic64_fetch_and(i, v);
}
@@ -903,6 +962,7 @@ atomic64_fetch_and_acquire(s64 i, atomic64_t *v)
static __always_inline s64
atomic64_fetch_and_release(s64 i, atomic64_t *v)
{
+ kcsan_release();
instrument_atomic_read_write(v, sizeof(*v));
return arch_atomic64_fetch_and_release(i, v);
}
@@ -924,6 +984,7 @@ atomic64_andnot(s64 i, atomic64_t *v)
static __always_inline s64
atomic64_fetch_andnot(s64 i, atomic64_t *v)
{
+ kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return arch_atomic64_fetch_andnot(i, v);
}
@@ -938,6 +999,7 @@ atomic64_fetch_andnot_acquire(s64 i, atomic64_t *v)
static __always_inline s64
atomic64_fetch_andnot_release(s64 i, atomic64_t *v)
{
+ kcsan_release();
instrument_atomic_read_write(v, sizeof(*v));
return arch_atomic64_fetch_andnot_release(i, v);
}
@@ -959,6 +1021,7 @@ atomic64_or(s64 i, atomic64_t *v)
static __always_inline s64
atomic64_fetch_or(s64 i, atomic64_t *v)
{
+ kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return arch_atomic64_fetch_or(i, v);
}
@@ -973,6 +1036,7 @@ atomic64_fetch_or_acquire(s64 i, atomic64_t *v)
static __always_inline s64
atomic64_fetch_or_release(s64 i, atomic64_t *v)
{
+ kcsan_release();
instrument_atomic_read_write(v, sizeof(*v));
return arch_atomic64_fetch_or_release(i, v);
}
@@ -994,6 +1058,7 @@ atomic64_xor(s64 i, atomic64_t *v)
static __always_inline s64
atomic64_fetch_xor(s64 i, atomic64_t *v)
{
+ kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return arch_atomic64_fetch_xor(i, v);
}
@@ -1008,6 +1073,7 @@ atomic64_fetch_xor_acquire(s64 i, atomic64_t *v)
static __always_inline s64
atomic64_fetch_xor_release(s64 i, atomic64_t *v)
{
+ kcsan_release();
instrument_atomic_read_write(v, sizeof(*v));
return arch_atomic64_fetch_xor_release(i, v);
}
@@ -1022,6 +1088,7 @@ atomic64_fetch_xor_relaxed(s64 i, atomic64_t *v)
static __always_inline s64
atomic64_xchg(atomic64_t *v, s64 i)
{
+ kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return arch_atomic64_xchg(v, i);
}
@@ -1036,6 +1103,7 @@ atomic64_xchg_acquire(atomic64_t *v, s64 i)
static __always_inline s64
atomic64_xchg_release(atomic64_t *v, s64 i)
{
+ kcsan_release();
instrument_atomic_read_write(v, sizeof(*v));
return arch_atomic64_xchg_release(v, i);
}
@@ -1050,6 +1118,7 @@ atomic64_xchg_relaxed(atomic64_t *v, s64 i)
static __always_inline s64
atomic64_cmpxchg(atomic64_t *v, s64 old, s64 new)
{
+ kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return arch_atomic64_cmpxchg(v, old, new);
}
@@ -1064,6 +1133,7 @@ atomic64_cmpxchg_acquire(atomic64_t *v, s64 old, s64 new)
static __always_inline s64
atomic64_cmpxchg_release(atomic64_t *v, s64 old, s64 new)
{
+ kcsan_release();
instrument_atomic_read_write(v, sizeof(*v));
return arch_atomic64_cmpxchg_release(v, old, new);
}
@@ -1078,6 +1148,7 @@ atomic64_cmpxchg_relaxed(atomic64_t *v, s64 old, s64 new)
static __always_inline bool
atomic64_try_cmpxchg(atomic64_t *v, s64 *old, s64 new)
{
+ kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
instrument_atomic_read_write(old, sizeof(*old));
return arch_atomic64_try_cmpxchg(v, old, new);
@@ -1094,6 +1165,7 @@ atomic64_try_cmpxchg_acquire(atomic64_t *v, s64 *old, s64 new)
static __always_inline bool
atomic64_try_cmpxchg_release(atomic64_t *v, s64 *old, s64 new)
{
+ kcsan_release();
instrument_atomic_read_write(v, sizeof(*v));
instrument_atomic_read_write(old, sizeof(*old));
return arch_atomic64_try_cmpxchg_release(v, old, new);
@@ -1110,6 +1182,7 @@ atomic64_try_cmpxchg_relaxed(atomic64_t *v, s64 *old, s64 new)
static __always_inline bool
atomic64_sub_and_test(s64 i, atomic64_t *v)
{
+ kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return arch_atomic64_sub_and_test(i, v);
}
@@ -1117,6 +1190,7 @@ atomic64_sub_and_test(s64 i, atomic64_t *v)
static __always_inline bool
atomic64_dec_and_test(atomic64_t *v)
{
+ kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return arch_atomic64_dec_and_test(v);
}
@@ -1124,6 +1198,7 @@ atomic64_dec_and_test(atomic64_t *v)
static __always_inline bool
atomic64_inc_and_test(atomic64_t *v)
{
+ kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return arch_atomic64_inc_and_test(v);
}
@@ -1131,6 +1206,7 @@ atomic64_inc_and_test(atomic64_t *v)
static __always_inline bool
atomic64_add_negative(s64 i, atomic64_t *v)
{
+ kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return arch_atomic64_add_negative(i, v);
}
@@ -1138,6 +1214,7 @@ atomic64_add_negative(s64 i, atomic64_t *v)
static __always_inline s64
atomic64_fetch_add_unless(atomic64_t *v, s64 a, s64 u)
{
+ kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return arch_atomic64_fetch_add_unless(v, a, u);
}
@@ -1145,6 +1222,7 @@ atomic64_fetch_add_unless(atomic64_t *v, s64 a, s64 u)
static __always_inline bool
atomic64_add_unless(atomic64_t *v, s64 a, s64 u)
{
+ kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return arch_atomic64_add_unless(v, a, u);
}
@@ -1152,6 +1230,7 @@ atomic64_add_unless(atomic64_t *v, s64 a, s64 u)
static __always_inline bool
atomic64_inc_not_zero(atomic64_t *v)
{
+ kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return arch_atomic64_inc_not_zero(v);
}
@@ -1159,6 +1238,7 @@ atomic64_inc_not_zero(atomic64_t *v)
static __always_inline bool
atomic64_inc_unless_negative(atomic64_t *v)
{
+ kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return arch_atomic64_inc_unless_negative(v);
}
@@ -1166,6 +1246,7 @@ atomic64_inc_unless_negative(atomic64_t *v)
static __always_inline bool
atomic64_dec_unless_positive(atomic64_t *v)
{
+ kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return arch_atomic64_dec_unless_positive(v);
}
@@ -1173,6 +1254,7 @@ atomic64_dec_unless_positive(atomic64_t *v)
static __always_inline s64
atomic64_dec_if_positive(atomic64_t *v)
{
+ kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return arch_atomic64_dec_if_positive(v);
}
@@ -1201,6 +1283,7 @@ atomic_long_set(atomic_long_t *v, long i)
static __always_inline void
atomic_long_set_release(atomic_long_t *v, long i)
{
+ kcsan_release();
instrument_atomic_write(v, sizeof(*v));
arch_atomic_long_set_release(v, i);
}
@@ -1215,6 +1298,7 @@ atomic_long_add(long i, atomic_long_t *v)
static __always_inline long
atomic_long_add_return(long i, atomic_long_t *v)
{
+ kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return arch_atomic_long_add_return(i, v);
}
@@ -1229,6 +1313,7 @@ atomic_long_add_return_acquire(long i, atomic_long_t *v)
static __always_inline long
atomic_long_add_return_release(long i, atomic_long_t *v)
{
+ kcsan_release();
instrument_atomic_read_write(v, sizeof(*v));
return arch_atomic_long_add_return_release(i, v);
}
@@ -1243,6 +1328,7 @@ atomic_long_add_return_relaxed(long i, atomic_long_t *v)
static __always_inline long
atomic_long_fetch_add(long i, atomic_long_t *v)
{
+ kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return arch_atomic_long_fetch_add(i, v);
}
@@ -1257,6 +1343,7 @@ atomic_long_fetch_add_acquire(long i, atomic_long_t *v)
static __always_inline long
atomic_long_fetch_add_release(long i, atomic_long_t *v)
{
+ kcsan_release();
instrument_atomic_read_write(v, sizeof(*v));
return arch_atomic_long_fetch_add_release(i, v);
}
@@ -1278,6 +1365,7 @@ atomic_long_sub(long i, atomic_long_t *v)
static __always_inline long
atomic_long_sub_return(long i, atomic_long_t *v)
{
+ kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return arch_atomic_long_sub_return(i, v);
}
@@ -1292,6 +1380,7 @@ atomic_long_sub_return_acquire(long i, atomic_long_t *v)
static __always_inline long
atomic_long_sub_return_release(long i, atomic_long_t *v)
{
+ kcsan_release();
instrument_atomic_read_write(v, sizeof(*v));
return arch_atomic_long_sub_return_release(i, v);
}
@@ -1306,6 +1395,7 @@ atomic_long_sub_return_relaxed(long i, atomic_long_t *v)
static __always_inline long
atomic_long_fetch_sub(long i, atomic_long_t *v)
{
+ kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return arch_atomic_long_fetch_sub(i, v);
}
@@ -1320,6 +1410,7 @@ atomic_long_fetch_sub_acquire(long i, atomic_long_t *v)
static __always_inline long
atomic_long_fetch_sub_release(long i, atomic_long_t *v)
{
+ kcsan_release();
instrument_atomic_read_write(v, sizeof(*v));
return arch_atomic_long_fetch_sub_release(i, v);
}
@@ -1341,6 +1432,7 @@ atomic_long_inc(atomic_long_t *v)
static __always_inline long
atomic_long_inc_return(atomic_long_t *v)
{
+ kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return arch_atomic_long_inc_return(v);
}
@@ -1355,6 +1447,7 @@ atomic_long_inc_return_acquire(atomic_long_t *v)
static __always_inline long
atomic_long_inc_return_release(atomic_long_t *v)
{
+ kcsan_release();
instrument_atomic_read_write(v, sizeof(*v));
return arch_atomic_long_inc_return_release(v);
}
@@ -1369,6 +1462,7 @@ atomic_long_inc_return_relaxed(atomic_long_t *v)
static __always_inline long
atomic_long_fetch_inc(atomic_long_t *v)
{
+ kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return arch_atomic_long_fetch_inc(v);
}
@@ -1383,6 +1477,7 @@ atomic_long_fetch_inc_acquire(atomic_long_t *v)
static __always_inline long
atomic_long_fetch_inc_release(atomic_long_t *v)
{
+ kcsan_release();
instrument_atomic_read_write(v, sizeof(*v));
return arch_atomic_long_fetch_inc_release(v);
}
@@ -1404,6 +1499,7 @@ atomic_long_dec(atomic_long_t *v)
static __always_inline long
atomic_long_dec_return(atomic_long_t *v)
{
+ kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return arch_atomic_long_dec_return(v);
}
@@ -1418,6 +1514,7 @@ atomic_long_dec_return_acquire(atomic_long_t *v)
static __always_inline long
atomic_long_dec_return_release(atomic_long_t *v)
{
+ kcsan_release();
instrument_atomic_read_write(v, sizeof(*v));
return arch_atomic_long_dec_return_release(v);
}
@@ -1432,6 +1529,7 @@ atomic_long_dec_return_relaxed(atomic_long_t *v)
static __always_inline long
atomic_long_fetch_dec(atomic_long_t *v)
{
+ kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return arch_atomic_long_fetch_dec(v);
}
@@ -1446,6 +1544,7 @@ atomic_long_fetch_dec_acquire(atomic_long_t *v)
static __always_inline long
atomic_long_fetch_dec_release(atomic_long_t *v)
{
+ kcsan_release();
instrument_atomic_read_write(v, sizeof(*v));
return arch_atomic_long_fetch_dec_release(v);
}
@@ -1467,6 +1566,7 @@ atomic_long_and(long i, atomic_long_t *v)
static __always_inline long
atomic_long_fetch_and(long i, atomic_long_t *v)
{
+ kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return arch_atomic_long_fetch_and(i, v);
}
@@ -1481,6 +1581,7 @@ atomic_long_fetch_and_acquire(long i, atomic_long_t *v)
static __always_inline long
atomic_long_fetch_and_release(long i, atomic_long_t *v)
{
+ kcsan_release();
instrument_atomic_read_write(v, sizeof(*v));
return arch_atomic_long_fetch_and_release(i, v);
}
@@ -1502,6 +1603,7 @@ atomic_long_andnot(long i, atomic_long_t *v)
static __always_inline long
atomic_long_fetch_andnot(long i, atomic_long_t *v)
{
+ kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return arch_atomic_long_fetch_andnot(i, v);
}
@@ -1516,6 +1618,7 @@ atomic_long_fetch_andnot_acquire(long i, atomic_long_t *v)
static __always_inline long
atomic_long_fetch_andnot_release(long i, atomic_long_t *v)
{
+ kcsan_release();
instrument_atomic_read_write(v, sizeof(*v));
return arch_atomic_long_fetch_andnot_release(i, v);
}
@@ -1537,6 +1640,7 @@ atomic_long_or(long i, atomic_long_t *v)
static __always_inline long
atomic_long_fetch_or(long i, atomic_long_t *v)
{
+ kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return arch_atomic_long_fetch_or(i, v);
}
@@ -1551,6 +1655,7 @@ atomic_long_fetch_or_acquire(long i, atomic_long_t *v)
static __always_inline long
atomic_long_fetch_or_release(long i, atomic_long_t *v)
{
+ kcsan_release();
instrument_atomic_read_write(v, sizeof(*v));
return arch_atomic_long_fetch_or_release(i, v);
}
@@ -1572,6 +1677,7 @@ atomic_long_xor(long i, atomic_long_t *v)
static __always_inline long
atomic_long_fetch_xor(long i, atomic_long_t *v)
{
+ kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return arch_atomic_long_fetch_xor(i, v);
}
@@ -1586,6 +1692,7 @@ atomic_long_fetch_xor_acquire(long i, atomic_long_t *v)
static __always_inline long
atomic_long_fetch_xor_release(long i, atomic_long_t *v)
{
+ kcsan_release();
instrument_atomic_read_write(v, sizeof(*v));
return arch_atomic_long_fetch_xor_release(i, v);
}
@@ -1600,6 +1707,7 @@ atomic_long_fetch_xor_relaxed(long i, atomic_long_t *v)
static __always_inline long
atomic_long_xchg(atomic_long_t *v, long i)
{
+ kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return arch_atomic_long_xchg(v, i);
}
@@ -1614,6 +1722,7 @@ atomic_long_xchg_acquire(atomic_long_t *v, long i)
static __always_inline long
atomic_long_xchg_release(atomic_long_t *v, long i)
{
+ kcsan_release();
instrument_atomic_read_write(v, sizeof(*v));
return arch_atomic_long_xchg_release(v, i);
}
@@ -1628,6 +1737,7 @@ atomic_long_xchg_relaxed(atomic_long_t *v, long i)
static __always_inline long
atomic_long_cmpxchg(atomic_long_t *v, long old, long new)
{
+ kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return arch_atomic_long_cmpxchg(v, old, new);
}
@@ -1642,6 +1752,7 @@ atomic_long_cmpxchg_acquire(atomic_long_t *v, long old, long new)
static __always_inline long
atomic_long_cmpxchg_release(atomic_long_t *v, long old, long new)
{
+ kcsan_release();
instrument_atomic_read_write(v, sizeof(*v));
return arch_atomic_long_cmpxchg_release(v, old, new);
}
@@ -1656,6 +1767,7 @@ atomic_long_cmpxchg_relaxed(atomic_long_t *v, long old, long new)
static __always_inline bool
atomic_long_try_cmpxchg(atomic_long_t *v, long *old, long new)
{
+ kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
instrument_atomic_read_write(old, sizeof(*old));
return arch_atomic_long_try_cmpxchg(v, old, new);
@@ -1672,6 +1784,7 @@ atomic_long_try_cmpxchg_acquire(atomic_long_t *v, long *old, long new)
static __always_inline bool
atomic_long_try_cmpxchg_release(atomic_long_t *v, long *old, long new)
{
+ kcsan_release();
instrument_atomic_read_write(v, sizeof(*v));
instrument_atomic_read_write(old, sizeof(*old));
return arch_atomic_long_try_cmpxchg_release(v, old, new);
@@ -1688,6 +1801,7 @@ atomic_long_try_cmpxchg_relaxed(atomic_long_t *v, long *old, long new)
static __always_inline bool
atomic_long_sub_and_test(long i, atomic_long_t *v)
{
+ kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return arch_atomic_long_sub_and_test(i, v);
}
@@ -1695,6 +1809,7 @@ atomic_long_sub_and_test(long i, atomic_long_t *v)
static __always_inline bool
atomic_long_dec_and_test(atomic_long_t *v)
{
+ kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return arch_atomic_long_dec_and_test(v);
}
@@ -1702,6 +1817,7 @@ atomic_long_dec_and_test(atomic_long_t *v)
static __always_inline bool
atomic_long_inc_and_test(atomic_long_t *v)
{
+ kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return arch_atomic_long_inc_and_test(v);
}
@@ -1709,6 +1825,7 @@ atomic_long_inc_and_test(atomic_long_t *v)
static __always_inline bool
atomic_long_add_negative(long i, atomic_long_t *v)
{
+ kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return arch_atomic_long_add_negative(i, v);
}
@@ -1716,6 +1833,7 @@ atomic_long_add_negative(long i, atomic_long_t *v)
static __always_inline long
atomic_long_fetch_add_unless(atomic_long_t *v, long a, long u)
{
+ kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return arch_atomic_long_fetch_add_unless(v, a, u);
}
@@ -1723,6 +1841,7 @@ atomic_long_fetch_add_unless(atomic_long_t *v, long a, long u)
static __always_inline bool
atomic_long_add_unless(atomic_long_t *v, long a, long u)
{
+ kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return arch_atomic_long_add_unless(v, a, u);
}
@@ -1730,6 +1849,7 @@ atomic_long_add_unless(atomic_long_t *v, long a, long u)
static __always_inline bool
atomic_long_inc_not_zero(atomic_long_t *v)
{
+ kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return arch_atomic_long_inc_not_zero(v);
}
@@ -1737,6 +1857,7 @@ atomic_long_inc_not_zero(atomic_long_t *v)
static __always_inline bool
atomic_long_inc_unless_negative(atomic_long_t *v)
{
+ kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return arch_atomic_long_inc_unless_negative(v);
}
@@ -1744,6 +1865,7 @@ atomic_long_inc_unless_negative(atomic_long_t *v)
static __always_inline bool
atomic_long_dec_unless_positive(atomic_long_t *v)
{
+ kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return arch_atomic_long_dec_unless_positive(v);
}
@@ -1751,6 +1873,7 @@ atomic_long_dec_unless_positive(atomic_long_t *v)
static __always_inline long
atomic_long_dec_if_positive(atomic_long_t *v)
{
+ kcsan_mb();
instrument_atomic_read_write(v, sizeof(*v));
return arch_atomic_long_dec_if_positive(v);
}
@@ -1758,6 +1881,7 @@ atomic_long_dec_if_positive(atomic_long_t *v)
#define xchg(ptr, ...) \
({ \
typeof(ptr) __ai_ptr = (ptr); \
+ kcsan_mb(); \
instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \
arch_xchg(__ai_ptr, __VA_ARGS__); \
})
@@ -1772,6 +1896,7 @@ atomic_long_dec_if_positive(atomic_long_t *v)
#define xchg_release(ptr, ...) \
({ \
typeof(ptr) __ai_ptr = (ptr); \
+ kcsan_release(); \
instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \
arch_xchg_release(__ai_ptr, __VA_ARGS__); \
})
@@ -1786,6 +1911,7 @@ atomic_long_dec_if_positive(atomic_long_t *v)
#define cmpxchg(ptr, ...) \
({ \
typeof(ptr) __ai_ptr = (ptr); \
+ kcsan_mb(); \
instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \
arch_cmpxchg(__ai_ptr, __VA_ARGS__); \
})
@@ -1800,6 +1926,7 @@ atomic_long_dec_if_positive(atomic_long_t *v)
#define cmpxchg_release(ptr, ...) \
({ \
typeof(ptr) __ai_ptr = (ptr); \
+ kcsan_release(); \
instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \
arch_cmpxchg_release(__ai_ptr, __VA_ARGS__); \
})
@@ -1814,6 +1941,7 @@ atomic_long_dec_if_positive(atomic_long_t *v)
#define cmpxchg64(ptr, ...) \
({ \
typeof(ptr) __ai_ptr = (ptr); \
+ kcsan_mb(); \
instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \
arch_cmpxchg64(__ai_ptr, __VA_ARGS__); \
})
@@ -1828,6 +1956,7 @@ atomic_long_dec_if_positive(atomic_long_t *v)
#define cmpxchg64_release(ptr, ...) \
({ \
typeof(ptr) __ai_ptr = (ptr); \
+ kcsan_release(); \
instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \
arch_cmpxchg64_release(__ai_ptr, __VA_ARGS__); \
})
@@ -1843,6 +1972,7 @@ atomic_long_dec_if_positive(atomic_long_t *v)
({ \
typeof(ptr) __ai_ptr = (ptr); \
typeof(oldp) __ai_oldp = (oldp); \
+ kcsan_mb(); \
instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \
instrument_atomic_write(__ai_oldp, sizeof(*__ai_oldp)); \
arch_try_cmpxchg(__ai_ptr, __ai_oldp, __VA_ARGS__); \
@@ -1861,6 +1991,7 @@ atomic_long_dec_if_positive(atomic_long_t *v)
({ \
typeof(ptr) __ai_ptr = (ptr); \
typeof(oldp) __ai_oldp = (oldp); \
+ kcsan_release(); \
instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \
instrument_atomic_write(__ai_oldp, sizeof(*__ai_oldp)); \
arch_try_cmpxchg_release(__ai_ptr, __ai_oldp, __VA_ARGS__); \
@@ -1892,6 +2023,7 @@ atomic_long_dec_if_positive(atomic_long_t *v)
#define sync_cmpxchg(ptr, ...) \
({ \
typeof(ptr) __ai_ptr = (ptr); \
+ kcsan_mb(); \
instrument_atomic_write(__ai_ptr, sizeof(*__ai_ptr)); \
arch_sync_cmpxchg(__ai_ptr, __VA_ARGS__); \
})
@@ -1899,6 +2031,7 @@ atomic_long_dec_if_positive(atomic_long_t *v)
#define cmpxchg_double(ptr, ...) \
({ \
typeof(ptr) __ai_ptr = (ptr); \
+ kcsan_mb(); \
instrument_atomic_write(__ai_ptr, 2 * sizeof(*__ai_ptr)); \
arch_cmpxchg_double(__ai_ptr, __VA_ARGS__); \
})
@@ -1912,4 +2045,4 @@ atomic_long_dec_if_positive(atomic_long_t *v)
})
#endif /* _LINUX_ATOMIC_INSTRUMENTED_H */
-// 2a9553f0a9d5619f19151092df5cabbbf16ce835
+// 87c974b93032afd42143613434d1a7788fa598f9
diff --git a/include/linux/compiler_attributes.h b/include/linux/compiler_attributes.h
index b9121afd8733..37e260020221 100644
--- a/include/linux/compiler_attributes.h
+++ b/include/linux/compiler_attributes.h
@@ -309,6 +309,24 @@
#endif
/*
+ * Optional: only supported since clang >= 14.0
+ *
+ * clang: https://clang.llvm.org/docs/AttributeReference.html#disable-sanitizer-instrumentation
+ *
+ * disable_sanitizer_instrumentation is not always similar to
+ * no_sanitize((<sanitizer-name>)): the latter may still let specific sanitizers
+ * insert code into functions to prevent false positives. Unlike that,
+ * disable_sanitizer_instrumentation prevents all kinds of instrumentation to
+ * functions with the attribute.
+ */
+#if __has_attribute(disable_sanitizer_instrumentation)
+# define __disable_sanitizer_instrumentation \
+ __attribute__((disable_sanitizer_instrumentation))
+#else
+# define __disable_sanitizer_instrumentation
+#endif
+
+/*
* gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Function-Attributes.html#index-weak-function-attribute
* gcc: https://gcc.gnu.org/onlinedocs/gcc/Common-Variable-Attributes.html#index-weak-variable-attribute
*/
diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h
index 1d32f4c03c9e..3c1795fdb568 100644
--- a/include/linux/compiler_types.h
+++ b/include/linux/compiler_types.h
@@ -198,9 +198,20 @@ struct ftrace_likely_data {
# define __no_kasan_or_inline __always_inline
#endif
-#define __no_kcsan __no_sanitize_thread
#ifdef __SANITIZE_THREAD__
+/*
+ * Clang still emits instrumentation for __tsan_func_{entry,exit}() and builtin
+ * atomics even with __no_sanitize_thread (to avoid false positives in userspace
+ * ThreadSanitizer). The kernel's requirements are stricter and we really do not
+ * want any instrumentation with __no_kcsan.
+ *
+ * Therefore we add __disable_sanitizer_instrumentation where available to
+ * disable all instrumentation. See Kconfig.kcsan where this is mandatory.
+ */
+# define __no_kcsan __no_sanitize_thread __disable_sanitizer_instrumentation
# define __no_sanitize_or_inline __no_kcsan notrace __maybe_unused
+#else
+# define __no_kcsan
#endif
#ifndef __no_sanitize_or_inline
diff --git a/include/linux/kcsan-checks.h b/include/linux/kcsan-checks.h
index 5f5965246877..92f3843d9ebb 100644
--- a/include/linux/kcsan-checks.h
+++ b/include/linux/kcsan-checks.h
@@ -36,6 +36,36 @@
*/
void __kcsan_check_access(const volatile void *ptr, size_t size, int type);
+/*
+ * See definition of __tsan_atomic_signal_fence() in kernel/kcsan/core.c.
+ * Note: The mappings are arbitrary, and do not reflect any real mappings of C11
+ * memory orders to the LKMM memory orders and vice-versa!
+ */
+#define __KCSAN_BARRIER_TO_SIGNAL_FENCE_mb __ATOMIC_SEQ_CST
+#define __KCSAN_BARRIER_TO_SIGNAL_FENCE_wmb __ATOMIC_ACQ_REL
+#define __KCSAN_BARRIER_TO_SIGNAL_FENCE_rmb __ATOMIC_ACQUIRE
+#define __KCSAN_BARRIER_TO_SIGNAL_FENCE_release __ATOMIC_RELEASE
+
+/**
+ * __kcsan_mb - full memory barrier instrumentation
+ */
+void __kcsan_mb(void);
+
+/**
+ * __kcsan_wmb - write memory barrier instrumentation
+ */
+void __kcsan_wmb(void);
+
+/**
+ * __kcsan_rmb - read memory barrier instrumentation
+ */
+void __kcsan_rmb(void);
+
+/**
+ * __kcsan_release - release barrier instrumentation
+ */
+void __kcsan_release(void);
+
/**
* kcsan_disable_current - disable KCSAN for the current context
*
@@ -99,7 +129,15 @@ void kcsan_set_access_mask(unsigned long mask);
/* Scoped access information. */
struct kcsan_scoped_access {
- struct list_head list;
+ union {
+ struct list_head list; /* scoped_accesses list */
+ /*
+ * Not an entry in scoped_accesses list; stack depth from where
+ * the access was initialized.
+ */
+ int stack_depth;
+ };
+
/* Access information. */
const volatile void *ptr;
size_t size;
@@ -151,6 +189,10 @@ void kcsan_end_scoped_access(struct kcsan_scoped_access *sa);
static inline void __kcsan_check_access(const volatile void *ptr, size_t size,
int type) { }
+static inline void __kcsan_mb(void) { }
+static inline void __kcsan_wmb(void) { }
+static inline void __kcsan_rmb(void) { }
+static inline void __kcsan_release(void) { }
static inline void kcsan_disable_current(void) { }
static inline void kcsan_enable_current(void) { }
static inline void kcsan_enable_current_nowarn(void) { }
@@ -183,12 +225,47 @@ static inline void kcsan_end_scoped_access(struct kcsan_scoped_access *sa) { }
*/
#define __kcsan_disable_current kcsan_disable_current
#define __kcsan_enable_current kcsan_enable_current_nowarn
-#else
+#else /* __SANITIZE_THREAD__ */
static inline void kcsan_check_access(const volatile void *ptr, size_t size,
int type) { }
static inline void __kcsan_enable_current(void) { }
static inline void __kcsan_disable_current(void) { }
-#endif
+#endif /* __SANITIZE_THREAD__ */
+
+#if defined(CONFIG_KCSAN_WEAK_MEMORY) && defined(__SANITIZE_THREAD__)
+/*
+ * Normal barrier instrumentation is not done via explicit calls, but by mapping
+ * to a repurposed __atomic_signal_fence(), which normally does not generate any
+ * real instructions, but is still intercepted by fsanitize=thread. This means,
+ * like any other compile-time instrumentation, barrier instrumentation can be
+ * disabled with the __no_kcsan function attribute.
+ *
+ * Also see definition of __tsan_atomic_signal_fence() in kernel/kcsan/core.c.
+ *
+ * These are all macros, like <asm/barrier.h>, since some architectures use them
+ * in non-static inline functions.
+ */
+#define __KCSAN_BARRIER_TO_SIGNAL_FENCE(name) \
+ do { \
+ barrier(); \
+ __atomic_signal_fence(__KCSAN_BARRIER_TO_SIGNAL_FENCE_##name); \
+ barrier(); \
+ } while (0)
+#define kcsan_mb() __KCSAN_BARRIER_TO_SIGNAL_FENCE(mb)
+#define kcsan_wmb() __KCSAN_BARRIER_TO_SIGNAL_FENCE(wmb)
+#define kcsan_rmb() __KCSAN_BARRIER_TO_SIGNAL_FENCE(rmb)
+#define kcsan_release() __KCSAN_BARRIER_TO_SIGNAL_FENCE(release)
+#elif defined(CONFIG_KCSAN_WEAK_MEMORY) && defined(__KCSAN_INSTRUMENT_BARRIERS__)
+#define kcsan_mb __kcsan_mb
+#define kcsan_wmb __kcsan_wmb
+#define kcsan_rmb __kcsan_rmb
+#define kcsan_release __kcsan_release
+#else /* CONFIG_KCSAN_WEAK_MEMORY && ... */
+#define kcsan_mb() do { } while (0)
+#define kcsan_wmb() do { } while (0)
+#define kcsan_rmb() do { } while (0)
+#define kcsan_release() do { } while (0)
+#endif /* CONFIG_KCSAN_WEAK_MEMORY && ... */
/**
* __kcsan_check_read - check regular read access for races
diff --git a/include/linux/kcsan.h b/include/linux/kcsan.h
index fc266ecb2a4d..c07c71f5ba4f 100644
--- a/include/linux/kcsan.h
+++ b/include/linux/kcsan.h
@@ -21,6 +21,7 @@
*/
struct kcsan_ctx {
int disable_count; /* disable counter */
+ int disable_scoped; /* disable scoped access counter */
int atomic_next; /* number of following atomic ops */
/*
@@ -48,8 +49,16 @@ struct kcsan_ctx {
*/
unsigned long access_mask;
- /* List of scoped accesses. */
+ /* List of scoped accesses; likely to be empty. */
struct list_head scoped_accesses;
+
+#ifdef CONFIG_KCSAN_WEAK_MEMORY
+ /*
+ * Scoped access for modeling access reordering to detect missing memory
+ * barriers; only keep 1 to keep fast-path complexity manageable.
+ */
+ struct kcsan_scoped_access reorder_access;
+#endif
};
/**
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 78c351e35fec..0cd40b010487 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1339,6 +1339,9 @@ struct task_struct {
#ifdef CONFIG_TRACE_IRQFLAGS
struct irqtrace_events kcsan_save_irqtrace;
#endif
+#ifdef CONFIG_KCSAN_WEAK_MEMORY
+ int kcsan_stack_depth;
+#endif
#endif
#if IS_ENABLED(CONFIG_KUNIT)
diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h
index b4e5ca23f840..5c0c5174155d 100644
--- a/include/linux/spinlock.h
+++ b/include/linux/spinlock.h
@@ -171,7 +171,7 @@ do { \
* Architectures that can implement ACQUIRE better need to take care.
*/
#ifndef smp_mb__after_spinlock
-#define smp_mb__after_spinlock() do { } while (0)
+#define smp_mb__after_spinlock() kcsan_mb()
#endif
#ifdef CONFIG_DEBUG_SPINLOCK
diff --git a/init/init_task.c b/init/init_task.c
index 2d024066e27b..73cc8f03511a 100644
--- a/init/init_task.c
+++ b/init/init_task.c
@@ -182,11 +182,6 @@ struct task_struct init_task
#endif
#ifdef CONFIG_KCSAN
.kcsan_ctx = {
- .disable_count = 0,
- .atomic_next = 0,
- .atomic_nest_count = 0,
- .in_flat_atomic = false,
- .access_mask = 0,
.scoped_accesses = {LIST_POISON1, NULL},
},
#endif
diff --git a/kernel/kcsan/Makefile b/kernel/kcsan/Makefile
index e893b0e1d62a..4f35d1bced6a 100644
--- a/kernel/kcsan/Makefile
+++ b/kernel/kcsan/Makefile
@@ -12,6 +12,8 @@ CFLAGS_core.o := $(call cc-option,-fno-conserve-stack) \
-fno-stack-protector -DDISABLE_BRANCH_PROFILING
obj-y := core.o debugfs.o report.o
+
+KCSAN_INSTRUMENT_BARRIERS_selftest.o := y
obj-$(CONFIG_KCSAN_SELFTEST) += selftest.o
CFLAGS_kcsan_test.o := $(CFLAGS_KCSAN) -g -fno-omit-frame-pointer
diff --git a/kernel/kcsan/core.c b/kernel/kcsan/core.c
index 4b84c8e7884b..fe12dfe254ec 100644
--- a/kernel/kcsan/core.c
+++ b/kernel/kcsan/core.c
@@ -40,15 +40,17 @@ module_param_named(udelay_interrupt, kcsan_udelay_interrupt, uint, 0644);
module_param_named(skip_watch, kcsan_skip_watch, long, 0644);
module_param_named(interrupt_watcher, kcsan_interrupt_watcher, bool, 0444);
+#ifdef CONFIG_KCSAN_WEAK_MEMORY
+static bool kcsan_weak_memory = true;
+module_param_named(weak_memory, kcsan_weak_memory, bool, 0644);
+#else
+#define kcsan_weak_memory false
+#endif
+
bool kcsan_enabled;
/* Per-CPU kcsan_ctx for interrupts */
static DEFINE_PER_CPU(struct kcsan_ctx, kcsan_cpu_ctx) = {
- .disable_count = 0,
- .atomic_next = 0,
- .atomic_nest_count = 0,
- .in_flat_atomic = false,
- .access_mask = 0,
.scoped_accesses = {LIST_POISON1, NULL},
};
@@ -209,15 +211,17 @@ check_access(const volatile void *ptr, size_t size, int type, unsigned long ip);
static noinline void kcsan_check_scoped_accesses(void)
{
struct kcsan_ctx *ctx = get_ctx();
- struct list_head *prev_save = ctx->scoped_accesses.prev;
struct kcsan_scoped_access *scoped_access;
- ctx->scoped_accesses.prev = NULL; /* Avoid recursion. */
+ if (ctx->disable_scoped)
+ return;
+
+ ctx->disable_scoped++;
list_for_each_entry(scoped_access, &ctx->scoped_accesses, list) {
check_access(scoped_access->ptr, scoped_access->size,
scoped_access->type, scoped_access->ip);
}
- ctx->scoped_accesses.prev = prev_save;
+ ctx->disable_scoped--;
}
/* Rules for generic atomic accesses. Called from fast-path. */
@@ -325,6 +329,21 @@ static void delay_access(int type)
udelay(delay);
}
+/*
+ * Reads the instrumented memory for value change detection; value change
+ * detection is currently done for accesses up to a size of 8 bytes.
+ */
+static __always_inline u64 read_instrumented_memory(const volatile void *ptr, size_t size)
+{
+ switch (size) {
+ case 1: return READ_ONCE(*(const u8 *)ptr);
+ case 2: return READ_ONCE(*(const u16 *)ptr);
+ case 4: return READ_ONCE(*(const u32 *)ptr);
+ case 8: return READ_ONCE(*(const u64 *)ptr);
+ default: return 0; /* Ignore; we do not diff the values. */
+ }
+}
+
void kcsan_save_irqtrace(struct task_struct *task)
{
#ifdef CONFIG_TRACE_IRQFLAGS
@@ -339,6 +358,76 @@ void kcsan_restore_irqtrace(struct task_struct *task)
#endif
}
+static __always_inline int get_kcsan_stack_depth(void)
+{
+#ifdef CONFIG_KCSAN_WEAK_MEMORY
+ return current->kcsan_stack_depth;
+#else
+ BUILD_BUG();
+ return 0;
+#endif
+}
+
+static __always_inline void add_kcsan_stack_depth(int val)
+{
+#ifdef CONFIG_KCSAN_WEAK_MEMORY
+ current->kcsan_stack_depth += val;
+#else
+ BUILD_BUG();
+#endif
+}
+
+static __always_inline struct kcsan_scoped_access *get_reorder_access(struct kcsan_ctx *ctx)
+{
+#ifdef CONFIG_KCSAN_WEAK_MEMORY
+ return ctx->disable_scoped ? NULL : &ctx->reorder_access;
+#else
+ return NULL;
+#endif
+}
+
+static __always_inline bool
+find_reorder_access(struct kcsan_ctx *ctx, const volatile void *ptr, size_t size,
+ int type, unsigned long ip)
+{
+ struct kcsan_scoped_access *reorder_access = get_reorder_access(ctx);
+
+ if (!reorder_access)
+ return false;
+
+ /*
+ * Note: If accesses are repeated while reorder_access is identical,
+ * never matches the new access, because !(type & KCSAN_ACCESS_SCOPED).
+ */
+ return reorder_access->ptr == ptr && reorder_access->size == size &&
+ reorder_access->type == type && reorder_access->ip == ip;
+}
+
+static inline void
+set_reorder_access(struct kcsan_ctx *ctx, const volatile void *ptr, size_t size,
+ int type, unsigned long ip)
+{
+ struct kcsan_scoped_access *reorder_access = get_reorder_access(ctx);
+
+ if (!reorder_access || !kcsan_weak_memory)
+ return;
+
+ /*
+ * To avoid nested interrupts or scheduler (which share kcsan_ctx)
+ * reading an inconsistent reorder_access, ensure that the below has
+ * exclusive access to reorder_access by disallowing concurrent use.
+ */
+ ctx->disable_scoped++;
+ barrier();
+ reorder_access->ptr = ptr;
+ reorder_access->size = size;
+ reorder_access->type = type | KCSAN_ACCESS_SCOPED;
+ reorder_access->ip = ip;
+ reorder_access->stack_depth = get_kcsan_stack_depth();
+ barrier();
+ ctx->disable_scoped--;
+}
+
/*
* Pull everything together: check_access() below contains the performance
* critical operations; the fast-path (including check_access) functions should
@@ -377,8 +466,10 @@ static noinline void kcsan_found_watchpoint(const volatile void *ptr,
* The access_mask check relies on value-change comparison. To avoid
* reporting a race where e.g. the writer set up the watchpoint, but the
* reader has access_mask!=0, we have to ignore the found watchpoint.
+ *
+ * reorder_access is never created from an access with access_mask set.
*/
- if (ctx->access_mask)
+ if (ctx->access_mask && !find_reorder_access(ctx, ptr, size, type, ip))
return;
/*
@@ -428,11 +519,13 @@ kcsan_setup_watchpoint(const volatile void *ptr, size_t size, int type, unsigned
const bool is_assert = (type & KCSAN_ACCESS_ASSERT) != 0;
atomic_long_t *watchpoint;
u64 old, new, diff;
- unsigned long access_mask;
enum kcsan_value_change value_change = KCSAN_VALUE_CHANGE_MAYBE;
+ bool interrupt_watcher = kcsan_interrupt_watcher;
unsigned long ua_flags = user_access_save();
struct kcsan_ctx *ctx = get_ctx();
+ unsigned long access_mask = ctx->access_mask;
unsigned long irq_flags = 0;
+ bool is_reorder_access;
/*
* Always reset kcsan_skip counter in slow-path to avoid underflow; see
@@ -456,12 +549,32 @@ kcsan_setup_watchpoint(const volatile void *ptr, size_t size, int type, unsigned
}
/*
+ * The local CPU cannot observe reordering of its own accesses, and
+ * therefore we need to take care of 2 cases to avoid false positives:
+ *
+ * 1. Races of the reordered access with interrupts. To avoid, if
+ * the current access is reorder_access, disable interrupts.
+ * 2. Avoid races of scoped accesses from nested interrupts (below).
+ */
+ is_reorder_access = find_reorder_access(ctx, ptr, size, type, ip);
+ if (is_reorder_access)
+ interrupt_watcher = false;
+ /*
+ * Avoid races of scoped accesses from nested interrupts (or scheduler).
+ * Assume setting up a watchpoint for a non-scoped (normal) access that
+ * also conflicts with a current scoped access. In a nested interrupt,
+ * which shares the context, it would check a conflicting scoped access.
+ * To avoid, disable scoped access checking.
+ */
+ ctx->disable_scoped++;
+
+ /*
* Save and restore the IRQ state trace touched by KCSAN, since KCSAN's
* runtime is entered for every memory access, and potentially useful
* information is lost if dirtied by KCSAN.
*/
kcsan_save_irqtrace(current);
- if (!kcsan_interrupt_watcher)
+ if (!interrupt_watcher)
local_irq_save(irq_flags);
watchpoint = insert_watchpoint((unsigned long)ptr, size, is_write);
@@ -482,23 +595,7 @@ kcsan_setup_watchpoint(const volatile void *ptr, size_t size, int type, unsigned
* Read the current value, to later check and infer a race if the data
* was modified via a non-instrumented access, e.g. from a device.
*/
- old = 0;
- switch (size) {
- case 1:
- old = READ_ONCE(*(const u8 *)ptr);
- break;
- case 2:
- old = READ_ONCE(*(const u16 *)ptr);
- break;
- case 4:
- old = READ_ONCE(*(const u32 *)ptr);
- break;
- case 8:
- old = READ_ONCE(*(const u64 *)ptr);
- break;
- default:
- break; /* ignore; we do not diff the values */
- }
+ old = is_reorder_access ? 0 : read_instrumented_memory(ptr, size);
/*
* Delay this thread, to increase probability of observing a racy
@@ -510,23 +607,16 @@ kcsan_setup_watchpoint(const volatile void *ptr, size_t size, int type, unsigned
* Re-read value, and check if it is as expected; if not, we infer a
* racy access.
*/
- access_mask = ctx->access_mask;
- new = 0;
- switch (size) {
- case 1:
- new = READ_ONCE(*(const u8 *)ptr);
- break;
- case 2:
- new = READ_ONCE(*(const u16 *)ptr);
- break;
- case 4:
- new = READ_ONCE(*(const u32 *)ptr);
- break;
- case 8:
- new = READ_ONCE(*(const u64 *)ptr);
- break;
- default:
- break; /* ignore; we do not diff the values */
+ if (!is_reorder_access) {
+ new = read_instrumented_memory(ptr, size);
+ } else {
+ /*
+ * Reordered accesses cannot be used for value change detection,
+ * because the memory location may no longer be accessible and
+ * could result in a fault.
+ */
+ new = 0;
+ access_mask = 0;
}
diff = old ^ new;
@@ -596,10 +686,20 @@ kcsan_setup_watchpoint(const volatile void *ptr, size_t size, int type, unsigned
*/
remove_watchpoint(watchpoint);
atomic_long_dec(&kcsan_counters[KCSAN_COUNTER_USED_WATCHPOINTS]);
+
out_unlock:
- if (!kcsan_interrupt_watcher)
+ if (!interrupt_watcher)
local_irq_restore(irq_flags);
kcsan_restore_irqtrace(current);
+ ctx->disable_scoped--;
+
+ /*
+ * Reordered accesses cannot be used for value change detection,
+ * therefore never consider for reordering if access_mask is set.
+ * ASSERT_EXCLUSIVE are not real accesses, ignore them as well.
+ */
+ if (!access_mask && !is_assert)
+ set_reorder_access(ctx, ptr, size, type, ip);
out:
user_access_restore(ua_flags);
}
@@ -607,7 +707,6 @@ out:
static __always_inline void
check_access(const volatile void *ptr, size_t size, int type, unsigned long ip)
{
- const bool is_write = (type & KCSAN_ACCESS_WRITE) != 0;
atomic_long_t *watchpoint;
long encoded_watchpoint;
@@ -618,12 +717,14 @@ check_access(const volatile void *ptr, size_t size, int type, unsigned long ip)
if (unlikely(size == 0))
return;
+again:
/*
* Avoid user_access_save in fast-path: find_watchpoint is safe without
* user_access_save, as the address that ptr points to is only used to
* check if a watchpoint exists; ptr is never dereferenced.
*/
- watchpoint = find_watchpoint((unsigned long)ptr, size, !is_write,
+ watchpoint = find_watchpoint((unsigned long)ptr, size,
+ !(type & KCSAN_ACCESS_WRITE),
&encoded_watchpoint);
/*
* It is safe to check kcsan_is_enabled() after find_watchpoint in the
@@ -637,9 +738,42 @@ check_access(const volatile void *ptr, size_t size, int type, unsigned long ip)
else {
struct kcsan_ctx *ctx = get_ctx(); /* Call only once in fast-path. */
- if (unlikely(should_watch(ctx, ptr, size, type)))
+ if (unlikely(should_watch(ctx, ptr, size, type))) {
kcsan_setup_watchpoint(ptr, size, type, ip);
- else if (unlikely(ctx->scoped_accesses.prev))
+ return;
+ }
+
+ if (!(type & KCSAN_ACCESS_SCOPED)) {
+ struct kcsan_scoped_access *reorder_access = get_reorder_access(ctx);
+
+ if (reorder_access) {
+ /*
+ * reorder_access check: simulates reordering of
+ * the access after subsequent operations.
+ */
+ ptr = reorder_access->ptr;
+ type = reorder_access->type;
+ ip = reorder_access->ip;
+ /*
+ * Upon a nested interrupt, this context's
+ * reorder_access can be modified (shared ctx).
+ * We know that upon return, reorder_access is
+ * always invalidated by setting size to 0 via
+ * __tsan_func_exit(). Therefore we must read
+ * and check size after the other fields.
+ */
+ barrier();
+ size = READ_ONCE(reorder_access->size);
+ if (size)
+ goto again;
+ }
+ }
+
+ /*
+ * Always checked last, right before returning from runtime;
+ * if reorder_access is valid, checked after it was checked.
+ */
+ if (unlikely(ctx->scoped_accesses.prev))
kcsan_check_scoped_accesses();
}
}
@@ -814,6 +948,22 @@ void __kcsan_check_access(const volatile void *ptr, size_t size, int type)
}
EXPORT_SYMBOL(__kcsan_check_access);
+#define DEFINE_MEMORY_BARRIER(name, order_before_cond) \
+ void __kcsan_##name(void) \
+ { \
+ struct kcsan_scoped_access *sa = get_reorder_access(get_ctx()); \
+ if (!sa) \
+ return; \
+ if (order_before_cond) \
+ sa->size = 0; \
+ } \
+ EXPORT_SYMBOL(__kcsan_##name)
+
+DEFINE_MEMORY_BARRIER(mb, true);
+DEFINE_MEMORY_BARRIER(wmb, sa->type & (KCSAN_ACCESS_WRITE | KCSAN_ACCESS_COMPOUND));
+DEFINE_MEMORY_BARRIER(rmb, !(sa->type & KCSAN_ACCESS_WRITE) || (sa->type & KCSAN_ACCESS_COMPOUND));
+DEFINE_MEMORY_BARRIER(release, true);
+
/*
* KCSAN uses the same instrumentation that is emitted by supported compilers
* for ThreadSanitizer (TSAN).
@@ -926,19 +1076,56 @@ DEFINE_TSAN_VOLATILE_READ_WRITE(8);
DEFINE_TSAN_VOLATILE_READ_WRITE(16);
/*
- * The below are not required by KCSAN, but can still be emitted by the
- * compiler.
+ * Function entry and exit are used to determine the validty of reorder_access.
+ * Reordering of the access ends at the end of the function scope where the
+ * access happened. This is done for two reasons:
+ *
+ * 1. Artificially limits the scope where missing barriers are detected.
+ * This minimizes false positives due to uninstrumented functions that
+ * contain the required barriers but were missed.
+ *
+ * 2. Simplifies generating the stack trace of the access.
*/
void __tsan_func_entry(void *call_pc);
-void __tsan_func_entry(void *call_pc)
+noinline void __tsan_func_entry(void *call_pc)
{
+ if (!IS_ENABLED(CONFIG_KCSAN_WEAK_MEMORY))
+ return;
+
+ add_kcsan_stack_depth(1);
}
EXPORT_SYMBOL(__tsan_func_entry);
+
void __tsan_func_exit(void);
-void __tsan_func_exit(void)
+noinline void __tsan_func_exit(void)
{
+ struct kcsan_scoped_access *reorder_access;
+
+ if (!IS_ENABLED(CONFIG_KCSAN_WEAK_MEMORY))
+ return;
+
+ reorder_access = get_reorder_access(get_ctx());
+ if (!reorder_access)
+ goto out;
+
+ if (get_kcsan_stack_depth() <= reorder_access->stack_depth) {
+ /*
+ * Access check to catch cases where write without a barrier
+ * (supposed release) was last access in function: because
+ * instrumentation is inserted before the real access, a data
+ * race due to the write giving up a c-s would only be caught if
+ * we do the conflicting access after.
+ */
+ check_access(reorder_access->ptr, reorder_access->size,
+ reorder_access->type, reorder_access->ip);
+ reorder_access->size = 0;
+ reorder_access->stack_depth = INT_MIN;
+ }
+out:
+ add_kcsan_stack_depth(-1);
}
EXPORT_SYMBOL(__tsan_func_exit);
+
void __tsan_init(void);
void __tsan_init(void)
{
@@ -961,10 +1148,19 @@ EXPORT_SYMBOL(__tsan_init);
* functions, whose job is to also execute the operation itself.
*/
+static __always_inline void kcsan_atomic_builtin_memorder(int memorder)
+{
+ if (memorder == __ATOMIC_RELEASE ||
+ memorder == __ATOMIC_SEQ_CST ||
+ memorder == __ATOMIC_ACQ_REL)
+ __kcsan_release();
+}
+
#define DEFINE_TSAN_ATOMIC_LOAD_STORE(bits) \
u##bits __tsan_atomic##bits##_load(const u##bits *ptr, int memorder); \
u##bits __tsan_atomic##bits##_load(const u##bits *ptr, int memorder) \
{ \
+ kcsan_atomic_builtin_memorder(memorder); \
if (!IS_ENABLED(CONFIG_KCSAN_IGNORE_ATOMICS)) { \
check_access(ptr, bits / BITS_PER_BYTE, KCSAN_ACCESS_ATOMIC, _RET_IP_); \
} \
@@ -974,6 +1170,7 @@ EXPORT_SYMBOL(__tsan_init);
void __tsan_atomic##bits##_store(u##bits *ptr, u##bits v, int memorder); \
void __tsan_atomic##bits##_store(u##bits *ptr, u##bits v, int memorder) \
{ \
+ kcsan_atomic_builtin_memorder(memorder); \
if (!IS_ENABLED(CONFIG_KCSAN_IGNORE_ATOMICS)) { \
check_access(ptr, bits / BITS_PER_BYTE, \
KCSAN_ACCESS_WRITE | KCSAN_ACCESS_ATOMIC, _RET_IP_); \
@@ -986,6 +1183,7 @@ EXPORT_SYMBOL(__tsan_init);
u##bits __tsan_atomic##bits##_##op(u##bits *ptr, u##bits v, int memorder); \
u##bits __tsan_atomic##bits##_##op(u##bits *ptr, u##bits v, int memorder) \
{ \
+ kcsan_atomic_builtin_memorder(memorder); \
if (!IS_ENABLED(CONFIG_KCSAN_IGNORE_ATOMICS)) { \
check_access(ptr, bits / BITS_PER_BYTE, \
KCSAN_ACCESS_COMPOUND | KCSAN_ACCESS_WRITE | \
@@ -1018,6 +1216,7 @@ EXPORT_SYMBOL(__tsan_init);
int __tsan_atomic##bits##_compare_exchange_##strength(u##bits *ptr, u##bits *exp, \
u##bits val, int mo, int fail_mo) \
{ \
+ kcsan_atomic_builtin_memorder(mo); \
if (!IS_ENABLED(CONFIG_KCSAN_IGNORE_ATOMICS)) { \
check_access(ptr, bits / BITS_PER_BYTE, \
KCSAN_ACCESS_COMPOUND | KCSAN_ACCESS_WRITE | \
@@ -1033,6 +1232,7 @@ EXPORT_SYMBOL(__tsan_init);
u##bits __tsan_atomic##bits##_compare_exchange_val(u##bits *ptr, u##bits exp, u##bits val, \
int mo, int fail_mo) \
{ \
+ kcsan_atomic_builtin_memorder(mo); \
if (!IS_ENABLED(CONFIG_KCSAN_IGNORE_ATOMICS)) { \
check_access(ptr, bits / BITS_PER_BYTE, \
KCSAN_ACCESS_COMPOUND | KCSAN_ACCESS_WRITE | \
@@ -1064,10 +1264,47 @@ DEFINE_TSAN_ATOMIC_OPS(64);
void __tsan_atomic_thread_fence(int memorder);
void __tsan_atomic_thread_fence(int memorder)
{
+ kcsan_atomic_builtin_memorder(memorder);
__atomic_thread_fence(memorder);
}
EXPORT_SYMBOL(__tsan_atomic_thread_fence);
+/*
+ * In instrumented files, we emit instrumentation for barriers by mapping the
+ * kernel barriers to an __atomic_signal_fence(), which is interpreted specially
+ * and otherwise has no relation to a real __atomic_signal_fence(). No known
+ * kernel code uses __atomic_signal_fence().
+ *
+ * Since fsanitize=thread instrumentation handles __atomic_signal_fence(), which
+ * are turned into calls to __tsan_atomic_signal_fence(), such instrumentation
+ * can be disabled via the __no_kcsan function attribute (vs. an explicit call
+ * which could not). When __no_kcsan is requested, __atomic_signal_fence()
+ * generates no code.
+ *
+ * Note: The result of using __atomic_signal_fence() with KCSAN enabled is
+ * potentially limiting the compiler's ability to reorder operations; however,
+ * if barriers were instrumented with explicit calls (without LTO), the compiler
+ * couldn't optimize much anyway. The result of a hypothetical architecture
+ * using __atomic_signal_fence() in normal code would be KCSAN false negatives.
+ */
void __tsan_atomic_signal_fence(int memorder);
-void __tsan_atomic_signal_fence(int memorder) { }
+noinline void __tsan_atomic_signal_fence(int memorder)
+{
+ switch (memorder) {
+ case __KCSAN_BARRIER_TO_SIGNAL_FENCE_mb:
+ __kcsan_mb();
+ break;
+ case __KCSAN_BARRIER_TO_SIGNAL_FENCE_wmb:
+ __kcsan_wmb();
+ break;
+ case __KCSAN_BARRIER_TO_SIGNAL_FENCE_rmb:
+ __kcsan_rmb();
+ break;
+ case __KCSAN_BARRIER_TO_SIGNAL_FENCE_release:
+ __kcsan_release();
+ break;
+ default:
+ break;
+ }
+}
EXPORT_SYMBOL(__tsan_atomic_signal_fence);
diff --git a/kernel/kcsan/kcsan_test.c b/kernel/kcsan/kcsan_test.c
index 660729238588..a36fca063a73 100644
--- a/kernel/kcsan/kcsan_test.c
+++ b/kernel/kcsan/kcsan_test.c
@@ -16,9 +16,12 @@
#define pr_fmt(fmt) "kcsan_test: " fmt
#include <kunit/test.h>
+#include <linux/atomic.h>
+#include <linux/bitops.h>
#include <linux/jiffies.h>
#include <linux/kcsan-checks.h>
#include <linux/kernel.h>
+#include <linux/mutex.h>
#include <linux/sched.h>
#include <linux/seqlock.h>
#include <linux/spinlock.h>
@@ -151,7 +154,7 @@ struct expect_report {
/* Check observed report matches information in @r. */
__no_kcsan
-static bool report_matches(const struct expect_report *r)
+static bool __report_matches(const struct expect_report *r)
{
const bool is_assert = (r->access[0].type | r->access[1].type) & KCSAN_ACCESS_ASSERT;
bool ret = false;
@@ -213,9 +216,9 @@ static bool report_matches(const struct expect_report *r)
const bool is_atomic = (ty & KCSAN_ACCESS_ATOMIC);
const bool is_scoped = (ty & KCSAN_ACCESS_SCOPED);
const char *const access_type_aux =
- (is_atomic && is_scoped) ? " (marked, scoped)"
+ (is_atomic && is_scoped) ? " (marked, reordered)"
: (is_atomic ? " (marked)"
- : (is_scoped ? " (scoped)" : ""));
+ : (is_scoped ? " (reordered)" : ""));
if (i == 1) {
/* Access 2 */
@@ -253,6 +256,40 @@ out:
return ret;
}
+static __always_inline const struct expect_report *
+__report_set_scoped(struct expect_report *r, int accesses)
+{
+ BUILD_BUG_ON(accesses > 3);
+
+ if (accesses & 1)
+ r->access[0].type |= KCSAN_ACCESS_SCOPED;
+ else
+ r->access[0].type &= ~KCSAN_ACCESS_SCOPED;
+
+ if (accesses & 2)
+ r->access[1].type |= KCSAN_ACCESS_SCOPED;
+ else
+ r->access[1].type &= ~KCSAN_ACCESS_SCOPED;
+
+ return r;
+}
+
+__no_kcsan
+static bool report_matches_any_reordered(struct expect_report *r)
+{
+ return __report_matches(__report_set_scoped(r, 0)) ||
+ __report_matches(__report_set_scoped(r, 1)) ||
+ __report_matches(__report_set_scoped(r, 2)) ||
+ __report_matches(__report_set_scoped(r, 3));
+}
+
+#ifdef CONFIG_KCSAN_WEAK_MEMORY
+/* Due to reordering accesses, any access may appear as "(reordered)". */
+#define report_matches report_matches_any_reordered
+#else
+#define report_matches __report_matches
+#endif
+
/* ===== Test kernels ===== */
static long test_sink;
@@ -263,6 +300,8 @@ static struct {
long val[8];
} test_struct;
static DEFINE_SEQLOCK(test_seqlock);
+static DEFINE_SPINLOCK(test_spinlock);
+static DEFINE_MUTEX(test_mutex);
/*
* Helper to avoid compiler optimizing out reads, and to generate source values
@@ -271,6 +310,16 @@ static DEFINE_SEQLOCK(test_seqlock);
__no_kcsan
static noinline void sink_value(long v) { WRITE_ONCE(test_sink, v); }
+/*
+ * Generates a delay and some accesses that enter the runtime but do not produce
+ * data races.
+ */
+static noinline void test_delay(int iter)
+{
+ while (iter--)
+ sink_value(READ_ONCE(test_sink));
+}
+
static noinline void test_kernel_read(void) { sink_value(test_var); }
static noinline void test_kernel_write(void)
@@ -432,19 +481,239 @@ static noinline void test_kernel_xor_1bit(void)
kcsan_nestable_atomic_end();
}
+#define TEST_KERNEL_LOCKED(name, acquire, release) \
+ static noinline void test_kernel_##name(void) \
+ { \
+ long *flag = &test_struct.val[0]; \
+ long v = 0; \
+ if (!(acquire)) \
+ return; \
+ while (v++ < 100) { \
+ test_var++; \
+ barrier(); \
+ } \
+ release; \
+ test_delay(10); \
+ }
+
+TEST_KERNEL_LOCKED(with_memorder,
+ cmpxchg_acquire(flag, 0, 1) == 0,
+ smp_store_release(flag, 0));
+TEST_KERNEL_LOCKED(wrong_memorder,
+ cmpxchg_relaxed(flag, 0, 1) == 0,
+ WRITE_ONCE(*flag, 0));
+TEST_KERNEL_LOCKED(atomic_builtin_with_memorder,
+ __atomic_compare_exchange_n(flag, &v, 1, 0, __ATOMIC_ACQUIRE, __ATOMIC_RELAXED),
+ __atomic_store_n(flag, 0, __ATOMIC_RELEASE));
+TEST_KERNEL_LOCKED(atomic_builtin_wrong_memorder,
+ __atomic_compare_exchange_n(flag, &v, 1, 0, __ATOMIC_RELAXED, __ATOMIC_RELAXED),
+ __atomic_store_n(flag, 0, __ATOMIC_RELAXED));
+
/* ===== Test cases ===== */
+/*
+ * Tests that various barriers have the expected effect on internal state. Not
+ * exhaustive on atomic_t operations. Unlike the selftest, also checks for
+ * too-strict barrier instrumentation; these can be tolerated, because it does
+ * not cause false positives, but at least we should be aware of such cases.
+ */
+static void test_barrier_nothreads(struct kunit *test)
+{
+#ifdef CONFIG_KCSAN_WEAK_MEMORY
+ struct kcsan_scoped_access *reorder_access = &current->kcsan_ctx.reorder_access;
+#else
+ struct kcsan_scoped_access *reorder_access = NULL;
+#endif
+ arch_spinlock_t arch_spinlock = __ARCH_SPIN_LOCK_UNLOCKED;
+ atomic_t dummy;
+
+ KCSAN_TEST_REQUIRES(test, reorder_access != NULL);
+ KCSAN_TEST_REQUIRES(test, IS_ENABLED(CONFIG_SMP));
+
+#define __KCSAN_EXPECT_BARRIER(access_type, barrier, order_before, name) \
+ do { \
+ reorder_access->type = (access_type) | KCSAN_ACCESS_SCOPED; \
+ reorder_access->size = sizeof(test_var); \
+ barrier; \
+ KUNIT_EXPECT_EQ_MSG(test, reorder_access->size, \
+ order_before ? 0 : sizeof(test_var), \
+ "improperly instrumented type=(" #access_type "): " name); \
+ } while (0)
+#define KCSAN_EXPECT_READ_BARRIER(b, o) __KCSAN_EXPECT_BARRIER(0, b, o, #b)
+#define KCSAN_EXPECT_WRITE_BARRIER(b, o) __KCSAN_EXPECT_BARRIER(KCSAN_ACCESS_WRITE, b, o, #b)
+#define KCSAN_EXPECT_RW_BARRIER(b, o) __KCSAN_EXPECT_BARRIER(KCSAN_ACCESS_COMPOUND | KCSAN_ACCESS_WRITE, b, o, #b)
+
+ /*
+ * Lockdep initialization can strengthen certain locking operations due
+ * to calling into instrumented files; "warm up" our locks.
+ */
+ spin_lock(&test_spinlock);
+ spin_unlock(&test_spinlock);
+ mutex_lock(&test_mutex);
+ mutex_unlock(&test_mutex);
+
+ /* Force creating a valid entry in reorder_access first. */
+ test_var = 0;
+ while (test_var++ < 1000000 && reorder_access->size != sizeof(test_var))
+ __kcsan_check_read(&test_var, sizeof(test_var));
+ KUNIT_ASSERT_EQ(test, reorder_access->size, sizeof(test_var));
+
+ kcsan_nestable_atomic_begin(); /* No watchpoints in called functions. */
+
+ KCSAN_EXPECT_READ_BARRIER(mb(), true);
+ KCSAN_EXPECT_READ_BARRIER(wmb(), false);
+ KCSAN_EXPECT_READ_BARRIER(rmb(), true);
+ KCSAN_EXPECT_READ_BARRIER(smp_mb(), true);
+ KCSAN_EXPECT_READ_BARRIER(smp_wmb(), false);
+ KCSAN_EXPECT_READ_BARRIER(smp_rmb(), true);
+ KCSAN_EXPECT_READ_BARRIER(dma_wmb(), false);
+ KCSAN_EXPECT_READ_BARRIER(dma_rmb(), true);
+ KCSAN_EXPECT_READ_BARRIER(smp_mb__before_atomic(), true);
+ KCSAN_EXPECT_READ_BARRIER(smp_mb__after_atomic(), true);
+ KCSAN_EXPECT_READ_BARRIER(smp_mb__after_spinlock(), true);
+ KCSAN_EXPECT_READ_BARRIER(smp_store_mb(test_var, 0), true);
+ KCSAN_EXPECT_READ_BARRIER(smp_load_acquire(&test_var), false);
+ KCSAN_EXPECT_READ_BARRIER(smp_store_release(&test_var, 0), true);
+ KCSAN_EXPECT_READ_BARRIER(xchg(&test_var, 0), true);
+ KCSAN_EXPECT_READ_BARRIER(xchg_release(&test_var, 0), true);
+ KCSAN_EXPECT_READ_BARRIER(xchg_relaxed(&test_var, 0), false);
+ KCSAN_EXPECT_READ_BARRIER(cmpxchg(&test_var, 0, 0), true);
+ KCSAN_EXPECT_READ_BARRIER(cmpxchg_release(&test_var, 0, 0), true);
+ KCSAN_EXPECT_READ_BARRIER(cmpxchg_relaxed(&test_var, 0, 0), false);
+ KCSAN_EXPECT_READ_BARRIER(atomic_read(&dummy), false);
+ KCSAN_EXPECT_READ_BARRIER(atomic_read_acquire(&dummy), false);
+ KCSAN_EXPECT_READ_BARRIER(atomic_set(&dummy, 0), false);
+ KCSAN_EXPECT_READ_BARRIER(atomic_set_release(&dummy, 0), true);
+ KCSAN_EXPECT_READ_BARRIER(atomic_add(1, &dummy), false);
+ KCSAN_EXPECT_READ_BARRIER(atomic_add_return(1, &dummy), true);
+ KCSAN_EXPECT_READ_BARRIER(atomic_add_return_acquire(1, &dummy), false);
+ KCSAN_EXPECT_READ_BARRIER(atomic_add_return_release(1, &dummy), true);
+ KCSAN_EXPECT_READ_BARRIER(atomic_add_return_relaxed(1, &dummy), false);
+ KCSAN_EXPECT_READ_BARRIER(atomic_fetch_add(1, &dummy), true);
+ KCSAN_EXPECT_READ_BARRIER(atomic_fetch_add_acquire(1, &dummy), false);
+ KCSAN_EXPECT_READ_BARRIER(atomic_fetch_add_release(1, &dummy), true);
+ KCSAN_EXPECT_READ_BARRIER(atomic_fetch_add_relaxed(1, &dummy), false);
+ KCSAN_EXPECT_READ_BARRIER(test_and_set_bit(0, &test_var), true);
+ KCSAN_EXPECT_READ_BARRIER(test_and_clear_bit(0, &test_var), true);
+ KCSAN_EXPECT_READ_BARRIER(test_and_change_bit(0, &test_var), true);
+ KCSAN_EXPECT_READ_BARRIER(clear_bit_unlock(0, &test_var), true);
+ KCSAN_EXPECT_READ_BARRIER(__clear_bit_unlock(0, &test_var), true);
+ KCSAN_EXPECT_READ_BARRIER(arch_spin_lock(&arch_spinlock), false);
+ KCSAN_EXPECT_READ_BARRIER(arch_spin_unlock(&arch_spinlock), true);
+ KCSAN_EXPECT_READ_BARRIER(spin_lock(&test_spinlock), false);
+ KCSAN_EXPECT_READ_BARRIER(spin_unlock(&test_spinlock), true);
+ KCSAN_EXPECT_READ_BARRIER(mutex_lock(&test_mutex), false);
+ KCSAN_EXPECT_READ_BARRIER(mutex_unlock(&test_mutex), true);
+
+ KCSAN_EXPECT_WRITE_BARRIER(mb(), true);
+ KCSAN_EXPECT_WRITE_BARRIER(wmb(), true);
+ KCSAN_EXPECT_WRITE_BARRIER(rmb(), false);
+ KCSAN_EXPECT_WRITE_BARRIER(smp_mb(), true);
+ KCSAN_EXPECT_WRITE_BARRIER(smp_wmb(), true);
+ KCSAN_EXPECT_WRITE_BARRIER(smp_rmb(), false);
+ KCSAN_EXPECT_WRITE_BARRIER(dma_wmb(), true);
+ KCSAN_EXPECT_WRITE_BARRIER(dma_rmb(), false);
+ KCSAN_EXPECT_WRITE_BARRIER(smp_mb__before_atomic(), true);
+ KCSAN_EXPECT_WRITE_BARRIER(smp_mb__after_atomic(), true);
+ KCSAN_EXPECT_WRITE_BARRIER(smp_mb__after_spinlock(), true);
+ KCSAN_EXPECT_WRITE_BARRIER(smp_store_mb(test_var, 0), true);
+ KCSAN_EXPECT_WRITE_BARRIER(smp_load_acquire(&test_var), false);
+ KCSAN_EXPECT_WRITE_BARRIER(smp_store_release(&test_var, 0), true);
+ KCSAN_EXPECT_WRITE_BARRIER(xchg(&test_var, 0), true);
+ KCSAN_EXPECT_WRITE_BARRIER(xchg_release(&test_var, 0), true);
+ KCSAN_EXPECT_WRITE_BARRIER(xchg_relaxed(&test_var, 0), false);
+ KCSAN_EXPECT_WRITE_BARRIER(cmpxchg(&test_var, 0, 0), true);
+ KCSAN_EXPECT_WRITE_BARRIER(cmpxchg_release(&test_var, 0, 0), true);
+ KCSAN_EXPECT_WRITE_BARRIER(cmpxchg_relaxed(&test_var, 0, 0), false);
+ KCSAN_EXPECT_WRITE_BARRIER(atomic_read(&dummy), false);
+ KCSAN_EXPECT_WRITE_BARRIER(atomic_read_acquire(&dummy), false);
+ KCSAN_EXPECT_WRITE_BARRIER(atomic_set(&dummy, 0), false);
+ KCSAN_EXPECT_WRITE_BARRIER(atomic_set_release(&dummy, 0), true);
+ KCSAN_EXPECT_WRITE_BARRIER(atomic_add(1, &dummy), false);
+ KCSAN_EXPECT_WRITE_BARRIER(atomic_add_return(1, &dummy), true);
+ KCSAN_EXPECT_WRITE_BARRIER(atomic_add_return_acquire(1, &dummy), false);
+ KCSAN_EXPECT_WRITE_BARRIER(atomic_add_return_release(1, &dummy), true);
+ KCSAN_EXPECT_WRITE_BARRIER(atomic_add_return_relaxed(1, &dummy), false);
+ KCSAN_EXPECT_WRITE_BARRIER(atomic_fetch_add(1, &dummy), true);
+ KCSAN_EXPECT_WRITE_BARRIER(atomic_fetch_add_acquire(1, &dummy), false);
+ KCSAN_EXPECT_WRITE_BARRIER(atomic_fetch_add_release(1, &dummy), true);
+ KCSAN_EXPECT_WRITE_BARRIER(atomic_fetch_add_relaxed(1, &dummy), false);
+ KCSAN_EXPECT_WRITE_BARRIER(test_and_set_bit(0, &test_var), true);
+ KCSAN_EXPECT_WRITE_BARRIER(test_and_clear_bit(0, &test_var), true);
+ KCSAN_EXPECT_WRITE_BARRIER(test_and_change_bit(0, &test_var), true);
+ KCSAN_EXPECT_WRITE_BARRIER(clear_bit_unlock(0, &test_var), true);
+ KCSAN_EXPECT_WRITE_BARRIER(__clear_bit_unlock(0, &test_var), true);
+ KCSAN_EXPECT_WRITE_BARRIER(arch_spin_lock(&arch_spinlock), false);
+ KCSAN_EXPECT_WRITE_BARRIER(arch_spin_unlock(&arch_spinlock), true);
+ KCSAN_EXPECT_WRITE_BARRIER(spin_lock(&test_spinlock), false);
+ KCSAN_EXPECT_WRITE_BARRIER(spin_unlock(&test_spinlock), true);
+ KCSAN_EXPECT_WRITE_BARRIER(mutex_lock(&test_mutex), false);
+ KCSAN_EXPECT_WRITE_BARRIER(mutex_unlock(&test_mutex), true);
+
+ KCSAN_EXPECT_RW_BARRIER(mb(), true);
+ KCSAN_EXPECT_RW_BARRIER(wmb(), true);
+ KCSAN_EXPECT_RW_BARRIER(rmb(), true);
+ KCSAN_EXPECT_RW_BARRIER(smp_mb(), true);
+ KCSAN_EXPECT_RW_BARRIER(smp_wmb(), true);
+ KCSAN_EXPECT_RW_BARRIER(smp_rmb(), true);
+ KCSAN_EXPECT_RW_BARRIER(dma_wmb(), true);
+ KCSAN_EXPECT_RW_BARRIER(dma_rmb(), true);
+ KCSAN_EXPECT_RW_BARRIER(smp_mb__before_atomic(), true);
+ KCSAN_EXPECT_RW_BARRIER(smp_mb__after_atomic(), true);
+ KCSAN_EXPECT_RW_BARRIER(smp_mb__after_spinlock(), true);
+ KCSAN_EXPECT_RW_BARRIER(smp_store_mb(test_var, 0), true);
+ KCSAN_EXPECT_RW_BARRIER(smp_load_acquire(&test_var), false);
+ KCSAN_EXPECT_RW_BARRIER(smp_store_release(&test_var, 0), true);
+ KCSAN_EXPECT_RW_BARRIER(xchg(&test_var, 0), true);
+ KCSAN_EXPECT_RW_BARRIER(xchg_release(&test_var, 0), true);
+ KCSAN_EXPECT_RW_BARRIER(xchg_relaxed(&test_var, 0), false);
+ KCSAN_EXPECT_RW_BARRIER(cmpxchg(&test_var, 0, 0), true);
+ KCSAN_EXPECT_RW_BARRIER(cmpxchg_release(&test_var, 0, 0), true);
+ KCSAN_EXPECT_RW_BARRIER(cmpxchg_relaxed(&test_var, 0, 0), false);
+ KCSAN_EXPECT_RW_BARRIER(atomic_read(&dummy), false);
+ KCSAN_EXPECT_RW_BARRIER(atomic_read_acquire(&dummy), false);
+ KCSAN_EXPECT_RW_BARRIER(atomic_set(&dummy, 0), false);
+ KCSAN_EXPECT_RW_BARRIER(atomic_set_release(&dummy, 0), true);
+ KCSAN_EXPECT_RW_BARRIER(atomic_add(1, &dummy), false);
+ KCSAN_EXPECT_RW_BARRIER(atomic_add_return(1, &dummy), true);
+ KCSAN_EXPECT_RW_BARRIER(atomic_add_return_acquire(1, &dummy), false);
+ KCSAN_EXPECT_RW_BARRIER(atomic_add_return_release(1, &dummy), true);
+ KCSAN_EXPECT_RW_BARRIER(atomic_add_return_relaxed(1, &dummy), false);
+ KCSAN_EXPECT_RW_BARRIER(atomic_fetch_add(1, &dummy), true);
+ KCSAN_EXPECT_RW_BARRIER(atomic_fetch_add_acquire(1, &dummy), false);
+ KCSAN_EXPECT_RW_BARRIER(atomic_fetch_add_release(1, &dummy), true);
+ KCSAN_EXPECT_RW_BARRIER(atomic_fetch_add_relaxed(1, &dummy), false);
+ KCSAN_EXPECT_RW_BARRIER(test_and_set_bit(0, &test_var), true);
+ KCSAN_EXPECT_RW_BARRIER(test_and_clear_bit(0, &test_var), true);
+ KCSAN_EXPECT_RW_BARRIER(test_and_change_bit(0, &test_var), true);
+ KCSAN_EXPECT_RW_BARRIER(clear_bit_unlock(0, &test_var), true);
+ KCSAN_EXPECT_RW_BARRIER(__clear_bit_unlock(0, &test_var), true);
+ KCSAN_EXPECT_RW_BARRIER(arch_spin_lock(&arch_spinlock), false);
+ KCSAN_EXPECT_RW_BARRIER(arch_spin_unlock(&arch_spinlock), true);
+ KCSAN_EXPECT_RW_BARRIER(spin_lock(&test_spinlock), false);
+ KCSAN_EXPECT_RW_BARRIER(spin_unlock(&test_spinlock), true);
+ KCSAN_EXPECT_RW_BARRIER(mutex_lock(&test_mutex), false);
+ KCSAN_EXPECT_RW_BARRIER(mutex_unlock(&test_mutex), true);
+
+#ifdef clear_bit_unlock_is_negative_byte
+ KCSAN_EXPECT_READ_BARRIER(clear_bit_unlock_is_negative_byte(0, &test_var), true);
+ KCSAN_EXPECT_WRITE_BARRIER(clear_bit_unlock_is_negative_byte(0, &test_var), true);
+ KCSAN_EXPECT_RW_BARRIER(clear_bit_unlock_is_negative_byte(0, &test_var), true);
+#endif
+ kcsan_nestable_atomic_end();
+}
+
/* Simple test with normal data race. */
__no_kcsan
static void test_basic(struct kunit *test)
{
- const struct expect_report expect = {
+ struct expect_report expect = {
.access = {
{ test_kernel_write, &test_var, sizeof(test_var), KCSAN_ACCESS_WRITE },
{ test_kernel_read, &test_var, sizeof(test_var), 0 },
},
};
- static const struct expect_report never = {
+ struct expect_report never = {
.access = {
{ test_kernel_read, &test_var, sizeof(test_var), 0 },
{ test_kernel_read, &test_var, sizeof(test_var), 0 },
@@ -469,14 +738,14 @@ static void test_basic(struct kunit *test)
__no_kcsan
static void test_concurrent_races(struct kunit *test)
{
- const struct expect_report expect = {
+ struct expect_report expect = {
.access = {
/* NULL will match any address. */
{ test_kernel_rmw_array, NULL, 0, __KCSAN_ACCESS_RW(KCSAN_ACCESS_WRITE) },
{ test_kernel_rmw_array, NULL, 0, __KCSAN_ACCESS_RW(0) },
},
};
- static const struct expect_report never = {
+ struct expect_report never = {
.access = {
{ test_kernel_rmw_array, NULL, 0, 0 },
{ test_kernel_rmw_array, NULL, 0, 0 },
@@ -498,13 +767,13 @@ static void test_concurrent_races(struct kunit *test)
__no_kcsan
static void test_novalue_change(struct kunit *test)
{
- const struct expect_report expect_rw = {
+ struct expect_report expect_rw = {
.access = {
{ test_kernel_write_nochange, &test_var, sizeof(test_var), KCSAN_ACCESS_WRITE },
{ test_kernel_read, &test_var, sizeof(test_var), 0 },
},
};
- const struct expect_report expect_ww = {
+ struct expect_report expect_ww = {
.access = {
{ test_kernel_write_nochange, &test_var, sizeof(test_var), KCSAN_ACCESS_WRITE },
{ test_kernel_write_nochange, &test_var, sizeof(test_var), KCSAN_ACCESS_WRITE },
@@ -530,13 +799,13 @@ static void test_novalue_change(struct kunit *test)
__no_kcsan
static void test_novalue_change_exception(struct kunit *test)
{
- const struct expect_report expect_rw = {
+ struct expect_report expect_rw = {
.access = {
{ test_kernel_write_nochange_rcu, &test_var, sizeof(test_var), KCSAN_ACCESS_WRITE },
{ test_kernel_read, &test_var, sizeof(test_var), 0 },
},
};
- const struct expect_report expect_ww = {
+ struct expect_report expect_ww = {
.access = {
{ test_kernel_write_nochange_rcu, &test_var, sizeof(test_var), KCSAN_ACCESS_WRITE },
{ test_kernel_write_nochange_rcu, &test_var, sizeof(test_var), KCSAN_ACCESS_WRITE },
@@ -556,7 +825,7 @@ static void test_novalue_change_exception(struct kunit *test)
__no_kcsan
static void test_unknown_origin(struct kunit *test)
{
- const struct expect_report expect = {
+ struct expect_report expect = {
.access = {
{ test_kernel_read, &test_var, sizeof(test_var), 0 },
{ NULL },
@@ -578,7 +847,7 @@ static void test_unknown_origin(struct kunit *test)
__no_kcsan
static void test_write_write_assume_atomic(struct kunit *test)
{
- const struct expect_report expect = {
+ struct expect_report expect = {
.access = {
{ test_kernel_write, &test_var, sizeof(test_var), KCSAN_ACCESS_WRITE },
{ test_kernel_write, &test_var, sizeof(test_var), KCSAN_ACCESS_WRITE },
@@ -604,7 +873,7 @@ static void test_write_write_assume_atomic(struct kunit *test)
__no_kcsan
static void test_write_write_struct(struct kunit *test)
{
- const struct expect_report expect = {
+ struct expect_report expect = {
.access = {
{ test_kernel_write_struct, &test_struct, sizeof(test_struct), KCSAN_ACCESS_WRITE },
{ test_kernel_write_struct, &test_struct, sizeof(test_struct), KCSAN_ACCESS_WRITE },
@@ -626,7 +895,7 @@ static void test_write_write_struct(struct kunit *test)
__no_kcsan
static void test_write_write_struct_part(struct kunit *test)
{
- const struct expect_report expect = {
+ struct expect_report expect = {
.access = {
{ test_kernel_write_struct, &test_struct, sizeof(test_struct), KCSAN_ACCESS_WRITE },
{ test_kernel_write_struct_part, &test_struct.val[3], sizeof(test_struct.val[3]), KCSAN_ACCESS_WRITE },
@@ -658,7 +927,7 @@ static void test_read_atomic_write_atomic(struct kunit *test)
__no_kcsan
static void test_read_plain_atomic_write(struct kunit *test)
{
- const struct expect_report expect = {
+ struct expect_report expect = {
.access = {
{ test_kernel_read, &test_var, sizeof(test_var), 0 },
{ test_kernel_write_atomic, &test_var, sizeof(test_var), KCSAN_ACCESS_WRITE | KCSAN_ACCESS_ATOMIC },
@@ -679,7 +948,7 @@ static void test_read_plain_atomic_write(struct kunit *test)
__no_kcsan
static void test_read_plain_atomic_rmw(struct kunit *test)
{
- const struct expect_report expect = {
+ struct expect_report expect = {
.access = {
{ test_kernel_read, &test_var, sizeof(test_var), 0 },
{ test_kernel_atomic_rmw, &test_var, sizeof(test_var),
@@ -701,13 +970,13 @@ static void test_read_plain_atomic_rmw(struct kunit *test)
__no_kcsan
static void test_zero_size_access(struct kunit *test)
{
- const struct expect_report expect = {
+ struct expect_report expect = {
.access = {
{ test_kernel_write_struct, &test_struct, sizeof(test_struct), KCSAN_ACCESS_WRITE },
{ test_kernel_write_struct, &test_struct, sizeof(test_struct), KCSAN_ACCESS_WRITE },
},
};
- const struct expect_report never = {
+ struct expect_report never = {
.access = {
{ test_kernel_write_struct, &test_struct, sizeof(test_struct), KCSAN_ACCESS_WRITE },
{ test_kernel_read_struct_zero_size, &test_struct.val[3], 0, 0 },
@@ -741,7 +1010,7 @@ static void test_data_race(struct kunit *test)
__no_kcsan
static void test_assert_exclusive_writer(struct kunit *test)
{
- const struct expect_report expect = {
+ struct expect_report expect = {
.access = {
{ test_kernel_assert_writer, &test_var, sizeof(test_var), KCSAN_ACCESS_ASSERT },
{ test_kernel_write_nochange, &test_var, sizeof(test_var), KCSAN_ACCESS_WRITE },
@@ -759,7 +1028,7 @@ static void test_assert_exclusive_writer(struct kunit *test)
__no_kcsan
static void test_assert_exclusive_access(struct kunit *test)
{
- const struct expect_report expect = {
+ struct expect_report expect = {
.access = {
{ test_kernel_assert_access, &test_var, sizeof(test_var), KCSAN_ACCESS_ASSERT | KCSAN_ACCESS_WRITE },
{ test_kernel_read, &test_var, sizeof(test_var), 0 },
@@ -777,19 +1046,19 @@ static void test_assert_exclusive_access(struct kunit *test)
__no_kcsan
static void test_assert_exclusive_access_writer(struct kunit *test)
{
- const struct expect_report expect_access_writer = {
+ struct expect_report expect_access_writer = {
.access = {
{ test_kernel_assert_access, &test_var, sizeof(test_var), KCSAN_ACCESS_ASSERT | KCSAN_ACCESS_WRITE },
{ test_kernel_assert_writer, &test_var, sizeof(test_var), KCSAN_ACCESS_ASSERT },
},
};
- const struct expect_report expect_access_access = {
+ struct expect_report expect_access_access = {
.access = {
{ test_kernel_assert_access, &test_var, sizeof(test_var), KCSAN_ACCESS_ASSERT | KCSAN_ACCESS_WRITE },
{ test_kernel_assert_access, &test_var, sizeof(test_var), KCSAN_ACCESS_ASSERT | KCSAN_ACCESS_WRITE },
},
};
- const struct expect_report never = {
+ struct expect_report never = {
.access = {
{ test_kernel_assert_writer, &test_var, sizeof(test_var), KCSAN_ACCESS_ASSERT },
{ test_kernel_assert_writer, &test_var, sizeof(test_var), KCSAN_ACCESS_ASSERT },
@@ -813,7 +1082,7 @@ static void test_assert_exclusive_access_writer(struct kunit *test)
__no_kcsan
static void test_assert_exclusive_bits_change(struct kunit *test)
{
- const struct expect_report expect = {
+ struct expect_report expect = {
.access = {
{ test_kernel_assert_bits_change, &test_var, sizeof(test_var), KCSAN_ACCESS_ASSERT },
{ test_kernel_change_bits, &test_var, sizeof(test_var),
@@ -844,13 +1113,13 @@ static void test_assert_exclusive_bits_nochange(struct kunit *test)
__no_kcsan
static void test_assert_exclusive_writer_scoped(struct kunit *test)
{
- const struct expect_report expect_start = {
+ struct expect_report expect_start = {
.access = {
{ test_kernel_assert_writer_scoped, &test_var, sizeof(test_var), KCSAN_ACCESS_ASSERT | KCSAN_ACCESS_SCOPED },
{ test_kernel_write_nochange, &test_var, sizeof(test_var), KCSAN_ACCESS_WRITE },
},
};
- const struct expect_report expect_inscope = {
+ struct expect_report expect_inscope = {
.access = {
{ test_enter_scope, &test_var, sizeof(test_var), KCSAN_ACCESS_ASSERT | KCSAN_ACCESS_SCOPED },
{ test_kernel_write_nochange, &test_var, sizeof(test_var), KCSAN_ACCESS_WRITE },
@@ -871,16 +1140,16 @@ static void test_assert_exclusive_writer_scoped(struct kunit *test)
__no_kcsan
static void test_assert_exclusive_access_scoped(struct kunit *test)
{
- const struct expect_report expect_start1 = {
+ struct expect_report expect_start1 = {
.access = {
{ test_kernel_assert_access_scoped, &test_var, sizeof(test_var), KCSAN_ACCESS_ASSERT | KCSAN_ACCESS_WRITE | KCSAN_ACCESS_SCOPED },
{ test_kernel_read, &test_var, sizeof(test_var), 0 },
},
};
- const struct expect_report expect_start2 = {
+ struct expect_report expect_start2 = {
.access = { expect_start1.access[0], expect_start1.access[0] },
};
- const struct expect_report expect_inscope = {
+ struct expect_report expect_inscope = {
.access = {
{ test_enter_scope, &test_var, sizeof(test_var), KCSAN_ACCESS_ASSERT | KCSAN_ACCESS_WRITE | KCSAN_ACCESS_SCOPED },
{ test_kernel_read, &test_var, sizeof(test_var), 0 },
@@ -985,7 +1254,7 @@ static void test_atomic_builtins(struct kunit *test)
__no_kcsan
static void test_1bit_value_change(struct kunit *test)
{
- const struct expect_report expect = {
+ struct expect_report expect = {
.access = {
{ test_kernel_read, &test_var, sizeof(test_var), 0 },
{ test_kernel_xor_1bit, &test_var, sizeof(test_var), __KCSAN_ACCESS_RW(KCSAN_ACCESS_WRITE) },
@@ -1005,6 +1274,90 @@ static void test_1bit_value_change(struct kunit *test)
KUNIT_EXPECT_TRUE(test, match);
}
+__no_kcsan
+static void test_correct_barrier(struct kunit *test)
+{
+ struct expect_report expect = {
+ .access = {
+ { test_kernel_with_memorder, &test_var, sizeof(test_var), __KCSAN_ACCESS_RW(KCSAN_ACCESS_WRITE) },
+ { test_kernel_with_memorder, &test_var, sizeof(test_var), __KCSAN_ACCESS_RW(0) },
+ },
+ };
+ bool match_expect = false;
+
+ test_struct.val[0] = 0; /* init unlocked */
+ begin_test_checks(test_kernel_with_memorder, test_kernel_with_memorder);
+ do {
+ match_expect = report_matches_any_reordered(&expect);
+ } while (!end_test_checks(match_expect));
+ KUNIT_EXPECT_FALSE(test, match_expect);
+}
+
+__no_kcsan
+static void test_missing_barrier(struct kunit *test)
+{
+ struct expect_report expect = {
+ .access = {
+ { test_kernel_wrong_memorder, &test_var, sizeof(test_var), __KCSAN_ACCESS_RW(KCSAN_ACCESS_WRITE) },
+ { test_kernel_wrong_memorder, &test_var, sizeof(test_var), __KCSAN_ACCESS_RW(0) },
+ },
+ };
+ bool match_expect = false;
+
+ test_struct.val[0] = 0; /* init unlocked */
+ begin_test_checks(test_kernel_wrong_memorder, test_kernel_wrong_memorder);
+ do {
+ match_expect = report_matches_any_reordered(&expect);
+ } while (!end_test_checks(match_expect));
+ if (IS_ENABLED(CONFIG_KCSAN_WEAK_MEMORY))
+ KUNIT_EXPECT_TRUE(test, match_expect);
+ else
+ KUNIT_EXPECT_FALSE(test, match_expect);
+}
+
+__no_kcsan
+static void test_atomic_builtins_correct_barrier(struct kunit *test)
+{
+ struct expect_report expect = {
+ .access = {
+ { test_kernel_atomic_builtin_with_memorder, &test_var, sizeof(test_var), __KCSAN_ACCESS_RW(KCSAN_ACCESS_WRITE) },
+ { test_kernel_atomic_builtin_with_memorder, &test_var, sizeof(test_var), __KCSAN_ACCESS_RW(0) },
+ },
+ };
+ bool match_expect = false;
+
+ test_struct.val[0] = 0; /* init unlocked */
+ begin_test_checks(test_kernel_atomic_builtin_with_memorder,
+ test_kernel_atomic_builtin_with_memorder);
+ do {
+ match_expect = report_matches_any_reordered(&expect);
+ } while (!end_test_checks(match_expect));
+ KUNIT_EXPECT_FALSE(test, match_expect);
+}
+
+__no_kcsan
+static void test_atomic_builtins_missing_barrier(struct kunit *test)
+{
+ struct expect_report expect = {
+ .access = {
+ { test_kernel_atomic_builtin_wrong_memorder, &test_var, sizeof(test_var), __KCSAN_ACCESS_RW(KCSAN_ACCESS_WRITE) },
+ { test_kernel_atomic_builtin_wrong_memorder, &test_var, sizeof(test_var), __KCSAN_ACCESS_RW(0) },
+ },
+ };
+ bool match_expect = false;
+
+ test_struct.val[0] = 0; /* init unlocked */
+ begin_test_checks(test_kernel_atomic_builtin_wrong_memorder,
+ test_kernel_atomic_builtin_wrong_memorder);
+ do {
+ match_expect = report_matches_any_reordered(&expect);
+ } while (!end_test_checks(match_expect));
+ if (IS_ENABLED(CONFIG_KCSAN_WEAK_MEMORY))
+ KUNIT_EXPECT_TRUE(test, match_expect);
+ else
+ KUNIT_EXPECT_FALSE(test, match_expect);
+}
+
/*
* Generate thread counts for all test cases. Values generated are in interval
* [2, 5] followed by exponentially increasing thread counts from 8 to 32.
@@ -1054,6 +1407,7 @@ static const void *nthreads_gen_params(const void *prev, char *desc)
#define KCSAN_KUNIT_CASE(test_name) KUNIT_CASE_PARAM(test_name, nthreads_gen_params)
static struct kunit_case kcsan_test_cases[] = {
+ KUNIT_CASE(test_barrier_nothreads),
KCSAN_KUNIT_CASE(test_basic),
KCSAN_KUNIT_CASE(test_concurrent_races),
KCSAN_KUNIT_CASE(test_novalue_change),
@@ -1078,6 +1432,10 @@ static struct kunit_case kcsan_test_cases[] = {
KCSAN_KUNIT_CASE(test_seqlock_noreport),
KCSAN_KUNIT_CASE(test_atomic_builtins),
KCSAN_KUNIT_CASE(test_1bit_value_change),
+ KCSAN_KUNIT_CASE(test_correct_barrier),
+ KCSAN_KUNIT_CASE(test_missing_barrier),
+ KCSAN_KUNIT_CASE(test_atomic_builtins_correct_barrier),
+ KCSAN_KUNIT_CASE(test_atomic_builtins_missing_barrier),
{},
};
@@ -1142,6 +1500,9 @@ static int test_init(struct kunit *test)
observed.nlines = 0;
spin_unlock_irqrestore(&observed.lock, flags);
+ if (strstr(test->name, "nothreads"))
+ return 0;
+
if (!torture_init_begin((char *)test->name, 1))
return -EBUSY;
@@ -1184,6 +1545,9 @@ static void test_exit(struct kunit *test)
struct task_struct **stop_thread;
int i;
+ if (strstr(test->name, "nothreads"))
+ return;
+
if (torture_cleanup_begin())
return;
diff --git a/kernel/kcsan/report.c b/kernel/kcsan/report.c
index fc15077991c4..67794404042a 100644
--- a/kernel/kcsan/report.c
+++ b/kernel/kcsan/report.c
@@ -215,9 +215,9 @@ static const char *get_access_type(int type)
if (type & KCSAN_ACCESS_ASSERT) {
if (type & KCSAN_ACCESS_SCOPED) {
if (type & KCSAN_ACCESS_WRITE)
- return "assert no accesses (scoped)";
+ return "assert no accesses (reordered)";
else
- return "assert no writes (scoped)";
+ return "assert no writes (reordered)";
} else {
if (type & KCSAN_ACCESS_WRITE)
return "assert no accesses";
@@ -240,17 +240,17 @@ static const char *get_access_type(int type)
case KCSAN_ACCESS_COMPOUND | KCSAN_ACCESS_WRITE | KCSAN_ACCESS_ATOMIC:
return "read-write (marked)";
case KCSAN_ACCESS_SCOPED:
- return "read (scoped)";
+ return "read (reordered)";
case KCSAN_ACCESS_SCOPED | KCSAN_ACCESS_ATOMIC:
- return "read (marked, scoped)";
+ return "read (marked, reordered)";
case KCSAN_ACCESS_SCOPED | KCSAN_ACCESS_WRITE:
- return "write (scoped)";
+ return "write (reordered)";
case KCSAN_ACCESS_SCOPED | KCSAN_ACCESS_WRITE | KCSAN_ACCESS_ATOMIC:
- return "write (marked, scoped)";
+ return "write (marked, reordered)";
case KCSAN_ACCESS_SCOPED | KCSAN_ACCESS_COMPOUND | KCSAN_ACCESS_WRITE:
- return "read-write (scoped)";
+ return "read-write (reordered)";
case KCSAN_ACCESS_SCOPED | KCSAN_ACCESS_COMPOUND | KCSAN_ACCESS_WRITE | KCSAN_ACCESS_ATOMIC:
- return "read-write (marked, scoped)";
+ return "read-write (marked, reordered)";
default:
BUG();
}
@@ -308,10 +308,12 @@ static int get_stack_skipnr(const unsigned long stack_entries[], int num_entries
/*
* Skips to the first entry that matches the function of @ip, and then replaces
- * that entry with @ip, returning the entries to skip.
+ * that entry with @ip, returning the entries to skip with @replaced containing
+ * the replaced entry.
*/
static int
-replace_stack_entry(unsigned long stack_entries[], int num_entries, unsigned long ip)
+replace_stack_entry(unsigned long stack_entries[], int num_entries, unsigned long ip,
+ unsigned long *replaced)
{
unsigned long symbolsize, offset;
unsigned long target_func;
@@ -330,6 +332,7 @@ replace_stack_entry(unsigned long stack_entries[], int num_entries, unsigned lon
func -= offset;
if (func == target_func) {
+ *replaced = stack_entries[skip];
stack_entries[skip] = ip;
return skip;
}
@@ -342,9 +345,10 @@ fallback:
}
static int
-sanitize_stack_entries(unsigned long stack_entries[], int num_entries, unsigned long ip)
+sanitize_stack_entries(unsigned long stack_entries[], int num_entries, unsigned long ip,
+ unsigned long *replaced)
{
- return ip ? replace_stack_entry(stack_entries, num_entries, ip) :
+ return ip ? replace_stack_entry(stack_entries, num_entries, ip, replaced) :
get_stack_skipnr(stack_entries, num_entries);
}
@@ -360,6 +364,14 @@ static int sym_strcmp(void *addr1, void *addr2)
return strncmp(buf1, buf2, sizeof(buf1));
}
+static void
+print_stack_trace(unsigned long stack_entries[], int num_entries, unsigned long reordered_to)
+{
+ stack_trace_print(stack_entries, num_entries, 0);
+ if (reordered_to)
+ pr_err(" |\n +-> reordered to: %pS\n", (void *)reordered_to);
+}
+
static void print_verbose_info(struct task_struct *task)
{
if (!task)
@@ -378,10 +390,12 @@ static void print_report(enum kcsan_value_change value_change,
struct other_info *other_info,
u64 old, u64 new, u64 mask)
{
+ unsigned long reordered_to = 0;
unsigned long stack_entries[NUM_STACK_ENTRIES] = { 0 };
int num_stack_entries = stack_trace_save(stack_entries, NUM_STACK_ENTRIES, 1);
- int skipnr = sanitize_stack_entries(stack_entries, num_stack_entries, ai->ip);
+ int skipnr = sanitize_stack_entries(stack_entries, num_stack_entries, ai->ip, &reordered_to);
unsigned long this_frame = stack_entries[skipnr];
+ unsigned long other_reordered_to = 0;
unsigned long other_frame = 0;
int other_skipnr = 0; /* silence uninit warnings */
@@ -394,7 +408,7 @@ static void print_report(enum kcsan_value_change value_change,
if (other_info) {
other_skipnr = sanitize_stack_entries(other_info->stack_entries,
other_info->num_stack_entries,
- other_info->ai.ip);
+ other_info->ai.ip, &other_reordered_to);
other_frame = other_info->stack_entries[other_skipnr];
/* @value_change is only known for the other thread */
@@ -434,10 +448,9 @@ static void print_report(enum kcsan_value_change value_change,
other_info->ai.cpu_id);
/* Print the other thread's stack trace. */
- stack_trace_print(other_info->stack_entries + other_skipnr,
+ print_stack_trace(other_info->stack_entries + other_skipnr,
other_info->num_stack_entries - other_skipnr,
- 0);
-
+ other_reordered_to);
if (IS_ENABLED(CONFIG_KCSAN_VERBOSE))
print_verbose_info(other_info->task);
@@ -451,9 +464,7 @@ static void print_report(enum kcsan_value_change value_change,
get_thread_desc(ai->task_pid), ai->cpu_id);
}
/* Print stack trace of this thread. */
- stack_trace_print(stack_entries + skipnr, num_stack_entries - skipnr,
- 0);
-
+ print_stack_trace(stack_entries + skipnr, num_stack_entries - skipnr, reordered_to);
if (IS_ENABLED(CONFIG_KCSAN_VERBOSE))
print_verbose_info(current);
diff --git a/kernel/kcsan/selftest.c b/kernel/kcsan/selftest.c
index b4295a3892b7..75712959c84e 100644
--- a/kernel/kcsan/selftest.c
+++ b/kernel/kcsan/selftest.c
@@ -7,10 +7,15 @@
#define pr_fmt(fmt) "kcsan: " fmt
+#include <linux/atomic.h>
+#include <linux/bitops.h>
#include <linux/init.h>
+#include <linux/kcsan-checks.h>
#include <linux/kernel.h>
#include <linux/printk.h>
#include <linux/random.h>
+#include <linux/sched.h>
+#include <linux/spinlock.h>
#include <linux/types.h>
#include "encoding.h"
@@ -103,6 +108,143 @@ static bool __init test_matching_access(void)
return true;
}
+/*
+ * Correct memory barrier instrumentation is critical to avoiding false
+ * positives: simple test to check at boot certain barriers are always properly
+ * instrumented. See kcsan_test for a more complete test.
+ */
+static DEFINE_SPINLOCK(test_spinlock);
+static bool __init test_barrier(void)
+{
+#ifdef CONFIG_KCSAN_WEAK_MEMORY
+ struct kcsan_scoped_access *reorder_access = &current->kcsan_ctx.reorder_access;
+#else
+ struct kcsan_scoped_access *reorder_access = NULL;
+#endif
+ bool ret = true;
+ arch_spinlock_t arch_spinlock = __ARCH_SPIN_LOCK_UNLOCKED;
+ atomic_t dummy;
+ long test_var;
+
+ if (!reorder_access || !IS_ENABLED(CONFIG_SMP))
+ return true;
+
+#define __KCSAN_CHECK_BARRIER(access_type, barrier, name) \
+ do { \
+ reorder_access->type = (access_type) | KCSAN_ACCESS_SCOPED; \
+ reorder_access->size = 1; \
+ barrier; \
+ if (reorder_access->size != 0) { \
+ pr_err("improperly instrumented type=(" #access_type "): " name "\n"); \
+ ret = false; \
+ } \
+ } while (0)
+#define KCSAN_CHECK_READ_BARRIER(b) __KCSAN_CHECK_BARRIER(0, b, #b)
+#define KCSAN_CHECK_WRITE_BARRIER(b) __KCSAN_CHECK_BARRIER(KCSAN_ACCESS_WRITE, b, #b)
+#define KCSAN_CHECK_RW_BARRIER(b) __KCSAN_CHECK_BARRIER(KCSAN_ACCESS_WRITE | KCSAN_ACCESS_COMPOUND, b, #b)
+
+ kcsan_nestable_atomic_begin(); /* No watchpoints in called functions. */
+
+ KCSAN_CHECK_READ_BARRIER(mb());
+ KCSAN_CHECK_READ_BARRIER(rmb());
+ KCSAN_CHECK_READ_BARRIER(smp_mb());
+ KCSAN_CHECK_READ_BARRIER(smp_rmb());
+ KCSAN_CHECK_READ_BARRIER(dma_rmb());
+ KCSAN_CHECK_READ_BARRIER(smp_mb__before_atomic());
+ KCSAN_CHECK_READ_BARRIER(smp_mb__after_atomic());
+ KCSAN_CHECK_READ_BARRIER(smp_mb__after_spinlock());
+ KCSAN_CHECK_READ_BARRIER(smp_store_mb(test_var, 0));
+ KCSAN_CHECK_READ_BARRIER(smp_store_release(&test_var, 0));
+ KCSAN_CHECK_READ_BARRIER(xchg(&test_var, 0));
+ KCSAN_CHECK_READ_BARRIER(xchg_release(&test_var, 0));
+ KCSAN_CHECK_READ_BARRIER(cmpxchg(&test_var, 0, 0));
+ KCSAN_CHECK_READ_BARRIER(cmpxchg_release(&test_var, 0, 0));
+ KCSAN_CHECK_READ_BARRIER(atomic_set_release(&dummy, 0));
+ KCSAN_CHECK_READ_BARRIER(atomic_add_return(1, &dummy));
+ KCSAN_CHECK_READ_BARRIER(atomic_add_return_release(1, &dummy));
+ KCSAN_CHECK_READ_BARRIER(atomic_fetch_add(1, &dummy));
+ KCSAN_CHECK_READ_BARRIER(atomic_fetch_add_release(1, &dummy));
+ KCSAN_CHECK_READ_BARRIER(test_and_set_bit(0, &test_var));
+ KCSAN_CHECK_READ_BARRIER(test_and_clear_bit(0, &test_var));
+ KCSAN_CHECK_READ_BARRIER(test_and_change_bit(0, &test_var));
+ KCSAN_CHECK_READ_BARRIER(clear_bit_unlock(0, &test_var));
+ KCSAN_CHECK_READ_BARRIER(__clear_bit_unlock(0, &test_var));
+ arch_spin_lock(&arch_spinlock);
+ KCSAN_CHECK_READ_BARRIER(arch_spin_unlock(&arch_spinlock));
+ spin_lock(&test_spinlock);
+ KCSAN_CHECK_READ_BARRIER(spin_unlock(&test_spinlock));
+
+ KCSAN_CHECK_WRITE_BARRIER(mb());
+ KCSAN_CHECK_WRITE_BARRIER(wmb());
+ KCSAN_CHECK_WRITE_BARRIER(smp_mb());
+ KCSAN_CHECK_WRITE_BARRIER(smp_wmb());
+ KCSAN_CHECK_WRITE_BARRIER(dma_wmb());
+ KCSAN_CHECK_WRITE_BARRIER(smp_mb__before_atomic());
+ KCSAN_CHECK_WRITE_BARRIER(smp_mb__after_atomic());
+ KCSAN_CHECK_WRITE_BARRIER(smp_mb__after_spinlock());
+ KCSAN_CHECK_WRITE_BARRIER(smp_store_mb(test_var, 0));
+ KCSAN_CHECK_WRITE_BARRIER(smp_store_release(&test_var, 0));
+ KCSAN_CHECK_WRITE_BARRIER(xchg(&test_var, 0));
+ KCSAN_CHECK_WRITE_BARRIER(xchg_release(&test_var, 0));
+ KCSAN_CHECK_WRITE_BARRIER(cmpxchg(&test_var, 0, 0));
+ KCSAN_CHECK_WRITE_BARRIER(cmpxchg_release(&test_var, 0, 0));
+ KCSAN_CHECK_WRITE_BARRIER(atomic_set_release(&dummy, 0));
+ KCSAN_CHECK_WRITE_BARRIER(atomic_add_return(1, &dummy));
+ KCSAN_CHECK_WRITE_BARRIER(atomic_add_return_release(1, &dummy));
+ KCSAN_CHECK_WRITE_BARRIER(atomic_fetch_add(1, &dummy));
+ KCSAN_CHECK_WRITE_BARRIER(atomic_fetch_add_release(1, &dummy));
+ KCSAN_CHECK_WRITE_BARRIER(test_and_set_bit(0, &test_var));
+ KCSAN_CHECK_WRITE_BARRIER(test_and_clear_bit(0, &test_var));
+ KCSAN_CHECK_WRITE_BARRIER(test_and_change_bit(0, &test_var));
+ KCSAN_CHECK_WRITE_BARRIER(clear_bit_unlock(0, &test_var));
+ KCSAN_CHECK_WRITE_BARRIER(__clear_bit_unlock(0, &test_var));
+ arch_spin_lock(&arch_spinlock);
+ KCSAN_CHECK_WRITE_BARRIER(arch_spin_unlock(&arch_spinlock));
+ spin_lock(&test_spinlock);
+ KCSAN_CHECK_WRITE_BARRIER(spin_unlock(&test_spinlock));
+
+ KCSAN_CHECK_RW_BARRIER(mb());
+ KCSAN_CHECK_RW_BARRIER(wmb());
+ KCSAN_CHECK_RW_BARRIER(rmb());
+ KCSAN_CHECK_RW_BARRIER(smp_mb());
+ KCSAN_CHECK_RW_BARRIER(smp_wmb());
+ KCSAN_CHECK_RW_BARRIER(smp_rmb());
+ KCSAN_CHECK_RW_BARRIER(dma_wmb());
+ KCSAN_CHECK_RW_BARRIER(dma_rmb());
+ KCSAN_CHECK_RW_BARRIER(smp_mb__before_atomic());
+ KCSAN_CHECK_RW_BARRIER(smp_mb__after_atomic());
+ KCSAN_CHECK_RW_BARRIER(smp_mb__after_spinlock());
+ KCSAN_CHECK_RW_BARRIER(smp_store_mb(test_var, 0));
+ KCSAN_CHECK_RW_BARRIER(smp_store_release(&test_var, 0));
+ KCSAN_CHECK_RW_BARRIER(xchg(&test_var, 0));
+ KCSAN_CHECK_RW_BARRIER(xchg_release(&test_var, 0));
+ KCSAN_CHECK_RW_BARRIER(cmpxchg(&test_var, 0, 0));
+ KCSAN_CHECK_RW_BARRIER(cmpxchg_release(&test_var, 0, 0));
+ KCSAN_CHECK_RW_BARRIER(atomic_set_release(&dummy, 0));
+ KCSAN_CHECK_RW_BARRIER(atomic_add_return(1, &dummy));
+ KCSAN_CHECK_RW_BARRIER(atomic_add_return_release(1, &dummy));
+ KCSAN_CHECK_RW_BARRIER(atomic_fetch_add(1, &dummy));
+ KCSAN_CHECK_RW_BARRIER(atomic_fetch_add_release(1, &dummy));
+ KCSAN_CHECK_RW_BARRIER(test_and_set_bit(0, &test_var));
+ KCSAN_CHECK_RW_BARRIER(test_and_clear_bit(0, &test_var));
+ KCSAN_CHECK_RW_BARRIER(test_and_change_bit(0, &test_var));
+ KCSAN_CHECK_RW_BARRIER(clear_bit_unlock(0, &test_var));
+ KCSAN_CHECK_RW_BARRIER(__clear_bit_unlock(0, &test_var));
+ arch_spin_lock(&arch_spinlock);
+ KCSAN_CHECK_RW_BARRIER(arch_spin_unlock(&arch_spinlock));
+ spin_lock(&test_spinlock);
+ KCSAN_CHECK_RW_BARRIER(spin_unlock(&test_spinlock));
+
+#ifdef clear_bit_unlock_is_negative_byte
+ KCSAN_CHECK_RW_BARRIER(clear_bit_unlock_is_negative_byte(0, &test_var));
+ KCSAN_CHECK_READ_BARRIER(clear_bit_unlock_is_negative_byte(0, &test_var));
+ KCSAN_CHECK_WRITE_BARRIER(clear_bit_unlock_is_negative_byte(0, &test_var));
+#endif
+ kcsan_nestable_atomic_end();
+
+ return ret;
+}
+
static int __init kcsan_selftest(void)
{
int passed = 0;
@@ -120,6 +262,7 @@ static int __init kcsan_selftest(void)
RUN_TEST(test_requires);
RUN_TEST(test_encode_decode);
RUN_TEST(test_matching_access);
+ RUN_TEST(test_barrier);
pr_info("selftest: %d/%d tests passed\n", passed, total);
if (passed != total)
diff --git a/kernel/sched/Makefile b/kernel/sched/Makefile
index c7421f2d05e1..c83b37af155b 100644
--- a/kernel/sched/Makefile
+++ b/kernel/sched/Makefile
@@ -11,11 +11,10 @@ ccflags-y += $(call cc-disable-warning, unused-but-set-variable)
# that is not a function of syscall inputs. E.g. involuntary context switches.
KCOV_INSTRUMENT := n
-# There are numerous data races here, however, most of them are due to plain accesses.
-# This would make it even harder for syzbot to find reproducers, because these
-# bugs trigger without specific input. Disable by default, but should re-enable
-# eventually.
+# Disable KCSAN to avoid excessive noise and performance degradation. To avoid
+# false positives ensure barriers implied by sched functions are instrumented.
KCSAN_SANITIZE := n
+KCSAN_INSTRUMENT_BARRIERS := y
ifneq ($(CONFIG_SCHED_OMIT_FRAME_POINTER),y)
# According to Alan Modra <alan@linuxcare.com.au>, the -fno-omit-frame-pointer is
diff --git a/lib/Kconfig.kcsan b/lib/Kconfig.kcsan
index e0a93ffdef30..63b70b8c5551 100644
--- a/lib/Kconfig.kcsan
+++ b/lib/Kconfig.kcsan
@@ -191,6 +191,26 @@ config KCSAN_STRICT
closely aligns with the rules defined by the Linux-kernel memory
consistency model (LKMM).
+config KCSAN_WEAK_MEMORY
+ bool "Enable weak memory modeling to detect missing memory barriers"
+ default y
+ depends on KCSAN_STRICT
+ # We can either let objtool nop __tsan_func_{entry,exit}() and builtin
+ # atomics instrumentation in .noinstr.text, or use a compiler that can
+ # implement __no_kcsan to really remove all instrumentation.
+ depends on STACK_VALIDATION || CC_IS_GCC || CLANG_VERSION >= 140000
+ help
+ Enable support for modeling a subset of weak memory, which allows
+ detecting a subset of data races due to missing memory barriers.
+
+ Depends on KCSAN_STRICT, because the options strenghtening certain
+ plain accesses by default (depending on !KCSAN_STRICT) reduce the
+ ability to detect any data races invoving reordered accesses, in
+ particular reordered writes.
+
+ Weak memory modeling relies on additional instrumentation and may
+ affect performance.
+
config KCSAN_REPORT_VALUE_CHANGE_ONLY
bool "Only report races where watcher observed a data value change"
default y
diff --git a/mm/Makefile b/mm/Makefile
index d6c0042e3aa0..7919cd7f13f2 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -15,6 +15,8 @@ KCSAN_SANITIZE_slab_common.o := n
KCSAN_SANITIZE_slab.o := n
KCSAN_SANITIZE_slub.o := n
KCSAN_SANITIZE_page_alloc.o := n
+# But enable explicit instrumentation for memory barriers.
+KCSAN_INSTRUMENT_BARRIERS := y
# These files are disabled because they produce non-interesting and/or
# flaky coverage that is not a function of syscall inputs. E.g. slab is out of
diff --git a/scripts/Makefile.kcsan b/scripts/Makefile.kcsan
index 37cb504c77e1..19f693b68a96 100644
--- a/scripts/Makefile.kcsan
+++ b/scripts/Makefile.kcsan
@@ -9,7 +9,18 @@ endif
# Keep most options here optional, to allow enabling more compilers if absence
# of some options does not break KCSAN nor causes false positive reports.
-export CFLAGS_KCSAN := -fsanitize=thread \
- $(call cc-option,$(call cc-param,tsan-instrument-func-entry-exit=0) -fno-optimize-sibling-calls) \
+kcsan-cflags := -fsanitize=thread -fno-optimize-sibling-calls \
$(call cc-option,$(call cc-param,tsan-compound-read-before-write=1),$(call cc-option,$(call cc-param,tsan-instrument-read-before-write=1))) \
$(call cc-param,tsan-distinguish-volatile=1)
+
+ifdef CONFIG_CC_IS_GCC
+# GCC started warning about operations unsupported by the TSan runtime. But
+# KCSAN != TSan, so just ignore these warnings.
+kcsan-cflags += -Wno-tsan
+endif
+
+ifndef CONFIG_KCSAN_WEAK_MEMORY
+kcsan-cflags += $(call cc-option,$(call cc-param,tsan-instrument-func-entry-exit=0))
+endif
+
+export CFLAGS_KCSAN := $(kcsan-cflags)
diff --git a/scripts/Makefile.lib b/scripts/Makefile.lib
index d1f865b8c0cb..ab17f7b2e33c 100644
--- a/scripts/Makefile.lib
+++ b/scripts/Makefile.lib
@@ -182,6 +182,11 @@ ifeq ($(CONFIG_KCSAN),y)
_c_flags += $(if $(patsubst n%,, \
$(KCSAN_SANITIZE_$(basetarget).o)$(KCSAN_SANITIZE)y), \
$(CFLAGS_KCSAN))
+# Some uninstrumented files provide implied barriers required to avoid false
+# positives: set KCSAN_INSTRUMENT_BARRIERS for barrier instrumentation only.
+_c_flags += $(if $(patsubst n%,, \
+ $(KCSAN_INSTRUMENT_BARRIERS_$(basetarget).o)$(KCSAN_INSTRUMENT_BARRIERS)n), \
+ -D__KCSAN_INSTRUMENT_BARRIERS__)
endif
# $(srctree)/$(src) for including checkin headers from generated source files
diff --git a/scripts/atomic/gen-atomic-instrumented.sh b/scripts/atomic/gen-atomic-instrumented.sh
index 035ceb4ee85c..68f902731d01 100755
--- a/scripts/atomic/gen-atomic-instrumented.sh
+++ b/scripts/atomic/gen-atomic-instrumented.sh
@@ -34,6 +34,14 @@ gen_param_check()
gen_params_checks()
{
local meta="$1"; shift
+ local order="$1"; shift
+
+ if [ "${order}" = "_release" ]; then
+ printf "\tkcsan_release();\n"
+ elif [ -z "${order}" ] && ! meta_in "$meta" "slv"; then
+ # RMW with return value is fully ordered
+ printf "\tkcsan_mb();\n"
+ fi
while [ "$#" -gt 0 ]; do
gen_param_check "$meta" "$1"
@@ -56,7 +64,7 @@ gen_proto_order_variant()
local ret="$(gen_ret_type "${meta}" "${int}")"
local params="$(gen_params "${int}" "${atomic}" "$@")"
- local checks="$(gen_params_checks "${meta}" "$@")"
+ local checks="$(gen_params_checks "${meta}" "${order}" "$@")"
local args="$(gen_args "$@")"
local retstmt="$(gen_ret_stmt "${meta}")"
@@ -75,29 +83,44 @@ EOF
gen_xchg()
{
local xchg="$1"; shift
+ local order="$1"; shift
local mult="$1"; shift
+ kcsan_barrier=""
+ if [ "${xchg%_local}" = "${xchg}" ]; then
+ case "$order" in
+ _release) kcsan_barrier="kcsan_release()" ;;
+ "") kcsan_barrier="kcsan_mb()" ;;
+ esac
+ fi
+
if [ "${xchg%${xchg#try_cmpxchg}}" = "try_cmpxchg" ] ; then
cat <<EOF
-#define ${xchg}(ptr, oldp, ...) \\
+#define ${xchg}${order}(ptr, oldp, ...) \\
({ \\
typeof(ptr) __ai_ptr = (ptr); \\
typeof(oldp) __ai_oldp = (oldp); \\
+EOF
+[ -n "$kcsan_barrier" ] && printf "\t${kcsan_barrier}; \\\\\n"
+cat <<EOF
instrument_atomic_write(__ai_ptr, ${mult}sizeof(*__ai_ptr)); \\
instrument_atomic_write(__ai_oldp, ${mult}sizeof(*__ai_oldp)); \\
- arch_${xchg}(__ai_ptr, __ai_oldp, __VA_ARGS__); \\
+ arch_${xchg}${order}(__ai_ptr, __ai_oldp, __VA_ARGS__); \\
})
EOF
else
cat <<EOF
-#define ${xchg}(ptr, ...) \\
+#define ${xchg}${order}(ptr, ...) \\
({ \\
typeof(ptr) __ai_ptr = (ptr); \\
+EOF
+[ -n "$kcsan_barrier" ] && printf "\t${kcsan_barrier}; \\\\\n"
+cat <<EOF
instrument_atomic_write(__ai_ptr, ${mult}sizeof(*__ai_ptr)); \\
- arch_${xchg}(__ai_ptr, __VA_ARGS__); \\
+ arch_${xchg}${order}(__ai_ptr, __VA_ARGS__); \\
})
EOF
@@ -145,21 +168,21 @@ done
for xchg in "xchg" "cmpxchg" "cmpxchg64" "try_cmpxchg"; do
for order in "" "_acquire" "_release" "_relaxed"; do
- gen_xchg "${xchg}${order}" ""
+ gen_xchg "${xchg}" "${order}" ""
printf "\n"
done
done
for xchg in "cmpxchg_local" "cmpxchg64_local" "sync_cmpxchg"; do
- gen_xchg "${xchg}" ""
+ gen_xchg "${xchg}" "" ""
printf "\n"
done
-gen_xchg "cmpxchg_double" "2 * "
+gen_xchg "cmpxchg_double" "" "2 * "
printf "\n\n"
-gen_xchg "cmpxchg_double_local" "2 * "
+gen_xchg "cmpxchg_double_local" "" "2 * "
cat <<EOF
diff --git a/tools/objtool/check.c b/tools/objtool/check.c
index 21735829b860..a9a1f7259d62 100644
--- a/tools/objtool/check.c
+++ b/tools/objtool/check.c
@@ -849,6 +849,10 @@ static const char *uaccess_safe_builtin[] = {
"__asan_report_store16_noabort",
/* KCSAN */
"__kcsan_check_access",
+ "__kcsan_mb",
+ "__kcsan_wmb",
+ "__kcsan_rmb",
+ "__kcsan_release",
"kcsan_found_watchpoint",
"kcsan_setup_watchpoint",
"kcsan_check_scoped_accesses",
@@ -1068,11 +1072,11 @@ static void annotate_call_site(struct objtool_file *file,
}
/*
- * Many compilers cannot disable KCOV with a function attribute
- * so they need a little help, NOP out any KCOV calls from noinstr
- * text.
+ * Many compilers cannot disable KCOV or sanitizer calls with a function
+ * attribute so they need a little help, NOP out any such calls from
+ * noinstr text.
*/
- if (insn->sec->noinstr && sym->kcov) {
+ if (insn->sec->noinstr && sym->profiling_func) {
if (reloc) {
reloc->type = R_NONE;
elf_write_reloc(file->elf, reloc);
@@ -1987,6 +1991,31 @@ static int read_intra_function_calls(struct objtool_file *file)
return 0;
}
+/*
+ * Return true if name matches an instrumentation function, where calls to that
+ * function from noinstr code can safely be removed, but compilers won't do so.
+ */
+static bool is_profiling_func(const char *name)
+{
+ /*
+ * Many compilers cannot disable KCOV with a function attribute.
+ */
+ if (!strncmp(name, "__sanitizer_cov_", 16))
+ return true;
+
+ /*
+ * Some compilers currently do not remove __tsan_func_entry/exit nor
+ * __tsan_atomic_signal_fence (used for barrier instrumentation) with
+ * the __no_sanitize_thread attribute, remove them. Once the kernel's
+ * minimum Clang version is 14.0, this can be removed.
+ */
+ if (!strncmp(name, "__tsan_func_", 12) ||
+ !strcmp(name, "__tsan_atomic_signal_fence"))
+ return true;
+
+ return false;
+}
+
static int classify_symbols(struct objtool_file *file)
{
struct section *sec;
@@ -2007,8 +2036,8 @@ static int classify_symbols(struct objtool_file *file)
if (!strcmp(func->name, "__fentry__"))
func->fentry = true;
- if (!strncmp(func->name, "__sanitizer_cov_", 16))
- func->kcov = true;
+ if (is_profiling_func(func->name))
+ func->profiling_func = true;
}
}
diff --git a/tools/objtool/include/objtool/elf.h b/tools/objtool/include/objtool/elf.h
index cdc739fa9a6f..d22336781401 100644
--- a/tools/objtool/include/objtool/elf.h
+++ b/tools/objtool/include/objtool/elf.h
@@ -58,7 +58,7 @@ struct symbol {
u8 static_call_tramp : 1;
u8 retpoline_thunk : 1;
u8 fentry : 1;
- u8 kcov : 1;
+ u8 profiling_func : 1;
struct list_head pv_target;
};