backport of patches 8238b4579866b7c1bb99883cfe102a43db5506ff and d6ffe6067a54972564552ea45d320fb98db1ac5e

backport of patches 8238b4579866b7c1bb99883cfe102a43db5506ff and d6ffe6067a54972564552ea45d320fb98db1ac5e

[Mikulas Patocka]

Hi

Here I'm submitting backport of patches 
8238b4579866b7c1bb99883cfe102a43db5506ff and 
d6ffe6067a54972564552ea45d320fb98db1ac5e to the stable branches.

Mikulas

[PATCH] wait_on_bit: add an acquire memory barrier

[Mikulas Patocka]

This is backport of the upstream patch 8238b4579866b7c1bb99883cfe102a43db5506ff
for the stable branches 5.10, 5.15, 5.19

Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>

---
 arch/x86/include/asm/bitops.h                        |   21 +++++++++++++++++++
 include/asm-generic/bitops/instrumented-non-atomic.h |   12 ++++++++++
 include/asm-generic/bitops/non-atomic.h              |   14 ++++++++++++
 include/linux/buffer_head.h                          |    2 -
 include/linux/wait_bit.h                             |    8 +++----
 kernel/sched/wait_bit.c                              |    2 -
 6 files changed, 53 insertions(+), 6 deletions(-)

Index: linux-stable/arch/x86/include/asm/bitops.h
===================================================================
--- linux-stable.orig/arch/x86/include/asm/bitops.h	2022-09-30 13:07:11.000000000 +0200
+++ linux-stable/arch/x86/include/asm/bitops.h	2022-09-30 13:07:11.000000000 +0200
@@ -207,6 +207,20 @@ static __always_inline bool constant_tes
 		(addr[nr >> _BITOPS_LONG_SHIFT])) != 0;
 }
 
+static __always_inline bool constant_test_bit_acquire(long nr, const volatile unsigned long *addr)
+{
+	bool oldbit;
+
+	asm volatile("testb %2,%1"
+		     CC_SET(nz)
+		     : CC_OUT(nz) (oldbit)
+		     : "m" (((unsigned char *)addr)[nr >> 3]),
+		       "i" (1 << (nr & 7))
+		     :"memory");
+
+	return oldbit;
+}
+
 static __always_inline bool variable_test_bit(long nr, volatile const unsigned long *addr)
 {
 	bool oldbit;
@@ -224,6 +238,13 @@ static __always_inline bool variable_tes
 	 ? constant_test_bit((nr), (addr))	\
 	 : variable_test_bit((nr), (addr)))
 
+static __always_inline bool
+arch_test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	return __builtin_constant_p(nr) ? constant_test_bit_acquire(nr, addr) :
+					  variable_test_bit(nr, addr);
+}
+
 /**
  * __ffs - find first set bit in word
  * @word: The word to search
Index: linux-stable/include/asm-generic/bitops/instrumented-non-atomic.h
===================================================================
--- linux-stable.orig/include/asm-generic/bitops/instrumented-non-atomic.h	2022-09-30 13:07:11.000000000 +0200
+++ linux-stable/include/asm-generic/bitops/instrumented-non-atomic.h	2022-09-30 13:07:11.000000000 +0200
@@ -135,4 +135,16 @@ static __always_inline bool test_bit(lon
 	return arch_test_bit(nr, addr);
 }
 
+/**
+ * _test_bit_acquire - Determine, with acquire semantics, whether a bit is set
+ * @nr: bit number to test
+ * @addr: Address to start counting from
+ */
+static __always_inline bool
+test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	instrument_atomic_read(addr + BIT_WORD(nr), sizeof(long));
+	return arch_test_bit_acquire(nr, addr);
+}
+
 #endif /* _ASM_GENERIC_BITOPS_INSTRUMENTED_NON_ATOMIC_H */
Index: linux-stable/include/asm-generic/bitops/non-atomic.h
===================================================================
--- linux-stable.orig/include/asm-generic/bitops/non-atomic.h	2022-09-30 13:07:11.000000000 +0200
+++ linux-stable/include/asm-generic/bitops/non-atomic.h	2022-09-30 13:07:11.000000000 +0200
@@ -3,6 +3,7 @@
 #define _ASM_GENERIC_BITOPS_NON_ATOMIC_H_
 
 #include <asm/types.h>
+#include <asm/barrier.h>
 
 /**
  * arch___set_bit - Set a bit in memory
@@ -119,4 +120,17 @@ arch_test_bit(unsigned int nr, const vol
 }
 #define test_bit arch_test_bit
 
+/**
+ * arch_test_bit_acquire - Determine, with acquire semantics, whether a bit is set
+ * @nr: bit number to test
+ * @addr: Address to start counting from
+ */
+static __always_inline bool
+arch_test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	return 1UL & (smp_load_acquire(p) >> (nr & (BITS_PER_LONG-1)));
+}
+#define test_bit_acquire arch_test_bit_acquire
+
 #endif /* _ASM_GENERIC_BITOPS_NON_ATOMIC_H_ */
Index: linux-stable/include/linux/buffer_head.h
===================================================================
--- linux-stable.orig/include/linux/buffer_head.h	2022-09-30 13:07:11.000000000 +0200
+++ linux-stable/include/linux/buffer_head.h	2022-09-30 13:07:11.000000000 +0200
@@ -166,7 +166,7 @@ static __always_inline int buffer_uptoda
 	 * make it consistent with folio_test_uptodate
 	 * pairs with smp_mb__before_atomic in set_buffer_uptodate
 	 */
-	return (smp_load_acquire(&bh->b_state) & (1UL << BH_Uptodate)) != 0;
+	return test_bit_acquire(BH_Uptodate, &bh->b_state);
 }
 
 #define bh_offset(bh)		((unsigned long)(bh)->b_data & ~PAGE_MASK)
Index: linux-stable/include/linux/wait_bit.h
===================================================================
--- linux-stable.orig/include/linux/wait_bit.h	2022-09-30 13:07:11.000000000 +0200
+++ linux-stable/include/linux/wait_bit.h	2022-09-30 13:07:11.000000000 +0200
@@ -71,7 +71,7 @@ static inline int
 wait_on_bit(unsigned long *word, int bit, unsigned mode)
 {
 	might_sleep();
-	if (!test_bit(bit, word))
+	if (!test_bit_acquire(bit, word))
 		return 0;
 	return out_of_line_wait_on_bit(word, bit,
 				       bit_wait,
@@ -96,7 +96,7 @@ static inline int
 wait_on_bit_io(unsigned long *word, int bit, unsigned mode)
 {
 	might_sleep();
-	if (!test_bit(bit, word))
+	if (!test_bit_acquire(bit, word))
 		return 0;
 	return out_of_line_wait_on_bit(word, bit,
 				       bit_wait_io,
@@ -123,7 +123,7 @@ wait_on_bit_timeout(unsigned long *word,
 		    unsigned long timeout)
 {
 	might_sleep();
-	if (!test_bit(bit, word))
+	if (!test_bit_acquire(bit, word))
 		return 0;
 	return out_of_line_wait_on_bit_timeout(word, bit,
 					       bit_wait_timeout,
@@ -151,7 +151,7 @@ wait_on_bit_action(unsigned long *word,
 		   unsigned mode)
 {
 	might_sleep();
-	if (!test_bit(bit, word))
+	if (!test_bit_acquire(bit, word))
 		return 0;
 	return out_of_line_wait_on_bit(word, bit, action, mode);
 }
Index: linux-stable/kernel/sched/wait_bit.c
===================================================================
--- linux-stable.orig/kernel/sched/wait_bit.c	2022-09-30 13:07:11.000000000 +0200
+++ linux-stable/kernel/sched/wait_bit.c	2022-09-30 13:07:11.000000000 +0200
@@ -47,7 +47,7 @@ __wait_on_bit(struct wait_queue_head *wq
 		prepare_to_wait(wq_head, &wbq_entry->wq_entry, mode);
 		if (test_bit(wbq_entry->key.bit_nr, wbq_entry->key.flags))
 			ret = (*action)(&wbq_entry->key, mode);
-	} while (test_bit(wbq_entry->key.bit_nr, wbq_entry->key.flags) && !ret);
+	} while (test_bit_acquire(wbq_entry->key.bit_nr, wbq_entry->key.flags) && !ret);
 
 	finish_wait(wq_head, &wbq_entry->wq_entry);
 

[PATCH] wait_on_bit: add an acquire memory barrier

[Mikulas Patocka]

This is backport of the upstream patch 8238b4579866b7c1bb99883cfe102a43db5506ff
for the stable branch 5.4

Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>

---
 arch/x86/include/asm/bitops.h             |   21 +++++++++++++++++++++
 include/asm-generic/bitops-instrumented.h |    6 ++++++
 include/asm-generic/bitops/non-atomic.h   |   14 ++++++++++++++
 include/linux/buffer_head.h               |    2 +-
 include/linux/wait_bit.h                  |    8 ++++----
 kernel/sched/wait_bit.c                   |    2 +-
 6 files changed, 47 insertions(+), 6 deletions(-)

Index: linux-stable/arch/x86/include/asm/bitops.h
===================================================================
--- linux-stable.orig/arch/x86/include/asm/bitops.h	2022-09-30 15:38:29.000000000 +0200
+++ linux-stable/arch/x86/include/asm/bitops.h	2022-09-30 15:38:29.000000000 +0200
@@ -207,6 +207,20 @@ static __always_inline bool constant_tes
 		(addr[nr >> _BITOPS_LONG_SHIFT])) != 0;
 }
 
+static __always_inline bool constant_test_bit_acquire(long nr, const volatile unsigned long *addr)
+{
+	bool oldbit;
+
+	asm volatile("testb %2,%1"
+		     CC_SET(nz)
+		     : CC_OUT(nz) (oldbit)
+		     : "m" (((unsigned char *)addr)[nr >> 3]),
+		       "i" (1 << (nr & 7))
+		     :"memory");
+
+	return oldbit;
+}
+
 static __always_inline bool variable_test_bit(long nr, volatile const unsigned long *addr)
 {
 	bool oldbit;
@@ -224,6 +238,13 @@ static __always_inline bool variable_tes
 	 ? constant_test_bit((nr), (addr))	\
 	 : variable_test_bit((nr), (addr)))
 
+static __always_inline bool
+arch_test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	return __builtin_constant_p(nr) ? constant_test_bit_acquire(nr, addr) :
+					  variable_test_bit(nr, addr);
+}
+
 /**
  * __ffs - find first set bit in word
  * @word: The word to search
Index: linux-stable/include/asm-generic/bitops/non-atomic.h
===================================================================
--- linux-stable.orig/include/asm-generic/bitops/non-atomic.h	2022-09-30 15:38:29.000000000 +0200
+++ linux-stable/include/asm-generic/bitops/non-atomic.h	2022-09-30 15:38:29.000000000 +0200
@@ -3,6 +3,7 @@
 #define _ASM_GENERIC_BITOPS_NON_ATOMIC_H_
 
 #include <asm/types.h>
+#include <asm/barrier.h>
 
 /**
  * __set_bit - Set a bit in memory
@@ -106,4 +107,17 @@ static inline int test_bit(int nr, const
 	return 1UL & (addr[BIT_WORD(nr)] >> (nr & (BITS_PER_LONG-1)));
 }
 
+/**
+ * arch_test_bit_acquire - Determine, with acquire semantics, whether a bit is set
+ * @nr: bit number to test
+ * @addr: Address to start counting from
+ */
+static __always_inline bool
+arch_test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	return 1UL & (smp_load_acquire(p) >> (nr & (BITS_PER_LONG-1)));
+}
+#define test_bit_acquire arch_test_bit_acquire
+
 #endif /* _ASM_GENERIC_BITOPS_NON_ATOMIC_H_ */
Index: linux-stable/include/linux/buffer_head.h
===================================================================
--- linux-stable.orig/include/linux/buffer_head.h	2022-09-30 15:38:29.000000000 +0200
+++ linux-stable/include/linux/buffer_head.h	2022-09-30 15:38:29.000000000 +0200
@@ -166,7 +166,7 @@ static __always_inline int buffer_uptoda
 	 * make it consistent with folio_test_uptodate
 	 * pairs with smp_mb__before_atomic in set_buffer_uptodate
 	 */
-	return (smp_load_acquire(&bh->b_state) & (1UL << BH_Uptodate)) != 0;
+	return test_bit_acquire(BH_Uptodate, &bh->b_state);
 }
 
 #define bh_offset(bh)		((unsigned long)(bh)->b_data & ~PAGE_MASK)
Index: linux-stable/include/linux/wait_bit.h
===================================================================
--- linux-stable.orig/include/linux/wait_bit.h	2022-09-30 15:38:29.000000000 +0200
+++ linux-stable/include/linux/wait_bit.h	2022-09-30 15:38:29.000000000 +0200
@@ -71,7 +71,7 @@ static inline int
 wait_on_bit(unsigned long *word, int bit, unsigned mode)
 {
 	might_sleep();
-	if (!test_bit(bit, word))
+	if (!test_bit_acquire(bit, word))
 		return 0;
 	return out_of_line_wait_on_bit(word, bit,
 				       bit_wait,
@@ -96,7 +96,7 @@ static inline int
 wait_on_bit_io(unsigned long *word, int bit, unsigned mode)
 {
 	might_sleep();
-	if (!test_bit(bit, word))
+	if (!test_bit_acquire(bit, word))
 		return 0;
 	return out_of_line_wait_on_bit(word, bit,
 				       bit_wait_io,
@@ -123,7 +123,7 @@ wait_on_bit_timeout(unsigned long *word,
 		    unsigned long timeout)
 {
 	might_sleep();
-	if (!test_bit(bit, word))
+	if (!test_bit_acquire(bit, word))
 		return 0;
 	return out_of_line_wait_on_bit_timeout(word, bit,
 					       bit_wait_timeout,
@@ -151,7 +151,7 @@ wait_on_bit_action(unsigned long *word,
 		   unsigned mode)
 {
 	might_sleep();
-	if (!test_bit(bit, word))
+	if (!test_bit_acquire(bit, word))
 		return 0;
 	return out_of_line_wait_on_bit(word, bit, action, mode);
 }
Index: linux-stable/kernel/sched/wait_bit.c
===================================================================
--- linux-stable.orig/kernel/sched/wait_bit.c	2022-09-30 15:38:29.000000000 +0200
+++ linux-stable/kernel/sched/wait_bit.c	2022-09-30 15:38:29.000000000 +0200
@@ -47,7 +47,7 @@ __wait_on_bit(struct wait_queue_head *wq
 		prepare_to_wait(wq_head, &wbq_entry->wq_entry, mode);
 		if (test_bit(wbq_entry->key.bit_nr, wbq_entry->key.flags))
 			ret = (*action)(&wbq_entry->key, mode);
-	} while (test_bit(wbq_entry->key.bit_nr, wbq_entry->key.flags) && !ret);
+	} while (test_bit_acquire(wbq_entry->key.bit_nr, wbq_entry->key.flags) && !ret);
 
 	finish_wait(wq_head, &wbq_entry->wq_entry);
 
Index: linux-stable/include/asm-generic/bitops-instrumented.h
===================================================================
--- linux-stable.orig/include/asm-generic/bitops-instrumented.h	2022-09-30 15:37:42.000000000 +0200
+++ linux-stable/include/asm-generic/bitops-instrumented.h	2022-09-30 15:40:55.000000000 +0200
@@ -238,6 +238,12 @@ static inline bool test_bit(long nr, con
 	return arch_test_bit(nr, addr);
 }
 
+static inline bool test_bit_acquire(long nr, const volatile unsigned long *addr)
+{
+	kasan_check_read(addr + BIT_WORD(nr), sizeof(long));
+	return arch_test_bit_acquire(nr, addr);
+}
+
 #if defined(arch_clear_bit_unlock_is_negative_byte)
 /**
  * clear_bit_unlock_is_negative_byte - Clear a bit in memory and test if bottom

[PATCH] wait_on_bit: add an acquire memory barrier

[Mikulas Patocka]

This is backport of the upstream patch 8238b4579866b7c1bb99883cfe102a43db5506ff
for the stable branch 4.19

Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>

---
 arch/x86/include/asm/bitops.h           |   21 +++++++++++++++++++++
 include/asm-generic/bitops/non-atomic.h |   14 ++++++++++++++
 include/linux/buffer_head.h             |    2 +-
 include/linux/wait_bit.h                |    8 ++++----
 kernel/sched/wait_bit.c                 |    2 +-
 5 files changed, 41 insertions(+), 6 deletions(-)

Index: linux-stable/arch/x86/include/asm/bitops.h
===================================================================
--- linux-stable.orig/arch/x86/include/asm/bitops.h	2022-09-30 15:44:48.000000000 +0200
+++ linux-stable/arch/x86/include/asm/bitops.h	2022-09-30 15:46:38.000000000 +0200
@@ -317,6 +317,20 @@ static __always_inline bool constant_tes
 		(addr[nr >> _BITOPS_LONG_SHIFT])) != 0;
 }
 
+static __always_inline bool constant_test_bit_acquire(long nr, const volatile unsigned long *addr)
+{
+	bool oldbit;
+
+	asm volatile("testb %2,%1"
+		     CC_SET(nz)
+		     : CC_OUT(nz) (oldbit)
+		     : "m" (((unsigned char *)addr)[nr >> 3]),
+		       "i" (1 << (nr & 7))
+		     :"memory");
+
+	return oldbit;
+}
+
 static __always_inline bool variable_test_bit(long nr, volatile const unsigned long *addr)
 {
 	bool oldbit;
@@ -343,6 +357,13 @@ static bool test_bit(int nr, const volat
 	 ? constant_test_bit((nr), (addr))	\
 	 : variable_test_bit((nr), (addr)))
 
+static __always_inline bool
+test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	return __builtin_constant_p(nr) ? constant_test_bit_acquire(nr, addr) :
+					  variable_test_bit(nr, addr);
+}
+
 /**
  * __ffs - find first set bit in word
  * @word: The word to search
Index: linux-stable/include/asm-generic/bitops/non-atomic.h
===================================================================
--- linux-stable.orig/include/asm-generic/bitops/non-atomic.h	2022-09-30 15:44:48.000000000 +0200
+++ linux-stable/include/asm-generic/bitops/non-atomic.h	2022-09-30 15:44:48.000000000 +0200
@@ -3,6 +3,7 @@
 #define _ASM_GENERIC_BITOPS_NON_ATOMIC_H_
 
 #include <asm/types.h>
+#include <asm/barrier.h>
 
 /**
  * __set_bit - Set a bit in memory
@@ -106,4 +107,17 @@ static inline int test_bit(int nr, const
 	return 1UL & (addr[BIT_WORD(nr)] >> (nr & (BITS_PER_LONG-1)));
 }
 
+/**
+ * arch_test_bit_acquire - Determine, with acquire semantics, whether a bit is set
+ * @nr: bit number to test
+ * @addr: Address to start counting from
+ */
+static __always_inline bool
+arch_test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	return 1UL & (smp_load_acquire(p) >> (nr & (BITS_PER_LONG-1)));
+}
+#define test_bit_acquire arch_test_bit_acquire
+
 #endif /* _ASM_GENERIC_BITOPS_NON_ATOMIC_H_ */
Index: linux-stable/include/linux/buffer_head.h
===================================================================
--- linux-stable.orig/include/linux/buffer_head.h	2022-09-30 15:44:48.000000000 +0200
+++ linux-stable/include/linux/buffer_head.h	2022-09-30 15:44:48.000000000 +0200
@@ -166,7 +166,7 @@ static __always_inline int buffer_uptoda
 	 * make it consistent with folio_test_uptodate
 	 * pairs with smp_mb__before_atomic in set_buffer_uptodate
 	 */
-	return (smp_load_acquire(&bh->b_state) & (1UL << BH_Uptodate)) != 0;
+	return test_bit_acquire(BH_Uptodate, &bh->b_state);
 }
 
 #define bh_offset(bh)		((unsigned long)(bh)->b_data & ~PAGE_MASK)
Index: linux-stable/include/linux/wait_bit.h
===================================================================
--- linux-stable.orig/include/linux/wait_bit.h	2022-09-30 15:44:48.000000000 +0200
+++ linux-stable/include/linux/wait_bit.h	2022-09-30 15:44:48.000000000 +0200
@@ -71,7 +71,7 @@ static inline int
 wait_on_bit(unsigned long *word, int bit, unsigned mode)
 {
 	might_sleep();
-	if (!test_bit(bit, word))
+	if (!test_bit_acquire(bit, word))
 		return 0;
 	return out_of_line_wait_on_bit(word, bit,
 				       bit_wait,
@@ -96,7 +96,7 @@ static inline int
 wait_on_bit_io(unsigned long *word, int bit, unsigned mode)
 {
 	might_sleep();
-	if (!test_bit(bit, word))
+	if (!test_bit_acquire(bit, word))
 		return 0;
 	return out_of_line_wait_on_bit(word, bit,
 				       bit_wait_io,
@@ -123,7 +123,7 @@ wait_on_bit_timeout(unsigned long *word,
 		    unsigned long timeout)
 {
 	might_sleep();
-	if (!test_bit(bit, word))
+	if (!test_bit_acquire(bit, word))
 		return 0;
 	return out_of_line_wait_on_bit_timeout(word, bit,
 					       bit_wait_timeout,
@@ -151,7 +151,7 @@ wait_on_bit_action(unsigned long *word,
 		   unsigned mode)
 {
 	might_sleep();
-	if (!test_bit(bit, word))
+	if (!test_bit_acquire(bit, word))
 		return 0;
 	return out_of_line_wait_on_bit(word, bit, action, mode);
 }
Index: linux-stable/kernel/sched/wait_bit.c
===================================================================
--- linux-stable.orig/kernel/sched/wait_bit.c	2022-09-30 15:44:48.000000000 +0200
+++ linux-stable/kernel/sched/wait_bit.c	2022-09-30 15:44:48.000000000 +0200
@@ -46,7 +46,7 @@ __wait_on_bit(struct wait_queue_head *wq
 		prepare_to_wait(wq_head, &wbq_entry->wq_entry, mode);
 		if (test_bit(wbq_entry->key.bit_nr, wbq_entry->key.flags))
 			ret = (*action)(&wbq_entry->key, mode);
-	} while (test_bit(wbq_entry->key.bit_nr, wbq_entry->key.flags) && !ret);
+	} while (test_bit_acquire(wbq_entry->key.bit_nr, wbq_entry->key.flags) && !ret);
 
 	finish_wait(wq_head, &wbq_entry->wq_entry);
 

[PATCH] wait_on_bit: add an acquire memory barrier

[Mikulas Patocka]

This is backport of the upstream patch 8238b4579866b7c1bb99883cfe102a43db5506ff
for the stable branch 4.14

Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>

---
 arch/x86/include/asm/bitops.h           |   21 +++++++++++++++++++++
 include/asm-generic/bitops/non-atomic.h |   14 ++++++++++++++
 include/linux/buffer_head.h             |    2 +-
 include/linux/wait_bit.h                |    8 ++++----
 kernel/sched/wait_bit.c                 |    2 +-
 5 files changed, 41 insertions(+), 6 deletions(-)

Index: linux-stable/arch/x86/include/asm/bitops.h
===================================================================
--- linux-stable.orig/arch/x86/include/asm/bitops.h	2022-09-30 15:55:01.000000000 +0200
+++ linux-stable/arch/x86/include/asm/bitops.h	2022-09-30 15:55:01.000000000 +0200
@@ -328,6 +328,20 @@ static __always_inline bool constant_tes
 		(addr[nr >> _BITOPS_LONG_SHIFT])) != 0;
 }
 
+static __always_inline bool constant_test_bit_acquire(long nr, const volatile unsigned long *addr)
+{
+	bool oldbit;
+
+	asm volatile("testb %2,%1"
+		     CC_SET(nz)
+		     : CC_OUT(nz) (oldbit)
+		     : "m" (((unsigned char *)addr)[nr >> 3]),
+		       "i" (1 << (nr & 7))
+		     :"memory");
+
+	return oldbit;
+}
+
 static __always_inline bool variable_test_bit(long nr, volatile const unsigned long *addr)
 {
 	bool oldbit;
@@ -354,6 +368,13 @@ static bool test_bit(int nr, const volat
 	 ? constant_test_bit((nr), (addr))	\
 	 : variable_test_bit((nr), (addr)))
 
+static __always_inline bool
+test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	return __builtin_constant_p(nr) ? constant_test_bit_acquire(nr, addr) :
+					  variable_test_bit(nr, addr);
+}
+
 /**
  * __ffs - find first set bit in word
  * @word: The word to search
Index: linux-stable/include/asm-generic/bitops/non-atomic.h
===================================================================
--- linux-stable.orig/include/asm-generic/bitops/non-atomic.h	2022-09-30 15:55:01.000000000 +0200
+++ linux-stable/include/asm-generic/bitops/non-atomic.h	2022-09-30 15:55:01.000000000 +0200
@@ -3,6 +3,7 @@
 #define _ASM_GENERIC_BITOPS_NON_ATOMIC_H_
 
 #include <asm/types.h>
+#include <asm/barrier.h>
 
 /**
  * __set_bit - Set a bit in memory
@@ -106,4 +107,17 @@ static inline int test_bit(int nr, const
 	return 1UL & (addr[BIT_WORD(nr)] >> (nr & (BITS_PER_LONG-1)));
 }
 
+/**
+ * arch_test_bit_acquire - Determine, with acquire semantics, whether a bit is set
+ * @nr: bit number to test
+ * @addr: Address to start counting from
+ */
+static __always_inline bool
+arch_test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	return 1UL & (smp_load_acquire(p) >> (nr & (BITS_PER_LONG-1)));
+}
+#define test_bit_acquire arch_test_bit_acquire
+
 #endif /* _ASM_GENERIC_BITOPS_NON_ATOMIC_H_ */
Index: linux-stable/include/linux/buffer_head.h
===================================================================
--- linux-stable.orig/include/linux/buffer_head.h	2022-09-30 15:55:01.000000000 +0200
+++ linux-stable/include/linux/buffer_head.h	2022-09-30 15:55:01.000000000 +0200
@@ -163,7 +163,7 @@ static __always_inline int buffer_uptoda
 	 * make it consistent with folio_test_uptodate
 	 * pairs with smp_mb__before_atomic in set_buffer_uptodate
 	 */
-	return (smp_load_acquire(&bh->b_state) & (1UL << BH_Uptodate)) != 0;
+	return test_bit_acquire(BH_Uptodate, &bh->b_state);
 }
 
 #define bh_offset(bh)		((unsigned long)(bh)->b_data & ~PAGE_MASK)
Index: linux-stable/include/linux/wait_bit.h
===================================================================
--- linux-stable.orig/include/linux/wait_bit.h	2022-09-30 15:55:01.000000000 +0200
+++ linux-stable/include/linux/wait_bit.h	2022-09-30 15:55:01.000000000 +0200
@@ -76,7 +76,7 @@ static inline int
 wait_on_bit(unsigned long *word, int bit, unsigned mode)
 {
 	might_sleep();
-	if (!test_bit(bit, word))
+	if (!test_bit_acquire(bit, word))
 		return 0;
 	return out_of_line_wait_on_bit(word, bit,
 				       bit_wait,
@@ -101,7 +101,7 @@ static inline int
 wait_on_bit_io(unsigned long *word, int bit, unsigned mode)
 {
 	might_sleep();
-	if (!test_bit(bit, word))
+	if (!test_bit_acquire(bit, word))
 		return 0;
 	return out_of_line_wait_on_bit(word, bit,
 				       bit_wait_io,
@@ -128,7 +128,7 @@ wait_on_bit_timeout(unsigned long *word,
 		    unsigned long timeout)
 {
 	might_sleep();
-	if (!test_bit(bit, word))
+	if (!test_bit_acquire(bit, word))
 		return 0;
 	return out_of_line_wait_on_bit_timeout(word, bit,
 					       bit_wait_timeout,
@@ -156,7 +156,7 @@ wait_on_bit_action(unsigned long *word,
 		   unsigned mode)
 {
 	might_sleep();
-	if (!test_bit(bit, word))
+	if (!test_bit_acquire(bit, word))
 		return 0;
 	return out_of_line_wait_on_bit(word, bit, action, mode);
 }
Index: linux-stable/kernel/sched/wait_bit.c
===================================================================
--- linux-stable.orig/kernel/sched/wait_bit.c	2022-09-30 15:55:01.000000000 +0200
+++ linux-stable/kernel/sched/wait_bit.c	2022-09-30 15:55:55.000000000 +0200
@@ -49,7 +49,7 @@ __wait_on_bit(struct wait_queue_head *wq
 		prepare_to_wait(wq_head, &wbq_entry->wq_entry, mode);
 		if (test_bit(wbq_entry->key.bit_nr, wbq_entry->key.flags))
 			ret = (*action)(&wbq_entry->key, mode);
-	} while (test_bit(wbq_entry->key.bit_nr, wbq_entry->key.flags) && !ret);
+	} while (test_bit_acquire(wbq_entry->key.bit_nr, wbq_entry->key.flags) && !ret);
 	finish_wait(wq_head, &wbq_entry->wq_entry);
 	return ret;
 }

[PATCH] wait_on_bit: add an acquire memory barrier

[Mikulas Patocka]

This is backport of the upstream patch 8238b4579866b7c1bb99883cfe102a43db5506ff
for the stable branch 4.9

Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>

---
 arch/x86/include/asm/bitops.h           |   21 +++++++++++++++++++++
 include/asm-generic/bitops/non-atomic.h |   14 ++++++++++++++
 include/linux/buffer_head.h             |    2 +-
 include/linux/wait.h                    |    8 ++++----
 kernel/sched/wait.c                     |    2 +-
 5 files changed, 41 insertions(+), 6 deletions(-)

Index: linux-stable/arch/x86/include/asm/bitops.h
===================================================================
--- linux-stable.orig/arch/x86/include/asm/bitops.h	2022-09-30 16:01:38.000000000 +0200
+++ linux-stable/arch/x86/include/asm/bitops.h	2022-09-30 16:01:38.000000000 +0200
@@ -314,6 +314,20 @@ static __always_inline bool constant_tes
 		(addr[nr >> _BITOPS_LONG_SHIFT])) != 0;
 }
 
+static __always_inline bool constant_test_bit_acquire(long nr, const volatile unsigned long *addr)
+{
+	bool oldbit;
+
+	asm volatile("testb %2,%1"
+		     CC_SET(nz)
+		     : CC_OUT(nz) (oldbit)
+		     : "m" (((unsigned char *)addr)[nr >> 3]),
+		       "i" (1 << (nr & 7))
+		     :"memory");
+
+	return oldbit;
+}
+
 static __always_inline bool variable_test_bit(long nr, volatile const unsigned long *addr)
 {
 	bool oldbit;
@@ -340,6 +354,13 @@ static bool test_bit(int nr, const volat
 	 ? constant_test_bit((nr), (addr))	\
 	 : variable_test_bit((nr), (addr)))
 
+static __always_inline bool
+test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	return __builtin_constant_p(nr) ? constant_test_bit_acquire(nr, addr) :
+					  variable_test_bit(nr, addr);
+}
+
 /**
  * __ffs - find first set bit in word
  * @word: The word to search
Index: linux-stable/include/asm-generic/bitops/non-atomic.h
===================================================================
--- linux-stable.orig/include/asm-generic/bitops/non-atomic.h	2022-09-30 16:01:38.000000000 +0200
+++ linux-stable/include/asm-generic/bitops/non-atomic.h	2022-09-30 16:01:38.000000000 +0200
@@ -2,6 +2,7 @@
 #define _ASM_GENERIC_BITOPS_NON_ATOMIC_H_
 
 #include <asm/types.h>
+#include <asm/barrier.h>
 
 /**
  * __set_bit - Set a bit in memory
@@ -105,4 +106,17 @@ static inline int test_bit(int nr, const
 	return 1UL & (addr[BIT_WORD(nr)] >> (nr & (BITS_PER_LONG-1)));
 }
 
+/**
+ * arch_test_bit_acquire - Determine, with acquire semantics, whether a bit is set
+ * @nr: bit number to test
+ * @addr: Address to start counting from
+ */
+static __always_inline bool
+arch_test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	return 1UL & (smp_load_acquire(p) >> (nr & (BITS_PER_LONG-1)));
+}
+#define test_bit_acquire arch_test_bit_acquire
+
 #endif /* _ASM_GENERIC_BITOPS_NON_ATOMIC_H_ */
Index: linux-stable/include/linux/buffer_head.h
===================================================================
--- linux-stable.orig/include/linux/buffer_head.h	2022-09-30 16:01:38.000000000 +0200
+++ linux-stable/include/linux/buffer_head.h	2022-09-30 16:01:38.000000000 +0200
@@ -162,7 +162,7 @@ static __always_inline int buffer_uptoda
 	 * make it consistent with folio_test_uptodate
 	 * pairs with smp_mb__before_atomic in set_buffer_uptodate
 	 */
-	return (smp_load_acquire(&bh->b_state) & (1UL << BH_Uptodate)) != 0;
+	return test_bit_acquire(BH_Uptodate, &bh->b_state);
 }
 
 #define bh_offset(bh)		((unsigned long)(bh)->b_data & ~PAGE_MASK)
Index: linux-stable/include/linux/wait.h
===================================================================
--- linux-stable.orig/include/linux/wait.h	2022-09-30 16:01:38.000000000 +0200
+++ linux-stable/include/linux/wait.h	2022-09-30 16:01:38.000000000 +0200
@@ -1066,7 +1066,7 @@ static inline int
 wait_on_bit(unsigned long *word, int bit, unsigned mode)
 {
 	might_sleep();
-	if (!test_bit(bit, word))
+	if (!test_bit_acquire(bit, word))
 		return 0;
 	return out_of_line_wait_on_bit(word, bit,
 				       bit_wait,
@@ -1091,7 +1091,7 @@ static inline int
 wait_on_bit_io(unsigned long *word, int bit, unsigned mode)
 {
 	might_sleep();
-	if (!test_bit(bit, word))
+	if (!test_bit_acquire(bit, word))
 		return 0;
 	return out_of_line_wait_on_bit(word, bit,
 				       bit_wait_io,
@@ -1118,7 +1118,7 @@ wait_on_bit_timeout(unsigned long *word,
 		    unsigned long timeout)
 {
 	might_sleep();
-	if (!test_bit(bit, word))
+	if (!test_bit_acquire(bit, word))
 		return 0;
 	return out_of_line_wait_on_bit_timeout(word, bit,
 					       bit_wait_timeout,
@@ -1146,7 +1146,7 @@ wait_on_bit_action(unsigned long *word,
 		   unsigned mode)
 {
 	might_sleep();
-	if (!test_bit(bit, word))
+	if (!test_bit_acquire(bit, word))
 		return 0;
 	return out_of_line_wait_on_bit(word, bit, action, mode);
 }
Index: linux-stable/kernel/sched/wait.c
===================================================================
--- linux-stable.orig/kernel/sched/wait.c	2022-09-30 16:01:38.000000000 +0200
+++ linux-stable/kernel/sched/wait.c	2022-09-30 16:01:58.000000000 +0200
@@ -389,7 +389,7 @@ __wait_on_bit(wait_queue_head_t *wq, str
 		prepare_to_wait(wq, &q->wait, mode);
 		if (test_bit(q->key.bit_nr, q->key.flags))
 			ret = (*action)(&q->key, mode);
-	} while (test_bit(q->key.bit_nr, q->key.flags) && !ret);
+	} while (test_bit_acquire(q->key.bit_nr, q->key.flags) && !ret);
 	finish_wait(wq, &q->wait);
 	return ret;
 }

[PATCH] provide arch_test_bit_acquire for architectures that define test_bit

[Mikulas Patocka]

This is backport of the upstream patch d6ffe6067a54972564552ea45d320fb98db1ac5e
for the stable branches 5.19, 5.15, 5.10

Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>

---
 arch/alpha/include/asm/bitops.h   |    7 +++++++
 arch/hexagon/include/asm/bitops.h |   15 +++++++++++++++
 arch/ia64/include/asm/bitops.h    |    7 +++++++
 arch/m68k/include/asm/bitops.h    |    6 ++++++
 arch/s390/include/asm/bitops.h    |    7 +++++++
 arch/sh/include/asm/bitops-op32.h |    7 +++++++
 6 files changed, 49 insertions(+)

Index: linux-stable/arch/alpha/include/asm/bitops.h
===================================================================
--- linux-stable.orig/arch/alpha/include/asm/bitops.h	2022-09-30 13:07:14.000000000 +0200
+++ linux-stable/arch/alpha/include/asm/bitops.h	2022-09-30 13:07:14.000000000 +0200
@@ -289,6 +289,13 @@ test_bit(int nr, const volatile void * a
 	return (1UL & (((const int *) addr)[nr >> 5] >> (nr & 31))) != 0UL;
 }
 
+static __always_inline bool
+test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	return 1UL & (smp_load_acquire(p) >> (nr & (BITS_PER_LONG-1)));
+}
+
 /*
  * ffz = Find First Zero in word. Undefined if no zero exists,
  * so code should check against ~0UL first..
Index: linux-stable/arch/hexagon/include/asm/bitops.h
===================================================================
--- linux-stable.orig/arch/hexagon/include/asm/bitops.h	2022-09-30 13:07:14.000000000 +0200
+++ linux-stable/arch/hexagon/include/asm/bitops.h	2022-09-30 13:07:14.000000000 +0200
@@ -172,7 +172,22 @@ static inline int __test_bit(int nr, con
 	return retval;
 }
 
+static inline int __test_bit_acquire(int nr, const volatile unsigned long *addr)
+{
+	int retval;
+
+	asm volatile(
+	"{P0 = tstbit(%1,%2); if (P0.new) %0 = #1; if (!P0.new) %0 = #0;}\n"
+	: "=&r" (retval)
+	: "r" (addr[BIT_WORD(nr)]), "r" (nr % BITS_PER_LONG)
+	: "p0", "memory"
+	);
+
+	return retval;
+}
+
 #define test_bit(nr, addr) __test_bit(nr, addr)
+#define test_bit_acquire(nr, addr) __test_bit_acquire(nr, addr)
 
 /*
  * ffz - find first zero in word.
Index: linux-stable/arch/ia64/include/asm/bitops.h
===================================================================
--- linux-stable.orig/arch/ia64/include/asm/bitops.h	2022-09-30 13:07:14.000000000 +0200
+++ linux-stable/arch/ia64/include/asm/bitops.h	2022-09-30 13:07:14.000000000 +0200
@@ -337,6 +337,13 @@ test_bit (int nr, const volatile void *a
 	return 1 & (((const volatile __u32 *) addr)[nr >> 5] >> (nr & 31));
 }
 
+static __always_inline bool
+test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	return 1UL & (smp_load_acquire(p) >> (nr & (BITS_PER_LONG-1)));
+}
+
 /**
  * ffz - find the first zero bit in a long word
  * @x: The long word to find the bit in
Index: linux-stable/arch/m68k/include/asm/bitops.h
===================================================================
--- linux-stable.orig/arch/m68k/include/asm/bitops.h	2022-09-30 13:07:14.000000000 +0200
+++ linux-stable/arch/m68k/include/asm/bitops.h	2022-09-30 13:07:14.000000000 +0200
@@ -153,6 +153,12 @@ static inline int test_bit(int nr, const
 	return (vaddr[nr >> 5] & (1UL << (nr & 31))) != 0;
 }
 
+static __always_inline bool
+test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	return 1UL & (smp_load_acquire(p) >> (nr & (BITS_PER_LONG-1)));
+}
 
 static inline int bset_reg_test_and_set_bit(int nr,
 					    volatile unsigned long *vaddr)
Index: linux-stable/arch/s390/include/asm/bitops.h
===================================================================
--- linux-stable.orig/arch/s390/include/asm/bitops.h	2022-09-30 13:07:14.000000000 +0200
+++ linux-stable/arch/s390/include/asm/bitops.h	2022-09-30 13:07:14.000000000 +0200
@@ -184,6 +184,13 @@ static inline bool arch_test_bit(unsigne
 	return *addr & mask;
 }
 
+static __always_inline bool
+arch_test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	return 1UL & (smp_load_acquire(p) >> (nr & (BITS_PER_LONG-1)));
+}
+
 static inline bool arch_test_and_set_bit_lock(unsigned long nr,
 					      volatile unsigned long *ptr)
 {
Index: linux-stable/arch/sh/include/asm/bitops-op32.h
===================================================================
--- linux-stable.orig/arch/sh/include/asm/bitops-op32.h	2022-09-30 13:07:14.000000000 +0200
+++ linux-stable/arch/sh/include/asm/bitops-op32.h	2022-09-30 13:07:14.000000000 +0200
@@ -138,4 +138,11 @@ static inline int test_bit(int nr, const
 	return 1UL & (addr[BIT_WORD(nr)] >> (nr & (BITS_PER_LONG-1)));
 }
 
+static __always_inline bool
+test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	return 1UL & (smp_load_acquire(p) >> (nr & (BITS_PER_LONG-1)));
+}
+
 #endif /* __ASM_SH_BITOPS_OP32_H */

[PATCH] provide arch_test_bit_acquire for architectures that define test_bit

[Mikulas Patocka]

This is backport of the upstream patch d6ffe6067a54972564552ea45d320fb98db1ac5e
for the stable branch 5.4

Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>

---
 arch/alpha/include/asm/bitops.h   |    7 +++++++
 arch/hexagon/include/asm/bitops.h |   15 +++++++++++++++
 arch/ia64/include/asm/bitops.h    |    7 +++++++
 arch/m68k/include/asm/bitops.h    |    6 ++++++
 arch/s390/include/asm/bitops.h    |    7 +++++++
 arch/sh/include/asm/bitops-op32.h |    7 +++++++
 6 files changed, 49 insertions(+)

Index: linux-stable/arch/alpha/include/asm/bitops.h
===================================================================
--- linux-stable.orig/arch/alpha/include/asm/bitops.h	2022-09-30 15:39:09.000000000 +0200
+++ linux-stable/arch/alpha/include/asm/bitops.h	2022-09-30 15:39:09.000000000 +0200
@@ -289,6 +289,13 @@ test_bit(int nr, const volatile void * a
 	return (1UL & (((const int *) addr)[nr >> 5] >> (nr & 31))) != 0UL;
 }
 
+static __always_inline bool
+test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	return 1UL & (smp_load_acquire(p) >> (nr & (BITS_PER_LONG-1)));
+}
+
 /*
  * ffz = Find First Zero in word. Undefined if no zero exists,
  * so code should check against ~0UL first..
Index: linux-stable/arch/hexagon/include/asm/bitops.h
===================================================================
--- linux-stable.orig/arch/hexagon/include/asm/bitops.h	2022-09-30 15:39:09.000000000 +0200
+++ linux-stable/arch/hexagon/include/asm/bitops.h	2022-09-30 15:39:09.000000000 +0200
@@ -172,7 +172,22 @@ static inline int __test_bit(int nr, con
 	return retval;
 }
 
+static inline int __test_bit_acquire(int nr, const volatile unsigned long *addr)
+{
+	int retval;
+
+	asm volatile(
+	"{P0 = tstbit(%1,%2); if (P0.new) %0 = #1; if (!P0.new) %0 = #0;}\n"
+	: "=&r" (retval)
+	: "r" (addr[BIT_WORD(nr)]), "r" (nr % BITS_PER_LONG)
+	: "p0", "memory"
+	);
+
+	return retval;
+}
+
 #define test_bit(nr, addr) __test_bit(nr, addr)
+#define test_bit_acquire(nr, addr) __test_bit_acquire(nr, addr)
 
 /*
  * ffz - find first zero in word.
Index: linux-stable/arch/ia64/include/asm/bitops.h
===================================================================
--- linux-stable.orig/arch/ia64/include/asm/bitops.h	2022-09-30 15:39:09.000000000 +0200
+++ linux-stable/arch/ia64/include/asm/bitops.h	2022-09-30 15:39:09.000000000 +0200
@@ -337,6 +337,13 @@ test_bit (int nr, const volatile void *a
 	return 1 & (((const volatile __u32 *) addr)[nr >> 5] >> (nr & 31));
 }
 
+static __always_inline bool
+test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	return 1UL & (smp_load_acquire(p) >> (nr & (BITS_PER_LONG-1)));
+}
+
 /**
  * ffz - find the first zero bit in a long word
  * @x: The long word to find the bit in
Index: linux-stable/arch/m68k/include/asm/bitops.h
===================================================================
--- linux-stable.orig/arch/m68k/include/asm/bitops.h	2022-09-30 15:39:09.000000000 +0200
+++ linux-stable/arch/m68k/include/asm/bitops.h	2022-09-30 15:39:09.000000000 +0200
@@ -153,6 +153,12 @@ static inline int test_bit(int nr, const
 	return (vaddr[nr >> 5] & (1UL << (nr & 31))) != 0;
 }
 
+static __always_inline bool
+test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	return 1UL & (smp_load_acquire(p) >> (nr & (BITS_PER_LONG-1)));
+}
 
 static inline int bset_reg_test_and_set_bit(int nr,
 					    volatile unsigned long *vaddr)
Index: linux-stable/arch/s390/include/asm/bitops.h
===================================================================
--- linux-stable.orig/arch/s390/include/asm/bitops.h	2022-09-30 15:39:09.000000000 +0200
+++ linux-stable/arch/s390/include/asm/bitops.h	2022-09-30 15:39:09.000000000 +0200
@@ -219,6 +219,13 @@ static inline bool arch_test_bit(unsigne
 	return (*addr >> (nr & 7)) & 1;
 }
 
+static __always_inline bool
+arch_test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	return 1UL & (smp_load_acquire(p) >> (nr & (BITS_PER_LONG-1)));
+}
+
 static inline bool arch_test_and_set_bit_lock(unsigned long nr,
 					      volatile unsigned long *ptr)
 {
Index: linux-stable/arch/sh/include/asm/bitops-op32.h
===================================================================
--- linux-stable.orig/arch/sh/include/asm/bitops-op32.h	2022-09-30 15:39:09.000000000 +0200
+++ linux-stable/arch/sh/include/asm/bitops-op32.h	2022-09-30 15:39:09.000000000 +0200
@@ -140,4 +140,11 @@ static inline int test_bit(int nr, const
 	return 1UL & (addr[BIT_WORD(nr)] >> (nr & (BITS_PER_LONG-1)));
 }
 
+static __always_inline bool
+test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	return 1UL & (smp_load_acquire(p) >> (nr & (BITS_PER_LONG-1)));
+}
+
 #endif /* __ASM_SH_BITOPS_OP32_H */

[PATCH] provide arch_test_bit_acquire for architectures that define test_bit

[Mikulas Patocka]

This is backport of the upstream patch d6ffe6067a54972564552ea45d320fb98db1ac5e
for the stable branch 4.19

Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>

---
 arch/alpha/include/asm/bitops.h   |    7 +++++++
 arch/hexagon/include/asm/bitops.h |   15 +++++++++++++++
 arch/ia64/include/asm/bitops.h    |    7 +++++++
 arch/m68k/include/asm/bitops.h    |    6 ++++++
 arch/s390/include/asm/bitops.h    |    7 +++++++
 arch/sh/include/asm/bitops-op32.h |    7 +++++++
 6 files changed, 49 insertions(+)

Index: linux-stable/arch/alpha/include/asm/bitops.h
===================================================================
--- linux-stable.orig/arch/alpha/include/asm/bitops.h	2022-09-30 15:48:24.000000000 +0200
+++ linux-stable/arch/alpha/include/asm/bitops.h	2022-09-30 15:48:24.000000000 +0200
@@ -289,6 +289,13 @@ test_bit(int nr, const volatile void * a
 	return (1UL & (((const int *) addr)[nr >> 5] >> (nr & 31))) != 0UL;
 }
 
+static __always_inline bool
+test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	return 1UL & (smp_load_acquire(p) >> (nr & (BITS_PER_LONG-1)));
+}
+
 /*
  * ffz = Find First Zero in word. Undefined if no zero exists,
  * so code should check against ~0UL first..
Index: linux-stable/arch/hexagon/include/asm/bitops.h
===================================================================
--- linux-stable.orig/arch/hexagon/include/asm/bitops.h	2022-09-30 15:48:24.000000000 +0200
+++ linux-stable/arch/hexagon/include/asm/bitops.h	2022-09-30 15:48:24.000000000 +0200
@@ -186,7 +186,22 @@ static inline int __test_bit(int nr, con
 	return retval;
 }
 
+static inline int __test_bit_acquire(int nr, const volatile unsigned long *addr)
+{
+	int retval;
+
+	asm volatile(
+	"{P0 = tstbit(%1,%2); if (P0.new) %0 = #1; if (!P0.new) %0 = #0;}\n"
+	: "=&r" (retval)
+	: "r" (addr[BIT_WORD(nr)]), "r" (nr % BITS_PER_LONG)
+	: "p0", "memory"
+	);
+
+	return retval;
+}
+
 #define test_bit(nr, addr) __test_bit(nr, addr)
+#define test_bit_acquire(nr, addr) __test_bit_acquire(nr, addr)
 
 /*
  * ffz - find first zero in word.
Index: linux-stable/arch/ia64/include/asm/bitops.h
===================================================================
--- linux-stable.orig/arch/ia64/include/asm/bitops.h	2022-09-30 15:48:24.000000000 +0200
+++ linux-stable/arch/ia64/include/asm/bitops.h	2022-09-30 15:48:24.000000000 +0200
@@ -337,6 +337,13 @@ test_bit (int nr, const volatile void *a
 	return 1 & (((const volatile __u32 *) addr)[nr >> 5] >> (nr & 31));
 }
 
+static __always_inline bool
+test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	return 1UL & (smp_load_acquire(p) >> (nr & (BITS_PER_LONG-1)));
+}
+
 /**
  * ffz - find the first zero bit in a long word
  * @x: The long word to find the bit in
Index: linux-stable/arch/m68k/include/asm/bitops.h
===================================================================
--- linux-stable.orig/arch/m68k/include/asm/bitops.h	2022-09-30 15:48:24.000000000 +0200
+++ linux-stable/arch/m68k/include/asm/bitops.h	2022-09-30 15:48:24.000000000 +0200
@@ -153,6 +153,12 @@ static inline int test_bit(int nr, const
 	return (vaddr[nr >> 5] & (1UL << (nr & 31))) != 0;
 }
 
+static __always_inline bool
+test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	return 1UL & (smp_load_acquire(p) >> (nr & (BITS_PER_LONG-1)));
+}
 
 static inline int bset_reg_test_and_set_bit(int nr,
 					    volatile unsigned long *vaddr)
Index: linux-stable/arch/s390/include/asm/bitops.h
===================================================================
--- linux-stable.orig/arch/s390/include/asm/bitops.h	2022-09-30 15:48:24.000000000 +0200
+++ linux-stable/arch/s390/include/asm/bitops.h	2022-09-30 15:49:53.000000000 +0200
@@ -215,6 +215,13 @@ static inline int test_bit(unsigned long
 	return (*addr >> (nr & 7)) & 1;
 }
 
+static __always_inline bool
+test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	return 1UL & (smp_load_acquire(p) >> (nr & (BITS_PER_LONG-1)));
+}
+
 static inline int test_and_set_bit_lock(unsigned long nr,
 					volatile unsigned long *ptr)
 {
Index: linux-stable/arch/sh/include/asm/bitops-op32.h
===================================================================
--- linux-stable.orig/arch/sh/include/asm/bitops-op32.h	2022-09-30 15:48:24.000000000 +0200
+++ linux-stable/arch/sh/include/asm/bitops-op32.h	2022-09-30 15:48:24.000000000 +0200
@@ -140,4 +140,11 @@ static inline int test_bit(int nr, const
 	return 1UL & (addr[BIT_WORD(nr)] >> (nr & (BITS_PER_LONG-1)));
 }
 
+static __always_inline bool
+test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	return 1UL & (smp_load_acquire(p) >> (nr & (BITS_PER_LONG-1)));
+}
+
 #endif /* __ASM_SH_BITOPS_OP32_H */

[PATCH] provide arch_test_bit_acquire for architectures that define test_bit

[Mikulas Patocka]

This is backport of the upstream patch d6ffe6067a54972564552ea45d320fb98db1ac5e
for the stable branch 4.14

Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>

---
 arch/alpha/include/asm/bitops.h   |    7 +++++++
 arch/hexagon/include/asm/bitops.h |   15 +++++++++++++++
 arch/ia64/include/asm/bitops.h    |    7 +++++++
 arch/m68k/include/asm/bitops.h    |    6 ++++++
 arch/s390/include/asm/bitops.h    |    7 +++++++
 arch/sh/include/asm/bitops-op32.h |    7 +++++++
 6 files changed, 49 insertions(+)

Index: linux-stable/arch/alpha/include/asm/bitops.h
===================================================================
--- linux-stable.orig/arch/alpha/include/asm/bitops.h	2022-09-30 15:48:24.000000000 +0200
+++ linux-stable/arch/alpha/include/asm/bitops.h	2022-09-30 15:48:24.000000000 +0200
@@ -289,6 +289,13 @@ test_bit(int nr, const volatile void * a
 	return (1UL & (((const int *) addr)[nr >> 5] >> (nr & 31))) != 0UL;
 }
 
+static __always_inline bool
+test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	return 1UL & (smp_load_acquire(p) >> (nr & (BITS_PER_LONG-1)));
+}
+
 /*
  * ffz = Find First Zero in word. Undefined if no zero exists,
  * so code should check against ~0UL first..
Index: linux-stable/arch/hexagon/include/asm/bitops.h
===================================================================
--- linux-stable.orig/arch/hexagon/include/asm/bitops.h	2022-09-30 15:48:24.000000000 +0200
+++ linux-stable/arch/hexagon/include/asm/bitops.h	2022-09-30 15:48:24.000000000 +0200
@@ -186,7 +186,22 @@ static inline int __test_bit(int nr, con
 	return retval;
 }
 
+static inline int __test_bit_acquire(int nr, const volatile unsigned long *addr)
+{
+	int retval;
+
+	asm volatile(
+	"{P0 = tstbit(%1,%2); if (P0.new) %0 = #1; if (!P0.new) %0 = #0;}\n"
+	: "=&r" (retval)
+	: "r" (addr[BIT_WORD(nr)]), "r" (nr % BITS_PER_LONG)
+	: "p0", "memory"
+	);
+
+	return retval;
+}
+
 #define test_bit(nr, addr) __test_bit(nr, addr)
+#define test_bit_acquire(nr, addr) __test_bit_acquire(nr, addr)
 
 /*
  * ffz - find first zero in word.
Index: linux-stable/arch/ia64/include/asm/bitops.h
===================================================================
--- linux-stable.orig/arch/ia64/include/asm/bitops.h	2022-09-30 15:48:24.000000000 +0200
+++ linux-stable/arch/ia64/include/asm/bitops.h	2022-09-30 15:48:24.000000000 +0200
@@ -337,6 +337,13 @@ test_bit (int nr, const volatile void *a
 	return 1 & (((const volatile __u32 *) addr)[nr >> 5] >> (nr & 31));
 }
 
+static __always_inline bool
+test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	return 1UL & (smp_load_acquire(p) >> (nr & (BITS_PER_LONG-1)));
+}
+
 /**
  * ffz - find the first zero bit in a long word
  * @x: The long word to find the bit in
Index: linux-stable/arch/m68k/include/asm/bitops.h
===================================================================
--- linux-stable.orig/arch/m68k/include/asm/bitops.h	2022-09-30 15:48:24.000000000 +0200
+++ linux-stable/arch/m68k/include/asm/bitops.h	2022-09-30 15:48:24.000000000 +0200
@@ -153,6 +153,12 @@ static inline int test_bit(int nr, const
 	return (vaddr[nr >> 5] & (1UL << (nr & 31))) != 0;
 }
 
+static __always_inline bool
+test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	return 1UL & (smp_load_acquire(p) >> (nr & (BITS_PER_LONG-1)));
+}
 
 static inline int bset_reg_test_and_set_bit(int nr,
 					    volatile unsigned long *vaddr)
Index: linux-stable/arch/s390/include/asm/bitops.h
===================================================================
--- linux-stable.orig/arch/s390/include/asm/bitops.h	2022-09-30 15:48:24.000000000 +0200
+++ linux-stable/arch/s390/include/asm/bitops.h	2022-09-30 15:49:53.000000000 +0200
@@ -215,6 +215,13 @@ static inline int test_bit(unsigned long
 	return (*addr >> (nr & 7)) & 1;
 }
 
+static __always_inline bool
+test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	return 1UL & (smp_load_acquire(p) >> (nr & (BITS_PER_LONG-1)));
+}
+
 static inline int test_and_set_bit_lock(unsigned long nr,
 					volatile unsigned long *ptr)
 {
Index: linux-stable/arch/sh/include/asm/bitops-op32.h
===================================================================
--- linux-stable.orig/arch/sh/include/asm/bitops-op32.h	2022-09-30 15:48:24.000000000 +0200
+++ linux-stable/arch/sh/include/asm/bitops-op32.h	2022-09-30 15:48:24.000000000 +0200
@@ -140,4 +140,11 @@ static inline int test_bit(int nr, const
 	return 1UL & (addr[BIT_WORD(nr)] >> (nr & (BITS_PER_LONG-1)));
 }
 
+static __always_inline bool
+test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	return 1UL & (smp_load_acquire(p) >> (nr & (BITS_PER_LONG-1)));
+}
+
 #endif /* __ASM_SH_BITOPS_OP32_H */

[PATCH] provide arch_test_bit_acquire for architectures that define test_bit

[Mikulas Patocka]

This is backport of the upstream patch d6ffe6067a54972564552ea45d320fb98db1ac5e
for the stable branch 4.9

Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>

---
 arch/alpha/include/asm/bitops.h   |    7 +++++++
 arch/hexagon/include/asm/bitops.h |   15 +++++++++++++++
 arch/ia64/include/asm/bitops.h    |    7 +++++++
 arch/m68k/include/asm/bitops.h    |    6 ++++++
 arch/s390/include/asm/bitops.h    |    7 +++++++
 arch/sh/include/asm/bitops-op32.h |    7 +++++++
 6 files changed, 49 insertions(+)

Index: linux-stable/arch/alpha/include/asm/bitops.h
===================================================================
--- linux-stable.orig/arch/alpha/include/asm/bitops.h	2022-09-30 16:03:22.000000000 +0200
+++ linux-stable/arch/alpha/include/asm/bitops.h	2022-09-30 16:03:22.000000000 +0200
@@ -288,6 +288,13 @@ test_bit(int nr, const volatile void * a
 	return (1UL & (((const int *) addr)[nr >> 5] >> (nr & 31))) != 0UL;
 }
 
+static __always_inline bool
+test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	return 1UL & (smp_load_acquire(p) >> (nr & (BITS_PER_LONG-1)));
+}
+
 /*
  * ffz = Find First Zero in word. Undefined if no zero exists,
  * so code should check against ~0UL first..
Index: linux-stable/arch/hexagon/include/asm/bitops.h
===================================================================
--- linux-stable.orig/arch/hexagon/include/asm/bitops.h	2022-09-30 16:03:22.000000000 +0200
+++ linux-stable/arch/hexagon/include/asm/bitops.h	2022-09-30 16:03:22.000000000 +0200
@@ -186,7 +186,22 @@ static inline int __test_bit(int nr, con
 	return retval;
 }
 
+static inline int __test_bit_acquire(int nr, const volatile unsigned long *addr)
+{
+	int retval;
+
+	asm volatile(
+	"{P0 = tstbit(%1,%2); if (P0.new) %0 = #1; if (!P0.new) %0 = #0;}\n"
+	: "=&r" (retval)
+	: "r" (addr[BIT_WORD(nr)]), "r" (nr % BITS_PER_LONG)
+	: "p0", "memory"
+	);
+
+	return retval;
+}
+
 #define test_bit(nr, addr) __test_bit(nr, addr)
+#define test_bit_acquire(nr, addr) __test_bit_acquire(nr, addr)
 
 /*
  * ffz - find first zero in word.
Index: linux-stable/arch/ia64/include/asm/bitops.h
===================================================================
--- linux-stable.orig/arch/ia64/include/asm/bitops.h	2022-09-30 16:03:22.000000000 +0200
+++ linux-stable/arch/ia64/include/asm/bitops.h	2022-09-30 16:03:22.000000000 +0200
@@ -336,6 +336,13 @@ test_bit (int nr, const volatile void *a
 	return 1 & (((const volatile __u32 *) addr)[nr >> 5] >> (nr & 31));
 }
 
+static __always_inline bool
+test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	return 1UL & (smp_load_acquire(p) >> (nr & (BITS_PER_LONG-1)));
+}
+
 /**
  * ffz - find the first zero bit in a long word
  * @x: The long word to find the bit in
Index: linux-stable/arch/m68k/include/asm/bitops.h
===================================================================
--- linux-stable.orig/arch/m68k/include/asm/bitops.h	2022-09-30 16:03:22.000000000 +0200
+++ linux-stable/arch/m68k/include/asm/bitops.h	2022-09-30 16:03:22.000000000 +0200
@@ -153,6 +153,12 @@ static inline int test_bit(int nr, const
 	return (vaddr[nr >> 5] & (1UL << (nr & 31))) != 0;
 }
 
+static __always_inline bool
+test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	return 1UL & (smp_load_acquire(p) >> (nr & (BITS_PER_LONG-1)));
+}
 
 static inline int bset_reg_test_and_set_bit(int nr,
 					    volatile unsigned long *vaddr)
Index: linux-stable/arch/s390/include/asm/bitops.h
===================================================================
--- linux-stable.orig/arch/s390/include/asm/bitops.h	2022-09-30 16:03:22.000000000 +0200
+++ linux-stable/arch/s390/include/asm/bitops.h	2022-09-30 16:03:22.000000000 +0200
@@ -270,6 +270,13 @@ static inline int test_bit(unsigned long
 	return (*addr >> (nr & 7)) & 1;
 }
 
+static __always_inline bool
+test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	return 1UL & (smp_load_acquire(p) >> (nr & (BITS_PER_LONG-1)));
+}
+
 static inline int test_and_set_bit_lock(unsigned long nr,
 					volatile unsigned long *ptr)
 {
Index: linux-stable/arch/sh/include/asm/bitops-op32.h
===================================================================
--- linux-stable.orig/arch/sh/include/asm/bitops-op32.h	2022-09-30 16:03:22.000000000 +0200
+++ linux-stable/arch/sh/include/asm/bitops-op32.h	2022-09-30 16:03:22.000000000 +0200
@@ -139,4 +139,11 @@ static inline int test_bit(int nr, const
 	return 1UL & (addr[BIT_WORD(nr)] >> (nr & (BITS_PER_LONG-1)));
 }
 
+static __always_inline bool
+test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	return 1UL & (smp_load_acquire(p) >> (nr & (BITS_PER_LONG-1)));
+}
+
 #endif /* __ASM_SH_BITOPS_OP32_H */

Re: backport of patches 8238b4579866b7c1bb99883cfe102a43db5506ff and d6ffe6067a54972564552ea45d320fb98db1ac5e

[Greg KH]

On Fri, Sep 30, 2022 at 11:32:30AM -0400, Mikulas Patocka wrote:
> Hi
> 
> Here I'm submitting backport of patches 
> 8238b4579866b7c1bb99883cfe102a43db5506ff and 
> d6ffe6067a54972564552ea45d320fb98db1ac5e to the stable branches.

Thanks, but you provide no information as to why these are needed.

What needs them?  They are just adding new functions to the tree from
what I can tell.

thanks,

greg k-h

Re: [PATCH] provide arch_test_bit_acquire for architectures that define test_bit

[Greg KH]

On Fri, Sep 30, 2022 at 11:36:52AM -0400, Mikulas Patocka wrote:
> This is backport of the upstream patch d6ffe6067a54972564552ea45d320fb98db1ac5e
> for the stable branch 4.9
> 
> Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>

What happened to the original changelog information and the original
signed-off-by information?

Please keep that when backporting changes.  Fix that up for all of these
when you resend.

thanks,

greg k-h

Re: [PATCH] wait_on_bit: add an acquire memory barrier

[Greg KH]

On Fri, Sep 30, 2022 at 11:34:55AM -0400, Mikulas Patocka wrote:
> This is backport of the upstream patch 8238b4579866b7c1bb99883cfe102a43db5506ff
> for the stable branch 4.9
> 
> Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>

Again, you lost all of the original changelog and authorship/review
information here :(

And what order are these to be applied in?  Please make a patch series
for each stable/LTS tree they are to be backported to.  Would you want
to try to unwind this if you were the reciever of these emails?

thanks,

greg k-h

Re: backport of patches 8238b4579866b7c1bb99883cfe102a43db5506ff and d6ffe6067a54972564552ea45d320fb98db1ac5e

[Mikulas Patocka]

On Sat, 1 Oct 2022, Greg KH wrote:

> On Fri, Sep 30, 2022 at 11:32:30AM -0400, Mikulas Patocka wrote:
> > Hi
> > 
> > Here I'm submitting backport of patches 
> > 8238b4579866b7c1bb99883cfe102a43db5506ff and 
> > d6ffe6067a54972564552ea45d320fb98db1ac5e to the stable branches.
> 
> Thanks, but you provide no information as to why these are needed.
> 
> What needs them?  They are just adding new functions to the tree from
> what I can tell.
> 
> thanks,
> 
> greg k-h

There's a race condition in wait_on_bit. wait_on_bit tests a bit using the 
"test_bit" function, however this function doesn't do any memory barrier, 
so the memory accesses that follow wait_on_bit may be reordered before it 
and return invalid data.

Linus didn't want to add a memory barrier to wait_on_bit, he instead 
wanted to introduce a new function test_bit_acquire that performs the 
"acquire" memory barrier and use it in wait_on_bit.

The patch d6ffe6067a54972564552ea45d320fb98db1ac5e fixes an oversight in 
the patch 8238b4579866b7c1bb99883cfe102a43db5506ff where the function 
test_bit_acquire was not defined for some architectures and this caused 
compile failure.

The backport of the patch 8238b4579866b7c1bb99883cfe102a43db5506ff should 
be applied first and the backport of the patch 
d6ffe6067a54972564552ea45d320fb98db1ac5e afterwards.

Mikulas

[PATCH] wait_on_bit: add an acquire memory barrier

[Mikulas Patocka]

This is backport of the upstream patch 8238b4579866b7c1bb99883cfe102a43db5506ff
for the stable branches 5.10, 5.15, 5.19

wait_on_bit: add an acquire memory barrier

There are several places in the kernel where wait_on_bit is not followed
by a memory barrier (for example, in drivers/md/dm-bufio.c:new_read).

On architectures with weak memory ordering, it may happen that memory
accesses that follow wait_on_bit are reordered before wait_on_bit and
they may return invalid data.

Fix this class of bugs by introducing a new function "test_bit_acquire"
that works like test_bit, but has acquire memory ordering semantics.

Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Acked-by: Will Deacon <will@kernel.org>
Cc: stable@vger.kernel.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

---
 arch/x86/include/asm/bitops.h                        |   21 +++++++++++++++++++
 include/asm-generic/bitops/instrumented-non-atomic.h |   12 ++++++++++
 include/asm-generic/bitops/non-atomic.h              |   14 ++++++++++++
 include/linux/buffer_head.h                          |    2 -
 include/linux/wait_bit.h                             |    8 +++----
 kernel/sched/wait_bit.c                              |    2 -
 6 files changed, 53 insertions(+), 6 deletions(-)

Index: linux-stable/arch/x86/include/asm/bitops.h
===================================================================
--- linux-stable.orig/arch/x86/include/asm/bitops.h	2022-09-30 13:07:11.000000000 +0200
+++ linux-stable/arch/x86/include/asm/bitops.h	2022-09-30 13:07:11.000000000 +0200
@@ -207,6 +207,20 @@ static __always_inline bool constant_tes
 		(addr[nr >> _BITOPS_LONG_SHIFT])) != 0;
 }
 
+static __always_inline bool constant_test_bit_acquire(long nr, const volatile unsigned long *addr)
+{
+	bool oldbit;
+
+	asm volatile("testb %2,%1"
+		     CC_SET(nz)
+		     : CC_OUT(nz) (oldbit)
+		     : "m" (((unsigned char *)addr)[nr >> 3]),
+		       "i" (1 << (nr & 7))
+		     :"memory");
+
+	return oldbit;
+}
+
 static __always_inline bool variable_test_bit(long nr, volatile const unsigned long *addr)
 {
 	bool oldbit;
@@ -224,6 +238,13 @@ static __always_inline bool variable_tes
 	 ? constant_test_bit((nr), (addr))	\
 	 : variable_test_bit((nr), (addr)))
 
+static __always_inline bool
+arch_test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	return __builtin_constant_p(nr) ? constant_test_bit_acquire(nr, addr) :
+					  variable_test_bit(nr, addr);
+}
+
 /**
  * __ffs - find first set bit in word
  * @word: The word to search
Index: linux-stable/include/asm-generic/bitops/instrumented-non-atomic.h
===================================================================
--- linux-stable.orig/include/asm-generic/bitops/instrumented-non-atomic.h	2022-09-30 13:07:11.000000000 +0200
+++ linux-stable/include/asm-generic/bitops/instrumented-non-atomic.h	2022-09-30 13:07:11.000000000 +0200
@@ -135,4 +135,16 @@ static __always_inline bool test_bit(lon
 	return arch_test_bit(nr, addr);
 }
 
+/**
+ * _test_bit_acquire - Determine, with acquire semantics, whether a bit is set
+ * @nr: bit number to test
+ * @addr: Address to start counting from
+ */
+static __always_inline bool
+test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	instrument_atomic_read(addr + BIT_WORD(nr), sizeof(long));
+	return arch_test_bit_acquire(nr, addr);
+}
+
 #endif /* _ASM_GENERIC_BITOPS_INSTRUMENTED_NON_ATOMIC_H */
Index: linux-stable/include/asm-generic/bitops/non-atomic.h
===================================================================
--- linux-stable.orig/include/asm-generic/bitops/non-atomic.h	2022-09-30 13:07:11.000000000 +0200
+++ linux-stable/include/asm-generic/bitops/non-atomic.h	2022-09-30 13:07:11.000000000 +0200
@@ -3,6 +3,7 @@
 #define _ASM_GENERIC_BITOPS_NON_ATOMIC_H_
 
 #include <asm/types.h>
+#include <asm/barrier.h>
 
 /**
  * arch___set_bit - Set a bit in memory
@@ -119,4 +120,17 @@ arch_test_bit(unsigned int nr, const vol
 }
 #define test_bit arch_test_bit
 
+/**
+ * arch_test_bit_acquire - Determine, with acquire semantics, whether a bit is set
+ * @nr: bit number to test
+ * @addr: Address to start counting from
+ */
+static __always_inline bool
+arch_test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	return 1UL & (smp_load_acquire(p) >> (nr & (BITS_PER_LONG-1)));
+}
+#define test_bit_acquire arch_test_bit_acquire
+
 #endif /* _ASM_GENERIC_BITOPS_NON_ATOMIC_H_ */
Index: linux-stable/include/linux/buffer_head.h
===================================================================
--- linux-stable.orig/include/linux/buffer_head.h	2022-09-30 13:07:11.000000000 +0200
+++ linux-stable/include/linux/buffer_head.h	2022-09-30 13:07:11.000000000 +0200
@@ -166,7 +166,7 @@ static __always_inline int buffer_uptoda
 	 * make it consistent with folio_test_uptodate
 	 * pairs with smp_mb__before_atomic in set_buffer_uptodate
 	 */
-	return (smp_load_acquire(&bh->b_state) & (1UL << BH_Uptodate)) != 0;
+	return test_bit_acquire(BH_Uptodate, &bh->b_state);
 }
 
 #define bh_offset(bh)		((unsigned long)(bh)->b_data & ~PAGE_MASK)
Index: linux-stable/include/linux/wait_bit.h
===================================================================
--- linux-stable.orig/include/linux/wait_bit.h	2022-09-30 13:07:11.000000000 +0200
+++ linux-stable/include/linux/wait_bit.h	2022-09-30 13:07:11.000000000 +0200
@@ -71,7 +71,7 @@ static inline int
 wait_on_bit(unsigned long *word, int bit, unsigned mode)
 {
 	might_sleep();
-	if (!test_bit(bit, word))
+	if (!test_bit_acquire(bit, word))
 		return 0;
 	return out_of_line_wait_on_bit(word, bit,
 				       bit_wait,
@@ -96,7 +96,7 @@ static inline int
 wait_on_bit_io(unsigned long *word, int bit, unsigned mode)
 {
 	might_sleep();
-	if (!test_bit(bit, word))
+	if (!test_bit_acquire(bit, word))
 		return 0;
 	return out_of_line_wait_on_bit(word, bit,
 				       bit_wait_io,
@@ -123,7 +123,7 @@ wait_on_bit_timeout(unsigned long *word,
 		    unsigned long timeout)
 {
 	might_sleep();
-	if (!test_bit(bit, word))
+	if (!test_bit_acquire(bit, word))
 		return 0;
 	return out_of_line_wait_on_bit_timeout(word, bit,
 					       bit_wait_timeout,
@@ -151,7 +151,7 @@ wait_on_bit_action(unsigned long *word,
 		   unsigned mode)
 {
 	might_sleep();
-	if (!test_bit(bit, word))
+	if (!test_bit_acquire(bit, word))
 		return 0;
 	return out_of_line_wait_on_bit(word, bit, action, mode);
 }
Index: linux-stable/kernel/sched/wait_bit.c
===================================================================
--- linux-stable.orig/kernel/sched/wait_bit.c	2022-09-30 13:07:11.000000000 +0200
+++ linux-stable/kernel/sched/wait_bit.c	2022-09-30 13:07:11.000000000 +0200
@@ -47,7 +47,7 @@ __wait_on_bit(struct wait_queue_head *wq
 		prepare_to_wait(wq_head, &wbq_entry->wq_entry, mode);
 		if (test_bit(wbq_entry->key.bit_nr, wbq_entry->key.flags))
 			ret = (*action)(&wbq_entry->key, mode);
-	} while (test_bit(wbq_entry->key.bit_nr, wbq_entry->key.flags) && !ret);
+	} while (test_bit_acquire(wbq_entry->key.bit_nr, wbq_entry->key.flags) && !ret);
 
 	finish_wait(wq_head, &wbq_entry->wq_entry);
 

[PATCH] wait_on_bit: add an acquire memory barrier

[Mikulas Patocka]

This is backport of the upstream patch 8238b4579866b7c1bb99883cfe102a43db5506ff
for the stable branch 5.4

wait_on_bit: add an acquire memory barrier

There are several places in the kernel where wait_on_bit is not followed
by a memory barrier (for example, in drivers/md/dm-bufio.c:new_read).

On architectures with weak memory ordering, it may happen that memory
accesses that follow wait_on_bit are reordered before wait_on_bit and
they may return invalid data.

Fix this class of bugs by introducing a new function "test_bit_acquire"
that works like test_bit, but has acquire memory ordering semantics.

Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Acked-by: Will Deacon <will@kernel.org>
Cc: stable@vger.kernel.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

---
 arch/x86/include/asm/bitops.h             |   21 +++++++++++++++++++++
 include/asm-generic/bitops-instrumented.h |    6 ++++++
 include/asm-generic/bitops/non-atomic.h   |   14 ++++++++++++++
 include/linux/buffer_head.h               |    2 +-
 include/linux/wait_bit.h                  |    8 ++++----
 kernel/sched/wait_bit.c                   |    2 +-
 6 files changed, 47 insertions(+), 6 deletions(-)

Index: linux-stable/arch/x86/include/asm/bitops.h
===================================================================
--- linux-stable.orig/arch/x86/include/asm/bitops.h	2022-09-30 15:38:29.000000000 +0200
+++ linux-stable/arch/x86/include/asm/bitops.h	2022-09-30 15:38:29.000000000 +0200
@@ -207,6 +207,20 @@ static __always_inline bool constant_tes
 		(addr[nr >> _BITOPS_LONG_SHIFT])) != 0;
 }
 
+static __always_inline bool constant_test_bit_acquire(long nr, const volatile unsigned long *addr)
+{
+	bool oldbit;
+
+	asm volatile("testb %2,%1"
+		     CC_SET(nz)
+		     : CC_OUT(nz) (oldbit)
+		     : "m" (((unsigned char *)addr)[nr >> 3]),
+		       "i" (1 << (nr & 7))
+		     :"memory");
+
+	return oldbit;
+}
+
 static __always_inline bool variable_test_bit(long nr, volatile const unsigned long *addr)
 {
 	bool oldbit;
@@ -224,6 +238,13 @@ static __always_inline bool variable_tes
 	 ? constant_test_bit((nr), (addr))	\
 	 : variable_test_bit((nr), (addr)))
 
+static __always_inline bool
+arch_test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	return __builtin_constant_p(nr) ? constant_test_bit_acquire(nr, addr) :
+					  variable_test_bit(nr, addr);
+}
+
 /**
  * __ffs - find first set bit in word
  * @word: The word to search
Index: linux-stable/include/asm-generic/bitops/non-atomic.h
===================================================================
--- linux-stable.orig/include/asm-generic/bitops/non-atomic.h	2022-09-30 15:38:29.000000000 +0200
+++ linux-stable/include/asm-generic/bitops/non-atomic.h	2022-09-30 15:38:29.000000000 +0200
@@ -3,6 +3,7 @@
 #define _ASM_GENERIC_BITOPS_NON_ATOMIC_H_
 
 #include <asm/types.h>
+#include <asm/barrier.h>
 
 /**
  * __set_bit - Set a bit in memory
@@ -106,4 +107,17 @@ static inline int test_bit(int nr, const
 	return 1UL & (addr[BIT_WORD(nr)] >> (nr & (BITS_PER_LONG-1)));
 }
 
+/**
+ * arch_test_bit_acquire - Determine, with acquire semantics, whether a bit is set
+ * @nr: bit number to test
+ * @addr: Address to start counting from
+ */
+static __always_inline bool
+arch_test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	return 1UL & (smp_load_acquire(p) >> (nr & (BITS_PER_LONG-1)));
+}
+#define test_bit_acquire arch_test_bit_acquire
+
 #endif /* _ASM_GENERIC_BITOPS_NON_ATOMIC_H_ */
Index: linux-stable/include/linux/buffer_head.h
===================================================================
--- linux-stable.orig/include/linux/buffer_head.h	2022-09-30 15:38:29.000000000 +0200
+++ linux-stable/include/linux/buffer_head.h	2022-09-30 15:38:29.000000000 +0200
@@ -166,7 +166,7 @@ static __always_inline int buffer_uptoda
 	 * make it consistent with folio_test_uptodate
 	 * pairs with smp_mb__before_atomic in set_buffer_uptodate
 	 */
-	return (smp_load_acquire(&bh->b_state) & (1UL << BH_Uptodate)) != 0;
+	return test_bit_acquire(BH_Uptodate, &bh->b_state);
 }
 
 #define bh_offset(bh)		((unsigned long)(bh)->b_data & ~PAGE_MASK)
Index: linux-stable/include/linux/wait_bit.h
===================================================================
--- linux-stable.orig/include/linux/wait_bit.h	2022-09-30 15:38:29.000000000 +0200
+++ linux-stable/include/linux/wait_bit.h	2022-09-30 15:38:29.000000000 +0200
@@ -71,7 +71,7 @@ static inline int
 wait_on_bit(unsigned long *word, int bit, unsigned mode)
 {
 	might_sleep();
-	if (!test_bit(bit, word))
+	if (!test_bit_acquire(bit, word))
 		return 0;
 	return out_of_line_wait_on_bit(word, bit,
 				       bit_wait,
@@ -96,7 +96,7 @@ static inline int
 wait_on_bit_io(unsigned long *word, int bit, unsigned mode)
 {
 	might_sleep();
-	if (!test_bit(bit, word))
+	if (!test_bit_acquire(bit, word))
 		return 0;
 	return out_of_line_wait_on_bit(word, bit,
 				       bit_wait_io,
@@ -123,7 +123,7 @@ wait_on_bit_timeout(unsigned long *word,
 		    unsigned long timeout)
 {
 	might_sleep();
-	if (!test_bit(bit, word))
+	if (!test_bit_acquire(bit, word))
 		return 0;
 	return out_of_line_wait_on_bit_timeout(word, bit,
 					       bit_wait_timeout,
@@ -151,7 +151,7 @@ wait_on_bit_action(unsigned long *word,
 		   unsigned mode)
 {
 	might_sleep();
-	if (!test_bit(bit, word))
+	if (!test_bit_acquire(bit, word))
 		return 0;
 	return out_of_line_wait_on_bit(word, bit, action, mode);
 }
Index: linux-stable/kernel/sched/wait_bit.c
===================================================================
--- linux-stable.orig/kernel/sched/wait_bit.c	2022-09-30 15:38:29.000000000 +0200
+++ linux-stable/kernel/sched/wait_bit.c	2022-09-30 15:38:29.000000000 +0200
@@ -47,7 +47,7 @@ __wait_on_bit(struct wait_queue_head *wq
 		prepare_to_wait(wq_head, &wbq_entry->wq_entry, mode);
 		if (test_bit(wbq_entry->key.bit_nr, wbq_entry->key.flags))
 			ret = (*action)(&wbq_entry->key, mode);
-	} while (test_bit(wbq_entry->key.bit_nr, wbq_entry->key.flags) && !ret);
+	} while (test_bit_acquire(wbq_entry->key.bit_nr, wbq_entry->key.flags) && !ret);
 
 	finish_wait(wq_head, &wbq_entry->wq_entry);
 
Index: linux-stable/include/asm-generic/bitops-instrumented.h
===================================================================
--- linux-stable.orig/include/asm-generic/bitops-instrumented.h	2022-09-30 15:37:42.000000000 +0200
+++ linux-stable/include/asm-generic/bitops-instrumented.h	2022-09-30 15:40:55.000000000 +0200
@@ -238,6 +238,12 @@ static inline bool test_bit(long nr, con
 	return arch_test_bit(nr, addr);
 }
 
+static inline bool test_bit_acquire(long nr, const volatile unsigned long *addr)
+{
+	kasan_check_read(addr + BIT_WORD(nr), sizeof(long));
+	return arch_test_bit_acquire(nr, addr);
+}
+
 #if defined(arch_clear_bit_unlock_is_negative_byte)
 /**
  * clear_bit_unlock_is_negative_byte - Clear a bit in memory and test if bottom

[PATCH] wait_on_bit: add an acquire memory barrier

[Mikulas Patocka]

This is backport of the upstream patch 8238b4579866b7c1bb99883cfe102a43db5506ff
for the stable branch 4.19

wait_on_bit: add an acquire memory barrier

There are several places in the kernel where wait_on_bit is not followed
by a memory barrier (for example, in drivers/md/dm-bufio.c:new_read).

On architectures with weak memory ordering, it may happen that memory
accesses that follow wait_on_bit are reordered before wait_on_bit and
they may return invalid data.

Fix this class of bugs by introducing a new function "test_bit_acquire"
that works like test_bit, but has acquire memory ordering semantics.

Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Acked-by: Will Deacon <will@kernel.org>
Cc: stable@vger.kernel.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

---
 arch/x86/include/asm/bitops.h           |   21 +++++++++++++++++++++
 include/asm-generic/bitops/non-atomic.h |   14 ++++++++++++++
 include/linux/buffer_head.h             |    2 +-
 include/linux/wait_bit.h                |    8 ++++----
 kernel/sched/wait_bit.c                 |    2 +-
 5 files changed, 41 insertions(+), 6 deletions(-)

Index: linux-stable/arch/x86/include/asm/bitops.h
===================================================================
--- linux-stable.orig/arch/x86/include/asm/bitops.h	2022-09-30 15:44:48.000000000 +0200
+++ linux-stable/arch/x86/include/asm/bitops.h	2022-09-30 15:46:38.000000000 +0200
@@ -317,6 +317,20 @@ static __always_inline bool constant_tes
 		(addr[nr >> _BITOPS_LONG_SHIFT])) != 0;
 }
 
+static __always_inline bool constant_test_bit_acquire(long nr, const volatile unsigned long *addr)
+{
+	bool oldbit;
+
+	asm volatile("testb %2,%1"
+		     CC_SET(nz)
+		     : CC_OUT(nz) (oldbit)
+		     : "m" (((unsigned char *)addr)[nr >> 3]),
+		       "i" (1 << (nr & 7))
+		     :"memory");
+
+	return oldbit;
+}
+
 static __always_inline bool variable_test_bit(long nr, volatile const unsigned long *addr)
 {
 	bool oldbit;
@@ -343,6 +357,13 @@ static bool test_bit(int nr, const volat
 	 ? constant_test_bit((nr), (addr))	\
 	 : variable_test_bit((nr), (addr)))
 
+static __always_inline bool
+test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	return __builtin_constant_p(nr) ? constant_test_bit_acquire(nr, addr) :
+					  variable_test_bit(nr, addr);
+}
+
 /**
  * __ffs - find first set bit in word
  * @word: The word to search
Index: linux-stable/include/asm-generic/bitops/non-atomic.h
===================================================================
--- linux-stable.orig/include/asm-generic/bitops/non-atomic.h	2022-09-30 15:44:48.000000000 +0200
+++ linux-stable/include/asm-generic/bitops/non-atomic.h	2022-09-30 15:44:48.000000000 +0200
@@ -3,6 +3,7 @@
 #define _ASM_GENERIC_BITOPS_NON_ATOMIC_H_
 
 #include <asm/types.h>
+#include <asm/barrier.h>
 
 /**
  * __set_bit - Set a bit in memory
@@ -106,4 +107,17 @@ static inline int test_bit(int nr, const
 	return 1UL & (addr[BIT_WORD(nr)] >> (nr & (BITS_PER_LONG-1)));
 }
 
+/**
+ * arch_test_bit_acquire - Determine, with acquire semantics, whether a bit is set
+ * @nr: bit number to test
+ * @addr: Address to start counting from
+ */
+static __always_inline bool
+arch_test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	return 1UL & (smp_load_acquire(p) >> (nr & (BITS_PER_LONG-1)));
+}
+#define test_bit_acquire arch_test_bit_acquire
+
 #endif /* _ASM_GENERIC_BITOPS_NON_ATOMIC_H_ */
Index: linux-stable/include/linux/buffer_head.h
===================================================================
--- linux-stable.orig/include/linux/buffer_head.h	2022-09-30 15:44:48.000000000 +0200
+++ linux-stable/include/linux/buffer_head.h	2022-09-30 15:44:48.000000000 +0200
@@ -166,7 +166,7 @@ static __always_inline int buffer_uptoda
 	 * make it consistent with folio_test_uptodate
 	 * pairs with smp_mb__before_atomic in set_buffer_uptodate
 	 */
-	return (smp_load_acquire(&bh->b_state) & (1UL << BH_Uptodate)) != 0;
+	return test_bit_acquire(BH_Uptodate, &bh->b_state);
 }
 
 #define bh_offset(bh)		((unsigned long)(bh)->b_data & ~PAGE_MASK)
Index: linux-stable/include/linux/wait_bit.h
===================================================================
--- linux-stable.orig/include/linux/wait_bit.h	2022-09-30 15:44:48.000000000 +0200
+++ linux-stable/include/linux/wait_bit.h	2022-09-30 15:44:48.000000000 +0200
@@ -71,7 +71,7 @@ static inline int
 wait_on_bit(unsigned long *word, int bit, unsigned mode)
 {
 	might_sleep();
-	if (!test_bit(bit, word))
+	if (!test_bit_acquire(bit, word))
 		return 0;
 	return out_of_line_wait_on_bit(word, bit,
 				       bit_wait,
@@ -96,7 +96,7 @@ static inline int
 wait_on_bit_io(unsigned long *word, int bit, unsigned mode)
 {
 	might_sleep();
-	if (!test_bit(bit, word))
+	if (!test_bit_acquire(bit, word))
 		return 0;
 	return out_of_line_wait_on_bit(word, bit,
 				       bit_wait_io,
@@ -123,7 +123,7 @@ wait_on_bit_timeout(unsigned long *word,
 		    unsigned long timeout)
 {
 	might_sleep();
-	if (!test_bit(bit, word))
+	if (!test_bit_acquire(bit, word))
 		return 0;
 	return out_of_line_wait_on_bit_timeout(word, bit,
 					       bit_wait_timeout,
@@ -151,7 +151,7 @@ wait_on_bit_action(unsigned long *word,
 		   unsigned mode)
 {
 	might_sleep();
-	if (!test_bit(bit, word))
+	if (!test_bit_acquire(bit, word))
 		return 0;
 	return out_of_line_wait_on_bit(word, bit, action, mode);
 }
Index: linux-stable/kernel/sched/wait_bit.c
===================================================================
--- linux-stable.orig/kernel/sched/wait_bit.c	2022-09-30 15:44:48.000000000 +0200
+++ linux-stable/kernel/sched/wait_bit.c	2022-09-30 15:44:48.000000000 +0200
@@ -46,7 +46,7 @@ __wait_on_bit(struct wait_queue_head *wq
 		prepare_to_wait(wq_head, &wbq_entry->wq_entry, mode);
 		if (test_bit(wbq_entry->key.bit_nr, wbq_entry->key.flags))
 			ret = (*action)(&wbq_entry->key, mode);
-	} while (test_bit(wbq_entry->key.bit_nr, wbq_entry->key.flags) && !ret);
+	} while (test_bit_acquire(wbq_entry->key.bit_nr, wbq_entry->key.flags) && !ret);
 
 	finish_wait(wq_head, &wbq_entry->wq_entry);
 

[PATCH] wait_on_bit: add an acquire memory barrier

[Mikulas Patocka]

This is backport of the upstream patch 8238b4579866b7c1bb99883cfe102a43db5506ff
for the stable branch 4.14

wait_on_bit: add an acquire memory barrier

There are several places in the kernel where wait_on_bit is not followed
by a memory barrier (for example, in drivers/md/dm-bufio.c:new_read).

On architectures with weak memory ordering, it may happen that memory
accesses that follow wait_on_bit are reordered before wait_on_bit and
they may return invalid data.

Fix this class of bugs by introducing a new function "test_bit_acquire"
that works like test_bit, but has acquire memory ordering semantics.

Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Acked-by: Will Deacon <will@kernel.org>
Cc: stable@vger.kernel.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

---
 arch/x86/include/asm/bitops.h           |   21 +++++++++++++++++++++
 include/asm-generic/bitops/non-atomic.h |   14 ++++++++++++++
 include/linux/buffer_head.h             |    2 +-
 include/linux/wait_bit.h                |    8 ++++----
 kernel/sched/wait_bit.c                 |    2 +-
 5 files changed, 41 insertions(+), 6 deletions(-)

Index: linux-stable/arch/x86/include/asm/bitops.h
===================================================================
--- linux-stable.orig/arch/x86/include/asm/bitops.h	2022-09-30 15:55:01.000000000 +0200
+++ linux-stable/arch/x86/include/asm/bitops.h	2022-09-30 15:55:01.000000000 +0200
@@ -328,6 +328,20 @@ static __always_inline bool constant_tes
 		(addr[nr >> _BITOPS_LONG_SHIFT])) != 0;
 }
 
+static __always_inline bool constant_test_bit_acquire(long nr, const volatile unsigned long *addr)
+{
+	bool oldbit;
+
+	asm volatile("testb %2,%1"
+		     CC_SET(nz)
+		     : CC_OUT(nz) (oldbit)
+		     : "m" (((unsigned char *)addr)[nr >> 3]),
+		       "i" (1 << (nr & 7))
+		     :"memory");
+
+	return oldbit;
+}
+
 static __always_inline bool variable_test_bit(long nr, volatile const unsigned long *addr)
 {
 	bool oldbit;
@@ -354,6 +368,13 @@ static bool test_bit(int nr, const volat
 	 ? constant_test_bit((nr), (addr))	\
 	 : variable_test_bit((nr), (addr)))
 
+static __always_inline bool
+test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	return __builtin_constant_p(nr) ? constant_test_bit_acquire(nr, addr) :
+					  variable_test_bit(nr, addr);
+}
+
 /**
  * __ffs - find first set bit in word
  * @word: The word to search
Index: linux-stable/include/asm-generic/bitops/non-atomic.h
===================================================================
--- linux-stable.orig/include/asm-generic/bitops/non-atomic.h	2022-09-30 15:55:01.000000000 +0200
+++ linux-stable/include/asm-generic/bitops/non-atomic.h	2022-09-30 15:55:01.000000000 +0200
@@ -3,6 +3,7 @@
 #define _ASM_GENERIC_BITOPS_NON_ATOMIC_H_
 
 #include <asm/types.h>
+#include <asm/barrier.h>
 
 /**
  * __set_bit - Set a bit in memory
@@ -106,4 +107,17 @@ static inline int test_bit(int nr, const
 	return 1UL & (addr[BIT_WORD(nr)] >> (nr & (BITS_PER_LONG-1)));
 }
 
+/**
+ * arch_test_bit_acquire - Determine, with acquire semantics, whether a bit is set
+ * @nr: bit number to test
+ * @addr: Address to start counting from
+ */
+static __always_inline bool
+arch_test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	return 1UL & (smp_load_acquire(p) >> (nr & (BITS_PER_LONG-1)));
+}
+#define test_bit_acquire arch_test_bit_acquire
+
 #endif /* _ASM_GENERIC_BITOPS_NON_ATOMIC_H_ */
Index: linux-stable/include/linux/buffer_head.h
===================================================================
--- linux-stable.orig/include/linux/buffer_head.h	2022-09-30 15:55:01.000000000 +0200
+++ linux-stable/include/linux/buffer_head.h	2022-09-30 15:55:01.000000000 +0200
@@ -163,7 +163,7 @@ static __always_inline int buffer_uptoda
 	 * make it consistent with folio_test_uptodate
 	 * pairs with smp_mb__before_atomic in set_buffer_uptodate
 	 */
-	return (smp_load_acquire(&bh->b_state) & (1UL << BH_Uptodate)) != 0;
+	return test_bit_acquire(BH_Uptodate, &bh->b_state);
 }
 
 #define bh_offset(bh)		((unsigned long)(bh)->b_data & ~PAGE_MASK)
Index: linux-stable/include/linux/wait_bit.h
===================================================================
--- linux-stable.orig/include/linux/wait_bit.h	2022-09-30 15:55:01.000000000 +0200
+++ linux-stable/include/linux/wait_bit.h	2022-09-30 15:55:01.000000000 +0200
@@ -76,7 +76,7 @@ static inline int
 wait_on_bit(unsigned long *word, int bit, unsigned mode)
 {
 	might_sleep();
-	if (!test_bit(bit, word))
+	if (!test_bit_acquire(bit, word))
 		return 0;
 	return out_of_line_wait_on_bit(word, bit,
 				       bit_wait,
@@ -101,7 +101,7 @@ static inline int
 wait_on_bit_io(unsigned long *word, int bit, unsigned mode)
 {
 	might_sleep();
-	if (!test_bit(bit, word))
+	if (!test_bit_acquire(bit, word))
 		return 0;
 	return out_of_line_wait_on_bit(word, bit,
 				       bit_wait_io,
@@ -128,7 +128,7 @@ wait_on_bit_timeout(unsigned long *word,
 		    unsigned long timeout)
 {
 	might_sleep();
-	if (!test_bit(bit, word))
+	if (!test_bit_acquire(bit, word))
 		return 0;
 	return out_of_line_wait_on_bit_timeout(word, bit,
 					       bit_wait_timeout,
@@ -156,7 +156,7 @@ wait_on_bit_action(unsigned long *word,
 		   unsigned mode)
 {
 	might_sleep();
-	if (!test_bit(bit, word))
+	if (!test_bit_acquire(bit, word))
 		return 0;
 	return out_of_line_wait_on_bit(word, bit, action, mode);
 }
Index: linux-stable/kernel/sched/wait_bit.c
===================================================================
--- linux-stable.orig/kernel/sched/wait_bit.c	2022-09-30 15:55:01.000000000 +0200
+++ linux-stable/kernel/sched/wait_bit.c	2022-09-30 15:55:55.000000000 +0200
@@ -49,7 +49,7 @@ __wait_on_bit(struct wait_queue_head *wq
 		prepare_to_wait(wq_head, &wbq_entry->wq_entry, mode);
 		if (test_bit(wbq_entry->key.bit_nr, wbq_entry->key.flags))
 			ret = (*action)(&wbq_entry->key, mode);
-	} while (test_bit(wbq_entry->key.bit_nr, wbq_entry->key.flags) && !ret);
+	} while (test_bit_acquire(wbq_entry->key.bit_nr, wbq_entry->key.flags) && !ret);
 	finish_wait(wq_head, &wbq_entry->wq_entry);
 	return ret;
 }

[PATCH] wait_on_bit: add an acquire memory barrier

[Mikulas Patocka]

This is backport of the upstream patch 8238b4579866b7c1bb99883cfe102a43db5506ff
for the stable branch 4.9

wait_on_bit: add an acquire memory barrier

There are several places in the kernel where wait_on_bit is not followed
by a memory barrier (for example, in drivers/md/dm-bufio.c:new_read).

On architectures with weak memory ordering, it may happen that memory
accesses that follow wait_on_bit are reordered before wait_on_bit and
they may return invalid data.

Fix this class of bugs by introducing a new function "test_bit_acquire"
that works like test_bit, but has acquire memory ordering semantics.

Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Acked-by: Will Deacon <will@kernel.org>
Cc: stable@vger.kernel.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

---
 arch/x86/include/asm/bitops.h           |   21 +++++++++++++++++++++
 include/asm-generic/bitops/non-atomic.h |   14 ++++++++++++++
 include/linux/buffer_head.h             |    2 +-
 include/linux/wait.h                    |    8 ++++----
 kernel/sched/wait.c                     |    2 +-
 5 files changed, 41 insertions(+), 6 deletions(-)

Index: linux-stable/arch/x86/include/asm/bitops.h
===================================================================
--- linux-stable.orig/arch/x86/include/asm/bitops.h	2022-09-30 16:01:38.000000000 +0200
+++ linux-stable/arch/x86/include/asm/bitops.h	2022-09-30 16:01:38.000000000 +0200
@@ -314,6 +314,20 @@ static __always_inline bool constant_tes
 		(addr[nr >> _BITOPS_LONG_SHIFT])) != 0;
 }
 
+static __always_inline bool constant_test_bit_acquire(long nr, const volatile unsigned long *addr)
+{
+	bool oldbit;
+
+	asm volatile("testb %2,%1"
+		     CC_SET(nz)
+		     : CC_OUT(nz) (oldbit)
+		     : "m" (((unsigned char *)addr)[nr >> 3]),
+		       "i" (1 << (nr & 7))
+		     :"memory");
+
+	return oldbit;
+}
+
 static __always_inline bool variable_test_bit(long nr, volatile const unsigned long *addr)
 {
 	bool oldbit;
@@ -340,6 +354,13 @@ static bool test_bit(int nr, const volat
 	 ? constant_test_bit((nr), (addr))	\
 	 : variable_test_bit((nr), (addr)))
 
+static __always_inline bool
+test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	return __builtin_constant_p(nr) ? constant_test_bit_acquire(nr, addr) :
+					  variable_test_bit(nr, addr);
+}
+
 /**
  * __ffs - find first set bit in word
  * @word: The word to search
Index: linux-stable/include/asm-generic/bitops/non-atomic.h
===================================================================
--- linux-stable.orig/include/asm-generic/bitops/non-atomic.h	2022-09-30 16:01:38.000000000 +0200
+++ linux-stable/include/asm-generic/bitops/non-atomic.h	2022-09-30 16:01:38.000000000 +0200
@@ -2,6 +2,7 @@
 #define _ASM_GENERIC_BITOPS_NON_ATOMIC_H_
 
 #include <asm/types.h>
+#include <asm/barrier.h>
 
 /**
  * __set_bit - Set a bit in memory
@@ -105,4 +106,17 @@ static inline int test_bit(int nr, const
 	return 1UL & (addr[BIT_WORD(nr)] >> (nr & (BITS_PER_LONG-1)));
 }
 
+/**
+ * arch_test_bit_acquire - Determine, with acquire semantics, whether a bit is set
+ * @nr: bit number to test
+ * @addr: Address to start counting from
+ */
+static __always_inline bool
+arch_test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	return 1UL & (smp_load_acquire(p) >> (nr & (BITS_PER_LONG-1)));
+}
+#define test_bit_acquire arch_test_bit_acquire
+
 #endif /* _ASM_GENERIC_BITOPS_NON_ATOMIC_H_ */
Index: linux-stable/include/linux/buffer_head.h
===================================================================
--- linux-stable.orig/include/linux/buffer_head.h	2022-09-30 16:01:38.000000000 +0200
+++ linux-stable/include/linux/buffer_head.h	2022-09-30 16:01:38.000000000 +0200
@@ -162,7 +162,7 @@ static __always_inline int buffer_uptoda
 	 * make it consistent with folio_test_uptodate
 	 * pairs with smp_mb__before_atomic in set_buffer_uptodate
 	 */
-	return (smp_load_acquire(&bh->b_state) & (1UL << BH_Uptodate)) != 0;
+	return test_bit_acquire(BH_Uptodate, &bh->b_state);
 }
 
 #define bh_offset(bh)		((unsigned long)(bh)->b_data & ~PAGE_MASK)
Index: linux-stable/include/linux/wait.h
===================================================================
--- linux-stable.orig/include/linux/wait.h	2022-09-30 16:01:38.000000000 +0200
+++ linux-stable/include/linux/wait.h	2022-09-30 16:01:38.000000000 +0200
@@ -1066,7 +1066,7 @@ static inline int
 wait_on_bit(unsigned long *word, int bit, unsigned mode)
 {
 	might_sleep();
-	if (!test_bit(bit, word))
+	if (!test_bit_acquire(bit, word))
 		return 0;
 	return out_of_line_wait_on_bit(word, bit,
 				       bit_wait,
@@ -1091,7 +1091,7 @@ static inline int
 wait_on_bit_io(unsigned long *word, int bit, unsigned mode)
 {
 	might_sleep();
-	if (!test_bit(bit, word))
+	if (!test_bit_acquire(bit, word))
 		return 0;
 	return out_of_line_wait_on_bit(word, bit,
 				       bit_wait_io,
@@ -1118,7 +1118,7 @@ wait_on_bit_timeout(unsigned long *word,
 		    unsigned long timeout)
 {
 	might_sleep();
-	if (!test_bit(bit, word))
+	if (!test_bit_acquire(bit, word))
 		return 0;
 	return out_of_line_wait_on_bit_timeout(word, bit,
 					       bit_wait_timeout,
@@ -1146,7 +1146,7 @@ wait_on_bit_action(unsigned long *word,
 		   unsigned mode)
 {
 	might_sleep();
-	if (!test_bit(bit, word))
+	if (!test_bit_acquire(bit, word))
 		return 0;
 	return out_of_line_wait_on_bit(word, bit, action, mode);
 }
Index: linux-stable/kernel/sched/wait.c
===================================================================
--- linux-stable.orig/kernel/sched/wait.c	2022-09-30 16:01:38.000000000 +0200
+++ linux-stable/kernel/sched/wait.c	2022-09-30 16:01:58.000000000 +0200
@@ -389,7 +389,7 @@ __wait_on_bit(wait_queue_head_t *wq, str
 		prepare_to_wait(wq, &q->wait, mode);
 		if (test_bit(q->key.bit_nr, q->key.flags))
 			ret = (*action)(&q->key, mode);
-	} while (test_bit(q->key.bit_nr, q->key.flags) && !ret);
+	} while (test_bit_acquire(q->key.bit_nr, q->key.flags) && !ret);
 	finish_wait(wq, &q->wait);
 	return ret;
 }

[PATCH] provide arch_test_bit_acquire for architectures that define test_bit

[Mikulas Patocka]

This is backport of the upstream patch d6ffe6067a54972564552ea45d320fb98db1ac5e
for the stable branches 5.19, 5.15, 5.10

provide arch_test_bit_acquire for architectures that define test_bit

Some architectures define their own arch_test_bit and they also need
arch_test_bit_acquire, otherwise they won't compile.  We also clean up
the code by using the generic test_bit if that is equivalent to the
arch-specific version.

Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Cc: stable@vger.kernel.org
Fixes: 8238b4579866 ("wait_on_bit: add an acquire memory barrier")
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

---
 arch/alpha/include/asm/bitops.h   |    7 +++++++
 arch/hexagon/include/asm/bitops.h |   15 +++++++++++++++
 arch/ia64/include/asm/bitops.h    |    7 +++++++
 arch/m68k/include/asm/bitops.h    |    6 ++++++
 arch/s390/include/asm/bitops.h    |    7 +++++++
 arch/sh/include/asm/bitops-op32.h |    7 +++++++
 6 files changed, 49 insertions(+)

Index: linux-stable/arch/alpha/include/asm/bitops.h
===================================================================
--- linux-stable.orig/arch/alpha/include/asm/bitops.h	2022-09-30 13:07:14.000000000 +0200
+++ linux-stable/arch/alpha/include/asm/bitops.h	2022-09-30 13:07:14.000000000 +0200
@@ -289,6 +289,13 @@ test_bit(int nr, const volatile void * a
 	return (1UL & (((const int *) addr)[nr >> 5] >> (nr & 31))) != 0UL;
 }
 
+static __always_inline bool
+test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	return 1UL & (smp_load_acquire(p) >> (nr & (BITS_PER_LONG-1)));
+}
+
 /*
  * ffz = Find First Zero in word. Undefined if no zero exists,
  * so code should check against ~0UL first..
Index: linux-stable/arch/hexagon/include/asm/bitops.h
===================================================================
--- linux-stable.orig/arch/hexagon/include/asm/bitops.h	2022-09-30 13:07:14.000000000 +0200
+++ linux-stable/arch/hexagon/include/asm/bitops.h	2022-09-30 13:07:14.000000000 +0200
@@ -172,7 +172,22 @@ static inline int __test_bit(int nr, con
 	return retval;
 }
 
+static inline int __test_bit_acquire(int nr, const volatile unsigned long *addr)
+{
+	int retval;
+
+	asm volatile(
+	"{P0 = tstbit(%1,%2); if (P0.new) %0 = #1; if (!P0.new) %0 = #0;}\n"
+	: "=&r" (retval)
+	: "r" (addr[BIT_WORD(nr)]), "r" (nr % BITS_PER_LONG)
+	: "p0", "memory"
+	);
+
+	return retval;
+}
+
 #define test_bit(nr, addr) __test_bit(nr, addr)
+#define test_bit_acquire(nr, addr) __test_bit_acquire(nr, addr)
 
 /*
  * ffz - find first zero in word.
Index: linux-stable/arch/ia64/include/asm/bitops.h
===================================================================
--- linux-stable.orig/arch/ia64/include/asm/bitops.h	2022-09-30 13:07:14.000000000 +0200
+++ linux-stable/arch/ia64/include/asm/bitops.h	2022-09-30 13:07:14.000000000 +0200
@@ -337,6 +337,13 @@ test_bit (int nr, const volatile void *a
 	return 1 & (((const volatile __u32 *) addr)[nr >> 5] >> (nr & 31));
 }
 
+static __always_inline bool
+test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	return 1UL & (smp_load_acquire(p) >> (nr & (BITS_PER_LONG-1)));
+}
+
 /**
  * ffz - find the first zero bit in a long word
  * @x: The long word to find the bit in
Index: linux-stable/arch/m68k/include/asm/bitops.h
===================================================================
--- linux-stable.orig/arch/m68k/include/asm/bitops.h	2022-09-30 13:07:14.000000000 +0200
+++ linux-stable/arch/m68k/include/asm/bitops.h	2022-09-30 13:07:14.000000000 +0200
@@ -153,6 +153,12 @@ static inline int test_bit(int nr, const
 	return (vaddr[nr >> 5] & (1UL << (nr & 31))) != 0;
 }
 
+static __always_inline bool
+test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	return 1UL & (smp_load_acquire(p) >> (nr & (BITS_PER_LONG-1)));
+}
 
 static inline int bset_reg_test_and_set_bit(int nr,
 					    volatile unsigned long *vaddr)
Index: linux-stable/arch/s390/include/asm/bitops.h
===================================================================
--- linux-stable.orig/arch/s390/include/asm/bitops.h	2022-09-30 13:07:14.000000000 +0200
+++ linux-stable/arch/s390/include/asm/bitops.h	2022-09-30 13:07:14.000000000 +0200
@@ -184,6 +184,13 @@ static inline bool arch_test_bit(unsigne
 	return *addr & mask;
 }
 
+static __always_inline bool
+arch_test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	return 1UL & (smp_load_acquire(p) >> (nr & (BITS_PER_LONG-1)));
+}
+
 static inline bool arch_test_and_set_bit_lock(unsigned long nr,
 					      volatile unsigned long *ptr)
 {
Index: linux-stable/arch/sh/include/asm/bitops-op32.h
===================================================================
--- linux-stable.orig/arch/sh/include/asm/bitops-op32.h	2022-09-30 13:07:14.000000000 +0200
+++ linux-stable/arch/sh/include/asm/bitops-op32.h	2022-09-30 13:07:14.000000000 +0200
@@ -138,4 +138,11 @@ static inline int test_bit(int nr, const
 	return 1UL & (addr[BIT_WORD(nr)] >> (nr & (BITS_PER_LONG-1)));
 }
 
+static __always_inline bool
+test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	return 1UL & (smp_load_acquire(p) >> (nr & (BITS_PER_LONG-1)));
+}
+
 #endif /* __ASM_SH_BITOPS_OP32_H */

[PATCH] provide arch_test_bit_acquire for architectures that define test_bit

[Mikulas Patocka]

This is backport of the upstream patch d6ffe6067a54972564552ea45d320fb98db1ac5e
for the stable branch 5.4

provide arch_test_bit_acquire for architectures that define test_bit

Some architectures define their own arch_test_bit and they also need
arch_test_bit_acquire, otherwise they won't compile.  We also clean up
the code by using the generic test_bit if that is equivalent to the
arch-specific version.

Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Cc: stable@vger.kernel.org
Fixes: 8238b4579866 ("wait_on_bit: add an acquire memory barrier")
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

---
 arch/alpha/include/asm/bitops.h   |    7 +++++++
 arch/hexagon/include/asm/bitops.h |   15 +++++++++++++++
 arch/ia64/include/asm/bitops.h    |    7 +++++++
 arch/m68k/include/asm/bitops.h    |    6 ++++++
 arch/s390/include/asm/bitops.h    |    7 +++++++
 arch/sh/include/asm/bitops-op32.h |    7 +++++++
 6 files changed, 49 insertions(+)

Index: linux-stable/arch/alpha/include/asm/bitops.h
===================================================================
--- linux-stable.orig/arch/alpha/include/asm/bitops.h	2022-09-30 15:39:09.000000000 +0200
+++ linux-stable/arch/alpha/include/asm/bitops.h	2022-09-30 15:39:09.000000000 +0200
@@ -289,6 +289,13 @@ test_bit(int nr, const volatile void * a
 	return (1UL & (((const int *) addr)[nr >> 5] >> (nr & 31))) != 0UL;
 }
 
+static __always_inline bool
+test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	return 1UL & (smp_load_acquire(p) >> (nr & (BITS_PER_LONG-1)));
+}
+
 /*
  * ffz = Find First Zero in word. Undefined if no zero exists,
  * so code should check against ~0UL first..
Index: linux-stable/arch/hexagon/include/asm/bitops.h
===================================================================
--- linux-stable.orig/arch/hexagon/include/asm/bitops.h	2022-09-30 15:39:09.000000000 +0200
+++ linux-stable/arch/hexagon/include/asm/bitops.h	2022-09-30 15:39:09.000000000 +0200
@@ -172,7 +172,22 @@ static inline int __test_bit(int nr, con
 	return retval;
 }
 
+static inline int __test_bit_acquire(int nr, const volatile unsigned long *addr)
+{
+	int retval;
+
+	asm volatile(
+	"{P0 = tstbit(%1,%2); if (P0.new) %0 = #1; if (!P0.new) %0 = #0;}\n"
+	: "=&r" (retval)
+	: "r" (addr[BIT_WORD(nr)]), "r" (nr % BITS_PER_LONG)
+	: "p0", "memory"
+	);
+
+	return retval;
+}
+
 #define test_bit(nr, addr) __test_bit(nr, addr)
+#define test_bit_acquire(nr, addr) __test_bit_acquire(nr, addr)
 
 /*
  * ffz - find first zero in word.
Index: linux-stable/arch/ia64/include/asm/bitops.h
===================================================================
--- linux-stable.orig/arch/ia64/include/asm/bitops.h	2022-09-30 15:39:09.000000000 +0200
+++ linux-stable/arch/ia64/include/asm/bitops.h	2022-09-30 15:39:09.000000000 +0200
@@ -337,6 +337,13 @@ test_bit (int nr, const volatile void *a
 	return 1 & (((const volatile __u32 *) addr)[nr >> 5] >> (nr & 31));
 }
 
+static __always_inline bool
+test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	return 1UL & (smp_load_acquire(p) >> (nr & (BITS_PER_LONG-1)));
+}
+
 /**
  * ffz - find the first zero bit in a long word
  * @x: The long word to find the bit in
Index: linux-stable/arch/m68k/include/asm/bitops.h
===================================================================
--- linux-stable.orig/arch/m68k/include/asm/bitops.h	2022-09-30 15:39:09.000000000 +0200
+++ linux-stable/arch/m68k/include/asm/bitops.h	2022-09-30 15:39:09.000000000 +0200
@@ -153,6 +153,12 @@ static inline int test_bit(int nr, const
 	return (vaddr[nr >> 5] & (1UL << (nr & 31))) != 0;
 }
 
+static __always_inline bool
+test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	return 1UL & (smp_load_acquire(p) >> (nr & (BITS_PER_LONG-1)));
+}
 
 static inline int bset_reg_test_and_set_bit(int nr,
 					    volatile unsigned long *vaddr)
Index: linux-stable/arch/s390/include/asm/bitops.h
===================================================================
--- linux-stable.orig/arch/s390/include/asm/bitops.h	2022-09-30 15:39:09.000000000 +0200
+++ linux-stable/arch/s390/include/asm/bitops.h	2022-09-30 15:39:09.000000000 +0200
@@ -219,6 +219,13 @@ static inline bool arch_test_bit(unsigne
 	return (*addr >> (nr & 7)) & 1;
 }
 
+static __always_inline bool
+arch_test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	return 1UL & (smp_load_acquire(p) >> (nr & (BITS_PER_LONG-1)));
+}
+
 static inline bool arch_test_and_set_bit_lock(unsigned long nr,
 					      volatile unsigned long *ptr)
 {
Index: linux-stable/arch/sh/include/asm/bitops-op32.h
===================================================================
--- linux-stable.orig/arch/sh/include/asm/bitops-op32.h	2022-09-30 15:39:09.000000000 +0200
+++ linux-stable/arch/sh/include/asm/bitops-op32.h	2022-09-30 15:39:09.000000000 +0200
@@ -140,4 +140,11 @@ static inline int test_bit(int nr, const
 	return 1UL & (addr[BIT_WORD(nr)] >> (nr & (BITS_PER_LONG-1)));
 }
 
+static __always_inline bool
+test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	return 1UL & (smp_load_acquire(p) >> (nr & (BITS_PER_LONG-1)));
+}
+
 #endif /* __ASM_SH_BITOPS_OP32_H */

[PATCH] provide arch_test_bit_acquire for architectures that define test_bit

[Mikulas Patocka]

This is backport of the upstream patch d6ffe6067a54972564552ea45d320fb98db1ac5e
for the stable branch 4.19

provide arch_test_bit_acquire for architectures that define test_bit

Some architectures define their own arch_test_bit and they also need
arch_test_bit_acquire, otherwise they won't compile.  We also clean up
the code by using the generic test_bit if that is equivalent to the
arch-specific version.

Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Cc: stable@vger.kernel.org
Fixes: 8238b4579866 ("wait_on_bit: add an acquire memory barrier")
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

---
 arch/alpha/include/asm/bitops.h   |    7 +++++++
 arch/hexagon/include/asm/bitops.h |   15 +++++++++++++++
 arch/ia64/include/asm/bitops.h    |    7 +++++++
 arch/m68k/include/asm/bitops.h    |    6 ++++++
 arch/s390/include/asm/bitops.h    |    7 +++++++
 arch/sh/include/asm/bitops-op32.h |    7 +++++++
 6 files changed, 49 insertions(+)

Index: linux-stable/arch/alpha/include/asm/bitops.h
===================================================================
--- linux-stable.orig/arch/alpha/include/asm/bitops.h	2022-09-30 15:48:24.000000000 +0200
+++ linux-stable/arch/alpha/include/asm/bitops.h	2022-09-30 15:48:24.000000000 +0200
@@ -289,6 +289,13 @@ test_bit(int nr, const volatile void * a
 	return (1UL & (((const int *) addr)[nr >> 5] >> (nr & 31))) != 0UL;
 }
 
+static __always_inline bool
+test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	return 1UL & (smp_load_acquire(p) >> (nr & (BITS_PER_LONG-1)));
+}
+
 /*
  * ffz = Find First Zero in word. Undefined if no zero exists,
  * so code should check against ~0UL first..
Index: linux-stable/arch/hexagon/include/asm/bitops.h
===================================================================
--- linux-stable.orig/arch/hexagon/include/asm/bitops.h	2022-09-30 15:48:24.000000000 +0200
+++ linux-stable/arch/hexagon/include/asm/bitops.h	2022-09-30 15:48:24.000000000 +0200
@@ -186,7 +186,22 @@ static inline int __test_bit(int nr, con
 	return retval;
 }
 
+static inline int __test_bit_acquire(int nr, const volatile unsigned long *addr)
+{
+	int retval;
+
+	asm volatile(
+	"{P0 = tstbit(%1,%2); if (P0.new) %0 = #1; if (!P0.new) %0 = #0;}\n"
+	: "=&r" (retval)
+	: "r" (addr[BIT_WORD(nr)]), "r" (nr % BITS_PER_LONG)
+	: "p0", "memory"
+	);
+
+	return retval;
+}
+
 #define test_bit(nr, addr) __test_bit(nr, addr)
+#define test_bit_acquire(nr, addr) __test_bit_acquire(nr, addr)
 
 /*
  * ffz - find first zero in word.
Index: linux-stable/arch/ia64/include/asm/bitops.h
===================================================================
--- linux-stable.orig/arch/ia64/include/asm/bitops.h	2022-09-30 15:48:24.000000000 +0200
+++ linux-stable/arch/ia64/include/asm/bitops.h	2022-09-30 15:48:24.000000000 +0200
@@ -337,6 +337,13 @@ test_bit (int nr, const volatile void *a
 	return 1 & (((const volatile __u32 *) addr)[nr >> 5] >> (nr & 31));
 }
 
+static __always_inline bool
+test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	return 1UL & (smp_load_acquire(p) >> (nr & (BITS_PER_LONG-1)));
+}
+
 /**
  * ffz - find the first zero bit in a long word
  * @x: The long word to find the bit in
Index: linux-stable/arch/m68k/include/asm/bitops.h
===================================================================
--- linux-stable.orig/arch/m68k/include/asm/bitops.h	2022-09-30 15:48:24.000000000 +0200
+++ linux-stable/arch/m68k/include/asm/bitops.h	2022-09-30 15:48:24.000000000 +0200
@@ -153,6 +153,12 @@ static inline int test_bit(int nr, const
 	return (vaddr[nr >> 5] & (1UL << (nr & 31))) != 0;
 }
 
+static __always_inline bool
+test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	return 1UL & (smp_load_acquire(p) >> (nr & (BITS_PER_LONG-1)));
+}
 
 static inline int bset_reg_test_and_set_bit(int nr,
 					    volatile unsigned long *vaddr)
Index: linux-stable/arch/s390/include/asm/bitops.h
===================================================================
--- linux-stable.orig/arch/s390/include/asm/bitops.h	2022-09-30 15:48:24.000000000 +0200
+++ linux-stable/arch/s390/include/asm/bitops.h	2022-09-30 15:49:53.000000000 +0200
@@ -215,6 +215,13 @@ static inline int test_bit(unsigned long
 	return (*addr >> (nr & 7)) & 1;
 }
 
+static __always_inline bool
+test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	return 1UL & (smp_load_acquire(p) >> (nr & (BITS_PER_LONG-1)));
+}
+
 static inline int test_and_set_bit_lock(unsigned long nr,
 					volatile unsigned long *ptr)
 {
Index: linux-stable/arch/sh/include/asm/bitops-op32.h
===================================================================
--- linux-stable.orig/arch/sh/include/asm/bitops-op32.h	2022-09-30 15:48:24.000000000 +0200
+++ linux-stable/arch/sh/include/asm/bitops-op32.h	2022-09-30 15:48:24.000000000 +0200
@@ -140,4 +140,11 @@ static inline int test_bit(int nr, const
 	return 1UL & (addr[BIT_WORD(nr)] >> (nr & (BITS_PER_LONG-1)));
 }
 
+static __always_inline bool
+test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	return 1UL & (smp_load_acquire(p) >> (nr & (BITS_PER_LONG-1)));
+}
+
 #endif /* __ASM_SH_BITOPS_OP32_H */

[PATCH] provide arch_test_bit_acquire for architectures that define test_bit

[Mikulas Patocka]

This is backport of the upstream patch d6ffe6067a54972564552ea45d320fb98db1ac5e
for the stable branch 4.14

provide arch_test_bit_acquire for architectures that define test_bit

Some architectures define their own arch_test_bit and they also need
arch_test_bit_acquire, otherwise they won't compile.  We also clean up
the code by using the generic test_bit if that is equivalent to the
arch-specific version.

Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Cc: stable@vger.kernel.org
Fixes: 8238b4579866 ("wait_on_bit: add an acquire memory barrier")
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

---
 arch/alpha/include/asm/bitops.h   |    7 +++++++
 arch/hexagon/include/asm/bitops.h |   15 +++++++++++++++
 arch/ia64/include/asm/bitops.h    |    7 +++++++
 arch/m68k/include/asm/bitops.h    |    6 ++++++
 arch/s390/include/asm/bitops.h    |    7 +++++++
 arch/sh/include/asm/bitops-op32.h |    7 +++++++
 6 files changed, 49 insertions(+)

Index: linux-stable/arch/alpha/include/asm/bitops.h
===================================================================
--- linux-stable.orig/arch/alpha/include/asm/bitops.h	2022-09-30 15:48:24.000000000 +0200
+++ linux-stable/arch/alpha/include/asm/bitops.h	2022-09-30 15:48:24.000000000 +0200
@@ -289,6 +289,13 @@ test_bit(int nr, const volatile void * a
 	return (1UL & (((const int *) addr)[nr >> 5] >> (nr & 31))) != 0UL;
 }
 
+static __always_inline bool
+test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	return 1UL & (smp_load_acquire(p) >> (nr & (BITS_PER_LONG-1)));
+}
+
 /*
  * ffz = Find First Zero in word. Undefined if no zero exists,
  * so code should check against ~0UL first..
Index: linux-stable/arch/hexagon/include/asm/bitops.h
===================================================================
--- linux-stable.orig/arch/hexagon/include/asm/bitops.h	2022-09-30 15:48:24.000000000 +0200
+++ linux-stable/arch/hexagon/include/asm/bitops.h	2022-09-30 15:48:24.000000000 +0200
@@ -186,7 +186,22 @@ static inline int __test_bit(int nr, con
 	return retval;
 }
 
+static inline int __test_bit_acquire(int nr, const volatile unsigned long *addr)
+{
+	int retval;
+
+	asm volatile(
+	"{P0 = tstbit(%1,%2); if (P0.new) %0 = #1; if (!P0.new) %0 = #0;}\n"
+	: "=&r" (retval)
+	: "r" (addr[BIT_WORD(nr)]), "r" (nr % BITS_PER_LONG)
+	: "p0", "memory"
+	);
+
+	return retval;
+}
+
 #define test_bit(nr, addr) __test_bit(nr, addr)
+#define test_bit_acquire(nr, addr) __test_bit_acquire(nr, addr)
 
 /*
  * ffz - find first zero in word.
Index: linux-stable/arch/ia64/include/asm/bitops.h
===================================================================
--- linux-stable.orig/arch/ia64/include/asm/bitops.h	2022-09-30 15:48:24.000000000 +0200
+++ linux-stable/arch/ia64/include/asm/bitops.h	2022-09-30 15:48:24.000000000 +0200
@@ -337,6 +337,13 @@ test_bit (int nr, const volatile void *a
 	return 1 & (((const volatile __u32 *) addr)[nr >> 5] >> (nr & 31));
 }
 
+static __always_inline bool
+test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	return 1UL & (smp_load_acquire(p) >> (nr & (BITS_PER_LONG-1)));
+}
+
 /**
  * ffz - find the first zero bit in a long word
  * @x: The long word to find the bit in
Index: linux-stable/arch/m68k/include/asm/bitops.h
===================================================================
--- linux-stable.orig/arch/m68k/include/asm/bitops.h	2022-09-30 15:48:24.000000000 +0200
+++ linux-stable/arch/m68k/include/asm/bitops.h	2022-09-30 15:48:24.000000000 +0200
@@ -153,6 +153,12 @@ static inline int test_bit(int nr, const
 	return (vaddr[nr >> 5] & (1UL << (nr & 31))) != 0;
 }
 
+static __always_inline bool
+test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	return 1UL & (smp_load_acquire(p) >> (nr & (BITS_PER_LONG-1)));
+}
 
 static inline int bset_reg_test_and_set_bit(int nr,
 					    volatile unsigned long *vaddr)
Index: linux-stable/arch/s390/include/asm/bitops.h
===================================================================
--- linux-stable.orig/arch/s390/include/asm/bitops.h	2022-09-30 15:48:24.000000000 +0200
+++ linux-stable/arch/s390/include/asm/bitops.h	2022-09-30 15:49:53.000000000 +0200
@@ -215,6 +215,13 @@ static inline int test_bit(unsigned long
 	return (*addr >> (nr & 7)) & 1;
 }
 
+static __always_inline bool
+test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	return 1UL & (smp_load_acquire(p) >> (nr & (BITS_PER_LONG-1)));
+}
+
 static inline int test_and_set_bit_lock(unsigned long nr,
 					volatile unsigned long *ptr)
 {
Index: linux-stable/arch/sh/include/asm/bitops-op32.h
===================================================================
--- linux-stable.orig/arch/sh/include/asm/bitops-op32.h	2022-09-30 15:48:24.000000000 +0200
+++ linux-stable/arch/sh/include/asm/bitops-op32.h	2022-09-30 15:48:24.000000000 +0200
@@ -140,4 +140,11 @@ static inline int test_bit(int nr, const
 	return 1UL & (addr[BIT_WORD(nr)] >> (nr & (BITS_PER_LONG-1)));
 }
 
+static __always_inline bool
+test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	return 1UL & (smp_load_acquire(p) >> (nr & (BITS_PER_LONG-1)));
+}
+
 #endif /* __ASM_SH_BITOPS_OP32_H */

[PATCH] provide arch_test_bit_acquire for architectures that define test_bit

[Mikulas Patocka]

This is backport of the upstream patch d6ffe6067a54972564552ea45d320fb98db1ac5e
for the stable branch 4.9

provide arch_test_bit_acquire for architectures that define test_bit

Some architectures define their own arch_test_bit and they also need
arch_test_bit_acquire, otherwise they won't compile.  We also clean up
the code by using the generic test_bit if that is equivalent to the
arch-specific version.

Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Cc: stable@vger.kernel.org
Fixes: 8238b4579866 ("wait_on_bit: add an acquire memory barrier")
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

---
 arch/alpha/include/asm/bitops.h   |    7 +++++++
 arch/hexagon/include/asm/bitops.h |   15 +++++++++++++++
 arch/ia64/include/asm/bitops.h    |    7 +++++++
 arch/m68k/include/asm/bitops.h    |    6 ++++++
 arch/s390/include/asm/bitops.h    |    7 +++++++
 arch/sh/include/asm/bitops-op32.h |    7 +++++++
 6 files changed, 49 insertions(+)

Index: linux-stable/arch/alpha/include/asm/bitops.h
===================================================================
--- linux-stable.orig/arch/alpha/include/asm/bitops.h	2022-09-30 16:03:22.000000000 +0200
+++ linux-stable/arch/alpha/include/asm/bitops.h	2022-09-30 16:03:22.000000000 +0200
@@ -288,6 +288,13 @@ test_bit(int nr, const volatile void * a
 	return (1UL & (((const int *) addr)[nr >> 5] >> (nr & 31))) != 0UL;
 }
 
+static __always_inline bool
+test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	return 1UL & (smp_load_acquire(p) >> (nr & (BITS_PER_LONG-1)));
+}
+
 /*
  * ffz = Find First Zero in word. Undefined if no zero exists,
  * so code should check against ~0UL first..
Index: linux-stable/arch/hexagon/include/asm/bitops.h
===================================================================
--- linux-stable.orig/arch/hexagon/include/asm/bitops.h	2022-09-30 16:03:22.000000000 +0200
+++ linux-stable/arch/hexagon/include/asm/bitops.h	2022-09-30 16:03:22.000000000 +0200
@@ -186,7 +186,22 @@ static inline int __test_bit(int nr, con
 	return retval;
 }
 
+static inline int __test_bit_acquire(int nr, const volatile unsigned long *addr)
+{
+	int retval;
+
+	asm volatile(
+	"{P0 = tstbit(%1,%2); if (P0.new) %0 = #1; if (!P0.new) %0 = #0;}\n"
+	: "=&r" (retval)
+	: "r" (addr[BIT_WORD(nr)]), "r" (nr % BITS_PER_LONG)
+	: "p0", "memory"
+	);
+
+	return retval;
+}
+
 #define test_bit(nr, addr) __test_bit(nr, addr)
+#define test_bit_acquire(nr, addr) __test_bit_acquire(nr, addr)
 
 /*
  * ffz - find first zero in word.
Index: linux-stable/arch/ia64/include/asm/bitops.h
===================================================================
--- linux-stable.orig/arch/ia64/include/asm/bitops.h	2022-09-30 16:03:22.000000000 +0200
+++ linux-stable/arch/ia64/include/asm/bitops.h	2022-09-30 16:03:22.000000000 +0200
@@ -336,6 +336,13 @@ test_bit (int nr, const volatile void *a
 	return 1 & (((const volatile __u32 *) addr)[nr >> 5] >> (nr & 31));
 }
 
+static __always_inline bool
+test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	return 1UL & (smp_load_acquire(p) >> (nr & (BITS_PER_LONG-1)));
+}
+
 /**
  * ffz - find the first zero bit in a long word
  * @x: The long word to find the bit in
Index: linux-stable/arch/m68k/include/asm/bitops.h
===================================================================
--- linux-stable.orig/arch/m68k/include/asm/bitops.h	2022-09-30 16:03:22.000000000 +0200
+++ linux-stable/arch/m68k/include/asm/bitops.h	2022-09-30 16:03:22.000000000 +0200
@@ -153,6 +153,12 @@ static inline int test_bit(int nr, const
 	return (vaddr[nr >> 5] & (1UL << (nr & 31))) != 0;
 }
 
+static __always_inline bool
+test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	return 1UL & (smp_load_acquire(p) >> (nr & (BITS_PER_LONG-1)));
+}
 
 static inline int bset_reg_test_and_set_bit(int nr,
 					    volatile unsigned long *vaddr)
Index: linux-stable/arch/s390/include/asm/bitops.h
===================================================================
--- linux-stable.orig/arch/s390/include/asm/bitops.h	2022-09-30 16:03:22.000000000 +0200
+++ linux-stable/arch/s390/include/asm/bitops.h	2022-09-30 16:03:22.000000000 +0200
@@ -270,6 +270,13 @@ static inline int test_bit(unsigned long
 	return (*addr >> (nr & 7)) & 1;
 }
 
+static __always_inline bool
+test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	return 1UL & (smp_load_acquire(p) >> (nr & (BITS_PER_LONG-1)));
+}
+
 static inline int test_and_set_bit_lock(unsigned long nr,
 					volatile unsigned long *ptr)
 {
Index: linux-stable/arch/sh/include/asm/bitops-op32.h
===================================================================
--- linux-stable.orig/arch/sh/include/asm/bitops-op32.h	2022-09-30 16:03:22.000000000 +0200
+++ linux-stable/arch/sh/include/asm/bitops-op32.h	2022-09-30 16:03:22.000000000 +0200
@@ -139,4 +139,11 @@ static inline int test_bit(int nr, const
 	return 1UL & (addr[BIT_WORD(nr)] >> (nr & (BITS_PER_LONG-1)));
 }
 
+static __always_inline bool
+test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	return 1UL & (smp_load_acquire(p) >> (nr & (BITS_PER_LONG-1)));
+}
+
 #endif /* __ASM_SH_BITOPS_OP32_H */

Re: backport of patches 8238b4579866b7c1bb99883cfe102a43db5506ff and d6ffe6067a54972564552ea45d320fb98db1ac5e

[Greg KH]

On Mon, Oct 03, 2022 at 08:28:06AM -0400, Mikulas Patocka wrote:
> 
> 
> On Sat, 1 Oct 2022, Greg KH wrote:
> 
> > On Fri, Sep 30, 2022 at 11:32:30AM -0400, Mikulas Patocka wrote:
> > > Hi
> > > 
> > > Here I'm submitting backport of patches 
> > > 8238b4579866b7c1bb99883cfe102a43db5506ff and 
> > > d6ffe6067a54972564552ea45d320fb98db1ac5e to the stable branches.
> > 
> > Thanks, but you provide no information as to why these are needed.
> > 
> > What needs them?  They are just adding new functions to the tree from
> > what I can tell.
> > 
> > thanks,
> > 
> > greg k-h
> 
> There's a race condition in wait_on_bit. wait_on_bit tests a bit using the 
> "test_bit" function, however this function doesn't do any memory barrier, 
> so the memory accesses that follow wait_on_bit may be reordered before it 
> and return invalid data.
> 
> Linus didn't want to add a memory barrier to wait_on_bit, he instead 
> wanted to introduce a new function test_bit_acquire that performs the 
> "acquire" memory barrier and use it in wait_on_bit.
> 
> The patch d6ffe6067a54972564552ea45d320fb98db1ac5e fixes an oversight in 
> the patch 8238b4579866b7c1bb99883cfe102a43db5506ff where the function 
> test_bit_acquire was not defined for some architectures and this caused 
> compile failure.
> 
> The backport of the patch 8238b4579866b7c1bb99883cfe102a43db5506ff should 
> be applied first and the backport of the patch 
> d6ffe6067a54972564552ea45d320fb98db1ac5e afterwards.

All now queued up, thanks.

greg k-h

Re: backport of patches 8238b4579866b7c1bb99883cfe102a43db5506ff and d6ffe6067a54972564552ea45d320fb98db1ac5e

[Greg KH]

On Wed, Oct 05, 2022 at 06:48:54PM +0200, Greg KH wrote:
> On Mon, Oct 03, 2022 at 08:28:06AM -0400, Mikulas Patocka wrote:
> > 
> > 
> > On Sat, 1 Oct 2022, Greg KH wrote:
> > 
> > > On Fri, Sep 30, 2022 at 11:32:30AM -0400, Mikulas Patocka wrote:
> > > > Hi
> > > > 
> > > > Here I'm submitting backport of patches 
> > > > 8238b4579866b7c1bb99883cfe102a43db5506ff and 
> > > > d6ffe6067a54972564552ea45d320fb98db1ac5e to the stable branches.
> > > 
> > > Thanks, but you provide no information as to why these are needed.
> > > 
> > > What needs them?  They are just adding new functions to the tree from
> > > what I can tell.
> > > 
> > > thanks,
> > > 
> > > greg k-h
> > 
> > There's a race condition in wait_on_bit. wait_on_bit tests a bit using the 
> > "test_bit" function, however this function doesn't do any memory barrier, 
> > so the memory accesses that follow wait_on_bit may be reordered before it 
> > and return invalid data.
> > 
> > Linus didn't want to add a memory barrier to wait_on_bit, he instead 
> > wanted to introduce a new function test_bit_acquire that performs the 
> > "acquire" memory barrier and use it in wait_on_bit.
> > 
> > The patch d6ffe6067a54972564552ea45d320fb98db1ac5e fixes an oversight in 
> > the patch 8238b4579866b7c1bb99883cfe102a43db5506ff where the function 
> > test_bit_acquire was not defined for some architectures and this caused 
> > compile failure.
> > 
> > The backport of the patch 8238b4579866b7c1bb99883cfe102a43db5506ff should 
> > be applied first and the backport of the patch 
> > d6ffe6067a54972564552ea45d320fb98db1ac5e afterwards.
> 
> All now queued up, thanks.

Nope, these cause loads of breakages.  See
https://lore.kernel.org/r/09eca44e-4d91-a060-d48c-d0aa41ac5045@roeck-us.net
for one such example, and I know kbuild sent you other build problems.
I'll drop all of these from the stable trees now.  Please feel free to
resend them when you have the build issues worked out.

thanks,

greg k-h

Re: backport of patches 8238b4579866b7c1bb99883cfe102a43db5506ff and d6ffe6067a54972564552ea45d320fb98db1ac5e

[Mikulas Patocka]

On Mon, 10 Oct 2022, Greg KH wrote:

> Nope, these cause loads of breakages.  See
> https://lore.kernel.org/r/09eca44e-4d91-a060-d48c-d0aa41ac5045@roeck-us.net
> for one such example, and I know kbuild sent you other build problems.
> I'll drop all of these from the stable trees now.  Please feel free to
> resend them when you have the build issues worked out.
> 
> thanks,
> 
> greg k-h

I don't have cross compilers for all the architectures that Linux 
supports. Is there some way how to have the patch compile-tested before I 
send it to you?

Or - would you accept this patch instead of the upstream patch? It fixes 
the same bug as the upstream patch, but it's noticeably smaller and it 
could be applied to the stable kernels 4.19 to 5.19.

Mikulas



From: Mikulas Patocka <mpatocka@redhat.com>

This fixes a bug that is fixed by the upstream patch 
8238b4579866b7c1bb99883cfe102a43db5506ff.

This patch differs from the upstream patch because backporting the 
upstream patch causes many build failures on various architectures.


Original commit message:

There are several places in the kernel where wait_on_bit is not followed
by a memory barrier (for example, in drivers/md/dm-bufio.c:new_read).

On architectures with weak memory ordering, it may happen that memory
accesses that follow wait_on_bit are reordered before wait_on_bit and
they may return invalid data.

Fix this class of bugs by introducing a new function "test_bit_acquire"
that works like test_bit, but has acquire memory ordering semantics.

Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Acked-by: Will Deacon <will@kernel.org>
Cc: stable@vger.kernel.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>


---
 include/linux/wait_bit.h |   16 ++++++++++++----
 kernel/sched/wait_bit.c  |    2 ++
 2 files changed, 14 insertions(+), 4 deletions(-)

Index: linux-stable/include/linux/wait_bit.h
===================================================================
--- linux-stable.orig/include/linux/wait_bit.h	2022-10-11 11:23:12.000000000 +0200
+++ linux-stable/include/linux/wait_bit.h	2022-10-11 11:24:33.000000000 +0200
@@ -71,8 +71,10 @@ static inline int
 wait_on_bit(unsigned long *word, int bit, unsigned mode)
 {
 	might_sleep();
-	if (!test_bit(bit, word))
+	if (!test_bit(bit, word)) {
+		smp_rmb();
 		return 0;
+	}
 	return out_of_line_wait_on_bit(word, bit,
 				       bit_wait,
 				       mode);
@@ -96,8 +98,10 @@ static inline int
 wait_on_bit_io(unsigned long *word, int bit, unsigned mode)
 {
 	might_sleep();
-	if (!test_bit(bit, word))
+	if (!test_bit(bit, word)) {
+		smp_rmb();
 		return 0;
+	}
 	return out_of_line_wait_on_bit(word, bit,
 				       bit_wait_io,
 				       mode);
@@ -123,8 +127,10 @@ wait_on_bit_timeout(unsigned long *word,
 		    unsigned long timeout)
 {
 	might_sleep();
-	if (!test_bit(bit, word))
+	if (!test_bit(bit, word)) {
+		smp_rmb();
 		return 0;
+	}
 	return out_of_line_wait_on_bit_timeout(word, bit,
 					       bit_wait_timeout,
 					       mode, timeout);
@@ -151,8 +157,10 @@ wait_on_bit_action(unsigned long *word,
 		   unsigned mode)
 {
 	might_sleep();
-	if (!test_bit(bit, word))
+	if (!test_bit(bit, word)) {
+		smp_rmb();
 		return 0;
+	}
 	return out_of_line_wait_on_bit(word, bit, action, mode);
 }
 
Index: linux-stable/kernel/sched/wait_bit.c
===================================================================
--- linux-stable.orig/kernel/sched/wait_bit.c	2022-10-11 11:23:12.000000000 +0200
+++ linux-stable/kernel/sched/wait_bit.c	2022-10-11 11:25:22.000000000 +0200
@@ -51,6 +51,8 @@ __wait_on_bit(struct wait_queue_head *wq
 
 	finish_wait(wq_head, &wbq_entry->wq_entry);
 
+	smp_rmb();
+
 	return ret;
 }
 EXPORT_SYMBOL(__wait_on_bit);

Re: backport of patches 8238b4579866b7c1bb99883cfe102a43db5506ff and d6ffe6067a54972564552ea45d320fb98db1ac5e

[Greg KH]

On Tue, Oct 11, 2022 at 05:48:26AM -0400, Mikulas Patocka wrote:
> 
> 
> On Mon, 10 Oct 2022, Greg KH wrote:
> 
> > Nope, these cause loads of breakages.  See
> > https://lore.kernel.org/r/09eca44e-4d91-a060-d48c-d0aa41ac5045@roeck-us.net
> > for one such example, and I know kbuild sent you other build problems.
> > I'll drop all of these from the stable trees now.  Please feel free to
> > resend them when you have the build issues worked out.
> > 
> > thanks,
> > 
> > greg k-h
> 
> I don't have cross compilers for all the architectures that Linux 
> supports. Is there some way how to have the patch compile-tested before I 
> send it to you?

You can download those compilers from kernel.org, they are all available
there.

> Or - would you accept this patch instead of the upstream patch? It fixes 
> the same bug as the upstream patch, but it's noticeably smaller and it 
> could be applied to the stable kernels 4.19 to 5.19.

We should stick with what is in Linus's tree so as to not cause new
bugs, and to make future backports easier.

thanks,

greg k-h

Re: backport of patches 8238b4579866b7c1bb99883cfe102a43db5506ff and d6ffe6067a54972564552ea45d320fb98db1ac5e

[Mikulas Patocka]

On Tue, 11 Oct 2022, Greg KH wrote:

> On Tue, Oct 11, 2022 at 05:48:26AM -0400, Mikulas Patocka wrote:
> > 
> > 
> > On Mon, 10 Oct 2022, Greg KH wrote:
> > 
> > > Nope, these cause loads of breakages.  See
> > > https://lore.kernel.org/r/09eca44e-4d91-a060-d48c-d0aa41ac5045@roeck-us.net
> > > for one such example, and I know kbuild sent you other build problems.
> > > I'll drop all of these from the stable trees now.  Please feel free to
> > > resend them when you have the build issues worked out.
> > > 
> > > thanks,
> > > 
> > > greg k-h
> > 
> > I don't have cross compilers for all the architectures that Linux 
> > supports. Is there some way how to have the patch compile-tested before I 
> > send it to you?
> 
> You can download those compilers from kernel.org, they are all available
> there.

OK. I downloaded cross compilers from 
https://mirrors.edge.kernel.org/pub/tools/crosstool/ and compile-tested 
the patches with all possible architectures.

Here I'm sending new versions.

Mikulas

[PATCH] wait_on_bit: add an acquire memory barrier

[Mikulas Patocka]

This is backport of the upstream patch 8238b4579866b7c1bb99883cfe102a43db5506ff
for the stable branch 5.19

wait_on_bit: add an acquire memory barrier

There are several places in the kernel where wait_on_bit is not followed
by a memory barrier (for example, in drivers/md/dm-bufio.c:new_read).

On architectures with weak memory ordering, it may happen that memory
accesses that follow wait_on_bit are reordered before wait_on_bit and
they may return invalid data.

Fix this class of bugs by introducing a new function "test_bit_acquire"
that works like test_bit, but has acquire memory ordering semantics.

Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Acked-by: Will Deacon <will@kernel.org>
Cc: stable@vger.kernel.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

---
 arch/alpha/include/asm/bitops.h                      |    7 ++++++
 arch/hexagon/include/asm/bitops.h                    |   15 +++++++++++++
 arch/ia64/include/asm/bitops.h                       |    7 ++++++
 arch/m68k/include/asm/bitops.h                       |    6 +++++
 arch/s390/include/asm/bitops.h                       |    7 ++++++
 arch/sh/include/asm/bitops-op32.h                    |    7 ++++++
 arch/x86/include/asm/bitops.h                        |   21 +++++++++++++++++++
 include/asm-generic/bitops/instrumented-non-atomic.h |   12 ++++++++++
 include/asm-generic/bitops/non-atomic.h              |   14 ++++++++++++
 include/linux/buffer_head.h                          |    2 -
 include/linux/wait_bit.h                             |    8 +++----
 kernel/sched/wait_bit.c                              |    2 -
 12 files changed, 102 insertions(+), 6 deletions(-)

Index: linux-stable/arch/x86/include/asm/bitops.h
===================================================================
--- linux-stable.orig/arch/x86/include/asm/bitops.h	2022-10-17 19:02:15.000000000 +0200
+++ linux-stable/arch/x86/include/asm/bitops.h	2022-10-17 19:02:15.000000000 +0200
@@ -207,6 +207,20 @@ static __always_inline bool constant_tes
 		(addr[nr >> _BITOPS_LONG_SHIFT])) != 0;
 }
 
+static __always_inline bool constant_test_bit_acquire(long nr, const volatile unsigned long *addr)
+{
+	bool oldbit;
+
+	asm volatile("testb %2,%1"
+		     CC_SET(nz)
+		     : CC_OUT(nz) (oldbit)
+		     : "m" (((unsigned char *)addr)[nr >> 3]),
+		       "i" (1 << (nr & 7))
+		     :"memory");
+
+	return oldbit;
+}
+
 static __always_inline bool variable_test_bit(long nr, volatile const unsigned long *addr)
 {
 	bool oldbit;
@@ -224,6 +238,13 @@ static __always_inline bool variable_tes
 	 ? constant_test_bit((nr), (addr))	\
 	 : variable_test_bit((nr), (addr)))
 
+static __always_inline bool
+arch_test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	return __builtin_constant_p(nr) ? constant_test_bit_acquire(nr, addr) :
+					  variable_test_bit(nr, addr);
+}
+
 /**
  * __ffs - find first set bit in word
  * @word: The word to search
Index: linux-stable/include/asm-generic/bitops/instrumented-non-atomic.h
===================================================================
--- linux-stable.orig/include/asm-generic/bitops/instrumented-non-atomic.h	2022-10-17 19:02:15.000000000 +0200
+++ linux-stable/include/asm-generic/bitops/instrumented-non-atomic.h	2022-10-17 19:02:15.000000000 +0200
@@ -135,4 +135,16 @@ static __always_inline bool test_bit(lon
 	return arch_test_bit(nr, addr);
 }
 
+/**
+ * _test_bit_acquire - Determine, with acquire semantics, whether a bit is set
+ * @nr: bit number to test
+ * @addr: Address to start counting from
+ */
+static __always_inline bool
+test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	instrument_atomic_read(addr + BIT_WORD(nr), sizeof(long));
+	return arch_test_bit_acquire(nr, addr);
+}
+
 #endif /* _ASM_GENERIC_BITOPS_INSTRUMENTED_NON_ATOMIC_H */
Index: linux-stable/include/asm-generic/bitops/non-atomic.h
===================================================================
--- linux-stable.orig/include/asm-generic/bitops/non-atomic.h	2022-10-17 19:02:15.000000000 +0200
+++ linux-stable/include/asm-generic/bitops/non-atomic.h	2022-10-17 19:02:15.000000000 +0200
@@ -3,6 +3,7 @@
 #define _ASM_GENERIC_BITOPS_NON_ATOMIC_H_
 
 #include <asm/types.h>
+#include <asm/barrier.h>
 
 /**
  * arch___set_bit - Set a bit in memory
@@ -119,4 +120,17 @@ arch_test_bit(unsigned int nr, const vol
 }
 #define test_bit arch_test_bit
 
+/**
+ * arch_test_bit_acquire - Determine, with acquire semantics, whether a bit is set
+ * @nr: bit number to test
+ * @addr: Address to start counting from
+ */
+static __always_inline bool
+arch_test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	return 1UL & (smp_load_acquire(p) >> (nr & (BITS_PER_LONG-1)));
+}
+#define test_bit_acquire arch_test_bit_acquire
+
 #endif /* _ASM_GENERIC_BITOPS_NON_ATOMIC_H_ */
Index: linux-stable/include/linux/buffer_head.h
===================================================================
--- linux-stable.orig/include/linux/buffer_head.h	2022-10-17 19:02:15.000000000 +0200
+++ linux-stable/include/linux/buffer_head.h	2022-10-17 19:02:15.000000000 +0200
@@ -166,7 +166,7 @@ static __always_inline int buffer_uptoda
 	 * make it consistent with folio_test_uptodate
 	 * pairs with smp_mb__before_atomic in set_buffer_uptodate
 	 */
-	return (smp_load_acquire(&bh->b_state) & (1UL << BH_Uptodate)) != 0;
+	return test_bit_acquire(BH_Uptodate, &bh->b_state);
 }
 
 #define bh_offset(bh)		((unsigned long)(bh)->b_data & ~PAGE_MASK)
Index: linux-stable/include/linux/wait_bit.h
===================================================================
--- linux-stable.orig/include/linux/wait_bit.h	2022-10-17 19:02:15.000000000 +0200
+++ linux-stable/include/linux/wait_bit.h	2022-10-17 19:02:15.000000000 +0200
@@ -71,7 +71,7 @@ static inline int
 wait_on_bit(unsigned long *word, int bit, unsigned mode)
 {
 	might_sleep();
-	if (!test_bit(bit, word))
+	if (!test_bit_acquire(bit, word))
 		return 0;
 	return out_of_line_wait_on_bit(word, bit,
 				       bit_wait,
@@ -96,7 +96,7 @@ static inline int
 wait_on_bit_io(unsigned long *word, int bit, unsigned mode)
 {
 	might_sleep();
-	if (!test_bit(bit, word))
+	if (!test_bit_acquire(bit, word))
 		return 0;
 	return out_of_line_wait_on_bit(word, bit,
 				       bit_wait_io,
@@ -123,7 +123,7 @@ wait_on_bit_timeout(unsigned long *word,
 		    unsigned long timeout)
 {
 	might_sleep();
-	if (!test_bit(bit, word))
+	if (!test_bit_acquire(bit, word))
 		return 0;
 	return out_of_line_wait_on_bit_timeout(word, bit,
 					       bit_wait_timeout,
@@ -151,7 +151,7 @@ wait_on_bit_action(unsigned long *word,
 		   unsigned mode)
 {
 	might_sleep();
-	if (!test_bit(bit, word))
+	if (!test_bit_acquire(bit, word))
 		return 0;
 	return out_of_line_wait_on_bit(word, bit, action, mode);
 }
Index: linux-stable/kernel/sched/wait_bit.c
===================================================================
--- linux-stable.orig/kernel/sched/wait_bit.c	2022-10-17 19:02:15.000000000 +0200
+++ linux-stable/kernel/sched/wait_bit.c	2022-10-17 19:02:15.000000000 +0200
@@ -47,7 +47,7 @@ __wait_on_bit(struct wait_queue_head *wq
 		prepare_to_wait(wq_head, &wbq_entry->wq_entry, mode);
 		if (test_bit(wbq_entry->key.bit_nr, wbq_entry->key.flags))
 			ret = (*action)(&wbq_entry->key, mode);
-	} while (test_bit(wbq_entry->key.bit_nr, wbq_entry->key.flags) && !ret);
+	} while (test_bit_acquire(wbq_entry->key.bit_nr, wbq_entry->key.flags) && !ret);
 
 	finish_wait(wq_head, &wbq_entry->wq_entry);
 
Index: linux-stable/arch/alpha/include/asm/bitops.h
===================================================================
--- linux-stable.orig/arch/alpha/include/asm/bitops.h	2022-10-17 19:02:15.000000000 +0200
+++ linux-stable/arch/alpha/include/asm/bitops.h	2022-10-17 19:02:15.000000000 +0200
@@ -289,6 +289,13 @@ test_bit(int nr, const volatile void * a
 	return (1UL & (((const int *) addr)[nr >> 5] >> (nr & 31))) != 0UL;
 }
 
+static __always_inline bool
+test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	return 1UL & (smp_load_acquire(p) >> (nr & (BITS_PER_LONG-1)));
+}
+
 /*
  * ffz = Find First Zero in word. Undefined if no zero exists,
  * so code should check against ~0UL first..
Index: linux-stable/arch/hexagon/include/asm/bitops.h
===================================================================
--- linux-stable.orig/arch/hexagon/include/asm/bitops.h	2022-10-17 19:02:15.000000000 +0200
+++ linux-stable/arch/hexagon/include/asm/bitops.h	2022-10-17 19:02:15.000000000 +0200
@@ -172,7 +172,22 @@ static inline int __test_bit(int nr, con
 	return retval;
 }
 
+static inline int __test_bit_acquire(int nr, const volatile unsigned long *addr)
+{
+	int retval;
+
+	asm volatile(
+	"{P0 = tstbit(%1,%2); if (P0.new) %0 = #1; if (!P0.new) %0 = #0;}\n"
+	: "=&r" (retval)
+	: "r" (addr[BIT_WORD(nr)]), "r" (nr % BITS_PER_LONG)
+	: "p0", "memory"
+	);
+
+	return retval;
+}
+
 #define test_bit(nr, addr) __test_bit(nr, addr)
+#define test_bit_acquire(nr, addr) __test_bit_acquire(nr, addr)
 
 /*
  * ffz - find first zero in word.
Index: linux-stable/arch/ia64/include/asm/bitops.h
===================================================================
--- linux-stable.orig/arch/ia64/include/asm/bitops.h	2022-10-17 19:02:15.000000000 +0200
+++ linux-stable/arch/ia64/include/asm/bitops.h	2022-10-17 19:02:15.000000000 +0200
@@ -337,6 +337,13 @@ test_bit (int nr, const volatile void *a
 	return 1 & (((const volatile __u32 *) addr)[nr >> 5] >> (nr & 31));
 }
 
+static __always_inline bool
+test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	return 1UL & (smp_load_acquire(p) >> (nr & (BITS_PER_LONG-1)));
+}
+
 /**
  * ffz - find the first zero bit in a long word
  * @x: The long word to find the bit in
Index: linux-stable/arch/m68k/include/asm/bitops.h
===================================================================
--- linux-stable.orig/arch/m68k/include/asm/bitops.h	2022-10-17 19:02:15.000000000 +0200
+++ linux-stable/arch/m68k/include/asm/bitops.h	2022-10-17 19:02:15.000000000 +0200
@@ -153,6 +153,12 @@ static inline int test_bit(int nr, const
 	return (vaddr[nr >> 5] & (1UL << (nr & 31))) != 0;
 }
 
+static __always_inline bool
+test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	return 1UL & (smp_load_acquire(p) >> (nr & (BITS_PER_LONG-1)));
+}
 
 static inline int bset_reg_test_and_set_bit(int nr,
 					    volatile unsigned long *vaddr)
Index: linux-stable/arch/s390/include/asm/bitops.h
===================================================================
--- linux-stable.orig/arch/s390/include/asm/bitops.h	2022-10-17 19:02:15.000000000 +0200
+++ linux-stable/arch/s390/include/asm/bitops.h	2022-10-17 19:02:15.000000000 +0200
@@ -184,6 +184,13 @@ static inline bool arch_test_bit(unsigne
 	return *addr & mask;
 }
 
+static __always_inline bool
+arch_test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	return 1UL & (smp_load_acquire(p) >> (nr & (BITS_PER_LONG-1)));
+}
+
 static inline bool arch_test_and_set_bit_lock(unsigned long nr,
 					      volatile unsigned long *ptr)
 {
Index: linux-stable/arch/sh/include/asm/bitops-op32.h
===================================================================
--- linux-stable.orig/arch/sh/include/asm/bitops-op32.h	2022-10-17 19:02:15.000000000 +0200
+++ linux-stable/arch/sh/include/asm/bitops-op32.h	2022-10-17 19:02:15.000000000 +0200
@@ -138,4 +138,11 @@ static inline int test_bit(int nr, const
 	return 1UL & (addr[BIT_WORD(nr)] >> (nr & (BITS_PER_LONG-1)));
 }
 
+static __always_inline bool
+test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	return 1UL & (smp_load_acquire(p) >> (nr & (BITS_PER_LONG-1)));
+}
+
 #endif /* __ASM_SH_BITOPS_OP32_H */

[PATCH] wait_on_bit: add an acquire memory barrier

[Mikulas Patocka]

This is backport of the upstream patch 8238b4579866b7c1bb99883cfe102a43db5506ff
for the stable branch 5.15

wait_on_bit: add an acquire memory barrier

There are several places in the kernel where wait_on_bit is not followed
by a memory barrier (for example, in drivers/md/dm-bufio.c:new_read).

On architectures with weak memory ordering, it may happen that memory
accesses that follow wait_on_bit are reordered before wait_on_bit and
they may return invalid data.

Fix this class of bugs by introducing a new function "test_bit_acquire"
that works like test_bit, but has acquire memory ordering semantics.

Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Acked-by: Will Deacon <will@kernel.org>
Cc: stable@vger.kernel.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

---
 arch/alpha/include/asm/bitops.h                      |    7 ++++++
 arch/h8300/include/asm/bitops.h                      |    3 +-
 arch/hexagon/include/asm/bitops.h                    |   15 +++++++++++++
 arch/ia64/include/asm/bitops.h                       |    7 ++++++
 arch/m68k/include/asm/bitops.h                       |    6 +++++
 arch/s390/include/asm/bitops.h                       |    7 ++++++
 arch/sh/include/asm/bitops-op32.h                    |    7 ++++++
 arch/x86/include/asm/bitops.h                        |   21 +++++++++++++++++++
 include/asm-generic/bitops/instrumented-non-atomic.h |   12 ++++++++++
 include/asm-generic/bitops/non-atomic.h              |   14 ++++++++++++
 include/linux/buffer_head.h                          |    2 -
 include/linux/wait_bit.h                             |    8 +++----
 kernel/sched/wait_bit.c                              |    2 -
 13 files changed, 104 insertions(+), 7 deletions(-)

Index: linux-stable/arch/x86/include/asm/bitops.h
===================================================================
--- linux-stable.orig/arch/x86/include/asm/bitops.h	2022-10-18 12:42:09.000000000 +0200
+++ linux-stable/arch/x86/include/asm/bitops.h	2022-10-18 12:42:09.000000000 +0200
@@ -207,6 +207,20 @@ static __always_inline bool constant_tes
 		(addr[nr >> _BITOPS_LONG_SHIFT])) != 0;
 }
 
+static __always_inline bool constant_test_bit_acquire(long nr, const volatile unsigned long *addr)
+{
+	bool oldbit;
+
+	asm volatile("testb %2,%1"
+		     CC_SET(nz)
+		     : CC_OUT(nz) (oldbit)
+		     : "m" (((unsigned char *)addr)[nr >> 3]),
+		       "i" (1 << (nr & 7))
+		     :"memory");
+
+	return oldbit;
+}
+
 static __always_inline bool variable_test_bit(long nr, volatile const unsigned long *addr)
 {
 	bool oldbit;
@@ -224,6 +238,13 @@ static __always_inline bool variable_tes
 	 ? constant_test_bit((nr), (addr))	\
 	 : variable_test_bit((nr), (addr)))
 
+static __always_inline bool
+arch_test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	return __builtin_constant_p(nr) ? constant_test_bit_acquire(nr, addr) :
+					  variable_test_bit(nr, addr);
+}
+
 /**
  * __ffs - find first set bit in word
  * @word: The word to search
Index: linux-stable/include/asm-generic/bitops/instrumented-non-atomic.h
===================================================================
--- linux-stable.orig/include/asm-generic/bitops/instrumented-non-atomic.h	2022-10-18 12:42:09.000000000 +0200
+++ linux-stable/include/asm-generic/bitops/instrumented-non-atomic.h	2022-10-18 12:42:09.000000000 +0200
@@ -135,4 +135,16 @@ static inline bool test_bit(long nr, con
 	return arch_test_bit(nr, addr);
 }
 
+/**
+ * _test_bit_acquire - Determine, with acquire semantics, whether a bit is set
+ * @nr: bit number to test
+ * @addr: Address to start counting from
+ */
+static __always_inline bool
+test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	instrument_atomic_read(addr + BIT_WORD(nr), sizeof(long));
+	return arch_test_bit_acquire(nr, addr);
+}
+
 #endif /* _ASM_GENERIC_BITOPS_INSTRUMENTED_NON_ATOMIC_H */
Index: linux-stable/include/asm-generic/bitops/non-atomic.h
===================================================================
--- linux-stable.orig/include/asm-generic/bitops/non-atomic.h	2022-10-18 12:42:09.000000000 +0200
+++ linux-stable/include/asm-generic/bitops/non-atomic.h	2022-10-18 12:42:09.000000000 +0200
@@ -3,6 +3,7 @@
 #define _ASM_GENERIC_BITOPS_NON_ATOMIC_H_
 
 #include <asm/types.h>
+#include <asm/barrier.h>
 
 /**
  * arch___set_bit - Set a bit in memory
@@ -119,4 +120,17 @@ arch_test_bit(unsigned int nr, const vol
 }
 #define test_bit arch_test_bit
 
+/**
+ * arch_test_bit_acquire - Determine, with acquire semantics, whether a bit is set
+ * @nr: bit number to test
+ * @addr: Address to start counting from
+ */
+static __always_inline bool
+arch_test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	return 1UL & (smp_load_acquire(p) >> (nr & (BITS_PER_LONG-1)));
+}
+#define test_bit_acquire arch_test_bit_acquire
+
 #endif /* _ASM_GENERIC_BITOPS_NON_ATOMIC_H_ */
Index: linux-stable/include/linux/buffer_head.h
===================================================================
--- linux-stable.orig/include/linux/buffer_head.h	2022-10-18 12:42:09.000000000 +0200
+++ linux-stable/include/linux/buffer_head.h	2022-10-18 12:42:09.000000000 +0200
@@ -166,7 +166,7 @@ static __always_inline int buffer_uptoda
 	 * make it consistent with folio_test_uptodate
 	 * pairs with smp_mb__before_atomic in set_buffer_uptodate
 	 */
-	return (smp_load_acquire(&bh->b_state) & (1UL << BH_Uptodate)) != 0;
+	return test_bit_acquire(BH_Uptodate, &bh->b_state);
 }
 
 #define bh_offset(bh)		((unsigned long)(bh)->b_data & ~PAGE_MASK)
Index: linux-stable/include/linux/wait_bit.h
===================================================================
--- linux-stable.orig/include/linux/wait_bit.h	2022-10-18 12:42:09.000000000 +0200
+++ linux-stable/include/linux/wait_bit.h	2022-10-18 12:42:09.000000000 +0200
@@ -71,7 +71,7 @@ static inline int
 wait_on_bit(unsigned long *word, int bit, unsigned mode)
 {
 	might_sleep();
-	if (!test_bit(bit, word))
+	if (!test_bit_acquire(bit, word))
 		return 0;
 	return out_of_line_wait_on_bit(word, bit,
 				       bit_wait,
@@ -96,7 +96,7 @@ static inline int
 wait_on_bit_io(unsigned long *word, int bit, unsigned mode)
 {
 	might_sleep();
-	if (!test_bit(bit, word))
+	if (!test_bit_acquire(bit, word))
 		return 0;
 	return out_of_line_wait_on_bit(word, bit,
 				       bit_wait_io,
@@ -123,7 +123,7 @@ wait_on_bit_timeout(unsigned long *word,
 		    unsigned long timeout)
 {
 	might_sleep();
-	if (!test_bit(bit, word))
+	if (!test_bit_acquire(bit, word))
 		return 0;
 	return out_of_line_wait_on_bit_timeout(word, bit,
 					       bit_wait_timeout,
@@ -151,7 +151,7 @@ wait_on_bit_action(unsigned long *word,
 		   unsigned mode)
 {
 	might_sleep();
-	if (!test_bit(bit, word))
+	if (!test_bit_acquire(bit, word))
 		return 0;
 	return out_of_line_wait_on_bit(word, bit, action, mode);
 }
Index: linux-stable/kernel/sched/wait_bit.c
===================================================================
--- linux-stable.orig/kernel/sched/wait_bit.c	2022-10-18 12:42:09.000000000 +0200
+++ linux-stable/kernel/sched/wait_bit.c	2022-10-18 12:42:09.000000000 +0200
@@ -47,7 +47,7 @@ __wait_on_bit(struct wait_queue_head *wq
 		prepare_to_wait(wq_head, &wbq_entry->wq_entry, mode);
 		if (test_bit(wbq_entry->key.bit_nr, wbq_entry->key.flags))
 			ret = (*action)(&wbq_entry->key, mode);
-	} while (test_bit(wbq_entry->key.bit_nr, wbq_entry->key.flags) && !ret);
+	} while (test_bit_acquire(wbq_entry->key.bit_nr, wbq_entry->key.flags) && !ret);
 
 	finish_wait(wq_head, &wbq_entry->wq_entry);
 
Index: linux-stable/arch/alpha/include/asm/bitops.h
===================================================================
--- linux-stable.orig/arch/alpha/include/asm/bitops.h	2022-10-18 12:42:09.000000000 +0200
+++ linux-stable/arch/alpha/include/asm/bitops.h	2022-10-18 12:42:09.000000000 +0200
@@ -289,6 +289,13 @@ test_bit(int nr, const volatile void * a
 	return (1UL & (((const int *) addr)[nr >> 5] >> (nr & 31))) != 0UL;
 }
 
+static __always_inline bool
+test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	return 1UL & (smp_load_acquire(p) >> (nr & (BITS_PER_LONG-1)));
+}
+
 /*
  * ffz = Find First Zero in word. Undefined if no zero exists,
  * so code should check against ~0UL first..
Index: linux-stable/arch/hexagon/include/asm/bitops.h
===================================================================
--- linux-stable.orig/arch/hexagon/include/asm/bitops.h	2022-10-18 12:42:09.000000000 +0200
+++ linux-stable/arch/hexagon/include/asm/bitops.h	2022-10-18 12:42:09.000000000 +0200
@@ -172,7 +172,22 @@ static inline int __test_bit(int nr, con
 	return retval;
 }
 
+static inline int __test_bit_acquire(int nr, const volatile unsigned long *addr)
+{
+	int retval;
+
+	asm volatile(
+	"{P0 = tstbit(%1,%2); if (P0.new) %0 = #1; if (!P0.new) %0 = #0;}\n"
+	: "=&r" (retval)
+	: "r" (addr[BIT_WORD(nr)]), "r" (nr % BITS_PER_LONG)
+	: "p0", "memory"
+	);
+
+	return retval;
+}
+
 #define test_bit(nr, addr) __test_bit(nr, addr)
+#define test_bit_acquire(nr, addr) __test_bit_acquire(nr, addr)
 
 /*
  * ffz - find first zero in word.
Index: linux-stable/arch/ia64/include/asm/bitops.h
===================================================================
--- linux-stable.orig/arch/ia64/include/asm/bitops.h	2022-10-18 12:42:09.000000000 +0200
+++ linux-stable/arch/ia64/include/asm/bitops.h	2022-10-18 12:42:09.000000000 +0200
@@ -337,6 +337,13 @@ test_bit (int nr, const volatile void *a
 	return 1 & (((const volatile __u32 *) addr)[nr >> 5] >> (nr & 31));
 }
 
+static __always_inline bool
+test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	return 1UL & (smp_load_acquire(p) >> (nr & (BITS_PER_LONG-1)));
+}
+
 /**
  * ffz - find the first zero bit in a long word
  * @x: The long word to find the bit in
Index: linux-stable/arch/m68k/include/asm/bitops.h
===================================================================
--- linux-stable.orig/arch/m68k/include/asm/bitops.h	2022-10-18 12:42:09.000000000 +0200
+++ linux-stable/arch/m68k/include/asm/bitops.h	2022-10-18 12:42:09.000000000 +0200
@@ -153,6 +153,12 @@ static inline int test_bit(int nr, const
 	return (vaddr[nr >> 5] & (1UL << (nr & 31))) != 0;
 }
 
+static __always_inline bool
+test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	return 1UL & (smp_load_acquire(p) >> (nr & (BITS_PER_LONG-1)));
+}
 
 static inline int bset_reg_test_and_set_bit(int nr,
 					    volatile unsigned long *vaddr)
Index: linux-stable/arch/s390/include/asm/bitops.h
===================================================================
--- linux-stable.orig/arch/s390/include/asm/bitops.h	2022-10-18 12:42:09.000000000 +0200
+++ linux-stable/arch/s390/include/asm/bitops.h	2022-10-18 12:42:09.000000000 +0200
@@ -184,6 +184,13 @@ static inline bool arch_test_bit(unsigne
 	return *addr & mask;
 }
 
+static __always_inline bool
+arch_test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	return 1UL & (smp_load_acquire(p) >> (nr & (BITS_PER_LONG-1)));
+}
+
 static inline bool arch_test_and_set_bit_lock(unsigned long nr,
 					      volatile unsigned long *ptr)
 {
Index: linux-stable/arch/sh/include/asm/bitops-op32.h
===================================================================
--- linux-stable.orig/arch/sh/include/asm/bitops-op32.h	2022-10-18 12:42:09.000000000 +0200
+++ linux-stable/arch/sh/include/asm/bitops-op32.h	2022-10-18 12:42:09.000000000 +0200
@@ -138,4 +138,11 @@ static inline int test_bit(int nr, const
 	return 1UL & (addr[BIT_WORD(nr)] >> (nr & (BITS_PER_LONG-1)));
 }
 
+static __always_inline bool
+test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	return 1UL & (smp_load_acquire(p) >> (nr & (BITS_PER_LONG-1)));
+}
+
 #endif /* __ASM_SH_BITOPS_OP32_H */
Index: linux-stable/arch/h8300/include/asm/bitops.h
===================================================================
--- linux-stable.orig/arch/h8300/include/asm/bitops.h	2022-10-18 12:42:09.000000000 +0200
+++ linux-stable/arch/h8300/include/asm/bitops.h	2022-10-18 12:42:09.000000000 +0200
@@ -87,7 +87,8 @@ static inline int test_bit(int nr, const
 	return ret;
 }
 
-#define __test_bit(nr, addr) test_bit(nr, addr)
+#define __test_bit(nr, addr)		test_bit(nr, addr)
+#define test_bit_acquire(nr, addr)	test_bit(nr, addr)
 
 #define H8300_GEN_TEST_BITOP(FNNAME, OP)				\
 static inline int FNNAME(int nr, void *addr)				\

[PATCH] wait_on_bit: add an acquire memory barrier

[Mikulas Patocka]

This is backport of the upstream patch 8238b4579866b7c1bb99883cfe102a43db5506ff
for the stable branch 5.10

wait_on_bit: add an acquire memory barrier

There are several places in the kernel where wait_on_bit is not followed
by a memory barrier (for example, in drivers/md/dm-bufio.c:new_read).

On architectures with weak memory ordering, it may happen that memory
accesses that follow wait_on_bit are reordered before wait_on_bit and
they may return invalid data.

Fix this class of bugs by introducing a new function "test_bit_acquire"
that works like test_bit, but has acquire memory ordering semantics.

Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Acked-by: Will Deacon <will@kernel.org>
Cc: stable@vger.kernel.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

---
 arch/alpha/include/asm/bitops.h                      |    7 ++++++
 arch/arc/include/asm/bitops.h                        |    7 ++++++
 arch/h8300/include/asm/bitops.h                      |    3 +-
 arch/hexagon/include/asm/bitops.h                    |   15 +++++++++++++
 arch/ia64/include/asm/bitops.h                       |    7 ++++++
 arch/m68k/include/asm/bitops.h                       |    6 +++++
 arch/s390/include/asm/bitops.h                       |    7 ++++++
 arch/sh/include/asm/bitops-op32.h                    |    7 ++++++
 arch/x86/include/asm/bitops.h                        |   21 +++++++++++++++++++
 include/asm-generic/bitops/instrumented-non-atomic.h |   12 ++++++++++
 include/asm-generic/bitops/non-atomic.h              |   14 ++++++++++++
 include/linux/buffer_head.h                          |    2 -
 include/linux/wait_bit.h                             |    8 +++----
 kernel/sched/wait_bit.c                              |    2 -
 14 files changed, 111 insertions(+), 7 deletions(-)

Index: linux-stable/arch/x86/include/asm/bitops.h
===================================================================
--- linux-stable.orig/arch/x86/include/asm/bitops.h	2022-10-17 19:38:32.000000000 +0200
+++ linux-stable/arch/x86/include/asm/bitops.h	2022-10-17 19:38:32.000000000 +0200
@@ -207,6 +207,20 @@ static __always_inline bool constant_tes
 		(addr[nr >> _BITOPS_LONG_SHIFT])) != 0;
 }
 
+static __always_inline bool constant_test_bit_acquire(long nr, const volatile unsigned long *addr)
+{
+	bool oldbit;
+
+	asm volatile("testb %2,%1"
+		     CC_SET(nz)
+		     : CC_OUT(nz) (oldbit)
+		     : "m" (((unsigned char *)addr)[nr >> 3]),
+		       "i" (1 << (nr & 7))
+		     :"memory");
+
+	return oldbit;
+}
+
 static __always_inline bool variable_test_bit(long nr, volatile const unsigned long *addr)
 {
 	bool oldbit;
@@ -224,6 +238,13 @@ static __always_inline bool variable_tes
 	 ? constant_test_bit((nr), (addr))	\
 	 : variable_test_bit((nr), (addr)))
 
+static __always_inline bool
+arch_test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	return __builtin_constant_p(nr) ? constant_test_bit_acquire(nr, addr) :
+					  variable_test_bit(nr, addr);
+}
+
 /**
  * __ffs - find first set bit in word
  * @word: The word to search
Index: linux-stable/include/asm-generic/bitops/instrumented-non-atomic.h
===================================================================
--- linux-stable.orig/include/asm-generic/bitops/instrumented-non-atomic.h	2022-10-17 19:38:32.000000000 +0200
+++ linux-stable/include/asm-generic/bitops/instrumented-non-atomic.h	2022-10-17 19:38:32.000000000 +0200
@@ -135,4 +135,16 @@ static inline bool test_bit(long nr, con
 	return arch_test_bit(nr, addr);
 }
 
+/**
+ * _test_bit_acquire - Determine, with acquire semantics, whether a bit is set
+ * @nr: bit number to test
+ * @addr: Address to start counting from
+ */
+static __always_inline bool
+test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	instrument_atomic_read(addr + BIT_WORD(nr), sizeof(long));
+	return arch_test_bit_acquire(nr, addr);
+}
+
 #endif /* _ASM_GENERIC_BITOPS_INSTRUMENTED_NON_ATOMIC_H */
Index: linux-stable/include/asm-generic/bitops/non-atomic.h
===================================================================
--- linux-stable.orig/include/asm-generic/bitops/non-atomic.h	2022-10-17 19:38:32.000000000 +0200
+++ linux-stable/include/asm-generic/bitops/non-atomic.h	2022-10-17 19:38:32.000000000 +0200
@@ -3,6 +3,7 @@
 #define _ASM_GENERIC_BITOPS_NON_ATOMIC_H_
 
 #include <asm/types.h>
+#include <asm/barrier.h>
 
 /**
  * __set_bit - Set a bit in memory
@@ -106,4 +107,17 @@ static inline int test_bit(int nr, const
 	return 1UL & (addr[BIT_WORD(nr)] >> (nr & (BITS_PER_LONG-1)));
 }
 
+/**
+ * arch_test_bit_acquire - Determine, with acquire semantics, whether a bit is set
+ * @nr: bit number to test
+ * @addr: Address to start counting from
+ */
+static __always_inline bool
+arch_test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	return 1UL & (smp_load_acquire(p) >> (nr & (BITS_PER_LONG-1)));
+}
+#define test_bit_acquire arch_test_bit_acquire
+
 #endif /* _ASM_GENERIC_BITOPS_NON_ATOMIC_H_ */
Index: linux-stable/include/linux/buffer_head.h
===================================================================
--- linux-stable.orig/include/linux/buffer_head.h	2022-10-17 19:38:32.000000000 +0200
+++ linux-stable/include/linux/buffer_head.h	2022-10-17 19:38:32.000000000 +0200
@@ -166,7 +166,7 @@ static __always_inline int buffer_uptoda
 	 * make it consistent with folio_test_uptodate
 	 * pairs with smp_mb__before_atomic in set_buffer_uptodate
 	 */
-	return (smp_load_acquire(&bh->b_state) & (1UL << BH_Uptodate)) != 0;
+	return test_bit_acquire(BH_Uptodate, &bh->b_state);
 }
 
 #define bh_offset(bh)		((unsigned long)(bh)->b_data & ~PAGE_MASK)
Index: linux-stable/include/linux/wait_bit.h
===================================================================
--- linux-stable.orig/include/linux/wait_bit.h	2022-10-17 19:38:32.000000000 +0200
+++ linux-stable/include/linux/wait_bit.h	2022-10-17 19:38:32.000000000 +0200
@@ -71,7 +71,7 @@ static inline int
 wait_on_bit(unsigned long *word, int bit, unsigned mode)
 {
 	might_sleep();
-	if (!test_bit(bit, word))
+	if (!test_bit_acquire(bit, word))
 		return 0;
 	return out_of_line_wait_on_bit(word, bit,
 				       bit_wait,
@@ -96,7 +96,7 @@ static inline int
 wait_on_bit_io(unsigned long *word, int bit, unsigned mode)
 {
 	might_sleep();
-	if (!test_bit(bit, word))
+	if (!test_bit_acquire(bit, word))
 		return 0;
 	return out_of_line_wait_on_bit(word, bit,
 				       bit_wait_io,
@@ -123,7 +123,7 @@ wait_on_bit_timeout(unsigned long *word,
 		    unsigned long timeout)
 {
 	might_sleep();
-	if (!test_bit(bit, word))
+	if (!test_bit_acquire(bit, word))
 		return 0;
 	return out_of_line_wait_on_bit_timeout(word, bit,
 					       bit_wait_timeout,
@@ -151,7 +151,7 @@ wait_on_bit_action(unsigned long *word,
 		   unsigned mode)
 {
 	might_sleep();
-	if (!test_bit(bit, word))
+	if (!test_bit_acquire(bit, word))
 		return 0;
 	return out_of_line_wait_on_bit(word, bit, action, mode);
 }
Index: linux-stable/kernel/sched/wait_bit.c
===================================================================
--- linux-stable.orig/kernel/sched/wait_bit.c	2022-10-17 19:38:32.000000000 +0200
+++ linux-stable/kernel/sched/wait_bit.c	2022-10-17 19:38:32.000000000 +0200
@@ -47,7 +47,7 @@ __wait_on_bit(struct wait_queue_head *wq
 		prepare_to_wait(wq_head, &wbq_entry->wq_entry, mode);
 		if (test_bit(wbq_entry->key.bit_nr, wbq_entry->key.flags))
 			ret = (*action)(&wbq_entry->key, mode);
-	} while (test_bit(wbq_entry->key.bit_nr, wbq_entry->key.flags) && !ret);
+	} while (test_bit_acquire(wbq_entry->key.bit_nr, wbq_entry->key.flags) && !ret);
 
 	finish_wait(wq_head, &wbq_entry->wq_entry);
 
Index: linux-stable/arch/alpha/include/asm/bitops.h
===================================================================
--- linux-stable.orig/arch/alpha/include/asm/bitops.h	2022-10-17 19:38:32.000000000 +0200
+++ linux-stable/arch/alpha/include/asm/bitops.h	2022-10-17 19:38:32.000000000 +0200
@@ -289,6 +289,13 @@ test_bit(int nr, const volatile void * a
 	return (1UL & (((const int *) addr)[nr >> 5] >> (nr & 31))) != 0UL;
 }
 
+static __always_inline bool
+test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	return 1UL & (smp_load_acquire(p) >> (nr & (BITS_PER_LONG-1)));
+}
+
 /*
  * ffz = Find First Zero in word. Undefined if no zero exists,
  * so code should check against ~0UL first..
Index: linux-stable/arch/hexagon/include/asm/bitops.h
===================================================================
--- linux-stable.orig/arch/hexagon/include/asm/bitops.h	2022-10-17 19:38:32.000000000 +0200
+++ linux-stable/arch/hexagon/include/asm/bitops.h	2022-10-17 19:38:32.000000000 +0200
@@ -172,7 +172,22 @@ static inline int __test_bit(int nr, con
 	return retval;
 }
 
+static inline int __test_bit_acquire(int nr, const volatile unsigned long *addr)
+{
+	int retval;
+
+	asm volatile(
+	"{P0 = tstbit(%1,%2); if (P0.new) %0 = #1; if (!P0.new) %0 = #0;}\n"
+	: "=&r" (retval)
+	: "r" (addr[BIT_WORD(nr)]), "r" (nr % BITS_PER_LONG)
+	: "p0", "memory"
+	);
+
+	return retval;
+}
+
 #define test_bit(nr, addr) __test_bit(nr, addr)
+#define test_bit_acquire(nr, addr) __test_bit_acquire(nr, addr)
 
 /*
  * ffz - find first zero in word.
Index: linux-stable/arch/ia64/include/asm/bitops.h
===================================================================
--- linux-stable.orig/arch/ia64/include/asm/bitops.h	2022-10-17 19:38:32.000000000 +0200
+++ linux-stable/arch/ia64/include/asm/bitops.h	2022-10-17 19:38:32.000000000 +0200
@@ -337,6 +337,13 @@ test_bit (int nr, const volatile void *a
 	return 1 & (((const volatile __u32 *) addr)[nr >> 5] >> (nr & 31));
 }
 
+static __always_inline bool
+test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	return 1UL & (smp_load_acquire(p) >> (nr & (BITS_PER_LONG-1)));
+}
+
 /**
  * ffz - find the first zero bit in a long word
  * @x: The long word to find the bit in
Index: linux-stable/arch/m68k/include/asm/bitops.h
===================================================================
--- linux-stable.orig/arch/m68k/include/asm/bitops.h	2022-10-17 19:38:32.000000000 +0200
+++ linux-stable/arch/m68k/include/asm/bitops.h	2022-10-17 19:38:32.000000000 +0200
@@ -153,6 +153,12 @@ static inline int test_bit(int nr, const
 	return (vaddr[nr >> 5] & (1UL << (nr & 31))) != 0;
 }
 
+static __always_inline bool
+test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	return 1UL & (smp_load_acquire(p) >> (nr & (BITS_PER_LONG-1)));
+}
 
 static inline int bset_reg_test_and_set_bit(int nr,
 					    volatile unsigned long *vaddr)
Index: linux-stable/arch/s390/include/asm/bitops.h
===================================================================
--- linux-stable.orig/arch/s390/include/asm/bitops.h	2022-10-17 19:38:32.000000000 +0200
+++ linux-stable/arch/s390/include/asm/bitops.h	2022-10-17 19:38:32.000000000 +0200
@@ -219,6 +219,13 @@ static inline bool arch_test_bit(unsigne
 	return (*addr >> (nr & 7)) & 1;
 }
 
+static __always_inline bool
+arch_test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	return 1UL & (smp_load_acquire(p) >> (nr & (BITS_PER_LONG-1)));
+}
+
 static inline bool arch_test_and_set_bit_lock(unsigned long nr,
 					      volatile unsigned long *ptr)
 {
Index: linux-stable/arch/sh/include/asm/bitops-op32.h
===================================================================
--- linux-stable.orig/arch/sh/include/asm/bitops-op32.h	2022-10-17 19:38:32.000000000 +0200
+++ linux-stable/arch/sh/include/asm/bitops-op32.h	2022-10-17 19:38:32.000000000 +0200
@@ -138,4 +138,11 @@ static inline int test_bit(int nr, const
 	return 1UL & (addr[BIT_WORD(nr)] >> (nr & (BITS_PER_LONG-1)));
 }
 
+static __always_inline bool
+test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	return 1UL & (smp_load_acquire(p) >> (nr & (BITS_PER_LONG-1)));
+}
+
 #endif /* __ASM_SH_BITOPS_OP32_H */
Index: linux-stable/arch/h8300/include/asm/bitops.h
===================================================================
--- linux-stable.orig/arch/h8300/include/asm/bitops.h	2022-10-17 19:38:32.000000000 +0200
+++ linux-stable/arch/h8300/include/asm/bitops.h	2022-10-17 19:38:32.000000000 +0200
@@ -83,7 +83,8 @@ static inline int test_bit(int nr, const
 	return ret;
 }
 
-#define __test_bit(nr, addr) test_bit(nr, addr)
+#define __test_bit(nr, addr)		test_bit(nr, addr)
+#define test_bit_acquire(nr, addr)	test_bit(nr, addr)
 
 #define H8300_GEN_TEST_BITOP(FNNAME, OP)				\
 static inline int FNNAME(int nr, void *addr)				\
Index: linux-stable/arch/arc/include/asm/bitops.h
===================================================================
--- linux-stable.orig/arch/arc/include/asm/bitops.h	2022-10-17 19:35:36.000000000 +0200
+++ linux-stable/arch/arc/include/asm/bitops.h	2022-10-17 19:41:07.000000000 +0200
@@ -197,6 +197,13 @@ test_bit(unsigned int nr, const volatile
 	return ((mask & *addr) != 0);
 }
 
+static __always_inline bool
+test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	return 1UL & (smp_load_acquire(p) >> (nr & (BITS_PER_LONG-1)));
+}
+
 #ifdef CONFIG_ISA_ARCOMPACT
 
 /*

[PATCH] wait_on_bit: add an acquire memory barrier

[Mikulas Patocka]

This is backport of the upstream patch 8238b4579866b7c1bb99883cfe102a43db5506ff
for the stable branch 5.4

wait_on_bit: add an acquire memory barrier

There are several places in the kernel where wait_on_bit is not followed
by a memory barrier (for example, in drivers/md/dm-bufio.c:new_read).

On architectures with weak memory ordering, it may happen that memory
accesses that follow wait_on_bit are reordered before wait_on_bit and
they may return invalid data.

Fix this class of bugs by introducing a new function "test_bit_acquire"
that works like test_bit, but has acquire memory ordering semantics.

Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Acked-by: Will Deacon <will@kernel.org>
Cc: stable@vger.kernel.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

---
 arch/alpha/include/asm/bitops.h           |    7 +++++++
 arch/arc/include/asm/bitops.h             |    7 +++++++
 arch/h8300/include/asm/bitops.h           |    3 ++-
 arch/hexagon/include/asm/bitops.h         |   15 +++++++++++++++
 arch/ia64/include/asm/bitops.h            |    7 +++++++
 arch/m68k/include/asm/bitops.h            |    6 ++++++
 arch/s390/include/asm/bitops.h            |    7 +++++++
 arch/sh/include/asm/bitops-op32.h         |    7 +++++++
 arch/x86/include/asm/bitops.h             |   21 +++++++++++++++++++++
 include/asm-generic/bitops-instrumented.h |    6 ++++++
 include/asm-generic/bitops/non-atomic.h   |   14 ++++++++++++++
 include/linux/buffer_head.h               |    2 +-
 include/linux/wait_bit.h                  |    8 ++++----
 kernel/sched/wait_bit.c                   |    2 +-
 14 files changed, 105 insertions(+), 7 deletions(-)

Index: linux-stable/arch/x86/include/asm/bitops.h
===================================================================
--- linux-stable.orig/arch/x86/include/asm/bitops.h	2022-10-17 19:50:18.000000000 +0200
+++ linux-stable/arch/x86/include/asm/bitops.h	2022-10-17 19:50:18.000000000 +0200
@@ -207,6 +207,20 @@ static __always_inline bool constant_tes
 		(addr[nr >> _BITOPS_LONG_SHIFT])) != 0;
 }
 
+static __always_inline bool constant_test_bit_acquire(long nr, const volatile unsigned long *addr)
+{
+	bool oldbit;
+
+	asm volatile("testb %2,%1"
+		     CC_SET(nz)
+		     : CC_OUT(nz) (oldbit)
+		     : "m" (((unsigned char *)addr)[nr >> 3]),
+		       "i" (1 << (nr & 7))
+		     :"memory");
+
+	return oldbit;
+}
+
 static __always_inline bool variable_test_bit(long nr, volatile const unsigned long *addr)
 {
 	bool oldbit;
@@ -224,6 +238,13 @@ static __always_inline bool variable_tes
 	 ? constant_test_bit((nr), (addr))	\
 	 : variable_test_bit((nr), (addr)))
 
+static __always_inline bool
+arch_test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	return __builtin_constant_p(nr) ? constant_test_bit_acquire(nr, addr) :
+					  variable_test_bit(nr, addr);
+}
+
 /**
  * __ffs - find first set bit in word
  * @word: The word to search
Index: linux-stable/include/asm-generic/bitops/non-atomic.h
===================================================================
--- linux-stable.orig/include/asm-generic/bitops/non-atomic.h	2022-10-17 19:50:18.000000000 +0200
+++ linux-stable/include/asm-generic/bitops/non-atomic.h	2022-10-17 19:50:18.000000000 +0200
@@ -3,6 +3,7 @@
 #define _ASM_GENERIC_BITOPS_NON_ATOMIC_H_
 
 #include <asm/types.h>
+#include <asm/barrier.h>
 
 /**
  * __set_bit - Set a bit in memory
@@ -106,4 +107,17 @@ static inline int test_bit(int nr, const
 	return 1UL & (addr[BIT_WORD(nr)] >> (nr & (BITS_PER_LONG-1)));
 }
 
+/**
+ * arch_test_bit_acquire - Determine, with acquire semantics, whether a bit is set
+ * @nr: bit number to test
+ * @addr: Address to start counting from
+ */
+static __always_inline bool
+arch_test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	return 1UL & (smp_load_acquire(p) >> (nr & (BITS_PER_LONG-1)));
+}
+#define test_bit_acquire arch_test_bit_acquire
+
 #endif /* _ASM_GENERIC_BITOPS_NON_ATOMIC_H_ */
Index: linux-stable/include/linux/buffer_head.h
===================================================================
--- linux-stable.orig/include/linux/buffer_head.h	2022-10-17 19:50:18.000000000 +0200
+++ linux-stable/include/linux/buffer_head.h	2022-10-17 19:50:18.000000000 +0200
@@ -166,7 +166,7 @@ static __always_inline int buffer_uptoda
 	 * make it consistent with folio_test_uptodate
 	 * pairs with smp_mb__before_atomic in set_buffer_uptodate
 	 */
-	return (smp_load_acquire(&bh->b_state) & (1UL << BH_Uptodate)) != 0;
+	return test_bit_acquire(BH_Uptodate, &bh->b_state);
 }
 
 #define bh_offset(bh)		((unsigned long)(bh)->b_data & ~PAGE_MASK)
Index: linux-stable/include/linux/wait_bit.h
===================================================================
--- linux-stable.orig/include/linux/wait_bit.h	2022-10-17 19:50:18.000000000 +0200
+++ linux-stable/include/linux/wait_bit.h	2022-10-17 19:50:18.000000000 +0200
@@ -71,7 +71,7 @@ static inline int
 wait_on_bit(unsigned long *word, int bit, unsigned mode)
 {
 	might_sleep();
-	if (!test_bit(bit, word))
+	if (!test_bit_acquire(bit, word))
 		return 0;
 	return out_of_line_wait_on_bit(word, bit,
 				       bit_wait,
@@ -96,7 +96,7 @@ static inline int
 wait_on_bit_io(unsigned long *word, int bit, unsigned mode)
 {
 	might_sleep();
-	if (!test_bit(bit, word))
+	if (!test_bit_acquire(bit, word))
 		return 0;
 	return out_of_line_wait_on_bit(word, bit,
 				       bit_wait_io,
@@ -123,7 +123,7 @@ wait_on_bit_timeout(unsigned long *word,
 		    unsigned long timeout)
 {
 	might_sleep();
-	if (!test_bit(bit, word))
+	if (!test_bit_acquire(bit, word))
 		return 0;
 	return out_of_line_wait_on_bit_timeout(word, bit,
 					       bit_wait_timeout,
@@ -151,7 +151,7 @@ wait_on_bit_action(unsigned long *word,
 		   unsigned mode)
 {
 	might_sleep();
-	if (!test_bit(bit, word))
+	if (!test_bit_acquire(bit, word))
 		return 0;
 	return out_of_line_wait_on_bit(word, bit, action, mode);
 }
Index: linux-stable/kernel/sched/wait_bit.c
===================================================================
--- linux-stable.orig/kernel/sched/wait_bit.c	2022-10-17 19:50:18.000000000 +0200
+++ linux-stable/kernel/sched/wait_bit.c	2022-10-17 19:50:18.000000000 +0200
@@ -47,7 +47,7 @@ __wait_on_bit(struct wait_queue_head *wq
 		prepare_to_wait(wq_head, &wbq_entry->wq_entry, mode);
 		if (test_bit(wbq_entry->key.bit_nr, wbq_entry->key.flags))
 			ret = (*action)(&wbq_entry->key, mode);
-	} while (test_bit(wbq_entry->key.bit_nr, wbq_entry->key.flags) && !ret);
+	} while (test_bit_acquire(wbq_entry->key.bit_nr, wbq_entry->key.flags) && !ret);
 
 	finish_wait(wq_head, &wbq_entry->wq_entry);
 
Index: linux-stable/include/asm-generic/bitops-instrumented.h
===================================================================
--- linux-stable.orig/include/asm-generic/bitops-instrumented.h	2022-10-17 19:50:18.000000000 +0200
+++ linux-stable/include/asm-generic/bitops-instrumented.h	2022-10-17 19:50:18.000000000 +0200
@@ -238,6 +238,12 @@ static inline bool test_bit(long nr, con
 	return arch_test_bit(nr, addr);
 }
 
+static inline bool test_bit_acquire(long nr, const volatile unsigned long *addr)
+{
+	kasan_check_read(addr + BIT_WORD(nr), sizeof(long));
+	return arch_test_bit_acquire(nr, addr);
+}
+
 #if defined(arch_clear_bit_unlock_is_negative_byte)
 /**
  * clear_bit_unlock_is_negative_byte - Clear a bit in memory and test if bottom
Index: linux-stable/arch/alpha/include/asm/bitops.h
===================================================================
--- linux-stable.orig/arch/alpha/include/asm/bitops.h	2022-10-17 19:50:18.000000000 +0200
+++ linux-stable/arch/alpha/include/asm/bitops.h	2022-10-17 19:50:18.000000000 +0200
@@ -289,6 +289,13 @@ test_bit(int nr, const volatile void * a
 	return (1UL & (((const int *) addr)[nr >> 5] >> (nr & 31))) != 0UL;
 }
 
+static __always_inline bool
+test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	return 1UL & (smp_load_acquire(p) >> (nr & (BITS_PER_LONG-1)));
+}
+
 /*
  * ffz = Find First Zero in word. Undefined if no zero exists,
  * so code should check against ~0UL first..
Index: linux-stable/arch/hexagon/include/asm/bitops.h
===================================================================
--- linux-stable.orig/arch/hexagon/include/asm/bitops.h	2022-10-17 19:50:18.000000000 +0200
+++ linux-stable/arch/hexagon/include/asm/bitops.h	2022-10-17 19:50:18.000000000 +0200
@@ -172,7 +172,22 @@ static inline int __test_bit(int nr, con
 	return retval;
 }
 
+static inline int __test_bit_acquire(int nr, const volatile unsigned long *addr)
+{
+	int retval;
+
+	asm volatile(
+	"{P0 = tstbit(%1,%2); if (P0.new) %0 = #1; if (!P0.new) %0 = #0;}\n"
+	: "=&r" (retval)
+	: "r" (addr[BIT_WORD(nr)]), "r" (nr % BITS_PER_LONG)
+	: "p0", "memory"
+	);
+
+	return retval;
+}
+
 #define test_bit(nr, addr) __test_bit(nr, addr)
+#define test_bit_acquire(nr, addr) __test_bit_acquire(nr, addr)
 
 /*
  * ffz - find first zero in word.
Index: linux-stable/arch/ia64/include/asm/bitops.h
===================================================================
--- linux-stable.orig/arch/ia64/include/asm/bitops.h	2022-10-17 19:50:18.000000000 +0200
+++ linux-stable/arch/ia64/include/asm/bitops.h	2022-10-17 19:50:18.000000000 +0200
@@ -337,6 +337,13 @@ test_bit (int nr, const volatile void *a
 	return 1 & (((const volatile __u32 *) addr)[nr >> 5] >> (nr & 31));
 }
 
+static __always_inline bool
+test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	return 1UL & (smp_load_acquire(p) >> (nr & (BITS_PER_LONG-1)));
+}
+
 /**
  * ffz - find the first zero bit in a long word
  * @x: The long word to find the bit in
Index: linux-stable/arch/m68k/include/asm/bitops.h
===================================================================
--- linux-stable.orig/arch/m68k/include/asm/bitops.h	2022-10-17 19:50:18.000000000 +0200
+++ linux-stable/arch/m68k/include/asm/bitops.h	2022-10-17 19:50:18.000000000 +0200
@@ -153,6 +153,12 @@ static inline int test_bit(int nr, const
 	return (vaddr[nr >> 5] & (1UL << (nr & 31))) != 0;
 }
 
+static __always_inline bool
+test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	return 1UL & (smp_load_acquire(p) >> (nr & (BITS_PER_LONG-1)));
+}
 
 static inline int bset_reg_test_and_set_bit(int nr,
 					    volatile unsigned long *vaddr)
Index: linux-stable/arch/s390/include/asm/bitops.h
===================================================================
--- linux-stable.orig/arch/s390/include/asm/bitops.h	2022-10-17 19:50:18.000000000 +0200
+++ linux-stable/arch/s390/include/asm/bitops.h	2022-10-17 19:50:18.000000000 +0200
@@ -219,6 +219,13 @@ static inline bool arch_test_bit(unsigne
 	return (*addr >> (nr & 7)) & 1;
 }
 
+static __always_inline bool
+arch_test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	return 1UL & (smp_load_acquire(p) >> (nr & (BITS_PER_LONG-1)));
+}
+
 static inline bool arch_test_and_set_bit_lock(unsigned long nr,
 					      volatile unsigned long *ptr)
 {
Index: linux-stable/arch/sh/include/asm/bitops-op32.h
===================================================================
--- linux-stable.orig/arch/sh/include/asm/bitops-op32.h	2022-10-17 19:50:18.000000000 +0200
+++ linux-stable/arch/sh/include/asm/bitops-op32.h	2022-10-17 19:50:18.000000000 +0200
@@ -140,4 +140,11 @@ static inline int test_bit(int nr, const
 	return 1UL & (addr[BIT_WORD(nr)] >> (nr & (BITS_PER_LONG-1)));
 }
 
+static __always_inline bool
+test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	return 1UL & (smp_load_acquire(p) >> (nr & (BITS_PER_LONG-1)));
+}
+
 #endif /* __ASM_SH_BITOPS_OP32_H */
Index: linux-stable/arch/arc/include/asm/bitops.h
===================================================================
--- linux-stable.orig/arch/arc/include/asm/bitops.h	2022-10-17 19:50:18.000000000 +0200
+++ linux-stable/arch/arc/include/asm/bitops.h	2022-10-17 19:50:18.000000000 +0200
@@ -251,6 +251,13 @@ test_bit(unsigned int nr, const volatile
 	return ((mask & *addr) != 0);
 }
 
+static __always_inline bool
+test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	return 1UL & (smp_load_acquire(p) >> (nr & (BITS_PER_LONG-1)));
+}
+
 #ifdef CONFIG_ISA_ARCOMPACT
 
 /*
Index: linux-stable/arch/h8300/include/asm/bitops.h
===================================================================
--- linux-stable.orig/arch/h8300/include/asm/bitops.h	2022-10-17 19:46:50.000000000 +0200
+++ linux-stable/arch/h8300/include/asm/bitops.h	2022-10-17 19:54:41.000000000 +0200
@@ -83,7 +83,8 @@ static inline int test_bit(int nr, const
 	return ret;
 }
 
-#define __test_bit(nr, addr) test_bit(nr, addr)
+#define __test_bit(nr, addr)		test_bit(nr, addr)
+#define test_bit_acquire(nr, addr)	test_bit(nr, addr)
 
 #define H8300_GEN_TEST_BITOP(FNNAME, OP)				\
 static inline int FNNAME(int nr, void *addr)				\

[PATCH] wait_on_bit: add an acquire memory barrier

[Mikulas Patocka]

This is backport of the upstream patch 8238b4579866b7c1bb99883cfe102a43db5506ff
for the stable branch 4.19

wait_on_bit: add an acquire memory barrier

There are several places in the kernel where wait_on_bit is not followed
by a memory barrier (for example, in drivers/md/dm-bufio.c:new_read).

On architectures with weak memory ordering, it may happen that memory
accesses that follow wait_on_bit are reordered before wait_on_bit and
they may return invalid data.

Fix this class of bugs by introducing a new function "test_bit_acquire"
that works like test_bit, but has acquire memory ordering semantics.

Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Acked-by: Will Deacon <will@kernel.org>
Cc: stable@vger.kernel.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

---
 arch/alpha/include/asm/bitops.h         |    7 +++++++
 arch/arc/include/asm/bitops.h           |    7 +++++++
 arch/h8300/include/asm/bitops.h         |    3 ++-
 arch/hexagon/include/asm/bitops.h       |   15 +++++++++++++++
 arch/ia64/include/asm/bitops.h          |    7 +++++++
 arch/m68k/include/asm/bitops.h          |    6 ++++++
 arch/s390/include/asm/bitops.h          |    7 +++++++
 arch/sh/include/asm/bitops-op32.h       |    7 +++++++
 arch/x86/include/asm/bitops.h           |   21 +++++++++++++++++++++
 include/asm-generic/bitops/non-atomic.h |   14 ++++++++++++++
 include/linux/buffer_head.h             |    2 +-
 include/linux/wait_bit.h                |    8 ++++----
 kernel/sched/wait_bit.c                 |    2 +-
 13 files changed, 99 insertions(+), 7 deletions(-)

Index: linux-stable/arch/x86/include/asm/bitops.h
===================================================================
--- linux-stable.orig/arch/x86/include/asm/bitops.h	2022-10-17 20:04:40.000000000 +0200
+++ linux-stable/arch/x86/include/asm/bitops.h	2022-10-17 20:04:40.000000000 +0200
@@ -317,6 +317,20 @@ static __always_inline bool constant_tes
 		(addr[nr >> _BITOPS_LONG_SHIFT])) != 0;
 }
 
+static __always_inline bool constant_test_bit_acquire(long nr, const volatile unsigned long *addr)
+{
+	bool oldbit;
+
+	asm volatile("testb %2,%1"
+		     CC_SET(nz)
+		     : CC_OUT(nz) (oldbit)
+		     : "m" (((unsigned char *)addr)[nr >> 3]),
+		       "i" (1 << (nr & 7))
+		     :"memory");
+
+	return oldbit;
+}
+
 static __always_inline bool variable_test_bit(long nr, volatile const unsigned long *addr)
 {
 	bool oldbit;
@@ -343,6 +357,13 @@ static bool test_bit(int nr, const volat
 	 ? constant_test_bit((nr), (addr))	\
 	 : variable_test_bit((nr), (addr)))
 
+static __always_inline bool
+test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	return __builtin_constant_p(nr) ? constant_test_bit_acquire(nr, addr) :
+					  variable_test_bit(nr, addr);
+}
+
 /**
  * __ffs - find first set bit in word
  * @word: The word to search
Index: linux-stable/include/asm-generic/bitops/non-atomic.h
===================================================================
--- linux-stable.orig/include/asm-generic/bitops/non-atomic.h	2022-10-17 20:04:40.000000000 +0200
+++ linux-stable/include/asm-generic/bitops/non-atomic.h	2022-10-17 20:04:40.000000000 +0200
@@ -3,6 +3,7 @@
 #define _ASM_GENERIC_BITOPS_NON_ATOMIC_H_
 
 #include <asm/types.h>
+#include <asm/barrier.h>
 
 /**
  * __set_bit - Set a bit in memory
@@ -106,4 +107,17 @@ static inline int test_bit(int nr, const
 	return 1UL & (addr[BIT_WORD(nr)] >> (nr & (BITS_PER_LONG-1)));
 }
 
+/**
+ * arch_test_bit_acquire - Determine, with acquire semantics, whether a bit is set
+ * @nr: bit number to test
+ * @addr: Address to start counting from
+ */
+static __always_inline bool
+arch_test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	return 1UL & (smp_load_acquire(p) >> (nr & (BITS_PER_LONG-1)));
+}
+#define test_bit_acquire arch_test_bit_acquire
+
 #endif /* _ASM_GENERIC_BITOPS_NON_ATOMIC_H_ */
Index: linux-stable/include/linux/buffer_head.h
===================================================================
--- linux-stable.orig/include/linux/buffer_head.h	2022-10-17 20:04:40.000000000 +0200
+++ linux-stable/include/linux/buffer_head.h	2022-10-17 20:04:40.000000000 +0200
@@ -166,7 +166,7 @@ static __always_inline int buffer_uptoda
 	 * make it consistent with folio_test_uptodate
 	 * pairs with smp_mb__before_atomic in set_buffer_uptodate
 	 */
-	return (smp_load_acquire(&bh->b_state) & (1UL << BH_Uptodate)) != 0;
+	return test_bit_acquire(BH_Uptodate, &bh->b_state);
 }
 
 #define bh_offset(bh)		((unsigned long)(bh)->b_data & ~PAGE_MASK)
Index: linux-stable/include/linux/wait_bit.h
===================================================================
--- linux-stable.orig/include/linux/wait_bit.h	2022-10-17 20:04:40.000000000 +0200
+++ linux-stable/include/linux/wait_bit.h	2022-10-17 20:04:40.000000000 +0200
@@ -71,7 +71,7 @@ static inline int
 wait_on_bit(unsigned long *word, int bit, unsigned mode)
 {
 	might_sleep();
-	if (!test_bit(bit, word))
+	if (!test_bit_acquire(bit, word))
 		return 0;
 	return out_of_line_wait_on_bit(word, bit,
 				       bit_wait,
@@ -96,7 +96,7 @@ static inline int
 wait_on_bit_io(unsigned long *word, int bit, unsigned mode)
 {
 	might_sleep();
-	if (!test_bit(bit, word))
+	if (!test_bit_acquire(bit, word))
 		return 0;
 	return out_of_line_wait_on_bit(word, bit,
 				       bit_wait_io,
@@ -123,7 +123,7 @@ wait_on_bit_timeout(unsigned long *word,
 		    unsigned long timeout)
 {
 	might_sleep();
-	if (!test_bit(bit, word))
+	if (!test_bit_acquire(bit, word))
 		return 0;
 	return out_of_line_wait_on_bit_timeout(word, bit,
 					       bit_wait_timeout,
@@ -151,7 +151,7 @@ wait_on_bit_action(unsigned long *word,
 		   unsigned mode)
 {
 	might_sleep();
-	if (!test_bit(bit, word))
+	if (!test_bit_acquire(bit, word))
 		return 0;
 	return out_of_line_wait_on_bit(word, bit, action, mode);
 }
Index: linux-stable/kernel/sched/wait_bit.c
===================================================================
--- linux-stable.orig/kernel/sched/wait_bit.c	2022-10-17 20:04:40.000000000 +0200
+++ linux-stable/kernel/sched/wait_bit.c	2022-10-17 20:04:40.000000000 +0200
@@ -46,7 +46,7 @@ __wait_on_bit(struct wait_queue_head *wq
 		prepare_to_wait(wq_head, &wbq_entry->wq_entry, mode);
 		if (test_bit(wbq_entry->key.bit_nr, wbq_entry->key.flags))
 			ret = (*action)(&wbq_entry->key, mode);
-	} while (test_bit(wbq_entry->key.bit_nr, wbq_entry->key.flags) && !ret);
+	} while (test_bit_acquire(wbq_entry->key.bit_nr, wbq_entry->key.flags) && !ret);
 
 	finish_wait(wq_head, &wbq_entry->wq_entry);
 
Index: linux-stable/arch/alpha/include/asm/bitops.h
===================================================================
--- linux-stable.orig/arch/alpha/include/asm/bitops.h	2022-10-17 20:04:40.000000000 +0200
+++ linux-stable/arch/alpha/include/asm/bitops.h	2022-10-17 20:04:40.000000000 +0200
@@ -289,6 +289,13 @@ test_bit(int nr, const volatile void * a
 	return (1UL & (((const int *) addr)[nr >> 5] >> (nr & 31))) != 0UL;
 }
 
+static __always_inline bool
+test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	return 1UL & (smp_load_acquire(p) >> (nr & (BITS_PER_LONG-1)));
+}
+
 /*
  * ffz = Find First Zero in word. Undefined if no zero exists,
  * so code should check against ~0UL first..
Index: linux-stable/arch/hexagon/include/asm/bitops.h
===================================================================
--- linux-stable.orig/arch/hexagon/include/asm/bitops.h	2022-10-17 20:04:40.000000000 +0200
+++ linux-stable/arch/hexagon/include/asm/bitops.h	2022-10-17 20:04:40.000000000 +0200
@@ -186,7 +186,22 @@ static inline int __test_bit(int nr, con
 	return retval;
 }
 
+static inline int __test_bit_acquire(int nr, const volatile unsigned long *addr)
+{
+	int retval;
+
+	asm volatile(
+	"{P0 = tstbit(%1,%2); if (P0.new) %0 = #1; if (!P0.new) %0 = #0;}\n"
+	: "=&r" (retval)
+	: "r" (addr[BIT_WORD(nr)]), "r" (nr % BITS_PER_LONG)
+	: "p0", "memory"
+	);
+
+	return retval;
+}
+
 #define test_bit(nr, addr) __test_bit(nr, addr)
+#define test_bit_acquire(nr, addr) __test_bit_acquire(nr, addr)
 
 /*
  * ffz - find first zero in word.
Index: linux-stable/arch/ia64/include/asm/bitops.h
===================================================================
--- linux-stable.orig/arch/ia64/include/asm/bitops.h	2022-10-17 20:04:40.000000000 +0200
+++ linux-stable/arch/ia64/include/asm/bitops.h	2022-10-17 20:04:40.000000000 +0200
@@ -337,6 +337,13 @@ test_bit (int nr, const volatile void *a
 	return 1 & (((const volatile __u32 *) addr)[nr >> 5] >> (nr & 31));
 }
 
+static __always_inline bool
+test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	return 1UL & (smp_load_acquire(p) >> (nr & (BITS_PER_LONG-1)));
+}
+
 /**
  * ffz - find the first zero bit in a long word
  * @x: The long word to find the bit in
Index: linux-stable/arch/m68k/include/asm/bitops.h
===================================================================
--- linux-stable.orig/arch/m68k/include/asm/bitops.h	2022-10-17 20:04:40.000000000 +0200
+++ linux-stable/arch/m68k/include/asm/bitops.h	2022-10-17 20:04:40.000000000 +0200
@@ -153,6 +153,12 @@ static inline int test_bit(int nr, const
 	return (vaddr[nr >> 5] & (1UL << (nr & 31))) != 0;
 }
 
+static __always_inline bool
+test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	return 1UL & (smp_load_acquire(p) >> (nr & (BITS_PER_LONG-1)));
+}
 
 static inline int bset_reg_test_and_set_bit(int nr,
 					    volatile unsigned long *vaddr)
Index: linux-stable/arch/s390/include/asm/bitops.h
===================================================================
--- linux-stable.orig/arch/s390/include/asm/bitops.h	2022-10-17 20:04:40.000000000 +0200
+++ linux-stable/arch/s390/include/asm/bitops.h	2022-10-17 20:04:40.000000000 +0200
@@ -215,6 +215,13 @@ static inline int test_bit(unsigned long
 	return (*addr >> (nr & 7)) & 1;
 }
 
+static __always_inline bool
+test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	return 1UL & (smp_load_acquire(p) >> (nr & (BITS_PER_LONG-1)));
+}
+
 static inline int test_and_set_bit_lock(unsigned long nr,
 					volatile unsigned long *ptr)
 {
Index: linux-stable/arch/sh/include/asm/bitops-op32.h
===================================================================
--- linux-stable.orig/arch/sh/include/asm/bitops-op32.h	2022-10-17 20:04:40.000000000 +0200
+++ linux-stable/arch/sh/include/asm/bitops-op32.h	2022-10-17 20:04:40.000000000 +0200
@@ -140,4 +140,11 @@ static inline int test_bit(int nr, const
 	return 1UL & (addr[BIT_WORD(nr)] >> (nr & (BITS_PER_LONG-1)));
 }
 
+static __always_inline bool
+test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	return 1UL & (smp_load_acquire(p) >> (nr & (BITS_PER_LONG-1)));
+}
+
 #endif /* __ASM_SH_BITOPS_OP32_H */
Index: linux-stable/arch/arc/include/asm/bitops.h
===================================================================
--- linux-stable.orig/arch/arc/include/asm/bitops.h	2022-10-17 20:04:40.000000000 +0200
+++ linux-stable/arch/arc/include/asm/bitops.h	2022-10-17 20:04:40.000000000 +0200
@@ -254,6 +254,13 @@ test_bit(unsigned int nr, const volatile
 	return ((mask & *addr) != 0);
 }
 
+static __always_inline bool
+test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	return 1UL & (smp_load_acquire(p) >> (nr & (BITS_PER_LONG-1)));
+}
+
 #ifdef CONFIG_ISA_ARCOMPACT
 
 /*
Index: linux-stable/arch/h8300/include/asm/bitops.h
===================================================================
--- linux-stable.orig/arch/h8300/include/asm/bitops.h	2022-10-17 20:04:40.000000000 +0200
+++ linux-stable/arch/h8300/include/asm/bitops.h	2022-10-17 20:04:40.000000000 +0200
@@ -89,7 +89,8 @@ static inline int test_bit(int nr, const
 	return ret;
 }
 
-#define __test_bit(nr, addr) test_bit(nr, addr)
+#define __test_bit(nr, addr)		test_bit(nr, addr)
+#define test_bit_acquire(nr, addr)	test_bit(nr, addr)
 
 #define H8300_GEN_TEST_BITOP(FNNAME, OP)				\
 static inline int FNNAME(int nr, void *addr)				\

[PATCH] wait_on_bit: add an acquire memory barrier

[Mikulas Patocka]

This is backport of the upstream patch 8238b4579866b7c1bb99883cfe102a43db5506ff
for the stable branch 4.14

wait_on_bit: add an acquire memory barrier

There are several places in the kernel where wait_on_bit is not followed
by a memory barrier (for example, in drivers/md/dm-bufio.c:new_read).

On architectures with weak memory ordering, it may happen that memory
accesses that follow wait_on_bit are reordered before wait_on_bit and
they may return invalid data.

Fix this class of bugs by introducing a new function "test_bit_acquire"
that works like test_bit, but has acquire memory ordering semantics.

Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Acked-by: Will Deacon <will@kernel.org>
Cc: stable@vger.kernel.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

---
 arch/alpha/include/asm/bitops.h         |    7 +++++++
 arch/arc/include/asm/bitops.h           |    7 +++++++
 arch/frv/include/asm/bitops.h           |    7 +++++++
 arch/h8300/include/asm/bitops.h         |    3 ++-
 arch/hexagon/include/asm/bitops.h       |   15 +++++++++++++++
 arch/ia64/include/asm/bitops.h          |    7 +++++++
 arch/m68k/include/asm/bitops.h          |    6 ++++++
 arch/mn10300/include/asm/bitops.h       |    7 +++++++
 arch/s390/include/asm/bitops.h          |    7 +++++++
 arch/sh/include/asm/bitops-op32.h       |    7 +++++++
 arch/x86/include/asm/bitops.h           |   21 +++++++++++++++++++++
 include/asm-generic/bitops/non-atomic.h |   14 ++++++++++++++
 include/linux/buffer_head.h             |    2 +-
 include/linux/wait_bit.h                |    8 ++++----
 kernel/sched/wait_bit.c                 |    2 +-
 15 files changed, 113 insertions(+), 7 deletions(-)

Index: linux-stable/arch/x86/include/asm/bitops.h
===================================================================
--- linux-stable.orig/arch/x86/include/asm/bitops.h	2022-10-17 20:39:55.000000000 +0200
+++ linux-stable/arch/x86/include/asm/bitops.h	2022-10-17 20:39:55.000000000 +0200
@@ -328,6 +328,20 @@ static __always_inline bool constant_tes
 		(addr[nr >> _BITOPS_LONG_SHIFT])) != 0;
 }
 
+static __always_inline bool constant_test_bit_acquire(long nr, const volatile unsigned long *addr)
+{
+	bool oldbit;
+
+	asm volatile("testb %2,%1"
+		     CC_SET(nz)
+		     : CC_OUT(nz) (oldbit)
+		     : "m" (((unsigned char *)addr)[nr >> 3]),
+		       "i" (1 << (nr & 7))
+		     :"memory");
+
+	return oldbit;
+}
+
 static __always_inline bool variable_test_bit(long nr, volatile const unsigned long *addr)
 {
 	bool oldbit;
@@ -354,6 +368,13 @@ static bool test_bit(int nr, const volat
 	 ? constant_test_bit((nr), (addr))	\
 	 : variable_test_bit((nr), (addr)))
 
+static __always_inline bool
+test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	return __builtin_constant_p(nr) ? constant_test_bit_acquire(nr, addr) :
+					  variable_test_bit(nr, addr);
+}
+
 /**
  * __ffs - find first set bit in word
  * @word: The word to search
Index: linux-stable/include/asm-generic/bitops/non-atomic.h
===================================================================
--- linux-stable.orig/include/asm-generic/bitops/non-atomic.h	2022-10-17 20:39:55.000000000 +0200
+++ linux-stable/include/asm-generic/bitops/non-atomic.h	2022-10-17 20:39:55.000000000 +0200
@@ -3,6 +3,7 @@
 #define _ASM_GENERIC_BITOPS_NON_ATOMIC_H_
 
 #include <asm/types.h>
+#include <asm/barrier.h>
 
 /**
  * __set_bit - Set a bit in memory
@@ -106,4 +107,17 @@ static inline int test_bit(int nr, const
 	return 1UL & (addr[BIT_WORD(nr)] >> (nr & (BITS_PER_LONG-1)));
 }
 
+/**
+ * arch_test_bit_acquire - Determine, with acquire semantics, whether a bit is set
+ * @nr: bit number to test
+ * @addr: Address to start counting from
+ */
+static __always_inline bool
+arch_test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	return 1UL & (smp_load_acquire(p) >> (nr & (BITS_PER_LONG-1)));
+}
+#define test_bit_acquire arch_test_bit_acquire
+
 #endif /* _ASM_GENERIC_BITOPS_NON_ATOMIC_H_ */
Index: linux-stable/include/linux/buffer_head.h
===================================================================
--- linux-stable.orig/include/linux/buffer_head.h	2022-10-17 20:39:55.000000000 +0200
+++ linux-stable/include/linux/buffer_head.h	2022-10-17 20:39:55.000000000 +0200
@@ -163,7 +163,7 @@ static __always_inline int buffer_uptoda
 	 * make it consistent with folio_test_uptodate
 	 * pairs with smp_mb__before_atomic in set_buffer_uptodate
 	 */
-	return (smp_load_acquire(&bh->b_state) & (1UL << BH_Uptodate)) != 0;
+	return test_bit_acquire(BH_Uptodate, &bh->b_state);
 }
 
 #define bh_offset(bh)		((unsigned long)(bh)->b_data & ~PAGE_MASK)
Index: linux-stable/include/linux/wait_bit.h
===================================================================
--- linux-stable.orig/include/linux/wait_bit.h	2022-10-17 20:39:55.000000000 +0200
+++ linux-stable/include/linux/wait_bit.h	2022-10-17 20:39:55.000000000 +0200
@@ -76,7 +76,7 @@ static inline int
 wait_on_bit(unsigned long *word, int bit, unsigned mode)
 {
 	might_sleep();
-	if (!test_bit(bit, word))
+	if (!test_bit_acquire(bit, word))
 		return 0;
 	return out_of_line_wait_on_bit(word, bit,
 				       bit_wait,
@@ -101,7 +101,7 @@ static inline int
 wait_on_bit_io(unsigned long *word, int bit, unsigned mode)
 {
 	might_sleep();
-	if (!test_bit(bit, word))
+	if (!test_bit_acquire(bit, word))
 		return 0;
 	return out_of_line_wait_on_bit(word, bit,
 				       bit_wait_io,
@@ -128,7 +128,7 @@ wait_on_bit_timeout(unsigned long *word,
 		    unsigned long timeout)
 {
 	might_sleep();
-	if (!test_bit(bit, word))
+	if (!test_bit_acquire(bit, word))
 		return 0;
 	return out_of_line_wait_on_bit_timeout(word, bit,
 					       bit_wait_timeout,
@@ -156,7 +156,7 @@ wait_on_bit_action(unsigned long *word,
 		   unsigned mode)
 {
 	might_sleep();
-	if (!test_bit(bit, word))
+	if (!test_bit_acquire(bit, word))
 		return 0;
 	return out_of_line_wait_on_bit(word, bit, action, mode);
 }
Index: linux-stable/kernel/sched/wait_bit.c
===================================================================
--- linux-stable.orig/kernel/sched/wait_bit.c	2022-10-17 20:39:55.000000000 +0200
+++ linux-stable/kernel/sched/wait_bit.c	2022-10-17 20:39:55.000000000 +0200
@@ -49,7 +49,7 @@ __wait_on_bit(struct wait_queue_head *wq
 		prepare_to_wait(wq_head, &wbq_entry->wq_entry, mode);
 		if (test_bit(wbq_entry->key.bit_nr, wbq_entry->key.flags))
 			ret = (*action)(&wbq_entry->key, mode);
-	} while (test_bit(wbq_entry->key.bit_nr, wbq_entry->key.flags) && !ret);
+	} while (test_bit_acquire(wbq_entry->key.bit_nr, wbq_entry->key.flags) && !ret);
 	finish_wait(wq_head, &wbq_entry->wq_entry);
 	return ret;
 }
Index: linux-stable/arch/alpha/include/asm/bitops.h
===================================================================
--- linux-stable.orig/arch/alpha/include/asm/bitops.h	2022-10-17 20:39:55.000000000 +0200
+++ linux-stable/arch/alpha/include/asm/bitops.h	2022-10-17 20:39:55.000000000 +0200
@@ -289,6 +289,13 @@ test_bit(int nr, const volatile void * a
 	return (1UL & (((const int *) addr)[nr >> 5] >> (nr & 31))) != 0UL;
 }
 
+static __always_inline bool
+test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	return 1UL & (smp_load_acquire(p) >> (nr & (BITS_PER_LONG-1)));
+}
+
 /*
  * ffz = Find First Zero in word. Undefined if no zero exists,
  * so code should check against ~0UL first..
Index: linux-stable/arch/hexagon/include/asm/bitops.h
===================================================================
--- linux-stable.orig/arch/hexagon/include/asm/bitops.h	2022-10-17 20:39:55.000000000 +0200
+++ linux-stable/arch/hexagon/include/asm/bitops.h	2022-10-17 20:39:55.000000000 +0200
@@ -186,7 +186,22 @@ static inline int __test_bit(int nr, con
 	return retval;
 }
 
+static inline int __test_bit_acquire(int nr, const volatile unsigned long *addr)
+{
+	int retval;
+
+	asm volatile(
+	"{P0 = tstbit(%1,%2); if (P0.new) %0 = #1; if (!P0.new) %0 = #0;}\n"
+	: "=&r" (retval)
+	: "r" (addr[BIT_WORD(nr)]), "r" (nr % BITS_PER_LONG)
+	: "p0", "memory"
+	);
+
+	return retval;
+}
+
 #define test_bit(nr, addr) __test_bit(nr, addr)
+#define test_bit_acquire(nr, addr) __test_bit_acquire(nr, addr)
 
 /*
  * ffz - find first zero in word.
Index: linux-stable/arch/ia64/include/asm/bitops.h
===================================================================
--- linux-stable.orig/arch/ia64/include/asm/bitops.h	2022-10-17 20:39:55.000000000 +0200
+++ linux-stable/arch/ia64/include/asm/bitops.h	2022-10-17 20:39:55.000000000 +0200
@@ -337,6 +337,13 @@ test_bit (int nr, const volatile void *a
 	return 1 & (((const volatile __u32 *) addr)[nr >> 5] >> (nr & 31));
 }
 
+static __always_inline bool
+test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	return 1UL & (smp_load_acquire(p) >> (nr & (BITS_PER_LONG-1)));
+}
+
 /**
  * ffz - find the first zero bit in a long word
  * @x: The long word to find the bit in
Index: linux-stable/arch/m68k/include/asm/bitops.h
===================================================================
--- linux-stable.orig/arch/m68k/include/asm/bitops.h	2022-10-17 20:39:55.000000000 +0200
+++ linux-stable/arch/m68k/include/asm/bitops.h	2022-10-17 20:39:55.000000000 +0200
@@ -153,6 +153,12 @@ static inline int test_bit(int nr, const
 	return (vaddr[nr >> 5] & (1UL << (nr & 31))) != 0;
 }
 
+static __always_inline bool
+test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	return 1UL & (smp_load_acquire(p) >> (nr & (BITS_PER_LONG-1)));
+}
 
 static inline int bset_reg_test_and_set_bit(int nr,
 					    volatile unsigned long *vaddr)
Index: linux-stable/arch/s390/include/asm/bitops.h
===================================================================
--- linux-stable.orig/arch/s390/include/asm/bitops.h	2022-10-17 20:39:55.000000000 +0200
+++ linux-stable/arch/s390/include/asm/bitops.h	2022-10-17 20:39:55.000000000 +0200
@@ -215,6 +215,13 @@ static inline int test_bit(unsigned long
 	return (*addr >> (nr & 7)) & 1;
 }
 
+static __always_inline bool
+test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	return 1UL & (smp_load_acquire(p) >> (nr & (BITS_PER_LONG-1)));
+}
+
 static inline int test_and_set_bit_lock(unsigned long nr,
 					volatile unsigned long *ptr)
 {
Index: linux-stable/arch/sh/include/asm/bitops-op32.h
===================================================================
--- linux-stable.orig/arch/sh/include/asm/bitops-op32.h	2022-10-17 20:39:55.000000000 +0200
+++ linux-stable/arch/sh/include/asm/bitops-op32.h	2022-10-17 20:39:55.000000000 +0200
@@ -140,4 +140,11 @@ static inline int test_bit(int nr, const
 	return 1UL & (addr[BIT_WORD(nr)] >> (nr & (BITS_PER_LONG-1)));
 }
 
+static __always_inline bool
+test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	return 1UL & (smp_load_acquire(p) >> (nr & (BITS_PER_LONG-1)));
+}
+
 #endif /* __ASM_SH_BITOPS_OP32_H */
Index: linux-stable/arch/arc/include/asm/bitops.h
===================================================================
--- linux-stable.orig/arch/arc/include/asm/bitops.h	2022-10-17 20:39:55.000000000 +0200
+++ linux-stable/arch/arc/include/asm/bitops.h	2022-10-17 20:39:55.000000000 +0200
@@ -254,6 +254,13 @@ test_bit(unsigned int nr, const volatile
 	return ((mask & *addr) != 0);
 }
 
+static __always_inline bool
+test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	return 1UL & (smp_load_acquire(p) >> (nr & (BITS_PER_LONG-1)));
+}
+
 #ifdef CONFIG_ISA_ARCOMPACT
 
 /*
Index: linux-stable/arch/h8300/include/asm/bitops.h
===================================================================
--- linux-stable.orig/arch/h8300/include/asm/bitops.h	2022-10-17 20:39:55.000000000 +0200
+++ linux-stable/arch/h8300/include/asm/bitops.h	2022-10-17 20:39:55.000000000 +0200
@@ -89,7 +89,8 @@ static inline int test_bit(int nr, const
 	return ret;
 }
 
-#define __test_bit(nr, addr) test_bit(nr, addr)
+#define __test_bit(nr, addr)		test_bit(nr, addr)
+#define test_bit_acquire(nr, addr)	test_bit(nr, addr)
 
 #define H8300_GEN_TEST_BITOP(FNNAME, OP)				\
 static inline int FNNAME(int nr, void *addr)				\
Index: linux-stable/arch/frv/include/asm/bitops.h
===================================================================
--- linux-stable.orig/arch/frv/include/asm/bitops.h	2022-10-17 20:39:55.000000000 +0200
+++ linux-stable/arch/frv/include/asm/bitops.h	2022-10-17 20:39:55.000000000 +0200
@@ -156,6 +156,13 @@ static inline int __test_bit(unsigned lo
  __constant_test_bit((nr),(addr)) : \
  __test_bit((nr),(addr)))
 
+static __always_inline bool
+test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	return 1UL & (smp_load_acquire(p) >> (nr & (BITS_PER_LONG-1)));
+}
+
 #include <asm-generic/bitops/find.h>
 
 /**
Index: linux-stable/arch/mn10300/include/asm/bitops.h
===================================================================
--- linux-stable.orig/arch/mn10300/include/asm/bitops.h	2022-10-17 20:39:46.000000000 +0200
+++ linux-stable/arch/mn10300/include/asm/bitops.h	2022-10-17 20:30:50.000000000 +0200
@@ -73,6 +73,13 @@ static inline int test_bit(unsigned long
 	return 1UL & (((const volatile unsigned int *) addr)[nr >> 5] >> (nr & 31));
 }
 
+static __always_inline bool
+test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	return 1UL & (smp_load_acquire(p) >> (nr & (BITS_PER_LONG-1)));
+}
+
 /*
  * change bit
  */

[PATCH] wait_on_bit: add an acquire memory barrier

[Mikulas Patocka]

This is backport of the upstream patch 8238b4579866b7c1bb99883cfe102a43db5506ff
for the stable branch 4.9

wait_on_bit: add an acquire memory barrier

There are several places in the kernel where wait_on_bit is not followed
by a memory barrier (for example, in drivers/md/dm-bufio.c:new_read).

On architectures with weak memory ordering, it may happen that memory
accesses that follow wait_on_bit are reordered before wait_on_bit and
they may return invalid data.

Fix this class of bugs by introducing a new function "test_bit_acquire"
that works like test_bit, but has acquire memory ordering semantics.

Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Acked-by: Will Deacon <will@kernel.org>
Cc: stable@vger.kernel.org
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

---
 arch/alpha/include/asm/bitops.h         |    7 +++++++
 arch/arc/include/asm/bitops.h           |    7 +++++++
 arch/frv/include/asm/bitops.h           |    7 +++++++
 arch/h8300/include/asm/bitops.h         |    3 ++-
 arch/hexagon/include/asm/bitops.h       |   15 +++++++++++++++
 arch/ia64/include/asm/bitops.h          |    7 +++++++
 arch/m68k/include/asm/bitops.h          |    6 ++++++
 arch/mn10300/include/asm/bitops.h       |    7 +++++++
 arch/s390/include/asm/bitops.h          |    7 +++++++
 arch/sh/include/asm/bitops-op32.h       |    7 +++++++
 arch/x86/include/asm/bitops.h           |   21 +++++++++++++++++++++
 include/asm-generic/bitops/non-atomic.h |   14 ++++++++++++++
 include/linux/buffer_head.h             |    2 +-
 include/linux/wait.h                    |    8 ++++----
 kernel/sched/wait.c                     |    2 +-
 15 files changed, 113 insertions(+), 7 deletions(-)

Index: linux-stable/arch/x86/include/asm/bitops.h
===================================================================
--- linux-stable.orig/arch/x86/include/asm/bitops.h	2022-10-17 20:43:20.000000000 +0200
+++ linux-stable/arch/x86/include/asm/bitops.h	2022-10-17 20:43:20.000000000 +0200
@@ -314,6 +314,20 @@ static __always_inline bool constant_tes
 		(addr[nr >> _BITOPS_LONG_SHIFT])) != 0;
 }
 
+static __always_inline bool constant_test_bit_acquire(long nr, const volatile unsigned long *addr)
+{
+	bool oldbit;
+
+	asm volatile("testb %2,%1"
+		     CC_SET(nz)
+		     : CC_OUT(nz) (oldbit)
+		     : "m" (((unsigned char *)addr)[nr >> 3]),
+		       "i" (1 << (nr & 7))
+		     :"memory");
+
+	return oldbit;
+}
+
 static __always_inline bool variable_test_bit(long nr, volatile const unsigned long *addr)
 {
 	bool oldbit;
@@ -340,6 +354,13 @@ static bool test_bit(int nr, const volat
 	 ? constant_test_bit((nr), (addr))	\
 	 : variable_test_bit((nr), (addr)))
 
+static __always_inline bool
+test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	return __builtin_constant_p(nr) ? constant_test_bit_acquire(nr, addr) :
+					  variable_test_bit(nr, addr);
+}
+
 /**
  * __ffs - find first set bit in word
  * @word: The word to search
Index: linux-stable/include/asm-generic/bitops/non-atomic.h
===================================================================
--- linux-stable.orig/include/asm-generic/bitops/non-atomic.h	2022-10-17 20:43:20.000000000 +0200
+++ linux-stable/include/asm-generic/bitops/non-atomic.h	2022-10-17 20:43:20.000000000 +0200
@@ -2,6 +2,7 @@
 #define _ASM_GENERIC_BITOPS_NON_ATOMIC_H_
 
 #include <asm/types.h>
+#include <asm/barrier.h>
 
 /**
  * __set_bit - Set a bit in memory
@@ -105,4 +106,17 @@ static inline int test_bit(int nr, const
 	return 1UL & (addr[BIT_WORD(nr)] >> (nr & (BITS_PER_LONG-1)));
 }
 
+/**
+ * arch_test_bit_acquire - Determine, with acquire semantics, whether a bit is set
+ * @nr: bit number to test
+ * @addr: Address to start counting from
+ */
+static __always_inline bool
+arch_test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	return 1UL & (smp_load_acquire(p) >> (nr & (BITS_PER_LONG-1)));
+}
+#define test_bit_acquire arch_test_bit_acquire
+
 #endif /* _ASM_GENERIC_BITOPS_NON_ATOMIC_H_ */
Index: linux-stable/include/linux/buffer_head.h
===================================================================
--- linux-stable.orig/include/linux/buffer_head.h	2022-10-17 20:43:20.000000000 +0200
+++ linux-stable/include/linux/buffer_head.h	2022-10-17 20:43:20.000000000 +0200
@@ -162,7 +162,7 @@ static __always_inline int buffer_uptoda
 	 * make it consistent with folio_test_uptodate
 	 * pairs with smp_mb__before_atomic in set_buffer_uptodate
 	 */
-	return (smp_load_acquire(&bh->b_state) & (1UL << BH_Uptodate)) != 0;
+	return test_bit_acquire(BH_Uptodate, &bh->b_state);
 }
 
 #define bh_offset(bh)		((unsigned long)(bh)->b_data & ~PAGE_MASK)
Index: linux-stable/include/linux/wait.h
===================================================================
--- linux-stable.orig/include/linux/wait.h	2022-10-17 20:43:20.000000000 +0200
+++ linux-stable/include/linux/wait.h	2022-10-17 20:43:20.000000000 +0200
@@ -1066,7 +1066,7 @@ static inline int
 wait_on_bit(unsigned long *word, int bit, unsigned mode)
 {
 	might_sleep();
-	if (!test_bit(bit, word))
+	if (!test_bit_acquire(bit, word))
 		return 0;
 	return out_of_line_wait_on_bit(word, bit,
 				       bit_wait,
@@ -1091,7 +1091,7 @@ static inline int
 wait_on_bit_io(unsigned long *word, int bit, unsigned mode)
 {
 	might_sleep();
-	if (!test_bit(bit, word))
+	if (!test_bit_acquire(bit, word))
 		return 0;
 	return out_of_line_wait_on_bit(word, bit,
 				       bit_wait_io,
@@ -1118,7 +1118,7 @@ wait_on_bit_timeout(unsigned long *word,
 		    unsigned long timeout)
 {
 	might_sleep();
-	if (!test_bit(bit, word))
+	if (!test_bit_acquire(bit, word))
 		return 0;
 	return out_of_line_wait_on_bit_timeout(word, bit,
 					       bit_wait_timeout,
@@ -1146,7 +1146,7 @@ wait_on_bit_action(unsigned long *word,
 		   unsigned mode)
 {
 	might_sleep();
-	if (!test_bit(bit, word))
+	if (!test_bit_acquire(bit, word))
 		return 0;
 	return out_of_line_wait_on_bit(word, bit, action, mode);
 }
Index: linux-stable/kernel/sched/wait.c
===================================================================
--- linux-stable.orig/kernel/sched/wait.c	2022-10-17 20:43:20.000000000 +0200
+++ linux-stable/kernel/sched/wait.c	2022-10-17 20:43:20.000000000 +0200
@@ -389,7 +389,7 @@ __wait_on_bit(wait_queue_head_t *wq, str
 		prepare_to_wait(wq, &q->wait, mode);
 		if (test_bit(q->key.bit_nr, q->key.flags))
 			ret = (*action)(&q->key, mode);
-	} while (test_bit(q->key.bit_nr, q->key.flags) && !ret);
+	} while (test_bit_acquire(q->key.bit_nr, q->key.flags) && !ret);
 	finish_wait(wq, &q->wait);
 	return ret;
 }
Index: linux-stable/arch/alpha/include/asm/bitops.h
===================================================================
--- linux-stable.orig/arch/alpha/include/asm/bitops.h	2022-10-17 20:43:20.000000000 +0200
+++ linux-stable/arch/alpha/include/asm/bitops.h	2022-10-17 20:43:20.000000000 +0200
@@ -288,6 +288,13 @@ test_bit(int nr, const volatile void * a
 	return (1UL & (((const int *) addr)[nr >> 5] >> (nr & 31))) != 0UL;
 }
 
+static __always_inline bool
+test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	return 1UL & (smp_load_acquire(p) >> (nr & (BITS_PER_LONG-1)));
+}
+
 /*
  * ffz = Find First Zero in word. Undefined if no zero exists,
  * so code should check against ~0UL first..
Index: linux-stable/arch/hexagon/include/asm/bitops.h
===================================================================
--- linux-stable.orig/arch/hexagon/include/asm/bitops.h	2022-10-17 20:43:20.000000000 +0200
+++ linux-stable/arch/hexagon/include/asm/bitops.h	2022-10-17 20:43:20.000000000 +0200
@@ -186,7 +186,22 @@ static inline int __test_bit(int nr, con
 	return retval;
 }
 
+static inline int __test_bit_acquire(int nr, const volatile unsigned long *addr)
+{
+	int retval;
+
+	asm volatile(
+	"{P0 = tstbit(%1,%2); if (P0.new) %0 = #1; if (!P0.new) %0 = #0;}\n"
+	: "=&r" (retval)
+	: "r" (addr[BIT_WORD(nr)]), "r" (nr % BITS_PER_LONG)
+	: "p0", "memory"
+	);
+
+	return retval;
+}
+
 #define test_bit(nr, addr) __test_bit(nr, addr)
+#define test_bit_acquire(nr, addr) __test_bit_acquire(nr, addr)
 
 /*
  * ffz - find first zero in word.
Index: linux-stable/arch/ia64/include/asm/bitops.h
===================================================================
--- linux-stable.orig/arch/ia64/include/asm/bitops.h	2022-10-17 20:43:20.000000000 +0200
+++ linux-stable/arch/ia64/include/asm/bitops.h	2022-10-17 20:43:20.000000000 +0200
@@ -336,6 +336,13 @@ test_bit (int nr, const volatile void *a
 	return 1 & (((const volatile __u32 *) addr)[nr >> 5] >> (nr & 31));
 }
 
+static __always_inline bool
+test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	return 1UL & (smp_load_acquire(p) >> (nr & (BITS_PER_LONG-1)));
+}
+
 /**
  * ffz - find the first zero bit in a long word
  * @x: The long word to find the bit in
Index: linux-stable/arch/m68k/include/asm/bitops.h
===================================================================
--- linux-stable.orig/arch/m68k/include/asm/bitops.h	2022-10-17 20:43:20.000000000 +0200
+++ linux-stable/arch/m68k/include/asm/bitops.h	2022-10-17 20:43:20.000000000 +0200
@@ -153,6 +153,12 @@ static inline int test_bit(int nr, const
 	return (vaddr[nr >> 5] & (1UL << (nr & 31))) != 0;
 }
 
+static __always_inline bool
+test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	return 1UL & (smp_load_acquire(p) >> (nr & (BITS_PER_LONG-1)));
+}
 
 static inline int bset_reg_test_and_set_bit(int nr,
 					    volatile unsigned long *vaddr)
Index: linux-stable/arch/s390/include/asm/bitops.h
===================================================================
--- linux-stable.orig/arch/s390/include/asm/bitops.h	2022-10-17 20:43:20.000000000 +0200
+++ linux-stable/arch/s390/include/asm/bitops.h	2022-10-17 20:43:20.000000000 +0200
@@ -270,6 +270,13 @@ static inline int test_bit(unsigned long
 	return (*addr >> (nr & 7)) & 1;
 }
 
+static __always_inline bool
+test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	return 1UL & (smp_load_acquire(p) >> (nr & (BITS_PER_LONG-1)));
+}
+
 static inline int test_and_set_bit_lock(unsigned long nr,
 					volatile unsigned long *ptr)
 {
Index: linux-stable/arch/sh/include/asm/bitops-op32.h
===================================================================
--- linux-stable.orig/arch/sh/include/asm/bitops-op32.h	2022-10-17 20:43:20.000000000 +0200
+++ linux-stable/arch/sh/include/asm/bitops-op32.h	2022-10-17 20:43:20.000000000 +0200
@@ -139,4 +139,11 @@ static inline int test_bit(int nr, const
 	return 1UL & (addr[BIT_WORD(nr)] >> (nr & (BITS_PER_LONG-1)));
 }
 
+static __always_inline bool
+test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	return 1UL & (smp_load_acquire(p) >> (nr & (BITS_PER_LONG-1)));
+}
+
 #endif /* __ASM_SH_BITOPS_OP32_H */
Index: linux-stable/arch/arc/include/asm/bitops.h
===================================================================
--- linux-stable.orig/arch/arc/include/asm/bitops.h	2022-10-17 20:43:20.000000000 +0200
+++ linux-stable/arch/arc/include/asm/bitops.h	2022-10-17 20:43:20.000000000 +0200
@@ -254,6 +254,13 @@ test_bit(unsigned int nr, const volatile
 	return ((mask & *addr) != 0);
 }
 
+static __always_inline bool
+test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	return 1UL & (smp_load_acquire(p) >> (nr & (BITS_PER_LONG-1)));
+}
+
 #ifdef CONFIG_ISA_ARCOMPACT
 
 /*
Index: linux-stable/arch/h8300/include/asm/bitops.h
===================================================================
--- linux-stable.orig/arch/h8300/include/asm/bitops.h	2022-10-17 20:43:20.000000000 +0200
+++ linux-stable/arch/h8300/include/asm/bitops.h	2022-10-17 20:43:20.000000000 +0200
@@ -88,7 +88,8 @@ static inline int test_bit(int nr, const
 	return ret;
 }
 
-#define __test_bit(nr, addr) test_bit(nr, addr)
+#define __test_bit(nr, addr)		test_bit(nr, addr)
+#define test_bit_acquire(nr, addr)	test_bit(nr, addr)
 
 #define H8300_GEN_TEST_BITOP(FNNAME, OP)				\
 static inline int FNNAME(int nr, void *addr)				\
Index: linux-stable/arch/frv/include/asm/bitops.h
===================================================================
--- linux-stable.orig/arch/frv/include/asm/bitops.h	2022-10-17 20:43:20.000000000 +0200
+++ linux-stable/arch/frv/include/asm/bitops.h	2022-10-17 20:43:20.000000000 +0200
@@ -156,6 +156,13 @@ static inline int __test_bit(unsigned lo
  __constant_test_bit((nr),(addr)) : \
  __test_bit((nr),(addr)))
 
+static __always_inline bool
+test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	return 1UL & (smp_load_acquire(p) >> (nr & (BITS_PER_LONG-1)));
+}
+
 #include <asm-generic/bitops/find.h>
 
 /**
Index: linux-stable/arch/mn10300/include/asm/bitops.h
===================================================================
--- linux-stable.orig/arch/mn10300/include/asm/bitops.h	2022-10-17 20:43:20.000000000 +0200
+++ linux-stable/arch/mn10300/include/asm/bitops.h	2022-10-17 20:43:20.000000000 +0200
@@ -73,6 +73,13 @@ static inline int test_bit(unsigned long
 	return 1UL & (((const volatile unsigned int *) addr)[nr >> 5] >> (nr & 31));
 }
 
+static __always_inline bool
+test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	return 1UL & (smp_load_acquire(p) >> (nr & (BITS_PER_LONG-1)));
+}
+
 /*
  * change bit
  */

Re: backport of patches 8238b4579866b7c1bb99883cfe102a43db5506ff and d6ffe6067a54972564552ea45d320fb98db1ac5e

[Greg KH]

On Tue, Oct 18, 2022 at 07:36:22AM -0400, Mikulas Patocka wrote:
> 
> 
> On Tue, 11 Oct 2022, Greg KH wrote:
> 
> > On Tue, Oct 11, 2022 at 05:48:26AM -0400, Mikulas Patocka wrote:
> > > 
> > > 
> > > On Mon, 10 Oct 2022, Greg KH wrote:
> > > 
> > > > Nope, these cause loads of breakages.  See
> > > > https://lore.kernel.org/r/09eca44e-4d91-a060-d48c-d0aa41ac5045@roeck-us.net
> > > > for one such example, and I know kbuild sent you other build problems.
> > > > I'll drop all of these from the stable trees now.  Please feel free to
> > > > resend them when you have the build issues worked out.
> > > > 
> > > > thanks,
> > > > 
> > > > greg k-h
> > > 
> > > I don't have cross compilers for all the architectures that Linux 
> > > supports. Is there some way how to have the patch compile-tested before I 
> > > send it to you?
> > 
> > You can download those compilers from kernel.org, they are all available
> > there.
> 
> OK. I downloaded cross compilers from 
> https://mirrors.edge.kernel.org/pub/tools/crosstool/ and compile-tested 
> the patches with all possible architectures.
> 
> Here I'm sending new versions.

But don't you need 2 patches, not just 1, to be applied?

Please resend a set of series, one series per stable kernel branch, to
make it more obvious what to do.  Your thread here is very confusing.

See the stable mailing list archives for lots of examples of how to do
this properly, here are 2 good examples:
	https://lore.kernel.org/r/20221019125303.2845522-1-conor.dooley@microchip.com
	https://lore.kernel.org/r/20221019125209.2844943-1-conor.dooley@microchip.com

thanks,

greg k-h

Re: backport of patches 8238b4579866b7c1bb99883cfe102a43db5506ff and d6ffe6067a54972564552ea45d320fb98db1ac5e

[Mikulas Patocka]

On Wed, 26 Oct 2022, Greg KH wrote:

> On Tue, Oct 18, 2022 at 07:36:22AM -0400, Mikulas Patocka wrote:
> > 
> > 
> > On Tue, 11 Oct 2022, Greg KH wrote:
> > 
> > > On Tue, Oct 11, 2022 at 05:48:26AM -0400, Mikulas Patocka wrote:
> > > > 
> > > > 
> > > > On Mon, 10 Oct 2022, Greg KH wrote:
> > > > 
> > > > > Nope, these cause loads of breakages.  See
> > > > > https://lore.kernel.org/r/09eca44e-4d91-a060-d48c-d0aa41ac5045@roeck-us.net
> > > > > for one such example, and I know kbuild sent you other build problems.
> > > > > I'll drop all of these from the stable trees now.  Please feel free to
> > > > > resend them when you have the build issues worked out.
> > > > > 
> > > > > thanks,
> > > > > 
> > > > > greg k-h
> > > > 
> > > > I don't have cross compilers for all the architectures that Linux 
> > > > supports. Is there some way how to have the patch compile-tested before I 
> > > > send it to you?
> > > 
> > > You can download those compilers from kernel.org, they are all available
> > > there.
> > 
> > OK. I downloaded cross compilers from 
> > https://mirrors.edge.kernel.org/pub/tools/crosstool/ and compile-tested 
> > the patches with all possible architectures.
> > 
> > Here I'm sending new versions.
> 
> But don't you need 2 patches, not just 1, to be applied?

Just one patch is sufficient.

The upstream patch 8238b4579866b7c1bb99883cfe102a43db5506ff fixes a bug 
and the patch d6ffe6067a54972564552ea45d320fb98db1ac5e fixes compile 
failures triggered by 8238b4579866b7c1bb99883cfe102a43db5506ff on some 
architectures.

For simplicity of making and testing the stable branch patches I folded 
these changes into just one patch - that fixes the bug and fixes compile 
failures as well.

> Please resend a set of series, one series per stable kernel branch, to
> make it more obvious what to do.  Your thread here is very confusing.

I'll resend it, but except for the subject line I don't know what have I 
done wrong.

Mikulas

> See the stable mailing list archives for lots of examples of how to do
> this properly, here are 2 good examples:
> 	https://lore.kernel.org/r/20221019125303.2845522-1-conor.dooley@microchip.com
> 	https://lore.kernel.org/r/20221019125209.2844943-1-conor.dooley@microchip.com
> 
> thanks,
> 
> greg k-h
> 

Re: backport of patches 8238b4579866b7c1bb99883cfe102a43db5506ff and d6ffe6067a54972564552ea45d320fb98db1ac5e

[Greg KH]

On Thu, Oct 27, 2022 at 07:45:52AM -0400, Mikulas Patocka wrote:
> 
> 
> On Wed, 26 Oct 2022, Greg KH wrote:
> 
> > On Tue, Oct 18, 2022 at 07:36:22AM -0400, Mikulas Patocka wrote:
> > > 
> > > 
> > > On Tue, 11 Oct 2022, Greg KH wrote:
> > > 
> > > > On Tue, Oct 11, 2022 at 05:48:26AM -0400, Mikulas Patocka wrote:
> > > > > 
> > > > > 
> > > > > On Mon, 10 Oct 2022, Greg KH wrote:
> > > > > 
> > > > > > Nope, these cause loads of breakages.  See
> > > > > > https://lore.kernel.org/r/09eca44e-4d91-a060-d48c-d0aa41ac5045@roeck-us.net
> > > > > > for one such example, and I know kbuild sent you other build problems.
> > > > > > I'll drop all of these from the stable trees now.  Please feel free to
> > > > > > resend them when you have the build issues worked out.
> > > > > > 
> > > > > > thanks,
> > > > > > 
> > > > > > greg k-h
> > > > > 
> > > > > I don't have cross compilers for all the architectures that Linux 
> > > > > supports. Is there some way how to have the patch compile-tested before I 
> > > > > send it to you?
> > > > 
> > > > You can download those compilers from kernel.org, they are all available
> > > > there.
> > > 
> > > OK. I downloaded cross compilers from 
> > > https://mirrors.edge.kernel.org/pub/tools/crosstool/ and compile-tested 
> > > the patches with all possible architectures.
> > > 
> > > Here I'm sending new versions.
> > 
> > But don't you need 2 patches, not just 1, to be applied?
> 
> Just one patch is sufficient.
> 
> The upstream patch 8238b4579866b7c1bb99883cfe102a43db5506ff fixes a bug 
> and the patch d6ffe6067a54972564552ea45d320fb98db1ac5e fixes compile 
> failures triggered by 8238b4579866b7c1bb99883cfe102a43db5506ff on some 
> architectures.
> 
> For simplicity of making and testing the stable branch patches I folded 
> these changes into just one patch - that fixes the bug and fixes compile 
> failures as well.

No, please do not do that.  We want both commits at once, not a "fixed
up" change, right?  Otherwise our tools will want to apply the second
one as it is insisting that a fix is still needed.

> > Please resend a set of series, one series per stable kernel branch, to
> > make it more obvious what to do.  Your thread here is very confusing.
> 
> I'll resend it, but except for the subject line I don't know what have I 
> done wrong.

Subject line is everything :)

As is the text in the body, I would have had to remove that from your
last one.  See the examples on the list for how to make this easy for us
to apply.

thanks,

greg k-h

Re: backport of patches 8238b4579866b7c1bb99883cfe102a43db5506ff and d6ffe6067a54972564552ea45d320fb98db1ac5e

[Mikulas Patocka]

On Thu, 27 Oct 2022, Greg KH wrote:
>
> > For simplicity of making and testing the stable branch patches I folded 
> > these changes into just one patch - that fixes the bug and fixes compile 
> > failures as well.
> 
> No, please do not do that.  We want both commits at once, not a "fixed
> up" change, right?  Otherwise our tools will want to apply the second
> one as it is insisting that a fix is still needed.

OK - so I split the patches in two and resent them.

Mikulas

Re: [PATCH] wait_on_bit: add an acquire memory barrier

[Mikulas Patocka]

On Sat, 27 Aug 2022, Ard Biesheuvel wrote:

> On Sat, 27 Aug 2022 at 08:32, Ard Biesheuvel <ardb@kernel.org> wrote:
> >
> > On Fri, 26 Aug 2022 at 21:10, Mikulas Patocka <mpatocka@redhat.com> wrote:
> > >
> > >
> > >
> > > On Fri, 26 Aug 2022, Ard Biesheuvel wrote:
> > >
> > > > Could you try booting with earlycon?
> > > >
> > > > Just 'earlycon' and if that does not help,
> > >
> > > It doesn't help.
> > >
> > > > 'earlycon=uart8250,mmio32,<uart PA>' [IIRC, mcbin uses 16550
> > > > compatible UARTs, right?]
> > >
> > > mcbin is the host system (running a stable kernel fine). The crash happens
> > > in a virtual machine. The vm uses /dev/ttyAMA0 as a console:
> > >
> > > Serial: AMBA PL011 UART driver
> > > 9000000.pl011: ttyAMA0 at MMIO 0x9000000 (irq = 45, base_baud = 0) is a PL011 rev1
> > > printk: console [ttyAMA0] enabled
> > >
> > > I tried earlycon=pl011,mmio32,0x9000000 - but it doesn't help, it hangs
> > > without printing anything.
> > >
> >
> > If you are using pl011, you should drop the mmio32 - it only takes a
> > physical address (and optionally baud rate etc, but QEMU doesn't need
> > those)
> 
> Could you try the diff below please?
> 
> --- a/arch/arm64/kernel/head.S
> +++ b/arch/arm64/kernel/head.S
> @@ -371,7 +371,9 @@ SYM_FUNC_END(create_idmap)
>  SYM_FUNC_START_LOCAL(create_kernel_mapping)
>         adrp    x0, init_pg_dir
>         mov_q   x5, KIMAGE_VADDR                // compile time __va(_text)
> +#ifdef CONFIG_RELOCATABLE
>         add     x5, x5, x23                     // add KASLR displacement
> +#endif
>         adrp    x6, _end                        // runtime __pa(_end)
>         adrp    x3, _text                       // runtime __pa(_text)
>         sub     x6, x6, x3                      // _end - _text
> 

Yes - this patch fixes the crash.

Mikulas

Re: [PATCH] wait_on_bit: add an acquire memory barrier

[Ard Biesheuvel]

On Sat, 27 Aug 2022 at 08:32, Ard Biesheuvel <ardb@kernel.org> wrote:
>
> On Fri, 26 Aug 2022 at 21:10, Mikulas Patocka <mpatocka@redhat.com> wrote:
> >
> >
> >
> > On Fri, 26 Aug 2022, Ard Biesheuvel wrote:
> >
> > > Could you try booting with earlycon?
> > >
> > > Just 'earlycon' and if that does not help,
> >
> > It doesn't help.
> >
> > > 'earlycon=uart8250,mmio32,<uart PA>' [IIRC, mcbin uses 16550
> > > compatible UARTs, right?]
> >
> > mcbin is the host system (running a stable kernel fine). The crash happens
> > in a virtual machine. The vm uses /dev/ttyAMA0 as a console:
> >
> > Serial: AMBA PL011 UART driver
> > 9000000.pl011: ttyAMA0 at MMIO 0x9000000 (irq = 45, base_baud = 0) is a PL011 rev1
> > printk: console [ttyAMA0] enabled
> >
> > I tried earlycon=pl011,mmio32,0x9000000 - but it doesn't help, it hangs
> > without printing anything.
> >
>
> If you are using pl011, you should drop the mmio32 - it only takes a
> physical address (and optionally baud rate etc, but QEMU doesn't need
> those)

Could you try the diff below please?

--- a/arch/arm64/kernel/head.S
+++ b/arch/arm64/kernel/head.S
@@ -371,7 +371,9 @@ SYM_FUNC_END(create_idmap)
 SYM_FUNC_START_LOCAL(create_kernel_mapping)
        adrp    x0, init_pg_dir
        mov_q   x5, KIMAGE_VADDR                // compile time __va(_text)
+#ifdef CONFIG_RELOCATABLE
        add     x5, x5, x23                     // add KASLR displacement
+#endif
        adrp    x6, _end                        // runtime __pa(_end)
        adrp    x3, _text                       // runtime __pa(_text)
        sub     x6, x6, x3                      // _end - _text

Re: [PATCH] wait_on_bit: add an acquire memory barrier

[Ard Biesheuvel]

On Fri, 26 Aug 2022 at 21:10, Mikulas Patocka <mpatocka@redhat.com> wrote:
>
>
>
> On Fri, 26 Aug 2022, Ard Biesheuvel wrote:
>
> > Could you try booting with earlycon?
> >
> > Just 'earlycon' and if that does not help,
>
> It doesn't help.
>
> > 'earlycon=uart8250,mmio32,<uart PA>' [IIRC, mcbin uses 16550
> > compatible UARTs, right?]
>
> mcbin is the host system (running a stable kernel fine). The crash happens
> in a virtual machine. The vm uses /dev/ttyAMA0 as a console:
>
> Serial: AMBA PL011 UART driver
> 9000000.pl011: ttyAMA0 at MMIO 0x9000000 (irq = 45, base_baud = 0) is a PL011 rev1
> printk: console [ttyAMA0] enabled
>
> I tried earlycon=pl011,mmio32,0x9000000 - but it doesn't help, it hangs
> without printing anything.
>

If you are using pl011, you should drop the mmio32 - it only takes a
physical address (and optionally baud rate etc, but QEMU doesn't need
those)

Re: [PATCH] wait_on_bit: add an acquire memory barrier

[Mikulas Patocka]

On Fri, 26 Aug 2022, Ard Biesheuvel wrote:

> Could you try booting with earlycon?
> 
> Just 'earlycon' and if that does not help,

It doesn't help.

> 'earlycon=uart8250,mmio32,<uart PA>' [IIRC, mcbin uses 16550
> compatible UARTs, right?]

mcbin is the host system (running a stable kernel fine). The crash happens 
in a virtual machine. The vm uses /dev/ttyAMA0 as a console:

Serial: AMBA PL011 UART driver
9000000.pl011: ttyAMA0 at MMIO 0x9000000 (irq = 45, base_baud = 0) is a PL011 rev1
printk: console [ttyAMA0] enabled

I tried earlycon=pl011,mmio32,0x9000000 - but it doesn't help, it hangs 
without printing anything.

Mikulas

Re: [PATCH] wait_on_bit: add an acquire memory barrier

[Ard Biesheuvel]

On Fri, 26 Aug 2022 at 20:25, Mikulas Patocka <mpatocka@redhat.com> wrote:
>
>
>
> On Fri, 26 Aug 2022, Will Deacon wrote:
>
> > > So, the bad commit is aacd149b62382c63911060b8f64c1e3d89bd405a ("arm64:
> > > head: avoid relocating the kernel twice for KASLR").
> >
> > Thanks. Any chance you could give this a go, please?
> >
> > https://lore.kernel.org/r/20220826164800.2059148-1-ardb@kernel.org
> >
> > Will
>
> This doesn't help.
>

Could you try booting with earlycon?

Just 'earlycon' and if that does not help,
'earlycon=uart8250,mmio32,<uart PA>' [IIRC, mcbin uses 16550
compatible UARTs, right?]

Re: [PATCH] wait_on_bit: add an acquire memory barrier

[Mikulas Patocka]

On Fri, 26 Aug 2022, Will Deacon wrote:

> > So, the bad commit is aacd149b62382c63911060b8f64c1e3d89bd405a ("arm64: 
> > head: avoid relocating the kernel twice for KASLR").
> 
> Thanks. Any chance you could give this a go, please?
> 
> https://lore.kernel.org/r/20220826164800.2059148-1-ardb@kernel.org
> 
> Will

This doesn't help.

Mikulas

Re: [PATCH] wait_on_bit: add an acquire memory barrier

[Will Deacon]

On Fri, Aug 26, 2022 at 10:08:42AM -0400, Mikulas Patocka wrote:
> On Fri, 26 Aug 2022, Mikulas Patocka wrote:
> > On Fri, 26 Aug 2022, Will Deacon wrote:
> > > On Thu, Aug 25, 2022 at 05:03:40PM -0400, Mikulas Patocka wrote:
> > > > For me, the kernel 6.0-rc2 doesn't boot in an arm64 virtual machine at all 
> > > > (with or without this patch), so I only compile-tested it on arm64. I have 
> > > > to bisect it.
> > > 
> > > It's working fine for me and I haven't had any other reports that it's not
> > > booting. Please could you share some more details about your setup so we
> > > can try to reproduce the problem?
> > 
> > I'm bisecting it now. I'll post the offending commit when I'm done.
> 
> So, the bad commit is aacd149b62382c63911060b8f64c1e3d89bd405a ("arm64: 
> head: avoid relocating the kernel twice for KASLR").

Thanks. Any chance you could give this a go, please?

https://lore.kernel.org/r/20220826164800.2059148-1-ardb@kernel.org

Will

Re: [PATCH] wait_on_bit: add an acquire memory barrier

[Mikulas Patocka]

On Fri, 26 Aug 2022, Mikulas Patocka wrote:

> 
> 
> On Fri, 26 Aug 2022, Will Deacon wrote:
> 
> > On Thu, Aug 25, 2022 at 05:03:40PM -0400, Mikulas Patocka wrote:
> > > 
> > > For me, the kernel 6.0-rc2 doesn't boot in an arm64 virtual machine at all 
> > > (with or without this patch), so I only compile-tested it on arm64. I have 
> > > to bisect it.
> > 
> > It's working fine for me and I haven't had any other reports that it's not
> > booting. Please could you share some more details about your setup so we
> > can try to reproduce the problem?
> 
> I'm bisecting it now. I'll post the offending commit when I'm done.

So, the bad commit is aacd149b62382c63911060b8f64c1e3d89bd405a ("arm64: 
head: avoid relocating the kernel twice for KASLR").

> It gets stuck without printing anything at this point:
> Loading Linux 6.0.0-rc2 ...
> Loading initial ramdisk ...
> EFI stub: Booting Linux Kernel...
> EFI stub: Using DTB from configuration table
> EFI stub: Exiting boot services...
> 
> I uploaded my .config here: 
> https://people.redhat.com/~mpatocka/testcases/arm64-config/config-6.0.0-rc2 
> so you can try it on your own.
> 
> The host system is MacchiatoBIN board with Debian 10.12.

Mikulas

Re: [PATCH] wait_on_bit: add an acquire memory barrier

[Mikulas Patocka]

On Fri, 26 Aug 2022, Will Deacon wrote:

> On Thu, Aug 25, 2022 at 05:03:40PM -0400, Mikulas Patocka wrote:
> > Here I reworked your patch, so that test_bit_acquire is defined just like 
> > test_bit. There's some code duplication (in 
> > include/asm-generic/bitops/generic-non-atomic.h and in 
> > arch/x86/include/asm/bitops.h), but that duplication exists in the 
> > test_bit function too.
> > 
> > I tested it on x86-64 and arm64. On x86-64 it generates the "bt" 
> > instruction for variable-bit test and "shr; and $1" for constant bit test. 
> > On arm64 it generates the "ldar" instruction for both constant and 
> > variable bit test.
> > 
> > For me, the kernel 6.0-rc2 doesn't boot in an arm64 virtual machine at all 
> > (with or without this patch), so I only compile-tested it on arm64. I have 
> > to bisect it.
> 
> It's working fine for me and I haven't had any other reports that it's not
> booting. Please could you share some more details about your setup so we
> can try to reproduce the problem?

I'm bisecting it now. I'll post the offending commit when I'm done.

It gets stuck without printing anything at this point:
Loading Linux 6.0.0-rc2 ...
Loading initial ramdisk ...
EFI stub: Booting Linux Kernel...
EFI stub: Using DTB from configuration table
EFI stub: Exiting boot services...

I uploaded my .config here: 
https://people.redhat.com/~mpatocka/testcases/arm64-config/config-6.0.0-rc2 
so you can try it on your own.

The host system is MacchiatoBIN board with Debian 10.12.

> This looks good to me, thanks for doing it! Just one thing that jumped out
> at me:
> 
> > Index: linux-2.6/include/linux/buffer_head.h
> > ===================================================================
> > --- linux-2.6.orig/include/linux/buffer_head.h
> > +++ linux-2.6/include/linux/buffer_head.h
> > @@ -156,7 +156,7 @@ static __always_inline int buffer_uptoda
> >  	 * make it consistent with folio_test_uptodate
> >  	 * pairs with smp_mb__before_atomic in set_buffer_uptodate
> >  	 */
> > -	return (smp_load_acquire(&bh->b_state) & (1UL << BH_Uptodate)) != 0;
> > +	return test_bit_acquire(BH_Uptodate, &bh->b_state);
> 
> Do you think it would be worth adding set_bit_release() and then relaxing
> set_buffer_uptodate() to use that rather than the smp_mb__before_atomic()?
> 
> Will

Yes, we could add this (but it would be better to add it in a separate 
patch, so that backporting of the origianal patch to -stable is easier).

Mikulas

Re: [PATCH] wait_on_bit: add an acquire memory barrier

[Will Deacon]

On Thu, Aug 25, 2022 at 05:03:40PM -0400, Mikulas Patocka wrote:
> Here I reworked your patch, so that test_bit_acquire is defined just like 
> test_bit. There's some code duplication (in 
> include/asm-generic/bitops/generic-non-atomic.h and in 
> arch/x86/include/asm/bitops.h), but that duplication exists in the 
> test_bit function too.
> 
> I tested it on x86-64 and arm64. On x86-64 it generates the "bt" 
> instruction for variable-bit test and "shr; and $1" for constant bit test. 
> On arm64 it generates the "ldar" instruction for both constant and 
> variable bit test.
> 
> For me, the kernel 6.0-rc2 doesn't boot in an arm64 virtual machine at all 
> (with or without this patch), so I only compile-tested it on arm64. I have 
> to bisect it.

It's working fine for me and I haven't had any other reports that it's not
booting. Please could you share some more details about your setup so we
can try to reproduce the problem?

> From: Mikulas Patocka <mpatocka@redhat.com>
> 
> There are several places in the kernel where wait_on_bit is not followed
> by a memory barrier (for example, in drivers/md/dm-bufio.c:new_read). On
> architectures with weak memory ordering, it may happen that memory
> accesses that follow wait_on_bit are reordered before wait_on_bit and they
> may return invalid data.
> 
> Fix this class of bugs by introducing a new function "test_bit_acquire"
> that works like test_bit, but has acquire memory ordering semantics.
> 
> Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
> Cc: stable@vger.kernel.org
> 
>  arch/x86/include/asm/bitops.h                            |   13 +++++++++++++
>  include/asm-generic/bitops/generic-non-atomic.h          |   14 ++++++++++++++
>  include/asm-generic/bitops/instrumented-non-atomic.h     |   12 ++++++++++++
>  include/asm-generic/bitops/non-atomic.h                  |    1 +
>  include/asm-generic/bitops/non-instrumented-non-atomic.h |    1 +
>  include/linux/bitops.h                                   |    1 +
>  include/linux/buffer_head.h                              |    2 +-
>  include/linux/wait_bit.h                                 |    8 ++++----
>  kernel/sched/wait_bit.c                                  |    2 +-
>  9 files changed, 48 insertions(+), 6 deletions(-)

This looks good to me, thanks for doing it! Just one thing that jumped out
at me:

> Index: linux-2.6/include/linux/buffer_head.h
> ===================================================================
> --- linux-2.6.orig/include/linux/buffer_head.h
> +++ linux-2.6/include/linux/buffer_head.h
> @@ -156,7 +156,7 @@ static __always_inline int buffer_uptoda
>  	 * make it consistent with folio_test_uptodate
>  	 * pairs with smp_mb__before_atomic in set_buffer_uptodate
>  	 */
> -	return (smp_load_acquire(&bh->b_state) & (1UL << BH_Uptodate)) != 0;
> +	return test_bit_acquire(BH_Uptodate, &bh->b_state);

Do you think it would be worth adding set_bit_release() and then relaxing
set_buffer_uptodate() to use that rather than the smp_mb__before_atomic()?

Will

Re: [PATCH] wait_on_bit: add an acquire memory barrier

[Alan Stern]

On Thu, Aug 25, 2022 at 05:03:40PM -0400, Mikulas Patocka wrote:
> From: Mikulas Patocka <mpatocka@redhat.com>
> 
> There are several places in the kernel where wait_on_bit is not followed
> by a memory barrier (for example, in drivers/md/dm-bufio.c:new_read). On
> architectures with weak memory ordering, it may happen that memory
> accesses that follow wait_on_bit are reordered before wait_on_bit and they
> may return invalid data.
> 
> Fix this class of bugs by introducing a new function "test_bit_acquire"
> that works like test_bit, but has acquire memory ordering semantics.
> 
> Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>

...

> --- linux-2.6.orig/include/asm-generic/bitops/generic-non-atomic.h
> +++ linux-2.6/include/asm-generic/bitops/generic-non-atomic.h
> @@ -4,6 +4,7 @@
>  #define __ASM_GENERIC_BITOPS_GENERIC_NON_ATOMIC_H
>  
>  #include <linux/bits.h>
> +#include <asm/barrier.h>
>  
>  #ifndef _LINUX_BITOPS_H
>  #error only <linux/bitops.h> can be included directly
> @@ -127,6 +128,18 @@ generic_test_bit(unsigned long nr, const
>  	return 1UL & (addr[BIT_WORD(nr)] >> (nr & (BITS_PER_LONG-1)));
>  }
>  
> +/**
> + * generic_test_bit - Determine whether a bit is set with acquire semantics

Trivial: Name in the kerneldoc isn't the same as the actual function name.

(Also, "with acquire semantics" is supposed to modify "Determine", not 
"is set" -- we don't set bits using acquire semantics.  You could change 
this to "Determine, with acquire semantics, whether a bit is set".)

Alan Stern

> + * @nr: bit number to test
> + * @addr: Address to start counting from
> + */
> +static __always_inline bool
> +generic_test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
> +{
> +	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
> +	return 1UL & (smp_load_acquire(p) >> (nr & (BITS_PER_LONG-1)));
> +}

Re: [PATCH] wait_on_bit: add an acquire memory barrier

[Linus Torvalds]

On Thu, Aug 25, 2022 at 2:03 PM Mikulas Patocka <mpatocka@redhat.com> wrote:
>
> Here I reworked your patch, so that test_bit_acquire is defined just like
> test_bit. There's some code duplication (in
> include/asm-generic/bitops/generic-non-atomic.h and in
> arch/x86/include/asm/bitops.h), but that duplication exists in the
> test_bit function too.

This looks fine to me, and I like how you fixed up buffer_uptodate()
while at it.

> I tested it on x86-64 and arm64. On x86-64 it generates the "bt"
> instruction for variable-bit test and "shr; and $1" for constant bit test.

That shr/and is almost certainly pessimal for small constant values at
least, and it's better done as "movq %rax" followed by "test %rax".
But I guess it depends on the bit value (and thus the constant size).

Doing a "testb $imm8" would likely be optimal, but you'll never get
that with smp_load_acquire() on x86 unless you use inline asm, because
of how we're doing it with a volatile pointer.

Anyway, you could try something like this:

  static __always_inline bool constant_test_bit(long nr, const
volatile unsigned long *addr)
  {
        bool oldbit;

        asm volatile("testb %2,%1"
                     CC_SET(nz)
                     : CC_OUT(nz) (oldbit)
                     : "m" (((unsigned char *)addr)[nr >> 3]),
                       "Ir" (1 << (nr & 7))
                      :"memory");
        return oldbit;
  }

for both the regular test_bit() and for the acquire (since all loads
are acquires on x86, and using an asm basically forces a memory load
so it just does that "volatile" part.

But that's a separate optimization and independent of the acquire thing.

> For me, the kernel 6.0-rc2 doesn't boot in an arm64 virtual machine at all
> (with or without this patch), so I only compile-tested it on arm64. I have
> to bisect it.

Hmm. I'm running it on real arm64 hardware (rc2+ - not your patch), so
I wonder what's up..

               Linus

Re: [PATCH] wait_on_bit: add an acquire memory barrier

[Mikulas Patocka]

On Mon, 22 Aug 2022, Linus Torvalds wrote:

> On Mon, Aug 22, 2022 at 10:08 AM Linus Torvalds
> <torvalds@linux-foundation.org> wrote:
> >
> > So why don't we just create a "test_bit_acquire()" and be done with
> > it? We literally created clear_bit_unlock() for the opposite reason,
> > and your comments about the new barrier hack even point to it.
> 
> Here's a patch that is
> 
>  (a) almost entirely untested (I checked that one single case builds
> and seems to generate the expected code)
> 
>  (b) needs some more loving
> 
> but seems to superficially work.
> 
> At a minimum this needs to be split into two (so the bitop and the
> wait_on_bit parts split up), and that whole placement of
> <asm/barrier.h> and generic_bit_test_acquire() need at least some
> thinking about, but on the whole it seems reasonable.
> 
> For example, it would make more sense to have this in
> <asm-generic/bitops/lock.h>, but not all architectures include that,
> and some do their own version. I didn't want to mess with
> architecture-specific headers, so this illogically just uses
> generic-non-atomic.h.
> 
> Maybe just put it in <linux/bitops.h> directly?
> 
> So I'm not at all claiming that this is a great patch. It definitely
> needs more work, and a lot more testing.
> 
> But I think this is at least the right _direction_ to take here.
> 
> And yes, I think it also would have been better if
> "clear_bit_unlock()" would have been called "clear_bit_release()", and
> we'd have more consistent naming with our ordered atomics. But it's
> probably not worth changing.
> 
>                Linus

Hi

Here I reworked your patch, so that test_bit_acquire is defined just like 
test_bit. There's some code duplication (in 
include/asm-generic/bitops/generic-non-atomic.h and in 
arch/x86/include/asm/bitops.h), but that duplication exists in the 
test_bit function too.

I tested it on x86-64 and arm64. On x86-64 it generates the "bt" 
instruction for variable-bit test and "shr; and $1" for constant bit test. 
On arm64 it generates the "ldar" instruction for both constant and 
variable bit test.

For me, the kernel 6.0-rc2 doesn't boot in an arm64 virtual machine at all 
(with or without this patch), so I only compile-tested it on arm64. I have 
to bisect it.

Mikulas



From: Mikulas Patocka <mpatocka@redhat.com>

There are several places in the kernel where wait_on_bit is not followed
by a memory barrier (for example, in drivers/md/dm-bufio.c:new_read). On
architectures with weak memory ordering, it may happen that memory
accesses that follow wait_on_bit are reordered before wait_on_bit and they
may return invalid data.

Fix this class of bugs by introducing a new function "test_bit_acquire"
that works like test_bit, but has acquire memory ordering semantics.

Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Cc: stable@vger.kernel.org

 arch/x86/include/asm/bitops.h                            |   13 +++++++++++++
 include/asm-generic/bitops/generic-non-atomic.h          |   14 ++++++++++++++
 include/asm-generic/bitops/instrumented-non-atomic.h     |   12 ++++++++++++
 include/asm-generic/bitops/non-atomic.h                  |    1 +
 include/asm-generic/bitops/non-instrumented-non-atomic.h |    1 +
 include/linux/bitops.h                                   |    1 +
 include/linux/buffer_head.h                              |    2 +-
 include/linux/wait_bit.h                                 |    8 ++++----
 kernel/sched/wait_bit.c                                  |    2 +-
 9 files changed, 48 insertions(+), 6 deletions(-)

Index: linux-2.6/include/asm-generic/bitops/generic-non-atomic.h
===================================================================
--- linux-2.6.orig/include/asm-generic/bitops/generic-non-atomic.h
+++ linux-2.6/include/asm-generic/bitops/generic-non-atomic.h
@@ -4,6 +4,7 @@
 #define __ASM_GENERIC_BITOPS_GENERIC_NON_ATOMIC_H
 
 #include <linux/bits.h>
+#include <asm/barrier.h>
 
 #ifndef _LINUX_BITOPS_H
 #error only <linux/bitops.h> can be included directly
@@ -127,6 +128,18 @@ generic_test_bit(unsigned long nr, const
 	return 1UL & (addr[BIT_WORD(nr)] >> (nr & (BITS_PER_LONG-1)));
 }
 
+/**
+ * generic_test_bit - Determine whether a bit is set with acquire semantics
+ * @nr: bit number to test
+ * @addr: Address to start counting from
+ */
+static __always_inline bool
+generic_test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	return 1UL & (smp_load_acquire(p) >> (nr & (BITS_PER_LONG-1)));
+}
+
 /*
  * const_*() definitions provide good compile-time optimizations when
  * the passed arguments can be resolved at compile time.
@@ -137,6 +150,7 @@ generic_test_bit(unsigned long nr, const
 #define const___test_and_set_bit	generic___test_and_set_bit
 #define const___test_and_clear_bit	generic___test_and_clear_bit
 #define const___test_and_change_bit	generic___test_and_change_bit
+#define const_test_bit_acquire		generic_test_bit_acquire
 
 /**
  * const_test_bit - Determine whether a bit is set
Index: linux-2.6/include/asm-generic/bitops/non-atomic.h
===================================================================
--- linux-2.6.orig/include/asm-generic/bitops/non-atomic.h
+++ linux-2.6/include/asm-generic/bitops/non-atomic.h
@@ -13,6 +13,7 @@
 #define arch___test_and_change_bit generic___test_and_change_bit
 
 #define arch_test_bit generic_test_bit
+#define arch_test_bit_acquire generic_test_bit_acquire
 
 #include <asm-generic/bitops/non-instrumented-non-atomic.h>
 
Index: linux-2.6/include/linux/bitops.h
===================================================================
--- linux-2.6.orig/include/linux/bitops.h
+++ linux-2.6/include/linux/bitops.h
@@ -59,6 +59,7 @@ extern unsigned long __sw_hweight64(__u6
 #define __test_and_clear_bit(nr, addr)	bitop(___test_and_clear_bit, nr, addr)
 #define __test_and_change_bit(nr, addr)	bitop(___test_and_change_bit, nr, addr)
 #define test_bit(nr, addr)		bitop(_test_bit, nr, addr)
+#define test_bit_acquire(nr, addr)	bitop(_test_bit_acquire, nr, addr)
 
 /*
  * Include this here because some architectures need generic_ffs/fls in
Index: linux-2.6/include/linux/wait_bit.h
===================================================================
--- linux-2.6.orig/include/linux/wait_bit.h
+++ linux-2.6/include/linux/wait_bit.h
@@ -71,7 +71,7 @@ static inline int
 wait_on_bit(unsigned long *word, int bit, unsigned mode)
 {
 	might_sleep();
-	if (!test_bit(bit, word))
+	if (!test_bit_acquire(bit, word))
 		return 0;
 	return out_of_line_wait_on_bit(word, bit,
 				       bit_wait,
@@ -96,7 +96,7 @@ static inline int
 wait_on_bit_io(unsigned long *word, int bit, unsigned mode)
 {
 	might_sleep();
-	if (!test_bit(bit, word))
+	if (!test_bit_acquire(bit, word))
 		return 0;
 	return out_of_line_wait_on_bit(word, bit,
 				       bit_wait_io,
@@ -123,7 +123,7 @@ wait_on_bit_timeout(unsigned long *word,
 		    unsigned long timeout)
 {
 	might_sleep();
-	if (!test_bit(bit, word))
+	if (!test_bit_acquire(bit, word))
 		return 0;
 	return out_of_line_wait_on_bit_timeout(word, bit,
 					       bit_wait_timeout,
@@ -151,7 +151,7 @@ wait_on_bit_action(unsigned long *word,
 		   unsigned mode)
 {
 	might_sleep();
-	if (!test_bit(bit, word))
+	if (!test_bit_acquire(bit, word))
 		return 0;
 	return out_of_line_wait_on_bit(word, bit, action, mode);
 }
Index: linux-2.6/kernel/sched/wait_bit.c
===================================================================
--- linux-2.6.orig/kernel/sched/wait_bit.c
+++ linux-2.6/kernel/sched/wait_bit.c
@@ -47,7 +47,7 @@ __wait_on_bit(struct wait_queue_head *wq
 		prepare_to_wait(wq_head, &wbq_entry->wq_entry, mode);
 		if (test_bit(wbq_entry->key.bit_nr, wbq_entry->key.flags))
 			ret = (*action)(&wbq_entry->key, mode);
-	} while (test_bit(wbq_entry->key.bit_nr, wbq_entry->key.flags) && !ret);
+	} while (test_bit_acquire(wbq_entry->key.bit_nr, wbq_entry->key.flags) && !ret);
 
 	finish_wait(wq_head, &wbq_entry->wq_entry);
 
Index: linux-2.6/include/asm-generic/bitops/non-instrumented-non-atomic.h
===================================================================
--- linux-2.6.orig/include/asm-generic/bitops/non-instrumented-non-atomic.h
+++ linux-2.6/include/asm-generic/bitops/non-instrumented-non-atomic.h
@@ -12,5 +12,6 @@
 #define ___test_and_change_bit	arch___test_and_change_bit
 
 #define _test_bit		arch_test_bit
+#define _test_bit_acquire	arch_test_bit_acquire
 
 #endif /* __ASM_GENERIC_BITOPS_NON_INSTRUMENTED_NON_ATOMIC_H */
Index: linux-2.6/arch/x86/include/asm/bitops.h
===================================================================
--- linux-2.6.orig/arch/x86/include/asm/bitops.h
+++ linux-2.6/arch/x86/include/asm/bitops.h
@@ -207,6 +207,12 @@ static __always_inline bool constant_tes
 		(addr[nr >> _BITOPS_LONG_SHIFT])) != 0;
 }
 
+static __always_inline bool constant_test_bit_acquire(long nr, const volatile unsigned long *addr)
+{
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	return 1UL & (smp_load_acquire(p) >> (nr & (BITS_PER_LONG-1)));
+}
+
 static __always_inline bool variable_test_bit(long nr, volatile const unsigned long *addr)
 {
 	bool oldbit;
@@ -226,6 +232,13 @@ arch_test_bit(unsigned long nr, const vo
 					  variable_test_bit(nr, addr);
 }
 
+static __always_inline bool
+arch_test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	return __builtin_constant_p(nr) ? constant_test_bit_acquire(nr, addr) :
+					  variable_test_bit(nr, addr);
+}
+
 /**
  * __ffs - find first set bit in word
  * @word: The word to search
Index: linux-2.6/include/asm-generic/bitops/instrumented-non-atomic.h
===================================================================
--- linux-2.6.orig/include/asm-generic/bitops/instrumented-non-atomic.h
+++ linux-2.6/include/asm-generic/bitops/instrumented-non-atomic.h
@@ -142,4 +142,16 @@ _test_bit(unsigned long nr, const volati
 	return arch_test_bit(nr, addr);
 }
 
+/**
+ * _test_bit_acquire - Determine whether a bit is set with acquire semantics
+ * @nr: bit number to test
+ * @addr: Address to start counting from
+ */
+static __always_inline bool
+_test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	instrument_atomic_read(addr + BIT_WORD(nr), sizeof(long));
+	return arch_test_bit_acquire(nr, addr);
+}
+
 #endif /* _ASM_GENERIC_BITOPS_INSTRUMENTED_NON_ATOMIC_H */
Index: linux-2.6/include/linux/buffer_head.h
===================================================================
--- linux-2.6.orig/include/linux/buffer_head.h
+++ linux-2.6/include/linux/buffer_head.h
@@ -156,7 +156,7 @@ static __always_inline int buffer_uptoda
 	 * make it consistent with folio_test_uptodate
 	 * pairs with smp_mb__before_atomic in set_buffer_uptodate
 	 */
-	return (smp_load_acquire(&bh->b_state) & (1UL << BH_Uptodate)) != 0;
+	return test_bit_acquire(BH_Uptodate, &bh->b_state);
 }
 
 #define bh_offset(bh)		((unsigned long)(bh)->b_data & ~PAGE_MASK)

Re: [PATCH] wait_on_bit: add an acquire memory barrier

[Joel Fernandes]

On Mon, Aug 22, 2022 at 1:39 PM Linus Torvalds
<torvalds@linux-foundation.org> wrote:
>
> On Mon, Aug 22, 2022 at 10:08 AM Linus Torvalds
> <torvalds@linux-foundation.org> wrote:
> >
> > So why don't we just create a "test_bit_acquire()" and be done with
> > it? We literally created clear_bit_unlock() for the opposite reason,
> > and your comments about the new barrier hack even point to it.
>
> Here's a patch that is
>
>  (a) almost entirely untested (I checked that one single case builds
> and seems to generate the expected code)
>
>  (b) needs some more loving
>
> but seems to superficially work.
>
> At a minimum this needs to be split into two (so the bitop and the
> wait_on_bit parts split up), and that whole placement of
> <asm/barrier.h> and generic_bit_test_acquire() need at least some
> thinking about, but on the whole it seems reasonable.
>
> For example, it would make more sense to have this in
> <asm-generic/bitops/lock.h>, but not all architectures include that,
> and some do their own version. I didn't want to mess with
> architecture-specific headers, so this illogically just uses
> generic-non-atomic.h.
>
> Maybe just put it in <linux/bitops.h> directly?
>
> So I'm not at all claiming that this is a great patch. It definitely
> needs more work, and a lot more testing.
>
> But I think this is at least the right _direction_ to take here.
>
> And yes, I think it also would have been better if
> "clear_bit_unlock()" would have been called "clear_bit_release()", and
> we'd have more consistent naming with our ordered atomics. But it's
> probably not worth changing.

Also, as a suggestion to Mikulas or whoever works on this - update the
ORDERING section of Documentation/atomic_bitops.txt too?

Thanks,

 - Joel

Re: [PATCH] wait_on_bit: add an acquire memory barrier

[Linus Torvalds]

[-- Attachment #1: Type: text/plain, Size: 1471 bytes --]

On Mon, Aug 22, 2022 at 10:08 AM Linus Torvalds
<torvalds@linux-foundation.org> wrote:
>
> So why don't we just create a "test_bit_acquire()" and be done with
> it? We literally created clear_bit_unlock() for the opposite reason,
> and your comments about the new barrier hack even point to it.

Here's a patch that is

 (a) almost entirely untested (I checked that one single case builds
and seems to generate the expected code)

 (b) needs some more loving

but seems to superficially work.

At a minimum this needs to be split into two (so the bitop and the
wait_on_bit parts split up), and that whole placement of
<asm/barrier.h> and generic_bit_test_acquire() need at least some
thinking about, but on the whole it seems reasonable.

For example, it would make more sense to have this in
<asm-generic/bitops/lock.h>, but not all architectures include that,
and some do their own version. I didn't want to mess with
architecture-specific headers, so this illogically just uses
generic-non-atomic.h.

Maybe just put it in <linux/bitops.h> directly?

So I'm not at all claiming that this is a great patch. It definitely
needs more work, and a lot more testing.

But I think this is at least the right _direction_ to take here.

And yes, I think it also would have been better if
"clear_bit_unlock()" would have been called "clear_bit_release()", and
we'd have more consistent naming with our ordered atomics. But it's
probably not worth changing.

               Linus

[-- Attachment #2: patch.diff --]
[-- Type: text/x-patch, Size: 4197 bytes --]

 include/asm-generic/bitops/generic-non-atomic.h | 9 +++++++++
 include/asm-generic/bitops/non-atomic.h         | 1 +
 include/linux/bitops.h                          | 2 +-
 include/linux/wait_bit.h                        | 8 ++++----
 kernel/sched/wait_bit.c                         | 2 +-
 5 files changed, 16 insertions(+), 6 deletions(-)

diff --git a/include/asm-generic/bitops/generic-non-atomic.h b/include/asm-generic/bitops/generic-non-atomic.h
index 3d5ebd24652b..f56a252db9e8 100644
--- a/include/asm-generic/bitops/generic-non-atomic.h
+++ b/include/asm-generic/bitops/generic-non-atomic.h
@@ -4,6 +4,7 @@
 #define __ASM_GENERIC_BITOPS_GENERIC_NON_ATOMIC_H
 
 #include <linux/bits.h>
+#include <asm/barrier.h>
 
 #ifndef _LINUX_BITOPS_H
 #error only <linux/bitops.h> can be included directly
@@ -158,4 +159,12 @@ const_test_bit(unsigned long nr, const volatile unsigned long *addr)
 	return !!(val & mask);
 }
 
+static __always_inline bool
+generic_test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
+{
+	unsigned long mask = BIT_MASK(nr);
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	return smp_load_acquire(p) & mask;
+}
+
 #endif /* __ASM_GENERIC_BITOPS_GENERIC_NON_ATOMIC_H */
diff --git a/include/asm-generic/bitops/non-atomic.h b/include/asm-generic/bitops/non-atomic.h
index 5c37ced343ae..71f8d54a5195 100644
--- a/include/asm-generic/bitops/non-atomic.h
+++ b/include/asm-generic/bitops/non-atomic.h
@@ -13,6 +13,7 @@
 #define arch___test_and_change_bit generic___test_and_change_bit
 
 #define arch_test_bit generic_test_bit
+#define arch_test_bit_acquire generic_test_bit_acquire
 
 #include <asm-generic/bitops/non-instrumented-non-atomic.h>
 
diff --git a/include/linux/bitops.h b/include/linux/bitops.h
index cf9bf65039f2..22adf74d5c25 100644
--- a/include/linux/bitops.h
+++ b/include/linux/bitops.h
@@ -59,7 +59,7 @@ extern unsigned long __sw_hweight64(__u64 w);
 #define __test_and_clear_bit(nr, addr)	bitop(___test_and_clear_bit, nr, addr)
 #define __test_and_change_bit(nr, addr)	bitop(___test_and_change_bit, nr, addr)
 #define test_bit(nr, addr)		bitop(_test_bit, nr, addr)
-
+#define test_bit_acquire(nr, addr)	generic_test_bit_acquire(nr, addr)
 /*
  * Include this here because some architectures need generic_ffs/fls in
  * scope
diff --git a/include/linux/wait_bit.h b/include/linux/wait_bit.h
index 7dec36aecbd9..7725b7579b78 100644
--- a/include/linux/wait_bit.h
+++ b/include/linux/wait_bit.h
@@ -71,7 +71,7 @@ static inline int
 wait_on_bit(unsigned long *word, int bit, unsigned mode)
 {
 	might_sleep();
-	if (!test_bit(bit, word))
+	if (!test_bit_acquire(bit, word))
 		return 0;
 	return out_of_line_wait_on_bit(word, bit,
 				       bit_wait,
@@ -96,7 +96,7 @@ static inline int
 wait_on_bit_io(unsigned long *word, int bit, unsigned mode)
 {
 	might_sleep();
-	if (!test_bit(bit, word))
+	if (!test_bit_acquire(bit, word))
 		return 0;
 	return out_of_line_wait_on_bit(word, bit,
 				       bit_wait_io,
@@ -123,7 +123,7 @@ wait_on_bit_timeout(unsigned long *word, int bit, unsigned mode,
 		    unsigned long timeout)
 {
 	might_sleep();
-	if (!test_bit(bit, word))
+	if (!test_bit_acquire(bit, word))
 		return 0;
 	return out_of_line_wait_on_bit_timeout(word, bit,
 					       bit_wait_timeout,
@@ -151,7 +151,7 @@ wait_on_bit_action(unsigned long *word, int bit, wait_bit_action_f *action,
 		   unsigned mode)
 {
 	might_sleep();
-	if (!test_bit(bit, word))
+	if (!test_bit_acquire(bit, word))
 		return 0;
 	return out_of_line_wait_on_bit(word, bit, action, mode);
 }
diff --git a/kernel/sched/wait_bit.c b/kernel/sched/wait_bit.c
index d4788f810b55..0b1cd985dc27 100644
--- a/kernel/sched/wait_bit.c
+++ b/kernel/sched/wait_bit.c
@@ -47,7 +47,7 @@ __wait_on_bit(struct wait_queue_head *wq_head, struct wait_bit_queue_entry *wbq_
 		prepare_to_wait(wq_head, &wbq_entry->wq_entry, mode);
 		if (test_bit(wbq_entry->key.bit_nr, wbq_entry->key.flags))
 			ret = (*action)(&wbq_entry->key, mode);
-	} while (test_bit(wbq_entry->key.bit_nr, wbq_entry->key.flags) && !ret);
+	} while (test_bit_acquire(wbq_entry->key.bit_nr, wbq_entry->key.flags) && !ret);
 
 	finish_wait(wq_head, &wbq_entry->wq_entry);
 

Re: [PATCH] wait_on_bit: add an acquire memory barrier

[Linus Torvalds]

On Mon, Aug 22, 2022 at 2:39 AM Mikulas Patocka <mpatocka@redhat.com> wrote:
>
> I'd like to ask what do you think about this patch?

I really don't like it. It adds a pointless read barrier only because
you didn't want to do it properly.

On x86, it doesn't matter, since rmb is a no-op and only a scheduling
barrier (and not noticeable in this case anyway).

On other architectures, it might.

But on all architectures it's just ugly.

I suggested in an earlier thread that you just do it right with an
explicit smp_load_acquire() and a manual bit test.

So why don't we just create a "test_bit_acquire()" and be done with
it? We literally created clear_bit_unlock() for the opposite reason,
and your comments about the new barrier hack even point to it.

Why is "clear_bit_unlock()" worthy of a real helper, but
"test_bit_acquire()" is not and people who want it have to use this
horrendous hack?

Please stop adding random barriers already. Just do it right. I've
said this before, why do you then keep doing this and asking for
comments?

My reply will remain the same: JUST DO IT RIGHT.

                Linus

[PATCH] wait_on_bit: add an acquire memory barrier

[Mikulas Patocka]

Hi

I'd like to ask what do you think about this patch? Do you want to commit 
it - or do you think that the barrier should be added to the callers of 
wait_on_bit?

Mikulas



From: Mikulas Patocka <mpatocka@redhat.com>

There are several places in the kernel where wait_on_bit is not followed
by a memory barrier (for example, in drivers/md/dm-bufio.c:new_read). On
architectures with weak memory ordering, it may happen that memory
accesses that follow wait_on_bit are reordered before wait_on_bit and they
may return invalid data.

Fix this class of bugs by adding an acquire memory barrier to wait_on_bit,
wait_on_bit_io, wait_on_bit_timeout and wait_on_bit_action. The code that
uses these functions should clear the bit using the function
clear_bit_unlock.

Signed-off-by: Mikulas Patocka <mpatocka@redhat.com>
Cc: stable@vger.kernel.org

---
 include/linux/wait_bit.h |   16 ++++++++++++----
 kernel/sched/wait_bit.c  |    2 ++
 2 files changed, 14 insertions(+), 4 deletions(-)

Index: linux-2.6/include/linux/wait_bit.h
===================================================================
--- linux-2.6.orig/include/linux/wait_bit.h	2022-08-20 14:33:44.000000000 +0200
+++ linux-2.6/include/linux/wait_bit.h	2022-08-20 15:41:43.000000000 +0200
@@ -71,8 +71,10 @@ static inline int
 wait_on_bit(unsigned long *word, int bit, unsigned mode)
 {
 	might_sleep();
-	if (!test_bit(bit, word))
+	if (!test_bit(bit, word)) {
+		smp_acquire__after_ctrl_dep();	/* should pair with clear_bit_unlock */
 		return 0;
+	}
 	return out_of_line_wait_on_bit(word, bit,
 				       bit_wait,
 				       mode);
@@ -96,8 +98,10 @@ static inline int
 wait_on_bit_io(unsigned long *word, int bit, unsigned mode)
 {
 	might_sleep();
-	if (!test_bit(bit, word))
+	if (!test_bit(bit, word)) {
+		smp_acquire__after_ctrl_dep();	/* should pair with clear_bit_unlock */
 		return 0;
+	}
 	return out_of_line_wait_on_bit(word, bit,
 				       bit_wait_io,
 				       mode);
@@ -123,8 +127,10 @@ wait_on_bit_timeout(unsigned long *word,
 		    unsigned long timeout)
 {
 	might_sleep();
-	if (!test_bit(bit, word))
+	if (!test_bit(bit, word)) {
+		smp_acquire__after_ctrl_dep();	/* should pair with clear_bit_unlock */
 		return 0;
+	}
 	return out_of_line_wait_on_bit_timeout(word, bit,
 					       bit_wait_timeout,
 					       mode, timeout);
@@ -151,8 +157,10 @@ wait_on_bit_action(unsigned long *word,
 		   unsigned mode)
 {
 	might_sleep();
-	if (!test_bit(bit, word))
+	if (!test_bit(bit, word)) {
+		smp_acquire__after_ctrl_dep();	/* should pair with clear_bit_unlock */
 		return 0;
+	}
 	return out_of_line_wait_on_bit(word, bit, action, mode);
 }
 
Index: linux-2.6/kernel/sched/wait_bit.c
===================================================================
--- linux-2.6.orig/kernel/sched/wait_bit.c	2022-08-20 14:33:44.000000000 +0200
+++ linux-2.6/kernel/sched/wait_bit.c	2022-08-20 15:41:39.000000000 +0200
@@ -49,6 +49,8 @@ __wait_on_bit(struct wait_queue_head *wq
 			ret = (*action)(&wbq_entry->key, mode);
 	} while (test_bit(wbq_entry->key.bit_nr, wbq_entry->key.flags) && !ret);
 
+	smp_acquire__after_ctrl_dep();	/* should pair with clear_bit_unlock */
+
 	finish_wait(wq_head, &wbq_entry->wq_entry);
 
 	return ret;