riscv/spinlock: Strengthen implementations with fences

Current implementations map locking operations using .rl and .aq
annotations.  However, this mapping is unsound w.r.t. the kernel
memory consistency model (LKMM) [1]:

Referring to the "unlock-lock-read-ordering" test reported below,
Daniel wrote:

  "I think an RCpc interpretation of .aq and .rl would in fact
   allow the two normal loads in P1 to be reordered [...]

   The intuition would be that the amoswap.w.aq can forward from
   the amoswap.w.rl while that's still in the store buffer, and
   then the lw x3,0(x4) can also perform while the amoswap.w.rl
   is still in the store buffer, all before the l1 x1,0(x2)
   executes.  That's not forbidden unless the amoswaps are RCsc,
   unless I'm missing something.

   Likewise even if the unlock()/lock() is between two stores.
   A control dependency might originate from the load part of
   the amoswap.w.aq, but there still would have to be something
   to ensure that this load part in fact performs after the store
   part of the amoswap.w.rl performs globally, and that's not
   automatic under RCpc."

Simulation of the RISC-V memory consistency model confirmed this
expectation.

In order to "synchronize" LKMM and RISC-V's implementation, this
commit strengthens the implementations of the locking operations
by replacing .rl and .aq with the use of ("lightweigth") fences,
resp., "fence rw,  w" and "fence r , rw".

C unlock-lock-read-ordering

{}
/* s initially owned by P1 */

P0(int *x, int *y)
{
        WRITE_ONCE(*x, 1);
        smp_wmb();
        WRITE_ONCE(*y, 1);
}

P1(int *x, int *y, spinlock_t *s)
{
        int r0;
        int r1;

        r0 = READ_ONCE(*y);
        spin_unlock(s);
        spin_lock(s);
        r1 = READ_ONCE(*x);
}

exists (1:r0=1 /\ 1:r1=0)

[1] https://marc.info/?l=linux-kernel&m=151930201102853&w=2
    https://groups.google.com/a/groups.riscv.org/forum/#!topic/isa-dev/hKywNHBkAXM
    https://marc.info/?l=linux-kernel&m=151633436614259&w=2

Signed-off-by: Andrea Parri <[email protected]>
Cc: Palmer Dabbelt <[email protected]>
Cc: Albert Ou <[email protected]>
Cc: Daniel Lustig <[email protected]>
Cc: Alan Stern <[email protected]>
Cc: Will Deacon <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Boqun Feng <[email protected]>
Cc: Nicholas Piggin <[email protected]>
Cc: David Howells <[email protected]>
Cc: Jade Alglave <[email protected]>
Cc: Luc Maranget <[email protected]>
Cc: "Paul E. McKenney" <[email protected]>
Cc: Akira Yokosawa <[email protected]>
Cc: Ingo Molnar <[email protected]>
Cc: Linus Torvalds <[email protected]>
Cc: [email protected]
Cc: [email protected]
Signed-off-by: Palmer Dabbelt <[email protected]>

diff --git a/arch/riscv/include/asm/fence.h b/arch/riscv/include/asm/fence.h
new file mode 100644 (file)
index 0000000..2b443a3
--- /dev/null
+++ b/arch/riscv/include/asm/fence.h
@@ -0,0 +1,12 @@
+#ifndef _ASM_RISCV_FENCE_H
+#define _ASM_RISCV_FENCE_H
+
+#ifdef CONFIG_SMP
+#define RISCV_ACQUIRE_BARRIER          "\tfence r , rw\n"
+#define RISCV_RELEASE_BARRIER          "\tfence rw,  w\n"
+#else
+#define RISCV_ACQUIRE_BARRIER
+#define RISCV_RELEASE_BARRIER
+#endif
+
+#endif /* _ASM_RISCV_FENCE_H */

diff --git a/arch/riscv/include/asm/spinlock.h b/arch/riscv/include/asm/spinlock.h
index 2fd27e8ef1fd686d8cf234143174a538223acc79..8eb26d1ede819b95876631dd06c21bcea3e4404f 100644 (file)
--- a/arch/riscv/include/asm/spinlock.h
+++ b/arch/riscv/include/asm/spinlock.h
@@ -17,6 +17,7 @@
 
 #include <linux/kernel.h>
 #include <asm/current.h>
+#include <asm/fence.h>
 
 /*
  * Simple spin lock operations.  These provide no fairness guarantees.
@@ -28,10 +29,7 @@
 
 static inline void arch_spin_unlock(arch_spinlock_t *lock)
 {
-       __asm__ __volatile__ (
-               "amoswap.w.rl x0, x0, %0"
-               : "=A" (lock->lock)
-               :: "memory");
+       smp_store_release(&lock->lock, 0);
 }
 
 static inline int arch_spin_trylock(arch_spinlock_t *lock)
@@ -39,7 +37,8 @@ static inline int arch_spin_trylock(arch_spinlock_t *lock)
        int tmp = 1, busy;
 
        __asm__ __volatile__ (
-               "amoswap.w.aq %0, %2, %1"
+               "       amoswap.w %0, %2, %1\n"
+               RISCV_ACQUIRE_BARRIER
                : "=r" (busy), "+A" (lock->lock)
                : "r" (tmp)
                : "memory");
@@ -68,8 +67,9 @@ static inline void arch_read_lock(arch_rwlock_t *lock)
                "1:     lr.w    %1, %0\n"
                "       bltz    %1, 1b\n"
                "       addi    %1, %1, 1\n"
-               "       sc.w.aq %1, %1, %0\n"
+               "       sc.w    %1, %1, %0\n"
                "       bnez    %1, 1b\n"
+               RISCV_ACQUIRE_BARRIER
                : "+A" (lock->lock), "=&r" (tmp)
                :: "memory");
 }
@@ -82,8 +82,9 @@ static inline void arch_write_lock(arch_rwlock_t *lock)
                "1:     lr.w    %1, %0\n"
                "       bnez    %1, 1b\n"
                "       li      %1, -1\n"
-               "       sc.w.aq %1, %1, %0\n"
+               "       sc.w    %1, %1, %0\n"
                "       bnez    %1, 1b\n"
+               RISCV_ACQUIRE_BARRIER
                : "+A" (lock->lock), "=&r" (tmp)
                :: "memory");
 }
@@ -96,8 +97,9 @@ static inline int arch_read_trylock(arch_rwlock_t *lock)
                "1:     lr.w    %1, %0\n"
                "       bltz    %1, 1f\n"
                "       addi    %1, %1, 1\n"
-               "       sc.w.aq %1, %1, %0\n"
+               "       sc.w    %1, %1, %0\n"
                "       bnez    %1, 1b\n"
+               RISCV_ACQUIRE_BARRIER
                "1:\n"
                : "+A" (lock->lock), "=&r" (busy)
                :: "memory");
@@ -113,8 +115,9 @@ static inline int arch_write_trylock(arch_rwlock_t *lock)
                "1:     lr.w    %1, %0\n"
                "       bnez    %1, 1f\n"
                "       li      %1, -1\n"
-               "       sc.w.aq %1, %1, %0\n"
+               "       sc.w    %1, %1, %0\n"
                "       bnez    %1, 1b\n"
+               RISCV_ACQUIRE_BARRIER
                "1:\n"
                : "+A" (lock->lock), "=&r" (busy)
                :: "memory");
@@ -125,7 +128,8 @@ static inline int arch_write_trylock(arch_rwlock_t *lock)
 static inline void arch_read_unlock(arch_rwlock_t *lock)
 {
        __asm__ __volatile__(
-               "amoadd.w.rl x0, %1, %0"
+               RISCV_RELEASE_BARRIER
+               "       amoadd.w x0, %1, %0\n"
                : "+A" (lock->lock)
                : "r" (-1)
                : "memory");
@@ -133,10 +137,7 @@ static inline void arch_read_unlock(arch_rwlock_t *lock)
 
 static inline void arch_write_unlock(arch_rwlock_t *lock)
 {
-       __asm__ __volatile__ (
-               "amoswap.w.rl x0, x0, %0"
-               : "=A" (lock->lock)
-               :: "memory");
+       smp_store_release(&lock->lock, 0);
 }
 
 #endif /* _ASM_RISCV_SPINLOCK_H */