mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-21 15:42:49 +07:00
1077fa36f2
There are a number of situations where the mandatory barriers rmb() and wmb() are used to order memory/memory operations in the device drivers and those barriers are much heavier than they actually need to be. For example in the case of PowerPC wmb() calls the heavy-weight sync instruction when for coherent memory operations all that is really needed is an lsync or eieio instruction. This commit adds a coherent only version of the mandatory memory barriers rmb() and wmb(). In most cases this should result in the barrier being the same as the SMP barriers for the SMP case, however in some cases we use a barrier that is somewhere in between rmb() and smp_rmb(). For example on ARM the rmb barriers break down as follows: Barrier Call Explanation --------- -------- ---------------------------------- rmb() dsb() Data synchronization barrier - system dma_rmb() dmb(osh) data memory barrier - outer sharable smp_rmb() dmb(ish) data memory barrier - inner sharable These new barriers are not as safe as the standard rmb() and wmb(). Specifically they do not guarantee ordering between coherent and incoherent memories. The primary use case for these would be to enforce ordering of reads and writes when accessing coherent memory that is shared between the CPU and a device. It may also be noted that there is no dma_mb(). Most architectures don't provide a good mechanism for performing a coherent only full barrier without resorting to the same mechanism used in mb(). As such there isn't much to be gained in trying to define such a function. Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Mathieu Desnoyers <mathieu.desnoyers@polymtl.ca> Cc: Michael Ellerman <michael@ellerman.id.au> Cc: Michael Neuling <mikey@neuling.org> Cc: Russell King <linux@arm.linux.org.uk> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Tony Luck <tony.luck@intel.com> Cc: Oleg Nesterov <oleg@redhat.com> Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ingo Molnar <mingo@kernel.org> Cc: David Miller <davem@davemloft.net> Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Acked-by: Will Deacon <will.deacon@arm.com> Signed-off-by: Alexander Duyck <alexander.h.duyck@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
78 lines
2.4 KiB
C
78 lines
2.4 KiB
C
#ifndef __SPARC64_BARRIER_H
|
|
#define __SPARC64_BARRIER_H
|
|
|
|
/* These are here in an effort to more fully work around Spitfire Errata
|
|
* #51. Essentially, if a memory barrier occurs soon after a mispredicted
|
|
* branch, the chip can stop executing instructions until a trap occurs.
|
|
* Therefore, if interrupts are disabled, the chip can hang forever.
|
|
*
|
|
* It used to be believed that the memory barrier had to be right in the
|
|
* delay slot, but a case has been traced recently wherein the memory barrier
|
|
* was one instruction after the branch delay slot and the chip still hung.
|
|
* The offending sequence was the following in sym_wakeup_done() of the
|
|
* sym53c8xx_2 driver:
|
|
*
|
|
* call sym_ccb_from_dsa, 0
|
|
* movge %icc, 0, %l0
|
|
* brz,pn %o0, .LL1303
|
|
* mov %o0, %l2
|
|
* membar #LoadLoad
|
|
*
|
|
* The branch has to be mispredicted for the bug to occur. Therefore, we put
|
|
* the memory barrier explicitly into a "branch always, predicted taken"
|
|
* delay slot to avoid the problem case.
|
|
*/
|
|
#define membar_safe(type) \
|
|
do { __asm__ __volatile__("ba,pt %%xcc, 1f\n\t" \
|
|
" membar " type "\n" \
|
|
"1:\n" \
|
|
: : : "memory"); \
|
|
} while (0)
|
|
|
|
/* The kernel always executes in TSO memory model these days,
|
|
* and furthermore most sparc64 chips implement more stringent
|
|
* memory ordering than required by the specifications.
|
|
*/
|
|
#define mb() membar_safe("#StoreLoad")
|
|
#define rmb() __asm__ __volatile__("":::"memory")
|
|
#define wmb() __asm__ __volatile__("":::"memory")
|
|
|
|
#define dma_rmb() rmb()
|
|
#define dma_wmb() wmb()
|
|
|
|
#define set_mb(__var, __value) \
|
|
do { __var = __value; membar_safe("#StoreLoad"); } while(0)
|
|
|
|
#ifdef CONFIG_SMP
|
|
#define smp_mb() mb()
|
|
#define smp_rmb() rmb()
|
|
#define smp_wmb() wmb()
|
|
#else
|
|
#define smp_mb() __asm__ __volatile__("":::"memory")
|
|
#define smp_rmb() __asm__ __volatile__("":::"memory")
|
|
#define smp_wmb() __asm__ __volatile__("":::"memory")
|
|
#endif
|
|
|
|
#define read_barrier_depends() do { } while (0)
|
|
#define smp_read_barrier_depends() do { } while (0)
|
|
|
|
#define smp_store_release(p, v) \
|
|
do { \
|
|
compiletime_assert_atomic_type(*p); \
|
|
barrier(); \
|
|
ACCESS_ONCE(*p) = (v); \
|
|
} while (0)
|
|
|
|
#define smp_load_acquire(p) \
|
|
({ \
|
|
typeof(*p) ___p1 = ACCESS_ONCE(*p); \
|
|
compiletime_assert_atomic_type(*p); \
|
|
barrier(); \
|
|
___p1; \
|
|
})
|
|
|
|
#define smp_mb__before_atomic() barrier()
|
|
#define smp_mb__after_atomic() barrier()
|
|
|
|
#endif /* !(__SPARC64_BARRIER_H) */
|