@@ -56,6 +56,8 @@ cpucap_is_possible(const unsigned int cap)
return IS_ENABLED(CONFIG_CAVIUM_ERRATUM_23154);
case ARM64_WORKAROUND_NVIDIA_CARMEL_CNP:
return IS_ENABLED(CONFIG_NVIDIA_CARMEL_CNP_ERRATUM);
+ case ARM64_WORKAROUND_REPEAT_TLBI:
+ return IS_ENABLED(CONFIG_ARM64_WORKAROUND_REPEAT_TLBI);
}
return true;
@@ -284,16 +284,15 @@ static inline void flush_tlb_page(struct vm_area_struct *vma,
static inline bool arch_tlbbatch_should_defer(struct mm_struct *mm)
{
-#ifdef CONFIG_ARM64_WORKAROUND_REPEAT_TLBI
/*
* TLB flush deferral is not required on systems which are affected by
* ARM64_WORKAROUND_REPEAT_TLBI, as __tlbi()/__tlbi_user() implementation
* will have two consecutive TLBI instructions with a dsb(ish) in between
* defeating the purpose (i.e save overall 'dsb ish' cost).
*/
- if (unlikely(cpus_have_const_cap(ARM64_WORKAROUND_REPEAT_TLBI)))
+ if (alternative_has_cap_unlikely(ARM64_WORKAROUND_REPEAT_TLBI))
return false;
-#endif
+
return true;
}
In arch_tlbbatch_should_defer() we use cpus_have_const_cap() to check for ARM64_WORKAROUND_REPEAT_TLBI, but this is not necessary and alternative_has_cap_*() would be preferable. For historical reasons, cpus_have_const_cap() is more complicated than it needs to be. Before cpucaps are finalized, it will perform a bitmap test of the system_cpucaps bitmap, and once cpucaps are finalized it will use an alternative branch. This used to be necessary to handle some race conditions in the window between cpucap detection and the subsequent patching of alternatives and static branches, where different branches could be out-of-sync with one another (or w.r.t. alternative sequences). Now that we use alternative branches instead of static branches, these are all patched atomically w.r.t. one another, and there are only a handful of cases that need special care in the window between cpucap detection and alternative patching. Due to the above, it would be nice to remove cpus_have_const_cap(), and migrate callers over to alternative_has_cap_*(), cpus_have_final_cap(), or cpus_have_cap() depending on when their requirements. This will remove redundant instructions and improve code generation, and will make it easier to determine how each callsite will behave before, during, and after alternative patching. The cpus_have_const_cap() check in arch_tlbbatch_should_defer() is an optimization to avoid some redundant work when the ARM64_WORKAROUND_REPEAT_TLBI cpucap is detected and forces the immediate use of TLBI + DSB ISH. In the window between detecting the ARM64_WORKAROUND_REPEAT_TLBI cpucap and patching alternatives this is not a big concern and there's no need to optimize this window at the expsense of subsequent usage at runtime. This patch replaces the use of cpus_have_const_cap() with alternative_has_cap_unlikely(), which will avoid generating code to test the system_cpucaps bitmap and should be better for all subsequent calls at runtime. The ARM64_WORKAROUND_REPEAT_TLBI cpucap is added to cpucap_is_possible() so that code can be elided entirely when this is not possible without requiring ifdeffery or IS_ENABLED() checks at each usage. Signed-off-by: Mark Rutland <mark.rutland@arm.com> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Suzuki K Poulose <suzuki.poulose@arm.com> Cc: Will Deacon <will@kernel.org> --- arch/arm64/include/asm/cpucaps.h | 2 ++ arch/arm64/include/asm/tlbflush.h | 5 ++--- 2 files changed, 4 insertions(+), 3 deletions(-)