summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorMark Rutland <mark.rutland@arm.com>2023-10-16 11:24:40 +0100
committerCatalin Marinas <catalin.marinas@arm.com>2023-10-16 14:17:04 +0100
commit6766a8ef18a7796e728774e390c0e8526abb6d6d (patch)
treec5a0811955160196fe9a1a005bdfdf06d957429c
parentbbbb65770bf44d3eaec5b7784028756b58ea08db (diff)
arm64: Avoid cpus_have_const_cap() for ARM64_HAS_CACHE_DIC
In icache_inval_all_pou() we use cpus_have_const_cap() to check for ARM64_HAS_CACHE_DIC, 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 icache_inval_all_pou() is an optimization to skip a redundant (but benign) IC IALLUIS + DSB ISH sequence when all CPUs in the system have DIC. In the window between detecting the ARM64_HAS_CACHE_DIC cpucap and patching alternative branches there is only a single potential call to icache_inval_all_pou() (in the alternatives patching itself), which there's no need to optimize for at the expense of other callers. 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. This also aligns better with the way we patch the assembly cache maintenance sequences in arch/arm64/mm/cache.S. Signed-off-by: Mark Rutland <mark.rutland@arm.com> Cc: Suzuki K Poulose <suzuki.poulose@arm.com> Cc: Will Deacon <will@kernel.org> Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
-rw-r--r--arch/arm64/include/asm/cacheflush.h2
1 files changed, 1 insertions, 1 deletions
diff --git a/arch/arm64/include/asm/cacheflush.h b/arch/arm64/include/asm/cacheflush.h
index d115451ed263..fefac75fa009 100644
--- a/arch/arm64/include/asm/cacheflush.h
+++ b/arch/arm64/include/asm/cacheflush.h
@@ -132,7 +132,7 @@ void flush_dcache_folio(struct folio *);
static __always_inline void icache_inval_all_pou(void)
{
- if (cpus_have_const_cap(ARM64_HAS_CACHE_DIC))
+ if (alternative_has_cap_unlikely(ARM64_HAS_CACHE_DIC))
return;
asm("ic ialluis");