summaryrefslogtreecommitdiff
path: root/lib
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2023-03-04 13:35:43 -0800
committerLinus Torvalds <torvalds@linux-foundation.org>2023-03-05 14:30:34 -0800
commit596ff4a09b8981790e15572e8e7bc904df5835e7 (patch)
tree82e598e740056e243a436f793923769f6354df10 /lib
parentf915322fe014c5c515119381e886faf07b3c9d31 (diff)
cpumask: re-introduce constant-sized cpumask optimizations
Commit aa47a7c215e7 ("lib/cpumask: deprecate nr_cpumask_bits") resulted in the cpumask operations potentially becoming hugely less efficient, because suddenly the cpumask was always considered to be variable-sized. The optimization was then later added back in a limited form by commit 6f9c07be9d02 ("lib/cpumask: add FORCE_NR_CPUS config option"), but that FORCE_NR_CPUS option is not useful in a generic kernel and more of a special case for embedded situations with fixed hardware. Instead, just re-introduce the optimization, with some changes. Instead of depending on CPUMASK_OFFSTACK being false, and then always using the full constant cpumask width, this introduces three different cpumask "sizes": - the exact size (nr_cpumask_bits) remains identical to nr_cpu_ids. This is used for situations where we should use the exact size. - the "small" size (small_cpumask_bits) is the NR_CPUS constant if it fits in a single word and the bitmap operations thus end up able to trigger the "small_const_nbits()" optimizations. This is used for the operations that have optimized single-word cases that get inlined, notably the bit find and scanning functions. - the "large" size (large_cpumask_bits) is the NR_CPUS constant if it is an sufficiently small constant that makes simple "copy" and "clear" operations more efficient. This is arbitrarily set at four words or less. As a an example of this situation, without this fixed size optimization, cpumask_clear() will generate code like movl nr_cpu_ids(%rip), %edx addq $63, %rdx shrq $3, %rdx andl $-8, %edx callq memset@PLT on x86-64, because it would calculate the "exact" number of longwords that need to be cleared. In contrast, with this patch, using a MAX_CPU of 64 (which is quite a reasonable value to use), the above becomes a single movq $0,cpumask instruction instead, because instead of caring to figure out exactly how many CPU's the system has, it just knows that the cpumask will be a single word and can just clear it all. Note that this does end up tightening the rules a bit from the original version in another way: operations that set bits in the cpumask are now limited to the actual nr_cpu_ids limit, whereas we used to do the nr_cpumask_bits thing almost everywhere in the cpumask code. But if you just clear bits, or scan for bits, we can use the simpler compile-time constants. In the process, remove 'cpumask_complement()' and 'for_each_cpu_not()' which were not useful, and which fundamentally have to be limited to 'nr_cpu_ids'. Better remove them now than have somebody introduce use of them later. Of course, on x86-64 with MAXSMP there is no sane small compile-time constant for the cpumask sizes, and we end up using the actual CPU bits, and will generate the above kind of horrors regardless. Please don't use MAXSMP unless you really expect to have machines with thousands of cores. Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'lib')
-rw-r--r--lib/cpumask_kunit.c14
1 files changed, 1 insertions, 13 deletions
diff --git a/lib/cpumask_kunit.c b/lib/cpumask_kunit.c
index d1fc6ece21f3..a105e6369efc 100644
--- a/lib/cpumask_kunit.c
+++ b/lib/cpumask_kunit.c
@@ -23,16 +23,6 @@
KUNIT_EXPECT_EQ_MSG((test), mask_weight, iter, MASK_MSG(mask)); \
} while (0)
-#define EXPECT_FOR_EACH_CPU_NOT_EQ(test, mask) \
- do { \
- const cpumask_t *m = (mask); \
- int mask_weight = cpumask_weight(m); \
- int cpu, iter = 0; \
- for_each_cpu_not(cpu, m) \
- iter++; \
- KUNIT_EXPECT_EQ_MSG((test), nr_cpu_ids - mask_weight, iter, MASK_MSG(mask)); \
- } while (0)
-
#define EXPECT_FOR_EACH_CPU_OP_EQ(test, op, mask1, mask2) \
do { \
const cpumask_t *m1 = (mask1); \
@@ -77,7 +67,7 @@ static void test_cpumask_weight(struct kunit *test)
KUNIT_EXPECT_EQ_MSG(test, 0, cpumask_weight(&mask_empty), MASK_MSG(&mask_empty));
KUNIT_EXPECT_EQ_MSG(test, nr_cpu_ids, cpumask_weight(cpu_possible_mask),
MASK_MSG(cpu_possible_mask));
- KUNIT_EXPECT_EQ_MSG(test, nr_cpumask_bits, cpumask_weight(&mask_all), MASK_MSG(&mask_all));
+ KUNIT_EXPECT_EQ_MSG(test, nr_cpu_ids, cpumask_weight(&mask_all), MASK_MSG(&mask_all));
}
static void test_cpumask_first(struct kunit *test)
@@ -113,14 +103,12 @@ static void test_cpumask_next(struct kunit *test)
static void test_cpumask_iterators(struct kunit *test)
{
EXPECT_FOR_EACH_CPU_EQ(test, &mask_empty);
- EXPECT_FOR_EACH_CPU_NOT_EQ(test, &mask_empty);
EXPECT_FOR_EACH_CPU_WRAP_EQ(test, &mask_empty);
EXPECT_FOR_EACH_CPU_OP_EQ(test, and, &mask_empty, &mask_empty);
EXPECT_FOR_EACH_CPU_OP_EQ(test, and, cpu_possible_mask, &mask_empty);
EXPECT_FOR_EACH_CPU_OP_EQ(test, andnot, &mask_empty, &mask_empty);
EXPECT_FOR_EACH_CPU_EQ(test, cpu_possible_mask);
- EXPECT_FOR_EACH_CPU_NOT_EQ(test, cpu_possible_mask);
EXPECT_FOR_EACH_CPU_WRAP_EQ(test, cpu_possible_mask);
EXPECT_FOR_EACH_CPU_OP_EQ(test, and, cpu_possible_mask, cpu_possible_mask);
EXPECT_FOR_EACH_CPU_OP_EQ(test, andnot, cpu_possible_mask, &mask_empty);