mirror of
https://sourceware.org/git/glibc.git
synced 2025-07-30 22:43:12 +03:00
linux: Simplify get_nprocs
This patch simplifies the memory allocation code and uses the sched routines instead of reimplement it. This still uses a stack allocation buffer, so it can be used on malloc initialization code. Linux currently supports at maximum of 4096 cpus for most architectures: $ find -iname Kconfig | xargs git grep -A10 -w NR_CPUS | grep -w range arch/alpha/Kconfig- range 2 32 arch/arc/Kconfig- range 2 4096 arch/arm/Kconfig- range 2 16 if DEBUG_KMAP_LOCAL arch/arm/Kconfig- range 2 32 if !DEBUG_KMAP_LOCAL arch/arm64/Kconfig- range 2 4096 arch/csky/Kconfig- range 2 32 arch/hexagon/Kconfig- range 2 6 if SMP arch/ia64/Kconfig- range 2 4096 arch/mips/Kconfig- range 2 256 arch/openrisc/Kconfig- range 2 32 arch/parisc/Kconfig- range 2 32 arch/riscv/Kconfig- range 2 32 arch/s390/Kconfig- range 2 512 arch/sh/Kconfig- range 2 32 arch/sparc/Kconfig- range 2 32 if SPARC32 arch/sparc/Kconfig- range 2 4096 if SPARC64 arch/um/Kconfig- range 1 1 arch/x86/Kconfig-# [NR_CPUS_RANGE_BEGIN ... NR_CPUS_RANGE_END] range. arch/x86/Kconfig- range NR_CPUS_RANGE_BEGIN NR_CPUS_RANGE_END arch/xtensa/Kconfig- range 2 32 With x86 supporting 8192: arch/x86/Kconfig 976 config NR_CPUS_RANGE_END 977 int 978 depends on X86_64 979 default 8192 if SMP && CPUMASK_OFFSTACK 980 default 512 if SMP && !CPUMASK_OFFSTACK 981 default 1 if !SMP So using a maximum of 32k cpu should cover all cases (and I would expect once we start to have many more CPUs that Linux would provide a more straightforward way to query for such information). A test is added to check if sched_getaffinity can successfully return with large buffers. Checked on x86_64-linux-gnu and i686-linux-gnu. Reviewed-by: Florian Weimer <fweimer@redhat.com>
This commit is contained in:
@ -28,61 +28,29 @@
|
||||
#include <sys/sysinfo.h>
|
||||
#include <sysdep.h>
|
||||
|
||||
/* Compute the population count of the entire array. */
|
||||
static int
|
||||
__get_nprocs_count (const unsigned long int *array, size_t length)
|
||||
{
|
||||
int count = 0;
|
||||
for (size_t i = 0; i < length; ++i)
|
||||
if (__builtin_add_overflow (count, __builtin_popcountl (array[i]),
|
||||
&count))
|
||||
return INT_MAX;
|
||||
return count;
|
||||
}
|
||||
|
||||
/* __get_nprocs with a large buffer. */
|
||||
static int
|
||||
__get_nprocs_large (void)
|
||||
{
|
||||
/* This code cannot use scratch_buffer because it is used during
|
||||
malloc initialization. */
|
||||
size_t pagesize = GLRO (dl_pagesize);
|
||||
unsigned long int *page = __mmap (0, pagesize, PROT_READ | PROT_WRITE,
|
||||
MAP_ANONYMOUS | MAP_PRIVATE, -1, 0);
|
||||
if (page == MAP_FAILED)
|
||||
return 2;
|
||||
int r = INTERNAL_SYSCALL_CALL (sched_getaffinity, 0, pagesize, page);
|
||||
int count;
|
||||
if (r > 0)
|
||||
count = __get_nprocs_count (page, pagesize / sizeof (unsigned long int));
|
||||
else if (r == -EINVAL)
|
||||
/* One page is still not enough to store the bits. A more-or-less
|
||||
arbitrary value. This assumes t hat such large systems never
|
||||
happen in practice. */
|
||||
count = GLRO (dl_pagesize) * CHAR_BIT;
|
||||
else
|
||||
count = 2;
|
||||
__munmap (page, GLRO (dl_pagesize));
|
||||
return count;
|
||||
}
|
||||
|
||||
int
|
||||
__get_nprocs (void)
|
||||
{
|
||||
/* Fast path for most systems. The kernel expects a buffer size
|
||||
that is a multiple of 8. */
|
||||
unsigned long int small_buffer[1024 / CHAR_BIT / sizeof (unsigned long int)];
|
||||
int r = INTERNAL_SYSCALL_CALL (sched_getaffinity, 0,
|
||||
sizeof (small_buffer), small_buffer);
|
||||
enum
|
||||
{
|
||||
max_num_cpus = 32768,
|
||||
cpu_bits_size = CPU_ALLOC_SIZE (32768)
|
||||
};
|
||||
|
||||
/* This cannot use malloc because it is used on malloc initialization. */
|
||||
__cpu_mask cpu_bits[cpu_bits_size / sizeof (__cpu_mask)];
|
||||
int r = INTERNAL_SYSCALL_CALL (sched_getaffinity, 0, cpu_bits_size,
|
||||
cpu_bits);
|
||||
if (r > 0)
|
||||
return __get_nprocs_count (small_buffer, r / sizeof (unsigned long int));
|
||||
return CPU_COUNT_S (cpu_bits_size, (cpu_set_t*) cpu_bits);
|
||||
else if (r == -EINVAL)
|
||||
/* The kernel requests a larger buffer to store the data. */
|
||||
return __get_nprocs_large ();
|
||||
else
|
||||
/* Some other error. 2 is conservative (not a uniprocessor
|
||||
system, so atomics are needed). */
|
||||
return 2;
|
||||
/* The input buffer is still not enough to store the number of cpus. This
|
||||
is an arbitrary values assuming such systems should be rare and there
|
||||
is no offline cpus. */
|
||||
return max_num_cpus;
|
||||
/* Some other error. 2 is conservative (not a uniprocessor system, so
|
||||
atomics are needed). */
|
||||
return 2;
|
||||
}
|
||||
libc_hidden_def (__get_nprocs)
|
||||
weak_alias (__get_nprocs, get_nprocs)
|
||||
|
Reference in New Issue
Block a user