diff options
| author | Linus Torvalds <torvalds@linux-foundation.org> | 2018-08-13 16:29:35 -0700 |
|---|---|---|
| committer | Linus Torvalds <torvalds@linux-foundation.org> | 2018-08-13 16:29:35 -0700 |
| commit | 203b4fc903b644223a27ad3f25f3a0f3a3911d1d (patch) | |
| tree | 8c210b67a17b74b2a39c500891a20e23c2390cf6 /mm/init-mm.c | |
| parent | 7edcf0d314f69e506ddd9562062b2a79fa965bb9 (diff) | |
| parent | 765d28f136291f9639e3c031a1070fb76d6625c7 (diff) | |
| download | linux-203b4fc903b644223a27ad3f25f3a0f3a3911d1d.tar.gz linux-203b4fc903b644223a27ad3f25f3a0f3a3911d1d.tar.bz2 linux-203b4fc903b644223a27ad3f25f3a0f3a3911d1d.zip | |
Merge branch 'x86-mm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull x86 mm updates from Thomas Gleixner:
- Make lazy TLB mode even lazier to avoid pointless switch_mm()
operations, which reduces CPU load by 1-2% for memcache workloads
- Small cleanups and improvements all over the place
* 'x86-mm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
x86/mm: Remove redundant check for kmem_cache_create()
arm/asm/tlb.h: Fix build error implicit func declaration
x86/mm/tlb: Make clear_asid_other() static
x86/mm/tlb: Skip atomic operations for 'init_mm' in switch_mm_irqs_off()
x86/mm/tlb: Always use lazy TLB mode
x86/mm/tlb: Only send page table free TLB flush to lazy TLB CPUs
x86/mm/tlb: Make lazy TLB mode lazier
x86/mm/tlb: Restructure switch_mm_irqs_off()
x86/mm/tlb: Leave lazy TLB mode at page table free time
mm: Allocate the mm_cpumask (mm->cpu_bitmap[]) dynamically based on nr_cpu_ids
x86/mm: Add TLB purge to free pmd/pte page interfaces
ioremap: Update pgtable free interfaces with addr
x86/mm: Disable ioremap free page handling on x86-PAE
Diffstat (limited to 'mm/init-mm.c')
| -rw-r--r-- | mm/init-mm.c | 11 |
1 files changed, 11 insertions, 0 deletions
diff --git a/mm/init-mm.c b/mm/init-mm.c index f0179c9c04c2..a787a319211e 100644 --- a/mm/init-mm.c +++ b/mm/init-mm.c @@ -15,6 +15,16 @@ #define INIT_MM_CONTEXT(name) #endif +/* + * For dynamically allocated mm_structs, there is a dynamically sized cpumask + * at the end of the structure, the size of which depends on the maximum CPU + * number the system can see. That way we allocate only as much memory for + * mm_cpumask() as needed for the hundreds, or thousands of processes that + * a system typically runs. + * + * Since there is only one init_mm in the entire system, keep it simple + * and size this cpu_bitmask to NR_CPUS. + */ struct mm_struct init_mm = { .mm_rb = RB_ROOT, .pgd = swapper_pg_dir, @@ -25,5 +35,6 @@ struct mm_struct init_mm = { .arg_lock = __SPIN_LOCK_UNLOCKED(init_mm.arg_lock), .mmlist = LIST_HEAD_INIT(init_mm.mmlist), .user_ns = &init_user_ns, + .cpu_bitmap = { [BITS_TO_LONGS(NR_CPUS)] = 0}, INIT_MM_CONTEXT(init_mm) }; |
