diff options
author | Marcel Ziswiler <marcel.ziswiler@toradex.com> | 2021-07-07 01:19:43 +0200 |
---|---|---|
committer | Marcel Ziswiler <marcel.ziswiler@toradex.com> | 2021-07-07 01:19:43 +0200 |
commit | d900385139e5aa8d584dee92c87bb85d0226253e (patch) | |
tree | 26aa082f242221c535f2d8aa03b0c314c713e8ea /arch/sparc | |
parent | 56168452b2a2fa8b4efc664d9fcb08536486a1ba (diff) | |
parent | 200ecf5055dfba12b9bff6984830a7cdddee8ab1 (diff) |
Merge tag 'v4.4.274' into toradex_vf_4.4-next
Linux 4.4.274
Diffstat (limited to 'arch/sparc')
-rw-r--r-- | arch/sparc/Kconfig | 2 | ||||
-rw-r--r-- | arch/sparc/kernel/smp_64.c | 65 | ||||
-rw-r--r-- | arch/sparc/lib/memset.S | 1 |
3 files changed, 16 insertions, 52 deletions
diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig index 94f4ac21761b..f42973685fd2 100644 --- a/arch/sparc/Kconfig +++ b/arch/sparc/Kconfig @@ -539,7 +539,7 @@ config COMPAT bool depends on SPARC64 default y - select COMPAT_BINFMT_ELF + select COMPAT_BINFMT_ELF if BINFMT_ELF select HAVE_UID16 select ARCH_WANT_OLD_COMPAT_IPC select COMPAT_OLD_SIGACTION diff --git a/arch/sparc/kernel/smp_64.c b/arch/sparc/kernel/smp_64.c index 46866b2097e8..bd27e86ce36d 100644 --- a/arch/sparc/kernel/smp_64.c +++ b/arch/sparc/kernel/smp_64.c @@ -1030,38 +1030,9 @@ void smp_fetch_global_pmu(void) * are flush_tlb_*() routines, and these run after flush_cache_*() * which performs the flushw. * - * The SMP TLB coherency scheme we use works as follows: - * - * 1) mm->cpu_vm_mask is a bit mask of which cpus an address - * space has (potentially) executed on, this is the heuristic - * we use to avoid doing cross calls. - * - * Also, for flushing from kswapd and also for clones, we - * use cpu_vm_mask as the list of cpus to make run the TLB. - * - * 2) TLB context numbers are shared globally across all processors - * in the system, this allows us to play several games to avoid - * cross calls. - * - * One invariant is that when a cpu switches to a process, and - * that processes tsk->active_mm->cpu_vm_mask does not have the - * current cpu's bit set, that tlb context is flushed locally. - * - * If the address space is non-shared (ie. mm->count == 1) we avoid - * cross calls when we want to flush the currently running process's - * tlb state. This is done by clearing all cpu bits except the current - * processor's in current->mm->cpu_vm_mask and performing the - * flush locally only. This will force any subsequent cpus which run - * this task to flush the context from the local tlb if the process - * migrates to another cpu (again). - * - * 3) For shared address spaces (threads) and swapping we bite the - * bullet for most cases and perform the cross call (but only to - * the cpus listed in cpu_vm_mask). - * - * The performance gain from "optimizing" away the cross call for threads is - * questionable (in theory the big win for threads is the massive sharing of - * address space state across processors). + * mm->cpu_vm_mask is a bit mask of which cpus an address + * space has (potentially) executed on, this is the heuristic + * we use to limit cross calls. */ /* This currently is only used by the hugetlb arch pre-fault @@ -1071,18 +1042,13 @@ void smp_fetch_global_pmu(void) void smp_flush_tlb_mm(struct mm_struct *mm) { u32 ctx = CTX_HWBITS(mm->context); - int cpu = get_cpu(); - if (atomic_read(&mm->mm_users) == 1) { - cpumask_copy(mm_cpumask(mm), cpumask_of(cpu)); - goto local_flush_and_out; - } + get_cpu(); smp_cross_call_masked(&xcall_flush_tlb_mm, ctx, 0, 0, mm_cpumask(mm)); -local_flush_and_out: __flush_tlb_mm(ctx, SECONDARY_CONTEXT); put_cpu(); @@ -1105,17 +1071,15 @@ void smp_flush_tlb_pending(struct mm_struct *mm, unsigned long nr, unsigned long { u32 ctx = CTX_HWBITS(mm->context); struct tlb_pending_info info; - int cpu = get_cpu(); + + get_cpu(); info.ctx = ctx; info.nr = nr; info.vaddrs = vaddrs; - if (mm == current->mm && atomic_read(&mm->mm_users) == 1) - cpumask_copy(mm_cpumask(mm), cpumask_of(cpu)); - else - smp_call_function_many(mm_cpumask(mm), tlb_pending_func, - &info, 1); + smp_call_function_many(mm_cpumask(mm), tlb_pending_func, + &info, 1); __flush_tlb_pending(ctx, nr, vaddrs); @@ -1125,14 +1089,13 @@ void smp_flush_tlb_pending(struct mm_struct *mm, unsigned long nr, unsigned long void smp_flush_tlb_page(struct mm_struct *mm, unsigned long vaddr) { unsigned long context = CTX_HWBITS(mm->context); - int cpu = get_cpu(); - if (mm == current->mm && atomic_read(&mm->mm_users) == 1) - cpumask_copy(mm_cpumask(mm), cpumask_of(cpu)); - else - smp_cross_call_masked(&xcall_flush_tlb_page, - context, vaddr, 0, - mm_cpumask(mm)); + get_cpu(); + + smp_cross_call_masked(&xcall_flush_tlb_page, + context, vaddr, 0, + mm_cpumask(mm)); + __flush_tlb_page(context, vaddr); put_cpu(); diff --git a/arch/sparc/lib/memset.S b/arch/sparc/lib/memset.S index f75e6906df14..19000777f7c9 100644 --- a/arch/sparc/lib/memset.S +++ b/arch/sparc/lib/memset.S @@ -137,6 +137,7 @@ __bzero: ZERO_LAST_BLOCKS(%o0, 0x48, %g2) ZERO_LAST_BLOCKS(%o0, 0x08, %g2) 13: + EXT(12b, 13b, 21f) be 8f andcc %o1, 4, %g0 |