| Message ID | 1495954328-28736-3-git-send-email-noamca@mellanox.com |
|---|---|
| State | New |
| Headers | show |
On 05/27/2017 11:51 PM, Noam Camus wrote: > From: Noam Camus <noamca@mellanox.com> > > This patch is derived due to performance issue. > The use case is a page fault that resides on more than the local cpu. > Trying to broadcast all CPUs results on performance degradation. > So we try to avoid this by sending only to the relevant CPUs. > > Signed-off-by: Noam Camus <noamca@mellanox.com> > Reviewed-by: Alexey Brodkin <abrodkin@synopsys.com> This indeed looks like a nice optimization - do you have any performance numbers when say running hackbench or other multi-threaded workloads ! -Vineet > --- > arch/arc/include/asm/cacheflush.h | 3 ++- > arch/arc/mm/cache.c | 12 ++++++++++-- > arch/arc/mm/tlb.c | 2 +- > 3 files changed, 13 insertions(+), 4 deletions(-) > > diff --git a/arch/arc/include/asm/cacheflush.h b/arch/arc/include/asm/cacheflush.h > index fc662f4..716dba1 100644 > --- a/arch/arc/include/asm/cacheflush.h > +++ b/arch/arc/include/asm/cacheflush.h > @@ -33,7 +33,8 @@ > > void flush_icache_range(unsigned long kstart, unsigned long kend); > void __sync_icache_dcache(phys_addr_t paddr, unsigned long vaddr, int len); > -void __inv_icache_page(phys_addr_t paddr, unsigned long vaddr); > +void __inv_icache_page(struct vm_area_struct *vma, > + phys_addr_t paddr, unsigned long vaddr); > void __flush_dcache_page(phys_addr_t paddr, unsigned long vaddr); > > #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1 > diff --git a/arch/arc/mm/cache.c b/arch/arc/mm/cache.c > index 7d3e79b..e1ea57f 100644 > --- a/arch/arc/mm/cache.c > +++ b/arch/arc/mm/cache.c > @@ -934,9 +934,17 @@ void __sync_icache_dcache(phys_addr_t paddr, unsigned long vaddr, int len) > } > > /* wrapper to compile time eliminate alignment checks in flush loop */ > -void __inv_icache_page(phys_addr_t paddr, unsigned long vaddr) > +void __inv_icache_page(struct vm_area_struct *vma, > + phys_addr_t paddr, unsigned long vaddr) > { > - __ic_line_inv_vaddr(paddr, vaddr, PAGE_SIZE); > + struct ic_inv_args ic_inv = { > + .paddr = paddr, > + .vaddr = vaddr, > + .sz = PAGE_SIZE > + }; > + > + on_each_cpu_mask(mm_cpumask(vma->vm_mm), > + __ic_line_inv_vaddr_helper, &ic_inv, 1); > } > > /* > diff --git a/arch/arc/mm/tlb.c b/arch/arc/mm/tlb.c > index c5e70d8..a095608 100644 > --- a/arch/arc/mm/tlb.c > +++ b/arch/arc/mm/tlb.c > @@ -626,7 +626,7 @@ void update_mmu_cache(struct vm_area_struct *vma, unsigned long vaddr_unaligned, > > /* invalidate any existing icache lines (U-mapping) */ > if (vma->vm_flags & VM_EXEC) > - __inv_icache_page(paddr, vaddr); > + __inv_icache_page(vma, paddr, vaddr); > } > } > } >
diff --git a/arch/arc/include/asm/cacheflush.h b/arch/arc/include/asm/cacheflush.h index fc662f4..716dba1 100644 --- a/arch/arc/include/asm/cacheflush.h +++ b/arch/arc/include/asm/cacheflush.h @@ -33,7 +33,8 @@ void flush_icache_range(unsigned long kstart, unsigned long kend); void __sync_icache_dcache(phys_addr_t paddr, unsigned long vaddr, int len); -void __inv_icache_page(phys_addr_t paddr, unsigned long vaddr); +void __inv_icache_page(struct vm_area_struct *vma, + phys_addr_t paddr, unsigned long vaddr); void __flush_dcache_page(phys_addr_t paddr, unsigned long vaddr); #define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE 1 diff --git a/arch/arc/mm/cache.c b/arch/arc/mm/cache.c index 7d3e79b..e1ea57f 100644 --- a/arch/arc/mm/cache.c +++ b/arch/arc/mm/cache.c @@ -934,9 +934,17 @@ void __sync_icache_dcache(phys_addr_t paddr, unsigned long vaddr, int len) } /* wrapper to compile time eliminate alignment checks in flush loop */ -void __inv_icache_page(phys_addr_t paddr, unsigned long vaddr) +void __inv_icache_page(struct vm_area_struct *vma, + phys_addr_t paddr, unsigned long vaddr) { - __ic_line_inv_vaddr(paddr, vaddr, PAGE_SIZE); + struct ic_inv_args ic_inv = { + .paddr = paddr, + .vaddr = vaddr, + .sz = PAGE_SIZE + }; + + on_each_cpu_mask(mm_cpumask(vma->vm_mm), + __ic_line_inv_vaddr_helper, &ic_inv, 1); } /* diff --git a/arch/arc/mm/tlb.c b/arch/arc/mm/tlb.c index c5e70d8..a095608 100644 --- a/arch/arc/mm/tlb.c +++ b/arch/arc/mm/tlb.c @@ -626,7 +626,7 @@ void update_mmu_cache(struct vm_area_struct *vma, unsigned long vaddr_unaligned, /* invalidate any existing icache lines (U-mapping) */ if (vma->vm_flags & VM_EXEC) - __inv_icache_page(paddr, vaddr); + __inv_icache_page(vma, paddr, vaddr); } } }