mmu_gather: Remove per arch tlb_{start,end}_vma()
Scattered across the archs are 3 basic forms of tlb_{start,end}_vma(). Provide two new MMU_GATHER_knobs to enumerate them and remove the per arch tlb_{start,end}_vma() implementations. - MMU_GATHER_NO_FLUSH_CACHE indicates the arch has flush_cache_range() but does *NOT* want to call it for each VMA. - MMU_GATHER_MERGE_VMAS indicates the arch wants to merge the invalidate across multiple VMAs if possible. With these it is possible to capture the three forms: 1) empty stubs; select MMU_GATHER_NO_FLUSH_CACHE and MMU_GATHER_MERGE_VMAS 2) start: flush_cache_range(), end: empty; select MMU_GATHER_MERGE_VMAS 3) start: flush_cache_range(), end: flush_tlb_range(); default Obviously, if the architecture does not have flush_cache_range() then it also doesn't need to select MMU_GATHER_NO_FLUSH_CACHE. Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Acked-by: Will Deacon <will@kernel.org> Cc: David Miller <davem@davemloft.net> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This commit is contained in:
parent
23a67619bc
commit
1e9fdf21a4
|
@ -438,6 +438,13 @@ config MMU_GATHER_PAGE_SIZE
|
|||
|
||||
config MMU_GATHER_NO_RANGE
|
||||
bool
|
||||
select MMU_GATHER_MERGE_VMAS
|
||||
|
||||
config MMU_GATHER_NO_FLUSH_CACHE
|
||||
bool
|
||||
|
||||
config MMU_GATHER_MERGE_VMAS
|
||||
bool
|
||||
|
||||
config MMU_GATHER_NO_GATHER
|
||||
bool
|
||||
|
|
|
@ -4,19 +4,6 @@
|
|||
#define __ASM_CSKY_TLB_H
|
||||
|
||||
#include <asm/cacheflush.h>
|
||||
|
||||
#define tlb_start_vma(tlb, vma) \
|
||||
do { \
|
||||
if (!(tlb)->fullmm) \
|
||||
flush_cache_range(vma, (vma)->vm_start, (vma)->vm_end); \
|
||||
} while (0)
|
||||
|
||||
#define tlb_end_vma(tlb, vma) \
|
||||
do { \
|
||||
if (!(tlb)->fullmm) \
|
||||
flush_tlb_range(vma, (vma)->vm_start, (vma)->vm_end); \
|
||||
} while (0)
|
||||
|
||||
#define tlb_flush(tlb) flush_tlb_mm((tlb)->mm)
|
||||
|
||||
#include <asm-generic/tlb.h>
|
||||
|
|
|
@ -108,6 +108,7 @@ config LOONGARCH
|
|||
select TRACE_IRQFLAGS_SUPPORT
|
||||
select USE_PERCPU_NUMA_NODE_ID
|
||||
select ZONE_DMA32
|
||||
select MMU_GATHER_MERGE_VMAS if MMU
|
||||
|
||||
config 32BIT
|
||||
bool
|
||||
|
|
|
@ -137,16 +137,6 @@ static inline void invtlb_all(u32 op, u32 info, u64 addr)
|
|||
);
|
||||
}
|
||||
|
||||
/*
|
||||
* LoongArch doesn't need any special per-pte or per-vma handling, except
|
||||
* we need to flush cache for area to be unmapped.
|
||||
*/
|
||||
#define tlb_start_vma(tlb, vma) \
|
||||
do { \
|
||||
if (!(tlb)->fullmm) \
|
||||
flush_cache_range(vma, vma->vm_start, vma->vm_end); \
|
||||
} while (0)
|
||||
#define tlb_end_vma(tlb, vma) do { } while (0)
|
||||
#define __tlb_remove_tlb_entry(tlb, ptep, address) do { } while (0)
|
||||
|
||||
static void tlb_flush(struct mmu_gather *tlb);
|
||||
|
|
|
@ -256,6 +256,7 @@ config PPC
|
|||
select IRQ_FORCED_THREADING
|
||||
select MMU_GATHER_PAGE_SIZE
|
||||
select MMU_GATHER_RCU_TABLE_FREE
|
||||
select MMU_GATHER_MERGE_VMAS
|
||||
select MODULES_USE_ELF_RELA
|
||||
select NEED_DMA_MAP_STATE if PPC64 || NOT_COHERENT_CACHE
|
||||
select NEED_PER_CPU_EMBED_FIRST_CHUNK if PPC64
|
||||
|
|
|
@ -19,8 +19,6 @@
|
|||
|
||||
#include <linux/pagemap.h>
|
||||
|
||||
#define tlb_start_vma(tlb, vma) do { } while (0)
|
||||
#define tlb_end_vma(tlb, vma) do { } while (0)
|
||||
#define __tlb_remove_tlb_entry __tlb_remove_tlb_entry
|
||||
|
||||
#define tlb_flush tlb_flush
|
||||
|
|
|
@ -204,6 +204,7 @@ config S390
|
|||
select IOMMU_SUPPORT if PCI
|
||||
select MMU_GATHER_NO_GATHER
|
||||
select MMU_GATHER_RCU_TABLE_FREE
|
||||
select MMU_GATHER_MERGE_VMAS
|
||||
select MODULES_USE_ELF_RELA
|
||||
select NEED_DMA_MAP_STATE if PCI
|
||||
select NEED_SG_DMA_LENGTH if PCI
|
||||
|
|
|
@ -27,9 +27,6 @@ static inline void tlb_flush(struct mmu_gather *tlb);
|
|||
static inline bool __tlb_remove_page_size(struct mmu_gather *tlb,
|
||||
struct page *page, int page_size);
|
||||
|
||||
#define tlb_start_vma(tlb, vma) do { } while (0)
|
||||
#define tlb_end_vma(tlb, vma) do { } while (0)
|
||||
|
||||
#define tlb_flush tlb_flush
|
||||
#define pte_free_tlb pte_free_tlb
|
||||
#define pmd_free_tlb pmd_free_tlb
|
||||
|
|
|
@ -67,6 +67,8 @@ config SPARC64
|
|||
select HAVE_KRETPROBES
|
||||
select HAVE_KPROBES
|
||||
select MMU_GATHER_RCU_TABLE_FREE if SMP
|
||||
select MMU_GATHER_MERGE_VMAS
|
||||
select MMU_GATHER_NO_FLUSH_CACHE
|
||||
select HAVE_ARCH_TRANSPARENT_HUGEPAGE
|
||||
select HAVE_DYNAMIC_FTRACE
|
||||
select HAVE_FTRACE_MCOUNT_RECORD
|
||||
|
|
|
@ -22,8 +22,6 @@ void smp_flush_tlb_mm(struct mm_struct *mm);
|
|||
void __flush_tlb_pending(unsigned long, unsigned long, unsigned long *);
|
||||
void flush_tlb_pending(void);
|
||||
|
||||
#define tlb_start_vma(tlb, vma) do { } while (0)
|
||||
#define tlb_end_vma(tlb, vma) do { } while (0)
|
||||
#define tlb_flush(tlb) flush_tlb_pending()
|
||||
|
||||
/*
|
||||
|
|
|
@ -245,6 +245,7 @@ config X86
|
|||
select HAVE_PERF_REGS
|
||||
select HAVE_PERF_USER_STACK_DUMP
|
||||
select MMU_GATHER_RCU_TABLE_FREE if PARAVIRT
|
||||
select MMU_GATHER_MERGE_VMAS
|
||||
select HAVE_POSIX_CPU_TIMERS_TASK_WORK
|
||||
select HAVE_REGS_AND_STACK_ACCESS_API
|
||||
select HAVE_RELIABLE_STACKTRACE if UNWINDER_ORC || STACK_VALIDATION
|
||||
|
|
|
@ -2,9 +2,6 @@
|
|||
#ifndef _ASM_X86_TLB_H
|
||||
#define _ASM_X86_TLB_H
|
||||
|
||||
#define tlb_start_vma(tlb, vma) do { } while (0)
|
||||
#define tlb_end_vma(tlb, vma) do { } while (0)
|
||||
|
||||
#define tlb_flush tlb_flush
|
||||
static inline void tlb_flush(struct mmu_gather *tlb);
|
||||
|
||||
|
|
|
@ -158,9 +158,24 @@
|
|||
* Useful if your architecture doesn't use IPIs for remote TLB invalidates
|
||||
* and therefore doesn't naturally serialize with software page-table walkers.
|
||||
*
|
||||
* MMU_GATHER_NO_FLUSH_CACHE
|
||||
*
|
||||
* Indicates the architecture has flush_cache_range() but it needs *NOT* be called
|
||||
* before unmapping a VMA.
|
||||
*
|
||||
* NOTE: strictly speaking we shouldn't have this knob and instead rely on
|
||||
* flush_cache_range() being a NOP, except Sparc64 seems to be
|
||||
* different here.
|
||||
*
|
||||
* MMU_GATHER_MERGE_VMAS
|
||||
*
|
||||
* Indicates the architecture wants to merge ranges over VMAs; typical when
|
||||
* multiple range invalidates are more expensive than a full invalidate.
|
||||
*
|
||||
* MMU_GATHER_NO_RANGE
|
||||
*
|
||||
* Use this if your architecture lacks an efficient flush_tlb_range().
|
||||
* Use this if your architecture lacks an efficient flush_tlb_range(). This
|
||||
* option implies MMU_GATHER_MERGE_VMAS above.
|
||||
*
|
||||
* MMU_GATHER_NO_GATHER
|
||||
*
|
||||
|
@ -493,14 +508,16 @@ static inline void tlb_start_vma(struct mmu_gather *tlb, struct vm_area_struct *
|
|||
return;
|
||||
|
||||
tlb_update_vma_flags(tlb, vma);
|
||||
#ifndef CONFIG_MMU_GATHER_NO_FLUSH_CACHE
|
||||
flush_cache_range(vma, vma->vm_start, vma->vm_end);
|
||||
#endif
|
||||
}
|
||||
#endif
|
||||
|
||||
#ifndef tlb_end_vma
|
||||
static inline void tlb_end_vma(struct mmu_gather *tlb, struct vm_area_struct *vma)
|
||||
{
|
||||
if (tlb->fullmm)
|
||||
if (tlb->fullmm || IS_ENABLED(CONFIG_MMU_GATHER_MERGE_VMAS))
|
||||
return;
|
||||
|
||||
/*
|
||||
|
|
Loading…
Reference in New Issue