x86/tlb: do flush_tlb_kernel_range by 'invlpg'

This patch do flush_tlb_kernel_range by 'invlpg'. The performance pay
and gain was analyzed in previous patch
(x86/flush_tlb: try flush_tlb_single one by one in flush_tlb_range).

In the testing: http://lkml.org/lkml/2012/6/21/10

The pay is mostly covered by long kernel path, but the gain is still
quite clear, memory access in user APP can increase 30+% when kernel
execute this funtion.

Signed-off-by: Alex Shi <alex.shi@intel.com>
Link: http://lkml.kernel.org/r/1340845344-27557-10-git-send-email-alex.shi@intel.com
Signed-off-by: H. Peter Anvin <hpa@zytor.com>

diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index 621b959e1dbf22410e36a7dc6d48ef9e5219bda2..b5a27bd77669a09af0f32af529452d786240a496 100644 (file)
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -123,6 +123,12 @@ static inline void reset_lazy_tlbstate(void)
 {
 }
 
+static inline void flush_tlb_kernel_range(unsigned long start,
+                                         unsigned long end)
+{
+       flush_tlb_all();
+}
+
 #else  /* SMP */
 
 #include <asm/smp.h>
@@ -139,6 +145,7 @@ extern void flush_tlb_current_task(void);
 extern void flush_tlb_page(struct vm_area_struct *, unsigned long);
 extern void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start,
                                unsigned long end, unsigned long vmflag);
+extern void flush_tlb_kernel_range(unsigned long start, unsigned long end);
 
 #define flush_tlb()    flush_tlb_current_task()
 
@@ -168,10 +175,4 @@ static inline void reset_lazy_tlbstate(void)
        native_flush_tlb_others(mask, mm, start, end)
 #endif
 
-static inline void flush_tlb_kernel_range(unsigned long start,
-                                         unsigned long end)
-{
-       flush_tlb_all();
-}
-
 #endif /* _ASM_X86_TLBFLUSH_H */

diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 2b5f506a7655596ae8472218bd5d9d1e4a8ef6e9..613cd83e8c0cf424bbf627973fb4af54634d8e8e 100644 (file)
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -264,6 +264,36 @@ void flush_tlb_all(void)
        on_each_cpu(do_flush_tlb_all, NULL, 1);
 }
 
+static void do_kernel_range_flush(void *info)
+{
+       struct flush_tlb_info *f = info;
+       unsigned long addr;
+
+       /* flush range by one by one 'invlpg' */
+       for (addr = f->flush_start; addr < f->flush_end; addr += PAGE_SIZE)
+               __flush_tlb_single(addr);
+}
+
+void flush_tlb_kernel_range(unsigned long start, unsigned long end)
+{
+       unsigned act_entries;
+       struct flush_tlb_info info;
+
+       /* In modern CPU, last level tlb used for both data/ins */
+       act_entries = tlb_lld_4k[ENTRIES];
+
+       /* Balance as user space task's flush, a bit conservative */
+       if (end == TLB_FLUSH_ALL || tlb_flushall_shift == -1 ||
+               (end - start) >> PAGE_SHIFT > act_entries >> tlb_flushall_shift)
+
+               on_each_cpu(do_flush_tlb_all, NULL, 1);
+       else {
+               info.flush_start = start;
+               info.flush_end = end;
+               on_each_cpu(do_kernel_range_flush, &info, 1);
+       }
+}
+
 #ifdef CONFIG_DEBUG_TLBFLUSH
 static ssize_t tlbflush_read_file(struct file *file, char __user *user_buf,
                             size_t count, loff_t *ppos)