From: Barry Song <v-songbaohua@xxxxxxxx>
on x86, batched and deferred tlb shootdown has lead to 90%
performance increase on tlb shootdown. on arm64, HW can do
tlb shootdown without software IPI. But sync tlbi is still
quite expensive.
Even running a simplest program which requires swapout can
prove this is true,
#include <sys/types.h>
#include <unistd.h>
#include <sys/mman.h>
#include <string.h>
int main()
{
#define SIZE (1 * 1024 * 1024)
volatile unsigned char *p = mmap(NULL, SIZE, PROT_READ | PROT_WRITE,
MAP_SHARED | MAP_ANONYMOUS, -1, 0);
memset(p, 0x88, SIZE);
for (int k = 0; k < 10000; k++) {
/* swap in */
for (int i = 0; i < SIZE; i += 4096) {
(void)p[i];
}
/* swap out */
madvise(p, SIZE, MADV_PAGEOUT);
}
}
Perf result on snapdragon 888 with 8 cores by using zRAM
as the swap block device.
~ # perf record taskset -c 4 ./a.out
[ perf record: Woken up 10 times to write data ]
[ perf record: Captured and wrote 2.297 MB perf.data (60084 samples) ]
~ # perf report
# To display the perf.data header info, please use --header/--header-only options.
# To display the perf.data header info, please use --header/--header-only options.
#
#
# Total Lost Samples: 0
#
# Samples: 60K of event 'cycles'
# Event count (approx.): 35706225414
#
# Overhead Command Shared Object Symbol
# ........ ....... ................. .............................................................................
#
21.07% a.out [kernel.kallsyms] [k] _raw_spin_unlock_irq
8.23% a.out [kernel.kallsyms] [k] _raw_spin_unlock_irqrestore
6.67% a.out [kernel.kallsyms] [k] filemap_map_pages
6.16% a.out [kernel.kallsyms] [k] __zram_bvec_write
5.36% a.out [kernel.kallsyms] [k] ptep_clear_flush
3.71% a.out [kernel.kallsyms] [k] _raw_spin_lock
3.49% a.out [kernel.kallsyms] [k] memset64
1.63% a.out [kernel.kallsyms] [k] clear_page
1.42% a.out [kernel.kallsyms] [k] _raw_spin_unlock
1.26% a.out [kernel.kallsyms] [k] mod_zone_state.llvm.8525150236079521930
1.23% a.out [kernel.kallsyms] [k] xas_load
1.15% a.out [kernel.kallsyms] [k] zram_slot_lock
ptep_clear_flush() takes 5.36% CPU in the micro-benchmark
swapping in/out a page mapped by only one process. If the
page is mapped by multiple processes, typically, like more
than 100 on a phone, the overhead would be much higher as
we have to run tlb flush 100 times for one single page.
Plus, tlb flush overhead will increase with the number
of CPU cores due to the bad scalability of tlb shootdown
in HW, so those ARM64 servers should expect much higher
overhead.
Further perf annonate shows 95% cpu time of ptep_clear_flush
is actually used by the final dsb() to wait for the completion
of tlb flush. This provides us a very good chance to leverage
the existing batched tlb in kernel. The minimum modification
is that we only send async tlbi in the first stage and we send
dsb while we have to sync in the second stage.
With the above simplest micro benchmark, collapsed time to
finish the program decreases around 5%.
Typical collapsed time w/o patch:
~ # time taskset -c 4 ./a.out
0.21user 14.34system 0:14.69elapsed
w/ patch:
~ # time taskset -c 4 ./a.out
0.22user 13.45system 0:13.80elapsed
Also, Yicong Yang added the following observation.
Tested with benchmark in the commit on Kunpeng920 arm64 server,
observed an improvement around 12.5% with command
`time ./swap_bench`.
w/o w/
real 0m13.460s 0m11.771s
user 0m0.248s 0m0.279s
sys 0m12.039s 0m11.458s
Originally it's noticed a 16.99% overhead of ptep_clear_flush()
which has been eliminated by this patch:
[root@localhost yang]# perf record -- ./swap_bench && perf report
[...]
16.99% swap_bench [kernel.kallsyms] [k] ptep_clear_flush
Cc: Jonathan Corbet <corbet@xxxxxxx>
Cc: Nadav Amit <namit@xxxxxxxxxx>
Cc: Mel Gorman <mgorman@xxxxxxx>
Tested-by: Yicong Yang <yangyicong@xxxxxxxxxxxxx>
Tested-by: Xin Hao <xhao@xxxxxxxxxxxxxxxxx>
Signed-off-by: Barry Song <v-songbaohua@xxxxxxxx>
Signed-off-by: Yicong Yang <yangyicong@xxxxxxxxxxxxx>
Reviewed-by: Kefeng Wang <wangkefeng.wang@xxxxxxxxxx>
---
.../features/vm/TLB/arch-support.txt | 2 +-
arch/arm64/Kconfig | 1 +
arch/arm64/include/asm/tlbbatch.h | 12 ++++++
arch/arm64/include/asm/tlbflush.h | 37 ++++++++++++++++++-
arch/x86/include/asm/tlbflush.h | 3 +-
mm/rmap.c | 10 +++--
6 files changed, 57 insertions(+), 8 deletions(-)
create mode 100644 arch/arm64/include/asm/tlbbatch.h
diff --git a/Documentation/features/vm/TLB/arch-support.txt b/Documentation/features/vm/TLB/arch-support.txt
index 039e4e91ada3..2caf815d7c6c 100644
--- a/Documentation/features/vm/TLB/arch-support.txt
+++ b/Documentation/features/vm/TLB/arch-support.txt
@@ -9,7 +9,7 @@
| alpha: | TODO |
| arc: | TODO |
| arm: | TODO |
- | arm64: | N/A |
+ | arm64: | ok |
| csky: | TODO |
| hexagon: | TODO |
| ia64: | TODO |
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 1ce7685ad5de..40da6984f303 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -93,6 +93,7 @@ config ARM64
select ARCH_SUPPORTS_INT128 if CC_HAS_INT128
select ARCH_SUPPORTS_NUMA_BALANCING
select ARCH_SUPPORTS_PAGE_TABLE_CHECK
+ select ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH
select ARCH_WANT_COMPAT_IPC_PARSE_VERSION if COMPAT
select ARCH_WANT_DEFAULT_BPF_JIT
select ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT
diff --git a/arch/arm64/include/asm/tlbbatch.h b/arch/arm64/include/asm/tlbbatch.h
new file mode 100644
index 000000000000..fedb0b87b8db
--- /dev/null
+++ b/arch/arm64/include/asm/tlbbatch.h
@@ -0,0 +1,12 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ARCH_ARM64_TLBBATCH_H
+#define _ARCH_ARM64_TLBBATCH_H
+
+struct arch_tlbflush_unmap_batch {
+ /*
+ * For arm64, HW can do tlb shootdown, so we don't
+ * need to record cpumask for sending IPI
+ */
+};
+
+#endif /* _ARCH_ARM64_TLBBATCH_H */
diff --git a/arch/arm64/include/asm/tlbflush.h b/arch/arm64/include/asm/tlbflush.h
index 412a3b9a3c25..1b4df0352960 100644
--- a/arch/arm64/include/asm/tlbflush.h
+++ b/arch/arm64/include/asm/tlbflush.h
@@ -254,17 +254,24 @@ static inline void flush_tlb_mm(struct mm_struct *mm)
dsb(ish);
}
-static inline void flush_tlb_page_nosync(struct vm_area_struct *vma,
+
+static inline void __flush_tlb_page_nosync(struct mm_struct *mm,
unsigned long uaddr)
{
unsigned long addr;
dsb(ishst);
- addr = __TLBI_VADDR(uaddr, ASID(vma->vm_mm));
+ addr = __TLBI_VADDR(uaddr, ASID(mm));
__tlbi(vale1is, addr);
__tlbi_user(vale1is, addr);
}
+static inline void flush_tlb_page_nosync(struct vm_area_struct *vma,
+ unsigned long uaddr)
+{
+ return __flush_tlb_page_nosync(vma->vm_mm, uaddr);
+}
+
static inline void flush_tlb_page(struct vm_area_struct *vma,
unsigned long uaddr)
{
@@ -272,6 +279,32 @@ static inline void flush_tlb_page(struct vm_area_struct *vma,
dsb(ish);
}
+static inline bool arch_tlbbatch_should_defer(struct mm_struct *mm)
+{
+ /* for small systems with small number of CPUs, TLB shootdown is cheap */
+ if (num_online_cpus() <= 4)
+ return false;
+
+#ifdef CONFIG_ARM64_WORKAROUND_REPEAT_TLBI
+ if (unlikely(this_cpu_has_cap(ARM64_WORKAROUND_REPEAT_TLBI)))
+ return false;
+#endif
+
+ return true;
+}
+
+static inline void arch_tlbbatch_add_mm(struct arch_tlbflush_unmap_batch *batch,
+ struct mm_struct *mm,
+ unsigned long uaddr)
+{
+ __flush_tlb_page_nosync(mm, uaddr);
+}
+
+static inline void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch)
+{
+ dsb(ish);
+}
+
/*
* This is meant to avoid soft lock-ups on large TLB flushing ranges and not
* necessarily a performance improvement.
diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index 8a497d902c16..5bd78ae55cd4 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -264,7 +264,8 @@ static inline u64 inc_mm_tlb_gen(struct mm_struct *mm)
}
static inline void arch_tlbbatch_add_mm(struct arch_tlbflush_unmap_batch *batch,
- struct mm_struct *mm)
+ struct mm_struct *mm,
+ unsigned long uaddr)
{
inc_mm_tlb_gen(mm);
cpumask_or(&batch->cpumask, &batch->cpumask, mm_cpumask(mm));
diff --git a/mm/rmap.c b/mm/rmap.c
index cd8cf5cb0b01..e060cc0187cd 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -645,12 +645,13 @@ void try_to_unmap_flush_dirty(void)
#define TLB_FLUSH_BATCH_PENDING_LARGE \
(TLB_FLUSH_BATCH_PENDING_MASK / 2)
-static void set_tlb_ubc_flush_pending(struct mm_struct *mm, bool writable)
+static void set_tlb_ubc_flush_pending(struct mm_struct *mm, bool writable,
+ unsigned long uaddr)
{
struct tlbflush_unmap_batch *tlb_ubc = ¤t->tlb_ubc;
int batch, nbatch;
- arch_tlbbatch_add_mm(&tlb_ubc->arch, mm);
+ arch_tlbbatch_add_mm(&tlb_ubc->arch, mm, uaddr);
tlb_ubc->flush_required = true;
/*
@@ -728,7 +729,8 @@ void flush_tlb_batched_pending(struct mm_struct *mm)
}
}
#else
-static void set_tlb_ubc_flush_pending(struct mm_struct *mm, bool writable)
+static void set_tlb_ubc_flush_pending(struct mm_struct *mm, bool writable,
+ unsigned long uaddr)
{
}
@@ -1590,7 +1592,7 @@ static bool try_to_unmap_one(struct folio *folio, struct vm_area_struct *vma,
*/
pteval = ptep_get_and_clear(mm, address, pvmw.pte);
- set_tlb_ubc_flush_pending(mm, pte_dirty(pteval));
+ set_tlb_ubc_flush_pending(mm, pte_dirty(pteval), address);
} else {
pteval = ptep_clear_flush(vma, address, pvmw.pte);
}
--
2.24.0
