arm64/mm: Optimize loop to reduce redundant operations of contpte_ptep_get

This commit optimizes the contpte_ptep_get and contpte_ptep_get_lockless
function by adding early termination logic. It checks if the dirty and
young bits of orig_pte are already set and skips redundant bit-setting
operations during the loop. This reduces unnecessary iterations and
improves performance.

In order to verify the optimization performance, a test function has been
designed. The function's execution time and instruction statistics have
been traced using perf, and the following are the operation results on a
certain Qualcomm mobile phone chip:

Test Code:
	#include <stdlib.h>
	#include <sys/mman.h>
	#include <stdio.h>

	#define PAGE_SIZE 4096
	#define CONT_PTES 16
	#define TEST_SIZE (4096* CONT_PTES * PAGE_SIZE)
	#define YOUNG_BIT 8
	void rwdata(char *buf)
	{
		for (size_t i = 0; i < TEST_SIZE; i += PAGE_SIZE) {
			buf[i] = 'a';
			volatile char c = buf[i];
		}
	}
	void clear_young_dirty(char *buf)
	{
		if (madvise(buf, TEST_SIZE, MADV_FREE) == -1) {
			perror("madvise free failed");
			free(buf);
			exit(EXIT_FAILURE);
		}
		if (madvise(buf, TEST_SIZE, MADV_COLD) == -1) {
			perror("madvise free failed");
			free(buf);
			exit(EXIT_FAILURE);
		}
	}
	void set_one_young(char *buf)
	{
		for (size_t i = 0; i < TEST_SIZE; i += CONT_PTES * PAGE_SIZE) {
			volatile char c = buf[i + YOUNG_BIT * PAGE_SIZE];
		}
	}

	void test_contpte_perf() {
		char *buf;
		int ret = posix_memalign((void **)&buf, CONT_PTES * PAGE_SIZE,
				TEST_SIZE);
		if ((ret != 0) || ((unsigned long)buf % CONT_PTES * PAGE_SIZE)) {
			perror("posix_memalign failed");
			exit(EXIT_FAILURE);
		}

		rwdata(buf);
	#if TEST_CASE2 || TEST_CASE3
		clear_young_dirty(buf);
	#endif
	#if TEST_CASE2
		set_one_young(buf);
	#endif

		for (int j = 0; j < 500; j++) {
			mlock(buf, TEST_SIZE);

			munlock(buf, TEST_SIZE);
		}
		free(buf);
	}

	int main(void)
	{
		test_contpte_perf();
		return 0;
	}

	Descriptions of three test scenarios

Scenario 1
	The data of all 16 PTEs are both dirty and young.
	#define TEST_CASE2 0
	#define TEST_CASE3 0

Scenario 2
	Among the 16 PTEs, only the 8th one is young, and there are no dirty ones.
	#define TEST_CASE2 1
	#define TEST_CASE3 0

Scenario 3
	Among the 16 PTEs, there are neither young nor dirty ones.
	#define TEST_CASE2 0
	#define TEST_CASE3 1

Test results

|Scenario 1         |       Original|       Optimized|
|-------------------|---------------|----------------|
|instructions       |    37912436160|     18731580031|
|test time          |         4.2797|          2.2949|
|overhead of        |               |                |
|contpte_ptep_get() |         21.31%|           4.80%|

|Scenario 2         |       Original|       Optimized|
|-------------------|---------------|----------------|
|instructions       |    36701270862|     36115790086|
|test time          |         3.2335|          3.0874|
|Overhead of        |               |                |
|contpte_ptep_get() |         32.26%|          33.57%|

|Scenario 3         |       Original|       Optimized|
|-------------------|---------------|----------------|
|instructions       |    36706279735|     36750881878|
|test time          |         3.2008|          3.1249|
|Overhead of        |               |                |
|contpte_ptep_get() |         31.94%|          34.59%|

For Scenario 1, optimized code can achieve an instruction benefit of 50.59%
and a time benefit of 46.38%.
For Scenario 2, optimized code can achieve an instruction count benefit of
1.6% and a time benefit of 4.5%.
For Scenario 3, since all the PTEs have neither the young nor the dirty
flag, the branches taken by optimized code should be the same as those of
the original code. In fact, the test results of optimized code seem to be
closer to those of the original code.

Ryan re-ran these tests on Apple M2 with 4K base pages + 64K mTHP.

Scenario 1: reduced to 56% of baseline execution time
Scenario 2: reduced to 89% of baseline execution time
Scenario 3: reduced to 91% of baseline execution time

It can be proven through test function that the optimization for
contpte_ptep_get is effective. Since the logic of contpte_ptep_get_lockless
is similar to that of contpte_ptep_get, the same optimization scheme is
also adopted for it.

Reviewed-by: Ryan Roberts <[email protected]>
Tested-by: Ryan Roberts <[email protected]>
Reviewed-by: Barry Song <[email protected]>
Signed-off-by: Xavier Xia <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Catalin Marinas <[email protected]>

Author: Xavier Xia

arch/arm64/mm/contpte.c

@@ -169,17 +169,46 @@ pte_t contpte_ptep_get(pte_t *ptep, pte_t orig_pte)
 	for (i = 0; i < CONT_PTES; i++, ptep++) {
 		pte = __ptep_get(ptep);
 
-		if (pte_dirty(pte))
+		if (pte_dirty(pte)) {
 			orig_pte = pte_mkdirty(orig_pte);
-
-		if (pte_young(pte))
+			for (; i < CONT_PTES; i++, ptep++) {
+				pte = __ptep_get(ptep);
+				if (pte_young(pte)) {
+					orig_pte = pte_mkyoung(orig_pte);
+					break;
+				}
+			}
+			break;
+		}
+
+		if (pte_young(pte)) {
 			orig_pte = pte_mkyoung(orig_pte);
+			i++;
+			ptep++;
+			for (; i < CONT_PTES; i++, ptep++) {
+				pte = __ptep_get(ptep);
+				if (pte_dirty(pte)) {
+					orig_pte = pte_mkdirty(orig_pte);
+					break;
+				}
+			}
+			break;
+		}
 	}
 
 	return orig_pte;
 }
 EXPORT_SYMBOL_GPL(contpte_ptep_get);
 
+static inline bool contpte_is_consistent(pte_t pte, unsigned long pfn,
+					pgprot_t orig_prot)
+{
+	pgprot_t prot = pte_pgprot(pte_mkold(pte_mkclean(pte)));
+
+	return pte_valid_cont(pte) && pte_pfn(pte) == pfn &&
+			pgprot_val(prot) == pgprot_val(orig_prot);
+}
+
 pte_t contpte_ptep_get_lockless(pte_t *orig_ptep)
 {
 	/*
@@ -202,7 +231,6 @@ pte_t contpte_ptep_get_lockless(pte_t *orig_ptep)
 	pgprot_t orig_prot;
 	unsigned long pfn;
 	pte_t orig_pte;
-	pgprot_t prot;
 	pte_t *ptep;
 	pte_t pte;
 	int i;
@@ -219,18 +247,44 @@ pte_t contpte_ptep_get_lockless(pte_t *orig_ptep)
 
 	for (i = 0; i < CONT_PTES; i++, ptep++, pfn++) {
 		pte = __ptep_get(ptep);
-		prot = pte_pgprot(pte_mkold(pte_mkclean(pte)));
 
-		if (!pte_valid_cont(pte) ||
-		   pte_pfn(pte) != pfn ||
-		   pgprot_val(prot) != pgprot_val(orig_prot))
+		if (!contpte_is_consistent(pte, pfn, orig_prot))
 			goto retry;
 
-		if (pte_dirty(pte))
+		if (pte_dirty(pte)) {
 			orig_pte = pte_mkdirty(orig_pte);
+			for (; i < CONT_PTES; i++, ptep++, pfn++) {
+				pte = __ptep_get(ptep);
+
+				if (!contpte_is_consistent(pte, pfn, orig_prot))
+					goto retry;
+
+				if (pte_young(pte)) {
+					orig_pte = pte_mkyoung(orig_pte);
+					break;
+				}
+			}
+			break;
+		}
 
-		if (pte_young(pte))
+		if (pte_young(pte)) {
 			orig_pte = pte_mkyoung(orig_pte);
+			i++;
+			ptep++;
+			pfn++;
+			for (; i < CONT_PTES; i++, ptep++, pfn++) {
+				pte = __ptep_get(ptep);
+
+				if (!contpte_is_consistent(pte, pfn, orig_prot))
+					goto retry;
+
+				if (pte_dirty(pte)) {
+					orig_pte = pte_mkdirty(orig_pte);
+					break;
+				}
+			}
+			break;
+		}
 	}
 
 	return orig_pte;