[PATCH net-next v19 01/14] mm: page_frag: add a test module for page_frag

[PATCH net-next v19 01/14] mm: page_frag: add a test module for page_frag

[Yunsheng Lin]

The testing is done by ensuring that the fragment allocated
from a frag_frag_cache instance is pushed into a ptr_ring
instance in a kthread binded to a specified cpu, and a kthread
binded to a specified cpu will pop the fragment from the
ptr_ring and free the fragment.

CC: Alexander Duyck <alexander.duyck@gmail.com>
Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
Reviewed-by: Alexander Duyck <alexanderduyck@fb.com>
---
 tools/testing/selftests/mm/Makefile           |   3 +
 tools/testing/selftests/mm/page_frag/Makefile |  18 ++
 .../selftests/mm/page_frag/page_frag_test.c   | 173 ++++++++++++++++++
 tools/testing/selftests/mm/run_vmtests.sh     |   8 +
 tools/testing/selftests/mm/test_page_frag.sh  | 171 +++++++++++++++++
 5 files changed, 373 insertions(+)
 create mode 100644 tools/testing/selftests/mm/page_frag/Makefile
 create mode 100644 tools/testing/selftests/mm/page_frag/page_frag_test.c
 create mode 100755 tools/testing/selftests/mm/test_page_frag.sh

diff --git a/tools/testing/selftests/mm/Makefile b/tools/testing/selftests/mm/Makefile
index 02e1204971b0..acec529baaca 100644
--- a/tools/testing/selftests/mm/Makefile
+++ b/tools/testing/selftests/mm/Makefile
@@ -36,6 +36,8 @@ MAKEFLAGS += --no-builtin-rules
 CFLAGS = -Wall -I $(top_srcdir) $(EXTRA_CFLAGS) $(KHDR_INCLUDES) $(TOOLS_INCLUDES)
 LDLIBS = -lrt -lpthread -lm
 
+TEST_GEN_MODS_DIR := page_frag
+
 TEST_GEN_FILES = cow
 TEST_GEN_FILES += compaction_test
 TEST_GEN_FILES += gup_longterm
@@ -126,6 +128,7 @@ TEST_FILES += test_hmm.sh
 TEST_FILES += va_high_addr_switch.sh
 TEST_FILES += charge_reserved_hugetlb.sh
 TEST_FILES += hugetlb_reparenting_test.sh
+TEST_FILES += test_page_frag.sh
 
 # required by charge_reserved_hugetlb.sh
 TEST_FILES += write_hugetlb_memory.sh
diff --git a/tools/testing/selftests/mm/page_frag/Makefile b/tools/testing/selftests/mm/page_frag/Makefile
new file mode 100644
index 000000000000..58dda74d50a3
--- /dev/null
+++ b/tools/testing/selftests/mm/page_frag/Makefile
@@ -0,0 +1,18 @@
+PAGE_FRAG_TEST_DIR := $(realpath $(dir $(abspath $(lastword $(MAKEFILE_LIST)))))
+KDIR ?= $(abspath $(PAGE_FRAG_TEST_DIR)/../../../../..)
+
+ifeq ($(V),1)
+Q =
+else
+Q = @
+endif
+
+MODULES = page_frag_test.ko
+
+obj-m += page_frag_test.o
+
+all:
+	+$(Q)make -C $(KDIR) M=$(PAGE_FRAG_TEST_DIR) modules
+
+clean:
+	+$(Q)make -C $(KDIR) M=$(PAGE_FRAG_TEST_DIR) clean
diff --git a/tools/testing/selftests/mm/page_frag/page_frag_test.c b/tools/testing/selftests/mm/page_frag/page_frag_test.c
new file mode 100644
index 000000000000..eeb2b6bc681a
--- /dev/null
+++ b/tools/testing/selftests/mm/page_frag/page_frag_test.c
@@ -0,0 +1,173 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * Test module for page_frag cache
+ *
+ * Copyright (C) 2024 Yunsheng Lin <linyunsheng@huawei.com>
+ */
+
+#include <linux/mm.h>
+#include <linux/module.h>
+#include <linux/cpumask.h>
+#include <linux/completion.h>
+#include <linux/ptr_ring.h>
+#include <linux/kthread.h>
+
+static struct ptr_ring ptr_ring;
+static int nr_objs = 512;
+static atomic_t nthreads;
+static struct completion wait;
+static struct page_frag_cache test_nc;
+static int test_popped;
+static int test_pushed;
+
+static int nr_test = 2000000;
+module_param(nr_test, int, 0);
+MODULE_PARM_DESC(nr_test, "number of iterations to test");
+
+static bool test_align;
+module_param(test_align, bool, 0);
+MODULE_PARM_DESC(test_align, "use align API for testing");
+
+static int test_alloc_len = 2048;
+module_param(test_alloc_len, int, 0);
+MODULE_PARM_DESC(test_alloc_len, "alloc len for testing");
+
+static int test_push_cpu;
+module_param(test_push_cpu, int, 0);
+MODULE_PARM_DESC(test_push_cpu, "test cpu for pushing fragment");
+
+static int test_pop_cpu;
+module_param(test_pop_cpu, int, 0);
+MODULE_PARM_DESC(test_pop_cpu, "test cpu for popping fragment");
+
+static int page_frag_pop_thread(void *arg)
+{
+	struct ptr_ring *ring = arg;
+
+	pr_info("page_frag pop test thread begins on cpu %d\n",
+		smp_processor_id());
+
+	while (test_popped < nr_test) {
+		void *obj = __ptr_ring_consume(ring);
+
+		if (obj) {
+			test_popped++;
+			page_frag_free(obj);
+		} else {
+			cond_resched();
+		}
+	}
+
+	if (atomic_dec_and_test(&nthreads))
+		complete(&wait);
+
+	pr_info("page_frag pop test thread exits on cpu %d\n",
+		smp_processor_id());
+
+	return 0;
+}
+
+static int page_frag_push_thread(void *arg)
+{
+	struct ptr_ring *ring = arg;
+
+	pr_info("page_frag push test thread begins on cpu %d\n",
+		smp_processor_id());
+
+	while (test_pushed < nr_test) {
+		void *va;
+		int ret;
+
+		if (test_align) {
+			va = page_frag_alloc_align(&test_nc, test_alloc_len,
+						   GFP_KERNEL, SMP_CACHE_BYTES);
+
+			WARN_ONCE((unsigned long)va & (SMP_CACHE_BYTES - 1),
+				  "unaligned va returned\n");
+		} else {
+			va = page_frag_alloc(&test_nc, test_alloc_len, GFP_KERNEL);
+		}
+
+		if (!va)
+			continue;
+
+		ret = __ptr_ring_produce(ring, va);
+		if (ret) {
+			page_frag_free(va);
+			cond_resched();
+		} else {
+			test_pushed++;
+		}
+	}
+
+	pr_info("page_frag push test thread exits on cpu %d\n",
+		smp_processor_id());
+
+	if (atomic_dec_and_test(&nthreads))
+		complete(&wait);
+
+	return 0;
+}
+
+static int __init page_frag_test_init(void)
+{
+	struct task_struct *tsk_push, *tsk_pop;
+	ktime_t start;
+	u64 duration;
+	int ret;
+
+	test_nc.va = NULL;
+	atomic_set(&nthreads, 2);
+	init_completion(&wait);
+
+	if (test_alloc_len > PAGE_SIZE || test_alloc_len <= 0 ||
+	    !cpu_active(test_push_cpu) || !cpu_active(test_pop_cpu))
+		return -EINVAL;
+
+	ret = ptr_ring_init(&ptr_ring, nr_objs, GFP_KERNEL);
+	if (ret)
+		return ret;
+
+	tsk_push = kthread_create_on_cpu(page_frag_push_thread, &ptr_ring,
+					 test_push_cpu, "page_frag_push");
+	if (IS_ERR(tsk_push))
+		return PTR_ERR(tsk_push);
+
+	tsk_pop = kthread_create_on_cpu(page_frag_pop_thread, &ptr_ring,
+					test_pop_cpu, "page_frag_pop");
+	if (IS_ERR(tsk_pop)) {
+		kthread_stop(tsk_push);
+		return PTR_ERR(tsk_pop);
+	}
+
+	start = ktime_get();
+	wake_up_process(tsk_push);
+	wake_up_process(tsk_pop);
+
+	pr_info("waiting for test to complete\n");
+
+	while (!wait_for_completion_timeout(&wait, msecs_to_jiffies(10000)))
+		pr_info("page_frag_test progress: pushed = %d, popped = %d\n",
+			test_pushed, test_popped);
+
+	duration = (u64)ktime_us_delta(ktime_get(), start);
+	pr_info("%d of iterations for %s testing took: %lluus\n", nr_test,
+		test_align ? "aligned" : "non-aligned", duration);
+
+	ptr_ring_cleanup(&ptr_ring, NULL);
+	page_frag_cache_drain(&test_nc);
+
+	return -EAGAIN;
+}
+
+static void __exit page_frag_test_exit(void)
+{
+}
+
+module_init(page_frag_test_init);
+module_exit(page_frag_test_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Yunsheng Lin <linyunsheng@huawei.com>");
+MODULE_DESCRIPTION("Test module for page_frag");
diff --git a/tools/testing/selftests/mm/run_vmtests.sh b/tools/testing/selftests/mm/run_vmtests.sh
index c5797ad1d37b..2c5394584af4 100755
--- a/tools/testing/selftests/mm/run_vmtests.sh
+++ b/tools/testing/selftests/mm/run_vmtests.sh
@@ -75,6 +75,8 @@ separated by spaces:
 	read-only VMAs
 - mdwe
 	test prctl(PR_SET_MDWE, ...)
+- page_frag
+	test handling of page fragment allocation and freeing
 
 example: ./run_vmtests.sh -t "hmm mmap ksm"
 EOF
@@ -456,6 +458,12 @@ CATEGORY="mkdirty" run_test ./mkdirty
 
 CATEGORY="mdwe" run_test ./mdwe_test
 
+CATEGORY="page_frag" run_test ./test_page_frag.sh smoke
+
+CATEGORY="page_frag" run_test ./test_page_frag.sh aligned
+
+CATEGORY="page_frag" run_test ./test_page_frag.sh nonaligned
+
 echo "SUMMARY: PASS=${count_pass} SKIP=${count_skip} FAIL=${count_fail}" | tap_prefix
 echo "1..${count_total}" | tap_output
 
diff --git a/tools/testing/selftests/mm/test_page_frag.sh b/tools/testing/selftests/mm/test_page_frag.sh
new file mode 100755
index 000000000000..d750d910c899
--- /dev/null
+++ b/tools/testing/selftests/mm/test_page_frag.sh
@@ -0,0 +1,171 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# Copyright (C) 2024 Yunsheng Lin <linyunsheng@huawei.com>
+# Copyright (C) 2018 Uladzislau Rezki (Sony) <urezki@gmail.com>
+#
+# This is a test script for the kernel test driver to test the
+# correctness and performance of page_frag's implementation.
+# Therefore it is just a kernel module loader. You can specify
+# and pass different parameters in order to:
+#     a) analyse performance of page fragment allocations;
+#     b) stressing and stability check of page_frag subsystem.
+
+DRIVER="./page_frag/page_frag_test.ko"
+CPU_LIST=$(grep -m 2 processor /proc/cpuinfo | cut -d ' ' -f 2)
+TEST_CPU_0=$(echo $CPU_LIST | awk '{print $1}')
+
+if [ $(echo $CPU_LIST | wc -w) -gt 1 ]; then
+	TEST_CPU_1=$(echo $CPU_LIST | awk '{print $2}')
+	NR_TEST=100000000
+else
+	TEST_CPU_1=$TEST_CPU_0
+	NR_TEST=1000000
+fi
+
+# 1 if fails
+exitcode=1
+
+# Kselftest framework requirement - SKIP code is 4.
+ksft_skip=4
+
+#
+# Static templates for testing of page_frag APIs.
+# Also it is possible to pass any supported parameters manually.
+#
+SMOKE_PARAM="test_push_cpu=$TEST_CPU_0 test_pop_cpu=$TEST_CPU_1"
+NONALIGNED_PARAM="$SMOKE_PARAM test_alloc_len=75 nr_test=$NR_TEST"
+ALIGNED_PARAM="$NONALIGNED_PARAM test_align=1"
+
+check_test_requirements()
+{
+	uid=$(id -u)
+	if [ $uid -ne 0 ]; then
+		echo "$0: Must be run as root"
+		exit $ksft_skip
+	fi
+
+	if ! which insmod > /dev/null 2>&1; then
+		echo "$0: You need insmod installed"
+		exit $ksft_skip
+	fi
+
+	if [ ! -f $DRIVER ]; then
+		echo "$0: You need to compile page_frag_test module"
+		exit $ksft_skip
+	fi
+}
+
+run_nonaligned_check()
+{
+	echo "Run performance tests to evaluate how fast nonaligned alloc API is."
+
+	insmod $DRIVER $NONALIGNED_PARAM > /dev/null 2>&1
+	echo "Done."
+	echo "Check the kernel ring buffer to see the summary."
+}
+
+run_aligned_check()
+{
+	echo "Run performance tests to evaluate how fast aligned alloc API is."
+
+	insmod $DRIVER $ALIGNED_PARAM > /dev/null 2>&1
+	echo "Done."
+	echo "Check the kernel ring buffer to see the summary."
+}
+
+run_smoke_check()
+{
+	echo "Run smoke test."
+
+	insmod $DRIVER $SMOKE_PARAM > /dev/null 2>&1
+	echo "Done."
+	echo "Check the kernel ring buffer to see the summary."
+}
+
+usage()
+{
+	echo -n "Usage: $0 [ aligned ] | [ nonaligned ] | | [ smoke ] | "
+	echo "manual parameters"
+	echo
+	echo "Valid tests and parameters:"
+	echo
+	modinfo $DRIVER
+	echo
+	echo "Example usage:"
+	echo
+	echo "# Shows help message"
+	echo "$0"
+	echo
+	echo "# Smoke testing"
+	echo "$0 smoke"
+	echo
+	echo "# Performance testing for nonaligned alloc API"
+	echo "$0 nonaligned"
+	echo
+	echo "# Performance testing for aligned alloc API"
+	echo "$0 aligned"
+	echo
+	exit 0
+}
+
+function validate_passed_args()
+{
+	VALID_ARGS=`modinfo $DRIVER | awk '/parm:/ {print $2}' | sed 's/:.*//'`
+
+	#
+	# Something has been passed, check it.
+	#
+	for passed_arg in $@; do
+		key=${passed_arg//=*/}
+		valid=0
+
+		for valid_arg in $VALID_ARGS; do
+			if [[ $key = $valid_arg ]]; then
+				valid=1
+				break
+			fi
+		done
+
+		if [[ $valid -ne 1 ]]; then
+			echo "Error: key is not correct: ${key}"
+			exit $exitcode
+		fi
+	done
+}
+
+function run_manual_check()
+{
+	#
+	# Validate passed parameters. If there is wrong one,
+	# the script exists and does not execute further.
+	#
+	validate_passed_args $@
+
+	echo "Run the test with following parameters: $@"
+	insmod $DRIVER $@ > /dev/null 2>&1
+	echo "Done."
+	echo "Check the kernel ring buffer to see the summary."
+}
+
+function run_test()
+{
+	if [ $# -eq 0 ]; then
+		usage
+	else
+		if [[ "$1" = "smoke" ]]; then
+			run_smoke_check
+		elif [[ "$1" = "nonaligned" ]]; then
+			run_nonaligned_check
+		elif [[ "$1" = "aligned" ]]; then
+			run_aligned_check
+		else
+			run_manual_check $@
+		fi
+	fi
+}
+
+check_test_requirements
+run_test $@
+
+exit 0
-- 
2.34.1

[PATCH net-next v19 02/14] mm: move the page fragment allocator from page_alloc into its own file

[Yunsheng Lin]

Inspired by [1], move the page fragment allocator from page_alloc
into its own c file and header file, as we are about to make more
change for it to replace another page_frag implementation in
sock.c

As this patchset is going to replace 'struct page_frag' with
'struct page_frag_cache' in sched.h, including page_frag_cache.h
in sched.h has a compiler error caused by interdependence between
mm_types.h and mm.h for asm-offsets.c, see [2]. So avoid the compiler
error by moving 'struct page_frag_cache' to mm_types_task.h as
suggested by Alexander, see [3].

1. https://lore.kernel.org/all/20230411160902.4134381-3-dhowells@redhat.com/
2. https://lore.kernel.org/all/15623dac-9358-4597-b3ee-3694a5956920@gmail.com/
3. https://lore.kernel.org/all/CAKgT0UdH1yD=LSCXFJ=YM_aiA4OomD-2wXykO42bizaWMt_HOA@mail.gmail.com/
CC: David Howells <dhowells@redhat.com>
CC: Alexander Duyck <alexander.duyck@gmail.com>
Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
Acked-by: Andrew Morton <akpm@linux-foundation.org>
Reviewed-by: Alexander Duyck <alexanderduyck@fb.com>
---
 include/linux/gfp.h                           |  22 ---
 include/linux/mm_types.h                      |  18 ---
 include/linux/mm_types_task.h                 |  18 +++
 include/linux/page_frag_cache.h               |  31 ++++
 include/linux/skbuff.h                        |   1 +
 mm/Makefile                                   |   1 +
 mm/page_alloc.c                               | 136 ----------------
 mm/page_frag_cache.c                          | 145 ++++++++++++++++++
 .../selftests/mm/page_frag/page_frag_test.c   |   2 +-
 9 files changed, 197 insertions(+), 177 deletions(-)
 create mode 100644 include/linux/page_frag_cache.h
 create mode 100644 mm/page_frag_cache.c

diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index a951de920e20..a0a6d25f883f 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -371,28 +371,6 @@ __meminit void *alloc_pages_exact_nid_noprof(int nid, size_t size, gfp_t gfp_mas
 extern void __free_pages(struct page *page, unsigned int order);
 extern void free_pages(unsigned long addr, unsigned int order);
 
-struct page_frag_cache;
-void page_frag_cache_drain(struct page_frag_cache *nc);
-extern void __page_frag_cache_drain(struct page *page, unsigned int count);
-void *__page_frag_alloc_align(struct page_frag_cache *nc, unsigned int fragsz,
-			      gfp_t gfp_mask, unsigned int align_mask);
-
-static inline void *page_frag_alloc_align(struct page_frag_cache *nc,
-					  unsigned int fragsz, gfp_t gfp_mask,
-					  unsigned int align)
-{
-	WARN_ON_ONCE(!is_power_of_2(align));
-	return __page_frag_alloc_align(nc, fragsz, gfp_mask, -align);
-}
-
-static inline void *page_frag_alloc(struct page_frag_cache *nc,
-			     unsigned int fragsz, gfp_t gfp_mask)
-{
-	return __page_frag_alloc_align(nc, fragsz, gfp_mask, ~0u);
-}
-
-extern void page_frag_free(void *addr);
-
 #define __free_page(page) __free_pages((page), 0)
 #define free_page(addr) free_pages((addr), 0)
 
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 6e3bdf8e38bc..92314ef2d978 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -521,9 +521,6 @@ static_assert(sizeof(struct ptdesc) <= sizeof(struct page));
  */
 #define STRUCT_PAGE_MAX_SHIFT	(order_base_2(sizeof(struct page)))
 
-#define PAGE_FRAG_CACHE_MAX_SIZE	__ALIGN_MASK(32768, ~PAGE_MASK)
-#define PAGE_FRAG_CACHE_MAX_ORDER	get_order(PAGE_FRAG_CACHE_MAX_SIZE)
-
 /*
  * page_private can be used on tail pages.  However, PagePrivate is only
  * checked by the VM on the head page.  So page_private on the tail pages
@@ -542,21 +539,6 @@ static inline void *folio_get_private(struct folio *folio)
 	return folio->private;
 }
 
-struct page_frag_cache {
-	void * va;
-#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE)
-	__u16 offset;
-	__u16 size;
-#else
-	__u32 offset;
-#endif
-	/* we maintain a pagecount bias, so that we dont dirty cache line
-	 * containing page->_refcount every time we allocate a fragment.
-	 */
-	unsigned int		pagecnt_bias;
-	bool pfmemalloc;
-};
-
 typedef unsigned long vm_flags_t;
 
 /*
diff --git a/include/linux/mm_types_task.h b/include/linux/mm_types_task.h
index bff5706b76e1..0ac6daebdd5c 100644
--- a/include/linux/mm_types_task.h
+++ b/include/linux/mm_types_task.h
@@ -8,6 +8,7 @@
  * (These are defined separately to decouple sched.h from mm_types.h as much as possible.)
  */
 
+#include <linux/align.h>
 #include <linux/types.h>
 
 #include <asm/page.h>
@@ -43,6 +44,23 @@ struct page_frag {
 #endif
 };
 
+#define PAGE_FRAG_CACHE_MAX_SIZE	__ALIGN_MASK(32768, ~PAGE_MASK)
+#define PAGE_FRAG_CACHE_MAX_ORDER	get_order(PAGE_FRAG_CACHE_MAX_SIZE)
+struct page_frag_cache {
+	void *va;
+#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE)
+	__u16 offset;
+	__u16 size;
+#else
+	__u32 offset;
+#endif
+	/* we maintain a pagecount bias, so that we dont dirty cache line
+	 * containing page->_refcount every time we allocate a fragment.
+	 */
+	unsigned int		pagecnt_bias;
+	bool pfmemalloc;
+};
+
 /* Track pages that require TLB flushes */
 struct tlbflush_unmap_batch {
 #ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH
diff --git a/include/linux/page_frag_cache.h b/include/linux/page_frag_cache.h
new file mode 100644
index 000000000000..67ac8626ed9b
--- /dev/null
+++ b/include/linux/page_frag_cache.h
@@ -0,0 +1,31 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef _LINUX_PAGE_FRAG_CACHE_H
+#define _LINUX_PAGE_FRAG_CACHE_H
+
+#include <linux/log2.h>
+#include <linux/mm_types_task.h>
+#include <linux/types.h>
+
+void page_frag_cache_drain(struct page_frag_cache *nc);
+void __page_frag_cache_drain(struct page *page, unsigned int count);
+void *__page_frag_alloc_align(struct page_frag_cache *nc, unsigned int fragsz,
+			      gfp_t gfp_mask, unsigned int align_mask);
+
+static inline void *page_frag_alloc_align(struct page_frag_cache *nc,
+					  unsigned int fragsz, gfp_t gfp_mask,
+					  unsigned int align)
+{
+	WARN_ON_ONCE(!is_power_of_2(align));
+	return __page_frag_alloc_align(nc, fragsz, gfp_mask, -align);
+}
+
+static inline void *page_frag_alloc(struct page_frag_cache *nc,
+				    unsigned int fragsz, gfp_t gfp_mask)
+{
+	return __page_frag_alloc_align(nc, fragsz, gfp_mask, ~0u);
+}
+
+void page_frag_free(void *addr);
+
+#endif
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 39f1d16f3628..560e2b49f98b 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -31,6 +31,7 @@
 #include <linux/in6.h>
 #include <linux/if_packet.h>
 #include <linux/llist.h>
+#include <linux/page_frag_cache.h>
 #include <net/flow.h>
 #if IS_ENABLED(CONFIG_NF_CONNTRACK)
 #include <linux/netfilter/nf_conntrack_common.h>
diff --git a/mm/Makefile b/mm/Makefile
index d5639b036166..dba52bb0da8a 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -65,6 +65,7 @@ page-alloc-$(CONFIG_SHUFFLE_PAGE_ALLOCATOR) += shuffle.o
 memory-hotplug-$(CONFIG_MEMORY_HOTPLUG) += memory_hotplug.o
 
 obj-y += page-alloc.o
+obj-y += page_frag_cache.o
 obj-y += init-mm.o
 obj-y += memblock.o
 obj-y += $(memory-hotplug-y)
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 8afab64814dc..6ca2abce857b 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -4836,142 +4836,6 @@ void free_pages(unsigned long addr, unsigned int order)
 
 EXPORT_SYMBOL(free_pages);
 
-/*
- * Page Fragment:
- *  An arbitrary-length arbitrary-offset area of memory which resides
- *  within a 0 or higher order page.  Multiple fragments within that page
- *  are individually refcounted, in the page's reference counter.
- *
- * The page_frag functions below provide a simple allocation framework for
- * page fragments.  This is used by the network stack and network device
- * drivers to provide a backing region of memory for use as either an
- * sk_buff->head, or to be used in the "frags" portion of skb_shared_info.
- */
-static struct page *__page_frag_cache_refill(struct page_frag_cache *nc,
-					     gfp_t gfp_mask)
-{
-	struct page *page = NULL;
-	gfp_t gfp = gfp_mask;
-
-#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE)
-	gfp_mask = (gfp_mask & ~__GFP_DIRECT_RECLAIM) |  __GFP_COMP |
-		   __GFP_NOWARN | __GFP_NORETRY | __GFP_NOMEMALLOC;
-	page = alloc_pages_node(NUMA_NO_NODE, gfp_mask,
-				PAGE_FRAG_CACHE_MAX_ORDER);
-	nc->size = page ? PAGE_FRAG_CACHE_MAX_SIZE : PAGE_SIZE;
-#endif
-	if (unlikely(!page))
-		page = alloc_pages_node(NUMA_NO_NODE, gfp, 0);
-
-	nc->va = page ? page_address(page) : NULL;
-
-	return page;
-}
-
-void page_frag_cache_drain(struct page_frag_cache *nc)
-{
-	if (!nc->va)
-		return;
-
-	__page_frag_cache_drain(virt_to_head_page(nc->va), nc->pagecnt_bias);
-	nc->va = NULL;
-}
-EXPORT_SYMBOL(page_frag_cache_drain);
-
-void __page_frag_cache_drain(struct page *page, unsigned int count)
-{
-	VM_BUG_ON_PAGE(page_ref_count(page) == 0, page);
-
-	if (page_ref_sub_and_test(page, count))
-		free_unref_page(page, compound_order(page));
-}
-EXPORT_SYMBOL(__page_frag_cache_drain);
-
-void *__page_frag_alloc_align(struct page_frag_cache *nc,
-			      unsigned int fragsz, gfp_t gfp_mask,
-			      unsigned int align_mask)
-{
-	unsigned int size = PAGE_SIZE;
-	struct page *page;
-	int offset;
-
-	if (unlikely(!nc->va)) {
-refill:
-		page = __page_frag_cache_refill(nc, gfp_mask);
-		if (!page)
-			return NULL;
-
-#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE)
-		/* if size can vary use size else just use PAGE_SIZE */
-		size = nc->size;
-#endif
-		/* Even if we own the page, we do not use atomic_set().
-		 * This would break get_page_unless_zero() users.
-		 */
-		page_ref_add(page, PAGE_FRAG_CACHE_MAX_SIZE);
-
-		/* reset page count bias and offset to start of new frag */
-		nc->pfmemalloc = page_is_pfmemalloc(page);
-		nc->pagecnt_bias = PAGE_FRAG_CACHE_MAX_SIZE + 1;
-		nc->offset = size;
-	}
-
-	offset = nc->offset - fragsz;
-	if (unlikely(offset < 0)) {
-		page = virt_to_page(nc->va);
-
-		if (!page_ref_sub_and_test(page, nc->pagecnt_bias))
-			goto refill;
-
-		if (unlikely(nc->pfmemalloc)) {
-			free_unref_page(page, compound_order(page));
-			goto refill;
-		}
-
-#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE)
-		/* if size can vary use size else just use PAGE_SIZE */
-		size = nc->size;
-#endif
-		/* OK, page count is 0, we can safely set it */
-		set_page_count(page, PAGE_FRAG_CACHE_MAX_SIZE + 1);
-
-		/* reset page count bias and offset to start of new frag */
-		nc->pagecnt_bias = PAGE_FRAG_CACHE_MAX_SIZE + 1;
-		offset = size - fragsz;
-		if (unlikely(offset < 0)) {
-			/*
-			 * The caller is trying to allocate a fragment
-			 * with fragsz > PAGE_SIZE but the cache isn't big
-			 * enough to satisfy the request, this may
-			 * happen in low memory conditions.
-			 * We don't release the cache page because
-			 * it could make memory pressure worse
-			 * so we simply return NULL here.
-			 */
-			return NULL;
-		}
-	}
-
-	nc->pagecnt_bias--;
-	offset &= align_mask;
-	nc->offset = offset;
-
-	return nc->va + offset;
-}
-EXPORT_SYMBOL(__page_frag_alloc_align);
-
-/*
- * Frees a page fragment allocated out of either a compound or order 0 page.
- */
-void page_frag_free(void *addr)
-{
-	struct page *page = virt_to_head_page(addr);
-
-	if (unlikely(put_page_testzero(page)))
-		free_unref_page(page, compound_order(page));
-}
-EXPORT_SYMBOL(page_frag_free);
-
 static void *make_alloc_exact(unsigned long addr, unsigned int order,
 		size_t size)
 {
diff --git a/mm/page_frag_cache.c b/mm/page_frag_cache.c
new file mode 100644
index 000000000000..609a485cd02a
--- /dev/null
+++ b/mm/page_frag_cache.c
@@ -0,0 +1,145 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Page fragment allocator
+ *
+ * Page Fragment:
+ *  An arbitrary-length arbitrary-offset area of memory which resides within a
+ *  0 or higher order page.  Multiple fragments within that page are
+ *  individually refcounted, in the page's reference counter.
+ *
+ * The page_frag functions provide a simple allocation framework for page
+ * fragments.  This is used by the network stack and network device drivers to
+ * provide a backing region of memory for use as either an sk_buff->head, or to
+ * be used in the "frags" portion of skb_shared_info.
+ */
+
+#include <linux/export.h>
+#include <linux/gfp_types.h>
+#include <linux/init.h>
+#include <linux/mm.h>
+#include <linux/page_frag_cache.h>
+#include "internal.h"
+
+static struct page *__page_frag_cache_refill(struct page_frag_cache *nc,
+					     gfp_t gfp_mask)
+{
+	struct page *page = NULL;
+	gfp_t gfp = gfp_mask;
+
+#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE)
+	gfp_mask = (gfp_mask & ~__GFP_DIRECT_RECLAIM) |  __GFP_COMP |
+		   __GFP_NOWARN | __GFP_NORETRY | __GFP_NOMEMALLOC;
+	page = alloc_pages_node(NUMA_NO_NODE, gfp_mask,
+				PAGE_FRAG_CACHE_MAX_ORDER);
+	nc->size = page ? PAGE_FRAG_CACHE_MAX_SIZE : PAGE_SIZE;
+#endif
+	if (unlikely(!page))
+		page = alloc_pages_node(NUMA_NO_NODE, gfp, 0);
+
+	nc->va = page ? page_address(page) : NULL;
+
+	return page;
+}
+
+void page_frag_cache_drain(struct page_frag_cache *nc)
+{
+	if (!nc->va)
+		return;
+
+	__page_frag_cache_drain(virt_to_head_page(nc->va), nc->pagecnt_bias);
+	nc->va = NULL;
+}
+EXPORT_SYMBOL(page_frag_cache_drain);
+
+void __page_frag_cache_drain(struct page *page, unsigned int count)
+{
+	VM_BUG_ON_PAGE(page_ref_count(page) == 0, page);
+
+	if (page_ref_sub_and_test(page, count))
+		free_unref_page(page, compound_order(page));
+}
+EXPORT_SYMBOL(__page_frag_cache_drain);
+
+void *__page_frag_alloc_align(struct page_frag_cache *nc,
+			      unsigned int fragsz, gfp_t gfp_mask,
+			      unsigned int align_mask)
+{
+	unsigned int size = PAGE_SIZE;
+	struct page *page;
+	int offset;
+
+	if (unlikely(!nc->va)) {
+refill:
+		page = __page_frag_cache_refill(nc, gfp_mask);
+		if (!page)
+			return NULL;
+
+#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE)
+		/* if size can vary use size else just use PAGE_SIZE */
+		size = nc->size;
+#endif
+		/* Even if we own the page, we do not use atomic_set().
+		 * This would break get_page_unless_zero() users.
+		 */
+		page_ref_add(page, PAGE_FRAG_CACHE_MAX_SIZE);
+
+		/* reset page count bias and offset to start of new frag */
+		nc->pfmemalloc = page_is_pfmemalloc(page);
+		nc->pagecnt_bias = PAGE_FRAG_CACHE_MAX_SIZE + 1;
+		nc->offset = size;
+	}
+
+	offset = nc->offset - fragsz;
+	if (unlikely(offset < 0)) {
+		page = virt_to_page(nc->va);
+
+		if (!page_ref_sub_and_test(page, nc->pagecnt_bias))
+			goto refill;
+
+		if (unlikely(nc->pfmemalloc)) {
+			free_unref_page(page, compound_order(page));
+			goto refill;
+		}
+
+#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE)
+		/* if size can vary use size else just use PAGE_SIZE */
+		size = nc->size;
+#endif
+		/* OK, page count is 0, we can safely set it */
+		set_page_count(page, PAGE_FRAG_CACHE_MAX_SIZE + 1);
+
+		/* reset page count bias and offset to start of new frag */
+		nc->pagecnt_bias = PAGE_FRAG_CACHE_MAX_SIZE + 1;
+		offset = size - fragsz;
+		if (unlikely(offset < 0)) {
+			/*
+			 * The caller is trying to allocate a fragment
+			 * with fragsz > PAGE_SIZE but the cache isn't big
+			 * enough to satisfy the request, this may
+			 * happen in low memory conditions.
+			 * We don't release the cache page because
+			 * it could make memory pressure worse
+			 * so we simply return NULL here.
+			 */
+			return NULL;
+		}
+	}
+
+	nc->pagecnt_bias--;
+	offset &= align_mask;
+	nc->offset = offset;
+
+	return nc->va + offset;
+}
+EXPORT_SYMBOL(__page_frag_alloc_align);
+
+/*
+ * Frees a page fragment allocated out of either a compound or order 0 page.
+ */
+void page_frag_free(void *addr)
+{
+	struct page *page = virt_to_head_page(addr);
+
+	if (unlikely(put_page_testzero(page)))
+		free_unref_page(page, compound_order(page));
+}
+EXPORT_SYMBOL(page_frag_free);
diff --git a/tools/testing/selftests/mm/page_frag/page_frag_test.c b/tools/testing/selftests/mm/page_frag/page_frag_test.c
index eeb2b6bc681a..fdf204550c9a 100644
--- a/tools/testing/selftests/mm/page_frag/page_frag_test.c
+++ b/tools/testing/selftests/mm/page_frag/page_frag_test.c
@@ -6,12 +6,12 @@
  * Copyright (C) 2024 Yunsheng Lin <linyunsheng@huawei.com>
  */
 
-#include <linux/mm.h>
 #include <linux/module.h>
 #include <linux/cpumask.h>
 #include <linux/completion.h>
 #include <linux/ptr_ring.h>
 #include <linux/kthread.h>
+#include <linux/page_frag_cache.h>
 
 static struct ptr_ring ptr_ring;
 static int nr_objs = 512;
-- 
2.34.1

[PATCH net-next v19 03/14] mm: page_frag: use initial zero offset for page_frag_alloc_align()

[Yunsheng Lin]

We are about to use page_frag_alloc_*() API to not just
allocate memory for skb->data, but also use them to do
the memory allocation for skb frag too. Currently the
implementation of page_frag in mm subsystem is running
the offset as a countdown rather than count-up value,
there may have several advantages to that as mentioned
in [1], but it may have some disadvantages, for example,
it may disable skb frag coalescing and more correct cache
prefetching

We have a trade-off to make in order to have a unified
implementation and API for page_frag, so use a initial zero
offset in this patch, and the following patch will try to
make some optimization to avoid the disadvantages as much
as possible.

1. https://lore.kernel.org/all/f4abe71b3439b39d17a6fb2d410180f367cadf5c.camel@gmail.com/

CC: Alexander Duyck <alexander.duyck@gmail.com>
Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
Reviewed-by: Alexander Duyck <alexanderduyck@fb.com>
---
 mm/page_frag_cache.c | 46 ++++++++++++++++++++++----------------------
 1 file changed, 23 insertions(+), 23 deletions(-)

diff --git a/mm/page_frag_cache.c b/mm/page_frag_cache.c
index 609a485cd02a..4c8e04379cb3 100644
--- a/mm/page_frag_cache.c
+++ b/mm/page_frag_cache.c
@@ -63,9 +63,13 @@ void *__page_frag_alloc_align(struct page_frag_cache *nc,
 			      unsigned int fragsz, gfp_t gfp_mask,
 			      unsigned int align_mask)
 {
+#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE)
+	unsigned int size = nc->size;
+#else
 	unsigned int size = PAGE_SIZE;
+#endif
+	unsigned int offset;
 	struct page *page;
-	int offset;
 
 	if (unlikely(!nc->va)) {
 refill:
@@ -85,11 +89,24 @@ void *__page_frag_alloc_align(struct page_frag_cache *nc,
 		/* reset page count bias and offset to start of new frag */
 		nc->pfmemalloc = page_is_pfmemalloc(page);
 		nc->pagecnt_bias = PAGE_FRAG_CACHE_MAX_SIZE + 1;
-		nc->offset = size;
+		nc->offset = 0;
 	}
 
-	offset = nc->offset - fragsz;
-	if (unlikely(offset < 0)) {
+	offset = __ALIGN_KERNEL_MASK(nc->offset, ~align_mask);
+	if (unlikely(offset + fragsz > size)) {
+		if (unlikely(fragsz > PAGE_SIZE)) {
+			/*
+			 * The caller is trying to allocate a fragment
+			 * with fragsz > PAGE_SIZE but the cache isn't big
+			 * enough to satisfy the request, this may
+			 * happen in low memory conditions.
+			 * We don't release the cache page because
+			 * it could make memory pressure worse
+			 * so we simply return NULL here.
+			 */
+			return NULL;
+		}
+
 		page = virt_to_page(nc->va);
 
 		if (!page_ref_sub_and_test(page, nc->pagecnt_bias))
@@ -100,33 +117,16 @@ void *__page_frag_alloc_align(struct page_frag_cache *nc,
 			goto refill;
 		}
 
-#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE)
-		/* if size can vary use size else just use PAGE_SIZE */
-		size = nc->size;
-#endif
 		/* OK, page count is 0, we can safely set it */
 		set_page_count(page, PAGE_FRAG_CACHE_MAX_SIZE + 1);
 
 		/* reset page count bias and offset to start of new frag */
 		nc->pagecnt_bias = PAGE_FRAG_CACHE_MAX_SIZE + 1;
-		offset = size - fragsz;
-		if (unlikely(offset < 0)) {
-			/*
-			 * The caller is trying to allocate a fragment
-			 * with fragsz > PAGE_SIZE but the cache isn't big
-			 * enough to satisfy the request, this may
-			 * happen in low memory conditions.
-			 * We don't release the cache page because
-			 * it could make memory pressure worse
-			 * so we simply return NULL here.
-			 */
-			return NULL;
-		}
+		offset = 0;
 	}
 
 	nc->pagecnt_bias--;
-	offset &= align_mask;
-	nc->offset = offset;
+	nc->offset = offset + fragsz;
 
 	return nc->va + offset;
 }
-- 
2.34.1

[PATCH net-next v19 04/14] mm: page_frag: avoid caller accessing 'page_frag_cache' directly

[Yunsheng Lin]

Use appropriate frag_page API instead of caller accessing
'page_frag_cache' directly.

CC: Alexander Duyck <alexander.duyck@gmail.com>
Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
Reviewed-by: Alexander Duyck <alexanderduyck@fb.com>
Acked-by: Chuck Lever <chuck.lever@oracle.com>
---
 drivers/vhost/net.c                                   |  2 +-
 include/linux/page_frag_cache.h                       | 10 ++++++++++
 net/core/skbuff.c                                     |  6 +++---
 net/rxrpc/conn_object.c                               |  4 +---
 net/rxrpc/local_object.c                              |  4 +---
 net/sunrpc/svcsock.c                                  |  6 ++----
 tools/testing/selftests/mm/page_frag/page_frag_test.c |  2 +-
 7 files changed, 19 insertions(+), 15 deletions(-)

diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index f16279351db5..9ad37c012189 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -1325,7 +1325,7 @@ static int vhost_net_open(struct inode *inode, struct file *f)
 			vqs[VHOST_NET_VQ_RX]);
 
 	f->private_data = n;
-	n->pf_cache.va = NULL;
+	page_frag_cache_init(&n->pf_cache);
 
 	return 0;
 }
diff --git a/include/linux/page_frag_cache.h b/include/linux/page_frag_cache.h
index 67ac8626ed9b..0a52f7a179c8 100644
--- a/include/linux/page_frag_cache.h
+++ b/include/linux/page_frag_cache.h
@@ -7,6 +7,16 @@
 #include <linux/mm_types_task.h>
 #include <linux/types.h>
 
+static inline void page_frag_cache_init(struct page_frag_cache *nc)
+{
+	nc->va = NULL;
+}
+
+static inline bool page_frag_cache_is_pfmemalloc(struct page_frag_cache *nc)
+{
+	return !!nc->pfmemalloc;
+}
+
 void page_frag_cache_drain(struct page_frag_cache *nc);
 void __page_frag_cache_drain(struct page *page, unsigned int count);
 void *__page_frag_alloc_align(struct page_frag_cache *nc, unsigned int fragsz,
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 74149dc4ee31..ca01880c7ad0 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -753,14 +753,14 @@ struct sk_buff *__netdev_alloc_skb(struct net_device *dev, unsigned int len,
 	if (in_hardirq() || irqs_disabled()) {
 		nc = this_cpu_ptr(&netdev_alloc_cache);
 		data = page_frag_alloc(nc, len, gfp_mask);
-		pfmemalloc = nc->pfmemalloc;
+		pfmemalloc = page_frag_cache_is_pfmemalloc(nc);
 	} else {
 		local_bh_disable();
 		local_lock_nested_bh(&napi_alloc_cache.bh_lock);
 
 		nc = this_cpu_ptr(&napi_alloc_cache.page);
 		data = page_frag_alloc(nc, len, gfp_mask);
-		pfmemalloc = nc->pfmemalloc;
+		pfmemalloc = page_frag_cache_is_pfmemalloc(nc);
 
 		local_unlock_nested_bh(&napi_alloc_cache.bh_lock);
 		local_bh_enable();
@@ -850,7 +850,7 @@ struct sk_buff *napi_alloc_skb(struct napi_struct *napi, unsigned int len)
 		len = SKB_HEAD_ALIGN(len);
 
 		data = page_frag_alloc(&nc->page, len, gfp_mask);
-		pfmemalloc = nc->page.pfmemalloc;
+		pfmemalloc = page_frag_cache_is_pfmemalloc(&nc->page);
 	}
 	local_unlock_nested_bh(&napi_alloc_cache.bh_lock);
 
diff --git a/net/rxrpc/conn_object.c b/net/rxrpc/conn_object.c
index 1539d315afe7..694c4df7a1a3 100644
--- a/net/rxrpc/conn_object.c
+++ b/net/rxrpc/conn_object.c
@@ -337,9 +337,7 @@ static void rxrpc_clean_up_connection(struct work_struct *work)
 	 */
 	rxrpc_purge_queue(&conn->rx_queue);
 
-	if (conn->tx_data_alloc.va)
-		__page_frag_cache_drain(virt_to_page(conn->tx_data_alloc.va),
-					conn->tx_data_alloc.pagecnt_bias);
+	page_frag_cache_drain(&conn->tx_data_alloc);
 	call_rcu(&conn->rcu, rxrpc_rcu_free_connection);
 }
 
diff --git a/net/rxrpc/local_object.c b/net/rxrpc/local_object.c
index 504453c688d7..a8cffe47cf01 100644
--- a/net/rxrpc/local_object.c
+++ b/net/rxrpc/local_object.c
@@ -452,9 +452,7 @@ void rxrpc_destroy_local(struct rxrpc_local *local)
 #endif
 	rxrpc_purge_queue(&local->rx_queue);
 	rxrpc_purge_client_connections(local);
-	if (local->tx_alloc.va)
-		__page_frag_cache_drain(virt_to_page(local->tx_alloc.va),
-					local->tx_alloc.pagecnt_bias);
+	page_frag_cache_drain(&local->tx_alloc);
 }
 
 /*
diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c
index 825ec5357691..b785425c3315 100644
--- a/net/sunrpc/svcsock.c
+++ b/net/sunrpc/svcsock.c
@@ -1608,7 +1608,6 @@ static void svc_tcp_sock_detach(struct svc_xprt *xprt)
 static void svc_sock_free(struct svc_xprt *xprt)
 {
 	struct svc_sock *svsk = container_of(xprt, struct svc_sock, sk_xprt);
-	struct page_frag_cache *pfc = &svsk->sk_frag_cache;
 	struct socket *sock = svsk->sk_sock;
 
 	trace_svcsock_free(svsk, sock);
@@ -1618,8 +1617,7 @@ static void svc_sock_free(struct svc_xprt *xprt)
 		sockfd_put(sock);
 	else
 		sock_release(sock);
-	if (pfc->va)
-		__page_frag_cache_drain(virt_to_head_page(pfc->va),
-					pfc->pagecnt_bias);
+
+	page_frag_cache_drain(&svsk->sk_frag_cache);
 	kfree(svsk);
 }
diff --git a/tools/testing/selftests/mm/page_frag/page_frag_test.c b/tools/testing/selftests/mm/page_frag/page_frag_test.c
index fdf204550c9a..36543a129e40 100644
--- a/tools/testing/selftests/mm/page_frag/page_frag_test.c
+++ b/tools/testing/selftests/mm/page_frag/page_frag_test.c
@@ -117,7 +117,7 @@ static int __init page_frag_test_init(void)
 	u64 duration;
 	int ret;
 
-	test_nc.va = NULL;
+	page_frag_cache_init(&test_nc);
 	atomic_set(&nthreads, 2);
 	init_completion(&wait);
 
-- 
2.34.1

[PATCH net-next v19 06/14] mm: page_frag: reuse existing space for 'size' and 'pfmemalloc'

[Yunsheng Lin]

Currently there is one 'struct page_frag' for every 'struct
sock' and 'struct task_struct', we are about to replace the
'struct page_frag' with 'struct page_frag_cache' for them.
Before begin the replacing, we need to ensure the size of
'struct page_frag_cache' is not bigger than the size of
'struct page_frag', as there may be tens of thousands of
'struct sock' and 'struct task_struct' instances in the
system.

By or'ing the page order & pfmemalloc with lower bits of
'va' instead of using 'u16' or 'u32' for page size and 'u8'
for pfmemalloc, we are able to avoid 3 or 5 bytes space waste.
And page address & pfmemalloc & order is unchanged for the
same page in the same 'page_frag_cache' instance, it makes
sense to fit them together.

After this patch, the size of 'struct page_frag_cache' should be
the same as the size of 'struct page_frag'.

CC: Alexander Duyck <alexander.duyck@gmail.com>
Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
---
 include/linux/mm_types_task.h   | 19 +++++----
 include/linux/page_frag_cache.h | 26 +++++++++++-
 mm/page_frag_cache.c            | 75 +++++++++++++++++++++++----------
 3 files changed, 88 insertions(+), 32 deletions(-)

diff --git a/include/linux/mm_types_task.h b/include/linux/mm_types_task.h
index 0ac6daebdd5c..a82aa80c0ba4 100644
--- a/include/linux/mm_types_task.h
+++ b/include/linux/mm_types_task.h
@@ -47,18 +47,21 @@ struct page_frag {
 #define PAGE_FRAG_CACHE_MAX_SIZE	__ALIGN_MASK(32768, ~PAGE_MASK)
 #define PAGE_FRAG_CACHE_MAX_ORDER	get_order(PAGE_FRAG_CACHE_MAX_SIZE)
 struct page_frag_cache {
-	void *va;
-#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE)
+	/* encoded_page consists of the virtual address, pfmemalloc bit and
+	 * order of a page.
+	 */
+	unsigned long encoded_page;
+
+	/* we maintain a pagecount bias, so that we dont dirty cache line
+	 * containing page->_refcount every time we allocate a fragment.
+	 */
+#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE) && (BITS_PER_LONG <= 32)
 	__u16 offset;
-	__u16 size;
+	__u16 pagecnt_bias;
 #else
 	__u32 offset;
+	__u32 pagecnt_bias;
 #endif
-	/* we maintain a pagecount bias, so that we dont dirty cache line
-	 * containing page->_refcount every time we allocate a fragment.
-	 */
-	unsigned int		pagecnt_bias;
-	bool pfmemalloc;
 };
 
 /* Track pages that require TLB flushes */
diff --git a/include/linux/page_frag_cache.h b/include/linux/page_frag_cache.h
index 0a52f7a179c8..75aaad6eaea2 100644
--- a/include/linux/page_frag_cache.h
+++ b/include/linux/page_frag_cache.h
@@ -3,18 +3,40 @@
 #ifndef _LINUX_PAGE_FRAG_CACHE_H
 #define _LINUX_PAGE_FRAG_CACHE_H
 
+#include <linux/bits.h>
 #include <linux/log2.h>
 #include <linux/mm_types_task.h>
 #include <linux/types.h>
 
+#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE)
+/* Use a full byte here to enable assembler optimization as the shift
+ * operation is usually expecting a byte.
+ */
+#define PAGE_FRAG_CACHE_ORDER_MASK		GENMASK(7, 0)
+#define PAGE_FRAG_CACHE_PFMEMALLOC_SHIFT	8
+#define PAGE_FRAG_CACHE_PFMEMALLOC_BIT		BIT(PAGE_FRAG_CACHE_PFMEMALLOC_SHIFT)
+#else
+/* Compiler should be able to figure out we don't read things as any value
+ * ANDed with 0 is 0.
+ */
+#define PAGE_FRAG_CACHE_ORDER_MASK		0
+#define PAGE_FRAG_CACHE_PFMEMALLOC_SHIFT	0
+#define PAGE_FRAG_CACHE_PFMEMALLOC_BIT		BIT(PAGE_FRAG_CACHE_PFMEMALLOC_SHIFT)
+#endif
+
+static inline bool page_frag_encoded_page_pfmemalloc(unsigned long encoded_page)
+{
+	return !!(encoded_page & PAGE_FRAG_CACHE_PFMEMALLOC_BIT);
+}
+
 static inline void page_frag_cache_init(struct page_frag_cache *nc)
 {
-	nc->va = NULL;
+	nc->encoded_page = 0;
 }
 
 static inline bool page_frag_cache_is_pfmemalloc(struct page_frag_cache *nc)
 {
-	return !!nc->pfmemalloc;
+	return page_frag_encoded_page_pfmemalloc(nc->encoded_page);
 }
 
 void page_frag_cache_drain(struct page_frag_cache *nc);
diff --git a/mm/page_frag_cache.c b/mm/page_frag_cache.c
index 4c8e04379cb3..cf9375a81a64 100644
--- a/mm/page_frag_cache.c
+++ b/mm/page_frag_cache.c
@@ -12,6 +12,7 @@
  * be used in the "frags" portion of skb_shared_info.
  */
 
+#include <linux/build_bug.h>
 #include <linux/export.h>
 #include <linux/gfp_types.h>
 #include <linux/init.h>
@@ -19,9 +20,41 @@
 #include <linux/page_frag_cache.h>
 #include "internal.h"
 
+static unsigned long page_frag_encode_page(struct page *page, unsigned int order,
+					   bool pfmemalloc)
+{
+	BUILD_BUG_ON(PAGE_FRAG_CACHE_MAX_ORDER > PAGE_FRAG_CACHE_ORDER_MASK);
+	BUILD_BUG_ON(PAGE_FRAG_CACHE_PFMEMALLOC_BIT >= PAGE_SIZE);
+
+	return (unsigned long)page_address(page) |
+		(order & PAGE_FRAG_CACHE_ORDER_MASK) |
+		((unsigned long)pfmemalloc << PAGE_FRAG_CACHE_PFMEMALLOC_SHIFT);
+}
+
+static unsigned long page_frag_encoded_page_order(unsigned long encoded_page)
+{
+	return encoded_page & PAGE_FRAG_CACHE_ORDER_MASK;
+}
+
+static void *page_frag_encoded_page_address(unsigned long encoded_page)
+{
+	return (void *)(encoded_page & PAGE_MASK);
+}
+
+static struct page *page_frag_encoded_page_ptr(unsigned long encoded_page)
+{
+	return virt_to_page((void *)encoded_page);
+}
+
+static unsigned int page_frag_cache_page_size(unsigned long encoded_page)
+{
+	return PAGE_SIZE << page_frag_encoded_page_order(encoded_page);
+}
+
 static struct page *__page_frag_cache_refill(struct page_frag_cache *nc,
 					     gfp_t gfp_mask)
 {
+	unsigned long order = PAGE_FRAG_CACHE_MAX_ORDER;
 	struct page *page = NULL;
 	gfp_t gfp = gfp_mask;
 
@@ -30,23 +63,26 @@ static struct page *__page_frag_cache_refill(struct page_frag_cache *nc,
 		   __GFP_NOWARN | __GFP_NORETRY | __GFP_NOMEMALLOC;
 	page = alloc_pages_node(NUMA_NO_NODE, gfp_mask,
 				PAGE_FRAG_CACHE_MAX_ORDER);
-	nc->size = page ? PAGE_FRAG_CACHE_MAX_SIZE : PAGE_SIZE;
 #endif
-	if (unlikely(!page))
+	if (unlikely(!page)) {
 		page = alloc_pages_node(NUMA_NO_NODE, gfp, 0);
+		order = 0;
+	}
 
-	nc->va = page ? page_address(page) : NULL;
+	nc->encoded_page = page ?
+		page_frag_encode_page(page, order, page_is_pfmemalloc(page)) : 0;
 
 	return page;
 }
 
 void page_frag_cache_drain(struct page_frag_cache *nc)
 {
-	if (!nc->va)
+	if (!nc->encoded_page)
 		return;
 
-	__page_frag_cache_drain(virt_to_head_page(nc->va), nc->pagecnt_bias);
-	nc->va = NULL;
+	__page_frag_cache_drain(page_frag_encoded_page_ptr(nc->encoded_page),
+				nc->pagecnt_bias);
+	nc->encoded_page = 0;
 }
 EXPORT_SYMBOL(page_frag_cache_drain);
 
@@ -63,35 +99,29 @@ void *__page_frag_alloc_align(struct page_frag_cache *nc,
 			      unsigned int fragsz, gfp_t gfp_mask,
 			      unsigned int align_mask)
 {
-#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE)
-	unsigned int size = nc->size;
-#else
-	unsigned int size = PAGE_SIZE;
-#endif
-	unsigned int offset;
+	unsigned long encoded_page = nc->encoded_page;
+	unsigned int size, offset;
 	struct page *page;
 
-	if (unlikely(!nc->va)) {
+	if (unlikely(!encoded_page)) {
 refill:
 		page = __page_frag_cache_refill(nc, gfp_mask);
 		if (!page)
 			return NULL;
 
-#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE)
-		/* if size can vary use size else just use PAGE_SIZE */
-		size = nc->size;
-#endif
+		encoded_page = nc->encoded_page;
+
 		/* Even if we own the page, we do not use atomic_set().
 		 * This would break get_page_unless_zero() users.
 		 */
 		page_ref_add(page, PAGE_FRAG_CACHE_MAX_SIZE);
 
 		/* reset page count bias and offset to start of new frag */
-		nc->pfmemalloc = page_is_pfmemalloc(page);
 		nc->pagecnt_bias = PAGE_FRAG_CACHE_MAX_SIZE + 1;
 		nc->offset = 0;
 	}
 
+	size = page_frag_cache_page_size(encoded_page);
 	offset = __ALIGN_KERNEL_MASK(nc->offset, ~align_mask);
 	if (unlikely(offset + fragsz > size)) {
 		if (unlikely(fragsz > PAGE_SIZE)) {
@@ -107,13 +137,14 @@ void *__page_frag_alloc_align(struct page_frag_cache *nc,
 			return NULL;
 		}
 
-		page = virt_to_page(nc->va);
+		page = page_frag_encoded_page_ptr(encoded_page);
 
 		if (!page_ref_sub_and_test(page, nc->pagecnt_bias))
 			goto refill;
 
-		if (unlikely(nc->pfmemalloc)) {
-			free_unref_page(page, compound_order(page));
+		if (unlikely(page_frag_encoded_page_pfmemalloc(encoded_page))) {
+			free_unref_page(page,
+					page_frag_encoded_page_order(encoded_page));
 			goto refill;
 		}
 
@@ -128,7 +159,7 @@ void *__page_frag_alloc_align(struct page_frag_cache *nc,
 	nc->pagecnt_bias--;
 	nc->offset = offset + fragsz;
 
-	return nc->va + offset;
+	return page_frag_encoded_page_address(encoded_page) + offset;
 }
 EXPORT_SYMBOL(__page_frag_alloc_align);
 
-- 
2.34.1

Re: [PATCH net-next v19 06/14] mm: page_frag: reuse existing space for 'size' and 'pfmemalloc'

[Alexander Duyck]

On Tue, Oct 1, 2024 at 12:59 AM Yunsheng Lin <yunshenglin0825@gmail.com> wrote:
>
> Currently there is one 'struct page_frag' for every 'struct
> sock' and 'struct task_struct', we are about to replace the
> 'struct page_frag' with 'struct page_frag_cache' for them.
> Before begin the replacing, we need to ensure the size of
> 'struct page_frag_cache' is not bigger than the size of
> 'struct page_frag', as there may be tens of thousands of
> 'struct sock' and 'struct task_struct' instances in the
> system.
>
> By or'ing the page order & pfmemalloc with lower bits of
> 'va' instead of using 'u16' or 'u32' for page size and 'u8'
> for pfmemalloc, we are able to avoid 3 or 5 bytes space waste.
> And page address & pfmemalloc & order is unchanged for the
> same page in the same 'page_frag_cache' instance, it makes
> sense to fit them together.
>
> After this patch, the size of 'struct page_frag_cache' should be
> the same as the size of 'struct page_frag'.
>
> CC: Alexander Duyck <alexander.duyck@gmail.com>
> Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
> ---
>  include/linux/mm_types_task.h   | 19 +++++----
>  include/linux/page_frag_cache.h | 26 +++++++++++-
>  mm/page_frag_cache.c            | 75 +++++++++++++++++++++++----------
>  3 files changed, 88 insertions(+), 32 deletions(-)
>
> diff --git a/include/linux/mm_types_task.h b/include/linux/mm_types_task.h
> index 0ac6daebdd5c..a82aa80c0ba4 100644
> --- a/include/linux/mm_types_task.h
> +++ b/include/linux/mm_types_task.h
> @@ -47,18 +47,21 @@ struct page_frag {
>  #define PAGE_FRAG_CACHE_MAX_SIZE       __ALIGN_MASK(32768, ~PAGE_MASK)
>  #define PAGE_FRAG_CACHE_MAX_ORDER      get_order(PAGE_FRAG_CACHE_MAX_SIZE)
>  struct page_frag_cache {
> -       void *va;
> -#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE)
> +       /* encoded_page consists of the virtual address, pfmemalloc bit and
> +        * order of a page.
> +        */
> +       unsigned long encoded_page;
> +
> +       /* we maintain a pagecount bias, so that we dont dirty cache line
> +        * containing page->_refcount every time we allocate a fragment.
> +        */
> +#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE) && (BITS_PER_LONG <= 32)
>         __u16 offset;
> -       __u16 size;
> +       __u16 pagecnt_bias;
>  #else
>         __u32 offset;
> +       __u32 pagecnt_bias;
>  #endif
> -       /* we maintain a pagecount bias, so that we dont dirty cache line
> -        * containing page->_refcount every time we allocate a fragment.
> -        */
> -       unsigned int            pagecnt_bias;
> -       bool pfmemalloc;
>  };
>
>  /* Track pages that require TLB flushes */
> diff --git a/include/linux/page_frag_cache.h b/include/linux/page_frag_cache.h
> index 0a52f7a179c8..75aaad6eaea2 100644
> --- a/include/linux/page_frag_cache.h
> +++ b/include/linux/page_frag_cache.h
> @@ -3,18 +3,40 @@
>  #ifndef _LINUX_PAGE_FRAG_CACHE_H
>  #define _LINUX_PAGE_FRAG_CACHE_H
>
> +#include <linux/bits.h>
>  #include <linux/log2.h>
>  #include <linux/mm_types_task.h>
>  #include <linux/types.h>
>
> +#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE)
> +/* Use a full byte here to enable assembler optimization as the shift
> + * operation is usually expecting a byte.
> + */
> +#define PAGE_FRAG_CACHE_ORDER_MASK             GENMASK(7, 0)
> +#define PAGE_FRAG_CACHE_PFMEMALLOC_SHIFT       8
> +#define PAGE_FRAG_CACHE_PFMEMALLOC_BIT         BIT(PAGE_FRAG_CACHE_PFMEMALLOC_SHIFT)
> +#else
> +/* Compiler should be able to figure out we don't read things as any value
> + * ANDed with 0 is 0.
> + */
> +#define PAGE_FRAG_CACHE_ORDER_MASK             0
> +#define PAGE_FRAG_CACHE_PFMEMALLOC_SHIFT       0
> +#define PAGE_FRAG_CACHE_PFMEMALLOC_BIT         BIT(PAGE_FRAG_CACHE_PFMEMALLOC_SHIFT)
> +#endif
> +

Minor nit on this. You probably only need to have
PAGE_FRAG_CACHE_ORDER_SHIFT defined in the ifdef. The PFMEMALLOC bit
code is the same in both so you could pull it out.

Also depending on how you defined it you could just define the
PFMEMALLOC_BIT as the ORDER_MASK + 1.

Re: [PATCH net-next v19 06/14] mm: page_frag: reuse existing space for 'size' and 'pfmemalloc'

[Yunsheng Lin]

On 10/4/2024 6:40 AM, Alexander Duyck wrote:
> On Tue, Oct 1, 2024 at 12:59 AM Yunsheng Lin <yunshenglin0825@gmail.com> wrote:
>>
>> Currently there is one 'struct page_frag' for every 'struct
>> sock' and 'struct task_struct', we are about to replace the
>> 'struct page_frag' with 'struct page_frag_cache' for them.
>> Before begin the replacing, we need to ensure the size of
>> 'struct page_frag_cache' is not bigger than the size of
>> 'struct page_frag', as there may be tens of thousands of
>> 'struct sock' and 'struct task_struct' instances in the
>> system.
>>
>> By or'ing the page order & pfmemalloc with lower bits of
>> 'va' instead of using 'u16' or 'u32' for page size and 'u8'
>> for pfmemalloc, we are able to avoid 3 or 5 bytes space waste.
>> And page address & pfmemalloc & order is unchanged for the
>> same page in the same 'page_frag_cache' instance, it makes
>> sense to fit them together.
>>
>> After this patch, the size of 'struct page_frag_cache' should be
>> the same as the size of 'struct page_frag'.
>>
>> CC: Alexander Duyck <alexander.duyck@gmail.com>
>> Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
>> ---
>>   include/linux/mm_types_task.h   | 19 +++++----
>>   include/linux/page_frag_cache.h | 26 +++++++++++-
>>   mm/page_frag_cache.c            | 75 +++++++++++++++++++++++----------
>>   3 files changed, 88 insertions(+), 32 deletions(-)
>>
>> diff --git a/include/linux/mm_types_task.h b/include/linux/mm_types_task.h
>> index 0ac6daebdd5c..a82aa80c0ba4 100644
>> --- a/include/linux/mm_types_task.h
>> +++ b/include/linux/mm_types_task.h
>> @@ -47,18 +47,21 @@ struct page_frag {
>>   #define PAGE_FRAG_CACHE_MAX_SIZE       __ALIGN_MASK(32768, ~PAGE_MASK)
>>   #define PAGE_FRAG_CACHE_MAX_ORDER      get_order(PAGE_FRAG_CACHE_MAX_SIZE)
>>   struct page_frag_cache {
>> -       void *va;
>> -#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE)
>> +       /* encoded_page consists of the virtual address, pfmemalloc bit and
>> +        * order of a page.
>> +        */
>> +       unsigned long encoded_page;
>> +
>> +       /* we maintain a pagecount bias, so that we dont dirty cache line
>> +        * containing page->_refcount every time we allocate a fragment.
>> +        */
>> +#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE) && (BITS_PER_LONG <= 32)
>>          __u16 offset;
>> -       __u16 size;
>> +       __u16 pagecnt_bias;
>>   #else
>>          __u32 offset;
>> +       __u32 pagecnt_bias;
>>   #endif
>> -       /* we maintain a pagecount bias, so that we dont dirty cache line
>> -        * containing page->_refcount every time we allocate a fragment.
>> -        */
>> -       unsigned int            pagecnt_bias;
>> -       bool pfmemalloc;
>>   };
>>
>>   /* Track pages that require TLB flushes */
>> diff --git a/include/linux/page_frag_cache.h b/include/linux/page_frag_cache.h
>> index 0a52f7a179c8..75aaad6eaea2 100644
>> --- a/include/linux/page_frag_cache.h
>> +++ b/include/linux/page_frag_cache.h
>> @@ -3,18 +3,40 @@
>>   #ifndef _LINUX_PAGE_FRAG_CACHE_H
>>   #define _LINUX_PAGE_FRAG_CACHE_H
>>
>> +#include <linux/bits.h>
>>   #include <linux/log2.h>
>>   #include <linux/mm_types_task.h>
>>   #include <linux/types.h>
>>
>> +#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE)
>> +/* Use a full byte here to enable assembler optimization as the shift
>> + * operation is usually expecting a byte.
>> + */
>> +#define PAGE_FRAG_CACHE_ORDER_MASK             GENMASK(7, 0)
>> +#define PAGE_FRAG_CACHE_PFMEMALLOC_SHIFT       8
>> +#define PAGE_FRAG_CACHE_PFMEMALLOC_BIT         BIT(PAGE_FRAG_CACHE_PFMEMALLOC_SHIFT)
>> +#else
>> +/* Compiler should be able to figure out we don't read things as any value
>> + * ANDed with 0 is 0.
>> + */
>> +#define PAGE_FRAG_CACHE_ORDER_MASK             0
>> +#define PAGE_FRAG_CACHE_PFMEMALLOC_SHIFT       0
>> +#define PAGE_FRAG_CACHE_PFMEMALLOC_BIT         BIT(PAGE_FRAG_CACHE_PFMEMALLOC_SHIFT)
>> +#endif
>> +
> 
> Minor nit on this. You probably only need to have
> PAGE_FRAG_CACHE_ORDER_SHIFT defined in the ifdef. The PFMEMALLOC bit

I guess you meant PAGE_FRAG_CACHE_ORDER_MASK here instead of
PAGE_FRAG_CACHE_ORDER_SHIFT, as the ORDER_SHIFT is always
zero?

> code is the same in both so you could pull it out.
> 
> Also depending on how you defined it you could just define the
> PFMEMALLOC_BIT as the ORDER_MASK + 1.

But the PFMEMALLOC_SHIFT still need to be defined as it is used in
page_frag_encode_page(), right? I am not sure if I understand what is
the point of defining the PFMEMALLOC_BIT as the ORDER_MASK + 1 instead
of defining the PFMEMALLOC_BIT as BIT(PAGE_FRAG_CACHE_PFMEMALLOC_SHIFT) 
here.

Re: [PATCH net-next v19 06/14] mm: page_frag: reuse existing space for 'size' and 'pfmemalloc'

[Alexander Duyck]

On Sat, Oct 5, 2024 at 6:06 AM Yunsheng Lin <yunshenglin0825@gmail.com> wrote:
>
> On 10/4/2024 6:40 AM, Alexander Duyck wrote:
> > On Tue, Oct 1, 2024 at 12:59 AM Yunsheng Lin <yunshenglin0825@gmail.com> wrote:
> >>
> >> Currently there is one 'struct page_frag' for every 'struct
> >> sock' and 'struct task_struct', we are about to replace the
> >> 'struct page_frag' with 'struct page_frag_cache' for them.
> >> Before begin the replacing, we need to ensure the size of
> >> 'struct page_frag_cache' is not bigger than the size of
> >> 'struct page_frag', as there may be tens of thousands of
> >> 'struct sock' and 'struct task_struct' instances in the
> >> system.
> >>
> >> By or'ing the page order & pfmemalloc with lower bits of
> >> 'va' instead of using 'u16' or 'u32' for page size and 'u8'
> >> for pfmemalloc, we are able to avoid 3 or 5 bytes space waste.
> >> And page address & pfmemalloc & order is unchanged for the
> >> same page in the same 'page_frag_cache' instance, it makes
> >> sense to fit them together.
> >>
> >> After this patch, the size of 'struct page_frag_cache' should be
> >> the same as the size of 'struct page_frag'.
> >>
> >> CC: Alexander Duyck <alexander.duyck@gmail.com>
> >> Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
> >> ---
> >>   include/linux/mm_types_task.h   | 19 +++++----
> >>   include/linux/page_frag_cache.h | 26 +++++++++++-
> >>   mm/page_frag_cache.c            | 75 +++++++++++++++++++++++----------
> >>   3 files changed, 88 insertions(+), 32 deletions(-)
> >>
> >> diff --git a/include/linux/mm_types_task.h b/include/linux/mm_types_task.h
> >> index 0ac6daebdd5c..a82aa80c0ba4 100644
> >> --- a/include/linux/mm_types_task.h
> >> +++ b/include/linux/mm_types_task.h
> >> @@ -47,18 +47,21 @@ struct page_frag {
> >>   #define PAGE_FRAG_CACHE_MAX_SIZE       __ALIGN_MASK(32768, ~PAGE_MASK)
> >>   #define PAGE_FRAG_CACHE_MAX_ORDER      get_order(PAGE_FRAG_CACHE_MAX_SIZE)
> >>   struct page_frag_cache {
> >> -       void *va;
> >> -#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE)
> >> +       /* encoded_page consists of the virtual address, pfmemalloc bit and
> >> +        * order of a page.
> >> +        */
> >> +       unsigned long encoded_page;
> >> +
> >> +       /* we maintain a pagecount bias, so that we dont dirty cache line
> >> +        * containing page->_refcount every time we allocate a fragment.
> >> +        */
> >> +#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE) && (BITS_PER_LONG <= 32)
> >>          __u16 offset;
> >> -       __u16 size;
> >> +       __u16 pagecnt_bias;
> >>   #else
> >>          __u32 offset;
> >> +       __u32 pagecnt_bias;
> >>   #endif
> >> -       /* we maintain a pagecount bias, so that we dont dirty cache line
> >> -        * containing page->_refcount every time we allocate a fragment.
> >> -        */
> >> -       unsigned int            pagecnt_bias;
> >> -       bool pfmemalloc;
> >>   };
> >>
> >>   /* Track pages that require TLB flushes */
> >> diff --git a/include/linux/page_frag_cache.h b/include/linux/page_frag_cache.h
> >> index 0a52f7a179c8..75aaad6eaea2 100644
> >> --- a/include/linux/page_frag_cache.h
> >> +++ b/include/linux/page_frag_cache.h
> >> @@ -3,18 +3,40 @@
> >>   #ifndef _LINUX_PAGE_FRAG_CACHE_H
> >>   #define _LINUX_PAGE_FRAG_CACHE_H
> >>
> >> +#include <linux/bits.h>
> >>   #include <linux/log2.h>
> >>   #include <linux/mm_types_task.h>
> >>   #include <linux/types.h>
> >>
> >> +#if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE)
> >> +/* Use a full byte here to enable assembler optimization as the shift
> >> + * operation is usually expecting a byte.
> >> + */
> >> +#define PAGE_FRAG_CACHE_ORDER_MASK             GENMASK(7, 0)
> >> +#define PAGE_FRAG_CACHE_PFMEMALLOC_SHIFT       8
> >> +#define PAGE_FRAG_CACHE_PFMEMALLOC_BIT         BIT(PAGE_FRAG_CACHE_PFMEMALLOC_SHIFT)
> >> +#else
> >> +/* Compiler should be able to figure out we don't read things as any value
> >> + * ANDed with 0 is 0.
> >> + */
> >> +#define PAGE_FRAG_CACHE_ORDER_MASK             0
> >> +#define PAGE_FRAG_CACHE_PFMEMALLOC_SHIFT       0
> >> +#define PAGE_FRAG_CACHE_PFMEMALLOC_BIT         BIT(PAGE_FRAG_CACHE_PFMEMALLOC_SHIFT)
> >> +#endif
> >> +
> >
> > Minor nit on this. You probably only need to have
> > PAGE_FRAG_CACHE_ORDER_SHIFT defined in the ifdef. The PFMEMALLOC bit
>
> I guess you meant PAGE_FRAG_CACHE_ORDER_MASK here instead of
> PAGE_FRAG_CACHE_ORDER_SHIFT, as the ORDER_SHIFT is always
> zero?

Yes.

> > code is the same in both so you could pull it out.
> >
> > Also depending on how you defined it you could just define the
> > PFMEMALLOC_BIT as the ORDER_MASK + 1.
>
> But the PFMEMALLOC_SHIFT still need to be defined as it is used in
> page_frag_encode_page(), right? I am not sure if I understand what is
> the point of defining the PFMEMALLOC_BIT as the ORDER_MASK + 1 instead
> of defining the PFMEMALLOC_BIT as BIT(PAGE_FRAG_CACHE_PFMEMALLOC_SHIFT)
> here.

Actually the shift probably isn't needed. Since it is a single bit
value you could just use a multiply by the bit and it would accomplish
the same thing as the shift and would likely be converted to the same
assembler code.

[PATCH net-next v19 07/14] mm: page_frag: some minor refactoring before adding new API

[Yunsheng Lin]

Refactor common codes from __page_frag_alloc_va_align() to
__page_frag_cache_prepare() and __page_frag_cache_commit(),
so that the new API can make use of them.

CC: Alexander Duyck <alexander.duyck@gmail.com>
Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
---
 include/linux/page_frag_cache.h | 36 +++++++++++++++++++++++++++--
 mm/page_frag_cache.c            | 40 ++++++++++++++++++++++++++-------
 2 files changed, 66 insertions(+), 10 deletions(-)

diff --git a/include/linux/page_frag_cache.h b/include/linux/page_frag_cache.h
index 75aaad6eaea2..b634e1338741 100644
--- a/include/linux/page_frag_cache.h
+++ b/include/linux/page_frag_cache.h
@@ -5,6 +5,7 @@
 
 #include <linux/bits.h>
 #include <linux/log2.h>
+#include <linux/mmdebug.h>
 #include <linux/mm_types_task.h>
 #include <linux/types.h>
 
@@ -41,8 +42,39 @@ static inline bool page_frag_cache_is_pfmemalloc(struct page_frag_cache *nc)
 
 void page_frag_cache_drain(struct page_frag_cache *nc);
 void __page_frag_cache_drain(struct page *page, unsigned int count);
-void *__page_frag_alloc_align(struct page_frag_cache *nc, unsigned int fragsz,
-			      gfp_t gfp_mask, unsigned int align_mask);
+void *__page_frag_cache_prepare(struct page_frag_cache *nc, unsigned int fragsz,
+				struct page_frag *pfrag, gfp_t gfp_mask,
+				unsigned int align_mask);
+unsigned int __page_frag_cache_commit_noref(struct page_frag_cache *nc,
+					    struct page_frag *pfrag,
+					    unsigned int used_sz);
+
+static inline unsigned int __page_frag_cache_commit(struct page_frag_cache *nc,
+						    struct page_frag *pfrag,
+						    unsigned int used_sz)
+{
+	VM_BUG_ON(!nc->pagecnt_bias);
+	nc->pagecnt_bias--;
+
+	return __page_frag_cache_commit_noref(nc, pfrag, used_sz);
+}
+
+static inline void *__page_frag_alloc_align(struct page_frag_cache *nc,
+					    unsigned int fragsz, gfp_t gfp_mask,
+					    unsigned int align_mask)
+{
+	struct page_frag page_frag;
+	void *va;
+
+	va = __page_frag_cache_prepare(nc, fragsz, &page_frag, gfp_mask,
+				       align_mask);
+	if (unlikely(!va))
+		return NULL;
+
+	__page_frag_cache_commit(nc, &page_frag, fragsz);
+
+	return va;
+}
 
 static inline void *page_frag_alloc_align(struct page_frag_cache *nc,
 					  unsigned int fragsz, gfp_t gfp_mask,
diff --git a/mm/page_frag_cache.c b/mm/page_frag_cache.c
index cf9375a81a64..6f6e47bbdc8d 100644
--- a/mm/page_frag_cache.c
+++ b/mm/page_frag_cache.c
@@ -95,9 +95,31 @@ void __page_frag_cache_drain(struct page *page, unsigned int count)
 }
 EXPORT_SYMBOL(__page_frag_cache_drain);
 
-void *__page_frag_alloc_align(struct page_frag_cache *nc,
-			      unsigned int fragsz, gfp_t gfp_mask,
-			      unsigned int align_mask)
+unsigned int __page_frag_cache_commit_noref(struct page_frag_cache *nc,
+					    struct page_frag *pfrag,
+					    unsigned int used_sz)
+{
+	unsigned int orig_offset;
+
+	VM_BUG_ON(used_sz > pfrag->size);
+	VM_BUG_ON(pfrag->page != page_frag_encoded_page_ptr(nc->encoded_page));
+	VM_BUG_ON(pfrag->offset + pfrag->size >
+		  page_frag_cache_page_size(nc->encoded_page));
+
+	/* pfrag->offset might be bigger than the nc->offset due to alignment */
+	VM_BUG_ON(nc->offset > pfrag->offset);
+
+	orig_offset = nc->offset;
+	nc->offset = pfrag->offset + used_sz;
+
+	/* Return true size back to caller considering the offset alignment */
+	return nc->offset - orig_offset;
+}
+EXPORT_SYMBOL(__page_frag_cache_commit_noref);
+
+void *__page_frag_cache_prepare(struct page_frag_cache *nc, unsigned int fragsz,
+				struct page_frag *pfrag, gfp_t gfp_mask,
+				unsigned int align_mask)
 {
 	unsigned long encoded_page = nc->encoded_page;
 	unsigned int size, offset;
@@ -119,6 +141,8 @@ void *__page_frag_alloc_align(struct page_frag_cache *nc,
 		/* reset page count bias and offset to start of new frag */
 		nc->pagecnt_bias = PAGE_FRAG_CACHE_MAX_SIZE + 1;
 		nc->offset = 0;
+	} else {
+		page = page_frag_encoded_page_ptr(encoded_page);
 	}
 
 	size = page_frag_cache_page_size(encoded_page);
@@ -137,8 +161,6 @@ void *__page_frag_alloc_align(struct page_frag_cache *nc,
 			return NULL;
 		}
 
-		page = page_frag_encoded_page_ptr(encoded_page);
-
 		if (!page_ref_sub_and_test(page, nc->pagecnt_bias))
 			goto refill;
 
@@ -153,15 +175,17 @@ void *__page_frag_alloc_align(struct page_frag_cache *nc,
 
 		/* reset page count bias and offset to start of new frag */
 		nc->pagecnt_bias = PAGE_FRAG_CACHE_MAX_SIZE + 1;
+		nc->offset = 0;
 		offset = 0;
 	}
 
-	nc->pagecnt_bias--;
-	nc->offset = offset + fragsz;
+	pfrag->page = page;
+	pfrag->offset = offset;
+	pfrag->size = size - offset;
 
 	return page_frag_encoded_page_address(encoded_page) + offset;
 }
-EXPORT_SYMBOL(__page_frag_alloc_align);
+EXPORT_SYMBOL(__page_frag_cache_prepare);
 
 /*
  * Frees a page fragment allocated out of either a compound or order 0 page.
-- 
2.34.1

[PATCH net-next v19 08/14] mm: page_frag: use __alloc_pages() to replace alloc_pages_node()

[Yunsheng Lin]

It seems there is about 24Bytes binary size increase for
__page_frag_cache_refill() after refactoring in arm64 system
with 64K PAGE_SIZE. By doing the gdb disassembling, It seems
we can have more than 100Bytes decrease for the binary size
by using __alloc_pages() to replace alloc_pages_node(), as
there seems to be some unnecessary checking for nid being
NUMA_NO_NODE, especially when page_frag is part of the mm
system.

CC: Alexander Duyck <alexander.duyck@gmail.com>
Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
---
 mm/page_frag_cache.c | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/mm/page_frag_cache.c b/mm/page_frag_cache.c
index 6f6e47bbdc8d..a5448b44068a 100644
--- a/mm/page_frag_cache.c
+++ b/mm/page_frag_cache.c
@@ -61,11 +61,11 @@ static struct page *__page_frag_cache_refill(struct page_frag_cache *nc,
 #if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE)
 	gfp_mask = (gfp_mask & ~__GFP_DIRECT_RECLAIM) |  __GFP_COMP |
 		   __GFP_NOWARN | __GFP_NORETRY | __GFP_NOMEMALLOC;
-	page = alloc_pages_node(NUMA_NO_NODE, gfp_mask,
-				PAGE_FRAG_CACHE_MAX_ORDER);
+	page = __alloc_pages(gfp_mask, PAGE_FRAG_CACHE_MAX_ORDER,
+			     numa_mem_id(), NULL);
 #endif
 	if (unlikely(!page)) {
-		page = alloc_pages_node(NUMA_NO_NODE, gfp, 0);
+		page = __alloc_pages(gfp, 0, numa_mem_id(), NULL);
 		order = 0;
 	}
 
-- 
2.34.1

Re: [PATCH net-next v19 08/14] mm: page_frag: use __alloc_pages() to replace alloc_pages_node()

[Alexander Duyck]

On Tue, Oct 1, 2024 at 12:59 AM Yunsheng Lin <yunshenglin0825@gmail.com> wrote:
>
> It seems there is about 24Bytes binary size increase for
> __page_frag_cache_refill() after refactoring in arm64 system
> with 64K PAGE_SIZE. By doing the gdb disassembling, It seems
> we can have more than 100Bytes decrease for the binary size
> by using __alloc_pages() to replace alloc_pages_node(), as
> there seems to be some unnecessary checking for nid being
> NUMA_NO_NODE, especially when page_frag is part of the mm
> system.
>
> CC: Alexander Duyck <alexander.duyck@gmail.com>
> Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
> ---
>  mm/page_frag_cache.c | 6 +++---
>  1 file changed, 3 insertions(+), 3 deletions(-)
>
> diff --git a/mm/page_frag_cache.c b/mm/page_frag_cache.c
> index 6f6e47bbdc8d..a5448b44068a 100644
> --- a/mm/page_frag_cache.c
> +++ b/mm/page_frag_cache.c
> @@ -61,11 +61,11 @@ static struct page *__page_frag_cache_refill(struct page_frag_cache *nc,
>  #if (PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE)
>         gfp_mask = (gfp_mask & ~__GFP_DIRECT_RECLAIM) |  __GFP_COMP |
>                    __GFP_NOWARN | __GFP_NORETRY | __GFP_NOMEMALLOC;
> -       page = alloc_pages_node(NUMA_NO_NODE, gfp_mask,
> -                               PAGE_FRAG_CACHE_MAX_ORDER);
> +       page = __alloc_pages(gfp_mask, PAGE_FRAG_CACHE_MAX_ORDER,
> +                            numa_mem_id(), NULL);
>  #endif
>         if (unlikely(!page)) {
> -               page = alloc_pages_node(NUMA_NO_NODE, gfp, 0);
> +               page = __alloc_pages(gfp, 0, numa_mem_id(), NULL);
>                 order = 0;
>         }
>

Still not a huge fan of fixing the bigger issue here, but I guess
there is only one or two other spots that encounter this, so I would
classify it as "mostly harmless" in terms of not fixing it.

Reviewed-by: Alexander Duyck <alexanderduyck@fb.com>

[PATCH net-next v19 10/14] mm: page_frag: introduce prepare/probe/commit API

[Yunsheng Lin]

There are many use cases that need minimum memory in order
for forward progress, but more performant if more memory is
available or need to probe the cache info to use any memory
available for frag caoleasing reason.

Currently skb_page_frag_refill() API is used to solve the
above use cases, but caller needs to know about the internal
detail and access the data field of 'struct page_frag' to
meet the requirement of the above use cases and its
implementation is similar to the one in mm subsystem.

To unify those two page_frag implementations, introduce a
prepare API to ensure minimum memory is satisfied and return
how much the actual memory is available to the caller and a
probe API to report the current available memory to caller
without doing cache refilling. The caller needs to either call
the commit API to report how much memory it actually uses, or
not do so if deciding to not use any memory.

CC: Alexander Duyck <alexander.duyck@gmail.com>
Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
---
 include/linux/page_frag_cache.h | 135 ++++++++++++++++++++++++++++++++
 mm/page_frag_cache.c            |  21 +++++
 2 files changed, 156 insertions(+)

diff --git a/include/linux/page_frag_cache.h b/include/linux/page_frag_cache.h
index b634e1338741..4e9018051956 100644
--- a/include/linux/page_frag_cache.h
+++ b/include/linux/page_frag_cache.h
@@ -40,6 +40,11 @@ static inline bool page_frag_cache_is_pfmemalloc(struct page_frag_cache *nc)
 	return page_frag_encoded_page_pfmemalloc(nc->encoded_page);
 }
 
+static inline unsigned int page_frag_cache_page_offset(const struct page_frag_cache *nc)
+{
+	return nc->offset;
+}
+
 void page_frag_cache_drain(struct page_frag_cache *nc);
 void __page_frag_cache_drain(struct page *page, unsigned int count);
 void *__page_frag_cache_prepare(struct page_frag_cache *nc, unsigned int fragsz,
@@ -48,6 +53,10 @@ void *__page_frag_cache_prepare(struct page_frag_cache *nc, unsigned int fragsz,
 unsigned int __page_frag_cache_commit_noref(struct page_frag_cache *nc,
 					    struct page_frag *pfrag,
 					    unsigned int used_sz);
+void *__page_frag_alloc_refill_probe_align(struct page_frag_cache *nc,
+					   unsigned int fragsz,
+					   struct page_frag *pfrag,
+					   unsigned int align_mask);
 
 static inline unsigned int __page_frag_cache_commit(struct page_frag_cache *nc,
 						    struct page_frag *pfrag,
@@ -90,6 +99,132 @@ static inline void *page_frag_alloc(struct page_frag_cache *nc,
 	return __page_frag_alloc_align(nc, fragsz, gfp_mask, ~0u);
 }
 
+static inline bool __page_frag_refill_align(struct page_frag_cache *nc,
+					    unsigned int fragsz,
+					    struct page_frag *pfrag,
+					    gfp_t gfp_mask,
+					    unsigned int align_mask)
+{
+	if (unlikely(!__page_frag_cache_prepare(nc, fragsz, pfrag, gfp_mask,
+						align_mask)))
+		return false;
+
+	__page_frag_cache_commit(nc, pfrag, fragsz);
+	return true;
+}
+
+static inline bool page_frag_refill_align(struct page_frag_cache *nc,
+					  unsigned int fragsz,
+					  struct page_frag *pfrag,
+					  gfp_t gfp_mask, unsigned int align)
+{
+	WARN_ON_ONCE(!is_power_of_2(align));
+	return __page_frag_refill_align(nc, fragsz, pfrag, gfp_mask, -align);
+}
+
+static inline bool page_frag_refill(struct page_frag_cache *nc,
+				    unsigned int fragsz,
+				    struct page_frag *pfrag, gfp_t gfp_mask)
+{
+	return __page_frag_refill_align(nc, fragsz, pfrag, gfp_mask, ~0u);
+}
+
+static inline bool __page_frag_refill_prepare_align(struct page_frag_cache *nc,
+						    unsigned int fragsz,
+						    struct page_frag *pfrag,
+						    gfp_t gfp_mask,
+						    unsigned int align_mask)
+{
+	return !!__page_frag_cache_prepare(nc, fragsz, pfrag, gfp_mask,
+					   align_mask);
+}
+
+static inline bool page_frag_refill_prepare_align(struct page_frag_cache *nc,
+						  unsigned int fragsz,
+						  struct page_frag *pfrag,
+						  gfp_t gfp_mask,
+						  unsigned int align)
+{
+	WARN_ON_ONCE(!is_power_of_2(align));
+	return __page_frag_refill_prepare_align(nc, fragsz, pfrag, gfp_mask,
+						-align);
+}
+
+static inline bool page_frag_refill_prepare(struct page_frag_cache *nc,
+					    unsigned int fragsz,
+					    struct page_frag *pfrag,
+					    gfp_t gfp_mask)
+{
+	return __page_frag_refill_prepare_align(nc, fragsz, pfrag, gfp_mask,
+						~0u);
+}
+
+static inline void *__page_frag_alloc_refill_prepare_align(struct page_frag_cache *nc,
+							   unsigned int fragsz,
+							   struct page_frag *pfrag,
+							   gfp_t gfp_mask,
+							   unsigned int align_mask)
+{
+	return __page_frag_cache_prepare(nc, fragsz, pfrag, gfp_mask, align_mask);
+}
+
+static inline void *page_frag_alloc_refill_prepare_align(struct page_frag_cache *nc,
+							 unsigned int fragsz,
+							 struct page_frag *pfrag,
+							 gfp_t gfp_mask,
+							 unsigned int align)
+{
+	WARN_ON_ONCE(!is_power_of_2(align));
+	return __page_frag_alloc_refill_prepare_align(nc, fragsz, pfrag,
+						      gfp_mask, -align);
+}
+
+static inline void *page_frag_alloc_refill_prepare(struct page_frag_cache *nc,
+						   unsigned int fragsz,
+						   struct page_frag *pfrag,
+						   gfp_t gfp_mask)
+{
+	return __page_frag_alloc_refill_prepare_align(nc, fragsz, pfrag,
+						      gfp_mask, ~0u);
+}
+
+static inline void *page_frag_alloc_refill_probe(struct page_frag_cache *nc,
+						 unsigned int fragsz,
+						 struct page_frag *pfrag)
+{
+	return __page_frag_alloc_refill_probe_align(nc, fragsz, pfrag, ~0u);
+}
+
+static inline bool page_frag_refill_probe(struct page_frag_cache *nc,
+					  unsigned int fragsz,
+					  struct page_frag *pfrag)
+{
+	return !!page_frag_alloc_refill_probe(nc, fragsz, pfrag);
+}
+
+static inline void page_frag_commit(struct page_frag_cache *nc,
+				    struct page_frag *pfrag,
+				    unsigned int used_sz)
+{
+	__page_frag_cache_commit(nc, pfrag, used_sz);
+}
+
+static inline void page_frag_commit_noref(struct page_frag_cache *nc,
+					  struct page_frag *pfrag,
+					  unsigned int used_sz)
+{
+	__page_frag_cache_commit_noref(nc, pfrag, used_sz);
+}
+
+static inline void page_frag_alloc_abort(struct page_frag_cache *nc,
+					 unsigned int fragsz)
+{
+	VM_BUG_ON(fragsz > nc->offset);
+
+	nc->pagecnt_bias++;
+	nc->offset -= fragsz;
+}
+
 void page_frag_free(void *addr);
 
 #endif
diff --git a/mm/page_frag_cache.c b/mm/page_frag_cache.c
index a5448b44068a..c052c77a96eb 100644
--- a/mm/page_frag_cache.c
+++ b/mm/page_frag_cache.c
@@ -117,6 +117,27 @@ unsigned int __page_frag_cache_commit_noref(struct page_frag_cache *nc,
 }
 EXPORT_SYMBOL(__page_frag_cache_commit_noref);
 
+void *__page_frag_alloc_refill_probe_align(struct page_frag_cache *nc,
+					   unsigned int fragsz,
+					   struct page_frag *pfrag,
+					   unsigned int align_mask)
+{
+	unsigned long encoded_page = nc->encoded_page;
+	unsigned int size, offset;
+
+	size = page_frag_cache_page_size(encoded_page);
+	offset = __ALIGN_KERNEL_MASK(nc->offset, ~align_mask);
+	if (unlikely(!encoded_page || offset + fragsz > size))
+		return NULL;
+
+	pfrag->page = page_frag_encoded_page_ptr(encoded_page);
+	pfrag->size = size - offset;
+	pfrag->offset = offset;
+
+	return page_frag_encoded_page_address(encoded_page) + offset;
+}
+EXPORT_SYMBOL(__page_frag_alloc_refill_probe_align);
+
 void *__page_frag_cache_prepare(struct page_frag_cache *nc, unsigned int fragsz,
 				struct page_frag *pfrag, gfp_t gfp_mask,
 				unsigned int align_mask)
-- 
2.34.1

[PATCH net-next v19 11/14] mm: page_frag: add testing for the newly added prepare API

[Yunsheng Lin]

Add testing for the newly added prepare API, for both aligned
and non-aligned API, also probe API is also tested along with
prepare API.

CC: Alexander Duyck <alexander.duyck@gmail.com>
Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
---
 .../selftests/mm/page_frag/page_frag_test.c   | 66 +++++++++++++++++--
 tools/testing/selftests/mm/run_vmtests.sh     |  4 ++
 tools/testing/selftests/mm/test_page_frag.sh  | 31 +++++++++
 3 files changed, 96 insertions(+), 5 deletions(-)

diff --git a/tools/testing/selftests/mm/page_frag/page_frag_test.c b/tools/testing/selftests/mm/page_frag/page_frag_test.c
index 36543a129e40..567bcc6a181e 100644
--- a/tools/testing/selftests/mm/page_frag/page_frag_test.c
+++ b/tools/testing/selftests/mm/page_frag/page_frag_test.c
@@ -29,6 +29,10 @@ static bool test_align;
 module_param(test_align, bool, 0);
 MODULE_PARM_DESC(test_align, "use align API for testing");
 
+static bool test_prepare;
+module_param(test_prepare, bool, 0);
+MODULE_PARM_DESC(test_prepare, "use prepare API for testing");
+
 static int test_alloc_len = 2048;
 module_param(test_alloc_len, int, 0);
 MODULE_PARM_DESC(test_alloc_len, "alloc len for testing");
@@ -68,6 +72,18 @@ static int page_frag_pop_thread(void *arg)
 	return 0;
 }
 
+static void frag_frag_test_commit(struct page_frag_cache *nc,
+				  struct page_frag *prepare_pfrag,
+				  struct page_frag *probe_pfrag,
+				  unsigned int used_sz)
+{
+	WARN_ON_ONCE(prepare_pfrag->page != probe_pfrag->page ||
+		     prepare_pfrag->offset != probe_pfrag->offset ||
+		     prepare_pfrag->size != probe_pfrag->size);
+
+	page_frag_commit(nc, prepare_pfrag, used_sz);
+}
+
 static int page_frag_push_thread(void *arg)
 {
 	struct ptr_ring *ring = arg;
@@ -80,13 +96,52 @@ static int page_frag_push_thread(void *arg)
 		int ret;
 
 		if (test_align) {
-			va = page_frag_alloc_align(&test_nc, test_alloc_len,
-						   GFP_KERNEL, SMP_CACHE_BYTES);
+			if (test_prepare) {
+				struct page_frag prepare_frag, probe_frag;
+				void *probe_va;
+
+				va = page_frag_alloc_refill_prepare_align(&test_nc,
+									  test_alloc_len,
+									  &prepare_frag,
+									  GFP_KERNEL,
+									  SMP_CACHE_BYTES);
+
+				probe_va = __page_frag_alloc_refill_probe_align(&test_nc,
+										test_alloc_len,
+										&probe_frag,
+										-SMP_CACHE_BYTES);
+				WARN_ON_ONCE(va != probe_va);
+
+				if (likely(va))
+					frag_frag_test_commit(&test_nc, &prepare_frag,
+							      &probe_frag, test_alloc_len);
+			} else {
+				va = page_frag_alloc_align(&test_nc,
+							   test_alloc_len,
+							   GFP_KERNEL,
+							   SMP_CACHE_BYTES);
+			}
 
 			WARN_ONCE((unsigned long)va & (SMP_CACHE_BYTES - 1),
 				  "unaligned va returned\n");
 		} else {
-			va = page_frag_alloc(&test_nc, test_alloc_len, GFP_KERNEL);
+			if (test_prepare) {
+				struct page_frag prepare_frag, probe_frag;
+				void *probe_va;
+
+				va = page_frag_alloc_refill_prepare(&test_nc, test_alloc_len,
+								    &prepare_frag, GFP_KERNEL);
+
+				probe_va = page_frag_alloc_refill_probe(&test_nc, test_alloc_len,
+									&probe_frag);
+
+				WARN_ON_ONCE(va != probe_va);
+				if (likely(va))
+					frag_frag_test_commit(&test_nc, &prepare_frag,
+							      &probe_frag, test_alloc_len);
+			} else {
+				va = page_frag_alloc(&test_nc, test_alloc_len, GFP_KERNEL);
+			}
 		}
 
 		if (!va)
@@ -152,8 +207,9 @@ static int __init page_frag_test_init(void)
 			test_pushed, test_popped);
 
 	duration = (u64)ktime_us_delta(ktime_get(), start);
-	pr_info("%d of iterations for %s testing took: %lluus\n", nr_test,
-		test_align ? "aligned" : "non-aligned", duration);
+	pr_info("%d of iterations for %s %s API testing took: %lluus\n", nr_test,
+		test_align ? "aligned" : "non-aligned",
+		test_prepare ? "prepare" : "alloc", duration);
 
 	ptr_ring_cleanup(&ptr_ring, NULL);
 	page_frag_cache_drain(&test_nc);
diff --git a/tools/testing/selftests/mm/run_vmtests.sh b/tools/testing/selftests/mm/run_vmtests.sh
index 2c5394584af4..f6ff9080a6f2 100755
--- a/tools/testing/selftests/mm/run_vmtests.sh
+++ b/tools/testing/selftests/mm/run_vmtests.sh
@@ -464,6 +464,10 @@ CATEGORY="page_frag" run_test ./test_page_frag.sh aligned
 
 CATEGORY="page_frag" run_test ./test_page_frag.sh nonaligned
 
+CATEGORY="page_frag" run_test ./test_page_frag.sh aligned_prepare
+
+CATEGORY="page_frag" run_test ./test_page_frag.sh nonaligned_prepare
+
 echo "SUMMARY: PASS=${count_pass} SKIP=${count_skip} FAIL=${count_fail}" | tap_prefix
 echo "1..${count_total}" | tap_output
 
diff --git a/tools/testing/selftests/mm/test_page_frag.sh b/tools/testing/selftests/mm/test_page_frag.sh
index d750d910c899..71c3531fa38e 100755
--- a/tools/testing/selftests/mm/test_page_frag.sh
+++ b/tools/testing/selftests/mm/test_page_frag.sh
@@ -36,6 +36,8 @@ ksft_skip=4
 SMOKE_PARAM="test_push_cpu=$TEST_CPU_0 test_pop_cpu=$TEST_CPU_1"
 NONALIGNED_PARAM="$SMOKE_PARAM test_alloc_len=75 nr_test=$NR_TEST"
 ALIGNED_PARAM="$NONALIGNED_PARAM test_align=1"
+NONALIGNED_PREPARE_PARAM="$NONALIGNED_PARAM test_prepare=1"
+ALIGNED_PREPARE_PARAM="$ALIGNED_PARAM test_prepare=1"
 
 check_test_requirements()
 {
@@ -74,6 +76,24 @@ run_aligned_check()
 	echo "Check the kernel ring buffer to see the summary."
 }
 
+run_nonaligned_prepare_check()
+{
+	echo "Run performance tests to evaluate how fast nonaligned prepare API is."
+
+	insmod $DRIVER $NONALIGNED_PREPARE_PARAM > /dev/null 2>&1
+	echo "Done."
+	echo "Ccheck the kernel ring buffer to see the summary."
+}
+
+run_aligned_prepare_check()
+{
+	echo "Run performance tests to evaluate how fast aligned prepare API is."
+
+	insmod $DRIVER $ALIGNED_PREPARE_PARAM > /dev/null 2>&1
+	echo "Done."
+	echo "Check the kernel ring buffer to see the summary."
+}
+
 run_smoke_check()
 {
 	echo "Run smoke test."
@@ -86,6 +106,7 @@ run_smoke_check()
 usage()
 {
 	echo -n "Usage: $0 [ aligned ] | [ nonaligned ] | | [ smoke ] | "
+	echo "[ aligned_prepare ] | [ nonaligned_prepare ] | "
 	echo "manual parameters"
 	echo
 	echo "Valid tests and parameters:"
@@ -106,6 +127,12 @@ usage()
 	echo "# Performance testing for aligned alloc API"
 	echo "$0 aligned"
 	echo
+	echo "# Performance testing for nonaligned prepare API"
+	echo "$0 nonaligned_prepare"
+	echo
+	echo "# Performance testing for aligned prepare API"
+	echo "$0 aligned_prepare"
+	echo
 	exit 0
 }
 
@@ -159,6 +186,10 @@ function run_test()
 			run_nonaligned_check
 		elif [[ "$1" = "aligned" ]]; then
 			run_aligned_check
+		elif [[ "$1" = "nonaligned_prepare" ]]; then
+			run_nonaligned_prepare_check
+		elif [[ "$1" = "aligned_prepare" ]]; then
+			run_aligned_prepare_check
 		else
 			run_manual_check $@
 		fi
-- 
2.34.1

[PATCH net-next v19 13/14] mm: page_frag: update documentation for page_frag

[Yunsheng Lin]

Update documentation about design, implementation and API usages
for page_frag.

CC: Alexander Duyck <alexander.duyck@gmail.com>
Signed-off-by: Yunsheng Lin <linyunsheng@huawei.com>
---
 Documentation/mm/page_frags.rst | 177 +++++++++++++++++++++-
 include/linux/page_frag_cache.h | 259 +++++++++++++++++++++++++++++++-
 mm/page_frag_cache.c            |  26 +++-
 3 files changed, 451 insertions(+), 11 deletions(-)

diff --git a/Documentation/mm/page_frags.rst b/Documentation/mm/page_frags.rst
index 503ca6cdb804..5eec04a3fe90 100644
--- a/Documentation/mm/page_frags.rst
+++ b/Documentation/mm/page_frags.rst
@@ -1,3 +1,5 @@
+.. SPDX-License-Identifier: GPL-2.0
+
 ==============
 Page fragments
 ==============
@@ -40,4 +42,177 @@ page via a single call.  The advantage to doing this is that it allows for
 cleaning up the multiple references that were added to a page in order to
 avoid calling get_page per allocation.
 
-Alexander Duyck, Nov 29, 2016.
+
+Architecture overview
+=====================
+
+.. code-block:: none
+
+                      +----------------------+
+                      | page_frag API caller |
+                      +----------------------+
+                                  |
+                                  |
+                                  v
+    +------------------------------------------------------------------+
+    |                   request page fragment                          |
+    +------------------------------------------------------------------+
+             |                                 |                     |
+             |                                 |                     |
+             |                          Cache not enough             |
+             |                                 |                     |
+             |                         +-----------------+           |
+             |                         | reuse old cache |--Usable-->|
+             |                         +-----------------+           |
+             |                                 |                     |
+             |                             Not usable                |
+             |                                 |                     |
+             |                                 v                     |
+        Cache empty                   +-----------------+            |
+             |                        | drain old cache |            |
+             |                        +-----------------+            |
+             |                                 |                     |
+             v_________________________________v                     |
+                              |                                      |
+                              |                                      |
+             _________________v_______________                       |
+            |                                 |              Cache is enough
+            |                                 |                      |
+ PAGE_SIZE < PAGE_FRAG_CACHE_MAX_SIZE         |                      |
+            |                                 |                      |
+            |               PAGE_SIZE >= PAGE_FRAG_CACHE_MAX_SIZE    |
+            v                                 |                      |
+    +----------------------------------+      |                      |
+    | refill cache with order > 0 page |      |                      |
+    +----------------------------------+      |                      |
+      |                    |                  |                      |
+      |                    |                  |                      |
+      |              Refill failed            |                      |
+      |                    |                  |                      |
+      |                    v                  v                      |
+      |      +------------------------------------+                  |
+      |      |   refill cache with order 0 page   |                  |
+      |      +----------------------------------=-+                  |
+      |                       |                                      |
+ Refill succeed               |                                      |
+      |                 Refill succeed                               |
+      |                       |                                      |
+      v                       v                                      v
+    +------------------------------------------------------------------+
+    |             allocate fragment from cache                         |
+    +------------------------------------------------------------------+
+
+API interface
+=============
+As the design and implementation of page_frag API implies, the allocation side
+does not allow concurrent calling. Instead it is assumed that the caller must
+ensure there is not concurrent alloc calling to the same page_frag_cache
+instance by using its own lock or rely on some lockless guarantee like NAPI
+softirq.
+
+Depending on different aligning requirement, the page_frag API caller may call
+page_frag_*_align*() to ensure the returned virtual address or offset of the
+page is aligned according to the 'align/alignment' parameter. Note the size of
+the allocated fragment is not aligned, the caller needs to provide an aligned
+fragsz if there is an alignment requirement for the size of the fragment.
+
+Depending on different use cases, callers expecting to deal with va, page or
+both va and page for them may call page_frag_alloc, page_frag_refill, or
+page_frag_alloc_refill API accordingly.
+
+There is also a use case that needs minimum memory in order for forward progress,
+but more performant if more memory is available. Using page_frag_*_prepare() and
+page_frag_commit*() related API, the caller requests the minimum memory it needs
+and the prepare API will return the maximum size of the fragment returned. The
+caller needs to either call the commit API to report how much memory it actually
+uses, or not do so if deciding to not use any memory.
+
+.. kernel-doc:: include/linux/page_frag_cache.h
+   :identifiers: page_frag_cache_init page_frag_cache_is_pfmemalloc
+		 page_frag_cache_page_offset __page_frag_alloc_align
+		 page_frag_alloc_align page_frag_alloc
+		 __page_frag_refill_align page_frag_refill_align
+		 page_frag_refill __page_frag_refill_prepare_align
+		 page_frag_refill_prepare_align page_frag_refill_prepare
+		 __page_frag_alloc_refill_prepare_align
+		 page_frag_alloc_refill_prepare_align
+		 page_frag_alloc_refill_prepare page_frag_alloc_refill_probe
+		 page_frag_refill_probe page_frag_commit
+		 page_frag_commit_noref page_frag_alloc_abort
+
+.. kernel-doc:: mm/page_frag_cache.c
+   :identifiers: page_frag_cache_drain page_frag_free
+		 __page_frag_alloc_refill_probe_align
+
+Coding examples
+===============
+
+Init & Drain API
+----------------
+
+.. code-block:: c
+
+   page_frag_cache_init(nc);
+   ...
+   page_frag_cache_drain(nc);
+
+
+Alloc & Free API
+----------------
+
+.. code-block:: c
+
+    void *va;
+
+    va = page_frag_alloc_align(nc, size, gfp, align);
+    if (!va)
+        goto do_error;
+
+    err = do_something(va, size);
+    if (err) {
+        page_frag_abort(nc, size);
+        goto do_error;
+    }
+
+    ...
+
+    page_frag_free(va);
+
+
+Prepare & Commit API
+--------------------
+
+.. code-block:: c
+
+    struct page_frag page_frag, *pfrag;
+    bool merge = true;
+    void *va;
+
+    pfrag = &page_frag;
+    va = page_frag_alloc_refill_prepare(nc, 32U, pfrag, GFP_KERNEL);
+    if (!va)
+        goto wait_for_space;
+
+    copy = min_t(unsigned int, copy, pfrag->size);
+    if (!skb_can_coalesce(skb, i, pfrag->page, pfrag->offset)) {
+        if (i >= max_skb_frags)
+            goto new_segment;
+
+        merge = false;
+    }
+
+    copy = mem_schedule(copy);
+    if (!copy)
+        goto wait_for_space;
+
+    err = copy_from_iter_full_nocache(va, copy, iter);
+    if (err)
+        goto do_error;
+
+    if (merge) {
+        skb_frag_size_add(&skb_shinfo(skb)->frags[i - 1], copy);
+        page_frag_commit_noref(nc, pfrag, copy);
+    } else {
+        skb_fill_page_desc(skb, i, pfrag->page, pfrag->offset, copy);
+        page_frag_commit(nc, pfrag, copy);
+    }
diff --git a/include/linux/page_frag_cache.h b/include/linux/page_frag_cache.h
index 4e9018051956..dff68d8e0f30 100644
--- a/include/linux/page_frag_cache.h
+++ b/include/linux/page_frag_cache.h
@@ -30,16 +30,43 @@ static inline bool page_frag_encoded_page_pfmemalloc(unsigned long encoded_page)
 	return !!(encoded_page & PAGE_FRAG_CACHE_PFMEMALLOC_BIT);
 }
 
+/**
+ * page_frag_cache_init() - Init page_frag cache.
+ * @nc: page_frag cache from which to init
+ *
+ * Inline helper to init the page_frag cache.
+ */
 static inline void page_frag_cache_init(struct page_frag_cache *nc)
 {
 	nc->encoded_page = 0;
 }
 
+/**
+ * page_frag_cache_is_pfmemalloc() - Check for pfmemalloc.
+ * @nc: page_frag cache from which to check
+ *
+ * Used to check if the current page in page_frag cache is pfmemalloc'ed.
+ * It has the same calling context expectation as the alloc API.
+ *
+ * Return:
+ * true if the current page in page_frag cache is pfmemalloc'ed, otherwise
+ * return false.
+ */
 static inline bool page_frag_cache_is_pfmemalloc(struct page_frag_cache *nc)
 {
 	return page_frag_encoded_page_pfmemalloc(nc->encoded_page);
 }
 
+/**
+ * page_frag_cache_page_offset() - Return the current page fragment's offset.
+ * @nc: page_frag cache from which to check
+ *
+ * The API is only used in net/sched/em_meta.c for historical reason, do not use
+ * it for new caller unless there is a strong reason.
+ *
+ * Return:
+ * the offset of the current page fragment in the page_frag cache.
+ */
 static inline unsigned int page_frag_cache_page_offset(const struct page_frag_cache *nc)
 {
 	return nc->offset;
@@ -68,6 +95,19 @@ static inline unsigned int __page_frag_cache_commit(struct page_frag_cache *nc,
 	return __page_frag_cache_commit_noref(nc, pfrag, used_sz);
 }
 
+/**
+ * __page_frag_alloc_align() - Alloc a page fragment with aligning
+ * requirement.
+ * @nc: page_frag cache from which to allocate
+ * @fragsz: the requested fragment size
+ * @gfp_mask: the allocation gfp to use when cache need to be refilled
+ * @align_mask: the requested aligning requirement for the 'va'
+ *
+ * Alloc a page fragment from page_frag cache with aligning requirement.
+ *
+ * Return:
+ * Virtual address of the page fragment, otherwise return NULL.
+ */
 static inline void *__page_frag_alloc_align(struct page_frag_cache *nc,
 					    unsigned int fragsz, gfp_t gfp_mask,
 					    unsigned int align_mask)
@@ -85,6 +125,19 @@ static inline void *__page_frag_alloc_align(struct page_frag_cache *nc,
 	return va;
 }
 
+/**
+ * page_frag_alloc_align() - Alloc a page fragment with aligning requirement.
+ * @nc: page_frag cache from which to allocate
+ * @fragsz: the requested fragment size
+ * @gfp_mask: the allocation gfp to use when cache needs to be refilled
+ * @align: the requested aligning requirement for the fragment
+ *
+ * WARN_ON_ONCE() checking for @align before allocing a page fragment from
+ * page_frag cache with aligning requirement.
+ *
+ * Return:
+ * virtual address of the page fragment, otherwise return NULL.
+ */
 static inline void *page_frag_alloc_align(struct page_frag_cache *nc,
 					  unsigned int fragsz, gfp_t gfp_mask,
 					  unsigned int align)
@@ -93,12 +146,36 @@ static inline void *page_frag_alloc_align(struct page_frag_cache *nc,
 	return __page_frag_alloc_align(nc, fragsz, gfp_mask, -align);
 }
 
+/**
+ * page_frag_alloc() - Alloc a page fragment.
+ * @nc: page_frag cache from which to allocate
+ * @fragsz: the requested fragment size
+ * @gfp_mask: the allocation gfp to use when cache need to be refilled
+ *
+ * Alloc a page fragment from page_frag cache.
+ *
+ * Return:
+ * virtual address of the page fragment, otherwise return NULL.
+ */
 static inline void *page_frag_alloc(struct page_frag_cache *nc,
 				    unsigned int fragsz, gfp_t gfp_mask)
 {
 	return __page_frag_alloc_align(nc, fragsz, gfp_mask, ~0u);
 }
 
+/**
+ * __page_frag_refill_align() - Refill a page_frag with aligning requirement.
+ * @nc: page_frag cache from which to refill
+ * @fragsz: the requested fragment size
+ * @pfrag: the page_frag to be refilled.
+ * @gfp_mask: the allocation gfp to use when cache need to be refilled
+ * @align_mask: the requested aligning requirement for the fragment
+ *
+ * Refill a page_frag from page_frag cache with aligning requirement.
+ *
+ * Return:
+ * True if refill succeeds, otherwise return false.
+ */
 static inline bool __page_frag_refill_align(struct page_frag_cache *nc,
 					    unsigned int fragsz,
 					    struct page_frag *pfrag,
@@ -113,6 +190,20 @@ static inline bool __page_frag_refill_align(struct page_frag_cache *nc,
 	return true;
 }
 
+/**
+ * page_frag_refill_align() - Refill a page_frag with aligning requirement.
+ * @nc: page_frag cache from which to refill
+ * @fragsz: the requested fragment size
+ * @pfrag: the page_frag to be refilled.
+ * @gfp_mask: the allocation gfp to use when cache needs to be refilled
+ * @align: the requested aligning requirement for the fragment
+ *
+ * WARN_ON_ONCE() checking for @align before refilling a page_frag from
+ * page_frag cache with aligning requirement.
+ *
+ * Return:
+ * True if refill succeeds, otherwise return false.
+ */
 static inline bool page_frag_refill_align(struct page_frag_cache *nc,
 					  unsigned int fragsz,
 					  struct page_frag *pfrag,
@@ -122,6 +213,18 @@ static inline bool page_frag_refill_align(struct page_frag_cache *nc,
 	return __page_frag_refill_align(nc, fragsz, pfrag, gfp_mask, -align);
 }
 
+/**
+ * page_frag_refill() - Refill a page_frag.
+ * @nc: page_frag cache from which to refill
+ * @fragsz: the requested fragment size
+ * @pfrag: the page_frag to be refilled.
+ * @gfp_mask: the allocation gfp to use when cache need to be refilled
+ *
+ * Refill a page_frag from page_frag cache.
+ *
+ * Return:
+ * True if refill succeeds, otherwise return false.
+ */
 static inline bool page_frag_refill(struct page_frag_cache *nc,
 				    unsigned int fragsz,
 				    struct page_frag *pfrag, gfp_t gfp_mask)
@@ -129,6 +232,20 @@ static inline bool page_frag_refill(struct page_frag_cache *nc,
 	return __page_frag_refill_align(nc, fragsz, pfrag, gfp_mask, ~0u);
 }
 
+/**
+ * __page_frag_refill_prepare_align() - Prepare refilling a page_frag with
+ * aligning requirement.
+ * @nc: page_frag cache from which to refill
+ * @fragsz: the requested fragment size
+ * @pfrag: the page_frag to be refilled.
+ * @gfp_mask: the allocation gfp to use when cache need to be refilled
+ * @align_mask: the requested aligning requirement for the fragment
+ *
+ * Prepare refill a page_frag from page_frag cache with aligning requirement.
+ *
+ * Return:
+ * True if prepare refilling succeeds, otherwise return false.
+ */
 static inline bool __page_frag_refill_prepare_align(struct page_frag_cache *nc,
 						    unsigned int fragsz,
 						    struct page_frag *pfrag,
@@ -139,6 +256,21 @@ static inline bool __page_frag_refill_prepare_align(struct page_frag_cache *nc,
 					   align_mask);
 }
 
+/**
+ * page_frag_refill_prepare_align() - Prepare refilling a page_frag with
+ * aligning requirement.
+ * @nc: page_frag cache from which to refill
+ * @fragsz: the requested fragment size
+ * @pfrag: the page_frag to be refilled.
+ * @gfp_mask: the allocation gfp to use when cache needs to be refilled
+ * @align: the requested aligning requirement for the fragment
+ *
+ * WARN_ON_ONCE() checking for @align before prepare refilling a page_frag from
+ * page_frag cache with aligning requirement.
+ *
+ * Return:
+ * True if prepare refilling succeeds, otherwise return false.
+ */
 static inline bool page_frag_refill_prepare_align(struct page_frag_cache *nc,
 						  unsigned int fragsz,
 						  struct page_frag *pfrag,
@@ -150,6 +282,18 @@ static inline bool page_frag_refill_prepare_align(struct page_frag_cache *nc,
 						-align);
 }
 
+/**
+ * page_frag_refill_prepare() - Prepare refilling a page_frag.
+ * @nc: page_frag cache from which to refill
+ * @fragsz: the requested fragment size
+ * @pfrag: the page_frag to be refilled.
+ * @gfp_mask: the allocation gfp to use when cache need to be refilled
+ *
+ * Prepare refilling a page_frag from page_frag cache.
+ *
+ * Return:
+ * True if refill succeeds, otherwise return false.
+ */
 static inline bool page_frag_refill_prepare(struct page_frag_cache *nc,
 					    unsigned int fragsz,
 					    struct page_frag *pfrag,
@@ -159,6 +303,20 @@ static inline bool page_frag_refill_prepare(struct page_frag_cache *nc,
 						~0u);
 }
 
+/**
+ * __page_frag_alloc_refill_prepare_align() - Prepare allocing a fragment and
+ * refilling a page_frag with aligning requirement.
+ * @nc: page_frag cache from which to allocate and refill
+ * @fragsz: the requested fragment size
+ * @pfrag: the page_frag to be refilled.
+ * @gfp_mask: the allocation gfp to use when cache need to be refilled
+ * @align_mask: the requested aligning requirement for the fragment.
+ *
+ * Prepare allocing a fragment and refilling a page_frag from page_frag cache.
+ *
+ * Return:
+ * virtual address of the page fragment, otherwise return NULL.
+ */
 static inline void *__page_frag_alloc_refill_prepare_align(struct page_frag_cache *nc,
 							   unsigned int fragsz,
 							   struct page_frag *pfrag,
@@ -168,6 +326,21 @@ static inline void *__page_frag_alloc_refill_prepare_align(struct page_frag_cach
 	return __page_frag_cache_prepare(nc, fragsz, pfrag, gfp_mask, align_mask);
 }
 
+/**
+ * page_frag_alloc_refill_prepare_align() - Prepare allocing a fragment and
+ * refilling a page_frag with aligning requirement.
+ * @nc: page_frag cache from which to allocate and refill
+ * @fragsz: the requested fragment size
+ * @pfrag: the page_frag to be refilled.
+ * @gfp_mask: the allocation gfp to use when cache need to be refilled
+ * @align: the requested aligning requirement for the fragment.
+ *
+ * WARN_ON_ONCE() checking for @align before prepare allocing a fragment and
+ * refilling a page_frag from page_frag cache.
+ *
+ * Return:
+ * virtual address of the page fragment, otherwise return NULL.
+ */
 static inline void *page_frag_alloc_refill_prepare_align(struct page_frag_cache *nc,
 							 unsigned int fragsz,
 							 struct page_frag *pfrag,
@@ -179,6 +352,19 @@ static inline void *page_frag_alloc_refill_prepare_align(struct page_frag_cache
 						      gfp_mask, -align);
 }
 
+/**
+ * page_frag_alloc_refill_prepare() - Prepare allocing a fragment and refilling
+ * a page_frag.
+ * @nc: page_frag cache from which to allocate and refill
+ * @fragsz: the requested fragment size
+ * @pfrag: the page_frag to be refilled.
+ * @gfp_mask: the allocation gfp to use when cache need to be refilled
+ *
+ * Prepare allocing a fragment and refilling a page_frag from page_frag cache.
+ *
+ * Return:
+ * virtual address of the page fragment, otherwise return NULL.
+ */
 static inline void *page_frag_alloc_refill_prepare(struct page_frag_cache *nc,
 						   unsigned int fragsz,
 						   struct page_frag *pfrag,
@@ -188,6 +374,18 @@ static inline void *page_frag_alloc_refill_prepare(struct page_frag_cache *nc,
 						      gfp_mask, ~0u);
 }
 
+/**
+ * page_frag_alloc_refill_probe() - Probe allocing a fragment and refilling
+ * a page_frag.
+ * @nc: page_frag cache from which to allocate and refill
+ * @fragsz: the requested fragment size
+ * @pfrag: the page_frag to be refilled
+ *
+ * Probe allocing a fragment and refilling a page_frag from page_frag cache.
+ *
+ * Return:
+ * virtual address of the page fragment, otherwise return NULL.
+ */
 static inline void *page_frag_alloc_refill_probe(struct page_frag_cache *nc,
 						 unsigned int fragsz,
 						 struct page_frag *pfrag)
@@ -195,6 +393,17 @@ static inline void *page_frag_alloc_refill_probe(struct page_frag_cache *nc,
 	return __page_frag_alloc_refill_probe_align(nc, fragsz, pfrag, ~0u);
 }
 
+/**
+ * page_frag_refill_probe() - Probe refilling a page_frag.
+ * @nc: page_frag cache from which to refill
+ * @fragsz: the requested fragment size
+ * @pfrag: the page_frag to be refilled
+ *
+ * Probe refilling a page_frag from page_frag cache.
+ *
+ * Return:
+ * True if refill succeeds, otherwise return false.
+ */
 static inline bool page_frag_refill_probe(struct page_frag_cache *nc,
 					  unsigned int fragsz,
 					  struct page_frag *pfrag)
@@ -202,20 +411,54 @@ static inline bool page_frag_refill_probe(struct page_frag_cache *nc,
 	return !!page_frag_alloc_refill_probe(nc, fragsz, pfrag);
 }
 
-static inline void page_frag_commit(struct page_frag_cache *nc,
-				    struct page_frag *pfrag,
-				    unsigned int used_sz)
+/**
+ * page_frag_commit - Commit allocing a page fragment.
+ * @nc: page_frag cache from which to commit
+ * @pfrag: the page_frag to be committed
+ * @used_sz: size of the page fragment has been used
+ *
+ * Commit the actual used size for the allocation that was either prepared
+ * or probed.
+ *
+ * Return:
+ * The true size of the fragment considering the offset alignment.
+ */
+static inline unsigned int page_frag_commit(struct page_frag_cache *nc,
+					    struct page_frag *pfrag,
+					    unsigned int used_sz)
 {
-	__page_frag_cache_commit(nc, pfrag, used_sz);
+	return __page_frag_cache_commit(nc, pfrag, used_sz);
 }
 
-static inline void page_frag_commit_noref(struct page_frag_cache *nc,
-					  struct page_frag *pfrag,
-					  unsigned int used_sz)
+/**
+ * page_frag_commit_noref - Commit allocing a page fragment without taking
+ * page refcount.
+ * @nc: page_frag cache from which to commit
+ * @pfrag: the page_frag to be committed
+ * @used_sz: size of the page fragment has been used
+ *
+ * Commit the alloc preparing or probing by passing the actual used size, but
+ * not taking refcount. Mostly used for fragmemt coalescing case when the
+ * current fragment can share the same refcount with previous fragment.
+ *
+ * Return:
+ * The true size of the fragment considering the offset alignment.
+ */
+static inline unsigned int page_frag_commit_noref(struct page_frag_cache *nc,
+						  struct page_frag *pfrag,
+						  unsigned int used_sz)
 {
-	__page_frag_cache_commit_noref(nc, pfrag, used_sz);
+	return __page_frag_cache_commit_noref(nc, pfrag, used_sz);
 }
 
+/**
+ * page_frag_alloc_abort - Abort the page fragment allocation.
+ * @nc: page_frag cache to which the page fragment is aborted back
+ * @fragsz: size of the page fragment to be aborted
+ *
+ * It is expected to be called from the same context as the alloc API.
+ * Mostly used for error handling cases where the fragment is no longer needed.
+ */
 static inline void page_frag_alloc_abort(struct page_frag_cache *nc,
 					 unsigned int fragsz)
 {
diff --git a/mm/page_frag_cache.c b/mm/page_frag_cache.c
index c052c77a96eb..209cc1e278ab 100644
--- a/mm/page_frag_cache.c
+++ b/mm/page_frag_cache.c
@@ -75,6 +75,10 @@ static struct page *__page_frag_cache_refill(struct page_frag_cache *nc,
 	return page;
 }
 
+/**
+ * page_frag_cache_drain - Drain the current page from page_frag cache.
+ * @nc: page_frag cache from which to drain
+ */
 void page_frag_cache_drain(struct page_frag_cache *nc)
 {
 	if (!nc->encoded_page)
@@ -117,6 +121,20 @@ unsigned int __page_frag_cache_commit_noref(struct page_frag_cache *nc,
 }
 EXPORT_SYMBOL(__page_frag_cache_commit_noref);
 
+/**
+ * __page_frag_alloc_refill_probe_align() - Probe allocing a fragment and
+ * refilling a page_frag with aligning requirement.
+ * @nc: page_frag cache from which to allocate and refill
+ * @fragsz: the requested fragment size
+ * @pfrag: the page_frag to be refilled.
+ * @align_mask: the requested aligning requirement for the fragment.
+ *
+ * Probe allocing a fragment and refilling a page_frag from page_frag cache with
+ * aligning requirement.
+ *
+ * Return:
+ * virtual address of the page fragment, otherwise return NULL.
+ */
 void *__page_frag_alloc_refill_probe_align(struct page_frag_cache *nc,
 					   unsigned int fragsz,
 					   struct page_frag *pfrag,
@@ -208,8 +226,12 @@ void *__page_frag_cache_prepare(struct page_frag_cache *nc, unsigned int fragsz,
 }
 EXPORT_SYMBOL(__page_frag_cache_prepare);
 
-/*
- * Frees a page fragment allocated out of either a compound or order 0 page.
+/**
+ * page_frag_free - Free a page fragment.
+ * @addr: va of page fragment to be freed
+ *
+ * Free a page fragment allocated out of either a compound or order 0 page by
+ * virtual address.
  */
 void page_frag_free(void *addr)
 {
-- 
2.34.1