LKML Archive on lore.kernel.org
 help / color / Atom feed
From: Minchan Kim <minchan@kernel.org>
To: Andrew Morton <akpm@linux-foundation.org>
Cc: linux-mm <linux-mm@kvack.org>,
	LKML <linux-kernel@vger.kernel.org>,
	linux-api@vger.kernel.org, Michal Hocko <mhocko@suse.com>,
	Johannes Weiner <hannes@cmpxchg.org>,
	Tim Murray <timmurray@google.com>,
	Joel Fernandes <joel@joelfernandes.org>,
	Suren Baghdasaryan <surenb@google.com>,
	Daniel Colascione <dancol@google.com>,
	Shakeel Butt <shakeelb@google.com>,
	Sonny Rao <sonnyrao@google.com>,
	Brian Geffon <bgeffon@google.com>,
	jannh@google.com, oleg@redhat.com, christian@brauner.io,
	oleksandr@redhat.com, hdanton@sina.com,
	Minchan Kim <minchan@kernel.org>
Subject: [RFCv2 4/6] mm: factor out madvise's core functionality
Date: Fri, 31 May 2019 15:43:11 +0900
Message-ID: <20190531064313.193437-5-minchan@kernel.org> (raw)
In-Reply-To: <20190531064313.193437-1-minchan@kernel.org>

This patch factor out madvise's core functionality so that upcoming
patch can reuse it without duplication. It shouldn't change any behavior.

Signed-off-by: Minchan Kim <minchan@kernel.org>
---
 mm/madvise.c | 188 +++++++++++++++++++++++++++------------------------
 1 file changed, 101 insertions(+), 87 deletions(-)

diff --git a/mm/madvise.c b/mm/madvise.c
index 9d749a1420b4..466623ea8c36 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -425,9 +425,10 @@ static int madvise_pageout_pte_range(pmd_t *pmd, unsigned long addr,
 	struct page *page;
 	int isolated = 0;
 	struct vm_area_struct *vma = walk->vma;
+	struct task_struct *task = walk->private;
 	unsigned long next;
 
-	if (fatal_signal_pending(current))
+	if (fatal_signal_pending(task))
 		return -EINTR;
 
 	next = pmd_addr_end(addr, end);
@@ -505,12 +506,14 @@ static int madvise_pageout_pte_range(pmd_t *pmd, unsigned long addr,
 }
 
 static void madvise_pageout_page_range(struct mmu_gather *tlb,
-			     struct vm_area_struct *vma,
-			     unsigned long addr, unsigned long end)
+				struct task_struct *task,
+				struct vm_area_struct *vma,
+				unsigned long addr, unsigned long end)
 {
 	struct mm_walk warm_walk = {
 		.pmd_entry = madvise_pageout_pte_range,
 		.mm = vma->vm_mm,
+		.private = task,
 	};
 
 	tlb_start_vma(tlb, vma);
@@ -519,9 +522,9 @@ static void madvise_pageout_page_range(struct mmu_gather *tlb,
 }
 
 
-static long madvise_pageout(struct vm_area_struct *vma,
-			struct vm_area_struct **prev,
-			unsigned long start_addr, unsigned long end_addr)
+static long madvise_pageout(struct task_struct *task,
+		struct vm_area_struct *vma, struct vm_area_struct **prev,
+		unsigned long start_addr, unsigned long end_addr)
 {
 	struct mm_struct *mm = vma->vm_mm;
 	struct mmu_gather tlb;
@@ -532,7 +535,7 @@ static long madvise_pageout(struct vm_area_struct *vma,
 
 	lru_add_drain();
 	tlb_gather_mmu(&tlb, mm, start_addr, end_addr);
-	madvise_pageout_page_range(&tlb, vma, start_addr, end_addr);
+	madvise_pageout_page_range(&tlb, task, vma, start_addr, end_addr);
 	tlb_finish_mmu(&tlb, start_addr, end_addr);
 
 	return 0;
@@ -744,7 +747,8 @@ static long madvise_dontneed_single_vma(struct vm_area_struct *vma,
 	return 0;
 }
 
-static long madvise_dontneed_free(struct vm_area_struct *vma,
+static long madvise_dontneed_free(struct mm_struct *mm,
+				  struct vm_area_struct *vma,
 				  struct vm_area_struct **prev,
 				  unsigned long start, unsigned long end,
 				  int behavior)
@@ -756,8 +760,8 @@ static long madvise_dontneed_free(struct vm_area_struct *vma,
 	if (!userfaultfd_remove(vma, start, end)) {
 		*prev = NULL; /* mmap_sem has been dropped, prev is stale */
 
-		down_read(&current->mm->mmap_sem);
-		vma = find_vma(current->mm, start);
+		down_read(&mm->mmap_sem);
+		vma = find_vma(mm, start);
 		if (!vma)
 			return -ENOMEM;
 		if (start < vma->vm_start) {
@@ -804,7 +808,8 @@ static long madvise_dontneed_free(struct vm_area_struct *vma,
  * Application wants to free up the pages and associated backing store.
  * This is effectively punching a hole into the middle of a file.
  */
-static long madvise_remove(struct vm_area_struct *vma,
+static long madvise_remove(struct mm_struct *mm,
+				struct vm_area_struct *vma,
 				struct vm_area_struct **prev,
 				unsigned long start, unsigned long end)
 {
@@ -838,13 +843,13 @@ static long madvise_remove(struct vm_area_struct *vma,
 	get_file(f);
 	if (userfaultfd_remove(vma, start, end)) {
 		/* mmap_sem was not released by userfaultfd_remove() */
-		up_read(&current->mm->mmap_sem);
+		up_read(&mm->mmap_sem);
 	}
 	error = vfs_fallocate(f,
 				FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE,
 				offset, end - start);
 	fput(f);
-	down_read(&current->mm->mmap_sem);
+	down_read(&mm->mmap_sem);
 	return error;
 }
 
@@ -918,21 +923,23 @@ static int madvise_inject_error(int behavior,
 #endif
 
 static long
-madvise_vma(struct vm_area_struct *vma, struct vm_area_struct **prev,
+madvise_vma(struct task_struct *task, struct mm_struct *mm,
+		struct vm_area_struct *vma, struct vm_area_struct **prev,
 		unsigned long start, unsigned long end, int behavior)
 {
 	switch (behavior) {
 	case MADV_REMOVE:
-		return madvise_remove(vma, prev, start, end);
+		return madvise_remove(mm, vma, prev, start, end);
 	case MADV_WILLNEED:
 		return madvise_willneed(vma, prev, start, end);
 	case MADV_COLD:
 		return madvise_cold(vma, prev, start, end);
 	case MADV_PAGEOUT:
-		return madvise_pageout(vma, prev, start, end);
+		return madvise_pageout(task, vma, prev, start, end);
 	case MADV_FREE:
 	case MADV_DONTNEED:
-		return madvise_dontneed_free(vma, prev, start, end, behavior);
+		return madvise_dontneed_free(mm, vma, prev, start,
+						end, behavior);
 	default:
 		return madvise_behavior(vma, prev, start, end, behavior);
 	}
@@ -976,68 +983,8 @@ madvise_behavior_valid(int behavior)
 	}
 }
 
-/*
- * The madvise(2) system call.
- *
- * Applications can use madvise() to advise the kernel how it should
- * handle paging I/O in this VM area.  The idea is to help the kernel
- * use appropriate read-ahead and caching techniques.  The information
- * provided is advisory only, and can be safely disregarded by the
- * kernel without affecting the correct operation of the application.
- *
- * behavior values:
- *  MADV_NORMAL - the default behavior is to read clusters.  This
- *		results in some read-ahead and read-behind.
- *  MADV_RANDOM - the system should read the minimum amount of data
- *		on any access, since it is unlikely that the appli-
- *		cation will need more than what it asks for.
- *  MADV_SEQUENTIAL - pages in the given range will probably be accessed
- *		once, so they can be aggressively read ahead, and
- *		can be freed soon after they are accessed.
- *  MADV_WILLNEED - the application is notifying the system to read
- *		some pages ahead.
- *  MADV_DONTNEED - the application is finished with the given range,
- *		so the kernel can free resources associated with it.
- *  MADV_FREE - the application marks pages in the given range as lazy free,
- *		where actual purges are postponed until memory pressure happens.
- *  MADV_REMOVE - the application wants to free up the given range of
- *		pages and associated backing store.
- *  MADV_DONTFORK - omit this area from child's address space when forking:
- *		typically, to avoid COWing pages pinned by get_user_pages().
- *  MADV_DOFORK - cancel MADV_DONTFORK: no longer omit this area when forking.
- *  MADV_WIPEONFORK - present the child process with zero-filled memory in this
- *              range after a fork.
- *  MADV_KEEPONFORK - undo the effect of MADV_WIPEONFORK
- *  MADV_HWPOISON - trigger memory error handler as if the given memory range
- *		were corrupted by unrecoverable hardware memory failure.
- *  MADV_SOFT_OFFLINE - try to soft-offline the given range of memory.
- *  MADV_MERGEABLE - the application recommends that KSM try to merge pages in
- *		this area with pages of identical content from other such areas.
- *  MADV_UNMERGEABLE- cancel MADV_MERGEABLE: no longer merge pages with others.
- *  MADV_HUGEPAGE - the application wants to back the given range by transparent
- *		huge pages in the future. Existing pages might be coalesced and
- *		new pages might be allocated as THP.
- *  MADV_NOHUGEPAGE - mark the given range as not worth being backed by
- *		transparent huge pages so the existing pages will not be
- *		coalesced into THP and new pages will not be allocated as THP.
- *  MADV_DONTDUMP - the application wants to prevent pages in the given range
- *		from being included in its core dump.
- *  MADV_DODUMP - cancel MADV_DONTDUMP: no longer exclude from core dump.
- *
- * return values:
- *  zero    - success
- *  -EINVAL - start + len < 0, start is not page-aligned,
- *		"behavior" is not a valid value, or application
- *		is attempting to release locked or shared pages,
- *		or the specified address range includes file, Huge TLB,
- *		MAP_SHARED or VMPFNMAP range.
- *  -ENOMEM - addresses in the specified range are not currently
- *		mapped, or are outside the AS of the process.
- *  -EIO    - an I/O error occurred while paging in data.
- *  -EBADF  - map exists, but area maps something that isn't a file.
- *  -EAGAIN - a kernel resource was temporarily unavailable.
- */
-SYSCALL_DEFINE3(madvise, unsigned long, start, size_t, len_in, int, behavior)
+static int madvise_core(struct task_struct *task, struct mm_struct *mm,
+			unsigned long start, size_t len_in, int behavior)
 {
 	unsigned long end, tmp;
 	struct vm_area_struct *vma, *prev;
@@ -1068,15 +1015,16 @@ SYSCALL_DEFINE3(madvise, unsigned long, start, size_t, len_in, int, behavior)
 
 #ifdef CONFIG_MEMORY_FAILURE
 	if (behavior == MADV_HWPOISON || behavior == MADV_SOFT_OFFLINE)
-		return madvise_inject_error(behavior, start, start + len_in);
+		return madvise_inject_error(behavior,
+					start, start + len_in);
 #endif
 
 	write = madvise_need_mmap_write(behavior);
 	if (write) {
-		if (down_write_killable(&current->mm->mmap_sem))
+		if (down_write_killable(&mm->mmap_sem))
 			return -EINTR;
 	} else {
-		down_read(&current->mm->mmap_sem);
+		down_read(&mm->mmap_sem);
 	}
 
 	/*
@@ -1084,7 +1032,7 @@ SYSCALL_DEFINE3(madvise, unsigned long, start, size_t, len_in, int, behavior)
 	 * ranges, just ignore them, but return -ENOMEM at the end.
 	 * - different from the way of handling in mlock etc.
 	 */
-	vma = find_vma_prev(current->mm, start, &prev);
+	vma = find_vma_prev(mm, start, &prev);
 	if (vma && start > vma->vm_start)
 		prev = vma;
 
@@ -1109,7 +1057,7 @@ SYSCALL_DEFINE3(madvise, unsigned long, start, size_t, len_in, int, behavior)
 			tmp = end;
 
 		/* Here vma->vm_start <= start < tmp <= (end|vma->vm_end). */
-		error = madvise_vma(vma, &prev, start, tmp, behavior);
+		error = madvise_vma(task, mm, vma, &prev, start, tmp, behavior);
 		if (error)
 			goto out;
 		start = tmp;
@@ -1121,14 +1069,80 @@ SYSCALL_DEFINE3(madvise, unsigned long, start, size_t, len_in, int, behavior)
 		if (prev)
 			vma = prev->vm_next;
 		else	/* madvise_remove dropped mmap_sem */
-			vma = find_vma(current->mm, start);
+			vma = find_vma(mm, start);
 	}
 out:
 	blk_finish_plug(&plug);
 	if (write)
-		up_write(&current->mm->mmap_sem);
+		up_write(&mm->mmap_sem);
 	else
-		up_read(&current->mm->mmap_sem);
+		up_read(&mm->mmap_sem);
 
 	return error;
 }
+
+/*
+ * The madvise(2) system call.
+ *
+ * Applications can use madvise() to advise the kernel how it should
+ * handle paging I/O in this VM area.  The idea is to help the kernel
+ * use appropriate read-ahead and caching techniques.  The information
+ * provided is advisory only, and can be safely disregarded by the
+ * kernel without affecting the correct operation of the application.
+ *
+ * behavior values:
+ *  MADV_NORMAL - the default behavior is to read clusters.  This
+ *		results in some read-ahead and read-behind.
+ *  MADV_RANDOM - the system should read the minimum amount of data
+ *		on any access, since it is unlikely that the appli-
+ *		cation will need more than what it asks for.
+ *  MADV_SEQUENTIAL - pages in the given range will probably be accessed
+ *		once, so they can be aggressively read ahead, and
+ *		can be freed soon after they are accessed.
+ *  MADV_WILLNEED - the application is notifying the system to read
+ *		some pages ahead.
+ *  MADV_DONTNEED - the application is finished with the given range,
+ *		so the kernel can free resources associated with it.
+ *  MADV_FREE - the application marks pages in the given range as lazy free,
+ *		where actual purges are postponed until memory pressure happens.
+ *  MADV_REMOVE - the application wants to free up the given range of
+ *		pages and associated backing store.
+ *  MADV_DONTFORK - omit this area from child's address space when forking:
+ *		typically, to avoid COWing pages pinned by get_user_pages().
+ *  MADV_DOFORK - cancel MADV_DONTFORK: no longer omit this area when forking.
+ *  MADV_WIPEONFORK - present the child process with zero-filled memory in this
+ *              range after a fork.
+ *  MADV_KEEPONFORK - undo the effect of MADV_WIPEONFORK
+ *  MADV_HWPOISON - trigger memory error handler as if the given memory range
+ *		were corrupted by unrecoverable hardware memory failure.
+ *  MADV_SOFT_OFFLINE - try to soft-offline the given range of memory.
+ *  MADV_MERGEABLE - the application recommends that KSM try to merge pages in
+ *		this area with pages of identical content from other such areas.
+ *  MADV_UNMERGEABLE- cancel MADV_MERGEABLE: no longer merge pages with others.
+ *  MADV_HUGEPAGE - the application wants to back the given range by transparent
+ *		huge pages in the future. Existing pages might be coalesced and
+ *		new pages might be allocated as THP.
+ *  MADV_NOHUGEPAGE - mark the given range as not worth being backed by
+ *		transparent huge pages so the existing pages will not be
+ *		coalesced into THP and new pages will not be allocated as THP.
+ *  MADV_DONTDUMP - the application wants to prevent pages in the given range
+ *		from being included in its core dump.
+ *  MADV_DODUMP - cancel MADV_DONTDUMP: no longer exclude from core dump.
+ *
+ * return values:
+ *  zero    - success
+ *  -EINVAL - start + len < 0, start is not page-aligned,
+ *		"behavior" is not a valid value, or application
+ *		is attempting to release locked or shared pages,
+ *		or the specified address range includes file, Huge TLB,
+ *		MAP_SHARED or VMPFNMAP range.
+ *  -ENOMEM - addresses in the specified range are not currently
+ *		mapped, or are outside the AS of the process.
+ *  -EIO    - an I/O error occurred while paging in data.
+ *  -EBADF  - map exists, but area maps something that isn't a file.
+ *  -EAGAIN - a kernel resource was temporarily unavailable.
+ */
+SYSCALL_DEFINE3(madvise, unsigned long, start, size_t, len_in, int, behavior)
+{
+	return madvise_core(current, current->mm, start, len_in, behavior);
+}
-- 
2.22.0.rc1.257.g3120a18244-goog


  parent reply index

Thread overview: 39+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-05-31  6:43 [RFCv2 0/6] introduce memory hinting API for external process Minchan Kim
2019-05-31  6:43 ` [RFCv2 1/6] mm: introduce MADV_COLD Minchan Kim
2019-05-31  8:47   ` Michal Hocko
2019-05-31 13:39     ` Minchan Kim
2019-05-31 14:03       ` Michal Hocko
2019-05-31 14:34         ` Minchan Kim
2019-06-03  7:16           ` Michal Hocko
2019-06-03 15:43             ` Daniel Colascione
2019-06-03 17:27             ` Johannes Weiner
2019-06-03 20:32               ` Michal Hocko
2019-06-03 21:50                 ` Johannes Weiner
2019-06-03 23:02                   ` Minchan Kim
2019-06-04  6:56                     ` Michal Hocko
2019-06-04 12:06                     ` Johannes Weiner
2019-06-04  6:55                   ` Michal Hocko
2019-06-04  4:26             ` Minchan Kim
2019-06-04  7:02               ` Michal Hocko
2019-05-31  6:43 ` [RFCv2 2/6] mm: change PAGEREF_RECLAIM_CLEAN with PAGE_REFRECLAIM Minchan Kim
2019-05-31  6:43 ` [RFCv2 3/6] mm: introduce MADV_PAGEOUT Minchan Kim
2019-05-31  8:50   ` Michal Hocko
2019-05-31 13:44     ` Minchan Kim
2019-05-31 16:59   ` Johannes Weiner
2019-05-31 23:14     ` Minchan Kim
2019-05-31  6:43 ` Minchan Kim [this message]
2019-05-31  7:04   ` [RFCv2 4/6] mm: factor out madvise's core functionality Oleksandr Natalenko
2019-05-31 13:12     ` Minchan Kim
2019-05-31 14:35       ` Oleksandr Natalenko
2019-05-31 23:29         ` Minchan Kim
2019-06-05 13:27           ` Oleksandr Natalenko
2019-06-10 10:12             ` Minchan Kim
2019-05-31  6:43 ` [RFCv2 5/6] mm: introduce external memory hinting API Minchan Kim
2019-05-31  8:37   ` Michal Hocko
2019-05-31 13:19     ` Minchan Kim
2019-05-31 14:00       ` Michal Hocko
2019-05-31 14:11         ` Minchan Kim
2019-05-31 17:35   ` Daniel Colascione
2019-05-31  6:43 ` [RFCv2 6/6] mm: extend process_madvise syscall to support vector arrary Minchan Kim
2019-05-31 10:06   ` Yann Droneaud
2019-05-31 23:18     ` Minchan Kim

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20190531064313.193437-5-minchan@kernel.org \
    --to=minchan@kernel.org \
    --cc=akpm@linux-foundation.org \
    --cc=bgeffon@google.com \
    --cc=christian@brauner.io \
    --cc=dancol@google.com \
    --cc=hannes@cmpxchg.org \
    --cc=hdanton@sina.com \
    --cc=jannh@google.com \
    --cc=joel@joelfernandes.org \
    --cc=linux-api@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=mhocko@suse.com \
    --cc=oleg@redhat.com \
    --cc=oleksandr@redhat.com \
    --cc=shakeelb@google.com \
    --cc=sonnyrao@google.com \
    --cc=surenb@google.com \
    --cc=timmurray@google.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

LKML Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/lkml/0 lkml/git/0.git
	git clone --mirror https://lore.kernel.org/lkml/1 lkml/git/1.git
	git clone --mirror https://lore.kernel.org/lkml/2 lkml/git/2.git
	git clone --mirror https://lore.kernel.org/lkml/3 lkml/git/3.git
	git clone --mirror https://lore.kernel.org/lkml/4 lkml/git/4.git
	git clone --mirror https://lore.kernel.org/lkml/5 lkml/git/5.git
	git clone --mirror https://lore.kernel.org/lkml/6 lkml/git/6.git
	git clone --mirror https://lore.kernel.org/lkml/7 lkml/git/7.git
	git clone --mirror https://lore.kernel.org/lkml/8 lkml/git/8.git
	git clone --mirror https://lore.kernel.org/lkml/9 lkml/git/9.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 lkml lkml/ https://lore.kernel.org/lkml \
		linux-kernel@vger.kernel.org
	public-inbox-index lkml

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.linux-kernel


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git