diff mbox

[03/12] vrange: Add new vrange(2) system call

Message ID 1367605636-18284-4-git-send-email-john.stultz@linaro.org
State Superseded
Headers show

Commit Message

John Stultz May 3, 2013, 6:27 p.m. UTC 
From: Minchan Kim <minchan@kernel.org>

This patch adds new system call sys_vrange.

NAME
	vrange - Mark or unmark range of memory as volatile

SYNOPSIS
	int vrange(unsigned_long start, size_t length, int mode,
			 int behavior, int *purged);

DESCRIPTION
	Applications can use vrange(2) to advise the kernel how it should
	handle paging I/O in this VM area.  The idea is to help the kernel
	discard pages of vrange instead of reclaiming when memory pressure
	happens. It means kernel doesn't discard any pages of vrange if
	there is no memory pressure.

	mode:
	VRANGE_VOLATILE
		hint to kernel so VM can discard in vrange pages when
		memory pressure happens.
	VRANGE_NONVOLATILE
		hint to kernel so VM doesn't discard vrange pages
		any more.

	behavior:
	VRANGE_MODE_SHARED
		Normally the volatility is private to the process
		doing the marking. In other words, pages will only
		be purged if *all* processes that have that page
		mapped considers it as volatile.
		With the MODE_SHARED bit flag set, the file pages can
		be purged if any process has marked it volatile. This
		is very similar to MAP_SHARED semantics of mmap,
		where modifications by one process to a mmapped file
		will be seen by other processes.
		(NOTE: This functionality is not present in this patch,
		but is introduced with a following patch)

	If user try to access purged memory without VRANGE_NOVOLATILE call,
	he can encounter SIGBUS if the page was discarded by kernel.

	purged: Pointer to an integer which will return 1 if
	mode == VRANGE_NONVOLATILE and any page in the affected range
	was purged. If purged returns zero during a mode ==
	VRANGE_NONVOLATILE call, it means all of the pages in the range
	are intact.

RETURN VALUE
	On success vrange returns the number of bytes marked or unmarked.
	Similar to write(), it may return fewer bytes then specified
	if it ran into a problem.

	If an error is returned, no changes were made.

ERRORS
	EINVAL This error can occur for the following reasons:
		* The value length is negative.
		* addr is not page-aligned
		* mode or behavior are not a valid value.

	ENOMEM Not enough memory

	ENOTSUPP Behavior is not yet supported

Signed-off-by: Minchan Kim <minchan@kernel.org>
[jstultz: Major rework of interface and commit message]
Signed-off-by: John Stultz <john.stultz@linaro.org>
---
 arch/x86/syscalls/syscall_64.tbl       |  1 +
 include/linux/mm_types.h               |  5 +++
 include/uapi/asm-generic/mman-common.h |  3 ++
 kernel/fork.c                          |  3 ++
 mm/vrange.c                            | 75 ++++++++++++++++++++++++++++++++++
 5 files changed, 87 insertions(+)
diff mbox

Patch

diff --git a/arch/x86/syscalls/syscall_64.tbl b/arch/x86/syscalls/syscall_64.tbl
index 38ae65d..dc332bd 100644
--- a/arch/x86/syscalls/syscall_64.tbl
+++ b/arch/x86/syscalls/syscall_64.tbl
@@ -320,6 +320,7 @@ 
 311	64	process_vm_writev	sys_process_vm_writev
 312	common	kcmp			sys_kcmp
 313	common	finit_module		sys_finit_module
+314	common	vrange			sys_vrange
 
 #
 # x32-specific system call numbers start at 512 to avoid cache impact
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index ace9a5f..2e02a6d 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -13,6 +13,8 @@ 
 #include <linux/page-debug-flags.h>
 #include <linux/uprobes.h>
 #include <linux/page-flags-layout.h>
+#include <linux/mutex.h>
+#include <linux/vrange_types.h>
 #include <asm/page.h>
 #include <asm/mmu.h>
 
@@ -351,6 +353,9 @@  struct mm_struct {
 						 */
 
 
+#ifdef CONFIG_MMU
+	struct vrange_root vroot;
+#endif
 	unsigned long hiwater_rss;	/* High-watermark of RSS usage */
 	unsigned long hiwater_vm;	/* High-water virtual memory usage */
 
diff --git a/include/uapi/asm-generic/mman-common.h b/include/uapi/asm-generic/mman-common.h
index 4164529..9be120b 100644
--- a/include/uapi/asm-generic/mman-common.h
+++ b/include/uapi/asm-generic/mman-common.h
@@ -66,4 +66,7 @@ 
 #define MAP_HUGE_SHIFT	26
 #define MAP_HUGE_MASK	0x3f
 
+#define VRANGE_VOLATILE		0	/* unpin pages so VM can discard them */
+#define VRANGE_NONVOLATILE	1	/* pin pages so VM can't discard them */
+
 #endif /* __ASM_GENERIC_MMAN_COMMON_H */
diff --git a/kernel/fork.c b/kernel/fork.c
index 1766d32..360ad65 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -70,6 +70,7 @@ 
 #include <linux/khugepaged.h>
 #include <linux/signalfd.h>
 #include <linux/uprobes.h>
+#include <linux/vrange.h>
 
 #include <asm/pgtable.h>
 #include <asm/pgalloc.h>
@@ -541,6 +542,7 @@  static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p)
 	spin_lock_init(&mm->page_table_lock);
 	mm->free_area_cache = TASK_UNMAPPED_BASE;
 	mm->cached_hole_size = ~0UL;
+	vrange_root_init(&mm->vroot, VRANGE_MM);
 	mm_init_aio(mm);
 	mm_init_owner(mm, p);
 
@@ -612,6 +614,7 @@  void mmput(struct mm_struct *mm)
 
 	if (atomic_dec_and_test(&mm->mm_users)) {
 		uprobe_clear_state(mm);
+		vrange_root_cleanup(&mm->vroot);
 		exit_aio(mm);
 		ksm_exit(mm);
 		khugepaged_exit(mm); /* must run before exit_mmap */
diff --git a/mm/vrange.c b/mm/vrange.c
index 565bca34..537e3d5 100644
--- a/mm/vrange.c
+++ b/mm/vrange.c
@@ -4,6 +4,8 @@ 
 
 #include <linux/vrange.h>
 #include <linux/slab.h>
+#include <linux/syscalls.h>
+#include <linux/mman.h>
 
 static struct kmem_cache *vrange_cachep;
 
@@ -163,3 +165,76 @@  void vrange_root_cleanup(struct vrange_root *vroot)
 	vrange_unlock(vroot);
 }
 
+static int vrange_private(struct mm_struct *mm,
+			unsigned long start, unsigned long end,
+			int mode, int *purged)
+{
+	int ret = -EINVAL;
+
+	if (mode == VRANGE_VOLATILE)
+		ret = vrange_add(&mm->vroot, start, end-1);
+	else if (mode == VRANGE_NONVOLATILE)
+		ret = vrange_remove(&mm->vroot, start, end-1, purged);
+
+	if (ret < 0)
+		return ret;
+	return end-start;
+}
+
+/*
+ * The vrange(2) system call.
+ *
+ * Applications can use vrange() to advise the kernel how it should
+ * handle paging I/O in this VM area.  The idea is to help the kernel
+ * discard pages of vrange instead of swapping out when memory pressure
+ * happens. The information provided is advisory only, and can be safely
+ * disregarded by the kernel if system has enough free memory.
+ *
+ * mode values:
+ *  VRANGE_VOLATILE - hint to kernel so VM can discard vrange pages when
+ *		memory pressure happens.
+ *  VRANGE_NONVOLATILE - Removes any volatile hints previous specified in that
+ *		range.
+ *
+ * behavior values (bitflags): None yet supported.
+ *
+ * purged ptr:
+ *  Returns 1 if any page in the range being marked nonvolatile has been purged.
+ *
+ * return values:
+ *  non-negative - Number of bytes marked or unmarked.
+ *  -EINVAL - start  len < 0, start is not page-aligned, start is greater
+ *		than TASK_SIZE or "mode" is not a valid value.
+ *  -ENOMEM -  Short of free memory in system for successful system call.
+ *  -ENOSUP -  Feature not yet supported.
+ */
+SYSCALL_DEFINE5(vrange, unsigned long, start,
+		size_t, len, int, mode, int, behavior, int*, purged)
+{
+	unsigned long end;
+	struct mm_struct *mm = current->mm;
+	int ret = -EINVAL;
+
+	/* We don't yet support any behavior modes */
+	if (behavior)
+		return -ENOTSUPP;
+
+	if (start & ~PAGE_MASK)
+		goto out;
+
+	len &= PAGE_MASK;
+	if (!len)
+		goto out;
+
+	end = start + len;
+	if (end < start)
+		goto out;
+
+	if (start >= TASK_SIZE)
+		goto out;
+
+	ret = vrange_private(mm, start, end, mode, purged);
+
+out:
+	return ret;
+}