maps4: pagemap monitoring v4

PATCH In review Matt Mackall 2 participants 15 messages Oct 26, 2007

Subsystems (7)

Memory management MM core Scheduler Proc filesystem +3 more subsystems

lore

Share & tools

lore

Matt Mackall

author

2007-10-26 16:36 UTC #1 lore raw

PATCH 1/12 maps4: add proportional set size accounting in smaps

In reply to Matt Mackall

From: Fengguang Wu <[email protected]>

The "proportional set size" (PSS) of a process is the count of pages it has in memory, where each page is divided by the number of processes sharing it. So if a process has 1000 pages all to itself, and 1000 shared with one other process, its PSS will be 1500.

- lwn.net: "ELC: How much memory are applications really using?"

The PSS proposed by Matt Mackall is a very nice metic for measuring an process's memory footprint. So collect and export it via /proc/<pid>/smaps.

Matt Mackall's pagemap/kpagemap and John Berthels's exmap can also do the job. They are comprehensive tools. But for PSS, let's do it in the simple way.

Cc John Berthels <[email protected]>

Cc Bernardo Innocenti <[email protected]>

Cc Padraig Brady <[email protected]>

Cc Denys Vlasenko <[email protected]>

Cc Balbir Singh <[email protected]>

Signed-off-by Matt Mackall <[email protected]>

Signed-off-by Fengguang Wu <[email protected]>

Cc Hugh Dickins <[email protected]>

---

 fs/proc/task_mmu.c |   29 ++++++++++++++++++++++++++++-
 1 files changed, 28 insertions(+), 1 deletion(-)

fs/proc/task_mmu.c +27 -1

Index: l/fs/proc/task_mmu.c
===================================================================
@@ -114,6 +114,25 @@ static void pad_len_spaces(struct seq_fi
 	seq_printf(m, "%*c", len, ' ');
 }
 
+/*
+ * Proportional Set Size(PSS): my share of RSS.
+ *
+ * PSS of a process is the count of pages it has in memory, where each
+ * page is divided by the number of processes sharing it.  So if a
+ * process has 1000 pages all to itself, and 1000 shared with one other
+ * process, its PSS will be 1500.
+ *
+ * To keep (accumulated) division errors low, we adopt a 64bit
+ * fixed-point pss counter to minimize division errors. So (pss >>
+ * PSS_SHIFT) would be the real byte count.
+ *
+ * A shift of 12 before division means (assuming 4K page size):
+ * 	- 1M 3-user-pages add up to 8KB errors;
+ * 	- supports mapcount up to 2^24, or 16M;
+ * 	- supports PSS up to 2^52 bytes, or 4PB.
+ */
+#define PSS_SHIFT 12
+
 struct mem_size_stats
 {
 	unsigned long resident;

@@ -122,6 +141,7 @@ struct mem_size_stats
 	unsigned long private_clean;
 	unsigned long private_dirty;
 	unsigned long referenced;
+	u64 pss;
 };
 
 struct pmd_walker {

@@ -195,6 +215,7 @@ static int show_map_internal(struct seq_
 		seq_printf(m,
 			   "Size:           %8lu kB\n"
 			   "Rss:            %8lu kB\n"
+			   "Pss:            %8lu kB\n"
 			   "Shared_Clean:   %8lu kB\n"
 			   "Shared_Dirty:   %8lu kB\n"
 			   "Private_Clean:  %8lu kB\n"

@@ -202,6 +223,7 @@ static int show_map_internal(struct seq_
 			   "Referenced:     %8lu kB\n",
 			   (vma->vm_end - vma->vm_start) >> 10,
 			   mss->resident >> 10,
+			   (unsigned long)(mss.pss >> (10 + PSS_SHIFT)),
 			   mss->shared_clean  >> 10,
 			   mss->shared_dirty  >> 10,
 			   mss->private_clean >> 10,

@@ -226,6 +248,7 @@ static void smaps_pte_range(struct vm_ar
 	pte_t *pte, ptent;
 	spinlock_t *ptl;
 	struct page *page;
+	int mapcount;
 
 	pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
 	for (; addr != end; pte++, addr += PAGE_SIZE) {

@@ -242,16 +265,19 @@ static void smaps_pte_range(struct vm_ar
 		/* Accumulate the size in pages that have been accessed. */
 		if (pte_young(ptent) || PageReferenced(page))
 			mss->referenced += PAGE_SIZE;
-		if (page_mapcount(page) >= 2) {
+		mapcount = page_mapcount(page);
+		if (mapcount >= 2) {
 			if (pte_dirty(ptent))
 				mss->shared_dirty += PAGE_SIZE;
 			else
 				mss->shared_clean += PAGE_SIZE;
+			mss->pss += (PAGE_SIZE << PSS_SHIFT) / mapcount;
 		} else {
 			if (pte_dirty(ptent))
 				mss->private_dirty += PAGE_SIZE;
 			else
 				mss->private_clean += PAGE_SIZE;
+			mss->pss += (PAGE_SIZE << PSS_SHIFT);
 		}
 	}
 	pte_unmap_unlock(pte - 1, ptl);

Matt Mackall

author

2007-10-26 16:36 UTC #5 lore raw

PATCH 4/12 maps4: introduce a generic page walker

In reply to Matt Mackall

Introduce a general page table walker

Signed-off-by Matt Mackall <[email protected]>

include/linux/mm.h +22 -0

Index: l/include/linux/mm.h
===================================================================
@@ -773,6 +773,28 @@ unsigned long unmap_vmas(struct mmu_gath
 		struct vm_area_struct *start_vma, unsigned long start_addr,
 		unsigned long end_addr, unsigned long *nr_accounted,
 		struct zap_details *);
+
+/**
+ * mm_walk - callbacks for walk_page_range
+ * @pgd_entry: if set, called for each non-empty PGD (top-level) entry
+ * @pud_entry: if set, called for each non-empty PUD (2nd-level) entry
+ * @pmd_entry: if set, called for each non-empty PMD (3rd-level) entry
+ * @pte_entry: if set, called for each non-empty PTE (4th-level) entry
+ * @pte_hole: if set, called for each hole at all levels
+ *
+ * (see walk_page_range for more details)
+ */
+struct mm_walk {
+	int (*pgd_entry)(pgd_t *, unsigned long, unsigned long, void *);
+	int (*pud_entry)(pud_t *, unsigned long, unsigned long, void *);
+	int (*pmd_entry)(pmd_t *, unsigned long, unsigned long, void *);
+	int (*pte_entry)(pte_t *, unsigned long, unsigned long, void *);
+	int (*pte_hole)(unsigned long, unsigned long, void *);
+};
+
+int walk_page_range(const struct mm_struct *, unsigned long addr,
+		    unsigned long end, const struct mm_walk *walk,
+		    void *private);
 void free_pgd_range(struct mmu_gather **tlb, unsigned long addr,
 		unsigned long end, unsigned long floor, unsigned long ceiling);
 void free_pgtables(struct mmu_gather **tlb, struct vm_area_struct *start_vma,

mm/Makefile +1 -1

Index: l/mm/Makefile
===================================================================
@@ -5,7 +5,7 @@
 mmu-y			:= nommu.o
 mmu-$(CONFIG_MMU)	:= fremap.o highmem.o madvise.o memory.o mincore.o \
 			   mlock.o mmap.o mprotect.o mremap.o msync.o rmap.o \
-			   vmalloc.o
+			   vmalloc.o pagewalk.o
 
 obj-y			:= bootmem.o filemap.o mempool.o oom_kill.o fadvise.o \
 			   page_alloc.o page-writeback.o pdflush.o \

mm/pagewalk.c new file +131 -0

131 lines not on this page · raw message

Matt Mackall

author

2007-10-26 16:37 UTC #0 lore raw

cover maps4: pagemap monitoring v4

This patchset is version 4 of my /proc/pid/pagemaps code.

Changes in this series:

- kpageflags decoupled from kernel internal flag bits (suggested by Dave Hansen)
- better docs for walk_page_range (suggested by Jeremy Fitzhardinge)
- a number of cleanups suggested by Dave Rientjes
- fixed kconfig (spotted by Rusty Russell)

Matt Mackall

author

2007-10-26 16:37 UTC #4 lore raw

PATCH 3/12 maps4: move is_swap_pte

Move is_swap_pte helper function to swapops.h for use by pagemap code

Signed-off-by Matt Mackall <[email protected]>

include/linux/swapops.h +6 -0

Index: l/include/linux/swapops.h
===================================================================
@@ -42,6 +42,12 @@ static inline pgoff_t swp_offset(swp_ent
 	return entry.val & SWP_OFFSET_MASK(entry);
 }
 
+/* check whether a pte points to a swap entry */
+static inline int is_swap_pte(pte_t pte)
+{
+	return !pte_none(pte) && !pte_present(pte) && !pte_file(pte);
+}
+
 /*
  * Convert the arch-dependent pte representation of a swp_entry_t into an
  * arch-independent swp_entry_t.

mm/migrate.c +0 -5

Index: l/mm/migrate.c
===================================================================
@@ -114,11 +114,6 @@ int putback_lru_pages(struct list_head *
 	return count;
 }
 
-static inline int is_swap_pte(pte_t pte)
-{
-	return !pte_none(pte) && !pte_present(pte) && !pte_file(pte);
-}
-
 /*
  * Restore a potential migration pte to a working pte entry
  */

Matt Mackall

author

2007-10-26 16:38 UTC #6 lore raw

PATCH 5/12 maps4: use pagewalker in clear_refs and smaps

In reply to Matt Mackall

Use the generic pagewalker for smaps and clear_refs

Signed-off-by Matt Mackall <[email protected]>

fs/proc/task_mmu.c +17 ~~-78~~

Index: l/fs/proc/task_mmu.c
===================================================================
@@ -135,6 +135,7 @@ static void pad_len_spaces(struct seq_fi
 
 struct mem_size_stats
 {
+	struct vm_area_struct *vma;
 	unsigned long resident;
 	unsigned long shared_clean;
 	unsigned long shared_dirty;

@@ -144,13 +145,6 @@ struct mem_size_stats
 	u64 pss;
 };
 
-struct pmd_walker {
-	struct vm_area_struct *vma;
-	void *private;
-	void (*action)(struct vm_area_struct *, pmd_t *, unsigned long,
-		       unsigned long, void *);
-};
-
 static int show_map_internal(struct seq_file *m, void *v, struct mem_size_stats *mss)
 {
 	struct proc_maps_private *priv = m->private;

@@ -240,11 +234,11 @@ static int show_map(struct seq_file *m, 
 	return show_map_internal(m, v, NULL);
 }
 
-static void smaps_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
-			    unsigned long addr, unsigned long end,
-			    void *private)
+static int smaps_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
+			   void *private)
 {
 	struct mem_size_stats *mss = private;
+	struct vm_area_struct *vma = mss->vma;
 	pte_t *pte, ptent;
 	spinlock_t *ptl;
 	struct page *page;

@@ -282,12 +276,13 @@ static void smaps_pte_range(struct vm_ar
 	}
 	pte_unmap_unlock(pte - 1, ptl);
 	cond_resched();
+	return 0;
 }
 
-static void clear_refs_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
-				 unsigned long addr, unsigned long end,
-				 void *private)
+static int clear_refs_pte_range(pmd_t *pmd, unsigned long addr,
+				unsigned long end, void *private)
 {
+	struct vm_area_struct *vma = private;
 	pte_t *pte, ptent;
 	spinlock_t *ptl;
 	struct page *page;

@@ -308,71 +303,10 @@ static void clear_refs_pte_range(struct 
 	}
 	pte_unmap_unlock(pte - 1, ptl);
 	cond_resched();
+	return 0;
 }
 
-static inline void walk_pmd_range(struct pmd_walker *walker, pud_t *pud,
-				  unsigned long addr, unsigned long end)
-{
-	pmd_t *pmd;
-	unsigned long next;
-
-	for (pmd = pmd_offset(pud, addr); addr != end;
-	     pmd++, addr = next) {
-		next = pmd_addr_end(addr, end);
-		if (pmd_none_or_clear_bad(pmd))
-			continue;
-		walker->action(walker->vma, pmd, addr, next, walker->private);
-	}
-}
-
-static inline void walk_pud_range(struct pmd_walker *walker, pgd_t *pgd,
-				  unsigned long addr, unsigned long end)
-{
-	pud_t *pud;
-	unsigned long next;
-
-	for (pud = pud_offset(pgd, addr); addr != end;
-	     pud++, addr = next) {
-		next = pud_addr_end(addr, end);
-		if (pud_none_or_clear_bad(pud))
-			continue;
-		walk_pmd_range(walker, pud, addr, next);
-	}
-}
-
-/*
- * walk_page_range - walk the page tables of a VMA with a callback
- * @vma - VMA to walk
- * @action - callback invoked for every bottom-level (PTE) page table
- * @private - private data passed to the callback function
- *
- * Recursively walk the page table for the memory area in a VMA, calling
- * a callback for every bottom-level (PTE) page table.
- */
-static inline void walk_page_range(struct vm_area_struct *vma,
-				   void (*action)(struct vm_area_struct *,
-						  pmd_t *, unsigned long,
-						  unsigned long, void *),
-				   void *private)
-{
-	unsigned long addr = vma->vm_start;
-	unsigned long end = vma->vm_end;
-	struct pmd_walker walker = {
-		.vma		= vma,
-		.private	= private,
-		.action		= action,
-	};
-	pgd_t *pgd;
-	unsigned long next;
-
-	for (pgd = pgd_offset(vma->vm_mm, addr); addr != end;
-	     pgd++, addr = next) {
-		next = pgd_addr_end(addr, end);
-		if (pgd_none_or_clear_bad(pgd))
-			continue;
-		walk_pud_range(&walker, pgd, addr, next);
-	}
-}
+static struct mm_walk smaps_walk = { .pmd_entry = smaps_pte_range };
 
 static int show_smap(struct seq_file *m, void *v)
 {

@@ -380,11 +314,15 @@ static int show_smap(struct seq_file *m,
 	struct mem_size_stats mss;
 
 	memset(&mss, 0, sizeof mss);
+	mss.vma = vma;
 	if (vma->vm_mm && !is_vm_hugetlb_page(vma))
-		walk_page_range(vma, smaps_pte_range, &mss);
+		walk_page_range(vma->vm_mm, vma->vm_start, vma->vm_end,
+				&smaps_walk, &mss);
 	return show_map_internal(m, v, &mss);
 }
 
+static struct mm_walk clear_refs_walk = { .pmd_entry = clear_refs_pte_range };
+
 void clear_refs_smap(struct mm_struct *mm)
 {
 	struct vm_area_struct *vma;

@@ -392,7 +330,8 @@ void clear_refs_smap(struct mm_struct *m
 	down_read(&mm->mmap_sem);
 	for (vma = mm->mmap; vma; vma = vma->vm_next)
 		if (vma->vm_mm && !is_vm_hugetlb_page(vma))
-			walk_page_range(vma, clear_refs_pte_range, NULL);
+			walk_page_range(vma->vm_mm, vma->vm_start, vma->vm_end,
+					&clear_refs_walk, vma);
 	flush_tlb_mm(mm);
 	up_read(&mm->mmap_sem);
 }

Matt Mackall

author

2007-10-26 16:38 UTC #2 lore raw

PATCH 2/12 maps4: From: Dave Hansen <[email protected]>

In reply to Matt Mackall

From: Dave Hansen <[email protected]>

The following replaces the earlier patches sent. It should address David Rientjes's comments, and has been compile tested on all the architectures that it touches, save for parisc.

----

For the /proc/<pid>/pagemap code[1], we need to able to query how much virtual address space a particular task has. The trick is that we do it through /proc and can't use TASK_SIZE since it references "current" on some arches. The process opening the /proc file might be a 32-bit process opening a 64-bit process's pagemap file.

x86_64 already has a TASK_SIZE_OF() macro:

#define TASK_SIZE_OF(child) ((test_tsk_thread_flag(child, TIF_IA32)) ? IA32_PAGE_OFFSET : TASK_SIZE64)

I'd like to have that for other architectures. So, add it for all the architectures that actually use "current" in their TASK_SIZE. For the others, just add a quick #define in sched.h to use plain old TASK_SIZE.

1. http://www.linuxworld.com/news/2007/042407-kernel.html

- MIPS portion from Ralf Baechle <[email protected]>

Signed-off-by Dave Hansen <[email protected]>

Signed-off-by Ralf Baechle <[email protected]>

Signed-off-by Matt Mackall <[email protected]>

Acked-by David Rientjes <[email protected]>

---

 lxc-dave/include/asm-ia64/processor.h    |    3 ++-
 lxc-dave/include/asm-mips/processor.h    |    4 ++++
 lxc-dave/include/asm-parisc/processor.h  |    3 ++-
 lxc-dave/include/asm-powerpc/processor.h |    3 ++-
 lxc-dave/include/asm-s390/processor.h    |    3 ++-
 lxc-dave/include/linux/sched.h           |    4 ++++
 6 files changed, 16 insertions(+), 4 deletions(-)

include/asm-ia64/processor.h +2 -1

Index: l/include/asm-ia64/processor.h
===================================================================
@@ -31,7 +31,8 @@
  * each (assuming 8KB page size), for a total of 8TB of user virtual
  * address space.
  */
-#define TASK_SIZE		(current->thread.task_size)
+#define TASK_SIZE_OF(tsk)	((tsk)->thread.task_size)
+#define TASK_SIZE       	TASK_SIZE_OF(current)
 
 /*
  * This decides where the kernel will search for a free chunk of vm

include/asm-mips/processor.h +4 -0

Index: l/include/asm-mips/processor.h
===================================================================
@@ -45,6 +45,8 @@ extern unsigned int vced_count, vcei_cou
  * space during mmap's.
  */
 #define TASK_UNMAPPED_BASE	(PAGE_ALIGN(TASK_SIZE / 3))
+#define TASK_SIZE_OF(tsk)						\
+	(test_tsk_thread_flag(tsk, TIF_32BIT_ADDR) ? TASK_SIZE32 : TASK_SIZE)
 #endif
 
 #ifdef CONFIG_64BIT

@@ -65,6 +67,8 @@ extern unsigned int vced_count, vcei_cou
 #define TASK_UNMAPPED_BASE						\
 	(test_thread_flag(TIF_32BIT_ADDR) ?				\
 		PAGE_ALIGN(TASK_SIZE32 / 3) : PAGE_ALIGN(TASK_SIZE / 3))
+#define TASK_SIZE_OF(tsk)						\
+	(test_tsk_thread_flag(tsk, TIF_32BIT_ADDR) ? TASK_SIZE32 : TASK_SIZE)
 #endif
 
 #define NUM_FPU_REGS	32

include/asm-parisc/processor.h +2 -1

Index: l/include/asm-parisc/processor.h
===================================================================
@@ -32,7 +32,8 @@
 #endif
 #define current_text_addr() ({ void *pc; current_ia(pc); pc; })
 
-#define TASK_SIZE               (current->thread.task_size)
+#define TASK_SIZE_OF(tsk)       ((tsk)->thread.task_size)
+#define TASK_SIZE	        TASK_SIZE_OF(current)
 #define TASK_UNMAPPED_BASE      (current->thread.map_base)
 
 #define DEFAULT_TASK_SIZE32	(0xFFF00000UL)

include/asm-powerpc/processor.h +2 -1

Index: l/include/asm-powerpc/processor.h
===================================================================
@@ -99,8 +99,9 @@ extern struct task_struct *last_task_use
  */
 #define TASK_SIZE_USER32 (0x0000000100000000UL - (1*PAGE_SIZE))
 
-#define TASK_SIZE (test_thread_flag(TIF_32BIT) ? \
+#define TASK_SIZE_OF(tsk) (test_tsk_thread_flag(tsk, TIF_32BIT) ? \
 		TASK_SIZE_USER32 : TASK_SIZE_USER64)
+#define TASK_SIZE	  TASK_SIZE_OF(current)
 
 /* This decides where the kernel will search for a free chunk of vm
  * space during mmap's.

include/asm-s390/processor.h +2 -1

Index: l/include/asm-s390/processor.h
===================================================================
@@ -73,8 +73,9 @@ extern struct task_struct *last_task_use
 
 #else /* __s390x__ */
 
-# define TASK_SIZE		(test_thread_flag(TIF_31BIT) ? \
+# define TASK_SIZE_OF(tsk)	(test_tsk_thread_flag(tsk, TIF_31BIT) ? \
 					(0x80000000UL) : (0x40000000000UL))
+# define TASK_SIZE		TASK_SIZE_OF(current)
 # define TASK_UNMAPPED_BASE	(TASK_SIZE / 2)
 # define DEFAULT_TASK_SIZE	(0x40000000000UL)

include/linux/sched.h +4 -0

Index: l/include/linux/sched.h
===================================================================
@@ -1880,6 +1880,10 @@ static inline void inc_syscw(struct task
 }
 #endif
 
+#ifndef TASK_SIZE_OF
+#define TASK_SIZE_OF(tsk)	TASK_SIZE
+#endif
+
 #endif /* __KERNEL__ */
 
 #endif

Matt Mackall

author

2007-10-26 16:38 UTC #7 lore raw

PATCH 6/12 maps4: simplify interdependence of maps and smaps

In reply to Matt Mackall

From: Matt Mackall <[email protected]>

This pulls the shared map display code out of show_map and puts it in show_smap where it belongs.

Signed-off-by Matt Mackall <[email protected]>

Cc Jeremy Fitzhardinge <[email protected]>

Cc David Rientjes <[email protected]>

Signed-off-by Andrew Morton <[email protected]>

fs/proc/task_mmu.c +26 ~~-26~~

Index: l/fs/proc/task_mmu.c
===================================================================
@@ -145,7 +145,7 @@ struct mem_size_stats
 	u64 pss;
 };
 
-static int show_map_internal(struct seq_file *m, void *v, struct mem_size_stats *mss)
+static int show_map(struct seq_file *m, void *v)
 {
 	struct proc_maps_private *priv = m->private;
 	struct task_struct *task = priv->task;

@@ -205,35 +205,11 @@ static int show_map_internal(struct seq_
 	}
 	seq_putc(m, '\n');
 
-	if (mss)
-		seq_printf(m,
-			   "Size:           %8lu kB\n"
-			   "Rss:            %8lu kB\n"
-			   "Pss:            %8lu kB\n"
-			   "Shared_Clean:   %8lu kB\n"
-			   "Shared_Dirty:   %8lu kB\n"
-			   "Private_Clean:  %8lu kB\n"
-			   "Private_Dirty:  %8lu kB\n"
-			   "Referenced:     %8lu kB\n",
-			   (vma->vm_end - vma->vm_start) >> 10,
-			   mss->resident >> 10,
-			   (unsigned long)(mss.pss >> (10 + PSS_SHIFT)),
-			   mss->shared_clean  >> 10,
-			   mss->shared_dirty  >> 10,
-			   mss->private_clean >> 10,
-			   mss->private_dirty >> 10,
-			   mss->referenced >> 10);
-
 	if (m->count < m->size)  /* vma is copied successfully */
 		m->version = (vma != get_gate_vma(task))? vma->vm_start: 0;
 	return 0;
 }
 
-static int show_map(struct seq_file *m, void *v)
-{
-	return show_map_internal(m, v, NULL);
-}
-
 static int smaps_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
 			   void *private)
 {

@@ -312,13 +288,37 @@ static int show_smap(struct seq_file *m,
 {
 	struct vm_area_struct *vma = v;
 	struct mem_size_stats mss;
+	int ret;
 
 	memset(&mss, 0, sizeof mss);
 	mss.vma = vma;
 	if (vma->vm_mm && !is_vm_hugetlb_page(vma))
 		walk_page_range(vma->vm_mm, vma->vm_start, vma->vm_end,
 				&smaps_walk, &mss);
-	return show_map_internal(m, v, &mss);
+
+	ret = show_map(m, v);
+	if (ret)
+		return ret;
+
+	seq_printf(m,
+		   "Size:           %8lu kB\n"
+		   "Rss:            %8lu kB\n"
+		   "Pss:            %8lu kB\n"
+		   "Shared_Clean:   %8lu kB\n"
+		   "Shared_Dirty:   %8lu kB\n"
+		   "Private_Clean:  %8lu kB\n"
+		   "Private_Dirty:  %8lu kB\n"
+		   "Referenced:     %8lu kB\n",
+		   (vma->vm_end - vma->vm_start) >> 10,
+		   mss.resident >> 10,
+		   (unsigned long)(mss.pss >> (10 + PSS_SHIFT)),
+		   mss.shared_clean  >> 10,
+		   mss.shared_dirty  >> 10,
+		   mss.private_clean >> 10,
+		   mss.private_dirty >> 10,
+		   mss.referenced >> 10);
+
+	return ret;
 }
 
 static struct mm_walk clear_refs_walk = { .pmd_entry = clear_refs_pte_range };

Matt Mackall

author

2007-10-26 16:39 UTC #9 lore raw

PATCH 7/12 maps4: move clear_refs code to task_mmu.c

In reply to Matt Mackall

From: Matt Mackall <[email protected]>

This puts all the clear_refs code where it belongs and probably lets things compile on MMU-less systems as well.

Signed-off-by Matt Mackall <[email protected]>

Cc Jeremy Fitzhardinge <[email protected]>

Cc David Rientjes <[email protected]>

Signed-off-by Andrew Morton <[email protected]>

fs/proc/base.c +0 ~~-40~~

Index: l/fs/proc/base.c
===================================================================
@@ -85,10 +85,6 @@
  *	in /proc for a task before it execs a suid executable.
  */
 
-
-/* Worst case buffer size needed for holding an integer. */
-#define PROC_NUMBUF 13
-
 struct pid_entry {
 	char *name;
 	int len;

@@ -713,42 +709,6 @@ static const struct file_operations proc
 	.write		= oom_adjust_write,
 };
 
-#ifdef CONFIG_MMU
-static ssize_t clear_refs_write(struct file *file, const char __user *buf,
-				size_t count, loff_t *ppos)
-{
-	struct task_struct *task;
-	char buffer[PROC_NUMBUF], *end;
-	struct mm_struct *mm;
-
-	memset(buffer, 0, sizeof(buffer));
-	if (count > sizeof(buffer) - 1)
-		count = sizeof(buffer) - 1;
-	if (copy_from_user(buffer, buf, count))
-		return -EFAULT;
-	if (!simple_strtol(buffer, &end, 0))
-		return -EINVAL;
-	if (*end == '\n')
-		end++;
-	task = get_proc_task(file->f_path.dentry->d_inode);
-	if (!task)
-		return -ESRCH;
-	mm = get_task_mm(task);
-	if (mm) {
-		clear_refs_smap(mm);
-		mmput(mm);
-	}
-	put_task_struct(task);
-	if (end - buffer == 0)
-		return -EIO;
-	return end - buffer;
-}
-
-static struct file_operations proc_clear_refs_operations = {
-	.write		= clear_refs_write,
-};
-#endif
-
 #ifdef CONFIG_AUDITSYSCALL
 #define TMPBUFLEN 21
 static ssize_t proc_loginuid_read(struct file * file, char __user * buf,

fs/proc/internal.h +1 -5

Index: l/fs/proc/internal.h
===================================================================
@@ -49,11 +49,7 @@ extern int proc_pid_statm(struct task_st
 extern const struct file_operations proc_maps_operations;
 extern const struct file_operations proc_numa_maps_operations;
 extern const struct file_operations proc_smaps_operations;
-
-extern const struct file_operations proc_maps_operations;
-extern const struct file_operations proc_numa_maps_operations;
-extern const struct file_operations proc_smaps_operations;
-
+extern const struct file_operations proc_clear_refs_operations;
 
 void free_proc_entry(struct proc_dir_entry *de);

fs/proc/task_mmu.c +36 -8

55 lines not on this page · raw message

include/linux/proc_fs.h +2 -1

Index: l/include/linux/proc_fs.h
===================================================================
@@ -18,6 +18,8 @@ struct completion;
  */
 #define FIRST_PROCESS_ENTRY 256
 
+/* Worst case buffer size needed for holding an integer. */
+#define PROC_NUMBUF 13
 
 /*
  * We always define these enumerators

@@ -116,7 +118,6 @@ int proc_pid_readdir(struct file * filp,
 unsigned long task_vsize(struct mm_struct *);
 int task_statm(struct mm_struct *, int *, int *, int *, int *);
 char *task_mem(struct mm_struct *, char *);
-void clear_refs_smap(struct mm_struct *mm);
 
 struct proc_dir_entry *de_get(struct proc_dir_entry *de);
 void de_put(struct proc_dir_entry *de);

Matt Mackall

author

2007-10-26 16:39 UTC #10 lore raw

PATCH 8/12 maps4: regroup task_mmu by interface

In reply to Matt Mackall

From: Matt Mackall <[email protected]>

Reorder source so that all the code and data for each interface is together.

Signed-off-by Matt Mackall <[email protected]>

Cc Jeremy Fitzhardinge <[email protected]>

Cc David Rientjes <[email protected]>

Signed-off-by Andrew Morton <[email protected]>

fs/proc/task_mmu.c +211 ~~-208~~

Index: l/fs/proc/task_mmu.c
===================================================================
@@ -114,36 +114,123 @@ static void pad_len_spaces(struct seq_fi
 	seq_printf(m, "%*c", len, ' ');
 }
 
-/*
- * Proportional Set Size(PSS): my share of RSS.
- *
- * PSS of a process is the count of pages it has in memory, where each
- * page is divided by the number of processes sharing it.  So if a
- * process has 1000 pages all to itself, and 1000 shared with one other
- * process, its PSS will be 1500.
- *
- * To keep (accumulated) division errors low, we adopt a 64bit
- * fixed-point pss counter to minimize division errors. So (pss >>
- * PSS_SHIFT) would be the real byte count.
- *
- * A shift of 12 before division means (assuming 4K page size):
- * 	- 1M 3-user-pages add up to 8KB errors;
- * 	- supports mapcount up to 2^24, or 16M;
- * 	- supports PSS up to 2^52 bytes, or 4PB.
- */
-#define PSS_SHIFT 12
+static void vma_stop(struct proc_maps_private *priv, struct vm_area_struct *vma)
+{
+	if (vma && vma != priv->tail_vma) {
+		struct mm_struct *mm = vma->vm_mm;
+		up_read(&mm->mmap_sem);
+		mmput(mm);
+	}
+}
 
-struct mem_size_stats
+static void *m_start(struct seq_file *m, loff_t *pos)
 {
-	struct vm_area_struct *vma;
-	unsigned long resident;
-	unsigned long shared_clean;
-	unsigned long shared_dirty;
-	unsigned long private_clean;
-	unsigned long private_dirty;
-	unsigned long referenced;
-	u64 pss;
-};
+	struct proc_maps_private *priv = m->private;
+	unsigned long last_addr = m->version;
+	struct mm_struct *mm;
+	struct vm_area_struct *vma, *tail_vma = NULL;
+	loff_t l = *pos;
+
+	/* Clear the per syscall fields in priv */
+	priv->task = NULL;
+	priv->tail_vma = NULL;
+
+	/*
+	 * We remember last_addr rather than next_addr to hit with
+	 * mmap_cache most of the time. We have zero last_addr at
+	 * the beginning and also after lseek. We will have -1 last_addr
+	 * after the end of the vmas.
+	 */
+
+	if (last_addr == -1UL)
+		return NULL;
+
+	priv->task = get_pid_task(priv->pid, PIDTYPE_PID);
+	if (!priv->task)
+		return NULL;
+
+	mm = get_task_mm(priv->task);
+	if (!mm)
+		return NULL;
+
+	tail_vma = get_gate_vma(priv->task);
+	priv->tail_vma = tail_vma;
+	down_read(&mm->mmap_sem);
+
+	/* Start with last addr hint */
+	vma = find_vma(mm, last_addr);
+	if (last_addr && vma) {
+		vma = vma->vm_next;
+		goto out;
+	}
+
+	/*
+	 * Check the vma index is within the range and do
+	 * sequential scan until m_index.
+	 */
+	vma = NULL;
+	if ((unsigned long)l < mm->map_count) {
+		vma = mm->mmap;
+		while (l-- && vma)
+			vma = vma->vm_next;
+		goto out;
+	}
+
+	if (l != mm->map_count)
+		tail_vma = NULL; /* After gate vma */
+
+out:
+	if (vma)
+		return vma;
+
+	/* End of vmas has been reached */
+	m->version = (tail_vma != NULL)? 0: -1UL;
+	up_read(&mm->mmap_sem);
+	mmput(mm);
+	return tail_vma;
+}
+
+static void *m_next(struct seq_file *m, void *v, loff_t *pos)
+{
+	struct proc_maps_private *priv = m->private;
+	struct vm_area_struct *vma = v;
+	struct vm_area_struct *tail_vma = priv->tail_vma;
+
+	(*pos)++;
+	if (vma && (vma != tail_vma) && vma->vm_next)
+		return vma->vm_next;
+	vma_stop(priv, vma);
+	return (vma != tail_vma)? tail_vma: NULL;
+}
+
+static void m_stop(struct seq_file *m, void *v)
+{
+	struct proc_maps_private *priv = m->private;
+	struct vm_area_struct *vma = v;
+
+	vma_stop(priv, vma);
+	if (priv->task)
+		put_task_struct(priv->task);
+}
+
+static int do_maps_open(struct inode *inode, struct file *file,
+			struct seq_operations *ops)
+{
+	struct proc_maps_private *priv;
+	int ret = -ENOMEM;
+	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
+	if (priv) {
+		priv->pid = proc_pid(inode);
+		ret = seq_open(file, ops);
+		if (!ret) {
+			struct seq_file *m = file->private_data;
+			m->private = priv;
+		} else {
+			kfree(priv);
+		}
+	}
+	return ret;
+}
 
 static int show_map(struct seq_file *m, void *v)
 {

@@ -210,6 +297,56 @@ static int show_map(struct seq_file *m, 
 	return 0;
 }
 
+static struct seq_operations proc_pid_maps_op = {
+	.start	= m_start,
+	.next	= m_next,
+	.stop	= m_stop,
+	.show	= show_map
+};
+
+static int maps_open(struct inode *inode, struct file *file)
+{
+	return do_maps_open(inode, file, &proc_pid_maps_op);
+}
+
+const struct file_operations proc_maps_operations = {
+	.open		= maps_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= seq_release_private,
+};
+
+/*
+ * Proportional Set Size(PSS): my share of RSS.
+ *
+ * PSS of a process is the count of pages it has in memory, where each
+ * page is divided by the number of processes sharing it.  So if a
+ * process has 1000 pages all to itself, and 1000 shared with one other
+ * process, its PSS will be 1500.
+ *
+ * To keep (accumulated) division errors low, we adopt a 64bit
+ * fixed-point pss counter to minimize division errors. So (pss >>
+ * PSS_SHIFT) would be the real byte count.
+ *
+ * A shift of 12 before division means (assuming 4K page size):
+ * 	- 1M 3-user-pages add up to 8KB errors;
+ * 	- supports mapcount up to 2^24, or 16M;
+ * 	- supports PSS up to 2^52 bytes, or 4PB.
+ */
+#define PSS_SHIFT 12
+
+struct mem_size_stats
+{
+	struct vm_area_struct *vma;
+	unsigned long resident;
+	unsigned long shared_clean;
+	unsigned long shared_dirty;
+	unsigned long private_clean;
+	unsigned long private_dirty;
+	unsigned long referenced;
+	u64 pss;
+};
+
 static int smaps_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end,
 			   void *private)
 {

@@ -255,33 +392,6 @@ static int smaps_pte_range(pmd_t *pmd, u
 	return 0;
 }
 
-static int clear_refs_pte_range(pmd_t *pmd, unsigned long addr,
-				unsigned long end, void *private)
-{
-	struct vm_area_struct *vma = private;
-	pte_t *pte, ptent;
-	spinlock_t *ptl;
-	struct page *page;
-
-	pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
-	for (; addr != end; pte++, addr += PAGE_SIZE) {
-		ptent = *pte;
-		if (!pte_present(ptent))
-			continue;
-
-		page = vm_normal_page(vma, addr, ptent);
-		if (!page)
-			continue;
-
-		/* Clear accessed and referenced bits. */
-		ptep_test_and_clear_young(vma, addr, pte);
-		ClearPageReferenced(page);
-	}
-	pte_unmap_unlock(pte - 1, ptl);
-	cond_resched();
-	return 0;
-}
-
 static struct mm_walk smaps_walk = { .pmd_entry = smaps_pte_range };
 
 static int show_smap(struct seq_file *m, void *v)

@@ -321,6 +431,52 @@ static int show_smap(struct seq_file *m,
 	return ret;
 }
 
+static struct seq_operations proc_pid_smaps_op = {
+	.start	= m_start,
+	.next	= m_next,
+	.stop	= m_stop,
+	.show	= show_smap
+};
+
+static int smaps_open(struct inode *inode, struct file *file)
+{
+	return do_maps_open(inode, file, &proc_pid_smaps_op);
+}
+
+const struct file_operations proc_smaps_operations = {
+	.open		= smaps_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= seq_release_private,
+};
+
+static int clear_refs_pte_range(pmd_t *pmd, unsigned long addr,
+				unsigned long end, void *private)
+{
+	struct vm_area_struct *vma = private;
+	pte_t *pte, ptent;
+	spinlock_t *ptl;
+	struct page *page;
+
+	pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
+	for (; addr != end; pte++, addr += PAGE_SIZE) {
+		ptent = *pte;
+		if (!pte_present(ptent))
+			continue;
+
+		page = vm_normal_page(vma, addr, ptent);
+		if (!page)
+			continue;
+
+		/* Clear accessed and referenced bits. */
+		ptep_test_and_clear_young(vma, addr, pte);
+		ClearPageReferenced(page);
+	}
+	pte_unmap_unlock(pte - 1, ptl);
+	cond_resched();
+	return 0;
+}
+
 static struct mm_walk clear_refs_walk = { .pmd_entry = clear_refs_pte_range };
 
 static ssize_t clear_refs_write(struct file *file, const char __user *buf,

@@ -364,148 +520,6 @@ const struct file_operations proc_clear_
 	.write		= clear_refs_write,
 };
 
-static void *m_start(struct seq_file *m, loff_t *pos)
-{
-	struct proc_maps_private *priv = m->private;
-	unsigned long last_addr = m->version;
-	struct mm_struct *mm;
-	struct vm_area_struct *vma, *tail_vma = NULL;
-	loff_t l = *pos;
-
-	/* Clear the per syscall fields in priv */
-	priv->task = NULL;
-	priv->tail_vma = NULL;
-
-	/*
-	 * We remember last_addr rather than next_addr to hit with
-	 * mmap_cache most of the time. We have zero last_addr at
-	 * the beginning and also after lseek. We will have -1 last_addr
-	 * after the end of the vmas.
-	 */
-
-	if (last_addr == -1UL)
-		return NULL;
-
-	priv->task = get_pid_task(priv->pid, PIDTYPE_PID);
-	if (!priv->task)
-		return NULL;
-
-	mm = get_task_mm(priv->task);
-	if (!mm)
-		return NULL;
-
-	priv->tail_vma = tail_vma = get_gate_vma(priv->task);
-	down_read(&mm->mmap_sem);
-
-	/* Start with last addr hint */
-	if (last_addr && (vma = find_vma(mm, last_addr))) {
-		vma = vma->vm_next;
-		goto out;
-	}
-
-	/*
-	 * Check the vma index is within the range and do
-	 * sequential scan until m_index.
-	 */
-	vma = NULL;
-	if ((unsigned long)l < mm->map_count) {
-		vma = mm->mmap;
-		while (l-- && vma)
-			vma = vma->vm_next;
-		goto out;
-	}
-
-	if (l != mm->map_count)
-		tail_vma = NULL; /* After gate vma */
-
-out:
-	if (vma)
-		return vma;
-
-	/* End of vmas has been reached */
-	m->version = (tail_vma != NULL)? 0: -1UL;
-	up_read(&mm->mmap_sem);
-	mmput(mm);
-	return tail_vma;
-}
-
-static void vma_stop(struct proc_maps_private *priv, struct vm_area_struct *vma)
-{
-	if (vma && vma != priv->tail_vma) {
-		struct mm_struct *mm = vma->vm_mm;
-		up_read(&mm->mmap_sem);
-		mmput(mm);
-	}
-}
-
-static void *m_next(struct seq_file *m, void *v, loff_t *pos)
-{
-	struct proc_maps_private *priv = m->private;
-	struct vm_area_struct *vma = v;
-	struct vm_area_struct *tail_vma = priv->tail_vma;
-
-	(*pos)++;
-	if (vma && (vma != tail_vma) && vma->vm_next)
-		return vma->vm_next;
-	vma_stop(priv, vma);
-	return (vma != tail_vma)? tail_vma: NULL;
-}
-
-static void m_stop(struct seq_file *m, void *v)
-{
-	struct proc_maps_private *priv = m->private;
-	struct vm_area_struct *vma = v;
-
-	vma_stop(priv, vma);
-	if (priv->task)
-		put_task_struct(priv->task);
-}
-
-static struct seq_operations proc_pid_maps_op = {
-	.start	= m_start,
-	.next	= m_next,
-	.stop	= m_stop,
-	.show	= show_map
-};
-
-static struct seq_operations proc_pid_smaps_op = {
-	.start	= m_start,
-	.next	= m_next,
-	.stop	= m_stop,
-	.show	= show_smap
-};
-
-static int do_maps_open(struct inode *inode, struct file *file,
-			struct seq_operations *ops)
-{
-	struct proc_maps_private *priv;
-	int ret = -ENOMEM;
-	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
-	if (priv) {
-		priv->pid = proc_pid(inode);
-		ret = seq_open(file, ops);
-		if (!ret) {
-			struct seq_file *m = file->private_data;
-			m->private = priv;
-		} else {
-			kfree(priv);
-		}
-	}
-	return ret;
-}
-
-static int maps_open(struct inode *inode, struct file *file)
-{
-	return do_maps_open(inode, file, &proc_pid_maps_op);
-}
-
-const struct file_operations proc_maps_operations = {
-	.open		= maps_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= seq_release_private,
-};
-
 #ifdef CONFIG_NUMA
 extern int show_numa_map(struct seq_file *m, void *v);

@@ -540,14 +554,3 @@ const struct file_operations proc_numa_m
 };
 #endif
 
-static int smaps_open(struct inode *inode, struct file *file)
-{
-	return do_maps_open(inode, file, &proc_pid_smaps_op);
-}
-
-const struct file_operations proc_smaps_operations = {
-	.open		= smaps_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= seq_release_private,
-};

Matt Mackall

author

2007-10-26 16:39 UTC #11 lore raw

PATCH 9/12 maps4: add /proc/pid/pagemap interface

In reply to Matt Mackall

From: Matt Mackall <[email protected]>

This interface provides a mapping for each page in an address space to its physical page frame number, allowing precise determination of what pages are mapped and what pages are shared between processes.

New in this version:

- headers gone again (as recommended by Dave Hansen and Alan Cox)
- 64-bit entries (as per discussion with Andi Kleen)
- swap pte information exported (from Dave Hansen)
- page walker callback for holes (from Dave Hansen)
- direct put_user I/O (as suggested by Rusty Russell)

This patch folds in cleanups and swap PTE support from Dave Hansen <[email protected]>.

Signed-off-by Matt Mackall <[email protected]>

fs/proc/base.c +3 -1

Index: l/fs/proc/base.c
===================================================================
@@ -631,7 +631,7 @@ out_no_task:
 }
 #endif
 
-static loff_t mem_lseek(struct file * file, loff_t offset, int orig)
+loff_t mem_lseek(struct file *file, loff_t offset, int orig)
 {
 	switch (orig) {
 	case 0:

@@ -2030,6 +2030,7 @@ static const struct pid_entry tgid_base_
 #ifdef CONFIG_MMU
 	REG("clear_refs", S_IWUSR, clear_refs),
 	REG("smaps",      S_IRUGO, smaps),
+	REG("pagemap",    S_IRUSR, pagemap),
 #endif
 #ifdef CONFIG_SECURITY
 	DIR("attr",       S_IRUGO|S_IXUGO, attr_dir),

@@ -2316,6 +2317,7 @@ static const struct pid_entry tid_base_s
 #ifdef CONFIG_MMU
 	REG("clear_refs", S_IWUSR, clear_refs),
 	REG("smaps",     S_IRUGO, smaps),
+	REG("pagemap",    S_IRUSR, pagemap),
 #endif
 #ifdef CONFIG_SECURITY
 	DIR("attr",      S_IRUGO|S_IXUGO, attr_dir),

fs/proc/internal.h +2 -0

Index: l/fs/proc/internal.h
===================================================================
@@ -45,11 +45,13 @@ extern int proc_tid_stat(struct task_str
 extern int proc_tgid_stat(struct task_struct *, char *);
 extern int proc_pid_status(struct task_struct *, char *);
 extern int proc_pid_statm(struct task_struct *, char *);
+extern loff_t mem_lseek(struct file *file, loff_t offset, int orig);
 
 extern const struct file_operations proc_maps_operations;
 extern const struct file_operations proc_numa_maps_operations;
 extern const struct file_operations proc_smaps_operations;
 extern const struct file_operations proc_clear_refs_operations;
+extern const struct file_operations proc_pagemap_operations;
 
 void free_proc_entry(struct proc_dir_entry *de);

fs/proc/task_mmu.c +198 -1

215 lines not on this page · raw message

Matt Mackall

author

2007-10-26 16:40 UTC #12 lore raw

PATCH 10/12 maps4: add /proc/kpagecount interface

In reply to Matt Mackall

From: Matt Mackall <[email protected]>

This makes physical page map counts available to userspace. Together with /proc/pid/pagemap and /proc/pid/clear_refs, this can be used to monitor memory usage on a per-page basis.

[[email protected]: make struct proc_kpagemap static]

Signed-off-by Matt Mackall <[email protected]>

Cc Jeremy Fitzhardinge <[email protected]>

Cc David Rientjes <[email protected]>

Signed-off-by Adrian Bunk <[email protected]>

Signed-off-by Andrew Morton <[email protected]>

---

fs/proc/proc_misc.c +53 -0

Index: l/fs/proc/proc_misc.c
===================================================================
@@ -46,6 +46,7 @@
 #include <linux/vmalloc.h>
 #include <linux/crash_dump.h>
 #include <linux/pid_namespace.h>
+#include <linux/bootmem.h>
 #include <asm/uaccess.h>
 #include <asm/pgtable.h>
 #include <asm/io.h>

@@ -656,6 +657,57 @@ static const struct file_operations proc
 };
 #endif
 
+#define KPMSIZE sizeof(u64)
+#define KPMMASK (KPMSIZE - 1)
+/* /proc/kpagecount - an array exposing page counts
+ *
+ * Each entry is a u64 representing the corresponding
+ * physical page count.
+ */
+static ssize_t kpagecount_read(struct file *file, char __user *buf,
+			     size_t count, loff_t *ppos)
+{
+	u64 __user *out = (u64 __user *)buf;
+	struct page *ppage;
+	unsigned long src = *ppos;
+	unsigned long pfn;
+	ssize_t ret = 0;
+	u64 pcount;
+
+	if (!access_ok(VERIFY_WRITE, buf, count))
+		return -EFAULT;
+
+	pfn = src / KPMSIZE;
+	count = min_t(size_t, count, (max_pfn * KPMSIZE) - src);
+	if (src & KPMMASK || count & KPMMASK)
+		return -EIO;
+
+	while (count > 0) {
+		ppage = pfn_to_page(pfn++);
+		if (!ppage)
+			pcount = 0;
+		else
+			pcount = atomic_read(&ppage->_count);
+
+		if (put_user(pcount, out++)) {
+			ret = -EFAULT;
+			break;
+		}
+
+		count -= KPMSIZE;
+	}
+
+	*ppos += (char __user *)out - buf;
+	if (!ret)
+		ret = (char __user *)out - buf;
+	return ret;
+}
+
+static struct file_operations proc_kpagecount_operations = {
+	.llseek = mem_lseek,
+	.read = kpagecount_read,
+};
+
 struct proc_dir_entry *proc_root_kcore;
 
 void create_seq_entry(char *name, mode_t mode, const struct file_operations *f)

@@ -735,6 +787,7 @@ void __init proc_misc_init(void)
 				(size_t)high_memory - PAGE_OFFSET + PAGE_SIZE;
 	}
 #endif
+	create_seq_entry("kpagecount", S_IRUSR, &proc_kpagecount_operations);
 #ifdef CONFIG_PROC_VMCORE
 	proc_vmcore = create_proc_entry("vmcore", S_IRUSR, NULL);
 	if (proc_vmcore)

Matt Mackall

author

2007-10-26 16:40 UTC #13 lore raw

PATCH 11/12 maps4: add /proc/kpageflags interface

In reply to Matt Mackall

From: Matt Mackall <[email protected]>

This makes a subset of physical page flags available to userspace. Together with /proc/pid/kpagemap, this allows tracking of a wide variety of VM behaviors.

Exported flags are decoupled from the kernel's internal flags. This allows us to reorder flag bits, and synthesize any bits that get redefined in terms of other bits.

Signed-off-by Matt Mackall <[email protected]>

---

fs/proc/proc_misc.c +79 -0

Index: l/fs/proc/proc_misc.c
===================================================================
@@ -708,6 +708,84 @@ static struct file_operations proc_kpage
 	.read = kpagecount_read,
 };
 
+/* /proc/kpageflags - an array exposing page flags
+ *
+ * Each entry is a u64 representing the corresponding
+ * physical page flags.
+ */
+
+/* These macros are used to decouple internal flags from exported ones */
+
+#define KPF_LOCKED     0
+#define KPF_ERROR      1
+#define KPF_REFERENCED 2
+#define KPF_UPTODATE   3
+#define KPF_DIRTY      4
+#define KPF_LRU        5
+#define KPF_ACTIVE     6
+#define KPF_SLAB       7
+#define KPF_WRITEBACK  8
+#define KPF_RECLAIM    9
+#define KPF_BUDDY     10
+
+#define kpf_copy_bit(flags, srcpos, dstpos) (((flags >> srcpos) & 1) << dstpos)
+
+static ssize_t kpageflags_read(struct file *file, char __user *buf,
+			     size_t count, loff_t *ppos)
+{
+	u64 __user *out = (u64 __user *)buf;
+	struct page *ppage;
+	unsigned long src = *ppos;
+	unsigned long pfn;
+	ssize_t ret = 0;
+	u64 kflags, uflags;
+
+	if (!access_ok(VERIFY_WRITE, buf, count))
+		return -EFAULT;
+
+	pfn = src / KPMSIZE;
+	count = min_t(unsigned long, count, (max_pfn * KPMSIZE) - src);
+	if (src & KPMMASK || count & KPMMASK)
+		return -EIO;
+
+	while (count > 0) {
+		ppage = pfn_to_page(pfn++);
+		if (!ppage)
+			kflags = 0;
+		else
+			kflags = ppage->flags;
+
+		uflags = kpf_copy_bit(KPF_LOCKED, PG_locked, kflags) |
+			kpf_copy_bit(kflags, KPF_ERROR, PG_error) |
+			kpf_copy_bit(kflags, KPF_REFERENCED, PG_referenced) |
+			kpf_copy_bit(kflags, KPF_UPTODATE, PG_uptodate) |
+			kpf_copy_bit(kflags, KPF_DIRTY, PG_dirty) |
+			kpf_copy_bit(kflags, KPF_LRU, PG_lru) |
+			kpf_copy_bit(kflags, KPF_ACTIVE, PG_active) |
+			kpf_copy_bit(kflags, KPF_SLAB, PG_slab) |
+			kpf_copy_bit(kflags, KPF_WRITEBACK, PG_writeback) |
+			kpf_copy_bit(kflags, KPF_RECLAIM, PG_reclaim) |
+			kpf_copy_bit(kflags, KPF_BUDDY, PG_buddy);
+
+		if (put_user(uflags, out++)) {
+			ret = -EFAULT;
+			break;
+		}
+
+		count -= KPMSIZE;
+	}
+
+	*ppos += (char __user *)out - buf;
+	if (!ret)
+		ret = (char __user *)out - buf;
+	return ret;
+}
+
+static struct file_operations proc_kpageflags_operations = {
+	.llseek = mem_lseek,
+	.read = kpageflags_read,
+};
+
 struct proc_dir_entry *proc_root_kcore;
 
 void create_seq_entry(char *name, mode_t mode, const struct file_operations *f)

@@ -788,6 +866,7 @@ void __init proc_misc_init(void)
 	}
 #endif
 	create_seq_entry("kpagecount", S_IRUSR, &proc_kpagecount_operations);
+	create_seq_entry("kpageflags", S_IRUSR, &proc_kpageflags_operations);
 #ifdef CONFIG_PROC_VMCORE
 	proc_vmcore = create_proc_entry("vmcore", S_IRUSR, NULL);
 	if (proc_vmcore)

Matt Mackall

author

2007-10-26 16:41 UTC #14 lore raw

PATCH 12/12 maps4: make page monitoring /proc file optional

In reply to Matt Mackall

Make /proc/ page monitoring configurable

This puts the following files under an embedded config option:

/proc/pid/clear_refs
/proc/pid/smaps
/proc/pid/pagemap
/proc/kpagecount
/proc/kpageflags

Signed-off-by Matt Mackall <[email protected]>

fs/proc/base.c +2 -2

Index: l/fs/proc/base.c
===================================================================
@@ -2027,7 +2027,7 @@ static const struct pid_entry tgid_base_
 	LNK("exe",        exe),
 	REG("mounts",     S_IRUGO, mounts),
 	REG("mountstats", S_IRUSR, mountstats),
-#ifdef CONFIG_MMU
+#ifdef CONFIG_PROC_PAGE_MONITOR
 	REG("clear_refs", S_IWUSR, clear_refs),
 	REG("smaps",      S_IRUGO, smaps),
 	REG("pagemap",    S_IRUSR, pagemap),

@@ -2314,7 +2314,7 @@ static const struct pid_entry tid_base_s
 	LNK("root",      root),
 	LNK("exe",       exe),
 	REG("mounts",    S_IRUGO, mounts),
-#ifdef CONFIG_MMU
+#ifdef CONFIG_PROC_PAGE_MONITOR
 	REG("clear_refs", S_IWUSR, clear_refs),
 	REG("smaps",     S_IRUGO, smaps),
 	REG("pagemap",    S_IRUSR, pagemap),

fs/proc/proc_misc.c +4 -0

Index: l/fs/proc/proc_misc.c
===================================================================
@@ -657,6 +657,7 @@ static const struct file_operations proc
 };
 #endif
 
+#ifdef CONFIG_PROC_PAGE_MONITOR
 #define KPMSIZE sizeof(u64)
 #define KPMMASK (KPMSIZE - 1)
 /* /proc/kpagecount - an array exposing page counts

@@ -785,6 +786,7 @@ static struct file_operations proc_kpage
 	.llseek = mem_lseek,
 	.read = kpageflags_read,
 };
+#endif /* CONFIG_PROC_PAGE_MONITOR */
 
 struct proc_dir_entry *proc_root_kcore;

@@ -865,8 +867,10 @@ void __init proc_misc_init(void)
 				(size_t)high_memory - PAGE_OFFSET + PAGE_SIZE;
 	}
 #endif
+#ifdef CONFIG_PROC_PAGE_MONITOR
 	create_seq_entry("kpagecount", S_IRUSR, &proc_kpagecount_operations);
 	create_seq_entry("kpageflags", S_IRUSR, &proc_kpageflags_operations);
+#endif
 #ifdef CONFIG_PROC_VMCORE
 	proc_vmcore = create_proc_entry("vmcore", S_IRUSR, NULL);
 	if (proc_vmcore)

fs/proc/task_mmu.c +2 -0

Index: l/fs/proc/task_mmu.c
===================================================================
@@ -338,6 +338,7 @@ const struct file_operations proc_maps_o
  */
 #define PSS_SHIFT 12
 
+#ifdef CONFIG_PROC_PAGE_MONITOR
 struct mem_size_stats
 {
 	struct vm_area_struct *vma;

@@ -717,6 +718,7 @@ const struct file_operations proc_pagema
 	.llseek		= mem_lseek, /* borrow this */
 	.read		= pagemap_read,
 };
+#endif /* CONFIG_PROC_PAGE_MONITOR */
 
 #ifdef CONFIG_NUMA
 extern int show_numa_map(struct seq_file *m, void *v);

init/Kconfig +10 -0

Index: l/init/Kconfig
===================================================================
@@ -571,6 +571,16 @@ config SLOB
 
 endchoice
 
+config PROC_PAGE_MONITOR
+ 	default y
+	depends PROC_FS && MMU
+	bool "Enable /proc page monitoring" if EMBEDDED
+ 	help
+	  Various /proc files exist to monitor process memory utilization:
+	  /proc/pid/smaps, /proc/pid/clear_refs, /proc/pid/pagemap,
+	  /proc/kpagecount, and /proc/kpageflags. Disabling these
+          interfaces will reduce the size of the kernel by approximately 4kb.
+
 endmenu		# General setup
 
 config RT_MUTEXES

mm/Makefile +2 -1

Index: l/mm/Makefile
===================================================================
@@ -5,7 +5,7 @@
 mmu-y			:= nommu.o
 mmu-$(CONFIG_MMU)	:= fremap.o highmem.o madvise.o memory.o mincore.o \
 			   mlock.o mmap.o mprotect.o mremap.o msync.o rmap.o \
-			   vmalloc.o pagewalk.o
+			   vmalloc.o
 
 obj-y			:= bootmem.o filemap.o mempool.o oom_kill.o fadvise.o \
 			   page_alloc.o page-writeback.o pdflush.o \

@@ -13,6 +13,7 @@ obj-y			:= bootmem.o filemap.o mempool.o
 			   prio_tree.o util.o mmzone.o vmstat.o backing-dev.o \
 			   $(mmu-y)
 
+obj-$(CONFIG_PROC_PAGE_MONITOR) += pagewalk.o
 obj-$(CONFIG_BOUNCE)	+= bounce.o
 obj-$(CONFIG_SWAP)	+= page_io.o swap_state.o swapfile.o thrash.o
 obj-$(CONFIG_HUGETLBFS)	+= hugetlb.o

David Rientjes

2007-10-26 21:23 UTC #3 lore raw

Re: [PATCH 2/12] maps4: From: Dave Hansen <[email protected]>

In reply to Matt Mackall

Quoted 4 lines · Matt Mackall

The following replaces the earlier patches sent. It should address David Rientjes's comments, and has been compile tested on all the architectures that it touches, save for parisc.

Looks good, thanks.

David Rientjes

Acked-by on v1 6/12

2007-10-26 21:24 UTC #8 lore raw

Re: [PATCH 6/12] maps4: simplify interdependence of maps and smaps

In reply to Matt Mackall

Quoted 8 lines · Matt Mackall

From: Matt Mackall <[email protected]>
This pulls the shared map display code out of show_map and puts it in show_smap where it belongs.
Signed-off-by Matt Mackall <[email protected]>
Cc Jeremy Fitzhardinge <[email protected]>
Cc David Rientjes <[email protected]>

Acked-by David Rientjes <[email protected]>