Attachment 148864 Details for Bug 215407 – Fifth take of the smaps patch

[patch] Fifth take of the smaps patch

linux-2.6.9-smaps-5.patch (text/plain), 11.02 KB, created by Chris Lalancette on 2007-02-27 14:48:17 UTC

(hide)

Description:

Filename:

MIME Type:

Creator: Chris Lalancette

Created: 2007-02-27 14:48:17 UTC

Size: 11.02 KB

patch

obsolete

>diff -urp linux-2.6.9.orig/Documentation/filesystems/proc.txt linux-2.6.9/Documentation/filesystems/proc.txt
>--- linux-2.6.9.orig/Documentation/filesystems/proc.txt	2006-12-06 13:58:52.000000000 -0500
>+++ linux-2.6.9/Documentation/filesystems/proc.txt	2006-12-06 13:59:34.000000000 -0500
>@@ -133,6 +133,7 @@ Table 1-1: Process specific entries in /
>  statm   Process memory status information              
>  status  Process status in human readable form          
>  wchan   If CONFIG_KALLSYMS is set, a pre-decoded wchan
>+ smaps   Extension based on maps, presenting the rss size for each mapped file
> ..............................................................................
> 
> For example, to get the status information of a process, all you have to do is
>diff -urp linux-2.6.9.orig/fs/proc/base.c linux-2.6.9/fs/proc/base.c
>--- linux-2.6.9.orig/fs/proc/base.c	2006-12-06 13:58:52.000000000 -0500
>+++ linux-2.6.9/fs/proc/base.c	2006-12-06 14:03:04.000000000 -0500
>@@ -11,6 +11,40 @@
>  *  go into icache. We cache the reference to task_struct upon lookup too.
>  *  Eventually it should become a filesystem in its own. We don't use the
>  *  rest of procfs anymore.
>+ *
>+ *
>+ *  Changelog:
>+ *  17-Jan-2005
>+ *  Allan Bezerra
>+ *  Bruna Moreira <bruna.moreira@indt.org.br>
>+ *  Edjard Mota <edjard.mota@indt.org.br>
>+ *  Ilias Biris <ilias.biris@indt.org.br>
>+ *  Mauricio Lin <mauricio.lin@indt.org.br>
>+ *
>+ *  Embedded Linux Lab - 10LE Instituto Nokia de Tecnologia - INdT
>+ *
>+ *  A new process specific entry (smaps) included in /proc. It shows the
>+ *  size of rss for each memory area. The maps entry lacks information
>+ *  about physical memory size (rss) for each mapped file, i.e.,
>+ *  rss information for executables and library files.
>+ *  This additional information is useful for any tools that need to know
>+ *  about physical memory consumption for a process specific library.
>+ *
>+ *  Changelog:
>+ *  21-Feb-2005
>+ *  Embedded Linux Lab - 10LE Instituto Nokia de Tecnologia - INdT
>+ *  Pud inclusion in the page table walking.
>+ *
>+ *  ChangeLog:
>+ *  10-Mar-2005
>+ *  10LE Instituto Nokia de Tecnologia - INdT:
>+ *  A better way to walks through the page table as suggested by Hugh Dickins.
>+ *
>+ *  Simo Piiroinen <simo.piiroinen@nokia.com>:
>+ *  Smaps information related to shared, private, clean and dirty pages.
>+ *
>+ *  Paul Mundt <paul.mundt@nokia.com>:
>+ *  Overall revision about smaps.
>  */
> 
> #include <asm/uaccess.h>
>@@ -62,6 +96,9 @@ enum pid_directory_inos {
> 	PROC_TGID_MOUNTS,
> 	PROC_TGID_MOUNTSTATS,
> 	PROC_TGID_WCHAN,
>+#ifdef CONFIG_MMU
>+	PROC_TGID_SMAPS,
>+#endif
> #ifdef CONFIG_SCHEDSTATS
> 	PROC_TGID_SCHEDSTAT,
> #endif
>@@ -92,6 +129,9 @@ enum pid_directory_inos {
> 	PROC_TID_MOUNTS,
> 	PROC_TID_MOUNTSTATS,
> 	PROC_TID_WCHAN,
>+#ifdef CONFIG_MMU
>+	PROC_TID_SMAPS,
>+#endif
> #ifdef CONFIG_SCHEDSTATS
> 	PROC_TID_SCHEDSTAT,
> #endif
>@@ -133,6 +173,9 @@ static struct pid_entry tgid_base_stuff[
> 	E(PROC_TGID_EXE,       "exe",     S_IFLNK|S_IRWXUGO),
> 	E(PROC_TGID_MOUNTS,    "mounts",  S_IFREG|S_IRUGO),
> 	E(PROC_TGID_MOUNTSTATS, "mountstats", S_IFREG|S_IRUSR),
>+#ifdef CONFIG_MMU
>+	E(PROC_TGID_SMAPS,     "smaps",   S_IFREG|S_IRUSR),
>+#endif
> #ifdef CONFIG_SECURITY
> 	E(PROC_TGID_ATTR,      "attr",    S_IFDIR|S_IRUGO|S_IXUGO),
> #endif
>@@ -161,6 +204,9 @@ static struct pid_entry tid_base_stuff[]
> 	E(PROC_TID_ROOT,       "root",    S_IFLNK|S_IRWXUGO),
> 	E(PROC_TID_EXE,        "exe",     S_IFLNK|S_IRWXUGO),
> 	E(PROC_TID_MOUNTS,     "mounts",  S_IFREG|S_IRUGO),
>+#ifdef CONFIG_MMU
>+	E(PROC_TID_SMAPS,      "smaps",   S_IFREG|S_IRUSR),
>+#endif
> #ifdef CONFIG_SECURITY
> 	E(PROC_TID_ATTR,       "attr",    S_IFDIR|S_IRUGO|S_IXUGO),
> #endif
>@@ -528,6 +574,36 @@ static struct file_operations proc_maps_
> 	.release	= seq_release_private,
> };
> 
>+#ifdef CONFIG_MMU
>+extern struct seq_operations proc_pid_smaps_op;
>+static int smaps_open(struct inode *inode, struct file *file)
>+{
>+	struct proc_maps_private *priv;
>+	struct task_struct *task = proc_task(inode);
>+	int ret = -ENOMEM;
>+
>+	priv = kzalloc(sizeof(*priv), GFP_KERNEL);
>+	if (priv) {
>+		ret = seq_open(file, &proc_pid_smaps_op);
>+		if (!ret) {
>+			struct seq_file *m = file->private_data;
>+			priv->task = task;
>+			m->private = priv;
>+		} else {
>+			kfree(priv);
>+		}
>+	}
>+	return ret;
>+}
>+
>+static struct file_operations proc_smaps_operations = {
>+	.open		= smaps_open,
>+	.read		= seq_read,
>+	.llseek		= seq_lseek,
>+	.release	= seq_release_private,
>+};
>+#endif
>+
> extern struct seq_operations mounts_op;
> static int mounts_open(struct inode *inode, struct file *file)
> {
>@@ -1477,6 +1553,12 @@ static struct dentry *proc_pident_lookup
> 		case PROC_TGID_MOUNTSTATS:
> 			inode->i_fop = &proc_mountstats_operations;
> 			break;
>+#ifdef CONFIG_MMU
>+		case PROC_TID_SMAPS:
>+		case PROC_TGID_SMAPS:
>+			inode->i_fop = &proc_smaps_operations;
>+			break;
>+#endif
> #ifdef CONFIG_SECURITY
> 		case PROC_TID_ATTR:
> 			inode->i_nlink = 2;
>diff -urp linux-2.6.9.orig/fs/proc/task_mmu.c linux-2.6.9/fs/proc/task_mmu.c
>--- linux-2.6.9.orig/fs/proc/task_mmu.c	2006-12-06 13:58:52.000000000 -0500
>+++ linux-2.6.9/fs/proc/task_mmu.c	2006-12-06 13:59:34.000000000 -0500
>@@ -2,6 +2,7 @@
> #include <linux/hugetlb.h>
> #include <linux/seq_file.h>
> #include <linux/proc_fs.h>
>+#include <linux/highmem.h>
> #include <asm/elf.h>
> #include <asm/uaccess.h>
> 
>@@ -96,6 +97,112 @@ static int show_map(struct seq_file *m, 
> 	return 0;
> }
> 
>+struct mem_size_stats
>+{
>+	unsigned long resident;
>+	unsigned long shared_clean;
>+	unsigned long shared_dirty;
>+	unsigned long private_clean;
>+	unsigned long private_dirty;
>+};
>+
>+static void smaps_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
>+				unsigned long addr, unsigned long end,
>+				struct mem_size_stats *mss)
>+{
>+	pte_t *pte, ptent;
>+	unsigned long pfn;
>+	struct page *page;
>+
>+	pte = pte_offset_map(pmd, addr);
>+	do {
>+		ptent = *pte;
>+		if (pte_none(ptent) || !pte_present(ptent))
>+			continue;
>+
>+		mss->resident += PAGE_SIZE;
>+		pfn = pte_pfn(ptent);
>+		if (!pfn_valid(pfn))
>+			continue;
>+
>+		page = pfn_to_page(pfn);
>+		if (page_count(page) >= 2) {
>+			if (pte_dirty(ptent))
>+				mss->shared_dirty += PAGE_SIZE;
>+			else
>+				mss->shared_clean += PAGE_SIZE;
>+		} else {
>+			if (pte_dirty(ptent))
>+				mss->private_dirty += PAGE_SIZE;
>+			else
>+				mss->private_clean += PAGE_SIZE;
>+		}
>+	} while (pte++, addr += PAGE_SIZE, addr != end);
>+	pte_unmap(pte - 1);
>+	cond_resched();
>+}
>+
>+static inline void smaps_pmd_range(struct vm_area_struct *vma, pgd_t *pgd,
>+				unsigned long addr, unsigned long end,
>+				struct mem_size_stats *mss)
>+{
>+	pmd_t *pmd;
>+	unsigned long next;
>+
>+	pmd = pmd_offset(pgd, addr);
>+	do {
>+		next = pmd_addr_end(addr, end);
>+		if (pmd_none_or_clear_bad(pmd))
>+			continue;
>+		smaps_pte_range(vma, pmd, addr, next, mss);
>+	} while (pmd++, addr = next, addr != end);
>+}
>+
>+static inline void smaps_pgd_range(struct vm_area_struct *vma,
>+				unsigned long addr, unsigned long end,
>+				struct mem_size_stats *mss)
>+{
>+	pgd_t *pgd;
>+	unsigned long next;
>+
>+	pgd = pgd_offset(vma->vm_mm, addr);
>+	do {
>+		next = pgd_addr_end(addr, end);
>+		if (pgd_none_or_clear_bad(pgd))
>+			continue;
>+		smaps_pmd_range(vma, pgd, addr, next, mss);
>+	} while (pgd++, addr = next, addr != end);
>+}
>+
>+static int show_smap(struct seq_file *m, void *v)
>+{
>+	struct vm_area_struct *vma = v;
>+	unsigned long vma_len = (vma->vm_end - vma->vm_start);
>+	struct mem_size_stats mss;
>+
>+	memset(&mss, 0, sizeof mss);
>+
>+	show_map(m, v);
>+
>+	if (vma->vm_mm && !is_vm_hugetlb_page(vma))
>+		smaps_pgd_range(vma, vma->vm_start, vma->vm_end, &mss);
>+
>+	seq_printf(m,
>+		   "Size:          %8lu kB\n"
>+		   "Rss:           %8lu kB\n"
>+		   "Shared_Clean:  %8lu kB\n"
>+		   "Shared_Dirty:  %8lu kB\n"
>+		   "Private_Clean: %8lu kB\n"
>+		   "Private_Dirty: %8lu kB\n",
>+		   vma_len >> 10,
>+		   mss.resident >> 10,
>+		   mss.shared_clean  >> 10,
>+		   mss.shared_dirty  >> 10,
>+		   mss.private_clean >> 10,
>+		   mss.private_dirty >> 10);
>+	return 0;
>+}
>+
> static void *m_start(struct seq_file *m, loff_t *pos)
> {
> 	struct proc_maps_private *priv = m->private;
>@@ -164,6 +271,13 @@ struct seq_operations proc_pid_maps_op =
> 	.show	= show_map
> };
> 
>+struct seq_operations proc_pid_smaps_op = {
>+	.start	= m_start,
>+	.next	= m_next,
>+	.stop	= m_stop,
>+	.show	= show_smap
>+};
>+
> struct mm_struct *mm_for_maps(struct task_struct *task)
> {
> 	struct mm_struct *mm = get_task_mm(task);
>diff -urp linux-2.6.9.orig/include/asm-generic/pgtable.h linux-2.6.9/include/asm-generic/pgtable.h
>--- linux-2.6.9.orig/include/asm-generic/pgtable.h	2006-12-06 13:58:47.000000000 -0500
>+++ linux-2.6.9/include/asm-generic/pgtable.h	2006-12-06 13:59:34.000000000 -0500
>@@ -137,4 +137,56 @@ static inline void ptep_mkdirty(pte_t *p
> #ifndef __HAVE_ARCH_LAZY_MMU_UPDATE
> #define lazy_mmu_prot_update(pte)		do { } while (0)
> #endif
>+
>+/*
>+ * When walking page tables, get the address of the next boundary,
>+ * or the end address of the range if that comes earlier.  Although no
>+ * vma end wraps to 0, rounded up __boundary may wrap to 0 throughout.
>+ */
>+
>+#define pgd_addr_end(addr, end)                                         \
>+({      unsigned long __boundary = ((addr) + PGDIR_SIZE) & PGDIR_MASK;  \
>+        (__boundary - 1 < (end) - 1)? __boundary: (end);                \
>+})
>+
>+#ifndef pmd_addr_end
>+#define pmd_addr_end(addr, end)                                         \
>+({      unsigned long __boundary = ((addr) + PMD_SIZE) & PMD_MASK;      \
>+        (__boundary - 1 < (end) - 1)? __boundary: (end);                \
>+})
>+#endif
>+
>+
>+#ifndef __ASSEMBLY__
>+/*
>+ * When walking page tables, we usually want to skip any p?d_none entries;
>+ * and any p?d_bad entries - reporting the error before resetting to none.
>+ * Do the tests inline, but report and clear the bad entry in mm/memory.c.
>+ */
>+void pgd_clear_bad(pgd_t *);
>+void pmd_clear_bad(pmd_t *);
>+
>+static inline int pgd_none_or_clear_bad(pgd_t *pgd)
>+{
>+        if (pgd_none(*pgd))
>+                return 1;
>+        if (unlikely(pgd_bad(*pgd))) {
>+                pgd_clear_bad(pgd);
>+                return 1;
>+        }
>+        return 0;
>+}
>+
>+static inline int pmd_none_or_clear_bad(pmd_t *pmd)
>+{
>+        if (pmd_none(*pmd))
>+                return 1;
>+        if (unlikely(pmd_bad(*pmd))) {
>+                pmd_clear_bad(pmd);
>+                return 1;
>+        }
>+        return 0;
>+}
>+#endif /* !__ASSEMBLY__ */
>+
> #endif /* _ASM_GENERIC_PGTABLE_H */
>diff -urp linux-2.6.9.orig/mm/memory.c linux-2.6.9/mm/memory.c
>--- linux-2.6.9.orig/mm/memory.c	2006-12-06 13:58:52.000000000 -0500
>+++ linux-2.6.9/mm/memory.c	2006-12-06 13:59:34.000000000 -0500
>@@ -83,6 +83,24 @@ EXPORT_SYMBOL(high_memory);
> EXPORT_SYMBOL(vmalloc_earlyreserve);
> 
> /*
>+ * If a p?d_bad entry is found while walking page tables, report
>+ * the error, before resetting entry to p?d_none.  Usually (but
>+ * very seldom) called out from the p?d_none_or_clear_bad macros.
>+ */
>+
>+void pgd_clear_bad(pgd_t *pgd)
>+{
>+        pgd_ERROR(*pgd);
>+        pgd_clear(pgd);
>+}
>+
>+void pmd_clear_bad(pmd_t *pmd)
>+{
>+        pmd_ERROR(*pmd);
>+        pmd_clear(pmd);
>+}
>+
>+/*
>  * We special-case the C-O-W ZERO_PAGE, because it's such
>  * a common occurrence (no need to read the page to know
>  * that it's zero - better for the cache and memory subsystem).

Actions: View | Diff

Attachments on bug 215407: 141096 | 142996 | 148864