[PATCH V6] makedumpfile: exclude page structures of non-dumped pages

Cliff Wickman cpw at sgi.com
Fri Oct 23 13:40:50 PDT 2015


From: Cliff Wickman <cpw at sgi.com>

Applies to the development branch as of 10/13/2015.

Incorporates review 10/22 by kumagai-atsushi.

This patch adds a -e option to makedumpfile.
The -e option excludes kernel pages that contain nothing but kernel page
structures for pages that are not being included in the dump.
The -e option only works in non-cyclic mode, which its use implies.

The -e requires the use of --work-dir, as it will create a pfn file in that
work directory.  The --work-dir should probably be set up by the distro procedures
which determine the mount point of the root device.
This patch formerly applied after patch:
  [PATCH V2] makedumpfile: make --work-dir easier to use
but now it stands alone.

I have tested on large memory systems to demonstrate the importance
of this feature to such systems. See some numbers below.

The most dramatic demonstration was on a 32TB system where the patch
reduced the process from 2 hours to 26 minutes.  The size of the dump
would probably have been over 30GB (but I ran out of disk space). It was
reduced to 5.4GB.

A page structure (56 bytes) exists for every 4096-byte page.
This amounts to 3.67 million pages, or about 14GB, per terabyte of system memory!

Without -e an idle 2-terabyte system can be dumped (compressed) to a file of
about 3.6G.  
With -e that is reduced to about 456M.  And the time and space savings
multiply for each additional terabyte of memory in the system.

Experimental time/size results:  (basically idle systems)

Memory Size	With -e			Without -e
		(sec.)			(sec.)
(using a sles11sp3 kernel that does not provide mmap of /proc/vmcore:)
1TB		   52 244M		  257  1.7G
2TB		  128 456M		  526  3.6G
8TB		  780 1.6G		 3400 13.8G
16TB		 2600 3.1G		 9800 (extrapolated, 2:40 is too long to wait)
(using a sles11sp3 kernel that provides mmap of /proc/vmcore:)
16TB		  900 3.8G		 not done
32TB		 6000 5.4G		 not done
(using a sles11sp3 kernel that provides mmap of /proc/vmcore:)
32TB		 1600 5.4G		7300 (extrapolated)
                                        (ran out of 19G space before 1/2 done)

The only disadvantage is that various options of the crash 'kmem' command (that
walk lists of page structures) will not work. 
Version 7.0.9 of crash is already patched to issue a warning about such commands
when the dump is flagged DUMP_DH_EXCLUDED_VMEMMAP.


Sorry that this patch is large.  The vmemmap page scan is done by some very large
functions, and they are all interrelated. I didn't see any point to breaking
them into several inter-dependent patches.

---
 arch/x86_64.c  |  307 ++++++++++++++++++++++++++++++++++++++++++++++
 diskdump_mod.h |    1 
 makedumpfile.c |  375 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++-
 makedumpfile.h |   57 ++++++++
 print_info.c   |   13 +
 5 files changed, 751 insertions(+), 2 deletions(-)

Index: code/print_info.c
===================================================================
--- code.orig/print_info.c
+++ code/print_info.c
@@ -58,7 +58,11 @@ print_usage(void)
 	MSG("\n");
 	MSG("Usage:\n");
 	MSG("  Creating DUMPFILE:\n");
+#ifdef __x86_64__
+	MSG("  # makedumpfile    [-c|-l|-p|-E] [-d DL] [-e] [-x VMLINUX|-i VMCOREINFO] VMCORE\n");
+#else
 	MSG("  # makedumpfile    [-c|-l|-p|-E] [-d DL] [-x VMLINUX|-i VMCOREINFO] VMCORE\n");
+#endif
 	MSG("    DUMPFILE\n");
 	MSG("\n");
 	MSG("  Creating DUMPFILE with filtered kernel data specified through filter config\n");
@@ -112,6 +116,15 @@ print_usage(void)
 	MSG("      or snappy for -p option. A user cannot specify either of these options with\n");
 	MSG("      -E option, because the ELF format does not support compressed data.\n");
 	MSG("      THIS IS ONLY FOR THE CRASH UTILITY.\n");
+#ifdef __x86_64__
+	MSG("\n");
+	MSG("  [-e]:\n");
+	MSG("      Exclude the page structures (vmemmap) which represent excluded pages.\n");
+	MSG("      This greatly shortens the dump of a very large memory system.\n");
+	MSG("      The --work-dir option must also be specified, as it will be used\n");
+	MSG("      to hold bitmaps and a file of page numbers that are to be excluded.\n");
+	MSG("      The -e option will cause a noncyclic dump procedure.\n");
+#endif
 	MSG("\n");
 	MSG("  [-d DL]:\n");
 	MSG("      Specify the type of unnecessary page for analysis.\n");
Index: code/makedumpfile.h
===================================================================
--- code.orig/makedumpfile.h
+++ code/makedumpfile.h
@@ -45,6 +45,9 @@
 #include "sadump_mod.h"
 #include <pthread.h>
 
+#define VMEMMAPSTART 0xffffea0000000000UL
+#define BITS_PER_WORD 64
+
 /*
  * Result of command
  */
@@ -496,6 +499,7 @@ do { \
 #define VMALLOC_END		(info->vmalloc_end)
 #define VMEMMAP_START		(info->vmemmap_start)
 #define VMEMMAP_END		(info->vmemmap_end)
+#define PMASK			(0x7ffffffffffff000UL)
 
 #ifdef __aarch64__
 #define CONFIG_ARM64_PGTABLE_LEVELS	2
@@ -609,15 +613,20 @@ do { \
 #define PGDIR_SIZE		(1UL << PGDIR_SHIFT)
 #define PGDIR_MASK		(~(PGDIR_SIZE - 1))
 #define PTRS_PER_PGD		(512)
+#define PGD_SHIFT		(39)
+#define PUD_SHIFT		(30)
 #define PMD_SHIFT		(21)
 #define PMD_SIZE		(1UL << PMD_SHIFT)
 #define PMD_MASK		(~(PMD_SIZE - 1))
+#define PTRS_PER_PUD		(512)
 #define PTRS_PER_PMD		(512)
 #define PTRS_PER_PTE		(512)
 #define PTE_SHIFT		(12)
 
 #define pml4_index(address) (((address) >> PML4_SHIFT) & (PTRS_PER_PML4 - 1))
 #define pgd_index(address)  (((address) >> PGDIR_SHIFT) & (PTRS_PER_PGD - 1))
+#define pgd4_index(address) (((address) >> PGD_SHIFT) & (PTRS_PER_PGD - 1))
+#define pud_index(address)  (((address) >> PUD_SHIFT) & (PTRS_PER_PUD - 1))
 #define pmd_index(address)  (((address) >> PMD_SHIFT) & (PTRS_PER_PMD - 1))
 #define pte_index(address)  (((address) >> PTE_SHIFT) & (PTRS_PER_PTE - 1))
 
@@ -783,7 +792,6 @@ do { \
 /*
  * 4 Levels paging
  */
-#define PUD_SHIFT		(PMD_SHIFT + PTRS_PER_PTD_SHIFT)
 #define PGDIR_SHIFT_4L		(PUD_SHIFT + PTRS_PER_PTD_SHIFT)
 
 #define MASK_PUD   	((1UL << REGION_SHIFT) - 1) & (~((1UL << PUD_SHIFT) - 1))
@@ -1095,6 +1103,7 @@ struct DumpInfo {
 	int		flag_use_printk_log; /* did we read printk_log symbol name? */
 	int		flag_nospace;	     /* the flag of "No space on device" error */
 	int		flag_vmemmap;        /* kernel supports vmemmap address space */
+	int		flag_excludevm;      /* -e - excluding unused vmemmap pages */
 	unsigned long	vaddr_for_vtop;      /* virtual address for debugging */
 	long		page_size;           /* size of page */
 	long		page_shift;
@@ -1686,6 +1695,51 @@ struct srcfile_table {
 	char	pud_t[LEN_SRCFILE];
 };
 
+/*
+ * This structure records where the vmemmap page structures reside, and which
+ * pfn's are represented by those page structures.
+ * The actual pages containing the page structures are 2MB pages, so their pfn's
+ * will all be multiples of 0x200.
+ * The page structures are 7 64-bit words in length (0x38) so they overlap the
+ * 2MB boundaries. Each page structure represents a 4k page.
+ * A 4k page is here defined to be represented on a 2MB page if its page structure
+ * 'ends' on that page (even if it began on the page before).
+ */
+struct vmap_pfns {
+       struct vmap_pfns *next;
+       struct vmap_pfns *prev;
+       /*
+        * These (start/end) are literal pfns of 2MB pages on which the page
+        * structures reside, not start and end+1.
+        */
+       unsigned long vmap_pfn_start;
+       unsigned long vmap_pfn_end;
+       /*
+        * These (start/end) are literal pfns represented on these pages, not
+        * start and end+1.
+        * The starting page struct is at least partly on the first page; the
+        * ending page struct is entirely on the last page.
+        */
+       unsigned long rep_pfn_start;
+       unsigned long rep_pfn_end;
+};
+
+/* for saving a list of pfns to a buffer, and then to a file if necessary */
+struct save_control {
+       int sc_fd;
+       char *sc_filename;
+       char *sc_buf;
+       long sc_buflen; /* length of buffer never changes */
+       long sc_bufposition; /* offset of next slot for write, or next to be read */
+       long sc_filelen; /* length of valid data written */
+       long sc_fileposition; /* offset in file of next entry to be read */
+};
+/* one entry in the buffer and file */
+struct sc_entry {
+       unsigned long startpfn;
+       unsigned long numpfns;
+};
+
 extern struct symbol_table	symbol_table;
 extern struct size_table	size_table;
 extern struct offset_table	offset_table;
@@ -2011,6 +2065,7 @@ struct elf_prstatus {
 #define OPT_DEBUG               'D'
 #define OPT_DUMP_LEVEL          'd'
 #define OPT_ELF_DUMPFILE        'E'
+#define OPT_EXCLUDE_UNUSED_VM	'e'
 #define OPT_FLATTEN             'F'
 #define OPT_FORCE               'f'
 #define OPT_GENERATE_VMCOREINFO 'g'
Index: code/makedumpfile.c
===================================================================
--- code.orig/makedumpfile.c
+++ code/makedumpfile.c
@@ -32,10 +32,14 @@ struct offset_table	offset_table;
 struct array_table	array_table;
 struct number_table	number_table;
 struct srcfile_table	srcfile_table;
+struct save_control	sc;
 
 struct vm_table		vt = { 0 };
 struct DumpInfo		*info = NULL;
 struct SplitBlock		*splitblock = NULL;
+struct vmap_pfns	*gvmem_pfns;
+int nr_gvmem_pfns;
+extern int find_vmemmap();
 
 char filename_stdout[] = FILENAME_STDOUT;
 
@@ -5736,6 +5740,329 @@ copy_bitmap(void)
 	}
 }
 
+/*
+ * Initialize the structure for saving pfn's to be deleted.
+ */
+int
+init_save_control()
+{
+	int flags;
+	char *filename;
+
+	filename = malloc(50);
+	*filename = '\0';
+	strcpy(filename, info->working_dir);
+	strcat(filename, "/");
+	strcat(filename, "makedumpfilepfns");
+	sc.sc_filename = filename;
+	flags = O_RDWR|O_CREAT|O_TRUNC;
+	if ((sc.sc_fd = open(sc.sc_filename, flags, S_IRUSR|S_IWUSR)) < 0) {
+		ERRMSG("Can't open the pfn file %s.\n", sc.sc_filename);
+		return FAILED;
+	}
+	unlink(sc.sc_filename);
+
+	sc.sc_buf = malloc(info->page_size);
+	if (!sc.sc_buf) {
+		ERRMSG("Can't allocate a page for pfn buf.\n");
+		return FAILED;
+	}
+	sc.sc_buflen = info->page_size;
+	sc.sc_bufposition = 0;
+	sc.sc_fileposition = 0;
+	sc.sc_filelen = 0;
+	return COMPLETED;
+}
+
+/*
+ * Save a starting pfn and number of pfns for later delete from bitmap.
+ */
+int
+save_deletes(unsigned long startpfn, unsigned long numpfns)
+{
+	int i;
+	struct sc_entry *scp;
+
+	if (sc.sc_bufposition == sc.sc_buflen) {
+		i = write(sc.sc_fd, sc.sc_buf, sc.sc_buflen);
+		if (i != sc.sc_buflen) {
+			ERRMSG("save: Can't write a page to %s\n",
+				sc.sc_filename);
+			return FAILED;
+		}
+		sc.sc_filelen += sc.sc_buflen;
+		sc.sc_bufposition = 0;
+	}
+	scp = (struct sc_entry *)(sc.sc_buf + sc.sc_bufposition);
+	scp->startpfn = startpfn;
+	scp->numpfns = numpfns;
+	sc.sc_bufposition += sizeof(struct sc_entry);
+	return COMPLETED;
+}
+
+/*
+ * Get a starting pfn and number of pfns for delete from bitmap.
+ * Return 0 for success, 1 for 'no more'
+ */
+int
+get_deletes(unsigned long *startpfn, unsigned long *numpfns)
+{
+	int i;
+	struct sc_entry *scp;
+
+	if (sc.sc_fileposition >= sc.sc_filelen) {
+		return FAILED;
+	}
+
+	if (sc.sc_bufposition == sc.sc_buflen) {
+		i = read(sc.sc_fd, sc.sc_buf, sc.sc_buflen);
+		if (i <= 0) {
+			ERRMSG("Can't read a page from %s.\n", sc.sc_filename);
+			return FAILED;
+		}
+		sc.sc_bufposition = 0;
+	}
+	scp = (struct sc_entry *)(sc.sc_buf + sc.sc_bufposition);
+	*startpfn = scp->startpfn;
+	*numpfns = scp->numpfns;
+	sc.sc_bufposition += sizeof(struct sc_entry);
+	sc.sc_fileposition += sizeof(struct sc_entry);
+	return COMPLETED;
+}
+
+/*
+ * Given a range of unused pfn's, check whether we can drop the vmemmap pages
+ * that represent them.
+ *  (pfn ranges are literally start and end, not start and end+1)
+ *   see the array of vmemmap pfns and the pfns they represent: gvmem_pfns
+ * Return COMPLETED for delete, FAILED for not to delete.
+ */
+int
+find_vmemmap_pages(unsigned long startpfn, unsigned long endpfn, unsigned long *vmappfn,
+									unsigned long *nmapnpfns)
+{
+	int i;
+	long npfns_offset, vmemmap_offset, vmemmap_pfns, start_vmemmap_pfn;
+	long npages, end_vmemmap_pfn;
+	struct vmap_pfns *vmapp;
+	int pagesize = info->page_size;
+
+	for (i = 0; i < nr_gvmem_pfns; i++) {
+		vmapp = gvmem_pfns + i;
+		if ((startpfn >= vmapp->rep_pfn_start) &&
+		    (endpfn <= vmapp->rep_pfn_end)) {
+			npfns_offset = startpfn - vmapp->rep_pfn_start;
+			vmemmap_offset = npfns_offset * size_table.page;
+			// round up to a page boundary
+			if (vmemmap_offset % pagesize)
+				vmemmap_offset += (pagesize - (vmemmap_offset % pagesize));
+			vmemmap_pfns = vmemmap_offset / pagesize;
+			start_vmemmap_pfn = vmapp->vmap_pfn_start + vmemmap_pfns;
+			*vmappfn = start_vmemmap_pfn;
+
+			npfns_offset = endpfn - vmapp->rep_pfn_start;
+			vmemmap_offset = npfns_offset * size_table.page;
+			// round down to page boundary
+			vmemmap_offset -= (vmemmap_offset % pagesize);
+			vmemmap_pfns = vmemmap_offset / pagesize;
+			end_vmemmap_pfn = vmapp->vmap_pfn_start + vmemmap_pfns;
+			npages = end_vmemmap_pfn - start_vmemmap_pfn;
+			if (npages == 0)
+				return FAILED;
+			*nmapnpfns = npages;
+			return COMPLETED;
+		}
+	}
+	return FAILED;
+}
+
+/*
+ * Find the big holes in bitmap2; they represent ranges for which
+ * we do not need page structures.
+ * Bitmap1 is a map of dumpable (i.e existing) pages.
+ * They must only be pages that exist, so they will be 0 bits
+ * in the 2nd bitmap but 1 bits in the 1st bitmap.
+ * For speed, only worry about whole words full of bits.
+ */
+int
+find_unused_vmemmap_pages(void)
+{
+	struct dump_bitmap *bitmap1 = info->bitmap1;
+	struct dump_bitmap *bitmap2 = info->bitmap2;
+	unsigned long long pfn;
+	unsigned long *lp1, *lp2, startpfn, endpfn;
+	unsigned long vmapstartpfn, vmapnumpfns;
+	int i, sz, numpages=0, did_deletes;
+	int startword, numwords, do_break=0;
+	long deleted_pages = 0;
+	off_t new_offset1, new_offset2;
+
+	/* read each block of both bitmaps */
+	for (pfn = 0; pfn < info->max_mapnr; pfn += PFN_BUFBITMAP) { /* size in bits */
+		numpages++;
+		did_deletes = 0;
+		new_offset1 = bitmap1->offset + BUFSIZE_BITMAP * (pfn / PFN_BUFBITMAP);
+		if (lseek(bitmap1->fd, new_offset1, SEEK_SET) < 0 ) {
+			ERRMSG("Can't seek the bitmap(%s). %s\n",
+				bitmap1->file_name, strerror(errno));
+			return FAILED;
+		}
+		if (read(bitmap1->fd, bitmap1->buf, BUFSIZE_BITMAP) != BUFSIZE_BITMAP) {
+			ERRMSG("Can't read the bitmap(%s). %s\n",
+				bitmap1->file_name, strerror(errno));
+			return FAILED;
+		}
+		bitmap1->no_block = pfn / PFN_BUFBITMAP;
+
+		new_offset2 = bitmap2->offset + BUFSIZE_BITMAP * (pfn / PFN_BUFBITMAP);
+		if (lseek(bitmap2->fd, new_offset2, SEEK_SET) < 0 ) {
+			ERRMSG("Can't seek the bitmap(%s). %s\n",
+				bitmap2->file_name, strerror(errno));
+			return FAILED;
+		}
+		if (read(bitmap2->fd, bitmap2->buf, BUFSIZE_BITMAP) != BUFSIZE_BITMAP) {
+			ERRMSG("Can't read the bitmap(%s). %s\n",
+				bitmap2->file_name, strerror(errno));
+			return FAILED;
+		}
+		bitmap2->no_block = pfn / PFN_BUFBITMAP;
+
+		/* process this one page of both bitmaps at a time */
+		lp1 = (unsigned long *)bitmap1->buf;
+		lp2 = (unsigned long *)bitmap2->buf;
+		/* sz is words in the block */
+		sz = BUFSIZE_BITMAP / sizeof(unsigned long);
+		startword = -1;
+		for (i = 0; i < sz; i++, lp1++, lp2++) {
+			/* for each whole word in the block */
+			/* deal in full 64-page chunks only */
+			if (*lp1 == 0xffffffffffffffffUL) {
+				if (*lp2 == 0) {
+					/* we are in a series we want */
+					if (startword == -1) {
+						/* starting a new group */
+						startword = i;
+					}
+				} else {
+					/* we hit a used page */
+					if (startword >= 0)
+						do_break = 1;
+				}
+			} else {
+				/* we hit a hole in real memory, or part of one */
+				if (startword >= 0)
+					do_break = 1;
+			}
+			if (do_break) {
+				do_break = 0;
+				if (startword >= 0) {
+					numwords = i - startword;
+					/* 64 bits represents 64 page structs, which
+ 					   are not even one page of them (takes
+					   at least 73) */
+					if (numwords > 1) {
+						startpfn = pfn +
+							(startword * BITS_PER_WORD);
+						/* pfn ranges are literally start and end,
+						   not start and end + 1 */
+						endpfn = startpfn +
+							(numwords * BITS_PER_WORD) - 1;
+						if (find_vmemmap_pages(startpfn, endpfn,
+							&vmapstartpfn, &vmapnumpfns) ==
+							COMPLETED) {
+							if (save_deletes(vmapstartpfn,
+								vmapnumpfns) == FAILED) {
+								ERRMSG("save_deletes failed\n");
+								return FAILED;
+							}
+							deleted_pages += vmapnumpfns;
+							did_deletes = 1;
+						}
+					}
+				}
+				startword = -1;
+			}
+		}
+		if (startword >= 0) {
+			numwords = i - startword;
+			if (numwords > 1) {
+				startpfn = pfn + (startword * BITS_PER_WORD);
+				/* pfn ranges are literally start and end,
+				   not start and end + 1 */
+				endpfn = startpfn + (numwords * BITS_PER_WORD) - 1;
+				if (find_vmemmap_pages(startpfn, endpfn,
+					&vmapstartpfn, &vmapnumpfns) == COMPLETED) {
+					if (save_deletes(vmapstartpfn, vmapnumpfns)
+						== FAILED) {
+						ERRMSG("save_deletes failed\n");
+						return FAILED;
+					}
+					deleted_pages += vmapnumpfns;
+					did_deletes = 1;
+				}
+			}
+		}
+	}
+	PROGRESS_MSG("\nExcluded %ld unused vmemmap pages\n", deleted_pages);
+
+	return COMPLETED;
+}
+
+/*
+ * Retrieve the list of pfn's and delete them from bitmap2;
+ */
+void
+delete_unused_vmemmap_pages(void)
+{
+	unsigned long startpfn, numpfns, pfn, i;
+
+	while (get_deletes(&startpfn, &numpfns) == COMPLETED) {
+		for (i = 0, pfn = startpfn; i < numpfns; i++, pfn++) {
+			clear_bit_on_2nd_bitmap_for_kernel(pfn, (struct cycle *)0);
+			// note that this is never to be used in cyclic mode!
+		}
+	}
+	return;
+}
+
+/*
+ * Finalize the structure for saving pfn's to be deleted.
+ */
+void
+finalize_save_control()
+{
+	free(sc.sc_buf);
+	close(sc.sc_fd);
+	return;
+}
+
+/*
+ * Reset the structure for saving pfn's to be deleted so that it can be read
+ */
+int
+reset_save_control()
+{
+	int i;
+	if (sc.sc_bufposition == 0)
+		return COMPLETED;
+
+	i = write(sc.sc_fd, sc.sc_buf, sc.sc_buflen);
+	if (i != sc.sc_buflen) {
+		ERRMSG("reset: Can't write a page to %s\n",
+			sc.sc_filename);
+		return FAILED;
+	}
+	sc.sc_filelen += sc.sc_bufposition;
+
+	if (lseek(sc.sc_fd, 0, SEEK_SET) < 0) {
+		ERRMSG("Can't seek the pfn file %s).", sc.sc_filename);
+		return FAILED;
+	}
+	sc.sc_fileposition = 0;
+	sc.sc_bufposition = sc.sc_buflen; /* trigger 1st read */
+	return COMPLETED;
+}
+
 int
 create_2nd_bitmap(struct cycle *cycle)
 {
@@ -5815,6 +6142,22 @@ create_2nd_bitmap(struct cycle *cycle)
 	if (!sync_2nd_bitmap())
 		return FALSE;
 
+#ifdef __x86_64__
+	/* --exclude-unused-vm means exclude vmemmap page structures for unused pages */
+	if (info->flag_excludevm) {
+		if (init_save_control() == FAILED)
+			return FALSE;
+		if (find_unused_vmemmap_pages() == FAILED)
+			return FALSE;
+		if (reset_save_control() == FAILED)
+			return FALSE;
+		delete_unused_vmemmap_pages();
+		finalize_save_control();
+		if (!sync_2nd_bitmap())
+			return FALSE;
+	}
+#endif
+
 	return TRUE;
 }
 
@@ -6231,6 +6574,12 @@ write_kdump_header(void)
 	dh->bitmap_blocks  = divideup(info->len_bitmap, dh->block_size);
 	memcpy(&dh->timestamp, &info->timestamp, sizeof(dh->timestamp));
 	memcpy(&dh->utsname, &info->system_utsname, sizeof(dh->utsname));
+
+#ifdef __x86_64__
+	if (info->flag_excludevm)
+		dh->status |= DUMP_DH_EXCLUDED_VMEMMAP;
+#endif
+
 	if (info->flag_compress & DUMP_DH_COMPRESSED_ZLIB)
 		dh->status |= DUMP_DH_COMPRESSED_ZLIB;
 #ifdef USELZO
@@ -9198,6 +9547,14 @@ create_dumpfile(void)
 	if (!initial())
 		return FALSE;
 
+#ifdef __x86_64__
+	/* create an array of translations from pfn to vmemmap pages */
+	if (info->flag_excludevm) {
+		if (find_vmemmap() == FAILED)
+			ERRMSG("Can't find vmemmap pages\n");
+	}
+#endif
+
 	print_vtop();
 
 	num_retry = 0;
@@ -10418,7 +10775,7 @@ main(int argc, char *argv[])
 
 	info->block_order = DEFAULT_ORDER;
 	message_level = DEFAULT_MSG_LEVEL;
-	while ((opt = getopt_long(argc, argv, "b:cDd:EFfg:hi:lpRvXx:", longopts,
+	while ((opt = getopt_long(argc, argv, "b:cDd:eEFfg:hi:lpRvXx:", longopts,
 	    NULL)) != -1) {
 		switch (opt) {
 		case OPT_BLOCK_ORDER:
@@ -10462,6 +10819,14 @@ main(int argc, char *argv[])
 			info->flag_read_vmcoreinfo = 1;
 			info->name_vmcoreinfo = optarg;
 			break;
+		case OPT_EXCLUDE_UNUSED_VM:
+#ifdef __x86_64__
+			info->flag_excludevm = 1;	/* exclude unused vmemmap pages */
+			info->flag_cyclic = FALSE;	/* force create_2nd_bitmap */
+#else
+			ERRMSG("OPT_EXCLUDE_UNUSED_VM is not supported on this architecture\n");
+#endif
+			break;
 		case OPT_DISKSET:
 			if (!sadump_add_diskset_info(optarg))
 				goto out;
@@ -10540,6 +10905,14 @@ main(int argc, char *argv[])
 	if (flag_debug)
 		message_level |= ML_PRINT_DEBUG_MSG;
 
+#ifdef __x86_64__
+	if (info->flag_excludevm && !info->working_dir) {
+		ERRMSG("Error: -%c requires --work-dir\n", OPT_EXCLUDE_UNUSED_VM);
+		ERRMSG("Try `makedumpfile --help' for more information\n");
+		return COMPLETED;
+	}
+#endif
+
 	if (info->flag_show_usage) {
 		print_usage();
 		return COMPLETED;
Index: code/diskdump_mod.h
===================================================================
--- code.orig/diskdump_mod.h
+++ code/diskdump_mod.h
@@ -97,6 +97,7 @@ struct kdump_sub_header {
 					/* paged is compressed with snappy */
 #define DUMP_DH_COMPRESSED_INCOMPLETE	0x8
 					/* indicate an incomplete dumpfile */
+#define DUMP_DH_EXCLUDED_VMEMMAP 0x10	/* unused vmemmap pages are excluded */
 
 /* descriptor of each page for vmcore */
 typedef struct page_desc {
Index: code/arch/x86_64.c
===================================================================
--- code.orig/arch/x86_64.c
+++ code/arch/x86_64.c
@@ -18,6 +18,8 @@
 #include "../print_info.h"
 #include "../elf_info.h"
 #include "../makedumpfile.h"
+extern struct vmap_pfns *gvmem_pfns;
+extern int nr_gvmem_pfns;
 
 int
 is_vmalloc_addr_x86_64(ulong vaddr)
@@ -460,5 +462,310 @@ int get_xen_info_x86_64(void)
 	return TRUE;
 }
 
+/*
+ * Scan the kernel page table for the pfn's of the page structs
+ * Place them in array gvmem_pfns[nr_gvmem_pfns]
+ */
+int
+find_vmemmap()
+{
+	int i;
+	int pgd_index, pud_index;
+	int start_range = 1;
+	int num_pmds=0, num_pmds_valid=0;
+	int break_in_valids, break_after_invalids;
+	int do_break, done = 0;
+	int last_valid=0, last_invalid=0;
+	int pagestructsize, structsperhpage, hugepagesize;
+	long page_structs_per_pud;
+	long num_puds, groups = 0;
+	long pgdindex, pudindex, pmdindex;
+	long vaddr, vaddr_base;
+	long rep_pfn_start = 0, rep_pfn_end = 0;
+	unsigned long init_level4_pgt;
+	unsigned long max_paddr, high_pfn;
+	unsigned long pgd_addr, pud_addr, pmd_addr;
+	unsigned long *pgdp, *pudp, *pmdp;
+	unsigned long pud_page[PTRS_PER_PUD];
+	unsigned long pmd_page[PTRS_PER_PMD];
+	unsigned long vmap_offset_start = 0, vmap_offset_end = 0;
+	unsigned long pmd, tpfn;
+	unsigned long pvaddr = 0;
+	unsigned long data_addr = 0, last_data_addr = 0, start_data_addr = 0;
+	/*
+	 * data_addr is the paddr of the page holding the page structs.
+	 * We keep lists of contiguous pages and the pfn's that their
+	 * page structs represent.
+	 *  start_data_addr and last_data_addr mark start/end of those
+	 *  contiguous areas.
+	 * An area descriptor is vmap start/end pfn and rep start/end
+	 *  of the pfn's represented by the vmap start/end.
+	 */
+	struct vmap_pfns *vmapp, *vmaphead = NULL, *cur, *tail;
+
+	init_level4_pgt = SYMBOL(init_level4_pgt);
+	if (init_level4_pgt == NOT_FOUND_SYMBOL) {
+		ERRMSG("init_level4_pgt not found\n");
+		return FAILED;
+	}
+	pagestructsize = size_table.page;
+	hugepagesize = PTRS_PER_PMD * info->page_size;
+	vaddr_base = info->vmemmap_start;
+	vaddr = vaddr_base;
+	max_paddr = get_max_paddr();
+	/*
+	 * the page structures are mapped at VMEMMAP_START (info->vmemmap_start)
+	 * for max_paddr >> 12 page structures
+	 */
+	high_pfn = max_paddr >> 12;
+	pgd_index = pgd4_index(vaddr_base);
+	pud_index = pud_index(vaddr_base);
+	pgd_addr = vaddr_to_paddr(init_level4_pgt); /* address of pgd */
+	pgd_addr += pgd_index * sizeof(unsigned long);
+	page_structs_per_pud = (PTRS_PER_PUD * PTRS_PER_PMD * info->page_size) /
+									pagestructsize;
+	num_puds = (high_pfn + page_structs_per_pud - 1) / page_structs_per_pud;
+	pvaddr = VMEMMAP_START;
+	structsperhpage = hugepagesize / pagestructsize;
+
+	/* outer loop is for pud entries in the pgd */
+	for (pgdindex = 0, pgdp = (unsigned long *)pgd_addr; pgdindex < num_puds;
+								pgdindex++, pgdp++) {
+		/* read the pgd one word at a time, into pud_addr */
+		if (!readmem(PADDR, (unsigned long long)pgdp, (void *)&pud_addr,
+								sizeof(unsigned long))) {
+			ERRMSG("Can't get pgd entry for slot %d.\n", pgd_index);
+			return FAILED;
+		}
+		/* mask the pgd entry for the address of the pud page */
+		pud_addr &= PMASK;
+		/* read the entire pud page */
+		if (!readmem(PADDR, (unsigned long long)pud_addr, (void *)pud_page,
+					PTRS_PER_PUD * sizeof(unsigned long))) {
+			ERRMSG("Can't get pud entry for pgd slot %ld.\n", pgdindex);
+			return FAILED;
+		}
+		/* step thru each pmd address in the pud page */
+		/* pudp points to an entry in the pud page */
+		for (pudp = (unsigned long *)pud_page, pudindex = 0;
+					pudindex < PTRS_PER_PUD; pudindex++, pudp++) {
+			pmd_addr = *pudp & PMASK;
+			/* read the entire pmd page */
+			if (!readmem(PADDR, pmd_addr, (void *)pmd_page,
+					PTRS_PER_PMD * sizeof(unsigned long))) {
+				ERRMSG("Can't get pud entry for slot %ld.\n", pudindex);
+				return FAILED;
+			}
+			/* pmdp points to an entry in the pmd */
+			for (pmdp = (unsigned long *)pmd_page, pmdindex = 0;
+					pmdindex < PTRS_PER_PMD; pmdindex++, pmdp++) {
+				/* linear page position in this page table: */
+				pmd = *pmdp;
+				num_pmds++;
+				tpfn = (pvaddr - VMEMMAP_START) /
+							pagestructsize;
+				if (tpfn >= high_pfn) {
+					done = 1;
+					break;
+				}
+				/*
+				 * vmap_offset_start:
+				 * Starting logical position in the
+				 * vmemmap array for the group stays
+				 * constant until a hole in the table
+				 * or a break in contiguousness.
+				 */
+
+				/*
+				 * Ending logical position in the
+				 * vmemmap array:
+				 */
+				vmap_offset_end += hugepagesize;
+				do_break = 0;
+				break_in_valids = 0;
+				break_after_invalids = 0;
+				/*
+				 * We want breaks either when:
+				 * - we hit a hole (invalid)
+				 * - we discontiguous page is a string of valids
+				 */
+				if (pmd) {
+					data_addr = (pmd & PMASK);
+					if (start_range) {
+						/* first-time kludge */
+						start_data_addr = data_addr;
+						last_data_addr = start_data_addr
+							 - hugepagesize;
+						start_range = 0;
+					}
+					if (last_invalid) {
+						/* end of a hole */
+						start_data_addr = data_addr;
+						last_data_addr = start_data_addr
+							 - hugepagesize;
+						/* trigger update of offset */
+						do_break = 1;
+					}
+					last_valid = 1;
+					last_invalid = 0;
+					/*
+					 * we have a gap in physical
+					 * contiguousness in the table.
+					 */
+					/* ?? consecutive holes will have
+					   same data_addr */
+					if (data_addr !=
+						last_data_addr + hugepagesize) {
+						do_break = 1;
+						break_in_valids = 1;
+					}
+					DEBUG_MSG("valid: pud %ld pmd %ld pfn %#lx"
+						" pvaddr %#lx pfns %#lx-%lx"
+						" start %#lx end %#lx\n",
+						pudindex, pmdindex,
+						data_addr >> 12,
+						pvaddr, tpfn,
+						tpfn + structsperhpage - 1,
+						vmap_offset_start,
+						vmap_offset_end);
+					num_pmds_valid++;
+					if (!(pmd & _PAGE_PSE)) {
+						printf("vmemmap pmd not huge, abort\n");
+						return FAILED;
+					}
+				} else {
+					if (last_valid) {
+						/* this a hole after some valids */
+						do_break = 1;
+						break_in_valids = 1;
+						break_after_invalids = 0;
+					}
+					last_valid = 0;
+					last_invalid = 1;
+					/*
+					 * There are holes in this sparsely
+					 * populated table; they are 2MB gaps
+					 * represented by null pmd entries.
+					 */
+					DEBUG_MSG("invalid: pud %ld pmd %ld %#lx"
+						" pfns %#lx-%lx start %#lx end"
+						" %#lx\n", pudindex, pmdindex,
+						pvaddr, tpfn,
+						tpfn + structsperhpage - 1,
+						vmap_offset_start,
+						vmap_offset_end);
+				}
+				if (do_break) {
+					/* The end of a hole is not summarized.
+					 * It must be the start of a hole or
+					 * hitting a discontiguous series.
+					 */
+					if (break_in_valids || break_after_invalids) {
+						/*
+						 * calculate that pfns
+						 * represented by the current
+						 * offset in the vmemmap.
+						 */
+						/* page struct even partly on this page */
+						rep_pfn_start = vmap_offset_start /
+							pagestructsize;
+						/* ending page struct entirely on
+ 						   this page */
+						rep_pfn_end = ((vmap_offset_end -
+							hugepagesize) / pagestructsize);
+ 						DEBUG_MSG("vmap pfns %#lx-%lx "
+							"represent pfns %#lx-%lx\n\n",
+							start_data_addr >> PAGESHIFT(),
+							last_data_addr >> PAGESHIFT(),
+							rep_pfn_start, rep_pfn_end);
+						groups++;
+						vmapp = (struct vmap_pfns *)malloc(
+								sizeof(struct vmap_pfns));
+						/* pfn of this 2MB page of page structs */
+						vmapp->vmap_pfn_start = start_data_addr
+									>> PTE_SHIFT;
+						vmapp->vmap_pfn_end = last_data_addr
+									>> PTE_SHIFT;
+						/* these (start/end) are literal pfns
+ 						 * on this page, not start and end+1 */
+						vmapp->rep_pfn_start = rep_pfn_start;
+						vmapp->rep_pfn_end = rep_pfn_end;
+
+						if (!vmaphead) {
+							vmaphead = vmapp;
+							vmapp->next = vmapp;
+							vmapp->prev = vmapp;
+						} else {
+							tail = vmaphead->prev;
+							vmaphead->prev = vmapp;
+							tail->next = vmapp;
+							vmapp->next = vmaphead;
+							vmapp->prev = tail;
+						}
+					}
+
+					/* update logical position at every break */
+					vmap_offset_start =
+						vmap_offset_end - hugepagesize;
+					start_data_addr = data_addr;
+				}
+
+				last_data_addr = data_addr;
+				pvaddr += hugepagesize;
+				/*
+				 * pvaddr is current virtual address
+				 *   eg 0xffffea0004200000 if
+				 *    vmap_offset_start is 4200000
+				 */
+			}
+		}
+		tpfn = (pvaddr - VMEMMAP_START) / pagestructsize;
+		if (tpfn >= high_pfn) {
+			done = 1;
+			break;
+		}
+	}
+	rep_pfn_start = vmap_offset_start / pagestructsize;
+	rep_pfn_end = (vmap_offset_end - hugepagesize) / pagestructsize;
+	DEBUG_MSG("vmap pfns %#lx-%lx represent pfns %#lx-%lx\n\n",
+		start_data_addr >> PAGESHIFT(), last_data_addr >> PAGESHIFT(),
+		rep_pfn_start, rep_pfn_end);
+	groups++;
+	vmapp = (struct vmap_pfns *)malloc(sizeof(struct vmap_pfns));
+	vmapp->vmap_pfn_start = start_data_addr >> PTE_SHIFT;
+	vmapp->vmap_pfn_end = last_data_addr >> PTE_SHIFT;
+	vmapp->rep_pfn_start = rep_pfn_start;
+	vmapp->rep_pfn_end = rep_pfn_end;
+	if (!vmaphead) {
+		vmaphead = vmapp;
+		vmapp->next = vmapp;
+		vmapp->prev = vmapp;
+	} else {
+		tail = vmaphead->prev;
+		vmaphead->prev = vmapp;
+		tail->next = vmapp;
+		vmapp->next = vmaphead;
+		vmapp->prev = tail;
+	}
+	DEBUG_MSG("num_pmds: %d num_pmds_valid %d\n", num_pmds, num_pmds_valid);
+
+	/* transfer the linked list to an array */
+	cur = vmaphead;
+	gvmem_pfns = (struct vmap_pfns *)malloc(sizeof(struct vmap_pfns) * groups);
+	i = 0;
+	do {
+		vmapp = gvmem_pfns + i;
+		vmapp->vmap_pfn_start = cur->vmap_pfn_start;
+		vmapp->vmap_pfn_end = cur->vmap_pfn_end;
+		vmapp->rep_pfn_start = cur->rep_pfn_start;
+		vmapp->rep_pfn_end = cur->rep_pfn_end;
+		cur = cur->next;
+		free(cur->prev);
+		i++;
+	} while (cur != vmaphead);
+	nr_gvmem_pfns = i;
+	return COMPLETED;
+}
+
 #endif /* x86_64 */
 



More information about the kexec mailing list