All of lore.kernel.org
 help / color / mirror / Atom feed
From: HATAYAMA Daisuke <d.hatayama@jp.fujitsu.com>
To: ebiederm@xmission.com, vgoyal@redhat.com, cpw@sgi.com,
	kumagai-atsushi@mxc.nes.nec.co.jp, lisa.mitchell@hp.com
Cc: kexec@lists.infradead.org, linux-kernel@vger.kernel.org
Subject: [PATCH 12/13] vmcore: copy non page-size aligned head and tail pages in 2nd kernel
Date: Thu, 14 Feb 2013 19:12:48 +0900	[thread overview]
Message-ID: <20130214101248.22466.53004.stgit@localhost6.localdomain6> (raw)
In-Reply-To: <20130214100945.22466.4172.stgit@localhost6.localdomain6>

Due to mmap() requirement, we need to copy pages not starting or
ending with page-size aligned address in 2nd kernel and to map them to
user-space.

For example, see the map below:

    00000000-0001ffff : reserved
    00010000-0009f7ff : System RAM
    0009f800-0009ffff : reserved

where the System RAM ends with 0x9f800 that is not page-size
aligned. This map is divided into two parts:

    00010000-0009dfff
    0009f000-0009f7ff

and the first one is kept in old memory and the 2nd one is copied into
buffer on 2nd kernel.

This kind of non-page-size-aligned area can always occur since any
part of System RAM can be converted into reserved area at runtime.

If not doing copying like this and if remapping non page-size aligned
pages on old memory directly, mmap() had to export memory which is not
dump target to user-space. In the above example this is reserved
0x9f800-0xa0000.

Signed-off-by: HATAYAMA Daisuke <d.hatayama@jp.fujitsu.com>
---

 fs/proc/vmcore.c |   97 ++++++++++++++++++++++++++++++++++++++++++++++++------
 1 files changed, 87 insertions(+), 10 deletions(-)

diff --git a/fs/proc/vmcore.c b/fs/proc/vmcore.c
index 2968e5a..99f5673 100644
--- a/fs/proc/vmcore.c
+++ b/fs/proc/vmcore.c
@@ -446,11 +446,10 @@ static int __init process_ptload_program_headers_elf64(char *elfptr,
 						size_t elfsz,
 						struct list_head *vc_list)
 {
-	int i;
+	int i, rc;
 	Elf64_Ehdr *ehdr_ptr;
 	Elf64_Phdr *phdr_ptr;
 	loff_t vmcore_off;
-	struct vmcore *new;
 
 	ehdr_ptr = (Elf64_Ehdr *)elfptr;
 	phdr_ptr = (Elf64_Phdr*)(elfptr + sizeof(Elf64_Ehdr)); /* PT_NOTE hdr */
@@ -460,20 +459,98 @@ static int __init process_ptload_program_headers_elf64(char *elfptr,
 						  PAGE_SIZE);
 
 	for (i = 0; i < ehdr_ptr->e_phnum; i++, phdr_ptr++) {
+		u64 start, end, rest;
+
 		if (phdr_ptr->p_type != PT_LOAD)
 			continue;
 
-		/* Add this contiguous chunk of memory to vmcore list.*/
-		new = get_new_element();
-		if (!new)
-			return -ENOMEM;
-		new->paddr = phdr_ptr->p_offset;
-		new->size = phdr_ptr->p_memsz;
-		list_add_tail(&new->list, vc_list);
+		start = phdr_ptr->p_offset;
+		end = phdr_ptr->p_offset + phdr_ptr->p_memsz;
+		rest = phdr_ptr->p_memsz;
+
+		if (start & ~PAGE_MASK) {
+			u64 paddr, len;
+			char *buf;
+			struct vmcore *new;
+
+			paddr = start;
+			len = min(roundup(start,PAGE_SIZE), end) - start;
+
+			buf = (char *)get_zeroed_page(GFP_KERNEL);
+			if (!buf)
+				return -ENOMEM;
+			rc = read_from_oldmem(buf + (start & ~PAGE_MASK), len,
+					      &paddr, 0);
+			if (rc < 0) {
+				free_pages((unsigned long)buf, 0);
+				return rc;
+			}
+
+			new = get_new_element();
+			if (!new) {
+				free_pages((unsigned long)buf, 0);
+				return -ENOMEM;
+			}
+			new->type = VMCORE_2ND_KERNEL;
+			new->size = PAGE_SIZE;
+			new->buf = buf;
+			list_add_tail(&new->list, vc_list);
+
+			rest -= len;
+		}
+
+		if (rest > 0 &&
+		    roundup(start, PAGE_SIZE) < rounddown(end, PAGE_SIZE)) {
+			u64 paddr, len;
+			struct vmcore *new;
+
+			paddr = roundup(start, PAGE_SIZE);
+			len =rounddown(end,PAGE_SIZE)-roundup(start,PAGE_SIZE);
+
+			new = get_new_element();
+			if (!new)
+				return -ENOMEM;
+			new->type = VMCORE_OLD_MEMORY;
+			new->paddr = paddr;
+			new->size = len;
+			list_add_tail(&new->list, vc_list);
+
+			rest -= new->size;
+		}
+
+		if (rest > 0) {
+			u64 paddr, len;
+			char *buf;
+			struct vmcore *new;
+
+			paddr = rounddown(end, PAGE_SIZE);
+			len = end - rounddown(end, PAGE_SIZE);
+
+			buf = (char *)get_zeroed_page(GFP_KERNEL);
+			if (!buf)
+				return -ENOMEM;
+			rc = read_from_oldmem(buf, len, &paddr, 0);
+			if (rc < 0) {
+				free_pages((unsigned long)buf, 0);
+				return rc;
+			}
+
+			new = get_new_element();
+			if (!new) {
+				free_pages((unsigned long)buf, 0);
+				return -ENOMEM;
+			}
+			new->type = VMCORE_2ND_KERNEL;
+			new->size = PAGE_SIZE;
+			new->buf = buf;
+			list_add_tail(&new->list, vc_list);
+
+			rest -= len;
+		}
 
 		/* Update the program header offset. */
 		phdr_ptr->p_offset = vmcore_off;
-		vmcore_off = vmcore_off + phdr_ptr->p_memsz;
+		vmcore_off +=roundup(end,PAGE_SIZE)-rounddown(start,PAGE_SIZE);
 	}
 	return 0;
 }


WARNING: multiple messages have this Message-ID (diff)
From: HATAYAMA Daisuke <d.hatayama@jp.fujitsu.com>
To: ebiederm@xmission.com, vgoyal@redhat.com, cpw@sgi.com,
	kumagai-atsushi@mxc.nes.nec.co.jp, lisa.mitchell@hp.com
Cc: kexec@lists.infradead.org, linux-kernel@vger.kernel.org
Subject: [PATCH 12/13] vmcore: copy non page-size aligned head and tail pages in 2nd kernel
Date: Thu, 14 Feb 2013 19:12:48 +0900	[thread overview]
Message-ID: <20130214101248.22466.53004.stgit@localhost6.localdomain6> (raw)
In-Reply-To: <20130214100945.22466.4172.stgit@localhost6.localdomain6>

Due to mmap() requirement, we need to copy pages not starting or
ending with page-size aligned address in 2nd kernel and to map them to
user-space.

For example, see the map below:

    00000000-0001ffff : reserved
    00010000-0009f7ff : System RAM
    0009f800-0009ffff : reserved

where the System RAM ends with 0x9f800 that is not page-size
aligned. This map is divided into two parts:

    00010000-0009dfff
    0009f000-0009f7ff

and the first one is kept in old memory and the 2nd one is copied into
buffer on 2nd kernel.

This kind of non-page-size-aligned area can always occur since any
part of System RAM can be converted into reserved area at runtime.

If not doing copying like this and if remapping non page-size aligned
pages on old memory directly, mmap() had to export memory which is not
dump target to user-space. In the above example this is reserved
0x9f800-0xa0000.

Signed-off-by: HATAYAMA Daisuke <d.hatayama@jp.fujitsu.com>
---

 fs/proc/vmcore.c |   97 ++++++++++++++++++++++++++++++++++++++++++++++++------
 1 files changed, 87 insertions(+), 10 deletions(-)

diff --git a/fs/proc/vmcore.c b/fs/proc/vmcore.c
index 2968e5a..99f5673 100644
--- a/fs/proc/vmcore.c
+++ b/fs/proc/vmcore.c
@@ -446,11 +446,10 @@ static int __init process_ptload_program_headers_elf64(char *elfptr,
 						size_t elfsz,
 						struct list_head *vc_list)
 {
-	int i;
+	int i, rc;
 	Elf64_Ehdr *ehdr_ptr;
 	Elf64_Phdr *phdr_ptr;
 	loff_t vmcore_off;
-	struct vmcore *new;
 
 	ehdr_ptr = (Elf64_Ehdr *)elfptr;
 	phdr_ptr = (Elf64_Phdr*)(elfptr + sizeof(Elf64_Ehdr)); /* PT_NOTE hdr */
@@ -460,20 +459,98 @@ static int __init process_ptload_program_headers_elf64(char *elfptr,
 						  PAGE_SIZE);
 
 	for (i = 0; i < ehdr_ptr->e_phnum; i++, phdr_ptr++) {
+		u64 start, end, rest;
+
 		if (phdr_ptr->p_type != PT_LOAD)
 			continue;
 
-		/* Add this contiguous chunk of memory to vmcore list.*/
-		new = get_new_element();
-		if (!new)
-			return -ENOMEM;
-		new->paddr = phdr_ptr->p_offset;
-		new->size = phdr_ptr->p_memsz;
-		list_add_tail(&new->list, vc_list);
+		start = phdr_ptr->p_offset;
+		end = phdr_ptr->p_offset + phdr_ptr->p_memsz;
+		rest = phdr_ptr->p_memsz;
+
+		if (start & ~PAGE_MASK) {
+			u64 paddr, len;
+			char *buf;
+			struct vmcore *new;
+
+			paddr = start;
+			len = min(roundup(start,PAGE_SIZE), end) - start;
+
+			buf = (char *)get_zeroed_page(GFP_KERNEL);
+			if (!buf)
+				return -ENOMEM;
+			rc = read_from_oldmem(buf + (start & ~PAGE_MASK), len,
+					      &paddr, 0);
+			if (rc < 0) {
+				free_pages((unsigned long)buf, 0);
+				return rc;
+			}
+
+			new = get_new_element();
+			if (!new) {
+				free_pages((unsigned long)buf, 0);
+				return -ENOMEM;
+			}
+			new->type = VMCORE_2ND_KERNEL;
+			new->size = PAGE_SIZE;
+			new->buf = buf;
+			list_add_tail(&new->list, vc_list);
+
+			rest -= len;
+		}
+
+		if (rest > 0 &&
+		    roundup(start, PAGE_SIZE) < rounddown(end, PAGE_SIZE)) {
+			u64 paddr, len;
+			struct vmcore *new;
+
+			paddr = roundup(start, PAGE_SIZE);
+			len =rounddown(end,PAGE_SIZE)-roundup(start,PAGE_SIZE);
+
+			new = get_new_element();
+			if (!new)
+				return -ENOMEM;
+			new->type = VMCORE_OLD_MEMORY;
+			new->paddr = paddr;
+			new->size = len;
+			list_add_tail(&new->list, vc_list);
+
+			rest -= new->size;
+		}
+
+		if (rest > 0) {
+			u64 paddr, len;
+			char *buf;
+			struct vmcore *new;
+
+			paddr = rounddown(end, PAGE_SIZE);
+			len = end - rounddown(end, PAGE_SIZE);
+
+			buf = (char *)get_zeroed_page(GFP_KERNEL);
+			if (!buf)
+				return -ENOMEM;
+			rc = read_from_oldmem(buf, len, &paddr, 0);
+			if (rc < 0) {
+				free_pages((unsigned long)buf, 0);
+				return rc;
+			}
+
+			new = get_new_element();
+			if (!new) {
+				free_pages((unsigned long)buf, 0);
+				return -ENOMEM;
+			}
+			new->type = VMCORE_2ND_KERNEL;
+			new->size = PAGE_SIZE;
+			new->buf = buf;
+			list_add_tail(&new->list, vc_list);
+
+			rest -= len;
+		}
 
 		/* Update the program header offset. */
 		phdr_ptr->p_offset = vmcore_off;
-		vmcore_off = vmcore_off + phdr_ptr->p_memsz;
+		vmcore_off +=roundup(end,PAGE_SIZE)-rounddown(start,PAGE_SIZE);
 	}
 	return 0;
 }


_______________________________________________
kexec mailing list
kexec@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/kexec

  parent reply	other threads:[~2013-02-14 10:13 UTC|newest]

Thread overview: 66+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2013-02-14 10:11 [PATCH 00/13] kdump, vmcore: support mmap() on /proc/vmcore HATAYAMA Daisuke
2013-02-14 10:11 ` HATAYAMA Daisuke
2013-02-14 10:11 ` [PATCH 01/13] vmcore: allocate buffer for ELF headers on page-size alignment HATAYAMA Daisuke
2013-02-14 10:11   ` HATAYAMA Daisuke
2013-02-15 15:01   ` Vivek Goyal
2013-02-15 15:01     ` Vivek Goyal
2013-02-14 10:11 ` [PATCH 02/13] vmcore: round up buffer size of ELF headers by PAGE_SIZE HATAYAMA Daisuke
2013-02-14 10:11   ` HATAYAMA Daisuke
2013-02-15 15:18   ` Vivek Goyal
2013-02-15 15:18     ` Vivek Goyal
2013-02-18 15:58     ` HATAYAMA Daisuke
2013-02-18 15:58       ` HATAYAMA Daisuke
2013-02-14 10:11 ` [PATCH 03/13] vmcore: fill unused part of buffer for ELF headers with 0 HATAYAMA Daisuke
2013-02-14 10:11   ` HATAYAMA Daisuke
2013-02-14 10:12 ` [PATCH 04/13] vmcore: introduce types for objects copied in 2nd kernel HATAYAMA Daisuke
2013-02-14 10:12   ` HATAYAMA Daisuke
2013-02-15 15:28   ` Vivek Goyal
2013-02-15 15:28     ` Vivek Goyal
2013-02-18 16:06     ` HATAYAMA Daisuke
2013-02-18 16:06       ` HATAYAMA Daisuke
2013-02-19 23:07       ` Vivek Goyal
2013-02-19 23:07         ` Vivek Goyal
2013-02-14 10:12 ` [PATCH 05/13] vmcore: modify ELF32 code according to new type HATAYAMA Daisuke
2013-02-14 10:12   ` HATAYAMA Daisuke
2013-02-15 15:30   ` Vivek Goyal
2013-02-15 15:30     ` Vivek Goyal
2013-02-18 16:11     ` HATAYAMA Daisuke
2013-02-18 16:11       ` HATAYAMA Daisuke
2013-02-14 10:12 ` [PATCH 06/13] vmcore: modify vmcore clean-up function to free buffer on 2nd kernel HATAYAMA Daisuke
2013-02-14 10:12   ` HATAYAMA Daisuke
2013-02-15 15:32   ` Vivek Goyal
2013-02-15 15:32     ` Vivek Goyal
2013-02-14 10:12 ` [PATCH 07/13] vmcore: modify read_vmcore() to read " HATAYAMA Daisuke
2013-02-14 10:12   ` HATAYAMA Daisuke
2013-02-15 15:51   ` Vivek Goyal
2013-02-15 15:51     ` Vivek Goyal
2013-02-14 10:12 ` [PATCH 08/13] vmcore: remove unused helper function HATAYAMA Daisuke
2013-02-14 10:12   ` HATAYAMA Daisuke
2013-02-15 15:52   ` Vivek Goyal
2013-02-15 15:52     ` Vivek Goyal
2013-02-14 10:12 ` [PATCH 09/13] vmcore: copy ELF note segments in buffer on 2nd kernel HATAYAMA Daisuke
2013-02-14 10:12   ` HATAYAMA Daisuke
2013-02-15 16:53   ` Vivek Goyal
2013-02-15 16:53     ` Vivek Goyal
2013-02-18 17:02     ` HATAYAMA Daisuke
2013-02-18 17:02       ` HATAYAMA Daisuke
2013-02-19 23:05       ` Vivek Goyal
2013-02-19 23:05         ` Vivek Goyal
2013-02-14 10:12 ` [PATCH 10/13] vmcore: round-up offset of vmcore object in page-size boundary HATAYAMA Daisuke
2013-02-14 10:12   ` HATAYAMA Daisuke
2013-02-14 10:12 ` [PATCH 11/13] vmcore: count holes generated by round-up operation for vmcore size HATAYAMA Daisuke
2013-02-14 10:12   ` HATAYAMA Daisuke
2013-02-14 10:12 ` HATAYAMA Daisuke [this message]
2013-02-14 10:12   ` [PATCH 12/13] vmcore: copy non page-size aligned head and tail pages in 2nd kernel HATAYAMA Daisuke
2013-02-14 10:12 ` [PATCH 13/13] vmcore: introduce mmap_vmcore() HATAYAMA Daisuke
2013-02-14 10:12   ` HATAYAMA Daisuke
2013-02-15  3:57 ` [PATCH 00/13] kdump, vmcore: support mmap() on /proc/vmcore Atsushi Kumagai
2013-02-15  3:57   ` Atsushi Kumagai
2013-02-18  0:16   ` Hatayama, Daisuke
2013-02-18  0:16     ` Hatayama, Daisuke
2013-03-27  5:51 ` makedumpfile mmap() benchmark Jingbai Ma
2013-03-27  5:51   ` Jingbai Ma
2013-03-27  6:23   ` HATAYAMA Daisuke
2013-03-27  6:23     ` HATAYAMA Daisuke
2013-03-27  6:35     ` Jingbai Ma
2013-03-27  6:35       ` Jingbai Ma

Reply instructions:

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

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

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

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

  git send-email \
    --in-reply-to=20130214101248.22466.53004.stgit@localhost6.localdomain6 \
    --to=d.hatayama@jp.fujitsu.com \
    --cc=cpw@sgi.com \
    --cc=ebiederm@xmission.com \
    --cc=kexec@lists.infradead.org \
    --cc=kumagai-atsushi@mxc.nes.nec.co.jp \
    --cc=linux-kernel@vger.kernel.org \
    --cc=lisa.mitchell@hp.com \
    --cc=vgoyal@redhat.com \
    /path/to/YOUR_REPLY

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

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.