All of lore.kernel.org
 help / color / mirror / Atom feed
From: Michael Holzheu <holzheu@linux.vnet.ibm.com>
To: Vivek Goyal <vgoyal@redhat.com>
Cc: HATAYAMA Daisuke <d.hatayama@jp.fujitsu.com>,
	Jan Willeke <willeke@de.ibm.com>,
	Martin Schwidefsky <schwidefsky@de.ibm.com>,
	Heiko Carstens <heiko.carstens@de.ibm.com>,
	linux-kernel@vger.kernel.org, kexec@lists.infradead.org
Subject: [PATCH v5 3/5] vmcore: Introduce remap_oldmem_pfn_range()
Date: Fri,  7 Jun 2013 18:55:59 +0200	[thread overview]
Message-ID: <1370624161-2298-4-git-send-email-holzheu@linux.vnet.ibm.com> (raw)
In-Reply-To: <1370624161-2298-1-git-send-email-holzheu@linux.vnet.ibm.com>

For zfcpdump we can't map the HSA storage because it is only available
via a read interface. Therefore, for the new vmcore mmap feature we have
introduce a new mechanism to create mappings on demand.

This patch introduces a new architecture function remap_oldmem_pfn_range()
that should be used to create mappings with remap_pfn_range() for oldmem
areas that can be directly mapped. For zfcpdump this is everything besides
of the HSA memory. For the areas that are not mapped by remap_oldmem_pfn_range()
a generic vmcore a new generic vmcore fault handler mmap_vmcore_fault()
is called. This handler does the following:

* Check if /proc/vmcore page cache page is already available
* If yes:
  - Return that page
* If no:
  - Allocate new page
  - Fill page using __vmcore_read()
  - Add new page to page cache

Signed-off-by: Michael Holzheu <holzheu@linux.vnet.ibm.com>
---
 fs/proc/vmcore.c           | 94 ++++++++++++++++++++++++++++++++++++++++++----
 include/linux/crash_dump.h |  3 ++
 2 files changed, 89 insertions(+), 8 deletions(-)

diff --git a/fs/proc/vmcore.c b/fs/proc/vmcore.c
index 221f84b..259a639 100644
--- a/fs/proc/vmcore.c
+++ b/fs/proc/vmcore.c
@@ -21,6 +21,7 @@
 #include <linux/crash_dump.h>
 #include <linux/list.h>
 #include <linux/vmalloc.h>
+#include <linux/pagemap.h>
 #include <asm/uaccess.h>
 #include <asm/io.h>
 #include "internal.h"
@@ -153,11 +154,36 @@ ssize_t __weak elfcorehdr_read_notes(char *buf, size_t count, u64 *ppos)
 	return read_from_oldmem(buf, count, ppos, 0);
 }
 
+/*
+ * Architectures may override this function to map oldmem
+ */
+int __weak remap_oldmem_pfn_range(struct vm_area_struct *vma,
+				  unsigned long from, unsigned long pfn,
+				  unsigned long size, pgprot_t prot)
+{
+	return remap_pfn_range(vma, from, pfn, size, prot);
+}
+
+/*
+ * Copy to either kernel or user space
+ */
+static int copy_to(void *target, void *src, size_t size, int userbuf)
+{
+	if (userbuf) {
+		if (copy_to_user(target, src, size))
+			return -EFAULT;
+		return 0;
+	} else {
+		memcpy(target, src, size);
+		return 0;
+	}
+}
+
 /* Read from the ELF header and then the crash dump. On error, negative value is
  * returned otherwise number of bytes read are returned.
  */
-static ssize_t read_vmcore(struct file *file, char __user *buffer,
-				size_t buflen, loff_t *fpos)
+static ssize_t __read_vmcore(char *buffer, size_t buflen, loff_t *fpos,
+			     int userbuf)
 {
 	ssize_t acc = 0, tmp;
 	size_t tsz;
@@ -174,7 +200,7 @@ static ssize_t read_vmcore(struct file *file, char __user *buffer,
 	/* Read ELF core header */
 	if (*fpos < elfcorebuf_sz) {
 		tsz = min(elfcorebuf_sz - (size_t)*fpos, buflen);
-		if (copy_to_user(buffer, elfcorebuf + *fpos, tsz))
+		if (copy_to(buffer, elfcorebuf + *fpos, tsz, userbuf))
 			return -EFAULT;
 		buflen -= tsz;
 		*fpos += tsz;
@@ -192,7 +218,7 @@ static ssize_t read_vmcore(struct file *file, char __user *buffer,
 
 		tsz = min(elfcorebuf_sz + elfnotes_sz - (size_t)*fpos, buflen);
 		kaddr = elfnotes_buf + *fpos - elfcorebuf_sz;
-		if (copy_to_user(buffer, kaddr, tsz))
+		if (copy_to(buffer, kaddr, tsz, userbuf))
 			return -EFAULT;
 		buflen -= tsz;
 		*fpos += tsz;
@@ -208,7 +234,7 @@ static ssize_t read_vmcore(struct file *file, char __user *buffer,
 		if (*fpos < m->offset + m->size) {
 			tsz = min_t(size_t, m->offset + m->size - *fpos, buflen);
 			start = m->paddr + *fpos - m->offset;
-			tmp = read_from_oldmem(buffer, tsz, &start, 1);
+			tmp = read_from_oldmem(buffer, tsz, &start, userbuf);
 			if (tmp < 0)
 				return tmp;
 			buflen -= tsz;
@@ -225,6 +251,56 @@ static ssize_t read_vmcore(struct file *file, char __user *buffer,
 	return acc;
 }
 
+static ssize_t read_vmcore(struct file *file, char __user *buffer,
+			   size_t buflen, loff_t *fpos)
+{
+	return __read_vmcore(buffer, buflen, fpos, 1);
+}
+
+/*
+ * The vmcore fault handler uses the page cache and fills data using the
+ * standard __vmcore_read() function.
+ */
+static int mmap_vmcore_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
+{
+	struct address_space *mapping = vma->vm_private_data;
+	pgoff_t index = vmf->pgoff;
+	struct page *page;
+	loff_t src;
+	char *buf;
+	int rc;
+
+find_page:
+	page = find_lock_page(mapping, index);
+	if (page) {
+		unlock_page(page);
+		rc = VM_FAULT_MINOR;
+	} else {
+		page = page_cache_alloc_cold(mapping);
+		if (!page)
+			return VM_FAULT_OOM;
+		rc = add_to_page_cache_lru(page, mapping, index, GFP_KERNEL);
+		if (rc) {
+			page_cache_release(page);
+			if (rc == -EEXIST)
+				goto find_page;
+			/* Probably ENOMEM for radix tree node */
+			return VM_FAULT_OOM;
+		}
+		buf = (void *) (page_to_pfn(page) << PAGE_SHIFT);
+		src = index << PAGE_CACHE_SHIFT;
+		__read_vmcore(buf, PAGE_SIZE, &src, 0);
+		unlock_page(page);
+		rc = VM_FAULT_MAJOR;
+	}
+	vmf->page = page;
+	return rc;
+}
+
+static const struct vm_operations_struct vmcore_mmap_ops = {
+	.fault = mmap_vmcore_fault,
+};
+
 static int mmap_vmcore(struct file *file, struct vm_area_struct *vma)
 {
 	size_t size = vma->vm_end - vma->vm_start;
@@ -242,6 +318,8 @@ static int mmap_vmcore(struct file *file, struct vm_area_struct *vma)
 
 	vma->vm_flags &= ~(VM_MAYWRITE | VM_MAYEXEC);
 	vma->vm_flags |= VM_MIXEDMAP;
+	vma->vm_ops = &vmcore_mmap_ops;
+	vma->vm_private_data = file->f_mapping;
 
 	len = 0;
 
@@ -283,9 +361,9 @@ static int mmap_vmcore(struct file *file, struct vm_area_struct *vma)
 
 			tsz = min_t(size_t, m->offset + m->size - start, size);
 			paddr = m->paddr + start - m->offset;
-			if (remap_pfn_range(vma, vma->vm_start + len,
-					    paddr >> PAGE_SHIFT, tsz,
-					    vma->vm_page_prot))
+			if (remap_oldmem_pfn_range(vma, vma->vm_start + len,
+						   paddr >> PAGE_SHIFT, tsz,
+						   vma->vm_page_prot))
 				goto fail;
 			size -= tsz;
 			start += tsz;
diff --git a/include/linux/crash_dump.h b/include/linux/crash_dump.h
index dd0f434..c0818de 100644
--- a/include/linux/crash_dump.h
+++ b/include/linux/crash_dump.h
@@ -16,6 +16,9 @@ extern int __weak elfcorehdr_alloc(void);
 extern void __weak elfcorehdr_free(void);
 extern ssize_t __weak elfcorehdr_read(char *buf, size_t count, u64 *ppos);
 extern ssize_t __weak elfcorehdr_read_notes(char *buf, size_t count, u64 *ppos);
+extern int __weak remap_oldmem_pfn_range(struct vm_area_struct *vma,
+					 unsigned long from, unsigned long pfn,
+					 unsigned long size, pgprot_t prot);
 
 extern ssize_t copy_oldmem_page(unsigned long, char *, size_t,
 						unsigned long, int);
-- 
1.8.1.6


WARNING: multiple messages have this Message-ID (diff)
From: Michael Holzheu <holzheu@linux.vnet.ibm.com>
To: Vivek Goyal <vgoyal@redhat.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>,
	kexec@lists.infradead.org, Jan Willeke <willeke@de.ibm.com>,
	linux-kernel@vger.kernel.org,
	HATAYAMA Daisuke <d.hatayama@jp.fujitsu.com>,
	Martin Schwidefsky <schwidefsky@de.ibm.com>
Subject: [PATCH v5 3/5] vmcore: Introduce remap_oldmem_pfn_range()
Date: Fri,  7 Jun 2013 18:55:59 +0200	[thread overview]
Message-ID: <1370624161-2298-4-git-send-email-holzheu@linux.vnet.ibm.com> (raw)
In-Reply-To: <1370624161-2298-1-git-send-email-holzheu@linux.vnet.ibm.com>

For zfcpdump we can't map the HSA storage because it is only available
via a read interface. Therefore, for the new vmcore mmap feature we have
introduce a new mechanism to create mappings on demand.

This patch introduces a new architecture function remap_oldmem_pfn_range()
that should be used to create mappings with remap_pfn_range() for oldmem
areas that can be directly mapped. For zfcpdump this is everything besides
of the HSA memory. For the areas that are not mapped by remap_oldmem_pfn_range()
a generic vmcore a new generic vmcore fault handler mmap_vmcore_fault()
is called. This handler does the following:

* Check if /proc/vmcore page cache page is already available
* If yes:
  - Return that page
* If no:
  - Allocate new page
  - Fill page using __vmcore_read()
  - Add new page to page cache

Signed-off-by: Michael Holzheu <holzheu@linux.vnet.ibm.com>
---
 fs/proc/vmcore.c           | 94 ++++++++++++++++++++++++++++++++++++++++++----
 include/linux/crash_dump.h |  3 ++
 2 files changed, 89 insertions(+), 8 deletions(-)

diff --git a/fs/proc/vmcore.c b/fs/proc/vmcore.c
index 221f84b..259a639 100644
--- a/fs/proc/vmcore.c
+++ b/fs/proc/vmcore.c
@@ -21,6 +21,7 @@
 #include <linux/crash_dump.h>
 #include <linux/list.h>
 #include <linux/vmalloc.h>
+#include <linux/pagemap.h>
 #include <asm/uaccess.h>
 #include <asm/io.h>
 #include "internal.h"
@@ -153,11 +154,36 @@ ssize_t __weak elfcorehdr_read_notes(char *buf, size_t count, u64 *ppos)
 	return read_from_oldmem(buf, count, ppos, 0);
 }
 
+/*
+ * Architectures may override this function to map oldmem
+ */
+int __weak remap_oldmem_pfn_range(struct vm_area_struct *vma,
+				  unsigned long from, unsigned long pfn,
+				  unsigned long size, pgprot_t prot)
+{
+	return remap_pfn_range(vma, from, pfn, size, prot);
+}
+
+/*
+ * Copy to either kernel or user space
+ */
+static int copy_to(void *target, void *src, size_t size, int userbuf)
+{
+	if (userbuf) {
+		if (copy_to_user(target, src, size))
+			return -EFAULT;
+		return 0;
+	} else {
+		memcpy(target, src, size);
+		return 0;
+	}
+}
+
 /* Read from the ELF header and then the crash dump. On error, negative value is
  * returned otherwise number of bytes read are returned.
  */
-static ssize_t read_vmcore(struct file *file, char __user *buffer,
-				size_t buflen, loff_t *fpos)
+static ssize_t __read_vmcore(char *buffer, size_t buflen, loff_t *fpos,
+			     int userbuf)
 {
 	ssize_t acc = 0, tmp;
 	size_t tsz;
@@ -174,7 +200,7 @@ static ssize_t read_vmcore(struct file *file, char __user *buffer,
 	/* Read ELF core header */
 	if (*fpos < elfcorebuf_sz) {
 		tsz = min(elfcorebuf_sz - (size_t)*fpos, buflen);
-		if (copy_to_user(buffer, elfcorebuf + *fpos, tsz))
+		if (copy_to(buffer, elfcorebuf + *fpos, tsz, userbuf))
 			return -EFAULT;
 		buflen -= tsz;
 		*fpos += tsz;
@@ -192,7 +218,7 @@ static ssize_t read_vmcore(struct file *file, char __user *buffer,
 
 		tsz = min(elfcorebuf_sz + elfnotes_sz - (size_t)*fpos, buflen);
 		kaddr = elfnotes_buf + *fpos - elfcorebuf_sz;
-		if (copy_to_user(buffer, kaddr, tsz))
+		if (copy_to(buffer, kaddr, tsz, userbuf))
 			return -EFAULT;
 		buflen -= tsz;
 		*fpos += tsz;
@@ -208,7 +234,7 @@ static ssize_t read_vmcore(struct file *file, char __user *buffer,
 		if (*fpos < m->offset + m->size) {
 			tsz = min_t(size_t, m->offset + m->size - *fpos, buflen);
 			start = m->paddr + *fpos - m->offset;
-			tmp = read_from_oldmem(buffer, tsz, &start, 1);
+			tmp = read_from_oldmem(buffer, tsz, &start, userbuf);
 			if (tmp < 0)
 				return tmp;
 			buflen -= tsz;
@@ -225,6 +251,56 @@ static ssize_t read_vmcore(struct file *file, char __user *buffer,
 	return acc;
 }
 
+static ssize_t read_vmcore(struct file *file, char __user *buffer,
+			   size_t buflen, loff_t *fpos)
+{
+	return __read_vmcore(buffer, buflen, fpos, 1);
+}
+
+/*
+ * The vmcore fault handler uses the page cache and fills data using the
+ * standard __vmcore_read() function.
+ */
+static int mmap_vmcore_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
+{
+	struct address_space *mapping = vma->vm_private_data;
+	pgoff_t index = vmf->pgoff;
+	struct page *page;
+	loff_t src;
+	char *buf;
+	int rc;
+
+find_page:
+	page = find_lock_page(mapping, index);
+	if (page) {
+		unlock_page(page);
+		rc = VM_FAULT_MINOR;
+	} else {
+		page = page_cache_alloc_cold(mapping);
+		if (!page)
+			return VM_FAULT_OOM;
+		rc = add_to_page_cache_lru(page, mapping, index, GFP_KERNEL);
+		if (rc) {
+			page_cache_release(page);
+			if (rc == -EEXIST)
+				goto find_page;
+			/* Probably ENOMEM for radix tree node */
+			return VM_FAULT_OOM;
+		}
+		buf = (void *) (page_to_pfn(page) << PAGE_SHIFT);
+		src = index << PAGE_CACHE_SHIFT;
+		__read_vmcore(buf, PAGE_SIZE, &src, 0);
+		unlock_page(page);
+		rc = VM_FAULT_MAJOR;
+	}
+	vmf->page = page;
+	return rc;
+}
+
+static const struct vm_operations_struct vmcore_mmap_ops = {
+	.fault = mmap_vmcore_fault,
+};
+
 static int mmap_vmcore(struct file *file, struct vm_area_struct *vma)
 {
 	size_t size = vma->vm_end - vma->vm_start;
@@ -242,6 +318,8 @@ static int mmap_vmcore(struct file *file, struct vm_area_struct *vma)
 
 	vma->vm_flags &= ~(VM_MAYWRITE | VM_MAYEXEC);
 	vma->vm_flags |= VM_MIXEDMAP;
+	vma->vm_ops = &vmcore_mmap_ops;
+	vma->vm_private_data = file->f_mapping;
 
 	len = 0;
 
@@ -283,9 +361,9 @@ static int mmap_vmcore(struct file *file, struct vm_area_struct *vma)
 
 			tsz = min_t(size_t, m->offset + m->size - start, size);
 			paddr = m->paddr + start - m->offset;
-			if (remap_pfn_range(vma, vma->vm_start + len,
-					    paddr >> PAGE_SHIFT, tsz,
-					    vma->vm_page_prot))
+			if (remap_oldmem_pfn_range(vma, vma->vm_start + len,
+						   paddr >> PAGE_SHIFT, tsz,
+						   vma->vm_page_prot))
 				goto fail;
 			size -= tsz;
 			start += tsz;
diff --git a/include/linux/crash_dump.h b/include/linux/crash_dump.h
index dd0f434..c0818de 100644
--- a/include/linux/crash_dump.h
+++ b/include/linux/crash_dump.h
@@ -16,6 +16,9 @@ extern int __weak elfcorehdr_alloc(void);
 extern void __weak elfcorehdr_free(void);
 extern ssize_t __weak elfcorehdr_read(char *buf, size_t count, u64 *ppos);
 extern ssize_t __weak elfcorehdr_read_notes(char *buf, size_t count, u64 *ppos);
+extern int __weak remap_oldmem_pfn_range(struct vm_area_struct *vma,
+					 unsigned long from, unsigned long pfn,
+					 unsigned long size, pgprot_t prot);
 
 extern ssize_t copy_oldmem_page(unsigned long, char *, size_t,
 						unsigned long, int);
-- 
1.8.1.6


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

  parent reply	other threads:[~2013-06-07 16:56 UTC|newest]

Thread overview: 68+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2013-06-07 16:55 [PATCH v5 0/5] kdump: Allow ELF header creation in new kernel Michael Holzheu
2013-06-07 16:55 ` Michael Holzheu
2013-06-07 16:55 ` [PATCH v5 1/5] vmcore: Introduce ELF header in new memory feature Michael Holzheu
2013-06-07 16:55   ` Michael Holzheu
2013-06-10 13:35   ` HATAYAMA Daisuke
2013-06-10 13:35     ` HATAYAMA Daisuke
2013-06-10 13:53     ` Michael Holzheu
2013-06-10 13:53       ` Michael Holzheu
2013-06-14 18:54   ` Vivek Goyal
2013-06-14 18:54     ` Vivek Goyal
2013-06-21 14:17     ` Michael Holzheu
2013-06-21 14:17       ` Michael Holzheu
2013-06-27 19:32       ` Vivek Goyal
2013-06-27 19:32         ` Vivek Goyal
2013-06-27 20:10         ` Cliff Wickman
2013-06-27 20:10           ` Cliff Wickman
2013-06-27 20:23         ` Vivek Goyal
2013-06-27 20:23           ` Vivek Goyal
2013-06-28  8:15           ` Michael Holzheu
2013-06-28  8:15             ` Michael Holzheu
2013-07-01 17:37             ` Vivek Goyal
2013-07-01 17:37               ` Vivek Goyal
2013-07-01 18:29               ` Michael Holzheu
2013-07-01 18:29                 ` Michael Holzheu
2013-06-07 16:55 ` [PATCH v5 2/5] s390/vmcore: Use " Michael Holzheu
2013-06-07 16:55   ` Michael Holzheu
2013-06-10 13:36   ` HATAYAMA Daisuke
2013-06-10 13:36     ` HATAYAMA Daisuke
2013-06-10 13:48     ` Michael Holzheu
2013-06-10 13:48       ` Michael Holzheu
2013-06-14 19:16   ` Vivek Goyal
2013-06-14 19:16     ` Vivek Goyal
2013-06-07 16:55 ` Michael Holzheu [this message]
2013-06-07 16:55   ` [PATCH v5 3/5] vmcore: Introduce remap_oldmem_pfn_range() Michael Holzheu
     [not found]   ` <CAJGZr0+_W0dp2f9VtVAiUT2fqiwe91gHXd9zYzfMMzBZSZogww@mail.gmail.com>
2013-06-10  8:00     ` Michael Holzheu
2013-06-10  8:00       ` Michael Holzheu
2013-06-10 13:40   ` HATAYAMA Daisuke
2013-06-10 13:40     ` HATAYAMA Daisuke
2013-06-10 14:03     ` Michael Holzheu
2013-06-10 14:03       ` Michael Holzheu
2013-06-10 15:37     ` Michael Holzheu
2013-06-10 15:37       ` Michael Holzheu
2013-06-11 12:42       ` HATAYAMA Daisuke
2013-06-11 12:42         ` HATAYAMA Daisuke
2013-06-12  9:13         ` Michael Holzheu
2013-06-12  9:13           ` Michael Holzheu
2013-06-13  1:32           ` HATAYAMA Daisuke
2013-06-13  1:32             ` HATAYAMA Daisuke
2013-06-13  8:54             ` Michael Holzheu
2013-06-13  8:54               ` Michael Holzheu
2013-06-13  4:00           ` HATAYAMA Daisuke
2013-06-13  4:00             ` HATAYAMA Daisuke
2013-06-11 13:20       ` HATAYAMA Daisuke
2013-06-11 13:20         ` HATAYAMA Daisuke
2013-06-07 16:56 ` [PATCH v5 4/5] s390/vmcore: Implement remap_oldmem_pfn_range for s390 Michael Holzheu
2013-06-07 16:56   ` Michael Holzheu
2013-06-14 20:08   ` Vivek Goyal
2013-06-14 20:08     ` Vivek Goyal
2013-06-07 16:56 ` [PATCH v5 5/5] s390/vmcore: Use vmcore for zfcpdump Michael Holzheu
2013-06-07 16:56   ` Michael Holzheu
2013-06-11 23:47   ` HATAYAMA Daisuke
2013-06-11 23:47     ` HATAYAMA Daisuke
2013-06-12  9:14     ` Michael Holzheu
2013-06-12  9:14       ` Michael Holzheu
2013-06-14 18:54 ` [PATCH v5 0/5] kdump: Allow ELF header creation in new kernel Vivek Goyal
2013-06-14 18:54   ` Vivek Goyal
2013-06-21 13:39   ` Michael Holzheu
2013-06-21 13:39     ` Michael Holzheu

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=1370624161-2298-4-git-send-email-holzheu@linux.vnet.ibm.com \
    --to=holzheu@linux.vnet.ibm.com \
    --cc=d.hatayama@jp.fujitsu.com \
    --cc=heiko.carstens@de.ibm.com \
    --cc=kexec@lists.infradead.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=schwidefsky@de.ibm.com \
    --cc=vgoyal@redhat.com \
    --cc=willeke@de.ibm.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.