Hello Hatayama,
On Tue, 09 Jul 2013 14:49:48 +0900
HATAYAMA Daisuke <d.hatayama at jp.fujitsu.com> wrote:
> (2013/07/08 23:28), Vivek Goyal wrote:
> > On Mon, Jul 08, 2013 at 11:28:39AM +0200, Michael Holzheu wrote:
> >> On Mon, 08 Jul 2013 14:32:09 +0900
> >> HATAYAMA Daisuke <d.hatayama at jp.fujitsu.com> wrote:
[snip]
> > I personally perfer not to special case it for s390 only and let the
> > handler be generic.
> >
> > If there is a bug in remap_old_pfn_range(), only side affect is that
> > we will fault in the page when it is accessed and that will be slow. BUG()
> > sounds excessive. At max it could be WARN_ONCE().
> >
> > In regular cases for x86, this path should not even hit. So special casing
> > it to detect issues with remap_old_pfn_range() does not sound very good
> > to me. I would rather leave it as it is and if there are bugs and mmap()
> > slows down, then somebody needs to debug it.
> >
>
> I agree to WARN_ONCE(). Then, we can notice bug at least if it occurs.
>
> Interface is like this?
>
> [generic]
>
> bool __weak in_valid_fault_range(pgoff_t pgoff)
> {
> return false;
> }
>
> [s390]
>
> bool in_valid_fault_range(pgoff_t pgoff)
> {
> loff_t offset = pgoff << PAGE_CACHE_SHIFT;
> u64 paddr = vmcore_offset_to_paddr(offset);
>
> return paddr < ZFCPDUMP_HSA_SIZE;
> }
>
> assuming vmcore_offset_to_paddr() that looks up vmcore_list and returns physical
> address corresponding to given offset of vmcore. I guess this could return error
> value if there's no entry corresponding to given offset in vmcore_list.
I think this is too much code (and overhead) just for checking the correctness the
kdump mmap implementation.
My suggestion is to add the WARN_ONCE() for #ifndef CONFIG_S390. This has the same
effect as your suggestion for all architectures besides of s390. And for s390 we
take the risk that a programming error would result in poor /proc/vmcore
performance.
So, at least for this patch series I would implement the fault handler as follows:
static int mmap_vmcore_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
{
...
char *buf;
int rc;
#ifndef CONFIG_S390
WARN_ONCE(1, "vmcore: Unexpected call of mmap_vmcore_fault()");
#endif
page = find_or_create_page(mapping, index, GFP_KERNEL);
At this point I have to tell you that we plan another vmcore patch series where
the fault handler might be called also for other architectures. But I think we
should *then* discuss your issue again.
So in order to make progress with this patch series (which is also needed to
make your mmap patches work for s390) I would suggest to use the following patch:
---
fs/proc/vmcore.c | 90 +++++++++++++++++++++++++++++++++++++++++----
include/linux/crash_dump.h | 3 +
2 files changed, 85 insertions(+), 8 deletions(-)
--- 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 +154,35 @@ ssize_t __weak elfcorehdr_read_notes(cha
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;
+ } 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 +199,7 @@ static ssize_t read_vmcore(struct file *
/* 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 +217,7 @@ static ssize_t read_vmcore(struct file *
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 +233,7 @@ static ssize_t read_vmcore(struct file *
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 +250,54 @@ static ssize_t read_vmcore(struct file *
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.
+ *
+ * On s390 the fault handler is used for memory regions that can't be mapped
+ * directly with remap_pfn_range().
+ */
+static int mmap_vmcore_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
+{
+ struct address_space *mapping = vma->vm_file->f_mapping;
+ pgoff_t index = vmf->pgoff;
+ struct page *page;
+ loff_t offset;
+ char *buf;
+ int rc;
+
+#ifndef CONFIG_S390
+ WARN_ONCE(1, "vmcore: Unexpected call of mmap_vmcore_fault()");
+#endif
+ page = find_or_create_page(mapping, index, GFP_KERNEL);
+ if (!page)
+ return VM_FAULT_OOM;
+ if (!PageUptodate(page)) {
+ offset = (loff_t) index << PAGE_CACHE_SHIFT;
+ buf = __va((page_to_pfn(page) << PAGE_SHIFT));
+ rc = __read_vmcore(buf, PAGE_SIZE, &offset, 0);
+ if (rc < 0) {
+ unlock_page(page);
+ page_cache_release(page);
+ return (rc == -ENOMEM) ? VM_FAULT_OOM : VM_FAULT_SIGBUS;
+ }
+ SetPageUptodate(page);
+ }
+ unlock_page(page);
+ vmf->page = page;
+ return 0;
+}
+
+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 +315,7 @@ static int mmap_vmcore(struct file *file
vma->vm_flags &= ~(VM_MAYWRITE | VM_MAYEXEC);
vma->vm_flags |= VM_MIXEDMAP;
+ vma->vm_ops = &vmcore_mmap_ops;
len = 0;
@@ -283,9 +357,9 @@ static int mmap_vmcore(struct file *file
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;
--- a/include/linux/crash_dump.h
+++ b/include/linux/crash_dump.h
@@ -17,6 +17,9 @@ extern int __weak elfcorehdr_alloc(unsig
extern void __weak elfcorehdr_free(unsigned long long addr);
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,
