The patch titled
Subject: fs/proc/vmcore.c:mmap_vmcore: skip non-ram pages reported by hypervisors
has been added to the -mm tree. Its filename is
mmap_vmcore-skip-non-ram-pages-reported-by-hypervisors.patch
This patch should soon appear at
http://ozlabs.org/~akpm/mmots/broken-out/mmap_vmcore-skip-non-ram-pages-reported-by-hypervisors.patch
and later at
http://ozlabs.org/~akpm/mmotm/broken-out/mmap_vmcore-skip-non-ram-pages-reported-by-hypervisors.patch
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/SubmitChecklist when testing your code ***
The -mm tree is included into linux-next and is updated
there every 3-4 working days
------------------------------------------------------
From: Vitaly Kuznetsov <vkuznets@xxxxxxxxxx>
Subject: fs/proc/vmcore.c:mmap_vmcore: skip non-ram pages reported by hypervisors
We have a special check in read_vmcore() handler to check if the page was
reported as ram or not by the hypervisor (pfn_is_ram()). However, when
vmcore is read with mmap() no such check is performed. That can lead to
unpredictable results, e.g. when running Xen PVHVM guest memcpy() after
mmap() on /proc/vmcore will hang processing HVMMEM_mmio_dm pages creating
enormous load in both DomU and Dom0.
Fix the issue by mapping each non-ram page to the zero page. Keep direct
path with remap_oldmem_pfn_range() to avoid looping through all pages on
bare metal.
The issue can also be solved by overriding remap_oldmem_pfn_range() in
xen-specific code, as remap_oldmem_pfn_range() was been designed for.
That, however, would involve non-obvious xen code path for all x86 builds
with CONFIG_XEN_PVHVM=y and would prevent all other hypervisor-specific
code on x86 arch from doing the same override.
Signed-off-by: Vitaly Kuznetsov <vkuznets@xxxxxxxxxx>
Reviewed-by: Andrew Jones <drjones@xxxxxxxxxx>
Cc: Michael Holzheu <holzheu@xxxxxxxxxxxxxxxxxx>
Cc: Vivek Goyal <vgoyal@xxxxxxxxxx>
Cc: David Vrabel <david.vrabel@xxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
fs/proc/vmcore.c | 89 ++++++++++++++++++++++++++++++++++++++++++---
1 file changed, 84 insertions(+), 5 deletions(-)
diff -puN fs/proc/vmcore.c~mmap_vmcore-skip-non-ram-pages-reported-by-hypervisors fs/proc/vmcore.c
--- a/fs/proc/vmcore.c~mmap_vmcore-skip-non-ram-pages-reported-by-hypervisors
+++ a/fs/proc/vmcore.c
@@ -328,6 +328,67 @@ static inline char *alloc_elfnotes_buf(s
* virtually contiguous user-space in ELF layout.
*/
#ifdef CONFIG_MMU
+/*
+ * remap_oldmem_pfn_checked - do remap_oldmem_pfn replacing all pages reported
+ * as not being ram with the zero page.
+ *
+ * @vma: vm_area_struct describing requested mapping
+ * @vma_addr: start remapping from
+ * @pfn: page frame number to start remapping to
+ * @size: remapping size
+ *
+ * Returns the remapped length. If no errors were hit during the remapping it
+ * should be equal to size.
+ */
+static u64 remap_oldmem_pfn_checked(struct vm_area_struct *vma,
+ unsigned long vma_addr, unsigned long pfn,
+ unsigned long size)
+{
+ size_t map_size;
+ unsigned long pos_start, pos_end, pos;
+ unsigned long zeropage_pfn = my_zero_pfn(0);
+ u64 len = 0;
+
+ pos_start = pfn;
+ pos_end = pfn + (size >> PAGE_SHIFT);
+
+ for (pos = pos_start; pos < pos_end; ++pos) {
+ if (!pfn_is_ram(pos)) {
+ /* We hit a page which is not ram. Remap the continuous
+ * region between pos_start and pos-1 and replace
+ * the non-ram page at pos with the zero page.
+ */
+ if (pos > pos_start) {
+ /* Remap continuous region */
+ map_size = (pos - pos_start) << PAGE_SHIFT;
+ if (remap_oldmem_pfn_range(vma, vma_addr + len,
+ pos_start, map_size,
+ vma->vm_page_prot))
+ return len;
+ len += map_size;
+ }
+ /* Remap the zero page */
+ if (remap_oldmem_pfn_range(vma, vma_addr + len,
+ zeropage_pfn,
+ PAGE_SIZE,
+ vma->vm_page_prot))
+ return len;
+ len += PAGE_SIZE;
+ pos_start = pos + 1;
+ }
+ }
+ if (pos > pos_start) {
+ /* Remap the rest */
+ map_size = (pos - pos_start) << PAGE_SHIFT;
+ if (remap_oldmem_pfn_range(vma, vma_addr + len, pos_start,
+ map_size,
+ vma->vm_page_prot))
+ return len;
+ len += map_size;
+ }
+ return len;
+}
+
static int mmap_vmcore(struct file *file, struct vm_area_struct *vma)
{
size_t size = vma->vm_end - vma->vm_start;
@@ -387,13 +448,31 @@ 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_oldmem_pfn_range(vma, vma->vm_start + len,
- paddr >> PAGE_SHIFT, tsz,
- vma->vm_page_prot))
- goto fail;
+
+ /* Check if oldmem_pfn_is_ram was registered to avoid
+ looping over all pages without a reason. */
+ if (oldmem_pfn_is_ram) {
+ u64 original_len;
+ unsigned long pfn, vma_addr;
+
+ pfn = paddr >> PAGE_SHIFT;
+ vma_addr = vma->vm_start + len;
+ original_len = len;
+ len += remap_oldmem_pfn_checked(vma, vma_addr,
+ pfn, tsz);
+ if (len != original_len + tsz)
+ goto fail;
+ } else {
+ if (remap_oldmem_pfn_range(vma,
+ vma->vm_start + len,
+ paddr >> PAGE_SHIFT,
+ tsz,
+ vma->vm_page_prot))
+ goto fail;
+ len += tsz;
+ }
size -= tsz;
start += tsz;
- len += tsz;
if (size == 0)
return 0;
_
Patches currently in -mm which might be from vkuznets@xxxxxxxxxx are
mmap_vmcore-skip-non-ram-pages-reported-by-hypervisors.patch
--
To unsubscribe from this list: send the line "unsubscribe mm-commits" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
