@@ -375,6 +375,22 @@ static int __init_refok get_nid_for_pfn(
return pfn_to_nid(pfn);
}
+/*
+ * A memory block can have several absent sections. A helper function for
+ * skipping over these holes.
+ *
+ * If an absent section is detected, skip_absent_section() will advance *pfn
+ * to the final page in that section and will return true.
+ */
+static bool skip_absent_section(unsigned long *pfn)
+{
+ if (present_section_nr(pfn_to_section_nr(*pfn)))
+ return false;
+
+ *pfn = round_down(*pfn + PAGES_PER_SECTION, PAGES_PER_SECTION) - 1;
+ return true;
+}
+
/* register memory section under specified node if it spans that node */
int register_mem_sect_under_node(struct memory_block *mem_blk, int nid)
{
@@ -390,18 +406,10 @@ int register_mem_sect_under_node(struct
sect_end_pfn = section_nr_to_pfn(mem_blk->end_section_nr);
sect_end_pfn += PAGES_PER_SECTION - 1;
for (pfn = sect_start_pfn; pfn <= sect_end_pfn; pfn++) {
- int page_nid, scn_nr;
+ int page_nid;
- /*
- * memory block could have several absent sections from start.
- * skip pfn range from absent section
- */
- scn_nr = pfn_to_section_nr(pfn);
- if (!present_section_nr(scn_nr)) {
- pfn = round_down(pfn + PAGES_PER_SECTION,
- PAGES_PER_SECTION) - 1;
+ if (skip_absent_section(&pfn))
continue;
- }
page_nid = get_nid_for_pfn(pfn);
if (page_nid < 0)
@@ -441,18 +449,10 @@ int unregister_mem_sect_under_nodes(stru
sect_end_pfn = section_nr_to_pfn(mem_blk->end_section_nr);
sect_end_pfn += PAGES_PER_SECTION - 1;
for (pfn = sect_start_pfn; pfn <= sect_end_pfn; pfn++) {
- int nid, scn_nr;
+ int nid;
- /*
- * memory block could have several absent sections from start.
- * skip pfn range from absent section
- */
- scn_nr = pfn_to_section_nr(pfn);
- if (!present_section_nr(scn_nr)) {
- pfn = round_down(pfn + PAGES_PER_SECTION,
- PAGES_PER_SECTION) - 1;
+ if (skip_absent_section(&pfn))
continue;
- }
nid = get_nid_for_pfn(pfn);
if (nid < 0)
_
> Andrew,
> Ingo NAKed raw version of this patch, so you may need to remove it
> from -mm tree.
I don't know what that means. We have multiple patches under at least
two different Subject:s. Please be very careful and very specific when
identifying patches. Otherwise mistakes will be made.
I presently have three patches:
mm-check-if-section-present-during-memory-block-unregistering.patch
mm-check-if-section-present-during-memory-block-unregistering-v2.patch
mm-check-if-section-present-during-memory-block-unregistering-v2-fix.patch
When these are consolidated together, this is the result:
From: Yinghai Lu <yinghai@kernel.org>
Subject: mm: check if section present during memory block (un)registering
Tony Luck found on his setup, if memory block size 512M will cause crash
during booting.
BUG: unable to handle kernel paging request at ffffea0074000020
IP: [<ffffffff81670527>] get_nid_for_pfn+0x17/0x40
PGD 128ffcb067 PUD 128ffc9067 PMD 0
Oops: 0000 [#1] SMP
Modules linked in:
CPU: 0 PID: 1 Comm: swapper/0 Not tainted 4.2.0-rc8 #1
...
Call Trace:
[<ffffffff81453b56>] ? register_mem_sect_under_node+0x66/0xe0
[<ffffffff81453eeb>] register_one_node+0x17b/0x240
[<ffffffff81b1f1ed>] ? pci_iommu_alloc+0x6e/0x6e
[<ffffffff81b1f229>] topology_init+0x3c/0x95
[<ffffffff8100213d>] do_one_initcall+0xcd/0x1f0
The system has non continuous RAM address:
BIOS-e820: [mem 0x0000001300000000-0x0000001cffffffff] usable
BIOS-e820: [mem 0x0000001d70000000-0x0000001ec7ffefff] usable
BIOS-e820: [mem 0x0000001f00000000-0x0000002bffffffff] usable
BIOS-e820: [mem 0x0000002c18000000-0x0000002d6fffefff] usable
BIOS-e820: [mem 0x0000002e00000000-0x00000039ffffffff] usable
So there are start sections in memory block not present.
For example:
memory block : [0x2c18000000, 0x2c20000000) 512M
first three sections are not present.
Current register_mem_sect_under_node() assume first section is present,
but memory block section number range [start_section_nr, end_section_nr]
would include not present section.
For arch that support vmemmap, we don't setup memmap for struct page area
within not present sections area.
So skip the pfn range that belong to not present section.
Also fixes unregister_mem_sect_under_nodes().
Fixes: bdee237c0343 ("x86: mm: Use 2GB memory block size on large memory x86-64 systems")
Fixes: 982792c782ef ("x86, mm: probe memory block size for generic x86 64bit")
[akpm@linux-foundation.org: factor out common code]
Signed-off-by: Yinghai Lu <yinghai@kernel.org>
Reported-by: Tony Luck <tony.luck@intel.com>
Tested-by: Tony Luck <tony.luck@intel.com>
Cc: Greg KH <greg@kroah.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: <stable@vger.kernel.org> [3.15+]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
drivers/base/node.c | 27 +++++++++++++++++++++++++--
1 file changed, 25 insertions(+), 2 deletions(-)
@@ -375,6 +375,22 @@ static int __init_refok get_nid_for_pfn(
return pfn_to_nid(pfn);
}
+/*
+ * A memory block can have several absent sections. A helper function for
+ * skipping over these holes.
+ *
+ * If an absent section is detected, skip_absent_section() will advance *pfn
+ * to the final page in that section and will return true.
+ */
+static bool skip_absent_section(unsigned long *pfn)
+{
+ if (present_section_nr(pfn_to_section_nr(*pfn)))
+ return false;
+
+ *pfn = round_down(*pfn + PAGES_PER_SECTION, PAGES_PER_SECTION) - 1;
+ return true;
+}
+
/* register memory section under specified node if it spans that node */
int register_mem_sect_under_node(struct memory_block *mem_blk, int nid)
{
@@ -392,6 +408,9 @@ int register_mem_sect_under_node(struct
for (pfn = sect_start_pfn; pfn <= sect_end_pfn; pfn++) {
int page_nid;
+ if (skip_absent_section(&pfn))
+ continue;
+
page_nid = get_nid_for_pfn(pfn);
if (page_nid < 0)
continue;
@@ -426,11 +445,15 @@ int unregister_mem_sect_under_nodes(stru
return -ENOMEM;
nodes_clear(*unlinked_nodes);
- sect_start_pfn = section_nr_to_pfn(phys_index);
- sect_end_pfn = sect_start_pfn + PAGES_PER_SECTION - 1;
+ sect_start_pfn = section_nr_to_pfn(mem_blk->start_section_nr);
+ sect_end_pfn = section_nr_to_pfn(mem_blk->end_section_nr);
+ sect_end_pfn += PAGES_PER_SECTION - 1;
for (pfn = sect_start_pfn; pfn <= sect_end_pfn; pfn++) {
int nid;
+ if (skip_absent_section(&pfn))
+ continue;
+
nid = get_nid_for_pfn(pfn);
if (nid < 0)
continue;