[PATCH] x86, mm: fix boot hang regression
From: Yuanhan Liu
Date: Sat May 25 2013 - 00:29:24 EST
Commit 8d57470d introduced a kernel panic while setting mem=2G at
boot time, and commit c9b3234a6 turns the the kernel panic to hang.
While, the reason is the same: the are accessing a BAD address; I mean
the mapping is broken.
Here is a mem mapping range dumped at boot time:
[mem 0x00000000-0x000fffff] page 4k (0)
[mem 0x7fe00000-0x7fffffff] page 1G (1)
[mem 0x7c000000-0x7fdfffff] page 1G (2)
[mem 0x00100000-0x001fffff] page 4k (3)
[mem 0x00200000-0x7bffffff] page 2M (4)
Where, we met no problems while setting memory map for region (0) to
(3). But we have set PG_LEVEL_1G mapping for pud index 0x1 at (1).
And pud index comes to 0x1 as well while setting 0x40000000-0x7bf00000
part of (4). What's more, it's PG_LEVEL_2M mapping, which results to a
splitting of PG_LEVEL_1G mapping. This breaks former mapping for (1) and
(2). In the same time, due to "end" setting to 0x7c000000, we missed the
chance to fix it at phys_pmd_init() for code:
if (address >= end) {
....
continue;
}
Thus, using a extra flag to indicate we are splitting a large PUD(or PMD)
and changing the above if statement to following will make this issue gone:
if(address >= end && !spliting) {
...
}
Reported-by: LKP <lkp@xxxxxxxxxxxxxxx>
CC: For 3.9+ <stable@xxxxxxxxxxxxxxx>
Cc: H. Peter Anvin <hpa@xxxxxxxxx>
Cc: Yinghai Lu <yinghai@xxxxxxxxxx>
Bisected-by: "Xie, ChanglongX" <changlongx.xie@xxxxxxxxx>
Signed-off-by: Yuanhan Liu <yuanhan.liu@xxxxxxxxxxxxxxx>
---
I reported this panic regression long time ago, and I didn't notic the above
panic->hang change before, which might confuse Yinghai for understanding
what happened from 2 logs I sent before(one is from 8d57470d, another is
from the HEAD commit at that time, which turn to a hang as stated).
More, it seems that Yinghai can't produce it. And I was busying at
something else. And I finally got a day yesterday(and a good mood ;).
Last, Thanks Changlong's effort for bisecting the 2 above commit.
---
arch/x86/mm/init_64.c | 51 +++++++++++++++++++++++++++++++++++++++++-------
1 files changed, 43 insertions(+), 8 deletions(-)
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index bb00c46..e4c7038 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -401,7 +401,7 @@ void __init cleanup_highmap(void)
static unsigned long __meminit
phys_pte_init(pte_t *pte_page, unsigned long addr, unsigned long end,
- pgprot_t prot)
+ pgprot_t prot, bool split_pmd)
{
unsigned long pages = 0, next;
unsigned long last_map_addr = end;
@@ -411,7 +411,7 @@ phys_pte_init(pte_t *pte_page, unsigned long addr, unsigned long end,
for (i = pte_index(addr); i < PTRS_PER_PTE; i++, addr = next, pte++) {
next = (addr & PAGE_MASK) + PAGE_SIZE;
- if (addr >= end) {
+ if (addr >= end && !split_pmd) {
if (!after_bootmem &&
!e820_any_mapped(addr & PAGE_MASK, next, E820_RAM) &&
!e820_any_mapped(addr & PAGE_MASK, next, E820_RESERVED_KERN))
@@ -446,7 +446,7 @@ phys_pte_init(pte_t *pte_page, unsigned long addr, unsigned long end,
static unsigned long __meminit
phys_pmd_init(pmd_t *pmd_page, unsigned long address, unsigned long end,
- unsigned long page_size_mask, pgprot_t prot)
+ unsigned long page_size_mask, pgprot_t prot, bool split_pud)
{
unsigned long pages = 0, next;
unsigned long last_map_addr = end;
@@ -457,9 +457,10 @@ phys_pmd_init(pmd_t *pmd_page, unsigned long address, unsigned long end,
pmd_t *pmd = pmd_page + pmd_index(address);
pte_t *pte;
pgprot_t new_prot = prot;
+ bool split_pmd = false;
next = (address & PMD_MASK) + PMD_SIZE;
- if (address >= end) {
+ if (address >= end && !split_pud) {
if (!after_bootmem &&
!e820_any_mapped(address & PMD_MASK, next, E820_RAM) &&
!e820_any_mapped(address & PMD_MASK, next, E820_RESERVED_KERN))
@@ -472,7 +473,7 @@ phys_pmd_init(pmd_t *pmd_page, unsigned long address, unsigned long end,
spin_lock(&init_mm.page_table_lock);
pte = (pte_t *)pmd_page_vaddr(*pmd);
last_map_addr = phys_pte_init(pte, address,
- end, prot);
+ end, prot, split_pmd);
spin_unlock(&init_mm.page_table_lock);
continue;
}
@@ -495,6 +496,7 @@ phys_pmd_init(pmd_t *pmd_page, unsigned long address, unsigned long end,
continue;
}
new_prot = pte_pgprot(pte_clrhuge(*(pte_t *)pmd));
+ split_pmd = true;
}
if (page_size_mask & (1<<PG_LEVEL_2M)) {
@@ -509,7 +511,8 @@ phys_pmd_init(pmd_t *pmd_page, unsigned long address, unsigned long end,
}
pte = alloc_low_page();
- last_map_addr = phys_pte_init(pte, address, end, new_prot);
+ last_map_addr = phys_pte_init(pte, address, end,
+ new_prot, split_pmd);
spin_lock(&init_mm.page_table_lock);
pmd_populate_kernel(&init_mm, pmd, pte);
@@ -531,6 +534,7 @@ phys_pud_init(pud_t *pud_page, unsigned long addr, unsigned long end,
pud_t *pud = pud_page + pud_index(addr);
pmd_t *pmd;
pgprot_t prot = PAGE_KERNEL;
+ bool split_pud = false;
next = (addr & PUD_MASK) + PUD_SIZE;
if (addr >= end) {
@@ -545,7 +549,8 @@ phys_pud_init(pud_t *pud_page, unsigned long addr, unsigned long end,
if (!pud_large(*pud)) {
pmd = pmd_offset(pud, 0);
last_map_addr = phys_pmd_init(pmd, addr, end,
- page_size_mask, prot);
+ page_size_mask, prot,
+ split_pud);
__flush_tlb_all();
continue;
}
@@ -568,6 +573,36 @@ phys_pud_init(pud_t *pud_page, unsigned long addr, unsigned long end,
continue;
}
prot = pte_pgprot(pte_clrhuge(*(pte_t *)pud));
+ /*
+ * We set page table in top-down now, which means we
+ * might have set a PG_LEVEL_1G mapping for a higher
+ * address.
+ *
+ * And in the meantime, here we meet the same PUD in
+ * a lower mem region and we are about to split it.
+ * Setting split_pud to make sure we will re-map
+ * former mapping as well. Or, we will just ignore
+ * it due to
+ * if (address >= end) {
+ * ...
+ * continue;
+ * }
+ * at phys_pmd_init().
+ *
+ * Example: here is one case I met:
+ * [mem 0x00000000-0x000fffff] page 4k (0)
+ * [mem 0x7fe00000-0x7fffffff] page 1G (1)
+ * [mem 0x7c000000-0x7fdfffff] page 1G (2)
+ * [mem 0x00100000-0x001fffff] page 4k (3)
+ * [mem 0x00200000-0x7bffffff] page 2M (4)
+ *
+ * Where mem 0x400000000 to mem 0x7fffffff will use same
+ * PUD, and we have set a PG_LEVEL_1G mapping at (1).
+ * While handling 0x40000000 - 0x7bf00000 part of (4),
+ * we will split PUD and break former mapping for (1)
+ * and (2) as stated above.
+ */
+ split_pud = true;
}
if (page_size_mask & (1<<PG_LEVEL_1G)) {
@@ -583,7 +618,7 @@ phys_pud_init(pud_t *pud_page, unsigned long addr, unsigned long end,
pmd = alloc_low_page();
last_map_addr = phys_pmd_init(pmd, addr, end, page_size_mask,
- prot);
+ prot, split_pud);
spin_lock(&init_mm.page_table_lock);
pud_populate(&init_mm, pud, pmd);
--
1.7.7.6
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/