The recently merged API for ensuring break-before-make on page-table
entries when installing huge mappings in the vmalloc/ioremap region is
fairly counter-intuitive, resulting in the arch freeing functions
(e.g. pmd_free_pte_page()) being called even on entries that aren't
present. This resulted in a minor bug in the arm64 implementation, giving
rise to spurious VM_WARN messages.
This patch moves the pXd_present() checks out into the core code,
refactoring the callsites at the same time so that we avoid the complex
conjunctions when determining whether or not we can put down a huge
mapping.
Cc: Chintan Pandya <cpandya@xxxxxxxxxxxxxx>
Cc: Toshi Kani <toshi.kani@xxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: Michal Hocko <mhocko@xxxxxxxx>
Cc: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
Suggested-by: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
Signed-off-by: Will Deacon <will.deacon@xxxxxxx>
---
lib/ioremap.c | 56 ++++++++++++++++++++++++++++++++++++++++++--------------
1 file changed, 42 insertions(+), 14 deletions(-)
diff --git a/lib/ioremap.c b/lib/ioremap.c
index 517f5853ffed..6c72764af19c 100644
--- a/lib/ioremap.c
+++ b/lib/ioremap.c
@@ -76,6 +76,25 @@ static int ioremap_pte_range(pmd_t *pmd, unsigned long addr,
return 0;
}
+static int ioremap_try_huge_pmd(pmd_t *pmd, unsigned long addr,
+ unsigned long end, phys_addr_t phys_addr,
+ pgprot_t prot)
+{
+ if (!ioremap_pmd_enabled())
+ return 0;
+
+ if ((end - addr) != PMD_SIZE)
+ return 0;
+
+ if (!IS_ALIGNED(phys_addr, PMD_SIZE))
+ return 0;
+
+ if (pmd_present(*pmd) && !pmd_free_pte_page(pmd, addr))
+ return 0;
+
+ return pmd_set_huge(pmd, phys_addr, prot);
+}
+
static inline int ioremap_pmd_range(pud_t *pud, unsigned long addr,
unsigned long end, phys_addr_t phys_addr, pgprot_t prot)
{
@@ -89,13 +108,8 @@ static inline int ioremap_pmd_range(pud_t *pud, unsigned long addr,
do {
next = pmd_addr_end(addr, end);
- if (ioremap_pmd_enabled() &&
- ((next - addr) == PMD_SIZE) &&
- IS_ALIGNED(phys_addr + addr, PMD_SIZE) &&
- pmd_free_pte_page(pmd, addr)) {
- if (pmd_set_huge(pmd, phys_addr + addr, prot))
- continue;
- }
+ if (ioremap_try_huge_pmd(pmd, addr, next, phys_addr + addr, prot))
+ continue;
if (ioremap_pte_range(pmd, addr, next, phys_addr + addr, prot))
return -ENOMEM;
@@ -103,6 +117,25 @@ static inline int ioremap_pmd_range(pud_t *pud, unsigned long addr,
return 0;
}
+static int ioremap_try_huge_pud(pud_t *pud, unsigned long addr,
+ unsigned long end, phys_addr_t phys_addr,
+ pgprot_t prot)
+{
+ if (!ioremap_pud_enabled())
+ return 0;
+
+ if ((end - addr) != PUD_SIZE)
+ return 0;
+
+ if (!IS_ALIGNED(phys_addr, PUD_SIZE))
+ return 0;
+
+ if (pud_present(*pud) && !pud_free_pmd_page(pud, addr))
+ return 0;
+
+ return pud_set_huge(pud, phys_addr, prot);
+}
+
static inline int ioremap_pud_range(p4d_t *p4d, unsigned long addr,
unsigned long end, phys_addr_t phys_addr, pgprot_t prot)
{
@@ -116,13 +149,8 @@ static inline int ioremap_pud_range(p4d_t *p4d, unsigned long addr,
do {
next = pud_addr_end(addr, end);
- if (ioremap_pud_enabled() &&
- ((next - addr) == PUD_SIZE) &&
- IS_ALIGNED(phys_addr + addr, PUD_SIZE) &&
- pud_free_pmd_page(pud, addr)) {
- if (pud_set_huge(pud, phys_addr + addr, prot))
- continue;
- }
+ if (ioremap_try_huge_pud(pud, addr, next, phys_addr + addr, prot))
+ continue;
if (ioremap_pmd_range(pud, addr, next, phys_addr + addr, prot))
return -ENOMEM;
--
2.1.4
