This is a note to let you know that I've just added the patch titled
arm/arm64: KVM: Fix and refactor unmap_range
to the 3.14-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary
The filename of the patch is:
arm-arm64-kvm-fix-and-refactor-unmap_range.patch
and it can be found in the queue-3.14 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable@xxxxxxxxxxxxxxx> know about it.
>From 4f853a714bf16338ff5261128e6c7ae2569e9505 Mon Sep 17 00:00:00 2001
From: Christoffer Dall <christoffer.dall@xxxxxxxxxx>
Date: Fri, 9 May 2014 23:31:31 +0200
Subject: arm/arm64: KVM: Fix and refactor unmap_range
From: Christoffer Dall <christoffer.dall@xxxxxxxxxx>
commit 4f853a714bf16338ff5261128e6c7ae2569e9505 upstream.
unmap_range() was utterly broken, to quote Marc, and broke in all sorts
of situations. It was also quite complicated to follow and didn't
follow the usual scheme of having a separate iterating function for each
level of page tables.
Address this by refactoring the code and introduce a pgd_clear()
function.
Reviewed-by: Jungseok Lee <jays.lee@xxxxxxxxxxx>
Reviewed-by: Mario Smarduch <m.smarduch@xxxxxxxxxxx>
Acked-by: Marc Zyngier <marc.zyngier@xxxxxxx>
Signed-off-by: Christoffer Dall <christoffer.dall@xxxxxxxxxx>
Signed-off-by: Shannon Zhao <shannon.zhao@xxxxxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
---
arch/arm/include/asm/kvm_mmu.h | 12 +++
arch/arm/kvm/mmu.c | 156 +++++++++++++++++++++------------------
arch/arm64/include/asm/kvm_mmu.h | 15 +++
3 files changed, 111 insertions(+), 72 deletions(-)
--- a/arch/arm/include/asm/kvm_mmu.h
+++ b/arch/arm/include/asm/kvm_mmu.h
@@ -127,6 +127,18 @@ static inline void kvm_set_s2pmd_writabl
(__boundary - 1 < (end) - 1)? __boundary: (end); \
})
+static inline bool kvm_page_empty(void *ptr)
+{
+ struct page *ptr_page = virt_to_page(ptr);
+ return page_count(ptr_page) == 1;
+}
+
+
+#define kvm_pte_table_empty(ptep) kvm_page_empty(ptep)
+#define kvm_pmd_table_empty(pmdp) kvm_page_empty(pmdp)
+#define kvm_pud_table_empty(pudp) (0)
+
+
struct kvm;
#define kvm_flush_dcache_to_poc(a,l) __cpuc_flush_dcache_area((a), (l))
--- a/arch/arm/kvm/mmu.c
+++ b/arch/arm/kvm/mmu.c
@@ -90,103 +90,115 @@ static void *mmu_memory_cache_alloc(stru
return p;
}
-static bool page_empty(void *ptr)
+static void clear_pgd_entry(struct kvm *kvm, pgd_t *pgd, phys_addr_t addr)
{
- struct page *ptr_page = virt_to_page(ptr);
- return page_count(ptr_page) == 1;
+ pud_t *pud_table __maybe_unused = pud_offset(pgd, 0);
+ pgd_clear(pgd);
+ kvm_tlb_flush_vmid_ipa(kvm, addr);
+ pud_free(NULL, pud_table);
+ put_page(virt_to_page(pgd));
}
static void clear_pud_entry(struct kvm *kvm, pud_t *pud, phys_addr_t addr)
{
- if (pud_huge(*pud)) {
- pud_clear(pud);
- kvm_tlb_flush_vmid_ipa(kvm, addr);
- } else {
- pmd_t *pmd_table = pmd_offset(pud, 0);
- pud_clear(pud);
- kvm_tlb_flush_vmid_ipa(kvm, addr);
- pmd_free(NULL, pmd_table);
- }
+ pmd_t *pmd_table = pmd_offset(pud, 0);
+ VM_BUG_ON(pud_huge(*pud));
+ pud_clear(pud);
+ kvm_tlb_flush_vmid_ipa(kvm, addr);
+ pmd_free(NULL, pmd_table);
put_page(virt_to_page(pud));
}
static void clear_pmd_entry(struct kvm *kvm, pmd_t *pmd, phys_addr_t addr)
{
- if (kvm_pmd_huge(*pmd)) {
- pmd_clear(pmd);
- kvm_tlb_flush_vmid_ipa(kvm, addr);
- } else {
- pte_t *pte_table = pte_offset_kernel(pmd, 0);
- pmd_clear(pmd);
- kvm_tlb_flush_vmid_ipa(kvm, addr);
- pte_free_kernel(NULL, pte_table);
- }
+ pte_t *pte_table = pte_offset_kernel(pmd, 0);
+ VM_BUG_ON(kvm_pmd_huge(*pmd));
+ pmd_clear(pmd);
+ kvm_tlb_flush_vmid_ipa(kvm, addr);
+ pte_free_kernel(NULL, pte_table);
put_page(virt_to_page(pmd));
}
-static void clear_pte_entry(struct kvm *kvm, pte_t *pte, phys_addr_t addr)
+static void unmap_ptes(struct kvm *kvm, pmd_t *pmd,
+ phys_addr_t addr, phys_addr_t end)
{
- if (pte_present(*pte)) {
- kvm_set_pte(pte, __pte(0));
- put_page(virt_to_page(pte));
- kvm_tlb_flush_vmid_ipa(kvm, addr);
+ phys_addr_t start_addr = addr;
+ pte_t *pte, *start_pte;
+
+ start_pte = pte = pte_offset_kernel(pmd, addr);
+ do {
+ if (!pte_none(*pte)) {
+ kvm_set_pte(pte, __pte(0));
+ put_page(virt_to_page(pte));
+ kvm_tlb_flush_vmid_ipa(kvm, addr);
+ }
+ } while (pte++, addr += PAGE_SIZE, addr != end);
+
+ if (kvm_pte_table_empty(start_pte))
+ clear_pmd_entry(kvm, pmd, start_addr);
}
-}
-static void unmap_range(struct kvm *kvm, pgd_t *pgdp,
- unsigned long long start, u64 size)
+static void unmap_pmds(struct kvm *kvm, pud_t *pud,
+ phys_addr_t addr, phys_addr_t end)
{
- pgd_t *pgd;
- pud_t *pud;
- pmd_t *pmd;
- pte_t *pte;
- unsigned long long addr = start, end = start + size;
- u64 next;
-
- while (addr < end) {
- pgd = pgdp + pgd_index(addr);
- pud = pud_offset(pgd, addr);
- if (pud_none(*pud)) {
- addr = kvm_pud_addr_end(addr, end);
- continue;
- }
+ phys_addr_t next, start_addr = addr;
+ pmd_t *pmd, *start_pmd;
- if (pud_huge(*pud)) {
- /*
- * If we are dealing with a huge pud, just clear it and
- * move on.
- */
- clear_pud_entry(kvm, pud, addr);
- addr = kvm_pud_addr_end(addr, end);
- continue;
+ start_pmd = pmd = pmd_offset(pud, addr);
+ do {
+ next = kvm_pmd_addr_end(addr, end);
+ if (!pmd_none(*pmd)) {
+ if (kvm_pmd_huge(*pmd)) {
+ pmd_clear(pmd);
+ kvm_tlb_flush_vmid_ipa(kvm, addr);
+ put_page(virt_to_page(pmd));
+ } else {
+ unmap_ptes(kvm, pmd, addr, next);
+ }
}
+ } while (pmd++, addr = next, addr != end);
- pmd = pmd_offset(pud, addr);
- if (pmd_none(*pmd)) {
- addr = kvm_pmd_addr_end(addr, end);
- continue;
- }
+ if (kvm_pmd_table_empty(start_pmd))
+ clear_pud_entry(kvm, pud, start_addr);
+}
- if (!kvm_pmd_huge(*pmd)) {
- pte = pte_offset_kernel(pmd, addr);
- clear_pte_entry(kvm, pte, addr);
- next = addr + PAGE_SIZE;
- }
+static void unmap_puds(struct kvm *kvm, pgd_t *pgd,
+ phys_addr_t addr, phys_addr_t end)
+{
+ phys_addr_t next, start_addr = addr;
+ pud_t *pud, *start_pud;
- /*
- * If the pmd entry is to be cleared, walk back up the ladder
- */
- if (kvm_pmd_huge(*pmd) || page_empty(pte)) {
- clear_pmd_entry(kvm, pmd, addr);
- next = kvm_pmd_addr_end(addr, end);
- if (page_empty(pmd) && !page_empty(pud)) {
- clear_pud_entry(kvm, pud, addr);
- next = kvm_pud_addr_end(addr, end);
+ start_pud = pud = pud_offset(pgd, addr);
+ do {
+ next = kvm_pud_addr_end(addr, end);
+ if (!pud_none(*pud)) {
+ if (pud_huge(*pud)) {
+ pud_clear(pud);
+ kvm_tlb_flush_vmid_ipa(kvm, addr);
+ put_page(virt_to_page(pud));
+ } else {
+ unmap_pmds(kvm, pud, addr, next);
}
}
+ } while (pud++, addr = next, addr != end);
- addr = next;
- }
+ if (kvm_pud_table_empty(start_pud))
+ clear_pgd_entry(kvm, pgd, start_addr);
+}
+
+
+static void unmap_range(struct kvm *kvm, pgd_t *pgdp,
+ phys_addr_t start, u64 size)
+{
+ pgd_t *pgd;
+ phys_addr_t addr = start, end = start + size;
+ phys_addr_t next;
+
+ pgd = pgdp + pgd_index(addr);
+ do {
+ next = kvm_pgd_addr_end(addr, end);
+ unmap_puds(kvm, pgd, addr, next);
+ } while (pgd++, addr = next, addr != end);
}
static void stage2_flush_ptes(struct kvm *kvm, pmd_t *pmd,
--- a/arch/arm64/include/asm/kvm_mmu.h
+++ b/arch/arm64/include/asm/kvm_mmu.h
@@ -125,6 +125,21 @@ static inline void kvm_set_s2pmd_writabl
#define kvm_pud_addr_end(addr, end) pud_addr_end(addr, end)
#define kvm_pmd_addr_end(addr, end) pmd_addr_end(addr, end)
+static inline bool kvm_page_empty(void *ptr)
+{
+ struct page *ptr_page = virt_to_page(ptr);
+ return page_count(ptr_page) == 1;
+}
+
+#define kvm_pte_table_empty(ptep) kvm_page_empty(ptep)
+#ifndef CONFIG_ARM64_64K_PAGES
+#define kvm_pmd_table_empty(pmdp) kvm_page_empty(pmdp)
+#else
+#define kvm_pmd_table_empty(pmdp) (0)
+#endif
+#define kvm_pud_table_empty(pudp) (0)
+
+
struct kvm;
#define kvm_flush_dcache_to_poc(a,l) __flush_dcache_area((a), (l))
Patches currently in stable-queue which might be from christoffer.dall@xxxxxxxxxx are
queue-3.14/arm-kvm-user_mem_abort-support-stage-2-mmio-page-mapping.patch
queue-3.14/kvm-arm-arm64-avoid-returning-negative-error-code-as-bool.patch
queue-3.14/arm-kvm-unmap-ipa-on-memslot-delete-move.patch
queue-3.14/kvm-arm-arm64-fix-non-const-declaration-of-function-returning-const.patch
queue-3.14/arm64-kvm-store-kvm_vcpu_fault_info-est_el2-as-word.patch
queue-3.14/kvm-vgic-return-int-instead-of-bool-when-checking-i-o-ranges.patch
queue-3.14/kvm-arm-arm64-fix-broken-__percpu-annotation.patch
queue-3.14/arm64-kvm-export-demux-regids-as-kvm_reg_arm64.patch
queue-3.14/arm-arm64-kvm-fix-and-refactor-unmap_range.patch
--
To unsubscribe from this list: send the line "unsubscribe stable" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html