Hi Suzuki,
On Mon, Apr 03, 2017 at 03:12:43PM +0100, Suzuki K Poulose wrote:
> In kvm_free_stage2_pgd() we don't hold the kvm->mmu_lock while calling
> unmap_stage2_range() on the entire memory range for the guest. This could
> cause problems with other callers (e.g, munmap on a memslot) trying to
> unmap a range. And since we have to unmap the entire Guest memory range
> holding a spinlock, make sure we yield the lock if necessary, after we
> unmap each PUD range.
>
> Fixes: commit d5d8184d35c9 ("KVM: ARM: Memory virtualization setup")
> Cc: stable@xxxxxxxxxxxxxxx # v3.10+
> Cc: Paolo Bonzini <pbonzin@xxxxxxxxxx>
> Cc: Marc Zyngier <marc.zyngier@xxxxxxx>
> Cc: Christoffer Dall <christoffer.dall@xxxxxxxxxx>
> Cc: Mark Rutland <mark.rutland@xxxxxxx>
> Signed-off-by: Suzuki K Poulose <suzuki.poulose@xxxxxxx>
> [ Avoid vCPU starvation and lockup detector warnings ]
> Signed-off-by: Marc Zyngier <marc.zyngier@xxxxxxx>
> Signed-off-by: Suzuki K Poulose <suzuki.poulose@xxxxxxx>
>
This unfortunately fails to build on 32-bit ARM, and I also think we
intended to check against S2_PGDIR_SIZE, not S2_PUD_SIZE.
How about adding this to your patch (which includes a rename of
S2_PGD_SIZE which is horribly confusing as it indicates the size of the
first level stage-2 table itself, where S2_PGDIR_SIZE indicates the size
of address space mapped by a single entry in the same table):
diff --git a/arch/arm/include/asm/stage2_pgtable.h b/arch/arm/include/asm/stage2_pgtable.h
index 460d616..c997f2d 100644
--- a/arch/arm/include/asm/stage2_pgtable.h
+++ b/arch/arm/include/asm/stage2_pgtable.h
@@ -35,10 +35,13 @@
#define stage2_pud_huge(pud) pud_huge(pud)
+#define S2_PGDIR_SIZE PGDIR_SIZE
+#define S2_PGDIR_MASK PGDIR_MASK
+
/* Open coded p*d_addr_end that can deal with 64bit addresses */
static inline phys_addr_t stage2_pgd_addr_end(phys_addr_t addr, phys_addr_t end)
{
- phys_addr_t boundary = (addr + PGDIR_SIZE) & PGDIR_MASK;
+ phys_addr_t boundary = (addr + S2_PGDIR_SIZE) & S2_PGDIR_MASK;
return (boundary - 1 < end - 1) ? boundary : end;
}
diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c
index db94f3a..6e79a4c 100644
--- a/arch/arm/kvm/mmu.c
+++ b/arch/arm/kvm/mmu.c
@@ -41,7 +41,7 @@ static unsigned long hyp_idmap_start;
static unsigned long hyp_idmap_end;
static phys_addr_t hyp_idmap_vector;
-#define S2_PGD_SIZE (PTRS_PER_S2_PGD * sizeof(pgd_t))
+#define S2_PGD_TABLE_SIZE (PTRS_PER_S2_PGD * sizeof(pgd_t))
#define hyp_pgd_order get_order(PTRS_PER_PGD * sizeof(pgd_t))
#define KVM_S2PTE_FLAG_IS_IOMAP (1UL << 0)
@@ -299,7 +299,7 @@ static void unmap_stage2_range(struct kvm *kvm, phys_addr_t start, u64 size)
* If the range is too large, release the kvm->mmu_lock
* to prevent starvation and lockup detector warnings.
*/
- if (size > S2_PUD_SIZE)
+ if (size > S2_PGDIR_SIZE)
cond_resched_lock(&kvm->mmu_lock);
next = stage2_pgd_addr_end(addr, end);
if (!stage2_pgd_none(*pgd))
@@ -747,7 +747,7 @@ int kvm_alloc_stage2_pgd(struct kvm *kvm)
}
/* Allocate the HW PGD, making sure that each page gets its own refcount */
- pgd = alloc_pages_exact(S2_PGD_SIZE, GFP_KERNEL | __GFP_ZERO);
+ pgd = alloc_pages_exact(S2_PGD_TABLE_SIZE, GFP_KERNEL | __GFP_ZERO);
if (!pgd)
return -ENOMEM;
@@ -843,7 +843,7 @@ void kvm_free_stage2_pgd(struct kvm *kvm)
spin_unlock(&kvm->mmu_lock);
/* Free the HW pgd, one page at a time */
- free_pages_exact(kvm->arch.pgd, S2_PGD_SIZE);
+ free_pages_exact(kvm->arch.pgd, S2_PGD_TABLE_SIZE);
kvm->arch.pgd = NULL;
}
Thanks,
-Christoffer
> ---
> Changes since V2:
> - Restrict kvm->mmu_lock relaxation to bigger ranges in unmap_stage2_range(),
> to avoid possible issues like [0]
>
> [0] http://lists.infradead.org/pipermail/linux-arm-kernel/2017-March/498210.html
>
> Changes since V1:
> - Yield the kvm->mmu_lock if necessary in unmap_stage2_range to prevent
> vCPU starvation and lockup detector warnings.
> ---
> arch/arm/kvm/mmu.c | 10 ++++++++++
> 1 file changed, 10 insertions(+)
>
> diff --git a/arch/arm/kvm/mmu.c b/arch/arm/kvm/mmu.c
> index 13b9c1f..db94f3a 100644
> --- a/arch/arm/kvm/mmu.c
> +++ b/arch/arm/kvm/mmu.c
> @@ -292,8 +292,15 @@ static void unmap_stage2_range(struct kvm *kvm, phys_addr_t start, u64 size)
> phys_addr_t addr = start, end = start + size;
> phys_addr_t next;
>
> + assert_spin_locked(&kvm->mmu_lock);
> pgd = kvm->arch.pgd + stage2_pgd_index(addr);
> do {
> + /*
> + * If the range is too large, release the kvm->mmu_lock
> + * to prevent starvation and lockup detector warnings.
> + */
> + if (size > S2_PUD_SIZE)
> + cond_resched_lock(&kvm->mmu_lock);
> next = stage2_pgd_addr_end(addr, end);
> if (!stage2_pgd_none(*pgd))
> unmap_stage2_puds(kvm, pgd, addr, next);
> @@ -831,7 +838,10 @@ void kvm_free_stage2_pgd(struct kvm *kvm)
> if (kvm->arch.pgd == NULL)
> return;
>
> + spin_lock(&kvm->mmu_lock);
> unmap_stage2_range(kvm, 0, KVM_PHYS_SIZE);
> + spin_unlock(&kvm->mmu_lock);
> +
> /* Free the HW pgd, one page at a time */
> free_pages_exact(kvm->arch.pgd, S2_PGD_SIZE);
> kvm->arch.pgd = NULL;
> --
> 2.7.4
>