Update Linux to v5.4.148
Sourced from [1]
[1] https://cdn.kernel.org/pub/linux/kernel/v5.x/linux-5.4.148.tar.gz
Change-Id: Ib3d26c5ba9b022e2e03533005c4fed4d7c30b61b
Signed-off-by: Olivier Deprez <olivier.deprez@arm.com>
diff --git a/virt/kvm/arm/mmu.c b/virt/kvm/arm/mmu.c
index 38b4c91..c6ba672 100644
--- a/virt/kvm/arm/mmu.c
+++ b/virt/kvm/arm/mmu.c
@@ -38,6 +38,11 @@
#define KVM_S2PTE_FLAG_IS_IOMAP (1UL << 0)
#define KVM_S2_FLAG_LOGGING_ACTIVE (1UL << 1)
+static bool is_iomap(unsigned long flags)
+{
+ return flags & KVM_S2PTE_FLAG_IS_IOMAP;
+}
+
static bool memslot_is_logging(struct kvm_memory_slot *memslot)
{
return memslot->dirty_bitmap && !(memslot->flags & KVM_MEM_READONLY);
@@ -327,7 +332,8 @@
* destroying the VM), otherwise another faulting VCPU may come in and mess
* with things behind our backs.
*/
-static void unmap_stage2_range(struct kvm *kvm, phys_addr_t start, u64 size)
+static void __unmap_stage2_range(struct kvm *kvm, phys_addr_t start, u64 size,
+ bool may_block)
{
pgd_t *pgd;
phys_addr_t addr = start, end = start + size;
@@ -352,11 +358,16 @@
* If the range is too large, release the kvm->mmu_lock
* to prevent starvation and lockup detector warnings.
*/
- if (next != end)
+ if (may_block && next != end)
cond_resched_lock(&kvm->mmu_lock);
} while (pgd++, addr = next, addr != end);
}
+static void unmap_stage2_range(struct kvm *kvm, phys_addr_t start, u64 size)
+{
+ __unmap_stage2_range(kvm, start, size, true);
+}
+
static void stage2_flush_ptes(struct kvm *kvm, pmd_t *pmd,
phys_addr_t addr, phys_addr_t end)
{
@@ -1194,7 +1205,7 @@
return true;
}
-static bool stage2_is_exec(struct kvm *kvm, phys_addr_t addr)
+static bool stage2_is_exec(struct kvm *kvm, phys_addr_t addr, unsigned long sz)
{
pud_t *pudp;
pmd_t *pmdp;
@@ -1206,11 +1217,11 @@
return false;
if (pudp)
- return kvm_s2pud_exec(pudp);
+ return sz <= PUD_SIZE && kvm_s2pud_exec(pudp);
else if (pmdp)
- return kvm_s2pmd_exec(pmdp);
+ return sz <= PMD_SIZE && kvm_s2pmd_exec(pmdp);
else
- return kvm_s2pte_exec(ptep);
+ return sz == PAGE_SIZE && kvm_s2pte_exec(ptep);
}
static int stage2_set_pte(struct kvm *kvm, struct kvm_mmu_memory_cache *cache,
@@ -1679,7 +1690,7 @@
unsigned long vma_pagesize, flags = 0;
write_fault = kvm_is_write_fault(vcpu);
- exec_fault = kvm_vcpu_trap_is_iabt(vcpu);
+ exec_fault = kvm_vcpu_trap_is_exec_fault(vcpu);
VM_BUG_ON(write_fault && exec_fault);
if (fault_status == FSC_PERM && !write_fault && !exec_fault) {
@@ -1698,6 +1709,7 @@
vma_pagesize = vma_kernel_pagesize(vma);
if (logging_active ||
+ (vma->vm_flags & VM_PFNMAP) ||
!fault_supports_stage2_huge_mapping(memslot, hva, vma_pagesize)) {
force_pte = true;
vma_pagesize = PAGE_SIZE;
@@ -1744,6 +1756,7 @@
if (kvm_is_device_pfn(pfn)) {
mem_type = PAGE_S2_DEVICE;
flags |= KVM_S2PTE_FLAG_IS_IOMAP;
+ force_pte = true;
} else if (logging_active) {
/*
* Faults on pages in a memslot with logging enabled
@@ -1760,6 +1773,9 @@
writable = false;
}
+ if (exec_fault && is_iomap(flags))
+ return -ENOEXEC;
+
spin_lock(&kvm->mmu_lock);
if (mmu_notifier_retry(kvm, mmu_seq))
goto out_unlock;
@@ -1781,7 +1797,7 @@
if (writable)
kvm_set_pfn_dirty(pfn);
- if (fault_status != FSC_PERM)
+ if (fault_status != FSC_PERM && !is_iomap(flags))
clean_dcache_guest_page(pfn, vma_pagesize);
if (exec_fault)
@@ -1796,9 +1812,15 @@
* execute permissions, and we preserve whatever we have.
*/
needs_exec = exec_fault ||
- (fault_status == FSC_PERM && stage2_is_exec(kvm, fault_ipa));
+ (fault_status == FSC_PERM &&
+ stage2_is_exec(kvm, fault_ipa, vma_pagesize));
- if (vma_pagesize == PUD_SIZE) {
+ /*
+ * If PUD_SIZE == PMD_SIZE, there is no real PUD level, and
+ * all we have is a 2-level page table. Trying to map a PUD in
+ * this case would be fatally wrong.
+ */
+ if (PUD_SIZE != PMD_SIZE && vma_pagesize == PUD_SIZE) {
pud_t new_pud = kvm_pfn_pud(pfn, mem_type);
new_pud = kvm_pud_mkhuge(new_pud);
@@ -1948,9 +1970,8 @@
if (kvm_is_error_hva(hva) || (write_fault && !writable)) {
if (is_iabt) {
/* Prefetch Abort on I/O address */
- kvm_inject_pabt(vcpu, kvm_vcpu_get_hfar(vcpu));
- ret = 1;
- goto out_unlock;
+ ret = -ENOEXEC;
+ goto out;
}
/*
@@ -1992,6 +2013,11 @@
ret = user_mem_abort(vcpu, fault_ipa, memslot, hva, fault_status);
if (ret == 0)
ret = 1;
+out:
+ if (ret == -ENOEXEC) {
+ kvm_inject_pabt(vcpu, kvm_vcpu_get_hfar(vcpu));
+ ret = 1;
+ }
out_unlock:
srcu_read_unlock(&vcpu->kvm->srcu, idx);
return ret;
@@ -2031,18 +2057,21 @@
static int kvm_unmap_hva_handler(struct kvm *kvm, gpa_t gpa, u64 size, void *data)
{
- unmap_stage2_range(kvm, gpa, size);
+ unsigned flags = *(unsigned *)data;
+ bool may_block = flags & MMU_NOTIFIER_RANGE_BLOCKABLE;
+
+ __unmap_stage2_range(kvm, gpa, size, may_block);
return 0;
}
int kvm_unmap_hva_range(struct kvm *kvm,
- unsigned long start, unsigned long end)
+ unsigned long start, unsigned long end, unsigned flags)
{
if (!kvm->arch.pgd)
return 0;
trace_kvm_unmap_hva_range(start, end);
- handle_hva_to_gpa(kvm, start, end, &kvm_unmap_hva_handler, NULL);
+ handle_hva_to_gpa(kvm, start, end, &kvm_unmap_hva_handler, &flags);
return 0;
}
@@ -2134,7 +2163,8 @@
if (!kvm->arch.pgd)
return 0;
trace_kvm_test_age_hva(hva);
- return handle_hva_to_gpa(kvm, hva, hva, kvm_test_age_hva_handler, NULL);
+ return handle_hva_to_gpa(kvm, hva, hva + PAGE_SIZE,
+ kvm_test_age_hva_handler, NULL);
}
void kvm_mmu_free_memory_caches(struct kvm_vcpu *vcpu)
@@ -2277,8 +2307,7 @@
* Prevent userspace from creating a memory region outside of the IPA
* space addressable by the KVM guest IPA space.
*/
- if (memslot->base_gfn + memslot->npages >=
- (kvm_phys_size(kvm) >> PAGE_SHIFT))
+ if ((memslot->base_gfn + memslot->npages) > (kvm_phys_size(kvm) >> PAGE_SHIFT))
return -EFAULT;
down_read(¤t->mm->mmap_sem);