pve-kernel-thunderx/patches/kernel/0007-Revert-Merge-branch-mmu_notifier_fixes.patch
2017-11-29 09:48:40 +01:00

825 lines
29 KiB
Diff

From dfd4ec1fd8d1d09930e9cf9ed7ebd07a66813337 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Fabian=20Gr=C3=BCnbichler?= <f.gruenbichler@proxmox.com>
Date: Wed, 29 Nov 2017 09:45:44 +0100
Subject: [PATCH 7/7] Revert "Merge branch 'mmu_notifier_fixes'"
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit
This reverts commit ea25c43179462e342d4a0e66c3f6a5f53514da05, reversing
changes made to c227390c91a355300f47f9bef0aefbdfaaca1500.
This series causes blue screens in Windows VMs running under heavy
memory/swap pressure.
Signed-off-by: Fabian Grünbichler <f.gruenbichler@proxmox.com>
---
arch/arm/include/asm/kvm_host.h | 6 +++++
arch/arm64/include/asm/kvm_host.h | 6 +++++
arch/mips/include/asm/kvm_host.h | 5 ++++
arch/powerpc/include/asm/kvm_host.h | 5 ++++
arch/x86/include/asm/kvm_host.h | 2 ++
include/linux/mm.h | 1 -
include/linux/mmu_notifier.h | 25 +++++++++++++++++++
arch/powerpc/platforms/powernv/npu-dma.c | 10 ++++++++
arch/x86/kvm/x86.c | 11 +++++++++
drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c | 31 +++++++++++++++++++++++
drivers/infiniband/core/umem_odp.c | 19 +++++++++++++++
drivers/infiniband/hw/hfi1/mmu_rb.c | 9 +++++++
drivers/iommu/amd_iommu_v2.c | 8 ++++++
drivers/iommu/intel-svm.c | 9 +++++++
drivers/misc/mic/scif/scif_dma.c | 11 +++++++++
drivers/misc/sgi-gru/grutlbpurge.c | 12 +++++++++
drivers/xen/gntdev.c | 8 ++++++
fs/dax.c | 19 ++++++---------
mm/memory.c | 26 ++++----------------
mm/mmu_notifier.c | 14 +++++++++++
mm/rmap.c | 35 +++-----------------------
virt/kvm/kvm_main.c | 42 ++++++++++++++++++++++++++++++++
22 files changed, 249 insertions(+), 65 deletions(-)
diff --git a/arch/arm/include/asm/kvm_host.h b/arch/arm/include/asm/kvm_host.h
index 4a879f6ff13b..127e2dd2e21c 100644
--- a/arch/arm/include/asm/kvm_host.h
+++ b/arch/arm/include/asm/kvm_host.h
@@ -225,6 +225,12 @@ int kvm_arm_copy_reg_indices(struct kvm_vcpu *vcpu, u64 __user *indices);
int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end);
int kvm_test_age_hva(struct kvm *kvm, unsigned long hva);
+/* We do not have shadow page tables, hence the empty hooks */
+static inline void kvm_arch_mmu_notifier_invalidate_page(struct kvm *kvm,
+ unsigned long address)
+{
+}
+
struct kvm_vcpu *kvm_arm_get_running_vcpu(void);
struct kvm_vcpu __percpu **kvm_get_running_vcpus(void);
void kvm_arm_halt_guest(struct kvm *kvm);
diff --git a/arch/arm64/include/asm/kvm_host.h b/arch/arm64/include/asm/kvm_host.h
index e923b58606e2..d68630007b14 100644
--- a/arch/arm64/include/asm/kvm_host.h
+++ b/arch/arm64/include/asm/kvm_host.h
@@ -326,6 +326,12 @@ void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte);
int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end);
int kvm_test_age_hva(struct kvm *kvm, unsigned long hva);
+/* We do not have shadow page tables, hence the empty hooks */
+static inline void kvm_arch_mmu_notifier_invalidate_page(struct kvm *kvm,
+ unsigned long address)
+{
+}
+
struct kvm_vcpu *kvm_arm_get_running_vcpu(void);
struct kvm_vcpu * __percpu *kvm_get_running_vcpus(void);
void kvm_arm_halt_guest(struct kvm *kvm);
diff --git a/arch/mips/include/asm/kvm_host.h b/arch/mips/include/asm/kvm_host.h
index a9af1d2dcd69..2998479fd4e8 100644
--- a/arch/mips/include/asm/kvm_host.h
+++ b/arch/mips/include/asm/kvm_host.h
@@ -938,6 +938,11 @@ void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte);
int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end);
int kvm_test_age_hva(struct kvm *kvm, unsigned long hva);
+static inline void kvm_arch_mmu_notifier_invalidate_page(struct kvm *kvm,
+ unsigned long address)
+{
+}
+
/* Emulation */
int kvm_get_inst(u32 *opc, struct kvm_vcpu *vcpu, u32 *out);
enum emulation_result update_pc(struct kvm_vcpu *vcpu, u32 cause);
diff --git a/arch/powerpc/include/asm/kvm_host.h b/arch/powerpc/include/asm/kvm_host.h
index e372ed871c51..8b3f1238d07f 100644
--- a/arch/powerpc/include/asm/kvm_host.h
+++ b/arch/powerpc/include/asm/kvm_host.h
@@ -67,6 +67,11 @@ extern int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end);
extern int kvm_test_age_hva(struct kvm *kvm, unsigned long hva);
extern void kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte);
+static inline void kvm_arch_mmu_notifier_invalidate_page(struct kvm *kvm,
+ unsigned long address)
+{
+}
+
#define HPTEG_CACHE_NUM (1 << 15)
#define HPTEG_HASH_BITS_PTE 13
#define HPTEG_HASH_BITS_PTE_LONG 12
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 92c9032502d8..f4d120a3e22e 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1375,6 +1375,8 @@ int kvm_arch_interrupt_allowed(struct kvm_vcpu *vcpu);
int kvm_cpu_get_interrupt(struct kvm_vcpu *v);
void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event);
void kvm_vcpu_reload_apic_access_page(struct kvm_vcpu *vcpu);
+void kvm_arch_mmu_notifier_invalidate_page(struct kvm *kvm,
+ unsigned long address);
void kvm_define_shared_msr(unsigned index, u32 msr);
int kvm_set_shared_msr(unsigned index, u64 val, u64 mask);
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 07630442bbf2..701de4b55ece 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1260,7 +1260,6 @@ int copy_page_range(struct mm_struct *dst, struct mm_struct *src,
void unmap_mapping_range(struct address_space *mapping,
loff_t const holebegin, loff_t const holelen, int even_cows);
int follow_pte_pmd(struct mm_struct *mm, unsigned long address,
- unsigned long *start, unsigned long *end,
pte_t **ptepp, pmd_t **pmdpp, spinlock_t **ptlp);
int follow_pfn(struct vm_area_struct *vma, unsigned long address,
unsigned long *pfn);
diff --git a/include/linux/mmu_notifier.h b/include/linux/mmu_notifier.h
index 6866e8126982..947f21b451d2 100644
--- a/include/linux/mmu_notifier.h
+++ b/include/linux/mmu_notifier.h
@@ -94,6 +94,17 @@ struct mmu_notifier_ops {
unsigned long address,
pte_t pte);
+ /*
+ * Before this is invoked any secondary MMU is still ok to
+ * read/write to the page previously pointed to by the Linux
+ * pte because the page hasn't been freed yet and it won't be
+ * freed until this returns. If required set_page_dirty has to
+ * be called internally to this method.
+ */
+ void (*invalidate_page)(struct mmu_notifier *mn,
+ struct mm_struct *mm,
+ unsigned long address);
+
/*
* invalidate_range_start() and invalidate_range_end() must be
* paired and are called only when the mmap_sem and/or the
@@ -209,6 +220,8 @@ extern int __mmu_notifier_test_young(struct mm_struct *mm,
unsigned long address);
extern void __mmu_notifier_change_pte(struct mm_struct *mm,
unsigned long address, pte_t pte);
+extern void __mmu_notifier_invalidate_page(struct mm_struct *mm,
+ unsigned long address);
extern void __mmu_notifier_invalidate_range_start(struct mm_struct *mm,
unsigned long start, unsigned long end);
extern void __mmu_notifier_invalidate_range_end(struct mm_struct *mm,
@@ -255,6 +268,13 @@ static inline void mmu_notifier_change_pte(struct mm_struct *mm,
__mmu_notifier_change_pte(mm, address, pte);
}
+static inline void mmu_notifier_invalidate_page(struct mm_struct *mm,
+ unsigned long address)
+{
+ if (mm_has_notifiers(mm))
+ __mmu_notifier_invalidate_page(mm, address);
+}
+
static inline void mmu_notifier_invalidate_range_start(struct mm_struct *mm,
unsigned long start, unsigned long end)
{
@@ -427,6 +447,11 @@ static inline void mmu_notifier_change_pte(struct mm_struct *mm,
{
}
+static inline void mmu_notifier_invalidate_page(struct mm_struct *mm,
+ unsigned long address)
+{
+}
+
static inline void mmu_notifier_invalidate_range_start(struct mm_struct *mm,
unsigned long start, unsigned long end)
{
diff --git a/arch/powerpc/platforms/powernv/npu-dma.c b/arch/powerpc/platforms/powernv/npu-dma.c
index 2cb6cbea4b3b..3d4f879e687c 100644
--- a/arch/powerpc/platforms/powernv/npu-dma.c
+++ b/arch/powerpc/platforms/powernv/npu-dma.c
@@ -614,6 +614,15 @@ static void pnv_npu2_mn_change_pte(struct mmu_notifier *mn,
mmio_invalidate(npu_context, 1, address, true);
}
+static void pnv_npu2_mn_invalidate_page(struct mmu_notifier *mn,
+ struct mm_struct *mm,
+ unsigned long address)
+{
+ struct npu_context *npu_context = mn_to_npu_context(mn);
+
+ mmio_invalidate(npu_context, 1, address, true);
+}
+
static void pnv_npu2_mn_invalidate_range(struct mmu_notifier *mn,
struct mm_struct *mm,
unsigned long start, unsigned long end)
@@ -631,6 +640,7 @@ static void pnv_npu2_mn_invalidate_range(struct mmu_notifier *mn,
static const struct mmu_notifier_ops nv_nmmu_notifier_ops = {
.release = pnv_npu2_mn_release,
.change_pte = pnv_npu2_mn_change_pte,
+ .invalidate_page = pnv_npu2_mn_invalidate_page,
.invalidate_range = pnv_npu2_mn_invalidate_range,
};
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 7351cdc46cc7..a669b4dd51e7 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -6734,6 +6734,17 @@ void kvm_vcpu_reload_apic_access_page(struct kvm_vcpu *vcpu)
}
EXPORT_SYMBOL_GPL(kvm_vcpu_reload_apic_access_page);
+void kvm_arch_mmu_notifier_invalidate_page(struct kvm *kvm,
+ unsigned long address)
+{
+ /*
+ * The physical address of apic access page is stored in the VMCS.
+ * Update it when it becomes invalid.
+ */
+ if (address == gfn_to_hva(kvm, APIC_DEFAULT_PHYS_BASE >> PAGE_SHIFT))
+ kvm_make_all_cpus_request(kvm, KVM_REQ_APIC_PAGE_RELOAD);
+}
+
/*
* Returns 1 to let vcpu_run() continue the guest execution loop without
* exiting to the userspace. Otherwise, the value will be returned to the
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c
index e1cde6b80027..6558a3ed57a7 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_mn.c
@@ -146,6 +146,36 @@ static void amdgpu_mn_invalidate_node(struct amdgpu_mn_node *node,
}
}
+/**
+ * amdgpu_mn_invalidate_page - callback to notify about mm change
+ *
+ * @mn: our notifier
+ * @mn: the mm this callback is about
+ * @address: address of invalidate page
+ *
+ * Invalidation of a single page. Blocks for all BOs mapping it
+ * and unmap them by move them into system domain again.
+ */
+static void amdgpu_mn_invalidate_page(struct mmu_notifier *mn,
+ struct mm_struct *mm,
+ unsigned long address)
+{
+ struct amdgpu_mn *rmn = container_of(mn, struct amdgpu_mn, mn);
+ struct interval_tree_node *it;
+
+ mutex_lock(&rmn->lock);
+
+ it = interval_tree_iter_first(&rmn->objects, address, address);
+ if (it) {
+ struct amdgpu_mn_node *node;
+
+ node = container_of(it, struct amdgpu_mn_node, it);
+ amdgpu_mn_invalidate_node(node, address, address);
+ }
+
+ mutex_unlock(&rmn->lock);
+}
+
/**
* amdgpu_mn_invalidate_range_start - callback to notify about mm change
*
@@ -185,6 +215,7 @@ static void amdgpu_mn_invalidate_range_start(struct mmu_notifier *mn,
static const struct mmu_notifier_ops amdgpu_mn_ops = {
.release = amdgpu_mn_release,
+ .invalidate_page = amdgpu_mn_invalidate_page,
.invalidate_range_start = amdgpu_mn_invalidate_range_start,
};
diff --git a/drivers/infiniband/core/umem_odp.c b/drivers/infiniband/core/umem_odp.c
index 55e8f5ed8b3c..8c4ec564e495 100644
--- a/drivers/infiniband/core/umem_odp.c
+++ b/drivers/infiniband/core/umem_odp.c
@@ -166,6 +166,24 @@ static int invalidate_page_trampoline(struct ib_umem *item, u64 start,
return 0;
}
+static void ib_umem_notifier_invalidate_page(struct mmu_notifier *mn,
+ struct mm_struct *mm,
+ unsigned long address)
+{
+ struct ib_ucontext *context = container_of(mn, struct ib_ucontext, mn);
+
+ if (!context->invalidate_range)
+ return;
+
+ ib_ucontext_notifier_start_account(context);
+ down_read(&context->umem_rwsem);
+ rbt_ib_umem_for_each_in_range(&context->umem_tree, address,
+ address + PAGE_SIZE,
+ invalidate_page_trampoline, NULL);
+ up_read(&context->umem_rwsem);
+ ib_ucontext_notifier_end_account(context);
+}
+
static int invalidate_range_start_trampoline(struct ib_umem *item, u64 start,
u64 end, void *cookie)
{
@@ -219,6 +237,7 @@ static void ib_umem_notifier_invalidate_range_end(struct mmu_notifier *mn,
static const struct mmu_notifier_ops ib_umem_notifiers = {
.release = ib_umem_notifier_release,
+ .invalidate_page = ib_umem_notifier_invalidate_page,
.invalidate_range_start = ib_umem_notifier_invalidate_range_start,
.invalidate_range_end = ib_umem_notifier_invalidate_range_end,
};
diff --git a/drivers/infiniband/hw/hfi1/mmu_rb.c b/drivers/infiniband/hw/hfi1/mmu_rb.c
index e4b56a0dd6d0..ccbf52c8ff6f 100644
--- a/drivers/infiniband/hw/hfi1/mmu_rb.c
+++ b/drivers/infiniband/hw/hfi1/mmu_rb.c
@@ -67,6 +67,8 @@ struct mmu_rb_handler {
static unsigned long mmu_node_start(struct mmu_rb_node *);
static unsigned long mmu_node_last(struct mmu_rb_node *);
+static inline void mmu_notifier_page(struct mmu_notifier *, struct mm_struct *,
+ unsigned long);
static inline void mmu_notifier_range_start(struct mmu_notifier *,
struct mm_struct *,
unsigned long, unsigned long);
@@ -80,6 +82,7 @@ static void do_remove(struct mmu_rb_handler *handler,
static void handle_remove(struct work_struct *work);
static const struct mmu_notifier_ops mn_opts = {
+ .invalidate_page = mmu_notifier_page,
.invalidate_range_start = mmu_notifier_range_start,
};
@@ -282,6 +285,12 @@ void hfi1_mmu_rb_remove(struct mmu_rb_handler *handler,
handler->ops->remove(handler->ops_arg, node);
}
+static inline void mmu_notifier_page(struct mmu_notifier *mn,
+ struct mm_struct *mm, unsigned long addr)
+{
+ mmu_notifier_mem_invalidate(mn, mm, addr, addr + PAGE_SIZE);
+}
+
static inline void mmu_notifier_range_start(struct mmu_notifier *mn,
struct mm_struct *mm,
unsigned long start,
diff --git a/drivers/iommu/amd_iommu_v2.c b/drivers/iommu/amd_iommu_v2.c
index dccf5b76eff2..6629c472eafd 100644
--- a/drivers/iommu/amd_iommu_v2.c
+++ b/drivers/iommu/amd_iommu_v2.c
@@ -391,6 +391,13 @@ static int mn_clear_flush_young(struct mmu_notifier *mn,
return 0;
}
+static void mn_invalidate_page(struct mmu_notifier *mn,
+ struct mm_struct *mm,
+ unsigned long address)
+{
+ __mn_flush_page(mn, address);
+}
+
static void mn_invalidate_range(struct mmu_notifier *mn,
struct mm_struct *mm,
unsigned long start, unsigned long end)
@@ -429,6 +436,7 @@ static void mn_release(struct mmu_notifier *mn, struct mm_struct *mm)
static const struct mmu_notifier_ops iommu_mn = {
.release = mn_release,
.clear_flush_young = mn_clear_flush_young,
+ .invalidate_page = mn_invalidate_page,
.invalidate_range = mn_invalidate_range,
};
diff --git a/drivers/iommu/intel-svm.c b/drivers/iommu/intel-svm.c
index f620dccec8ee..f167c0d84ebf 100644
--- a/drivers/iommu/intel-svm.c
+++ b/drivers/iommu/intel-svm.c
@@ -223,6 +223,14 @@ static void intel_change_pte(struct mmu_notifier *mn, struct mm_struct *mm,
intel_flush_svm_range(svm, address, 1, 1, 0);
}
+static void intel_invalidate_page(struct mmu_notifier *mn, struct mm_struct *mm,
+ unsigned long address)
+{
+ struct intel_svm *svm = container_of(mn, struct intel_svm, notifier);
+
+ intel_flush_svm_range(svm, address, 1, 1, 0);
+}
+
/* Pages have been freed at this point */
static void intel_invalidate_range(struct mmu_notifier *mn,
struct mm_struct *mm,
@@ -277,6 +285,7 @@ static void intel_mm_release(struct mmu_notifier *mn, struct mm_struct *mm)
static const struct mmu_notifier_ops intel_mmuops = {
.release = intel_mm_release,
.change_pte = intel_change_pte,
+ .invalidate_page = intel_invalidate_page,
.invalidate_range = intel_invalidate_range,
};
diff --git a/drivers/misc/mic/scif/scif_dma.c b/drivers/misc/mic/scif/scif_dma.c
index 63d6246d6dff..64d5760d069a 100644
--- a/drivers/misc/mic/scif/scif_dma.c
+++ b/drivers/misc/mic/scif/scif_dma.c
@@ -200,6 +200,16 @@ static void scif_mmu_notifier_release(struct mmu_notifier *mn,
schedule_work(&scif_info.misc_work);
}
+static void scif_mmu_notifier_invalidate_page(struct mmu_notifier *mn,
+ struct mm_struct *mm,
+ unsigned long address)
+{
+ struct scif_mmu_notif *mmn;
+
+ mmn = container_of(mn, struct scif_mmu_notif, ep_mmu_notifier);
+ scif_rma_destroy_tcw(mmn, address, PAGE_SIZE);
+}
+
static void scif_mmu_notifier_invalidate_range_start(struct mmu_notifier *mn,
struct mm_struct *mm,
unsigned long start,
@@ -225,6 +235,7 @@ static void scif_mmu_notifier_invalidate_range_end(struct mmu_notifier *mn,
static const struct mmu_notifier_ops scif_mmu_notifier_ops = {
.release = scif_mmu_notifier_release,
.clear_flush_young = NULL,
+ .invalidate_page = scif_mmu_notifier_invalidate_page,
.invalidate_range_start = scif_mmu_notifier_invalidate_range_start,
.invalidate_range_end = scif_mmu_notifier_invalidate_range_end};
diff --git a/drivers/misc/sgi-gru/grutlbpurge.c b/drivers/misc/sgi-gru/grutlbpurge.c
index 9918eda0e05f..e936d43895d2 100644
--- a/drivers/misc/sgi-gru/grutlbpurge.c
+++ b/drivers/misc/sgi-gru/grutlbpurge.c
@@ -247,6 +247,17 @@ static void gru_invalidate_range_end(struct mmu_notifier *mn,
gru_dbg(grudev, "gms %p, start 0x%lx, end 0x%lx\n", gms, start, end);
}
+static void gru_invalidate_page(struct mmu_notifier *mn, struct mm_struct *mm,
+ unsigned long address)
+{
+ struct gru_mm_struct *gms = container_of(mn, struct gru_mm_struct,
+ ms_notifier);
+
+ STAT(mmu_invalidate_page);
+ gru_flush_tlb_range(gms, address, PAGE_SIZE);
+ gru_dbg(grudev, "gms %p, address 0x%lx\n", gms, address);
+}
+
static void gru_release(struct mmu_notifier *mn, struct mm_struct *mm)
{
struct gru_mm_struct *gms = container_of(mn, struct gru_mm_struct,
@@ -258,6 +269,7 @@ static void gru_release(struct mmu_notifier *mn, struct mm_struct *mm)
static const struct mmu_notifier_ops gru_mmuops = {
+ .invalidate_page = gru_invalidate_page,
.invalidate_range_start = gru_invalidate_range_start,
.invalidate_range_end = gru_invalidate_range_end,
.release = gru_release,
diff --git a/drivers/xen/gntdev.c b/drivers/xen/gntdev.c
index 82360594fa8e..f3bf8f4e2d6c 100644
--- a/drivers/xen/gntdev.c
+++ b/drivers/xen/gntdev.c
@@ -484,6 +484,13 @@ static void mn_invl_range_start(struct mmu_notifier *mn,
mutex_unlock(&priv->lock);
}
+static void mn_invl_page(struct mmu_notifier *mn,
+ struct mm_struct *mm,
+ unsigned long address)
+{
+ mn_invl_range_start(mn, mm, address, address + PAGE_SIZE);
+}
+
static void mn_release(struct mmu_notifier *mn,
struct mm_struct *mm)
{
@@ -515,6 +522,7 @@ static void mn_release(struct mmu_notifier *mn,
static const struct mmu_notifier_ops gntdev_mmu_ops = {
.release = mn_release,
+ .invalidate_page = mn_invl_page,
.invalidate_range_start = mn_invl_range_start,
};
diff --git a/fs/dax.c b/fs/dax.c
index fa8e358c3c6b..57da1d0a6a40 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -591,10 +591,11 @@ static void dax_mapping_entry_mkclean(struct address_space *mapping,
pte_t pte, *ptep = NULL;
pmd_t *pmdp = NULL;
spinlock_t *ptl;
+ bool changed;
i_mmap_lock_read(mapping);
vma_interval_tree_foreach(vma, &mapping->i_mmap, index, index) {
- unsigned long address, start, end;
+ unsigned long address;
cond_resched();
@@ -602,13 +603,8 @@ static void dax_mapping_entry_mkclean(struct address_space *mapping,
continue;
address = pgoff_address(index, vma);
-
- /*
- * Note because we provide start/end to follow_pte_pmd it will
- * call mmu_notifier_invalidate_range_start() on our behalf
- * before taking any lock.
- */
- if (follow_pte_pmd(vma->vm_mm, address, &start, &end, &ptep, &pmdp, &ptl))
+ changed = false;
+ if (follow_pte_pmd(vma->vm_mm, address, &ptep, &pmdp, &ptl))
continue;
if (pmdp) {
@@ -625,7 +621,7 @@ static void dax_mapping_entry_mkclean(struct address_space *mapping,
pmd = pmd_wrprotect(pmd);
pmd = pmd_mkclean(pmd);
set_pmd_at(vma->vm_mm, address, pmdp, pmd);
- mmu_notifier_invalidate_range(vma->vm_mm, start, end);
+ changed = true;
unlock_pmd:
spin_unlock(ptl);
#endif
@@ -640,12 +636,13 @@ static void dax_mapping_entry_mkclean(struct address_space *mapping,
pte = pte_wrprotect(pte);
pte = pte_mkclean(pte);
set_pte_at(vma->vm_mm, address, ptep, pte);
- mmu_notifier_invalidate_range(vma->vm_mm, start, end);
+ changed = true;
unlock_pte:
pte_unmap_unlock(ptep, ptl);
}
- mmu_notifier_invalidate_range_end(vma->vm_mm, start, end);
+ if (changed)
+ mmu_notifier_invalidate_page(vma->vm_mm, address);
}
i_mmap_unlock_read(mapping);
}
diff --git a/mm/memory.c b/mm/memory.c
index 969c5bf31997..7834310a6b64 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -4044,8 +4044,7 @@ int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address)
#endif /* __PAGETABLE_PMD_FOLDED */
static int __follow_pte_pmd(struct mm_struct *mm, unsigned long address,
- unsigned long *start, unsigned long *end,
- pte_t **ptepp, pmd_t **pmdpp, spinlock_t **ptlp)
+ pte_t **ptepp, pmd_t **pmdpp, spinlock_t **ptlp)
{
pgd_t *pgd;
p4d_t *p4d;
@@ -4072,29 +4071,17 @@ static int __follow_pte_pmd(struct mm_struct *mm, unsigned long address,
if (!pmdpp)
goto out;
- if (start && end) {
- *start = address & PMD_MASK;
- *end = *start + PMD_SIZE;
- mmu_notifier_invalidate_range_start(mm, *start, *end);
- }
*ptlp = pmd_lock(mm, pmd);
if (pmd_huge(*pmd)) {
*pmdpp = pmd;
return 0;
}
spin_unlock(*ptlp);
- if (start && end)
- mmu_notifier_invalidate_range_end(mm, *start, *end);
}
if (pmd_none(*pmd) || unlikely(pmd_bad(*pmd)))
goto out;
- if (start && end) {
- *start = address & PAGE_MASK;
- *end = *start + PAGE_SIZE;
- mmu_notifier_invalidate_range_start(mm, *start, *end);
- }
ptep = pte_offset_map_lock(mm, pmd, address, ptlp);
if (!pte_present(*ptep))
goto unlock;
@@ -4102,8 +4089,6 @@ static int __follow_pte_pmd(struct mm_struct *mm, unsigned long address,
return 0;
unlock:
pte_unmap_unlock(ptep, *ptlp);
- if (start && end)
- mmu_notifier_invalidate_range_end(mm, *start, *end);
out:
return -EINVAL;
}
@@ -4115,21 +4100,20 @@ static inline int follow_pte(struct mm_struct *mm, unsigned long address,
/* (void) is needed to make gcc happy */
(void) __cond_lock(*ptlp,
- !(res = __follow_pte_pmd(mm, address, NULL, NULL,
- ptepp, NULL, ptlp)));
+ !(res = __follow_pte_pmd(mm, address, ptepp, NULL,
+ ptlp)));
return res;
}
int follow_pte_pmd(struct mm_struct *mm, unsigned long address,
- unsigned long *start, unsigned long *end,
pte_t **ptepp, pmd_t **pmdpp, spinlock_t **ptlp)
{
int res;
/* (void) is needed to make gcc happy */
(void) __cond_lock(*ptlp,
- !(res = __follow_pte_pmd(mm, address, start, end,
- ptepp, pmdpp, ptlp)));
+ !(res = __follow_pte_pmd(mm, address, ptepp, pmdpp,
+ ptlp)));
return res;
}
EXPORT_SYMBOL(follow_pte_pmd);
diff --git a/mm/mmu_notifier.c b/mm/mmu_notifier.c
index 314285284e6e..54ca54562928 100644
--- a/mm/mmu_notifier.c
+++ b/mm/mmu_notifier.c
@@ -174,6 +174,20 @@ void __mmu_notifier_change_pte(struct mm_struct *mm, unsigned long address,
srcu_read_unlock(&srcu, id);
}
+void __mmu_notifier_invalidate_page(struct mm_struct *mm,
+ unsigned long address)
+{
+ struct mmu_notifier *mn;
+ int id;
+
+ id = srcu_read_lock(&srcu);
+ hlist_for_each_entry_rcu(mn, &mm->mmu_notifier_mm->list, hlist) {
+ if (mn->ops->invalidate_page)
+ mn->ops->invalidate_page(mn, mm, address);
+ }
+ srcu_read_unlock(&srcu, id);
+}
+
void __mmu_notifier_invalidate_range_start(struct mm_struct *mm,
unsigned long start, unsigned long end)
{
diff --git a/mm/rmap.c b/mm/rmap.c
index c570f82e6827..c8993c63eb25 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -887,21 +887,11 @@ static bool page_mkclean_one(struct page *page, struct vm_area_struct *vma,
.address = address,
.flags = PVMW_SYNC,
};
- unsigned long start = address, end;
int *cleaned = arg;
- /*
- * We have to assume the worse case ie pmd for invalidation. Note that
- * the page can not be free from this function.
- */
- end = min(vma->vm_end, start + (PAGE_SIZE << compound_order(page)));
- mmu_notifier_invalidate_range_start(vma->vm_mm, start, end);
-
while (page_vma_mapped_walk(&pvmw)) {
- unsigned long cstart, cend;
int ret = 0;
-
- cstart = address = pvmw.address;
+ address = pvmw.address;
if (pvmw.pte) {
pte_t entry;
pte_t *pte = pvmw.pte;
@@ -914,7 +904,6 @@ static bool page_mkclean_one(struct page *page, struct vm_area_struct *vma,
entry = pte_wrprotect(entry);
entry = pte_mkclean(entry);
set_pte_at(vma->vm_mm, address, pte, entry);
- cend = cstart + PAGE_SIZE;
ret = 1;
} else {
#ifdef CONFIG_TRANSPARENT_HUGE_PAGECACHE
@@ -929,8 +918,6 @@ static bool page_mkclean_one(struct page *page, struct vm_area_struct *vma,
entry = pmd_wrprotect(entry);
entry = pmd_mkclean(entry);
set_pmd_at(vma->vm_mm, address, pmd, entry);
- cstart &= PMD_MASK;
- cend = cstart + PMD_SIZE;
ret = 1;
#else
/* unexpected pmd-mapped page? */
@@ -939,13 +926,11 @@ static bool page_mkclean_one(struct page *page, struct vm_area_struct *vma,
}
if (ret) {
- mmu_notifier_invalidate_range(vma->vm_mm, cstart, cend);
+ mmu_notifier_invalidate_page(vma->vm_mm, address);
(*cleaned)++;
}
}
- mmu_notifier_invalidate_range_end(vma->vm_mm, start, end);
-
return true;
}
@@ -1339,7 +1324,6 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
pte_t pteval;
struct page *subpage;
bool ret = true;
- unsigned long start = address, end;
enum ttu_flags flags = (enum ttu_flags)arg;
/* munlock has nothing to gain from examining un-locked vmas */
@@ -1351,14 +1335,6 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
flags & TTU_MIGRATION, page);
}
- /*
- * We have to assume the worse case ie pmd for invalidation. Note that
- * the page can not be free in this function as call of try_to_unmap()
- * must hold a reference on the page.
- */
- end = min(vma->vm_end, start + (PAGE_SIZE << compound_order(page)));
- mmu_notifier_invalidate_range_start(vma->vm_mm, start, end);
-
while (page_vma_mapped_walk(&pvmw)) {
/*
* If the page is mlock()d, we cannot swap it out.
@@ -1469,7 +1445,6 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
if (unlikely(PageSwapBacked(page) != PageSwapCache(page))) {
WARN_ON_ONCE(1);
ret = false;
- /* We have to invalidate as we cleared the pte */
page_vma_mapped_walk_done(&pvmw);
break;
}
@@ -1515,12 +1490,8 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
discard:
page_remove_rmap(subpage, PageHuge(page));
put_page(page);
- mmu_notifier_invalidate_range(mm, address,
- address + PAGE_SIZE);
+ mmu_notifier_invalidate_page(mm, address);
}
-
- mmu_notifier_invalidate_range_end(vma->vm_mm, start, end);
-
return ret;
}
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index bfa9c4d34102..1d048ef969a8 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -322,6 +322,47 @@ static inline struct kvm *mmu_notifier_to_kvm(struct mmu_notifier *mn)
return container_of(mn, struct kvm, mmu_notifier);
}
+static void kvm_mmu_notifier_invalidate_page(struct mmu_notifier *mn,
+ struct mm_struct *mm,
+ unsigned long address)
+{
+ struct kvm *kvm = mmu_notifier_to_kvm(mn);
+ int need_tlb_flush, idx;
+
+ /*
+ * When ->invalidate_page runs, the linux pte has been zapped
+ * already but the page is still allocated until
+ * ->invalidate_page returns. So if we increase the sequence
+ * here the kvm page fault will notice if the spte can't be
+ * established because the page is going to be freed. If
+ * instead the kvm page fault establishes the spte before
+ * ->invalidate_page runs, kvm_unmap_hva will release it
+ * before returning.
+ *
+ * The sequence increase only need to be seen at spin_unlock
+ * time, and not at spin_lock time.
+ *
+ * Increasing the sequence after the spin_unlock would be
+ * unsafe because the kvm page fault could then establish the
+ * pte after kvm_unmap_hva returned, without noticing the page
+ * is going to be freed.
+ */
+ idx = srcu_read_lock(&kvm->srcu);
+ spin_lock(&kvm->mmu_lock);
+
+ kvm->mmu_notifier_seq++;
+ need_tlb_flush = kvm_unmap_hva(kvm, address) | kvm->tlbs_dirty;
+ /* we've to flush the tlb before the pages can be freed */
+ if (need_tlb_flush)
+ kvm_flush_remote_tlbs(kvm);
+
+ spin_unlock(&kvm->mmu_lock);
+
+ kvm_arch_mmu_notifier_invalidate_page(kvm, address);
+
+ srcu_read_unlock(&kvm->srcu, idx);
+}
+
static void kvm_mmu_notifier_change_pte(struct mmu_notifier *mn,
struct mm_struct *mm,
unsigned long address,
@@ -469,6 +510,7 @@ static void kvm_mmu_notifier_release(struct mmu_notifier *mn,
}
static const struct mmu_notifier_ops kvm_mmu_notifier_ops = {
+ .invalidate_page = kvm_mmu_notifier_invalidate_page,
.invalidate_range_start = kvm_mmu_notifier_invalidate_range_start,
.invalidate_range_end = kvm_mmu_notifier_invalidate_range_end,
.clear_flush_young = kvm_mmu_notifier_clear_flush_young,
--
2.14.2