From: Anup Patel <Anup.Patel@wdc.com>
To: Palmer Dabbelt <palmer@dabbelt.com>,
Paul Walmsley <paul.walmsley@sifive.com>,
Albert Ou <aou@eecs.berkeley.edu>,
Paolo Bonzini <pbonzini@redhat.com>, Radim K <rkrcmar@redhat.com>
Cc: Damien Le Moal <Damien.LeMoal@wdc.com>,
"kvm@vger.kernel.org" <kvm@vger.kernel.org>,
Anup Patel <anup@brainfault.org>, Anup Patel <Anup.Patel@wdc.com>,
"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
Atish Patra <Atish.Patra@wdc.com>,
Alistair Francis <Alistair.Francis@wdc.com>,
"kvm-riscv@lists.infradead.org" <kvm-riscv@lists.infradead.org>,
Alexander Graf <graf@amazon.com>,
"linux-riscv@lists.infradead.org"
<linux-riscv@lists.infradead.org>, Christoph Hellwig <hch@lst.de>
Subject: [PATCH v10 13/19] RISC-V: KVM: Implement MMU notifiers
Date: Mon, 23 Dec 2019 11:37:00 +0000
Message-ID: <20191223113443.68969-14-anup.patel@wdc.com> (raw)
In-Reply-To: <20191223113443.68969-1-anup.patel@wdc.com>
This patch implements MMU notifiers for KVM RISC-V so that Guest
physical address space is in-sync with Host physical address space.
This will allow swapping, page migration, etc to work transparently
with KVM RISC-V.
Signed-off-by: Anup Patel <anup.patel@wdc.com>
Acked-by: Paolo Bonzini <pbonzini@redhat.com>
Reviewed-by: Paolo Bonzini <pbonzini@redhat.com>
Reviewed-by: Alexander Graf <graf@amazon.com>
---
arch/riscv/include/asm/kvm_host.h | 7 ++
arch/riscv/kvm/Kconfig | 1 +
arch/riscv/kvm/mmu.c | 129 +++++++++++++++++++++++++++++-
arch/riscv/kvm/vm.c | 1 +
4 files changed, 137 insertions(+), 1 deletion(-)
diff --git a/arch/riscv/include/asm/kvm_host.h b/arch/riscv/include/asm/kvm_host.h
index dd1acb011fff..cc0b09918431 100644
--- a/arch/riscv/include/asm/kvm_host.h
+++ b/arch/riscv/include/asm/kvm_host.h
@@ -190,6 +190,13 @@ static inline void kvm_arch_vcpu_uninit(struct kvm_vcpu *vcpu) {}
static inline void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) {}
static inline void kvm_arch_vcpu_block_finish(struct kvm_vcpu *vcpu) {}
+#define KVM_ARCH_WANT_MMU_NOTIFIER
+int kvm_unmap_hva_range(struct kvm *kvm,
+ unsigned long start, unsigned long end);
+int 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);
+
void __kvm_riscv_hfence_gvma_vmid_gpa(unsigned long vmid,
unsigned long gpa);
void __kvm_riscv_hfence_gvma_vmid(unsigned long vmid);
diff --git a/arch/riscv/kvm/Kconfig b/arch/riscv/kvm/Kconfig
index 88edd477b3a8..2356dc52ebb3 100644
--- a/arch/riscv/kvm/Kconfig
+++ b/arch/riscv/kvm/Kconfig
@@ -20,6 +20,7 @@ if VIRTUALIZATION
config KVM
tristate "Kernel-based Virtual Machine (KVM) support (EXPERIMENTAL)"
depends on RISCV_SBI && MMU
+ select MMU_NOTIFIER
select PREEMPT_NOTIFIERS
select ANON_INODES
select KVM_MMIO
diff --git a/arch/riscv/kvm/mmu.c b/arch/riscv/kvm/mmu.c
index f491c6aa4502..d88a50cde750 100644
--- a/arch/riscv/kvm/mmu.c
+++ b/arch/riscv/kvm/mmu.c
@@ -369,6 +369,38 @@ int stage2_ioremap(struct kvm *kvm, gpa_t gpa, phys_addr_t hpa,
}
+static int handle_hva_to_gpa(struct kvm *kvm,
+ unsigned long start,
+ unsigned long end,
+ int (*handler)(struct kvm *kvm,
+ gpa_t gpa, u64 size,
+ void *data),
+ void *data)
+{
+ struct kvm_memslots *slots;
+ struct kvm_memory_slot *memslot;
+ int ret = 0;
+
+ slots = kvm_memslots(kvm);
+
+ /* we only care about the pages that the guest sees */
+ kvm_for_each_memslot(memslot, slots) {
+ unsigned long hva_start, hva_end;
+ gfn_t gpa;
+
+ hva_start = max(start, memslot->userspace_addr);
+ hva_end = min(end, memslot->userspace_addr +
+ (memslot->npages << PAGE_SHIFT));
+ if (hva_start >= hva_end)
+ continue;
+
+ gpa = hva_to_gfn_memslot(hva_start, memslot) << PAGE_SHIFT;
+ ret |= handler(kvm, gpa, (u64)(hva_end - hva_start), data);
+ }
+
+ return ret;
+}
+
void kvm_arch_free_memslot(struct kvm *kvm, struct kvm_memory_slot *free,
struct kvm_memory_slot *dont)
{
@@ -501,6 +533,95 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm,
return ret;
}
+static int kvm_unmap_hva_handler(struct kvm *kvm,
+ gpa_t gpa, u64 size, void *data)
+{
+ stage2_unmap_range(kvm, gpa, size);
+ return 0;
+}
+
+int kvm_unmap_hva_range(struct kvm *kvm,
+ unsigned long start, unsigned long end)
+{
+ if (!kvm->arch.pgd)
+ return 0;
+
+ handle_hva_to_gpa(kvm, start, end,
+ &kvm_unmap_hva_handler, NULL);
+ return 0;
+}
+
+static int kvm_set_spte_handler(struct kvm *kvm,
+ gpa_t gpa, u64 size, void *data)
+{
+ pte_t *pte = (pte_t *)data;
+
+ WARN_ON(size != PAGE_SIZE);
+ stage2_set_pte(kvm, 0, NULL, gpa, pte);
+
+ return 0;
+}
+
+int kvm_set_spte_hva(struct kvm *kvm, unsigned long hva, pte_t pte)
+{
+ unsigned long end = hva + PAGE_SIZE;
+ kvm_pfn_t pfn = pte_pfn(pte);
+ pte_t stage2_pte;
+
+ if (!kvm->arch.pgd)
+ return 0;
+
+ stage2_pte = pfn_pte(pfn, PAGE_WRITE_EXEC);
+ handle_hva_to_gpa(kvm, hva, end,
+ &kvm_set_spte_handler, &stage2_pte);
+
+ return 0;
+}
+
+static int kvm_age_hva_handler(struct kvm *kvm,
+ gpa_t gpa, u64 size, void *data)
+{
+ pte_t *ptep;
+ u32 ptep_level = 0;
+
+ WARN_ON(size != PAGE_SIZE && size != PMD_SIZE && size != PGDIR_SIZE);
+
+ if (!stage2_get_leaf_entry(kvm, gpa, &ptep, &ptep_level))
+ return 0;
+
+ return ptep_test_and_clear_young(NULL, 0, ptep);
+}
+
+int kvm_age_hva(struct kvm *kvm, unsigned long start, unsigned long end)
+{
+ if (!kvm->arch.pgd)
+ return 0;
+
+ return handle_hva_to_gpa(kvm, start, end, kvm_age_hva_handler, NULL);
+}
+
+static int kvm_test_age_hva_handler(struct kvm *kvm,
+ gpa_t gpa, u64 size, void *data)
+{
+ pte_t *ptep;
+ u32 ptep_level = 0;
+
+ WARN_ON(size != PAGE_SIZE && size != PMD_SIZE);
+ if (!stage2_get_leaf_entry(kvm, gpa, &ptep, &ptep_level))
+ return 0;
+
+ return pte_young(*ptep);
+}
+
+int kvm_test_age_hva(struct kvm *kvm, unsigned long hva)
+{
+ if (!kvm->arch.pgd)
+ return 0;
+
+ return handle_hva_to_gpa(kvm, hva, hva,
+ kvm_test_age_hva_handler, NULL);
+}
+
int kvm_riscv_stage2_map(struct kvm_vcpu *vcpu, gpa_t gpa, unsigned long hva,
bool is_write)
{
@@ -512,7 +633,7 @@ int kvm_riscv_stage2_map(struct kvm_vcpu *vcpu, gpa_t gpa, unsigned long hva,
struct vm_area_struct *vma;
struct kvm *kvm = vcpu->kvm;
struct kvm_mmu_page_cache *pcache = &vcpu->arch.mmu_page_cache;
- unsigned long vma_pagesize;
+ unsigned long vma_pagesize, mmu_seq;
down_read(¤t->mm->mmap_sem);
@@ -545,6 +666,8 @@ int kvm_riscv_stage2_map(struct kvm_vcpu *vcpu, gpa_t gpa, unsigned long hva,
return ret;
}
+ mmu_seq = kvm->mmu_notifier_seq;
+
hfn = gfn_to_pfn_prot(kvm, gfn, is_write, &writeable);
if (hfn == KVM_PFN_ERR_HWPOISON) {
if (is_vm_hugetlb_page(vma))
@@ -563,6 +686,9 @@ int kvm_riscv_stage2_map(struct kvm_vcpu *vcpu, gpa_t gpa, unsigned long hva,
spin_lock(&kvm->mmu_lock);
+ if (mmu_notifier_retry(kvm, mmu_seq))
+ goto out_unlock;
+
if (writeable) {
kvm_set_pfn_dirty(hfn);
ret = stage2_map_page(kvm, pcache, gpa, hfn << PAGE_SHIFT,
@@ -575,6 +701,7 @@ int kvm_riscv_stage2_map(struct kvm_vcpu *vcpu, gpa_t gpa, unsigned long hva,
if (ret)
kvm_err("Failed to map in stage2\n");
+out_unlock:
spin_unlock(&kvm->mmu_lock);
kvm_set_pfn_accessed(hfn);
kvm_release_pfn_clean(hfn);
diff --git a/arch/riscv/kvm/vm.c b/arch/riscv/kvm/vm.c
index c5aab5478c38..fd84b4d914dc 100644
--- a/arch/riscv/kvm/vm.c
+++ b/arch/riscv/kvm/vm.c
@@ -54,6 +54,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
switch (ext) {
case KVM_CAP_DEVICE_CTRL:
case KVM_CAP_USER_MEMORY:
+ case KVM_CAP_SYNC_MMU:
case KVM_CAP_DESTROY_MEMORY_REGION_WORKS:
case KVM_CAP_ONE_REG:
case KVM_CAP_READONLY_MEM:
--
2.17.1
next prev parent reply index
Thread overview: 30+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-12-23 11:35 [PATCH v10 00/19] KVM RISC-V Support Anup Patel
2019-12-23 11:35 ` [PATCH v10 01/19] RISC-V: Export riscv_cpuid_to_hartid_mask() API Anup Patel
2019-12-23 11:35 ` [PATCH v10 02/19] RISC-V: Add bitmap reprensenting ISA features common across CPUs Anup Patel
2019-12-23 11:35 ` [PATCH v10 03/19] RISC-V: Add hypervisor extension related CSR defines Anup Patel
2019-12-23 11:35 ` [PATCH v10 04/19] RISC-V: Add initial skeletal KVM support Anup Patel
2019-12-23 11:35 ` [PATCH v10 05/19] RISC-V: KVM: Implement VCPU create, init and destroy functions Anup Patel
2019-12-23 11:36 ` [PATCH v10 06/19] RISC-V: KVM: Implement VCPU interrupts and requests handling Anup Patel
2019-12-23 11:36 ` [PATCH v10 07/19] RISC-V: KVM: Implement KVM_GET_ONE_REG/KVM_SET_ONE_REG ioctls Anup Patel
2019-12-23 11:36 ` [PATCH v10 08/19] RISC-V: KVM: Implement VCPU world-switch Anup Patel
2019-12-23 11:36 ` [PATCH v10 09/19] RISC-V: KVM: Handle MMIO exits for VCPU Anup Patel
2019-12-23 11:36 ` [PATCH v10 10/19] RISC-V: KVM: Handle WFI " Anup Patel
2019-12-23 11:36 ` [PATCH v10 11/19] RISC-V: KVM: Implement VMID allocator Anup Patel
2019-12-23 11:36 ` [PATCH v10 12/19] RISC-V: KVM: Implement stage2 page table programming Anup Patel
2019-12-23 11:37 ` Anup Patel [this message]
2019-12-23 11:37 ` [PATCH v10 14/19] RISC-V: KVM: Add timer functionality Anup Patel
2019-12-23 11:37 ` [PATCH v10 15/19] RISC-V: KVM: FP lazy save/restore Anup Patel
2019-12-23 11:37 ` [PATCH v10 16/19] RISC-V: KVM: Implement ONE REG interface for FP registers Anup Patel
2019-12-23 11:37 ` [PATCH v10 17/19] RISC-V: KVM: Add SBI v0.1 support Anup Patel
2019-12-23 11:37 ` [PATCH v10 18/19] RISC-V: KVM: Document RISC-V specific parts of KVM API Anup Patel
2019-12-23 11:37 ` [PATCH v10 19/19] RISC-V: KVM: Add MAINTAINERS entry Anup Patel
2020-01-16 1:45 ` [PATCH v10 00/19] KVM RISC-V Support Palmer Dabbelt
2020-01-16 16:51 ` [PATCH v10 01/19] RISC-V: Export riscv_cpuid_to_hartid_mask() API Palmer Dabbelt
2020-01-16 19:51 ` [PATCH v10 02/19] RISC-V: Add bitmap reprensenting ISA features common across CPUs Palmer Dabbelt
2020-01-17 6:45 ` Anup Patel
2020-01-16 19:51 ` [PATCH v10 03/19] RISC-V: Add hypervisor extension related CSR defines Palmer Dabbelt
2020-01-17 7:14 ` Anup Patel
2020-01-16 23:37 ` [PATCH v10 04/19] RISC-V: Add initial skeletal KVM support Palmer Dabbelt
2020-01-17 7:11 ` Anup Patel
2020-01-22 19:04 ` [PATCH v10 05/19] RISC-V: KVM: Implement VCPU create, init and destroy functions Palmer Dabbelt
2020-01-23 3:34 ` Anup Patel
Reply instructions:
You may reply publically to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20191223113443.68969-14-anup.patel@wdc.com \
--to=anup.patel@wdc.com \
--cc=Alistair.Francis@wdc.com \
--cc=Atish.Patra@wdc.com \
--cc=Damien.LeMoal@wdc.com \
--cc=anup@brainfault.org \
--cc=aou@eecs.berkeley.edu \
--cc=graf@amazon.com \
--cc=hch@lst.de \
--cc=kvm-riscv@lists.infradead.org \
--cc=kvm@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-riscv@lists.infradead.org \
--cc=palmer@dabbelt.com \
--cc=paul.walmsley@sifive.com \
--cc=pbonzini@redhat.com \
--cc=rkrcmar@redhat.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Linux-RISC-V Archive on lore.kernel.org
Archives are clonable:
git clone --mirror https://lore.kernel.org/linux-riscv/0 linux-riscv/git/0.git
# If you have public-inbox 1.1+ installed, you may
# initialize and index your mirror using the following commands:
public-inbox-init -V2 linux-riscv linux-riscv/ https://lore.kernel.org/linux-riscv \
linux-riscv@lists.infradead.org
public-inbox-index linux-riscv
Example config snippet for mirrors
Newsgroup available over NNTP:
nntp://nntp.lore.kernel.org/org.infradead.lists.linux-riscv
AGPL code for this site: git clone https://public-inbox.org/public-inbox.git