From: Peter Xu <peterx@redhat.com>
To: kvm@vger.kernel.org, linux-kernel@vger.kernel.org
Cc: peterx@redhat.com,
Sean Christopherson <sean.j.christopherson@intel.com>,
"Dr . David Alan Gilbert" <dgilbert@redhat.com>,
Andrew Jones <drjones@redhat.com>,
Paolo Bonzini <pbonzini@redhat.com>
Subject: [PATCH v11 02/13] KVM: X86: Don't track dirty for KVM_SET_[TSS_ADDR|IDENTITY_MAP_ADDR]
Date: Wed, 8 Jul 2020 15:33:57 -0400 [thread overview]
Message-ID: <20200708193408.242909-3-peterx@redhat.com> (raw)
In-Reply-To: <20200708193408.242909-1-peterx@redhat.com>
Originally, we have three code paths that can dirty a page without
vcpu context for X86:
- init_rmode_identity_map
- init_rmode_tss
- kvmgt_rw_gpa
init_rmode_identity_map and init_rmode_tss will be setup on
destination VM no matter what (and the guest cannot even see them), so
it does not make sense to track them at all.
To do this, allow __x86_set_memory_region() to return the userspace
address that just allocated to the caller. Then in both of the
functions we directly write to the userspace address instead of
calling kvm_write_*() APIs.
Another trivial change is that we don't need to explicitly clear the
identity page table root in init_rmode_identity_map() because no
matter what we'll write to the whole page with 4M huge page entries.
Suggested-by: Paolo Bonzini <pbonzini@redhat.com>
Signed-off-by: Peter Xu <peterx@redhat.com>
---
arch/x86/include/asm/kvm_host.h | 3 +-
arch/x86/kvm/svm/avic.c | 9 ++--
arch/x86/kvm/vmx/vmx.c | 88 ++++++++++++++++-----------------
arch/x86/kvm/x86.c | 37 +++++++++++---
4 files changed, 81 insertions(+), 56 deletions(-)
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 97cb005c7aa7..f26bc2bdacf4 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1647,7 +1647,8 @@ void __kvm_request_immediate_exit(struct kvm_vcpu *vcpu);
int kvm_is_in_guest(void);
-int __x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, u32 size);
+void __user *__x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa,
+ u32 size);
bool kvm_vcpu_is_reset_bsp(struct kvm_vcpu *vcpu);
bool kvm_vcpu_is_bsp(struct kvm_vcpu *vcpu);
diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c
index ac830cd50830..f9d665bbfd68 100644
--- a/arch/x86/kvm/svm/avic.c
+++ b/arch/x86/kvm/svm/avic.c
@@ -235,7 +235,8 @@ static u64 *avic_get_physical_id_entry(struct kvm_vcpu *vcpu,
*/
static int avic_update_access_page(struct kvm *kvm, bool activate)
{
- int ret = 0;
+ void __user *ret;
+ int r = 0;
mutex_lock(&kvm->slots_lock);
/*
@@ -251,13 +252,15 @@ static int avic_update_access_page(struct kvm *kvm, bool activate)
APIC_ACCESS_PAGE_PRIVATE_MEMSLOT,
APIC_DEFAULT_PHYS_BASE,
activate ? PAGE_SIZE : 0);
- if (ret)
+ if (IS_ERR(ret)) {
+ r = PTR_ERR(ret);
goto out;
+ }
kvm->arch.apic_access_page_done = activate;
out:
mutex_unlock(&kvm->slots_lock);
- return ret;
+ return r;
}
static int avic_init_backing_page(struct kvm_vcpu *vcpu)
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 8187ca152ad2..6e5208a735ec 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -3552,42 +3552,33 @@ static bool guest_state_valid(struct kvm_vcpu *vcpu)
return true;
}
-static int init_rmode_tss(struct kvm *kvm)
+static int init_rmode_tss(struct kvm *kvm, void __user *ua)
{
- gfn_t fn;
- u16 data = 0;
- int idx, r;
+ const void *zero_page = (const void *) __va(page_to_phys(ZERO_PAGE(0)));
+ u16 data;
+ int i;
+
+ for (i = 0; i < 3; i++) {
+ if (__copy_to_user(ua + PAGE_SIZE * i, zero_page, PAGE_SIZE))
+ return -EFAULT;
+ }
- idx = srcu_read_lock(&kvm->srcu);
- fn = to_kvm_vmx(kvm)->tss_addr >> PAGE_SHIFT;
- r = kvm_clear_guest_page(kvm, fn, 0, PAGE_SIZE);
- if (r < 0)
- goto out;
data = TSS_BASE_SIZE + TSS_REDIRECTION_SIZE;
- r = kvm_write_guest_page(kvm, fn++, &data,
- TSS_IOPB_BASE_OFFSET, sizeof(u16));
- if (r < 0)
- goto out;
- r = kvm_clear_guest_page(kvm, fn++, 0, PAGE_SIZE);
- if (r < 0)
- goto out;
- r = kvm_clear_guest_page(kvm, fn, 0, PAGE_SIZE);
- if (r < 0)
- goto out;
+ if (__copy_to_user(ua + TSS_IOPB_BASE_OFFSET, &data, sizeof(u16)))
+ return -EFAULT;
+
data = ~0;
- r = kvm_write_guest_page(kvm, fn, &data,
- RMODE_TSS_SIZE - 2 * PAGE_SIZE - 1,
- sizeof(u8));
-out:
- srcu_read_unlock(&kvm->srcu, idx);
- return r;
+ if (__copy_to_user(ua + RMODE_TSS_SIZE - 1, &data, sizeof(u8)))
+ return -EFAULT;
+
+ return 0;
}
static int init_rmode_identity_map(struct kvm *kvm)
{
struct kvm_vmx *kvm_vmx = to_kvm_vmx(kvm);
int i, r = 0;
- kvm_pfn_t identity_map_pfn;
+ void __user *uaddr;
u32 tmp;
/* Protect kvm_vmx->ept_identity_pagetable_done. */
@@ -3598,24 +3589,24 @@ static int init_rmode_identity_map(struct kvm *kvm)
if (!kvm_vmx->ept_identity_map_addr)
kvm_vmx->ept_identity_map_addr = VMX_EPT_IDENTITY_PAGETABLE_ADDR;
- identity_map_pfn = kvm_vmx->ept_identity_map_addr >> PAGE_SHIFT;
- r = __x86_set_memory_region(kvm, IDENTITY_PAGETABLE_PRIVATE_MEMSLOT,
- kvm_vmx->ept_identity_map_addr, PAGE_SIZE);
- if (r < 0)
+ uaddr = __x86_set_memory_region(kvm,
+ IDENTITY_PAGETABLE_PRIVATE_MEMSLOT,
+ kvm_vmx->ept_identity_map_addr,
+ PAGE_SIZE);
+ if (IS_ERR(uaddr)) {
+ r = PTR_ERR(uaddr);
goto out;
+ }
- r = kvm_clear_guest_page(kvm, identity_map_pfn, 0, PAGE_SIZE);
- if (r < 0)
- goto out;
/* Set up identity-mapping pagetable for EPT in real mode */
for (i = 0; i < PT32_ENT_PER_PAGE; i++) {
tmp = (i << 22) + (_PAGE_PRESENT | _PAGE_RW | _PAGE_USER |
_PAGE_ACCESSED | _PAGE_DIRTY | _PAGE_PSE);
- r = kvm_write_guest_page(kvm, identity_map_pfn,
- &tmp, i * sizeof(tmp), sizeof(tmp));
- if (r < 0)
+ if (__copy_to_user(uaddr + i * sizeof(tmp), &tmp, sizeof(tmp))) {
+ r = -EFAULT;
goto out;
+ }
}
kvm_vmx->ept_identity_pagetable_done = true;
@@ -3642,19 +3633,22 @@ static void seg_setup(int seg)
static int alloc_apic_access_page(struct kvm *kvm)
{
struct page *page;
- int r = 0;
+ void __user *hva;
+ int ret = 0;
mutex_lock(&kvm->slots_lock);
if (kvm->arch.apic_access_page_done)
goto out;
- r = __x86_set_memory_region(kvm, APIC_ACCESS_PAGE_PRIVATE_MEMSLOT,
- APIC_DEFAULT_PHYS_BASE, PAGE_SIZE);
- if (r)
+ hva = __x86_set_memory_region(kvm, APIC_ACCESS_PAGE_PRIVATE_MEMSLOT,
+ APIC_DEFAULT_PHYS_BASE, PAGE_SIZE);
+ if (IS_ERR(hva)) {
+ ret = PTR_ERR(hva);
goto out;
+ }
page = gfn_to_page(kvm, APIC_DEFAULT_PHYS_BASE >> PAGE_SHIFT);
if (is_error_page(page)) {
- r = -EFAULT;
+ ret = -EFAULT;
goto out;
}
@@ -3666,7 +3660,7 @@ static int alloc_apic_access_page(struct kvm *kvm)
kvm->arch.apic_access_page_done = true;
out:
mutex_unlock(&kvm->slots_lock);
- return r;
+ return ret;
}
int allocate_vpid(void)
@@ -4616,7 +4610,7 @@ static int vmx_interrupt_allowed(struct kvm_vcpu *vcpu, bool for_injection)
static int vmx_set_tss_addr(struct kvm *kvm, unsigned int addr)
{
- int ret;
+ void __user *ret;
if (enable_unrestricted_guest)
return 0;
@@ -4626,10 +4620,12 @@ static int vmx_set_tss_addr(struct kvm *kvm, unsigned int addr)
PAGE_SIZE * 3);
mutex_unlock(&kvm->slots_lock);
- if (ret)
- return ret;
+ if (IS_ERR(ret))
+ return PTR_ERR(ret);
+
to_kvm_vmx(kvm)->tss_addr = addr;
- return init_rmode_tss(kvm);
+
+ return init_rmode_tss(kvm, ret);
}
static int vmx_set_identity_map_addr(struct kvm *kvm, u64 ident_addr)
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 09ee54f5e385..65be4977f608 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -9959,7 +9959,32 @@ void kvm_arch_sync_events(struct kvm *kvm)
kvm_free_pit(kvm);
}
-int __x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, u32 size)
+#define ERR_PTR_USR(e) ((void __user *)ERR_PTR(e))
+
+/**
+ * __x86_set_memory_region: Setup KVM internal memory slot
+ *
+ * @kvm: the kvm pointer to the VM.
+ * @id: the slot ID to setup.
+ * @gpa: the GPA to install the slot (unused when @size == 0).
+ * @size: the size of the slot. Set to zero to uninstall a slot.
+ *
+ * This function helps to setup a KVM internal memory slot. Specify
+ * @size > 0 to install a new slot, while @size == 0 to uninstall a
+ * slot. The return code can be one of the following:
+ *
+ * HVA: on success (uninstall will return a bogus HVA)
+ * -errno: on error
+ *
+ * The caller should always use IS_ERR() to check the return value
+ * before use. Note, the KVM internal memory slots are guaranteed to
+ * remain valid and unchanged until the VM is destroyed, i.e., the
+ * GPA->HVA translation will not change. However, the HVA is a user
+ * address, i.e. its accessibility is not guaranteed, and must be
+ * accessed via __copy_{to,from}_user().
+ */
+void __user * __x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa,
+ u32 size)
{
int i, r;
unsigned long hva, uninitialized_var(old_npages);
@@ -9968,12 +9993,12 @@ int __x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, u32 size)
/* Called with kvm->slots_lock held. */
if (WARN_ON(id >= KVM_MEM_SLOTS_NUM))
- return -EINVAL;
+ return ERR_PTR_USR(-EINVAL);
slot = id_to_memslot(slots, id);
if (size) {
if (slot && slot->npages)
- return -EEXIST;
+ return ERR_PTR_USR(-EEXIST);
/*
* MAP_SHARED to prevent internal slot pages from being moved
@@ -9982,7 +10007,7 @@ int __x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, u32 size)
hva = vm_mmap(NULL, 0, size, PROT_READ | PROT_WRITE,
MAP_SHARED | MAP_ANONYMOUS, 0);
if (IS_ERR((void *)hva))
- return PTR_ERR((void *)hva);
+ return (void __user *)hva;
} else {
if (!slot || !slot->npages)
return 0;
@@ -10001,13 +10026,13 @@ int __x86_set_memory_region(struct kvm *kvm, int id, gpa_t gpa, u32 size)
m.memory_size = size;
r = __kvm_set_memory_region(kvm, &m);
if (r < 0)
- return r;
+ return ERR_PTR_USR(r);
}
if (!size)
vm_munmap(hva, old_npages * PAGE_SIZE);
- return 0;
+ return (void __user *)hva;
}
EXPORT_SYMBOL_GPL(__x86_set_memory_region);
--
2.26.2
next prev parent reply other threads:[~2020-07-08 19:34 UTC|newest]
Thread overview: 16+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-07-08 19:33 [PATCH v11 00/13] KVM: Dirty ring interface Peter Xu
2020-07-08 19:33 ` [PATCH v11 01/13] KVM: Cache as_id in kvm_memory_slot Peter Xu
2020-07-23 0:27 ` Sean Christopherson
2020-07-08 19:33 ` Peter Xu [this message]
2020-07-23 0:29 ` [PATCH v11 02/13] KVM: X86: Don't track dirty for KVM_SET_[TSS_ADDR|IDENTITY_MAP_ADDR] Sean Christopherson
2020-07-08 19:33 ` [PATCH v11 03/13] KVM: Pass in kvm pointer into mark_page_dirty_in_slot() Peter Xu
2020-07-08 19:33 ` [PATCH v11 04/13] KVM: X86: Implement ring-based dirty memory tracking Peter Xu
2020-07-08 19:34 ` [PATCH v11 05/13] KVM: Make dirty ring exclusive to dirty bitmap log Peter Xu
2020-07-08 19:34 ` [PATCH v11 06/13] KVM: Don't allocate dirty bitmap if dirty ring is enabled Peter Xu
2020-07-08 19:34 ` [PATCH v11 07/13] KVM: selftests: Always clear dirty bitmap after iteration Peter Xu
2020-07-08 19:34 ` [PATCH v11 08/13] KVM: selftests: Sync uapi/linux/kvm.h to tools/ Peter Xu
2020-07-08 19:34 ` [PATCH v11 09/13] KVM: selftests: Use a single binary for dirty/clear log test Peter Xu
2020-07-08 19:34 ` [PATCH v11 10/13] KVM: selftests: Introduce after_vcpu_run hook for dirty " Peter Xu
2020-07-08 19:34 ` [PATCH v11 11/13] KVM: selftests: Add dirty ring buffer test Peter Xu
2020-07-08 19:34 ` [PATCH v11 12/13] KVM: selftests: Let dirty_log_test async for dirty ring test Peter Xu
2020-07-08 19:34 ` [PATCH v11 13/13] KVM: selftests: Add "-c" parameter to dirty log test Peter Xu
Reply instructions:
You may reply publicly 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=20200708193408.242909-3-peterx@redhat.com \
--to=peterx@redhat.com \
--cc=dgilbert@redhat.com \
--cc=drjones@redhat.com \
--cc=kvm@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=pbonzini@redhat.com \
--cc=sean.j.christopherson@intel.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
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).