lkml.org 
[lkml]   [2022]   [Aug]   [7]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
Patch in this message
/
From
Subject[PATCH v8 060/103] KVM: TDX: Create initial guest memory
Date
From: Isaku Yamahata <isaku.yamahata@intel.com>

Because the guest memory is protected in TDX, the creation of the initial
guest memory requires a dedicated TDX module API, tdh_mem_page_add, instead
of directly copying the memory contents into the guest memory in the case
of the default VM type. KVM MMU page fault handler callback,
private_page_add, handles it.

Define new subcommand, KVM_TDX_INIT_MEM_REGION, of VM-scoped
KVM_MEMORY_ENCRYPT_OP. It assigns the guest page, copies the initial
memory contents into the guest memory, encrypts the guest memory. At the
same time, optionally it extends memory measurement of the TDX guest. It
calls the KVM MMU page fault(EPT-violation) handler to trigger the
callbacks for it.

Signed-off-by: Isaku Yamahata <isaku.yamahata@intel.com>
---
arch/x86/include/uapi/asm/kvm.h | 9 ++
arch/x86/kvm/mmu/mmu.c | 1 +
arch/x86/kvm/vmx/tdx.c | 147 +++++++++++++++++++++++++-
arch/x86/kvm/vmx/tdx.h | 2 +
tools/arch/x86/include/uapi/asm/kvm.h | 9 ++
5 files changed, 163 insertions(+), 5 deletions(-)

diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h
index 3cd723b7e2cf..787644687586 100644
--- a/arch/x86/include/uapi/asm/kvm.h
+++ b/arch/x86/include/uapi/asm/kvm.h
@@ -540,6 +540,7 @@ enum kvm_tdx_cmd_id {
KVM_TDX_CAPABILITIES = 0,
KVM_TDX_INIT_VM,
KVM_TDX_INIT_VCPU,
+ KVM_TDX_INIT_MEM_REGION,

KVM_TDX_CMD_NR_MAX,
};
@@ -617,4 +618,12 @@ struct kvm_tdx_init_vm {
};
};

+#define KVM_TDX_MEASURE_MEMORY_REGION (1UL << 0)
+
+struct kvm_tdx_init_mem_region {
+ __u64 source_addr;
+ __u64 gpa;
+ __u64 nr_pages;
+};
+
#endif /* _ASM_X86_KVM_H */
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 8d3b45db07eb..526bf5ecefbf 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -5423,6 +5423,7 @@ int kvm_mmu_load(struct kvm_vcpu *vcpu)
out:
return r;
}
+EXPORT_SYMBOL(kvm_mmu_load);

void kvm_mmu_unload(struct kvm_vcpu *vcpu)
{
diff --git a/arch/x86/kvm/vmx/tdx.c b/arch/x86/kvm/vmx/tdx.c
index edb5af011794..7970a2cfa909 100644
--- a/arch/x86/kvm/vmx/tdx.c
+++ b/arch/x86/kvm/vmx/tdx.c
@@ -544,6 +544,21 @@ void tdx_load_mmu_pgd(struct kvm_vcpu *vcpu, hpa_t root_hpa, int pgd_level)
td_vmcs_write64(to_tdx(vcpu), SHARED_EPT_POINTER, root_hpa & PAGE_MASK);
}

+static void tdx_measure_page(struct kvm_tdx *kvm_tdx, hpa_t gpa)
+{
+ struct tdx_module_output out;
+ u64 err;
+ int i;
+
+ for (i = 0; i < PAGE_SIZE; i += TDX_EXTENDMR_CHUNKSIZE) {
+ err = tdh_mr_extend(kvm_tdx->tdr.pa, gpa + i, &out);
+ if (KVM_BUG_ON(err, &kvm_tdx->kvm)) {
+ pr_tdx_error(TDH_MR_EXTEND, err, &out);
+ break;
+ }
+ }
+}
+
static void tdx_unpin_pfn(struct kvm *kvm, kvm_pfn_t pfn)
{
struct page *page = pfn_to_page(pfn);
@@ -559,27 +574,58 @@ static void __tdx_sept_set_private_spte(struct kvm *kvm, gfn_t gfn,
hpa_t hpa = pfn_to_hpa(pfn);
gpa_t gpa = gfn_to_gpa(gfn);
struct tdx_module_output out;
+ hpa_t source_pa;
u64 err;

if (WARN_ON_ONCE(is_error_noslot_pfn(pfn) ||
!kvm_pfn_to_refcounted_page(pfn)))
return;

- /* TODO: handle large pages. */
- if (KVM_BUG_ON(level != PG_LEVEL_4K, kvm))
- return;
-
/* To prevent page migration, do nothing on mmu notifier. */
get_page(pfn_to_page(pfn));

+ /* Build-time faults are induced and handled via TDH_MEM_PAGE_ADD. */
if (likely(is_td_finalized(kvm_tdx))) {
+ /* TODO: handle large pages. */
+ if (KVM_BUG_ON(level != PG_LEVEL_4K, kvm))
+ return;
+
err = tdh_mem_page_aug(kvm_tdx->tdr.pa, gpa, hpa, &out);
if (KVM_BUG_ON(err, kvm)) {
pr_tdx_error(TDH_MEM_PAGE_AUG, err, &out);
- put_page(pfn_to_page(pfn));
+ tdx_unpin_pfn(kvm, pfn);
}
return;
}
+
+ /* KVM_INIT_MEM_REGION, tdx_init_mem_region(), supports only 4K page. */
+ if (KVM_BUG_ON(level != PG_LEVEL_4K, kvm))
+ return;
+
+ /*
+ * In case of TDP MMU, fault handler can run concurrently. Note
+ * 'source_pa' is a TD scope variable, meaning if there are multiple
+ * threads reaching here with all needing to access 'source_pa', it
+ * will break. However fortunately this won't happen, because below
+ * TDH_MEM_PAGE_ADD code path is only used when VM is being created
+ * before it is running, using KVM_TDX_INIT_MEM_REGION ioctl (which
+ * always uses vcpu 0's page table and protected by vcpu->mutex).
+ */
+ if (KVM_BUG_ON(kvm_tdx->source_pa == INVALID_PAGE, kvm)) {
+ tdx_unpin_pfn(kvm, pfn);
+ return;
+ }
+
+ source_pa = kvm_tdx->source_pa & ~KVM_TDX_MEASURE_MEMORY_REGION;
+
+ err = tdh_mem_page_add(kvm_tdx->tdr.pa, gpa, hpa, source_pa, &out);
+ if (KVM_BUG_ON(err, kvm)) {
+ pr_tdx_error(TDH_MEM_PAGE_ADD, err, &out);
+ tdx_unpin_pfn(kvm, pfn);
+ } else if ((kvm_tdx->source_pa & KVM_TDX_MEASURE_MEMORY_REGION))
+ tdx_measure_page(kvm_tdx, gpa);
+
+ kvm_tdx->source_pa = INVALID_PAGE;
}

static void tdx_sept_set_private_spte(struct kvm *kvm, gfn_t gfn,
@@ -1087,6 +1133,94 @@ void tdx_flush_tlb(struct kvm_vcpu *vcpu)
cpu_relax();
}

+#define TDX_SEPT_PFERR PFERR_WRITE_MASK
+
+static int tdx_init_mem_region(struct kvm *kvm, struct kvm_tdx_cmd *cmd)
+{
+ struct kvm_tdx *kvm_tdx = to_kvm_tdx(kvm);
+ struct kvm_tdx_init_mem_region region;
+ struct kvm_vcpu *vcpu;
+ struct page *page;
+ kvm_pfn_t pfn;
+ int idx, ret = 0;
+
+ /* The BSP vCPU must be created before initializing memory regions. */
+ if (!atomic_read(&kvm->online_vcpus))
+ return -EINVAL;
+
+ if (cmd->flags & ~KVM_TDX_MEASURE_MEMORY_REGION)
+ return -EINVAL;
+
+ if (copy_from_user(&region, (void __user *)cmd->data, sizeof(region)))
+ return -EFAULT;
+
+ /* Sanity check */
+ if (!IS_ALIGNED(region.source_addr, PAGE_SIZE) ||
+ !IS_ALIGNED(region.gpa, PAGE_SIZE) ||
+ !region.nr_pages ||
+ region.gpa + (region.nr_pages << PAGE_SHIFT) <= region.gpa ||
+ !kvm_is_private_gpa(kvm, region.gpa) ||
+ !kvm_is_private_gpa(kvm, region.gpa + (region.nr_pages << PAGE_SHIFT)))
+ return -EINVAL;
+
+ vcpu = kvm_get_vcpu(kvm, 0);
+ if (mutex_lock_killable(&vcpu->mutex))
+ return -EINTR;
+
+ vcpu_load(vcpu);
+ idx = srcu_read_lock(&kvm->srcu);
+
+ kvm_mmu_reload(vcpu);
+
+ while (region.nr_pages) {
+ if (signal_pending(current)) {
+ ret = -ERESTARTSYS;
+ break;
+ }
+
+ if (need_resched())
+ cond_resched();
+
+
+ /* Pin the source page. */
+ ret = get_user_pages_fast(region.source_addr, 1, 0, &page);
+ if (ret < 0)
+ break;
+ if (ret != 1) {
+ ret = -ENOMEM;
+ break;
+ }
+
+ kvm_tdx->source_pa = pfn_to_hpa(page_to_pfn(page)) |
+ (cmd->flags & KVM_TDX_MEASURE_MEMORY_REGION);
+
+ pfn = kvm_mmu_map_tdp_page(vcpu, region.gpa, TDX_SEPT_PFERR,
+ PG_LEVEL_4K);
+ if (is_error_noslot_pfn(pfn) || kvm->vm_bugged)
+ ret = -EFAULT;
+ else
+ ret = 0;
+
+ put_page(page);
+ if (ret)
+ break;
+
+ region.source_addr += PAGE_SIZE;
+ region.gpa += PAGE_SIZE;
+ region.nr_pages--;
+ }
+
+ srcu_read_unlock(&kvm->srcu, idx);
+ vcpu_put(vcpu);
+
+ mutex_unlock(&vcpu->mutex);
+
+ if (copy_to_user((void __user *)cmd->data, &region, sizeof(region)))
+ ret = -EFAULT;
+
+ return ret;
+}
+
int tdx_vm_ioctl(struct kvm *kvm, void __user *argp)
{
struct kvm_tdx_cmd tdx_cmd;
@@ -1103,6 +1237,9 @@ int tdx_vm_ioctl(struct kvm *kvm, void __user *argp)
case KVM_TDX_INIT_VM:
r = tdx_td_init(kvm, &tdx_cmd);
break;
+ case KVM_TDX_INIT_MEM_REGION:
+ r = tdx_init_mem_region(kvm, &tdx_cmd);
+ break;
default:
r = -EINVAL;
goto out;
diff --git a/arch/x86/kvm/vmx/tdx.h b/arch/x86/kvm/vmx/tdx.h
index d1b1cd60ff6f..eace70f4a0a1 100644
--- a/arch/x86/kvm/vmx/tdx.h
+++ b/arch/x86/kvm/vmx/tdx.h
@@ -25,6 +25,8 @@ struct kvm_tdx {
u64 xfam;
int hkid;

+ hpa_t source_pa;
+
bool finalized;
atomic_t tdh_mem_track;

diff --git a/tools/arch/x86/include/uapi/asm/kvm.h b/tools/arch/x86/include/uapi/asm/kvm.h
index 938fcf6bc002..f6d6da7515bf 100644
--- a/tools/arch/x86/include/uapi/asm/kvm.h
+++ b/tools/arch/x86/include/uapi/asm/kvm.h
@@ -534,6 +534,7 @@ enum kvm_tdx_cmd_id {
KVM_TDX_CAPABILITIES = 0,
KVM_TDX_INIT_VM,
KVM_TDX_INIT_VCPU,
+ KVM_TDX_INIT_MEM_REGION,

KVM_TDX_CMD_NR_MAX,
};
@@ -611,4 +612,12 @@ struct kvm_tdx_init_vm {
};
};

+#define KVM_TDX_MEASURE_MEMORY_REGION (1UL << 0)
+
+struct kvm_tdx_init_mem_region {
+ __u64 source_addr;
+ __u64 gpa;
+ __u64 nr_pages;
+};
+
#endif /* _ASM_X86_KVM_H */
--
2.25.1
\
 
 \ /
  Last update: 2022-08-08 00:10    [W:0.920 / U:0.360 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site