Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:18 as permitted sender) client-ip=2620:137:e000::1:18;
From:   "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
To:     tglx@linutronix.de, mingo@redhat.com, bp@alien8.de,
        dave.hansen@intel.com, luto@kernel.org, peterz@infradead.org
Cc:     sathyanarayanan.kuppuswamy@linux.intel.com, aarcange@redhat.com,
        ak@linux.intel.com, dan.j.williams@intel.com, david@redhat.com,
        hpa@zytor.com, jgross@suse.com, jmattson@google.com,
        joro@8bytes.org, jpoimboe@redhat.com, knsathya@kernel.org,
        pbonzini@redhat.com, sdeep@vmware.com, seanjc@google.com,
        tony.luck@intel.com, vkuznets@redhat.com, wanpengli@tencent.com,
        thomas.lendacky@amd.com, brijesh.singh@amd.com, x86@kernel.org,
        linux-kernel@vger.kernel.org,
        "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Subject: [PATCHv4 11/30] x86/tdx: Handle in-kernel MMIO
Date:   Thu, 24 Feb 2022 18:56:11 +0300
Message-Id: <20220224155630.52734-12-kirill.shutemov@linux.intel.com>
In-Reply-To: <20220224155630.52734-1-kirill.shutemov@linux.intel.com>
References: <20220224155630.52734-1-kirill.shutemov@linux.intel.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

In non-TDX VMs, MMIO is implemented by providing the guest a mapping
which will cause a VMEXIT on access and then the VMM emulating the
instruction that caused the VMEXIT. That's not possible for TDX VM.

To emulate an instruction an emulator needs two things:

  - R/W access to the register file to read/modify instruction arguments
    and see RIP of the faulted instruction.

  - Read access to memory where instruction is placed to see what to
    emulate. In this case it is guest kernel text.

Both of them are not available to VMM in TDX environment:

  - Register file is never exposed to VMM. When a TD exits to the module,
    it saves registers into the state-save area allocated for that TD.
    The module then scrubs these registers before returning execution
    control to the VMM, to help prevent leakage of TD state.

  - Memory is encrypted a TD-private key. The CPU disallows software
    other than the TDX module and TDs from making memory accesses using
    the private key.

In TDX the MMIO regions are instead configured to trigger a #VE
exception in the guest. The guest #VE handler then emulates the MMIO
instruction inside the guest and converts it into a controlled hypercall
to the host.

MMIO addresses can be used with any CPU instruction that accesses
memory. Address only MMIO accesses done via io.h helpers, such as
'readl()' or 'writeq()'.

readX()/writeX() helpers limit the range of instructions which can trigger
MMIO. It makes MMIO instruction emulation feasible. Raw access to a MMIO
region allows the compiler to generate whatever instruction it wants.
Supporting all possible instructions is a task of a different scope.

MMIO access with anything other than helpers from io.h may result in
MMIO_DECODE_FAILED and an oops.

AMD SEV has the same limitations to MMIO handling.

=== Potential alternative approaches ===

== Paravirtualizing all MMIO ==

An alternative to letting MMIO induce a #VE exception is to avoid
the #VE in the first place. Similar to the port I/O case, it is
theoretically possible to paravirtualize MMIO accesses.

Like the exception-based approach offered here, a fully paravirtualized
approach would be limited to MMIO users that leverage common
infrastructure like the io.h macros.

However, any paravirtual approach would be patching approximately
120k call sites. With a conservative overhead estimation of 5 bytes per
call site (CALL instruction), it leads to bloating code by 600k.

Many drivers will never be used in the TDX environment and the bloat
cannot be justified.

== Patching TDX drivers ==

Rather than touching the entire kernel, it might also be possible to
just go after drivers that use MMIO in TDX guests.  Right now, that's
limited only to virtio and some x86-specific drivers.

All virtio MMIO appears to be done through a single function, which
makes virtio eminently easy to patch. This will be implemented in the
future, removing the bulk of MMIO #VEs.

Co-developed-by: Kuppuswamy Sathyanarayanan <sathyanarayanan.kuppuswamy@linux.intel.com>
Signed-off-by: Kuppuswamy Sathyanarayanan <sathyanarayanan.kuppuswamy@linux.intel.com>
Reviewed-by: Andi Kleen <ak@linux.intel.com>
Reviewed-by: Tony Luck <tony.luck@intel.com>
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
---
 arch/x86/coco/tdx.c | 110 ++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 110 insertions(+)

diff --git a/arch/x86/coco/tdx.c b/arch/x86/coco/tdx.c
index fd78b81a951d..15519e498679 100644
--- a/arch/x86/coco/tdx.c
+++ b/arch/x86/coco/tdx.c
@@ -8,11 +8,17 @@
 #include <asm/coco.h>
 #include <asm/tdx.h>
 #include <asm/vmx.h>
+#include <asm/insn.h>
+#include <asm/insn-eval.h>
 
 /* TDX module Call Leaf IDs */
 #define TDX_GET_INFO			1
 #define TDX_GET_VEINFO			3
 
+/* MMIO direction */
+#define EPT_READ	0
+#define EPT_WRITE	1
+
 static struct {
 	unsigned int gpa_width;
 	unsigned long attributes;
@@ -184,6 +190,108 @@ static bool handle_cpuid(struct pt_regs *regs)
 	return true;
 }
 
+static bool mmio_read(int size, unsigned long addr, unsigned long *val)
+{
+	struct tdx_hypercall_args args = {
+		.r10 = TDX_HYPERCALL_STANDARD,
+		.r11 = EXIT_REASON_EPT_VIOLATION,
+		.r12 = size,
+		.r13 = EPT_READ,
+		.r14 = addr,
+		.r15 = *val,
+	};
+
+	if (__tdx_hypercall(&args, TDX_HCALL_HAS_OUTPUT))
+		return false;
+	*val = args.r11;
+	return true;
+}
+
+static bool mmio_write(int size, unsigned long addr, unsigned long val)
+{
+	return !_tdx_hypercall(EXIT_REASON_EPT_VIOLATION, size, EPT_WRITE,
+			       addr, val);
+}
+
+static bool handle_mmio(struct pt_regs *regs, struct ve_info *ve)
+{
+	char buffer[MAX_INSN_SIZE];
+	unsigned long *reg, val;
+	struct insn insn = {};
+	enum mmio_type mmio;
+	int size, extend_size;
+	u8 extend_val = 0;
+
+	if (copy_from_kernel_nofault(buffer, (void *)regs->ip, MAX_INSN_SIZE))
+		return false;
+
+	if (insn_decode(&insn, buffer, MAX_INSN_SIZE, INSN_MODE_64))
+		return false;
+
+	mmio = insn_decode_mmio(&insn, &size);
+	if (WARN_ON_ONCE(mmio == MMIO_DECODE_FAILED))
+		return false;
+
+	if (mmio != MMIO_WRITE_IMM && mmio != MMIO_MOVS) {
+		reg = insn_get_modrm_reg_ptr(&insn, regs);
+		if (!reg)
+			return false;
+	}
+
+	ve->instr_len = insn.length;
+
+	switch (mmio) {
+	case MMIO_WRITE:
+		memcpy(&val, reg, size);
+		return mmio_write(size, ve->gpa, val);
+	case MMIO_WRITE_IMM:
+		val = insn.immediate.value;
+		return mmio_write(size, ve->gpa, val);
+	case MMIO_READ:
+	case MMIO_READ_ZERO_EXTEND:
+	case MMIO_READ_SIGN_EXTEND:
+		break;
+	case MMIO_MOVS:
+	case MMIO_DECODE_FAILED:
+		return false;
+	default:
+		BUG();
+	}
+
+	/* Handle reads */
+	if (!mmio_read(size, ve->gpa, &val))
+		return false;
+
+	switch (mmio) {
+	case MMIO_READ:
+		/* Zero-extend for 32-bit operation */
+		extend_size = size == 4 ? sizeof(*reg) : 0;
+		break;
+	case MMIO_READ_ZERO_EXTEND:
+		/* Zero extend based on operand size */
+		extend_size = insn.opnd_bytes;
+		break;
+	case MMIO_READ_SIGN_EXTEND:
+		/* Sign extend based on operand size */
+		extend_size = insn.opnd_bytes;
+		if (size == 1 && val & BIT(7))
+			extend_val = 0xFF;
+		else if (size > 1 && val & BIT(15))
+			extend_val = 0xFF;
+		break;
+	case MMIO_MOVS:
+	case MMIO_DECODE_FAILED:
+		return false;
+	default:
+		BUG();
+	}
+
+	if (extend_size)
+		memset(reg, extend_val, extend_size);
+	memcpy(reg, &val, size);
+	return true;
+}
+
 void tdx_get_ve_info(struct ve_info *ve)
 {
 	struct tdx_module_output out;
@@ -237,6 +345,8 @@ static bool virt_exception_kernel(struct pt_regs *regs, struct ve_info *ve)
 		return write_msr(regs);
 	case EXIT_REASON_CPUID:
 		return handle_cpuid(regs);
+	case EXIT_REASON_EPT_VIOLATION:
+		return handle_mmio(regs, ve);
 	default:
 		pr_warn("Unexpected #VE: %lld\n", ve->exit_reason);
 		return false;
-- 
2.34.1