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 17/30] x86/tdx: Add port I/O emulation
Date:   Thu, 24 Feb 2022 18:56:17 +0300
Message-Id: <20220224155630.52734-18-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

From: Kuppuswamy Sathyanarayanan <sathyanarayanan.kuppuswamy@linux.intel.com>

TDX hypervisors cannot emulate instructions directly. This includes
port I/O which is normally emulated in the hypervisor. All port I/O
instructions inside TDX trigger the #VE exception in the guest and
would be normally emulated there.

Use a hypercall to emulate port I/O. Extend the
tdx_handle_virt_exception() and add support to handle the #VE due to
port I/O instructions.

String I/O operations are not supported in TDX. Unroll them by declaring
CC_ATTR_GUEST_UNROLL_STRING_IO confidential computing attribute.

Signed-off-by: Kuppuswamy Sathyanarayanan <sathyanarayanan.kuppuswamy@linux.intel.com>
Reviewed-by: Andi Kleen <ak@linux.intel.com>
Reviewed-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
---
 arch/x86/coco/core.c |  7 +++++-
 arch/x86/coco/tdx.c  | 54 ++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 60 insertions(+), 1 deletion(-)

diff --git a/arch/x86/coco/core.c b/arch/x86/coco/core.c
index 9113baebbfd2..5615b75e6fc6 100644
--- a/arch/x86/coco/core.c
+++ b/arch/x86/coco/core.c
@@ -18,7 +18,12 @@ static u64 cc_mask __ro_after_init;
 
 static bool intel_cc_platform_has(enum cc_attr attr)
 {
-	return false;
+	switch (attr) {
+	case CC_ATTR_GUEST_UNROLL_STRING_IO:
+		return true;
+	default:
+		return false;
+	}
 }
 
 /*
diff --git a/arch/x86/coco/tdx.c b/arch/x86/coco/tdx.c
index 15519e498679..2e342760b1d2 100644
--- a/arch/x86/coco/tdx.c
+++ b/arch/x86/coco/tdx.c
@@ -19,6 +19,12 @@
 #define EPT_READ	0
 #define EPT_WRITE	1
 
+/* See Exit Qualification for I/O Instructions in VMX documentation */
+#define VE_IS_IO_IN(e)		((e) & BIT(3))
+#define VE_GET_IO_SIZE(e)	(((e) & GENMASK(2, 0)) + 1)
+#define VE_GET_PORT_NUM(e)	((e) >> 16)
+#define VE_IS_IO_STRING(e)	((e) & BIT(4))
+
 static struct {
 	unsigned int gpa_width;
 	unsigned long attributes;
@@ -292,6 +298,52 @@ static bool handle_mmio(struct pt_regs *regs, struct ve_info *ve)
 	return true;
 }
 
+/*
+ * Emulate I/O using hypercall.
+ *
+ * Assumes the IO instruction was using ax, which is enforced
+ * by the standard io.h macros.
+ *
+ * Return True on success or False on failure.
+ */
+static bool handle_io(struct pt_regs *regs, u32 exit_qual)
+{
+	struct tdx_hypercall_args args = {
+		.r10 = TDX_HYPERCALL_STANDARD,
+		.r11 = EXIT_REASON_IO_INSTRUCTION,
+	};
+	int size, port;
+	u64 mask;
+	bool in, ret;
+
+	if (VE_IS_IO_STRING(exit_qual))
+		return false;
+
+	in   = VE_IS_IO_IN(exit_qual);
+	size = VE_GET_IO_SIZE(exit_qual);
+	port = VE_GET_PORT_NUM(exit_qual);
+	mask = GENMASK(BITS_PER_BYTE * size, 0);
+
+	args.r12 = size;
+	args.r13 = !in;
+	args.r14 = port;
+	args.r15 = in ? 0 : regs->ax;
+
+	/*
+	 * Emulate the I/O read/write via hypercall. More info about
+	 * ABI can be found in TDX Guest-Host-Communication Interface
+	 * (GHCI) section titled "TDG.VP.VMCALL<Instruction.IO>".
+	 */
+	ret = !__tdx_hypercall(&args, in ? TDX_HCALL_HAS_OUTPUT : 0);
+	if (!ret || !in)
+		return ret;
+
+	regs->ax &= ~mask;
+	regs->ax |= ret ? args.r11 & mask : UINT_MAX;
+
+	return ret;
+}
+
 void tdx_get_ve_info(struct ve_info *ve)
 {
 	struct tdx_module_output out;
@@ -347,6 +399,8 @@ static bool virt_exception_kernel(struct pt_regs *regs, struct ve_info *ve)
 		return handle_cpuid(regs);
 	case EXIT_REASON_EPT_VIOLATION:
 		return handle_mmio(regs, ve);
+	case EXIT_REASON_IO_INSTRUCTION:
+		return handle_io(regs, ve->exit_qual);
 	default:
 		pr_warn("Unexpected #VE: %lld\n", ve->exit_reason);
 		return false;
-- 
2.34.1