[PATCH v5 4/6] x86/hyperv: Support hypercalls for TDX guests

[Dexuan Cui <decui@microsoft.com>]

A TDX guest uses the GHCI call rather than hv_hypercall_pg.

In hv_do_hypercall(), Hyper-V requires that the input/output addresses
must have the cc_mask.

Reviewed-by: Kuppuswamy Sathyanarayanan <sathyanarayanan.kuppuswamy@linux.intel.com>
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
Signed-off-by: Dexuan Cui <decui@microsoft.com>
---
 arch/x86/hyperv/hv_init.c       |  8 ++++++++
 arch/x86/hyperv/ivm.c           | 14 ++++++++++++++
 arch/x86/include/asm/mshyperv.h | 17 +++++++++++++++++
 drivers/hv/hv_common.c          | 24 ++++++++++++++++++++++++
 4 files changed, 63 insertions(+)

Changes in v2:
  Implemented hv_tdx_hypercall() in C rather than in assembly code.
  Renamed the parameter names of hv_tdx_hypercall().
  Used cc_mkdec() directly in hv_do_hypercall().

Changes in v3:
  Decrypted/encrypted hyperv_pcpu_input_arg in
    hv_common_cpu_init() and hv_common_cpu_die().

Changes in v4:
  __tdx_hypercall(&args, TDX_HCALL_HAS_OUTPUT) -> __tdx_hypercall_ret()
  hv_common_cpu_die(): explicitly ignore the error set_memory_encrypted() [Michael Kelley]
  Added Sathyanarayanan's Reviewed-by.

Changes in v5:
  Added Michael's Reviewed-by.

diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c
index a5f9474f08e1..f175e0de821c 100644
--- a/arch/x86/hyperv/hv_init.c
+++ b/arch/x86/hyperv/hv_init.c
@@ -432,6 +432,10 @@ void __init hyperv_init(void)
 	/* Hyper-V requires to write guest os id via ghcb in SNP IVM. */
 	hv_ghcb_msr_write(HV_X64_MSR_GUEST_OS_ID, guest_id);
 
+	/* A TDX guest uses the GHCI call rather than hv_hypercall_pg. */
+	if (hv_isolation_type_tdx())
+		goto skip_hypercall_pg_init;
+
 	hv_hypercall_pg = __vmalloc_node_range(PAGE_SIZE, 1, VMALLOC_START,
 			VMALLOC_END, GFP_KERNEL, PAGE_KERNEL_ROX,
 			VM_FLUSH_RESET_PERMS, NUMA_NO_NODE,
@@ -471,6 +475,7 @@ void __init hyperv_init(void)
 		wrmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
 	}
 
+skip_hypercall_pg_init:
 	/*
 	 * hyperv_init() is called before LAPIC is initialized: see
 	 * apic_intr_mode_init() -> x86_platform.apic_post_init() and
@@ -594,6 +599,9 @@ bool hv_is_hyperv_initialized(void)
 	if (x86_hyper_type != X86_HYPER_MS_HYPERV)
 		return false;
 
+	/* A TDX guest uses the GHCI call rather than hv_hypercall_pg. */
+	if (hv_isolation_type_tdx())
+		return true;
 	/*
 	 * Verify that earlier initialization succeeded by checking
 	 * that the hypercall page is setup
diff --git a/arch/x86/hyperv/ivm.c b/arch/x86/hyperv/ivm.c
index 3658ade4f412..23304c9ddd34 100644
--- a/arch/x86/hyperv/ivm.c
+++ b/arch/x86/hyperv/ivm.c
@@ -415,3 +415,17 @@ bool hv_isolation_type_tdx(void)
 {
 	return static_branch_unlikely(&isolation_type_tdx);
 }
+
+u64 hv_tdx_hypercall(u64 control, u64 param1, u64 param2)
+{
+	struct tdx_hypercall_args args = { };
+
+	args.r10 = control;
+	args.rdx = param1;
+	args.r8  = param2;
+
+	(void)__tdx_hypercall_ret(&args);
+
+	return args.r11;
+}
+EXPORT_SYMBOL_GPL(hv_tdx_hypercall);
diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h
index de7ceae9e65e..71077326f57b 100644
--- a/arch/x86/include/asm/mshyperv.h
+++ b/arch/x86/include/asm/mshyperv.h
@@ -10,6 +10,7 @@
 #include <asm/nospec-branch.h>
 #include <asm/paravirt.h>
 #include <asm/mshyperv.h>
+#include <asm/coco.h>
 
 /*
  * Hyper-V always provides a single IO-APIC at this MMIO address.
@@ -45,6 +46,12 @@ int hv_call_deposit_pages(int node, u64 partition_id, u32 num_pages);
 int hv_call_add_logical_proc(int node, u32 lp_index, u32 acpi_id);
 int hv_call_create_vp(int node, u64 partition_id, u32 vp_index, u32 flags);
 
+u64 hv_tdx_hypercall(u64 control, u64 param1, u64 param2);
+
+/*
+ * If the hypercall involves no input or output parameters, the hypervisor
+ * ignores the corresponding GPA pointer.
+ */
 static inline u64 hv_do_hypercall(u64 control, void *input, void *output)
 {
 	u64 input_address = input ? virt_to_phys(input) : 0;
@@ -52,6 +59,10 @@ static inline u64 hv_do_hypercall(u64 control, void *input, void *output)
 	u64 hv_status;
 
 #ifdef CONFIG_X86_64
+	if (hv_isolation_type_tdx())
+		return hv_tdx_hypercall(control,
+					cc_mkdec(input_address),
+					cc_mkdec(output_address));
 	if (!hv_hypercall_pg)
 		return U64_MAX;
 
@@ -95,6 +106,9 @@ static inline u64 _hv_do_fast_hypercall8(u64 control, u64 input1)
 	u64 hv_status;
 
 #ifdef CONFIG_X86_64
+	if (hv_isolation_type_tdx())
+		return hv_tdx_hypercall(control, input1, 0);
+
 	{
 		__asm__ __volatile__(CALL_NOSPEC
 				     : "=a" (hv_status), ASM_CALL_CONSTRAINT,
@@ -140,6 +154,9 @@ static inline u64 _hv_do_fast_hypercall16(u64 control, u64 input1, u64 input2)
 	u64 hv_status;
 
 #ifdef CONFIG_X86_64
+	if (hv_isolation_type_tdx())
+		return hv_tdx_hypercall(control, input1, input2);
+
 	{
 		__asm__ __volatile__("mov %4, %%r8\n"
 				     CALL_NOSPEC
diff --git a/drivers/hv/hv_common.c b/drivers/hv/hv_common.c
index c55db7ea6580..10e85682e83e 100644
--- a/drivers/hv/hv_common.c
+++ b/drivers/hv/hv_common.c
@@ -21,6 +21,7 @@
 #include <linux/ptrace.h>
 #include <linux/slab.h>
 #include <linux/dma-map-ops.h>
+#include <linux/set_memory.h>
 #include <asm/hyperv-tlfs.h>
 #include <asm/mshyperv.h>
 
@@ -128,6 +129,7 @@ int hv_common_cpu_init(unsigned int cpu)
 	u64 msr_vp_index;
 	gfp_t flags;
 	int pgcount = hv_root_partition ? 2 : 1;
+	int ret;
 
 	/* hv_cpu_init() can be called with IRQs disabled from hv_resume() */
 	flags = irqs_disabled() ? GFP_ATOMIC : GFP_KERNEL;
@@ -137,6 +139,17 @@ int hv_common_cpu_init(unsigned int cpu)
 	if (!(*inputarg))
 		return -ENOMEM;
 
+	if (hv_isolation_type_tdx()) {
+		ret = set_memory_decrypted((unsigned long)*inputarg, pgcount);
+		if (ret) {
+			/* It may be unsafe to free *inputarg */
+			*inputarg = NULL;
+			return ret;
+		}
+
+		memset(*inputarg, 0x00, pgcount * HV_HYP_PAGE_SIZE);
+	}
+
 	if (hv_root_partition) {
 		outputarg = (void **)this_cpu_ptr(hyperv_pcpu_output_arg);
 		*outputarg = (char *)(*inputarg) + HV_HYP_PAGE_SIZE;
@@ -157,6 +170,8 @@ int hv_common_cpu_die(unsigned int cpu)
 	unsigned long flags;
 	void **inputarg, **outputarg;
 	void *mem;
+	int pgcount = hv_root_partition ? 2 : 1;
+	int ret;
 
 	local_irq_save(flags);
 
@@ -171,6 +186,15 @@ int hv_common_cpu_die(unsigned int cpu)
 
 	local_irq_restore(flags);
 
+	if (hv_isolation_type_tdx()) {
+		ret = set_memory_encrypted((unsigned long)mem, pgcount);
+		if (ret)
+			pr_warn("Hyper-V: Failed to encrypt input arg on cpu%d: %d\n",
+				cpu, ret);
+		/* It's unsafe to free 'mem'. */
+		return 0;
+	}
+
 	kfree(mem);
 
 	return 0;
-- 
2.25.1