[RFC v2-fix 1/1] x86/traps: Add #VE support for TDX guest

[Kuppuswamy Sathyanarayanan]

From: "Kirill A. Shutemov" <kirill.shutemov@xxxxxxxxxxxxxxx>

Virtualization Exceptions (#VE) are delivered to TDX guests due to
specific guest actions which may happen in either user space or the kernel:

 * Specific instructions (WBINVD, for example)
 * Specific MSR accesses
 * Specific CPUID leaf accesses
 * Access to TD-shared memory, which includes MMIO

In the settings that Linux will run in, virtual exceptions are never
generated on accesses to normal, TD-private memory that has been
accepted.

The entry paths do not access TD-shared memory, MMIO regions or use
those specific MSRs, instructions, CPUID leaves that might generate #VE.
In addition, all interrupts including NMIs are blocked by the hardware
starting with #VE delivery until TDGETVEINFO is called.  This eliminates
the chance of a #VE during the syscall gap or paranoid entry paths and
simplifies #VE handling.

After TDGETVEINFO #VE could happen in theory (e.g. through an NMI),
although we don't expect it to happen because we don't expect NMIs to
trigger #VEs. Another case where they could happen is if the #VE
exception panics, but in this case there are no guarantees on anything
anyways.

If a guest kernel action which would normally cause a #VE occurs in the
interrupt-disabled region before TDGETVEINFO, a #DF is delivered to the
guest which will result in an oops (and should eventually be a panic, as
we would like to set panic_on_oops to 1 for TDX guests).

Add basic infrastructure to handle any #VE which occurs in the kernel or
userspace.  Later patches will add handling for specific #VE scenarios.

Convert unhandled #VE's (everything, until later in this series) so that
they appear just like a #GP by calling ve_raise_fault() directly.
ve_raise_fault() is similar to #GP handler and is responsible for
sending SIGSEGV to userspace and cpu die and notifying debuggers and
other die chain users.  

Co-developed-by: Sean Christopherson <sean.j.christopherson@xxxxxxxxx>
Signed-off-by: Sean Christopherson <sean.j.christopherson@xxxxxxxxx>
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@xxxxxxxxxxxxxxx>
Reviewed-by: Andi Kleen <ak@xxxxxxxxxxxxxxx>
Signed-off-by: Kuppuswamy Sathyanarayanan <sathyanarayanan.kuppuswamy@xxxxxxxxxxxxxxx>
---

Changes since v1:
 * Removed [RFC v2 07/32] x86/traps: Add do_general_protection() helper function.
 * Instead of resuing #GP handler, defined a custom handler.
 * Fixed commit log as per review comments.

 arch/x86/include/asm/idtentry.h |  4 ++
 arch/x86/include/asm/tdx.h      | 20 ++++++++++
 arch/x86/kernel/idt.c           |  6 +++
 arch/x86/kernel/tdx.c           | 35 +++++++++++++++++
 arch/x86/kernel/traps.c         | 70 +++++++++++++++++++++++++++++++++
 5 files changed, 135 insertions(+)

diff --git a/arch/x86/include/asm/idtentry.h b/arch/x86/include/asm/idtentry.h
index 5eb3bdf36a41..41a0732d5f68 100644
--- a/arch/x86/include/asm/idtentry.h
+++ b/arch/x86/include/asm/idtentry.h
@@ -619,6 +619,10 @@ DECLARE_IDTENTRY_XENCB(X86_TRAP_OTHER,	exc_xen_hypervisor_callback);
 DECLARE_IDTENTRY_RAW(X86_TRAP_OTHER,	exc_xen_unknown_trap);
 #endif
 
+#ifdef CONFIG_INTEL_TDX_GUEST
+DECLARE_IDTENTRY(X86_TRAP_VE,		exc_virtualization_exception);
+#endif
+
 /* Device interrupts common/spurious */
 DECLARE_IDTENTRY_IRQ(X86_TRAP_OTHER,	common_interrupt);
 #ifdef CONFIG_X86_LOCAL_APIC
diff --git a/arch/x86/include/asm/tdx.h b/arch/x86/include/asm/tdx.h
index 1d75be21a09b..8ab4067afefc 100644
--- a/arch/x86/include/asm/tdx.h
+++ b/arch/x86/include/asm/tdx.h
@@ -11,6 +11,7 @@
 #include <linux/types.h>
 
 #define TDINFO			1
+#define TDGETVEINFO		3
 
 struct tdx_module_output {
 	u64 rcx;
@@ -29,6 +30,25 @@ struct tdx_hypercall_output {
 	u64 r15;
 };
 
+/*
+ * Used by #VE exception handler to gather the #VE exception
+ * info from the TDX module. This is software only structure
+ * and not related to TDX module/VMM.
+ */
+struct ve_info {
+	u64 exit_reason;
+	u64 exit_qual;
+	u64 gla;
+	u64 gpa;
+	u32 instr_len;
+	u32 instr_info;
+};
+
+unsigned long tdg_get_ve_info(struct ve_info *ve);
+
+int tdg_handle_virtualization_exception(struct pt_regs *regs,
+		struct ve_info *ve);
+
 /* Common API to check TDX support in decompression and common kernel code. */
 bool is_tdx_guest(void);
 
diff --git a/arch/x86/kernel/idt.c b/arch/x86/kernel/idt.c
index ee1a283f8e96..546b6b636c7d 100644
--- a/arch/x86/kernel/idt.c
+++ b/arch/x86/kernel/idt.c
@@ -64,6 +64,9 @@ static const __initconst struct idt_data early_idts[] = {
 	 */
 	INTG(X86_TRAP_PF,		asm_exc_page_fault),
 #endif
+#ifdef CONFIG_INTEL_TDX_GUEST
+	INTG(X86_TRAP_VE,		asm_exc_virtualization_exception),
+#endif
 };
 
 /*
@@ -87,6 +90,9 @@ static const __initconst struct idt_data def_idts[] = {
 	INTG(X86_TRAP_MF,		asm_exc_coprocessor_error),
 	INTG(X86_TRAP_AC,		asm_exc_alignment_check),
 	INTG(X86_TRAP_XF,		asm_exc_simd_coprocessor_error),
+#ifdef CONFIG_INTEL_TDX_GUEST
+	INTG(X86_TRAP_VE,		asm_exc_virtualization_exception),
+#endif
 
 #ifdef CONFIG_X86_32
 	TSKG(X86_TRAP_DF,		GDT_ENTRY_DOUBLEFAULT_TSS),
diff --git a/arch/x86/kernel/tdx.c b/arch/x86/kernel/tdx.c
index 4dfacde05f0c..b5fffbd86331 100644
--- a/arch/x86/kernel/tdx.c
+++ b/arch/x86/kernel/tdx.c
@@ -85,6 +85,41 @@ static void tdg_get_info(void)
 	td_info.attributes = out.rdx;
 }
 
+unsigned long tdg_get_ve_info(struct ve_info *ve)
+{
+	u64 ret;
+	struct tdx_module_output out = {0};
+
+	/*
+	 * NMIs and machine checks are suppressed. Before this point any
+	 * #VE is fatal. After this point (TDGETVEINFO call), NMIs and
+	 * additional #VEs are permitted (but we don't expect them to
+	 * happen unless you panic).
+	 */
+	ret = __tdx_module_call(TDGETVEINFO, 0, 0, 0, 0, &out);
+
+	ve->exit_reason = out.rcx;
+	ve->exit_qual   = out.rdx;
+	ve->gla         = out.r8;
+	ve->gpa         = out.r9;
+	ve->instr_len   = out.r10 & UINT_MAX;
+	ve->instr_info  = out.r10 >> 32;
+
+	return ret;
+}
+
+int tdg_handle_virtualization_exception(struct pt_regs *regs,
+		struct ve_info *ve)
+{
+	/*
+	 * TODO: Add handler support for various #VE exit
+	 * reasons. It will be added by other patches in
+	 * the series.
+	 */
+	pr_warn("Unexpected #VE: %lld\n", ve->exit_reason);
+	return -EFAULT;
+}
+
 void __init tdx_early_init(void)
 {
 	if (!cpuid_has_tdx_guest())
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 651e3e508959..af8efa2e57ba 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -61,6 +61,7 @@
 #include <asm/insn.h>
 #include <asm/insn-eval.h>
 #include <asm/vdso.h>
+#include <asm/tdx.h>
 
 #ifdef CONFIG_X86_64
 #include <asm/x86_init.h>
@@ -1137,6 +1138,75 @@ DEFINE_IDTENTRY(exc_device_not_available)
 	}
 }
 
+#define VEFSTR "VE fault"
+static void ve_raise_fault(struct pt_regs *regs, long error_code)
+{
+	struct task_struct *tsk = current;
+
+	if (user_mode(regs)) {
+		tsk->thread.error_code = error_code;
+		tsk->thread.trap_nr = X86_TRAP_VE;
+
+		/*
+		 * Not fixing up VDSO exceptions similar to #GP handler
+		 * because we don't expect the VDSO to trigger #VE.
+		 */
+		show_signal(tsk, SIGSEGV, "", VEFSTR, regs, error_code);
+		force_sig(SIGSEGV);
+		return;
+	}
+
+
+	if (fixup_exception(regs, X86_TRAP_VE, error_code, 0))
+		return;
+
+	tsk->thread.error_code = error_code;
+	tsk->thread.trap_nr = X86_TRAP_VE;
+
+	/*
+	 * To be potentially processing a kprobe fault and to trust the result
+	 * from kprobe_running(), we have to be non-preemptible.
+	 */
+	if (!preemptible() &&
+	    kprobe_running() &&
+	    kprobe_fault_handler(regs, X86_TRAP_VE))
+		return;
+
+	notify_die(DIE_GPF, VEFSTR, regs, error_code, X86_TRAP_VE, SIGSEGV);
+
+	die_addr(VEFSTR, regs, error_code, 0);
+}
+
+#ifdef CONFIG_INTEL_TDX_GUEST
+DEFINE_IDTENTRY(exc_virtualization_exception)
+{
+	struct ve_info ve;
+	int ret;
+
+	RCU_LOCKDEP_WARN(!rcu_is_watching(), "entry code didn't wake RCU");
+
+	/*
+	 * NMIs/Machine-checks/Interrupts will be in a disabled state
+	 * till TDGETVEINFO TDCALL is executed. This prevents #VE
+	 * nesting issue.
+	 */
+	ret = tdg_get_ve_info(&ve);
+
+	cond_local_irq_enable(regs);
+
+	if (!ret)
+		ret = tdg_handle_virtualization_exception(regs, &ve);
+	/*
+	 * If tdg_handle_virtualization_exception() could not process
+	 * it successfully, treat it as #GP(0) and handle it.
+	 */
+	if (ret)
+		ve_raise_fault(regs, 0);
+
+	cond_local_irq_disable(regs);
+}
+#endif
+
 #ifdef CONFIG_X86_32
 DEFINE_IDTENTRY_SW(iret_error)
 {
-- 
2.25.1