x86/entry: Add fred_entry_from_kvm() for VMX to handle IRQ/NMI

In IRQ/NMI induced VM exits, KVM VMX needs to execute the respective
handlers, which requires the software to create a FRED stack frame,
and use it to invoke the handlers. Add fred_irq_entry_from_kvm() for
this job.

Export fred_entry_from_kvm() because VMX can be compiled as a module.

Suggested-by: Sean Christopherson <seanjc@google.com>
Suggested-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Xin Li <xin3.li@intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Tested-by: Shan Kang <shan.kang@intel.com>
Link: https://lore.kernel.org/r/20231205105030.8698-32-xin3.li@intel.com

Author: xinli-intel

arch/x86/entry/entry_64_fred.S

@@ -3,8 +3,11 @@
  * The actual FRED entry points.
  */
 
+#include <linux/export.h>
+
 #include <asm/asm.h>
 #include <asm/fred.h>
+#include <asm/segment.h>
 
 #include "calling.h"
 
@@ -52,3 +55,77 @@ SYM_CODE_START_NOALIGN(asm_fred_entrypoint_kernel)
 	FRED_EXIT
 	ERETS
 SYM_CODE_END(asm_fred_entrypoint_kernel)
+
+#if IS_ENABLED(CONFIG_KVM_INTEL)
+SYM_FUNC_START(asm_fred_entry_from_kvm)
+	push %rbp
+	mov %rsp, %rbp
+
+	UNWIND_HINT_SAVE
+
+	/*
+	 * Both IRQ and NMI from VMX can be handled on current task stack
+	 * because there is no need to protect from reentrancy and the call
+	 * stack leading to this helper is effectively constant and shallow
+	 * (relatively speaking). Do the same when FRED is active, i.e., no
+	 * need to check current stack level for a stack switch.
+	 *
+	 * Emulate the FRED-defined redzone and stack alignment.
+	 */
+	sub $(FRED_CONFIG_REDZONE_AMOUNT << 6), %rsp
+	and $FRED_STACK_FRAME_RSP_MASK, %rsp
+
+	/*
+	 * Start to push a FRED stack frame, which is always 64 bytes:
+	 *
+	 * +--------+-----------------+
+	 * | Bytes  | Usage           |
+	 * +--------+-----------------+
+	 * | 63:56  | Reserved        |
+	 * | 55:48  | Event Data      |
+	 * | 47:40  | SS + Event Info |
+	 * | 39:32  | RSP             |
+	 * | 31:24  | RFLAGS          |
+	 * | 23:16  | CS + Aux Info   |
+	 * |  15:8  | RIP             |
+	 * |   7:0  | Error Code      |
+	 * +--------+-----------------+
+	 */
+	push $0				/* Reserved, must be 0 */
+	push $0				/* Event data, 0 for IRQ/NMI */
+	push %rdi			/* fred_ss handed in by the caller */
+	push %rbp
+	pushf
+	mov $__KERNEL_CS, %rax
+	push %rax
+
+	/*
+	 * Unlike the IDT event delivery, FRED _always_ pushes an error code
+	 * after pushing the return RIP, thus the CALL instruction CANNOT be
+	 * used here to push the return RIP, otherwise there is no chance to
+	 * push an error code before invoking the IRQ/NMI handler.
+	 *
+	 * Use LEA to get the return RIP and push it, then push an error code.
+	 */
+	lea 1f(%rip), %rax
+	push %rax				/* Return RIP */
+	push $0					/* Error code, 0 for IRQ/NMI */
+
+	PUSH_AND_CLEAR_REGS clear_bp=0 unwind_hint=0
+	movq %rsp, %rdi				/* %rdi -> pt_regs */
+	call __fred_entry_from_kvm		/* Call the C entry point */
+	POP_REGS
+	ERETS
+1:
+	/*
+	 * Objtool doesn't understand what ERETS does, this hint tells it that
+	 * yes, we'll reach here and with what stack state. A save/restore pair
+	 * isn't strictly needed, but it's the simplest form.
+	 */
+	UNWIND_HINT_RESTORE
+	pop %rbp
+	RET
+
+SYM_FUNC_END(asm_fred_entry_from_kvm)
+EXPORT_SYMBOL_GPL(asm_fred_entry_from_kvm);
+#endif

arch/x86/entry/entry_fred.c

@@ -257,3 +257,17 @@ __visible noinstr void fred_entry_from_kernel(struct pt_regs *regs)
 
 	return fred_bad_type(regs, error_code);
 }
+
+#if IS_ENABLED(CONFIG_KVM_INTEL)
+__visible noinstr void __fred_entry_from_kvm(struct pt_regs *regs)
+{
+	switch (regs->fred_ss.type) {
+	case EVENT_TYPE_EXTINT:
+		return fred_extint(regs);
+	case EVENT_TYPE_NMI:
+		return fred_exc_nmi(regs);
+	default:
+		WARN_ON_ONCE(1);
+	}
+}
+#endif

arch/x86/include/asm/fred.h

@@ -9,6 +9,7 @@
 #include <linux/const.h>
 
 #include <asm/asm.h>
+#include <asm/trapnr.h>
 
 /*
  * FRED event return instruction opcodes for ERET{S,U}; supported in
@@ -62,12 +63,29 @@ static __always_inline unsigned long fred_event_data(struct pt_regs *regs)
 
 void asm_fred_entrypoint_user(void);
 void asm_fred_entrypoint_kernel(void);
+void asm_fred_entry_from_kvm(struct fred_ss);
 
 __visible void fred_entry_from_user(struct pt_regs *regs);
 __visible void fred_entry_from_kernel(struct pt_regs *regs);
+__visible void __fred_entry_from_kvm(struct pt_regs *regs);
+
+/* Can be called from noinstr code, thus __always_inline */
+static __always_inline void fred_entry_from_kvm(unsigned int type, unsigned int vector)
+{
+	struct fred_ss ss = {
+		.ss     =__KERNEL_DS,
+		.type   = type,
+		.vector = vector,
+		.nmi    = type == EVENT_TYPE_NMI,
+		.lm     = 1,
+	};
+
+	asm_fred_entry_from_kvm(ss);
+}
 
 #else /* CONFIG_X86_FRED */
 static __always_inline unsigned long fred_event_data(struct pt_regs *regs) { return 0; }
+static __always_inline void fred_entry_from_kvm(unsigned int type, unsigned int vector) { }
 #endif /* CONFIG_X86_FRED */
 #endif /* !__ASSEMBLY__ */