[kernel] Fix SMP boot on KVM

KVM didn't like setting all the CR4 bits we wanted at once. I suspect
that means real hardware won't either. Delay the setting of the rest of
CR4 until after the CPU is in long mode - only set PAE and PGE from real
mode.

src/kernel/ap_startup.s

@@ -20,6 +20,7 @@ CR4_OSFXSR     equ (1 << 9)
 CR4_OSCMMEXCPT equ (1 << 10)
 CR4_FSGSBASE   equ (1 << 16)
 CR4_PCIDE      equ (1 << 17)
+CR4_INIT equ CR4_PAE|CR4_PGE
 CR4_VAL equ CR4_DE|CR4_PAE|CR4_MCE|CR4_PGE|CR4_OSFXSR|CR4_OSCMMEXCPT|CR4_FSGSBASE|CR4_PCIDE
 
 EFER_MSR  equ 0xC0000080
@@ -69,7 +70,8 @@ align 4
 	lidt [BASE + (.idtd - ap_startup)]
 
 	; Enter long mode
-	mov eax, CR4_VAL
+	mov eax, cr4
+	or eax, CR4_INIT
 	mov cr4, eax
 
 	mov eax, [BASE + (.pml4 - ap_startup)]
@@ -100,6 +102,8 @@ align 8
 	mov gs, ax
 	mov ss, ax
 
+	mov eax, CR4_VAL
+
 	mov rdi, [BASE + (.cpu - ap_startup)]
 	mov rax, [rdi + CPU_DATA.rsp0]
 	mov rsp, rax

src/kernel/apic.cpp

@@ -70,16 +70,32 @@ lapic::get_id()
 }
 
 void
-lapic::send_ipi(ipi_mode mode, uint8_t vector, uint8_t dest)
+lapic::send_ipi(ipi mode, uint8_t vector, uint8_t dest)
 {
 	// Wait until the APIC is ready to send
 	ipi_wait();
 
-	apic_write(m_base, lapic_icr_high, static_cast<uint32_t>(dest) << 24);
 	uint32_t command =
 		static_cast<uint32_t>(vector) |
-		static_cast<uint32_t>(mode) << 8;
+		static_cast<uint32_t>(mode);
 
+	apic_write(m_base, lapic_icr_high, static_cast<uint32_t>(dest) << 24);
+	apic_write(m_base, lapic_icr_low, command);
+}
+
+void
+lapic::send_ipi_broadcast(ipi mode, bool self, uint8_t vector)
+{
+	// Wait until the APIC is ready to send
+	ipi_wait();
+
+	uint32_t command =
+		static_cast<uint32_t>(vector) |
+		static_cast<uint32_t>(mode) |
+		(self ? 0 : (1 << 18)) |
+		(1 << 19);
+
+	apic_write(m_base, lapic_icr_high, 0);
 	apic_write(m_base, lapic_icr_low, command);
 }
 

src/kernel/apic.h

@@ -3,6 +3,7 @@
 /// Classes to control both local and I/O APICs.
 
 #include <stdint.h>
+#include "kutil/enum_bitfields.h"
 
 enum class isr : uint8_t;
 
@@ -18,6 +19,22 @@ protected:
 	uint32_t *m_base;
 };
 
+enum class ipi : uint32_t
+{
+	// Delivery modes
+	fixed    = 0x0000,
+	smi      = 0x0200,
+	nmi      = 0x0400,
+	init     = 0x0500,
+	startup  = 0x0600,
+
+	// Flags
+	deassert = 0x0000,
+	assert   = 0x4000,
+	edge     = 0x0000, ///< edge-triggered
+	level    = 0x8000, ///< level-triggered
+};
+IS_BITFIELD(ipi);
 
 /// Controller for processor-local APICs
 class lapic :
@@ -32,19 +49,17 @@ public:
 	/// Get the local APIC's ID
 	uint8_t get_id();
 
-	enum class ipi_mode : uint8_t {
-		fixed   = 0,
-		smi     = 2,
-		nmi     = 4,
-		init    = 5,
-		startup = 6,
-	};
-
 	/// Send an inter-processor interrupt.
 	/// \arg mode   The sending mode
 	/// \arg vector The interrupt vector
 	/// \arg dest   The APIC ID of the destination
-	void send_ipi(ipi_mode mode, uint8_t vector, uint8_t dest);
+	void send_ipi(ipi mode, uint8_t vector, uint8_t dest);
+
+	/// Send an inter-processor broadcast interrupt to all other CPUs
+	/// \arg mode   The sending mode
+	/// \arg self   If true, include this CPU in the broadcast
+	/// \arg vector The interrupt vector
+	void send_ipi_broadcast(ipi mode, bool self, uint8_t vector);
 
 	/// Wait for an IPI to finish sending. This is done automatically
 	/// before sending another IPI with send_ipi().

src/kernel/main.cpp

@@ -254,6 +254,9 @@ start_aps(void *kpml4)
 	size_t free_stack_count = 0;
 	uintptr_t stack_area_start = 0;
 
+	ipi mode = ipi::init | ipi::level | ipi::assert;
+	apic.send_ipi_broadcast(mode, false, 0);
+
 	for (uint8_t id : ids) {
 		if (id == apic.get_id()) continue;
 
@@ -287,10 +290,10 @@ start_aps(void *kpml4)
 		// Kick it off!
 		size_t current_count = ap_startup_count;
 		log::debug(logs::boot, "Starting AP %d: stack %llx", cpu->index, stack_end);
-		apic.send_ipi(lapic::ipi_mode::init, 0, id);
-		clk.spinwait(1000);
 
-		apic.send_ipi(lapic::ipi_mode::startup, vector, id);
+		ipi startup = ipi::startup | ipi::assert;
+
+		apic.send_ipi(startup, vector, id);
 		for (unsigned i = 0; i < 20; ++i) {
 			if (ap_startup_count > current_count) break;
 			clk.spinwait(20);
@@ -301,7 +304,7 @@ start_aps(void *kpml4)
 			continue;
 
 		// Send the second SIPI (intel recommends this)
-		apic.send_ipi(lapic::ipi_mode::startup, vector, id);
+		apic.send_ipi(startup, vector, id);
 		for (unsigned i = 0; i < 100; ++i) {
 			if (ap_startup_count > current_count) break;
 			clk.spinwait(100);