Merge branch 'x86-platform-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 platform updates from Thomas Gleixner:
 "The platform support for x86 contains the following updates:

   - A set of updates for the UV platform to support new CPUs and to fix
     some of the UV4A BAU MRRs

   - The initial platform support for the jailhouse hypervisor to allow
     native Linux guests (inmates) in non-root cells.

   - A fix for the PCI initialization on Intel MID platforms"

* 'x86-platform-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (24 commits)
  x86/jailhouse: Respect pci=lastbus command line settings
  x86/jailhouse: Set X86_FEATURE_TSC_KNOWN_FREQ
  x86/platform/intel-mid: Move PCI initialization to arch_init()
  x86/platform/uv/BAU: Replace hard-coded values with MMR definitions
  x86/platform/UV: Fix UV4A BAU MMRs
  x86/platform/UV: Fix GAM MMR references in the UV x2apic code
  x86/platform/UV: Fix GAM MMR changes in UV4A
  x86/platform/UV: Add references to access fixed UV4A HUB MMRs
  x86/platform/UV: Fix UV4A support on new Intel Processors
  x86/platform/UV: Update uv_mmrs.h to prepare for UV4A fixes
  x86/jailhouse: Add PCI dependency
  x86/jailhouse: Hide x2apic code when CONFIG_X86_X2APIC=n
  x86/jailhouse: Initialize PCI support
  x86/jailhouse: Wire up IOAPIC for legacy UART ports
  x86/jailhouse: Halt instead of failing to restart
  x86/jailhouse: Silence ACPI warning
  x86/jailhouse: Avoid access of unsupported platform resources
  x86/jailhouse: Set up timekeeping
  x86/jailhouse: Enable PMTIMER
  x86/jailhouse: Enable APIC and SMP support
  ...

arch/x86/Kconfig

@@ -810,6 +810,15 @@ config PARAVIRT_TIME_ACCOUNTING
 config PARAVIRT_CLOCK
 	bool
 
+config JAILHOUSE_GUEST
+	bool "Jailhouse non-root cell support"
+	depends on X86_64 && PCI
+	select X86_PM_TIMER
+	---help---
+	  This option allows to run Linux as guest in a Jailhouse non-root
+	  cell. You can leave this option disabled if you only want to start
+	  Jailhouse and run Linux afterwards in the root cell.
+
 endif #HYPERVISOR_GUEST
 
 config NO_BOOTMEM

arch/x86/include/asm/hypervisor.h

@@ -28,6 +28,7 @@ enum x86_hypervisor_type {
 	X86_HYPER_XEN_PV,
 	X86_HYPER_XEN_HVM,
 	X86_HYPER_KVM,
+	X86_HYPER_JAILHOUSE,
 };
 
 #ifdef CONFIG_HYPERVISOR_GUEST

arch/x86/include/asm/jailhouse_para.h

+/* SPDX-License-Identifier: GPL2.0 */
+
+/*
+ * Jailhouse paravirt_ops implementation
+ *
+ * Copyright (c) Siemens AG, 2015-2017
+ *
+ * Authors:
+ *  Jan Kiszka <jan.kiszka@siemens.com>
+ */
+
+#ifndef _ASM_X86_JAILHOUSE_PARA_H
+#define _ASM_X86_JAILHOUSE_PARA_H
+
+#include <linux/types.h>
+
+#ifdef CONFIG_JAILHOUSE_GUEST
+bool jailhouse_paravirt(void);
+#else
+static inline bool jailhouse_paravirt(void)
+{
+	return false;
+}
+#endif
+
+#endif /* _ASM_X86_JAILHOUSE_PARA_H */

arch/x86/include/asm/mpspec_def.h

@@ -128,9 +128,17 @@ enum mp_irq_source_types {
 	mp_ExtINT = 3
 };
 
-#define MP_IRQDIR_DEFAULT	0
-#define MP_IRQDIR_HIGH		1
-#define MP_IRQDIR_LOW		3
+#define MP_IRQPOL_DEFAULT	0x0
+#define MP_IRQPOL_ACTIVE_HIGH	0x1
+#define MP_IRQPOL_RESERVED	0x2
+#define MP_IRQPOL_ACTIVE_LOW	0x3
+#define MP_IRQPOL_MASK		0x3
+
+#define MP_IRQTRIG_DEFAULT	0x0
+#define MP_IRQTRIG_EDGE		0x4
+#define MP_IRQTRIG_RESERVED	0x8
+#define MP_IRQTRIG_LEVEL	0xc
+#define MP_IRQTRIG_MASK		0xc
 
 #define MP_APIC_ALL	0xFF
 

arch/x86/include/asm/uv/uv_bau.h

@@ -48,7 +48,6 @@
 #define UV2_NET_ENDPOINT_INTD		0x28
 #define UV_NET_ENDPOINT_INTD		(is_uv1_hub() ?			\
 			UV1_NET_ENDPOINT_INTD : UV2_NET_ENDPOINT_INTD)
-#define UV_DESC_PSHIFT			49
 #define UV_PAYLOADQ_GNODE_SHIFT		49
 #define UV_PTC_BASENAME			"sgi_uv/ptc_statistics"
 #define UV_BAU_BASENAME			"sgi_uv/bau_tunables"

arch/x86/include/asm/uv/uv_hub.h

@@ -241,6 +241,7 @@ static inline int uv_hub_info_check(int version)
 #define UV2_HUB_REVISION_BASE		3
 #define UV3_HUB_REVISION_BASE		5
 #define UV4_HUB_REVISION_BASE		7
+#define UV4A_HUB_REVISION_BASE		8	/* UV4 (fixed) rev 2 */
 
 #ifdef	UV1_HUB_IS_SUPPORTED
 static inline int is_uv1_hub(void)
@@ -280,6 +281,19 @@ static inline int is_uv3_hub(void)
 }
 #endif
 
+/* First test "is UV4A", then "is UV4" */
+#ifdef	UV4A_HUB_IS_SUPPORTED
+static inline int is_uv4a_hub(void)
+{
+	return (uv_hub_info->hub_revision >= UV4A_HUB_REVISION_BASE);
+}
+#else
+static inline int is_uv4a_hub(void)
+{
+	return 0;
+}
+#endif
+
 #ifdef	UV4_HUB_IS_SUPPORTED
 static inline int is_uv4_hub(void)
 {

arch/x86/include/asm/x86_init.h

@@ -212,6 +212,7 @@ enum x86_legacy_i8042_state {
 struct x86_legacy_features {
 	enum x86_legacy_i8042_state i8042;
 	int rtc;
+	int warm_reset;
 	int no_vga;
 	int reserve_bios_regions;
 	struct x86_legacy_devices devices;

arch/x86/include/uapi/asm/bootparam.h

@@ -9,6 +9,7 @@
 #define SETUP_PCI			3
 #define SETUP_EFI			4
 #define SETUP_APPLE_PROPERTIES		5
+#define SETUP_JAILHOUSE			6
 
 /* ram_size flags */
 #define RAMDISK_IMAGE_START_MASK	0x07FF
@@ -126,6 +127,27 @@ struct boot_e820_entry {
 	__u32 type;
 } __attribute__((packed));
 
+/*
+ * Smallest compatible version of jailhouse_setup_data required by this kernel.
+ */
+#define JAILHOUSE_SETUP_REQUIRED_VERSION	1
+
+/*
+ * The boot loader is passing platform information via this Jailhouse-specific
+ * setup data structure.
+ */
+struct jailhouse_setup_data {
+	u16	version;
+	u16	compatible_version;
+	u16	pm_timer_address;
+	u16	num_cpus;
+	u64	pci_mmconfig_base;
+	u32	tsc_khz;
+	u32	apic_khz;
+	u8	standard_ioapic;
+	u8	cpu_ids[255];
+} __attribute__((packed));
+
 /* The so-called "zeropage" */
 struct boot_params {
 	struct screen_info screen_info;			/* 0x000 */

arch/x86/kernel/Makefile

@@ -115,6 +115,8 @@ obj-$(CONFIG_PARAVIRT_SPINLOCKS)+= paravirt-spinlocks.o
 obj-$(CONFIG_PARAVIRT_CLOCK)	+= pvclock.o
 obj-$(CONFIG_X86_PMEM_LEGACY_DEVICE) += pmem.o
 
+obj-$(CONFIG_JAILHOUSE_GUEST)	+= jailhouse.o
+
 obj-$(CONFIG_EISA)		+= eisa.o
 obj-$(CONFIG_PCSPKR_PLATFORM)	+= pcspeaker.o
 

arch/x86/kernel/apic/apic_flat_64.c

@@ -19,6 +19,7 @@
 #include <asm/smp.h>
 #include <asm/apic.h>
 #include <asm/ipi.h>
+#include <asm/jailhouse_para.h>
 
 #include <linux/acpi.h>
 
@@ -218,6 +219,15 @@ static int physflat_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
 	return 0;
 }
 
+static void physflat_init_apic_ldr(void)
+{
+	/*
+	 * LDR and DFR are not involved in physflat mode, rather:
+	 * "In physical destination mode, the destination processor is
+	 * specified by its local APIC ID [...]." (Intel SDM, 10.6.2.1)
+	 */
+}
+
 static void physflat_send_IPI_allbutself(int vector)
 {
 	default_send_IPI_mask_allbutself_phys(cpu_online_mask, vector);
@@ -230,7 +240,8 @@ static void physflat_send_IPI_all(int vector)
 
 static int physflat_probe(void)
 {
-	if (apic == &apic_physflat || num_possible_cpus() > 8)
+	if (apic == &apic_physflat || num_possible_cpus() > 8 ||
+	    jailhouse_paravirt())
 		return 1;
 
 	return 0;
@@ -251,8 +262,7 @@ static struct apic apic_physflat __ro_after_init = {
 	.dest_logical			= 0,
 	.check_apicid_used		= NULL,
 
-	/* not needed, but shouldn't hurt: */
-	.init_apic_ldr			= flat_init_apic_ldr,
+	.init_apic_ldr			= physflat_init_apic_ldr,
 
 	.ioapic_phys_id_map		= NULL,
 	.setup_apic_routing		= NULL,

arch/x86/kernel/apic/io_apic.c

@@ -800,18 +800,18 @@ static int irq_polarity(int idx)
 	/*
 	 * Determine IRQ line polarity (high active or low active):
 	 */
-	switch (mp_irqs[idx].irqflag & 0x03) {
-	case 0:
+	switch (mp_irqs[idx].irqflag & MP_IRQPOL_MASK) {
+	case MP_IRQPOL_DEFAULT:
 		/* conforms to spec, ie. bus-type dependent polarity */
 		if (test_bit(bus, mp_bus_not_pci))
 			return default_ISA_polarity(idx);
 		else
 			return default_PCI_polarity(idx);
-	case 1:
+	case MP_IRQPOL_ACTIVE_HIGH:
 		return IOAPIC_POL_HIGH;
-	case 2:
+	case MP_IRQPOL_RESERVED:
 		pr_warn("IOAPIC: Invalid polarity: 2, defaulting to low\n");
-	case 3:
+	case MP_IRQPOL_ACTIVE_LOW:
 	default: /* Pointless default required due to do gcc stupidity */
 		return IOAPIC_POL_LOW;
 	}
@@ -845,8 +845,8 @@ static int irq_trigger(int idx)
 	/*
 	 * Determine IRQ trigger mode (edge or level sensitive):
 	 */
-	switch ((mp_irqs[idx].irqflag >> 2) & 0x03) {
-	case 0:
+	switch (mp_irqs[idx].irqflag & MP_IRQTRIG_MASK) {
+	case MP_IRQTRIG_DEFAULT:
 		/* conforms to spec, ie. bus-type dependent trigger mode */
 		if (test_bit(bus, mp_bus_not_pci))
 			trigger = default_ISA_trigger(idx);
@@ -854,11 +854,11 @@ static int irq_trigger(int idx)
 			trigger = default_PCI_trigger(idx);
 		/* Take EISA into account */
 		return eisa_irq_trigger(idx, bus, trigger);
-	case 1:
+	case MP_IRQTRIG_EDGE:
 		return IOAPIC_EDGE;
-	case 2:
+	case MP_IRQTRIG_RESERVED:
 		pr_warn("IOAPIC: Invalid trigger mode 2 defaulting to level\n");
-	case 3:
+	case MP_IRQTRIG_LEVEL:
 	default: /* Pointless default required due to do gcc stupidity */
 		return IOAPIC_LEVEL;
 	}

arch/x86/kernel/apic/x2apic_uv_x.c

@@ -137,6 +137,8 @@ static int __init early_get_pnodeid(void)
 	case UV3_HUB_PART_NUMBER_X:
 		uv_min_hub_revision_id += UV3_HUB_REVISION_BASE;
 		break;
+
+	/* Update: UV4A has only a modified revision to indicate HUB fixes */
 	case UV4_HUB_PART_NUMBER:
 		uv_min_hub_revision_id += UV4_HUB_REVISION_BASE - 1;
 		uv_cpuid.gnode_shift = 2; /* min partition is 4 sockets */
@@ -316,6 +318,7 @@ static int __init uv_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
 	} else if (!strcmp(oem_table_id, "UVH")) {
 		/* Only UV1 systems: */
 		uv_system_type = UV_NON_UNIQUE_APIC;
+		x86_platform.legacy.warm_reset = 0;
 		__this_cpu_write(x2apic_extra_bits, pnodeid << uvh_apicid.s.pnode_shift);
 		uv_set_apicid_hibit();
 		uv_apic = 1;
@@ -767,6 +770,7 @@ static __init void map_gru_high(int max_pnode)
 		return;
 	}
 
+	/* Only UV3 has distributed GRU mode */
 	if (is_uv3_hub() && gru.s3.mode) {
 		map_gru_distributed(gru.v);
 		return;
@@ -790,63 +794,61 @@ static __init void map_mmr_high(int max_pnode)
 		pr_info("UV: MMR disabled\n");
 }
 
-/*
- * This commonality works because both 0 & 1 versions of the MMIOH OVERLAY
- * and REDIRECT MMR regs are exactly the same on UV3.
- */
-struct mmioh_config {
-	unsigned long overlay;
-	unsigned long redirect;
-	char *id;
-};
-
-static __initdata struct mmioh_config mmiohs[] = {
-	{
-		UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR,
-		UV3H_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR,
-		"MMIOH0"
-	},
-	{
-		UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR,
-		UV3H_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR,
-		"MMIOH1"
-	},
-};
-
-/* UV3 & UV4 have identical MMIOH overlay configs */
-static __init void map_mmioh_high_uv3(int index, int min_pnode, int max_pnode)
+/* UV3/4 have identical MMIOH overlay configs, UV4A is slightly different */
+static __init void map_mmioh_high_uv34(int index, int min_pnode, int max_pnode)
 {
-	union uv3h_rh_gam_mmioh_overlay_config0_mmr_u overlay;
+	unsigned long overlay;
 	unsigned long mmr;
 	unsigned long base;
+	unsigned long nasid_mask;
+	unsigned long m_overlay;
 	int i, n, shift, m_io, max_io;
 	int nasid, lnasid, fi, li;
 	char *id;
 
-	id = mmiohs[index].id;
-	overlay.v = uv_read_local_mmr(mmiohs[index].overlay);
-
-	pr_info("UV: %s overlay 0x%lx base:0x%x m_io:%d\n", id, overlay.v, overlay.s3.base, overlay.s3.m_io);
-	if (!overlay.s3.enable) {
+	if (index == 0) {
+		id = "MMIOH0";
+		m_overlay = UVH_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR;
+		overlay = uv_read_local_mmr(m_overlay);
+		base = overlay & UVH_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_BASE_MASK;
+		mmr = UVH_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR;
+		m_io = (overlay & UVH_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_M_IO_MASK)
+			>> UVH_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_M_IO_SHFT;
+		shift = UVH_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_M_IO_SHFT;
+		n = UVH_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR_DEPTH;
+		nasid_mask = UVH_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR_NASID_MASK;
+	} else {
+		id = "MMIOH1";
+		m_overlay = UVH_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR;
+		overlay = uv_read_local_mmr(m_overlay);
+		base = overlay & UVH_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR_BASE_MASK;
+		mmr = UVH_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR;
+		m_io = (overlay & UVH_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR_M_IO_MASK)
+			>> UVH_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR_M_IO_SHFT;
+		shift = UVH_RH_GAM_MMIOH_OVERLAY_CONFIG1_MMR_M_IO_SHFT;
+		n = UVH_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR_DEPTH;
+		nasid_mask = UVH_RH_GAM_MMIOH_REDIRECT_CONFIG1_MMR_NASID_MASK;
+	}
+	pr_info("UV: %s overlay 0x%lx base:0x%lx m_io:%d\n", id, overlay, base, m_io);
+	if (!(overlay & UVH_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_ENABLE_MASK)) {
 		pr_info("UV: %s disabled\n", id);
 		return;
 	}
 
-	shift = UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR_BASE_SHFT;
-	base = (unsigned long)overlay.s3.base;
-	m_io = overlay.s3.m_io;
-	mmr = mmiohs[index].redirect;
-	n = UV3H_RH_GAM_MMIOH_REDIRECT_CONFIG0_MMR_DEPTH;
 	/* Convert to NASID: */
 	min_pnode *= 2;
 	max_pnode *= 2;
 	max_io = lnasid = fi = li = -1;
 
 	for (i = 0; i < n; i++) {
-		union uv3h_rh_gam_mmioh_redirect_config0_mmr_u redirect;
+		unsigned long m_redirect = mmr + i * 8;
+		unsigned long redirect = uv_read_local_mmr(m_redirect);
+
+		nasid = redirect & nasid_mask;
+		if (i == 0)
+			pr_info("UV: %s redirect base 0x%lx(@0x%lx) 0x%04x\n",
+				id, redirect, m_redirect, nasid);
 
-		redirect.v = uv_read_local_mmr(mmr + i * 8);
-		nasid = redirect.s3.nasid;
 		/* Invalid NASID: */
 		if (nasid < min_pnode || max_pnode < nasid)
 			nasid = -1;
@@ -894,8 +896,8 @@ static __init void map_mmioh_high(int min_pnode, int max_pnode)
 
 	if (is_uv3_hub() || is_uv4_hub()) {
 		/* Map both MMIOH regions: */
-		map_mmioh_high_uv3(0, min_pnode, max_pnode);
-		map_mmioh_high_uv3(1, min_pnode, max_pnode);
+		map_mmioh_high_uv34(0, min_pnode, max_pnode);
+		map_mmioh_high_uv34(1, min_pnode, max_pnode);
 		return;
 	}
 

arch/x86/kernel/cpu/hypervisor.c

@@ -31,6 +31,7 @@ extern const struct hypervisor_x86 x86_hyper_ms_hyperv;
 extern const struct hypervisor_x86 x86_hyper_xen_pv;
 extern const struct hypervisor_x86 x86_hyper_xen_hvm;
 extern const struct hypervisor_x86 x86_hyper_kvm;
+extern const struct hypervisor_x86 x86_hyper_jailhouse;
 
 static const __initconst struct hypervisor_x86 * const hypervisors[] =
 {
@@ -45,6 +46,9 @@ static const __initconst struct hypervisor_x86 * const hypervisors[] =
 #ifdef CONFIG_KVM_GUEST
 	&x86_hyper_kvm,
 #endif
+#ifdef CONFIG_JAILHOUSE_GUEST
+	&x86_hyper_jailhouse,
+#endif
 };
 
 enum x86_hypervisor_type x86_hyper_type;

arch/x86/kernel/jailhouse.c

+// SPDX-License-Identifier: GPL2.0
+/*
+ * Jailhouse paravirt_ops implementation
+ *
+ * Copyright (c) Siemens AG, 2015-2017
+ *
+ * Authors:
+ *  Jan Kiszka <jan.kiszka@siemens.com>
+ */
+
+#include <linux/acpi_pmtmr.h>
+#include <linux/kernel.h>
+#include <linux/reboot.h>
+#include <asm/apic.h>
+#include <asm/cpu.h>
+#include <asm/hypervisor.h>
+#include <asm/i8259.h>
+#include <asm/irqdomain.h>
+#include <asm/pci_x86.h>
+#include <asm/reboot.h>
+#include <asm/setup.h>
+
+static __initdata struct jailhouse_setup_data setup_data;
+static unsigned int precalibrated_tsc_khz;
+
+static uint32_t jailhouse_cpuid_base(void)
+{
+	if (boot_cpu_data.cpuid_level < 0 ||
+	    !boot_cpu_has(X86_FEATURE_HYPERVISOR))
+		return 0;
+
+	return hypervisor_cpuid_base("Jailhouse\0\0\0", 0);
+}
+
+static uint32_t __init jailhouse_detect(void)
+{
+	return jailhouse_cpuid_base();
+}
+
+static void jailhouse_get_wallclock(struct timespec *now)
+{
+	memset(now, 0, sizeof(*now));
+}
+
+static void __init jailhouse_timer_init(void)
+{
+	lapic_timer_frequency = setup_data.apic_khz * (1000 / HZ);
+}
+
+static unsigned long jailhouse_get_tsc(void)
+{
+	return precalibrated_tsc_khz;
+}
+
+static void __init jailhouse_x2apic_init(void)
+{
+#ifdef CONFIG_X86_X2APIC
+	if (!x2apic_enabled())
+		return;
+	/*
+	 * We do not have access to IR inside Jailhouse non-root cells.  So
+	 * we have to run in physical mode.
+	 */
+	x2apic_phys = 1;
+	/*
+	 * This will trigger the switch to apic_x2apic_phys.  Empty OEM IDs
+	 * ensure that only this APIC driver picks up the call.
+	 */
+	default_acpi_madt_oem_check("", "");
+#endif
+}
+
+static void __init jailhouse_get_smp_config(unsigned int early)
+{
+	struct ioapic_domain_cfg ioapic_cfg = {
+		.type = IOAPIC_DOMAIN_STRICT,
+		.ops = &mp_ioapic_irqdomain_ops,
+	};
+	struct mpc_intsrc mp_irq = {
+		.type = MP_INTSRC,
+		.irqtype = mp_INT,
+		.irqflag = MP_IRQPOL_ACTIVE_HIGH | MP_IRQTRIG_EDGE,
+	};
+	unsigned int cpu;
+
+	jailhouse_x2apic_init();
+
+	register_lapic_address(0xfee00000);
+
+	for (cpu = 0; cpu < setup_data.num_cpus; cpu++) {
+		generic_processor_info(setup_data.cpu_ids[cpu],
+				       boot_cpu_apic_version);
+	}
+
+	smp_found_config = 1;
+
+	if (setup_data.standard_ioapic) {
+		mp_register_ioapic(0, 0xfec00000, gsi_top, &ioapic_cfg);
+
+		/* Register 1:1 mapping for legacy UART IRQs 3 and 4 */
+		mp_irq.srcbusirq = mp_irq.dstirq = 3;
+		mp_save_irq(&mp_irq);
+
+		mp_irq.srcbusirq = mp_irq.dstirq = 4;
+		mp_save_irq(&mp_irq);
+	}
+}
+
+static void jailhouse_no_restart(void)
+{
+	pr_notice("Jailhouse: Restart not supported, halting\n");
+	machine_halt();
+}
+
+static int __init jailhouse_pci_arch_init(void)
+{
+	pci_direct_init(1);
+
+	/*
+	 * There are no bridges on the virtual PCI root bus under Jailhouse,
+	 * thus no other way to discover all devices than a full scan.
+	 * Respect any overrides via the command line, though.
+	 */
+	if (pcibios_last_bus < 0)
+		pcibios_last_bus = 0xff;
+
+	return 0;
+}
+
+static void __init jailhouse_init_platform(void)
+{
+	u64 pa_data = boot_params.hdr.setup_data;
+	struct setup_data header;
+	void *mapping;
+
+	x86_init.irqs.pre_vector_init	= x86_init_noop;
+	x86_init.timers.timer_init	= jailhouse_timer_init;
+	x86_init.mpparse.get_smp_config	= jailhouse_get_smp_config;
+	x86_init.pci.arch_init		= jailhouse_pci_arch_init;
+
+	x86_platform.calibrate_cpu	= jailhouse_get_tsc;
+	x86_platform.calibrate_tsc	= jailhouse_get_tsc;
+	x86_platform.get_wallclock	= jailhouse_get_wallclock;
+	x86_platform.legacy.rtc		= 0;
+	x86_platform.legacy.warm_reset	= 0;
+	x86_platform.legacy.i8042	= X86_LEGACY_I8042_PLATFORM_ABSENT;
+
+	legacy_pic			= &null_legacy_pic;
+
+	machine_ops.emergency_restart	= jailhouse_no_restart;
+
+	while (pa_data) {
+		mapping = early_memremap(pa_data, sizeof(header));
+		memcpy(&header, mapping, sizeof(header));
+		early_memunmap(mapping, sizeof(header));
+
+		if (header.type == SETUP_JAILHOUSE &&
+		    header.len >= sizeof(setup_data)) {
+			pa_data += offsetof(struct setup_data, data);
+
+			mapping = early_memremap(pa_data, sizeof(setup_data));
+			memcpy(&setup_data, mapping, sizeof(setup_data));
+			early_memunmap(mapping, sizeof(setup_data));
+
+			break;
+		}
+
+		pa_data = header.next;
+	}
+
+	if (!pa_data)
+		panic("Jailhouse: No valid setup data found");
+
+	if (setup_data.compatible_version > JAILHOUSE_SETUP_REQUIRED_VERSION)
+		panic("Jailhouse: Unsupported setup data structure");
+
+	pmtmr_ioport = setup_data.pm_timer_address;
+	pr_debug("Jailhouse: PM-Timer IO Port: %#x\n", pmtmr_ioport);
+
+	precalibrated_tsc_khz = setup_data.tsc_khz;
+	setup_force_cpu_cap(X86_FEATURE_TSC_KNOWN_FREQ);
+
+	pci_probe = 0;
+
+	/*
+	 * Avoid that the kernel complains about missing ACPI tables - there
+	 * are none in a non-root cell.
+	 */
+	disable_acpi();
+}
+
+bool jailhouse_paravirt(void)
+{
+	return jailhouse_cpuid_base() != 0;
+}
+
+static bool jailhouse_x2apic_available(void)
+{
+	/*
+	 * The x2APIC is only available if the root cell enabled it. Jailhouse
+	 * does not support switching between xAPIC and x2APIC.
+	 */
+	return x2apic_enabled();
+}
+
+const struct hypervisor_x86 x86_hyper_jailhouse __refconst = {
+	.name			= "Jailhouse",
+	.detect			= jailhouse_detect,
+	.init.init_platform	= jailhouse_init_platform,
+	.init.x2apic_available	= jailhouse_x2apic_available,
+};

arch/x86/kernel/mpparse.c

@@ -281,7 +281,7 @@ static void __init construct_default_ioirq_mptable(int mpc_default_type)
 	int ELCR_fallback = 0;
 
 	intsrc.type = MP_INTSRC;
-	intsrc.irqflag = 0;	/* conforming */
+	intsrc.irqflag = MP_IRQTRIG_DEFAULT | MP_IRQPOL_DEFAULT;
 	intsrc.srcbus = 0;
 	intsrc.dstapic = mpc_ioapic_id(0);
 
@@ -324,10 +324,13 @@ static void __init construct_default_ioirq_mptable(int mpc_default_type)
 			 *  copy that information over to the MP table in the
 			 *  irqflag field (level sensitive, active high polarity).
 			 */
-			if (ELCR_trigger(i))
-				intsrc.irqflag = 13;
-			else
-				intsrc.irqflag = 0;
+			if (ELCR_trigger(i)) {
+				intsrc.irqflag = MP_IRQTRIG_LEVEL |
+						 MP_IRQPOL_ACTIVE_HIGH;
+			} else {
+				intsrc.irqflag = MP_IRQTRIG_DEFAULT |
+						 MP_IRQPOL_DEFAULT;
+			}
 		}
 
 		intsrc.srcbusirq = i;
@@ -419,7 +422,7 @@ static inline void __init construct_default_ISA_mptable(int mpc_default_type)
 	construct_ioapic_table(mpc_default_type);
 
 	lintsrc.type = MP_LINTSRC;
-	lintsrc.irqflag = 0;		/* conforming */
+	lintsrc.irqflag = MP_IRQTRIG_DEFAULT | MP_IRQPOL_DEFAULT;
 	lintsrc.srcbusid = 0;
 	lintsrc.srcbusirq = 0;
 	lintsrc.destapic = MP_APIC_ALL;
@@ -664,7 +667,7 @@ static int  __init get_MP_intsrc_index(struct mpc_intsrc *m)
 	if (m->irqtype != mp_INT)
 		return 0;
 
-	if (m->irqflag != 0x0f)
+	if (m->irqflag != (MP_IRQTRIG_LEVEL | MP_IRQPOL_ACTIVE_LOW))
 		return 0;
 
 	/* not legacy */
@@ -673,7 +676,8 @@ static int  __init get_MP_intsrc_index(struct mpc_intsrc *m)
 		if (mp_irqs[i].irqtype != mp_INT)
 			continue;
 
-		if (mp_irqs[i].irqflag != 0x0f)
+		if (mp_irqs[i].irqflag != (MP_IRQTRIG_LEVEL |
+					   MP_IRQPOL_ACTIVE_LOW))
 			continue;
 
 		if (mp_irqs[i].srcbus != m->srcbus)
@@ -784,7 +788,8 @@ static int  __init replace_intsrc_all(struct mpc_table *mpc,
 		if (mp_irqs[i].irqtype != mp_INT)
 			continue;
 
-		if (mp_irqs[i].irqflag != 0x0f)
+		if (mp_irqs[i].irqflag != (MP_IRQTRIG_LEVEL |
+					   MP_IRQPOL_ACTIVE_LOW))
 			continue;
 
 		if (nr_m_spare > 0) {

arch/x86/kernel/platform-quirks.c

@@ -9,6 +9,7 @@ void __init x86_early_init_platform_quirks(void)
 {
 	x86_platform.legacy.i8042 = X86_LEGACY_I8042_EXPECTED_PRESENT;
 	x86_platform.legacy.rtc = 1;
+	x86_platform.legacy.warm_reset = 1;
 	x86_platform.legacy.reserve_bios_regions = 0;
 	x86_platform.legacy.devices.pnpbios = 1;
 

arch/x86/kernel/smpboot.c

@@ -934,7 +934,7 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle,
 	 * the targeted processor.
 	 */
 
-	if (get_uv_system_type() != UV_NON_UNIQUE_APIC) {
+	if (x86_platform.legacy.warm_reset) {
 
 		pr_debug("Setting warm reset code and vector.\n");
 
@@ -1006,7 +1006,7 @@ static int do_boot_cpu(int apicid, int cpu, struct task_struct *idle,
 	/* mark "stuck" area as not stuck */
 	*trampoline_status = 0;
 
-	if (get_uv_system_type() != UV_NON_UNIQUE_APIC) {
+	if (x86_platform.legacy.warm_reset) {
 		/*
 		 * Cleanup possible dangling ends...
 		 */

arch/x86/pci/intel_mid_pci.c

@@ -300,6 +300,7 @@ int __init intel_mid_pci_init(void)
 	pci_root_ops = intel_mid_pci_ops;
 	pci_soc_mode = 1;
 	/* Continue with standard init */
+	acpi_noirq_set();
 	return 1;
 }
 

arch/x86/platform/intel-mid/intel-mid.c

@@ -194,7 +194,7 @@ void __init x86_intel_mid_early_setup(void)
 	x86_platform.calibrate_tsc = intel_mid_calibrate_tsc;
 	x86_platform.get_nmi_reason = intel_mid_get_nmi_reason;
 
-	x86_init.pci.init = intel_mid_pci_init;
+	x86_init.pci.arch_init = intel_mid_pci_init;
 	x86_init.pci.fixup_irqs = x86_init_noop;
 
 	legacy_pic = &null_legacy_pic;

arch/x86/platform/intel-mid/sfi.c

@@ -96,8 +96,7 @@ int __init sfi_parse_mtmr(struct sfi_table_header *table)
 			pentry->freq_hz, pentry->irq);
 		mp_irq.type = MP_INTSRC;
 		mp_irq.irqtype = mp_INT;
-		/* triggering mode edge bit 2-3, active high polarity bit 0-1 */
-		mp_irq.irqflag = 5;
+		mp_irq.irqflag = MP_IRQTRIG_EDGE | MP_IRQPOL_ACTIVE_HIGH;
 		mp_irq.srcbus = MP_BUS_ISA;
 		mp_irq.srcbusirq = pentry->irq;	/* IRQ */
 		mp_irq.dstapic = MP_APIC_ALL;
@@ -168,7 +167,7 @@ int __init sfi_parse_mrtc(struct sfi_table_header *table)
 			totallen, (u32)pentry->phys_addr, pentry->irq);
 		mp_irq.type = MP_INTSRC;
 		mp_irq.irqtype = mp_INT;
-		mp_irq.irqflag = 0xf;	/* level trigger and active low */
+		mp_irq.irqflag = MP_IRQTRIG_LEVEL | MP_IRQPOL_ACTIVE_LOW;
 		mp_irq.srcbus = MP_BUS_ISA;
 		mp_irq.srcbusirq = pentry->irq;	/* IRQ */
 		mp_irq.dstapic = MP_APIC_ALL;

arch/x86/platform/uv/tlb_uv.c

@@ -1751,7 +1751,8 @@ static void activation_descriptor_init(int node, int pnode, int base_pnode)
 		uv1 = 1;
 
 	/* the 14-bit pnode */
-	write_mmr_descriptor_base(pnode, (n << UV_DESC_PSHIFT | m));
+	write_mmr_descriptor_base(pnode,
+		(n << UVH_LB_BAU_SB_DESCRIPTOR_BASE_NODE_ID_SHFT | m));
 	/*
 	 * Initializing all 8 (ITEMS_PER_DESC) descriptors for each
 	 * cpu even though we only use the first one; one descriptor can

drivers/acpi/Kconfig

@@ -361,22 +361,6 @@ config ACPI_PCI_SLOT
 	  i.e., segment/bus/device/function tuples, with physical slots in
 	  the system.  If you are unsure, say N.
 
-config X86_PM_TIMER
-	bool "Power Management Timer Support" if EXPERT
-	depends on X86
-	default y
-	help
-	  The Power Management Timer is available on all ACPI-capable,
-	  in most cases even if ACPI is unusable or blacklisted.
-
-	  This timing source is not affected by power management features
-	  like aggressive processor idling, throttling, frequency and/or
-	  voltage scaling, unlike the commonly used Time Stamp Counter
-	  (TSC) timing source.
-
-	  You should nearly always say Y here because many modern
-	  systems require this timer. 
-
 config ACPI_CONTAINER
 	bool "Container and Module Devices"
 	default (ACPI_HOTPLUG_MEMORY || ACPI_HOTPLUG_CPU)
@@ -564,3 +548,19 @@ config TPS68470_PMIC_OPREGION
 	  using this, are probed.
 
 endif	# ACPI
+
+config X86_PM_TIMER
+	bool "Power Management Timer Support" if EXPERT
+	depends on X86 && (ACPI || JAILHOUSE_GUEST)
+	default y
+	help
+	  The Power Management Timer is available on all ACPI-capable,
+	  in most cases even if ACPI is unusable or blacklisted.
+
+	  This timing source is not affected by power management features
+	  like aggressive processor idling, throttling, frequency and/or
+	  voltage scaling, unlike the commonly used Time Stamp Counter
+	  (TSC) timing source.
+
+	  You should nearly always say Y here because many modern
+	  systems require this timer.