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

Pull misc x86 fixes from Ingo Molnar:
 - topology enumeration fixes
 - KASAN fix
 - two entry fixes (not yet the big series related to KASLR)
 - remove obsolete code
 - instruction decoder fix
 - better /dev/mem sanity checks, hopefully working better this time
 - pkeys fixes
 - two ACPI fixes
 - 5-level paging related fixes
 - UMIP fixes that should make application visible faults more debuggable
 - boot fix for weird virtualization environment

* 'x86-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (24 commits)
  x86/decoder: Add new TEST instruction pattern
  x86/PCI: Remove unused HyperTransport interrupt support
  x86/umip: Fix insn_get_code_seg_params()'s return value
  x86/boot/KASLR: Remove unused variable
  x86/entry/64: Add missing irqflags tracing to native_load_gs_index()
  x86/mm/kasan: Don't use vmemmap_populate() to initialize shadow
  x86/entry/64: Fix entry_SYSCALL_64_after_hwframe() IRQ tracing
  x86/pkeys/selftests: Fix protection keys write() warning
  x86/pkeys/selftests: Rename 'si_pkey' to 'siginfo_pkey'
  x86/mpx/selftests: Fix up weird arrays
  x86/pkeys: Update documentation about availability
  x86/umip: Print a warning into the syslog if UMIP-protected instructions are used
  x86/smpboot: Fix __max_logical_packages estimate
  x86/topology: Avoid wasting 128k for package id array
  perf/x86/intel/uncore: Cache logical pkg id in uncore driver
  x86/acpi: Reduce code duplication in mp_override_legacy_irq()
  x86/acpi: Handle SCI interrupts above legacy space gracefully
  x86/boot: Fix boot failure when SMP MP-table is based at 0
  x86/mm: Limit mmap() of /dev/mem to valid physical addresses
  x86/selftests: Add test for mapping placement for 5-level paging
  ...

Documentation/x86/protection-keys.txt

-Memory Protection Keys for Userspace (PKU aka PKEYs) is a CPU feature
-which will be found on future Intel CPUs.
+Memory Protection Keys for Userspace (PKU aka PKEYs) is a feature
+which is found on Intel's Skylake "Scalable Processor" Server CPUs.
+It will be avalable in future non-server parts.
+
+For anyone wishing to test or use this feature, it is available in
+Amazon's EC2 C5 instances and is known to work there using an Ubuntu
+17.04 image.
 
 Memory Protection Keys provides a mechanism for enforcing page-based
 protections, but without requiring modification of the page tables

arch/x86/Kconfig

@@ -1804,14 +1804,20 @@ config X86_SMAP
 	  If unsure, say Y.
 
 config X86_INTEL_UMIP
-	def_bool n
+	def_bool y
 	depends on CPU_SUP_INTEL
 	prompt "Intel User Mode Instruction Prevention" if EXPERT
 	---help---
 	  The User Mode Instruction Prevention (UMIP) is a security
 	  feature in newer Intel processors. If enabled, a general
-	  protection fault is issued if the instructions SGDT, SLDT,
-	  SIDT, SMSW and STR are executed in user mode.
+	  protection fault is issued if the SGDT, SLDT, SIDT, SMSW
+	  or STR instructions are executed in user mode. These instructions
+	  unnecessarily expose information about the hardware state.
+
+	  The vast majority of applications do not use these instructions.
+	  For the very few that do, software emulation is provided in
+	  specific cases in protected and virtual-8086 modes. Emulated
+	  results are dummy.
 
 config X86_INTEL_MPX
 	prompt "Intel MPX (Memory Protection Extensions)"

arch/x86/boot/compressed/kaslr.c

@@ -171,7 +171,6 @@ parse_memmap(char *p, unsigned long long *start, unsigned long long *size)
 static void mem_avoid_memmap(char *str)
 {
 	static int i;
-	int rc;
 
 	if (i >= MAX_MEMMAP_REGIONS)
 		return;
@@ -219,7 +218,7 @@ static int handle_mem_memmap(void)
 		return 0;
 
 	tmp_cmdline = malloc(len + 1);
-	if (!tmp_cmdline )
+	if (!tmp_cmdline)
 		error("Failed to allocate space for tmp_cmdline");
 
 	memcpy(tmp_cmdline, args, len);
@@ -363,7 +362,7 @@ static void mem_avoid_init(unsigned long input, unsigned long input_size,
 	cmd_line |= boot_params->hdr.cmd_line_ptr;
 	/* Calculate size of cmd_line. */
 	ptr = (char *)(unsigned long)cmd_line;
-	for (cmd_line_size = 0; ptr[cmd_line_size++]; )
+	for (cmd_line_size = 0; ptr[cmd_line_size++];)
 		;
 	mem_avoid[MEM_AVOID_CMDLINE].start = cmd_line;
 	mem_avoid[MEM_AVOID_CMDLINE].size = cmd_line_size;

arch/x86/entry/entry_64.S

@@ -51,15 +51,19 @@ ENTRY(native_usergs_sysret64)
 END(native_usergs_sysret64)
 #endif /* CONFIG_PARAVIRT */
 
-.macro TRACE_IRQS_IRETQ
+.macro TRACE_IRQS_FLAGS flags:req
 #ifdef CONFIG_TRACE_IRQFLAGS
-	bt	$9, EFLAGS(%rsp)		/* interrupts off? */
+	bt	$9, \flags		/* interrupts off? */
 	jnc	1f
 	TRACE_IRQS_ON
 1:
 #endif
 .endm
 
+.macro TRACE_IRQS_IRETQ
+	TRACE_IRQS_FLAGS EFLAGS(%rsp)
+.endm
+
 /*
  * When dynamic function tracer is enabled it will add a breakpoint
  * to all locations that it is about to modify, sync CPUs, update
@@ -148,8 +152,6 @@ ENTRY(entry_SYSCALL_64)
 	movq	%rsp, PER_CPU_VAR(rsp_scratch)
 	movq	PER_CPU_VAR(cpu_current_top_of_stack), %rsp
 
-	TRACE_IRQS_OFF
-
 	/* Construct struct pt_regs on stack */
 	pushq	$__USER_DS			/* pt_regs->ss */
 	pushq	PER_CPU_VAR(rsp_scratch)	/* pt_regs->sp */
@@ -170,6 +172,8 @@ GLOBAL(entry_SYSCALL_64_after_hwframe)
 	sub	$(6*8), %rsp			/* pt_regs->bp, bx, r12-15 not saved */
 	UNWIND_HINT_REGS extra=0
 
+	TRACE_IRQS_OFF
+
 	/*
 	 * If we need to do entry work or if we guess we'll need to do
 	 * exit work, go straight to the slow path.
@@ -943,11 +947,13 @@ ENTRY(native_load_gs_index)
 	FRAME_BEGIN
 	pushfq
 	DISABLE_INTERRUPTS(CLBR_ANY & ~CLBR_RDI)
+	TRACE_IRQS_OFF
 	SWAPGS
 .Lgs_change:
 	movl	%edi, %gs
 2:	ALTERNATIVE "", "mfence", X86_BUG_SWAPGS_FENCE
 	SWAPGS
+	TRACE_IRQS_FLAGS (%rsp)
 	popfq
 	FRAME_END
 	ret

arch/x86/events/intel/uncore.c

@@ -975,10 +975,10 @@ static void uncore_pci_remove(struct pci_dev *pdev)
 	int i, phys_id, pkg;
 
 	phys_id = uncore_pcibus_to_physid(pdev->bus);
-	pkg = topology_phys_to_logical_pkg(phys_id);
 
 	box = pci_get_drvdata(pdev);
 	if (!box) {
+		pkg = topology_phys_to_logical_pkg(phys_id);
 		for (i = 0; i < UNCORE_EXTRA_PCI_DEV_MAX; i++) {
 			if (uncore_extra_pci_dev[pkg].dev[i] == pdev) {
 				uncore_extra_pci_dev[pkg].dev[i] = NULL;
@@ -994,7 +994,7 @@ static void uncore_pci_remove(struct pci_dev *pdev)
 		return;
 
 	pci_set_drvdata(pdev, NULL);
-	pmu->boxes[pkg] = NULL;
+	pmu->boxes[box->pkgid] = NULL;
 	if (atomic_dec_return(&pmu->activeboxes) == 0)
 		uncore_pmu_unregister(pmu);
 	uncore_box_exit(box);

arch/x86/events/intel/uncore.h

@@ -100,7 +100,7 @@ struct intel_uncore_extra_reg {
 
 struct intel_uncore_box {
 	int pci_phys_id;
-	int pkgid;
+	int pkgid;	/* Logical package ID */
 	int n_active;	/* number of active events */
 	int n_events;
 	int cpu;	/* cpu to collect events */

arch/x86/events/intel/uncore_snbep.c

@@ -1057,7 +1057,7 @@ static void snbep_qpi_enable_event(struct intel_uncore_box *box, struct perf_eve
 
 	if (reg1->idx != EXTRA_REG_NONE) {
 		int idx = box->pmu->pmu_idx + SNBEP_PCI_QPI_PORT0_FILTER;
-		int pkg = topology_phys_to_logical_pkg(box->pci_phys_id);
+		int pkg = box->pkgid;
 		struct pci_dev *filter_pdev = uncore_extra_pci_dev[pkg].dev[idx];
 
 		if (filter_pdev) {

arch/x86/include/asm/elf.h

@@ -309,6 +309,7 @@ static inline int mmap_is_ia32(void)
 extern unsigned long task_size_32bit(void);
 extern unsigned long task_size_64bit(int full_addr_space);
 extern unsigned long get_mmap_base(int is_legacy);
+extern bool mmap_address_hint_valid(unsigned long addr, unsigned long len);
 
 #ifdef CONFIG_X86_32
 

arch/x86/include/asm/hw_irq.h

@@ -99,14 +99,6 @@ struct irq_alloc_info {
 			void		*dmar_data;
 		};
 #endif
-#ifdef	CONFIG_HT_IRQ
-		struct {
-			int		ht_pos;
-			int		ht_idx;
-			struct pci_dev	*ht_dev;
-			void		*ht_update;
-		};
-#endif
 #ifdef	CONFIG_X86_UV
 		struct {
 			int		uv_limit;

arch/x86/include/asm/hypertransport.h

-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _ASM_X86_HYPERTRANSPORT_H
-#define _ASM_X86_HYPERTRANSPORT_H
-
-/*
- * Constants for x86 Hypertransport Interrupts.
- */
-
-#define HT_IRQ_LOW_BASE			0xf8000000
-
-#define HT_IRQ_LOW_VECTOR_SHIFT		16
-#define HT_IRQ_LOW_VECTOR_MASK		0x00ff0000
-#define HT_IRQ_LOW_VECTOR(v)						\
-	(((v) << HT_IRQ_LOW_VECTOR_SHIFT) & HT_IRQ_LOW_VECTOR_MASK)
-
-#define HT_IRQ_LOW_DEST_ID_SHIFT	8
-#define HT_IRQ_LOW_DEST_ID_MASK		0x0000ff00
-#define HT_IRQ_LOW_DEST_ID(v)						\
-	(((v) << HT_IRQ_LOW_DEST_ID_SHIFT) & HT_IRQ_LOW_DEST_ID_MASK)
-
-#define HT_IRQ_LOW_DM_PHYSICAL		0x0000000
-#define HT_IRQ_LOW_DM_LOGICAL		0x0000040
-
-#define HT_IRQ_LOW_RQEOI_EDGE		0x0000000
-#define HT_IRQ_LOW_RQEOI_LEVEL		0x0000020
-
-
-#define HT_IRQ_LOW_MT_FIXED		0x0000000
-#define HT_IRQ_LOW_MT_ARBITRATED	0x0000004
-#define HT_IRQ_LOW_MT_SMI		0x0000008
-#define HT_IRQ_LOW_MT_NMI		0x000000c
-#define HT_IRQ_LOW_MT_INIT		0x0000010
-#define HT_IRQ_LOW_MT_STARTUP		0x0000014
-#define HT_IRQ_LOW_MT_EXTINT		0x0000018
-#define HT_IRQ_LOW_MT_LINT1		0x000008c
-#define HT_IRQ_LOW_MT_LINT0		0x0000098
-
-#define HT_IRQ_LOW_IRQ_MASKED		0x0000001
-
-
-#define HT_IRQ_HIGH_DEST_ID_SHIFT	0
-#define HT_IRQ_HIGH_DEST_ID_MASK	0x00ffffff
-#define HT_IRQ_HIGH_DEST_ID(v)						\
-	((((v) >> 8) << HT_IRQ_HIGH_DEST_ID_SHIFT) & HT_IRQ_HIGH_DEST_ID_MASK)
-
-#endif /* _ASM_X86_HYPERTRANSPORT_H */

arch/x86/include/asm/insn-eval.h

@@ -18,6 +18,6 @@
 void __user *insn_get_addr_ref(struct insn *insn, struct pt_regs *regs);
 int insn_get_modrm_rm_off(struct insn *insn, struct pt_regs *regs);
 unsigned long insn_get_seg_base(struct pt_regs *regs, int seg_reg_idx);
-char insn_get_code_seg_params(struct pt_regs *regs);
+int insn_get_code_seg_params(struct pt_regs *regs);
 
 #endif /* _ASM_X86_INSN_EVAL_H */

arch/x86/include/asm/io.h

@@ -111,6 +111,10 @@ build_mmio_write(__writeq, "q", unsigned long, "r", )
 
 #endif
 
+#define ARCH_HAS_VALID_PHYS_ADDR_RANGE
+extern int valid_phys_addr_range(phys_addr_t addr, size_t size);
+extern int valid_mmap_phys_addr_range(unsigned long pfn, size_t size);
+
 /**
  *	virt_to_phys	-	map virtual addresses to physical
  *	@address: address to remap

arch/x86/include/asm/irqdomain.h

@@ -56,10 +56,4 @@ extern void arch_init_msi_domain(struct irq_domain *domain);
 static inline void arch_init_msi_domain(struct irq_domain *domain) { }
 #endif
 
-#ifdef CONFIG_HT_IRQ
-extern void arch_init_htirq_domain(struct irq_domain *domain);
-#else
-static inline void arch_init_htirq_domain(struct irq_domain *domain) { }
-#endif
-
 #endif

arch/x86/include/asm/processor.h

@@ -132,6 +132,7 @@ struct cpuinfo_x86 {
 	/* Index into per_cpu list: */
 	u16			cpu_index;
 	u32			microcode;
+	unsigned		initialized : 1;
 } __randomize_layout;
 
 struct cpuid_regs {

arch/x86/kernel/acpi/boot.c

@@ -342,13 +342,12 @@ acpi_parse_lapic_nmi(struct acpi_subtable_header * header, const unsigned long e
 #ifdef CONFIG_X86_IO_APIC
 #define MP_ISA_BUS		0
 
+static int __init mp_register_ioapic_irq(u8 bus_irq, u8 polarity,
+						u8 trigger, u32 gsi);
+
 static void __init mp_override_legacy_irq(u8 bus_irq, u8 polarity, u8 trigger,
 					  u32 gsi)
 {
-	int ioapic;
-	int pin;
-	struct mpc_intsrc mp_irq;
-
 	/*
 	 * Check bus_irq boundary.
 	 */
@@ -357,14 +356,6 @@ static void __init mp_override_legacy_irq(u8 bus_irq, u8 polarity, u8 trigger,
 		return;
 	}
 
-	/*
-	 * Convert 'gsi' to 'ioapic.pin'.
-	 */
-	ioapic = mp_find_ioapic(gsi);
-	if (ioapic < 0)
-		return;
-	pin = mp_find_ioapic_pin(ioapic, gsi);
-
 	/*
 	 * TBD: This check is for faulty timer entries, where the override
 	 *      erroneously sets the trigger to level, resulting in a HUGE
@@ -373,16 +364,8 @@ static void __init mp_override_legacy_irq(u8 bus_irq, u8 polarity, u8 trigger,
 	if ((bus_irq == 0) && (trigger == 3))
 		trigger = 1;
 
-	mp_irq.type = MP_INTSRC;
-	mp_irq.irqtype = mp_INT;
-	mp_irq.irqflag = (trigger << 2) | polarity;
-	mp_irq.srcbus = MP_ISA_BUS;
-	mp_irq.srcbusirq = bus_irq;	/* IRQ */
-	mp_irq.dstapic = mpc_ioapic_id(ioapic); /* APIC ID */
-	mp_irq.dstirq = pin;	/* INTIN# */
-
-	mp_save_irq(&mp_irq);
-
+	if (mp_register_ioapic_irq(bus_irq, polarity, trigger, gsi) < 0)
+		return;
 	/*
 	 * Reset default identity mapping if gsi is also an legacy IRQ,
 	 * otherwise there will be more than one entry with the same GSI
@@ -429,6 +412,34 @@ static int mp_config_acpi_gsi(struct device *dev, u32 gsi, int trigger,
 	return 0;
 }
 
+static int __init mp_register_ioapic_irq(u8 bus_irq, u8 polarity,
+						u8 trigger, u32 gsi)
+{
+	struct mpc_intsrc mp_irq;
+	int ioapic, pin;
+
+	/* Convert 'gsi' to 'ioapic.pin'(INTIN#) */
+	ioapic = mp_find_ioapic(gsi);
+	if (ioapic < 0) {
+		pr_warn("Failed to find ioapic for gsi : %u\n", gsi);
+		return ioapic;
+	}
+
+	pin = mp_find_ioapic_pin(ioapic, gsi);
+
+	mp_irq.type = MP_INTSRC;
+	mp_irq.irqtype = mp_INT;
+	mp_irq.irqflag = (trigger << 2) | polarity;
+	mp_irq.srcbus = MP_ISA_BUS;
+	mp_irq.srcbusirq = bus_irq;
+	mp_irq.dstapic = mpc_ioapic_id(ioapic);
+	mp_irq.dstirq = pin;
+
+	mp_save_irq(&mp_irq);
+
+	return 0;
+}
+
 static int __init
 acpi_parse_ioapic(struct acpi_subtable_header * header, const unsigned long end)
 {
@@ -473,7 +484,11 @@ static void __init acpi_sci_ioapic_setup(u8 bus_irq, u16 polarity, u16 trigger,
 	if (acpi_sci_flags & ACPI_MADT_POLARITY_MASK)
 		polarity = acpi_sci_flags & ACPI_MADT_POLARITY_MASK;
 
+	if (bus_irq < NR_IRQS_LEGACY)
 		mp_override_legacy_irq(bus_irq, polarity, trigger, gsi);
+	else
+		mp_register_ioapic_irq(bus_irq, polarity, trigger, gsi);
+
 	acpi_penalize_sci_irq(bus_irq, trigger, polarity);
 
 	/*

arch/x86/kernel/apic/Makefile

@@ -12,7 +12,6 @@ obj-y				+= hw_nmi.o
 
 obj-$(CONFIG_X86_IO_APIC)	+= io_apic.o
 obj-$(CONFIG_PCI_MSI)		+= msi.o
-obj-$(CONFIG_HT_IRQ)		+= htirq.o
 obj-$(CONFIG_SMP)		+= ipi.o
 
 ifeq ($(CONFIG_X86_64),y)

arch/x86/kernel/apic/htirq.c

-/*
- * Support Hypertransport IRQ
- *
- * Copyright (C) 1997, 1998, 1999, 2000, 2009 Ingo Molnar, Hajnalka Szabo
- *	Moved from arch/x86/kernel/apic/io_apic.c.
- * Jiang Liu <jiang.liu@linux.intel.com>
- *	Add support of hierarchical irqdomain
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-#include <linux/mm.h>
-#include <linux/interrupt.h>
-#include <linux/init.h>
-#include <linux/device.h>
-#include <linux/pci.h>
-#include <linux/htirq.h>
-#include <asm/irqdomain.h>
-#include <asm/hw_irq.h>
-#include <asm/apic.h>
-#include <asm/hypertransport.h>
-
-static struct irq_domain *htirq_domain;
-
-/*
- * Hypertransport interrupt support
- */
-static int
-ht_set_affinity(struct irq_data *data, const struct cpumask *mask, bool force)
-{
-	struct irq_data *parent = data->parent_data;
-	int ret;
-
-	ret = parent->chip->irq_set_affinity(parent, mask, force);
-	if (ret >= 0) {
-		struct ht_irq_msg msg;
-		struct irq_cfg *cfg = irqd_cfg(data);
-
-		fetch_ht_irq_msg(data->irq, &msg);
-		msg.address_lo &= ~(HT_IRQ_LOW_VECTOR_MASK |
-				    HT_IRQ_LOW_DEST_ID_MASK);
-		msg.address_lo |= HT_IRQ_LOW_VECTOR(cfg->vector) |
-				  HT_IRQ_LOW_DEST_ID(cfg->dest_apicid);
-		msg.address_hi &= ~(HT_IRQ_HIGH_DEST_ID_MASK);
-		msg.address_hi |= HT_IRQ_HIGH_DEST_ID(cfg->dest_apicid);
-		write_ht_irq_msg(data->irq, &msg);
-	}
-
-	return ret;
-}
-
-static struct irq_chip ht_irq_chip = {
-	.name			= "PCI-HT",
-	.irq_mask		= mask_ht_irq,
-	.irq_unmask		= unmask_ht_irq,
-	.irq_ack		= irq_chip_ack_parent,
-	.irq_set_affinity	= ht_set_affinity,
-	.irq_retrigger		= irq_chip_retrigger_hierarchy,
-	.flags			= IRQCHIP_SKIP_SET_WAKE,
-};
-
-static int htirq_domain_alloc(struct irq_domain *domain, unsigned int virq,
-			      unsigned int nr_irqs, void *arg)
-{
-	struct ht_irq_cfg *ht_cfg;
-	struct irq_alloc_info *info = arg;
-	struct pci_dev *dev;
-	irq_hw_number_t hwirq;
-	int ret;
-
-	if (nr_irqs > 1 || !info)
-		return -EINVAL;
-
-	dev = info->ht_dev;
-	hwirq = (info->ht_idx & 0xFF) |
-		PCI_DEVID(dev->bus->number, dev->devfn) << 8 |
-		(pci_domain_nr(dev->bus) & 0xFFFFFFFF) << 24;
-	if (irq_find_mapping(domain, hwirq) > 0)
-		return -EEXIST;
-
-	ht_cfg = kmalloc(sizeof(*ht_cfg), GFP_KERNEL);
-	if (!ht_cfg)
-		return -ENOMEM;
-
-	ret = irq_domain_alloc_irqs_parent(domain, virq, nr_irqs, info);
-	if (ret < 0) {
-		kfree(ht_cfg);
-		return ret;
-	}
-
-	/* Initialize msg to a value that will never match the first write. */
-	ht_cfg->msg.address_lo = 0xffffffff;
-	ht_cfg->msg.address_hi = 0xffffffff;
-	ht_cfg->dev = info->ht_dev;
-	ht_cfg->update = info->ht_update;
-	ht_cfg->pos = info->ht_pos;
-	ht_cfg->idx = 0x10 + (info->ht_idx * 2);
-	irq_domain_set_info(domain, virq, hwirq, &ht_irq_chip, ht_cfg,
-			    handle_edge_irq, ht_cfg, "edge");
-
-	return 0;
-}
-
-static void htirq_domain_free(struct irq_domain *domain, unsigned int virq,
-			      unsigned int nr_irqs)
-{
-	struct irq_data *irq_data = irq_domain_get_irq_data(domain, virq);
-
-	BUG_ON(nr_irqs != 1);
-	kfree(irq_data->chip_data);
-	irq_domain_free_irqs_top(domain, virq, nr_irqs);
-}
-
-static int htirq_domain_activate(struct irq_domain *domain,
-				 struct irq_data *irq_data, bool early)
-{
-	struct ht_irq_msg msg;
-	struct irq_cfg *cfg = irqd_cfg(irq_data);
-
-	msg.address_hi = HT_IRQ_HIGH_DEST_ID(cfg->dest_apicid);
-	msg.address_lo =
-		HT_IRQ_LOW_BASE |
-		HT_IRQ_LOW_DEST_ID(cfg->dest_apicid) |
-		HT_IRQ_LOW_VECTOR(cfg->vector) |
-		((apic->irq_dest_mode == 0) ?
-			HT_IRQ_LOW_DM_PHYSICAL :
-			HT_IRQ_LOW_DM_LOGICAL) |
-		HT_IRQ_LOW_RQEOI_EDGE |
-		((apic->irq_delivery_mode != dest_LowestPrio) ?
-			HT_IRQ_LOW_MT_FIXED :
-			HT_IRQ_LOW_MT_ARBITRATED) |
-		HT_IRQ_LOW_IRQ_MASKED;
-	write_ht_irq_msg(irq_data->irq, &msg);
-	return 0;
-}
-
-static void htirq_domain_deactivate(struct irq_domain *domain,
-				    struct irq_data *irq_data)
-{
-	struct ht_irq_msg msg;
-
-	memset(&msg, 0, sizeof(msg));
-	write_ht_irq_msg(irq_data->irq, &msg);
-}
-
-static const struct irq_domain_ops htirq_domain_ops = {
-	.alloc		= htirq_domain_alloc,
-	.free		= htirq_domain_free,
-	.activate	= htirq_domain_activate,
-	.deactivate	= htirq_domain_deactivate,
-};
-
-void __init arch_init_htirq_domain(struct irq_domain *parent)
-{
-	struct fwnode_handle *fn;
-
-	if (disable_apic)
-		return;
-
-	fn = irq_domain_alloc_named_fwnode("PCI-HT");
-	if (!fn)
-		goto warn;
-
-	htirq_domain = irq_domain_create_tree(fn, &htirq_domain_ops, NULL);
-	irq_domain_free_fwnode(fn);
-	if (!htirq_domain)
-		goto warn;
-
-	htirq_domain->parent = parent;
-	return;
-
-warn:
-	pr_warn("Failed to initialize irqdomain for HTIRQ.\n");
-}
-
-int arch_setup_ht_irq(int idx, int pos, struct pci_dev *dev,
-		      ht_irq_update_t *update)
-{
-	struct irq_alloc_info info;
-
-	if (!htirq_domain)
-		return -ENOSYS;
-
-	init_irq_alloc_info(&info, NULL);
-	info.ht_idx = idx;
-	info.ht_pos = pos;
-	info.ht_dev = dev;
-	info.ht_update = update;
-
-	return irq_domain_alloc_irqs(htirq_domain, 1, dev_to_node(&dev->dev),
-				     &info);
-}
-
-void arch_teardown_ht_irq(unsigned int irq)
-{
-	irq_domain_free_irqs(irq, 1);
-}

arch/x86/kernel/apic/vector.c

 /*
- * Local APIC related interfaces to support IOAPIC, MSI, HT_IRQ etc.
+ * Local APIC related interfaces to support IOAPIC, MSI, etc.
  *
  * Copyright (C) 1997, 1998, 1999, 2000, 2009 Ingo Molnar, Hajnalka Szabo
  *	Moved from arch/x86/kernel/apic/io_apic.c.
@@ -601,7 +601,7 @@ int __init arch_probe_nr_irqs(void)
 		nr_irqs = NR_VECTORS * nr_cpu_ids;
 
 	nr = (gsi_top + nr_legacy_irqs()) + 8 * nr_cpu_ids;
-#if defined(CONFIG_PCI_MSI) || defined(CONFIG_HT_IRQ)
+#if defined(CONFIG_PCI_MSI)
 	/*
 	 * for MSI and HT dyn irq
 	 */
@@ -663,7 +663,6 @@ int __init arch_early_irq_init(void)
 	irq_set_default_host(x86_vector_domain);
 
 	arch_init_msi_domain(x86_vector_domain);
-	arch_init_htirq_domain(x86_vector_domain);
 
 	BUG_ON(!alloc_cpumask_var(&vector_searchmask, GFP_KERNEL));
 

arch/x86/kernel/cpu/common.c

@@ -341,6 +341,8 @@ static __always_inline void setup_umip(struct cpuinfo_x86 *c)
 
 	cr4_set_bits(X86_CR4_UMIP);
 
+	pr_info("x86/cpu: Activated the Intel User Mode Instruction Prevention (UMIP) CPU feature\n");
+
 	return;
 
 out:

arch/x86/kernel/mpparse.c

@@ -431,6 +431,7 @@ static inline void __init construct_default_ISA_mptable(int mpc_default_type)
 }
 
 static unsigned long mpf_base;
+static bool mpf_found;
 
 static unsigned long __init get_mpc_size(unsigned long physptr)
 {
@@ -504,7 +505,7 @@ void __init default_get_smp_config(unsigned int early)
 	if (!smp_found_config)
 		return;
 
-	if (!mpf_base)
+	if (!mpf_found)
 		return;
 
 	if (acpi_lapic && early)
@@ -593,6 +594,7 @@ static int __init smp_scan_config(unsigned long base, unsigned long length)
 			smp_found_config = 1;
 #endif
 			mpf_base = base;
+			mpf_found = true;
 
 			pr_info("found SMP MP-table at [mem %#010lx-%#010lx] mapped at [%p]\n",
 				base, base + sizeof(*mpf) - 1, mpf);
@@ -858,7 +860,7 @@ static int __init update_mp_table(void)
 	if (!enable_update_mptable)
 		return 0;
 
-	if (!mpf_base)
+	if (!mpf_found)
 		return 0;
 
 	mpf = early_memremap(mpf_base, sizeof(*mpf));

arch/x86/kernel/smpboot.c

@@ -101,9 +101,6 @@ DEFINE_PER_CPU_READ_MOSTLY(struct cpuinfo_x86, cpu_info);
 EXPORT_PER_CPU_SYMBOL(cpu_info);
 
 /* Logical package management. We might want to allocate that dynamically */
-static int *physical_to_logical_pkg __read_mostly;
-static unsigned long *physical_package_map __read_mostly;;
-static unsigned int max_physical_pkg_id __read_mostly;
 unsigned int __max_logical_packages __read_mostly;
 EXPORT_SYMBOL(__max_logical_packages);
 static unsigned int logical_packages __read_mostly;
@@ -280,6 +277,25 @@ static void notrace start_secondary(void *unused)
 	cpu_startup_entry(CPUHP_AP_ONLINE_IDLE);
 }
 
+/**
+ * topology_phys_to_logical_pkg - Map a physical package id to a logical
+ *
+ * Returns logical package id or -1 if not found
+ */
+int topology_phys_to_logical_pkg(unsigned int phys_pkg)
+{
+	int cpu;
+
+	for_each_possible_cpu(cpu) {
+		struct cpuinfo_x86 *c = &cpu_data(cpu);
+
+		if (c->initialized && c->phys_proc_id == phys_pkg)
+			return c->logical_proc_id;
+	}
+	return -1;
+}
+EXPORT_SYMBOL(topology_phys_to_logical_pkg);
+
 /**
  * topology_update_package_map - Update the physical to logical package map
  * @pkg:	The physical package id as retrieved via CPUID
@@ -287,102 +303,23 @@ static void notrace start_secondary(void *unused)
  */
 int topology_update_package_map(unsigned int pkg, unsigned int cpu)
 {
-	unsigned int new;
-
-	/* Called from early boot ? */
-	if (!physical_package_map)
-		return 0;
-
-	if (pkg >= max_physical_pkg_id)
-		return -EINVAL;
+	int new;
 
-	/* Set the logical package id */
-	if (test_and_set_bit(pkg, physical_package_map))
+	/* Already available somewhere? */
+	new = topology_phys_to_logical_pkg(pkg);
+	if (new >= 0)
 		goto found;
 
-	if (logical_packages >= __max_logical_packages) {
-		pr_warn("Package %u of CPU %u exceeds BIOS package data %u.\n",
-			logical_packages, cpu, __max_logical_packages);
-		return -ENOSPC;
-	}
-
 	new = logical_packages++;
 	if (new != pkg) {
 		pr_info("CPU %u Converting physical %u to logical package %u\n",
 			cpu, pkg, new);
 	}
-	physical_to_logical_pkg[pkg] = new;
-
 found:
-	cpu_data(cpu).logical_proc_id = physical_to_logical_pkg[pkg];
+	cpu_data(cpu).logical_proc_id = new;
 	return 0;
 }
 
-/**
- * topology_phys_to_logical_pkg - Map a physical package id to a logical
- *
- * Returns logical package id or -1 if not found
- */
-int topology_phys_to_logical_pkg(unsigned int phys_pkg)
-{
-	if (phys_pkg >= max_physical_pkg_id)
-		return -1;
-	return physical_to_logical_pkg[phys_pkg];
-}
-EXPORT_SYMBOL(topology_phys_to_logical_pkg);
-
-static void __init smp_init_package_map(struct cpuinfo_x86 *c, unsigned int cpu)
-{
-	unsigned int ncpus;
-	size_t size;
-
-	/*
-	 * Today neither Intel nor AMD support heterogenous systems. That
-	 * might change in the future....
-	 *
-	 * While ideally we'd want '* smp_num_siblings' in the below @ncpus
-	 * computation, this won't actually work since some Intel BIOSes
-	 * report inconsistent HT data when they disable HT.
-	 *
-	 * In particular, they reduce the APIC-IDs to only include the cores,
-	 * but leave the CPUID topology to say there are (2) siblings.
-	 * This means we don't know how many threads there will be until
-	 * after the APIC enumeration.
-	 *
-	 * By not including this we'll sometimes over-estimate the number of
-	 * logical packages by the amount of !present siblings, but this is
-	 * still better than MAX_LOCAL_APIC.
-	 *
-	 * We use total_cpus not nr_cpu_ids because nr_cpu_ids can be limited
-	 * on the command line leading to a similar issue as the HT disable
-	 * problem because the hyperthreads are usually enumerated after the
-	 * primary cores.
-	 */
-	ncpus = boot_cpu_data.x86_max_cores;
-	if (!ncpus) {
-		pr_warn("x86_max_cores == zero !?!?");
-		ncpus = 1;
-	}
-
-	__max_logical_packages = DIV_ROUND_UP(total_cpus, ncpus);
-	logical_packages = 0;
-
-	/*
-	 * Possibly larger than what we need as the number of apic ids per
-	 * package can be smaller than the actual used apic ids.
-	 */
-	max_physical_pkg_id = DIV_ROUND_UP(MAX_LOCAL_APIC, ncpus);
-	size = max_physical_pkg_id * sizeof(unsigned int);
-	physical_to_logical_pkg = kmalloc(size, GFP_KERNEL);
-	memset(physical_to_logical_pkg, 0xff, size);
-	size = BITS_TO_LONGS(max_physical_pkg_id) * sizeof(unsigned long);
-	physical_package_map = kzalloc(size, GFP_KERNEL);
-
-	pr_info("Max logical packages: %u\n", __max_logical_packages);
-
-	topology_update_package_map(c->phys_proc_id, cpu);
-}
-
 void __init smp_store_boot_cpu_info(void)
 {
 	int id = 0; /* CPU 0 */
@@ -390,7 +327,8 @@ void __init smp_store_boot_cpu_info(void)
 
 	*c = boot_cpu_data;
 	c->cpu_index = id;
-	smp_init_package_map(c, id);
+	topology_update_package_map(c->phys_proc_id, id);
+	c->initialized = true;
 }
 
 /*
@@ -401,6 +339,8 @@ void smp_store_cpu_info(int id)
 {
 	struct cpuinfo_x86 *c = &cpu_data(id);
 
+	/* Copy boot_cpu_data only on the first bringup */
+	if (!c->initialized)
 		*c = boot_cpu_data;
 	c->cpu_index = id;
 	/*
@@ -408,6 +348,7 @@ void smp_store_cpu_info(int id)
 	 * bringing up AP or offlined CPU0.
 	 */
 	identify_secondary_cpu(c);
+	c->initialized = true;
 }
 
 static bool
@@ -1356,7 +1297,16 @@ void __init native_smp_prepare_boot_cpu(void)
 
 void __init native_smp_cpus_done(unsigned int max_cpus)
 {
+	int ncpus;
+
 	pr_debug("Boot done\n");
+	/*
+	 * Today neither Intel nor AMD support heterogenous systems so
+	 * extrapolate the boot cpu's data to all packages.
+	 */
+	ncpus = cpu_data(0).booted_cores * smp_num_siblings;
+	__max_logical_packages = DIV_ROUND_UP(nr_cpu_ids, ncpus);
+	pr_info("Max logical packages: %u\n", __max_logical_packages);
 
 	if (x86_has_numa_in_package)
 		set_sched_topology(x86_numa_in_package_topology);

arch/x86/kernel/sys_x86_64.c

@@ -188,6 +188,7 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
 	if (len > TASK_SIZE)
 		return -ENOMEM;
 
+	/* No address checking. See comment at mmap_address_hint_valid() */
 	if (flags & MAP_FIXED)
 		return addr;
 
@@ -197,12 +198,15 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0,
 
 	/* requesting a specific address */
 	if (addr) {
-		addr = PAGE_ALIGN(addr);
+		addr &= PAGE_MASK;
+		if (!mmap_address_hint_valid(addr, len))
+			goto get_unmapped_area;
+
 		vma = find_vma(mm, addr);
-		if (TASK_SIZE - len >= addr &&
-				(!vma || addr + len <= vm_start_gap(vma)))
+		if (!vma || addr + len <= vm_start_gap(vma))
 			return addr;
 	}
+get_unmapped_area:
 
 	info.flags = VM_UNMAPPED_AREA_TOPDOWN;
 	info.length = len;

arch/x86/kernel/umip.c

@@ -78,7 +78,60 @@
 
 #define	UMIP_INST_SGDT	0	/* 0F 01 /0 */
 #define	UMIP_INST_SIDT	1	/* 0F 01 /1 */
-#define	UMIP_INST_SMSW	3	/* 0F 01 /4 */
+#define	UMIP_INST_SMSW	2	/* 0F 01 /4 */
+#define	UMIP_INST_SLDT  3       /* 0F 00 /0 */
+#define	UMIP_INST_STR   4       /* 0F 00 /1 */
+
+const char * const umip_insns[5] = {
+	[UMIP_INST_SGDT] = "SGDT",
+	[UMIP_INST_SIDT] = "SIDT",
+	[UMIP_INST_SMSW] = "SMSW",
+	[UMIP_INST_SLDT] = "SLDT",
+	[UMIP_INST_STR] = "STR",
+};
+
+#define umip_pr_err(regs, fmt, ...) \
+	umip_printk(regs, KERN_ERR, fmt, ##__VA_ARGS__)
+#define umip_pr_warning(regs, fmt, ...) \
+	umip_printk(regs, KERN_WARNING, fmt,  ##__VA_ARGS__)
+
+/**
+ * umip_printk() - Print a rate-limited message
+ * @regs:	Register set with the context in which the warning is printed
+ * @log_level:	Kernel log level to print the message
+ * @fmt:	The text string to print
+ *
+ * Print the text contained in @fmt. The print rate is limited to bursts of 5
+ * messages every two minutes. The purpose of this customized version of
+ * printk() is to print messages when user space processes use any of the
+ * UMIP-protected instructions. Thus, the printed text is prepended with the
+ * task name and process ID number of the current task as well as the
+ * instruction and stack pointers in @regs as seen when entering kernel mode.
+ *
+ * Returns:
+ *
+ * None.
+ */
+static __printf(3, 4)
+void umip_printk(const struct pt_regs *regs, const char *log_level,
+		 const char *fmt, ...)
+{
+	/* Bursts of 5 messages every two minutes */
+	static DEFINE_RATELIMIT_STATE(ratelimit, 2 * 60 * HZ, 5);
+	struct task_struct *tsk = current;
+	struct va_format vaf;
+	va_list args;
+
+	if (!__ratelimit(&ratelimit))
+		return;
+
+	va_start(args, fmt);
+	vaf.fmt = fmt;
+	vaf.va = &args;
+	printk("%s" pr_fmt("%s[%d] ip:%lx sp:%lx: %pV"), log_level, tsk->comm,
+	       task_pid_nr(tsk), regs->ip, regs->sp, &vaf);
+	va_end(args);
+}
 
 /**
  * identify_insn() - Identify a UMIP-protected instruction
@@ -118,10 +171,16 @@ static int identify_insn(struct insn *insn)
 		default:
 			return -EINVAL;
 		}
-	}
-
-	/* SLDT AND STR are not emulated */
+	} else if (insn->opcode.bytes[1] == 0x0) {
+		if (X86_MODRM_REG(insn->modrm.value) == 0)
+			return UMIP_INST_SLDT;
+		else if (X86_MODRM_REG(insn->modrm.value) == 1)
+			return UMIP_INST_STR;
+		else
 			return -EINVAL;
+	} else {
+		return -EINVAL;
+	}
 }
 
 /**
@@ -228,10 +287,8 @@ static void force_sig_info_umip_fault(void __user *addr, struct pt_regs *regs)
 	if (!(show_unhandled_signals && unhandled_signal(tsk, SIGSEGV)))
 		return;
 
-	pr_err_ratelimited("%s[%d] umip emulation segfault ip:%lx sp:%lx error:%x in %lx\n",
-			   tsk->comm, task_pid_nr(tsk), regs->ip,
-			   regs->sp, X86_PF_USER | X86_PF_WRITE,
-			   regs->ip);
+	umip_pr_err(regs, "segfault in emulation. error%x\n",
+		    X86_PF_USER | X86_PF_WRITE);
 }
 
 /**
@@ -262,15 +319,11 @@ bool fixup_umip_exception(struct pt_regs *regs)
 	unsigned char buf[MAX_INSN_SIZE];
 	void __user *uaddr;
 	struct insn insn;
-	char seg_defs;
+	int seg_defs;
 
 	if (!regs)
 		return false;
 
-	/* Do not emulate 64-bit processes. */
-	if (user_64bit_mode(regs))
-		return false;
-
 	/*
 	 * If not in user-space long mode, a custom code segment could be in
 	 * use. This is true in protected mode (if the process defined a local
@@ -322,6 +375,15 @@ bool fixup_umip_exception(struct pt_regs *regs)
 	if (umip_inst < 0)
 		return false;
 
+	umip_pr_warning(regs, "%s instruction cannot be used by applications.\n",
+			umip_insns[umip_inst]);
+
+	/* Do not emulate SLDT, STR or user long mode processes. */
+	if (umip_inst == UMIP_INST_STR || umip_inst == UMIP_INST_SLDT || user_64bit_mode(regs))
+		return false;
+
+	umip_pr_warning(regs, "For now, expensive software emulation returns the result.\n");
+
 	if (emulate_umip_insn(&insn, umip_inst, dummy_data, &dummy_data_size))
 		return false;
 

arch/x86/lib/insn-eval.c

@@ -733,11 +733,11 @@ static unsigned long get_seg_limit(struct pt_regs *regs, int seg_reg_idx)
  *
  * Returns:
  *
- * A signed 8-bit value containing the default parameters on success.
+ * An int containing ORed-in default parameters on success.
  *
  * -EINVAL on error.
  */
-char insn_get_code_seg_params(struct pt_regs *regs)
+int insn_get_code_seg_params(struct pt_regs *regs)
 {
 	struct desc_struct *desc;
 	short sel;

arch/x86/lib/x86-opcode-map.txt

@@ -896,7 +896,7 @@ EndTable
 
 GrpTable: Grp3_1
 0: TEST Eb,Ib
-1:
+1: TEST Eb,Ib
 2: NOT Eb
 3: NEG Eb
 4: MUL AL,Eb

arch/x86/mm/hugetlbpage.c

@@ -158,6 +158,7 @@ hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
 	if (len > TASK_SIZE)
 		return -ENOMEM;
 
+	/* No address checking. See comment at mmap_address_hint_valid() */
 	if (flags & MAP_FIXED) {
 		if (prepare_hugepage_range(file, addr, len))
 			return -EINVAL;
@@ -165,12 +166,16 @@ hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
 	}
 
 	if (addr) {
-		addr = ALIGN(addr, huge_page_size(h));
+		addr &= huge_page_mask(h);
+		if (!mmap_address_hint_valid(addr, len))
+			goto get_unmapped_area;
+
 		vma = find_vma(mm, addr);
-		if (TASK_SIZE - len >= addr &&
-		    (!vma || addr + len <= vm_start_gap(vma)))
+		if (!vma || addr + len <= vm_start_gap(vma))
 			return addr;
 	}
+
+get_unmapped_area:
 	if (mm->get_unmapped_area == arch_get_unmapped_area)
 		return hugetlb_get_unmapped_area_bottomup(file, addr, len,
 				pgoff, flags);

arch/x86/mm/mmap.c

@@ -33,6 +33,8 @@
 #include <linux/compat.h>
 #include <asm/elf.h>
 
+#include "physaddr.h"
+
 struct va_alignment __read_mostly va_align = {
 	.flags = -1,
 };
@@ -174,3 +176,63 @@ const char *arch_vma_name(struct vm_area_struct *vma)
 		return "[mpx]";
 	return NULL;
 }
+
+/**
+ * mmap_address_hint_valid - Validate the address hint of mmap
+ * @addr:	Address hint
+ * @len:	Mapping length
+ *
+ * Check whether @addr and @addr + @len result in a valid mapping.
+ *
+ * On 32bit this only checks whether @addr + @len is <= TASK_SIZE.
+ *
+ * On 64bit with 5-level page tables another sanity check is required
+ * because mappings requested by mmap(@addr, 0) which cross the 47-bit
+ * virtual address boundary can cause the following theoretical issue:
+ *
+ *  An application calls mmap(addr, 0), i.e. without MAP_FIXED, where @addr
+ *  is below the border of the 47-bit address space and @addr + @len is
+ *  above the border.
+ *
+ *  With 4-level paging this request succeeds, but the resulting mapping
+ *  address will always be within the 47-bit virtual address space, because
+ *  the hint address does not result in a valid mapping and is
+ *  ignored. Hence applications which are not prepared to handle virtual
+ *  addresses above 47-bit work correctly.
+ *
+ *  With 5-level paging this request would be granted and result in a
+ *  mapping which crosses the border of the 47-bit virtual address
+ *  space. If the application cannot handle addresses above 47-bit this
+ *  will lead to misbehaviour and hard to diagnose failures.
+ *
+ * Therefore ignore address hints which would result in a mapping crossing
+ * the 47-bit virtual address boundary.
+ *
+ * Note, that in the same scenario with MAP_FIXED the behaviour is
+ * different. The request with @addr < 47-bit and @addr + @len > 47-bit
+ * fails on a 4-level paging machine but succeeds on a 5-level paging
+ * machine. It is reasonable to expect that an application does not rely on
+ * the failure of such a fixed mapping request, so the restriction is not
+ * applied.
+ */
+bool mmap_address_hint_valid(unsigned long addr, unsigned long len)
+{
+	if (TASK_SIZE - len < addr)
+		return false;
+
+	return (addr > DEFAULT_MAP_WINDOW) == (addr + len > DEFAULT_MAP_WINDOW);
+}
+
+/* Can we access it for direct reading/writing? Must be RAM: */
+int valid_phys_addr_range(phys_addr_t addr, size_t count)
+{
+	return addr + count <= __pa(high_memory);
+}
+
+/* Can we access it through mmap? Must be a valid physical address: */
+int valid_mmap_phys_addr_range(unsigned long pfn, size_t count)
+{
+	phys_addr_t addr = (phys_addr_t)pfn << PAGE_SHIFT;
+
+	return phys_addr_valid(addr + count - 1);
+}

drivers/char/mem.c

@@ -343,6 +343,10 @@ static int mmap_mem(struct file *file, struct vm_area_struct *vma)
 	size_t size = vma->vm_end - vma->vm_start;
 	phys_addr_t offset = (phys_addr_t)vma->vm_pgoff << PAGE_SHIFT;
 
+	/* Does it even fit in phys_addr_t? */
+	if (offset >> PAGE_SHIFT != vma->vm_pgoff)
+		return -EINVAL;
+
 	/* It's illegal to wrap around the end of the physical address space. */
 	if (offset + (phys_addr_t)size - 1 < offset)
 		return -EINVAL;

drivers/pci/Kconfig

@@ -80,15 +80,6 @@ config XEN_PCIDEV_FRONTEND
           The PCI device frontend driver allows the kernel to import arbitrary
           PCI devices from a PCI backend to support PCI driver domains.
 
-config HT_IRQ
-	bool "Interrupts on hypertransport devices"
-	default y
-	depends on PCI && X86_LOCAL_APIC
-	help
-	   This allows native hypertransport devices to use interrupts.
-
-	   If unsure say Y.
-
 config PCI_ATS
 	bool
 

drivers/pci/Makefile

@@ -21,9 +21,6 @@ obj-$(CONFIG_HOTPLUG_PCI) += hotplug/
 # Build the PCI MSI interrupt support
 obj-$(CONFIG_PCI_MSI) += msi.o
 
-# Build the Hypertransport interrupt support
-obj-$(CONFIG_HT_IRQ) += htirq.o
-
 obj-$(CONFIG_PCI_ATS) += ats.o
 obj-$(CONFIG_PCI_IOV) += iov.o
 

drivers/pci/htirq.c

-// SPDX-License-Identifier: GPL-2.0
-/*
- * File:	htirq.c
- * Purpose:	Hypertransport Interrupt Capability
- *
- * Copyright (C) 2006 Linux Networx
- * Copyright (C) Eric Biederman <ebiederman@lnxi.com>
- */
-
-#include <linux/irq.h>
-#include <linux/pci.h>
-#include <linux/spinlock.h>
-#include <linux/export.h>
-#include <linux/slab.h>
-#include <linux/htirq.h>
-
-/* Global ht irq lock.
- *
- * This is needed to serialize access to the data port in hypertransport
- * irq capability.
- *
- * With multiple simultaneous hypertransport irq devices it might pay
- * to make this more fine grained.  But start with simple, stupid, and correct.
- */
-static DEFINE_SPINLOCK(ht_irq_lock);
-
-void write_ht_irq_msg(unsigned int irq, struct ht_irq_msg *msg)
-{
-	struct ht_irq_cfg *cfg = irq_get_handler_data(irq);
-	unsigned long flags;
-
-	spin_lock_irqsave(&ht_irq_lock, flags);
-	if (cfg->msg.address_lo != msg->address_lo) {
-		pci_write_config_byte(cfg->dev, cfg->pos + 2, cfg->idx);
-		pci_write_config_dword(cfg->dev, cfg->pos + 4, msg->address_lo);
-	}
-	if (cfg->msg.address_hi != msg->address_hi) {
-		pci_write_config_byte(cfg->dev, cfg->pos + 2, cfg->idx + 1);
-		pci_write_config_dword(cfg->dev, cfg->pos + 4, msg->address_hi);
-	}
-	if (cfg->update)
-		cfg->update(cfg->dev, irq, msg);
-	spin_unlock_irqrestore(&ht_irq_lock, flags);
-	cfg->msg = *msg;
-}
-
-void fetch_ht_irq_msg(unsigned int irq, struct ht_irq_msg *msg)
-{
-	struct ht_irq_cfg *cfg = irq_get_handler_data(irq);
-
-	*msg = cfg->msg;
-}
-
-void mask_ht_irq(struct irq_data *data)
-{
-	struct ht_irq_cfg *cfg = irq_data_get_irq_handler_data(data);
-	struct ht_irq_msg msg = cfg->msg;
-
-	msg.address_lo |= 1;
-	write_ht_irq_msg(data->irq, &msg);
-}
-
-void unmask_ht_irq(struct irq_data *data)
-{
-	struct ht_irq_cfg *cfg = irq_data_get_irq_handler_data(data);
-	struct ht_irq_msg msg = cfg->msg;
-
-	msg.address_lo &= ~1;
-	write_ht_irq_msg(data->irq, &msg);
-}
-
-/**
- * __ht_create_irq - create an irq and attach it to a device.
- * @dev: The hypertransport device to find the irq capability on.
- * @idx: Which of the possible irqs to attach to.
- * @update: Function to be called when changing the htirq message
- *
- * The irq number of the new irq or a negative error value is returned.
- */
-int __ht_create_irq(struct pci_dev *dev, int idx, ht_irq_update_t *update)
-{
-	int max_irq, pos, irq;
-	unsigned long flags;
-	u32 data;
-
-	pos = pci_find_ht_capability(dev, HT_CAPTYPE_IRQ);
-	if (!pos)
-		return -EINVAL;
-
-	/* Verify the idx I want to use is in range */
-	spin_lock_irqsave(&ht_irq_lock, flags);
-	pci_write_config_byte(dev, pos + 2, 1);
-	pci_read_config_dword(dev, pos + 4, &data);
-	spin_unlock_irqrestore(&ht_irq_lock, flags);
-
-	max_irq = (data >> 16) & 0xff;
-	if (idx > max_irq)
-		return -EINVAL;
-
-	irq = arch_setup_ht_irq(idx, pos, dev, update);
-	if (irq > 0)
-		dev_dbg(&dev->dev, "irq %d for HT\n", irq);
-
-	return irq;
-}
-EXPORT_SYMBOL(__ht_create_irq);
-
-/**
- * ht_create_irq - create an irq and attach it to a device.
- * @dev: The hypertransport device to find the irq capability on.
- * @idx: Which of the possible irqs to attach to.
- *
- * ht_create_irq needs to be called for all hypertransport devices
- * that generate irqs.
- *
- * The irq number of the new irq or a negative error value is returned.
- */
-int ht_create_irq(struct pci_dev *dev, int idx)
-{
-	return __ht_create_irq(dev, idx, NULL);
-}
-EXPORT_SYMBOL(ht_create_irq);
-
-/**
- * ht_destroy_irq - destroy an irq created with ht_create_irq
- * @irq: irq to be destroyed
- *
- * This reverses ht_create_irq removing the specified irq from
- * existence.  The irq should be free before this happens.
- */
-void ht_destroy_irq(unsigned int irq)
-{
-	arch_teardown_ht_irq(irq);
-}
-EXPORT_SYMBOL(ht_destroy_irq);

include/linux/htirq.h

-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef LINUX_HTIRQ_H
-#define LINUX_HTIRQ_H
-
-struct pci_dev;
-struct irq_data;
-
-struct ht_irq_msg {
-	u32	address_lo;	/* low 32 bits of the ht irq message */
-	u32	address_hi;	/* high 32 bits of the it irq message */
-};
-
-typedef void (ht_irq_update_t)(struct pci_dev *dev, int irq,
-			       struct ht_irq_msg *msg);
-
-struct ht_irq_cfg {
-	struct pci_dev *dev;
-	 /* Update callback used to cope with buggy hardware */
-	ht_irq_update_t *update;
-	unsigned pos;
-	unsigned idx;
-	struct ht_irq_msg msg;
-};
-
-/* Helper functions.. */
-void fetch_ht_irq_msg(unsigned int irq, struct ht_irq_msg *msg);
-void write_ht_irq_msg(unsigned int irq, struct ht_irq_msg *msg);
-void mask_ht_irq(struct irq_data *data);
-void unmask_ht_irq(struct irq_data *data);
-
-/* The arch hook for getting things started */
-int arch_setup_ht_irq(int idx, int pos, struct pci_dev *dev,
-		      ht_irq_update_t *update);
-void arch_teardown_ht_irq(unsigned int irq);
-
-/* For drivers of buggy hardware */
-int __ht_create_irq(struct pci_dev *dev, int idx, ht_irq_update_t *update);
-
-#endif /* LINUX_HTIRQ_H */

include/linux/pci.h

@@ -1485,12 +1485,6 @@ static inline void pcie_set_ecrc_checking(struct pci_dev *dev) { }
 static inline void pcie_ecrc_get_policy(char *str) { }
 #endif
 
-#ifdef CONFIG_HT_IRQ
-/* The functions a driver should call */
-int  ht_create_irq(struct pci_dev *dev, int idx);
-void ht_destroy_irq(unsigned int irq);
-#endif /* CONFIG_HT_IRQ */
-
 #ifdef CONFIG_PCI_ATS
 /* Address Translation Service */
 void pci_ats_init(struct pci_dev *dev);

tools/testing/selftests/x86/5lvl.c

+#include <stdio.h>
+#include <sys/mman.h>
+
+#define ARRAY_SIZE(arr) (sizeof(arr) / sizeof((arr)[0]))
+
+#define PAGE_SIZE	4096
+#define LOW_ADDR	((void *) (1UL << 30))
+#define HIGH_ADDR	((void *) (1UL << 50))
+
+struct testcase {
+	void *addr;
+	unsigned long size;
+	unsigned long flags;
+	const char *msg;
+	unsigned int low_addr_required:1;
+	unsigned int keep_mapped:1;
+};
+
+static struct testcase testcases[] = {
+	{
+		.addr = NULL,
+		.size = 2 * PAGE_SIZE,
+		.flags = MAP_PRIVATE | MAP_ANONYMOUS,
+		.msg = "mmap(NULL)",
+		.low_addr_required = 1,
+	},
+	{
+		.addr = LOW_ADDR,
+		.size = 2 * PAGE_SIZE,
+		.flags = MAP_PRIVATE | MAP_ANONYMOUS,
+		.msg = "mmap(LOW_ADDR)",
+		.low_addr_required = 1,
+	},
+	{
+		.addr = HIGH_ADDR,
+		.size = 2 * PAGE_SIZE,
+		.flags = MAP_PRIVATE | MAP_ANONYMOUS,
+		.msg = "mmap(HIGH_ADDR)",
+		.keep_mapped = 1,
+	},
+	{
+		.addr = HIGH_ADDR,
+		.size = 2 * PAGE_SIZE,
+		.flags = MAP_PRIVATE | MAP_ANONYMOUS,
+		.msg = "mmap(HIGH_ADDR) again",
+		.keep_mapped = 1,
+	},
+	{
+		.addr = HIGH_ADDR,
+		.size = 2 * PAGE_SIZE,
+		.flags = MAP_PRIVATE | MAP_ANONYMOUS | MAP_FIXED,
+		.msg = "mmap(HIGH_ADDR, MAP_FIXED)",
+	},
+	{
+		.addr = (void*) -1,
+		.size = 2 * PAGE_SIZE,
+		.flags = MAP_PRIVATE | MAP_ANONYMOUS,
+		.msg = "mmap(-1)",
+		.keep_mapped = 1,
+	},
+	{
+		.addr = (void*) -1,
+		.size = 2 * PAGE_SIZE,
+		.flags = MAP_PRIVATE | MAP_ANONYMOUS,
+		.msg = "mmap(-1) again",
+	},
+	{
+		.addr = (void *)((1UL << 47) - PAGE_SIZE),
+		.size = 2 * PAGE_SIZE,
+		.flags = MAP_PRIVATE | MAP_ANONYMOUS,
+		.msg = "mmap((1UL << 47), 2 * PAGE_SIZE)",
+		.low_addr_required = 1,
+		.keep_mapped = 1,
+	},
+	{
+		.addr = (void *)((1UL << 47) - PAGE_SIZE / 2),
+		.size = 2 * PAGE_SIZE,
+		.flags = MAP_PRIVATE | MAP_ANONYMOUS,
+		.msg = "mmap((1UL << 47), 2 * PAGE_SIZE / 2)",
+		.low_addr_required = 1,
+		.keep_mapped = 1,
+	},
+	{
+		.addr = (void *)((1UL << 47) - PAGE_SIZE),
+		.size = 2 * PAGE_SIZE,
+		.flags = MAP_PRIVATE | MAP_ANONYMOUS | MAP_FIXED,
+		.msg = "mmap((1UL << 47) - PAGE_SIZE, 2 * PAGE_SIZE, MAP_FIXED)",
+	},
+	{
+		.addr = NULL,
+		.size = 2UL << 20,
+		.flags = MAP_HUGETLB | MAP_PRIVATE | MAP_ANONYMOUS,
+		.msg = "mmap(NULL, MAP_HUGETLB)",
+		.low_addr_required = 1,
+	},
+	{
+		.addr = LOW_ADDR,
+		.size = 2UL << 20,
+		.flags = MAP_HUGETLB | MAP_PRIVATE | MAP_ANONYMOUS,
+		.msg = "mmap(LOW_ADDR, MAP_HUGETLB)",
+		.low_addr_required = 1,
+	},
+	{
+		.addr = HIGH_ADDR,
+		.size = 2UL << 20,
+		.flags = MAP_HUGETLB | MAP_PRIVATE | MAP_ANONYMOUS,
+		.msg = "mmap(HIGH_ADDR, MAP_HUGETLB)",
+		.keep_mapped = 1,
+	},
+	{
+		.addr = HIGH_ADDR,
+		.size = 2UL << 20,
+		.flags = MAP_HUGETLB | MAP_PRIVATE | MAP_ANONYMOUS,
+		.msg = "mmap(HIGH_ADDR, MAP_HUGETLB) again",
+		.keep_mapped = 1,
+	},
+	{
+		.addr = HIGH_ADDR,
+		.size = 2UL << 20,
+		.flags = MAP_HUGETLB | MAP_PRIVATE | MAP_ANONYMOUS | MAP_FIXED,
+		.msg = "mmap(HIGH_ADDR, MAP_FIXED | MAP_HUGETLB)",
+	},
+	{
+		.addr = (void*) -1,
+		.size = 2UL << 20,
+		.flags = MAP_HUGETLB | MAP_PRIVATE | MAP_ANONYMOUS,
+		.msg = "mmap(-1, MAP_HUGETLB)",
+		.keep_mapped = 1,
+	},
+	{
+		.addr = (void*) -1,
+		.size = 2UL << 20,
+		.flags = MAP_HUGETLB | MAP_PRIVATE | MAP_ANONYMOUS,
+		.msg = "mmap(-1, MAP_HUGETLB) again",
+	},
+	{
+		.addr = (void *)((1UL << 47) - PAGE_SIZE),
+		.size = 4UL << 20,
+		.flags = MAP_HUGETLB | MAP_PRIVATE | MAP_ANONYMOUS,
+		.msg = "mmap((1UL << 47), 4UL << 20, MAP_HUGETLB)",
+		.low_addr_required = 1,
+		.keep_mapped = 1,
+	},
+	{
+		.addr = (void *)((1UL << 47) - (2UL << 20)),
+		.size = 4UL << 20,
+		.flags = MAP_HUGETLB | MAP_PRIVATE | MAP_ANONYMOUS | MAP_FIXED,
+		.msg = "mmap((1UL << 47) - (2UL << 20), 4UL << 20, MAP_FIXED | MAP_HUGETLB)",
+	},
+};
+
+int main(int argc, char **argv)
+{
+	int i;
+	void *p;
+
+	for (i = 0; i < ARRAY_SIZE(testcases); i++) {
+		struct testcase *t = testcases + i;
+
+		p = mmap(t->addr, t->size, PROT_NONE, t->flags, -1, 0);
+
+		printf("%s: %p - ", t->msg, p);
+
+		if (p == MAP_FAILED) {
+			printf("FAILED\n");
+			continue;
+		}
+
+		if (t->low_addr_required && p >= (void *)(1UL << 47))
+			printf("FAILED\n");
+		else
+			printf("OK\n");
+		if (!t->keep_mapped)
+			munmap(p, t->size);
+	}
+	return 0;
+}

tools/testing/selftests/x86/Makefile

@@ -11,7 +11,7 @@ TARGETS_C_BOTHBITS := single_step_syscall sysret_ss_attrs syscall_nt ptrace_sysc
 TARGETS_C_32BIT_ONLY := entry_from_vm86 syscall_arg_fault test_syscall_vdso unwind_vdso \
 			test_FCMOV test_FCOMI test_FISTTP \
 			vdso_restorer
-TARGETS_C_64BIT_ONLY := fsgsbase sysret_rip
+TARGETS_C_64BIT_ONLY := fsgsbase sysret_rip 5lvl
 
 TARGETS_C_32BIT_ALL := $(TARGETS_C_BOTHBITS) $(TARGETS_C_32BIT_ONLY)
 TARGETS_C_64BIT_ALL := $(TARGETS_C_BOTHBITS) $(TARGETS_C_64BIT_ONLY)

tools/testing/selftests/x86/mpx-hw.h

@@ -52,14 +52,14 @@
 struct mpx_bd_entry {
 	union {
 		char x[MPX_BOUNDS_DIR_ENTRY_SIZE_BYTES];
-		void *contents[1];
+		void *contents[0];
 	};
 } __attribute__((packed));
 
 struct mpx_bt_entry {
 	union {
 		char x[MPX_BOUNDS_TABLE_ENTRY_SIZE_BYTES];
-		unsigned long contents[1];
+		unsigned long contents[0];
 	};
 } __attribute__((packed));
 

tools/testing/selftests/x86/pkey-helpers.h

@@ -30,6 +30,7 @@ static inline void sigsafe_printf(const char *format, ...)
 	if (!dprint_in_signal) {
 		vprintf(format, ap);
 	} else {
+		int ret;
 		int len = vsnprintf(dprint_in_signal_buffer,
 				    DPRINT_IN_SIGNAL_BUF_SIZE,
 				    format, ap);
@@ -39,7 +40,9 @@ static inline void sigsafe_printf(const char *format, ...)
 		 */
 		if (len > DPRINT_IN_SIGNAL_BUF_SIZE)
 			len = DPRINT_IN_SIGNAL_BUF_SIZE;
-		write(1, dprint_in_signal_buffer, len);
+		ret = write(1, dprint_in_signal_buffer, len);
+		if (ret < 0)
+			abort();
 	}
 	va_end(ap);
 }

tools/testing/selftests/x86/protection_keys.c

@@ -250,7 +250,7 @@ void signal_handler(int signum, siginfo_t *si, void *vucontext)
 	unsigned long ip;
 	char *fpregs;
 	u32 *pkru_ptr;
-	u64 si_pkey;
+	u64 siginfo_pkey;
 	u32 *si_pkey_ptr;
 	int pkru_offset;
 	fpregset_t fpregset;
@@ -292,9 +292,9 @@ void signal_handler(int signum, siginfo_t *si, void *vucontext)
 	si_pkey_ptr = (u32 *)(((u8 *)si) + si_pkey_offset);
 	dprintf1("si_pkey_ptr: %p\n", si_pkey_ptr);
 	dump_mem(si_pkey_ptr - 8, 24);
-	si_pkey = *si_pkey_ptr;
-	pkey_assert(si_pkey < NR_PKEYS);
-	last_si_pkey = si_pkey;
+	siginfo_pkey = *si_pkey_ptr;
+	pkey_assert(siginfo_pkey < NR_PKEYS);
+	last_si_pkey = siginfo_pkey;
 
 	if ((si->si_code == SEGV_MAPERR) ||
 	    (si->si_code == SEGV_ACCERR) ||
@@ -306,7 +306,7 @@ void signal_handler(int signum, siginfo_t *si, void *vucontext)
 	dprintf1("signal pkru from xsave: %08x\n", *pkru_ptr);
 	/* need __rdpkru() version so we do not do shadow_pkru checking */
 	dprintf1("signal pkru from  pkru: %08x\n", __rdpkru());
-	dprintf1("si_pkey from siginfo: %jx\n", si_pkey);
+	dprintf1("pkey from siginfo: %jx\n", siginfo_pkey);
 	*(u64 *)pkru_ptr = 0x00000000;
 	dprintf1("WARNING: set PRKU=0 to allow faulting instruction to continue\n");
 	pkru_faults++;