diff options
Diffstat (limited to 'arch/x86')
95 files changed, 1953 insertions, 1157 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 956c770..b660088 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -26,7 +26,7 @@ config X86 select ARCH_MIGHT_HAVE_PC_SERIO select HAVE_AOUT if X86_32 select HAVE_UNSTABLE_SCHED_CLOCK - select ARCH_SUPPORTS_NUMA_BALANCING + select ARCH_SUPPORTS_NUMA_BALANCING if X86_64 select ARCH_SUPPORTS_INT128 if X86_64 select ARCH_WANTS_PROT_NUMA_PROT_NONE select HAVE_IDE @@ -41,7 +41,7 @@ config X86 select ARCH_WANT_OPTIONAL_GPIOLIB select ARCH_WANT_FRAME_POINTERS select HAVE_DMA_ATTRS - select HAVE_DMA_CONTIGUOUS if !SWIOTLB + select HAVE_DMA_CONTIGUOUS select HAVE_KRETPROBES select GENERIC_EARLY_IOREMAP select HAVE_OPTPROBES @@ -105,7 +105,7 @@ config X86 select HAVE_ARCH_SECCOMP_FILTER select BUILDTIME_EXTABLE_SORT select GENERIC_CMOS_UPDATE - select HAVE_ARCH_SOFT_DIRTY + select HAVE_ARCH_SOFT_DIRTY if X86_64 select CLOCKSOURCE_WATCHDOG select GENERIC_CLOCKEVENTS select ARCH_CLOCKSOURCE_DATA @@ -261,6 +261,9 @@ config ARCH_HWEIGHT_CFLAGS config ARCH_SUPPORTS_UPROBES def_bool y +config FIX_EARLYCON_MEM + def_bool y + source "init/Kconfig" source "kernel/Kconfig.freezer" @@ -415,7 +418,6 @@ config X86_UV config X86_GOLDFISH bool "Goldfish (Virtual Platform)" - depends on X86_32 depends on X86_EXTENDED_PLATFORM ---help--- Enable support for the Goldfish virtual platform used primarily @@ -831,6 +833,7 @@ config X86_LOCAL_APIC config X86_IO_APIC def_bool y depends on X86_64 || SMP || X86_32_NON_STANDARD || X86_UP_IOAPIC || PCI_MSI + select GENERIC_IRQ_LEGACY_ALLOC_HWIRQ config X86_REROUTE_FOR_BROKEN_BOOT_IRQS bool "Reroute for broken boot IRQs" @@ -1888,6 +1891,10 @@ config ARCH_ENABLE_SPLIT_PMD_PTLOCK def_bool y depends on X86_64 || X86_PAE +config ARCH_ENABLE_HUGEPAGE_MIGRATION + def_bool y + depends on X86_64 && HUGETLB_PAGE && MIGRATION + menu "Power management and ACPI options" config ARCH_HIBERNATION_HEADER @@ -2392,12 +2399,9 @@ config X86_DMA_REMAP depends on STA2X11 config IOSF_MBI - bool + tristate + default m depends on PCI - ---help--- - To be selected by modules requiring access to the Intel OnChip System - Fabric (IOSF) Sideband MailBox Interface (MBI). For MBI platforms - enumerable by PCI. source "net/Kconfig" diff --git a/arch/x86/boot/compressed/string.c b/arch/x86/boot/compressed/string.c index f3c57e3..00e788b 100644 --- a/arch/x86/boot/compressed/string.c +++ b/arch/x86/boot/compressed/string.c @@ -1,9 +1,5 @@ -#include "misc.h" #include "../string.c" -/* misc.h might pull in string_32.h which has a macro for memcpy. undef that */ -#undef memcpy - #ifdef CONFIG_X86_32 void *memcpy(void *dest, const void *src, size_t n) { diff --git a/arch/x86/boot/string.c b/arch/x86/boot/string.c index 5339040..493f3fd 100644 --- a/arch/x86/boot/string.c +++ b/arch/x86/boot/string.c @@ -12,14 +12,9 @@ * Very basic string functions */ -#include "boot.h" +#include <linux/types.h> +#include "ctype.h" -/* - * This file gets included in compressed/string.c which might pull in - * string_32.h and which in turn maps memcmp to __builtin_memcmp(). Undo - * that first. - */ -#undef memcmp int memcmp(const void *s1, const void *s2, size_t len) { u8 diff; diff --git a/arch/x86/configs/i386_defconfig b/arch/x86/configs/i386_defconfig index 619e7f7..32d2e70 100644 --- a/arch/x86/configs/i386_defconfig +++ b/arch/x86/configs/i386_defconfig @@ -244,7 +244,6 @@ CONFIG_HID_TOPSEED=y CONFIG_HID_PID=y CONFIG_USB_HIDDEV=y CONFIG_USB=y -CONFIG_USB_DEBUG=y CONFIG_USB_ANNOUNCE_NEW_DEVICES=y CONFIG_USB_MON=y CONFIG_USB_EHCI_HCD=y diff --git a/arch/x86/configs/x86_64_defconfig b/arch/x86/configs/x86_64_defconfig index 6181c69..a481dd4 100644 --- a/arch/x86/configs/x86_64_defconfig +++ b/arch/x86/configs/x86_64_defconfig @@ -239,7 +239,6 @@ CONFIG_HID_TOPSEED=y CONFIG_HID_PID=y CONFIG_USB_HIDDEV=y CONFIG_USB=y -CONFIG_USB_DEBUG=y CONFIG_USB_ANNOUNCE_NEW_DEVICES=y CONFIG_USB_MON=y CONFIG_USB_EHCI_HCD=y diff --git a/arch/x86/include/asm/acenv.h b/arch/x86/include/asm/acenv.h new file mode 100644 index 0000000..6687329 --- /dev/null +++ b/arch/x86/include/asm/acenv.h @@ -0,0 +1,49 @@ +/* + * X86 specific ACPICA environments and implementation + * + * Copyright (C) 2014, Intel Corporation + * Author: Lv Zheng <lv.zheng@intel.com> + * + * 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. + */ + +#ifndef _ASM_X86_ACENV_H +#define _ASM_X86_ACENV_H + +#include <asm/special_insns.h> + +/* Asm macros */ + +#define ACPI_FLUSH_CPU_CACHE() wbinvd() + +#ifdef CONFIG_ACPI + +int __acpi_acquire_global_lock(unsigned int *lock); +int __acpi_release_global_lock(unsigned int *lock); + +#define ACPI_ACQUIRE_GLOBAL_LOCK(facs, Acq) \ + ((Acq) = __acpi_acquire_global_lock(&facs->global_lock)) + +#define ACPI_RELEASE_GLOBAL_LOCK(facs, Acq) \ + ((Acq) = __acpi_release_global_lock(&facs->global_lock)) + +/* + * Math helper asm macros + */ +#define ACPI_DIV_64_BY_32(n_hi, n_lo, d32, q32, r32) \ + asm("divl %2;" \ + : "=a"(q32), "=d"(r32) \ + : "r"(d32), \ + "0"(n_lo), "1"(n_hi)) + +#define ACPI_SHIFT_RIGHT_64(n_hi, n_lo) \ + asm("shrl $1,%2 ;" \ + "rcrl $1,%3;" \ + : "=r"(n_hi), "=r"(n_lo) \ + : "0"(n_hi), "1"(n_lo)) + +#endif + +#endif /* _ASM_X86_ACENV_H */ diff --git a/arch/x86/include/asm/acpi.h b/arch/x86/include/asm/acpi.h index c8c1e70..e06225e 100644 --- a/arch/x86/include/asm/acpi.h +++ b/arch/x86/include/asm/acpi.h @@ -32,51 +32,6 @@ #include <asm/mpspec.h> #include <asm/realmode.h> -#define COMPILER_DEPENDENT_INT64 long long -#define COMPILER_DEPENDENT_UINT64 unsigned long long - -/* - * Calling conventions: - * - * ACPI_SYSTEM_XFACE - Interfaces to host OS (handlers, threads) - * ACPI_EXTERNAL_XFACE - External ACPI interfaces - * ACPI_INTERNAL_XFACE - Internal ACPI interfaces - * ACPI_INTERNAL_VAR_XFACE - Internal variable-parameter list interfaces - */ -#define ACPI_SYSTEM_XFACE -#define ACPI_EXTERNAL_XFACE -#define ACPI_INTERNAL_XFACE -#define ACPI_INTERNAL_VAR_XFACE - -/* Asm macros */ - -#define ACPI_FLUSH_CPU_CACHE() wbinvd() - -int __acpi_acquire_global_lock(unsigned int *lock); -int __acpi_release_global_lock(unsigned int *lock); - -#define ACPI_ACQUIRE_GLOBAL_LOCK(facs, Acq) \ - ((Acq) = __acpi_acquire_global_lock(&facs->global_lock)) - -#define ACPI_RELEASE_GLOBAL_LOCK(facs, Acq) \ - ((Acq) = __acpi_release_global_lock(&facs->global_lock)) - -/* - * Math helper asm macros - */ -#define ACPI_DIV_64_BY_32(n_hi, n_lo, d32, q32, r32) \ - asm("divl %2;" \ - : "=a"(q32), "=d"(r32) \ - : "r"(d32), \ - "0"(n_lo), "1"(n_hi)) - - -#define ACPI_SHIFT_RIGHT_64(n_hi, n_lo) \ - asm("shrl $1,%2 ;" \ - "rcrl $1,%3;" \ - : "=r"(n_hi), "=r"(n_lo) \ - : "0"(n_hi), "1"(n_lo)) - #ifdef CONFIG_ACPI extern int acpi_lapic; extern int acpi_ioapic; diff --git a/arch/x86/include/asm/atomic.h b/arch/x86/include/asm/atomic.h index b17f4f4..6dd1c7d 100644 --- a/arch/x86/include/asm/atomic.h +++ b/arch/x86/include/asm/atomic.h @@ -7,6 +7,7 @@ #include <asm/alternative.h> #include <asm/cmpxchg.h> #include <asm/rmwcc.h> +#include <asm/barrier.h> /* * Atomic operations that C can't guarantee us. Useful for @@ -243,12 +244,6 @@ static inline void atomic_or_long(unsigned long *v1, unsigned long v2) : : "r" ((unsigned)(mask)), "m" (*(addr)) \ : "memory") -/* Atomic operations are already serializing on x86 */ -#define smp_mb__before_atomic_dec() barrier() -#define smp_mb__after_atomic_dec() barrier() -#define smp_mb__before_atomic_inc() barrier() -#define smp_mb__after_atomic_inc() barrier() - #ifdef CONFIG_X86_32 # include <asm/atomic64_32.h> #else diff --git a/arch/x86/include/asm/barrier.h b/arch/x86/include/asm/barrier.h index 69bbb48..5c7198c 100644 --- a/arch/x86/include/asm/barrier.h +++ b/arch/x86/include/asm/barrier.h @@ -137,6 +137,10 @@ do { \ #endif +/* Atomic operations are already serializing on x86 */ +#define smp_mb__before_atomic() barrier() +#define smp_mb__after_atomic() barrier() + /* * Stop RDTSC speculation. This is needed when you need to use RDTSC * (or get_cycles or vread that possibly accesses the TSC) in a defined diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h index 9fc1af7..afcd35d 100644 --- a/arch/x86/include/asm/bitops.h +++ b/arch/x86/include/asm/bitops.h @@ -15,6 +15,7 @@ #include <linux/compiler.h> #include <asm/alternative.h> #include <asm/rmwcc.h> +#include <asm/barrier.h> #if BITS_PER_LONG == 32 # define _BITOPS_LONG_SHIFT 5 @@ -102,7 +103,7 @@ static inline void __set_bit(long nr, volatile unsigned long *addr) * * clear_bit() is atomic and may not be reordered. However, it does * not contain a memory barrier, so if it is used for locking purposes, - * you should call smp_mb__before_clear_bit() and/or smp_mb__after_clear_bit() + * you should call smp_mb__before_atomic() and/or smp_mb__after_atomic() * in order to ensure changes are visible on other processors. */ static __always_inline void @@ -156,9 +157,6 @@ static inline void __clear_bit_unlock(long nr, volatile unsigned long *addr) __clear_bit(nr, addr); } -#define smp_mb__before_clear_bit() barrier() -#define smp_mb__after_clear_bit() barrier() - /** * __change_bit - Toggle a bit in memory * @nr: the bit to change diff --git a/arch/x86/include/asm/cmdline.h b/arch/x86/include/asm/cmdline.h new file mode 100644 index 0000000..e01f7f7 --- /dev/null +++ b/arch/x86/include/asm/cmdline.h @@ -0,0 +1,6 @@ +#ifndef _ASM_X86_CMDLINE_H +#define _ASM_X86_CMDLINE_H + +int cmdline_find_option_bool(const char *cmdline_ptr, const char *option); + +#endif /* _ASM_X86_CMDLINE_H */ diff --git a/arch/x86/include/asm/hw_irq.h b/arch/x86/include/asm/hw_irq.h index a307b75..4615906 100644 --- a/arch/x86/include/asm/hw_irq.h +++ b/arch/x86/include/asm/hw_irq.h @@ -190,8 +190,8 @@ extern void (*__initconst interrupt[NR_VECTORS-FIRST_EXTERNAL_VECTOR])(void); #define trace_interrupt interrupt #endif -#define VECTOR_UNDEFINED -1 -#define VECTOR_RETRIGGERED -2 +#define VECTOR_UNDEFINED (-1) +#define VECTOR_RETRIGGERED (-2) typedef int vector_irq_t[NR_VECTORS]; DECLARE_PER_CPU(vector_irq_t, vector_irq); diff --git a/arch/x86/include/asm/io_apic.h b/arch/x86/include/asm/io_apic.h index 459e50a..90f97b4 100644 --- a/arch/x86/include/asm/io_apic.h +++ b/arch/x86/include/asm/io_apic.h @@ -168,8 +168,6 @@ extern int save_ioapic_entries(void); extern void mask_ioapic_entries(void); extern int restore_ioapic_entries(void); -extern int get_nr_irqs_gsi(void); - extern void setup_ioapic_ids_from_mpc(void); extern void setup_ioapic_ids_from_mpc_nocheck(void); diff --git a/arch/x86/include/asm/iosf_mbi.h b/arch/x86/include/asm/iosf_mbi.h index 8e71c79..57995f0 100644 --- a/arch/x86/include/asm/iosf_mbi.h +++ b/arch/x86/include/asm/iosf_mbi.h @@ -50,6 +50,32 @@ #define BT_MBI_PCIE_READ 0x00 #define BT_MBI_PCIE_WRITE 0x01 +/* Quark available units */ +#define QRK_MBI_UNIT_HBA 0x00 +#define QRK_MBI_UNIT_HB 0x03 +#define QRK_MBI_UNIT_RMU 0x04 +#define QRK_MBI_UNIT_MM 0x05 +#define QRK_MBI_UNIT_MMESRAM 0x05 +#define QRK_MBI_UNIT_SOC 0x31 + +/* Quark read/write opcodes */ +#define QRK_MBI_HBA_READ 0x10 +#define QRK_MBI_HBA_WRITE 0x11 +#define QRK_MBI_HB_READ 0x10 +#define QRK_MBI_HB_WRITE 0x11 +#define QRK_MBI_RMU_READ 0x10 +#define QRK_MBI_RMU_WRITE 0x11 +#define QRK_MBI_MM_READ 0x10 +#define QRK_MBI_MM_WRITE 0x11 +#define QRK_MBI_MMESRAM_READ 0x12 +#define QRK_MBI_MMESRAM_WRITE 0x13 +#define QRK_MBI_SOC_READ 0x06 +#define QRK_MBI_SOC_WRITE 0x07 + +#if IS_ENABLED(CONFIG_IOSF_MBI) + +bool iosf_mbi_available(void); + /** * iosf_mbi_read() - MailBox Interface read command * @port: port indicating subunit being accessed @@ -87,4 +113,33 @@ int iosf_mbi_write(u8 port, u8 opcode, u32 offset, u32 mdr); */ int iosf_mbi_modify(u8 port, u8 opcode, u32 offset, u32 mdr, u32 mask); +#else /* CONFIG_IOSF_MBI is not enabled */ +static inline +bool iosf_mbi_available(void) +{ + return false; +} + +static inline +int iosf_mbi_read(u8 port, u8 opcode, u32 offset, u32 *mdr) +{ + WARN(1, "IOSF_MBI driver not available"); + return -EPERM; +} + +static inline +int iosf_mbi_write(u8 port, u8 opcode, u32 offset, u32 mdr) +{ + WARN(1, "IOSF_MBI driver not available"); + return -EPERM; +} + +static inline +int iosf_mbi_modify(u8 port, u8 opcode, u32 offset, u32 mdr, u32 mask) +{ + WARN(1, "IOSF_MBI driver not available"); + return -EPERM; +} +#endif /* CONFIG_IOSF_MBI */ + #endif /* IOSF_MBI_SYMS_H */ diff --git a/arch/x86/include/asm/irq_remapping.h b/arch/x86/include/asm/irq_remapping.h index d806b22..b7747c4 100644 --- a/arch/x86/include/asm/irq_remapping.h +++ b/arch/x86/include/asm/irq_remapping.h @@ -103,4 +103,7 @@ static inline bool setup_remapped_irq(int irq, } #endif /* CONFIG_IRQ_REMAP */ +#define dmar_alloc_hwirq() irq_alloc_hwirq(-1) +#define dmar_free_hwirq irq_free_hwirq + #endif /* __X86_IRQ_REMAPPING_H */ diff --git a/arch/x86/include/asm/kvm_emulate.h b/arch/x86/include/asm/kvm_emulate.h index 24ec121..a04fe4e 100644 --- a/arch/x86/include/asm/kvm_emulate.h +++ b/arch/x86/include/asm/kvm_emulate.h @@ -189,7 +189,6 @@ struct x86_emulate_ops { void (*set_idt)(struct x86_emulate_ctxt *ctxt, struct desc_ptr *dt); ulong (*get_cr)(struct x86_emulate_ctxt *ctxt, int cr); int (*set_cr)(struct x86_emulate_ctxt *ctxt, int cr, ulong val); - void (*set_rflags)(struct x86_emulate_ctxt *ctxt, ulong val); int (*cpl)(struct x86_emulate_ctxt *ctxt); int (*get_dr)(struct x86_emulate_ctxt *ctxt, int dr, ulong *dest); int (*set_dr)(struct x86_emulate_ctxt *ctxt, int dr, ulong value); diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 7de069af..4931415 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -50,11 +50,7 @@ | X86_CR0_ET | X86_CR0_NE | X86_CR0_WP | X86_CR0_AM \ | X86_CR0_NW | X86_CR0_CD | X86_CR0_PG)) -#define CR3_PAE_RESERVED_BITS ((X86_CR3_PWT | X86_CR3_PCD) - 1) -#define CR3_NONPAE_RESERVED_BITS ((PAGE_SIZE-1) & ~(X86_CR3_PWT | X86_CR3_PCD)) -#define CR3_PCID_ENABLED_RESERVED_BITS 0xFFFFFF0000000000ULL -#define CR3_L_MODE_RESERVED_BITS (CR3_NONPAE_RESERVED_BITS | \ - 0xFFFFFF0000000000ULL) +#define CR3_L_MODE_RESERVED_BITS 0xFFFFFF0000000000ULL #define CR4_RESERVED_BITS \ (~(unsigned long)(X86_CR4_VME | X86_CR4_PVI | X86_CR4_TSD | X86_CR4_DE\ | X86_CR4_PSE | X86_CR4_PAE | X86_CR4_MCE \ @@ -134,7 +130,6 @@ enum kvm_reg_ex { VCPU_EXREG_PDPTR = NR_VCPU_REGS, VCPU_EXREG_CR3, VCPU_EXREG_RFLAGS, - VCPU_EXREG_CPL, VCPU_EXREG_SEGMENTS, }; diff --git a/arch/x86/include/asm/mce.h b/arch/x86/include/asm/mce.h index 6e4ce2d..958b90f 100644 --- a/arch/x86/include/asm/mce.h +++ b/arch/x86/include/asm/mce.h @@ -176,8 +176,6 @@ int mce_available(struct cpuinfo_x86 *c); DECLARE_PER_CPU(unsigned, mce_exception_count); DECLARE_PER_CPU(unsigned, mce_poll_count); -extern atomic_t mce_entry; - typedef DECLARE_BITMAP(mce_banks_t, MAX_NR_BANKS); DECLARE_PER_CPU(mce_banks_t, mce_poll_banks); diff --git a/arch/x86/include/asm/microcode.h b/arch/x86/include/asm/microcode.h index b59827e..64dc362 100644 --- a/arch/x86/include/asm/microcode.h +++ b/arch/x86/include/asm/microcode.h @@ -25,6 +25,7 @@ struct cpu_signature { struct device; enum ucode_state { UCODE_ERROR, UCODE_OK, UCODE_NFOUND }; +extern bool dis_ucode_ldr; struct microcode_ops { enum ucode_state (*request_microcode_user) (int cpu, diff --git a/arch/x86/include/asm/page_64_types.h b/arch/x86/include/asm/page_64_types.h index 8de6d9c..6782051 100644 --- a/arch/x86/include/asm/page_64_types.h +++ b/arch/x86/include/asm/page_64_types.h @@ -1,7 +1,7 @@ #ifndef _ASM_X86_PAGE_64_DEFS_H #define _ASM_X86_PAGE_64_DEFS_H -#define THREAD_SIZE_ORDER 1 +#define THREAD_SIZE_ORDER 2 #define THREAD_SIZE (PAGE_SIZE << THREAD_SIZE_ORDER) #define CURRENT_MASK (~(THREAD_SIZE - 1)) diff --git a/arch/x86/include/asm/pci.h b/arch/x86/include/asm/pci.h index 96ae4f4..0892ea0 100644 --- a/arch/x86/include/asm/pci.h +++ b/arch/x86/include/asm/pci.h @@ -68,7 +68,6 @@ void pcibios_config_init(void); void pcibios_scan_root(int bus); void pcibios_set_master(struct pci_dev *dev); -void pcibios_penalize_isa_irq(int irq, int active); struct irq_routing_table *pcibios_get_irq_routing_table(void); int pcibios_set_irq_routing(struct pci_dev *dev, int pin, int irq); diff --git a/arch/x86/include/asm/pgtable-2level.h b/arch/x86/include/asm/pgtable-2level.h index 0d193e2..206a87f 100644 --- a/arch/x86/include/asm/pgtable-2level.h +++ b/arch/x86/include/asm/pgtable-2level.h @@ -62,66 +62,14 @@ static inline unsigned long pte_bitop(unsigned long value, unsigned int rightshi return ((value >> rightshift) & mask) << leftshift; } -#ifdef CONFIG_MEM_SOFT_DIRTY - -/* - * Bits _PAGE_BIT_PRESENT, _PAGE_BIT_FILE, _PAGE_BIT_SOFT_DIRTY and - * _PAGE_BIT_PROTNONE are taken, split up the 28 bits of offset - * into this range. - */ -#define PTE_FILE_MAX_BITS 28 -#define PTE_FILE_SHIFT1 (_PAGE_BIT_PRESENT + 1) -#define PTE_FILE_SHIFT2 (_PAGE_BIT_FILE + 1) -#define PTE_FILE_SHIFT3 (_PAGE_BIT_PROTNONE + 1) -#define PTE_FILE_SHIFT4 (_PAGE_BIT_SOFT_DIRTY + 1) -#define PTE_FILE_BITS1 (PTE_FILE_SHIFT2 - PTE_FILE_SHIFT1 - 1) -#define PTE_FILE_BITS2 (PTE_FILE_SHIFT3 - PTE_FILE_SHIFT2 - 1) -#define PTE_FILE_BITS3 (PTE_FILE_SHIFT4 - PTE_FILE_SHIFT3 - 1) - -#define PTE_FILE_MASK1 ((1U << PTE_FILE_BITS1) - 1) -#define PTE_FILE_MASK2 ((1U << PTE_FILE_BITS2) - 1) -#define PTE_FILE_MASK3 ((1U << PTE_FILE_BITS3) - 1) - -#define PTE_FILE_LSHIFT2 (PTE_FILE_BITS1) -#define PTE_FILE_LSHIFT3 (PTE_FILE_BITS1 + PTE_FILE_BITS2) -#define PTE_FILE_LSHIFT4 (PTE_FILE_BITS1 + PTE_FILE_BITS2 + PTE_FILE_BITS3) - -static __always_inline pgoff_t pte_to_pgoff(pte_t pte) -{ - return (pgoff_t) - (pte_bitop(pte.pte_low, PTE_FILE_SHIFT1, PTE_FILE_MASK1, 0) + - pte_bitop(pte.pte_low, PTE_FILE_SHIFT2, PTE_FILE_MASK2, PTE_FILE_LSHIFT2) + - pte_bitop(pte.pte_low, PTE_FILE_SHIFT3, PTE_FILE_MASK3, PTE_FILE_LSHIFT3) + - pte_bitop(pte.pte_low, PTE_FILE_SHIFT4, -1UL, PTE_FILE_LSHIFT4)); -} - -static __always_inline pte_t pgoff_to_pte(pgoff_t off) -{ - return (pte_t){ - .pte_low = - pte_bitop(off, 0, PTE_FILE_MASK1, PTE_FILE_SHIFT1) + - pte_bitop(off, PTE_FILE_LSHIFT2, PTE_FILE_MASK2, PTE_FILE_SHIFT2) + - pte_bitop(off, PTE_FILE_LSHIFT3, PTE_FILE_MASK3, PTE_FILE_SHIFT3) + - pte_bitop(off, PTE_FILE_LSHIFT4, -1UL, PTE_FILE_SHIFT4) + - _PAGE_FILE, - }; -} - -#else /* CONFIG_MEM_SOFT_DIRTY */ - /* * Bits _PAGE_BIT_PRESENT, _PAGE_BIT_FILE and _PAGE_BIT_PROTNONE are taken, * split up the 29 bits of offset into this range. */ #define PTE_FILE_MAX_BITS 29 #define PTE_FILE_SHIFT1 (_PAGE_BIT_PRESENT + 1) -#if _PAGE_BIT_FILE < _PAGE_BIT_PROTNONE #define PTE_FILE_SHIFT2 (_PAGE_BIT_FILE + 1) #define PTE_FILE_SHIFT3 (_PAGE_BIT_PROTNONE + 1) -#else -#define PTE_FILE_SHIFT2 (_PAGE_BIT_PROTNONE + 1) -#define PTE_FILE_SHIFT3 (_PAGE_BIT_FILE + 1) -#endif #define PTE_FILE_BITS1 (PTE_FILE_SHIFT2 - PTE_FILE_SHIFT1 - 1) #define PTE_FILE_BITS2 (PTE_FILE_SHIFT3 - PTE_FILE_SHIFT2 - 1) @@ -150,16 +98,9 @@ static __always_inline pte_t pgoff_to_pte(pgoff_t off) }; } -#endif /* CONFIG_MEM_SOFT_DIRTY */ - /* Encode and de-code a swap entry */ -#if _PAGE_BIT_FILE < _PAGE_BIT_PROTNONE #define SWP_TYPE_BITS (_PAGE_BIT_FILE - _PAGE_BIT_PRESENT - 1) #define SWP_OFFSET_SHIFT (_PAGE_BIT_PROTNONE + 1) -#else -#define SWP_TYPE_BITS (_PAGE_BIT_PROTNONE - _PAGE_BIT_PRESENT - 1) -#define SWP_OFFSET_SHIFT (_PAGE_BIT_FILE + 1) -#endif #define MAX_SWAPFILES_CHECK() BUILD_BUG_ON(MAX_SWAPFILES_SHIFT > SWP_TYPE_BITS) diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h index b459ddf..0ec0560 100644 --- a/arch/x86/include/asm/pgtable.h +++ b/arch/x86/include/asm/pgtable.h @@ -131,7 +131,8 @@ static inline int pte_exec(pte_t pte) static inline int pte_special(pte_t pte) { - return pte_flags(pte) & _PAGE_SPECIAL; + return (pte_flags(pte) & (_PAGE_PRESENT|_PAGE_SPECIAL)) == + (_PAGE_PRESENT|_PAGE_SPECIAL); } static inline unsigned long pte_pfn(pte_t pte) @@ -296,6 +297,7 @@ static inline pmd_t pmd_mknotpresent(pmd_t pmd) return pmd_clear_flags(pmd, _PAGE_PRESENT); } +#ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY static inline int pte_soft_dirty(pte_t pte) { return pte_flags(pte) & _PAGE_SOFT_DIRTY; @@ -331,6 +333,8 @@ static inline int pte_file_soft_dirty(pte_t pte) return pte_flags(pte) & _PAGE_SOFT_DIRTY; } +#endif /* CONFIG_HAVE_ARCH_SOFT_DIRTY */ + /* * Mask out unsupported bits in a present pgprot. Non-present pgprots * can use those bits for other purposes, so leave them be. @@ -452,6 +456,12 @@ static inline int pte_present(pte_t a) _PAGE_NUMA); } +#define pte_present_nonuma pte_present_nonuma +static inline int pte_present_nonuma(pte_t a) +{ + return pte_flags(a) & (_PAGE_PRESENT | _PAGE_PROTNONE); +} + #define pte_accessible pte_accessible static inline bool pte_accessible(struct mm_struct *mm, pte_t a) { @@ -858,23 +868,25 @@ static inline void update_mmu_cache_pmd(struct vm_area_struct *vma, { } +#ifdef CONFIG_HAVE_ARCH_SOFT_DIRTY static inline pte_t pte_swp_mksoft_dirty(pte_t pte) { - VM_BUG_ON(pte_present(pte)); + VM_BUG_ON(pte_present_nonuma(pte)); return pte_set_flags(pte, _PAGE_SWP_SOFT_DIRTY); } static inline int pte_swp_soft_dirty(pte_t pte) { - VM_BUG_ON(pte_present(pte)); + VM_BUG_ON(pte_present_nonuma(pte)); return pte_flags(pte) & _PAGE_SWP_SOFT_DIRTY; } static inline pte_t pte_swp_clear_soft_dirty(pte_t pte) { - VM_BUG_ON(pte_present(pte)); + VM_BUG_ON(pte_present_nonuma(pte)); return pte_clear_flags(pte, _PAGE_SWP_SOFT_DIRTY); } +#endif #include <asm-generic/pgtable.h> #endif /* __ASSEMBLY__ */ diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h index e22c1db..5be9063 100644 --- a/arch/x86/include/asm/pgtable_64.h +++ b/arch/x86/include/asm/pgtable_64.h @@ -143,12 +143,12 @@ static inline int pgd_large(pgd_t pgd) { return 0; } #define pte_unmap(pte) ((void)(pte))/* NOP */ /* Encode and de-code a swap entry */ -#if _PAGE_BIT_FILE < _PAGE_BIT_PROTNONE #define SWP_TYPE_BITS (_PAGE_BIT_FILE - _PAGE_BIT_PRESENT - 1) -#define SWP_OFFSET_SHIFT (_PAGE_BIT_PROTNONE + 1) +#ifdef CONFIG_NUMA_BALANCING +/* Automatic NUMA balancing needs to be distinguishable from swap entries */ +#define SWP_OFFSET_SHIFT (_PAGE_BIT_PROTNONE + 2) #else -#define SWP_TYPE_BITS (_PAGE_BIT_PROTNONE - _PAGE_BIT_PRESENT - 1) -#define SWP_OFFSET_SHIFT (_PAGE_BIT_FILE + 1) +#define SWP_OFFSET_SHIFT (_PAGE_BIT_PROTNONE + 1) #endif #define MAX_SWAPFILES_CHECK() BUILD_BUG_ON(MAX_SWAPFILES_SHIFT > SWP_TYPE_BITS) diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h index eb3d449..f216963 100644 --- a/arch/x86/include/asm/pgtable_types.h +++ b/arch/x86/include/asm/pgtable_types.h @@ -16,15 +16,26 @@ #define _PAGE_BIT_PSE 7 /* 4 MB (or 2MB) page */ #define _PAGE_BIT_PAT 7 /* on 4KB pages */ #define _PAGE_BIT_GLOBAL 8 /* Global TLB entry PPro+ */ -#define _PAGE_BIT_UNUSED1 9 /* available for programmer */ -#define _PAGE_BIT_IOMAP 10 /* flag used to indicate IO mapping */ -#define _PAGE_BIT_HIDDEN 11 /* hidden by kmemcheck */ +#define _PAGE_BIT_SOFTW1 9 /* available for programmer */ +#define _PAGE_BIT_SOFTW2 10 /* " */ +#define _PAGE_BIT_SOFTW3 11 /* " */ #define _PAGE_BIT_PAT_LARGE 12 /* On 2MB or 1GB pages */ -#define _PAGE_BIT_SPECIAL _PAGE_BIT_UNUSED1 -#define _PAGE_BIT_CPA_TEST _PAGE_BIT_UNUSED1 -#define _PAGE_BIT_SPLITTING _PAGE_BIT_UNUSED1 /* only valid on a PSE pmd */ +#define _PAGE_BIT_SPECIAL _PAGE_BIT_SOFTW1 +#define _PAGE_BIT_CPA_TEST _PAGE_BIT_SOFTW1 +#define _PAGE_BIT_SPLITTING _PAGE_BIT_SOFTW2 /* only valid on a PSE pmd */ +#define _PAGE_BIT_IOMAP _PAGE_BIT_SOFTW2 /* flag used to indicate IO mapping */ +#define _PAGE_BIT_HIDDEN _PAGE_BIT_SOFTW3 /* hidden by kmemcheck */ +#define _PAGE_BIT_SOFT_DIRTY _PAGE_BIT_SOFTW3 /* software dirty tracking */ #define _PAGE_BIT_NX 63 /* No execute: only valid after cpuid check */ +/* + * Swap offsets on configurations that allow automatic NUMA balancing use the + * bits after _PAGE_BIT_GLOBAL. To uniquely distinguish NUMA hinting PTEs from + * swap entries, we use the first bit after _PAGE_BIT_GLOBAL and shrink the + * maximum possible swap space from 16TB to 8TB. + */ +#define _PAGE_BIT_NUMA (_PAGE_BIT_GLOBAL+1) + /* If _PAGE_BIT_PRESENT is clear, we use these: */ /* - if the user mapped it with PROT_NONE; pte_present gives true */ #define _PAGE_BIT_PROTNONE _PAGE_BIT_GLOBAL @@ -40,7 +51,7 @@ #define _PAGE_DIRTY (_AT(pteval_t, 1) << _PAGE_BIT_DIRTY) #define _PAGE_PSE (_AT(pteval_t, 1) << _PAGE_BIT_PSE) #define _PAGE_GLOBAL (_AT(pteval_t, 1) << _PAGE_BIT_GLOBAL) -#define _PAGE_UNUSED1 (_AT(pteval_t, 1) << _PAGE_BIT_UNUSED1) +#define _PAGE_SOFTW1 (_AT(pteval_t, 1) << _PAGE_BIT_SOFTW1) #define _PAGE_IOMAP (_AT(pteval_t, 1) << _PAGE_BIT_IOMAP) #define _PAGE_PAT (_AT(pteval_t, 1) << _PAGE_BIT_PAT) #define _PAGE_PAT_LARGE (_AT(pteval_t, 1) << _PAGE_BIT_PAT_LARGE) @@ -61,8 +72,6 @@ * they do not conflict with each other. */ -#define _PAGE_BIT_SOFT_DIRTY _PAGE_BIT_HIDDEN - #ifdef CONFIG_MEM_SOFT_DIRTY #define _PAGE_SOFT_DIRTY (_AT(pteval_t, 1) << _PAGE_BIT_SOFT_DIRTY) #else @@ -70,6 +79,21 @@ #endif /* + * _PAGE_NUMA distinguishes between a numa hinting minor fault and a page + * that is not present. The hinting fault gathers numa placement statistics + * (see pte_numa()). The bit is always zero when the PTE is not present. + * + * The bit picked must be always zero when the pmd is present and not + * present, so that we don't lose information when we set it while + * atomically clearing the present bit. + */ +#ifdef CONFIG_NUMA_BALANCING +#define _PAGE_NUMA (_AT(pteval_t, 1) << _PAGE_BIT_NUMA) +#else +#define _PAGE_NUMA (_AT(pteval_t, 0)) +#endif + +/* * Tracking soft dirty bit when a page goes to a swap is tricky. * We need a bit which can be stored in pte _and_ not conflict * with swap entry format. On x86 bits 6 and 7 are *not* involved @@ -94,26 +118,6 @@ #define _PAGE_FILE (_AT(pteval_t, 1) << _PAGE_BIT_FILE) #define _PAGE_PROTNONE (_AT(pteval_t, 1) << _PAGE_BIT_PROTNONE) -/* - * _PAGE_NUMA indicates that this page will trigger a numa hinting - * minor page fault to gather numa placement statistics (see - * pte_numa()). The bit picked (8) is within the range between - * _PAGE_FILE (6) and _PAGE_PROTNONE (8) bits. Therefore, it doesn't - * require changes to the swp entry format because that bit is always - * zero when the pte is not present. - * - * The bit picked must be always zero when the pmd is present and not - * present, so that we don't lose information when we set it while - * atomically clearing the present bit. - * - * Because we shared the same bit (8) with _PAGE_PROTNONE this can be - * interpreted as _PAGE_NUMA only in places that _PAGE_PROTNONE - * couldn't reach, like handle_mm_fault() (see access_error in - * arch/x86/mm/fault.c, the vma protection must not be PROT_NONE for - * handle_mm_fault() to be invoked). - */ -#define _PAGE_NUMA _PAGE_PROTNONE - #define _PAGE_TABLE (_PAGE_PRESENT | _PAGE_RW | _PAGE_USER | \ _PAGE_ACCESSED | _PAGE_DIRTY) #define _KERNPG_TABLE (_PAGE_PRESENT | _PAGE_RW | _PAGE_ACCESSED | \ @@ -122,8 +126,8 @@ /* Set of bits not changed in pte_modify */ #define _PAGE_CHG_MASK (PTE_PFN_MASK | _PAGE_PCD | _PAGE_PWT | \ _PAGE_SPECIAL | _PAGE_ACCESSED | _PAGE_DIRTY | \ - _PAGE_SOFT_DIRTY) -#define _HPAGE_CHG_MASK (_PAGE_CHG_MASK | _PAGE_PSE) + _PAGE_SOFT_DIRTY | _PAGE_NUMA) +#define _HPAGE_CHG_MASK (_PAGE_CHG_MASK | _PAGE_PSE | _PAGE_NUMA) #define _PAGE_CACHE_MASK (_PAGE_PCD | _PAGE_PWT) #define _PAGE_CACHE_WB (0) diff --git a/arch/x86/include/asm/swiotlb.h b/arch/x86/include/asm/swiotlb.h index 977f176..ab05d73 100644 --- a/arch/x86/include/asm/swiotlb.h +++ b/arch/x86/include/asm/swiotlb.h @@ -29,4 +29,11 @@ static inline void pci_swiotlb_late_init(void) static inline void dma_mark_clean(void *addr, size_t size) {} +extern void *x86_swiotlb_alloc_coherent(struct device *hwdev, size_t size, + dma_addr_t *dma_handle, gfp_t flags, + struct dma_attrs *attrs); +extern void x86_swiotlb_free_coherent(struct device *dev, size_t size, + void *vaddr, dma_addr_t dma_addr, + struct dma_attrs *attrs); + #endif /* _ASM_X86_SWIOTLB_H */ diff --git a/arch/x86/include/asm/sync_bitops.h b/arch/x86/include/asm/sync_bitops.h index 05af3b3..f28a24b 100644 --- a/arch/x86/include/asm/sync_bitops.h +++ b/arch/x86/include/asm/sync_bitops.h @@ -41,7 +41,7 @@ static inline void sync_set_bit(long nr, volatile unsigned long *addr) * * sync_clear_bit() is atomic and may not be reordered. However, it does * not contain a memory barrier, so if it is used for locking purposes, - * you should call smp_mb__before_clear_bit() and/or smp_mb__after_clear_bit() + * you should call smp_mb__before_atomic() and/or smp_mb__after_atomic() * in order to ensure changes are visible on other processors. */ static inline void sync_clear_bit(long nr, volatile unsigned long *addr) diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h index 47e5de2..8540538 100644 --- a/arch/x86/include/asm/thread_info.h +++ b/arch/x86/include/asm/thread_info.h @@ -83,6 +83,7 @@ struct thread_info { #define TIF_FORK 18 /* ret_from_fork */ #define TIF_NOHZ 19 /* in adaptive nohz mode */ #define TIF_MEMDIE 20 /* is terminating due to OOM killer */ +#define TIF_POLLING_NRFLAG 21 /* idle is polling for TIF_NEED_RESCHED */ #define TIF_IO_BITMAP 22 /* uses I/O bitmap */ #define TIF_FORCED_TF 24 /* true if TF in eflags artificially */ #define TIF_BLOCKSTEP 25 /* set when we want DEBUGCTLMSR_BTF */ @@ -106,6 +107,7 @@ struct thread_info { #define _TIF_IA32 (1 << TIF_IA32) #define _TIF_FORK (1 << TIF_FORK) #define _TIF_NOHZ (1 << TIF_NOHZ) +#define _TIF_POLLING_NRFLAG (1 << TIF_POLLING_NRFLAG) #define _TIF_IO_BITMAP (1 << TIF_IO_BITMAP) #define _TIF_FORCED_TF (1 << TIF_FORCED_TF) #define _TIF_BLOCKSTEP (1 << TIF_BLOCKSTEP) @@ -191,8 +193,6 @@ static inline struct thread_info *current_thread_info(void) * have to worry about atomic accesses. */ #define TS_COMPAT 0x0002 /* 32bit syscall active (64BIT)*/ -#define TS_POLLING 0x0004 /* idle task polling need_resched, - skip sending interrupt */ #define TS_RESTORE_SIGMASK 0x0008 /* restore signal mask in do_signal() */ #ifndef __ASSEMBLY__ diff --git a/arch/x86/include/asm/traps.h b/arch/x86/include/asm/traps.h index 58d66fe..8ba1884 100644 --- a/arch/x86/include/asm/traps.h +++ b/arch/x86/include/asm/traps.h @@ -74,6 +74,11 @@ dotraplinkage void do_general_protection(struct pt_regs *, long); dotraplinkage void do_page_fault(struct pt_regs *, unsigned long); #ifdef CONFIG_TRACING dotraplinkage void trace_do_page_fault(struct pt_regs *, unsigned long); +#else +static inline void trace_do_page_fault(struct pt_regs *regs, unsigned long error) +{ + do_page_fault(regs, error); +} #endif dotraplinkage void do_spurious_interrupt_bug(struct pt_regs *, long); dotraplinkage void do_coprocessor_error(struct pt_regs *, long); diff --git a/arch/x86/include/asm/unistd.h b/arch/x86/include/asm/unistd.h index 3f556c6..2b19caa 100644 --- a/arch/x86/include/asm/unistd.h +++ b/arch/x86/include/asm/unistd.h @@ -41,7 +41,6 @@ # define __ARCH_WANT_SYS_OLD_GETRLIMIT # define __ARCH_WANT_SYS_OLD_UNAME # define __ARCH_WANT_SYS_PAUSE -# define __ARCH_WANT_SYS_SGETMASK # define __ARCH_WANT_SYS_SIGNAL # define __ARCH_WANT_SYS_SIGPENDING # define __ARCH_WANT_SYS_SIGPROCMASK diff --git a/arch/x86/include/asm/uprobes.h b/arch/x86/include/asm/uprobes.h index 3087ea9..93bee7b 100644 --- a/arch/x86/include/asm/uprobes.h +++ b/arch/x86/include/asm/uprobes.h @@ -33,15 +33,27 @@ typedef u8 uprobe_opcode_t; #define UPROBE_SWBP_INSN 0xcc #define UPROBE_SWBP_INSN_SIZE 1 +struct uprobe_xol_ops; + struct arch_uprobe { - u16 fixups; union { u8 insn[MAX_UINSN_BYTES]; u8 ixol[MAX_UINSN_BYTES]; }; + + u16 fixups; + const struct uprobe_xol_ops *ops; + + union { #ifdef CONFIG_X86_64 - unsigned long rip_rela_target_address; + unsigned long rip_rela_target_address; #endif + struct { + s32 offs; + u8 ilen; + u8 opc1; + } branch; + }; }; struct arch_uprobe_task { diff --git a/arch/x86/include/asm/uv/uv_hub.h b/arch/x86/include/asm/uv/uv_hub.h index a30836c..c63e925 100644 --- a/arch/x86/include/asm/uv/uv_hub.h +++ b/arch/x86/include/asm/uv/uv_hub.h @@ -5,7 +5,7 @@ * * SGI UV architectural definitions * - * Copyright (C) 2007-2013 Silicon Graphics, Inc. All rights reserved. + * Copyright (C) 2007-2014 Silicon Graphics, Inc. All rights reserved. */ #ifndef _ASM_X86_UV_UV_HUB_H @@ -204,16 +204,6 @@ static inline int is_uvx_hub(void) return uv_hub_info->hub_revision >= UV2_HUB_REVISION_BASE; } -static inline int is_uv2_1_hub(void) -{ - return uv_hub_info->hub_revision == UV2_HUB_REVISION_BASE; -} - -static inline int is_uv2_2_hub(void) -{ - return uv_hub_info->hub_revision == UV2_HUB_REVISION_BASE + 1; -} - union uvh_apicid { unsigned long v; struct uvh_apicid_s { diff --git a/arch/x86/include/asm/uv/uv_mmrs.h b/arch/x86/include/asm/uv/uv_mmrs.h index e42249b..ddd8db6 100644 --- a/arch/x86/include/asm/uv/uv_mmrs.h +++ b/arch/x86/include/asm/uv/uv_mmrs.h @@ -5,7 +5,7 @@ * * SGI UV MMR definitions * - * Copyright (C) 2007-2013 Silicon Graphics, Inc. All rights reserved. + * Copyright (C) 2007-2014 Silicon Graphics, Inc. All rights reserved. */ #ifndef _ASM_X86_UV_UV_MMRS_H @@ -2803,6 +2803,46 @@ union uv1h_lb_target_physical_apic_id_mask_u { }; /* ========================================================================= */ +/* UV3H_GR0_GAM_GR_CONFIG */ +/* ========================================================================= */ +#define UV3H_GR0_GAM_GR_CONFIG 0xc00028UL + +#define UV3H_GR0_GAM_GR_CONFIG_M_SKT_SHFT 0 +#define UV3H_GR0_GAM_GR_CONFIG_SUBSPACE_SHFT 10 +#define UV3H_GR0_GAM_GR_CONFIG_M_SKT_MASK 0x000000000000003fUL +#define UV3H_GR0_GAM_GR_CONFIG_SUBSPACE_MASK 0x0000000000000400UL + +union uv3h_gr0_gam_gr_config_u { + unsigned long v; + struct uv3h_gr0_gam_gr_config_s { + unsigned long m_skt:6; /* RW */ + unsigned long undef_6_9:4; /* Undefined */ + unsigned long subspace:1; /* RW */ + unsigned long reserved:53; + } s3; +}; + +/* ========================================================================= */ +/* UV3H_GR1_GAM_GR_CONFIG */ +/* ========================================================================= */ +#define UV3H_GR1_GAM_GR_CONFIG 0x1000028UL + +#define UV3H_GR1_GAM_GR_CONFIG_M_SKT_SHFT 0 +#define UV3H_GR1_GAM_GR_CONFIG_SUBSPACE_SHFT 10 +#define UV3H_GR1_GAM_GR_CONFIG_M_SKT_MASK 0x000000000000003fUL +#define UV3H_GR1_GAM_GR_CONFIG_SUBSPACE_MASK 0x0000000000000400UL + +union uv3h_gr1_gam_gr_config_u { + unsigned long v; + struct uv3h_gr1_gam_gr_config_s { + unsigned long m_skt:6; /* RW */ + unsigned long undef_6_9:4; /* Undefined */ + unsigned long subspace:1; /* RW */ + unsigned long reserved:53; + } s3; +}; + +/* ========================================================================= */ /* UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR */ /* ========================================================================= */ #define UV3H_RH_GAM_MMIOH_OVERLAY_CONFIG0_MMR 0x1603000UL diff --git a/arch/x86/include/asm/xen/hypercall.h b/arch/x86/include/asm/xen/hypercall.h index e709884..ca08a27 100644 --- a/arch/x86/include/asm/xen/hypercall.h +++ b/arch/x86/include/asm/xen/hypercall.h @@ -343,7 +343,7 @@ HYPERVISOR_memory_op(unsigned int cmd, void *arg) } static inline int -HYPERVISOR_multicall(void *call_list, int nr_calls) +HYPERVISOR_multicall(void *call_list, uint32_t nr_calls) { return _hypercall2(int, multicall, call_list, nr_calls); } diff --git a/arch/x86/include/asm/xen/interface.h b/arch/x86/include/asm/xen/interface.h index fd9cb76..3400dba 100644 --- a/arch/x86/include/asm/xen/interface.h +++ b/arch/x86/include/asm/xen/interface.h @@ -54,6 +54,9 @@ typedef unsigned long xen_pfn_t; #define PRI_xen_pfn "lx" typedef unsigned long xen_ulong_t; #define PRI_xen_ulong "lx" +typedef long xen_long_t; +#define PRI_xen_long "lx" + /* Guest handles for primitive C types. */ __DEFINE_GUEST_HANDLE(uchar, unsigned char); __DEFINE_GUEST_HANDLE(uint, unsigned int); diff --git a/arch/x86/kernel/amd_gart_64.c b/arch/x86/kernel/amd_gart_64.c index b574b29..8e3842f 100644 --- a/arch/x86/kernel/amd_gart_64.c +++ b/arch/x86/kernel/amd_gart_64.c @@ -512,7 +512,7 @@ gart_free_coherent(struct device *dev, size_t size, void *vaddr, dma_addr_t dma_addr, struct dma_attrs *attrs) { gart_unmap_page(dev, dma_addr, size, DMA_BIDIRECTIONAL, NULL); - free_pages((unsigned long)vaddr, get_order(size)); + dma_generic_free_coherent(dev, size, vaddr, dma_addr, attrs); } static int gart_mapping_error(struct device *dev, dma_addr_t dma_addr) diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c index 9fa8aa0..76164e1 100644 --- a/arch/x86/kernel/aperture_64.c +++ b/arch/x86/kernel/aperture_64.c @@ -10,6 +10,8 @@ * * Copyright 2002 Andi Kleen, SuSE Labs. */ +#define pr_fmt(fmt) "AGP: " fmt + #include <linux/kernel.h> #include <linux/types.h> #include <linux/init.h> @@ -75,14 +77,13 @@ static u32 __init allocate_aperture(void) addr = memblock_find_in_range(GART_MIN_ADDR, GART_MAX_ADDR, aper_size, aper_size); if (!addr) { - printk(KERN_ERR - "Cannot allocate aperture memory hole (%lx,%uK)\n", - addr, aper_size>>10); + pr_err("Cannot allocate aperture memory hole [mem %#010lx-%#010lx] (%uKB)\n", + addr, addr + aper_size - 1, aper_size >> 10); return 0; } memblock_reserve(addr, aper_size); - printk(KERN_INFO "Mapping aperture over %d KB of RAM @ %lx\n", - aper_size >> 10, addr); + pr_info("Mapping aperture over RAM [mem %#010lx-%#010lx] (%uKB)\n", + addr, addr + aper_size - 1, aper_size >> 10); register_nosave_region(addr >> PAGE_SHIFT, (addr+aper_size) >> PAGE_SHIFT); @@ -126,10 +127,11 @@ static u32 __init read_agp(int bus, int slot, int func, int cap, u32 *order) u64 aper; u32 old_order; - printk(KERN_INFO "AGP bridge at %02x:%02x:%02x\n", bus, slot, func); + pr_info("pci 0000:%02x:%02x:%02x: AGP bridge\n", bus, slot, func); apsizereg = read_pci_config_16(bus, slot, func, cap + 0x14); if (apsizereg == 0xffffffff) { - printk(KERN_ERR "APSIZE in AGP bridge unreadable\n"); + pr_err("pci 0000:%02x:%02x.%d: APSIZE unreadable\n", + bus, slot, func); return 0; } @@ -153,16 +155,18 @@ static u32 __init read_agp(int bus, int slot, int func, int cap, u32 *order) * On some sick chips, APSIZE is 0. It means it wants 4G * so let double check that order, and lets trust AMD NB settings: */ - printk(KERN_INFO "Aperture from AGP @ %Lx old size %u MB\n", - aper, 32 << old_order); + pr_info("pci 0000:%02x:%02x.%d: AGP aperture [bus addr %#010Lx-%#010Lx] (old size %uMB)\n", + bus, slot, func, aper, aper + (32ULL << (old_order + 20)) - 1, + 32 << old_order); if (aper + (32ULL<<(20 + *order)) > 0x100000000ULL) { - printk(KERN_INFO "Aperture size %u MB (APSIZE %x) is not right, using settings from NB\n", - 32 << *order, apsizereg); + pr_info("pci 0000:%02x:%02x.%d: AGP aperture size %uMB (APSIZE %#x) is not right, using settings from NB\n", + bus, slot, func, 32 << *order, apsizereg); *order = old_order; } - printk(KERN_INFO "Aperture from AGP @ %Lx size %u MB (APSIZE %x)\n", - aper, 32 << *order, apsizereg); + pr_info("pci 0000:%02x:%02x.%d: AGP aperture [bus addr %#010Lx-%#010Lx] (%uMB, APSIZE %#x)\n", + bus, slot, func, aper, aper + (32ULL << (*order + 20)) - 1, + 32 << *order, apsizereg); if (!aperture_valid(aper, (32*1024*1024) << *order, 32<<20)) return 0; @@ -218,7 +222,7 @@ static u32 __init search_agp_bridge(u32 *order, int *valid_agp) } } } - printk(KERN_INFO "No AGP bridge found\n"); + pr_info("No AGP bridge found\n"); return 0; } @@ -310,7 +314,8 @@ void __init early_gart_iommu_check(void) if (e820_any_mapped(aper_base, aper_base + aper_size, E820_RAM)) { /* reserve it, so we can reuse it in second kernel */ - printk(KERN_INFO "update e820 for GART\n"); + pr_info("e820: reserve [mem %#010Lx-%#010Lx] for GART\n", + aper_base, aper_base + aper_size - 1); e820_add_region(aper_base, aper_size, E820_RESERVED); update_e820(); } @@ -354,7 +359,7 @@ int __init gart_iommu_hole_init(void) !early_pci_allowed()) return -ENODEV; - printk(KERN_INFO "Checking aperture...\n"); + pr_info("Checking aperture...\n"); if (!fallback_aper_force) agp_aper_base = search_agp_bridge(&agp_aper_order, &valid_agp); @@ -395,8 +400,9 @@ int __init gart_iommu_hole_init(void) aper_base = read_pci_config(bus, slot, 3, AMD64_GARTAPERTUREBASE) & 0x7fff; aper_base <<= 25; - printk(KERN_INFO "Node %d: aperture @ %Lx size %u MB\n", - node, aper_base, aper_size >> 20); + pr_info("Node %d: aperture [bus addr %#010Lx-%#010Lx] (%uMB)\n", + node, aper_base, aper_base + aper_size - 1, + aper_size >> 20); node++; if (!aperture_valid(aper_base, aper_size, 64<<20)) { @@ -407,9 +413,9 @@ int __init gart_iommu_hole_init(void) if (!no_iommu && max_pfn > MAX_DMA32_PFN && !printed_gart_size_msg) { - printk(KERN_ERR "you are using iommu with agp, but GART size is less than 64M\n"); - printk(KERN_ERR "please increase GART size in your BIOS setup\n"); - printk(KERN_ERR "if BIOS doesn't have that option, contact your HW vendor!\n"); + pr_err("you are using iommu with agp, but GART size is less than 64MB\n"); + pr_err("please increase GART size in your BIOS setup\n"); + pr_err("if BIOS doesn't have that option, contact your HW vendor!\n"); printed_gart_size_msg = 1; } } else { @@ -446,13 +452,10 @@ out: force_iommu || valid_agp || fallback_aper_force) { - printk(KERN_INFO - "Your BIOS doesn't leave a aperture memory hole\n"); - printk(KERN_INFO - "Please enable the IOMMU option in the BIOS setup\n"); - printk(KERN_INFO - "This costs you %d MB of RAM\n", - 32 << fallback_aper_order); + pr_info("Your BIOS doesn't leave a aperture memory hole\n"); + pr_info("Please enable the IOMMU option in the BIOS setup\n"); + pr_info("This costs you %dMB of RAM\n", + 32 << fallback_aper_order); aper_order = fallback_aper_order; aper_alloc = allocate_aperture(); diff --git a/arch/x86/kernel/apic/hw_nmi.c b/arch/x86/kernel/apic/hw_nmi.c index a698d71..eab6704 100644 --- a/arch/x86/kernel/apic/hw_nmi.c +++ b/arch/x86/kernel/apic/hw_nmi.c @@ -57,7 +57,7 @@ void arch_trigger_all_cpu_backtrace(void) } clear_bit(0, &backtrace_flag); - smp_mb__after_clear_bit(); + smp_mb__after_atomic(); } static int __kprobes diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c index 992060e..9d0a979 100644 --- a/arch/x86/kernel/apic/io_apic.c +++ b/arch/x86/kernel/apic/io_apic.c @@ -206,9 +206,6 @@ int __init arch_early_irq_init(void) count = ARRAY_SIZE(irq_cfgx); node = cpu_to_node(0); - /* Make sure the legacy interrupts are marked in the bitmap */ - irq_reserve_irqs(0, legacy_pic->nr_legacy_irqs); - for (i = 0; i < count; i++) { irq_set_chip_data(i, &cfg[i]); zalloc_cpumask_var_node(&cfg[i].domain, GFP_KERNEL, node); @@ -281,18 +278,6 @@ static struct irq_cfg *alloc_irq_and_cfg_at(unsigned int at, int node) return cfg; } -static int alloc_irqs_from(unsigned int from, unsigned int count, int node) -{ - return irq_alloc_descs_from(from, count, node); -} - -static void free_irq_at(unsigned int at, struct irq_cfg *cfg) -{ - free_irq_cfg(at, cfg); - irq_free_desc(at); -} - - struct io_apic { unsigned int index; unsigned int unused[3]; @@ -2916,98 +2901,39 @@ static int __init ioapic_init_ops(void) device_initcall(ioapic_init_ops); /* - * Dynamic irq allocate and deallocation + * Dynamic irq allocate and deallocation. Should be replaced by irq domains! */ -unsigned int __create_irqs(unsigned int from, unsigned int count, int node) +int arch_setup_hwirq(unsigned int irq, int node) { - struct irq_cfg **cfg; + struct irq_cfg *cfg; unsigned long flags; - int irq, i; - - if (from < nr_irqs_gsi) - from = nr_irqs_gsi; + int ret; - cfg = kzalloc_node(count * sizeof(cfg[0]), GFP_KERNEL, node); + cfg = alloc_irq_cfg(irq, node); if (!cfg) - return 0; - - irq = alloc_irqs_from(from, count, node); - if (irq < 0) - goto out_cfgs; - - for (i = 0; i < count; i++) { - cfg[i] = alloc_irq_cfg(irq + i, node); - if (!cfg[i]) - goto out_irqs; - } + return -ENOMEM; raw_spin_lock_irqsave(&vector_lock, flags); - for (i = 0; i < count; i++) - if (__assign_irq_vector(irq + i, cfg[i], apic->target_cpus())) - goto out_vecs; - raw_spin_unlock_irqrestore(&vector_lock, flags); - - for (i = 0; i < count; i++) { - irq_set_chip_data(irq + i, cfg[i]); - irq_clear_status_flags(irq + i, IRQ_NOREQUEST); - } - - kfree(cfg); - return irq; - -out_vecs: - for (i--; i >= 0; i--) - __clear_irq_vector(irq + i, cfg[i]); + ret = __assign_irq_vector(irq, cfg, apic->target_cpus()); raw_spin_unlock_irqrestore(&vector_lock, flags); -out_irqs: - for (i = 0; i < count; i++) - free_irq_at(irq + i, cfg[i]); -out_cfgs: - kfree(cfg); - return 0; -} -unsigned int create_irq_nr(unsigned int from, int node) -{ - return __create_irqs(from, 1, node); -} - -int create_irq(void) -{ - int node = cpu_to_node(0); - unsigned int irq_want; - int irq; - - irq_want = nr_irqs_gsi; - irq = create_irq_nr(irq_want, node); - - if (irq == 0) - irq = -1; - - return irq; + if (!ret) + irq_set_chip_data(irq, cfg); + else + free_irq_cfg(irq, cfg); + return ret; } -void destroy_irq(unsigned int irq) +void arch_teardown_hwirq(unsigned int irq) { struct irq_cfg *cfg = irq_get_chip_data(irq); unsigned long flags; - irq_set_status_flags(irq, IRQ_NOREQUEST|IRQ_NOPROBE); - free_remapped_irq(irq); - raw_spin_lock_irqsave(&vector_lock, flags); __clear_irq_vector(irq, cfg); raw_spin_unlock_irqrestore(&vector_lock, flags); - free_irq_at(irq, cfg); -} - -void destroy_irqs(unsigned int irq, unsigned int count) -{ - unsigned int i; - - for (i = 0; i < count; i++) - destroy_irq(irq + i); + free_irq_cfg(irq, cfg); } /* @@ -3136,8 +3062,8 @@ int setup_msi_irq(struct pci_dev *dev, struct msi_desc *msidesc, int native_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) { - unsigned int irq, irq_want; struct msi_desc *msidesc; + unsigned int irq; int node, ret; /* Multiple MSI vectors only supported with interrupt remapping */ @@ -3145,28 +3071,25 @@ int native_setup_msi_irqs(struct pci_dev *dev, int nvec, int type) return 1; node = dev_to_node(&dev->dev); - irq_want = nr_irqs_gsi; + list_for_each_entry(msidesc, &dev->msi_list, list) { - irq = create_irq_nr(irq_want, node); - if (irq == 0) + irq = irq_alloc_hwirq(node); + if (!irq) return -ENOSPC; - irq_want = irq + 1; - ret = setup_msi_irq(dev, msidesc, irq, 0); - if (ret < 0) - goto error; + if (ret < 0) { + irq_free_hwirq(irq); + return ret; + } + } return 0; - -error: - destroy_irq(irq); - return ret; } void native_teardown_msi_irq(unsigned int irq) { - destroy_irq(irq); + irq_free_hwirq(irq); } #ifdef CONFIG_DMAR_TABLE @@ -3420,11 +3343,6 @@ static void __init probe_nr_irqs_gsi(void) printk(KERN_DEBUG "nr_irqs_gsi: %d\n", nr_irqs_gsi); } -int get_nr_irqs_gsi(void) -{ - return nr_irqs_gsi; -} - unsigned int arch_dynirq_lower_bound(unsigned int from) { return from < nr_irqs_gsi ? nr_irqs_gsi : from; diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c index 7834389..293b41d 100644 --- a/arch/x86/kernel/apic/x2apic_uv_x.c +++ b/arch/x86/kernel/apic/x2apic_uv_x.c @@ -5,7 +5,7 @@ * * SGI UV APIC functions (note: not an Intel compatible APIC) * - * Copyright (C) 2007-2013 Silicon Graphics, Inc. All rights reserved. + * Copyright (C) 2007-2014 Silicon Graphics, Inc. All rights reserved. */ #include <linux/cpumask.h> #include <linux/hardirq.h> @@ -440,6 +440,20 @@ static __initdata struct redir_addr redir_addrs[] = { {UVH_RH_GAM_ALIAS210_REDIRECT_CONFIG_2_MMR, UVH_RH_GAM_ALIAS210_OVERLAY_CONFIG_2_MMR}, }; +static unsigned char get_n_lshift(int m_val) +{ + union uv3h_gr0_gam_gr_config_u m_gr_config; + + if (is_uv1_hub()) + return m_val; + + if (is_uv2_hub()) + return m_val == 40 ? 40 : 39; + + m_gr_config.v = uv_read_local_mmr(UV3H_GR0_GAM_GR_CONFIG); + return m_gr_config.s3.m_skt; +} + static __init void get_lowmem_redirect(unsigned long *base, unsigned long *size) { union uvh_rh_gam_alias210_overlay_config_2_mmr_u alias; @@ -849,6 +863,7 @@ void __init uv_system_init(void) int gnode_extra, min_pnode = 999999, max_pnode = -1; unsigned long mmr_base, present, paddr; unsigned short pnode_mask; + unsigned char n_lshift; char *hub = (is_uv1_hub() ? "UV1" : (is_uv2_hub() ? "UV2" : "UV3")); @@ -860,6 +875,7 @@ void __init uv_system_init(void) m_val = m_n_config.s.m_skt; n_val = m_n_config.s.n_skt; pnode_mask = (1 << n_val) - 1; + n_lshift = get_n_lshift(m_val); mmr_base = uv_read_local_mmr(UVH_RH_GAM_MMR_OVERLAY_CONFIG_MMR) & ~UV_MMR_ENABLE; @@ -867,8 +883,9 @@ void __init uv_system_init(void) node_id.v = uv_read_local_mmr(UVH_NODE_ID); gnode_extra = (node_id.s.node_id & ~((1 << n_val) - 1)) >> 1; gnode_upper = ((unsigned long)gnode_extra << m_val); - pr_info("UV: N:%d M:%d pnode_mask:0x%x gnode_upper/extra:0x%lx/0x%x\n", - n_val, m_val, pnode_mask, gnode_upper, gnode_extra); + pr_info("UV: N:%d M:%d pnode_mask:0x%x gnode_upper/extra:0x%lx/0x%x n_lshift 0x%x\n", + n_val, m_val, pnode_mask, gnode_upper, gnode_extra, + n_lshift); pr_info("UV: global MMR base 0x%lx\n", mmr_base); @@ -935,8 +952,7 @@ void __init uv_system_init(void) uv_cpu_hub_info(cpu)->hub_revision = uv_hub_info->hub_revision; uv_cpu_hub_info(cpu)->m_shift = 64 - m_val; - uv_cpu_hub_info(cpu)->n_lshift = is_uv2_1_hub() ? - (m_val == 40 ? 40 : 39) : m_val; + uv_cpu_hub_info(cpu)->n_lshift = n_lshift; pnode = uv_apicid_to_pnode(apicid); blade = boot_pnode_to_blade(pnode); diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c index 3ab0343..f3a1f04 100644 --- a/arch/x86/kernel/apm_32.c +++ b/arch/x86/kernel/apm_32.c @@ -844,21 +844,10 @@ static int apm_do_idle(void) int polling; int err = 0; - polling = !!(current_thread_info()->status & TS_POLLING); - if (polling) { - current_thread_info()->status &= ~TS_POLLING; - /* - * TS_POLLING-cleared state must be visible before we - * test NEED_RESCHED: - */ - smp_mb(); - } if (!need_resched()) { idled = 1; ret = apm_bios_call_simple(APM_FUNC_IDLE, 0, 0, &eax, &err); } - if (polling) - current_thread_info()->status |= TS_POLLING; if (!idled) return 0; diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c index 68317c8..bb92f38 100644 --- a/arch/x86/kernel/cpu/mcheck/mce.c +++ b/arch/x86/kernel/cpu/mcheck/mce.c @@ -60,8 +60,6 @@ static DEFINE_MUTEX(mce_chrdev_read_mutex); #define SPINUNIT 100 /* 100ns */ -atomic_t mce_entry; - DEFINE_PER_CPU(unsigned, mce_exception_count); struct mce_bank *mce_banks __read_mostly; @@ -704,8 +702,7 @@ static int mce_timed_out(u64 *t) if (!mca_cfg.monarch_timeout) goto out; if ((s64)*t < SPINUNIT) { - /* CHECKME: Make panic default for 1 too? */ - if (mca_cfg.tolerant < 1) + if (mca_cfg.tolerant <= 1) mce_panic("Timeout synchronizing machine check over CPUs", NULL, NULL); cpu_missing = 1; @@ -1041,8 +1038,6 @@ void do_machine_check(struct pt_regs *regs, long error_code) DECLARE_BITMAP(valid_banks, MAX_NR_BANKS); char *msg = "Unknown"; - atomic_inc(&mce_entry); - this_cpu_inc(mce_exception_count); if (!cfg->banks) @@ -1172,7 +1167,6 @@ void do_machine_check(struct pt_regs *regs, long error_code) mce_report_event(regs); mce_wrmsrl(MSR_IA32_MCG_STATUS, 0); out: - atomic_dec(&mce_entry); sync_core(); } EXPORT_SYMBOL_GPL(do_machine_check); @@ -2437,32 +2431,65 @@ static __init int mcheck_init_device(void) int err; int i = 0; - if (!mce_available(&boot_cpu_data)) - return -EIO; + if (!mce_available(&boot_cpu_data)) { + err = -EIO; + goto err_out; + } - zalloc_cpumask_var(&mce_device_initialized, GFP_KERNEL); + if (!zalloc_cpumask_var(&mce_device_initialized, GFP_KERNEL)) { + err = -ENOMEM; + goto err_out; + } mce_init_banks(); err = subsys_system_register(&mce_subsys, NULL); if (err) - return err; + goto err_out_mem; cpu_notifier_register_begin(); for_each_online_cpu(i) { err = mce_device_create(i); if (err) { cpu_notifier_register_done(); - return err; + goto err_device_create; } } - register_syscore_ops(&mce_syscore_ops); __register_hotcpu_notifier(&mce_cpu_notifier); cpu_notifier_register_done(); + register_syscore_ops(&mce_syscore_ops); + /* register character device /dev/mcelog */ - misc_register(&mce_chrdev_device); + err = misc_register(&mce_chrdev_device); + if (err) + goto err_register; + + return 0; + +err_register: + unregister_syscore_ops(&mce_syscore_ops); + + cpu_notifier_register_begin(); + __unregister_hotcpu_notifier(&mce_cpu_notifier); + cpu_notifier_register_done(); + +err_device_create: + /* + * We didn't keep track of which devices were created above, but + * even if we had, the set of online cpus might have changed. + * Play safe and remove for every possible cpu, since + * mce_device_remove() will do the right thing. + */ + for_each_possible_cpu(i) + mce_device_remove(i); + +err_out_mem: + free_cpumask_var(mce_device_initialized); + +err_out: + pr_err("Unable to init device /dev/mcelog (rc: %d)\n", err); return err; } diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c index 15c9876..dd9d619 100644 --- a/arch/x86/kernel/cpu/microcode/core.c +++ b/arch/x86/kernel/cpu/microcode/core.c @@ -97,6 +97,9 @@ MODULE_LICENSE("GPL"); static struct microcode_ops *microcode_ops; +bool dis_ucode_ldr; +module_param(dis_ucode_ldr, bool, 0); + /* * Synchronization. * @@ -546,6 +549,9 @@ static int __init microcode_init(void) struct cpuinfo_x86 *c = &cpu_data(0); int error; + if (dis_ucode_ldr) + return 0; + if (c->x86_vendor == X86_VENDOR_INTEL) microcode_ops = init_intel_microcode(); else if (c->x86_vendor == X86_VENDOR_AMD) diff --git a/arch/x86/kernel/cpu/microcode/core_early.c b/arch/x86/kernel/cpu/microcode/core_early.c index be7f851..5f28a64 100644 --- a/arch/x86/kernel/cpu/microcode/core_early.c +++ b/arch/x86/kernel/cpu/microcode/core_early.c @@ -17,9 +17,11 @@ * 2 of the License, or (at your option) any later version. */ #include <linux/module.h> +#include <asm/microcode.h> #include <asm/microcode_intel.h> #include <asm/microcode_amd.h> #include <asm/processor.h> +#include <asm/cmdline.h> #define QCHAR(a, b, c, d) ((a) + ((b) << 8) + ((c) << 16) + ((d) << 24)) #define CPUID_INTEL1 QCHAR('G', 'e', 'n', 'u') @@ -72,10 +74,33 @@ static int x86_family(void) return x86; } +static bool __init check_loader_disabled_bsp(void) +{ +#ifdef CONFIG_X86_32 + const char *cmdline = (const char *)__pa_nodebug(boot_command_line); + const char *opt = "dis_ucode_ldr"; + const char *option = (const char *)__pa_nodebug(opt); + bool *res = (bool *)__pa_nodebug(&dis_ucode_ldr); + +#else /* CONFIG_X86_64 */ + const char *cmdline = boot_command_line; + const char *option = "dis_ucode_ldr"; + bool *res = &dis_ucode_ldr; +#endif + + if (cmdline_find_option_bool(cmdline, option)) + *res = true; + + return *res; +} + void __init load_ucode_bsp(void) { int vendor, x86; + if (check_loader_disabled_bsp()) + return; + if (!have_cpuid_p()) return; @@ -96,10 +121,22 @@ void __init load_ucode_bsp(void) } } +static bool check_loader_disabled_ap(void) +{ +#ifdef CONFIG_X86_32 + return __pa_nodebug(dis_ucode_ldr); +#else + return dis_ucode_ldr; +#endif +} + void load_ucode_ap(void) { int vendor, x86; + if (check_loader_disabled_ap()) + return; + if (!have_cpuid_p()) return; diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c index ae407f7..89f3b7c 100644 --- a/arch/x86/kernel/cpu/perf_event.c +++ b/arch/x86/kernel/cpu/perf_event.c @@ -721,6 +721,7 @@ int perf_assign_events(struct perf_event **events, int n, return sched.state.unassigned; } +EXPORT_SYMBOL_GPL(perf_assign_events); int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign) { diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c index aa333d9..adb02aa 100644 --- a/arch/x86/kernel/cpu/perf_event_intel.c +++ b/arch/x86/kernel/cpu/perf_event_intel.c @@ -169,7 +169,6 @@ static struct event_constraint intel_slm_event_constraints[] __read_mostly = { FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* INST_RETIRED.ANY */ FIXED_EVENT_CONSTRAINT(0x003c, 1), /* CPU_CLK_UNHALTED.CORE */ - FIXED_EVENT_CONSTRAINT(0x013c, 2), /* CPU_CLK_UNHALTED.REF */ FIXED_EVENT_CONSTRAINT(0x0300, 2), /* pseudo CPU_CLK_UNHALTED.REF */ EVENT_CONSTRAINT_END }; diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c index ae96cfa..980970c 100644 --- a/arch/x86/kernel/cpu/perf_event_intel_ds.c +++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c @@ -108,15 +108,31 @@ static u64 precise_store_data(u64 status) return val; } -static u64 precise_store_data_hsw(u64 status) +static u64 precise_store_data_hsw(struct perf_event *event, u64 status) { union perf_mem_data_src dse; + u64 cfg = event->hw.config & INTEL_ARCH_EVENT_MASK; dse.val = 0; dse.mem_op = PERF_MEM_OP_STORE; dse.mem_lvl = PERF_MEM_LVL_NA; + + /* + * L1 info only valid for following events: + * + * MEM_UOPS_RETIRED.STLB_MISS_STORES + * MEM_UOPS_RETIRED.LOCK_STORES + * MEM_UOPS_RETIRED.SPLIT_STORES + * MEM_UOPS_RETIRED.ALL_STORES + */ + if (cfg != 0x12d0 && cfg != 0x22d0 && cfg != 0x42d0 && cfg != 0x82d0) + return dse.mem_lvl; + if (status & 1) - dse.mem_lvl = PERF_MEM_LVL_L1; + dse.mem_lvl = PERF_MEM_LVL_L1 | PERF_MEM_LVL_HIT; + else + dse.mem_lvl = PERF_MEM_LVL_L1 | PERF_MEM_LVL_MISS; + /* Nothing else supported. Sorry. */ return dse.val; } @@ -887,7 +903,7 @@ static void __intel_pmu_pebs_event(struct perf_event *event, data.data_src.val = load_latency_data(pebs->dse); else if (event->hw.flags & PERF_X86_EVENT_PEBS_ST_HSW) data.data_src.val = - precise_store_data_hsw(pebs->dse); + precise_store_data_hsw(event, pebs->dse); else data.data_src.val = precise_store_data(pebs->dse); } diff --git a/arch/x86/kernel/devicetree.c b/arch/x86/kernel/devicetree.c index d35078e..7db54b5 100644 --- a/arch/x86/kernel/devicetree.c +++ b/arch/x86/kernel/devicetree.c @@ -206,23 +206,21 @@ static void __init dtb_apic_setup(void) static void __init x86_flattree_get_config(void) { u32 size, map_len; - struct boot_param_header *dt; + void *dt; if (!initial_dtb) return; - map_len = max(PAGE_SIZE - (initial_dtb & ~PAGE_MASK), - (u64)sizeof(struct boot_param_header)); + map_len = max(PAGE_SIZE - (initial_dtb & ~PAGE_MASK), (u64)128); - dt = early_memremap(initial_dtb, map_len); - size = be32_to_cpu(dt->totalsize); + initial_boot_params = dt = early_memremap(initial_dtb, map_len); + size = of_get_flat_dt_size(); if (map_len < size) { early_iounmap(dt, map_len); - dt = early_memremap(initial_dtb, size); + initial_boot_params = dt = early_memremap(initial_dtb, size); map_len = size; } - initial_boot_params = dt; unflatten_and_copy_device_tree(); early_iounmap(dt, map_len); } diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S index da0b9bd..9698798 100644 --- a/arch/x86/kernel/entry_64.S +++ b/arch/x86/kernel/entry_64.S @@ -36,7 +36,7 @@ * - FIXUP_TOP_OF_STACK/RESTORE_TOP_OF_STACK - Fix up the hardware stack * frame that is otherwise undefined after a SYSCALL * - TRACE_IRQ_* - Trace hard interrupt state for lock debugging. - * - errorentry/paranoidentry/zeroentry - Define exception entry points. + * - idtentry - Define exception entry points. */ #include <linux/linkage.h> @@ -1276,125 +1276,100 @@ apicinterrupt IRQ_WORK_VECTOR \ /* * Exception entry points. */ -.macro zeroentry sym do_sym -ENTRY(\sym) - INTR_FRAME - ASM_CLAC - PARAVIRT_ADJUST_EXCEPTION_FRAME - pushq_cfi $-1 /* ORIG_RAX: no syscall to restart */ - subq $ORIG_RAX-R15, %rsp - CFI_ADJUST_CFA_OFFSET ORIG_RAX-R15 - call error_entry - DEFAULT_FRAME 0 - movq %rsp,%rdi /* pt_regs pointer */ - xorl %esi,%esi /* no error code */ - call \do_sym - jmp error_exit /* %ebx: no swapgs flag */ - CFI_ENDPROC -END(\sym) -.endm +#define INIT_TSS_IST(x) PER_CPU_VAR(init_tss) + (TSS_ist + ((x) - 1) * 8) -.macro paranoidzeroentry sym do_sym +.macro idtentry sym do_sym has_error_code:req paranoid=0 shift_ist=-1 ENTRY(\sym) - INTR_FRAME - ASM_CLAC - PARAVIRT_ADJUST_EXCEPTION_FRAME - pushq_cfi $-1 /* ORIG_RAX: no syscall to restart */ - subq $ORIG_RAX-R15, %rsp - CFI_ADJUST_CFA_OFFSET ORIG_RAX-R15 - call save_paranoid - TRACE_IRQS_OFF - movq %rsp,%rdi /* pt_regs pointer */ - xorl %esi,%esi /* no error code */ - call \do_sym - jmp paranoid_exit /* %ebx: no swapgs flag */ - CFI_ENDPROC -END(\sym) -.endm + /* Sanity check */ + .if \shift_ist != -1 && \paranoid == 0 + .error "using shift_ist requires paranoid=1" + .endif -#define INIT_TSS_IST(x) PER_CPU_VAR(init_tss) + (TSS_ist + ((x) - 1) * 8) -.macro paranoidzeroentry_ist sym do_sym ist -ENTRY(\sym) + .if \has_error_code + XCPT_FRAME + .else INTR_FRAME - ASM_CLAC - PARAVIRT_ADJUST_EXCEPTION_FRAME - pushq_cfi $-1 /* ORIG_RAX: no syscall to restart */ - subq $ORIG_RAX-R15, %rsp - CFI_ADJUST_CFA_OFFSET ORIG_RAX-R15 - call save_paranoid - TRACE_IRQS_OFF_DEBUG - movq %rsp,%rdi /* pt_regs pointer */ - xorl %esi,%esi /* no error code */ - subq $EXCEPTION_STKSZ, INIT_TSS_IST(\ist) - call \do_sym - addq $EXCEPTION_STKSZ, INIT_TSS_IST(\ist) - jmp paranoid_exit /* %ebx: no swapgs flag */ - CFI_ENDPROC -END(\sym) -.endm + .endif -.macro errorentry sym do_sym -ENTRY(\sym) - XCPT_FRAME ASM_CLAC PARAVIRT_ADJUST_EXCEPTION_FRAME + + .ifeq \has_error_code + pushq_cfi $-1 /* ORIG_RAX: no syscall to restart */ + .endif + subq $ORIG_RAX-R15, %rsp CFI_ADJUST_CFA_OFFSET ORIG_RAX-R15 + + .if \paranoid + call save_paranoid + .else call error_entry + .endif + DEFAULT_FRAME 0 + + .if \paranoid + .if \shift_ist != -1 + TRACE_IRQS_OFF_DEBUG /* reload IDT in case of recursion */ + .else + TRACE_IRQS_OFF + .endif + .endif + movq %rsp,%rdi /* pt_regs pointer */ + + .if \has_error_code movq ORIG_RAX(%rsp),%rsi /* get error code */ movq $-1,ORIG_RAX(%rsp) /* no syscall to restart */ + .else + xorl %esi,%esi /* no error code */ + .endif + + .if \shift_ist != -1 + subq $EXCEPTION_STKSZ, INIT_TSS_IST(\shift_ist) + .endif + call \do_sym + + .if \shift_ist != -1 + addq $EXCEPTION_STKSZ, INIT_TSS_IST(\shift_ist) + .endif + + .if \paranoid + jmp paranoid_exit /* %ebx: no swapgs flag */ + .else jmp error_exit /* %ebx: no swapgs flag */ + .endif + CFI_ENDPROC END(\sym) .endm #ifdef CONFIG_TRACING -.macro trace_errorentry sym do_sym -errorentry trace(\sym) trace(\do_sym) -errorentry \sym \do_sym +.macro trace_idtentry sym do_sym has_error_code:req +idtentry trace(\sym) trace(\do_sym) has_error_code=\has_error_code +idtentry \sym \do_sym has_error_code=\has_error_code .endm #else -.macro trace_errorentry sym do_sym -errorentry \sym \do_sym +.macro trace_idtentry sym do_sym has_error_code:req +idtentry \sym \do_sym has_error_code=\has_error_code .endm #endif - /* error code is on the stack already */ -.macro paranoiderrorentry sym do_sym -ENTRY(\sym) - XCPT_FRAME - ASM_CLAC - PARAVIRT_ADJUST_EXCEPTION_FRAME - subq $ORIG_RAX-R15, %rsp - CFI_ADJUST_CFA_OFFSET ORIG_RAX-R15 - call save_paranoid - DEFAULT_FRAME 0 - TRACE_IRQS_OFF - movq %rsp,%rdi /* pt_regs pointer */ - movq ORIG_RAX(%rsp),%rsi /* get error code */ - movq $-1,ORIG_RAX(%rsp) /* no syscall to restart */ - call \do_sym - jmp paranoid_exit /* %ebx: no swapgs flag */ - CFI_ENDPROC -END(\sym) -.endm - -zeroentry divide_error do_divide_error -zeroentry overflow do_overflow -zeroentry bounds do_bounds -zeroentry invalid_op do_invalid_op -zeroentry device_not_available do_device_not_available -paranoiderrorentry double_fault __do_double_fault -zeroentry coprocessor_segment_overrun do_coprocessor_segment_overrun -errorentry invalid_TSS do_invalid_TSS -errorentry segment_not_present do_segment_not_present -zeroentry spurious_interrupt_bug do_spurious_interrupt_bug -zeroentry coprocessor_error do_coprocessor_error -errorentry alignment_check do_alignment_check -zeroentry simd_coprocessor_error do_simd_coprocessor_error +idtentry divide_error do_divide_error has_error_code=0 +idtentry overflow do_overflow has_error_code=0 +idtentry bounds do_bounds has_error_code=0 +idtentry invalid_op do_invalid_op has_error_code=0 +idtentry device_not_available do_device_not_available has_error_code=0 +idtentry double_fault __do_double_fault has_error_code=1 paranoid=1 +idtentry coprocessor_segment_overrun do_coprocessor_segment_overrun has_error_code=0 +idtentry invalid_TSS do_invalid_TSS has_error_code=1 +idtentry segment_not_present do_segment_not_present has_error_code=1 +idtentry spurious_interrupt_bug do_spurious_interrupt_bug has_error_code=0 +idtentry coprocessor_error do_coprocessor_error has_error_code=0 +idtentry alignment_check do_alignment_check has_error_code=1 +idtentry simd_coprocessor_error do_simd_coprocessor_error has_error_code=0 /* Reload gs selector with exception handling */ @@ -1444,7 +1419,7 @@ ENTRY(do_softirq_own_stack) END(do_softirq_own_stack) #ifdef CONFIG_XEN -zeroentry xen_hypervisor_callback xen_do_hypervisor_callback +idtentry xen_hypervisor_callback xen_do_hypervisor_callback has_error_code=0 /* * A note on the "critical region" in our callback handler. @@ -1555,21 +1530,21 @@ apicinterrupt3 HYPERVISOR_CALLBACK_VECTOR \ */ .pushsection .kprobes.text, "ax" -paranoidzeroentry_ist debug do_debug DEBUG_STACK -paranoidzeroentry_ist int3 do_int3 DEBUG_STACK -paranoiderrorentry stack_segment do_stack_segment +idtentry debug do_debug has_error_code=0 paranoid=1 shift_ist=DEBUG_STACK +idtentry int3 do_int3 has_error_code=0 paranoid=1 shift_ist=DEBUG_STACK +idtentry stack_segment do_stack_segment has_error_code=1 paranoid=1 #ifdef CONFIG_XEN -zeroentry xen_debug do_debug -zeroentry xen_int3 do_int3 -errorentry xen_stack_segment do_stack_segment +idtentry xen_debug do_debug has_error_code=0 +idtentry xen_int3 do_int3 has_error_code=0 +idtentry xen_stack_segment do_stack_segment has_error_code=1 #endif -errorentry general_protection do_general_protection -trace_errorentry page_fault do_page_fault +idtentry general_protection do_general_protection has_error_code=1 +trace_idtentry page_fault do_page_fault has_error_code=1 #ifdef CONFIG_KVM_GUEST -errorentry async_page_fault do_async_page_fault +idtentry async_page_fault do_async_page_fault has_error_code=1 #endif #ifdef CONFIG_X86_MCE -paranoidzeroentry machine_check *machine_check_vector(%rip) +idtentry machine_check has_error_code=0 paranoid=1 do_sym=*machine_check_vector(%rip) #endif /* diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c index 068054f..eda1a86 100644 --- a/arch/x86/kernel/head64.c +++ b/arch/x86/kernel/head64.c @@ -172,7 +172,7 @@ asmlinkage __visible void __init x86_64_start_kernel(char * real_mode_data) */ load_ucode_bsp(); - if (console_loglevel == 10) + if (console_loglevel >= CONSOLE_LOGLEVEL_DEBUG) early_printk("Kernel alive\n"); clear_page(init_level4_pgt); diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c index 4177bfb..5f5a147 100644 --- a/arch/x86/kernel/hpet.c +++ b/arch/x86/kernel/hpet.c @@ -479,7 +479,7 @@ static int hpet_msi_next_event(unsigned long delta, static int hpet_setup_msi_irq(unsigned int irq) { if (x86_msi.setup_hpet_msi(irq, hpet_blockid)) { - destroy_irq(irq); + irq_free_hwirq(irq); return -EINVAL; } return 0; @@ -487,9 +487,8 @@ static int hpet_setup_msi_irq(unsigned int irq) static int hpet_assign_irq(struct hpet_dev *dev) { - unsigned int irq; + unsigned int irq = irq_alloc_hwirq(-1); - irq = create_irq_nr(0, -1); if (!irq) return -EINVAL; diff --git a/arch/x86/kernel/iosf_mbi.c b/arch/x86/kernel/iosf_mbi.c index c3aae66..d30acdc 100644 --- a/arch/x86/kernel/iosf_mbi.c +++ b/arch/x86/kernel/iosf_mbi.c @@ -25,6 +25,9 @@ #include <asm/iosf_mbi.h> +#define PCI_DEVICE_ID_BAYTRAIL 0x0F00 +#define PCI_DEVICE_ID_QUARK_X1000 0x0958 + static DEFINE_SPINLOCK(iosf_mbi_lock); static inline u32 iosf_mbi_form_mcr(u8 op, u8 port, u8 offset) @@ -177,6 +180,13 @@ int iosf_mbi_modify(u8 port, u8 opcode, u32 offset, u32 mdr, u32 mask) } EXPORT_SYMBOL(iosf_mbi_modify); +bool iosf_mbi_available(void) +{ + /* Mbi isn't hot-pluggable. No remove routine is provided */ + return mbi_pdev; +} +EXPORT_SYMBOL(iosf_mbi_available); + static int iosf_mbi_probe(struct pci_dev *pdev, const struct pci_device_id *unused) { @@ -193,7 +203,8 @@ static int iosf_mbi_probe(struct pci_dev *pdev, } static DEFINE_PCI_DEVICE_TABLE(iosf_mbi_pci_ids) = { - { PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x0F00) }, + { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_BAYTRAIL) }, + { PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_QUARK_X1000) }, { 0, }, }; MODULE_DEVICE_TABLE(pci, iosf_mbi_pci_ids); diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c index 0331cb3..7e97371 100644 --- a/arch/x86/kernel/kvm.c +++ b/arch/x86/kernel/kvm.c @@ -259,7 +259,7 @@ do_async_page_fault(struct pt_regs *regs, unsigned long error_code) switch (kvm_read_and_reset_pf_reason()) { default: - do_page_fault(regs, error_code); + trace_do_page_fault(regs, error_code); break; case KVM_PV_REASON_PAGE_NOT_PRESENT: /* page is swapped out by the host. */ diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c index f7d0672..a25e202 100644 --- a/arch/x86/kernel/pci-dma.c +++ b/arch/x86/kernel/pci-dma.c @@ -97,12 +97,17 @@ void *dma_generic_alloc_coherent(struct device *dev, size_t size, dma_mask = dma_alloc_coherent_mask(dev, flag); - flag |= __GFP_ZERO; + flag &= ~__GFP_ZERO; again: page = NULL; /* CMA can be used only in the context which permits sleeping */ - if (flag & __GFP_WAIT) + if (flag & __GFP_WAIT) { page = dma_alloc_from_contiguous(dev, count, get_order(size)); + if (page && page_to_phys(page) + size > dma_mask) { + dma_release_from_contiguous(dev, page, count); + page = NULL; + } + } /* fallback */ if (!page) page = alloc_pages_node(dev_to_node(dev), flag, get_order(size)); @@ -120,7 +125,7 @@ again: return NULL; } - + memset(page_address(page), 0, size); *dma_addr = addr; return page_address(page); } diff --git a/arch/x86/kernel/pci-swiotlb.c b/arch/x86/kernel/pci-swiotlb.c index 6c483ba..77dd0ad 100644 --- a/arch/x86/kernel/pci-swiotlb.c +++ b/arch/x86/kernel/pci-swiotlb.c @@ -14,7 +14,7 @@ #include <asm/iommu_table.h> int swiotlb __read_mostly; -static void *x86_swiotlb_alloc_coherent(struct device *hwdev, size_t size, +void *x86_swiotlb_alloc_coherent(struct device *hwdev, size_t size, dma_addr_t *dma_handle, gfp_t flags, struct dma_attrs *attrs) { @@ -28,11 +28,14 @@ static void *x86_swiotlb_alloc_coherent(struct device *hwdev, size_t size, return swiotlb_alloc_coherent(hwdev, size, dma_handle, flags); } -static void x86_swiotlb_free_coherent(struct device *dev, size_t size, +void x86_swiotlb_free_coherent(struct device *dev, size_t size, void *vaddr, dma_addr_t dma_addr, struct dma_attrs *attrs) { - swiotlb_free_coherent(dev, size, vaddr, dma_addr); + if (is_swiotlb_buffer(dma_to_phys(dev, dma_addr))) + swiotlb_free_coherent(dev, size, vaddr, dma_addr); + else + dma_generic_free_coherent(dev, size, vaddr, dma_addr, attrs); } static struct dma_map_ops swiotlb_dma_ops = { diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index 09c76d2..78a0e62 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -1119,7 +1119,7 @@ void __init setup_arch(char **cmdline_p) setup_real_mode(); memblock_set_current_limit(get_max_mapped()); - dma_contiguous_reserve(0); + dma_contiguous_reserve(max_pfn_mapped << PAGE_SHIFT); /* * NOTE: On x86-32, only from this point on, fixmaps are ready for use. diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c index 2ed8459..ace2291 100644 --- a/arch/x86/kernel/uprobes.c +++ b/arch/x86/kernel/uprobes.c @@ -53,7 +53,7 @@ #define OPCODE1(insn) ((insn)->opcode.bytes[0]) #define OPCODE2(insn) ((insn)->opcode.bytes[1]) #define OPCODE3(insn) ((insn)->opcode.bytes[2]) -#define MODRM_REG(insn) X86_MODRM_REG(insn->modrm.value) +#define MODRM_REG(insn) X86_MODRM_REG((insn)->modrm.value) #define W(row, b0, b1, b2, b3, b4, b5, b6, b7, b8, b9, ba, bb, bc, bd, be, bf)\ (((b0##UL << 0x0)|(b1##UL << 0x1)|(b2##UL << 0x2)|(b3##UL << 0x3) | \ @@ -229,63 +229,6 @@ static int validate_insn_32bits(struct arch_uprobe *auprobe, struct insn *insn) return -ENOTSUPP; } -/* - * Figure out which fixups arch_uprobe_post_xol() will need to perform, and - * annotate arch_uprobe->fixups accordingly. To start with, - * arch_uprobe->fixups is either zero or it reflects rip-related fixups. - */ -static void prepare_fixups(struct arch_uprobe *auprobe, struct insn *insn) -{ - bool fix_ip = true, fix_call = false; /* defaults */ - int reg; - - insn_get_opcode(insn); /* should be a nop */ - - switch (OPCODE1(insn)) { - case 0x9d: - /* popf */ - auprobe->fixups |= UPROBE_FIX_SETF; - break; - case 0xc3: /* ret/lret */ - case 0xcb: - case 0xc2: - case 0xca: - /* ip is correct */ - fix_ip = false; - break; - case 0xe8: /* call relative - Fix return addr */ - fix_call = true; - break; - case 0x9a: /* call absolute - Fix return addr, not ip */ - fix_call = true; - fix_ip = false; - break; - case 0xff: - insn_get_modrm(insn); - reg = MODRM_REG(insn); - if (reg == 2 || reg == 3) { - /* call or lcall, indirect */ - /* Fix return addr; ip is correct. */ - fix_call = true; - fix_ip = false; - } else if (reg == 4 || reg == 5) { - /* jmp or ljmp, indirect */ - /* ip is correct. */ - fix_ip = false; - } - break; - case 0xea: /* jmp absolute -- ip is correct */ - fix_ip = false; - break; - default: - break; - } - if (fix_ip) - auprobe->fixups |= UPROBE_FIX_IP; - if (fix_call) - auprobe->fixups |= UPROBE_FIX_CALL; -} - #ifdef CONFIG_X86_64 /* * If arch_uprobe->insn doesn't use rip-relative addressing, return @@ -310,15 +253,11 @@ static void prepare_fixups(struct arch_uprobe *auprobe, struct insn *insn) * - The displacement is always 4 bytes. */ static void -handle_riprel_insn(struct arch_uprobe *auprobe, struct mm_struct *mm, struct insn *insn) +handle_riprel_insn(struct arch_uprobe *auprobe, struct insn *insn) { u8 *cursor; u8 reg; - if (mm->context.ia32_compat) - return; - - auprobe->rip_rela_target_address = 0x0; if (!insn_rip_relative(insn)) return; @@ -372,7 +311,48 @@ handle_riprel_insn(struct arch_uprobe *auprobe, struct mm_struct *mm, struct ins cursor++; memmove(cursor, cursor + insn->displacement.nbytes, insn->immediate.nbytes); } - return; +} + +/* + * If we're emulating a rip-relative instruction, save the contents + * of the scratch register and store the target address in that register. + */ +static void +pre_xol_rip_insn(struct arch_uprobe *auprobe, struct pt_regs *regs, + struct arch_uprobe_task *autask) +{ + if (auprobe->fixups & UPROBE_FIX_RIP_AX) { + autask->saved_scratch_register = regs->ax; + regs->ax = current->utask->vaddr; + regs->ax += auprobe->rip_rela_target_address; + } else if (auprobe->fixups & UPROBE_FIX_RIP_CX) { + autask->saved_scratch_register = regs->cx; + regs->cx = current->utask->vaddr; + regs->cx += auprobe->rip_rela_target_address; + } +} + +static void +handle_riprel_post_xol(struct arch_uprobe *auprobe, struct pt_regs *regs, long *correction) +{ + if (auprobe->fixups & (UPROBE_FIX_RIP_AX | UPROBE_FIX_RIP_CX)) { + struct arch_uprobe_task *autask; + + autask = ¤t->utask->autask; + if (auprobe->fixups & UPROBE_FIX_RIP_AX) + regs->ax = autask->saved_scratch_register; + else + regs->cx = autask->saved_scratch_register; + + /* + * The original instruction includes a displacement, and so + * is 4 bytes longer than what we've just single-stepped. + * Caller may need to apply other fixups to handle stuff + * like "jmpq *...(%rip)" and "callq *...(%rip)". + */ + if (correction) + *correction += 4; + } } static int validate_insn_64bits(struct arch_uprobe *auprobe, struct insn *insn) @@ -401,9 +381,19 @@ static int validate_insn_bits(struct arch_uprobe *auprobe, struct mm_struct *mm, return validate_insn_64bits(auprobe, insn); } #else /* 32-bit: */ -static void handle_riprel_insn(struct arch_uprobe *auprobe, struct mm_struct *mm, struct insn *insn) +/* + * No RIP-relative addressing on 32-bit + */ +static void handle_riprel_insn(struct arch_uprobe *auprobe, struct insn *insn) +{ +} +static void pre_xol_rip_insn(struct arch_uprobe *auprobe, struct pt_regs *regs, + struct arch_uprobe_task *autask) +{ +} +static void handle_riprel_post_xol(struct arch_uprobe *auprobe, struct pt_regs *regs, + long *correction) { - /* No RIP-relative addressing on 32-bit */ } static int validate_insn_bits(struct arch_uprobe *auprobe, struct mm_struct *mm, struct insn *insn) @@ -412,141 +402,311 @@ static int validate_insn_bits(struct arch_uprobe *auprobe, struct mm_struct *mm, } #endif /* CONFIG_X86_64 */ -/** - * arch_uprobe_analyze_insn - instruction analysis including validity and fixups. - * @mm: the probed address space. - * @arch_uprobe: the probepoint information. - * @addr: virtual address at which to install the probepoint - * Return 0 on success or a -ve number on error. +struct uprobe_xol_ops { + bool (*emulate)(struct arch_uprobe *, struct pt_regs *); + int (*pre_xol)(struct arch_uprobe *, struct pt_regs *); + int (*post_xol)(struct arch_uprobe *, struct pt_regs *); +}; + +static inline int sizeof_long(void) +{ + return is_ia32_task() ? 4 : 8; +} + +static int default_pre_xol_op(struct arch_uprobe *auprobe, struct pt_regs *regs) +{ + pre_xol_rip_insn(auprobe, regs, ¤t->utask->autask); + return 0; +} + +/* + * Adjust the return address pushed by a call insn executed out of line. */ -int arch_uprobe_analyze_insn(struct arch_uprobe *auprobe, struct mm_struct *mm, unsigned long addr) +static int adjust_ret_addr(unsigned long sp, long correction) { - int ret; - struct insn insn; + int rasize = sizeof_long(); + long ra; - auprobe->fixups = 0; - ret = validate_insn_bits(auprobe, mm, &insn); - if (ret != 0) - return ret; + if (copy_from_user(&ra, (void __user *)sp, rasize)) + return -EFAULT; - handle_riprel_insn(auprobe, mm, &insn); - prepare_fixups(auprobe, &insn); + ra += correction; + if (copy_to_user((void __user *)sp, &ra, rasize)) + return -EFAULT; return 0; } -#ifdef CONFIG_X86_64 -/* - * If we're emulating a rip-relative instruction, save the contents - * of the scratch register and store the target address in that register. - */ -static void -pre_xol_rip_insn(struct arch_uprobe *auprobe, struct pt_regs *regs, - struct arch_uprobe_task *autask) +static int default_post_xol_op(struct arch_uprobe *auprobe, struct pt_regs *regs) { - if (auprobe->fixups & UPROBE_FIX_RIP_AX) { - autask->saved_scratch_register = regs->ax; - regs->ax = current->utask->vaddr; - regs->ax += auprobe->rip_rela_target_address; - } else if (auprobe->fixups & UPROBE_FIX_RIP_CX) { - autask->saved_scratch_register = regs->cx; - regs->cx = current->utask->vaddr; - regs->cx += auprobe->rip_rela_target_address; + struct uprobe_task *utask = current->utask; + long correction = (long)(utask->vaddr - utask->xol_vaddr); + + handle_riprel_post_xol(auprobe, regs, &correction); + if (auprobe->fixups & UPROBE_FIX_IP) + regs->ip += correction; + + if (auprobe->fixups & UPROBE_FIX_CALL) { + if (adjust_ret_addr(regs->sp, correction)) { + regs->sp += sizeof_long(); + return -ERESTART; + } } + + return 0; } -#else -static void -pre_xol_rip_insn(struct arch_uprobe *auprobe, struct pt_regs *regs, - struct arch_uprobe_task *autask) + +static struct uprobe_xol_ops default_xol_ops = { + .pre_xol = default_pre_xol_op, + .post_xol = default_post_xol_op, +}; + +static bool branch_is_call(struct arch_uprobe *auprobe) { - /* No RIP-relative addressing on 32-bit */ + return auprobe->branch.opc1 == 0xe8; } -#endif -/* - * arch_uprobe_pre_xol - prepare to execute out of line. - * @auprobe: the probepoint information. - * @regs: reflects the saved user state of current task. - */ -int arch_uprobe_pre_xol(struct arch_uprobe *auprobe, struct pt_regs *regs) -{ - struct arch_uprobe_task *autask; +#define CASE_COND \ + COND(70, 71, XF(OF)) \ + COND(72, 73, XF(CF)) \ + COND(74, 75, XF(ZF)) \ + COND(78, 79, XF(SF)) \ + COND(7a, 7b, XF(PF)) \ + COND(76, 77, XF(CF) || XF(ZF)) \ + COND(7c, 7d, XF(SF) != XF(OF)) \ + COND(7e, 7f, XF(ZF) || XF(SF) != XF(OF)) - autask = ¤t->utask->autask; - autask->saved_trap_nr = current->thread.trap_nr; - current->thread.trap_nr = UPROBE_TRAP_NR; - regs->ip = current->utask->xol_vaddr; - pre_xol_rip_insn(auprobe, regs, autask); +#define COND(op_y, op_n, expr) \ + case 0x ## op_y: DO((expr) != 0) \ + case 0x ## op_n: DO((expr) == 0) - autask->saved_tf = !!(regs->flags & X86_EFLAGS_TF); - regs->flags |= X86_EFLAGS_TF; - if (test_tsk_thread_flag(current, TIF_BLOCKSTEP)) - set_task_blockstep(current, false); +#define XF(xf) (!!(flags & X86_EFLAGS_ ## xf)) - return 0; +static bool is_cond_jmp_opcode(u8 opcode) +{ + switch (opcode) { + #define DO(expr) \ + return true; + CASE_COND + #undef DO + + default: + return false; + } } -/* - * This function is called by arch_uprobe_post_xol() to adjust the return - * address pushed by a call instruction executed out of line. - */ -static int adjust_ret_addr(unsigned long sp, long correction) +static bool check_jmp_cond(struct arch_uprobe *auprobe, struct pt_regs *regs) { - int rasize, ncopied; - long ra = 0; + unsigned long flags = regs->flags; - if (is_ia32_task()) - rasize = 4; - else - rasize = 8; + switch (auprobe->branch.opc1) { + #define DO(expr) \ + return expr; + CASE_COND + #undef DO - ncopied = copy_from_user(&ra, (void __user *)sp, rasize); - if (unlikely(ncopied)) - return -EFAULT; + default: /* not a conditional jmp */ + return true; + } +} - ra += correction; - ncopied = copy_to_user((void __user *)sp, &ra, rasize); - if (unlikely(ncopied)) - return -EFAULT; +#undef XF +#undef COND +#undef CASE_COND - return 0; +static bool branch_emulate_op(struct arch_uprobe *auprobe, struct pt_regs *regs) +{ + unsigned long new_ip = regs->ip += auprobe->branch.ilen; + unsigned long offs = (long)auprobe->branch.offs; + + if (branch_is_call(auprobe)) { + unsigned long new_sp = regs->sp - sizeof_long(); + /* + * If it fails we execute this (mangled, see the comment in + * branch_clear_offset) insn out-of-line. In the likely case + * this should trigger the trap, and the probed application + * should die or restart the same insn after it handles the + * signal, arch_uprobe_post_xol() won't be even called. + * + * But there is corner case, see the comment in ->post_xol(). + */ + if (copy_to_user((void __user *)new_sp, &new_ip, sizeof_long())) + return false; + regs->sp = new_sp; + } else if (!check_jmp_cond(auprobe, regs)) { + offs = 0; + } + + regs->ip = new_ip + offs; + return true; } -#ifdef CONFIG_X86_64 -static bool is_riprel_insn(struct arch_uprobe *auprobe) +static int branch_post_xol_op(struct arch_uprobe *auprobe, struct pt_regs *regs) { - return ((auprobe->fixups & (UPROBE_FIX_RIP_AX | UPROBE_FIX_RIP_CX)) != 0); + BUG_ON(!branch_is_call(auprobe)); + /* + * We can only get here if branch_emulate_op() failed to push the ret + * address _and_ another thread expanded our stack before the (mangled) + * "call" insn was executed out-of-line. Just restore ->sp and restart. + * We could also restore ->ip and try to call branch_emulate_op() again. + */ + regs->sp += sizeof_long(); + return -ERESTART; } -static void -handle_riprel_post_xol(struct arch_uprobe *auprobe, struct pt_regs *regs, long *correction) +static void branch_clear_offset(struct arch_uprobe *auprobe, struct insn *insn) { - if (is_riprel_insn(auprobe)) { - struct arch_uprobe_task *autask; + /* + * Turn this insn into "call 1f; 1:", this is what we will execute + * out-of-line if ->emulate() fails. We only need this to generate + * a trap, so that the probed task receives the correct signal with + * the properly filled siginfo. + * + * But see the comment in ->post_xol(), in the unlikely case it can + * succeed. So we need to ensure that the new ->ip can not fall into + * the non-canonical area and trigger #GP. + * + * We could turn it into (say) "pushf", but then we would need to + * divorce ->insn[] and ->ixol[]. We need to preserve the 1st byte + * of ->insn[] for set_orig_insn(). + */ + memset(auprobe->insn + insn_offset_immediate(insn), + 0, insn->immediate.nbytes); +} - autask = ¤t->utask->autask; - if (auprobe->fixups & UPROBE_FIX_RIP_AX) - regs->ax = autask->saved_scratch_register; - else - regs->cx = autask->saved_scratch_register; +static struct uprobe_xol_ops branch_xol_ops = { + .emulate = branch_emulate_op, + .post_xol = branch_post_xol_op, +}; + +/* Returns -ENOSYS if branch_xol_ops doesn't handle this insn */ +static int branch_setup_xol_ops(struct arch_uprobe *auprobe, struct insn *insn) +{ + u8 opc1 = OPCODE1(insn); + + /* has the side-effect of processing the entire instruction */ + insn_get_length(insn); + if (WARN_ON_ONCE(!insn_complete(insn))) + return -ENOEXEC; + + switch (opc1) { + case 0xeb: /* jmp 8 */ + case 0xe9: /* jmp 32 */ + case 0x90: /* prefix* + nop; same as jmp with .offs = 0 */ + break; + + case 0xe8: /* call relative */ + branch_clear_offset(auprobe, insn); + break; + case 0x0f: + if (insn->opcode.nbytes != 2) + return -ENOSYS; /* - * The original instruction includes a displacement, and so - * is 4 bytes longer than what we've just single-stepped. - * Fall through to handle stuff like "jmpq *...(%rip)" and - * "callq *...(%rip)". + * If it is a "near" conditional jmp, OPCODE2() - 0x10 matches + * OPCODE1() of the "short" jmp which checks the same condition. */ - if (correction) - *correction += 4; + opc1 = OPCODE2(insn) - 0x10; + default: + if (!is_cond_jmp_opcode(opc1)) + return -ENOSYS; } + + auprobe->branch.opc1 = opc1; + auprobe->branch.ilen = insn->length; + auprobe->branch.offs = insn->immediate.value; + + auprobe->ops = &branch_xol_ops; + return 0; } -#else -static void -handle_riprel_post_xol(struct arch_uprobe *auprobe, struct pt_regs *regs, long *correction) + +/** + * arch_uprobe_analyze_insn - instruction analysis including validity and fixups. + * @mm: the probed address space. + * @arch_uprobe: the probepoint information. + * @addr: virtual address at which to install the probepoint + * Return 0 on success or a -ve number on error. + */ +int arch_uprobe_analyze_insn(struct arch_uprobe *auprobe, struct mm_struct *mm, unsigned long addr) +{ + struct insn insn; + bool fix_ip = true, fix_call = false; + int ret; + + ret = validate_insn_bits(auprobe, mm, &insn); + if (ret) + return ret; + + ret = branch_setup_xol_ops(auprobe, &insn); + if (ret != -ENOSYS) + return ret; + + /* + * Figure out which fixups arch_uprobe_post_xol() will need to perform, + * and annotate arch_uprobe->fixups accordingly. To start with, ->fixups + * is either zero or it reflects rip-related fixups. + */ + switch (OPCODE1(&insn)) { + case 0x9d: /* popf */ + auprobe->fixups |= UPROBE_FIX_SETF; + break; + case 0xc3: /* ret or lret -- ip is correct */ + case 0xcb: + case 0xc2: + case 0xca: + fix_ip = false; + break; + case 0x9a: /* call absolute - Fix return addr, not ip */ + fix_call = true; + fix_ip = false; + break; + case 0xea: /* jmp absolute -- ip is correct */ + fix_ip = false; + break; + case 0xff: + insn_get_modrm(&insn); + switch (MODRM_REG(&insn)) { + case 2: case 3: /* call or lcall, indirect */ + fix_call = true; + case 4: case 5: /* jmp or ljmp, indirect */ + fix_ip = false; + } + /* fall through */ + default: + handle_riprel_insn(auprobe, &insn); + } + + if (fix_ip) + auprobe->fixups |= UPROBE_FIX_IP; + if (fix_call) + auprobe->fixups |= UPROBE_FIX_CALL; + + auprobe->ops = &default_xol_ops; + return 0; +} + +/* + * arch_uprobe_pre_xol - prepare to execute out of line. + * @auprobe: the probepoint information. + * @regs: reflects the saved user state of current task. + */ +int arch_uprobe_pre_xol(struct arch_uprobe *auprobe, struct pt_regs *regs) { - /* No RIP-relative addressing on 32-bit */ + struct uprobe_task *utask = current->utask; + + regs->ip = utask->xol_vaddr; + utask->autask.saved_trap_nr = current->thread.trap_nr; + current->thread.trap_nr = UPROBE_TRAP_NR; + + utask->autask.saved_tf = !!(regs->flags & X86_EFLAGS_TF); + regs->flags |= X86_EFLAGS_TF; + if (test_tsk_thread_flag(current, TIF_BLOCKSTEP)) + set_task_blockstep(current, false); + + if (auprobe->ops->pre_xol) + return auprobe->ops->pre_xol(auprobe, regs); + return 0; } -#endif /* * If xol insn itself traps and generates a signal(Say, @@ -592,22 +752,25 @@ bool arch_uprobe_xol_was_trapped(struct task_struct *t) */ int arch_uprobe_post_xol(struct arch_uprobe *auprobe, struct pt_regs *regs) { - struct uprobe_task *utask; - long correction; - int result = 0; + struct uprobe_task *utask = current->utask; WARN_ON_ONCE(current->thread.trap_nr != UPROBE_TRAP_NR); - utask = current->utask; - current->thread.trap_nr = utask->autask.saved_trap_nr; - correction = (long)(utask->vaddr - utask->xol_vaddr); - handle_riprel_post_xol(auprobe, regs, &correction); - if (auprobe->fixups & UPROBE_FIX_IP) - regs->ip += correction; - - if (auprobe->fixups & UPROBE_FIX_CALL) - result = adjust_ret_addr(regs->sp, correction); + if (auprobe->ops->post_xol) { + int err = auprobe->ops->post_xol(auprobe, regs); + if (err) { + arch_uprobe_abort_xol(auprobe, regs); + /* + * Restart the probed insn. ->post_xol() must ensure + * this is really possible if it returns -ERESTART. + */ + if (err == -ERESTART) + return 0; + return err; + } + } + current->thread.trap_nr = utask->autask.saved_trap_nr; /* * arch_uprobe_pre_xol() doesn't save the state of TIF_BLOCKSTEP * so we can get an extra SIGTRAP if we do not clear TF. We need @@ -618,7 +781,7 @@ int arch_uprobe_post_xol(struct arch_uprobe *auprobe, struct pt_regs *regs) else if (!(auprobe->fixups & UPROBE_FIX_SETF)) regs->flags &= ~X86_EFLAGS_TF; - return result; + return 0; } /* callback routine for handling exceptions. */ @@ -652,8 +815,9 @@ int arch_uprobe_exception_notify(struct notifier_block *self, unsigned long val, /* * This function gets called when XOL instruction either gets trapped or - * the thread has a fatal signal, so reset the instruction pointer to its - * probed address. + * the thread has a fatal signal, or if arch_uprobe_post_xol() failed. + * Reset the instruction pointer to its probed address for the potential + * restart or for post mortem analysis. */ void arch_uprobe_abort_xol(struct arch_uprobe *auprobe, struct pt_regs *regs) { @@ -668,25 +832,10 @@ void arch_uprobe_abort_xol(struct arch_uprobe *auprobe, struct pt_regs *regs) regs->flags &= ~X86_EFLAGS_TF; } -/* - * Skip these instructions as per the currently known x86 ISA. - * rep=0x66*; nop=0x90 - */ static bool __skip_sstep(struct arch_uprobe *auprobe, struct pt_regs *regs) { - int i; - - for (i = 0; i < MAX_UINSN_BYTES; i++) { - if (auprobe->insn[i] == 0x66) - continue; - - if (auprobe->insn[i] == 0x90) { - regs->ip += i + 1; - return true; - } - - break; - } + if (auprobe->ops->emulate) + return auprobe->ops->emulate(auprobe, regs); return false; } @@ -701,23 +850,21 @@ bool arch_uprobe_skip_sstep(struct arch_uprobe *auprobe, struct pt_regs *regs) unsigned long arch_uretprobe_hijack_return_addr(unsigned long trampoline_vaddr, struct pt_regs *regs) { - int rasize, ncopied; + int rasize = sizeof_long(), nleft; unsigned long orig_ret_vaddr = 0; /* clear high bits for 32-bit apps */ - rasize = is_ia32_task() ? 4 : 8; - ncopied = copy_from_user(&orig_ret_vaddr, (void __user *)regs->sp, rasize); - if (unlikely(ncopied)) + if (copy_from_user(&orig_ret_vaddr, (void __user *)regs->sp, rasize)) return -1; /* check whether address has been already hijacked */ if (orig_ret_vaddr == trampoline_vaddr) return orig_ret_vaddr; - ncopied = copy_to_user((void __user *)regs->sp, &trampoline_vaddr, rasize); - if (likely(!ncopied)) + nleft = copy_to_user((void __user *)regs->sp, &trampoline_vaddr, rasize); + if (likely(!nleft)) return orig_ret_vaddr; - if (ncopied != rasize) { + if (nleft != rasize) { pr_err("uprobe: return address clobbered: pid=%d, %%sp=%#lx, " "%%ip=%#lx\n", current->pid, regs->sp, regs->ip); diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index f47a104..38a0afe 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -283,6 +283,8 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, 0 /* Reserved */ | f_lm | F(3DNOWEXT) | F(3DNOW); /* cpuid 1.ecx */ const u32 kvm_supported_word4_x86_features = + /* NOTE: MONITOR (and MWAIT) are emulated as NOP, + * but *not* advertised to guests via CPUID ! */ F(XMM3) | F(PCLMULQDQ) | 0 /* DTES64, MONITOR */ | 0 /* DS-CPL, VMX, SMX, EST */ | 0 /* TM2 */ | F(SSSE3) | 0 /* CNXT-ID */ | 0 /* Reserved */ | @@ -495,6 +497,13 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, entry->ecx &= kvm_supported_word6_x86_features; cpuid_mask(&entry->ecx, 6); break; + case 0x80000007: /* Advanced power management */ + /* invariant TSC is CPUID.80000007H:EDX[8] */ + entry->edx &= (1 << 8); + /* mask against host */ + entry->edx &= boot_cpu_data.x86_power; + entry->eax = entry->ebx = entry->ecx = 0; + break; case 0x80000008: { unsigned g_phys_as = (entry->eax >> 16) & 0xff; unsigned virt_as = max((entry->eax >> 8) & 0xff, 48U); @@ -525,7 +534,6 @@ static inline int __do_cpuid_ent(struct kvm_cpuid_entry2 *entry, u32 function, case 3: /* Processor serial number */ case 5: /* MONITOR/MWAIT */ case 6: /* Thermal management */ - case 0x80000007: /* Advanced power management */ case 0xC0000002: case 0xC0000003: case 0xC0000004: @@ -726,6 +734,7 @@ int cpuid_maxphyaddr(struct kvm_vcpu *vcpu) not_found: return 36; } +EXPORT_SYMBOL_GPL(cpuid_maxphyaddr); /* * If no match is found, check whether we exceed the vCPU's limit diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h index eeecbed..f908731 100644 --- a/arch/x86/kvm/cpuid.h +++ b/arch/x86/kvm/cpuid.h @@ -88,4 +88,11 @@ static inline bool guest_cpuid_has_x2apic(struct kvm_vcpu *vcpu) return best && (best->ecx & bit(X86_FEATURE_X2APIC)); } +static inline bool guest_cpuid_has_gbpages(struct kvm_vcpu *vcpu) +{ + struct kvm_cpuid_entry2 *best; + + best = kvm_find_cpuid_entry(vcpu, 0x80000001, 0); + return best && (best->edx & bit(X86_FEATURE_GBPAGES)); +} #endif diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c index 205b17e..e4e833d 100644 --- a/arch/x86/kvm/emulate.c +++ b/arch/x86/kvm/emulate.c @@ -161,6 +161,7 @@ #define Fastop ((u64)1 << 44) /* Use opcode::u.fastop */ #define NoWrite ((u64)1 << 45) /* No writeback */ #define SrcWrite ((u64)1 << 46) /* Write back src operand */ +#define NoMod ((u64)1 << 47) /* Mod field is ignored */ #define DstXacc (DstAccLo | SrcAccHi | SrcWrite) @@ -1077,7 +1078,7 @@ static int decode_modrm(struct x86_emulate_ctxt *ctxt, ctxt->modrm_rm |= (ctxt->modrm & 0x07); ctxt->modrm_seg = VCPU_SREG_DS; - if (ctxt->modrm_mod == 3) { + if (ctxt->modrm_mod == 3 || (ctxt->d & NoMod)) { op->type = OP_REG; op->bytes = (ctxt->d & ByteOp) ? 1 : ctxt->op_bytes; op->addr.reg = decode_register(ctxt, ctxt->modrm_rm, @@ -1324,7 +1325,8 @@ static int pio_in_emulated(struct x86_emulate_ctxt *ctxt, rc->end = n * size; } - if (ctxt->rep_prefix && !(ctxt->eflags & EFLG_DF)) { + if (ctxt->rep_prefix && (ctxt->d & String) && + !(ctxt->eflags & EFLG_DF)) { ctxt->dst.data = rc->data + rc->pos; ctxt->dst.type = OP_MEM_STR; ctxt->dst.count = (rc->end - rc->pos) / size; @@ -1409,11 +1411,11 @@ static int write_segment_descriptor(struct x86_emulate_ctxt *ctxt, } /* Does not support long mode */ -static int load_segment_descriptor(struct x86_emulate_ctxt *ctxt, - u16 selector, int seg) +static int __load_segment_descriptor(struct x86_emulate_ctxt *ctxt, + u16 selector, int seg, u8 cpl, bool in_task_switch) { struct desc_struct seg_desc, old_desc; - u8 dpl, rpl, cpl; + u8 dpl, rpl; unsigned err_vec = GP_VECTOR; u32 err_code = 0; bool null_selector = !(selector & ~0x3); /* 0000-0003 are null */ @@ -1441,7 +1443,6 @@ static int load_segment_descriptor(struct x86_emulate_ctxt *ctxt, } rpl = selector & 3; - cpl = ctxt->ops->cpl(ctxt); /* NULL selector is not valid for TR, CS and SS (except for long mode) */ if ((seg == VCPU_SREG_CS @@ -1486,6 +1487,9 @@ static int load_segment_descriptor(struct x86_emulate_ctxt *ctxt, goto exception; break; case VCPU_SREG_CS: + if (in_task_switch && rpl != dpl) + goto exception; + if (!(seg_desc.type & 8)) goto exception; @@ -1543,6 +1547,13 @@ exception: return X86EMUL_PROPAGATE_FAULT; } +static int load_segment_descriptor(struct x86_emulate_ctxt *ctxt, + u16 selector, int seg) +{ + u8 cpl = ctxt->ops->cpl(ctxt); + return __load_segment_descriptor(ctxt, selector, seg, cpl, false); +} + static void write_register_operand(struct operand *op) { /* The 4-byte case *is* correct: in 64-bit mode we zero-extend. */ @@ -2404,6 +2415,7 @@ static int load_state_from_tss16(struct x86_emulate_ctxt *ctxt, struct tss_segment_16 *tss) { int ret; + u8 cpl; ctxt->_eip = tss->ip; ctxt->eflags = tss->flag | 2; @@ -2426,23 +2438,25 @@ static int load_state_from_tss16(struct x86_emulate_ctxt *ctxt, set_segment_selector(ctxt, tss->ss, VCPU_SREG_SS); set_segment_selector(ctxt, tss->ds, VCPU_SREG_DS); + cpl = tss->cs & 3; + /* * Now load segment descriptors. If fault happens at this stage * it is handled in a context of new task */ - ret = load_segment_descriptor(ctxt, tss->ldt, VCPU_SREG_LDTR); + ret = __load_segment_descriptor(ctxt, tss->ldt, VCPU_SREG_LDTR, cpl, true); if (ret != X86EMUL_CONTINUE) return ret; - ret = load_segment_descriptor(ctxt, tss->es, VCPU_SREG_ES); + ret = __load_segment_descriptor(ctxt, tss->es, VCPU_SREG_ES, cpl, true); if (ret != X86EMUL_CONTINUE) return ret; - ret = load_segment_descriptor(ctxt, tss->cs, VCPU_SREG_CS); + ret = __load_segment_descriptor(ctxt, tss->cs, VCPU_SREG_CS, cpl, true); if (ret != X86EMUL_CONTINUE) return ret; - ret = load_segment_descriptor(ctxt, tss->ss, VCPU_SREG_SS); + ret = __load_segment_descriptor(ctxt, tss->ss, VCPU_SREG_SS, cpl, true); if (ret != X86EMUL_CONTINUE) return ret; - ret = load_segment_descriptor(ctxt, tss->ds, VCPU_SREG_DS); + ret = __load_segment_descriptor(ctxt, tss->ds, VCPU_SREG_DS, cpl, true); if (ret != X86EMUL_CONTINUE) return ret; @@ -2496,7 +2510,7 @@ static int task_switch_16(struct x86_emulate_ctxt *ctxt, static void save_state_to_tss32(struct x86_emulate_ctxt *ctxt, struct tss_segment_32 *tss) { - tss->cr3 = ctxt->ops->get_cr(ctxt, 3); + /* CR3 and ldt selector are not saved intentionally */ tss->eip = ctxt->_eip; tss->eflags = ctxt->eflags; tss->eax = reg_read(ctxt, VCPU_REGS_RAX); @@ -2514,13 +2528,13 @@ static void save_state_to_tss32(struct x86_emulate_ctxt *ctxt, tss->ds = get_segment_selector(ctxt, VCPU_SREG_DS); tss->fs = get_segment_selector(ctxt, VCPU_SREG_FS); tss->gs = get_segment_selector(ctxt, VCPU_SREG_GS); - tss->ldt_selector = get_segment_selector(ctxt, VCPU_SREG_LDTR); } static int load_state_from_tss32(struct x86_emulate_ctxt *ctxt, struct tss_segment_32 *tss) { int ret; + u8 cpl; if (ctxt->ops->set_cr(ctxt, 3, tss->cr3)) return emulate_gp(ctxt, 0); @@ -2539,7 +2553,8 @@ static int load_state_from_tss32(struct x86_emulate_ctxt *ctxt, /* * SDM says that segment selectors are loaded before segment - * descriptors + * descriptors. This is important because CPL checks will + * use CS.RPL. */ set_segment_selector(ctxt, tss->ldt_selector, VCPU_SREG_LDTR); set_segment_selector(ctxt, tss->es, VCPU_SREG_ES); @@ -2553,43 +2568,38 @@ static int load_state_from_tss32(struct x86_emulate_ctxt *ctxt, * If we're switching between Protected Mode and VM86, we need to make * sure to update the mode before loading the segment descriptors so * that the selectors are interpreted correctly. - * - * Need to get rflags to the vcpu struct immediately because it - * influences the CPL which is checked at least when loading the segment - * descriptors and when pushing an error code to the new kernel stack. - * - * TODO Introduce a separate ctxt->ops->set_cpl callback */ - if (ctxt->eflags & X86_EFLAGS_VM) + if (ctxt->eflags & X86_EFLAGS_VM) { ctxt->mode = X86EMUL_MODE_VM86; - else + cpl = 3; + } else { ctxt->mode = X86EMUL_MODE_PROT32; - - ctxt->ops->set_rflags(ctxt, ctxt->eflags); + cpl = tss->cs & 3; + } /* * Now load segment descriptors. If fault happenes at this stage * it is handled in a context of new task */ - ret = load_segment_descriptor(ctxt, tss->ldt_selector, VCPU_SREG_LDTR); + ret = __load_segment_descriptor(ctxt, tss->ldt_selector, VCPU_SREG_LDTR, cpl, true); if (ret != X86EMUL_CONTINUE) return ret; - ret = load_segment_descriptor(ctxt, tss->es, VCPU_SREG_ES); + ret = __load_segment_descriptor(ctxt, tss->es, VCPU_SREG_ES, cpl, true); if (ret != X86EMUL_CONTINUE) return ret; - ret = load_segment_descriptor(ctxt, tss->cs, VCPU_SREG_CS); + ret = __load_segment_descriptor(ctxt, tss->cs, VCPU_SREG_CS, cpl, true); if (ret != X86EMUL_CONTINUE) return ret; - ret = load_segment_descriptor(ctxt, tss->ss, VCPU_SREG_SS); + ret = __load_segment_descriptor(ctxt, tss->ss, VCPU_SREG_SS, cpl, true); if (ret != X86EMUL_CONTINUE) return ret; - ret = load_segment_descriptor(ctxt, tss->ds, VCPU_SREG_DS); + ret = __load_segment_descriptor(ctxt, tss->ds, VCPU_SREG_DS, cpl, true); if (ret != X86EMUL_CONTINUE) return ret; - ret = load_segment_descriptor(ctxt, tss->fs, VCPU_SREG_FS); + ret = __load_segment_descriptor(ctxt, tss->fs, VCPU_SREG_FS, cpl, true); if (ret != X86EMUL_CONTINUE) return ret; - ret = load_segment_descriptor(ctxt, tss->gs, VCPU_SREG_GS); + ret = __load_segment_descriptor(ctxt, tss->gs, VCPU_SREG_GS, cpl, true); if (ret != X86EMUL_CONTINUE) return ret; @@ -2604,6 +2614,8 @@ static int task_switch_32(struct x86_emulate_ctxt *ctxt, struct tss_segment_32 tss_seg; int ret; u32 new_tss_base = get_desc_base(new_desc); + u32 eip_offset = offsetof(struct tss_segment_32, eip); + u32 ldt_sel_offset = offsetof(struct tss_segment_32, ldt_selector); ret = ops->read_std(ctxt, old_tss_base, &tss_seg, sizeof tss_seg, &ctxt->exception); @@ -2613,8 +2625,9 @@ static int task_switch_32(struct x86_emulate_ctxt *ctxt, save_state_to_tss32(ctxt, &tss_seg); - ret = ops->write_std(ctxt, old_tss_base, &tss_seg, sizeof tss_seg, - &ctxt->exception); + /* Only GP registers and segment selectors are saved */ + ret = ops->write_std(ctxt, old_tss_base + eip_offset, &tss_seg.eip, + ldt_sel_offset - eip_offset, &ctxt->exception); if (ret != X86EMUL_CONTINUE) /* FIXME: need to provide precise fault address */ return ret; @@ -3386,10 +3399,6 @@ static int check_cr_write(struct x86_emulate_ctxt *ctxt) ctxt->ops->get_msr(ctxt, MSR_EFER, &efer); if (efer & EFER_LMA) rsvd = CR3_L_MODE_RESERVED_BITS; - else if (ctxt->ops->get_cr(ctxt, 4) & X86_CR4_PAE) - rsvd = CR3_PAE_RESERVED_BITS; - else if (ctxt->ops->get_cr(ctxt, 0) & X86_CR0_PG) - rsvd = CR3_NONPAE_RESERVED_BITS; if (new_val & rsvd) return emulate_gp(ctxt, 0); @@ -3869,10 +3878,12 @@ static const struct opcode twobyte_table[256] = { N, N, N, N, N, N, N, N, D(ImplicitOps | ModRM), N, N, N, N, N, N, D(ImplicitOps | ModRM), /* 0x20 - 0x2F */ - DIP(ModRM | DstMem | Priv | Op3264, cr_read, check_cr_read), - DIP(ModRM | DstMem | Priv | Op3264, dr_read, check_dr_read), - IIP(ModRM | SrcMem | Priv | Op3264, em_cr_write, cr_write, check_cr_write), - IIP(ModRM | SrcMem | Priv | Op3264, em_dr_write, dr_write, check_dr_write), + DIP(ModRM | DstMem | Priv | Op3264 | NoMod, cr_read, check_cr_read), + DIP(ModRM | DstMem | Priv | Op3264 | NoMod, dr_read, check_dr_read), + IIP(ModRM | SrcMem | Priv | Op3264 | NoMod, em_cr_write, cr_write, + check_cr_write), + IIP(ModRM | SrcMem | Priv | Op3264 | NoMod, em_dr_write, dr_write, + check_dr_write), N, N, N, N, GP(ModRM | DstReg | SrcMem | Mov | Sse, &pfx_0f_28_0f_29), GP(ModRM | DstMem | SrcReg | Mov | Sse, &pfx_0f_28_0f_29), diff --git a/arch/x86/kvm/irq.c b/arch/x86/kvm/irq.c index 484bc87..bd0da43 100644 --- a/arch/x86/kvm/irq.c +++ b/arch/x86/kvm/irq.c @@ -113,6 +113,7 @@ int kvm_cpu_get_interrupt(struct kvm_vcpu *v) return kvm_get_apic_interrupt(v); /* APIC */ } +EXPORT_SYMBOL_GPL(kvm_cpu_get_interrupt); void kvm_inject_pending_timer_irqs(struct kvm_vcpu *vcpu) { diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index 9736529..0069118 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -360,6 +360,8 @@ static inline void apic_clear_irr(int vec, struct kvm_lapic *apic) static inline void apic_set_isr(int vec, struct kvm_lapic *apic) { + /* Note that we never get here with APIC virtualization enabled. */ + if (!__apic_test_and_set_vector(vec, apic->regs + APIC_ISR)) ++apic->isr_count; BUG_ON(apic->isr_count > MAX_APIC_VECTOR); @@ -371,12 +373,48 @@ static inline void apic_set_isr(int vec, struct kvm_lapic *apic) apic->highest_isr_cache = vec; } +static inline int apic_find_highest_isr(struct kvm_lapic *apic) +{ + int result; + + /* + * Note that isr_count is always 1, and highest_isr_cache + * is always -1, with APIC virtualization enabled. + */ + if (!apic->isr_count) + return -1; + if (likely(apic->highest_isr_cache != -1)) + return apic->highest_isr_cache; + + result = find_highest_vector(apic->regs + APIC_ISR); + ASSERT(result == -1 || result >= 16); + + return result; +} + static inline void apic_clear_isr(int vec, struct kvm_lapic *apic) { - if (__apic_test_and_clear_vector(vec, apic->regs + APIC_ISR)) + struct kvm_vcpu *vcpu; + if (!__apic_test_and_clear_vector(vec, apic->regs + APIC_ISR)) + return; + + vcpu = apic->vcpu; + + /* + * We do get here for APIC virtualization enabled if the guest + * uses the Hyper-V APIC enlightenment. In this case we may need + * to trigger a new interrupt delivery by writing the SVI field; + * on the other hand isr_count and highest_isr_cache are unused + * and must be left alone. + */ + if (unlikely(kvm_apic_vid_enabled(vcpu->kvm))) + kvm_x86_ops->hwapic_isr_update(vcpu->kvm, + apic_find_highest_isr(apic)); + else { --apic->isr_count; - BUG_ON(apic->isr_count < 0); - apic->highest_isr_cache = -1; + BUG_ON(apic->isr_count < 0); + apic->highest_isr_cache = -1; + } } int kvm_lapic_find_highest_irr(struct kvm_vcpu *vcpu) @@ -456,22 +494,6 @@ static void pv_eoi_clr_pending(struct kvm_vcpu *vcpu) __clear_bit(KVM_APIC_PV_EOI_PENDING, &vcpu->arch.apic_attention); } -static inline int apic_find_highest_isr(struct kvm_lapic *apic) -{ - int result; - - /* Note that isr_count is always 1 with vid enabled */ - if (!apic->isr_count) - return -1; - if (likely(apic->highest_isr_cache != -1)) - return apic->highest_isr_cache; - - result = find_highest_vector(apic->regs + APIC_ISR); - ASSERT(result == -1 || result >= 16); - - return result; -} - void kvm_apic_update_tmr(struct kvm_vcpu *vcpu, u32 *tmr) { struct kvm_lapic *apic = vcpu->arch.apic; @@ -1605,6 +1627,8 @@ int kvm_get_apic_interrupt(struct kvm_vcpu *vcpu) int vector = kvm_apic_has_interrupt(vcpu); struct kvm_lapic *apic = vcpu->arch.apic; + /* Note that we never get here with APIC virtualization enabled. */ + if (vector == -1) return -1; diff --git a/arch/x86/kvm/mmu.c b/arch/x86/kvm/mmu.c index 813d310..9314678 100644 --- a/arch/x86/kvm/mmu.c +++ b/arch/x86/kvm/mmu.c @@ -22,6 +22,7 @@ #include "mmu.h" #include "x86.h" #include "kvm_cache_regs.h" +#include "cpuid.h" #include <linux/kvm_host.h> #include <linux/types.h> @@ -595,7 +596,8 @@ static bool mmu_spte_update(u64 *sptep, u64 new_spte) * we always atomicly update it, see the comments in * spte_has_volatile_bits(). */ - if (is_writable_pte(old_spte) && !is_writable_pte(new_spte)) + if (spte_is_locklessly_modifiable(old_spte) && + !is_writable_pte(new_spte)) ret = true; if (!shadow_accessed_mask) @@ -1176,8 +1178,7 @@ static void drop_large_spte(struct kvm_vcpu *vcpu, u64 *sptep) /* * Write-protect on the specified @sptep, @pt_protect indicates whether - * spte writ-protection is caused by protecting shadow page table. - * @flush indicates whether tlb need be flushed. + * spte write-protection is caused by protecting shadow page table. * * Note: write protection is difference between drity logging and spte * protection: @@ -1186,10 +1187,9 @@ static void drop_large_spte(struct kvm_vcpu *vcpu, u64 *sptep) * - for spte protection, the spte can be writable only after unsync-ing * shadow page. * - * Return true if the spte is dropped. + * Return true if tlb need be flushed. */ -static bool -spte_write_protect(struct kvm *kvm, u64 *sptep, bool *flush, bool pt_protect) +static bool spte_write_protect(struct kvm *kvm, u64 *sptep, bool pt_protect) { u64 spte = *sptep; @@ -1199,17 +1199,11 @@ spte_write_protect(struct kvm *kvm, u64 *sptep, bool *flush, bool pt_protect) rmap_printk("rmap_write_protect: spte %p %llx\n", sptep, *sptep); - if (__drop_large_spte(kvm, sptep)) { - *flush |= true; - return true; - } - if (pt_protect) spte &= ~SPTE_MMU_WRITEABLE; spte = spte & ~PT_WRITABLE_MASK; - *flush |= mmu_spte_update(sptep, spte); - return false; + return mmu_spte_update(sptep, spte); } static bool __rmap_write_protect(struct kvm *kvm, unsigned long *rmapp, @@ -1221,11 +1215,8 @@ static bool __rmap_write_protect(struct kvm *kvm, unsigned long *rmapp, for (sptep = rmap_get_first(*rmapp, &iter); sptep;) { BUG_ON(!(*sptep & PT_PRESENT_MASK)); - if (spte_write_protect(kvm, sptep, &flush, pt_protect)) { - sptep = rmap_get_first(*rmapp, &iter); - continue; - } + flush |= spte_write_protect(kvm, sptep, pt_protect); sptep = rmap_get_next(&iter); } @@ -2802,9 +2793,9 @@ static bool page_fault_can_be_fast(u32 error_code) } static bool -fast_pf_fix_direct_spte(struct kvm_vcpu *vcpu, u64 *sptep, u64 spte) +fast_pf_fix_direct_spte(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp, + u64 *sptep, u64 spte) { - struct kvm_mmu_page *sp = page_header(__pa(sptep)); gfn_t gfn; WARN_ON(!sp->role.direct); @@ -2830,6 +2821,7 @@ static bool fast_page_fault(struct kvm_vcpu *vcpu, gva_t gva, int level, u32 error_code) { struct kvm_shadow_walk_iterator iterator; + struct kvm_mmu_page *sp; bool ret = false; u64 spte = 0ull; @@ -2853,7 +2845,8 @@ static bool fast_page_fault(struct kvm_vcpu *vcpu, gva_t gva, int level, goto exit; } - if (!is_last_spte(spte, level)) + sp = page_header(__pa(iterator.sptep)); + if (!is_last_spte(spte, sp->role.level)) goto exit; /* @@ -2875,11 +2868,24 @@ static bool fast_page_fault(struct kvm_vcpu *vcpu, gva_t gva, int level, goto exit; /* + * Do not fix write-permission on the large spte since we only dirty + * the first page into the dirty-bitmap in fast_pf_fix_direct_spte() + * that means other pages are missed if its slot is dirty-logged. + * + * Instead, we let the slow page fault path create a normal spte to + * fix the access. + * + * See the comments in kvm_arch_commit_memory_region(). + */ + if (sp->role.level > PT_PAGE_TABLE_LEVEL) + goto exit; + + /* * Currently, fast page fault only works for direct mapping since * the gfn is not stable for indirect shadow page. * See Documentation/virtual/kvm/locking.txt to get more detail. */ - ret = fast_pf_fix_direct_spte(vcpu, iterator.sptep, spte); + ret = fast_pf_fix_direct_spte(vcpu, sp, iterator.sptep, spte); exit: trace_fast_page_fault(vcpu, gva, error_code, iterator.sptep, spte, ret); @@ -3511,11 +3517,14 @@ static void reset_rsvds_bits_mask(struct kvm_vcpu *vcpu, { int maxphyaddr = cpuid_maxphyaddr(vcpu); u64 exb_bit_rsvd = 0; + u64 gbpages_bit_rsvd = 0; context->bad_mt_xwr = 0; if (!context->nx) exb_bit_rsvd = rsvd_bits(63, 63); + if (!guest_cpuid_has_gbpages(vcpu)) + gbpages_bit_rsvd = rsvd_bits(7, 7); switch (context->root_level) { case PT32_ROOT_LEVEL: /* no rsvd bits for 2 level 4K page table entries */ @@ -3538,7 +3547,7 @@ static void reset_rsvds_bits_mask(struct kvm_vcpu *vcpu, case PT32E_ROOT_LEVEL: context->rsvd_bits_mask[0][2] = rsvd_bits(maxphyaddr, 63) | - rsvd_bits(7, 8) | rsvd_bits(1, 2); /* PDPTE */ + rsvd_bits(5, 8) | rsvd_bits(1, 2); /* PDPTE */ context->rsvd_bits_mask[0][1] = exb_bit_rsvd | rsvd_bits(maxphyaddr, 62); /* PDE */ context->rsvd_bits_mask[0][0] = exb_bit_rsvd | @@ -3550,16 +3559,16 @@ static void reset_rsvds_bits_mask(struct kvm_vcpu *vcpu, break; case PT64_ROOT_LEVEL: context->rsvd_bits_mask[0][3] = exb_bit_rsvd | - rsvd_bits(maxphyaddr, 51) | rsvd_bits(7, 8); + rsvd_bits(maxphyaddr, 51) | rsvd_bits(7, 7); context->rsvd_bits_mask[0][2] = exb_bit_rsvd | - rsvd_bits(maxphyaddr, 51) | rsvd_bits(7, 8); + gbpages_bit_rsvd | rsvd_bits(maxphyaddr, 51); context->rsvd_bits_mask[0][1] = exb_bit_rsvd | rsvd_bits(maxphyaddr, 51); context->rsvd_bits_mask[0][0] = exb_bit_rsvd | rsvd_bits(maxphyaddr, 51); context->rsvd_bits_mask[1][3] = context->rsvd_bits_mask[0][3]; context->rsvd_bits_mask[1][2] = exb_bit_rsvd | - rsvd_bits(maxphyaddr, 51) | + gbpages_bit_rsvd | rsvd_bits(maxphyaddr, 51) | rsvd_bits(13, 29); context->rsvd_bits_mask[1][1] = exb_bit_rsvd | rsvd_bits(maxphyaddr, 51) | @@ -4304,15 +4313,32 @@ void kvm_mmu_slot_remove_write_access(struct kvm *kvm, int slot) if (*rmapp) __rmap_write_protect(kvm, rmapp, false); - if (need_resched() || spin_needbreak(&kvm->mmu_lock)) { - kvm_flush_remote_tlbs(kvm); + if (need_resched() || spin_needbreak(&kvm->mmu_lock)) cond_resched_lock(&kvm->mmu_lock); - } } } - kvm_flush_remote_tlbs(kvm); spin_unlock(&kvm->mmu_lock); + + /* + * kvm_mmu_slot_remove_write_access() and kvm_vm_ioctl_get_dirty_log() + * which do tlb flush out of mmu-lock should be serialized by + * kvm->slots_lock otherwise tlb flush would be missed. + */ + lockdep_assert_held(&kvm->slots_lock); + + /* + * We can flush all the TLBs out of the mmu lock without TLB + * corruption since we just change the spte from writable to + * readonly so that we only need to care the case of changing + * spte from present to present (changing the spte from present + * to nonpresent will flush all the TLBs immediately), in other + * words, the only case we care is mmu_spte_update() where we + * haved checked SPTE_HOST_WRITEABLE | SPTE_MMU_WRITEABLE + * instead of PT_WRITABLE_MASK, that means it does not depend + * on PT_WRITABLE_MASK anymore. + */ + kvm_flush_remote_tlbs(kvm); } #define BATCH_ZAP_PAGES 10 diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h index 3842e70..b982112 100644 --- a/arch/x86/kvm/mmu.h +++ b/arch/x86/kvm/mmu.h @@ -104,6 +104,39 @@ static inline int is_present_gpte(unsigned long pte) return pte & PT_PRESENT_MASK; } +/* + * Currently, we have two sorts of write-protection, a) the first one + * write-protects guest page to sync the guest modification, b) another one is + * used to sync dirty bitmap when we do KVM_GET_DIRTY_LOG. The differences + * between these two sorts are: + * 1) the first case clears SPTE_MMU_WRITEABLE bit. + * 2) the first case requires flushing tlb immediately avoiding corrupting + * shadow page table between all vcpus so it should be in the protection of + * mmu-lock. And the another case does not need to flush tlb until returning + * the dirty bitmap to userspace since it only write-protects the page + * logged in the bitmap, that means the page in the dirty bitmap is not + * missed, so it can flush tlb out of mmu-lock. + * + * So, there is the problem: the first case can meet the corrupted tlb caused + * by another case which write-protects pages but without flush tlb + * immediately. In order to making the first case be aware this problem we let + * it flush tlb if we try to write-protect a spte whose SPTE_MMU_WRITEABLE bit + * is set, it works since another case never touches SPTE_MMU_WRITEABLE bit. + * + * Anyway, whenever a spte is updated (only permission and status bits are + * changed) we need to check whether the spte with SPTE_MMU_WRITEABLE becomes + * readonly, if that happens, we need to flush tlb. Fortunately, + * mmu_spte_update() has already handled it perfectly. + * + * The rules to use SPTE_MMU_WRITEABLE and PT_WRITABLE_MASK: + * - if we want to see if it has writable tlb entry or if the spte can be + * writable on the mmu mapping, check SPTE_MMU_WRITEABLE, this is the most + * case, otherwise + * - if we fix page fault on the spte or do write-protection by dirty logging, + * check PT_WRITABLE_MASK. + * + * TODO: introduce APIs to split these two cases. + */ static inline int is_writable_pte(unsigned long pte) { return pte & PT_WRITABLE_MASK; diff --git a/arch/x86/kvm/paging_tmpl.h b/arch/x86/kvm/paging_tmpl.h index 123efd3..4107765 100644 --- a/arch/x86/kvm/paging_tmpl.h +++ b/arch/x86/kvm/paging_tmpl.h @@ -913,8 +913,7 @@ static gpa_t FNAME(gva_to_gpa_nested)(struct kvm_vcpu *vcpu, gva_t vaddr, * and kvm_mmu_notifier_invalidate_range_start detect the mapping page isn't * used by guest then tlbs are not flushed, so guest is allowed to access the * freed pages. - * We set tlbs_dirty to let the notifier know this change and delay the flush - * until such a case actually happens. + * And we increase kvm->tlbs_dirty to delay tlbs flush in this case. */ static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp) { @@ -943,7 +942,7 @@ static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp) return -EINVAL; if (FNAME(prefetch_invalid_gpte)(vcpu, sp, &sp->spt[i], gpte)) { - vcpu->kvm->tlbs_dirty = true; + vcpu->kvm->tlbs_dirty++; continue; } @@ -958,7 +957,7 @@ static int FNAME(sync_page)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp) if (gfn != sp->gfns[i]) { drop_spte(vcpu->kvm, &sp->spt[i]); - vcpu->kvm->tlbs_dirty = true; + vcpu->kvm->tlbs_dirty++; continue; } diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c index 5c4f631..cbecaa9 100644 --- a/arch/x86/kvm/pmu.c +++ b/arch/x86/kvm/pmu.c @@ -108,7 +108,10 @@ static void kvm_perf_overflow(struct perf_event *perf_event, { struct kvm_pmc *pmc = perf_event->overflow_handler_context; struct kvm_pmu *pmu = &pmc->vcpu->arch.pmu; - __set_bit(pmc->idx, (unsigned long *)&pmu->global_status); + if (!test_and_set_bit(pmc->idx, (unsigned long *)&pmu->reprogram_pmi)) { + __set_bit(pmc->idx, (unsigned long *)&pmu->global_status); + kvm_make_request(KVM_REQ_PMU, pmc->vcpu); + } } static void kvm_perf_overflow_intr(struct perf_event *perf_event, @@ -117,7 +120,7 @@ static void kvm_perf_overflow_intr(struct perf_event *perf_event, struct kvm_pmc *pmc = perf_event->overflow_handler_context; struct kvm_pmu *pmu = &pmc->vcpu->arch.pmu; if (!test_and_set_bit(pmc->idx, (unsigned long *)&pmu->reprogram_pmi)) { - kvm_perf_overflow(perf_event, data, regs); + __set_bit(pmc->idx, (unsigned long *)&pmu->global_status); kvm_make_request(KVM_REQ_PMU, pmc->vcpu); /* * Inject PMI. If vcpu was in a guest mode during NMI PMI diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c index 7f4f9c2..ec8366c 100644 --- a/arch/x86/kvm/svm.c +++ b/arch/x86/kvm/svm.c @@ -1338,21 +1338,6 @@ static void svm_vcpu_put(struct kvm_vcpu *vcpu) wrmsrl(host_save_user_msrs[i], svm->host_user_msrs[i]); } -static void svm_update_cpl(struct kvm_vcpu *vcpu) -{ - struct vcpu_svm *svm = to_svm(vcpu); - int cpl; - - if (!is_protmode(vcpu)) - cpl = 0; - else if (svm->vmcb->save.rflags & X86_EFLAGS_VM) - cpl = 3; - else - cpl = svm->vmcb->save.cs.selector & 0x3; - - svm->vmcb->save.cpl = cpl; -} - static unsigned long svm_get_rflags(struct kvm_vcpu *vcpu) { return to_svm(vcpu)->vmcb->save.rflags; @@ -1360,11 +1345,12 @@ static unsigned long svm_get_rflags(struct kvm_vcpu *vcpu) static void svm_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags) { - unsigned long old_rflags = to_svm(vcpu)->vmcb->save.rflags; - + /* + * Any change of EFLAGS.VM is accompained by a reload of SS + * (caused by either a task switch or an inter-privilege IRET), + * so we do not need to update the CPL here. + */ to_svm(vcpu)->vmcb->save.rflags = rflags; - if ((old_rflags ^ rflags) & X86_EFLAGS_VM) - svm_update_cpl(vcpu); } static void svm_cache_reg(struct kvm_vcpu *vcpu, enum kvm_reg reg) @@ -1631,8 +1617,15 @@ static void svm_set_segment(struct kvm_vcpu *vcpu, s->attrib |= (var->db & 1) << SVM_SELECTOR_DB_SHIFT; s->attrib |= (var->g & 1) << SVM_SELECTOR_G_SHIFT; } - if (seg == VCPU_SREG_CS) - svm_update_cpl(vcpu); + + /* + * This is always accurate, except if SYSRET returned to a segment + * with SS.DPL != 3. Intel does not have this quirk, and always + * forces SS.DPL to 3 on sysret, so we ignore that case; fixing it + * would entail passing the CPL to userspace and back. + */ + if (seg == VCPU_SREG_SS) + svm->vmcb->save.cpl = (s->attrib >> SVM_SELECTOR_DPL_SHIFT) & 3; mark_dirty(svm->vmcb, VMCB_SEG); } @@ -2770,12 +2763,6 @@ static int xsetbv_interception(struct vcpu_svm *svm) return 1; } -static int invalid_op_interception(struct vcpu_svm *svm) -{ - kvm_queue_exception(&svm->vcpu, UD_VECTOR); - return 1; -} - static int task_switch_interception(struct vcpu_svm *svm) { u16 tss_selector; @@ -3287,6 +3274,24 @@ static int pause_interception(struct vcpu_svm *svm) return 1; } +static int nop_interception(struct vcpu_svm *svm) +{ + skip_emulated_instruction(&(svm->vcpu)); + return 1; +} + +static int monitor_interception(struct vcpu_svm *svm) +{ + printk_once(KERN_WARNING "kvm: MONITOR instruction emulated as NOP!\n"); + return nop_interception(svm); +} + +static int mwait_interception(struct vcpu_svm *svm) +{ + printk_once(KERN_WARNING "kvm: MWAIT instruction emulated as NOP!\n"); + return nop_interception(svm); +} + static int (*const svm_exit_handlers[])(struct vcpu_svm *svm) = { [SVM_EXIT_READ_CR0] = cr_interception, [SVM_EXIT_READ_CR3] = cr_interception, @@ -3344,8 +3349,8 @@ static int (*const svm_exit_handlers[])(struct vcpu_svm *svm) = { [SVM_EXIT_CLGI] = clgi_interception, [SVM_EXIT_SKINIT] = skinit_interception, [SVM_EXIT_WBINVD] = emulate_on_interception, - [SVM_EXIT_MONITOR] = invalid_op_interception, - [SVM_EXIT_MWAIT] = invalid_op_interception, + [SVM_EXIT_MONITOR] = monitor_interception, + [SVM_EXIT_MWAIT] = mwait_interception, [SVM_EXIT_XSETBV] = xsetbv_interception, [SVM_EXIT_NPF] = pf_interception, }; diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h index 545245d..33574c9 100644 --- a/arch/x86/kvm/trace.h +++ b/arch/x86/kvm/trace.h @@ -91,16 +91,21 @@ TRACE_EVENT(kvm_hv_hypercall, /* * Tracepoint for PIO. */ + +#define KVM_PIO_IN 0 +#define KVM_PIO_OUT 1 + TRACE_EVENT(kvm_pio, TP_PROTO(unsigned int rw, unsigned int port, unsigned int size, - unsigned int count), - TP_ARGS(rw, port, size, count), + unsigned int count, void *data), + TP_ARGS(rw, port, size, count, data), TP_STRUCT__entry( __field( unsigned int, rw ) __field( unsigned int, port ) __field( unsigned int, size ) __field( unsigned int, count ) + __field( unsigned int, val ) ), TP_fast_assign( @@ -108,11 +113,18 @@ TRACE_EVENT(kvm_pio, __entry->port = port; __entry->size = size; __entry->count = count; + if (size == 1) + __entry->val = *(unsigned char *)data; + else if (size == 2) + __entry->val = *(unsigned short *)data; + else + __entry->val = *(unsigned int *)data; ), - TP_printk("pio_%s at 0x%x size %d count %d", + TP_printk("pio_%s at 0x%x size %d count %d val 0x%x %s", __entry->rw ? "write" : "read", - __entry->port, __entry->size, __entry->count) + __entry->port, __entry->size, __entry->count, __entry->val, + __entry->count > 1 ? "(...)" : "") ); /* diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c index 33e8c02..801332e 100644 --- a/arch/x86/kvm/vmx.c +++ b/arch/x86/kvm/vmx.c @@ -354,6 +354,7 @@ struct vmcs02_list { struct nested_vmx { /* Has the level1 guest done vmxon? */ bool vmxon; + gpa_t vmxon_ptr; /* The guest-physical address of the current VMCS L1 keeps for L2 */ gpa_t current_vmptr; @@ -413,7 +414,6 @@ struct vcpu_vmx { struct kvm_vcpu vcpu; unsigned long host_rsp; u8 fail; - u8 cpl; bool nmi_known_unmasked; u32 exit_intr_info; u32 idt_vectoring_info; @@ -2283,7 +2283,7 @@ static __init void nested_vmx_setup_ctls_msrs(void) rdmsr(MSR_IA32_VMX_EXIT_CTLS, nested_vmx_exit_ctls_low, nested_vmx_exit_ctls_high); nested_vmx_exit_ctls_low = VM_EXIT_ALWAYSON_WITHOUT_TRUE_MSR; - /* Note that guest use of VM_EXIT_ACK_INTR_ON_EXIT is not supported. */ + nested_vmx_exit_ctls_high &= #ifdef CONFIG_X86_64 VM_EXIT_HOST_ADDR_SPACE_SIZE | @@ -2291,7 +2291,8 @@ static __init void nested_vmx_setup_ctls_msrs(void) VM_EXIT_LOAD_IA32_PAT | VM_EXIT_SAVE_IA32_PAT; nested_vmx_exit_ctls_high |= VM_EXIT_ALWAYSON_WITHOUT_TRUE_MSR | VM_EXIT_LOAD_IA32_EFER | VM_EXIT_SAVE_IA32_EFER | - VM_EXIT_SAVE_VMX_PREEMPTION_TIMER; + VM_EXIT_SAVE_VMX_PREEMPTION_TIMER | VM_EXIT_ACK_INTR_ON_EXIT; + if (vmx_mpx_supported()) nested_vmx_exit_ctls_high |= VM_EXIT_CLEAR_BNDCFGS; @@ -2353,12 +2354,11 @@ static __init void nested_vmx_setup_ctls_msrs(void) VMX_EPT_INVEPT_BIT; nested_vmx_ept_caps &= vmx_capability.ept; /* - * Since invept is completely emulated we support both global - * and context invalidation independent of what host cpu - * supports + * For nested guests, we don't do anything specific + * for single context invalidation. Hence, only advertise + * support for global context invalidation. */ - nested_vmx_ept_caps |= VMX_EPT_EXTENT_GLOBAL_BIT | - VMX_EPT_EXTENT_CONTEXT_BIT; + nested_vmx_ept_caps |= VMX_EPT_EXTENT_GLOBAL_BIT; } else nested_vmx_ept_caps = 0; @@ -3186,10 +3186,6 @@ static void enter_pmode(struct kvm_vcpu *vcpu) fix_pmode_seg(vcpu, VCPU_SREG_DS, &vmx->rmode.segs[VCPU_SREG_DS]); fix_pmode_seg(vcpu, VCPU_SREG_FS, &vmx->rmode.segs[VCPU_SREG_FS]); fix_pmode_seg(vcpu, VCPU_SREG_GS, &vmx->rmode.segs[VCPU_SREG_GS]); - - /* CPL is always 0 when CPU enters protected mode */ - __set_bit(VCPU_EXREG_CPL, (ulong *)&vcpu->arch.regs_avail); - vmx->cpl = 0; } static void fix_rmode_seg(int seg, struct kvm_segment *save) @@ -3591,22 +3587,14 @@ static int vmx_get_cpl(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); - if (!is_protmode(vcpu)) + if (unlikely(vmx->rmode.vm86_active)) return 0; - - if (!is_long_mode(vcpu) - && (kvm_get_rflags(vcpu) & X86_EFLAGS_VM)) /* if virtual 8086 */ - return 3; - - if (!test_bit(VCPU_EXREG_CPL, (ulong *)&vcpu->arch.regs_avail)) { - __set_bit(VCPU_EXREG_CPL, (ulong *)&vcpu->arch.regs_avail); - vmx->cpl = vmx_read_guest_seg_selector(vmx, VCPU_SREG_CS) & 3; + else { + int ar = vmx_read_guest_seg_ar(vmx, VCPU_SREG_SS); + return AR_DPL(ar); } - - return vmx->cpl; } - static u32 vmx_segment_access_rights(struct kvm_segment *var) { u32 ar; @@ -3634,8 +3622,6 @@ static void vmx_set_segment(struct kvm_vcpu *vcpu, const struct kvm_vmx_segment_field *sf = &kvm_vmx_segment_fields[seg]; vmx_segment_cache_clear(vmx); - if (seg == VCPU_SREG_CS) - __clear_bit(VCPU_EXREG_CPL, (ulong *)&vcpu->arch.regs_avail); if (vmx->rmode.vm86_active && seg != VCPU_SREG_LDTR) { vmx->rmode.segs[seg] = *var; @@ -4564,6 +4550,16 @@ static bool nested_exit_on_intr(struct kvm_vcpu *vcpu) PIN_BASED_EXT_INTR_MASK; } +/* + * In nested virtualization, check if L1 has set + * VM_EXIT_ACK_INTR_ON_EXIT + */ +static bool nested_exit_intr_ack_set(struct kvm_vcpu *vcpu) +{ + return get_vmcs12(vcpu)->vm_exit_controls & + VM_EXIT_ACK_INTR_ON_EXIT; +} + static bool nested_exit_on_nmi(struct kvm_vcpu *vcpu) { return get_vmcs12(vcpu)->pin_based_vm_exec_control & @@ -4878,6 +4874,9 @@ static int handle_exception(struct kvm_vcpu *vcpu) (KVM_GUESTDBG_SINGLESTEP | KVM_GUESTDBG_USE_HW_BP))) { vcpu->arch.dr6 &= ~15; vcpu->arch.dr6 |= dr6; + if (!(dr6 & ~DR6_RESERVED)) /* icebp */ + skip_emulated_instruction(vcpu); + kvm_queue_exception(vcpu, DB_VECTOR); return 1; } @@ -5166,7 +5165,7 @@ static int handle_dr(struct kvm_vcpu *vcpu) return 1; kvm_register_write(vcpu, reg, val); } else - if (kvm_set_dr(vcpu, dr, vcpu->arch.regs[reg])) + if (kvm_set_dr(vcpu, dr, kvm_register_read(vcpu, reg))) return 1; skip_emulated_instruction(vcpu); @@ -5439,7 +5438,7 @@ static int handle_task_switch(struct kvm_vcpu *vcpu) } /* clear all local breakpoint enable flags */ - vmcs_writel(GUEST_DR7, vmcs_readl(GUEST_DR7) & ~55); + vmcs_writel(GUEST_DR7, vmcs_readl(GUEST_DR7) & ~0x55); /* * TODO: What about debug traps on tss switch? @@ -5565,6 +5564,10 @@ static int handle_ept_misconfig(struct kvm_vcpu *vcpu) gpa_t gpa; gpa = vmcs_read64(GUEST_PHYSICAL_ADDRESS); + if (!kvm_io_bus_write(vcpu->kvm, KVM_FAST_MMIO_BUS, gpa, 0, NULL)) { + skip_emulated_instruction(vcpu); + return 1; + } ret = handle_mmio_page_fault_common(vcpu, gpa, true); if (likely(ret == RET_MMIO_PF_EMULATE)) @@ -5669,12 +5672,24 @@ static int handle_pause(struct kvm_vcpu *vcpu) return 1; } -static int handle_invalid_op(struct kvm_vcpu *vcpu) +static int handle_nop(struct kvm_vcpu *vcpu) { - kvm_queue_exception(vcpu, UD_VECTOR); + skip_emulated_instruction(vcpu); return 1; } +static int handle_mwait(struct kvm_vcpu *vcpu) +{ + printk_once(KERN_WARNING "kvm: MWAIT instruction emulated as NOP!\n"); + return handle_nop(vcpu); +} + +static int handle_monitor(struct kvm_vcpu *vcpu) +{ + printk_once(KERN_WARNING "kvm: MONITOR instruction emulated as NOP!\n"); + return handle_nop(vcpu); +} + /* * To run an L2 guest, we need a vmcs02 based on the L1-specified vmcs12. * We could reuse a single VMCS for all the L2 guests, but we also want the @@ -5812,6 +5827,154 @@ static enum hrtimer_restart vmx_preemption_timer_fn(struct hrtimer *timer) } /* + * Decode the memory-address operand of a vmx instruction, as recorded on an + * exit caused by such an instruction (run by a guest hypervisor). + * On success, returns 0. When the operand is invalid, returns 1 and throws + * #UD or #GP. + */ +static int get_vmx_mem_address(struct kvm_vcpu *vcpu, + unsigned long exit_qualification, + u32 vmx_instruction_info, gva_t *ret) +{ + /* + * According to Vol. 3B, "Information for VM Exits Due to Instruction + * Execution", on an exit, vmx_instruction_info holds most of the + * addressing components of the operand. Only the displacement part + * is put in exit_qualification (see 3B, "Basic VM-Exit Information"). + * For how an actual address is calculated from all these components, + * refer to Vol. 1, "Operand Addressing". + */ + int scaling = vmx_instruction_info & 3; + int addr_size = (vmx_instruction_info >> 7) & 7; + bool is_reg = vmx_instruction_info & (1u << 10); + int seg_reg = (vmx_instruction_info >> 15) & 7; + int index_reg = (vmx_instruction_info >> 18) & 0xf; + bool index_is_valid = !(vmx_instruction_info & (1u << 22)); + int base_reg = (vmx_instruction_info >> 23) & 0xf; + bool base_is_valid = !(vmx_instruction_info & (1u << 27)); + + if (is_reg) { + kvm_queue_exception(vcpu, UD_VECTOR); + return 1; + } + + /* Addr = segment_base + offset */ + /* offset = base + [index * scale] + displacement */ + *ret = vmx_get_segment_base(vcpu, seg_reg); + if (base_is_valid) + *ret += kvm_register_read(vcpu, base_reg); + if (index_is_valid) + *ret += kvm_register_read(vcpu, index_reg)<<scaling; + *ret += exit_qualification; /* holds the displacement */ + + if (addr_size == 1) /* 32 bit */ + *ret &= 0xffffffff; + + /* + * TODO: throw #GP (and return 1) in various cases that the VM* + * instructions require it - e.g., offset beyond segment limit, + * unusable or unreadable/unwritable segment, non-canonical 64-bit + * address, and so on. Currently these are not checked. + */ + return 0; +} + +/* + * This function performs the various checks including + * - if it's 4KB aligned + * - No bits beyond the physical address width are set + * - Returns 0 on success or else 1 + * (Intel SDM Section 30.3) + */ +static int nested_vmx_check_vmptr(struct kvm_vcpu *vcpu, int exit_reason, + gpa_t *vmpointer) +{ + gva_t gva; + gpa_t vmptr; + struct x86_exception e; + struct page *page; + struct vcpu_vmx *vmx = to_vmx(vcpu); + int maxphyaddr = cpuid_maxphyaddr(vcpu); + + if (get_vmx_mem_address(vcpu, vmcs_readl(EXIT_QUALIFICATION), + vmcs_read32(VMX_INSTRUCTION_INFO), &gva)) + return 1; + + if (kvm_read_guest_virt(&vcpu->arch.emulate_ctxt, gva, &vmptr, + sizeof(vmptr), &e)) { + kvm_inject_page_fault(vcpu, &e); + return 1; + } + + switch (exit_reason) { + case EXIT_REASON_VMON: + /* + * SDM 3: 24.11.5 + * The first 4 bytes of VMXON region contain the supported + * VMCS revision identifier + * + * Note - IA32_VMX_BASIC[48] will never be 1 + * for the nested case; + * which replaces physical address width with 32 + * + */ + if (!IS_ALIGNED(vmptr, PAGE_SIZE) || (vmptr >> maxphyaddr)) { + nested_vmx_failInvalid(vcpu); + skip_emulated_instruction(vcpu); + return 1; + } + + page = nested_get_page(vcpu, vmptr); + if (page == NULL || + *(u32 *)kmap(page) != VMCS12_REVISION) { + nested_vmx_failInvalid(vcpu); + kunmap(page); + skip_emulated_instruction(vcpu); + return 1; + } + kunmap(page); + vmx->nested.vmxon_ptr = vmptr; + break; + case EXIT_REASON_VMCLEAR: + if (!IS_ALIGNED(vmptr, PAGE_SIZE) || (vmptr >> maxphyaddr)) { + nested_vmx_failValid(vcpu, + VMXERR_VMCLEAR_INVALID_ADDRESS); + skip_emulated_instruction(vcpu); + return 1; + } + + if (vmptr == vmx->nested.vmxon_ptr) { + nested_vmx_failValid(vcpu, + VMXERR_VMCLEAR_VMXON_POINTER); + skip_emulated_instruction(vcpu); + return 1; + } + break; + case EXIT_REASON_VMPTRLD: + if (!IS_ALIGNED(vmptr, PAGE_SIZE) || (vmptr >> maxphyaddr)) { + nested_vmx_failValid(vcpu, + VMXERR_VMPTRLD_INVALID_ADDRESS); + skip_emulated_instruction(vcpu); + return 1; + } + + if (vmptr == vmx->nested.vmxon_ptr) { + nested_vmx_failValid(vcpu, + VMXERR_VMCLEAR_VMXON_POINTER); + skip_emulated_instruction(vcpu); + return 1; + } + break; + default: + return 1; /* shouldn't happen */ + } + + if (vmpointer) + *vmpointer = vmptr; + return 0; +} + +/* * Emulate the VMXON instruction. * Currently, we just remember that VMX is active, and do not save or even * inspect the argument to VMXON (the so-called "VMXON pointer") because we @@ -5849,6 +6012,10 @@ static int handle_vmon(struct kvm_vcpu *vcpu) kvm_inject_gp(vcpu, 0); return 1; } + + if (nested_vmx_check_vmptr(vcpu, EXIT_REASON_VMON, NULL)) + return 1; + if (vmx->nested.vmxon) { nested_vmx_failValid(vcpu, VMXERR_VMXON_IN_VMX_ROOT_OPERATION); skip_emulated_instruction(vcpu); @@ -5971,87 +6138,19 @@ static int handle_vmoff(struct kvm_vcpu *vcpu) return 1; } -/* - * Decode the memory-address operand of a vmx instruction, as recorded on an - * exit caused by such an instruction (run by a guest hypervisor). - * On success, returns 0. When the operand is invalid, returns 1 and throws - * #UD or #GP. - */ -static int get_vmx_mem_address(struct kvm_vcpu *vcpu, - unsigned long exit_qualification, - u32 vmx_instruction_info, gva_t *ret) -{ - /* - * According to Vol. 3B, "Information for VM Exits Due to Instruction - * Execution", on an exit, vmx_instruction_info holds most of the - * addressing components of the operand. Only the displacement part - * is put in exit_qualification (see 3B, "Basic VM-Exit Information"). - * For how an actual address is calculated from all these components, - * refer to Vol. 1, "Operand Addressing". - */ - int scaling = vmx_instruction_info & 3; - int addr_size = (vmx_instruction_info >> 7) & 7; - bool is_reg = vmx_instruction_info & (1u << 10); - int seg_reg = (vmx_instruction_info >> 15) & 7; - int index_reg = (vmx_instruction_info >> 18) & 0xf; - bool index_is_valid = !(vmx_instruction_info & (1u << 22)); - int base_reg = (vmx_instruction_info >> 23) & 0xf; - bool base_is_valid = !(vmx_instruction_info & (1u << 27)); - - if (is_reg) { - kvm_queue_exception(vcpu, UD_VECTOR); - return 1; - } - - /* Addr = segment_base + offset */ - /* offset = base + [index * scale] + displacement */ - *ret = vmx_get_segment_base(vcpu, seg_reg); - if (base_is_valid) - *ret += kvm_register_read(vcpu, base_reg); - if (index_is_valid) - *ret += kvm_register_read(vcpu, index_reg)<<scaling; - *ret += exit_qualification; /* holds the displacement */ - - if (addr_size == 1) /* 32 bit */ - *ret &= 0xffffffff; - - /* - * TODO: throw #GP (and return 1) in various cases that the VM* - * instructions require it - e.g., offset beyond segment limit, - * unusable or unreadable/unwritable segment, non-canonical 64-bit - * address, and so on. Currently these are not checked. - */ - return 0; -} - /* Emulate the VMCLEAR instruction */ static int handle_vmclear(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); - gva_t gva; gpa_t vmptr; struct vmcs12 *vmcs12; struct page *page; - struct x86_exception e; if (!nested_vmx_check_permission(vcpu)) return 1; - if (get_vmx_mem_address(vcpu, vmcs_readl(EXIT_QUALIFICATION), - vmcs_read32(VMX_INSTRUCTION_INFO), &gva)) - return 1; - - if (kvm_read_guest_virt(&vcpu->arch.emulate_ctxt, gva, &vmptr, - sizeof(vmptr), &e)) { - kvm_inject_page_fault(vcpu, &e); - return 1; - } - - if (!IS_ALIGNED(vmptr, PAGE_SIZE)) { - nested_vmx_failValid(vcpu, VMXERR_VMCLEAR_INVALID_ADDRESS); - skip_emulated_instruction(vcpu); + if (nested_vmx_check_vmptr(vcpu, EXIT_REASON_VMCLEAR, &vmptr)) return 1; - } if (vmptr == vmx->nested.current_vmptr) { nested_release_vmcs12(vmx); @@ -6372,29 +6471,14 @@ static int handle_vmwrite(struct kvm_vcpu *vcpu) static int handle_vmptrld(struct kvm_vcpu *vcpu) { struct vcpu_vmx *vmx = to_vmx(vcpu); - gva_t gva; gpa_t vmptr; - struct x86_exception e; u32 exec_control; if (!nested_vmx_check_permission(vcpu)) return 1; - if (get_vmx_mem_address(vcpu, vmcs_readl(EXIT_QUALIFICATION), - vmcs_read32(VMX_INSTRUCTION_INFO), &gva)) - return 1; - - if (kvm_read_guest_virt(&vcpu->arch.emulate_ctxt, gva, &vmptr, - sizeof(vmptr), &e)) { - kvm_inject_page_fault(vcpu, &e); - return 1; - } - - if (!IS_ALIGNED(vmptr, PAGE_SIZE)) { - nested_vmx_failValid(vcpu, VMXERR_VMPTRLD_INVALID_ADDRESS); - skip_emulated_instruction(vcpu); + if (nested_vmx_check_vmptr(vcpu, EXIT_REASON_VMPTRLD, &vmptr)) return 1; - } if (vmx->nested.current_vmptr != vmptr) { struct vmcs12 *new_vmcs12; @@ -6471,7 +6555,6 @@ static int handle_invept(struct kvm_vcpu *vcpu) struct { u64 eptp, gpa; } operand; - u64 eptp_mask = ((1ull << 51) - 1) & PAGE_MASK; if (!(nested_vmx_secondary_ctls_high & SECONDARY_EXEC_ENABLE_EPT) || !(nested_vmx_ept_caps & VMX_EPT_INVEPT_BIT)) { @@ -6511,16 +6594,13 @@ static int handle_invept(struct kvm_vcpu *vcpu) } switch (type) { - case VMX_EPT_EXTENT_CONTEXT: - if ((operand.eptp & eptp_mask) != - (nested_ept_get_cr3(vcpu) & eptp_mask)) - break; case VMX_EPT_EXTENT_GLOBAL: kvm_mmu_sync_roots(vcpu); kvm_mmu_flush_tlb(vcpu); nested_vmx_succeed(vcpu); break; default: + /* Trap single context invalidation invept calls */ BUG_ON(1); break; } @@ -6571,8 +6651,8 @@ static int (*const kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu) = { [EXIT_REASON_EPT_VIOLATION] = handle_ept_violation, [EXIT_REASON_EPT_MISCONFIG] = handle_ept_misconfig, [EXIT_REASON_PAUSE_INSTRUCTION] = handle_pause, - [EXIT_REASON_MWAIT_INSTRUCTION] = handle_invalid_op, - [EXIT_REASON_MONITOR_INSTRUCTION] = handle_invalid_op, + [EXIT_REASON_MWAIT_INSTRUCTION] = handle_mwait, + [EXIT_REASON_MONITOR_INSTRUCTION] = handle_monitor, [EXIT_REASON_INVEPT] = handle_invept, }; @@ -7413,7 +7493,6 @@ static void __noclone vmx_vcpu_run(struct kvm_vcpu *vcpu) vcpu->arch.regs_avail = ~((1 << VCPU_REGS_RIP) | (1 << VCPU_REGS_RSP) | (1 << VCPU_EXREG_RFLAGS) - | (1 << VCPU_EXREG_CPL) | (1 << VCPU_EXREG_PDPTR) | (1 << VCPU_EXREG_SEGMENTS) | (1 << VCPU_EXREG_CR3)); @@ -7778,7 +7857,8 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) exec_control = vmcs12->pin_based_vm_exec_control; exec_control |= vmcs_config.pin_based_exec_ctrl; - exec_control &= ~PIN_BASED_VMX_PREEMPTION_TIMER; + exec_control &= ~(PIN_BASED_VMX_PREEMPTION_TIMER | + PIN_BASED_POSTED_INTR); vmcs_write32(PIN_BASED_VM_EXEC_CONTROL, exec_control); vmx->nested.preemption_timer_expired = false; @@ -7815,7 +7895,9 @@ static void prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12) if (!vmx->rdtscp_enabled) exec_control &= ~SECONDARY_EXEC_RDTSCP; /* Take the following fields only from vmcs12 */ - exec_control &= ~SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES; + exec_control &= ~(SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES | + SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY | + SECONDARY_EXEC_APIC_REGISTER_VIRT); if (nested_cpu_has(vmcs12, CPU_BASED_ACTIVATE_SECONDARY_CONTROLS)) exec_control |= vmcs12->secondary_vm_exec_control; @@ -8598,6 +8680,14 @@ static void nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 exit_reason, prepare_vmcs12(vcpu, vmcs12, exit_reason, exit_intr_info, exit_qualification); + if ((exit_reason == EXIT_REASON_EXTERNAL_INTERRUPT) + && nested_exit_intr_ack_set(vcpu)) { + int irq = kvm_cpu_get_interrupt(vcpu); + WARN_ON(irq < 0); + vmcs12->vm_exit_intr_info = irq | + INTR_INFO_VALID_MASK | INTR_TYPE_EXT_INTR; + } + trace_kvm_nested_vmexit_inject(vmcs12->vm_exit_reason, vmcs12->exit_qualification, vmcs12->idt_vectoring_info_field, diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index b6c0bac..f32a025 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -106,6 +106,8 @@ EXPORT_SYMBOL_GPL(kvm_max_guest_tsc_khz); static u32 tsc_tolerance_ppm = 250; module_param(tsc_tolerance_ppm, uint, S_IRUGO | S_IWUSR); +static bool backwards_tsc_observed = false; + #define KVM_NR_SHARED_MSRS 16 struct kvm_shared_msrs_global { @@ -702,25 +704,11 @@ int kvm_set_cr3(struct kvm_vcpu *vcpu, unsigned long cr3) } if (is_long_mode(vcpu)) { - if (kvm_read_cr4_bits(vcpu, X86_CR4_PCIDE)) { - if (cr3 & CR3_PCID_ENABLED_RESERVED_BITS) - return 1; - } else - if (cr3 & CR3_L_MODE_RESERVED_BITS) - return 1; - } else { - if (is_pae(vcpu)) { - if (cr3 & CR3_PAE_RESERVED_BITS) - return 1; - if (is_paging(vcpu) && - !load_pdptrs(vcpu, vcpu->arch.walk_mmu, cr3)) - return 1; - } - /* - * We don't check reserved bits in nonpae mode, because - * this isn't enforced, and VMware depends on this. - */ - } + if (cr3 & CR3_L_MODE_RESERVED_BITS) + return 1; + } else if (is_pae(vcpu) && is_paging(vcpu) && + !load_pdptrs(vcpu, vcpu->arch.walk_mmu, cr3)) + return 1; vcpu->arch.cr3 = cr3; __set_bit(VCPU_EXREG_CR3, (ulong *)&vcpu->arch.regs_avail); @@ -1486,7 +1474,8 @@ static void pvclock_update_vm_gtod_copy(struct kvm *kvm) &ka->master_kernel_ns, &ka->master_cycle_now); - ka->use_master_clock = host_tsc_clocksource & vcpus_matched; + ka->use_master_clock = host_tsc_clocksource && vcpus_matched + && !backwards_tsc_observed; if (ka->use_master_clock) atomic_set(&kvm_guest_has_master_clock, 1); @@ -1932,6 +1921,8 @@ static int set_msr_hyperv(struct kvm_vcpu *vcpu, u32 msr, u64 data) if (!(data & HV_X64_MSR_APIC_ASSIST_PAGE_ENABLE)) { vcpu->arch.hv_vapic = data; + if (kvm_lapic_enable_pv_eoi(vcpu, 0)) + return 1; break; } gfn = data >> HV_X64_MSR_APIC_ASSIST_PAGE_ADDRESS_SHIFT; @@ -1942,6 +1933,8 @@ static int set_msr_hyperv(struct kvm_vcpu *vcpu, u32 msr, u64 data) return 1; vcpu->arch.hv_vapic = data; mark_page_dirty(vcpu->kvm, gfn); + if (kvm_lapic_enable_pv_eoi(vcpu, gfn_to_gpa(gfn) | KVM_MSR_ENABLED)) + return 1; break; } case HV_X64_MSR_EOI: @@ -2644,6 +2637,7 @@ int kvm_dev_ioctl_check_extension(long ext) case KVM_CAP_IRQ_INJECT_STATUS: case KVM_CAP_IRQFD: case KVM_CAP_IOEVENTFD: + case KVM_CAP_IOEVENTFD_NO_LENGTH: case KVM_CAP_PIT2: case KVM_CAP_PIT_STATE2: case KVM_CAP_SET_IDENTITY_MAP_ADDR: @@ -3646,11 +3640,19 @@ int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log) offset = i * BITS_PER_LONG; kvm_mmu_write_protect_pt_masked(kvm, memslot, offset, mask); } - if (is_dirty) - kvm_flush_remote_tlbs(kvm); spin_unlock(&kvm->mmu_lock); + /* See the comments in kvm_mmu_slot_remove_write_access(). */ + lockdep_assert_held(&kvm->slots_lock); + + /* + * All the TLBs can be flushed out of mmu lock, see the comments in + * kvm_mmu_slot_remove_write_access(). + */ + if (is_dirty) + kvm_flush_remote_tlbs(kvm); + r = -EFAULT; if (copy_to_user(log->dirty_bitmap, dirty_bitmap_buffer, n)) goto out; @@ -4486,8 +4488,6 @@ static int emulator_pio_in_out(struct kvm_vcpu *vcpu, int size, unsigned short port, void *val, unsigned int count, bool in) { - trace_kvm_pio(!in, port, size, count); - vcpu->arch.pio.port = port; vcpu->arch.pio.in = in; vcpu->arch.pio.count = count; @@ -4522,6 +4522,7 @@ static int emulator_pio_in_emulated(struct x86_emulate_ctxt *ctxt, if (ret) { data_avail: memcpy(val, vcpu->arch.pio_data, size * count); + trace_kvm_pio(KVM_PIO_IN, port, size, count, vcpu->arch.pio_data); vcpu->arch.pio.count = 0; return 1; } @@ -4536,6 +4537,7 @@ static int emulator_pio_out_emulated(struct x86_emulate_ctxt *ctxt, struct kvm_vcpu *vcpu = emul_to_vcpu(ctxt); memcpy(vcpu->arch.pio_data, val, size * count); + trace_kvm_pio(KVM_PIO_OUT, port, size, count, vcpu->arch.pio_data); return emulator_pio_in_out(vcpu, size, port, (void *)val, count, false); } @@ -4647,11 +4649,6 @@ static int emulator_set_cr(struct x86_emulate_ctxt *ctxt, int cr, ulong val) return res; } -static void emulator_set_rflags(struct x86_emulate_ctxt *ctxt, ulong val) -{ - kvm_set_rflags(emul_to_vcpu(ctxt), val); -} - static int emulator_get_cpl(struct x86_emulate_ctxt *ctxt) { return kvm_x86_ops->get_cpl(emul_to_vcpu(ctxt)); @@ -4836,7 +4833,6 @@ static const struct x86_emulate_ops emulate_ops = { .set_idt = emulator_set_idt, .get_cr = emulator_get_cr, .set_cr = emulator_set_cr, - .set_rflags = emulator_set_rflags, .cpl = emulator_get_cpl, .get_dr = emulator_get_dr, .set_dr = emulator_set_dr, @@ -4902,7 +4898,7 @@ static void init_emulate_ctxt(struct kvm_vcpu *vcpu) ctxt->eip = kvm_rip_read(vcpu); ctxt->mode = (!is_protmode(vcpu)) ? X86EMUL_MODE_REAL : (ctxt->eflags & X86_EFLAGS_VM) ? X86EMUL_MODE_VM86 : - cs_l ? X86EMUL_MODE_PROT64 : + (cs_l && is_long_mode(vcpu)) ? X86EMUL_MODE_PROT64 : cs_db ? X86EMUL_MODE_PROT32 : X86EMUL_MODE_PROT16; ctxt->guest_mode = is_guest_mode(vcpu); @@ -6945,6 +6941,7 @@ int kvm_arch_hardware_enable(void *garbage) */ if (backwards_tsc) { u64 delta_cyc = max_tsc - local_tsc; + backwards_tsc_observed = true; list_for_each_entry(kvm, &vm_list, vm_list) { kvm_for_each_vcpu(i, vcpu, kvm) { vcpu->arch.tsc_offset_adjustment += delta_cyc; @@ -7329,8 +7326,12 @@ void kvm_arch_commit_memory_region(struct kvm *kvm, kvm_mmu_change_mmu_pages(kvm, nr_mmu_pages); /* * Write protect all pages for dirty logging. - * Existing largepage mappings are destroyed here and new ones will - * not be created until the end of the logging. + * + * All the sptes including the large sptes which point to this + * slot are set to readonly. We can not create any new large + * spte on this slot until the end of the logging. + * + * See the comments in fast_page_fault(). */ if ((change != KVM_MR_DELETE) && (mem->flags & KVM_MEM_LOG_DIRTY_PAGES)) kvm_mmu_slot_remove_write_access(kvm, mem->slot); diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile index eabcb6e..4d4f96a 100644 --- a/arch/x86/lib/Makefile +++ b/arch/x86/lib/Makefile @@ -16,7 +16,7 @@ clean-files := inat-tables.c obj-$(CONFIG_SMP) += msr-smp.o cache-smp.o -lib-y := delay.o misc.o +lib-y := delay.o misc.o cmdline.o lib-y += thunk_$(BITS).o lib-y += usercopy_$(BITS).o usercopy.o getuser.o putuser.o lib-y += memcpy_$(BITS).o diff --git a/arch/x86/lib/cmdline.c b/arch/x86/lib/cmdline.c new file mode 100644 index 0000000..422db00 --- /dev/null +++ b/arch/x86/lib/cmdline.c @@ -0,0 +1,84 @@ +/* + * This file is part of the Linux kernel, and is made available under + * the terms of the GNU General Public License version 2. + * + * Misc librarized functions for cmdline poking. + */ +#include <linux/kernel.h> +#include <linux/string.h> +#include <linux/ctype.h> +#include <asm/setup.h> + +static inline int myisspace(u8 c) +{ + return c <= ' '; /* Close enough approximation */ +} + +/** + * Find a boolean option (like quiet,noapic,nosmp....) + * + * @cmdline: the cmdline string + * @option: option string to look for + * + * Returns the position of that @option (starts counting with 1) + * or 0 on not found. + */ +int cmdline_find_option_bool(const char *cmdline, const char *option) +{ + char c; + int len, pos = 0, wstart = 0; + const char *opptr = NULL; + enum { + st_wordstart = 0, /* Start of word/after whitespace */ + st_wordcmp, /* Comparing this word */ + st_wordskip, /* Miscompare, skip */ + } state = st_wordstart; + + if (!cmdline) + return -1; /* No command line */ + + len = min_t(int, strlen(cmdline), COMMAND_LINE_SIZE); + if (!len) + return 0; + + while (len--) { + c = *(char *)cmdline++; + pos++; + + switch (state) { + case st_wordstart: + if (!c) + return 0; + else if (myisspace(c)) + break; + + state = st_wordcmp; + opptr = option; + wstart = pos; + /* fall through */ + + case st_wordcmp: + if (!*opptr) + if (!c || myisspace(c)) + return wstart; + else + state = st_wordskip; + else if (!c) + return 0; + else if (c != *opptr++) + state = st_wordskip; + else if (!len) /* last word and is matching */ + return wstart; + break; + + case st_wordskip: + if (!c) + return 0; + else if (myisspace(c)) + state = st_wordstart; + break; + } + } + + return 0; /* Buffer overrun */ +} diff --git a/arch/x86/mm/hugetlbpage.c b/arch/x86/mm/hugetlbpage.c index 8c9f647..8b977eb 100644 --- a/arch/x86/mm/hugetlbpage.c +++ b/arch/x86/mm/hugetlbpage.c @@ -58,11 +58,6 @@ follow_huge_pmd(struct mm_struct *mm, unsigned long address, { return NULL; } - -int pmd_huge_support(void) -{ - return 0; -} #else struct page * @@ -80,11 +75,6 @@ int pud_huge(pud_t pud) { return !!(pud_val(pud) & _PAGE_PSE); } - -int pmd_huge_support(void) -{ - return 1; -} #endif #ifdef CONFIG_HUGETLB_PAGE diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index f35c66c..b92591f 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -1230,17 +1230,43 @@ const char *arch_vma_name(struct vm_area_struct *vma) return NULL; } -#ifdef CONFIG_X86_UV -unsigned long memory_block_size_bytes(void) +static unsigned long probe_memory_block_size(void) { + /* start from 2g */ + unsigned long bz = 1UL<<31; + +#ifdef CONFIG_X86_UV if (is_uv_system()) { printk(KERN_INFO "UV: memory block size 2GB\n"); return 2UL * 1024 * 1024 * 1024; } - return MIN_MEMORY_BLOCK_SIZE; -} #endif + /* less than 64g installed */ + if ((max_pfn << PAGE_SHIFT) < (16UL << 32)) + return MIN_MEMORY_BLOCK_SIZE; + + /* get the tail size */ + while (bz > MIN_MEMORY_BLOCK_SIZE) { + if (!((max_pfn << PAGE_SHIFT) & (bz - 1))) + break; + bz >>= 1; + } + + printk(KERN_DEBUG "memory block size : %ldMB\n", bz >> 20); + + return bz; +} + +static unsigned long memory_block_size_probed; +unsigned long memory_block_size_bytes(void) +{ + if (!memory_block_size_probed) + memory_block_size_probed = probe_memory_block_size(); + + return memory_block_size_probed; +} + #ifdef CONFIG_SPARSEMEM_VMEMMAP /* * Initialise the sparsemem vmemmap using huge-pages at the PMD level. diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c index 597ac15..bc7527e 100644 --- a/arch/x86/mm/ioremap.c +++ b/arch/x86/mm/ioremap.c @@ -50,6 +50,21 @@ int ioremap_change_attr(unsigned long vaddr, unsigned long size, return err; } +static int __ioremap_check_ram(unsigned long start_pfn, unsigned long nr_pages, + void *arg) +{ + unsigned long i; + + for (i = 0; i < nr_pages; ++i) + if (pfn_valid(start_pfn + i) && + !PageReserved(pfn_to_page(start_pfn + i))) + return 1; + + WARN_ONCE(1, "ioremap on RAM pfn 0x%lx\n", start_pfn); + + return 0; +} + /* * Remap an arbitrary physical address space into the kernel virtual * address space. Needed when the kernel wants to access high addresses @@ -93,14 +108,11 @@ static void __iomem *__ioremap_caller(resource_size_t phys_addr, /* * Don't allow anybody to remap normal RAM that we're using.. */ + pfn = phys_addr >> PAGE_SHIFT; last_pfn = last_addr >> PAGE_SHIFT; - for (pfn = phys_addr >> PAGE_SHIFT; pfn <= last_pfn; pfn++) { - int is_ram = page_is_ram(pfn); - - if (is_ram && pfn_valid(pfn) && !PageReserved(pfn_to_page(pfn))) - return NULL; - WARN_ON_ONCE(is_ram); - } + if (walk_system_ram_range(pfn, last_pfn - pfn + 1, NULL, + __ioremap_check_ram) == 1) + return NULL; /* * Mappings have to be page-aligned diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c index 1d045f9..a32b706 100644 --- a/arch/x86/mm/numa.c +++ b/arch/x86/mm/numa.c @@ -559,7 +559,7 @@ static void __init numa_clear_kernel_node_hotplug(void) int i, nid; nodemask_t numa_kernel_nodes = NODE_MASK_NONE; unsigned long start, end; - struct memblock_type *type = &memblock.reserved; + struct memblock_region *r; /* * At this time, all memory regions reserved by memblock are @@ -573,8 +573,8 @@ static void __init numa_clear_kernel_node_hotplug(void) } /* Mark all kernel nodes. */ - for (i = 0; i < type->cnt; i++) - node_set(type->regions[i].nid, numa_kernel_nodes); + for_each_memblock(reserved, r) + node_set(r->nid, numa_kernel_nodes); /* Clear MEMBLOCK_HOTPLUG flag for memory in kernel nodes. */ for (i = 0; i < numa_meminfo.nr_blks; i++) { diff --git a/arch/x86/mm/pageattr-test.c b/arch/x86/mm/pageattr-test.c index 461bc82..6629f39 100644 --- a/arch/x86/mm/pageattr-test.c +++ b/arch/x86/mm/pageattr-test.c @@ -35,7 +35,7 @@ enum { static int pte_testbit(pte_t pte) { - return pte_flags(pte) & _PAGE_UNUSED1; + return pte_flags(pte) & _PAGE_SOFTW1; } struct split_state { diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c index c96314a..0004ac7 100644 --- a/arch/x86/mm/pgtable.c +++ b/arch/x86/mm/pgtable.c @@ -399,13 +399,20 @@ int pmdp_test_and_clear_young(struct vm_area_struct *vma, int ptep_clear_flush_young(struct vm_area_struct *vma, unsigned long address, pte_t *ptep) { - int young; - - young = ptep_test_and_clear_young(vma, address, ptep); - if (young) - flush_tlb_page(vma, address); - - return young; + /* + * On x86 CPUs, clearing the accessed bit without a TLB flush + * doesn't cause data corruption. [ It could cause incorrect + * page aging and the (mistaken) reclaim of hot pages, but the + * chance of that should be relatively low. ] + * + * So as a performance optimization don't flush the TLB when + * clearing the accessed bit, it will eventually be flushed by + * a context switch or a VM operation anyway. [ In the rare + * event of it not getting flushed for a long time the delay + * shouldn't really matter because there's no real memory + * pressure for swapout to react to. ] + */ + return ptep_test_and_clear_young(vma, address, ptep); } #ifdef CONFIG_TRANSPARENT_HUGEPAGE diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index dc01773..6d5663a 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -171,7 +171,7 @@ static struct bpf_binary_header *bpf_alloc_binary(unsigned int proglen, memset(header, 0xcc, sz); /* fill whole space with int3 instructions */ header->pages = sz / PAGE_SIZE; - hole = sz - (proglen + sizeof(*header)); + hole = min(sz - (proglen + sizeof(*header)), PAGE_SIZE - sizeof(*header)); /* insert a random number of int3 instructions before BPF code */ *image_ptr = &header->image[prandom_u32() % hole]; diff --git a/arch/x86/pci/acpi.c b/arch/x86/pci/acpi.c index 01edac6..5075371 100644 --- a/arch/x86/pci/acpi.c +++ b/arch/x86/pci/acpi.c @@ -489,8 +489,12 @@ struct pci_bus *pci_acpi_scan_root(struct acpi_pci_root *root) } node = acpi_get_node(device->handle); - if (node == NUMA_NO_NODE) + if (node == NUMA_NO_NODE) { node = x86_pci_root_bus_node(busnum); + if (node != 0 && node != NUMA_NO_NODE) + dev_info(&device->dev, FW_BUG "no _PXM; falling back to node %d from hardware (may be inconsistent with ACPI node numbers)\n", + node); + } if (node != NUMA_NO_NODE && !node_online(node)) node = NUMA_NO_NODE; diff --git a/arch/x86/pci/amd_bus.c b/arch/x86/pci/amd_bus.c index e88f4c5..c20d2cc 100644 --- a/arch/x86/pci/amd_bus.c +++ b/arch/x86/pci/amd_bus.c @@ -11,27 +11,33 @@ #include "bus_numa.h" -/* - * This discovers the pcibus <-> node mapping on AMD K8. - * also get peer root bus resource for io,mmio - */ +#define AMD_NB_F0_NODE_ID 0x60 +#define AMD_NB_F0_UNIT_ID 0x64 +#define AMD_NB_F1_CONFIG_MAP_REG 0xe0 + +#define RANGE_NUM 16 +#define AMD_NB_F1_CONFIG_MAP_RANGES 4 -struct pci_hostbridge_probe { +struct amd_hostbridge { u32 bus; u32 slot; - u32 vendor; u32 device; }; -static struct pci_hostbridge_probe pci_probes[] __initdata = { - { 0, 0x18, PCI_VENDOR_ID_AMD, 0x1100 }, - { 0, 0x18, PCI_VENDOR_ID_AMD, 0x1200 }, - { 0xff, 0, PCI_VENDOR_ID_AMD, 0x1200 }, - { 0, 0x18, PCI_VENDOR_ID_AMD, 0x1300 }, +/* + * IMPORTANT NOTE: + * hb_probes[] and early_root_info_init() is in maintenance mode. + * It only supports K8, Fam10h, Fam11h, and Fam15h_00h-0fh . + * Future processor will rely on information in ACPI. + */ +static struct amd_hostbridge hb_probes[] __initdata = { + { 0, 0x18, 0x1100 }, /* K8 */ + { 0, 0x18, 0x1200 }, /* Family10h */ + { 0xff, 0, 0x1200 }, /* Family10h */ + { 0, 0x18, 0x1300 }, /* Family11h */ + { 0, 0x18, 0x1600 }, /* Family15h */ }; -#define RANGE_NUM 16 - static struct pci_root_info __init *find_pci_root_info(int node, int link) { struct pci_root_info *info; @@ -45,12 +51,12 @@ static struct pci_root_info __init *find_pci_root_info(int node, int link) } /** - * early_fill_mp_bus_to_node() + * early_root_info_init() * called before pcibios_scan_root and pci_scan_bus - * fills the mp_bus_to_cpumask array based according to the LDT Bus Number - * Registers found in the K8 northbridge + * fills the mp_bus_to_cpumask array based according + * to the LDT Bus Number Registers found in the northbridge. */ -static int __init early_fill_mp_bus_info(void) +static int __init early_root_info_init(void) { int i; unsigned bus; @@ -75,19 +81,21 @@ static int __init early_fill_mp_bus_info(void) return -1; found = false; - for (i = 0; i < ARRAY_SIZE(pci_probes); i++) { + for (i = 0; i < ARRAY_SIZE(hb_probes); i++) { u32 id; u16 device; u16 vendor; - bus = pci_probes[i].bus; - slot = pci_probes[i].slot; + bus = hb_probes[i].bus; + slot = hb_probes[i].slot; id = read_pci_config(bus, slot, 0, PCI_VENDOR_ID); - vendor = id & 0xffff; device = (id>>16) & 0xffff; - if (pci_probes[i].vendor == vendor && - pci_probes[i].device == device) { + + if (vendor != PCI_VENDOR_ID_AMD) + continue; + + if (hb_probes[i].device == device) { found = true; break; } @@ -96,10 +104,16 @@ static int __init early_fill_mp_bus_info(void) if (!found) return 0; - for (i = 0; i < 4; i++) { + /* + * We should learn topology and routing information from _PXM and + * _CRS methods in the ACPI namespace. We extract node numbers + * here to work around BIOSes that don't supply _PXM. + */ + for (i = 0; i < AMD_NB_F1_CONFIG_MAP_RANGES; i++) { int min_bus; int max_bus; - reg = read_pci_config(bus, slot, 1, 0xe0 + (i << 2)); + reg = read_pci_config(bus, slot, 1, + AMD_NB_F1_CONFIG_MAP_REG + (i << 2)); /* Check if that register is enabled for bus range */ if ((reg & 7) != 3) @@ -113,10 +127,21 @@ static int __init early_fill_mp_bus_info(void) info = alloc_pci_root_info(min_bus, max_bus, node, link); } + /* + * The following code extracts routing information for use on old + * systems where Linux doesn't automatically use host bridge _CRS + * methods (or when the user specifies "pci=nocrs"). + * + * We only do this through Fam11h, because _CRS should be enough on + * newer systems. + */ + if (boot_cpu_data.x86 > 0x11) + return 0; + /* get the default node and link for left over res */ - reg = read_pci_config(bus, slot, 0, 0x60); + reg = read_pci_config(bus, slot, 0, AMD_NB_F0_NODE_ID); def_node = (reg >> 8) & 0x07; - reg = read_pci_config(bus, slot, 0, 0x64); + reg = read_pci_config(bus, slot, 0, AMD_NB_F0_UNIT_ID); def_link = (reg >> 8) & 0x03; memset(range, 0, sizeof(range)); @@ -363,7 +388,7 @@ static int __init pci_io_ecs_init(void) int cpu; /* assume all cpus from fam10h have IO ECS */ - if (boot_cpu_data.x86 < 0x10) + if (boot_cpu_data.x86 < 0x10) return 0; /* Try the PCI method first. */ @@ -387,7 +412,7 @@ static int __init amd_postcore_init(void) if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD) return 0; - early_fill_mp_bus_info(); + early_root_info_init(); pci_io_ecs_init(); return 0; diff --git a/arch/x86/pci/broadcom_bus.c b/arch/x86/pci/broadcom_bus.c index 614392c..bb461cf 100644 --- a/arch/x86/pci/broadcom_bus.c +++ b/arch/x86/pci/broadcom_bus.c @@ -60,8 +60,8 @@ static void __init cnb20le_res(u8 bus, u8 slot, u8 func) word1 = read_pci_config_16(bus, slot, func, 0xc4); word2 = read_pci_config_16(bus, slot, func, 0xc6); if (word1 != word2) { - res.start = (word1 << 16) | 0x0000; - res.end = (word2 << 16) | 0xffff; + res.start = ((resource_size_t) word1 << 16) | 0x0000; + res.end = ((resource_size_t) word2 << 16) | 0xffff; res.flags = IORESOURCE_MEM | IORESOURCE_PREFETCH; update_res(info, res.start, res.end, res.flags, 0); } diff --git a/arch/x86/pci/fixup.c b/arch/x86/pci/fixup.c index 94ae9ae..b5e6026 100644 --- a/arch/x86/pci/fixup.c +++ b/arch/x86/pci/fixup.c @@ -6,6 +6,7 @@ #include <linux/dmi.h> #include <linux/pci.h> #include <linux/vgaarb.h> +#include <asm/hpet.h> #include <asm/pci_x86.h> static void pci_fixup_i450nx(struct pci_dev *d) @@ -337,9 +338,7 @@ static void pci_fixup_video(struct pci_dev *pdev) * type BRIDGE, or CARDBUS. Host to PCI controllers use * PCI header type NORMAL. */ - if (bridge - && ((bridge->hdr_type == PCI_HEADER_TYPE_BRIDGE) - || (bridge->hdr_type == PCI_HEADER_TYPE_CARDBUS))) { + if (bridge && (pci_is_bridge(bridge))) { pci_read_config_word(bridge, PCI_BRIDGE_CONTROL, &config); if (!(config & PCI_BRIDGE_CTL_VGA)) @@ -526,6 +525,19 @@ static void sb600_disable_hpet_bar(struct pci_dev *dev) } DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_ATI, 0x4385, sb600_disable_hpet_bar); +#ifdef CONFIG_HPET_TIMER +static void sb600_hpet_quirk(struct pci_dev *dev) +{ + struct resource *r = &dev->resource[1]; + + if (r->flags & IORESOURCE_MEM && r->start == hpet_address) { + r->flags |= IORESOURCE_PCI_FIXED; + dev_info(&dev->dev, "reg 0x14 contains HPET; making it immovable\n"); + } +} +DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_ATI, 0x4385, sb600_hpet_quirk); +#endif + /* * Twinhead H12Y needs us to block out a region otherwise we map devices * there and any access kills the box. diff --git a/arch/x86/pci/i386.c b/arch/x86/pci/i386.c index db6b1ab..a19ed92 100644 --- a/arch/x86/pci/i386.c +++ b/arch/x86/pci/i386.c @@ -271,11 +271,16 @@ static void pcibios_allocate_dev_resources(struct pci_dev *dev, int pass) "BAR %d: reserving %pr (d=%d, p=%d)\n", idx, r, disabled, pass); if (pci_claim_resource(dev, idx) < 0) { - /* We'll assign a new address later */ - pcibios_save_fw_addr(dev, - idx, r->start); - r->end -= r->start; - r->start = 0; + if (r->flags & IORESOURCE_PCI_FIXED) { + dev_info(&dev->dev, "BAR %d %pR is immovable\n", + idx, r); + } else { + /* We'll assign a new address later */ + pcibios_save_fw_addr(dev, + idx, r->start); + r->end -= r->start; + r->start = 0; + } } } } @@ -356,6 +361,12 @@ static int __init pcibios_assign_resources(void) return 0; } +/** + * called in fs_initcall (one below subsys_initcall), + * give a chance for motherboard reserve resources + */ +fs_initcall(pcibios_assign_resources); + void pcibios_resource_survey_bus(struct pci_bus *bus) { dev_printk(KERN_DEBUG, &bus->dev, "Allocating resources\n"); @@ -392,12 +403,6 @@ void __init pcibios_resource_survey(void) ioapic_insert_resources(); } -/** - * called in fs_initcall (one below subsys_initcall), - * give a chance for motherboard reserve resources - */ -fs_initcall(pcibios_assign_resources); - static const struct vm_operations_struct pci_mmap_ops = { .access = generic_access_phys, }; diff --git a/arch/x86/pci/sta2x11-fixup.c b/arch/x86/pci/sta2x11-fixup.c index 9d8a509..5ceda85 100644 --- a/arch/x86/pci/sta2x11-fixup.c +++ b/arch/x86/pci/sta2x11-fixup.c @@ -173,9 +173,7 @@ static void *sta2x11_swiotlb_alloc_coherent(struct device *dev, { void *vaddr; - vaddr = dma_generic_alloc_coherent(dev, size, dma_handle, flags, attrs); - if (!vaddr) - vaddr = swiotlb_alloc_coherent(dev, size, dma_handle, flags); + vaddr = x86_swiotlb_alloc_coherent(dev, size, dma_handle, flags, attrs); *dma_handle = p2a(*dma_handle, to_pci_dev(dev)); return vaddr; } @@ -183,7 +181,7 @@ static void *sta2x11_swiotlb_alloc_coherent(struct device *dev, /* We have our own dma_ops: the same as swiotlb but from alloc (above) */ static struct dma_map_ops sta2x11_dma_ops = { .alloc = sta2x11_swiotlb_alloc_coherent, - .free = swiotlb_free_coherent, + .free = x86_swiotlb_free_coherent, .map_page = swiotlb_map_page, .unmap_page = swiotlb_unmap_page, .map_sg = swiotlb_map_sg_attrs, diff --git a/arch/x86/platform/uv/uv_irq.c b/arch/x86/platform/uv/uv_irq.c index acf7752..b233681 100644 --- a/arch/x86/platform/uv/uv_irq.c +++ b/arch/x86/platform/uv/uv_irq.c @@ -238,11 +238,9 @@ uv_set_irq_affinity(struct irq_data *data, const struct cpumask *mask, int uv_setup_irq(char *irq_name, int cpu, int mmr_blade, unsigned long mmr_offset, int limit) { - int irq, ret; + int ret, irq = irq_alloc_hwirq(uv_blade_to_memory_nid(mmr_blade)); - irq = create_irq_nr(NR_IRQS_LEGACY, uv_blade_to_memory_nid(mmr_blade)); - - if (irq <= 0) + if (!irq) return -EBUSY; ret = arch_enable_uv_irq(irq_name, irq, cpu, mmr_blade, mmr_offset, @@ -250,7 +248,7 @@ int uv_setup_irq(char *irq_name, int cpu, int mmr_blade, if (ret == irq) uv_set_irq_2_mmr_info(irq, mmr_offset, mmr_blade); else - destroy_irq(irq); + irq_free_hwirq(irq); return ret; } @@ -285,6 +283,6 @@ void uv_teardown_irq(unsigned int irq) n = n->rb_right; } spin_unlock_irqrestore(&uv_irq_lock, irqflags); - destroy_irq(irq); + irq_free_hwirq(irq); } EXPORT_SYMBOL_GPL(uv_teardown_irq); diff --git a/arch/x86/platform/uv/uv_nmi.c b/arch/x86/platform/uv/uv_nmi.c index be27da6..c89c933 100644 --- a/arch/x86/platform/uv/uv_nmi.c +++ b/arch/x86/platform/uv/uv_nmi.c @@ -85,7 +85,7 @@ static cpumask_var_t uv_nmi_cpu_mask; * Default is all stack dumps go to the console and buffer. * Lower level to send to log buffer only. */ -static int uv_nmi_loglevel = 7; +static int uv_nmi_loglevel = CONSOLE_LOGLEVEL_DEFAULT; module_param_named(dump_loglevel, uv_nmi_loglevel, int, 0644); /* diff --git a/arch/x86/realmode/rm/Makefile b/arch/x86/realmode/rm/Makefile index 3497f14..7c0d7be 100644 --- a/arch/x86/realmode/rm/Makefile +++ b/arch/x86/realmode/rm/Makefile @@ -52,8 +52,9 @@ $(obj)/realmode.elf: $(obj)/realmode.lds $(REALMODE_OBJS) FORCE OBJCOPYFLAGS_realmode.bin := -O binary targets += realmode.bin -$(obj)/realmode.bin: $(obj)/realmode.elf $(obj)/realmode.relocs +$(obj)/realmode.bin: $(obj)/realmode.elf $(obj)/realmode.relocs FORCE $(call if_changed,objcopy) + @: quiet_cmd_relocs = RELOCS $@ cmd_relocs = arch/x86/tools/relocs --realmode $< > $@ diff --git a/arch/x86/syscalls/syscall_64.tbl b/arch/x86/syscalls/syscall_64.tbl index 04376ac..ec255a1 100644 --- a/arch/x86/syscalls/syscall_64.tbl +++ b/arch/x86/syscalls/syscall_64.tbl @@ -212,10 +212,10 @@ 203 common sched_setaffinity sys_sched_setaffinity 204 common sched_getaffinity sys_sched_getaffinity 205 64 set_thread_area -206 common io_setup sys_io_setup +206 64 io_setup sys_io_setup 207 common io_destroy sys_io_destroy 208 common io_getevents sys_io_getevents -209 common io_submit sys_io_submit +209 64 io_submit sys_io_submit 210 common io_cancel sys_io_cancel 211 64 get_thread_area 212 common lookup_dcookie sys_lookup_dcookie @@ -359,3 +359,5 @@ 540 x32 process_vm_writev compat_sys_process_vm_writev 541 x32 setsockopt compat_sys_setsockopt 542 x32 getsockopt compat_sys_getsockopt +543 x32 io_setup compat_sys_io_setup +544 x32 io_submit compat_sys_io_submit diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c index c34bfc4..f17b292 100644 --- a/arch/x86/xen/enlighten.c +++ b/arch/x86/xen/enlighten.c @@ -1339,6 +1339,7 @@ xen_panic_event(struct notifier_block *this, unsigned long event, void *ptr) static struct notifier_block xen_panic_block = { .notifier_call= xen_panic_event, + .priority = INT_MIN }; int xen_panic_handler_init(void) diff --git a/arch/x86/xen/mmu.c b/arch/x86/xen/mmu.c index 86e02ea..6f6e15d 100644 --- a/arch/x86/xen/mmu.c +++ b/arch/x86/xen/mmu.c @@ -2510,6 +2510,95 @@ void __init xen_hvm_init_mmu_ops(void) } #endif +#ifdef CONFIG_XEN_PVH +/* + * Map foreign gfn (fgfn), to local pfn (lpfn). This for the user + * space creating new guest on pvh dom0 and needing to map domU pages. + */ +static int xlate_add_to_p2m(unsigned long lpfn, unsigned long fgfn, + unsigned int domid) +{ + int rc, err = 0; + xen_pfn_t gpfn = lpfn; + xen_ulong_t idx = fgfn; + + struct xen_add_to_physmap_range xatp = { + .domid = DOMID_SELF, + .foreign_domid = domid, + .size = 1, + .space = XENMAPSPACE_gmfn_foreign, + }; + set_xen_guest_handle(xatp.idxs, &idx); + set_xen_guest_handle(xatp.gpfns, &gpfn); + set_xen_guest_handle(xatp.errs, &err); + + rc = HYPERVISOR_memory_op(XENMEM_add_to_physmap_range, &xatp); + if (rc < 0) + return rc; + return err; +} + +static int xlate_remove_from_p2m(unsigned long spfn, int count) +{ + struct xen_remove_from_physmap xrp; + int i, rc; + + for (i = 0; i < count; i++) { + xrp.domid = DOMID_SELF; + xrp.gpfn = spfn+i; + rc = HYPERVISOR_memory_op(XENMEM_remove_from_physmap, &xrp); + if (rc) + break; + } + return rc; +} + +struct xlate_remap_data { + unsigned long fgfn; /* foreign domain's gfn */ + pgprot_t prot; + domid_t domid; + int index; + struct page **pages; +}; + +static int xlate_map_pte_fn(pte_t *ptep, pgtable_t token, unsigned long addr, + void *data) +{ + int rc; + struct xlate_remap_data *remap = data; + unsigned long pfn = page_to_pfn(remap->pages[remap->index++]); + pte_t pteval = pte_mkspecial(pfn_pte(pfn, remap->prot)); + + rc = xlate_add_to_p2m(pfn, remap->fgfn, remap->domid); + if (rc) + return rc; + native_set_pte(ptep, pteval); + + return 0; +} + +static int xlate_remap_gfn_range(struct vm_area_struct *vma, + unsigned long addr, unsigned long mfn, + int nr, pgprot_t prot, unsigned domid, + struct page **pages) +{ + int err; + struct xlate_remap_data pvhdata; + + BUG_ON(!pages); + + pvhdata.fgfn = mfn; + pvhdata.prot = prot; + pvhdata.domid = domid; + pvhdata.index = 0; + pvhdata.pages = pages; + err = apply_to_page_range(vma->vm_mm, addr, nr << PAGE_SHIFT, + xlate_map_pte_fn, &pvhdata); + flush_tlb_all(); + return err; +} +#endif + #define REMAP_BATCH_SIZE 16 struct remap_data { @@ -2522,7 +2611,7 @@ static int remap_area_mfn_pte_fn(pte_t *ptep, pgtable_t token, unsigned long addr, void *data) { struct remap_data *rmd = data; - pte_t pte = pte_mkspecial(pfn_pte(rmd->mfn++, rmd->prot)); + pte_t pte = pte_mkspecial(mfn_pte(rmd->mfn++, rmd->prot)); rmd->mmu_update->ptr = virt_to_machine(ptep).maddr; rmd->mmu_update->val = pte_val_ma(pte); @@ -2544,13 +2633,18 @@ int xen_remap_domain_mfn_range(struct vm_area_struct *vma, unsigned long range; int err = 0; - if (xen_feature(XENFEAT_auto_translated_physmap)) - return -EINVAL; - - prot = __pgprot(pgprot_val(prot) | _PAGE_IOMAP); - BUG_ON(!((vma->vm_flags & (VM_PFNMAP | VM_IO)) == (VM_PFNMAP | VM_IO))); + if (xen_feature(XENFEAT_auto_translated_physmap)) { +#ifdef CONFIG_XEN_PVH + /* We need to update the local page tables and the xen HAP */ + return xlate_remap_gfn_range(vma, addr, mfn, nr, prot, + domid, pages); +#else + return -EINVAL; +#endif + } + rmd.mfn = mfn; rmd.prot = prot; @@ -2588,6 +2682,25 @@ int xen_unmap_domain_mfn_range(struct vm_area_struct *vma, if (!pages || !xen_feature(XENFEAT_auto_translated_physmap)) return 0; +#ifdef CONFIG_XEN_PVH + while (numpgs--) { + /* + * The mmu has already cleaned up the process mmu + * resources at this point (lookup_address will return + * NULL). + */ + unsigned long pfn = page_to_pfn(pages[numpgs]); + + xlate_remove_from_p2m(pfn, 1); + } + /* + * We don't need to flush tlbs because as part of + * xlate_remove_from_p2m, the hypervisor will do tlb flushes + * after removing the p2m entries from the EPT/NPT + */ + return 0; +#else return -EINVAL; +#endif } EXPORT_SYMBOL_GPL(xen_unmap_domain_mfn_range); diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c index 85e5d78..9bb3d82 100644 --- a/arch/x86/xen/p2m.c +++ b/arch/x86/xen/p2m.c @@ -36,7 +36,7 @@ * pfn_to_mfn(0xc0000)=0xc0000 * * The benefit of this is, that we can assume for non-RAM regions (think - * PCI BARs, or ACPI spaces), we can create mappings easily b/c we + * PCI BARs, or ACPI spaces), we can create mappings easily because we * get the PFN value to match the MFN. * * For this to work efficiently we have one new page p2m_identity and @@ -60,7 +60,7 @@ * There is also a digram of the P2M at the end that can help. * Imagine your E820 looking as so: * - * 1GB 2GB + * 1GB 2GB 4GB * /-------------------+---------\/----\ /----------\ /---+-----\ * | System RAM | Sys RAM ||ACPI| | reserved | | Sys RAM | * \-------------------+---------/\----/ \----------/ \---+-----/ @@ -77,9 +77,8 @@ * of the PFN and the end PFN (263424 and 512256 respectively). The first step * is to reserve_brk a top leaf page if the p2m[1] is missing. The top leaf page * covers 512^2 of page estate (1GB) and in case the start or end PFN is not - * aligned on 512^2*PAGE_SIZE (1GB) we loop on aligned 1GB PFNs from start pfn - * to end pfn. We reserve_brk top leaf pages if they are missing (means they - * point to p2m_mid_missing). + * aligned on 512^2*PAGE_SIZE (1GB) we reserve_brk new middle and leaf pages as + * required to split any existing p2m_mid_missing middle pages. * * With the E820 example above, 263424 is not 1GB aligned so we allocate a * reserve_brk page which will cover the PFNs estate from 0x40000 to 0x80000. @@ -88,7 +87,7 @@ * Next stage is to determine if we need to do a more granular boundary check * on the 4MB (or 2MB depending on architecture) off the start and end pfn's. * We check if the start pfn and end pfn violate that boundary check, and if - * so reserve_brk a middle (p2m[x][y]) leaf page. This way we have a much finer + * so reserve_brk a (p2m[x][y]) leaf page. This way we have a much finer * granularity of setting which PFNs are missing and which ones are identity. * In our example 263424 and 512256 both fail the check so we reserve_brk two * pages. Populate them with INVALID_P2M_ENTRY (so they both have "missing" @@ -102,9 +101,10 @@ * * The next step is to walk from the start pfn to the end pfn setting * the IDENTITY_FRAME_BIT on each PFN. This is done in set_phys_range_identity. - * If we find that the middle leaf is pointing to p2m_missing we can swap it - * over to p2m_identity - this way covering 4MB (or 2MB) PFN space. At this - * point we do not need to worry about boundary aligment (so no need to + * If we find that the middle entry is pointing to p2m_missing we can swap it + * over to p2m_identity - this way covering 4MB (or 2MB) PFN space (and + * similarly swapping p2m_mid_missing for p2m_mid_identity for larger regions). + * At this point we do not need to worry about boundary aligment (so no need to * reserve_brk a middle page, figure out which PFNs are "missing" and which * ones are identity), as that has been done earlier. If we find that the * middle leaf is not occupied by p2m_identity or p2m_missing, we dereference @@ -118,6 +118,9 @@ * considered missing). In our case, p2m[1][2][0->255] and p2m[1][488][257->511] * contain the INVALID_P2M_ENTRY value and are considered "missing." * + * Finally, the region beyond the end of of the E820 (4 GB in this example) + * is set to be identity (in case there are MMIO regions placed here). + * * This is what the p2m ends up looking (for the E820 above) with this * fabulous drawing: * @@ -129,21 +132,27 @@ * |-----| \ | [p2m_identity]+\\ | .... | * | 2 |--\ \-------------------->| ... | \\ \----------------/ * |-----| \ \---------------/ \\ - * | 3 |\ \ \\ p2m_identity - * |-----| \ \-------------------->/---------------\ /-----------------\ - * | .. +->+ | [p2m_identity]+-->| ~0, ~0, ~0, ... | - * \-----/ / | [p2m_identity]+-->| ..., ~0 | - * / /---------------\ | .... | \-----------------/ - * / | IDENTITY[@0] | /-+-[x], ~0, ~0.. | - * / | IDENTITY[@256]|<----/ \---------------/ - * / | ~0, ~0, .... | - * | \---------------/ - * | - * p2m_mid_missing p2m_missing - * /-----------------\ /------------\ - * | [p2m_missing] +---->| ~0, ~0, ~0 | - * | [p2m_missing] +---->| ..., ~0 | - * \-----------------/ \------------/ + * | 3 |-\ \ \\ p2m_identity [1] + * |-----| \ \-------------------->/---------------\ /-----------------\ + * | .. |\ | | [p2m_identity]+-->| ~0, ~0, ~0, ... | + * \-----/ | | | [p2m_identity]+-->| ..., ~0 | + * | | | .... | \-----------------/ + * | | +-[x], ~0, ~0.. +\ + * | | \---------------/ \ + * | | \-> /---------------\ + * | V p2m_mid_missing p2m_missing | IDENTITY[@0] | + * | /-----------------\ /------------\ | IDENTITY[@256]| + * | | [p2m_missing] +---->| ~0, ~0, ...| | ~0, ~0, .... | + * | | [p2m_missing] +---->| ..., ~0 | \---------------/ + * | | ... | \------------/ + * | \-----------------/ + * | + * | p2m_mid_identity + * | /-----------------\ + * \-->| [p2m_identity] +---->[1] + * | [p2m_identity] +---->[1] + * | ... | + * \-----------------/ * * where ~0 is INVALID_P2M_ENTRY. IDENTITY is (PFN | IDENTITY_BIT) */ @@ -187,13 +196,15 @@ static RESERVE_BRK_ARRAY(unsigned long, p2m_top_mfn, P2M_TOP_PER_PAGE); static RESERVE_BRK_ARRAY(unsigned long *, p2m_top_mfn_p, P2M_TOP_PER_PAGE); static RESERVE_BRK_ARRAY(unsigned long, p2m_identity, P2M_PER_PAGE); +static RESERVE_BRK_ARRAY(unsigned long *, p2m_mid_identity, P2M_MID_PER_PAGE); +static RESERVE_BRK_ARRAY(unsigned long, p2m_mid_identity_mfn, P2M_MID_PER_PAGE); RESERVE_BRK(p2m_mid, PAGE_SIZE * (MAX_DOMAIN_PAGES / (P2M_PER_PAGE * P2M_MID_PER_PAGE))); RESERVE_BRK(p2m_mid_mfn, PAGE_SIZE * (MAX_DOMAIN_PAGES / (P2M_PER_PAGE * P2M_MID_PER_PAGE))); /* We might hit two boundary violations at the start and end, at max each * boundary violation will require three middle nodes. */ -RESERVE_BRK(p2m_mid_identity, PAGE_SIZE * 2 * 3); +RESERVE_BRK(p2m_mid_extra, PAGE_SIZE * 2 * 3); /* When we populate back during bootup, the amount of pages can vary. The * max we have is seen is 395979, but that does not mean it can't be more. @@ -242,20 +253,20 @@ static void p2m_top_mfn_p_init(unsigned long **top) top[i] = p2m_mid_missing_mfn; } -static void p2m_mid_init(unsigned long **mid) +static void p2m_mid_init(unsigned long **mid, unsigned long *leaf) { unsigned i; for (i = 0; i < P2M_MID_PER_PAGE; i++) - mid[i] = p2m_missing; + mid[i] = leaf; } -static void p2m_mid_mfn_init(unsigned long *mid) +static void p2m_mid_mfn_init(unsigned long *mid, unsigned long *leaf) { unsigned i; for (i = 0; i < P2M_MID_PER_PAGE; i++) - mid[i] = virt_to_mfn(p2m_missing); + mid[i] = virt_to_mfn(leaf); } static void p2m_init(unsigned long *p2m) @@ -286,7 +297,9 @@ void __ref xen_build_mfn_list_list(void) /* Pre-initialize p2m_top_mfn to be completely missing */ if (p2m_top_mfn == NULL) { p2m_mid_missing_mfn = extend_brk(PAGE_SIZE, PAGE_SIZE); - p2m_mid_mfn_init(p2m_mid_missing_mfn); + p2m_mid_mfn_init(p2m_mid_missing_mfn, p2m_missing); + p2m_mid_identity_mfn = extend_brk(PAGE_SIZE, PAGE_SIZE); + p2m_mid_mfn_init(p2m_mid_identity_mfn, p2m_identity); p2m_top_mfn_p = extend_brk(PAGE_SIZE, PAGE_SIZE); p2m_top_mfn_p_init(p2m_top_mfn_p); @@ -295,7 +308,8 @@ void __ref xen_build_mfn_list_list(void) p2m_top_mfn_init(p2m_top_mfn); } else { /* Reinitialise, mfn's all change after migration */ - p2m_mid_mfn_init(p2m_mid_missing_mfn); + p2m_mid_mfn_init(p2m_mid_missing_mfn, p2m_missing); + p2m_mid_mfn_init(p2m_mid_identity_mfn, p2m_identity); } for (pfn = 0; pfn < xen_max_p2m_pfn; pfn += P2M_PER_PAGE) { @@ -327,7 +341,7 @@ void __ref xen_build_mfn_list_list(void) * it too late. */ mid_mfn_p = extend_brk(PAGE_SIZE, PAGE_SIZE); - p2m_mid_mfn_init(mid_mfn_p); + p2m_mid_mfn_init(mid_mfn_p, p2m_missing); p2m_top_mfn_p[topidx] = mid_mfn_p; } @@ -365,16 +379,17 @@ void __init xen_build_dynamic_phys_to_machine(void) p2m_missing = extend_brk(PAGE_SIZE, PAGE_SIZE); p2m_init(p2m_missing); + p2m_identity = extend_brk(PAGE_SIZE, PAGE_SIZE); + p2m_init(p2m_identity); p2m_mid_missing = extend_brk(PAGE_SIZE, PAGE_SIZE); - p2m_mid_init(p2m_mid_missing); + p2m_mid_init(p2m_mid_missing, p2m_missing); + p2m_mid_identity = extend_brk(PAGE_SIZE, PAGE_SIZE); + p2m_mid_init(p2m_mid_identity, p2m_identity); p2m_top = extend_brk(PAGE_SIZE, PAGE_SIZE); p2m_top_init(p2m_top); - p2m_identity = extend_brk(PAGE_SIZE, PAGE_SIZE); - p2m_init(p2m_identity); - /* * The domain builder gives us a pre-constructed p2m array in * mfn_list for all the pages initially given to us, so we just @@ -386,7 +401,7 @@ void __init xen_build_dynamic_phys_to_machine(void) if (p2m_top[topidx] == p2m_mid_missing) { unsigned long **mid = extend_brk(PAGE_SIZE, PAGE_SIZE); - p2m_mid_init(mid); + p2m_mid_init(mid, p2m_missing); p2m_top[topidx] = mid; } @@ -492,7 +507,7 @@ unsigned long get_phys_to_machine(unsigned long pfn) unsigned topidx, mididx, idx; if (unlikely(pfn >= MAX_P2M_PFN)) - return INVALID_P2M_ENTRY; + return IDENTITY_FRAME(pfn); topidx = p2m_top_index(pfn); mididx = p2m_mid_index(pfn); @@ -545,7 +560,7 @@ static bool alloc_p2m(unsigned long pfn) if (!mid) return false; - p2m_mid_init(mid); + p2m_mid_init(mid, p2m_missing); if (cmpxchg(top_p, p2m_mid_missing, mid) != p2m_mid_missing) free_p2m_page(mid); @@ -565,7 +580,7 @@ static bool alloc_p2m(unsigned long pfn) if (!mid_mfn) return false; - p2m_mid_mfn_init(mid_mfn); + p2m_mid_mfn_init(mid_mfn, p2m_missing); missing_mfn = virt_to_mfn(p2m_mid_missing_mfn); mid_mfn_mfn = virt_to_mfn(mid_mfn); @@ -596,7 +611,7 @@ static bool alloc_p2m(unsigned long pfn) return true; } -static bool __init early_alloc_p2m_middle(unsigned long pfn, bool check_boundary) +static bool __init early_alloc_p2m(unsigned long pfn, bool check_boundary) { unsigned topidx, mididx, idx; unsigned long *p2m; @@ -638,7 +653,7 @@ static bool __init early_alloc_p2m_middle(unsigned long pfn, bool check_boundary return true; } -static bool __init early_alloc_p2m(unsigned long pfn) +static bool __init early_alloc_p2m_middle(unsigned long pfn) { unsigned topidx = p2m_top_index(pfn); unsigned long *mid_mfn_p; @@ -649,7 +664,7 @@ static bool __init early_alloc_p2m(unsigned long pfn) if (mid == p2m_mid_missing) { mid = extend_brk(PAGE_SIZE, PAGE_SIZE); - p2m_mid_init(mid); + p2m_mid_init(mid, p2m_missing); p2m_top[topidx] = mid; @@ -658,12 +673,12 @@ static bool __init early_alloc_p2m(unsigned long pfn) /* And the save/restore P2M tables.. */ if (mid_mfn_p == p2m_mid_missing_mfn) { mid_mfn_p = extend_brk(PAGE_SIZE, PAGE_SIZE); - p2m_mid_mfn_init(mid_mfn_p); + p2m_mid_mfn_init(mid_mfn_p, p2m_missing); p2m_top_mfn_p[topidx] = mid_mfn_p; p2m_top_mfn[topidx] = virt_to_mfn(mid_mfn_p); /* Note: we don't set mid_mfn_p[midix] here, - * look in early_alloc_p2m_middle */ + * look in early_alloc_p2m() */ } return true; } @@ -739,7 +754,7 @@ found: /* This shouldn't happen */ if (WARN_ON(p2m_top[topidx] == p2m_mid_missing)) - early_alloc_p2m(set_pfn); + early_alloc_p2m_middle(set_pfn); if (WARN_ON(p2m_top[topidx][mididx] != p2m_missing)) return false; @@ -754,13 +769,13 @@ found: bool __init early_set_phys_to_machine(unsigned long pfn, unsigned long mfn) { if (unlikely(!__set_phys_to_machine(pfn, mfn))) { - if (!early_alloc_p2m(pfn)) + if (!early_alloc_p2m_middle(pfn)) return false; if (early_can_reuse_p2m_middle(pfn, mfn)) return __set_phys_to_machine(pfn, mfn); - if (!early_alloc_p2m_middle(pfn, false /* boundary crossover OK!*/)) + if (!early_alloc_p2m(pfn, false /* boundary crossover OK!*/)) return false; if (!__set_phys_to_machine(pfn, mfn)) @@ -769,12 +784,30 @@ bool __init early_set_phys_to_machine(unsigned long pfn, unsigned long mfn) return true; } + +static void __init early_split_p2m(unsigned long pfn) +{ + unsigned long mididx, idx; + + mididx = p2m_mid_index(pfn); + idx = p2m_index(pfn); + + /* + * Allocate new middle and leaf pages if this pfn lies in the + * middle of one. + */ + if (mididx || idx) + early_alloc_p2m_middle(pfn); + if (idx) + early_alloc_p2m(pfn, false); +} + unsigned long __init set_phys_range_identity(unsigned long pfn_s, unsigned long pfn_e) { unsigned long pfn; - if (unlikely(pfn_s >= MAX_P2M_PFN || pfn_e >= MAX_P2M_PFN)) + if (unlikely(pfn_s >= MAX_P2M_PFN)) return 0; if (unlikely(xen_feature(XENFEAT_auto_translated_physmap))) @@ -783,19 +816,30 @@ unsigned long __init set_phys_range_identity(unsigned long pfn_s, if (pfn_s > pfn_e) return 0; - for (pfn = (pfn_s & ~(P2M_MID_PER_PAGE * P2M_PER_PAGE - 1)); - pfn < ALIGN(pfn_e, (P2M_MID_PER_PAGE * P2M_PER_PAGE)); - pfn += P2M_MID_PER_PAGE * P2M_PER_PAGE) - { - WARN_ON(!early_alloc_p2m(pfn)); - } + if (pfn_e > MAX_P2M_PFN) + pfn_e = MAX_P2M_PFN; - early_alloc_p2m_middle(pfn_s, true); - early_alloc_p2m_middle(pfn_e, true); + early_split_p2m(pfn_s); + early_split_p2m(pfn_e); + + for (pfn = pfn_s; pfn < pfn_e;) { + unsigned topidx = p2m_top_index(pfn); + unsigned mididx = p2m_mid_index(pfn); - for (pfn = pfn_s; pfn < pfn_e; pfn++) if (!__set_phys_to_machine(pfn, IDENTITY_FRAME(pfn))) break; + pfn++; + + /* + * If the PFN was set to a middle or leaf identity + * page the remainder must also be identity, so skip + * ahead to the next middle or leaf entry. + */ + if (p2m_top[topidx] == p2m_mid_identity) + pfn = ALIGN(pfn, P2M_MID_PER_PAGE * P2M_PER_PAGE); + else if (p2m_top[topidx][mididx] == p2m_identity) + pfn = ALIGN(pfn, P2M_PER_PAGE); + } if (!WARN((pfn - pfn_s) != (pfn_e - pfn_s), "Identity mapping failed. We are %ld short of 1-1 mappings!\n", @@ -825,8 +869,22 @@ bool __set_phys_to_machine(unsigned long pfn, unsigned long mfn) /* For sparse holes were the p2m leaf has real PFN along with * PCI holes, stick in the PFN as the MFN value. + * + * set_phys_range_identity() will have allocated new middle + * and leaf pages as required so an existing p2m_mid_missing + * or p2m_missing mean that whole range will be identity so + * these can be switched to p2m_mid_identity or p2m_identity. */ if (mfn != INVALID_P2M_ENTRY && (mfn & IDENTITY_FRAME_BIT)) { + if (p2m_top[topidx] == p2m_mid_identity) + return true; + + if (p2m_top[topidx] == p2m_mid_missing) { + WARN_ON(cmpxchg(&p2m_top[topidx], p2m_mid_missing, + p2m_mid_identity) != p2m_mid_missing); + return true; + } + if (p2m_top[topidx][mididx] == p2m_identity) return true; diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c index 0982233..210426a 100644 --- a/arch/x86/xen/setup.c +++ b/arch/x86/xen/setup.c @@ -89,10 +89,10 @@ static void __init xen_add_extra_mem(u64 start, u64 size) for (pfn = PFN_DOWN(start); pfn < xen_max_p2m_pfn; pfn++) { unsigned long mfn = pfn_to_mfn(pfn); - if (WARN(mfn == pfn, "Trying to over-write 1-1 mapping (pfn: %lx)\n", pfn)) + if (WARN_ONCE(mfn == pfn, "Trying to over-write 1-1 mapping (pfn: %lx)\n", pfn)) continue; - WARN(mfn != INVALID_P2M_ENTRY, "Trying to remove %lx which has %lx mfn!\n", - pfn, mfn); + WARN_ONCE(mfn != INVALID_P2M_ENTRY, "Trying to remove %lx which has %lx mfn!\n", + pfn, mfn); __set_phys_to_machine(pfn, INVALID_P2M_ENTRY); } @@ -469,6 +469,15 @@ char * __init xen_memory_setup(void) } /* + * Set the rest as identity mapped, in case PCI BARs are + * located here. + * + * PFNs above MAX_P2M_PFN are considered identity mapped as + * well. + */ + set_phys_range_identity(map[i-1].addr / PAGE_SIZE, ~0ul); + + /* * In domU, the ISA region is normal, usable memory, but we * reserve ISA memory anyway because too many things poke * about in there. diff --git a/arch/x86/xen/suspend.c b/arch/x86/xen/suspend.c index 45329c8..c4df9db 100644 --- a/arch/x86/xen/suspend.c +++ b/arch/x86/xen/suspend.c @@ -12,8 +12,10 @@ #include "xen-ops.h" #include "mmu.h" -void xen_arch_pre_suspend(void) +static void xen_pv_pre_suspend(void) { + xen_mm_pin_all(); + xen_start_info->store_mfn = mfn_to_pfn(xen_start_info->store_mfn); xen_start_info->console.domU.mfn = mfn_to_pfn(xen_start_info->console.domU.mfn); @@ -26,7 +28,7 @@ void xen_arch_pre_suspend(void) BUG(); } -void xen_arch_hvm_post_suspend(int suspend_cancelled) +static void xen_hvm_post_suspend(int suspend_cancelled) { #ifdef CONFIG_XEN_PVHVM int cpu; @@ -41,7 +43,7 @@ void xen_arch_hvm_post_suspend(int suspend_cancelled) #endif } -void xen_arch_post_suspend(int suspend_cancelled) +static void xen_pv_post_suspend(int suspend_cancelled) { xen_build_mfn_list_list(); @@ -60,6 +62,21 @@ void xen_arch_post_suspend(int suspend_cancelled) xen_vcpu_restore(); } + xen_mm_unpin_all(); +} + +void xen_arch_pre_suspend(void) +{ + if (xen_pv_domain()) + xen_pv_pre_suspend(); +} + +void xen_arch_post_suspend(int cancelled) +{ + if (xen_pv_domain()) + xen_pv_post_suspend(cancelled); + else + xen_hvm_post_suspend(cancelled); } static void xen_vcpu_notify_restore(void *data) diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h index 1cb6f4c..c834d4b 100644 --- a/arch/x86/xen/xen-ops.h +++ b/arch/x86/xen/xen-ops.h @@ -31,6 +31,8 @@ void xen_setup_kernel_pagetable(pgd_t *pgd, unsigned long max_pfn); void xen_reserve_top(void); extern unsigned long xen_max_p2m_pfn; +void xen_mm_pin_all(void); +void xen_mm_unpin_all(void); void xen_set_pat(u64); char * __init xen_memory_setup(void); |
