summaryrefslogtreecommitdiffstats
path: root/arch/x86
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86')
-rw-r--r--arch/x86/Kconfig16
-rw-r--r--arch/x86/Kconfig.debug13
-rw-r--r--arch/x86/Makefile.um2
-rw-r--r--arch/x86/boot/compressed/Makefile1
-rw-r--r--arch/x86/boot/compressed/aslr.c34
-rw-r--r--arch/x86/boot/compressed/efi_stub_64.S25
-rw-r--r--arch/x86/boot/compressed/efi_thunk_64.S196
-rw-r--r--arch/x86/boot/compressed/misc.c3
-rw-r--r--arch/x86/boot/compressed/misc.h6
-rw-r--r--arch/x86/include/asm/apic.h8
-rw-r--r--arch/x86/include/asm/imr.h60
-rw-r--r--arch/x86/include/asm/lguest_hcall.h1
-rw-r--r--arch/x86/include/asm/page_types.h2
-rw-r--r--arch/x86/include/asm/pgtable.h6
-rw-r--r--arch/x86/include/asm/spinlock.h90
-rw-r--r--arch/x86/include/asm/uaccess.h2
-rw-r--r--arch/x86/include/uapi/asm/bootparam.h1
-rw-r--r--arch/x86/kernel/acpi/boot.c5
-rw-r--r--arch/x86/kernel/cpu/common.c6
-rw-r--r--arch/x86/kernel/cpu/intel.c4
-rw-r--r--arch/x86/kernel/cpu/microcode/intel.c5
-rw-r--r--arch/x86/kernel/cpu/microcode/intel_early.c6
-rw-r--r--arch/x86/kernel/entry_32.S3
-rw-r--r--arch/x86/kernel/entry_64.S3
-rw-r--r--arch/x86/kernel/irq.c3
-rw-r--r--arch/x86/kernel/kprobes/core.c56
-rw-r--r--arch/x86/kernel/kprobes/opt.c2
-rw-r--r--arch/x86/kernel/kvm.c13
-rw-r--r--arch/x86/kernel/module.c10
-rw-r--r--arch/x86/kernel/setup.c22
-rw-r--r--arch/x86/kernel/uprobes.c153
-rw-r--r--arch/x86/lguest/Kconfig4
-rw-r--r--arch/x86/lguest/boot.c173
-rw-r--r--arch/x86/mm/init.c28
-rw-r--r--arch/x86/mm/mmap.c6
-rw-r--r--arch/x86/platform/Makefile1
-rw-r--r--arch/x86/platform/efi/efi_stub_64.S161
-rw-r--r--arch/x86/platform/efi/efi_thunk_64.S121
-rw-r--r--arch/x86/platform/intel-mid/intel-mid.c2
-rw-r--r--arch/x86/platform/intel-quark/Makefile2
-rw-r--r--arch/x86/platform/intel-quark/imr.c661
-rw-r--r--arch/x86/platform/intel-quark/imr_selftest.c129
-rw-r--r--arch/x86/xen/enlighten.c20
-rw-r--r--arch/x86/xen/spinlock.c13
44 files changed, 1709 insertions, 369 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index eb1cf898ed3c..c2fb8a87dccb 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -488,6 +488,22 @@ config X86_INTEL_MID
Intel MID platforms are based on an Intel processor and chipset which
consume less power than most of the x86 derivatives.
+config X86_INTEL_QUARK
+ bool "Intel Quark platform support"
+ depends on X86_32
+ depends on X86_EXTENDED_PLATFORM
+ depends on X86_PLATFORM_DEVICES
+ depends on X86_TSC
+ depends on PCI
+ depends on PCI_GOANY
+ depends on X86_IO_APIC
+ select IOSF_MBI
+ select INTEL_IMR
+ ---help---
+ Select to include support for Quark X1000 SoC.
+ Say Y here if you have a Quark based system such as the Arduino
+ compatible Intel Galileo.
+
config X86_INTEL_LPSS
bool "Intel Low Power Subsystem Support"
depends on ACPI
diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug
index 61bd2ad94281..20028da8ae18 100644
--- a/arch/x86/Kconfig.debug
+++ b/arch/x86/Kconfig.debug
@@ -313,6 +313,19 @@ config DEBUG_NMI_SELFTEST
If unsure, say N.
+config DEBUG_IMR_SELFTEST
+ bool "Isolated Memory Region self test"
+ default n
+ depends on INTEL_IMR
+ ---help---
+ This option enables automated sanity testing of the IMR code.
+ Some simple tests are run to verify IMR bounds checking, alignment
+ and overlapping. This option is really only useful if you are
+ debugging an IMR memory map or are modifying the IMR code and want to
+ test your changes.
+
+ If unsure say N here.
+
config X86_DEBUG_STATIC_CPU_HAS
bool "Debug alternatives"
depends on DEBUG_KERNEL
diff --git a/arch/x86/Makefile.um b/arch/x86/Makefile.um
index 36b62bc52638..95eba554baf9 100644
--- a/arch/x86/Makefile.um
+++ b/arch/x86/Makefile.um
@@ -30,7 +30,7 @@ cflags-y += -ffreestanding
# Disable unit-at-a-time mode on pre-gcc-4.0 compilers, it makes gcc use
# a lot more stack due to the lack of sharing of stacklots. Also, gcc
# 4.3.0 needs -funit-at-a-time for extern inline functions.
-KBUILD_CFLAGS += $(shell if [ $(call cc-version) -lt 0400 ] ; then \
+KBUILD_CFLAGS += $(shell if [ $(cc-version) -lt 0400 ] ; then \
echo $(call cc-option,-fno-unit-at-a-time); \
else echo $(call cc-option,-funit-at-a-time); fi ;)
diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile
index 843feb3eb20b..0a291cdfaf77 100644
--- a/arch/x86/boot/compressed/Makefile
+++ b/arch/x86/boot/compressed/Makefile
@@ -51,6 +51,7 @@ $(obj)/eboot.o: KBUILD_CFLAGS += -fshort-wchar -mno-red-zone
vmlinux-objs-$(CONFIG_EFI_STUB) += $(obj)/eboot.o $(obj)/efi_stub_$(BITS).o \
$(objtree)/drivers/firmware/efi/libstub/lib.a
+vmlinux-objs-$(CONFIG_EFI_MIXED) += $(obj)/efi_thunk_$(BITS).o
$(obj)/vmlinux: $(vmlinux-objs-y) FORCE
$(call if_changed,ld)
diff --git a/arch/x86/boot/compressed/aslr.c b/arch/x86/boot/compressed/aslr.c
index bb1376381985..7083c16cccba 100644
--- a/arch/x86/boot/compressed/aslr.c
+++ b/arch/x86/boot/compressed/aslr.c
@@ -14,6 +14,13 @@
static const char build_str[] = UTS_RELEASE " (" LINUX_COMPILE_BY "@"
LINUX_COMPILE_HOST ") (" LINUX_COMPILER ") " UTS_VERSION;
+struct kaslr_setup_data {
+ __u64 next;
+ __u32 type;
+ __u32 len;
+ __u8 data[1];
+} kaslr_setup_data;
+
#define I8254_PORT_CONTROL 0x43
#define I8254_PORT_COUNTER0 0x40
#define I8254_CMD_READBACK 0xC0
@@ -295,7 +302,29 @@ static unsigned long find_random_addr(unsigned long minimum,
return slots_fetch_random();
}
-unsigned char *choose_kernel_location(unsigned char *input,
+static void add_kaslr_setup_data(struct boot_params *params, __u8 enabled)
+{
+ struct setup_data *data;
+
+ kaslr_setup_data.type = SETUP_KASLR;
+ kaslr_setup_data.len = 1;
+ kaslr_setup_data.next = 0;
+ kaslr_setup_data.data[0] = enabled;
+
+ data = (struct setup_data *)(unsigned long)params->hdr.setup_data;
+
+ while (data && data->next)
+ data = (struct setup_data *)(unsigned long)data->next;
+
+ if (data)
+ data->next = (unsigned long)&kaslr_setup_data;
+ else
+ params->hdr.setup_data = (unsigned long)&kaslr_setup_data;
+
+}
+
+unsigned char *choose_kernel_location(struct boot_params *params,
+ unsigned char *input,
unsigned long input_size,
unsigned char *output,
unsigned long output_size)
@@ -306,14 +335,17 @@ unsigned char *choose_kernel_location(unsigned char *input,
#ifdef CONFIG_HIBERNATION
if (!cmdline_find_option_bool("kaslr")) {
debug_putstr("KASLR disabled by default...\n");
+ add_kaslr_setup_data(params, 0);
goto out;
}
#else
if (cmdline_find_option_bool("nokaslr")) {
debug_putstr("KASLR disabled by cmdline...\n");
+ add_kaslr_setup_data(params, 0);
goto out;
}
#endif
+ add_kaslr_setup_data(params, 1);
/* Record the various known unsafe memory ranges. */
mem_avoid_init((unsigned long)input, input_size,
diff --git a/arch/x86/boot/compressed/efi_stub_64.S b/arch/x86/boot/compressed/efi_stub_64.S
index 7ff3632806b1..99494dff2113 100644
--- a/arch/x86/boot/compressed/efi_stub_64.S
+++ b/arch/x86/boot/compressed/efi_stub_64.S
@@ -3,28 +3,3 @@
#include <asm/processor-flags.h>
#include "../../platform/efi/efi_stub_64.S"
-
-#ifdef CONFIG_EFI_MIXED
- .code64
- .text
-ENTRY(efi64_thunk)
- push %rbp
- push %rbx
-
- subq $16, %rsp
- leaq efi_exit32(%rip), %rax
- movl %eax, 8(%rsp)
- leaq efi_gdt64(%rip), %rax
- movl %eax, 4(%rsp)
- movl %eax, 2(%rax) /* Fixup the gdt base address */
- leaq efi32_boot_gdt(%rip), %rax
- movl %eax, (%rsp)
-
- call __efi64_thunk
-
- addq $16, %rsp
- pop %rbx
- pop %rbp
- ret
-ENDPROC(efi64_thunk)
-#endif /* CONFIG_EFI_MIXED */
diff --git a/arch/x86/boot/compressed/efi_thunk_64.S b/arch/x86/boot/compressed/efi_thunk_64.S
new file mode 100644
index 000000000000..630384a4c14a
--- /dev/null
+++ b/arch/x86/boot/compressed/efi_thunk_64.S
@@ -0,0 +1,196 @@
+/*
+ * Copyright (C) 2014, 2015 Intel Corporation; author Matt Fleming
+ *
+ * Early support for invoking 32-bit EFI services from a 64-bit kernel.
+ *
+ * Because this thunking occurs before ExitBootServices() we have to
+ * restore the firmware's 32-bit GDT before we make EFI serivce calls,
+ * since the firmware's 32-bit IDT is still currently installed and it
+ * needs to be able to service interrupts.
+ *
+ * On the plus side, we don't have to worry about mangling 64-bit
+ * addresses into 32-bits because we're executing with an identify
+ * mapped pagetable and haven't transitioned to 64-bit virtual addresses
+ * yet.
+ */
+
+#include <linux/linkage.h>
+#include <asm/msr.h>
+#include <asm/page_types.h>
+#include <asm/processor-flags.h>
+#include <asm/segment.h>
+
+ .code64
+ .text
+ENTRY(efi64_thunk)
+ push %rbp
+ push %rbx
+
+ subq $8, %rsp
+ leaq efi_exit32(%rip), %rax
+ movl %eax, 4(%rsp)
+ leaq efi_gdt64(%rip), %rax
+ movl %eax, (%rsp)
+ movl %eax, 2(%rax) /* Fixup the gdt base address */
+
+ movl %ds, %eax
+ push %rax
+ movl %es, %eax
+ push %rax
+ movl %ss, %eax
+ push %rax
+
+ /*
+ * Convert x86-64 ABI params to i386 ABI
+ */
+ subq $32, %rsp
+ movl %esi, 0x0(%rsp)
+ movl %edx, 0x4(%rsp)
+ movl %ecx, 0x8(%rsp)
+ movq %r8, %rsi
+ movl %esi, 0xc(%rsp)
+ movq %r9, %rsi
+ movl %esi, 0x10(%rsp)
+
+ sgdt save_gdt(%rip)
+
+ leaq 1f(%rip), %rbx
+ movq %rbx, func_rt_ptr(%rip)
+
+ /*
+ * Switch to gdt with 32-bit segments. This is the firmware GDT
+ * that was installed when the kernel started executing. This
+ * pointer was saved at the EFI stub entry point in head_64.S.
+ */
+ leaq efi32_boot_gdt(%rip), %rax
+ lgdt (%rax)
+
+ pushq $__KERNEL_CS
+ leaq efi_enter32(%rip), %rax
+ pushq %rax
+ lretq
+
+1: addq $32, %rsp
+
+ lgdt save_gdt(%rip)
+
+ pop %rbx
+ movl %ebx, %ss
+ pop %rbx
+ movl %ebx, %es
+ pop %rbx
+ movl %ebx, %ds
+
+ /*
+ * Convert 32-bit status code into 64-bit.
+ */
+ test %rax, %rax
+ jz 1f
+ movl %eax, %ecx
+ andl $0x0fffffff, %ecx
+ andl $0xf0000000, %eax
+ shl $32, %rax
+ or %rcx, %rax
+1:
+ addq $8, %rsp
+ pop %rbx
+ pop %rbp
+ ret
+ENDPROC(efi64_thunk)
+
+ENTRY(efi_exit32)
+ movq func_rt_ptr(%rip), %rax
+ push %rax
+ mov %rdi, %rax
+ ret
+ENDPROC(efi_exit32)
+
+ .code32
+/*
+ * EFI service pointer must be in %edi.
+ *
+ * The stack should represent the 32-bit calling convention.
+ */
+ENTRY(efi_enter32)
+ movl $__KERNEL_DS, %eax
+ movl %eax, %ds
+ movl %eax, %es
+ movl %eax, %ss
+
+ /* Reload pgtables */
+ movl %cr3, %eax
+ movl %eax, %cr3
+
+ /* Disable paging */
+ movl %cr0, %eax
+ btrl $X86_CR0_PG_BIT, %eax
+ movl %eax, %cr0
+
+ /* Disable long mode via EFER */
+ movl $MSR_EFER, %ecx
+ rdmsr
+ btrl $_EFER_LME, %eax
+ wrmsr
+
+ call *%edi
+
+ /* We must preserve return value */
+ movl %eax, %edi
+
+ /*
+ * Some firmware will return with interrupts enabled. Be sure to
+ * disable them before we switch GDTs.
+ */
+ cli
+
+ movl 56(%esp), %eax
+ movl %eax, 2(%eax)
+ lgdtl (%eax)
+
+ movl %cr4, %eax
+ btsl $(X86_CR4_PAE_BIT), %eax
+ movl %eax, %cr4
+
+ movl %cr3, %eax
+ movl %eax, %cr3
+
+ movl $MSR_EFER, %ecx
+ rdmsr
+ btsl $_EFER_LME, %eax
+ wrmsr
+
+ xorl %eax, %eax
+ lldt %ax
+
+ movl 60(%esp), %eax
+ pushl $__KERNEL_CS
+ pushl %eax
+
+ /* Enable paging */
+ movl %cr0, %eax
+ btsl $X86_CR0_PG_BIT, %eax
+ movl %eax, %cr0
+ lret
+ENDPROC(efi_enter32)
+
+ .data
+ .balign 8
+ .global efi32_boot_gdt
+efi32_boot_gdt: .word 0
+ .quad 0
+
+save_gdt: .word 0
+ .quad 0
+func_rt_ptr: .quad 0
+
+ .global efi_gdt64
+efi_gdt64:
+ .word efi_gdt64_end - efi_gdt64
+ .long 0 /* Filled out by user */
+ .word 0
+ .quad 0x0000000000000000 /* NULL descriptor */
+ .quad 0x00af9a000000ffff /* __KERNEL_CS */
+ .quad 0x00cf92000000ffff /* __KERNEL_DS */
+ .quad 0x0080890000000000 /* TS descriptor */
+ .quad 0x0000000000000000 /* TS continued */
+efi_gdt64_end:
diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c
index a950864a64da..5903089c818f 100644
--- a/arch/x86/boot/compressed/misc.c
+++ b/arch/x86/boot/compressed/misc.c
@@ -401,7 +401,8 @@ asmlinkage __visible void *decompress_kernel(void *rmode, memptr heap,
* the entire decompressed kernel plus relocation table, or the
* entire decompressed kernel plus .bss and .brk sections.
*/
- output = choose_kernel_location(input_data, input_len, output,
+ output = choose_kernel_location(real_mode, input_data, input_len,
+ output,
output_len > run_size ? output_len
: run_size);
diff --git a/arch/x86/boot/compressed/misc.h b/arch/x86/boot/compressed/misc.h
index 04477d68403f..ee3576b2666b 100644
--- a/arch/x86/boot/compressed/misc.h
+++ b/arch/x86/boot/compressed/misc.h
@@ -57,7 +57,8 @@ int cmdline_find_option_bool(const char *option);
#if CONFIG_RANDOMIZE_BASE
/* aslr.c */
-unsigned char *choose_kernel_location(unsigned char *input,
+unsigned char *choose_kernel_location(struct boot_params *params,
+ unsigned char *input,
unsigned long input_size,
unsigned char *output,
unsigned long output_size);
@@ -65,7 +66,8 @@ unsigned char *choose_kernel_location(unsigned char *input,
bool has_cpuflag(int flag);
#else
static inline
-unsigned char *choose_kernel_location(unsigned char *input,
+unsigned char *choose_kernel_location(struct boot_params *params,
+ unsigned char *input,
unsigned long input_size,
unsigned char *output,
unsigned long output_size)
diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index 92003f3c8a42..efc3b22d896e 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -213,7 +213,15 @@ void register_lapic_address(unsigned long address);
extern void setup_boot_APIC_clock(void);
extern void setup_secondary_APIC_clock(void);
extern int APIC_init_uniprocessor(void);
+
+#ifdef CONFIG_X86_64
+static inline int apic_force_enable(unsigned long addr)
+{
+ return -1;
+}
+#else
extern int apic_force_enable(unsigned long addr);
+#endif
extern int apic_bsp_setup(bool upmode);
extern void apic_ap_setup(void);
diff --git a/arch/x86/include/asm/imr.h b/arch/x86/include/asm/imr.h
new file mode 100644
index 000000000000..cd2ce4068441
--- /dev/null
+++ b/arch/x86/include/asm/imr.h
@@ -0,0 +1,60 @@
+/*
+ * imr.h: Isolated Memory Region API
+ *
+ * Copyright(c) 2013 Intel Corporation.
+ * Copyright(c) 2015 Bryan O'Donoghue <pure.logic@nexus-software.ie>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; version 2
+ * of the License.
+ */
+#ifndef _IMR_H
+#define _IMR_H
+
+#include <linux/types.h>
+
+/*
+ * IMR agent access mask bits
+ * See section 12.7.4.7 from quark-x1000-datasheet.pdf for register
+ * definitions.
+ */
+#define IMR_ESRAM_FLUSH BIT(31)
+#define IMR_CPU_SNOOP BIT(30) /* Applicable only to write */
+#define IMR_RMU BIT(29)
+#define IMR_VC1_SAI_ID3 BIT(15)
+#define IMR_VC1_SAI_ID2 BIT(14)
+#define IMR_VC1_SAI_ID1 BIT(13)
+#define IMR_VC1_SAI_ID0 BIT(12)
+#define IMR_VC0_SAI_ID3 BIT(11)
+#define IMR_VC0_SAI_ID2 BIT(10)
+#define IMR_VC0_SAI_ID1 BIT(9)
+#define IMR_VC0_SAI_ID0 BIT(8)
+#define IMR_CPU_0 BIT(1) /* SMM mode */
+#define IMR_CPU BIT(0) /* Non SMM mode */
+#define IMR_ACCESS_NONE 0
+
+/*
+ * Read/Write access-all bits here include some reserved bits
+ * These are the values firmware uses and are accepted by hardware.
+ * The kernel defines read/write access-all in the same way as firmware
+ * in order to have a consistent and crisp definition across firmware,
+ * bootloader and kernel.
+ */
+#define IMR_READ_ACCESS_ALL 0xBFFFFFFF
+#define IMR_WRITE_ACCESS_ALL 0xFFFFFFFF
+
+/* Number of IMRs provided by Quark X1000 SoC */
+#define QUARK_X1000_IMR_MAX 0x08
+#define QUARK_X1000_IMR_REGBASE 0x40
+
+/* IMR alignment bits - only bits 31:10 are checked for IMR validity */
+#define IMR_ALIGN 0x400
+#define IMR_MASK (IMR_ALIGN - 1)
+
+int imr_add_range(phys_addr_t base, size_t size,
+ unsigned int rmask, unsigned int wmask, bool lock);
+
+int imr_remove_range(phys_addr_t base, size_t size);
+
+#endif /* _IMR_H */
diff --git a/arch/x86/include/asm/lguest_hcall.h b/arch/x86/include/asm/lguest_hcall.h
index 879fd7d33877..ef01fef3eebc 100644
--- a/arch/x86/include/asm/lguest_hcall.h
+++ b/arch/x86/include/asm/lguest_hcall.h
@@ -16,7 +16,6 @@
#define LHCALL_SET_PTE 14
#define LHCALL_SET_PGD 15
#define LHCALL_LOAD_TLS 16
-#define LHCALL_NOTIFY 17
#define LHCALL_LOAD_GDT_ENTRY 18
#define LHCALL_SEND_INTERRUPTS 19
diff --git a/arch/x86/include/asm/page_types.h b/arch/x86/include/asm/page_types.h
index f97fbe3abb67..95e11f79f123 100644
--- a/arch/x86/include/asm/page_types.h
+++ b/arch/x86/include/asm/page_types.h
@@ -51,6 +51,8 @@ extern int devmem_is_allowed(unsigned long pagenr);
extern unsigned long max_low_pfn_mapped;
extern unsigned long max_pfn_mapped;
+extern bool kaslr_enabled;
+
static inline phys_addr_t get_max_mapped(void)
{
return (phys_addr_t)max_pfn_mapped << PAGE_SHIFT;
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 67fc3d2b0aab..a0c35bf6cb92 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -476,12 +476,14 @@ static inline int pmd_present(pmd_t pmd)
*/
static inline int pte_protnone(pte_t pte)
{
- return pte_flags(pte) & _PAGE_PROTNONE;
+ return (pte_flags(pte) & (_PAGE_PROTNONE | _PAGE_PRESENT))
+ == _PAGE_PROTNONE;
}
static inline int pmd_protnone(pmd_t pmd)
{
- return pmd_flags(pmd) & _PAGE_PROTNONE;
+ return (pmd_flags(pmd) & (_PAGE_PROTNONE | _PAGE_PRESENT))
+ == _PAGE_PROTNONE;
}
#endif /* CONFIG_NUMA_BALANCING */
diff --git a/arch/x86/include/asm/spinlock.h b/arch/x86/include/asm/spinlock.h
index 7050d864f520..cf87de3fc390 100644
--- a/arch/x86/include/asm/spinlock.h
+++ b/arch/x86/include/asm/spinlock.h
@@ -46,7 +46,7 @@ static __always_inline bool static_key_false(struct static_key *key);
static inline void __ticket_enter_slowpath(arch_spinlock_t *lock)
{
- set_bit(0, (volatile unsigned long *)&lock->tickets.tail);
+ set_bit(0, (volatile unsigned long *)&lock->tickets.head);
}
#else /* !CONFIG_PARAVIRT_SPINLOCKS */
@@ -60,10 +60,30 @@ static inline void __ticket_unlock_kick(arch_spinlock_t *lock,
}
#endif /* CONFIG_PARAVIRT_SPINLOCKS */
+static inline int __tickets_equal(__ticket_t one, __ticket_t two)
+{
+ return !((one ^ two) & ~TICKET_SLOWPATH_FLAG);
+}
+
+static inline void __ticket_check_and_clear_slowpath(arch_spinlock_t *lock,
+ __ticket_t head)
+{
+ if (head & TICKET_SLOWPATH_FLAG) {
+ arch_spinlock_t old, new;
+
+ old.tickets.head = head;
+ new.tickets.head = head & ~TICKET_SLOWPATH_FLAG;
+ old.tickets.tail = new.tickets.head + TICKET_LOCK_INC;
+ new.tickets.tail = old.tickets.tail;
+
+ /* try to clear slowpath flag when there are no contenders */
+ cmpxchg(&lock->head_tail, old.head_tail, new.head_tail);
+ }
+}
static __always_inline int arch_spin_value_unlocked(arch_spinlock_t lock)
{
- return lock.tickets.head == lock.tickets.tail;
+ return __tickets_equal(lock.tickets.head, lock.tickets.tail);
}
/*
@@ -87,18 +107,21 @@ static __always_inline void arch_spin_lock(arch_spinlock_t *lock)
if (likely(inc.head == inc.tail))
goto out;
- inc.tail &= ~TICKET_SLOWPATH_FLAG;
for (;;) {
unsigned count = SPIN_THRESHOLD;
do {
- if (READ_ONCE(lock->tickets.head) == inc.tail)
- goto out;
+ inc.head = READ_ONCE(lock->tickets.head);
+ if (__tickets_equal(inc.head, inc.tail))
+ goto clear_slowpath;
cpu_relax();
} while (--count);
__ticket_lock_spinning(lock, inc.tail);
}
-out: barrier(); /* make sure nothing creeps before the lock is taken */
+clear_slowpath:
+ __ticket_check_and_clear_slowpath(lock, inc.head);
+out:
+ barrier(); /* make sure nothing creeps before the lock is taken */
}
static __always_inline int arch_spin_trylock(arch_spinlock_t *lock)
@@ -106,56 +129,30 @@ static __always_inline int arch_spin_trylock(arch_spinlock_t *lock)
arch_spinlock_t old, new;
old.tickets = READ_ONCE(lock->tickets);
- if (old.tickets.head != (old.tickets.tail & ~TICKET_SLOWPATH_FLAG))
+ if (!__tickets_equal(old.tickets.head, old.tickets.tail))
return 0;
new.head_tail = old.head_tail + (TICKET_LOCK_INC << TICKET_SHIFT);
+ new.head_tail &= ~TICKET_SLOWPATH_FLAG;
/* cmpxchg is a full barrier, so nothing can move before it */
return cmpxchg(&lock->head_tail, old.head_tail, new.head_tail) == old.head_tail;
}
-static inline void __ticket_unlock_slowpath(arch_spinlock_t *lock,
- arch_spinlock_t old)
-{
- arch_spinlock_t new;
-
- BUILD_BUG_ON(((__ticket_t)NR_CPUS) != NR_CPUS);
-
- /* Perform the unlock on the "before" copy */
- old.tickets.head += TICKET_LOCK_INC;
-
- /* Clear the slowpath flag */
- new.head_tail = old.head_tail & ~(TICKET_SLOWPATH_FLAG << TICKET_SHIFT);
-
- /*
- * If the lock is uncontended, clear the flag - use cmpxchg in
- * case it changes behind our back though.
- */
- if (new.tickets.head != new.tickets.tail ||
- cmpxchg(&lock->head_tail, old.head_tail,
- new.head_tail) != old.head_tail) {
- /*
- * Lock still has someone queued for it, so wake up an
- * appropriate waiter.
- */
- __ticket_unlock_kick(lock, old.tickets.head);
- }
-}
-
static __always_inline void arch_spin_unlock(arch_spinlock_t *lock)
{
if (TICKET_SLOWPATH_FLAG &&
- static_key_false(&paravirt_ticketlocks_enabled)) {
- arch_spinlock_t prev;
+ static_key_false(&paravirt_ticketlocks_enabled)) {
+ __ticket_t head;
- prev = *lock;
- add_smp(&lock->tickets.head, TICKET_LOCK_INC);
+ BUILD_BUG_ON(((__ticket_t)NR_CPUS) != NR_CPUS);
- /* add_smp() is a full mb() */
+ head = xadd(&lock->tickets.head, TICKET_LOCK_INC);
- if (unlikely(lock->tickets.tail & TICKET_SLOWPATH_FLAG))
- __ticket_unlock_slowpath(lock, prev);
+ if (unlikely(head & TICKET_SLOWPATH_FLAG)) {
+ head &= ~TICKET_SLOWPATH_FLAG;
+ __ticket_unlock_kick(lock, (head + TICKET_LOCK_INC));
+ }
} else
__add(&lock->tickets.head, TICKET_LOCK_INC, UNLOCK_LOCK_PREFIX);
}
@@ -164,14 +161,15 @@ static inline int arch_spin_is_locked(arch_spinlock_t *lock)
{
struct __raw_tickets tmp = READ_ONCE(lock->tickets);
- return tmp.tail != tmp.head;
+ return !__tickets_equal(tmp.tail, tmp.head);
}
static inline int arch_spin_is_contended(arch_spinlock_t *lock)
{
struct __raw_tickets tmp = READ_ONCE(lock->tickets);
- return (__ticket_t)(tmp.tail - tmp.head) > TICKET_LOCK_INC;
+ tmp.head &= ~TICKET_SLOWPATH_FLAG;
+ return (tmp.tail - tmp.head) > TICKET_LOCK_INC;
}
#define arch_spin_is_contended arch_spin_is_contended
@@ -191,8 +189,8 @@ static inline void arch_spin_unlock_wait(arch_spinlock_t *lock)
* We need to check "unlocked" in a loop, tmp.head == head
* can be false positive because of overflow.
*/
- if (tmp.head == (tmp.tail & ~TICKET_SLOWPATH_FLAG) ||
- tmp.head != head)
+ if (__tickets_equal(tmp.head, tmp.tail) ||
+ !__tickets_equal(tmp.head, head))
break;
cpu_relax();
diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index 0d592e0a5b84..ace9dec050b1 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -179,7 +179,7 @@ __typeof__(__builtin_choose_expr(sizeof(x) > sizeof(0UL), 0ULL, 0UL))
asm volatile("call __get_user_%P3" \
: "=a" (__ret_gu), "=r" (__val_gu) \
: "0" (ptr), "i" (sizeof(*(ptr)))); \
- (x) = (__typeof__(*(ptr))) __val_gu; \
+ (x) = (__force __typeof__(*(ptr))) __val_gu; \
__ret_gu; \
})
diff --git a/arch/x86/include/uapi/asm/bootparam.h b/arch/x86/include/uapi/asm/bootparam.h
index 225b0988043a..44e6dd7e36a2 100644
--- a/arch/x86/include/uapi/asm/bootparam.h
+++ b/arch/x86/include/uapi/asm/bootparam.h
@@ -7,6 +7,7 @@
#define SETUP_DTB 2
#define SETUP_PCI 3
#define SETUP_EFI 4
+#define SETUP_KASLR 5
/* ram_size flags */
#define RAMDISK_IMAGE_START_MASK 0x07FF
diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index ae97ed0873c6..3d525c6124f6 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -613,6 +613,11 @@ int acpi_gsi_to_irq(u32 gsi, unsigned int *irqp)
{
int rc, irq, trigger, polarity;
+ if (acpi_irq_model == ACPI_IRQ_MODEL_PIC) {
+ *irqp = gsi;
+ return 0;
+ }
+
rc = acpi_get_override_irq(gsi, &trigger, &polarity);
if (rc == 0) {
trigger = trigger ? ACPI_LEVEL_SENSITIVE : ACPI_EDGE_SENSITIVE;
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index b5c8ff5e9dfc..2346c95c6ab1 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1396,6 +1396,12 @@ void cpu_init(void)
wait_for_master_cpu(cpu);
+ /*
+ * Initialize the CR4 shadow before doing anything that could
+ * try to read it.
+ */
+ cr4_init_shadow();
+
show_ucode_info_early();
printk(KERN_INFO "Initializing CPU#%d\n", cpu);
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index 94d7dcb12145..50163fa9034f 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -565,8 +565,8 @@ static const struct _tlb_table intel_tlb_table[] = {
{ 0xb2, TLB_INST_4K, 64, " TLB_INST 4KByte pages, 4-way set associative" },
{ 0xb3, TLB_DATA_4K, 128, " TLB_DATA 4 KByte pages, 4-way set associative" },
{ 0xb4, TLB_DATA_4K, 256, " TLB_DATA 4 KByte pages, 4-way associative" },
- { 0xb5, TLB_INST_4K, 64, " TLB_INST 4 KByte pages, 8-way set ssociative" },
- { 0xb6, TLB_INST_4K, 128, " TLB_INST 4 KByte pages, 8-way set ssociative" },
+ { 0xb5, TLB_INST_4K, 64, " TLB_INST 4 KByte pages, 8-way set associative" },
+ { 0xb6, TLB_INST_4K, 128, " TLB_INST 4 KByte pages, 8-way set associative" },
{ 0xba, TLB_DATA_4K, 64, " TLB_DATA 4 KByte pages, 4-way associative" },
{ 0xc0, TLB_DATA_4K_4M, 8, " TLB_DATA 4 KByte and 4 MByte pages, 4-way associative" },
{ 0xc1, STLB_4K_2M, 1024, " STLB 4 KByte and 2 MByte pages, 8-way associative" },
diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c
index c6826d1e8082..746e7fd08aad 100644
--- a/arch/x86/kernel/cpu/microcode/intel.c
+++ b/arch/x86/kernel/cpu/microcode/intel.c
@@ -196,6 +196,11 @@ static enum ucode_state generic_load_microcode(int cpu, void *data, size_t size,
struct microcode_header_intel mc_header;
unsigned int mc_size;
+ if (leftover < sizeof(mc_header)) {
+ pr_err("error! Truncated header in microcode data file\n");
+ break;
+ }
+
if (get_ucode_data(&mc_header, ucode_ptr, sizeof(mc_header)))
break;
diff --git a/arch/x86/kernel/cpu/microcode/intel_early.c b/arch/x86/kernel/cpu/microcode/intel_early.c
index ec9df6f9cd47..420eb933189c 100644
--- a/arch/x86/kernel/cpu/microcode/intel_early.c
+++ b/arch/x86/kernel/cpu/microcode/intel_early.c
@@ -321,7 +321,11 @@ get_matching_model_microcode(int cpu, unsigned long start,
unsigned int mc_saved_count = mc_saved_data->mc_saved_count;
int i;
- while (leftover) {
+ while (leftover && mc_saved_count < ARRAY_SIZE(mc_saved_tmp)) {
+
+ if (leftover < sizeof(mc_header))
+ break;
+
mc_header = (struct microcode_header_intel *)ucode_ptr;
mc_size = get_totalsize(mc_header);
diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S
index 000d4199b03e..31e2d5bf3e38 100644
--- a/arch/x86/kernel/entry_32.S
+++ b/arch/x86/kernel/entry_32.S
@@ -982,6 +982,9 @@ ENTRY(xen_hypervisor_callback)
ENTRY(xen_do_upcall)
1: mov %esp, %eax
call xen_evtchn_do_upcall
+#ifndef CONFIG_PREEMPT
+ call xen_maybe_preempt_hcall
+#endif
jmp ret_from_intr
CFI_ENDPROC
ENDPROC(xen_hypervisor_callback)
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index db13655c3a2a..10074ad9ebf8 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -1208,6 +1208,9 @@ ENTRY(xen_do_hypervisor_callback) # do_hypervisor_callback(struct *pt_regs)
popq %rsp
CFI_DEF_CFA_REGISTER rsp
decl PER_CPU_VAR(irq_count)
+#ifndef CONFIG_PREEMPT
+ call xen_maybe_preempt_hcall
+#endif
jmp error_exit
CFI_ENDPROC
END(xen_do_hypervisor_callback)
diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c
index 705ef8d48e2d..67b1cbe0093a 100644
--- a/arch/x86/kernel/irq.c
+++ b/arch/x86/kernel/irq.c
@@ -302,6 +302,9 @@ int check_irq_vectors_for_cpu_disable(void)
irq = __this_cpu_read(vector_irq[vector]);
if (irq >= 0) {
desc = irq_to_desc(irq);
+ if (!desc)
+ continue;
+
data = irq_desc_get_irq_data(desc);
cpumask_copy(&affinity_new, data->affinity);
cpu_clear(this_cpu, affinity_new);
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index 98f654d466e5..4e3d5a9621fe 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -84,7 +84,7 @@ static volatile u32 twobyte_is_boostable[256 / 32] = {
/* 0 1 2 3 4 5 6 7 8 9 a b c d e f */
/* ---------------------------------------------- */
W(0x00, 0, 0, 1, 1, 0, 0, 1, 0, 1, 1, 0, 0, 0, 0, 0, 0) | /* 00 */
- W(0x10, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0) , /* 10 */
+ W(0x10, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1) , /* 10 */
W(0x20, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0) | /* 20 */
W(0x30, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0) , /* 30 */
W(0x40, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) | /* 40 */
@@ -223,27 +223,48 @@ static unsigned long
__recover_probed_insn(kprobe_opcode_t *buf, unsigned long addr)
{
struct kprobe *kp;
+ unsigned long faddr;
kp = get_kprobe((void *)addr);
- /* There is no probe, return original address */
- if (!kp)
+ faddr = ftrace_location(addr);
+ /*
+ * Addresses inside the ftrace location are refused by
+ * arch_check_ftrace_location(). Something went terribly wrong
+ * if such an address is checked here.
+ */
+ if (WARN_ON(faddr && faddr != addr))
+ return 0UL;
+ /*
+ * Use the current code if it is not modified by Kprobe
+ * and it cannot be modified by ftrace.
+ */
+ if (!kp && !faddr)
return addr;
/*
- * Basically, kp->ainsn.insn has an original instruction.
- * However, RIP-relative instruction can not do single-stepping
- * at different place, __copy_instruction() tweaks the displacement of
- * that instruction. In that case, we can't recover the instruction
- * from the kp->ainsn.insn.
+ * Basically, kp->ainsn.insn has an original instruction.
+ * However, RIP-relative instruction can not do single-stepping
+ * at different place, __copy_instruction() tweaks the displacement of
+ * that instruction. In that case, we can't recover the instruction
+ * from the kp->ainsn.insn.
*
- * On the other hand, kp->opcode has a copy of the first byte of
- * the probed instruction, which is overwritten by int3. And
- * the instruction at kp->addr is not modified by kprobes except
- * for the first byte, we can recover the original instruction
- * from it and kp->opcode.
+ * On the other hand, in case on normal Kprobe, kp->opcode has a copy
+ * of the first byte of the probed instruction, which is overwritten
+ * by int3. And the instruction at kp->addr is not modified by kprobes
+ * except for the first byte, we can recover the original instruction
+ * from it and kp->opcode.
+ *
+ * In case of Kprobes using ftrace, we do not have a copy of
+ * the original instruction. In fact, the ftrace location might
+ * be modified at anytime and even could be in an inconsistent state.
+ * Fortunately, we know that the original code is the ideal 5-byte
+ * long NOP.
*/
- memcpy(buf, kp->addr, MAX_INSN_SIZE * sizeof(kprobe_opcode_t));
- buf[0] = kp->opcode;
+ memcpy(buf, (void *)addr, MAX_INSN_SIZE * sizeof(kprobe_opcode_t));
+ if (faddr)
+ memcpy(buf, ideal_nops[NOP_ATOMIC5], 5);
+ else
+ buf[0] = kp->opcode;
return (unsigned long)buf;
}
@@ -251,6 +272,7 @@ __recover_probed_insn(kprobe_opcode_t *buf, unsigned long addr)
* Recover the probed instruction at addr for further analysis.
* Caller must lock kprobes by kprobe_mutex, or disable preemption
* for preventing to release referencing kprobes.
+ * Returns zero if the instruction can not get recovered.
*/
unsigned long recover_probed_instruction(kprobe_opcode_t *buf, unsigned long addr)
{
@@ -285,6 +307,8 @@ static int can_probe(unsigned long paddr)
* normally used, we just go through if there is no kprobe.
*/
__addr = recover_probed_instruction(buf, addr);
+ if (!__addr)
+ return 0;
kernel_insn_init(&insn, (void *)__addr, MAX_INSN_SIZE);
insn_get_length(&insn);
@@ -333,6 +357,8 @@ int __copy_instruction(u8 *dest, u8 *src)
unsigned long recovered_insn =
recover_probed_instruction(buf, (unsigned long)src);
+ if (!recovered_insn)
+ return 0;
kernel_insn_init(&insn, (void *)recovered_insn, MAX_INSN_SIZE);
insn_get_length(&insn);
/* Another subsystem puts a breakpoint, failed to recover */
diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c
index 0dd8d089c315..7b3b9d15c47a 100644
--- a/arch/x86/kernel/kprobes/opt.c
+++ b/arch/x86/kernel/kprobes/opt.c
@@ -259,6 +259,8 @@ static int can_optimize(unsigned long paddr)
*/
return 0;
recovered_insn = recover_probed_instruction(buf, addr);
+ if (!recovered_insn)
+ return 0;
kernel_insn_init(&insn, (void *)recovered_insn, MAX_INSN_SIZE);
insn_get_length(&insn);
/* Another subsystem puts a breakpoint */
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index 94f643484300..e354cc6446ab 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -609,7 +609,7 @@ static inline void check_zero(void)
u8 ret;
u8 old;
- old = ACCESS_ONCE(zero_stats);
+ old = READ_ONCE(zero_stats);
if (unlikely(old)) {
ret = cmpxchg(&zero_stats, old, 0);
/* This ensures only one fellow resets the stat */
@@ -727,6 +727,7 @@ __visible void kvm_lock_spinning(struct arch_spinlock *lock, __ticket_t want)
int cpu;
u64 start;
unsigned long flags;
+ __ticket_t head;
if (in_nmi())
return;
@@ -768,11 +769,15 @@ __visible void kvm_lock_spinning(struct arch_spinlock *lock, __ticket_t want)
*/
__ticket_enter_slowpath(lock);
+ /* make sure enter_slowpath, which is atomic does not cross the read */
+ smp_mb__after_atomic();
+
/*
* check again make sure it didn't become free while
* we weren't looking.
*/
- if (ACCESS_ONCE(lock->tickets.head) == want) {
+ head = READ_ONCE(lock->tickets.head);
+ if (__tickets_equal(head, want)) {
add_stats(TAKEN_SLOW_PICKUP, 1);
goto out;
}
@@ -803,8 +808,8 @@ static void kvm_unlock_kick(struct arch_spinlock *lock, __ticket_t ticket)
add_stats(RELEASED_SLOW, 1);
for_each_cpu(cpu, &waiting_cpus) {
const struct kvm_lock_waiting *w = &per_cpu(klock_waiting, cpu);
- if (ACCESS_ONCE(w->lock) == lock &&
- ACCESS_ONCE(w->want) == ticket) {
+ if (READ_ONCE(w->lock) == lock &&
+ READ_ONCE(w->want) == ticket) {
add_stats(RELEASED_SLOW_KICKED, 1);
kvm_kick_cpu(cpu);
break;
diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c
index d1ac80b72c72..9bbb9b35c144 100644
--- a/arch/x86/kernel/module.c
+++ b/arch/x86/kernel/module.c
@@ -47,21 +47,13 @@ do { \
#ifdef CONFIG_RANDOMIZE_BASE
static unsigned long module_load_offset;
-static int randomize_modules = 1;
/* Mutex protects the module_load_offset. */
static DEFINE_MUTEX(module_kaslr_mutex);
-static int __init parse_nokaslr(char *p)
-{
- randomize_modules = 0;
- return 0;
-}
-early_param("nokaslr", parse_nokaslr);
-
static unsigned long int get_module_load_offset(void)
{
- if (randomize_modules) {
+ if (kaslr_enabled) {
mutex_lock(&module_kaslr_mutex);
/*
* Calculate the module_load_offset the first time this
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 0a2421cca01f..98dc9317286e 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -122,6 +122,8 @@
unsigned long max_low_pfn_mapped;
unsigned long max_pfn_mapped;
+bool __read_mostly kaslr_enabled = false;
+
#ifdef CONFIG_DMI
RESERVE_BRK(dmi_alloc, 65536);
#endif
@@ -425,6 +427,11 @@ static void __init reserve_initrd(void)
}
#endif /* CONFIG_BLK_DEV_INITRD */
+static void __init parse_kaslr_setup(u64 pa_data, u32 data_len)
+{
+ kaslr_enabled = (bool)(pa_data + sizeof(struct setup_data));
+}
+
static void __init parse_setup_data(void)
{
struct setup_data *data;
@@ -450,6 +457,9 @@ static void __init parse_setup_data(void)
case SETUP_EFI:
parse_efi_setup(pa_data, data_len);
break;
+ case SETUP_KASLR:
+ parse_kaslr_setup(pa_data, data_len);
+ break;
default:
break;
}
@@ -832,10 +842,14 @@ static void __init trim_low_memory_range(void)
static int
dump_kernel_offset(struct notifier_block *self, unsigned long v, void *p)
{
- pr_emerg("Kernel Offset: 0x%lx from 0x%lx "
- "(relocation range: 0x%lx-0x%lx)\n",
- (unsigned long)&_text - __START_KERNEL, __START_KERNEL,
- __START_KERNEL_map, MODULES_VADDR-1);
+ if (kaslr_enabled)
+ pr_emerg("Kernel Offset: 0x%lx from 0x%lx (relocation range: 0x%lx-0x%lx)\n",
+ (unsigned long)&_text - __START_KERNEL,
+ __START_KERNEL,
+ __START_KERNEL_map,
+ MODULES_VADDR-1);
+ else
+ pr_emerg("Kernel Offset: disabled\n");
return 0;
}
diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c
index 8b96a947021f..81f8adb0679e 100644
--- a/arch/x86/kernel/uprobes.c
+++ b/arch/x86/kernel/uprobes.c
@@ -66,27 +66,54 @@
* Good-instruction tables for 32-bit apps. This is non-const and volatile
* to keep gcc from statically optimizing it out, as variable_test_bit makes
* some versions of gcc to think only *(unsigned long*) is used.
+ *
+ * Opcodes we'll probably never support:
+ * 6c-6f - ins,outs. SEGVs if used in userspace
+ * e4-e7 - in,out imm. SEGVs if used in userspace
+ * ec-ef - in,out acc. SEGVs if used in userspace
+ * cc - int3. SIGTRAP if used in userspace
+ * ce - into. Not used in userspace - no kernel support to make it useful. SEGVs
+ * (why we support bound (62) then? it's similar, and similarly unused...)
+ * f1 - int1. SIGTRAP if used in userspace
+ * f4 - hlt. SEGVs if used in userspace
+ * fa - cli. SEGVs if used in userspace
+ * fb - sti. SEGVs if used in userspace
+ *
+ * Opcodes which need some work to be supported:
+ * 07,17,1f - pop es/ss/ds
+ * Normally not used in userspace, but would execute if used.
+ * Can cause GP or stack exception if tries to load wrong segment descriptor.
+ * We hesitate to run them under single step since kernel's handling
+ * of userspace single-stepping (TF flag) is fragile.
+ * We can easily refuse to support push es/cs/ss/ds (06/0e/16/1e)
+ * on the same grounds that they are never used.
+ * cd - int N.
+ * Used by userspace for "int 80" syscall entry. (Other "int N"
+ * cause GP -> SEGV since their IDT gates don't allow calls from CPL 3).
+ * Not supported since kernel's handling of userspace single-stepping
+ * (TF flag) is fragile.
+ * cf - iret. Normally not used in userspace. Doesn't SEGV unless arguments are bad
*/
#if defined(CONFIG_X86_32) || defined(CONFIG_IA32_EMULATION)
static volatile u32 good_insns_32[256 / 32] = {
/* 0 1 2 3 4 5 6 7 8 9 a b c d e f */
/* ---------------------------------------------- */
- W(0x00, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 0) | /* 00 */
+ W(0x00, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1) | /* 00 */
W(0x10, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 0) , /* 10 */
- W(0x20, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 0, 1) | /* 20 */
- W(0x30, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 0, 1) , /* 30 */
+ W(0x20, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) | /* 20 */
+ W(0x30, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) , /* 30 */
W(0x40, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) | /* 40 */
W(0x50, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) , /* 50 */
- W(0x60, 1, 1, 1, 0, 1, 1, 0, 0, 1, 1, 1, 1, 0, 0, 0, 0) | /* 60 */
+ W(0x60, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0) | /* 60 */
W(0x70, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) , /* 70 */
W(0x80, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) | /* 80 */
W(0x90, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) , /* 90 */
W(0xa0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) | /* a0 */
W(0xb0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) , /* b0 */
W(0xc0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0) | /* c0 */
- W(0xd0, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1) , /* d0 */
+ W(0xd0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) , /* d0 */
W(0xe0, 1, 1, 1, 1, 0, 0, 0, 0, 1, 1, 1, 1, 0, 0, 0, 0) | /* e0 */
- W(0xf0, 0, 0, 1, 1, 0, 1, 1, 1, 1, 1, 0, 0, 1, 1, 1, 1) /* f0 */
+ W(0xf0, 1, 0, 1, 1, 0, 1, 1, 1, 1, 1, 0, 0, 1, 1, 1, 1) /* f0 */
/* ---------------------------------------------- */
/* 0 1 2 3 4 5 6 7 8 9 a b c d e f */
};
@@ -94,27 +121,61 @@ static volatile u32 good_insns_32[256 / 32] = {
#define good_insns_32 NULL
#endif
-/* Good-instruction tables for 64-bit apps */
+/* Good-instruction tables for 64-bit apps.
+ *
+ * Genuinely invalid opcodes:
+ * 06,07 - formerly push/pop es
+ * 0e - formerly push cs
+ * 16,17 - formerly push/pop ss
+ * 1e,1f - formerly push/pop ds
+ * 27,2f,37,3f - formerly daa/das/aaa/aas
+ * 60,61 - formerly pusha/popa
+ * 62 - formerly bound. EVEX prefix for AVX512 (not yet supported)
+ * 82 - formerly redundant encoding of Group1
+ * 9a - formerly call seg:ofs
+ * ce - formerly into
+ * d4,d5 - formerly aam/aad
+ * d6 - formerly undocumented salc
+ * ea - formerly jmp seg:ofs
+ *
+ * Opcodes we'll probably never support:
+ * 6c-6f - ins,outs. SEGVs if used in userspace
+ * e4-e7 - in,out imm. SEGVs if used in userspace
+ * ec-ef - in,out acc. SEGVs if used in userspace
+ * cc - int3. SIGTRAP if used in userspace
+ * f1 - int1. SIGTRAP if used in userspace
+ * f4 - hlt. SEGVs if used in userspace
+ * fa - cli. SEGVs if used in userspace
+ * fb - sti. SEGVs if used in userspace
+ *
+ * Opcodes which need some work to be supported:
+ * cd - int N.
+ * Used by userspace for "int 80" syscall entry. (Other "int N"
+ * cause GP -> SEGV since their IDT gates don't allow calls from CPL 3).
+ * Not supported since kernel's handling of userspace single-stepping
+ * (TF flag) is fragile.
+ * cf - iret. Normally not used in userspace. Doesn't SEGV unless arguments are bad
+ */
#if defined(CONFIG_X86_64)
static volatile u32 good_insns_64[256 / 32] = {
/* 0 1 2 3 4 5 6 7 8 9 a b c d e f */
/* ---------------------------------------------- */
- W(0x00, 1, 1, 1, 1, 1, 1, 0, 0, 1, 1, 1, 1, 1, 1, 0, 0) | /* 00 */
+ W(0x00, 1, 1, 1, 1, 1, 1, 0, 0, 1, 1, 1, 1, 1, 1, 0, 1) | /* 00 */
W(0x10, 1, 1, 1, 1, 1, 1, 0, 0, 1, 1, 1, 1, 1, 1, 0, 0) , /* 10 */
- W(0x20, 1, 1, 1, 1, 1, 1, 0, 0, 1, 1, 1, 1, 1, 1, 0, 0) | /* 20 */
- W(0x30, 1, 1, 1, 1, 1, 1, 0, 0, 1, 1, 1, 1, 1, 1, 0, 0) , /* 30 */
- W(0x40, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0) | /* 40 */
+ W(0x20, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 0) | /* 20 */
+ W(0x30, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 0) , /* 30 */
+ W(0x40, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) | /* 40 */
W(0x50, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) , /* 50 */
- W(0x60, 0, 0, 0, 1, 1, 1, 0, 0, 1, 1, 1, 1, 0, 0, 0, 0) | /* 60 */
+ W(0x60, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0) | /* 60 */
W(0x70, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) , /* 70 */
W(0x80, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) | /* 80 */
- W(0x90, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) , /* 90 */
+ W(0x90, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1) , /* 90 */
W(0xa0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) | /* a0 */
W(0xb0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) , /* b0 */
- W(0xc0, 1, 1, 1, 1, 0, 0, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0) | /* c0 */
+ W(0xc0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0) | /* c0 */
W(0xd0, 1, 1, 1, 1, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1) , /* d0 */
- W(0xe0, 1, 1, 1, 1, 0, 0, 0, 0, 1, 1, 1, 1, 0, 0, 0, 0) | /* e0 */
- W(0xf0, 0, 0, 1, 1, 0, 1, 1, 1, 1, 1, 0, 0, 1, 1, 1, 1) /* f0 */
+ W(0xe0, 1, 1, 1, 1, 0, 0, 0, 0, 1, 1, 0, 1, 0, 0, 0, 0) | /* e0 */
+ W(0xf0, 1, 0, 1, 1, 0, 1, 1, 1, 1, 1, 0, 0, 1, 1, 1, 1) /* f0 */
/* ---------------------------------------------- */
/* 0 1 2 3 4 5 6 7 8 9 a b c d e f */
};
@@ -122,49 +183,55 @@ static volatile u32 good_insns_64[256 / 32] = {
#define good_insns_64 NULL
#endif
-/* Using this for both 64-bit and 32-bit apps */
+/* Using this for both 64-bit and 32-bit apps.
+ * Opcodes we don't support:
+ * 0f 00 - SLDT/STR/LLDT/LTR/VERR/VERW/-/- group. System insns
+ * 0f 01 - SGDT/SIDT/LGDT/LIDT/SMSW/-/LMSW/INVLPG group.
+ * Also encodes tons of other system insns if mod=11.
+ * Some are in fact non-system: xend, xtest, rdtscp, maybe more
+ * 0f 05 - syscall
+ * 0f 06 - clts (CPL0 insn)
+ * 0f 07 - sysret
+ * 0f 08 - invd (CPL0 insn)
+ * 0f 09 - wbinvd (CPL0 insn)
+ * 0f 0b - ud2
+ * 0f 30 - wrmsr (CPL0 insn) (then why rdmsr is allowed, it's also CPL0 insn?)
+ * 0f 34 - sysenter
+ * 0f 35 - sysexit
+ * 0f 37 - getsec
+ * 0f 78 - vmread (Intel VMX. CPL0 insn)
+ * 0f 79 - vmwrite (Intel VMX. CPL0 insn)
+ * Note: with prefixes, these two opcodes are
+ * extrq/insertq/AVX512 convert vector ops.
+ * 0f ae - group15: [f]xsave,[f]xrstor,[v]{ld,st}mxcsr,clflush[opt],
+ * {rd,wr}{fs,gs}base,{s,l,m}fence.
+ * Why? They are all user-executable.
+ */
static volatile u32 good_2byte_insns[256 / 32] = {
/* 0 1 2 3 4 5 6 7 8 9 a b c d e f */
/* ---------------------------------------------- */
- W(0x00, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 1) | /* 00 */
- W(0x10, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1) , /* 10 */
- W(0x20, 1, 1, 1, 1, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1, 1) | /* 20 */
- W(0x30, 0, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0) , /* 30 */
+ W(0x00, 0, 0, 1, 1, 1, 0, 0, 0, 0, 0, 1, 0, 1, 1, 1, 1) | /* 00 */
+ W(0x10, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) , /* 10 */
+ W(0x20, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) | /* 20 */
+ W(0x30, 0, 1, 1, 1, 0, 0, 1, 0, 1, 1, 1, 1, 1, 1, 1, 1) , /* 30 */
W(0x40, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) | /* 40 */
W(0x50, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) , /* 50 */
W(0x60, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) | /* 60 */
- W(0x70, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 1, 1) , /* 70 */
+ W(0x70, 1, 1, 1, 1, 1, 1, 1, 1, 0, 0, 1, 1, 1, 1, 1, 1) , /* 70 */
W(0x80, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) | /* 80 */
W(0x90, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) , /* 90 */
- W(0xa0, 1, 1, 1, 1, 1, 1, 0, 0, 1, 1, 1, 1, 1, 1, 0, 1) | /* a0 */
- W(0xb0, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1, 1, 1, 1, 1, 1, 1) , /* b0 */
+ W(0xa0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0, 1) | /* a0 */
+ W(0xb0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) , /* b0 */
W(0xc0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) | /* c0 */
- W(0xd0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) , /* d0 */
+ W(0xd0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) , /* d0 */
W(0xe0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) | /* e0 */
- W(0xf0, 0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 0) /* f0 */
+ W(0xf0, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1) /* f0 */
/* ---------------------------------------------- */
/* 0 1 2 3 4 5 6 7 8 9 a b c d e f */
};
#undef W
/*
- * opcodes we'll probably never support:
- *
- * 6c-6d, e4-e5, ec-ed - in
- * 6e-6f, e6-e7, ee-ef - out
- * cc, cd - int3, int
- * cf - iret
- * d6 - illegal instruction
- * f1 - int1/icebp
- * f4 - hlt
- * fa, fb - cli, sti
- * 0f - lar, lsl, syscall, clts, sysret, sysenter, sysexit, invd, wbinvd, ud2
- *
- * invalid opcodes in 64-bit mode:
- *
- * 06, 0e, 16, 1e, 27, 2f, 37, 3f, 60-62, 82, c4-c5, d4-d5
- * 63 - we support this opcode in x86_64 but not in i386.
- *
* opcodes we may need to refine support for:
*
* 0f - 2-byte instructions: For many of these instructions, the validity
diff --git a/arch/x86/lguest/Kconfig b/arch/x86/lguest/Kconfig
index 4a0890f815c4..08f41caada45 100644
--- a/arch/x86/lguest/Kconfig
+++ b/arch/x86/lguest/Kconfig
@@ -1,6 +1,6 @@
config LGUEST_GUEST
bool "Lguest guest support"
- depends on X86_32 && PARAVIRT
+ depends on X86_32 && PARAVIRT && PCI
select TTY
select VIRTUALIZATION
select VIRTIO
@@ -8,7 +8,7 @@ config LGUEST_GUEST
help
Lguest is a tiny in-kernel hypervisor. Selecting this will
allow your kernel to boot under lguest. This option will increase
- your kernel size by about 6k. If in doubt, say N.
+ your kernel size by about 10k. If in doubt, say N.
If you say Y here, make sure you say Y (or M) to the virtio block
and net drivers which lguest needs.
diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c
index c1c1544b8485..ac4453d8520e 100644
--- a/arch/x86/lguest/boot.c
+++ b/arch/x86/lguest/boot.c
@@ -56,6 +56,9 @@
#include <linux/virtio_console.h>
#include <linux/pm.h>
#include <linux/export.h>
+#include <linux/pci.h>
+#include <linux/virtio_pci.h>
+#include <asm/acpi.h>
#include <asm/apic.h>
#include <asm/lguest.h>
#include <asm/paravirt.h>
@@ -71,6 +74,8 @@
#include <asm/stackprotector.h>
#include <asm/reboot.h> /* for struct machine_ops */
#include <asm/kvm_para.h>
+#include <asm/pci_x86.h>
+#include <asm/pci-direct.h>
/*G:010
* Welcome to the Guest!
@@ -831,6 +836,24 @@ static struct irq_chip lguest_irq_controller = {
.irq_unmask = enable_lguest_irq,
};
+static int lguest_enable_irq(struct pci_dev *dev)
+{
+ u8 line = 0;
+
+ /* We literally use the PCI interrupt line as the irq number. */
+ pci_read_config_byte(dev, PCI_INTERRUPT_LINE, &line);
+ irq_set_chip_and_handler_name(line, &lguest_irq_controller,
+ handle_level_irq, "level");
+ dev->irq = line;
+ return 0;
+}
+
+/* We don't do hotplug PCI, so this shouldn't be called. */
+static void lguest_disable_irq(struct pci_dev *dev)
+{
+ WARN_ON(1);
+}
+
/*
* This sets up the Interrupt Descriptor Table (IDT) entry for each hardware
* interrupt (except 128, which is used for system calls), and then tells the
@@ -1181,25 +1204,136 @@ static __init char *lguest_memory_setup(void)
return "LGUEST";
}
+/* Offset within PCI config space of BAR access capability. */
+static int console_cfg_offset = 0;
+static int console_access_cap;
+
+/* Set up so that we access off in bar0 (on bus 0, device 1, function 0) */
+static void set_cfg_window(u32 cfg_offset, u32 off)
+{
+ write_pci_config_byte(0, 1, 0,
+ cfg_offset + offsetof(struct virtio_pci_cap, bar),
+ 0);
+ write_pci_config(0, 1, 0,
+ cfg_offset + offsetof(struct virtio_pci_cap, length),
+ 4);
+ write_pci_config(0, 1, 0,
+ cfg_offset + offsetof(struct virtio_pci_cap, offset),
+ off);
+}
+
+static void write_bar_via_cfg(u32 cfg_offset, u32 off, u32 val)
+{
+ /*
+ * We could set this up once, then leave it; nothing else in the *
+ * kernel should touch these registers. But if it went wrong, that
+ * would be a horrible bug to find.
+ */
+ set_cfg_window(cfg_offset, off);
+ write_pci_config(0, 1, 0,
+ cfg_offset + sizeof(struct virtio_pci_cap), val);
+}
+
+static void probe_pci_console(void)
+{
+ u8 cap, common_cap = 0, device_cap = 0;
+ /* Offset within BAR0 */
+ u32 device_offset;
+ u32 device_len;
+
+ /* Avoid recursive printk into here. */
+ console_cfg_offset = -1;
+
+ if (!early_pci_allowed()) {
+ printk(KERN_ERR "lguest: early PCI access not allowed!\n");
+ return;
+ }
+
+ /* We expect a console PCI device at BUS0, slot 1. */
+ if (read_pci_config(0, 1, 0, 0) != 0x10431AF4) {
+ printk(KERN_ERR "lguest: PCI device is %#x!\n",
+ read_pci_config(0, 1, 0, 0));
+ return;
+ }
+
+ /* Find the capabilities we need (must be in bar0) */
+ cap = read_pci_config_byte(0, 1, 0, PCI_CAPABILITY_LIST);
+ while (cap) {
+ u8 vndr = read_pci_config_byte(0, 1, 0, cap);
+ if (vndr == PCI_CAP_ID_VNDR) {
+ u8 type, bar;
+ u32 offset, length;
+
+ type = read_pci_config_byte(0, 1, 0,
+ cap + offsetof(struct virtio_pci_cap, cfg_type));
+ bar = read_pci_config_byte(0, 1, 0,
+ cap + offsetof(struct virtio_pci_cap, bar));
+ offset = read_pci_config(0, 1, 0,
+ cap + offsetof(struct virtio_pci_cap, offset));
+ length = read_pci_config(0, 1, 0,
+ cap + offsetof(struct virtio_pci_cap, length));
+
+ switch (type) {
+ case VIRTIO_PCI_CAP_DEVICE_CFG:
+ if (bar == 0) {
+ device_cap = cap;
+ device_offset = offset;
+ device_len = length;
+ }
+ break;
+ case VIRTIO_PCI_CAP_PCI_CFG:
+ console_access_cap = cap;
+ break;
+ }
+ }
+ cap = read_pci_config_byte(0, 1, 0, cap + PCI_CAP_LIST_NEXT);
+ }
+ if (!device_cap || !console_access_cap) {
+ printk(KERN_ERR "lguest: No caps (%u/%u/%u) in console!\n",
+ common_cap, device_cap, console_access_cap);
+ return;
+ }
+
+ /*
+ * Note that we can't check features, until we've set the DRIVER
+ * status bit. We don't want to do that until we have a real driver,
+ * so we just check that the device-specific config has room for
+ * emerg_wr. If it doesn't support VIRTIO_CONSOLE_F_EMERG_WRITE
+ * it should ignore the access.
+ */
+ if (device_len < (offsetof(struct virtio_console_config, emerg_wr)
+ + sizeof(u32))) {
+ printk(KERN_ERR "lguest: console missing emerg_wr field\n");
+ return;
+ }
+
+ console_cfg_offset = device_offset;
+ printk(KERN_INFO "lguest: Console via virtio-pci emerg_wr\n");
+}
+
/*
* We will eventually use the virtio console device to produce console output,
- * but before that is set up we use LHCALL_NOTIFY on normal memory to produce
- * console output.
+ * but before that is set up we use the virtio PCI console's backdoor mmio
+ * access and the "emergency" write facility (which is legal even before the
+ * device is configured).
*/
static __init int early_put_chars(u32 vtermno, const char *buf, int count)
{
- char scratch[17];
- unsigned int len = count;
+ /* If we couldn't find PCI console, forget it. */
+ if (console_cfg_offset < 0)
+ return count;
- /* We use a nul-terminated string, so we make a copy. Icky, huh? */
- if (len > sizeof(scratch) - 1)
- len = sizeof(scratch) - 1;
- scratch[len] = '\0';
- memcpy(scratch, buf, len);
- hcall(LHCALL_NOTIFY, __pa(scratch), 0, 0, 0);
+ if (unlikely(!console_cfg_offset)) {
+ probe_pci_console();
+ if (console_cfg_offset < 0)
+ return count;
+ }
- /* This routine returns the number of bytes actually written. */
- return len;
+ write_bar_via_cfg(console_access_cap,
+ console_cfg_offset
+ + offsetof(struct virtio_console_config, emerg_wr),
+ buf[0]);
+ return 1;
}
/*
@@ -1400,14 +1534,6 @@ __init void lguest_init(void)
atomic_notifier_chain_register(&panic_notifier_list, &paniced);
/*
- * The IDE code spends about 3 seconds probing for disks: if we reserve
- * all the I/O ports up front it can't get them and so doesn't probe.
- * Other device drivers are similar (but less severe). This cuts the
- * kernel boot time on my machine from 4.1 seconds to 0.45 seconds.
- */
- paravirt_disable_iospace();
-
- /*
* This is messy CPU setup stuff which the native boot code does before
* start_kernel, so we have to do, too:
*/
@@ -1436,6 +1562,13 @@ __init void lguest_init(void)
/* Register our very early console. */
virtio_cons_early_init(early_put_chars);
+ /* Don't let ACPI try to control our PCI interrupts. */
+ disable_acpi();
+
+ /* We control them ourselves, by overriding these two hooks. */
+ pcibios_enable_irq = lguest_enable_irq;
+ pcibios_disable_irq = lguest_disable_irq;
+
/*
* Last of all, we set the power management poweroff hook to point to
* the Guest routine to power off, and the reboot hook to our restart
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index 553c094b9cd7..a110efca6d06 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -238,6 +238,31 @@ static void __init_refok adjust_range_page_size_mask(struct map_range *mr,
}
}
+static const char *page_size_string(struct map_range *mr)
+{
+ static const char str_1g[] = "1G";
+ static const char str_2m[] = "2M";
+ static const char str_4m[] = "4M";
+ static const char str_4k[] = "4k";
+
+ if (mr->page_size_mask & (1<<PG_LEVEL_1G))
+ return str_1g;
+ /*
+ * 32-bit without PAE has a 4M large page size.
+ * PG_LEVEL_2M is misnamed, but we can at least
+ * print out the right size in the string.
+ */
+ if (IS_ENABLED(CONFIG_X86_32) &&
+ !IS_ENABLED(CONFIG_X86_PAE) &&
+ mr->page_size_mask & (1<<PG_LEVEL_2M))
+ return str_4m;
+
+ if (mr->page_size_mask & (1<<PG_LEVEL_2M))
+ return str_2m;
+
+ return str_4k;
+}
+
static int __meminit split_mem_range(struct map_range *mr, int nr_range,
unsigned long start,
unsigned long end)
@@ -333,8 +358,7 @@ static int __meminit split_mem_range(struct map_range *mr, int nr_range,
for (i = 0; i < nr_range; i++)
printk(KERN_DEBUG " [mem %#010lx-%#010lx] page %s\n",
mr[i].start, mr[i].end - 1,
- (mr[i].page_size_mask & (1<<PG_LEVEL_1G))?"1G":(
- (mr[i].page_size_mask & (1<<PG_LEVEL_2M))?"2M":"4k"));
+ page_size_string(&mr[i]));
return nr_range;
}
diff --git a/arch/x86/mm/mmap.c b/arch/x86/mm/mmap.c
index 919b91205cd4..df4552bd239e 100644
--- a/arch/x86/mm/mmap.c
+++ b/arch/x86/mm/mmap.c
@@ -35,12 +35,12 @@ struct va_alignment __read_mostly va_align = {
.flags = -1,
};
-static unsigned int stack_maxrandom_size(void)
+static unsigned long stack_maxrandom_size(void)
{
- unsigned int max = 0;
+ unsigned long max = 0;
if ((current->flags & PF_RANDOMIZE) &&
!(current->personality & ADDR_NO_RANDOMIZE)) {
- max = ((-1U) & STACK_RND_MASK) << PAGE_SHIFT;
+ max = ((-1UL) & STACK_RND_MASK) << PAGE_SHIFT;
}
return max;
diff --git a/arch/x86/platform/Makefile b/arch/x86/platform/Makefile
index 85afde1fa3e5..a62e0be3a2f1 100644
--- a/arch/x86/platform/Makefile
+++ b/arch/x86/platform/Makefile
@@ -5,6 +5,7 @@ obj-y += geode/
obj-y += goldfish/
obj-y += iris/
obj-y += intel-mid/
+obj-y += intel-quark/
obj-y += olpc/
obj-y += scx200/
obj-y += sfi/
diff --git a/arch/x86/platform/efi/efi_stub_64.S b/arch/x86/platform/efi/efi_stub_64.S
index 5fcda7272550..86d0f9e08dd9 100644
--- a/arch/x86/platform/efi/efi_stub_64.S
+++ b/arch/x86/platform/efi/efi_stub_64.S
@@ -91,167 +91,6 @@ ENTRY(efi_call)
ret
ENDPROC(efi_call)
-#ifdef CONFIG_EFI_MIXED
-
-/*
- * We run this function from the 1:1 mapping.
- *
- * This function must be invoked with a 1:1 mapped stack.
- */
-ENTRY(__efi64_thunk)
- movl %ds, %eax
- push %rax
- movl %es, %eax
- push %rax
- movl %ss, %eax
- push %rax
-
- subq $32, %rsp
- movl %esi, 0x0(%rsp)
- movl %edx, 0x4(%rsp)
- movl %ecx, 0x8(%rsp)
- movq %r8, %rsi
- movl %esi, 0xc(%rsp)
- movq %r9, %rsi
- movl %esi, 0x10(%rsp)
-
- sgdt save_gdt(%rip)
-
- leaq 1f(%rip), %rbx
- movq %rbx, func_rt_ptr(%rip)
-
- /* Switch to gdt with 32-bit segments */
- movl 64(%rsp), %eax
- lgdt (%rax)
-
- leaq efi_enter32(%rip), %rax
- pushq $__KERNEL_CS
- pushq %rax
- lretq
-
-1: addq $32, %rsp
-
- lgdt save_gdt(%rip)
-
- pop %rbx
- movl %ebx, %ss
- pop %rbx
- movl %ebx, %es
- pop %rbx
- movl %ebx, %ds
-
- /*
- * Convert 32-bit status code into 64-bit.
- */
- test %rax, %rax
- jz 1f
- movl %eax, %ecx
- andl $0x0fffffff, %ecx
- andl $0xf0000000, %eax
- shl $32, %rax
- or %rcx, %rax
-1:
- ret
-ENDPROC(__efi64_thunk)
-
-ENTRY(efi_exit32)
- movq func_rt_ptr(%rip), %rax
- push %rax
- mov %rdi, %rax
- ret
-ENDPROC(efi_exit32)
-
- .code32
-/*
- * EFI service pointer must be in %edi.
- *
- * The stack should represent the 32-bit calling convention.
- */
-ENTRY(efi_enter32)
- movl $__KERNEL_DS, %eax
- movl %eax, %ds
- movl %eax, %es
- movl %eax, %ss
-
- /* Reload pgtables */
- movl %cr3, %eax
- movl %eax, %cr3
-
- /* Disable paging */
- movl %cr0, %eax
- btrl $X86_CR0_PG_BIT, %eax
- movl %eax, %cr0
-
- /* Disable long mode via EFER */
- movl $MSR_EFER, %ecx
- rdmsr
- btrl $_EFER_LME, %eax
- wrmsr
-
- call *%edi
-
- /* We must preserve return value */
- movl %eax, %edi
-
- /*
- * Some firmware will return with interrupts enabled. Be sure to
- * disable them before we switch GDTs.
- */
- cli
-
- movl 68(%esp), %eax
- movl %eax, 2(%eax)
- lgdtl (%eax)
-
- movl %cr4, %eax
- btsl $(X86_CR4_PAE_BIT), %eax
- movl %eax, %cr4
-
- movl %cr3, %eax
- movl %eax, %cr3
-
- movl $MSR_EFER, %ecx
- rdmsr
- btsl $_EFER_LME, %eax
- wrmsr
-
- xorl %eax, %eax
- lldt %ax
-
- movl 72(%esp), %eax
- pushl $__KERNEL_CS
- pushl %eax
-
- /* Enable paging */
- movl %cr0, %eax
- btsl $X86_CR0_PG_BIT, %eax
- movl %eax, %cr0
- lret
-ENDPROC(efi_enter32)
-
- .data
- .balign 8
- .global efi32_boot_gdt
-efi32_boot_gdt: .word 0
- .quad 0
-
-save_gdt: .word 0
- .quad 0
-func_rt_ptr: .quad 0
-
- .global efi_gdt64
-efi_gdt64:
- .word efi_gdt64_end - efi_gdt64
- .long 0 /* Filled out by user */
- .word 0
- .quad 0x0000000000000000 /* NULL descriptor */
- .quad 0x00af9a000000ffff /* __KERNEL_CS */
- .quad 0x00cf92000000ffff /* __KERNEL_DS */
- .quad 0x0080890000000000 /* TS descriptor */
- .quad 0x0000000000000000 /* TS continued */
-efi_gdt64_end:
-#endif /* CONFIG_EFI_MIXED */
-
.data
ENTRY(efi_scratch)
.fill 3,8,0
diff --git a/arch/x86/platform/efi/efi_thunk_64.S b/arch/x86/platform/efi/efi_thunk_64.S
index 8806fa73e6e6..ff85d28c50f2 100644
--- a/arch/x86/platform/efi/efi_thunk_64.S
+++ b/arch/x86/platform/efi/efi_thunk_64.S
@@ -1,9 +1,26 @@
/*
* Copyright (C) 2014 Intel Corporation; author Matt Fleming
+ *
+ * Support for invoking 32-bit EFI runtime services from a 64-bit
+ * kernel.
+ *
+ * The below thunking functions are only used after ExitBootServices()
+ * has been called. This simplifies things considerably as compared with
+ * the early EFI thunking because we can leave all the kernel state
+ * intact (GDT, IDT, etc) and simply invoke the the 32-bit EFI runtime
+ * services from __KERNEL32_CS. This means we can continue to service
+ * interrupts across an EFI mixed mode call.
+ *
+ * We do however, need to handle the fact that we're running in a full
+ * 64-bit virtual address space. Things like the stack and instruction
+ * addresses need to be accessible by the 32-bit firmware, so we rely on
+ * using the identity mappings in the EFI page table to access the stack
+ * and kernel text (see efi_setup_page_tables()).
*/
#include <linux/linkage.h>
#include <asm/page_types.h>
+#include <asm/segment.h>
.text
.code64
@@ -33,14 +50,6 @@ ENTRY(efi64_thunk)
leaq efi_exit32(%rip), %rbx
subq %rax, %rbx
movl %ebx, 8(%rsp)
- leaq efi_gdt64(%rip), %rbx
- subq %rax, %rbx
- movl %ebx, 2(%ebx)
- movl %ebx, 4(%rsp)
- leaq efi_gdt32(%rip), %rbx
- subq %rax, %rbx
- movl %ebx, 2(%ebx)
- movl %ebx, (%rsp)
leaq __efi64_thunk(%rip), %rbx
subq %rax, %rbx
@@ -52,14 +61,92 @@ ENTRY(efi64_thunk)
retq
ENDPROC(efi64_thunk)
- .data
-efi_gdt32:
- .word efi_gdt32_end - efi_gdt32
- .long 0 /* Filled out above */
- .word 0
- .quad 0x0000000000000000 /* NULL descriptor */
- .quad 0x00cf9a000000ffff /* __KERNEL_CS */
- .quad 0x00cf93000000ffff /* __KERNEL_DS */
-efi_gdt32_end:
+/*
+ * We run this function from the 1:1 mapping.
+ *
+ * This function must be invoked with a 1:1 mapped stack.
+ */
+ENTRY(__efi64_thunk)
+ movl %ds, %eax
+ push %rax
+ movl %es, %eax
+ push %rax
+ movl %ss, %eax
+ push %rax
+
+ subq $32, %rsp
+ movl %esi, 0x0(%rsp)
+ movl %edx, 0x4(%rsp)
+ movl %ecx, 0x8(%rsp)
+ movq %r8, %rsi
+ movl %esi, 0xc(%rsp)
+ movq %r9, %rsi
+ movl %esi, 0x10(%rsp)
+
+ leaq 1f(%rip), %rbx
+ movq %rbx, func_rt_ptr(%rip)
+
+ /* Switch to 32-bit descriptor */
+ pushq $__KERNEL32_CS
+ leaq efi_enter32(%rip), %rax
+ pushq %rax
+ lretq
+
+1: addq $32, %rsp
+
+ pop %rbx
+ movl %ebx, %ss
+ pop %rbx
+ movl %ebx, %es
+ pop %rbx
+ movl %ebx, %ds
+ /*
+ * Convert 32-bit status code into 64-bit.
+ */
+ test %rax, %rax
+ jz 1f
+ movl %eax, %ecx
+ andl $0x0fffffff, %ecx
+ andl $0xf0000000, %eax
+ shl $32, %rax
+ or %rcx, %rax
+1:
+ ret
+ENDPROC(__efi64_thunk)
+
+ENTRY(efi_exit32)
+ movq func_rt_ptr(%rip), %rax
+ push %rax
+ mov %rdi, %rax
+ ret
+ENDPROC(efi_exit32)
+
+ .code32
+/*
+ * EFI service pointer must be in %edi.
+ *
+ * The stack should represent the 32-bit calling convention.
+ */
+ENTRY(efi_enter32)
+ movl $__KERNEL_DS, %eax
+ movl %eax, %ds
+ movl %eax, %es
+ movl %eax, %ss
+
+ call *%edi
+
+ /* We must preserve return value */
+ movl %eax, %edi
+
+ movl 72(%esp), %eax
+ pushl $__KERNEL_CS
+ pushl %eax
+
+ lret
+ENDPROC(efi_enter32)
+
+ .data
+ .balign 8
+func_rt_ptr: .quad 0
efi_saved_sp: .quad 0
diff --git a/arch/x86/platform/intel-mid/intel-mid.c b/arch/x86/platform/intel-mid/intel-mid.c
index 1bbedc4b0f88..3005f0c89f2e 100644
--- a/arch/x86/platform/intel-mid/intel-mid.c
+++ b/arch/x86/platform/intel-mid/intel-mid.c
@@ -130,7 +130,7 @@ static void intel_mid_arch_setup(void)
intel_mid_ops = get_intel_mid_ops[__intel_mid_cpu_chip]();
else {
intel_mid_ops = get_intel_mid_ops[INTEL_MID_CPU_CHIP_PENWELL]();
- pr_info("ARCH: Uknown SoC, assuming PENWELL!\n");
+ pr_info("ARCH: Unknown SoC, assuming PENWELL!\n");
}
out:
diff --git a/arch/x86/platform/intel-quark/Makefile b/arch/x86/platform/intel-quark/Makefile
new file mode 100644
index 000000000000..9cc57ed36022
--- /dev/null
+++ b/arch/x86/platform/intel-quark/Makefile
@@ -0,0 +1,2 @@
+obj-$(CONFIG_INTEL_IMR) += imr.o
+obj-$(CONFIG_DEBUG_IMR_SELFTEST) += imr_selftest.o
diff --git a/arch/x86/platform/intel-quark/imr.c b/arch/x86/platform/intel-quark/imr.c
new file mode 100644
index 000000000000..0ee619f9fcb7
--- /dev/null
+++ b/arch/x86/platform/intel-quark/imr.c
@@ -0,0 +1,661 @@
+/**
+ * imr.c
+ *
+ * Copyright(c) 2013 Intel Corporation.
+ * Copyright(c) 2015 Bryan O'Donoghue <pure.logic@nexus-software.ie>
+ *
+ * IMR registers define an isolated region of memory that can
+ * be masked to prohibit certain system agents from accessing memory.
+ * When a device behind a masked port performs an access - snooped or
+ * not, an IMR may optionally prevent that transaction from changing
+ * the state of memory or from getting correct data in response to the
+ * operation.
+ *
+ * Write data will be dropped and reads will return 0xFFFFFFFF, the
+ * system will reset and system BIOS will print out an error message to
+ * inform the user that an IMR has been violated.
+ *
+ * This code is based on the Linux MTRR code and reference code from
+ * Intel's Quark BSP EFI, Linux and grub code.
+ *
+ * See quark-x1000-datasheet.pdf for register definitions.
+ * http://www.intel.com/content/dam/www/public/us/en/documents/datasheets/quark-x1000-datasheet.pdf
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <asm-generic/sections.h>
+#include <asm/cpu_device_id.h>
+#include <asm/imr.h>
+#include <asm/iosf_mbi.h>
+#include <linux/debugfs.h>
+#include <linux/init.h>
+#include <linux/mm.h>
+#include <linux/module.h>
+#include <linux/types.h>
+
+struct imr_device {
+ struct dentry *file;
+ bool init;
+ struct mutex lock;
+ int max_imr;
+ int reg_base;
+};
+
+static struct imr_device imr_dev;
+
+/*
+ * IMR read/write mask control registers.
+ * See quark-x1000-datasheet.pdf sections 12.7.4.5 and 12.7.4.6 for
+ * bit definitions.
+ *
+ * addr_hi
+ * 31 Lock bit
+ * 30:24 Reserved
+ * 23:2 1 KiB aligned lo address
+ * 1:0 Reserved
+ *
+ * addr_hi
+ * 31:24 Reserved
+ * 23:2 1 KiB aligned hi address
+ * 1:0 Reserved
+ */
+#define IMR_LOCK BIT(31)
+
+struct imr_regs {
+ u32 addr_lo;
+ u32 addr_hi;
+ u32 rmask;
+ u32 wmask;
+};
+
+#define IMR_NUM_REGS (sizeof(struct imr_regs)/sizeof(u32))
+#define IMR_SHIFT 8
+#define imr_to_phys(x) ((x) << IMR_SHIFT)
+#define phys_to_imr(x) ((x) >> IMR_SHIFT)
+
+/**
+ * imr_is_enabled - true if an IMR is enabled false otherwise.
+ *
+ * Determines if an IMR is enabled based on address range and read/write
+ * mask. An IMR set with an address range set to zero and a read/write
+ * access mask set to all is considered to be disabled. An IMR in any
+ * other state - for example set to zero but without read/write access
+ * all is considered to be enabled. This definition of disabled is how
+ * firmware switches off an IMR and is maintained in kernel for
+ * consistency.
+ *
+ * @imr: pointer to IMR descriptor.
+ * @return: true if IMR enabled false if disabled.
+ */
+static inline int imr_is_enabled(struct imr_regs *imr)
+{
+ return !(imr->rmask == IMR_READ_ACCESS_ALL &&
+ imr->wmask == IMR_WRITE_ACCESS_ALL &&
+ imr_to_phys(imr->addr_lo) == 0 &&
+ imr_to_phys(imr->addr_hi) == 0);
+}
+
+/**
+ * imr_read - read an IMR at a given index.
+ *
+ * Requires caller to hold imr mutex.
+ *
+ * @idev: pointer to imr_device structure.
+ * @imr_id: IMR entry to read.
+ * @imr: IMR structure representing address and access masks.
+ * @return: 0 on success or error code passed from mbi_iosf on failure.
+ */
+static int imr_read(struct imr_device *idev, u32 imr_id, struct imr_regs *imr)
+{
+ u32 reg = imr_id * IMR_NUM_REGS + idev->reg_base;
+ int ret;
+
+ ret = iosf_mbi_read(QRK_MBI_UNIT_MM, QRK_MBI_MM_READ,
+ reg++, &imr->addr_lo);
+ if (ret)
+ return ret;
+
+ ret = iosf_mbi_read(QRK_MBI_UNIT_MM, QRK_MBI_MM_READ,
+ reg++, &imr->addr_hi);
+ if (ret)
+ return ret;
+
+ ret = iosf_mbi_read(QRK_MBI_UNIT_MM, QRK_MBI_MM_READ,
+ reg++, &imr->rmask);
+ if (ret)
+ return ret;
+
+ return iosf_mbi_read(QRK_MBI_UNIT_MM, QRK_MBI_MM_READ,
+ reg++, &imr->wmask);
+}
+
+/**
+ * imr_write - write an IMR at a given index.
+ *
+ * Requires caller to hold imr mutex.
+ * Note lock bits need to be written independently of address bits.
+ *
+ * @idev: pointer to imr_device structure.
+ * @imr_id: IMR entry to write.
+ * @imr: IMR structure representing address and access masks.
+ * @lock: indicates if the IMR lock bit should be applied.
+ * @return: 0 on success or error code passed from mbi_iosf on failure.
+ */
+static int imr_write(struct imr_device *idev, u32 imr_id,
+ struct imr_regs *imr, bool lock)
+{
+ unsigned long flags;
+ u32 reg = imr_id * IMR_NUM_REGS + idev->reg_base;
+ int ret;
+
+ local_irq_save(flags);
+
+ ret = iosf_mbi_write(QRK_MBI_UNIT_MM, QRK_MBI_MM_WRITE, reg++,
+ imr->addr_lo);
+ if (ret)
+ goto failed;
+
+ ret = iosf_mbi_write(QRK_MBI_UNIT_MM, QRK_MBI_MM_WRITE,
+ reg++, imr->addr_hi);
+ if (ret)
+ goto failed;
+
+ ret = iosf_mbi_write(QRK_MBI_UNIT_MM, QRK_MBI_MM_WRITE,
+ reg++, imr->rmask);
+ if (ret)
+ goto failed;
+
+ ret = iosf_mbi_write(QRK_MBI_UNIT_MM, QRK_MBI_MM_WRITE,
+ reg++, imr->wmask);
+ if (ret)
+ goto failed;
+
+ /* Lock bit must be set separately to addr_lo address bits. */
+ if (lock) {
+ imr->addr_lo |= IMR_LOCK;
+ ret = iosf_mbi_write(QRK_MBI_UNIT_MM, QRK_MBI_MM_WRITE,
+ reg - IMR_NUM_REGS, imr->addr_lo);
+ if (ret)
+ goto failed;
+ }
+
+ local_irq_restore(flags);
+ return 0;
+failed:
+ /*
+ * If writing to the IOSF failed then we're in an unknown state,
+ * likely a very bad state. An IMR in an invalid state will almost
+ * certainly lead to a memory access violation.
+ */
+ local_irq_restore(flags);
+ WARN(ret, "IOSF-MBI write fail range 0x%08x-0x%08x unreliable\n",
+ imr_to_phys(imr->addr_lo), imr_to_phys(imr->addr_hi) + IMR_MASK);
+
+ return ret;
+}
+
+/**
+ * imr_dbgfs_state_show - print state of IMR registers.
+ *
+ * @s: pointer to seq_file for output.
+ * @unused: unused parameter.
+ * @return: 0 on success or error code passed from mbi_iosf on failure.
+ */
+static int imr_dbgfs_state_show(struct seq_file *s, void *unused)
+{
+ phys_addr_t base;
+ phys_addr_t end;
+ int i;
+ struct imr_device *idev = s->private;
+ struct imr_regs imr;
+ size_t size;
+ int ret = -ENODEV;
+
+ mutex_lock(&idev->lock);
+
+ for (i = 0; i < idev->max_imr; i++) {
+
+ ret = imr_read(idev, i, &imr);
+ if (ret)
+ break;
+
+ /*
+ * Remember to add IMR_ALIGN bytes to size to indicate the
+ * inherent IMR_ALIGN size bytes contained in the masked away
+ * lower ten bits.
+ */
+ if (imr_is_enabled(&imr)) {
+ base = imr_to_phys(imr.addr_lo);
+ end = imr_to_phys(imr.addr_hi) + IMR_MASK;
+ } else {
+ base = 0;
+ end = 0;
+ }
+ size = end - base;
+ seq_printf(s, "imr%02i: base=%pa, end=%pa, size=0x%08zx "
+ "rmask=0x%08x, wmask=0x%08x, %s, %s\n", i,
+ &base, &end, size, imr.rmask, imr.wmask,
+ imr_is_enabled(&imr) ? "enabled " : "disabled",
+ imr.addr_lo & IMR_LOCK ? "locked" : "unlocked");
+ }
+
+ mutex_unlock(&idev->lock);
+ return ret;
+}
+
+/**
+ * imr_state_open - debugfs open callback.
+ *
+ * @inode: pointer to struct inode.
+ * @file: pointer to struct file.
+ * @return: result of single open.
+ */
+static int imr_state_open(struct inode *inode, struct file *file)
+{
+ return single_open(file, imr_dbgfs_state_show, inode->i_private);
+}
+
+static const struct file_operations imr_state_ops = {
+ .open = imr_state_open,
+ .read = seq_read,
+ .llseek = seq_lseek,
+ .release = single_release,
+};
+
+/**
+ * imr_debugfs_register - register debugfs hooks.
+ *
+ * @idev: pointer to imr_device structure.
+ * @return: 0 on success - errno on failure.
+ */
+static int imr_debugfs_register(struct imr_device *idev)
+{
+ idev->file = debugfs_create_file("imr_state", S_IFREG | S_IRUGO, NULL,
+ idev, &imr_state_ops);
+ return PTR_ERR_OR_ZERO(idev->file);
+}
+
+/**
+ * imr_debugfs_unregister - unregister debugfs hooks.
+ *
+ * @idev: pointer to imr_device structure.
+ * @return:
+ */
+static void imr_debugfs_unregister(struct imr_device *idev)
+{
+ debugfs_remove(idev->file);
+}
+
+/**
+ * imr_check_params - check passed address range IMR alignment and non-zero size
+ *
+ * @base: base address of intended IMR.
+ * @size: size of intended IMR.
+ * @return: zero on valid range -EINVAL on unaligned base/size.
+ */
+static int imr_check_params(phys_addr_t base, size_t size)
+{
+ if ((base & IMR_MASK) || (size & IMR_MASK)) {
+ pr_err("base %pa size 0x%08zx must align to 1KiB\n",
+ &base, size);
+ return -EINVAL;
+ }
+ if (size == 0)
+ return -EINVAL;
+
+ return 0;
+}
+
+/**
+ * imr_raw_size - account for the IMR_ALIGN bytes that addr_hi appends.
+ *
+ * IMR addr_hi has a built in offset of plus IMR_ALIGN (0x400) bytes from the
+ * value in the register. We need to subtract IMR_ALIGN bytes from input sizes
+ * as a result.
+ *
+ * @size: input size bytes.
+ * @return: reduced size.
+ */
+static inline size_t imr_raw_size(size_t size)
+{
+ return size - IMR_ALIGN;
+}
+
+/**
+ * imr_address_overlap - detects an address overlap.
+ *
+ * @addr: address to check against an existing IMR.
+ * @imr: imr being checked.
+ * @return: true for overlap false for no overlap.
+ */
+static inline int imr_address_overlap(phys_addr_t addr, struct imr_regs *imr)
+{
+ return addr >= imr_to_phys(imr->addr_lo) && addr <= imr_to_phys(imr->addr_hi);
+}
+
+/**
+ * imr_add_range - add an Isolated Memory Region.
+ *
+ * @base: physical base address of region aligned to 1KiB.
+ * @size: physical size of region in bytes must be aligned to 1KiB.
+ * @read_mask: read access mask.
+ * @write_mask: write access mask.
+ * @lock: indicates whether or not to permanently lock this region.
+ * @return: zero on success or negative value indicating error.
+ */
+int imr_add_range(phys_addr_t base, size_t size,
+ unsigned int rmask, unsigned int wmask, bool lock)
+{
+ phys_addr_t end;
+ unsigned int i;
+ struct imr_device *idev = &imr_dev;
+ struct imr_regs imr;
+ size_t raw_size;
+ int reg;
+ int ret;
+
+ if (WARN_ONCE(idev->init == false, "driver not initialized"))
+ return -ENODEV;
+
+ ret = imr_check_params(base, size);
+ if (ret)
+ return ret;
+
+ /* Tweak the size value. */
+ raw_size = imr_raw_size(size);
+ end = base + raw_size;
+
+ /*
+ * Check for reserved IMR value common to firmware, kernel and grub
+ * indicating a disabled IMR.
+ */
+ imr.addr_lo = phys_to_imr(base);
+ imr.addr_hi = phys_to_imr(end);
+ imr.rmask = rmask;
+ imr.wmask = wmask;
+ if (!imr_is_enabled(&imr))
+ return -ENOTSUPP;
+
+ mutex_lock(&idev->lock);
+
+ /*
+ * Find a free IMR while checking for an existing overlapping range.
+ * Note there's no restriction in silicon to prevent IMR overlaps.
+ * For the sake of simplicity and ease in defining/debugging an IMR
+ * memory map we exclude IMR overlaps.
+ */
+ reg = -1;
+ for (i = 0; i < idev->max_imr; i++) {
+ ret = imr_read(idev, i, &imr);
+ if (ret)
+ goto failed;
+
+ /* Find overlap @ base or end of requested range. */
+ ret = -EINVAL;
+ if (imr_is_enabled(&imr)) {
+ if (imr_address_overlap(base, &imr))
+ goto failed;
+ if (imr_address_overlap(end, &imr))
+ goto failed;
+ } else {
+ reg = i;
+ }
+ }
+
+ /* Error out if we have no free IMR entries. */
+ if (reg == -1) {
+ ret = -ENOMEM;
+ goto failed;
+ }
+
+ pr_debug("add %d phys %pa-%pa size %zx mask 0x%08x wmask 0x%08x\n",
+ reg, &base, &end, raw_size, rmask, wmask);
+
+ /* Enable IMR at specified range and access mask. */
+ imr.addr_lo = phys_to_imr(base);
+ imr.addr_hi = phys_to_imr(end);
+ imr.rmask = rmask;
+ imr.wmask = wmask;
+
+ ret = imr_write(idev, reg, &imr, lock);
+ if (ret < 0) {
+ /*
+ * In the highly unlikely event iosf_mbi_write failed
+ * attempt to rollback the IMR setup skipping the trapping
+ * of further IOSF write failures.
+ */
+ imr.addr_lo = 0;
+ imr.addr_hi = 0;
+ imr.rmask = IMR_READ_ACCESS_ALL;
+ imr.wmask = IMR_WRITE_ACCESS_ALL;
+ imr_write(idev, reg, &imr, false);
+ }
+failed:
+ mutex_unlock(&idev->lock);
+ return ret;
+}
+EXPORT_SYMBOL_GPL(imr_add_range);
+
+/**
+ * __imr_remove_range - delete an Isolated Memory Region.
+ *
+ * This function allows you to delete an IMR by its index specified by reg or
+ * by address range specified by base and size respectively. If you specify an
+ * index on its own the base and size parameters are ignored.
+ * imr_remove_range(0, base, size); delete IMR at index 0 base/size ignored.
+ * imr_remove_range(-1, base, size); delete IMR from base to base+size.
+ *
+ * @reg: imr index to remove.
+ * @base: physical base address of region aligned to 1 KiB.
+ * @size: physical size of region in bytes aligned to 1 KiB.
+ * @return: -EINVAL on invalid range or out or range id
+ * -ENODEV if reg is valid but no IMR exists or is locked
+ * 0 on success.
+ */
+static int __imr_remove_range(int reg, phys_addr_t base, size_t size)
+{
+ phys_addr_t end;
+ bool found = false;
+ unsigned int i;
+ struct imr_device *idev = &imr_dev;
+ struct imr_regs imr;
+ size_t raw_size;
+ int ret = 0;
+
+ if (WARN_ONCE(idev->init == false, "driver not initialized"))
+ return -ENODEV;
+
+ /*
+ * Validate address range if deleting by address, else we are
+ * deleting by index where base and size will be ignored.
+ */
+ if (reg == -1) {
+ ret = imr_check_params(base, size);
+ if (ret)
+ return ret;
+ }
+
+ /* Tweak the size value. */
+ raw_size = imr_raw_size(size);
+ end = base + raw_size;
+
+ mutex_lock(&idev->lock);
+
+ if (reg >= 0) {
+ /* If a specific IMR is given try to use it. */
+ ret = imr_read(idev, reg, &imr);
+ if (ret)
+ goto failed;
+
+ if (!imr_is_enabled(&imr) || imr.addr_lo & IMR_LOCK) {
+ ret = -ENODEV;
+ goto failed;
+ }
+ found = true;
+ } else {
+ /* Search for match based on address range. */
+ for (i = 0; i < idev->max_imr; i++) {
+ ret = imr_read(idev, i, &imr);
+ if (ret)
+ goto failed;
+
+ if (!imr_is_enabled(&imr) || imr.addr_lo & IMR_LOCK)
+ continue;
+
+ if ((imr_to_phys(imr.addr_lo) == base) &&
+ (imr_to_phys(imr.addr_hi) == end)) {
+ found = true;
+ reg = i;
+ break;
+ }
+ }
+ }
+
+ if (!found) {
+ ret = -ENODEV;
+ goto failed;
+ }
+
+ pr_debug("remove %d phys %pa-%pa size %zx\n", reg, &base, &end, raw_size);
+
+ /* Tear down the IMR. */
+ imr.addr_lo = 0;
+ imr.addr_hi = 0;
+ imr.rmask = IMR_READ_ACCESS_ALL;
+ imr.wmask = IMR_WRITE_ACCESS_ALL;
+
+ ret = imr_write(idev, reg, &imr, false);
+
+failed:
+ mutex_unlock(&idev->lock);
+ return ret;
+}
+
+/**
+ * imr_remove_range - delete an Isolated Memory Region by address
+ *
+ * This function allows you to delete an IMR by an address range specified
+ * by base and size respectively.
+ * imr_remove_range(base, size); delete IMR from base to base+size.
+ *
+ * @base: physical base address of region aligned to 1 KiB.
+ * @size: physical size of region in bytes aligned to 1 KiB.
+ * @return: -EINVAL on invalid range or out or range id
+ * -ENODEV if reg is valid but no IMR exists or is locked
+ * 0 on success.
+ */
+int imr_remove_range(phys_addr_t base, size_t size)
+{
+ return __imr_remove_range(-1, base, size);
+}
+EXPORT_SYMBOL_GPL(imr_remove_range);
+
+/**
+ * imr_clear - delete an Isolated Memory Region by index
+ *
+ * This function allows you to delete an IMR by an address range specified
+ * by the index of the IMR. Useful for initial sanitization of the IMR
+ * address map.
+ * imr_ge(base, size); delete IMR from base to base+size.
+ *
+ * @reg: imr index to remove.
+ * @return: -EINVAL on invalid range or out or range id
+ * -ENODEV if reg is valid but no IMR exists or is locked
+ * 0 on success.
+ */
+static inline int imr_clear(int reg)
+{
+ return __imr_remove_range(reg, 0, 0);
+}
+
+/**
+ * imr_fixup_memmap - Tear down IMRs used during bootup.
+ *
+ * BIOS and Grub both setup IMRs around compressed kernel, initrd memory
+ * that need to be removed before the kernel hands out one of the IMR
+ * encased addresses to a downstream DMA agent such as the SD or Ethernet.
+ * IMRs on Galileo are setup to immediately reset the system on violation.
+ * As a result if you're running a root filesystem from SD - you'll need
+ * the boot-time IMRs torn down or you'll find seemingly random resets when
+ * using your filesystem.
+ *
+ * @idev: pointer to imr_device structure.
+ * @return:
+ */
+static void __init imr_fixup_memmap(struct imr_device *idev)
+{
+ phys_addr_t base = virt_to_phys(&_text);
+ size_t size = virt_to_phys(&__end_rodata) - base;
+ int i;
+ int ret;
+
+ /* Tear down all existing unlocked IMRs. */
+ for (i = 0; i < idev->max_imr; i++)
+ imr_clear(i);
+
+ /*
+ * Setup a locked IMR around the physical extent of the kernel
+ * from the beginning of the .text secton to the end of the
+ * .rodata section as one physically contiguous block.
+ */
+ ret = imr_add_range(base, size, IMR_CPU, IMR_CPU, true);
+ if (ret < 0) {
+ pr_err("unable to setup IMR for kernel: (%p - %p)\n",
+ &_text, &__end_rodata);
+ } else {
+ pr_info("protecting kernel .text - .rodata: %zu KiB (%p - %p)\n",
+ size / 1024, &_text, &__end_rodata);
+ }
+
+}
+
+static const struct x86_cpu_id imr_ids[] __initconst = {
+ { X86_VENDOR_INTEL, 5, 9 }, /* Intel Quark SoC X1000. */
+ {}
+};
+MODULE_DEVICE_TABLE(x86cpu, imr_ids);
+
+/**
+ * imr_init - entry point for IMR driver.
+ *
+ * return: -ENODEV for no IMR support 0 if good to go.
+ */
+static int __init imr_init(void)
+{
+ struct imr_device *idev = &imr_dev;
+ int ret;
+
+ if (!x86_match_cpu(imr_ids) || !iosf_mbi_available())
+ return -ENODEV;
+
+ idev->max_imr = QUARK_X1000_IMR_MAX;
+ idev->reg_base = QUARK_X1000_IMR_REGBASE;
+ idev->init = true;
+
+ mutex_init(&idev->lock);
+ ret = imr_debugfs_register(idev);
+ if (ret != 0)
+ pr_warn("debugfs register failed!\n");
+ imr_fixup_memmap(idev);
+ return 0;
+}
+
+/**
+ * imr_exit - exit point for IMR code.
+ *
+ * Deregisters debugfs, leave IMR state as-is.
+ *
+ * return:
+ */
+static void __exit imr_exit(void)
+{
+ imr_debugfs_unregister(&imr_dev);
+}
+
+module_init(imr_init);
+module_exit(imr_exit);
+
+MODULE_AUTHOR("Bryan O'Donoghue <pure.logic@nexus-software.ie>");
+MODULE_DESCRIPTION("Intel Isolated Memory Region driver");
+MODULE_LICENSE("Dual BSD/GPL");
diff --git a/arch/x86/platform/intel-quark/imr_selftest.c b/arch/x86/platform/intel-quark/imr_selftest.c
new file mode 100644
index 000000000000..c9a0838890e2
--- /dev/null
+++ b/arch/x86/platform/intel-quark/imr_selftest.c
@@ -0,0 +1,129 @@
+/**
+ * imr_selftest.c
+ *
+ * Copyright(c) 2013 Intel Corporation.
+ * Copyright(c) 2015 Bryan O'Donoghue <pure.logic@nexus-software.ie>
+ *
+ * IMR self test. The purpose of this module is to run a set of tests on the
+ * IMR API to validate it's sanity. We check for overlapping, reserved
+ * addresses and setup/teardown sanity.
+ *
+ */
+
+#include <asm-generic/sections.h>
+#include <asm/imr.h>
+#include <linux/init.h>
+#include <linux/mm.h>
+#include <linux/module.h>
+#include <linux/types.h>
+
+#define SELFTEST KBUILD_MODNAME ": "
+/**
+ * imr_self_test_result - Print result string for self test.
+ *
+ * @res: result code - true if test passed false otherwise.
+ * @fmt: format string.
+ * ... variadic argument list.
+ */
+static void __init imr_self_test_result(int res, const char *fmt, ...)
+{
+ va_list vlist;
+
+ /* Print pass/fail. */
+ if (res)
+ pr_info(SELFTEST "pass ");
+ else
+ pr_info(SELFTEST "fail ");
+
+ /* Print variable string. */
+ va_start(vlist, fmt);
+ vprintk(fmt, vlist);
+ va_end(vlist);
+
+ /* Optional warning. */
+ WARN(res == 0, "test failed");
+}
+#undef SELFTEST
+
+/**
+ * imr_self_test
+ *
+ * Verify IMR self_test with some simple tests to verify overlap,
+ * zero sized allocations and 1 KiB sized areas.
+ *
+ */
+static void __init imr_self_test(void)
+{
+ phys_addr_t base = virt_to_phys(&_text);
+ size_t size = virt_to_phys(&__end_rodata) - base;
+ const char *fmt_over = "overlapped IMR @ (0x%08lx - 0x%08lx)\n";
+ int ret;
+
+ /* Test zero zero. */
+ ret = imr_add_range(0, 0, 0, 0, false);
+ imr_self_test_result(ret < 0, "zero sized IMR\n");
+
+ /* Test exact overlap. */
+ ret = imr_add_range(base, size, IMR_CPU, IMR_CPU, false);
+ imr_self_test_result(ret < 0, fmt_over, __va(base), __va(base + size));
+
+ /* Test overlap with base inside of existing. */
+ base += size - IMR_ALIGN;
+ ret = imr_add_range(base, size, IMR_CPU, IMR_CPU, false);
+ imr_self_test_result(ret < 0, fmt_over, __va(base), __va(base + size));
+
+ /* Test overlap with end inside of existing. */
+ base -= size + IMR_ALIGN * 2;
+ ret = imr_add_range(base, size, IMR_CPU, IMR_CPU, false);
+ imr_self_test_result(ret < 0, fmt_over, __va(base), __va(base + size));
+
+ /* Test that a 1 KiB IMR @ zero with read/write all will bomb out. */
+ ret = imr_add_range(0, IMR_ALIGN, IMR_READ_ACCESS_ALL,
+ IMR_WRITE_ACCESS_ALL, false);
+ imr_self_test_result(ret < 0, "1KiB IMR @ 0x00000000 - access-all\n");
+
+ /* Test that a 1 KiB IMR @ zero with CPU only will work. */
+ ret = imr_add_range(0, IMR_ALIGN, IMR_CPU, IMR_CPU, false);
+ imr_self_test_result(ret >= 0, "1KiB IMR @ 0x00000000 - cpu-access\n");
+ if (ret >= 0) {
+ ret = imr_remove_range(0, IMR_ALIGN);
+ imr_self_test_result(ret == 0, "teardown - cpu-access\n");
+ }
+
+ /* Test 2 KiB works. */
+ size = IMR_ALIGN * 2;
+ ret = imr_add_range(0, size, IMR_READ_ACCESS_ALL,
+ IMR_WRITE_ACCESS_ALL, false);
+ imr_self_test_result(ret >= 0, "2KiB IMR @ 0x00000000\n");
+ if (ret >= 0) {
+ ret = imr_remove_range(0, size);
+ imr_self_test_result(ret == 0, "teardown 2KiB\n");
+ }
+}
+
+/**
+ * imr_self_test_init - entry point for IMR driver.
+ *
+ * return: -ENODEV for no IMR support 0 if good to go.
+ */
+static int __init imr_self_test_init(void)
+{
+ imr_self_test();
+ return 0;
+}
+
+/**
+ * imr_self_test_exit - exit point for IMR code.
+ *
+ * return:
+ */
+static void __exit imr_self_test_exit(void)
+{
+}
+
+module_init(imr_self_test_init);
+module_exit(imr_self_test_exit);
+
+MODULE_AUTHOR("Bryan O'Donoghue <pure.logic@nexus-software.ie>");
+MODULE_DESCRIPTION("Intel Isolated Memory Region self-test driver");
+MODULE_LICENSE("Dual BSD/GPL");
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index bd8b8459c3d0..5240f563076d 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -1070,6 +1070,23 @@ static inline void xen_write_cr8(unsigned long val)
BUG_ON(val);
}
#endif
+
+static u64 xen_read_msr_safe(unsigned int msr, int *err)
+{
+ u64 val;
+
+ val = native_read_msr_safe(msr, err);
+ switch (msr) {
+ case MSR_IA32_APICBASE:
+#ifdef CONFIG_X86_X2APIC
+ if (!(cpuid_ecx(1) & (1 << (X86_FEATURE_X2APIC & 31))))
+#endif
+ val &= ~X2APIC_ENABLE;
+ break;
+ }
+ return val;
+}
+
static int xen_write_msr_safe(unsigned int msr, unsigned low, unsigned high)
{
int ret;
@@ -1240,7 +1257,7 @@ static const struct pv_cpu_ops xen_cpu_ops __initconst = {
.wbinvd = native_wbinvd,
- .read_msr = native_read_msr_safe,
+ .read_msr = xen_read_msr_safe,
.write_msr = xen_write_msr_safe,
.read_tsc = native_read_tsc,
@@ -1741,6 +1758,7 @@ asmlinkage __visible void __init xen_start_kernel(void)
#ifdef CONFIG_X86_32
i386_start_kernel();
#else
+ cr4_init_shadow(); /* 32b kernel does this in i386_start_kernel() */
x86_64_start_reservations((char *)__pa_symbol(&boot_params));
#endif
}
diff --git a/arch/x86/xen/spinlock.c b/arch/x86/xen/spinlock.c
index 23b45eb9a89c..956374c1edbc 100644
--- a/arch/x86/xen/spinlock.c
+++ b/arch/x86/xen/spinlock.c
@@ -41,7 +41,7 @@ static u8 zero_stats;
static inline void check_zero(void)
{
u8 ret;
- u8 old = ACCESS_ONCE(zero_stats);
+ u8 old = READ_ONCE(zero_stats);
if (unlikely(old)) {
ret = cmpxchg(&zero_stats, old, 0);
/* This ensures only one fellow resets the stat */
@@ -112,6 +112,7 @@ __visible void xen_lock_spinning(struct arch_spinlock *lock, __ticket_t want)
struct xen_lock_waiting *w = this_cpu_ptr(&lock_waiting);
int cpu = smp_processor_id();
u64 start;
+ __ticket_t head;
unsigned long flags;
/* If kicker interrupts not initialized yet, just spin */
@@ -159,11 +160,15 @@ __visible void xen_lock_spinning(struct arch_spinlock *lock, __ticket_t want)
*/
__ticket_enter_slowpath(lock);
+ /* make sure enter_slowpath, which is atomic does not cross the read */
+ smp_mb__after_atomic();
+
/*
* check again make sure it didn't become free while
* we weren't looking
*/
- if (ACCESS_ONCE(lock->tickets.head) == want) {
+ head = READ_ONCE(lock->tickets.head);
+ if (__tickets_equal(head, want)) {
add_stats(TAKEN_SLOW_PICKUP, 1);
goto out;
}
@@ -204,8 +209,8 @@ static void xen_unlock_kick(struct arch_spinlock *lock, __ticket_t next)
const struct xen_lock_waiting *w = &per_cpu(lock_waiting, cpu);
/* Make sure we read lock before want */
- if (ACCESS_ONCE(w->lock) == lock &&
- ACCESS_ONCE(w->want) == next) {
+ if (READ_ONCE(w->lock) == lock &&
+ READ_ONCE(w->want) == next) {
add_stats(RELEASED_SLOW_KICKED, 1);
xen_send_IPI_one(cpu, XEN_SPIN_UNLOCK_VECTOR);
break;