VERSION = 4
PATCHLEVEL = 16
SUBLEVEL = 0
-EXTRAVERSION = -rc1
+EXTRAVERSION = -rc3
NAME = Fearless Coyote
# *DOCUMENTATION*
KBUILD_AFLAGS += $(CLANG_TARGET) $(CLANG_GCC_TC)
endif
+ RETPOLINE_CFLAGS_GCC := -mindirect-branch=thunk-extern -mindirect-branch-register
+ RETPOLINE_CFLAGS_CLANG := -mretpoline-external-thunk
+ RETPOLINE_CFLAGS := $(call cc-option,$(RETPOLINE_CFLAGS_GCC),$(call cc-option,$(RETPOLINE_CFLAGS_CLANG)))
+ export RETPOLINE_CFLAGS
+
ifeq ($(config-targets),1)
# ===========================================================================
# *config targets only - make sure prerequisites are updated, and descend
For old smp systems that do not have proper acpi support. Newer systems
(esp with 64bit cpus) with acpi support, MADT and DSDT will override it
-config X86_BIGSMP
- bool "Support for big SMP systems with more than 8 CPUs"
- depends on X86_32 && SMP
- ---help---
- This option is needed for the systems that have more than 8 CPUs
-
config GOLDFISH
def_bool y
depends on X86_GOLDFISH
config RETPOLINE
bool "Avoid speculative indirect branches in kernel"
default y
+ select STACK_VALIDATION if HAVE_STACK_VALIDATION
help
Compile kernel with the retpoline compiler options to guard against
kernel-to-user data leaks by avoiding speculative indirect
Say N if unsure.
if X86_32
+config X86_BIGSMP
+ bool "Support for big SMP systems with more than 8 CPUs"
+ depends on SMP
+ ---help---
+ This option is needed for the systems that have more than 8 CPUs
+
config X86_EXTENDED_PLATFORM
bool "Support for extended (non-PC) x86 platforms"
default y
Enable maximum number of CPUS and NUMA Nodes for this architecture.
If unsure, say N.
+#
+# The maximum number of CPUs supported:
+#
+# The main config value is NR_CPUS, which defaults to NR_CPUS_DEFAULT,
+# and which can be configured interactively in the
+# [NR_CPUS_RANGE_BEGIN ... NR_CPUS_RANGE_END] range.
+#
+# The ranges are different on 32-bit and 64-bit kernels, depending on
+# hardware capabilities and scalability features of the kernel.
+#
+# ( If MAXSMP is enabled we just use the highest possible value and disable
+# interactive configuration. )
+#
+
+config NR_CPUS_RANGE_BEGIN
+ int
+ default NR_CPUS_RANGE_END if MAXSMP
+ default 1 if !SMP
+ default 2
+
+config NR_CPUS_RANGE_END
+ int
+ depends on X86_32
+ default 64 if SMP && X86_BIGSMP
+ default 8 if SMP && !X86_BIGSMP
+ default 1 if !SMP
+
+config NR_CPUS_RANGE_END
+ int
+ depends on X86_64
+ default 8192 if SMP && ( MAXSMP || CPUMASK_OFFSTACK)
+ default 512 if SMP && (!MAXSMP && !CPUMASK_OFFSTACK)
+ default 1 if !SMP
+
+config NR_CPUS_DEFAULT
+ int
+ depends on X86_32
+ default 32 if X86_BIGSMP
+ default 8 if SMP
+ default 1 if !SMP
+
+config NR_CPUS_DEFAULT
+ int
+ depends on X86_64
+ default 8192 if MAXSMP
+ default 64 if SMP
+ default 1 if !SMP
+
config NR_CPUS
int "Maximum number of CPUs" if SMP && !MAXSMP
- range 2 8 if SMP && X86_32 && !X86_BIGSMP
- range 2 64 if SMP && X86_32 && X86_BIGSMP
- range 2 512 if SMP && !MAXSMP && !CPUMASK_OFFSTACK && X86_64
- range 2 8192 if SMP && !MAXSMP && CPUMASK_OFFSTACK && X86_64
- default "1" if !SMP
- default "8192" if MAXSMP
- default "32" if SMP && X86_BIGSMP
- default "8" if SMP && X86_32
- default "64" if SMP
+ range NR_CPUS_RANGE_BEGIN NR_CPUS_RANGE_END
+ default NR_CPUS_DEFAULT
---help---
This allows you to specify the maximum number of CPUs which this
kernel will support. If CPUMASK_OFFSTACK is enabled, the maximum
supported value is 8192, otherwise the maximum value is 512. The
minimum value which makes sense is 2.
- This is purely to save memory - each supported CPU adds
- approximately eight kilobytes to the kernel image.
+ This is purely to save memory: each supported CPU adds about 8KB
+ to the kernel image.
config SCHED_SMT
bool "SMT (Hyperthreading) scheduler support"
config HIGHMEM64G
bool "64GB"
- depends on !M486
+ depends on !M486 && !M586 && !M586TSC && !M586MMX && !MGEODE_LX && !MGEODEGX1 && !MCYRIXIII && !MELAN && !MWINCHIPC6 && !WINCHIP3D && !MK6
select X86_PAE
---help---
Select this if you have a 32-bit processor and more than 4
config X86_5LEVEL
bool "Enable 5-level page tables support"
+ select DYNAMIC_MEMORY_LAYOUT
+ select SPARSEMEM_VMEMMAP
depends on X86_64
---help---
5-level paging enables access to larger address space:
It will be supported by future Intel CPUs.
- Note: a kernel with this option enabled can only be booted
- on machines that support the feature.
+ A kernel with the option enabled can be booted on machines that
+ support 4- or 5-level paging.
See Documentation/x86/x86_64/5level-paging.txt for more
information.
Don't change this unless you know what you are doing.
+config DYNAMIC_MEMORY_LAYOUT
+ bool
+ ---help---
+ This option makes base addresses of vmalloc and vmemmap as well as
+ __PAGE_OFFSET movable during boot.
+
config RANDOMIZE_MEMORY
bool "Randomize the kernel memory sections"
depends on X86_64
depends on RANDOMIZE_BASE
+ select DYNAMIC_MEMORY_LAYOUT
default RANDOMIZE_BASE
---help---
Randomizes the base virtual address of kernel memory sections
it can be used to assist security vulnerability exploitation.
This setting can be changed at boot time via the kernel command
- line parameter vsyscall=[native|emulate|none].
+ line parameter vsyscall=[emulate|none].
On a system with recent enough glibc (2.14 or newer) and no
static binaries, you can say None without a performance penalty
If unsure, select "Emulate".
- config LEGACY_VSYSCALL_NATIVE
- bool "Native"
- help
- Actual executable code is located in the fixed vsyscall
- address mapping, implementing time() efficiently. Since
- this makes the mapping executable, it can be used during
- security vulnerability exploitation (traditionally as
- ROP gadgets). This configuration is not recommended.
-
config LEGACY_VSYSCALL_EMULATE
bool "Emulate"
help
* Change top bits to match most significant bit (47th or 56th bit
* depending on paging mode) in the address.
*/
+#ifdef CONFIG_X86_5LEVEL
+ ALTERNATIVE "shl $(64 - 48), %rcx; sar $(64 - 48), %rcx", \
+ "shl $(64 - 57), %rcx; sar $(64 - 57), %rcx", X86_FEATURE_LA57
+#else
shl $(64 - (__VIRTUAL_MASK_SHIFT+1)), %rcx
sar $(64 - (__VIRTUAL_MASK_SHIFT+1)), %rcx
+#endif
/* If this changed %rcx, it was not canonical */
cmpq %rcx, %r11
* exist, overwrite the RSB with entries which capture
* speculative execution to prevent attack.
*/
- /* Clobbers %rbx */
- FILL_RETURN_BUFFER RSB_CLEAR_LOOPS, X86_FEATURE_RSB_CTXSW
+ FILL_RETURN_BUFFER %r12, RSB_CLEAR_LOOPS, X86_FEATURE_RSB_CTXSW
#endif
/* restore callee-saved registers */
*
* The invariant is that, if irq_count != -1, then the IRQ stack is in use.
*/
- .macro ENTER_IRQ_STACK regs=1 old_rsp
+ .macro ENTER_IRQ_STACK regs=1 old_rsp save_ret=0
DEBUG_ENTRY_ASSERT_IRQS_OFF
+
+ .if \save_ret
+ /*
+ * If save_ret is set, the original stack contains one additional
+ * entry -- the return address. Therefore, move the address one
+ * entry below %rsp to \old_rsp.
+ */
+ leaq 8(%rsp), \old_rsp
+ .else
movq %rsp, \old_rsp
+ .endif
.if \regs
UNWIND_HINT_REGS base=\old_rsp
.if \regs
UNWIND_HINT_REGS indirect=1
.endif
+
+ .if \save_ret
+ /*
+ * Push the return address to the stack. This return address can
+ * be found at the "real" original RSP, which was offset by 8 at
+ * the beginning of this macro.
+ */
+ pushq -8(\old_rsp)
+ .endif
.endm
/*
.endm
/*
- * Interrupt entry/exit.
- *
- * Interrupt entry points save only callee clobbered registers in fast path.
+ * Interrupt entry helper function.
*
- * Entry runs with interrupts off.
+ * Entry runs with interrupts off. Stack layout at entry:
+ * +----------------------------------------------------+
+ * | regs->ss |
+ * | regs->rsp |
+ * | regs->eflags |
+ * | regs->cs |
+ * | regs->ip |
+ * +----------------------------------------------------+
+ * | regs->orig_ax = ~(interrupt number) |
+ * +----------------------------------------------------+
+ * | return address |
+ * +----------------------------------------------------+
*/
-
- /* 0(%rsp): ~(interrupt number) */
- .macro interrupt func
+ ENTRY(interrupt_entry)
+ UNWIND_HINT_FUNC
+ ASM_CLAC
cld
- testb $3, CS-ORIG_RAX(%rsp)
+ testb $3, CS-ORIG_RAX+8(%rsp)
jz 1f
SWAPGS
- call switch_to_thread_stack
+
+ /*
+ * Switch to the thread stack. The IRET frame and orig_ax are
+ * on the stack, as well as the return address. RDI..R12 are
+ * not (yet) on the stack and space has not (yet) been
+ * allocated for them.
+ */
+ pushq %rdi
+
+ /* Need to switch before accessing the thread stack. */
+ SWITCH_TO_KERNEL_CR3 scratch_reg=%rdi
+ movq %rsp, %rdi
+ movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp
+
+ /*
+ * We have RDI, return address, and orig_ax on the stack on
+ * top of the IRET frame. That means offset=24
+ */
+ UNWIND_HINT_IRET_REGS base=%rdi offset=24
+
+ pushq 7*8(%rdi) /* regs->ss */
+ pushq 6*8(%rdi) /* regs->rsp */
+ pushq 5*8(%rdi) /* regs->eflags */
+ pushq 4*8(%rdi) /* regs->cs */
+ pushq 3*8(%rdi) /* regs->ip */
+ pushq 2*8(%rdi) /* regs->orig_ax */
+ pushq 8(%rdi) /* return address */
+ UNWIND_HINT_FUNC
+
+ movq (%rdi), %rdi
1:
- PUSH_AND_CLEAR_REGS
- ENCODE_FRAME_POINTER
+ PUSH_AND_CLEAR_REGS save_ret=1
+ ENCODE_FRAME_POINTER 8
- testb $3, CS(%rsp)
+ testb $3, CS+8(%rsp)
jz 1f
/*
*
* We need to tell lockdep that IRQs are off. We can't do this until
* we fix gsbase, and we should do it before enter_from_user_mode
- * (which can take locks). Since TRACE_IRQS_OFF idempotent,
+ * (which can take locks). Since TRACE_IRQS_OFF is idempotent,
* the simplest way to handle it is to just call it twice if
* we enter from user mode. There's no reason to optimize this since
* TRACE_IRQS_OFF is a no-op if lockdep is off.
CALL_enter_from_user_mode
1:
- ENTER_IRQ_STACK old_rsp=%rdi
+ ENTER_IRQ_STACK old_rsp=%rdi save_ret=1
/* We entered an interrupt context - irqs are off: */
TRACE_IRQS_OFF
- call \func /* rdi points to pt_regs */
- .endm
+ ret
+ END(interrupt_entry)
+
+
+ /* Interrupt entry/exit. */
/*
* The interrupt stubs push (~vector+0x80) onto the stack and
*/
.p2align CONFIG_X86_L1_CACHE_SHIFT
common_interrupt:
- ASM_CLAC
addq $-0x80, (%rsp) /* Adjust vector to [-256, -1] range */
- interrupt do_IRQ
+ call interrupt_entry
+ UNWIND_HINT_REGS indirect=1
+ call do_IRQ /* rdi points to pt_regs */
/* 0(%rsp): old RSP */
ret_from_intr:
DISABLE_INTERRUPTS(CLBR_ANY)
.macro apicinterrupt3 num sym do_sym
ENTRY(\sym)
UNWIND_HINT_IRET_REGS
- ASM_CLAC
pushq $~(\num)
.Lcommon_\sym:
- interrupt \do_sym
+ call interrupt_entry
+ UNWIND_HINT_REGS indirect=1
+ call \do_sym /* rdi points to pt_regs */
jmp ret_from_intr
END(\sym)
.endm
*/
#define CPU_TSS_IST(x) PER_CPU_VAR(cpu_tss_rw) + (TSS_ist + ((x) - 1) * 8)
- /*
- * Switch to the thread stack. This is called with the IRET frame and
- * orig_ax on the stack. (That is, RDI..R12 are not on the stack and
- * space has not been allocated for them.)
- */
- ENTRY(switch_to_thread_stack)
- UNWIND_HINT_FUNC
-
- pushq %rdi
- /* Need to switch before accessing the thread stack. */
- SWITCH_TO_KERNEL_CR3 scratch_reg=%rdi
- movq %rsp, %rdi
- movq PER_CPU_VAR(cpu_current_top_of_stack), %rsp
- UNWIND_HINT sp_offset=16 sp_reg=ORC_REG_DI
-
- pushq 7*8(%rdi) /* regs->ss */
- pushq 6*8(%rdi) /* regs->rsp */
- pushq 5*8(%rdi) /* regs->eflags */
- pushq 4*8(%rdi) /* regs->cs */
- pushq 3*8(%rdi) /* regs->ip */
- pushq 2*8(%rdi) /* regs->orig_ax */
- pushq 8(%rdi) /* return address */
- UNWIND_HINT_FUNC
-
- movq (%rdi), %rdi
- ret
- END(switch_to_thread_stack)
-
.macro idtentry sym do_sym has_error_code:req paranoid=0 shift_ist=-1
ENTRY(\sym)
UNWIND_HINT_IRET_REGS offset=\has_error_code*8
pushq $-1 /* ORIG_RAX: no syscall to restart */
.endif
- /* Save all registers in pt_regs */
- PUSH_AND_CLEAR_REGS
- ENCODE_FRAME_POINTER
-
.if \paranoid < 2
- testb $3, CS(%rsp) /* If coming from userspace, switch stacks */
+ testb $3, CS-ORIG_RAX(%rsp) /* If coming from userspace, switch stacks */
jnz .Lfrom_usermode_switch_stack_\@
.endif
#endif
/*
- * Switch gs if needed.
+ * Save all registers in pt_regs, and switch gs if needed.
* Use slow, but surefire "are we in kernel?" check.
* Return: ebx=0: need swapgs on exit, ebx=1: otherwise
*/
ENTRY(paranoid_entry)
UNWIND_HINT_FUNC
cld
+ PUSH_AND_CLEAR_REGS save_ret=1
+ ENCODE_FRAME_POINTER 8
movl $1, %ebx
movl $MSR_GS_BASE, %ecx
rdmsr
END(paranoid_exit)
/*
- * Switch gs if needed.
+ * Save all registers in pt_regs, and switch GS if needed.
* Return: EBX=0: came from user mode; EBX=1: otherwise
*/
ENTRY(error_entry)
- UNWIND_HINT_REGS offset=8
+ UNWIND_HINT_FUNC
cld
+ PUSH_AND_CLEAR_REGS save_ret=1
+ ENCODE_FRAME_POINTER 8
testb $3, CS+8(%rsp)
jz .Lerror_kernelspace
* frame to point back to repeat_nmi.
*/
pushq $-1 /* ORIG_RAX: no syscall to restart */
- PUSH_AND_CLEAR_REGS
- ENCODE_FRAME_POINTER
/*
* Use paranoid_entry to handle SWAPGS, but no need to use paranoid_exit
#include <asm/cpufeatures.h>
#include <asm/msr-index.h>
+ /*
+ * Fill the CPU return stack buffer.
+ *
+ * Each entry in the RSB, if used for a speculative 'ret', contains an
+ * infinite 'pause; lfence; jmp' loop to capture speculative execution.
+ *
+ * This is required in various cases for retpoline and IBRS-based
+ * mitigations for the Spectre variant 2 vulnerability. Sometimes to
+ * eliminate potentially bogus entries from the RSB, and sometimes
+ * purely to ensure that it doesn't get empty, which on some CPUs would
+ * allow predictions from other (unwanted!) sources to be used.
+ *
+ * We define a CPP macro such that it can be used from both .S files and
+ * inline assembly. It's possible to do a .macro and then include that
+ * from C via asm(".include <asm/nospec-branch.h>") but let's not go there.
+ */
+
+ #define RSB_CLEAR_LOOPS 32 /* To forcibly overwrite all entries */
+ #define RSB_FILL_LOOPS 16 /* To avoid underflow */
+
+ /*
+ * Google experimented with loop-unrolling and this turned out to be
+ * the optimal version — two calls, each with their own speculation
+ * trap should their return address end up getting used, in a loop.
+ */
+ #define __FILL_RETURN_BUFFER(reg, nr, sp) \
+ mov $(nr/2), reg; \
+ 771: \
+ call 772f; \
+ 773: /* speculation trap */ \
+ pause; \
+ lfence; \
+ jmp 773b; \
+ 772: \
+ call 774f; \
+ 775: /* speculation trap */ \
+ pause; \
+ lfence; \
+ jmp 775b; \
+ 774: \
+ dec reg; \
+ jnz 771b; \
+ add $(BITS_PER_LONG/8) * nr, sp;
+
#ifdef __ASSEMBLY__
/*
.popsection
.endm
+ /*
+ * This should be used immediately before an indirect jump/call. It tells
+ * objtool the subsequent indirect jump/call is vouched safe for retpoline
+ * builds.
+ */
+ .macro ANNOTATE_RETPOLINE_SAFE
+ .Lannotate_\@:
+ .pushsection .discard.retpoline_safe
+ _ASM_PTR .Lannotate_\@
+ .popsection
+ .endm
+
/*
* These are the bare retpoline primitives for indirect jmp and call.
* Do not use these directly; they only exist to make the ALTERNATIVE
.macro JMP_NOSPEC reg:req
#ifdef CONFIG_RETPOLINE
ANNOTATE_NOSPEC_ALTERNATIVE
- ALTERNATIVE_2 __stringify(jmp *\reg), \
+ ALTERNATIVE_2 __stringify(ANNOTATE_RETPOLINE_SAFE; jmp *\reg), \
__stringify(RETPOLINE_JMP \reg), X86_FEATURE_RETPOLINE, \
- __stringify(lfence; jmp *\reg), X86_FEATURE_RETPOLINE_AMD
+ __stringify(lfence; ANNOTATE_RETPOLINE_SAFE; jmp *\reg), X86_FEATURE_RETPOLINE_AMD
#else
jmp *\reg
#endif
.macro CALL_NOSPEC reg:req
#ifdef CONFIG_RETPOLINE
ANNOTATE_NOSPEC_ALTERNATIVE
- ALTERNATIVE_2 __stringify(call *\reg), \
+ ALTERNATIVE_2 __stringify(ANNOTATE_RETPOLINE_SAFE; call *\reg), \
__stringify(RETPOLINE_CALL \reg), X86_FEATURE_RETPOLINE,\
- __stringify(lfence; call *\reg), X86_FEATURE_RETPOLINE_AMD
+ __stringify(lfence; ANNOTATE_RETPOLINE_SAFE; call *\reg), X86_FEATURE_RETPOLINE_AMD
#else
call *\reg
#endif
.endm
- /* This clobbers the BX register */
- .macro FILL_RETURN_BUFFER nr:req ftr:req
+ /*
+ * A simpler FILL_RETURN_BUFFER macro. Don't make people use the CPP
+ * monstrosity above, manually.
+ */
+ .macro FILL_RETURN_BUFFER reg:req nr:req ftr:req
#ifdef CONFIG_RETPOLINE
- ALTERNATIVE "", "call __clear_rsb", \ftr
+ ANNOTATE_NOSPEC_ALTERNATIVE
+ ALTERNATIVE "jmp .Lskip_rsb_\@", \
+ __stringify(__FILL_RETURN_BUFFER(\reg,\nr,%_ASM_SP)) \
+ \ftr
+ .Lskip_rsb_\@:
#endif
.endm
".long 999b - .\n\t" \
".popsection\n\t"
+ #define ANNOTATE_RETPOLINE_SAFE \
+ "999:\n\t" \
+ ".pushsection .discard.retpoline_safe\n\t" \
+ _ASM_PTR " 999b\n\t" \
+ ".popsection\n\t"
+
#if defined(CONFIG_X86_64) && defined(RETPOLINE)
/*
# define CALL_NOSPEC \
ANNOTATE_NOSPEC_ALTERNATIVE \
ALTERNATIVE( \
+ ANNOTATE_RETPOLINE_SAFE \
"call *%[thunk_target]\n", \
"call __x86_indirect_thunk_%V[thunk_target]\n", \
X86_FEATURE_RETPOLINE)
static inline void vmexit_fill_RSB(void)
{
#ifdef CONFIG_RETPOLINE
- alternative_input("",
- "call __fill_rsb",
- X86_FEATURE_RETPOLINE,
- ASM_NO_INPUT_CLOBBER(_ASM_BX, "memory"));
+ unsigned long loops;
+
+ asm volatile (ANNOTATE_NOSPEC_ALTERNATIVE
+ ALTERNATIVE("jmp 910f",
+ __stringify(__FILL_RETURN_BUFFER(%0, RSB_CLEAR_LOOPS, %1)),
+ X86_FEATURE_RETPOLINE)
+ "910:"
+ : "=r" (loops), ASM_CALL_CONSTRAINT
+ : : "memory" );
#endif
}
+ #define alternative_msr_write(_msr, _val, _feature) \
+ asm volatile(ALTERNATIVE("", \
+ "movl %[msr], %%ecx\n\t" \
+ "movl %[val], %%eax\n\t" \
+ "movl $0, %%edx\n\t" \
+ "wrmsr", \
+ _feature) \
+ : : [msr] "i" (_msr), [val] "i" (_val) \
+ : "eax", "ecx", "edx", "memory")
+
static inline void indirect_branch_prediction_barrier(void)
{
- asm volatile(ALTERNATIVE("",
- "movl %[msr], %%ecx\n\t"
- "movl %[val], %%eax\n\t"
- "movl $0, %%edx\n\t"
- "wrmsr",
- X86_FEATURE_USE_IBPB)
- : : [msr] "i" (MSR_IA32_PRED_CMD),
- [val] "i" (PRED_CMD_IBPB)
- : "eax", "ecx", "edx", "memory");
+ alternative_msr_write(MSR_IA32_PRED_CMD, PRED_CMD_IBPB,
+ X86_FEATURE_USE_IBPB);
}
+ /*
+ * With retpoline, we must use IBRS to restrict branch prediction
+ * before calling into firmware.
+ *
+ * (Implemented as CPP macros due to header hell.)
+ */
+ #define firmware_restrict_branch_speculation_start() \
+ do { \
+ preempt_disable(); \
+ alternative_msr_write(MSR_IA32_SPEC_CTRL, SPEC_CTRL_IBRS, \
+ X86_FEATURE_USE_IBRS_FW); \
+ } while (0)
+
+ #define firmware_restrict_branch_speculation_end() \
+ do { \
+ alternative_msr_write(MSR_IA32_SPEC_CTRL, 0, \
+ X86_FEATURE_USE_IBRS_FW); \
+ preempt_enable(); \
+ } while (0)
+
#endif /* __ASSEMBLY__ */
+
+/*
+ * Below is used in the eBPF JIT compiler and emits the byte sequence
+ * for the following assembly:
+ *
+ * With retpolines configured:
+ *
+ * callq do_rop
+ * spec_trap:
+ * pause
+ * lfence
+ * jmp spec_trap
+ * do_rop:
+ * mov %rax,(%rsp)
+ * retq
+ *
+ * Without retpolines configured:
+ *
+ * jmp *%rax
+ */
+#ifdef CONFIG_RETPOLINE
+# define RETPOLINE_RAX_BPF_JIT_SIZE 17
+# define RETPOLINE_RAX_BPF_JIT() \
+ EMIT1_off32(0xE8, 7); /* callq do_rop */ \
+ /* spec_trap: */ \
+ EMIT2(0xF3, 0x90); /* pause */ \
+ EMIT3(0x0F, 0xAE, 0xE8); /* lfence */ \
+ EMIT2(0xEB, 0xF9); /* jmp spec_trap */ \
+ /* do_rop: */ \
+ EMIT4(0x48, 0x89, 0x04, 0x24); /* mov %rax,(%rsp) */ \
+ EMIT1(0xC3); /* retq */
+#else
+# define RETPOLINE_RAX_BPF_JIT_SIZE 2
+# define RETPOLINE_RAX_BPF_JIT() \
+ EMIT2(0xFF, 0xE0); /* jmp *%rax */
+#endif
+
#endif /* _ASM_X86_NOSPEC_BRANCH_H_ */
#ifdef CONFIG_PARAVIRT
#include <asm/pgtable_types.h>
#include <asm/asm.h>
+ #include <asm/nospec-branch.h>
#include <asm/paravirt_types.h>
return PVOP_CALLEE1(p4dval_t, pv_mmu_ops.p4d_val, p4d.p4d);
}
-static inline void set_pgd(pgd_t *pgdp, pgd_t pgd)
+static inline void __set_pgd(pgd_t *pgdp, pgd_t pgd)
{
- pgdval_t val = native_pgd_val(pgd);
-
- PVOP_VCALL2(pv_mmu_ops.set_pgd, pgdp, val);
+ PVOP_VCALL2(pv_mmu_ops.set_pgd, pgdp, native_pgd_val(pgd));
}
-static inline void pgd_clear(pgd_t *pgdp)
-{
- set_pgd(pgdp, __pgd(0));
-}
+#define set_pgd(pgdp, pgdval) do { \
+ if (pgtable_l5_enabled) \
+ __set_pgd(pgdp, pgdval); \
+ else \
+ set_p4d((p4d_t *)(pgdp), (p4d_t) { (pgdval).pgd }); \
+} while (0)
+
+#define pgd_clear(pgdp) do { \
+ if (pgtable_l5_enabled) \
+ set_pgd(pgdp, __pgd(0)); \
+} while (0)
#endif /* CONFIG_PGTABLE_LEVELS == 5 */
#define INTERRUPT_RETURN \
PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_iret), CLBR_NONE, \
- jmp PARA_INDIRECT(pv_cpu_ops+PV_CPU_iret))
+ ANNOTATE_RETPOLINE_SAFE; \
+ jmp PARA_INDIRECT(pv_cpu_ops+PV_CPU_iret);)
#define DISABLE_INTERRUPTS(clobbers) \
PARA_SITE(PARA_PATCH(pv_irq_ops, PV_IRQ_irq_disable), clobbers, \
PV_SAVE_REGS(clobbers | CLBR_CALLEE_SAVE); \
+ ANNOTATE_RETPOLINE_SAFE; \
call PARA_INDIRECT(pv_irq_ops+PV_IRQ_irq_disable); \
PV_RESTORE_REGS(clobbers | CLBR_CALLEE_SAVE);)
#define ENABLE_INTERRUPTS(clobbers) \
PARA_SITE(PARA_PATCH(pv_irq_ops, PV_IRQ_irq_enable), clobbers, \
PV_SAVE_REGS(clobbers | CLBR_CALLEE_SAVE); \
+ ANNOTATE_RETPOLINE_SAFE; \
call PARA_INDIRECT(pv_irq_ops+PV_IRQ_irq_enable); \
PV_RESTORE_REGS(clobbers | CLBR_CALLEE_SAVE);)
#ifdef CONFIG_X86_32
#define GET_CR0_INTO_EAX \
push %ecx; push %edx; \
+ ANNOTATE_RETPOLINE_SAFE; \
call PARA_INDIRECT(pv_cpu_ops+PV_CPU_read_cr0); \
pop %edx; pop %ecx
#else /* !CONFIG_X86_32 */
*/
#define SWAPGS \
PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_swapgs), CLBR_NONE, \
- call PARA_INDIRECT(pv_cpu_ops+PV_CPU_swapgs) \
+ ANNOTATE_RETPOLINE_SAFE; \
+ call PARA_INDIRECT(pv_cpu_ops+PV_CPU_swapgs); \
)
#define GET_CR2_INTO_RAX \
- call PARA_INDIRECT(pv_mmu_ops+PV_MMU_read_cr2)
+ ANNOTATE_RETPOLINE_SAFE; \
+ call PARA_INDIRECT(pv_mmu_ops+PV_MMU_read_cr2);
#define USERGS_SYSRET64 \
PARA_SITE(PARA_PATCH(pv_cpu_ops, PV_CPU_usergs_sysret64), \
CLBR_NONE, \
- jmp PARA_INDIRECT(pv_cpu_ops+PV_CPU_usergs_sysret64))
+ ANNOTATE_RETPOLINE_SAFE; \
+ jmp PARA_INDIRECT(pv_cpu_ops+PV_CPU_usergs_sysret64);)
#ifdef CONFIG_DEBUG_ENTRY
#define SAVE_FLAGS(clobbers) \
PARA_SITE(PARA_PATCH(pv_irq_ops, PV_IRQ_save_fl), clobbers, \
PV_SAVE_REGS(clobbers | CLBR_CALLEE_SAVE); \
+ ANNOTATE_RETPOLINE_SAFE; \
call PARA_INDIRECT(pv_irq_ops+PV_IRQ_save_fl); \
PV_RESTORE_REGS(clobbers | CLBR_CALLEE_SAVE);)
#endif
#ifndef __PAGETABLE_P4D_FOLDED
#define set_pgd(pgdp, pgd) native_set_pgd(pgdp, pgd)
-#define pgd_clear(pgd) native_pgd_clear(pgd)
+#define pgd_clear(pgd) (pgtable_l5_enabled ? native_pgd_clear(pgd) : 0)
#endif
#ifndef set_p4d
{
pmdval_t v = native_pmd_val(pmd);
- return __pmd(v | set);
+ return native_make_pmd(v | set);
}
static inline pmd_t pmd_clear_flags(pmd_t pmd, pmdval_t clear)
{
pmdval_t v = native_pmd_val(pmd);
- return __pmd(v & ~clear);
+ return native_make_pmd(v & ~clear);
}
static inline pmd_t pmd_mkold(pmd_t pmd)
{
pudval_t v = native_pud_val(pud);
- return __pud(v | set);
+ return native_make_pud(v | set);
}
static inline pud_t pud_clear_flags(pud_t pud, pudval_t clear)
{
pudval_t v = native_pud_val(pud);
- return __pud(v & ~clear);
+ return native_make_pud(v & ~clear);
}
static inline pud_t pud_mkold(pud_t pud)
#if CONFIG_PGTABLE_LEVELS > 4
static inline int pgd_present(pgd_t pgd)
{
+ if (!pgtable_l5_enabled)
+ return 1;
return pgd_flags(pgd) & _PAGE_PRESENT;
}
/* to find an entry in a page-table-directory. */
static inline p4d_t *p4d_offset(pgd_t *pgd, unsigned long address)
{
+ if (!pgtable_l5_enabled)
+ return (p4d_t *)pgd;
return (p4d_t *)pgd_page_vaddr(*pgd) + p4d_index(address);
}
{
unsigned long ignore_flags = _PAGE_USER;
+ if (!pgtable_l5_enabled)
+ return 0;
+
if (IS_ENABLED(CONFIG_PAGE_TABLE_ISOLATION))
ignore_flags |= _PAGE_NX;
static inline int pgd_none(pgd_t pgd)
{
+ if (!pgtable_l5_enabled)
+ return 0;
/*
* There is no need to do a workaround for the KNL stray
* A/D bit erratum here. PGDs only point to page tables
static inline void pgtable_cache_init(void) { }
static inline void check_pgt_cache(void) { }
void paging_init(void);
+ void sync_initial_page_table(void);
+static inline int pgd_large(pgd_t pgd) { return 0; }
+
/*
* Define this if things work differently on an i386 and an i486:
* it will (on an i486) warn about kernel memory accesses that are
#define swapper_pg_dir init_top_pgt
extern void paging_init(void);
+ static inline void sync_initial_page_table(void) { }
#define pte_ERROR(e) \
pr_err("%s:%d: bad pte %p(%016lx)\n", \
static inline void native_set_p4d(p4d_t *p4dp, p4d_t p4d)
{
-#if defined(CONFIG_PAGE_TABLE_ISOLATION) && !defined(CONFIG_X86_5LEVEL)
- p4dp->pgd = pti_set_user_pgd(&p4dp->pgd, p4d.pgd);
-#else
- *p4dp = p4d;
-#endif
+ pgd_t pgd;
+
+ if (pgtable_l5_enabled || !IS_ENABLED(CONFIG_PAGE_TABLE_ISOLATION)) {
+ *p4dp = p4d;
+ return;
+ }
+
+ pgd = native_make_pgd(native_p4d_val(p4d));
+ pgd = pti_set_user_pgd((pgd_t *)p4dp, pgd);
+ *p4dp = native_make_p4d(native_pgd_val(pgd));
}
static inline void native_p4d_clear(p4d_t *p4d)
{
-#ifdef CONFIG_X86_5LEVEL
native_set_p4d(p4d, native_make_p4d(0));
-#else
- native_set_p4d(p4d, (p4d_t) { .pgd = native_make_pgd(0)});
-#endif
}
static inline void native_set_pgd(pgd_t *pgdp, pgd_t pgd)
{
-#ifdef CONFIG_PAGE_TABLE_ISOLATION
*pgdp = pti_set_user_pgd(pgdp, pgd);
-#else
- *pgdp = pgd;
-#endif
}
static inline void native_pgd_clear(pgd_t *pgd)
#include <asm/nops.h>
#include "../entry/calling.h"
#include <asm/export.h>
+ #include <asm/nospec-branch.h>
#ifdef CONFIG_PARAVIRT
#include <asm/asm-offsets.h>
*
*/
+#define l4_index(x) (((x) >> 39) & 511)
#define pud_index(x) (((x) >> PUD_SHIFT) & (PTRS_PER_PUD-1))
-#if defined(CONFIG_XEN_PV) || defined(CONFIG_XEN_PVH)
-PGD_PAGE_OFFSET = pgd_index(__PAGE_OFFSET_BASE)
-PGD_START_KERNEL = pgd_index(__START_KERNEL_map)
-#endif
+L4_PAGE_OFFSET = l4_index(__PAGE_OFFSET_BASE_L4)
+L4_START_KERNEL = l4_index(__START_KERNEL_map)
+
L3_START_KERNEL = pud_index(__START_KERNEL_map)
.text
/* Enable PAE mode, PGE and LA57 */
movl $(X86_CR4_PAE | X86_CR4_PGE), %ecx
#ifdef CONFIG_X86_5LEVEL
+ testl $1, __pgtable_l5_enabled(%rip)
+ jz 1f
orl $X86_CR4_LA57, %ecx
+1:
#endif
movq %rcx, %cr4
/* Ensure I am executing from virtual addresses */
movq $1f, %rax
+ ANNOTATE_RETPOLINE_SAFE
jmp *%rax
1:
UNWIND_HINT_EMPTY
__INITDATA
NEXT_PGD_PAGE(early_top_pgt)
- .fill 511,8,0
-#ifdef CONFIG_X86_5LEVEL
- .quad level4_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE_NOENC
-#else
- .quad level3_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE_NOENC
-#endif
+ .fill 512,8,0
.fill PTI_USER_PGD_FILL,8,0
NEXT_PAGE(early_dynamic_pgts)
#if defined(CONFIG_XEN_PV) || defined(CONFIG_XEN_PVH)
NEXT_PGD_PAGE(init_top_pgt)
.quad level3_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE_NOENC
- .org init_top_pgt + PGD_PAGE_OFFSET*8, 0
+ .org init_top_pgt + L4_PAGE_OFFSET*8, 0
.quad level3_ident_pgt - __START_KERNEL_map + _KERNPG_TABLE_NOENC
- .org init_top_pgt + PGD_START_KERNEL*8, 0
+ .org init_top_pgt + L4_START_KERNEL*8, 0
/* (2^48-(2*1024*1024*1024))/(2^39) = 511 */
.quad level3_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE_NOENC
.fill PTI_USER_PGD_FILL,8,0
#endif
#else
-struct cpuinfo_x86 boot_cpu_data __read_mostly = {
- .x86_phys_bits = MAX_PHYSMEM_BITS,
-};
+struct cpuinfo_x86 boot_cpu_data __read_mostly;
EXPORT_SYMBOL(boot_cpu_data);
#endif
__flush_tlb_all();
#else
printk(KERN_INFO "Command line: %s\n", boot_command_line);
+ boot_cpu_data.x86_phys_bits = MAX_PHYSMEM_BITS;
#endif
/*
kasan_init();
- #ifdef CONFIG_X86_32
- /* sync back kernel address range */
- clone_pgd_range(initial_page_table + KERNEL_PGD_BOUNDARY,
- swapper_pg_dir + KERNEL_PGD_BOUNDARY,
- KERNEL_PGD_PTRS);
-
/*
- * sync back low identity map too. It is used for example
- * in the 32-bit EFI stub.
+ * Sync back kernel address range.
+ *
+ * FIXME: Can the later sync in setup_cpu_entry_areas() replace
+ * this call?
*/
- clone_pgd_range(initial_page_table,
- swapper_pg_dir + KERNEL_PGD_BOUNDARY,
- min(KERNEL_PGD_PTRS, KERNEL_PGD_BOUNDARY));
- #endif
+ sync_initial_page_table();
tboot_probe();
if (pgd_none(*pgd_ref))
return -1;
- if (CONFIG_PGTABLE_LEVELS > 4) {
+ if (pgtable_l5_enabled) {
if (pgd_none(*pgd)) {
set_pgd(pgd, *pgd_ref);
arch_flush_lazy_mmu_mode();
if (p4d_none(*p4d_ref))
return -1;
- if (p4d_none(*p4d) && CONFIG_PGTABLE_LEVELS == 4) {
+ if (p4d_none(*p4d) && !pgtable_l5_enabled) {
set_p4d(p4d, *p4d_ref);
arch_flush_lazy_mmu_mode();
} else {
tsk = current;
mm = tsk->mm;
- /*
- * Detect and handle instructions that would cause a page fault for
- * both a tracked kernel page and a userspace page.
- */
prefetchw(&mm->mmap_sem);
if (unlikely(kmmio_fault(regs, address)))
#define __weak __attribute__((weak))
#define __alias(symbol) __attribute__((alias(#symbol)))
+ #ifdef RETPOLINE
+ #define __noretpoline __attribute__((indirect_branch("keep")))
+ #endif
+
/*
* it doesn't make sense on ARM (currently the only user of __naked)
* to trace naked functions because then mcount is called without
#endif
#endif
+/*
+ * calling noreturn functions, __builtin_unreachable() and __builtin_trap()
+ * confuse the stack allocation in gcc, leading to overly large stack
+ * frames, see https://gcc.gnu.org/bugzilla/show_bug.cgi?id=82365
+ *
+ * Adding an empty inline assembly before it works around the problem
+ */
+#define barrier_before_unreachable() asm volatile("")
+
/*
* Mark a position in code as unreachable. This can be used to
* suppress control flow warnings after asm blocks that transfer
* unreleased. Really, we need to have autoconf for the kernel.
*/
#define unreachable() \
- do { annotate_unreachable(); __builtin_unreachable(); } while (0)
+ do { \
+ annotate_unreachable(); \
+ barrier_before_unreachable(); \
+ __builtin_unreachable(); \
+ } while (0)
/* Mark a function definition as prohibited from being cloned. */
#define __noclone __attribute__((__noclone__, __optimize__("no-tracer")))