summaryrefslogtreecommitdiff
path: root/arch/x86/entry
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2024-03-11 19:53:15 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2024-03-11 19:53:15 -0700
commit685d98211273f60e38a6d361b62d7016c545297e (patch)
tree76c3be7af88578437c72325c322a52a12be3d05d /arch/x86/entry
parentfcc196579aa1fc167d6778948bff69fae6116737 (diff)
parent35ce64922c8263448e58a2b9e8d15a64e11e9b2d (diff)
Merge tag 'x86-core-2024-03-11' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull core x86 updates from Ingo Molnar: - The biggest change is the rework of the percpu code, to support the 'Named Address Spaces' GCC feature, by Uros Bizjak: - This allows C code to access GS and FS segment relative memory via variables declared with such attributes, which allows the compiler to better optimize those accesses than the previous inline assembly code. - The series also includes a number of micro-optimizations for various percpu access methods, plus a number of cleanups of %gs accesses in assembly code. - These changes have been exposed to linux-next testing for the last ~5 months, with no known regressions in this area. - Fix/clean up __switch_to()'s broken but accidentally working handling of FPU switching - which also generates better code - Propagate more RIP-relative addressing in assembly code, to generate slightly better code - Rework the CPU mitigations Kconfig space to be less idiosyncratic, to make it easier for distros to follow & maintain these options - Rework the x86 idle code to cure RCU violations and to clean up the logic - Clean up the vDSO Makefile logic - Misc cleanups and fixes * tag 'x86-core-2024-03-11' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (52 commits) x86/idle: Select idle routine only once x86/idle: Let prefer_mwait_c1_over_halt() return bool x86/idle: Cleanup idle_setup() x86/idle: Clean up idle selection x86/idle: Sanitize X86_BUG_AMD_E400 handling sched/idle: Conditionally handle tick broadcast in default_idle_call() x86: Increase brk randomness entropy for 64-bit systems x86/vdso: Move vDSO to mmap region x86/vdso/kbuild: Group non-standard build attributes and primary object file rules together x86/vdso: Fix rethunk patching for vdso-image-{32,64}.o x86/retpoline: Ensure default return thunk isn't used at runtime x86/vdso: Use CONFIG_COMPAT_32 to specify vdso32 x86/vdso: Use $(addprefix ) instead of $(foreach ) x86/vdso: Simplify obj-y addition x86/vdso: Consolidate targets and clean-files x86/bugs: Rename CONFIG_RETHUNK => CONFIG_MITIGATION_RETHUNK x86/bugs: Rename CONFIG_CPU_SRSO => CONFIG_MITIGATION_SRSO x86/bugs: Rename CONFIG_CPU_IBRS_ENTRY => CONFIG_MITIGATION_IBRS_ENTRY x86/bugs: Rename CONFIG_CPU_UNRET_ENTRY => CONFIG_MITIGATION_UNRET_ENTRY x86/bugs: Rename CONFIG_SLS => CONFIG_MITIGATION_SLS ...
Diffstat (limited to 'arch/x86/entry')
-rw-r--r--arch/x86/entry/calling.h74
-rw-r--r--arch/x86/entry/entry.S3
-rw-r--r--arch/x86/entry/entry_32.S2
-rw-r--r--arch/x86/entry/entry_64.S8
-rw-r--r--arch/x86/entry/thunk_32.S34
-rw-r--r--arch/x86/entry/thunk_64.S33
-rw-r--r--arch/x86/entry/vdso/Makefile57
-rw-r--r--arch/x86/entry/vdso/vma.c57
8 files changed, 108 insertions, 160 deletions
diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h
index 1c3b561528fd..ea81770629ee 100644
--- a/arch/x86/entry/calling.h
+++ b/arch/x86/entry/calling.h
@@ -147,10 +147,10 @@ For 32-bit we have the following conventions - kernel is built with
.endif
.endm
-#ifdef CONFIG_PAGE_TABLE_ISOLATION
+#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION
/*
- * PAGE_TABLE_ISOLATION PGDs are 8k. Flip bit 12 to switch between the two
+ * MITIGATION_PAGE_TABLE_ISOLATION PGDs are 8k. Flip bit 12 to switch between the two
* halves:
*/
#define PTI_USER_PGTABLE_BIT PAGE_SHIFT
@@ -165,7 +165,7 @@ For 32-bit we have the following conventions - kernel is built with
.macro ADJUST_KERNEL_CR3 reg:req
ALTERNATIVE "", "SET_NOFLUSH_BIT \reg", X86_FEATURE_PCID
- /* Clear PCID and "PAGE_TABLE_ISOLATION bit", point CR3 at kernel pagetables: */
+ /* Clear PCID and "MITIGATION_PAGE_TABLE_ISOLATION bit", point CR3 at kernel pagetables: */
andq $(~PTI_USER_PGTABLE_AND_PCID_MASK), \reg
.endm
@@ -178,7 +178,7 @@ For 32-bit we have the following conventions - kernel is built with
.endm
#define THIS_CPU_user_pcid_flush_mask \
- PER_CPU_VAR(cpu_tlbstate) + TLB_STATE_user_pcid_flush_mask
+ PER_CPU_VAR(cpu_tlbstate + TLB_STATE_user_pcid_flush_mask)
.macro SWITCH_TO_USER_CR3 scratch_reg:req scratch_reg2:req
mov %cr3, \scratch_reg
@@ -274,7 +274,7 @@ For 32-bit we have the following conventions - kernel is built with
.Lend_\@:
.endm
-#else /* CONFIG_PAGE_TABLE_ISOLATION=n: */
+#else /* CONFIG_MITIGATION_PAGE_TABLE_ISOLATION=n: */
.macro SWITCH_TO_KERNEL_CR3 scratch_reg:req
.endm
@@ -302,7 +302,7 @@ For 32-bit we have the following conventions - kernel is built with
* Assumes x86_spec_ctrl_{base,current} to have SPEC_CTRL_IBRS set.
*/
.macro IBRS_ENTER save_reg
-#ifdef CONFIG_CPU_IBRS_ENTRY
+#ifdef CONFIG_MITIGATION_IBRS_ENTRY
ALTERNATIVE "jmp .Lend_\@", "", X86_FEATURE_KERNEL_IBRS
movl $MSR_IA32_SPEC_CTRL, %ecx
@@ -331,7 +331,7 @@ For 32-bit we have the following conventions - kernel is built with
* regs. Must be called after the last RET.
*/
.macro IBRS_EXIT save_reg
-#ifdef CONFIG_CPU_IBRS_ENTRY
+#ifdef CONFIG_MITIGATION_IBRS_ENTRY
ALTERNATIVE "jmp .Lend_\@", "", X86_FEATURE_KERNEL_IBRS
movl $MSR_IA32_SPEC_CTRL, %ecx
@@ -425,3 +425,63 @@ For 32-bit we have the following conventions - kernel is built with
.endm
#endif /* CONFIG_SMP */
+
+#ifdef CONFIG_X86_64
+
+/* rdi: arg1 ... normal C conventions. rax is saved/restored. */
+.macro THUNK name, func
+SYM_FUNC_START(\name)
+ pushq %rbp
+ movq %rsp, %rbp
+
+ pushq %rdi
+ pushq %rsi
+ pushq %rdx
+ pushq %rcx
+ pushq %rax
+ pushq %r8
+ pushq %r9
+ pushq %r10
+ pushq %r11
+
+ call \func
+
+ popq %r11
+ popq %r10
+ popq %r9
+ popq %r8
+ popq %rax
+ popq %rcx
+ popq %rdx
+ popq %rsi
+ popq %rdi
+ popq %rbp
+ RET
+SYM_FUNC_END(\name)
+ _ASM_NOKPROBE(\name)
+.endm
+
+#else /* CONFIG_X86_32 */
+
+/* put return address in eax (arg1) */
+.macro THUNK name, func, put_ret_addr_in_eax=0
+SYM_CODE_START_NOALIGN(\name)
+ pushl %eax
+ pushl %ecx
+ pushl %edx
+
+ .if \put_ret_addr_in_eax
+ /* Place EIP in the arg1 */
+ movl 3*4(%esp), %eax
+ .endif
+
+ call \func
+ popl %edx
+ popl %ecx
+ popl %eax
+ RET
+ _ASM_NOKPROBE(\name)
+SYM_CODE_END(\name)
+ .endm
+
+#endif
diff --git a/arch/x86/entry/entry.S b/arch/x86/entry/entry.S
index 003379049924..d9feadffa972 100644
--- a/arch/x86/entry/entry.S
+++ b/arch/x86/entry/entry.S
@@ -10,6 +10,8 @@
#include <asm/segment.h>
#include <asm/cache.h>
+#include "calling.h"
+
.pushsection .noinstr.text, "ax"
SYM_FUNC_START(entry_ibpb)
@@ -43,3 +45,4 @@ EXPORT_SYMBOL_GPL(mds_verw_sel);
.popsection
+THUNK warn_thunk_thunk, __warn_thunk
diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S
index b8be0164385c..d3a814efbff6 100644
--- a/arch/x86/entry/entry_32.S
+++ b/arch/x86/entry/entry_32.S
@@ -305,7 +305,7 @@
.macro CHECK_AND_APPLY_ESPFIX
#ifdef CONFIG_X86_ESPFIX32
#define GDT_ESPFIX_OFFSET (GDT_ENTRY_ESPFIX_SS * 8)
-#define GDT_ESPFIX_SS PER_CPU_VAR(gdt_page) + GDT_ESPFIX_OFFSET
+#define GDT_ESPFIX_SS PER_CPU_VAR(gdt_page + GDT_ESPFIX_OFFSET)
ALTERNATIVE "jmp .Lend_\@", "", X86_BUG_ESPFIX
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index a19ed151a813..8af2a26b24f6 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -191,7 +191,7 @@ SYM_FUNC_START(__switch_to_asm)
#ifdef CONFIG_STACKPROTECTOR
movq TASK_stack_canary(%rsi), %rbx
- movq %rbx, PER_CPU_VAR(fixed_percpu_data) + FIXED_stack_canary
+ movq %rbx, PER_CPU_VAR(fixed_percpu_data + FIXED_stack_canary)
#endif
/*
@@ -561,7 +561,7 @@ SYM_INNER_LABEL(swapgs_restore_regs_and_return_to_usermode, SYM_L_GLOBAL)
#ifdef CONFIG_XEN_PV
ALTERNATIVE "", "jmp xenpv_restore_regs_and_return_to_usermode", X86_FEATURE_XENPV
#endif
-#ifdef CONFIG_PAGE_TABLE_ISOLATION
+#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION
ALTERNATIVE "", "jmp .Lpti_restore_regs_and_return_to_usermode", X86_FEATURE_PTI
#endif
@@ -578,7 +578,7 @@ SYM_INNER_LABEL(swapgs_restore_regs_and_return_to_usermode, SYM_L_GLOBAL)
jnz .Lnative_iret
ud2
-#ifdef CONFIG_PAGE_TABLE_ISOLATION
+#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION
.Lpti_restore_regs_and_return_to_usermode:
POP_REGS pop_rdi=0
@@ -1098,7 +1098,7 @@ SYM_CODE_END(error_return)
*
* Registers:
* %r14: Used to save/restore the CR3 of the interrupted context
- * when PAGE_TABLE_ISOLATION is in use. Do not clobber.
+ * when MITIGATION_PAGE_TABLE_ISOLATION is in use. Do not clobber.
*/
SYM_CODE_START(asm_exc_nmi)
UNWIND_HINT_IRET_ENTRY
diff --git a/arch/x86/entry/thunk_32.S b/arch/x86/entry/thunk_32.S
index 0103e103a657..da37f42f4549 100644
--- a/arch/x86/entry/thunk_32.S
+++ b/arch/x86/entry/thunk_32.S
@@ -4,33 +4,15 @@
* Copyright 2008 by Steven Rostedt, Red Hat, Inc
* (inspired by Andi Kleen's thunk_64.S)
*/
- #include <linux/export.h>
- #include <linux/linkage.h>
- #include <asm/asm.h>
- /* put return address in eax (arg1) */
- .macro THUNK name, func, put_ret_addr_in_eax=0
-SYM_CODE_START_NOALIGN(\name)
- pushl %eax
- pushl %ecx
- pushl %edx
+#include <linux/export.h>
+#include <linux/linkage.h>
+#include <asm/asm.h>
- .if \put_ret_addr_in_eax
- /* Place EIP in the arg1 */
- movl 3*4(%esp), %eax
- .endif
+#include "calling.h"
- call \func
- popl %edx
- popl %ecx
- popl %eax
- RET
- _ASM_NOKPROBE(\name)
-SYM_CODE_END(\name)
- .endm
-
- THUNK preempt_schedule_thunk, preempt_schedule
- THUNK preempt_schedule_notrace_thunk, preempt_schedule_notrace
- EXPORT_SYMBOL(preempt_schedule_thunk)
- EXPORT_SYMBOL(preempt_schedule_notrace_thunk)
+THUNK preempt_schedule_thunk, preempt_schedule
+THUNK preempt_schedule_notrace_thunk, preempt_schedule_notrace
+EXPORT_SYMBOL(preempt_schedule_thunk)
+EXPORT_SYMBOL(preempt_schedule_notrace_thunk)
diff --git a/arch/x86/entry/thunk_64.S b/arch/x86/entry/thunk_64.S
index 416b400f39db..119ebdc3d362 100644
--- a/arch/x86/entry/thunk_64.S
+++ b/arch/x86/entry/thunk_64.S
@@ -9,39 +9,6 @@
#include "calling.h"
#include <asm/asm.h>
- /* rdi: arg1 ... normal C conventions. rax is saved/restored. */
- .macro THUNK name, func
-SYM_FUNC_START(\name)
- pushq %rbp
- movq %rsp, %rbp
-
- pushq %rdi
- pushq %rsi
- pushq %rdx
- pushq %rcx
- pushq %rax
- pushq %r8
- pushq %r9
- pushq %r10
- pushq %r11
-
- call \func
-
- popq %r11
- popq %r10
- popq %r9
- popq %r8
- popq %rax
- popq %rcx
- popq %rdx
- popq %rsi
- popq %rdi
- popq %rbp
- RET
-SYM_FUNC_END(\name)
- _ASM_NOKPROBE(\name)
- .endm
-
THUNK preempt_schedule_thunk, preempt_schedule
THUNK preempt_schedule_notrace_thunk, preempt_schedule_notrace
EXPORT_SYMBOL(preempt_schedule_thunk)
diff --git a/arch/x86/entry/vdso/Makefile b/arch/x86/entry/vdso/Makefile
index b1b8dd1608f7..620f6257bbe9 100644
--- a/arch/x86/entry/vdso/Makefile
+++ b/arch/x86/entry/vdso/Makefile
@@ -3,7 +3,7 @@
# Building vDSO images for x86.
#
-# Include the generic Makefile to check the built vdso.
+# Include the generic Makefile to check the built vDSO:
include $(srctree)/lib/vdso/Makefile
# Sanitizer runtimes are unavailable and cannot be linked here.
@@ -18,48 +18,39 @@ OBJECT_FILES_NON_STANDARD := y
# Prevents link failures: __sanitizer_cov_trace_pc() is not linked in.
KCOV_INSTRUMENT := n
-VDSO64-$(CONFIG_X86_64) := y
-VDSOX32-$(CONFIG_X86_X32_ABI) := y
-VDSO32-$(CONFIG_X86_32) := y
-VDSO32-$(CONFIG_IA32_EMULATION) := y
-
-# files to link into the vdso
+# Files to link into the vDSO:
vobjs-y := vdso-note.o vclock_gettime.o vgetcpu.o
vobjs32-y := vdso32/note.o vdso32/system_call.o vdso32/sigreturn.o
vobjs32-y += vdso32/vclock_gettime.o vdso32/vgetcpu.o
vobjs-$(CONFIG_X86_SGX) += vsgx.o
-# files to link into kernel
-obj-y += vma.o extable.o
-KASAN_SANITIZE_vma.o := y
-UBSAN_SANITIZE_vma.o := y
-KCSAN_SANITIZE_vma.o := y
-OBJECT_FILES_NON_STANDARD_vma.o := n
-OBJECT_FILES_NON_STANDARD_extable.o := n
+# Files to link into the kernel:
+obj-y += vma.o extable.o
+KASAN_SANITIZE_vma.o := y
+UBSAN_SANITIZE_vma.o := y
+KCSAN_SANITIZE_vma.o := y
+
+OBJECT_FILES_NON_STANDARD_vma.o := n
+OBJECT_FILES_NON_STANDARD_extable.o := n
-# vDSO images to build
-vdso_img-$(VDSO64-y) += 64
-vdso_img-$(VDSOX32-y) += x32
-vdso_img-$(VDSO32-y) += 32
+# vDSO images to build:
+obj-$(CONFIG_X86_64) += vdso-image-64.o
+obj-$(CONFIG_X86_X32_ABI) += vdso-image-x32.o
+obj-$(CONFIG_COMPAT_32) += vdso-image-32.o vdso32-setup.o
-obj-$(VDSO32-y) += vdso32-setup.o
-OBJECT_FILES_NON_STANDARD_vdso32-setup.o := n
+OBJECT_FILES_NON_STANDARD_vdso-image-32.o := n
+OBJECT_FILES_NON_STANDARD_vdso-image-64.o := n
+OBJECT_FILES_NON_STANDARD_vdso32-setup.o := n
-vobjs := $(foreach F,$(vobjs-y),$(obj)/$F)
-vobjs32 := $(foreach F,$(vobjs32-y),$(obj)/$F)
+vobjs := $(addprefix $(obj)/, $(vobjs-y))
+vobjs32 := $(addprefix $(obj)/, $(vobjs32-y))
$(obj)/vdso.o: $(obj)/vdso.so
targets += vdso.lds $(vobjs-y)
targets += vdso32/vdso32.lds $(vobjs32-y)
-# Build the vDSO image C files and link them in.
-vdso_img_objs := $(vdso_img-y:%=vdso-image-%.o)
-vdso_img_cfiles := $(vdso_img-y:%=vdso-image-%.c)
-vdso_img_sodbg := $(vdso_img-y:%=vdso%.so.dbg)
-obj-y += $(vdso_img_objs)
-targets += $(vdso_img_cfiles)
-targets += $(vdso_img_sodbg) $(vdso_img-y:%=vdso%.so)
+targets += $(foreach x, 64 x32 32, vdso-image-$(x).c vdso$(x).so vdso$(x).so.dbg)
CPPFLAGS_vdso.lds += -P -C
@@ -87,7 +78,7 @@ CFL := $(PROFILING) -mcmodel=small -fPIC -O2 -fasynchronous-unwind-tables -m64 \
-fno-omit-frame-pointer -foptimize-sibling-calls \
-DDISABLE_BRANCH_PROFILING -DBUILD_VDSO
-ifdef CONFIG_RETPOLINE
+ifdef CONFIG_MITIGATION_RETPOLINE
ifneq ($(RETPOLINE_VDSO_CFLAGS),)
CFL += $(RETPOLINE_VDSO_CFLAGS)
endif
@@ -123,7 +114,7 @@ VDSO_LDFLAGS_vdsox32.lds = -m elf32_x86_64 -soname linux-vdso.so.1 \
vobjx32s-y := $(vobjs-y:.o=-x32.o)
# same thing, but in the output directory
-vobjx32s := $(foreach F,$(vobjx32s-y),$(obj)/$F)
+vobjx32s := $(addprefix $(obj)/, $(vobjx32s-y))
# Convert 64bit object file to x32 for x32 vDSO.
quiet_cmd_x32 = X32 $@
@@ -164,7 +155,7 @@ KBUILD_CFLAGS_32 += $(call cc-option, -foptimize-sibling-calls)
KBUILD_CFLAGS_32 += -fno-omit-frame-pointer
KBUILD_CFLAGS_32 += -DDISABLE_BRANCH_PROFILING
-ifdef CONFIG_RETPOLINE
+ifdef CONFIG_MITIGATION_RETPOLINE
ifneq ($(RETPOLINE_VDSO_CFLAGS),)
KBUILD_CFLAGS_32 += $(RETPOLINE_VDSO_CFLAGS)
endif
@@ -190,5 +181,3 @@ GCOV_PROFILE := n
quiet_cmd_vdso_and_check = VDSO $@
cmd_vdso_and_check = $(cmd_vdso); $(cmd_vdso_check)
-
-clean-files := vdso32.so vdso32.so.dbg vdso64* vdso-image-*.c vdsox32.so*
diff --git a/arch/x86/entry/vdso/vma.c b/arch/x86/entry/vdso/vma.c
index 7645730dc228..6d83ceb7f1ba 100644
--- a/arch/x86/entry/vdso/vma.c
+++ b/arch/x86/entry/vdso/vma.c
@@ -274,59 +274,6 @@ up_fail:
return ret;
}
-#ifdef CONFIG_X86_64
-/*
- * Put the vdso above the (randomized) stack with another randomized
- * offset. This way there is no hole in the middle of address space.
- * To save memory make sure it is still in the same PTE as the stack
- * top. This doesn't give that many random bits.
- *
- * Note that this algorithm is imperfect: the distribution of the vdso
- * start address within a PMD is biased toward the end.
- *
- * Only used for the 64-bit and x32 vdsos.
- */
-static unsigned long vdso_addr(unsigned long start, unsigned len)
-{
- unsigned long addr, end;
- unsigned offset;
-
- /*
- * Round up the start address. It can start out unaligned as a result
- * of stack start randomization.
- */
- start = PAGE_ALIGN(start);
-
- /* Round the lowest possible end address up to a PMD boundary. */
- end = (start + len + PMD_SIZE - 1) & PMD_MASK;
- if (end >= DEFAULT_MAP_WINDOW)
- end = DEFAULT_MAP_WINDOW;
- end -= len;
-
- if (end > start) {
- offset = get_random_u32_below(((end - start) >> PAGE_SHIFT) + 1);
- addr = start + (offset << PAGE_SHIFT);
- } else {
- addr = start;
- }
-
- /*
- * Forcibly align the final address in case we have a hardware
- * issue that requires alignment for performance reasons.
- */
- addr = align_vdso_addr(addr);
-
- return addr;
-}
-
-static int map_vdso_randomized(const struct vdso_image *image)
-{
- unsigned long addr = vdso_addr(current->mm->start_stack, image->size-image->sym_vvar_start);
-
- return map_vdso(image, addr);
-}
-#endif
-
int map_vdso_once(const struct vdso_image *image, unsigned long addr)
{
struct mm_struct *mm = current->mm;
@@ -369,7 +316,7 @@ int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
if (!vdso64_enabled)
return 0;
- return map_vdso_randomized(&vdso_image_64);
+ return map_vdso(&vdso_image_64, 0);
}
#ifdef CONFIG_COMPAT
@@ -380,7 +327,7 @@ int compat_arch_setup_additional_pages(struct linux_binprm *bprm,
if (x32) {
if (!vdso64_enabled)
return 0;
- return map_vdso_randomized(&vdso_image_x32);
+ return map_vdso(&vdso_image_x32, 0);
}
#endif
#ifdef CONFIG_IA32_EMULATION