summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
-rw-r--r--arch/x86/Kconfig31
-rw-r--r--arch/x86/Makefile20
-rw-r--r--arch/x86/boot/compressed/misc.c14
-rw-r--r--arch/x86/entry/entry.S2
-rw-r--r--arch/x86/entry/entry_64.S2
-rw-r--r--arch/x86/include/asm/desc.h1
-rw-r--r--arch/x86/include/asm/elf.h5
-rw-r--r--arch/x86/include/asm/percpu.h68
-rw-r--r--arch/x86/include/asm/processor.h28
-rw-r--r--arch/x86/include/asm/stackprotector.h36
-rw-r--r--arch/x86/kernel/Makefile2
-rw-r--r--arch/x86/kernel/asm-offsets_64.c6
-rw-r--r--arch/x86/kernel/cpu/common.c9
-rw-r--r--arch/x86/kernel/head64.c2
-rw-r--r--arch/x86/kernel/head_64.S20
-rw-r--r--arch/x86/kernel/ioport.c2
-rw-r--r--arch/x86/kernel/irq_64.c1
-rw-r--r--arch/x86/kernel/module.c15
-rw-r--r--arch/x86/kernel/setup_percpu.c12
-rw-r--r--arch/x86/kernel/signal_32.c62
-rw-r--r--arch/x86/kernel/vmlinux.lds.S35
-rw-r--r--arch/x86/platform/pvh/head.S14
-rw-r--r--arch/x86/tools/relocs.c147
-rw-r--r--arch/x86/xen/xen-head.S10
-rw-r--r--include/asm-generic/sections.h2
-rw-r--r--include/asm-generic/vmlinux.lds.h38
-rw-r--r--include/linux/percpu-defs.h12
-rw-r--r--init/Kconfig5
-rw-r--r--kernel/bpf/verifier.c2
-rw-r--r--kernel/kallsyms.c12
-rw-r--r--mm/percpu.c4
-rwxr-xr-xscripts/gcc-x86_32-has-stack-protector.sh8
-rwxr-xr-xscripts/gcc-x86_64-has-stack-protector.sh4
-rw-r--r--scripts/kallsyms.c72
-rwxr-xr-xscripts/link-vmlinux.sh4
-rwxr-xr-xscripts/min-tool-version.sh4
-rw-r--r--tools/testing/selftests/x86/lam.c4
37 files changed, 181 insertions, 534 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 017035f461cf..79f6febd177f 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -286,7 +286,7 @@ config X86
select HAVE_FUNCTION_ARG_ACCESS_API
select HAVE_SETUP_PER_CPU_AREA
select HAVE_SOFTIRQ_ON_OWN_STACK
- select HAVE_STACKPROTECTOR if CC_HAS_SANE_STACKPROTECTOR
+ select HAVE_STACKPROTECTOR
select HAVE_STACK_VALIDATION if HAVE_OBJTOOL
select HAVE_STATIC_CALL
select HAVE_STATIC_CALL_INLINE if HAVE_OBJTOOL
@@ -427,15 +427,6 @@ config PGTABLE_LEVELS
default 3 if X86_PAE
default 2
-config CC_HAS_SANE_STACKPROTECTOR
- bool
- default $(success,$(srctree)/scripts/gcc-x86_64-has-stack-protector.sh $(CC) $(CLANG_FLAGS)) if 64BIT
- default $(success,$(srctree)/scripts/gcc-x86_32-has-stack-protector.sh $(CC) $(CLANG_FLAGS))
- help
- We have to make sure stack protector is unconditionally disabled if
- the compiler produces broken code or if it does not let us control
- the segment on 32-bit kernels.
-
menu "Processor type and features"
config SMP
@@ -2377,18 +2368,20 @@ config CC_HAS_NAMED_AS
def_bool $(success,echo 'int __seg_fs fs; int __seg_gs gs;' | $(CC) -x c - -S -o /dev/null)
depends on CC_IS_GCC
+#
+# -fsanitize=kernel-address (KASAN) and -fsanitize=thread (KCSAN)
+# are incompatible with named address spaces with GCC < 13.3
+# (see GCC PR sanitizer/111736 and also PR sanitizer/115172).
+#
+
config CC_HAS_NAMED_AS_FIXED_SANITIZERS
- def_bool CC_IS_GCC && GCC_VERSION >= 130300
+ def_bool y
+ depends on !(KASAN || KCSAN) || GCC_VERSION >= 130300
+ depends on !(UBSAN_BOOL && KASAN) || GCC_VERSION >= 140200
config USE_X86_SEG_SUPPORT
- def_bool y
- depends on CC_HAS_NAMED_AS
- #
- # -fsanitize=kernel-address (KASAN) and -fsanitize=thread
- # (KCSAN) are incompatible with named address spaces with
- # GCC < 13.3 - see GCC PR sanitizer/111736.
- #
- depends on !(KASAN || KCSAN) || CC_HAS_NAMED_AS_FIXED_SANITIZERS
+ def_bool CC_HAS_NAMED_AS
+ depends on CC_HAS_NAMED_AS_FIXED_SANITIZERS
config CC_HAS_SLS
def_bool $(cc-option,-mharden-sls=all)
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index 8120085b00a4..6784129328f6 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -140,14 +140,7 @@ ifeq ($(CONFIG_X86_32),y)
# temporary until string.h is fixed
KBUILD_CFLAGS += -ffreestanding
- ifeq ($(CONFIG_STACKPROTECTOR),y)
- ifeq ($(CONFIG_SMP),y)
- KBUILD_CFLAGS += -mstack-protector-guard-reg=fs \
- -mstack-protector-guard-symbol=__ref_stack_chk_guard
- else
- KBUILD_CFLAGS += -mstack-protector-guard=global
- endif
- endif
+ percpu_seg := fs
else
BITS := 64
UTS_MACHINE := x86_64
@@ -185,6 +178,17 @@ else
KBUILD_CFLAGS += -mcmodel=kernel
KBUILD_RUSTFLAGS += -Cno-redzone=y
KBUILD_RUSTFLAGS += -Ccode-model=kernel
+
+ percpu_seg := gs
+endif
+
+ifeq ($(CONFIG_STACKPROTECTOR),y)
+ ifeq ($(CONFIG_SMP),y)
+ KBUILD_CFLAGS += -mstack-protector-guard-reg=$(percpu_seg)
+ KBUILD_CFLAGS += -mstack-protector-guard-symbol=__ref_stack_chk_guard
+ else
+ KBUILD_CFLAGS += -mstack-protector-guard=global
+ endif
endif
#
diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c
index 0d37420cad02..1cdcd4aaf395 100644
--- a/arch/x86/boot/compressed/misc.c
+++ b/arch/x86/boot/compressed/misc.c
@@ -235,7 +235,7 @@ static void handle_relocations(void *output, unsigned long output_len,
/*
* Process relocations: 32 bit relocations first then 64 bit after.
- * Three sets of binary relocations are added to the end of the kernel
+ * Two sets of binary relocations are added to the end of the kernel
* before compression. Each relocation table entry is the kernel
* address of the location which needs to be updated stored as a
* 32-bit value which is sign extended to 64 bits.
@@ -245,8 +245,6 @@ static void handle_relocations(void *output, unsigned long output_len,
* kernel bits...
* 0 - zero terminator for 64 bit relocations
* 64 bit relocation repeated
- * 0 - zero terminator for inverse 32 bit relocations
- * 32 bit inverse relocation repeated
* 0 - zero terminator for 32 bit relocations
* 32 bit relocation repeated
*
@@ -263,16 +261,6 @@ static void handle_relocations(void *output, unsigned long output_len,
*(uint32_t *)ptr += delta;
}
#ifdef CONFIG_X86_64
- while (*--reloc) {
- long extended = *reloc;
- extended += map;
-
- ptr = (unsigned long)extended;
- if (ptr < min_addr || ptr > max_addr)
- error("inverse 32-bit relocation outside of kernel!\n");
-
- *(int32_t *)ptr -= delta;
- }
for (reloc--; *reloc; reloc--) {
long extended = *reloc;
extended += map;
diff --git a/arch/x86/entry/entry.S b/arch/x86/entry/entry.S
index b7ea3e8e9ecc..fe5344a249a1 100644
--- a/arch/x86/entry/entry.S
+++ b/arch/x86/entry/entry.S
@@ -52,7 +52,6 @@ EXPORT_SYMBOL_GPL(mds_verw_sel);
THUNK warn_thunk_thunk, __warn_thunk
-#ifndef CONFIG_X86_64
/*
* Clang's implementation of TLS stack cookies requires the variable in
* question to be a TLS variable. If the variable happens to be defined as an
@@ -66,4 +65,3 @@ THUNK warn_thunk_thunk, __warn_thunk
#ifdef CONFIG_STACKPROTECTOR
EXPORT_SYMBOL(__ref_stack_chk_guard);
#endif
-#endif
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index f52dbe0ad93c..33a955aa01d8 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -192,7 +192,7 @@ 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(__stack_chk_guard)
#endif
/*
diff --git a/arch/x86/include/asm/desc.h b/arch/x86/include/asm/desc.h
index 62dc9f59ea76..ec95fe44fa3a 100644
--- a/arch/x86/include/asm/desc.h
+++ b/arch/x86/include/asm/desc.h
@@ -46,7 +46,6 @@ struct gdt_page {
} __attribute__((aligned(PAGE_SIZE)));
DECLARE_PER_CPU_PAGE_ALIGNED(struct gdt_page, gdt_page);
-DECLARE_INIT_PER_CPU(gdt_page);
/* Provide the original GDT */
static inline struct desc_struct *get_cpu_gdt_rw(unsigned int cpu)
diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h
index 1fb83d47711f..128602612eca 100644
--- a/arch/x86/include/asm/elf.h
+++ b/arch/x86/include/asm/elf.h
@@ -54,8 +54,9 @@ typedef struct user_i387_struct elf_fpregset_t;
#define R_X86_64_GLOB_DAT 6 /* Create GOT entry */
#define R_X86_64_JUMP_SLOT 7 /* Create PLT entry */
#define R_X86_64_RELATIVE 8 /* Adjust by program base */
-#define R_X86_64_GOTPCREL 9 /* 32 bit signed pc relative
- offset to GOT */
+#define R_X86_64_GOTPCREL 9 /* 32 bit signed pc relative offset to GOT */
+#define R_X86_64_GOTPCRELX 41
+#define R_X86_64_REX_GOTPCRELX 42
#define R_X86_64_32 10 /* Direct 32 bit zero extended */
#define R_X86_64_32S 11 /* Direct 32 bit sign extended */
#define R_X86_64_16 12 /* Direct 16 bit zero extended */
diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h
index e525cd85f999..7cb4f64b2e60 100644
--- a/arch/x86/include/asm/percpu.h
+++ b/arch/x86/include/asm/percpu.h
@@ -20,14 +20,9 @@
#define PER_CPU_VAR(var) __percpu(var)__percpu_rel
-#ifdef CONFIG_X86_64_SMP
-# define INIT_PER_CPU_VAR(var) init_per_cpu__##var
-#else
-# define INIT_PER_CPU_VAR(var) var
-#endif
-
#else /* !__ASSEMBLY__: */
+#include <linux/args.h>
#include <linux/build_bug.h>
#include <linux/stringify.h>
#include <asm/asm.h>
@@ -41,12 +36,7 @@
# define __seg_fs __attribute__((address_space(__seg_fs)))
#endif
-#ifdef CONFIG_X86_64
-# define __percpu_seg_override __seg_gs
-#else
-# define __percpu_seg_override __seg_fs
-#endif
-
+#define __percpu_seg_override CONCATENATE(__seg_, __percpu_seg)
#define __percpu_prefix ""
#else /* !CONFIG_CC_HAS_NAMED_AS: */
@@ -98,22 +88,6 @@
#define __force_percpu_arg(x) __force_percpu_prefix "%" #x
/*
- * Initialized pointers to per-CPU variables needed for the boot
- * processor need to use these macros to get the proper address
- * offset from __per_cpu_load on SMP.
- *
- * There also must be an entry in vmlinux_64.lds.S
- */
-#define DECLARE_INIT_PER_CPU(var) \
- extern typeof(var) init_per_cpu_var(var)
-
-#ifdef CONFIG_X86_64_SMP
-# define init_per_cpu_var(var) init_per_cpu__##var
-#else
-# define init_per_cpu_var(var) var
-#endif
-
-/*
* For arch-specific code, we can use direct single-insn ops (they
* don't give an lvalue though).
*/
@@ -128,15 +102,10 @@
#define __pcpu_cast_4(val) ((u32)(((unsigned long) val) & 0xffffffff))
#define __pcpu_cast_8(val) ((u64)(val))
-#define __pcpu_op1_1(op, dst) op "b " dst
-#define __pcpu_op1_2(op, dst) op "w " dst
-#define __pcpu_op1_4(op, dst) op "l " dst
-#define __pcpu_op1_8(op, dst) op "q " dst
-
-#define __pcpu_op2_1(op, src, dst) op "b " src ", " dst
-#define __pcpu_op2_2(op, src, dst) op "w " src ", " dst
-#define __pcpu_op2_4(op, src, dst) op "l " src ", " dst
-#define __pcpu_op2_8(op, src, dst) op "q " src ", " dst
+#define __pcpu_op_1(op) op "b "
+#define __pcpu_op_2(op) op "w "
+#define __pcpu_op_4(op) op "l "
+#define __pcpu_op_8(op) op "q "
#define __pcpu_reg_1(mod, x) mod "q" (x)
#define __pcpu_reg_2(mod, x) mod "r" (x)
@@ -168,7 +137,8 @@ do { \
({ \
__pcpu_type_##size pfo_val__; \
\
- asm qual (__pcpu_op2_##size("mov", __percpu_arg([var]), "%[val]") \
+ asm qual (__pcpu_op_##size("mov") \
+ __percpu_arg([var]) ", %[val]" \
: [val] __pcpu_reg_##size("=", pfo_val__) \
: [var] "m" (__my_cpu_var(_var))); \
\
@@ -184,7 +154,8 @@ do { \
pto_tmp__ = (_val); \
(void)pto_tmp__; \
} \
- asm qual(__pcpu_op2_##size("mov", "%[val]", __percpu_arg([var])) \
+ asm qual (__pcpu_op_##size("mov") "%[val], " \
+ __percpu_arg([var]) \
: [var] "=m" (__my_cpu_var(_var)) \
: [val] __pcpu_reg_imm_##size(pto_val__)); \
} while (0)
@@ -201,7 +172,8 @@ do { \
({ \
__pcpu_type_##size pfo_val__; \
\
- asm(__pcpu_op2_##size("mov", __force_percpu_arg(a[var]), "%[val]") \
+ asm(__pcpu_op_##size("mov") \
+ __force_percpu_arg(a[var]) ", %[val]" \
: [val] __pcpu_reg_##size("=", pfo_val__) \
: [var] "i" (&(_var))); \
\
@@ -210,7 +182,7 @@ do { \
#define percpu_unary_op(size, qual, op, _var) \
({ \
- asm qual (__pcpu_op1_##size(op, __percpu_arg([var])) \
+ asm qual (__pcpu_op_##size(op) __percpu_arg([var]) \
: [var] "+m" (__my_cpu_var(_var))); \
})
@@ -223,7 +195,7 @@ do { \
pto_tmp__ = (_val); \
(void)pto_tmp__; \
} \
- asm qual(__pcpu_op2_##size(op, "%[val]", __percpu_arg([var])) \
+ asm qual (__pcpu_op_##size(op) "%[val], " __percpu_arg([var]) \
: [var] "+m" (__my_cpu_var(_var)) \
: [val] __pcpu_reg_imm_##size(pto_val__)); \
} while (0)
@@ -259,8 +231,8 @@ do { \
({ \
__pcpu_type_##size paro_tmp__ = __pcpu_cast_##size(_val); \
\
- asm qual (__pcpu_op2_##size("xadd", "%[tmp]", \
- __percpu_arg([var])) \
+ asm qual (__pcpu_op_##size("xadd") "%[tmp], " \
+ __percpu_arg([var]) \
: [tmp] __pcpu_reg_##size("+", paro_tmp__), \
[var] "+m" (__my_cpu_var(_var)) \
: : "memory"); \
@@ -303,8 +275,8 @@ do { \
__pcpu_type_##size pco_old__ = __pcpu_cast_##size(_oval); \
__pcpu_type_##size pco_new__ = __pcpu_cast_##size(_nval); \
\
- asm qual (__pcpu_op2_##size("cmpxchg", "%[nval]", \
- __percpu_arg([var])) \
+ asm qual (__pcpu_op_##size("cmpxchg") "%[nval], " \
+ __percpu_arg([var]) \
: [oval] "+a" (pco_old__), \
[var] "+m" (__my_cpu_var(_var)) \
: [nval] __pcpu_reg_##size(, pco_new__) \
@@ -320,8 +292,8 @@ do { \
__pcpu_type_##size pco_old__ = *pco_oval__; \
__pcpu_type_##size pco_new__ = __pcpu_cast_##size(_nval); \
\
- asm qual (__pcpu_op2_##size("cmpxchg", "%[nval]", \
- __percpu_arg([var])) \
+ asm qual (__pcpu_op_##size("cmpxchg") "%[nval], " \
+ __percpu_arg([var]) \
CC_SET(z) \
: CC_OUT(z) (success), \
[oval] "+a" (pco_old__), \
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index d5d9a071cddc..8f7023438626 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -416,36 +416,20 @@ struct irq_stack {
} __aligned(IRQ_STACK_SIZE);
#ifdef CONFIG_X86_64
-struct fixed_percpu_data {
- /*
- * GCC hardcodes the stack canary as %gs:40. Since the
- * irq_stack is the object at %gs:0, we reserve the bottom
- * 48 bytes of the irq stack for the canary.
- *
- * Once we are willing to require -mstack-protector-guard-symbol=
- * support for x86_64 stackprotector, we can get rid of this.
- */
- char gs_base[40];
- unsigned long stack_canary;
-};
-
-DECLARE_PER_CPU_FIRST(struct fixed_percpu_data, fixed_percpu_data) __visible;
-DECLARE_INIT_PER_CPU(fixed_percpu_data);
-
static inline unsigned long cpu_kernelmode_gs_base(int cpu)
{
- return (unsigned long)per_cpu(fixed_percpu_data.gs_base, cpu);
+#ifdef CONFIG_SMP
+ return per_cpu_offset(cpu);
+#else
+ return 0;
+#endif
}
extern asmlinkage void entry_SYSCALL32_ignore(void);
/* Save actual FS/GS selectors and bases to current->thread */
void current_save_fsgs(void);
-#else /* X86_64 */
-#ifdef CONFIG_STACKPROTECTOR
-DECLARE_PER_CPU(unsigned long, __stack_chk_guard);
-#endif
-#endif /* !X86_64 */
+#endif /* X86_64 */
struct perf_event;
diff --git a/arch/x86/include/asm/stackprotector.h b/arch/x86/include/asm/stackprotector.h
index 00473a650f51..d43fb589fcf6 100644
--- a/arch/x86/include/asm/stackprotector.h
+++ b/arch/x86/include/asm/stackprotector.h
@@ -2,26 +2,10 @@
/*
* GCC stack protector support.
*
- * Stack protector works by putting predefined pattern at the start of
+ * Stack protector works by putting a predefined pattern at the start of
* the stack frame and verifying that it hasn't been overwritten when
- * returning from the function. The pattern is called stack canary
- * and unfortunately gcc historically required it to be at a fixed offset
- * from the percpu segment base. On x86_64, the offset is 40 bytes.
- *
- * The same segment is shared by percpu area and stack canary. On
- * x86_64, percpu symbols are zero based and %gs (64-bit) points to the
- * base of percpu area. The first occupant of the percpu area is always
- * fixed_percpu_data which contains stack_canary at the appropriate
- * offset. On x86_32, the stack canary is just a regular percpu
- * variable.
- *
- * Putting percpu data in %fs on 32-bit is a minor optimization compared to
- * using %gs. Since 32-bit userspace normally has %fs == 0, we are likely
- * to load 0 into %fs on exit to usermode, whereas with percpu data in
- * %gs, we are likely to load a non-null %gs on return to user mode.
- *
- * Once we are willing to require GCC 8.1 or better for 64-bit stackprotector
- * support, we can remove some of this complexity.
+ * returning from the function. The pattern is called the stack canary
+ * and is a unique value for each task.
*/
#ifndef _ASM_STACKPROTECTOR_H
@@ -36,6 +20,8 @@
#include <linux/sched.h>
+DECLARE_PER_CPU(unsigned long, __stack_chk_guard);
+
/*
* Initialize the stackprotector canary value.
*
@@ -51,25 +37,13 @@ static __always_inline void boot_init_stack_canary(void)
{
unsigned long canary = get_random_canary();
-#ifdef CONFIG_X86_64
- BUILD_BUG_ON(offsetof(struct fixed_percpu_data, stack_canary) != 40);
-#endif
-
current->stack_canary = canary;
-#ifdef CONFIG_X86_64
- this_cpu_write(fixed_percpu_data.stack_canary, canary);
-#else
this_cpu_write(__stack_chk_guard, canary);
-#endif
}
static inline void cpu_init_stack_canary(int cpu, struct task_struct *idle)
{
-#ifdef CONFIG_X86_64
- per_cpu(fixed_percpu_data.stack_canary, cpu) = idle->stack_canary;
-#else
per_cpu(__stack_chk_guard, cpu) = idle->stack_canary;
-#endif
}
#else /* STACKPROTECTOR */
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index b43eb7e384eb..84cfa179802c 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -44,6 +44,8 @@ KCOV_INSTRUMENT_unwind_orc.o := n
KCOV_INSTRUMENT_unwind_frame.o := n
KCOV_INSTRUMENT_unwind_guess.o := n
+CFLAGS_head32.o := -fno-stack-protector
+CFLAGS_head64.o := -fno-stack-protector
CFLAGS_irq.o := -I $(src)/../include/asm/trace
obj-y += head_$(BITS).o
diff --git a/arch/x86/kernel/asm-offsets_64.c b/arch/x86/kernel/asm-offsets_64.c
index bb65371ea9df..590b6cd0eac0 100644
--- a/arch/x86/kernel/asm-offsets_64.c
+++ b/arch/x86/kernel/asm-offsets_64.c
@@ -54,11 +54,5 @@ int main(void)
BLANK();
#undef ENTRY
- BLANK();
-
-#ifdef CONFIG_STACKPROTECTOR
- OFFSET(FIXED_stack_canary, fixed_percpu_data, stack_canary);
- BLANK();
-#endif
return 0;
}
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 5f81c553e733..88a6707b765c 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -2073,10 +2073,6 @@ EXPORT_PER_CPU_SYMBOL(pcpu_hot);
EXPORT_PER_CPU_SYMBOL(const_pcpu_hot);
#ifdef CONFIG_X86_64
-DEFINE_PER_CPU_FIRST(struct fixed_percpu_data,
- fixed_percpu_data) __aligned(PAGE_SIZE) __visible;
-EXPORT_PER_CPU_SYMBOL_GPL(fixed_percpu_data);
-
static void wrmsrl_cstar(unsigned long val)
{
/*
@@ -2139,8 +2135,7 @@ void syscall_init(void)
if (!cpu_feature_enabled(X86_FEATURE_FRED))
idt_syscall_init();
}
-
-#else /* CONFIG_X86_64 */
+#endif /* CONFIG_X86_64 */
#ifdef CONFIG_STACKPROTECTOR
DEFINE_PER_CPU(unsigned long, __stack_chk_guard);
@@ -2149,8 +2144,6 @@ EXPORT_PER_CPU_SYMBOL(__stack_chk_guard);
#endif
#endif
-#endif /* CONFIG_X86_64 */
-
/*
* Clear all 6 debug registers:
*/
diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
index 22c9ba305ac1..05f8b8acf784 100644
--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -567,7 +567,7 @@ void early_setup_idt(void)
*/
void __head startup_64_setup_gdt_idt(void)
{
- struct desc_struct *gdt = (void *)(__force unsigned long)init_per_cpu_var(gdt_page.gdt);
+ struct desc_struct *gdt = (void *)(__force unsigned long)gdt_page.gdt;
void *handler = NULL;
struct desc_ptr startup_gdt_descr = {
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index 31345e0ba006..2843b0a56198 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -61,11 +61,14 @@ SYM_CODE_START_NOALIGN(startup_64)
/* Set up the stack for verify_cpu() */
leaq __top_init_kernel_stack(%rip), %rsp
- /* Setup GSBASE to allow stack canary access for C code */
+ /*
+ * Set up GSBASE.
+ * Note that on SMP the boot CPU uses the init data section until
+ * the per-CPU areas are set up.
+ */
movl $MSR_GS_BASE, %ecx
- leaq INIT_PER_CPU_VAR(fixed_percpu_data)(%rip), %rdx
- movl %edx, %eax
- shrq $32, %rdx
+ xorl %eax, %eax
+ xorl %edx, %edx
wrmsr
call startup_64_setup_gdt_idt
@@ -359,17 +362,12 @@ SYM_INNER_LABEL(common_startup_64, SYM_L_LOCAL)
movl %eax,%fs
movl %eax,%gs
- /* Set up %gs.
- *
- * The base of %gs always points to fixed_percpu_data. If the
- * stack protector canary is enabled, it is located at %gs:40.
+ /*
+ * Set up GSBASE.
* Note that, on SMP, the boot cpu uses init data section until
* the per cpu areas are set up.
*/
movl $MSR_GS_BASE,%ecx
-#ifndef CONFIG_SMP
- leaq INIT_PER_CPU_VAR(fixed_percpu_data)(%rip), %rdx
-#endif
movl %edx, %eax
shrq $32, %rdx
wrmsr
diff --git a/arch/x86/kernel/ioport.c b/arch/x86/kernel/ioport.c
index e2fab3ceb09f..6290dd120f5e 100644
--- a/arch/x86/kernel/ioport.c
+++ b/arch/x86/kernel/ioport.c
@@ -144,7 +144,7 @@ long ksys_ioperm(unsigned long from, unsigned long num, int turn_on)
* Update the sequence number to force a TSS update on return to
* user mode.
*/
- iobm->sequence = atomic64_add_return(1, &io_bitmap_sequence);
+ iobm->sequence = atomic64_inc_return(&io_bitmap_sequence);
return 0;
}
diff --git a/arch/x86/kernel/irq_64.c b/arch/x86/kernel/irq_64.c
index ade0043ce56e..56bdeecd8ee0 100644
--- a/arch/x86/kernel/irq_64.c
+++ b/arch/x86/kernel/irq_64.c
@@ -27,7 +27,6 @@
#include <asm/apic.h>
DEFINE_PER_CPU_PAGE_ALIGNED(struct irq_stack, irq_stack_backing_store) __visible;
-DECLARE_INIT_PER_CPU(irq_stack_backing_store);
#ifdef CONFIG_VMAP_STACK
/*
diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c
index 837450b6e882..9929be7a76e7 100644
--- a/arch/x86/kernel/module.c
+++ b/arch/x86/kernel/module.c
@@ -19,6 +19,7 @@
#include <linux/jump_label.h>
#include <linux/random.h>
#include <linux/memory.h>
+#include <linux/stackprotector.h>
#include <asm/text-patching.h>
#include <asm/page.h>
@@ -130,6 +131,20 @@ static int __write_relocate_add(Elf64_Shdr *sechdrs,
goto overflow;
size = 4;
break;
+#if defined(CONFIG_STACKPROTECTOR) && \
+ defined(CONFIG_CC_IS_CLANG) && CONFIG_CLANG_VERSION < 170000
+ case R_X86_64_REX_GOTPCRELX: {
+ static unsigned long __percpu *const addr = &__stack_chk_guard;
+
+ if (sym->st_value != (u64)addr) {
+ pr_err("%s: Unsupported GOTPCREL relocation\n", me->name);
+ return -ENOEXEC;
+ }
+
+ val = (u64)&addr + rel[i].r_addend;
+ fallthrough;
+ }
+#endif
case R_X86_64_PC32:
case R_X86_64_PLT32:
val -= (u64)loc;
diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c
index b30d6e180df7..1e7be9409aa2 100644
--- a/arch/x86/kernel/setup_percpu.c
+++ b/arch/x86/kernel/setup_percpu.c
@@ -23,18 +23,10 @@
#include <asm/cpumask.h>
#include <asm/cpu.h>
-#ifdef CONFIG_X86_64
-#define BOOT_PERCPU_OFFSET ((unsigned long)__per_cpu_load)
-#else
-#define BOOT_PERCPU_OFFSET 0
-#endif
-
-DEFINE_PER_CPU_READ_MOSTLY(unsigned long, this_cpu_off) = BOOT_PERCPU_OFFSET;
+DEFINE_PER_CPU_READ_MOSTLY(unsigned long, this_cpu_off);
EXPORT_PER_CPU_SYMBOL(this_cpu_off);
-unsigned long __per_cpu_offset[NR_CPUS] __ro_after_init = {
- [0 ... NR_CPUS-1] = BOOT_PERCPU_OFFSET,
-};
+unsigned long __per_cpu_offset[NR_CPUS] __ro_after_init;
EXPORT_SYMBOL(__per_cpu_offset);
/*
diff --git a/arch/x86/kernel/signal_32.c b/arch/x86/kernel/signal_32.c
index ef654530bf5a..98123ff10506 100644
--- a/arch/x86/kernel/signal_32.c
+++ b/arch/x86/kernel/signal_32.c
@@ -33,25 +33,55 @@
#include <asm/smap.h>
#include <asm/gsseg.h>
+/*
+ * The first GDT descriptor is reserved as 'NULL descriptor'. As bits 0
+ * and 1 of a segment selector, i.e., the RPL bits, are NOT used to index
+ * GDT, selector values 0~3 all point to the NULL descriptor, thus values
+ * 0, 1, 2 and 3 are all valid NULL selector values.
+ *
+ * However IRET zeros ES, FS, GS, and DS segment registers if any of them
+ * is found to have any nonzero NULL selector value, which can be used by
+ * userspace in pre-FRED systems to spot any interrupt/exception by loading
+ * a nonzero NULL selector and waiting for it to become zero. Before FRED
+ * there was nothing software could do to prevent such an information leak.
+ *
+ * ERETU, the only legit instruction to return to userspace from kernel
+ * under FRED, by design does NOT zero any segment register to avoid this
+ * problem behavior.
+ *
+ * As such, leave NULL selector values 0~3 unchanged.
+ */
+static inline u16 fixup_rpl(u16 sel)
+{
+ return sel <= 3 ? sel : sel | 3;
+}
+
#ifdef CONFIG_IA32_EMULATION
#include <asm/unistd_32_ia32.h>
static inline void reload_segments(struct sigcontext_32 *sc)
{
- unsigned int cur;
+ u16 cur;
+ /*
+ * Reload fs and gs if they have changed in the signal
+ * handler. This does not handle long fs/gs base changes in
+ * the handler, but does not clobber them at least in the
+ * normal case.
+ */
savesegment(gs, cur);
- if ((sc->gs | 0x03) != cur)
- load_gs_index(sc->gs | 0x03);
+ if (fixup_rpl(sc->gs) != cur)
+ load_gs_index(fixup_rpl(sc->gs));
savesegment(fs, cur);
- if ((sc->fs | 0x03) != cur)
- loadsegment(fs, sc->fs | 0x03);
+ if (fixup_rpl(sc->fs) != cur)
+ loadsegment(fs, fixup_rpl(sc->fs));
+
savesegment(ds, cur);
- if ((sc->ds | 0x03) != cur)
- loadsegment(ds, sc->ds | 0x03);
+ if (fixup_rpl(sc->ds) != cur)
+ loadsegment(ds, fixup_rpl(sc->ds));
savesegment(es, cur);
- if ((sc->es | 0x03) != cur)
- loadsegment(es, sc->es | 0x03);
+ if (fixup_rpl(sc->es) != cur)
+ loadsegment(es, fixup_rpl(sc->es));
}
#define sigset32_t compat_sigset_t
@@ -105,18 +135,12 @@ static bool ia32_restore_sigcontext(struct pt_regs *regs,
regs->orig_ax = -1;
#ifdef CONFIG_IA32_EMULATION
- /*
- * Reload fs and gs if they have changed in the signal
- * handler. This does not handle long fs/gs base changes in
- * the handler, but does not clobber them at least in the
- * normal case.
- */
reload_segments(&sc);
#else
- loadsegment(gs, sc.gs);
- regs->fs = sc.fs;
- regs->es = sc.es;
- regs->ds = sc.ds;
+ loadsegment(gs, fixup_rpl(sc.gs));
+ regs->fs = fixup_rpl(sc.fs);
+ regs->es = fixup_rpl(sc.es);
+ regs->ds = fixup_rpl(sc.ds);
#endif
return fpu__restore_sig(compat_ptr(sc.fpstate), 1);
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index 0deb4887d6e9..1769a7126224 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -112,12 +112,6 @@ ASSERT(__relocate_kernel_end - __relocate_kernel_start <= KEXEC_CONTROL_CODE_MAX
PHDRS {
text PT_LOAD FLAGS(5); /* R_E */
data PT_LOAD FLAGS(6); /* RW_ */
-#ifdef CONFIG_X86_64
-#ifdef CONFIG_SMP
- percpu PT_LOAD FLAGS(6); /* RW_ */
-#endif
- init PT_LOAD FLAGS(7); /* RWE */
-#endif
note PT_NOTE FLAGS(0); /* ___ */
}
@@ -216,21 +210,7 @@ SECTIONS
__init_begin = .; /* paired with __init_end */
}
-#if defined(CONFIG_X86_64) && defined(CONFIG_SMP)
- /*
- * percpu offsets are zero-based on SMP. PERCPU_VADDR() changes the
- * output PHDR, so the next output section - .init.text - should
- * start another segment - init.
- */
- PERCPU_VADDR(INTERNODE_CACHE_BYTES, 0, :percpu)
- ASSERT(SIZEOF(.data..percpu) < CONFIG_PHYSICAL_START,
- "per-CPU data too large - increase CONFIG_PHYSICAL_START")
-#endif
-
INIT_TEXT_SECTION(PAGE_SIZE)
-#ifdef CONFIG_X86_64
- :init
-#endif
/*
* Section for code used exclusively before alternatives are run. All
@@ -347,9 +327,7 @@ SECTIONS
EXIT_DATA
}
-#if !defined(CONFIG_X86_64) || !defined(CONFIG_SMP)
PERCPU_SECTION(INTERNODE_CACHE_BYTES)
-#endif
RUNTIME_CONST_VARIABLES
RUNTIME_CONST(ptr, USER_PTR_MAX)
@@ -493,19 +471,6 @@ SECTIONS
PROVIDE(__ref_stack_chk_guard = __stack_chk_guard);
#ifdef CONFIG_X86_64
-/*
- * Per-cpu symbols which need to be offset from __per_cpu_load
- * for the boot processor.
- */
-#define INIT_PER_CPU(x) init_per_cpu__##x = ABSOLUTE(x) + __per_cpu_load
-INIT_PER_CPU(gdt_page);
-INIT_PER_CPU(fixed_percpu_data);
-INIT_PER_CPU(irq_stack_backing_store);
-
-#ifdef CONFIG_SMP
-. = ASSERT((fixed_percpu_data == 0),
- "fixed_percpu_data is not at start of per-cpu area");
-#endif
#ifdef CONFIG_MITIGATION_UNRET_ENTRY
. = ASSERT((retbleed_return_thunk & 0x3f) == 0, "retbleed_return_thunk not cacheline-aligned");
diff --git a/arch/x86/platform/pvh/head.S b/arch/x86/platform/pvh/head.S
index 4733a5f467b8..cfa18ec7d55f 100644
--- a/arch/x86/platform/pvh/head.S
+++ b/arch/x86/platform/pvh/head.S
@@ -173,10 +173,14 @@ SYM_CODE_START(pvh_start_xen)
1:
UNWIND_HINT_END_OF_STACK
- /* Set base address in stack canary descriptor. */
- mov $MSR_GS_BASE,%ecx
- leal canary(%rip), %eax
- xor %edx, %edx
+ /*
+ * Set up GSBASE.
+ * Note that on SMP the boot CPU uses the init data section until
+ * the per-CPU areas are set up.
+ */
+ movl $MSR_GS_BASE,%ecx
+ xorl %eax, %eax
+ xorl %edx, %edx
wrmsr
/* Call xen_prepare_pvh() via the kernel virtual mapping */
@@ -238,8 +242,6 @@ SYM_DATA_START_LOCAL(gdt_start)
SYM_DATA_END_LABEL(gdt_start, SYM_L_LOCAL, gdt_end)
.balign 16
-SYM_DATA_LOCAL(canary, .fill 48, 1, 0)
-
SYM_DATA_START_LOCAL(early_stack)
.fill BOOT_STACK_SIZE, 1, 0
SYM_DATA_END_LABEL(early_stack, SYM_L_LOCAL, early_stack_end)
diff --git a/arch/x86/tools/relocs.c b/arch/x86/tools/relocs.c
index e937be979ec8..5778bc498415 100644
--- a/arch/x86/tools/relocs.c
+++ b/arch/x86/tools/relocs.c
@@ -29,9 +29,13 @@ static struct relocs relocs16;
static struct relocs relocs32;
#if ELF_BITS == 64
-static struct relocs relocs32neg;
static struct relocs relocs64;
# define FMT PRIu64
+
+#ifndef R_X86_64_REX_GOTPCRELX
+# define R_X86_64_REX_GOTPCRELX 42
+#endif
+
#else
# define FMT PRIu32
#endif
@@ -86,8 +90,6 @@ static const char * const sym_regex_kernel[S_NSYMTYPES] = {
"__initramfs_start|"
"(jiffies|jiffies_64)|"
#if ELF_BITS == 64
- "__per_cpu_load|"
- "init_per_cpu__.*|"
"__end_rodata_hpage_align|"
#endif
"_end)$"
@@ -227,6 +229,7 @@ static const char *rel_type(unsigned type)
REL_TYPE(R_X86_64_PC16),
REL_TYPE(R_X86_64_8),
REL_TYPE(R_X86_64_PC8),
+ REL_TYPE(R_X86_64_REX_GOTPCRELX),
#else
REL_TYPE(R_386_NONE),
REL_TYPE(R_386_32),
@@ -284,34 +287,6 @@ static const char *sym_name(const char *sym_strtab, Elf_Sym *sym)
return name;
}
-static Elf_Sym *sym_lookup(const char *symname)
-{
- int i;
-
- for (i = 0; i < shnum; i++) {
- struct section *sec = &secs[i];
- long nsyms;
- char *strtab;
- Elf_Sym *symtab;
- Elf_Sym *sym;
-
- if (sec->shdr.sh_type != SHT_SYMTAB)
- continue;
-
- nsyms = sec->shdr.sh_size/sizeof(Elf_Sym);
- symtab = sec->symtab;
- strtab = sec->link->strtab;
-
- for (sym = symtab; --nsyms >= 0; sym++) {
- if (!sym->st_name)
- continue;
- if (strcmp(symname, strtab + sym->st_name) == 0)
- return sym;
- }
- }
- return 0;
-}
-
#if BYTE_ORDER == LITTLE_ENDIAN
# define le16_to_cpu(val) (val)
# define le32_to_cpu(val) (val)
@@ -760,84 +735,8 @@ static void walk_relocs(int (*process)(struct section *sec, Elf_Rel *rel,
}
}
-/*
- * The .data..percpu section is a special case for x86_64 SMP kernels.
- * It is used to initialize the actual per_cpu areas and to provide
- * definitions for the per_cpu variables that correspond to their offsets
- * within the percpu area. Since the values of all of the symbols need
- * to be offsets from the start of the per_cpu area the virtual address
- * (sh_addr) of .data..percpu is 0 in SMP kernels.
- *
- * This means that:
- *
- * Relocations that reference symbols in the per_cpu area do not
- * need further relocation (since the value is an offset relative
- * to the start of the per_cpu area that does not change).
- *
- * Relocations that apply to the per_cpu area need to have their
- * offset adjusted by by the value of __per_cpu_load to make them
- * point to the correct place in the loaded image (because the
- * virtual address of .data..percpu is 0).
- *
- * For non SMP kernels .data..percpu is linked as part of the normal
- * kernel data and does not require special treatment.
- *
- */
-static int per_cpu_shndx = -1;
-static Elf_Addr per_cpu_load_addr;
-
-static void percpu_init(void)
-{
- int i;
-
- for (i = 0; i < shnum; i++) {
- ElfW(Sym) *sym;
-
- if (strcmp(sec_name(i), ".data..percpu"))
- continue;
-
- if (secs[i].shdr.sh_addr != 0) /* non SMP kernel */
- return;
-
- sym = sym_lookup("__per_cpu_load");
- if (!sym)
- die("can't find __per_cpu_load\n");
-
- per_cpu_shndx = i;
- per_cpu_load_addr = sym->st_value;
-
- return;
- }
-}
-
#if ELF_BITS == 64
-/*
- * Check to see if a symbol lies in the .data..percpu section.
- *
- * The linker incorrectly associates some symbols with the
- * .data..percpu section so we also need to check the symbol
- * name to make sure that we classify the symbol correctly.
- *
- * The GNU linker incorrectly associates:
- * __init_begin
- * __per_cpu_load
- *
- * The "gold" linker incorrectly associates:
- * init_per_cpu__fixed_percpu_data
- * init_per_cpu__gdt_page
- */
-static int is_percpu_sym(ElfW(Sym) *sym, const char *symname)
-{
- int shndx = sym_index(sym);
-
- return (shndx == per_cpu_shndx) &&
- strcmp(symname, "__init_begin") &&
- strcmp(symname, "__per_cpu_load") &&
- strncmp(symname, "init_per_cpu_", 13);
-}
-
-
static int do_reloc64(struct section *sec, Elf_Rel *rel, ElfW(Sym) *sym,
const char *symname)
{
@@ -848,12 +747,6 @@ static int do_reloc64(struct section *sec, Elf_Rel *rel, ElfW(Sym) *sym,
if (sym->st_shndx == SHN_UNDEF)
return 0;
- /*
- * Adjust the offset if this reloc applies to the percpu section.
- */
- if (sec->shdr.sh_info == per_cpu_shndx)
- offset += per_cpu_load_addr;
-
switch (r_type) {
case R_X86_64_NONE:
/* NONE can be ignored. */
@@ -861,33 +754,23 @@ static int do_reloc64(struct section *sec, Elf_Rel *rel, ElfW(Sym) *sym,
case R_X86_64_PC32:
case R_X86_64_PLT32:
+ case R_X86_64_REX_GOTPCRELX:
/*
- * PC relative relocations don't need to be adjusted unless
- * referencing a percpu symbol.
+ * PC relative relocations don't need to be adjusted.
*
* NB: R_X86_64_PLT32 can be treated as R_X86_64_PC32.
*/
- if (is_percpu_sym(sym, symname))
- add_reloc(&relocs32neg, offset);
break;
case R_X86_64_PC64:
/*
* Only used by jump labels
*/
- if (is_percpu_sym(sym, symname))
- die("Invalid R_X86_64_PC64 relocation against per-CPU symbol %s\n", symname);
break;
case R_X86_64_32:
case R_X86_64_32S:
case R_X86_64_64:
- /*
- * References to the percpu area don't need to be adjusted.
- */
- if (is_percpu_sym(sym, symname))
- break;
-
if (shn_abs) {
/*
* Whitelisted absolute symbols do not require
@@ -1055,7 +938,8 @@ static int cmp_relocs(const void *va, const void *vb)
static void sort_relocs(struct relocs *r)
{
- qsort(r->offset, r->count, sizeof(r->offset[0]), cmp_relocs);
+ if (r->count)
+ qsort(r->offset, r->count, sizeof(r->offset[0]), cmp_relocs);
}
static int write32(uint32_t v, FILE *f)
@@ -1099,7 +983,6 @@ static void emit_relocs(int as_text, int use_real_mode)
/* Order the relocations for more efficient processing */
sort_relocs(&relocs32);
#if ELF_BITS == 64
- sort_relocs(&relocs32neg);
sort_relocs(&relocs64);
#else
sort_relocs(&relocs16);
@@ -1131,13 +1014,6 @@ static void emit_relocs(int as_text, int use_real_mode)
/* Now print each relocation */
for (i = 0; i < relocs64.count; i++)
write_reloc(relocs64.offset[i], stdout);
-
- /* Print a stop */
- write_reloc(0, stdout);
-
- /* Now print each inverse 32-bit relocation */
- for (i = 0; i < relocs32neg.count; i++)
- write_reloc(relocs32neg.offset[i], stdout);
#endif
/* Print a stop */
@@ -1190,9 +1066,6 @@ void process(FILE *fp, int use_real_mode, int as_text,
read_symtabs(fp);
read_relocs(fp);
- if (ELF_BITS == 64)
- percpu_init();
-
if (show_absolute_syms) {
print_absolute_symbols();
return;
diff --git a/arch/x86/xen/xen-head.S b/arch/x86/xen/xen-head.S
index 894edf8d6d62..5ccb4c54e241 100644
--- a/arch/x86/xen/xen-head.S
+++ b/arch/x86/xen/xen-head.S
@@ -31,16 +31,14 @@ SYM_CODE_START(startup_xen)
leaq __top_init_kernel_stack(%rip), %rsp
- /* Set up %gs.
- *
- * The base of %gs always points to fixed_percpu_data. If the
- * stack protector canary is enabled, it is located at %gs:40.
+ /*
+ * Set up GSBASE.
* Note that, on SMP, the boot cpu uses init data section until
* the per cpu areas are set up.
*/
movl $MSR_GS_BASE,%ecx
- movq $INIT_PER_CPU_VAR(fixed_percpu_data),%rax
- cdq
+ xorl %eax, %eax
+ xorl %edx, %edx
wrmsr
mov %rsi, %rdi
diff --git a/include/asm-generic/sections.h b/include/asm-generic/sections.h
index c768de6f19a9..0755bc39b0d8 100644
--- a/include/asm-generic/sections.h
+++ b/include/asm-generic/sections.h
@@ -39,7 +39,7 @@ extern char __init_begin[], __init_end[];
extern char _sinittext[], _einittext[];
extern char __start_ro_after_init[], __end_ro_after_init[];
extern char _end[];
-extern char __per_cpu_load[], __per_cpu_start[], __per_cpu_end[];
+extern char __per_cpu_start[], __per_cpu_end[];
extern char __kprobes_text_start[], __kprobes_text_end[];
extern char __entry_text_start[], __entry_text_end[];
extern char __start_rodata[], __end_rodata[];
diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index 0d5b186abee8..b32e453acf9d 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -1062,7 +1062,6 @@ defined(CONFIG_AUTOFDO_CLANG) || defined(CONFIG_PROPELLER_CLANG)
*/
#define PERCPU_INPUT(cacheline) \
__per_cpu_start = .; \
- *(.data..percpu..first) \
. = ALIGN(PAGE_SIZE); \
*(.data..percpu..page_aligned) \
. = ALIGN(cacheline); \
@@ -1074,52 +1073,17 @@ defined(CONFIG_AUTOFDO_CLANG) || defined(CONFIG_PROPELLER_CLANG)
__per_cpu_end = .;
/**
- * PERCPU_VADDR - define output section for percpu area
+ * PERCPU_SECTION - define output section for percpu area
* @cacheline: cacheline size
- * @vaddr: explicit base address (optional)
- * @phdr: destination PHDR (optional)
*
* Macro which expands to output section for percpu area.
*
* @cacheline is used to align subsections to avoid false cacheline
* sharing between subsections for different purposes.
- *
- * If @vaddr is not blank, it specifies explicit base address and all
- * percpu symbols will be offset from the given address. If blank,
- * @vaddr always equals @laddr + LOAD_OFFSET.
- *
- * @phdr defines the output PHDR to use if not blank. Be warned that
- * output PHDR is sticky. If @phdr is specified, the next output
- * section in the linker script will go there too. @phdr should have
- * a leading colon.
- *
- * Note that this macros defines __per_cpu_load as an absolute symbol.
- * If there is no need to put the percpu section at a predetermined
- * address, use PERCPU_SECTION.
- */
-#define PERCPU_VADDR(cacheline, vaddr, phdr) \
- __per_cpu_load = .; \
- .data..percpu vaddr : AT(__per_cpu_load - LOAD_OFFSET) { \
- PERCPU_INPUT(cacheline) \
- } phdr \
- . = __per_cpu_load + SIZEOF(.data..percpu);
-
-/**
- * PERCPU_SECTION - define output section for percpu area, simple version
- * @cacheline: cacheline size
- *
- * Align to PAGE_SIZE and outputs output section for percpu area. This
- * macro doesn't manipulate @vaddr or @phdr and __per_cpu_load and
- * __per_cpu_start will be identical.
- *
- * This macro is equivalent to ALIGN(PAGE_SIZE); PERCPU_VADDR(@cacheline,,)
- * except that __per_cpu_load is defined as a relative symbol against
- * .data..percpu which is required for relocatable x86_32 configuration.
*/
#define PERCPU_SECTION(cacheline) \
. = ALIGN(PAGE_SIZE); \
.data..percpu : AT(ADDR(.data..percpu) - LOAD_OFFSET) { \
- __per_cpu_load = .; \
PERCPU_INPUT(cacheline) \
}
diff --git a/include/linux/percpu-defs.h b/include/linux/percpu-defs.h
index 5b520fe86b60..40d34e032d5b 100644
--- a/include/linux/percpu-defs.h
+++ b/include/linux/percpu-defs.h
@@ -26,13 +26,11 @@
#define PER_CPU_SHARED_ALIGNED_SECTION "..shared_aligned"
#define PER_CPU_ALIGNED_SECTION "..shared_aligned"
#endif
-#define PER_CPU_FIRST_SECTION "..first"
#else
#define PER_CPU_SHARED_ALIGNED_SECTION ""
#define PER_CPU_ALIGNED_SECTION "..shared_aligned"
-#define PER_CPU_FIRST_SECTION ""
#endif
@@ -115,16 +113,6 @@
DEFINE_PER_CPU_SECTION(type, name, "")
/*
- * Declaration/definition used for per-CPU variables that must come first in
- * the set of variables.
- */
-#define DECLARE_PER_CPU_FIRST(type, name) \
- DECLARE_PER_CPU_SECTION(type, name, PER_CPU_FIRST_SECTION)
-
-#define DEFINE_PER_CPU_FIRST(type, name) \
- DEFINE_PER_CPU_SECTION(type, name, PER_CPU_FIRST_SECTION)
-
-/*
* Declaration/definition used for per-CPU variables that must be cacheline
* aligned under SMP conditions so that, whilst a particular instance of the
* data corresponds to a particular CPU, inefficiencies due to direct access by
diff --git a/init/Kconfig b/init/Kconfig
index d0d021b3fa3b..a0ea04c17784 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -1869,11 +1869,6 @@ config KALLSYMS_ALL
Say N unless you really need all symbols, or kernel live patching.
-config KALLSYMS_ABSOLUTE_PERCPU
- bool
- depends on KALLSYMS
- default X86_64 && SMP
-
# end of the "standard kernel features (expert users)" menu
config ARCH_HAS_MEMBARRIER_CALLBACKS
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 60611df77957..f4859516b190 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -21707,7 +21707,7 @@ patch_map_ops_generic:
* way, it's fine to back out this inlining logic
*/
#ifdef CONFIG_SMP
- insn_buf[0] = BPF_MOV32_IMM(BPF_REG_0, (u32)(unsigned long)&pcpu_hot.cpu_number);
+ insn_buf[0] = BPF_MOV64_IMM(BPF_REG_0, (u32)(unsigned long)&pcpu_hot.cpu_number);
insn_buf[1] = BPF_MOV64_PERCPU_REG(BPF_REG_0, BPF_REG_0);
insn_buf[2] = BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_0, 0);
cnt = 3;
diff --git a/kernel/kallsyms.c b/kernel/kallsyms.c
index a9a0ca605d4a..4198f30aac3c 100644
--- a/kernel/kallsyms.c
+++ b/kernel/kallsyms.c
@@ -148,16 +148,8 @@ static unsigned int get_symbol_offset(unsigned long pos)
unsigned long kallsyms_sym_address(int idx)
{
- /* values are unsigned offsets if --absolute-percpu is not in effect */
- if (!IS_ENABLED(CONFIG_KALLSYMS_ABSOLUTE_PERCPU))
- return kallsyms_relative_base + (u32)kallsyms_offsets[idx];
-
- /* ...otherwise, positive offsets are absolute values */
- if (kallsyms_offsets[idx] >= 0)
- return kallsyms_offsets[idx];
-
- /* ...and negative offsets are relative to kallsyms_relative_base - 1 */
- return kallsyms_relative_base - 1 - kallsyms_offsets[idx];
+ /* values are unsigned offsets */
+ return kallsyms_relative_base + (u32)kallsyms_offsets[idx];
}
static unsigned int get_symbol_seq(int index)
diff --git a/mm/percpu.c b/mm/percpu.c
index ac61e3fc5f15..7b5835356d1e 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -3071,7 +3071,7 @@ int __init pcpu_embed_first_chunk(size_t reserved_size, size_t dyn_size,
continue;
}
/* copy and return the unused part */
- memcpy(ptr, __per_cpu_load, ai->static_size);
+ memcpy(ptr, __per_cpu_start, ai->static_size);
pcpu_fc_free(ptr + size_sum, ai->unit_size - size_sum);
}
}
@@ -3240,7 +3240,7 @@ int __init pcpu_page_first_chunk(size_t reserved_size, pcpu_fc_cpu_to_node_fn_t
flush_cache_vmap_early(unit_addr, unit_addr + ai->unit_size);
/* copy static data */
- memcpy((void *)unit_addr, __per_cpu_load, ai->static_size);
+ memcpy((void *)unit_addr, __per_cpu_start, ai->static_size);
}
/* we're ready, commit */
diff --git a/scripts/gcc-x86_32-has-stack-protector.sh b/scripts/gcc-x86_32-has-stack-protector.sh
deleted file mode 100755
index 9459ca4f0f11..000000000000
--- a/scripts/gcc-x86_32-has-stack-protector.sh
+++ /dev/null
@@ -1,8 +0,0 @@
-#!/bin/sh
-# SPDX-License-Identifier: GPL-2.0
-
-# This requires GCC 8.1 or better. Specifically, we require
-# -mstack-protector-guard-reg, added by
-# https://gcc.gnu.org/bugzilla/show_bug.cgi?id=81708
-
-echo "int foo(void) { char X[200]; return 3; }" | $* -S -x c -m32 -O0 -fstack-protector -mstack-protector-guard-reg=fs -mstack-protector-guard-symbol=__stack_chk_guard - -o - 2> /dev/null | grep -q "%fs"
diff --git a/scripts/gcc-x86_64-has-stack-protector.sh b/scripts/gcc-x86_64-has-stack-protector.sh
deleted file mode 100755
index f680bb01aeeb..000000000000
--- a/scripts/gcc-x86_64-has-stack-protector.sh
+++ /dev/null
@@ -1,4 +0,0 @@
-#!/bin/sh
-# SPDX-License-Identifier: GPL-2.0
-
-echo "int foo(void) { char X[200]; return 3; }" | $* -S -x c -m64 -O0 -mcmodel=kernel -fno-PIE -fstack-protector - -o - 2> /dev/null | grep -q "%gs"
diff --git a/scripts/kallsyms.c b/scripts/kallsyms.c
index 03852da3d249..4b0234e4b12f 100644
--- a/scripts/kallsyms.c
+++ b/scripts/kallsyms.c
@@ -5,7 +5,7 @@
* This software may be used and distributed according to the terms
* of the GNU General Public License, incorporated herein by reference.
*
- * Usage: kallsyms [--all-symbols] [--absolute-percpu] in.map > out.S
+ * Usage: kallsyms [--all-symbols] in.map > out.S
*
* Table compression uses all the unused char codes on the symbols and
* maps these to the most used substrings (tokens). For instance, it might
@@ -37,7 +37,6 @@ struct sym_entry {
unsigned long long addr;
unsigned int len;
unsigned int seq;
- bool percpu_absolute;
unsigned char sym[];
};
@@ -55,14 +54,9 @@ static struct addr_range text_ranges[] = {
#define text_range_text (&text_ranges[0])
#define text_range_inittext (&text_ranges[1])
-static struct addr_range percpu_range = {
- "__per_cpu_start", "__per_cpu_end", -1ULL, 0
-};
-
static struct sym_entry **table;
static unsigned int table_size, table_cnt;
static int all_symbols;
-static int absolute_percpu;
static int token_profit[0x10000];
@@ -73,7 +67,7 @@ static unsigned char best_table_len[256];
static void usage(void)
{
- fprintf(stderr, "Usage: kallsyms [--all-symbols] [--absolute-percpu] in.map > out.S\n");
+ fprintf(stderr, "Usage: kallsyms [--all-symbols] in.map > out.S\n");
exit(1);
}
@@ -164,7 +158,6 @@ static struct sym_entry *read_symbol(FILE *in, char **buf, size_t *buf_len)
return NULL;
check_symbol_range(name, addr, text_ranges, ARRAY_SIZE(text_ranges));
- check_symbol_range(name, addr, &percpu_range, 1);
/* include the type field in the symbol name, so that it gets
* compressed together */
@@ -175,7 +168,6 @@ static struct sym_entry *read_symbol(FILE *in, char **buf, size_t *buf_len)
sym->len = len;
sym->sym[0] = type;
strcpy(sym_name(sym), name);
- sym->percpu_absolute = false;
return sym;
}
@@ -319,11 +311,6 @@ static int expand_symbol(const unsigned char *data, int len, char *result)
return total;
}
-static bool symbol_absolute(const struct sym_entry *s)
-{
- return s->percpu_absolute;
-}
-
static int compare_names(const void *a, const void *b)
{
int ret;
@@ -455,22 +442,11 @@ static void write_src(void)
*/
long long offset;
- bool overflow;
-
- if (!absolute_percpu) {
- offset = table[i]->addr - relative_base;
- overflow = offset < 0 || offset > UINT_MAX;
- } else if (symbol_absolute(table[i])) {
- offset = table[i]->addr;
- overflow = offset < 0 || offset > INT_MAX;
- } else {
- offset = relative_base - table[i]->addr - 1;
- overflow = offset < INT_MIN || offset >= 0;
- }
- if (overflow) {
+
+ offset = table[i]->addr - relative_base;
+ if (offset < 0 || offset > UINT_MAX) {
fprintf(stderr, "kallsyms failure: "
- "%s symbol value %#llx out of range in relative mode\n",
- symbol_absolute(table[i]) ? "absolute" : "relative",
+ "relative symbol value %#llx out of range\n",
table[i]->addr);
exit(EXIT_FAILURE);
}
@@ -725,36 +701,15 @@ static void sort_symbols(void)
qsort(table, table_cnt, sizeof(table[0]), compare_symbols);
}
-static void make_percpus_absolute(void)
-{
- unsigned int i;
-
- for (i = 0; i < table_cnt; i++)
- if (symbol_in_range(table[i], &percpu_range, 1)) {
- /*
- * Keep the 'A' override for percpu symbols to
- * ensure consistent behavior compared to older
- * versions of this tool.
- */
- table[i]->sym[0] = 'A';
- table[i]->percpu_absolute = true;
- }
-}
-
/* find the minimum non-absolute symbol address */
static void record_relative_base(void)
{
- unsigned int i;
-
- for (i = 0; i < table_cnt; i++)
- if (!symbol_absolute(table[i])) {
- /*
- * The table is sorted by address.
- * Take the first non-absolute symbol value.
- */
- relative_base = table[i]->addr;
- return;
- }
+ /*
+ * The table is sorted by address.
+ * Take the first symbol value.
+ */
+ if (table_cnt)
+ relative_base = table[0]->addr;
}
int main(int argc, char **argv)
@@ -762,7 +717,6 @@ int main(int argc, char **argv)
while (1) {
static const struct option long_options[] = {
{"all-symbols", no_argument, &all_symbols, 1},
- {"absolute-percpu", no_argument, &absolute_percpu, 1},
{},
};
@@ -779,8 +733,6 @@ int main(int argc, char **argv)
read_map(argv[optind]);
shrink_table();
- if (absolute_percpu)
- make_percpus_absolute();
sort_symbols();
record_relative_base();
optimize_token_table();
diff --git a/scripts/link-vmlinux.sh b/scripts/link-vmlinux.sh
index 56a077d204cf..67e66333bd2a 100755
--- a/scripts/link-vmlinux.sh
+++ b/scripts/link-vmlinux.sh
@@ -144,10 +144,6 @@ kallsyms()
kallsymopt="${kallsymopt} --all-symbols"
fi
- if is_enabled CONFIG_KALLSYMS_ABSOLUTE_PERCPU; then
- kallsymopt="${kallsymopt} --absolute-percpu"
- fi
-
info KSYMS "${2}.S"
scripts/kallsyms ${kallsymopt} "${1}" > "${2}.S"
diff --git a/scripts/min-tool-version.sh b/scripts/min-tool-version.sh
index 91c91201212c..787868183b84 100755
--- a/scripts/min-tool-version.sh
+++ b/scripts/min-tool-version.sh
@@ -19,12 +19,14 @@ binutils)
gcc)
if [ "$ARCH" = parisc64 ]; then
echo 12.0.0
+ elif [ "$SRCARCH" = x86 ]; then
+ echo 8.1.0
else
echo 5.1.0
fi
;;
llvm)
- if [ "$SRCARCH" = s390 ]; then
+ if [ "$SRCARCH" = s390 -o "$SRCARCH" = x86 ]; then
echo 15.0.0
elif [ "$SRCARCH" = loongarch ]; then
echo 18.0.0
diff --git a/tools/testing/selftests/x86/lam.c b/tools/testing/selftests/x86/lam.c
index b6166a5f37d6..18d736640ece 100644
--- a/tools/testing/selftests/x86/lam.c
+++ b/tools/testing/selftests/x86/lam.c
@@ -696,8 +696,10 @@ int do_uring(unsigned long lam)
fi->file_fd = file_fd;
ring = malloc(sizeof(*ring));
- if (!ring)
+ if (!ring) {
+ free(fi);
return 1;
+ }
memset(ring, 0, sizeof(struct io_ring));