Merge branch into tip/master: 'x86/percpu'HEADmaster

 # New commits in x86/percpu:
    0548eb067ed6 ("x86/percpu: Return correct variable from current_top_of_stack()")
    ed2f752e0e0a ("x86/percpu: Introduce const-qualified const_pcpu_hot to micro-optimize code generation")
    59bec00ace28 ("x86/percpu: Introduce %rip-relative addressing to PER_CPU_VAR()")
    aa47f90cd433 ("x86/percpu, xen: Correct PER_CPU_VAR() usage to include symbol and its addend")
    39d64ee59cee ("x86/percpu: Correct PER_CPU_VAR() usage to include symbol and its addend")
    24b8a23638cb ("x86/fpu: Clean up FPU switching in the middle of task switching")
    e39828d2c1c0 ("x86/percpu: Use the correct asm operand modifier in percpu_stable_op()")
    1d10f3aec2bb ("x86/percpu: Use C for arch_raw_cpu_ptr(), to improve code generation")
    a048d3abae7c ("x86/percpu: Rewrite arch_raw_cpu_ptr() to be easier for compilers to optimize")
    e29aad08b1da ("x86/percpu: Disable named address spaces for KASAN")
    ca4256348660 ("x86/percpu: Use C for percpu read/write accessors")
    9a462b9eafa6 ("x86/percpu: Use compiler segment prefix qualifier")
    1ca3683cc6d2 ("x86/percpu: Enable named address spaces with known compiler version")

Signed-off-by: Ingo Molnar <mingo@kernel.org>

18 files changed, 205 insertions, 79 deletions

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 5a6728dda6708..c456c9b1fc7cb 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -2425,6 +2425,18 @@ source "kernel/livepatch/Kconfig"
 
 endmenu
 
+config CC_HAS_NAMED_AS
+	def_bool CC_IS_GCC && GCC_VERSION >= 120100
+
+config USE_X86_SEG_SUPPORT
+	def_bool y
+	depends on CC_HAS_NAMED_AS
+	#
+	# -fsanitize=kernel-address (KASAN) is at the moment incompatible
+	# with named address spaces - see GCC PR sanitizer/111736.
+	#
+	depends on !KASAN
+
 config CC_HAS_SLS
 	def_bool $(cc-option,-mharden-sls=all)
 
diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h
index 9f1d94790a549..e59d3073e7cf2 100644
--- a/arch/x86/entry/calling.h
+++ b/arch/x86/entry/calling.h
@@ -173,7 +173,7 @@ 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
diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S
index c73047bf9f4bf..4e295798638b8 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 c40f89ab1b4c7..567d973eed038 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -190,7 +190,7 @@ 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
 
 	/*
diff --git a/arch/x86/include/asm/current.h b/arch/x86/include/asm/current.h
index a1168e7b69e5b..0538d24366733 100644
--- a/arch/x86/include/asm/current.h
+++ b/arch/x86/include/asm/current.h
@@ -36,8 +36,15 @@ static_assert(sizeof(struct pcpu_hot) == 64);
 
 DECLARE_PER_CPU_ALIGNED(struct pcpu_hot, pcpu_hot);
 
+/* const-qualified alias to pcpu_hot, aliased by linker. */
+DECLARE_PER_CPU_ALIGNED(const struct pcpu_hot __percpu_seg_override,
+			const_pcpu_hot);
+
 static __always_inline struct task_struct *get_current(void)
 {
+	if (IS_ENABLED(CONFIG_USE_X86_SEG_SUPPORT))
+		return const_pcpu_hot.current_task;
+
 	return this_cpu_read_stable(pcpu_hot.current_task);
 }
 
diff --git a/arch/x86/include/asm/fpu/sched.h b/arch/x86/include/asm/fpu/sched.h
index ca6e5e5f16b2e..c485f1944c5f8 100644
--- a/arch/x86/include/asm/fpu/sched.h
+++ b/arch/x86/include/asm/fpu/sched.h
@@ -37,10 +37,12 @@ extern void fpu_flush_thread(void);
  * The FPU context is only stored/restored for a user task and
  * PF_KTHREAD is used to distinguish between kernel and user threads.
  */
-static inline void switch_fpu_prepare(struct fpu *old_fpu, int cpu)
+static inline void switch_fpu_prepare(struct task_struct *old, int cpu)
 {
 	if (cpu_feature_enabled(X86_FEATURE_FPU) &&
-	    !(current->flags & (PF_KTHREAD | PF_USER_WORKER))) {
+	    !(old->flags & (PF_KTHREAD | PF_USER_WORKER))) {
+		struct fpu *old_fpu = &old->thread.fpu;
+
 		save_fpregs_to_fpstate(old_fpu);
 		/*
 		 * The save operation preserved register state, so the
@@ -60,10 +62,10 @@ static inline void switch_fpu_prepare(struct fpu *old_fpu, int cpu)
  * Delay loading of the complete FPU state until the return to userland.
  * PKRU is handled separately.
  */
-static inline void switch_fpu_finish(void)
+static inline void switch_fpu_finish(struct task_struct *new)
 {
 	if (cpu_feature_enabled(X86_FEATURE_FPU))
-		set_thread_flag(TIF_NEED_FPU_LOAD);
+		set_tsk_thread_flag(new, TIF_NEED_FPU_LOAD);
 }
 
 #endif /* _ASM_X86_FPU_SCHED_H */
diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h
index 20624b80f8904..b86b27d15e528 100644
--- a/arch/x86/include/asm/percpu.h
+++ b/arch/x86/include/asm/percpu.h
@@ -4,17 +4,21 @@
 
 #ifdef CONFIG_X86_64
 #define __percpu_seg		gs
+#define __percpu_rel		(%rip)
 #else
 #define __percpu_seg		fs
+#define __percpu_rel
 #endif
 
 #ifdef __ASSEMBLY__
 
 #ifdef CONFIG_SMP
-#define PER_CPU_VAR(var)	%__percpu_seg:var
-#else /* ! SMP */
-#define PER_CPU_VAR(var)	var
-#endif	/* SMP */
+#define __percpu		%__percpu_seg:
+#else
+#define __percpu
+#endif
+
+#define PER_CPU_VAR(var)	__percpu(var)__percpu_rel
 
 #ifdef CONFIG_X86_64_SMP
 #define INIT_PER_CPU_VAR(var)  init_per_cpu__##var
@@ -28,26 +32,69 @@
 #include <linux/stringify.h>
 
 #ifdef CONFIG_SMP
+
+#ifdef CONFIG_CC_HAS_NAMED_AS
+
+#ifdef CONFIG_X86_64
+#define __percpu_seg_override	__seg_gs
+#else
+#define __percpu_seg_override	__seg_fs
+#endif
+
+#define __percpu_prefix		""
+
+#else /* CONFIG_CC_HAS_NAMED_AS */
+
+#define __percpu_seg_override
 #define __percpu_prefix		"%%"__stringify(__percpu_seg)":"
+
+#endif /* CONFIG_CC_HAS_NAMED_AS */
+
+#define __force_percpu_prefix	"%%"__stringify(__percpu_seg)":"
 #define __my_cpu_offset		this_cpu_read(this_cpu_off)
 
+#ifdef CONFIG_USE_X86_SEG_SUPPORT
+/*
+ * Efficient implementation for cases in which the compiler supports
+ * named address spaces.  Allows the compiler to perform additional
+ * optimizations that can save more instructions.
+ */
+#define arch_raw_cpu_ptr(ptr)					\
+({								\
+	unsigned long tcp_ptr__;				\
+	tcp_ptr__ = __raw_cpu_read(, this_cpu_off);		\
+								\
+	tcp_ptr__ += (unsigned long)(ptr);			\
+	(typeof(*(ptr)) __kernel __force *)tcp_ptr__;		\
+})
+#else /* CONFIG_USE_X86_SEG_SUPPORT */
 /*
  * Compared to the generic __my_cpu_offset version, the following
  * saves one instruction and avoids clobbering a temp register.
  */
-#define arch_raw_cpu_ptr(ptr)				\
-({							\
-	unsigned long tcp_ptr__;			\
-	asm ("add " __percpu_arg(1) ", %0"		\
-	     : "=r" (tcp_ptr__)				\
-	     : "m" (this_cpu_off), "0" (ptr));		\
-	(typeof(*(ptr)) __kernel __force *)tcp_ptr__;	\
+#define arch_raw_cpu_ptr(ptr)					\
+({								\
+	unsigned long tcp_ptr__;				\
+	asm ("mov " __percpu_arg(1) ", %0"			\
+	     : "=r" (tcp_ptr__)					\
+	     : "m" (__my_cpu_var(this_cpu_off)));		\
+								\
+	tcp_ptr__ += (unsigned long)(ptr);			\
+	(typeof(*(ptr)) __kernel __force *)tcp_ptr__;		\
 })
-#else
+#endif /* CONFIG_USE_X86_SEG_SUPPORT */
+
+#else /* CONFIG_SMP */
+#define __percpu_seg_override
 #define __percpu_prefix		""
-#endif
+#define __force_percpu_prefix	""
+#endif /* CONFIG_SMP */
 
+#define __my_cpu_type(var)	typeof(var) __percpu_seg_override
+#define __my_cpu_ptr(ptr)	(__my_cpu_type(*ptr) *)(uintptr_t)(ptr)
+#define __my_cpu_var(var)	(*__my_cpu_ptr(&var))
 #define __percpu_arg(x)		__percpu_prefix "%" #x
+#define __force_percpu_arg(x)	__force_percpu_prefix "%" #x
 
 /*
  * Initialized pointers to per-cpu variables needed for the boot
@@ -107,14 +154,14 @@ do {									\
 		(void)pto_tmp__;					\
 	}								\
 	asm qual(__pcpu_op2_##size(op, "%[val]", __percpu_arg([var]))	\
-	    : [var] "+m" (_var)						\
+	    : [var] "+m" (__my_cpu_var(_var))				\
 	    : [val] __pcpu_reg_imm_##size(pto_val__));			\
 } while (0)
 
 #define percpu_unary_op(size, qual, op, _var)				\
 ({									\
 	asm qual (__pcpu_op1_##size(op, __percpu_arg([var]))		\
-	    : [var] "+m" (_var));					\
+	    : [var] "+m" (__my_cpu_var(_var)));				\
 })
 
 /*
@@ -144,16 +191,16 @@ do {									\
 	__pcpu_type_##size pfo_val__;					\
 	asm qual (__pcpu_op2_##size(op, __percpu_arg([var]), "%[val]")	\
 	    : [val] __pcpu_reg_##size("=", pfo_val__)			\
-	    : [var] "m" (_var));					\
+	    : [var] "m" (__my_cpu_var(_var)));				\
 	(typeof(_var))(unsigned long) pfo_val__;			\
 })
 
 #define percpu_stable_op(size, op, _var)				\
 ({									\
 	__pcpu_type_##size pfo_val__;					\
-	asm(__pcpu_op2_##size(op, __percpu_arg(P[var]), "%[val]")	\
+	asm(__pcpu_op2_##size(op, __force_percpu_arg(a[var]), "%[val]")	\
 	    : [val] __pcpu_reg_##size("=", pfo_val__)			\
-	    : [var] "p" (&(_var)));					\
+	    : [var] "i" (&(_var)));					\
 	(typeof(_var))(unsigned long) pfo_val__;			\
 })
 
@@ -166,7 +213,7 @@ do {									\
 	asm qual (__pcpu_op2_##size("xadd", "%[tmp]",			\
 				     __percpu_arg([var]))		\
 		  : [tmp] __pcpu_reg_##size("+", paro_tmp__),		\
-		    [var] "+m" (_var)					\
+		    [var] "+m" (__my_cpu_var(_var))			\
 		  : : "memory");					\
 	(typeof(_var))(unsigned long) (paro_tmp__ + _val);		\
 })
@@ -187,7 +234,7 @@ do {									\
 				    __percpu_arg([var]))		\
 		  "\n\tjnz 1b"						\
 		  : [oval] "=&a" (pxo_old__),				\
-		    [var] "+m" (_var)					\
+		    [var] "+m" (__my_cpu_var(_var))			\
 		  : [nval] __pcpu_reg_##size(, pxo_new__)		\
 		  : "memory");						\
 	(typeof(_var))(unsigned long) pxo_old__;			\
@@ -204,7 +251,7 @@ do {									\
 	asm qual (__pcpu_op2_##size("cmpxchg", "%[nval]",		\
 				    __percpu_arg([var]))		\
 		  : [oval] "+a" (pco_old__),				\
-		    [var] "+m" (_var)					\
+		    [var] "+m" (__my_cpu_var(_var))			\
 		  : [nval] __pcpu_reg_##size(, pco_new__)		\
 		  : "memory");						\
 	(typeof(_var))(unsigned long) pco_old__;			\
@@ -221,7 +268,7 @@ do {									\
 		  CC_SET(z)						\
 		  : CC_OUT(z) (success),				\
 		    [oval] "+a" (pco_old__),				\
-		    [var] "+m" (_var)					\
+		    [var] "+m" (__my_cpu_var(_var))			\
 		  : [nval] __pcpu_reg_##size(, pco_new__)		\
 		  : "memory");						\
 	if (unlikely(!success))						\
@@ -244,7 +291,7 @@ do {									\
 									\
 	asm qual (ALTERNATIVE("call this_cpu_cmpxchg8b_emu",		\
 			      "cmpxchg8b " __percpu_arg([var]), X86_FEATURE_CX8) \
-		  : [var] "+m" (_var),					\
+		  : [var] "+m" (__my_cpu_var(_var)),			\
 		    "+a" (old__.low),					\
 		    "+d" (old__.high)					\
 		  : "b" (new__.low),					\
@@ -276,7 +323,7 @@ do {									\
 			      "cmpxchg8b " __percpu_arg([var]), X86_FEATURE_CX8) \
 		  CC_SET(z)						\
 		  : CC_OUT(z) (success),				\
-		    [var] "+m" (_var),					\
+		    [var] "+m" (__my_cpu_var(_var)),			\
 		    "+a" (old__.low),					\
 		    "+d" (old__.high)					\
 		  : "b" (new__.low),					\
@@ -313,7 +360,7 @@ do {									\
 									\
 	asm qual (ALTERNATIVE("call this_cpu_cmpxchg16b_emu",		\
 			      "cmpxchg16b " __percpu_arg([var]), X86_FEATURE_CX16) \
-		  : [var] "+m" (_var),					\
+		  : [var] "+m" (__my_cpu_var(_var)),			\
 		    "+a" (old__.low),					\
 		    "+d" (old__.high)					\
 		  : "b" (new__.low),					\
@@ -345,7 +392,7 @@ do {									\
 			      "cmpxchg16b " __percpu_arg([var]), X86_FEATURE_CX16) \
 		  CC_SET(z)						\
 		  : CC_OUT(z) (success),				\
-		    [var] "+m" (_var),					\
+		    [var] "+m" (__my_cpu_var(_var)),			\
 		    "+a" (old__.low),					\
 		    "+d" (old__.high)					\
 		  : "b" (new__.low),					\
@@ -366,9 +413,9 @@ do {									\
  * accessed while this_cpu_read_stable() allows the value to be cached.
  * this_cpu_read_stable() is more efficient and can be used if its value
  * is guaranteed to be valid across cpus.  The current users include
- * get_current() and get_thread_info() both of which are actually
- * per-thread variables implemented as per-cpu variables and thus
- * stable for the duration of the respective task.
+ * pcpu_hot.current_task and pcpu_hot.top_of_stack, both of which are
+ * actually per-thread variables implemented as per-CPU variables and
+ * thus stable for the duration of the respective task.
  */
 #define this_cpu_read_stable_1(pcp)	percpu_stable_op(1, "mov", pcp)
 #define this_cpu_read_stable_2(pcp)	percpu_stable_op(2, "mov", pcp)
@@ -376,13 +423,66 @@ do {									\
 #define this_cpu_read_stable_8(pcp)	percpu_stable_op(8, "mov", pcp)
 #define this_cpu_read_stable(pcp)	__pcpu_size_call_return(this_cpu_read_stable_, pcp)
 
+#ifdef CONFIG_USE_X86_SEG_SUPPORT
+
+#define __raw_cpu_read(qual, pcp)					\
+({									\
+	*(qual __my_cpu_type(pcp) *)__my_cpu_ptr(&(pcp));		\
+})
+
+#define __raw_cpu_write(qual, pcp, val)					\
+do {									\
+	*(qual __my_cpu_type(pcp) *)__my_cpu_ptr(&(pcp)) = (val);	\
+} while (0)
+
+#define raw_cpu_read_1(pcp)		__raw_cpu_read(, pcp)
+#define raw_cpu_read_2(pcp)		__raw_cpu_read(, pcp)
+#define raw_cpu_read_4(pcp)		__raw_cpu_read(, pcp)
+#define raw_cpu_write_1(pcp, val)	__raw_cpu_write(, pcp, val)
+#define raw_cpu_write_2(pcp, val)	__raw_cpu_write(, pcp, val)
+#define raw_cpu_write_4(pcp, val)	__raw_cpu_write(, pcp, val)
+
+#define this_cpu_read_1(pcp)		__raw_cpu_read(volatile, pcp)
+#define this_cpu_read_2(pcp)		__raw_cpu_read(volatile, pcp)
+#define this_cpu_read_4(pcp)		__raw_cpu_read(volatile, pcp)
+#define this_cpu_write_1(pcp, val)	__raw_cpu_write(volatile, pcp, val)
+#define this_cpu_write_2(pcp, val)	__raw_cpu_write(volatile, pcp, val)
+#define this_cpu_write_4(pcp, val)	__raw_cpu_write(volatile, pcp, val)
+
+#ifdef CONFIG_X86_64
+#define raw_cpu_read_8(pcp)		__raw_cpu_read(, pcp)
+#define raw_cpu_write_8(pcp, val)	__raw_cpu_write(, pcp, val)
+
+#define this_cpu_read_8(pcp)		__raw_cpu_read(volatile, pcp)
+#define this_cpu_write_8(pcp, val)	__raw_cpu_write(volatile, pcp, val)
+#endif
+
+#else /* CONFIG_USE_X86_SEG_SUPPORT */
+
 #define raw_cpu_read_1(pcp)		percpu_from_op(1, , "mov", pcp)
 #define raw_cpu_read_2(pcp)		percpu_from_op(2, , "mov", pcp)
 #define raw_cpu_read_4(pcp)		percpu_from_op(4, , "mov", pcp)
-
 #define raw_cpu_write_1(pcp, val)	percpu_to_op(1, , "mov", (pcp), val)
 #define raw_cpu_write_2(pcp, val)	percpu_to_op(2, , "mov", (pcp), val)
 #define raw_cpu_write_4(pcp, val)	percpu_to_op(4, , "mov", (pcp), val)
+
+#define this_cpu_read_1(pcp)		percpu_from_op(1, volatile, "mov", pcp)
+#define this_cpu_read_2(pcp)		percpu_from_op(2, volatile, "mov", pcp)
+#define this_cpu_read_4(pcp)		percpu_from_op(4, volatile, "mov", pcp)
+#define this_cpu_write_1(pcp, val)	percpu_to_op(1, volatile, "mov", (pcp), val)
+#define this_cpu_write_2(pcp, val)	percpu_to_op(2, volatile, "mov", (pcp), val)
+#define this_cpu_write_4(pcp, val)	percpu_to_op(4, volatile, "mov", (pcp), val)
+
+#ifdef CONFIG_X86_64
+#define raw_cpu_read_8(pcp)		percpu_from_op(8, , "mov", pcp)
+#define raw_cpu_write_8(pcp, val)	percpu_to_op(8, , "mov", (pcp), val)
+
+#define this_cpu_read_8(pcp)		percpu_from_op(8, volatile, "mov", pcp)
+#define this_cpu_write_8(pcp, val)	percpu_to_op(8, volatile, "mov", (pcp), val)
+#endif
+
+#endif /* CONFIG_USE_X86_SEG_SUPPORT */
+
 #define raw_cpu_add_1(pcp, val)		percpu_add_op(1, , (pcp), val)
 #define raw_cpu_add_2(pcp, val)		percpu_add_op(2, , (pcp), val)
 #define raw_cpu_add_4(pcp, val)		percpu_add_op(4, , (pcp), val)
@@ -408,12 +508,6 @@ do {									\
 #define raw_cpu_xchg_2(pcp, val)	raw_percpu_xchg_op(pcp, val)
 #define raw_cpu_xchg_4(pcp, val)	raw_percpu_xchg_op(pcp, val)
 
-#define this_cpu_read_1(pcp)		percpu_from_op(1, volatile, "mov", pcp)
-#define this_cpu_read_2(pcp)		percpu_from_op(2, volatile, "mov", pcp)
-#define this_cpu_read_4(pcp)		percpu_from_op(4, volatile, "mov", pcp)
-#define this_cpu_write_1(pcp, val)	percpu_to_op(1, volatile, "mov", (pcp), val)
-#define this_cpu_write_2(pcp, val)	percpu_to_op(2, volatile, "mov", (pcp), val)
-#define this_cpu_write_4(pcp, val)	percpu_to_op(4, volatile, "mov", (pcp), val)
 #define this_cpu_add_1(pcp, val)	percpu_add_op(1, volatile, (pcp), val)
 #define this_cpu_add_2(pcp, val)	percpu_add_op(2, volatile, (pcp), val)
 #define this_cpu_add_4(pcp, val)	percpu_add_op(4, volatile, (pcp), val)
@@ -452,8 +546,6 @@ do {									\
  * 32 bit must fall back to generic operations.
  */
 #ifdef CONFIG_X86_64
-#define raw_cpu_read_8(pcp)			percpu_from_op(8, , "mov", pcp)
-#define raw_cpu_write_8(pcp, val)		percpu_to_op(8, , "mov", (pcp), val)
 #define raw_cpu_add_8(pcp, val)			percpu_add_op(8, , (pcp), val)
 #define raw_cpu_and_8(pcp, val)			percpu_to_op(8, , "and", (pcp), val)
 #define raw_cpu_or_8(pcp, val)			percpu_to_op(8, , "or", (pcp), val)
@@ -462,8 +554,6 @@ do {									\
 #define raw_cpu_cmpxchg_8(pcp, oval, nval)	percpu_cmpxchg_op(8, , pcp, oval, nval)
 #define raw_cpu_try_cmpxchg_8(pcp, ovalp, nval)	percpu_try_cmpxchg_op(8, , pcp, ovalp, nval)
 
-#define this_cpu_read_8(pcp)			percpu_from_op(8, volatile, "mov", pcp)
-#define this_cpu_write_8(pcp, val)		percpu_to_op(8, volatile, "mov", (pcp), val)
 #define this_cpu_add_8(pcp, val)		percpu_add_op(8, volatile, (pcp), val)
 #define this_cpu_and_8(pcp, val)		percpu_to_op(8, volatile, "and", (pcp), val)
 #define this_cpu_or_8(pcp, val)			percpu_to_op(8, volatile, "or", (pcp), val)
@@ -494,7 +584,7 @@ static inline bool x86_this_cpu_variable_test_bit(int nr,
 	asm volatile("btl "__percpu_arg(2)",%1"
 			CC_SET(c)
 			: CC_OUT(c) (oldbit)
-			: "m" (*(unsigned long __percpu *)addr), "Ir" (nr));
+			: "m" (*__my_cpu_ptr((unsigned long __percpu *)(addr))), "Ir" (nr));
 
 	return oldbit;
 }
diff --git a/arch/x86/include/asm/preempt.h b/arch/x86/include/asm/preempt.h
index 4527e1430c6dc..4b2a35d8d56a8 100644
--- a/arch/x86/include/asm/preempt.h
+++ b/arch/x86/include/asm/preempt.h
@@ -92,7 +92,7 @@ static __always_inline void __preempt_count_sub(int val)
  */
 static __always_inline bool __preempt_count_dec_and_test(void)
 {
-	return GEN_UNARY_RMWcc("decl", pcpu_hot.preempt_count, e,
+	return GEN_UNARY_RMWcc("decl", __my_cpu_var(pcpu_hot.preempt_count), e,
 			       __percpu_arg([var]));
 }
 
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 26620d7642a9f..061aa86b46622 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -533,6 +533,9 @@ static __always_inline unsigned long current_top_of_stack(void)
 	 *  and around vm86 mode and sp0 on x86_64 is special because of the
 	 *  entry trampoline.
 	 */
+	if (IS_ENABLED(CONFIG_USE_X86_SEG_SUPPORT))
+		return const_pcpu_hot.top_of_stack;
+
 	return this_cpu_read_stable(pcpu_hot.top_of_stack);
 }
 
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 98f7ea6b931cb..4d4b87c6885de 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -2056,6 +2056,7 @@ DEFINE_PER_CPU_ALIGNED(struct pcpu_hot, pcpu_hot) = {
 	.top_of_stack	= TOP_OF_INIT_STACK,
 };
 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,
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index 086a2c3aaaa04..3dcabbc49149d 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -448,7 +448,7 @@ SYM_CODE_START(soft_restart_cpu)
 	UNWIND_HINT_END_OF_STACK
 
 	/* Find the idle task stack */
-	movq	PER_CPU_VAR(pcpu_hot) + X86_current_task, %rcx
+	movq	PER_CPU_VAR(pcpu_hot + X86_current_task), %rcx
 	movq	TASK_threadsp(%rcx), %rsp
 
 	jmp	.Ljump_to_C_code
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index 708c87b88cc15..0917c7f25720b 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -156,13 +156,12 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 {
 	struct thread_struct *prev = &prev_p->thread,
 			     *next = &next_p->thread;
-	struct fpu *prev_fpu = &prev->fpu;
 	int cpu = smp_processor_id();
 
 	/* never put a printk in __switch_to... printk() calls wake_up*() indirectly */
 
-	if (!test_thread_flag(TIF_NEED_FPU_LOAD))
-		switch_fpu_prepare(prev_fpu, cpu);
+	if (!test_tsk_thread_flag(prev_p, TIF_NEED_FPU_LOAD))
+		switch_fpu_prepare(prev_p, cpu);
 
 	/*
 	 * Save away %gs. No need to save %fs, as it was saved on the
@@ -209,7 +208,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 
 	raw_cpu_write(pcpu_hot.current_task, next_p);
 
-	switch_fpu_finish();
+	switch_fpu_finish(next_p);
 
 	/* Load the Intel cache allocation PQR MSR. */
 	resctrl_sched_in(next_p);
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 33b268747bb7b..1553e19904e05 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -562,14 +562,13 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 {
 	struct thread_struct *prev = &prev_p->thread;
 	struct thread_struct *next = &next_p->thread;
-	struct fpu *prev_fpu = &prev->fpu;
 	int cpu = smp_processor_id();
 
 	WARN_ON_ONCE(IS_ENABLED(CONFIG_DEBUG_ENTRY) &&
 		     this_cpu_read(pcpu_hot.hardirq_stack_inuse));
 
-	if (!test_thread_flag(TIF_NEED_FPU_LOAD))
-		switch_fpu_prepare(prev_fpu, cpu);
+	if (!test_tsk_thread_flag(prev_p, TIF_NEED_FPU_LOAD))
+		switch_fpu_prepare(prev_p, cpu);
 
 	/* We must save %fs and %gs before load_TLS() because
 	 * %fs and %gs may be cleared by load_TLS().
@@ -623,7 +622,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 	raw_cpu_write(pcpu_hot.current_task, next_p);
 	raw_cpu_write(pcpu_hot.top_of_stack, task_top_of_stack(next_p));
 
-	switch_fpu_finish();
+	switch_fpu_finish(next_p);
 
 	/* Reload sp0. */
 	update_task_stack(next_p);
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index 54a5596adaa61..1239be7cc8d85 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -46,6 +46,7 @@ ENTRY(phys_startup_64)
 #endif
 
 jiffies = jiffies_64;
+const_pcpu_hot = pcpu_hot;
 
 #if defined(CONFIG_X86_64)
 /*
diff --git a/arch/x86/lib/cmpxchg16b_emu.S b/arch/x86/lib/cmpxchg16b_emu.S
index 6962df3157938..4fb44894ad875 100644
--- a/arch/x86/lib/cmpxchg16b_emu.S
+++ b/arch/x86/lib/cmpxchg16b_emu.S
@@ -23,14 +23,14 @@ SYM_FUNC_START(this_cpu_cmpxchg16b_emu)
 	cli
 
 	/* if (*ptr == old) */
-	cmpq	PER_CPU_VAR(0(%rsi)), %rax
+	cmpq	__percpu (%rsi), %rax
 	jne	.Lnot_same
-	cmpq	PER_CPU_VAR(8(%rsi)), %rdx
+	cmpq	__percpu 8(%rsi), %rdx
 	jne	.Lnot_same
 
 	/* *ptr = new */
-	movq	%rbx, PER_CPU_VAR(0(%rsi))
-	movq	%rcx, PER_CPU_VAR(8(%rsi))
+	movq	%rbx, __percpu (%rsi)
+	movq	%rcx, __percpu 8(%rsi)
 
 	/* set ZF in EFLAGS to indicate success */
 	orl	$X86_EFLAGS_ZF, (%rsp)
@@ -42,8 +42,8 @@ SYM_FUNC_START(this_cpu_cmpxchg16b_emu)
 	/* *ptr != old */
 
 	/* old = *ptr */
-	movq	PER_CPU_VAR(0(%rsi)), %rax
-	movq	PER_CPU_VAR(8(%rsi)), %rdx
+	movq	__percpu (%rsi), %rax
+	movq	__percpu 8(%rsi), %rdx
 
 	/* clear ZF in EFLAGS to indicate failure */
 	andl	$(~X86_EFLAGS_ZF), (%rsp)
diff --git a/arch/x86/lib/cmpxchg8b_emu.S b/arch/x86/lib/cmpxchg8b_emu.S
index 873e4ef23e495..1c96be769adc3 100644
--- a/arch/x86/lib/cmpxchg8b_emu.S
+++ b/arch/x86/lib/cmpxchg8b_emu.S
@@ -24,12 +24,12 @@ SYM_FUNC_START(cmpxchg8b_emu)
 	pushfl
 	cli
 
-	cmpl	0(%esi), %eax
+	cmpl	(%esi), %eax
 	jne	.Lnot_same
 	cmpl	4(%esi), %edx
 	jne	.Lnot_same
 
-	movl	%ebx, 0(%esi)
+	movl	%ebx, (%esi)
 	movl	%ecx, 4(%esi)
 
 	orl	$X86_EFLAGS_ZF, (%esp)
@@ -38,7 +38,7 @@ SYM_FUNC_START(cmpxchg8b_emu)
 	RET
 
 .Lnot_same:
-	movl	0(%esi), %eax
+	movl	(%esi), %eax
 	movl	4(%esi), %edx
 
 	andl	$(~X86_EFLAGS_ZF), (%esp)
@@ -53,18 +53,30 @@ EXPORT_SYMBOL(cmpxchg8b_emu)
 
 #ifndef CONFIG_UML
 
+/*
+ * Emulate 'cmpxchg8b %fs:(%rsi)'
+ *
+ * Inputs:
+ * %esi : memory location to compare
+ * %eax : low 32 bits of old value
+ * %edx : high 32 bits of old value
+ * %ebx : low 32 bits of new value
+ * %ecx : high 32 bits of new value
+ *
+ * Notably this is not LOCK prefixed and is not safe against NMIs
+ */
 SYM_FUNC_START(this_cpu_cmpxchg8b_emu)
 
 	pushfl
 	cli
 
-	cmpl	PER_CPU_VAR(0(%esi)), %eax
+	cmpl	__percpu (%esi), %eax
 	jne	.Lnot_same2
-	cmpl	PER_CPU_VAR(4(%esi)), %edx
+	cmpl	__percpu 4(%esi), %edx
 	jne	.Lnot_same2
 
-	movl	%ebx, PER_CPU_VAR(0(%esi))
-	movl	%ecx, PER_CPU_VAR(4(%esi))
+	movl	%ebx, __percpu (%esi)
+	movl	%ecx, __percpu 4(%esi)
 
 	orl	$X86_EFLAGS_ZF, (%esp)
 
@@ -72,8 +84,8 @@ SYM_FUNC_START(this_cpu_cmpxchg8b_emu)
 	RET
 
 .Lnot_same2:
-	movl	PER_CPU_VAR(0(%esi)), %eax
-	movl	PER_CPU_VAR(4(%esi)), %edx
+	movl	__percpu (%esi), %eax
+	movl	__percpu 4(%esi), %edx
 
 	andl	$(~X86_EFLAGS_ZF), (%esp)
 
diff --git a/arch/x86/xen/xen-asm.S b/arch/x86/xen/xen-asm.S
index 9e5e680087853..448958ddbaf87 100644
--- a/arch/x86/xen/xen-asm.S
+++ b/arch/x86/xen/xen-asm.S
@@ -28,7 +28,7 @@
  * non-zero.
  */
 SYM_FUNC_START(xen_irq_disable_direct)
-	movb $1, PER_CPU_VAR(xen_vcpu_info) + XEN_vcpu_info_mask
+	movb $1, PER_CPU_VAR(xen_vcpu_info + XEN_vcpu_info_mask)
 	RET
 SYM_FUNC_END(xen_irq_disable_direct)
 
@@ -69,7 +69,7 @@ SYM_FUNC_END(check_events)
 SYM_FUNC_START(xen_irq_enable_direct)
 	FRAME_BEGIN
 	/* Unmask events */
-	movb $0, PER_CPU_VAR(xen_vcpu_info) + XEN_vcpu_info_mask
+	movb $0, PER_CPU_VAR(xen_vcpu_info + XEN_vcpu_info_mask)
 
 	/*
 	 * Preempt here doesn't matter because that will deal with any
@@ -78,7 +78,7 @@ SYM_FUNC_START(xen_irq_enable_direct)
 	 */
 
 	/* Test for pending */
-	testb $0xff, PER_CPU_VAR(xen_vcpu_info) + XEN_vcpu_info_pending
+	testb $0xff, PER_CPU_VAR(xen_vcpu_info + XEN_vcpu_info_pending)
 	jz 1f
 
 	call check_events
@@ -97,7 +97,7 @@ SYM_FUNC_END(xen_irq_enable_direct)
  * x86 use opposite senses (mask vs enable).
  */
 SYM_FUNC_START(xen_save_fl_direct)
-	testb $0xff, PER_CPU_VAR(xen_vcpu_info) + XEN_vcpu_info_mask
+	testb $0xff, PER_CPU_VAR(xen_vcpu_info + XEN_vcpu_info_mask)
 	setz %ah
 	addb %ah, %ah
 	RET
@@ -113,7 +113,7 @@ SYM_FUNC_END(xen_read_cr2);
 
 SYM_FUNC_START(xen_read_cr2_direct)
 	FRAME_BEGIN
-	_ASM_MOV PER_CPU_VAR(xen_vcpu_info) + XEN_vcpu_info_arch_cr2, %_ASM_AX
+	_ASM_MOV PER_CPU_VAR(xen_vcpu_info + XEN_vcpu_info_arch_cr2), %_ASM_AX
 	FRAME_END
 	RET
 SYM_FUNC_END(xen_read_cr2_direct);
diff --git a/include/linux/compiler.h b/include/linux/compiler.h
index bb1339c7057b4..cdcdaa48b4d2d 100644
--- a/include/linux/compiler.h
+++ b/include/linux/compiler.h
@@ -209,7 +209,7 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val,
  */
 #define ___ADDRESSABLE(sym, __attrs) \
 	static void * __used __attrs \
-		__UNIQUE_ID(__PASTE(__addressable_,sym)) = (void *)&sym;
+	__UNIQUE_ID(__PASTE(__addressable_,sym)) = (void *)(uintptr_t)&sym;
 #define __ADDRESSABLE(sym) \
 	___ADDRESSABLE(sym, __section(".discard.addressable"))