Merging upstream version 5.10.216.

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

22 files changed, 298 insertions, 142 deletions

diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index 3b4412c83..01064ba1a 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -12,6 +12,7 @@
 #include <asm/mpspec.h>
 #include <asm/msr.h>
 #include <asm/hardirq.h>
+#include <asm/io.h>
 
 #define ARCH_APICTIMER_STOPS_ON_C3	1
 
@@ -111,7 +112,7 @@ static inline void native_apic_mem_write(u32 reg, u32 v)
 
 static inline u32 native_apic_mem_read(u32 reg)
 {
-	return *((volatile u32 *)(APIC_BASE + reg));
+	return readl((void __iomem *)(APIC_BASE + reg));
 }
 
 extern void native_apic_wait_icr_idle(void);
diff --git a/arch/x86/include/asm/asm-prototypes.h b/arch/x86/include/asm/asm-prototypes.h
index 8f80de627..5cdccea45 100644
--- a/arch/x86/include/asm/asm-prototypes.h
+++ b/arch/x86/include/asm/asm-prototypes.h
@@ -12,6 +12,7 @@
 #include <asm/special_insns.h>
 #include <asm/preempt.h>
 #include <asm/asm.h>
+#include <asm/nospec-branch.h>
 
 #ifndef CONFIG_X86_CMPXCHG64
 extern void cmpxchg8b_emu(void);
diff --git a/arch/x86/include/asm/asm.h b/arch/x86/include/asm/asm.h
index 0603c7423..c01005d7a 100644
--- a/arch/x86/include/asm/asm.h
+++ b/arch/x86/include/asm/asm.h
@@ -6,12 +6,14 @@
 # define __ASM_FORM(x)	x
 # define __ASM_FORM_RAW(x)     x
 # define __ASM_FORM_COMMA(x) x,
+# define __ASM_REGPFX			%
 #else
 #include <linux/stringify.h>
 
 # define __ASM_FORM(x)	" " __stringify(x) " "
 # define __ASM_FORM_RAW(x)     __stringify(x)
 # define __ASM_FORM_COMMA(x) " " __stringify(x) ","
+# define __ASM_REGPFX			%%
 #endif
 
 #ifndef __x86_64__
@@ -48,6 +50,9 @@
 #define _ASM_SI		__ASM_REG(si)
 #define _ASM_DI		__ASM_REG(di)
 
+/* Adds a (%rip) suffix on 64 bits only; for immediate memory references */
+#define _ASM_RIP(x)	__ASM_SEL_RAW(x, x (__ASM_REGPFX rip))
+
 #ifndef __x86_64__
 /* 32 bit */
 
diff --git a/arch/x86/include/asm/cpu_entry_area.h b/arch/x86/include/asm/cpu_entry_area.h
index dd5ea1bdf..75efc4c6f 100644
--- a/arch/x86/include/asm/cpu_entry_area.h
+++ b/arch/x86/include/asm/cpu_entry_area.h
@@ -143,7 +143,7 @@ extern void cea_set_pte(void *cea_vaddr, phys_addr_t pa, pgprot_t flags);
 
 extern struct cpu_entry_area *get_cpu_entry_area(int cpu);
 
-static inline struct entry_stack *cpu_entry_stack(int cpu)
+static __always_inline struct entry_stack *cpu_entry_stack(int cpu)
 {
 	return &get_cpu_entry_area(cpu)->entry_stack_page.stack;
 }
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index cc3f62f5d..955ca6b13 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -33,6 +33,8 @@ enum cpuid_leafs
 	CPUID_7_EDX,
 	CPUID_8000_001F_EAX,
 	CPUID_8000_0021_EAX,
+	CPUID_LNX_5,
+	NR_CPUID_WORDS,
 };
 
 #ifdef CONFIG_X86_FEATURE_NAMES
@@ -93,8 +95,9 @@ extern const char * const x86_bug_flags[NBUGINTS*32];
 	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 18, feature_bit) ||	\
 	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 19, feature_bit) ||	\
 	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 20, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(REQUIRED_MASK, 21, feature_bit) ||	\
 	   REQUIRED_MASK_CHECK					  ||	\
-	   BUILD_BUG_ON_ZERO(NCAPINTS != 21))
+	   BUILD_BUG_ON_ZERO(NCAPINTS != 22))
 
 #define DISABLED_MASK_BIT_SET(feature_bit)				\
 	 ( CHECK_BIT_IN_MASK_WORD(DISABLED_MASK,  0, feature_bit) ||	\
@@ -118,8 +121,9 @@ extern const char * const x86_bug_flags[NBUGINTS*32];
 	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 18, feature_bit) ||	\
 	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 19, feature_bit) ||	\
 	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 20, feature_bit) ||	\
+	   CHECK_BIT_IN_MASK_WORD(DISABLED_MASK, 21, feature_bit) ||	\
 	   DISABLED_MASK_CHECK					  ||	\
-	   BUILD_BUG_ON_ZERO(NCAPINTS != 21))
+	   BUILD_BUG_ON_ZERO(NCAPINTS != 22))
 
 #define cpu_has(c, bit)							\
 	(__builtin_constant_p(bit) && REQUIRED_MASK_BIT_SET(bit) ? 1 :	\
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index 5a54c3685..e1bc2bad8 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -13,7 +13,7 @@
 /*
  * Defines x86 CPU feature bits
  */
-#define NCAPINTS			21	   /* N 32-bit words worth of info */
+#define NCAPINTS			22	   /* N 32-bit words worth of info */
 #define NBUGINTS			2	   /* N 32-bit bug flags */
 
 /*
@@ -300,6 +300,7 @@
 #define X86_FEATURE_USE_IBPB_FW		(11*32+16) /* "" Use IBPB during runtime firmware calls */
 #define X86_FEATURE_RSB_VMEXIT_LITE	(11*32+17) /* "" Fill RSB on VM exit when EIBRS is enabled */
 #define X86_FEATURE_MSR_TSX_CTRL	(11*32+18) /* "" MSR IA32_TSX_CTRL (Intel) implemented */
+#define X86_FEATURE_CLEAR_CPU_BUF	(11*32+19) /* "" Clear CPU buffers using VERW */
 
 #define X86_FEATURE_SRSO		(11*32+24) /* "" AMD BTB untrain RETs */
 #define X86_FEATURE_SRSO_ALIAS		(11*32+25) /* "" AMD BTB untrain RETs through aliasing */
@@ -403,6 +404,7 @@
 #define X86_FEATURE_SEV_ES		(19*32+ 3) /* AMD Secure Encrypted Virtualization - Encrypted State */
 #define X86_FEATURE_SME_COHERENT	(19*32+10) /* "" AMD hardware-enforced cache coherency */
 
+#define X86_FEATURE_AUTOIBRS		(20*32+ 8) /* "" Automatic IBRS */
 #define X86_FEATURE_SBPB		(20*32+27) /* "" Selective Branch Prediction Barrier */
 #define X86_FEATURE_IBPB_BRTYPE		(20*32+28) /* "" MSR_PRED_CMD[IBPB] flushes all branch type predictions */
 #define X86_FEATURE_SRSO_NO		(20*32+29) /* "" CPU is not affected by SRSO */
@@ -452,4 +454,5 @@
 /* BUG word 2 */
 #define X86_BUG_SRSO			X86_BUG(1*32 + 0) /* AMD SRSO bug */
 #define X86_BUG_DIV0			X86_BUG(1*32 + 1) /* AMD DIV0 speculation bug */
+#define X86_BUG_RFDS			X86_BUG(1*32 + 2) /* CPU is vulnerable to Register File Data Sampling */
 #endif /* _ASM_X86_CPUFEATURES_H */
diff --git a/arch/x86/include/asm/disabled-features.h b/arch/x86/include/asm/disabled-features.h
index 3c24378e6..e5f44a3e2 100644
--- a/arch/x86/include/asm/disabled-features.h
+++ b/arch/x86/include/asm/disabled-features.h
@@ -103,6 +103,7 @@
 #define DISABLED_MASK18	0
 #define DISABLED_MASK19	0
 #define DISABLED_MASK20	0
-#define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 21)
+#define DISABLED_MASK21	0
+#define DISABLED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 22)
 
 #endif /* _ASM_X86_DISABLED_FEATURES_H */
diff --git a/arch/x86/include/asm/entry-common.h b/arch/x86/include/asm/entry-common.h
index 5443851d3..264ab414e 100644
--- a/arch/x86/include/asm/entry-common.h
+++ b/arch/x86/include/asm/entry-common.h
@@ -77,7 +77,6 @@ static inline void arch_exit_to_user_mode_prepare(struct pt_regs *regs,
 
 static __always_inline void arch_exit_to_user_mode(void)
 {
-	mds_user_clear_cpu_buffers();
 	amd_clear_divider();
 }
 #define arch_exit_to_user_mode arch_exit_to_user_mode
diff --git a/arch/x86/include/asm/irqflags.h b/arch/x86/include/asm/irqflags.h
index 8c86edefa..f40dea50d 100644
--- a/arch/x86/include/asm/irqflags.h
+++ b/arch/x86/include/asm/irqflags.h
@@ -134,6 +134,7 @@ static __always_inline unsigned long arch_local_irq_save(void)
 #define INTERRUPT_RETURN	jmp native_iret
 #define USERGS_SYSRET64				\
 	swapgs;					\
+	CLEAR_CPU_BUFFERS;			\
 	sysretq;
 #define USERGS_SYSRET32				\
 	swapgs;					\
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 7d7a3cbb8..52a6d43ed 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -30,6 +30,7 @@
 #define _EFER_SVME		12 /* Enable virtualization */
 #define _EFER_LMSLE		13 /* Long Mode Segment Limit Enable */
 #define _EFER_FFXSR		14 /* Enable Fast FXSAVE/FXRSTOR */
+#define _EFER_AUTOIBRS		21 /* Enable Automatic IBRS */
 
 #define EFER_SCE		(1<<_EFER_SCE)
 #define EFER_LME		(1<<_EFER_LME)
@@ -38,6 +39,7 @@
 #define EFER_SVME		(1<<_EFER_SVME)
 #define EFER_LMSLE		(1<<_EFER_LMSLE)
 #define EFER_FFXSR		(1<<_EFER_FFXSR)
+#define EFER_AUTOIBRS		(1<<_EFER_AUTOIBRS)
 
 /* Intel MSRs. Some also available on other CPUs */
 
@@ -166,6 +168,14 @@
 						 * CPU is not vulnerable to Gather
 						 * Data Sampling (GDS).
 						 */
+#define ARCH_CAP_RFDS_NO		BIT(27)	/*
+						 * Not susceptible to Register
+						 * File Data Sampling.
+						 */
+#define ARCH_CAP_RFDS_CLEAR		BIT(28)	/*
+						 * VERW clears CPU Register
+						 * File.
+						 */
 
 #define MSR_IA32_FLUSH_CMD		0x0000010b
 #define L1D_FLUSH			BIT(0)	/*
diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index 7b4782249..87e1ff064 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -155,11 +155,20 @@
 .Lskip_rsb_\@:
 .endm
 
+/*
+ * The CALL to srso_alias_untrain_ret() must be patched in directly at
+ * the spot where untraining must be done, ie., srso_alias_untrain_ret()
+ * must be the target of a CALL instruction instead of indirectly
+ * jumping to a wrapper which then calls it. Therefore, this macro is
+ * called outside of __UNTRAIN_RET below, for the time being, before the
+ * kernel can support nested alternatives with arbitrary nesting.
+ */
+.macro CALL_UNTRAIN_RET
 #ifdef CONFIG_CPU_UNRET_ENTRY
-#define CALL_UNTRAIN_RET	"call entry_untrain_ret"
-#else
-#define CALL_UNTRAIN_RET	""
+	ALTERNATIVE_2 "", "call entry_untrain_ret", X86_FEATURE_UNRET, \
+		          "call srso_alias_untrain_ret", X86_FEATURE_SRSO_ALIAS
 #endif
+.endm
 
 /*
  * Mitigate RETBleed for AMD/Hygon Zen uarch. Requires KERNEL CR3 because the
@@ -176,12 +185,24 @@
 #if defined(CONFIG_CPU_UNRET_ENTRY) || defined(CONFIG_CPU_IBPB_ENTRY) || \
 	defined(CONFIG_CPU_SRSO)
 	ANNOTATE_UNRET_END
-	ALTERNATIVE_2 "",						\
-		      CALL_UNTRAIN_RET, X86_FEATURE_UNRET,		\
-		      "call entry_ibpb", X86_FEATURE_ENTRY_IBPB
+	CALL_UNTRAIN_RET
+	ALTERNATIVE "", "call entry_ibpb", X86_FEATURE_ENTRY_IBPB
 #endif
 .endm
 
+/*
+ * Macro to execute VERW instruction that mitigate transient data sampling
+ * attacks such as MDS. On affected systems a microcode update overloaded VERW
+ * instruction to also clear the CPU buffers. VERW clobbers CFLAGS.ZF.
+ *
+ * Note: Only the memory operand variant of VERW clears the CPU buffers.
+ */
+.macro CLEAR_CPU_BUFFERS
+	ALTERNATIVE "jmp .Lskip_verw_\@", "", X86_FEATURE_CLEAR_CPU_BUF
+	verw _ASM_RIP(mds_verw_sel)
+.Lskip_verw_\@:
+.endm
+
 #else /* __ASSEMBLY__ */
 
 #define ANNOTATE_RETPOLINE_SAFE					\
@@ -207,6 +228,8 @@ extern void srso_alias_untrain_ret(void);
 extern void entry_untrain_ret(void);
 extern void entry_ibpb(void);
 
+extern void (*x86_return_thunk)(void);
+
 #ifdef CONFIG_RETPOLINE
 
 typedef u8 retpoline_thunk_t[RETPOLINE_THUNK_SIZE];
@@ -355,11 +378,12 @@ DECLARE_STATIC_KEY_FALSE(switch_to_cond_stibp);
 DECLARE_STATIC_KEY_FALSE(switch_mm_cond_ibpb);
 DECLARE_STATIC_KEY_FALSE(switch_mm_always_ibpb);
 
-DECLARE_STATIC_KEY_FALSE(mds_user_clear);
 DECLARE_STATIC_KEY_FALSE(mds_idle_clear);
 
 DECLARE_STATIC_KEY_FALSE(mmio_stale_data_clear);
 
+extern u16 mds_verw_sel;
+
 #include <asm/segment.h>
 
 /**
@@ -386,17 +410,6 @@ static __always_inline void mds_clear_cpu_buffers(void)
 }
 
 /**
- * mds_user_clear_cpu_buffers - Mitigation for MDS and TAA vulnerability
- *
- * Clear CPU buffers if the corresponding static key is enabled
- */
-static __always_inline void mds_user_clear_cpu_buffers(void)
-{
-	if (static_branch_likely(&mds_user_clear))
-		mds_clear_cpu_buffers();
-}
-
-/**
  * mds_idle_clear_cpu_buffers - Mitigation for MDS vulnerability
  *
  * Clear CPU buffers if the corresponding static key is enabled
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index d7e017b0b..6dc3c5f0b 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -441,6 +441,9 @@ 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;
@@ -461,17 +464,7 @@ extern asmlinkage void ignore_sysret(void);
 void current_save_fsgs(void);
 #else	/* X86_64 */
 #ifdef CONFIG_STACKPROTECTOR
-/*
- * Make sure stack canary segment base is cached-aligned:
- *   "For Intel Atom processors, avoid non zero segment base address
- *    that is not aligned to cache line boundary at all cost."
- * (Optim Ref Manual Assembly/Compiler Coding Rule 15.)
- */
-struct stack_canary {
-	char __pad[20];		/* canary at %gs:20 */
-	unsigned long canary;
-};
-DECLARE_PER_CPU_ALIGNED(struct stack_canary, stack_canary);
+DECLARE_PER_CPU(unsigned long, __stack_chk_guard);
 #endif
 /* Per CPU softirq stack pointer */
 DECLARE_PER_CPU(struct irq_stack *, softirq_stack_ptr);
diff --git a/arch/x86/include/asm/ptrace.h b/arch/x86/include/asm/ptrace.h
index 409f66148..b94f61560 100644
--- a/arch/x86/include/asm/ptrace.h
+++ b/arch/x86/include/asm/ptrace.h
@@ -37,7 +37,10 @@ struct pt_regs {
 	unsigned short __esh;
 	unsigned short fs;
 	unsigned short __fsh;
-	/* On interrupt, gs and __gsh store the vector number. */
+	/*
+	 * On interrupt, gs and __gsh store the vector number.  They never
+	 * store gs any more.
+	 */
 	unsigned short gs;
 	unsigned short __gsh;
 	/* On interrupt, this is the error code. */
diff --git a/arch/x86/include/asm/required-features.h b/arch/x86/include/asm/required-features.h
index 9bf60a8b9..1fbe53583 100644
--- a/arch/x86/include/asm/required-features.h
+++ b/arch/x86/include/asm/required-features.h
@@ -103,6 +103,7 @@
 #define REQUIRED_MASK18	0
 #define REQUIRED_MASK19	0
 #define REQUIRED_MASK20	0
-#define REQUIRED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 21)
+#define REQUIRED_MASK21	0
+#define REQUIRED_MASK_CHECK BUILD_BUG_ON_ZERO(NCAPINTS != 22)
 
 #endif /* _ASM_X86_REQUIRED_FEATURES_H */
diff --git a/arch/x86/include/asm/segment.h b/arch/x86/include/asm/segment.h
index 7fdd4facf..72044026e 100644
--- a/arch/x86/include/asm/segment.h
+++ b/arch/x86/include/asm/segment.h
@@ -95,7 +95,7 @@
  *
  *  26 - ESPFIX small SS
  *  27 - per-cpu			[ offset to per-cpu data area ]
- *  28 - stack_canary-20		[ for stack protector ]		<=== cacheline #8
+ *  28 - unused
  *  29 - unused
  *  30 - unused
  *  31 - TSS for double fault handler
@@ -118,7 +118,6 @@
 
 #define GDT_ENTRY_ESPFIX_SS		26
 #define GDT_ENTRY_PERCPU		27
-#define GDT_ENTRY_STACK_CANARY		28
 
 #define GDT_ENTRY_DOUBLEFAULT_TSS	31
 
@@ -158,12 +157,6 @@
 # define __KERNEL_PERCPU		0
 #endif
 
-#ifdef CONFIG_STACKPROTECTOR
-# define __KERNEL_STACK_CANARY		(GDT_ENTRY_STACK_CANARY*8)
-#else
-# define __KERNEL_STACK_CANARY		0
-#endif
-
 #else /* 64-bit: */
 
 #include <asm/cache.h>
@@ -364,22 +357,15 @@ static inline void __loadsegment_fs(unsigned short value)
 	asm("mov %%" #seg ",%0":"=r" (value) : : "memory")
 
 /*
- * x86-32 user GS accessors:
+ * x86-32 user GS accessors.  This is ugly and could do with some cleaning up.
  */
 #ifdef CONFIG_X86_32
-# ifdef CONFIG_X86_32_LAZY_GS
-#  define get_user_gs(regs)		(u16)({ unsigned long v; savesegment(gs, v); v; })
-#  define set_user_gs(regs, v)		loadsegment(gs, (unsigned long)(v))
-#  define task_user_gs(tsk)		((tsk)->thread.gs)
-#  define lazy_save_gs(v)		savesegment(gs, (v))
-#  define lazy_load_gs(v)		loadsegment(gs, (v))
-# else	/* X86_32_LAZY_GS */
-#  define get_user_gs(regs)		(u16)((regs)->gs)
-#  define set_user_gs(regs, v)		do { (regs)->gs = (v); } while (0)
-#  define task_user_gs(tsk)		(task_pt_regs(tsk)->gs)
-#  define lazy_save_gs(v)		do { } while (0)
-#  define lazy_load_gs(v)		do { } while (0)
-# endif	/* X86_32_LAZY_GS */
+# define get_user_gs(regs)		(u16)({ unsigned long v; savesegment(gs, v); v; })
+# define set_user_gs(regs, v)		loadsegment(gs, (unsigned long)(v))
+# define task_user_gs(tsk)		((tsk)->thread.gs)
+# define lazy_save_gs(v)		savesegment(gs, (v))
+# define lazy_load_gs(v)		loadsegment(gs, (v))
+# define load_gs_index(v)		loadsegment(gs, (v))
 #endif	/* X86_32 */
 
 #endif /* !__ASSEMBLY__ */
diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h
index 4e1757bf6..d65bfc293 100644
--- a/arch/x86/include/asm/setup.h
+++ b/arch/x86/include/asm/setup.h
@@ -49,7 +49,6 @@ extern unsigned long saved_video_mode;
 extern void reserve_standard_io_resources(void);
 extern void i386_reserve_resources(void);
 extern unsigned long __startup_64(unsigned long physaddr, struct boot_params *bp);
-extern unsigned long __startup_secondary_64(void);
 extern void startup_64_setup_env(unsigned long physbase);
 extern void early_setup_idt(void);
 extern void __init do_early_exception(struct pt_regs *regs, int trapnr);
diff --git a/arch/x86/include/asm/stackprotector.h b/arch/x86/include/asm/stackprotector.h
index 7fb482f0f..b6ffe58c7 100644
--- a/arch/x86/include/asm/stackprotector.h
+++ b/arch/x86/include/asm/stackprotector.h
@@ -5,30 +5,23 @@
  * Stack protector works by putting 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 requires it to be at a fixed offset from %gs.
- * On x86_64, the offset is 40 bytes and on x86_32 20 bytes.  x86_64
- * and x86_32 use segment registers differently and thus handles this
- * requirement differently.
+ * 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.
  *
- * On x86_64, %gs is shared by percpu area and stack canary.  All
- * percpu symbols are zero based and %gs points to the base of percpu
- * area.  The first occupant of the percpu area is always
- * fixed_percpu_data which contains stack_canary at offset 40.  Userland
- * %gs is always saved and restored on kernel entry and exit using
- * swapgs, so stack protector doesn't add any complexity there.
+ * 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 approproate
+ * offset.  On x86_32, the stack canary is just a regular percpu
+ * variable.
  *
- * On x86_32, it's slightly more complicated.  As in x86_64, %gs is
- * used for userland TLS.  Unfortunately, some processors are much
- * slower at loading segment registers with different value when
- * entering and leaving the kernel, so the kernel uses %fs for percpu
- * area and manages %gs lazily so that %gs is switched only when
- * necessary, usually during task switch.
+ * 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.
  *
- * As gcc requires the stack canary at %gs:20, %gs can't be managed
- * lazily if stack protector is enabled, so the kernel saves and
- * restores userland %gs on kernel entry and exit.  This behavior is
- * controlled by CONFIG_X86_32_LAZY_GS and accessors are defined in
- * system.h to hide the details.
+ * Once we are willing to require GCC 8.1 or better for 64-bit stackprotector
+ * support, we can remove some of this complexity.
  */
 
 #ifndef _ASM_STACKPROTECTOR_H
@@ -45,14 +38,6 @@
 #include <linux/sched.h>
 
 /*
- * 24 byte read-only segment initializer for stack canary.  Linker
- * can't handle the address bit shifting.  Address will be set in
- * head_32 for boot CPU and setup_per_cpu_areas() for others.
- */
-#define GDT_STACK_CANARY_INIT						\
-	[GDT_ENTRY_STACK_CANARY] = GDT_ENTRY_INIT(0x4090, 0, 0x18),
-
-/*
  * Initialize the stackprotector canary value.
  *
  * NOTE: this must only be called from functions that never return
@@ -86,7 +71,7 @@ static __always_inline void boot_init_stack_canary(void)
 #ifdef CONFIG_X86_64
 	this_cpu_write(fixed_percpu_data.stack_canary, canary);
 #else
-	this_cpu_write(stack_canary.canary, canary);
+	this_cpu_write(__stack_chk_guard, canary);
 #endif
 }
 
@@ -95,48 +80,16 @@ 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_canary.canary, cpu) = idle->stack_canary;
-#endif
-}
-
-static inline void setup_stack_canary_segment(int cpu)
-{
-#ifdef CONFIG_X86_32
-	unsigned long canary = (unsigned long)&per_cpu(stack_canary, cpu);
-	struct desc_struct *gdt_table = get_cpu_gdt_rw(cpu);
-	struct desc_struct desc;
-
-	desc = gdt_table[GDT_ENTRY_STACK_CANARY];
-	set_desc_base(&desc, canary);
-	write_gdt_entry(gdt_table, GDT_ENTRY_STACK_CANARY, &desc, DESCTYPE_S);
-#endif
-}
-
-static inline void load_stack_canary_segment(void)
-{
-#ifdef CONFIG_X86_32
-	asm("mov %0, %%gs" : : "r" (__KERNEL_STACK_CANARY) : "memory");
+	per_cpu(__stack_chk_guard, cpu) = idle->stack_canary;
 #endif
 }
 
 #else	/* STACKPROTECTOR */
 
-#define GDT_STACK_CANARY_INIT
-
 /* dummy boot_init_stack_canary() is defined in linux/stackprotector.h */
 
-static inline void setup_stack_canary_segment(int cpu)
-{ }
-
 static inline void cpu_init_stack_canary(int cpu, struct task_struct *idle)
 { }
 
-static inline void load_stack_canary_segment(void)
-{
-#ifdef CONFIG_X86_32
-	asm volatile ("mov %0, %%gs" : : "r" (0));
-#endif
-}
-
 #endif	/* STACKPROTECTOR */
 #endif	/* _ASM_STACKPROTECTOR_H */
diff --git a/arch/x86/include/asm/suspend_32.h b/arch/x86/include/asm/suspend_32.h
index 3b97aa921..d8416b3bf 100644
--- a/arch/x86/include/asm/suspend_32.h
+++ b/arch/x86/include/asm/suspend_32.h
@@ -12,13 +12,6 @@
 
 /* image of the saved processor state */
 struct saved_context {
-	/*
-	 * On x86_32, all segment registers, with the possible exception of
-	 * gs, are saved at kernel entry in pt_regs.
-	 */
-#ifdef CONFIG_X86_32_LAZY_GS
-	u16 gs;
-#endif
 	unsigned long cr0, cr2, cr3, cr4;
 	u64 misc_enable;
 	struct saved_msrs saved_msrs;
@@ -29,6 +22,11 @@ struct saved_context {
 	unsigned long tr;
 	unsigned long safety;
 	unsigned long return_address;
+	/*
+	 * On x86_32, all segment registers except gs are saved at kernel
+	 * entry in pt_regs.
+	 */
+	u16 gs;
 	bool misc_enable_saved;
 } __attribute__((packed));
 
diff --git a/arch/x86/include/asm/syscall_wrapper.h b/arch/x86/include/asm/syscall_wrapper.h
index a84333ade..a507be368 100644
--- a/arch/x86/include/asm/syscall_wrapper.h
+++ b/arch/x86/include/asm/syscall_wrapper.h
@@ -58,12 +58,29 @@ extern long __ia32_sys_ni_syscall(const struct pt_regs *regs);
 		,,regs->di,,regs->si,,regs->dx				\
 		,,regs->r10,,regs->r8,,regs->r9)			\
 
+
+/* SYSCALL_PT_ARGS is Adapted from s390x */
+#define SYSCALL_PT_ARG6(m, t1, t2, t3, t4, t5, t6)			\
+	SYSCALL_PT_ARG5(m, t1, t2, t3, t4, t5), m(t6, (regs->bp))
+#define SYSCALL_PT_ARG5(m, t1, t2, t3, t4, t5)				\
+	SYSCALL_PT_ARG4(m, t1, t2, t3, t4),  m(t5, (regs->di))
+#define SYSCALL_PT_ARG4(m, t1, t2, t3, t4)				\
+	SYSCALL_PT_ARG3(m, t1, t2, t3),  m(t4, (regs->si))
+#define SYSCALL_PT_ARG3(m, t1, t2, t3)					\
+	SYSCALL_PT_ARG2(m, t1, t2), m(t3, (regs->dx))
+#define SYSCALL_PT_ARG2(m, t1, t2)					\
+	SYSCALL_PT_ARG1(m, t1), m(t2, (regs->cx))
+#define SYSCALL_PT_ARG1(m, t1) m(t1, (regs->bx))
+#define SYSCALL_PT_ARGS(x, ...) SYSCALL_PT_ARG##x(__VA_ARGS__)
+
+#define __SC_COMPAT_CAST(t, a)						\
+	(__typeof(__builtin_choose_expr(__TYPE_IS_L(t), 0, 0U)))	\
+	(unsigned int)a
+
 /* Mapping of registers to parameters for syscalls on i386 */
 #define SC_IA32_REGS_TO_ARGS(x, ...)					\
-	__MAP(x,__SC_ARGS						\
-	      ,,(unsigned int)regs->bx,,(unsigned int)regs->cx		\
-	      ,,(unsigned int)regs->dx,,(unsigned int)regs->si		\
-	      ,,(unsigned int)regs->di,,(unsigned int)regs->bp)
+	SYSCALL_PT_ARGS(x, __SC_COMPAT_CAST,				\
+			__MAP(x, __SC_TYPE, __VA_ARGS__))		\
 
 #define __SYS_STUB0(abi, name)						\
 	long __##abi##_##name(const struct pt_regs *regs);		\
diff --git a/arch/x86/include/asm/text-patching.h b/arch/x86/include/asm/text-patching.h
index b7421780e..c6015b407 100644
--- a/arch/x86/include/asm/text-patching.h
+++ b/arch/x86/include/asm/text-patching.h
@@ -96,24 +96,40 @@ union text_poke_insn {
 };
 
 static __always_inline
-void *text_gen_insn(u8 opcode, const void *addr, const void *dest)
+void __text_gen_insn(void *buf, u8 opcode, const void *addr, const void *dest, int size)
 {
-	static union text_poke_insn insn; /* per instance */
-	int size = text_opcode_size(opcode);
+	union text_poke_insn *insn = buf;
+
+	BUG_ON(size < text_opcode_size(opcode));
+
+	/*
+	 * Hide the addresses to avoid the compiler folding in constants when
+	 * referencing code, these can mess up annotations like
+	 * ANNOTATE_NOENDBR.
+	 */
+	OPTIMIZER_HIDE_VAR(insn);
+	OPTIMIZER_HIDE_VAR(addr);
+	OPTIMIZER_HIDE_VAR(dest);
 
-	insn.opcode = opcode;
+	insn->opcode = opcode;
 
 	if (size > 1) {
-		insn.disp = (long)dest - (long)(addr + size);
+		insn->disp = (long)dest - (long)(addr + size);
 		if (size == 2) {
 			/*
-			 * Ensure that for JMP9 the displacement
+			 * Ensure that for JMP8 the displacement
 			 * actually fits the signed byte.
 			 */
-			BUG_ON((insn.disp >> 31) != (insn.disp >> 7));
+			BUG_ON((insn->disp >> 31) != (insn->disp >> 7));
 		}
 	}
+}
 
+static __always_inline
+void *text_gen_insn(u8 opcode, const void *addr, const void *dest)
+{
+	static union text_poke_insn insn; /* per instance */
+	__text_gen_insn(&insn, opcode, addr, dest, text_opcode_size(opcode));
 	return &insn.text;
 }
 
diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index bf2561a5e..3616fd4ba 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -414,6 +414,103 @@ do {									\
 
 #endif // CONFIG_CC_ASM_GOTO_OUTPUT
 
+#ifdef CONFIG_CC_HAS_ASM_GOTO_TIED_OUTPUT
+#define __try_cmpxchg_user_asm(itype, ltype, _ptr, _pold, _new, label)	({ \
+	bool success;							\
+	__typeof__(_ptr) _old = (__typeof__(_ptr))(_pold);		\
+	__typeof__(*(_ptr)) __old = *_old;				\
+	__typeof__(*(_ptr)) __new = (_new);				\
+	asm_volatile_goto("\n"						\
+		     "1: " LOCK_PREFIX "cmpxchg"itype" %[new], %[ptr]\n"\
+		     _ASM_EXTABLE_UA(1b, %l[label])			\
+		     : CC_OUT(z) (success),				\
+		       [ptr] "+m" (*_ptr),				\
+		       [old] "+a" (__old)				\
+		     : [new] ltype (__new)				\
+		     : "memory"						\
+		     : label);						\
+	if (unlikely(!success))						\
+		*_old = __old;						\
+	likely(success);					})
+
+#ifdef CONFIG_X86_32
+#define __try_cmpxchg64_user_asm(_ptr, _pold, _new, label)	({	\
+	bool success;							\
+	__typeof__(_ptr) _old = (__typeof__(_ptr))(_pold);		\
+	__typeof__(*(_ptr)) __old = *_old;				\
+	__typeof__(*(_ptr)) __new = (_new);				\
+	asm_volatile_goto("\n"						\
+		     "1: " LOCK_PREFIX "cmpxchg8b %[ptr]\n"		\
+		     _ASM_EXTABLE_UA(1b, %l[label])			\
+		     : CC_OUT(z) (success),				\
+		       "+A" (__old),					\
+		       [ptr] "+m" (*_ptr)				\
+		     : "b" ((u32)__new),				\
+		       "c" ((u32)((u64)__new >> 32))			\
+		     : "memory"						\
+		     : label);						\
+	if (unlikely(!success))						\
+		*_old = __old;						\
+	likely(success);					})
+#endif // CONFIG_X86_32
+#else  // !CONFIG_CC_HAS_ASM_GOTO_TIED_OUTPUT
+#define __try_cmpxchg_user_asm(itype, ltype, _ptr, _pold, _new, label)	({ \
+	int __err = 0;							\
+	bool success;							\
+	__typeof__(_ptr) _old = (__typeof__(_ptr))(_pold);		\
+	__typeof__(*(_ptr)) __old = *_old;				\
+	__typeof__(*(_ptr)) __new = (_new);				\
+	asm volatile("\n"						\
+		     "1: " LOCK_PREFIX "cmpxchg"itype" %[new], %[ptr]\n"\
+		     CC_SET(z)						\
+		     "2:\n"						\
+		     _ASM_EXTABLE_TYPE_REG(1b, 2b, EX_TYPE_EFAULT_REG,	\
+					   %[errout])			\
+		     : CC_OUT(z) (success),				\
+		       [errout] "+r" (__err),				\
+		       [ptr] "+m" (*_ptr),				\
+		       [old] "+a" (__old)				\
+		     : [new] ltype (__new)				\
+		     : "memory");					\
+	if (unlikely(__err))						\
+		goto label;						\
+	if (unlikely(!success))						\
+		*_old = __old;						\
+	likely(success);					})
+
+#ifdef CONFIG_X86_32
+/*
+ * Unlike the normal CMPXCHG, hardcode ECX for both success/fail and error.
+ * There are only six GPRs available and four (EAX, EBX, ECX, and EDX) are
+ * hardcoded by CMPXCHG8B, leaving only ESI and EDI.  If the compiler uses
+ * both ESI and EDI for the memory operand, compilation will fail if the error
+ * is an input+output as there will be no register available for input.
+ */
+#define __try_cmpxchg64_user_asm(_ptr, _pold, _new, label)	({	\
+	int __result;							\
+	__typeof__(_ptr) _old = (__typeof__(_ptr))(_pold);		\
+	__typeof__(*(_ptr)) __old = *_old;				\
+	__typeof__(*(_ptr)) __new = (_new);				\
+	asm volatile("\n"						\
+		     "1: " LOCK_PREFIX "cmpxchg8b %[ptr]\n"		\
+		     "mov $0, %%ecx\n\t"				\
+		     "setz %%cl\n"					\
+		     "2:\n"						\
+		     _ASM_EXTABLE_TYPE_REG(1b, 2b, EX_TYPE_EFAULT_REG, %%ecx) \
+		     : [result]"=c" (__result),				\
+		       "+A" (__old),					\
+		       [ptr] "+m" (*_ptr)				\
+		     : "b" ((u32)__new),				\
+		       "c" ((u32)((u64)__new >> 32))			\
+		     : "memory", "cc");					\
+	if (unlikely(__result < 0))					\
+		goto label;						\
+	if (unlikely(!__result))					\
+		*_old = __old;						\
+	likely(__result);					})
+#endif // CONFIG_X86_32
+#endif // CONFIG_CC_HAS_ASM_GOTO_TIED_OUTPUT
+
 /* FIXME: this hack is definitely wrong -AK */
 struct __large_struct { unsigned long buf[100]; };
 #define __m(x) (*(struct __large_struct __user *)(x))
@@ -506,6 +603,51 @@ do {										\
 } while (0)
 #endif // CONFIG_CC_HAS_ASM_GOTO_OUTPUT
 
+extern void __try_cmpxchg_user_wrong_size(void);
+
+#ifndef CONFIG_X86_32
+#define __try_cmpxchg64_user_asm(_ptr, _oldp, _nval, _label)		\
+	__try_cmpxchg_user_asm("q", "r", (_ptr), (_oldp), (_nval), _label)
+#endif
+
+/*
+ * Force the pointer to u<size> to match the size expected by the asm helper.
+ * clang/LLVM compiles all cases and only discards the unused paths after
+ * processing errors, which breaks i386 if the pointer is an 8-byte value.
+ */
+#define unsafe_try_cmpxchg_user(_ptr, _oldp, _nval, _label) ({			\
+	bool __ret;								\
+	__chk_user_ptr(_ptr);							\
+	switch (sizeof(*(_ptr))) {						\
+	case 1:	__ret = __try_cmpxchg_user_asm("b", "q",			\
+					       (__force u8 *)(_ptr), (_oldp),	\
+					       (_nval), _label);		\
+		break;								\
+	case 2:	__ret = __try_cmpxchg_user_asm("w", "r",			\
+					       (__force u16 *)(_ptr), (_oldp),	\
+					       (_nval), _label);		\
+		break;								\
+	case 4:	__ret = __try_cmpxchg_user_asm("l", "r",			\
+					       (__force u32 *)(_ptr), (_oldp),	\
+					       (_nval), _label);		\
+		break;								\
+	case 8:	__ret = __try_cmpxchg64_user_asm((__force u64 *)(_ptr), (_oldp),\
+						 (_nval), _label);		\
+		break;								\
+	default: __try_cmpxchg_user_wrong_size();				\
+	}									\
+	__ret;						})
+
+/* "Returns" 0 on success, 1 on failure, -EFAULT if the access faults. */
+#define __try_cmpxchg_user(_ptr, _oldp, _nval, _label)	({		\
+	int __ret = -EFAULT;						\
+	__uaccess_begin_nospec();					\
+	__ret = !unsafe_try_cmpxchg_user(_ptr, _oldp, _nval, _label);	\
+_label:									\
+	__uaccess_end();						\
+	__ret;								\
+							})
+
 /*
  * We want the unsafe accessors to always be inlined and use
  * the error labels - thus the macro games.
diff --git a/arch/x86/include/asm/vsyscall.h b/arch/x86/include/asm/vsyscall.h
index ab60a71a8..472f0263d 100644
--- a/arch/x86/include/asm/vsyscall.h
+++ b/arch/x86/include/asm/vsyscall.h
@@ -4,6 +4,7 @@
 
 #include <linux/seqlock.h>
 #include <uapi/asm/vsyscall.h>
+#include <asm/page_types.h>
 
 #ifdef CONFIG_X86_VSYSCALL_EMULATION
 extern void map_vsyscall(void);
@@ -24,4 +25,13 @@ static inline bool emulate_vsyscall(unsigned long error_code,
 }
 #endif
 
+/*
+ * The (legacy) vsyscall page is the long page in the kernel portion
+ * of the address space that has user-accessible permissions.
+ */
+static inline bool is_vsyscall_vaddr(unsigned long vaddr)
+{
+	return unlikely((vaddr & PAGE_MASK) == VSYSCALL_ADDR);
+}
+
 #endif /* _ASM_X86_VSYSCALL_H */