Update Linux to v5.10.157

Sourced from [1]

[1] https://cdn.kernel.org/pub/linux/kernel/v5.x/linux-5.10.157.tar.xz

Signed-off-by: Olivier Deprez <olivier.deprez@arm.com>
Change-Id: I7b30d9e98d8c465d6b44de8e7433b4a40b3289ba
diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index 4d0f538..07f5030 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -5,12 +5,15 @@
 
 #include <linux/static_key.h>
 #include <linux/objtool.h>
+#include <linux/linkage.h>
 
 #include <asm/alternative.h>
-#include <asm/alternative-asm.h>
 #include <asm/cpufeatures.h>
 #include <asm/msr-index.h>
 #include <asm/unwind_hints.h>
+#include <asm/percpu.h>
+
+#define RETPOLINE_THUNK_SIZE	32
 
 /*
  * Fill the CPU return stack buffer.
@@ -32,32 +35,57 @@
 #define RSB_CLEAR_LOOPS		32	/* To forcibly overwrite all entries */
 
 /*
+ * Common helper for __FILL_RETURN_BUFFER and __FILL_ONE_RETURN.
+ */
+#define __FILL_RETURN_SLOT			\
+	ANNOTATE_INTRA_FUNCTION_CALL;		\
+	call	772f;				\
+	int3;					\
+772:
+
+/*
+ * Stuff the entire RSB.
+ *
  * Google experimented with loop-unrolling and this turned out to be
  * the optimal version — two calls, each with their own speculation
  * trap should their return address end up getting used, in a loop.
  */
-#define __FILL_RETURN_BUFFER(reg, nr, sp)	\
-	mov	$(nr/2), reg;			\
-771:						\
-	ANNOTATE_INTRA_FUNCTION_CALL;		\
-	call	772f;				\
-773:	/* speculation trap */			\
-	UNWIND_HINT_EMPTY;			\
-	pause;					\
-	lfence;					\
-	jmp	773b;				\
-772:						\
-	ANNOTATE_INTRA_FUNCTION_CALL;		\
-	call	774f;				\
-775:	/* speculation trap */			\
-	UNWIND_HINT_EMPTY;			\
-	pause;					\
-	lfence;					\
-	jmp	775b;				\
-774:						\
-	add	$(BITS_PER_LONG/8) * 2, sp;	\
-	dec	reg;				\
-	jnz	771b;
+#ifdef CONFIG_X86_64
+#define __FILL_RETURN_BUFFER(reg, nr)			\
+	mov	$(nr/2), reg;				\
+771:							\
+	__FILL_RETURN_SLOT				\
+	__FILL_RETURN_SLOT				\
+	add	$(BITS_PER_LONG/8) * 2, %_ASM_SP;	\
+	dec	reg;					\
+	jnz	771b;					\
+	/* barrier for jnz misprediction */		\
+	lfence;
+#else
+/*
+ * i386 doesn't unconditionally have LFENCE, as such it can't
+ * do a loop.
+ */
+#define __FILL_RETURN_BUFFER(reg, nr)			\
+	.rept nr;					\
+	__FILL_RETURN_SLOT;				\
+	.endr;						\
+	add	$(BITS_PER_LONG/8) * nr, %_ASM_SP;
+#endif
+
+/*
+ * Stuff a single RSB slot.
+ *
+ * To mitigate Post-Barrier RSB speculation, one CALL instruction must be
+ * forced to retire before letting a RET instruction execute.
+ *
+ * On PBRSB-vulnerable CPUs, it is not safe for a RET to be executed
+ * before this point.
+ */
+#define __FILL_ONE_RETURN				\
+	__FILL_RETURN_SLOT				\
+	add	$(BITS_PER_LONG/8), %_ASM_SP;		\
+	lfence;
 
 #ifdef __ASSEMBLY__
 
@@ -74,6 +102,23 @@
 .endm
 
 /*
+ * (ab)use RETPOLINE_SAFE on RET to annotate away 'bare' RET instructions
+ * vs RETBleed validation.
+ */
+#define ANNOTATE_UNRET_SAFE ANNOTATE_RETPOLINE_SAFE
+
+/*
+ * Abuse ANNOTATE_RETPOLINE_SAFE on a NOP to indicate UNRET_END, should
+ * eventually turn into it's own annotation.
+ */
+.macro ANNOTATE_UNRET_END
+#ifdef CONFIG_DEBUG_ENTRY
+	ANNOTATE_RETPOLINE_SAFE
+	nop
+#endif
+.endm
+
+/*
  * JMP_NOSPEC and CALL_NOSPEC macros can be used instead of a simple
  * indirect jmp/call which may be susceptible to the Spectre variant 2
  * attack.
@@ -81,7 +126,7 @@
 .macro JMP_NOSPEC reg:req
 #ifdef CONFIG_RETPOLINE
 	ALTERNATIVE_2 __stringify(ANNOTATE_RETPOLINE_SAFE; jmp *%\reg), \
-		      __stringify(jmp __x86_retpoline_\reg), X86_FEATURE_RETPOLINE, \
+		      __stringify(jmp __x86_indirect_thunk_\reg), X86_FEATURE_RETPOLINE, \
 		      __stringify(lfence; ANNOTATE_RETPOLINE_SAFE; jmp *%\reg), X86_FEATURE_RETPOLINE_LFENCE
 #else
 	jmp	*%\reg
@@ -91,7 +136,7 @@
 .macro CALL_NOSPEC reg:req
 #ifdef CONFIG_RETPOLINE
 	ALTERNATIVE_2 __stringify(ANNOTATE_RETPOLINE_SAFE; call *%\reg), \
-		      __stringify(call __x86_retpoline_\reg), X86_FEATURE_RETPOLINE, \
+		      __stringify(call __x86_indirect_thunk_\reg), X86_FEATURE_RETPOLINE, \
 		      __stringify(lfence; ANNOTATE_RETPOLINE_SAFE; call *%\reg), X86_FEATURE_RETPOLINE_LFENCE
 #else
 	call	*%\reg
@@ -102,11 +147,37 @@
   * A simpler FILL_RETURN_BUFFER macro. Don't make people use the CPP
   * monstrosity above, manually.
   */
-.macro FILL_RETURN_BUFFER reg:req nr:req ftr:req
-#ifdef CONFIG_RETPOLINE
-	ALTERNATIVE "jmp .Lskip_rsb_\@", "", \ftr
-	__FILL_RETURN_BUFFER(\reg,\nr,%_ASM_SP)
+.macro FILL_RETURN_BUFFER reg:req nr:req ftr:req ftr2=ALT_NOT(X86_FEATURE_ALWAYS)
+	ALTERNATIVE_2 "jmp .Lskip_rsb_\@", \
+		__stringify(__FILL_RETURN_BUFFER(\reg,\nr)), \ftr, \
+		__stringify(__FILL_ONE_RETURN), \ftr2
+
 .Lskip_rsb_\@:
+.endm
+
+#ifdef CONFIG_CPU_UNRET_ENTRY
+#define CALL_ZEN_UNTRAIN_RET	"call zen_untrain_ret"
+#else
+#define CALL_ZEN_UNTRAIN_RET	""
+#endif
+
+/*
+ * Mitigate RETBleed for AMD/Hygon Zen uarch. Requires KERNEL CR3 because the
+ * return thunk isn't mapped into the userspace tables (then again, AMD
+ * typically has NO_MELTDOWN).
+ *
+ * While zen_untrain_ret() doesn't clobber anything but requires stack,
+ * entry_ibpb() will clobber AX, CX, DX.
+ *
+ * As such, this must be placed after every *SWITCH_TO_KERNEL_CR3 at a point
+ * where we have a stack but before any RET instruction.
+ */
+.macro UNTRAIN_RET
+#if defined(CONFIG_CPU_UNRET_ENTRY) || defined(CONFIG_CPU_IBPB_ENTRY)
+	ANNOTATE_UNRET_END
+	ALTERNATIVE_2 "",						\
+	              CALL_ZEN_UNTRAIN_RET, X86_FEATURE_UNRET,		\
+		      "call entry_ibpb", X86_FEATURE_ENTRY_IBPB
 #endif
 .endm
 
@@ -118,7 +189,21 @@
 	_ASM_PTR " 999b\n\t"					\
 	".popsection\n\t"
 
+extern void __x86_return_thunk(void);
+extern void zen_untrain_ret(void);
+extern void entry_ibpb(void);
+
 #ifdef CONFIG_RETPOLINE
+
+typedef u8 retpoline_thunk_t[RETPOLINE_THUNK_SIZE];
+
+#define GEN(reg) \
+	extern retpoline_thunk_t __x86_indirect_thunk_ ## reg;
+#include <asm/GEN-for-each-reg.h>
+#undef GEN
+
+extern retpoline_thunk_t __x86_indirect_thunk_array[];
+
 #ifdef CONFIG_X86_64
 
 /*
@@ -129,7 +214,7 @@
 	ALTERNATIVE_2(						\
 	ANNOTATE_RETPOLINE_SAFE					\
 	"call *%[thunk_target]\n",				\
-	"call __x86_retpoline_%V[thunk_target]\n",		\
+	"call __x86_indirect_thunk_%V[thunk_target]\n",		\
 	X86_FEATURE_RETPOLINE,					\
 	"lfence;\n"						\
 	ANNOTATE_RETPOLINE_SAFE					\
@@ -181,6 +266,7 @@
 	SPECTRE_V2_EIBRS,
 	SPECTRE_V2_EIBRS_RETPOLINE,
 	SPECTRE_V2_EIBRS_LFENCE,
+	SPECTRE_V2_IBRS,
 };
 
 /* The indirect branch speculation control variants */
@@ -223,6 +309,9 @@
 
 /* The Intel SPEC CTRL MSR base value cache */
 extern u64 x86_spec_ctrl_base;
+DECLARE_PER_CPU(u64, x86_spec_ctrl_current);
+extern void write_spec_ctrl_current(u64 val, bool force);
+extern u64 spec_ctrl_current(void);
 
 /*
  * With retpoline, we must use IBRS to restrict branch prediction
@@ -232,18 +321,18 @@
  */
 #define firmware_restrict_branch_speculation_start()			\
 do {									\
-	u64 val = x86_spec_ctrl_base | SPEC_CTRL_IBRS;			\
-									\
 	preempt_disable();						\
-	alternative_msr_write(MSR_IA32_SPEC_CTRL, val,			\
+	alternative_msr_write(MSR_IA32_SPEC_CTRL,			\
+			      spec_ctrl_current() | SPEC_CTRL_IBRS,	\
 			      X86_FEATURE_USE_IBRS_FW);			\
+	alternative_msr_write(MSR_IA32_PRED_CMD, PRED_CMD_IBPB,		\
+			      X86_FEATURE_USE_IBPB_FW);			\
 } while (0)
 
 #define firmware_restrict_branch_speculation_end()			\
 do {									\
-	u64 val = x86_spec_ctrl_base;					\
-									\
-	alternative_msr_write(MSR_IA32_SPEC_CTRL, val,			\
+	alternative_msr_write(MSR_IA32_SPEC_CTRL,			\
+			      spec_ctrl_current(),			\
 			      X86_FEATURE_USE_IBRS_FW);			\
 	preempt_enable();						\
 } while (0)
@@ -255,6 +344,8 @@
 DECLARE_STATIC_KEY_FALSE(mds_user_clear);
 DECLARE_STATIC_KEY_FALSE(mds_idle_clear);
 
+DECLARE_STATIC_KEY_FALSE(mmio_stale_data_clear);
+
 #include <asm/segment.h>
 
 /**
@@ -304,63 +395,4 @@
 
 #endif /* __ASSEMBLY__ */
 
-/*
- * Below is used in the eBPF JIT compiler and emits the byte sequence
- * for the following assembly:
- *
- * With retpolines configured:
- *
- *    callq do_rop
- *  spec_trap:
- *    pause
- *    lfence
- *    jmp spec_trap
- *  do_rop:
- *    mov %rcx,(%rsp) for x86_64
- *    mov %edx,(%esp) for x86_32
- *    retq
- *
- * Without retpolines configured:
- *
- *    jmp *%rcx for x86_64
- *    jmp *%edx for x86_32
- */
-#ifdef CONFIG_RETPOLINE
-# ifdef CONFIG_X86_64
-#  define RETPOLINE_RCX_BPF_JIT_SIZE	17
-#  define RETPOLINE_RCX_BPF_JIT()				\
-do {								\
-	EMIT1_off32(0xE8, 7);	 /* callq do_rop */		\
-	/* spec_trap: */					\
-	EMIT2(0xF3, 0x90);       /* pause */			\
-	EMIT3(0x0F, 0xAE, 0xE8); /* lfence */			\
-	EMIT2(0xEB, 0xF9);       /* jmp spec_trap */		\
-	/* do_rop: */						\
-	EMIT4(0x48, 0x89, 0x0C, 0x24); /* mov %rcx,(%rsp) */	\
-	EMIT1(0xC3);             /* retq */			\
-} while (0)
-# else /* !CONFIG_X86_64 */
-#  define RETPOLINE_EDX_BPF_JIT()				\
-do {								\
-	EMIT1_off32(0xE8, 7);	 /* call do_rop */		\
-	/* spec_trap: */					\
-	EMIT2(0xF3, 0x90);       /* pause */			\
-	EMIT3(0x0F, 0xAE, 0xE8); /* lfence */			\
-	EMIT2(0xEB, 0xF9);       /* jmp spec_trap */		\
-	/* do_rop: */						\
-	EMIT3(0x89, 0x14, 0x24); /* mov %edx,(%esp) */		\
-	EMIT1(0xC3);             /* ret */			\
-} while (0)
-# endif
-#else /* !CONFIG_RETPOLINE */
-# ifdef CONFIG_X86_64
-#  define RETPOLINE_RCX_BPF_JIT_SIZE	2
-#  define RETPOLINE_RCX_BPF_JIT()				\
-	EMIT2(0xFF, 0xE1);       /* jmp *%rcx */
-# else /* !CONFIG_X86_64 */
-#  define RETPOLINE_EDX_BPF_JIT()				\
-	EMIT2(0xFF, 0xE2)        /* jmp *%edx */
-# endif
-#endif
-
 #endif /* _ASM_X86_NOSPEC_BRANCH_H_ */