Merging upstream version 6.9.7.

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

11 files changed, 136 insertions, 45 deletions

diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h
index 67b68d0d17..0cb2396de0 100644
--- a/arch/x86/include/asm/alternative.h
+++ b/arch/x86/include/asm/alternative.h
@@ -294,10 +294,10 @@ static inline int alternatives_text_reserved(void *start, void *end)
  * Otherwise, if CPU has feature1, newinstr1 is used.
  * Otherwise, oldinstr is used.
  */
-#define alternative_input_2(oldinstr, newinstr1, ft_flags1, newinstr2,	     \
-			   ft_flags2, input...)				     \
-	asm_inline volatile(ALTERNATIVE_2(oldinstr, newinstr1, ft_flags1,     \
-		newinstr2, ft_flags2)					     \
+#define alternative_input_2(oldinstr, newinstr1, ft_flags1, newinstr2,	\
+			   ft_flags2, input...)				\
+	asm_inline volatile(ALTERNATIVE_2(oldinstr, newinstr1, ft_flags1, \
+		newinstr2, ft_flags2)					\
 		: : "i" (0), ## input)
 
 /* Like alternative_input, but with a single output argument */
@@ -307,7 +307,7 @@ static inline int alternatives_text_reserved(void *start, void *end)
 
 /* Like alternative_io, but for replacing a direct call with another one. */
 #define alternative_call(oldfunc, newfunc, ft_flags, output, input...)	\
-	asm_inline volatile (ALTERNATIVE("call %P[old]", "call %P[new]", ft_flags) \
+	asm_inline volatile (ALTERNATIVE("call %c[old]", "call %c[new]", ft_flags) \
 		: output : [old] "i" (oldfunc), [new] "i" (newfunc), ## input)
 
 /*
@@ -316,12 +316,12 @@ static inline int alternatives_text_reserved(void *start, void *end)
  * Otherwise, if CPU has feature1, function1 is used.
  * Otherwise, old function is used.
  */
-#define alternative_call_2(oldfunc, newfunc1, ft_flags1, newfunc2, ft_flags2,   \
-			   output, input...)				      \
-	asm_inline volatile (ALTERNATIVE_2("call %P[old]", "call %P[new1]", ft_flags1,\
-		"call %P[new2]", ft_flags2)				      \
-		: output, ASM_CALL_CONSTRAINT				      \
-		: [old] "i" (oldfunc), [new1] "i" (newfunc1),		      \
+#define alternative_call_2(oldfunc, newfunc1, ft_flags1, newfunc2, ft_flags2, \
+			   output, input...)				\
+	asm_inline volatile (ALTERNATIVE_2("call %c[old]", "call %c[new1]", ft_flags1, \
+		"call %c[new2]", ft_flags2)				\
+		: output, ASM_CALL_CONSTRAINT				\
+		: [old] "i" (oldfunc), [new1] "i" (newfunc1),		\
 		  [new2] "i" (newfunc2), ## input)
 
 /*
diff --git a/arch/x86/include/asm/atomic64_32.h b/arch/x86/include/asm/atomic64_32.h
index 3486d91b85..d510405e4e 100644
--- a/arch/x86/include/asm/atomic64_32.h
+++ b/arch/x86/include/asm/atomic64_32.h
@@ -24,7 +24,7 @@ typedef struct {
 
 #ifdef CONFIG_X86_CMPXCHG64
 #define __alternative_atomic64(f, g, out, in...) \
-	asm volatile("call %P[func]" \
+	asm volatile("call %c[func]" \
 		     : out : [func] "i" (atomic64_##g##_cx8), ## in)
 
 #define ATOMIC64_DECL(sym) ATOMIC64_DECL_ONE(sym##_cx8)
diff --git a/arch/x86/include/asm/cmpxchg_64.h b/arch/x86/include/asm/cmpxchg_64.h
index 44b08b53ab..c1d6cd58f8 100644
--- a/arch/x86/include/asm/cmpxchg_64.h
+++ b/arch/x86/include/asm/cmpxchg_64.h
@@ -62,7 +62,7 @@ static __always_inline u128 arch_cmpxchg128_local(volatile u128 *ptr, u128 old,
 	asm volatile(_lock "cmpxchg16b %[ptr]"				\
 		     CC_SET(e)						\
 		     : CC_OUT(e) (ret),					\
-		       [ptr] "+m" (*ptr),				\
+		       [ptr] "+m" (*(_ptr)),				\
 		       "+a" (o.low), "+d" (o.high)			\
 		     : "b" (n.low), "c" (n.high)			\
 		     : "memory");					\
diff --git a/arch/x86/include/asm/cpu_device_id.h b/arch/x86/include/asm/cpu_device_id.h
index eb8fcede9e..e8e3dbe7f1 100644
--- a/arch/x86/include/asm/cpu_device_id.h
+++ b/arch/x86/include/asm/cpu_device_id.h
@@ -3,6 +3,39 @@
 #define _ASM_X86_CPU_DEVICE_ID
 
 /*
+ * Can't use <linux/bitfield.h> because it generates expressions that
+ * cannot be used in structure initializers. Bitfield construction
+ * here must match the union in struct cpuinfo_86:
+ *	union {
+ *		struct {
+ *			__u8	x86_model;
+ *			__u8	x86;
+ *			__u8	x86_vendor;
+ *			__u8	x86_reserved;
+ *		};
+ *		__u32		x86_vfm;
+ *	};
+ */
+#define VFM_MODEL_BIT	0
+#define VFM_FAMILY_BIT	8
+#define VFM_VENDOR_BIT	16
+#define VFM_RSVD_BIT	24
+
+#define	VFM_MODEL_MASK	GENMASK(VFM_FAMILY_BIT - 1, VFM_MODEL_BIT)
+#define	VFM_FAMILY_MASK	GENMASK(VFM_VENDOR_BIT - 1, VFM_FAMILY_BIT)
+#define	VFM_VENDOR_MASK	GENMASK(VFM_RSVD_BIT - 1, VFM_VENDOR_BIT)
+
+#define VFM_MODEL(vfm)	(((vfm) & VFM_MODEL_MASK) >> VFM_MODEL_BIT)
+#define VFM_FAMILY(vfm)	(((vfm) & VFM_FAMILY_MASK) >> VFM_FAMILY_BIT)
+#define VFM_VENDOR(vfm)	(((vfm) & VFM_VENDOR_MASK) >> VFM_VENDOR_BIT)
+
+#define	VFM_MAKE(_vendor, _family, _model) (	\
+	((_model) << VFM_MODEL_BIT) |		\
+	((_family) << VFM_FAMILY_BIT) |		\
+	((_vendor) << VFM_VENDOR_BIT)		\
+)
+
+/*
  * Declare drivers belonging to specific x86 CPUs
  * Similar in spirit to pci_device_id and related PCI functions
  *
@@ -20,6 +53,9 @@
 #define X86_CENTAUR_FAM6_C7_D		0xd
 #define X86_CENTAUR_FAM6_NANO		0xf
 
+/* x86_cpu_id::flags */
+#define X86_CPU_ID_FLAG_ENTRY_VALID	BIT(0)
+
 #define X86_STEPPINGS(mins, maxs)    GENMASK(maxs, mins)
 /**
  * X86_MATCH_VENDOR_FAM_MODEL_STEPPINGS_FEATURE - Base macro for CPU matching
@@ -46,6 +82,18 @@
 	.model		= _model,					\
 	.steppings	= _steppings,					\
 	.feature	= _feature,					\
+	.flags		= X86_CPU_ID_FLAG_ENTRY_VALID,			\
+	.driver_data	= (unsigned long) _data				\
+}
+
+#define X86_MATCH_VENDORID_FAM_MODEL_STEPPINGS_FEATURE(_vendor, _family, _model, \
+						    _steppings, _feature, _data) { \
+	.vendor		= _vendor,					\
+	.family		= _family,					\
+	.model		= _model,					\
+	.steppings	= _steppings,					\
+	.feature	= _feature,					\
+	.flags		= X86_CPU_ID_FLAG_ENTRY_VALID,			\
 	.driver_data	= (unsigned long) _data				\
 }
 
@@ -164,6 +212,56 @@
 	X86_MATCH_VENDOR_FAM_MODEL_STEPPINGS_FEATURE(INTEL, 6, INTEL_FAM6_##model, \
 						     steppings, X86_FEATURE_ANY, data)
 
+/**
+ * X86_MATCH_VFM - Match encoded vendor/family/model
+ * @vfm:	Encoded 8-bits each for vendor, family, model
+ * @data:	Driver specific data or NULL. The internal storage
+ *		format is unsigned long. The supplied value, pointer
+ *		etc. is cast to unsigned long internally.
+ *
+ * Stepping and feature are set to wildcards
+ */
+#define X86_MATCH_VFM(vfm, data)			\
+	X86_MATCH_VENDORID_FAM_MODEL_STEPPINGS_FEATURE(	\
+		VFM_VENDOR(vfm),			\
+		VFM_FAMILY(vfm),			\
+		VFM_MODEL(vfm),				\
+		X86_STEPPING_ANY, X86_FEATURE_ANY, data)
+
+/**
+ * X86_MATCH_VFM_STEPPINGS - Match encoded vendor/family/model/stepping
+ * @vfm:	Encoded 8-bits each for vendor, family, model
+ * @steppings:	Bitmask of steppings to match
+ * @data:	Driver specific data or NULL. The internal storage
+ *		format is unsigned long. The supplied value, pointer
+ *		etc. is cast to unsigned long internally.
+ *
+ * feature is set to wildcard
+ */
+#define X86_MATCH_VFM_STEPPINGS(vfm, steppings, data)	\
+	X86_MATCH_VENDORID_FAM_MODEL_STEPPINGS_FEATURE(	\
+		VFM_VENDOR(vfm),			\
+		VFM_FAMILY(vfm),			\
+		VFM_MODEL(vfm),				\
+		steppings, X86_FEATURE_ANY, data)
+
+/**
+ * X86_MATCH_VFM_FEATURE - Match encoded vendor/family/model/feature
+ * @vfm:	Encoded 8-bits each for vendor, family, model
+ * @feature:	A X86_FEATURE bit
+ * @data:	Driver specific data or NULL. The internal storage
+ *		format is unsigned long. The supplied value, pointer
+ *		etc. is cast to unsigned long internally.
+ *
+ * Steppings is set to wildcard
+ */
+#define X86_MATCH_VFM_FEATURE(vfm, feature, data)	\
+	X86_MATCH_VENDORID_FAM_MODEL_STEPPINGS_FEATURE(	\
+		VFM_VENDOR(vfm),			\
+		VFM_FAMILY(vfm),			\
+		VFM_MODEL(vfm),				\
+		X86_STEPPING_ANY, feature, data)
+
 /*
  * Match specific microcode revisions.
  *
diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h
index 686e92d266..3508f3fc92 100644
--- a/arch/x86/include/asm/cpufeature.h
+++ b/arch/x86/include/asm/cpufeature.h
@@ -173,7 +173,7 @@ extern void clear_cpu_cap(struct cpuinfo_x86 *c, unsigned int bit);
 static __always_inline bool _static_cpu_has(u16 bit)
 {
 	asm goto(
-		ALTERNATIVE_TERNARY("jmp 6f", %P[feature], "", "jmp %l[t_no]")
+		ALTERNATIVE_TERNARY("jmp 6f", %c[feature], "", "jmp %l[t_no]")
 		".pushsection .altinstr_aux,\"ax\"\n"
 		"6:\n"
 		" testb %[bitnum]," _ASM_RIP(%P[cap_byte]) "\n"
diff --git a/arch/x86/include/asm/efi.h b/arch/x86/include/asm/efi.h
index 1dc600fa3b..4810961775 100644
--- a/arch/x86/include/asm/efi.h
+++ b/arch/x86/include/asm/efi.h
@@ -401,7 +401,6 @@ extern int __init efi_memmap_alloc(unsigned int num_entries,
 				   struct efi_memory_map_data *data);
 extern void __efi_memmap_free(u64 phys, unsigned long size,
 			      unsigned long flags);
-#define __efi_memmap_free __efi_memmap_free
 
 extern int __init efi_memmap_install(struct efi_memory_map_data *data);
 extern int __init efi_memmap_split_count(efi_memory_desc_t *md,
diff --git a/arch/x86/include/asm/irq_stack.h b/arch/x86/include/asm/irq_stack.h
index 798183867d..b71ad173f8 100644
--- a/arch/x86/include/asm/irq_stack.h
+++ b/arch/x86/include/asm/irq_stack.h
@@ -100,7 +100,7 @@
 }
 
 #define ASM_CALL_ARG0							\
-	"call %P[__func]				\n"		\
+	"call %c[__func]				\n"		\
 	ASM_REACHABLE
 
 #define ASM_CALL_ARG1							\
diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h
index b77bbb67e7..ce5111cec3 100644
--- a/arch/x86/include/asm/percpu.h
+++ b/arch/x86/include/asm/percpu.h
@@ -59,36 +59,30 @@
 #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__ += (__force unsigned long)(ptr);		\
-	(typeof(*(ptr)) __kernel __force *)tcp_ptr__;		\
-})
-#else /* CONFIG_USE_X86_SEG_SUPPORT */
+#ifdef CONFIG_X86_64
+#define __raw_my_cpu_offset	raw_cpu_read_8(this_cpu_off);
+#else
+#define __raw_my_cpu_offset	raw_cpu_read_4(this_cpu_off);
+#endif
+
 /*
  * Compared to the generic __my_cpu_offset version, the following
  * saves one instruction and avoids clobbering a temp register.
+ *
+ * arch_raw_cpu_ptr should not be used in 32-bit VDSO for a 64-bit
+ * kernel, because games are played with CONFIG_X86_64 there and
+ * sizeof(this_cpu_off) becames 4.
  */
-#define arch_raw_cpu_ptr(ptr)					\
+#ifndef BUILD_VDSO32_64
+#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__;		\
+	unsigned long tcp_ptr__ = __raw_my_cpu_offset;		\
+	tcp_ptr__ += (__force unsigned long)(_ptr);		\
+	(typeof(*(_ptr)) __kernel __force *)tcp_ptr__;		\
 })
-#endif /* CONFIG_USE_X86_SEG_SUPPORT */
+#else
+#define arch_raw_cpu_ptr(_ptr) ({ BUILD_BUG(); (typeof(_ptr))0; })
+#endif
 
 #define PER_CPU_VAR(var)	%__percpu_seg:(var)__percpu_rel
 
diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h
index 9abb8cc4cd..b786449626 100644
--- a/arch/x86/include/asm/pgtable_types.h
+++ b/arch/x86/include/asm/pgtable_types.h
@@ -567,6 +567,8 @@ static inline void update_page_count(int level, unsigned long pages) { }
 extern pte_t *lookup_address(unsigned long address, unsigned int *level);
 extern pte_t *lookup_address_in_pgd(pgd_t *pgd, unsigned long address,
 				    unsigned int *level);
+pte_t *lookup_address_in_pgd_attr(pgd_t *pgd, unsigned long address,
+				  unsigned int *level, bool *nx, bool *rw);
 extern pmd_t *lookup_pmd_address(unsigned long address);
 extern phys_addr_t slow_virt_to_phys(void *__address);
 extern int __init kernel_map_pages_in_pgd(pgd_t *pgd, u64 pfn,
diff --git a/arch/x86/include/asm/sparsemem.h b/arch/x86/include/asm/sparsemem.h
index 1be13b2dfe..64df897c0e 100644
--- a/arch/x86/include/asm/sparsemem.h
+++ b/arch/x86/include/asm/sparsemem.h
@@ -37,8 +37,6 @@ extern int phys_to_target_node(phys_addr_t start);
 #define phys_to_target_node phys_to_target_node
 extern int memory_add_physaddr_to_nid(u64 start);
 #define memory_add_physaddr_to_nid memory_add_physaddr_to_nid
-extern int numa_fill_memblks(u64 start, u64 end);
-#define numa_fill_memblks numa_fill_memblks
 #endif
 #endif /* __ASSEMBLY__ */
 
diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h
index 237dc8cdd1..3a7755c1a4 100644
--- a/arch/x86/include/asm/uaccess.h
+++ b/arch/x86/include/asm/uaccess.h
@@ -78,10 +78,10 @@ extern int __get_user_bad(void);
 	int __ret_gu;							\
 	register __inttype(*(ptr)) __val_gu asm("%"_ASM_DX);		\
 	__chk_user_ptr(ptr);						\
-	asm volatile("call __" #fn "_%P4"				\
+	asm volatile("call __" #fn "_%c[size]"				\
 		     : "=a" (__ret_gu), "=r" (__val_gu),		\
 			ASM_CALL_CONSTRAINT				\
-		     : "0" (ptr), "i" (sizeof(*(ptr))));		\
+		     : "0" (ptr), [size] "i" (sizeof(*(ptr))));		\
 	instrument_get_user(__val_gu);					\
 	(x) = (__force __typeof__(*(ptr))) __val_gu;			\
 	__builtin_expect(__ret_gu, 0);					\
@@ -177,7 +177,7 @@ extern void __put_user_nocheck_8(void);
 	__chk_user_ptr(__ptr);						\
 	__ptr_pu = __ptr;						\
 	__val_pu = __x;							\
-	asm volatile("call __" #fn "_%P[size]"				\
+	asm volatile("call __" #fn "_%c[size]"				\
 		     : "=c" (__ret_pu),					\
 			ASM_CALL_CONSTRAINT				\
 		     : "0" (__ptr_pu),					\