Re: Linux 4.4.245

[Greg Kroah-Hartman <gregkh@linuxfoundation.org>]

diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index 17747dcd0e77..a8ceef14e781 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -2196,6 +2196,8 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 					       spec_store_bypass_disable=off [X86]
 					       mds=off [X86]
 					       tsx_async_abort=off [X86]
+					       no_entry_flush [PPC]
+					       no_uaccess_flush [PPC]
 
 			auto (default)
 				Mitigate all CPU vulnerabilities, but leave SMT
@@ -2476,6 +2478,8 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 
 	noefi		Disable EFI runtime services support.
 
+	no_entry_flush	[PPC] Don't flush the L1-D cache when entering the kernel.
+
 	noexec		[IA-64]
 
 	noexec		[X86]
@@ -2518,6 +2522,9 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 	nospec_store_bypass_disable
 			[HW] Disable all mitigations for the Speculative Store Bypass vulnerability
 
+	no_uaccess_flush
+			[PPC] Don't flush the L1-D cache after accessing user data.
+
 	noxsave		[BUGS=X86] Disables x86 extended register state save
 			and restore using xsave. The kernel will fallback to
 			enabling legacy floating-point and sse state.
diff --git a/Makefile b/Makefile
index f8b9fd688781..2d9e5c4688a4 100644
--- a/Makefile
+++ b/Makefile
@@ -1,6 +1,6 @@
 VERSION = 4
 PATCHLEVEL = 4
-SUBLEVEL = 244
+SUBLEVEL = 245
 EXTRAVERSION =
 NAME = Blurry Fish Butt
 
diff --git a/arch/powerpc/include/asm/book3s/64/kup-radix.h b/arch/powerpc/include/asm/book3s/64/kup-radix.h
new file mode 100644
index 000000000000..cce8e7497d72
--- /dev/null
+++ b/arch/powerpc/include/asm/book3s/64/kup-radix.h
@@ -0,0 +1,23 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_POWERPC_BOOK3S_64_KUP_RADIX_H
+#define _ASM_POWERPC_BOOK3S_64_KUP_RADIX_H
+#include <linux/jump_label.h>
+
+DECLARE_STATIC_KEY_FALSE(uaccess_flush_key);
+
+/* Prototype for function defined in exceptions-64s.S */
+void do_uaccess_flush(void);
+
+static __always_inline void allow_user_access(void __user *to, const void __user *from,
+					      unsigned long size)
+{
+}
+
+static inline void prevent_user_access(void __user *to, const void __user *from,
+				       unsigned long size)
+{
+	if (static_branch_unlikely(&uaccess_flush_key))
+		do_uaccess_flush();
+}
+
+#endif /* _ASM_POWERPC_BOOK3S_64_KUP_RADIX_H */
diff --git a/arch/powerpc/include/asm/exception-64s.h b/arch/powerpc/include/asm/exception-64s.h
index 3ed536bec462..fbcfc722d109 100644
--- a/arch/powerpc/include/asm/exception-64s.h
+++ b/arch/powerpc/include/asm/exception-64s.h
@@ -65,11 +65,18 @@
 	nop;								\
 	nop
 
+#define ENTRY_FLUSH_SLOT						\
+	ENTRY_FLUSH_FIXUP_SECTION;					\
+	nop;								\
+	nop;								\
+	nop;
+
 /*
  * r10 must be free to use, r13 must be paca
  */
 #define INTERRUPT_TO_KERNEL						\
-	STF_ENTRY_BARRIER_SLOT
+	STF_ENTRY_BARRIER_SLOT;						\
+	ENTRY_FLUSH_SLOT
 
 /*
  * Macros for annotating the expected destination of (h)rfid
@@ -597,6 +604,12 @@ label##_relon_hv:							\
 	EXCEPTION_PROLOG_1(PACA_EXGEN, SOFTEN_NOTEST_HV, vec);		\
 	EXCEPTION_PROLOG_PSERIES_1(label##_common, EXC_HV);
 
+#define MASKABLE_RELON_EXCEPTION_PSERIES_OOL(vec, label)               \
+       .globl label##_relon_pSeries;                                   \
+label##_relon_pSeries:                                                 \
+       EXCEPTION_PROLOG_1(PACA_EXGEN, SOFTEN_NOTEST_PR, vec);          \
+       EXCEPTION_PROLOG_PSERIES_1(label##_common, EXC_STD)
+
 /*
  * Our exception common code can be passed various "additions"
  * to specify the behaviour of interrupts, whether to kick the
diff --git a/arch/powerpc/include/asm/feature-fixups.h b/arch/powerpc/include/asm/feature-fixups.h
index 145a37ab2d3e..83219710e904 100644
--- a/arch/powerpc/include/asm/feature-fixups.h
+++ b/arch/powerpc/include/asm/feature-fixups.h
@@ -200,6 +200,22 @@ label##3:					       	\
 	FTR_ENTRY_OFFSET 955b-956b;			\
 	.popsection;
 
+#define UACCESS_FLUSH_FIXUP_SECTION			\
+959:							\
+	.pushsection __uaccess_flush_fixup,"a";		\
+	.align 2;					\
+960:							\
+	FTR_ENTRY_OFFSET 959b-960b;			\
+	.popsection;
+
+#define ENTRY_FLUSH_FIXUP_SECTION			\
+957:							\
+	.pushsection __entry_flush_fixup,"a";		\
+	.align 2;					\
+958:							\
+	FTR_ENTRY_OFFSET 957b-958b;			\
+	.popsection;
+
 #define RFI_FLUSH_FIXUP_SECTION				\
 951:							\
 	.pushsection __rfi_flush_fixup,"a";		\
@@ -231,8 +247,11 @@ label##3:					       	\
 #ifndef __ASSEMBLY__
 
 extern long stf_barrier_fallback;
+extern long entry_flush_fallback;
 extern long __start___stf_entry_barrier_fixup, __stop___stf_entry_barrier_fixup;
 extern long __start___stf_exit_barrier_fixup, __stop___stf_exit_barrier_fixup;
+extern long __start___uaccess_flush_fixup, __stop___uaccess_flush_fixup;
+extern long __start___entry_flush_fixup, __stop___entry_flush_fixup;
 extern long __start___rfi_flush_fixup, __stop___rfi_flush_fixup;
 extern long __start___barrier_nospec_fixup, __stop___barrier_nospec_fixup;
 extern long __start__btb_flush_fixup, __stop__btb_flush_fixup;
diff --git a/arch/powerpc/include/asm/futex.h b/arch/powerpc/include/asm/futex.h
index b73ab8a7ebc3..10746519b351 100644
--- a/arch/powerpc/include/asm/futex.h
+++ b/arch/powerpc/include/asm/futex.h
@@ -36,6 +36,7 @@ static inline int arch_futex_atomic_op_inuser(int op, int oparg, int *oval,
 {
 	int oldval = 0, ret;
 
+	allow_write_to_user(uaddr, sizeof(*uaddr));
 	pagefault_disable();
 
 	switch (op) {
@@ -62,6 +63,7 @@ static inline int arch_futex_atomic_op_inuser(int op, int oparg, int *oval,
 
 	*oval = oldval;
 
+	prevent_write_to_user(uaddr, sizeof(*uaddr));
 	return ret;
 }
 
@@ -75,6 +77,7 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 	if (!access_ok(VERIFY_WRITE, uaddr, sizeof(u32)))
 		return -EFAULT;
 
+	allow_write_to_user(uaddr, sizeof(*uaddr));
         __asm__ __volatile__ (
         PPC_ATOMIC_ENTRY_BARRIER
 "1:     lwarx   %1,0,%3         # futex_atomic_cmpxchg_inatomic\n\
@@ -97,6 +100,7 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
         : "cc", "memory");
 
 	*uval = prev;
+	prevent_write_to_user(uaddr, sizeof(*uaddr));
         return ret;
 }
 
diff --git a/arch/powerpc/include/asm/kup.h b/arch/powerpc/include/asm/kup.h
new file mode 100644
index 000000000000..f0f8e36ad71f
--- /dev/null
+++ b/arch/powerpc/include/asm/kup.h
@@ -0,0 +1,40 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_POWERPC_KUP_H_
+#define _ASM_POWERPC_KUP_H_
+
+#ifndef __ASSEMBLY__
+
+#include <asm/pgtable.h>
+
+#ifdef CONFIG_PPC_BOOK3S_64
+#include <asm/book3s/64/kup-radix.h>
+#else
+static inline void allow_user_access(void __user *to, const void __user *from,
+				     unsigned long size) { }
+static inline void prevent_user_access(void __user *to, const void __user *from,
+				       unsigned long size) { }
+#endif /* CONFIG_PPC_BOOK3S_64 */
+
+static inline void allow_read_from_user(const void __user *from, unsigned long size)
+{
+	allow_user_access(NULL, from, size);
+}
+
+static inline void allow_write_to_user(void __user *to, unsigned long size)
+{
+	allow_user_access(to, NULL, size);
+}
+
+static inline void prevent_read_from_user(const void __user *from, unsigned long size)
+{
+	prevent_user_access(NULL, from, size);
+}
+
+static inline void prevent_write_to_user(void __user *to, unsigned long size)
+{
+	prevent_user_access(to, NULL, size);
+}
+
+#endif /* !__ASSEMBLY__ */
+
+#endif /* _ASM_POWERPC_KUP_H_ */
diff --git a/arch/powerpc/include/asm/security_features.h b/arch/powerpc/include/asm/security_features.h
index ccf44c135389..3b45a64e491e 100644
--- a/arch/powerpc/include/asm/security_features.h
+++ b/arch/powerpc/include/asm/security_features.h
@@ -84,12 +84,19 @@ static inline bool security_ftr_enabled(unsigned long feature)
 // Software required to flush link stack on context switch
 #define SEC_FTR_FLUSH_LINK_STACK	0x0000000000001000ull
 
+// The L1-D cache should be flushed when entering the kernel
+#define SEC_FTR_L1D_FLUSH_ENTRY		0x0000000000004000ull
+
+// The L1-D cache should be flushed after user accesses from the kernel
+#define SEC_FTR_L1D_FLUSH_UACCESS	0x0000000000008000ull
 
 // Features enabled by default
 #define SEC_FTR_DEFAULT \
 	(SEC_FTR_L1D_FLUSH_HV | \
 	 SEC_FTR_L1D_FLUSH_PR | \
 	 SEC_FTR_BNDS_CHK_SPEC_BAR | \
+	 SEC_FTR_L1D_FLUSH_ENTRY | \
+	 SEC_FTR_L1D_FLUSH_UACCESS | \
 	 SEC_FTR_FAVOUR_SECURITY)
 
 #endif /* _ASM_POWERPC_SECURITY_FEATURES_H */
diff --git a/arch/powerpc/include/asm/setup.h b/arch/powerpc/include/asm/setup.h
index d299479c770b..1ccf474f08ab 100644
--- a/arch/powerpc/include/asm/setup.h
+++ b/arch/powerpc/include/asm/setup.h
@@ -38,12 +38,16 @@ enum l1d_flush_type {
 };
 
 void setup_rfi_flush(enum l1d_flush_type, bool enable);
+void setup_entry_flush(bool enable);
+void setup_uaccess_flush(bool enable);
 void do_rfi_flush_fixups(enum l1d_flush_type types);
 #ifdef CONFIG_PPC_BARRIER_NOSPEC
 void setup_barrier_nospec(void);
 #else
 static inline void setup_barrier_nospec(void) { };
 #endif
+void do_uaccess_flush_fixups(enum l1d_flush_type types);
+void do_entry_flush_fixups(enum l1d_flush_type types);
 void do_barrier_nospec_fixups(bool enable);
 extern bool barrier_nospec_enabled;
 
diff --git a/arch/powerpc/include/asm/uaccess.h b/arch/powerpc/include/asm/uaccess.h
index e51ce5a0e221..eb4b060efd95 100644
--- a/arch/powerpc/include/asm/uaccess.h
+++ b/arch/powerpc/include/asm/uaccess.h
@@ -9,6 +9,7 @@
 #include <asm/asm-compat.h>
 #include <asm/processor.h>
 #include <asm/page.h>
+#include <asm/kup.h>
 
 #define VERIFY_READ	0
 #define VERIFY_WRITE	1
@@ -105,9 +106,14 @@ struct exception_table_entry {
 	__put_user_check((__typeof__(*(ptr)))(x), (ptr), sizeof(*(ptr)))
 
 #define __get_user(x, ptr) \
-	__get_user_nocheck((x), (ptr), sizeof(*(ptr)))
+	__get_user_nocheck((x), (ptr), sizeof(*(ptr)), true)
 #define __put_user(x, ptr) \
-	__put_user_nocheck((__typeof__(*(ptr)))(x), (ptr), sizeof(*(ptr)))
+	__put_user_nocheck((__typeof__(*(ptr)))(x), (ptr), sizeof(*(ptr)), true)
+
+#define __get_user_allowed(x, ptr) \
+	__get_user_nocheck((x), (ptr), sizeof(*(ptr)), false)
+#define __put_user_allowed(x, ptr) \
+	__put_user_nocheck((__typeof__(*(ptr)))(x), (ptr), sizeof(*(ptr)), false)
 
 #define __get_user_inatomic(x, ptr) \
 	__get_user_nosleep((x), (ptr), sizeof(*(ptr)))
@@ -161,7 +167,7 @@ extern long __put_user_bad(void);
 		: "r" (x), "b" (addr), "i" (-EFAULT), "0" (err))
 #endif /* __powerpc64__ */
 
-#define __put_user_size(x, ptr, size, retval)			\
+#define __put_user_size_allowed(x, ptr, size, retval)		\
 do {								\
 	retval = 0;						\
 	switch (size) {						\
@@ -173,14 +179,28 @@ do {								\
 	}							\
 } while (0)
 
-#define __put_user_nocheck(x, ptr, size)			\
+#define __put_user_size(x, ptr, size, retval)			\
+do {								\
+	allow_write_to_user(ptr, size);				\
+	__put_user_size_allowed(x, ptr, size, retval);		\
+	prevent_write_to_user(ptr, size);			\
+} while (0)
+
+#define __put_user_nocheck(x, ptr, size, do_allow)			\
 ({								\
 	long __pu_err;						\
 	__typeof__(*(ptr)) __user *__pu_addr = (ptr);		\
+	__typeof__(*(ptr)) __pu_val = (x);			\
+	__typeof__(size) __pu_size = (size);			\
+								\
 	if (!is_kernel_addr((unsigned long)__pu_addr))		\
 		might_fault();					\
-	__chk_user_ptr(ptr);					\
-	__put_user_size((x), __pu_addr, (size), __pu_err);	\
+	__chk_user_ptr(__pu_addr);				\
+	if (do_allow)								\
+		__put_user_size(__pu_val, __pu_addr, __pu_size, __pu_err);	\
+	else									\
+		__put_user_size_allowed(__pu_val, __pu_addr, __pu_size, __pu_err); \
+								\
 	__pu_err;						\
 })
 
@@ -188,9 +208,13 @@ do {								\
 ({									\
 	long __pu_err = -EFAULT;					\
 	__typeof__(*(ptr)) __user *__pu_addr = (ptr);			\
+	__typeof__(*(ptr)) __pu_val = (x);				\
+	__typeof__(size) __pu_size = (size);				\
+									\
 	might_fault();							\
-	if (access_ok(VERIFY_WRITE, __pu_addr, size))			\
-		__put_user_size((x), __pu_addr, (size), __pu_err);	\
+	if (access_ok(VERIFY_WRITE, __pu_addr, __pu_size))			\
+		__put_user_size(__pu_val, __pu_addr, __pu_size, __pu_err); \
+									\
 	__pu_err;							\
 })
 
@@ -198,8 +222,12 @@ do {								\
 ({								\
 	long __pu_err;						\
 	__typeof__(*(ptr)) __user *__pu_addr = (ptr);		\
-	__chk_user_ptr(ptr);					\
-	__put_user_size((x), __pu_addr, (size), __pu_err);	\
+	__typeof__(*(ptr)) __pu_val = (x);			\
+	__typeof__(size) __pu_size = (size);			\
+								\
+	__chk_user_ptr(__pu_addr);				\
+	__put_user_size(__pu_val, __pu_addr, __pu_size, __pu_err); \
+								\
 	__pu_err;						\
 })
 
@@ -246,7 +274,7 @@ extern long __get_user_bad(void);
 		: "b" (addr), "i" (-EFAULT), "0" (err))
 #endif /* __powerpc64__ */
 
-#define __get_user_size(x, ptr, size, retval)			\
+#define __get_user_size_allowed(x, ptr, size, retval)		\
 do {								\
 	retval = 0;						\
 	__chk_user_ptr(ptr);					\
@@ -261,17 +289,30 @@ do {								\
 	}							\
 } while (0)
 
-#define __get_user_nocheck(x, ptr, size)			\
+#define __get_user_size(x, ptr, size, retval)			\
+do {								\
+	allow_read_from_user(ptr, size);			\
+	__get_user_size_allowed(x, ptr, size, retval);		\
+	prevent_read_from_user(ptr, size);			\
+} while (0)
+
+#define __get_user_nocheck(x, ptr, size, do_allow)			\
 ({								\
 	long __gu_err;						\
 	unsigned long __gu_val;					\
 	__typeof__(*(ptr)) __user *__gu_addr = (ptr);	\
-	__chk_user_ptr(ptr);					\
+	__typeof__(size) __gu_size = (size);			\
+								\
+	__chk_user_ptr(__gu_addr);				\
 	if (!is_kernel_addr((unsigned long)__gu_addr))		\
 		might_fault();					\
 	barrier_nospec();					\
-	__get_user_size(__gu_val, __gu_addr, (size), __gu_err);	\
+	if (do_allow)								\
+		__get_user_size(__gu_val, __gu_addr, __gu_size, __gu_err);	\
+	else									\
+		__get_user_size_allowed(__gu_val, __gu_addr, __gu_size, __gu_err); \
 	(x) = (__typeof__(*(ptr)))__gu_val;			\
+								\
 	__gu_err;						\
 })
 
@@ -296,12 +337,15 @@ do {								\
 	long __gu_err = -EFAULT;					\
 	unsigned long  __gu_val = 0;					\
 	__typeof__(*(ptr)) __user *__gu_addr = (ptr);		\
+	__typeof__(size) __gu_size = (size);				\
+									\
 	might_fault();							\
-	if (access_ok(VERIFY_READ, __gu_addr, (size))) {		\
+	if (access_ok(VERIFY_READ, __gu_addr, __gu_size)) {		\
 		barrier_nospec();					\
-		__get_user_size(__gu_val, __gu_addr, (size), __gu_err);	\
+		__get_user_size(__gu_val, __gu_addr, __gu_size, __gu_err); \
 	}								\
 	(x) = (__force __typeof__(*(ptr)))__gu_val;				\
+									\
 	__gu_err;							\
 })
 
@@ -310,10 +354,13 @@ do {								\
 	long __gu_err;						\
 	unsigned long __gu_val;					\
 	__typeof__(*(ptr)) __user *__gu_addr = (ptr);	\
-	__chk_user_ptr(ptr);					\
+	__typeof__(size) __gu_size = (size);			\
+								\
+	__chk_user_ptr(__gu_addr);				\
 	barrier_nospec();					\
-	__get_user_size(__gu_val, __gu_addr, (size), __gu_err);	\
+	__get_user_size(__gu_val, __gu_addr, __gu_size, __gu_err); \
 	(x) = (__force __typeof__(*(ptr)))__gu_val;			\
+								\
 	__gu_err;						\
 })
 
@@ -328,9 +375,14 @@ extern unsigned long __copy_tofrom_user(void __user *to,
 static inline unsigned long copy_from_user(void *to,
 		const void __user *from, unsigned long n)
 {
+	unsigned long ret;
+
 	if (likely(access_ok(VERIFY_READ, from, n))) {
+		allow_user_access(to, from, n);
 		barrier_nospec();
-		return __copy_tofrom_user((__force void __user *)to, from, n);
+		ret = __copy_tofrom_user((__force void __user *)to, from, n);
+		prevent_user_access(to, from, n);
+		return ret;
 	}
 	memset(to, 0, n);
 	return n;
@@ -361,8 +413,9 @@ extern unsigned long copy_in_user(void __user *to, const void __user *from,
 static inline unsigned long __copy_from_user_inatomic(void *to,
 		const void __user *from, unsigned long n)
 {
+	unsigned long ret;
 	if (__builtin_constant_p(n) && (n <= 8)) {
-		unsigned long ret = 1;
+		ret = 1;
 
 		switch (n) {
 		case 1:
@@ -387,34 +440,42 @@ static inline unsigned long __copy_from_user_inatomic(void *to,
 	}
 
 	barrier_nospec();
-	return __copy_tofrom_user((__force void __user *)to, from, n);
+	allow_read_from_user(from, n);
+	ret = __copy_tofrom_user((__force void __user *)to, from, n);
+	prevent_read_from_user(from, n);
+	return ret;
 }
 
 static inline unsigned long __copy_to_user_inatomic(void __user *to,
 		const void *from, unsigned long n)
 {
+	unsigned long ret;
+
 	if (__builtin_constant_p(n) && (n <= 8)) {
-		unsigned long ret = 1;
+		ret = 1;
 
 		switch (n) {
 		case 1:
-			__put_user_size(*(u8 *)from, (u8 __user *)to, 1, ret);
+			__put_user_size_allowed(*(u8 *)from, (u8 __user *)to, 1, ret);
 			break;
 		case 2:
-			__put_user_size(*(u16 *)from, (u16 __user *)to, 2, ret);
+			__put_user_size_allowed(*(u16 *)from, (u16 __user *)to, 2, ret);
 			break;
 		case 4:
-			__put_user_size(*(u32 *)from, (u32 __user *)to, 4, ret);
+			__put_user_size_allowed(*(u32 *)from, (u32 __user *)to, 4, ret);
 			break;
 		case 8:
-			__put_user_size(*(u64 *)from, (u64 __user *)to, 8, ret);
+			__put_user_size_allowed(*(u64 *)from, (u64 __user *)to, 8, ret);
 			break;
 		}
 		if (ret == 0)
 			return 0;
 	}
 
-	return __copy_tofrom_user(to, (__force const void __user *)from, n);
+	allow_write_to_user(to, n);
+	ret = __copy_tofrom_user(to, (__force const void __user *)from, n);
+	prevent_write_to_user(to, n);
+	return ret;
 }
 
 static inline unsigned long __copy_from_user(void *to,
@@ -431,20 +492,39 @@ static inline unsigned long __copy_to_user(void __user *to,
 	return __copy_to_user_inatomic(to, from, size);
 }
 
-extern unsigned long __clear_user(void __user *addr, unsigned long size);
+unsigned long __arch_clear_user(void __user *addr, unsigned long size);
 
 static inline unsigned long clear_user(void __user *addr, unsigned long size)
 {
+	unsigned long ret = size;
 	might_fault();
-	if (likely(access_ok(VERIFY_WRITE, addr, size)))
-		return __clear_user(addr, size);
-	return size;
+	if (likely(access_ok(VERIFY_WRITE, addr, size))) {
+		allow_write_to_user(addr, size);
+		ret = __arch_clear_user(addr, size);
+		prevent_write_to_user(addr, size);
+	}
+	return ret;
+}
+
+static inline unsigned long __clear_user(void __user *addr, unsigned long size)
+{
+	return clear_user(addr, size);
 }
 
 extern long strncpy_from_user(char *dst, const char __user *src, long count);
 extern __must_check long strlen_user(const char __user *str);
 extern __must_check long strnlen_user(const char __user *str, long n);
 
+
+#define user_access_begin()	do { } while (0)
+#define user_access_end()	prevent_user_access(NULL, NULL, ~0ul)
+
+#define unsafe_op_wrap(op, err) do { if (unlikely(op)) goto err; } while (0)
+#define unsafe_get_user(x, p, e) unsafe_op_wrap(__get_user_allowed(x, p), e)
+#define unsafe_put_user(x, p, e) unsafe_op_wrap(__put_user_allowed(x, p), e)
+#define unsafe_copy_to_user(d, s, l, e) \
+	unsafe_op_wrap(__copy_to_user_inatomic(d, s, l), e)
+
 #endif  /* __ASSEMBLY__ */
 #endif /* __KERNEL__ */
 
diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 536718ed033f..7f8e1bdbe3e2 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -202,8 +202,8 @@ ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE)
 data_access_pSeries:
 	HMT_MEDIUM_PPR_DISCARD
 	SET_SCRATCH0(r13)
-	EXCEPTION_PROLOG_PSERIES(PACA_EXGEN, data_access_common, EXC_STD,
-				 KVMTEST, 0x300)
+	EXCEPTION_PROLOG_0(PACA_EXGEN)
+	b data_access_pSeries_ool
 
 	. = 0x380
 	.globl data_access_slb_pSeries
@@ -211,31 +211,15 @@ data_access_slb_pSeries:
 	HMT_MEDIUM_PPR_DISCARD
 	SET_SCRATCH0(r13)
 	EXCEPTION_PROLOG_0(PACA_EXSLB)
-	EXCEPTION_PROLOG_1(PACA_EXSLB, KVMTEST, 0x380)
-	std	r3,PACA_EXSLB+EX_R3(r13)
-	mfspr	r3,SPRN_DAR
-#ifdef __DISABLED__
-	/* Keep that around for when we re-implement dynamic VSIDs */
-	cmpdi	r3,0
-	bge	slb_miss_user_pseries
-#endif /* __DISABLED__ */
-	mfspr	r12,SPRN_SRR1
-#ifndef CONFIG_RELOCATABLE
-	b	slb_miss_realmode
-#else
-	/*
-	 * We can't just use a direct branch to slb_miss_realmode
-	 * because the distance from here to there depends on where
-	 * the kernel ends up being put.
-	 */
-	mfctr	r11
-	ld	r10,PACAKBASE(r13)
-	LOAD_HANDLER(r10, slb_miss_realmode)
-	mtctr	r10
-	bctr
-#endif
+	b data_access_slb_pSeries_ool
 
-	STD_EXCEPTION_PSERIES(0x400, 0x400, instruction_access)
+	. = 0x400
+	.globl instruction_access_pSeries
+instruction_access_pSeries:
+	HMT_MEDIUM_PPR_DISCARD
+	SET_SCRATCH0(r13)
+	EXCEPTION_PROLOG_0(PACA_EXGEN)
+	b instruction_access_pSeries_ool
 
 	. = 0x480
 	.globl instruction_access_slb_pSeries
@@ -243,24 +227,7 @@ instruction_access_slb_pSeries:
 	HMT_MEDIUM_PPR_DISCARD
 	SET_SCRATCH0(r13)
 	EXCEPTION_PROLOG_0(PACA_EXSLB)
-	EXCEPTION_PROLOG_1(PACA_EXSLB, KVMTEST_PR, 0x480)
-	std	r3,PACA_EXSLB+EX_R3(r13)
-	mfspr	r3,SPRN_SRR0		/* SRR0 is faulting address */
-#ifdef __DISABLED__
-	/* Keep that around for when we re-implement dynamic VSIDs */
-	cmpdi	r3,0
-	bge	slb_miss_user_pseries
-#endif /* __DISABLED__ */
-	mfspr	r12,SPRN_SRR1
-#ifndef CONFIG_RELOCATABLE
-	b	slb_miss_realmode
-#else
-	mfctr	r11
-	ld	r10,PACAKBASE(r13)
-	LOAD_HANDLER(r10, slb_miss_realmode)
-	mtctr	r10
-	bctr
-#endif
+	b instruction_access_slb_pSeries_ool
 
 	/* We open code these as we can't have a ". = x" (even with
 	 * x = "." within a feature section
@@ -291,13 +258,19 @@ hardware_interrupt_hv:
 	KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0x800)
 
 	. = 0x900
-	.globl decrementer_pSeries
-decrementer_pSeries:
+	.globl decrementer_trampoline
+decrementer_trampoline:
 	SET_SCRATCH0(r13)
 	EXCEPTION_PROLOG_0(PACA_EXGEN)
 	b	decrementer_ool
 
-	STD_EXCEPTION_HV(0x980, 0x982, hdecrementer)
+	. = 0x980
+	.globl hdecrementer_trampoline
+hdecrementer_trampoline:
+	HMT_MEDIUM_PPR_DISCARD;
+	SET_SCRATCH0(r13);
+	EXCEPTION_PROLOG_0(PACA_EXGEN)
+	b hdecrementer_hv
 
 	MASKABLE_EXCEPTION_PSERIES(0xa00, 0xa00, doorbell_super)
 	KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0xa00)
@@ -545,6 +518,64 @@ machine_check_pSeries_0:
 	KVM_HANDLER_PR(PACA_EXGEN, EXC_STD, 0x900)
 	KVM_HANDLER(PACA_EXGEN, EXC_HV, 0x982)
 
+/* moved from 0x300 */
+	.globl data_access_pSeries_ool
+data_access_pSeries_ool:
+	EXCEPTION_PROLOG_1(PACA_EXGEN, KVMTEST, 0x300)
+	EXCEPTION_PROLOG_PSERIES_1(data_access_common, EXC_STD)
+
+	.globl data_access_slb_pSeries_ool
+data_access_slb_pSeries_ool:
+	EXCEPTION_PROLOG_1(PACA_EXSLB, KVMTEST, 0x380)
+	std	r3,PACA_EXSLB+EX_R3(r13)
+	mfspr	r3,SPRN_DAR
+#ifdef __DISABLED__
+	/* Keep that around for when we re-implement dynamic VSIDs */
+	cmpdi	r3,0
+	bge	slb_miss_user_pseries
+#endif /* __DISABLED__ */
+	mfspr	r12,SPRN_SRR1
+#ifndef CONFIG_RELOCATABLE
+	b	slb_miss_realmode
+#else
+	/*
+	 * We can't just use a direct branch to slb_miss_realmode
+	 * because the distance from here to there depends on where
+	 * the kernel ends up being put.
+	 */
+	mfctr	r11
+	ld	r10,PACAKBASE(r13)
+	LOAD_HANDLER(r10, slb_miss_realmode)
+	mtctr	r10
+	bctr
+#endif
+
+	.globl instruction_access_pSeries_ool
+instruction_access_pSeries_ool:
+	EXCEPTION_PROLOG_1(PACA_EXGEN, KVMTEST_PR, 0x400)
+	EXCEPTION_PROLOG_PSERIES_1(instruction_access_common, EXC_STD)
+
+	.globl instruction_access_slb_pSeries_ool
+instruction_access_slb_pSeries_ool:
+	EXCEPTION_PROLOG_1(PACA_EXSLB, KVMTEST_PR, 0x480)
+	std	r3,PACA_EXSLB+EX_R3(r13)
+	mfspr	r3,SPRN_SRR0		/* SRR0 is faulting address */
+#ifdef __DISABLED__
+	/* Keep that around for when we re-implement dynamic VSIDs */
+	cmpdi	r3,0
+	bge	slb_miss_user_pseries
+#endif /* __DISABLED__ */
+	mfspr	r12,SPRN_SRR1
+#ifndef CONFIG_RELOCATABLE
+	b	slb_miss_realmode
+#else
+	mfctr	r11
+	ld	r10,PACAKBASE(r13)
+	LOAD_HANDLER(r10, slb_miss_realmode)
+	mtctr	r10
+	bctr
+#endif
+
 #ifdef CONFIG_PPC_DENORMALISATION
 denorm_assist:
 BEGIN_FTR_SECTION
@@ -612,6 +643,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_CFAR)
 	.align	7
 	/* moved from 0xe00 */
 	MASKABLE_EXCEPTION_OOL(0x900, decrementer)
+	STD_EXCEPTION_HV_OOL(0x982, hdecrementer)
 	STD_EXCEPTION_HV_OOL(0xe02, h_data_storage)
 	KVM_HANDLER_SKIP(PACA_EXGEN, EXC_HV, 0xe02)
 	STD_EXCEPTION_HV_OOL(0xe22, h_instr_storage)
@@ -894,7 +926,15 @@ hardware_interrupt_relon_hv:
 	STD_RELON_EXCEPTION_PSERIES(0x4600, 0x600, alignment)
 	STD_RELON_EXCEPTION_PSERIES(0x4700, 0x700, program_check)
 	STD_RELON_EXCEPTION_PSERIES(0x4800, 0x800, fp_unavailable)
-	MASKABLE_RELON_EXCEPTION_PSERIES(0x4900, 0x900, decrementer)
+
+	. = 0x4900
+	.globl decrementer_relon_trampoline
+decrementer_relon_trampoline:
+	HMT_MEDIUM_PPR_DISCARD
+	SET_SCRATCH0(r13)
+	EXCEPTION_PROLOG_0(PACA_EXGEN)
+	b decrementer_relon_pSeries
+
 	STD_RELON_EXCEPTION_HV(0x4980, 0x982, hdecrementer)
 	MASKABLE_RELON_EXCEPTION_PSERIES(0x4a00, 0xa00, doorbell_super)
 	STD_RELON_EXCEPTION_PSERIES(0x4b00, 0xb00, trap_0b)
@@ -1244,6 +1284,8 @@ END_FTR_SECTION_IFSET(CPU_FTR_VSX)
 __end_handlers:
 
 	/* Equivalents to the above handlers for relocation-on interrupt vectors */
+	MASKABLE_RELON_EXCEPTION_PSERIES_OOL(0x900, decrementer)
+
 	STD_RELON_EXCEPTION_HV_OOL(0xe40, emulation_assist)
 	MASKABLE_RELON_EXCEPTION_HV_OOL(0xe80, h_doorbell)
 
@@ -1588,14 +1630,9 @@ stf_barrier_fallback:
 	.endr
 	blr
 
-	.globl rfi_flush_fallback
-rfi_flush_fallback:
-	SET_SCRATCH0(r13);
-	GET_PACA(r13);
-	std	r9,PACA_EXRFI+EX_R9(r13)
-	std	r10,PACA_EXRFI+EX_R10(r13)
-	std	r11,PACA_EXRFI+EX_R11(r13)
-	mfctr	r9
+
+/* Clobbers r10, r11, ctr */
+.macro L1D_DISPLACEMENT_FLUSH
 	ld	r10,PACA_RFI_FLUSH_FALLBACK_AREA(r13)
 	ld	r11,PACA_L1D_FLUSH_SIZE(r13)
 	srdi	r11,r11,(7 + 3) /* 128 byte lines, unrolled 8x */
@@ -1621,7 +1658,18 @@ rfi_flush_fallback:
 	ld	r11,(0x80 + 8)*7(r10)
 	addi	r10,r10,0x80*8
 	bdnz	1b
+.endm
+
 
+	.globl rfi_flush_fallback
+rfi_flush_fallback:
+	SET_SCRATCH0(r13);
+	GET_PACA(r13);
+	std	r9,PACA_EXRFI+EX_R9(r13)
+	std	r10,PACA_EXRFI+EX_R10(r13)
+	std	r11,PACA_EXRFI+EX_R11(r13)
+	mfctr	r9
+	L1D_DISPLACEMENT_FLUSH
 	mtctr	r9
 	ld	r9,PACA_EXRFI+EX_R9(r13)
 	ld	r10,PACA_EXRFI+EX_R10(r13)
@@ -1637,32 +1685,7 @@ hrfi_flush_fallback:
 	std	r10,PACA_EXRFI+EX_R10(r13)
 	std	r11,PACA_EXRFI+EX_R11(r13)
 	mfctr	r9
-	ld	r10,PACA_RFI_FLUSH_FALLBACK_AREA(r13)
-	ld	r11,PACA_L1D_FLUSH_SIZE(r13)
-	srdi	r11,r11,(7 + 3) /* 128 byte lines, unrolled 8x */
-	mtctr	r11
-	DCBT_STOP_ALL_STREAM_IDS(r11) /* Stop prefetch streams */
-
-	/* order ld/st prior to dcbt stop all streams with flushing */
-	sync
-
-	/*
-	 * The load adresses are at staggered offsets within cachelines,
-	 * which suits some pipelines better (on others it should not
-	 * hurt).
-	 */
-1:
-	ld	r11,(0x80 + 8)*0(r10)
-	ld	r11,(0x80 + 8)*1(r10)
-	ld	r11,(0x80 + 8)*2(r10)
-	ld	r11,(0x80 + 8)*3(r10)
-	ld	r11,(0x80 + 8)*4(r10)
-	ld	r11,(0x80 + 8)*5(r10)
-	ld	r11,(0x80 + 8)*6(r10)
-	ld	r11,(0x80 + 8)*7(r10)
-	addi	r10,r10,0x80*8
-	bdnz	1b
-
+	L1D_DISPLACEMENT_FLUSH
 	mtctr	r9
 	ld	r9,PACA_EXRFI+EX_R9(r13)
 	ld	r10,PACA_EXRFI+EX_R10(r13)
@@ -1670,6 +1693,20 @@ hrfi_flush_fallback:
 	GET_SCRATCH0(r13);
 	hrfid
 
+	.globl entry_flush_fallback
+entry_flush_fallback:
+	std	r9,PACA_EXRFI+EX_R9(r13)
+	std	r10,PACA_EXRFI+EX_R10(r13)
+	std	r11,PACA_EXRFI+EX_R11(r13)
+	mfctr	r9
+	L1D_DISPLACEMENT_FLUSH
+	mtctr	r9
+	ld	r9,PACA_EXRFI+EX_R9(r13)
+	ld	r10,PACA_EXRFI+EX_R10(r13)
+	ld	r11,PACA_EXRFI+EX_R11(r13)
+	blr
+
+
 /*
  * Hash table stuff
  */
@@ -1829,3 +1866,12 @@ END_FTR_SECTION_IFSET(CPU_FTR_CFAR)
 1:	addi	r3,r1,STACK_FRAME_OVERHEAD
 	bl	kernel_bad_stack
 	b	1b
+
+_KPROBE(do_uaccess_flush)
+	UACCESS_FLUSH_FIXUP_SECTION
+	nop
+	nop
+	nop
+	blr
+	L1D_DISPLACEMENT_FLUSH
+	blr
diff --git a/arch/powerpc/kernel/head_8xx.S b/arch/powerpc/kernel/head_8xx.S
index 01e274e6907b..3d7512e72900 100644
--- a/arch/powerpc/kernel/head_8xx.S
+++ b/arch/powerpc/kernel/head_8xx.S
@@ -361,11 +361,9 @@ InstructionTLBMiss:
 	/* Load the MI_TWC with the attributes for this "segment." */
 	MTSPR_CPU6(SPRN_MI_TWC, r11, r3)	/* Set segment attributes */
 
-#ifdef CONFIG_SWAP
-	rlwinm	r11, r10, 32-5, _PAGE_PRESENT
+	rlwinm	r11, r10, 32-11, _PAGE_PRESENT
 	and	r11, r11, r10
 	rlwimi	r10, r11, 0, _PAGE_PRESENT
-#endif
 	li	r11, RPN_PATTERN
 	/* The Linux PTE won't go exactly into the MMU TLB.
 	 * Software indicator bits 20-23 and 28 must be clear.
@@ -436,11 +434,9 @@ DataStoreTLBMiss:
 	 * r11 = ((r10 & PRESENT) & ((r10 & ACCESSED) >> 5));
 	 * r10 = (r10 & ~PRESENT) | r11;
 	 */
-#ifdef CONFIG_SWAP
-	rlwinm	r11, r10, 32-5, _PAGE_PRESENT
+	rlwinm	r11, r10, 32-11, _PAGE_PRESENT
 	and	r11, r11, r10
 	rlwimi	r10, r11, 0, _PAGE_PRESENT
-#endif
 	/* The Linux PTE won't go exactly into the MMU TLB.
 	 * Software indicator bits 22 and 28 must be clear.
 	 * Software indicator bits 24, 25, 26, and 27 must be
diff --git a/arch/powerpc/kernel/ppc_ksyms.c b/arch/powerpc/kernel/ppc_ksyms.c
index 202963ee013a..80eb47113d5d 100644
--- a/arch/powerpc/kernel/ppc_ksyms.c
+++ b/arch/powerpc/kernel/ppc_ksyms.c
@@ -5,6 +5,10 @@
 #include <asm/switch_to.h>
 #include <asm/cacheflush.h>
 #include <asm/epapr_hcalls.h>
+#include <asm/uaccess.h>
+#ifdef CONFIG_PPC64
+#include <asm/book3s/64/kup-radix.h>
+#endif
 
 EXPORT_SYMBOL(flush_dcache_range);
 EXPORT_SYMBOL(flush_icache_range);
@@ -43,3 +47,9 @@ EXPORT_SYMBOL(epapr_hypercall_start);
 #endif
 
 EXPORT_SYMBOL(current_stack_pointer);
+
+EXPORT_SYMBOL(__arch_clear_user);
+
+#ifdef CONFIG_PPC64
+EXPORT_SYMBOL(do_uaccess_flush);
+#endif
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index 11590f6cb2f9..3c6717569360 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -844,7 +844,13 @@ early_initcall(disable_hardlockup_detector);
 static enum l1d_flush_type enabled_flush_types;
 static void *l1d_flush_fallback_area;
 static bool no_rfi_flush;
+static bool no_entry_flush;
+static bool no_uaccess_flush;
 bool rfi_flush;
+bool entry_flush;
+bool uaccess_flush;
+DEFINE_STATIC_KEY_FALSE(uaccess_flush_key);
+EXPORT_SYMBOL(uaccess_flush_key);
 
 static int __init handle_no_rfi_flush(char *p)
 {
@@ -854,6 +860,22 @@ static int __init handle_no_rfi_flush(char *p)
 }
 early_param("no_rfi_flush", handle_no_rfi_flush);
 
+static int __init handle_no_entry_flush(char *p)
+{
+	pr_info("entry-flush: disabled on command line.");
+	no_entry_flush = true;
+	return 0;
+}
+early_param("no_entry_flush", handle_no_entry_flush);
+
+static int __init handle_no_uaccess_flush(char *p)
+{
+	pr_info("uaccess-flush: disabled on command line.");
+	no_uaccess_flush = true;
+	return 0;
+}
+early_param("no_uaccess_flush", handle_no_uaccess_flush);
+
 /*
  * The RFI flush is not KPTI, but because users will see doco that says to use
  * nopti we hijack that option here to also disable the RFI flush.
@@ -885,6 +907,35 @@ void rfi_flush_enable(bool enable)
 	rfi_flush = enable;
 }
 
+void entry_flush_enable(bool enable)
+{
+	if (enable) {
+		do_entry_flush_fixups(enabled_flush_types);
+		on_each_cpu(do_nothing, NULL, 1);
+	} else {
+		do_entry_flush_fixups(L1D_FLUSH_NONE);
+	}
+
+	entry_flush = enable;
+}
+
+void uaccess_flush_enable(bool enable)
+{
+	if (enable) {
+		do_uaccess_flush_fixups(enabled_flush_types);
+		if (static_key_initialized)
+			static_branch_enable(&uaccess_flush_key);
+		else
+			printk(KERN_DEBUG "uaccess-flush: deferring static key until after static key initialization\n");
+		on_each_cpu(do_nothing, NULL, 1);
+	} else {
+		static_branch_disable(&uaccess_flush_key);
+		do_uaccess_flush_fixups(L1D_FLUSH_NONE);
+	}
+
+	uaccess_flush = enable;
+}
+
 static void __ref init_fallback_flush(void)
 {
 	u64 l1d_size, limit;
@@ -930,6 +981,24 @@ void setup_rfi_flush(enum l1d_flush_type types, bool enable)
 		rfi_flush_enable(enable);
 }
 
+void setup_entry_flush(bool enable)
+{
+	if (cpu_mitigations_off())
+		return;
+
+	if (!no_entry_flush)
+		entry_flush_enable(enable);
+}
+
+void setup_uaccess_flush(bool enable)
+{
+	if (cpu_mitigations_off())
+		return;
+
+	if (!no_uaccess_flush)
+		uaccess_flush_enable(enable);
+}
+
 #ifdef CONFIG_DEBUG_FS
 static int rfi_flush_set(void *data, u64 val)
 {
@@ -957,11 +1026,80 @@ static int rfi_flush_get(void *data, u64 *val)
 
 DEFINE_SIMPLE_ATTRIBUTE(fops_rfi_flush, rfi_flush_get, rfi_flush_set, "%llu\n");
 
+static int entry_flush_set(void *data, u64 val)
+{
+	bool enable;
+
+	if (val == 1)
+		enable = true;
+	else if (val == 0)
+		enable = false;
+	else
+		return -EINVAL;
+
+	/* Only do anything if we're changing state */
+	if (enable != entry_flush)
+		entry_flush_enable(enable);
+
+	return 0;
+}
+
+static int entry_flush_get(void *data, u64 *val)
+{
+	*val = entry_flush ? 1 : 0;
+	return 0;
+}
+
+DEFINE_SIMPLE_ATTRIBUTE(fops_entry_flush, entry_flush_get, entry_flush_set, "%llu\n");
+
+static int uaccess_flush_set(void *data, u64 val)
+{
+	bool enable;
+
+	if (val == 1)
+		enable = true;
+	else if (val == 0)
+		enable = false;
+	else
+		return -EINVAL;
+
+	/* Only do anything if we're changing state */
+	if (enable != uaccess_flush)
+		uaccess_flush_enable(enable);
+
+	return 0;
+}
+
+static int uaccess_flush_get(void *data, u64 *val)
+{
+	*val = uaccess_flush ? 1 : 0;
+	return 0;
+}
+
+DEFINE_SIMPLE_ATTRIBUTE(fops_uaccess_flush, uaccess_flush_get, uaccess_flush_set, "%llu\n");
+
+
 static __init int rfi_flush_debugfs_init(void)
 {
 	debugfs_create_file("rfi_flush", 0600, powerpc_debugfs_root, NULL, &fops_rfi_flush);
+	debugfs_create_file("entry_flush", 0600, powerpc_debugfs_root, NULL, &fops_entry_flush);
+	debugfs_create_file("uaccess_flush", 0600, powerpc_debugfs_root, NULL, &fops_uaccess_flush);
 	return 0;
 }
 device_initcall(rfi_flush_debugfs_init);
 #endif
+
+/*
+ * setup_uaccess_flush runs before jump_label_init, so we can't do the setup
+ * there. Do it now instead.
+ */
+static __init int uaccess_flush_static_key_init(void)
+{
+	if (uaccess_flush) {
+		printk(KERN_DEBUG "uaccess-flush: switching on static key\n");
+		static_branch_enable(&uaccess_flush_key);
+	}
+	return 0;
+}
+early_initcall(uaccess_flush_static_key_init);
 #endif /* CONFIG_PPC_BOOK3S_64 */
diff --git a/arch/powerpc/kernel/vmlinux.lds.S b/arch/powerpc/kernel/vmlinux.lds.S
index 9b1e297be673..f820d03335eb 100644
--- a/arch/powerpc/kernel/vmlinux.lds.S
+++ b/arch/powerpc/kernel/vmlinux.lds.S
@@ -80,6 +80,20 @@ SECTIONS
 		__stop___stf_entry_barrier_fixup = .;
 	}
 
+	. = ALIGN(8);
+	__uaccess_flush_fixup : AT(ADDR(__uaccess_flush_fixup) - LOAD_OFFSET) {
+		__start___uaccess_flush_fixup = .;
+		*(__uaccess_flush_fixup)
+		__stop___uaccess_flush_fixup = .;
+	}
+
+	. = ALIGN(8);
+	__entry_flush_fixup : AT(ADDR(__entry_flush_fixup) - LOAD_OFFSET) {
+		__start___entry_flush_fixup = .;
+		*(__entry_flush_fixup)
+		__stop___entry_flush_fixup = .;
+	}
+
 	. = ALIGN(8);
 	__stf_exit_barrier_fixup : AT(ADDR(__stf_exit_barrier_fixup) - LOAD_OFFSET) {
 		__start___stf_exit_barrier_fixup = .;
diff --git a/arch/powerpc/lib/checksum_wrappers_64.c b/arch/powerpc/lib/checksum_wrappers_64.c
index 08e3a3356c40..11b58949eb62 100644
--- a/arch/powerpc/lib/checksum_wrappers_64.c
+++ b/arch/powerpc/lib/checksum_wrappers_64.c
@@ -29,6 +29,7 @@ __wsum csum_and_copy_from_user(const void __user *src, void *dst,
 	unsigned int csum;
 
 	might_sleep();
+	allow_read_from_user(src, len);
 
 	*err_ptr = 0;
 
@@ -60,6 +61,7 @@ __wsum csum_and_copy_from_user(const void __user *src, void *dst,
 	}
 
 out:
+	prevent_read_from_user(src, len);
 	return (__force __wsum)csum;
 }
 EXPORT_SYMBOL(csum_and_copy_from_user);
@@ -70,6 +72,7 @@ __wsum csum_and_copy_to_user(const void *src, void __user *dst, int len,
 	unsigned int csum;
 
 	might_sleep();
+	allow_write_to_user(dst, len);
 
 	*err_ptr = 0;
 
@@ -97,6 +100,7 @@ __wsum csum_and_copy_to_user(const void *src, void __user *dst, int len,
 	}
 
 out:
+	prevent_write_to_user(dst, len);
 	return (__force __wsum)csum;
 }
 EXPORT_SYMBOL(csum_and_copy_to_user);
diff --git a/arch/powerpc/lib/feature-fixups.c b/arch/powerpc/lib/feature-fixups.c
index 7bdfc19a491d..40b134bf5a68 100644
--- a/arch/powerpc/lib/feature-fixups.c
+++ b/arch/powerpc/lib/feature-fixups.c
@@ -229,6 +229,110 @@ void do_stf_barrier_fixups(enum stf_barrier_type types)
 	do_stf_exit_barrier_fixups(types);
 }
 
+void do_uaccess_flush_fixups(enum l1d_flush_type types)
+{
+	unsigned int instrs[4], *dest;
+	long *start, *end;
+	int i;
+
+	start = PTRRELOC(&__start___uaccess_flush_fixup);
+	end = PTRRELOC(&__stop___uaccess_flush_fixup);
+
+	instrs[0] = 0x60000000; /* nop */
+	instrs[1] = 0x60000000; /* nop */
+	instrs[2] = 0x60000000; /* nop */
+	instrs[3] = 0x4e800020; /* blr */
+
+	i = 0;
+	if (types == L1D_FLUSH_FALLBACK) {
+		instrs[3] = 0x60000000; /* nop */
+		/* fallthrough to fallback flush */
+	}
+
+	if (types & L1D_FLUSH_ORI) {
+		instrs[i++] = 0x63ff0000; /* ori 31,31,0 speculation barrier */
+		instrs[i++] = 0x63de0000; /* ori 30,30,0 L1d flush*/
+	}
+
+	if (types & L1D_FLUSH_MTTRIG)
+		instrs[i++] = 0x7c12dba6; /* mtspr TRIG2,r0 (SPR #882) */
+
+	for (i = 0; start < end; start++, i++) {
+		dest = (void *)start + *start;
+
+		pr_devel("patching dest %lx\n", (unsigned long)dest);
+
+		patch_instruction(dest, instrs[0]);
+
+		patch_instruction((dest + 1), instrs[1]);
+		patch_instruction((dest + 2), instrs[2]);
+		patch_instruction((dest + 3), instrs[3]);
+	}
+
+	printk(KERN_DEBUG "uaccess-flush: patched %d locations (%s flush)\n", i,
+		(types == L1D_FLUSH_NONE)       ? "no" :
+		(types == L1D_FLUSH_FALLBACK)   ? "fallback displacement" :
+		(types &  L1D_FLUSH_ORI)        ? (types & L1D_FLUSH_MTTRIG)
+							? "ori+mttrig type"
+							: "ori type" :
+		(types &  L1D_FLUSH_MTTRIG)     ? "mttrig type"
+						: "unknown");
+}
+
+void do_entry_flush_fixups(enum l1d_flush_type types)
+{
+	unsigned int instrs[3], *dest;
+	long *start, *end;
+	int i;
+
+	start = PTRRELOC(&__start___entry_flush_fixup);
+	end = PTRRELOC(&__stop___entry_flush_fixup);
+
+	instrs[0] = 0x60000000; /* nop */
+	instrs[1] = 0x60000000; /* nop */
+	instrs[2] = 0x60000000; /* nop */
+
+	i = 0;
+	if (types == L1D_FLUSH_FALLBACK) {
+		instrs[i++] = 0x7d4802a6; /* mflr r10		*/
+		instrs[i++] = 0x60000000; /* branch patched below */
+		instrs[i++] = 0x7d4803a6; /* mtlr r10		*/
+	}
+
+	if (types & L1D_FLUSH_ORI) {
+		instrs[i++] = 0x63ff0000; /* ori 31,31,0 speculation barrier */
+		instrs[i++] = 0x63de0000; /* ori 30,30,0 L1d flush*/
+	}
+
+	if (types & L1D_FLUSH_MTTRIG)
+		instrs[i++] = 0x7c12dba6; /* mtspr TRIG2,r0 (SPR #882) */
+
+	for (i = 0; start < end; start++, i++) {
+		dest = (void *)start + *start;
+
+		pr_devel("patching dest %lx\n", (unsigned long)dest);
+
+		patch_instruction(dest, instrs[0]);
+
+		if (types == L1D_FLUSH_FALLBACK)
+			patch_branch((dest + 1), (unsigned long)&entry_flush_fallback,
+				     BRANCH_SET_LINK);
+		else
+			patch_instruction((dest + 1), instrs[1]);
+
+		patch_instruction((dest + 2), instrs[2]);
+	}
+
+	printk(KERN_DEBUG "entry-flush: patched %d locations (%s flush)\n", i,
+		(types == L1D_FLUSH_NONE)       ? "no" :
+		(types == L1D_FLUSH_FALLBACK)   ? "fallback displacement" :
+		(types &  L1D_FLUSH_ORI)        ? (types & L1D_FLUSH_MTTRIG)
+							? "ori+mttrig type"
+							: "ori type" :
+		(types &  L1D_FLUSH_MTTRIG)     ? "mttrig type"
+						: "unknown");
+}
+
 void do_rfi_flush_fixups(enum l1d_flush_type types)
 {
 	unsigned int instrs[3], *dest;
diff --git a/arch/powerpc/lib/string.S b/arch/powerpc/lib/string.S
index c80fb49ce607..93c4c34ad091 100644
--- a/arch/powerpc/lib/string.S
+++ b/arch/powerpc/lib/string.S
@@ -122,7 +122,7 @@ _GLOBAL(memchr)
 	blr
 
 #ifdef CONFIG_PPC32
-_GLOBAL(__clear_user)
+_GLOBAL(__arch_clear_user)
 	addi	r6,r3,-4
 	li	r3,0
 	li	r5,0
diff --git a/arch/powerpc/lib/string_64.S b/arch/powerpc/lib/string_64.S
index 7bd9549a90a2..14d26ad2cd69 100644
--- a/arch/powerpc/lib/string_64.S
+++ b/arch/powerpc/lib/string_64.S
@@ -27,7 +27,7 @@ PPC64_CACHES:
 	.section	".text"
 
 /**
- * __clear_user: - Zero a block of memory in user space, with less checking.
+ * __arch_clear_user: - Zero a block of memory in user space, with less checking.
  * @to:   Destination address, in user space.
  * @n:    Number of bytes to zero.
  *
@@ -77,7 +77,7 @@ err3;	stb	r0,0(r3)
 	mr	r3,r4
 	blr
 
-_GLOBAL_TOC(__clear_user)
+_GLOBAL_TOC(__arch_clear_user)
 	cmpdi	r4,32
 	neg	r6,r3
 	li	r0,0
diff --git a/arch/powerpc/platforms/powernv/setup.c b/arch/powerpc/platforms/powernv/setup.c
index e14b52c7ebd8..6259228a0e18 100644
--- a/arch/powerpc/platforms/powernv/setup.c
+++ b/arch/powerpc/platforms/powernv/setup.c
@@ -124,12 +124,27 @@ static void pnv_setup_rfi_flush(void)
 			type = L1D_FLUSH_ORI;
 	}
 
+	/*
+	 * 4.4 doesn't support Power9 bare metal, so we don't need to flush
+	 * here - the flushes fix a P9 specific vulnerability.
+	 */
+	security_ftr_clear(SEC_FTR_L1D_FLUSH_ENTRY);
+	security_ftr_clear(SEC_FTR_L1D_FLUSH_UACCESS);
+
 	enable = security_ftr_enabled(SEC_FTR_FAVOUR_SECURITY) && \
 		 (security_ftr_enabled(SEC_FTR_L1D_FLUSH_PR)   || \
 		  security_ftr_enabled(SEC_FTR_L1D_FLUSH_HV));
 
 	setup_rfi_flush(type, enable);
 	setup_count_cache_flush();
+
+	enable = security_ftr_enabled(SEC_FTR_FAVOUR_SECURITY) &&
+		 security_ftr_enabled(SEC_FTR_L1D_FLUSH_ENTRY);
+	setup_entry_flush(enable);
+
+	enable = security_ftr_enabled(SEC_FTR_FAVOUR_SECURITY) &&
+		 security_ftr_enabled(SEC_FTR_L1D_FLUSH_UACCESS);
+	setup_uaccess_flush(enable);
 }
 
 static void __init pnv_setup_arch(void)
diff --git a/arch/powerpc/platforms/pseries/setup.c b/arch/powerpc/platforms/pseries/setup.c
index 88fcf6a95fa6..498c5092bd23 100644
--- a/arch/powerpc/platforms/pseries/setup.c
+++ b/arch/powerpc/platforms/pseries/setup.c
@@ -584,6 +584,14 @@ void pseries_setup_rfi_flush(void)
 
 	setup_rfi_flush(types, enable);
 	setup_count_cache_flush();
+
+	enable = security_ftr_enabled(SEC_FTR_FAVOUR_SECURITY) &&
+		 security_ftr_enabled(SEC_FTR_L1D_FLUSH_ENTRY);
+	setup_entry_flush(enable);
+
+	enable = security_ftr_enabled(SEC_FTR_FAVOUR_SECURITY) &&
+		 security_ftr_enabled(SEC_FTR_L1D_FLUSH_UACCESS);
+	setup_uaccess_flush(enable);
 }
 
 static void __init pSeries_setup_arch(void)
diff --git a/arch/x86/kvm/emulate.c b/arch/x86/kvm/emulate.c
index 0c1e249a7ab6..827d54a5126e 100644
--- a/arch/x86/kvm/emulate.c
+++ b/arch/x86/kvm/emulate.c
@@ -3922,6 +3922,12 @@ static int em_clflush(struct x86_emulate_ctxt *ctxt)
 	return X86EMUL_CONTINUE;
 }
 
+static int em_clflushopt(struct x86_emulate_ctxt *ctxt)
+{
+	/* emulating clflushopt regardless of cpuid */
+	return X86EMUL_CONTINUE;
+}
+
 static int em_movsxd(struct x86_emulate_ctxt *ctxt)
 {
 	ctxt->dst.val = (s32) ctxt->src.val;
@@ -4411,7 +4417,7 @@ static const struct opcode group11[] = {
 };
 
 static const struct gprefix pfx_0f_ae_7 = {
-	I(SrcMem | ByteOp, em_clflush), N, N, N,
+	I(SrcMem | ByteOp, em_clflush), I(SrcMem | ByteOp, em_clflushopt), N, N,
 };
 
 static const struct group_dual group15 = { {
diff --git a/drivers/i2c/busses/i2c-imx.c b/drivers/i2c/busses/i2c-imx.c
index d121c5732d7d..37303a7a2e73 100644
--- a/drivers/i2c/busses/i2c-imx.c
+++ b/drivers/i2c/busses/i2c-imx.c
@@ -1093,20 +1093,20 @@ static int i2c_imx_probe(struct platform_device *pdev)
 		goto clk_disable;
 	}
 
-	/* Request IRQ */
-	ret = devm_request_irq(&pdev->dev, irq, i2c_imx_isr, 0,
-				pdev->name, i2c_imx);
-	if (ret) {
-		dev_err(&pdev->dev, "can't claim irq %d\n", irq);
-		goto clk_disable;
-	}
-
 	/* Init queue */
 	init_waitqueue_head(&i2c_imx->queue);
 
 	/* Set up adapter data */
 	i2c_set_adapdata(&i2c_imx->adapter, i2c_imx);
 
+	/* Request IRQ */
+	ret = request_threaded_irq(irq, i2c_imx_isr, NULL, 0,
+				   pdev->name, i2c_imx);
+	if (ret) {
+		dev_err(&pdev->dev, "can't claim irq %d\n", irq);
+		goto clk_disable;
+	}
+
 	/* Set up clock divider */
 	i2c_imx->bitrate = IMX_I2C_BIT_RATE;
 	ret = of_property_read_u32(pdev->dev.of_node,
@@ -1125,7 +1125,7 @@ static int i2c_imx_probe(struct platform_device *pdev)
 	ret = i2c_add_numbered_adapter(&i2c_imx->adapter);
 	if (ret < 0) {
 		dev_err(&pdev->dev, "registration failed\n");
-		goto clk_disable;
+		goto clk_free_irq;
 	}
 
 	/* Set up platform driver data */
@@ -1143,6 +1143,8 @@ static int i2c_imx_probe(struct platform_device *pdev)
 
 	return 0;   /* Return OK */
 
+clk_free_irq:
+	free_irq(irq, i2c_imx);
 clk_disable:
 	clk_disable_unprepare(i2c_imx->clk);
 	return ret;
@@ -1151,6 +1153,7 @@ clk_disable:
 static int i2c_imx_remove(struct platform_device *pdev)
 {
 	struct imx_i2c_struct *i2c_imx = platform_get_drvdata(pdev);
+	int irq;
 
 	/* remove adapter */
 	dev_dbg(&i2c_imx->adapter.dev, "adapter removed\n");
@@ -1165,6 +1168,10 @@ static int i2c_imx_remove(struct platform_device *pdev)
 	imx_i2c_write_reg(0, i2c_imx, IMX_I2C_I2CR);
 	imx_i2c_write_reg(0, i2c_imx, IMX_I2C_I2SR);
 
+	irq = platform_get_irq(pdev, 0);
+	if (irq >= 0)
+		free_irq(irq, i2c_imx);
+
 	return 0;
 }
 
diff --git a/drivers/input/keyboard/sunkbd.c b/drivers/input/keyboard/sunkbd.c
index dc6bb9d5b4f0..191c27dda386 100644
--- a/drivers/input/keyboard/sunkbd.c
+++ b/drivers/input/keyboard/sunkbd.c
@@ -115,7 +115,8 @@ static irqreturn_t sunkbd_interrupt(struct serio *serio,
 	switch (data) {
 
 	case SUNKBD_RET_RESET:
-		schedule_work(&sunkbd->tq);
+		if (sunkbd->enabled)
+			schedule_work(&sunkbd->tq);
 		sunkbd->reset = -1;
 		break;
 
@@ -216,16 +217,12 @@ static int sunkbd_initialize(struct sunkbd *sunkbd)
 }
 
 /*
- * sunkbd_reinit() sets leds and beeps to a state the computer remembers they
- * were in.
+ * sunkbd_set_leds_beeps() sets leds and beeps to a state the computer remembers
+ * they were in.
  */
 
-static void sunkbd_reinit(struct work_struct *work)
+static void sunkbd_set_leds_beeps(struct sunkbd *sunkbd)
 {
-	struct sunkbd *sunkbd = container_of(work, struct sunkbd, tq);
-
-	wait_event_interruptible_timeout(sunkbd->wait, sunkbd->reset >= 0, HZ);
-
 	serio_write(sunkbd->serio, SUNKBD_CMD_SETLED);
 	serio_write(sunkbd->serio,
 		(!!test_bit(LED_CAPSL,   sunkbd->dev->led) << 3) |
@@ -238,11 +235,39 @@ static void sunkbd_reinit(struct work_struct *work)
 		SUNKBD_CMD_BELLOFF - !!test_bit(SND_BELL, sunkbd->dev->snd));
 }
 
+
+/*
+ * sunkbd_reinit() wait for the keyboard reset to complete and restores state
+ * of leds and beeps.
+ */
+
+static void sunkbd_reinit(struct work_struct *work)
+{
+	struct sunkbd *sunkbd = container_of(work, struct sunkbd, tq);
+
+	/*
+	 * It is OK that we check sunkbd->enabled without pausing serio,
+	 * as we only want to catch true->false transition that will
+	 * happen once and we will be woken up for it.
+	 */
+	wait_event_interruptible_timeout(sunkbd->wait,
+					 sunkbd->reset >= 0 || !sunkbd->enabled,
+					 HZ);
+
+	if (sunkbd->reset >= 0 && sunkbd->enabled)
+		sunkbd_set_leds_beeps(sunkbd);
+}
+
 static void sunkbd_enable(struct sunkbd *sunkbd, bool enable)
 {
 	serio_pause_rx(sunkbd->serio);
 	sunkbd->enabled = enable;
 	serio_continue_rx(sunkbd->serio);
+
+	if (!enable) {
+		wake_up_interruptible(&sunkbd->wait);
+		cancel_work_sync(&sunkbd->tq);
+	}
 }
 
 /*
diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c
index adbc1f59969a..d8cdab4bfd30 100644
--- a/fs/xfs/xfs_icache.c
+++ b/fs/xfs/xfs_icache.c
@@ -134,6 +134,46 @@ xfs_inode_free(
 	call_rcu(&VFS_I(ip)->i_rcu, xfs_inode_free_callback);
 }
 
+/*
+ * If we are allocating a new inode, then check what was returned is
+ * actually a free, empty inode. If we are not allocating an inode,
+ * then check we didn't find a free inode.
+ *
+ * Returns:
+ *	0		if the inode free state matches the lookup context
+ *	-ENOENT		if the inode is free and we are not allocating
+ *	-EFSCORRUPTED	if there is any state mismatch at all
+ */
+static int
+xfs_iget_check_free_state(
+	struct xfs_inode	*ip,
+	int			flags)
+{
+	if (flags & XFS_IGET_CREATE) {
+		/* should be a free inode */
+		if (ip->i_d.di_mode != 0) {
+			xfs_warn(ip->i_mount,
+"Corruption detected! Free inode 0x%llx not marked free! (mode 0x%x)",
+				ip->i_ino, ip->i_d.di_mode);
+			return -EFSCORRUPTED;
+		}
+
+		if (ip->i_d.di_nblocks != 0) {
+			xfs_warn(ip->i_mount,
+"Corruption detected! Free inode 0x%llx has blocks allocated!",
+				ip->i_ino);
+			return -EFSCORRUPTED;
+		}
+		return 0;
+	}
+
+	/* should be an allocated inode */
+	if (ip->i_d.di_mode == 0)
+		return -ENOENT;
+
+	return 0;
+}
+
 /*
  * Check the validity of the inode we just found it the cache
  */
@@ -183,12 +223,12 @@ xfs_iget_cache_hit(
 	}
 
 	/*
-	 * If lookup is racing with unlink return an error immediately.
+	 * Check the inode free state is valid. This also detects lookup
+	 * racing with unlinks.
 	 */
-	if (ip->i_d.di_mode == 0 && !(flags & XFS_IGET_CREATE)) {
-		error = -ENOENT;
+	error = xfs_iget_check_free_state(ip, flags);
+	if (error)
 		goto out_error;
-	}
 
 	/*
 	 * If IRECLAIMABLE is set, we've torn down the VFS inode already.
@@ -298,10 +338,14 @@ xfs_iget_cache_miss(
 
 	trace_xfs_iget_miss(ip);
 
-	if ((ip->i_d.di_mode == 0) && !(flags & XFS_IGET_CREATE)) {
-		error = -ENOENT;
+
+	/*
+	 * Check the inode free state is valid. This also detects lookup
+	 * racing with unlinks.
+	 */
+	error = xfs_iget_check_free_state(ip, flags);
+	if (error)
 		goto out_destroy;
-	}
 
 	/*
 	 * Preload the radix tree so we can insert safely under the
diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c
index bbddab248c48..6f7c3f6a5027 100644
--- a/net/mac80211/sta_info.c
+++ b/net/mac80211/sta_info.c
@@ -242,6 +242,24 @@ struct sta_info *sta_info_get_by_idx(struct ieee80211_sub_if_data *sdata,
  */
 void sta_info_free(struct ieee80211_local *local, struct sta_info *sta)
 {
+	/*
+	 * If we had used sta_info_pre_move_state() then we might not
+	 * have gone through the state transitions down again, so do
+	 * it here now (and warn if it's inserted).
+	 *
+	 * This will clear state such as fast TX/RX that may have been
+	 * allocated during state transitions.
+	 */
+	while (sta->sta_state > IEEE80211_STA_NONE) {
+		int ret;
+
+		WARN_ON_ONCE(test_sta_flag(sta, WLAN_STA_INSERTED));
+
+		ret = sta_info_move_state(sta, sta->sta_state - 1);
+		if (WARN_ONCE(ret, "sta_info_move_state() returned %d\n", ret))
+			break;
+	}
+
 	if (sta->rate_ctrl)
 		rate_control_free_sta(sta);