Merge tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux

Pull arm64 updates from Catalin Marinas:
 "arm64 updates for 3.20:

   - reimplementation of the virtual remapping of UEFI Runtime Services
     in a way that is stable across kexec
   - emulation of the "setend" instruction for 32-bit tasks (user
     endianness switching trapped in the kernel, SCTLR_EL1.E0E bit set
     accordingly)
   - compat_sys_call_table implemented in C (from asm) and made it a
     constant array together with sys_call_table
   - export CPU cache information via /sys (like other architectures)
   - DMA API implementation clean-up in preparation for IOMMU support
   - macros clean-up for KVM
   - dropped some unnecessary cache+tlb maintenance
   - CONFIG_ARM64_CPU_SUSPEND clean-up
   - defconfig update (CPU_IDLE)

  The EFI changes going via the arm64 tree have been acked by Matt
  Fleming.  There is also a patch adding sys_*stat64 prototypes to
  include/linux/syscalls.h, acked by Andrew Morton"

* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (47 commits)
  arm64: compat: Remove incorrect comment in compat_siginfo
  arm64: Fix section mismatch on alloc_init_p[mu]d()
  arm64: Avoid breakage caused by .altmacro in fpsimd save/restore macros
  arm64: mm: use *_sect to check for section maps
  arm64: drop unnecessary cache+tlb maintenance
  arm64:mm: free the useless initial page table
  arm64: Enable CPU_IDLE in defconfig
  arm64: kernel: remove ARM64_CPU_SUSPEND config option
  arm64: make sys_call_table const
  arm64: Remove asm/syscalls.h
  arm64: Implement the compat_sys_call_table in C
  syscalls: Declare sys_*stat64 prototypes if __ARCH_WANT_(COMPAT_)STAT64
  compat: Declare compat_sys_sigpending and compat_sys_sigprocmask prototypes
  arm64: uapi: expose our struct ucontext to the uapi headers
  smp, ARM64: Kill SMP single function call interrupt
  arm64: Emulate SETEND for AArch32 tasks
  arm64: Consolidate hotplug notifier for instruction emulation
  arm64: Track system support for mixed endian EL0
  arm64: implement generic IOMMU configuration
  arm64: Combine coherent and non-coherent swiotlb dma_ops
  ...

73 files changed, 1533 insertions, 919 deletions

diff --git a/Documentation/arm64/legacy_instructions.txt b/Documentation/arm64/legacy_instructions.txt
index a3b3da2ec6ed..01bf3d9fac85 100644
--- a/Documentation/arm64/legacy_instructions.txt
+++ b/Documentation/arm64/legacy_instructions.txt
@@ -32,6 +32,9 @@ The default mode depends on the status of the instruction in the
 architecture. Deprecated instructions should default to emulation
 while obsolete instructions must be undefined by default.
 
+Note: Instruction emulation may not be possible in all cases. See
+individual instruction notes for further information.
+
 Supported legacy instructions
 -----------------------------
 * SWP{B}
@@ -43,3 +46,12 @@ Default: Undef (0)
 Node: /proc/sys/abi/cp15_barrier
 Status: Deprecated
 Default: Emulate (1)
+
+* SETEND
+Node: /proc/sys/abi/setend
+Status: Deprecated
+Default: Emulate (1)*
+Note: All the cpus on the system must have mixed endian support at EL0
+for this feature to be enabled. If a new CPU - which doesn't support mixed
+endian - is hotplugged in after this feature has been enabled, there could
+be unexpected results in the application.
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index b1f9a20a3677..d3f7e4941231 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -540,6 +540,21 @@ config CP15_BARRIER_EMULATION
 
 	  If unsure, say Y
 
+config SETEND_EMULATION
+	bool "Emulate SETEND instruction"
+	help
+	  The SETEND instruction alters the data-endianness of the
+	  AArch32 EL0, and is deprecated in ARMv8.
+
+	  Say Y here to enable software emulation of the instruction
+	  for AArch32 userspace code.
+
+	  Note: All the cpus on the system must have mixed endian support at EL0
+	  for this feature to be enabled. If a new CPU - which doesn't support mixed
+	  endian - is hotplugged in after this feature has been enabled, there could
+	  be unexpected results in the applications.
+
+	  If unsure, say Y
 endif
 
 endmenu
@@ -627,9 +642,6 @@ source "kernel/power/Kconfig"
 config ARCH_SUSPEND_POSSIBLE
 	def_bool y
 
-config ARM64_CPU_SUSPEND
-	def_bool PM_SLEEP
-
 endmenu
 
 menu "CPU Power Management"
diff --git a/arch/arm64/Kconfig.debug b/arch/arm64/Kconfig.debug
index 5fdd6dce8061..4a8741073c90 100644
--- a/arch/arm64/Kconfig.debug
+++ b/arch/arm64/Kconfig.debug
@@ -66,4 +66,27 @@ config DEBUG_SET_MODULE_RONX
           against certain classes of kernel exploits.
           If in doubt, say "N".
 
+config DEBUG_RODATA
+	bool "Make kernel text and rodata read-only"
+	help
+	  If this is set, kernel text and rodata will be made read-only. This
+	  is to help catch accidental or malicious attempts to change the
+	  kernel's executable code. Additionally splits rodata from kernel
+	  text so it can be made explicitly non-executable.
+
+          If in doubt, say Y
+
+config DEBUG_ALIGN_RODATA
+	depends on DEBUG_RODATA && !ARM64_64K_PAGES
+	bool "Align linker sections up to SECTION_SIZE"
+	help
+	  If this option is enabled, sections that may potentially be marked as
+	  read only or non-executable will be aligned up to the section size of
+	  the kernel. This prevents sections from being split into pages and
+	  avoids a potential TLB penalty. The downside is an increase in
+	  alignment and potentially wasted space. Turn on this option if
+	  performance is more important than memory pressure.
+
+	  If in doubt, say N
+
 endmenu
diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile
index 066688863920..69ceedc982a5 100644
--- a/arch/arm64/Makefile
+++ b/arch/arm64/Makefile
@@ -15,8 +15,6 @@ CPPFLAGS_vmlinux.lds = -DTEXT_OFFSET=$(TEXT_OFFSET)
 OBJCOPYFLAGS	:=-O binary -R .note -R .note.gnu.build-id -R .comment -S
 GZFLAGS		:=-9
 
-LIBGCC 		:= $(shell $(CC) $(KBUILD_CFLAGS) -print-libgcc-file-name)
-
 KBUILD_DEFCONFIG := defconfig
 
 KBUILD_CFLAGS	+= -mgeneral-regs-only
@@ -50,7 +48,6 @@ core-$(CONFIG_KVM) += arch/arm64/kvm/
 core-$(CONFIG_XEN) += arch/arm64/xen/
 core-$(CONFIG_CRYPTO) += arch/arm64/crypto/
 libs-y		:= arch/arm64/lib/ $(libs-y)
-libs-y		+= $(LIBGCC)
 libs-$(CONFIG_EFI_STUB) += drivers/firmware/efi/libstub/
 
 # Default target when executing plain make
diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig
index 5376d908eabe..66b6cacc3251 100644
--- a/arch/arm64/configs/defconfig
+++ b/arch/arm64/configs/defconfig
@@ -45,6 +45,8 @@ CONFIG_CMA=y
 CONFIG_CMDLINE="console=ttyAMA0"
 # CONFIG_CORE_DUMP_DEFAULT_ELF_HEADERS is not set
 CONFIG_COMPAT=y
+CONFIG_CPU_IDLE=y
+CONFIG_ARM64_CPUIDLE=y
 CONFIG_NET=y
 CONFIG_PACKET=y
 CONFIG_UNIX=y
diff --git a/arch/arm64/include/asm/cacheflush.h b/arch/arm64/include/asm/cacheflush.h
index 7ae31a2cc6c0..67d309cc3b6b 100644
--- a/arch/arm64/include/asm/cacheflush.h
+++ b/arch/arm64/include/asm/cacheflush.h
@@ -152,4 +152,9 @@ int set_memory_ro(unsigned long addr, int numpages);
 int set_memory_rw(unsigned long addr, int numpages);
 int set_memory_x(unsigned long addr, int numpages);
 int set_memory_nx(unsigned long addr, int numpages);
+
+#ifdef CONFIG_DEBUG_RODATA
+void mark_rodata_ro(void);
+#endif
+
 #endif
diff --git a/arch/arm64/include/asm/cachetype.h b/arch/arm64/include/asm/cachetype.h
index 4c631a0a3609..da2fc9e3cedd 100644
--- a/arch/arm64/include/asm/cachetype.h
+++ b/arch/arm64/include/asm/cachetype.h
@@ -39,24 +39,41 @@
 
 extern unsigned long __icache_flags;
 
+/*
+ * NumSets, bits[27:13] - (Number of sets in cache) - 1
+ * Associativity, bits[12:3] - (Associativity of cache) - 1
+ * LineSize, bits[2:0] - (Log2(Number of words in cache line)) - 2
+ */
+#define CCSIDR_EL1_WRITE_THROUGH	BIT(31)
+#define CCSIDR_EL1_WRITE_BACK		BIT(30)
+#define CCSIDR_EL1_READ_ALLOCATE	BIT(29)
+#define CCSIDR_EL1_WRITE_ALLOCATE	BIT(28)
 #define CCSIDR_EL1_LINESIZE_MASK	0x7
 #define CCSIDR_EL1_LINESIZE(x)		((x) & CCSIDR_EL1_LINESIZE_MASK)
-
+#define CCSIDR_EL1_ASSOCIATIVITY_SHIFT	3
+#define CCSIDR_EL1_ASSOCIATIVITY_MASK	0x3ff
+#define CCSIDR_EL1_ASSOCIATIVITY(x)	\
+	(((x) >> CCSIDR_EL1_ASSOCIATIVITY_SHIFT) & CCSIDR_EL1_ASSOCIATIVITY_MASK)
 #define CCSIDR_EL1_NUMSETS_SHIFT	13
-#define CCSIDR_EL1_NUMSETS_MASK		(0x7fff << CCSIDR_EL1_NUMSETS_SHIFT)
+#define CCSIDR_EL1_NUMSETS_MASK		0x7fff
 #define CCSIDR_EL1_NUMSETS(x) \
-	(((x) & CCSIDR_EL1_NUMSETS_MASK) >> CCSIDR_EL1_NUMSETS_SHIFT)
+	(((x) >> CCSIDR_EL1_NUMSETS_SHIFT) & CCSIDR_EL1_NUMSETS_MASK)
+
+#define CACHE_LINESIZE(x)	(16 << CCSIDR_EL1_LINESIZE(x))
+#define CACHE_NUMSETS(x)	(CCSIDR_EL1_NUMSETS(x) + 1)
+#define CACHE_ASSOCIATIVITY(x)	(CCSIDR_EL1_ASSOCIATIVITY(x) + 1)
 
-extern u64 __attribute_const__ icache_get_ccsidr(void);
+extern u64 __attribute_const__ cache_get_ccsidr(u64 csselr);
 
+/* Helpers for Level 1 Instruction cache csselr = 1L */
 static inline int icache_get_linesize(void)
 {
-	return 16 << CCSIDR_EL1_LINESIZE(icache_get_ccsidr());
+	return CACHE_LINESIZE(cache_get_ccsidr(1L));
 }
 
 static inline int icache_get_numsets(void)
 {
-	return 1 + CCSIDR_EL1_NUMSETS(icache_get_ccsidr());
+	return CACHE_NUMSETS(cache_get_ccsidr(1L));
 }
 
 /*
diff --git a/arch/arm64/include/asm/compat.h b/arch/arm64/include/asm/compat.h
index 3fb053fa6e98..7fbed6919b54 100644
--- a/arch/arm64/include/asm/compat.h
+++ b/arch/arm64/include/asm/compat.h
@@ -161,7 +161,6 @@ typedef struct compat_siginfo {
 	int si_code;
 
 	union {
-		/* The padding is the same size as AArch64. */
 		int _pad[128/sizeof(int) - 3];
 
 		/* kill() */
diff --git a/arch/arm64/include/asm/cpu_ops.h b/arch/arm64/include/asm/cpu_ops.h
index 6f8e2ef9094a..da301ee7395c 100644
--- a/arch/arm64/include/asm/cpu_ops.h
+++ b/arch/arm64/include/asm/cpu_ops.h
@@ -28,8 +28,6 @@ struct device_node;
  *		enable-method property.
  * @cpu_init:	Reads any data necessary for a specific enable-method from the
  *		devicetree, for a given cpu node and proposed logical id.
- * @cpu_init_idle: Reads any data necessary to initialize CPU idle states from
- *		devicetree, for a given cpu node and proposed logical id.
  * @cpu_prepare: Early one-time preparation step for a cpu. If there is a
  *		mechanism for doing so, tests whether it is possible to boot
  *		the given CPU.
@@ -42,6 +40,8 @@ struct device_node;
  * @cpu_die:	Makes a cpu leave the kernel. Must not fail. Called from the
  *		cpu being killed.
  * @cpu_kill:  Ensures a cpu has left the kernel. Called from another cpu.
+ * @cpu_init_idle: Reads any data necessary to initialize CPU idle states from
+ *		devicetree, for a given cpu node and proposed logical id.
  * @cpu_suspend: Suspends a cpu and saves the required context. May fail owing
  *               to wrong parameters or error conditions. Called from the
  *               CPU being suspended. Must be called with IRQs disabled.
@@ -49,7 +49,6 @@ struct device_node;
 struct cpu_operations {
 	const char	*name;
 	int		(*cpu_init)(struct device_node *, unsigned int);
-	int		(*cpu_init_idle)(struct device_node *, unsigned int);
 	int		(*cpu_prepare)(unsigned int);
 	int		(*cpu_boot)(unsigned int);
 	void		(*cpu_postboot)(void);
@@ -58,7 +57,8 @@ struct cpu_operations {
 	void		(*cpu_die)(unsigned int cpu);
 	int		(*cpu_kill)(unsigned int cpu);
 #endif
-#ifdef CONFIG_ARM64_CPU_SUSPEND
+#ifdef CONFIG_CPU_IDLE
+	int		(*cpu_init_idle)(struct device_node *, unsigned int);
 	int		(*cpu_suspend)(unsigned long);
 #endif
 };
diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h
index 07547ccc1f2b..b6c16d5f622f 100644
--- a/arch/arm64/include/asm/cpufeature.h
+++ b/arch/arm64/include/asm/cpufeature.h
@@ -52,6 +52,8 @@ static inline void cpus_set_cap(unsigned int num)
 }
 
 void check_local_cpu_errata(void);
+bool cpu_supports_mixed_endian_el0(void);
+bool system_supports_mixed_endian_el0(void);
 
 #endif /* __ASSEMBLY__ */
 
diff --git a/arch/arm64/include/asm/cpuidle.h b/arch/arm64/include/asm/cpuidle.h
index b52a9932e2b1..0710654631e7 100644
--- a/arch/arm64/include/asm/cpuidle.h
+++ b/arch/arm64/include/asm/cpuidle.h
@@ -3,11 +3,17 @@
 
 #ifdef CONFIG_CPU_IDLE
 extern int cpu_init_idle(unsigned int cpu);
+extern int cpu_suspend(unsigned long arg);
 #else
 static inline int cpu_init_idle(unsigned int cpu)
 {
 	return -EOPNOTSUPP;
 }
+
+static inline int cpu_suspend(unsigned long arg)
+{
+	return -EOPNOTSUPP;
+}
 #endif
 
 #endif
diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h
index 8adb986a3086..a84ec605bed8 100644
--- a/arch/arm64/include/asm/cputype.h
+++ b/arch/arm64/include/asm/cputype.h
@@ -72,6 +72,18 @@
 
 #define APM_CPU_PART_POTENZA	0x000
 
+#define ID_AA64MMFR0_BIGENDEL0_SHIFT	16
+#define ID_AA64MMFR0_BIGENDEL0_MASK	(0xf << ID_AA64MMFR0_BIGENDEL0_SHIFT)
+#define ID_AA64MMFR0_BIGENDEL0(mmfr0)	\
+	(((mmfr0) & ID_AA64MMFR0_BIGENDEL0_MASK) >> ID_AA64MMFR0_BIGENDEL0_SHIFT)
+#define ID_AA64MMFR0_BIGEND_SHIFT	8
+#define ID_AA64MMFR0_BIGEND_MASK	(0xf << ID_AA64MMFR0_BIGEND_SHIFT)
+#define ID_AA64MMFR0_BIGEND(mmfr0)	\
+	(((mmfr0) & ID_AA64MMFR0_BIGEND_MASK) >> ID_AA64MMFR0_BIGEND_SHIFT)
+
+#define SCTLR_EL1_CP15BEN	(0x1 << 5)
+#define SCTLR_EL1_SED		(0x1 << 8)
+
 #ifndef __ASSEMBLY__
 
 /*
@@ -104,6 +116,11 @@ static inline u32 __attribute_const__ read_cpuid_cachetype(void)
 	return read_cpuid(CTR_EL0);
 }
 
+static inline bool id_aa64mmfr0_mixed_endian_el0(u64 mmfr0)
+{
+	return (ID_AA64MMFR0_BIGEND(mmfr0) == 0x1) ||
+		(ID_AA64MMFR0_BIGENDEL0(mmfr0) == 0x1);
+}
 #endif /* __ASSEMBLY__ */
 
 #endif
diff --git a/arch/arm64/include/asm/dma-mapping.h b/arch/arm64/include/asm/dma-mapping.h
index 9ce3e680ae1c..6932bb57dba0 100644
--- a/arch/arm64/include/asm/dma-mapping.h
+++ b/arch/arm64/include/asm/dma-mapping.h
@@ -28,8 +28,6 @@
 
 #define DMA_ERROR_CODE	(~(dma_addr_t)0)
 extern struct dma_map_ops *dma_ops;
-extern struct dma_map_ops coherent_swiotlb_dma_ops;
-extern struct dma_map_ops noncoherent_swiotlb_dma_ops;
 
 static inline struct dma_map_ops *__generic_dma_ops(struct device *dev)
 {
@@ -47,23 +45,18 @@ static inline struct dma_map_ops *get_dma_ops(struct device *dev)
 		return __generic_dma_ops(dev);
 }
 
-static inline void set_dma_ops(struct device *dev, struct dma_map_ops *ops)
-{
-	dev->archdata.dma_ops = ops;
-}
-
 static inline void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
 				      struct iommu_ops *iommu, bool coherent)
 {
 	dev->archdata.dma_coherent = coherent;
-	if (coherent)
-		set_dma_ops(dev, &coherent_swiotlb_dma_ops);
 }
 #define arch_setup_dma_ops	arch_setup_dma_ops
 
 /* do not use this function in a driver */
 static inline bool is_device_dma_coherent(struct device *dev)
 {
+	if (!dev)
+		return false;
 	return dev->archdata.dma_coherent;
 }
 
diff --git a/arch/arm64/include/asm/efi.h b/arch/arm64/include/asm/efi.h
index a34fd3b12e2b..ef572206f1c3 100644
--- a/arch/arm64/include/asm/efi.h
+++ b/arch/arm64/include/asm/efi.h
@@ -6,29 +6,33 @@
 
 #ifdef CONFIG_EFI
 extern void efi_init(void);
-extern void efi_idmap_init(void);
 #else
 #define efi_init()
-#define efi_idmap_init()
 #endif
 
 #define efi_call_virt(f, ...)						\
 ({									\
-	efi_##f##_t *__f = efi.systab->runtime->f;			\
+	efi_##f##_t *__f;						\
 	efi_status_t __s;						\
 									\
 	kernel_neon_begin();						\
+	efi_virtmap_load();						\
+	__f = efi.systab->runtime->f;					\
 	__s = __f(__VA_ARGS__);						\
+	efi_virtmap_unload();						\
 	kernel_neon_end();						\
 	__s;								\
 })
 
 #define __efi_call_virt(f, ...)						\
 ({									\
-	efi_##f##_t *__f = efi.systab->runtime->f;			\
+	efi_##f##_t *__f;						\
 									\
 	kernel_neon_begin();						\
+	efi_virtmap_load();						\
+	__f = efi.systab->runtime->f;					\
 	__f(__VA_ARGS__);						\
+	efi_virtmap_unload();						\
 	kernel_neon_end();						\
 })
 
@@ -44,4 +48,22 @@ extern void efi_idmap_init(void);
 
 #define efi_call_early(f, ...) sys_table_arg->boottime->f(__VA_ARGS__)
 
+#define EFI_ALLOC_ALIGN		SZ_64K
+
+/*
+ * On ARM systems, virtually remapped UEFI runtime services are set up in two
+ * distinct stages:
+ * - The stub retrieves the final version of the memory map from UEFI, populates
+ *   the virt_addr fields and calls the SetVirtualAddressMap() [SVAM] runtime
+ *   service to communicate the new mapping to the firmware (Note that the new
+ *   mapping is not live at this time)
+ * - During an early initcall(), the EFI system table is permanently remapped
+ *   and the virtual remapping of the UEFI Runtime Services regions is loaded
+ *   into a private set of page tables. If this all succeeds, the Runtime
+ *   Services are enabled and the EFI_RUNTIME_SERVICES bit set.
+ */
+
+void efi_virtmap_load(void);
+void efi_virtmap_unload(void);
+
 #endif /* _ASM_EFI_H */
diff --git a/arch/arm64/include/asm/esr.h b/arch/arm64/include/asm/esr.h
index 72674f4c3871..62167090937d 100644
--- a/arch/arm64/include/asm/esr.h
+++ b/arch/arm64/include/asm/esr.h
@@ -18,40 +18,89 @@
 #ifndef __ASM_ESR_H
 #define __ASM_ESR_H
 
-#define ESR_EL1_WRITE		(1 << 6)
-#define ESR_EL1_CM		(1 << 8)
-#define ESR_EL1_IL		(1 << 25)
+#define ESR_ELx_EC_UNKNOWN	(0x00)
+#define ESR_ELx_EC_WFx		(0x01)
+/* Unallocated EC: 0x02 */
+#define ESR_ELx_EC_CP15_32	(0x03)
+#define ESR_ELx_EC_CP15_64	(0x04)
+#define ESR_ELx_EC_CP14_MR	(0x05)
+#define ESR_ELx_EC_CP14_LS	(0x06)
+#define ESR_ELx_EC_FP_ASIMD	(0x07)
+#define E