Merge tag 'for-linus' of git://git.armlinux.org.uk/~rmk/linux-arm

Pull ARM updates from Russell King:
 "Updates for IRQ stacks and virtually mapped stack support, and ftrace:

   - Support for IRQ and vmap'ed stacks

     This covers all the work related to implementing IRQ stacks and
     vmap'ed stacks for all 32-bit ARM systems that are currently
     supported by the Linux kernel, including RiscPC and Footbridge. It
     has been submitted for review in four different waves:

      - IRQ stacks support for v7 SMP systems [0]

      - vmap'ed stacks support for v7 SMP systems[1]

      - extending support for both IRQ stacks and vmap'ed stacks for all
        remaining configurations, including v6/v7 SMP multiplatform
        kernels and uniprocessor configurations including v7-M [2]

      - fixes and updates in [3]

   - ftrace fixes and cleanups

     Make all flavors of ftrace available on all builds, regardless of
     ISA choice, unwinder choice or compiler [4]:

      - use ADD not POP where possible

      - fix a couple of Thumb2 related issues

      - enable HAVE_FUNCTION_GRAPH_FP_TEST for robustness

      - enable the graph tracer with the EABI unwinder

      - avoid clobbering frame pointer registers to make Clang happy

   - Fixes for the above"

[0] https://lore.kernel.org/linux-arm-kernel/20211115084732.3704393-1-ardb@kernel.org/
[1] https://lore.kernel.org/linux-arm-kernel/20211122092816.2865873-1-ardb@kernel.org/
[2] https://lore.kernel.org/linux-arm-kernel/20211206164659.1495084-1-ardb@kernel.org/
[3] https://lore.kernel.org/linux-arm-kernel/20220124174744.1054712-1-ardb@kernel.org/
[4] https://lore.kernel.org/linux-arm-kernel/20220203082204.1176734-1-ardb@kernel.org/

* tag 'for-linus' of git://git.armlinux.org.uk/~rmk/linux-arm: (62 commits)
  ARM: fix building NOMMU ARMv4/v5 kernels
  ARM: unwind: only permit stack switch when unwinding call_with_stack()
  ARM: Revert "unwind: dump exception stack from calling frame"
  ARM: entry: fix unwinder problems caused by IRQ stacks
  ARM: unwind: set frame.pc correctly for current-thread unwinding
  ARM: 9184/1: return_address: disable again for CONFIG_ARM_UNWIND=y
  ARM: 9183/1: unwind: avoid spurious warnings on bogus code addresses
  Revert "ARM: 9144/1: forbid ftrace with clang and thumb2_kernel"
  ARM: mach-bcm: disable ftrace in SMC invocation routines
  ARM: cacheflush: avoid clobbering the frame pointer
  ARM: kprobes: treat R7 as the frame pointer register in Thumb2 builds
  ARM: ftrace: enable the graph tracer with the EABI unwinder
  ARM: unwind: track location of LR value in stack frame
  ARM: ftrace: enable HAVE_FUNCTION_GRAPH_FP_TEST
  ARM: ftrace: avoid unnecessary literal loads
  ARM: ftrace: avoid redundant loads or clobbering IP
  ARM: ftrace: use trampolines to keep .init.text in branching range
  ARM: ftrace: use ADD not POP to counter PUSH at entry
  ARM: ftrace: ensure that ADR takes the Thumb bit into account
  ARM: make get_current() and __my_cpu_offset() __always_inline
  ...

arch/arm/Kconfig

@@ -60,6 +60,7 @@ config ARM
 	select GENERIC_CPU_AUTOPROBE
 	select GENERIC_EARLY_IOREMAP
 	select GENERIC_IDLE_POLL_SETUP
+	select GENERIC_IRQ_MULTI_HANDLER
 	select GENERIC_IRQ_PROBE
 	select GENERIC_IRQ_SHOW
 	select GENERIC_IRQ_SHOW_LEVEL
@@ -94,8 +95,8 @@ config ARM
 	select HAVE_EXIT_THREAD
 	select HAVE_FAST_GUP if ARM_LPAE
 	select HAVE_FTRACE_MCOUNT_RECORD if !XIP_KERNEL
-	select HAVE_FUNCTION_GRAPH_TRACER if !THUMB2_KERNEL && !CC_IS_CLANG
-	select HAVE_FUNCTION_TRACER if !XIP_KERNEL && !(THUMB2_KERNEL && CC_IS_CLANG)
+	select HAVE_FUNCTION_GRAPH_TRACER
+	select HAVE_FUNCTION_TRACER if !XIP_KERNEL
 	select HAVE_GCC_PLUGINS
 	select HAVE_HW_BREAKPOINT if PERF_EVENTS && (CPU_V6 || CPU_V6K || CPU_V7)
 	select HAVE_IRQ_TIME_ACCOUNTING
@@ -129,7 +130,8 @@ config ARM
 	select PERF_USE_VMALLOC
 	select RTC_LIB
 	select SYS_SUPPORTS_APM_EMULATION
-	select THREAD_INFO_IN_TASK if CURRENT_POINTER_IN_TPIDRURO
+	select THREAD_INFO_IN_TASK
+	select HAVE_ARCH_VMAP_STACK if MMU && ARM_HAS_GROUP_RELOCS
 	select TRACE_IRQFLAGS_SUPPORT if !CPU_V7M
 	# Above selects are sorted alphabetically; please add new ones
 	# according to that.  Thanks.
@@ -141,6 +143,17 @@ config ARM
 	  Europe.  There is an ARM Linux project with a web page at
 	  <http://www.arm.linux.org.uk/>.
 
+config ARM_HAS_GROUP_RELOCS
+	def_bool y
+	depends on !LD_IS_LLD || LLD_VERSION >= 140000
+	depends on !COMPILE_TEST
+	help
+	  Whether or not to use R_ARM_ALU_PC_Gn or R_ARM_LDR_PC_Gn group
+	  relocations, which have been around for a long time, but were not
+	  supported in LLD until version 14. The combined range is -/+ 256 MiB,
+	  which is usually sufficient, but not for allyesconfig, so we disable
+	  this feature when doing compile testing.
+
 config ARM_HAS_SG_CHAIN
 	bool
 
@@ -229,9 +242,6 @@ config GENERIC_ISA_DMA
 config FIQ
 	bool
 
-config NEED_RET_TO_USER
-	bool
-
 config ARCH_MTD_XIP
 	bool
 
@@ -325,7 +335,6 @@ config ARCH_MULTIPLATFORM
 	select AUTO_ZRELADDR
 	select TIMER_OF
 	select COMMON_CLK
-	select GENERIC_IRQ_MULTI_HANDLER
 	select HAVE_PCI
 	select PCI_DOMAINS_GENERIC if PCI
 	select SPARSE_IRQ
@@ -349,7 +358,6 @@ config ARCH_EP93XX
 	select ARM_AMBA
 	imply ARM_PATCH_PHYS_VIRT
 	select ARM_VIC
-	select GENERIC_IRQ_MULTI_HANDLER
 	select AUTO_ZRELADDR
 	select CLKSRC_MMIO
 	select CPU_ARM920T
@@ -374,7 +382,6 @@ config ARCH_IOP32X
 	select CPU_XSCALE
 	select GPIO_IOP
 	select GPIOLIB
-	select NEED_RET_TO_USER
 	select FORCE_PCI
 	select PLAT_IOP
 	help
@@ -388,7 +395,6 @@ config ARCH_IXP4XX
 	select ARCH_SUPPORTS_BIG_ENDIAN
 	select CPU_XSCALE
 	select DMABOUNCE if PCI
-	select GENERIC_IRQ_MULTI_HANDLER
 	select GPIO_IXP4XX
 	select GPIOLIB
 	select HAVE_PCI
@@ -404,7 +410,6 @@ config ARCH_IXP4XX
 config ARCH_DOVE
 	bool "Marvell Dove"
 	select CPU_PJ4
-	select GENERIC_IRQ_MULTI_HANDLER
 	select GPIOLIB
 	select HAVE_PCI
 	select MVEBU_MBUS
@@ -427,7 +432,6 @@ config ARCH_PXA
 	select CLKSRC_MMIO
 	select TIMER_OF
 	select CPU_XSCALE if !CPU_XSC3
-	select GENERIC_IRQ_MULTI_HANDLER
 	select GPIO_PXA
 	select GPIOLIB
 	select IRQ_DOMAIN
@@ -466,7 +470,6 @@ config ARCH_SA1100
 	select COMMON_CLK
 	select CPU_FREQ
 	select CPU_SA1100
-	select GENERIC_IRQ_MULTI_HANDLER
 	select GPIOLIB
 	select IRQ_DOMAIN
 	select ISA
@@ -481,7 +484,6 @@ config ARCH_S3C24XX
 	select CLKSRC_SAMSUNG_PWM
 	select GPIO_SAMSUNG
 	select GPIOLIB
-	select GENERIC_IRQ_MULTI_HANDLER
 	select NEED_MACH_IO_H
 	select S3C2410_WATCHDOG
 	select SAMSUNG_ATAGS
@@ -499,7 +501,6 @@ config ARCH_OMAP1
 	select ARCH_OMAP
 	select CLKSRC_MMIO
 	select GENERIC_IRQ_CHIP
-	select GENERIC_IRQ_MULTI_HANDLER
 	select GPIOLIB
 	select HAVE_LEGACY_CLK
 	select IRQ_DOMAIN
@@ -1166,7 +1167,12 @@ config SMP_ON_UP
 
 config CURRENT_POINTER_IN_TPIDRURO
 	def_bool y
-	depends on SMP && CPU_32v6K && !CPU_V6
+	depends on CPU_32v6K && !CPU_V6
+
+config IRQSTACKS
+	def_bool y
+	select HAVE_IRQ_EXIT_ON_IRQ_STACK
+	select HAVE_SOFTIRQ_ON_OWN_STACK
 
 config ARM_CPU_TOPOLOGY
 	bool "Support cpu topology definition"
@@ -1607,10 +1613,14 @@ config XEN
 	help
 	  Say Y if you want to run Linux in a Virtual Machine on Xen on ARM.
 
+config CC_HAVE_STACKPROTECTOR_TLS
+	def_bool $(cc-option,-mtp=cp15 -mstack-protector-guard=tls -mstack-protector-guard-offset=0)
+
 config STACKPROTECTOR_PER_TASK
 	bool "Use a unique stack canary value for each task"
-	depends on GCC_PLUGINS && STACKPROTECTOR && THREAD_INFO_IN_TASK && !XIP_DEFLATED_DATA
-	select GCC_PLUGIN_ARM_SSP_PER_TASK
+	depends on STACKPROTECTOR && CURRENT_POINTER_IN_TPIDRURO && !XIP_DEFLATED_DATA
+	depends on GCC_PLUGINS || CC_HAVE_STACKPROTECTOR_TLS
+	select GCC_PLUGIN_ARM_SSP_PER_TASK if !CC_HAVE_STACKPROTECTOR_TLS
 	default y
 	help
 	  Due to the fact that GCC uses an ordinary symbol reference from

arch/arm/Kconfig.debug

@@ -65,7 +65,7 @@ config UNWINDER_FRAME_POINTER
 
 config UNWINDER_ARM
 	bool "ARM EABI stack unwinder"
-	depends on AEABI && !FUNCTION_GRAPH_TRACER
+	depends on AEABI
 	select ARM_UNWIND
 	help
 	  This option enables stack unwinding support in the kernel

arch/arm/Makefile

@@ -275,6 +275,14 @@ endif
 
 ifeq ($(CONFIG_STACKPROTECTOR_PER_TASK),y)
 prepare: stack_protector_prepare
+ifeq ($(CONFIG_CC_HAVE_STACKPROTECTOR_TLS),y)
+stack_protector_prepare: prepare0
+	$(eval KBUILD_CFLAGS += \
+		-mstack-protector-guard=tls \
+		-mstack-protector-guard-offset=$(shell	\
+			awk '{if ($$2 == "TSK_STACK_CANARY") print $$3;}'\
+				include/generated/asm-offsets.h))
+else
 stack_protector_prepare: prepare0
 	$(eval SSP_PLUGIN_CFLAGS := \
 		-fplugin-arg-arm_ssp_per_task_plugin-offset=$(shell	\
@@ -283,6 +291,7 @@ stack_protector_prepare: prepare0
 	$(eval KBUILD_CFLAGS += $(SSP_PLUGIN_CFLAGS))
 	$(eval GCC_PLUGINS_CFLAGS += $(SSP_PLUGIN_CFLAGS))
 endif
+endif
 
 all:	$(notdir $(KBUILD_IMAGE))
 

arch/arm/boot/compressed/Makefile

@@ -92,17 +92,13 @@ ifeq ($(CONFIG_USE_OF),y)
 OBJS	+= $(libfdt_objs) fdt_check_mem_start.o
 endif
 
-# -fstack-protector-strong triggers protection checks in this code,
-# but it is being used too early to link to meaningful stack_chk logic.
-$(foreach o, $(libfdt_objs) atags_to_fdt.o fdt_check_mem_start.o, \
-	$(eval CFLAGS_$(o) := -I $(srctree)/scripts/dtc/libfdt -fno-stack-protector))
-
 targets       := vmlinux vmlinux.lds piggy_data piggy.o \
 		 head.o $(OBJS)
 
 KBUILD_CFLAGS += -DDISABLE_BRANCH_PROFILING
 
 ccflags-y := -fpic $(call cc-option,-mno-single-pic-base,) -fno-builtin \
+	     -I$(srctree)/scripts/dtc/libfdt -fno-stack-protector \
 	     -I$(obj) $(DISABLE_ARM_SSP_PER_TASK_PLUGIN)
 ccflags-remove-$(CONFIG_FUNCTION_TRACER) += -pg
 asflags-y := -DZIMAGE

arch/arm/boot/compressed/misc.c

@@ -128,13 +128,6 @@ asmlinkage void __div0(void)
 	error("Attempting division by 0!");
 }
 
-const unsigned long __stack_chk_guard = 0x000a0dff;
-
-void __stack_chk_fail(void)
-{
-	error("stack-protector: Kernel stack is corrupted\n");
-}
-
 extern int do_decompress(u8 *input, int len, u8 *output, void (*error)(char *x));
 
 

arch/arm/include/asm/assembler.h

@@ -86,6 +86,10 @@
 
 #define IMM12_MASK 0xfff
 
+/* the frame pointer used for stack unwinding */
+ARM(	fpreg	.req	r11	)
+THUMB(	fpreg	.req	r7	)
+
 /*
  * Enable and disable interrupts
  */
@@ -209,43 +213,12 @@
 	.endm
 	.endr
 
-	.macro	get_current, rd
-#ifdef CONFIG_CURRENT_POINTER_IN_TPIDRURO
-	mrc	p15, 0, \rd, c13, c0, 3		@ get TPIDRURO register
-#else
-	get_thread_info \rd
-	ldr	\rd, [\rd, #TI_TASK]
-#endif
-	.endm
-
-	.macro	set_current, rn
-#ifdef CONFIG_CURRENT_POINTER_IN_TPIDRURO
-	mcr	p15, 0, \rn, c13, c0, 3		@ set TPIDRURO register
-#endif
-	.endm
-
-	.macro	reload_current, t1:req, t2:req
-#ifdef CONFIG_CURRENT_POINTER_IN_TPIDRURO
-	adr_l	\t1, __entry_task		@ get __entry_task base address
-	mrc	p15, 0, \t2, c13, c0, 4		@ get per-CPU offset
-	ldr	\t1, [\t1, \t2]			@ load variable
-	mcr	p15, 0, \t1, c13, c0, 3		@ store in TPIDRURO
-#endif
-	.endm
-
 /*
  * Get current thread_info.
  */
 	.macro	get_thread_info, rd
-#ifdef CONFIG_THREAD_INFO_IN_TASK
 	/* thread_info is the first member of struct task_struct */
 	get_current \rd
-#else
- ARM(	mov	\rd, sp, lsr #THREAD_SIZE_ORDER + PAGE_SHIFT	)
- THUMB(	mov	\rd, sp			)
- THUMB(	lsr	\rd, \rd, #THREAD_SIZE_ORDER + PAGE_SHIFT	)
-	mov	\rd, \rd, lsl #THREAD_SIZE_ORDER + PAGE_SHIFT
-#endif
 	.endm
 
 /*
@@ -320,6 +293,80 @@
 #define ALT_UP_B(label) b label
 #endif
 
+	/*
+	 * this_cpu_offset - load the per-CPU offset of this CPU into
+	 * 		     register 'rd'
+	 */
+	.macro		this_cpu_offset, rd:req
+#ifdef CONFIG_SMP
+ALT_SMP(mrc		p15, 0, \rd, c13, c0, 4)
+#ifdef CONFIG_CPU_V6
+ALT_UP_B(.L1_\@)
+.L0_\@:
+	.subsection	1
+.L1_\@: ldr_va		\rd, __per_cpu_offset
+	b		.L0_\@
+	.previous
+#endif
+#else
+	mov		\rd, #0
+#endif
+	.endm
+
+	/*
+	 * set_current - store the task pointer of this CPU's current task
+	 */
+	.macro		set_current, rn:req, tmp:req
+#if defined(CONFIG_CURRENT_POINTER_IN_TPIDRURO) || defined(CONFIG_SMP)
+9998:	mcr		p15, 0, \rn, c13, c0, 3		@ set TPIDRURO register
+#ifdef CONFIG_CPU_V6
+ALT_UP_B(.L0_\@)
+	.subsection	1
+.L0_\@: str_va		\rn, __current, \tmp
+	b		.L1_\@
+	.previous
+.L1_\@:
+#endif
+#else
+	str_va		\rn, __current, \tmp
+#endif
+	.endm
+
+	/*
+	 * get_current - load the task pointer of this CPU's current task
+	 */
+	.macro		get_current, rd:req
+#if defined(CONFIG_CURRENT_POINTER_IN_TPIDRURO) || defined(CONFIG_SMP)
+9998:	mrc		p15, 0, \rd, c13, c0, 3		@ get TPIDRURO register
+#ifdef CONFIG_CPU_V6
+ALT_UP_B(.L0_\@)
+	.subsection	1
+.L0_\@: ldr_va		\rd, __current
+	b		.L1_\@
+	.previous
+.L1_\@:
+#endif
+#else
+	ldr_va		\rd, __current
+#endif
+	.endm
+
+	/*
+	 * reload_current - reload the task pointer of this CPU's current task
+	 *		    into the TLS register
+	 */
+	.macro		reload_current, t1:req, t2:req
+#if defined(CONFIG_CURRENT_POINTER_IN_TPIDRURO) || defined(CONFIG_SMP)
+#ifdef CONFIG_CPU_V6
+ALT_SMP(nop)
+ALT_UP_B(.L0_\@)
+#endif
+	ldr_this_cpu	\t1, __entry_task, \t1, \t2
+	mcr		p15, 0, \t1, c13, c0, 3		@ store in TPIDRURO
+.L0_\@:
+#endif
+	.endm
+
 /*
  * Instruction barrier
  */
@@ -576,12 +623,12 @@ THUMB(	orr	\reg , \reg , #PSR_T_BIT	)
 	/*
 	 * mov_l - move a constant value or [relocated] address into a register
 	 */
-	.macro		mov_l, dst:req, imm:req
+	.macro		mov_l, dst:req, imm:req, cond
 	.if		__LINUX_ARM_ARCH__ < 7
-	ldr		\dst, =\imm
+	ldr\cond	\dst, =\imm
 	.else
-	movw		\dst, #:lower16:\imm
-	movt		\dst, #:upper16:\imm
+	movw\cond	\dst, #:lower16:\imm
+	movt\cond	\dst, #:upper16:\imm
 	.endif
 	.endm
 
@@ -619,6 +666,78 @@ THUMB(	orr	\reg , \reg , #PSR_T_BIT	)
 	__adldst_l	str, \src, \sym, \tmp, \cond
 	.endm
 
+	.macro		__ldst_va, op, reg, tmp, sym, cond
+#if __LINUX_ARM_ARCH__ >= 7 || \
+    !defined(CONFIG_ARM_HAS_GROUP_RELOCS) || \
+    (defined(MODULE) && defined(CONFIG_ARM_MODULE_PLTS))
+	mov_l		\tmp, \sym, \cond
+	\op\cond	\reg, [\tmp]
+#else
+	/*
+	 * Avoid a literal load, by emitting a sequence of ADD/LDR instructions
+	 * with the appropriate relocations. The combined sequence has a range
+	 * of -/+ 256 MiB, which should be sufficient for the core kernel and
+	 * for modules loaded into the module region.
+	 */
+	.globl		\sym
+	.reloc		.L0_\@, R_ARM_ALU_PC_G0_NC, \sym
+	.reloc		.L1_\@, R_ARM_ALU_PC_G1_NC, \sym
+	.reloc		.L2_\@, R_ARM_LDR_PC_G2, \sym
+.L0_\@: sub\cond	\tmp, pc, #8
+.L1_\@: sub\cond	\tmp, \tmp, #4
+.L2_\@: \op\cond	\reg, [\tmp, #0]
+#endif
+	.endm
+
+	/*
+	 * ldr_va - load a 32-bit word from the virtual address of \sym
+	 */
+	.macro		ldr_va, rd:req, sym:req, cond
+	__ldst_va	ldr, \rd, \rd, \sym, \cond
+	.endm
+
+	/*
+	 * str_va - store a 32-bit word to the virtual address of \sym
+	 */
+	.macro		str_va, rn:req, sym:req, tmp:req, cond
+	__ldst_va	str, \rn, \tmp, \sym, \cond
+	.endm
+
+	/*
+	 * ldr_this_cpu_armv6 - Load a 32-bit word from the per-CPU variable 'sym',
+	 *			without using a temp register. Supported in ARM mode
+	 *			only.
+	 */
+	.macro		ldr_this_cpu_armv6, rd:req, sym:req
+	this_cpu_offset	\rd
+	.globl		\sym
+	.reloc		.L0_\@, R_ARM_ALU_PC_G0_NC, \sym
+	.reloc		.L1_\@, R_ARM_ALU_PC_G1_NC, \sym
+	.reloc		.L2_\@, R_ARM_LDR_PC_G2, \sym
+	add		\rd, \rd, pc
+.L0_\@: sub		\rd, \rd, #4
+.L1_\@: sub		\rd, \rd, #0
+.L2_\@: ldr		\rd, [\rd, #4]
+	.endm
+
+	/*
+	 * ldr_this_cpu - Load a 32-bit word from the per-CPU variable 'sym'
+	 *		  into register 'rd', which may be the stack pointer,
+	 *		  using 't1' and 't2' as general temp registers. These
+	 *		  are permitted to overlap with 'rd' if != sp
+	 */
+	.macro		ldr_this_cpu, rd:req, sym:req, t1:req, t2:req
+#if __LINUX_ARM_ARCH__ >= 7 || \
+    !defined(CONFIG_ARM_HAS_GROUP_RELOCS) || \
+    (defined(MODULE) && defined(CONFIG_ARM_MODULE_PLTS))
+	this_cpu_offset	\t1
+	mov_l		\t2, \sym
+	ldr		\rd, [\t1, \t2]
+#else
+	ldr_this_cpu_armv6 \rd, \sym
+#endif
+	.endm
+
 	/*
 	 * rev_l - byte-swap a 32-bit value
 	 *
@@ -636,4 +755,19 @@ THUMB(	orr	\reg , \reg , #PSR_T_BIT	)
 	.endif
 	.endm
 
+	/*
+	 * bl_r - branch and link to register
+	 *
+	 * @dst: target to branch to
+	 * @c: conditional opcode suffix
+	 */
+	.macro		bl_r, dst:req, c
+	.if		__LINUX_ARM_ARCH__ < 6
+	mov\c		lr, pc
+	mov\c		pc, \dst
+	.else
+	blx\c		\dst
+	.endif
+	.endm
+
 #endif /* __ASM_ASSEMBLER_H__ */

arch/arm/include/asm/cacheflush.h

@@ -445,15 +445,10 @@ static inline void __sync_cache_range_r(volatile void *p, size_t size)
  *   however some exceptions may exist.  Caveat emptor.
  *
  * - The clobber list is dictated by the call to v7_flush_dcache_*.
- *   fp is preserved to the stack explicitly prior disabling the cache
- *   since adding it to the clobber list is incompatible with having
- *   CONFIG_FRAME_POINTER=y.  ip is saved as well if ever r12-clobbering
- *   trampoline are inserted by the linker and to keep sp 64-bit aligned.
  */
 #define v7_exit_coherency_flush(level) \
 	asm volatile( \
 	".arch	armv7-a \n\t" \
-	"stmfd	sp!, {fp, ip} \n\t" \
 	"mrc	p15, 0, r0, c1, c0, 0	@ get SCTLR \n\t" \
 	"bic	r0, r0, #"__stringify(CR_C)" \n\t" \
 	"mcr	p15, 0, r0, c1, c0, 0	@ set SCTLR \n\t" \
@@ -463,10 +458,9 @@ static inline void __sync_cache_range_r(volatile void *p, size_t size)
 	"bic	r0, r0, #(1 << 6)	@ disable local coherency \n\t" \
 	"mcr	p15, 0, r0, c1, c0, 1	@ set ACTLR \n\t" \
 	"isb	\n\t" \
-	"dsb	\n\t" \
-	"ldmfd	sp!, {fp, ip}" \
-	: : : "r0","r1","r2","r3","r4","r5","r6","r7", \
-	      "r9","r10","lr","memory" )
+	"dsb" \
+	: : : "r0","r1","r2","r3","r4","r5","r6", \
+	      "r9","r10","ip","lr","memory" )
 
 void flush_uprobe_xol_access(struct page *page, unsigned long uaddr,
 			     void *kaddr, unsigned long len);

arch/arm/include/asm/current.h

@@ -8,25 +8,18 @@
 #define _ASM_ARM_CURRENT_H
 
 #ifndef __ASSEMBLY__
+#include <asm/insn.h>
 
 struct task_struct;
 
-static inline void set_current(struct task_struct *cur)
-{
-	if (!IS_ENABLED(CONFIG_CURRENT_POINTER_IN_TPIDRURO))
-		return;
+extern struct task_struct *__current;
 
-	/* Set TPIDRURO */
-	asm("mcr p15, 0, %0, c13, c0, 3" :: "r"(cur) : "memory");
-}
-
-#ifdef CONFIG_CURRENT_POINTER_IN_TPIDRURO
-
-static inline struct task_struct *get_current(void)
+static __always_inline __attribute_const__ struct task_struct *get_current(void)
 {
 	struct task_struct *cur;
 
 #if __has_builtin(__builtin_thread_pointer) && \
+    defined(CONFIG_CURRENT_POINTER_IN_TPIDRURO) && \
     !(defined(CONFIG_THUMB2_KERNEL) && \
       defined(CONFIG_CC_IS_CLANG) && CONFIG_CLANG_VERSION < 130001)
 	/*
@@ -39,16 +32,39 @@ static inline struct task_struct *get_current(void)
 	 * https://github.com/ClangBuiltLinux/linux/issues/1485
 	 */
 	cur = __builtin_thread_pointer();
+#elif defined(CONFIG_CURRENT_POINTER_IN_TPIDRURO) || defined(CONFIG_SMP)
+	asm("0:	mrc p15, 0, %0, c13, c0, 3			\n\t"
+#ifdef CONFIG_CPU_V6
+	    "1:							\n\t"
+	    "	.subsection 1					\n\t"
+#if defined(CONFIG_ARM_HAS_GROUP_RELOCS) && \
+    !(defined(MODULE) && defined(CONFIG_ARM_MODULE_PLTS))
+	    "2: " LOAD_SYM_ARMV6(%0, __current) "		\n\t"
+	    "	b	1b					\n\t"
 #else
-	asm("mrc p15, 0, %0, c13, c0, 3" : "=r"(cur));
+	    "2:	ldr	%0, 3f					\n\t"
+	    "	ldr	%0, [%0]				\n\t"
+	    "	b	1b					\n\t"
+	    "3:	.long	__current				\n\t"
+#endif
+	    "	.previous					\n\t"
+	    "	.pushsection \".alt.smp.init\", \"a\"		\n\t"
+	    "	.long	0b - .					\n\t"
+	    "	b	. + (2b - 0b)				\n\t"
+	    "	.popsection					\n\t"
+#endif
+	    : "=r"(cur));
+#elif __LINUX_ARM_ARCH__>= 7 || \
+      !defined(CONFIG_ARM_HAS_GROUP_RELOCS) || \
+      (defined(MODULE) && defined(CONFIG_ARM_MODULE_PLTS))
+	cur = __current;
+#else
+	asm(LOAD_SYM_ARMV6(%0, __current) : "=r"(cur));
 #endif
 	return cur;
 }
 
 #define current get_current()
-#else
-#include <asm-generic/current.h>
-#endif /* CONFIG_CURRENT_POINTER_IN_TPIDRURO */
 
 #endif /* __ASSEMBLY__ */
 

arch/arm/include/asm/elf.h

@@ -61,6 +61,9 @@ typedef struct user_fp elf_fpregset_t;
 #define R_ARM_MOVT_ABS		44
 #define R_ARM_MOVW_PREL_NC	45
 #define R_ARM_MOVT_PREL		46
+#define R_ARM_ALU_PC_G0_NC	57
+#define R_ARM_ALU_PC_G1_NC	59
+#define R_ARM_LDR_PC_G2		63
 
 #define R_ARM_THM_CALL		10
 #define R_ARM_THM_JUMP24	30

arch/arm/include/asm/entry-macro-multi.S

@@ -1,40 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#include <asm/assembler.h>
-
-/*
- * Interrupt handling.  Preserves r7, r8, r9
- */
-	.macro	arch_irq_handler_default
-	get_irqnr_preamble r6, lr
-1:	get_irqnr_and_base r0, r2, r6, lr
-	movne	r1, sp
-	@
-	@ routine called with r0 = irq number, r1 = struct pt_regs *
-	@
-	badrne	lr, 1b
-	bne	asm_do_IRQ
-
-#ifdef CONFIG_SMP
-	/*
-	 * XXX
-	 *
-	 * this macro assumes that irqstat (r2) and base (r6) are
-	 * preserved from get_irqnr_and_base above
-	 */
-	ALT_SMP(test_for_ipi r0, r2, r6, lr)
-	ALT_UP_B(9997f)
-	movne	r1, sp
-	badrne	lr, 1b
-	bne	do_IPI
-#endif
-9997:
-	.endm
-
-	.macro	arch_irq_handler, symbol_name
-	.align	5
-	.global \symbol_name
-\symbol_name:
-	mov	r8, lr
-	arch_irq_handler_default
-	ret	r8
-	.endm

arch/arm/include/asm/ftrace.h

@@ -2,6 +2,8 @@
 #ifndef _ASM_ARM_FTRACE
 #define _ASM_ARM_FTRACE
 
+#define HAVE_FUNCTION_GRAPH_FP_TEST
+
 #ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
 #define ARCH_SUPPORTS_FTRACE_OPS 1
 #endif
@@ -48,7 +50,7 @@ void *return_address(unsigned int);
 
 static inline void *return_address(unsigned int level)
 {
-	return NULL;
+       return NULL;
 }
 
 #endif

arch/arm/include/asm/hardware/entry-macro-iomd.S

@@ -1,131 +0,0 @@
-/*
- * arch/arm/include/asm/hardware/entry-macro-iomd.S
- *
- * Low-level IRQ helper macros for IOC/IOMD based platforms
- *
- * This file is licensed under  the terms of the GNU General Public
- * License version 2. This program is licensed "as is" without any
- * warranty of any kind, whether express or implied.
- */
-
-/* IOC / IOMD based hardware */
-#include <asm/hardware/iomd.h>
-
-		.macro	get_irqnr_and_base, irqnr, irqstat, base, tmp
-		ldrb	\irqstat, [\base, #IOMD_IRQREQB]	@ get high priority first
-		ldr	\tmp, =irq_prio_h
-		teq	\irqstat, #0
-#ifdef IOMD_BASE
-		ldrbeq	\irqstat, [\base, #IOMD_DMAREQ]	@ get dma
-		addeq	\tmp, \tmp, #256		@ irq_prio_h table size
-		teqeq	\irqstat, #0
-		bne	2406f
-#endif
-		ldrbeq	\irqstat, [\base, #IOMD_IRQREQA]	@ get low priority
-		addeq	\tmp, \tmp, #256		@ irq_prio_d table size
-		teqeq	\irqstat, #0
-#ifdef IOMD_IRQREQC
-		ldrbeq	\irqstat, [\base, #IOMD_IRQREQC]
-		addeq	\tmp, \tmp, #256		@ irq_prio_l table size
-		teqeq	\irqstat, #0
-#endif
-#ifdef IOMD_IRQREQD
-		ldrbeq	\irqstat, [\base, #IOMD_IRQREQD]
-		addeq	\tmp, \tmp, #256		@ irq_prio_lc table size
-		teqeq	\irqstat, #0
-#endif
-2406:		ldrbne	\irqnr, [\tmp, \irqstat]	@ get IRQ number
-		.endm
-
-/*
- * Interrupt table (incorporates priority).  Please note that we
- * rely on the order of these tables (see above code).
- */
-		.align	5
-irq_prio_h:	.byte	 0, 8, 9, 8,10,10,10,10,11,11,11,11,10,10,10,10
-		.byte	12, 8, 9, 8,10,10,10,10,11,11,11,11,10,10,10,10
-		.byte	13,13,13,13,10,10,10,10,11,11,11,11,10,10,10,10
-		.byte	13,13,13,13,10,10,10,10,11,11,11,11,10,10,10,10
-		.byte	14,14,14,14,10,10,10,10,11,11,11,11,10,10,10,10
-		.byte	14,14,14,14,10,10,10,10,11,11,11,11,10,10,10,10
-		.byte	13,13,13,13,10,10,10,10,11,11,11,11,10,10,10,10
-		.byte	13,13,13,13,10,10,10,10,11,11,11,11,10,10,10,10
-		.byte	15,15,15,15,10,10,10,10,11,11,11,11,10,10,10,10
-		.byte	15,15,15,15,10,10,10,10,11,11,11,11,10,10,10,10
-		.byte	13,13,13,13,10,10,10,10,11,11,11,11,10,10,10,10
-		.byte	13,13,13,13,10,10,10,10,11,11,11,11,10,10,10,10
-		.byte	15,15,15,15,10,10,10,10,11,11,11,11,10,10,10,10
-		.byte	15,15,15,15,10,10,10,10,11,11,11,11,10,10,10,10
-		.byte	13,13,13,13,10,10,10,10,11,11,11,11,10,10,10,10
-		.byte	13,13,13,13,10,10,10,10,11,11,11,11,10,10,10,10
-#ifdef IOMD_BASE
-irq_prio_d:	.byte	 0,16,17,16,18,16,17,16,19,16,17,16,18,16,17,16
-		.byte	20,16,17,16,18,16,17,16,19,16,17,16,18,16,17,16
-		.byte	21,16,17,16,18,16,17,16,19,16,17,16,18,16,17,16
-		.byte	21,16,17,16,18,16,17,16,19,16,17,16,18,16,17,16
-		.byte	22,16,17,16,18,16,17,16,19,16,17,16,18,16,17,16
-		.byte	22,16,17,16,18,16,17,16,19,16,17,16,18,16,17,16
-		.byte	21,16,17,16,18,16,17,16,19,16,17,16,18,16,17,16
-		.byte	21,16,17,16,18,16,17,16,19,16,17,16,18,16,17,16
-		.byte	23,16,17,16,18,16,17,16,19,16,17,16,18,16,17,16
-		.byte	23,16,17,16,18,16,17,16,19,16,17,16,18,16,17,16
-		.byte	21,16,17,16,18,16,17,16,19,16,17,16,18,16,17,16
-		.byte	21,16,17,16,18,16,17,16,19,16,17,16,18,16,17,16
-		.byte	22,16,17,16,18,16,17,16,19,16,17,16,18,16,17,16
-		.byte	22,16,17,16,18,16,17,16,19,16,17,16,18,16,17,16
-		.byte	21,16,17,16,18,16,17,16,19,16,17,16,18,16,17,16
-		.byte	21,16,17,16,18,16,17,16,19,16,17,16,18,16,17,16
-#endif
-irq_prio_l:	.byte	 0, 0, 1, 0, 2, 2, 2, 2, 3, 3, 3, 3, 3, 3, 3, 3
-		.byte	 4, 0, 1, 0, 2, 2, 2, 2, 3, 3, 3, 3, 3, 3, 3, 3
-		.byte	 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5
-		.byte	 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5
-		.byte	 6, 6, 6, 6, 6, 6, 6, 6, 3, 3, 3, 3, 3, 3, 3, 3
-		.byte	 6, 6, 6, 6, 6, 6, 6, 6, 3, 3, 3, 3, 3, 3, 3, 3
-		.byte	 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5
-		.byte	 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5
-		.byte	 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7
-		.byte	 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7
-		.byte	 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7
-		.byte	 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7
-		.byte	 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7
-		.byte	 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7
-		.byte	 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7
-		.byte	 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7
-#ifdef IOMD_IRQREQC
-irq_prio_lc:	.byte	24,24,25,24,26,26,26,26,27,27,27,27,27,27,27,27
-		.byte	28,24,25,24,26,26,26,26,27,27,27,27,27,27,27,27
-		.byte	29,29,29,29,29,29,29,29,29,29,29,29,29,29,29,29
-		.byte	29,29,29,29,29,29,29,29,29,29,29,29,29,29,29,29
-		.byte	30,30,30,30,30,30,30,30,27,27,27,27,27,27,27,27
-		.byte	30,30,30,30,30,30,30,30,27,27,27,27,27,27,27,27
-		.byte	29,29,29,29,29,29,29,29,29,29,29,29,29,29,29,29
-		.byte	29,29,29,29,29,29,29,29,29,29,29,29,29,29,29,29
-		.byte	31,31,31,31,31,31,31,31,31,31,31,31,31,31,31,31
-		.byte	31,31,31,31,31,31,31,31,31,31,31,31,31,31,31,31
-		.byte	31,31,31,31,31,31,31,31,31,31,31,31,31,31,31,31
-		.byte	31,31,31,31,31,31,31,31,31,31,31,31,31,31,31,31
-		.byte	31,31,31,31,31,31,31,31,31,31,31,31,31,31,31,31
-		.byte	31,31,31,31,31,31,31,31,31,31,31,31,31,31,31,31
-		.byte	31,31,31,31,31,31,31,31,31,31,31,31,31,31,31,31
-		.byte	31,31,31,31,31,31,31,31,31,31,31,31,31,31,31,31
-#endif
-#ifdef IOMD_IRQREQD
-irq_prio_ld:	.byte	40,40,41,40,42,42,42,42,43,43,43,43,43,43,43,43
-		.byte	44,40,41,40,42,42,42,42,43,43,43,43,43,43,43,43
-		.byte	45,45,45,45,45,45,45,45,45,45,45,45,45,45,45,45
-		.byte	45,45,45,45,45,45,45,45,45,45,45,45,45,45,45,45
-		.byte	46,46,46,46,46,46,46,46,43,43,43,43,43,43,43,43
-		.byte	46,46,46,46,46,46,46,46,43,43,43,43,43,43,43,43
-		.byte	45,45,45,45,45,45,45,45,45,45,45,45,45,45,45,45
-		.byte	45,45,45,45,45,45,45,45,45,45,45,45,45,45,45,45
-		.byte	47,47,47,47,47,47,47,47,47,47,47,47,47,47,47,47
-		.byte	47,47,47,47,47,47,47,47,47,47,47,47,47,47,47,47
-		.byte	47,47,47,47,47,47,47,47,47,47,47,47,47,47,47,47
-		.byte	47,47,47,47,47,47,47,47,47,47,47,47,47,47,47,47
-		.byte	47,47,47,47,47,47,47,47,47,47,47,47,47,47,47,47
-		.byte	47,47,47,47,47,47,47,47,47,47,47,47,47,47,47,47
-		.byte	47,47,47,47,47,47,47,47,47,47,47,47,47,47,47,47
-		.byte	47,47,47,47,47,47,47,47,47,47,47,47,47,47,47,47
-#endif
-

arch/arm/include/asm/insn.h

@@ -2,6 +2,23 @@
 #ifndef __ASM_ARM_INSN_H
 #define __ASM_ARM_INSN_H
 
+#include <linux/types.h>
+
+/*
+ * Avoid a literal load by emitting a sequence of ADD/LDR instructions with the
+ * appropriate relocations. The combined sequence has a range of -/+ 256 MiB,
+ * which should be sufficient for the core kernel as well as modules loaded
+ * into the module region. (Not supported by LLD before release 14)
+ */
+#define LOAD_SYM_ARMV6(reg, sym)					\
+	"	.globl	" #sym "				\n\t"	\
+	"	.reloc	10f, R_ARM_ALU_PC_G0_NC, " #sym "	\n\t"	\
+	"	.reloc	11f, R_ARM_ALU_PC_G1_NC, " #sym "	\n\t"	\
+	"	.reloc	12f, R_ARM_LDR_PC_G2, " #sym "		\n\t"	\
+	"10:	sub	" #reg ", pc, #8			\n\t"	\
+	"11:	sub	" #reg ", " #reg ", #4			\n\t"	\
+	"12:	ldr	" #reg ", [" #reg ", #0]		\n\t"
+
 static inline unsigned long
 arm_gen_nop(void)
 {

arch/arm/include/asm/irq.h

@@ -26,7 +26,6 @@
 struct irqaction;
 struct pt_regs;
 
-extern void asm_do_IRQ(unsigned int, struct pt_regs *);
 void handle_IRQ(unsigned int, struct pt_regs *);
 void init_IRQ(void);
 

arch/arm/include/asm/mach/arch.h

@@ -56,9 +56,7 @@ struct machine_desc {
 	void			(*init_time)(void);
 	void			(*init_machine)(void);
 	void			(*init_late)(void);
-#ifdef CONFIG_GENERIC_IRQ_MULTI_HANDLER
 	void			(*handle_irq)(struct pt_regs *);
-#endif
 	void			(*restart)(enum reboot_mode, const char *);
 };
 

arch/arm/include/asm/mmu.h

@@ -10,7 +10,7 @@ typedef struct {
 #else
 	int		switch_pending;
 #endif
-	unsigned int	vmalloc_seq;
+	atomic_t	vmalloc_seq;
 	unsigned long	sigpage;
 #ifdef CONFIG_VDSO
 	unsigned long	vdso;

arch/arm/include/asm/mmu_context.h

@@ -23,6 +23,16 @@
 
 void __check_vmalloc_seq(struct mm_struct *mm);
 
+#ifdef CONFIG_MMU
+static inline void check_vmalloc_seq(struct mm_struct *mm)
+{
+	if (!IS_ENABLED(CONFIG_ARM_LPAE) &&
+	    unlikely(atomic_read(&mm->context.vmalloc_seq) !=
+		     atomic_read(&init_mm.context.vmalloc_seq)))
+		__check_vmalloc_seq(mm);
+}
+#endif
+
 #ifdef CONFIG_CPU_HAS_ASID
 
 void check_and_switch_context(struct mm_struct *mm, struct task_struct *tsk);
@@ -52,8 +62,7 @@ static inline void a15_erratum_get_cpumask(int this_cpu, struct mm_struct *mm,
 static inline void check_and_switch_context(struct mm_struct *mm,
 					    struct task_struct *tsk)
 {
-	if (unlikely(mm->context.vmalloc_seq != init_mm.context.vmalloc_seq))
-		__check_vmalloc_seq(mm);
+	check_vmalloc_seq(mm);
 
 	if (irqs_disabled())
 		/*
@@ -129,6 +138,15 @@ switch_mm(struct mm_struct *prev, struct mm_struct *next,
 #endif
 }
 
+#ifdef CONFIG_VMAP_STACK
+static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
+{
+	if (mm != &init_mm)
+		check_vmalloc_seq(mm);
+}
+#define enter_lazy_tlb enter_lazy_tlb
+#endif
+
 #include <asm-generic/mmu_context.h>
 
 #endif

arch/arm/include/asm/page.h

@@ -147,6 +147,9 @@ extern void copy_page(void *to, const void *from);
 #include <asm/pgtable-3level-types.h>
 #else
 #include <asm/pgtable-2level-types.h>
+#ifdef CONFIG_VMAP_STACK
+#define ARCH_PAGE_TABLE_SYNC_MASK	PGTBL_PMD_MODIFIED
+#endif
 #endif
 
 #endif /* CONFIG_MMU */

arch/arm/include/asm/percpu.h

@@ -5,20 +5,27 @@
 #ifndef _ASM_ARM_PERCPU_H_
 #define _ASM_ARM_PERCPU_H_
 
+#include <asm/insn.h>
+
 register unsigned long current_stack_pointer asm ("sp");
 
 /*
  * Same as asm-generic/percpu.h, except that we store the per cpu offset
  * in the TPIDRPRW. TPIDRPRW only exists on V6K and V7
  */
-#if defined(CONFIG_SMP) && !defined(CONFIG_CPU_V6)
+#ifdef CONFIG_SMP
 static inline void set_my_cpu_offset(unsigned long off)
 {
+	extern unsigned int smp_on_up;
+
+	if (IS_ENABLED(CONFIG_CPU_V6) && !smp_on_up)
+		return;
+
 	/* Set TPIDRPRW */
 	asm volatile("mcr p15, 0, %0, c13, c0, 4" : : "r" (off) : "memory");
 }
 
-static inline unsigned long __my_cpu_offset(void)
+static __always_inline unsigned long __my_cpu_offset(void)
 {
 	unsigned long off;
 
@@ -27,8 +34,28 @@ static inline unsigned long __my_cpu_offset(void)
 	 * We want to allow caching the value, so avoid using volatile and
 	 * instead use a fake stack read to hazard against barrier().
 	 */
-	asm("mrc p15, 0, %0, c13, c0, 4" : "=r" (off)
-		: "Q" (*(const unsigned long *)current_stack_pointer));
+	asm("0:	mrc p15, 0, %0, c13, c0, 4			\n\t"
+#ifdef CONFIG_CPU_V6
+	    "1:							\n\t"
+	    "	.subsection 1					\n\t"
+#if defined(CONFIG_ARM_HAS_GROUP_RELOCS) && \
+    !(defined(MODULE) && defined(CONFIG_ARM_MODULE_PLTS))
+	    "2: " LOAD_SYM_ARMV6(%0, __per_cpu_offset) "	\n\t"
+	    "	b	1b					\n\t"
+#else
+	    "2: ldr	%0, 3f					\n\t"
+	    "	ldr	%0, [%0]				\n\t"
+	    "	b	1b					\n\t"
+	    "3:	.long	__per_cpu_offset			\n\t"
+#endif
+	    "	.previous					\n\t"
+	    "	.pushsection \".alt.smp.init\", \"a\"		\n\t"
+	    "	.long	0b - .					\n\t"
+	    "	b	. + (2b - 0b)				\n\t"
+	    "	.popsection					\n\t"
+#endif
+	     : "=r" (off)
+	     : "Q" (*(const unsigned long *)current_stack_pointer));
 
 	return off;
 }

arch/arm/include/asm/smp.h

@@ -24,11 +24,6 @@ struct seq_file;
  */
 extern void show_ipi_list(struct seq_file *, int);
 
-/*
- * Called from assembly code, this handles an IPI.
- */
-asmlinkage void do_IPI(int ipinr, struct pt_regs *regs);
-
 /*
  * Called from C code, this handles an IPI.
  */