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

Pull ARM updates from Russell King:

 - amba bus irq rework

 - add kfence support

 - support for Cortex M33 and M55 CPUs

 - kbuild updates for decompressor

 - let core code manage thread_info::cpu

 - avoid unpredictable NOP encoding in decompressor

 - reduce information printed in calltraces

* tag 'for-linus' of git://git.armlinux.org.uk/~rmk/linux-arm:
  ARM: reduce the information printed in call traces
  ARM: 9168/1: Add support for Cortex-M55 processor
  ARM: 9167/1: Add support for Cortex-M33 processor
  ARM: 9166/1: Support KFENCE for ARM
  ARM: 9165/1: mm: Provide is_write_fault()
  ARM: 9164/1: mm: Provide set_memory_valid()
  ARM: 9163/1: amba: Move of_amba_device_decode_irq() into amba_probe()
  ARM: 9162/1: amba: Kill sysfs attribute file of irq
  ARM: 9161/1: mm: mark private VM_FAULT_X defines as vm_fault_t
  ARM: 9159/1: decompressor: Avoid UNPREDICTABLE NOP encoding
  ARM: 9158/1: leave it to core code to manage thread_info::cpu
  ARM: 9154/1: decompressor: do not copy source files while building

Documentation/features/core/thread-info-in-task/arch-support.txt

@@ -8,7 +8,7 @@
     -----------------------
     |       alpha: | TODO |
     |         arc: | TODO |
-    |         arm: | TODO |
+    |         arm: |  ok  |
     |       arm64: |  ok  |
     |        csky: | TODO |
     |       h8300: | TODO |

arch/arm/Kconfig

@@ -69,6 +69,7 @@ config ARM
 	select HAVE_ARCH_AUDITSYSCALL if AEABI && !OABI_COMPAT
 	select HAVE_ARCH_BITREVERSE if (CPU_32v7M || CPU_32v7) && !CPU_32v6
 	select HAVE_ARCH_JUMP_LABEL if !XIP_KERNEL && !CPU_ENDIAN_BE32 && MMU
+	select HAVE_ARCH_KFENCE if MMU && !XIP_KERNEL
 	select HAVE_ARCH_KGDB if !CPU_ENDIAN_BE32 && MMU
 	select HAVE_ARCH_KASAN if MMU && !XIP_KERNEL
 	select HAVE_ARCH_MMAP_RND_BITS if MMU

arch/arm/Kconfig.debug

@@ -81,6 +81,17 @@ endchoice
 config ARM_UNWIND
 	bool
 
+config BACKTRACE_VERBOSE
+	bool "Verbose backtrace"
+	depends on EXPERT
+	help
+	  When the kernel produces a warning or oops, the kernel prints a
+	  trace of the call chain. This option controls whether we include
+	  the numeric addresses or only include the symbolic information.
+
+	  In most cases, say N here, unless you are intending to debug the
+	  kernel and have access to the kernel binary image.
+
 config FRAME_POINTER
 	bool
 

arch/arm/boot/compressed/.gitignore

 # SPDX-License-Identifier: GPL-2.0-only
-ashldi3.S
-bswapsdi2.S
-font.c
-lib1funcs.S
-hyp-stub.S
 piggy_data
 vmlinux
 vmlinux.lds

arch/arm/boot/compressed/Makefile

@@ -13,7 +13,6 @@ ifeq ($(CONFIG_DEBUG_UNCOMPRESS),y)
 OBJS	+= debug.o
 AFLAGS_head.o += -DDEBUG
 endif
-FONTC	= $(srctree)/lib/fonts/font_acorn_8x8.c
 
 # string library code (-Os is enforced to keep it much smaller)
 OBJS		+= string.o
@@ -99,11 +98,8 @@ $(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 \
-		 lib1funcs.o ashldi3.o bswapsdi2.o \
 		 head.o $(OBJS)
 
-clean-files += lib1funcs.S ashldi3.S bswapsdi2.S hyp-stub.S
-
 KBUILD_CFLAGS += -DDISABLE_BRANCH_PROFILING
 
 ccflags-y := -fpic $(call cc-option,-mno-single-pic-base,) -fno-builtin \
@@ -134,23 +130,7 @@ endif
 # Next argument is a linker script
 LDFLAGS_vmlinux += -T
 
-# For __aeabi_uidivmod
-lib1funcs = $(obj)/lib1funcs.o
-
-$(obj)/lib1funcs.S: $(srctree)/arch/$(SRCARCH)/lib/lib1funcs.S
-	$(call cmd,shipped)
-
-# For __aeabi_llsl
-ashldi3 = $(obj)/ashldi3.o
-
-$(obj)/ashldi3.S: $(srctree)/arch/$(SRCARCH)/lib/ashldi3.S
-	$(call cmd,shipped)
-
-# For __bswapsi2, __bswapdi2
-bswapsdi2 = $(obj)/bswapsdi2.o
-
-$(obj)/bswapsdi2.S: $(srctree)/arch/$(SRCARCH)/lib/bswapsdi2.S
-	$(call cmd,shipped)
+OBJS	+= lib1funcs.o ashldi3.o bswapsdi2.o
 
 # We need to prevent any GOTOFF relocs being used with references
 # to symbols in the .bss section since we cannot relocate them
@@ -175,8 +155,8 @@ fi
 efi-obj-$(CONFIG_EFI_STUB) := $(objtree)/drivers/firmware/efi/libstub/lib.a
 
 $(obj)/vmlinux: $(obj)/vmlinux.lds $(obj)/$(HEAD) $(obj)/piggy.o \
-		$(addprefix $(obj)/, $(OBJS)) $(lib1funcs) $(ashldi3) \
-		$(bswapsdi2) $(efi-obj-y) FORCE
+		$(addprefix $(obj)/, $(OBJS)) \
+		$(efi-obj-y) FORCE
 	@$(check_for_multiple_zreladdr)
 	$(call if_changed,ld)
 	@$(check_for_bad_syms)
@@ -187,11 +167,4 @@ $(obj)/piggy_data: $(obj)/../Image FORCE
 $(obj)/piggy.o: $(obj)/piggy_data
 
 CFLAGS_font.o := -Dstatic=
-
-$(obj)/font.c: $(FONTC)
-	$(call cmd,shipped)
-
 AFLAGS_hyp-stub.o := -Wa,-march=armv7-a
-
-$(obj)/hyp-stub.S: $(srctree)/arch/$(SRCARCH)/kernel/hyp-stub.S
-	$(call cmd,shipped)

arch/arm/boot/compressed/ashldi3.S

+/* SPDX-License-Identifier: GPL-2.0-only */
+/* For __aeabi_llsl */
+#include "../../lib/ashldi3.S"

arch/arm/boot/compressed/bswapsdi2.S

+/* SPDX-License-Identifier: GPL-2.0-only */
+/* For __bswapsi2, __bswapdi2 */
+#include "../../lib/bswapsdi2.S"

arch/arm/boot/compressed/efi-header.S

@@ -9,16 +9,22 @@
 #include <linux/sizes.h>
 
 		.macro	__nop
-#ifdef CONFIG_EFI_STUB
-		@ This is almost but not quite a NOP, since it does clobber the
-		@ condition flags. But it is the best we can do for EFI, since
-		@ PE/COFF expects the magic string "MZ" at offset 0, while the
-		@ ARM/Linux boot protocol expects an executable instruction
-		@ there.
-		.inst	MZ_MAGIC | (0x1310 << 16)	@ tstne r0, #0x4d000
-#else
  AR_CLASS(	mov	r0, r0		)
   M_CLASS(	nop.w			)
+		.endm
+
+		.macro __initial_nops
+#ifdef CONFIG_EFI_STUB
+		@ This is a two-instruction NOP, which happens to bear the
+		@ PE/COFF signature "MZ" in the first two bytes, so the kernel
+		@ is accepted as an EFI binary. Booting via the UEFI stub
+		@ will not execute those instructions, but the ARM/Linux
+		@ boot protocol does, so we need some NOPs here.
+		.inst	MZ_MAGIC | (0xe225 << 16)	@ eor r5, r5, 0x4d000
+		eor	r5, r5, 0x4d000			@ undo previous insn
+#else
+		__nop
+		__nop
 #endif
 		.endm
 

arch/arm/boot/compressed/font.c

+// SPDX-License-Identifier: GPL-2.0-only
+#include "../../../../lib/fonts/font_acorn_8x8.c"

arch/arm/boot/compressed/head.S

@@ -203,7 +203,8 @@ start:
 		 * were patching the initial instructions of the kernel, i.e
 		 * had started to exploit this "patch area".
 		 */
-		.rept	7
+		__initial_nops
+		.rept	5
 		__nop
 		.endr
 #ifndef CONFIG_THUMB2_KERNEL

arch/arm/boot/compressed/hyp-stub.S

+/* SPDX-License-Identifier: GPL-2.0-only */
+#include "../../kernel/hyp-stub.S"

arch/arm/boot/compressed/lib1funcs.S

+/* SPDX-License-Identifier: GPL-2.0-only */
+/* For __aeabi_uidivmod */
+#include "../../lib/lib1funcs.S"

arch/arm/include/asm/kfence.h

+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __ASM_ARM_KFENCE_H
+#define __ASM_ARM_KFENCE_H
+
+#include <linux/kfence.h>
+
+#include <asm/pgalloc.h>
+#include <asm/set_memory.h>
+
+static inline int split_pmd_page(pmd_t *pmd, unsigned long addr)
+{
+	int i;
+	unsigned long pfn = PFN_DOWN(__pa(addr));
+	pte_t *pte = pte_alloc_one_kernel(&init_mm);
+
+	if (!pte)
+		return -ENOMEM;
+
+	for (i = 0; i < PTRS_PER_PTE; i++)
+		set_pte_ext(pte + i, pfn_pte(pfn + i, PAGE_KERNEL), 0);
+	pmd_populate_kernel(&init_mm, pmd, pte);
+
+	flush_tlb_kernel_range(addr, addr + PMD_SIZE);
+	return 0;
+}
+
+static inline bool arch_kfence_init_pool(void)
+{
+	unsigned long addr;
+	pmd_t *pmd;
+
+	for (addr = (unsigned long)__kfence_pool; is_kfence_address((void *)addr);
+	     addr += PAGE_SIZE) {
+		pmd = pmd_off_k(addr);
+
+		if (pmd_leaf(*pmd)) {
+			if (split_pmd_page(pmd, addr & PMD_MASK))
+				return false;
+		}
+	}
+
+	return true;
+}
+
+static inline bool kfence_protect_page(unsigned long addr, bool protect)
+{
+	set_memory_valid(addr, 1, !protect);
+
+	return true;
+}
+
+#endif /* __ASM_ARM_KFENCE_H */

arch/arm/include/asm/set_memory.h

@@ -11,6 +11,7 @@ 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);
+int set_memory_valid(unsigned long addr, int numpages, int enable);
 #else
 static inline int set_memory_ro(unsigned long addr, int numpages) { return 0; }
 static inline int set_memory_rw(unsigned long addr, int numpages) { return 0; }

arch/arm/include/asm/switch_to.h

@@ -23,23 +23,9 @@
  */
 extern struct task_struct *__switch_to(struct task_struct *, struct thread_info *, struct thread_info *);
 
-static inline void set_ti_cpu(struct task_struct *p)
-{
-#ifdef CONFIG_THREAD_INFO_IN_TASK
-	/*
-	 * The core code no longer maintains the thread_info::cpu field once
-	 * CONFIG_THREAD_INFO_IN_TASK is in effect, but we rely on it for
-	 * raw_smp_processor_id(), which cannot access struct task_struct*
-	 * directly for reasons of circular #inclusion hell.
-	 */
-	task_thread_info(p)->cpu = task_cpu(p);
-#endif
-}
-
 #define switch_to(prev,next,last)					\
 do {									\
 	__complete_pending_tlbi();					\
-	set_ti_cpu(next);						\
 	if (IS_ENABLED(CONFIG_CURRENT_POINTER_IN_TPIDRURO))		\
 		__this_cpu_write(__entry_task, next);			\
 	last = __switch_to(prev,task_thread_info(prev), task_thread_info(next));	\

arch/arm/kernel/smp.c

@@ -154,9 +154,6 @@ int __cpu_up(unsigned int cpu, struct task_struct *idle)
 	secondary_data.swapper_pg_dir = get_arch_pgd(swapper_pg_dir);
 #endif
 	secondary_data.task = idle;
-	if (IS_ENABLED(CONFIG_THREAD_INFO_IN_TASK))
-		task_thread_info(idle)->cpu = cpu;
-
 	sync_cache_w(&secondary_data);
 
 	/*

arch/arm/kernel/traps.c

@@ -67,12 +67,14 @@ void dump_backtrace_entry(unsigned long where, unsigned long from,
 {
 	unsigned long end = frame + 4 + sizeof(struct pt_regs);
 
-#ifdef CONFIG_KALLSYMS
+#ifndef CONFIG_KALLSYMS
+	printk("%sFunction entered at [<%08lx>] from [<%08lx>]\n",
+		loglvl, where, from);
+#elif defined CONFIG_BACKTRACE_VERBOSE
 	printk("%s[<%08lx>] (%ps) from [<%08lx>] (%pS)\n",
 		loglvl, where, (void *)where, from, (void *)from);
 #else
-	printk("%sFunction entered at [<%08lx>] from [<%08lx>]\n",
-		loglvl, where, from);
+	printk("%s %ps from %pS\n", loglvl, (void *)where, (void *)from);
 #endif
 
 	if (in_entry_text(from) && end <= ALIGN(frame, THREAD_SIZE))

arch/arm/mm/fault.c

@@ -17,6 +17,7 @@
 #include <linux/sched/debug.h>
 #include <linux/highmem.h>
 #include <linux/perf_event.h>
+#include <linux/kfence.h>
 
 #include <asm/system_misc.h>
 #include <asm/system_info.h>
@@ -99,6 +100,11 @@ void show_pte(const char *lvl, struct mm_struct *mm, unsigned long addr)
 { }
 #endif					/* CONFIG_MMU */
 
+static inline bool is_write_fault(unsigned int fsr)
+{
+	return (fsr & FSR_WRITE) && !(fsr & FSR_CM);
+}
+
 static void die_kernel_fault(const char *msg, struct mm_struct *mm,
 			     unsigned long addr, unsigned int fsr,
 			     struct pt_regs *regs)
@@ -131,10 +137,14 @@ __do_kernel_fault(struct mm_struct *mm, unsigned long addr, unsigned int fsr,
 	/*
 	 * No handler, we'll have to terminate things with extreme prejudice.
 	 */
-	if (addr < PAGE_SIZE)
+	if (addr < PAGE_SIZE) {
 		msg = "NULL pointer dereference";
-	else
+	} else {
+		if (kfence_handle_page_fault(addr, is_write_fault(fsr), regs))
+			return;
+
 		msg = "paging request";
+	}
 
 	die_kernel_fault(msg, mm, addr, fsr, regs);
 }
@@ -191,8 +201,8 @@ void do_bad_area(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
 }
 
 #ifdef CONFIG_MMU
-#define VM_FAULT_BADMAP		0x010000
-#define VM_FAULT_BADACCESS	0x020000
+#define VM_FAULT_BADMAP		((__force vm_fault_t)0x010000)
+#define VM_FAULT_BADACCESS	((__force vm_fault_t)0x020000)
 
 static inline bool is_permission_fault(unsigned int fsr)
 {
@@ -261,7 +271,7 @@ do_page_fault(unsigned long addr, unsigned int fsr, struct pt_regs *regs)
 	if (user_mode(regs))
 		flags |= FAULT_FLAG_USER;
 
-	if ((fsr & FSR_WRITE) && !(fsr & FSR_CM)) {
+	if (is_write_fault(fsr)) {
 		flags |= FAULT_FLAG_WRITE;
 		vm_flags = VM_WRITE;
 	}

arch/arm/mm/pageattr.c

@@ -32,14 +32,31 @@ static bool in_range(unsigned long start, unsigned long size,
 		size <= range_end - start;
 }
 
+/*
+ * This function assumes that the range is mapped with PAGE_SIZE pages.
+ */
+static int __change_memory_common(unsigned long start, unsigned long size,
+				pgprot_t set_mask, pgprot_t clear_mask)
+{
+	struct page_change_data data;
+	int ret;
+
+	data.set_mask = set_mask;
+	data.clear_mask = clear_mask;
+
+	ret = apply_to_page_range(&init_mm, start, size, change_page_range,
+				  &data);
+
+	flush_tlb_kernel_range(start, start + size);
+	return ret;
+}
+
 static int change_memory_common(unsigned long addr, int numpages,
 				pgprot_t set_mask, pgprot_t clear_mask)
 {
 	unsigned long start = addr & PAGE_MASK;
 	unsigned long end = PAGE_ALIGN(addr) + numpages * PAGE_SIZE;
 	unsigned long size = end - start;
-	int ret;
-	struct page_change_data data;
 
 	WARN_ON_ONCE(start != addr);
 
@@ -50,14 +67,7 @@ static int change_memory_common(unsigned long addr, int numpages,
 	    !in_range(start, size, VMALLOC_START, VMALLOC_END))
 		return -EINVAL;
 
-	data.set_mask = set_mask;
-	data.clear_mask = clear_mask;
-
-	ret = apply_to_page_range(&init_mm, start, size, change_page_range,
-					&data);
-
-	flush_tlb_kernel_range(start, end);
-	return ret;
+	return __change_memory_common(start, size, set_mask, clear_mask);
 }
 
 int set_memory_ro(unsigned long addr, int numpages)
@@ -87,3 +97,15 @@ int set_memory_x(unsigned long addr, int numpages)
 					__pgprot(0),
 					__pgprot(L_PTE_XN));
 }
+
+int set_memory_valid(unsigned long addr, int numpages, int enable)
+{
+	if (enable)
+		return __change_memory_common(addr, PAGE_SIZE * numpages,
+					      __pgprot(L_PTE_VALID),
+					      __pgprot(0));
+	else
+		return __change_memory_common(addr, PAGE_SIZE * numpages,
+					      __pgprot(0),
+					      __pgprot(L_PTE_VALID));
+}

arch/arm/mm/proc-v7m.S

@@ -193,6 +193,26 @@ ENDPROC(__v7m_setup)
 	.long	\cache_fns
 .endm
 
+	/*
+	 * Match ARM Cortex-M55 processor.
+	 */
+	.type	__v7m_cm55_proc_info, #object
+__v7m_cm55_proc_info:
+	.long	0x410fd220		/* ARM Cortex-M55 0xD22 */
+	.long	0xff0ffff0		/* Mask off revision, patch release */
+	__v7m_proc __v7m_cm55_proc_info, __v7m_cm7_setup, hwcaps = HWCAP_EDSP, cache_fns = v7m_cache_fns, proc_fns = cm7_processor_functions
+	.size	__v7m_cm55_proc_info, . - __v7m_cm55_proc_info
+
+	/*
+	 * Match ARM Cortex-M33 processor.
+	 */
+	.type	__v7m_cm33_proc_info, #object
+__v7m_cm33_proc_info:
+	.long	0x410fd210		/* ARM Cortex-M33 0xD21 */
+	.long	0xff0ffff0		/* Mask off revision, patch release */
+	__v7m_proc __v7m_cm33_proc_info, __v7m_setup, hwcaps = HWCAP_EDSP
+	.size	__v7m_cm33_proc_info, . - __v7m_cm33_proc_info
+
 	/*
 	 * Match ARM Cortex-M7 processor.
 	 */

drivers/amba/bus.c

@@ -21,8 +21,6 @@
 #include <linux/reset.h>
 #include <linux/of_irq.h>
 
-#include <asm/irq.h>
-
 #define to_amba_driver(d)	container_of(d, struct amba_driver, drv)
 
 /* called on periphid match and class 0x9 coresight device. */
@@ -136,8 +134,6 @@ static ssize_t name##_show(struct device *_dev,				\
 static DEVICE_ATTR_RO(name)
 
 amba_attr_func(id, "%08x\n", dev->periphid);
-amba_attr_func(irq0, "%u\n", dev->irq[0]);
-amba_attr_func(irq1, "%u\n", dev->irq[1]);
 amba_attr_func(resource, "\t%016llx\t%016llx\t%016lx\n",
 	 (unsigned long long)dev->res.start, (unsigned long long)dev->res.end,
 	 dev->res.flags);
@@ -175,6 +171,28 @@ static int amba_uevent(struct device *dev, struct kobj_uevent_env *env)
 	return retval;
 }
 
+static int of_amba_device_decode_irq(struct amba_device *dev)
+{
+	struct device_node *node = dev->dev.of_node;
+	int i, irq = 0;
+
+	if (IS_ENABLED(CONFIG_OF_IRQ) && node) {
+		/* Decode the IRQs and address ranges */
+		for (i = 0; i < AMBA_NR_IRQS; i++) {
+			irq = of_irq_get(node, i);
+			if (irq < 0) {
+				if (irq == -EPROBE_DEFER)
+					return irq;
+				irq = 0;
+			}
+
+			dev->irq[i] = irq;
+		}
+	}
+
+	return 0;
+}
+
 /*
  * These are the device model conversion veneers; they convert the
  * device model structures to our more specific structures.
@@ -187,6 +205,10 @@ static int amba_probe(struct device *dev)
 	int ret;
 
 	do {
+		ret = of_amba_device_decode_irq(pcdev);
+		if (ret)
+			break;
+
 		ret = of_clk_set_defaults(dev->of_node, false);
 		if (ret < 0)
 			break;
@@ -372,38 +394,12 @@ static void amba_device_release(struct device *dev)
 	kfree(d);
 }
 
-static int of_amba_device_decode_irq(struct amba_device *dev)
-{
-	struct device_node *node = dev->dev.of_node;
-	int i, irq = 0;
-
-	if (IS_ENABLED(CONFIG_OF_IRQ) && node) {
-		/* Decode the IRQs and address ranges */
-		for (i = 0; i < AMBA_NR_IRQS; i++) {
-			irq = of_irq_get(node, i);
-			if (irq < 0) {
-				if (irq == -EPROBE_DEFER)
-					return irq;
-				irq = 0;
-			}
-
-			dev->irq[i] = irq;
-		}
-	}
-
-	return 0;
-}
-
 static int amba_device_try_add(struct amba_device *dev, struct resource *parent)
 {
 	u32 size;
 	void __iomem *tmp;
 	int i, ret;
 
-	ret = of_amba_device_decode_irq(dev);
-	if (ret)
-		goto err_out;
-
 	ret = request_resource(parent, &dev->res);
 	if (ret)
 		goto err_out;
@@ -488,19 +484,8 @@ static int amba_device_try_add(struct amba_device *dev, struct resource *parent)
 
  skip_probe:
 	ret = device_add(&dev->dev);
-	if (ret)
-		goto err_release;
-
-	if (dev->irq[0])
-		ret = device_create_file(&dev->dev, &dev_attr_irq0);
-	if (ret == 0 && dev->irq[1])
-		ret = device_create_file(&dev->dev, &dev_attr_irq1);
-	if (ret == 0)
-		return ret;
-
-	device_unregister(&dev->dev);
-
  err_release:
+	if (ret)
 		release_resource(&dev->res);
  err_out:
 	return ret;

scripts/remove-stale-files

@@ -24,7 +24,7 @@ set -e
 # with O=, make sure to remove the stale files in the output tree. Otherwise,
 # the build system wrongly compiles the stale ones.
 if [ -n "${building_out_of_srctree}" ]; then
-	for f in fdt_rw.c fdt_ro.c fdt_wip.c fdt.c
+	for f in fdt_rw.c fdt_ro.c fdt_wip.c fdt.c ashldi3.S bswapsdi2.S font.c lib1funcs.S hyp-stub.S
 	do
 		rm -f arch/arm/boot/compressed/${f}
 	done