Update Linux to v5.4.148

Sourced from [1]

[1] https://cdn.kernel.org/pub/linux/kernel/v5.x/linux-5.4.148.tar.gz

Change-Id: Ib3d26c5ba9b022e2e03533005c4fed4d7c30b61b
Signed-off-by: Olivier Deprez <olivier.deprez@arm.com>
diff --git a/arch/arm/kernel/Makefile b/arch/arm/kernel/Makefile
index 8cad594..8b679e2 100644
--- a/arch/arm/kernel/Makefile
+++ b/arch/arm/kernel/Makefile
@@ -17,10 +17,14 @@
 # Object file lists.
 
 obj-y		:= elf.o entry-common.o irq.o opcodes.o \
-		   process.o ptrace.o reboot.o return_address.o \
+		   process.o ptrace.o reboot.o \
 		   setup.o signal.o sigreturn_codes.o \
 		   stacktrace.o sys_arm.o time.o traps.o
 
+ifneq ($(CONFIG_ARM_UNWIND),y)
+obj-$(CONFIG_FRAME_POINTER)	+= return_address.o
+endif
+
 obj-$(CONFIG_ATAGS)		+= atags_parse.o
 obj-$(CONFIG_ATAGS_PROC)	+= atags_proc.o
 obj-$(CONFIG_DEPRECATED_PARAM_STRUCT) += atags_compat.o
diff --git a/arch/arm/kernel/asm-offsets.c b/arch/arm/kernel/asm-offsets.c
index c773b82..4ce2e29 100644
--- a/arch/arm/kernel/asm-offsets.c
+++ b/arch/arm/kernel/asm-offsets.c
@@ -15,6 +15,7 @@
 #include <linux/kvm_host.h>
 #endif
 #include <asm/cacheflush.h>
+#include <asm/kexec-internal.h>
 #include <asm/glue-df.h>
 #include <asm/glue-pf.h>
 #include <asm/mach/arch.h>
@@ -26,6 +27,7 @@
 #include <asm/vdso_datapage.h>
 #include <asm/hardware/cache-l2x0.h>
 #include <linux/kbuild.h>
+#include <linux/arm-smccc.h>
 #include "signal.h"
 
 /*
@@ -159,6 +161,8 @@
   DEFINE(SLEEP_SAVE_SP_PHYS,	offsetof(struct sleep_save_sp, save_ptr_stash_phys));
   DEFINE(SLEEP_SAVE_SP_VIRT,	offsetof(struct sleep_save_sp, save_ptr_stash));
 #endif
+  DEFINE(ARM_SMCCC_QUIRK_ID_OFFS,	offsetof(struct arm_smccc_quirk, id));
+  DEFINE(ARM_SMCCC_QUIRK_STATE_OFFS,	offsetof(struct arm_smccc_quirk, state));
   BLANK();
   DEFINE(DMA_BIDIRECTIONAL,	DMA_BIDIRECTIONAL);
   DEFINE(DMA_TO_DEVICE,		DMA_TO_DEVICE);
@@ -190,5 +194,9 @@
   DEFINE(MPU_RGN_PRBAR,	offsetof(struct mpu_rgn, prbar));
   DEFINE(MPU_RGN_PRLAR,	offsetof(struct mpu_rgn, prlar));
 #endif
+  DEFINE(KEXEC_START_ADDR,	offsetof(struct kexec_relocate_data, kexec_start_address));
+  DEFINE(KEXEC_INDIR_PAGE,	offsetof(struct kexec_relocate_data, kexec_indirection_page));
+  DEFINE(KEXEC_MACH_TYPE,	offsetof(struct kexec_relocate_data, kexec_mach_type));
+  DEFINE(KEXEC_R2,		offsetof(struct kexec_relocate_data, kexec_r2));
   return 0; 
 }
diff --git a/arch/arm/kernel/atags.h b/arch/arm/kernel/atags.h
index 067e12e..f2819c2 100644
--- a/arch/arm/kernel/atags.h
+++ b/arch/arm/kernel/atags.h
@@ -2,11 +2,11 @@
 void convert_to_tag_list(struct tag *tags);
 
 #ifdef CONFIG_ATAGS
-const struct machine_desc *setup_machine_tags(phys_addr_t __atags_pointer,
+const struct machine_desc *setup_machine_tags(void *__atags_vaddr,
 	unsigned int machine_nr);
 #else
 static inline const struct machine_desc * __init __noreturn
-setup_machine_tags(phys_addr_t __atags_pointer, unsigned int machine_nr)
+setup_machine_tags(void *__atags_vaddr, unsigned int machine_nr)
 {
 	early_print("no ATAGS support: can't continue\n");
 	while (true);
diff --git a/arch/arm/kernel/atags_parse.c b/arch/arm/kernel/atags_parse.c
index ce02f92..8288151 100644
--- a/arch/arm/kernel/atags_parse.c
+++ b/arch/arm/kernel/atags_parse.c
@@ -176,7 +176,7 @@
 }
 
 const struct machine_desc * __init
-setup_machine_tags(phys_addr_t __atags_pointer, unsigned int machine_nr)
+setup_machine_tags(void *atags_vaddr, unsigned int machine_nr)
 {
 	struct tag *tags = (struct tag *)&default_tags;
 	const struct machine_desc *mdesc = NULL, *p;
@@ -197,8 +197,8 @@
 	if (!mdesc)
 		return NULL;
 
-	if (__atags_pointer)
-		tags = phys_to_virt(__atags_pointer);
+	if (atags_vaddr)
+		tags = atags_vaddr;
 	else if (mdesc->atag_offset)
 		tags = (void *)(PAGE_OFFSET + mdesc->atag_offset);
 
diff --git a/arch/arm/kernel/devtree.c b/arch/arm/kernel/devtree.c
index 39c9786..4e09883 100644
--- a/arch/arm/kernel/devtree.c
+++ b/arch/arm/kernel/devtree.c
@@ -203,12 +203,12 @@
 
 /**
  * setup_machine_fdt - Machine setup when an dtb was passed to the kernel
- * @dt_phys: physical address of dt blob
+ * @dt_virt: virtual address of dt blob
  *
  * If a dtb was passed to the kernel in r2, then use it to choose the
  * correct machine_desc and to setup the system.
  */
-const struct machine_desc * __init setup_machine_fdt(unsigned int dt_phys)
+const struct machine_desc * __init setup_machine_fdt(void *dt_virt)
 {
 	const struct machine_desc *mdesc, *mdesc_best = NULL;
 
@@ -221,7 +221,7 @@
 	mdesc_best = &__mach_desc_GENERIC_DT;
 #endif
 
-	if (!dt_phys || !early_init_dt_verify(phys_to_virt(dt_phys)))
+	if (!dt_virt || !early_init_dt_verify(dt_virt))
 		return NULL;
 
 	mdesc = of_flat_dt_match_machine(mdesc_best, arch_get_next_mach);
diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S
index 858d4e5..b62d74a 100644
--- a/arch/arm/kernel/entry-armv.S
+++ b/arch/arm/kernel/entry-armv.S
@@ -27,6 +27,7 @@
 #include <asm/unistd.h>
 #include <asm/tls.h>
 #include <asm/system_info.h>
+#include <asm/uaccess-asm.h>
 
 #include "entry-header.S"
 #include <asm/entry-macro-multi.S>
@@ -179,15 +180,7 @@
 	stmia	r7, {r2 - r6}
 
 	get_thread_info tsk
-	ldr	r0, [tsk, #TI_ADDR_LIMIT]
-	mov	r1, #TASK_SIZE
-	str	r1, [tsk, #TI_ADDR_LIMIT]
-	str	r0, [sp, #SVC_ADDR_LIMIT]
-
-	uaccess_save r0
-	.if \uaccess
-	uaccess_disable r0
-	.endif
+	uaccess_entry tsk, r0, r1, r2, \uaccess
 
 	.if \trace
 #ifdef CONFIG_TRACE_IRQFLAGS
@@ -259,31 +252,10 @@
 #else
 	svc_entry
 #endif
-	@
-	@ call emulation code, which returns using r9 if it has emulated
-	@ the instruction, or the more conventional lr if we are to treat
-	@ this as a real undefined instruction
-	@
-	@  r0 - instruction
-	@
-#ifndef CONFIG_THUMB2_KERNEL
-	ldr	r0, [r4, #-4]
-#else
-	mov	r1, #2
-	ldrh	r0, [r4, #-2]			@ Thumb instruction at LR - 2
-	cmp	r0, #0xe800			@ 32-bit instruction if xx >= 0
-	blo	__und_svc_fault
-	ldrh	r9, [r4]			@ bottom 16 bits
-	add	r4, r4, #2
-	str	r4, [sp, #S_PC]
-	orr	r0, r9, r0, lsl #16
-#endif
-	badr	r9, __und_svc_finish
-	mov	r2, r4
-	bl	call_fpe
 
 	mov	r1, #4				@ PC correction to apply
-__und_svc_fault:
+ THUMB(	tst	r5, #PSR_T_BIT		)	@ exception taken in Thumb mode?
+ THUMB(	movne	r1, #2			)	@ if so, fix up PC correction
 	mov	r0, sp				@ struct pt_regs *regs
 	bl	__und_fault
 
diff --git a/arch/arm/kernel/entry-header.S b/arch/arm/kernel/entry-header.S
index 32051ec..40db0f9 100644
--- a/arch/arm/kernel/entry-header.S
+++ b/arch/arm/kernel/entry-header.S
@@ -6,6 +6,7 @@
 #include <asm/asm-offsets.h>
 #include <asm/errno.h>
 #include <asm/thread_info.h>
+#include <asm/uaccess-asm.h>
 #include <asm/v7m.h>
 
 @ Bad Abort numbers
@@ -217,9 +218,7 @@
 	blne	trace_hardirqs_off
 #endif
 	.endif
-	ldr	r1, [sp, #SVC_ADDR_LIMIT]
-	uaccess_restore
-	str	r1, [tsk, #TI_ADDR_LIMIT]
+	uaccess_exit tsk, r0, r1
 
 #ifndef CONFIG_THUMB2_KERNEL
 	@ ARM mode SVC restore
@@ -263,9 +262,7 @@
 	@ on the stack remains correct).
 	@
 	.macro  svc_exit_via_fiq
-	ldr	r1, [sp, #SVC_ADDR_LIMIT]
-	uaccess_restore
-	str	r1, [tsk, #TI_ADDR_LIMIT]
+	uaccess_exit tsk, r0, r1
 #ifndef CONFIG_THUMB2_KERNEL
 	@ ARM mode restore
 	mov	r0, sp
diff --git a/arch/arm/kernel/head.S b/arch/arm/kernel/head.S
index c49b393..5ceed4d 100644
--- a/arch/arm/kernel/head.S
+++ b/arch/arm/kernel/head.S
@@ -274,11 +274,10 @@
 	 * We map 2 sections in case the ATAGs/DTB crosses a section boundary.
 	 */
 	mov	r0, r2, lsr #SECTION_SHIFT
-	movs	r0, r0, lsl #SECTION_SHIFT
-	subne	r3, r0, r8
-	addne	r3, r3, #PAGE_OFFSET
-	addne	r3, r4, r3, lsr #(SECTION_SHIFT - PMD_ORDER)
-	orrne	r6, r7, r0
+	cmp	r2, #0
+	ldrne	r3, =FDT_FIXED_BASE >> (SECTION_SHIFT - PMD_ORDER)
+	addne	r3, r3, r4
+	orrne	r6, r7, r0, lsl #SECTION_SHIFT
 	strne	r6, [r3], #1 << PMD_ORDER
 	addne	r6, r6, #1 << SECTION_SHIFT
 	strne	r6, [r3]
@@ -672,11 +671,7 @@
 	bcc	1b
 	bx	lr
 #else
-#ifdef CONFIG_CPU_ENDIAN_BE8
-	moveq	r0, #0x00004000	@ set bit 22, mov to mvn instruction
-#else
 	moveq	r0, #0x400000	@ set bit 22, mov to mvn instruction
-#endif
 	b	2f
 1:	ldr	ip, [r7, r3]
 #ifdef CONFIG_CPU_ENDIAN_BE8
@@ -685,7 +680,7 @@
 	tst	ip, #0x000f0000	@ check the rotation field
 	orrne	ip, ip, r6, lsl #24 @ mask in offset bits 31-24
 	biceq	ip, ip, #0x00004000 @ clear bit 22
-	orreq	ip, ip, r0      @ mask in offset bits 7-0
+	orreq	ip, ip, r0, ror #8  @ mask in offset bits 7-0
 #else
 	bic	ip, ip, #0x000000ff
 	tst	ip, #0xf00	@ check the rotation field
diff --git a/arch/arm/kernel/hw_breakpoint.c b/arch/arm/kernel/hw_breakpoint.c
index b0c195e..b06d9ea 100644
--- a/arch/arm/kernel/hw_breakpoint.c
+++ b/arch/arm/kernel/hw_breakpoint.c
@@ -680,26 +680,68 @@
 	arch_install_hw_breakpoint(bp);
 }
 
+/*
+ * Arm32 hardware does not always report a watchpoint hit address that matches
+ * one of the watchpoints set. It can also report an address "near" the
+ * watchpoint if a single instruction access both watched and unwatched
+ * addresses. There is no straight-forward way, short of disassembling the
+ * offending instruction, to map that address back to the watchpoint. This
+ * function computes the distance of the memory access from the watchpoint as a
+ * heuristic for the likelyhood that a given access triggered the watchpoint.
+ *
+ * See this same function in the arm64 platform code, which has the same
+ * problem.
+ *
+ * The function returns the distance of the address from the bytes watched by
+ * the watchpoint. In case of an exact match, it returns 0.
+ */
+static u32 get_distance_from_watchpoint(unsigned long addr, u32 val,
+					struct arch_hw_breakpoint_ctrl *ctrl)
+{
+	u32 wp_low, wp_high;
+	u32 lens, lene;
+
+	lens = __ffs(ctrl->len);
+	lene = __fls(ctrl->len);
+
+	wp_low = val + lens;
+	wp_high = val + lene;
+	if (addr < wp_low)
+		return wp_low - addr;
+	else if (addr > wp_high)
+		return addr - wp_high;
+	else
+		return 0;
+}
+
+static int watchpoint_fault_on_uaccess(struct pt_regs *regs,
+				       struct arch_hw_breakpoint *info)
+{
+	return !user_mode(regs) && info->ctrl.privilege == ARM_BREAKPOINT_USER;
+}
+
 static void watchpoint_handler(unsigned long addr, unsigned int fsr,
 			       struct pt_regs *regs)
 {
-	int i, access;
-	u32 val, ctrl_reg, alignment_mask;
+	int i, access, closest_match = 0;
+	u32 min_dist = -1, dist;
+	u32 val, ctrl_reg;
 	struct perf_event *wp, **slots;
 	struct arch_hw_breakpoint *info;
 	struct arch_hw_breakpoint_ctrl ctrl;
 
 	slots = this_cpu_ptr(wp_on_reg);
 
+	/*
+	 * Find all watchpoints that match the reported address. If no exact
+	 * match is found. Attribute the hit to the closest watchpoint.
+	 */
+	rcu_read_lock();
 	for (i = 0; i < core_num_wrps; ++i) {
-		rcu_read_lock();
-
 		wp = slots[i];
-
 		if (wp == NULL)
-			goto unlock;
+			continue;
 
-		info = counter_arch_bp(wp);
 		/*
 		 * The DFAR is an unknown value on debug architectures prior
 		 * to 7.1. Since we only allow a single watchpoint on these
@@ -708,50 +750,69 @@
 		 */
 		if (debug_arch < ARM_DEBUG_ARCH_V7_1) {
 			BUG_ON(i > 0);
+			info = counter_arch_bp(wp);
 			info->trigger = wp->attr.bp_addr;
 		} else {
-			if (info->ctrl.len == ARM_BREAKPOINT_LEN_8)
-				alignment_mask = 0x7;
-			else
-				alignment_mask = 0x3;
-
-			/* Check if the watchpoint value matches. */
-			val = read_wb_reg(ARM_BASE_WVR + i);
-			if (val != (addr & ~alignment_mask))
-				goto unlock;
-
-			/* Possible match, check the byte address select. */
-			ctrl_reg = read_wb_reg(ARM_BASE_WCR + i);
-			decode_ctrl_reg(ctrl_reg, &ctrl);
-			if (!((1 << (addr & alignment_mask)) & ctrl.len))
-				goto unlock;
-
 			/* Check that the access type matches. */
 			if (debug_exception_updates_fsr()) {
 				access = (fsr & ARM_FSR_ACCESS_MASK) ?
 					  HW_BREAKPOINT_W : HW_BREAKPOINT_R;
 				if (!(access & hw_breakpoint_type(wp)))
-					goto unlock;
+					continue;
 			}
 
+			val = read_wb_reg(ARM_BASE_WVR + i);
+			ctrl_reg = read_wb_reg(ARM_BASE_WCR + i);
+			decode_ctrl_reg(ctrl_reg, &ctrl);
+			dist = get_distance_from_watchpoint(addr, val, &ctrl);
+			if (dist < min_dist) {
+				min_dist = dist;
+				closest_match = i;
+			}
+			/* Is this an exact match? */
+			if (dist != 0)
+				continue;
+
 			/* We have a winner. */
+			info = counter_arch_bp(wp);
 			info->trigger = addr;
 		}
 
 		pr_debug("watchpoint fired: address = 0x%x\n", info->trigger);
+
+		/*
+		 * If we triggered a user watchpoint from a uaccess routine,
+		 * then handle the stepping ourselves since userspace really
+		 * can't help us with this.
+		 */
+		if (watchpoint_fault_on_uaccess(regs, info))
+			goto step;
+
 		perf_bp_event(wp, regs);
 
 		/*
-		 * If no overflow handler is present, insert a temporary
-		 * mismatch breakpoint so we can single-step over the
-		 * watchpoint trigger.
+		 * Defer stepping to the overflow handler if one is installed.
+		 * Otherwise, insert a temporary mismatch breakpoint so that
+		 * we can single-step over the watchpoint trigger.
 		 */
+		if (!is_default_overflow_handler(wp))
+			continue;
+step:
+		enable_single_step(wp, instruction_pointer(regs));
+	}
+
+	if (min_dist > 0 && min_dist != -1) {
+		/* No exact match found. */
+		wp = slots[closest_match];
+		info = counter_arch_bp(wp);
+		info->trigger = addr;
+		pr_debug("watchpoint fired: address = 0x%x\n", info->trigger);
+		perf_bp_event(wp, regs);
 		if (is_default_overflow_handler(wp))
 			enable_single_step(wp, instruction_pointer(regs));
-
-unlock:
-		rcu_read_unlock();
 	}
+
+	rcu_read_unlock();
 }
 
 static void watchpoint_single_step_handler(unsigned long pc)
@@ -822,7 +883,7 @@
 			info->trigger = addr;
 			pr_debug("breakpoint fired: address = 0x%x\n", addr);
 			perf_bp_event(bp, regs);
-			if (!bp->overflow_handler)
+			if (is_default_overflow_handler(bp))
 				enable_single_step(bp, addr);
 			goto unlock;
 		}
diff --git a/arch/arm/kernel/hyp-stub.S b/arch/arm/kernel/hyp-stub.S
index ae50203..6607fa8 100644
--- a/arch/arm/kernel/hyp-stub.S
+++ b/arch/arm/kernel/hyp-stub.S
@@ -146,10 +146,9 @@
 #if !defined(ZIMAGE) && defined(CONFIG_ARM_ARCH_TIMER)
 	@ make CNTP_* and CNTPCT accessible from PL1
 	mrc	p15, 0, r7, c0, c1, 1	@ ID_PFR1
-	lsr	r7, #16
-	and	r7, #0xf
-	cmp	r7, #1
-	bne	1f
+	ubfx	r7, r7, #16, #4
+	teq	r7, #0
+	beq	1f
 	mrc	p15, 4, r7, c14, c1, 0	@ CNTHCTL
 	orr	r7, r7, #3		@ PL1PCEN | PL1PCTEN
 	mcr	p15, 4, r7, c14, c1, 0	@ CNTHCTL
diff --git a/arch/arm/kernel/machine_kexec.c b/arch/arm/kernel/machine_kexec.c
index 76300f3..734adeb 100644
--- a/arch/arm/kernel/machine_kexec.c
+++ b/arch/arm/kernel/machine_kexec.c
@@ -15,6 +15,7 @@
 #include <asm/pgalloc.h>
 #include <asm/mmu_context.h>
 #include <asm/cacheflush.h>
+#include <asm/kexec-internal.h>
 #include <asm/fncpy.h>
 #include <asm/mach-types.h>
 #include <asm/smp_plat.h>
@@ -24,11 +25,6 @@
 extern void relocate_new_kernel(void);
 extern const unsigned int relocate_new_kernel_size;
 
-extern unsigned long kexec_start_address;
-extern unsigned long kexec_indirection_page;
-extern unsigned long kexec_mach_type;
-extern unsigned long kexec_boot_atags;
-
 static atomic_t waiting_for_crash_ipi;
 
 /*
@@ -161,6 +157,7 @@
 void machine_kexec(struct kimage *image)
 {
 	unsigned long page_list, reboot_entry_phys;
+	struct kexec_relocate_data *data;
 	void (*reboot_entry)(void);
 	void *reboot_code_buffer;
 
@@ -176,18 +173,17 @@
 
 	reboot_code_buffer = page_address(image->control_code_page);
 
-	/* Prepare parameters for reboot_code_buffer*/
-	set_kernel_text_rw();
-	kexec_start_address = image->start;
-	kexec_indirection_page = page_list;
-	kexec_mach_type = machine_arch_type;
-	kexec_boot_atags = image->arch.kernel_r2;
-
 	/* copy our kernel relocation code to the control code page */
 	reboot_entry = fncpy(reboot_code_buffer,
 			     &relocate_new_kernel,
 			     relocate_new_kernel_size);
 
+	data = reboot_code_buffer + relocate_new_kernel_size;
+	data->kexec_start_address = image->start;
+	data->kexec_indirection_page = page_list;
+	data->kexec_mach_type = machine_arch_type;
+	data->kexec_r2 = image->arch.kernel_r2;
+
 	/* get the identity mapping physical address for the reboot code */
 	reboot_entry_phys = virt_to_idmap(reboot_entry);
 
diff --git a/arch/arm/kernel/perf_event_v7.c b/arch/arm/kernel/perf_event_v7.c
index 2924d79..eb21904 100644
--- a/arch/arm/kernel/perf_event_v7.c
+++ b/arch/arm/kernel/perf_event_v7.c
@@ -773,10 +773,10 @@
 		pr_err("CPU%u writing wrong counter %d\n",
 			smp_processor_id(), idx);
 	} else if (idx == ARMV7_IDX_CYCLE_COUNTER) {
-		asm volatile("mcr p15, 0, %0, c9, c13, 0" : : "r" (value));
+		asm volatile("mcr p15, 0, %0, c9, c13, 0" : : "r" ((u32)value));
 	} else {
 		armv7_pmnc_select_counter(idx);
-		asm volatile("mcr p15, 0, %0, c9, c13, 2" : : "r" (value));
+		asm volatile("mcr p15, 0, %0, c9, c13, 2" : : "r" ((u32)value));
 	}
 }
 
diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c
index 9485acc..e7fac12 100644
--- a/arch/arm/kernel/process.c
+++ b/arch/arm/kernel/process.c
@@ -224,8 +224,8 @@
 asmlinkage void ret_from_fork(void) __asm__("ret_from_fork");
 
 int
-copy_thread(unsigned long clone_flags, unsigned long stack_start,
-	    unsigned long stk_sz, struct task_struct *p)
+copy_thread_tls(unsigned long clone_flags, unsigned long stack_start,
+	    unsigned long stk_sz, struct task_struct *p, unsigned long tls)
 {
 	struct thread_info *thread = task_thread_info(p);
 	struct pt_regs *childregs = task_pt_regs(p);
@@ -259,7 +259,7 @@
 	clear_ptrace_hw_breakpoint(p);
 
 	if (clone_flags & CLONE_SETTLS)
-		thread->tp_value[0] = childregs->ARM_r3;
+		thread->tp_value[0] = tls;
 	thread->tp_value[1] = get_tpuser();
 
 	thread_notify(THREAD_NOTIFY_COPY, thread);
diff --git a/arch/arm/kernel/ptrace.c b/arch/arm/kernel/ptrace.c
index 3243527..db94015 100644
--- a/arch/arm/kernel/ptrace.c
+++ b/arch/arm/kernel/ptrace.c
@@ -219,8 +219,8 @@
 };
 
 static struct undef_hook thumb_break_hook = {
-	.instr_mask	= 0xffff,
-	.instr_val	= 0xde01,
+	.instr_mask	= 0xffffffff,
+	.instr_val	= 0x0000de01,
 	.cpsr_mask	= PSR_T_BIT,
 	.cpsr_val	= PSR_T_BIT,
 	.fn		= break_trap,
diff --git a/arch/arm/kernel/relocate_kernel.S b/arch/arm/kernel/relocate_kernel.S
index 7eaa2ae..5e15b59 100644
--- a/arch/arm/kernel/relocate_kernel.S
+++ b/arch/arm/kernel/relocate_kernel.S
@@ -5,14 +5,16 @@
 
 #include <linux/linkage.h>
 #include <asm/assembler.h>
+#include <asm/asm-offsets.h>
 #include <asm/kexec.h>
 
 	.align	3	/* not needed for this code, but keeps fncpy() happy */
 
 ENTRY(relocate_new_kernel)
 
-	ldr	r0,kexec_indirection_page
-	ldr	r1,kexec_start_address
+	adr	r7, relocate_new_kernel_end
+	ldr	r0, [r7, #KEXEC_INDIR_PAGE]
+	ldr	r1, [r7, #KEXEC_START_ADDR]
 
 	/*
 	 * If there is no indirection page (we are doing crashdumps)
@@ -57,34 +59,16 @@
 
 2:
 	/* Jump to relocated kernel */
-	mov lr,r1
-	mov r0,#0
-	ldr r1,kexec_mach_type
-	ldr r2,kexec_boot_atags
- ARM(	ret lr	)
- THUMB(	bx lr		)
-
-	.align
-
-	.globl kexec_start_address
-kexec_start_address:
-	.long	0x0
-
-	.globl kexec_indirection_page
-kexec_indirection_page:
-	.long	0x0
-
-	.globl kexec_mach_type
-kexec_mach_type:
-	.long	0x0
-
-	/* phy addr of the atags for the new kernel */
-	.globl kexec_boot_atags
-kexec_boot_atags:
-	.long	0x0
+	mov	lr, r1
+	mov	r0, #0
+	ldr	r1, [r7, #KEXEC_MACH_TYPE]
+	ldr	r2, [r7, #KEXEC_R2]
+ ARM(	ret	lr	)
+ THUMB(	bx	lr	)
 
 ENDPROC(relocate_new_kernel)
 
+	.align	3
 relocate_new_kernel_end:
 
 	.globl relocate_new_kernel_size
diff --git a/arch/arm/kernel/return_address.c b/arch/arm/kernel/return_address.c
index b0d2f1f..7b42ac0 100644
--- a/arch/arm/kernel/return_address.c
+++ b/arch/arm/kernel/return_address.c
@@ -7,8 +7,6 @@
  */
 #include <linux/export.h>
 #include <linux/ftrace.h>
-
-#if defined(CONFIG_FRAME_POINTER) && !defined(CONFIG_ARM_UNWIND)
 #include <linux/sched.h>
 
 #include <asm/stacktrace.h>
@@ -53,6 +51,4 @@
 		return NULL;
 }
 
-#endif /* if defined(CONFIG_FRAME_POINTER) && !defined(CONFIG_ARM_UNWIND) */
-
 EXPORT_SYMBOL_GPL(return_address);
diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c
index d0a464e..43d6a60 100644
--- a/arch/arm/kernel/setup.c
+++ b/arch/arm/kernel/setup.c
@@ -18,6 +18,7 @@
 #include <linux/of_platform.h>
 #include <linux/init.h>
 #include <linux/kexec.h>
+#include <linux/libfdt.h>
 #include <linux/of_fdt.h>
 #include <linux/cpu.h>
 #include <linux/interrupt.h>
@@ -543,9 +544,11 @@
 	 * In Thumb-2, msr with an immediate value is not allowed.
 	 */
 #ifdef CONFIG_THUMB2_KERNEL
-#define PLC	"r"
+#define PLC_l	"l"
+#define PLC_r	"r"
 #else
-#define PLC	"I"
+#define PLC_l	"I"
+#define PLC_r	"I"
 #endif
 
 	/*
@@ -567,15 +570,15 @@
 	"msr	cpsr_c, %9"
 	    :
 	    : "r" (stk),
-	      PLC (PSR_F_BIT | PSR_I_BIT | IRQ_MODE),
+	      PLC_r (PSR_F_BIT | PSR_I_BIT | IRQ_MODE),
 	      "I" (offsetof(struct stack, irq[0])),
-	      PLC (PSR_F_BIT | PSR_I_BIT | ABT_MODE),
+	      PLC_r (PSR_F_BIT | PSR_I_BIT | ABT_MODE),
 	      "I" (offsetof(struct stack, abt[0])),
-	      PLC (PSR_F_BIT | PSR_I_BIT | UND_MODE),
+	      PLC_r (PSR_F_BIT | PSR_I_BIT | UND_MODE),
 	      "I" (offsetof(struct stack, und[0])),
-	      PLC (PSR_F_BIT | PSR_I_BIT | FIQ_MODE),
+	      PLC_r (PSR_F_BIT | PSR_I_BIT | FIQ_MODE),
 	      "I" (offsetof(struct stack, fiq[0])),
-	      PLC (PSR_F_BIT | PSR_I_BIT | SVC_MODE)
+	      PLC_l (PSR_F_BIT | PSR_I_BIT | SVC_MODE)
 	    : "r14");
 #endif
 }
@@ -1075,19 +1078,27 @@
 
 void __init setup_arch(char **cmdline_p)
 {
-	const struct machine_desc *mdesc;
+	const struct machine_desc *mdesc = NULL;
+	void *atags_vaddr = NULL;
+
+	if (__atags_pointer)
+		atags_vaddr = FDT_VIRT_BASE(__atags_pointer);
 
 	setup_processor();
-	mdesc = setup_machine_fdt(__atags_pointer);
+	if (atags_vaddr) {
+		mdesc = setup_machine_fdt(atags_vaddr);
+		if (mdesc)
+			memblock_reserve(__atags_pointer,
+					 fdt_totalsize(atags_vaddr));
+	}
 	if (!mdesc)
-		mdesc = setup_machine_tags(__atags_pointer, __machine_arch_type);
+		mdesc = setup_machine_tags(atags_vaddr, __machine_arch_type);
 	if (!mdesc) {
 		early_print("\nError: invalid dtb and unrecognized/unsupported machine ID\n");
 		early_print("  r1=0x%08x, r2=0x%08x\n", __machine_arch_type,
 			    __atags_pointer);
 		if (__atags_pointer)
-			early_print("  r2[]=%*ph\n", 16,
-				    phys_to_virt(__atags_pointer));
+			early_print("  r2[]=%*ph\n", 16, atags_vaddr);
 		dump_machine_table();
 	}
 
diff --git a/arch/arm/kernel/signal.c b/arch/arm/kernel/signal.c
index ab25689..c01f76c 100644
--- a/arch/arm/kernel/signal.c
+++ b/arch/arm/kernel/signal.c
@@ -694,18 +694,20 @@
 
 	addr = page_address(page);
 
+	/* Poison the entire page */
+	memset32(addr, __opcode_to_mem_arm(0xe7fddef1),
+		 PAGE_SIZE / sizeof(u32));
+
 	/* Give the signal return code some randomness */
 	offset = 0x200 + (get_random_int() & 0x7fc);
 	signal_return_offset = offset;
 
-	/*
-	 * Copy signal return handlers into the vector page, and
-	 * set sigreturn to be a pointer to these.
-	 */
+	/* Copy signal return handlers into the page */
 	memcpy(addr + offset, sigreturn_codes, sizeof(sigreturn_codes));
 
-	ptr = (unsigned long)addr + offset;
-	flush_icache_range(ptr, ptr + sizeof(sigreturn_codes));
+	/* Flush out all instructions in this page */
+	ptr = (unsigned long)addr;
+	flush_icache_range(ptr, ptr + PAGE_SIZE);
 
 	return page;
 }
diff --git a/arch/arm/kernel/smccc-call.S b/arch/arm/kernel/smccc-call.S
index 00664c7..931df62 100644
--- a/arch/arm/kernel/smccc-call.S
+++ b/arch/arm/kernel/smccc-call.S
@@ -3,7 +3,9 @@
  * Copyright (c) 2015, Linaro Limited
  */
 #include <linux/linkage.h>
+#include <linux/arm-smccc.h>
 
+#include <asm/asm-offsets.h>
 #include <asm/opcodes-sec.h>
 #include <asm/opcodes-virt.h>
 #include <asm/unwind.h>
@@ -27,7 +29,14 @@
 UNWIND(	.save	{r4-r7})
 	ldm	r12, {r4-r7}
 	\instr
-	pop	{r4-r7}
+	ldr	r4, [sp, #36]
+	cmp	r4, #0
+	beq	1f			// No quirk structure
+	ldr     r5, [r4, #ARM_SMCCC_QUIRK_ID_OFFS]
+	cmp     r5, #ARM_SMCCC_QUIRK_QCOM_A6
+	bne	1f			// No quirk present
+	str	r6, [r4, #ARM_SMCCC_QUIRK_STATE_OFFS]
+1:	pop	{r4-r7}
 	ldr	r12, [sp, #(4 * 4)]
 	stm	r12, {r0-r3}
 	bx	lr
diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c
index 4b0bab2..46e1be9 100644
--- a/arch/arm/kernel/smp.c
+++ b/arch/arm/kernel/smp.c
@@ -240,6 +240,10 @@
 	if (ret)
 		return ret;
 
+#ifdef CONFIG_GENERIC_ARCH_TOPOLOGY
+	remove_cpu_topology(cpu);
+#endif
+
 	/*
 	 * Take this CPU offline.  Once we clear this, we can't return,
 	 * and we must not schedule until we're ready to give up the cpu.
diff --git a/arch/arm/kernel/stacktrace.c b/arch/arm/kernel/stacktrace.c
index 71778bb..76ea417 100644
--- a/arch/arm/kernel/stacktrace.c
+++ b/arch/arm/kernel/stacktrace.c
@@ -22,6 +22,19 @@
  * A simple function epilogue looks like this:
  *	ldm	sp, {fp, sp, pc}
  *
+ * When compiled with clang, pc and sp are not pushed. A simple function
+ * prologue looks like this when built with clang:
+ *
+ *	stmdb	{..., fp, lr}
+ *	add	fp, sp, #x
+ *	sub	sp, sp, #y
+ *
+ * A simple function epilogue looks like this when built with clang:
+ *
+ *	sub	sp, fp, #x
+ *	ldm	{..., fp, pc}
+ *
+ *
  * Note that with framepointer enabled, even the leaf functions have the same
  * prologue and epilogue, therefore we can ignore the LR value in this case.
  */
@@ -34,6 +47,16 @@
 	low = frame->sp;
 	high = ALIGN(low, THREAD_SIZE);
 
+#ifdef CONFIG_CC_IS_CLANG
+	/* check current frame pointer is within bounds */
+	if (fp < low + 4 || fp > high - 4)
+		return -EINVAL;
+
+	frame->sp = frame->fp;
+	frame->fp = *(unsigned long *)(fp);
+	frame->pc = frame->lr;
+	frame->lr = *(unsigned long *)(fp + 4);
+#else
 	/* check current frame pointer is within bounds */
 	if (fp < low + 12 || fp > high - 4)
 		return -EINVAL;
@@ -42,6 +65,7 @@
 	frame->fp = *(unsigned long *)(fp - 12);
 	frame->sp = *(unsigned long *)(fp - 8);
 	frame->pc = *(unsigned long *)(fp - 4);
+#endif
 
 	return 0;
 }
@@ -92,6 +116,8 @@
 		return 0;
 
 	regs = (struct pt_regs *)frame->sp;
+	if ((unsigned long)&regs[1] > ALIGN(frame->sp, THREAD_SIZE))
+		return 0;
 
 	trace->entries[trace->nr_entries++] = regs->ARM_pc;
 
diff --git a/arch/arm/kernel/suspend.c b/arch/arm/kernel/suspend.c
index d080992..e126386 100644
--- a/arch/arm/kernel/suspend.c
+++ b/arch/arm/kernel/suspend.c
@@ -1,4 +1,5 @@
 // SPDX-License-Identifier: GPL-2.0
+#include <linux/ftrace.h>
 #include <linux/init.h>
 #include <linux/slab.h>
 #include <linux/mm_types.h>
@@ -27,12 +28,22 @@
 		return -EINVAL;
 
 	/*
+	 * Function graph tracer state gets incosistent when the kernel
+	 * calls functions that never return (aka suspend finishers) hence
+	 * disable graph tracing during their execution.
+	 */
+	pause_graph_tracing();
+
+	/*
 	 * Provide a temporary page table with an identity mapping for
 	 * the MMU-enable code, required for resuming.  On successful
 	 * resume (indicated by a zero return code), we need to switch
 	 * back to the correct page tables.
 	 */
 	ret = __cpu_suspend(arg, fn, __mpidr);
+
+	unpause_graph_tracing();
+
 	if (ret == 0) {
 		cpu_switch_mm(mm->pgd, mm);
 		local_flush_bp_all();
@@ -46,7 +57,13 @@
 int cpu_suspend(unsigned long arg, int (*fn)(unsigned long))
 {
 	u32 __mpidr = cpu_logical_map(smp_processor_id());
-	return __cpu_suspend(arg, fn, __mpidr);
+	int ret;
+
+	pause_graph_tracing();
+	ret = __cpu_suspend(arg, fn, __mpidr);
+	unpause_graph_tracing();
+
+	return ret;
 }
 #define	idmap_pgd	NULL
 #endif
diff --git a/arch/arm/kernel/topology.c b/arch/arm/kernel/topology.c
index 5b9faba..8d2e61d 100644
--- a/arch/arm/kernel/topology.c
+++ b/arch/arm/kernel/topology.c
@@ -196,9 +196,8 @@
 	struct cpu_topology *cpuid_topo = &cpu_topology[cpuid];
 	unsigned int mpidr;
 
-	/* If the cpu topology has been already set, just return */
-	if (cpuid_topo->core_id != -1)
-		return;
+	if (cpuid_topo->package_id != -1)
+		goto topology_populated;
 
 	mpidr = read_cpuid_mpidr();
 
@@ -231,14 +230,15 @@
 		cpuid_topo->package_id = -1;
 	}
 
-	update_siblings_masks(cpuid);
-
 	update_cpu_capacity(cpuid);
 
 	pr_info("CPU%u: thread %d, cpu %d, socket %d, mpidr %x\n",
 		cpuid, cpu_topology[cpuid].thread_id,
 		cpu_topology[cpuid].core_id,
 		cpu_topology[cpuid].package_id, mpidr);
+
+topology_populated:
+	update_siblings_masks(cpuid);
 }
 
 static inline int cpu_corepower_flags(void)
diff --git a/arch/arm/kernel/traps.c b/arch/arm/kernel/traps.c
index c053abd..97a5125 100644
--- a/arch/arm/kernel/traps.c
+++ b/arch/arm/kernel/traps.c
@@ -64,14 +64,16 @@
 
 void dump_backtrace_entry(unsigned long where, unsigned long from, unsigned long frame)
 {
+	unsigned long end = frame + 4 + sizeof(struct pt_regs);
+
 #ifdef CONFIG_KALLSYMS
 	printk("[<%08lx>] (%ps) from [<%08lx>] (%pS)\n", where, (void *)where, from, (void *)from);
 #else
 	printk("Function entered at [<%08lx>] from [<%08lx>]\n", where, from);
 #endif
 
-	if (in_entry_text(from))
-		dump_mem("", "Exception stack", frame + 4, frame + 4 + sizeof(struct pt_regs));
+	if (in_entry_text(from) && end <= ALIGN(frame, THREAD_SIZE))
+		dump_mem("", "Exception stack", frame + 4, end);
 }
 
 void dump_backtrace_stm(u32 *stack, u32 instruction)
diff --git a/arch/arm/kernel/vdso.c b/arch/arm/kernel/vdso.c
index 9bf16c9..6c69a55 100644
--- a/arch/arm/kernel/vdso.c
+++ b/arch/arm/kernel/vdso.c
@@ -93,6 +93,8 @@
 	 */
 	np = of_find_compatible_node(NULL, NULL, "arm,armv7-timer");
 	if (!np)
+		np = of_find_compatible_node(NULL, NULL, "arm,armv8-timer");
+	if (!np)
 		goto out_put;
 
 	if (of_property_read_bool(np, "arm,cpu-registers-not-fw-configured"))
@@ -279,7 +281,7 @@
 	if (!IS_ENABLED(CONFIG_ARM_ARCH_TIMER))
 		return false;
 
-	if (!tk->tkr_mono.clock->archdata.vdso_direct)
+	if (tk->tkr_mono.clock->archdata.clock_mode != VDSO_CLOCKMODE_ARCHTIMER)
 		return false;
 
 	return true;