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

Pull arm64 updates from Catalin Marinas:

 - VMAP_STACK support, allowing the kernel stacks to be allocated in the
   vmalloc space with a guard page for trapping stack overflows. One of
   the patches introduces THREAD_ALIGN and changes the generic
   alloc_thread_stack_node() to use this instead of THREAD_SIZE (no
   functional change for other architectures)

 - Contiguous PTE hugetlb support re-enabled (after being reverted a
   couple of times). We now have the semantics agreed in the generic mm
   layer together with API improvements so that the architecture code
   can detect between contiguous and non-contiguous huge PTEs

 - Initial support for persistent memory on ARM: DC CVAP instruction
   exposed to user space (HWCAP) and the in-kernel pmem API implemented

 - raid6 improvements for arm64: faster algorithm for the delta syndrome
   and implementation of the recovery routines using Neon

 - FP/SIMD refactoring and removal of support for Neon in interrupt
   context. This is in preparation for full SVE support

 - PTE accessors converted from inline asm to cmpxchg so that we can use
   LSE atomics if available (ARMv8.1)

 - Perf support for Cortex-A35 and A73

 - Non-urgent fixes and cleanups

* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (75 commits)
  arm64: cleanup {COMPAT_,}SET_PERSONALITY() macro
  arm64: introduce separated bits for mm_context_t flags
  arm64: hugetlb: Cleanup setup_hugepagesz
  arm64: Re-enable support for contiguous hugepages
  arm64: hugetlb: Override set_huge_swap_pte_at() to support contiguous hugepages
  arm64: hugetlb: Override huge_pte_clear() to support contiguous hugepages
  arm64: hugetlb: Handle swap entries in huge_pte_offset() for contiguous hugepages
  arm64: hugetlb: Add break-before-make logic for contiguous entries
  arm64: hugetlb: Spring clean huge pte accessors
  arm64: hugetlb: Introduce pte_pgprot helper
  arm64: hugetlb: set_huge_pte_at Add WARN_ON on !pte_present
  arm64: kexec: have own crash_smp_send_stop() for crash dump for nonpanic cores
  arm64: dma-mapping: Mark atomic_pool as __ro_after_init
  arm64: dma-mapping: Do not pass data to gen_pool_set_algo()
  arm64: Remove the !CONFIG_ARM64_HW_AFDBM alternative code paths
  arm64: Ignore hardware dirty bit updates in ptep_set_wrprotect()
  arm64: Move PTE_RDONLY bit handling out of set_pte_at()
  kvm: arm64: Convert kvm_set_s2pte_readonly() from inline asm to cmpxchg()
  arm64: Convert pte handling from inline asm to using (cmp)xchg
  arm64: neon/efi: Make EFI fpsimd save/restore variables static
  ...

1 files changed, 10 insertions, 50 deletions

diff --git a/arch/arm64/kernel/stacktrace.c b/arch/arm64/kernel/stacktrace.c
index 09d37d66b630..3144584617e7 100644
--- a/arch/arm64/kernel/stacktrace.c
+++ b/arch/arm64/kernel/stacktrace.c
@@ -42,33 +42,17 @@
  */
 int notrace unwind_frame(struct task_struct *tsk, struct stackframe *frame)
 {
-	unsigned long high, low;
 	unsigned long fp = frame->fp;
-	unsigned long irq_stack_ptr;
+
+	if (fp & 0xf)
+		return -EINVAL;
 
 	if (!tsk)
 		tsk = current;
 
-	/*
-	 * Switching between stacks is valid when tracing current and in
-	 * non-preemptible context.
-	 */
-	if (tsk == current && !preemptible())
-		irq_stack_ptr = IRQ_STACK_PTR(smp_processor_id());
-	else
-		irq_stack_ptr = 0;
-
-	low  = frame->sp;
-	/* irq stacks are not THREAD_SIZE aligned */
-	if (on_irq_stack(frame->sp, raw_smp_processor_id()))
-		high = irq_stack_ptr;
-	else
-		high = ALIGN(low, THREAD_SIZE) - 0x20;
-
-	if (fp < low || fp > high || fp & 0xf)
+	if (!on_accessible_stack(tsk, fp))
 		return -EINVAL;
 
-	frame->sp = fp + 0x10;
 	frame->fp = READ_ONCE_NOCHECK(*(unsigned long *)(fp));
 	frame->pc = READ_ONCE_NOCHECK(*(unsigned long *)(fp + 8));
 
@@ -86,34 +70,13 @@ int notrace unwind_frame(struct task_struct *tsk, struct stackframe *frame)
 #endif /* CONFIG_FUNCTION_GRAPH_TRACER */
 
 	/*
-	 * Check whether we are going to walk through from interrupt stack
-	 * to task stack.
-	 * If we reach the end of the stack - and its an interrupt stack,
-	 * unpack the dummy frame to find the original elr.
-	 *
-	 * Check the frame->fp we read from the bottom of the irq_stack,
-	 * and the original task stack pointer are both in current->stack.
+	 * Frames created upon entry from EL0 have NULL FP and PC values, so
+	 * don't bother reporting these. Frames created by __noreturn functions
+	 * might have a valid FP even if PC is bogus, so only terminate where
+	 * both are NULL.
 	 */
-	if (frame->sp == irq_stack_ptr) {
-		struct pt_regs *irq_args;
-		unsigned long orig_sp = IRQ_STACK_TO_TASK_STACK(irq_stack_ptr);
-
-		if (object_is_on_stack((void *)orig_sp) &&
-		   object_is_on_stack((void *)frame->fp)) {
-			frame->sp = orig_sp;
-
-			/* orig_sp is the saved pt_regs, find the elr */
-			irq_args = (struct pt_regs *)orig_sp;
-			frame->pc = irq_args->pc;
-		} else {
-			/*
-			 * This frame has a non-standard format, and we
-			 * didn't fix it, because the data looked wrong.
-			 * Refuse to output this frame.
-			 */
-			return -EINVAL;
-		}
-	}
+	if (!frame->fp && !frame->pc)
+		return -EINVAL;
 
 	return 0;
 }
@@ -167,7 +130,6 @@ void save_stack_trace_regs(struct pt_regs *regs, struct stack_trace *trace)
 	data.no_sched_functions = 0;
 
 	frame.fp = regs->regs[29];
-	frame.sp = regs->sp;
 	frame.pc = regs->pc;
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 	frame.graph = current->curr_ret_stack;
@@ -192,12 +154,10 @@ void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
 	if (tsk != current) {
 		data.no_sched_functions = 1;
 		frame.fp = thread_saved_fp(tsk);
-		frame.sp = thread_saved_sp(tsk);
 		frame.pc = thread_saved_pc(tsk);
 	} else {
 		data.no_sched_functions = 0;
 		frame.fp = (unsigned long)__builtin_frame_address(0);
-		frame.sp = current_stack_pointer;
 		frame.pc = (unsigned long)save_stack_trace_tsk;
 	}
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER