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
  ...

1 files changed, 55 insertions, 7 deletions

diff --git a/arch/arm/kernel/ftrace.c b/arch/arm/kernel/ftrace.c
index a006585e1c09..83cc068586bc 100644
--- a/arch/arm/kernel/ftrace.c
+++ b/arch/arm/kernel/ftrace.c
@@ -22,12 +22,24 @@
 #include <asm/ftrace.h>
 #include <asm/insn.h>
 #include <asm/set_memory.h>
+#include <asm/stacktrace.h>
 #include <asm/patch.h>
 
+/*
+ * The compiler emitted profiling hook consists of
+ *
+ *   PUSH    {LR}
+ *   BL	     __gnu_mcount_nc
+ *
+ * To turn this combined sequence into a NOP, we need to restore the value of
+ * SP before the PUSH. Let's use an ADD rather than a POP into LR, as LR is not
+ * modified anyway, and reloading LR from memory is highly likely to be less
+ * efficient.
+ */
 #ifdef CONFIG_THUMB2_KERNEL
-#define	NOP		0xf85deb04	/* pop.w {lr} */
+#define	NOP		0xf10d0d04	/* add.w sp, sp, #4 */
 #else
-#define	NOP		0xe8bd4000	/* pop {lr} */
+#define	NOP		0xe28dd004	/* add   sp, sp, #4 */
 #endif
 
 #ifdef CONFIG_DYNAMIC_FTRACE
@@ -51,9 +63,20 @@ static unsigned long ftrace_nop_replace(struct dyn_ftrace *rec)
 	return NOP;
 }
 
-static unsigned long adjust_address(struct dyn_ftrace *rec, unsigned long addr)
+void ftrace_caller_from_init(void);
+void ftrace_regs_caller_from_init(void);
+
+static unsigned long __ref adjust_address(struct dyn_ftrace *rec,
+					  unsigned long addr)
 {
-	return addr;
+	if (!IS_ENABLED(CONFIG_DYNAMIC_FTRACE) ||
+	    system_state >= SYSTEM_FREEING_INITMEM ||
+	    likely(!is_kernel_inittext(rec->ip)))
+		return addr;
+	if (!IS_ENABLED(CONFIG_DYNAMIC_FTRACE_WITH_REGS) ||
+	    addr == (unsigned long)&ftrace_caller)
+		return (unsigned long)&ftrace_caller_from_init;
+	return (unsigned long)&ftrace_regs_caller_from_init;
 }
 
 int ftrace_arch_code_modify_prepare(void)
@@ -189,15 +212,23 @@ int ftrace_make_nop(struct module *mod,
 #endif
 
 	new = ftrace_nop_replace(rec);
-	ret = ftrace_modify_code(ip, old, new, true);
+	/*
+	 * Locations in .init.text may call __gnu_mcount_mc via a linker
+	 * emitted veneer if they are too far away from its implementation, and
+	 * so validation may fail spuriously in such cases. Let's work around
+	 * this by omitting those from validation.
+	 */
+	ret = ftrace_modify_code(ip, old, new, !is_kernel_inittext(ip));
 
 	return ret;
 }
 #endif /* CONFIG_DYNAMIC_FTRACE */
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
+asmlinkage
 void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr,
-			   unsigned long frame_pointer)
+			   unsigned long frame_pointer,
+			   unsigned long stack_pointer)
 {
 	unsigned long return_hooker = (unsigned long) &return_to_handler;
 	unsigned long old;
@@ -205,6 +236,23 @@ void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr,
 	if (unlikely(atomic_read(&current->tracing_graph_pause)))
 		return;
 
+	if (IS_ENABLED(CONFIG_UNWINDER_FRAME_POINTER)) {
+		/* FP points one word below parent's top of stack */
+		frame_pointer += 4;
+	} else {
+		struct stackframe frame = {
+			.fp = frame_pointer,
+			.sp = stack_pointer,
+			.lr = self_addr,
+			.pc = self_addr,
+		};
+		if (unwind_frame(&frame) < 0)
+			return;
+		if (frame.lr != self_addr)
+			parent = frame.lr_addr;
+		frame_pointer = frame.sp;
+	}
+
 	old = *parent;
 	*parent = return_hooker;
 
@@ -225,7 +273,7 @@ static int __ftrace_modify_caller(unsigned long *callsite,
 	unsigned long caller_fn = (unsigned long) func;
 	unsigned long pc = (unsigned long) callsite;
 	unsigned long branch = arm_gen_branch(pc, caller_fn);
-	unsigned long nop = 0xe1a00000;	/* mov r0, r0 */
+	unsigned long nop = arm_gen_nop();
 	unsigned long old = enable ? nop : branch;
 	unsigned long new = enable ? branch : nop;