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

Pull arm64 updates from Catalin Marinas:

 - arm64 perf: DDR PMU driver for Alibaba's T-Head Yitian 710 SoC, SVE
   vector granule register added to the user regs together with SVE perf
   extensions documentation.

 - SVE updates: add HWCAP for SVE EBF16, update the SVE ABI
   documentation to match the actual kernel behaviour (zeroing the
   registers on syscall rather than "zeroed or preserved" previously).

 - More conversions to automatic system registers generation.

 - vDSO: use self-synchronising virtual counter access in gettimeofday()
   if the architecture supports it.

 - arm64 stacktrace cleanups and improvements.

 - arm64 atomics improvements: always inline assembly, remove LL/SC
   trampolines.

 - Improve the reporting of EL1 exceptions: rework BTI and FPAC
   exception handling, better EL1 undefs reporting.

 - Cortex-A510 erratum 2658417: remove BF16 support due to incorrect
   result.

 - arm64 defconfig updates: build CoreSight as a module, enable options
   necessary for docker, memory hotplug/hotremove, enable all PMUs
   provided by Arm.

 - arm64 ptrace() support for TPIDR2_EL0 (register provided with the SME
   extensions).

 - arm64 ftraces updates/fixes: fix module PLTs with mcount, remove
   unused function.

 - kselftest updates for arm64: simple HWCAP validation, FP stress test
   improvements, validation of ZA regs in signal handlers, include
   larger SVE and SME vector lengths in signal tests, various cleanups.

 - arm64 alternatives (code patching) improvements to robustness and
   consistency: replace cpucap static branches with equivalent
   alternatives, associate callback alternatives with a cpucap.

 - Miscellaneous updates: optimise kprobe performance of patching
   single-step slots, simplify uaccess_mask_ptr(), move MTE registers
   initialisation to C, support huge vmalloc() mappings, run softirqs on
   the per-CPU IRQ stack, compat (arm32) misalignment fixups for
   multiword accesses.

* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (126 commits)
  arm64: alternatives: Use vdso/bits.h instead of linux/bits.h
  arm64/kprobe: Optimize the performance of patching single-step slot
  arm64: defconfig: Add Coresight as module
  kselftest/arm64: Handle EINTR while reading data from children
  kselftest/arm64: Flag fp-stress as exiting when we begin finishing up
  kselftest/arm64: Don't repeat termination handler for fp-stress
  ARM64: reloc_test: add __init/__exit annotations to module init/exit funcs
  arm64/mm: fold check for KFENCE into can_set_direct_map()
  arm64: ftrace: fix module PLTs with mcount
  arm64: module: Remove unused plt_entry_is_initialized()
  arm64: module: Make plt_equals_entry() static
  arm64: fix the build with binutils 2.27
  kselftest/arm64: Don't enable v8.5 for MTE selftest builds
  arm64: uaccess: simplify uaccess_mask_ptr()
  arm64: asm/perf_regs.h: Avoid C++-style comment in UAPI header
  kselftest/arm64: Fix typo in hwcap check
  arm64: mte: move register initialization to C
  arm64: mm: handle ARM64_KERNEL_USES_PMD_MAPS in vmemmap_populate()
  arm64: dma: Drop cache invalidation from arch_dma_prep_coherent()
  arm64/sve: Add Perf extensions documentation
  ...

arch/arm64/kernel/ptrace.c

@@ -121,7 +121,7 @@ static bool regs_within_kernel_stack(struct pt_regs *regs, unsigned long addr)
 {
 	return ((addr & ~(THREAD_SIZE - 1))  ==
 		(kernel_stack_pointer(regs) & ~(THREAD_SIZE - 1))) ||
-		on_irq_stack(addr, sizeof(unsigned long), NULL);
+		on_irq_stack(addr, sizeof(unsigned long));
 }
 
 /**
@@ -666,10 +666,18 @@ static int fpr_set(struct task_struct *target, const struct user_regset *regset,
 static int tls_get(struct task_struct *target, const struct user_regset *regset,
 		   struct membuf to)
 {
+	int ret;
+
 	if (target == current)
 		tls_preserve_current_state();
 
-	return membuf_store(&to, target->thread.uw.tp_value);
+	ret = membuf_store(&to, target->thread.uw.tp_value);
+	if (system_supports_tpidr2())
+		ret = membuf_store(&to, target->thread.tpidr2_el0);
+	else
+		ret = membuf_zero(&to, sizeof(u64));
+
+	return ret;
 }
 
 static int tls_set(struct task_struct *target, const struct user_regset *regset,
@@ -677,13 +685,20 @@ static int tls_set(struct task_struct *target, const struct user_regset *regset,
 		   const void *kbuf, const void __user *ubuf)
 {
 	int ret;
-	unsigned long tls = target->thread.uw.tp_value;
+	unsigned long tls[2];
 
-	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &tls, 0, -1);
+	tls[0] = target->thread.uw.tp_value;
+	if (system_supports_sme())
+		tls[1] = target->thread.tpidr2_el0;
+
+	ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, tls, 0, count);
 	if (ret)
 		return ret;
 
-	target->thread.uw.tp_value = tls;
+	target->thread.uw.tp_value = tls[0];
+	if (system_supports_sme())
+		target->thread.tpidr2_el0 = tls[1];
+
 	return ret;
 }
 
@@ -1390,7 +1405,7 @@ static const struct user_regset aarch64_regsets[] = {
 	},
 	[REGSET_TLS] = {
 		.core_note_type = NT_ARM_TLS,
-		.n = 1,
+		.n = 2,
 		.size = sizeof(void *),
 		.align = sizeof(void *),
 		.regset_get = tls_get,