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

Pull arm64 updates from Will Deacon:
 "The headline feature is the re-enablement of support for Arm's
  Scalable Matrix Extension (SME) thanks to a bumper crop of fixes
  from Mark Rutland.

  If matrices aren't your thing, then Ryan's page-table optimisation
  work is much more interesting.

  Summary:

  ACPI, EFI and PSCI:

   - Decouple Arm's "Software Delegated Exception Interface" (SDEI)
     support from the ACPI GHES code so that it can be used by platforms
     booted with device-tree

   - Remove unnecessary per-CPU tracking of the FPSIMD state across EFI
     runtime calls

   - Fix a node refcount imbalance in the PSCI device-tree code

  CPU Features:

   - Ensure register sanitisation is applied to fields in ID_AA64MMFR4

   - Expose AIDR_EL1 to userspace via sysfs, primarily so that KVM
     guests can reliably query the underlying CPU types from the VMM

   - Re-enabling of SME support (CONFIG_ARM64_SME) as a result of fixes
     to our context-switching, signal handling and ptrace code

  Entry code:

   - Hook up TIF_NEED_RESCHED_LAZY so that CONFIG_PREEMPT_LAZY can be
     selected

  Memory management:

   - Prevent BSS exports from being used by the early PI code

   - Propagate level and stride information to the low-level TLB
     invalidation routines when operating on hugetlb entries

   - Use the page-table contiguous hint for vmap() mappings with
     VM_ALLOW_HUGE_VMAP where possible

   - Optimise vmalloc()/vmap() page-table updates to use "lazy MMU mode"
     and hook this up on arm64 so that the trailing DSB (used to publish
     the updates to the hardware walker) can be deferred until the end
     of the mapping operation

   - Extend mmap() randomisation for 52-bit virtual addresses (on par
     with 48-bit addressing) and remove limited support for
     randomisation of the linear map

  Perf and PMUs:

   - Add support for probing the CMN-S3 driver using ACPI

   - Minor driver fixes to the CMN, Arm-NI and amlogic PMU drivers

  Selftests:

   - Fix FPSIMD and SME tests to align with the freshly re-enabled SME
     support

   - Fix default setting of the OUTPUT variable so that tests are
     installed in the right location

  vDSO:

   - Replace raw counter access from inline assembly code with a call to
     the the __arch_counter_get_cntvct() helper function

  Miscellaneous:

   - Add some missing header inclusions to the CCA headers

   - Rework rendering of /proc/cpuinfo to follow the x86-approach and
     avoid repeated buffer expansion (the user-visible format remains
     identical)

   - Remove redundant selection of CONFIG_CRC32

   - Extend early error message when failing to map the device-tree
     blob"

* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (83 commits)
  arm64: cputype: Add cputype definition for HIP12
  arm64: el2_setup.h: Make __init_el2_fgt labels consistent, again
  perf/arm-cmn: Add CMN S3 ACPI binding
  arm64/boot: Disallow BSS exports to startup code
  arm64/boot: Move global CPU override variables out of BSS
  arm64/boot: Move init_pgdir[] and init_idmap_pgdir[] into __pi_ namespace
  perf/arm-cmn: Initialise cmn->cpu earlier
  kselftest/arm64: Set default OUTPUT path when undefined
  arm64: Update comment regarding values in __boot_cpu_mode
  arm64: mm: Drop redundant check in pmd_trans_huge()
  arm64/mm: Re-organise setting up FEAT_S1PIE registers PIRE0_EL1 and PIR_EL1
  arm64/mm: Permit lazy_mmu_mode to be nested
  arm64/mm: Disable barrier batching in interrupt contexts
  arm64/cpuinfo: only show one cpu's info in c_show()
  arm64/mm: Batch barriers when updating kernel mappings
  mm/vmalloc: Enter lazy mmu mode while manipulating vmalloc ptes
  arm64/mm: Support huge pte-mapped pages in vmap
  mm/vmalloc: Gracefully unmap huge ptes
  mm/vmalloc: Warn on improper use of vunmap_range()
  arm64/mm: Hoist barriers out of set_ptes_anysz() loop
  ...

3 files changed, 40 insertions, 38 deletions

diff --git a/tools/testing/selftests/arm64/Makefile b/tools/testing/selftests/arm64/Makefile
index 22029e60eff3..c4c72ee2ef55 100644
--- a/tools/testing/selftests/arm64/Makefile
+++ b/tools/testing/selftests/arm64/Makefile
@@ -21,6 +21,8 @@ CFLAGS += $(KHDR_INCLUDES)
 
 CFLAGS += -I$(top_srcdir)/tools/include
 
+OUTPUT ?= $(CURDIR)
+
 export CFLAGS
 export top_srcdir
 
diff --git a/tools/testing/selftests/arm64/abi/tpidr2.c b/tools/testing/selftests/arm64/abi/tpidr2.c
index 285c47dd42f6..eb19dcc37a75 100644
--- a/tools/testing/selftests/arm64/abi/tpidr2.c
+++ b/tools/testing/selftests/arm64/abi/tpidr2.c
@@ -169,8 +169,10 @@ static int sys_clone(unsigned long clone_flags, unsigned long newsp,
 			   child_tidptr);
 }
 
+#define __STACK_SIZE (8 * 1024 * 1024)
+
 /*
- * If we clone with CLONE_SETTLS then the value in the parent should
+ * If we clone with CLONE_VM then the value in the parent should
  * be unchanged and the child should start with zero and be able to
  * set its own value.
  */
@@ -179,11 +181,19 @@ static int write_clone_read(void)
 	int parent_tid, child_tid;
 	pid_t parent, waiting;
 	int ret, status;
+	void *stack;
 
 	parent = getpid();
 	set_tpidr2(parent);
 
-	ret = sys_clone(CLONE_SETTLS, 0, &parent_tid, 0, &child_tid);
+	stack = malloc(__STACK_SIZE);
+	if (!stack) {
+		putstr("# malloc() failed\n");
+		return 0;
+	}
+
+	ret = sys_clone(CLONE_VM, (unsigned long)stack + __STACK_SIZE,
+			&parent_tid, 0, &child_tid);
 	if (ret == -1) {
 		putstr("# clone() failed\n");
 		putnum(errno);
diff --git a/tools/testing/selftests/arm64/fp/fp-ptrace.c b/tools/testing/selftests/arm64/fp/fp-ptrace.c
index 4930e03a7b99..191c47ca0ed8 100644
--- a/tools/testing/selftests/arm64/fp/fp-ptrace.c
+++ b/tools/testing/selftests/arm64/fp/fp-ptrace.c
@@ -439,10 +439,17 @@ static bool check_ptrace_values_sve(pid_t child, struct test_config *config)
 		pass = false;
 	}
 
-	if (sve->size != SVE_PT_SIZE(vq, sve->flags)) {
-		ksft_print_msg("Mismatch in SVE header size: %d != %lu\n",
-			       sve->size, SVE_PT_SIZE(vq, sve->flags));
-		pass = false;
+	if (svcr_in & SVCR_SM) {
+		if (sve->size != sizeof(sve)) {
+			ksft_print_msg("NT_ARM_SVE reports data with PSTATE.SM\n");
+			pass = false;
+		}
+	} else {
+		if (sve->size != SVE_PT_SIZE(vq, sve->flags)) {
+			ksft_print_msg("Mismatch in SVE header size: %d != %lu\n",
+				       sve->size, SVE_PT_SIZE(vq, sve->flags));
+			pass = false;
+		}
 	}
 
 	/* The registers might be in completely different formats! */
@@ -515,10 +522,17 @@ static bool check_ptrace_values_ssve(pid_t child, struct test_config *config)
 		pass = false;
 	}
 
-	if (sve->size != SVE_PT_SIZE(vq, sve->flags)) {
-		ksft_print_msg("Mismatch in SSVE header size: %d != %lu\n",
-			       sve->size, SVE_PT_SIZE(vq, sve->flags));
-		pass = false;
+	if (!(svcr_in & SVCR_SM)) {
+		if (sve->size != sizeof(sve)) {
+			ksft_print_msg("NT_ARM_SSVE reports data without PSTATE.SM\n");
+			pass = false;
+		}
+	} else {
+		if (sve->size != SVE_PT_SIZE(vq, sve->flags)) {
+			ksft_print_msg("Mismatch in SSVE header size: %d != %lu\n",
+				       sve->size, SVE_PT_SIZE(vq, sve->flags));
+			pass = false;
+		}
 	}
 
 	/* The registers might be in completely different formats! */
@@ -891,18 +905,11 @@ static void set_initial_values(struct test_config *config)
 {
 	int vq = __sve_vq_from_vl(vl_in(config));
 	int sme_vq = __sve_vq_from_vl(config->sme_vl_in);
-	bool sm_change;
 
 	svcr_in = config->svcr_in;
 	svcr_expected = config->svcr_expected;
 	svcr_out = 0;
 
-	if (sme_supported() &&
-	    (svcr_in & SVCR_SM) != (svcr_expected & SVCR_SM))
-		sm_change = true;
-	else
-		sm_change = false;
-
 	fill_random(&v_in, sizeof(v_in));
 	memcpy(v_expected, v_in, sizeof(v_in));
 	memset(v_out, 0, sizeof(v_out));
@@ -953,12 +960,7 @@ static void set_initial_values(struct test_config *config)
 	if (fpmr_supported()) {
 		fill_random(&fpmr_in, sizeof(fpmr_in));
 		fpmr_in &= FPMR_SAFE_BITS;
-
-		/* Entering or exiting streaming mode clears FPMR */
-		if (sm_change)
-			fpmr_expected = 0;
-		else
-			fpmr_expected = fpmr_in;
+		fpmr_expected = fpmr_in;
 	} else {
 		fpmr_in = 0;
 		fpmr_expected = 0;
@@ -1195,18 +1197,8 @@ static void sve_write(pid_t child, struct test_config *config)
 
 static bool za_write_supported(struct test_config *config)
 {
-	if (config->sme_vl_in != config->sme_vl_expected) {
-		/* Changing the SME VL exits streaming mode. */
-		if (config->svcr_expected & SVCR_SM) {
-			return false;
-		}
-	} else {
-		/* Otherwise we can't change streaming mode */
-		if ((config->svcr_in & SVCR_SM) !=
-		    (config->svcr_expected & SVCR_SM)) {
-			return false;
-		}
-	}
+	if ((config->svcr_in & SVCR_SM) != (config->svcr_expected & SVCR_SM))
+		return false;
 
 	return true;
 }
@@ -1224,10 +1216,8 @@ static void za_write_expected(struct test_config *config)
 		memset(zt_expected, 0, sizeof(zt_expected));
 	}
 
-	/* Changing the SME VL flushes ZT, SVE state and exits SM */
+	/* Changing the SME VL flushes ZT, SVE state */
 	if (config->sme_vl_in != config->sme_vl_expected) {
-		svcr_expected &= ~SVCR_SM;
-
 		sve_vq = __sve_vq_from_vl(vl_expected(config));
 		memset(z_expected, 0, __SVE_ZREGS_SIZE(sve_vq));
 		memset(p_expected, 0, __SVE_PREGS_SIZE(sve_vq));