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
  ...

7 files changed, 27 insertions, 63 deletions

diff --git a/arch/arm64/mm/context.c b/arch/arm64/mm/context.c
index b8b4cf0bcf39..e1e0dca01839 100644
--- a/arch/arm64/mm/context.c
+++ b/arch/arm64/mm/context.c
@@ -43,17 +43,17 @@ static u32 get_cpu_asid_bits(void)
 {
 	u32 asid;
 	int fld = cpuid_feature_extract_unsigned_field(read_cpuid(ID_AA64MMFR0_EL1),
-						ID_AA64MMFR0_ASID_SHIFT);
+						ID_AA64MMFR0_EL1_ASIDBITS_SHIFT);
 
 	switch (fld) {
 	default:
 		pr_warn("CPU%d: Unknown ASID size (%d); assuming 8-bit\n",
 					smp_processor_id(),  fld);
 		fallthrough;
-	case ID_AA64MMFR0_ASID_8:
+	case ID_AA64MMFR0_EL1_ASIDBITS_8:
 		asid = 8;
 		break;
-	case ID_AA64MMFR0_ASID_16:
+	case ID_AA64MMFR0_EL1_ASIDBITS_16:
 		asid = 16;
 	}
 
diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c
index 599cf81f5685..83a512a6ff0d 100644
--- a/arch/arm64/mm/dma-mapping.c
+++ b/arch/arm64/mm/dma-mapping.c
@@ -36,7 +36,7 @@ void arch_dma_prep_coherent(struct page *page, size_t size)
 {
 	unsigned long start = (unsigned long)page_address(page);
 
-	dcache_clean_inval_poc(start, start + size);
+	dcache_clean_poc(start, start + size);
 }
 
 #ifdef CONFIG_IOMMU_DMA
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index c33f1fad2745..5b391490e045 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -691,6 +691,9 @@ static int __kprobes do_translation_fault(unsigned long far,
 static int do_alignment_fault(unsigned long far, unsigned long esr,
 			      struct pt_regs *regs)
 {
+	if (IS_ENABLED(CONFIG_COMPAT_ALIGNMENT_FIXUPS) &&
+	    compat_user_mode(regs))
+		return do_compat_alignment_fixup(far, regs);
 	do_bad_area(far, esr, regs);
 	return 0;
 }
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index b9af30be813e..4b4651ee47f2 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -360,7 +360,7 @@ void __init arm64_memblock_init(void)
 		extern u16 memstart_offset_seed;
 		u64 mmfr0 = read_cpuid(ID_AA64MMFR0_EL1);
 		int parange = cpuid_feature_extract_unsigned_field(
-					mmfr0, ID_AA64MMFR0_PARANGE_SHIFT);
+					mmfr0, ID_AA64MMFR0_EL1_PARANGE_SHIFT);
 		s64 range = linear_region_size -
 			    BIT(id_aa64mmfr0_parange_to_phys_shift(parange));
 
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index eb489302c28a..9a7c38965154 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -539,7 +539,7 @@ static void __init map_mem(pgd_t *pgdp)
 	 */
 	BUILD_BUG_ON(pgd_index(direct_map_end - 1) == pgd_index(direct_map_end));
 
-	if (can_set_direct_map() || IS_ENABLED(CONFIG_KFENCE))
+	if (can_set_direct_map())
 		flags |= NO_BLOCK_MAPPINGS | NO_CONT_MAPPINGS;
 
 	/*
@@ -690,7 +690,7 @@ static bool arm64_early_this_cpu_has_bti(void)
 
 	pfr1 = __read_sysreg_by_encoding(SYS_ID_AA64PFR1_EL1);
 	return cpuid_feature_extract_unsigned_field(pfr1,
-						    ID_AA64PFR1_BT_SHIFT);
+						    ID_AA64PFR1_EL1_BT_SHIFT);
 }
 
 /*
@@ -1184,14 +1184,6 @@ static void free_empty_tables(unsigned long addr, unsigned long end,
 }
 #endif
 
-#if !ARM64_KERNEL_USES_PMD_MAPS
-int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node,
-		struct vmem_altmap *altmap)
-{
-	WARN_ON((start < VMEMMAP_START) || (end > VMEMMAP_END));
-	return vmemmap_populate_basepages(start, end, node, altmap);
-}
-#else	/* !ARM64_KERNEL_USES_PMD_MAPS */
 int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node,
 		struct vmem_altmap *altmap)
 {
@@ -1203,6 +1195,10 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node,
 	pmd_t *pmdp;
 
 	WARN_ON((start < VMEMMAP_START) || (end > VMEMMAP_END));
+
+	if (!ARM64_KERNEL_USES_PMD_MAPS)
+		return vmemmap_populate_basepages(start, end, node, altmap);
+
 	do {
 		next = pmd_addr_end(addr, end);
 
@@ -1236,7 +1232,6 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node,
 
 	return 0;
 }
-#endif	/* !ARM64_KERNEL_USES_PMD_MAPS */
 
 #ifdef CONFIG_MEMORY_HOTPLUG
 void vmemmap_free(unsigned long start, unsigned long end,
@@ -1551,11 +1546,7 @@ int arch_add_memory(int nid, u64 start, u64 size,
 
 	VM_BUG_ON(!mhp_range_allowed(start, size, true));
 
-	/*
-	 * KFENCE requires linear map to be mapped at page granularity, so that
-	 * it is possible to protect/unprotect single pages in the KFENCE pool.
-	 */
-	if (can_set_direct_map() || IS_ENABLED(CONFIG_KFENCE))
+	if (can_set_direct_map())
 		flags |= NO_BLOCK_MAPPINGS | NO_CONT_MAPPINGS;
 
 	__create_pgd_mapping(swapper_pg_dir, start, __phys_to_virt(start),
diff --git a/arch/arm64/mm/pageattr.c b/arch/arm64/mm/pageattr.c
index 64e985eaa52d..d107c3d434e2 100644
--- a/arch/arm64/mm/pageattr.c
+++ b/arch/arm64/mm/pageattr.c
@@ -21,7 +21,13 @@ bool rodata_full __ro_after_init = IS_ENABLED(CONFIG_RODATA_FULL_DEFAULT_ENABLED
 
 bool can_set_direct_map(void)
 {
-	return rodata_full || debug_pagealloc_enabled();
+	/*
+	 * rodata_full, DEBUG_PAGEALLOC and KFENCE require linear map to be
+	 * mapped at page granularity, so that it is possible to
+	 * protect/unprotect single pages.
+	 */
+	return rodata_full || debug_pagealloc_enabled() ||
+		IS_ENABLED(CONFIG_KFENCE);
 }
 
 static int change_page_range(pte_t *ptep, unsigned long addr, void *data)
diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S
index 8b9f419fcad9..b9ecbbae1e1a 100644
--- a/arch/arm64/mm/proc.S
+++ b/arch/arm64/mm/proc.S
@@ -49,17 +49,19 @@
 
 #ifdef CONFIG_KASAN_HW_TAGS
 #define TCR_MTE_FLAGS TCR_TCMA1 | TCR_TBI1 | TCR_TBID1
-#else
+#elif defined(CONFIG_ARM64_MTE)
 /*
  * The mte_zero_clear_page_tags() implementation uses DC GZVA, which relies on
  * TBI being enabled at EL1.
  */
 #define TCR_MTE_FLAGS TCR_TBI1 | TCR_TBID1
+#else
+#define TCR_MTE_FLAGS 0
 #endif
 
 /*
  * Default MAIR_EL1. MT_NORMAL_TAGGED is initially mapped as Normal memory and
- * changed during __cpu_setup to Normal Tagged if the system supports MTE.
+ * changed during mte_cpu_setup to Normal Tagged if the system supports MTE.
  */
 #define MAIR_EL1_SET							\
 	(MAIR_ATTRIDX(MAIR_ATTR_DEVICE_nGnRnE, MT_DEVICE_nGnRnE) |	\
@@ -427,46 +429,8 @@ SYM_FUNC_START(__cpu_setup)
 	mov_q	mair, MAIR_EL1_SET
 	mov_q	tcr, TCR_TxSZ(VA_BITS) | TCR_CACHE_FLAGS | TCR_SMP_FLAGS | \
 			TCR_TG_FLAGS | TCR_KASLR_FLAGS | TCR_ASID16 | \
-			TCR_TBI0 | TCR_A1 | TCR_KASAN_SW_FLAGS
-
-#ifdef CONFIG_ARM64_MTE
-	/*
-	 * Update MAIR_EL1, GCR_EL1 and TFSR*_EL1 if MTE is supported
-	 * (ID_AA64PFR1_EL1[11:8] > 1).
-	 */
-	mrs	x10, ID_AA64PFR1_EL1
-	ubfx	x10, x10, #ID_AA64PFR1_MTE_SHIFT, #4
-	cmp	x10, #ID_AA64PFR1_MTE
-	b.lt	1f
-
-	/* Normal Tagged memory type at the corresponding MAIR index */
-	mov	x10, #MAIR_ATTR_NORMAL_TAGGED
-	bfi	mair, x10, #(8 *  MT_NORMAL_TAGGED), #8
+			TCR_TBI0 | TCR_A1 | TCR_KASAN_SW_FLAGS | TCR_MTE_FLAGS
 
-	mov	x10, #KERNEL_GCR_EL1
-	msr_s	SYS_GCR_EL1, x10
-
-	/*
-	 * If GCR_EL1.RRND=1 is implemented the same way as RRND=0, then
-	 * RGSR_EL1.SEED must be non-zero for IRG to produce
-	 * pseudorandom numbers. As RGSR_EL1 is UNKNOWN out of reset, we
-	 * must initialize it.
-	 */
-	mrs	x10, CNTVCT_EL0
-	ands	x10, x10, #SYS_RGSR_EL1_SEED_MASK
-	csinc	x10, x10, xzr, ne
-	lsl	x10, x10, #SYS_RGSR_EL1_SEED_SHIFT
-	msr_s	SYS_RGSR_EL1, x10
-
-	/* clear any pending tag check faults in TFSR*_EL1 */
-	msr_s	SYS_TFSR_EL1, xzr
-	msr_s	SYS_TFSRE0_EL1, xzr
-
-	/* set the TCR_EL1 bits */
-	mov_q	x10, TCR_MTE_FLAGS
-	orr	tcr, tcr, x10
-1:
-#endif
 	tcr_clear_errata_bits tcr, x9, x5
 
 #ifdef CONFIG_ARM64_VA_BITS_52