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

Pull arm64 updates from Will Deacon:

 - Support for including MTE tags in ELF coredumps

 - Instruction encoder updates, including fixes to 64-bit immediate
   generation and support for the LSE atomic instructions

 - Improvements to kselftests for MTE and fpsimd

 - Symbol aliasing and linker script cleanups

 - Reduce instruction cache maintenance performed for user mappings
   created using contiguous PTEs

 - Support for the new "asymmetric" MTE mode, where stores are checked
   asynchronously but loads are checked synchronously

 - Support for the latest pointer authentication algorithm ("QARMA3")

 - Support for the DDR PMU present in the Marvell CN10K platform

 - Support for the CPU PMU present in the Apple M1 platform

 - Use the RNDR instruction for arch_get_random_{int,long}()

 - Update our copy of the Arm optimised string routines for str{n}cmp()

 - Fix signal frame generation for CPUs which have foolishly elected to
   avoid building in support for the fpsimd instructions

 - Workaround for Marvell GICv3 erratum #38545

 - Clarification to our Documentation (booting reqs. and MTE prctl())

 - Miscellanous cleanups and minor fixes

* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (90 commits)
  docs: sysfs-devices-system-cpu: document "asymm" value for mte_tcf_preferred
  arm64/mte: Remove asymmetric mode from the prctl() interface
  arm64: Add cavium_erratum_23154_cpus missing sentinel
  perf/marvell: Fix !CONFIG_OF build for CN10K DDR PMU driver
  arm64: mm: Drop 'const' from conditional arm64_dma_phys_limit definition
  Documentation: vmcoreinfo: Fix htmldocs warning
  kasan: fix a missing header include of static_keys.h
  drivers/perf: Add Apple icestorm/firestorm CPU PMU driver
  drivers/perf: arm_pmu: Handle 47 bit counters
  arm64: perf: Consistently make all event numbers as 16-bits
  arm64: perf: Expose some Armv9 common events under sysfs
  perf/marvell: cn10k DDR perf event core ownership
  perf/marvell: cn10k DDR perfmon event overflow handling
  perf/marvell: CN10k DDR performance monitor support
  dt-bindings: perf: marvell: cn10k ddr performance monitor
  arm64: clean up tools Makefile
  perf/arm-cmn: Update watchpoint format
  perf/arm-cmn: Hide XP PUB events for CMN-600
  arm64: drop unused includes of <linux/personality.h>
  arm64: Do not defer reserve_crashkernel() for platforms with no DMA memory zones
  ...

7 files changed, 122 insertions, 54 deletions

diff --git a/arch/arm64/mm/cache.S b/arch/arm64/mm/cache.S
index 7d0563db4201..0ea6cc25dc66 100644
--- a/arch/arm64/mm/cache.S
+++ b/arch/arm64/mm/cache.S
@@ -107,10 +107,11 @@ SYM_FUNC_END(icache_inval_pou)
  *	- start   - virtual start address of region
  *	- end     - virtual end address of region
  */
-SYM_FUNC_START_PI(dcache_clean_inval_poc)
+SYM_FUNC_START(__pi_dcache_clean_inval_poc)
 	dcache_by_line_op civac, sy, x0, x1, x2, x3
 	ret
-SYM_FUNC_END_PI(dcache_clean_inval_poc)
+SYM_FUNC_END(__pi_dcache_clean_inval_poc)
+SYM_FUNC_ALIAS(dcache_clean_inval_poc, __pi_dcache_clean_inval_poc)
 
 /*
  *	dcache_clean_pou(start, end)
@@ -140,7 +141,7 @@ SYM_FUNC_END(dcache_clean_pou)
  *	- start   - kernel start address of region
  *	- end     - kernel end address of region
  */
-SYM_FUNC_START_PI(dcache_inval_poc)
+SYM_FUNC_START(__pi_dcache_inval_poc)
 	dcache_line_size x2, x3
 	sub	x3, x2, #1
 	tst	x1, x3				// end cache line aligned?
@@ -158,7 +159,8 @@ SYM_FUNC_START_PI(dcache_inval_poc)
 	b.lo	2b
 	dsb	sy
 	ret
-SYM_FUNC_END_PI(dcache_inval_poc)
+SYM_FUNC_END(__pi_dcache_inval_poc)
+SYM_FUNC_ALIAS(dcache_inval_poc, __pi_dcache_inval_poc)
 
 /*
  *	dcache_clean_poc(start, end)
@@ -169,10 +171,11 @@ SYM_FUNC_END_PI(dcache_inval_poc)
  *	- start   - virtual start address of region
  *	- end     - virtual end address of region
  */
-SYM_FUNC_START_PI(dcache_clean_poc)
+SYM_FUNC_START(__pi_dcache_clean_poc)
 	dcache_by_line_op cvac, sy, x0, x1, x2, x3
 	ret
-SYM_FUNC_END_PI(dcache_clean_poc)
+SYM_FUNC_END(__pi_dcache_clean_poc)
+SYM_FUNC_ALIAS(dcache_clean_poc, __pi_dcache_clean_poc)
 
 /*
  *	dcache_clean_pop(start, end)
@@ -183,13 +186,14 @@ SYM_FUNC_END_PI(dcache_clean_poc)
  *	- start   - virtual start address of region
  *	- end     - virtual end address of region
  */
-SYM_FUNC_START_PI(dcache_clean_pop)
+SYM_FUNC_START(__pi_dcache_clean_pop)
 	alternative_if_not ARM64_HAS_DCPOP
 	b	dcache_clean_poc
 	alternative_else_nop_endif
 	dcache_by_line_op cvap, sy, x0, x1, x2, x3
 	ret
-SYM_FUNC_END_PI(dcache_clean_pop)
+SYM_FUNC_END(__pi_dcache_clean_pop)
+SYM_FUNC_ALIAS(dcache_clean_pop, __pi_dcache_clean_pop)
 
 /*
  *	__dma_flush_area(start, size)
@@ -199,11 +203,12 @@ SYM_FUNC_END_PI(dcache_clean_pop)
  *	- start   - virtual start address of region
  *	- size    - size in question
  */
-SYM_FUNC_START_PI(__dma_flush_area)
+SYM_FUNC_START(__pi___dma_flush_area)
 	add	x1, x0, x1
 	dcache_by_line_op civac, sy, x0, x1, x2, x3
 	ret
-SYM_FUNC_END_PI(__dma_flush_area)
+SYM_FUNC_END(__pi___dma_flush_area)
+SYM_FUNC_ALIAS(__dma_flush_area, __pi___dma_flush_area)
 
 /*
  *	__dma_map_area(start, size, dir)
@@ -211,12 +216,13 @@ SYM_FUNC_END_PI(__dma_flush_area)
  *	- size	- size of region
  *	- dir	- DMA direction
  */
-SYM_FUNC_START_PI(__dma_map_area)
+SYM_FUNC_START(__pi___dma_map_area)
 	add	x1, x0, x1
 	cmp	w2, #DMA_FROM_DEVICE
 	b.eq	__pi_dcache_inval_poc
 	b	__pi_dcache_clean_poc
-SYM_FUNC_END_PI(__dma_map_area)
+SYM_FUNC_END(__pi___dma_map_area)
+SYM_FUNC_ALIAS(__dma_map_area, __pi___dma_map_area)
 
 /*
  *	__dma_unmap_area(start, size, dir)
@@ -224,9 +230,10 @@ SYM_FUNC_END_PI(__dma_map_area)
  *	- size	- size of region
  *	- dir	- DMA direction
  */
-SYM_FUNC_START_PI(__dma_unmap_area)
+SYM_FUNC_START(__pi___dma_unmap_area)
 	add	x1, x0, x1
 	cmp	w2, #DMA_TO_DEVICE
 	b.ne	__pi_dcache_inval_poc
 	ret
-SYM_FUNC_END_PI(__dma_unmap_area)
+SYM_FUNC_END(__pi___dma_unmap_area)
+SYM_FUNC_ALIAS(__dma_unmap_area, __pi___dma_unmap_area)
diff --git a/arch/arm64/mm/flush.c b/arch/arm64/mm/flush.c
index 2aaf950b906c..a06c6ac770d4 100644
--- a/arch/arm64/mm/flush.c
+++ b/arch/arm64/mm/flush.c
@@ -52,6 +52,13 @@ void __sync_icache_dcache(pte_t pte)
 {
 	struct page *page = pte_page(pte);
 
+	/*
+	 * HugeTLB pages are always fully mapped, so only setting head page's
+	 * PG_dcache_clean flag is enough.
+	 */
+	if (PageHuge(page))
+		page = compound_head(page);
+
 	if (!test_bit(PG_dcache_clean, &page->flags)) {
 		sync_icache_aliases((unsigned long)page_address(page),
 				    (unsigned long)page_address(page) +
diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c
index ffb9c229610a..a33aba91ad89 100644
--- a/arch/arm64/mm/hugetlbpage.c
+++ b/arch/arm64/mm/hugetlbpage.c
@@ -56,25 +56,34 @@ void __init arm64_hugetlb_cma_reserve(void)
 }
 #endif /* CONFIG_CMA */
 
-#ifdef CONFIG_ARCH_ENABLE_HUGEPAGE_MIGRATION
-bool arch_hugetlb_migration_supported(struct hstate *h)
+static bool __hugetlb_valid_size(unsigned long size)
 {
-	size_t pagesize = huge_page_size(h);
-
-	switch (pagesize) {
+	switch (size) {
 #ifndef __PAGETABLE_PMD_FOLDED
 	case PUD_SIZE:
 		return pud_sect_supported();
 #endif
-	case PMD_SIZE:
 	case CONT_PMD_SIZE:
+	case PMD_SIZE:
 	case CONT_PTE_SIZE:
 		return true;
 	}
-	pr_warn("%s: unrecognized huge page size 0x%lx\n",
-			__func__, pagesize);
+
 	return false;
 }
+
+#ifdef CONFIG_ARCH_ENABLE_HUGEPAGE_MIGRATION
+bool arch_hugetlb_migration_supported(struct hstate *h)
+{
+	size_t pagesize = huge_page_size(h);
+
+	if (!__hugetlb_valid_size(pagesize)) {
+		pr_warn("%s: unrecognized huge page size 0x%lx\n",
+			__func__, pagesize);
+		return false;
+	}
+	return true;
+}
 #endif
 
 int pmd_huge(pmd_t pmd)
@@ -506,16 +515,5 @@ arch_initcall(hugetlbpage_init);
 
 bool __init arch_hugetlb_valid_size(unsigned long size)
 {
-	switch (size) {
-#ifndef __PAGETABLE_PMD_FOLDED
-	case PUD_SIZE:
-		return pud_sect_supported();
-#endif
-	case CONT_PMD_SIZE:
-	case PMD_SIZE:
-	case CONT_PTE_SIZE:
-		return true;
-	}
-
-	return false;
+	return __hugetlb_valid_size(size);
 }
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index db63cc885771..9e26ec80d317 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -61,8 +61,34 @@ EXPORT_SYMBOL(memstart_addr);
  * unless restricted on specific platforms (e.g. 30-bit on Raspberry Pi 4).
  * In such case, ZONE_DMA32 covers the rest of the 32-bit addressable memory,
  * otherwise it is empty.
+ *
+ * Memory reservation for crash kernel either done early or deferred
+ * depending on DMA memory zones configs (ZONE_DMA) --
+ *
+ * In absence of ZONE_DMA configs arm64_dma_phys_limit initialized
+ * here instead of max_zone_phys().  This lets early reservation of
+ * crash kernel memory which has a dependency on arm64_dma_phys_limit.
+ * Reserving memory early for crash kernel allows linear creation of block
+ * mappings (greater than page-granularity) for all the memory bank rangs.
+ * In this scheme a comparatively quicker boot is observed.
+ *
+ * If ZONE_DMA configs are defined, crash kernel memory reservation
+ * is delayed until DMA zone memory range size initilazation performed in
+ * zone_sizes_init().  The defer is necessary to steer clear of DMA zone
+ * memory range to avoid overlap allocation.  So crash kernel memory boundaries
+ * are not known when mapping all bank memory ranges, which otherwise means
+ * not possible to exclude crash kernel range from creating block mappings
+ * so page-granularity mappings are created for the entire memory range.
+ * Hence a slightly slower boot is observed.
+ *
+ * Note: Page-granularity mapppings are necessary for crash kernel memory
+ * range for shrinking its size via /sys/kernel/kexec_crash_size interface.
  */
-phys_addr_t arm64_dma_phys_limit __ro_after_init;
+#if IS_ENABLED(CONFIG_ZONE_DMA) || IS_ENABLED(CONFIG_ZONE_DMA32)
+phys_addr_t __ro_after_init arm64_dma_phys_limit;
+#else
+phys_addr_t __ro_after_init arm64_dma_phys_limit = PHYS_MASK + 1;
+#endif
 
 #ifdef CONFIG_KEXEC_CORE
 /*
@@ -153,8 +179,6 @@ static void __init zone_sizes_init(unsigned long min, unsigned long max)
 	if (!arm64_dma_phys_limit)
 		arm64_dma_phys_limit = dma32_phys_limit;
 #endif
-	if (!arm64_dma_phys_limit)
-		arm64_dma_phys_limit = PHYS_MASK + 1;
 	max_zone_pfns[ZONE_NORMAL] = max;
 
 	free_area_init(max_zone_pfns);
@@ -315,6 +339,9 @@ void __init arm64_memblock_init(void)
 
 	early_init_fdt_scan_reserved_mem();
 
+	if (!IS_ENABLED(CONFIG_ZONE_DMA) && !IS_ENABLED(CONFIG_ZONE_DMA32))
+		reserve_crashkernel();
+
 	high_memory = __va(memblock_end_of_DRAM() - 1) + 1;
 }
 
@@ -361,7 +388,8 @@ void __init bootmem_init(void)
 	 * request_standard_resources() depends on crashkernel's memory being
 	 * reserved, so do it here.
 	 */
-	reserve_crashkernel();
+	if (IS_ENABLED(CONFIG_ZONE_DMA) || IS_ENABLED(CONFIG_ZONE_DMA32))
+		reserve_crashkernel();
 
 	memblock_dump_all();
 }
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index 49abbf43bf35..0b7d25887ec3 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -63,6 +63,7 @@ static pmd_t bm_pmd[PTRS_PER_PMD] __page_aligned_bss __maybe_unused;
 static pud_t bm_pud[PTRS_PER_PUD] __page_aligned_bss __maybe_unused;
 
 static DEFINE_SPINLOCK(swapper_pgdir_lock);
+static DEFINE_MUTEX(fixmap_lock);
 
 void set_swapper_pgd(pgd_t *pgdp, pgd_t pgd)
 {
@@ -294,18 +295,6 @@ static void alloc_init_cont_pmd(pud_t *pudp, unsigned long addr,
 	} while (addr = next, addr != end);
 }
 
-static inline bool use_1G_block(unsigned long addr, unsigned long next,
-			unsigned long phys)
-{
-	if (PAGE_SHIFT != 12)
-		return false;
-
-	if (((addr | next | phys) & ~PUD_MASK) != 0)
-		return false;
-
-	return true;
-}
-
 static void alloc_init_pud(pgd_t *pgdp, unsigned long addr, unsigned long end,
 			   phys_addr_t phys, pgprot_t prot,
 			   phys_addr_t (*pgtable_alloc)(int),
@@ -329,6 +318,12 @@ static void alloc_init_pud(pgd_t *pgdp, unsigned long addr, unsigned long end,
 	}
 	BUG_ON(p4d_bad(p4d));
 
+	/*
+	 * No need for locking during early boot. And it doesn't work as
+	 * expected with KASLR enabled.
+	 */
+	if (system_state != SYSTEM_BOOTING)
+		mutex_lock(&fixmap_lock);
 	pudp = pud_set_fixmap_offset(p4dp, addr);
 	do {
 		pud_t old_pud = READ_ONCE(*pudp);
@@ -338,7 +333,8 @@ static void alloc_init_pud(pgd_t *pgdp, unsigned long addr, unsigned long end,
 		/*
 		 * For 4K granule only, attempt to put down a 1GB block
 		 */
-		if (use_1G_block(addr, next, phys) &&
+		if (pud_sect_supported() &&
+		   ((addr | next | phys) & ~PUD_MASK) == 0 &&
 		    (flags & NO_BLOCK_MAPPINGS) == 0) {
 			pud_set_huge(pudp, phys, prot);
 
@@ -359,6 +355,8 @@ static void alloc_init_pud(pgd_t *pgdp, unsigned long addr, unsigned long end,
 	} while (pudp++, addr = next, addr != end);
 
 	pud_clear_fixmap();
+	if (system_state != SYSTEM_BOOTING)
+		mutex_unlock(&fixmap_lock);
 }
 
 static void __create_pgd_mapping(pgd_t *pgdir, phys_addr_t phys,
@@ -517,7 +515,7 @@ 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() || crash_mem_map || IS_ENABLED(CONFIG_KFENCE))
+	if (can_set_direct_map() || IS_ENABLED(CONFIG_KFENCE))
 		flags |= NO_BLOCK_MAPPINGS | NO_CONT_MAPPINGS;
 
 	/*
@@ -528,6 +526,17 @@ static void __init map_mem(pgd_t *pgdp)
 	 */
 	memblock_mark_nomap(kernel_start, kernel_end - kernel_start);
 
+#ifdef CONFIG_KEXEC_CORE
+	if (crash_mem_map) {
+		if (IS_ENABLED(CONFIG_ZONE_DMA) ||
+		    IS_ENABLED(CONFIG_ZONE_DMA32))
+			flags |= NO_BLOCK_MAPPINGS | NO_CONT_MAPPINGS;
+		else if (crashk_res.end)
+			memblock_mark_nomap(crashk_res.start,
+			    resource_size(&crashk_res));
+	}
+#endif
+
 	/* map all the memory banks */
 	for_each_mem_range(i, &start, &end) {
 		if (start >= end)
@@ -554,6 +563,25 @@ static void __init map_mem(pgd_t *pgdp)
 	__map_memblock(pgdp, kernel_start, kernel_end,
 		       PAGE_KERNEL, NO_CONT_MAPPINGS);
 	memblock_clear_nomap(kernel_start, kernel_end - kernel_start);
+
+	/*
+	 * Use page-level mappings here so that we can shrink the region
+	 * in page granularity and put back unused memory to buddy system
+	 * through /sys/kernel/kexec_crash_size interface.
+	 */
+#ifdef CONFIG_KEXEC_CORE
+	if (crash_mem_map &&
+	    !IS_ENABLED(CONFIG_ZONE_DMA) && !IS_ENABLED(CONFIG_ZONE_DMA32)) {
+		if (crashk_res.end) {
+			__map_memblock(pgdp, crashk_res.start,
+				       crashk_res.end + 1,
+				       PAGE_KERNEL,
+				       NO_BLOCK_MAPPINGS | NO_CONT_MAPPINGS);
+			memblock_clear_nomap(crashk_res.start,
+					     resource_size(&crashk_res));
+		}
+	}
+#endif
 }
 
 void mark_rodata_ro(void)
diff --git a/arch/arm64/mm/mteswap.c b/arch/arm64/mm/mteswap.c
index 7c4ef56265ee..a9e50e930484 100644
--- a/arch/arm64/mm/mteswap.c
+++ b/arch/arm64/mm/mteswap.c
@@ -12,7 +12,7 @@ static DEFINE_XARRAY(mte_pages);
 void *mte_allocate_tag_storage(void)
 {
 	/* tags granule is 16 bytes, 2 tags stored per byte */
-	return kmalloc(PAGE_SIZE / 16 / 2, GFP_KERNEL);
+	return kmalloc(MTE_PAGE_TAG_STORAGE, GFP_KERNEL);
 }
 
 void mte_free_tag_storage(char *storage)
diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S
index d35c90d2e47a..50bbed947bec 100644
--- a/arch/arm64/mm/proc.S
+++ b/arch/arm64/mm/proc.S
@@ -46,7 +46,7 @@
 #endif
 
 #ifdef CONFIG_KASAN_HW_TAGS
-#define TCR_MTE_FLAGS SYS_TCR_EL1_TCMA1 | TCR_TBI1 | TCR_TBID1
+#define TCR_MTE_FLAGS TCR_TCMA1 | TCR_TBI1 | TCR_TBID1
 #else
 /*
  * The mte_zero_clear_page_tags() implementation uses DC GZVA, which relies on