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

Pull arm64 updates from Catalin Marinas:
 "No major architecture features this time around, just some new HWCAP
  definitions, support for the Ampere SoC PMUs and a few fixes/cleanups.

  The bulk of the changes is reworking of the CPU capability checking
  code (cpus_have_cap() etc).

   - Major refactoring of the CPU capability detection logic resulting
     in the removal of the cpus_have_const_cap() function and migrating
     the code to "alternative" branches where possible

   - Backtrace/kgdb: use IPIs and pseudo-NMI

   - Perf and PMU:

      - Add support for Ampere SoC PMUs

      - Multi-DTC improvements for larger CMN configurations with
        multiple Debug & Trace Controllers

      - Rework the Arm CoreSight PMU driver to allow separate
        registration of vendor backend modules

      - Fixes: add missing MODULE_DEVICE_TABLE to the amlogic perf
        driver; use device_get_match_data() in the xgene driver; fix
        NULL pointer dereference in the hisi driver caused by calling
        cpuhp_state_remove_instance(); use-after-free in the hisi driver

   - HWCAP updates:

      - FEAT_SVE_B16B16 (BFloat16)

      - FEAT_LRCPC3 (release consistency model)

      - FEAT_LSE128 (128-bit atomic instructions)

   - SVE: remove a couple of pseudo registers from the cpufeature code.
     There is logic in place already to detect mismatched SVE features

   - Miscellaneous:

      - Reduce the default swiotlb size (currently 64MB) if no ZONE_DMA
        bouncing is needed. The buffer is still required for small
        kmalloc() buffers

      - Fix module PLT counting with !RANDOMIZE_BASE

      - Restrict CPU_BIG_ENDIAN to LLVM IAS 15.x or newer move
        synchronisation code out of the set_ptes() loop

      - More compact cpufeature displaying enabled cores

      - Kselftest updates for the new CPU features"

 * tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (83 commits)
  arm64: Restrict CPU_BIG_ENDIAN to GNU as or LLVM IAS 15.x or newer
  arm64: module: Fix PLT counting when CONFIG_RANDOMIZE_BASE=n
  arm64, irqchip/gic-v3, ACPI: Move MADT GICC enabled check into a helper
  perf: hisi: Fix use-after-free when register pmu fails
  drivers/perf: hisi_pcie: Initialize event->cpu only on success
  drivers/perf: hisi_pcie: Check the type first in pmu::event_init()
  arm64: cpufeature: Change DBM to display enabled cores
  arm64: cpufeature: Display the set of cores with a feature
  perf/arm-cmn: Enable per-DTC counter allocation
  perf/arm-cmn: Rework DTC counters (again)
  perf/arm-cmn: Fix DTC domain detection
  drivers: perf: arm_pmuv3: Drop some unused arguments from armv8_pmu_init()
  drivers: perf: arm_pmuv3: Read PMMIR_EL1 unconditionally
  drivers/perf: hisi: use cpuhp_state_remove_instance_nocalls() for hisi_hns3_pmu uninit process
  clocksource/drivers/arm_arch_timer: limit XGene-1 workaround
  arm64: Remove system_uses_lse_atomics()
  arm64: Mark the 'addr' argument to set_ptes() and __set_pte_at() as unused
  drivers/perf: xgene: Use device_get_match_data()
  perf/amlogic: add missing MODULE_DEVICE_TABLE
  arm64/mm: Hoist synchronization out of set_ptes() loop
  ...

6 files changed, 15 insertions, 9 deletions

diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index 2e5d1e238af9..460d799e1296 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -571,7 +571,7 @@ static int __kprobes do_page_fault(unsigned long far, unsigned long esr,
 		/* Write implies read */
 		vm_flags |= VM_WRITE;
 		/* If EPAN is absent then exec implies read */
-		if (!cpus_have_const_cap(ARM64_HAS_EPAN))
+		if (!alternative_has_cap_unlikely(ARM64_HAS_EPAN))
 			vm_flags |= VM_EXEC;
 	}
 
diff --git a/arch/arm64/mm/hugetlbpage.c b/arch/arm64/mm/hugetlbpage.c
index 13fd592228b1..f5aae342632c 100644
--- a/arch/arm64/mm/hugetlbpage.c
+++ b/arch/arm64/mm/hugetlbpage.c
@@ -544,8 +544,7 @@ bool __init arch_hugetlb_valid_size(unsigned long size)
 
 pte_t huge_ptep_modify_prot_start(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep)
 {
-	if (IS_ENABLED(CONFIG_ARM64_ERRATUM_2645198) &&
-	    cpus_have_const_cap(ARM64_WORKAROUND_2645198)) {
+	if (alternative_has_cap_unlikely(ARM64_WORKAROUND_2645198)) {
 		/*
 		 * Break-before-make (BBM) is required for all user space mappings
 		 * when the permission changes from executable to non-executable
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index 8a0f8604348b..8deec68028ac 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -16,6 +16,7 @@
 #include <linux/nodemask.h>
 #include <linux/initrd.h>
 #include <linux/gfp.h>
+#include <linux/math.h>
 #include <linux/memblock.h>
 #include <linux/sort.h>
 #include <linux/of.h>
@@ -493,8 +494,16 @@ void __init mem_init(void)
 {
 	bool swiotlb = max_pfn > PFN_DOWN(arm64_dma_phys_limit);
 
-	if (IS_ENABLED(CONFIG_DMA_BOUNCE_UNALIGNED_KMALLOC))
+	if (IS_ENABLED(CONFIG_DMA_BOUNCE_UNALIGNED_KMALLOC) && !swiotlb) {
+		/*
+		 * If no bouncing needed for ZONE_DMA, reduce the swiotlb
+		 * buffer for kmalloc() bouncing to 1MB per 1GB of RAM.
+		 */
+		unsigned long size =
+			DIV_ROUND_UP(memblock_phys_mem_size(), 1024);
+		swiotlb_adjust_size(min(swiotlb_size_or_default(), size));
 		swiotlb = true;
+	}
 
 	swiotlb_init(swiotlb, SWIOTLB_VERBOSE);
 
diff --git a/arch/arm64/mm/mmap.c b/arch/arm64/mm/mmap.c
index 8f5b7ce857ed..645fe60d000f 100644
--- a/arch/arm64/mm/mmap.c
+++ b/arch/arm64/mm/mmap.c
@@ -68,7 +68,7 @@ static int __init adjust_protection_map(void)
 	 * With Enhanced PAN we can honour the execute-only permissions as
 	 * there is no PAN override with such mappings.
 	 */
-	if (cpus_have_const_cap(ARM64_HAS_EPAN)) {
+	if (cpus_have_cap(ARM64_HAS_EPAN)) {
 		protection_map[VM_EXEC] = PAGE_EXECONLY;
 		protection_map[VM_EXEC | VM_SHARED] = PAGE_EXECONLY;
 	}
diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index 47781bec6171..15f6347d23b6 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -1469,8 +1469,7 @@ early_initcall(prevent_bootmem_remove_init);
 
 pte_t ptep_modify_prot_start(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep)
 {
-	if (IS_ENABLED(CONFIG_ARM64_ERRATUM_2645198) &&
-	    cpus_have_const_cap(ARM64_WORKAROUND_2645198)) {
+	if (alternative_has_cap_unlikely(ARM64_WORKAROUND_2645198)) {
 		/*
 		 * Break-before-make (BBM) is required for all user space mappings
 		 * when the permission changes from executable to non-executable
diff --git a/arch/arm64/mm/proc.S b/arch/arm64/mm/proc.S
index 14fdf645edc8..f66c37a1610e 100644
--- a/arch/arm64/mm/proc.S
+++ b/arch/arm64/mm/proc.S
@@ -405,8 +405,7 @@ SYM_FUNC_START(__cpu_setup)
 	tlbi	vmalle1				// Invalidate local TLB
 	dsb	nsh
 
-	mov	x1, #3 << 20
-	msr	cpacr_el1, x1			// Enable FP/ASIMD
+	msr	cpacr_el1, xzr			// Reset cpacr_el1
 	mov	x1, #1 << 12			// Reset mdscr_el1 and disable
 	msr	mdscr_el1, x1			// access to the DCC from EL0
 	isb					// Unmask debug exceptions now,