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

Pull arm64 updates from Will Deacon:
 "There's quite a lot of code here, but much of it is due to the
  addition of a new PMU driver as well as some arm64-specific selftests
  which is an area where we've traditionally been lagging a bit.

  In terms of exciting features, this includes support for the Memory
  Tagging Extension which narrowly missed 5.9, hopefully allowing
  userspace to run with use-after-free detection in production on CPUs
  that support it. Work is ongoing to integrate the feature with KASAN
  for 5.11.

  Another change that I'm excited about (assuming they get the hardware
  right) is preparing the ASID allocator for sharing the CPU page-table
  with the SMMU. Those changes will also come in via Joerg with the
  IOMMU pull.

  We do stray outside of our usual directories in a few places, mostly
  due to core changes required by MTE. Although much of this has been
  Acked, there were a couple of places where we unfortunately didn't get
  any review feedback.

  Other than that, we ran into a handful of minor conflicts in -next,
  but nothing that should post any issues.

  Summary:

   - Userspace support for the Memory Tagging Extension introduced by
     Armv8.5. Kernel support (via KASAN) is likely to follow in 5.11.

   - Selftests for MTE, Pointer Authentication and FPSIMD/SVE context
     switching.

   - Fix and subsequent rewrite of our Spectre mitigations, including
     the addition of support for PR_SPEC_DISABLE_NOEXEC.

   - Support for the Armv8.3 Pointer Authentication enhancements.

   - Support for ASID pinning, which is required when sharing
     page-tables with the SMMU.

   - MM updates, including treating flush_tlb_fix_spurious_fault() as a
     no-op.

   - Perf/PMU driver updates, including addition of the ARM CMN PMU
     driver and also support to handle CPU PMU IRQs as NMIs.

   - Allow prefetchable PCI BARs to be exposed to userspace using normal
     non-cacheable mappings.

   - Implementation of ARCH_STACKWALK for unwinding.

   - Improve reporting of unexpected kernel traps due to BPF JIT
     failure.

   - Improve robustness of user-visible HWCAP strings and their
     corresponding numerical constants.

   - Removal of TEXT_OFFSET.

   - Removal of some unused functions, parameters and prototypes.

   - Removal of MPIDR-based topology detection in favour of firmware
     description.

   - Cleanups to handling of SVE and FPSIMD register state in
     preparation for potential future optimisation of handling across
     syscalls.

   - Cleanups to the SDEI driver in preparation for support in KVM.

   - Miscellaneous cleanups and refactoring work"

* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (148 commits)
  Revert "arm64: initialize per-cpu offsets earlier"
  arm64: random: Remove no longer needed prototypes
  arm64: initialize per-cpu offsets earlier
  kselftest/arm64: Check mte tagged user address in kernel
  kselftest/arm64: Verify KSM page merge for MTE pages
  kselftest/arm64: Verify all different mmap MTE options
  kselftest/arm64: Check forked child mte memory accessibility
  kselftest/arm64: Verify mte tag inclusion via prctl
  kselftest/arm64: Add utilities and a test to validate mte memory
  perf: arm-cmn: Fix conversion specifiers for node type
  perf: arm-cmn: Fix unsigned comparison to less than zero
  arm64: dbm: Invalidate local TLB when setting TCR_EL1.HD
  arm64: mm: Make flush_tlb_fix_spurious_fault() a no-op
  arm64: Add support for PR_SPEC_DISABLE_NOEXEC prctl() option
  arm64: Pull in task_stack_page() to Spectre-v4 mitigation code
  KVM: arm64: Allow patching EL2 vectors even with KASLR is not enabled
  arm64: Get rid of arm64_ssbd_state
  KVM: arm64: Convert ARCH_WORKAROUND_2 to arm64_get_spectre_v4_state()
  KVM: arm64: Get rid of kvm_arm_have_ssbd()
  KVM: arm64: Simplify handling of ARCH_WORKAROUND_2
  ...

7 files changed, 40 insertions, 1 deletions

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index da397779a6d4..ec0f0cc49545 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -2370,6 +2370,9 @@ static void __split_huge_page_tail(struct page *head, int tail,
 			 (1L << PG_workingset) |
 			 (1L << PG_locked) |
 			 (1L << PG_unevictable) |
+#ifdef CONFIG_64BIT
+			 (1L << PG_arch_2) |
+#endif
 			 (1L << PG_dirty)));
 
 	/* ->mapping in first tail page is compound_mapcount */
diff --git a/mm/mmap.c b/mm/mmap.c
index bdd19f5b994e..f793eb72a060 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -1816,6 +1816,15 @@ unsigned long mmap_region(struct file *file, unsigned long addr,
 		vma_set_anonymous(vma);
 	}
 
+	/* Allow architectures to sanity-check the vm_flags */
+	if (!arch_validate_flags(vma->vm_flags)) {
+		error = -EINVAL;
+		if (file)
+			goto unmap_and_free_vma;
+		else
+			goto free_vma;
+	}
+
 	vma_link(mm, vma, prev, rb_link, rb_parent);
 	/* Once vma denies write, undo our temporary denial count */
 	if (file) {
diff --git a/mm/mprotect.c b/mm/mprotect.c
index ce8b8a5eacbb..56c02beb6041 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -603,6 +603,12 @@ static int do_mprotect_pkey(unsigned long start, size_t len,
 			goto out;
 		}
 
+		/* Allow architectures to sanity-check the new flags */
+		if (!arch_validate_flags(newflags)) {
+			error = -EINVAL;
+			goto out;
+		}
+
 		error = security_file_mprotect(vma, reqprot, prot);
 		if (error)
 			goto out;
diff --git a/mm/page_io.c b/mm/page_io.c
index e485a6e8a6cd..4ca28aad0d94 100644
--- a/mm/page_io.c
+++ b/mm/page_io.c
@@ -252,6 +252,16 @@ int swap_writepage(struct page *page, struct writeback_control *wbc)
 		unlock_page(page);
 		goto out;
 	}
+	/*
+	 * Arch code may have to preserve more data than just the page
+	 * contents, e.g. memory tags.
+	 */
+	ret = arch_prepare_to_swap(page);
+	if (ret) {
+		set_page_dirty(page);
+		unlock_page(page);
+		goto out;
+	}
 	if (frontswap_store(page) == 0) {
 		set_page_writeback(page);
 		unlock_page(page);
diff --git a/mm/shmem.c b/mm/shmem.c
index 8e2b35ba93ad..d42c27e4769f 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -1736,6 +1736,12 @@ static int shmem_swapin_page(struct inode *inode, pgoff_t index,
 	}
 	wait_on_page_writeback(page);
 
+	/*
+	 * Some architectures may have to restore extra metadata to the
+	 * physical page after reading from swap.
+	 */
+	arch_swap_restore(swap, page);
+
 	if (shmem_should_replace_page(page, gfp)) {
 		error = shmem_replace_page(&page, gfp, info, index);
 		if (error)
@@ -2269,6 +2275,9 @@ static int shmem_mmap(struct file *file, struct vm_area_struct *vma)
 			vma->vm_flags &= ~(VM_MAYWRITE);
 	}
 
+	/* arm64 - allow memory tagging on RAM-based files */
+	vma->vm_flags |= VM_MTE_ALLOWED;
+
 	file_accessed(file);
 	vma->vm_ops = &shmem_vm_ops;
 	if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) &&
diff --git a/mm/swapfile.c b/mm/swapfile.c
index debc94155f74..4951f5339a2f 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -717,6 +717,7 @@ static void swap_range_free(struct swap_info_struct *si, unsigned long offset,
 	else
 		swap_slot_free_notify = NULL;
 	while (offset <= end) {
+		arch_swap_invalidate_page(si->type, offset);
 		frontswap_invalidate_page(si->type, offset);
 		if (swap_slot_free_notify)
 			swap_slot_free_notify(si->bdev, offset);
@@ -2682,6 +2683,7 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile)
 	frontswap_map = frontswap_map_get(p);
 	spin_unlock(&p->lock);
 	spin_unlock(&swap_lock);
+	arch_swap_invalidate_area(p->type);
 	frontswap_invalidate_area(p->type);
 	frontswap_map_set(p, NULL);
 	mutex_unlock(&swapon_mutex);
diff --git a/mm/util.c b/mm/util.c
index 5ef378a2a038..4e21fe7eae27 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -957,7 +957,7 @@ out:
 	return res;
 }
 
-int memcmp_pages(struct page *page1, struct page *page2)
+int __weak memcmp_pages(struct page *page1, struct page *page2)
 {
 	char *addr1, *addr2;
 	int ret;