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

Pull arm64 updates from Catalin Marinas:
 "Apart from the arm64-specific bits (core arch and perf, new arm64
  selftests), it touches the generic cow_user_page() (reviewed by
  Kirill) together with a macro for x86 to preserve the existing
  behaviour on this architecture.

  Summary:

   - On ARMv8 CPUs without hardware updates of the access flag, avoid
     failing cow_user_page() on PFN mappings if the pte is old. The
     patches introduce an arch_faults_on_old_pte() macro, defined as
     false on x86. When true, cow_user_page() makes the pte young before
     attempting __copy_from_user_inatomic().

   - Covert the synchronous exception handling paths in
     arch/arm64/kernel/entry.S to C.

   - FTRACE_WITH_REGS support for arm64.

   - ZONE_DMA re-introduced on arm64 to support Raspberry Pi 4

   - Several kselftest cases specific to arm64, together with a
     MAINTAINERS update for these files (moved to the ARM64 PORT entry).

   - Workaround for a Neoverse-N1 erratum where the CPU may fetch stale
     instructions under certain conditions.

   - Workaround for Cortex-A57 and A72 errata where the CPU may
     speculatively execute an AT instruction and associate a VMID with
     the wrong guest page tables (corrupting the TLB).

   - Perf updates for arm64: additional PMU topologies on HiSilicon
     platforms, support for CCN-512 interconnect, AXI ID filtering in
     the IMX8 DDR PMU, support for the CCPI2 uncore PMU in ThunderX2.

   - GICv3 optimisation to avoid a heavy barrier when accessing the
     ICC_PMR_EL1 register.

   - ELF HWCAP documentation updates and clean-up.

   - SMC calling convention conduit code clean-up.

   - KASLR diagnostics printed during boot

   - NVIDIA Carmel CPU added to the KPTI whitelist

   - Some arm64 mm clean-ups: use generic free_initrd_mem(), remove
     stale macro, simplify calculation in __create_pgd_mapping(), typos.

   - Kconfig clean-ups: CMDLINE_FORCE to depend on CMDLINE, choice for
     endinanness to help with allmodconfig"

* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (93 commits)
  arm64: Kconfig: add a choice for endianness
  kselftest: arm64: fix spelling mistake "contiguos" -> "contiguous"
  arm64: Kconfig: make CMDLINE_FORCE depend on CMDLINE
  MAINTAINERS: Add arm64 selftests to the ARM64 PORT entry
  arm64: kaslr: Check command line before looking for a seed
  arm64: kaslr: Announce KASLR status on boot
  kselftest: arm64: fake_sigreturn_misaligned_sp
  kselftest: arm64: fake_sigreturn_bad_size
  kselftest: arm64: fake_sigreturn_duplicated_fpsimd
  kselftest: arm64: fake_sigreturn_missing_fpsimd
  kselftest: arm64: fake_sigreturn_bad_size_for_magic0
  kselftest: arm64: fake_sigreturn_bad_magic
  kselftest: arm64: add helper get_current_context
  kselftest: arm64: extend test_init functionalities
  kselftest: arm64: mangle_pstate_invalid_mode_el[123][ht]
  kselftest: arm64: mangle_pstate_invalid_daif_bits
  kselftest: arm64: mangle_pstate_invalid_compat_toggle and common utils
  kselftest: arm64: extend toplevel skeleton Makefile
  drivers/perf: hisi: update the sccl_id/ccl_id for certain HiSilicon platform
  arm64: mm: reserve CMA and crashkernel in ZONE_DMA32
  ...

1 files changed, 89 insertions, 15 deletions

diff --git a/mm/memory.c b/mm/memory.c
index b1ca51a079f2..b6a5d6a08438 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -118,6 +118,18 @@ int randomize_va_space __read_mostly =
 					2;
 #endif
 
+#ifndef arch_faults_on_old_pte
+static inline bool arch_faults_on_old_pte(void)
+{
+	/*
+	 * Those arches which don't have hw access flag feature need to
+	 * implement their own helper. By default, "true" means pagefault
+	 * will be hit on old pte.
+	 */
+	return true;
+}
+#endif
+
 static int __init disable_randmaps(char *s)
 {
 	randomize_va_space = 0;
@@ -2145,32 +2157,82 @@ static inline int pte_unmap_same(struct mm_struct *mm, pmd_t *pmd,
 	return same;
 }
 
-static inline void cow_user_page(struct page *dst, struct page *src, unsigned long va, struct vm_area_struct *vma)
+static inline bool cow_user_page(struct page *dst, struct page *src,
+				 struct vm_fault *vmf)
 {
+	bool ret;
+	void *kaddr;
+	void __user *uaddr;
+	bool force_mkyoung;
+	struct vm_area_struct *vma = vmf->vma;
+	struct mm_struct *mm = vma->vm_mm;
+	unsigned long addr = vmf->address;
+
 	debug_dma_assert_idle(src);
 
+	if (likely(src)) {
+		copy_user_highpage(dst, src, addr, vma);
+		return true;
+	}
+
 	/*
 	 * If the source page was a PFN mapping, we don't have
 	 * a "struct page" for it. We do a best-effort copy by
 	 * just copying from the original user address. If that
 	 * fails, we just zero-fill it. Live with it.
 	 */
-	if (unlikely(!src)) {
-		void *kaddr = kmap_atomic(dst);
-		void __user *uaddr = (void __user *)(va & PAGE_MASK);
+	kaddr = kmap_atomic(dst);
+	uaddr = (void __user *)(addr & PAGE_MASK);
+
+	/*
+	 * On architectures with software "accessed" bits, we would
+	 * take a double page fault, so mark it accessed here.
+	 */
+	force_mkyoung = arch_faults_on_old_pte() && !pte_young(vmf->orig_pte);
+	if (force_mkyoung) {
+		pte_t entry;
+
+		vmf->pte = pte_offset_map_lock(mm, vmf->pmd, addr, &vmf->ptl);
+		if (!likely(pte_same(*vmf->pte, vmf->orig_pte))) {
+			/*
+			 * Other thread has already handled the fault
+			 * and we don't need to do anything. If it's
+			 * not the case, the fault will be triggered
+			 * again on the same address.
+			 */
+			ret = false;
+			goto pte_unlock;
+		}
 
+		entry = pte_mkyoung(vmf->orig_pte);
+		if (ptep_set_access_flags(vma, addr, vmf->pte, entry, 0))
+			update_mmu_cache(vma, addr, vmf->pte);
+	}
+
+	/*
+	 * This really shouldn't fail, because the page is there
+	 * in the page tables. But it might just be unreadable,
+	 * in which case we just give up and fill the result with
+	 * zeroes.
+	 */
+	if (__copy_from_user_inatomic(kaddr, uaddr, PAGE_SIZE)) {
 		/*
-		 * This really shouldn't fail, because the page is there
-		 * in the page tables. But it might just be unreadable,
-		 * in which case we just give up and fill the result with
-		 * zeroes.
+		 * Give a warn in case there can be some obscure
+		 * use-case
 		 */
-		if (__copy_from_user_inatomic(kaddr, uaddr, PAGE_SIZE))
-			clear_page(kaddr);
-		kunmap_atomic(kaddr);
-		flush_dcache_page(dst);
-	} else
-		copy_user_highpage(dst, src, va, vma);
+		WARN_ON_ONCE(1);
+		clear_page(kaddr);
+	}
+
+	ret = true;
+
+pte_unlock:
+	if (force_mkyoung)
+		pte_unmap_unlock(vmf->pte, vmf->ptl);
+	kunmap_atomic(kaddr);
+	flush_dcache_page(dst);
+
+	return ret;
 }
 
 static gfp_t __get_fault_gfp_mask(struct vm_area_struct *vma)
@@ -2327,7 +2389,19 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf)
 				vmf->address);
 		if (!new_page)
 			goto oom;
-		cow_user_page(new_page, old_page, vmf->address, vma);
+
+		if (!cow_user_page(new_page, old_page, vmf)) {
+			/*
+			 * COW failed, if the fault was solved by other,
+			 * it's fine. If not, userspace would re-fault on
+			 * the same address and we will handle the fault
+			 * from the second attempt.
+			 */
+			put_page(new_page);
+			if (old_page)
+				put_page(old_page);
+			return 0;
+		}
 	}
 
 	if (mem_cgroup_try_charge_delay(new_page, mm, GFP_KERNEL, &memcg, false))