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

Pull arm64 and cross-arch updates from Catalin Marinas:
 "Here's a slightly wider-spread set of updates for 5.9.

  Going outside the usual arch/arm64/ area is the removal of
  read_barrier_depends() series from Will and the MSI/IOMMU ID
  translation series from Lorenzo.

  The notable arm64 updates include ARMv8.4 TLBI range operations and
  translation level hint, time namespace support, and perf.

  Summary:

   - Removal of the tremendously unpopular read_barrier_depends()
     barrier, which is a NOP on all architectures apart from Alpha, in
     favour of allowing architectures to override READ_ONCE() and do
     whatever dance they need to do to ensure address dependencies
     provide LOAD -> LOAD/STORE ordering.

     This work also offers a potential solution if compilers are shown
     to convert LOAD -> LOAD address dependencies into control
     dependencies (e.g. under LTO), as weakly ordered architectures will
     effectively be able to upgrade READ_ONCE() to smp_load_acquire().
     The latter case is not used yet, but will be discussed further at
     LPC.

   - Make the MSI/IOMMU input/output ID translation PCI agnostic,
     augment the MSI/IOMMU ACPI/OF ID mapping APIs to accept an input ID
     bus-specific parameter and apply the resulting changes to the
     device ID space provided by the Freescale FSL bus.

   - arm64 support for TLBI range operations and translation table level
     hints (part of the ARMv8.4 architecture version).

   - Time namespace support for arm64.

   - Export the virtual and physical address sizes in vmcoreinfo for
     makedumpfile and crash utilities.

   - CPU feature handling cleanups and checks for programmer errors
     (overlapping bit-fields).

   - ACPI updates for arm64: disallow AML accesses to EFI code regions
     and kernel memory.

   - perf updates for arm64.

   - Miscellaneous fixes and cleanups, most notably PLT counting
     optimisation for module loading, recordmcount fix to ignore
     relocations other than R_AARCH64_CALL26, CMA areas reserved for
     gigantic pages on 16K and 64K configurations.

   - Trivial typos, duplicate words"

Link: http://lkml.kernel.org/r/20200710165203.31284-1-will@kernel.org
Link: http://lkml.kernel.org/r/20200619082013.13661-1-lorenzo.pieralisi@arm.com

* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (82 commits)
  arm64: use IRQ_STACK_SIZE instead of THREAD_SIZE for irq stack
  arm64/mm: save memory access in check_and_switch_context() fast switch path
  arm64: sigcontext.h: delete duplicated word
  arm64: ptrace.h: delete duplicated word
  arm64: pgtable-hwdef.h: delete duplicated words
  bus: fsl-mc: Add ACPI support for fsl-mc
  bus/fsl-mc: Refactor the MSI domain creation in the DPRC driver
  of/irq: Make of_msi_map_rid() PCI bus agnostic
  of/irq: make of_msi_map_get_device_domain() bus agnostic
  dt-bindings: arm: fsl: Add msi-map device-tree binding for fsl-mc bus
  of/device: Add input id to of_dma_configure()
  of/iommu: Make of_map_rid() PCI agnostic
  ACPI/IORT: Add an input ID to acpi_dma_configure()
  ACPI/IORT: Remove useless PCI bus walk
  ACPI/IORT: Make iort_msi_map_rid() PCI agnostic
  ACPI/IORT: Make iort_get_device_domain IRQ domain agnostic
  ACPI/IORT: Make iort_match_node_callback walk the ACPI namespace for NC
  arm64: enable time namespace support
  arm64/vdso: Restrict splitting VVAR VMA
  arm64/vdso: Handle faults on timens page
  ...

4 files changed, 132 insertions, 33 deletions

diff --git a/include/asm-generic/Kbuild b/include/asm-generic/Kbuild
index 44ec80e70518..74b0612601dd 100644
--- a/include/asm-generic/Kbuild
+++ b/include/asm-generic/Kbuild
@@ -45,6 +45,7 @@ mandatory-y += pci.h
 mandatory-y += percpu.h
 mandatory-y += pgalloc.h
 mandatory-y += preempt.h
+mandatory-y += rwonce.h
 mandatory-y += sections.h
 mandatory-y += serial.h
 mandatory-y += shmparam.h
diff --git a/include/asm-generic/barrier.h b/include/asm-generic/barrier.h
index 2eacaf7d62f6..fec97dc34de7 100644
--- a/include/asm-generic/barrier.h
+++ b/include/asm-generic/barrier.h
@@ -13,7 +13,7 @@
 
 #ifndef __ASSEMBLY__
 
-#include <linux/compiler.h>
+#include <asm/rwonce.h>
 
 #ifndef nop
 #define nop()	asm volatile ("nop")
@@ -46,10 +46,6 @@
 #define dma_wmb()	wmb()
 #endif
 
-#ifndef read_barrier_depends
-#define read_barrier_depends()		do { } while (0)
-#endif
-
 #ifndef __smp_mb
 #define __smp_mb()	mb()
 #endif
@@ -62,10 +58,6 @@
 #define __smp_wmb()	wmb()
 #endif
 
-#ifndef __smp_read_barrier_depends
-#define __smp_read_barrier_depends()	read_barrier_depends()
-#endif
-
 #ifdef CONFIG_SMP
 
 #ifndef smp_mb
@@ -80,10 +72,6 @@
 #define smp_wmb()	__smp_wmb()
 #endif
 
-#ifndef smp_read_barrier_depends
-#define smp_read_barrier_depends()	__smp_read_barrier_depends()
-#endif
-
 #else	/* !CONFIG_SMP */
 
 #ifndef smp_mb
@@ -98,10 +86,6 @@
 #define smp_wmb()	barrier()
 #endif
 
-#ifndef smp_read_barrier_depends
-#define smp_read_barrier_depends()	do { } while (0)
-#endif
-
 #endif	/* CONFIG_SMP */
 
 #ifndef __smp_store_mb
@@ -196,7 +180,6 @@ do {									\
 #define virt_mb() __smp_mb()
 #define virt_rmb() __smp_rmb()
 #define virt_wmb() __smp_wmb()
-#define virt_read_barrier_depends() __smp_read_barrier_depends()
 #define virt_store_mb(var, value) __smp_store_mb(var, value)
 #define virt_mb__before_atomic() __smp_mb__before_atomic()
 #define virt_mb__after_atomic()	__smp_mb__after_atomic()
diff --git a/include/asm-generic/rwonce.h b/include/asm-generic/rwonce.h
new file mode 100644
index 000000000000..8d0a6280e982
--- /dev/null
+++ b/include/asm-generic/rwonce.h
@@ -0,0 +1,90 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Prevent the compiler from merging or refetching reads or writes. The
+ * compiler is also forbidden from reordering successive instances of
+ * READ_ONCE and WRITE_ONCE, but only when the compiler is aware of some
+ * particular ordering. One way to make the compiler aware of ordering is to
+ * put the two invocations of READ_ONCE or WRITE_ONCE in different C
+ * statements.
+ *
+ * These two macros will also work on aggregate data types like structs or
+ * unions.
+ *
+ * Their two major use cases are: (1) Mediating communication between
+ * process-level code and irq/NMI handlers, all running on the same CPU,
+ * and (2) Ensuring that the compiler does not fold, spindle, or otherwise
+ * mutilate accesses that either do not require ordering or that interact
+ * with an explicit memory barrier or atomic instruction that provides the
+ * required ordering.
+ */
+#ifndef __ASM_GENERIC_RWONCE_H
+#define __ASM_GENERIC_RWONCE_H
+
+#ifndef __ASSEMBLY__
+
+#include <linux/compiler_types.h>
+#include <linux/kasan-checks.h>
+#include <linux/kcsan-checks.h>
+
+/*
+ * Yes, this permits 64-bit accesses on 32-bit architectures. These will
+ * actually be atomic in some cases (namely Armv7 + LPAE), but for others we
+ * rely on the access being split into 2x32-bit accesses for a 32-bit quantity
+ * (e.g. a virtual address) and a strong prevailing wind.
+ */
+#define compiletime_assert_rwonce_type(t)					\
+	compiletime_assert(__native_word(t) || sizeof(t) == sizeof(long long),	\
+		"Unsupported access size for {READ,WRITE}_ONCE().")
+
+/*
+ * Use __READ_ONCE() instead of READ_ONCE() if you do not require any
+ * atomicity. Note that this may result in tears!
+ */
+#ifndef __READ_ONCE
+#define __READ_ONCE(x)	(*(const volatile __unqual_scalar_typeof(x) *)&(x))
+#endif
+
+#define READ_ONCE(x)							\
+({									\
+	compiletime_assert_rwonce_type(x);				\
+	__READ_ONCE(x);							\
+})
+
+#define __WRITE_ONCE(x, val)						\
+do {									\
+	*(volatile typeof(x) *)&(x) = (val);				\
+} while (0)
+
+#define WRITE_ONCE(x, val)						\
+do {									\
+	compiletime_assert_rwonce_type(x);				\
+	__WRITE_ONCE(x, val);						\
+} while (0)
+
+static __no_sanitize_or_inline
+unsigned long __read_once_word_nocheck(const void *addr)
+{
+	return __READ_ONCE(*(unsigned long *)addr);
+}
+
+/*
+ * Use READ_ONCE_NOCHECK() instead of READ_ONCE() if you need to load a
+ * word from memory atomically but without telling KASAN/KCSAN. This is
+ * usually used by unwinding code when walking the stack of a running process.
+ */
+#define READ_ONCE_NOCHECK(x)						\
+({									\
+	compiletime_assert(sizeof(x) == sizeof(unsigned long),		\
+		"Unsupported access size for READ_ONCE_NOCHECK().");	\
+	(typeof(x))__read_once_word_nocheck(&(x));			\
+})
+
+static __no_kasan_or_inline
+unsigned long read_word_at_a_time(const void *addr)
+{
+	kasan_check_read(addr, 1);
+	return *(unsigned long *)addr;
+}
+
+#endif /* __ASSEMBLY__ */
+#endif	/* __ASM_GENERIC_RWONCE_H */
diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h
index 3f1649a8cf55..ef75ec86f865 100644
--- a/include/asm-generic/tlb.h
+++ b/include/asm-generic/tlb.h
@@ -512,6 +512,38 @@ static inline void tlb_end_vma(struct mmu_gather *tlb, struct vm_area_struct *vm
 }
 #endif
 
+/*
+ * tlb_flush_{pte|pmd|pud|p4d}_range() adjust the tlb->start and tlb->end,
+ * and set corresponding cleared_*.
+ */
+static inline void tlb_flush_pte_range(struct mmu_gather *tlb,
+				     unsigned long address, unsigned long size)
+{
+	__tlb_adjust_range(tlb, address, size);
+	tlb->cleared_ptes = 1;
+}
+
+static inline void tlb_flush_pmd_range(struct mmu_gather *tlb,
+				     unsigned long address, unsigned long size)
+{
+	__tlb_adjust_range(tlb, address, size);
+	tlb->cleared_pmds = 1;
+}
+
+static inline void tlb_flush_pud_range(struct mmu_gather *tlb,
+				     unsigned long address, unsigned long size)
+{
+	__tlb_adjust_range(tlb, address, size);
+	tlb->cleared_puds = 1;
+}
+
+static inline void tlb_flush_p4d_range(struct mmu_gather *tlb,
+				     unsigned long address, unsigned long size)
+{
+	__tlb_adjust_range(tlb, address, size);
+	tlb->cleared_p4ds = 1;
+}
+
 #ifndef __tlb_remove_tlb_entry
 #define __tlb_remove_tlb_entry(tlb, ptep, address) do { } while (0)
 #endif
@@ -525,19 +557,17 @@ static inline void tlb_end_vma(struct mmu_gather *tlb, struct vm_area_struct *vm
  */
 #define tlb_remove_tlb_entry(tlb, ptep, address)		\
 	do {							\
-		__tlb_adjust_range(tlb, address, PAGE_SIZE);	\
-		tlb->cleared_ptes = 1;				\
+		tlb_flush_pte_range(tlb, address, PAGE_SIZE);	\
 		__tlb_remove_tlb_entry(tlb, ptep, address);	\
 	} while (0)
 
 #define tlb_remove_huge_tlb_entry(h, tlb, ptep, address)	\
 	do {							\
 		unsigned long _sz = huge_page_size(h);		\
-		__tlb_adjust_range(tlb, address, _sz);		\
 		if (_sz == PMD_SIZE)				\
-			tlb->cleared_pmds = 1;			\
+			tlb_flush_pmd_range(tlb, address, _sz);	\
 		else if (_sz == PUD_SIZE)			\
-			tlb->cleared_puds = 1;			\
+			tlb_flush_pud_range(tlb, address, _sz);	\
 		__tlb_remove_tlb_entry(tlb, ptep, address);	\
 	} while (0)
 
@@ -551,8 +581,7 @@ static inline void tlb_end_vma(struct mmu_gather *tlb, struct vm_area_struct *vm
 
 #define tlb_remove_pmd_tlb_entry(tlb, pmdp, address)			\
 	do {								\
-		__tlb_adjust_range(tlb, address, HPAGE_PMD_SIZE);	\
-		tlb->cleared_pmds = 1;					\
+		tlb_flush_pmd_range(tlb, address, HPAGE_PMD_SIZE);	\
 		__tlb_remove_pmd_tlb_entry(tlb, pmdp, address);		\
 	} while (0)
 
@@ -566,8 +595,7 @@ static inline void tlb_end_vma(struct mmu_gather *tlb, struct vm_area_struct *vm
 
 #define tlb_remove_pud_tlb_entry(tlb, pudp, address)			\
 	do {								\
-		__tlb_adjust_range(tlb, address, HPAGE_PUD_SIZE);	\
-		tlb->cleared_puds = 1;					\
+		tlb_flush_pud_range(tlb, address, HPAGE_PUD_SIZE);	\
 		__tlb_remove_pud_tlb_entry(tlb, pudp, address);		\
 	} while (0)
 
@@ -592,9 +620,8 @@ static inline void tlb_end_vma(struct mmu_gather *tlb, struct vm_area_struct *vm
 #ifndef pte_free_tlb
 #define pte_free_tlb(tlb, ptep, address)			\
 	do {							\
-		__tlb_adjust_range(tlb, address, PAGE_SIZE);	\
+		tlb_flush_pmd_range(tlb, address, PAGE_SIZE);	\
 		tlb->freed_tables = 1;				\
-		tlb->cleared_pmds = 1;				\
 		__pte_free_tlb(tlb, ptep, address);		\
 	} while (0)
 #endif
@@ -602,9 +629,8 @@ static inline void tlb_end_vma(struct mmu_gather *tlb, struct vm_area_struct *vm
 #ifndef pmd_free_tlb
 #define pmd_free_tlb(tlb, pmdp, address)			\
 	do {							\
-		__tlb_adjust_range(tlb, address, PAGE_SIZE);	\
+		tlb_flush_pud_range(tlb, address, PAGE_SIZE);	\
 		tlb->freed_tables = 1;				\
-		tlb->cleared_puds = 1;				\
 		__pmd_free_tlb(tlb, pmdp, address);		\
 	} while (0)
 #endif
@@ -612,9 +638,8 @@ static inline void tlb_end_vma(struct mmu_gather *tlb, struct vm_area_struct *vm
 #ifndef pud_free_tlb
 #define pud_free_tlb(tlb, pudp, address)			\
 	do {							\
-		__tlb_adjust_range(tlb, address, PAGE_SIZE);	\
+		tlb_flush_p4d_range(tlb, address, PAGE_SIZE);	\
 		tlb->freed_tables = 1;				\
-		tlb->cleared_p4ds = 1;				\
 		__pud_free_tlb(tlb, pudp, address);		\
 	} while (0)
 #endif