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

Pull arm64 fixes from Catalin Marinas:

 - Fix size alignment in __iommu_{alloc,free}_attrs

 - Kernel memory mapping fix with CONFIG_DEBUG_RODATA for page sizes
   other than 4KB and a fix of the mark_rodata_ro permissions

 - dma_get_ops() simplification and behaviour alignment between DT and
   ACPI

 - function_graph trace fix for cpu_suspend() (CPUs returning from deep
   sleep via a different path and confusing the tracer)

 - Use of non-global mappings for UEFI run-time services to avoid a
   (potentially theoretical) TLB conflict

 - Crypto priority reduction of core AES cipher (the accelerated
   asynchronous implementation is preferred when available)

 - Reverting an old commit that removed BogoMIPS from /proc/cpuinfo on
   arm64.  Apparently, we had it for a relatively short time and libvirt
   started checking for its presence

 - Compiler warnings fixed (ptrace.h inclusion from compat.h,
   smp_load_acquire with const argument)

* tag 'arm64-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux:
  arm64: restore bogomips information in /proc/cpuinfo
  arm64: barriers: fix smp_load_acquire to work with const arguments
  arm64: Fix R/O permissions in mark_rodata_ro
  arm64: crypto: reduce priority of core AES cipher
  arm64: use non-global mappings for UEFI runtime regions
  arm64: kernel: pause/unpause function graph tracer in cpu_suspend()
  arm64: do not include ptrace.h from compat.h
  arm64: simplify dma_get_ops
  arm64: mm: use correct mapping granularity under DEBUG_RODATA
  arm64/dma-mapping: Fix sizes in __iommu_{alloc,free}_attrs

arch/arm64/crypto/aes-ce-cipher.c

@@ -237,7 +237,7 @@ EXPORT_SYMBOL(ce_aes_setkey);
 static struct crypto_alg aes_alg = {
 	.cra_name		= "aes",
 	.cra_driver_name	= "aes-ce",
-	.cra_priority		= 300,
+	.cra_priority		= 250,
 	.cra_flags		= CRYPTO_ALG_TYPE_CIPHER,
 	.cra_blocksize		= AES_BLOCK_SIZE,
 	.cra_ctxsize		= sizeof(struct crypto_aes_ctx),

arch/arm64/include/asm/barrier.h

@@ -64,27 +64,31 @@ do {									\
 
 #define smp_load_acquire(p)						\
 ({									\
-	typeof(*p) ___p1;						\
+	union { typeof(*p) __val; char __c[1]; } __u;			\
 	compiletime_assert_atomic_type(*p);				\
 	switch (sizeof(*p)) {						\
 	case 1:								\
 		asm volatile ("ldarb %w0, %1"				\
-			: "=r" (___p1) : "Q" (*p) : "memory");		\
+			: "=r" (*(__u8 *)__u.__c)			\
+			: "Q" (*p) : "memory");				\
 		break;							\
 	case 2:								\
 		asm volatile ("ldarh %w0, %1"				\
-			: "=r" (___p1) : "Q" (*p) : "memory");		\
+			: "=r" (*(__u16 *)__u.__c)			\
+			: "Q" (*p) : "memory");				\
 		break;							\
 	case 4:								\
 		asm volatile ("ldar %w0, %1"				\
-			: "=r" (___p1) : "Q" (*p) : "memory");		\
+			: "=r" (*(__u32 *)__u.__c)			\
+			: "Q" (*p) : "memory");				\
 		break;							\
 	case 8:								\
 		asm volatile ("ldar %0, %1"				\
-			: "=r" (___p1) : "Q" (*p) : "memory");		\
+			: "=r" (*(__u64 *)__u.__c)			\
+			: "Q" (*p) : "memory");				\
 		break;							\
 	}								\
-	___p1;								\
+	__u.__val;							\
 })
 
 #define read_barrier_depends()		do { } while(0)

arch/arm64/include/asm/compat.h

@@ -23,7 +23,6 @@
  */
 #include <linux/types.h>
 #include <linux/sched.h>
-#include <linux/ptrace.h>
 
 #define COMPAT_USER_HZ		100
 #ifdef __AARCH64EB__
@@ -234,7 +233,7 @@ static inline compat_uptr_t ptr_to_compat(void __user *uptr)
 	return (u32)(unsigned long)uptr;
 }
 
-#define compat_user_stack_pointer() (user_stack_pointer(current_pt_regs()))
+#define compat_user_stack_pointer() (user_stack_pointer(task_pt_regs(current)))
 
 static inline void __user *arch_compat_alloc_user_space(long len)
 {

arch/arm64/include/asm/dma-mapping.h

@@ -18,7 +18,6 @@
 
 #ifdef __KERNEL__
 
-#include <linux/acpi.h>
 #include <linux/types.h>
 #include <linux/vmalloc.h>
 
@@ -26,22 +25,16 @@
 #include <asm/xen/hypervisor.h>
 
 #define DMA_ERROR_CODE	(~(dma_addr_t)0)
-extern struct dma_map_ops *dma_ops;
 extern struct dma_map_ops dummy_dma_ops;
 
 static inline struct dma_map_ops *__generic_dma_ops(struct device *dev)
 {
-	if (unlikely(!dev))
-		return dma_ops;
-	else if (dev->archdata.dma_ops)
+	if (dev && dev->archdata.dma_ops)
 		return dev->archdata.dma_ops;
-	else if (acpi_disabled)
-		return dma_ops;
 
 	/*
-	 * When ACPI is enabled, if arch_set_dma_ops is not called,
-	 * we will disable device DMA capability by setting it
-	 * to dummy_dma_ops.
+	 * We expect no ISA devices, and all other DMA masters are expected to
+	 * have someone call arch_setup_dma_ops at device creation time.
 	 */
 	return &dummy_dma_ops;
 }

arch/arm64/include/asm/mmu_context.h

@@ -101,7 +101,7 @@ static inline void cpu_set_default_tcr_t0sz(void)
 #define destroy_context(mm)		do { } while(0)
 void check_and_switch_context(struct mm_struct *mm, unsigned int cpu);
 
-#define init_new_context(tsk,mm)	({ atomic64_set(&mm->context.id, 0); 0; })
+#define init_new_context(tsk,mm)	({ atomic64_set(&(mm)->context.id, 0); 0; })
 
 /*
  * This is called when "tsk" is about to enter lazy TLB mode.

arch/arm64/include/asm/pgtable.h

@@ -81,6 +81,7 @@ extern void __pgd_error(const char *file, int line, unsigned long val);
 
 #define PAGE_KERNEL		__pgprot(_PAGE_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_WRITE)
 #define PAGE_KERNEL_RO		__pgprot(_PAGE_DEFAULT | PTE_PXN | PTE_UXN | PTE_DIRTY | PTE_RDONLY)
+#define PAGE_KERNEL_ROX	__pgprot(_PAGE_DEFAULT | PTE_UXN | PTE_DIRTY | PTE_RDONLY)
 #define PAGE_KERNEL_EXEC	__pgprot(_PAGE_DEFAULT | PTE_UXN | PTE_DIRTY | PTE_WRITE)
 #define PAGE_KERNEL_EXEC_CONT	__pgprot(_PAGE_DEFAULT | PTE_UXN | PTE_DIRTY | PTE_WRITE | PTE_CONT)
 

arch/arm64/kernel/cpuinfo.c

@@ -30,6 +30,7 @@
 #include <linux/seq_file.h>
 #include <linux/sched.h>
 #include <linux/smp.h>
+#include <linux/delay.h>
 
 /*
  * In case the boot CPU is hotpluggable, we record its initial state and
@@ -112,6 +113,10 @@ static int c_show(struct seq_file *m, void *v)
 		 */
 		seq_printf(m, "processor\t: %d\n", i);
 
+		seq_printf(m, "BogoMIPS\t: %lu.%02lu\n",
+			   loops_per_jiffy / (500000UL/HZ),
+			   loops_per_jiffy / (5000UL/HZ) % 100);
+
 		/*
 		 * Dump out the common processor features in a single line.
 		 * Userspace should read the hwcaps with getauxval(AT_HWCAP)

arch/arm64/kernel/efi.c

@@ -224,6 +224,8 @@ static bool __init efi_virtmap_init(void)
 {
 	efi_memory_desc_t *md;
 
+	init_new_context(NULL, &efi_mm);
+
 	for_each_efi_memory_desc(&memmap, md) {
 		u64 paddr, npages, size;
 		pgprot_t prot;
@@ -254,7 +256,8 @@ static bool __init efi_virtmap_init(void)
 		else
 			prot = PAGE_KERNEL;
 
-		create_pgd_mapping(&efi_mm, paddr, md->virt_addr, size, prot);
+		create_pgd_mapping(&efi_mm, paddr, md->virt_addr, size,
+				   __pgprot(pgprot_val(prot) | PTE_NG));
 	}
 	return true;
 }
@@ -329,14 +332,7 @@ core_initcall(arm64_dmi_init);
 
 static void efi_set_pgd(struct mm_struct *mm)
 {
-	if (mm == &init_mm)
-		cpu_set_reserved_ttbr0();
-	else
-		cpu_switch_mm(mm->pgd, mm);
-
-	local_flush_tlb_all();
-	if (icache_is_aivivt())
-		__local_flush_icache_all();
+	switch_mm(NULL, mm, NULL);
 }
 
 void efi_virtmap_load(void)

arch/arm64/kernel/suspend.c

+#include <linux/ftrace.h>
 #include <linux/percpu.h>
 #include <linux/slab.h>
 #include <asm/cacheflush.h>
@@ -70,6 +71,13 @@ int cpu_suspend(unsigned long arg, int (*fn)(unsigned long))
 	 */
 	local_dbg_save(flags);
 
+	/*
+	 * Function graph tracer state gets incosistent when the kernel
+	 * calls functions that never return (aka suspend finishers) hence
+	 * disable graph tracing during their execution.
+	 */
+	pause_graph_tracing();
+
 	/*
 	 * mm context saved on the stack, it will be restored when
 	 * the cpu comes out of reset through the identity mapped
@@ -111,6 +119,8 @@ int cpu_suspend(unsigned long arg, int (*fn)(unsigned long))
 			hw_breakpoint_restore(NULL);
 	}
 
+	unpause_graph_tracing();
+
 	/*
 	 * Restore pstate flags. OS lock and mdscr have been already
 	 * restored, so from this point onwards, debugging is fully

arch/arm64/mm/dma-mapping.c

@@ -18,6 +18,7 @@
  */
 
 #include <linux/gfp.h>
+#include <linux/acpi.h>
 #include <linux/export.h>
 #include <linux/slab.h>
 #include <linux/genalloc.h>
@@ -28,9 +29,6 @@
 
 #include <asm/cacheflush.h>
 
-struct dma_map_ops *dma_ops;
-EXPORT_SYMBOL(dma_ops);
-
 static pgprot_t __get_dma_pgprot(struct dma_attrs *attrs, pgprot_t prot,
 				 bool coherent)
 {
@@ -515,13 +513,7 @@ EXPORT_SYMBOL(dummy_dma_ops);
 
 static int __init arm64_dma_init(void)
 {
-	int ret;
-
-	dma_ops = &swiotlb_dma_ops;
-
-	ret = atomic_pool_init();
-
-	return ret;
+	return atomic_pool_init();
 }
 arch_initcall(arm64_dma_init);
 
@@ -552,10 +544,14 @@ static void *__iommu_alloc_attrs(struct device *dev, size_t size,
 {
 	bool coherent = is_device_dma_coherent(dev);
 	int ioprot = dma_direction_to_prot(DMA_BIDIRECTIONAL, coherent);
+	size_t iosize = size;
 	void *addr;
 
 	if (WARN(!dev, "cannot create IOMMU mapping for unknown device\n"))
 		return NULL;
+
+	size = PAGE_ALIGN(size);
+
 	/*
 	 * Some drivers rely on this, and we probably don't want the
 	 * possibility of stale kernel data being read by devices anyway.
@@ -566,7 +562,7 @@ static void *__iommu_alloc_attrs(struct device *dev, size_t size,
 		struct page **pages;
 		pgprot_t prot = __get_dma_pgprot(attrs, PAGE_KERNEL, coherent);
 
-		pages = iommu_dma_alloc(dev, size, gfp, ioprot,	handle,
+		pages = iommu_dma_alloc(dev, iosize, gfp, ioprot, handle,
 					flush_page);
 		if (!pages)
 			return NULL;
@@ -574,7 +570,7 @@ static void *__iommu_alloc_attrs(struct device *dev, size_t size,
 		addr = dma_common_pages_remap(pages, size, VM_USERMAP, prot,
 					      __builtin_return_address(0));
 		if (!addr)
-			iommu_dma_free(dev, pages, size, handle);
+			iommu_dma_free(dev, pages, iosize, handle);
 	} else {
 		struct page *page;
 		/*
@@ -591,7 +587,7 @@ static void *__iommu_alloc_attrs(struct device *dev, size_t size,
 		if (!addr)
 			return NULL;
 
-		*handle = iommu_dma_map_page(dev, page, 0, size, ioprot);
+		*handle = iommu_dma_map_page(dev, page, 0, iosize, ioprot);
 		if (iommu_dma_mapping_error(dev, *handle)) {
 			if (coherent)
 				__free_pages(page, get_order(size));
@@ -606,6 +602,9 @@ static void *__iommu_alloc_attrs(struct device *dev, size_t size,
 static void __iommu_free_attrs(struct device *dev, size_t size, void *cpu_addr,
 			       dma_addr_t handle, struct dma_attrs *attrs)
 {
+	size_t iosize = size;
+
+	size = PAGE_ALIGN(size);
 	/*
 	 * @cpu_addr will be one of 3 things depending on how it was allocated:
 	 * - A remapped array of pages from iommu_dma_alloc(), for all
@@ -617,17 +616,17 @@ static void __iommu_free_attrs(struct device *dev, size_t size, void *cpu_addr,
 	 * Hence how dodgy the below logic looks...
 	 */
 	if (__in_atomic_pool(cpu_addr, size)) {
-		iommu_dma_unmap_page(dev, handle, size, 0, NULL);
+		iommu_dma_unmap_page(dev, handle, iosize, 0, NULL);
 		__free_from_pool(cpu_addr, size);
 	} else if (is_vmalloc_addr(cpu_addr)){
 		struct vm_struct *area = find_vm_area(cpu_addr);
 
 		if (WARN_ON(!area || !area->pages))
 			return;
-		iommu_dma_free(dev, area->pages, size, &handle);
+		iommu_dma_free(dev, area->pages, iosize, &handle);
 		dma_common_free_remap(cpu_addr, size, VM_USERMAP);
 	} else {
-		iommu_dma_unmap_page(dev, handle, size, 0, NULL);
+		iommu_dma_unmap_page(dev, handle, iosize, 0, NULL);
 		__free_pages(virt_to_page(cpu_addr), get_order(size));
 	}
 }
@@ -984,8 +983,8 @@ static void __iommu_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
 void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size,
 			struct iommu_ops *iommu, bool coherent)
 {
-	if (!acpi_disabled && !dev->archdata.dma_ops)
-		dev->archdata.dma_ops = dma_ops;
+	if (!dev->archdata.dma_ops)
+		dev->archdata.dma_ops = &swiotlb_dma_ops;
 
 	dev->archdata.dma_coherent = coherent;
 	__iommu_setup_dma_ops(dev, dma_base, size, iommu);

arch/arm64/mm/mmu.c

@@ -362,8 +362,8 @@ static void __init __map_memblock(phys_addr_t start, phys_addr_t end)
 	 * for now. This will get more fine grained later once all memory
 	 * is mapped
 	 */
-	unsigned long kernel_x_start = round_down(__pa(_stext), SECTION_SIZE);
-	unsigned long kernel_x_end = round_up(__pa(__init_end), SECTION_SIZE);
+	unsigned long kernel_x_start = round_down(__pa(_stext), SWAPPER_BLOCK_SIZE);
+	unsigned long kernel_x_end = round_up(__pa(__init_end), SWAPPER_BLOCK_SIZE);
 
 	if (end < kernel_x_start) {
 		create_mapping(start, __phys_to_virt(start),
@@ -451,18 +451,18 @@ static void __init fixup_executable(void)
 {
 #ifdef CONFIG_DEBUG_RODATA
 	/* now that we are actually fully mapped, make the start/end more fine grained */
-	if (!IS_ALIGNED((unsigned long)_stext, SECTION_SIZE)) {
+	if (!IS_ALIGNED((unsigned long)_stext, SWAPPER_BLOCK_SIZE)) {
 		unsigned long aligned_start = round_down(__pa(_stext),
-							SECTION_SIZE);
+							 SWAPPER_BLOCK_SIZE);
 
 		create_mapping(aligned_start, __phys_to_virt(aligned_start),
 				__pa(_stext) - aligned_start,
 				PAGE_KERNEL);
 	}
 
-	if (!IS_ALIGNED((unsigned long)__init_end, SECTION_SIZE)) {
+	if (!IS_ALIGNED((unsigned long)__init_end, SWAPPER_BLOCK_SIZE)) {
 		unsigned long aligned_end = round_up(__pa(__init_end),
-							SECTION_SIZE);
+							  SWAPPER_BLOCK_SIZE);
 		create_mapping(__pa(__init_end), (unsigned long)__init_end,
 				aligned_end - __pa(__init_end),
 				PAGE_KERNEL);
@@ -475,7 +475,7 @@ void mark_rodata_ro(void)
 {
 	create_mapping_late(__pa(_stext), (unsigned long)_stext,
 				(unsigned long)_etext - (unsigned long)_stext,
-				PAGE_KERNEL_EXEC | PTE_RDONLY);
+				PAGE_KERNEL_ROX);
 
 }
 #endif