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

Pull arm64 fixes from Catalin Marinas:

 - ZONE_DMA32 initialisation fix when memblocks fall entirely within the
   first GB (used by ZONE_DMA in 5.5 for Raspberry Pi 4).

 - Couple of ftrace fixes following the FTRACE_WITH_REGS patchset.

 - access_ok() fix for the Tagged Address ABI when called from from a
   kernel thread (asynchronous I/O): the kthread does not have the TIF
   flags of the mm owner, so untag the user address unconditionally.

 - KVM compute_layout() called before the alternatives code patching.

 - Minor clean-ups.

* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux:
  arm64: entry: refine comment of stack overflow check
  arm64: ftrace: fix ifdeffery
  arm64: KVM: Invoke compute_layout() before alternatives are applied
  arm64: Validate tagged addresses in access_ok() called from kernel threads
  arm64: mm: Fix column alignment for UXN in kernel_page_tables
  arm64: insn: consistently handle exit text
  arm64: mm: Fix initialisation of DMA zones on non-NUMA systems

arch/arm64/include/asm/kvm_mmu.h

@@ -91,6 +91,7 @@ alternative_cb_end
 
 void kvm_update_va_mask(struct alt_instr *alt,
 			__le32 *origptr, __le32 *updptr, int nr_inst);
+void kvm_compute_layout(void);
 
 static inline unsigned long __kern_hyp_va(unsigned long v)
 {

arch/arm64/include/asm/sections.h

@@ -15,6 +15,7 @@ extern char __hyp_text_start[], __hyp_text_end[];
 extern char __idmap_text_start[], __idmap_text_end[];
 extern char __initdata_begin[], __initdata_end[];
 extern char __inittext_begin[], __inittext_end[];
+extern char __exittext_begin[], __exittext_end[];
 extern char __irqentry_text_start[], __irqentry_text_end[];
 extern char __mmuoff_data_start[], __mmuoff_data_end[];
 extern char __entry_tramp_text_start[], __entry_tramp_text_end[];

arch/arm64/include/asm/uaccess.h

@@ -62,8 +62,13 @@ static inline unsigned long __range_ok(const void __user *addr, unsigned long si
 {
 	unsigned long ret, limit = current_thread_info()->addr_limit;
 
+	/*
+	 * Asynchronous I/O running in a kernel thread does not have the
+	 * TIF_TAGGED_ADDR flag of the process owning the mm, so always untag
+	 * the user address before checking.
+	 */
 	if (IS_ENABLED(CONFIG_ARM64_TAGGED_ADDR_ABI) &&
-	    test_thread_flag(TIF_TAGGED_ADDR))
+	    (current->flags & PF_KTHREAD || test_thread_flag(TIF_TAGGED_ADDR)))
 		addr = untagged_addr(addr);
 
 	__chk_user_ptr(addr);

arch/arm64/kernel/entry-ftrace.S

@@ -133,7 +133,6 @@ ENTRY(ftrace_graph_caller)
 	bl	prepare_ftrace_return
 	b	ftrace_common_return
 ENDPROC(ftrace_graph_caller)
-#else
 #endif
 
 #else /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */
@@ -287,6 +286,7 @@ GLOBAL(ftrace_graph_call)		// ftrace_graph_caller();
 
 	mcount_exit
 ENDPROC(ftrace_caller)
+#endif /* CONFIG_DYNAMIC_FTRACE */
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 /*
@@ -307,7 +307,6 @@ ENTRY(ftrace_graph_caller)
 	mcount_exit
 ENDPROC(ftrace_graph_caller)
 #endif /* CONFIG_FUNCTION_GRAPH_TRACER */
-#endif /* CONFIG_DYNAMIC_FTRACE */
 #endif /* CONFIG_DYNAMIC_FTRACE_WITH_REGS */
 
 ENTRY(ftrace_stub)

arch/arm64/kernel/entry.S

@@ -76,7 +76,8 @@ alternative_else_nop_endif
 #ifdef CONFIG_VMAP_STACK
 	/*
 	 * Test whether the SP has overflowed, without corrupting a GPR.
-	 * Task and IRQ stacks are aligned to (1 << THREAD_SHIFT).
+	 * Task and IRQ stacks are aligned so that SP & (1 << THREAD_SHIFT)
+	 * should always be zero.
 	 */
 	add	sp, sp, x0			// sp' = sp + x0
 	sub	x0, sp, x0			// x0' = sp' - x0 = (sp + x0) - x0 = sp

arch/arm64/kernel/insn.c

@@ -21,6 +21,7 @@
 #include <asm/fixmap.h>
 #include <asm/insn.h>
 #include <asm/kprobes.h>
+#include <asm/sections.h>
 
 #define AARCH64_INSN_SF_BIT	BIT(31)
 #define AARCH64_INSN_N_BIT	BIT(22)
@@ -78,16 +79,29 @@ bool aarch64_insn_is_branch_imm(u32 insn)
 
 static DEFINE_RAW_SPINLOCK(patch_lock);
 
+static bool is_exit_text(unsigned long addr)
+{
+	/* discarded with init text/data */
+	return system_state < SYSTEM_RUNNING &&
+		addr >= (unsigned long)__exittext_begin &&
+		addr < (unsigned long)__exittext_end;
+}
+
+static bool is_image_text(unsigned long addr)
+{
+	return core_kernel_text(addr) || is_exit_text(addr);
+}
+
 static void __kprobes *patch_map(void *addr, int fixmap)
 {
 	unsigned long uintaddr = (uintptr_t) addr;
-	bool module = !core_kernel_text(uintaddr);
+	bool image = is_image_text(uintaddr);
 	struct page *page;
 
-	if (module && IS_ENABLED(CONFIG_STRICT_MODULE_RWX))
-		page = vmalloc_to_page(addr);
-	else if (!module)
+	if (image)
 		page = phys_to_page(__pa_symbol(addr));
+	else if (IS_ENABLED(CONFIG_STRICT_MODULE_RWX))
+		page = vmalloc_to_page(addr);
 	else
 		return addr;
 

arch/arm64/kernel/smp.c

@@ -31,6 +31,7 @@
 #include <linux/of.h>
 #include <linux/irq_work.h>
 #include <linux/kexec.h>
+#include <linux/kvm_host.h>
 
 #include <asm/alternative.h>
 #include <asm/atomic.h>
@@ -39,6 +40,7 @@
 #include <asm/cputype.h>
 #include <asm/cpu_ops.h>
 #include <asm/daifflags.h>
+#include <asm/kvm_mmu.h>
 #include <asm/mmu_context.h>
 #include <asm/numa.h>
 #include <asm/pgtable.h>
@@ -407,6 +409,8 @@ static void __init hyp_mode_check(void)
 			   "CPU: CPUs started in inconsistent modes");
 	else
 		pr_info("CPU: All CPU(s) started at EL1\n");
+	if (IS_ENABLED(CONFIG_KVM_ARM_HOST))
+		kvm_compute_layout();
 }
 
 void __init smp_cpus_done(unsigned int max_cpus)

arch/arm64/kernel/vmlinux.lds.S

@@ -158,9 +158,12 @@ SECTIONS
 	__inittext_begin = .;
 
 	INIT_TEXT_SECTION(8)
+
+	__exittext_begin = .;
 	.exit.text : {
 		ARM_EXIT_KEEP(EXIT_TEXT)
 	}
+	__exittext_end = .;
 
 	. = ALIGN(4);
 	.altinstructions : {

arch/arm64/kvm/va_layout.c

@@ -22,7 +22,7 @@ static u8 tag_lsb;
 static u64 tag_val;
 static u64 va_mask;
 
-static void compute_layout(void)
+__init void kvm_compute_layout(void)
 {
 	phys_addr_t idmap_addr = __pa_symbol(__hyp_idmap_text_start);
 	u64 hyp_va_msb;
@@ -110,9 +110,6 @@ void __init kvm_update_va_mask(struct alt_instr *alt,
 
 	BUG_ON(nr_inst != 5);
 
-	if (!has_vhe() && !va_mask)
-		compute_layout();
-
 	for (i = 0; i < nr_inst; i++) {
 		u32 rd, rn, insn, oinsn;
 
@@ -156,9 +153,6 @@ void kvm_patch_vector_branch(struct alt_instr *alt,
 		return;
 	}
 
-	if (!va_mask)
-		compute_layout();
-
 	/*
 	 * Compute HYP VA by using the same computation as kern_hyp_va()
 	 */

arch/arm64/mm/dump.c

@@ -142,6 +142,7 @@ static const struct prot_bits pte_bits[] = {
 		.mask	= PTE_UXN,
 		.val	= PTE_UXN,
 		.set	= "UXN",
+		.clear	= "   ",
 	}, {
 		.mask	= PTE_ATTRINDX_MASK,
 		.val	= PTE_ATTRINDX(MT_DEVICE_nGnRnE),

arch/arm64/mm/init.c

@@ -214,15 +214,14 @@ static void __init zone_sizes_init(unsigned long min, unsigned long max)
 {
 	struct memblock_region *reg;
 	unsigned long zone_size[MAX_NR_ZONES], zhole_size[MAX_NR_ZONES];
-	unsigned long max_dma32 = min;
-	unsigned long __maybe_unused max_dma = min;
+	unsigned long __maybe_unused max_dma, max_dma32;
 
 	memset(zone_size, 0, sizeof(zone_size));
 
+	max_dma = max_dma32 = min;
 #ifdef CONFIG_ZONE_DMA
-	max_dma = PFN_DOWN(arm64_dma_phys_limit);
+	max_dma = max_dma32 = PFN_DOWN(arm64_dma_phys_limit);
 	zone_size[ZONE_DMA] = max_dma - min;
-	max_dma32 = max_dma;
 #endif
 #ifdef CONFIG_ZONE_DMA32
 	max_dma32 = PFN_DOWN(arm64_dma32_phys_limit);
@@ -236,25 +235,23 @@ static void __init zone_sizes_init(unsigned long min, unsigned long max)
 		unsigned long start = memblock_region_memory_base_pfn(reg);
 		unsigned long end = memblock_region_memory_end_pfn(reg);
 
-		if (start >= max)
-			continue;
 #ifdef CONFIG_ZONE_DMA
-		if (start < max_dma) {
-			unsigned long dma_end = min_not_zero(end, max_dma);
+		if (start >= min && start < max_dma) {
+			unsigned long dma_end = min(end, max_dma);
 			zhole_size[ZONE_DMA] -= dma_end - start;
+			start = dma_end;
 		}
 #endif
 #ifdef CONFIG_ZONE_DMA32
-		if (start < max_dma32) {
+		if (start >= max_dma && start < max_dma32) {
 			unsigned long dma32_end = min(end, max_dma32);
-			unsigned long dma32_start = max(start, max_dma);
-			zhole_size[ZONE_DMA32] -= dma32_end - dma32_start;
+			zhole_size[ZONE_DMA32] -= dma32_end - start;
+			start = dma32_end;
 		}
 #endif
-		if (end > max_dma32) {
+		if (start >= max_dma32 && start < max) {
 			unsigned long normal_end = min(end, max);
-			unsigned long normal_start = max(start, max_dma32);
-			zhole_size[ZONE_NORMAL] -= normal_end - normal_start;
+			zhole_size[ZONE_NORMAL] -= normal_end - start;
 		}
 	}