Merge branch 'arm64/vmap-stack' of git://git.kernel.org/pub/scm/linux/kernel/git/mark/linux into for-next/core

* 'arm64/vmap-stack' of git://git.kernel.org/pub/scm/linux/kernel/git/mark/linux:
  arm64: add VMAP_STACK overflow detection
  arm64: add on_accessible_stack()
  arm64: add basic VMAP_STACK support
  arm64: use an irq stack pointer
  arm64: assembler: allow adr_this_cpu to use the stack pointer
  arm64: factor out entry stack manipulation
  efi/arm64: add EFI_KIMG_ALIGN
  arm64: move SEGMENT_ALIGN to <asm/memory.h>
  arm64: clean up irq stack definitions
  arm64: clean up THREAD_* definitions
  arm64: factor out PAGE_* and CONT_* definitions
  arm64: kernel: remove {THREAD,IRQ_STACK}_START_SP
  fork: allow arch-override of VMAP stack alignment
  arm64: remove __die()'s stack dump

7 files changed, 180 insertions, 53 deletions

diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index 0b8461158c56..e1c59d4008a8 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -69,8 +69,55 @@
 #define BAD_FIQ		2
 #define BAD_ERROR	3
 
-	.macro	kernel_entry, el, regsize = 64
+	.macro kernel_ventry	label
+	.align 7
 	sub	sp, sp, #S_FRAME_SIZE
+#ifdef CONFIG_VMAP_STACK
+	/*
+	 * Test whether the SP has overflowed, without corrupting a GPR.
+	 * Task and IRQ stacks are aligned to (1 << THREAD_SHIFT).
+	 */
+	add	sp, sp, x0			// sp' = sp + x0
+	sub	x0, sp, x0			// x0' = sp' - x0 = (sp + x0) - x0 = sp
+	tbnz	x0, #THREAD_SHIFT, 0f
+	sub	x0, sp, x0			// x0'' = sp' - x0' = (sp + x0) - sp = x0
+	sub	sp, sp, x0			// sp'' = sp' - x0 = (sp + x0) - x0 = sp
+	b	\label
+
+0:
+	/*
+	 * Either we've just detected an overflow, or we've taken an exception
+	 * while on the overflow stack. Either way, we won't return to
+	 * userspace, and can clobber EL0 registers to free up GPRs.
+	 */
+
+	/* Stash the original SP (minus S_FRAME_SIZE) in tpidr_el0. */
+	msr	tpidr_el0, x0
+
+	/* Recover the original x0 value and stash it in tpidrro_el0 */
+	sub	x0, sp, x0
+	msr	tpidrro_el0, x0
+
+	/* Switch to the overflow stack */
+	adr_this_cpu sp, overflow_stack + OVERFLOW_STACK_SIZE, x0
+
+	/*
+	 * Check whether we were already on the overflow stack. This may happen
+	 * after panic() re-enables interrupts.
+	 */
+	mrs	x0, tpidr_el0			// sp of interrupted context
+	sub	x0, sp, x0			// delta with top of overflow stack
+	tst	x0, #~(OVERFLOW_STACK_SIZE - 1)	// within range?
+	b.ne	__bad_stack			// no? -> bad stack pointer
+
+	/* We were already on the overflow stack. Restore sp/x0 and carry on. */
+	sub	sp, sp, x0
+	mrs	x0, tpidrro_el0
+#endif
+	b	\label
+	.endm
+
+	.macro	kernel_entry, el, regsize = 64
 	.if	\regsize == 32
 	mov	w0, w0				// zero upper 32 bits of x0
 	.endif
@@ -269,8 +316,8 @@ alternative_else_nop_endif
 	and	x25, x25, #~(THREAD_SIZE - 1)
 	cbnz	x25, 9998f
 
-	adr_this_cpu x25, irq_stack, x26
-	mov	x26, #IRQ_STACK_START_SP
+	ldr_this_cpu x25, irq_stack_ptr, x26
+	mov	x26, #IRQ_STACK_SIZE
 	add	x26, x25, x26
 
 	/* switch to the irq stack */
@@ -318,34 +365,62 @@ tsk	.req	x28		// current thread_info
 
 	.align	11
 ENTRY(vectors)
-	ventry	el1_sync_invalid		// Synchronous EL1t
-	ventry	el1_irq_invalid			// IRQ EL1t
-	ventry	el1_fiq_invalid			// FIQ EL1t
-	ventry	el1_error_invalid		// Error EL1t
+	kernel_ventry	el1_sync_invalid		// Synchronous EL1t
+	kernel_ventry	el1_irq_invalid			// IRQ EL1t
+	kernel_ventry	el1_fiq_invalid			// FIQ EL1t
+	kernel_ventry	el1_error_invalid		// Error EL1t
 
-	ventry	el1_sync			// Synchronous EL1h
-	ventry	el1_irq				// IRQ EL1h
-	ventry	el1_fiq_invalid			// FIQ EL1h
-	ventry	el1_error_invalid		// Error EL1h
+	kernel_ventry	el1_sync			// Synchronous EL1h
+	kernel_ventry	el1_irq				// IRQ EL1h
+	kernel_ventry	el1_fiq_invalid			// FIQ EL1h
+	kernel_ventry	el1_error_invalid		// Error EL1h
 
-	ventry	el0_sync			// Synchronous 64-bit EL0
-	ventry	el0_irq				// IRQ 64-bit EL0
-	ventry	el0_fiq_invalid			// FIQ 64-bit EL0
-	ventry	el0_error_invalid		// Error 64-bit EL0
+	kernel_ventry	el0_sync			// Synchronous 64-bit EL0
+	kernel_ventry	el0_irq				// IRQ 64-bit EL0
+	kernel_ventry	el0_fiq_invalid			// FIQ 64-bit EL0
+	kernel_ventry	el0_error_invalid		// Error 64-bit EL0
 
 #ifdef CONFIG_COMPAT
-	ventry	el0_sync_compat			// Synchronous 32-bit EL0
-	ventry	el0_irq_compat			// IRQ 32-bit EL0
-	ventry	el0_fiq_invalid_compat		// FIQ 32-bit EL0
-	ventry	el0_error_invalid_compat	// Error 32-bit EL0
+	kernel_ventry	el0_sync_compat			// Synchronous 32-bit EL0
+	kernel_ventry	el0_irq_compat			// IRQ 32-bit EL0
+	kernel_ventry	el0_fiq_invalid_compat		// FIQ 32-bit EL0
+	kernel_ventry	el0_error_invalid_compat	// Error 32-bit EL0
 #else
-	ventry	el0_sync_invalid		// Synchronous 32-bit EL0
-	ventry	el0_irq_invalid			// IRQ 32-bit EL0
-	ventry	el0_fiq_invalid			// FIQ 32-bit EL0
-	ventry	el0_error_invalid		// Error 32-bit EL0
+	kernel_ventry	el0_sync_invalid		// Synchronous 32-bit EL0
+	kernel_ventry	el0_irq_invalid			// IRQ 32-bit EL0
+	kernel_ventry	el0_fiq_invalid			// FIQ 32-bit EL0
+	kernel_ventry	el0_error_invalid		// Error 32-bit EL0
 #endif
 END(vectors)
 
+#ifdef CONFIG_VMAP_STACK
+	/*
+	 * We detected an overflow in kernel_ventry, which switched to the
+	 * overflow stack. Stash the exception regs, and head to our overflow
+	 * handler.
+	 */
+__bad_stack:
+	/* Restore the original x0 value */
+	mrs	x0, tpidrro_el0
+
+	/*
+	 * Store the original GPRs to the new stack. The orginal SP (minus
+	 * S_FRAME_SIZE) was stashed in tpidr_el0 by kernel_ventry.
+	 */
+	sub	sp, sp, #S_FRAME_SIZE
+	kernel_entry 1
+	mrs	x0, tpidr_el0
+	add	x0, x0, #S_FRAME_SIZE
+	str	x0, [sp, #S_SP]
+
+	/* Stash the regs for handle_bad_stack */
+	mov	x0, sp
+
+	/* Time to die */
+	bl	handle_bad_stack
+	ASM_BUG()
+#endif /* CONFIG_VMAP_STACK */
+
 /*
  * Invalid mode handlers
  */
diff --git a/arch/arm64/kernel/irq.c b/arch/arm64/kernel/irq.c
index 2386b26c0712..713561e5bcab 100644
--- a/arch/arm64/kernel/irq.c
+++ b/arch/arm64/kernel/irq.c
@@ -23,15 +23,16 @@
 
 #include <linux/kernel_stat.h>
 #include <linux/irq.h>
+#include <linux/memory.h>
 #include <linux/smp.h>
 #include <linux/init.h>
 #include <linux/irqchip.h>
 #include <linux/seq_file.h>
+#include <linux/vmalloc.h>
 
 unsigned long irq_err_count;
 
-/* irq stack only needs to be 16 byte aligned - not IRQ_STACK_SIZE aligned. */
-DEFINE_PER_CPU(unsigned long [IRQ_STACK_SIZE/sizeof(long)], irq_stack) __aligned(16);
+DEFINE_PER_CPU(unsigned long *, irq_stack_ptr);
 
 int arch_show_interrupts(struct seq_file *p, int prec)
 {
@@ -50,8 +51,43 @@ void __init set_handle_irq(void (*handle_irq)(struct pt_regs *))
 	handle_arch_irq = handle_irq;
 }
 
+#ifdef CONFIG_VMAP_STACK
+static void init_irq_stacks(void)
+{
+	int cpu;
+	unsigned long *p;
+
+	for_each_possible_cpu(cpu) {
+		/*
+		* To ensure that VMAP'd stack overflow detection works
+		* correctly, the IRQ stacks need to have the same
+		* alignment as other stacks.
+		*/
+		p = __vmalloc_node_range(IRQ_STACK_SIZE, THREAD_ALIGN,
+					 VMALLOC_START, VMALLOC_END,
+					 THREADINFO_GFP, PAGE_KERNEL,
+					 0, cpu_to_node(cpu),
+					 __builtin_return_address(0));
+
+		per_cpu(irq_stack_ptr, cpu) = p;
+	}
+}
+#else
+/* irq stack only needs to be 16 byte aligned - not IRQ_STACK_SIZE aligned. */
+DEFINE_PER_CPU_ALIGNED(unsigned long [IRQ_STACK_SIZE/sizeof(long)], irq_stack);
+
+static void init_irq_stacks(void)
+{
+	int cpu;
+
+	for_each_possible_cpu(cpu)
+		per_cpu(irq_stack_ptr, cpu) = per_cpu(irq_stack, cpu);
+}
+#endif
+
 void __init init_IRQ(void)
 {
+	init_irq_stacks();
 	irqchip_init();
 	if (!handle_arch_irq)
 		panic("No interrupt controller found.");
diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c
index 320df70c11e6..9cbb6123208f 100644
--- a/arch/arm64/kernel/ptrace.c
+++ b/arch/arm64/kernel/ptrace.c
@@ -42,6 +42,7 @@
 #include <asm/compat.h>
 #include <asm/debug-monitors.h>
 #include <asm/pgtable.h>
+#include <asm/stacktrace.h>
 #include <asm/syscall.h>
 #include <asm/traps.h>
 #include <asm/system_misc.h>
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index dc66e6ec3a99..f13ddb2404f9 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -154,7 +154,7 @@ int __cpu_up(unsigned int cpu, struct task_struct *idle)
 	 * page tables.
 	 */
 	secondary_data.task = idle;
-	secondary_data.stack = task_stack_page(idle) + THREAD_START_SP;
+	secondary_data.stack = task_stack_page(idle) + THREAD_SIZE;
 	update_cpu_boot_status(CPU_MMU_OFF);
 	__flush_dcache_area(&secondary_data, sizeof(secondary_data));
 
diff --git a/arch/arm64/kernel/stacktrace.c b/arch/arm64/kernel/stacktrace.c
index 35588caad9d0..3144584617e7 100644
--- a/arch/arm64/kernel/stacktrace.c
+++ b/arch/arm64/kernel/stacktrace.c
@@ -50,12 +50,7 @@ int notrace unwind_frame(struct task_struct *tsk, struct stackframe *frame)
 	if (!tsk)
 		tsk = current;
 
-	/*
-	 * Switching between stacks is valid when tracing current and in
-	 * non-preemptible context.
-	 */
-	if (!(tsk == current && !preemptible() && on_irq_stack(fp)) &&
-	    !on_task_stack(tsk, fp))
+	if (!on_accessible_stack(tsk, fp))
 		return -EINVAL;
 
 	frame->fp = READ_ONCE_NOCHECK(*(unsigned long *)(fp));
diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c
index 9f023d128c8c..5ea4b85aee0e 100644
--- a/arch/arm64/kernel/traps.c
+++ b/arch/arm64/kernel/traps.c
@@ -32,6 +32,7 @@
 #include <linux/sched/signal.h>
 #include <linux/sched/debug.h>
 #include <linux/sched/task_stack.h>
+#include <linux/sizes.h>
 #include <linux/syscalls.h>
 #include <linux/mm_types.h>
 
@@ -41,6 +42,7 @@
 #include <asm/esr.h>
 #include <asm/insn.h>
 #include <asm/traps.h>
+#include <asm/smp.h>
 #include <asm/stack_pointer.h>
 #include <asm/stacktrace.h>
 #include <asm/exception.h>
@@ -193,8 +195,7 @@ void dump_backtrace(struct pt_regs *regs, struct task_struct *tsk)
 		if (in_entry_text(frame.pc)) {
 			stack = frame.fp - offsetof(struct pt_regs, stackframe);
 
-			if (on_task_stack(tsk, stack) ||
-			    (tsk == current && !preemptible() && on_irq_stack(stack)))
+			if (on_accessible_stack(tsk, stack))
 				dump_mem("", "Exception stack", stack,
 					 stack + sizeof(struct pt_regs));
 		}
@@ -237,8 +238,6 @@ static int __die(const char *str, int err, struct pt_regs *regs)
 		 end_of_stack(tsk));
 
 	if (!user_mode(regs)) {
-		dump_mem(KERN_EMERG, "Stack: ", regs->sp,
-			 THREAD_SIZE + (unsigned long)task_stack_page(tsk));
 		dump_backtrace(regs, tsk);
 		dump_instr(KERN_EMERG, regs);
 	}
@@ -672,6 +671,43 @@ asmlinkage void bad_el0_sync(struct pt_regs *regs, int reason, unsigned int esr)
 	force_sig_info(info.si_signo, &info, current);
 }
 
+#ifdef CONFIG_VMAP_STACK
+
+DEFINE_PER_CPU(unsigned long [OVERFLOW_STACK_SIZE/sizeof(long)], overflow_stack)
+	__aligned(16);
+
+asmlinkage void handle_bad_stack(struct pt_regs *regs)
+{
+	unsigned long tsk_stk = (unsigned long)current->stack;
+	unsigned long irq_stk = (unsigned long)this_cpu_read(irq_stack_ptr);
+	unsigned long ovf_stk = (unsigned long)this_cpu_ptr(overflow_stack);
+	unsigned int esr = read_sysreg(esr_el1);
+	unsigned long far = read_sysreg(far_el1);
+
+	console_verbose();
+	pr_emerg("Insufficient stack space to handle exception!");
+
+	pr_emerg("ESR: 0x%08x -- %s\n", esr, esr_get_class_string(esr));
+	pr_emerg("FAR: 0x%016lx\n", far);
+
+	pr_emerg("Task stack:     [0x%016lx..0x%016lx]\n",
+		 tsk_stk, tsk_stk + THREAD_SIZE);
+	pr_emerg("IRQ stack:      [0x%016lx..0x%016lx]\n",
+		 irq_stk, irq_stk + THREAD_SIZE);
+	pr_emerg("Overflow stack: [0x%016lx..0x%016lx]\n",
+		 ovf_stk, ovf_stk + OVERFLOW_STACK_SIZE);
+
+	__show_regs(regs);
+
+	/*
+	 * We use nmi_panic to limit the potential for recusive overflows, and
+	 * to get a better stack trace.
+	 */
+	nmi_panic(NULL, "kernel stack overflow");
+	cpu_park_loop();
+}
+#endif
+
 void __pte_error(const char *file, int line, unsigned long val)
 {
 	pr_err("%s:%d: bad pte %016lx.\n", file, line, val);
diff --git a/arch/arm64/kernel/vmlinux.lds.S b/arch/arm64/kernel/vmlinux.lds.S
index 987a00ee446c..fe56c268a7d9 100644
--- a/arch/arm64/kernel/vmlinux.lds.S
+++ b/arch/arm64/kernel/vmlinux.lds.S
@@ -72,22 +72,6 @@ PECOFF_FILE_ALIGNMENT = 0x200;
 #define PECOFF_EDATA_PADDING
 #endif
 
-#if defined(CONFIG_DEBUG_ALIGN_RODATA)
-/*
- *  4 KB granule:   1 level 2 entry
- * 16 KB granule: 128 level 3 entries, with contiguous bit
- * 64 KB granule:  32 level 3 entries, with contiguous bit
- */
-#define SEGMENT_ALIGN			SZ_2M
-#else
-/*
- *  4 KB granule:  16 level 3 entries, with contiguous bit
- * 16 KB granule:   4 level 3 entries, without contiguous bit
- * 64 KB granule:   1 level 3 entry
- */
-#define SEGMENT_ALIGN			SZ_64K
-#endif
-
 SECTIONS
 {
 	/*
@@ -192,7 +176,7 @@ SECTIONS
 
 	_data = .;
 	_sdata = .;
-	RW_DATA_SECTION(L1_CACHE_BYTES, PAGE_SIZE, THREAD_SIZE)
+	RW_DATA_SECTION(L1_CACHE_BYTES, PAGE_SIZE, THREAD_ALIGN)
 
 	/*
 	 * Data written with the MMU off but read with the MMU on requires