arm64: add VMAP_STACK overflow detection

This patch adds stack overflow detection to arm64, usable when vmap'd stacks
are in use.

Overflow is detected in a small preamble executed for each exception entry,
which checks whether there is enough space on the current stack for the general
purpose registers to be saved. If there is not enough space, the overflow
handler is invoked on a per-cpu overflow stack. This approach preserves the
original exception information in ESR_EL1 (and where appropriate, FAR_EL1).

Task and IRQ stacks are aligned to double their size, enabling overflow to be
detected with a single bit test. For example, a 16K stack is aligned to 32K,
ensuring that bit 14 of the SP must be zero. On an overflow (or underflow),
this bit is flipped. Thus, overflow (of less than the size of the stack) can be
detected by testing whether this bit is set.

The overflow check is performed before any attempt is made to access the
stack, avoiding recursive faults (and the loss of exception information
these would entail). As logical operations cannot be performed on the SP
directly, the SP is temporarily swapped with a general purpose register
using arithmetic operations to enable the test to be performed.

This gives us a useful error message on stack overflow, as can be trigger with
the LKDTM overflow test:

[  305.388749] lkdtm: Performing direct entry OVERFLOW
[  305.395444] Insufficient stack space to handle exception!
[  305.395482] ESR: 0x96000047 -- DABT (current EL)
[  305.399890] FAR: 0xffff00000a5e7f30
[  305.401315] Task stack:     [0xffff00000a5e8000..0xffff00000a5ec000]
[  305.403815] IRQ stack:      [0xffff000008000000..0xffff000008004000]
[  305.407035] Overflow stack: [0xffff80003efce4e0..0xffff80003efcf4e0]
[  305.409622] CPU: 0 PID: 1219 Comm: sh Not tainted 4.13.0-rc3-00021-g9636aea #5
[  305.412785] Hardware name: linux,dummy-virt (DT)
[  305.415756] task: ffff80003d051c00 task.stack: ffff00000a5e8000
[  305.419221] PC is at recursive_loop+0x10/0x48
[  305.421637] LR is at recursive_loop+0x38/0x48
[  305.423768] pc : [<ffff00000859f330>] lr : [<ffff00000859f358>] pstate: 40000145
[  305.428020] sp : ffff00000a5e7f50
[  305.430469] x29: ffff00000a5e8350 x28: ffff80003d051c00
[  305.433191] x27: ffff000008981000 x26: ffff000008f80400
[  305.439012] x25: ffff00000a5ebeb8 x24: ffff00000a5ebeb8
[  305.440369] x23: ffff000008f80138 x22: 0000000000000009
[  305.442241] x21: ffff80003ce65000 x20: ffff000008f80188
[  305.444552] x19: 0000000000000013 x18: 0000000000000006
[  305.446032] x17: 0000ffffa2601280 x16: ffff0000081fe0b8
[  305.448252] x15: ffff000008ff546d x14: 000000000047a4c8
[  305.450246] x13: ffff000008ff7872 x12: 0000000005f5e0ff
[  305.452953] x11: ffff000008ed2548 x10: 000000000005ee8d
[  305.454824] x9 : ffff000008545380 x8 : ffff00000a5e8770
[  305.457105] x7 : 1313131313131313 x6 : 00000000000000e1
[  305.459285] x5 : 0000000000000000 x4 : 0000000000000000
[  305.461781] x3 : 0000000000000000 x2 : 0000000000000400
[  305.465119] x1 : 0000000000000013 x0 : 0000000000000012
[  305.467724] Kernel panic - not syncing: kernel stack overflow
[  305.470561] CPU: 0 PID: 1219 Comm: sh Not tainted 4.13.0-rc3-00021-g9636aea #5
[  305.473325] Hardware name: linux,dummy-virt (DT)
[  305.475070] Call trace:
[  305.476116] [<ffff000008088ad8>] dump_backtrace+0x0/0x378
[  305.478991] [<ffff000008088e64>] show_stack+0x14/0x20
[  305.481237] [<ffff00000895a178>] dump_stack+0x98/0xb8
[  305.483294] [<ffff0000080c3288>] panic+0x118/0x280
[  305.485673] [<ffff0000080c2e9c>] nmi_panic+0x6c/0x70
[  305.486216] [<ffff000008089710>] handle_bad_stack+0x118/0x128
[  305.486612] Exception stack(0xffff80003efcf3a0 to 0xffff80003efcf4e0)
[  305.487334] f3a0: 0000000000000012 0000000000000013 0000000000000400 0000000000000000
[  305.488025] f3c0: 0000000000000000 0000000000000000 00000000000000e1 1313131313131313
[  305.488908] f3e0: ffff00000a5e8770 ffff000008545380 000000000005ee8d ffff000008ed2548
[  305.489403] f400: 0000000005f5e0ff ffff000008ff7872 000000000047a4c8 ffff000008ff546d
[  305.489759] f420: ffff0000081fe0b8 0000ffffa2601280 0000000000000006 0000000000000013
[  305.490256] f440: ffff000008f80188 ffff80003ce65000 0000000000000009 ffff000008f80138
[  305.490683] f460: ffff00000a5ebeb8 ffff00000a5ebeb8 ffff000008f80400 ffff000008981000
[  305.491051] f480: ffff80003d051c00 ffff00000a5e8350 ffff00000859f358 ffff00000a5e7f50
[  305.491444] f4a0: ffff00000859f330 0000000040000145 0000000000000000 0000000000000000
[  305.492008] f4c0: 0001000000000000 0000000000000000 ffff00000a5e8350 ffff00000859f330
[  305.493063] [<ffff00000808205c>] __bad_stack+0x88/0x8c
[  305.493396] [<ffff00000859f330>] recursive_loop+0x10/0x48
[  305.493731] [<ffff00000859f358>] recursive_loop+0x38/0x48
[  305.494088] [<ffff00000859f358>] recursive_loop+0x38/0x48
[  305.494425] [<ffff00000859f358>] recursive_loop+0x38/0x48
[  305.494649] [<ffff00000859f358>] recursive_loop+0x38/0x48
[  305.494898] [<ffff00000859f358>] recursive_loop+0x38/0x48
[  305.495205] [<ffff00000859f358>] recursive_loop+0x38/0x48
[  305.495453] [<ffff00000859f358>] recursive_loop+0x38/0x48
[  305.495708] [<ffff00000859f358>] recursive_loop+0x38/0x48
[  305.496000] [<ffff00000859f358>] recursive_loop+0x38/0x48
[  305.496302] [<ffff00000859f358>] recursive_loop+0x38/0x48
[  305.496644] [<ffff00000859f358>] recursive_loop+0x38/0x48
[  305.496894] [<ffff00000859f358>] recursive_loop+0x38/0x48
[  305.497138] [<ffff00000859f358>] recursive_loop+0x38/0x48
[  305.497325] [<ffff00000859f3dc>] lkdtm_OVERFLOW+0x14/0x20
[  305.497506] [<ffff00000859f314>] lkdtm_do_action+0x1c/0x28
[  305.497786] [<ffff00000859f178>] direct_entry+0xe0/0x170
[  305.498095] [<ffff000008345568>] full_proxy_write+0x60/0xa8
[  305.498387] [<ffff0000081fb7f4>] __vfs_write+0x1c/0x128
[  305.498679] [<ffff0000081fcc68>] vfs_write+0xa0/0x1b0
[  305.498926] [<ffff0000081fe0fc>] SyS_write+0x44/0xa0
[  305.499182] Exception stack(0xffff00000a5ebec0 to 0xffff00000a5ec000)
[  305.499429] bec0: 0000000000000001 000000001c4cf5e0 0000000000000009 000000001c4cf5e0
[  305.499674] bee0: 574f4c465245564f 0000000000000000 0000000000000000 8000000080808080
[  305.499904] bf00: 0000000000000040 0000000000000038 fefefeff1b4bc2ff 7f7f7f7f7f7fff7f
[  305.500189] bf20: 0101010101010101 0000000000000000 000000000047a4c8 0000000000000038
[  305.500712] bf40: 0000000000000000 0000ffffa2601280 0000ffffc63f6068 00000000004b5000
[  305.501241] bf60: 0000000000000001 000000001c4cf5e0 0000000000000009 000000001c4cf5e0
[  305.501791] bf80: 0000000000000020 0000000000000000 00000000004b5000 000000001c4cc458
[  305.502314] bfa0: 0000000000000000 0000ffffc63f7950 000000000040a3c4 0000ffffc63f70e0
[  305.502762] bfc0: 0000ffffa2601268 0000000080000000 0000000000000001 0000000000000040
[  305.503207] bfe0: 0000000000000000 0000000000000000 0000000000000000 0000000000000000
[  305.503680] [<ffff000008082fb0>] el0_svc_naked+0x24/0x28
[  305.504720] Kernel Offset: disabled
[  305.505189] CPU features: 0x002082
[  305.505473] Memory Limit: none
[  305.506181] ---[ end Kernel panic - not syncing: kernel stack overflow

This patch was co-authored by Ard Biesheuvel and Mark Rutland.
Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Reviewed-by: Will Deacon <will.deacon@arm.com>
Tested-by: Laura Abbott <labbott@redhat.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: James Morse <james.morse@arm.com>

arch/arm64/include/asm/memory.h

@@ -133,6 +133,8 @@
 
 #define IRQ_STACK_SIZE		THREAD_SIZE
 
+#define OVERFLOW_STACK_SIZE	SZ_4K
+
 /*
  * Alignment of kernel segments (e.g. .text, .data).
  */

arch/arm64/include/asm/stacktrace.h

@@ -57,6 +57,20 @@ static inline bool on_task_stack(struct task_struct *tsk, unsigned long sp)
 	return (low <= sp && sp < high);
 }
 
+#ifdef CONFIG_VMAP_STACK
+DECLARE_PER_CPU(unsigned long [OVERFLOW_STACK_SIZE/sizeof(long)], overflow_stack);
+
+static inline bool on_overflow_stack(unsigned long sp)
+{
+	unsigned long low = (unsigned long)raw_cpu_ptr(overflow_stack);
+	unsigned long high = low + OVERFLOW_STACK_SIZE;
+
+	return (low <= sp && sp < high);
+}
+#else
+static inline bool on_overflow_stack(unsigned long sp) { return false; }
+#endif
+
 /*
  * We can only safely access per-cpu stacks from current in a non-preemptible
  * context.
@@ -69,6 +83,8 @@ static inline bool on_accessible_stack(struct task_struct *tsk, unsigned long sp
 		return false;
 	if (on_irq_stack(sp))
 		return true;
+	if (on_overflow_stack(sp))
+		return true;
 
 	return false;
 }

arch/arm64/kernel/entry.S

@@ -72,6 +72,48 @@
 	.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
 
@@ -352,6 +394,34 @@ ENTRY(vectors)
 #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
  */

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>
@@ -666,6 +668,43 @@ 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);