powerpc/32: Add early stack overflow detection with VMAP stack.

To avoid recursive faults, stack overflow detection has to be
performed before writing in the stack in exception prologs.

Do it by checking the alignment. If the stack pointer alignment is
wrong, it means it is pointing to the following or preceding page.

Without VMAP stack, a stack overflow is catastrophic. With VMAP
stack, a stack overflow isn't destructive, so don't panic. Kill
the task with SIGSEGV instead.

A dedicated overflow stack is set up for each CPU.

  lkdtm: Performing direct entry EXHAUST_STACK
  lkdtm: Calling function with 512 frame size to depth 32 ...
  lkdtm: loop 32/32 ...
  lkdtm: loop 31/32 ...
  lkdtm: loop 30/32 ...
  lkdtm: loop 29/32 ...
  lkdtm: loop 28/32 ...
  lkdtm: loop 27/32 ...
  lkdtm: loop 26/32 ...
  lkdtm: loop 25/32 ...
  lkdtm: loop 24/32 ...
  lkdtm: loop 23/32 ...
  lkdtm: loop 22/32 ...
  lkdtm: loop 21/32 ...
  lkdtm: loop 20/32 ...
  Kernel stack overflow in process test[359], r1=c900c008
  Oops: Kernel stack overflow, sig: 6 [#1]
  BE PAGE_SIZE=4K MMU=Hash PowerMac
  Modules linked in:
  CPU: 0 PID: 359 Comm: test Not tainted 5.3.0-rc7+ #2225
  NIP:  c0622060 LR: c0626710 CTR: 00000000
  REGS: c0895f48 TRAP: 0000   Not tainted  (5.3.0-rc7+)
  MSR:  00001032 <ME,IR,DR,RI>  CR: 28004224  XER: 00000000
  GPR00: c0626ca4 c900c008 c783c000 c07335cc c900c010 c07335cc c900c0f0 c07335cc
  GPR08: c900c0f0 00000001 00000000 00000000 28008222 00000000 00000000 00000000
  GPR16: 00000000 00000000 10010128 10010000 b799c245 10010158 c07335cc 00000025
  GPR24: c0690000 c08b91d4 c068f688 00000020 c900c0f0 c068f668 c08b95b4 c08b91d4
  NIP [c0622060] format_decode+0x0/0x4d4
  LR [c0626710] vsnprintf+0x80/0x5fc
  Call Trace:
  [c900c068] [c0626ca4] vscnprintf+0x18/0x48
  [c900c078] [c007b944] vprintk_store+0x40/0x214
  [c900c0b8] [c007bf50] vprintk_emit+0x90/0x1dc
  [c900c0e8] [c007c5cc] printk+0x50/0x60
  [c900c128] [c03da5b0] recursive_loop+0x44/0x6c
  [c900c338] [c03da5c4] recursive_loop+0x58/0x6c
  [c900c548] [c03da5c4] recursive_loop+0x58/0x6c
  [c900c758] [c03da5c4] recursive_loop+0x58/0x6c
  [c900c968] [c03da5c4] recursive_loop+0x58/0x6c
  [c900cb78] [c03da5c4] recursive_loop+0x58/0x6c
  [c900cd88] [c03da5c4] recursive_loop+0x58/0x6c
  [c900cf98] [c03da5c4] recursive_loop+0x58/0x6c
  [c900d1a8] [c03da5c4] recursive_loop+0x58/0x6c
  [c900d3b8] [c03da5c4] recursive_loop+0x58/0x6c
  [c900d5c8] [c03da5c4] recursive_loop+0x58/0x6c
  [c900d7d8] [c03da5c4] recursive_loop+0x58/0x6c
  [c900d9e8] [c03da5c4] recursive_loop+0x58/0x6c
  [c900dbf8] [c03da5c4] recursive_loop+0x58/0x6c
  [c900de08] [c03da67c] lkdtm_EXHAUST_STACK+0x30/0x4c
  [c900de18] [c03da3e8] direct_entry+0xc8/0x140
  [c900de48] [c029fb40] full_proxy_write+0x64/0xcc
  [c900de68] [c01500f8] __vfs_write+0x30/0x1d0
  [c900dee8] [c0152cb8] vfs_write+0xb8/0x1d4
  [c900df08] [c0152f7c] ksys_write+0x58/0xe8
  [c900df38] [c0014208] ret_from_syscall+0x0/0x34
  --- interrupt: c01 at 0xf806664
      LR = 0x1000c868
  Instruction dump:
  4bffff91 80010014 7c832378 7c0803a6 38210010 4e800020 3d20c08a 3ca0c089
  8089a0cc 38a58f0c 38600001 4ba2d494 <9421ffe0> 7c0802a6 bfc10018 7c9f2378
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/1b89c121b4070c7ee99e4f22cc178f15a736b07b.1576916812.git.christophe.leroy@c-s.fr

arch/powerpc/kernel/entry_32.S

@@ -182,9 +182,11 @@ transfer_to_handler:
          */
 	kuap_save_and_lock r11, r12, r9, r2, r0
 	addi	r2, r12, -THREAD
+#ifndef CONFIG_VMAP_STACK
 	lwz	r9,KSP_LIMIT(r12)
 	cmplw	r1,r9			/* if r1 <= ksp_limit */
 	ble-	stack_ovf		/* then the kernel stack overflowed */
+#endif
 5:
 #if defined(CONFIG_PPC_BOOK3S_32) || defined(CONFIG_E500)
 	lwz	r12,TI_LOCAL_FLAGS(r2)
@@ -289,6 +291,7 @@ reenable_mmu:
 	b	fast_exception_return
 #endif
 
+#ifndef CONFIG_VMAP_STACK
 /*
  * On kernel stack overflow, load up an initial stack pointer
  * and call StackOverflow(regs), which should not return.
@@ -314,6 +317,7 @@ stack_ovf:
 	mtspr	SPRN_SRR1,r10
 	SYNC
 	RFI
+#endif
 
 #ifdef CONFIG_TRACE_IRQFLAGS
 trace_syscall_entry_irq_off:

arch/powerpc/kernel/head_32.h

@@ -55,6 +55,10 @@
 	addi	r11, r11, THREAD_SIZE - INT_FRAME_SIZE
 	tophys_novmstack r11, r11
 1:
+#ifdef CONFIG_VMAP_STACK
+	mtcrf	0x7f, r11
+	bt	32 - THREAD_ALIGN_SHIFT, stack_overflow
+#endif
 .endm
 
 .macro EXCEPTION_PROLOG_2 handle_dar_dsisr=0
@@ -299,4 +303,28 @@
 	EXC_XFER_TEMPLATE(hdlr, n+1, MSR_KERNEL, transfer_to_handler, \
 			  ret_from_except)
 
+.macro vmap_stack_overflow_exception
+#ifdef CONFIG_VMAP_STACK
+#ifdef CONFIG_SMP
+	mfspr	r11, SPRN_SPRG_THREAD
+	tovirt(r11, r11)
+	lwz	r11, TASK_CPU - THREAD(r11)
+	slwi	r11, r11, 3
+	addis	r11, r11, emergency_ctx@ha
+#else
+	lis	r11, emergency_ctx@ha
+#endif
+	lwz	r11, emergency_ctx@l(r11)
+	cmpwi	cr1, r11, 0
+	bne	cr1, 1f
+	lis	r11, init_thread_union@ha
+	addi	r11, r11, init_thread_union@l
+1:	addi	r11, r11, THREAD_SIZE - INT_FRAME_SIZE
+	EXCEPTION_PROLOG_2
+	SAVE_NVGPRS(r11)
+	addi	r3, r1, STACK_FRAME_OVERHEAD
+	EXC_XFER_STD(0, stack_overflow_exception)
+#endif
+.endm
+
 #endif /* __HEAD_32_H__ */

arch/powerpc/kernel/setup.h

@@ -35,7 +35,7 @@ void exc_lvl_early_init(void);
 static inline void exc_lvl_early_init(void) { };
 #endif
 
-#ifdef CONFIG_PPC64
+#if defined(CONFIG_PPC64) || defined(CONFIG_VMAP_STACK)
 void emergency_stack_init(void);
 #else
 static inline void emergency_stack_init(void) { };

arch/powerpc/kernel/setup_32.c

@@ -161,6 +161,18 @@ void __init irqstack_early_init(void)
 	}
 }
 
+#ifdef CONFIG_VMAP_STACK
+void *emergency_ctx[NR_CPUS] __ro_after_init;
+
+void __init emergency_stack_init(void)
+{
+	unsigned int i;
+
+	for_each_possible_cpu(i)
+		emergency_ctx[i] = alloc_stack();
+}
+#endif
+
 #if defined(CONFIG_BOOKE) || defined(CONFIG_40x)
 void __init exc_lvl_early_init(void)
 {

arch/powerpc/kernel/traps.c

@@ -1637,6 +1637,15 @@ void StackOverflow(struct pt_regs *regs)
 	panic("kernel stack overflow");
 }
 
+void stack_overflow_exception(struct pt_regs *regs)
+{
+	enum ctx_state prev_state = exception_enter();
+
+	die("Kernel stack overflow", regs, SIGSEGV);
+
+	exception_exit(prev_state);
+}
+
 void kernel_fp_unavailable_exception(struct pt_regs *regs)
 {
 	enum ctx_state prev_state = exception_enter();