powerpc: Activate CONFIG_THREAD_INFO_IN_TASK

This patch activates CONFIG_THREAD_INFO_IN_TASK which
moves the thread_info into task_struct.

Moving thread_info into task_struct has the following advantages:
  - It protects thread_info from corruption in the case of stack
    overflows.
  - Its address is harder to determine if stack addresses are leaked,
    making a number of attacks more difficult.

This has the following consequences:
  - thread_info is now located at the beginning of task_struct.
  - The 'cpu' field is now in task_struct, and only exists when
    CONFIG_SMP is active.
  - thread_info doesn't have anymore the 'task' field.

This patch:
  - Removes all recopy of thread_info struct when the stack changes.
  - Changes the CURRENT_THREAD_INFO() macro to point to current.
  - Selects CONFIG_THREAD_INFO_IN_TASK.
  - Modifies raw_smp_processor_id() to get ->cpu from current without
    including linux/sched.h to avoid circular inclusion and without
    including asm/asm-offsets.h to avoid symbol names duplication
    between ASM constants and C constants.
  - Modifies klp_init_thread_info() to take a task_struct pointer
    argument.
Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
Reviewed-by: Nicholas Piggin <npiggin@gmail.com>
[mpe: Add task_stack.h to livepatch.h to fix build fails]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

arch/powerpc/Kconfig

@@ -238,6 +238,7 @@ config PPC
 	select RTC_LIB
 	select SPARSE_IRQ
 	select SYSCTL_EXCEPTION_TRACE
+	select THREAD_INFO_IN_TASK
 	select VIRT_TO_BUS			if !PPC64
 	#
 	# Please keep this list sorted alphabetically.

arch/powerpc/Makefile

@@ -427,6 +427,13 @@ else
 endif
 endif
 
+ifdef CONFIG_SMP
+prepare: task_cpu_prepare
+
+task_cpu_prepare: prepare0
+	$(eval KBUILD_CFLAGS += -D_TASK_CPU=$(shell awk '{if ($$2 == "TI_CPU") print $$3;}' include/generated/asm-offsets.h))
+endif
+
 # Check toolchain versions:
 # - gcc-4.6 is the minimum kernel-wide version so nothing required.
 checkbin:

arch/powerpc/include/asm/irq.h

@@ -51,9 +51,6 @@ struct pt_regs;
 extern struct thread_info *critirq_ctx[NR_CPUS];
 extern struct thread_info *dbgirq_ctx[NR_CPUS];
 extern struct thread_info *mcheckirq_ctx[NR_CPUS];
-extern void exc_lvl_ctx_init(void);
-#else
-#define exc_lvl_ctx_init()
 #endif
 
 /*
@@ -62,7 +59,6 @@ extern void exc_lvl_ctx_init(void);
 extern struct thread_info *hardirq_ctx[NR_CPUS];
 extern struct thread_info *softirq_ctx[NR_CPUS];
 
-extern void irq_ctx_init(void);
 void call_do_softirq(void *sp);
 void call_do_irq(struct pt_regs *regs, void *sp);
 extern void do_IRQ(struct pt_regs *regs);

arch/powerpc/include/asm/livepatch.h

@@ -21,6 +21,7 @@
 
 #include <linux/module.h>
 #include <linux/ftrace.h>
+#include <linux/sched/task_stack.h>
 
 #ifdef CONFIG_LIVEPATCH
 static inline int klp_check_compiler_support(void)
@@ -43,13 +44,13 @@ static inline unsigned long klp_get_ftrace_location(unsigned long faddr)
 	return ftrace_location_range(faddr, faddr + 16);
 }
 
-static inline void klp_init_thread_info(struct thread_info *ti)
+static inline void klp_init_thread_info(struct task_struct *p)
 {
 	/* + 1 to account for STACK_END_MAGIC */
-	ti->livepatch_sp = (unsigned long *)(ti + 1) + 1;
+	task_thread_info(p)->livepatch_sp = end_of_stack(p) + 1;
 }
 #else
-static void klp_init_thread_info(struct thread_info *ti) { }
+static inline void klp_init_thread_info(struct task_struct *p) { }
 #endif /* CONFIG_LIVEPATCH */
 
 #endif /* _ASM_POWERPC_LIVEPATCH_H */

arch/powerpc/include/asm/smp.h

@@ -83,7 +83,22 @@ int is_cpu_dead(unsigned int cpu);
 /* 32-bit */
 extern int smp_hw_index[];
 
-#define raw_smp_processor_id()	(current_thread_info()->cpu)
+/*
+ * This is particularly ugly: it appears we can't actually get the definition
+ * of task_struct here, but we need access to the CPU this task is running on.
+ * Instead of using task_struct we're using _TASK_CPU which is extracted from
+ * asm-offsets.h by kbuild to get the current processor ID.
+ *
+ * This also needs to be safeguarded when building asm-offsets.s because at
+ * that time _TASK_CPU is not defined yet. It could have been guarded by
+ * _TASK_CPU itself, but we want the build to fail if _TASK_CPU is missing
+ * when building something else than asm-offsets.s
+ */
+#ifdef GENERATING_ASM_OFFSETS
+#define raw_smp_processor_id()		(0)
+#else
+#define raw_smp_processor_id()		(*(unsigned int *)((void *)current + _TASK_CPU))
+#endif
 #define hard_smp_processor_id() 	(smp_hw_index[smp_processor_id()])
 
 static inline int get_hard_smp_processor_id(int cpu)

arch/powerpc/include/asm/thread_info.h

@@ -18,9 +18,9 @@
 #define THREAD_SIZE		(1 << THREAD_SHIFT)
 
 #ifdef CONFIG_PPC64
-#define CURRENT_THREAD_INFO(dest, sp)	stringify_in_c(clrrdi dest, sp, THREAD_SHIFT)
+#define CURRENT_THREAD_INFO(dest, sp)	stringify_in_c(ld dest, PACACURRENT(r13))
 #else
-#define CURRENT_THREAD_INFO(dest, sp)	stringify_in_c(rlwinm dest, sp, 0, 0, 31-THREAD_SHIFT)
+#define CURRENT_THREAD_INFO(dest, sp)	stringify_in_c(mr dest, r2)
 #endif
 
 #ifndef __ASSEMBLY__
@@ -34,8 +34,6 @@
  * low level task data.
  */
 struct thread_info {
-	struct task_struct *task;		/* main task structure */
-	int		cpu;			/* cpu we're on */
 	int		preempt_count;		/* 0 => preemptable,
 						   <0 => BUG */
 	unsigned long	local_flags;		/* private flags for thread */
@@ -58,8 +56,6 @@ struct thread_info {
  */
 #define INIT_THREAD_INFO(tsk)			\
 {						\
-	.task =		&tsk,			\
-	.cpu =		0,			\
 	.preempt_count = INIT_PREEMPT_COUNT,	\
 	.flags =	0,			\
 }
@@ -67,15 +63,6 @@ struct thread_info {
 #define THREAD_SIZE_ORDER	(THREAD_SHIFT - PAGE_SHIFT)
 
 /* how to get the thread information struct from C */
-static inline struct thread_info *current_thread_info(void)
-{
-	unsigned long val;
-
-	asm (CURRENT_THREAD_INFO(%0,1) : "=r" (val));
-
-	return (struct thread_info *)val;
-}
-
 extern int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src);
 
 #ifdef CONFIG_PPC_BOOK3S_64

arch/powerpc/kernel/asm-offsets.c

@@ -13,6 +13,8 @@
  * 2 of the License, or (at your option) any later version.
  */
 
+#define GENERATING_ASM_OFFSETS	/* asm/smp.h */
+
 #include <linux/compat.h>
 #include <linux/signal.h>
 #include <linux/sched.h>
@@ -97,6 +99,9 @@ int main(void)
 #endif
 #endif /* CONFIG_PPC64 */
 	OFFSET(TASK_STACK, task_struct, stack);
+#ifdef CONFIG_SMP
+	OFFSET(TI_CPU, task_struct, cpu);
+#endif
 
 #ifdef CONFIG_LIVEPATCH
 	OFFSET(TI_livepatch_sp, thread_info, livepatch_sp);
@@ -164,8 +169,6 @@ int main(void)
 	OFFSET(TI_FLAGS, thread_info, flags);
 	OFFSET(TI_LOCAL_FLAGS, thread_info, local_flags);
 	OFFSET(TI_PREEMPT, thread_info, preempt_count);
-	OFFSET(TI_TASK, thread_info, task);
-	OFFSET(TI_CPU, thread_info, cpu);
 
 #ifdef CONFIG_PPC64
 	OFFSET(DCACHEL1BLOCKSIZE, ppc64_caches, l1d.block_size);

arch/powerpc/kernel/entry_32.S

@@ -1165,10 +1165,6 @@ ret_from_debug_exc:
 	mfspr	r9,SPRN_SPRG_THREAD
 	lwz	r10,SAVED_KSP_LIMIT(r1)
 	stw	r10,KSP_LIMIT(r9)
-	lwz	r9,TASK_STACK-THREAD(r9)
-	CURRENT_THREAD_INFO(r10, r1)
-	lwz	r10,TI_PREEMPT(r10)
-	stw	r10,TI_PREEMPT(r9)
 	RESTORE_xSRR(SRR0,SRR1);
 	RESTORE_xSRR(CSRR0,CSRR1);
 	RESTORE_MMU_REGS;
@@ -1291,10 +1287,13 @@ BEGIN_FTR_SECTION
 END_FTR_SECTION_IFSET(CPU_FTR_601)
 	lwz	r3,_TRAP(r1)
 	andi.	r0,r3,1
-	beq	4f
+	beq	5f
 	SAVE_NVGPRS(r1)
 	rlwinm	r3,r3,0,0,30
 	stw	r3,_TRAP(r1)
+5:	mfspr	r2,SPRN_SPRG_THREAD
+	addi	r2,r2,-THREAD
+	tovirt(r2,r2)			/* set back r2 to current */
 4:	addi	r3,r1,STACK_FRAME_OVERHEAD
 	bl	unrecoverable_exception
 	/* shouldn't return */

arch/powerpc/kernel/exceptions-64e.S

@@ -77,17 +77,6 @@ special_reg_save:
 	andi.	r3,r3,MSR_PR
 	bnelr
 
-	/* Copy info into temporary exception thread info */
-	ld	r11,PACAKSAVE(r13)
-	CURRENT_THREAD_INFO(r11, r11)
-	CURRENT_THREAD_INFO(r12, r1)
-	ld	r10,TI_FLAGS(r11)
-	std	r10,TI_FLAGS(r12)
-	ld	r10,TI_PREEMPT(r11)
-	std	r10,TI_PREEMPT(r12)
-	ld	r10,TI_TASK(r11)
-	std	r10,TI_TASK(r12)
-
 	/*
 	 * Advance to the next TLB exception frame for handler
 	 * types that don't do it automatically.

arch/powerpc/kernel/head_32.S

@@ -834,9 +834,9 @@ __secondary_start:
 	/* get current's stack and current */
 	lis	r1,secondary_ti@ha
 	tophys(r1,r1)
-	lwz	r1,secondary_ti@l(r1)
-	tophys(r2,r1)
-	lwz	r2,TI_TASK(r2)
+	lwz	r2,secondary_ti@l(r1)
+	tophys(r1,r2)
+	lwz	r1,TASK_STACK(r1)
 
 	/* stack */
 	addi	r1,r1,THREAD_SIZE-STACK_FRAME_OVERHEAD

arch/powerpc/kernel/head_44x.S

@@ -1021,8 +1021,8 @@ _GLOBAL(start_secondary_47x)
 
 	/* Get current's stack and current */
 	lis	r1,secondary_ti@ha
-	lwz	r1,secondary_ti@l(r1)
-	lwz	r2,TI_TASK(r1)
+	lwz	r2,secondary_ti@l(r1)
+	lwz	r1,TASK_STACK(r2)
 
 	/* Current stack pointer */
 	addi	r1,r1,THREAD_SIZE-STACK_FRAME_OVERHEAD

arch/powerpc/kernel/head_booke.h

@@ -155,13 +155,7 @@ END_BTB_FLUSH_SECTION
 	stw	r10,GPR11(r11);						     \
 	b	2f;							     \
 	/* COMING FROM PRIV MODE */					     \
-1:	lwz	r9,TI_FLAGS-EXC_LVL_FRAME_OVERHEAD(r11);		     \
-	lwz	r10,TI_PREEMPT-EXC_LVL_FRAME_OVERHEAD(r11);		     \
-	stw	r9,TI_FLAGS-EXC_LVL_FRAME_OVERHEAD(r8);			     \
-	stw	r10,TI_PREEMPT-EXC_LVL_FRAME_OVERHEAD(r8);		     \
-	lwz	r9,TI_TASK-EXC_LVL_FRAME_OVERHEAD(r11);			     \
-	stw	r9,TI_TASK-EXC_LVL_FRAME_OVERHEAD(r8);			     \
-	mr	r11,r8;							     \
+1:	mr	r11, r8;							     \
 2:	mfspr	r8,SPRN_SPRG_RSCRATCH_##exc_level;			     \
 	stw	r12,GPR12(r11);		/* save various registers	   */\
 	mflr	r10;							     \

arch/powerpc/kernel/head_fsl_booke.S

@@ -719,8 +719,7 @@ finish_tlb_load:
 
 	/* Get the next_tlbcam_idx percpu var */
 #ifdef CONFIG_SMP
-	lwz	r12, TASK_STACK-THREAD(r12)
-	lwz	r15, TI_CPU(r12)
+	lwz	r15, TI_CPU-THREAD(r12)
 	lis     r14, __per_cpu_offset@h
 	ori     r14, r14, __per_cpu_offset@l
 	rlwinm  r15, r15, 2, 0, 29
@@ -1093,8 +1092,8 @@ __secondary_start:
 
 	/* get current's stack and current */
 	lis	r1,secondary_ti@ha
-	lwz	r1,secondary_ti@l(r1)
-	lwz	r2,TI_TASK(r1)
+	lwz	r2,secondary_ti@l(r1)
+	lwz	r1,TASK_STACK(r2)
 
 	/* stack */
 	addi	r1,r1,THREAD_SIZE-STACK_FRAME_OVERHEAD

arch/powerpc/kernel/irq.c

@@ -673,24 +673,9 @@ void do_IRQ(struct pt_regs *regs)
 		set_irq_regs(old_regs);
 		return;
 	}
-
-	/* Prepare the thread_info in the irq stack */
-	irqtp->task = curtp->task;
-	irqtp->flags = 0;
-
-	/* Copy the preempt_count so that the [soft]irq checks work. */
-	irqtp->preempt_count = curtp->preempt_count;
-
 	/* Switch stack and call */
 	call_do_irq(regs, irqtp);
 
-	/* Restore stack limit */
-	irqtp->task = NULL;
-
-	/* Copy back updates to the thread_info */
-	if (irqtp->flags)
-		set_bits(irqtp->flags, &curtp->flags);
-
 	set_irq_regs(old_regs);
 }
 
@@ -698,85 +683,23 @@ void __init init_IRQ(void)
 {
 	if (ppc_md.init_IRQ)
 		ppc_md.init_IRQ();
-
-	exc_lvl_ctx_init();
-
-	irq_ctx_init();
 }
 
 #if defined(CONFIG_BOOKE) || defined(CONFIG_40x)
 struct thread_info   *critirq_ctx[NR_CPUS] __read_mostly;
 struct thread_info    *dbgirq_ctx[NR_CPUS] __read_mostly;
 struct thread_info *mcheckirq_ctx[NR_CPUS] __read_mostly;
-
-void exc_lvl_ctx_init(void)
-{
-	struct thread_info *tp;
-	int i, cpu_nr;
-
-	for_each_possible_cpu(i) {
-#ifdef CONFIG_PPC64
-		cpu_nr = i;
-#else
-#ifdef CONFIG_SMP
-		cpu_nr = get_hard_smp_processor_id(i);
-#else
-		cpu_nr = 0;
-#endif
-#endif
-
-		tp = critirq_ctx[cpu_nr];
-		tp->cpu = cpu_nr;
-		tp->preempt_count = 0;
-
-#ifdef CONFIG_BOOKE
-		tp = dbgirq_ctx[cpu_nr];
-		tp->cpu = cpu_nr;
-		tp->preempt_count = 0;
-
-		tp = mcheckirq_ctx[cpu_nr];
-		tp->cpu = cpu_nr;
-		tp->preempt_count = HARDIRQ_OFFSET;
-#endif
-	}
-}
 #endif
 
 struct thread_info *softirq_ctx[NR_CPUS] __read_mostly;
 struct thread_info *hardirq_ctx[NR_CPUS] __read_mostly;
 
-void irq_ctx_init(void)
-{
-	struct thread_info *tp;
-	int i;
-
-	for_each_possible_cpu(i) {
-		tp = softirq_ctx[i];
-		tp->cpu = i;
-		klp_init_thread_info(tp);
-
-		tp = hardirq_ctx[i];
-		tp->cpu = i;
-		klp_init_thread_info(tp);
-	}
-}
-
 void do_softirq_own_stack(void)
 {
-	struct thread_info *curtp, *irqtp;
+	struct thread_info *irqtp;
 
-	curtp = current_thread_info();
 	irqtp = softirq_ctx[smp_processor_id()];
-	irqtp->task = curtp->task;
-	irqtp->flags = 0;
 	call_do_softirq(irqtp);
-	irqtp->task = NULL;
-
-	/* Set any flag that may have been set on the
-	 * alternate stack
-	 */
-	if (irqtp->flags)
-		set_bits(irqtp->flags, &curtp->flags);
 }
 
 irq_hw_number_t virq_to_hw(unsigned int virq)

arch/powerpc/kernel/kgdb.c

@@ -151,41 +151,13 @@ static int kgdb_handle_breakpoint(struct pt_regs *regs)
 	return 1;
 }
 
-static DEFINE_PER_CPU(struct thread_info, kgdb_thread_info);
 static int kgdb_singlestep(struct pt_regs *regs)
 {
-	struct thread_info *thread_info, *exception_thread_info;
-	struct thread_info *backup_current_thread_info =
-		this_cpu_ptr(&kgdb_thread_info);
-
 	if (user_mode(regs))
 		return 0;
 
-	/*
-	 * On Book E and perhaps other processors, singlestep is handled on
-	 * the critical exception stack.  This causes current_thread_info()
-	 * to fail, since it it locates the thread_info by masking off
-	 * the low bits of the current stack pointer.  We work around
-	 * this issue by copying the thread_info from the kernel stack
-	 * before calling kgdb_handle_exception, and copying it back
-	 * afterwards.  On most processors the copy is avoided since
-	 * exception_thread_info == thread_info.
-	 */
-	thread_info = (struct thread_info *)(regs->gpr[1] & ~(THREAD_SIZE-1));
-	exception_thread_info = current_thread_info();
-
-	if (thread_info != exception_thread_info) {
-		/* Save the original current_thread_info. */
-		memcpy(backup_current_thread_info, exception_thread_info, sizeof *thread_info);
-		memcpy(exception_thread_info, thread_info, sizeof *thread_info);
-	}
-
 	kgdb_handle_exception(0, SIGTRAP, 0, regs);
 
-	if (thread_info != exception_thread_info)
-		/* Restore current_thread_info lastly. */
-		memcpy(exception_thread_info, backup_current_thread_info, sizeof *thread_info);
-
 	return 1;
 }
 

arch/powerpc/kernel/machine_kexec_64.c

@@ -317,10 +317,8 @@ void default_machine_kexec(struct kimage *image)
 	 * We setup preempt_count to avoid using VMX in memcpy.
 	 * XXX: the task struct will likely be invalid once we do the copy!
 	 */
-	kexec_stack.thread_info.task = current_thread_info()->task;
-	kexec_stack.thread_info.flags = 0;
-	kexec_stack.thread_info.preempt_count = HARDIRQ_OFFSET;
-	kexec_stack.thread_info.cpu = current_thread_info()->cpu;
+	current_thread_info()->flags = 0;
+	current_thread_info()->preempt_count = HARDIRQ_OFFSET;
 
 	/* We need a static PACA, too; copy this CPU's PACA over and switch to
 	 * it. Also poison per_cpu_offset and NULL lppaca to catch anyone using

arch/powerpc/kernel/process.c

@@ -1634,7 +1634,7 @@ int copy_thread(unsigned long clone_flags, unsigned long usp,
 	unsigned long sp = (unsigned long)task_stack_page(p) + THREAD_SIZE;
 	struct thread_info *ti = task_thread_info(p);
 
-	klp_init_thread_info(ti);
+	klp_init_thread_info(p);
 
 	/* Copy registers */
 	sp -= sizeof(struct pt_regs);

arch/powerpc/kernel/setup-common.c

@@ -937,7 +937,7 @@ void __init setup_arch(char **cmdline_p)
 	/* Reserve large chunks of memory for use by CMA for KVM. */
 	kvm_cma_reserve();
 
-	klp_init_thread_info(&init_thread_info);
+	klp_init_thread_info(&init_task);
 
 	init_mm.start_code = (unsigned long)_stext;
 	init_mm.end_code = (unsigned long) _etext;

arch/powerpc/kernel/setup_64.c

@@ -689,24 +689,6 @@ void __init exc_lvl_early_init(void)
 }
 #endif
 
-/*
- * Emergency stacks are used for a range of things, from asynchronous
- * NMIs (system reset, machine check) to synchronous, process context.
- * We set preempt_count to zero, even though that isn't necessarily correct. To
- * get the right value we'd need to copy it from the previous thread_info, but
- * doing that might fault causing more problems.
- * TODO: what to do with accounting?
- */
-static void emerg_stack_init_thread_info(struct thread_info *ti, int cpu)
-{
-	ti->task = NULL;
-	ti->cpu = cpu;
-	ti->preempt_count = 0;
-	ti->local_flags = 0;
-	ti->flags = 0;
-	klp_init_thread_info(ti);
-}
-
 /*
  * Stack space used when we detect a bad kernel stack pointer, and
  * early in SMP boots before relocation is enabled. Exclusive emergency
@@ -737,18 +719,15 @@ void __init emergency_stack_init(void)
 		struct thread_info *ti;
 
 		ti = alloc_stack(limit, i);
-		emerg_stack_init_thread_info(ti, i);
 		paca_ptrs[i]->emergency_sp = (void *)ti + THREAD_SIZE;
 
 #ifdef CONFIG_PPC_BOOK3S_64
 		/* emergency stack for NMI exception handling. */
 		ti = alloc_stack(limit, i);
-		emerg_stack_init_thread_info(ti, i);
 		paca_ptrs[i]->nmi_emergency_sp = (void *)ti + THREAD_SIZE;
 
 		/* emergency stack for machine check exception handling. */
 		ti = alloc_stack(limit, i);
-		emerg_stack_init_thread_info(ti, i);
 		paca_ptrs[i]->mc_emergency_sp = (void *)ti + THREAD_SIZE;
 #endif
 	}

arch/powerpc/kernel/smp.c

@@ -988,7 +988,7 @@ static void cpu_idle_thread_init(unsigned int cpu, struct task_struct *idle)
 	paca_ptrs[cpu]->kstack = (unsigned long)task_stack_page(idle) +
 				 THREAD_SIZE - STACK_FRAME_OVERHEAD;
 #endif
-	ti->cpu = cpu;
+	idle->cpu = cpu;
 	secondary_ti = current_set[cpu] = ti;
 }
 

arch/powerpc/net/bpf_jit32.h

@@ -106,9 +106,8 @@ DECLARE_LOAD_FUNC(sk_load_byte_msh);
 	} while (0)
 #else
 #define PPC_BPF_LOAD_CPU(r)     \
-	do { BUILD_BUG_ON(FIELD_SIZEOF(struct thread_info, cpu) != 4);		\
-		PPC_LHZ_OFFS(r, (1 & ~(THREAD_SIZE - 1)),			\
-				offsetof(struct thread_info, cpu));		\
+	do { BUILD_BUG_ON(FIELD_SIZEOF(struct task_struct, cpu) != 4);		\
+		PPC_LHZ_OFFS(r, 2, offsetof(struct task_struct, cpu));		\
 	} while(0)
 #endif
 #else