powerpc: regain entire stack space

thread_info is not anymore in the stack, so the entire stack
can now be used.

There is also no risk anymore of corrupting task_cpu(p) with a
stack overflow so the patch removes the test.

When doing this, an explicit test for NULL stack pointer is
needed in validate_sp() as it is not anymore implicitely covered
by the sizeof(thread_info) gap.

In the meantime, with the previous patch all pointers to the stacks
are not anymore pointers to thread_info so this patch changes them
to void*

Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>

8 files changed, 38 insertions, 55 deletions

diff --git a/arch/powerpc/include/asm/irq.h b/arch/powerpc/include/asm/irq.h
index 28a7ace0a1b9..c91a60cda4fa 100644
--- a/arch/powerpc/include/asm/irq.h
+++ b/arch/powerpc/include/asm/irq.h
@@ -48,16 +48,16 @@ struct pt_regs;
  * Per-cpu stacks for handling critical, debug and machine check
  * level interrupts.
  */
-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 *critirq_ctx[NR_CPUS];
+extern void *dbgirq_ctx[NR_CPUS];
+extern void *mcheckirq_ctx[NR_CPUS];
 #endif
 
 /*
  * Per-cpu stacks for handling hard and soft interrupts.
  */
-extern struct thread_info *hardirq_ctx[NR_CPUS];
-extern struct thread_info *softirq_ctx[NR_CPUS];
+extern void *hardirq_ctx[NR_CPUS];
+extern void *softirq_ctx[NR_CPUS];
 
 void call_do_softirq(void *sp);
 void call_do_irq(struct pt_regs *regs, void *sp);
diff --git a/arch/powerpc/include/asm/processor.h b/arch/powerpc/include/asm/processor.h
index 2c740042b8d3..3351bcf42f2d 100644
--- a/arch/powerpc/include/asm/processor.h
+++ b/arch/powerpc/include/asm/processor.h
@@ -270,8 +270,7 @@ struct thread_struct {
 #define ARCH_MIN_TASKALIGN 16
 
 #define INIT_SP		(sizeof(init_stack) + (unsigned long) &init_stack)
-#define INIT_SP_LIMIT \
-	(_ALIGN_UP(sizeof(struct thread_info), 16) + (unsigned long)&init_stack)
+#define INIT_SP_LIMIT	((unsigned long)&init_stack)
 
 #ifdef CONFIG_SPE
 #define SPEFSCR_INIT \
diff --git a/arch/powerpc/kernel/asm-offsets.c b/arch/powerpc/kernel/asm-offsets.c
index ca3fb836cbb9..1ad0cbcc5f13 100644
--- a/arch/powerpc/kernel/asm-offsets.c
+++ b/arch/powerpc/kernel/asm-offsets.c
@@ -92,7 +92,6 @@ int main(void)
 	DEFINE(SIGSEGV, SIGSEGV);
 	DEFINE(NMI_MASK, NMI_MASK);
 #else
-	DEFINE(THREAD_INFO_GAP, _ALIGN_UP(sizeof(struct thread_info), 16));
 	OFFSET(KSP_LIMIT, thread_struct, ksp_limit);
 #ifdef CONFIG_PPC_RTAS
 	OFFSET(RTAS_SP, thread_struct, rtas_sp);
diff --git a/arch/powerpc/kernel/entry_32.S b/arch/powerpc/kernel/entry_32.S
index f3618353c1c4..424e7265e790 100644
--- a/arch/powerpc/kernel/entry_32.S
+++ b/arch/powerpc/kernel/entry_32.S
@@ -97,14 +97,11 @@ crit_transfer_to_handler:
 	mfspr	r0,SPRN_SRR1
 	stw	r0,_SRR1(r11)
 
-	/* set the stack limit to the current stack
-	 * and set the limit to protect the thread_info
-	 * struct
-	 */
+	/* set the stack limit to the current stack */
 	mfspr	r8,SPRN_SPRG_THREAD
 	lwz	r0,KSP_LIMIT(r8)
 	stw	r0,SAVED_KSP_LIMIT(r11)
-	rlwimi	r0,r1,0,0,(31-THREAD_SHIFT)
+	rlwinm	r0,r1,0,0,(31 - THREAD_SHIFT)
 	stw	r0,KSP_LIMIT(r8)
 	/* fall through */
 #endif
@@ -121,14 +118,11 @@ crit_transfer_to_handler:
 	mfspr	r0,SPRN_SRR1
 	stw	r0,crit_srr1@l(0)
 
-	/* set the stack limit to the current stack
-	 * and set the limit to protect the thread_info
-	 * struct
-	 */
+	/* set the stack limit to the current stack */
 	mfspr	r8,SPRN_SPRG_THREAD
 	lwz	r0,KSP_LIMIT(r8)
 	stw	r0,saved_ksp_limit@l(0)
-	rlwimi	r0,r1,0,0,(31-THREAD_SHIFT)
+	rlwinm	r0,r1,0,0,(31 - THREAD_SHIFT)
 	stw	r0,KSP_LIMIT(r8)
 	/* fall through */
 #endif
diff --git a/arch/powerpc/kernel/irq.c b/arch/powerpc/kernel/irq.c
index 85c48911938a..938944c6e2ee 100644
--- a/arch/powerpc/kernel/irq.c
+++ b/arch/powerpc/kernel/irq.c
@@ -618,9 +618,8 @@ static inline void check_stack_overflow(void)
 	sp = current_stack_pointer() & (THREAD_SIZE-1);
 
 	/* check for stack overflow: is there less than 2KB free? */
-	if (unlikely(sp < (sizeof(struct thread_info) + 2048))) {
-		pr_err("do_IRQ: stack overflow: %ld\n",
-			sp - sizeof(struct thread_info));
+	if (unlikely(sp < 2048)) {
+		pr_err("do_IRQ: stack overflow: %ld\n", sp);
 		dump_stack();
 	}
 #endif
@@ -660,7 +659,7 @@ void __do_irq(struct pt_regs *regs)
 void do_IRQ(struct pt_regs *regs)
 {
 	struct pt_regs *old_regs = set_irq_regs(regs);
-	struct thread_info *curtp, *irqtp, *sirqtp;
+	void *curtp, *irqtp, *sirqtp;
 
 	/* Switch to the irq stack to handle this */
 	curtp = (void *)(current_stack_pointer() & ~(THREAD_SIZE - 1));
@@ -686,17 +685,17 @@ void __init init_IRQ(void)
 }
 
 #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   *critirq_ctx[NR_CPUS] __read_mostly;
+void    *dbgirq_ctx[NR_CPUS] __read_mostly;
+void *mcheckirq_ctx[NR_CPUS] __read_mostly;
 #endif
 
-struct thread_info *softirq_ctx[NR_CPUS] __read_mostly;
-struct thread_info *hardirq_ctx[NR_CPUS] __read_mostly;
+void *softirq_ctx[NR_CPUS] __read_mostly;
+void *hardirq_ctx[NR_CPUS] __read_mostly;
 
 void do_softirq_own_stack(void)
 {
-	struct thread_info *irqtp;
+	void *irqtp;
 
 	irqtp = softirq_ctx[smp_processor_id()];
 	call_do_softirq(irqtp);
diff --git a/arch/powerpc/kernel/misc_32.S b/arch/powerpc/kernel/misc_32.S
index b37b50fde828..6f6127c3760c 100644
--- a/arch/powerpc/kernel/misc_32.S
+++ b/arch/powerpc/kernel/misc_32.S
@@ -46,11 +46,10 @@ _GLOBAL(call_do_softirq)
 	mflr	r0
 	stw	r0,4(r1)
 	lwz	r10,THREAD+KSP_LIMIT(r2)
-	addi	r11,r3,THREAD_INFO_GAP
+	stw	r3, THREAD+KSP_LIMIT(r2)
 	stwu	r1,THREAD_SIZE-STACK_FRAME_OVERHEAD(r3)
 	mr	r1,r3
 	stw	r10,8(r1)
-	stw	r11,THREAD+KSP_LIMIT(r2)
 	bl	__do_softirq
 	lwz	r10,8(r1)
 	lwz	r1,0(r1)
@@ -66,11 +65,10 @@ _GLOBAL(call_do_irq)
 	mflr	r0
 	stw	r0,4(r1)
 	lwz	r10,THREAD+KSP_LIMIT(r2)
-	addi	r11,r4,THREAD_INFO_GAP
+	stw	r4, THREAD+KSP_LIMIT(r2)
 	stwu	r1,THREAD_SIZE-STACK_FRAME_OVERHEAD(r4)
 	mr	r1,r4
 	stw	r10,8(r1)
-	stw	r11,THREAD+KSP_LIMIT(r2)
 	bl	__do_irq
 	lwz	r10,8(r1)
 	lwz	r1,0(r1)
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index fd07711035bd..dd9e0d5386ee 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -1691,8 +1691,7 @@ int copy_thread(unsigned long clone_flags, unsigned long usp,
 	sp -= STACK_FRAME_OVERHEAD;
 	p->thread.ksp = sp;
 #ifdef CONFIG_PPC32
-	p->thread.ksp_limit = (unsigned long)task_stack_page(p) +
-				_ALIGN_UP(sizeof(struct thread_info), 16);
+	p->thread.ksp_limit = (unsigned long)end_of_stack(p);
 #endif
 #ifdef CONFIG_HAVE_HW_BREAKPOINT
 	p->thread.ptrace_bps[0] = NULL;
@@ -1995,21 +1994,14 @@ static inline int valid_irq_stack(unsigned long sp, struct task_struct *p,
 	unsigned long stack_page;
 	unsigned long cpu = task_cpu(p);
 
-	/*
-	 * Avoid crashing if the stack has overflowed and corrupted
-	 * task_cpu(p), which is in the thread_info struct.
-	 */
-	if (cpu < NR_CPUS && cpu_possible(cpu)) {
-		stack_page = (unsigned long) hardirq_ctx[cpu];
-		if (sp >= stack_page + sizeof(struct thread_struct)
-		    && sp <= stack_page + THREAD_SIZE - nbytes)
-			return 1;
-
-		stack_page = (unsigned long) softirq_ctx[cpu];
-		if (sp >= stack_page + sizeof(struct thread_struct)
-		    && sp <= stack_page + THREAD_SIZE - nbytes)
-			return 1;
-	}
+	stack_page = (unsigned long)hardirq_ctx[cpu];
+	if (sp >= stack_page && sp <= stack_page + THREAD_SIZE - nbytes)
+		return 1;
+
+	stack_page = (unsigned long)softirq_ctx[cpu];
+	if (sp >= stack_page && sp <= stack_page + THREAD_SIZE - nbytes)
+		return 1;
+
 	return 0;
 }
 
@@ -2018,8 +2010,10 @@ int validate_sp(unsigned long sp, struct task_struct *p,
 {
 	unsigned long stack_page = (unsigned long)task_stack_page(p);
 
-	if (sp >= stack_page + sizeof(struct thread_struct)
-	    && sp <= stack_page + THREAD_SIZE - nbytes)
+	if (sp < THREAD_SIZE)
+		return 0;
+
+	if (sp >= stack_page && sp <= stack_page + THREAD_SIZE - nbytes)
 		return 1;
 
 	return valid_irq_stack(sp, p, nbytes);
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index 0912948a8ea6..2db1c5f7d141 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -716,19 +716,19 @@ void __init emergency_stack_init(void)
 	limit = min(ppc64_bolted_size(), ppc64_rma_size);
 
 	for_each_possible_cpu(i) {
-		struct thread_info *ti;
+		void *ti;
 
 		ti = alloc_stack(limit, i);
-		paca_ptrs[i]->emergency_sp = (void *)ti + THREAD_SIZE;
+		paca_ptrs[i]->emergency_sp = ti + THREAD_SIZE;
 
 #ifdef CONFIG_PPC_BOOK3S_64
 		/* emergency stack for NMI exception handling. */
 		ti = alloc_stack(limit, i);
-		paca_ptrs[i]->nmi_emergency_sp = (void *)ti + THREAD_SIZE;
+		paca_ptrs[i]->nmi_emergency_sp = ti + THREAD_SIZE;
 
 		/* emergency stack for machine check exception handling. */
 		ti = alloc_stack(limit, i);
-		paca_ptrs[i]->mc_emergency_sp = (void *)ti + THREAD_SIZE;
+		paca_ptrs[i]->mc_emergency_sp = ti + THREAD_SIZE;
 #endif
 	}
 }