[PATCH v3 0/9] MMU disabling code and kexec fixes

@@ -120,17 +120,22 @@ static void l2x0_cache_sync(void)
 	spin_unlock_irqrestore(&l2x0_lock, flags);
 }
 
-static void l2x0_flush_all(void)
+static void __l2x0_flush_all(void)
 {
-	unsigned long flags;
-
-	/* clean all ways */
-	spin_lock_irqsave(&l2x0_lock, flags);
 	debug_writel(0x03);
 	writel_relaxed(l2x0_way_mask, l2x0_base + L2X0_CLEAN_INV_WAY);
 	cache_wait_way(l2x0_base + L2X0_CLEAN_INV_WAY, l2x0_way_mask);
 	cache_sync();
 	debug_writel(0x00);
+}
+
+static void l2x0_flush_all(void)
+{
+	unsigned long flags;
+
+	/* clean all ways */
+	spin_lock_irqsave(&l2x0_lock, flags);
+	__l2x0_flush_all();
 	spin_unlock_irqrestore(&l2x0_lock, flags);
 }
 

@@ -266,7 +271,9 @@ static void l2x0_disable(void)
 	unsigned long flags;
 
 	spin_lock_irqsave(&l2x0_lock, flags);
-	writel(0, l2x0_base + L2X0_CTRL);
+	__l2x0_flush_all();
+	writel_relaxed(0, l2x0_base + L2X0_CTRL);
+	dsb();
 	spin_unlock_irqrestore(&l2x0_lock, flags);
 }
 

@@ -56,6 +56,11 @@ ENTRY(cpu_v6_proc_fin)
  */
 	.align	5
 ENTRY(cpu_v6_reset)
+	mrc	p15, 0, r1, c1, c0, 0		@ ctrl register
+	bic	r1, r1, #0x1			@ ...............m
+	mcr	p15, 0, r1, c1, c0, 0		@ disable MMU
+	mov	r1, #0
+	mcr	p15, 0, r1, c7, c5, 4		@ ISB
 	mov	pc, r0
 
 /*

@@ -58,9 +58,16 @@ ENDPROC(cpu_v7_proc_fin)
  *	to what would be the reset vector.
  *
  *	- loc   - location to jump to for soft reset
+ *
+ *	This code must be executed using a flat identity mapping with
+ *      caches disabled.
  */
 	.align	5
 ENTRY(cpu_v7_reset)
+	mrc	p15, 0, r1, c1, c0, 0		@ ctrl register
+	bic	r1, r1, #0x1			@ ...............m
+	mcr	p15, 0, r1, c1, c0, 0		@ disable MMU
+	isb
 	mov	pc, r0
 ENDPROC(cpu_v7_reset)
 

@@ -13,7 +13,8 @@ lib-y		:= backtrace.o changebit.o csumipv6.o csumpartial.o   \
 		   testchangebit.o testclearbit.o testsetbit.o        \
 		   ashldi3.o ashrdi3.o lshrdi3.o muldi3.o             \
 		   ucmpdi2.o lib1funcs.o div64.o sha1.o               \
-		   io-readsb.o io-writesb.o io-readsl.o io-writesl.o
+		   io-readsb.o io-writesb.o io-readsl.o io-writesl.o  \
+		   switch_stack.o
 
 mmu-y	:= clear_user.o copy_page.o getuser.o putuser.o
 

@@ -0,0 +1,44 @@
+/*
+ * arch/arm/lib/switch_stack.S
+ *
+ * Copyright (C) 2011 ARM Ltd.
+ * Written by Will Deacon <will.deacon@arm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+ */
+
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+
+/*
+ * void switch_stack(void (*fn)(void *), void *arg, void *sp)
+ *
+ * Change the stack to that pointed at by sp, then invoke fn(arg) with
+ * the new stack.
+ */
+ENTRY(switch_stack)
+	str	sp, [r2, #-4]!
+	str	lr, [r2, #-4]!
+
+	mov	sp, r2
+	mov	r2, r0
+	mov	r0, r1
+
+	adr	lr, BSYM(1f)
+	mov	pc, r2
+
+1:	ldr	lr, [sp]
+	ldr	sp, [sp, #4]
+	mov	pc, lr
+ENDPROC(switch_stack)

@@ -0,0 +1,16 @@
+#ifndef _ARM_IDMAP_H
+#define _ARM_IDMAP_H
+
+#include <asm/page.h>
+
+void identity_mapping_add(pgd_t *pgd, unsigned long addr, unsigned long end);
+
+#ifdef CONFIG_SMP
+void identity_mapping_del(pgd_t *pgd, unsigned long addr, unsigned long end);
+#else
+void identity_mapping_del(pgd_t *pgd, unsigned long addr, unsigned long end) {};
+#endif
+
+void setup_mm_for_reboot(char mode);
+
+#endif	/* _ARM_IDMAP_H */

@@ -474,9 +474,6 @@ static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
 
 #define pgtable_cache_init() do { } while (0)
 
-void identity_mapping_add(pgd_t *, unsigned long, unsigned long);
-void identity_mapping_del(pgd_t *, unsigned long, unsigned long);
-
 #endif /* !__ASSEMBLY__ */
 
 #endif /* CONFIG_MMU */

@@ -32,6 +32,7 @@
 #include <linux/hw_breakpoint.h>
 
 #include <asm/cacheflush.h>
+#include <asm/idmap.h>
 #include <asm/leds.h>
 #include <asm/processor.h>
 #include <asm/system.h>

@@ -56,8 +57,6 @@ static const char *isa_modes[] = {
   "ARM" , "Thumb" , "Jazelle", "ThumbEE"
 };
 
-extern void setup_mm_for_reboot(char mode);
-
 static volatile int hlt_counter;
 
 #include <mach/system.h>

@@ -39,6 +39,7 @@
 #include <asm/tlbflush.h>
 #include <asm/ptrace.h>
 #include <asm/localtimer.h>
+#include <asm/idmap.h>
 
 /*
  * as from 2.5, kernels no longer have an init_tasks structure

@@ -1,6 +1,7 @@
 #include <linux/kernel.h>
 
 #include <asm/cputype.h>
+#include <asm/idmap.h>
 #include <asm/pgalloc.h>
 #include <asm/pgtable.h>
 

@@ -2,6 +2,7 @@
 #define _ARM_IDMAP_H
 
 #include <asm/page.h>
+#include <asm/sections.h>
 
 void identity_mapping_add(pgd_t *pgd, unsigned long addr, unsigned long end);
 

@@ -11,6 +12,12 @@ void identity_mapping_del(pgd_t *pgd, unsigned long addr, unsigned long end);
 void identity_mapping_del(pgd_t *pgd, unsigned long addr, unsigned long end) {};
 #endif
 
+/* Modes understood from arm_machine_{restart,reset}. */
+#define MODE_REMAP_KERNEL	'k'
+
+/* Page reserved after the kernel image. */
+#define RESERVE_STACK_PAGE	ALIGN((unsigned long)_end + PAGE_SIZE, PMD_SIZE)
+
 void setup_mm_for_reboot(char mode);
 
 #endif	/* _ARM_IDMAP_H */

@@ -75,17 +75,29 @@ void identity_mapping_del(pgd_t *pgd, unsigned long addr, unsigned long end)
 #endif
 
 /*
- * In order to soft-boot, we need to insert a 1:1 mapping in place of
- * the user-mode pages.  This will then ensure that we have predictable
- * results when turning the mmu off
+ * In order to soft-boot, we need to insert a 1:1 mapping of memory.
+ * This will then ensure that we have predictable results when turning
+ * the mmu off.
  */
 void setup_mm_for_reboot(char mode)
 {
-	/*
-	 * We need to access to user-mode page tables here. For kernel threads
-	 * we don't have any user-mode mappings so we use the context that we
-	 * "borrowed".
-	 */
-	identity_mapping_add(current->active_mm->pgd, 0, TASK_SIZE);
+
+	identity_mapping_add(swapper_pg_dir, 0, TASK_SIZE);
+	if (mode == MODE_REMAP_KERNEL) {
+		/*
+		 * Extend the flat mapping into kernelspace.
+		 * We leave room for the kernel image and a `reboot stack'.
+		 */
+		identity_mapping_add(swapper_pg_dir, TASK_SIZE, PAGE_OFFSET);
+		identity_mapping_add(swapper_pg_dir, RESERVE_STACK_PAGE, 0);
+	}
+
+	/* Clean and invalidate L1. */
+	flush_cache_all();
+
+	/* Switch exclusively to kernel mappings. */
+	cpu_switch_mm(swapper_pg_dir, &init_mm);
+
+	/* Flush the TLB. */
 	local_flush_tlb_all();
 }

@@ -82,13 +82,13 @@ extern void cpu_do_switch_mm(unsigned long pgd_phys, struct mm_struct *mm);
 extern void cpu_set_pte_ext(pte_t *ptep, pte_t pte, unsigned int ext);
 extern void cpu_reset(unsigned long addr) __attribute__((noreturn));
 #else
-#define cpu_proc_init()			processor._proc_init()
-#define cpu_proc_fin()			processor._proc_fin()
-#define cpu_reset(addr)			processor.reset(addr)
-#define cpu_do_idle()			processor._do_idle()
-#define cpu_dcache_clean_area(addr,sz)	processor.dcache_clean_area(addr,sz)
-#define cpu_set_pte_ext(ptep,pte,ext)	processor.set_pte_ext(ptep,pte,ext)
-#define cpu_do_switch_mm(pgd,mm)	processor.switch_mm(pgd,mm)
+#define cpu_proc_init			processor._proc_init
+#define cpu_proc_fin			processor._proc_fin
+#define cpu_reset			processor.reset
+#define cpu_do_idle			processor._do_idle
+#define cpu_dcache_clean_area		processor.dcache_clean_area
+#define cpu_set_pte_ext			processor.set_pte_ext
+#define cpu_do_switch_mm		processor.switch_mm
 #endif
 
 extern void cpu_resume(void);

@@ -108,6 +108,7 @@ extern int cpu_architecture(void);
 extern void cpu_init(void);
 
 void arm_machine_restart(char mode, const char *cmd);
+void arm_machine_reset(unsigned long reset_code_phys);
 extern void (*arm_pm_restart)(char str, const char *cmd);
 
 #define UDBG_UNDEFINED	(1 << 0)

@@ -90,12 +90,10 @@ static int __init hlt_setup(char *__unused)
 __setup("nohlt", nohlt_setup);
 __setup("hlt", hlt_setup);
 
-void arm_machine_restart(char mode, const char *cmd)
-{
-	/* Disable interrupts first */
-	local_irq_disable();
-	local_fiq_disable();
+extern void switch_stack(void (*fn)(void *), void *arg, void *sp);
 
+static void prepare_for_reboot(char mode)
+{
 	/*
 	 * Tell the mm system that we are going to reboot -
 	 * we may need it to insert some 1:1 mappings so that

@@ -103,14 +101,20 @@ void arm_machine_restart(char mode, const char *cmd)
 	 */
 	setup_mm_for_reboot(mode);
 
-	/* Clean and invalidate caches */
-	flush_cache_all();
-
 	/* Turn off caching */
 	cpu_proc_fin();
 
 	/* Push out any further dirty data, and ensure cache is empty */
 	flush_cache_all();
+}
+
+void arm_machine_restart(char mode, const char *cmd)
+{
+	/* Disable interrupts first */
+	local_irq_disable();
+	local_fiq_disable();
+
+	prepare_for_reboot(mode);
 
 	/*
 	 * Now call the architecture specific reboot code.

@@ -126,6 +130,50 @@ void arm_machine_restart(char mode, const char *cmd)
 	while (1);
 }
 
+typedef void (*phys_reset_t)(unsigned long);
+void __arm_machine_reset(void *reset_code_phys)
+{
+	phys_reset_t phys_reset;
+
+	prepare_for_reboot(MODE_REMAP_KERNEL);
+
+	/* Switch to the identity mapping. */
+	phys_reset = (phys_reset_t)virt_to_phys(cpu_reset);
+	phys_reset((unsigned long)reset_code_phys);
+
+	/* Should never get here. */
+	BUG();
+}
+
+void arm_machine_reset(unsigned long reset_code_phys)
+{
+	phys_addr_t cpu_reset_end_phys;
+	void *cpu_reset_end, *new_stack = (void *)RESERVE_STACK_PAGE;
+
+	cpu_reset_end = (void *)PAGE_ALIGN((unsigned long)cpu_reset);
+	cpu_reset_end_phys = virt_to_phys(cpu_reset_end);
+
+	/* Check that we can safely identity map the reset code. */
+	BUG_ON(cpu_reset_end_phys > TASK_SIZE &&
+	       cpu_reset_end_phys <= RESERVE_STACK_PAGE);
+
+	/* Check that the reserve stack page is valid memory. */
+	BUG_ON(!pfn_valid(__phys_to_pfn(virt_to_phys(new_stack - 1))));
+
+	/* Disable interrupts first. */
+	local_irq_disable();
+	local_fiq_disable();
+
+	/* Disable the L2. */
+	outer_disable();
+
+	/* Change to the new stack and continue with the reset. */
+	switch_stack(__arm_machine_reset, (void *)reset_code_phys, new_stack);
+
+	/* Should never get here. */
+	BUG();
+}
+
 /*
  * Function pointers to optional machine specific functions
  */

@@ -16,8 +16,6 @@
 extern const unsigned char relocate_new_kernel[];
 extern const unsigned int relocate_new_kernel_size;
 
-extern void setup_mm_for_reboot(char mode);
-
 extern unsigned long kexec_start_address;
 extern unsigned long kexec_indirection_page;
 extern unsigned long kexec_mach_type;

@@ -111,14 +109,6 @@ void machine_kexec(struct kimage *image)
 
 	if (kexec_reinit)
 		kexec_reinit();
-	local_irq_disable();
-	local_fiq_disable();
-	setup_mm_for_reboot(0); /* mode is not used, so just pass 0*/
-	flush_cache_all();
-	outer_flush_all();
-	outer_disable();
-	cpu_proc_fin();
-	outer_inv_all();
-	flush_cache_all();
-	cpu_reset(reboot_code_buffer_phys);
+
+	arm_machine_reset(reboot_code_buffer_phys);
 }

@@ -1795,7 +1795,7 @@ config XIP_PHYS_ADDR
 
 config KEXEC
 	bool "Kexec system call (EXPERIMENTAL)"
-	depends on EXPERIMENTAL
+	depends on EXPERIMENTAL && (!SMP || HOTPLUG_CPU)
 	help
 	  kexec is a system call that implements the ability to shutdown your
 	  current kernel, and to start another kernel.  It is like a reboot

@@ -548,6 +548,10 @@ static void ipi_cpu_stop(unsigned int cpu)
 	local_fiq_disable();
 	local_irq_disable();
 
+#ifdef CONFIG_HOTPLUG_CPU
+	platform_cpu_kill(cpu);
+#endif
+
 	while (1)
 		cpu_relax();
 }