Merge branch 'fixes' of git://git.linaro.org/people/rmk/linux-arm

Pull ARM fixes from Russell King:
 "The larger changes this time are

   - "ARM: 7755/1: handle user space mapped pages in flush_kernel_dcache_page"
     which fixes more data corruption problems with O_DIRECT

   - "ARM: 7759/1: decouple CPU offlining from reboot/shutdown" which
     gets us back to working shutdown/reboot on SMP platforms

   - "ARM: 7752/1: errata: LoUIS bit field in CLIDR register is incorrect"
     which fixes a shutdown regression found in v3.10 on Versatile
     Express platforms.

  The remainder are the quite small, maybe one or two line changes"

* 'fixes' of git://git.linaro.org/people/rmk/linux-arm:
  ARM: 7759/1: decouple CPU offlining from reboot/shutdown
  ARM: 7756/1: zImage/virt: remove hyp-stub.S during distclean
  ARM: 7755/1: handle user space mapped pages in flush_kernel_dcache_page
  ARM: 7754/1: Fix the CPU ID and the mask associated to the PJ4B
  ARM: 7753/1: map_init_section flushes incorrect pmd
  ARM: 7752/1: errata: LoUIS bit field in CLIDR register is incorrect

10 files changed, 103 insertions, 29 deletions

diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 49d993cee512..2651b1da1c56 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -1189,6 +1189,16 @@ config PL310_ERRATA_588369
 	   is not correctly implemented in PL310 as clean lines are not
 	   invalidated as a result of these operations.
 
+config ARM_ERRATA_643719
+	bool "ARM errata: LoUIS bit field in CLIDR register is incorrect"
+	depends on CPU_V7 && SMP
+	help
+	  This option enables the workaround for the 643719 Cortex-A9 (prior to
+	  r1p0) erratum. On affected cores the LoUIS bit field of the CLIDR
+	  register returns zero when it should return one. The workaround
+	  corrects this value, ensuring cache maintenance operations which use
+	  it behave as intended and avoiding data corruption.
+
 config ARM_ERRATA_720789
 	bool "ARM errata: TLBIASIDIS and TLBIMVAIS operations can broadcast a faulty ASID"
 	depends on CPU_V7
@@ -2006,7 +2016,7 @@ config XIP_PHYS_ADDR
 
 config KEXEC
 	bool "Kexec system call (EXPERIMENTAL)"
-	depends on (!SMP || HOTPLUG_CPU)
+	depends on (!SMP || PM_SLEEP_SMP)
 	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
diff --git a/arch/arm/boot/compressed/Makefile b/arch/arm/boot/compressed/Makefile
index 79e9bdbfc491..120b83bfde20 100644
--- a/arch/arm/boot/compressed/Makefile
+++ b/arch/arm/boot/compressed/Makefile
@@ -116,7 +116,8 @@ targets       := vmlinux vmlinux.lds \
 
 # Make sure files are removed during clean
 extra-y       += piggy.gzip piggy.lzo piggy.lzma piggy.xzkern \
-		 lib1funcs.S ashldi3.S $(libfdt) $(libfdt_hdrs)
+		 lib1funcs.S ashldi3.S $(libfdt) $(libfdt_hdrs) \
+		 hyp-stub.S
 
 ifeq ($(CONFIG_FUNCTION_TRACER),y)
 ORIG_CFLAGS := $(KBUILD_CFLAGS)
diff --git a/arch/arm/include/asm/cacheflush.h b/arch/arm/include/asm/cacheflush.h
index bff71388e72a..17d0ae8672fa 100644
--- a/arch/arm/include/asm/cacheflush.h
+++ b/arch/arm/include/asm/cacheflush.h
@@ -320,9 +320,7 @@ static inline void flush_anon_page(struct vm_area_struct *vma,
 }
 
 #define ARCH_HAS_FLUSH_KERNEL_DCACHE_PAGE
-static inline void flush_kernel_dcache_page(struct page *page)
-{
-}
+extern void flush_kernel_dcache_page(struct page *);
 
 #define flush_dcache_mmap_lock(mapping) \
 	spin_lock_irq(&(mapping)->tree_lock)
diff --git a/arch/arm/kernel/machine_kexec.c b/arch/arm/kernel/machine_kexec.c
index 8ef8c9337809..4fb074c446bf 100644
--- a/arch/arm/kernel/machine_kexec.c
+++ b/arch/arm/kernel/machine_kexec.c
@@ -134,6 +134,10 @@ void machine_kexec(struct kimage *image)
 	unsigned long reboot_code_buffer_phys;
 	void *reboot_code_buffer;
 
+	if (num_online_cpus() > 1) {
+		pr_err("kexec: error: multiple CPUs still online\n");
+		return;
+	}
 
 	page_list = image->head & PAGE_MASK;
 
diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c
index 282de4826abb..6e8931ccf13e 100644
--- a/arch/arm/kernel/process.c
+++ b/arch/arm/kernel/process.c
@@ -184,30 +184,61 @@ int __init reboot_setup(char *str)
 
 __setup("reboot=", reboot_setup);
 
+/*
+ * Called by kexec, immediately prior to machine_kexec().
+ *
+ * This must completely disable all secondary CPUs; simply causing those CPUs
+ * to execute e.g. a RAM-based pin loop is not sufficient. This allows the
+ * kexec'd kernel to use any and all RAM as it sees fit, without having to
+ * avoid any code or data used by any SW CPU pin loop. The CPU hotplug
+ * functionality embodied in disable_nonboot_cpus() to achieve this.
+ */
 void machine_shutdown(void)
 {
-#ifdef CONFIG_SMP
-	smp_send_stop();
-#endif
+	disable_nonboot_cpus();
 }
 
+/*
+ * Halting simply requires that the secondary CPUs stop performing any
+ * activity (executing tasks, handling interrupts). smp_send_stop()
+ * achieves this.
+ */
 void machine_halt(void)
 {
-	machine_shutdown();
+	smp_send_stop();
+
 	local_irq_disable();
 	while (1);
 }
 
+/*
+ * Power-off simply requires that the secondary CPUs stop performing any
+ * activity (executing tasks, handling interrupts). smp_send_stop()
+ * achieves this. When the system power is turned off, it will take all CPUs
+ * with it.
+ */
 void machine_power_off(void)
 {
-	machine_shutdown();
+	smp_send_stop();
+
 	if (pm_power_off)
 		pm_power_off();
 }
 
+/*
+ * Restart requires that the secondary CPUs stop performing any activity
+ * while the primary CPU resets the system. Systems with a single CPU can
+ * use soft_restart() as their machine descriptor's .restart hook, since that
+ * will cause the only available CPU to reset. Systems with multiple CPUs must
+ * provide a HW restart implementation, to ensure that all CPUs reset at once.
+ * This is required so that any code running after reset on the primary CPU
+ * doesn't have to co-ordinate with other CPUs to ensure they aren't still
+ * executing pre-reset code, and using RAM that the primary CPU's code wishes
+ * to use. Implementing such co-ordination would be essentially impossible.
+ */
 void machine_restart(char *cmd)
 {
-	machine_shutdown();
+	smp_send_stop();
 
 	arm_pm_restart(reboot_mode, cmd);
 
diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c
index 550d63cef68e..5919eb451bb9 100644
--- a/arch/arm/kernel/smp.c
+++ b/arch/arm/kernel/smp.c
@@ -651,17 +651,6 @@ void smp_send_reschedule(int cpu)
 	smp_cross_call(cpumask_of(cpu), IPI_RESCHEDULE);
 }
 
-#ifdef CONFIG_HOTPLUG_CPU
-static void smp_kill_cpus(cpumask_t *mask)
-{
-	unsigned int cpu;
-	for_each_cpu(cpu, mask)
-		platform_cpu_kill(cpu);
-}
-#else
-static void smp_kill_cpus(cpumask_t *mask) { }
-#endif
-
 void smp_send_stop(void)
 {
 	unsigned long timeout;
@@ -679,8 +668,6 @@ void smp_send_stop(void)
 
 	if (num_online_cpus() > 1)
 		pr_warning("SMP: failed to stop secondary CPUs\n");
-
-	smp_kill_cpus(&mask);
 }
 
 /*
diff --git a/arch/arm/mm/cache-v7.S b/arch/arm/mm/cache-v7.S
index 15451ee4acc8..515b00064da8 100644
--- a/arch/arm/mm/cache-v7.S
+++ b/arch/arm/mm/cache-v7.S
@@ -92,6 +92,14 @@ ENTRY(v7_flush_dcache_louis)
 	mrc	p15, 1, r0, c0, c0, 1		@ read clidr, r0 = clidr
 	ALT_SMP(ands	r3, r0, #(7 << 21))	@ extract LoUIS from clidr
 	ALT_UP(ands	r3, r0, #(7 << 27))	@ extract LoUU from clidr
+#ifdef CONFIG_ARM_ERRATA_643719
+	ALT_SMP(mrceq	p15, 0, r2, c0, c0, 0)	@ read main ID register
+	ALT_UP(moveq	pc, lr)			@ LoUU is zero, so nothing to do
+	ldreq	r1, =0x410fc090                 @ ID of ARM Cortex A9 r0p?
+	biceq	r2, r2, #0x0000000f             @ clear minor revision number
+	teqeq	r2, r1                          @ test for errata affected core and if so...
+	orreqs	r3, #(1 << 21)			@   fix LoUIS value (and set flags state to 'ne')
+#endif
 	ALT_SMP(mov	r3, r3, lsr #20)	@ r3 = LoUIS * 2
 	ALT_UP(mov	r3, r3, lsr #26)	@ r3 = LoUU * 2
 	moveq	pc, lr				@ return if level == 0
diff --git a/arch/arm/mm/flush.c b/arch/arm/mm/flush.c
index 0d473cce501c..32aa5861119f 100644
--- a/arch/arm/mm/flush.c
+++ b/arch/arm/mm/flush.c
@@ -301,6 +301,39 @@ void flush_dcache_page(struct page *page)
 EXPORT_SYMBOL(flush_dcache_page);
 
 /*
+ * Ensure cache coherency for the kernel mapping of this page. We can
+ * assume that the page is pinned via kmap.
+ *
+ * If the page only exists in the page cache and there are no user
+ * space mappings, this is a no-op since the page was already marked
+ * dirty at creation.  Otherwise, we need to flush the dirty kernel
+ * cache lines directly.
+ */
+void flush_kernel_dcache_page(struct page *page)
+{
+	if (cache_is_vivt() || cache_is_vipt_aliasing()) {
+		struct address_space *mapping;
+
+		mapping = page_mapping(page);
+
+		if (!mapping || mapping_mapped(mapping)) {
+			void *addr;
+
+			addr = page_address(page);
+			/*
+			 * kmap_atomic() doesn't set the page virtual
+			 * address for highmem pages, and
+			 * kunmap_atomic() takes care of cache
+			 * flushing already.
+			 */
+			if (!IS_ENABLED(CONFIG_HIGHMEM) || addr)
+				__cpuc_flush_dcache_area(addr, PAGE_SIZE);
+		}
+	}
+}
+EXPORT_SYMBOL(flush_kernel_dcache_page);
+
+/*
  * Flush an anonymous page so that users of get_user_pages()
  * can safely access the data.  The expected sequence is:
  *
diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c
index e0d8565671a6..4d409e6a552d 100644
--- a/arch/arm/mm/mmu.c
+++ b/arch/arm/mm/mmu.c
@@ -616,10 +616,12 @@ static void __init alloc_init_pte(pmd_t *pmd, unsigned long addr,
 	} while (pte++, addr += PAGE_SIZE, addr != end);
 }
 
-static void __init map_init_section(pmd_t *pmd, unsigned long addr,
+static void __init __map_init_section(pmd_t *pmd, unsigned long addr,
 			unsigned long end, phys_addr_t phys,
 			const struct mem_type *type)
 {
+	pmd_t *p = pmd;
+
 #ifndef CONFIG_ARM_LPAE
 	/*
 	 * In classic MMU format, puds and pmds are folded in to
@@ -638,7 +640,7 @@ static void __init map_init_section(pmd_t *pmd, unsigned long addr,
 		phys += SECTION_SIZE;
 	} while (pmd++, addr += SECTION_SIZE, addr != end);
 
-	flush_pmd_entry(pmd);
+	flush_pmd_entry(p);
 }
 
 static void __init alloc_init_pmd(pud_t *pud, unsigned long addr,
@@ -661,7 +663,7 @@ static void __init alloc_init_pmd(pud_t *pud, unsigned long addr,
 		 */
 		if (type->prot_sect &&
 				((addr | next | phys) & ~SECTION_MASK) == 0) {
-			map_init_section(pmd, addr, next, phys, type);
+			__map_init_section(pmd, addr, next, phys, type);
 		} else {
 			alloc_init_pte(pmd, addr, next,
 						__phys_to_pfn(phys), type);
diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S
index 2c73a7301ff7..4c8c9c10a388 100644
--- a/arch/arm/mm/proc-v7.S
+++ b/arch/arm/mm/proc-v7.S
@@ -409,8 +409,8 @@ __v7_ca9mp_proc_info:
 	 */
 	.type   __v7_pj4b_proc_info, #object
 __v7_pj4b_proc_info:
-	.long	0x562f5840
-	.long	0xfffffff0
+	.long	0x560f5800
+	.long	0xff0fff00
 	__v7_proc __v7_pj4b_setup
 	.size	__v7_pj4b_proc_info, . - __v7_pj4b_proc_info