1 files changed, 86 insertions, 11 deletions

diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c
index 0e96f6b24344..3a9a9f240dbc 100644
--- a/kernel/kexec_core.c
+++ b/kernel/kexec_core.c
@@ -210,6 +210,16 @@ int sanity_check_segment_list(struct kimage *image)
 	}
 #endif
 
+	/*
+	 * The destination addresses are searched from system RAM rather than
+	 * being allocated from the buddy allocator, so they are not guaranteed
+	 * to be accepted by the current kernel.  Accept the destination
+	 * addresses before kexec swaps their content with the segments' source
+	 * pages to avoid accessing memory before it is accepted.
+	 */
+	for (i = 0; i < nr_segments; i++)
+		accept_memory(image->segment[i].mem, image->segment[i].memsz);
+
 	return 0;
 }
 
@@ -867,6 +877,60 @@ int kimage_load_segment(struct kimage *image,
 	return result;
 }
 
+void *kimage_map_segment(struct kimage *image,
+			 unsigned long addr, unsigned long size)
+{
+	unsigned long src_page_addr, dest_page_addr = 0;
+	unsigned long eaddr = addr + size;
+	kimage_entry_t *ptr, entry;
+	struct page **src_pages;
+	unsigned int npages;
+	void *vaddr = NULL;
+	int i;
+
+	/*
+	 * Collect the source pages and map them in a contiguous VA range.
+	 */
+	npages = PFN_UP(eaddr) - PFN_DOWN(addr);
+	src_pages = kmalloc_array(npages, sizeof(*src_pages), GFP_KERNEL);
+	if (!src_pages) {
+		pr_err("Could not allocate ima pages array.\n");
+		return NULL;
+	}
+
+	i = 0;
+	for_each_kimage_entry(image, ptr, entry) {
+		if (entry & IND_DESTINATION) {
+			dest_page_addr = entry & PAGE_MASK;
+		} else if (entry & IND_SOURCE) {
+			if (dest_page_addr >= addr && dest_page_addr < eaddr) {
+				src_page_addr = entry & PAGE_MASK;
+				src_pages[i++] =
+					virt_to_page(__va(src_page_addr));
+				if (i == npages)
+					break;
+				dest_page_addr += PAGE_SIZE;
+			}
+		}
+	}
+
+	/* Sanity check. */
+	WARN_ON(i < npages);
+
+	vaddr = vmap(src_pages, npages, VM_MAP, PAGE_KERNEL);
+	kfree(src_pages);
+
+	if (!vaddr)
+		pr_err("Could not map ima buffer.\n");
+
+	return vaddr;
+}
+
+void kimage_unmap_segment(void *segment_buffer)
+{
+	vunmap(segment_buffer);
+}
+
 struct kexec_load_limit {
 	/* Mutex protects the limit count. */
 	struct mutex mutex;
@@ -888,7 +952,7 @@ struct kimage *kexec_crash_image;
 static int kexec_load_disabled;
 
 #ifdef CONFIG_SYSCTL
-static int kexec_limit_handler(struct ctl_table *table, int write,
+static int kexec_limit_handler(const struct ctl_table *table, int write,
 			       void *buffer, size_t *lenp, loff_t *ppos)
 {
 	struct kexec_load_limit *limit = table->data;
@@ -925,7 +989,7 @@ static int kexec_limit_handler(struct ctl_table *table, int write,
 	return proc_dointvec(&tmp, write, buffer, lenp, ppos);
 }
 
-static struct ctl_table kexec_core_sysctls[] = {
+static const struct ctl_table kexec_core_sysctls[] = {
 	{
 		.procname	= "kexec_load_disabled",
 		.data		= &kexec_load_disabled,
@@ -948,7 +1012,6 @@ static struct ctl_table kexec_core_sysctls[] = {
 		.mode		= 0644,
 		.proc_handler	= kexec_limit_handler,
 	},
-	{ }
 };
 
 static int __init kexec_core_sysctl_init(void)
@@ -1002,22 +1065,26 @@ int kernel_kexec(void)
 
 #ifdef CONFIG_KEXEC_JUMP
 	if (kexec_image->preserve_context) {
+		/*
+		 * This flow is analogous to hibernation flows that occur
+		 * before creating an image and before jumping from the
+		 * restore kernel to the image one, so it uses the same
+		 * device callbacks as those two flows.
+		 */
 		pm_prepare_console();
 		error = freeze_processes();
 		if (error) {
 			error = -EBUSY;
 			goto Restore_console;
 		}
-		suspend_console();
+		console_suspend_all();
 		error = dpm_suspend_start(PMSG_FREEZE);
 		if (error)
 			goto Resume_console;
-		/* At this point, dpm_suspend_start() has been called,
-		 * but *not* dpm_suspend_end(). We *must* call
-		 * dpm_suspend_end() now.  Otherwise, drivers for
-		 * some devices (e.g. interrupt controllers) become
-		 * desynchronized with the actual state of the
-		 * hardware at resume time, and evil weirdness ensues.
+		/*
+		 * dpm_suspend_end() must be called after dpm_suspend_start()
+		 * to complete the transition, like in the hibernation flows
+		 * mentioned above.
 		 */
 		error = dpm_suspend_end(PMSG_FREEZE);
 		if (error)
@@ -1053,6 +1120,13 @@ int kernel_kexec(void)
 
 #ifdef CONFIG_KEXEC_JUMP
 	if (kexec_image->preserve_context) {
+		/*
+		 * This flow is analogous to hibernation flows that occur after
+		 * creating an image and after the image kernel has got control
+		 * back, and in case the devices have been reset or otherwise
+		 * manipulated in the meantime, it uses the device callbacks
+		 * used by the latter.
+		 */
 		syscore_resume();
  Enable_irqs:
 		local_irq_enable();
@@ -1062,7 +1136,8 @@ int kernel_kexec(void)
  Resume_devices:
 		dpm_resume_end(PMSG_RESTORE);
  Resume_console:
-		resume_console();
+		pm_restore_gfp_mask();
+		console_resume_all();
 		thaw_processes();
  Restore_console:
 		pm_restore_console();