Merge branch 'tip/x86/ftrace' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-2.6-trace into tracing/ftrace

Conflicts:
	include/linux/ftrace.h
	kernel/trace/ftrace.c

6 files changed, 95 insertions, 19 deletions

diff --git a/arch/x86/include/asm/cacheflush.h b/arch/x86/include/asm/cacheflush.h
index 2f8466540fb5..6145063cfe0e 100644
--- a/arch/x86/include/asm/cacheflush.h
+++ b/arch/x86/include/asm/cacheflush.h
@@ -104,6 +104,11 @@ void clflush_cache_range(void *addr, unsigned int size);
 #ifdef CONFIG_DEBUG_RODATA
 void mark_rodata_ro(void);
 extern const int rodata_test_data;
+void set_kernel_text_rw(void);
+void set_kernel_text_ro(void);
+#else
+static inline void set_kernel_text_rw(void) { }
+static inline void set_kernel_text_ro(void) { }
 #endif
 
 #ifdef CONFIG_DEBUG_RODATA_TEST
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index c2e057d9f88c..3925ec0184b1 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -18,6 +18,7 @@
 #include <linux/init.h>
 #include <linux/list.h>
 
+#include <asm/cacheflush.h>
 #include <asm/ftrace.h>
 #include <linux/ftrace.h>
 #include <asm/nops.h>
@@ -26,6 +27,18 @@
 
 #ifdef CONFIG_DYNAMIC_FTRACE
 
+int ftrace_arch_code_modify_prepare(void)
+{
+	set_kernel_text_rw();
+	return 0;
+}
+
+int ftrace_arch_code_modify_post_process(void)
+{
+	set_kernel_text_ro();
+	return 0;
+}
+
 union ftrace_code_union {
 	char code[MCOUNT_INSN_SIZE];
 	struct {
@@ -111,6 +124,10 @@ static void ftrace_mod_code(void)
 	 */
 	mod_code_status = probe_kernel_write(mod_code_ip, mod_code_newcode,
 					     MCOUNT_INSN_SIZE);
+
+	/* if we fail, then kill any new writers */
+	if (mod_code_status)
+		mod_code_write = 0;
 }
 
 void ftrace_nmi_enter(void)
diff --git a/arch/x86/kernel/vmiclock_32.c b/arch/x86/kernel/vmiclock_32.c
index c4c1f9e09402..bde106cae0a9 100644
--- a/arch/x86/kernel/vmiclock_32.c
+++ b/arch/x86/kernel/vmiclock_32.c
@@ -283,10 +283,13 @@ void __devinit vmi_time_ap_init(void)
 #endif
 
 /** vmi clocksource */
+static struct clocksource clocksource_vmi;
 
 static cycle_t read_real_cycles(void)
 {
-	return vmi_timer_ops.get_cycle_counter(VMI_CYCLES_REAL);
+	cycle_t ret = (cycle_t)vmi_timer_ops.get_cycle_counter(VMI_CYCLES_REAL);
+	return ret >= clocksource_vmi.cycle_last ?
+		ret : clocksource_vmi.cycle_last;
 }
 
 static struct clocksource clocksource_vmi = {
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index 2cef05074413..3eb2ed188a4c 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -1155,17 +1155,47 @@ static noinline int do_test_wp_bit(void)
 const int rodata_test_data = 0xC3;
 EXPORT_SYMBOL_GPL(rodata_test_data);
 
+static int kernel_set_to_readonly;
+
+void set_kernel_text_rw(void)
+{
+	unsigned long start = PFN_ALIGN(_text);
+	unsigned long size = PFN_ALIGN(_etext) - start;
+
+	if (!kernel_set_to_readonly)
+		return;
+
+	pr_debug("Set kernel text: %lx - %lx for read write\n",
+		 start, start+size);
+
+	set_pages_rw(virt_to_page(start), size >> PAGE_SHIFT);
+}
+
+void set_kernel_text_ro(void)
+{
+	unsigned long start = PFN_ALIGN(_text);
+	unsigned long size = PFN_ALIGN(_etext) - start;
+
+	if (!kernel_set_to_readonly)
+		return;
+
+	pr_debug("Set kernel text: %lx - %lx for read only\n",
+		 start, start+size);
+
+	set_pages_ro(virt_to_page(start), size >> PAGE_SHIFT);
+}
+
 void mark_rodata_ro(void)
 {
 	unsigned long start = PFN_ALIGN(_text);
 	unsigned long size = PFN_ALIGN(_etext) - start;
 
-#ifndef CONFIG_DYNAMIC_FTRACE
-	/* Dynamic tracing modifies the kernel text section */
 	set_pages_ro(virt_to_page(start), size >> PAGE_SHIFT);
 	printk(KERN_INFO "Write protecting the kernel text: %luk\n",
 		size >> 10);
 
+	kernel_set_to_readonly = 1;
+
 #ifdef CONFIG_CPA_DEBUG
 	printk(KERN_INFO "Testing CPA: Reverting %lx-%lx\n",
 		start, start+size);
@@ -1174,7 +1204,6 @@ void mark_rodata_ro(void)
 	printk(KERN_INFO "Testing CPA: write protecting again\n");
 	set_pages_ro(virt_to_page(start), size>>PAGE_SHIFT);
 #endif
-#endif /* CONFIG_DYNAMIC_FTRACE */
 
 	start += size;
 	size = (unsigned long)__end_rodata - start;
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index e6d36b490250..63fdc531601d 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -986,21 +986,48 @@ void free_initmem(void)
 const int rodata_test_data = 0xC3;
 EXPORT_SYMBOL_GPL(rodata_test_data);
 
+static int kernel_set_to_readonly;
+
+void set_kernel_text_rw(void)
+{
+	unsigned long start = PFN_ALIGN(_stext);
+	unsigned long end = PFN_ALIGN(__start_rodata);
+
+	if (!kernel_set_to_readonly)
+		return;
+
+	pr_debug("Set kernel text: %lx - %lx for read write\n",
+		 start, end);
+
+	set_memory_rw(start, (end - start) >> PAGE_SHIFT);
+}
+
+void set_kernel_text_ro(void)
+{
+	unsigned long start = PFN_ALIGN(_stext);
+	unsigned long end = PFN_ALIGN(__start_rodata);
+
+	if (!kernel_set_to_readonly)
+		return;
+
+	pr_debug("Set kernel text: %lx - %lx for read only\n",
+		 start, end);
+
+	set_memory_ro(start, (end - start) >> PAGE_SHIFT);
+}
+
 void mark_rodata_ro(void)
 {
 	unsigned long start = PFN_ALIGN(_stext), end = PFN_ALIGN(__end_rodata);
 	unsigned long rodata_start =
 		((unsigned long)__start_rodata + PAGE_SIZE - 1) & PAGE_MASK;
 
-#ifdef CONFIG_DYNAMIC_FTRACE
-	/* Dynamic tracing modifies the kernel text section */
-	start = rodata_start;
-#endif
-
 	printk(KERN_INFO "Write protecting the kernel read-only data: %luk\n",
 	       (end - start) >> 10);
 	set_memory_ro(start, (end - start) >> PAGE_SHIFT);
 
+	kernel_set_to_readonly = 1;
+
 	/*
 	 * The rodata section (but not the kernel text!) should also be
 	 * not-executable.
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index 8ca0d8566fc8..7be47d1a97e4 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -508,18 +508,13 @@ static int split_large_page(pte_t *kpte, unsigned long address)
 #endif
 
 	/*
-	 * Install the new, split up pagetable. Important details here:
+	 * Install the new, split up pagetable.
 	 *
-	 * On Intel the NX bit of all levels must be cleared to make a
-	 * page executable. See section 4.13.2 of Intel 64 and IA-32
-	 * Architectures Software Developer's Manual).
-	 *
-	 * Mark the entry present. The current mapping might be
-	 * set to not present, which we preserved above.
+	 * We use the standard kernel pagetable protections for the new
+	 * pagetable protections, the actual ptes set above control the
+	 * primary protection behavior:
 	 */
-	ref_prot = pte_pgprot(pte_mkexec(pte_clrhuge(*kpte)));
-	pgprot_val(ref_prot) |= _PAGE_PRESENT;
-	__set_pmd_pte(kpte, address, mk_pte(base, ref_prot));
+	__set_pmd_pte(kpte, address, mk_pte(base, __pgprot(_KERNPG_TABLE)));
 	base = NULL;
 
 out_unlock: