Merge remote-tracking branch 'lsk/v4.4/topic/ro-vdso' into linux-linaro-lsk-v4.4

broonie · broonie · commit dfabba9c3737 · 2016-03-17T18:54:33.000Z
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
@@ -3409,6 +3409,10 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 
 	ro		[KNL] Mount root device read-only on boot
 
+	rodata=		[KNL]
+		on	Mark read-only kernel memory as read-only (default).
+		off	Leave read-only kernel memory writable for debugging.
+
 	root=		[KNL] Root filesystem
 			See name_to_dev_t comment in init/do_mounts.c.
 
diff --git a/arch/arm/include/asm/cacheflush.h b/arch/arm/include/asm/cacheflush.h
@@ -491,7 +491,6 @@ static inline int set_memory_nx(unsigned long addr, int numpages) { return 0; }
 #endif
 
 #ifdef CONFIG_DEBUG_RODATA
-void mark_rodata_ro(void);
 void set_kernel_text_rw(void);
 void set_kernel_text_ro(void);
 #else
diff --git a/arch/arm/vdso/vdso.S b/arch/arm/vdso/vdso.S
@@ -23,9 +23,8 @@
 #include <linux/const.h>
 #include <asm/page.h>
 
-	__PAGE_ALIGNED_DATA
-
 	.globl vdso_start, vdso_end
+	.section .data..ro_after_init
 	.balign PAGE_SIZE
 vdso_start:
 	.incbin "arch/arm/vdso/vdso.so"
diff --git a/arch/arm64/include/asm/cacheflush.h b/arch/arm64/include/asm/cacheflush.h
@@ -155,8 +155,4 @@ int set_memory_rw(unsigned long addr, int numpages);
 int set_memory_x(unsigned long addr, int numpages);
 int set_memory_nx(unsigned long addr, int numpages);
 
-#ifdef CONFIG_DEBUG_RODATA
-void mark_rodata_ro(void);
-#endif
-
 #endif
diff --git a/arch/parisc/include/asm/cache.h b/arch/parisc/include/asm/cache.h
@@ -22,6 +22,9 @@
 
 #define __read_mostly __attribute__((__section__(".data..read_mostly")))
 
+/* Read-only memory is marked before mark_rodata_ro() is called. */
+#define __ro_after_init	__read_mostly
+
 void parisc_cache_init(void);	/* initializes cache-flushing */
 void disable_sr_hashing_asm(int); /* low level support for above */
 void disable_sr_hashing(void);   /* turns off space register hashing */
diff --git a/arch/parisc/include/asm/cacheflush.h b/arch/parisc/include/asm/cacheflush.h
@@ -121,10 +121,6 @@ flush_anon_page(struct vm_area_struct *vma, struct page *page, unsigned long vma
 	}
 }
 
-#ifdef CONFIG_DEBUG_RODATA
-void mark_rodata_ro(void);
-#endif
-
 #include <asm/kmap_types.h>
 
 #define ARCH_HAS_KMAP
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
@@ -289,6 +289,9 @@ config ARCH_SUPPORTS_UPROBES
 config FIX_EARLYCON_MEM
 	def_bool y
 
+config DEBUG_RODATA
+	def_bool y
+
 config PGTABLE_LEVELS
 	int
 	default 4 if X86_64
diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug
@@ -91,28 +91,16 @@ config EFI_PGT_DUMP
 	  issues with the mapping of the EFI runtime regions into that
 	  table.
 
-config DEBUG_RODATA
-	bool "Write protect kernel read-only data structures"
-	default y
-	depends on DEBUG_KERNEL
-	---help---
-	  Mark the kernel read-only data as write-protected in the pagetables,
-	  in order to catch accidental (and incorrect) writes to such const
-	  data. This is recommended so that we can catch kernel bugs sooner.
-	  If in doubt, say "Y".
-
 config DEBUG_RODATA_TEST
-	bool "Testcase for the DEBUG_RODATA feature"
-	depends on DEBUG_RODATA
+	bool "Testcase for the marking rodata read-only"
 	default y
 	---help---
-	  This option enables a testcase for the DEBUG_RODATA
-	  feature as well as for the change_page_attr() infrastructure.
+	  This option enables a testcase for the setting rodata read-only
+	  as well as for the change_page_attr() infrastructure.
 	  If in doubt, say "N"
 
 config DEBUG_WX
 	bool "Warn on W+X mappings at boot"
-	depends on DEBUG_RODATA
 	select X86_PTDUMP_CORE
 	---help---
 	  Generate a warning if any W+X mappings are found at boot.
diff --git a/arch/x86/entry/vdso/vdso2c.h b/arch/x86/entry/vdso/vdso2c.h
@@ -140,7 +140,7 @@ static void BITSFUNC(go)(void *raw_addr, size_t raw_len,
 	fprintf(outfile, "#include <asm/vdso.h>\n");
 	fprintf(outfile, "\n");
 	fprintf(outfile,
-		"static unsigned char raw_data[%lu] __page_aligned_data = {",
+		"static unsigned char raw_data[%lu] __ro_after_init __aligned(PAGE_SIZE) = {",
 		mapping_size);
 	for (j = 0; j < stripped_len; j++) {
 		if (j % 10 == 0)
diff --git a/arch/x86/include/asm/cacheflush.h b/arch/x86/include/asm/cacheflush.h
@@ -91,16 +91,10 @@ void clflush_cache_range(void *addr, unsigned int size);
 
 #define mmio_flush_range(addr, size) clflush_cache_range(addr, size)
 
-#ifdef CONFIG_DEBUG_RODATA
-void mark_rodata_ro(void);
 extern const int rodata_test_data;
 extern int kernel_set_to_readonly;
 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
 int rodata_test(void);
diff --git a/arch/x86/include/asm/kvm_para.h b/arch/x86/include/asm/kvm_para.h
@@ -17,15 +17,8 @@ static inline bool kvm_check_and_clear_guest_paused(void)
 }
 #endif /* CONFIG_KVM_GUEST */
 
-#ifdef CONFIG_DEBUG_RODATA
 #define KVM_HYPERCALL \
         ALTERNATIVE(".byte 0x0f,0x01,0xc1", ".byte 0x0f,0x01,0xd9", X86_FEATURE_VMMCALL)
-#else
-/* On AMD processors, vmcall will generate a trap that we will
- * then rewrite to the appropriate instruction.
- */
-#define KVM_HYPERCALL ".byte 0x0f,0x01,0xc1"
-#endif
 
 /* For KVM hypercalls, a three-byte sequence of either the vmcall or the vmmcall
  * instruction.  The hypervisor may replace it with something else but only the
diff --git a/arch/x86/include/asm/sections.h b/arch/x86/include/asm/sections.h
@@ -7,7 +7,7 @@
 extern char __brk_base[], __brk_limit[];
 extern struct exception_table_entry __stop___ex_table[];
 
-#if defined(CONFIG_X86_64) && defined(CONFIG_DEBUG_RODATA)
+#if defined(CONFIG_X86_64)
 extern char __end_rodata_hpage_align[];
 #endif
 
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
@@ -81,9 +81,9 @@ within(unsigned long addr, unsigned long start, unsigned long end)
 static unsigned long text_ip_addr(unsigned long ip)
 {
 	/*
-	 * On x86_64, kernel text mappings are mapped read-only with
-	 * CONFIG_DEBUG_RODATA. So we use the kernel identity mapping instead
-	 * of the kernel text mapping to modify the kernel text.
+	 * On x86_64, kernel text mappings are mapped read-only, so we use
+	 * the kernel identity mapping instead of the kernel text mapping
+	 * to modify the kernel text.
 	 *
 	 * For 32bit kernels, these mappings are same and we can use
 	 * kernel identity mapping to modify code.
diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c
@@ -750,9 +750,7 @@ void kgdb_arch_set_pc(struct pt_regs *regs, unsigned long ip)
 int kgdb_arch_set_breakpoint(struct kgdb_bkpt *bpt)
 {
 	int err;
-#ifdef CONFIG_DEBUG_RODATA
 	char opc[BREAK_INSTR_SIZE];
-#endif /* CONFIG_DEBUG_RODATA */
 
 	bpt->type = BP_BREAKPOINT;
 	err = probe_kernel_read(bpt->saved_instr, (char *)bpt->bpt_addr,
@@ -761,7 +759,6 @@ int kgdb_arch_set_breakpoint(struct kgdb_bkpt *bpt)
 		return err;
 	err = probe_kernel_write((char *)bpt->bpt_addr,
 				 arch_kgdb_ops.gdb_bpt_instr, BREAK_INSTR_SIZE);
-#ifdef CONFIG_DEBUG_RODATA
 	if (!err)
 		return err;
 	/*
@@ -778,13 +775,12 @@ int kgdb_arch_set_breakpoint(struct kgdb_bkpt *bpt)
 	if (memcmp(opc, arch_kgdb_ops.gdb_bpt_instr, BREAK_INSTR_SIZE))
 		return -EINVAL;
 	bpt->type = BP_POKE_BREAKPOINT;
-#endif /* CONFIG_DEBUG_RODATA */
+
 	return err;
 }
 
 int kgdb_arch_remove_breakpoint(struct kgdb_bkpt *bpt)
 {
-#ifdef CONFIG_DEBUG_RODATA
 	int err;
 	char opc[BREAK_INSTR_SIZE];
 
@@ -801,8 +797,8 @@ int kgdb_arch_remove_breakpoint(struct kgdb_bkpt *bpt)
 	if (err || memcmp(opc, bpt->saved_instr, BREAK_INSTR_SIZE))
 		goto knl_write;
 	return err;
+
 knl_write:
-#endif /* CONFIG_DEBUG_RODATA */
 	return probe_kernel_write((char *)bpt->bpt_addr,
 				  (char *)bpt->saved_instr, BREAK_INSTR_SIZE);
 }
diff --git a/arch/x86/kernel/test_nx.c b/arch/x86/kernel/test_nx.c
@@ -142,7 +142,6 @@ static int test_NX(void)
 	 * by the error message
 	 */
 
-#ifdef CONFIG_DEBUG_RODATA
 	/* Test 3: Check if the .rodata section is executable */
 	if (rodata_test_data != 0xC3) {
 		printk(KERN_ERR "test_nx: .rodata marker has invalid value\n");
@@ -151,7 +150,6 @@ static int test_NX(void)
 		printk(KERN_ERR "test_nx: .rodata section is executable\n");
 		ret = -ENODEV;
 	}
-#endif
 
 #if 0
 	/* Test 4: Check if the .data section of a module is executable */
diff --git a/arch/x86/kernel/test_rodata.c b/arch/x86/kernel/test_rodata.c
@@ -76,5 +76,5 @@ int rodata_test(void)
 }
 
 MODULE_LICENSE("GPL");
-MODULE_DESCRIPTION("Testcase for the DEBUG_RODATA infrastructure");
+MODULE_DESCRIPTION("Testcase for marking rodata as read-only");
 MODULE_AUTHOR("Arjan van de Ven <arjan@linux.intel.com>");
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
@@ -41,29 +41,28 @@ ENTRY(phys_startup_64)
 jiffies_64 = jiffies;
 #endif
 
-#if defined(CONFIG_X86_64) && defined(CONFIG_DEBUG_RODATA)
+#if defined(CONFIG_X86_64)
 /*
- * On 64-bit, align RODATA to 2MB so that even with CONFIG_DEBUG_RODATA
- * we retain large page mappings for boundaries spanning kernel text, rodata
- * and data sections.
+ * On 64-bit, align RODATA to 2MB so we retain large page mappings for
+ * boundaries spanning kernel text, rodata and data sections.
  *
  * However, kernel identity mappings will have different RWX permissions
  * to the pages mapping to text and to the pages padding (which are freed) the
  * text section. Hence kernel identity mappings will be broken to smaller
  * pages. For 64-bit, kernel text and kernel identity mappings are different,
- * so we can enable protection checks that come with CONFIG_DEBUG_RODATA,
- * as well as retain 2MB large page mappings for kernel text.
+ * so we can enable protection checks as well as retain 2MB large page
+ * mappings for kernel text.
  */
-#define X64_ALIGN_DEBUG_RODATA_BEGIN	. = ALIGN(HPAGE_SIZE);
+#define X64_ALIGN_RODATA_BEGIN	. = ALIGN(HPAGE_SIZE);
 
-#define X64_ALIGN_DEBUG_RODATA_END				\
+#define X64_ALIGN_RODATA_END					\
 		. = ALIGN(HPAGE_SIZE);				\
 		__end_rodata_hpage_align = .;
 
 #else
 
-#define X64_ALIGN_DEBUG_RODATA_BEGIN
-#define X64_ALIGN_DEBUG_RODATA_END
+#define X64_ALIGN_RODATA_BEGIN
+#define X64_ALIGN_RODATA_END
 
 #endif
 
@@ -112,13 +111,11 @@ SECTIONS
 
 	EXCEPTION_TABLE(16) :text = 0x9090
 
-#if defined(CONFIG_DEBUG_RODATA)
 	/* .text should occupy whole number of pages */
 	. = ALIGN(PAGE_SIZE);
-#endif
-	X64_ALIGN_DEBUG_RODATA_BEGIN
+	X64_ALIGN_RODATA_BEGIN
 	RO_DATA(PAGE_SIZE)
-	X64_ALIGN_DEBUG_RODATA_END
+	X64_ALIGN_RODATA_END
 
 	/* Data */
 	.data : AT(ADDR(.data) - LOAD_OFFSET) {
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
@@ -871,7 +871,6 @@ static noinline int do_test_wp_bit(void)
 	return flag;
 }
 
-#ifdef CONFIG_DEBUG_RODATA
 const int rodata_test_data = 0xC3;
 EXPORT_SYMBOL_GPL(rodata_test_data);
 
@@ -960,5 +959,3 @@ void mark_rodata_ro(void)
 	if (__supported_pte_mask & _PAGE_NX)
 		debug_checkwx();
 }
-#endif
-
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
@@ -1062,7 +1062,6 @@ void __init mem_init(void)
 	mem_init_print_info(NULL);
 }
 
-#ifdef CONFIG_DEBUG_RODATA
 const int rodata_test_data = 0xC3;
 EXPORT_SYMBOL_GPL(rodata_test_data);
 
@@ -1154,8 +1153,6 @@ void mark_rodata_ro(void)
 	debug_checkwx();
 }
 
-#endif
-
 int kern_addr_valid(unsigned long addr)
 {
 	unsigned long above = ((long)addr) >> __VIRTUAL_MASK_SHIFT;
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
@@ -278,7 +278,7 @@ static inline pgprot_t static_protections(pgprot_t prot, unsigned long address,
 		   __pa_symbol(__end_rodata) >> PAGE_SHIFT))
 		pgprot_val(forbidden) |= _PAGE_RW;
 
-#if defined(CONFIG_X86_64) && defined(CONFIG_DEBUG_RODATA)
+#if defined(CONFIG_X86_64)
 	/*
 	 * Once the kernel maps the text as RO (kernel_set_to_readonly is set),
 	 * kernel text mappings for the large page aligned text, rodata sections
diff --git a/drivers/misc/lkdtm.c b/drivers/misc/lkdtm.c
@@ -103,6 +103,7 @@ enum ctype {
 	CT_EXEC_USERSPACE,
 	CT_ACCESS_USERSPACE,
 	CT_WRITE_RO,
+	CT_WRITE_RO_AFTER_INIT,
 	CT_WRITE_KERN,
 };
 
@@ -140,6 +141,7 @@ static char* cp_type[] = {
 	"EXEC_USERSPACE",
 	"ACCESS_USERSPACE",
 	"WRITE_RO",
+	"WRITE_RO_AFTER_INIT",
 	"WRITE_KERN",
 };
 
@@ -162,6 +164,7 @@ static DEFINE_SPINLOCK(lock_me_up);
 static u8 data_area[EXEC_SIZE];
 
 static const unsigned long rodata = 0xAA55AA55;
+static unsigned long ro_after_init __ro_after_init = 0x55AA5500;
 
 module_param(recur_count, int, 0644);
 MODULE_PARM_DESC(recur_count, " Recursion level for the stack overflow test");
@@ -503,11 +506,28 @@ static void lkdtm_do_action(enum ctype which)
 		break;
 	}
 	case CT_WRITE_RO: {
-		unsigned long *ptr;
+		/* Explicitly cast away "const" for the test. */
+		unsigned long *ptr = (unsigned long *)&rodata;
 
-		ptr = (unsigned long *)&rodata;
+		pr_info("attempting bad rodata write at %p\n", ptr);
+		*ptr ^= 0xabcd1234;
 
-		pr_info("attempting bad write at %p\n", ptr);
+		break;
+	}
+	case CT_WRITE_RO_AFTER_INIT: {
+		unsigned long *ptr = &ro_after_init;
+
+		/*
+		 * Verify we were written to during init. Since an Oops
+		 * is considered a "success", a failure is to just skip the
+		 * real test.
+		 */
+		if ((*ptr & 0xAA) != 0xAA) {
+			pr_info("%p was NOT written during init!?\n", ptr);
+			break;
+		}
+
+		pr_info("attempting bad ro_after_init write at %p\n", ptr);
 		*ptr ^= 0xabcd1234;
 
 		break;
@@ -817,6 +837,9 @@ static int __init lkdtm_module_init(void)
 	int n_debugfs_entries = 1; /* Assume only the direct entry */
 	int i;
 
+	/* Make sure we can write to __ro_after_init values during __init */
+	ro_after_init |= 0xAA;
+
 	/* Register debugfs interface */
 	lkdtm_debugfs_root = debugfs_create_dir("provoke-crash", NULL);
 	if (!lkdtm_debugfs_root) {
diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
diff --git a/include/linux/cache.h b/include/linux/cache.h
diff --git a/include/linux/init.h b/include/linux/init.h
diff --git a/init/main.c b/init/main.c
diff --git a/kernel/debug/kdb/kdb_bp.c b/kernel/debug/kdb/kdb_bp.c

Original file line number	Diff line number	Diff line change
`@@ -121,10 +121,6 @@ flush_anon_page(struct vm_area_struct vma, struct page page, unsigned long vma`
`121`	`121`	`}`
`122`	`122`	`}`
`123`	`123`
`124`		`-#ifdef CONFIG_DEBUG_RODATA`
`125`		`-void mark_rodata_ro(void);`
`126`		`-#endif`
`127`		`-`
`128`	`124`	`#include <asm/kmap_types.h>`
`129`	`125`
`130`	`126`	`#define ARCH_HAS_KMAP`