Merge branch 'akpm' (patches from Andrew)

Merge final set of updates from Andrew Morton:

 - a series to make IMA play better across kexec

 - a handful of random fixes

* emailed patches from Andrew Morton <akpm@linux-foundation.org>:
  printk: fix typo in CONSOLE_LOGLEVEL_DEFAULT help text
  ratelimit: fix WARN_ON_RATELIMIT return value
  kcov: make kcov work properly with KASLR enabled
  arm64: setup: introduce kaslr_offset()
  mm: fadvise: avoid expensive remote LRU cache draining after FADV_DONTNEED
  ima: platform-independent hash value
  ima: define a canonical binary_runtime_measurements list format
  ima: support restoring multiple template formats
  ima: store the builtin/custom template definitions in a list
  ima: on soft reboot, save the measurement list
  powerpc: ima: send the kexec buffer to the next kernel
  ima: maintain memory size needed for serializing the measurement list
  ima: permit duplicate measurement list entries
  ima: on soft reboot, restore the measurement list
  powerpc: ima: get the kexec buffer passed by the previous kernel

Documentation/admin-guide/kernel-parameters.txt

@@ -1441,6 +1441,10 @@
 			The builtin appraise policy appraises all files
 			owned by uid=0.
 
+	ima_canonical_fmt [IMA]
+			Use the canonical format for the binary runtime
+			measurements, instead of host native format.
+
 	ima_hash=	[IMA]
 			Format: { md5 | sha1 | rmd160 | sha256 | sha384
 				   | sha512 | ... }

arch/Kconfig

@@ -5,6 +5,9 @@
 config KEXEC_CORE
 	bool
 
+config HAVE_IMA_KEXEC
+	bool
+
 config OPROFILE
 	tristate "OProfile system profiling"
 	depends on PROFILING

arch/arm64/include/asm/memory.h

@@ -165,6 +165,11 @@ extern u64			kimage_vaddr;
 /* the offset between the kernel virtual and physical mappings */
 extern u64			kimage_voffset;
 
+static inline unsigned long kaslr_offset(void)
+{
+	return kimage_vaddr - KIMAGE_VADDR;
+}
+
 /*
  * Allow all memory at the discovery stage. We will clip it later.
  */

arch/arm64/kernel/setup.c

@@ -338,11 +338,11 @@ subsys_initcall(topology_init);
 static int dump_kernel_offset(struct notifier_block *self, unsigned long v,
 			      void *p)
 {
-	u64 const kaslr_offset = kimage_vaddr - KIMAGE_VADDR;
+	const unsigned long offset = kaslr_offset();
 
-	if (IS_ENABLED(CONFIG_RANDOMIZE_BASE) && kaslr_offset > 0) {
-		pr_emerg("Kernel Offset: 0x%llx from 0x%lx\n",
-			 kaslr_offset, KIMAGE_VADDR);
+	if (IS_ENABLED(CONFIG_RANDOMIZE_BASE) && offset > 0) {
+		pr_emerg("Kernel Offset: 0x%lx from 0x%lx\n",
+			 offset, KIMAGE_VADDR);
 	} else {
 		pr_emerg("Kernel Offset: disabled\n");
 	}

arch/powerpc/Kconfig

@@ -469,6 +469,7 @@ config KEXEC
 config KEXEC_FILE
 	bool "kexec file based system call"
 	select KEXEC_CORE
+	select HAVE_IMA_KEXEC
 	select BUILD_BIN2C
 	depends on PPC64
 	depends on CRYPTO=y

arch/powerpc/include/asm/ima.h

+#ifndef _ASM_POWERPC_IMA_H
+#define _ASM_POWERPC_IMA_H
+
+struct kimage;
+
+int ima_get_kexec_buffer(void **addr, size_t *size);
+int ima_free_kexec_buffer(void);
+
+#ifdef CONFIG_IMA
+void remove_ima_buffer(void *fdt, int chosen_node);
+#else
+static inline void remove_ima_buffer(void *fdt, int chosen_node) {}
+#endif
+
+#ifdef CONFIG_IMA_KEXEC
+int arch_ima_add_kexec_buffer(struct kimage *image, unsigned long load_addr,
+			      size_t size);
+
+int setup_ima_buffer(const struct kimage *image, void *fdt, int chosen_node);
+#else
+static inline int setup_ima_buffer(const struct kimage *image, void *fdt,
+				   int chosen_node)
+{
+	remove_ima_buffer(fdt, chosen_node);
+	return 0;
+}
+#endif /* CONFIG_IMA_KEXEC */
+
+#endif /* _ASM_POWERPC_IMA_H */

arch/powerpc/include/asm/kexec.h

@@ -94,11 +94,22 @@ static inline bool kdump_in_progress(void)
 #ifdef CONFIG_KEXEC_FILE
 extern struct kexec_file_ops kexec_elf64_ops;
 
+#ifdef CONFIG_IMA_KEXEC
+#define ARCH_HAS_KIMAGE_ARCH
+
+struct kimage_arch {
+	phys_addr_t ima_buffer_addr;
+	size_t ima_buffer_size;
+};
+#endif
+
 int setup_purgatory(struct kimage *image, const void *slave_code,
 		    const void *fdt, unsigned long kernel_load_addr,
 		    unsigned long fdt_load_addr);
-int setup_new_fdt(void *fdt, unsigned long initrd_load_addr,
-		  unsigned long initrd_len, const char *cmdline);
+int setup_new_fdt(const struct kimage *image, void *fdt,
+		  unsigned long initrd_load_addr, unsigned long initrd_len,
+		  const char *cmdline);
+int delete_fdt_mem_rsv(void *fdt, unsigned long start, unsigned long size);
 #endif /* CONFIG_KEXEC_FILE */
 
 #else /* !CONFIG_KEXEC_CORE */

arch/powerpc/kernel/Makefile

@@ -112,6 +112,10 @@ obj-$(CONFIG_PCI_MSI)		+= msi.o
 obj-$(CONFIG_KEXEC_CORE)	+= machine_kexec.o crash.o \
 				   machine_kexec_$(BITS).o
 obj-$(CONFIG_KEXEC_FILE)	+= machine_kexec_file_$(BITS).o kexec_elf_$(BITS).o
+ifeq ($(CONFIG_HAVE_IMA_KEXEC)$(CONFIG_IMA),yy)
+obj-y				+= ima_kexec.o
+endif
+
 obj-$(CONFIG_AUDIT)		+= audit.o
 obj64-$(CONFIG_AUDIT)		+= compat_audit.o
 

arch/powerpc/kernel/ima_kexec.c

+/*
+ * Copyright (C) 2016 IBM Corporation
+ *
+ * Authors:
+ * Thiago Jung Bauermann <bauerman@linux.vnet.ibm.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include <linux/slab.h>
+#include <linux/kexec.h>
+#include <linux/of.h>
+#include <linux/memblock.h>
+#include <linux/libfdt.h>
+
+static int get_addr_size_cells(int *addr_cells, int *size_cells)
+{
+	struct device_node *root;
+
+	root = of_find_node_by_path("/");
+	if (!root)
+		return -EINVAL;
+
+	*addr_cells = of_n_addr_cells(root);
+	*size_cells = of_n_size_cells(root);
+
+	of_node_put(root);
+
+	return 0;
+}
+
+static int do_get_kexec_buffer(const void *prop, int len, unsigned long *addr,
+			       size_t *size)
+{
+	int ret, addr_cells, size_cells;
+
+	ret = get_addr_size_cells(&addr_cells, &size_cells);
+	if (ret)
+		return ret;
+
+	if (len < 4 * (addr_cells + size_cells))
+		return -ENOENT;
+
+	*addr = of_read_number(prop, addr_cells);
+	*size = of_read_number(prop + 4 * addr_cells, size_cells);
+
+	return 0;
+}
+
+/**
+ * ima_get_kexec_buffer - get IMA buffer from the previous kernel
+ * @addr:	On successful return, set to point to the buffer contents.
+ * @size:	On successful return, set to the buffer size.
+ *
+ * Return: 0 on success, negative errno on error.
+ */
+int ima_get_kexec_buffer(void **addr, size_t *size)
+{
+	int ret, len;
+	unsigned long tmp_addr;
+	size_t tmp_size;
+	const void *prop;
+
+	prop = of_get_property(of_chosen, "linux,ima-kexec-buffer", &len);
+	if (!prop)
+		return -ENOENT;
+
+	ret = do_get_kexec_buffer(prop, len, &tmp_addr, &tmp_size);
+	if (ret)
+		return ret;
+
+	*addr = __va(tmp_addr);
+	*size = tmp_size;
+
+	return 0;
+}
+
+/**
+ * ima_free_kexec_buffer - free memory used by the IMA buffer
+ */
+int ima_free_kexec_buffer(void)
+{
+	int ret;
+	unsigned long addr;
+	size_t size;
+	struct property *prop;
+
+	prop = of_find_property(of_chosen, "linux,ima-kexec-buffer", NULL);
+	if (!prop)
+		return -ENOENT;
+
+	ret = do_get_kexec_buffer(prop->value, prop->length, &addr, &size);
+	if (ret)
+		return ret;
+
+	ret = of_remove_property(of_chosen, prop);
+	if (ret)
+		return ret;
+
+	return memblock_free(addr, size);
+
+}
+
+/**
+ * remove_ima_buffer - remove the IMA buffer property and reservation from @fdt
+ *
+ * The IMA measurement buffer is of no use to a subsequent kernel, so we always
+ * remove it from the device tree.
+ */
+void remove_ima_buffer(void *fdt, int chosen_node)
+{
+	int ret, len;
+	unsigned long addr;
+	size_t size;
+	const void *prop;
+
+	prop = fdt_getprop(fdt, chosen_node, "linux,ima-kexec-buffer", &len);
+	if (!prop)
+		return;
+
+	ret = do_get_kexec_buffer(prop, len, &addr, &size);
+	fdt_delprop(fdt, chosen_node, "linux,ima-kexec-buffer");
+	if (ret)
+		return;
+
+	ret = delete_fdt_mem_rsv(fdt, addr, size);
+	if (!ret)
+		pr_debug("Removed old IMA buffer reservation.\n");
+}
+
+#ifdef CONFIG_IMA_KEXEC
+/**
+ * arch_ima_add_kexec_buffer - do arch-specific steps to add the IMA buffer
+ *
+ * Architectures should use this function to pass on the IMA buffer
+ * information to the next kernel.
+ *
+ * Return: 0 on success, negative errno on error.
+ */
+int arch_ima_add_kexec_buffer(struct kimage *image, unsigned long load_addr,
+			      size_t size)
+{
+	image->arch.ima_buffer_addr = load_addr;
+	image->arch.ima_buffer_size = size;
+
+	return 0;
+}
+
+static int write_number(void *p, u64 value, int cells)
+{
+	if (cells == 1) {
+		u32 tmp;
+
+		if (value > U32_MAX)
+			return -EINVAL;
+
+		tmp = cpu_to_be32(value);
+		memcpy(p, &tmp, sizeof(tmp));
+	} else if (cells == 2) {
+		u64 tmp;
+
+		tmp = cpu_to_be64(value);
+		memcpy(p, &tmp, sizeof(tmp));
+	} else
+		return -EINVAL;
+
+	return 0;
+}
+
+/**
+ * setup_ima_buffer - add IMA buffer information to the fdt
+ * @image:		kexec image being loaded.
+ * @fdt:		Flattened device tree for the next kernel.
+ * @chosen_node:	Offset to the chosen node.
+ *
+ * Return: 0 on success, or negative errno on error.
+ */
+int setup_ima_buffer(const struct kimage *image, void *fdt, int chosen_node)
+{
+	int ret, addr_cells, size_cells, entry_size;
+	u8 value[16];
+
+	remove_ima_buffer(fdt, chosen_node);
+	if (!image->arch.ima_buffer_size)
+		return 0;
+
+	ret = get_addr_size_cells(&addr_cells, &size_cells);
+	if (ret)
+		return ret;
+
+	entry_size = 4 * (addr_cells + size_cells);
+
+	if (entry_size > sizeof(value))
+		return -EINVAL;
+
+	ret = write_number(value, image->arch.ima_buffer_addr, addr_cells);
+	if (ret)
+		return ret;
+
+	ret = write_number(value + 4 * addr_cells, image->arch.ima_buffer_size,
+			   size_cells);
+	if (ret)
+		return ret;
+
+	ret = fdt_setprop(fdt, chosen_node, "linux,ima-kexec-buffer", value,
+			  entry_size);
+	if (ret < 0)
+		return -EINVAL;
+
+	ret = fdt_add_mem_rsv(fdt, image->arch.ima_buffer_addr,
+			      image->arch.ima_buffer_size);
+	if (ret)
+		return -EINVAL;
+
+	pr_debug("IMA buffer at 0x%llx, size = 0x%zx\n",
+		 image->arch.ima_buffer_addr, image->arch.ima_buffer_size);
+
+	return 0;
+}
+#endif /* CONFIG_IMA_KEXEC */

arch/powerpc/kernel/kexec_elf_64.c

@@ -627,7 +627,7 @@ static void *elf64_load(struct kimage *image, char *kernel_buf,
 		goto out;
 	}
 
-	ret = setup_new_fdt(fdt, initrd_load_addr, initrd_len, cmdline);
+	ret = setup_new_fdt(image, fdt, initrd_load_addr, initrd_len, cmdline);
 	if (ret)
 		goto out;
 

arch/powerpc/kernel/machine_kexec_file_64.c

@@ -27,6 +27,7 @@
 #include <linux/memblock.h>
 #include <linux/of_fdt.h>
 #include <linux/libfdt.h>
+#include <asm/ima.h>
 
 #define SLAVE_CODE_SIZE		256
 
@@ -180,7 +181,7 @@ int setup_purgatory(struct kimage *image, const void *slave_code,
  *
  * Return: 0 on success, or negative errno on error.
  */
-static int delete_fdt_mem_rsv(void *fdt, unsigned long start, unsigned long size)
+int delete_fdt_mem_rsv(void *fdt, unsigned long start, unsigned long size)
 {
 	int i, ret, num_rsvs = fdt_num_mem_rsv(fdt);
 
@@ -209,6 +210,7 @@ static int delete_fdt_mem_rsv(void *fdt, unsigned long start, unsigned long size
 
 /*
  * setup_new_fdt - modify /chosen and memory reservation for the next kernel
+ * @image:		kexec image being loaded.
  * @fdt:		Flattened device tree for the next kernel.
  * @initrd_load_addr:	Address where the next initrd will be loaded.
  * @initrd_len:		Size of the next initrd, or 0 if there will be none.
@@ -217,8 +219,9 @@ static int delete_fdt_mem_rsv(void *fdt, unsigned long start, unsigned long size
  *
  * Return: 0 on success, or negative errno on error.
  */
-int setup_new_fdt(void *fdt, unsigned long initrd_load_addr,
-		  unsigned long initrd_len, const char *cmdline)
+int setup_new_fdt(const struct kimage *image, void *fdt,
+		  unsigned long initrd_load_addr, unsigned long initrd_len,
+		  const char *cmdline)
 {
 	int ret, chosen_node;
 	const void *prop;
@@ -328,6 +331,12 @@ int setup_new_fdt(void *fdt, unsigned long initrd_load_addr,
 		}
 	}
 
+	ret = setup_ima_buffer(image, fdt, chosen_node);
+	if (ret) {
+		pr_err("Error setting up the new device tree.\n");
+		return ret;
+	}
+
 	ret = fdt_setprop(fdt, chosen_node, "linux,booted-from-kexec", NULL, 0);
 	if (ret) {
 		pr_err("Error setting up the new device tree.\n");

include/linux/ima.h

@@ -11,6 +11,7 @@
 #define _LINUX_IMA_H
 
 #include <linux/fs.h>
+#include <linux/kexec.h>
 struct linux_binprm;
 
 #ifdef CONFIG_IMA
@@ -23,6 +24,10 @@ extern int ima_post_read_file(struct file *file, void *buf, loff_t size,
 			      enum kernel_read_file_id id);
 extern void ima_post_path_mknod(struct dentry *dentry);
 
+#ifdef CONFIG_IMA_KEXEC
+extern void ima_add_kexec_buffer(struct kimage *image);
+#endif
+
 #else
 static inline int ima_bprm_check(struct linux_binprm *bprm)
 {
@@ -62,6 +67,13 @@ static inline void ima_post_path_mknod(struct dentry *dentry)
 
 #endif /* CONFIG_IMA */
 
+#ifndef CONFIG_IMA_KEXEC
+struct kimage;
+
+static inline void ima_add_kexec_buffer(struct kimage *image)
+{}
+#endif
+
 #ifdef CONFIG_IMA_APPRAISE
 extern void ima_inode_post_setattr(struct dentry *dentry);
 extern int ima_inode_setxattr(struct dentry *dentry, const char *xattr_name,

include/linux/ratelimit.h

@@ -77,8 +77,11 @@ extern int ___ratelimit(struct ratelimit_state *rs, const char *func);
 
 #ifdef CONFIG_PRINTK
 
-#define WARN_ON_RATELIMIT(condition, state)			\
-		WARN_ON((condition) && __ratelimit(state))
+#define WARN_ON_RATELIMIT(condition, state)	({		\
+	bool __rtn_cond = !!(condition);			\
+	WARN_ON(__rtn_cond && __ratelimit(state));		\
+	__rtn_cond;						\
+})
 
 #define WARN_RATELIMIT(condition, format, ...)			\
 ({								\

kernel/kcov.c

@@ -19,6 +19,7 @@
 #include <linux/debugfs.h>
 #include <linux/uaccess.h>
 #include <linux/kcov.h>
+#include <asm/setup.h>
 
 /*
  * kcov descriptor (one per opened debugfs file).
@@ -73,6 +74,11 @@ void notrace __sanitizer_cov_trace_pc(void)
 	if (mode == KCOV_MODE_TRACE) {
 		unsigned long *area;
 		unsigned long pos;
+		unsigned long ip = _RET_IP_;
+
+#ifdef CONFIG_RANDOMIZE_BASE
+		ip -= kaslr_offset();
+#endif
 
 		/*
 		 * There is some code that runs in interrupts but for which
@@ -86,7 +92,7 @@ void notrace __sanitizer_cov_trace_pc(void)
 		/* The first word is number of subsequent PCs. */
 		pos = READ_ONCE(area[0]) + 1;
 		if (likely(pos < t->kcov_size)) {
-			area[pos] = _RET_IP_;
+			area[pos] = ip;
 			WRITE_ONCE(area[0], pos);
 		}
 	}

kernel/kexec_file.c

@@ -19,6 +19,7 @@
 #include <linux/mutex.h>
 #include <linux/list.h>
 #include <linux/fs.h>
+#include <linux/ima.h>
 #include <crypto/hash.h>
 #include <crypto/sha.h>
 #include <linux/syscalls.h>
@@ -132,6 +133,9 @@ kimage_file_prepare_segments(struct kimage *image, int kernel_fd, int initrd_fd,
 		return ret;
 	image->kernel_buf_len = size;
 
+	/* IMA needs to pass the measurement list to the next kernel. */
+	ima_add_kexec_buffer(image);
+
 	/* Call arch image probe handlers */
 	ret = arch_kexec_kernel_image_probe(image, image->kernel_buf,
 					    image->kernel_buf_len);

lib/Kconfig.debug

@@ -26,7 +26,7 @@ config CONSOLE_LOGLEVEL_DEFAULT
 	  the kernel bootargs. loglevel=<x> continues to override whatever
 	  value is specified here as well.
 
-	  Note: This does not affect the log level of un-prefixed prink()
+	  Note: This does not affect the log level of un-prefixed printk()
 	  usage in the kernel. That is controlled by the MESSAGE_LOGLEVEL_DEFAULT
 	  option.
 

mm/fadvise.c

@@ -139,7 +139,20 @@ SYSCALL_DEFINE4(fadvise64_64, int, fd, loff_t, offset, loff_t, len, int, advice)
 		}
 
 		if (end_index >= start_index) {
-			unsigned long count = invalidate_mapping_pages(mapping,
+			unsigned long count;
+
+			/*
+			 * It's common to FADV_DONTNEED right after
+			 * the read or write that instantiates the
+			 * pages, in which case there will be some
+			 * sitting on the local LRU cache. Try to
+			 * avoid the expensive remote drain and the
+			 * second cache tree walk below by flushing
+			 * them out right away.
+			 */
+			lru_add_drain();
+
+			count = invalidate_mapping_pages(mapping,
 						start_index, end_index);
 
 			/*

security/integrity/ima/Kconfig

@@ -27,6 +27,18 @@ config IMA
 	  to learn more about IMA.
 	  If unsure, say N.
 
+config IMA_KEXEC
+	bool "Enable carrying the IMA measurement list across a soft boot"
+	depends on IMA && TCG_TPM && HAVE_IMA_KEXEC
+	default n
+	help
+	   TPM PCRs are only reset on a hard reboot.  In order to validate
+	   a TPM's quote after a soft boot, the IMA measurement list of the
+	   running kernel must be saved and restored on boot.
+
+	   Depending on the IMA policy, the measurement list can grow to
+	   be very large.
+
 config IMA_MEASURE_PCR_IDX
 	int
 	depends on IMA

security/integrity/ima/Makefile

@@ -8,4 +8,5 @@ obj-$(CONFIG_IMA) += ima.o
 ima-y := ima_fs.o ima_queue.o ima_init.o ima_main.o ima_crypto.o ima_api.o \
 	 ima_policy.o ima_template.o ima_template_lib.o
 ima-$(CONFIG_IMA_APPRAISE) += ima_appraise.o
+ima-$(CONFIG_HAVE_IMA_KEXEC) += ima_kexec.o
 obj-$(CONFIG_IMA_BLACKLIST_KEYRING) += ima_mok.o

security/integrity/ima/ima.h

@@ -28,6 +28,10 @@
 
 #include "../integrity.h"
 
+#ifdef CONFIG_HAVE_IMA_KEXEC
+#include <asm/ima.h>
+#endif
+
 enum ima_show_type { IMA_SHOW_BINARY, IMA_SHOW_BINARY_NO_FIELD_LEN,
 		     IMA_SHOW_BINARY_OLD_STRING_FMT, IMA_SHOW_ASCII };
 enum tpm_pcrs { TPM_PCR0 = 0, TPM_PCR8 = 8 };
@@ -81,6 +85,7 @@ struct ima_template_field {
 
 /* IMA template descriptor definition */
 struct ima_template_desc {
+	struct list_head list;
 	char *name;
 	char *fmt;
 	int num_fields;
@@ -102,6 +107,27 @@ struct ima_queue_entry {
 };
 extern struct list_head ima_measurements;	/* list of all measurements */
 
+/* Some details preceding the binary serialized measurement list */
+struct ima_kexec_hdr {
+	u16 version;
+	u16 _reserved0;
+	u32 _reserved1;
+	u64 buffer_size;
+	u64 count;
+};
+
+#ifdef CONFIG_HAVE_IMA_KEXEC
+void ima_load_kexec_buffer(void);
+#else
+static inline void ima_load_kexec_buffer(void) {}
+#endif /* CONFIG_HAVE_IMA_KEXEC */
+
+/*
+ * The default binary_runtime_measurements list format is defined as the
+ * platform native format.  The canonical format is defined as little-endian.
+ */
+extern bool ima_canonical_fmt;
+
 /* Internal IMA function definitions */
 int ima_init(void);
 int ima_fs_init(void);
@@ -122,7 +148,12 @@ int ima_init_crypto(void);
 void ima_putc(struct seq_file *m, void *data, int datalen);
 void ima_print_digest(struct seq_file *m, u8 *digest, u32 size);
 struct ima_template_desc *ima_template_desc_current(void);
+int ima_restore_measurement_entry(struct ima_template_entry *entry);
+int ima_restore_measurement_list(loff_t bufsize, void *buf);
+int ima_measurements_show(struct seq_file *m, void *v);
+unsigned long ima_get_binary_runtime_size(void);
 int ima_init_template(void);
+void ima_init_template_list(void);
 
 /*
  * used to protect h_table and sha_table