Blob Blame History Raw
From 56ce13afe1b17cd2817c596b3a9e25e51937a328 Mon Sep 17 00:00:00 2001
From: Matt Fleming <matt.fleming@intel.com>
Date: Thu, 19 Jul 2012 10:23:48 +0100
Subject: [PATCH 01/14] x86, efi: Handover Protocol

As things currently stand, traditional EFI boot loaders and the EFI
boot stub are carrying essentially the same initialisation code
required to setup an EFI machine for booting a kernel. There's really
no need to have this code in two places and the hope is that, with
this new protocol, initialisation and booting of the kernel can be
left solely to the kernel's EFI boot stub. The responsibilities of the
boot loader then become,

   o Loading the kernel image from boot media

File system code still needs to be carried by boot loaders for the
scenario where the kernel and initrd files reside on a file system
that the EFI firmware doesn't natively understand, such as ext4, etc.

   o Providing a user interface

Boot loaders still need to display any menus/interfaces, for example
to allow the user to select from a list of kernels.

Bump the boot protocol number because we added the 'handover_offset'
field to indicate the location of the handover protocol entry point.

Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Matthew Garrett <mjg@redhat.com>
Cc: Peter Jones <pjones@redhat.com>
Cc: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Matt Fleming <matt.fleming@intel.com>
---
 Documentation/x86/boot.txt         |  41 ++++++++
 arch/x86/boot/compressed/eboot.c   | 198 ++++++++++++++++++++++---------------
 arch/x86/boot/compressed/head_32.S |  10 ++
 arch/x86/boot/compressed/head_64.S |  10 ++
 arch/x86/boot/header.S             |   4 +-
 arch/x86/include/asm/bootparam.h   |   1 +
 6 files changed, 185 insertions(+), 79 deletions(-)

diff --git a/Documentation/x86/boot.txt b/Documentation/x86/boot.txt
index 7c3a880..c6539a4 100644
--- a/Documentation/x86/boot.txt
+++ b/Documentation/x86/boot.txt
@@ -54,6 +54,9 @@ Protocol 2.10:	(Kernel 2.6.31) Added a protocol for relaxed alignment
 		beyond the kernel_alignment added, new init_size and
 		pref_address fields.  Added extended boot loader IDs.
 
+Protocol 2.11:	(Kernel 3.6) Added a field for offset of EFI handover
+		protocol entry point.
+
 **** MEMORY LAYOUT
 
 The traditional memory map for the kernel loader, used for Image or
@@ -189,6 +192,7 @@ Offset	Proto	Name		Meaning
 				of struct setup_data
 0258/8	2.10+	pref_address	Preferred loading address
 0260/4	2.10+	init_size	Linear memory required during initialization
+0264/4	2.11+	handover_offset	Offset of handover entry point
 
 (1) For backwards compatibility, if the setup_sects field contains 0, the
     real value is 4.
@@ -690,6 +694,16 @@ Offset/size:	0x260/4
   else
 	runtime_start = pref_address
 
+Field name:	handover_offset
+Type:		read
+Offset/size:	0x264/4
+
+  This field is the offset from the beginning of the kernel image to
+  the EFI handover protocol entry point. Boot loaders using the EFI
+  handover protocol to boot the kernel should jump to this offset.
+
+  See EFI HANDOVER PROTOCOL below for more details.
+
 
 **** THE IMAGE CHECKSUM
 
@@ -1010,3 +1024,30 @@ segment; __BOOS_CS must have execute/read permission, and __BOOT_DS
 must have read/write permission; CS must be __BOOT_CS and DS, ES, SS
 must be __BOOT_DS; interrupt must be disabled; %esi must hold the base
 address of the struct boot_params; %ebp, %edi and %ebx must be zero.
+
+**** EFI HANDOVER PROTOCOL
+
+This protocol allows boot loaders to defer initialisation to the EFI
+boot stub. The boot loader is required to load the kernel/initrd(s)
+from the boot media and jump to the EFI handover protocol entry point
+which is hdr->handover_offset bytes from the beginning of
+startup_{32,64}.
+
+The function prototype for the handover entry point looks like this,
+
+    efi_main(void *handle, efi_system_table_t *table, struct boot_params *bp)
+
+'handle' is the EFI image handle passed to the boot loader by the EFI
+firmware, 'table' is the EFI system table - these are the first two
+arguments of the "handoff state" as described in section 2.3 of the
+UEFI specification. 'bp' is the boot loader-allocated boot params.
+
+The boot loader *must* fill out the following fields in bp,
+
+    o hdr.code32_start
+    o hdr.cmd_line_ptr
+    o hdr.cmdline_size
+    o hdr.ramdisk_image (if applicable)
+    o hdr.ramdisk_size  (if applicable)
+
+All other fields should be zero.
diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c
index 4e85f5f..b3e0227 100644
--- a/arch/x86/boot/compressed/eboot.c
+++ b/arch/x86/boot/compressed/eboot.c
@@ -729,32 +729,68 @@ fail:
  * need to create one ourselves (usually the bootloader would create
  * one for us).
  */
-static efi_status_t make_boot_params(struct boot_params *boot_params,
-				     efi_loaded_image_t *image,
-				     void *handle)
+struct boot_params *make_boot_params(void *handle, efi_system_table_t *_table)
 {
-	struct efi_info *efi = &boot_params->efi_info;
-	struct apm_bios_info *bi = &boot_params->apm_bios_info;
-	struct sys_desc_table *sdt = &boot_params->sys_desc_table;
-	struct e820entry *e820_map = &boot_params->e820_map[0];
-	struct e820entry *prev = NULL;
-	struct setup_header *hdr = &boot_params->hdr;
-	unsigned long size, key, desc_size, _size;
-	efi_memory_desc_t *mem_map;
-	void *options = image->load_options;
-	u32 load_options_size = image->load_options_size / 2; /* ASCII */
+	struct boot_params *boot_params;
+	struct sys_desc_table *sdt;
+	struct apm_bios_info *bi;
+	struct setup_header *hdr;
+	struct efi_info *efi;
+	efi_loaded_image_t *image;
+	void *options;
+	u32 load_options_size;
+	efi_guid_t proto = LOADED_IMAGE_PROTOCOL_GUID;
 	int options_size = 0;
 	efi_status_t status;
-	__u32 desc_version;
 	unsigned long cmdline;
-	u8 nr_entries;
 	u16 *s2;
 	u8 *s1;
 	int i;
 
+	sys_table = _table;
+
+	/* Check if we were booted by the EFI firmware */
+	if (sys_table->hdr.signature != EFI_SYSTEM_TABLE_SIGNATURE)
+		return NULL;
+
+	status = efi_call_phys3(sys_table->boottime->handle_protocol,
+				handle, &proto, (void *)&image);
+	if (status != EFI_SUCCESS) {
+		efi_printk("Failed to get handle for LOADED_IMAGE_PROTOCOL\n");
+		return NULL;
+	}
+
+	status = low_alloc(0x4000, 1, (unsigned long *)&boot_params);
+	if (status != EFI_SUCCESS) {
+		efi_printk("Failed to alloc lowmem for boot params\n");
+		return NULL;
+	}
+
+	memset(boot_params, 0x0, 0x4000);
+
+	hdr = &boot_params->hdr;
+	efi = &boot_params->efi_info;
+	bi = &boot_params->apm_bios_info;
+	sdt = &boot_params->sys_desc_table;
+
+	/* Copy the second sector to boot_params */
+	memcpy(&hdr->jump, image->image_base + 512, 512);
+
+	/*
+	 * Fill out some of the header fields ourselves because the
+	 * EFI firmware loader doesn't load the first sector.
+	 */
+	hdr->root_flags = 1;
+	hdr->vid_mode = 0xffff;
+	hdr->boot_flag = 0xAA55;
+
+	hdr->code32_start = (__u64)(unsigned long)image->image_base;
+
 	hdr->type_of_loader = 0x21;
 
 	/* Convert unicode cmdline to ascii */
+	options = image->load_options;
+	load_options_size = image->load_options_size / 2; /* ASCII */
 	cmdline = 0;
 	s2 = (u16 *)options;
 
@@ -791,18 +827,36 @@ static efi_status_t make_boot_params(struct boot_params *boot_params,
 	hdr->ramdisk_image = 0;
 	hdr->ramdisk_size = 0;
 
-	status = handle_ramdisks(image, hdr);
-	if (status != EFI_SUCCESS)
-		goto free_cmdline;
-
-	setup_graphics(boot_params);
-
 	/* Clear APM BIOS info */
 	memset(bi, 0, sizeof(*bi));
 
 	memset(sdt, 0, sizeof(*sdt));
 
-	memcpy(&efi->efi_loader_signature, EFI_LOADER_SIGNATURE, sizeof(__u32));
+	status = handle_ramdisks(image, hdr);
+	if (status != EFI_SUCCESS)
+		goto fail2;
+
+	return boot_params;
+fail2:
+	if (options_size)
+		low_free(options_size, hdr->cmd_line_ptr);
+fail:
+	low_free(0x4000, (unsigned long)boot_params);
+	return NULL;
+}
+
+static efi_status_t exit_boot(struct boot_params *boot_params,
+			      void *handle)
+{
+	struct efi_info *efi = &boot_params->efi_info;
+	struct e820entry *e820_map = &boot_params->e820_map[0];
+	struct e820entry *prev = NULL;
+	unsigned long size, key, desc_size, _size;
+	efi_memory_desc_t *mem_map;
+	efi_status_t status;
+	__u32 desc_version;
+	u8 nr_entries;
+	int i;
 
 	size = sizeof(*mem_map) * 32;
 
@@ -811,7 +865,7 @@ again:
 	_size = size;
 	status = low_alloc(size, 1, (unsigned long *)&mem_map);
 	if (status != EFI_SUCCESS)
-		goto free_cmdline;
+		return status;
 
 	status = efi_call_phys5(sys_table->boottime->get_memory_map, &size,
 				mem_map, &key, &desc_size, &desc_version);
@@ -823,6 +877,7 @@ again:
 	if (status != EFI_SUCCESS)
 		goto free_mem_map;
 
+	memcpy(&efi->efi_loader_signature, EFI_LOADER_SIGNATURE, sizeof(__u32));
 	efi->efi_systab = (unsigned long)sys_table;
 	efi->efi_memdesc_size = desc_size;
 	efi->efi_memdesc_version = desc_version;
@@ -906,61 +961,13 @@ again:
 
 free_mem_map:
 	low_free(_size, (unsigned long)mem_map);
-free_cmdline:
-	if (options_size)
-		low_free(options_size, hdr->cmd_line_ptr);
-fail:
 	return status;
 }
 
-/*
- * On success we return a pointer to a boot_params structure, and NULL
- * on failure.
- */
-struct boot_params *efi_main(void *handle, efi_system_table_t *_table)
+static efi_status_t relocate_kernel(struct setup_header *hdr)
 {
-	struct boot_params *boot_params;
 	unsigned long start, nr_pages;
-	struct desc_ptr *gdt, *idt;
-	efi_loaded_image_t *image;
-	struct setup_header *hdr;
 	efi_status_t status;
-	efi_guid_t proto = LOADED_IMAGE_PROTOCOL_GUID;
-	struct desc_struct *desc;
-
-	sys_table = _table;
-
-	/* Check if we were booted by the EFI firmware */
-	if (sys_table->hdr.signature != EFI_SYSTEM_TABLE_SIGNATURE)
-		goto fail;
-
-	status = efi_call_phys3(sys_table->boottime->handle_protocol,
-				handle, &proto, (void *)&image);
-	if (status != EFI_SUCCESS) {
-		efi_printk("Failed to get handle for LOADED_IMAGE_PROTOCOL\n");
-		goto fail;
-	}
-
-	status = low_alloc(0x4000, 1, (unsigned long *)&boot_params);
-	if (status != EFI_SUCCESS) {
-		efi_printk("Failed to alloc lowmem for boot params\n");
-		goto fail;
-	}
-
-	memset(boot_params, 0x0, 0x4000);
-
-	hdr = &boot_params->hdr;
-
-	/* Copy the second sector to boot_params */
-	memcpy(&hdr->jump, image->image_base + 512, 512);
-
-	/*
-	 * Fill out some of the header fields ourselves because the
-	 * EFI firmware loader doesn't load the first sector.
-	 */
-	hdr->root_flags = 1;
-	hdr->vid_mode = 0xffff;
-	hdr->boot_flag = 0xAA55;
 
 	/*
 	 * The EFI firmware loader could have placed the kernel image
@@ -978,16 +985,40 @@ struct boot_params *efi_main(void *handle, efi_system_table_t *_table)
 	if (status != EFI_SUCCESS) {
 		status = low_alloc(hdr->init_size, hdr->kernel_alignment,
 				   &start);
-		if (status != EFI_SUCCESS) {
+		if (status != EFI_SUCCESS)
 			efi_printk("Failed to alloc mem for kernel\n");
-			goto fail;
-		}
 	}
 
+	if (status == EFI_SUCCESS)
+		memcpy((void *)start, (void *)(unsigned long)hdr->code32_start,
+		       hdr->init_size);
+
+	hdr->pref_address = hdr->code32_start;
 	hdr->code32_start = (__u32)start;
-	hdr->pref_address = (__u64)(unsigned long)image->image_base;
 
-	memcpy((void *)start, image->image_base, image->image_size);
+	return status;
+}
+
+/*
+ * On success we return a pointer to a boot_params structure, and NULL
+ * on failure.
+ */
+struct boot_params *efi_main(void *handle, efi_system_table_t *_table,
+			     struct boot_params *boot_params)
+{
+	struct desc_ptr *gdt, *idt;
+	efi_loaded_image_t *image;
+	struct setup_header *hdr = &boot_params->hdr;
+	efi_status_t status;
+	struct desc_struct *desc;
+
+	sys_table = _table;
+
+	/* Check if we were booted by the EFI firmware */
+	if (sys_table->hdr.signature != EFI_SYSTEM_TABLE_SIGNATURE)
+		goto fail;
+
+	setup_graphics(boot_params);
 
 	status = efi_call_phys3(sys_table->boottime->allocate_pool,
 				EFI_LOADER_DATA, sizeof(*gdt),
@@ -1015,7 +1046,18 @@ struct boot_params *efi_main(void *handle, efi_system_table_t *_table)
 	idt->size = 0;
 	idt->address = 0;
 
-	status = make_boot_params(boot_params, image, handle);
+	/*
+	 * If the kernel isn't already loaded at the preferred load
+	 * address, relocate it.
+	 */
+	if (hdr->pref_address != hdr->code32_start) {
+		status = relocate_kernel(hdr);
+
+		if (status != EFI_SUCCESS)
+			goto fail;
+	}
+
+	status = exit_boot(boot_params, handle);
 	if (status != EFI_SUCCESS)
 		goto fail;
 
diff --git a/arch/x86/boot/compressed/head_32.S b/arch/x86/boot/compressed/head_32.S
index c85e3ac..aa4aaf1 100644
--- a/arch/x86/boot/compressed/head_32.S
+++ b/arch/x86/boot/compressed/head_32.S
@@ -42,6 +42,16 @@ ENTRY(startup_32)
 	 */
 	add	$0x4, %esp
 
+	call	make_boot_params
+	cmpl	$0, %eax
+	je	1f
+	movl	0x4(%esp), %esi
+	movl	(%esp), %ecx
+	pushl	%eax
+	pushl	%esi
+	pushl	%ecx
+
+	.org 0x30,0x90
 	call	efi_main
 	cmpl	$0, %eax
 	movl	%eax, %esi
diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S
index 87e03a1..2c4b171 100644
--- a/arch/x86/boot/compressed/head_64.S
+++ b/arch/x86/boot/compressed/head_64.S
@@ -209,6 +209,16 @@ ENTRY(startup_64)
 	.org 0x210
 	mov	%rcx, %rdi
 	mov	%rdx, %rsi
+	pushq	%rdi
+	pushq	%rsi
+	call	make_boot_params
+	cmpq	$0,%rax
+	je	1f
+	mov	%rax, %rdx
+	popq	%rsi
+	popq	%rdi
+
+	.org 0x230,0x90
 	call	efi_main
 	movq	%rax,%rsi
 	cmpq	$0,%rax
diff --git a/arch/x86/boot/header.S b/arch/x86/boot/header.S
index efe5acf..cd921fe 100644
--- a/arch/x86/boot/header.S
+++ b/arch/x86/boot/header.S
@@ -283,7 +283,7 @@ _start:
 	# Part 2 of the header, from the old setup.S
 
 		.ascii	"HdrS"		# header signature
-		.word	0x020a		# header version number (>= 0x0105)
+		.word	0x020b		# header version number (>= 0x0105)
 					# or else old loadlin-1.5 will fail)
 		.globl realmode_swtch
 realmode_swtch:	.word	0, 0		# default_switch, SETUPSEG
@@ -401,6 +401,8 @@ pref_address:		.quad LOAD_PHYSICAL_ADDR	# preferred load addr
 #define INIT_SIZE VO_INIT_SIZE
 #endif
 init_size:		.long INIT_SIZE		# kernel initialization size
+handover_offset:	.long 0x30		# offset to the handover
+						# protocol entry point
 
 # End of setup header #####################################################
 
diff --git a/arch/x86/include/asm/bootparam.h b/arch/x86/include/asm/bootparam.h
index eb45aa6..2ad874c 100644
--- a/arch/x86/include/asm/bootparam.h
+++ b/arch/x86/include/asm/bootparam.h
@@ -66,6 +66,7 @@ struct setup_header {
 	__u64	setup_data;
 	__u64	pref_address;
 	__u32	init_size;
+	__u32	handover_offset;
 } __attribute__((packed));
 
 struct sys_desc_table {
-- 
1.7.11.2


From 948fbe310f85f3a51a101ea23f38c59c70792832 Mon Sep 17 00:00:00 2001
From: Matthew Garrett <mjg@redhat.com>
Date: Thu, 8 Mar 2012 09:56:33 -0500
Subject: [PATCH 02/14] Secure boot: Add new capability

Secure boot adds certain policy requirements, including that root must not
be able to do anything that could cause the kernel to execute arbitrary code.
The simplest way to handle this would seem to be to add a new capability
and gate various functionality on that. We'll then strip it from the initial
capability set if required.

Signed-off-by: Matthew Garrett <mjg@redhat.com>
---
 include/linux/capability.h | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/include/linux/capability.h b/include/linux/capability.h
index d10b7ed..6a39163 100644
--- a/include/linux/capability.h
+++ b/include/linux/capability.h
@@ -364,7 +364,11 @@ struct cpu_vfs_cap_data {
 
 #define CAP_BLOCK_SUSPEND    36
 
-#define CAP_LAST_CAP         CAP_BLOCK_SUSPEND
+/* Allow things that are dangerous under secure boot */
+
+#define CAP_SECURE_FIRMWARE  37
+
+#define CAP_LAST_CAP         CAP_SECURE_FIRMWARE
 
 #define cap_valid(x) ((x) >= 0 && (x) <= CAP_LAST_CAP)
 
-- 
1.7.11.2


From 56150c6ad369f31e34e438744d34c505751a8b78 Mon Sep 17 00:00:00 2001
From: Matthew Garrett <mjg@redhat.com>
Date: Thu, 8 Mar 2012 10:10:38 -0500
Subject: [PATCH 03/14] PCI: Lock down BAR access in secure boot environments

Any hardware that can potentially generate DMA has to be locked down from
userspace in order to avoid it being possible for an attacker to cause
arbitrary kernel behaviour. Default to paranoid - in future we can
potentially relax this for sufficiently IOMMU-isolated devices.

Signed-off-by: Matthew Garrett <mjg@redhat.com>
---
 drivers/pci/pci-sysfs.c | 9 +++++++++
 drivers/pci/proc.c      | 8 +++++++-
 drivers/pci/syscall.c   | 2 +-
 3 files changed, 17 insertions(+), 2 deletions(-)

diff --git a/drivers/pci/pci-sysfs.c b/drivers/pci/pci-sysfs.c
index 86c63fe..d3adb7b 100644
--- a/drivers/pci/pci-sysfs.c
+++ b/drivers/pci/pci-sysfs.c
@@ -513,6 +513,9 @@ pci_write_config(struct file* filp, struct kobject *kobj,
 	loff_t init_off = off;
 	u8 *data = (u8*) buf;
 
+	if (!capable(CAP_SECURE_FIRMWARE))
+		return -EPERM;
+
 	if (off > dev->cfg_size)
 		return 0;
 	if (off + count > dev->cfg_size) {
@@ -815,6 +818,9 @@ pci_mmap_resource(struct kobject *kobj, struct bin_attribute *attr,
 	resource_size_t start, end;
 	int i;
 
+	if (!capable(CAP_SECURE_FIRMWARE))
+		return -EPERM;
+
 	for (i = 0; i < PCI_ROM_RESOURCE; i++)
 		if (res == &pdev->resource[i])
 			break;
@@ -922,6 +928,9 @@ pci_write_resource_io(struct file *filp, struct kobject *kobj,
 		      struct bin_attribute *attr, char *buf,
 		      loff_t off, size_t count)
 {
+	if (!capable(CAP_SECURE_FIRMWARE))
+		return -EPERM;
+
 	return pci_resource_io(filp, kobj, attr, buf, off, count, true);
 }
 
diff --git a/drivers/pci/proc.c b/drivers/pci/proc.c
index 27911b5..01d4753 100644
--- a/drivers/pci/proc.c
+++ b/drivers/pci/proc.c
@@ -135,6 +135,9 @@ proc_bus_pci_write(struct file *file, const char __user *buf, size_t nbytes, lof
 	int size = dp->size;
 	int cnt;
 
+	if (!capable(CAP_SECURE_FIRMWARE))
+		return -EPERM;
+
 	if (pos >= size)
 		return 0;
 	if (nbytes >= size)
@@ -211,6 +214,9 @@ static long proc_bus_pci_ioctl(struct file *file, unsigned int cmd,
 #endif /* HAVE_PCI_MMAP */
 	int ret = 0;
 
+	if (!capable(CAP_SECURE_FIRMWARE))
+		return -EPERM;
+
 	switch (cmd) {
 	case PCIIOC_CONTROLLER:
 		ret = pci_domain_nr(dev->bus);
@@ -251,7 +257,7 @@ static int proc_bus_pci_mmap(struct file *file, struct vm_area_struct *vma)
 	struct pci_filp_private *fpriv = file->private_data;
 	int i, ret;
 
-	if (!capable(CAP_SYS_RAWIO))
+	if (!capable(CAP_SYS_RAWIO) || !capable(CAP_SECURE_FIRMWARE))
 		return -EPERM;
 
 	/* Make sure the caller is mapping a real resource for this device */
diff --git a/drivers/pci/syscall.c b/drivers/pci/syscall.c
index e1c1ec5..a778ba9 100644
--- a/drivers/pci/syscall.c
+++ b/drivers/pci/syscall.c
@@ -92,7 +92,7 @@ SYSCALL_DEFINE5(pciconfig_write, unsigned long, bus, unsigned long, dfn,
 	u32 dword;
 	int err = 0;
 
-	if (!capable(CAP_SYS_ADMIN))
+	if (!capable(CAP_SYS_ADMIN) || !capable(CAP_SECURE_FIRMWARE))
 		return -EPERM;
 
 	dev = pci_get_bus_and_slot(bus, dfn);
-- 
1.7.11.2


From 888347d81b1ddcdcd5989cba1c212aed549928eb Mon Sep 17 00:00:00 2001
From: Matthew Garrett <mjg@redhat.com>
Date: Thu, 8 Mar 2012 10:35:59 -0500
Subject: [PATCH 04/14] x86: Lock down IO port access in secure boot
 environments

IO port access would permit users to gain access to PCI configuration
registers, which in turn (on a lot of hardware) give access to MMIO register
space. This would potentially permit root to trigger arbitrary DMA, so lock
it down by default.

Signed-off-by: Matthew Garrett <mjg@redhat.com>
---
 arch/x86/kernel/ioport.c | 4 ++--
 drivers/char/mem.c       | 3 +++
 2 files changed, 5 insertions(+), 2 deletions(-)

diff --git a/arch/x86/kernel/ioport.c b/arch/x86/kernel/ioport.c
index 8c96897..c3a1bb2 100644
--- a/arch/x86/kernel/ioport.c
+++ b/arch/x86/kernel/ioport.c
@@ -28,7 +28,7 @@ asmlinkage long sys_ioperm(unsigned long from, unsigned long num, int turn_on)
 
 	if ((from + num <= from) || (from + num > IO_BITMAP_BITS))
 		return -EINVAL;
-	if (turn_on && !capable(CAP_SYS_RAWIO))
+	if (turn_on && (!capable(CAP_SYS_RAWIO) || !capable(CAP_SECURE_FIRMWARE)))
 		return -EPERM;
 
 	/*
@@ -102,7 +102,7 @@ long sys_iopl(unsigned int level, struct pt_regs *regs)
 		return -EINVAL;
 	/* Trying to gain more privileges? */
 	if (level > old) {
-		if (!capable(CAP_SYS_RAWIO))
+		if (!capable(CAP_SYS_RAWIO) || !capable(CAP_SECURE_FIRMWARE))
 			return -EPERM;
 	}
 	regs->flags = (regs->flags & ~X86_EFLAGS_IOPL) | (level << 12);
diff --git a/drivers/char/mem.c b/drivers/char/mem.c
index e5eedfa..8f5f872 100644
--- a/drivers/char/mem.c
+++ b/drivers/char/mem.c
@@ -597,6 +597,9 @@ static ssize_t write_port(struct file *file, const char __user *buf,
 	unsigned long i = *ppos;
 	const char __user * tmp = buf;
 
+	if (!capable(CAP_SECURE_FIRMWARE))
+		return -EPERM;
+
 	if (!access_ok(VERIFY_READ, buf, count))
 		return -EFAULT;
 	while (count-- > 0 && i < 65536) {
-- 
1.7.11.2


From a02e91ca8639c6a3a43c684892e2802973c02efc Mon Sep 17 00:00:00 2001
From: Matthew Garrett <mjg@redhat.com>
Date: Fri, 9 Mar 2012 08:39:37 -0500
Subject: [PATCH 05/14] ACPI: Limit access to custom_method

It must be impossible for even root to get code executed in kernel context
under a secure boot environment. custom_method effectively allows arbitrary
access to system memory, so it needs to have a capability check here.

Signed-off-by: Matthew Garrett <mjg@redhat.com>
---
 drivers/acpi/custom_method.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/acpi/custom_method.c b/drivers/acpi/custom_method.c
index 5d42c24..3e78014 100644
--- a/drivers/acpi/custom_method.c
+++ b/drivers/acpi/custom_method.c
@@ -29,6 +29,9 @@ static ssize_t cm_write(struct file *file, const char __user * user_buf,
 	struct acpi_table_header table;
 	acpi_status status;
 
+	if (!capable(CAP_SECURE_FIRMWARE))
+		return -EPERM;
+
 	if (!(*ppos)) {
 		/* parse the table header to get the table length */
 		if (count <= sizeof(struct acpi_table_header))
-- 
1.7.11.2


From c523e4918f56e5c17e39c0a5997cc1e741c0f42b Mon Sep 17 00:00:00 2001
From: Matthew Garrett <mjg@redhat.com>
Date: Fri, 9 Mar 2012 08:46:50 -0500
Subject: [PATCH 06/14] asus-wmi: Restrict debugfs interface

We have no way of validating what all of the Asus WMI methods do on a
given machine, and there's a risk that some will allow hardware state to
be manipulated in such a way that arbitrary code can be executed in the
kernel. Add a capability check to prevent that.

Signed-off-by: Matthew Garrett <mjg@redhat.com>
---
 drivers/platform/x86/asus-wmi.c | 9 +++++++++
 1 file changed, 9 insertions(+)

diff --git a/drivers/platform/x86/asus-wmi.c b/drivers/platform/x86/asus-wmi.c
index 77aadde..ba715c0 100644
--- a/drivers/platform/x86/asus-wmi.c
+++ b/drivers/platform/x86/asus-wmi.c
@@ -1504,6 +1504,9 @@ static int show_dsts(struct seq_file *m, void *data)
 	int err;
 	u32 retval = -1;
 
+	if (!capable(CAP_SECURE_FIRMWARE))
+		return -EPERM;
+
 	err = asus_wmi_get_devstate(asus, asus->debug.dev_id, &retval);
 
 	if (err < 0)
@@ -1520,6 +1523,9 @@ static int show_devs(struct seq_file *m, void *data)
 	int err;
 	u32 retval = -1;
 
+	if (!capable(CAP_SECURE_FIRMWARE))
+		return -EPERM;
+
 	err = asus_wmi_set_devstate(asus->debug.dev_id, asus->debug.ctrl_param,
 				    &retval);
 
@@ -1544,6 +1550,9 @@ static int show_call(struct seq_file *m, void *data)
 	union acpi_object *obj;
 	acpi_status status;
 
+	if (!capable(CAP_SECURE_FIRMWARE))
+		return -EPERM;
+
 	status = wmi_evaluate_method(ASUS_WMI_MGMT_GUID,
 				     1, asus->debug.method_id,
 				     &input, &output);
-- 
1.7.11.2


From 5dc9f0a45d092e5aec177eac1e5e19b62fb28cb2 Mon Sep 17 00:00:00 2001
From: Matthew Garrett <mjg@redhat.com>
Date: Fri, 9 Mar 2012 09:28:15 -0500
Subject: [PATCH 07/14] Restrict /dev/mem and /dev/kmem in secure boot setups

Allowing users to write to address space makes it possible for the kernel
to be subverted. Restrict this when we need to protect the kernel.

Signed-off-by: Matthew Garrett <mjg@redhat.com>
---
 drivers/char/mem.c | 6 ++++++
 1 file changed, 6 insertions(+)

diff --git a/drivers/char/mem.c b/drivers/char/mem.c
index 8f5f872..c1de8e1 100644
--- a/drivers/char/mem.c
+++ b/drivers/char/mem.c
@@ -158,6 +158,9 @@ static ssize_t write_mem(struct file *file, const char __user *buf,
 	unsigned long copied;
 	void *ptr;
 
+	if (!capable(CAP_SECURE_FIRMWARE))
+		return -EPERM;
+
 	if (!valid_phys_addr_range(p, count))
 		return -EFAULT;
 
@@ -530,6 +533,9 @@ static ssize_t write_kmem(struct file *file, const char __user *buf,
 	char * kbuf; /* k-addr because vwrite() takes vmlist_lock rwlock */
 	int err = 0;
 
+	if (!capable(CAP_SECURE_FIRMWARE))
+		return -EPERM;
+
 	if (p < (unsigned long) high_memory) {
 		unsigned long to_write = min_t(unsigned long, count,
 					       (unsigned long)high_memory - p);
-- 
1.7.11.2


From 16a693dde4c4dca871d920e15fe9dda01000ef86 Mon Sep 17 00:00:00 2001
From: Matthew Garrett <mjg@redhat.com>
Date: Fri, 9 Mar 2012 11:47:56 -0500
Subject: [PATCH 08/14] kexec: Disable in a secure boot environment

kexec could be used as a vector for a malicious user to use a signed kernel
to circumvent the secure boot trust model. In the long run we'll want to
support signed kexec payloads, but for the moment we should just disable
loading entirely in that situation.

Signed-off-by: Matthew Garrett <mjg@redhat.com>
---
 kernel/kexec.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/kexec.c b/kernel/kexec.c
index 4e2e472..35051f9 100644
--- a/kernel/kexec.c
+++ b/kernel/kexec.c
@@ -944,7 +944,7 @@ SYSCALL_DEFINE4(kexec_load, unsigned long, entry, unsigned long, nr_segments,
 	int result;
 
 	/* We only trust the superuser with rebooting the system. */
-	if (!capable(CAP_SYS_BOOT))
+	if (!capable(CAP_SYS_BOOT) || !capable(CAP_SECURE_FIRMWARE))
 		return -EPERM;
 
 	/*
-- 
1.7.11.2


From 82fe599f1192ba0bae968a8e05d8cddbbadd57bc Mon Sep 17 00:00:00 2001
From: Josh Boyer <jwboyer@redhat.com>
Date: Mon, 25 Jun 2012 19:45:15 -0400
Subject: [PATCH 09/14] Secure boot: Add a dummy kernel parameter that will
 switch on Secure Boot mode

This forcibly drops CAP_SECURE_FIRMWARE from both cap_permitted and cap_bset
in the init_cred struct, which everything else inherits from.  This works on
any machine and can be used to develop even if the box doesn't have UEFI.

Signed-off-by: Josh Boyer <jwboyer@redhat.com>
---
 kernel/cred.c | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

diff --git a/kernel/cred.c b/kernel/cred.c
index de728ac..0d71d02 100644
--- a/kernel/cred.c
+++ b/kernel/cred.c
@@ -623,6 +623,20 @@ void __init cred_init(void)
 				     0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL);
 }
 
+/* Dummy Secure Boot enable option to fake out UEFI SB=1 */
+static int __init secureboot_enable(char *str)
+{
+
+	int sb_enable = !!simple_strtol(str, NULL, 0);
+	pr_info("Secure Boot mode %s\n", (sb_enable ? "enabled" : "disabled"));
+	if (sb_enable) {
+		cap_lower((&init_cred)->cap_bset, CAP_SECURE_FIRMWARE);
+		cap_lower((&init_cred)->cap_permitted, CAP_SECURE_FIRMWARE);
+	}
+	return 1;
+}
+__setup("secureboot_enable=", secureboot_enable);
+
 /**
  * prepare_kernel_cred - Prepare a set of credentials for a kernel service
  * @daemon: A userspace daemon to be used as a reference
-- 
1.7.11.2


From 5aa21bbaad50af58a54cc339f6ab7bf5c163d64f Mon Sep 17 00:00:00 2001
From: Matthew Garrett <mjg@redhat.com>
Date: Wed, 18 Jul 2012 11:28:00 -0400
Subject: [PATCH 10/14] efi: Enable secure boot lockdown automatically when
 enabled in firmware

The firmware has a set of flags that indicate whether secure boot is enabled
and enforcing. Use them to indicate whether the kernel should lock itself
down.

Signed-off-by: Matthew Garrett <mjg@redhat.com>
---
 arch/x86/boot/compressed/eboot.c | 32 ++++++++++++++++++++++++++++++++
 arch/x86/include/asm/bootparam.h |  3 ++-
 arch/x86/kernel/setup.c          |  3 +++
 include/linux/cred.h             |  2 ++
 kernel/cred.c                    | 18 +++++++++++-------
 5 files changed, 50 insertions(+), 8 deletions(-)

diff --git a/arch/x86/boot/compressed/eboot.c b/arch/x86/boot/compressed/eboot.c
index b3e0227..3789356 100644
--- a/arch/x86/boot/compressed/eboot.c
+++ b/arch/x86/boot/compressed/eboot.c
@@ -724,6 +724,36 @@ fail:
 	return status;
 }
 
+static int get_secure_boot(efi_system_table_t *_table)
+{
+	u8 sb, setup;
+	unsigned long datasize = sizeof(sb);
+	efi_guid_t var_guid = EFI_GLOBAL_VARIABLE_GUID;
+	efi_status_t status;
+
+	status = efi_call_phys5(sys_table->runtime->get_variable,
+				L"SecureBoot", &var_guid, NULL, &datasize, &sb);
+
+	if (status != EFI_SUCCESS)
+		return 0;
+
+	if (sb == 0)
+		return 0;
+
+
+	status = efi_call_phys5(sys_table->runtime->get_variable,
+				L"SetupMode", &var_guid, NULL, &datasize,
+				&setup);
+
+	if (status != EFI_SUCCESS)
+		return 0;
+
+	if (setup == 1)
+		return 0;
+
+	return 1;
+}
+
 /*
  * Because the x86 boot code expects to be passed a boot_params we
  * need to create one ourselves (usually the bootloader would create
@@ -1018,6 +1048,8 @@ struct boot_params *efi_main(void *handle, efi_system_table_t *_table,
 	if (sys_table->hdr.signature != EFI_SYSTEM_TABLE_SIGNATURE)
 		goto fail;
 
+	boot_params->secure_boot = get_secure_boot(sys_table);
+
 	setup_graphics(boot_params);
 
 	status = efi_call_phys3(sys_table->boottime->allocate_pool,
diff --git a/arch/x86/include/asm/bootparam.h b/arch/x86/include/asm/bootparam.h
index 2ad874c..c7338e0 100644
--- a/arch/x86/include/asm/bootparam.h
+++ b/arch/x86/include/asm/bootparam.h
@@ -114,7 +114,8 @@ struct boot_params {
 	__u8  eddbuf_entries;				/* 0x1e9 */
 	__u8  edd_mbr_sig_buf_entries;			/* 0x1ea */
 	__u8  kbd_status;				/* 0x1eb */
-	__u8  _pad6[5];					/* 0x1ec */
+	__u8  secure_boot;				/* 0x1ec */
+	__u8  _pad6[4];					/* 0x1ed */
 	struct setup_header hdr;    /* setup header */	/* 0x1f1 */
 	__u8  _pad7[0x290-0x1f1-sizeof(struct setup_header)];
 	__u32 edd_mbr_sig_buffer[EDD_MBR_SIG_MAX];	/* 0x290 */
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index f4b9b80..239bf2a 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -947,6 +947,9 @@ void __init setup_arch(char **cmdline_p)
 
 	io_delay_init();
 
+	if (boot_params.secure_boot)
+		secureboot_enable();
+
 	/*
 	 * Parse the ACPI tables for possible boot-time SMP configuration.
 	 */
diff --git a/include/linux/cred.h b/include/linux/cred.h
index ebbed2c..a24faf1 100644
--- a/include/linux/cred.h
+++ b/include/linux/cred.h
@@ -170,6 +170,8 @@ extern int set_security_override_from_ctx(struct cred *, const char *);
 extern int set_create_files_as(struct cred *, struct inode *);
 extern void __init cred_init(void);
 
+extern void secureboot_enable(void);
+
 /*
  * check for validity of credentials
  */
diff --git a/kernel/cred.c b/kernel/cred.c
index 0d71d02..c43e2b0 100644
--- a/kernel/cred.c
+++ b/kernel/cred.c
@@ -623,19 +623,23 @@ void __init cred_init(void)
 				     0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL);
 }
 
+void __init secureboot_enable()
+{
+	pr_info("Secure boot enabled\n");
+	cap_lower((&init_cred)->cap_bset, CAP_SECURE_FIRMWARE);
+	cap_lower((&init_cred)->cap_permitted, CAP_SECURE_FIRMWARE);
+}
+
 /* Dummy Secure Boot enable option to fake out UEFI SB=1 */
-static int __init secureboot_enable(char *str)
+static int __init secureboot_enable_opt(char *str)
 {
 
 	int sb_enable = !!simple_strtol(str, NULL, 0);
-	pr_info("Secure Boot mode %s\n", (sb_enable ? "enabled" : "disabled"));
-	if (sb_enable) {
-		cap_lower((&init_cred)->cap_bset, CAP_SECURE_FIRMWARE);
-		cap_lower((&init_cred)->cap_permitted, CAP_SECURE_FIRMWARE);
-	}
+	if (sb_enable)
+		secureboot_enable();
 	return 1;
 }
-__setup("secureboot_enable=", secureboot_enable);
+__setup("secureboot_enable=", secureboot_enable_opt);
 
 /**
  * prepare_kernel_cred - Prepare a set of credentials for a kernel service
-- 
1.7.11.2


From 7b875c254033d29fa05b0c026b8097f8e5e1b96c Mon Sep 17 00:00:00 2001
From: Josh Boyer <jwboyer@redhat.com>
Date: Mon, 25 Jun 2012 19:57:30 -0400
Subject: [PATCH 11/14] acpi: Ignore acpi_rsdp kernel parameter in a secure
 boot environment

This option allows userspace to pass the RSDP address to the kernel.  This
could potentially be used to circumvent the secure boot trust model.
We ignore the setting if we don't have the CAP_SECURE_FIRMWARE capability.

Signed-off-by: Josh Boyer <jwboyer@redhat.com>
---
 drivers/acpi/osl.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/acpi/osl.c b/drivers/acpi/osl.c
index c3881b2..fb84388 100644
--- a/drivers/acpi/osl.c
+++ b/drivers/acpi/osl.c
@@ -246,7 +246,7 @@ early_param("acpi_rsdp", setup_acpi_rsdp);
 acpi_physical_address __init acpi_os_get_root_pointer(void)
 {
 #ifdef CONFIG_KEXEC
-	if (acpi_rsdp)
+	if (acpi_rsdp && capable(CAP_SECURE_FIRMWARE))
 		return acpi_rsdp;
 #endif
 
-- 
1.7.11.2


From 5ba183ef3e556bf11bbe73abd2cba50dc097881d Mon Sep 17 00:00:00 2001
From: Josh Boyer <jwboyer@redhat.com>
Date: Mon, 25 Jun 2012 21:29:46 -0400
Subject: [PATCH 12/14] Documentation: kernel-parameters.txt remove
 capability.disable

Remove the documentation for capability.disable.  The code supporting this
parameter was removed with:

	commit 5915eb53861c5776cfec33ca4fcc1fd20d66dd27
	Author: Miklos Szeredi <mszeredi@suse.cz>
	Date:   Thu Jul 3 20:56:05 2008 +0200

    	security: remove dummy module

Signed-off-by: Josh Boyer <jwboyer@redhat.com>
---
 Documentation/kernel-parameters.txt | 6 ------
 1 file changed, 6 deletions(-)

diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index 12783fa..cec4bf2 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -446,12 +446,6 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			possible to determine what the correct size should be.
 			This option provides an override for these situations.
 
-	capability.disable=
-			[SECURITY] Disable capabilities.  This would normally
-			be used only if an alternative security model is to be
-			configured.  Potentially dangerous and should only be
-			used if you are entirely sure of the consequences.
-
 	ccw_timeout_log [S390]
 			See Documentation/s390/CommonIO for details.
 
-- 
1.7.11.2


From 220f3a8cc351d220156e4903bf03c28ab44db6e3 Mon Sep 17 00:00:00 2001
From: Josh Boyer <jwboyer@redhat.com>
Date: Tue, 26 Jun 2012 14:15:51 -0400
Subject: [PATCH 13/14] SELinux: define mapping for new Secure Boot capability

Add the name of the new Secure Boot capability.  This allows SELinux
policies to properly map CAP_SECURE_FIRMWARE to the appropriate
capability class.

Signed-off-by: Josh Boyer <jwboyer@redhat.com>
---
 security/selinux/include/classmap.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/security/selinux/include/classmap.h b/security/selinux/include/classmap.h
index df2de54..0a1e348 100644
--- a/security/selinux/include/classmap.h
+++ b/security/selinux/include/classmap.h
@@ -146,8 +146,8 @@ struct security_class_mapping secclass_map[] = {
 	{ "memprotect", { "mmap_zero", NULL } },
 	{ "peer", { "recv", NULL } },
 	{ "capability2",
-	  { "mac_override", "mac_admin", "syslog", "wake_alarm", "block_suspend",
-	    NULL } },
+	  { "mac_override", "mac_admin", "syslog", "wake_alarm",
+	    "block_suspend", "secure_firmware", NULL } },
 	{ "kernel_service", { "use_as_override", "create_files_as", NULL } },
 	{ "tun_socket",
 	  { COMMON_SOCK_PERMS, NULL } },
-- 
1.7.11.2


From e5df15082c685dbf5c6917b891af73106342c0bb Mon Sep 17 00:00:00 2001
From: Josh Boyer <jwboyer@redhat.com>
Date: Tue, 26 Jun 2012 16:27:26 -0400
Subject: [PATCH 14/14] modsign: Reject unsigned modules in a Secure Boot
 environment

If a machine is booted into a Secure Boot environment, we need to
protect the trust model.  This requires that all modules be signed
with a key that is in the kernel's _modsign keyring.  We add a
capability check and reject modules that are not signed.

Signed-off-by: Josh Boyer <jwboyer@redhat.com>
---
 kernel/module-verify.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/kernel/module-verify.c b/kernel/module-verify.c
index b9c3955..f35532a 100644
--- a/kernel/module-verify.c
+++ b/kernel/module-verify.c
@@ -31,6 +31,7 @@
 #include <linux/modsign.h>
 #include <linux/moduleparam.h>
 #include <linux/fips.h>
+#include <linux/capability.h>
 #include <keys/crypto-type.h>
 #include "module-verify.h"
 #include "module-verify-defs.h"
@@ -699,7 +700,7 @@ int module_verify(const Elf_Ehdr *hdr, size_t size, bool *_gpgsig_ok)
 	/* The ELF checker found the sig for us if it exists */
 	if (mvdata.sig_index <= 0) {
 		/* Deal with an unsigned module */
-		if (modsign_signedonly) {
+		if (modsign_signedonly || !capable(CAP_SECURE_FIRMWARE)) {
 			pr_err("An attempt to load unsigned module was rejected\n");
 			return -EKEYREJECTED;
 		} else {
-- 
1.7.11.2