From 07ff2bbc3633a42ef5f0988b5bb821ed5d3399b9 Mon Sep 17 00:00:00 2001 From: David Howells Date: Mon, 18 Feb 2019 12:44:57 +0000 Subject: [PATCH 01/27] Add the ability to lock down access to the running kernel image Provide a single call to allow kernel code to determine whether the system should be locked down, thereby disallowing various accesses that might allow the running kernel image to be changed including the loading of modules that aren't validly signed with a key we recognise, fiddling with MSR registers and disallowing hibernation. Signed-off-by: David Howells Acked-by: James Morris Signed-off-by: Matthew Garrett --- include/linux/kernel.h | 17 ++++++++++++ include/linux/security.h | 9 +++++- security/Kconfig | 15 ++++++++++ security/Makefile | 3 ++ security/lock_down.c | 60 ++++++++++++++++++++++++++++++++++++++++ 5 files changed, 103 insertions(+), 1 deletion(-) create mode 100644 security/lock_down.c diff --git a/include/linux/kernel.h b/include/linux/kernel.h index 8f0e68e250a7..833bf32ce4e6 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -340,6 +340,23 @@ static inline void refcount_error_report(struct pt_regs *regs, const char *err) { } #endif +#ifdef CONFIG_LOCK_DOWN_KERNEL +extern bool __kernel_is_locked_down(const char *what, bool first); +#else +static inline bool __kernel_is_locked_down(const char *what, bool first) +{ + return false; +} +#endif + +#define kernel_is_locked_down(what) \ + ({ \ + static bool message_given; \ + bool locked_down = __kernel_is_locked_down(what, !message_given); \ + message_given = true; \ + locked_down; \ + }) + /* Internal, do not use. */ int __must_check _kstrtoul(const char *s, unsigned int base, unsigned long *res); int __must_check _kstrtol(const char *s, unsigned int base, long *res); diff --git a/include/linux/security.h b/include/linux/security.h index 13537a49ae97..b290946341a4 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -1798,5 +1798,12 @@ static inline void security_bpf_prog_free(struct bpf_prog_aux *aux) #endif /* CONFIG_SECURITY */ #endif /* CONFIG_BPF_SYSCALL */ -#endif /* ! __LINUX_SECURITY_H */ +#ifdef CONFIG_LOCK_DOWN_KERNEL +extern void __init init_lockdown(void); +#else +static inline void __init init_lockdown(void) +{ +} +#endif +#endif /* ! __LINUX_SECURITY_H */ diff --git a/security/Kconfig b/security/Kconfig index 1d6463fb1450..47dc3403b5af 100644 --- a/security/Kconfig +++ b/security/Kconfig @@ -229,6 +229,21 @@ config STATIC_USERMODEHELPER_PATH If you wish for all usermode helper programs to be disabled, specify an empty string here (i.e. ""). +config LOCK_DOWN_KERNEL + bool "Allow the kernel to be 'locked down'" + help + Allow the kernel to be locked down. If lockdown support is enabled + and activated, the kernel will impose additional restrictions + intended to prevent uid 0 from being able to modify the running + kernel. This may break userland applications that rely on low-level + access to hardware. + +config LOCK_DOWN_KERNEL_FORCE + bool "Enable kernel lockdown mode automatically" + depends on LOCK_DOWN_KERNEL + help + Enable the kernel lock down functionality automatically at boot. + source "security/selinux/Kconfig" source "security/smack/Kconfig" source "security/tomoyo/Kconfig" diff --git a/security/Makefile b/security/Makefile index c598b904938f..5ff090149c88 100644 --- a/security/Makefile +++ b/security/Makefile @@ -32,3 +32,6 @@ obj-$(CONFIG_CGROUP_DEVICE) += device_cgroup.o # Object integrity file lists subdir-$(CONFIG_INTEGRITY) += integrity obj-$(CONFIG_INTEGRITY) += integrity/ + +# Allow the kernel to be locked down +obj-$(CONFIG_LOCK_DOWN_KERNEL) += lock_down.o diff --git a/security/lock_down.c b/security/lock_down.c new file mode 100644 index 000000000000..18d8776a4d02 --- /dev/null +++ b/security/lock_down.c @@ -0,0 +1,60 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Lock down the kernel + * + * Copyright (C) 2016 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public Licence + * as published by the Free Software Foundation; either version + * 2 of the Licence, or (at your option) any later version. + */ + +#include +#include + +static __ro_after_init bool kernel_locked_down; + +/* + * Put the kernel into lock-down mode. + */ +static void __init lock_kernel_down(const char *where) +{ + if (!kernel_locked_down) { + kernel_locked_down = true; + pr_notice("Kernel is locked down from %s; see man kernel_lockdown.7\n", + where); + } +} + +static int __init lockdown_param(char *ignored) +{ + lock_kernel_down("command line"); + return 0; +} + +early_param("lockdown", lockdown_param); + +/* + * Lock the kernel down from very early in the arch setup. This must happen + * prior to things like ACPI being initialised. + */ +void __init init_lockdown(void) +{ +#ifdef CONFIG_LOCK_DOWN_FORCE + lock_kernel_down("Kernel configuration"); +#endif +} + +/** + * kernel_is_locked_down - Find out if the kernel is locked down + * @what: Tag to use in notice generated if lockdown is in effect + */ +bool __kernel_is_locked_down(const char *what, bool first) +{ + if (what && first && kernel_locked_down) + pr_notice("Lockdown: %s is restricted; see man kernel_lockdown.7\n", + what); + return kernel_locked_down; +} +EXPORT_SYMBOL(__kernel_is_locked_down); -- 2.21.0 From e5709852ca1e9ed443d9abebcb35cbc2f0d9d987 Mon Sep 17 00:00:00 2001 From: David Howells Date: Mon, 18 Feb 2019 12:44:58 +0000 Subject: [PATCH 02/27] Enforce module signatures if the kernel is locked down If the kernel is locked down, require that all modules have valid signatures that we can verify. I have adjusted the errors generated: (1) If there's no signature (ENODATA) or we can't check it (ENOPKG, ENOKEY), then: (a) If signatures are enforced then EKEYREJECTED is returned. (b) If there's no signature or we can't check it, but the kernel is locked down then EPERM is returned (this is then consistent with other lockdown cases). (2) If the signature is unparseable (EBADMSG, EINVAL), the signature fails the check (EKEYREJECTED) or a system error occurs (eg. ENOMEM), we return the error we got. Note that the X.509 code doesn't check for key expiry as the RTC might not be valid or might not have been transferred to the kernel's clock yet. [Modified by Matthew Garrett to remove the IMA integration. This will be replaced with integration with the IMA architecture policy patchset.] Signed-off-by: David Howells Reviewed-by: Jiri Bohac Signed-off-by: Matthew Garrett Cc: Jessica Yu --- kernel/module.c | 39 ++++++++++++++++++++++++++++++++------- 1 file changed, 32 insertions(+), 7 deletions(-) diff --git a/kernel/module.c b/kernel/module.c index 2ad1b5239910..9a377c6ea200 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -2767,8 +2767,9 @@ static inline void kmemleak_load_module(const struct module *mod, #ifdef CONFIG_MODULE_SIG static int module_sig_check(struct load_info *info, int flags) { - int err = -ENOKEY; + int err = -ENODATA; const unsigned long markerlen = sizeof(MODULE_SIG_STRING) - 1; + const char *reason; const void *mod = info->hdr; /* @@ -2783,16 +2784,40 @@ static int module_sig_check(struct load_info *info, int flags) err = mod_verify_sig(mod, info); } - if (!err) { + switch (err) { + case 0: info->sig_ok = true; return 0; - } - /* Not having a signature is only an error if we're strict. */ - if (err == -ENOKEY && !is_module_sig_enforced()) - err = 0; + /* We don't permit modules to be loaded into trusted kernels + * without a valid signature on them, but if we're not + * enforcing, certain errors are non-fatal. + */ + case -ENODATA: + reason = "Loading of unsigned module"; + goto decide; + case -ENOPKG: + reason = "Loading of module with unsupported crypto"; + goto decide; + case -ENOKEY: + reason = "Loading of module with unavailable key"; + decide: + if (is_module_sig_enforced()) { + pr_notice("%s is rejected\n", reason); + return -EKEYREJECTED; + } - return err; + if (kernel_is_locked_down(reason)) + return -EPERM; + return 0; + + /* All other errors are fatal, including nomem, unparseable + * signatures and signature check failures - even if signatures + * aren't required. + */ + default: + return err; + } } #else /* !CONFIG_MODULE_SIG */ static int module_sig_check(struct load_info *info, int flags) -- 2.21.0 From 4da16916fdf7dd6271bc6f16c0f9c32f430e7b42 Mon Sep 17 00:00:00 2001 From: Matthew Garrett Date: Mon, 18 Feb 2019 12:44:58 +0000 Subject: [PATCH 03/27] Restrict /dev/{mem,kmem,port} when the kernel is locked down Allowing users to read and write to core kernel memory makes it possible for the kernel to be subverted, avoiding module loading restrictions, and also to steal cryptographic information. Disallow /dev/mem and /dev/kmem from being opened this when the kernel has been locked down to prevent this. Also disallow /dev/port from being opened to prevent raw ioport access and thus DMA from being used to accomplish the same thing. Signed-off-by: Matthew Garrett Signed-off-by: David Howells Signed-off-by: Matthew Garrett Cc: x86@kernel.org --- drivers/char/mem.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/drivers/char/mem.c b/drivers/char/mem.c index b08dc50f9f26..0a2f2e75d5f4 100644 --- a/drivers/char/mem.c +++ b/drivers/char/mem.c @@ -786,6 +786,8 @@ static loff_t memory_lseek(struct file *file, loff_t offset, int orig) static int open_port(struct inode *inode, struct file *filp) { + if (kernel_is_locked_down("/dev/mem,kmem,port")) + return -EPERM; return capable(CAP_SYS_RAWIO) ? 0 : -EPERM; } -- 2.21.0 From e6802bece8b23dea57d5dfe72dc8383d0fa7f89c Mon Sep 17 00:00:00 2001 From: Matthew Garrett Date: Mon, 18 Feb 2019 12:44:58 +0000 Subject: [PATCH 04/27] kexec_load: Disable at runtime if the kernel is locked down The kexec_load() syscall permits the loading and execution of arbitrary code in ring 0, which is something that lock-down is meant to prevent. It makes sense to disable kexec_load() in this situation. This does not affect kexec_file_load() syscall which can check for a signature on the image to be booted. Signed-off-by: Matthew Garrett Signed-off-by: David Howells Acked-by: Dave Young cc: kexec@lists.infradead.org Signed-off-by: Matthew Garrett --- kernel/kexec.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/kernel/kexec.c b/kernel/kexec.c index 68559808fdfa..8ea0ce31271f 100644 --- a/kernel/kexec.c +++ b/kernel/kexec.c @@ -207,6 +207,13 @@ static inline int kexec_load_check(unsigned long nr_segments, if (result < 0) return result; + /* + * kexec can be used to circumvent module loading restrictions, so + * prevent loading in that case + */ + if (kernel_is_locked_down("kexec of unsigned images")) + return -EPERM; + /* * Verify we have a legal set of flags * This leaves us room for future extensions. -- 2.21.0 From 082fd91e5e574dff4063bc6062378ae581747c5a Mon Sep 17 00:00:00 2001 From: Dave Young Date: Mon, 18 Feb 2019 12:44:58 +0000 Subject: [PATCH 05/27] Copy secure_boot flag in boot params across kexec reboot Kexec reboot in case secure boot being enabled does not keep the secure boot mode in new kernel, so later one can load unsigned kernel via legacy kexec_load. In this state, the system is missing the protections provided by secure boot. Adding a patch to fix this by retain the secure_boot flag in original kernel. secure_boot flag in boot_params is set in EFI stub, but kexec bypasses the stub. Fixing this issue by copying secure_boot flag across kexec reboot. Signed-off-by: Dave Young Signed-off-by: David Howells cc: kexec@lists.infradead.org Signed-off-by: Matthew Garrett --- arch/x86/kernel/kexec-bzimage64.c | 1 + 1 file changed, 1 insertion(+) diff --git a/arch/x86/kernel/kexec-bzimage64.c b/arch/x86/kernel/kexec-bzimage64.c index 278cd07228dd..d49554b948fd 100644 --- a/arch/x86/kernel/kexec-bzimage64.c +++ b/arch/x86/kernel/kexec-bzimage64.c @@ -179,6 +179,7 @@ setup_efi_state(struct boot_params *params, unsigned long params_load_addr, if (efi_enabled(EFI_OLD_MEMMAP)) return 0; + params->secure_boot = boot_params.secure_boot; ei->efi_loader_signature = current_ei->efi_loader_signature; ei->efi_systab = current_ei->efi_systab; ei->efi_systab_hi = current_ei->efi_systab_hi; -- 2.21.0 From 4b84eb5e3c362deee572d47d12e8dd30d6ad1333 Mon Sep 17 00:00:00 2001 From: Jiri Bohac Date: Mon, 18 Feb 2019 12:44:58 +0000 Subject: [PATCH 06/27] kexec_file: split KEXEC_VERIFY_SIG into KEXEC_SIG and KEXEC_SIG_FORCE This is a preparatory patch for kexec_file_load() lockdown. A locked down kernel needs to prevent unsigned kernel images from being loaded with kexec_file_load(). Currently, the only way to force the signature verification is compiling with KEXEC_VERIFY_SIG. This prevents loading usigned images even when the kernel is not locked down at runtime. This patch splits KEXEC_VERIFY_SIG into KEXEC_SIG and KEXEC_SIG_FORCE. Analogous to the MODULE_SIG and MODULE_SIG_FORCE for modules, KEXEC_SIG turns on the signature verification but allows unsigned images to be loaded. KEXEC_SIG_FORCE disallows images without a valid signature. [Modified by David Howells such that: (1) verify_pefile_signature() differentiates between no-signature and sig-didn't-match in its returned errors. (2) kexec fails with EKEYREJECTED and logs an appropriate message if signature checking is enforced and an signature is not found, uses unsupported crypto or has no matching key. (3) kexec fails with EKEYREJECTED if there is a signature for which we have a key, but signature doesn't match - even if in non-forcing mode. (4) kexec fails with EBADMSG or some other error if there is a signature which cannot be parsed - even if in non-forcing mode. (5) kexec fails with ELIBBAD if the PE file cannot be parsed to extract the signature - even if in non-forcing mode. ] Signed-off-by: Jiri Bohac Signed-off-by: David Howells Reviewed-by: Jiri Bohac cc: kexec@lists.infradead.org Signed-off-by: Matthew Garrett --- arch/x86/Kconfig | 20 ++++++++--- crypto/asymmetric_keys/verify_pefile.c | 4 ++- include/linux/kexec.h | 4 +-- kernel/kexec_file.c | 48 ++++++++++++++++++++++---- 4 files changed, 61 insertions(+), 15 deletions(-) diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 4b4a7f32b68e..735d04a4b18f 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -2016,20 +2016,30 @@ config KEXEC_FILE config ARCH_HAS_KEXEC_PURGATORY def_bool KEXEC_FILE -config KEXEC_VERIFY_SIG +config KEXEC_SIG bool "Verify kernel signature during kexec_file_load() syscall" depends on KEXEC_FILE ---help--- - This option makes kernel signature verification mandatory for - the kexec_file_load() syscall. - In addition to that option, you need to enable signature + This option makes the kexec_file_load() syscall check for a valid + signature of the kernel image. The image can still be loaded without + a valid signature unless you also enable KEXEC_SIG_FORCE, though if + there's a signature that we can check, then it must be valid. + + In addition to this option, you need to enable signature verification for the corresponding kernel image type being loaded in order for this to work. +config KEXEC_SIG_FORCE + bool "Require a valid signature in kexec_file_load() syscall" + depends on KEXEC_SIG + ---help--- + This option makes kernel signature verification mandatory for + the kexec_file_load() syscall. + config KEXEC_BZIMAGE_VERIFY_SIG bool "Enable bzImage signature verification support" - depends on KEXEC_VERIFY_SIG + depends on KEXEC_SIG depends on SIGNED_PE_FILE_VERIFICATION select SYSTEM_TRUSTED_KEYRING ---help--- diff --git a/crypto/asymmetric_keys/verify_pefile.c b/crypto/asymmetric_keys/verify_pefile.c index d178650fd524..4473cea1e877 100644 --- a/crypto/asymmetric_keys/verify_pefile.c +++ b/crypto/asymmetric_keys/verify_pefile.c @@ -100,7 +100,7 @@ static int pefile_parse_binary(const void *pebuf, unsigned int pelen, if (!ddir->certs.virtual_address || !ddir->certs.size) { pr_debug("Unsigned PE binary\n"); - return -EKEYREJECTED; + return -ENODATA; } chkaddr(ctx->header_size, ddir->certs.virtual_address, @@ -408,6 +408,8 @@ static int pefile_digest_pe(const void *pebuf, unsigned int pelen, * (*) 0 if at least one signature chain intersects with the keys in the trust * keyring, or: * + * (*) -ENODATA if there is no signature present. + * * (*) -ENOPKG if a suitable crypto module couldn't be found for a check on a * chain. * diff --git a/include/linux/kexec.h b/include/linux/kexec.h index b9b1bc5f9669..58b27c7bdc2b 100644 --- a/include/linux/kexec.h +++ b/include/linux/kexec.h @@ -125,7 +125,7 @@ typedef void *(kexec_load_t)(struct kimage *image, char *kernel_buf, unsigned long cmdline_len); typedef int (kexec_cleanup_t)(void *loader_data); -#ifdef CONFIG_KEXEC_VERIFY_SIG +#ifdef CONFIG_KEXEC_SIG typedef int (kexec_verify_sig_t)(const char *kernel_buf, unsigned long kernel_len); #endif @@ -134,7 +134,7 @@ struct kexec_file_ops { kexec_probe_t *probe; kexec_load_t *load; kexec_cleanup_t *cleanup; -#ifdef CONFIG_KEXEC_VERIFY_SIG +#ifdef CONFIG_KEXEC_SIG kexec_verify_sig_t *verify_sig; #endif }; diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c index f1d0e00a3971..67f3a866eabe 100644 --- a/kernel/kexec_file.c +++ b/kernel/kexec_file.c @@ -90,7 +90,7 @@ int __weak arch_kimage_file_post_load_cleanup(struct kimage *image) return kexec_image_post_load_cleanup_default(image); } -#ifdef CONFIG_KEXEC_VERIFY_SIG +#ifdef CONFIG_KEXEC_SIG static int kexec_image_verify_sig_default(struct kimage *image, void *buf, unsigned long buf_len) { @@ -188,7 +188,8 @@ kimage_file_prepare_segments(struct kimage *image, int kernel_fd, int initrd_fd, const char __user *cmdline_ptr, unsigned long cmdline_len, unsigned flags) { - int ret = 0; + const char *reason; + int ret; void *ldata; loff_t size; @@ -207,15 +208,48 @@ kimage_file_prepare_segments(struct kimage *image, int kernel_fd, int initrd_fd, if (ret) goto out; -#ifdef CONFIG_KEXEC_VERIFY_SIG +#ifdef CONFIG_KEXEC_SIG ret = arch_kexec_kernel_verify_sig(image, image->kernel_buf, image->kernel_buf_len); - if (ret) { - pr_debug("kernel signature verification failed.\n"); +#else + ret = -ENODATA; +#endif + + switch (ret) { + case 0: + break; + + /* Certain verification errors are non-fatal if we're not + * checking errors, provided we aren't mandating that there + * must be a valid signature. + */ + case -ENODATA: + reason = "kexec of unsigned image"; + goto decide; + case -ENOPKG: + reason = "kexec of image with unsupported crypto"; + goto decide; + case -ENOKEY: + reason = "kexec of image with unavailable key"; + decide: + if (IS_ENABLED(CONFIG_KEXEC_SIG_FORCE)) { + pr_notice("%s rejected\n", reason); + ret = -EKEYREJECTED; + goto out; + } + + ret = 0; + break; + + /* All other errors are fatal, including nomem, unparseable + * signatures and signature check failures - even if signatures + * aren't required. + */ + default: + pr_notice("kernel signature verification failed (%d).\n", ret); goto out; } - pr_debug("kernel signature verification successful.\n"); -#endif + /* It is possible that there no initramfs is being loaded */ if (!(flags & KEXEC_FILE_NO_INITRAMFS)) { ret = kernel_read_file_from_fd(initrd_fd, &image->initrd_buf, -- 2.21.0 From 854a15bda329f93a425d592cd10d06c3a0486e75 Mon Sep 17 00:00:00 2001 From: Jiri Bohac Date: Mon, 18 Feb 2019 12:44:58 +0000 Subject: [PATCH 07/27] kexec_file: Restrict at runtime if the kernel is locked down When KEXEC_SIG is not enabled, kernel should not load images through kexec_file systemcall if the kernel is locked down. [Modified by David Howells to fit with modifications to the previous patch and to return -EPERM if the kernel is locked down for consistency with other lockdowns. Modified by Matthew Garrett to remove the IMA integration, which will be replaced by integrating with the IMA architecture policy patches.] Signed-off-by: Jiri Bohac Signed-off-by: David Howells Reviewed-by: Jiri Bohac cc: kexec@lists.infradead.org Signed-off-by: Matthew Garrett --- kernel/kexec_file.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c index 67f3a866eabe..0cfe4f6f7f85 100644 --- a/kernel/kexec_file.c +++ b/kernel/kexec_file.c @@ -239,6 +239,12 @@ kimage_file_prepare_segments(struct kimage *image, int kernel_fd, int initrd_fd, } ret = 0; + + if (kernel_is_locked_down(reason)) { + ret = -EPERM; + goto out; + } + break; /* All other errors are fatal, including nomem, unparseable -- 2.21.0 From 5077fcf70e31cb618274da06a8ef3b49aa92cda0 Mon Sep 17 00:00:00 2001 From: Josh Boyer Date: Mon, 18 Feb 2019 12:44:59 +0000 Subject: [PATCH 08/27] hibernate: Disable when the kernel is locked down There is currently no way to verify the resume image when returning from hibernate. This might compromise the signed modules trust model, so until we can work with signed hibernate images we disable it when the kernel is locked down. Signed-off-by: Josh Boyer Signed-off-by: David Howells Cc: rjw@rjwysocki.net Cc: pavel@ucw.cz cc: linux-pm@vger.kernel.org Signed-off-by: Matthew Garrett --- kernel/power/hibernate.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c index abef759de7c8..802795becb88 100644 --- a/kernel/power/hibernate.c +++ b/kernel/power/hibernate.c @@ -70,7 +70,7 @@ static const struct platform_hibernation_ops *hibernation_ops; bool hibernation_available(void) { - return (nohibernate == 0); + return nohibernate == 0 && !kernel_is_locked_down("Hibernation"); } /** -- 2.21.0 From 6687ec57697209008a846f94b8079dd3b8c5426d Mon Sep 17 00:00:00 2001 From: Matthew Garrett Date: Mon, 18 Feb 2019 12:44:59 +0000 Subject: [PATCH 09/27] uswsusp: Disable when the kernel is locked down uswsusp allows a user process to dump and then restore kernel state, which makes it possible to modify the running kernel. Disable this if the kernel is locked down. Signed-off-by: Matthew Garrett Signed-off-by: David Howells Reviewed-by: James Morris cc: linux-pm@vger.kernel.org Cc: pavel@ucw.cz Cc: rjw@rjwysocki.net Signed-off-by: Matthew Garrett --- kernel/power/user.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/kernel/power/user.c b/kernel/power/user.c index 2d8b60a3c86b..0305d513c274 100644 --- a/kernel/power/user.c +++ b/kernel/power/user.c @@ -52,6 +52,9 @@ static int snapshot_open(struct inode *inode, struct file *filp) if (!hibernation_available()) return -EPERM; + if (kernel_is_locked_down("/dev/snapshot")) + return -EPERM; + lock_system_sleep(); if (!atomic_add_unless(&snapshot_device_available, -1, 0)) { -- 2.21.0 From 074f89fba44418ebcf18e0ebbf1ed63fbc0b1d49 Mon Sep 17 00:00:00 2001 From: Matthew Garrett Date: Mon, 18 Feb 2019 12:44:59 +0000 Subject: [PATCH 10/27] PCI: Lock down BAR access when the kernel is locked down Any hardware that can potentially generate DMA has to be locked down in order to avoid it being possible for an attacker to modify kernel code, allowing them to circumvent disabled module loading or module signing. Default to paranoid - in future we can potentially relax this for sufficiently IOMMU-isolated devices. Signed-off-by: Matthew Garrett Signed-off-by: David Howells Acked-by: Bjorn Helgaas cc: linux-pci@vger.kernel.org Signed-off-by: Matthew Garrett --- drivers/pci/pci-sysfs.c | 9 +++++++++ drivers/pci/proc.c | 9 ++++++++- drivers/pci/syscall.c | 3 ++- 3 files changed, 19 insertions(+), 2 deletions(-) diff --git a/drivers/pci/pci-sysfs.c b/drivers/pci/pci-sysfs.c index 9ecfe13157c0..40c14574fcf8 100644 --- a/drivers/pci/pci-sysfs.c +++ b/drivers/pci/pci-sysfs.c @@ -905,6 +905,9 @@ static ssize_t pci_write_config(struct file *filp, struct kobject *kobj, loff_t init_off = off; u8 *data = (u8 *) buf; + if (kernel_is_locked_down("Direct PCI access")) + return -EPERM; + if (off > dev->cfg_size) return 0; if (off + count > dev->cfg_size) { @@ -1167,6 +1170,9 @@ static int pci_mmap_resource(struct kobject *kobj, struct bin_attribute *attr, enum pci_mmap_state mmap_type; struct resource *res = &pdev->resource[bar]; + if (kernel_is_locked_down("Direct PCI access")) + return -EPERM; + if (res->flags & IORESOURCE_MEM && iomem_is_exclusive(res->start)) return -EINVAL; @@ -1242,6 +1248,9 @@ static ssize_t pci_write_resource_io(struct file *filp, struct kobject *kobj, struct bin_attribute *attr, char *buf, loff_t off, size_t count) { + if (kernel_is_locked_down("Direct PCI access")) + 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 6fa1627ce08d..1549cdd0710e 100644 --- a/drivers/pci/proc.c +++ b/drivers/pci/proc.c @@ -117,6 +117,9 @@ static ssize_t proc_bus_pci_write(struct file *file, const char __user *buf, int size = dev->cfg_size; int cnt; + if (kernel_is_locked_down("Direct PCI access")) + return -EPERM; + if (pos >= size) return 0; if (nbytes >= size) @@ -196,6 +199,9 @@ static long proc_bus_pci_ioctl(struct file *file, unsigned int cmd, #endif /* HAVE_PCI_MMAP */ int ret = 0; + if (kernel_is_locked_down("Direct PCI access")) + return -EPERM; + switch (cmd) { case PCIIOC_CONTROLLER: ret = pci_domain_nr(dev->bus); @@ -237,7 +243,8 @@ 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, write_combine = 0, res_bit = IORESOURCE_MEM; - if (!capable(CAP_SYS_RAWIO)) + if (!capable(CAP_SYS_RAWIO) || + kernel_is_locked_down("Direct PCI access")) return -EPERM; if (fpriv->mmap_state == pci_mmap_io) { diff --git a/drivers/pci/syscall.c b/drivers/pci/syscall.c index d96626c614f5..b8a08d3166a1 100644 --- a/drivers/pci/syscall.c +++ b/drivers/pci/syscall.c @@ -90,7 +90,8 @@ 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) || + kernel_is_locked_down("Direct PCI access")) return -EPERM; dev = pci_get_domain_bus_and_slot(0, bus, dfn); -- 2.21.0 From 206cc8259d1da899524e42e506c5ea975a28082a Mon Sep 17 00:00:00 2001 From: Matthew Garrett Date: Mon, 18 Feb 2019 12:44:59 +0000 Subject: [PATCH 11/27] x86: Lock down IO port access when the kernel is locked down 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. This also implicitly locks down the KDADDIO, KDDELIO, KDENABIO and KDDISABIO console ioctls. Signed-off-by: Matthew Garrett Signed-off-by: David Howells Reviewed-by: Thomas Gleixner cc: x86@kernel.org Signed-off-by: Matthew Garrett --- arch/x86/kernel/ioport.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/arch/x86/kernel/ioport.c b/arch/x86/kernel/ioport.c index 0fe1c8782208..abc702a6ae9c 100644 --- a/arch/x86/kernel/ioport.c +++ b/arch/x86/kernel/ioport.c @@ -31,7 +31,8 @@ long ksys_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) || + kernel_is_locked_down("ioperm"))) return -EPERM; /* @@ -126,7 +127,8 @@ SYSCALL_DEFINE1(iopl, unsigned int, level) return -EINVAL; /* Trying to gain more privileges? */ if (level > old) { - if (!capable(CAP_SYS_RAWIO)) + if (!capable(CAP_SYS_RAWIO) || + kernel_is_locked_down("iopl")) return -EPERM; } regs->flags = (regs->flags & ~X86_EFLAGS_IOPL) | -- 2.21.0 From 8138905c5c6ff3c6a54913a41a658c17496de070 Mon Sep 17 00:00:00 2001 From: Matthew Garrett Date: Mon, 18 Feb 2019 12:44:59 +0000 Subject: [PATCH 12/27] x86/msr: Restrict MSR access when the kernel is locked down Writing to MSRs should not be allowed if the kernel is locked down, since it could lead to execution of arbitrary code in kernel mode. Based on a patch by Kees Cook. MSR accesses are logged for the purposes of building up a whitelist as per Alan Cox's suggestion. Signed-off-by: Matthew Garrett Signed-off-by: David Howells Acked-by: Kees Cook Reviewed-by: Thomas Gleixner cc: x86@kernel.org Signed-off-by: Matthew Garrett --- arch/x86/kernel/msr.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/arch/x86/kernel/msr.c b/arch/x86/kernel/msr.c index 4588414e2561..f5a2cf07972f 100644 --- a/arch/x86/kernel/msr.c +++ b/arch/x86/kernel/msr.c @@ -84,6 +84,11 @@ static ssize_t msr_write(struct file *file, const char __user *buf, int err = 0; ssize_t bytes = 0; + if (kernel_is_locked_down("Direct MSR access")) { + pr_info("Direct access to MSR %x\n", reg); + return -EPERM; + } + if (count % 8) return -EINVAL; /* Invalid chunk size */ @@ -135,6 +140,11 @@ static long msr_ioctl(struct file *file, unsigned int ioc, unsigned long arg) err = -EFAULT; break; } + if (kernel_is_locked_down("Direct MSR access")) { + pr_info("Direct access to MSR %x\n", regs[1]); /* Display %ecx */ + err = -EPERM; + break; + } err = wrmsr_safe_regs_on_cpu(cpu, regs); if (err) break; -- 2.21.0 From 8f7a5950f729e8eb182a260286155940d8cdfe40 Mon Sep 17 00:00:00 2001 From: Matthew Garrett Date: Mon, 18 Feb 2019 12:44:59 +0000 Subject: [PATCH 13/27] ACPI: Limit access to custom_method when the kernel is locked down custom_method effectively allows arbitrary access to system memory, making it possible for an attacker to circumvent restrictions on module loading. Disable it if the kernel is locked down. Signed-off-by: Matthew Garrett Signed-off-by: David Howells cc: linux-acpi@vger.kernel.org Signed-off-by: Matthew Garrett --- 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 4451877f83b6..ac8a90dc7096 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 (kernel_is_locked_down("ACPI custom methods")) + return -EPERM; + if (!(*ppos)) { /* parse the table header to get the table length */ if (count <= sizeof(struct acpi_table_header)) -- 2.21.0 From 72e33c3bf28a388e657955143c0cbea7afa2e522 Mon Sep 17 00:00:00 2001 From: Josh Boyer Date: Mon, 18 Feb 2019 12:44:59 +0000 Subject: [PATCH 14/27] acpi: Ignore acpi_rsdp kernel param when the kernel has been locked down This option allows userspace to pass the RSDP address to the kernel, which makes it possible for a user to modify the workings of hardware . Reject the option when the kernel is locked down. Signed-off-by: Josh Boyer Signed-off-by: David Howells cc: Dave Young cc: linux-acpi@vger.kernel.org Signed-off-by: Matthew Garrett --- 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 f29e427d0d1d..3e44cef7a0cd 100644 --- a/drivers/acpi/osl.c +++ b/drivers/acpi/osl.c @@ -194,7 +194,7 @@ acpi_physical_address __init acpi_os_get_root_pointer(void) acpi_physical_address pa; #ifdef CONFIG_KEXEC - if (acpi_rsdp) + if (acpi_rsdp && !kernel_is_locked_down("ACPI RSDP specification")) return acpi_rsdp; #endif pa = acpi_arch_get_root_pointer(); -- 2.21.0 From 6a23b59330d20f81b610a4f140bd29f54ceb577a Mon Sep 17 00:00:00 2001 From: Linn Crosetto Date: Mon, 18 Feb 2019 12:45:00 +0000 Subject: [PATCH 15/27] acpi: Disable ACPI table override if the kernel is locked down From the kernel documentation (initrd_table_override.txt): If the ACPI_INITRD_TABLE_OVERRIDE compile option is true, it is possible to override nearly any ACPI table provided by the BIOS with an instrumented, modified one. When securelevel is set, the kernel should disallow any unauthenticated changes to kernel space. ACPI tables contain code invoked by the kernel, so do not allow ACPI tables to be overridden if the kernel is locked down. Signed-off-by: Linn Crosetto Signed-off-by: David Howells cc: linux-acpi@vger.kernel.org Signed-off-by: Matthew Garrett --- drivers/acpi/tables.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/acpi/tables.c b/drivers/acpi/tables.c index 48eabb6c2d4f..f3b4117cd8f3 100644 --- a/drivers/acpi/tables.c +++ b/drivers/acpi/tables.c @@ -531,6 +531,11 @@ void __init acpi_table_upgrade(void) if (table_nr == 0) return; + if (kernel_is_locked_down("ACPI table override")) { + pr_notice("kernel is locked down, ignoring table override\n"); + return; + } + acpi_tables_addr = memblock_find_in_range(0, ACPI_TABLE_UPGRADE_MAX_PHYS, all_tables_size, PAGE_SIZE); -- 2.21.0 From 97f806b68d7286ec7026f802c22c5fb5a6311a45 Mon Sep 17 00:00:00 2001 From: Linn Crosetto Date: Mon, 18 Feb 2019 12:45:00 +0000 Subject: [PATCH 16/27] acpi: Disable APEI error injection if the kernel is locked down ACPI provides an error injection mechanism, EINJ, for debugging and testing the ACPI Platform Error Interface (APEI) and other RAS features. If supported by the firmware, ACPI specification 5.0 and later provide for a way to specify a physical memory address to which to inject the error. Injecting errors through EINJ can produce errors which to the platform are indistinguishable from real hardware errors. This can have undesirable side-effects, such as causing the platform to mark hardware as needing replacement. While it does not provide a method to load unauthenticated privileged code, the effect of these errors may persist across reboots and affect trust in the underlying hardware, so disable error injection through EINJ if the kernel is locked down. Signed-off-by: Linn Crosetto Signed-off-by: David Howells cc: linux-acpi@vger.kernel.org Signed-off-by: Matthew Garrett --- drivers/acpi/apei/einj.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/acpi/apei/einj.c b/drivers/acpi/apei/einj.c index fcccbfdbdd1a..9fe6bbab2e7d 100644 --- a/drivers/acpi/apei/einj.c +++ b/drivers/acpi/apei/einj.c @@ -518,6 +518,9 @@ static int einj_error_inject(u32 type, u32 flags, u64 param1, u64 param2, int rc; u64 base_addr, size; + if (kernel_is_locked_down("ACPI error injection")) + return -EPERM; + /* If user manually set "flags", make sure it is legal */ if (flags && (flags & ~(SETWA_FLAGS_APICID|SETWA_FLAGS_MEM|SETWA_FLAGS_PCIE_SBDF))) -- 2.21.0 From afc8d146b3f5a9a24338bd6588c55b6e70024f87 Mon Sep 17 00:00:00 2001 From: David Howells Date: Mon, 18 Feb 2019 12:45:00 +0000 Subject: [PATCH 17/27] Prohibit PCMCIA CIS storage when the kernel is locked down Prohibit replacement of the PCMCIA Card Information Structure when the kernel is locked down. Suggested-by: Dominik Brodowski Signed-off-by: David Howells cc: linux-pcmcia@lists.infradead.org Signed-off-by: Matthew Garrett --- drivers/pcmcia/cistpl.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/pcmcia/cistpl.c b/drivers/pcmcia/cistpl.c index ac0672b8dfca..8adf092d0e18 100644 --- a/drivers/pcmcia/cistpl.c +++ b/drivers/pcmcia/cistpl.c @@ -1578,6 +1578,9 @@ static ssize_t pccard_store_cis(struct file *filp, struct kobject *kobj, struct pcmcia_socket *s; int error; + if (kernel_is_locked_down("Direct PCMCIA CIS storage")) + return -EPERM; + s = to_socket(container_of(kobj, struct device, kobj)); if (off) -- 2.21.0 From ff1d4a9114a86373a24fe52b0b5a9503ad4fab1b Mon Sep 17 00:00:00 2001 From: David Howells Date: Mon, 18 Feb 2019 12:45:00 +0000 Subject: [PATCH 18/27] Lock down TIOCSSERIAL Lock down TIOCSSERIAL as that can be used to change the ioport and irq settings on a serial port. This only appears to be an issue for the serial drivers that use the core serial code. All other drivers seem to either ignore attempts to change port/irq or give an error. Reported-by: Greg Kroah-Hartman Signed-off-by: David Howells cc: Jiri Slaby Cc: linux-serial@vger.kernel.org Signed-off-by: Matthew Garrett --- drivers/tty/serial/serial_core.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c index d4cca5bdaf1c..04534877b575 100644 --- a/drivers/tty/serial/serial_core.c +++ b/drivers/tty/serial/serial_core.c @@ -842,6 +842,12 @@ static int uart_set_info(struct tty_struct *tty, struct tty_port *port, new_flags = (__force upf_t)new_info->flags; old_custom_divisor = uport->custom_divisor; + if ((change_port || change_irq) && + kernel_is_locked_down("Using TIOCSSERIAL to change device addresses, irqs and dma channels")) { + retval = -EPERM; + goto exit; + } + if (!capable(CAP_SYS_ADMIN)) { retval = -EPERM; if (change_irq || change_port || -- 2.21.0 From 2465b843e56020672d9704d3ab925a0399184e36 Mon Sep 17 00:00:00 2001 From: David Howells Date: Mon, 18 Feb 2019 12:45:01 +0000 Subject: [PATCH 19/27] Lock down module params that specify hardware parameters (eg. ioport) Provided an annotation for module parameters that specify hardware parameters (such as io ports, iomem addresses, irqs, dma channels, fixed dma buffers and other types). Suggested-by: Alan Cox Signed-off-by: David Howells Signed-off-by: Matthew Garrett --- kernel/params.c | 26 +++++++++++++++++++++----- 1 file changed, 21 insertions(+), 5 deletions(-) diff --git a/kernel/params.c b/kernel/params.c index ce89f757e6da..8ac751c938f8 100644 --- a/kernel/params.c +++ b/kernel/params.c @@ -108,13 +108,19 @@ bool parameq(const char *a, const char *b) return parameqn(a, b, strlen(a)+1); } -static void param_check_unsafe(const struct kernel_param *kp) +static bool param_check_unsafe(const struct kernel_param *kp, + const char *doing) { if (kp->flags & KERNEL_PARAM_FL_UNSAFE) { pr_notice("Setting dangerous option %s - tainting kernel\n", kp->name); add_taint(TAINT_USER, LOCKDEP_STILL_OK); } + + if (kp->flags & KERNEL_PARAM_FL_HWPARAM && + kernel_is_locked_down("Command line-specified device addresses, irqs and dma channels")) + return false; + return true; } static int parse_one(char *param, @@ -144,8 +150,10 @@ static int parse_one(char *param, pr_debug("handling %s with %p\n", param, params[i].ops->set); kernel_param_lock(params[i].mod); - param_check_unsafe(¶ms[i]); - err = params[i].ops->set(val, ¶ms[i]); + if (param_check_unsafe(¶ms[i], doing)) + err = params[i].ops->set(val, ¶ms[i]); + else + err = -EPERM; kernel_param_unlock(params[i].mod); return err; } @@ -553,6 +561,12 @@ static ssize_t param_attr_show(struct module_attribute *mattr, return count; } +#ifdef CONFIG_MODULES +#define mod_name(mod) (mod)->name +#else +#define mod_name(mod) "unknown" +#endif + /* sysfs always hands a nul-terminated string in buf. We rely on that. */ static ssize_t param_attr_store(struct module_attribute *mattr, struct module_kobject *mk, @@ -565,8 +579,10 @@ static ssize_t param_attr_store(struct module_attribute *mattr, return -EPERM; kernel_param_lock(mk->mod); - param_check_unsafe(attribute->param); - err = attribute->param->ops->set(buf, attribute->param); + if (param_check_unsafe(attribute->param, mod_name(mk->mod))) + err = attribute->param->ops->set(buf, attribute->param); + else + err = -EPERM; kernel_param_unlock(mk->mod); if (!err) return len; -- 2.21.0 From 7b4a19032dfd343a927c2fa4b1cd83a2d0c81bc0 Mon Sep 17 00:00:00 2001 From: David Howells Date: Mon, 18 Feb 2019 12:45:01 +0000 Subject: [PATCH 20/27] x86/mmiotrace: Lock down the testmmiotrace module The testmmiotrace module shouldn't be permitted when the kernel is locked down as it can be used to arbitrarily read and write MMIO space. Suggested-by: Thomas Gleixner Signed-off-by: David Howells cc: Steven Rostedt cc: Ingo Molnar cc: "H. Peter Anvin" cc: x86@kernel.org Signed-off-by: Matthew Garrett --- arch/x86/mm/testmmiotrace.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/arch/x86/mm/testmmiotrace.c b/arch/x86/mm/testmmiotrace.c index f6ae6830b341..bbaad357f5d7 100644 --- a/arch/x86/mm/testmmiotrace.c +++ b/arch/x86/mm/testmmiotrace.c @@ -115,6 +115,9 @@ static int __init init(void) { unsigned long size = (read_far) ? (8 << 20) : (16 << 10); + if (kernel_is_locked_down("MMIO trace testing")) + return -EPERM; + if (mmio_address == 0) { pr_err("you have to use the module argument mmio_address.\n"); pr_err("DO NOT LOAD THIS MODULE UNLESS YOU REALLY KNOW WHAT YOU ARE DOING!\n"); -- 2.21.0 From a7e2f1bfd9eda4cde25effdd7e663b68e31a36cf Mon Sep 17 00:00:00 2001 From: David Howells Date: Mon, 18 Feb 2019 12:45:02 +0000 Subject: [PATCH 21/27] Lock down /proc/kcore Disallow access to /proc/kcore when the kernel is locked down to prevent access to cryptographic data. Signed-off-by: David Howells Reviewed-by: James Morris Signed-off-by: Matthew Garrett --- fs/proc/kcore.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/fs/proc/kcore.c b/fs/proc/kcore.c index bbcc185062bb..d50ebfbf3dbb 100644 --- a/fs/proc/kcore.c +++ b/fs/proc/kcore.c @@ -518,6 +518,8 @@ read_kcore(struct file *file, char __user *buffer, size_t buflen, loff_t *fpos) static int open_kcore(struct inode *inode, struct file *filp) { + if (kernel_is_locked_down("/proc/kcore")) + return -EPERM; if (!capable(CAP_SYS_RAWIO)) return -EPERM; -- 2.21.0 From 0b8b0a68642ba0dedb57f7c734a7cc84d96cd30c Mon Sep 17 00:00:00 2001 From: David Howells Date: Mon, 18 Feb 2019 12:45:02 +0000 Subject: [PATCH 22/27] Lock down kprobes Disallow the creation of kprobes when the kernel is locked down by preventing their registration. This prevents kprobes from being used to access kernel memory, either to make modifications or to steal crypto data. Reported-by: Alexei Starovoitov Signed-off-by: David Howells Signed-off-by: Matthew Garrett Cc: Naveen N. Rao Cc: Anil S Keshavamurthy Cc: davem@davemloft.net Cc: Masami Hiramatsu --- kernel/kprobes.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/kernel/kprobes.c b/kernel/kprobes.c index f4ddfdd2d07e..6f66cca8e2c6 100644 --- a/kernel/kprobes.c +++ b/kernel/kprobes.c @@ -1552,6 +1552,9 @@ int register_kprobe(struct kprobe *p) struct module *probed_mod; kprobe_opcode_t *addr; + if (kernel_is_locked_down("Use of kprobes")) + return -EPERM; + /* Adjust probe address from symbol */ addr = kprobe_addr(p); if (IS_ERR(addr)) -- 2.21.0 From 2128009ce3291b0c4ced8672e68c6b57fc0202a8 Mon Sep 17 00:00:00 2001 From: David Howells Date: Mon, 18 Feb 2019 12:45:02 +0000 Subject: [PATCH 23/27] bpf: Restrict kernel image access functions when the kernel is locked down There are some bpf functions can be used to read kernel memory: bpf_probe_read, bpf_probe_write_user and bpf_trace_printk. These allow private keys in kernel memory (e.g. the hibernation image signing key) to be read by an eBPF program and kernel memory to be altered without restriction. Completely prohibit the use of BPF when the kernel is locked down. Suggested-by: Alexei Starovoitov Signed-off-by: David Howells cc: netdev@vger.kernel.org cc: Chun-Yi Lee cc: Alexei Starovoitov Cc: Daniel Borkmann Signed-off-by: Matthew Garrett --- kernel/bpf/syscall.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index b155cd17c1bd..2cde39a875aa 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -2585,6 +2585,9 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz if (sysctl_unprivileged_bpf_disabled && !capable(CAP_SYS_ADMIN)) return -EPERM; + if (kernel_is_locked_down("BPF")) + return -EPERM; + err = bpf_check_uarg_tail_zero(uattr, sizeof(attr), size); if (err) return err; -- 2.21.0 From 2fba6ffa91430a0c2a3177c6a5a0982deb966781 Mon Sep 17 00:00:00 2001 From: David Howells Date: Mon, 18 Feb 2019 12:45:02 +0000 Subject: [PATCH 24/27] Lock down perf Disallow the use of certain perf facilities that might allow userspace to access kernel data. Signed-off-by: David Howells Signed-off-by: Matthew Garrett Cc: Peter Zijlstra Cc: Ingo Molnar Cc: Arnaldo Carvalho de Melo --- kernel/events/core.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/kernel/events/core.c b/kernel/events/core.c index 3cd13a30f732..7748c6f39992 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -10461,6 +10461,11 @@ SYSCALL_DEFINE5(perf_event_open, return -EINVAL; } + if ((attr.sample_type & PERF_SAMPLE_REGS_INTR) && + kernel_is_locked_down("PERF_SAMPLE_REGS_INTR")) + /* REGS_INTR can leak data, lockdown must prevent this */ + return -EPERM; + /* Only privileged users can get physical addresses */ if ((attr.sample_type & PERF_SAMPLE_PHYS_ADDR) && perf_paranoid_kernel() && !capable(CAP_SYS_ADMIN)) -- 2.21.0 From 8972429a68131c4e1387978697d8cd3e3a51fce2 Mon Sep 17 00:00:00 2001 From: David Howells Date: Mon, 18 Feb 2019 12:45:02 +0000 Subject: [PATCH 25/27] debugfs: Restrict debugfs when the kernel is locked down Disallow opening of debugfs files that might be used to muck around when the kernel is locked down as various drivers give raw access to hardware through debugfs. Given the effort of auditing all 2000 or so files and manually fixing each one as necessary, I've chosen to apply a heuristic instead. The following changes are made: (1) chmod and chown are disallowed on debugfs objects (though the root dir can be modified by mount and remount, but I'm not worried about that). (2) When the kernel is locked down, only files with the following criteria are permitted to be opened: - The file must have mode 00444 - The file must not have ioctl methods - The file must not have mmap (3) When the kernel is locked down, files may only be opened for reading. Normal device interaction should be done through configfs, sysfs or a miscdev, not debugfs. Note that this makes it unnecessary to specifically lock down show_dsts(), show_devs() and show_call() in the asus-wmi driver. I would actually prefer to lock down all files by default and have the the files unlocked by the creator. This is tricky to manage correctly, though, as there are 19 creation functions and ~1600 call sites (some of them in loops scanning tables). Signed-off-by: David Howells cc: Andy Shevchenko cc: acpi4asus-user@lists.sourceforge.net cc: platform-driver-x86@vger.kernel.org cc: Matthew Garrett cc: Thomas Gleixner Cc: Greg Kroah-Hartman Signed-off-by: Matthew Garrett --- fs/debugfs/file.c | 28 ++++++++++++++++++++++++++++ fs/debugfs/inode.c | 30 ++++++++++++++++++++++++++++-- 2 files changed, 56 insertions(+), 2 deletions(-) diff --git a/fs/debugfs/file.c b/fs/debugfs/file.c index 4fce1da7db23..c33042c1eff3 100644 --- a/fs/debugfs/file.c +++ b/fs/debugfs/file.c @@ -136,6 +136,25 @@ void debugfs_file_put(struct dentry *dentry) } EXPORT_SYMBOL_GPL(debugfs_file_put); +/* + * Only permit access to world-readable files when the kernel is locked down. + * We also need to exclude any file that has ways to write or alter it as root + * can bypass the permissions check. + */ +static bool debugfs_is_locked_down(struct inode *inode, + struct file *filp, + const struct file_operations *real_fops) +{ + if ((inode->i_mode & 07777) == 0444 && + !(filp->f_mode & FMODE_WRITE) && + !real_fops->unlocked_ioctl && + !real_fops->compat_ioctl && + !real_fops->mmap) + return false; + + return kernel_is_locked_down("debugfs"); +} + static int open_proxy_open(struct inode *inode, struct file *filp) { struct dentry *dentry = F_DENTRY(filp); @@ -147,6 +166,11 @@ static int open_proxy_open(struct inode *inode, struct file *filp) return r == -EIO ? -ENOENT : r; real_fops = debugfs_real_fops(filp); + + r = -EPERM; + if (debugfs_is_locked_down(inode, filp, real_fops)) + goto out; + real_fops = fops_get(real_fops); if (!real_fops) { /* Huh? Module did not clean up after itself at exit? */ @@ -272,6 +296,10 @@ static int full_proxy_open(struct inode *inode, struct file *filp) return r == -EIO ? -ENOENT : r; real_fops = debugfs_real_fops(filp); + r = -EPERM; + if (debugfs_is_locked_down(inode, filp, real_fops)) + goto out; + real_fops = fops_get(real_fops); if (!real_fops) { /* Huh? Module did not cleanup after itself at exit? */ diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c index 13b01351dd1c..4daec17b8215 100644 --- a/fs/debugfs/inode.c +++ b/fs/debugfs/inode.c @@ -32,6 +32,31 @@ static struct vfsmount *debugfs_mount; static int debugfs_mount_count; static bool debugfs_registered; +/* + * Don't allow access attributes to be changed whilst the kernel is locked down + * so that we can use the file mode as part of a heuristic to determine whether + * to lock down individual files. + */ +static int debugfs_setattr(struct dentry *dentry, struct iattr *ia) +{ + if ((ia->ia_valid & (ATTR_MODE | ATTR_UID | ATTR_GID)) && + kernel_is_locked_down("debugfs")) + return -EPERM; + return simple_setattr(dentry, ia); +} + +static const struct inode_operations debugfs_file_inode_operations = { + .setattr = debugfs_setattr, +}; +static const struct inode_operations debugfs_dir_inode_operations = { + .lookup = simple_lookup, + .setattr = debugfs_setattr, +}; +static const struct inode_operations debugfs_symlink_inode_operations = { + .get_link = simple_get_link, + .setattr = debugfs_setattr, +}; + static struct inode *debugfs_get_inode(struct super_block *sb) { struct inode *inode = new_inode(sb); @@ -356,6 +381,7 @@ static struct dentry *__debugfs_create_file(const char *name, umode_t mode, inode->i_mode = mode; inode->i_private = data; + inode->i_op = &debugfs_file_inode_operations; inode->i_fop = proxy_fops; dentry->d_fsdata = (void *)((unsigned long)real_fops | DEBUGFS_FSDATA_IS_REAL_FOPS_BIT); @@ -513,7 +539,7 @@ struct dentry *debugfs_create_dir(const char *name, struct dentry *parent) return failed_creating(dentry); inode->i_mode = S_IFDIR | S_IRWXU | S_IRUGO | S_IXUGO; - inode->i_op = &simple_dir_inode_operations; + inode->i_op = &debugfs_dir_inode_operations; inode->i_fop = &simple_dir_operations; /* directory inodes start off with i_nlink == 2 (for "." entry) */ @@ -608,7 +634,7 @@ struct dentry *debugfs_create_symlink(const char *name, struct dentry *parent, return failed_creating(dentry); } inode->i_mode = S_IFLNK | S_IRWXUGO; - inode->i_op = &simple_symlink_inode_operations; + inode->i_op = &debugfs_symlink_inode_operations; inode->i_link = link; d_instantiate(dentry, inode); return end_creating(dentry); -- 2.21.0 From e9bf5c2e6f6cad9c992b5195af04d1f6500aa3ed Mon Sep 17 00:00:00 2001 From: David Howells Date: Wed, 28 Feb 2018 14:43:03 +0000 Subject: [PATCH 26/27] lockdown: Print current->comm in restriction messages Print the content of current->comm in messages generated by lockdown to indicate a restriction that was hit. This makes it a bit easier to find out what caused the message. The message now patterned something like: Lockdown: : is restricted; see man kernel_lockdown.7 Signed-off-by: David Howells Signed-off-by: Matthew Garrett --- security/lock_down.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/security/lock_down.c b/security/lock_down.c index 18d8776a4d02..ee00ca2677e7 100644 --- a/security/lock_down.c +++ b/security/lock_down.c @@ -53,8 +53,8 @@ void __init init_lockdown(void) bool __kernel_is_locked_down(const char *what, bool first) { if (what && first && kernel_locked_down) - pr_notice("Lockdown: %s is restricted; see man kernel_lockdown.7\n", - what); + pr_notice("Lockdown: %s: %s is restricted; see man kernel_lockdown.7\n", + current->comm, what); return kernel_locked_down; } EXPORT_SYMBOL(__kernel_is_locked_down); -- 2.21.0 From 1c57935ab108280aa79fe4420d4bc13e19bd38e2 Mon Sep 17 00:00:00 2001 From: Matthew Garrett Date: Tue, 12 Mar 2019 12:50:30 -0700 Subject: [PATCH 27/27] kexec: Allow kexec_file() with appropriate IMA policy when locked down Systems in lockdown mode should block the kexec of untrusted kernels. For x86 and ARM we can ensure that a kernel is trustworthy by validating a PE signature, but this isn't possible on other architectures. On those platforms we can use IMA digital signatures instead. Add a function to determine whether IMA has or will verify signatures for a given event type, and if so permit kexec_file() even if the kernel is otherwise locked down. This is restricted to cases where CONFIG_INTEGRITY_TRUSTED_KEYRING is set in order to prevent an attacker from loading additional keys at runtime. Signed-off-by: Matthew Garrett Cc: Mimi Zohar Cc: Dmitry Kasatkin Cc: linux-integrity@vger.kernel.org --- include/linux/ima.h | 9 ++++++ kernel/kexec_file.c | 7 +++- security/integrity/ima/ima.h | 2 ++ security/integrity/ima/ima_main.c | 2 +- security/integrity/ima/ima_policy.c | 50 +++++++++++++++++++++++++++++ 5 files changed, 68 insertions(+), 2 deletions(-) diff --git a/include/linux/ima.h b/include/linux/ima.h index b5e16b8c50b7..05921227d700 100644 --- a/include/linux/ima.h +++ b/include/linux/ima.h @@ -127,4 +127,13 @@ static inline int ima_inode_removexattr(struct dentry *dentry, return 0; } #endif /* CONFIG_IMA_APPRAISE */ + +#if defined(CONFIG_IMA_APPRAISE) && defined(CONFIG_INTEGRITY_TRUSTED_KEYRING) +extern bool ima_appraise_signature(enum kernel_read_file_id func); +#else +static inline bool ima_appraise_kexec_signature(enum kernel_read_file_id func) +{ + return false; +} +#endif /* CONFIG_IMA_APPRAISE && CONFIG_INTEGRITY_TRUSTED_KEYRING */ #endif /* _LINUX_IMA_H */ diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c index 0cfe4f6f7f85..8ffa4b75c620 100644 --- a/kernel/kexec_file.c +++ b/kernel/kexec_file.c @@ -240,7 +240,12 @@ kimage_file_prepare_segments(struct kimage *image, int kernel_fd, int initrd_fd, ret = 0; - if (kernel_is_locked_down(reason)) { + /* If IMA is guaranteed to appraise a signature on the kexec + * image, permit it even if the kernel is otherwise locked + * down. + */ + if (!ima_appraise_signature(READING_KEXEC_IMAGE) && + kernel_is_locked_down(reason)) { ret = -EPERM; goto out; } diff --git a/security/integrity/ima/ima.h b/security/integrity/ima/ima.h index cc12f3449a72..fe03cc6f1ca4 100644 --- a/security/integrity/ima/ima.h +++ b/security/integrity/ima/ima.h @@ -115,6 +115,8 @@ struct ima_kexec_hdr { u64 count; }; +extern const int read_idmap[]; + #ifdef CONFIG_HAVE_IMA_KEXEC void ima_load_kexec_buffer(void); #else diff --git a/security/integrity/ima/ima_main.c b/security/integrity/ima/ima_main.c index 4ffac4f5c647..106f06dee9d1 100644 --- a/security/integrity/ima/ima_main.c +++ b/security/integrity/ima/ima_main.c @@ -442,7 +442,7 @@ int ima_read_file(struct file *file, enum kernel_read_file_id read_id) return 0; } -static const int read_idmap[READING_MAX_ID] = { +const int read_idmap[READING_MAX_ID] = { [READING_FIRMWARE] = FIRMWARE_CHECK, [READING_FIRMWARE_PREALLOC_BUFFER] = FIRMWARE_CHECK, [READING_MODULE] = MODULE_CHECK, diff --git a/security/integrity/ima/ima_policy.c b/security/integrity/ima/ima_policy.c index 122797023bdb..f8f1cdb74a4f 100644 --- a/security/integrity/ima/ima_policy.c +++ b/security/integrity/ima/ima_policy.c @@ -1341,3 +1341,53 @@ int ima_policy_show(struct seq_file *m, void *v) return 0; } #endif /* CONFIG_IMA_READ_POLICY */ + +#if defined(CONFIG_IMA_APPRAISE) && defined(CONFIG_INTEGRITY_TRUSTED_KEYRING) +/* + * ima_appraise_signature: whether IMA will appraise a given function using + * an IMA digital signature. This is restricted to cases where the kernel + * has a set of built-in trusted keys in order to avoid an attacker simply + * loading additional keys. + */ +bool ima_appraise_signature(enum kernel_read_file_id id) +{ + struct ima_rule_entry *entry; + bool found = false; + enum ima_hooks func; + + if (id >= READING_MAX_ID) + return false; + + func = read_idmap[id] ?: FILE_CHECK; + + rcu_read_lock(); + list_for_each_entry_rcu(entry, ima_rules, list) { + if (entry->action != APPRAISE) + continue; + + /* + * A generic entry will match, but otherwise require that it + * match the func we're looking for + */ + if (entry->func && entry->func != func) + continue; + + /* + * We require this to be a digital signature, not a raw IMA + * hash. + */ + if (entry->flags & IMA_DIGSIG_REQUIRED) + found = true; + + /* + * We've found a rule that matches, so break now even if it + * didn't require a digital signature - a later rule that does + * won't override it, so would be a false positive. + */ + break; + } + + rcu_read_unlock(); + return found; +} +#endif /* CONFIG_IMA_APPRAISE && CONFIG_INTEGRITY_TRUSTED_KEYRING */ -- 2.21.0