diff options
Diffstat (limited to 'sys-kernel/linux-image-redcore-lts/files')
-rw-r--r-- | sys-kernel/linux-image-redcore-lts/files/5.10-ZEN-Add-sysctl-and-CONFIG-to-disallow-unprivileged-C.patch | 154 | ||||
-rw-r--r-- | sys-kernel/linux-image-redcore-lts/files/5.10-amd64.config | 21 | ||||
-rw-r--r-- | sys-kernel/linux-image-redcore-lts/files/5.10-linux-hardened.patch | 3479 | ||||
-rw-r--r-- | sys-kernel/linux-image-redcore-lts/files/5.10-uksm.patch (renamed from sys-kernel/linux-image-redcore-lts/files/5.10-uksm-linux-hardened.patch) | 232 |
4 files changed, 285 insertions, 3601 deletions
diff --git a/sys-kernel/linux-image-redcore-lts/files/5.10-ZEN-Add-sysctl-and-CONFIG-to-disallow-unprivileged-C.patch b/sys-kernel/linux-image-redcore-lts/files/5.10-ZEN-Add-sysctl-and-CONFIG-to-disallow-unprivileged-C.patch new file mode 100644 index 00000000..31a1d918 --- /dev/null +++ b/sys-kernel/linux-image-redcore-lts/files/5.10-ZEN-Add-sysctl-and-CONFIG-to-disallow-unprivileged-C.patch @@ -0,0 +1,154 @@ +From f615330c6169a5fe5750706f1db7cbdd520f9534 Mon Sep 17 00:00:00 2001 +From: "Jan Alexander Steffens (heftig)" <jan.steffens@gmail.com> +Date: Mon, 16 Sep 2019 04:53:20 +0200 +Subject: [PATCH 1/2] ZEN: Add sysctl and CONFIG to disallow unprivileged + CLONE_NEWUSER + +Our default behavior continues to match the vanilla kernel. +--- + include/linux/user_namespace.h | 4 ++++ + init/Kconfig | 16 ++++++++++++++++ + kernel/fork.c | 14 ++++++++++++++ + kernel/sysctl.c | 12 ++++++++++++ + kernel/user_namespace.c | 7 +++++++ + 5 files changed, 53 insertions(+) + +diff --git a/include/linux/user_namespace.h b/include/linux/user_namespace.h +index 6ef1c7109fc4..2140091b0b8d 100644 +--- a/include/linux/user_namespace.h ++++ b/include/linux/user_namespace.h +@@ -106,6 +106,8 @@ void dec_ucount(struct ucounts *ucounts, enum ucount_type type); + + #ifdef CONFIG_USER_NS + ++extern int unprivileged_userns_clone; ++ + static inline struct user_namespace *get_user_ns(struct user_namespace *ns) + { + if (ns) +@@ -139,6 +141,8 @@ extern bool current_in_userns(const struct user_namespace *target_ns); + struct ns_common *ns_get_owner(struct ns_common *ns); + #else + ++#define unprivileged_userns_clone 0 ++ + static inline struct user_namespace *get_user_ns(struct user_namespace *ns) + { + return &init_user_ns; +diff --git a/init/Kconfig b/init/Kconfig +index 0872a5a2e759..a40d8afeb1bb 100644 +--- a/init/Kconfig ++++ b/init/Kconfig +@@ -1173,6 +1173,22 @@ config USER_NS + + If unsure, say N. + ++config USER_NS_UNPRIVILEGED ++ bool "Allow unprivileged users to create namespaces" ++ default y ++ depends on USER_NS ++ help ++ When disabled, unprivileged users will not be able to create ++ new namespaces. Allowing users to create their own namespaces ++ has been part of several recent local privilege escalation ++ exploits, so if you need user namespaces but are ++ paranoid^Wsecurity-conscious you want to disable this. ++ ++ This setting can be overridden at runtime via the ++ kernel.unprivileged_userns_clone sysctl. ++ ++ If unsure, say Y. ++ + config PID_NS + bool "PID Namespaces" + default y +diff --git a/kernel/fork.c b/kernel/fork.c +index c675fdbd3dce..9266039e28e4 100644 +--- a/kernel/fork.c ++++ b/kernel/fork.c +@@ -97,6 +97,10 @@ + #include <linux/scs.h> + #include <linux/io_uring.h> + ++#ifdef CONFIG_USER_NS ++#include <linux/user_namespace.h> ++#endif ++ + #include <asm/pgalloc.h> + #include <linux/uaccess.h> + #include <asm/mmu_context.h> +@@ -1863,6 +1867,10 @@ static __latent_entropy struct task_struct *copy_process( + if ((clone_flags & (CLONE_NEWUSER|CLONE_FS)) == (CLONE_NEWUSER|CLONE_FS)) + return ERR_PTR(-EINVAL); + ++ if ((clone_flags & CLONE_NEWUSER) && !unprivileged_userns_clone) ++ if (!capable(CAP_SYS_ADMIN)) ++ return ERR_PTR(-EPERM); ++ + /* + * Thread groups must share signals as well, and detached threads + * can only be started up within the thread group. +@@ -2928,6 +2936,12 @@ int ksys_unshare(unsigned long unshare_flags) + if (unshare_flags & CLONE_NEWNS) + unshare_flags |= CLONE_FS; + ++ if ((unshare_flags & CLONE_NEWUSER) && !unprivileged_userns_clone) { ++ err = -EPERM; ++ if (!capable(CAP_SYS_ADMIN)) ++ goto bad_unshare_out; ++ } ++ + err = check_unshare_flags(unshare_flags); + if (err) + goto bad_unshare_out; +diff --git a/kernel/sysctl.c b/kernel/sysctl.c +index afad085960b8..a94828fb31c2 100644 +--- a/kernel/sysctl.c ++++ b/kernel/sysctl.c +@@ -103,6 +103,9 @@ + #ifdef CONFIG_LOCKUP_DETECTOR + #include <linux/nmi.h> + #endif ++#ifdef CONFIG_USER_NS ++#include <linux/user_namespace.h> ++#endif + + #if defined(CONFIG_SYSCTL) + +@@ -1902,6 +1905,15 @@ static struct ctl_table kern_table[] = { + .proc_handler = proc_dointvec, + }, + #endif ++#ifdef CONFIG_USER_NS ++ { ++ .procname = "unprivileged_userns_clone", ++ .data = &unprivileged_userns_clone, ++ .maxlen = sizeof(int), ++ .mode = 0644, ++ .proc_handler = proc_dointvec, ++ }, ++#endif + #ifdef CONFIG_PROC_SYSCTL + { + .procname = "tainted", +diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c +index e703d5d9cbe8..5758274feaee 100644 +--- a/kernel/user_namespace.c ++++ b/kernel/user_namespace.c +@@ -21,6 +21,13 @@ + #include <linux/bsearch.h> + #include <linux/sort.h> + ++/* sysctl */ ++#ifdef CONFIG_USER_NS_UNPRIVILEGED ++int unprivileged_userns_clone = 1; ++#else ++int unprivileged_userns_clone; ++#endif ++ + static struct kmem_cache *user_ns_cachep __read_mostly; + static DEFINE_MUTEX(userns_state_mutex); + +-- +2.31.1 + diff --git a/sys-kernel/linux-image-redcore-lts/files/5.10-amd64.config b/sys-kernel/linux-image-redcore-lts/files/5.10-amd64.config index 0d48c66c..f2fd796d 100644 --- a/sys-kernel/linux-image-redcore-lts/files/5.10-amd64.config +++ b/sys-kernel/linux-image-redcore-lts/files/5.10-amd64.config @@ -1,6 +1,6 @@ # # Automatically generated file; DO NOT EDIT. -# Linux/x86 5.10.47-redcore-lts Kernel Configuration +# Linux/x86 5.10.56-redcore-lts Kernel Configuration # CONFIG_CC_VERSION_TEXT="gcc (Gentoo Hardened 10.3.0-r10 p1) 10.3.0" CONFIG_CC_IS_GCC=y @@ -251,7 +251,6 @@ CONFIG_BPF_JIT_ALWAYS_ON=y CONFIG_BPF_JIT_DEFAULT_ON=y # CONFIG_BPF_PRELOAD is not set CONFIG_USERFAULTFD=y -# CONFIG_USERFAULTFD_UNPRIVILEGED is not set CONFIG_ARCH_HAS_MEMBARRIER_SYNC_CORE=y CONFIG_KCMP=y CONFIG_RSEQ=y @@ -806,9 +805,9 @@ CONFIG_MODULES_USE_ELF_RELA=y CONFIG_ARCH_HAS_ELF_RANDOMIZE=y CONFIG_HAVE_ARCH_MMAP_RND_BITS=y CONFIG_HAVE_EXIT_THREAD=y -CONFIG_ARCH_MMAP_RND_BITS=32 +CONFIG_ARCH_MMAP_RND_BITS=28 CONFIG_HAVE_ARCH_MMAP_RND_COMPAT_BITS=y -CONFIG_ARCH_MMAP_RND_COMPAT_BITS=16 +CONFIG_ARCH_MMAP_RND_COMPAT_BITS=8 CONFIG_HAVE_ARCH_COMPAT_MMAP_BASES=y CONFIG_HAVE_STACK_VALIDATION=y CONFIG_HAVE_RELIABLE_STACKTRACE=y @@ -1123,7 +1122,6 @@ CONFIG_TCP_CONG_BBR=m CONFIG_DEFAULT_RENO=y CONFIG_DEFAULT_TCP_CONG="reno" CONFIG_TCP_MD5SIG=y -# CONFIG_TCP_SIMULT_CONNECT_DEFAULT_ON is not set CONFIG_IPV6=m CONFIG_IPV6_ROUTER_PREF=y CONFIG_IPV6_ROUTE_INFO=y @@ -2246,7 +2244,6 @@ CONFIG_RFD_FTL=m CONFIG_SSFDC=m CONFIG_SM_FTL=m CONFIG_MTD_OOPS=m -CONFIG_MTD_PSTORE=m CONFIG_MTD_SWAP=m # CONFIG_MTD_PARTITIONED_MASTER is not set @@ -9102,7 +9099,6 @@ CONFIG_IPACK_BUS=m CONFIG_BOARD_TPCI200=m CONFIG_SERIAL_IPOCTAL=m CONFIG_RESET_CONTROLLER=y -# CONFIG_RESET_BRCMSTB_RESCAL is not set CONFIG_RESET_TI_SYSCON=m # @@ -9489,12 +9485,6 @@ CONFIG_PSTORE_COMPRESS_DEFAULT="zstd" CONFIG_PSTORE_PMSG=y # CONFIG_PSTORE_FTRACE is not set CONFIG_PSTORE_RAM=m -CONFIG_PSTORE_ZONE=m -CONFIG_PSTORE_BLK=m -CONFIG_PSTORE_BLK_BLKDEV="" -CONFIG_PSTORE_BLK_KMSG_SIZE=64 -CONFIG_PSTORE_BLK_MAX_REASON=2 -CONFIG_PSTORE_BLK_PMSG_SIZE=64 CONFIG_SYSV_FS=m CONFIG_UFS_FS=m # CONFIG_UFS_FS_WRITE is not set @@ -9642,8 +9632,6 @@ CONFIG_TRUSTED_KEYS=m CONFIG_ENCRYPTED_KEYS=m # CONFIG_KEY_DH_OPERATIONS is not set CONFIG_SECURITY_DMESG_RESTRICT=y -CONFIG_SECURITY_PERF_EVENTS_RESTRICT=y -CONFIG_SECURITY_TIOCSTI_RESTRICT=y CONFIG_SECURITY=y CONFIG_SECURITYFS=y CONFIG_SECURITY_NETWORK=y @@ -9688,8 +9676,6 @@ CONFIG_LSM="yama,loadpin,safesetid,integrity,apparmor" CONFIG_INIT_STACK_NONE=y # CONFIG_INIT_ON_ALLOC_DEFAULT_ON is not set # CONFIG_INIT_ON_FREE_DEFAULT_ON is not set -CONFIG_PAGE_SANITIZE_VERIFY=y -CONFIG_SLAB_SANITIZE_VERIFY=y # end of Memory initialization # end of Kernel hardening options # end of Security options @@ -10143,7 +10129,6 @@ CONFIG_STRIP_ASM_SYMS=y # CONFIG_HEADERS_INSTALL is not set # CONFIG_DEBUG_SECTION_MISMATCH is not set CONFIG_SECTION_MISMATCH_WARN_ONLY=y -# CONFIG_DEBUG_WRITABLE_FUNCTION_POINTERS_VERBOSE is not set CONFIG_STACK_VALIDATION=y # CONFIG_DEBUG_FORCE_WEAK_PER_CPU is not set # end of Compile-time checks and compiler options diff --git a/sys-kernel/linux-image-redcore-lts/files/5.10-linux-hardened.patch b/sys-kernel/linux-image-redcore-lts/files/5.10-linux-hardened.patch deleted file mode 100644 index e304e170..00000000 --- a/sys-kernel/linux-image-redcore-lts/files/5.10-linux-hardened.patch +++ /dev/null @@ -1,3479 +0,0 @@ -diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt -index 26bfe7ae711b..0e8e3fdd7005 100644 ---- a/Documentation/admin-guide/kernel-parameters.txt -+++ b/Documentation/admin-guide/kernel-parameters.txt -@@ -518,17 +518,6 @@ - nosocket -- Disable socket memory accounting. - nokmem -- Disable kernel memory accounting. - -- checkreqprot [SELINUX] Set initial checkreqprot flag value. -- Format: { "0" | "1" } -- See security/selinux/Kconfig help text. -- 0 -- check protection applied by kernel (includes -- any implied execute protection). -- 1 -- check protection requested by application. -- Default value is set via a kernel config option. -- Value can be changed at runtime via -- /sys/fs/selinux/checkreqprot. -- Setting checkreqprot to 1 is deprecated. -- - cio_ignore= [S390] - See Documentation/s390/common_io.rst for details. - clk_ignore_unused -@@ -3566,6 +3555,11 @@ - the specified number of seconds. This is to be used if - your oopses keep scrolling off the screen. - -+ extra_latent_entropy -+ Enable a very simple form of latent entropy extraction -+ from the first 4GB of memory as the bootmem allocator -+ passes the memory pages to the buddy allocator. -+ - pcbit= [HW,ISDN] - - pcd. [PARIDE] -diff --git a/Documentation/admin-guide/sysctl/kernel.rst b/Documentation/admin-guide/sysctl/kernel.rst -index d4b32cc32bb7..3cd263f8ac46 100644 ---- a/Documentation/admin-guide/sysctl/kernel.rst -+++ b/Documentation/admin-guide/sysctl/kernel.rst -@@ -860,6 +860,8 @@ with respect to CAP_PERFMON use cases. - >=1 Disallow CPU event access by users without ``CAP_PERFMON``. - - >=2 Disallow kernel profiling by users without ``CAP_PERFMON``. -+ -+>=3 Disallow use of any event by users without ``CAP_PERFMON``. - === ================================================================== - - -@@ -1383,6 +1385,26 @@ If a value outside of this range is written to ``threads-max`` an - ``EINVAL`` error occurs. - - -+tiocsti_restrict -+================ -+ -+This toggle indicates whether unprivileged users are prevented from using the -+``TIOCSTI`` ioctl to inject commands into other processes which share a tty -+session. -+ -+= ============================================================================ -+0 No restriction, except the default one of only being able to inject commands -+ into one's own tty. -+1 Users must have ``CAP_SYS_ADMIN`` to use the ``TIOCSTI`` ioctl. -+= ============================================================================ -+ -+When user namespaces are in use, the check for ``CAP_SYS_ADMIN`` is done -+against the user namespace that originally opened the tty. -+ -+The kernel config option ``CONFIG_SECURITY_TIOCSTI_RESTRICT`` sets the default -+value of ``tiocsti_restrict``. -+ -+ - traceoff_on_warning - =================== - -diff --git a/Documentation/networking/ip-sysctl.rst b/Documentation/networking/ip-sysctl.rst -index 4abcfff15e38..fa2d0a9709f2 100644 ---- a/Documentation/networking/ip-sysctl.rst -+++ b/Documentation/networking/ip-sysctl.rst -@@ -664,6 +664,24 @@ tcp_comp_sack_nr - INTEGER - - Default : 44 - -+tcp_simult_connect - BOOLEAN -+ Enable TCP simultaneous connect that adds a weakness in Linux's strict -+ implementation of TCP that allows two clients to connect to each other -+ without either entering a listening state. The weakness allows an attacker -+ to easily prevent a client from connecting to a known server provided the -+ source port for the connection is guessed correctly. -+ -+ As the weakness could be used to prevent an antivirus or IPS from fetching -+ updates, or prevent an SSL gateway from fetching a CRL, it should be -+ eliminated by disabling this option. Though Linux is one of few operating -+ systems supporting simultaneous connect, it has no legitimate use in -+ practice and is rarely supported by firewalls. -+ -+ Disabling this may break TCP STUNT which is used by some applications for -+ NAT traversal. -+ -+ Default: Value of CONFIG_TCP_SIMULT_CONNECT_DEFAULT_ON -+ - tcp_slow_start_after_idle - BOOLEAN - If set, provide RFC2861 behavior and time out the congestion - window after an idle period. An idle period is defined at -diff --git a/Makefile b/Makefile -index fb2937bca41b..711389d443ab 100644 ---- a/Makefile -+++ b/Makefile -@@ -2,7 +2,7 @@ - VERSION = 5 - PATCHLEVEL = 10 - SUBLEVEL = 47 --EXTRAVERSION = -+EXTRAVERSION = -hardened1 - NAME = Dare mighty things - - # *DOCUMENTATION* -diff --git a/arch/Kconfig b/arch/Kconfig -index 69fe7133c765..8b5c346d5dd8 100644 ---- a/arch/Kconfig -+++ b/arch/Kconfig -@@ -752,7 +752,7 @@ config ARCH_MMAP_RND_BITS - int "Number of bits to use for ASLR of mmap base address" if EXPERT - range ARCH_MMAP_RND_BITS_MIN ARCH_MMAP_RND_BITS_MAX - default ARCH_MMAP_RND_BITS_DEFAULT if ARCH_MMAP_RND_BITS_DEFAULT -- default ARCH_MMAP_RND_BITS_MIN -+ default ARCH_MMAP_RND_BITS_MAX - depends on HAVE_ARCH_MMAP_RND_BITS - help - This value can be used to select the number of bits to use to -@@ -786,7 +786,7 @@ config ARCH_MMAP_RND_COMPAT_BITS - int "Number of bits to use for ASLR of mmap base address for compatible applications" if EXPERT - range ARCH_MMAP_RND_COMPAT_BITS_MIN ARCH_MMAP_RND_COMPAT_BITS_MAX - default ARCH_MMAP_RND_COMPAT_BITS_DEFAULT if ARCH_MMAP_RND_COMPAT_BITS_DEFAULT -- default ARCH_MMAP_RND_COMPAT_BITS_MIN -+ default ARCH_MMAP_RND_COMPAT_BITS_MAX - depends on HAVE_ARCH_MMAP_RND_COMPAT_BITS - help - This value can be used to select the number of bits to use to -diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig -index 5e5cf3af6351..d13da5ae03e7 100644 ---- a/arch/arm64/Kconfig -+++ b/arch/arm64/Kconfig -@@ -1200,6 +1200,7 @@ config RODATA_FULL_DEFAULT_ENABLED - - config ARM64_SW_TTBR0_PAN - bool "Emulate Privileged Access Never using TTBR0_EL1 switching" -+ default y - help - Enabling this option prevents the kernel from accessing - user-space memory directly by pointing TTBR0_EL1 to a reserved -@@ -1794,6 +1795,7 @@ config RANDOMIZE_BASE - bool "Randomize the address of the kernel image" - select ARM64_MODULE_PLTS if MODULES - select RELOCATABLE -+ default y - help - Randomizes the virtual address at which the kernel image is - loaded, as a security feature that deters exploit attempts -diff --git a/arch/arm64/configs/defconfig b/arch/arm64/configs/defconfig -index 5cfe3cf6f2ac..f25871361bdc 100644 ---- a/arch/arm64/configs/defconfig -+++ b/arch/arm64/configs/defconfig -@@ -1,4 +1,3 @@ --CONFIG_SYSVIPC=y - CONFIG_POSIX_MQUEUE=y - CONFIG_AUDIT=y - CONFIG_NO_HZ_IDLE=y -diff --git a/arch/arm64/include/asm/elf.h b/arch/arm64/include/asm/elf.h -index 8d1c8dcb87fd..32c1609a1158 100644 ---- a/arch/arm64/include/asm/elf.h -+++ b/arch/arm64/include/asm/elf.h -@@ -124,14 +124,10 @@ - - /* - * This is the base location for PIE (ET_DYN with INTERP) loads. On -- * 64-bit, this is above 4GB to leave the entire 32-bit address -+ * 64-bit, this is raised to 4GB to leave the entire 32-bit address - * space open for things that want to use the area for 32-bit pointers. - */ --#ifdef CONFIG_ARM64_FORCE_52BIT --#define ELF_ET_DYN_BASE (2 * TASK_SIZE_64 / 3) --#else --#define ELF_ET_DYN_BASE (2 * DEFAULT_MAP_WINDOW_64 / 3) --#endif /* CONFIG_ARM64_FORCE_52BIT */ -+#define ELF_ET_DYN_BASE 0x100000000UL - - #ifndef __ASSEMBLY__ - -@@ -189,10 +185,10 @@ extern int arch_setup_additional_pages(struct linux_binprm *bprm, - /* 1GB of VA */ - #ifdef CONFIG_COMPAT - #define STACK_RND_MASK (test_thread_flag(TIF_32BIT) ? \ -- 0x7ff >> (PAGE_SHIFT - 12) : \ -- 0x3ffff >> (PAGE_SHIFT - 12)) -+ ((1UL << mmap_rnd_compat_bits) - 1) >> (PAGE_SHIFT - 12) : \ -+ ((1UL << mmap_rnd_bits) - 1) >> (PAGE_SHIFT - 12)) - #else --#define STACK_RND_MASK (0x3ffff >> (PAGE_SHIFT - 12)) -+#define STACK_RND_MASK (((1UL << mmap_rnd_bits) - 1) >> (PAGE_SHIFT - 12)) - #endif - - #ifdef __AARCH64EB__ -diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig -index f3c8a8110f60..372192b9ebd1 100644 ---- a/arch/x86/Kconfig -+++ b/arch/x86/Kconfig -@@ -1195,8 +1195,7 @@ config VM86 - default X86_LEGACY_VM86 - - config X86_16BIT -- bool "Enable support for 16-bit segments" if EXPERT -- default y -+ bool "Enable support for 16-bit segments" - depends on MODIFY_LDT_SYSCALL - help - This option is required by programs like Wine to run 16-bit -@@ -2298,7 +2297,7 @@ config COMPAT_VDSO - choice - prompt "vsyscall table for legacy applications" - depends on X86_64 -- default LEGACY_VSYSCALL_XONLY -+ default LEGACY_VSYSCALL_NONE - help - Legacy user code that does not know how to find the vDSO expects - to be able to issue three syscalls by calling fixed addresses in -@@ -2394,8 +2393,7 @@ config CMDLINE_OVERRIDE - be set to 'N' under normal conditions. - - config MODIFY_LDT_SYSCALL -- bool "Enable the LDT (local descriptor table)" if EXPERT -- default y -+ bool "Enable the LDT (local descriptor table)" - help - Linux can allow user programs to install a per-process x86 - Local Descriptor Table (LDT) using the modify_ldt(2) system -diff --git a/arch/x86/configs/x86_64_defconfig b/arch/x86/configs/x86_64_defconfig -index 9936528e1939..981ee8c0e330 100644 ---- a/arch/x86/configs/x86_64_defconfig -+++ b/arch/x86/configs/x86_64_defconfig -@@ -1,5 +1,4 @@ - # CONFIG_LOCALVERSION_AUTO is not set --CONFIG_SYSVIPC=y - CONFIG_POSIX_MQUEUE=y - CONFIG_AUDIT=y - CONFIG_NO_HZ=y -diff --git a/arch/x86/entry/vdso/vma.c b/arch/x86/entry/vdso/vma.c -index 9185cb1d13b9..543912071557 100644 ---- a/arch/x86/entry/vdso/vma.c -+++ b/arch/x86/entry/vdso/vma.c -@@ -315,55 +315,9 @@ static int map_vdso(const struct vdso_image *image, unsigned long addr) - } - - #ifdef CONFIG_X86_64 --/* -- * Put the vdso above the (randomized) stack with another randomized -- * offset. This way there is no hole in the middle of address space. -- * To save memory make sure it is still in the same PTE as the stack -- * top. This doesn't give that many random bits. -- * -- * Note that this algorithm is imperfect: the distribution of the vdso -- * start address within a PMD is biased toward the end. -- * -- * Only used for the 64-bit and x32 vdsos. -- */ --static unsigned long vdso_addr(unsigned long start, unsigned len) --{ -- unsigned long addr, end; -- unsigned offset; -- -- /* -- * Round up the start address. It can start out unaligned as a result -- * of stack start randomization. -- */ -- start = PAGE_ALIGN(start); -- -- /* Round the lowest possible end address up to a PMD boundary. */ -- end = (start + len + PMD_SIZE - 1) & PMD_MASK; -- if (end >= TASK_SIZE_MAX) -- end = TASK_SIZE_MAX; -- end -= len; -- -- if (end > start) { -- offset = get_random_int() % (((end - start) >> PAGE_SHIFT) + 1); -- addr = start + (offset << PAGE_SHIFT); -- } else { -- addr = start; -- } -- -- /* -- * Forcibly align the final address in case we have a hardware -- * issue that requires alignment for performance reasons. -- */ -- addr = align_vdso_addr(addr); -- -- return addr; --} -- - static int map_vdso_randomized(const struct vdso_image *image) - { -- unsigned long addr = vdso_addr(current->mm->start_stack, image->size-image->sym_vvar_start); -- -- return map_vdso(image, addr); -+ return map_vdso(image, 0); - } - #endif - -diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h -index b9a5d488f1a5..608cca19cf8c 100644 ---- a/arch/x86/include/asm/elf.h -+++ b/arch/x86/include/asm/elf.h -@@ -246,11 +246,11 @@ extern int force_personality32; - - /* - * This is the base location for PIE (ET_DYN with INTERP) loads. On -- * 64-bit, this is above 4GB to leave the entire 32-bit address -+ * 64-bit, this is raised to 4GB to leave the entire 32-bit address - * space open for things that want to use the area for 32-bit pointers. - */ - #define ELF_ET_DYN_BASE (mmap_is_ia32() ? 0x000400000UL : \ -- (DEFAULT_MAP_WINDOW / 3 * 2)) -+ 0x100000000UL) - - /* This yields a mask that user programs can use to figure out what - instruction set this CPU supports. This could be done in user space, -@@ -330,8 +330,8 @@ extern bool mmap_address_hint_valid(unsigned long addr, unsigned long len); - - #ifdef CONFIG_X86_32 - --#define __STACK_RND_MASK(is32bit) (0x7ff) --#define STACK_RND_MASK (0x7ff) -+#define __STACK_RND_MASK(is32bit) ((1UL << mmap_rnd_bits) - 1) -+#define STACK_RND_MASK ((1UL << mmap_rnd_bits) - 1) - - #define ARCH_DLINFO ARCH_DLINFO_IA32 - -@@ -340,7 +340,11 @@ extern bool mmap_address_hint_valid(unsigned long addr, unsigned long len); - #else /* CONFIG_X86_32 */ - - /* 1GB for 64bit, 8MB for 32bit */ --#define __STACK_RND_MASK(is32bit) ((is32bit) ? 0x7ff : 0x3fffff) -+#ifdef CONFIG_COMPAT -+#define __STACK_RND_MASK(is32bit) ((is32bit) ? (1UL << mmap_rnd_compat_bits) - 1 : (1UL << mmap_rnd_bits) - 1) -+#else -+#define __STACK_RND_MASK(is32bit) ((1UL << mmap_rnd_bits) - 1) -+#endif - #define STACK_RND_MASK __STACK_RND_MASK(mmap_is_ia32()) - - #define ARCH_DLINFO \ -@@ -398,5 +402,4 @@ struct va_alignment { - } ____cacheline_aligned; - - extern struct va_alignment va_align; --extern unsigned long align_vdso_addr(unsigned long); - #endif /* _ASM_X86_ELF_H */ -diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c -index 25148ebd3634..1a41d2c767a1 100644 ---- a/arch/x86/kernel/cpu/common.c -+++ b/arch/x86/kernel/cpu/common.c -@@ -399,6 +399,7 @@ EXPORT_SYMBOL_GPL(native_write_cr4); - void cr4_update_irqsoff(unsigned long set, unsigned long clear) - { - unsigned long newval, cr4 = this_cpu_read(cpu_tlbstate.cr4); -+ BUG_ON(cr4 != __read_cr4()); - - lockdep_assert_irqs_disabled(); - -diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c -index 145a7ac0c19a..161e25d02fd5 100644 ---- a/arch/x86/kernel/process.c -+++ b/arch/x86/kernel/process.c -@@ -43,6 +43,8 @@ - #include <asm/io_bitmap.h> - #include <asm/proto.h> - #include <asm/frame.h> -+#include <asm/elf.h> -+#include <linux/sizes.h> - - #include "process.h" - -@@ -596,6 +598,7 @@ void speculation_ctrl_update_current(void) - static inline void cr4_toggle_bits_irqsoff(unsigned long mask) - { - unsigned long newval, cr4 = this_cpu_read(cpu_tlbstate.cr4); -+ BUG_ON(cr4 != __read_cr4()); - - newval = cr4 ^ mask; - if (newval != cr4) { -@@ -905,7 +908,10 @@ unsigned long arch_align_stack(unsigned long sp) - - unsigned long arch_randomize_brk(struct mm_struct *mm) - { -- return randomize_page(mm->brk, 0x02000000); -+ if (mmap_is_ia32()) -+ return mm->brk + get_random_long() % SZ_32M + PAGE_SIZE; -+ else -+ return mm->brk + get_random_long() % SZ_1G + PAGE_SIZE; - } - - /* -diff --git a/arch/x86/kernel/sys_x86_64.c b/arch/x86/kernel/sys_x86_64.c -index 504fa5425bce..e30ec4c750d1 100644 ---- a/arch/x86/kernel/sys_x86_64.c -+++ b/arch/x86/kernel/sys_x86_64.c -@@ -52,13 +52,6 @@ static unsigned long get_align_bits(void) - return va_align.bits & get_align_mask(); - } - --unsigned long align_vdso_addr(unsigned long addr) --{ -- unsigned long align_mask = get_align_mask(); -- addr = (addr + align_mask) & ~align_mask; -- return addr | get_align_bits(); --} -- - static int __init control_va_addr_alignment(char *str) - { - /* guard against enabling this on other CPU families */ -@@ -120,10 +113,7 @@ static void find_start_end(unsigned long addr, unsigned long flags, - } - - *begin = get_mmap_base(1); -- if (in_32bit_syscall()) -- *end = task_size_32bit(); -- else -- *end = task_size_64bit(addr > DEFAULT_MAP_WINDOW); -+ *end = get_mmap_base(0); - } - - unsigned long -@@ -200,7 +190,7 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, - - info.flags = VM_UNMAPPED_AREA_TOPDOWN; - info.length = len; -- info.low_limit = PAGE_SIZE; -+ info.low_limit = get_mmap_base(1); - info.high_limit = get_mmap_base(0); - - /* -diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c -index 7c055259de3a..291b7b4476a9 100644 ---- a/arch/x86/mm/init_32.c -+++ b/arch/x86/mm/init_32.c -@@ -546,9 +546,9 @@ static void __init pagetable_init(void) - - #define DEFAULT_PTE_MASK ~(_PAGE_NX | _PAGE_GLOBAL) - /* Bits supported by the hardware: */ --pteval_t __supported_pte_mask __read_mostly = DEFAULT_PTE_MASK; -+pteval_t __supported_pte_mask __ro_after_init = DEFAULT_PTE_MASK; - /* Bits allowed in normal kernel mappings: */ --pteval_t __default_kernel_pte_mask __read_mostly = DEFAULT_PTE_MASK; -+pteval_t __default_kernel_pte_mask __ro_after_init = DEFAULT_PTE_MASK; - EXPORT_SYMBOL_GPL(__supported_pte_mask); - /* Used in PAGE_KERNEL_* macros which are reasonably used out-of-tree: */ - EXPORT_SYMBOL(__default_kernel_pte_mask); -diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c -index b5a3fa4033d3..c3d771ffc178 100644 ---- a/arch/x86/mm/init_64.c -+++ b/arch/x86/mm/init_64.c -@@ -97,9 +97,9 @@ DEFINE_ENTRY(pte, pte, init) - */ - - /* Bits supported by the hardware: */ --pteval_t __supported_pte_mask __read_mostly = ~0; -+pteval_t __supported_pte_mask __ro_after_init = ~0; - /* Bits allowed in normal kernel mappings: */ --pteval_t __default_kernel_pte_mask __read_mostly = ~0; -+pteval_t __default_kernel_pte_mask __ro_after_init = ~0; - EXPORT_SYMBOL_GPL(__supported_pte_mask); - /* Used in PAGE_KERNEL_* macros which are reasonably used out-of-tree: */ - EXPORT_SYMBOL(__default_kernel_pte_mask); -diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c -index 569ac1d57f55..044d88da4aee 100644 ---- a/arch/x86/mm/tlb.c -+++ b/arch/x86/mm/tlb.c -@@ -1066,6 +1066,7 @@ STATIC_NOPV void native_flush_tlb_global(void) - raw_local_irq_save(flags); - - cr4 = this_cpu_read(cpu_tlbstate.cr4); -+ BUG_ON(cr4 != __read_cr4()); - /* toggle PGE */ - native_write_cr4(cr4 ^ X86_CR4_PGE); - /* write old PGE again and flush TLBs */ -diff --git a/block/blk-mq.c b/block/blk-mq.c -index 4bf9449b4586..3215e9d0025c 100644 ---- a/block/blk-mq.c -+++ b/block/blk-mq.c -@@ -569,7 +569,7 @@ EXPORT_SYMBOL(blk_mq_end_request); - * Softirq action handler - move entries to local list and loop over them - * while passing them to the queue registered handler. - */ --static __latent_entropy void blk_done_softirq(struct softirq_action *h) -+static __latent_entropy void blk_done_softirq(void) - { - struct list_head *cpu_list, local_list; - -diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c -index 61c762961ca8..02a83039c25b 100644 ---- a/drivers/ata/libata-core.c -+++ b/drivers/ata/libata-core.c -@@ -4540,7 +4540,7 @@ void ata_qc_free(struct ata_queued_cmd *qc) - struct ata_port *ap; - unsigned int tag; - -- WARN_ON_ONCE(qc == NULL); /* ata_qc_from_tag _might_ return NULL */ -+ BUG_ON(qc == NULL); /* ata_qc_from_tag _might_ return NULL */ - ap = qc->ap; - - qc->flags = 0; -@@ -4557,7 +4557,7 @@ void __ata_qc_complete(struct ata_queued_cmd *qc) - struct ata_port *ap; - struct ata_link *link; - -- WARN_ON_ONCE(qc == NULL); /* ata_qc_from_tag _might_ return NULL */ -+ BUG_ON(qc == NULL); /* ata_qc_from_tag _might_ return NULL */ - WARN_ON_ONCE(!(qc->flags & ATA_QCFLAG_ACTIVE)); - ap = qc->ap; - link = qc->dev->link; -diff --git a/drivers/char/Kconfig b/drivers/char/Kconfig -index d229a2d0c017..2fd45f01e7a2 100644 ---- a/drivers/char/Kconfig -+++ b/drivers/char/Kconfig -@@ -327,7 +327,6 @@ config NSC_GPIO - - config DEVMEM - bool "/dev/mem virtual device support" -- default y - help - Say Y here if you want to support the /dev/mem device. - The /dev/mem device is used to access areas of physical -@@ -391,7 +390,6 @@ config MAX_RAW_DEVS - config DEVPORT - bool "/dev/port character device" - depends on ISA || PCI -- default y - help - Say Y here if you want to support the /dev/port device. The /dev/port - device is similar to /dev/mem, but for I/O ports. -diff --git a/drivers/tty/Kconfig b/drivers/tty/Kconfig -index 93fd984eb2f5..d9086484d2de 100644 ---- a/drivers/tty/Kconfig -+++ b/drivers/tty/Kconfig -@@ -122,7 +122,6 @@ config UNIX98_PTYS - - config LEGACY_PTYS - bool "Legacy (BSD) PTY support" -- default y - help - A pseudo terminal (PTY) is a software device consisting of two - halves: a master and a slave. The slave device behaves identical to -diff --git a/drivers/tty/tty_io.c b/drivers/tty/tty_io.c -index bc5314092aa4..4de9e74c701c 100644 ---- a/drivers/tty/tty_io.c -+++ b/drivers/tty/tty_io.c -@@ -171,6 +171,7 @@ static void free_tty_struct(struct tty_struct *tty) - put_device(tty->dev); - kfree(tty->write_buf); - tty->magic = 0xDEADDEAD; -+ put_user_ns(tty->owner_user_ns); - kfree(tty); - } - -@@ -2261,11 +2262,19 @@ static int tty_fasync(int fd, struct file *filp, int on) - * FIXME: may race normal receive processing - */ - -+int tiocsti_restrict = IS_ENABLED(CONFIG_SECURITY_TIOCSTI_RESTRICT); -+ - static int tiocsti(struct tty_struct *tty, char __user *p) - { - char ch, mbz = 0; - struct tty_ldisc *ld; - -+ if (tiocsti_restrict && -+ !ns_capable(tty->owner_user_ns, CAP_SYS_ADMIN)) { -+ dev_warn_ratelimited(tty->dev, -+ "Denied TIOCSTI ioctl for non-privileged process\n"); -+ return -EPERM; -+ } - if ((current->signal->tty != tty) && !capable(CAP_SYS_ADMIN)) - return -EPERM; - if (get_user(ch, p)) -@@ -3100,6 +3109,7 @@ struct tty_struct *alloc_tty_struct(struct tty_driver *driver, int idx) - tty->index = idx; - tty_line_name(driver, idx, tty->name); - tty->dev = tty_get_device(tty); -+ tty->owner_user_ns = get_user_ns(current_user_ns()); - - return tty; - } -diff --git a/drivers/usb/core/Makefile b/drivers/usb/core/Makefile -index 18e874b0441e..fc7a3a9aa72a 100644 ---- a/drivers/usb/core/Makefile -+++ b/drivers/usb/core/Makefile -@@ -11,6 +11,7 @@ usbcore-y += phy.o port.o - usbcore-$(CONFIG_OF) += of.o - usbcore-$(CONFIG_USB_PCI) += hcd-pci.o - usbcore-$(CONFIG_ACPI) += usb-acpi.o -+usbcore-$(CONFIG_SYSCTL) += sysctl.o - - obj-$(CONFIG_USB) += usbcore.o - -diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c -index 357730e8f52f..3884416d9029 100644 ---- a/drivers/usb/core/hub.c -+++ b/drivers/usb/core/hub.c -@@ -5116,6 +5116,12 @@ static void hub_port_connect(struct usb_hub *hub, int port1, u16 portstatus, - goto done; - return; - } -+ -+ if (deny_new_usb) { -+ dev_err(&port_dev->dev, "denied insert of USB device on port %d\n", port1); -+ goto done; -+ } -+ - if (hub_is_superspeed(hub->hdev)) - unit_load = 150; - else -diff --git a/drivers/usb/core/sysctl.c b/drivers/usb/core/sysctl.c -new file mode 100644 -index 000000000000..3fa188ac8f67 ---- /dev/null -+++ b/drivers/usb/core/sysctl.c -@@ -0,0 +1,44 @@ -+#include <linux/errno.h> -+#include <linux/init.h> -+#include <linux/kmemleak.h> -+#include <linux/sysctl.h> -+#include <linux/usb.h> -+ -+static struct ctl_table usb_table[] = { -+ { -+ .procname = "deny_new_usb", -+ .data = &deny_new_usb, -+ .maxlen = sizeof(int), -+ .mode = 0644, -+ .proc_handler = proc_dointvec_minmax_sysadmin, -+ .extra1 = SYSCTL_ZERO, -+ .extra2 = SYSCTL_ONE, -+ }, -+ { } -+}; -+ -+static struct ctl_table usb_root_table[] = { -+ { .procname = "kernel", -+ .mode = 0555, -+ .child = usb_table }, -+ { } -+}; -+ -+static struct ctl_table_header *usb_table_header; -+ -+int __init usb_init_sysctl(void) -+{ -+ usb_table_header = register_sysctl_table(usb_root_table); -+ if (!usb_table_header) { -+ pr_warn("usb: sysctl registration failed\n"); -+ return -ENOMEM; -+ } -+ -+ kmemleak_not_leak(usb_table_header); -+ return 0; -+} -+ -+void usb_exit_sysctl(void) -+{ -+ unregister_sysctl_table(usb_table_header); -+} -diff --git a/drivers/usb/core/usb.c b/drivers/usb/core/usb.c -index db4de5367737..28bdbd91e33c 100644 ---- a/drivers/usb/core/usb.c -+++ b/drivers/usb/core/usb.c -@@ -72,6 +72,9 @@ MODULE_PARM_DESC(autosuspend, "default autosuspend delay"); - #define usb_autosuspend_delay 0 - #endif - -+int deny_new_usb __read_mostly = 0; -+EXPORT_SYMBOL(deny_new_usb); -+ - static bool match_endpoint(struct usb_endpoint_descriptor *epd, - struct usb_endpoint_descriptor **bulk_in, - struct usb_endpoint_descriptor **bulk_out, -@@ -1010,6 +1013,9 @@ static int __init usb_init(void) - usb_debugfs_init(); - - usb_acpi_register(); -+ retval = usb_init_sysctl(); -+ if (retval) -+ goto sysctl_init_failed; - retval = bus_register(&usb_bus_type); - if (retval) - goto bus_register_failed; -@@ -1044,6 +1050,8 @@ static int __init usb_init(void) - bus_notifier_failed: - bus_unregister(&usb_bus_type); - bus_register_failed: -+ usb_exit_sysctl(); -+sysctl_init_failed: - usb_acpi_unregister(); - usb_debugfs_cleanup(); - out: -@@ -1067,6 +1075,7 @@ static void __exit usb_exit(void) - usb_hub_cleanup(); - bus_unregister_notifier(&usb_bus_type, &usb_bus_nb); - bus_unregister(&usb_bus_type); -+ usb_exit_sysctl(); - usb_acpi_unregister(); - usb_debugfs_cleanup(); - idr_destroy(&usb_bus_idr); -diff --git a/fs/exec.c b/fs/exec.c -index ca89e0e3ef10..d2a03d32e195 100644 ---- a/fs/exec.c -+++ b/fs/exec.c -@@ -34,6 +34,7 @@ - #include <linux/swap.h> - #include <linux/string.h> - #include <linux/init.h> -+#include <linux/sched.h> - #include <linux/sched/mm.h> - #include <linux/sched/coredump.h> - #include <linux/sched/signal.h> -@@ -64,6 +65,7 @@ - #include <linux/compat.h> - #include <linux/vmalloc.h> - #include <linux/io_uring.h> -+#include <linux/random.h> - - #include <linux/uaccess.h> - #include <asm/mmu_context.h> -@@ -280,6 +282,8 @@ static int __bprm_mm_init(struct linux_binprm *bprm) - mm->stack_vm = mm->total_vm = 1; - mmap_write_unlock(mm); - bprm->p = vma->vm_end - sizeof(void *); -+ if (!(current->personality & ADDR_NO_RANDOMIZE) && randomize_va_space) -+ bprm->p ^= get_random_int() & ~PAGE_MASK; - return 0; - err: - mmap_write_unlock(mm); -diff --git a/fs/inode.c b/fs/inode.c -index 5eea9912a0b9..f86f383a3e1d 100644 ---- a/fs/inode.c -+++ b/fs/inode.c -@@ -116,6 +116,10 @@ int proc_nr_inodes(struct ctl_table *table, int write, - } - #endif - -+/* sysctl */ -+int device_sidechannel_restrict __read_mostly = 1; -+EXPORT_SYMBOL(device_sidechannel_restrict); -+ - static int no_open(struct inode *inode, struct file *file) - { - return -ENXIO; -diff --git a/fs/namei.c b/fs/namei.c -index 4c9d0c36545d..e05f9512934a 100644 ---- a/fs/namei.c -+++ b/fs/namei.c -@@ -932,10 +932,10 @@ static inline void put_link(struct nameidata *nd) - path_put(&last->link); - } - --int sysctl_protected_symlinks __read_mostly = 0; --int sysctl_protected_hardlinks __read_mostly = 0; --int sysctl_protected_fifos __read_mostly; --int sysctl_protected_regular __read_mostly; -+int sysctl_protected_symlinks __read_mostly = 1; -+int sysctl_protected_hardlinks __read_mostly = 1; -+int sysctl_protected_fifos __read_mostly = 2; -+int sysctl_protected_regular __read_mostly = 2; - - /** - * may_follow_link - Check symlink following for unsafe situations -diff --git a/fs/nfs/Kconfig b/fs/nfs/Kconfig -index 14a72224b657..080a8027c6b1 100644 ---- a/fs/nfs/Kconfig -+++ b/fs/nfs/Kconfig -@@ -195,7 +195,6 @@ config NFS_DEBUG - bool - depends on NFS_FS && SUNRPC_DEBUG - select CRC32 -- default y - - config NFS_DISABLE_UDP_SUPPORT - bool "NFS: Disable NFS UDP protocol support" -diff --git a/fs/proc/Kconfig b/fs/proc/Kconfig -index c930001056f9..6a0a51b3f593 100644 ---- a/fs/proc/Kconfig -+++ b/fs/proc/Kconfig -@@ -41,7 +41,6 @@ config PROC_KCORE - config PROC_VMCORE - bool "/proc/vmcore support" - depends on PROC_FS && CRASH_DUMP -- default y - help - Exports the dump image of crashed kernel in ELF format. - -diff --git a/fs/stat.c b/fs/stat.c -index 1196af4d1ea0..4291a2c694e5 100644 ---- a/fs/stat.c -+++ b/fs/stat.c -@@ -43,8 +43,13 @@ void generic_fillattr(struct inode *inode, struct kstat *stat) - stat->gid = inode->i_gid; - stat->rdev = inode->i_rdev; - stat->size = i_size_read(inode); -- stat->atime = inode->i_atime; -- stat->mtime = inode->i_mtime; -+ if (is_sidechannel_device(inode) && !capable_noaudit(CAP_MKNOD)) { -+ stat->atime = inode->i_ctime; -+ stat->mtime = inode->i_ctime; -+ } else { -+ stat->atime = inode->i_atime; -+ stat->mtime = inode->i_mtime; -+ } - stat->ctime = inode->i_ctime; - stat->blksize = i_blocksize(inode); - stat->blocks = inode->i_blocks; -@@ -91,9 +96,14 @@ int vfs_getattr_nosec(const struct path *path, struct kstat *stat, - stat->attributes_mask |= (STATX_ATTR_AUTOMOUNT | - STATX_ATTR_DAX); - -- if (inode->i_op->getattr) -- return inode->i_op->getattr(path, stat, request_mask, -- query_flags); -+ if (inode->i_op->getattr) { -+ int retval = inode->i_op->getattr(path, stat, request_mask, query_flags); -+ if (!retval && is_sidechannel_device(inode) && !capable_noaudit(CAP_MKNOD)) { -+ stat->atime = stat->ctime; -+ stat->mtime = stat->ctime; -+ } -+ return retval; -+ } - - generic_fillattr(inode, stat); - return 0; -diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c -index 000b457ad087..06d35ecdcbc8 100644 ---- a/fs/userfaultfd.c -+++ b/fs/userfaultfd.c -@@ -28,7 +28,11 @@ - #include <linux/security.h> - #include <linux/hugetlb.h> - -+#ifdef CONFIG_USERFAULTFD_UNPRIVILEGED - int sysctl_unprivileged_userfaultfd __read_mostly = 1; -+#else -+int sysctl_unprivileged_userfaultfd __read_mostly; -+#endif - - static struct kmem_cache *userfaultfd_ctx_cachep __read_mostly; - -diff --git a/include/linux/cache.h b/include/linux/cache.h -index d742c57eaee5..f0222c070458 100644 ---- a/include/linux/cache.h -+++ b/include/linux/cache.h -@@ -37,6 +37,8 @@ - #define __ro_after_init __section(".data..ro_after_init") - #endif - -+#define __read_only __ro_after_init -+ - #ifndef ____cacheline_aligned - #define ____cacheline_aligned __attribute__((__aligned__(SMP_CACHE_BYTES))) - #endif -diff --git a/include/linux/capability.h b/include/linux/capability.h -index 1e7fe311cabe..a5b6d4c9acf5 100644 ---- a/include/linux/capability.h -+++ b/include/linux/capability.h -@@ -208,6 +208,7 @@ extern bool has_capability_noaudit(struct task_struct *t, int cap); - extern bool has_ns_capability_noaudit(struct task_struct *t, - struct user_namespace *ns, int cap); - extern bool capable(int cap); -+extern bool capable_noaudit(int cap); - extern bool ns_capable(struct user_namespace *ns, int cap); - extern bool ns_capable_noaudit(struct user_namespace *ns, int cap); - extern bool ns_capable_setid(struct user_namespace *ns, int cap); -@@ -234,6 +235,10 @@ static inline bool capable(int cap) - { - return true; - } -+static inline bool capable_noaudit(int cap) -+{ -+ return true; -+} - static inline bool ns_capable(struct user_namespace *ns, int cap) - { - return true; -diff --git a/include/linux/dccp.h b/include/linux/dccp.h -index 07e547c02fd8..504afa1a4be6 100644 ---- a/include/linux/dccp.h -+++ b/include/linux/dccp.h -@@ -259,6 +259,7 @@ struct dccp_ackvec; - * @dccps_sync_scheduled - flag which signals "send out-of-band message soon" - * @dccps_xmitlet - tasklet scheduled by the TX CCID to dequeue data packets - * @dccps_xmit_timer - used by the TX CCID to delay sending (rate-based pacing) -+ * @dccps_ccid_timer - used by the CCIDs - * @dccps_syn_rtt - RTT sample from Request/Response exchange (in usecs) - */ - struct dccp_sock { -@@ -303,6 +304,7 @@ struct dccp_sock { - __u8 dccps_sync_scheduled:1; - struct tasklet_struct dccps_xmitlet; - struct timer_list dccps_xmit_timer; -+ struct timer_list dccps_ccid_timer; - }; - - static inline struct dccp_sock *dccp_sk(const struct sock *sk) -diff --git a/include/linux/fs.h b/include/linux/fs.h -index 8bde32cf9711..83d50b0a2a18 100644 ---- a/include/linux/fs.h -+++ b/include/linux/fs.h -@@ -3475,4 +3475,15 @@ static inline int inode_drain_writes(struct inode *inode) - return filemap_write_and_wait(inode->i_mapping); - } - -+extern int device_sidechannel_restrict; -+ -+static inline bool is_sidechannel_device(const struct inode *inode) -+{ -+ umode_t mode; -+ if (!device_sidechannel_restrict) -+ return false; -+ mode = inode->i_mode; -+ return ((S_ISCHR(mode) || S_ISBLK(mode)) && (mode & (S_IROTH | S_IWOTH))); -+} -+ - #endif /* _LINUX_FS_H */ -diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h -index f8acddcf54fb..7b109980327f 100644 ---- a/include/linux/fsnotify.h -+++ b/include/linux/fsnotify.h -@@ -83,10 +83,14 @@ static inline void fsnotify_dentry(struct dentry *dentry, __u32 mask) - static inline int fsnotify_file(struct file *file, __u32 mask) - { - const struct path *path = &file->f_path; -+ struct inode *inode = file_inode(file); - - if (file->f_mode & FMODE_NONOTIFY) - return 0; - -+ if (mask & (FS_ACCESS | FS_MODIFY) && is_sidechannel_device(inode)) -+ return 0; -+ - return fsnotify_parent(path->dentry, mask, path, FSNOTIFY_EVENT_PATH); - } - -diff --git a/include/linux/gfp.h b/include/linux/gfp.h -index c603237e006c..893378b0262e 100644 ---- a/include/linux/gfp.h -+++ b/include/linux/gfp.h -@@ -568,9 +568,9 @@ static inline struct page *alloc_pages(gfp_t gfp_mask, unsigned int order) - extern unsigned long __get_free_pages(gfp_t gfp_mask, unsigned int order); - extern unsigned long get_zeroed_page(gfp_t gfp_mask); - --void *alloc_pages_exact(size_t size, gfp_t gfp_mask); -+void *alloc_pages_exact(size_t size, gfp_t gfp_mask) __attribute__((alloc_size(1))); - void free_pages_exact(void *virt, size_t size); --void * __meminit alloc_pages_exact_nid(int nid, size_t size, gfp_t gfp_mask); -+void * __meminit alloc_pages_exact_nid(int nid, size_t size, gfp_t gfp_mask) __attribute__((alloc_size(2))); - - #define __get_free_page(gfp_mask) \ - __get_free_pages((gfp_mask), 0) -diff --git a/include/linux/highmem.h b/include/linux/highmem.h -index 14e6202ce47f..4348ad7f5c50 100644 ---- a/include/linux/highmem.h -+++ b/include/linux/highmem.h -@@ -284,6 +284,13 @@ static inline void clear_highpage(struct page *page) - kunmap_atomic(kaddr); - } - -+static inline void verify_zero_highpage(struct page *page) -+{ -+ void *kaddr = kmap_atomic(page); -+ BUG_ON(memchr_inv(kaddr, 0, PAGE_SIZE)); -+ kunmap_atomic(kaddr); -+} -+ - static inline void zero_user_segments(struct page *page, - unsigned start1, unsigned end1, - unsigned start2, unsigned end2) -diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h -index ee8299eb1f52..4381b79f76cf 100644 ---- a/include/linux/interrupt.h -+++ b/include/linux/interrupt.h -@@ -554,7 +554,7 @@ extern const char * const softirq_to_name[NR_SOFTIRQS]; - - struct softirq_action - { -- void (*action)(struct softirq_action *); -+ void (*action)(void); - }; - - asmlinkage void do_softirq(void); -@@ -569,7 +569,7 @@ static inline void do_softirq_own_stack(void) - } - #endif - --extern void open_softirq(int nr, void (*action)(struct softirq_action *)); -+extern void __init open_softirq(int nr, void (*action)(void)); - extern void softirq_init(void); - extern void __raise_softirq_irqoff(unsigned int nr); - -diff --git a/include/linux/kobject_ns.h b/include/linux/kobject_ns.h -index 2b5b64256cf4..8cdce21dce0f 100644 ---- a/include/linux/kobject_ns.h -+++ b/include/linux/kobject_ns.h -@@ -45,7 +45,7 @@ struct kobj_ns_type_operations { - void (*drop_ns)(void *); - }; - --int kobj_ns_type_register(const struct kobj_ns_type_operations *ops); -+int __init kobj_ns_type_register(const struct kobj_ns_type_operations *ops); - int kobj_ns_type_registered(enum kobj_ns_type type); - const struct kobj_ns_type_operations *kobj_child_ns_ops(struct kobject *parent); - const struct kobj_ns_type_operations *kobj_ns_ops(struct kobject *kobj); -diff --git a/include/linux/mm.h b/include/linux/mm.h -index 289c26f055cd..0a691a57044d 100644 ---- a/include/linux/mm.h -+++ b/include/linux/mm.h -@@ -759,7 +759,7 @@ static inline int is_vmalloc_or_module_addr(const void *x) - } - #endif - --extern void *kvmalloc_node(size_t size, gfp_t flags, int node); -+extern void *kvmalloc_node(size_t size, gfp_t flags, int node) __attribute__((alloc_size(1))); - static inline void *kvmalloc(size_t size, gfp_t flags) - { - return kvmalloc_node(size, flags, NUMA_NO_NODE); -@@ -894,10 +894,15 @@ static inline void set_compound_page_dtor(struct page *page, - page[1].compound_dtor = compound_dtor; - } - --static inline void destroy_compound_page(struct page *page) -+static inline compound_page_dtor *get_compound_page_dtor(struct page *page) - { - VM_BUG_ON_PAGE(page[1].compound_dtor >= NR_COMPOUND_DTORS, page); -- compound_page_dtors[page[1].compound_dtor](page); -+ return compound_page_dtors[page[1].compound_dtor]; -+} -+ -+static inline void destroy_compound_page(struct page *page) -+{ -+ (*get_compound_page_dtor(page))(page); - } - - static inline unsigned int compound_order(struct page *page) -diff --git a/include/linux/percpu.h b/include/linux/percpu.h -index 5e76af742c80..9a6c682ec127 100644 ---- a/include/linux/percpu.h -+++ b/include/linux/percpu.h -@@ -123,7 +123,7 @@ extern int __init pcpu_page_first_chunk(size_t reserved_size, - pcpu_fc_populate_pte_fn_t populate_pte_fn); - #endif - --extern void __percpu *__alloc_reserved_percpu(size_t size, size_t align); -+extern void __percpu *__alloc_reserved_percpu(size_t size, size_t align) __attribute__((alloc_size(1))); - extern bool __is_kernel_percpu_address(unsigned long addr, unsigned long *can_addr); - extern bool is_kernel_percpu_address(unsigned long addr); - -@@ -131,8 +131,8 @@ extern bool is_kernel_percpu_address(unsigned long addr); - extern void __init setup_per_cpu_areas(void); - #endif - --extern void __percpu *__alloc_percpu_gfp(size_t size, size_t align, gfp_t gfp); --extern void __percpu *__alloc_percpu(size_t size, size_t align); -+extern void __percpu *__alloc_percpu_gfp(size_t size, size_t align, gfp_t gfp) __attribute__((alloc_size(1))); -+extern void __percpu *__alloc_percpu(size_t size, size_t align) __attribute__((alloc_size(1))); - extern void free_percpu(void __percpu *__pdata); - extern phys_addr_t per_cpu_ptr_to_phys(void *addr); - -diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h -index 072ac6c1ef2b..2c8f98a8f8b0 100644 ---- a/include/linux/perf_event.h -+++ b/include/linux/perf_event.h -@@ -1315,6 +1315,14 @@ static inline int perf_is_paranoid(void) - return sysctl_perf_event_paranoid > -1; - } - -+static inline int perf_allow_open(struct perf_event_attr *attr) -+{ -+ if (sysctl_perf_event_paranoid > 2 && !perfmon_capable()) -+ return -EACCES; -+ -+ return security_perf_event_open(attr, PERF_SECURITY_OPEN); -+} -+ - static inline int perf_allow_kernel(struct perf_event_attr *attr) - { - if (sysctl_perf_event_paranoid > 1 && !perfmon_capable()) -diff --git a/include/linux/slab.h b/include/linux/slab.h -index dd6897f62010..78f99835b91b 100644 ---- a/include/linux/slab.h -+++ b/include/linux/slab.h -@@ -181,7 +181,7 @@ int kmem_cache_shrink(struct kmem_cache *); - /* - * Common kmalloc functions provided by all allocators - */ --void * __must_check krealloc(const void *, size_t, gfp_t); -+void * __must_check krealloc(const void *, size_t, gfp_t) __attribute((alloc_size(2))); - void kfree(const void *); - void kfree_sensitive(const void *); - size_t __ksize(const void *); -@@ -386,7 +386,7 @@ static __always_inline unsigned int kmalloc_index(size_t size) - } - #endif /* !CONFIG_SLOB */ - --void *__kmalloc(size_t size, gfp_t flags) __assume_kmalloc_alignment __malloc; -+void *__kmalloc(size_t size, gfp_t flags) __assume_kmalloc_alignment __malloc __attribute__((alloc_size(1))); - void *kmem_cache_alloc(struct kmem_cache *, gfp_t flags) __assume_slab_alignment __malloc; - void kmem_cache_free(struct kmem_cache *, void *); - -@@ -410,7 +410,7 @@ static __always_inline void kfree_bulk(size_t size, void **p) - } - - #ifdef CONFIG_NUMA --void *__kmalloc_node(size_t size, gfp_t flags, int node) __assume_kmalloc_alignment __malloc; -+void *__kmalloc_node(size_t size, gfp_t flags, int node) __assume_kmalloc_alignment __malloc __attribute__((alloc_size(1))); - void *kmem_cache_alloc_node(struct kmem_cache *, gfp_t flags, int node) __assume_slab_alignment __malloc; - #else - static __always_inline void *__kmalloc_node(size_t size, gfp_t flags, int node) -@@ -535,7 +535,7 @@ static __always_inline void *kmalloc_large(size_t size, gfp_t flags) - * Try really hard to succeed the allocation but fail - * eventually. - */ --static __always_inline void *kmalloc(size_t size, gfp_t flags) -+static __always_inline __attribute__((alloc_size(1))) void *kmalloc(size_t size, gfp_t flags) - { - if (__builtin_constant_p(size)) { - #ifndef CONFIG_SLOB -@@ -557,7 +557,7 @@ static __always_inline void *kmalloc(size_t size, gfp_t flags) - return __kmalloc(size, flags); - } - --static __always_inline void *kmalloc_node(size_t size, gfp_t flags, int node) -+static __always_inline __attribute__((alloc_size(1))) void *kmalloc_node(size_t size, gfp_t flags, int node) - { - #ifndef CONFIG_SLOB - if (__builtin_constant_p(size) && -diff --git a/include/linux/slub_def.h b/include/linux/slub_def.h -index 1be0ed5befa1..c71cf30b5987 100644 ---- a/include/linux/slub_def.h -+++ b/include/linux/slub_def.h -@@ -113,6 +113,11 @@ struct kmem_cache { - unsigned long random; - #endif - -+#ifdef CONFIG_SLAB_CANARY -+ unsigned long random_active; -+ unsigned long random_inactive; -+#endif -+ - #ifdef CONFIG_NUMA - /* - * Defragmentation by allocating from a remote node. -diff --git a/include/linux/string.h b/include/linux/string.h -index b1f3894a0a3e..4c5564a6ad80 100644 ---- a/include/linux/string.h -+++ b/include/linux/string.h -@@ -264,6 +264,12 @@ void __read_overflow2(void) __compiletime_error("detected read beyond size of ob - void __read_overflow3(void) __compiletime_error("detected read beyond size of object passed as 3rd parameter"); - void __write_overflow(void) __compiletime_error("detected write beyond size of object passed as 1st parameter"); - -+#ifdef CONFIG_FORTIFY_SOURCE_STRICT_STRING -+#define __string_size(p) __builtin_object_size(p, 1) -+#else -+#define __string_size(p) __builtin_object_size(p, 0) -+#endif -+ - #if !defined(__NO_FORTIFY) && defined(__OPTIMIZE__) && defined(CONFIG_FORTIFY_SOURCE) - - #ifdef CONFIG_KASAN -@@ -292,7 +298,7 @@ extern char *__underlying_strncpy(char *p, const char *q, __kernel_size_t size) - - __FORTIFY_INLINE char *strncpy(char *p, const char *q, __kernel_size_t size) - { -- size_t p_size = __builtin_object_size(p, 0); -+ size_t p_size = __string_size(p); - if (__builtin_constant_p(size) && p_size < size) - __write_overflow(); - if (p_size < size) -@@ -302,7 +308,7 @@ __FORTIFY_INLINE char *strncpy(char *p, const char *q, __kernel_size_t size) - - __FORTIFY_INLINE char *strcat(char *p, const char *q) - { -- size_t p_size = __builtin_object_size(p, 0); -+ size_t p_size = __string_size(p); - if (p_size == (size_t)-1) - return __underlying_strcat(p, q); - if (strlcat(p, q, p_size) >= p_size) -@@ -313,7 +319,7 @@ __FORTIFY_INLINE char *strcat(char *p, const char *q) - __FORTIFY_INLINE __kernel_size_t strlen(const char *p) - { - __kernel_size_t ret; -- size_t p_size = __builtin_object_size(p, 0); -+ size_t p_size = __string_size(p); - - /* Work around gcc excess stack consumption issue */ - if (p_size == (size_t)-1 || -@@ -328,7 +334,7 @@ __FORTIFY_INLINE __kernel_size_t strlen(const char *p) - extern __kernel_size_t __real_strnlen(const char *, __kernel_size_t) __RENAME(strnlen); - __FORTIFY_INLINE __kernel_size_t strnlen(const char *p, __kernel_size_t maxlen) - { -- size_t p_size = __builtin_object_size(p, 0); -+ size_t p_size = __string_size(p); - __kernel_size_t ret = __real_strnlen(p, maxlen < p_size ? maxlen : p_size); - if (p_size <= ret && maxlen != ret) - fortify_panic(__func__); -@@ -340,8 +346,8 @@ extern size_t __real_strlcpy(char *, const char *, size_t) __RENAME(strlcpy); - __FORTIFY_INLINE size_t strlcpy(char *p, const char *q, size_t size) - { - size_t ret; -- size_t p_size = __builtin_object_size(p, 0); -- size_t q_size = __builtin_object_size(q, 0); -+ size_t p_size = __string_size(p); -+ size_t q_size = __string_size(q); - if (p_size == (size_t)-1 && q_size == (size_t)-1) - return __real_strlcpy(p, q, size); - ret = strlen(q); -@@ -361,8 +367,8 @@ __FORTIFY_INLINE size_t strlcpy(char *p, const char *q, size_t size) - __FORTIFY_INLINE char *strncat(char *p, const char *q, __kernel_size_t count) - { - size_t p_len, copy_len; -- size_t p_size = __builtin_object_size(p, 0); -- size_t q_size = __builtin_object_size(q, 0); -+ size_t p_size = __string_size(p); -+ size_t q_size = __string_size(q); - if (p_size == (size_t)-1 && q_size == (size_t)-1) - return __underlying_strncat(p, q, count); - p_len = strlen(p); -@@ -475,8 +481,8 @@ __FORTIFY_INLINE void *kmemdup(const void *p, size_t size, gfp_t gfp) - /* defined after fortified strlen and memcpy to reuse them */ - __FORTIFY_INLINE char *strcpy(char *p, const char *q) - { -- size_t p_size = __builtin_object_size(p, 0); -- size_t q_size = __builtin_object_size(q, 0); -+ size_t p_size = __string_size(p); -+ size_t q_size = __string_size(q); - if (p_size == (size_t)-1 && q_size == (size_t)-1) - return __underlying_strcpy(p, q); - memcpy(p, q, strlen(q) + 1); -diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h -index 51298a4f4623..b835c57330f2 100644 ---- a/include/linux/sysctl.h -+++ b/include/linux/sysctl.h -@@ -53,6 +53,8 @@ int proc_douintvec(struct ctl_table *, int, void *, size_t *, loff_t *); - int proc_dointvec_minmax(struct ctl_table *, int, void *, size_t *, loff_t *); - int proc_douintvec_minmax(struct ctl_table *table, int write, void *buffer, - size_t *lenp, loff_t *ppos); -+int proc_dointvec_minmax_sysadmin(struct ctl_table *table, int write, -+ void *buffer, size_t *lenp, loff_t *ppos); - int proc_dointvec_jiffies(struct ctl_table *, int, void *, size_t *, loff_t *); - int proc_dointvec_userhz_jiffies(struct ctl_table *, int, void *, size_t *, - loff_t *); -diff --git a/include/linux/tty.h b/include/linux/tty.h -index 5972f43b9d5a..b1750024d570 100644 ---- a/include/linux/tty.h -+++ b/include/linux/tty.h -@@ -14,6 +14,7 @@ - #include <uapi/linux/tty.h> - #include <linux/rwsem.h> - #include <linux/llist.h> -+#include <linux/user_namespace.h> - - - /* -@@ -341,6 +342,7 @@ struct tty_struct { - /* If the tty has a pending do_SAK, queue it here - akpm */ - struct work_struct SAK_work; - struct tty_port *port; -+ struct user_namespace *owner_user_ns; - } __randomize_layout; - - /* Each of a tty's open files has private_data pointing to tty_file_private */ -@@ -350,6 +352,8 @@ struct tty_file_private { - struct list_head list; - }; - -+extern int tiocsti_restrict; -+ - /* tty magic number */ - #define TTY_MAGIC 0x5401 - -diff --git a/include/linux/usb.h b/include/linux/usb.h -index d6a41841b93e..f7f3d138b4e6 100644 ---- a/include/linux/usb.h -+++ b/include/linux/usb.h -@@ -2037,6 +2037,17 @@ extern void usb_led_activity(enum usb_led_event ev); - static inline void usb_led_activity(enum usb_led_event ev) {} - #endif - -+/* sysctl.c */ -+extern int deny_new_usb; -+#ifdef CONFIG_SYSCTL -+extern int usb_init_sysctl(void); -+extern void usb_exit_sysctl(void); -+#else -+static inline int usb_init_sysctl(void) { return 0; } -+static inline void usb_exit_sysctl(void) { } -+#endif /* CONFIG_SYSCTL */ -+ -+ - #endif /* __KERNEL__ */ - - #endif -diff --git a/include/linux/user_namespace.h b/include/linux/user_namespace.h -index 7616c7bf4b24..bdbfcfe5df1e 100644 ---- a/include/linux/user_namespace.h -+++ b/include/linux/user_namespace.h -@@ -109,6 +109,8 @@ void dec_ucount(struct ucounts *ucounts, enum ucount_type type); - - #ifdef CONFIG_USER_NS - -+extern int unprivileged_userns_clone; -+ - static inline struct user_namespace *get_user_ns(struct user_namespace *ns) - { - if (ns) -@@ -142,6 +144,8 @@ extern bool current_in_userns(const struct user_namespace *target_ns); - struct ns_common *ns_get_owner(struct ns_common *ns); - #else - -+#define unprivileged_userns_clone 0 -+ - static inline struct user_namespace *get_user_ns(struct user_namespace *ns) - { - return &init_user_ns; -diff --git a/include/linux/vmalloc.h b/include/linux/vmalloc.h -index 76dad53a410a..35de3a67efa4 100644 ---- a/include/linux/vmalloc.h -+++ b/include/linux/vmalloc.h -@@ -97,18 +97,18 @@ static inline void vmalloc_init(void) - static inline unsigned long vmalloc_nr_pages(void) { return 0; } - #endif - --extern void *vmalloc(unsigned long size); --extern void *vzalloc(unsigned long size); --extern void *vmalloc_user(unsigned long size); --extern void *vmalloc_node(unsigned long size, int node); --extern void *vzalloc_node(unsigned long size, int node); --extern void *vmalloc_32(unsigned long size); --extern void *vmalloc_32_user(unsigned long size); --extern void *__vmalloc(unsigned long size, gfp_t gfp_mask); -+extern void *vmalloc(unsigned long size) __attribute__((alloc_size(1))); -+extern void *vzalloc(unsigned long size) __attribute__((alloc_size(1))); -+extern void *vmalloc_user(unsigned long size) __attribute__((alloc_size(1))); -+extern void *vmalloc_node(unsigned long size, int node) __attribute__((alloc_size(1))); -+extern void *vzalloc_node(unsigned long size, int node) __attribute__((alloc_size(1))); -+extern void *vmalloc_32(unsigned long size) __attribute__((alloc_size(1))); -+extern void *vmalloc_32_user(unsigned long size) __attribute__((alloc_size(1))); -+extern void *__vmalloc(unsigned long size, gfp_t gfp_mask) __attribute__((alloc_size(1))); - extern void *__vmalloc_node_range(unsigned long size, unsigned long align, - unsigned long start, unsigned long end, gfp_t gfp_mask, - pgprot_t prot, unsigned long vm_flags, int node, -- const void *caller); -+ const void *caller) __attribute__((alloc_size(1))); - void *__vmalloc_node(unsigned long size, unsigned long align, gfp_t gfp_mask, - int node, const void *caller); - -diff --git a/include/net/tcp.h b/include/net/tcp.h -index 7d66c61d22c7..cbb8c45ac186 100644 ---- a/include/net/tcp.h -+++ b/include/net/tcp.h -@@ -245,6 +245,7 @@ void tcp_time_wait(struct sock *sk, int state, int timeo); - /* sysctl variables for tcp */ - extern int sysctl_tcp_max_orphans; - extern long sysctl_tcp_mem[3]; -+extern int sysctl_tcp_simult_connect; - - #define TCP_RACK_LOSS_DETECTION 0x1 /* Use RACK to detect losses */ - #define TCP_RACK_STATIC_REO_WND 0x2 /* Use static RACK reo wnd */ -diff --git a/init/Kconfig b/init/Kconfig -index fc4c9f416fad..36edd8448d40 100644 ---- a/init/Kconfig -+++ b/init/Kconfig -@@ -418,6 +418,7 @@ config USELIB - config AUDIT - bool "Auditing support" - depends on NET -+ default y - help - Enable auditing infrastructure that can be used with another - kernel subsystem, such as SELinux (which requires this for -@@ -1172,6 +1173,22 @@ config USER_NS - - If unsure, say N. - -+config USER_NS_UNPRIVILEGED -+ bool "Allow unprivileged users to create namespaces" -+ depends on USER_NS -+ default n -+ help -+ When disabled, unprivileged users will not be able to create -+ new namespaces. Allowing users to create their own namespaces -+ has been part of several recent local privilege escalation -+ exploits, so if you need user namespaces but are -+ paranoid^Wsecurity-conscious you want to disable this. -+ -+ This setting can be overridden at runtime via the -+ kernel.unprivileged_userns_clone sysctl. -+ -+ If unsure, say N. -+ - config PID_NS - bool "PID Namespaces" - default y -@@ -1402,9 +1419,8 @@ menuconfig EXPERT - Only use this if you really know what you are doing. - - config UID16 -- bool "Enable 16-bit UID system calls" if EXPERT -+ bool "Enable 16-bit UID system calls" - depends on HAVE_UID16 && MULTIUSER -- default y - help - This enables the legacy 16-bit UID syscall wrappers. - -@@ -1433,14 +1449,13 @@ config SGETMASK_SYSCALL - If unsure, leave the default option here. - - config SYSFS_SYSCALL -- bool "Sysfs syscall support" if EXPERT -- default y -+ bool "Sysfs syscall support" - help - sys_sysfs is an obsolete system call no longer supported in libc. - Note that disabling this option is more secure but might break - compatibility with some systems. - -- If unsure say Y here. -+ If unsure say N here. - - config FHANDLE - bool "open by fhandle syscalls" if EXPERT -@@ -1591,8 +1606,7 @@ config SHMEM - which may be appropriate on small systems without swap. - - config AIO -- bool "Enable AIO support" if EXPERT -- default y -+ bool "Enable AIO support" - help - This option enables POSIX asynchronous I/O which may by used - by some high performance threaded applications. Disabling -@@ -1731,6 +1745,23 @@ config USERFAULTFD - Enable the userfaultfd() system call that allows to intercept and - handle page faults in userland. - -+config USERFAULTFD_UNPRIVILEGED -+ bool "Allow unprivileged users to use the userfaultfd syscall" -+ depends on USERFAULTFD -+ default n -+ help -+ When disabled, unprivileged users will not be able to use the userfaultfd -+ syscall. Userfaultfd provide attackers with a way to stall a kernel -+ thread in the middle of memory accesses from userspace by initiating an -+ access on an unmapped page. To avoid various heap grooming and heap -+ spraying techniques for exploiting use-after-free flaws this should be -+ disabled by default. -+ -+ This setting can be overridden at runtime via the -+ vm.unprivileged_userfaultfd sysctl. -+ -+ If unsure, say N. -+ - config ARCH_HAS_MEMBARRIER_CALLBACKS - bool - -@@ -1853,7 +1884,7 @@ config VM_EVENT_COUNTERS - - config SLUB_DEBUG - default y -- bool "Enable SLUB debugging support" if EXPERT -+ bool "Enable SLUB debugging support" - depends on SLUB && SYSFS - help - SLUB has extensive debug support features. Disabling these can -@@ -1877,7 +1908,6 @@ config SLUB_MEMCG_SYSFS_ON - - config COMPAT_BRK - bool "Disable heap randomization" -- default y - help - Randomizing heap placement makes heap exploits harder, but it - also breaks ancient binaries (including anything libc5 based). -@@ -1924,7 +1954,6 @@ endchoice - - config SLAB_MERGE_DEFAULT - bool "Allow slab caches to be merged" -- default y - help - For reduced kernel memory fragmentation, slab caches can be - merged when they share the same size and other characteristics. -@@ -1939,6 +1968,7 @@ config SLAB_MERGE_DEFAULT - config SLAB_FREELIST_RANDOM - bool "Randomize slab freelist" - depends on SLAB || SLUB -+ default y - help - Randomizes the freelist order used on creating new pages. This - security feature reduces the predictability of the kernel slab -@@ -1947,6 +1977,7 @@ config SLAB_FREELIST_RANDOM - config SLAB_FREELIST_HARDENED - bool "Harden slab freelist metadata" - depends on SLAB || SLUB -+ default y - help - Many kernel heap attacks try to target slab cache metadata and - other infrastructure. This options makes minor performance -@@ -1955,6 +1986,23 @@ config SLAB_FREELIST_HARDENED - sanity-checking than others. This option is most effective with - CONFIG_SLUB. - -+config SLAB_CANARY -+ depends on SLUB -+ depends on !SLAB_MERGE_DEFAULT -+ bool "SLAB canaries" -+ default y -+ help -+ Place canaries at the end of kernel slab allocations, sacrificing -+ some performance and memory usage for security. -+ -+ Canaries can detect some forms of heap corruption when allocations -+ are freed and as part of the HARDENED_USERCOPY feature. It provides -+ basic use-after-free detection for HARDENED_USERCOPY. -+ -+ Canaries absorb small overflows (rendering them harmless), mitigate -+ non-NUL terminated C string overflows on 64-bit via a guaranteed zero -+ byte and provide basic double-free detection. -+ - config SHUFFLE_PAGE_ALLOCATOR - bool "Page allocator randomization" - default SLAB_FREELIST_RANDOM && ACPI_NUMA -diff --git a/kernel/audit.c b/kernel/audit.c -index 68cee3bc8cfe..2059c66f7c9b 100644 ---- a/kernel/audit.c -+++ b/kernel/audit.c -@@ -1693,6 +1693,9 @@ static int __init audit_enable(char *str) - - if (audit_default == AUDIT_OFF) - audit_initialized = AUDIT_DISABLED; -+ else if (!audit_ever_enabled) -+ audit_initialized = AUDIT_UNINITIALIZED; -+ - if (audit_set_enabled(audit_default)) - pr_err("audit: error setting audit state (%d)\n", - audit_default); -diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c -index 182e162f8fd0..1705707b3b90 100644 ---- a/kernel/bpf/core.c -+++ b/kernel/bpf/core.c -@@ -524,7 +524,7 @@ void bpf_prog_kallsyms_del_all(struct bpf_prog *fp) - /* All BPF JIT sysctl knobs here. */ - int bpf_jit_enable __read_mostly = IS_BUILTIN(CONFIG_BPF_JIT_DEFAULT_ON); - int bpf_jit_kallsyms __read_mostly = IS_BUILTIN(CONFIG_BPF_JIT_DEFAULT_ON); --int bpf_jit_harden __read_mostly; -+int bpf_jit_harden __read_mostly = 2; - long bpf_jit_limit __read_mostly; - - static void -diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c -index 9433ab9995cd..348c36273f1a 100644 ---- a/kernel/bpf/syscall.c -+++ b/kernel/bpf/syscall.c -@@ -50,7 +50,7 @@ static DEFINE_SPINLOCK(map_idr_lock); - static DEFINE_IDR(link_idr); - static DEFINE_SPINLOCK(link_idr_lock); - --int sysctl_unprivileged_bpf_disabled __read_mostly; -+int sysctl_unprivileged_bpf_disabled __read_mostly = 1; - - static const struct bpf_map_ops * const bpf_map_types[] = { - #define BPF_PROG_TYPE(_id, _name, prog_ctx_type, kern_ctx_type) -diff --git a/kernel/capability.c b/kernel/capability.c -index de7eac903a2a..5602178f3d21 100644 ---- a/kernel/capability.c -+++ b/kernel/capability.c -@@ -449,6 +449,12 @@ bool capable(int cap) - return ns_capable(&init_user_ns, cap); - } - EXPORT_SYMBOL(capable); -+ -+bool capable_noaudit(int cap) -+{ -+ return ns_capable_noaudit(&init_user_ns, cap); -+} -+EXPORT_SYMBOL(capable_noaudit); - #endif /* CONFIG_MULTIUSER */ - - /** -diff --git a/kernel/events/core.c b/kernel/events/core.c -index 7e0fdc19043e..42636279e201 100644 ---- a/kernel/events/core.c -+++ b/kernel/events/core.c -@@ -408,8 +408,13 @@ static cpumask_var_t perf_online_mask; - * 0 - disallow raw tracepoint access for unpriv - * 1 - disallow cpu events for unpriv - * 2 - disallow kernel profiling for unpriv -+ * 3 - disallow all unpriv perf event use - */ -+#ifdef CONFIG_SECURITY_PERF_EVENTS_RESTRICT -+int sysctl_perf_event_paranoid __read_mostly = 3; -+#else - int sysctl_perf_event_paranoid __read_mostly = 2; -+#endif - - /* Minimum for 512 kiB + 1 user control page */ - int sysctl_perf_event_mlock __read_mostly = 512 + (PAGE_SIZE / 1024); /* 'free' kiB per user */ -@@ -11692,7 +11697,7 @@ SYSCALL_DEFINE5(perf_event_open, - return -EINVAL; - - /* Do we allow access to perf_event_open(2) ? */ -- err = security_perf_event_open(&attr, PERF_SECURITY_OPEN); -+ err = perf_allow_open(&attr); - if (err) - return err; - -diff --git a/kernel/fork.c b/kernel/fork.c -index 7c044d377926..8066141b692f 100644 ---- a/kernel/fork.c -+++ b/kernel/fork.c -@@ -82,6 +82,7 @@ - #include <linux/perf_event.h> - #include <linux/posix-timers.h> - #include <linux/user-return-notifier.h> -+#include <linux/user_namespace.h> - #include <linux/oom.h> - #include <linux/khugepaged.h> - #include <linux/signalfd.h> -@@ -1871,6 +1872,10 @@ static __latent_entropy struct task_struct *copy_process( - if ((clone_flags & (CLONE_NEWUSER|CLONE_FS)) == (CLONE_NEWUSER|CLONE_FS)) - return ERR_PTR(-EINVAL); - -+ if ((clone_flags & CLONE_NEWUSER) && !unprivileged_userns_clone) -+ if (!capable(CAP_SYS_ADMIN)) -+ return ERR_PTR(-EPERM); -+ - /* - * Thread groups must share signals as well, and detached threads - * can only be started up within the thread group. -@@ -2936,6 +2941,12 @@ int ksys_unshare(unsigned long unshare_flags) - if (unshare_flags & CLONE_NEWNS) - unshare_flags |= CLONE_FS; - -+ if ((unshare_flags & CLONE_NEWUSER) && !unprivileged_userns_clone) { -+ err = -EPERM; -+ if (!capable(CAP_SYS_ADMIN)) -+ goto bad_unshare_out; -+ } -+ - err = check_unshare_flags(unshare_flags); - if (err) - goto bad_unshare_out; -diff --git a/kernel/rcu/tiny.c b/kernel/rcu/tiny.c -index aa897c3f2e92..d8976886fd68 100644 ---- a/kernel/rcu/tiny.c -+++ b/kernel/rcu/tiny.c -@@ -101,7 +101,7 @@ static inline bool rcu_reclaim_tiny(struct rcu_head *head) - } - - /* Invoke the RCU callbacks whose grace period has elapsed. */ --static __latent_entropy void rcu_process_callbacks(struct softirq_action *unused) -+static __latent_entropy void rcu_process_callbacks(void) - { - struct rcu_head *next, *list; - unsigned long flags; -diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c -index 61e250cdd7c9..9ef3aa84f3c9 100644 ---- a/kernel/rcu/tree.c -+++ b/kernel/rcu/tree.c -@@ -2727,7 +2727,7 @@ static __latent_entropy void rcu_core(void) - queue_work_on(rdp->cpu, rcu_gp_wq, &rdp->strict_work); - } - --static void rcu_core_si(struct softirq_action *h) -+static void rcu_core_si(void) - { - rcu_core(); - } -diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c -index d6e1c90de570..03ea833c66a5 100644 ---- a/kernel/sched/fair.c -+++ b/kernel/sched/fair.c -@@ -10669,7 +10669,7 @@ static int newidle_balance(struct rq *this_rq, struct rq_flags *rf) - * run_rebalance_domains is triggered when needed from the scheduler tick. - * Also triggered for nohz idle balancing (with nohz_balancing_kick set). - */ --static __latent_entropy void run_rebalance_domains(struct softirq_action *h) -+static __latent_entropy void run_rebalance_domains(void) - { - struct rq *this_rq = this_rq(); - enum cpu_idle_type idle = this_rq->idle_balance ? -diff --git a/kernel/softirq.c b/kernel/softirq.c -index 09229ad82209..6a02d63b135a 100644 ---- a/kernel/softirq.c -+++ b/kernel/softirq.c -@@ -52,7 +52,7 @@ DEFINE_PER_CPU_ALIGNED(irq_cpustat_t, irq_stat); - EXPORT_PER_CPU_SYMBOL(irq_stat); - #endif - --static struct softirq_action softirq_vec[NR_SOFTIRQS] __cacheline_aligned_in_smp; -+static struct softirq_action softirq_vec[NR_SOFTIRQS] __ro_after_init __aligned(PAGE_SIZE); - - DEFINE_PER_CPU(struct task_struct *, ksoftirqd); - -@@ -295,7 +295,7 @@ asmlinkage __visible void __softirq_entry __do_softirq(void) - kstat_incr_softirqs_this_cpu(vec_nr); - - trace_softirq_entry(vec_nr); -- h->action(h); -+ h->action(); - trace_softirq_exit(vec_nr); - if (unlikely(prev_count != preempt_count())) { - pr_err("huh, entered softirq %u %s %p with preempt_count %08x, exited with %08x?\n", -@@ -486,7 +486,7 @@ void __raise_softirq_irqoff(unsigned int nr) - or_softirq_pending(1UL << nr); - } - --void open_softirq(int nr, void (*action)(struct softirq_action *)) -+void __init open_softirq(int nr, void (*action)(void)) - { - softirq_vec[nr].action = action; - } -@@ -532,8 +532,7 @@ void __tasklet_hi_schedule(struct tasklet_struct *t) - } - EXPORT_SYMBOL(__tasklet_hi_schedule); - --static void tasklet_action_common(struct softirq_action *a, -- struct tasklet_head *tl_head, -+static void tasklet_action_common(struct tasklet_head *tl_head, - unsigned int softirq_nr) - { - struct tasklet_struct *list; -@@ -573,14 +572,14 @@ static void tasklet_action_common(struct softirq_action *a, - } - } - --static __latent_entropy void tasklet_action(struct softirq_action *a) -+static __latent_entropy void tasklet_action(void) - { -- tasklet_action_common(a, this_cpu_ptr(&tasklet_vec), TASKLET_SOFTIRQ); -+ tasklet_action_common(this_cpu_ptr(&tasklet_vec), TASKLET_SOFTIRQ); - } - --static __latent_entropy void tasklet_hi_action(struct softirq_action *a) -+static __latent_entropy void tasklet_hi_action(void) - { -- tasklet_action_common(a, this_cpu_ptr(&tasklet_hi_vec), HI_SOFTIRQ); -+ tasklet_action_common(this_cpu_ptr(&tasklet_hi_vec), HI_SOFTIRQ); - } - - void tasklet_setup(struct tasklet_struct *t, -diff --git a/kernel/sysctl.c b/kernel/sysctl.c -index b9306d2bb426..c88545fb5967 100644 ---- a/kernel/sysctl.c -+++ b/kernel/sysctl.c -@@ -103,38 +103,44 @@ - #ifdef CONFIG_LOCKUP_DETECTOR - #include <linux/nmi.h> - #endif -+#ifdef CONFIG_USER_NS -+#include <linux/user_namespace.h> -+#endif -+#if defined CONFIG_TTY -+#include <linux/tty.h> -+#endif - - #if defined(CONFIG_SYSCTL) - - /* Constants used for minimum and maximum */ - #ifdef CONFIG_LOCKUP_DETECTOR --static int sixty = 60; --#endif -- --static int __maybe_unused neg_one = -1; --static int __maybe_unused two = 2; --static int __maybe_unused four = 4; --static unsigned long zero_ul; --static unsigned long one_ul = 1; --static unsigned long long_max = LONG_MAX; --static int one_hundred = 100; --static int two_hundred = 200; --static int one_thousand = 1000; -+static int sixty __read_only = 60; -+#endif -+ -+static int __maybe_unused neg_one __read_only = -1; -+static int __maybe_unused two __read_only = 2; -+static int __maybe_unused four __read_only = 4; -+static unsigned long zero_ul __read_only; -+static unsigned long one_ul __read_only = 1; -+static unsigned long long_max __read_only = LONG_MAX; -+static int one_hundred __read_only = 100; -+static int two_hundred __read_only = 200; -+static int one_thousand __read_only = 1000; - #ifdef CONFIG_PRINTK --static int ten_thousand = 10000; -+static int ten_thousand __read_only = 10000; - #endif - #ifdef CONFIG_PERF_EVENTS --static int six_hundred_forty_kb = 640 * 1024; -+static int six_hundred_forty_kb __read_only = 640 * 1024; - #endif - - /* this is needed for the proc_doulongvec_minmax of vm_dirty_bytes */ --static unsigned long dirty_bytes_min = 2 * PAGE_SIZE; -+static unsigned long dirty_bytes_min __read_only = 2 * PAGE_SIZE; - - /* this is needed for the proc_dointvec_minmax for [fs_]overflow UID and GID */ --static int maxolduid = 65535; --static int minolduid; -+static int maxolduid __read_only = 65535; -+static int minolduid __read_only; - --static int ngroups_max = NGROUPS_MAX; -+static int ngroups_max __read_only = NGROUPS_MAX; - static const int cap_last_cap = CAP_LAST_CAP; - - /* -@@ -142,7 +148,7 @@ static const int cap_last_cap = CAP_LAST_CAP; - * and hung_task_check_interval_secs - */ - #ifdef CONFIG_DETECT_HUNG_TASK --static unsigned long hung_task_timeout_max = (LONG_MAX/HZ); -+static unsigned long hung_task_timeout_max __read_only = (LONG_MAX/HZ); - #endif - - #ifdef CONFIG_INOTIFY_USER -@@ -185,19 +191,19 @@ int sysctl_legacy_va_layout; - #endif - - #ifdef CONFIG_SCHED_DEBUG --static int min_sched_granularity_ns = 100000; /* 100 usecs */ --static int max_sched_granularity_ns = NSEC_PER_SEC; /* 1 second */ --static int min_wakeup_granularity_ns; /* 0 usecs */ --static int max_wakeup_granularity_ns = NSEC_PER_SEC; /* 1 second */ -+static int min_sched_granularity_ns __read_only = 100000; /* 100 usecs */ -+static int max_sched_granularity_ns __read_only = NSEC_PER_SEC; /* 1 second */ -+static int min_wakeup_granularity_ns __read_only; /* 0 usecs */ -+static int max_wakeup_granularity_ns __read_only = NSEC_PER_SEC; /* 1 second */ - #ifdef CONFIG_SMP --static int min_sched_tunable_scaling = SCHED_TUNABLESCALING_NONE; --static int max_sched_tunable_scaling = SCHED_TUNABLESCALING_END-1; -+static int min_sched_tunable_scaling __read_only = SCHED_TUNABLESCALING_NONE; -+static int max_sched_tunable_scaling __read_only = SCHED_TUNABLESCALING_END-1; - #endif /* CONFIG_SMP */ - #endif /* CONFIG_SCHED_DEBUG */ - - #ifdef CONFIG_COMPACTION --static int min_extfrag_threshold; --static int max_extfrag_threshold = 1000; -+static int min_extfrag_threshold __read_only; -+static int max_extfrag_threshold __read_only = 1000; - #endif - - #endif /* CONFIG_SYSCTL */ -@@ -887,8 +893,27 @@ static int proc_taint(struct ctl_table *table, int write, - return err; - } - --#ifdef CONFIG_PRINTK --static int proc_dointvec_minmax_sysadmin(struct ctl_table *table, int write, -+/** -+ * proc_dointvec_minmax_sysadmin - read a vector of integers with min/max values -+ * checking CAP_SYS_ADMIN on write -+ * @table: the sysctl table -+ * @write: %TRUE if this is a write to the sysctl file -+ * @buffer: the user buffer -+ * @lenp: the size of the user buffer -+ * @ppos: file position -+ * -+ * Reads/writes up to table->maxlen/sizeof(unsigned int) integer -+ * values from/to the user buffer, treated as an ASCII string. -+ * -+ * This routine will ensure the values are within the range specified by -+ * table->extra1 (min) and table->extra2 (max). -+ * -+ * Writing is only allowed when root has CAP_SYS_ADMIN. -+ * -+ * Returns 0 on success, -EPERM on permission failure or -EINVAL on write -+ * when the range check fails. -+ */ -+int proc_dointvec_minmax_sysadmin(struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos) - { - if (write && !capable(CAP_SYS_ADMIN)) -@@ -896,7 +921,6 @@ static int proc_dointvec_minmax_sysadmin(struct ctl_table *table, int write, - - return proc_dointvec_minmax(table, write, buffer, lenp, ppos); - } --#endif - - /** - * struct do_proc_dointvec_minmax_conv_param - proc_dointvec_minmax() range checking structure -@@ -1582,6 +1606,12 @@ int proc_douintvec_minmax(struct ctl_table *table, int write, - return -ENOSYS; - } - -+int proc_dointvec_minmax_sysadmin(struct ctl_table *table, int write, -+ void *buffer, size_t *lenp, loff_t *ppos) -+{ -+ return -ENOSYS; -+} -+ - int proc_dointvec_jiffies(struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos) - { -@@ -1902,6 +1932,15 @@ static struct ctl_table kern_table[] = { - .proc_handler = proc_dointvec, - }, - #endif -+#ifdef CONFIG_USER_NS -+ { -+ .procname = "unprivileged_userns_clone", -+ .data = &unprivileged_userns_clone, -+ .maxlen = sizeof(int), -+ .mode = 0644, -+ .proc_handler = proc_dointvec, -+ }, -+#endif - #ifdef CONFIG_PROC_SYSCTL - { - .procname = "tainted", -@@ -2260,6 +2299,26 @@ static struct ctl_table kern_table[] = { - .extra2 = &two, - }, - #endif -+#if defined CONFIG_TTY -+ { -+ .procname = "tiocsti_restrict", -+ .data = &tiocsti_restrict, -+ .maxlen = sizeof(int), -+ .mode = 0644, -+ .proc_handler = proc_dointvec_minmax_sysadmin, -+ .extra1 = SYSCTL_ZERO, -+ .extra2 = SYSCTL_ONE, -+ }, -+#endif -+ { -+ .procname = "device_sidechannel_restrict", -+ .data = &device_sidechannel_restrict, -+ .maxlen = sizeof(int), -+ .mode = 0644, -+ .proc_handler = proc_dointvec_minmax_sysadmin, -+ .extra1 = SYSCTL_ZERO, -+ .extra2 = SYSCTL_ONE, -+ }, - { - .procname = "ngroups_max", - .data = &ngroups_max, -@@ -3415,6 +3474,7 @@ EXPORT_SYMBOL(proc_douintvec); - EXPORT_SYMBOL(proc_dointvec_jiffies); - EXPORT_SYMBOL(proc_dointvec_minmax); - EXPORT_SYMBOL_GPL(proc_douintvec_minmax); -+EXPORT_SYMBOL(proc_dointvec_minmax_sysadmin); - EXPORT_SYMBOL(proc_dointvec_userhz_jiffies); - EXPORT_SYMBOL(proc_dointvec_ms_jiffies); - EXPORT_SYMBOL(proc_dostring); -diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c -index 9505b1f21cdf..b67bb69052af 100644 ---- a/kernel/time/hrtimer.c -+++ b/kernel/time/hrtimer.c -@@ -1605,7 +1605,7 @@ static void __hrtimer_run_queues(struct hrtimer_cpu_base *cpu_base, ktime_t now, - } - } - --static __latent_entropy void hrtimer_run_softirq(struct softirq_action *h) -+static __latent_entropy void hrtimer_run_softirq(void) - { - struct hrtimer_cpu_base *cpu_base = this_cpu_ptr(&hrtimer_bases); - unsigned long flags; -diff --git a/kernel/time/timer.c b/kernel/time/timer.c -index c3ad64fb9d8b..217bc49a3856 100644 ---- a/kernel/time/timer.c -+++ b/kernel/time/timer.c -@@ -1753,7 +1753,7 @@ static inline void __run_timers(struct timer_base *base) - /* - * This function runs timers and the timer-tq in bottom half context. - */ --static __latent_entropy void run_timer_softirq(struct softirq_action *h) -+static __latent_entropy void run_timer_softirq(void) - { - struct timer_base *base = this_cpu_ptr(&timer_bases[BASE_STD]); - -diff --git a/kernel/user_namespace.c b/kernel/user_namespace.c -index ce396ea4de60..c3a6ef1f10ed 100644 ---- a/kernel/user_namespace.c -+++ b/kernel/user_namespace.c -@@ -21,6 +21,13 @@ - #include <linux/bsearch.h> - #include <linux/sort.h> - -+/* sysctl */ -+#ifdef CONFIG_USER_NS_UNPRIVILEGED -+int unprivileged_userns_clone = 1; -+#else -+int unprivileged_userns_clone; -+#endif -+ - static struct kmem_cache *user_ns_cachep __read_mostly; - static DEFINE_MUTEX(userns_state_mutex); - -diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug -index dcf4a9028e16..82f084142d8b 100644 ---- a/lib/Kconfig.debug -+++ b/lib/Kconfig.debug -@@ -374,6 +374,9 @@ config DEBUG_FORCE_FUNCTION_ALIGN_32B - - It is mainly for debug and performance tuning use. - -+config DEBUG_WRITABLE_FUNCTION_POINTERS_VERBOSE -+ bool "Enable verbose reporting of writable function pointers" -+ - # - # Select this config option from the architecture Kconfig, if it - # is preferred to always offer frame pointers as a config -@@ -488,7 +491,7 @@ config DEBUG_FS - choice - prompt "Debugfs default access" - depends on DEBUG_FS -- default DEBUG_FS_ALLOW_ALL -+ default DEBUG_FS_ALLOW_NONE - help - This selects the default access restrictions for debugfs. - It can be overridden with kernel command line option -@@ -894,6 +897,7 @@ menu "Debug Oops, Lockups and Hangs" - - config PANIC_ON_OOPS - bool "Panic on Oops" -+ default y - help - Say Y here to enable the kernel to panic when it oopses. This - has the same effect as setting oops=panic on the kernel command -@@ -903,7 +907,7 @@ config PANIC_ON_OOPS - anything erroneous after an oops which could result in data - corruption or other issues. - -- Say N if unsure. -+ Say Y if unsure. - - config PANIC_ON_OOPS_VALUE - int -@@ -1471,6 +1475,7 @@ menu "Debug kernel data structures" - config DEBUG_LIST - bool "Debug linked list manipulation" - depends on DEBUG_KERNEL || BUG_ON_DATA_CORRUPTION -+ default y - help - Enable this to turn on extended checks in the linked-list - walking routines. -@@ -1510,6 +1515,7 @@ config DEBUG_NOTIFIERS - config BUG_ON_DATA_CORRUPTION - bool "Trigger a BUG when data corruption is detected" - select DEBUG_LIST -+ default y - help - Select this option if the kernel should BUG when it encounters - data corruption in kernel memory structures when they get checked -@@ -1665,6 +1671,7 @@ config STRICT_DEVMEM - config IO_STRICT_DEVMEM - bool "Filter I/O access to /dev/mem" - depends on STRICT_DEVMEM -+ default y - help - If this option is disabled, you allow userspace (root) access to all - io-memory regardless of whether a driver is actively using that -diff --git a/lib/irq_poll.c b/lib/irq_poll.c -index 2f17b488d58e..b6e7996a0058 100644 ---- a/lib/irq_poll.c -+++ b/lib/irq_poll.c -@@ -75,7 +75,7 @@ void irq_poll_complete(struct irq_poll *iop) - } - EXPORT_SYMBOL(irq_poll_complete); - --static void __latent_entropy irq_poll_softirq(struct softirq_action *h) -+static void __latent_entropy irq_poll_softirq(void) - { - struct list_head *list = this_cpu_ptr(&blk_cpu_iopoll); - int rearm = 0, budget = irq_poll_budget; -diff --git a/lib/kobject.c b/lib/kobject.c -index ea53b30cf483..5343bbeea5f8 100644 ---- a/lib/kobject.c -+++ b/lib/kobject.c -@@ -1023,9 +1023,9 @@ EXPORT_SYMBOL_GPL(kset_create_and_add); - - - static DEFINE_SPINLOCK(kobj_ns_type_lock); --static const struct kobj_ns_type_operations *kobj_ns_ops_tbl[KOBJ_NS_TYPES]; -+static const struct kobj_ns_type_operations *kobj_ns_ops_tbl[KOBJ_NS_TYPES] __ro_after_init; - --int kobj_ns_type_register(const struct kobj_ns_type_operations *ops) -+int __init kobj_ns_type_register(const struct kobj_ns_type_operations *ops) - { - enum kobj_ns_type type = ops->type; - int error; -diff --git a/lib/nlattr.c b/lib/nlattr.c -index fe60f9ae9db1..0e9d8d239973 100644 ---- a/lib/nlattr.c -+++ b/lib/nlattr.c -@@ -778,6 +778,8 @@ int nla_memcpy(void *dest, const struct nlattr *src, int count) - { - int minlen = min_t(int, count, nla_len(src)); - -+ BUG_ON(minlen < 0); -+ - memcpy(dest, nla_data(src), minlen); - if (count > minlen) - memset(dest + minlen, 0, count - minlen); -diff --git a/lib/vsprintf.c b/lib/vsprintf.c -index fd0fde639ec9..a4c940a6aff2 100644 ---- a/lib/vsprintf.c -+++ b/lib/vsprintf.c -@@ -821,7 +821,7 @@ static char *ptr_to_id(char *buf, char *end, const void *ptr, - return pointer_string(buf, end, (const void *)hashval, spec); - } - --int kptr_restrict __read_mostly; -+int kptr_restrict __read_mostly = 2; - - static noinline_for_stack - char *restricted_pointer(char *buf, char *end, const void *ptr, -diff --git a/mm/Kconfig b/mm/Kconfig -index 390165ffbb0f..3b24c9e3535e 100644 ---- a/mm/Kconfig -+++ b/mm/Kconfig -@@ -321,7 +321,8 @@ config KSM - config DEFAULT_MMAP_MIN_ADDR - int "Low address space to protect from user allocation" - depends on MMU -- default 4096 -+ default 32768 if ARM || (ARM64 && COMPAT) -+ default 65536 - help - This is the portion of low virtual memory which should be protected - from userspace allocation. Keeping a user from writing to low pages -diff --git a/mm/Kconfig.debug b/mm/Kconfig.debug -index 864f129f1937..929d585bd267 100644 ---- a/mm/Kconfig.debug -+++ b/mm/Kconfig.debug -@@ -126,6 +126,7 @@ config DEBUG_WX - depends on ARCH_HAS_DEBUG_WX - depends on MMU - select PTDUMP_CORE -+ default y - help - Generate a warning if any W+X mappings are found at boot. - -diff --git a/mm/mmap.c b/mm/mmap.c -index 5c8b4485860d..0e26c225bb53 100644 ---- a/mm/mmap.c -+++ b/mm/mmap.c -@@ -231,6 +231,13 @@ SYSCALL_DEFINE1(brk, unsigned long, brk) - - newbrk = PAGE_ALIGN(brk); - oldbrk = PAGE_ALIGN(mm->brk); -+ /* properly handle unaligned min_brk as an empty heap */ -+ if (min_brk & ~PAGE_MASK) { -+ if (brk == min_brk) -+ newbrk -= PAGE_SIZE; -+ if (mm->brk == min_brk) -+ oldbrk -= PAGE_SIZE; -+ } - if (oldbrk == newbrk) { - mm->brk = brk; - goto success; -diff --git a/mm/page_alloc.c b/mm/page_alloc.c -index 81cc7fdc9c8f..254def6fa5b3 100644 ---- a/mm/page_alloc.c -+++ b/mm/page_alloc.c -@@ -70,6 +70,7 @@ - #include <linux/psi.h> - #include <linux/padata.h> - #include <linux/khugepaged.h> -+#include <linux/random.h> - - #include <asm/sections.h> - #include <asm/tlbflush.h> -@@ -136,6 +137,15 @@ struct pcpu_drain { - static DEFINE_MUTEX(pcpu_drain_mutex); - static DEFINE_PER_CPU(struct pcpu_drain, pcpu_drain); - -+bool __meminitdata extra_latent_entropy; -+ -+static int __init setup_extra_latent_entropy(char *str) -+{ -+ extra_latent_entropy = true; -+ return 0; -+} -+early_param("extra_latent_entropy", setup_extra_latent_entropy); -+ - #ifdef CONFIG_GCC_PLUGIN_LATENT_ENTROPY - volatile unsigned long latent_entropy __latent_entropy; - EXPORT_SYMBOL(latent_entropy); -@@ -1529,6 +1539,25 @@ static void __free_pages_ok(struct page *page, unsigned int order, - local_irq_restore(flags); - } - -+static void __init __gather_extra_latent_entropy(struct page *page, -+ unsigned int nr_pages) -+{ -+ if (extra_latent_entropy && !PageHighMem(page) && page_to_pfn(page) < 0x100000) { -+ unsigned long hash = 0; -+ size_t index, end = PAGE_SIZE * nr_pages / sizeof hash; -+ const unsigned long *data = lowmem_page_address(page); -+ -+ for (index = 0; index < end; index++) -+ hash ^= hash + data[index]; -+#ifdef CONFIG_GCC_PLUGIN_LATENT_ENTROPY -+ latent_entropy ^= hash; -+ add_device_randomness((const void *)&latent_entropy, sizeof(latent_entropy)); -+#else -+ add_device_randomness((const void *)&hash, sizeof(hash)); -+#endif -+ } -+} -+ - void __free_pages_core(struct page *page, unsigned int order) - { - unsigned int nr_pages = 1 << order; -@@ -1548,7 +1577,6 @@ void __free_pages_core(struct page *page, unsigned int order) - } - __ClearPageReserved(p); - set_page_count(p, 0); -- - atomic_long_add(nr_pages, &page_zone(page)->managed_pages); - - /* -@@ -1607,6 +1635,7 @@ void __init memblock_free_pages(struct page *page, unsigned long pfn, - { - if (early_page_uninitialised(pfn)) - return; -+ __gather_extra_latent_entropy(page, 1 << order); - __free_pages_core(page, order); - } - -@@ -1698,6 +1727,7 @@ static void __init deferred_free_range(unsigned long pfn, - if (nr_pages == pageblock_nr_pages && - (pfn & (pageblock_nr_pages - 1)) == 0) { - set_pageblock_migratetype(page, MIGRATE_MOVABLE); -+ __gather_extra_latent_entropy(page, 1 << pageblock_order); - __free_pages_core(page, pageblock_order); - return; - } -@@ -1705,6 +1735,7 @@ static void __init deferred_free_range(unsigned long pfn, - for (i = 0; i < nr_pages; i++, page++, pfn++) { - if ((pfn & (pageblock_nr_pages - 1)) == 0) - set_pageblock_migratetype(page, MIGRATE_MOVABLE); -+ __gather_extra_latent_entropy(page, 1); - __free_pages_core(page, 0); - } - } -@@ -2284,6 +2315,12 @@ static void prep_new_page(struct page *page, unsigned int order, gfp_t gfp_flags - { - post_alloc_hook(page, order, gfp_flags); - -+ if (IS_ENABLED(CONFIG_PAGE_SANITIZE_VERIFY) && want_init_on_free()) { -+ int i; -+ for (i = 0; i < (1 << order); i++) -+ verify_zero_highpage(page + i); -+ } -+ - if (!free_pages_prezeroed() && want_init_on_alloc(gfp_flags)) - kernel_init_free_pages(page, 1 << order); - -diff --git a/mm/slab.h b/mm/slab.h -index e258ffcfb0ef..6208d0d5ef15 100644 ---- a/mm/slab.h -+++ b/mm/slab.h -@@ -433,9 +433,13 @@ static inline struct kmem_cache *virt_to_cache(const void *obj) - struct page *page; - - page = virt_to_head_page(obj); -+#ifdef CONFIG_BUG_ON_DATA_CORRUPTION -+ BUG_ON(!PageSlab(page)); -+#else - if (WARN_ONCE(!PageSlab(page), "%s: Object is not a Slab page!\n", - __func__)) - return NULL; -+#endif - return page->slab_cache; - } - -@@ -465,10 +469,15 @@ static inline struct kmem_cache *cache_from_obj(struct kmem_cache *s, void *x) - return s; - - cachep = virt_to_cache(x); -- if (WARN(cachep && cachep != s, -- "%s: Wrong slab cache. %s but object is from %s\n", -- __func__, s->name, cachep->name)) -+ if (cachep && cachep != s) { -+#ifdef CONFIG_BUG_ON_DATA_CORRUPTION -+ BUG(); -+#else -+ WARN(1, "%s: Wrong slab cache. %s but object is from %s\n", -+ __func__, s->name, cachep->name); -+#endif - print_tracking(cachep, x); -+ } - return cachep; - } - -@@ -493,7 +502,7 @@ static inline size_t slab_ksize(const struct kmem_cache *s) - * back there or track user information then we can - * only use the space before that information. - */ -- if (s->flags & (SLAB_TYPESAFE_BY_RCU | SLAB_STORE_USER)) -+ if ((s->flags & (SLAB_TYPESAFE_BY_RCU | SLAB_STORE_USER)) || IS_ENABLED(CONFIG_SLAB_CANARY)) - return s->inuse; - /* - * Else we can use all the padding etc for the allocation -@@ -619,8 +628,10 @@ static inline void cache_random_seq_destroy(struct kmem_cache *cachep) { } - static inline bool slab_want_init_on_alloc(gfp_t flags, struct kmem_cache *c) - { - if (static_branch_unlikely(&init_on_alloc)) { -+#ifndef CONFIG_SLUB - if (c->ctor) - return false; -+#endif - if (c->flags & (SLAB_TYPESAFE_BY_RCU | SLAB_POISON)) - return flags & __GFP_ZERO; - return true; -@@ -630,9 +641,15 @@ static inline bool slab_want_init_on_alloc(gfp_t flags, struct kmem_cache *c) - - static inline bool slab_want_init_on_free(struct kmem_cache *c) - { -- if (static_branch_unlikely(&init_on_free)) -- return !(c->ctor || -- (c->flags & (SLAB_TYPESAFE_BY_RCU | SLAB_POISON))); -+ if (static_branch_unlikely(&init_on_free)) { -+#ifndef CONFIG_SLUB -+ if (c->ctor) -+ return false; -+#endif -+ if (c->flags & (SLAB_TYPESAFE_BY_RCU | SLAB_POISON)) -+ return false; -+ return true; -+ } - return false; - } - -diff --git a/mm/slab_common.c b/mm/slab_common.c -index ec832904f408..c24e2f33c9fb 100644 ---- a/mm/slab_common.c -+++ b/mm/slab_common.c -@@ -30,10 +30,10 @@ - - #include "slab.h" - --enum slab_state slab_state; -+enum slab_state slab_state __ro_after_init; - LIST_HEAD(slab_caches); - DEFINE_MUTEX(slab_mutex); --struct kmem_cache *kmem_cache; -+struct kmem_cache *kmem_cache __ro_after_init; - - #ifdef CONFIG_HARDENED_USERCOPY - bool usercopy_fallback __ro_after_init = -@@ -61,7 +61,7 @@ static DECLARE_WORK(slab_caches_to_rcu_destroy_work, - /* - * Merge control. If this is set then no merging of slab caches will occur. - */ --static bool slab_nomerge = !IS_ENABLED(CONFIG_SLAB_MERGE_DEFAULT); -+static bool slab_nomerge __ro_after_init = !IS_ENABLED(CONFIG_SLAB_MERGE_DEFAULT); - - static int __init setup_slab_nomerge(char *str) - { -diff --git a/mm/slub.c b/mm/slub.c -index f5fc44208bdc..d1021b7544a6 100644 ---- a/mm/slub.c -+++ b/mm/slub.c -@@ -128,6 +128,12 @@ static inline bool kmem_cache_debug(struct kmem_cache *s) - return kmem_cache_debug_flags(s, SLAB_DEBUG_FLAGS); - } - -+static inline bool has_sanitize_verify(struct kmem_cache *s) -+{ -+ return IS_ENABLED(CONFIG_SLAB_SANITIZE_VERIFY) && -+ slab_want_init_on_free(s); -+} -+ - void *fixup_red_left(struct kmem_cache *s, void *p) - { - if (kmem_cache_debug_flags(s, SLAB_RED_ZONE)) -@@ -433,6 +439,55 @@ static inline bool cmpxchg_double_slab(struct kmem_cache *s, struct page *page, - return false; - } - -+#if defined(CONFIG_SLUB_DEBUG) || defined(CONFIG_SLAB_CANARY) -+/* -+ * See comment in calculate_sizes(). -+ */ -+static inline bool freeptr_outside_object(struct kmem_cache *s) -+{ -+ return s->offset >= s->inuse; -+} -+ -+/* -+ * Return offset of the end of info block which is inuse + free pointer if -+ * not overlapping with object. -+ */ -+static inline unsigned int get_info_end(struct kmem_cache *s) -+{ -+ if (freeptr_outside_object(s)) -+ return s->inuse + sizeof(void *); -+ else -+ return s->inuse; -+} -+#endif -+ -+#ifdef CONFIG_SLAB_CANARY -+static inline unsigned long *get_canary(struct kmem_cache *s, void *object) -+{ -+ return object + get_info_end(s); -+} -+ -+static inline unsigned long get_canary_value(const void *canary, unsigned long value) -+{ -+ return (value ^ (unsigned long)canary) & CANARY_MASK; -+} -+ -+static inline void set_canary(struct kmem_cache *s, void *object, unsigned long value) -+{ -+ unsigned long *canary = get_canary(s, object); -+ *canary = get_canary_value(canary, value); -+} -+ -+static inline void check_canary(struct kmem_cache *s, void *object, unsigned long value) -+{ -+ unsigned long *canary = get_canary(s, object); -+ BUG_ON(*canary != get_canary_value(canary, value)); -+} -+#else -+#define set_canary(s, object, value) -+#define check_canary(s, object, value) -+#endif -+ - #ifdef CONFIG_SLUB_DEBUG - static unsigned long object_map[BITS_TO_LONGS(MAX_OBJS_PER_PAGE)]; - static DEFINE_SPINLOCK(object_map_lock); -@@ -487,13 +542,13 @@ static inline void *restore_red_left(struct kmem_cache *s, void *p) - * Debug settings: - */ - #if defined(CONFIG_SLUB_DEBUG_ON) --static slab_flags_t slub_debug = DEBUG_DEFAULT_FLAGS; -+static slab_flags_t slub_debug __ro_after_init = DEBUG_DEFAULT_FLAGS; - #else --static slab_flags_t slub_debug; -+static slab_flags_t slub_debug __ro_after_init; - #endif - --static char *slub_debug_string; --static int disable_higher_order_debug; -+static char *slub_debug_string __ro_after_init; -+static int disable_higher_order_debug __ro_after_init; - - /* - * slub is about to manipulate internal object metadata. This memory lies -@@ -544,26 +599,6 @@ static void print_section(char *level, char *text, u8 *addr, - metadata_access_disable(); - } - --/* -- * See comment in calculate_sizes(). -- */ --static inline bool freeptr_outside_object(struct kmem_cache *s) --{ -- return s->offset >= s->inuse; --} -- --/* -- * Return offset of the end of info block which is inuse + free pointer if -- * not overlapping with object. -- */ --static inline unsigned int get_info_end(struct kmem_cache *s) --{ -- if (freeptr_outside_object(s)) -- return s->inuse + sizeof(void *); -- else -- return s->inuse; --} -- - static struct track *get_track(struct kmem_cache *s, void *object, - enum track_item alloc) - { -@@ -571,6 +606,9 @@ static struct track *get_track(struct kmem_cache *s, void *object, - - p = object + get_info_end(s); - -+ if (IS_ENABLED(CONFIG_SLAB_CANARY)) -+ p = (void *)p + sizeof(void *); -+ - return p + alloc; - } - -@@ -712,6 +750,9 @@ static void print_trailer(struct kmem_cache *s, struct page *page, u8 *p) - - off = get_info_end(s); - -+ if (IS_ENABLED(CONFIG_SLAB_CANARY)) -+ off += sizeof(void *); -+ - if (s->flags & SLAB_STORE_USER) - off += 2 * sizeof(struct track); - -@@ -820,8 +861,9 @@ static int check_bytes_and_report(struct kmem_cache *s, struct page *page, - * Meta data starts here. - * - * A. Free pointer (if we cannot overwrite object on free) -- * B. Tracking data for SLAB_STORE_USER -- * C. Padding to reach required alignment boundary or at mininum -+ * B. Canary for SLAB_CANARY -+ * C. Tracking data for SLAB_STORE_USER -+ * D. Padding to reach required alignment boundary or at mininum - * one word if debugging is on to be able to detect writes - * before the word boundary. - * -@@ -839,6 +881,9 @@ static int check_pad_bytes(struct kmem_cache *s, struct page *page, u8 *p) - { - unsigned long off = get_info_end(s); /* The end of info */ - -+ if (IS_ENABLED(CONFIG_SLAB_CANARY)) -+ off += sizeof(void *); -+ - if (s->flags & SLAB_STORE_USER) - /* We also have user information there */ - off += 2 * sizeof(struct track); -@@ -1559,6 +1604,8 @@ static inline bool slab_free_freelist_hook(struct kmem_cache *s, - object = next; - next = get_freepointer(s, object); - -+ check_canary(s, object, s->random_active); -+ - if (slab_want_init_on_free(s)) { - /* - * Clear the object and the metadata, but don't touch -@@ -1569,8 +1616,12 @@ static inline bool slab_free_freelist_hook(struct kmem_cache *s, - : 0; - memset((char *)object + s->inuse, 0, - s->size - s->inuse - rsize); -- -+ if (!IS_ENABLED(CONFIG_SLAB_SANITIZE_VERIFY) && s->ctor) -+ s->ctor(object); - } -+ -+ set_canary(s, object, s->random_inactive); -+ - /* If object's reuse doesn't have to be delayed */ - if (!slab_free_hook(s, object)) { - /* Move object to the new freelist */ -@@ -1578,6 +1629,18 @@ static inline bool slab_free_freelist_hook(struct kmem_cache *s, - *head = object; - if (!*tail) - *tail = object; -+ } else if (slab_want_init_on_free(s) && s->ctor) { -+ /* Objects that are put into quarantine by KASAN will -+ * still undergo free_consistency_checks() and thus -+ * need to show a valid freepointer to check_object(). -+ * -+ * Note that doing this for all caches (not just ctor -+ * ones, which have s->offset >= object_size)) causes a -+ * GPF, due to KASAN poisoning and the way -+ * set_freepointer() eventually dereferences the -+ * freepointer. -+ */ -+ set_freepointer(s, object, NULL); - } - } while (object != old_tail); - -@@ -1591,8 +1654,9 @@ static void *setup_object(struct kmem_cache *s, struct page *page, - void *object) - { - setup_object_debug(s, page, object); -+ set_canary(s, object, s->random_inactive); - object = kasan_init_slab_obj(s, object); -- if (unlikely(s->ctor)) { -+ if (unlikely(s->ctor) && !has_sanitize_verify(s)) { - kasan_unpoison_object_data(s, object); - s->ctor(object); - kasan_poison_object_data(s, object); -@@ -2883,8 +2947,28 @@ static __always_inline void *slab_alloc_node(struct kmem_cache *s, - - maybe_wipe_obj_freeptr(s, object); - -- if (unlikely(slab_want_init_on_alloc(gfpflags, s)) && object) -+ if (has_sanitize_verify(s) && object) { -+ /* KASAN hasn't unpoisoned the object yet (this is done in the -+ * post-alloc hook), so let's do it temporarily. -+ */ -+ kasan_unpoison_object_data(s, object); -+ BUG_ON(memchr_inv(object, 0, s->object_size)); -+ if (s->ctor) -+ s->ctor(object); -+ kasan_poison_object_data(s, object); -+ } else if (unlikely(slab_want_init_on_alloc(gfpflags, s)) && object) { - memset(object, 0, s->object_size); -+ if (s->ctor) { -+ kasan_unpoison_object_data(s, object); -+ s->ctor(object); -+ kasan_poison_object_data(s, object); -+ } -+ } -+ -+ if (object) { -+ check_canary(s, object, s->random_inactive); -+ set_canary(s, object, s->random_active); -+ } - - slab_post_alloc_hook(s, objcg, gfpflags, 1, &object); - -@@ -3273,7 +3357,7 @@ int kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size, - void **p) - { - struct kmem_cache_cpu *c; -- int i; -+ int i, k; - struct obj_cgroup *objcg = NULL; - - /* memcg and kmem_cache debug support */ -@@ -3323,11 +3407,35 @@ int kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size, - local_irq_enable(); - - /* Clear memory outside IRQ disabled fastpath loop */ -- if (unlikely(slab_want_init_on_alloc(flags, s))) { -+ if (has_sanitize_verify(s)) { -+ int j; -+ -+ for (j = 0; j < i; j++) { -+ /* KASAN hasn't unpoisoned the object yet (this is done -+ * in the post-alloc hook), so let's do it temporarily. -+ */ -+ kasan_unpoison_object_data(s, p[j]); -+ BUG_ON(memchr_inv(p[j], 0, s->object_size)); -+ if (s->ctor) -+ s->ctor(p[j]); -+ kasan_poison_object_data(s, p[j]); -+ } -+ } else if (unlikely(slab_want_init_on_alloc(flags, s))) { - int j; - -- for (j = 0; j < i; j++) -+ for (j = 0; j < i; j++) { - memset(p[j], 0, s->object_size); -+ if (s->ctor) { -+ kasan_unpoison_object_data(s, p[j]); -+ s->ctor(p[j]); -+ kasan_poison_object_data(s, p[j]); -+ } -+ } -+ } -+ -+ for (k = 0; k < i; k++) { -+ check_canary(s, p[k], s->random_inactive); -+ set_canary(s, p[k], s->random_active); - } - - /* memcg and kmem_cache debug support */ -@@ -3361,9 +3469,9 @@ EXPORT_SYMBOL(kmem_cache_alloc_bulk); - * and increases the number of allocations possible without having to - * take the list_lock. - */ --static unsigned int slub_min_order; --static unsigned int slub_max_order = PAGE_ALLOC_COSTLY_ORDER; --static unsigned int slub_min_objects; -+static unsigned int slub_min_order __ro_after_init; -+static unsigned int slub_max_order __ro_after_init = PAGE_ALLOC_COSTLY_ORDER; -+static unsigned int slub_min_objects __ro_after_init; - - /* - * Calculate the order of allocation given an slab object size. -@@ -3531,6 +3639,7 @@ static void early_kmem_cache_node_alloc(int node) - init_object(kmem_cache_node, n, SLUB_RED_ACTIVE); - init_tracking(kmem_cache_node, n); - #endif -+ set_canary(kmem_cache_node, n, kmem_cache_node->random_active); - n = kasan_kmalloc(kmem_cache_node, n, sizeof(struct kmem_cache_node), - GFP_KERNEL); - page->freelist = get_freepointer(kmem_cache_node, n); -@@ -3705,6 +3814,9 @@ static int calculate_sizes(struct kmem_cache *s, int forced_order) - s->offset = ALIGN_DOWN(s->object_size / 2, sizeof(void *)); - } - -+ if (IS_ENABLED(CONFIG_SLAB_CANARY)) -+ size += sizeof(void *); -+ - #ifdef CONFIG_SLUB_DEBUG - if (flags & SLAB_STORE_USER) - /* -@@ -3778,6 +3890,10 @@ static int kmem_cache_open(struct kmem_cache *s, slab_flags_t flags) - #ifdef CONFIG_SLAB_FREELIST_HARDENED - s->random = get_random_long(); - #endif -+#ifdef CONFIG_SLAB_CANARY -+ s->random_active = get_random_long(); -+ s->random_inactive = get_random_long(); -+#endif - - if (!calculate_sizes(s, -1)) - goto error; -@@ -4051,6 +4167,8 @@ void __check_heap_object(const void *ptr, unsigned long n, struct page *page, - offset -= s->red_left_pad; - } - -+ check_canary(s, (void *)ptr - offset, s->random_active); -+ - /* Allow address range falling entirely within usercopy region. */ - if (offset >= s->useroffset && - offset - s->useroffset <= s->usersize && -@@ -4084,7 +4202,11 @@ size_t __ksize(const void *object) - page = virt_to_head_page(object); - - if (unlikely(!PageSlab(page))) { -+#ifdef CONFIG_BUG_ON_DATA_CORRUPTION -+ BUG_ON(!PageCompound(page)); -+#else - WARN_ON(!PageCompound(page)); -+#endif - return page_size(page); - } - -@@ -4875,7 +4997,7 @@ enum slab_stat_type { - #define SO_TOTAL (1 << SL_TOTAL) - - #ifdef CONFIG_MEMCG --static bool memcg_sysfs_enabled = IS_ENABLED(CONFIG_SLUB_MEMCG_SYSFS_ON); -+static bool memcg_sysfs_enabled __ro_after_init = IS_ENABLED(CONFIG_SLUB_MEMCG_SYSFS_ON); - - static int __init setup_slub_memcg_sysfs(char *str) - { -diff --git a/mm/swap.c b/mm/swap.c -index 47a47681c86b..762095d95092 100644 ---- a/mm/swap.c -+++ b/mm/swap.c -@@ -102,6 +102,8 @@ static void __put_single_page(struct page *page) - - static void __put_compound_page(struct page *page) - { -+ compound_page_dtor *dtor; -+ - /* - * __page_cache_release() is supposed to be called for thp, not for - * hugetlb. This is because hugetlb page does never have PageLRU set -@@ -110,7 +112,15 @@ static void __put_compound_page(struct page *page) - */ - if (!PageHuge(page)) - __page_cache_release(page); -- destroy_compound_page(page); -+ dtor = get_compound_page_dtor(page); -+ if (!PageHuge(page)) -+ BUG_ON(dtor != free_compound_page -+#ifdef CONFIG_TRANSPARENT_HUGEPAGE -+ && dtor != free_transhuge_page -+#endif -+ ); -+ -+ (*dtor)(page); - } - - void __put_page(struct page *page) -diff --git a/mm/util.c b/mm/util.c -index 4ddb6e186dd5..62ed34dfceb7 100644 ---- a/mm/util.c -+++ b/mm/util.c -@@ -336,9 +336,9 @@ unsigned long arch_randomize_brk(struct mm_struct *mm) - { - /* Is the current task 32bit ? */ - if (!IS_ENABLED(CONFIG_64BIT) || is_compat_task()) -- return randomize_page(mm->brk, SZ_32M); -+ return mm->brk + get_random_long() % SZ_32M + PAGE_SIZE; - -- return randomize_page(mm->brk, SZ_1G); -+ return mm->brk + get_random_long() % SZ_1G + PAGE_SIZE; - } - - unsigned long arch_mmap_rnd(void) -diff --git a/net/core/dev.c b/net/core/dev.c -index 0c9ce36afc8c..c77d2c765b03 100644 ---- a/net/core/dev.c -+++ b/net/core/dev.c -@@ -4870,7 +4870,7 @@ int netif_rx_any_context(struct sk_buff *skb) - } - EXPORT_SYMBOL(netif_rx_any_context); - --static __latent_entropy void net_tx_action(struct softirq_action *h) -+static __latent_entropy void net_tx_action(void) - { - struct softnet_data *sd = this_cpu_ptr(&softnet_data); - -@@ -6838,7 +6838,7 @@ static int napi_poll(struct napi_struct *n, struct list_head *repoll) - return work; - } - --static __latent_entropy void net_rx_action(struct softirq_action *h) -+static __latent_entropy void net_rx_action(void) - { - struct softnet_data *sd = this_cpu_ptr(&softnet_data); - unsigned long time_limit = jiffies + -diff --git a/net/dccp/ccids/ccid2.c b/net/dccp/ccids/ccid2.c -index 3da1f77bd039..dbca1f1e2449 100644 ---- a/net/dccp/ccids/ccid2.c -+++ b/net/dccp/ccids/ccid2.c -@@ -126,21 +126,26 @@ static void dccp_tasklet_schedule(struct sock *sk) - - static void ccid2_hc_tx_rto_expire(struct timer_list *t) - { -- struct ccid2_hc_tx_sock *hc = from_timer(hc, t, tx_rtotimer); -- struct sock *sk = hc->sk; -- const bool sender_was_blocked = ccid2_cwnd_network_limited(hc); -+ struct dccp_sock *dp = from_timer(dp, t, dccps_ccid_timer); -+ struct sock *sk = (struct sock *)dp; -+ struct ccid2_hc_tx_sock *hc; -+ bool sender_was_blocked; - - bh_lock_sock(sk); -+ -+ if (inet_sk_state_load(sk) == DCCP_CLOSED) -+ goto out; -+ -+ hc = ccid_priv(dp->dccps_hc_tx_ccid); -+ sender_was_blocked = ccid2_cwnd_network_limited(hc); -+ - if (sock_owned_by_user(sk)) { -- sk_reset_timer(sk, &hc->tx_rtotimer, jiffies + HZ / 5); -+ sk_reset_timer(sk, &dp->dccps_ccid_timer, jiffies + HZ / 5); - goto out; - } - - ccid2_pr_debug("RTO_EXPIRE\n"); - -- if (sk->sk_state == DCCP_CLOSED) -- goto out; -- - /* back-off timer */ - hc->tx_rto <<= 1; - if (hc->tx_rto > DCCP_RTO_MAX) -@@ -166,7 +171,7 @@ static void ccid2_hc_tx_rto_expire(struct timer_list *t) - if (sender_was_blocked) - dccp_tasklet_schedule(sk); - /* restart backed-off timer */ -- sk_reset_timer(sk, &hc->tx_rtotimer, jiffies + hc->tx_rto); -+ sk_reset_timer(sk, &dp->dccps_ccid_timer, jiffies + hc->tx_rto); - out: - bh_unlock_sock(sk); - sock_put(sk); -@@ -330,7 +335,7 @@ static void ccid2_hc_tx_packet_sent(struct sock *sk, unsigned int len) - } - #endif - -- sk_reset_timer(sk, &hc->tx_rtotimer, jiffies + hc->tx_rto); -+ sk_reset_timer(sk, &dp->dccps_ccid_timer, jiffies + hc->tx_rto); - - #ifdef CONFIG_IP_DCCP_CCID2_DEBUG - do { -@@ -700,9 +705,9 @@ static void ccid2_hc_tx_packet_recv(struct sock *sk, struct sk_buff *skb) - - /* restart RTO timer if not all outstanding data has been acked */ - if (hc->tx_pipe == 0) -- sk_stop_timer(sk, &hc->tx_rtotimer); -+ sk_stop_timer(sk, &dp->dccps_ccid_timer); - else -- sk_reset_timer(sk, &hc->tx_rtotimer, jiffies + hc->tx_rto); -+ sk_reset_timer(sk, &dp->dccps_ccid_timer, jiffies + hc->tx_rto); - done: - /* check if incoming Acks allow pending packets to be sent */ - if (sender_was_blocked && !ccid2_cwnd_network_limited(hc)) -@@ -737,17 +742,18 @@ static int ccid2_hc_tx_init(struct ccid *ccid, struct sock *sk) - hc->tx_last_cong = hc->tx_lsndtime = hc->tx_cwnd_stamp = ccid2_jiffies32; - hc->tx_cwnd_used = 0; - hc->sk = sk; -- timer_setup(&hc->tx_rtotimer, ccid2_hc_tx_rto_expire, 0); -+ timer_setup(&dp->dccps_ccid_timer, ccid2_hc_tx_rto_expire, 0); - INIT_LIST_HEAD(&hc->tx_av_chunks); - return 0; - } - - static void ccid2_hc_tx_exit(struct sock *sk) - { -+ struct dccp_sock *dp = dccp_sk(sk); - struct ccid2_hc_tx_sock *hc = ccid2_hc_tx_sk(sk); - int i; - -- sk_stop_timer(sk, &hc->tx_rtotimer); -+ sk_stop_timer(sk, &dp->dccps_ccid_timer); - - for (i = 0; i < hc->tx_seqbufc; i++) - kfree(hc->tx_seqbuf[i]); -diff --git a/net/dccp/ccids/ccid3.c b/net/dccp/ccids/ccid3.c -index b9ee1a4a8955..685f4d046c0d 100644 ---- a/net/dccp/ccids/ccid3.c -+++ b/net/dccp/ccids/ccid3.c -@@ -184,17 +184,24 @@ static inline void ccid3_hc_tx_update_win_count(struct ccid3_hc_tx_sock *hc, - - static void ccid3_hc_tx_no_feedback_timer(struct timer_list *t) - { -- struct ccid3_hc_tx_sock *hc = from_timer(hc, t, tx_no_feedback_timer); -- struct sock *sk = hc->sk; -+ struct dccp_sock *dp = from_timer(dp, t, dccps_ccid_timer); -+ struct ccid3_hc_tx_sock *hc; -+ struct sock *sk = (struct sock *)dp; - unsigned long t_nfb = USEC_PER_SEC / 5; - - bh_lock_sock(sk); -+ -+ if (inet_sk_state_load(sk) == DCCP_CLOSED) -+ goto out; -+ - if (sock_owned_by_user(sk)) { - /* Try again later. */ - /* XXX: set some sensible MIB */ - goto restart_timer; - } - -+ hc = ccid_priv(dp->dccps_hc_tx_ccid); -+ - ccid3_pr_debug("%s(%p, state=%s) - entry\n", dccp_role(sk), sk, - ccid3_tx_state_name(hc->tx_state)); - -@@ -250,8 +257,8 @@ static void ccid3_hc_tx_no_feedback_timer(struct timer_list *t) - t_nfb = max(hc->tx_t_rto, 2 * hc->tx_t_ipi); - - restart_timer: -- sk_reset_timer(sk, &hc->tx_no_feedback_timer, -- jiffies + usecs_to_jiffies(t_nfb)); -+ sk_reset_timer(sk, &dp->dccps_ccid_timer, -+ jiffies + usecs_to_jiffies(t_nfb)); - out: - bh_unlock_sock(sk); - sock_put(sk); -@@ -280,7 +287,7 @@ static int ccid3_hc_tx_send_packet(struct sock *sk, struct sk_buff *skb) - return -EBADMSG; - - if (hc->tx_state == TFRC_SSTATE_NO_SENT) { -- sk_reset_timer(sk, &hc->tx_no_feedback_timer, (jiffies + -+ sk_reset_timer(sk, &dp->dccps_ccid_timer, (jiffies + - usecs_to_jiffies(TFRC_INITIAL_TIMEOUT))); - hc->tx_last_win_count = 0; - hc->tx_t_last_win_count = now; -@@ -354,6 +361,7 @@ static void ccid3_hc_tx_packet_sent(struct sock *sk, unsigned int len) - static void ccid3_hc_tx_packet_recv(struct sock *sk, struct sk_buff *skb) - { - struct ccid3_hc_tx_sock *hc = ccid3_hc_tx_sk(sk); -+ struct dccp_sock *dp = dccp_sk(sk); - struct tfrc_tx_hist_entry *acked; - ktime_t now; - unsigned long t_nfb; -@@ -420,7 +428,7 @@ static void ccid3_hc_tx_packet_recv(struct sock *sk, struct sk_buff *skb) - (unsigned int)(hc->tx_x >> 6)); - - /* unschedule no feedback timer */ -- sk_stop_timer(sk, &hc->tx_no_feedback_timer); -+ sk_stop_timer(sk, &dp->dccps_ccid_timer); - - /* - * As we have calculated new ipi, delta, t_nom it is possible -@@ -445,8 +453,8 @@ static void ccid3_hc_tx_packet_recv(struct sock *sk, struct sk_buff *skb) - "expire in %lu jiffies (%luus)\n", - dccp_role(sk), sk, usecs_to_jiffies(t_nfb), t_nfb); - -- sk_reset_timer(sk, &hc->tx_no_feedback_timer, -- jiffies + usecs_to_jiffies(t_nfb)); -+ sk_reset_timer(sk, &dp->dccps_ccid_timer, -+ jiffies + usecs_to_jiffies(t_nfb)); - } - - static int ccid3_hc_tx_parse_options(struct sock *sk, u8 packet_type, -@@ -488,21 +496,23 @@ static int ccid3_hc_tx_parse_options(struct sock *sk, u8 packet_type, - - static int ccid3_hc_tx_init(struct ccid *ccid, struct sock *sk) - { -+ struct dccp_sock *dp = dccp_sk(sk); - struct ccid3_hc_tx_sock *hc = ccid_priv(ccid); - - hc->tx_state = TFRC_SSTATE_NO_SENT; - hc->tx_hist = NULL; - hc->sk = sk; -- timer_setup(&hc->tx_no_feedback_timer, -+ timer_setup(&dp->dccps_ccid_timer, - ccid3_hc_tx_no_feedback_timer, 0); - return 0; - } - - static void ccid3_hc_tx_exit(struct sock *sk) - { -+ struct dccp_sock *dp = dccp_sk(sk); - struct ccid3_hc_tx_sock *hc = ccid3_hc_tx_sk(sk); - -- sk_stop_timer(sk, &hc->tx_no_feedback_timer); -+ sk_stop_timer(sk, &dp->dccps_ccid_timer); - tfrc_tx_hist_purge(&hc->tx_hist); - } - -diff --git a/net/dccp/proto.c b/net/dccp/proto.c -index 6d705d90c614..359e848dba6c 100644 ---- a/net/dccp/proto.c -+++ b/net/dccp/proto.c -@@ -279,7 +279,9 @@ int dccp_disconnect(struct sock *sk, int flags) - - dccp_clear_xmit_timers(sk); - ccid_hc_rx_delete(dp->dccps_hc_rx_ccid, sk); -+ ccid_hc_tx_delete(dp->dccps_hc_tx_ccid, sk); - dp->dccps_hc_rx_ccid = NULL; -+ dp->dccps_hc_tx_ccid = NULL; - - __skb_queue_purge(&sk->sk_receive_queue); - __skb_queue_purge(&sk->sk_write_queue); -diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig -index 87983e70f03f..d1584b4b39f9 100644 ---- a/net/ipv4/Kconfig -+++ b/net/ipv4/Kconfig -@@ -267,6 +267,7 @@ config IP_PIMSM_V2 - - config SYN_COOKIES - bool "IP: TCP syncookie support" -+ default y - help - Normal TCP/IP networking is open to an attack known as "SYN - flooding". This denial-of-service attack prevents legitimate remote -@@ -742,3 +743,26 @@ config TCP_MD5SIG - on the Internet. - - If unsure, say N. -+ -+config TCP_SIMULT_CONNECT_DEFAULT_ON -+ bool "Enable TCP simultaneous connect" -+ help -+ Enable TCP simultaneous connect that adds a weakness in Linux's strict -+ implementation of TCP that allows two clients to connect to each other -+ without either entering a listening state. The weakness allows an -+ attacker to easily prevent a client from connecting to a known server -+ provided the source port for the connection is guessed correctly. -+ -+ As the weakness could be used to prevent an antivirus or IPS from -+ fetching updates, or prevent an SSL gateway from fetching a CRL, it -+ should be eliminated by disabling this option. Though Linux is one of -+ few operating systems supporting simultaneous connect, it has no -+ legitimate use in practice and is rarely supported by firewalls. -+ -+ Disabling this may break TCP STUNT which is used by some applications -+ for NAT traversal. -+ -+ This setting can be overridden at runtime via the -+ net.ipv4.tcp_simult_connect sysctl. -+ -+ If unsure, say N. -diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c -index 08829809e88b..d06be35bacbe 100644 ---- a/net/ipv4/sysctl_net_ipv4.c -+++ b/net/ipv4/sysctl_net_ipv4.c -@@ -588,6 +588,15 @@ static struct ctl_table ipv4_table[] = { - .mode = 0644, - .proc_handler = proc_do_static_key, - }, -+ { -+ .procname = "tcp_simult_connect", -+ .data = &sysctl_tcp_simult_connect, -+ .maxlen = sizeof(int), -+ .mode = 0644, -+ .proc_handler = proc_dointvec_minmax, -+ .extra1 = SYSCTL_ZERO, -+ .extra2 = SYSCTL_ONE, -+ }, - { } - }; - -diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c -index fac5c1469cee..7c3ffb3f4002 100644 ---- a/net/ipv4/tcp_input.c -+++ b/net/ipv4/tcp_input.c -@@ -82,6 +82,7 @@ - #include <net/mptcp.h> - - int sysctl_tcp_max_orphans __read_mostly = NR_FILE; -+int sysctl_tcp_simult_connect __read_mostly = IS_ENABLED(CONFIG_TCP_SIMULT_CONNECT_DEFAULT_ON); - - #define FLAG_DATA 0x01 /* Incoming frame contained data. */ - #define FLAG_WIN_UPDATE 0x02 /* Incoming ACK was a window update. */ -@@ -6197,7 +6198,7 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb, - tcp_paws_reject(&tp->rx_opt, 0)) - goto discard_and_undo; - -- if (th->syn) { -+ if (th->syn && sysctl_tcp_simult_connect) { - /* We see SYN without ACK. It is attempt of - * simultaneous connect with crossed SYNs. - * Particularly, it can be connect to self. -diff --git a/scripts/Makefile.modpost b/scripts/Makefile.modpost -index 12a87be0fb44..f4c69e330a53 100644 ---- a/scripts/Makefile.modpost -+++ b/scripts/Makefile.modpost -@@ -47,6 +47,7 @@ MODPOST = scripts/mod/modpost \ - $(if $(CONFIG_MODVERSIONS),-m) \ - $(if $(CONFIG_MODULE_SRCVERSION_ALL),-a) \ - $(if $(CONFIG_SECTION_MISMATCH_WARN_ONLY),,-E) \ -+ $(if $(CONFIG_DEBUG_WRITABLE_FUNCTION_POINTERS_VERBOSE),-f) \ - $(if $(KBUILD_MODPOST_WARN),-w) \ - -o $@ - -diff --git a/scripts/gcc-plugins/Kconfig b/scripts/gcc-plugins/Kconfig -index ae19fb0243b9..ad78375ece5e 100644 ---- a/scripts/gcc-plugins/Kconfig -+++ b/scripts/gcc-plugins/Kconfig -@@ -53,6 +53,11 @@ config GCC_PLUGIN_LATENT_ENTROPY - is some slowdown of the boot process (about 0.5%) and fork and - irq processing. - -+ When extra_latent_entropy is passed on the kernel command line, -+ entropy will be extracted from up to the first 4GB of RAM while the -+ runtime memory allocator is being initialized. This costs even more -+ slowdown of the boot process. -+ - Note that entropy extracted this way is not cryptographically - secure! - -diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c -index e08f75aed429..649595efc541 100644 ---- a/scripts/mod/modpost.c -+++ b/scripts/mod/modpost.c -@@ -35,6 +35,8 @@ static int warn_unresolved = 0; - /* How a symbol is exported */ - static int sec_mismatch_count = 0; - static int sec_mismatch_fatal = 0; -+static int writable_fptr_count = 0; -+static int writable_fptr_verbose = 0; - /* ignore missing files */ - static int ignore_missing_files; - /* If set to 1, only warn (instead of error) about missing ns imports */ -@@ -1007,6 +1009,7 @@ enum mismatch { - ANY_EXIT_TO_ANY_INIT, - EXPORT_TO_INIT_EXIT, - EXTABLE_TO_NON_TEXT, -+ DATA_TO_TEXT - }; - - /** -@@ -1133,6 +1136,12 @@ static const struct sectioncheck sectioncheck[] = { - .good_tosec = {ALL_TEXT_SECTIONS , NULL}, - .mismatch = EXTABLE_TO_NON_TEXT, - .handler = extable_mismatch_handler, -+}, -+/* Do not reference code from writable data */ -+{ -+ .fromsec = { DATA_SECTIONS, NULL }, -+ .bad_tosec = { ALL_TEXT_SECTIONS, NULL }, -+ .mismatch = DATA_TO_TEXT - } - }; - -@@ -1320,10 +1329,10 @@ static Elf_Sym *find_elf_symbol(struct elf_info *elf, Elf64_Sword addr, - continue; - if (!is_valid_name(elf, sym)) - continue; -- if (sym->st_value == addr) -- return sym; - /* Find a symbol nearby - addr are maybe negative */ - d = sym->st_value - addr; -+ if (d == 0) -+ return sym; - if (d < 0) - d = addr - sym->st_value; - if (d < distance) { -@@ -1458,7 +1467,13 @@ static void report_sec_mismatch(const char *modname, - char *prl_from; - char *prl_to; - -- sec_mismatch_count++; -+ if (mismatch->mismatch == DATA_TO_TEXT) { -+ writable_fptr_count++; -+ if (!writable_fptr_verbose) -+ return; -+ } else { -+ sec_mismatch_count++; -+ } - - get_pretty_name(from_is_func, &from, &from_p); - get_pretty_name(to_is_func, &to, &to_p); -@@ -1580,6 +1595,12 @@ static void report_sec_mismatch(const char *modname, - fatal("There's a special handler for this mismatch type, " - "we should never get here."); - break; -+ case DATA_TO_TEXT: -+ fprintf(stderr, -+ "The %s %s:%s references\n" -+ "the %s %s:%s%s\n", -+ from, fromsec, fromsym, to, tosec, tosym, to_p); -+ break; - } - fprintf(stderr, "\n"); - } -@@ -2546,7 +2567,7 @@ int main(int argc, char **argv) - struct dump_list *dump_read_start = NULL; - struct dump_list **dump_read_iter = &dump_read_start; - -- while ((opt = getopt(argc, argv, "ei:mnT:o:awENd:")) != -1) { -+ while ((opt = getopt(argc, argv, "ei:fmnT:o:awENd:")) != -1) { - switch (opt) { - case 'e': - external_module = 1; -@@ -2557,6 +2578,9 @@ int main(int argc, char **argv) - (*dump_read_iter)->file = optarg; - dump_read_iter = &(*dump_read_iter)->next; - break; -+ case 'f': -+ writable_fptr_verbose = 1; -+ break; - case 'm': - modversions = 1; - break; -@@ -2657,6 +2681,11 @@ int main(int argc, char **argv) - } - - free(buf.p); -+ if (writable_fptr_count && !writable_fptr_verbose) -+ warn("modpost: Found %d writable function pointer%s.\n" -+ "To see full details build your kernel with:\n" -+ "'make CONFIG_DEBUG_WRITABLE_FUNCTION_POINTERS_VERBOSE=y'\n", -+ writable_fptr_count, (writable_fptr_count == 1 ? "" : "s")); - - return err; - } -diff --git a/security/Kconfig b/security/Kconfig -index 7561f6f99f1d..615205c0113b 100644 ---- a/security/Kconfig -+++ b/security/Kconfig -@@ -9,7 +9,7 @@ source "security/keys/Kconfig" - - config SECURITY_DMESG_RESTRICT - bool "Restrict unprivileged access to the kernel syslog" -- default n -+ default y - help - This enforces restrictions on unprivileged users reading the kernel - syslog via dmesg(8). -@@ -19,10 +19,34 @@ config SECURITY_DMESG_RESTRICT - - If you are unsure how to answer this question, answer N. - -+config SECURITY_PERF_EVENTS_RESTRICT -+ bool "Restrict unprivileged use of performance events" -+ depends on PERF_EVENTS -+ default y -+ help -+ If you say Y here, the kernel.perf_event_paranoid sysctl -+ will be set to 3 by default, and no unprivileged use of the -+ perf_event_open syscall will be permitted unless it is -+ changed. -+ -+config SECURITY_TIOCSTI_RESTRICT -+ bool "Restrict unprivileged use of tiocsti command injection" -+ default y -+ help -+ This enforces restrictions on unprivileged users injecting commands -+ into other processes which share a tty session using the TIOCSTI -+ ioctl. This option makes TIOCSTI use require CAP_SYS_ADMIN. -+ -+ If this option is not selected, no restrictions will be enforced -+ unless the tiocsti_restrict sysctl is explicitly set to (1). -+ -+ If you are unsure how to answer this question, answer N. -+ - config SECURITY - bool "Enable different security models" - depends on SYSFS - depends on MULTIUSER -+ default y - help - This allows you to choose different security modules to be - configured into your kernel. -@@ -48,6 +72,7 @@ config SECURITYFS - config SECURITY_NETWORK - bool "Socket and Networking Security Hooks" - depends on SECURITY -+ default y - help - This enables the socket and networking security hooks. - If enabled, a security module can use these hooks to -@@ -154,6 +179,7 @@ config HARDENED_USERCOPY - bool "Harden memory copies between kernel and userspace" - depends on HAVE_HARDENED_USERCOPY_ALLOCATOR - imply STRICT_DEVMEM -+ default y - help - This option checks for obviously wrong memory regions when - copying memory to/from the kernel (via copy_to_user() and -@@ -166,7 +192,6 @@ config HARDENED_USERCOPY - config HARDENED_USERCOPY_FALLBACK - bool "Allow usercopy whitelist violations to fallback to object size" - depends on HARDENED_USERCOPY -- default y - help - This is a temporary option that allows missing usercopy whitelists - to be discovered via a WARN() to the kernel log, instead of -@@ -191,10 +216,21 @@ config HARDENED_USERCOPY_PAGESPAN - config FORTIFY_SOURCE - bool "Harden common str/mem functions against buffer overflows" - depends on ARCH_HAS_FORTIFY_SOURCE -+ default y - help - Detect overflows of buffers in common string and memory functions - where the compiler can determine and validate the buffer sizes. - -+config FORTIFY_SOURCE_STRICT_STRING -+ bool "Harden common functions against buffer overflows" -+ depends on FORTIFY_SOURCE -+ depends on EXPERT -+ help -+ Perform stricter overflow checks catching overflows within objects -+ for common C string functions rather than only between objects. -+ -+ This is not yet intended for production use, only bug finding. -+ - config STATIC_USERMODEHELPER - bool "Force all usermode helper calls through a single binary" - help -diff --git a/security/Kconfig.hardening b/security/Kconfig.hardening -index 269967c4fc1b..7dede18f1074 100644 ---- a/security/Kconfig.hardening -+++ b/security/Kconfig.hardening -@@ -190,6 +190,7 @@ config STACKLEAK_RUNTIME_DISABLE - - config INIT_ON_ALLOC_DEFAULT_ON - bool "Enable heap memory zeroing on allocation by default" -+ default yes - help - This has the effect of setting "init_on_alloc=1" on the kernel - command line. This can be disabled with "init_on_alloc=0". -@@ -202,6 +203,7 @@ config INIT_ON_ALLOC_DEFAULT_ON - - config INIT_ON_FREE_DEFAULT_ON - bool "Enable heap memory zeroing on free by default" -+ default yes - help - This has the effect of setting "init_on_free=1" on the kernel - command line. This can be disabled with "init_on_free=0". -@@ -217,6 +219,21 @@ config INIT_ON_FREE_DEFAULT_ON - touching "cold" memory areas. Most cases see 3-5% impact. Some - synthetic workloads have measured as high as 8%. - -+config PAGE_SANITIZE_VERIFY -+ bool "Verify sanitized pages" -+ default y -+ help -+ When init_on_free is enabled, verify that newly allocated pages -+ are zeroed to detect write-after-free bugs. -+ -+config SLAB_SANITIZE_VERIFY -+ bool "Verify sanitized SLAB allocations" -+ default y -+ depends on !KASAN -+ help -+ When init_on_free is enabled, verify that newly allocated slab -+ objects are zeroed to detect write-after-free bugs. -+ - endmenu - - endmenu -diff --git a/security/selinux/Kconfig b/security/selinux/Kconfig -index 9e921fc72538..ae851a826c26 100644 ---- a/security/selinux/Kconfig -+++ b/security/selinux/Kconfig -@@ -3,7 +3,7 @@ config SECURITY_SELINUX - bool "NSA SELinux Support" - depends on SECURITY_NETWORK && AUDIT && NET && INET - select NETWORK_SECMARK -- default n -+ default y - help - This selects NSA Security-Enhanced Linux (SELinux). - You will also need a policy configuration and a labeled filesystem. -@@ -70,29 +70,6 @@ config SECURITY_SELINUX_AVC_STATS - /sys/fs/selinux/avc/cache_stats, which may be monitored via - tools such as avcstat. - --config SECURITY_SELINUX_CHECKREQPROT_VALUE -- int "NSA SELinux checkreqprot default value" -- depends on SECURITY_SELINUX -- range 0 1 -- default 0 -- help -- This option sets the default value for the 'checkreqprot' flag -- that determines whether SELinux checks the protection requested -- by the application or the protection that will be applied by the -- kernel (including any implied execute for read-implies-exec) for -- mmap and mprotect calls. If this option is set to 0 (zero), -- SELinux will default to checking the protection that will be applied -- by the kernel. If this option is set to 1 (one), SELinux will -- default to checking the protection requested by the application. -- The checkreqprot flag may be changed from the default via the -- 'checkreqprot=' boot parameter. It may also be changed at runtime -- via /sys/fs/selinux/checkreqprot if authorized by policy. -- -- WARNING: this option is deprecated and will be removed in a future -- kernel release. -- -- If you are unsure how to answer this question, answer 0. -- - config SECURITY_SELINUX_SIDTAB_HASH_BITS - int "NSA SELinux sidtab hashtable size" - depends on SECURITY_SELINUX -diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c -index 227eb8967963..a8fe132825cd 100644 ---- a/security/selinux/hooks.c -+++ b/security/selinux/hooks.c -@@ -136,21 +136,7 @@ static int __init selinux_enabled_setup(char *str) - __setup("selinux=", selinux_enabled_setup); - #endif - --static unsigned int selinux_checkreqprot_boot = -- CONFIG_SECURITY_SELINUX_CHECKREQPROT_VALUE; -- --static int __init checkreqprot_setup(char *str) --{ -- unsigned long checkreqprot; -- -- if (!kstrtoul(str, 0, &checkreqprot)) { -- selinux_checkreqprot_boot = checkreqprot ? 1 : 0; -- if (checkreqprot) -- pr_warn("SELinux: checkreqprot set to 1 via kernel parameter. This is deprecated and will be rejected in a future kernel release.\n"); -- } -- return 1; --} --__setup("checkreqprot=", checkreqprot_setup); -+static const unsigned int selinux_checkreqprot_boot; - - /** - * selinux_secmark_enabled - Check to see if SECMARK is currently enabled -diff --git a/security/selinux/selinuxfs.c b/security/selinux/selinuxfs.c -index 2b745ae8cb98..de739d432da6 100644 ---- a/security/selinux/selinuxfs.c -+++ b/security/selinux/selinuxfs.c -@@ -724,7 +724,6 @@ static ssize_t sel_read_checkreqprot(struct file *filp, char __user *buf, - static ssize_t sel_write_checkreqprot(struct file *file, const char __user *buf, - size_t count, loff_t *ppos) - { -- struct selinux_fs_info *fsi = file_inode(file)->i_sb->s_fs_info; - char *page; - ssize_t length; - unsigned int new_value; -@@ -748,18 +747,9 @@ static ssize_t sel_write_checkreqprot(struct file *file, const char __user *buf, - return PTR_ERR(page); - - length = -EINVAL; -- if (sscanf(page, "%u", &new_value) != 1) -+ if (sscanf(page, "%u", &new_value) != 1 || new_value) - goto out; - -- if (new_value) { -- char comm[sizeof(current->comm)]; -- -- memcpy(comm, current->comm, sizeof(comm)); -- pr_warn_once("SELinux: %s (%d) set checkreqprot to 1. This is deprecated and will be rejected in a future kernel release.\n", -- comm, current->pid); -- } -- -- checkreqprot_set(fsi->state, (new_value ? 1 : 0)); - length = count; - out: - kfree(page); -diff --git a/security/yama/Kconfig b/security/yama/Kconfig -index a810304123ca..b809050b25d2 100644 ---- a/security/yama/Kconfig -+++ b/security/yama/Kconfig -@@ -2,7 +2,7 @@ - config SECURITY_YAMA - bool "Yama support" - depends on SECURITY -- default n -+ default y - help - This selects Yama, which extends DAC support with additional - system-wide security settings beyond regular Linux discretionary -diff --git a/tools/perf/Documentation/security.txt b/tools/perf/Documentation/security.txt -index 4fe3b8b1958f..a7d88cc23a70 100644 ---- a/tools/perf/Documentation/security.txt -+++ b/tools/perf/Documentation/security.txt -@@ -148,6 +148,7 @@ Perf tool provides a message similar to the one below: - >= 0: Disallow raw and ftrace function tracepoint access - >= 1: Disallow CPU event access - >= 2: Disallow kernel profiling -+ >= 3: Disallow use of any event - To make the adjusted perf_event_paranoid setting permanent preserve it - in /etc/sysctl.conf (e.g. kernel.perf_event_paranoid = <setting>) - diff --git a/sys-kernel/linux-image-redcore-lts/files/5.10-uksm-linux-hardened.patch b/sys-kernel/linux-image-redcore-lts/files/5.10-uksm.patch index f85a1de1..eacd7b69 100644 --- a/sys-kernel/linux-image-redcore-lts/files/5.10-uksm-linux-hardened.patch +++ b/sys-kernel/linux-image-redcore-lts/files/5.10-uksm.patch @@ -1,6 +1,8 @@ -diff -Nur a/Documentation/vm/uksm.txt b/Documentation/vm/uksm.txt ---- a/Documentation/vm/uksm.txt 1970-01-01 01:00:00.000000000 +0100 -+++ b/Documentation/vm/uksm.txt 2021-01-03 14:22:34.498459039 +0000 +diff --git a/Documentation/vm/uksm.txt b/Documentation/vm/uksm.txt +new file mode 100644 +index 000000000000..be19a3127001 +--- /dev/null ++++ b/Documentation/vm/uksm.txt @@ -0,0 +1,61 @@ +The Ultra Kernel Samepage Merging feature +---------------------------------------------- @@ -63,21 +65,23 @@ diff -Nur a/Documentation/vm/uksm.txt b/Documentation/vm/uksm.txt +2015-04-22 UKSM 0.1.2.4 Fix a race condition that can sometimes trigger anonying warnings. +2016-09-10 UKSM 0.1.2.5 Fix a bug in dedup ratio calculation. +2017-02-26 UKSM 0.1.2.6 Fix a bug in hugetlbpage handling and a race bug with page migration. -diff -Nur a/fs/exec.c b/fs/exec.c ---- a/fs/exec.c 2021-01-03 14:20:51.258372089 +0000 -+++ b/fs/exec.c 2021-01-03 14:23:32.755627017 +0000 -@@ -65,6 +65,7 @@ +diff --git a/fs/exec.c b/fs/exec.c +index 547a2390baf5..fc64a20db6bd 100644 +--- a/fs/exec.c ++++ b/fs/exec.c +@@ -64,6 +64,7 @@ + #include <linux/compat.h> #include <linux/vmalloc.h> #include <linux/io_uring.h> - #include <linux/random.h> +#include <linux/ksm.h> #include <linux/uaccess.h> #include <asm/mmu_context.h> -diff -Nur a/fs/proc/meminfo.c b/fs/proc/meminfo.c ---- a/fs/proc/meminfo.c 2020-12-30 10:54:29.000000000 +0000 -+++ b/fs/proc/meminfo.c 2021-01-03 14:22:34.498459039 +0000 -@@ -108,7 +108,10 @@ +diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c +index 887a5532e449..581a6762868e 100644 +--- a/fs/proc/meminfo.c ++++ b/fs/proc/meminfo.c +@@ -108,7 +108,10 @@ static int meminfo_proc_show(struct seq_file *m, void *v) #endif show_val_kb(m, "PageTables: ", global_zone_page_state(NR_PAGETABLE)); @@ -89,10 +93,11 @@ diff -Nur a/fs/proc/meminfo.c b/fs/proc/meminfo.c show_val_kb(m, "NFS_Unstable: ", 0); show_val_kb(m, "Bounce: ", global_zone_page_state(NR_BOUNCE)); -diff -Nur a/include/linux/ksm.h b/include/linux/ksm.h ---- a/include/linux/ksm.h 2020-12-30 10:54:29.000000000 +0000 -+++ b/include/linux/ksm.h 2021-01-03 14:22:34.498459039 +0000 -@@ -21,20 +21,16 @@ +diff --git a/include/linux/ksm.h b/include/linux/ksm.h +index 161e8164abcf..f0dbdf3c986a 100644 +--- a/include/linux/ksm.h ++++ b/include/linux/ksm.h +@@ -21,20 +21,16 @@ struct mem_cgroup; #ifdef CONFIG_KSM int ksm_madvise(struct vm_area_struct *vma, unsigned long start, unsigned long end, int advice, unsigned long *vm_flags); @@ -118,7 +123,7 @@ diff -Nur a/include/linux/ksm.h b/include/linux/ksm.h } /* -@@ -54,6 +50,33 @@ +@@ -54,6 +50,33 @@ struct page *ksm_might_need_to_copy(struct page *page, void rmap_walk_ksm(struct page *page, struct rmap_walk_control *rwc); void ksm_migrate_page(struct page *newpage, struct page *oldpage); @@ -152,17 +157,18 @@ diff -Nur a/include/linux/ksm.h b/include/linux/ksm.h #else /* !CONFIG_KSM */ static inline int ksm_fork(struct mm_struct *mm, struct mm_struct *oldmm) -@@ -89,4 +112,6 @@ +@@ -89,4 +112,6 @@ static inline void ksm_migrate_page(struct page *newpage, struct page *oldpage) #endif /* CONFIG_MMU */ #endif /* !CONFIG_KSM */ +#include <linux/uksm.h> + #endif /* __LINUX_KSM_H */ -diff -Nur a/include/linux/mm_types.h b/include/linux/mm_types.h ---- a/include/linux/mm_types.h 2020-12-30 10:54:29.000000000 +0000 -+++ b/include/linux/mm_types.h 2021-01-03 14:22:34.498459039 +0000 -@@ -372,6 +372,9 @@ +diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h +index 5a9238f6caad..5dd1ccf5cb69 100644 +--- a/include/linux/mm_types.h ++++ b/include/linux/mm_types.h +@@ -371,6 +371,9 @@ struct vm_area_struct { struct mempolicy *vm_policy; /* NUMA policy for the VMA */ #endif struct vm_userfaultfd_ctx vm_userfaultfd_ctx; @@ -172,10 +178,11 @@ diff -Nur a/include/linux/mm_types.h b/include/linux/mm_types.h } __randomize_layout; struct core_thread { -diff -Nur a/include/linux/mmzone.h b/include/linux/mmzone.h ---- a/include/linux/mmzone.h 2020-12-30 10:54:29.000000000 +0000 -+++ b/include/linux/mmzone.h 2021-01-03 14:22:34.498459039 +0000 -@@ -159,6 +159,9 @@ +diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h +index fb3bf696c05e..e4477c3a9a4b 100644 +--- a/include/linux/mmzone.h ++++ b/include/linux/mmzone.h +@@ -159,6 +159,9 @@ enum zone_stat_item { NR_ZSPAGES, /* allocated in zsmalloc */ #endif NR_FREE_CMA_PAGES, @@ -185,10 +192,11 @@ diff -Nur a/include/linux/mmzone.h b/include/linux/mmzone.h NR_VM_ZONE_STAT_ITEMS }; enum node_stat_item { -diff -Nur a/include/linux/pgtable.h b/include/linux/pgtable.h ---- a/include/linux/pgtable.h 2020-12-30 10:54:29.000000000 +0000 -+++ b/include/linux/pgtable.h 2021-01-03 14:22:34.498459039 +0000 -@@ -1060,12 +1060,25 @@ +diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h +index e237004d498d..092cdfb7090b 100644 +--- a/include/linux/pgtable.h ++++ b/include/linux/pgtable.h +@@ -1060,12 +1060,25 @@ extern void untrack_pfn(struct vm_area_struct *vma, unsigned long pfn, extern void untrack_pfn_moved(struct vm_area_struct *vma); #endif @@ -215,7 +223,7 @@ diff -Nur a/include/linux/pgtable.h b/include/linux/pgtable.h } #define my_zero_pfn(addr) page_to_pfn(ZERO_PAGE(addr)) -@@ -1074,7 +1087,7 @@ +@@ -1074,7 +1087,7 @@ static inline int is_zero_pfn(unsigned long pfn) static inline int is_zero_pfn(unsigned long pfn) { extern unsigned long zero_pfn; @@ -224,9 +232,11 @@ diff -Nur a/include/linux/pgtable.h b/include/linux/pgtable.h } static inline unsigned long my_zero_pfn(unsigned long addr) -diff -Nur a/include/linux/sradix-tree.h b/include/linux/sradix-tree.h ---- a/include/linux/sradix-tree.h 1970-01-01 01:00:00.000000000 +0100 -+++ b/include/linux/sradix-tree.h 2021-01-03 14:22:34.498459039 +0000 +diff --git a/include/linux/sradix-tree.h b/include/linux/sradix-tree.h +new file mode 100644 +index 000000000000..d71edba6b63f +--- /dev/null ++++ b/include/linux/sradix-tree.h @@ -0,0 +1,77 @@ +#ifndef _LINUX_SRADIX_TREE_H +#define _LINUX_SRADIX_TREE_H @@ -305,9 +315,11 @@ diff -Nur a/include/linux/sradix-tree.h b/include/linux/sradix-tree.h +extern void *sradix_tree_lookup(struct sradix_tree_root *root, unsigned long index); + +#endif /* _LINUX_SRADIX_TREE_H */ -diff -Nur a/include/linux/uksm.h b/include/linux/uksm.h ---- a/include/linux/uksm.h 1970-01-01 01:00:00.000000000 +0100 -+++ b/include/linux/uksm.h 2021-01-03 14:22:34.498459039 +0000 +diff --git a/include/linux/uksm.h b/include/linux/uksm.h +new file mode 100644 +index 000000000000..bb8651f534f2 +--- /dev/null ++++ b/include/linux/uksm.h @@ -0,0 +1,149 @@ +#ifndef __LINUX_UKSM_H +#define __LINUX_UKSM_H @@ -458,10 +470,11 @@ diff -Nur a/include/linux/uksm.h b/include/linux/uksm.h +} +#endif /* !CONFIG_UKSM */ +#endif /* __LINUX_UKSM_H */ -diff -Nur a/kernel/fork.c b/kernel/fork.c ---- a/kernel/fork.c 2021-01-03 14:20:51.263372191 +0000 -+++ b/kernel/fork.c 2021-01-03 14:22:34.499459059 +0000 -@@ -588,7 +588,7 @@ +diff --git a/kernel/fork.c b/kernel/fork.c +index 6d266388d380..bb52f8731dd6 100644 +--- a/kernel/fork.c ++++ b/kernel/fork.c +@@ -587,7 +587,7 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm, __vma_link_rb(mm, tmp, rb_link, rb_parent); rb_link = &tmp->vm_rb.rb_right; rb_parent = &tmp->vm_rb; @@ -470,10 +483,11 @@ diff -Nur a/kernel/fork.c b/kernel/fork.c mm->map_count++; if (!(tmp->vm_flags & VM_WIPEONFORK)) retval = copy_page_range(tmp, mpnt); -diff -Nur a/lib/Makefile b/lib/Makefile ---- a/lib/Makefile 2020-12-30 10:54:29.000000000 +0000 -+++ b/lib/Makefile 2021-01-03 14:22:34.499459059 +0000 -@@ -31,7 +31,7 @@ +diff --git a/lib/Makefile b/lib/Makefile +index d415fc7067c5..e4045ebec8cd 100644 +--- a/lib/Makefile ++++ b/lib/Makefile +@@ -31,7 +31,7 @@ endif KCSAN_SANITIZE_random32.o := n lib-y := ctype.o string.o vsprintf.o cmdline.o \ @@ -482,9 +496,11 @@ diff -Nur a/lib/Makefile b/lib/Makefile idr.o extable.o sha1.o irq_regs.o argv_split.o \ flex_proportions.o ratelimit.o show_mem.o \ is_single_threaded.o plist.o decompress.o kobject_uevent.o \ -diff -Nur a/lib/sradix-tree.c b/lib/sradix-tree.c ---- a/lib/sradix-tree.c 1970-01-01 01:00:00.000000000 +0100 -+++ b/lib/sradix-tree.c 2021-01-03 14:22:34.499459059 +0000 +diff --git a/lib/sradix-tree.c b/lib/sradix-tree.c +new file mode 100644 +index 000000000000..ab21e6309b93 +--- /dev/null ++++ b/lib/sradix-tree.c @@ -0,0 +1,476 @@ +#include <linux/errno.h> +#include <linux/mm.h> @@ -962,10 +978,11 @@ diff -Nur a/lib/sradix-tree.c b/lib/sradix-tree.c + + return 0; +} -diff -Nur a/mm/Kconfig b/mm/Kconfig ---- a/mm/Kconfig 2021-01-03 14:20:51.266372252 +0000 -+++ b/mm/Kconfig 2021-01-03 14:22:34.499459059 +0000 -@@ -317,6 +317,32 @@ +diff --git a/mm/Kconfig b/mm/Kconfig +index 390165ffbb0f..50d02cfa0b68 100644 +--- a/mm/Kconfig ++++ b/mm/Kconfig +@@ -317,6 +317,32 @@ config KSM See Documentation/vm/ksm.rst for more information: KSM is inactive until a program has madvised that an area is MADV_MERGEABLE, and root has set /sys/kernel/mm/ksm/run to 1 (if CONFIG_SYSFS is set). @@ -998,10 +1015,25 @@ diff -Nur a/mm/Kconfig b/mm/Kconfig config DEFAULT_MMAP_MIN_ADDR int "Low address space to protect from user allocation" -diff -Nur a/mm/ksm.c b/mm/ksm.c ---- a/mm/ksm.c 2020-12-30 10:54:29.000000000 +0000 -+++ b/mm/ksm.c 2021-01-03 14:22:34.499459059 +0000 -@@ -858,17 +858,6 @@ +diff --git a/mm/Makefile b/mm/Makefile +index d73aed0fc99c..d6612b76c5da 100644 +--- a/mm/Makefile ++++ b/mm/Makefile +@@ -76,7 +76,8 @@ obj-$(CONFIG_SPARSEMEM) += sparse.o + obj-$(CONFIG_SPARSEMEM_VMEMMAP) += sparse-vmemmap.o + obj-$(CONFIG_SLOB) += slob.o + obj-$(CONFIG_MMU_NOTIFIER) += mmu_notifier.o +-obj-$(CONFIG_KSM) += ksm.o ++obj-$(CONFIG_KSM_LEGACY) += ksm.o ++obj-$(CONFIG_UKSM) += uksm.o + obj-$(CONFIG_PAGE_POISONING) += page_poison.o + obj-$(CONFIG_SLAB) += slab.o + obj-$(CONFIG_SLUB) += slub.o +diff --git a/mm/ksm.c b/mm/ksm.c +index 0960750bb316..ae17158cb67a 100644 +--- a/mm/ksm.c ++++ b/mm/ksm.c +@@ -858,17 +858,6 @@ static int unmerge_ksm_pages(struct vm_area_struct *vma, return err; } @@ -1019,23 +1051,11 @@ diff -Nur a/mm/ksm.c b/mm/ksm.c #ifdef CONFIG_SYSFS /* * Only called through the sysfs control interface: -diff -Nur a/mm/Makefile b/mm/Makefile ---- a/mm/Makefile 2020-12-30 10:54:29.000000000 +0000 -+++ b/mm/Makefile 2021-01-03 14:22:34.499459059 +0000 -@@ -76,7 +76,8 @@ - obj-$(CONFIG_SPARSEMEM_VMEMMAP) += sparse-vmemmap.o - obj-$(CONFIG_SLOB) += slob.o - obj-$(CONFIG_MMU_NOTIFIER) += mmu_notifier.o --obj-$(CONFIG_KSM) += ksm.o -+obj-$(CONFIG_KSM_LEGACY) += ksm.o -+obj-$(CONFIG_UKSM) += uksm.o - obj-$(CONFIG_PAGE_POISONING) += page_poison.o - obj-$(CONFIG_SLAB) += slab.o - obj-$(CONFIG_SLUB) += slub.o -diff -Nur a/mm/memory.c b/mm/memory.c ---- a/mm/memory.c 2020-12-30 10:54:29.000000000 +0000 -+++ b/mm/memory.c 2021-01-03 14:22:34.500459079 +0000 -@@ -146,6 +146,25 @@ +diff --git a/mm/memory.c b/mm/memory.c +index c48f8df6e502..db47ee177008 100644 +--- a/mm/memory.c ++++ b/mm/memory.c +@@ -146,6 +146,25 @@ EXPORT_SYMBOL(zero_pfn); unsigned long highest_memmap_pfn __read_mostly; @@ -1061,7 +1081,7 @@ diff -Nur a/mm/memory.c b/mm/memory.c /* * CONFIG_MMU architectures set up ZERO_PAGE in their paging_init() */ -@@ -161,6 +180,7 @@ +@@ -161,6 +180,7 @@ void mm_trace_rss_stat(struct mm_struct *mm, int member, long count) trace_rss_stat(mm, member, count); } @@ -1069,7 +1089,7 @@ diff -Nur a/mm/memory.c b/mm/memory.c #if defined(SPLIT_RSS_COUNTING) void sync_mm_rss(struct mm_struct *mm) -@@ -869,6 +889,11 @@ +@@ -869,6 +889,11 @@ copy_present_pte(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, get_page(page); page_dup_rmap(page, false); rss[mm_counter(page)]++; @@ -1081,7 +1101,7 @@ diff -Nur a/mm/memory.c b/mm/memory.c } /* -@@ -1248,8 +1273,10 @@ +@@ -1237,8 +1262,10 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb, ptent = ptep_get_and_clear_full(mm, addr, pte, tlb->fullmm); tlb_remove_tlb_entry(tlb, pte, addr); @@ -1093,7 +1113,7 @@ diff -Nur a/mm/memory.c b/mm/memory.c if (!PageAnon(page)) { if (pte_dirty(ptent)) { -@@ -2597,6 +2624,7 @@ +@@ -2586,6 +2613,7 @@ static inline bool cow_user_page(struct page *dst, struct page *src, if (likely(src)) { copy_user_highpage(dst, src, addr, vma); @@ -1101,7 +1121,7 @@ diff -Nur a/mm/memory.c b/mm/memory.c return true; } -@@ -2843,6 +2871,7 @@ +@@ -2832,6 +2860,7 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf) vmf->address); if (!new_page) goto oom; @@ -1109,7 +1129,7 @@ diff -Nur a/mm/memory.c b/mm/memory.c } else { new_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, vmf->address); -@@ -2885,7 +2914,9 @@ +@@ -2874,7 +2903,9 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf) mm_counter_file(old_page)); inc_mm_counter_fast(mm, MM_ANONPAGES); } @@ -1119,9 +1139,10 @@ diff -Nur a/mm/memory.c b/mm/memory.c inc_mm_counter_fast(mm, MM_ANONPAGES); } flush_cache_page(vma, vmf->address, pte_pfn(vmf->orig_pte)); -diff -Nur a/mm/mmap.c b/mm/mmap.c ---- a/mm/mmap.c 2021-01-03 14:20:51.267372272 +0000 -+++ b/mm/mmap.c 2021-01-03 14:22:34.500459079 +0000 +diff --git a/mm/mmap.c b/mm/mmap.c +index 5c8b4485860d..b8dd56dd900d 100644 +--- a/mm/mmap.c ++++ b/mm/mmap.c @@ -46,6 +46,7 @@ #include <linux/moduleparam.h> #include <linux/pkeys.h> @@ -1130,7 +1151,7 @@ diff -Nur a/mm/mmap.c b/mm/mmap.c #include <linux/sched/mm.h> #include <linux/uaccess.h> -@@ -181,6 +182,7 @@ +@@ -181,6 +182,7 @@ static struct vm_area_struct *remove_vma(struct vm_area_struct *vma) if (vma->vm_file) fput(vma->vm_file); mpol_put(vma_policy(vma)); @@ -1138,7 +1159,7 @@ diff -Nur a/mm/mmap.c b/mm/mmap.c vm_area_free(vma); return next; } -@@ -757,9 +759,16 @@ +@@ -750,9 +752,16 @@ int __vma_adjust(struct vm_area_struct *vma, unsigned long start, long adjust_next = 0; int remove_next = 0; @@ -1155,7 +1176,7 @@ diff -Nur a/mm/mmap.c b/mm/mmap.c if (end >= next->vm_end) { /* * vma expands, overlapping all the next, and -@@ -890,6 +899,7 @@ +@@ -883,6 +892,7 @@ int __vma_adjust(struct vm_area_struct *vma, unsigned long start, end_changed = true; } vma->vm_pgoff = pgoff; @@ -1163,7 +1184,7 @@ diff -Nur a/mm/mmap.c b/mm/mmap.c if (adjust_next) { next->vm_start += adjust_next; next->vm_pgoff += adjust_next >> PAGE_SHIFT; -@@ -994,6 +1004,7 @@ +@@ -987,6 +997,7 @@ int __vma_adjust(struct vm_area_struct *vma, unsigned long start, if (remove_next == 2) { remove_next = 1; end = next->vm_end; @@ -1171,7 +1192,7 @@ diff -Nur a/mm/mmap.c b/mm/mmap.c goto again; } else if (next) -@@ -1020,10 +1031,14 @@ +@@ -1013,10 +1024,14 @@ int __vma_adjust(struct vm_area_struct *vma, unsigned long start, */ VM_WARN_ON(mm->highest_vm_end != vm_end_gap(vma)); } @@ -1186,7 +1207,7 @@ diff -Nur a/mm/mmap.c b/mm/mmap.c validate_mm(mm); return 0; -@@ -1479,6 +1494,9 @@ +@@ -1472,6 +1487,9 @@ unsigned long do_mmap(struct file *file, unsigned long addr, vm_flags = calc_vm_prot_bits(prot, pkey) | calc_vm_flag_bits(flags) | mm->def_flags | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC; @@ -1196,7 +1217,7 @@ diff -Nur a/mm/mmap.c b/mm/mmap.c if (flags & MAP_LOCKED) if (!can_do_mlock()) return -EPERM; -@@ -1874,6 +1892,7 @@ +@@ -1867,6 +1885,7 @@ unsigned long mmap_region(struct file *file, unsigned long addr, allow_write_access(file); } file = vma->vm_file; @@ -1204,7 +1225,7 @@ diff -Nur a/mm/mmap.c b/mm/mmap.c out: perf_event_mmap(vma); -@@ -1916,6 +1935,7 @@ +@@ -1909,6 +1928,7 @@ unsigned long mmap_region(struct file *file, unsigned long addr, if (vm_flags & VM_DENYWRITE) allow_write_access(file); free_vma: @@ -1212,7 +1233,7 @@ diff -Nur a/mm/mmap.c b/mm/mmap.c vm_area_free(vma); unacct_error: if (charged) -@@ -2775,6 +2795,8 @@ +@@ -2768,6 +2788,8 @@ int __split_vma(struct mm_struct *mm, struct vm_area_struct *vma, else err = vma_adjust(vma, vma->vm_start, addr, vma->vm_pgoff, new); @@ -1221,7 +1242,7 @@ diff -Nur a/mm/mmap.c b/mm/mmap.c /* Success. */ if (!err) return 0; -@@ -3082,6 +3104,7 @@ +@@ -3075,6 +3097,7 @@ static int do_brk_flags(unsigned long addr, unsigned long len, unsigned long fla if ((flags & (~VM_EXEC)) != 0) return -EINVAL; flags |= VM_DATA_DEFAULT_FLAGS | VM_ACCOUNT | mm->def_flags; @@ -1229,7 +1250,7 @@ diff -Nur a/mm/mmap.c b/mm/mmap.c mapped_addr = get_unmapped_area(NULL, addr, len, 0, MAP_FIXED); if (IS_ERR_VALUE(mapped_addr)) -@@ -3127,6 +3150,7 @@ +@@ -3120,6 +3143,7 @@ static int do_brk_flags(unsigned long addr, unsigned long len, unsigned long fla vma->vm_flags = flags; vma->vm_page_prot = vm_get_page_prot(flags); vma_link(mm, vma, prev, rb_link, rb_parent); @@ -1237,7 +1258,7 @@ diff -Nur a/mm/mmap.c b/mm/mmap.c out: perf_event_mmap(vma); mm->total_vm += len >> PAGE_SHIFT; -@@ -3204,6 +3228,12 @@ +@@ -3197,6 +3221,12 @@ void exit_mmap(struct mm_struct *mm) mmap_write_unlock(mm); } @@ -1250,7 +1271,7 @@ diff -Nur a/mm/mmap.c b/mm/mmap.c if (mm->locked_vm) { vma = mm->mmap; while (vma) { -@@ -3239,6 +3269,11 @@ +@@ -3232,6 +3262,11 @@ void exit_mmap(struct mm_struct *mm) cond_resched(); } vm_unacct_memory(nr_accounted); @@ -1262,7 +1283,7 @@ diff -Nur a/mm/mmap.c b/mm/mmap.c } /* Insert vm structure into process list sorted by address -@@ -3346,6 +3381,7 @@ +@@ -3339,6 +3374,7 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap, new_vma->vm_ops->open(new_vma); vma_link(mm, new_vma, prev, rb_link, rb_parent); *need_rmap_locks = false; @@ -1270,7 +1291,7 @@ diff -Nur a/mm/mmap.c b/mm/mmap.c } return new_vma; -@@ -3498,6 +3534,7 @@ +@@ -3491,6 +3527,7 @@ static struct vm_area_struct *__install_special_mapping( vm_stat_account(mm, vma->vm_flags, len >> PAGE_SHIFT); perf_event_mmap(vma); @@ -1278,9 +1299,11 @@ diff -Nur a/mm/mmap.c b/mm/mmap.c return vma; -diff -Nur a/mm/uksm.c b/mm/uksm.c ---- a/mm/uksm.c 1970-01-01 01:00:00.000000000 +0100 -+++ b/mm/uksm.c 2021-01-03 14:22:34.501459099 +0000 +diff --git a/mm/uksm.c b/mm/uksm.c +new file mode 100644 +index 000000000000..e4732c00be69 +--- /dev/null ++++ b/mm/uksm.c @@ -0,0 +1,5614 @@ +/* + * Ultra KSM. Copyright (C) 2011-2012 Nai Xia @@ -6896,10 +6919,11 @@ diff -Nur a/mm/uksm.c b/mm/uksm.c +late_initcall(uksm_init); +#endif + -diff -Nur a/mm/vmstat.c b/mm/vmstat.c ---- a/mm/vmstat.c 2020-12-30 10:54:29.000000000 +0000 -+++ b/mm/vmstat.c 2021-01-03 14:22:34.502459119 +0000 -@@ -1216,6 +1216,9 @@ +diff --git a/mm/vmstat.c b/mm/vmstat.c +index 698bc0bc18d1..b7590f4944ca 100644 +--- a/mm/vmstat.c ++++ b/mm/vmstat.c +@@ -1216,6 +1216,9 @@ const char * const vmstat_text[] = { "nr_shadow_call_stack", #endif |