From afaef01c001537fa97a25092d7f54d764dc7d8c1 Mon Sep 17 00:00:00 2001 From: Alexander Popov Date: Fri, 17 Aug 2018 01:16:58 +0300 Subject: x86/entry: Add STACKLEAK erasing the kernel stack at the end of syscalls The STACKLEAK feature (initially developed by PaX Team) has the following benefits: 1. Reduces the information that can be revealed through kernel stack leak bugs. The idea of erasing the thread stack at the end of syscalls is similar to CONFIG_PAGE_POISONING and memzero_explicit() in kernel crypto, which all comply with FDP_RIP.2 (Full Residual Information Protection) of the Common Criteria standard. 2. Blocks some uninitialized stack variable attacks (e.g. CVE-2017-17712, CVE-2010-2963). That kind of bugs should be killed by improving C compilers in future, which might take a long time. This commit introduces the code filling the used part of the kernel stack with a poison value before returning to userspace. Full STACKLEAK feature also contains the gcc plugin which comes in a separate commit. The STACKLEAK feature is ported from grsecurity/PaX. More information at: https://grsecurity.net/ https://pax.grsecurity.net/ This code is modified from Brad Spengler/PaX Team's code in the last public patch of grsecurity/PaX based on our understanding of the code. Changes or omissions from the original code are ours and don't reflect the original grsecurity/PaX code. Performance impact: Hardware: Intel Core i7-4770, 16 GB RAM Test #1: building the Linux kernel on a single core 0.91% slowdown Test #2: hackbench -s 4096 -l 2000 -g 15 -f 25 -P 4.2% slowdown So the STACKLEAK description in Kconfig includes: "The tradeoff is the performance impact: on a single CPU system kernel compilation sees a 1% slowdown, other systems and workloads may vary and you are advised to test this feature on your expected workload before deploying it". Signed-off-by: Alexander Popov Acked-by: Thomas Gleixner Reviewed-by: Dave Hansen Acked-by: Ingo Molnar Signed-off-by: Kees Cook --- kernel/Makefile | 4 ++++ kernel/fork.c | 3 +++ kernel/stackleak.c | 62 ++++++++++++++++++++++++++++++++++++++++++++++++++++++ 3 files changed, 69 insertions(+) create mode 100644 kernel/stackleak.c (limited to 'kernel') diff --git a/kernel/Makefile b/kernel/Makefile index 7a63d567fdb5..7343b3a9bff0 100644 --- a/kernel/Makefile +++ b/kernel/Makefile @@ -117,6 +117,10 @@ obj-$(CONFIG_HAS_IOMEM) += iomem.o obj-$(CONFIG_ZONE_DEVICE) += memremap.o obj-$(CONFIG_RSEQ) += rseq.o +obj-$(CONFIG_GCC_PLUGIN_STACKLEAK) += stackleak.o +KASAN_SANITIZE_stackleak.o := n +KCOV_INSTRUMENT_stackleak.o := n + $(obj)/configs.o: $(obj)/config_data.h targets += config_data.gz diff --git a/kernel/fork.c b/kernel/fork.c index d896e9ca38b0..47911e49c2b1 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -91,6 +91,7 @@ #include #include #include +#include #include #include @@ -1880,6 +1881,8 @@ static __latent_entropy struct task_struct *copy_process( if (retval) goto bad_fork_cleanup_io; + stackleak_task_init(p); + if (pid != &init_struct_pid) { pid = alloc_pid(p->nsproxy->pid_ns_for_children); if (IS_ERR(pid)) { diff --git a/kernel/stackleak.c b/kernel/stackleak.c new file mode 100644 index 000000000000..deba0d8992f9 --- /dev/null +++ b/kernel/stackleak.c @@ -0,0 +1,62 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * This code fills the used part of the kernel stack with a poison value + * before returning to userspace. It's part of the STACKLEAK feature + * ported from grsecurity/PaX. + * + * Author: Alexander Popov + * + * STACKLEAK reduces the information which kernel stack leak bugs can + * reveal and blocks some uninitialized stack variable attacks. + */ + +#include + +asmlinkage void stackleak_erase(void) +{ + /* It would be nice not to have 'kstack_ptr' and 'boundary' on stack */ + unsigned long kstack_ptr = current->lowest_stack; + unsigned long boundary = (unsigned long)end_of_stack(current); + unsigned int poison_count = 0; + const unsigned int depth = STACKLEAK_SEARCH_DEPTH / sizeof(unsigned long); + + /* Check that 'lowest_stack' value is sane */ + if (unlikely(kstack_ptr - boundary >= THREAD_SIZE)) + kstack_ptr = boundary; + + /* Search for the poison value in the kernel stack */ + while (kstack_ptr > boundary && poison_count <= depth) { + if (*(unsigned long *)kstack_ptr == STACKLEAK_POISON) + poison_count++; + else + poison_count = 0; + + kstack_ptr -= sizeof(unsigned long); + } + + /* + * One 'long int' at the bottom of the thread stack is reserved and + * should not be poisoned (see CONFIG_SCHED_STACK_END_CHECK=y). + */ + if (kstack_ptr == boundary) + kstack_ptr += sizeof(unsigned long); + + /* + * Now write the poison value to the kernel stack. Start from + * 'kstack_ptr' and move up till the new 'boundary'. We assume that + * the stack pointer doesn't change when we write poison. + */ + if (on_thread_stack()) + boundary = current_stack_pointer; + else + boundary = current_top_of_stack(); + + while (kstack_ptr < boundary) { + *(unsigned long *)kstack_ptr = STACKLEAK_POISON; + kstack_ptr += sizeof(unsigned long); + } + + /* Reset the 'lowest_stack' value for the next syscall */ + current->lowest_stack = current_top_of_stack() - THREAD_SIZE/64; +} + -- cgit v1.2.3-58-ga151 From 10e9ae9fabaf96c8e5227c1cd4827d58b3aa406d Mon Sep 17 00:00:00 2001 From: Alexander Popov Date: Fri, 17 Aug 2018 01:16:59 +0300 Subject: gcc-plugins: Add STACKLEAK plugin for tracking the kernel stack The STACKLEAK feature erases the kernel stack before returning from syscalls. That reduces the information which kernel stack leak bugs can reveal and blocks some uninitialized stack variable attacks. This commit introduces the STACKLEAK gcc plugin. It is needed for tracking the lowest border of the kernel stack, which is important for the code erasing the used part of the kernel stack at the end of syscalls (comes in a separate commit). The STACKLEAK feature is ported from grsecurity/PaX. More information at: https://grsecurity.net/ https://pax.grsecurity.net/ This code is modified from Brad Spengler/PaX Team's code in the last public patch of grsecurity/PaX based on our understanding of the code. Changes or omissions from the original code are ours and don't reflect the original grsecurity/PaX code. Signed-off-by: Alexander Popov Tested-by: Laura Abbott Signed-off-by: Kees Cook --- kernel/stackleak.c | 28 +++ scripts/Makefile.gcc-plugins | 10 + scripts/gcc-plugins/Kconfig | 12 + scripts/gcc-plugins/stackleak_plugin.c | 427 +++++++++++++++++++++++++++++++++ 4 files changed, 477 insertions(+) create mode 100644 scripts/gcc-plugins/stackleak_plugin.c (limited to 'kernel') diff --git a/kernel/stackleak.c b/kernel/stackleak.c index deba0d8992f9..628485db37ba 100644 --- a/kernel/stackleak.c +++ b/kernel/stackleak.c @@ -60,3 +60,31 @@ asmlinkage void stackleak_erase(void) current->lowest_stack = current_top_of_stack() - THREAD_SIZE/64; } +void __used stackleak_track_stack(void) +{ + /* + * N.B. stackleak_erase() fills the kernel stack with the poison value, + * which has the register width. That code assumes that the value + * of 'lowest_stack' is aligned on the register width boundary. + * + * That is true for x86 and x86_64 because of the kernel stack + * alignment on these platforms (for details, see 'cc_stack_align' in + * arch/x86/Makefile). Take care of that when you port STACKLEAK to + * new platforms. + */ + unsigned long sp = (unsigned long)&sp; + + /* + * Having CONFIG_STACKLEAK_TRACK_MIN_SIZE larger than + * STACKLEAK_SEARCH_DEPTH makes the poison search in + * stackleak_erase() unreliable. Let's prevent that. + */ + BUILD_BUG_ON(CONFIG_STACKLEAK_TRACK_MIN_SIZE > STACKLEAK_SEARCH_DEPTH); + + if (sp < current->lowest_stack && + sp >= (unsigned long)task_stack_page(current) + + sizeof(unsigned long)) { + current->lowest_stack = sp; + } +} +EXPORT_SYMBOL(stackleak_track_stack); diff --git a/scripts/Makefile.gcc-plugins b/scripts/Makefile.gcc-plugins index 0a482f341576..46c5c6809806 100644 --- a/scripts/Makefile.gcc-plugins +++ b/scripts/Makefile.gcc-plugins @@ -26,6 +26,16 @@ gcc-plugin-cflags-$(CONFIG_GCC_PLUGIN_RANDSTRUCT) \ gcc-plugin-cflags-$(CONFIG_GCC_PLUGIN_RANDSTRUCT_PERFORMANCE) \ += -fplugin-arg-randomize_layout_plugin-performance-mode +gcc-plugin-$(CONFIG_GCC_PLUGIN_STACKLEAK) += stackleak_plugin.so +gcc-plugin-cflags-$(CONFIG_GCC_PLUGIN_STACKLEAK) \ + += -DSTACKLEAK_PLUGIN +gcc-plugin-cflags-$(CONFIG_GCC_PLUGIN_STACKLEAK) \ + += -fplugin-arg-stackleak_plugin-track-min-size=$(CONFIG_STACKLEAK_TRACK_MIN_SIZE) +ifdef CONFIG_GCC_PLUGIN_STACKLEAK + DISABLE_STACKLEAK_PLUGIN += -fplugin-arg-stackleak_plugin-disable +endif +export DISABLE_STACKLEAK_PLUGIN + # All the plugin CFLAGS are collected here in case a build target needs to # filter them out of the KBUILD_CFLAGS. GCC_PLUGINS_CFLAGS := $(strip $(addprefix -fplugin=$(objtree)/scripts/gcc-plugins/, $(gcc-plugin-y)) $(gcc-plugin-cflags-y)) diff --git a/scripts/gcc-plugins/Kconfig b/scripts/gcc-plugins/Kconfig index 977b84e69787..c65fdd823591 100644 --- a/scripts/gcc-plugins/Kconfig +++ b/scripts/gcc-plugins/Kconfig @@ -158,4 +158,16 @@ config GCC_PLUGIN_STACKLEAK * https://grsecurity.net/ * https://pax.grsecurity.net/ +config STACKLEAK_TRACK_MIN_SIZE + int "Minimum stack frame size of functions tracked by STACKLEAK" + default 100 + range 0 4096 + depends on GCC_PLUGIN_STACKLEAK + help + The STACKLEAK gcc plugin instruments the kernel code for tracking + the lowest border of the kernel stack (and for some other purposes). + It inserts the stackleak_track_stack() call for the functions with + a stack frame size greater than or equal to this parameter. + If unsure, leave the default value 100. + endif diff --git a/scripts/gcc-plugins/stackleak_plugin.c b/scripts/gcc-plugins/stackleak_plugin.c new file mode 100644 index 000000000000..2f48da98b5d4 --- /dev/null +++ b/scripts/gcc-plugins/stackleak_plugin.c @@ -0,0 +1,427 @@ +/* + * Copyright 2011-2017 by the PaX Team + * Modified by Alexander Popov + * Licensed under the GPL v2 + * + * Note: the choice of the license means that the compilation process is + * NOT 'eligible' as defined by gcc's library exception to the GPL v3, + * but for the kernel it doesn't matter since it doesn't link against + * any of the gcc libraries + * + * This gcc plugin is needed for tracking the lowest border of the kernel stack. + * It instruments the kernel code inserting stackleak_track_stack() calls: + * - after alloca(); + * - for the functions with a stack frame size greater than or equal + * to the "track-min-size" plugin parameter. + * + * This plugin is ported from grsecurity/PaX. For more information see: + * https://grsecurity.net/ + * https://pax.grsecurity.net/ + * + * Debugging: + * - use fprintf() to stderr, debug_generic_expr(), debug_gimple_stmt(), + * print_rtl() and print_simple_rtl(); + * - add "-fdump-tree-all -fdump-rtl-all" to the plugin CFLAGS in + * Makefile.gcc-plugins to see the verbose dumps of the gcc passes; + * - use gcc -E to understand the preprocessing shenanigans; + * - use gcc with enabled CFG/GIMPLE/SSA verification (--enable-checking). + */ + +#include "gcc-common.h" + +__visible int plugin_is_GPL_compatible; + +static int track_frame_size = -1; +static const char track_function[] = "stackleak_track_stack"; + +/* + * Mark these global variables (roots) for gcc garbage collector since + * they point to the garbage-collected memory. + */ +static GTY(()) tree track_function_decl; + +static struct plugin_info stackleak_plugin_info = { + .version = "201707101337", + .help = "track-min-size=nn\ttrack stack for functions with a stack frame size >= nn bytes\n" + "disable\t\tdo not activate the plugin\n" +}; + +static void stackleak_add_track_stack(gimple_stmt_iterator *gsi, bool after) +{ + gimple stmt; + gcall *stackleak_track_stack; + cgraph_node_ptr node; + int frequency; + basic_block bb; + + /* Insert call to void stackleak_track_stack(void) */ + stmt = gimple_build_call(track_function_decl, 0); + stackleak_track_stack = as_a_gcall(stmt); + if (after) { + gsi_insert_after(gsi, stackleak_track_stack, + GSI_CONTINUE_LINKING); + } else { + gsi_insert_before(gsi, stackleak_track_stack, GSI_SAME_STMT); + } + + /* Update the cgraph */ + bb = gimple_bb(stackleak_track_stack); + node = cgraph_get_create_node(track_function_decl); + gcc_assert(node); + frequency = compute_call_stmt_bb_frequency(current_function_decl, bb); + cgraph_create_edge(cgraph_get_node(current_function_decl), node, + stackleak_track_stack, bb->count, frequency); +} + +static bool is_alloca(gimple stmt) +{ + if (gimple_call_builtin_p(stmt, BUILT_IN_ALLOCA)) + return true; + +#if BUILDING_GCC_VERSION >= 4007 + if (gimple_call_builtin_p(stmt, BUILT_IN_ALLOCA_WITH_ALIGN)) + return true; +#endif + + return false; +} + +/* + * Work with the GIMPLE representation of the code. Insert the + * stackleak_track_stack() call after alloca() and into the beginning + * of the function if it is not instrumented. + */ +static unsigned int stackleak_instrument_execute(void) +{ + basic_block bb, entry_bb; + bool prologue_instrumented = false, is_leaf = true; + gimple_stmt_iterator gsi; + + /* + * ENTRY_BLOCK_PTR is a basic block which represents possible entry + * point of a function. This block does not contain any code and + * has a CFG edge to its successor. + */ + gcc_assert(single_succ_p(ENTRY_BLOCK_PTR_FOR_FN(cfun))); + entry_bb = single_succ(ENTRY_BLOCK_PTR_FOR_FN(cfun)); + + /* + * Loop through the GIMPLE statements in each of cfun basic blocks. + * cfun is a global variable which represents the function that is + * currently processed. + */ + FOR_EACH_BB_FN(bb, cfun) { + for (gsi = gsi_start_bb(bb); !gsi_end_p(gsi); gsi_next(&gsi)) { + gimple stmt; + + stmt = gsi_stmt(gsi); + + /* Leaf function is a function which makes no calls */ + if (is_gimple_call(stmt)) + is_leaf = false; + + if (!is_alloca(stmt)) + continue; + + /* Insert stackleak_track_stack() call after alloca() */ + stackleak_add_track_stack(&gsi, true); + if (bb == entry_bb) + prologue_instrumented = true; + } + } + + if (prologue_instrumented) + return 0; + + /* + * Special cases to skip the instrumentation. + * + * Taking the address of static inline functions materializes them, + * but we mustn't instrument some of them as the resulting stack + * alignment required by the function call ABI will break other + * assumptions regarding the expected (but not otherwise enforced) + * register clobbering ABI. + * + * Case in point: native_save_fl on amd64 when optimized for size + * clobbers rdx if it were instrumented here. + * + * TODO: any more special cases? + */ + if (is_leaf && + !TREE_PUBLIC(current_function_decl) && + DECL_DECLARED_INLINE_P(current_function_decl)) { + return 0; + } + + if (is_leaf && + !strncmp(IDENTIFIER_POINTER(DECL_NAME(current_function_decl)), + "_paravirt_", 10)) { + return 0; + } + + /* Insert stackleak_track_stack() call at the function beginning */ + bb = entry_bb; + if (!single_pred_p(bb)) { + /* gcc_assert(bb_loop_depth(bb) || + (bb->flags & BB_IRREDUCIBLE_LOOP)); */ + split_edge(single_succ_edge(ENTRY_BLOCK_PTR_FOR_FN(cfun))); + gcc_assert(single_succ_p(ENTRY_BLOCK_PTR_FOR_FN(cfun))); + bb = single_succ(ENTRY_BLOCK_PTR_FOR_FN(cfun)); + } + gsi = gsi_after_labels(bb); + stackleak_add_track_stack(&gsi, false); + + return 0; +} + +static bool large_stack_frame(void) +{ +#if BUILDING_GCC_VERSION >= 8000 + return maybe_ge(get_frame_size(), track_frame_size); +#else + return (get_frame_size() >= track_frame_size); +#endif +} + +/* + * Work with the RTL representation of the code. + * Remove the unneeded stackleak_track_stack() calls from the functions + * which don't call alloca() and don't have a large enough stack frame size. + */ +static unsigned int stackleak_cleanup_execute(void) +{ + rtx_insn *insn, *next; + + if (cfun->calls_alloca) + return 0; + + if (large_stack_frame()) + return 0; + + /* + * Find stackleak_track_stack() calls. Loop through the chain of insns, + * which is an RTL representation of the code for a function. + * + * The example of a matching insn: + * (call_insn 8 4 10 2 (call (mem (symbol_ref ("stackleak_track_stack") + * [flags 0x41] ) + * [0 stackleak_track_stack S1 A8]) (0)) 675 {*call} (expr_list + * (symbol_ref ("stackleak_track_stack") [flags 0x41] ) (expr_list (0) (nil))) (nil)) + */ + for (insn = get_insns(); insn; insn = next) { + rtx body; + + next = NEXT_INSN(insn); + + /* Check the expression code of the insn */ + if (!CALL_P(insn)) + continue; + + /* + * Check the expression code of the insn body, which is an RTL + * Expression (RTX) describing the side effect performed by + * that insn. + */ + body = PATTERN(insn); + + if (GET_CODE(body) == PARALLEL) + body = XVECEXP(body, 0, 0); + + if (GET_CODE(body) != CALL) + continue; + + /* + * Check the first operand of the call expression. It should + * be a mem RTX describing the needed subroutine with a + * symbol_ref RTX. + */ + body = XEXP(body, 0); + if (GET_CODE(body) != MEM) + continue; + + body = XEXP(body, 0); + if (GET_CODE(body) != SYMBOL_REF) + continue; + + if (SYMBOL_REF_DECL(body) != track_function_decl) + continue; + + /* Delete the stackleak_track_stack() call */ + delete_insn_and_edges(insn); +#if BUILDING_GCC_VERSION >= 4007 && BUILDING_GCC_VERSION < 8000 + if (GET_CODE(next) == NOTE && + NOTE_KIND(next) == NOTE_INSN_CALL_ARG_LOCATION) { + insn = next; + next = NEXT_INSN(insn); + delete_insn_and_edges(insn); + } +#endif + } + + return 0; +} + +static bool stackleak_gate(void) +{ + tree section; + + section = lookup_attribute("section", + DECL_ATTRIBUTES(current_function_decl)); + if (section && TREE_VALUE(section)) { + section = TREE_VALUE(TREE_VALUE(section)); + + if (!strncmp(TREE_STRING_POINTER(section), ".init.text", 10)) + return false; + if (!strncmp(TREE_STRING_POINTER(section), ".devinit.text", 13)) + return false; + if (!strncmp(TREE_STRING_POINTER(section), ".cpuinit.text", 13)) + return false; + if (!strncmp(TREE_STRING_POINTER(section), ".meminit.text", 13)) + return false; + } + + return track_frame_size >= 0; +} + +/* Build the function declaration for stackleak_track_stack() */ +static void stackleak_start_unit(void *gcc_data __unused, + void *user_data __unused) +{ + tree fntype; + + /* void stackleak_track_stack(void) */ + fntype = build_function_type_list(void_type_node, NULL_TREE); + track_function_decl = build_fn_decl(track_function, fntype); + DECL_ASSEMBLER_NAME(track_function_decl); /* for LTO */ + TREE_PUBLIC(track_function_decl) = 1; + TREE_USED(track_function_decl) = 1; + DECL_EXTERNAL(track_function_decl) = 1; + DECL_ARTIFICIAL(track_function_decl) = 1; + DECL_PRESERVE_P(track_function_decl) = 1; +} + +/* + * Pass gate function is a predicate function that gets executed before the + * corresponding pass. If the return value is 'true' the pass gets executed, + * otherwise, it is skipped. + */ +static bool stackleak_instrument_gate(void) +{ + return stackleak_gate(); +} + +#define PASS_NAME stackleak_instrument +#define PROPERTIES_REQUIRED PROP_gimple_leh | PROP_cfg +#define TODO_FLAGS_START TODO_verify_ssa | TODO_verify_flow | TODO_verify_stmts +#define TODO_FLAGS_FINISH TODO_verify_ssa | TODO_verify_stmts | TODO_dump_func \ + | TODO_update_ssa | TODO_rebuild_cgraph_edges +#include "gcc-generate-gimple-pass.h" + +static bool stackleak_cleanup_gate(void) +{ + return stackleak_gate(); +} + +#define PASS_NAME stackleak_cleanup +#define TODO_FLAGS_FINISH TODO_dump_func +#include "gcc-generate-rtl-pass.h" + +/* + * Every gcc plugin exports a plugin_init() function that is called right + * after the plugin is loaded. This function is responsible for registering + * the plugin callbacks and doing other required initialization. + */ +__visible int plugin_init(struct plugin_name_args *plugin_info, + struct plugin_gcc_version *version) +{ + const char * const plugin_name = plugin_info->base_name; + const int argc = plugin_info->argc; + const struct plugin_argument * const argv = plugin_info->argv; + int i = 0; + + /* Extra GGC root tables describing our GTY-ed data */ + static const struct ggc_root_tab gt_ggc_r_gt_stackleak[] = { + { + .base = &track_function_decl, + .nelt = 1, + .stride = sizeof(track_function_decl), + .cb = >_ggc_mx_tree_node, + .pchw = >_pch_nx_tree_node + }, + LAST_GGC_ROOT_TAB + }; + + /* + * The stackleak_instrument pass should be executed before the + * "optimized" pass, which is the control flow graph cleanup that is + * performed just before expanding gcc trees to the RTL. In former + * versions of the plugin this new pass was inserted before the + * "tree_profile" pass, which is currently called "profile". + */ + PASS_INFO(stackleak_instrument, "optimized", 1, + PASS_POS_INSERT_BEFORE); + + /* + * The stackleak_cleanup pass should be executed after the + * "reload" pass, when the stack frame size is final. + */ + PASS_INFO(stackleak_cleanup, "reload", 1, PASS_POS_INSERT_AFTER); + + if (!plugin_default_version_check(version, &gcc_version)) { + error(G_("incompatible gcc/plugin versions")); + return 1; + } + + /* Parse the plugin arguments */ + for (i = 0; i < argc; i++) { + if (!strcmp(argv[i].key, "disable")) + return 0; + + if (!strcmp(argv[i].key, "track-min-size")) { + if (!argv[i].value) { + error(G_("no value supplied for option '-fplugin-arg-%s-%s'"), + plugin_name, argv[i].key); + return 1; + } + + track_frame_size = atoi(argv[i].value); + if (track_frame_size < 0) { + error(G_("invalid option argument '-fplugin-arg-%s-%s=%s'"), + plugin_name, argv[i].key, argv[i].value); + return 1; + } + } else { + error(G_("unknown option '-fplugin-arg-%s-%s'"), + plugin_name, argv[i].key); + return 1; + } + } + + /* Give the information about the plugin */ + register_callback(plugin_name, PLUGIN_INFO, NULL, + &stackleak_plugin_info); + + /* Register to be called before processing a translation unit */ + register_callback(plugin_name, PLUGIN_START_UNIT, + &stackleak_start_unit, NULL); + + /* Register an extra GCC garbage collector (GGC) root table */ + register_callback(plugin_name, PLUGIN_REGISTER_GGC_ROOTS, NULL, + (void *)>_ggc_r_gt_stackleak); + + /* + * Hook into the Pass Manager to register new gcc passes. + * + * The stack frame size info is available only at the last RTL pass, + * when it's too late to insert complex code like a function call. + * So we register two gcc passes to instrument every function at first + * and remove the unneeded instrumentation later. + */ + register_callback(plugin_name, PLUGIN_PASS_MANAGER_SETUP, NULL, + &stackleak_instrument_pass_info); + register_callback(plugin_name, PLUGIN_PASS_MANAGER_SETUP, NULL, + &stackleak_cleanup_pass_info); + + return 0; +} -- cgit v1.2.3-58-ga151 From c8d126275a5fa59394fe17109bdb9812fed296b8 Mon Sep 17 00:00:00 2001 From: Alexander Popov Date: Fri, 17 Aug 2018 01:17:01 +0300 Subject: fs/proc: Show STACKLEAK metrics in the /proc file system Introduce CONFIG_STACKLEAK_METRICS providing STACKLEAK information about tasks via the /proc file system. In particular, /proc//stack_depth shows the maximum kernel stack consumption for the current and previous syscalls. Although this information is not precise, it can be useful for estimating the STACKLEAK performance impact for your workloads. Suggested-by: Ingo Molnar Signed-off-by: Alexander Popov Tested-by: Laura Abbott Signed-off-by: Kees Cook --- fs/proc/base.c | 18 ++++++++++++++++++ include/linux/sched.h | 1 + include/linux/stackleak.h | 3 +++ kernel/stackleak.c | 4 ++++ scripts/gcc-plugins/Kconfig | 12 ++++++++++++ 5 files changed, 38 insertions(+) (limited to 'kernel') diff --git a/fs/proc/base.c b/fs/proc/base.c index ccf86f16d9f0..2a238d68610e 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -2891,6 +2891,21 @@ static int proc_pid_patch_state(struct seq_file *m, struct pid_namespace *ns, } #endif /* CONFIG_LIVEPATCH */ +#ifdef CONFIG_STACKLEAK_METRICS +static int proc_stack_depth(struct seq_file *m, struct pid_namespace *ns, + struct pid *pid, struct task_struct *task) +{ + unsigned long prev_depth = THREAD_SIZE - + (task->prev_lowest_stack & (THREAD_SIZE - 1)); + unsigned long depth = THREAD_SIZE - + (task->lowest_stack & (THREAD_SIZE - 1)); + + seq_printf(m, "previous stack depth: %lu\nstack depth: %lu\n", + prev_depth, depth); + return 0; +} +#endif /* CONFIG_STACKLEAK_METRICS */ + /* * Thread groups */ @@ -2992,6 +3007,9 @@ static const struct pid_entry tgid_base_stuff[] = { #ifdef CONFIG_LIVEPATCH ONE("patch_state", S_IRUSR, proc_pid_patch_state), #endif +#ifdef CONFIG_STACKLEAK_METRICS + ONE("stack_depth", S_IRUGO, proc_stack_depth), +#endif }; static int proc_tgid_base_readdir(struct file *file, struct dir_context *ctx) diff --git a/include/linux/sched.h b/include/linux/sched.h index c1a23acd24e7..ae9d10e14b82 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1194,6 +1194,7 @@ struct task_struct { #ifdef CONFIG_GCC_PLUGIN_STACKLEAK unsigned long lowest_stack; + unsigned long prev_lowest_stack; #endif /* diff --git a/include/linux/stackleak.h b/include/linux/stackleak.h index 628c2b947b89..b911b973d328 100644 --- a/include/linux/stackleak.h +++ b/include/linux/stackleak.h @@ -18,6 +18,9 @@ static inline void stackleak_task_init(struct task_struct *t) { t->lowest_stack = (unsigned long)end_of_stack(t) + sizeof(unsigned long); +# ifdef CONFIG_STACKLEAK_METRICS + t->prev_lowest_stack = t->lowest_stack; +# endif } #else /* !CONFIG_GCC_PLUGIN_STACKLEAK */ static inline void stackleak_task_init(struct task_struct *t) { } diff --git a/kernel/stackleak.c b/kernel/stackleak.c index 628485db37ba..f66239572c89 100644 --- a/kernel/stackleak.c +++ b/kernel/stackleak.c @@ -41,6 +41,10 @@ asmlinkage void stackleak_erase(void) if (kstack_ptr == boundary) kstack_ptr += sizeof(unsigned long); +#ifdef CONFIG_STACKLEAK_METRICS + current->prev_lowest_stack = kstack_ptr; +#endif + /* * Now write the poison value to the kernel stack. Start from * 'kstack_ptr' and move up till the new 'boundary'. We assume that diff --git a/scripts/gcc-plugins/Kconfig b/scripts/gcc-plugins/Kconfig index c65fdd823591..b0a015ef5268 100644 --- a/scripts/gcc-plugins/Kconfig +++ b/scripts/gcc-plugins/Kconfig @@ -170,4 +170,16 @@ config STACKLEAK_TRACK_MIN_SIZE a stack frame size greater than or equal to this parameter. If unsure, leave the default value 100. +config STACKLEAK_METRICS + bool "Show STACKLEAK metrics in the /proc file system" + depends on GCC_PLUGIN_STACKLEAK + depends on PROC_FS + help + If this is set, STACKLEAK metrics for every task are available in + the /proc file system. In particular, /proc//stack_depth + shows the maximum kernel stack consumption for the current and + previous syscalls. Although this information is not precise, it + can be useful for estimating the STACKLEAK performance impact for + your workloads. + endif -- cgit v1.2.3-58-ga151 From 964c9dff0091893a9a74a88edf984c6da0b779f7 Mon Sep 17 00:00:00 2001 From: Alexander Popov Date: Fri, 17 Aug 2018 01:17:03 +0300 Subject: stackleak: Allow runtime disabling of kernel stack erasing Introduce CONFIG_STACKLEAK_RUNTIME_DISABLE option, which provides 'stack_erasing' sysctl. It can be used in runtime to control kernel stack erasing for kernels built with CONFIG_GCC_PLUGIN_STACKLEAK. Suggested-by: Ingo Molnar Signed-off-by: Alexander Popov Tested-by: Laura Abbott Signed-off-by: Kees Cook --- Documentation/sysctl/kernel.txt | 18 ++++++++++++++++++ include/linux/stackleak.h | 6 ++++++ kernel/stackleak.c | 38 ++++++++++++++++++++++++++++++++++++++ kernel/sysctl.c | 15 ++++++++++++++- scripts/gcc-plugins/Kconfig | 8 ++++++++ 5 files changed, 84 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/Documentation/sysctl/kernel.txt b/Documentation/sysctl/kernel.txt index 37a679501ddc..1b8775298cf7 100644 --- a/Documentation/sysctl/kernel.txt +++ b/Documentation/sysctl/kernel.txt @@ -89,6 +89,7 @@ show up in /proc/sys/kernel: - shmmni - softlockup_all_cpu_backtrace - soft_watchdog +- stack_erasing - stop-a [ SPARC only ] - sysrq ==> Documentation/admin-guide/sysrq.rst - sysctl_writes_strict @@ -987,6 +988,23 @@ detect a hard lockup condition. ============================================================== +stack_erasing + +This parameter can be used to control kernel stack erasing at the end +of syscalls for kernels built with CONFIG_GCC_PLUGIN_STACKLEAK. + +That erasing reduces the information which kernel stack leak bugs +can reveal and blocks some uninitialized stack variable attacks. +The tradeoff is the performance impact: on a single CPU system kernel +compilation sees a 1% slowdown, other systems and workloads may vary. + + 0: kernel stack erasing is disabled, STACKLEAK_METRICS are not updated. + + 1: kernel stack erasing is enabled (default), it is performed before + returning to the userspace at the end of syscalls. + +============================================================== + tainted: Non-zero if the kernel has been tainted. Numeric values, which can be diff --git a/include/linux/stackleak.h b/include/linux/stackleak.h index b911b973d328..3d5c3271a9a8 100644 --- a/include/linux/stackleak.h +++ b/include/linux/stackleak.h @@ -22,6 +22,12 @@ static inline void stackleak_task_init(struct task_struct *t) t->prev_lowest_stack = t->lowest_stack; # endif } + +#ifdef CONFIG_STACKLEAK_RUNTIME_DISABLE +int stack_erasing_sysctl(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos); +#endif + #else /* !CONFIG_GCC_PLUGIN_STACKLEAK */ static inline void stackleak_task_init(struct task_struct *t) { } #endif diff --git a/kernel/stackleak.c b/kernel/stackleak.c index f66239572c89..e42892926244 100644 --- a/kernel/stackleak.c +++ b/kernel/stackleak.c @@ -12,6 +12,41 @@ #include +#ifdef CONFIG_STACKLEAK_RUNTIME_DISABLE +#include +#include + +static DEFINE_STATIC_KEY_FALSE(stack_erasing_bypass); + +int stack_erasing_sysctl(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + int ret = 0; + int state = !static_branch_unlikely(&stack_erasing_bypass); + int prev_state = state; + + table->data = &state; + table->maxlen = sizeof(int); + ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); + state = !!state; + if (ret || !write || state == prev_state) + return ret; + + if (state) + static_branch_disable(&stack_erasing_bypass); + else + static_branch_enable(&stack_erasing_bypass); + + pr_warn("stackleak: kernel stack erasing is %s\n", + state ? "enabled" : "disabled"); + return ret; +} + +#define skip_erasing() static_branch_unlikely(&stack_erasing_bypass) +#else +#define skip_erasing() false +#endif /* CONFIG_STACKLEAK_RUNTIME_DISABLE */ + asmlinkage void stackleak_erase(void) { /* It would be nice not to have 'kstack_ptr' and 'boundary' on stack */ @@ -20,6 +55,9 @@ asmlinkage void stackleak_erase(void) unsigned int poison_count = 0; const unsigned int depth = STACKLEAK_SEARCH_DEPTH / sizeof(unsigned long); + if (skip_erasing()) + return; + /* Check that 'lowest_stack' value is sane */ if (unlikely(kstack_ptr - boundary >= THREAD_SIZE)) kstack_ptr = boundary; diff --git a/kernel/sysctl.c b/kernel/sysctl.c index cc02050fd0c4..3ae223f7b5df 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -91,7 +91,9 @@ #ifdef CONFIG_CHR_DEV_SG #include #endif - +#ifdef CONFIG_STACKLEAK_RUNTIME_DISABLE +#include +#endif #ifdef CONFIG_LOCKUP_DETECTOR #include #endif @@ -1232,6 +1234,17 @@ static struct ctl_table kern_table[] = { .extra1 = &zero, .extra2 = &one, }, +#endif +#ifdef CONFIG_STACKLEAK_RUNTIME_DISABLE + { + .procname = "stack_erasing", + .data = NULL, + .maxlen = sizeof(int), + .mode = 0600, + .proc_handler = stack_erasing_sysctl, + .extra1 = &zero, + .extra2 = &one, + }, #endif { } }; diff --git a/scripts/gcc-plugins/Kconfig b/scripts/gcc-plugins/Kconfig index b0a015ef5268..0d5c799688f0 100644 --- a/scripts/gcc-plugins/Kconfig +++ b/scripts/gcc-plugins/Kconfig @@ -182,4 +182,12 @@ config STACKLEAK_METRICS can be useful for estimating the STACKLEAK performance impact for your workloads. +config STACKLEAK_RUNTIME_DISABLE + bool "Allow runtime disabling of kernel stack erasing" + depends on GCC_PLUGIN_STACKLEAK + help + This option provides 'stack_erasing' sysctl, which can be used in + runtime to control kernel stack erasing for kernels built with + CONFIG_GCC_PLUGIN_STACKLEAK. + endif -- cgit v1.2.3-58-ga151