From 977c1f9c8c022d0173181766b34a0db3705265a4 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Mon, 7 Nov 2016 15:14:20 -0800 Subject: ftrace: Ignore FTRACE_FL_DISABLED while walking dyn_ftrace records ftrace_shutdown() checks for sanity of ftrace records and if dyn_ftrace->flags is not zero, it will warn. It can happen that 'flags' are set to FTRACE_FL_DISABLED at this point, since some module was loaded, but before ftrace_module_enable() cleared the flags for this module. In other words the module.c is doing: ftrace_module_init(mod); // calls ftrace_update_code() that sets flags=FTRACE_FL_DISABLED ... // here ftrace_shutdown() is called that warns, since err = prepare_coming_module(mod); // didn't have a chance to clear FTRACE_FL_DISABLED Fix it by ignoring disabled records. It's similar to what __ftrace_hash_rec_update() is already doing. Link: http://lkml.kernel.org/r/1478560460-3818619-1-git-send-email-ast@fb.com Cc: stable@vger.kernel.org Fixes: b7ffffbb46f2 "ftrace: Add infrastructure for delayed enabling of module functions" Signed-off-by: Alexei Starovoitov Signed-off-by: Steven Rostedt --- kernel/trace/ftrace.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 2050a7652a86..326498baab83 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -2763,7 +2763,7 @@ static int ftrace_shutdown(struct ftrace_ops *ops, int command) struct dyn_ftrace *rec; do_for_each_ftrace_rec(pg, rec) { - if (FTRACE_WARN_ON_ONCE(rec->flags)) + if (FTRACE_WARN_ON_ONCE(rec->flags & ~FTRACE_FL_DISABLED)) pr_warn(" %pS flags:%lx\n", (void *)rec->ip, rec->flags); } while_for_each_ftrace_rec(); -- cgit v1.2.3 From 546fece4eae871f033925ccf0ff2b740725ae915 Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Red Hat)" Date: Mon, 14 Nov 2016 16:31:49 -0500 Subject: ftrace: Add more checks for FTRACE_FL_DISABLED in processing ip records When a module is first loaded and its function ip records are added to the ftrace list of functions to modify, they are set to DISABLED, as their text is still in a read only state. When the module is fully loaded, and can be updated, the flag is cleared, and if their's any functions that should be tracing them, it is updated at that moment. But there's several locations that do record accounting and should ignore records that are marked as disabled, or they can cause issues. Alexei already fixed one location, but others need to be addressed. Cc: stable@vger.kernel.org Fixes: b7ffffbb46f2 "ftrace: Add infrastructure for delayed enabling of module functions" Reported-by: Alexei Starovoitov Signed-off-by: Steven Rostedt --- kernel/trace/ftrace.c | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) (limited to 'kernel') diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index 326498baab83..da87b3cba5b3 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -1862,6 +1862,10 @@ static int __ftrace_hash_update_ipmodify(struct ftrace_ops *ops, /* Update rec->flags */ do_for_each_ftrace_rec(pg, rec) { + + if (rec->flags & FTRACE_FL_DISABLED) + continue; + /* We need to update only differences of filter_hash */ in_old = !!ftrace_lookup_ip(old_hash, rec->ip); in_new = !!ftrace_lookup_ip(new_hash, rec->ip); @@ -1884,6 +1888,10 @@ rollback: /* Roll back what we did above */ do_for_each_ftrace_rec(pg, rec) { + + if (rec->flags & FTRACE_FL_DISABLED) + continue; + if (rec == end) goto err_out; @@ -2397,6 +2405,10 @@ void __weak ftrace_replace_code(int enable) return; do_for_each_ftrace_rec(pg, rec) { + + if (rec->flags & FTRACE_FL_DISABLED) + continue; + failed = __ftrace_replace_code(rec, enable); if (failed) { ftrace_bug(failed, rec); @@ -3598,6 +3610,10 @@ match_records(struct ftrace_hash *hash, char *func, int len, char *mod) goto out_unlock; do_for_each_ftrace_rec(pg, rec) { + + if (rec->flags & FTRACE_FL_DISABLED) + continue; + if (ftrace_match_record(rec, &func_g, mod_match, exclude_mod)) { ret = enter_record(hash, rec, clear_filter); if (ret < 0) { @@ -3793,6 +3809,9 @@ register_ftrace_function_probe(char *glob, struct ftrace_probe_ops *ops, do_for_each_ftrace_rec(pg, rec) { + if (rec->flags & FTRACE_FL_DISABLED) + continue; + if (!ftrace_match_record(rec, &func_g, NULL, 0)) continue; @@ -4685,6 +4704,9 @@ ftrace_set_func(unsigned long *array, int *idx, int size, char *buffer) do_for_each_ftrace_rec(pg, rec) { + if (rec->flags & FTRACE_FL_DISABLED) + continue; + if (ftrace_match_record(rec, &func_g, NULL, 0)) { /* if it is in the array */ exists = false; -- cgit v1.2.3 From f23cc643f9baec7f71f2b74692da3cf03abbbfda Mon Sep 17 00:00:00 2001 From: Josef Bacik Date: Mon, 14 Nov 2016 15:45:36 -0500 Subject: bpf: fix range arithmetic for bpf map access I made some invalid assumptions with BPF_AND and BPF_MOD that could result in invalid accesses to bpf map entries. Fix this up by doing a few things 1) Kill BPF_MOD support. This doesn't actually get used by the compiler in real life and just adds extra complexity. 2) Fix the logic for BPF_AND, don't allow AND of negative numbers and set the minimum value to 0 for positive AND's. 3) Don't do operations on the ranges if they are set to the limits, as they are by definition undefined, and allowing arithmetic operations on those values could make them appear valid when they really aren't. This fixes the testcase provided by Jann as well as a few other theoretical problems. Reported-by: Jann Horn Signed-off-by: Josef Bacik Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- kernel/bpf/verifier.c | 70 ++++++++++++++++++++++++++++++++++----------------- 1 file changed, 47 insertions(+), 23 deletions(-) (limited to 'kernel') diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 99a7e5b388f2..6a936159c6e0 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -216,8 +216,8 @@ static void print_verifier_state(struct bpf_verifier_state *state) reg->map_ptr->key_size, reg->map_ptr->value_size); if (reg->min_value != BPF_REGISTER_MIN_RANGE) - verbose(",min_value=%llu", - (unsigned long long)reg->min_value); + verbose(",min_value=%lld", + (long long)reg->min_value); if (reg->max_value != BPF_REGISTER_MAX_RANGE) verbose(",max_value=%llu", (unsigned long long)reg->max_value); @@ -758,7 +758,7 @@ static int check_mem_access(struct bpf_verifier_env *env, u32 regno, int off, * index'es we need to make sure that whatever we use * will have a set floor within our range. */ - if ((s64)reg->min_value < 0) { + if (reg->min_value < 0) { verbose("R%d min value is negative, either use unsigned index or do a if (index >=0) check.\n", regno); return -EACCES; @@ -1468,7 +1468,8 @@ static void check_reg_overflow(struct bpf_reg_state *reg) { if (reg->max_value > BPF_REGISTER_MAX_RANGE) reg->max_value = BPF_REGISTER_MAX_RANGE; - if ((s64)reg->min_value < BPF_REGISTER_MIN_RANGE) + if (reg->min_value < BPF_REGISTER_MIN_RANGE || + reg->min_value > BPF_REGISTER_MAX_RANGE) reg->min_value = BPF_REGISTER_MIN_RANGE; } @@ -1476,7 +1477,8 @@ static void adjust_reg_min_max_vals(struct bpf_verifier_env *env, struct bpf_insn *insn) { struct bpf_reg_state *regs = env->cur_state.regs, *dst_reg; - u64 min_val = BPF_REGISTER_MIN_RANGE, max_val = BPF_REGISTER_MAX_RANGE; + s64 min_val = BPF_REGISTER_MIN_RANGE; + u64 max_val = BPF_REGISTER_MAX_RANGE; bool min_set = false, max_set = false; u8 opcode = BPF_OP(insn->code); @@ -1512,22 +1514,43 @@ static void adjust_reg_min_max_vals(struct bpf_verifier_env *env, return; } + /* If one of our values was at the end of our ranges then we can't just + * do our normal operations to the register, we need to set the values + * to the min/max since they are undefined. + */ + if (min_val == BPF_REGISTER_MIN_RANGE) + dst_reg->min_value = BPF_REGISTER_MIN_RANGE; + if (max_val == BPF_REGISTER_MAX_RANGE) + dst_reg->max_value = BPF_REGISTER_MAX_RANGE; + switch (opcode) { case BPF_ADD: - dst_reg->min_value += min_val; - dst_reg->max_value += max_val; + if (dst_reg->min_value != BPF_REGISTER_MIN_RANGE) + dst_reg->min_value += min_val; + if (dst_reg->max_value != BPF_REGISTER_MAX_RANGE) + dst_reg->max_value += max_val; break; case BPF_SUB: - dst_reg->min_value -= min_val; - dst_reg->max_value -= max_val; + if (dst_reg->min_value != BPF_REGISTER_MIN_RANGE) + dst_reg->min_value -= min_val; + if (dst_reg->max_value != BPF_REGISTER_MAX_RANGE) + dst_reg->max_value -= max_val; break; case BPF_MUL: - dst_reg->min_value *= min_val; - dst_reg->max_value *= max_val; + if (dst_reg->min_value != BPF_REGISTER_MIN_RANGE) + dst_reg->min_value *= min_val; + if (dst_reg->max_value != BPF_REGISTER_MAX_RANGE) + dst_reg->max_value *= max_val; break; case BPF_AND: - /* & is special since it could end up with 0 bits set. */ - dst_reg->min_value &= min_val; + /* Disallow AND'ing of negative numbers, ain't nobody got time + * for that. Otherwise the minimum is 0 and the max is the max + * value we could AND against. + */ + if (min_val < 0) + dst_reg->min_value = BPF_REGISTER_MIN_RANGE; + else + dst_reg->min_value = 0; dst_reg->max_value = max_val; break; case BPF_LSH: @@ -1537,24 +1560,25 @@ static void adjust_reg_min_max_vals(struct bpf_verifier_env *env, */ if (min_val > ilog2(BPF_REGISTER_MAX_RANGE)) dst_reg->min_value = BPF_REGISTER_MIN_RANGE; - else + else if (dst_reg->min_value != BPF_REGISTER_MIN_RANGE) dst_reg->min_value <<= min_val; if (max_val > ilog2(BPF_REGISTER_MAX_RANGE)) dst_reg->max_value = BPF_REGISTER_MAX_RANGE; - else + else if (dst_reg->max_value != BPF_REGISTER_MAX_RANGE) dst_reg->max_value <<= max_val; break; case BPF_RSH: - dst_reg->min_value >>= min_val; - dst_reg->max_value >>= max_val; - break; - case BPF_MOD: - /* % is special since it is an unsigned modulus, so the floor - * will always be 0. + /* RSH by a negative number is undefined, and the BPF_RSH is an + * unsigned shift, so make the appropriate casts. */ - dst_reg->min_value = 0; - dst_reg->max_value = max_val - 1; + if (min_val < 0 || dst_reg->min_value < 0) + dst_reg->min_value = BPF_REGISTER_MIN_RANGE; + else + dst_reg->min_value = + (u64)(dst_reg->min_value) >> min_val; + if (dst_reg->max_value != BPF_REGISTER_MAX_RANGE) + dst_reg->max_value >>= max_val; break; default: reset_reg_range_values(regs, insn->dst_reg); -- cgit v1.2.3 From e245d99e6cc4a0b904b87b46b4f60d46fb405987 Mon Sep 17 00:00:00 2001 From: Babu Moger Date: Wed, 2 Nov 2016 09:36:33 -0700 Subject: lockdep: Limit static allocations if PROVE_LOCKING_SMALL is defined Reduce the size of data structure for lockdep entries by half if PROVE_LOCKING_SMALL if defined. This is used only for sparc. Signed-off-by: Babu Moger Acked-by: Sam Ravnborg Signed-off-by: David S. Miller --- kernel/locking/lockdep_internals.h | 20 +++++++++++++++++--- 1 file changed, 17 insertions(+), 3 deletions(-) (limited to 'kernel') diff --git a/kernel/locking/lockdep_internals.h b/kernel/locking/lockdep_internals.h index 51c4b24b6328..c2b88490d857 100644 --- a/kernel/locking/lockdep_internals.h +++ b/kernel/locking/lockdep_internals.h @@ -45,6 +45,14 @@ enum { #define LOCKF_USED_IN_IRQ_READ \ (LOCKF_USED_IN_HARDIRQ_READ | LOCKF_USED_IN_SOFTIRQ_READ) +/* + * CONFIG_PROVE_LOCKING_SMALL is defined for sparc. Sparc requires .text, + * .data and .bss to fit in required 32MB limit for the kernel. With + * PROVE_LOCKING we could go over this limit and cause system boot-up problems. + * So, reduce the static allocations for lockdeps related structures so that + * everything fits in current required size limit. + */ +#ifdef CONFIG_PROVE_LOCKING_SMALL /* * MAX_LOCKDEP_ENTRIES is the maximum number of lock dependencies * we track. @@ -54,18 +62,24 @@ enum { * table (if it's not there yet), and we check it for lock order * conflicts and deadlocks. */ +#define MAX_LOCKDEP_ENTRIES 16384UL +#define MAX_LOCKDEP_CHAINS_BITS 15 +#define MAX_STACK_TRACE_ENTRIES 262144UL +#else #define MAX_LOCKDEP_ENTRIES 32768UL #define MAX_LOCKDEP_CHAINS_BITS 16 -#define MAX_LOCKDEP_CHAINS (1UL << MAX_LOCKDEP_CHAINS_BITS) - -#define MAX_LOCKDEP_CHAIN_HLOCKS (MAX_LOCKDEP_CHAINS*5) /* * Stack-trace: tightly packed array of stack backtrace * addresses. Protected by the hash_lock. */ #define MAX_STACK_TRACE_ENTRIES 524288UL +#endif + +#define MAX_LOCKDEP_CHAINS (1UL << MAX_LOCKDEP_CHAINS_BITS) + +#define MAX_LOCKDEP_CHAIN_HLOCKS (MAX_LOCKDEP_CHAINS*5) extern struct list_head all_lock_classes; extern struct lock_chain lock_chains[]; -- cgit v1.2.3