From f91fe17e243d1f279d425071a35e3d41290758a0 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Sun, 1 Mar 2015 12:31:41 +0100 Subject: ebpf: remove kernel test stubs Now that we have BPF_PROG_TYPE_SOCKET_FILTER up and running, we can remove the test stubs which were added to get the verifier suite up. We can just let the test cases probe under socket filter type instead. In the fill/spill test case, we cannot (yet) access fields from the context (skb), but we may adapt that test case in future. Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- kernel/bpf/Makefile | 3 -- kernel/bpf/test_stub.c | 78 -------------------------------------------------- 2 files changed, 81 deletions(-) delete mode 100644 kernel/bpf/test_stub.c (limited to 'kernel') diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile index a5ae60f0b0a2..e6983be12bd3 100644 --- a/kernel/bpf/Makefile +++ b/kernel/bpf/Makefile @@ -1,5 +1,2 @@ obj-y := core.o obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o hashtab.o arraymap.o helpers.o -ifdef CONFIG_TEST_BPF -obj-$(CONFIG_BPF_SYSCALL) += test_stub.o -endif diff --git a/kernel/bpf/test_stub.c b/kernel/bpf/test_stub.c deleted file mode 100644 index 0ceae1e6e8b5..000000000000 --- a/kernel/bpf/test_stub.c +++ /dev/null @@ -1,78 +0,0 @@ -/* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of version 2 of the GNU General Public - * License as published by the Free Software Foundation. - */ -#include -#include -#include -#include -#include - -/* test stubs for BPF_MAP_TYPE_UNSPEC and for BPF_PROG_TYPE_UNSPEC - * to be used by user space verifier testsuite - */ -struct bpf_context { - u64 arg1; - u64 arg2; -}; - -static const struct bpf_func_proto *test_func_proto(enum bpf_func_id func_id) -{ - switch (func_id) { - case BPF_FUNC_map_lookup_elem: - return &bpf_map_lookup_elem_proto; - case BPF_FUNC_map_update_elem: - return &bpf_map_update_elem_proto; - case BPF_FUNC_map_delete_elem: - return &bpf_map_delete_elem_proto; - default: - return NULL; - } -} - -static const struct bpf_context_access { - int size; - enum bpf_access_type type; -} test_ctx_access[] = { - [offsetof(struct bpf_context, arg1)] = { - FIELD_SIZEOF(struct bpf_context, arg1), - BPF_READ - }, - [offsetof(struct bpf_context, arg2)] = { - FIELD_SIZEOF(struct bpf_context, arg2), - BPF_READ - }, -}; - -static bool test_is_valid_access(int off, int size, enum bpf_access_type type) -{ - const struct bpf_context_access *access; - - if (off < 0 || off >= ARRAY_SIZE(test_ctx_access)) - return false; - - access = &test_ctx_access[off]; - if (access->size == size && (access->type & type)) - return true; - - return false; -} - -static struct bpf_verifier_ops test_ops = { - .get_func_proto = test_func_proto, - .is_valid_access = test_is_valid_access, -}; - -static struct bpf_prog_type_list tl_prog = { - .ops = &test_ops, - .type = BPF_PROG_TYPE_UNSPEC, -}; - -static int __init register_test_ops(void) -{ - bpf_register_prog_type(&tl_prog); - return 0; -} -late_initcall(register_test_ops); -- cgit v1.2.3 From a2c83fff582ae133d9f5bb187404ea9ce4da1f96 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Sun, 1 Mar 2015 12:31:42 +0100 Subject: ebpf: constify various function pointer structs We can move bpf_map_ops and bpf_verifier_ops and other structs into ro section, bpf_map_type_list and bpf_prog_type_list into read mostly. Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- kernel/bpf/arraymap.c | 6 +++--- kernel/bpf/hashtab.c | 6 +++--- kernel/bpf/helpers.c | 6 +++--- 3 files changed, 9 insertions(+), 9 deletions(-) (limited to 'kernel') diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index 9eb4d8a7cd87..8a6616583f38 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -134,7 +134,7 @@ static void array_map_free(struct bpf_map *map) kvfree(array); } -static struct bpf_map_ops array_ops = { +static const struct bpf_map_ops array_ops = { .map_alloc = array_map_alloc, .map_free = array_map_free, .map_get_next_key = array_map_get_next_key, @@ -143,14 +143,14 @@ static struct bpf_map_ops array_ops = { .map_delete_elem = array_map_delete_elem, }; -static struct bpf_map_type_list tl = { +static struct bpf_map_type_list array_type __read_mostly = { .ops = &array_ops, .type = BPF_MAP_TYPE_ARRAY, }; static int __init register_array_map(void) { - bpf_register_map_type(&tl); + bpf_register_map_type(&array_type); return 0; } late_initcall(register_array_map); diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c index b3ba43674310..83c209d9b17a 100644 --- a/kernel/bpf/hashtab.c +++ b/kernel/bpf/hashtab.c @@ -345,7 +345,7 @@ static void htab_map_free(struct bpf_map *map) kfree(htab); } -static struct bpf_map_ops htab_ops = { +static const struct bpf_map_ops htab_ops = { .map_alloc = htab_map_alloc, .map_free = htab_map_free, .map_get_next_key = htab_map_get_next_key, @@ -354,14 +354,14 @@ static struct bpf_map_ops htab_ops = { .map_delete_elem = htab_map_delete_elem, }; -static struct bpf_map_type_list tl = { +static struct bpf_map_type_list htab_type __read_mostly = { .ops = &htab_ops, .type = BPF_MAP_TYPE_HASH, }; static int __init register_htab_map(void) { - bpf_register_map_type(&tl); + bpf_register_map_type(&htab_type); return 0; } late_initcall(register_htab_map); diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 9e3414d85459..a3c7701a8b5e 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -41,7 +41,7 @@ static u64 bpf_map_lookup_elem(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) return (unsigned long) value; } -struct bpf_func_proto bpf_map_lookup_elem_proto = { +const struct bpf_func_proto bpf_map_lookup_elem_proto = { .func = bpf_map_lookup_elem, .gpl_only = false, .ret_type = RET_PTR_TO_MAP_VALUE_OR_NULL, @@ -60,7 +60,7 @@ static u64 bpf_map_update_elem(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) return map->ops->map_update_elem(map, key, value, r4); } -struct bpf_func_proto bpf_map_update_elem_proto = { +const struct bpf_func_proto bpf_map_update_elem_proto = { .func = bpf_map_update_elem, .gpl_only = false, .ret_type = RET_INTEGER, @@ -80,7 +80,7 @@ static u64 bpf_map_delete_elem(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) return map->ops->map_delete_elem(map, key); } -struct bpf_func_proto bpf_map_delete_elem_proto = { +const struct bpf_func_proto bpf_map_delete_elem_proto = { .func = bpf_map_delete_elem, .gpl_only = false, .ret_type = RET_INTEGER, -- cgit v1.2.3 From 96be4325f443dbbfeb37d2a157675ac0736531a1 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Sun, 1 Mar 2015 12:31:46 +0100 Subject: ebpf: add sched_cls_type and map it to sk_filter's verifier ops As discussed recently and at netconf/netdev01, we want to prevent making bpf_verifier_ops registration available for modules, but have them at a controlled place inside the kernel instead. The reason for this is, that out-of-tree modules can go crazy and define and register any verfifier ops they want, doing all sorts of crap, even bypassing available GPLed eBPF helper functions. We don't want to offer such a shiny playground, of course, but keep strict control to ourselves inside the core kernel. This also encourages us to design eBPF user helpers carefully and generically, so they can be shared among various subsystems using eBPF. For the eBPF traffic classifier (cls_bpf), it's a good start to share the same helper facilities as we currently do in eBPF for socket filters. That way, we have BPF_PROG_TYPE_SCHED_CLS look like it's own type, thus one day if there's a good reason to diverge the set of helper functions from the set available to socket filters, we keep ABI compatibility. In future, we could place all bpf_prog_type_list at a central place, perhaps. Signed-off-by: Daniel Borkmann Signed-off-by: Alexei Starovoitov Signed-off-by: David S. Miller --- kernel/bpf/verifier.c | 15 +++++++++++++-- 1 file changed, 13 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index a28e09c7825d..594d341f04db 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -1172,6 +1172,17 @@ static int check_ld_imm(struct verifier_env *env, struct bpf_insn *insn) return 0; } +static bool may_access_skb(enum bpf_prog_type type) +{ + switch (type) { + case BPF_PROG_TYPE_SOCKET_FILTER: + case BPF_PROG_TYPE_SCHED_CLS: + return true; + default: + return false; + } +} + /* verify safety of LD_ABS|LD_IND instructions: * - they can only appear in the programs where ctx == skb * - since they are wrappers of function calls, they scratch R1-R5 registers, @@ -1194,8 +1205,8 @@ static int check_ld_abs(struct verifier_env *env, struct bpf_insn *insn) struct reg_state *reg; int i, err; - if (env->prog->aux->prog_type != BPF_PROG_TYPE_SOCKET_FILTER) { - verbose("BPF_LD_ABS|IND instructions are only allowed in socket filters\n"); + if (!may_access_skb(env->prog->aux->prog_type)) { + verbose("BPF_LD_ABS|IND instructions not allowed for this program type\n"); return -EINVAL; } -- cgit v1.2.3 From 24701ecea76b0b93bd9667486934ec310825f558 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Sun, 1 Mar 2015 12:31:47 +0100 Subject: ebpf: move read-only fields to bpf_prog and shrink bpf_prog_aux is_gpl_compatible and prog_type should be moved directly into bpf_prog as they stay immutable during bpf_prog's lifetime, are core attributes and they can be locked as read-only later on via bpf_prog_select_runtime(). With a bit of rearranging, this also allows us to shrink bpf_prog_aux to exactly 1 cacheline. Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- kernel/bpf/syscall.c | 7 +++---- kernel/bpf/verifier.c | 4 ++-- 2 files changed, 5 insertions(+), 6 deletions(-) (limited to 'kernel') diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 536edc2be307..0d69449acbd0 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -354,10 +354,11 @@ static int find_prog_type(enum bpf_prog_type type, struct bpf_prog *prog) list_for_each_entry(tl, &bpf_prog_types, list_node) { if (tl->type == type) { prog->aux->ops = tl->ops; - prog->aux->prog_type = type; + prog->type = type; return 0; } } + return -EINVAL; } @@ -508,7 +509,7 @@ static int bpf_prog_load(union bpf_attr *attr) prog->jited = false; atomic_set(&prog->aux->refcnt, 1); - prog->aux->is_gpl_compatible = is_gpl; + prog->gpl_compatible = is_gpl; /* find program type: socket_filter vs tracing_filter */ err = find_prog_type(type, prog); @@ -517,7 +518,6 @@ static int bpf_prog_load(union bpf_attr *attr) /* run eBPF verifier */ err = bpf_check(prog, attr); - if (err < 0) goto free_used_maps; @@ -528,7 +528,6 @@ static int bpf_prog_load(union bpf_attr *attr) bpf_prog_select_runtime(prog); err = anon_inode_getfd("bpf-prog", &bpf_prog_fops, prog, O_RDWR | O_CLOEXEC); - if (err < 0) /* failed to allocate fd */ goto free_used_maps; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 594d341f04db..bdf4192a889b 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -852,7 +852,7 @@ static int check_call(struct verifier_env *env, int func_id) } /* eBPF programs must be GPL compatible to use GPL-ed functions */ - if (!env->prog->aux->is_gpl_compatible && fn->gpl_only) { + if (!env->prog->gpl_compatible && fn->gpl_only) { verbose("cannot call GPL only function from proprietary program\n"); return -EINVAL; } @@ -1205,7 +1205,7 @@ static int check_ld_abs(struct verifier_env *env, struct bpf_insn *insn) struct reg_state *reg; int i, err; - if (!may_access_skb(env->prog->aux->prog_type)) { + if (!may_access_skb(env->prog->type)) { verbose("BPF_LD_ABS|IND instructions not allowed for this program type\n"); return -EINVAL; } -- cgit v1.2.3 From e2e9b6541dd4b31848079da80fe2253daaafb549 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Sun, 1 Mar 2015 12:31:48 +0100 Subject: cls_bpf: add initial eBPF support for programmable classifiers This work extends the "classic" BPF programmable tc classifier by extending its scope also to native eBPF code! This allows for user space to implement own custom, 'safe' C like classifiers (or whatever other frontend language LLVM et al may provide in future), that can then be compiled with the LLVM eBPF backend to an eBPF elf file. The result of this can be loaded into the kernel via iproute2's tc. In the kernel, they can be JITed on major archs and thus run in native performance. Simple, minimal toy example to demonstrate the workflow: #include #include #include #include "tc_bpf_api.h" __section("classify") int cls_main(struct sk_buff *skb) { return (0x800 << 16) | load_byte(skb, ETH_HLEN + __builtin_offsetof(struct iphdr, tos)); } char __license[] __section("license") = "GPL"; The classifier can then be compiled into eBPF opcodes and loaded via tc, for example: clang -O2 -emit-llvm -c cls.c -o - | llc -march=bpf -filetype=obj -o cls.o tc filter add dev em1 parent 1: bpf cls.o [...] As it has been demonstrated, the scope can even reach up to a fully fledged flow dissector (similarly as in samples/bpf/sockex2_kern.c). For tc, maps are allowed to be used, but from kernel context only, in other words, eBPF code can keep state across filter invocations. In future, we perhaps may reattach from a different application to those maps e.g., to read out collected statistics/state. Similarly as in socket filters, we may extend functionality for eBPF classifiers over time depending on the use cases. For that purpose, cls_bpf programs are using BPF_PROG_TYPE_SCHED_CLS program type, so we can allow additional functions/accessors (e.g. an ABI compatible offset translation to skb fields/metadata). For an initial cls_bpf support, we allow the same set of helper functions as eBPF socket filters, but we could diverge at some point in time w/o problem. I was wondering whether cls_bpf and act_bpf could share C programs, I can imagine that at some point, we introduce i) further common handlers for both (or even beyond their scope), and/or if truly needed ii) some restricted function space for each of them. Both can be abstracted easily through struct bpf_verifier_ops in future. The context of cls_bpf versus act_bpf is slightly different though: a cls_bpf program will return a specific classid whereas act_bpf a drop/non-drop return code, latter may also in future mangle skbs. That said, we can surely have a "classify" and "action" section in a single object file, or considered mentioned constraint add a possibility of a shared section. The workflow for getting native eBPF running from tc [1] is as follows: for f_bpf, I've added a slightly modified ELF parser code from Alexei's kernel sample, which reads out the LLVM compiled object, sets up maps (and dynamically fixes up map fds) if any, and loads the eBPF instructions all centrally through the bpf syscall. The resulting fd from the loaded program itself is being passed down to cls_bpf, which looks up struct bpf_prog from the fd store, and holds reference, so that it stays available also after tc program lifetime. On tc filter destruction, it will then drop its reference. Moreover, I've also added the optional possibility to annotate an eBPF filter with a name (e.g. path to object file, or something else if preferred) so that when tc dumps currently installed filters, some more context can be given to an admin for a given instance (as opposed to just the file descriptor number). Last but not least, bpf_prog_get() and bpf_prog_put() needed to be exported, so that eBPF can be used from cls_bpf built as a module. Thanks to 60a3b2253c41 ("net: bpf: make eBPF interpreter images read-only") I think this is of no concern since anything wanting to alter eBPF opcode after verification stage would crash the kernel. [1] http://git.breakpoint.cc/cgit/dborkman/iproute2.git/log/?h=ebpf Signed-off-by: Daniel Borkmann Cc: Jamal Hadi Salim Cc: Jiri Pirko Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- kernel/bpf/syscall.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'kernel') diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 0d69449acbd0..669719ccc9ee 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -419,6 +419,7 @@ void bpf_prog_put(struct bpf_prog *prog) bpf_prog_free(prog); } } +EXPORT_SYMBOL_GPL(bpf_prog_put); static int bpf_prog_release(struct inode *inode, struct file *filp) { @@ -466,6 +467,7 @@ struct bpf_prog *bpf_prog_get(u32 ufd) fdput(f); return prog; } +EXPORT_SYMBOL_GPL(bpf_prog_get); /* last field in 'union bpf_attr' used by this command */ #define BPF_PROG_LOAD_LAST_FIELD log_buf -- cgit v1.2.3 From 3ba67dabaa58e3223325f0a813a6e830fb5f5cc5 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Thu, 5 Mar 2015 23:27:51 +0100 Subject: ebpf: bpf_map_*: fix linker error on avr32 and openrisc arch Fengguang reported, that on openrisc and avr32 architectures, we get the following linker errors on *_defconfig builds that have no bpf syscall support: net/built-in.o:(.rodata+0x1cd0): undefined reference to `bpf_map_lookup_elem_proto' net/built-in.o:(.rodata+0x1cd4): undefined reference to `bpf_map_update_elem_proto' net/built-in.o:(.rodata+0x1cd8): undefined reference to `bpf_map_delete_elem_proto' Fix it up by providing built-in weak definitions of the symbols, so they can be overridden when the syscall is enabled. I think the issue might be that gcc is not able to optimize all that away. This patch fixes the linker errors for me, tested with Fengguang's make.cross [1] script. [1] https://git.kernel.org/cgit/linux/kernel/git/wfg/lkp-tests.git/plain/sbin/make.cross Reported-by: Fengguang Wu Fixes: d4052c4aea0c ("ebpf: remove CONFIG_BPF_SYSCALL ifdefs in socket filter code") Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- kernel/bpf/core.c | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'kernel') diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index a64e7a207d2b..50603aec766a 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -656,6 +656,11 @@ void bpf_prog_free(struct bpf_prog *fp) } EXPORT_SYMBOL_GPL(bpf_prog_free); +/* Weak definitions of helper functions in case we don't have bpf syscall. */ +const struct bpf_func_proto bpf_map_lookup_elem_proto __weak; +const struct bpf_func_proto bpf_map_update_elem_proto __weak; +const struct bpf_func_proto bpf_map_delete_elem_proto __weak; + /* To execute LD_ABS/LD_IND instructions __bpf_prog_run() may call * skb_copy_bits(), so provide a weak definition of it for NET-less config. */ -- cgit v1.2.3 From 80f1d68ccba70b1060c9c7360ca83da430f66bed Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Thu, 12 Mar 2015 17:21:42 +0100 Subject: ebpf: verifier: check that call reg with ARG_ANYTHING is initialized I noticed that a helper function with argument type ARG_ANYTHING does not need to have an initialized value (register). This can worst case lead to unintented stack memory leakage in future helper functions if they are not carefully designed, or unintended application behaviour in case the application developer was not careful enough to match a correct helper function signature in the API. The underlying issue is that ARG_ANYTHING should actually be split into two different semantics: 1) ARG_DONTCARE for function arguments that the helper function does not care about (in other words: the default for unused function arguments), and 2) ARG_ANYTHING that is an argument actually being used by a helper function and *guaranteed* to be an initialized register. The current risk is low: ARG_ANYTHING is only used for the 'flags' argument (r4) in bpf_map_update_elem() that internally does strict checking. Fixes: 17a5267067f3 ("bpf: verifier (add verifier core)") Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- kernel/bpf/verifier.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index bdf4192a889b..e6b522496250 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -755,7 +755,7 @@ static int check_func_arg(struct verifier_env *env, u32 regno, enum bpf_reg_type expected_type; int err = 0; - if (arg_type == ARG_ANYTHING) + if (arg_type == ARG_DONTCARE) return 0; if (reg->type == NOT_INIT) { @@ -763,6 +763,9 @@ static int check_func_arg(struct verifier_env *env, u32 regno, return -EACCES; } + if (arg_type == ARG_ANYTHING) + return 0; + if (arg_type == ARG_PTR_TO_STACK || arg_type == ARG_PTR_TO_MAP_KEY || arg_type == ARG_PTR_TO_MAP_VALUE) { expected_type = PTR_TO_STACK; -- cgit v1.2.3 From 03e69b508b6f7c51743055c9f61d1dfeadf4b635 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Sat, 14 Mar 2015 02:27:16 +0100 Subject: ebpf: add prandom helper for packet sampling This work is similar to commit 4cd3675ebf74 ("filter: added BPF random opcode") and adds a possibility for packet sampling in eBPF. Currently, this is only possible in classic BPF and useful to combine sampling with f.e. packet sockets, possible also with tc. Example function proto-type looks like: u32 (*prandom_u32)(void) = (void *)BPF_FUNC_get_prandom_u32; Signed-off-by: Daniel Borkmann Signed-off-by: David S. Miller --- kernel/bpf/core.c | 2 ++ kernel/bpf/helpers.c | 12 ++++++++++++ 2 files changed, 14 insertions(+) (limited to 'kernel') diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 50603aec766a..c1dbbb5d289b 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -661,6 +661,8 @@ const struct bpf_func_proto bpf_map_lookup_elem_proto __weak; const struct bpf_func_proto bpf_map_update_elem_proto __weak; const struct bpf_func_proto bpf_map_delete_elem_proto __weak; +const struct bpf_func_proto bpf_get_prandom_u32_proto __weak; + /* To execute LD_ABS/LD_IND instructions __bpf_prog_run() may call * skb_copy_bits(), so provide a weak definition of it for NET-less config. */ diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index a3c7701a8b5e..95eb59a045ea 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -11,6 +11,7 @@ */ #include #include +#include /* If kernel subsystem is allowing eBPF programs to call this function, * inside its own verifier_ops->get_func_proto() callback it should return @@ -87,3 +88,14 @@ const struct bpf_func_proto bpf_map_delete_elem_proto = { .arg1_type = ARG_CONST_MAP_PTR, .arg2_type = ARG_PTR_TO_MAP_KEY, }; + +static u64 bpf_get_prandom_u32(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) +{ + return prandom_u32(); +} + +const struct bpf_func_proto bpf_get_prandom_u32_proto = { + .func = bpf_get_prandom_u32, + .gpl_only = false, + .ret_type = RET_INTEGER, +}; -- cgit v1.2.3 From c04167ce2ca0ecaeaafef006cb0d65cf01b68e42 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Sat, 14 Mar 2015 02:27:17 +0100 Subject: ebpf: add helper for obtaining current processor id This patch adds the possibility to obtain raw_smp_processor_id() in eBPF. Currently, this is only possible in classic BPF where commit da2033c28226 ("filter: add SKF_AD_RXHASH and SKF_AD_CPU") has added facilities for this. Perhaps most importantly, this would also allow us to track per CPU statistics with eBPF maps, or to implement a poor-man's per CPU data structure through eBPF maps. Example function proto-type looks like: u32 (*smp_processor_id)(void) = (void *)BPF_FUNC_get_smp_processor_id; Signed-off-by: Daniel Borkmann Signed-off-by: David S. Miller --- kernel/bpf/core.c | 1 + kernel/bpf/helpers.c | 12 ++++++++++++ 2 files changed, 13 insertions(+) (limited to 'kernel') diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index c1dbbb5d289b..4139a0f8b558 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -662,6 +662,7 @@ const struct bpf_func_proto bpf_map_update_elem_proto __weak; const struct bpf_func_proto bpf_map_delete_elem_proto __weak; const struct bpf_func_proto bpf_get_prandom_u32_proto __weak; +const struct bpf_func_proto bpf_get_smp_processor_id_proto __weak; /* To execute LD_ABS/LD_IND instructions __bpf_prog_run() may call * skb_copy_bits(), so provide a weak definition of it for NET-less config. diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 95eb59a045ea..bd7f5988ed9c 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -12,6 +12,7 @@ #include #include #include +#include /* If kernel subsystem is allowing eBPF programs to call this function, * inside its own verifier_ops->get_func_proto() callback it should return @@ -99,3 +100,14 @@ const struct bpf_func_proto bpf_get_prandom_u32_proto = { .gpl_only = false, .ret_type = RET_INTEGER, }; + +static u64 bpf_get_smp_processor_id(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5) +{ + return raw_smp_processor_id(); +} + +const struct bpf_func_proto bpf_get_smp_processor_id_proto = { + .func = bpf_get_smp_processor_id, + .gpl_only = false, + .ret_type = RET_INTEGER, +}; -- cgit v1.2.3 From 9bac3d6d548e5cc925570b263f35b70a00a00ffd Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Fri, 13 Mar 2015 11:57:42 -0700 Subject: bpf: allow extended BPF programs access skb fields introduce user accessible mirror of in-kernel 'struct sk_buff': struct __sk_buff { __u32 len; __u32 pkt_type; __u32 mark; __u32 queue_mapping; }; bpf programs can do: int bpf_prog(struct __sk_buff *skb) { __u32 var = skb->pkt_type; which will be compiled to bpf assembler as: dst_reg = *(u32 *)(src_reg + 4) // 4 == offsetof(struct __sk_buff, pkt_type) bpf verifier will check validity of access and will convert it to: dst_reg = *(u8 *)(src_reg + offsetof(struct sk_buff, __pkt_type_offset)) dst_reg &= 7 since skb->pkt_type is a bitfield. Signed-off-by: Alexei Starovoitov Signed-off-by: David S. Miller --- kernel/bpf/syscall.c | 2 +- kernel/bpf/verifier.c | 152 ++++++++++++++++++++++++++++++++++++++++++++------ 2 files changed, 137 insertions(+), 17 deletions(-) (limited to 'kernel') diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 669719ccc9ee..ea75c654af1b 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -519,7 +519,7 @@ static int bpf_prog_load(union bpf_attr *attr) goto free_prog; /* run eBPF verifier */ - err = bpf_check(prog, attr); + err = bpf_check(&prog, attr); if (err < 0) goto free_used_maps; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index e6b522496250..c22ebd36fa4b 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -1620,11 +1620,10 @@ static int do_check(struct verifier_env *env) return err; } else if (class == BPF_LDX) { - if (BPF_MODE(insn->code) != BPF_MEM || - insn->imm != 0) { - verbose("BPF_LDX uses reserved fields\n"); - return -EINVAL; - } + enum bpf_reg_type src_reg_type; + + /* check for reserved fields is already done */ + /* check src operand */ err = check_reg_arg(regs, insn->src_reg, SRC_OP); if (err) @@ -1643,6 +1642,29 @@ static int do_check(struct verifier_env *env) if (err) return err; + src_reg_type = regs[insn->src_reg].type; + + if (insn->imm == 0 && BPF_SIZE(insn->code) == BPF_W) { + /* saw a valid insn + * dst_reg = *(u32 *)(src_reg + off) + * use reserved 'imm' field to mark this insn + */ + insn->imm = src_reg_type; + + } else if (src_reg_type != insn->imm && + (src_reg_type == PTR_TO_CTX || + insn->imm == PTR_TO_CTX)) { + /* ABuser program is trying to use the same insn + * dst_reg = *(u32*) (src_reg + off) + * with different pointer types: + * src_reg == ctx in one branch and + * src_reg == stack|map in some other branch. + * Reject it. + */ + verbose("same insn cannot be used with different pointers\n"); + return -EINVAL; + } + } else if (class == BPF_STX) { if (BPF_MODE(insn->code) == BPF_XADD) { err = check_xadd(env, insn); @@ -1790,6 +1812,13 @@ static int replace_map_fd_with_map_ptr(struct verifier_env *env) int i, j; for (i = 0; i < insn_cnt; i++, insn++) { + if (BPF_CLASS(insn->code) == BPF_LDX && + (BPF_MODE(insn->code) != BPF_MEM || + insn->imm != 0)) { + verbose("BPF_LDX uses reserved fields\n"); + return -EINVAL; + } + if (insn[0].code == (BPF_LD | BPF_IMM | BPF_DW)) { struct bpf_map *map; struct fd f; @@ -1881,6 +1910,92 @@ static void convert_pseudo_ld_imm64(struct verifier_env *env) insn->src_reg = 0; } +static void adjust_branches(struct bpf_prog *prog, int pos, int delta) +{ + struct bpf_insn *insn = prog->insnsi; + int insn_cnt = prog->len; + int i; + + for (i = 0; i < insn_cnt; i++, insn++) { + if (BPF_CLASS(insn->code) != BPF_JMP || + BPF_OP(insn->code) == BPF_CALL || + BPF_OP(insn->code) == BPF_EXIT) + continue; + + /* adjust offset of jmps if necessary */ + if (i < pos && i + insn->off + 1 > pos) + insn->off += delta; + else if (i > pos && i + insn->off + 1 < pos) + insn->off -= delta; + } +} + +/* convert load instructions that access fields of 'struct __sk_buff' + * into sequence of instructions that access fields of 'struct sk_buff' + */ +static int convert_ctx_accesses(struct verifier_env *env) +{ + struct bpf_insn *insn = env->prog->insnsi; + int insn_cnt = env->prog->len; + struct bpf_insn insn_buf[16]; + struct bpf_prog *new_prog; + u32 cnt; + int i; + + if (!env->prog->aux->ops->convert_ctx_access) + return 0; + + for (i = 0; i < insn_cnt; i++, insn++) { + if (insn->code != (BPF_LDX | BPF_MEM | BPF_W)) + continue; + + if (insn->imm != PTR_TO_CTX) { + /* clear internal mark */ + insn->imm = 0; + continue; + } + + cnt = env->prog->aux->ops-> + convert_ctx_access(insn->dst_reg, insn->src_reg, + insn->off, insn_buf); + if (cnt == 0 || cnt >= ARRAY_SIZE(insn_buf)) { + verbose("bpf verifier is misconfigured\n"); + return -EINVAL; + } + + if (cnt == 1) { + memcpy(insn, insn_buf, sizeof(*insn)); + continue; + } + + /* several new insns need to be inserted. Make room for them */ + insn_cnt += cnt - 1; + new_prog = bpf_prog_realloc(env->prog, + bpf_prog_size(insn_cnt), + GFP_USER); + if (!new_prog) + return -ENOMEM; + + new_prog->len = insn_cnt; + + memmove(new_prog->insnsi + i + cnt, new_prog->insns + i + 1, + sizeof(*insn) * (insn_cnt - i - cnt)); + + /* copy substitute insns in place of load instruction */ + memcpy(new_prog->insnsi + i, insn_buf, sizeof(*insn) * cnt); + + /* adjust branches in the whole program */ + adjust_branches(new_prog, i, cnt - 1); + + /* keep walking new program and skip insns we just inserted */ + env->prog = new_prog; + insn = new_prog->insnsi + i + cnt - 1; + i += cnt - 1; + } + + return 0; +} + static void free_states(struct verifier_env *env) { struct verifier_state_list *sl, *sln; @@ -1903,13 +2018,13 @@ static void free_states(struct verifier_env *env) kfree(env->explored_states); } -int bpf_check(struct bpf_prog *prog, union bpf_attr *attr) +int bpf_check(struct bpf_prog **prog, union bpf_attr *attr) { char __user *log_ubuf = NULL; struct verifier_env *env; int ret = -EINVAL; - if (prog->len <= 0 || prog->len > BPF_MAXINSNS) + if ((*prog)->len <= 0 || (*prog)->len > BPF_MAXINSNS) return -E2BIG; /* 'struct verifier_env' can be global, but since it's not small, @@ -1919,7 +2034,7 @@ int bpf_check(struct bpf_prog *prog, union bpf_attr *attr) if (!env) return -ENOMEM; - env->prog = prog; + env->prog = *prog; /* grab the mutex to protect few globals used by verifier */ mutex_lock(&bpf_verifier_lock); @@ -1951,7 +2066,7 @@ int bpf_check(struct bpf_prog *prog, union bpf_attr *attr) if (ret < 0) goto skip_full_check; - env->explored_states = kcalloc(prog->len, + env->explored_states = kcalloc(env->prog->len, sizeof(struct verifier_state_list *), GFP_USER); ret = -ENOMEM; @@ -1968,6 +2083,10 @@ skip_full_check: while (pop_stack(env, NULL) >= 0); free_states(env); + if (ret == 0) + /* program is valid, convert *(u32*)(ctx + off) accesses */ + ret = convert_ctx_accesses(env); + if (log_level && log_len >= log_size - 1) { BUG_ON(log_len >= log_size); /* verifier log exceeded user supplied buffer */ @@ -1983,18 +2102,18 @@ skip_full_check: if (ret == 0 && env->used_map_cnt) { /* if program passed verifier, update used_maps in bpf_prog_info */ - prog->aux->used_maps = kmalloc_array(env->used_map_cnt, - sizeof(env->used_maps[0]), - GFP_KERNEL); + env->prog->aux->used_maps = kmalloc_array(env->used_map_cnt, + sizeof(env->used_maps[0]), + GFP_KERNEL); - if (!prog->aux->used_maps) { + if (!env->prog->aux->used_maps) { ret = -ENOMEM; goto free_log_buf; } - memcpy(prog->aux->used_maps, env->used_maps, + memcpy(env->prog->aux->used_maps, env->used_maps, sizeof(env->used_maps[0]) * env->used_map_cnt); - prog->aux->used_map_cnt = env->used_map_cnt; + env->prog->aux->used_map_cnt = env->used_map_cnt; /* program is valid. Convert pseudo bpf_ld_imm64 into generic * bpf_ld_imm64 instructions @@ -2006,11 +2125,12 @@ free_log_buf: if (log_level) vfree(log_buf); free_env: - if (!prog->aux->used_maps) + if (!env->prog->aux->used_maps) /* if we didn't copy map pointers into bpf_prog_info, release * them now. Otherwise free_bpf_prog_info() will release them. */ release_maps(env); + *prog = env->prog; kfree(env); mutex_unlock(&bpf_verifier_lock); return ret; -- cgit v1.2.3 From 1efff914afac8a965ad63817ecf8861a927c2ace Mon Sep 17 00:00:00 2001 From: Theodore Ts'o Date: Tue, 17 Mar 2015 12:23:32 -0400 Subject: fs: add dirtytime_expire_seconds sysctl Add a tuning knob so we can adjust the dirtytime expiration timeout, which is very useful for testing lazytime. Signed-off-by: Theodore Ts'o Reviewed-by: Jan Kara --- kernel/sysctl.c | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'kernel') diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 88ea2d6e0031..ce410bb9f2e1 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -1227,6 +1227,14 @@ static struct ctl_table vm_table[] = { .proc_handler = proc_dointvec_minmax, .extra1 = &zero, }, + { + .procname = "dirtytime_expire_seconds", + .data = &dirtytime_expire_interval, + .maxlen = sizeof(dirty_expire_interval), + .mode = 0644, + .proc_handler = dirtytime_interval_handler, + .extra1 = &zero, + }, { .procname = "nr_pdflush_threads", .mode = 0444 /* read-only */, -- cgit v1.2.3 From 94caee8c312d96522bcdae88791aaa9ebcd5f22c Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Fri, 20 Mar 2015 15:11:11 +0100 Subject: ebpf: add sched_act_type and map it to sk_filter's verifier ops In order to prepare eBPF support for tc action, we need to add sched_act_type, so that the eBPF verifier is aware of what helper function act_bpf may use, that it can load skb data and read out currently available skb fields. This is bascially analogous to 96be4325f443 ("ebpf: add sched_cls_type and map it to sk_filter's verifier ops"). BPF_PROG_TYPE_SCHED_CLS and BPF_PROG_TYPE_SCHED_ACT need to be separate since both will have a different set of functionality in future (classifier vs action), thus we won't run into ABI troubles when the point in time comes to diverge functionality from the classifier. The future plan for act_bpf would be that it will be able to write into skb->data and alter selected fields mirrored in struct __sk_buff. For an initial support, it's sufficient to map it to sk_filter_ops. Signed-off-by: Daniel Borkmann Cc: Jiri Pirko Reviewed-by: Jiri Pirko Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- kernel/bpf/verifier.c | 1 + 1 file changed, 1 insertion(+) (limited to 'kernel') diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index c22ebd36fa4b..0e714f799ec0 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -1180,6 +1180,7 @@ static bool may_access_skb(enum bpf_prog_type type) switch (type) { case BPF_PROG_TYPE_SOCKET_FILTER: case BPF_PROG_TYPE_SCHED_CLS: + case BPF_PROG_TYPE_SCHED_ACT: return true; default: return false; -- cgit v1.2.3 From d525211f9d1be8b523ec7633f080f2116f5ea536 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 19 Feb 2015 18:03:11 +0100 Subject: perf: Fix irq_work 'tail' recursion Vince reported a watchdog lockup like: [] perf_tp_event+0xc4/0x210 [] perf_trace_lock+0x12a/0x160 [] lock_release+0x130/0x260 [] _raw_spin_unlock_irqrestore+0x24/0x40 [] do_send_sig_info+0x5d/0x80 [] send_sigio_to_task+0x12f/0x1a0 [] send_sigio+0xae/0x100 [] kill_fasync+0x97/0xf0 [] perf_event_wakeup+0xd4/0xf0 [] perf_pending_event+0x33/0x60 [] irq_work_run_list+0x4c/0x80 [] irq_work_run+0x18/0x40 [] smp_trace_irq_work_interrupt+0x3f/0xc0 [] trace_irq_work_interrupt+0x6d/0x80 Which is caused by an irq_work generating new irq_work and therefore not allowing forward progress. This happens because processing the perf irq_work triggers another perf event (tracepoint stuff) which in turn generates an irq_work ad infinitum. Avoid this by raising the recursion counter in the irq_work -- which effectively disables all software events (including tracepoints) from actually triggering again. Reported-by: Vince Weaver Tested-by: Vince Weaver Signed-off-by: Peter Zijlstra (Intel) Cc: Arnaldo Carvalho de Melo Cc: Jiri Olsa Cc: Paul Mackerras Cc: Steven Rostedt Cc: Link: http://lkml.kernel.org/r/20150219170311.GH21418@twins.programming.kicks-ass.net Signed-off-by: Ingo Molnar --- kernel/events/core.c | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'kernel') diff --git a/kernel/events/core.c b/kernel/events/core.c index 453ef61311d4..2fabc0627165 100644 --- a/kernel/events/core.c +++ b/kernel/events/core.c @@ -4574,6 +4574,13 @@ static void perf_pending_event(struct irq_work *entry) { struct perf_event *event = container_of(entry, struct perf_event, pending); + int rctx; + + rctx = perf_swevent_get_recursion_context(); + /* + * If we 'fail' here, that's OK, it means recursion is already disabled + * and we won't recurse 'further'. + */ if (event->pending_disable) { event->pending_disable = 0; @@ -4584,6 +4591,9 @@ static void perf_pending_event(struct irq_work *entry) event->pending_wakeup = 0; perf_event_wakeup(event); } + + if (rctx >= 0) + perf_swevent_put_recursion_context(rctx); } /* -- cgit v1.2.3 From 746db9443ea57fd9c059f62c4bfbf41cf224fe13 Mon Sep 17 00:00:00 2001 From: Brian Silverman Date: Wed, 18 Feb 2015 16:23:56 -0800 Subject: sched: Fix RLIMIT_RTTIME when PI-boosting to RT When non-realtime tasks get priority-inheritance boosted to a realtime scheduling class, RLIMIT_RTTIME starts to apply to them. However, the counter used for checking this (the same one used for SCHED_RR timeslices) was not getting reset. This meant that tasks running with a non-realtime scheduling class which are repeatedly boosted to a realtime one, but never block while they are running realtime, eventually hit the timeout without ever running for a time over the limit. This patch resets the realtime timeslice counter when un-PI-boosting from an RT to a non-RT scheduling class. I have some test code with two threads and a shared PTHREAD_PRIO_INHERIT mutex which induces priority boosting and spins while boosted that gets killed by a SIGXCPU on non-fixed kernels but doesn't with this patch applied. It happens much faster with a CONFIG_PREEMPT_RT kernel, and does happen eventually with PREEMPT_VOLUNTARY kernels. Signed-off-by: Brian Silverman Signed-off-by: Peter Zijlstra (Intel) Cc: austin@peloton-tech.com Cc: Link: http://lkml.kernel.org/r/1424305436-6716-1-git-send-email-brian@peloton-tech.com Signed-off-by: Ingo Molnar --- kernel/sched/core.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'kernel') diff --git a/kernel/sched/core.c b/kernel/sched/core.c index f0f831e8a345..62671f53202a 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -3034,6 +3034,8 @@ void rt_mutex_setprio(struct task_struct *p, int prio) } else { if (dl_prio(oldprio)) p->dl.dl_boosted = 0; + if (rt_prio(oldprio)) + p->rt.timeout = 0; p->sched_class = &fair_sched_class; } -- cgit v1.2.3 From 35a9393c95b31870a74f51a3e7455f33f5657b6f Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 26 Feb 2015 16:23:11 +0100 Subject: lockdep: Fix the module unload key range freeing logic Module unload calls lockdep_free_key_range(), which removes entries from the data structures. Most of the lockdep code OTOH assumes the data structures are append only; in specific see the comments in add_lock_to_list() and look_up_lock_class(). Clearly this has only worked by accident; make it work proper. The actual scenario to make it go boom would involve the memory freed by the module unlock being re-allocated and re-used for a lock inside of a rcu-sched grace period. This is a very unlikely scenario, still better plug the hole. Use RCU list iteration in all places and ammend the comments. Change lockdep_free_key_range() to issue a sync_sched() between removal from the lists and returning -- which results in the memory being freed. Further ensure the callers are placed correctly and comment the requirements. Signed-off-by: Peter Zijlstra (Intel) Cc: Andrew Morton Cc: Andrey Tsyvarev Cc: Linus Torvalds Cc: Paul E. McKenney Cc: Peter Zijlstra Cc: Rusty Russell Cc: Thomas Gleixner Signed-off-by: Ingo Molnar --- kernel/locking/lockdep.c | 81 ++++++++++++++++++++++++++++++++---------------- kernel/module.c | 8 ++--- 2 files changed, 59 insertions(+), 30 deletions(-) (limited to 'kernel') diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c index 88d0d4420ad2..ba77ab5f64dd 100644 --- a/kernel/locking/lockdep.c +++ b/kernel/locking/lockdep.c @@ -633,7 +633,7 @@ static int count_matching_names(struct lock_class *new_class) if (!new_class->name) return 0; - list_for_each_entry(class, &all_lock_classes, lock_entry) { + list_for_each_entry_rcu(class, &all_lock_classes, lock_entry) { if (new_class->key - new_class->subclass == class->key) return class->name_version; if (class->name && !strcmp(class->name, new_class->name)) @@ -700,10 +700,12 @@ look_up_lock_class(struct lockdep_map *lock, unsigned int subclass) hash_head = classhashentry(key); /* - * We can walk the hash lockfree, because the hash only - * grows, and we are careful when adding entries to the end: + * We do an RCU walk of the hash, see lockdep_free_key_range(). */ - list_for_each_entry(class, hash_head, hash_entry) { + if (DEBUG_LOCKS_WARN_ON(!irqs_disabled())) + return NULL; + + list_for_each_entry_rcu(class, hash_head, hash_entry) { if (class->key == key) { /* * Huh! same key, different name? Did someone trample @@ -728,7 +730,8 @@ register_lock_class(struct lockdep_map *lock, unsigned int subclass, int force) struct lockdep_subclass_key *key; struct list_head *hash_head; struct lock_class *class; - unsigned long flags; + + DEBUG_LOCKS_WARN_ON(!irqs_disabled()); class = look_up_lock_class(lock, subclass); if (likely(class)) @@ -750,28 +753,26 @@ register_lock_class(struct lockdep_map *lock, unsigned int subclass, int force) key = lock->key->subkeys + subclass; hash_head = classhashentry(key); - raw_local_irq_save(flags); if (!graph_lock()) { - raw_local_irq_restore(flags); return NULL; } /* * We have to do the hash-walk again, to avoid races * with another CPU: */ - list_for_each_entry(class, hash_head, hash_entry) + list_for_each_entry_rcu(class, hash_head, hash_entry) { if (class->key == key) goto out_unlock_set; + } + /* * Allocate a new key from the static array, and add it to * the hash: */ if (nr_lock_classes >= MAX_LOCKDEP_KEYS) { if (!debug_locks_off_graph_unlock()) { - raw_local_irq_restore(flags); return NULL; } - raw_local_irq_restore(flags); print_lockdep_off("BUG: MAX_LOCKDEP_KEYS too low!"); dump_stack(); @@ -798,7 +799,6 @@ register_lock_class(struct lockdep_map *lock, unsigned int subclass, int force) if (verbose(class)) { graph_unlock(); - raw_local_irq_restore(flags); printk("\nnew class %p: %s", class->key, class->name); if (class->name_version > 1) @@ -806,15 +806,12 @@ register_lock_class(struct lockdep_map *lock, unsigned int subclass, int force) printk("\n"); dump_stack(); - raw_local_irq_save(flags); if (!graph_lock()) { - raw_local_irq_restore(flags); return NULL; } } out_unlock_set: graph_unlock(); - raw_local_irq_restore(flags); out_set_class_cache: if (!subclass || force) @@ -870,11 +867,9 @@ static int add_lock_to_list(struct lock_class *class, struct lock_class *this, entry->distance = distance; entry->trace = *trace; /* - * Since we never remove from the dependency list, the list can - * be walked lockless by other CPUs, it's only allocation - * that must be protected by the spinlock. But this also means - * we must make new entries visible only once writes to the - * entry become visible - hence the RCU op: + * Both allocation and removal are done under the graph lock; but + * iteration is under RCU-sched; see look_up_lock_class() and + * lockdep_free_key_range(). */ list_add_tail_rcu(&entry->entry, head); @@ -1025,7 +1020,9 @@ static int __bfs(struct lock_list *source_entry, else head = &lock->class->locks_before; - list_for_each_entry(entry, head, entry) { + DEBUG_LOCKS_WARN_ON(!irqs_disabled()); + + list_for_each_entry_rcu(entry, head, entry) { if (!lock_accessed(entry)) { unsigned int cq_depth; mark_lock_accessed(entry, lock); @@ -2022,7 +2019,7 @@ static inline int lookup_chain_cache(struct task_struct *curr, * We can walk it lock-free, because entries only get added * to the hash: */ - list_for_each_entry(chain, hash_head, entry) { + list_for_each_entry_rcu(chain, hash_head, entry) { if (chain->chain_key == chain_key) { cache_hit: debug_atomic_inc(chain_lookup_hits); @@ -2996,8 +2993,18 @@ void lockdep_init_map(struct lockdep_map *lock, const char *name, if (unlikely(!debug_locks)) return; - if (subclass) + if (subclass) { + unsigned long flags; + + if (DEBUG_LOCKS_WARN_ON(current->lockdep_recursion)) + return; + + raw_local_irq_save(flags); + current->lockdep_recursion = 1; register_lock_class(lock, subclass, 1); + current->lockdep_recursion = 0; + raw_local_irq_restore(flags); + } } EXPORT_SYMBOL_GPL(lockdep_init_map); @@ -3887,9 +3894,17 @@ static inline int within(const void *addr, void *start, unsigned long size) return addr >= start && addr < start + size; } +/* + * Used in module.c to remove lock classes from memory that is going to be + * freed; and possibly re-used by other modules. + * + * We will have had one sync_sched() before getting here, so we're guaranteed + * nobody will look up these exact classes -- they're properly dead but still + * allocated. + */ void lockdep_free_key_range(void *start, unsigned long size) { - struct lock_class *class, *next; + struct lock_class *class; struct list_head *head; unsigned long flags; int i; @@ -3905,7 +3920,7 @@ void lockdep_free_key_range(void *start, unsigned long size) head = classhash_table + i; if (list_empty(head)) continue; - list_for_each_entry_safe(class, next, head, hash_entry) { + list_for_each_entry_rcu(class, head, hash_entry) { if (within(class->key, start, size)) zap_class(class); else if (within(class->name, start, size)) @@ -3916,11 +3931,25 @@ void lockdep_free_key_range(void *start, unsigned long size) if (locked) graph_unlock(); raw_local_irq_restore(flags); + + /* + * Wait for any possible iterators from look_up_lock_class() to pass + * before continuing to free the memory they refer to. + * + * sync_sched() is sufficient because the read-side is IRQ disable. + */ + synchronize_sched(); + + /* + * XXX at this point we could return the resources to the pool; + * instead we leak them. We would need to change to bitmap allocators + * instead of the linear allocators we have now. + */ } void lockdep_reset_lock(struct lockdep_map *lock) { - struct lock_class *class, *next; + struct lock_class *class; struct list_head *head; unsigned long flags; int i, j; @@ -3948,7 +3977,7 @@ void lockdep_reset_lock(struct lockdep_map *lock) head = classhash_table + i; if (list_empty(head)) continue; - list_for_each_entry_safe(class, next, head, hash_entry) { + list_for_each_entry_rcu(class, head, hash_entry) { int match = 0; for (j = 0; j < NR_LOCKDEP_CACHING_CLASSES; j++) diff --git a/kernel/module.c b/kernel/module.c index b3d634ed06c9..99fdf94efce8 100644 --- a/kernel/module.c +++ b/kernel/module.c @@ -1865,7 +1865,7 @@ static void free_module(struct module *mod) kfree(mod->args); percpu_modfree(mod); - /* Free lock-classes: */ + /* Free lock-classes; relies on the preceding sync_rcu(). */ lockdep_free_key_range(mod->module_core, mod->core_size); /* Finally, free the core (containing the module structure) */ @@ -3349,9 +3349,6 @@ static int load_module(struct load_info *info, const char __user *uargs, module_bug_cleanup(mod); mutex_unlock(&module_mutex); - /* Free lock-classes: */ - lockdep_free_key_range(mod->module_core, mod->core_size); - /* we can't deallocate the module until we clear memory protection */ unset_module_init_ro_nx(mod); unset_module_core_ro_nx(mod); @@ -3375,6 +3372,9 @@ static int load_module(struct load_info *info, const char __user *uargs, synchronize_rcu(); mutex_unlock(&module_mutex); free_module: + /* Free lock-classes; relies on the preceding sync_rcu() */ + lockdep_free_key_range(mod->module_core, mod->core_size); + module_deallocate(mod, info); free_copy: free_copy(info); -- cgit v1.2.3 From a127d2bcf1fbc8c8e0b5cf0dab54f7d3ff50ce47 Mon Sep 17 00:00:00 2001 From: Preeti U Murthy Date: Wed, 18 Mar 2015 16:19:27 +0530 Subject: timers/tick/broadcast-hrtimer: Fix suspicious RCU usage in idle loop The hrtimer mode of broadcast queues hrtimers in the idle entry path so as to wakeup cpus in deep idle states. The associated call graph is : cpuidle_idle_call() |____ clockevents_notify(CLOCK_EVT_NOTIFY_BROADCAST_ENTER, ....)) |_____tick_broadcast_set_event() |____clockevents_program_event() |____bc_set_next() The hrtimer_{start/cancel} functions call into tracing which uses RCU. But it is not legal to call into RCU in cpuidle because it is one of the quiescent states. Hence protect this region with RCU_NONIDLE which informs RCU that the cpu is momentarily non-idle. As an aside it is helpful to point out that the clock event device that is programmed here is not a per-cpu clock device; it is a pseudo clock device, used by the broadcast framework alone. The per-cpu clock device programming never goes through bc_set_next(). Signed-off-by: Preeti U Murthy Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Paul E. McKenney Cc: linuxppc-dev@ozlabs.org Cc: mpe@ellerman.id.au Cc: tglx@linutronix.de Link: http://lkml.kernel.org/r/20150318104705.17763.56668.stgit@preeti.in.ibm.com Signed-off-by: Ingo Molnar --- kernel/time/tick-broadcast-hrtimer.c | 11 +++++++++-- 1 file changed, 9 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/time/tick-broadcast-hrtimer.c b/kernel/time/tick-broadcast-hrtimer.c index eb682d5c697c..6aac4beedbbe 100644 --- a/kernel/time/tick-broadcast-hrtimer.c +++ b/kernel/time/tick-broadcast-hrtimer.c @@ -49,6 +49,7 @@ static void bc_set_mode(enum clock_event_mode mode, */ static int bc_set_next(ktime_t expires, struct clock_event_device *bc) { + int bc_moved; /* * We try to cancel the timer first. If the callback is on * flight on some other cpu then we let it handle it. If we @@ -60,9 +61,15 @@ static int bc_set_next(ktime_t expires, struct clock_event_device *bc) * restart the timer because we are in the callback, but we * can set the expiry time and let the callback return * HRTIMER_RESTART. + * + * Since we are in the idle loop at this point and because + * hrtimer_{start/cancel} functions call into tracing, + * calls to these functions must be bound within RCU_NONIDLE. */ - if (hrtimer_try_to_cancel(&bctimer) >= 0) { - hrtimer_start(&bctimer, expires, HRTIMER_MODE_ABS_PINNED); + RCU_NONIDLE(bc_moved = (hrtimer_try_to_cancel(&bctimer) >= 0) ? + !hrtimer_start(&bctimer, expires, HRTIMER_MODE_ABS_PINNED) : + 0); + if (bc_moved) { /* Bind the "device" to the cpu */ bc->bound_on = smp_processor_id(); } else if (bc->bound_on == smp_processor_id()) { -- cgit v1.2.3 From 074c238177a75f5e79af3b2cb6a84e54823ef950 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Wed, 25 Mar 2015 15:55:42 -0700 Subject: mm: numa: slow PTE scan rate if migration failures occur Dave Chinner reported the following on https://lkml.org/lkml/2015/3/1/226 Across the board the 4.0-rc1 numbers are much slower, and the degradation is far worse when using the large memory footprint configs. Perf points straight at the cause - this is from 4.0-rc1 on the "-o bhash=101073" config: - 56.07% 56.07% [kernel] [k] default_send_IPI_mask_sequence_phys - default_send_IPI_mask_sequence_phys - 99.99% physflat_send_IPI_mask - 99.37% native_send_call_func_ipi smp_call_function_many - native_flush_tlb_others - 99.85% flush_tlb_page ptep_clear_flush try_to_unmap_one rmap_walk try_to_unmap migrate_pages migrate_misplaced_page - handle_mm_fault - 99.73% __do_page_fault trace_do_page_fault do_async_page_fault + async_page_fault 0.63% native_send_call_func_single_ipi generic_exec_single smp_call_function_single This is showing excessive migration activity even though excessive migrations are meant to get throttled. Normally, the scan rate is tuned on a per-task basis depending on the locality of faults. However, if migrations fail for any reason then the PTE scanner may scan faster if the faults continue to be remote. This means there is higher system CPU overhead and fault trapping at exactly the time we know that migrations cannot happen. This patch tracks when migration failures occur and slows the PTE scanner. Signed-off-by: Mel Gorman Reported-by: Dave Chinner Tested-by: Dave Chinner Cc: Ingo Molnar Cc: Aneesh Kumar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- kernel/sched/fair.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'kernel') diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 7ce18f3c097a..bcfe32088b37 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -1609,9 +1609,11 @@ static void update_task_scan_period(struct task_struct *p, /* * If there were no record hinting faults then either the task is * completely idle or all activity is areas that are not of interest - * to automatic numa balancing. Scan slower + * to automatic numa balancing. Related to that, if there were failed + * migration then it implies we are migrating too quickly or the local + * node is overloaded. In either case, scan slower */ - if (local + shared == 0) { + if (local + shared == 0 || p->numa_faults_locality[2]) { p->numa_scan_period = min(p->numa_scan_period_max, p->numa_scan_period << 1); @@ -2080,6 +2082,8 @@ void task_numa_fault(int last_cpupid, int mem_node, int pages, int flags) if (migrated) p->numa_pages_migrated += pages; + if (flags & TNF_MIGRATE_FAIL) + p->numa_faults_locality[2] += pages; p->numa_faults[task_faults_idx(NUMA_MEMBUF, mem_node, priv)] += pages; p->numa_faults[task_faults_idx(NUMA_CPUBUF, cpu_node, priv)] += pages; -- cgit v1.2.3 From 608cd71a9c7c9db76e78a792c5a4101e12fea43f Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Thu, 26 Mar 2015 19:53:57 -0700 Subject: tc: bpf: generalize pedit action existing TC action 'pedit' can munge any bits of the packet. Generalize it for use in bpf programs attached as cls_bpf and act_bpf via bpf_skb_store_bytes() helper function. Signed-off-by: Alexei Starovoitov Reviewed-by: Jiri Pirko Acked-by: Daniel Borkmann Signed-off-by: David S. Miller --- kernel/bpf/verifier.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'kernel') diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 0e714f799ec0..630a7bac1e51 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -773,6 +773,8 @@ static int check_func_arg(struct verifier_env *env, u32 regno, expected_type = CONST_IMM; } else if (arg_type == ARG_CONST_MAP_PTR) { expected_type = CONST_PTR_TO_MAP; + } else if (arg_type == ARG_PTR_TO_CTX) { + expected_type = PTR_TO_CTX; } else { verbose("unsupported arg_type %d\n", arg_type); return -EFAULT; -- cgit v1.2.3