From afd594240806acc138cf696c09f2f4829d55d02f Mon Sep 17 00:00:00 2001 From: Edward Cree Date: Fri, 16 Nov 2018 12:00:07 +0000 Subject: bpf: fix off-by-one error in adjust_subprog_starts When patching in a new sequence for the first insn of a subprog, the start of that subprog does not change (it's the first insn of the sequence), so adjust_subprog_starts should check start <= off (rather than < off). Also added a test to test_verifier.c (it's essentially the syz reproducer). Fixes: cc8b0b92a169 ("bpf: introduce function calls (function boundaries)") Reported-by: syzbot+4fc427c7af994b0948be@syzkaller.appspotmail.com Signed-off-by: Edward Cree Acked-by: Yonghong Song Signed-off-by: Alexei Starovoitov --- kernel/bpf/verifier.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 1971ca325fb4..6dd419550aba 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -5650,7 +5650,7 @@ static void adjust_subprog_starts(struct bpf_verifier_env *env, u32 off, u32 len return; /* NOTE: fake 'exit' subprog should be updated as well. */ for (i = 0; i <= env->subprog_cnt; i++) { - if (env->subprog_info[i].start < off) + if (env->subprog_info[i].start <= off) continue; env->subprog_info[i].start += len - 1; } -- cgit v1.2.3 From 569a933b03f3c48b392fe67c0086b3a6b9306b5a Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Wed, 14 Nov 2018 10:00:34 -0800 Subject: bpf: allocate local storage buffers using GFP_ATOMIC Naresh reported an issue with the non-atomic memory allocation of cgroup local storage buffers: [ 73.047526] BUG: sleeping function called from invalid context at /srv/oe/build/tmp-rpb-glibc/work-shared/intel-corei7-64/kernel-source/mm/slab.h:421 [ 73.060915] in_atomic(): 1, irqs_disabled(): 0, pid: 3157, name: test_cgroup_sto [ 73.068342] INFO: lockdep is turned off. [ 73.072293] CPU: 2 PID: 3157 Comm: test_cgroup_sto Not tainted 4.20.0-rc2-next-20181113 #1 [ 73.080548] Hardware name: Supermicro SYS-5019S-ML/X11SSH-F, BIOS 2.0b 07/27/2017 [ 73.088018] Call Trace: [ 73.090463] dump_stack+0x70/0xa5 [ 73.093783] ___might_sleep+0x152/0x240 [ 73.097619] __might_sleep+0x4a/0x80 [ 73.101191] __kmalloc_node+0x1cf/0x2f0 [ 73.105031] ? cgroup_storage_update_elem+0x46/0x90 [ 73.109909] cgroup_storage_update_elem+0x46/0x90 cgroup_storage_update_elem() (as well as other update map update callbacks) is called with disabled preemption, so GFP_ATOMIC allocation should be used: e.g. alloc_htab_elem() in hashtab.c. Reported-by: Naresh Kamboju Tested-by: Naresh Kamboju Signed-off-by: Roman Gushchin Cc: Alexei Starovoitov Cc: Daniel Borkmann Signed-off-by: Alexei Starovoitov --- kernel/bpf/local_storage.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/bpf/local_storage.c b/kernel/bpf/local_storage.c index c97a8f968638..bed9d48a7ae9 100644 --- a/kernel/bpf/local_storage.c +++ b/kernel/bpf/local_storage.c @@ -139,7 +139,8 @@ static int cgroup_storage_update_elem(struct bpf_map *map, void *_key, return -ENOENT; new = kmalloc_node(sizeof(struct bpf_storage_buffer) + - map->value_size, __GFP_ZERO | GFP_USER, + map->value_size, + __GFP_ZERO | GFP_ATOMIC | __GFP_NOWARN, map->numa_node); if (!new) return -ENOMEM; -- cgit v1.2.3 From cb216b84d6ea24fa10f1e7aac35de77246841041 Mon Sep 17 00:00:00 2001 From: Robin Murphy Date: Wed, 21 Nov 2018 16:00:51 +0000 Subject: swiotlb: Skip cache maintenance on map error If swiotlb_bounce_page() failed, calling arch_sync_dma_for_device() may lead to such delights as performing cache maintenance on whatever address phys_to_virt(SWIOTLB_MAP_ERROR) looks like, which is typically outside the kernel memory map and goes about as well as expected. Don't do that. Fixes: a4a4330db46a ("swiotlb: add support for non-coherent DMA") Tested-by: John Stultz Signed-off-by: Robin Murphy Signed-off-by: Christoph Hellwig --- kernel/dma/swiotlb.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'kernel') diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c index 5731daa09a32..045930e32c0e 100644 --- a/kernel/dma/swiotlb.c +++ b/kernel/dma/swiotlb.c @@ -679,7 +679,8 @@ dma_addr_t swiotlb_map_page(struct device *dev, struct page *page, } if (!dev_is_dma_coherent(dev) && - (attrs & DMA_ATTR_SKIP_CPU_SYNC) == 0) + (attrs & DMA_ATTR_SKIP_CPU_SYNC) == 0 && + dev_addr != DIRECT_MAPPING_ERROR) arch_sync_dma_for_device(dev, phys, size, dir); return dev_addr; -- cgit v1.2.3 From 813961de3ee6474dd5703e883471fd941d6c8f69 Mon Sep 17 00:00:00 2001 From: Alexei Starovoitov Date: Thu, 22 Nov 2018 10:49:56 -0800 Subject: bpf: fix integer overflow in queue_stack_map Fix the following issues: - allow queue_stack_map for root only - fix u32 max_entries overflow - disallow value_size == 0 Fixes: f1a2e44a3aec ("bpf: add queue and stack maps") Reported-by: Wei Wu Signed-off-by: Alexei Starovoitov Cc: Mauricio Vasquez B Signed-off-by: Daniel Borkmann --- kernel/bpf/queue_stack_maps.c | 16 ++++++++-------- 1 file changed, 8 insertions(+), 8 deletions(-) (limited to 'kernel') diff --git a/kernel/bpf/queue_stack_maps.c b/kernel/bpf/queue_stack_maps.c index 8bbd72d3a121..b384ea9f3254 100644 --- a/kernel/bpf/queue_stack_maps.c +++ b/kernel/bpf/queue_stack_maps.c @@ -7,6 +7,7 @@ #include #include #include +#include #include "percpu_freelist.h" #define QUEUE_STACK_CREATE_FLAG_MASK \ @@ -45,8 +46,12 @@ static bool queue_stack_map_is_full(struct bpf_queue_stack *qs) /* Called from syscall */ static int queue_stack_map_alloc_check(union bpf_attr *attr) { + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + /* check sanity of attributes */ if (attr->max_entries == 0 || attr->key_size != 0 || + attr->value_size == 0 || attr->map_flags & ~QUEUE_STACK_CREATE_FLAG_MASK) return -EINVAL; @@ -63,15 +68,10 @@ static struct bpf_map *queue_stack_map_alloc(union bpf_attr *attr) { int ret, numa_node = bpf_map_attr_numa_node(attr); struct bpf_queue_stack *qs; - u32 size, value_size; - u64 queue_size, cost; - - size = attr->max_entries + 1; - value_size = attr->value_size; - - queue_size = sizeof(*qs) + (u64) value_size * size; + u64 size, queue_size, cost; - cost = queue_size; + size = (u64) attr->max_entries + 1; + cost = queue_size = sizeof(*qs) + size * attr->value_size; if (cost >= U32_MAX - PAGE_SIZE) return ERR_PTR(-E2BIG); -- cgit v1.2.3 From 1efb6ee3edea57f57f9fb05dba8dcb3f7333f61f Mon Sep 17 00:00:00 2001 From: Martynas Pumputis Date: Fri, 23 Nov 2018 17:43:26 +0100 Subject: bpf: fix check of allowed specifiers in bpf_trace_printk A format string consisting of "%p" or "%s" followed by an invalid specifier (e.g. "%p%\n" or "%s%") could pass the check which would make format_decode (lib/vsprintf.c) to warn. Fixes: 9c959c863f82 ("tracing: Allow BPF programs to call bpf_trace_printk()") Reported-by: syzbot+1ec5c5ec949c4adaa0c4@syzkaller.appspotmail.com Signed-off-by: Martynas Pumputis Signed-off-by: Daniel Borkmann --- kernel/trace/bpf_trace.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) (limited to 'kernel') diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 08fcfe440c63..9864a35c8bb5 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -196,11 +196,13 @@ BPF_CALL_5(bpf_trace_printk, char *, fmt, u32, fmt_size, u64, arg1, i++; } else if (fmt[i] == 'p' || fmt[i] == 's') { mod[fmt_cnt]++; - i++; - if (!isspace(fmt[i]) && !ispunct(fmt[i]) && fmt[i] != 0) + /* disallow any further format extensions */ + if (fmt[i + 1] != 0 && + !isspace(fmt[i + 1]) && + !ispunct(fmt[i + 1])) return -EINVAL; fmt_cnt++; - if (fmt[i - 1] == 's') { + if (fmt[i] == 's') { if (str_seen) /* allow only one '%s' per fmt string */ return -EINVAL; -- cgit v1.2.3 From e2c95a61656d29ceaac97b6a975c8a1f26e26f15 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Mon, 26 Nov 2018 14:05:38 +0100 Subject: bpf, ppc64: generalize fetching subprog into bpf_jit_get_func_addr Make fetching of the BPF call address from ppc64 JIT generic. ppc64 was using a slightly different variant rather than through the insns' imm field encoding as the target address would not fit into that space. Therefore, the target subprog number was encoded into the insns' offset and fetched through fp->aux->func[off]->bpf_func instead. Given there are other JITs with this issue and the mechanism of fetching the address is JIT-generic, move it into the core as a helper instead. On the JIT side, we get information on whether the retrieved address is a fixed one, that is, not changing through JIT passes, or a dynamic one. For the former, JITs can optimize their imm emission because this doesn't change jump offsets throughout JIT process. Signed-off-by: Daniel Borkmann Reviewed-by: Sandipan Das Tested-by: Sandipan Das Signed-off-by: Alexei Starovoitov --- arch/powerpc/net/bpf_jit_comp64.c | 57 ++++++++++++++++++++++++++------------- include/linux/filter.h | 4 +++ kernel/bpf/core.c | 34 +++++++++++++++++++++++ 3 files changed, 76 insertions(+), 19 deletions(-) (limited to 'kernel') diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c index 50b129785aee..17482f5de3e2 100644 --- a/arch/powerpc/net/bpf_jit_comp64.c +++ b/arch/powerpc/net/bpf_jit_comp64.c @@ -166,7 +166,33 @@ static void bpf_jit_build_epilogue(u32 *image, struct codegen_context *ctx) PPC_BLR(); } -static void bpf_jit_emit_func_call(u32 *image, struct codegen_context *ctx, u64 func) +static void bpf_jit_emit_func_call_hlp(u32 *image, struct codegen_context *ctx, + u64 func) +{ +#ifdef PPC64_ELF_ABI_v1 + /* func points to the function descriptor */ + PPC_LI64(b2p[TMP_REG_2], func); + /* Load actual entry point from function descriptor */ + PPC_BPF_LL(b2p[TMP_REG_1], b2p[TMP_REG_2], 0); + /* ... and move it to LR */ + PPC_MTLR(b2p[TMP_REG_1]); + /* + * Load TOC from function descriptor at offset 8. + * We can clobber r2 since we get called through a + * function pointer (so caller will save/restore r2) + * and since we don't use a TOC ourself. + */ + PPC_BPF_LL(2, b2p[TMP_REG_2], 8); +#else + /* We can clobber r12 */ + PPC_FUNC_ADDR(12, func); + PPC_MTLR(12); +#endif + PPC_BLRL(); +} + +static void bpf_jit_emit_func_call_rel(u32 *image, struct codegen_context *ctx, + u64 func) { unsigned int i, ctx_idx = ctx->idx; @@ -273,7 +299,7 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, { const struct bpf_insn *insn = fp->insnsi; int flen = fp->len; - int i; + int i, ret; /* Start of epilogue code - will only be valid 2nd pass onwards */ u32 exit_addr = addrs[flen]; @@ -284,8 +310,9 @@ static int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, u32 src_reg = b2p[insn[i].src_reg]; s16 off = insn[i].off; s32 imm = insn[i].imm; + bool func_addr_fixed; + u64 func_addr; u64 imm64; - u8 *func; u32 true_cond; u32 tmp_idx; @@ -711,23 +738,15 @@ emit_clear: case BPF_JMP | BPF_CALL: ctx->seen |= SEEN_FUNC; - /* bpf function call */ - if (insn[i].src_reg == BPF_PSEUDO_CALL) - if (!extra_pass) - func = NULL; - else if (fp->aux->func && off < fp->aux->func_cnt) - /* use the subprog id from the off - * field to lookup the callee address - */ - func = (u8 *) fp->aux->func[off]->bpf_func; - else - return -EINVAL; - /* kernel helper call */ - else - func = (u8 *) __bpf_call_base + imm; - - bpf_jit_emit_func_call(image, ctx, (u64)func); + ret = bpf_jit_get_func_addr(fp, &insn[i], extra_pass, + &func_addr, &func_addr_fixed); + if (ret < 0) + return ret; + if (func_addr_fixed) + bpf_jit_emit_func_call_hlp(image, ctx, func_addr); + else + bpf_jit_emit_func_call_rel(image, ctx, func_addr); /* move return value from r3 to BPF_REG_0 */ PPC_MR(b2p[BPF_REG_0], 3); break; diff --git a/include/linux/filter.h b/include/linux/filter.h index de629b706d1d..448dcc448f1f 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -866,6 +866,10 @@ void bpf_jit_binary_free(struct bpf_binary_header *hdr); void bpf_jit_free(struct bpf_prog *fp); +int bpf_jit_get_func_addr(const struct bpf_prog *prog, + const struct bpf_insn *insn, bool extra_pass, + u64 *func_addr, bool *func_addr_fixed); + struct bpf_prog *bpf_jit_blind_constants(struct bpf_prog *fp); void bpf_jit_prog_release_other(struct bpf_prog *fp, struct bpf_prog *fp_other); diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 1a796e0799ec..b1a3545d0ec8 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -672,6 +672,40 @@ void __weak bpf_jit_free(struct bpf_prog *fp) bpf_prog_unlock_free(fp); } +int bpf_jit_get_func_addr(const struct bpf_prog *prog, + const struct bpf_insn *insn, bool extra_pass, + u64 *func_addr, bool *func_addr_fixed) +{ + s16 off = insn->off; + s32 imm = insn->imm; + u8 *addr; + + *func_addr_fixed = insn->src_reg != BPF_PSEUDO_CALL; + if (!*func_addr_fixed) { + /* Place-holder address till the last pass has collected + * all addresses for JITed subprograms in which case we + * can pick them up from prog->aux. + */ + if (!extra_pass) + addr = NULL; + else if (prog->aux->func && + off >= 0 && off < prog->aux->func_cnt) + addr = (u8 *)prog->aux->func[off]->bpf_func; + else + return -EINVAL; + } else { + /* Address of a BPF helper call. Since part of the core + * kernel, it's always at a fixed location. __bpf_call_base + * and the helper with imm relative to it are both in core + * kernel. + */ + addr = (u8 *)__bpf_call_base + imm; + } + + *func_addr = (unsigned long)addr; + return 0; +} + static int bpf_jit_blind_insn(const struct bpf_insn *from, const struct bpf_insn *aux, struct bpf_insn *to_buff) -- cgit v1.2.3