diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2017-07-05 22:31:59 +0300 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2017-07-05 22:31:59 +0300 |
commit | 5518b69b76680a4f2df96b1deca260059db0c2de (patch) | |
tree | f33cd1519c8efb4590500f2f9617400be233238c /arch/x86/net | |
parent | 8ad06e56dcbc1984ef0ff8f6e3c19982c5809f73 (diff) | |
parent | 0e72582270c07850b92cac351c8b97d4f9c123b9 (diff) | |
download | linux-5518b69b76680a4f2df96b1deca260059db0c2de.tar.xz |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next
Pull networking updates from David Miller:
"Reasonably busy this cycle, but perhaps not as busy as in the 4.12
merge window:
1) Several optimizations for UDP processing under high load from
Paolo Abeni.
2) Support pacing internally in TCP when using the sch_fq packet
scheduler for this is not practical. From Eric Dumazet.
3) Support mutliple filter chains per qdisc, from Jiri Pirko.
4) Move to 1ms TCP timestamp clock, from Eric Dumazet.
5) Add batch dequeueing to vhost_net, from Jason Wang.
6) Flesh out more completely SCTP checksum offload support, from
Davide Caratti.
7) More plumbing of extended netlink ACKs, from David Ahern, Pablo
Neira Ayuso, and Matthias Schiffer.
8) Add devlink support to nfp driver, from Simon Horman.
9) Add RTM_F_FIB_MATCH flag to RTM_GETROUTE queries, from Roopa
Prabhu.
10) Add stack depth tracking to BPF verifier and use this information
in the various eBPF JITs. From Alexei Starovoitov.
11) Support XDP on qed device VFs, from Yuval Mintz.
12) Introduce BPF PROG ID for better introspection of installed BPF
programs. From Martin KaFai Lau.
13) Add bpf_set_hash helper for TC bpf programs, from Daniel Borkmann.
14) For loads, allow narrower accesses in bpf verifier checking, from
Yonghong Song.
15) Support MIPS in the BPF selftests and samples infrastructure, the
MIPS eBPF JIT will be merged in via the MIPS GIT tree. From David
Daney.
16) Support kernel based TLS, from Dave Watson and others.
17) Remove completely DST garbage collection, from Wei Wang.
18) Allow installing TCP MD5 rules using prefixes, from Ivan
Delalande.
19) Add XDP support to Intel i40e driver, from Björn Töpel
20) Add support for TC flower offload in nfp driver, from Simon
Horman, Pieter Jansen van Vuuren, Benjamin LaHaise, Jakub
Kicinski, and Bert van Leeuwen.
21) IPSEC offloading support in mlx5, from Ilan Tayari.
22) Add HW PTP support to macb driver, from Rafal Ozieblo.
23) Networking refcount_t conversions, From Elena Reshetova.
24) Add sock_ops support to BPF, from Lawrence Brako. This is useful
for tuning the TCP sockopt settings of a group of applications,
currently via CGROUPs"
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1899 commits)
net: phy: dp83867: add workaround for incorrect RX_CTRL pin strap
dt-bindings: phy: dp83867: provide a workaround for incorrect RX_CTRL pin strap
cxgb4: Support for get_ts_info ethtool method
cxgb4: Add PTP Hardware Clock (PHC) support
cxgb4: time stamping interface for PTP
nfp: default to chained metadata prepend format
nfp: remove legacy MAC address lookup
nfp: improve order of interfaces in breakout mode
net: macb: remove extraneous return when MACB_EXT_DESC is defined
bpf: add missing break in for the TCP_BPF_SNDCWND_CLAMP case
bpf: fix return in load_bpf_file
mpls: fix rtm policy in mpls_getroute
net, ax25: convert ax25_cb.refcount from atomic_t to refcount_t
net, ax25: convert ax25_route.refcount from atomic_t to refcount_t
net, ax25: convert ax25_uid_assoc.refcount from atomic_t to refcount_t
net, sctp: convert sctp_ep_common.refcnt from atomic_t to refcount_t
net, sctp: convert sctp_transport.refcnt from atomic_t to refcount_t
net, sctp: convert sctp_chunk.refcnt from atomic_t to refcount_t
net, sctp: convert sctp_datamsg.refcnt from atomic_t to refcount_t
net, sctp: convert sctp_auth_bytes.refcnt from atomic_t to refcount_t
...
Diffstat (limited to 'arch/x86/net')
-rw-r--r-- | arch/x86/net/bpf_jit.S | 20 | ||||
-rw-r--r-- | arch/x86/net/bpf_jit_comp.c | 66 |
2 files changed, 45 insertions, 41 deletions
diff --git a/arch/x86/net/bpf_jit.S b/arch/x86/net/bpf_jit.S index f2a7faf4706e..b33093f84528 100644 --- a/arch/x86/net/bpf_jit.S +++ b/arch/x86/net/bpf_jit.S @@ -19,9 +19,6 @@ */ #define SKBDATA %r10 #define SKF_MAX_NEG_OFF $(-0x200000) /* SKF_LL_OFF from filter.h */ -#define MAX_BPF_STACK (512 /* from filter.h */ + \ - 32 /* space for rbx,r13,r14,r15 */ + \ - 8 /* space for skb_copy_bits */) #define FUNC(name) \ .globl name; \ @@ -66,7 +63,7 @@ FUNC(sk_load_byte_positive_offset) /* rsi contains offset and can be scratched */ #define bpf_slow_path_common(LEN) \ - lea -MAX_BPF_STACK + 32(%rbp), %rdx;\ + lea 32(%rbp), %rdx;\ FRAME_BEGIN; \ mov %rbx, %rdi; /* arg1 == skb */ \ push %r9; \ @@ -83,14 +80,14 @@ FUNC(sk_load_byte_positive_offset) bpf_slow_path_word: bpf_slow_path_common(4) js bpf_error - mov - MAX_BPF_STACK + 32(%rbp),%eax + mov 32(%rbp),%eax bswap %eax ret bpf_slow_path_half: bpf_slow_path_common(2) js bpf_error - mov - MAX_BPF_STACK + 32(%rbp),%ax + mov 32(%rbp),%ax rol $8,%ax movzwl %ax,%eax ret @@ -98,7 +95,7 @@ bpf_slow_path_half: bpf_slow_path_byte: bpf_slow_path_common(1) js bpf_error - movzbl - MAX_BPF_STACK + 32(%rbp),%eax + movzbl 32(%rbp),%eax ret #define sk_negative_common(SIZE) \ @@ -148,9 +145,10 @@ FUNC(sk_load_byte_negative_offset) bpf_error: # force a return 0 from jit handler xor %eax,%eax - mov - MAX_BPF_STACK(%rbp),%rbx - mov - MAX_BPF_STACK + 8(%rbp),%r13 - mov - MAX_BPF_STACK + 16(%rbp),%r14 - mov - MAX_BPF_STACK + 24(%rbp),%r15 + mov (%rbp),%rbx + mov 8(%rbp),%r13 + mov 16(%rbp),%r14 + mov 24(%rbp),%r15 + add $40, %rbp leaveq ret diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index f58939393eef..e1324f280e06 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -197,17 +197,16 @@ struct jit_context { #define BPF_MAX_INSN_SIZE 128 #define BPF_INSN_SAFETY 64 -#define STACKSIZE \ - (MAX_BPF_STACK + \ - 32 /* space for rbx, r13, r14, r15 */ + \ +#define AUX_STACK_SPACE \ + (32 /* space for rbx, r13, r14, r15 */ + \ 8 /* space for skb_copy_bits() buffer */) -#define PROLOGUE_SIZE 48 +#define PROLOGUE_SIZE 37 /* emit x64 prologue code for BPF program and check it's size. * bpf_tail_call helper will skip it while jumping into another program */ -static void emit_prologue(u8 **pprog) +static void emit_prologue(u8 **pprog, u32 stack_depth) { u8 *prog = *pprog; int cnt = 0; @@ -215,13 +214,17 @@ static void emit_prologue(u8 **pprog) EMIT1(0x55); /* push rbp */ EMIT3(0x48, 0x89, 0xE5); /* mov rbp,rsp */ - /* sub rsp, STACKSIZE */ - EMIT3_off32(0x48, 0x81, 0xEC, STACKSIZE); + /* sub rsp, rounded_stack_depth + AUX_STACK_SPACE */ + EMIT3_off32(0x48, 0x81, 0xEC, + round_up(stack_depth, 8) + AUX_STACK_SPACE); + + /* sub rbp, AUX_STACK_SPACE */ + EMIT4(0x48, 0x83, 0xED, AUX_STACK_SPACE); /* all classic BPF filters use R6(rbx) save it */ - /* mov qword ptr [rbp-X],rbx */ - EMIT3_off32(0x48, 0x89, 0x9D, -STACKSIZE); + /* mov qword ptr [rbp+0],rbx */ + EMIT4(0x48, 0x89, 0x5D, 0); /* bpf_convert_filter() maps classic BPF register X to R7 and uses R8 * as temporary, so all tcpdump filters need to spill/fill R7(r13) and @@ -231,12 +234,12 @@ static void emit_prologue(u8 **pprog) * than synthetic ones. Therefore not worth adding complexity. */ - /* mov qword ptr [rbp-X],r13 */ - EMIT3_off32(0x4C, 0x89, 0xAD, -STACKSIZE + 8); - /* mov qword ptr [rbp-X],r14 */ - EMIT3_off32(0x4C, 0x89, 0xB5, -STACKSIZE + 16); - /* mov qword ptr [rbp-X],r15 */ - EMIT3_off32(0x4C, 0x89, 0xBD, -STACKSIZE + 24); + /* mov qword ptr [rbp+8],r13 */ + EMIT4(0x4C, 0x89, 0x6D, 8); + /* mov qword ptr [rbp+16],r14 */ + EMIT4(0x4C, 0x89, 0x75, 16); + /* mov qword ptr [rbp+24],r15 */ + EMIT4(0x4C, 0x89, 0x7D, 24); /* Clear the tail call counter (tail_call_cnt): for eBPF tail calls * we need to reset the counter to 0. It's done in two instructions, @@ -246,8 +249,8 @@ static void emit_prologue(u8 **pprog) /* xor eax, eax */ EMIT2(0x31, 0xc0); - /* mov qword ptr [rbp-X], rax */ - EMIT3_off32(0x48, 0x89, 0x85, -STACKSIZE + 32); + /* mov qword ptr [rbp+32], rax */ + EMIT4(0x48, 0x89, 0x45, 32); BUILD_BUG_ON(cnt != PROLOGUE_SIZE); *pprog = prog; @@ -289,13 +292,13 @@ static void emit_bpf_tail_call(u8 **pprog) /* if (tail_call_cnt > MAX_TAIL_CALL_CNT) * goto out; */ - EMIT2_off32(0x8B, 0x85, -STACKSIZE + 36); /* mov eax, dword ptr [rbp - 516] */ + EMIT2_off32(0x8B, 0x85, 36); /* mov eax, dword ptr [rbp + 36] */ EMIT3(0x83, 0xF8, MAX_TAIL_CALL_CNT); /* cmp eax, MAX_TAIL_CALL_CNT */ #define OFFSET2 36 EMIT2(X86_JA, OFFSET2); /* ja out */ label2 = cnt; EMIT3(0x83, 0xC0, 0x01); /* add eax, 1 */ - EMIT2_off32(0x89, 0x85, -STACKSIZE + 36); /* mov dword ptr [rbp - 516], eax */ + EMIT2_off32(0x89, 0x85, 36); /* mov dword ptr [rbp + 36], eax */ /* prog = array->ptrs[index]; */ EMIT4_off32(0x48, 0x8D, 0x84, 0xD6, /* lea rax, [rsi + rdx * 8 + offsetof(...)] */ @@ -361,7 +364,7 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, int proglen = 0; u8 *prog = temp; - emit_prologue(&prog); + emit_prologue(&prog, bpf_prog->aux->stack_depth); if (seen_ld_abs) emit_load_skb_data_hlen(&prog); @@ -877,7 +880,7 @@ xadd: if (is_imm8(insn->off)) } break; - case BPF_JMP | BPF_CALL | BPF_X: + case BPF_JMP | BPF_TAIL_CALL: emit_bpf_tail_call(&prog); break; @@ -1036,15 +1039,17 @@ common_load: seen_exit = true; /* update cleanup_addr */ ctx->cleanup_addr = proglen; - /* mov rbx, qword ptr [rbp-X] */ - EMIT3_off32(0x48, 0x8B, 0x9D, -STACKSIZE); - /* mov r13, qword ptr [rbp-X] */ - EMIT3_off32(0x4C, 0x8B, 0xAD, -STACKSIZE + 8); - /* mov r14, qword ptr [rbp-X] */ - EMIT3_off32(0x4C, 0x8B, 0xB5, -STACKSIZE + 16); - /* mov r15, qword ptr [rbp-X] */ - EMIT3_off32(0x4C, 0x8B, 0xBD, -STACKSIZE + 24); - + /* mov rbx, qword ptr [rbp+0] */ + EMIT4(0x48, 0x8B, 0x5D, 0); + /* mov r13, qword ptr [rbp+8] */ + EMIT4(0x4C, 0x8B, 0x6D, 8); + /* mov r14, qword ptr [rbp+16] */ + EMIT4(0x4C, 0x8B, 0x75, 16); + /* mov r15, qword ptr [rbp+24] */ + EMIT4(0x4C, 0x8B, 0x7D, 24); + + /* add rbp, AUX_STACK_SPACE */ + EMIT4(0x48, 0x83, 0xC5, AUX_STACK_SPACE); EMIT1(0xC9); /* leave */ EMIT1(0xC3); /* ret */ break; @@ -1162,6 +1167,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) bpf_jit_binary_lock_ro(header); prog->bpf_func = (void *)image; prog->jited = 1; + prog->jited_len = proglen; } else { prog = orig_prog; } |