From 5b7c4cabbb65f5c469464da6c5f614cbd7f730f2 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Tue, 21 Feb 2023 18:24:12 -0800 Subject: Merge tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next Pull networking updates from Jakub Kicinski: "Core: - Add dedicated kmem_cache for typical/small skb->head, avoid having to access struct page at kfree time, and improve memory use. - Introduce sysctl to set default RPS configuration for new netdevs. - Define Netlink protocol specification format which can be used to describe messages used by each family and auto-generate parsers. Add tools for generating kernel data structures and uAPI headers. - Expose all net/core sysctls inside netns. - Remove 4s sleep in netpoll if carrier is instantly detected on boot. - Add configurable limit of MDB entries per port, and port-vlan. - Continue populating drop reasons throughout the stack. - Retire a handful of legacy Qdiscs and classifiers. Protocols: - Support IPv4 big TCP (TSO frames larger than 64kB). - Add IP_LOCAL_PORT_RANGE socket option, to control local port range on socket by socket basis. - Track and report in procfs number of MPTCP sockets used. - Support mixing IPv4 and IPv6 flows in the in-kernel MPTCP path manager. - IPv6: don't check net.ipv6.route.max_size and rely on garbage collection to free memory (similarly to IPv4). - Support Penultimate Segment Pop (PSP) flavor in SRv6 (RFC8986). - ICMP: add per-rate limit counters. - Add support for user scanning requests in ieee802154. - Remove static WEP support. - Support minimal Wi-Fi 7 Extremely High Throughput (EHT) rate reporting. - WiFi 7 EHT channel puncturing support (client & AP). BPF: - Add a rbtree data structure following the "next-gen data structure" precedent set by recently added linked list, that is, by using kfunc + kptr instead of adding a new BPF map type. - Expose XDP hints via kfuncs with initial support for RX hash and timestamp metadata. - Add BPF_F_NO_TUNNEL_KEY extension to bpf_skb_set_tunnel_key to better support decap on GRE tunnel devices not operating in collect metadata. - Improve x86 JIT's codegen for PROBE_MEM runtime error checks. - Remove the need for trace_printk_lock for bpf_trace_printk and bpf_trace_vprintk helpers. - Extend libbpf's bpf_tracing.h support for tracing arguments of kprobes/uprobes and syscall as a special case. - Significantly reduce the search time for module symbols by livepatch and BPF. - Enable cpumasks to be used as kptrs, which is useful for tracing programs tracking which tasks end up running on which CPUs in different time intervals. - Add support for BPF trampoline on s390x and riscv64. - Add capability to export the XDP features supported by the NIC. - Add __bpf_kfunc tag for marking kernel functions as kfuncs. - Add cgroup.memory=nobpf kernel parameter option to disable BPF memory accounting for container environments. Netfilter: - Remove the CLUSTERIP target. It has been marked as obsolete for years, and we still have WARN splats wrt races of the out-of-band /proc interface installed by this target. - Add 'destroy' commands to nf_tables. They are identical to the existing 'delete' commands, but do not return an error if the referenced object (set, chain, rule...) did not exist. Driver API: - Improve cpumask_local_spread() locality to help NICs set the right IRQ affinity on AMD platforms. - Separate C22 and C45 MDIO bus transactions more clearly. - Introduce new DCB table to control DSCP rewrite on egress. - Support configuration of Physical Layer Collision Avoidance (PLCA) Reconciliation Sublayer (RS) (802.3cg-2019). Modern version of shared medium Ethernet. - Support for MAC Merge layer (IEEE 802.3-2018 clause 99). Allowing preemption of low priority frames by high priority frames. - Add support for controlling MACSec offload using netlink SET. - Rework devlink instance refcounts to allow registration and de-registration under the instance lock. Split the code into multiple files, drop some of the unnecessarily granular locks and factor out common parts of netlink operation handling. - Add TX frame aggregation parameters (for USB drivers). - Add a new attr TCA_EXT_WARN_MSG to report TC (offload) warning messages with notifications for debug. - Allow offloading of UDP NEW connections via act_ct. - Add support for per action HW stats in TC. - Support hardware miss to TC action (continue processing in SW from a specific point in the action chain). - Warn if old Wireless Extension user space interface is used with modern cfg80211/mac80211 drivers. Do not support Wireless Extensions for Wi-Fi 7 devices at all. Everyone should switch to using nl80211 interface instead. - Improve the CAN bit timing configuration. Use extack to return error messages directly to user space, update the SJW handling, including the definition of a new default value that will benefit CAN-FD controllers, by increasing their oscillator tolerance. New hardware / drivers: - Ethernet: - nVidia BlueField-3 support (control traffic driver) - Ethernet support for imx93 SoCs - Motorcomm yt8531 gigabit Ethernet PHY - onsemi NCN26000 10BASE-T1S PHY (with support for PLCA) - Microchip LAN8841 PHY (incl. cable diagnostics and PTP) - Amlogic gxl MDIO mux - WiFi: - RealTek RTL8188EU (rtl8xxxu) - Qualcomm Wi-Fi 7 devices (ath12k) - CAN: - Renesas R-Car V4H Drivers: - Bluetooth: - Set Per Platform Antenna Gain (PPAG) for Intel controllers. - Ethernet NICs: - Intel (1G, igc): - support TSN / Qbv / packet scheduling features of i226 model - Intel (100G, ice): - use GNSS subsystem instead of TTY - multi-buffer XDP support - extend support for GPIO pins to E823 devices - nVidia/Mellanox: - update the shared buffer configuration on PFC commands - implement PTP adjphase function for HW offset control - TC support for Geneve and GRE with VF tunnel offload - more efficient crypto key management method - multi-port eswitch support - Netronome/Corigine: - add DCB IEEE support - support IPsec offloading for NFP3800 - Freescale/NXP (enetc): - support XDP_REDIRECT for XDP non-linear buffers - improve reconfig, avoid link flap and waiting for idle - support MAC Merge layer - Other NICs: - sfc/ef100: add basic devlink support for ef100 - ionic: rx_push mode operation (writing descriptors via MMIO) - bnxt: use the auxiliary bus abstraction for RDMA - r8169: disable ASPM and reset bus in case of tx timeout - cpsw: support QSGMII mode for J721e CPSW9G - cpts: support pulse-per-second output - ngbe: add an mdio bus driver - usbnet: optimize usbnet_bh() by avoiding unnecessary queuing - r8152: handle devices with FW with NCM support - amd-xgbe: support 10Mbps, 2.5GbE speeds and rx-adaptation - virtio-net: support multi buffer XDP - virtio/vsock: replace virtio_vsock_pkt with sk_buff - tsnep: XDP support - Ethernet high-speed switches: - nVidia/Mellanox (mlxsw): - add support for latency TLV (in FW control messages) - Microchip (sparx5): - separate explicit and implicit traffic forwarding rules, make the implicit rules always active - add support for egress DSCP rewrite - IS0 VCAP support (Ingress Classification) - IS2 VCAP filters (protos, L3 addrs, L4 ports, flags, ToS etc.) - ES2 VCAP support (Egress Access Control) - support for Per-Stream Filtering and Policing (802.1Q, 8.6.5.1) - Ethernet embedded switches: - Marvell (mv88e6xxx): - add MAB (port auth) offload support - enable PTP receive for mv88e6390 - NXP (ocelot): - support MAC Merge layer - support for the the vsc7512 internal copper phys - Microchip: - lan9303: convert to PHYLINK - lan966x: support TC flower filter statistics - lan937x: PTP support for KSZ9563/KSZ8563 and LAN937x - lan937x: support Credit Based Shaper configuration - ksz9477: support Energy Efficient Ethernet - other: - qca8k: convert to regmap read/write API, use bulk operations - rswitch: Improve TX timestamp accuracy - Intel WiFi (iwlwifi): - EHT (Wi-Fi 7) rate reporting - STEP equalizer support: transfer some STEP (connection to radio on platforms with integrated wifi) related parameters from the BIOS to the firmware. - Qualcomm 802.11ax WiFi (ath11k): - IPQ5018 support - Fine Timing Measurement (FTM) responder role support - channel 177 support - MediaTek WiFi (mt76): - per-PHY LED support - mt7996: EHT (Wi-Fi 7) support - Wireless Ethernet Dispatch (WED) reset support - switch to using page pool allocator - RealTek WiFi (rtw89): - support new version of Bluetooth co-existance - Mobile: - rmnet: support TX aggregation" * tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1872 commits) page_pool: add a comment explaining the fragment counter usage net: ethtool: fix __ethtool_dev_mm_supported() implementation ethtool: pse-pd: Fix double word in comments xsk: add linux/vmalloc.h to xsk.c sefltests: netdevsim: wait for devlink instance after netns removal selftest: fib_tests: Always cleanup before exit net/mlx5e: Align IPsec ASO result memory to be as required by hardware net/mlx5e: TC, Set CT miss to the specific ct action instance net/mlx5e: Rename CHAIN_TO_REG to MAPPED_OBJ_TO_REG net/mlx5: Refactor tc miss handling to a single function net/mlx5: Kconfig: Make tc offload depend on tc skb extension net/sched: flower: Support hardware miss to tc action net/sched: flower: Move filter handle initialization earlier net/sched: cls_api: Support hardware miss to tc action net/sched: Rename user cookie and act cookie sfc: fix builds without CONFIG_RTC_LIB sfc: clean up some inconsistent indentings net/mlx4_en: Introduce flexible array to silence overflow warning net: lan966x: Fix possible deadlock inside PTP net/ulp: Remove redundant ->clone() test in inet_clone_ulp(). ... --- arch/sparc/net/bpf_jit_comp_32.c | 764 +++++++++++++++++++++++++++++++++++++++ 1 file changed, 764 insertions(+) create mode 100644 arch/sparc/net/bpf_jit_comp_32.c (limited to 'arch/sparc/net/bpf_jit_comp_32.c') diff --git a/arch/sparc/net/bpf_jit_comp_32.c b/arch/sparc/net/bpf_jit_comp_32.c new file mode 100644 index 000000000..a74e5004c --- /dev/null +++ b/arch/sparc/net/bpf_jit_comp_32.c @@ -0,0 +1,764 @@ +// SPDX-License-Identifier: GPL-2.0 +#include +#include +#include +#include +#include +#include + +#include +#include + +#include "bpf_jit_32.h" + +static inline bool is_simm13(unsigned int value) +{ + return value + 0x1000 < 0x2000; +} + +#define SEEN_DATAREF 1 /* might call external helpers */ +#define SEEN_XREG 2 /* ebx is used */ +#define SEEN_MEM 4 /* use mem[] for temporary storage */ + +#define S13(X) ((X) & 0x1fff) +#define IMMED 0x00002000 +#define RD(X) ((X) << 25) +#define RS1(X) ((X) << 14) +#define RS2(X) ((X)) +#define OP(X) ((X) << 30) +#define OP2(X) ((X) << 22) +#define OP3(X) ((X) << 19) +#define COND(X) ((X) << 25) +#define F1(X) OP(X) +#define F2(X, Y) (OP(X) | OP2(Y)) +#define F3(X, Y) (OP(X) | OP3(Y)) + +#define CONDN COND(0x0) +#define CONDE COND(0x1) +#define CONDLE COND(0x2) +#define CONDL COND(0x3) +#define CONDLEU COND(0x4) +#define CONDCS COND(0x5) +#define CONDNEG COND(0x6) +#define CONDVC COND(0x7) +#define CONDA COND(0x8) +#define CONDNE COND(0x9) +#define CONDG COND(0xa) +#define CONDGE COND(0xb) +#define CONDGU COND(0xc) +#define CONDCC COND(0xd) +#define CONDPOS COND(0xe) +#define CONDVS COND(0xf) + +#define CONDGEU CONDCC +#define CONDLU CONDCS + +#define WDISP22(X) (((X) >> 2) & 0x3fffff) + +#define BA (F2(0, 2) | CONDA) +#define BGU (F2(0, 2) | CONDGU) +#define BLEU (F2(0, 2) | CONDLEU) +#define BGEU (F2(0, 2) | CONDGEU) +#define BLU (F2(0, 2) | CONDLU) +#define BE (F2(0, 2) | CONDE) +#define BNE (F2(0, 2) | CONDNE) + +#define BE_PTR BE + +#define SETHI(K, REG) \ + (F2(0, 0x4) | RD(REG) | (((K) >> 10) & 0x3fffff)) +#define OR_LO(K, REG) \ + (F3(2, 0x02) | IMMED | RS1(REG) | ((K) & 0x3ff) | RD(REG)) + +#define ADD F3(2, 0x00) +#define AND F3(2, 0x01) +#define ANDCC F3(2, 0x11) +#define OR F3(2, 0x02) +#define XOR F3(2, 0x03) +#define SUB F3(2, 0x04) +#define SUBCC F3(2, 0x14) +#define MUL F3(2, 0x0a) /* umul */ +#define DIV F3(2, 0x0e) /* udiv */ +#define SLL F3(2, 0x25) +#define SRL F3(2, 0x26) +#define JMPL F3(2, 0x38) +#define CALL F1(1) +#define BR F2(0, 0x01) +#define RD_Y F3(2, 0x28) +#define WR_Y F3(2, 0x30) + +#define LD32 F3(3, 0x00) +#define LD8 F3(3, 0x01) +#define LD16 F3(3, 0x02) +#define LD64 F3(3, 0x0b) +#define ST32 F3(3, 0x04) + +#define LDPTR LD32 +#define BASE_STACKFRAME 96 + +#define LD32I (LD32 | IMMED) +#define LD8I (LD8 | IMMED) +#define LD16I (LD16 | IMMED) +#define LD64I (LD64 | IMMED) +#define LDPTRI (LDPTR | IMMED) +#define ST32I (ST32 | IMMED) + +#define emit_nop() \ +do { \ + *prog++ = SETHI(0, G0); \ +} while (0) + +#define emit_neg() \ +do { /* sub %g0, r_A, r_A */ \ + *prog++ = SUB | RS1(G0) | RS2(r_A) | RD(r_A); \ +} while (0) + +#define emit_reg_move(FROM, TO) \ +do { /* or %g0, FROM, TO */ \ + *prog++ = OR | RS1(G0) | RS2(FROM) | RD(TO); \ +} while (0) + +#define emit_clear(REG) \ +do { /* or %g0, %g0, REG */ \ + *prog++ = OR | RS1(G0) | RS2(G0) | RD(REG); \ +} while (0) + +#define emit_set_const(K, REG) \ +do { /* sethi %hi(K), REG */ \ + *prog++ = SETHI(K, REG); \ + /* or REG, %lo(K), REG */ \ + *prog++ = OR_LO(K, REG); \ +} while (0) + + /* Emit + * + * OP r_A, r_X, r_A + */ +#define emit_alu_X(OPCODE) \ +do { \ + seen |= SEEN_XREG; \ + *prog++ = OPCODE | RS1(r_A) | RS2(r_X) | RD(r_A); \ +} while (0) + + /* Emit either: + * + * OP r_A, K, r_A + * + * or + * + * sethi %hi(K), r_TMP + * or r_TMP, %lo(K), r_TMP + * OP r_A, r_TMP, r_A + * + * depending upon whether K fits in a signed 13-bit + * immediate instruction field. Emit nothing if K + * is zero. + */ +#define emit_alu_K(OPCODE, K) \ +do { \ + if (K || OPCODE == AND || OPCODE == MUL) { \ + unsigned int _insn = OPCODE; \ + _insn |= RS1(r_A) | RD(r_A); \ + if (is_simm13(K)) { \ + *prog++ = _insn | IMMED | S13(K); \ + } else { \ + emit_set_const(K, r_TMP); \ + *prog++ = _insn | RS2(r_TMP); \ + } \ + } \ +} while (0) + +#define emit_loadimm(K, DEST) \ +do { \ + if (is_simm13(K)) { \ + /* or %g0, K, DEST */ \ + *prog++ = OR | IMMED | RS1(G0) | S13(K) | RD(DEST); \ + } else { \ + emit_set_const(K, DEST); \ + } \ +} while (0) + +#define emit_loadptr(BASE, STRUCT, FIELD, DEST) \ +do { unsigned int _off = offsetof(STRUCT, FIELD); \ + BUILD_BUG_ON(sizeof_field(STRUCT, FIELD) != sizeof(void *)); \ + *prog++ = LDPTRI | RS1(BASE) | S13(_off) | RD(DEST); \ +} while (0) + +#define emit_load32(BASE, STRUCT, FIELD, DEST) \ +do { unsigned int _off = offsetof(STRUCT, FIELD); \ + BUILD_BUG_ON(sizeof_field(STRUCT, FIELD) != sizeof(u32)); \ + *prog++ = LD32I | RS1(BASE) | S13(_off) | RD(DEST); \ +} while (0) + +#define emit_load16(BASE, STRUCT, FIELD, DEST) \ +do { unsigned int _off = offsetof(STRUCT, FIELD); \ + BUILD_BUG_ON(sizeof_field(STRUCT, FIELD) != sizeof(u16)); \ + *prog++ = LD16I | RS1(BASE) | S13(_off) | RD(DEST); \ +} while (0) + +#define __emit_load8(BASE, STRUCT, FIELD, DEST) \ +do { unsigned int _off = offsetof(STRUCT, FIELD); \ + *prog++ = LD8I | RS1(BASE) | S13(_off) | RD(DEST); \ +} while (0) + +#define emit_load8(BASE, STRUCT, FIELD, DEST) \ +do { BUILD_BUG_ON(sizeof_field(STRUCT, FIELD) != sizeof(u8)); \ + __emit_load8(BASE, STRUCT, FIELD, DEST); \ +} while (0) + +#define BIAS (-4) + +#define emit_ldmem(OFF, DEST) \ +do { *prog++ = LD32I | RS1(SP) | S13(BIAS - (OFF)) | RD(DEST); \ +} while (0) + +#define emit_stmem(OFF, SRC) \ +do { *prog++ = ST32I | RS1(SP) | S13(BIAS - (OFF)) | RD(SRC); \ +} while (0) + +#ifdef CONFIG_SMP +#define emit_load_cpu(REG) \ + emit_load32(G6, struct thread_info, cpu, REG) +#else +#define emit_load_cpu(REG) emit_clear(REG) +#endif + +#define emit_skb_loadptr(FIELD, DEST) \ + emit_loadptr(r_SKB, struct sk_buff, FIELD, DEST) +#define emit_skb_load32(FIELD, DEST) \ + emit_load32(r_SKB, struct sk_buff, FIELD, DEST) +#define emit_skb_load16(FIELD, DEST) \ + emit_load16(r_SKB, struct sk_buff, FIELD, DEST) +#define __emit_skb_load8(FIELD, DEST) \ + __emit_load8(r_SKB, struct sk_buff, FIELD, DEST) +#define emit_skb_load8(FIELD, DEST) \ + emit_load8(r_SKB, struct sk_buff, FIELD, DEST) + +#define emit_jmpl(BASE, IMM_OFF, LREG) \ + *prog++ = (JMPL | IMMED | RS1(BASE) | S13(IMM_OFF) | RD(LREG)) + +#define emit_call(FUNC) \ +do { void *_here = image + addrs[i] - 8; \ + unsigned int _off = (void *)(FUNC) - _here; \ + *prog++ = CALL | (((_off) >> 2) & 0x3fffffff); \ + emit_nop(); \ +} while (0) + +#define emit_branch(BR_OPC, DEST) \ +do { unsigned int _here = addrs[i] - 8; \ + *prog++ = BR_OPC | WDISP22((DEST) - _here); \ +} while (0) + +#define emit_branch_off(BR_OPC, OFF) \ +do { *prog++ = BR_OPC | WDISP22(OFF); \ +} while (0) + +#define emit_jump(DEST) emit_branch(BA, DEST) + +#define emit_read_y(REG) *prog++ = RD_Y | RD(REG) +#define emit_write_y(REG) *prog++ = WR_Y | IMMED | RS1(REG) | S13(0) + +#define emit_cmp(R1, R2) \ + *prog++ = (SUBCC | RS1(R1) | RS2(R2) | RD(G0)) + +#define emit_cmpi(R1, IMM) \ + *prog++ = (SUBCC | IMMED | RS1(R1) | S13(IMM) | RD(G0)); + +#define emit_btst(R1, R2) \ + *prog++ = (ANDCC | RS1(R1) | RS2(R2) | RD(G0)) + +#define emit_btsti(R1, IMM) \ + *prog++ = (ANDCC | IMMED | RS1(R1) | S13(IMM) | RD(G0)); + +#define emit_sub(R1, R2, R3) \ + *prog++ = (SUB | RS1(R1) | RS2(R2) | RD(R3)) + +#define emit_subi(R1, IMM, R3) \ + *prog++ = (SUB | IMMED | RS1(R1) | S13(IMM) | RD(R3)) + +#define emit_add(R1, R2, R3) \ + *prog++ = (ADD | RS1(R1) | RS2(R2) | RD(R3)) + +#define emit_addi(R1, IMM, R3) \ + *prog++ = (ADD | IMMED | RS1(R1) | S13(IMM) | RD(R3)) + +#define emit_and(R1, R2, R3) \ + *prog++ = (AND | RS1(R1) | RS2(R2) | RD(R3)) + +#define emit_andi(R1, IMM, R3) \ + *prog++ = (AND | IMMED | RS1(R1) | S13(IMM) | RD(R3)) + +#define emit_alloc_stack(SZ) \ + *prog++ = (SUB | IMMED | RS1(SP) | S13(SZ) | RD(SP)) + +#define emit_release_stack(SZ) \ + *prog++ = (ADD | IMMED | RS1(SP) | S13(SZ) | RD(SP)) + +/* A note about branch offset calculations. The addrs[] array, + * indexed by BPF instruction, records the address after all the + * sparc instructions emitted for that BPF instruction. + * + * The most common case is to emit a branch at the end of such + * a code sequence. So this would be two instructions, the + * branch and it's delay slot. + * + * Therefore by default the branch emitters calculate the branch + * offset field as: + * + * destination - (addrs[i] - 8) + * + * This "addrs[i] - 8" is the address of the branch itself or + * what "." would be in assembler notation. The "8" part is + * how we take into consideration the branch and it's delay + * slot mentioned above. + * + * Sometimes we need to emit a branch earlier in the code + * sequence. And in these situations we adjust "destination" + * to accommodate this difference. For example, if we needed + * to emit a branch (and it's delay slot) right before the + * final instruction emitted for a BPF opcode, we'd use + * "destination + 4" instead of just plain "destination" above. + * + * This is why you see all of these funny emit_branch() and + * emit_jump() calls with adjusted offsets. + */ + +void bpf_jit_compile(struct bpf_prog *fp) +{ + unsigned int cleanup_addr, proglen, oldproglen = 0; + u32 temp[8], *prog, *func, seen = 0, pass; + const struct sock_filter *filter = fp->insns; + int i, flen = fp->len, pc_ret0 = -1; + unsigned int *addrs; + void *image; + + if (!bpf_jit_enable) + return; + + addrs = kmalloc_array(flen, sizeof(*addrs), GFP_KERNEL); + if (addrs == NULL) + return; + + /* Before first pass, make a rough estimation of addrs[] + * each bpf instruction is translated to less than 64 bytes + */ + for (proglen = 0, i = 0; i < flen; i++) { + proglen += 64; + addrs[i] = proglen; + } + cleanup_addr = proglen; /* epilogue address */ + image = NULL; + for (pass = 0; pass < 10; pass++) { + u8 seen_or_pass0 = (pass == 0) ? (SEEN_XREG | SEEN_DATAREF | SEEN_MEM) : seen; + + /* no prologue/epilogue for trivial filters (RET something) */ + proglen = 0; + prog = temp; + + /* Prologue */ + if (seen_or_pass0) { + if (seen_or_pass0 & SEEN_MEM) { + unsigned int sz = BASE_STACKFRAME; + sz += BPF_MEMWORDS * sizeof(u32); + emit_alloc_stack(sz); + } + + /* Make sure we dont leek kernel memory. */ + if (seen_or_pass0 & SEEN_XREG) + emit_clear(r_X); + + /* If this filter needs to access skb data, + * load %o4 and %o5 with: + * %o4 = skb->len - skb->data_len + * %o5 = skb->data + * And also back up %o7 into r_saved_O7 so we can + * invoke the stubs using 'call'. + */ + if (seen_or_pass0 & SEEN_DATAREF) { + emit_load32(r_SKB, struct sk_buff, len, r_HEADLEN); + emit_load32(r_SKB, struct sk_buff, data_len, r_TMP); + emit_sub(r_HEADLEN, r_TMP, r_HEADLEN); + emit_loadptr(r_SKB, struct sk_buff, data, r_SKB_DATA); + } + } + emit_reg_move(O7, r_saved_O7); + + /* Make sure we dont leak kernel information to the user. */ + if (bpf_needs_clear_a(&filter[0])) + emit_clear(r_A); /* A = 0 */ + + for (i = 0; i < flen; i++) { + unsigned int K = filter[i].k; + unsigned int t_offset; + unsigned int f_offset; + u32 t_op, f_op; + u16 code = bpf_anc_helper(&filter[i]); + int ilen; + + switch (code) { + case BPF_ALU | BPF_ADD | BPF_X: /* A += X; */ + emit_alu_X(ADD); + break; + case BPF_ALU | BPF_ADD | BPF_K: /* A += K; */ + emit_alu_K(ADD, K); + break; + case BPF_ALU | BPF_SUB | BPF_X: /* A -= X; */ + emit_alu_X(SUB); + break; + case BPF_ALU | BPF_SUB | BPF_K: /* A -= K */ + emit_alu_K(SUB, K); + break; + case BPF_ALU | BPF_AND | BPF_X: /* A &= X */ + emit_alu_X(AND); + break; + case BPF_ALU | BPF_AND | BPF_K: /* A &= K */ + emit_alu_K(AND, K); + break; + case BPF_ALU | BPF_OR | BPF_X: /* A |= X */ + emit_alu_X(OR); + break; + case BPF_ALU | BPF_OR | BPF_K: /* A |= K */ + emit_alu_K(OR, K); + break; + case BPF_ANC | SKF_AD_ALU_XOR_X: /* A ^= X; */ + case BPF_ALU | BPF_XOR | BPF_X: + emit_alu_X(XOR); + break; + case BPF_ALU | BPF_XOR | BPF_K: /* A ^= K */ + emit_alu_K(XOR, K); + break; + case BPF_ALU | BPF_LSH | BPF_X: /* A <<= X */ + emit_alu_X(SLL); + break; + case BPF_ALU | BPF_LSH | BPF_K: /* A <<= K */ + emit_alu_K(SLL, K); + break; + case BPF_ALU | BPF_RSH | BPF_X: /* A >>= X */ + emit_alu_X(SRL); + break; + case BPF_ALU | BPF_RSH | BPF_K: /* A >>= K */ + emit_alu_K(SRL, K); + break; + case BPF_ALU | BPF_MUL | BPF_X: /* A *= X; */ + emit_alu_X(MUL); + break; + case BPF_ALU | BPF_MUL | BPF_K: /* A *= K */ + emit_alu_K(MUL, K); + break; + case BPF_ALU | BPF_DIV | BPF_K: /* A /= K with K != 0*/ + if (K == 1) + break; + emit_write_y(G0); + /* The Sparc v8 architecture requires + * three instructions between a %y + * register write and the first use. + */ + emit_nop(); + emit_nop(); + emit_nop(); + emit_alu_K(DIV, K); + break; + case BPF_ALU | BPF_DIV | BPF_X: /* A /= X; */ + emit_cmpi(r_X, 0); + if (pc_ret0 > 0) { + t_offset = addrs[pc_ret0 - 1]; + emit_branch(BE, t_offset + 20); + emit_nop(); /* delay slot */ + } else { + emit_branch_off(BNE, 16); + emit_nop(); + emit_jump(cleanup_addr + 20); + emit_clear(r_A); + } + emit_write_y(G0); + /* The Sparc v8 architecture requires + * three instructions between a %y + * register write and the first use. + */ + emit_nop(); + emit_nop(); + emit_nop(); + emit_alu_X(DIV); + break; + case BPF_ALU | BPF_NEG: + emit_neg(); + break; + case BPF_RET | BPF_K: + if (!K) { + if (pc_ret0 == -1) + pc_ret0 = i; + emit_clear(r_A); + } else { + emit_loadimm(K, r_A); + } + fallthrough; + case BPF_RET | BPF_A: + if (seen_or_pass0) { + if (i != flen - 1) { + emit_jump(cleanup_addr); + emit_nop(); + break; + } + if (seen_or_pass0 & SEEN_MEM) { + unsigned int sz = BASE_STACKFRAME; + sz += BPF_MEMWORDS * sizeof(u32); + emit_release_stack(sz); + } + } + /* jmpl %r_saved_O7 + 8, %g0 */ + emit_jmpl(r_saved_O7, 8, G0); + emit_reg_move(r_A, O0); /* delay slot */ + break; + case BPF_MISC | BPF_TAX: + seen |= SEEN_XREG; + emit_reg_move(r_A, r_X); + break; + case BPF_MISC | BPF_TXA: + seen |= SEEN_XREG; + emit_reg_move(r_X, r_A); + break; + case BPF_ANC | SKF_AD_CPU: + emit_load_cpu(r_A); + break; + case BPF_ANC | SKF_AD_PROTOCOL: + emit_skb_load16(protocol, r_A); + break; + case BPF_ANC | SKF_AD_PKTTYPE: + __emit_skb_load8(__pkt_type_offset, r_A); + emit_andi(r_A, PKT_TYPE_MAX, r_A); + emit_alu_K(SRL, 5); + break; + case BPF_ANC | SKF_AD_IFINDEX: + emit_skb_loadptr(dev, r_A); + emit_cmpi(r_A, 0); + emit_branch(BE_PTR, cleanup_addr + 4); + emit_nop(); + emit_load32(r_A, struct net_device, ifindex, r_A); + break; + case BPF_ANC | SKF_AD_MARK: + emit_skb_load32(mark, r_A); + break; + case BPF_ANC | SKF_AD_QUEUE: + emit_skb_load16(queue_mapping, r_A); + break; + case BPF_ANC | SKF_AD_HATYPE: + emit_skb_loadptr(dev, r_A); + emit_cmpi(r_A, 0); + emit_branch(BE_PTR, cleanup_addr + 4); + emit_nop(); + emit_load16(r_A, struct net_device, type, r_A); + break; + case BPF_ANC | SKF_AD_RXHASH: + emit_skb_load32(hash, r_A); + break; + case BPF_ANC | SKF_AD_VLAN_TAG: + emit_skb_load16(vlan_tci, r_A); + break; + case BPF_ANC | SKF_AD_VLAN_TAG_PRESENT: + emit_skb_load32(vlan_all, r_A); + emit_cmpi(r_A, 0); + emit_branch_off(BE, 12); + emit_nop(); + emit_loadimm(1, r_A); + break; + case BPF_LD | BPF_W | BPF_LEN: + emit_skb_load32(len, r_A); + break; + case BPF_LDX | BPF_W | BPF_LEN: + emit_skb_load32(len, r_X); + break; + case BPF_LD | BPF_IMM: + emit_loadimm(K, r_A); + break; + case BPF_LDX | BPF_IMM: + emit_loadimm(K, r_X); + break; + case BPF_LD | BPF_MEM: + seen |= SEEN_MEM; + emit_ldmem(K * 4, r_A); + break; + case BPF_LDX | BPF_MEM: + seen |= SEEN_MEM | SEEN_XREG; + emit_ldmem(K * 4, r_X); + break; + case BPF_ST: + seen |= SEEN_MEM; + emit_stmem(K * 4, r_A); + break; + case BPF_STX: + seen |= SEEN_MEM | SEEN_XREG; + emit_stmem(K * 4, r_X); + break; + +#define CHOOSE_LOAD_FUNC(K, func) \ + ((int)K < 0 ? ((int)K >= SKF_LL_OFF ? func##_negative_offset : func) : func##_positive_offset) + + case BPF_LD | BPF_W | BPF_ABS: + func = CHOOSE_LOAD_FUNC(K, bpf_jit_load_word); +common_load: seen |= SEEN_DATAREF; + emit_loadimm(K, r_OFF); + emit_call(func); + break; + case BPF_LD | BPF_H | BPF_ABS: + func = CHOOSE_LOAD_FUNC(K, bpf_jit_load_half); + goto common_load; + case BPF_LD | BPF_B | BPF_ABS: + func = CHOOSE_LOAD_FUNC(K, bpf_jit_load_byte); + goto common_load; + case BPF_LDX | BPF_B | BPF_MSH: + func = CHOOSE_LOAD_FUNC(K, bpf_jit_load_byte_msh); + goto common_load; + case BPF_LD | BPF_W | BPF_IND: + func = bpf_jit_load_word; +common_load_ind: seen |= SEEN_DATAREF | SEEN_XREG; + if (K) { + if (is_simm13(K)) { + emit_addi(r_X, K, r_OFF); + } else { + emit_loadimm(K, r_TMP); + emit_add(r_X, r_TMP, r_OFF); + } + } else { + emit_reg_move(r_X, r_OFF); + } + emit_call(func); + break; + case BPF_LD | BPF_H | BPF_IND: + func = bpf_jit_load_half; + goto common_load_ind; + case BPF_LD | BPF_B | BPF_IND: + func = bpf_jit_load_byte; + goto common_load_ind; + case BPF_JMP | BPF_JA: + emit_jump(addrs[i + K]); + emit_nop(); + break; + +#define COND_SEL(CODE, TOP, FOP) \ + case CODE: \ + t_op = TOP; \ + f_op = FOP; \ + goto cond_branch + + COND_SEL(BPF_JMP | BPF_JGT | BPF_K, BGU, BLEU); + COND_SEL(BPF_JMP | BPF_JGE | BPF_K, BGEU, BLU); + COND_SEL(BPF_JMP | BPF_JEQ | BPF_K, BE, BNE); + COND_SEL(BPF_JMP | BPF_JSET | BPF_K, BNE, BE); + COND_SEL(BPF_JMP | BPF_JGT | BPF_X, BGU, BLEU); + COND_SEL(BPF_JMP | BPF_JGE | BPF_X, BGEU, BLU); + COND_SEL(BPF_JMP | BPF_JEQ | BPF_X, BE, BNE); + COND_SEL(BPF_JMP | BPF_JSET | BPF_X, BNE, BE); + +cond_branch: f_offset = addrs[i + filter[i].jf]; + t_offset = addrs[i + filter[i].jt]; + + /* same targets, can avoid doing the test :) */ + if (filter[i].jt == filter[i].jf) { + emit_jump(t_offset); + emit_nop(); + break; + } + + switch (code) { + case BPF_JMP | BPF_JGT | BPF_X: + case BPF_JMP | BPF_JGE | BPF_X: + case BPF_JMP | BPF_JEQ | BPF_X: + seen |= SEEN_XREG; + emit_cmp(r_A, r_X); + break; + case BPF_JMP | BPF_JSET | BPF_X: + seen |= SEEN_XREG; + emit_btst(r_A, r_X); + break; + case BPF_JMP | BPF_JEQ | BPF_K: + case BPF_JMP | BPF_JGT | BPF_K: + case BPF_JMP | BPF_JGE | BPF_K: + if (is_simm13(K)) { + emit_cmpi(r_A, K); + } else { + emit_loadimm(K, r_TMP); + emit_cmp(r_A, r_TMP); + } + break; + case BPF_JMP | BPF_JSET | BPF_K: + if (is_simm13(K)) { + emit_btsti(r_A, K); + } else { + emit_loadimm(K, r_TMP); + emit_btst(r_A, r_TMP); + } + break; + } + if (filter[i].jt != 0) { + if (filter[i].jf) + t_offset += 8; + emit_branch(t_op, t_offset); + emit_nop(); /* delay slot */ + if (filter[i].jf) { + emit_jump(f_offset); + emit_nop(); + } + break; + } + emit_branch(f_op, f_offset); + emit_nop(); /* delay slot */ + break; + + default: + /* hmm, too complex filter, give up with jit compiler */ + goto out; + } + ilen = (void *) prog - (void *) temp; + if (image) { + if (unlikely(proglen + ilen > oldproglen)) { + pr_err("bpb_jit_compile fatal error\n"); + kfree(addrs); + module_memfree(image); + return; + } + memcpy(image + proglen, temp, ilen); + } + proglen += ilen; + addrs[i] = proglen; + prog = temp; + } + /* last bpf instruction is always a RET : + * use it to give the cleanup instruction(s) addr + */ + cleanup_addr = proglen - 8; /* jmpl; mov r_A,%o0; */ + if (seen_or_pass0 & SEEN_MEM) + cleanup_addr -= 4; /* add %sp, X, %sp; */ + + if (image) { + if (proglen != oldproglen) + pr_err("bpb_jit_compile proglen=%u != oldproglen=%u\n", + proglen, oldproglen); + break; + } + if (proglen == oldproglen) { + image = module_alloc(proglen); + if (!image) + goto out; + } + oldproglen = proglen; + } + + if (bpf_jit_enable > 1) + bpf_jit_dump(flen, proglen, pass + 1, image); + + if (image) { + fp->bpf_func = (void *)image; + fp->jited = 1; + } +out: + kfree(addrs); + return; +} + +void bpf_jit_free(struct bpf_prog *fp) +{ + if (fp->jited) + module_memfree(fp->bpf_func); + + bpf_prog_unlock_free(fp); +} -- cgit v1.2.3