diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index fe960ebd54a5eb8f4a500a2e42fe69b12370f2aa..00dd932d386a7d06c344a146d052ae83de9908e0 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -1589,6 +1589,8 @@ static int ib_prctl_set(struct task_struct *task, unsigned long ctrl) if (ctrl == PR_SPEC_FORCE_DISABLE) task_set_spec_ib_force_disable(task); task_update_spec_tif(task); + if (task == current) + indirect_branch_prediction_barrier(); break; default: return -ERANGE; diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c index 91e2487ba6de59c379faa030c6455a45dafac691..500d392f0e7e5410a7247a4d4460f7d482ec47e8 100644 --- a/drivers/block/virtio_blk.c +++ b/drivers/block/virtio_blk.c @@ -304,7 +304,8 @@ static blk_status_t virtio_queue_rq(struct blk_mq_hw_ctx *hctx, bool unmap = false; u32 type; - BUG_ON(req->nr_phys_segments + 2 > vblk->sg_elems); + if (req_op(req) != REQ_OP_DISCARD) + BUG_ON(req->nr_phys_segments + 2 > vblk->sg_elems); switch (req_op(req)) { case REQ_OP_READ: @@ -964,11 +965,12 @@ static int virtblk_probe(struct virtio_device *vdev) blk_queue_io_opt(q, blk_size * opt_io_size); if (virtio_has_feature(vdev, VIRTIO_BLK_F_DISCARD)) { - q->limits.discard_granularity = blk_size; - virtio_cread(vdev, struct virtio_blk_config, discard_sector_alignment, &v); - q->limits.discard_alignment = v ? v << SECTOR_SHIFT : 0; + if (v) + q->limits.discard_granularity = v << SECTOR_SHIFT; + else + q->limits.discard_granularity = blk_size; virtio_cread(vdev, struct virtio_blk_config, max_discard_sectors, &v); @@ -976,9 +978,15 @@ static int virtblk_probe(struct virtio_device *vdev) virtio_cread(vdev, struct virtio_blk_config, max_discard_seg, &v); + + /* + * max_discard_seg == 0 is out of spec but we always + * handled it. + */ + if (!v) + v = sg_elems - 2; blk_queue_max_discard_segments(q, - min_not_zero(v, - MAX_DISCARD_SEGMENTS)); + min(v, MAX_DISCARD_SEGMENTS)); blk_queue_flag_set(QUEUE_FLAG_DISCARD, q); } diff --git a/drivers/bluetooth/btsdio.c b/drivers/bluetooth/btsdio.c index 20142bc77554c0f3400da0506a6158e94722f54b..bd55bf7a9914c835291281421530404a36f99a31 100644 --- a/drivers/bluetooth/btsdio.c +++ b/drivers/bluetooth/btsdio.c @@ -353,6 +353,7 @@ static void btsdio_remove(struct sdio_func *func) BT_DBG("func %p", func); + cancel_work_sync(&data->work); if (!data) return; diff --git a/drivers/gpu/drm/i915/gvt/gtt.c b/drivers/gpu/drm/i915/gvt/gtt.c index 40b32b4d1d98be60f842466ab44a06bfe778cd46..afbc648befeccb2da9b3c86482db632658292a3e 100644 --- a/drivers/gpu/drm/i915/gvt/gtt.c +++ b/drivers/gpu/drm/i915/gvt/gtt.c @@ -1155,10 +1155,8 @@ static int split_2MB_gtt_entry(struct intel_vgpu *vgpu, for_each_shadow_entry(sub_spt, &sub_se, sub_index) { ret = intel_gvt_hypervisor_dma_map_guest_page(vgpu, start_gfn + sub_index, PAGE_SIZE, &dma_addr); - if (ret) { - ppgtt_invalidate_spt(spt); - return ret; - } + if (ret) + goto err; sub_se.val64 = se->val64; /* Copy the PAT field from PDE. */ @@ -1177,6 +1175,17 @@ static int split_2MB_gtt_entry(struct intel_vgpu *vgpu, ops->set_pfn(se, sub_spt->shadow_page.mfn); ppgtt_set_shadow_entry(spt, se, index); return 0; +err: + /* Cancel the existing addess mappings of DMA addr. */ + for_each_present_shadow_entry(sub_spt, &sub_se, sub_index) { + gvt_vdbg_mm("invalidate 4K entry\n"); + ppgtt_invalidate_pte(sub_spt, &sub_se); + } + /* Release the new allocated spt. */ + trace_spt_change(sub_spt->vgpu->id, "release", sub_spt, + sub_spt->guest_page.gfn, sub_spt->shadow_page.type); + ppgtt_free_spt(sub_spt); + return ret; } static int split_64KB_gtt_entry(struct intel_vgpu *vgpu, diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c index 4752f08f0884c131c0a5949f1cfc22c5e10f37e8..5852e1d356e13e5c041dc52192c25fb7a2f11fc8 100644 --- a/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c +++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_crtc.c @@ -1477,6 +1477,8 @@ static int dpu_crtc_atomic_check(struct drm_crtc *crtc, } pstates = kzalloc(sizeof(*pstates) * DPU_STAGE_MAX * 4, GFP_KERNEL); + if (!pstates) + return -ENOMEM; dpu_crtc = to_dpu_crtc(crtc); cstate = to_dpu_crtc_state(state); diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c index 248d92c85cf692ee0685ec4ebcab1714055d3013..befef87e0bb8f477d7b277809b9b50dd845cf529 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c @@ -179,7 +179,8 @@ void vmw_kms_cursor_snoop(struct vmw_surface *srf, if (cmd->dma.guest.ptr.offset % PAGE_SIZE || box->x != 0 || box->y != 0 || box->z != 0 || box->srcx != 0 || box->srcy != 0 || box->srcz != 0 || - box->d != 1 || box_count != 1) { + box->d != 1 || box_count != 1 || + box->w > 64 || box->h > 64) { /* TODO handle none page aligned offsets */ /* TODO handle more dst & src != 0 */ /* TODO handle more then one copy */ diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c index b0c8fae7f903d0f45a31b84c1705c4a3da8f19ff..01010a28332e576f03a67e80ee22a70a389519b8 100644 --- a/drivers/hid/hid-core.c +++ b/drivers/hid/hid-core.c @@ -970,8 +970,8 @@ struct hid_report *hid_validate_values(struct hid_device *hid, * Validating on id 0 means we should examine the first * report in the list. */ - report = list_entry( - hid->report_enum[type].report_list.next, + report = list_first_entry_or_null( + &hid->report_enum[type].report_list, struct hid_report, list); } else { report = hid->report_enum[type].report_id_hash[id]; diff --git a/drivers/hid/hid-roccat.c b/drivers/hid/hid-roccat.c index 5be8de70c65172c23bf3c6b7e761219f534dc978..c9cec00b4e6e303031b6491f808cb47219364eec 100644 --- a/drivers/hid/hid-roccat.c +++ b/drivers/hid/hid-roccat.c @@ -260,6 +260,8 @@ int roccat_report_event(int minor, u8 const *data) if (!new_value) return -ENOMEM; + mutex_lock(&device->cbuf_lock); + report = &device->cbuf[device->cbuf_end]; /* passing NULL is safe */ @@ -279,6 +281,8 @@ int roccat_report_event(int minor, u8 const *data) reader->cbuf_start = (reader->cbuf_start + 1) % ROCCAT_CBUF_SIZE; } + mutex_unlock(&device->cbuf_lock); + wake_up_interruptible(&device->wait); return 0; } diff --git a/drivers/hwmon/xgene-hwmon.c b/drivers/hwmon/xgene-hwmon.c index a3cd91f232679afd21c9ebbd206be377f5394333..2dd19a42030520c1b1835e7e8cac9cee07470158 100644 --- a/drivers/hwmon/xgene-hwmon.c +++ b/drivers/hwmon/xgene-hwmon.c @@ -780,6 +780,7 @@ static int xgene_hwmon_remove(struct platform_device *pdev) { struct xgene_hwmon_dev *ctx = platform_get_drvdata(pdev); + cancel_work_sync(&ctx->workq); hwmon_device_unregister(ctx->hwmon_dev); kfifo_free(&ctx->async_msg_fifo); if (acpi_disabled) diff --git a/drivers/i2c/busses/i2c-xgene-slimpro.c b/drivers/i2c/busses/i2c-xgene-slimpro.c index a7ac746018ad0c098d51eb56c1d5d8981d34c78c..7a746f41353514a7586626c913d77510452de35e 100644 --- a/drivers/i2c/busses/i2c-xgene-slimpro.c +++ b/drivers/i2c/busses/i2c-xgene-slimpro.c @@ -321,6 +321,9 @@ static int slimpro_i2c_blkwr(struct slimpro_i2c_dev *ctx, u32 chip, u32 msg[3]; int rc; + if (writelen > I2C_SMBUS_BLOCK_MAX) + return -EINVAL; + memcpy(ctx->dma_buffer, data, writelen); paddr = dma_map_single(ctx->dev, ctx->dma_buffer, writelen, DMA_TO_DEVICE); diff --git a/drivers/media/usb/dvb-usb/az6027.c b/drivers/media/usb/dvb-usb/az6027.c index 6321b8e302612080d2e93352975198e6a1430ad4..555c8ac44881ece62f92e0a09072a71b8350c2ef 100644 --- a/drivers/media/usb/dvb-usb/az6027.c +++ b/drivers/media/usb/dvb-usb/az6027.c @@ -977,6 +977,10 @@ static int az6027_i2c_xfer(struct i2c_adapter *adap, struct i2c_msg msg[], int n if (msg[i].addr == 0x99) { req = 0xBE; index = 0; + if (msg[i].len < 1) { + i = -EOPNOTSUPP; + break; + } value = msg[i].buf[0] & 0x00ff; length = 1; az6027_usb_out_op(d, req, value, index, data, length); diff --git a/drivers/media/usb/uvc/uvc_driver.c b/drivers/media/usb/uvc/uvc_driver.c index 063e229ead5ef7b8dfee8ceaae32018babfceac7..38c73cdbef70e85846a33dc0674b709c3bc1ed86 100644 --- a/drivers/media/usb/uvc/uvc_driver.c +++ b/drivers/media/usb/uvc/uvc_driver.c @@ -1482,6 +1482,11 @@ static int uvc_scan_chain_forward(struct uvc_video_chain *chain, break; if (forward == prev) continue; + if (forward->chain.next || forward->chain.prev) { + uvc_trace(UVC_TRACE_DESCR, "Found reference to " + "entity %d already in chain.\n", forward->id); + return -EINVAL; + } switch (UVC_ENTITY_TYPE(forward)) { case UVC_VC_EXTENSION_UNIT: @@ -1563,6 +1568,13 @@ static int uvc_scan_chain_backward(struct uvc_video_chain *chain, return -1; } + if (term->chain.next || term->chain.prev) { + uvc_trace(UVC_TRACE_DESCR, "Found reference to " + "entity %d already in chain.\n", + term->id); + return -EINVAL; + } + if (uvc_trace_param & UVC_TRACE_PROBE) printk(KERN_CONT " %d", term->id); diff --git a/drivers/memstick/host/r592.c b/drivers/memstick/host/r592.c index 627d6e62fe3133319f0da646a0b9f84fc12445d1..61b9c97cf0e7a9ae24f67c714e09ca43c797f7bf 100644 --- a/drivers/memstick/host/r592.c +++ b/drivers/memstick/host/r592.c @@ -827,7 +827,7 @@ static void r592_remove(struct pci_dev *pdev) /* Stop the processing thread. That ensures that we won't take any more requests */ kthread_stop(dev->io_thread); - + del_timer_sync(&dev->detect_timer); r592_enable_device(dev, false); while (!error && dev->req) { diff --git a/drivers/net/ethernet/xircom/xirc2ps_cs.c b/drivers/net/ethernet/xircom/xirc2ps_cs.c index fd5288ff53b5303271f20137dda57f125d879901..e3438cef5f9c66a68434461ae8bfe5edef443300 100644 --- a/drivers/net/ethernet/xircom/xirc2ps_cs.c +++ b/drivers/net/ethernet/xircom/xirc2ps_cs.c @@ -503,6 +503,11 @@ static void xirc2ps_detach(struct pcmcia_device *link) { struct net_device *dev = link->priv; + struct local_info *local = netdev_priv(dev); + + netif_carrier_off(dev); + netif_tx_disable(dev); + cancel_work_sync(&local->tx_timeout_task); dev_dbg(&link->dev, "detach\n"); diff --git a/drivers/net/tap.c b/drivers/net/tap.c index f0f7cd9776671fb6d3f3dd6498611afe593b41c3..43012a195b71ca914347558e939721ec3ded3b43 100644 --- a/drivers/net/tap.c +++ b/drivers/net/tap.c @@ -525,7 +525,7 @@ static int tap_open(struct inode *inode, struct file *file) q->sock.state = SS_CONNECTED; q->sock.file = file; q->sock.ops = &tap_socket_ops; - sock_init_data(&q->sock, &q->sk); + sock_init_data_uid(&q->sock, &q->sk, inode->i_uid); q->sk.sk_write_space = tap_sock_write_space; q->sk.sk_destruct = tap_sock_destruct; q->flags = IFF_VNET_HDR | IFF_NO_PI | IFF_TAP; diff --git a/drivers/net/tun.c b/drivers/net/tun.c index e1ac1c57089ff6e9f2d1e5e97f8bd5ce8c62179d..01758114b458f776849ed673390ade9f5800de9f 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -3237,7 +3237,7 @@ static int tun_chr_open(struct inode *inode, struct file * file) tfile->socket.file = file; tfile->socket.ops = &tun_socket_ops; - sock_init_data(&tfile->socket, &tfile->sk); + sock_init_data_uid(&tfile->socket, &tfile->sk, inode->i_uid); tfile->sk.sk_write_space = tun_sock_write_space; tfile->sk.sk_sndbuf = INT_MAX; diff --git a/drivers/nfc/st-nci/ndlc.c b/drivers/nfc/st-nci/ndlc.c index f26d938d240f03dbb27889fc101d552511ea9d92..12d73f9dbe9f37e3ef208971b16dee783d362312 100644 --- a/drivers/nfc/st-nci/ndlc.c +++ b/drivers/nfc/st-nci/ndlc.c @@ -297,13 +297,15 @@ EXPORT_SYMBOL(ndlc_probe); void ndlc_remove(struct llt_ndlc *ndlc) { - st_nci_remove(ndlc->ndev); - /* cancel timers */ del_timer_sync(&ndlc->t1_timer); del_timer_sync(&ndlc->t2_timer); ndlc->t2_active = false; ndlc->t1_active = false; + /* cancel work */ + cancel_work_sync(&ndlc->sm_work); + + st_nci_remove(ndlc->ndev); skb_queue_purge(&ndlc->rcv_q); skb_queue_purge(&ndlc->send_q); diff --git a/drivers/phy/tegra/xusb.c b/drivers/phy/tegra/xusb.c index de1b4ebe4de28356053b915458d756ccc87f6102..9e8fa1834a154912944d8a6d6684b0c6f679f440 100644 --- a/drivers/phy/tegra/xusb.c +++ b/drivers/phy/tegra/xusb.c @@ -441,7 +441,7 @@ tegra_xusb_find_port_node(struct tegra_xusb_padctl *padctl, const char *type, name = kasprintf(GFP_KERNEL, "%s-%u", type, index); if (!name) { of_node_put(ports); - return ERR_PTR(-ENOMEM); + return NULL; } np = of_get_child_by_name(ports, name); kfree(name); diff --git a/drivers/power/supply/da9150-charger.c b/drivers/power/supply/da9150-charger.c index 60099815296e75d86cfcde6a18d14c428214f987..b2d38eb32288a78d873e0e423010a0f74b46240c 100644 --- a/drivers/power/supply/da9150-charger.c +++ b/drivers/power/supply/da9150-charger.c @@ -666,6 +666,7 @@ static int da9150_charger_remove(struct platform_device *pdev) if (!IS_ERR_OR_NULL(charger->usb_phy)) usb_unregister_notifier(charger->usb_phy, &charger->otg_nb); + cancel_work_sync(&charger->otg_work); power_supply_unregister(charger->battery); power_supply_unregister(charger->usb); diff --git a/drivers/staging/rtl8712/rtl8712_cmd.c b/drivers/staging/rtl8712/rtl8712_cmd.c index 63bc811681d9614364e61a855d2e4807cded005f..fb092d4ec521992fcf88eea09f93c09d168dc471 100644 --- a/drivers/staging/rtl8712/rtl8712_cmd.c +++ b/drivers/staging/rtl8712/rtl8712_cmd.c @@ -129,34 +129,6 @@ static void r871x_internal_cmd_hdl(struct _adapter *padapter, u8 *pbuf) kfree(pdrvcmd->pbuf); } -static u8 read_macreg_hdl(struct _adapter *padapter, u8 *pbuf) -{ - void (*pcmd_callback)(struct _adapter *dev, struct cmd_obj *pcmd); - struct cmd_obj *pcmd = (struct cmd_obj *)pbuf; - - /* invoke cmd->callback function */ - pcmd_callback = cmd_callback[pcmd->cmdcode].callback; - if (!pcmd_callback) - r8712_free_cmd_obj(pcmd); - else - pcmd_callback(padapter, pcmd); - return H2C_SUCCESS; -} - -static u8 write_macreg_hdl(struct _adapter *padapter, u8 *pbuf) -{ - void (*pcmd_callback)(struct _adapter *dev, struct cmd_obj *pcmd); - struct cmd_obj *pcmd = (struct cmd_obj *)pbuf; - - /* invoke cmd->callback function */ - pcmd_callback = cmd_callback[pcmd->cmdcode].callback; - if (!pcmd_callback) - r8712_free_cmd_obj(pcmd); - else - pcmd_callback(padapter, pcmd); - return H2C_SUCCESS; -} - static u8 read_bbreg_hdl(struct _adapter *padapter, u8 *pbuf) { struct cmd_obj *pcmd = (struct cmd_obj *)pbuf; @@ -225,14 +197,6 @@ static struct cmd_obj *cmd_hdl_filter(struct _adapter *padapter, pcmd_r = NULL; switch (pcmd->cmdcode) { - case GEN_CMD_CODE(_Read_MACREG): - read_macreg_hdl(padapter, (u8 *)pcmd); - pcmd_r = pcmd; - break; - case GEN_CMD_CODE(_Write_MACREG): - write_macreg_hdl(padapter, (u8 *)pcmd); - pcmd_r = pcmd; - break; case GEN_CMD_CODE(_Read_BBREG): read_bbreg_hdl(padapter, (u8 *)pcmd); break; diff --git a/drivers/usb/gadget/function/rndis.c b/drivers/usb/gadget/function/rndis.c index 6b5848a2c7e917dd74cb503b45b45b99bb30f7dc..c2c45208abc59005c81190750597d6e038210e93 100644 --- a/drivers/usb/gadget/function/rndis.c +++ b/drivers/usb/gadget/function/rndis.c @@ -640,6 +640,7 @@ static int rndis_set_response(struct rndis_params *params, BufLength = le32_to_cpu(buf->InformationBufferLength); BufOffset = le32_to_cpu(buf->InformationBufferOffset); if ((BufLength > RNDIS_MAX_TOTAL_SIZE) || + (BufOffset > RNDIS_MAX_TOTAL_SIZE) || (BufOffset + 8 >= RNDIS_MAX_TOTAL_SIZE)) return -EINVAL; diff --git a/fs/erofs/internal.h b/fs/erofs/internal.h index 1ef0dfb3d2086ef07abd42700d8c06745c9c8942..89eb85b94930b71b8e97b689a4d4165c476dfa91 100644 --- a/fs/erofs/internal.h +++ b/fs/erofs/internal.h @@ -147,11 +147,6 @@ struct erofs_sb_info { /* Mount flags set via mount options or defaults */ #define EROFS_MOUNT_XATTR_USER 0x00000010 #define EROFS_MOUNT_POSIX_ACL 0x00000020 -/* - * Bypass [override_creds|revert_creds] for overlayfs - * when erofs is mounted as lowerfs. - */ -#define EROFS_MOUNT_OPT_CREDS 0x80000000 #define clear_opt(sbi, option) ((sbi)->mount_opt &= ~EROFS_MOUNT_##option) #define set_opt(sbi, option) ((sbi)->mount_opt |= EROFS_MOUNT_##option) diff --git a/fs/erofs/super.c b/fs/erofs/super.c index 29f1b22826bc46456f738ebe09270f0484eae4a7..e6ba90a0adc44b3eee0d76fb0fe84d7c337e3cc5 100644 --- a/fs/erofs/super.c +++ b/fs/erofs/super.c @@ -382,8 +382,6 @@ enum { Opt_domain_id, Opt_bootstrap_path, Opt_blob_dir_path, - Opt_opt_creds_on, - Opt_opt_creds_off, Opt_err }; @@ -398,8 +396,6 @@ static match_table_t erofs_tokens = { {Opt_domain_id, "domain_id=%s"}, {Opt_bootstrap_path, "bootstrap_path=%s"}, {Opt_blob_dir_path, "blob_dir_path=%s"}, - {Opt_opt_creds_on, "opt_creds=on"}, - {Opt_opt_creds_off, "opt_creds=off"}, {Opt_err, NULL} }; @@ -514,12 +510,6 @@ static int erofs_parse_options(struct super_block *sb, char *options) return -ENOMEM; erofs_dbg("RAFS bootstrap_path %s", sbi->bootstrap_path); break; - case Opt_opt_creds_on: - set_opt(EROFS_SB(sb), OPT_CREDS); - break; - case Opt_opt_creds_off: - clear_opt(EROFS_SB(sb), OPT_CREDS); - break; default: erofs_err(sb, "Unrecognized mount option \"%s\" or missing value", p); return -EINVAL; @@ -752,13 +742,6 @@ static int erofs_fill_super(struct super_block *sb, void *data, int silent) else sb->s_flags &= ~SB_POSIXACL; - if (test_opt(sbi, OPT_CREDS)) - sb->s_iflags |= SB_I_OVL_OPT_CREDS; - else - sb->s_iflags &= ~SB_I_OVL_OPT_CREDS; - - sb->s_iflags |= SB_I_OVL_OPT_ACL_RCU; - #ifdef CONFIG_EROFS_FS_ZIP INIT_RADIX_TREE(&sbi->workstn_tree, GFP_ATOMIC); #endif @@ -1039,11 +1022,6 @@ static int erofs_show_options(struct seq_file *seq, struct dentry *root) if (sbi->domain_id) seq_printf(seq, ",domain_id=%s", sbi->domain_id); #endif - if (test_opt(sbi, OPT_CREDS)) - seq_puts(seq, ",opt_creds=on"); - else - seq_puts(seq, ",opt_creds=off"); - return 0; } @@ -1063,11 +1041,6 @@ static int erofs_remount(struct super_block *sb, int *flags, char *data) else sb->s_flags &= ~SB_POSIXACL; - if (test_opt(sbi, OPT_CREDS)) - sb->s_iflags |= SB_I_OVL_OPT_CREDS; - else - sb->s_iflags &= ~SB_I_OVL_OPT_CREDS; - *flags |= SB_RDONLY; return 0; out: diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c index 893fcf28e30859d5a10b42e9d073b99d0b212f5e..7dff2da7434d91a7952954f52c5efb59fee72452 100644 --- a/fs/fuse/dev.c +++ b/fs/fuse/dev.c @@ -411,17 +411,20 @@ static void flush_bg_queue(struct fuse_conn *fc) } } -static void fuse_update_stats(struct fuse_conn *fc, int opcode, uint64_t send_time) +static void fuse_update_stats(struct fuse_conn *fc, struct fuse_req *req) { + unsigned int opcode = req->in.h.opcode; uint64_t delta_time; - delta_time = get_time_now_us() - send_time; + if (opcode < FUSE_OP_MAX) { + delta_time = get_time_now_us() - req->send_time; - atomic64_add(delta_time, &fc->stats.req_time[FUSE_SUMMARY]); - atomic64_add(delta_time, &fc->stats.req_time[opcode]); + atomic64_add(delta_time, &fc->stats.req_time[FUSE_SUMMARY]); + atomic64_add(delta_time, &fc->stats.req_time[opcode]); - atomic64_inc(&fc->stats.req_cnts[FUSE_SUMMARY]); - atomic64_inc(&fc->stats.req_cnts[opcode]); + atomic64_inc(&fc->stats.req_cnts[FUSE_SUMMARY]); + atomic64_inc(&fc->stats.req_cnts[opcode]); + } } /* @@ -445,7 +448,7 @@ void fuse_request_end(struct fuse_conn *fc, struct fuse_req *req) WARN_ON(test_bit(FR_PENDING, &req->flags)); WARN_ON(test_bit(FR_SENT, &req->flags)); if (test_bit(FR_BACKGROUND, &req->flags)) { - fuse_update_stats(fc, req->in.h.opcode, req->send_time); + fuse_update_stats(fc, req); spin_lock(&fc->bg_lock); clear_bit(FR_BACKGROUND, &req->flags); @@ -563,7 +566,7 @@ static void __fuse_request_send(struct fuse_conn *fc, struct fuse_req *req) /* Pairs with smp_wmb() in fuse_request_end() */ smp_rmb(); - fuse_update_stats(fc, req->in.h.opcode, req->send_time); + fuse_update_stats(fc, req); } } diff --git a/fs/hfsplus/super.c b/fs/hfsplus/super.c index eb4535eba95d9a5e13dfda5fb196849a069bda64..3b1356b10a4725b8153c82964097aebca733de35 100644 --- a/fs/hfsplus/super.c +++ b/fs/hfsplus/super.c @@ -294,11 +294,11 @@ static void hfsplus_put_super(struct super_block *sb) hfsplus_sync_fs(sb, 1); } + iput(sbi->alloc_file); + iput(sbi->hidden_dir); hfs_btree_close(sbi->attr_tree); hfs_btree_close(sbi->cat_tree); hfs_btree_close(sbi->ext_tree); - iput(sbi->alloc_file); - iput(sbi->hidden_dir); kfree(sbi->s_vhdr_buf); kfree(sbi->s_backup_vhdr_buf); unload_nls(sbi->nls); diff --git a/fs/locks.c b/fs/locks.c index 552476d6f6bbde7aafb58a56bc0d9e4961df1b85..21b05a053f3327d2c7daa9d1dc52f1ca0a7bbdff 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -1627,10 +1627,10 @@ int fcntl_getlease(struct file *filp) } /** - * check_conflicting_open - see if the given dentry points to a file that has - * an existing open that would conflict with the - * desired lease. - * @dentry: dentry to check + * check_conflicting_open - see if the given file points to an inode that has + * an existing open that would conflict with the + * desired lease. + * @filp: file to check * @arg: type of lease that we're trying to acquire * @flags: current lock flags * @@ -1638,30 +1638,42 @@ int fcntl_getlease(struct file *filp) * conflict with the lease we're trying to set. */ static int -check_conflicting_open(const struct dentry *dentry, const long arg, int flags) +check_conflicting_open(struct file *filp, const long arg, int flags) { - int ret = 0; - struct inode *inode = dentry->d_inode; + struct inode *inode = locks_inode(filp); + int self_wcount = 0, self_rcount = 0; if (flags & FL_LAYOUT) return 0; - if ((arg == F_RDLCK) && (atomic_read(&inode->i_writecount) > 0)) - return -EAGAIN; + if (arg == F_RDLCK) + return inode_is_open_for_write(inode) ? -EAGAIN : 0; + else if (arg != F_WRLCK) + return 0; + + /* + * Make sure that only read/write count is from lease requestor. + * Note that this will result in denying write leases when i_writecount + * is negative, which is what we want. (We shouldn't grant write leases + * on files open for execution.) + */ + if (filp->f_mode & FMODE_WRITE) + self_wcount = 1; + else if (filp->f_mode & FMODE_READ) + self_rcount = 1; - if ((arg == F_WRLCK) && ((d_count(dentry) > 1) || - (atomic_read(&inode->i_count) > 1))) - ret = -EAGAIN; + if (atomic_read(&inode->i_writecount) != self_wcount || + atomic_read(&inode->i_readcount) != self_rcount) + return -EAGAIN; - return ret; + return 0; } static int generic_add_lease(struct file *filp, long arg, struct file_lock **flp, void **priv) { struct file_lock *fl, *my_fl = NULL, *lease; - struct dentry *dentry = filp->f_path.dentry; - struct inode *inode = dentry->d_inode; + struct inode *inode = locks_inode(filp); struct file_lock_context *ctx; bool is_deleg = (*flp)->fl_flags & FL_DELEG; int error; @@ -1696,7 +1708,7 @@ generic_add_lease(struct file *filp, long arg, struct file_lock **flp, void **pr percpu_down_read(&file_rwsem); spin_lock(&ctx->flc_lock); time_out_leases(inode, &dispose); - error = check_conflicting_open(dentry, arg, lease->fl_flags); + error = check_conflicting_open(filp, arg, lease->fl_flags); if (error) goto out; @@ -1753,7 +1765,7 @@ generic_add_lease(struct file *filp, long arg, struct file_lock **flp, void **pr * precedes these checks. */ smp_mb(); - error = check_conflicting_open(dentry, arg, lease->fl_flags); + error = check_conflicting_open(filp, arg, lease->fl_flags); if (error) { locks_unlink_lock_ctx(lease); goto out; diff --git a/fs/ntfs/attrib.c b/fs/ntfs/attrib.c index 44a39a099b54e368ab074b0c26248fdd25735273..122a9b45b350642389e2568b5932656dd39fada3 100644 --- a/fs/ntfs/attrib.c +++ b/fs/ntfs/attrib.c @@ -606,9 +606,25 @@ static int ntfs_attr_find(const ATTR_TYPE type, const ntfschar *name, a = (ATTR_RECORD*)((u8*)ctx->attr + le32_to_cpu(ctx->attr->length)); for (;; a = (ATTR_RECORD*)((u8*)a + le32_to_cpu(a->length))) { - if ((u8*)a < (u8*)ctx->mrec || (u8*)a > (u8*)ctx->mrec + - le32_to_cpu(ctx->mrec->bytes_allocated)) + u8 *mrec_end = (u8 *)ctx->mrec + + le32_to_cpu(ctx->mrec->bytes_allocated); + u8 *name_end; + + /* check whether ATTR_RECORD wrap */ + if ((u8 *)a < (u8 *)ctx->mrec) + break; + + /* check whether Attribute Record Header is within bounds */ + if ((u8 *)a > mrec_end || + (u8 *)a + sizeof(ATTR_RECORD) > mrec_end) + break; + + /* check whether ATTR_RECORD's name is within bounds */ + name_end = (u8 *)a + le16_to_cpu(a->name_offset) + + a->name_length * sizeof(ntfschar); + if (name_end > mrec_end) break; + ctx->attr = a; if (unlikely(le32_to_cpu(a->type) > le32_to_cpu(type) || a->type == AT_END)) diff --git a/fs/overlayfs/file.c b/fs/overlayfs/file.c index db3dd10632bf719b00be79e60561b05b4cb9c96d..e089d6f409868f65a11abf20f5bc98ba28e80dc4 100644 --- a/fs/overlayfs/file.c +++ b/fs/overlayfs/file.c @@ -12,6 +12,9 @@ #include #include #include +#include +#include +#include #include "overlayfs.h" struct ovl_aio_req { @@ -397,6 +400,48 @@ static ssize_t ovl_write_iter(struct kiocb *iocb, struct iov_iter *iter) return ret; } +static ssize_t ovl_splice_read(struct file *in, loff_t *ppos, + struct pipe_inode_info *pipe, size_t len, + unsigned int flags) +{ + ssize_t ret; + struct fd real; + const struct cred *old_cred; + + ret = ovl_real_fdget(in, &real); + if (ret) + return ret; + + old_cred = ovl_override_creds(file_inode(in)->i_sb); + ret = generic_file_splice_read(real.file, ppos, pipe, len, flags); + revert_creds(old_cred); + + ovl_file_accessed(in); + fdput(real); + return ret; +} + +static ssize_t +ovl_splice_write(struct pipe_inode_info *pipe, struct file *out, + loff_t *ppos, size_t len, unsigned int flags) +{ + struct fd real; + const struct cred *old_cred; + ssize_t ret; + + ret = ovl_real_fdget(out, &real); + if (ret) + return ret; + + old_cred = ovl_override_creds(file_inode(out)->i_sb); + ret = iter_file_splice_write(pipe, real.file, ppos, len, flags); + revert_creds(old_cred); + + ovl_file_accessed(out); + fdput(real); + return ret; +} + static int ovl_fsync(struct file *file, loff_t start, loff_t end, int datasync) { struct fd real; @@ -750,6 +795,8 @@ const struct file_operations ovl_file_operations = { .fadvise = ovl_fadvise, .unlocked_ioctl = ovl_ioctl, .compat_ioctl = ovl_compat_ioctl, + .splice_read = ovl_splice_read, + .splice_write = ovl_splice_write, .copy_file_range = ovl_copy_file_range, .clone_file_range = ovl_clone_file_range, diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c index b7f9ad289ab73c2ca18d4cf36959d1ff9c8d1e9c..477f6d5213909782a24e57bd880cbe3a2d2bbfc1 100644 --- a/fs/overlayfs/inode.c +++ b/fs/overlayfs/inode.c @@ -300,7 +300,7 @@ int ovl_permission(struct inode *inode, int mask) if (err) return err; - old_cred = ovl_override_creds_opt(inode->i_sb); + old_cred = ovl_override_creds(inode->i_sb); if (!upperinode && !special_file(realinode->i_mode) && mask & MAY_WRITE) { mask &= ~(MAY_WRITE | MAY_APPEND); @@ -308,7 +308,7 @@ int ovl_permission(struct inode *inode, int mask) mask |= MAY_READ; } err = inode_permission(realinode, mask); - ovl_revert_creds(old_cred); + revert_creds(old_cred); return err; } @@ -450,22 +450,18 @@ ssize_t ovl_listxattr(struct dentry *dentry, char *list, size_t size) struct posix_acl *ovl_get_acl(struct inode *inode, int type, bool rcu) { struct inode *realinode = ovl_inode_real(inode); - struct ovl_fs *ofs = inode->i_sb->s_fs_info; const struct cred *old_cred; struct posix_acl *acl; if (!IS_ENABLED(CONFIG_FS_POSIX_ACL) || !IS_POSIXACL(realinode)) return NULL; - if (rcu) { - if (!ofs->config.opt_acl_rcu) - return ERR_PTR(-ECHILD); + if (rcu) return get_cached_acl_rcu(realinode, type); - } - old_cred = ovl_override_creds_opt(inode->i_sb); + old_cred = ovl_override_creds(inode->i_sb); acl = get_acl(realinode, type); - ovl_revert_creds(old_cred); + revert_creds(old_cred); return acl; } diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h index e932bd59fdad64402091e1c9301fa61526b0fd58..08ee430e4f646436dbdb4ad0ba8668e4835dd58f 100644 --- a/fs/overlayfs/overlayfs.h +++ b/fs/overlayfs/overlayfs.h @@ -247,8 +247,6 @@ int ovl_want_write(struct dentry *dentry); void ovl_drop_write(struct dentry *dentry); struct dentry *ovl_workdir(struct dentry *dentry); const struct cred *ovl_override_creds(struct super_block *sb); -const struct cred *ovl_override_creds_opt(struct super_block *sb); -void ovl_revert_creds(const struct cred *oldcred); int ovl_can_decode_fh(struct super_block *sb); struct dentry *ovl_indexdir(struct super_block *sb); bool ovl_index_all(struct super_block *sb); diff --git a/fs/overlayfs/ovl_entry.h b/fs/overlayfs/ovl_entry.h index ff76cda8e1beec2afea4f4a3ba464e515911ce0e..d9f5a4cd39385f4a1e11ee5acb3df02e5c1e7014 100644 --- a/fs/overlayfs/ovl_entry.h +++ b/fs/overlayfs/ovl_entry.h @@ -22,8 +22,6 @@ struct ovl_config { bool metacopy; bool userxattr; bool ovl_volatile; - bool opt_creds; - bool opt_acl_rcu; }; struct ovl_sb { diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c index c30ba99a4ff73b1a193ed93e004a3397eab4d768..a79ff8f6afd8a27601b7d8cfeb3c2faaf953a8aa 100644 --- a/fs/overlayfs/super.c +++ b/fs/overlayfs/super.c @@ -1774,22 +1774,6 @@ static struct dentry *ovl_get_root(struct super_block *sb, return root; } -static bool ovl_config_opt(struct ovl_fs *ofs, unsigned int opt_mask) -{ - int i; - bool opt = true; - - /* - * Enable the optimization for container scenarios if all lowerfs are - * configured with opt_mask. The optimization is disabled by default. - * ofs->numfs must be at least 2, thus the default "true" won't be - * returned without checking any lowerfs. - */ - for (i = 1; opt && i < ofs->numfs; i++) - opt = ofs->fs[i].sb->s_iflags & opt_mask; - return opt; -} - static int ovl_fill_super(struct super_block *sb, void *data, int silent) { struct path upperpath = { }; @@ -1913,9 +1897,6 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent) sb->s_fs_info = ofs; sb->s_flags |= SB_POSIXACL; - ofs->config.opt_creds = ovl_config_opt(ofs, SB_I_OVL_OPT_CREDS); - ofs->config.opt_acl_rcu = ovl_config_opt(ofs, SB_I_OVL_OPT_ACL_RCU); - err = -ENOMEM; root_dentry = ovl_get_root(sb, upperpath.dentry, oe); if (!root_dentry) diff --git a/fs/overlayfs/util.c b/fs/overlayfs/util.c index 138e864c07c29abe67473e7a528e648f721367ff..681a9a47975bccb8e2e518e64a824a0785b274da 100644 --- a/fs/overlayfs/util.c +++ b/fs/overlayfs/util.c @@ -43,21 +43,6 @@ const struct cred *ovl_override_creds(struct super_block *sb) return override_creds(ofs->creator_cred); } -const struct cred *ovl_override_creds_opt(struct super_block *sb) -{ - struct ovl_fs *ofs = sb->s_fs_info; - - if (ofs->config.opt_creds) - return NULL; - return override_creds(ofs->creator_cred); -} - -void ovl_revert_creds(const struct cred *old_cred) -{ - if (old_cred) - revert_creds(old_cred); -} - /* * Check if underlying fs supports file handles and try to determine encoding * type, in order to deduce maximum inode number used by fs. diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c index d7f3c03432e6906b4a59ab46b9f26c9960858cb0..b8df9945a9f00bc3cef890f6f313c21231213ec2 100644 --- a/fs/xfs/xfs_ioctl.c +++ b/fs/xfs/xfs_ioctl.c @@ -800,14 +800,13 @@ xfs_ioc_bulkstat( if (error) return error; - if (bulkreq.ocount != NULL) { - if (copy_to_user(bulkreq.lastip, &inlast, - sizeof(xfs_ino_t))) - return -EFAULT; + if (bulkreq.lastip != NULL && + copy_to_user(bulkreq.lastip, &inlast, sizeof(xfs_ino_t))) + return -EFAULT; - if (copy_to_user(bulkreq.ocount, &count, sizeof(count))) - return -EFAULT; - } + if (bulkreq.ocount != NULL && + copy_to_user(bulkreq.ocount, &count, sizeof(count))) + return -EFAULT; return 0; } diff --git a/fs/xfs/xfs_ioctl32.c b/fs/xfs/xfs_ioctl32.c index b044f7d36782c28573d57327d3cb56bb41b87d6c..71a8874a579b58e563f92a557ca24f5a6885e2d1 100644 --- a/fs/xfs/xfs_ioctl32.c +++ b/fs/xfs/xfs_ioctl32.c @@ -313,14 +313,13 @@ xfs_compat_ioc_bulkstat( if (error) return error; - if (bulkreq.ocount != NULL) { - if (copy_to_user(bulkreq.lastip, &inlast, - sizeof(xfs_ino_t))) - return -EFAULT; + if (bulkreq.lastip != NULL && + copy_to_user(bulkreq.lastip, &inlast, sizeof(xfs_ino_t))) + return -EFAULT; - if (copy_to_user(bulkreq.ocount, &count, sizeof(count))) - return -EFAULT; - } + if (bulkreq.ocount != NULL && + copy_to_user(bulkreq.ocount, &count, sizeof(count))) + return -EFAULT; return 0; } diff --git a/include/linux/fs.h b/include/linux/fs.h index 34e15e9dd6f54fbcfbd04b754503ecd80ea2b2ef..12ab65298082625804f55d39402e17338009a880 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -701,7 +701,7 @@ struct inode { atomic_t i_count; atomic_t i_dio_count; atomic_t i_writecount; -#ifdef CONFIG_IMA +#if defined(CONFIG_IMA) || defined(CONFIG_FILE_LOCKING) atomic_t i_readcount; /* struct files open RO */ #endif const struct file_operations *i_fop; /* former ->i_op->default_file_ops */ @@ -1394,10 +1394,6 @@ extern int send_sigurg(struct fown_struct *fown); #define SB_I_IMA_UNVERIFIABLE_SIGNATURE 0x00000020 #define SB_I_UNTRUSTED_MOUNTER 0x00000040 -/* hint from lowerfs for overlayfs optimizations (e.g. for container scenarios) */ -#define SB_I_OVL_OPT_CREDS 0x40000000 /* bypass [override|revert]_creds */ -#define SB_I_OVL_OPT_ACL_RCU 0x80000000 /* enable RCU'd ACL */ - /* Possible states of 'frozen' field */ enum { SB_UNFROZEN = 0, /* FS is unfrozen */ @@ -2930,7 +2926,7 @@ static inline bool inode_is_open_for_write(const struct inode *inode) return atomic_read(&inode->i_writecount) > 0; } -#ifdef CONFIG_IMA +#if defined(CONFIG_IMA) || defined(CONFIG_FILE_LOCKING) static inline void i_readcount_dec(struct inode *inode) { BUG_ON(!atomic_read(&inode->i_readcount)); diff --git a/include/linux/sched/isolation.h b/include/linux/sched/isolation.h index 30c84ba31a5216dfe722f14cd5b578a8349e6ff6..6d10cbc6d60565b29efc29a01cb40c840a12432d 100644 --- a/include/linux/sched/isolation.h +++ b/include/linux/sched/isolation.h @@ -13,6 +13,7 @@ enum hk_flags { HK_FLAG_TICK = (1 << 4), HK_FLAG_DOMAIN = (1 << 5), HK_FLAG_WQ = (1 << 6), + HK_FLAG_KTHREAD = (1 << 8), }; #ifdef CONFIG_CPU_ISOLATION diff --git a/include/net/sock.h b/include/net/sock.h index 7e39d72d0a9054a95262abf36fcf7951c38c5c71..9382a53c2f6f1bafc0c199375c264a77052bf982 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1682,7 +1682,12 @@ void sk_common_release(struct sock *sk); * Default socket callbacks and setup code */ -/* Initialise core socket variables */ +/* Initialise core socket variables using an explicit uid. */ +void sock_init_data_uid(struct socket *sock, struct sock *sk, kuid_t uid); + +/* Initialise core socket variables. + * Assumes struct socket *sock is embedded in a struct socket_alloc. + */ void sock_init_data(struct socket *sock, struct sock *sk); /* diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index 0c17aab3ce5f8c03867f57ca402d985f669fca11..1b2cccff59833fc252db8784689a4600f6c0eb79 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -529,6 +529,29 @@ static void bpf_fd_array_map_clear(struct bpf_map *map) fd_array_map_delete_elem(map, &i); } +static void prog_array_map_seq_show_elem(struct bpf_map *map, void *key, + struct seq_file *m) +{ + void **elem, *ptr; + u32 prog_id; + + rcu_read_lock(); + + elem = array_map_lookup_elem(map, key); + if (elem) { + ptr = READ_ONCE(*elem); + if (ptr) { + seq_printf(m, "%u: ", *(u32 *)key); + prog_id = prog_fd_array_sys_lookup_elem(ptr); + btf_type_seq_show(map->btf, map->btf_value_type_id, + &prog_id, m); + seq_puts(m, "\n"); + } + } + + rcu_read_unlock(); +} + const struct bpf_map_ops prog_array_map_ops = { .map_alloc_check = fd_array_map_alloc_check, .map_alloc = array_map_alloc, @@ -540,7 +563,7 @@ const struct bpf_map_ops prog_array_map_ops = { .map_fd_put_ptr = prog_fd_array_put_ptr, .map_fd_sys_lookup_elem = prog_fd_array_sys_lookup_elem, .map_release_uref = bpf_fd_array_map_clear, - .map_check_btf = map_check_no_btf, + .map_seq_show_elem = prog_array_map_seq_show_elem, }; static struct bpf_event_entry *bpf_event_entry_gen(struct file *perf_file, diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 9b74115452c6b406ea9f910bed9e729299ed7bc6..5ef0947969253fe35a0f007021b2c6471465d249 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -263,6 +263,13 @@ static const char * const reg_type_str[] = { [PTR_TO_PACKET_END] = "pkt_end", }; +static char slot_type_char[] = { + [STACK_INVALID] = '?', + [STACK_SPILL] = 'r', + [STACK_MISC] = 'm', + [STACK_ZERO] = '0', +}; + static void print_liveness(struct bpf_verifier_env *env, enum bpf_reg_liveness live) { @@ -349,15 +356,26 @@ static void print_verifier_state(struct bpf_verifier_env *env, } } for (i = 0; i < state->allocated_stack / BPF_REG_SIZE; i++) { - if (state->stack[i].slot_type[0] == STACK_SPILL) { - verbose(env, " fp%d", - (-i - 1) * BPF_REG_SIZE); - print_liveness(env, state->stack[i].spilled_ptr.live); + char types_buf[BPF_REG_SIZE + 1]; + bool valid = false; + int j; + + for (j = 0; j < BPF_REG_SIZE; j++) { + if (state->stack[i].slot_type[j] != STACK_INVALID) + valid = true; + types_buf[j] = slot_type_char[ + state->stack[i].slot_type[j]]; + } + types_buf[BPF_REG_SIZE] = 0; + if (!valid) + continue; + verbose(env, " fp%d", (-i - 1) * BPF_REG_SIZE); + print_liveness(env, state->stack[i].spilled_ptr.live); + if (state->stack[i].slot_type[0] == STACK_SPILL) verbose(env, "=%s", reg_type_str[state->stack[i].spilled_ptr.type]); - } - if (state->stack[i].slot_type[0] == STACK_ZERO) - verbose(env, " fp%d=0", (-i - 1) * BPF_REG_SIZE); + else + verbose(env, "=%s", types_buf); } verbose(env, "\n"); } diff --git a/kernel/kthread.c b/kernel/kthread.c index fcb3a1a6e14bc64fec6c97132fcc5d125a4050f4..d18066d51bca74ba19670d1da6ecd3fd6b59628c 100644 --- a/kernel/kthread.c +++ b/kernel/kthread.c @@ -21,6 +21,7 @@ #include #include #include +#include #include static DEFINE_SPINLOCK(kthread_create_lock); @@ -339,7 +340,8 @@ struct task_struct *__kthread_create_on_node(int (*threadfn)(void *data), * The kernel thread should not inherit these properties. */ sched_setscheduler_nocheck(task, SCHED_NORMAL, ¶m); - set_cpus_allowed_ptr(task, cpu_all_mask); + set_cpus_allowed_ptr(task, + housekeeping_cpumask(HK_FLAG_KTHREAD)); } kfree(create); return task; @@ -564,7 +566,7 @@ int kthreadd(void *unused) /* Setup a clean context for our children to inherit. */ set_task_comm(tsk, "kthreadd"); ignore_signals(tsk); - set_cpus_allowed_ptr(tsk, cpu_all_mask); + set_cpus_allowed_ptr(tsk, housekeeping_cpumask(HK_FLAG_KTHREAD)); set_mems_allowed(node_states[N_MEMORY]); current->flags |= PF_NOFREEZE; diff --git a/kernel/relay.c b/kernel/relay.c index 13c19f39e31e23e3d5f9ba2110699c5c7d079a82..b8703edb50dd31d2e4df70f62b73e9c8e0ed6120 100644 --- a/kernel/relay.c +++ b/kernel/relay.c @@ -996,14 +996,14 @@ static void relay_file_read_consume(struct rchan_buf *buf, /* * relay_file_read_avail - boolean, are there unconsumed bytes available? */ -static int relay_file_read_avail(struct rchan_buf *buf, size_t read_pos) +static int relay_file_read_avail(struct rchan_buf *buf) { size_t subbuf_size = buf->chan->subbuf_size; size_t n_subbufs = buf->chan->n_subbufs; size_t produced = buf->subbufs_produced; size_t consumed = buf->subbufs_consumed; - relay_file_read_consume(buf, read_pos, 0); + relay_file_read_consume(buf, 0, 0); consumed = buf->subbufs_consumed; @@ -1064,23 +1064,21 @@ static size_t relay_file_read_subbuf_avail(size_t read_pos, /** * relay_file_read_start_pos - find the first available byte to read - * @read_pos: file read position * @buf: relay channel buffer * - * If the @read_pos is in the middle of padding, return the + * If the read_pos is in the middle of padding, return the * position of the first actually available byte, otherwise * return the original value. */ -static size_t relay_file_read_start_pos(size_t read_pos, - struct rchan_buf *buf) +static size_t relay_file_read_start_pos(struct rchan_buf *buf) { size_t read_subbuf, padding, padding_start, padding_end; size_t subbuf_size = buf->chan->subbuf_size; size_t n_subbufs = buf->chan->n_subbufs; size_t consumed = buf->subbufs_consumed % n_subbufs; + size_t read_pos = (consumed * subbuf_size + buf->bytes_consumed) + % (n_subbufs * subbuf_size); - if (!read_pos) - read_pos = consumed * subbuf_size + buf->bytes_consumed; read_subbuf = read_pos / subbuf_size; padding = buf->padding[read_subbuf]; padding_start = (read_subbuf + 1) * subbuf_size - padding; @@ -1136,10 +1134,10 @@ static ssize_t relay_file_read(struct file *filp, do { void *from; - if (!relay_file_read_avail(buf, *ppos)) + if (!relay_file_read_avail(buf)) break; - read_start = relay_file_read_start_pos(*ppos, buf); + read_start = relay_file_read_start_pos(buf); avail = relay_file_read_subbuf_avail(read_start, buf); if (!avail) break; diff --git a/kernel/sched/isolation.c b/kernel/sched/isolation.c index da0ac89cc382a6c3a2fef45fb47e8c9e72b33c09..0409a879ae5f67ac0eb6c5f50897db573e4f2326 100644 --- a/kernel/sched/isolation.c +++ b/kernel/sched/isolation.c @@ -174,7 +174,8 @@ static int __init housekeeping_nohz_full_setup(char *str) { unsigned int flags; - flags = HK_FLAG_TICK | HK_FLAG_WQ | HK_FLAG_TIMER | HK_FLAG_RCU | HK_FLAG_MISC; + flags = HK_FLAG_TICK | HK_FLAG_WQ | HK_FLAG_TIMER | HK_FLAG_RCU | + HK_FLAG_MISC | HK_FLAG_KTHREAD; return housekeeping_setup(str, flags); } diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index f5f522d5151a64613c16c15ddbd8be30ba0563bf..53e294313ab7ae75c5c1505f2074e6383bd59f1a 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -1583,6 +1583,8 @@ static struct sched_rt_entity *pick_next_rt_entity(struct rq *rq, BUG_ON(idx >= MAX_RT_PRIO); queue = array->queue + idx; + if (SCHED_WARN_ON(list_empty(queue))) + return NULL; next = list_entry(queue->next, struct sched_rt_entity, run_list); return next; @@ -1596,7 +1598,8 @@ static struct task_struct *_pick_next_task_rt(struct rq *rq) do { rt_se = pick_next_rt_entity(rq, rt_rq); - BUG_ON(!rt_se); + if (unlikely(!rt_se)) + return NULL; rt_rq = group_rt_rq(rt_se); } while (rt_rq); diff --git a/kernel/sys.c b/kernel/sys.c index 6f7a0c9e83f3335e10505f0828ec1cfc06c0abee..3c990df3498e85fa84744edd83e568d223f21539 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -1531,6 +1531,8 @@ int do_prlimit(struct task_struct *tsk, unsigned int resource, if (resource >= RLIM_NLIMITS) return -EINVAL; + resource = array_index_nospec(resource, RLIM_NLIMITS); + if (new_rlim) { if (new_rlim->rlim_cur > new_rlim->rlim_max) return -EINVAL; diff --git a/net/core/sock.c b/net/core/sock.c index 0b370f5cc23ee3065fb2043e799fc9ef46735446..d4f24066eb12e771fcced860f7da5173f040f519 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -2769,7 +2769,7 @@ void sk_stop_timer(struct sock *sk, struct timer_list* timer) } EXPORT_SYMBOL(sk_stop_timer); -void sock_init_data(struct socket *sock, struct sock *sk) +void sock_init_data_uid(struct socket *sock, struct sock *sk, kuid_t uid) { sk_init_common(sk); sk->sk_send_head = NULL; @@ -2788,11 +2788,10 @@ void sock_init_data(struct socket *sock, struct sock *sk) sk->sk_type = sock->type; sk->sk_wq = sock->wq; sock->sk = sk; - sk->sk_uid = SOCK_INODE(sock)->i_uid; } else { sk->sk_wq = NULL; - sk->sk_uid = make_kuid(sock_net(sk)->user_ns, 0); } + sk->sk_uid = uid; rwlock_init(&sk->sk_callback_lock); if (sk->sk_kern_sock) @@ -2850,6 +2849,16 @@ void sock_init_data(struct socket *sock, struct sock *sk) refcount_set(&sk->sk_refcnt, 1); atomic_set(&sk->sk_drops, 0); } +EXPORT_SYMBOL(sock_init_data_uid); + +void sock_init_data(struct socket *sock, struct sock *sk) +{ + kuid_t uid = sock ? + SOCK_INODE(sock)->i_uid : + make_kuid(sock_net(sk)->user_ns, 0); + + sock_init_data_uid(sock, sk, uid); +} EXPORT_SYMBOL(sock_init_data); void lock_sock_nested(struct sock *sk, int subclass) diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 3676317e888033a3a7fd668044cab5c2d51f2218..bf19b384f9403fbdd732e41f1ed864115fa94db4 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -2730,7 +2730,8 @@ static int nf_tables_newrule(struct net *net, struct sock *nlsk, return 0; err2: - nf_tables_rule_release(&ctx, rule); + nft_rule_expr_deactivate(&ctx, rule, NFT_TRANS_RELEASE); + nf_tables_rule_destroy(&ctx, rule); err1: for (i = 0; i < n; i++) { if (info[i].ops) { diff --git a/net/rds/message.c b/net/rds/message.c index 4b00b1152a5f0a885100098e565b881ab68b7e57..309b54cc62ae317a0253a9122ff69438fb015142 100644 --- a/net/rds/message.c +++ b/net/rds/message.c @@ -104,9 +104,9 @@ static void rds_rm_zerocopy_callback(struct rds_sock *rs, spin_lock_irqsave(&q->lock, flags); head = &q->zcookie_head; if (!list_empty(head)) { - info = list_entry(head, struct rds_msg_zcopy_info, - rs_zcookie_next); - if (info && rds_zcookie_add(info, cookie)) { + info = list_first_entry(head, struct rds_msg_zcopy_info, + rs_zcookie_next); + if (rds_zcookie_add(info, cookie)) { spin_unlock_irqrestore(&q->lock, flags); kfree(rds_info_from_znotifier(znotif)); /* caller invokes rds_wake_sk_sleep() */ diff --git a/net/sched/Kconfig b/net/sched/Kconfig index e9574138831116a59db2c39aaa2cd4ee4f28e06b..4547022ed7f4ef13879fb3eed4c565dde77d4c01 100644 --- a/net/sched/Kconfig +++ b/net/sched/Kconfig @@ -458,17 +458,6 @@ config NET_CLS_BASIC To compile this code as a module, choose M here: the module will be called cls_basic. -config NET_CLS_TCINDEX - tristate "Traffic-Control Index (TCINDEX)" - select NET_CLS - ---help--- - Say Y here if you want to be able to classify packets based on - traffic control indices. You will want this feature if you want - to implement Differentiated Services together with DSMARK. - - To compile this code as a module, choose M here: the - module will be called cls_tcindex. - config NET_CLS_ROUTE4 tristate "Routing decision (ROUTE)" depends on INET diff --git a/net/sched/Makefile b/net/sched/Makefile index f0403f49edcbd50e27d9ea450c2e46b5b4727b8e..5eed580cdb4227286bd4cc50602c6cfce77d9e34 100644 --- a/net/sched/Makefile +++ b/net/sched/Makefile @@ -62,7 +62,6 @@ obj-$(CONFIG_NET_CLS_U32) += cls_u32.o obj-$(CONFIG_NET_CLS_ROUTE4) += cls_route.o obj-$(CONFIG_NET_CLS_FW) += cls_fw.o obj-$(CONFIG_NET_CLS_RSVP) += cls_rsvp.o -obj-$(CONFIG_NET_CLS_TCINDEX) += cls_tcindex.o obj-$(CONFIG_NET_CLS_RSVP6) += cls_rsvp6.o obj-$(CONFIG_NET_CLS_BASIC) += cls_basic.o obj-$(CONFIG_NET_CLS_FLOW) += cls_flow.o diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index 09b359784629e46b1ce5f60c42e193196f312549..789517fde7589cf7a4afc2bb6862b3344d0e4cae 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -632,6 +632,9 @@ static int fl_set_geneve_opt(const struct nlattr *nla, struct fl_flow_key *key, if (option_len > sizeof(struct geneve_opt)) data_len = option_len - sizeof(struct geneve_opt); + if (key->enc_opts.len > FLOW_DIS_TUN_OPTS_MAX - 4) + return -ERANGE; + opt = (struct geneve_opt *)&key->enc_opts.data[key->enc_opts.len]; memset(opt, 0xff, option_len); opt->length = data_len / 4; diff --git a/net/sched/cls_tcindex.c b/net/sched/cls_tcindex.c deleted file mode 100644 index 7735404da57295ec32e3989412abfb4087dc40f4..0000000000000000000000000000000000000000 --- a/net/sched/cls_tcindex.c +++ /dev/null @@ -1,715 +0,0 @@ -/* - * net/sched/cls_tcindex.c Packet classifier for skb->tc_index - * - * Written 1998,1999 by Werner Almesberger, EPFL ICA - */ - -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include -#include - -/* - * Passing parameters to the root seems to be done more awkwardly than really - * necessary. At least, u32 doesn't seem to use such dirty hacks. To be - * verified. FIXME. - */ - -#define PERFECT_HASH_THRESHOLD 64 /* use perfect hash if not bigger */ -#define DEFAULT_HASH_SIZE 64 /* optimized for diffserv */ - - -struct tcindex_filter_result { - struct tcf_exts exts; - struct tcf_result res; - struct rcu_work rwork; -}; - -struct tcindex_filter { - u16 key; - struct tcindex_filter_result result; - struct tcindex_filter __rcu *next; - struct rcu_work rwork; -}; - - -struct tcindex_data { - struct tcindex_filter_result *perfect; /* perfect hash; NULL if none */ - struct tcindex_filter __rcu **h; /* imperfect hash; */ - struct tcf_proto *tp; - u16 mask; /* AND key with mask */ - u32 shift; /* shift ANDed key to the right */ - u32 hash; /* hash table size; 0 if undefined */ - u32 alloc_hash; /* allocated size */ - u32 fall_through; /* 0: only classify if explicit match */ - struct rcu_work rwork; -}; - -static inline int tcindex_filter_is_set(struct tcindex_filter_result *r) -{ - return tcf_exts_has_actions(&r->exts) || r->res.classid; -} - -static struct tcindex_filter_result *tcindex_lookup(struct tcindex_data *p, - u16 key) -{ - if (p->perfect) { - struct tcindex_filter_result *f = p->perfect + key; - - return tcindex_filter_is_set(f) ? f : NULL; - } else if (p->h) { - struct tcindex_filter __rcu **fp; - struct tcindex_filter *f; - - fp = &p->h[key % p->hash]; - for (f = rcu_dereference_bh_rtnl(*fp); - f; - fp = &f->next, f = rcu_dereference_bh_rtnl(*fp)) - if (f->key == key) - return &f->result; - } - - return NULL; -} - - -static int tcindex_classify(struct sk_buff *skb, const struct tcf_proto *tp, - struct tcf_result *res) -{ - struct tcindex_data *p = rcu_dereference_bh(tp->root); - struct tcindex_filter_result *f; - int key = (skb->tc_index & p->mask) >> p->shift; - - pr_debug("tcindex_classify(skb %p,tp %p,res %p),p %p\n", - skb, tp, res, p); - - f = tcindex_lookup(p, key); - if (!f) { - struct Qdisc *q = tcf_block_q(tp->chain->block); - - if (!p->fall_through) - return -1; - res->classid = TC_H_MAKE(TC_H_MAJ(q->handle), key); - res->class = 0; - pr_debug("alg 0x%x\n", res->classid); - return 0; - } - *res = f->res; - pr_debug("map 0x%x\n", res->classid); - - return tcf_exts_exec(skb, &f->exts, res); -} - - -static void *tcindex_get(struct tcf_proto *tp, u32 handle) -{ - struct tcindex_data *p = rtnl_dereference(tp->root); - struct tcindex_filter_result *r; - - pr_debug("tcindex_get(tp %p,handle 0x%08x)\n", tp, handle); - if (p->perfect && handle >= p->alloc_hash) - return NULL; - r = tcindex_lookup(p, handle); - return r && tcindex_filter_is_set(r) ? r : NULL; -} - -static int tcindex_init(struct tcf_proto *tp) -{ - struct tcindex_data *p; - - pr_debug("tcindex_init(tp %p)\n", tp); - p = kzalloc(sizeof(struct tcindex_data), GFP_KERNEL); - if (!p) - return -ENOMEM; - - p->mask = 0xffff; - p->hash = DEFAULT_HASH_SIZE; - p->fall_through = 1; - - rcu_assign_pointer(tp->root, p); - return 0; -} - -static void __tcindex_destroy_rexts(struct tcindex_filter_result *r) -{ - tcf_exts_destroy(&r->exts); - tcf_exts_put_net(&r->exts); -} - -static void tcindex_destroy_rexts_work(struct work_struct *work) -{ - struct tcindex_filter_result *r; - - r = container_of(to_rcu_work(work), - struct tcindex_filter_result, - rwork); - rtnl_lock(); - __tcindex_destroy_rexts(r); - rtnl_unlock(); -} - -static void __tcindex_destroy_fexts(struct tcindex_filter *f) -{ - tcf_exts_destroy(&f->result.exts); - tcf_exts_put_net(&f->result.exts); - kfree(f); -} - -static void tcindex_destroy_fexts_work(struct work_struct *work) -{ - struct tcindex_filter *f = container_of(to_rcu_work(work), - struct tcindex_filter, - rwork); - - rtnl_lock(); - __tcindex_destroy_fexts(f); - rtnl_unlock(); -} - -static int tcindex_delete(struct tcf_proto *tp, void *arg, bool *last, - struct netlink_ext_ack *extack) -{ - struct tcindex_data *p = rtnl_dereference(tp->root); - struct tcindex_filter_result *r = arg; - struct tcindex_filter __rcu **walk; - struct tcindex_filter *f = NULL; - - pr_debug("tcindex_delete(tp %p,arg %p),p %p\n", tp, arg, p); - if (p->perfect) { - if (!r->res.class) - return -ENOENT; - } else { - int i; - - for (i = 0; i < p->hash; i++) { - walk = p->h + i; - for (f = rtnl_dereference(*walk); f; - walk = &f->next, f = rtnl_dereference(*walk)) { - if (&f->result == r) - goto found; - } - } - return -ENOENT; - -found: - rcu_assign_pointer(*walk, rtnl_dereference(f->next)); - } - tcf_unbind_filter(tp, &r->res); - /* all classifiers are required to call tcf_exts_destroy() after rcu - * grace period, since converted-to-rcu actions are relying on that - * in cleanup() callback - */ - if (f) { - if (tcf_exts_get_net(&f->result.exts)) - tcf_queue_work(&f->rwork, tcindex_destroy_fexts_work); - else - __tcindex_destroy_fexts(f); - } else { - if (tcf_exts_get_net(&r->exts)) - tcf_queue_work(&r->rwork, tcindex_destroy_rexts_work); - else - __tcindex_destroy_rexts(r); - } - - *last = false; - return 0; -} - -static void tcindex_destroy_work(struct work_struct *work) -{ - struct tcindex_data *p = container_of(to_rcu_work(work), - struct tcindex_data, - rwork); - - kfree(p->perfect); - kfree(p->h); - kfree(p); -} - -static inline int -valid_perfect_hash(struct tcindex_data *p) -{ - return p->hash > (p->mask >> p->shift); -} - -static const struct nla_policy tcindex_policy[TCA_TCINDEX_MAX + 1] = { - [TCA_TCINDEX_HASH] = { .type = NLA_U32 }, - [TCA_TCINDEX_MASK] = { .type = NLA_U16 }, - [TCA_TCINDEX_SHIFT] = { .type = NLA_U32 }, - [TCA_TCINDEX_FALL_THROUGH] = { .type = NLA_U32 }, - [TCA_TCINDEX_CLASSID] = { .type = NLA_U32 }, -}; - -static int tcindex_filter_result_init(struct tcindex_filter_result *r) -{ - memset(r, 0, sizeof(*r)); - return tcf_exts_init(&r->exts, TCA_TCINDEX_ACT, TCA_TCINDEX_POLICE); -} - -static void tcindex_partial_destroy_work(struct work_struct *work) -{ - struct tcindex_data *p = container_of(to_rcu_work(work), - struct tcindex_data, - rwork); - - kfree(p->perfect); - kfree(p); -} - -static void tcindex_free_perfect_hash(struct tcindex_data *cp) -{ - int i; - - for (i = 0; i < cp->hash; i++) - tcf_exts_destroy(&cp->perfect[i].exts); - kfree(cp->perfect); -} - -static int tcindex_alloc_perfect_hash(struct net *net, struct tcindex_data *cp) -{ - int i, err = 0; - - cp->perfect = kcalloc(cp->hash, sizeof(struct tcindex_filter_result), - GFP_KERNEL); - if (!cp->perfect) - return -ENOMEM; - - for (i = 0; i < cp->hash; i++) { - err = tcf_exts_init(&cp->perfect[i].exts, - TCA_TCINDEX_ACT, TCA_TCINDEX_POLICE); - if (err < 0) - goto errout; -#ifdef CONFIG_NET_CLS_ACT - cp->perfect[i].exts.net = net; -#endif - } - - return 0; - -errout: - tcindex_free_perfect_hash(cp); - return err; -} - -static int -tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base, - u32 handle, struct tcindex_data *p, - struct tcindex_filter_result *r, struct nlattr **tb, - struct nlattr *est, bool ovr, struct netlink_ext_ack *extack) -{ - struct tcindex_filter_result new_filter_result, *old_r = r; - struct tcindex_data *cp = NULL, *oldp; - struct tcindex_filter *f = NULL; /* make gcc behave */ - struct tcf_result cr = {}; - int err, balloc = 0; - struct tcf_exts e; - bool update_h = false; - - err = tcf_exts_init(&e, TCA_TCINDEX_ACT, TCA_TCINDEX_POLICE); - if (err < 0) - return err; - err = tcf_exts_validate(net, tp, tb, est, &e, ovr, extack); - if (err < 0) - goto errout; - - err = -ENOMEM; - /* tcindex_data attributes must look atomic to classifier/lookup so - * allocate new tcindex data and RCU assign it onto root. Keeping - * perfect hash and hash pointers from old data. - */ - cp = kzalloc(sizeof(*cp), GFP_KERNEL); - if (!cp) - goto errout; - - cp->mask = p->mask; - cp->shift = p->shift; - cp->hash = p->hash; - cp->alloc_hash = p->alloc_hash; - cp->fall_through = p->fall_through; - cp->tp = tp; - - if (p->perfect) { - int i; - - if (tcindex_alloc_perfect_hash(net, cp) < 0) - goto errout; - for (i = 0; i < cp->hash; i++) - cp->perfect[i].res = p->perfect[i].res; - balloc = 1; - } - cp->h = p->h; - - err = tcindex_filter_result_init(&new_filter_result); - if (err < 0) - goto errout1; - if (old_r) - cr = r->res; - - if (tb[TCA_TCINDEX_HASH]) - cp->hash = nla_get_u32(tb[TCA_TCINDEX_HASH]); - - if (tb[TCA_TCINDEX_MASK]) - cp->mask = nla_get_u16(tb[TCA_TCINDEX_MASK]); - - if (tb[TCA_TCINDEX_SHIFT]) - cp->shift = nla_get_u32(tb[TCA_TCINDEX_SHIFT]); - - err = -EBUSY; - - /* Hash already allocated, make sure that we still meet the - * requirements for the allocated hash. - */ - if (cp->perfect) { - if (!valid_perfect_hash(cp) || - cp->hash > cp->alloc_hash) - goto errout_alloc; - } else if (cp->h && cp->hash != cp->alloc_hash) { - goto errout_alloc; - } - - err = -EINVAL; - if (tb[TCA_TCINDEX_FALL_THROUGH]) - cp->fall_through = nla_get_u32(tb[TCA_TCINDEX_FALL_THROUGH]); - - if (!cp->hash) { - /* Hash not specified, use perfect hash if the upper limit - * of the hashing index is below the threshold. - */ - if ((cp->mask >> cp->shift) < PERFECT_HASH_THRESHOLD) - cp->hash = (cp->mask >> cp->shift) + 1; - else - cp->hash = DEFAULT_HASH_SIZE; - } - - if (!cp->perfect && !cp->h) - cp->alloc_hash = cp->hash; - - /* Note: this could be as restrictive as if (handle & ~(mask >> shift)) - * but then, we'd fail handles that may become valid after some future - * mask change. While this is extremely unlikely to ever matter, - * the check below is safer (and also more backwards-compatible). - */ - if (cp->perfect || valid_perfect_hash(cp)) - if (handle >= cp->alloc_hash) - goto errout_alloc; - - - err = -ENOMEM; - if (!cp->perfect && !cp->h) { - if (valid_perfect_hash(cp)) { - if (tcindex_alloc_perfect_hash(net, cp) < 0) - goto errout_alloc; - balloc = 1; - } else { - struct tcindex_filter __rcu **hash; - - hash = kcalloc(cp->hash, - sizeof(struct tcindex_filter *), - GFP_KERNEL); - - if (!hash) - goto errout_alloc; - - cp->h = hash; - balloc = 2; - } - } - - if (cp->perfect) { - r = cp->perfect + handle; - } else { - /* imperfect area is updated in-place using rcu */ - update_h = !!tcindex_lookup(cp, handle); - r = &new_filter_result; - } - - if (r == &new_filter_result) { - f = kzalloc(sizeof(*f), GFP_KERNEL); - if (!f) - goto errout_alloc; - f->key = handle; - f->next = NULL; - err = tcindex_filter_result_init(&f->result); - if (err < 0) { - kfree(f); - goto errout_alloc; - } - } - - if (tb[TCA_TCINDEX_CLASSID]) { - cr.classid = nla_get_u32(tb[TCA_TCINDEX_CLASSID]); - tcf_bind_filter(tp, &cr, base); - } - - if (old_r && old_r != r) { - err = tcindex_filter_result_init(old_r); - if (err < 0) { - kfree(f); - goto errout_alloc; - } - } - - oldp = p; - r->res = cr; - tcf_exts_change(&r->exts, &e); - - rcu_assign_pointer(tp->root, cp); - - if (update_h) { - struct tcindex_filter __rcu **fp; - struct tcindex_filter *cf; - - f->result.res = r->res; - tcf_exts_change(&f->result.exts, &r->exts); - - /* imperfect area bucket */ - fp = cp->h + (handle % cp->hash); - - /* lookup the filter, guaranteed to exist */ - for (cf = rcu_dereference_bh_rtnl(*fp); cf; - fp = &cf->next, cf = rcu_dereference_bh_rtnl(*fp)) - if (cf->key == handle) - break; - - f->next = cf->next; - - cf = rcu_replace_pointer(*fp, f, 1); - tcf_exts_get_net(&cf->result.exts); - tcf_queue_work(&cf->rwork, tcindex_destroy_fexts_work); - } else if (r == &new_filter_result) { - struct tcindex_filter *nfp; - struct tcindex_filter __rcu **fp; - - f->result.res = r->res; - tcf_exts_change(&f->result.exts, &r->exts); - - fp = cp->h + (handle % cp->hash); - for (nfp = rtnl_dereference(*fp); - nfp; - fp = &nfp->next, nfp = rtnl_dereference(*fp)) - ; /* nothing */ - - rcu_assign_pointer(*fp, f); - } else { - tcf_exts_destroy(&new_filter_result.exts); - } - - if (oldp) - tcf_queue_work(&oldp->rwork, tcindex_partial_destroy_work); - return 0; - -errout_alloc: - if (balloc == 1) - tcindex_free_perfect_hash(cp); - else if (balloc == 2) - kfree(cp->h); -errout1: - tcf_exts_destroy(&new_filter_result.exts); -errout: - kfree(cp); - tcf_exts_destroy(&e); - return err; -} - -static int -tcindex_change(struct net *net, struct sk_buff *in_skb, - struct tcf_proto *tp, unsigned long base, u32 handle, - struct nlattr **tca, void **arg, bool ovr, - struct netlink_ext_ack *extack) -{ - struct nlattr *opt = tca[TCA_OPTIONS]; - struct nlattr *tb[TCA_TCINDEX_MAX + 1]; - struct tcindex_data *p = rtnl_dereference(tp->root); - struct tcindex_filter_result *r = *arg; - int err; - - pr_debug("tcindex_change(tp %p,handle 0x%08x,tca %p,arg %p),opt %p," - "p %p,r %p,*arg %p\n", - tp, handle, tca, arg, opt, p, r, arg ? *arg : NULL); - - if (!opt) - return 0; - - err = nla_parse_nested(tb, TCA_TCINDEX_MAX, opt, tcindex_policy, NULL); - if (err < 0) - return err; - - return tcindex_set_parms(net, tp, base, handle, p, r, tb, - tca[TCA_RATE], ovr, extack); -} - -static void tcindex_walk(struct tcf_proto *tp, struct tcf_walker *walker) -{ - struct tcindex_data *p = rtnl_dereference(tp->root); - struct tcindex_filter *f, *next; - int i; - - pr_debug("tcindex_walk(tp %p,walker %p),p %p\n", tp, walker, p); - if (p->perfect) { - for (i = 0; i < p->hash; i++) { - if (!p->perfect[i].res.class) - continue; - if (walker->count >= walker->skip) { - if (walker->fn(tp, p->perfect + i, walker) < 0) { - walker->stop = 1; - return; - } - } - walker->count++; - } - } - if (!p->h) - return; - for (i = 0; i < p->hash; i++) { - for (f = rtnl_dereference(p->h[i]); f; f = next) { - next = rtnl_dereference(f->next); - if (walker->count >= walker->skip) { - if (walker->fn(tp, &f->result, walker) < 0) { - walker->stop = 1; - return; - } - } - walker->count++; - } - } -} - -static void tcindex_destroy(struct tcf_proto *tp, - struct netlink_ext_ack *extack) -{ - struct tcindex_data *p = rtnl_dereference(tp->root); - int i; - - pr_debug("tcindex_destroy(tp %p),p %p\n", tp, p); - - if (p->perfect) { - for (i = 0; i < p->hash; i++) { - struct tcindex_filter_result *r = p->perfect + i; - - tcf_unbind_filter(tp, &r->res); - if (tcf_exts_get_net(&r->exts)) - tcf_queue_work(&r->rwork, - tcindex_destroy_rexts_work); - else - __tcindex_destroy_rexts(r); - } - } - - for (i = 0; p->h && i < p->hash; i++) { - struct tcindex_filter *f, *next; - bool last; - - for (f = rtnl_dereference(p->h[i]); f; f = next) { - next = rtnl_dereference(f->next); - tcindex_delete(tp, &f->result, &last, NULL); - } - } - - tcf_queue_work(&p->rwork, tcindex_destroy_work); -} - - -static int tcindex_dump(struct net *net, struct tcf_proto *tp, void *fh, - struct sk_buff *skb, struct tcmsg *t) -{ - struct tcindex_data *p = rtnl_dereference(tp->root); - struct tcindex_filter_result *r = fh; - struct nlattr *nest; - - pr_debug("tcindex_dump(tp %p,fh %p,skb %p,t %p),p %p,r %p\n", - tp, fh, skb, t, p, r); - pr_debug("p->perfect %p p->h %p\n", p->perfect, p->h); - - nest = nla_nest_start(skb, TCA_OPTIONS); - if (nest == NULL) - goto nla_put_failure; - - if (!fh) { - t->tcm_handle = ~0; /* whatever ... */ - if (nla_put_u32(skb, TCA_TCINDEX_HASH, p->hash) || - nla_put_u16(skb, TCA_TCINDEX_MASK, p->mask) || - nla_put_u32(skb, TCA_TCINDEX_SHIFT, p->shift) || - nla_put_u32(skb, TCA_TCINDEX_FALL_THROUGH, p->fall_through)) - goto nla_put_failure; - nla_nest_end(skb, nest); - } else { - if (p->perfect) { - t->tcm_handle = r - p->perfect; - } else { - struct tcindex_filter *f; - struct tcindex_filter __rcu **fp; - int i; - - t->tcm_handle = 0; - for (i = 0; !t->tcm_handle && i < p->hash; i++) { - fp = &p->h[i]; - for (f = rtnl_dereference(*fp); - !t->tcm_handle && f; - fp = &f->next, f = rtnl_dereference(*fp)) { - if (&f->result == r) - t->tcm_handle = f->key; - } - } - } - pr_debug("handle = %d\n", t->tcm_handle); - if (r->res.class && - nla_put_u32(skb, TCA_TCINDEX_CLASSID, r->res.classid)) - goto nla_put_failure; - - if (tcf_exts_dump(skb, &r->exts) < 0) - goto nla_put_failure; - nla_nest_end(skb, nest); - - if (tcf_exts_dump_stats(skb, &r->exts) < 0) - goto nla_put_failure; - } - - return skb->len; - -nla_put_failure: - nla_nest_cancel(skb, nest); - return -1; -} - -static void tcindex_bind_class(void *fh, u32 classid, unsigned long cl) -{ - struct tcindex_filter_result *r = fh; - - if (r && r->res.classid == classid) - r->res.class = cl; -} - -static struct tcf_proto_ops cls_tcindex_ops __read_mostly = { - .kind = "tcindex", - .classify = tcindex_classify, - .init = tcindex_init, - .destroy = tcindex_destroy, - .get = tcindex_get, - .change = tcindex_change, - .delete = tcindex_delete, - .walk = tcindex_walk, - .dump = tcindex_dump, - .bind_class = tcindex_bind_class, - .owner = THIS_MODULE, -}; - -static int __init init_tcindex(void) -{ - return register_tcf_proto_ops(&cls_tcindex_ops); -} - -static void __exit exit_tcindex(void) -{ - unregister_tcf_proto_ops(&cls_tcindex_ops); -} - -module_init(init_tcindex) -module_exit(exit_tcindex) -MODULE_LICENSE("GPL"); diff --git a/security/selinux/ss/services.c b/security/selinux/ss/services.c index f3def298a90e9c3b766752fb3cd9566df02fb874..12763b6c7d51092d626227c75f6b426e4bf453ab 100644 --- a/security/selinux/ss/services.c +++ b/security/selinux/ss/services.c @@ -2263,6 +2263,43 @@ size_t security_policydb_len(struct selinux_state *state) return len; } +/** + * ocontext_to_sid - Helper to safely get sid for an ocontext + * @sidtab: SID table + * @c: ocontext structure + * @index: index of the context entry (0 or 1) + * @out_sid: pointer to the resulting SID value + * + * For all ocontexts except OCON_ISID the SID fields are populated + * on-demand when needed. Since updating the SID value is an SMP-sensitive + * operation, this helper must be used to do that safely. + * + * WARNING: This function may return -ESTALE, indicating that the caller + * must retry the operation after re-acquiring the policy pointer! + */ +static int ocontext_to_sid(struct sidtab *sidtab, struct ocontext *c, + size_t index, u32 *out_sid) +{ + int rc; + u32 sid; + + /* Ensure the associated sidtab entry is visible to this thread. */ + sid = smp_load_acquire(&c->sid[index]); + if (!sid) { + rc = sidtab_context_to_sid(sidtab, &c->context[index], &sid); + if (rc) + return rc; + + /* + * Ensure the new sidtab entry is visible to other threads + * when they see the SID. + */ + smp_store_release(&c->sid[index], sid); + } + *out_sid = sid; + return 0; +} + /** * security_port_sid - Obtain the SID for a port. * @protocol: protocol number @@ -2275,10 +2312,12 @@ int security_port_sid(struct selinux_state *state, struct policydb *policydb; struct sidtab *sidtab; struct ocontext *c; - int rc = 0; + int rc; read_lock(&state->ss->policy_rwlock); +retry: + rc = 0; policydb = &state->ss->policydb; sidtab = &state->ss->sidtab; @@ -2292,14 +2331,11 @@ int security_port_sid(struct selinux_state *state, } if (c) { - if (!c->sid[0]) { - rc = sidtab_context_to_sid(sidtab, - &c->context[0], - &c->sid[0]); - if (rc) - goto out; - } - *out_sid = c->sid[0]; + rc = ocontext_to_sid(sidtab, c, 0, out_sid); + if (rc == -ESTALE) + goto retry; + if (rc) + goto out; } else { *out_sid = SECINITSID_PORT; } @@ -2321,10 +2357,12 @@ int security_ib_pkey_sid(struct selinux_state *state, struct policydb *policydb; struct sidtab *sidtab; struct ocontext *c; - int rc = 0; + int rc; read_lock(&state->ss->policy_rwlock); +retry: + rc = 0; policydb = &state->ss->policydb; sidtab = &state->ss->sidtab; @@ -2339,14 +2377,11 @@ int security_ib_pkey_sid(struct selinux_state *state, } if (c) { - if (!c->sid[0]) { - rc = sidtab_context_to_sid(sidtab, - &c->context[0], - &c->sid[0]); - if (rc) - goto out; - } - *out_sid = c->sid[0]; + rc = ocontext_to_sid(sidtab, c, 0, out_sid); + if (rc == -ESTALE) + goto retry; + if (rc) + goto out; } else *out_sid = SECINITSID_UNLABELED; @@ -2367,10 +2402,12 @@ int security_ib_endport_sid(struct selinux_state *state, struct policydb *policydb; struct sidtab *sidtab; struct ocontext *c; - int rc = 0; + int rc; read_lock(&state->ss->policy_rwlock); +retry: + rc = 0; policydb = &state->ss->policydb; sidtab = &state->ss->sidtab; @@ -2386,14 +2423,11 @@ int security_ib_endport_sid(struct selinux_state *state, } if (c) { - if (!c->sid[0]) { - rc = sidtab_context_to_sid(sidtab, - &c->context[0], - &c->sid[0]); - if (rc) - goto out; - } - *out_sid = c->sid[0]; + rc = ocontext_to_sid(sidtab, c, 0, out_sid); + if (rc == -ESTALE) + goto retry; + if (rc) + goto out; } else *out_sid = SECINITSID_UNLABELED; @@ -2412,11 +2446,13 @@ int security_netif_sid(struct selinux_state *state, { struct policydb *policydb; struct sidtab *sidtab; - int rc = 0; + int rc; struct ocontext *c; read_lock(&state->ss->policy_rwlock); +retry: + rc = 0; policydb = &state->ss->policydb; sidtab = &state->ss->sidtab; @@ -2428,19 +2464,11 @@ int security_netif_sid(struct selinux_state *state, } if (c) { - if (!c->sid[0] || !c->sid[1]) { - rc = sidtab_context_to_sid(sidtab, - &c->context[0], - &c->sid[0]); - if (rc) - goto out; - rc = sidtab_context_to_sid(sidtab, - &c->context[1], - &c->sid[1]); - if (rc) - goto out; - } - *if_sid = c->sid[0]; + rc = ocontext_to_sid(sidtab, c, 0, if_sid); + if (rc == -ESTALE) + goto retry; + if (rc) + goto out; } else *if_sid = SECINITSID_NETIF; @@ -2482,6 +2510,7 @@ int security_node_sid(struct selinux_state *state, read_lock(&state->ss->policy_rwlock); +retry: policydb = &state->ss->policydb; sidtab = &state->ss->sidtab; @@ -2524,14 +2553,11 @@ int security_node_sid(struct selinux_state *state, } if (c) { - if (!c->sid[0]) { - rc = sidtab_context_to_sid(sidtab, - &c->context[0], - &c->sid[0]); - if (rc) - goto out; - } - *out_sid = c->sid[0]; + rc = ocontext_to_sid(sidtab, c, 0, out_sid); + if (rc == -ESTALE) + goto retry; + if (rc) + goto out; } else { *out_sid = SECINITSID_NODE; } @@ -2690,7 +2716,7 @@ static inline int __security_genfs_sid(struct selinux_state *state, u16 sclass; struct genfs *genfs; struct ocontext *c; - int rc, cmp = 0; + int cmp = 0; while (path[0] == '/' && path[1] == '/') path++; @@ -2704,9 +2730,8 @@ static inline int __security_genfs_sid(struct selinux_state *state, break; } - rc = -ENOENT; if (!genfs || cmp) - goto out; + return -ENOENT; for (c = genfs->head; c; c = c->next) { len = strlen(c->u.name); @@ -2715,20 +2740,10 @@ static inline int __security_genfs_sid(struct selinux_state *state, break; } - rc = -ENOENT; if (!c) - goto out; - - if (!c->sid[0]) { - rc = sidtab_context_to_sid(sidtab, &c->context[0], &c->sid[0]); - if (rc) - goto out; - } + return -ENOENT; - *sid = c->sid[0]; - rc = 0; -out: - return rc; + return ocontext_to_sid(sidtab, c, 0, sid); } /** @@ -2763,13 +2778,15 @@ int security_fs_use(struct selinux_state *state, struct super_block *sb) { struct policydb *policydb; struct sidtab *sidtab; - int rc = 0; + int rc; struct ocontext *c; struct superblock_security_struct *sbsec = sb->s_security; const char *fstype = sb->s_type->name; read_lock(&state->ss->policy_rwlock); +retry: + rc = 0; policydb = &state->ss->policydb; sidtab = &state->ss->sidtab; @@ -2782,13 +2799,11 @@ int security_fs_use(struct selinux_state *state, struct super_block *sb) if (c) { sbsec->behavior = c->v.behavior; - if (!c->sid[0]) { - rc = sidtab_context_to_sid(sidtab, &c->context[0], - &c->sid[0]); - if (rc) - goto out; - } - sbsec->sid = c->sid[0]; + rc = ocontext_to_sid(sidtab, c, 0, &sbsec->sid); + if (rc == -ESTALE) + goto retry; + if (rc) + goto out; } else { rc = __security_genfs_sid(state, fstype, "/", SECCLASS_DIR, &sbsec->sid); diff --git a/tools/bpf/bpftool/Documentation/bpftool-net.rst b/tools/bpf/bpftool/Documentation/bpftool-net.rst new file mode 100644 index 0000000000000000000000000000000000000000..408ec30d88726206b3bad8436ec8c9abdd11d806 --- /dev/null +++ b/tools/bpf/bpftool/Documentation/bpftool-net.rst @@ -0,0 +1,139 @@ +================ +bpftool-net +================ +------------------------------------------------------------------------------- +tool for inspection of netdev/tc related bpf prog attachments +------------------------------------------------------------------------------- + +:Manual section: 8 + +SYNOPSIS +======== + + **bpftool** [*OPTIONS*] **net** *COMMAND* + + *OPTIONS* := { [{ **-j** | **--json** }] [{ **-p** | **--pretty** }] } + + *COMMANDS* := + { **show** | **list** } [ **dev** name ] | **help** + +NET COMMANDS +============ + +| **bpftool** **net { show | list } [ dev name ]** +| **bpftool** **net help** + +DESCRIPTION +=========== + **bpftool net { show | list } [ dev name ]** + List bpf program attachments in the kernel networking subsystem. + + Currently, only device driver xdp attachments and tc filter + classification/action attachments are implemented, i.e., for + program types **BPF_PROG_TYPE_SCHED_CLS**, + **BPF_PROG_TYPE_SCHED_ACT** and **BPF_PROG_TYPE_XDP**. + For programs attached to a particular cgroup, e.g., + **BPF_PROG_TYPE_CGROUP_SKB**, **BPF_PROG_TYPE_CGROUP_SOCK**, + **BPF_PROG_TYPE_SOCK_OPS** and **BPF_PROG_TYPE_CGROUP_SOCK_ADDR**, + users can use **bpftool cgroup** to dump cgroup attachments. + For sk_{filter, skb, msg, reuseport} and lwt/seg6 + bpf programs, users should consult other tools, e.g., iproute2. + + The current output will start with all xdp program attachments, followed by + all tc class/qdisc bpf program attachments. Both xdp programs and + tc programs are ordered based on ifindex number. If multiple bpf + programs attached to the same networking device through **tc filter**, + the order will be first all bpf programs attached to tc classes, then + all bpf programs attached to non clsact qdiscs, and finally all + bpf programs attached to root and clsact qdisc. + + **bpftool net help** + Print short help message. + +OPTIONS +======= + -h, --help + Print short generic help message (similar to **bpftool help**). + + -v, --version + Print version number (similar to **bpftool version**). + + -j, --json + Generate JSON output. For commands that cannot produce JSON, this + option has no effect. + + -p, --pretty + Generate human-readable JSON output. Implies **-j**. + +EXAMPLES +======== + +| **# bpftool net** + +:: + + xdp: + eth0(2) driver id 198 + + tc: + eth0(2) htb name prefix_matcher.o:[cls_prefix_matcher_htb] id 111727 act [] + eth0(2) clsact/ingress fbflow_icmp id 130246 act [] + eth0(2) clsact/egress prefix_matcher.o:[cls_prefix_matcher_clsact] id 111726 + eth0(2) clsact/egress cls_fg_dscp id 108619 act [] + eth0(2) clsact/egress fbflow_egress id 130245 + +| +| **# bpftool -jp net** + +:: + + [{ + "xdp": [{ + "devname": "eth0", + "ifindex": 2, + "mode": "driver", + "id": 198 + } + ], + "tc": [{ + "devname": "eth0", + "ifindex": 2, + "kind": "htb", + "name": "prefix_matcher.o:[cls_prefix_matcher_htb]", + "id": 111727, + "act": [] + },{ + "devname": "eth0", + "ifindex": 2, + "kind": "clsact/ingress", + "name": "fbflow_icmp", + "id": 130246, + "act": [] + },{ + "devname": "eth0", + "ifindex": 2, + "kind": "clsact/egress", + "name": "prefix_matcher.o:[cls_prefix_matcher_clsact]", + "id": 111726, + },{ + "devname": "eth0", + "ifindex": 2, + "kind": "clsact/egress", + "name": "cls_fg_dscp", + "id": 108619, + "act": [] + },{ + "devname": "eth0", + "ifindex": 2, + "kind": "clsact/egress", + "name": "fbflow_egress", + "id": 130245, + } + ] + } + ] + + +SEE ALSO +======== + **bpftool**\ (8), **bpftool-prog**\ (8), **bpftool-map**\ (8) diff --git a/tools/bpf/bpftool/Documentation/bpftool.rst b/tools/bpf/bpftool/Documentation/bpftool.rst index b6f5d560460d5554d99df1f979faf6d5e49c7200..8dda77daeda968cc0cbfdf33c8d6537bc1842cf4 100644 --- a/tools/bpf/bpftool/Documentation/bpftool.rst +++ b/tools/bpf/bpftool/Documentation/bpftool.rst @@ -16,7 +16,7 @@ SYNOPSIS **bpftool** **version** - *OBJECT* := { **map** | **program** | **cgroup** | **perf** } + *OBJECT* := { **map** | **program** | **cgroup** | **perf** | **net** } *OPTIONS* := { { **-V** | **--version** } | { **-h** | **--help** } | { **-j** | **--json** } [{ **-p** | **--pretty** }] } @@ -32,6 +32,8 @@ SYNOPSIS *PERF-COMMANDS* := { **show** | **list** | **help** } + *NET-COMMANDS* := { **show** | **list** | **help** } + DESCRIPTION =========== *bpftool* allows for inspection and simple modification of BPF objects @@ -58,4 +60,4 @@ OPTIONS SEE ALSO ======== **bpftool-map**\ (8), **bpftool-prog**\ (8), **bpftool-cgroup**\ (8) - **bpftool-perf**\ (8) + **bpftool-perf**\ (8), **bpftool-net**\ (8) diff --git a/tools/bpf/bpftool/bash-completion/bpftool b/tools/bpf/bpftool/bash-completion/bpftool index c2b6b2176f3b75c37920e8ad7a21ae2604e4efca..ec577af2e5f0dfca1fed9fcdb314a861f889e898 100644 --- a/tools/bpf/bpftool/bash-completion/bpftool +++ b/tools/bpf/bpftool/bash-completion/bpftool @@ -494,10 +494,10 @@ _bpftool() _filedir return 0 ;; - tree) - _filedir - return 0 - ;; + tree) + _filedir + return 0 + ;; attach|detach) local ATTACH_TYPES='ingress egress sock_create sock_ops \ device bind4 bind6 post_bind4 post_bind6 connect4 \ @@ -552,6 +552,15 @@ _bpftool() ;; esac ;; + net) + case $command in + *) + [[ $prev == $object ]] && \ + COMPREPLY=( $( compgen -W 'help \ + show list' -- "$cur" ) ) + ;; + esac + ;; esac } && complete -F _bpftool bpftool diff --git a/tools/bpf/bpftool/main.c b/tools/bpf/bpftool/main.c index d15a62be6cf0fd0bbe306e9420fc07d9848ce679..79dc3f1935470f9fc3bda5a4afc5e91d7fb0f5f9 100644 --- a/tools/bpf/bpftool/main.c +++ b/tools/bpf/bpftool/main.c @@ -85,7 +85,7 @@ static int do_help(int argc, char **argv) " %s batch file FILE\n" " %s version\n" "\n" - " OBJECT := { prog | map | cgroup | perf }\n" + " OBJECT := { prog | map | cgroup | perf | net }\n" " " HELP_SPEC_OPTIONS "\n" "", bin_name, bin_name, bin_name); @@ -215,6 +215,7 @@ static const struct cmd cmds[] = { { "map", do_map }, { "cgroup", do_cgroup }, { "perf", do_perf }, + { "net", do_net }, { "version", do_version }, { 0 } }; diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h index 057a227bdb9f9a2a484118946c01db2db242e0a4..38413a16ab92cc9dd3fec59c63f3661288a91bde 100644 --- a/tools/bpf/bpftool/main.h +++ b/tools/bpf/bpftool/main.h @@ -136,6 +136,7 @@ int do_map(int argc, char **arg); int do_event_pipe(int argc, char **argv); int do_cgroup(int argc, char **arg); int do_perf(int argc, char **arg); +int do_net(int argc, char **arg); int prog_parse_fd(int *argc, char ***argv); int map_parse_fd(int *argc, char ***argv); @@ -165,4 +166,11 @@ struct btf_dumper { */ int btf_dumper_type(const struct btf_dumper *d, __u32 type_id, const void *data); + +struct nlattr; +struct ifinfomsg; +struct tcmsg; +int do_xdp_dump(struct ifinfomsg *ifinfo, struct nlattr **tb); +int do_filter_dump(struct tcmsg *ifinfo, struct nlattr **tb, const char *kind, + const char *devname, int ifindex); #endif diff --git a/tools/bpf/bpftool/map.c b/tools/bpf/bpftool/map.c index ec73d83d0d310aa5b6443cdaaf4ebcbd6e2556bb..f41e2907a3360e3f5c737c4322eafd5576d66257 100644 --- a/tools/bpf/bpftool/map.c +++ b/tools/bpf/bpftool/map.c @@ -660,12 +660,6 @@ static int do_dump(int argc, char **argv) if (fd < 0) return -1; - if (map_is_map_of_maps(info.type) || map_is_map_of_progs(info.type)) { - p_err("Dumping maps of maps and program maps not supported"); - close(fd); - return -1; - } - key = malloc(info.key_size); value = alloc_value(&info); if (!key || !value) { @@ -719,7 +713,9 @@ static int do_dump(int argc, char **argv) } else { print_entry_plain(&info, key, value); } - } else { + num_elems++; + } else if (!map_is_map_of_maps(info.type) && + !map_is_map_of_progs(info.type)) { if (json_output) { jsonw_name(json_wtr, "key"); print_hex_data_json(key, info.key_size); @@ -736,7 +732,6 @@ static int do_dump(int argc, char **argv) } prev_key = key; - num_elems++; } if (json_output) diff --git a/tools/bpf/bpftool/net.c b/tools/bpf/bpftool/net.c new file mode 100644 index 0000000000000000000000000000000000000000..63b47b8e5e419e2363d698042225bc7f63d66859 --- /dev/null +++ b/tools/bpf/bpftool/net.c @@ -0,0 +1,271 @@ +// SPDX-License-Identifier: GPL-2.0+ +// Copyright (C) 2018 Facebook + +#define _GNU_SOURCE +#include +#include +#include +#include +#include +#include +#include +#include +#include + +#include +#include +#include "main.h" +#include "netlink_dumper.h" + +struct ip_devname_ifindex { + char devname[64]; + int ifindex; +}; + +struct bpf_netdev_t { + struct ip_devname_ifindex *devices; + int used_len; + int array_len; + int filter_idx; +}; + +struct tc_kind_handle { + char kind[64]; + int handle; +}; + +struct bpf_tcinfo_t { + struct tc_kind_handle *handle_array; + int used_len; + int array_len; + bool is_qdisc; +}; + +struct bpf_filter_t { + const char *kind; + const char *devname; + int ifindex; +}; + +static int dump_link_nlmsg(void *cookie, void *msg, struct nlattr **tb) +{ + struct bpf_netdev_t *netinfo = cookie; + struct ifinfomsg *ifinfo = msg; + + if (netinfo->filter_idx > 0 && netinfo->filter_idx != ifinfo->ifi_index) + return 0; + + if (netinfo->used_len == netinfo->array_len) { + netinfo->devices = realloc(netinfo->devices, + (netinfo->array_len + 16) * + sizeof(struct ip_devname_ifindex)); + if (!netinfo->devices) + return -ENOMEM; + + netinfo->array_len += 16; + } + netinfo->devices[netinfo->used_len].ifindex = ifinfo->ifi_index; + snprintf(netinfo->devices[netinfo->used_len].devname, + sizeof(netinfo->devices[netinfo->used_len].devname), + "%s", + tb[IFLA_IFNAME] ? nla_getattr_str(tb[IFLA_IFNAME]) : ""); + netinfo->used_len++; + + return do_xdp_dump(ifinfo, tb); +} + +static int dump_class_qdisc_nlmsg(void *cookie, void *msg, struct nlattr **tb) +{ + struct bpf_tcinfo_t *tcinfo = cookie; + struct tcmsg *info = msg; + + if (tcinfo->is_qdisc) { + /* skip clsact qdisc */ + if (tb[TCA_KIND] && + strcmp(nla_data(tb[TCA_KIND]), "clsact") == 0) + return 0; + if (info->tcm_handle == 0) + return 0; + } + + if (tcinfo->used_len == tcinfo->array_len) { + tcinfo->handle_array = realloc(tcinfo->handle_array, + (tcinfo->array_len + 16) * sizeof(struct tc_kind_handle)); + if (!tcinfo->handle_array) + return -ENOMEM; + + tcinfo->array_len += 16; + } + tcinfo->handle_array[tcinfo->used_len].handle = info->tcm_handle; + snprintf(tcinfo->handle_array[tcinfo->used_len].kind, + sizeof(tcinfo->handle_array[tcinfo->used_len].kind), + "%s", + tb[TCA_KIND] ? nla_getattr_str(tb[TCA_KIND]) : "unknown"); + tcinfo->used_len++; + + return 0; +} + +static int dump_filter_nlmsg(void *cookie, void *msg, struct nlattr **tb) +{ + const struct bpf_filter_t *filter_info = cookie; + + return do_filter_dump((struct tcmsg *)msg, tb, filter_info->kind, + filter_info->devname, filter_info->ifindex); +} + +static int show_dev_tc_bpf(int sock, unsigned int nl_pid, + struct ip_devname_ifindex *dev) +{ + struct bpf_filter_t filter_info; + struct bpf_tcinfo_t tcinfo; + int i, handle, ret = 0; + + tcinfo.handle_array = NULL; + tcinfo.used_len = 0; + tcinfo.array_len = 0; + + tcinfo.is_qdisc = false; + ret = nl_get_class(sock, nl_pid, dev->ifindex, dump_class_qdisc_nlmsg, + &tcinfo); + if (ret) + goto out; + + tcinfo.is_qdisc = true; + ret = nl_get_qdisc(sock, nl_pid, dev->ifindex, dump_class_qdisc_nlmsg, + &tcinfo); + if (ret) + goto out; + + filter_info.devname = dev->devname; + filter_info.ifindex = dev->ifindex; + for (i = 0; i < tcinfo.used_len; i++) { + filter_info.kind = tcinfo.handle_array[i].kind; + ret = nl_get_filter(sock, nl_pid, dev->ifindex, + tcinfo.handle_array[i].handle, + dump_filter_nlmsg, + &filter_info); + if (ret) + goto out; + } + + /* root, ingress and egress handle */ + handle = TC_H_ROOT; + filter_info.kind = "root"; + ret = nl_get_filter(sock, nl_pid, dev->ifindex, handle, + dump_filter_nlmsg, &filter_info); + if (ret) + goto out; + + handle = TC_H_MAKE(TC_H_CLSACT, TC_H_MIN_INGRESS); + filter_info.kind = "clsact/ingress"; + ret = nl_get_filter(sock, nl_pid, dev->ifindex, handle, + dump_filter_nlmsg, &filter_info); + if (ret) + goto out; + + handle = TC_H_MAKE(TC_H_CLSACT, TC_H_MIN_EGRESS); + filter_info.kind = "clsact/egress"; + ret = nl_get_filter(sock, nl_pid, dev->ifindex, handle, + dump_filter_nlmsg, &filter_info); + if (ret) + goto out; + +out: + free(tcinfo.handle_array); + return 0; +} + +static int do_show(int argc, char **argv) +{ + int i, sock, ret, filter_idx = -1; + struct bpf_netdev_t dev_array; + unsigned int nl_pid; + char err_buf[256]; + + if (argc == 2) { + if (strcmp(argv[0], "dev") != 0) + usage(); + filter_idx = if_nametoindex(argv[1]); + if (filter_idx == 0) { + fprintf(stderr, "invalid dev name %s\n", argv[1]); + return -1; + } + } else if (argc != 0) { + usage(); + } + + sock = bpf_netlink_open(&nl_pid); + if (sock < 0) { + fprintf(stderr, "failed to open netlink sock\n"); + return -1; + } + + dev_array.devices = NULL; + dev_array.used_len = 0; + dev_array.array_len = 0; + dev_array.filter_idx = filter_idx; + + if (json_output) + jsonw_start_array(json_wtr); + NET_START_OBJECT; + NET_START_ARRAY("xdp", "%s:\n"); + ret = nl_get_link(sock, nl_pid, dump_link_nlmsg, &dev_array); + NET_END_ARRAY("\n"); + + if (!ret) { + NET_START_ARRAY("tc", "%s:\n"); + for (i = 0; i < dev_array.used_len; i++) { + ret = show_dev_tc_bpf(sock, nl_pid, + &dev_array.devices[i]); + if (ret) + break; + } + NET_END_ARRAY("\n"); + } + NET_END_OBJECT; + if (json_output) + jsonw_end_array(json_wtr); + + if (ret) { + if (json_output) + jsonw_null(json_wtr); + libbpf_strerror(ret, err_buf, sizeof(err_buf)); + fprintf(stderr, "Error: %s\n", err_buf); + } + free(dev_array.devices); + close(sock); + return ret; +} + +static int do_help(int argc, char **argv) +{ + if (json_output) { + jsonw_null(json_wtr); + return 0; + } + + fprintf(stderr, + "Usage: %s %s { show | list } [dev ]\n" + " %s %s help\n" + "Note: Only xdp and tc attachments are supported now.\n" + " For progs attached to cgroups, use \"bpftool cgroup\"\n" + " to dump program attachments. For program types\n" + " sk_{filter,skb,msg,reuseport} and lwt/seg6, please\n" + " consult iproute2.\n", + bin_name, argv[-2], bin_name, argv[-2]); + + return 0; +} + +static const struct cmd cmds[] = { + { "show", do_show }, + { "list", do_show }, + { "help", do_help }, + { 0 } +}; + +int do_net(int argc, char **argv) +{ + return cmd_select(cmds, argc, argv, do_help); +} diff --git a/tools/bpf/bpftool/netlink_dumper.c b/tools/bpf/bpftool/netlink_dumper.c new file mode 100644 index 0000000000000000000000000000000000000000..6f5e9cc6836c385651daf02a112f18a578384f7a --- /dev/null +++ b/tools/bpf/bpftool/netlink_dumper.c @@ -0,0 +1,174 @@ +// SPDX-License-Identifier: GPL-2.0+ +// Copyright (C) 2018 Facebook + +#include +#include +#include +#include +#include + +#include +#include "main.h" +#include "netlink_dumper.h" + +static void xdp_dump_prog_id(struct nlattr **tb, int attr, + const char *mode, + bool new_json_object) +{ + if (!tb[attr]) + return; + + if (new_json_object) + NET_START_OBJECT + NET_DUMP_STR("mode", " %s", mode); + NET_DUMP_UINT("id", " id %u", nla_getattr_u32(tb[attr])) + if (new_json_object) + NET_END_OBJECT +} + +static int do_xdp_dump_one(struct nlattr *attr, unsigned int ifindex, + const char *name) +{ + struct nlattr *tb[IFLA_XDP_MAX + 1]; + unsigned char mode; + + if (nla_parse_nested(tb, IFLA_XDP_MAX, attr, NULL) < 0) + return -1; + + if (!tb[IFLA_XDP_ATTACHED]) + return 0; + + mode = nla_getattr_u8(tb[IFLA_XDP_ATTACHED]); + if (mode == XDP_ATTACHED_NONE) + return 0; + + NET_START_OBJECT; + if (name) + NET_DUMP_STR("devname", "%s", name); + NET_DUMP_UINT("ifindex", "(%d)", ifindex); + + if (mode == XDP_ATTACHED_MULTI) { + if (json_output) { + jsonw_name(json_wtr, "multi_attachments"); + jsonw_start_array(json_wtr); + } + xdp_dump_prog_id(tb, IFLA_XDP_SKB_PROG_ID, "generic", true); + xdp_dump_prog_id(tb, IFLA_XDP_DRV_PROG_ID, "driver", true); + xdp_dump_prog_id(tb, IFLA_XDP_HW_PROG_ID, "offload", true); + if (json_output) + jsonw_end_array(json_wtr); + } else if (mode == XDP_ATTACHED_DRV) { + xdp_dump_prog_id(tb, IFLA_XDP_PROG_ID, "driver", false); + } else if (mode == XDP_ATTACHED_SKB) { + xdp_dump_prog_id(tb, IFLA_XDP_PROG_ID, "generic", false); + } else if (mode == XDP_ATTACHED_HW) { + xdp_dump_prog_id(tb, IFLA_XDP_PROG_ID, "offload", false); + } + + NET_END_OBJECT_FINAL; + return 0; +} + +int do_xdp_dump(struct ifinfomsg *ifinfo, struct nlattr **tb) +{ + if (!tb[IFLA_XDP]) + return 0; + + return do_xdp_dump_one(tb[IFLA_XDP], ifinfo->ifi_index, + nla_getattr_str(tb[IFLA_IFNAME])); +} + +static int do_bpf_dump_one_act(struct nlattr *attr) +{ + struct nlattr *tb[TCA_ACT_BPF_MAX + 1]; + + if (nla_parse_nested(tb, TCA_ACT_BPF_MAX, attr, NULL) < 0) + return -LIBBPF_ERRNO__NLPARSE; + + if (!tb[TCA_ACT_BPF_PARMS]) + return -LIBBPF_ERRNO__NLPARSE; + + NET_START_OBJECT_NESTED2; + if (tb[TCA_ACT_BPF_NAME]) + NET_DUMP_STR("name", "%s", + nla_getattr_str(tb[TCA_ACT_BPF_NAME])); + if (tb[TCA_ACT_BPF_ID]) + NET_DUMP_UINT("id", " id %u", + nla_getattr_u32(tb[TCA_ACT_BPF_ID])); + NET_END_OBJECT_NESTED; + return 0; +} + +static int do_dump_one_act(struct nlattr *attr) +{ + struct nlattr *tb[TCA_ACT_MAX + 1]; + + if (!attr) + return 0; + + if (nla_parse_nested(tb, TCA_ACT_MAX, attr, NULL) < 0) + return -LIBBPF_ERRNO__NLPARSE; + + if (tb[TCA_ACT_KIND] && strcmp(nla_data(tb[TCA_ACT_KIND]), "bpf") == 0) + return do_bpf_dump_one_act(tb[TCA_ACT_OPTIONS]); + + return 0; +} + +static int do_bpf_act_dump(struct nlattr *attr) +{ + struct nlattr *tb[TCA_ACT_MAX_PRIO + 1]; + int act, ret; + + if (nla_parse_nested(tb, TCA_ACT_MAX_PRIO, attr, NULL) < 0) + return -LIBBPF_ERRNO__NLPARSE; + + NET_START_ARRAY("act", " %s ["); + for (act = 0; act <= TCA_ACT_MAX_PRIO; act++) { + ret = do_dump_one_act(tb[act]); + if (ret) + break; + } + NET_END_ARRAY("] "); + + return ret; +} + +static int do_bpf_filter_dump(struct nlattr *attr) +{ + struct nlattr *tb[TCA_BPF_MAX + 1]; + int ret; + + if (nla_parse_nested(tb, TCA_BPF_MAX, attr, NULL) < 0) + return -LIBBPF_ERRNO__NLPARSE; + + if (tb[TCA_BPF_NAME]) + NET_DUMP_STR("name", " %s", nla_getattr_str(tb[TCA_BPF_NAME])); + if (tb[TCA_BPF_ID]) + NET_DUMP_UINT("id", " id %u", nla_getattr_u32(tb[TCA_BPF_ID])); + if (tb[TCA_BPF_ACT]) { + ret = do_bpf_act_dump(tb[TCA_BPF_ACT]); + if (ret) + return ret; + } + + return 0; +} + +int do_filter_dump(struct tcmsg *info, struct nlattr **tb, const char *kind, + const char *devname, int ifindex) +{ + int ret = 0; + + if (tb[TCA_OPTIONS] && strcmp(nla_data(tb[TCA_KIND]), "bpf") == 0) { + NET_START_OBJECT; + if (devname[0] != '\0') + NET_DUMP_STR("devname", "%s", devname); + NET_DUMP_UINT("ifindex", "(%u)", ifindex); + NET_DUMP_STR("kind", " %s", kind); + ret = do_bpf_filter_dump(tb[TCA_OPTIONS]); + NET_END_OBJECT_FINAL; + } + + return ret; +} diff --git a/tools/bpf/bpftool/netlink_dumper.h b/tools/bpf/bpftool/netlink_dumper.h new file mode 100644 index 0000000000000000000000000000000000000000..e3516b586a34bdb94781743b03750c69886ab6ff --- /dev/null +++ b/tools/bpf/bpftool/netlink_dumper.h @@ -0,0 +1,95 @@ +// SPDX-License-Identifier: GPL-2.0+ +// Copyright (C) 2018 Facebook + +#ifndef _NETLINK_DUMPER_H_ +#define _NETLINK_DUMPER_H_ + +#define NET_START_OBJECT \ +{ \ + if (json_output) \ + jsonw_start_object(json_wtr); \ +} + +#define NET_START_OBJECT_NESTED(name) \ +{ \ + if (json_output) { \ + jsonw_name(json_wtr, name); \ + jsonw_start_object(json_wtr); \ + } else { \ + fprintf(stdout, "%s {", name); \ + } \ +} + +#define NET_START_OBJECT_NESTED2 \ +{ \ + if (json_output) \ + jsonw_start_object(json_wtr); \ + else \ + fprintf(stdout, "{"); \ +} + +#define NET_END_OBJECT_NESTED \ +{ \ + if (json_output) \ + jsonw_end_object(json_wtr); \ + else \ + fprintf(stdout, "}"); \ +} + +#define NET_END_OBJECT \ +{ \ + if (json_output) \ + jsonw_end_object(json_wtr); \ +} + +#define NET_END_OBJECT_FINAL \ +{ \ + if (json_output) \ + jsonw_end_object(json_wtr); \ + else \ + fprintf(stdout, "\n"); \ +} + +#define NET_START_ARRAY(name, fmt_str) \ +{ \ + if (json_output) { \ + jsonw_name(json_wtr, name); \ + jsonw_start_array(json_wtr); \ + } else { \ + fprintf(stdout, fmt_str, name); \ + } \ +} + +#define NET_END_ARRAY(endstr) \ +{ \ + if (json_output) \ + jsonw_end_array(json_wtr); \ + else \ + fprintf(stdout, "%s", endstr); \ +} + +#define NET_DUMP_UINT(name, fmt_str, val) \ +{ \ + if (json_output) \ + jsonw_uint_field(json_wtr, name, val); \ + else \ + fprintf(stdout, fmt_str, val); \ +} + +#define NET_DUMP_STR(name, fmt_str, str) \ +{ \ + if (json_output) \ + jsonw_string_field(json_wtr, name, str);\ + else \ + fprintf(stdout, fmt_str, str); \ +} + +#define NET_DUMP_STR_ONLY(str) \ +{ \ + if (json_output) \ + jsonw_string(json_wtr, str); \ + else \ + fprintf(stdout, "%s ", str); \ +} + +#endif diff --git a/tools/include/uapi/linux/pkt_cls.h b/tools/include/uapi/linux/pkt_cls.h new file mode 100644 index 0000000000000000000000000000000000000000..682cda46aa1bb07380ff6e554c7436a22d23fca8 --- /dev/null +++ b/tools/include/uapi/linux/pkt_cls.h @@ -0,0 +1,612 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef __LINUX_PKT_CLS_H +#define __LINUX_PKT_CLS_H + +#include +#include + +#define TC_COOKIE_MAX_SIZE 16 + +/* Action attributes */ +enum { + TCA_ACT_UNSPEC, + TCA_ACT_KIND, + TCA_ACT_OPTIONS, + TCA_ACT_INDEX, + TCA_ACT_STATS, + TCA_ACT_PAD, + TCA_ACT_COOKIE, + __TCA_ACT_MAX +}; + +#define TCA_ACT_MAX __TCA_ACT_MAX +#define TCA_OLD_COMPAT (TCA_ACT_MAX+1) +#define TCA_ACT_MAX_PRIO 32 +#define TCA_ACT_BIND 1 +#define TCA_ACT_NOBIND 0 +#define TCA_ACT_UNBIND 1 +#define TCA_ACT_NOUNBIND 0 +#define TCA_ACT_REPLACE 1 +#define TCA_ACT_NOREPLACE 0 + +#define TC_ACT_UNSPEC (-1) +#define TC_ACT_OK 0 +#define TC_ACT_RECLASSIFY 1 +#define TC_ACT_SHOT 2 +#define TC_ACT_PIPE 3 +#define TC_ACT_STOLEN 4 +#define TC_ACT_QUEUED 5 +#define TC_ACT_REPEAT 6 +#define TC_ACT_REDIRECT 7 +#define TC_ACT_TRAP 8 /* For hw path, this means "trap to cpu" + * and don't further process the frame + * in hardware. For sw path, this is + * equivalent of TC_ACT_STOLEN - drop + * the skb and act like everything + * is alright. + */ +#define TC_ACT_VALUE_MAX TC_ACT_TRAP + +/* There is a special kind of actions called "extended actions", + * which need a value parameter. These have a local opcode located in + * the highest nibble, starting from 1. The rest of the bits + * are used to carry the value. These two parts together make + * a combined opcode. + */ +#define __TC_ACT_EXT_SHIFT 28 +#define __TC_ACT_EXT(local) ((local) << __TC_ACT_EXT_SHIFT) +#define TC_ACT_EXT_VAL_MASK ((1 << __TC_ACT_EXT_SHIFT) - 1) +#define TC_ACT_EXT_OPCODE(combined) ((combined) & (~TC_ACT_EXT_VAL_MASK)) +#define TC_ACT_EXT_CMP(combined, opcode) (TC_ACT_EXT_OPCODE(combined) == opcode) + +#define TC_ACT_JUMP __TC_ACT_EXT(1) +#define TC_ACT_GOTO_CHAIN __TC_ACT_EXT(2) +#define TC_ACT_EXT_OPCODE_MAX TC_ACT_GOTO_CHAIN + +/* Action type identifiers*/ +enum { + TCA_ID_UNSPEC=0, + TCA_ID_POLICE=1, + /* other actions go here */ + __TCA_ID_MAX=255 +}; + +#define TCA_ID_MAX __TCA_ID_MAX + +struct tc_police { + __u32 index; + int action; +#define TC_POLICE_UNSPEC TC_ACT_UNSPEC +#define TC_POLICE_OK TC_ACT_OK +#define TC_POLICE_RECLASSIFY TC_ACT_RECLASSIFY +#define TC_POLICE_SHOT TC_ACT_SHOT +#define TC_POLICE_PIPE TC_ACT_PIPE + + __u32 limit; + __u32 burst; + __u32 mtu; + struct tc_ratespec rate; + struct tc_ratespec peakrate; + int refcnt; + int bindcnt; + __u32 capab; +}; + +struct tcf_t { + __u64 install; + __u64 lastuse; + __u64 expires; + __u64 firstuse; +}; + +struct tc_cnt { + int refcnt; + int bindcnt; +}; + +#define tc_gen \ + __u32 index; \ + __u32 capab; \ + int action; \ + int refcnt; \ + int bindcnt + +enum { + TCA_POLICE_UNSPEC, + TCA_POLICE_TBF, + TCA_POLICE_RATE, + TCA_POLICE_PEAKRATE, + TCA_POLICE_AVRATE, + TCA_POLICE_RESULT, + TCA_POLICE_TM, + TCA_POLICE_PAD, + __TCA_POLICE_MAX +#define TCA_POLICE_RESULT TCA_POLICE_RESULT +}; + +#define TCA_POLICE_MAX (__TCA_POLICE_MAX - 1) + +/* tca flags definitions */ +#define TCA_CLS_FLAGS_SKIP_HW (1 << 0) /* don't offload filter to HW */ +#define TCA_CLS_FLAGS_SKIP_SW (1 << 1) /* don't use filter in SW */ +#define TCA_CLS_FLAGS_IN_HW (1 << 2) /* filter is offloaded to HW */ +#define TCA_CLS_FLAGS_NOT_IN_HW (1 << 3) /* filter isn't offloaded to HW */ +#define TCA_CLS_FLAGS_VERBOSE (1 << 4) /* verbose logging */ + +/* U32 filters */ + +#define TC_U32_HTID(h) ((h)&0xFFF00000) +#define TC_U32_USERHTID(h) (TC_U32_HTID(h)>>20) +#define TC_U32_HASH(h) (((h)>>12)&0xFF) +#define TC_U32_NODE(h) ((h)&0xFFF) +#define TC_U32_KEY(h) ((h)&0xFFFFF) +#define TC_U32_UNSPEC 0 +#define TC_U32_ROOT (0xFFF00000) + +enum { + TCA_U32_UNSPEC, + TCA_U32_CLASSID, + TCA_U32_HASH, + TCA_U32_LINK, + TCA_U32_DIVISOR, + TCA_U32_SEL, + TCA_U32_POLICE, + TCA_U32_ACT, + TCA_U32_INDEV, + TCA_U32_PCNT, + TCA_U32_MARK, + TCA_U32_FLAGS, + TCA_U32_PAD, + __TCA_U32_MAX +}; + +#define TCA_U32_MAX (__TCA_U32_MAX - 1) + +struct tc_u32_key { + __be32 mask; + __be32 val; + int off; + int offmask; +}; + +struct tc_u32_sel { + unsigned char flags; + unsigned char offshift; + unsigned char nkeys; + + __be16 offmask; + __u16 off; + short offoff; + + short hoff; + __be32 hmask; + struct tc_u32_key keys[0]; +}; + +struct tc_u32_mark { + __u32 val; + __u32 mask; + __u32 success; +}; + +struct tc_u32_pcnt { + __u64 rcnt; + __u64 rhit; + __u64 kcnts[0]; +}; + +/* Flags */ + +#define TC_U32_TERMINAL 1 +#define TC_U32_OFFSET 2 +#define TC_U32_VAROFFSET 4 +#define TC_U32_EAT 8 + +#define TC_U32_MAXDEPTH 8 + + +/* RSVP filter */ + +enum { + TCA_RSVP_UNSPEC, + TCA_RSVP_CLASSID, + TCA_RSVP_DST, + TCA_RSVP_SRC, + TCA_RSVP_PINFO, + TCA_RSVP_POLICE, + TCA_RSVP_ACT, + __TCA_RSVP_MAX +}; + +#define TCA_RSVP_MAX (__TCA_RSVP_MAX - 1 ) + +struct tc_rsvp_gpi { + __u32 key; + __u32 mask; + int offset; +}; + +struct tc_rsvp_pinfo { + struct tc_rsvp_gpi dpi; + struct tc_rsvp_gpi spi; + __u8 protocol; + __u8 tunnelid; + __u8 tunnelhdr; + __u8 pad; +}; + +/* ROUTE filter */ + +enum { + TCA_ROUTE4_UNSPEC, + TCA_ROUTE4_CLASSID, + TCA_ROUTE4_TO, + TCA_ROUTE4_FROM, + TCA_ROUTE4_IIF, + TCA_ROUTE4_POLICE, + TCA_ROUTE4_ACT, + __TCA_ROUTE4_MAX +}; + +#define TCA_ROUTE4_MAX (__TCA_ROUTE4_MAX - 1) + + +/* FW filter */ + +enum { + TCA_FW_UNSPEC, + TCA_FW_CLASSID, + TCA_FW_POLICE, + TCA_FW_INDEV, /* used by CONFIG_NET_CLS_IND */ + TCA_FW_ACT, /* used by CONFIG_NET_CLS_ACT */ + TCA_FW_MASK, + __TCA_FW_MAX +}; + +#define TCA_FW_MAX (__TCA_FW_MAX - 1) + +/* TC index filter */ + +enum { + TCA_TCINDEX_UNSPEC, + TCA_TCINDEX_HASH, + TCA_TCINDEX_MASK, + TCA_TCINDEX_SHIFT, + TCA_TCINDEX_FALL_THROUGH, + TCA_TCINDEX_CLASSID, + TCA_TCINDEX_POLICE, + TCA_TCINDEX_ACT, + __TCA_TCINDEX_MAX +}; + +#define TCA_TCINDEX_MAX (__TCA_TCINDEX_MAX - 1) + +/* Flow filter */ + +enum { + FLOW_KEY_SRC, + FLOW_KEY_DST, + FLOW_KEY_PROTO, + FLOW_KEY_PROTO_SRC, + FLOW_KEY_PROTO_DST, + FLOW_KEY_IIF, + FLOW_KEY_PRIORITY, + FLOW_KEY_MARK, + FLOW_KEY_NFCT, + FLOW_KEY_NFCT_SRC, + FLOW_KEY_NFCT_DST, + FLOW_KEY_NFCT_PROTO_SRC, + FLOW_KEY_NFCT_PROTO_DST, + FLOW_KEY_RTCLASSID, + FLOW_KEY_SKUID, + FLOW_KEY_SKGID, + FLOW_KEY_VLAN_TAG, + FLOW_KEY_RXHASH, + __FLOW_KEY_MAX, +}; + +#define FLOW_KEY_MAX (__FLOW_KEY_MAX - 1) + +enum { + FLOW_MODE_MAP, + FLOW_MODE_HASH, +}; + +enum { + TCA_FLOW_UNSPEC, + TCA_FLOW_KEYS, + TCA_FLOW_MODE, + TCA_FLOW_BASECLASS, + TCA_FLOW_RSHIFT, + TCA_FLOW_ADDEND, + TCA_FLOW_MASK, + TCA_FLOW_XOR, + TCA_FLOW_DIVISOR, + TCA_FLOW_ACT, + TCA_FLOW_POLICE, + TCA_FLOW_EMATCHES, + TCA_FLOW_PERTURB, + __TCA_FLOW_MAX +}; + +#define TCA_FLOW_MAX (__TCA_FLOW_MAX - 1) + +/* Basic filter */ + +enum { + TCA_BASIC_UNSPEC, + TCA_BASIC_CLASSID, + TCA_BASIC_EMATCHES, + TCA_BASIC_ACT, + TCA_BASIC_POLICE, + __TCA_BASIC_MAX +}; + +#define TCA_BASIC_MAX (__TCA_BASIC_MAX - 1) + + +/* Cgroup classifier */ + +enum { + TCA_CGROUP_UNSPEC, + TCA_CGROUP_ACT, + TCA_CGROUP_POLICE, + TCA_CGROUP_EMATCHES, + __TCA_CGROUP_MAX, +}; + +#define TCA_CGROUP_MAX (__TCA_CGROUP_MAX - 1) + +/* BPF classifier */ + +#define TCA_BPF_FLAG_ACT_DIRECT (1 << 0) + +enum { + TCA_BPF_UNSPEC, + TCA_BPF_ACT, + TCA_BPF_POLICE, + TCA_BPF_CLASSID, + TCA_BPF_OPS_LEN, + TCA_BPF_OPS, + TCA_BPF_FD, + TCA_BPF_NAME, + TCA_BPF_FLAGS, + TCA_BPF_FLAGS_GEN, + TCA_BPF_TAG, + TCA_BPF_ID, + __TCA_BPF_MAX, +}; + +#define TCA_BPF_MAX (__TCA_BPF_MAX - 1) + +/* Flower classifier */ + +enum { + TCA_FLOWER_UNSPEC, + TCA_FLOWER_CLASSID, + TCA_FLOWER_INDEV, + TCA_FLOWER_ACT, + TCA_FLOWER_KEY_ETH_DST, /* ETH_ALEN */ + TCA_FLOWER_KEY_ETH_DST_MASK, /* ETH_ALEN */ + TCA_FLOWER_KEY_ETH_SRC, /* ETH_ALEN */ + TCA_FLOWER_KEY_ETH_SRC_MASK, /* ETH_ALEN */ + TCA_FLOWER_KEY_ETH_TYPE, /* be16 */ + TCA_FLOWER_KEY_IP_PROTO, /* u8 */ + TCA_FLOWER_KEY_IPV4_SRC, /* be32 */ + TCA_FLOWER_KEY_IPV4_SRC_MASK, /* be32 */ + TCA_FLOWER_KEY_IPV4_DST, /* be32 */ + TCA_FLOWER_KEY_IPV4_DST_MASK, /* be32 */ + TCA_FLOWER_KEY_IPV6_SRC, /* struct in6_addr */ + TCA_FLOWER_KEY_IPV6_SRC_MASK, /* struct in6_addr */ + TCA_FLOWER_KEY_IPV6_DST, /* struct in6_addr */ + TCA_FLOWER_KEY_IPV6_DST_MASK, /* struct in6_addr */ + TCA_FLOWER_KEY_TCP_SRC, /* be16 */ + TCA_FLOWER_KEY_TCP_DST, /* be16 */ + TCA_FLOWER_KEY_UDP_SRC, /* be16 */ + TCA_FLOWER_KEY_UDP_DST, /* be16 */ + + TCA_FLOWER_FLAGS, + TCA_FLOWER_KEY_VLAN_ID, /* be16 */ + TCA_FLOWER_KEY_VLAN_PRIO, /* u8 */ + TCA_FLOWER_KEY_VLAN_ETH_TYPE, /* be16 */ + + TCA_FLOWER_KEY_ENC_KEY_ID, /* be32 */ + TCA_FLOWER_KEY_ENC_IPV4_SRC, /* be32 */ + TCA_FLOWER_KEY_ENC_IPV4_SRC_MASK,/* be32 */ + TCA_FLOWER_KEY_ENC_IPV4_DST, /* be32 */ + TCA_FLOWER_KEY_ENC_IPV4_DST_MASK,/* be32 */ + TCA_FLOWER_KEY_ENC_IPV6_SRC, /* struct in6_addr */ + TCA_FLOWER_KEY_ENC_IPV6_SRC_MASK,/* struct in6_addr */ + TCA_FLOWER_KEY_ENC_IPV6_DST, /* struct in6_addr */ + TCA_FLOWER_KEY_ENC_IPV6_DST_MASK,/* struct in6_addr */ + + TCA_FLOWER_KEY_TCP_SRC_MASK, /* be16 */ + TCA_FLOWER_KEY_TCP_DST_MASK, /* be16 */ + TCA_FLOWER_KEY_UDP_SRC_MASK, /* be16 */ + TCA_FLOWER_KEY_UDP_DST_MASK, /* be16 */ + TCA_FLOWER_KEY_SCTP_SRC_MASK, /* be16 */ + TCA_FLOWER_KEY_SCTP_DST_MASK, /* be16 */ + + TCA_FLOWER_KEY_SCTP_SRC, /* be16 */ + TCA_FLOWER_KEY_SCTP_DST, /* be16 */ + + TCA_FLOWER_KEY_ENC_UDP_SRC_PORT, /* be16 */ + TCA_FLOWER_KEY_ENC_UDP_SRC_PORT_MASK, /* be16 */ + TCA_FLOWER_KEY_ENC_UDP_DST_PORT, /* be16 */ + TCA_FLOWER_KEY_ENC_UDP_DST_PORT_MASK, /* be16 */ + + TCA_FLOWER_KEY_FLAGS, /* be32 */ + TCA_FLOWER_KEY_FLAGS_MASK, /* be32 */ + + TCA_FLOWER_KEY_ICMPV4_CODE, /* u8 */ + TCA_FLOWER_KEY_ICMPV4_CODE_MASK,/* u8 */ + TCA_FLOWER_KEY_ICMPV4_TYPE, /* u8 */ + TCA_FLOWER_KEY_ICMPV4_TYPE_MASK,/* u8 */ + TCA_FLOWER_KEY_ICMPV6_CODE, /* u8 */ + TCA_FLOWER_KEY_ICMPV6_CODE_MASK,/* u8 */ + TCA_FLOWER_KEY_ICMPV6_TYPE, /* u8 */ + TCA_FLOWER_KEY_ICMPV6_TYPE_MASK,/* u8 */ + + TCA_FLOWER_KEY_ARP_SIP, /* be32 */ + TCA_FLOWER_KEY_ARP_SIP_MASK, /* be32 */ + TCA_FLOWER_KEY_ARP_TIP, /* be32 */ + TCA_FLOWER_KEY_ARP_TIP_MASK, /* be32 */ + TCA_FLOWER_KEY_ARP_OP, /* u8 */ + TCA_FLOWER_KEY_ARP_OP_MASK, /* u8 */ + TCA_FLOWER_KEY_ARP_SHA, /* ETH_ALEN */ + TCA_FLOWER_KEY_ARP_SHA_MASK, /* ETH_ALEN */ + TCA_FLOWER_KEY_ARP_THA, /* ETH_ALEN */ + TCA_FLOWER_KEY_ARP_THA_MASK, /* ETH_ALEN */ + + TCA_FLOWER_KEY_MPLS_TTL, /* u8 - 8 bits */ + TCA_FLOWER_KEY_MPLS_BOS, /* u8 - 1 bit */ + TCA_FLOWER_KEY_MPLS_TC, /* u8 - 3 bits */ + TCA_FLOWER_KEY_MPLS_LABEL, /* be32 - 20 bits */ + + TCA_FLOWER_KEY_TCP_FLAGS, /* be16 */ + TCA_FLOWER_KEY_TCP_FLAGS_MASK, /* be16 */ + + TCA_FLOWER_KEY_IP_TOS, /* u8 */ + TCA_FLOWER_KEY_IP_TOS_MASK, /* u8 */ + TCA_FLOWER_KEY_IP_TTL, /* u8 */ + TCA_FLOWER_KEY_IP_TTL_MASK, /* u8 */ + + TCA_FLOWER_KEY_CVLAN_ID, /* be16 */ + TCA_FLOWER_KEY_CVLAN_PRIO, /* u8 */ + TCA_FLOWER_KEY_CVLAN_ETH_TYPE, /* be16 */ + + TCA_FLOWER_KEY_ENC_IP_TOS, /* u8 */ + TCA_FLOWER_KEY_ENC_IP_TOS_MASK, /* u8 */ + TCA_FLOWER_KEY_ENC_IP_TTL, /* u8 */ + TCA_FLOWER_KEY_ENC_IP_TTL_MASK, /* u8 */ + + TCA_FLOWER_KEY_ENC_OPTS, + TCA_FLOWER_KEY_ENC_OPTS_MASK, + + TCA_FLOWER_IN_HW_COUNT, + + __TCA_FLOWER_MAX, +}; + +#define TCA_FLOWER_MAX (__TCA_FLOWER_MAX - 1) + +enum { + TCA_FLOWER_KEY_ENC_OPTS_UNSPEC, + TCA_FLOWER_KEY_ENC_OPTS_GENEVE, /* Nested + * TCA_FLOWER_KEY_ENC_OPT_GENEVE_ + * attributes + */ + __TCA_FLOWER_KEY_ENC_OPTS_MAX, +}; + +#define TCA_FLOWER_KEY_ENC_OPTS_MAX (__TCA_FLOWER_KEY_ENC_OPTS_MAX - 1) + +enum { + TCA_FLOWER_KEY_ENC_OPT_GENEVE_UNSPEC, + TCA_FLOWER_KEY_ENC_OPT_GENEVE_CLASS, /* u16 */ + TCA_FLOWER_KEY_ENC_OPT_GENEVE_TYPE, /* u8 */ + TCA_FLOWER_KEY_ENC_OPT_GENEVE_DATA, /* 4 to 128 bytes */ + + __TCA_FLOWER_KEY_ENC_OPT_GENEVE_MAX, +}; + +#define TCA_FLOWER_KEY_ENC_OPT_GENEVE_MAX \ + (__TCA_FLOWER_KEY_ENC_OPT_GENEVE_MAX - 1) + +enum { + TCA_FLOWER_KEY_FLAGS_IS_FRAGMENT = (1 << 0), + TCA_FLOWER_KEY_FLAGS_FRAG_IS_FIRST = (1 << 1), +}; + +/* Match-all classifier */ + +enum { + TCA_MATCHALL_UNSPEC, + TCA_MATCHALL_CLASSID, + TCA_MATCHALL_ACT, + TCA_MATCHALL_FLAGS, + __TCA_MATCHALL_MAX, +}; + +#define TCA_MATCHALL_MAX (__TCA_MATCHALL_MAX - 1) + +/* Extended Matches */ + +struct tcf_ematch_tree_hdr { + __u16 nmatches; + __u16 progid; +}; + +enum { + TCA_EMATCH_TREE_UNSPEC, + TCA_EMATCH_TREE_HDR, + TCA_EMATCH_TREE_LIST, + __TCA_EMATCH_TREE_MAX +}; +#define TCA_EMATCH_TREE_MAX (__TCA_EMATCH_TREE_MAX - 1) + +struct tcf_ematch_hdr { + __u16 matchid; + __u16 kind; + __u16 flags; + __u16 pad; /* currently unused */ +}; + +/* 0 1 + * 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 + * +-----------------------+-+-+---+ + * | Unused |S|I| R | + * +-----------------------+-+-+---+ + * + * R(2) ::= relation to next ematch + * where: 0 0 END (last ematch) + * 0 1 AND + * 1 0 OR + * 1 1 Unused (invalid) + * I(1) ::= invert result + * S(1) ::= simple payload + */ +#define TCF_EM_REL_END 0 +#define TCF_EM_REL_AND (1<<0) +#define TCF_EM_REL_OR (1<<1) +#define TCF_EM_INVERT (1<<2) +#define TCF_EM_SIMPLE (1<<3) + +#define TCF_EM_REL_MASK 3 +#define TCF_EM_REL_VALID(v) (((v) & TCF_EM_REL_MASK) != TCF_EM_REL_MASK) + +enum { + TCF_LAYER_LINK, + TCF_LAYER_NETWORK, + TCF_LAYER_TRANSPORT, + __TCF_LAYER_MAX +}; +#define TCF_LAYER_MAX (__TCF_LAYER_MAX - 1) + +/* Ematch type assignments + * 1..32767 Reserved for ematches inside kernel tree + * 32768..65535 Free to use, not reliable + */ +#define TCF_EM_CONTAINER 0 +#define TCF_EM_CMP 1 +#define TCF_EM_NBYTE 2 +#define TCF_EM_U32 3 +#define TCF_EM_META 4 +#define TCF_EM_TEXT 5 +#define TCF_EM_VLAN 6 +#define TCF_EM_CANID 7 +#define TCF_EM_IPSET 8 +#define TCF_EM_IPT 9 +#define TCF_EM_MAX 9 + +enum { + TCF_EM_PROG_TC +}; + +enum { + TCF_EM_OPND_EQ, + TCF_EM_OPND_GT, + TCF_EM_OPND_LT +}; + +#endif diff --git a/tools/include/uapi/linux/pkt_sched.h b/tools/include/uapi/linux/pkt_sched.h new file mode 100644 index 0000000000000000000000000000000000000000..25060205bf3f08ad1bb8aedf6c55fabab345e2d4 --- /dev/null +++ b/tools/include/uapi/linux/pkt_sched.h @@ -0,0 +1,1163 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +#ifndef __LINUX_PKT_SCHED_H +#define __LINUX_PKT_SCHED_H + +#include + +/* Logical priority bands not depending on specific packet scheduler. + Every scheduler will map them to real traffic classes, if it has + no more precise mechanism to classify packets. + + These numbers have no special meaning, though their coincidence + with obsolete IPv6 values is not occasional :-). New IPv6 drafts + preferred full anarchy inspired by diffserv group. + + Note: TC_PRIO_BESTEFFORT does not mean that it is the most unhappy + class, actually, as rule it will be handled with more care than + filler or even bulk. + */ + +#define TC_PRIO_BESTEFFORT 0 +#define TC_PRIO_FILLER 1 +#define TC_PRIO_BULK 2 +#define TC_PRIO_INTERACTIVE_BULK 4 +#define TC_PRIO_INTERACTIVE 6 +#define TC_PRIO_CONTROL 7 + +#define TC_PRIO_MAX 15 + +/* Generic queue statistics, available for all the elements. + Particular schedulers may have also their private records. + */ + +struct tc_stats { + __u64 bytes; /* Number of enqueued bytes */ + __u32 packets; /* Number of enqueued packets */ + __u32 drops; /* Packets dropped because of lack of resources */ + __u32 overlimits; /* Number of throttle events when this + * flow goes out of allocated bandwidth */ + __u32 bps; /* Current flow byte rate */ + __u32 pps; /* Current flow packet rate */ + __u32 qlen; + __u32 backlog; +}; + +struct tc_estimator { + signed char interval; + unsigned char ewma_log; +}; + +/* "Handles" + --------- + + All the traffic control objects have 32bit identifiers, or "handles". + + They can be considered as opaque numbers from user API viewpoint, + but actually they always consist of two fields: major and + minor numbers, which are interpreted by kernel specially, + that may be used by applications, though not recommended. + + F.e. qdisc handles always have minor number equal to zero, + classes (or flows) have major equal to parent qdisc major, and + minor uniquely identifying class inside qdisc. + + Macros to manipulate handles: + */ + +#define TC_H_MAJ_MASK (0xFFFF0000U) +#define TC_H_MIN_MASK (0x0000FFFFU) +#define TC_H_MAJ(h) ((h)&TC_H_MAJ_MASK) +#define TC_H_MIN(h) ((h)&TC_H_MIN_MASK) +#define TC_H_MAKE(maj,min) (((maj)&TC_H_MAJ_MASK)|((min)&TC_H_MIN_MASK)) + +#define TC_H_UNSPEC (0U) +#define TC_H_ROOT (0xFFFFFFFFU) +#define TC_H_INGRESS (0xFFFFFFF1U) +#define TC_H_CLSACT TC_H_INGRESS + +#define TC_H_MIN_PRIORITY 0xFFE0U +#define TC_H_MIN_INGRESS 0xFFF2U +#define TC_H_MIN_EGRESS 0xFFF3U + +/* Need to corrospond to iproute2 tc/tc_core.h "enum link_layer" */ +enum tc_link_layer { + TC_LINKLAYER_UNAWARE, /* Indicate unaware old iproute2 util */ + TC_LINKLAYER_ETHERNET, + TC_LINKLAYER_ATM, +}; +#define TC_LINKLAYER_MASK 0x0F /* limit use to lower 4 bits */ + +struct tc_ratespec { + unsigned char cell_log; + __u8 linklayer; /* lower 4 bits */ + unsigned short overhead; + short cell_align; + unsigned short mpu; + __u32 rate; +}; + +#define TC_RTAB_SIZE 1024 + +struct tc_sizespec { + unsigned char cell_log; + unsigned char size_log; + short cell_align; + int overhead; + unsigned int linklayer; + unsigned int mpu; + unsigned int mtu; + unsigned int tsize; +}; + +enum { + TCA_STAB_UNSPEC, + TCA_STAB_BASE, + TCA_STAB_DATA, + __TCA_STAB_MAX +}; + +#define TCA_STAB_MAX (__TCA_STAB_MAX - 1) + +/* FIFO section */ + +struct tc_fifo_qopt { + __u32 limit; /* Queue length: bytes for bfifo, packets for pfifo */ +}; + +/* SKBPRIO section */ + +/* + * Priorities go from zero to (SKBPRIO_MAX_PRIORITY - 1). + * SKBPRIO_MAX_PRIORITY should be at least 64 in order for skbprio to be able + * to map one to one the DS field of IPV4 and IPV6 headers. + * Memory allocation grows linearly with SKBPRIO_MAX_PRIORITY. + */ + +#define SKBPRIO_MAX_PRIORITY 64 + +struct tc_skbprio_qopt { + __u32 limit; /* Queue length in packets. */ +}; + +/* PRIO section */ + +#define TCQ_PRIO_BANDS 16 +#define TCQ_MIN_PRIO_BANDS 2 + +struct tc_prio_qopt { + int bands; /* Number of bands */ + __u8 priomap[TC_PRIO_MAX+1]; /* Map: logical priority -> PRIO band */ +}; + +/* MULTIQ section */ + +struct tc_multiq_qopt { + __u16 bands; /* Number of bands */ + __u16 max_bands; /* Maximum number of queues */ +}; + +/* PLUG section */ + +#define TCQ_PLUG_BUFFER 0 +#define TCQ_PLUG_RELEASE_ONE 1 +#define TCQ_PLUG_RELEASE_INDEFINITE 2 +#define TCQ_PLUG_LIMIT 3 + +struct tc_plug_qopt { + /* TCQ_PLUG_BUFFER: Inset a plug into the queue and + * buffer any incoming packets + * TCQ_PLUG_RELEASE_ONE: Dequeue packets from queue head + * to beginning of the next plug. + * TCQ_PLUG_RELEASE_INDEFINITE: Dequeue all packets from queue. + * Stop buffering packets until the next TCQ_PLUG_BUFFER + * command is received (just act as a pass-thru queue). + * TCQ_PLUG_LIMIT: Increase/decrease queue size + */ + int action; + __u32 limit; +}; + +/* TBF section */ + +struct tc_tbf_qopt { + struct tc_ratespec rate; + struct tc_ratespec peakrate; + __u32 limit; + __u32 buffer; + __u32 mtu; +}; + +enum { + TCA_TBF_UNSPEC, + TCA_TBF_PARMS, + TCA_TBF_RTAB, + TCA_TBF_PTAB, + TCA_TBF_RATE64, + TCA_TBF_PRATE64, + TCA_TBF_BURST, + TCA_TBF_PBURST, + TCA_TBF_PAD, + __TCA_TBF_MAX, +}; + +#define TCA_TBF_MAX (__TCA_TBF_MAX - 1) + + +/* TEQL section */ + +/* TEQL does not require any parameters */ + +/* SFQ section */ + +struct tc_sfq_qopt { + unsigned quantum; /* Bytes per round allocated to flow */ + int perturb_period; /* Period of hash perturbation */ + __u32 limit; /* Maximal packets in queue */ + unsigned divisor; /* Hash divisor */ + unsigned flows; /* Maximal number of flows */ +}; + +struct tc_sfqred_stats { + __u32 prob_drop; /* Early drops, below max threshold */ + __u32 forced_drop; /* Early drops, after max threshold */ + __u32 prob_mark; /* Marked packets, below max threshold */ + __u32 forced_mark; /* Marked packets, after max threshold */ + __u32 prob_mark_head; /* Marked packets, below max threshold */ + __u32 forced_mark_head;/* Marked packets, after max threshold */ +}; + +struct tc_sfq_qopt_v1 { + struct tc_sfq_qopt v0; + unsigned int depth; /* max number of packets per flow */ + unsigned int headdrop; +/* SFQRED parameters */ + __u32 limit; /* HARD maximal flow queue length (bytes) */ + __u32 qth_min; /* Min average length threshold (bytes) */ + __u32 qth_max; /* Max average length threshold (bytes) */ + unsigned char Wlog; /* log(W) */ + unsigned char Plog; /* log(P_max/(qth_max-qth_min)) */ + unsigned char Scell_log; /* cell size for idle damping */ + unsigned char flags; + __u32 max_P; /* probability, high resolution */ +/* SFQRED stats */ + struct tc_sfqred_stats stats; +}; + + +struct tc_sfq_xstats { + __s32 allot; +}; + +/* RED section */ + +enum { + TCA_RED_UNSPEC, + TCA_RED_PARMS, + TCA_RED_STAB, + TCA_RED_MAX_P, + __TCA_RED_MAX, +}; + +#define TCA_RED_MAX (__TCA_RED_MAX - 1) + +struct tc_red_qopt { + __u32 limit; /* HARD maximal queue length (bytes) */ + __u32 qth_min; /* Min average length threshold (bytes) */ + __u32 qth_max; /* Max average length threshold (bytes) */ + unsigned char Wlog; /* log(W) */ + unsigned char Plog; /* log(P_max/(qth_max-qth_min)) */ + unsigned char Scell_log; /* cell size for idle damping */ + unsigned char flags; +#define TC_RED_ECN 1 +#define TC_RED_HARDDROP 2 +#define TC_RED_ADAPTATIVE 4 +}; + +struct tc_red_xstats { + __u32 early; /* Early drops */ + __u32 pdrop; /* Drops due to queue limits */ + __u32 other; /* Drops due to drop() calls */ + __u32 marked; /* Marked packets */ +}; + +/* GRED section */ + +#define MAX_DPs 16 + +enum { + TCA_GRED_UNSPEC, + TCA_GRED_PARMS, + TCA_GRED_STAB, + TCA_GRED_DPS, + TCA_GRED_MAX_P, + TCA_GRED_LIMIT, + TCA_GRED_VQ_LIST, /* nested TCA_GRED_VQ_ENTRY */ + __TCA_GRED_MAX, +}; + +#define TCA_GRED_MAX (__TCA_GRED_MAX - 1) + +enum { + TCA_GRED_VQ_ENTRY_UNSPEC, + TCA_GRED_VQ_ENTRY, /* nested TCA_GRED_VQ_* */ + __TCA_GRED_VQ_ENTRY_MAX, +}; +#define TCA_GRED_VQ_ENTRY_MAX (__TCA_GRED_VQ_ENTRY_MAX - 1) + +enum { + TCA_GRED_VQ_UNSPEC, + TCA_GRED_VQ_PAD, + TCA_GRED_VQ_DP, /* u32 */ + TCA_GRED_VQ_STAT_BYTES, /* u64 */ + TCA_GRED_VQ_STAT_PACKETS, /* u32 */ + TCA_GRED_VQ_STAT_BACKLOG, /* u32 */ + TCA_GRED_VQ_STAT_PROB_DROP, /* u32 */ + TCA_GRED_VQ_STAT_PROB_MARK, /* u32 */ + TCA_GRED_VQ_STAT_FORCED_DROP, /* u32 */ + TCA_GRED_VQ_STAT_FORCED_MARK, /* u32 */ + TCA_GRED_VQ_STAT_PDROP, /* u32 */ + TCA_GRED_VQ_STAT_OTHER, /* u32 */ + TCA_GRED_VQ_FLAGS, /* u32 */ + __TCA_GRED_VQ_MAX +}; + +#define TCA_GRED_VQ_MAX (__TCA_GRED_VQ_MAX - 1) + +struct tc_gred_qopt { + __u32 limit; /* HARD maximal queue length (bytes) */ + __u32 qth_min; /* Min average length threshold (bytes) */ + __u32 qth_max; /* Max average length threshold (bytes) */ + __u32 DP; /* up to 2^32 DPs */ + __u32 backlog; + __u32 qave; + __u32 forced; + __u32 early; + __u32 other; + __u32 pdrop; + __u8 Wlog; /* log(W) */ + __u8 Plog; /* log(P_max/(qth_max-qth_min)) */ + __u8 Scell_log; /* cell size for idle damping */ + __u8 prio; /* prio of this VQ */ + __u32 packets; + __u32 bytesin; +}; + +/* gred setup */ +struct tc_gred_sopt { + __u32 DPs; + __u32 def_DP; + __u8 grio; + __u8 flags; + __u16 pad1; +}; + +/* CHOKe section */ + +enum { + TCA_CHOKE_UNSPEC, + TCA_CHOKE_PARMS, + TCA_CHOKE_STAB, + TCA_CHOKE_MAX_P, + __TCA_CHOKE_MAX, +}; + +#define TCA_CHOKE_MAX (__TCA_CHOKE_MAX - 1) + +struct tc_choke_qopt { + __u32 limit; /* Hard queue length (packets) */ + __u32 qth_min; /* Min average threshold (packets) */ + __u32 qth_max; /* Max average threshold (packets) */ + unsigned char Wlog; /* log(W) */ + unsigned char Plog; /* log(P_max/(qth_max-qth_min)) */ + unsigned char Scell_log; /* cell size for idle damping */ + unsigned char flags; /* see RED flags */ +}; + +struct tc_choke_xstats { + __u32 early; /* Early drops */ + __u32 pdrop; /* Drops due to queue limits */ + __u32 other; /* Drops due to drop() calls */ + __u32 marked; /* Marked packets */ + __u32 matched; /* Drops due to flow match */ +}; + +/* HTB section */ +#define TC_HTB_NUMPRIO 8 +#define TC_HTB_MAXDEPTH 8 +#define TC_HTB_PROTOVER 3 /* the same as HTB and TC's major */ + +struct tc_htb_opt { + struct tc_ratespec rate; + struct tc_ratespec ceil; + __u32 buffer; + __u32 cbuffer; + __u32 quantum; + __u32 level; /* out only */ + __u32 prio; +}; +struct tc_htb_glob { + __u32 version; /* to match HTB/TC */ + __u32 rate2quantum; /* bps->quantum divisor */ + __u32 defcls; /* default class number */ + __u32 debug; /* debug flags */ + + /* stats */ + __u32 direct_pkts; /* count of non shaped packets */ +}; +enum { + TCA_HTB_UNSPEC, + TCA_HTB_PARMS, + TCA_HTB_INIT, + TCA_HTB_CTAB, + TCA_HTB_RTAB, + TCA_HTB_DIRECT_QLEN, + TCA_HTB_RATE64, + TCA_HTB_CEIL64, + TCA_HTB_PAD, + __TCA_HTB_MAX, +}; + +#define TCA_HTB_MAX (__TCA_HTB_MAX - 1) + +struct tc_htb_xstats { + __u32 lends; + __u32 borrows; + __u32 giants; /* unused since 'Make HTB scheduler work with TSO.' */ + __s32 tokens; + __s32 ctokens; +}; + +/* HFSC section */ + +struct tc_hfsc_qopt { + __u16 defcls; /* default class */ +}; + +struct tc_service_curve { + __u32 m1; /* slope of the first segment in bps */ + __u32 d; /* x-projection of the first segment in us */ + __u32 m2; /* slope of the second segment in bps */ +}; + +struct tc_hfsc_stats { + __u64 work; /* total work done */ + __u64 rtwork; /* work done by real-time criteria */ + __u32 period; /* current period */ + __u32 level; /* class level in hierarchy */ +}; + +enum { + TCA_HFSC_UNSPEC, + TCA_HFSC_RSC, + TCA_HFSC_FSC, + TCA_HFSC_USC, + __TCA_HFSC_MAX, +}; + +#define TCA_HFSC_MAX (__TCA_HFSC_MAX - 1) + + +/* CBQ section */ + +#define TC_CBQ_MAXPRIO 8 +#define TC_CBQ_MAXLEVEL 8 +#define TC_CBQ_DEF_EWMA 5 + +struct tc_cbq_lssopt { + unsigned char change; + unsigned char flags; +#define TCF_CBQ_LSS_BOUNDED 1 +#define TCF_CBQ_LSS_ISOLATED 2 + unsigned char ewma_log; + unsigned char level; +#define TCF_CBQ_LSS_FLAGS 1 +#define TCF_CBQ_LSS_EWMA 2 +#define TCF_CBQ_LSS_MAXIDLE 4 +#define TCF_CBQ_LSS_MINIDLE 8 +#define TCF_CBQ_LSS_OFFTIME 0x10 +#define TCF_CBQ_LSS_AVPKT 0x20 + __u32 maxidle; + __u32 minidle; + __u32 offtime; + __u32 avpkt; +}; + +struct tc_cbq_wrropt { + unsigned char flags; + unsigned char priority; + unsigned char cpriority; + unsigned char __reserved; + __u32 allot; + __u32 weight; +}; + +struct tc_cbq_ovl { + unsigned char strategy; +#define TC_CBQ_OVL_CLASSIC 0 +#define TC_CBQ_OVL_DELAY 1 +#define TC_CBQ_OVL_LOWPRIO 2 +#define TC_CBQ_OVL_DROP 3 +#define TC_CBQ_OVL_RCLASSIC 4 + unsigned char priority2; + __u16 pad; + __u32 penalty; +}; + +struct tc_cbq_police { + unsigned char police; + unsigned char __res1; + unsigned short __res2; +}; + +struct tc_cbq_fopt { + __u32 split; + __u32 defmap; + __u32 defchange; +}; + +struct tc_cbq_xstats { + __u32 borrows; + __u32 overactions; + __s32 avgidle; + __s32 undertime; +}; + +enum { + TCA_CBQ_UNSPEC, + TCA_CBQ_LSSOPT, + TCA_CBQ_WRROPT, + TCA_CBQ_FOPT, + TCA_CBQ_OVL_STRATEGY, + TCA_CBQ_RATE, + TCA_CBQ_RTAB, + TCA_CBQ_POLICE, + __TCA_CBQ_MAX, +}; + +#define TCA_CBQ_MAX (__TCA_CBQ_MAX - 1) + +/* dsmark section */ + +enum { + TCA_DSMARK_UNSPEC, + TCA_DSMARK_INDICES, + TCA_DSMARK_DEFAULT_INDEX, + TCA_DSMARK_SET_TC_INDEX, + TCA_DSMARK_MASK, + TCA_DSMARK_VALUE, + __TCA_DSMARK_MAX, +}; + +#define TCA_DSMARK_MAX (__TCA_DSMARK_MAX - 1) + +/* ATM section */ + +enum { + TCA_ATM_UNSPEC, + TCA_ATM_FD, /* file/socket descriptor */ + TCA_ATM_PTR, /* pointer to descriptor - later */ + TCA_ATM_HDR, /* LL header */ + TCA_ATM_EXCESS, /* excess traffic class (0 for CLP) */ + TCA_ATM_ADDR, /* PVC address (for output only) */ + TCA_ATM_STATE, /* VC state (ATM_VS_*; for output only) */ + __TCA_ATM_MAX, +}; + +#define TCA_ATM_MAX (__TCA_ATM_MAX - 1) + +/* Network emulator */ + +enum { + TCA_NETEM_UNSPEC, + TCA_NETEM_CORR, + TCA_NETEM_DELAY_DIST, + TCA_NETEM_REORDER, + TCA_NETEM_CORRUPT, + TCA_NETEM_LOSS, + TCA_NETEM_RATE, + TCA_NETEM_ECN, + TCA_NETEM_RATE64, + TCA_NETEM_PAD, + TCA_NETEM_LATENCY64, + TCA_NETEM_JITTER64, + TCA_NETEM_SLOT, + TCA_NETEM_SLOT_DIST, + __TCA_NETEM_MAX, +}; + +#define TCA_NETEM_MAX (__TCA_NETEM_MAX - 1) + +struct tc_netem_qopt { + __u32 latency; /* added delay (us) */ + __u32 limit; /* fifo limit (packets) */ + __u32 loss; /* random packet loss (0=none ~0=100%) */ + __u32 gap; /* re-ordering gap (0 for none) */ + __u32 duplicate; /* random packet dup (0=none ~0=100%) */ + __u32 jitter; /* random jitter in latency (us) */ +}; + +struct tc_netem_corr { + __u32 delay_corr; /* delay correlation */ + __u32 loss_corr; /* packet loss correlation */ + __u32 dup_corr; /* duplicate correlation */ +}; + +struct tc_netem_reorder { + __u32 probability; + __u32 correlation; +}; + +struct tc_netem_corrupt { + __u32 probability; + __u32 correlation; +}; + +struct tc_netem_rate { + __u32 rate; /* byte/s */ + __s32 packet_overhead; + __u32 cell_size; + __s32 cell_overhead; +}; + +struct tc_netem_slot { + __s64 min_delay; /* nsec */ + __s64 max_delay; + __s32 max_packets; + __s32 max_bytes; + __s64 dist_delay; /* nsec */ + __s64 dist_jitter; /* nsec */ +}; + +enum { + NETEM_LOSS_UNSPEC, + NETEM_LOSS_GI, /* General Intuitive - 4 state model */ + NETEM_LOSS_GE, /* Gilbert Elliot models */ + __NETEM_LOSS_MAX +}; +#define NETEM_LOSS_MAX (__NETEM_LOSS_MAX - 1) + +/* State transition probabilities for 4 state model */ +struct tc_netem_gimodel { + __u32 p13; + __u32 p31; + __u32 p32; + __u32 p14; + __u32 p23; +}; + +/* Gilbert-Elliot models */ +struct tc_netem_gemodel { + __u32 p; + __u32 r; + __u32 h; + __u32 k1; +}; + +#define NETEM_DIST_SCALE 8192 +#define NETEM_DIST_MAX 16384 + +/* DRR */ + +enum { + TCA_DRR_UNSPEC, + TCA_DRR_QUANTUM, + __TCA_DRR_MAX +}; + +#define TCA_DRR_MAX (__TCA_DRR_MAX - 1) + +struct tc_drr_stats { + __u32 deficit; +}; + +/* MQPRIO */ +#define TC_QOPT_BITMASK 15 +#define TC_QOPT_MAX_QUEUE 16 + +enum { + TC_MQPRIO_HW_OFFLOAD_NONE, /* no offload requested */ + TC_MQPRIO_HW_OFFLOAD_TCS, /* offload TCs, no queue counts */ + __TC_MQPRIO_HW_OFFLOAD_MAX +}; + +#define TC_MQPRIO_HW_OFFLOAD_MAX (__TC_MQPRIO_HW_OFFLOAD_MAX - 1) + +enum { + TC_MQPRIO_MODE_DCB, + TC_MQPRIO_MODE_CHANNEL, + __TC_MQPRIO_MODE_MAX +}; + +#define __TC_MQPRIO_MODE_MAX (__TC_MQPRIO_MODE_MAX - 1) + +enum { + TC_MQPRIO_SHAPER_DCB, + TC_MQPRIO_SHAPER_BW_RATE, /* Add new shapers below */ + __TC_MQPRIO_SHAPER_MAX +}; + +#define __TC_MQPRIO_SHAPER_MAX (__TC_MQPRIO_SHAPER_MAX - 1) + +struct tc_mqprio_qopt { + __u8 num_tc; + __u8 prio_tc_map[TC_QOPT_BITMASK + 1]; + __u8 hw; + __u16 count[TC_QOPT_MAX_QUEUE]; + __u16 offset[TC_QOPT_MAX_QUEUE]; +}; + +#define TC_MQPRIO_F_MODE 0x1 +#define TC_MQPRIO_F_SHAPER 0x2 +#define TC_MQPRIO_F_MIN_RATE 0x4 +#define TC_MQPRIO_F_MAX_RATE 0x8 + +enum { + TCA_MQPRIO_UNSPEC, + TCA_MQPRIO_MODE, + TCA_MQPRIO_SHAPER, + TCA_MQPRIO_MIN_RATE64, + TCA_MQPRIO_MAX_RATE64, + __TCA_MQPRIO_MAX, +}; + +#define TCA_MQPRIO_MAX (__TCA_MQPRIO_MAX - 1) + +/* SFB */ + +enum { + TCA_SFB_UNSPEC, + TCA_SFB_PARMS, + __TCA_SFB_MAX, +}; + +#define TCA_SFB_MAX (__TCA_SFB_MAX - 1) + +/* + * Note: increment, decrement are Q0.16 fixed-point values. + */ +struct tc_sfb_qopt { + __u32 rehash_interval; /* delay between hash move, in ms */ + __u32 warmup_time; /* double buffering warmup time in ms (warmup_time < rehash_interval) */ + __u32 max; /* max len of qlen_min */ + __u32 bin_size; /* maximum queue length per bin */ + __u32 increment; /* probability increment, (d1 in Blue) */ + __u32 decrement; /* probability decrement, (d2 in Blue) */ + __u32 limit; /* max SFB queue length */ + __u32 penalty_rate; /* inelastic flows are rate limited to 'rate' pps */ + __u32 penalty_burst; +}; + +struct tc_sfb_xstats { + __u32 earlydrop; + __u32 penaltydrop; + __u32 bucketdrop; + __u32 queuedrop; + __u32 childdrop; /* drops in child qdisc */ + __u32 marked; + __u32 maxqlen; + __u32 maxprob; + __u32 avgprob; +}; + +#define SFB_MAX_PROB 0xFFFF + +/* QFQ */ +enum { + TCA_QFQ_UNSPEC, + TCA_QFQ_WEIGHT, + TCA_QFQ_LMAX, + __TCA_QFQ_MAX +}; + +#define TCA_QFQ_MAX (__TCA_QFQ_MAX - 1) + +struct tc_qfq_stats { + __u32 weight; + __u32 lmax; +}; + +/* CODEL */ + +enum { + TCA_CODEL_UNSPEC, + TCA_CODEL_TARGET, + TCA_CODEL_LIMIT, + TCA_CODEL_INTERVAL, + TCA_CODEL_ECN, + TCA_CODEL_CE_THRESHOLD, + __TCA_CODEL_MAX +}; + +#define TCA_CODEL_MAX (__TCA_CODEL_MAX - 1) + +struct tc_codel_xstats { + __u32 maxpacket; /* largest packet we've seen so far */ + __u32 count; /* how many drops we've done since the last time we + * entered dropping state + */ + __u32 lastcount; /* count at entry to dropping state */ + __u32 ldelay; /* in-queue delay seen by most recently dequeued packet */ + __s32 drop_next; /* time to drop next packet */ + __u32 drop_overlimit; /* number of time max qdisc packet limit was hit */ + __u32 ecn_mark; /* number of packets we ECN marked instead of dropped */ + __u32 dropping; /* are we in dropping state ? */ + __u32 ce_mark; /* number of CE marked packets because of ce_threshold */ +}; + +/* FQ_CODEL */ + +enum { + TCA_FQ_CODEL_UNSPEC, + TCA_FQ_CODEL_TARGET, + TCA_FQ_CODEL_LIMIT, + TCA_FQ_CODEL_INTERVAL, + TCA_FQ_CODEL_ECN, + TCA_FQ_CODEL_FLOWS, + TCA_FQ_CODEL_QUANTUM, + TCA_FQ_CODEL_CE_THRESHOLD, + TCA_FQ_CODEL_DROP_BATCH_SIZE, + TCA_FQ_CODEL_MEMORY_LIMIT, + __TCA_FQ_CODEL_MAX +}; + +#define TCA_FQ_CODEL_MAX (__TCA_FQ_CODEL_MAX - 1) + +enum { + TCA_FQ_CODEL_XSTATS_QDISC, + TCA_FQ_CODEL_XSTATS_CLASS, +}; + +struct tc_fq_codel_qd_stats { + __u32 maxpacket; /* largest packet we've seen so far */ + __u32 drop_overlimit; /* number of time max qdisc + * packet limit was hit + */ + __u32 ecn_mark; /* number of packets we ECN marked + * instead of being dropped + */ + __u32 new_flow_count; /* number of time packets + * created a 'new flow' + */ + __u32 new_flows_len; /* count of flows in new list */ + __u32 old_flows_len; /* count of flows in old list */ + __u32 ce_mark; /* packets above ce_threshold */ + __u32 memory_usage; /* in bytes */ + __u32 drop_overmemory; +}; + +struct tc_fq_codel_cl_stats { + __s32 deficit; + __u32 ldelay; /* in-queue delay seen by most recently + * dequeued packet + */ + __u32 count; + __u32 lastcount; + __u32 dropping; + __s32 drop_next; +}; + +struct tc_fq_codel_xstats { + __u32 type; + union { + struct tc_fq_codel_qd_stats qdisc_stats; + struct tc_fq_codel_cl_stats class_stats; + }; +}; + +/* FQ */ + +enum { + TCA_FQ_UNSPEC, + + TCA_FQ_PLIMIT, /* limit of total number of packets in queue */ + + TCA_FQ_FLOW_PLIMIT, /* limit of packets per flow */ + + TCA_FQ_QUANTUM, /* RR quantum */ + + TCA_FQ_INITIAL_QUANTUM, /* RR quantum for new flow */ + + TCA_FQ_RATE_ENABLE, /* enable/disable rate limiting */ + + TCA_FQ_FLOW_DEFAULT_RATE,/* obsolete, do not use */ + + TCA_FQ_FLOW_MAX_RATE, /* per flow max rate */ + + TCA_FQ_BUCKETS_LOG, /* log2(number of buckets) */ + + TCA_FQ_FLOW_REFILL_DELAY, /* flow credit refill delay in usec */ + + TCA_FQ_ORPHAN_MASK, /* mask applied to orphaned skb hashes */ + + TCA_FQ_LOW_RATE_THRESHOLD, /* per packet delay under this rate */ + + TCA_FQ_CE_THRESHOLD, /* DCTCP-like CE-marking threshold */ + + __TCA_FQ_MAX +}; + +#define TCA_FQ_MAX (__TCA_FQ_MAX - 1) + +struct tc_fq_qd_stats { + __u64 gc_flows; + __u64 highprio_packets; + __u64 tcp_retrans; + __u64 throttled; + __u64 flows_plimit; + __u64 pkts_too_long; + __u64 allocation_errors; + __s64 time_next_delayed_flow; + __u32 flows; + __u32 inactive_flows; + __u32 throttled_flows; + __u32 unthrottle_latency_ns; + __u64 ce_mark; /* packets above ce_threshold */ +}; + +/* Heavy-Hitter Filter */ + +enum { + TCA_HHF_UNSPEC, + TCA_HHF_BACKLOG_LIMIT, + TCA_HHF_QUANTUM, + TCA_HHF_HH_FLOWS_LIMIT, + TCA_HHF_RESET_TIMEOUT, + TCA_HHF_ADMIT_BYTES, + TCA_HHF_EVICT_TIMEOUT, + TCA_HHF_NON_HH_WEIGHT, + __TCA_HHF_MAX +}; + +#define TCA_HHF_MAX (__TCA_HHF_MAX - 1) + +struct tc_hhf_xstats { + __u32 drop_overlimit; /* number of times max qdisc packet limit + * was hit + */ + __u32 hh_overlimit; /* number of times max heavy-hitters was hit */ + __u32 hh_tot_count; /* number of captured heavy-hitters so far */ + __u32 hh_cur_count; /* number of current heavy-hitters */ +}; + +/* PIE */ +enum { + TCA_PIE_UNSPEC, + TCA_PIE_TARGET, + TCA_PIE_LIMIT, + TCA_PIE_TUPDATE, + TCA_PIE_ALPHA, + TCA_PIE_BETA, + TCA_PIE_ECN, + TCA_PIE_BYTEMODE, + __TCA_PIE_MAX +}; +#define TCA_PIE_MAX (__TCA_PIE_MAX - 1) + +struct tc_pie_xstats { + __u32 prob; /* current probability */ + __u32 delay; /* current delay in ms */ + __u32 avg_dq_rate; /* current average dq_rate in bits/pie_time */ + __u32 packets_in; /* total number of packets enqueued */ + __u32 dropped; /* packets dropped due to pie_action */ + __u32 overlimit; /* dropped due to lack of space in queue */ + __u32 maxq; /* maximum queue size */ + __u32 ecn_mark; /* packets marked with ecn*/ +}; + +/* CBS */ +struct tc_cbs_qopt { + __u8 offload; + __u8 _pad[3]; + __s32 hicredit; + __s32 locredit; + __s32 idleslope; + __s32 sendslope; +}; + +enum { + TCA_CBS_UNSPEC, + TCA_CBS_PARMS, + __TCA_CBS_MAX, +}; + +#define TCA_CBS_MAX (__TCA_CBS_MAX - 1) + + +/* ETF */ +struct tc_etf_qopt { + __s32 delta; + __s32 clockid; + __u32 flags; +#define TC_ETF_DEADLINE_MODE_ON BIT(0) +#define TC_ETF_OFFLOAD_ON BIT(1) +}; + +enum { + TCA_ETF_UNSPEC, + TCA_ETF_PARMS, + __TCA_ETF_MAX, +}; + +#define TCA_ETF_MAX (__TCA_ETF_MAX - 1) + + +/* CAKE */ +enum { + TCA_CAKE_UNSPEC, + TCA_CAKE_PAD, + TCA_CAKE_BASE_RATE64, + TCA_CAKE_DIFFSERV_MODE, + TCA_CAKE_ATM, + TCA_CAKE_FLOW_MODE, + TCA_CAKE_OVERHEAD, + TCA_CAKE_RTT, + TCA_CAKE_TARGET, + TCA_CAKE_AUTORATE, + TCA_CAKE_MEMORY, + TCA_CAKE_NAT, + TCA_CAKE_RAW, + TCA_CAKE_WASH, + TCA_CAKE_MPU, + TCA_CAKE_INGRESS, + TCA_CAKE_ACK_FILTER, + TCA_CAKE_SPLIT_GSO, + __TCA_CAKE_MAX +}; +#define TCA_CAKE_MAX (__TCA_CAKE_MAX - 1) + +enum { + __TCA_CAKE_STATS_INVALID, + TCA_CAKE_STATS_PAD, + TCA_CAKE_STATS_CAPACITY_ESTIMATE64, + TCA_CAKE_STATS_MEMORY_LIMIT, + TCA_CAKE_STATS_MEMORY_USED, + TCA_CAKE_STATS_AVG_NETOFF, + TCA_CAKE_STATS_MIN_NETLEN, + TCA_CAKE_STATS_MAX_NETLEN, + TCA_CAKE_STATS_MIN_ADJLEN, + TCA_CAKE_STATS_MAX_ADJLEN, + TCA_CAKE_STATS_TIN_STATS, + TCA_CAKE_STATS_DEFICIT, + TCA_CAKE_STATS_COBALT_COUNT, + TCA_CAKE_STATS_DROPPING, + TCA_CAKE_STATS_DROP_NEXT_US, + TCA_CAKE_STATS_P_DROP, + TCA_CAKE_STATS_BLUE_TIMER_US, + __TCA_CAKE_STATS_MAX +}; +#define TCA_CAKE_STATS_MAX (__TCA_CAKE_STATS_MAX - 1) + +enum { + __TCA_CAKE_TIN_STATS_INVALID, + TCA_CAKE_TIN_STATS_PAD, + TCA_CAKE_TIN_STATS_SENT_PACKETS, + TCA_CAKE_TIN_STATS_SENT_BYTES64, + TCA_CAKE_TIN_STATS_DROPPED_PACKETS, + TCA_CAKE_TIN_STATS_DROPPED_BYTES64, + TCA_CAKE_TIN_STATS_ACKS_DROPPED_PACKETS, + TCA_CAKE_TIN_STATS_ACKS_DROPPED_BYTES64, + TCA_CAKE_TIN_STATS_ECN_MARKED_PACKETS, + TCA_CAKE_TIN_STATS_ECN_MARKED_BYTES64, + TCA_CAKE_TIN_STATS_BACKLOG_PACKETS, + TCA_CAKE_TIN_STATS_BACKLOG_BYTES, + TCA_CAKE_TIN_STATS_THRESHOLD_RATE64, + TCA_CAKE_TIN_STATS_TARGET_US, + TCA_CAKE_TIN_STATS_INTERVAL_US, + TCA_CAKE_TIN_STATS_WAY_INDIRECT_HITS, + TCA_CAKE_TIN_STATS_WAY_MISSES, + TCA_CAKE_TIN_STATS_WAY_COLLISIONS, + TCA_CAKE_TIN_STATS_PEAK_DELAY_US, + TCA_CAKE_TIN_STATS_AVG_DELAY_US, + TCA_CAKE_TIN_STATS_BASE_DELAY_US, + TCA_CAKE_TIN_STATS_SPARSE_FLOWS, + TCA_CAKE_TIN_STATS_BULK_FLOWS, + TCA_CAKE_TIN_STATS_UNRESPONSIVE_FLOWS, + TCA_CAKE_TIN_STATS_MAX_SKBLEN, + TCA_CAKE_TIN_STATS_FLOW_QUANTUM, + __TCA_CAKE_TIN_STATS_MAX +}; +#define TCA_CAKE_TIN_STATS_MAX (__TCA_CAKE_TIN_STATS_MAX - 1) +#define TC_CAKE_MAX_TINS (8) + +enum { + CAKE_FLOW_NONE = 0, + CAKE_FLOW_SRC_IP, + CAKE_FLOW_DST_IP, + CAKE_FLOW_HOSTS, /* = CAKE_FLOW_SRC_IP | CAKE_FLOW_DST_IP */ + CAKE_FLOW_FLOWS, + CAKE_FLOW_DUAL_SRC, /* = CAKE_FLOW_SRC_IP | CAKE_FLOW_FLOWS */ + CAKE_FLOW_DUAL_DST, /* = CAKE_FLOW_DST_IP | CAKE_FLOW_FLOWS */ + CAKE_FLOW_TRIPLE, /* = CAKE_FLOW_HOSTS | CAKE_FLOW_FLOWS */ + CAKE_FLOW_MAX, +}; + +enum { + CAKE_DIFFSERV_DIFFSERV3 = 0, + CAKE_DIFFSERV_DIFFSERV4, + CAKE_DIFFSERV_DIFFSERV8, + CAKE_DIFFSERV_BESTEFFORT, + CAKE_DIFFSERV_PRECEDENCE, + CAKE_DIFFSERV_MAX +}; + +enum { + CAKE_ACK_NONE = 0, + CAKE_ACK_FILTER, + CAKE_ACK_AGGRESSIVE, + CAKE_ACK_MAX +}; + +enum { + CAKE_ATM_NONE = 0, + CAKE_ATM_ATM, + CAKE_ATM_PTM, + CAKE_ATM_MAX +}; + + +/* TAPRIO */ +enum { + TC_TAPRIO_CMD_SET_GATES = 0x00, + TC_TAPRIO_CMD_SET_AND_HOLD = 0x01, + TC_TAPRIO_CMD_SET_AND_RELEASE = 0x02, +}; + +enum { + TCA_TAPRIO_SCHED_ENTRY_UNSPEC, + TCA_TAPRIO_SCHED_ENTRY_INDEX, /* u32 */ + TCA_TAPRIO_SCHED_ENTRY_CMD, /* u8 */ + TCA_TAPRIO_SCHED_ENTRY_GATE_MASK, /* u32 */ + TCA_TAPRIO_SCHED_ENTRY_INTERVAL, /* u32 */ + __TCA_TAPRIO_SCHED_ENTRY_MAX, +}; +#define TCA_TAPRIO_SCHED_ENTRY_MAX (__TCA_TAPRIO_SCHED_ENTRY_MAX - 1) + +/* The format for schedule entry list is: + * [TCA_TAPRIO_SCHED_ENTRY_LIST] + * [TCA_TAPRIO_SCHED_ENTRY] + * [TCA_TAPRIO_SCHED_ENTRY_CMD] + * [TCA_TAPRIO_SCHED_ENTRY_GATES] + * [TCA_TAPRIO_SCHED_ENTRY_INTERVAL] + */ +enum { + TCA_TAPRIO_SCHED_UNSPEC, + TCA_TAPRIO_SCHED_ENTRY, + __TCA_TAPRIO_SCHED_MAX, +}; + +#define TCA_TAPRIO_SCHED_MAX (__TCA_TAPRIO_SCHED_MAX - 1) + +enum { + TCA_TAPRIO_ATTR_UNSPEC, + TCA_TAPRIO_ATTR_PRIOMAP, /* struct tc_mqprio_qopt */ + TCA_TAPRIO_ATTR_SCHED_ENTRY_LIST, /* nested of entry */ + TCA_TAPRIO_ATTR_SCHED_BASE_TIME, /* s64 */ + TCA_TAPRIO_ATTR_SCHED_SINGLE_ENTRY, /* single entry */ + TCA_TAPRIO_ATTR_SCHED_CLOCKID, /* s32 */ + TCA_TAPRIO_PAD, + __TCA_TAPRIO_ATTR_MAX, +}; + +#define TCA_TAPRIO_ATTR_MAX (__TCA_TAPRIO_ATTR_MAX - 1) + +#endif diff --git a/tools/include/uapi/linux/tc_act/tc_bpf.h b/tools/include/uapi/linux/tc_act/tc_bpf.h new file mode 100644 index 0000000000000000000000000000000000000000..6e89a5df49a46a601cd5b4e82b0a4dcb6af7e23c --- /dev/null +++ b/tools/include/uapi/linux/tc_act/tc_bpf.h @@ -0,0 +1,37 @@ +/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ +/* + * Copyright (c) 2015 Jiri Pirko + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + */ + +#ifndef __LINUX_TC_BPF_H +#define __LINUX_TC_BPF_H + +#include + +#define TCA_ACT_BPF 13 + +struct tc_act_bpf { + tc_gen; +}; + +enum { + TCA_ACT_BPF_UNSPEC, + TCA_ACT_BPF_TM, + TCA_ACT_BPF_PARMS, + TCA_ACT_BPF_OPS_LEN, + TCA_ACT_BPF_OPS, + TCA_ACT_BPF_FD, + TCA_ACT_BPF_NAME, + TCA_ACT_BPF_PAD, + TCA_ACT_BPF_TAG, + TCA_ACT_BPF_ID, + __TCA_ACT_BPF_MAX, +}; +#define TCA_ACT_BPF_MAX (__TCA_ACT_BPF_MAX - 1) + +#endif diff --git a/tools/lib/bpf/Build b/tools/lib/bpf/Build index 6eb9bacd1948ad810c50f2192b348c81fcb1ac99..7bc31c90501846cc045f956c87e8035b140e0be2 100644 --- a/tools/lib/bpf/Build +++ b/tools/lib/bpf/Build @@ -1 +1 @@ -libbpf-y := libbpf.o bpf.o nlattr.o btf.o libbpf_errno.o str_error.o +libbpf-y := libbpf.o bpf.o nlattr.o btf.o libbpf_errno.o str_error.o netlink.o diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c index 482025b728399338eaa8df4ca32900c9b89a01c7..eba3ad604244d89600b4ac1ecee1c7a0932b9dc3 100644 --- a/tools/lib/bpf/bpf.c +++ b/tools/lib/bpf/bpf.c @@ -28,16 +28,8 @@ #include #include "bpf.h" #include "libbpf.h" -#include "nlattr.h" -#include -#include -#include #include -#ifndef SOL_NETLINK -#define SOL_NETLINK 270 -#endif - /* * When building perf, unistd.h is overridden. __NR_bpf is * required to be defined explicitly. @@ -521,127 +513,6 @@ int bpf_raw_tracepoint_open(const char *name, int prog_fd) return sys_bpf(BPF_RAW_TRACEPOINT_OPEN, &attr, sizeof(attr)); } -int bpf_set_link_xdp_fd(int ifindex, int fd, __u32 flags) -{ - struct sockaddr_nl sa; - int sock, seq = 0, len, ret = -1; - char buf[4096]; - struct nlattr *nla, *nla_xdp; - struct { - struct nlmsghdr nh; - struct ifinfomsg ifinfo; - char attrbuf[64]; - } req; - struct nlmsghdr *nh; - struct nlmsgerr *err; - socklen_t addrlen; - int one = 1; - - memset(&sa, 0, sizeof(sa)); - sa.nl_family = AF_NETLINK; - - sock = socket(AF_NETLINK, SOCK_RAW, NETLINK_ROUTE); - if (sock < 0) { - return -errno; - } - - if (setsockopt(sock, SOL_NETLINK, NETLINK_EXT_ACK, - &one, sizeof(one)) < 0) { - fprintf(stderr, "Netlink error reporting not supported\n"); - } - - if (bind(sock, (struct sockaddr *)&sa, sizeof(sa)) < 0) { - ret = -errno; - goto cleanup; - } - - addrlen = sizeof(sa); - if (getsockname(sock, (struct sockaddr *)&sa, &addrlen) < 0) { - ret = -errno; - goto cleanup; - } - - if (addrlen != sizeof(sa)) { - ret = -LIBBPF_ERRNO__INTERNAL; - goto cleanup; - } - - memset(&req, 0, sizeof(req)); - req.nh.nlmsg_len = NLMSG_LENGTH(sizeof(struct ifinfomsg)); - req.nh.nlmsg_flags = NLM_F_REQUEST | NLM_F_ACK; - req.nh.nlmsg_type = RTM_SETLINK; - req.nh.nlmsg_pid = 0; - req.nh.nlmsg_seq = ++seq; - req.ifinfo.ifi_family = AF_UNSPEC; - req.ifinfo.ifi_index = ifindex; - - /* started nested attribute for XDP */ - nla = (struct nlattr *)(((char *)&req) - + NLMSG_ALIGN(req.nh.nlmsg_len)); - nla->nla_type = NLA_F_NESTED | IFLA_XDP; - nla->nla_len = NLA_HDRLEN; - - /* add XDP fd */ - nla_xdp = (struct nlattr *)((char *)nla + nla->nla_len); - nla_xdp->nla_type = IFLA_XDP_FD; - nla_xdp->nla_len = NLA_HDRLEN + sizeof(int); - memcpy((char *)nla_xdp + NLA_HDRLEN, &fd, sizeof(fd)); - nla->nla_len += nla_xdp->nla_len; - - /* if user passed in any flags, add those too */ - if (flags) { - nla_xdp = (struct nlattr *)((char *)nla + nla->nla_len); - nla_xdp->nla_type = IFLA_XDP_FLAGS; - nla_xdp->nla_len = NLA_HDRLEN + sizeof(flags); - memcpy((char *)nla_xdp + NLA_HDRLEN, &flags, sizeof(flags)); - nla->nla_len += nla_xdp->nla_len; - } - - req.nh.nlmsg_len += NLA_ALIGN(nla->nla_len); - - if (send(sock, &req, req.nh.nlmsg_len, 0) < 0) { - ret = -errno; - goto cleanup; - } - - len = recv(sock, buf, sizeof(buf), 0); - if (len < 0) { - ret = -errno; - goto cleanup; - } - - for (nh = (struct nlmsghdr *)buf; NLMSG_OK(nh, len); - nh = NLMSG_NEXT(nh, len)) { - if (nh->nlmsg_pid != sa.nl_pid) { - ret = -LIBBPF_ERRNO__WRNGPID; - goto cleanup; - } - if (nh->nlmsg_seq != seq) { - ret = -LIBBPF_ERRNO__INVSEQ; - goto cleanup; - } - switch (nh->nlmsg_type) { - case NLMSG_ERROR: - err = (struct nlmsgerr *)NLMSG_DATA(nh); - if (!err->error) - continue; - ret = err->error; - nla_dump_errormsg(nh); - goto cleanup; - case NLMSG_DONE: - break; - default: - break; - } - } - - ret = 0; - -cleanup: - close(sock); - return ret; -} - int bpf_load_btf(void *btf, __u32 btf_size, char *log_buf, __u32 log_buf_size, bool do_log) { diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h index 96c55fac54c314167bb81f248c67107e77becf5f..e3b00e23e181cd123fd27d5c9af9fb627d14c0b2 100644 --- a/tools/lib/bpf/libbpf.h +++ b/tools/lib/bpf/libbpf.h @@ -46,6 +46,7 @@ enum libbpf_errno { LIBBPF_ERRNO__PROGTYPE, /* Kernel doesn't support this program type */ LIBBPF_ERRNO__WRNGPID, /* Wrong pid in netlink message */ LIBBPF_ERRNO__INVSEQ, /* Invalid netlink sequence */ + LIBBPF_ERRNO__NLPARSE, /* netlink parsing error */ __LIBBPF_ERRNO__END, }; @@ -297,4 +298,19 @@ int bpf_perf_event_read_simple(void *mem, unsigned long size, unsigned long page_size, void **buf, size_t *buf_len, bpf_perf_event_print_t fn, void *priv); + +struct nlmsghdr; +struct nlattr; +typedef int (*dump_nlmsg_t)(void *cookie, void *msg, struct nlattr **tb); +typedef int (*__dump_nlmsg_t)(struct nlmsghdr *nlmsg, dump_nlmsg_t, + void *cookie); +int bpf_netlink_open(unsigned int *nl_pid); +int nl_get_link(int sock, unsigned int nl_pid, dump_nlmsg_t dump_link_nlmsg, + void *cookie); +int nl_get_class(int sock, unsigned int nl_pid, int ifindex, + dump_nlmsg_t dump_class_nlmsg, void *cookie); +int nl_get_qdisc(int sock, unsigned int nl_pid, int ifindex, + dump_nlmsg_t dump_qdisc_nlmsg, void *cookie); +int nl_get_filter(int sock, unsigned int nl_pid, int ifindex, int handle, + dump_nlmsg_t dump_filter_nlmsg, void *cookie); #endif diff --git a/tools/lib/bpf/libbpf_errno.c b/tools/lib/bpf/libbpf_errno.c index d2d17226d9d6bb2a83b90682e2c7e2032f117cca..451283328fa907d5cc1d2e415846cdc2a37f241a 100644 --- a/tools/lib/bpf/libbpf_errno.c +++ b/tools/lib/bpf/libbpf_errno.c @@ -43,6 +43,7 @@ static const char *libbpf_strerror_table[NR_ERRNO] = { [ERRCODE_OFFSET(PROGTYPE)] = "Kernel doesn't support this program type", [ERRCODE_OFFSET(WRNGPID)] = "Wrong pid in netlink message", [ERRCODE_OFFSET(INVSEQ)] = "Invalid netlink sequence", + [ERRCODE_OFFSET(NLPARSE)] = "Incorrect netlink message parsing", }; int libbpf_strerror(int err, char *buf, size_t size) diff --git a/tools/lib/bpf/netlink.c b/tools/lib/bpf/netlink.c new file mode 100644 index 0000000000000000000000000000000000000000..fde1d7bf8199ede8fbd0d54e0f2bcd04f5af95fc --- /dev/null +++ b/tools/lib/bpf/netlink.c @@ -0,0 +1,331 @@ +// SPDX-License-Identifier: LGPL-2.1 +/* Copyright (c) 2018 Facebook */ + +#include +#include +#include +#include +#include +#include +#include +#include + +#include "bpf.h" +#include "libbpf.h" +#include "nlattr.h" + +#ifndef SOL_NETLINK +#define SOL_NETLINK 270 +#endif + +int bpf_netlink_open(__u32 *nl_pid) +{ + struct sockaddr_nl sa; + socklen_t addrlen; + int one = 1, ret; + int sock; + + memset(&sa, 0, sizeof(sa)); + sa.nl_family = AF_NETLINK; + + sock = socket(AF_NETLINK, SOCK_RAW, NETLINK_ROUTE); + if (sock < 0) + return -errno; + + if (setsockopt(sock, SOL_NETLINK, NETLINK_EXT_ACK, + &one, sizeof(one)) < 0) { + fprintf(stderr, "Netlink error reporting not supported\n"); + } + + if (bind(sock, (struct sockaddr *)&sa, sizeof(sa)) < 0) { + ret = -errno; + goto cleanup; + } + + addrlen = sizeof(sa); + if (getsockname(sock, (struct sockaddr *)&sa, &addrlen) < 0) { + ret = -errno; + goto cleanup; + } + + if (addrlen != sizeof(sa)) { + ret = -LIBBPF_ERRNO__INTERNAL; + goto cleanup; + } + + *nl_pid = sa.nl_pid; + return sock; + +cleanup: + close(sock); + return ret; +} + +static int bpf_netlink_recv(int sock, __u32 nl_pid, int seq, + __dump_nlmsg_t _fn, dump_nlmsg_t fn, + void *cookie) +{ + bool multipart = true; + struct nlmsgerr *err; + struct nlmsghdr *nh; + char buf[4096]; + int len, ret; + + while (multipart) { + multipart = false; + len = recv(sock, buf, sizeof(buf), 0); + if (len < 0) { + ret = -errno; + goto done; + } + + if (len == 0) + break; + + for (nh = (struct nlmsghdr *)buf; NLMSG_OK(nh, len); + nh = NLMSG_NEXT(nh, len)) { + if (nh->nlmsg_pid != nl_pid) { + ret = -LIBBPF_ERRNO__WRNGPID; + goto done; + } + if (nh->nlmsg_seq != seq) { + ret = -LIBBPF_ERRNO__INVSEQ; + goto done; + } + if (nh->nlmsg_flags & NLM_F_MULTI) + multipart = true; + switch (nh->nlmsg_type) { + case NLMSG_ERROR: + err = (struct nlmsgerr *)NLMSG_DATA(nh); + if (!err->error) + continue; + ret = err->error; + nla_dump_errormsg(nh); + goto done; + case NLMSG_DONE: + return 0; + default: + break; + } + if (_fn) { + ret = _fn(nh, fn, cookie); + if (ret) + return ret; + } + } + } + ret = 0; +done: + return ret; +} + +int bpf_set_link_xdp_fd(int ifindex, int fd, __u32 flags) +{ + int sock, seq = 0, ret; + struct nlattr *nla, *nla_xdp; + struct { + struct nlmsghdr nh; + struct ifinfomsg ifinfo; + char attrbuf[64]; + } req; + __u32 nl_pid; + + sock = bpf_netlink_open(&nl_pid); + if (sock < 0) + return sock; + + memset(&req, 0, sizeof(req)); + req.nh.nlmsg_len = NLMSG_LENGTH(sizeof(struct ifinfomsg)); + req.nh.nlmsg_flags = NLM_F_REQUEST | NLM_F_ACK; + req.nh.nlmsg_type = RTM_SETLINK; + req.nh.nlmsg_pid = 0; + req.nh.nlmsg_seq = ++seq; + req.ifinfo.ifi_family = AF_UNSPEC; + req.ifinfo.ifi_index = ifindex; + + /* started nested attribute for XDP */ + nla = (struct nlattr *)(((char *)&req) + + NLMSG_ALIGN(req.nh.nlmsg_len)); + nla->nla_type = NLA_F_NESTED | IFLA_XDP; + nla->nla_len = NLA_HDRLEN; + + /* add XDP fd */ + nla_xdp = (struct nlattr *)((char *)nla + nla->nla_len); + nla_xdp->nla_type = IFLA_XDP_FD; + nla_xdp->nla_len = NLA_HDRLEN + sizeof(int); + memcpy((char *)nla_xdp + NLA_HDRLEN, &fd, sizeof(fd)); + nla->nla_len += nla_xdp->nla_len; + + /* if user passed in any flags, add those too */ + if (flags) { + nla_xdp = (struct nlattr *)((char *)nla + nla->nla_len); + nla_xdp->nla_type = IFLA_XDP_FLAGS; + nla_xdp->nla_len = NLA_HDRLEN + sizeof(flags); + memcpy((char *)nla_xdp + NLA_HDRLEN, &flags, sizeof(flags)); + nla->nla_len += nla_xdp->nla_len; + } + + req.nh.nlmsg_len += NLA_ALIGN(nla->nla_len); + + if (send(sock, &req, req.nh.nlmsg_len, 0) < 0) { + ret = -errno; + goto cleanup; + } + ret = bpf_netlink_recv(sock, nl_pid, seq, NULL, NULL, NULL); + +cleanup: + close(sock); + return ret; +} + +static int __dump_link_nlmsg(struct nlmsghdr *nlh, dump_nlmsg_t dump_link_nlmsg, + void *cookie) +{ + struct nlattr *tb[IFLA_MAX + 1], *attr; + struct ifinfomsg *ifi = NLMSG_DATA(nlh); + int len; + + len = nlh->nlmsg_len - NLMSG_LENGTH(sizeof(*ifi)); + attr = (struct nlattr *) ((void *) ifi + NLMSG_ALIGN(sizeof(*ifi))); + if (nla_parse(tb, IFLA_MAX, attr, len, NULL) != 0) + return -LIBBPF_ERRNO__NLPARSE; + + return dump_link_nlmsg(cookie, ifi, tb); +} + +int nl_get_link(int sock, unsigned int nl_pid, dump_nlmsg_t dump_link_nlmsg, + void *cookie) +{ + struct { + struct nlmsghdr nlh; + struct ifinfomsg ifm; + } req = { + .nlh.nlmsg_len = NLMSG_LENGTH(sizeof(struct ifinfomsg)), + .nlh.nlmsg_type = RTM_GETLINK, + .nlh.nlmsg_flags = NLM_F_DUMP | NLM_F_REQUEST, + .ifm.ifi_family = AF_PACKET, + }; + int seq = time(NULL); + + req.nlh.nlmsg_seq = seq; + if (send(sock, &req, req.nlh.nlmsg_len, 0) < 0) + return -errno; + + return bpf_netlink_recv(sock, nl_pid, seq, __dump_link_nlmsg, + dump_link_nlmsg, cookie); +} + +static int __dump_class_nlmsg(struct nlmsghdr *nlh, + dump_nlmsg_t dump_class_nlmsg, void *cookie) +{ + struct nlattr *tb[TCA_MAX + 1], *attr; + struct tcmsg *t = NLMSG_DATA(nlh); + int len; + + len = nlh->nlmsg_len - NLMSG_LENGTH(sizeof(*t)); + attr = (struct nlattr *) ((void *) t + NLMSG_ALIGN(sizeof(*t))); + if (nla_parse(tb, TCA_MAX, attr, len, NULL) != 0) + return -LIBBPF_ERRNO__NLPARSE; + + return dump_class_nlmsg(cookie, t, tb); +} + +int nl_get_class(int sock, unsigned int nl_pid, int ifindex, + dump_nlmsg_t dump_class_nlmsg, void *cookie) +{ + struct { + struct nlmsghdr nlh; + struct tcmsg t; + } req = { + .nlh.nlmsg_len = NLMSG_LENGTH(sizeof(struct tcmsg)), + .nlh.nlmsg_type = RTM_GETTCLASS, + .nlh.nlmsg_flags = NLM_F_DUMP | NLM_F_REQUEST, + .t.tcm_family = AF_UNSPEC, + .t.tcm_ifindex = ifindex, + }; + int seq = time(NULL); + + req.nlh.nlmsg_seq = seq; + if (send(sock, &req, req.nlh.nlmsg_len, 0) < 0) + return -errno; + + return bpf_netlink_recv(sock, nl_pid, seq, __dump_class_nlmsg, + dump_class_nlmsg, cookie); +} + +static int __dump_qdisc_nlmsg(struct nlmsghdr *nlh, + dump_nlmsg_t dump_qdisc_nlmsg, void *cookie) +{ + struct nlattr *tb[TCA_MAX + 1], *attr; + struct tcmsg *t = NLMSG_DATA(nlh); + int len; + + len = nlh->nlmsg_len - NLMSG_LENGTH(sizeof(*t)); + attr = (struct nlattr *) ((void *) t + NLMSG_ALIGN(sizeof(*t))); + if (nla_parse(tb, TCA_MAX, attr, len, NULL) != 0) + return -LIBBPF_ERRNO__NLPARSE; + + return dump_qdisc_nlmsg(cookie, t, tb); +} + +int nl_get_qdisc(int sock, unsigned int nl_pid, int ifindex, + dump_nlmsg_t dump_qdisc_nlmsg, void *cookie) +{ + struct { + struct nlmsghdr nlh; + struct tcmsg t; + } req = { + .nlh.nlmsg_len = NLMSG_LENGTH(sizeof(struct tcmsg)), + .nlh.nlmsg_type = RTM_GETQDISC, + .nlh.nlmsg_flags = NLM_F_DUMP | NLM_F_REQUEST, + .t.tcm_family = AF_UNSPEC, + .t.tcm_ifindex = ifindex, + }; + int seq = time(NULL); + + req.nlh.nlmsg_seq = seq; + if (send(sock, &req, req.nlh.nlmsg_len, 0) < 0) + return -errno; + + return bpf_netlink_recv(sock, nl_pid, seq, __dump_qdisc_nlmsg, + dump_qdisc_nlmsg, cookie); +} + +static int __dump_filter_nlmsg(struct nlmsghdr *nlh, + dump_nlmsg_t dump_filter_nlmsg, void *cookie) +{ + struct nlattr *tb[TCA_MAX + 1], *attr; + struct tcmsg *t = NLMSG_DATA(nlh); + int len; + + len = nlh->nlmsg_len - NLMSG_LENGTH(sizeof(*t)); + attr = (struct nlattr *) ((void *) t + NLMSG_ALIGN(sizeof(*t))); + if (nla_parse(tb, TCA_MAX, attr, len, NULL) != 0) + return -LIBBPF_ERRNO__NLPARSE; + + return dump_filter_nlmsg(cookie, t, tb); +} + +int nl_get_filter(int sock, unsigned int nl_pid, int ifindex, int handle, + dump_nlmsg_t dump_filter_nlmsg, void *cookie) +{ + struct { + struct nlmsghdr nlh; + struct tcmsg t; + } req = { + .nlh.nlmsg_len = NLMSG_LENGTH(sizeof(struct tcmsg)), + .nlh.nlmsg_type = RTM_GETTFILTER, + .nlh.nlmsg_flags = NLM_F_DUMP | NLM_F_REQUEST, + .t.tcm_family = AF_UNSPEC, + .t.tcm_ifindex = ifindex, + .t.tcm_parent = handle, + }; + int seq = time(NULL); + + req.nlh.nlmsg_seq = seq; + if (send(sock, &req, req.nlh.nlmsg_len, 0) < 0) + return -errno; + + return bpf_netlink_recv(sock, nl_pid, seq, __dump_filter_nlmsg, + dump_filter_nlmsg, cookie); +} diff --git a/tools/lib/bpf/nlattr.c b/tools/lib/bpf/nlattr.c index 4719434278b20aac7147013f1636eb3362248d5c..49f514119bdb083e24b5720f9d077aaa63b053d9 100644 --- a/tools/lib/bpf/nlattr.c +++ b/tools/lib/bpf/nlattr.c @@ -26,11 +26,6 @@ static uint16_t nla_attr_minlen[NLA_TYPE_MAX+1] = { [NLA_FLAG] = 0, }; -static int nla_len(const struct nlattr *nla) -{ - return nla->nla_len - NLA_HDRLEN; -} - static struct nlattr *nla_next(const struct nlattr *nla, int *remaining) { int totlen = NLA_ALIGN(nla->nla_len); @@ -46,11 +41,6 @@ static int nla_ok(const struct nlattr *nla, int remaining) nla->nla_len <= remaining; } -static void *nla_data(const struct nlattr *nla) -{ - return (char *) nla + NLA_HDRLEN; -} - static int nla_type(const struct nlattr *nla) { return nla->nla_type & NLA_TYPE_MASK; @@ -114,8 +104,8 @@ static inline int nlmsg_len(const struct nlmsghdr *nlh) * @see nla_validate * @return 0 on success or a negative error code. */ -static int nla_parse(struct nlattr *tb[], int maxtype, struct nlattr *head, int len, - struct nla_policy *policy) +int nla_parse(struct nlattr *tb[], int maxtype, struct nlattr *head, int len, + struct nla_policy *policy) { struct nlattr *nla; int rem, err; @@ -146,6 +136,25 @@ static int nla_parse(struct nlattr *tb[], int maxtype, struct nlattr *head, int return err; } +/** + * Create attribute index based on nested attribute + * @arg tb Index array to be filled (maxtype+1 elements). + * @arg maxtype Maximum attribute type expected and accepted. + * @arg nla Nested Attribute. + * @arg policy Attribute validation policy. + * + * Feeds the stream of attributes nested into the specified attribute + * to nla_parse(). + * + * @see nla_parse + * @return 0 on success or a negative error code. + */ +int nla_parse_nested(struct nlattr *tb[], int maxtype, struct nlattr *nla, + struct nla_policy *policy) +{ + return nla_parse(tb, maxtype, nla_data(nla), nla_len(nla), policy); +} + /* dump netlink extended ack error message */ int nla_dump_errormsg(struct nlmsghdr *nlh) { diff --git a/tools/lib/bpf/nlattr.h b/tools/lib/bpf/nlattr.h index 931a71f68f934758170a4a114484461f4c37c0fb..a6e2396bce7ccba09f3d262741eaf7f8c81fc94c 100644 --- a/tools/lib/bpf/nlattr.h +++ b/tools/lib/bpf/nlattr.h @@ -67,6 +67,44 @@ struct nla_policy { nla_ok(pos, rem); \ pos = nla_next(pos, &(rem))) +/** + * nla_data - head of payload + * @nla: netlink attribute + */ +static inline void *nla_data(const struct nlattr *nla) +{ + return (char *) nla + NLA_HDRLEN; +} + +static inline uint8_t nla_getattr_u8(const struct nlattr *nla) +{ + return *(uint8_t *)nla_data(nla); +} + +static inline uint32_t nla_getattr_u32(const struct nlattr *nla) +{ + return *(uint32_t *)nla_data(nla); +} + +static inline const char *nla_getattr_str(const struct nlattr *nla) +{ + return (const char *)nla_data(nla); +} + +/** + * nla_len - length of payload + * @nla: netlink attribute + */ +static inline int nla_len(const struct nlattr *nla) +{ + return nla->nla_len - NLA_HDRLEN; +} + +int nla_parse(struct nlattr *tb[], int maxtype, struct nlattr *head, int len, + struct nla_policy *policy); +int nla_parse_nested(struct nlattr *tb[], int maxtype, struct nlattr *nla, + struct nla_policy *policy); + int nla_dump_errormsg(struct nlmsghdr *nlh); #endif /* __NLATTR_H */