diff options
136 files changed, 1513 insertions, 689 deletions
diff --git a/Documentation/devicetree/bindings/clock/google,gs101-clock.yaml b/Documentation/devicetree/bindings/clock/google,gs101-clock.yaml index 3eebc03a309b..ca7fdada3ff2 100644 --- a/Documentation/devicetree/bindings/clock/google,gs101-clock.yaml +++ b/Documentation/devicetree/bindings/clock/google,gs101-clock.yaml @@ -85,8 +85,8 @@ allOf: clock-names: items: - - const: dout_cmu_misc_bus - - const: dout_cmu_misc_sss + - const: bus + - const: sss additionalProperties: false diff --git a/Documentation/process/maintainer-netdev.rst b/Documentation/process/maintainer-netdev.rst index 84ee60fceef2..fd96e4a3cef9 100644 --- a/Documentation/process/maintainer-netdev.rst +++ b/Documentation/process/maintainer-netdev.rst @@ -431,7 +431,7 @@ patchwork checks Checks in patchwork are mostly simple wrappers around existing kernel scripts, the sources are available at: -https://github.com/kuba-moo/nipa/tree/master/tests +https://github.com/linux-netdev/nipa/tree/master/tests **Do not** post your patches just to run them through the checks. You must ensure that your patches are ready by testing them locally diff --git a/MAINTAINERS b/MAINTAINERS index 9ed4d3868539..bf77be03fb2b 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -15242,6 +15242,8 @@ F: Documentation/networking/ F: Documentation/networking/net_cachelines/ F: Documentation/process/maintainer-netdev.rst F: Documentation/userspace-api/netlink/ +F: include/linux/framer/framer-provider.h +F: include/linux/framer/framer.h F: include/linux/in.h F: include/linux/indirect_call_wrapper.h F: include/linux/net.h diff --git a/arch/arm64/kvm/vgic/vgic-its.c b/arch/arm64/kvm/vgic/vgic-its.c index e2764d0ffa9f..28a93074eca1 100644 --- a/arch/arm64/kvm/vgic/vgic-its.c +++ b/arch/arm64/kvm/vgic/vgic-its.c @@ -468,6 +468,9 @@ static int its_sync_lpi_pending_table(struct kvm_vcpu *vcpu) } irq = vgic_get_irq(vcpu->kvm, NULL, intids[i]); + if (!irq) + continue; + raw_spin_lock_irqsave(&irq->irq_lock, flags); irq->pending_latch = pendmask & (1U << bit_nr); vgic_queue_irq_unlock(vcpu->kvm, irq, flags); @@ -1432,6 +1435,8 @@ static int vgic_its_cmd_handle_movall(struct kvm *kvm, struct vgic_its *its, for (i = 0; i < irq_count; i++) { irq = vgic_get_irq(kvm, NULL, intids[i]); + if (!irq) + continue; update_affinity(irq, vcpu2); diff --git a/arch/x86/include/asm/vsyscall.h b/arch/x86/include/asm/vsyscall.h index ab60a71a8dcb..472f0263dbc6 100644 --- a/arch/x86/include/asm/vsyscall.h +++ b/arch/x86/include/asm/vsyscall.h @@ -4,6 +4,7 @@ #include <linux/seqlock.h> #include <uapi/asm/vsyscall.h> +#include <asm/page_types.h> #ifdef CONFIG_X86_VSYSCALL_EMULATION extern void map_vsyscall(void); @@ -24,4 +25,13 @@ static inline bool emulate_vsyscall(unsigned long error_code, } #endif +/* + * The (legacy) vsyscall page is the long page in the kernel portion + * of the address space that has user-accessible permissions. + */ +static inline bool is_vsyscall_vaddr(unsigned long vaddr) +{ + return unlikely((vaddr & PAGE_MASK) == VSYSCALL_ADDR); +} + #endif /* _ASM_X86_VSYSCALL_H */ diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index 679b09cfe241..d6375b3c633b 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -798,15 +798,6 @@ show_signal_msg(struct pt_regs *regs, unsigned long error_code, show_opcodes(regs, loglvl); } -/* - * The (legacy) vsyscall page is the long page in the kernel portion - * of the address space that has user-accessible permissions. - */ -static bool is_vsyscall_vaddr(unsigned long vaddr) -{ - return unlikely((vaddr & PAGE_MASK) == VSYSCALL_ADDR); -} - static void __bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code, unsigned long address, u32 pkey, int si_code) diff --git a/arch/x86/mm/maccess.c b/arch/x86/mm/maccess.c index 6993f026adec..42115ac079cf 100644 --- a/arch/x86/mm/maccess.c +++ b/arch/x86/mm/maccess.c @@ -3,6 +3,8 @@ #include <linux/uaccess.h> #include <linux/kernel.h> +#include <asm/vsyscall.h> + #ifdef CONFIG_X86_64 bool copy_from_kernel_nofault_allowed(const void *unsafe_src, size_t size) { @@ -16,6 +18,14 @@ bool copy_from_kernel_nofault_allowed(const void *unsafe_src, size_t size) return false; /* + * Reading from the vsyscall page may cause an unhandled fault in + * certain cases. Though it is at an address above TASK_SIZE_MAX, it is + * usually considered as a user space address. + */ + if (is_vsyscall_vaddr(vaddr)) + return false; + + /* * Allow everything during early boot before 'x86_virt_bits' * is initialized. Needed for instruction decoding in early * exception handlers. diff --git a/block/opal_proto.h b/block/opal_proto.h index dec7ce3a3edb..d247a457bf6e 100644 --- a/block/opal_proto.h +++ b/block/opal_proto.h @@ -71,6 +71,7 @@ enum opal_response_token { #define SHORT_ATOM_BYTE 0xBF #define MEDIUM_ATOM_BYTE 0xDF #define LONG_ATOM_BYTE 0xE3 +#define EMPTY_ATOM_BYTE 0xFF #define OPAL_INVAL_PARAM 12 #define OPAL_MANUFACTURED_INACTIVE 0x08 diff --git a/block/sed-opal.c b/block/sed-opal.c index 3d9e9cd250bd..fa4dba5d8531 100644 --- a/block/sed-opal.c +++ b/block/sed-opal.c @@ -1056,16 +1056,20 @@ static int response_parse(const u8 *buf, size_t length, token_length = response_parse_medium(iter, pos); else if (pos[0] <= LONG_ATOM_BYTE) /* long atom */ token_length = response_parse_long(iter, pos); + else if (pos[0] == EMPTY_ATOM_BYTE) /* empty atom */ + token_length = 1; else /* TOKEN */ token_length = response_parse_token(iter, pos); if (token_length < 0) return token_length; + if (pos[0] != EMPTY_ATOM_BYTE) + num_entries++; + pos += token_length; total -= token_length; iter++; - num_entries++; } resp->num = num_entries; diff --git a/drivers/clk/samsung/clk-gs101.c b/drivers/clk/samsung/clk-gs101.c index 0964bb11657f..782993951fff 100644 --- a/drivers/clk/samsung/clk-gs101.c +++ b/drivers/clk/samsung/clk-gs101.c @@ -2475,7 +2475,7 @@ static const struct samsung_cmu_info misc_cmu_info __initconst = { .nr_clk_ids = CLKS_NR_MISC, .clk_regs = misc_clk_regs, .nr_clk_regs = ARRAY_SIZE(misc_clk_regs), - .clk_name = "dout_cmu_misc_bus", + .clk_name = "bus", }; /* ---- platform_driver ----------------------------------------------------- */ diff --git a/drivers/crypto/virtio/virtio_crypto_akcipher_algs.c b/drivers/crypto/virtio/virtio_crypto_akcipher_algs.c index 2621ff8a9376..de53eddf6796 100644 --- a/drivers/crypto/virtio/virtio_crypto_akcipher_algs.c +++ b/drivers/crypto/virtio/virtio_crypto_akcipher_algs.c @@ -104,7 +104,8 @@ static void virtio_crypto_dataq_akcipher_callback(struct virtio_crypto_request * } static int virtio_crypto_alg_akcipher_init_session(struct virtio_crypto_akcipher_ctx *ctx, - struct virtio_crypto_ctrl_header *header, void *para, + struct virtio_crypto_ctrl_header *header, + struct virtio_crypto_akcipher_session_para *para, const uint8_t *key, unsigned int keylen) { struct scatterlist outhdr_sg, key_sg, inhdr_sg, *sgs[3]; @@ -128,7 +129,7 @@ static int virtio_crypto_alg_akcipher_init_session(struct virtio_crypto_akcipher ctrl = &vc_ctrl_req->ctrl; memcpy(&ctrl->header, header, sizeof(ctrl->header)); - memcpy(&ctrl->u, para, sizeof(ctrl->u)); + memcpy(&ctrl->u.akcipher_create_session.para, para, sizeof(*para)); input = &vc_ctrl_req->input; input->status = cpu_to_le32(VIRTIO_CRYPTO_ERR); diff --git a/drivers/gpu/drm/tests/drm_buddy_test.c b/drivers/gpu/drm/tests/drm_buddy_test.c index fee6bec757d1..8a464f7f4c61 100644 --- a/drivers/gpu/drm/tests/drm_buddy_test.c +++ b/drivers/gpu/drm/tests/drm_buddy_test.c @@ -21,7 +21,8 @@ static inline u64 get_size(int order, u64 chunk_size) static void drm_test_buddy_alloc_contiguous(struct kunit *test) { - u64 mm_size, ps = SZ_4K, i, n_pages, total; + const unsigned long ps = SZ_4K, mm_size = 16 * 3 * SZ_4K; + unsigned long i, n_pages, total; struct drm_buddy_block *block; struct drm_buddy mm; LIST_HEAD(left); @@ -29,8 +30,6 @@ static void drm_test_buddy_alloc_contiguous(struct kunit *test) LIST_HEAD(right); LIST_HEAD(allocated); - mm_size = 16 * 3 * SZ_4K; - KUNIT_EXPECT_FALSE(test, drm_buddy_init(&mm, mm_size, ps)); /* diff --git a/drivers/hwmon/nct6775-core.c b/drivers/hwmon/nct6775-core.c index 8d2ef3145bca..9fbab8f02334 100644 --- a/drivers/hwmon/nct6775-core.c +++ b/drivers/hwmon/nct6775-core.c @@ -3512,6 +3512,7 @@ int nct6775_probe(struct device *dev, struct nct6775_data *data, const u16 *reg_temp_mon, *reg_temp_alternate, *reg_temp_crit; const u16 *reg_temp_crit_l = NULL, *reg_temp_crit_h = NULL; int num_reg_temp, num_reg_temp_mon, num_reg_tsi_temp; + int num_reg_temp_config; struct device *hwmon_dev; struct sensor_template_group tsi_temp_tg; @@ -3594,6 +3595,7 @@ int nct6775_probe(struct device *dev, struct nct6775_data *data, reg_temp_over = NCT6106_REG_TEMP_OVER; reg_temp_hyst = NCT6106_REG_TEMP_HYST; reg_temp_config = NCT6106_REG_TEMP_CONFIG; + num_reg_temp_config = ARRAY_SIZE(NCT6106_REG_TEMP_CONFIG); reg_temp_alternate = NCT6106_REG_TEMP_ALTERNATE; reg_temp_crit = NCT6106_REG_TEMP_CRIT; reg_temp_crit_l = NCT6106_REG_TEMP_CRIT_L; @@ -3669,6 +3671,7 @@ int nct6775_probe(struct device *dev, struct nct6775_data *data, reg_temp_over = NCT6106_REG_TEMP_OVER; reg_temp_hyst = NCT6106_REG_TEMP_HYST; reg_temp_config = NCT6106_REG_TEMP_CONFIG; + num_reg_temp_config = ARRAY_SIZE(NCT6106_REG_TEMP_CONFIG); reg_temp_alternate = NCT6106_REG_TEMP_ALTERNATE; reg_temp_crit = NCT6106_REG_TEMP_CRIT; reg_temp_crit_l = NCT6106_REG_TEMP_CRIT_L; @@ -3746,6 +3749,7 @@ int nct6775_probe(struct device *dev, struct nct6775_data *data, reg_temp_over = NCT6775_REG_TEMP_OVER; reg_temp_hyst = NCT6775_REG_TEMP_HYST; reg_temp_config = NCT6775_REG_TEMP_CONFIG; + num_reg_temp_config = ARRAY_SIZE(NCT6775_REG_TEMP_CONFIG); reg_temp_alternate = NCT6775_REG_TEMP_ALTERNATE; reg_temp_crit = NCT6775_REG_TEMP_CRIT; @@ -3821,6 +3825,7 @@ int nct6775_probe(struct device *dev, struct nct6775_data *data, reg_temp_over = NCT6775_REG_TEMP_OVER; reg_temp_hyst = NCT6775_REG_TEMP_HYST; reg_temp_config = NCT6776_REG_TEMP_CONFIG; + num_reg_temp_config = ARRAY_SIZE(NCT6776_REG_TEMP_CONFIG); reg_temp_alternate = NCT6776_REG_TEMP_ALTERNATE; reg_temp_crit = NCT6776_REG_TEMP_CRIT; @@ -3900,6 +3905,7 @@ int nct6775_probe(struct device *dev, struct nct6775_data *data, reg_temp_over = NCT6779_REG_TEMP_OVER; reg_temp_hyst = NCT6779_REG_TEMP_HYST; reg_temp_config = NCT6779_REG_TEMP_CONFIG; + num_reg_temp_config = ARRAY_SIZE(NCT6779_REG_TEMP_CONFIG); reg_temp_alternate = NCT6779_REG_TEMP_ALTERNATE; reg_temp_crit = NCT6779_REG_TEMP_CRIT; @@ -4034,6 +4040,7 @@ int nct6775_probe(struct device *dev, struct nct6775_data *data, reg_temp_over = NCT6779_REG_TEMP_OVER; reg_temp_hyst = NCT6779_REG_TEMP_HYST; reg_temp_config = NCT6779_REG_TEMP_CONFIG; + num_reg_temp_config = ARRAY_SIZE(NCT6779_REG_TEMP_CONFIG); reg_temp_alternate = NCT6779_REG_TEMP_ALTERNATE; reg_temp_crit = NCT6779_REG_TEMP_CRIT; @@ -4123,6 +4130,7 @@ int nct6775_probe(struct device *dev, struct nct6775_data *data, reg_temp_over = NCT6798_REG_TEMP_OVER; reg_temp_hyst = NCT6798_REG_TEMP_HYST; reg_temp_config = NCT6779_REG_TEMP_CONFIG; + num_reg_temp_config = ARRAY_SIZE(NCT6779_REG_TEMP_CONFIG); reg_temp_alternate = NCT6798_REG_TEMP_ALTERNATE; reg_temp_crit = NCT6798_REG_TEMP_CRIT; @@ -4204,7 +4212,8 @@ int nct6775_probe(struct device *dev, struct nct6775_data *data, = reg_temp_crit[src - 1]; if (reg_temp_crit_l && reg_temp_crit_l[i]) data->reg_temp[4][src - 1] = reg_temp_crit_l[i]; - data->reg_temp_config[src - 1] = reg_temp_config[i]; + if (i < num_reg_temp_config) + data->reg_temp_config[src - 1] = reg_temp_config[i]; data->temp_src[src - 1] = src; continue; } @@ -4217,7 +4226,8 @@ int nct6775_probe(struct device *dev, struct nct6775_data *data, data->reg_temp[0][s] = reg_temp[i]; data->reg_temp[1][s] = reg_temp_over[i]; data->reg_temp[2][s] = reg_temp_hyst[i]; - data->reg_temp_config[s] = reg_temp_config[i]; + if (i < num_reg_temp_config) + data->reg_temp_config[s] = reg_temp_config[i]; if (reg_temp_crit_h && reg_temp_crit_h[i]) data->reg_temp[3][s] = reg_temp_crit_h[i]; else if (reg_temp_crit[src - 1]) diff --git a/drivers/infiniband/hw/bnxt_re/ib_verbs.c b/drivers/infiniband/hw/bnxt_re/ib_verbs.c index 824349659d69..ce9c5bae83bf 100644 --- a/drivers/infiniband/hw/bnxt_re/ib_verbs.c +++ b/drivers/infiniband/hw/bnxt_re/ib_verbs.c @@ -401,6 +401,10 @@ static void bnxt_re_create_fence_wqe(struct bnxt_re_pd *pd) struct bnxt_re_fence_data *fence = &pd->fence; struct ib_mr *ib_mr = &fence->mr->ib_mr; struct bnxt_qplib_swqe *wqe = &fence->bind_wqe; + struct bnxt_re_dev *rdev = pd->rdev; + + if (bnxt_qplib_is_chip_gen_p5_p7(rdev->chip_ctx)) + return; memset(wqe, 0, sizeof(*wqe)); wqe->type = BNXT_QPLIB_SWQE_TYPE_BIND_MW; @@ -455,6 +459,9 @@ static void bnxt_re_destroy_fence_mr(struct bnxt_re_pd *pd) struct device *dev = &rdev->en_dev->pdev->dev; struct bnxt_re_mr *mr = fence->mr; + if (bnxt_qplib_is_chip_gen_p5_p7(rdev->chip_ctx)) + return; + if (fence->mw) { bnxt_re_dealloc_mw(fence->mw); fence->mw = NULL; @@ -486,6 +493,9 @@ static int bnxt_re_create_fence_mr(struct bnxt_re_pd *pd) struct ib_mw *mw; int rc; + if (bnxt_qplib_is_chip_gen_p5_p7(rdev->chip_ctx)) + return 0; + dma_addr = dma_map_single(dev, fence->va, BNXT_RE_FENCE_BYTES, DMA_BIDIRECTIONAL); rc = dma_mapping_error(dev, dma_addr); @@ -1817,7 +1827,7 @@ int bnxt_re_modify_srq(struct ib_srq *ib_srq, struct ib_srq_attr *srq_attr, switch (srq_attr_mask) { case IB_SRQ_MAX_WR: /* SRQ resize is not supported */ - break; + return -EINVAL; case IB_SRQ_LIMIT: /* Change the SRQ threshold */ if (srq_attr->srq_limit > srq->qplib_srq.max_wqe) @@ -1832,13 +1842,12 @@ int bnxt_re_modify_srq(struct ib_srq *ib_srq, struct ib_srq_attr *srq_attr, /* On success, update the shadow */ srq->srq_limit = srq_attr->srq_limit; /* No need to Build and send response back to udata */ - break; + return 0; default: ibdev_err(&rdev->ibdev, "Unsupported srq_attr_mask 0x%x", srq_attr_mask); return -EINVAL; } - return 0; } int bnxt_re_query_srq(struct ib_srq *ib_srq, struct ib_srq_attr *srq_attr) @@ -2556,11 +2565,6 @@ static int bnxt_re_build_inv_wqe(const struct ib_send_wr *wr, wqe->type = BNXT_QPLIB_SWQE_TYPE_LOCAL_INV; wqe->local_inv.inv_l_key = wr->ex.invalidate_rkey; - /* Need unconditional fence for local invalidate - * opcode to work as expected. - */ - wqe->flags |= BNXT_QPLIB_SWQE_FLAGS_UC_FENCE; - if (wr->send_flags & IB_SEND_SIGNALED) wqe->flags |= BNXT_QPLIB_SWQE_FLAGS_SIGNAL_COMP; if (wr->send_flags & IB_SEND_SOLICITED) @@ -2583,12 +2587,6 @@ static int bnxt_re_build_reg_wqe(const struct ib_reg_wr *wr, wqe->frmr.levels = qplib_frpl->hwq.level; wqe->type = BNXT_QPLIB_SWQE_TYPE_REG_MR; - /* Need unconditional fence for reg_mr - * opcode to function as expected. - */ - - wqe->flags |= BNXT_QPLIB_SWQE_FLAGS_UC_FENCE; - if (wr->wr.send_flags & IB_SEND_SIGNALED) wqe->flags |= BNXT_QPLIB_SWQE_FLAGS_SIGNAL_COMP; @@ -2719,6 +2717,18 @@ bad: return rc; } +static void bnxt_re_legacy_set_uc_fence(struct bnxt_qplib_swqe *wqe) +{ + /* Need unconditional fence for non-wire memory opcode + * to work as expected. + */ + if (wqe->type == BNXT_QPLIB_SWQE_TYPE_LOCAL_INV || + wqe->type == BNXT_QPLIB_SWQE_TYPE_FAST_REG_MR || + wqe->type == BNXT_QPLIB_SWQE_TYPE_REG_MR || + wqe->type == BNXT_QPLIB_SWQE_TYPE_BIND_MW) + wqe->flags |= BNXT_QPLIB_SWQE_FLAGS_UC_FENCE; +} + int bnxt_re_post_send(struct ib_qp *ib_qp, const struct ib_send_wr *wr, const struct ib_send_wr **bad_wr) { @@ -2798,8 +2808,11 @@ int bnxt_re_post_send(struct ib_qp *ib_qp, const struct ib_send_wr *wr, rc = -EINVAL; goto bad; } - if (!rc) + if (!rc) { + if (!bnxt_qplib_is_chip_gen_p5_p7(qp->rdev->chip_ctx)) + bnxt_re_legacy_set_uc_fence(&wqe); rc = bnxt_qplib_post_send(&qp->qplib_qp, &wqe); + } bad: if (rc) { ibdev_err(&qp->rdev->ibdev, diff --git a/drivers/infiniband/hw/bnxt_re/main.c b/drivers/infiniband/hw/bnxt_re/main.c index f022c922fae5..54b4d2f3a5d8 100644 --- a/drivers/infiniband/hw/bnxt_re/main.c +++ b/drivers/infiniband/hw/bnxt_re/main.c @@ -280,9 +280,6 @@ static void bnxt_re_set_resource_limits(struct bnxt_re_dev *rdev) static void bnxt_re_vf_res_config(struct bnxt_re_dev *rdev) { - - if (test_bit(BNXT_RE_FLAG_ERR_DEVICE_DETACHED, &rdev->flags)) - return; rdev->num_vfs = pci_sriov_get_totalvfs(rdev->en_dev->pdev); if (!bnxt_qplib_is_chip_gen_p5_p7(rdev->chip_ctx)) { bnxt_re_set_resource_limits(rdev); diff --git a/drivers/infiniband/hw/bnxt_re/qplib_fp.c b/drivers/infiniband/hw/bnxt_re/qplib_fp.c index c98e04fe2ddd..439d0c7c5d0c 100644 --- a/drivers/infiniband/hw/bnxt_re/qplib_fp.c +++ b/drivers/infiniband/hw/bnxt_re/qplib_fp.c @@ -744,7 +744,8 @@ int bnxt_qplib_query_srq(struct bnxt_qplib_res *res, bnxt_qplib_fill_cmdqmsg(&msg, &req, &resp, &sbuf, sizeof(req), sizeof(resp), 0); rc = bnxt_qplib_rcfw_send_message(rcfw, &msg); - srq->threshold = le16_to_cpu(sb->srq_limit); + if (!rc) + srq->threshold = le16_to_cpu(sb->srq_limit); dma_free_coherent(&rcfw->pdev->dev, sbuf.size, sbuf.sb, sbuf.dma_addr); diff --git a/drivers/infiniband/hw/hfi1/pio.c b/drivers/infiniband/hw/hfi1/pio.c index 68c621ff59d0..5a91cbda4aee 100644 --- a/drivers/infiniband/hw/hfi1/pio.c +++ b/drivers/infiniband/hw/hfi1/pio.c @@ -2086,7 +2086,7 @@ int init_credit_return(struct hfi1_devdata *dd) "Unable to allocate credit return DMA range for NUMA %d\n", i); ret = -ENOMEM; - goto done; + goto free_cr_base; } } set_dev_node(&dd->pcidev->dev, dd->node); @@ -2094,6 +2094,10 @@ int init_credit_return(struct hfi1_devdata *dd) ret = 0; done: return ret; + +free_cr_base: + free_credit_return(dd); + goto done; } void free_credit_return(struct hfi1_devdata *dd) diff --git a/drivers/infiniband/hw/hfi1/sdma.c b/drivers/infiniband/hw/hfi1/sdma.c index 6e5ac2023328..b67d23b1f286 100644 --- a/drivers/infiniband/hw/hfi1/sdma.c +++ b/drivers/infiniband/hw/hfi1/sdma.c @@ -3158,7 +3158,7 @@ int _pad_sdma_tx_descs(struct hfi1_devdata *dd, struct sdma_txreq *tx) { int rval = 0; - if ((unlikely(tx->num_desc + 1 == tx->desc_limit))) { + if ((unlikely(tx->num_desc == tx->desc_limit))) { rval = _extend_sdma_tx_descs(dd, tx); if (rval) { __sdma_txclean(dd, tx); diff --git a/drivers/infiniband/hw/irdma/defs.h b/drivers/infiniband/hw/irdma/defs.h index 8fb752f2eda2..2cb4b96db721 100644 --- a/drivers/infiniband/hw/irdma/defs.h +++ b/drivers/infiniband/hw/irdma/defs.h @@ -346,6 +346,7 @@ enum irdma_cqp_op_type { #define IRDMA_AE_LLP_TOO_MANY_KEEPALIVE_RETRIES 0x050b #define IRDMA_AE_LLP_DOUBT_REACHABILITY 0x050c #define IRDMA_AE_LLP_CONNECTION_ESTABLISHED 0x050e +#define IRDMA_AE_LLP_TOO_MANY_RNRS 0x050f #define IRDMA_AE_RESOURCE_EXHAUSTION 0x0520 #define IRDMA_AE_RESET_SENT 0x0601 #define IRDMA_AE_TERMINATE_SENT 0x0602 diff --git a/drivers/infiniband/hw/irdma/hw.c b/drivers/infiniband/hw/irdma/hw.c index bd4b2b896444..ad50b77282f8 100644 --- a/drivers/infiniband/hw/irdma/hw.c +++ b/drivers/infiniband/hw/irdma/hw.c @@ -387,6 +387,7 @@ static void irdma_process_aeq(struct irdma_pci_f *rf) case IRDMA_AE_LLP_TOO_MANY_RETRIES: case IRDMA_AE_LCE_QP_CATASTROPHIC: case IRDMA_AE_LCE_FUNCTION_CATASTROPHIC: + case IRDMA_AE_LLP_TOO_MANY_RNRS: case IRDMA_AE_LCE_CQ_CATASTROPHIC: case IRDMA_AE_UDA_XMIT_DGRAM_TOO_LONG: default: @@ -570,6 +571,13 @@ static void irdma_destroy_irq(struct irdma_pci_f *rf, dev->irq_ops->irdma_dis_irq(dev, msix_vec->idx); irq_update_affinity_hint(msix_vec->irq, NULL); free_irq(msix_vec->irq, dev_id); + if (rf == dev_id) { + tasklet_kill(&rf->dpc_tasklet); + } else { + struct irdma_ceq *iwceq = (struct irdma_ceq *)dev_id; + + tasklet_kill(&iwceq->dpc_tasklet); + } } /** diff --git a/drivers/infiniband/hw/irdma/verbs.c b/drivers/infiniband/hw/irdma/verbs.c index b5eb8d421988..0b046c061742 100644 --- a/drivers/infiniband/hw/irdma/verbs.c +++ b/drivers/infiniband/hw/irdma/verbs.c @@ -839,7 +839,9 @@ static int irdma_validate_qp_attrs(struct ib_qp_init_attr *init_attr, if (init_attr->cap.max_inline_data > uk_attrs->max_hw_inline || init_attr->cap.max_send_sge > uk_attrs->max_hw_wq_frags || - init_attr->cap.max_recv_sge > uk_attrs->max_hw_wq_frags) + init_attr->cap.max_recv_sge > uk_attrs->max_hw_wq_frags || + init_attr->cap.max_send_wr > uk_attrs->max_hw_wq_quanta || + init_attr->cap.max_recv_wr > uk_attrs->max_hw_rq_quanta) return -EINVAL; if (rdma_protocol_roce(&iwdev->ibdev, 1)) { @@ -2184,9 +2186,8 @@ static int irdma_create_cq(struct ib_cq *ibcq, info.cq_base_pa = iwcq->kmem.pa; } - if (dev->hw_attrs.uk_attrs.hw_rev >= IRDMA_GEN_2) - info.shadow_read_threshold = min(info.cq_uk_init_info.cq_size / 2, - (u32)IRDMA_MAX_CQ_READ_THRESH); + info.shadow_read_threshold = min(info.cq_uk_init_info.cq_size / 2, + (u32)IRDMA_MAX_CQ_READ_THRESH); if (irdma_sc_cq_init(cq, &info)) { ibdev_dbg(&iwdev->ibdev, "VERBS: init cq fail\n"); diff --git a/drivers/infiniband/hw/mlx5/cong.c b/drivers/infiniband/hw/mlx5/cong.c index f87531318feb..a78a067e3ce7 100644 --- a/drivers/infiniband/hw/mlx5/cong.c +++ b/drivers/infiniband/hw/mlx5/cong.c @@ -458,6 +458,12 @@ void mlx5_ib_init_cong_debugfs(struct mlx5_ib_dev *dev, u32 port_num) dbg_cc_params->root = debugfs_create_dir("cc_params", mlx5_debugfs_get_dev_root(mdev)); for (i = 0; i < MLX5_IB_DBG_CC_MAX; i++) { + if ((i == MLX5_IB_DBG_CC_GENERAL_RTT_RESP_DSCP_VALID || + i == MLX5_IB_DBG_CC_GENERAL_RTT_RESP_DSCP)) + if (!MLX5_CAP_GEN(mdev, roce) || + !MLX5_CAP_ROCE(mdev, roce_cc_general)) + continue; + dbg_cc_params->params[i].offset = i; dbg_cc_params->params[i].dev = dev; dbg_cc_params->params[i].port_num = port_num; diff --git a/drivers/infiniband/hw/mlx5/devx.c b/drivers/infiniband/hw/mlx5/devx.c index 869369cb5b5f..253fea374a72 100644 --- a/drivers/infiniband/hw/mlx5/devx.c +++ b/drivers/infiniband/hw/mlx5/devx.c @@ -2949,7 +2949,7 @@ DECLARE_UVERBS_NAMED_METHOD( MLX5_IB_METHOD_DEVX_OBJ_MODIFY, UVERBS_ATTR_IDR(MLX5_IB_ATTR_DEVX_OBJ_MODIFY_HANDLE, UVERBS_IDR_ANY_OBJECT, - UVERBS_ACCESS_WRITE, + UVERBS_ACCESS_READ, UA_MANDATORY), UVERBS_ATTR_PTR_IN( MLX5_IB_ATTR_DEVX_OBJ_MODIFY_CMD_IN, diff --git a/drivers/infiniband/hw/mlx5/wr.c b/drivers/infiniband/hw/mlx5/wr.c index df1d1b0a3ef7..9947feb7fb8a 100644 --- a/drivers/infiniband/hw/mlx5/wr.c +++ b/drivers/infiniband/hw/mlx5/wr.c @@ -78,7 +78,7 @@ static void set_eth_seg(const struct ib_send_wr *wr, struct mlx5_ib_qp *qp, */ copysz = min_t(u64, *cur_edge - (void *)eseg->inline_hdr.start, left); - memcpy(eseg->inline_hdr.start, pdata, copysz); + memcpy(eseg->inline_hdr.data, pdata, copysz); stride = ALIGN(sizeof(struct mlx5_wqe_eth_seg) - sizeof(eseg->inline_hdr.start) + copysz, 16); *size += stride / 16; diff --git a/drivers/infiniband/hw/qedr/verbs.c b/drivers/infiniband/hw/qedr/verbs.c index 7887a6786ed4..f118ce0a9a61 100644 --- a/drivers/infiniband/hw/qedr/verbs.c +++ b/drivers/infiniband/hw/qedr/verbs.c @@ -1879,8 +1879,17 @@ static int qedr_create_user_qp(struct qedr_dev *dev, /* RQ - read access only (0) */ rc = qedr_init_user_queue(udata, dev, &qp->urq, ureq.rq_addr, ureq.rq_len, true, 0, alloc_and_init); - if (rc) + if (rc) { + ib_umem_release(qp->usq.umem); + qp->usq.umem = NULL; + if (rdma_protocol_roce(&dev->ibdev, 1)) { + qedr_free_pbl(dev, &qp->usq.pbl_info, + qp->usq.pbl_tbl); + } else { + kfree(qp->usq.pbl_tbl); + } return rc; + } } memset(&in_params, 0, sizeof(in_params)); diff --git a/drivers/infiniband/ulp/srpt/ib_srpt.c b/drivers/infiniband/ulp/srpt/ib_srpt.c index 58f70cfec45a..040234c01be4 100644 --- a/drivers/infiniband/ulp/srpt/ib_srpt.c +++ b/drivers/infiniband/ulp/srpt/ib_srpt.c @@ -79,12 +79,16 @@ module_param(srpt_srq_size, int, 0444); MODULE_PARM_DESC(srpt_srq_size, "Shared receive queue (SRQ) size."); +static int srpt_set_u64_x(const char *buffer, const struct kernel_param *kp) +{ + return kstrtou64(buffer, 16, (u64 *)kp->arg); +} static int srpt_get_u64_x(char *buffer, const struct kernel_param *kp) { return sprintf(buffer, "0x%016llx\n", *(u64 *)kp->arg); } -module_param_call(srpt_service_guid, NULL, srpt_get_u64_x, &srpt_service_guid, - 0444); +module_param_call(srpt_service_guid, srpt_set_u64_x, srpt_get_u64_x, + &srpt_service_guid, 0444); MODULE_PARM_DESC(srpt_service_guid, "Using this value for ioc_guid, id_ext, and cm_listen_id instead of using the node_guid of the first HCA."); @@ -210,10 +214,12 @@ static const char *get_ch_state_name(enum rdma_ch_state s) /** * srpt_qp_event - QP event callback function * @event: Description of the event that occurred. - * @ch: SRPT RDMA channel. + * @ptr: SRPT RDMA channel. */ -static void srpt_qp_event(struct ib_event *event, struct srpt_rdma_ch *ch) +static void srpt_qp_event(struct ib_event *event, void *ptr) { + struct srpt_rdma_ch *ch = ptr; + pr_debug("QP event %d on ch=%p sess_name=%s-%d state=%s\n", event->event, ch, ch->sess_name, ch->qp->qp_num, get_ch_state_name(ch->state)); @@ -1807,8 +1813,7 @@ retry: ch->cq_size = ch->rq_size + sq_size; qp_init->qp_context = (void *)ch; - qp_init->event_handler - = (void(*)(struct ib_event *, void*))srpt_qp_event; + qp_init->event_handler = srpt_qp_event; qp_init->send_cq = ch->cq; qp_init->recv_cq = ch->cq; qp_init->sq_sig_type = IB_SIGNAL_REQ_WR; diff --git a/drivers/iommu/iommufd/hw_pagetable.c b/drivers/iommu/iommufd/hw_pagetable.c index 3f3f1fa1a0a9..33d142f8057d 100644 --- a/drivers/iommu/iommufd/hw_pagetable.c +++ b/drivers/iommu/iommufd/hw_pagetable.c @@ -263,7 +263,8 @@ int iommufd_hwpt_alloc(struct iommufd_ucmd *ucmd) if (cmd->__reserved) return -EOPNOTSUPP; - if (cmd->data_type == IOMMU_HWPT_DATA_NONE && cmd->data_len) + if ((cmd->data_type == IOMMU_HWPT_DATA_NONE && cmd->data_len) || + (cmd->data_type != IOMMU_HWPT_DATA_NONE && !cmd->data_len)) return -EINVAL; idev = iommufd_get_device(ucmd, cmd->dev_id); diff --git a/drivers/iommu/iommufd/iommufd_test.h b/drivers/iommu/iommufd/iommufd_test.h index 482d4059f5db..e854d3f67205 100644 --- a/drivers/iommu/iommufd/iommufd_test.h +++ b/drivers/iommu/iommufd/iommufd_test.h @@ -45,6 +45,7 @@ enum { enum { MOCK_FLAGS_DEVICE_NO_DIRTY = 1 << 0, + MOCK_FLAGS_DEVICE_HUGE_IOVA = 1 << 1, }; enum { diff --git a/drivers/iommu/iommufd/iova_bitmap.c b/drivers/iommu/iommufd/iova_bitmap.c index 0a92c9eeaf7f..db8c46bee155 100644 --- a/drivers/iommu/iommufd/iova_bitmap.c +++ b/drivers/iommu/iommufd/iova_bitmap.c @@ -100,7 +100,7 @@ struct iova_bitmap { struct iova_bitmap_map mapped; /* userspace address of the bitmap */ - u64 __user *bitmap; + u8 __user *bitmap; /* u64 index that @mapped points to */ unsigned long mapped_base_index; @@ -113,6 +113,9 @@ struct iova_bitmap { /* length of the IOVA range for the whole bitmap */ size_t length; + + /* length of the IOVA range set ahead the pinned pages */ + unsigned long set_ahead_length; }; /* @@ -162,7 +165,7 @@ static int iova_bitmap_get(struct iova_bitmap *bitmap) { struct iova_bitmap_map *mapped = &bitmap->mapped; unsigned long npages; - u64 __user *addr; + u8 __user *addr; long ret; /* @@ -176,17 +179,18 @@ static int iova_bitmap_get(struct iova_bitmap *bitmap) sizeof(*bitmap->bitmap), PAGE_SIZE); /* - * We always cap at max number of 'struct page' a base page can fit. - * This is, for example, on x86 means 2M of bitmap data max. - */ - npages = min(npages, PAGE_SIZE / sizeof(struct page *)); - - /* * Bitmap address to be pinned is calculated via pointer arithmetic * with bitmap u64 word index. */ addr = bitmap->bitmap + bitmap->mapped_base_index; + /* + * We always cap at max number of 'struct page' a base page can fit. + * This is, for example, on x86 means 2M of bitmap data max. + */ + npages = min(npages + !!offset_in_page(addr), + PAGE_SIZE / sizeof(struct page *)); + ret = pin_user_pages_fast((unsigned long)addr, npages, FOLL_WRITE, mapped->pages); if (ret <= 0) @@ -247,7 +251,7 @@ struct iova_bitmap *iova_bitmap_alloc(unsigned long iova, size_t length, mapped = &bitmap->mapped; mapped->pgshift = __ffs(page_size); - bitmap->bitmap = data; + bitmap->bitmap = (u8 __user *)data; bitmap->mapped_total_index = iova_bitmap_offset_to_index(bitmap, length - 1) + 1; bitmap->iova = iova; @@ -304,7 +308,7 @@ static unsigned long iova_bitmap_mapped_remaining(struct iova_bitmap *bitmap) remaining = bitmap->mapped_total_index - bitmap->mapped_base_index; remaining = min_t(unsigned long, remaining, - bytes / sizeof(*bitmap->bitmap)); + DIV_ROUND_UP(bytes, sizeof(*bitmap->bitmap))); return remaining; } @@ -341,6 +345,32 @@ static bool iova_bitmap_done(struct iova_bitmap *bitmap) return bitmap->mapped_base_index >= bitmap->mapped_total_index; } +static int iova_bitmap_set_ahead(struct iova_bitmap *bitmap, + size_t set_ahead_length) +{ + int ret = 0; + + while (set_ahead_length > 0 && !iova_bitmap_done(bitmap)) { + unsigned long length = iova_bitmap_mapped_length(bitmap); + unsigned long iova = iova_bitmap_mapped_iova(bitmap); + + ret = iova_bitmap_get(bitmap); + if (ret) + break; + + length = min(length, set_ahead_length); + iova_bitmap_set(bitmap, iova, length); + + set_ahead_length -= length; + bitmap->mapped_base_index += + iova_bitmap_offset_to_index(bitmap, length - 1) + 1; + iova_bitmap_put(bitmap); + } + + bitmap->set_ahead_length = 0; + return ret; +} + /* * Advances to the next range, releases the current pinned * pages and pins the next set of bitmap pages. @@ -357,6 +387,15 @@ static int iova_bitmap_advance(struct iova_bitmap *bitmap) if (iova_bitmap_done(bitmap)) return 0; + /* Iterate, set and skip any bits requested for next iteration */ + if (bitmap->set_ahead_length) { + int ret; + + ret = iova_bitmap_set_ahead(bitmap, bitmap->set_ahead_length); + if (ret) + return ret; + } + /* When advancing the index we pin the next set of bitmap pages */ return iova_bitmap_get(bitmap); } @@ -409,6 +448,7 @@ void iova_bitmap_set(struct iova_bitmap *bitmap, mapped->pgshift) + mapped->pgoff * BITS_PER_BYTE; unsigned long last_bit = (((iova + length - 1) - mapped->iova) >> mapped->pgshift) + mapped->pgoff * BITS_PER_BYTE; + unsigned long last_page_idx = mapped->npages - 1; do { unsigned int page_idx = cur_bit / BITS_PER_PAGE; @@ -417,10 +457,18 @@ void iova_bitmap_set(struct iova_bitmap *bitmap, last_bit - cur_bit + 1); void *kaddr; + if (unlikely(page_idx > last_page_idx)) + break; + kaddr = kmap_local_page(mapped->pages[page_idx]); bitmap_set(kaddr, offset, nbits); kunmap_local(kaddr); cur_bit += nbits; } while (cur_bit <= last_bit); + + if (unlikely(cur_bit <= last_bit)) { + bitmap->set_ahead_length = + ((last_bit - cur_bit + 1) << bitmap->mapped.pgshift); + } } EXPORT_SYMBOL_NS_GPL(iova_bitmap_set, IOMMUFD); diff --git a/drivers/iommu/iommufd/selftest.c b/drivers/iommu/iommufd/selftest.c index d9e9920c7eba..8abf9747773e 100644 --- a/drivers/iommu/iommufd/selftest.c +++ b/drivers/iommu/iommufd/selftest.c @@ -41,6 +41,7 @@ static atomic_t mock_dev_num; enum { MOCK_DIRTY_TRACK = 1, MOCK_IO_PAGE_SIZE = PAGE_SIZE / 2, + MOCK_HUGE_PAGE_SIZE = 512 * MOCK_IO_PAGE_SIZE, /* * Like a real page table alignment requires the low bits of the address @@ -53,6 +54,7 @@ enum { MOCK_PFN_START_IOVA = _MOCK_PFN_START, MOCK_PFN_LAST_IOVA = _MOCK_PFN_START, MOCK_PFN_DIRTY_IOVA = _MOCK_PFN_START << 1, + MOCK_PFN_HUGE_IOVA = _MOCK_PFN_START << 2, }; /* @@ -191,6 +193,34 @@ static int mock_domain_set_dirty_tracking(struct iommu_domain *domain, return 0; } +static bool mock_test_and_clear_dirty(struct mock_iommu_domain *mock, + unsigned long iova, size_t page_size, + unsigned long flags) +{ + unsigned long cur, end = iova + page_size - 1; + bool dirty = false; + void *ent, *old; + + for (cur = iova; cur < end; cur += MOCK_IO_PAGE_SIZE) { + ent = xa_load(&mock->pfns, cur / MOCK_IO_PAGE_SIZE); + if (!ent || !(xa_to_value(ent) & MOCK_PFN_DIRTY_IOVA)) + continue; + + dirty = true; + /* Clear dirty */ + if (!(flags & IOMMU_DIRTY_NO_CLEAR)) { + unsigned long val; + + val = xa_to_value(ent) & ~MOCK_PFN_DIRTY_IOVA; + old = xa_store(&mock->pfns, cur / MOCK_IO_PAGE_SIZE, + xa_mk_value(val), GFP_KERNEL); + WARN_ON_ONCE(ent != old); + } + } + + return dirty; +} + static int mock_domain_read_and_clear_dirty(struct iommu_domain *domain, unsigned long iova, size_t size, unsigned long flags, @@ -198,31 +228,31 @@ static int mock_domain_read_and_clear_dirty(struct iommu_domain *domain, { struct mock_iommu_domain *mock = container_of(domain, struct mock_iommu_domain, domain); - unsigned long i, max = size / MOCK_IO_PAGE_SIZE; - void *ent, *old; + unsigned long end = iova + size; + void *ent; if (!(mock->flags & MOCK_DIRTY_TRACK) && dirty->bitmap) return -EINVAL; - for (i = 0; i < max; i++) { - unsigned long cur = iova + i * MOCK_IO_PAGE_SIZE; + do { + unsigned long pgsize = MOCK_IO_PAGE_SIZE; + unsigned long head; - ent = xa_load(&mock->pfns, cur / MOCK_IO_PAGE_SIZE); - if (ent && (xa_to_value(ent) & MOCK_PFN_DIRTY_IOVA)) { - /* Clear dirty */ - if (!(flags & IOMMU_DIRTY_NO_CLEAR)) { - unsigned long val; - - val = xa_to_value(ent) & ~MOCK_PFN_DIRTY_IOVA; - old = xa_store(&mock->pfns, - cur / MOCK_IO_PAGE_SIZE, - xa_mk_value(val), GFP_KERNEL); - WARN_ON_ONCE(ent != old); - } - iommu_dirty_bitmap_record(dirty, cur, - MOCK_IO_PAGE_SIZE); + ent = xa_load(&mock->pfns, iova / MOCK_IO_PAGE_SIZE); + if (!ent) { + iova += pgsize; + continue; } - } + + if (xa_to_value(ent) & MOCK_PFN_HUGE_IOVA) + pgsize = MOCK_HUGE_PAGE_SIZE; + head = iova & ~(pgsize - 1); + + /* Clear dirty */ + if (mock_test_and_clear_dirty(mock, head, pgsize, flags)) + iommu_dirty_bitmap_record(dirty, head, pgsize); + iova = head + pgsize; + } while (iova < end); return 0; } @@ -234,6 +264,7 @@ const struct iommu_dirty_ops dirty_ops = { static struct iommu_domain *mock_domain_alloc_paging(struct device *dev) { + struct mock_dev *mdev = container_of(dev, struct mock_dev, dev); struct mock_iommu_domain *mock; mock = kzalloc(sizeof(*mock), GFP_KERNEL); @@ -242,6 +273,8 @@ static struct iommu_domain *mock_domain_alloc_paging(struct device *dev) mock->domain.geometry.aperture_start = MOCK_APERTURE_START; mock->domain.geometry.aperture_end = MOCK_APERTURE_LAST; mock->domain.pgsize_bitmap = MOCK_IO_PAGE_SIZE; + if (dev && mdev->flags & MOCK_FLAGS_DEVICE_HUGE_IOVA) + mock->domain.pgsize_bitmap |= MOCK_HUGE_PAGE_SIZE; mock->domain.ops = mock_ops.default_domain_ops; mock->domain.type = IOMMU_DOMAIN_UNMANAGED; xa_init(&mock->pfns); @@ -287,7 +320,7 @@ mock_domain_alloc_user(struct device *dev, u32 flags, return ERR_PTR(-EOPNOTSUPP); if (user_data || (has_dirty_flag && no_dirty_ops)) return ERR_PTR(-EOPNOTSUPP); - domain = mock_domain_alloc_paging(NULL); + domain = mock_domain_alloc_paging(dev); if (!domain) return ERR_PTR(-ENOMEM); if (has_dirty_flag) @@ -350,6 +383,9 @@ static int mock_domain_map_pages(struct iommu_domain *domain, if (pgcount == 1 && cur + MOCK_IO_PAGE_SIZE == pgsize) flags = MOCK_PFN_LAST_IOVA; + if (pgsize != MOCK_IO_PAGE_SIZE) { + flags |= MOCK_PFN_HUGE_IOVA; + } old = xa_store(&mock->pfns, iova / MOCK_IO_PAGE_SIZE, xa_mk_value((paddr / MOCK_IO_PAGE_SIZE) | flags), @@ -604,7 +640,8 @@ static struct mock_dev *mock_dev_create(unsigned long dev_flags) struct mock_dev *mdev; int rc; - if (dev_flags & ~(MOCK_FLAGS_DEVICE_NO_DIRTY)) + if (dev_flags & + ~(MOCK_FLAGS_DEVICE_NO_DIRTY | MOCK_FLAGS_DEVICE_HUGE_IOVA)) return ERR_PTR(-EINVAL); mdev = kzalloc(sizeof(*mdev), GFP_KERNEL); diff --git a/drivers/md/md.c b/drivers/md/md.c index 2266358d8074..9e41a9aaba8b 100644 --- a/drivers/md/md.c +++ b/drivers/md/md.c @@ -579,8 +579,12 @@ static void submit_flushes(struct work_struct *ws) rcu_read_lock(); } rcu_read_unlock(); - if (atomic_dec_and_test(&mddev->flush_pending)) + if (atomic_dec_and_test(&mddev->flush_pending)) { + /* The pair is percpu_ref_get() from md_flush_request() */ + percpu_ref_put(&mddev->active_io); + queue_work(md_wq, &mddev->flush_work); + } } static void md_submit_flush_data(struct work_struct *ws) @@ -8788,12 +8792,16 @@ void md_do_sync(struct md_thread *thread) int ret; /* just incase thread restarts... */ - if (test_bit(MD_RECOVERY_DONE, &mddev->recovery) || - test_bit(MD_RECOVERY_WAIT, &mddev->recovery)) + if (test_bit(MD_RECOVERY_DONE, &mddev->recovery)) return; - if (!md_is_rdwr(mddev)) {/* never try to sync a read-only array */ + + if (test_bit(MD_RECOVERY_INTR, &mddev->recovery)) + goto skip; + + if (test_bit(MD_RECOVERY_WAIT, &mddev->recovery) || + !md_is_rdwr(mddev)) {/* never try to sync a read-only array */ set_bit(MD_RECOVERY_INTR, &mddev->recovery); - return; + goto skip; } if (mddev_is_clustered(mddev)) { @@ -9368,13 +9376,19 @@ static void md_start_sync(struct work_struct *ws) struct mddev *mddev = container_of(ws, struct mddev, sync_work); int spares = 0; bool suspend = false; + char *name; - if (md_spares_need_change(mddev)) + /* + * If reshape is still in progress, spares won't be added or removed + * from conf until reshape is done. + */ + if (mddev->reshape_position == MaxSector && + md_spares_need_change(mddev)) { suspend = true; + mddev_suspend(mddev, false); + } - suspend ? mddev_suspend_and_lock_nointr(mddev) : - mddev_lock_nointr(mddev); - + mddev_lock_nointr(mddev); if (!md_is_rdwr(mddev)) { /* * On a read-only array we can: @@ -9400,8 +9414,10 @@ static void md_start_sync(struct work_struct *ws) if (spares) md_bitmap_write_all(mddev->bitmap); + name = test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery) ? + "reshape" : "resync"; rcu_assign_pointer(mddev->sync_thread, - md_register_thread(md_do_sync, mddev, "resync")); + md_register_thread(md_do_sync, mddev, name)); if (!mddev->sync_thread) { pr_warn("%s: could not start resync thread...\n", mdname(mddev)); @@ -9445,6 +9461,20 @@ not_running: sysfs_notify_dirent_safe(mddev->sysfs_action); } +static void unregister_sync_thread(struct mddev *mddev) +{ + if (!test_bit(MD_RECOVERY_DONE, &mddev->recovery)) { + /* resync/recovery still happening */ + clear_bit(MD_RECOVERY_NEEDED, &mddev->recovery); + return; + } + + if (WARN_ON_ONCE(!mddev->sync_thread)) + return; + + md_reap_sync_thread(mddev); +} + /* * This routine is regularly called by all per-raid-array threads to * deal with generic issues like resync and super-block update. @@ -9469,9 +9499,6 @@ not_running: */ void md_check_recovery(struct mddev *mddev) { - if (READ_ONCE(mddev->suspended)) - return; - if (mddev->bitmap) md_bitmap_daemon_work(mddev); @@ -9485,7 +9512,8 @@ void md_check_recovery(struct mddev *mddev) } if (!md_is_rdwr(mddev) && - !test_bit(MD_RECOVERY_NEEDED, &mddev->recovery)) + !test_bit(MD_RECOVERY_NEEDED, &mddev->recovery) && + !test_bit(MD_RECOVERY_DONE, &mddev->recovery)) return; if ( ! ( (mddev->sb_flags & ~ (1<<MD_SB_CHANGE_PENDING)) || @@ -9507,8 +9535,7 @@ void md_check_recovery(struct mddev *mddev) struct md_rdev *rdev; if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) { - /* sync_work already queued. */ - clear_bit(MD_RECOVERY_NEEDED, &mddev->recovery); + unregister_sync_thread(mddev); goto unlock; } @@ -9571,16 +9598,7 @@ void md_check_recovery(struct mddev *mddev) * still set. */ if (test_bit(MD_RECOVERY_RUNNING, &mddev->recovery)) { - if (!test_bit(MD_RECOVERY_DONE, &mddev->recovery)) { - /* resync/recovery still happening */ - clear_bit(MD_RECOVERY_NEEDED, &mddev->recovery); - goto unlock; - } - - if (WARN_ON_ONCE(!mddev->sync_thread)) - goto unlock; - - md_reap_sync_thread(mddev); + unregister_sync_thread(mddev); goto unlock; } diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c index 7412066ea22c..a5f8419e2df1 100644 --- a/drivers/md/raid10.c +++ b/drivers/md/raid10.c @@ -4175,11 +4175,7 @@ static int raid10_run(struct mddev *mddev) clear_bit(MD_RECOVERY_SYNC, &mddev->recovery); clear_bit(MD_RECOVERY_CHECK, &mddev->recovery); set_bit(MD_RECOVERY_RESHAPE, &mddev->recovery); - set_bit(MD_RECOVERY_RUNNING, &mddev->recovery); - rcu_assign_pointer(mddev->sync_thread, - md_register_thread(md_do_sync, mddev, "reshape")); - if (!mddev->sync_thread) - goto out_free_conf; + set_bit(MD_RECOVERY_NEEDED, &mddev->recovery); } return 0; @@ -4573,16 +4569,8 @@ out: clear_bit(MD_RECOVERY_CHECK, &mddev->recovery); clear_bit(MD_RECOVERY_DONE, &mddev->recovery); set_bit(MD_RECOVERY_RESHAPE, &mddev->recovery); - set_bit(MD_RECOVERY_RUNNING, &mddev->recovery); - - rcu_assign_pointer(mddev->sync_thread, - md_register_thread(md_do_sync, mddev, "reshape")); - if (!mddev->sync_thread) { - ret = -EAGAIN; - goto abort; - } + set_bit(MD_RECOVERY_NEEDED, &mddev->recovery); conf->reshape_checkpoint = jiffies; - md_wakeup_thread(mddev->sync_thread); md_new_event(); return 0; diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c index 8497880135ee..6a7a32f7fb91 100644 --- a/drivers/md/raid5.c +++ b/drivers/md/raid5.c @@ -7936,11 +7936,7 @@ static int raid5_run(struct mddev *mddev) clear_bit(MD_RECOVERY_SYNC, &mddev->recovery); clear_bit(MD_RECOVERY_CHECK, &mddev->recovery); set_bit(MD_RECOVERY_RESHAPE, &mddev->recovery); - set_bit(MD_RECOVERY_RUNNING, &mddev->recovery); - rcu_assign_pointer(mddev->sync_thread, - md_register_thread(md_do_sync, mddev, "reshape")); - if (!mddev->sync_thread) - goto abort; + set_bit(MD_RECOVERY_NEEDED, &mddev->recovery); } /* Ok, everything is just fine now */ @@ -8506,29 +8502,8 @@ static int raid5_start_reshape(struct mddev *mddev) clear_bit(MD_RECOVERY_CHECK, &mddev->recovery); clear_bit(MD_RECOVERY_DONE, &mddev->recovery); set_bit(MD_RECOVERY_RESHAPE, &mddev->recovery); - set_bit(MD_RECOVERY_RUNNING, &mddev->recovery); - rcu_assign_pointer(mddev->sync_thread, - md_register_thread(md_do_sync, mddev, "reshape")); - if (!mddev->sync_thread) { - mddev->recovery = 0; - spin_lock_irq(&conf->device_lock); - write_seqcount_begin(&conf->gen_lock); - mddev->raid_disks = conf->raid_disks = conf->previous_raid_disks; - mddev->new_chunk_sectors = - conf->chunk_sectors = conf->prev_chunk_sectors; - mddev->new_layout = conf->algorithm = conf->prev_algo; - rdev_for_each(rdev, mddev) - rdev->new_data_offset = rdev->data_offset; - smp_wmb(); - conf->generation --; - conf->reshape_progress = MaxSector; - mddev->reshape_position = MaxSector; - write_seqcount_end(&conf->gen_lock); - spin_unlock_irq(&conf->device_lock); - return -EAGAIN; - } + set_bit(MD_RECOVERY_NEEDED, &mddev->recovery); conf->reshape_checkpoint = jiffies; - md_wakeup_thread(mddev->sync_thread); md_new_event(); return 0; } diff --git a/drivers/net/ethernet/adi/Kconfig b/drivers/net/ethernet/adi/Kconfig index da3bdd302502..c91b4dcef4ec 100644 --- a/drivers/net/ethernet/adi/Kconfig +++ b/drivers/net/ethernet/adi/Kconfig @@ -7,6 +7,7 @@ config NET_VENDOR_ADI bool "Analog Devices devices" default y depends on SPI + select PHYLIB help If you have a network (Ethernet) card belonging to this class, say Y. diff --git a/drivers/net/ethernet/broadcom/asp2/bcmasp.c b/drivers/net/ethernet/broadcom/asp2/bcmasp.c index 29b04a274d07..80245c65cc90 100644 --- a/drivers/net/ethernet/broadcom/asp2/bcmasp.c +++ b/drivers/net/ethernet/broadcom/asp2/bcmasp.c @@ -535,9 +535,6 @@ int bcmasp_netfilt_get_all_active(struct bcmasp_intf *intf, u32 *rule_locs, int j = 0, i; for (i = 0; i < NUM_NET_FILTERS; i++) { - if (j == *rule_cnt) - return -EMSGSIZE; - if (!priv->net_filters[i].claimed || priv->net_filters[i].port != intf->port) continue; @@ -547,6 +544,9 @@ int bcmasp_netfilt_get_all_active(struct bcmasp_intf *intf, u32 *rule_locs, priv->net_filters[i - 1].wake_filter) continue; + if (j == *rule_cnt) + return -EMSGSIZE; + rule_locs[j++] = priv->net_filters[i].fs.location; } diff --git a/drivers/net/ethernet/broadcom/asp2/bcmasp_intf.c b/drivers/net/ethernet/broadcom/asp2/bcmasp_intf.c index f59557b0cd51..6ad1366270f7 100644 --- a/drivers/net/ethernet/broadcom/asp2/bcmasp_intf.c +++ b/drivers/net/ethernet/broadcom/asp2/bcmasp_intf.c @@ -1050,6 +1050,9 @@ static int bcmasp_netif_init(struct net_device *dev, bool phy_connect) netdev_err(dev, "could not attach to PHY\n"); goto err_phy_disable; } + + /* Indicate that the MAC is responsible for PHY PM */ + phydev->mac_managed_pm = true; } else if (!intf->wolopts) { ret = phy_resume(dev->phydev); if (ret) diff --git a/drivers/net/ethernet/cisco/enic/vnic_vic.c b/drivers/net/ethernet/cisco/enic/vnic_vic.c index 20fcb20b42ed..66b577835338 100644 --- a/drivers/net/ethernet/cisco/enic/vnic_vic.c +++ b/drivers/net/ethernet/cisco/enic/vnic_vic.c @@ -49,7 +49,8 @@ int vic_provinfo_add_tlv(struct vic_provinfo *vp, u16 type, u16 length, tlv->type = htons(type); tlv->length = htons(length); - memcpy(tlv->value, value, length); + unsafe_memcpy(tlv->value, value, length, + /* Flexible array of flexible arrays */); vp->num_tlvs = htonl(ntohl(vp->num_tlvs) + 1); vp->length = htonl(ntohl(vp->length) + diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c index e5d6156655ba..516adb50f9f6 100644 --- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c +++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c @@ -415,6 +415,10 @@ static void npc_fixup_vf_rule(struct rvu *rvu, struct npc_mcam *mcam, return; } + /* AF modifies given action iff PF/VF has requested for it */ + if ((entry->action & 0xFULL) != NIX_RX_ACTION_DEFAULT) + return; + /* copy VF default entry action to the VF mcam entry */ rx_action = npc_get_default_entry_action(rvu, mcam, blkaddr, target_func); diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_main.c b/drivers/net/ethernet/microchip/sparx5/sparx5_main.c index d1f7fc8b1b71..3c066b62e689 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_main.c +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_main.c @@ -757,6 +757,7 @@ static int mchp_sparx5_probe(struct platform_device *pdev) platform_set_drvdata(pdev, sparx5); sparx5->pdev = pdev; sparx5->dev = &pdev->dev; + spin_lock_init(&sparx5->tx_lock); /* Do switch core reset if available */ reset = devm_reset_control_get_optional_shared(&pdev->dev, "switch"); diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_main.h b/drivers/net/ethernet/microchip/sparx5/sparx5_main.h index 6f565c0c0c3d..316fed5f2735 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_main.h +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_main.h @@ -280,6 +280,7 @@ struct sparx5 { int xtr_irq; /* Frame DMA */ int fdma_irq; + spinlock_t tx_lock; /* lock for frame transmission */ struct sparx5_rx rx; struct sparx5_tx tx; /* PTP */ diff --git a/drivers/net/ethernet/microchip/sparx5/sparx5_packet.c b/drivers/net/ethernet/microchip/sparx5/sparx5_packet.c index 6db6ac6a3bbc..ac7e1cffbcec 100644 --- a/drivers/net/ethernet/microchip/sparx5/sparx5_packet.c +++ b/drivers/net/ethernet/microchip/sparx5/sparx5_packet.c @@ -244,10 +244,12 @@ netdev_tx_t sparx5_port_xmit_impl(struct sk_buff *skb, struct net_device *dev) } skb_tx_timestamp(skb); + spin_lock(&sparx5->tx_lock); if (sparx5->fdma_irq > 0) ret = sparx5_fdma_xmit(sparx5, ifh, skb); else ret = sparx5_inject(sparx5, ifh, skb, dev); + spin_unlock(&sparx5->tx_lock); if (ret == -EBUSY) goto busy; diff --git a/drivers/net/ethernet/pensando/ionic/ionic_bus_pci.c b/drivers/net/ethernet/pensando/ionic/ionic_bus_pci.c index c49aa358e424..10a9d80db32c 100644 --- a/drivers/net/ethernet/pensando/ionic/ionic_bus_pci.c +++ b/drivers/net/ethernet/pensando/ionic/ionic_bus_pci.c @@ -223,7 +223,7 @@ static void ionic_clear_pci(struct ionic *ionic) ionic_unmap_bars(ionic); pci_release_regions(ionic->pdev); - if (atomic_read(&ionic->pdev->enable_cnt) > 0) + if (pci_is_enabled(ionic->pdev)) pci_disable_device(ionic->pdev); } diff --git a/drivers/net/ethernet/stmicro/stmmac/hwif.c b/drivers/net/ethernet/stmicro/stmmac/hwif.c index 1bd34b2a47e8..29367105df54 100644 --- a/drivers/net/ethernet/stmicro/stmmac/hwif.c +++ b/drivers/net/ethernet/stmicro/stmmac/hwif.c @@ -224,7 +224,7 @@ static const struct stmmac_hwif_entry { .regs = { .ptp_off = PTP_GMAC4_OFFSET, .mmc_off = MMC_GMAC4_OFFSET, - .est_off = EST_XGMAC_OFFSET, + .est_off = EST_GMAC4_OFFSET, }, .desc = &dwmac4_desc_ops, .dma = &dwmac410_dma_ops, diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 75d029704503..e80d77bd9f1f 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -6059,11 +6059,6 @@ static irqreturn_t stmmac_mac_interrupt(int irq, void *dev_id) struct net_device *dev = (struct net_device *)dev_id; struct stmmac_priv *priv = netdev_priv(dev); - if (unlikely(!dev)) { - netdev_err(priv->dev, "%s: invalid dev pointer\n", __func__); - return IRQ_NONE; - } - /* Check if adapter is up */ if (test_bit(STMMAC_DOWN, &priv->state)) return IRQ_HANDLED; @@ -6079,11 +6074,6 @@ static irqreturn_t stmmac_safety_interrupt(int irq, void *dev_id) struct net_device *dev = (struct net_device *)dev_id; struct stmmac_priv *priv = netdev_priv(dev); - if (unlikely(!dev)) { - netdev_err(priv->dev, "%s: invalid dev pointer\n", __func__); - return IRQ_NONE; - } - /* Check if adapter is up */ if (test_bit(STMMAC_DOWN, &priv->state)) return IRQ_HANDLED; @@ -6105,11 +6095,6 @@ static irqreturn_t stmmac_msi_intr_tx(int irq, void *data) dma_conf = container_of(tx_q, struct stmmac_dma_conf, tx_queue[chan]); priv = container_of(dma_conf, struct stmmac_priv, dma_conf); - if (unlikely(!data)) { - netdev_err(priv->dev, "%s: invalid dev pointer\n", __func__); - return IRQ_NONE; - } - /* Check if adapter is up */ if (test_bit(STMMAC_DOWN, &priv->state)) return IRQ_HANDLED; @@ -6136,11 +6121,6 @@ static irqreturn_t stmmac_msi_intr_rx(int irq, void *data) dma_conf = container_of(rx_q, struct stmmac_dma_conf, rx_queue[chan]); priv = container_of(dma_conf, struct stmmac_priv, dma_conf); - if (unlikely(!data)) { - netdev_err(priv->dev, "%s: invalid dev pointer\n", __func__); - return IRQ_NONE; - } - /* Check if adapter is up */ if (test_bit(STMMAC_DOWN, &priv->state)) return IRQ_HANDLED; diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c index b1919278e931..2129ae42c703 100644 --- a/drivers/net/gtp.c +++ b/drivers/net/gtp.c @@ -1907,20 +1907,20 @@ static int __init gtp_init(void) if (err < 0) goto error_out; - err = genl_register_family(>p_genl_family); + err = register_pernet_subsys(>p_net_ops); if (err < 0) goto unreg_rtnl_link; - err = register_pernet_subsys(>p_net_ops); + err = genl_register_family(>p_genl_family); if (err < 0) - goto unreg_genl_family; + goto unreg_pernet_subsys; pr_info("GTP module loaded (pdp ctx size %zd bytes)\n", sizeof(struct pdp_ctx)); return 0; -unreg_genl_family: - genl_unregister_family(>p_genl_family); +unreg_pernet_subsys: + unregister_pernet_subsys(>p_net_ops); unreg_rtnl_link: rtnl_link_unregister(>p_link_ops); error_out: diff --git a/drivers/net/ipa/ipa_interrupt.c b/drivers/net/ipa/ipa_interrupt.c index 4bc05948f772..a78c692f2d3c 100644 --- a/drivers/net/ipa/ipa_interrupt.c +++ b/drivers/net/ipa/ipa_interrupt.c @@ -212,7 +212,7 @@ void ipa_interrupt_suspend_clear_all(struct ipa_interrupt *interrupt) u32 unit_count; u32 unit; - unit_count = roundup(ipa->endpoint_count, 32); + unit_count = DIV_ROUND_UP(ipa->endpoint_count, 32); for (unit = 0; unit < unit_count; unit++) { const struct reg *reg; u32 val; diff --git a/drivers/net/phy/realtek.c b/drivers/net/phy/realtek.c index 894172a3e15f..337899c69738 100644 --- a/drivers/net/phy/realtek.c +++ b/drivers/net/phy/realtek.c @@ -421,9 +421,11 @@ static int rtl8211f_config_init(struct phy_device *phydev) ERR_PTR(ret)); return ret; } + + return genphy_soft_reset(phydev); } - return genphy_soft_reset(phydev); + return 0; } static int rtl821x_suspend(struct phy_device *phydev) diff --git a/drivers/platform/x86/amd/pmf/core.c b/drivers/platform/x86/amd/pmf/core.c index feaa09f5b35a..4f734e049f4a 100644 --- a/drivers/platform/x86/amd/pmf/core.c +++ b/drivers/platform/x86/amd/pmf/core.c @@ -296,7 +296,8 @@ static int amd_pmf_suspend_handler(struct device *dev) { struct amd_pmf_dev *pdev = dev_get_drvdata(dev); - kfree(pdev->buf); + if (pdev->smart_pc_enabled) + cancel_delayed_work_sync(&pdev->pb_work); return 0; } @@ -312,6 +313,9 @@ static int amd_pmf_resume_handler(struct device *dev) return ret; } + if (pdev->smart_pc_enabled) + schedule_delayed_work(&pdev->pb_work, msecs_to_jiffies(2000)); + return 0; } @@ -330,9 +334,14 @@ static void amd_pmf_init_features(struct amd_pmf_dev *dev) dev_dbg(dev->dev, "SPS enabled and Platform Profiles registered\n"); } - if (!amd_pmf_init_smart_pc(dev)) { + amd_pmf_init_smart_pc(dev); + if (dev->smart_pc_enabled) { dev_dbg(dev->dev, "Smart PC Solution Enabled\n"); - } else if (is_apmf_func_supported(dev, APMF_FUNC_AUTO_MODE)) { + /* If Smart PC is enabled, no need to check for other features */ + return; + } + + if (is_apmf_func_supported(dev, APMF_FUNC_AUTO_MODE)) { amd_pmf_init_auto_mode(dev); dev_dbg(dev->dev, "Auto Mode Init done\n"); } else if (is_apmf_func_supported(dev, APMF_FUNC_DYN_SLIDER_AC) || @@ -351,7 +360,7 @@ static void amd_pmf_deinit_features(struct amd_pmf_dev *dev) amd_pmf_deinit_sps(dev); } - if (!dev->smart_pc_enabled) { + if (dev->smart_pc_enabled) { amd_pmf_deinit_smart_pc(dev); } else if (is_apmf_func_supported(dev, APMF_FUNC_AUTO_MODE)) { amd_pmf_deinit_auto_mode(dev); diff --git a/drivers/platform/x86/amd/pmf/pmf.h b/drivers/platform/x86/amd/pmf/pmf.h index 16999c5b334f..66cae1cca73c 100644 --- a/drivers/platform/x86/amd/pmf/pmf.h +++ b/drivers/platform/x86/amd/pmf/pmf.h @@ -441,11 +441,6 @@ struct apmf_dyn_slider_output { struct apmf_cnqf_power_set ps[APMF_CNQF_MAX]; } __packed; -enum smart_pc_status { - PMF_SMART_PC_ENABLED, - PMF_SMART_PC_DISABLED, -}; - /* Smart PC - TA internals */ enum system_state { SYSTEM_STATE_S0i3, diff --git a/drivers/platform/x86/amd/pmf/tee-if.c b/drivers/platform/x86/amd/pmf/tee-if.c index f8c0177afb0d..8527dca9cf56 100644 --- a/drivers/platform/x86/amd/pmf/tee-if.c +++ b/drivers/platform/x86/amd/pmf/tee-if.c @@ -252,15 +252,17 @@ static int amd_pmf_start_policy_engine(struct amd_pmf_dev *dev) cookie = readl(dev->policy_buf + POLICY_COOKIE_OFFSET); length = readl(dev->policy_buf + POLICY_COOKIE_LEN); - if (cookie != POLICY_SIGN_COOKIE || !length) + if (cookie != POLICY_SIGN_COOKIE || !length) { + dev_dbg(dev->dev, "cookie doesn't match\n"); return -EINVAL; + } /* Update the actual length */ dev->policy_sz = length + 512; res = amd_pmf_invoke_cmd_init(dev); if (res == TA_PMF_TYPE_SUCCESS) { /* Now its safe to announce that smart pc is enabled */ - dev->smart_pc_enabled = PMF_SMART_PC_ENABLED; + dev->smart_pc_enabled = true; /* * Start collecting the data from TA FW after a small delay * or else, we might end up getting stale values. @@ -268,7 +270,7 @@ static int amd_pmf_start_policy_engine(struct amd_pmf_dev *dev) schedule_delayed_work(&dev->pb_work, msecs_to_jiffies(pb_actions_ms * 3)); } else { dev_err(dev->dev, "ta invoke cmd init failed err: %x\n", res); - dev->smart_pc_enabled = PMF_SMART_PC_DISABLED; + dev->smart_pc_enabled = false; return res; } @@ -336,25 +338,6 @@ static void amd_pmf_remove_pb(struct amd_pmf_dev *dev) {} static void amd_pmf_hex_dump_pb(struct amd_pmf_dev *dev) {} #endif -static int amd_pmf_get_bios_buffer(struct amd_pmf_dev *dev) -{ - dev->policy_buf = kzalloc(dev->policy_sz, GFP_KERNEL); - if (!dev->policy_buf) - return -ENOMEM; - - dev->policy_base = devm_ioremap(dev->dev, dev->policy_addr, dev->policy_sz); - if (!dev->policy_base) - return -ENOMEM; - - memcpy(dev->policy_buf, dev->policy_base, dev->policy_sz); - - amd_pmf_hex_dump_pb(dev); - if (pb_side_load) - amd_pmf_open_pb(dev, dev->dbgfs_dir); - - return amd_pmf_start_policy_engine(dev); -} - static int amd_pmf_amdtee_ta_match(struct tee_ioctl_version_data *ver, const void *data) { return ver->impl_id == TEE_IMPL_ID_AMDTEE; @@ -453,22 +436,57 @@ int amd_pmf_init_smart_pc(struct amd_pmf_dev *dev) return ret; INIT_DELAYED_WORK(&dev->pb_work, amd_pmf_invoke_cmd); - amd_pmf_set_dram_addr(dev, true); - amd_pmf_get_bios_buffer(dev); + + ret = amd_pmf_set_dram_addr(dev, true); + if (ret) + goto error; + + dev->policy_base = devm_ioremap(dev->dev, dev->policy_addr, dev->policy_sz); + if (!dev->policy_base) { + ret = -ENOMEM; + goto error; + } + + dev->policy_buf = kzalloc(dev->policy_sz, GFP_KERNEL); + if (!dev->policy_buf) { + ret = -ENOMEM; + goto error; + } + + memcpy(dev->policy_buf, dev->policy_base, dev->policy_sz); + + amd_pmf_hex_dump_pb(dev); + dev->prev_data = kzalloc(sizeof(*dev->prev_data), GFP_KERNEL); if (!dev->prev_data) - return -ENOMEM; + goto error; + + ret = amd_pmf_start_policy_engine(dev); + if (ret) + goto error; - return dev->smart_pc_enabled; + if (pb_side_load) + amd_pmf_open_pb(dev, dev->dbgfs_dir); + + return 0; + +error: + amd_pmf_deinit_smart_pc(dev); + + return ret; } void amd_pmf_deinit_smart_pc(struct amd_pmf_dev *dev) { - if (pb_side_load) + if (pb_side_load && dev->esbin) amd_pmf_remove_pb(dev); + cancel_delayed_work_sync(&dev->pb_work); kfree(dev->prev_data); + dev->prev_data = NULL; kfree(dev->policy_buf); - cancel_delayed_work_sync(&dev->pb_work); + dev->policy_buf = NULL; + kfree(dev->buf); + dev->buf = NULL; amd_pmf_tee_deinit(dev); } diff --git a/drivers/platform/x86/intel/int0002_vgpio.c b/drivers/platform/x86/intel/int0002_vgpio.c index b6708bab7c53..527d8fbc7cc1 100644 --- a/drivers/platform/x86/intel/int0002_vgpio.c +++ b/drivers/platform/x86/intel/int0002_vgpio.c @@ -196,7 +196,7 @@ static int int0002_probe(struct platform_device *pdev) * IRQs into gpiolib. */ ret = devm_request_irq(dev, irq, int0002_irq, - IRQF_SHARED, "INT0002", chip); + IRQF_ONESHOT | IRQF_SHARED, "INT0002", chip); if (ret) { dev_err(dev, "Error requesting IRQ %d: %d\n", irq, ret); return ret; diff --git a/drivers/platform/x86/intel/vbtn.c b/drivers/platform/x86/intel/vbtn.c index 210b0a81b7ec..084c355c86f5 100644 --- a/drivers/platform/x86/intel/vbtn.c +++ b/drivers/platform/x86/intel/vbtn.c @@ -200,9 +200,6 @@ static void notify_handler(acpi_handle handle, u32 event, void *context) autorelease = val && (!ke_rel || ke_rel->type == KE_IGNORE); sparse_keymap_report_event(input_dev, event, val, autorelease); - - /* Some devices need this to report further events */ - acpi_evaluate_object(handle, "VBDL", NULL, NULL); } /* diff --git a/drivers/platform/x86/serdev_helpers.h b/drivers/platform/x86/serdev_helpers.h new file mode 100644 index 000000000000..bcf3a0c356ea --- /dev/null +++ b/drivers/platform/x86/serdev_helpers.h @@ -0,0 +1,80 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * In some cases UART attached devices which require an in kernel driver, + * e.g. UART attached Bluetooth HCIs are described in the ACPI tables + * by an ACPI device with a broken or missing UartSerialBusV2() resource. + * + * This causes the kernel to create a /dev/ttyS# char-device for the UART + * instead of creating an in kernel serdev-controller + serdev-device pair + * for the in kernel driver. + * + * The quirk handling in acpi_quirk_skip_serdev_enumeration() makes the kernel + * create a serdev-controller device for these UARTs instead of a /dev/ttyS#. + * + * Instantiating the actual serdev-device to bind to is up to pdx86 code, + * this header provides a helper for getting the serdev-controller device. + */ +#include <linux/acpi.h> +#include <linux/device.h> +#include <linux/err.h> +#include <linux/printk.h> +#include <linux/sprintf.h> +#include <linux/string.h> + +static inline struct device * +get_serdev_controller(const char *serial_ctrl_hid, + const char *serial_ctrl_uid, + int serial_ctrl_port, + const char *serdev_ctrl_name) +{ + struct device *ctrl_dev, *child; + struct acpi_device *ctrl_adev; + char name[32]; + int i; + + ctrl_adev = acpi_dev_get_first_match_dev(serial_ctrl_hid, serial_ctrl_uid, -1); + if (!ctrl_adev) { + pr_err("error could not get %s/%s serial-ctrl adev\n", + serial_ctrl_hid, serial_ctrl_uid); + return ERR_PTR(-ENODEV); + } + + /* get_first_physical_node() returns a weak ref */ + ctrl_dev = get_device(acpi_get_first_physical_node(ctrl_adev)); + if (!ctrl_dev) { + pr_err("error could not get %s/%s serial-ctrl physical node\n", + serial_ctrl_hid, serial_ctrl_uid); + ctrl_dev = ERR_PTR(-ENODEV); + goto put_ctrl_adev; + } + + /* Walk host -> uart-ctrl -> port -> serdev-ctrl */ + for (i = 0; i < 3; i++) { + switch (i) { + case 0: + snprintf(name, sizeof(name), "%s:0", dev_name(ctrl_dev)); + break; + case 1: + snprintf(name, sizeof(name), "%s.%d", + dev_name(ctrl_dev), serial_ctrl_port); + break; + case 2: + strscpy(name, serdev_ctrl_name, sizeof(name)); + break; + } + + child = device_find_child_by_name(ctrl_dev, name); + put_device(ctrl_dev); + if (!child) { + pr_err("error could not find '%s' device\n", name); + ctrl_dev = ERR_PTR(-ENODEV); + goto put_ctrl_adev; + } + + ctrl_dev = child; + } + +put_ctrl_adev: + acpi_dev_put(ctrl_adev); + return ctrl_dev; +} diff --git a/drivers/platform/x86/think-lmi.c b/drivers/platform/x86/think-lmi.c index 3a396b763c49..ce3e08815a8e 100644 --- a/drivers/platform/x86/think-lmi.c +++ b/drivers/platform/x86/think-lmi.c @@ -1009,7 +1009,16 @@ static ssize_t current_value_store(struct kobject *kobj, * Note - this sets the variable and then the password as separate * WMI calls. Function tlmi_save_bios_settings will error if the * password is incorrect. + * Workstation's require the opcode to be set before changing the + * attribute. */ + if (tlmi_priv.pwd_admin->valid && tlmi_priv.pwd_admin->password[0]) { + ret = tlmi_opcode_setting("WmiOpcodePasswordAdmin", + tlmi_priv.pwd_admin->password); + if (ret) + goto out; + } + set_str = kasprintf(GFP_KERNEL, "%s,%s;", setting->display_name, new_setting); if (!set_str) { @@ -1021,17 +1030,10 @@ static ssize_t current_value_store(struct kobject *kobj, if (ret) goto out; - if (tlmi_priv.save_mode == TLMI_SAVE_BULK) { + if (tlmi_priv.save_mode == TLMI_SAVE_BULK) tlmi_priv.save_required = true; - } else { - if (tlmi_priv.pwd_admin->valid && tlmi_priv.pwd_admin->password[0]) { - ret = tlmi_opcode_setting("WmiOpcodePasswordAdmin", - tlmi_priv.pwd_admin->password); - if (ret) - goto out; - } + else ret = tlmi_save_bios_settings(""); - } } else { /* old non-opcode based authentication method (deprecated) */ if (tlmi_priv.pwd_admin->valid && tlmi_priv.pwd_admin->password[0]) { auth_str = kasprintf(GFP_KERNEL, "%s,%s,%s;", diff --git a/drivers/platform/x86/thinkpad_acpi.c b/drivers/platform/x86/thinkpad_acpi.c index c4895e9bc714..5ecd9d33250d 100644 --- a/drivers/platform/x86/thinkpad_acpi.c +++ b/drivers/platform/x86/thinkpad_acpi.c @@ -10308,6 +10308,7 @@ static int convert_dytc_to_profile(int funcmode, int dytcmode, return 0; default: /* Unknown function */ + pr_debug("unknown function 0x%x\n", funcmode); return -EOPNOTSUPP; } return 0; @@ -10493,8 +10494,8 @@ static void dytc_profile_refresh(void) return; perfmode = (output >> DYTC_GET_MODE_BIT) & 0xF; - convert_dytc_to_profile(funcmode, perfmode, &profile); - if (profile != dytc_current_profile) { + err = convert_dytc_to_profile(funcmode, perfmode, &profile); + if (!err && profile != dytc_current_profile) { dytc_current_profile = profile; platform_profile_notify(); } diff --git a/drivers/platform/x86/touchscreen_dmi.c b/drivers/platform/x86/touchscreen_dmi.c index 7aee5e9ff2b8..975cf24ae359 100644 --- a/drivers/platform/x86/touchscreen_dmi.c +++ b/drivers/platform/x86/touchscreen_dmi.c @@ -81,7 +81,7 @@ static const struct property_entry chuwi_hi8_air_props[] = { }; static const struct ts_dmi_data chuwi_hi8_air_data = { - .acpi_name = "MSSL1680:00", + .acpi_name = "MSSL1680", .properties = chuwi_hi8_air_props, }; @@ -415,18 +415,13 @@ static const struct property_entry gdix1001_upside_down_props[] = { { } }; -static const struct ts_dmi_data gdix1001_00_upside_down_data = { - .acpi_name = "GDIX1001:00", - .properties = gdix1001_upside_down_props, -}; - -static const struct ts_dmi_data gdix1001_01_upside_down_data = { - .acpi_name = "GDIX1001:01", +static const struct ts_dmi_data gdix1001_upside_down_data = { + .acpi_name = "GDIX1001", .properties = gdix1001_upside_down_props, }; -static const struct ts_dmi_data gdix1002_00_upside_down_data = { - .acpi_name = "GDIX1002:00", +static const struct ts_dmi_data gdix1002_upside_down_data = { + .acpi_name = "GDIX1002", .properties = gdix1001_upside_down_props, }; @@ -1412,7 +1407,7 @@ const struct dmi_system_id touchscreen_dmi_table[] = { }, { /* Juno Tablet */ - .driver_data = (void *)&gdix1002_00_upside_down_data, + .driver_data = (void *)&gdix1002_upside_down_data, .matches = { DMI_MATCH(DMI_SYS_VENDOR, "Default string"), /* Both product- and board-name being "Default string" is somewhat rare */ @@ -1658,7 +1653,7 @@ const struct dmi_system_id touchscreen_dmi_table[] = { }, { /* Teclast X89 (Android version / BIOS) */ - .driver_data = (void *)&gdix1001_00_upside_down_data, + .driver_data = (void *)&gdix1001_upside_down_data, .matches = { DMI_MATCH(DMI_BOARD_VENDOR, "WISKY"), DMI_MATCH(DMI_BOARD_NAME, "3G062i"), @@ -1666,7 +1661,7 @@ const struct dmi_system_id touchscreen_dmi_table[] = { }, { /* Teclast X89 (Windows version / BIOS) */ - .driver_data = (void *)&gdix1001_01_upside_down_data, + .driver_data = (void *)&gdix1001_upside_down_data, .matches = { /* tPAD is too generic, also match on bios date */ DMI_MATCH(DMI_BOARD_VENDOR, "TECLAST"), @@ -1684,7 +1679,7 @@ const struct dmi_system_id touchscreen_dmi_table[] = { }, { /* Teclast X98 Pro */ - .driver_data = (void *)&gdix1001_00_upside_down_data, + .driver_data = (void *)&gdix1001_upside_down_data, .matches = { /* * Only match BIOS date, because the manufacturers @@ -1788,7 +1783,7 @@ const struct dmi_system_id touchscreen_dmi_table[] = { }, { /* "WinBook TW100" */ - .driver_data = (void *)&gdix1001_00_upside_down_data, + .driver_data = (void *)&gdix1001_upside_down_data, .matches = { DMI_MATCH(DMI_SYS_VENDOR, "WinBook"), DMI_MATCH(DMI_PRODUCT_NAME, "TW100") @@ -1796,7 +1791,7 @@ const struct dmi_system_id touchscreen_dmi_table[] = { }, { /* WinBook TW700 */ - .driver_data = (void *)&gdix1001_00_upside_down_data, + .driver_data = (void *)&gdix1001_upside_down_data, .matches = { DMI_MATCH(DMI_SYS_VENDOR, "WinBook"), DMI_MATCH(DMI_PRODUCT_NAME, "TW700") @@ -1821,7 +1816,7 @@ static void ts_dmi_add_props(struct i2c_client *client) int error; if (has_acpi_companion(dev) && - !strncmp(ts_data->acpi_name, client->name, I2C_NAME_SIZE)) { + strstarts(client->name, ts_data->acpi_name)) { error = device_create_managed_software_node(dev, ts_data->properties, NULL); if (error) dev_err(dev, "failed to add properties: %d\n", error); diff --git a/drivers/platform/x86/x86-android-tablets/core.c b/drivers/platform/x86/x86-android-tablets/core.c index f8221a15575b..a3415f1c0b5f 100644 --- a/drivers/platform/x86/x86-android-tablets/core.c +++ b/drivers/platform/x86/x86-android-tablets/core.c @@ -21,6 +21,7 @@ #include <linux/string.h> #include "x86-android-tablets.h" +#include "../serdev_helpers.h" static struct platform_device *x86_android_tablet_device; @@ -113,6 +114,9 @@ int x86_acpi_irq_helper_get(const struct x86_acpi_irq_data *data) if (irq_type != IRQ_TYPE_NONE && irq_type != irq_get_trigger_type(irq)) irq_set_irq_type(irq, irq_type); + if (data->free_gpio) + devm_gpiod_put(&x86_android_tablet_device->dev, gpiod); + return irq; case X86_ACPI_IRQ_TYPE_PMIC: status = acpi_get_handle(NULL, data->chip, &handle); @@ -229,38 +233,20 @@ static __init int x86_instantiate_spi_dev(const struct x86_dev_info *dev_info, i static __init int x86_instantiate_serdev(const struct x86_serdev_info *info, int idx) { - struct acpi_device *ctrl_adev, *serdev_adev; + struct acpi_device *serdev_adev; struct serdev_device *serdev; struct device *ctrl_dev; int ret = -ENODEV; - ctrl_adev = acpi_dev_get_first_match_dev(info->ctrl_hid, info->ctrl_uid, -1); - if (!ctrl_adev) { - pr_err("error could not get %s/%s ctrl adev\n", - info->ctrl_hid, info->ctrl_uid); - return -ENODEV; - } + ctrl_dev = get_serdev_controller(info->ctrl_hid, info->ctrl_uid, 0, + info->ctrl_devname); + if (IS_ERR(ctrl_dev)) + return PTR_ERR(ctrl_dev); serdev_adev = acpi_dev_get_first_match_dev(info->serdev_hid, NULL, -1); if (!serdev_adev) { pr_err("error could not get %s serdev adev\n", info->serdev_hid); - goto put_ctrl_adev; - } - - /* get_first_physical_node() returns a weak ref, no need to put() it */ - ctrl_dev = acpi_get_first_physical_node(ctrl_adev); - if (!ctrl_dev) { - pr_err("error could not get %s/%s ctrl physical dev\n", - info->ctrl_hid, info->ctrl_uid); - goto put_serdev_adev; - } - - /* ctrl_dev now points to the controller's parent, get the controller */ - ctrl_dev = device_find_child_by_name(ctrl_dev, info->ctrl_devname); - if (!ctrl_dev) { - pr_err("error could not get %s/%s %s ctrl dev\n", - info->ctrl_hid, info->ctrl_uid, info->ctrl_devname); - goto put_serdev_adev; + goto put_ctrl_dev; } serdev = serdev_device_alloc(to_serdev_controller(ctrl_dev)); @@ -283,8 +269,8 @@ static __init int x86_instantiate_serdev(const struct x86_serdev_info *info, int put_serdev_adev: acpi_dev_put(serdev_adev); -put_ctrl_adev: - acpi_dev_put(ctrl_adev); +put_ctrl_dev: + put_device(ctrl_dev); return ret; } diff --git a/drivers/platform/x86/x86-android-tablets/lenovo.c b/drivers/platform/x86/x86-android-tablets/lenovo.c index f1c66a61bfc5..c297391955ad 100644 --- a/drivers/platform/x86/x86-android-tablets/lenovo.c +++ b/drivers/platform/x86/x86-android-tablets/lenovo.c @@ -116,6 +116,7 @@ static const struct x86_i2c_client_info lenovo_yb1_x90_i2c_clients[] __initconst .trigger = ACPI_EDGE_SENSITIVE, .polarity = ACPI_ACTIVE_LOW, .con_id = "goodix_ts_irq", + .free_gpio = true, }, }, { /* Wacom Digitizer in keyboard half */ diff --git a/drivers/platform/x86/x86-android-tablets/other.c b/drivers/platform/x86/x86-android-tablets/other.c index bc6bbf7ec6ea..278402dcb808 100644 --- a/drivers/platform/x86/x86-android-tablets/other.c +++ b/drivers/platform/x86/x86-android-tablets/other.c @@ -68,7 +68,7 @@ static const struct x86_i2c_client_info acer_b1_750_i2c_clients[] __initconst = }, }; -static struct gpiod_lookup_table acer_b1_750_goodix_gpios = { +static struct gpiod_lookup_table acer_b1_750_nvt_ts_gpios = { .dev_id = "i2c-NVT-ts", .table = { GPIO_LOOKUP("INT33FC:01", 26, "reset", GPIO_ACTIVE_LOW), @@ -77,7 +77,7 @@ static struct gpiod_lookup_table acer_b1_750_goodix_gpios = { }; static struct gpiod_lookup_table * const acer_b1_750_gpios[] = { - &acer_b1_750_goodix_gpios, + &acer_b1_750_nvt_ts_gpios, &int3496_reference_gpios, NULL }; diff --git a/drivers/platform/x86/x86-android-tablets/x86-android-tablets.h b/drivers/platform/x86/x86-android-tablets/x86-android-tablets.h index 49fed9410adb..468993edfeee 100644 --- a/drivers/platform/x86/x86-android-tablets/x86-android-tablets.h +++ b/drivers/platform/x86/x86-android-tablets/x86-android-tablets.h @@ -39,6 +39,7 @@ struct x86_acpi_irq_data { int index; int trigger; /* ACPI_EDGE_SENSITIVE / ACPI_LEVEL_SENSITIVE */ int polarity; /* ACPI_ACTIVE_HIGH / ACPI_ACTIVE_LOW / ACPI_ACTIVE_BOTH */ + bool free_gpio; /* Release GPIO after getting IRQ (for TYPE_GPIOINT) */ const char *con_id; }; diff --git a/fs/afs/internal.h b/fs/afs/internal.h index 9c03fcf7ffaa..6ce5a612937c 100644 --- a/fs/afs/internal.h +++ b/fs/afs/internal.h @@ -321,8 +321,7 @@ struct afs_net { struct list_head fs_probe_slow; /* List of afs_server to probe at 5m intervals */ struct hlist_head fs_proc; /* procfs servers list */ - struct hlist_head fs_addresses4; /* afs_server (by lowest IPv4 addr) */ - struct hlist_head fs_addresses6; /* afs_server (by lowest IPv6 addr) */ + struct hlist_head fs_addresses; /* afs_server (by lowest IPv6 addr) */ seqlock_t fs_addr_lock; /* For fs_addresses[46] */ struct work_struct fs_manager; @@ -561,8 +560,7 @@ struct afs_server { struct afs_server __rcu *uuid_next; /* Next server with same UUID */ struct afs_server *uuid_prev; /* Previous server with same UUID */ struct list_head probe_link; /* Link in net->fs_probe_list */ - struct hlist_node addr4_link; /* Link in net->fs_addresses4 */ - struct hlist_node addr6_link; /* Link in net->fs_addresses6 */ + struct hlist_node addr_link; /* Link in net->fs_addresses6 */ struct hlist_node proc_link; /* Link in net->fs_proc */ struct list_head volumes; /* RCU list of afs_server_entry objects */ struct afs_server *gc_next; /* Next server in manager's list */ diff --git a/fs/afs/main.c b/fs/afs/main.c index 1b3bd21c168a..a14f6013e316 100644 --- a/fs/afs/main.c +++ b/fs/afs/main.c @@ -90,8 +90,7 @@ static int __net_init afs_net_init(struct net *net_ns) INIT_LIST_HEAD(&net->fs_probe_slow); INIT_HLIST_HEAD(&net->fs_proc); - INIT_HLIST_HEAD(&net->fs_addresses4); - INIT_HLIST_HEAD(&net->fs_addresses6); + INIT_HLIST_HEAD(&net->fs_addresses); seqlock_init(&net->fs_addr_lock); INIT_WORK(&net->fs_manager, afs_manage_servers); diff --git a/fs/afs/server.c b/fs/afs/server.c index e169121f603e..038f9d0ae3af 100644 --- a/fs/afs/server.c +++ b/fs/afs/server.c @@ -38,7 +38,7 @@ struct afs_server *afs_find_server(struct afs_net *net, const struct rxrpc_peer seq++; /* 2 on the 1st/lockless path, otherwise odd */ read_seqbegin_or_lock(&net->fs_addr_lock, &seq); - hlist_for_each_entry_rcu(server, &net->fs_addresses6, addr6_link) { + hlist_for_each_entry_rcu(server, &net->fs_addresses, addr_link) { estate = rcu_dereference(server->endpoint_state); alist = estate->addresses; for (i = 0; i < alist->nr_addrs; i++) @@ -177,10 +177,8 @@ added_dup: * bit, but anything we might want to do gets messy and memory * intensive. */ - if (alist->nr_ipv4 > 0) - hlist_add_head_rcu(&server->addr4_link, &net->fs_addresses4); - if (alist->nr_addrs > alist->nr_ipv4) - hlist_add_head_rcu(&server->addr6_link, &net->fs_addresses6); + if (alist->nr_addrs > 0) + hlist_add_head_rcu(&server->addr_link, &net->fs_addresses); write_sequnlock(&net->fs_addr_lock); @@ -511,10 +509,8 @@ static void afs_gc_servers(struct afs_net *net, struct afs_server *gc_list) list_del(&server->probe_link); hlist_del_rcu(&server->proc_link); - if (!hlist_unhashed(&server->addr4_link)) - hlist_del_rcu(&server->addr4_link); - if (!hlist_unhashed(&server->addr6_link)) - hlist_del_rcu(&server->addr6_link); + if (!hlist_unhashed(&server->addr_link)) + hlist_del_rcu(&server->addr_link); } write_sequnlock(&net->fs_lock); diff --git a/fs/afs/volume.c b/fs/afs/volume.c index 020ecd45e476..af3a3f57c1b3 100644 --- a/fs/afs/volume.c +++ b/fs/afs/volume.c @@ -353,7 +353,7 @@ static int afs_update_volume_status(struct afs_volume *volume, struct key *key) { struct afs_server_list *new, *old, *discard; struct afs_vldb_entry *vldb; - char idbuf[16]; + char idbuf[24]; int ret, idsz; _enter(""); @@ -361,7 +361,7 @@ static int afs_update_volume_status(struct afs_volume *volume, struct key *key) /* We look up an ID by passing it as a decimal string in the * operation's name parameter. */ - idsz = sprintf(idbuf, "%llu", volume->vid); + idsz = snprintf(idbuf, sizeof(idbuf), "%llu", volume->vid); vldb = afs_vl_lookup_vldb(volume->cell, key, idbuf, idsz); if (IS_ERR(vldb)) { @@ -593,6 +593,13 @@ void kiocb_set_cancel_fn(struct kiocb *iocb, kiocb_cancel_fn *cancel) struct kioctx *ctx = req->ki_ctx; unsigned long flags; + /* + * kiocb didn't come from aio or is neither a read nor a write, hence + * ignore it. + */ + if (!(iocb->ki_flags & IOCB_AIO_RW)) + return; + if (WARN_ON_ONCE(!list_empty(&req->ki_list))) return; @@ -1509,7 +1516,7 @@ static int aio_prep_rw(struct kiocb *req, const struct iocb *iocb) req->ki_complete = aio_complete_rw; req->private = NULL; req->ki_pos = iocb->aio_offset; - req->ki_flags = req->ki_filp->f_iocb_flags; + req->ki_flags = req->ki_filp->f_iocb_flags | IOCB_AIO_RW; if (iocb->aio_flags & IOCB_FLAG_RESFD) req->ki_flags |= IOCB_EVENTFD; if (iocb->aio_flags & IOCB_FLAG_IOPRIO) { diff --git a/fs/btrfs/defrag.c b/fs/btrfs/defrag.c index c276b136ab63..5b0b64571418 100644 --- a/fs/btrfs/defrag.c +++ b/fs/btrfs/defrag.c @@ -1046,7 +1046,7 @@ static int defrag_collect_targets(struct btrfs_inode *inode, goto add; /* Skip too large extent */ - if (range_len >= extent_thresh) + if (em->len >= extent_thresh) goto next; /* diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index cfd2967f04a2..3e19a2475ab3 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -2689,16 +2689,34 @@ static int fiemap_process_hole(struct btrfs_inode *inode, * it beyond i_size. */ while (cur_offset < end && cur_offset < i_size) { + struct extent_state *cached_state = NULL; u64 delalloc_start; u64 delalloc_end; u64 prealloc_start; + u64 lockstart; + u64 lockend; u64 prealloc_len = 0; bool delalloc; + lockstart = round_down(cur_offset, inode->root->fs_info->sectorsize); + lockend = round_up(end, inode->root->fs_info->sectorsize); + + /* + * We are only locking for the delalloc range because that's the + * only thing that can change here. With fiemap we have a lock + * on the inode, so no buffered or direct writes can happen. + * + * However mmaps and normal page writeback will cause this to + * change arbitrarily. We have to lock the extent lock here to + * make sure that nobody messes with the tree while we're doing + * btrfs_find_delalloc_in_range. + */ + lock_extent(&inode->io_tree, lockstart, lockend, &cached_state); delalloc = btrfs_find_delalloc_in_range(inode, cur_offset, end, delalloc_cached_state, &delalloc_start, &delalloc_end); + unlock_extent(&inode->io_tree, lockstart, lockend, &cached_state); if (!delalloc) break; @@ -2866,15 +2884,15 @@ int extent_fiemap(struct btrfs_inode *inode, struct fiemap_extent_info *fieinfo, u64 start, u64 len) { const u64 ino = btrfs_ino(inode); - struct extent_state *cached_state = NULL; struct extent_state *delalloc_cached_state = NULL; struct btrfs_path *path; struct fiemap_cache cache = { 0 }; struct btrfs_backref_share_check_ctx *backref_ctx; u64 last_extent_end; u64 prev_extent_end; - u64 lockstart; - u64 lockend; + u64 range_start; + u64 range_end; + const u64 sectorsize = inode->root->fs_info->sectorsize; bool stopped = false; int ret; @@ -2885,12 +2903,11 @@ int extent_fiemap(struct btrfs_inode *inode, struct fiemap_extent_info *fieinfo, goto out; } - lockstart = round_down(start, inode->root->fs_info->sectorsize); - lockend = round_up(start + len, inode->root->fs_info->sectorsize); - prev_extent_end = lockstart; + range_start = round_down(start, sectorsize); + range_end = round_up(start + len, sectorsize); + prev_extent_end = range_start; btrfs_inode_lock(inode, BTRFS_ILOCK_SHARED); - lock_extent(&inode->io_tree, lockstart, lockend, &cached_state); ret = fiemap_find_last_extent_offset(inode, path, &last_extent_end); if (ret < 0) @@ -2898,7 +2915,7 @@ int extent_fiemap(struct btrfs_inode *inode, struct fiemap_extent_info *fieinfo, btrfs_release_path(path); path->reada = READA_FORWARD; - ret = fiemap_search_slot(inode, path, lockstart); + ret = fiemap_search_slot(inode, path, range_start); if (ret < 0) { goto out_unlock; } else if (ret > 0) { @@ -2910,7 +2927,7 @@ int extent_fiemap(struct btrfs_inode *inode, struct fiemap_extent_info *fieinfo, goto check_eof_delalloc; } - while (prev_extent_end < lockend) { + while (prev_extent_end < range_end) { struct extent_buffer *leaf = path->nodes[0]; struct btrfs_file_extent_item *ei; struct btrfs_key key; @@ -2933,19 +2950,19 @@ int extent_fiemap(struct btrfs_inode *inode, struct fiemap_extent_info *fieinfo, * The first iteration can leave us at an extent item that ends * before our range's start. Move to the next item. */ - if (extent_end <= lockstart) + if (extent_end <= range_start) goto next_item; backref_ctx->curr_leaf_bytenr = leaf->start; /* We have in implicit hole (NO_HOLES feature enabled). */ if (prev_extent_end < key.offset) { - const u64 range_end = min(key.offset, lockend) - 1; + const u64 hole_end = min(key.offset, range_end) - 1; ret = fiemap_process_hole(inode, fieinfo, &cache, &delalloc_cached_state, backref_ctx, 0, 0, 0, - prev_extent_end, range_end); + prev_extent_end, hole_end); if (ret < 0) { goto out_unlock; } else if (ret > 0) { @@ -2955,7 +2972,7 @@ int extent_fiemap(struct btrfs_inode *inode, struct fiemap_extent_info *fieinfo, } /* We've reached the end of the fiemap range, stop. */ - if (key.offset >= lockend) { + if (key.offset >= range_end) { stopped = true; break; } @@ -3049,29 +3066,41 @@ check_eof_delalloc: btrfs_free_path(path); path = NULL; - if (!stopped && prev_extent_end < lockend) { + if (!stopped && prev_extent_end < range_end) { ret = fiemap_process_hole(inode, fieinfo, &cache, &delalloc_cached_state, backref_ctx, - 0, 0, 0, prev_extent_end, lockend - 1); + 0, 0, 0, prev_extent_end, range_end - 1); if (ret < 0) goto out_unlock; - prev_extent_end = lockend; + prev_extent_end = range_end; } if (cache.cached && cache.offset + cache.len >= last_extent_end) { const u64 i_size = i_size_read(&inode->vfs_inode); if (prev_extent_end < i_size) { + struct extent_state *cached_state = NULL; u64 delalloc_start; u64 delalloc_end; + u64 lockstart; + u64 lockend; bool delalloc; + lockstart = round_down(prev_extent_end, sectorsize); + lockend = round_up(i_size, sectorsize); + + /* + * See the comment in fiemap_process_hole as to why + * we're doing the locking here. + */ + lock_extent(&inode->io_tree, lockstart, lockend, &cached_state); delalloc = btrfs_find_delalloc_in_range(inode, prev_extent_end, i_size - 1, &delalloc_cached_state, &delalloc_start, &delalloc_end); + unlock_extent(&inode->io_tree, lockstart, lockend, &cached_state); if (!delalloc) cache.flags |= FIEMAP_EXTENT_LAST; } else { @@ -3082,7 +3111,6 @@ check_eof_delalloc: ret = emit_last_fiemap_cache(fieinfo, &cache); out_unlock: - unlock_extent(&inode->io_tree, lockstart, lockend, &cached_state); btrfs_inode_unlock(inode, BTRFS_ILOCK_SHARED); out: free_extent_state(delalloc_cached_state); diff --git a/fs/cachefiles/cache.c b/fs/cachefiles/cache.c index 7077f72e6f47..f449f7340aad 100644 --- a/fs/cachefiles/cache.c +++ b/fs/cachefiles/cache.c @@ -168,6 +168,8 @@ error_unsupported: dput(root); error_open_root: cachefiles_end_secure(cache, saved_cred); + put_cred(cache->cache_cred); + cache->cache_cred = NULL; error_getsec: fscache_relinquish_cache(cache_cookie); cache->cache = NULL; diff --git a/fs/cachefiles/daemon.c b/fs/cachefiles/daemon.c index 3f24905f4066..6465e2574230 100644 --- a/fs/cachefiles/daemon.c +++ b/fs/cachefiles/daemon.c @@ -816,6 +816,7 @@ static void cachefiles_daemon_unbind(struct cachefiles_cache *cache) cachefiles_put_directory(cache->graveyard); cachefiles_put_directory(cache->store); mntput(cache->mnt); + put_cred(cache->cache_cred); kfree(cache->rootdirname); kfree(cache->secctx); diff --git a/fs/netfs/buffered_write.c b/fs/netfs/buffered_write.c index a3059b3168fd..9a0d32e4b422 100644 --- a/fs/netfs/buffered_write.c +++ b/fs/netfs/buffered_write.c @@ -477,6 +477,9 @@ ssize_t netfs_file_write_iter(struct kiocb *iocb, struct iov_iter *from) _enter("%llx,%zx,%llx", iocb->ki_pos, iov_iter_count(from), i_size_read(inode)); + if (!iov_iter_count(from)) + return 0; + if ((iocb->ki_flags & IOCB_DIRECT) || test_bit(NETFS_ICTX_UNBUFFERED, &ictx->flags)) return netfs_unbuffered_write_iter(iocb, from); diff --git a/fs/netfs/direct_write.c b/fs/netfs/direct_write.c index 60a40d293c87..bee047e20f5d 100644 --- a/fs/netfs/direct_write.c +++ b/fs/netfs/direct_write.c @@ -139,6 +139,9 @@ ssize_t netfs_unbuffered_write_iter(struct kiocb *iocb, struct iov_iter *from) _enter("%llx,%zx,%llx", iocb->ki_pos, iov_iter_count(from), i_size_read(inode)); + if (!iov_iter_count(from)) + return 0; + trace_netfs_write_iter(iocb, from); netfs_stat(&netfs_n_rh_dio_write); @@ -146,7 +149,7 @@ ssize_t netfs_unbuffered_write_iter(struct kiocb *iocb, struct iov_iter *from) if (ret < 0) return ret; ret = generic_write_checks(iocb, from); - if (ret < 0) + if (ret <= 0) goto out; ret = file_remove_privs(file); if (ret < 0) diff --git a/fs/netfs/io.c b/fs/netfs/io.c index e8ff1e61ce79..4261ad6c55b6 100644 --- a/fs/netfs/io.c +++ b/fs/netfs/io.c @@ -748,6 +748,8 @@ int netfs_begin_read(struct netfs_io_request *rreq, bool sync) if (!rreq->submitted) { netfs_put_request(rreq, false, netfs_rreq_trace_put_no_submit); + if (rreq->origin == NETFS_DIO_READ) + inode_dio_end(rreq->inode); ret = 0; goto out; } diff --git a/include/linux/fs.h b/include/linux/fs.h index 023f37c60709..1fbc72c5f112 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -352,6 +352,8 @@ enum rw_hint { * unrelated IO (like cache flushing, new IO generation, etc). */ #define IOCB_DIO_CALLER_COMP (1 << 22) +/* kiocb is a read or write operation submitted by fs/aio.c. */ +#define IOCB_AIO_RW (1 << 23) /* for use in trace events */ #define TRACE_IOCB_STRINGS \ diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index c726f90ab752..3fd6310b6da6 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -1103,7 +1103,7 @@ struct mlx5_ifc_roce_cap_bits { u8 sw_r_roce_src_udp_port[0x1]; u8 fl_rc_qp_when_roce_disabled[0x1]; u8 fl_rc_qp_when_roce_enabled[0x1]; - u8 reserved_at_7[0x1]; + u8 roce_cc_general[0x1]; u8 qp_ooo_transmit_default[0x1]; u8 reserved_at_9[0x15]; u8 qp_ts_format[0x2]; diff --git a/include/linux/mlx5/qp.h b/include/linux/mlx5/qp.h index bd53cf4be7bd..f0e55bf3ec8b 100644 --- a/include/linux/mlx5/qp.h +++ b/include/linux/mlx5/qp.h @@ -269,7 +269,10 @@ struct mlx5_wqe_eth_seg { union { struct { __be16 sz; - u8 start[2]; + union { + u8 start[2]; + DECLARE_FLEX_ARRAY(u8, data); + }; } inline_hdr; struct { __be16 type; diff --git a/include/net/netfilter/nf_flow_table.h b/include/net/netfilter/nf_flow_table.h index 956c752ceb31..a763dd327c6e 100644 --- a/include/net/netfilter/nf_flow_table.h +++ b/include/net/netfilter/nf_flow_table.h @@ -276,7 +276,7 @@ nf_flow_table_offload_del_cb(struct nf_flowtable *flow_table, } void flow_offload_route_init(struct flow_offload *flow, - const struct nf_flow_route *route); + struct nf_flow_route *route); int flow_offload_add(struct nf_flowtable *flow_table, struct flow_offload *flow); void flow_offload_refresh(struct nf_flowtable *flow_table, diff --git a/include/net/switchdev.h b/include/net/switchdev.h index a43062d4c734..8346b0d29542 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -308,6 +308,9 @@ void switchdev_deferred_process(void); int switchdev_port_attr_set(struct net_device *dev, const struct switchdev_attr *attr, struct netlink_ext_ack *extack); +bool switchdev_port_obj_act_is_deferred(struct net_device *dev, + enum switchdev_notifier_type nt, + const struct switchdev_obj *obj); int switchdev_port_obj_add(struct net_device *dev, const struct switchdev_obj *obj, struct netlink_ext_ack *extack); diff --git a/include/net/tcp.h b/include/net/tcp.h index dd78a1181031..f6eba9652d01 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -2506,7 +2506,7 @@ struct tcp_ulp_ops { /* cleanup ulp */ void (*release)(struct sock *sk); /* diagnostic */ - int (*get_info)(const struct sock *sk, struct sk_buff *skb); + int (*get_info)(struct sock *sk, struct sk_buff *skb); size_t (*get_info_size)(const struct sock *sk); /* clone ulp */ void (*clone)(const struct request_sock *req, struct sock *newsk, diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index be72824f32b2..d19cd863d294 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -1101,6 +1101,7 @@ struct bpf_hrtimer { struct bpf_prog *prog; void __rcu *callback_fn; void *value; + struct rcu_head rcu; }; /* the actual struct hidden inside uapi struct bpf_timer */ @@ -1332,6 +1333,7 @@ BPF_CALL_1(bpf_timer_cancel, struct bpf_timer_kern *, timer) if (in_nmi()) return -EOPNOTSUPP; + rcu_read_lock(); __bpf_spin_lock_irqsave(&timer->lock); t = timer->timer; if (!t) { @@ -1353,6 +1355,7 @@ out: * if it was running. */ ret = ret ?: hrtimer_cancel(&t->timer); + rcu_read_unlock(); return ret; } @@ -1407,7 +1410,7 @@ out: */ if (this_cpu_read(hrtimer_running) != t) hrtimer_cancel(&t->timer); - kfree(t); + kfree_rcu(t, rcu); } BPF_CALL_2(bpf_kptr_xchg, void *, map_value, void *, ptr) diff --git a/kernel/bpf/task_iter.c b/kernel/bpf/task_iter.c index e5c3500443c6..ec4e97c61eef 100644 --- a/kernel/bpf/task_iter.c +++ b/kernel/bpf/task_iter.c @@ -978,6 +978,8 @@ __bpf_kfunc int bpf_iter_task_new(struct bpf_iter_task *it, BUILD_BUG_ON(__alignof__(struct bpf_iter_task_kern) != __alignof__(struct bpf_iter_task)); + kit->pos = NULL; + switch (flags) { case BPF_TASK_ITER_ALL_THREADS: case BPF_TASK_ITER_ALL_PROCS: diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 65f598694d55..b263f093ee76 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -5227,7 +5227,9 @@ BTF_ID(struct, prog_test_ref_kfunc) #ifdef CONFIG_CGROUPS BTF_ID(struct, cgroup) #endif +#ifdef CONFIG_BPF_JIT BTF_ID(struct, bpf_cpumask) +#endif BTF_ID(struct, task_struct) BTF_SET_END(rcu_protected_types) diff --git a/kernel/sched/membarrier.c b/kernel/sched/membarrier.c index 2ad881d07752..4e715b9b278e 100644 --- a/kernel/sched/membarrier.c +++ b/kernel/sched/membarrier.c @@ -162,6 +162,9 @@ | MEMBARRIER_PRIVATE_EXPEDITED_RSEQ_BITMASK \ | MEMBARRIER_CMD_GET_REGISTRATIONS) +static DEFINE_MUTEX(membarrier_ipi_mutex); +#define SERIALIZE_IPI() guard(mutex)(&membarrier_ipi_mutex) + static void ipi_mb(void *info) { smp_mb(); /* IPIs should be serializing but paranoid. */ @@ -259,6 +262,7 @@ static int membarrier_global_expedited(void) if (!zalloc_cpumask_var(&tmpmask, GFP_KERNEL)) return -ENOMEM; + SERIALIZE_IPI(); cpus_read_lock(); rcu_read_lock(); for_each_online_cpu(cpu) { @@ -347,6 +351,7 @@ static int membarrier_private_expedited(int flags, int cpu_id) if (cpu_id < 0 && !zalloc_cpumask_var(&tmpmask, GFP_KERNEL)) return -ENOMEM; + SERIALIZE_IPI(); cpus_read_lock(); if (cpu_id >= 0) { @@ -460,6 +465,7 @@ static int sync_runqueues_membarrier_state(struct mm_struct *mm) * between threads which are users of @mm has its membarrier state * updated. */ + SERIALIZE_IPI(); cpus_read_lock(); rcu_read_lock(); for_each_online_cpu(cpu) { diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index fd4bfe3ecf01..0699027b4f4c 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -5877,6 +5877,10 @@ int ring_buffer_subbuf_order_set(struct trace_buffer *buffer, int order) if (psize <= BUF_PAGE_HDR_SIZE) return -EINVAL; + /* Size of a subbuf cannot be greater than the write counter */ + if (psize > RB_WRITE_MASK + 1) + return -EINVAL; + old_order = buffer->subbuf_order; old_size = buffer->subbuf_size; diff --git a/net/bridge/br_switchdev.c b/net/bridge/br_switchdev.c index ee84e783e1df..7b41ee8740cb 100644 --- a/net/bridge/br_switchdev.c +++ b/net/bridge/br_switchdev.c @@ -595,21 +595,40 @@ br_switchdev_mdb_replay_one(struct notifier_block *nb, struct net_device *dev, } static int br_switchdev_mdb_queue_one(struct list_head *mdb_list, + struct net_device *dev, + unsigned long action, enum switchdev_obj_id id, const struct net_bridge_mdb_entry *mp, struct net_device *orig_dev) { - struct switchdev_obj_port_mdb *mdb; + struct switchdev_obj_port_mdb mdb = { + .obj = { + .id = id, + .orig_dev = orig_dev, + }, + }; + struct switchdev_obj_port_mdb *pmdb; - mdb = kzalloc(sizeof(*mdb), GFP_ATOMIC); - if (!mdb) - return -ENOMEM; + br_switchdev_mdb_populate(&mdb, mp); + + if (action == SWITCHDEV_PORT_OBJ_ADD && + switchdev_port_obj_act_is_deferred(dev, action, &mdb.obj)) { + /* This event is already in the deferred queue of + * events, so this replay must be elided, lest the + * driver receives duplicate events for it. This can + * only happen when replaying additions, since + * modifications are always immediately visible in + * br->mdb_list, whereas actual event delivery may be + * delayed. + */ + return 0; + } - mdb->obj.id = id; - mdb->obj.orig_dev = orig_dev; - br_switchdev_mdb_populate(mdb, mp); - list_add_tail(&mdb->obj.list, mdb_list); + pmdb = kmemdup(&mdb, sizeof(mdb), GFP_ATOMIC); + if (!pmdb) + return -ENOMEM; + list_add_tail(&pmdb->obj.list, mdb_list); return 0; } @@ -677,51 +696,50 @@ br_switchdev_mdb_replay(struct net_device *br_dev, struct net_device *dev, if (!br_opt_get(br, BROPT_MULTICAST_ENABLED)) return 0; - /* We cannot walk over br->mdb_list protected just by the rtnl_mutex, - * because the write-side protection is br->multicast_lock. But we - * need to emulate the [ blocking ] calling context of a regular - * switchdev event, so since both br->multicast_lock and RCU read side - * critical sections are atomic, we have no choice but to pick the RCU - * read side lock, queue up all our events, leave the critical section - * and notify switchdev from blocking context. + if (adding) + action = SWITCHDEV_PORT_OBJ_ADD; + else + action = SWITCHDEV_PORT_OBJ_DEL; + + /* br_switchdev_mdb_queue_one() will take care to not queue a + * replay of an event that is already pending in the switchdev + * deferred queue. In order to safely determine that, there + * must be no new deferred MDB notifications enqueued for the + * duration of the MDB scan. Therefore, grab the write-side + * lock to avoid racing with any concurrent IGMP/MLD snooping. */ - rcu_read_lock(); + spin_lock_bh(&br->multicast_lock); - hlist_for_each_entry_rcu(mp, &br->mdb_list, mdb_node) { + hlist_for_each_entry(mp, &br->mdb_list, mdb_node) { struct net_bridge_port_group __rcu * const *pp; const struct net_bridge_port_group *p; if (mp->host_joined) { - err = br_switchdev_mdb_queue_one(&mdb_list, + err = br_switchdev_mdb_queue_one(&mdb_list, dev, action, SWITCHDEV_OBJ_ID_HOST_MDB, mp, br_dev); if (err) { - rcu_read_unlock(); + spin_unlock_bh(&br->multicast_lock); goto out_free_mdb; } } - for (pp = &mp->ports; (p = rcu_dereference(*pp)) != NULL; + for (pp = &mp->ports; (p = mlock_dereference(*pp, br)) != NULL; pp = &p->next) { if (p->key.port->dev != dev) continue; - err = br_switchdev_mdb_queue_one(&mdb_list, + err = br_switchdev_mdb_queue_one(&mdb_list, dev, action, SWITCHDEV_OBJ_ID_PORT_MDB, mp, dev); if (err) { - rcu_read_unlock(); + spin_unlock_bh(&br->multicast_lock); goto out_free_mdb; } } } - rcu_read_unlock(); - - if (adding) - action = SWITCHDEV_PORT_OBJ_ADD; - else - action = SWITCHDEV_PORT_OBJ_DEL; + spin_unlock_bh(&br->multicast_lock); list_for_each_entry(obj, &mdb_list, list) { err = br_switchdev_mdb_replay_one(nb, dev, @@ -786,6 +804,16 @@ static void nbp_switchdev_unsync_objs(struct net_bridge_port *p, br_switchdev_mdb_replay(br_dev, dev, ctx, false, blocking_nb, NULL); br_switchdev_vlan_replay(br_dev, ctx, false, blocking_nb, NULL); + + /* Make sure that the device leaving this bridge has seen all + * relevant events before it is disassociated. In the normal + * case, when the device is directly attached to the bridge, + * this is covered by del_nbp(). If the association was indirect + * however, e.g. via a team or bond, and the device is leaving + * that intermediate device, then the bridge port remains in + * place. + */ + switchdev_deferred_process(); } /* Let the bridge know that this port is offloaded, so that it can assign a diff --git a/net/core/skmsg.c b/net/core/skmsg.c index 93ecfceac1bc..4d75ef9d24bf 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -1226,8 +1226,11 @@ static void sk_psock_verdict_data_ready(struct sock *sk) rcu_read_lock(); psock = sk_psock(sk); - if (psock) - psock->saved_data_ready(sk); + if (psock) { + read_lock_bh(&sk->sk_callback_lock); + sk_psock_data_ready(sk, psock); + read_unlock_bh(&sk->sk_callback_lock); + } rcu_read_unlock(); } } diff --git a/net/core/sock.c b/net/core/sock.c index 0a7f46c37f0c..5e78798456fd 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1188,6 +1188,17 @@ int sk_setsockopt(struct sock *sk, int level, int optname, */ WRITE_ONCE(sk->sk_txrehash, (u8)val); return 0; + case SO_PEEK_OFF: + { + int (*set_peek_off)(struct sock *sk, int val); + + set_peek_off = READ_ONCE(sock->ops)->set_peek_off; + if (set_peek_off) + ret = set_peek_off(sk, val); + else + ret = -EOPNOTSUPP; + return ret; + } } sockopt_lock_sock(sk); @@ -1430,18 +1441,6 @@ set_sndbuf: sock_valbool_flag(sk, SOCK_WIFI_STATUS, valbool); break; - case SO_PEEK_OFF: - { - int (*set_peek_off)(struct sock *sk, int val); - - set_peek_off = READ_ONCE(sock->ops)->set_peek_off; - if (set_peek_off) - ret = set_peek_off(sk, val); - else - ret = -EOPNOTSUPP; - break; - } - case SO_NOFCS: sock_valbool_flag(sk, SOCK_NOFCS, valbool); break; diff --git a/net/devlink/core.c b/net/devlink/core.c index 6a58342752b4..7f0b093208d7 100644 --- a/net/devlink/core.c +++ b/net/devlink/core.c @@ -529,14 +529,20 @@ static int __init devlink_init(void) { int err; - err = genl_register_family(&devlink_nl_family); - if (err) - goto out; err = register_pernet_subsys(&devlink_pernet_ops); if (err) goto out; + err = genl_register_family(&devlink_nl_family); + if (err) + goto out_unreg_pernet_subsys; err = register_netdevice_notifier(&devlink_port_netdevice_nb); + if (!err) + return 0; + + genl_unregister_family(&devlink_nl_family); +out_unreg_pernet_subsys: + unregister_pernet_subsys(&devlink_pernet_ops); out: WARN_ON(err); return err; diff --git a/net/devlink/port.c b/net/devlink/port.c index 78592912f657..4b2d46ccfe48 100644 --- a/net/devlink/port.c +++ b/net/devlink/port.c @@ -583,7 +583,7 @@ devlink_nl_port_get_dump_one(struct sk_buff *msg, struct devlink *devlink, xa_for_each_start(&devlink->ports, port_index, devlink_port, state->idx) { err = devlink_nl_port_fill(msg, devlink_port, - DEVLINK_CMD_NEW, + DEVLINK_CMD_PORT_NEW, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, flags, cb->extack); diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index 9456f5bb35e5..0d0d725b46ad 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -1125,7 +1125,8 @@ static int arp_req_get(struct arpreq *r, struct net_device *dev) if (neigh) { if (!(READ_ONCE(neigh->nud_state) & NUD_NOARP)) { read_lock_bh(&neigh->lock); - memcpy(r->arp_ha.sa_data, neigh->ha, dev->addr_len); + memcpy(r->arp_ha.sa_data, neigh->ha, + min(dev->addr_len, sizeof(r->arp_ha.sa_data_min))); r->arp_flags = arp_state_to_flags(neigh); read_unlock_bh(&neigh->lock); r->arp_ha.sa_family = dev->type; diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index ca0ff15dc8fa..bc74f131fe4d 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -1825,6 +1825,21 @@ done: return err; } +/* Combine dev_addr_genid and dev_base_seq to detect changes. + */ +static u32 inet_base_seq(const struct net *net) +{ + u32 res = atomic_read(&net->ipv4.dev_addr_genid) + + net->dev_base_seq; + + /* Must not return 0 (see nl_dump_check_consistent()). + * Chose a value far away from 0. + */ + if (!res) + res = 0x80000000; + return res; +} + static int inet_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb) { const struct nlmsghdr *nlh = cb->nlh; @@ -1876,8 +1891,7 @@ static int inet_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb) idx = 0; head = &tgt_net->dev_index_head[h]; rcu_read_lock(); - cb->seq = atomic_read(&tgt_net->ipv4.dev_addr_genid) ^ - tgt_net->dev_base_seq; + cb->seq = inet_base_seq(tgt_net); hlist_for_each_entry_rcu(dev, head, index_hlist) { if (idx < s_idx) goto cont; @@ -2278,8 +2292,7 @@ static int inet_netconf_dump_devconf(struct sk_buff *skb, idx = 0; head = &net->dev_index_head[h]; rcu_read_lock(); - cb->seq = atomic_read(&net->ipv4.dev_addr_genid) ^ - net->dev_base_seq; + cb->seq = inet_base_seq(net); hlist_for_each_entry_rcu(dev, head, index_hlist) { if (idx < s_idx) goto cont; diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 93e9193df544..308ff34002ea 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -1130,10 +1130,33 @@ ok: return 0; error: + if (sk_hashed(sk)) { + spinlock_t *lock = inet_ehash_lockp(hinfo, sk->sk_hash); + + sock_prot_inuse_add(net, sk->sk_prot, -1); + + spin_lock(lock); + sk_nulls_del_node_init_rcu(sk); + spin_unlock(lock); + + sk->sk_hash = 0; + inet_sk(sk)->inet_sport = 0; + inet_sk(sk)->inet_num = 0; + + if (tw) + inet_twsk_bind_unhash(tw, hinfo); + } + spin_unlock(&head2->lock); if (tb_created) inet_bind_bucket_destroy(hinfo->bind_bucket_cachep, tb); - spin_unlock_bh(&head->lock); + spin_unlock(&head->lock); + + if (tw) + inet_twsk_deschedule_put(tw); + + local_bh_enable(); + return -ENOMEM; } diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index f631b0a21af4..e474b201900f 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1589,12 +1589,7 @@ int udp_init_sock(struct sock *sk) void skb_consume_udp(struct sock *sk, struct sk_buff *skb, int len) { - if (unlikely(READ_ONCE(sk->sk_peek_off) >= 0)) { - bool slow = lock_sock_fast(sk); - - sk_peek_offset_bwd(sk, len); - unlock_sock_fast(sk, slow); - } + sk_peek_offset_bwd(sk, len); if (!skb_unref(skb)) return; diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 733ace18806c..5a839c5fb1a5 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -708,6 +708,22 @@ errout: return err; } +/* Combine dev_addr_genid and dev_base_seq to detect changes. + */ +static u32 inet6_base_seq(const struct net *net) +{ + u32 res = atomic_read(&net->ipv6.dev_addr_genid) + + net->dev_base_seq; + + /* Must not return 0 (see nl_dump_check_consistent()). + * Chose a value far away from 0. + */ + if (!res) + res = 0x80000000; + return res; +} + + static int inet6_netconf_dump_devconf(struct sk_buff *skb, struct netlink_callback *cb) { @@ -741,8 +757,7 @@ static int inet6_netconf_dump_devconf(struct sk_buff *skb, idx = 0; head = &net->dev_index_head[h]; rcu_read_lock(); - cb->seq = atomic_read(&net->ipv6.dev_addr_genid) ^ - net->dev_base_seq; + cb->seq = inet6_base_seq(net); hlist_for_each_entry_rcu(dev, head, index_hlist) { if (idx < s_idx) goto cont; @@ -5362,7 +5377,7 @@ static int inet6_dump_addr(struct sk_buff *skb, struct netlink_callback *cb, } rcu_read_lock(); - cb->seq = atomic_read(&tgt_net->ipv6.dev_addr_genid) ^ tgt_net->dev_base_seq; + cb->seq = inet6_base_seq(tgt_net); for (h = s_h; h < NETDEV_HASHENTRIES; h++, s_idx = 0) { idx = 0; head = &tgt_net->dev_index_head[h]; diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c index 4952ae792450..02e9ffb63af1 100644 --- a/net/ipv6/exthdrs.c +++ b/net/ipv6/exthdrs.c @@ -177,6 +177,8 @@ static bool ip6_parse_tlv(bool hopbyhop, case IPV6_TLV_IOAM: if (!ipv6_hop_ioam(skb, off)) return false; + + nh = skb_network_header(skb); break; case IPV6_TLV_JUMBO: if (!ipv6_hop_jumbo(skb, off)) @@ -943,6 +945,14 @@ static bool ipv6_hop_ioam(struct sk_buff *skb, int optoff) if (!skb_valid_dst(skb)) ip6_route_input(skb); + /* About to mangle packet header */ + if (skb_ensure_writable(skb, optoff + 2 + hdr->opt_len)) + goto drop; + + /* Trace pointer may have changed */ + trace = (struct ioam6_trace_hdr *)(skb_network_header(skb) + + optoff + sizeof(*hdr)); + ioam6_fill_trace_data(skb, ns, trace, true); break; default: diff --git a/net/ipv6/seg6.c b/net/ipv6/seg6.c index 29346a6eec9f..35508abd76f4 100644 --- a/net/ipv6/seg6.c +++ b/net/ipv6/seg6.c @@ -512,22 +512,24 @@ int __init seg6_init(void) { int err; - err = genl_register_family(&seg6_genl_family); + err = register_pernet_subsys(&ip6_segments_ops); if (err) goto out; - err = register_pernet_subsys(&ip6_segments_ops); + err = genl_register_family(&seg6_genl_family); if (err) - goto out_unregister_genl; + goto out_unregister_pernet; #ifdef CONFIG_IPV6_SEG6_LWTUNNEL err = seg6_iptunnel_init(); if (err) - goto out_unregister_pernet; + goto out_unregister_genl; err = seg6_local_init(); - if (err) - goto out_unregister_pernet; + if (err) { + seg6_iptunnel_exit(); + goto out_unregister_genl; + } #endif #ifdef CONFIG_IPV6_SEG6_HMAC @@ -548,11 +550,11 @@ out_unregister_iptun: #endif #endif #ifdef CONFIG_IPV6_SEG6_LWTUNNEL -out_unregister_pernet: - unregister_pernet_subsys(&ip6_segments_ops); -#endif out_unregister_genl: genl_unregister_family(&seg6_genl_family); +#endif +out_unregister_pernet: + unregister_pernet_subsys(&ip6_segments_ops); goto out; } diff --git a/net/iucv/iucv.c b/net/iucv/iucv.c index 6334f64f04d5..b0b3e9c5af44 100644 --- a/net/iucv/iucv.c +++ b/net/iucv/iucv.c @@ -156,7 +156,7 @@ static char iucv_error_pathid[16] = "INVALID PATHID"; static LIST_HEAD(iucv_handler_list); /* - * iucv_path_table: an array of iucv_path structures. + * iucv_path_table: array of pointers to iucv_path structures. */ static struct iucv_path **iucv_path_table; static unsigned long iucv_max_pathid; @@ -544,7 +544,7 @@ static int iucv_enable(void) cpus_read_lock(); rc = -ENOMEM; - alloc_size = iucv_max_pathid * sizeof(struct iucv_path); + alloc_size = iucv_max_pathid * sizeof(*iucv_path_table); iucv_path_table = kzalloc(alloc_size, GFP_KERNEL); if (!iucv_path_table) goto out; diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c index dd3153966173..7bf14cf9ffaa 100644 --- a/net/l2tp/l2tp_ip6.c +++ b/net/l2tp/l2tp_ip6.c @@ -627,7 +627,7 @@ static int l2tp_ip6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) back_from_confirm: lock_sock(sk); - ulen = len + skb_queue_empty(&sk->sk_write_queue) ? transhdrlen : 0; + ulen = len + (skb_queue_empty(&sk->sk_write_queue) ? transhdrlen : 0); err = ip6_append_data(sk, ip_generic_getfrag, msg, ulen, transhdrlen, &ipc6, &fl6, (struct rt6_info *)dst, diff --git a/net/mctp/route.c b/net/mctp/route.c index 7a47a58aa54b..6218dcd07e18 100644 --- a/net/mctp/route.c +++ b/net/mctp/route.c @@ -663,7 +663,7 @@ struct mctp_sk_key *mctp_alloc_local_tag(struct mctp_sock *msk, spin_unlock_irqrestore(&mns->keys_lock, flags); if (!tagbits) { - kfree(key); + mctp_key_unref(key); return ERR_PTR(-EBUSY); } diff --git a/net/mptcp/diag.c b/net/mptcp/diag.c index a536586742f2..6ff6f14674aa 100644 --- a/net/mptcp/diag.c +++ b/net/mptcp/diag.c @@ -13,17 +13,19 @@ #include <uapi/linux/mptcp.h> #include "protocol.h" -static int subflow_get_info(const struct sock *sk, struct sk_buff *skb) +static int subflow_get_info(struct sock *sk, struct sk_buff *skb) { struct mptcp_subflow_context *sf; struct nlattr *start; u32 flags = 0; + bool slow; int err; start = nla_nest_start_noflag(skb, INET_ULP_INFO_MPTCP); if (!start) return -EMSGSIZE; + slow = lock_sock_fast(sk); rcu_read_lock(); sf = rcu_dereference(inet_csk(sk)->icsk_ulp_data); if (!sf) { @@ -63,17 +65,19 @@ static int subflow_get_info(const struct sock *sk, struct sk_buff *skb) sf->map_data_len) || nla_put_u32(skb, MPTCP_SUBFLOW_ATTR_FLAGS, flags) || nla_put_u8(skb, MPTCP_SUBFLOW_ATTR_ID_REM, sf->remote_id) || - nla_put_u8(skb, MPTCP_SUBFLOW_ATTR_ID_LOC, sf->local_id)) { + nla_put_u8(skb, MPTCP_SUBFLOW_ATTR_ID_LOC, subflow_get_local_id(sf))) { err = -EMSGSIZE; goto nla_failure; } rcu_read_unlock(); + unlock_sock_fast(sk, slow); nla_nest_end(skb, start); return 0; nla_failure: rcu_read_unlock(); + unlock_sock_fast(sk, slow); nla_nest_cancel(skb, start); return err; } diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index 287a60381eae..58d17d9604e7 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -396,19 +396,6 @@ void mptcp_pm_free_anno_list(struct mptcp_sock *msk) } } -static bool lookup_address_in_vec(const struct mptcp_addr_info *addrs, unsigned int nr, - const struct mptcp_addr_info *addr) -{ - int i; - - for (i = 0; i < nr; i++) { - if (addrs[i].id == addr->id) - return true; - } - - return false; -} - /* Fill all the remote addresses into the array addrs[], * and return the array size. */ @@ -440,18 +427,34 @@ static unsigned int fill_remote_addresses_vec(struct mptcp_sock *msk, msk->pm.subflows++; addrs[i++] = remote; } else { + DECLARE_BITMAP(unavail_id, MPTCP_PM_MAX_ADDR_ID + 1); + + /* Forbid creation of new subflows matching existing + * ones, possibly already created by incoming ADD_ADDR + */ + bitmap_zero(unavail_id, MPTCP_PM_MAX_ADDR_ID + 1); + mptcp_for_each_subflow(msk, subflow) + if (READ_ONCE(subflow->local_id) == local->id) + __set_bit(subflow->remote_id, unavail_id); + mptcp_for_each_subflow(msk, subflow) { ssk = mptcp_subflow_tcp_sock(subflow); remote_address((struct sock_common *)ssk, &addrs[i]); - addrs[i].id = subflow->remote_id; + addrs[i].id = READ_ONCE(subflow->remote_id); if (deny_id0 && !addrs[i].id) continue; + if (test_bit(addrs[i].id, unavail_id)) + continue; + if (!mptcp_pm_addr_families_match(sk, local, &addrs[i])) continue; - if (!lookup_address_in_vec(addrs, i, &addrs[i]) && - msk->pm.subflows < subflows_max) { + if (msk->pm.subflows < subflows_max) { + /* forbid creating multiple address towards + * this id + */ + __set_bit(addrs[i].id, unavail_id); msk->pm.subflows++; i++; } @@ -799,18 +802,18 @@ static void mptcp_pm_nl_rm_addr_or_subflow(struct mptcp_sock *msk, mptcp_for_each_subflow_safe(msk, subflow, tmp) { struct sock *ssk = mptcp_subflow_tcp_sock(subflow); + u8 remote_id = READ_ONCE(subflow->remote_id); int how = RCV_SHUTDOWN | SEND_SHUTDOWN; - u8 id = subflow->local_id; + u8 id = subflow_get_local_id(subflow); - if (rm_type == MPTCP_MIB_RMADDR && subflow->remote_id != rm_id) + if (rm_type == MPTCP_MIB_RMADDR && remote_id != rm_id) continue; if (rm_type == MPTCP_MIB_RMSUBFLOW && !mptcp_local_id_match(msk, id, rm_id)) continue; pr_debug(" -> %s rm_list_ids[%d]=%u local_id=%u remote_id=%u mpc_id=%u", rm_type == MPTCP_MIB_RMADDR ? "address" : "subflow", - i, rm_id, subflow->local_id, subflow->remote_id, - msk->mpc_endpoint_id); + i, rm_id, id, remote_id, msk->mpc_endpoint_id); spin_unlock_bh(&msk->pm.lock); mptcp_subflow_shutdown(sk, ssk, how); @@ -901,7 +904,8 @@ static void __mptcp_pm_release_addr_entry(struct mptcp_pm_addr_entry *entry) } static int mptcp_pm_nl_append_new_local_addr(struct pm_nl_pernet *pernet, - struct mptcp_pm_addr_entry *entry) + struct mptcp_pm_addr_entry *entry, + bool needs_id) { struct mptcp_pm_addr_entry *cur, *del_entry = NULL; unsigned int addr_max; @@ -949,7 +953,7 @@ static int mptcp_pm_nl_append_new_local_addr(struct pm_nl_pernet *pernet, } } - if (!entry->addr.id) { + if (!entry->addr.id && needs_id) { find_next: entry->addr.id = find_next_zero_bit(pernet->id_bitmap, MPTCP_PM_MAX_ADDR_ID + 1, @@ -960,7 +964,7 @@ find_next: } } - if (!entry->addr.id) + if (!entry->addr.id && needs_id) goto out; __set_bit(entry->addr.id, pernet->id_bitmap); @@ -1092,7 +1096,7 @@ int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk, struct mptcp_addr_info *skc entry->ifindex = 0; entry->flags = MPTCP_PM_ADDR_FLAG_IMPLICIT; entry->lsk = NULL; - ret = mptcp_pm_nl_append_new_local_addr(pernet, entry); + ret = mptcp_pm_nl_append_new_local_addr(pernet, entry, true); if (ret < 0) kfree(entry); @@ -1285,6 +1289,18 @@ next: return 0; } +static bool mptcp_pm_has_addr_attr_id(const struct nlattr *attr, + struct genl_info *info) +{ + struct nlattr *tb[MPTCP_PM_ADDR_ATTR_MAX + 1]; + + if (!nla_parse_nested_deprecated(tb, MPTCP_PM_ADDR_ATTR_MAX, attr, + mptcp_pm_address_nl_policy, info->extack) && + tb[MPTCP_PM_ADDR_ATTR_ID]) + return true; + return false; +} + int mptcp_pm_nl_add_addr_doit(struct sk_buff *skb, struct genl_info *info) { struct nlattr *attr = info->attrs[MPTCP_PM_ENDPOINT_ADDR]; @@ -1326,7 +1342,8 @@ int mptcp_pm_nl_add_addr_doit(struct sk_buff *skb, struct genl_info *info) goto out_free; } } - ret = mptcp_pm_nl_append_new_local_addr(pernet, entry); + ret = mptcp_pm_nl_append_new_local_addr(pernet, entry, + !mptcp_pm_has_addr_attr_id(attr, info)); if (ret < 0) { GENL_SET_ERR_MSG_FMT(info, "too many addresses or duplicate one: %d", ret); goto out_free; @@ -1980,7 +1997,7 @@ static int mptcp_event_add_subflow(struct sk_buff *skb, const struct sock *ssk) if (WARN_ON_ONCE(!sf)) return -EINVAL; - if (nla_put_u8(skb, MPTCP_ATTR_LOC_ID, sf->local_id)) + if (nla_put_u8(skb, MPTCP_ATTR_LOC_ID, subflow_get_local_id(sf))) return -EMSGSIZE; if (nla_put_u8(skb, MPTCP_ATTR_REM_ID, sf->remote_id)) diff --git a/net/mptcp/pm_userspace.c b/net/mptcp/pm_userspace.c index 4f3901d5b8ef..d396a5973429 100644 --- a/net/mptcp/pm_userspace.c +++ b/net/mptcp/pm_userspace.c @@ -26,7 +26,8 @@ void mptcp_free_local_addr_list(struct mptcp_sock *msk) } static int mptcp_userspace_pm_append_new_local_addr(struct mptcp_sock *msk, - struct mptcp_pm_addr_entry *entry) + struct mptcp_pm_addr_entry *entry, + bool needs_id) { DECLARE_BITMAP(id_bitmap, MPTCP_PM_MAX_ADDR_ID + 1); struct mptcp_pm_addr_entry *match = NULL; @@ -41,7 +42,7 @@ static int mptcp_userspace_pm_append_new_local_addr(struct mptcp_sock *msk, spin_lock_bh(&msk->pm.lock); list_for_each_entry(e, &msk->pm.userspace_pm_local_addr_list, list) { addr_match = mptcp_addresses_equal(&e->addr, &entry->addr, true); - if (addr_match && entry->addr.id == 0) + if (addr_match && entry->addr.id == 0 && needs_id) entry->addr.id = e->addr.id; id_match = (e->addr.id == entry->addr.id); if (addr_match && id_match) { @@ -64,7 +65,7 @@ static int mptcp_userspace_pm_append_new_local_addr(struct mptcp_sock *msk, } *e = *entry; - if (!e->addr.id) + if (!e->addr.id && needs_id) e->addr.id = find_next_zero_bit(id_bitmap, MPTCP_PM_MAX_ADDR_ID + 1, 1); @@ -153,7 +154,7 @@ int mptcp_userspace_pm_get_local_id(struct mptcp_sock *msk, if (new_entry.addr.port == msk_sport) new_entry.addr.port = 0; - return mptcp_userspace_pm_append_new_local_addr(msk, &new_entry); + return mptcp_userspace_pm_append_new_local_addr(msk, &new_entry, true); } int mptcp_pm_nl_announce_doit(struct sk_buff *skb, struct genl_info *info) @@ -198,7 +199,7 @@ int mptcp_pm_nl_announce_doit(struct sk_buff *skb, struct genl_info *info) goto announce_err; } - err = mptcp_userspace_pm_append_new_local_addr(msk, &addr_val); + err = mptcp_userspace_pm_append_new_local_addr(msk, &addr_val, false); if (err < 0) { GENL_SET_ERR_MSG(info, "did not match address and id"); goto announce_err; @@ -233,7 +234,7 @@ static int mptcp_userspace_pm_remove_id_zero_address(struct mptcp_sock *msk, lock_sock(sk); mptcp_for_each_subflow(msk, subflow) { - if (subflow->local_id == 0) { + if (READ_ONCE(subflow->local_id) == 0) { has_id_0 = true; break; } @@ -378,7 +379,7 @@ int mptcp_pm_nl_subflow_create_doit(struct sk_buff *skb, struct genl_info *info) } local.addr = addr_l; - err = mptcp_userspace_pm_append_new_local_addr(msk, &local); + err = mptcp_userspace_pm_append_new_local_addr(msk, &local, false); if (err < 0) { GENL_SET_ERR_MSG(info, "did not match address and id"); goto create_err; diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 8ef2927ebca2..948606a537da 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -85,7 +85,7 @@ static int __mptcp_socket_create(struct mptcp_sock *msk) subflow->subflow_id = msk->subflow_id++; /* This is the first subflow, always with id 0 */ - subflow->local_id_valid = 1; + WRITE_ONCE(subflow->local_id, 0); mptcp_sock_graft(msk->first, sk->sk_socket); iput(SOCK_INODE(ssock)); diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index ed50f2015dc3..631a7f445f34 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -491,10 +491,9 @@ struct mptcp_subflow_context { remote_key_valid : 1, /* received the peer key from */ disposable : 1, /* ctx can be free at ulp release time */ stale : 1, /* unable to snd/rcv data, do not use for xmit */ - local_id_valid : 1, /* local_id is correctly initialized */ valid_csum_seen : 1, /* at least one csum validated */ is_mptfo : 1, /* subflow is doing TFO */ - __unused : 9; + __unused : 10; bool data_avail; bool scheduled; u32 remote_nonce; @@ -505,7 +504,7 @@ struct mptcp_subflow_context { u8 hmac[MPTCPOPT_HMAC_LEN]; /* MPJ subflow only */ u64 iasn; /* initial ack sequence number, MPC subflows only */ }; - u8 local_id; + s16 local_id; /* if negative not initialized yet */ u8 remote_id; u8 reset_seen:1; u8 reset_transient:1; @@ -556,6 +555,7 @@ mptcp_subflow_ctx_reset(struct mptcp_subflow_context *subflow) { memset(&subflow->reset, 0, sizeof(subflow->reset)); subflow->request_mptcp = 1; + WRITE_ONCE(subflow->local_id, -1); } static inline u64 @@ -1022,6 +1022,15 @@ int mptcp_pm_get_local_id(struct mptcp_sock *msk, struct sock_common *skc); int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk, struct mptcp_addr_info *skc); int mptcp_userspace_pm_get_local_id(struct mptcp_sock *msk, struct mptcp_addr_info *skc); +static inline u8 subflow_get_local_id(const struct mptcp_subflow_context *subflow) +{ + int local_id = READ_ONCE(subflow->local_id); + + if (local_id < 0) + return 0; + return local_id; +} + void __init mptcp_pm_nl_init(void); void mptcp_pm_nl_work(struct mptcp_sock *msk); void mptcp_pm_nl_rm_subflow_received(struct mptcp_sock *msk, diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index c34ecadee120..71ba86246ff8 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -535,7 +535,7 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb) subflow->backup = mp_opt.backup; subflow->thmac = mp_opt.thmac; subflow->remote_nonce = mp_opt.nonce; - subflow->remote_id = mp_opt.join_id; + WRITE_ONCE(subflow->remote_id, mp_opt.join_id); pr_debug("subflow=%p, thmac=%llu, remote_nonce=%u backup=%d", subflow, subflow->thmac, subflow->remote_nonce, subflow->backup); @@ -577,8 +577,8 @@ do_reset: static void subflow_set_local_id(struct mptcp_subflow_context *subflow, int local_id) { - subflow->local_id = local_id; - subflow->local_id_valid = 1; + WARN_ON_ONCE(local_id < 0 || local_id > 255); + WRITE_ONCE(subflow->local_id, local_id); } static int subflow_chk_local_id(struct sock *sk) @@ -587,7 +587,7 @@ static int subflow_chk_local_id(struct sock *sk) struct mptcp_sock *msk = mptcp_sk(subflow->conn); int err; - if (likely(subflow->local_id_valid)) + if (likely(subflow->local_id >= 0)) return 0; err = mptcp_pm_get_local_id(msk, (struct sock_common *)sk); @@ -1567,7 +1567,7 @@ int __mptcp_subflow_connect(struct sock *sk, const struct mptcp_addr_info *loc, pr_debug("msk=%p remote_token=%u local_id=%d remote_id=%d", msk, remote_token, local_id, remote_id); subflow->remote_token = remote_token; - subflow->remote_id = remote_id; + WRITE_ONCE(subflow->remote_id, remote_id); subflow->request_join = 1; subflow->request_bkup = !!(flags & MPTCP_PM_ADDR_FLAG_BACKUP); subflow->subflow_id = msk->subflow_id++; @@ -1731,6 +1731,7 @@ static struct mptcp_subflow_context *subflow_create_ctx(struct sock *sk, pr_debug("subflow=%p", ctx); ctx->tcp_sock = sk; + WRITE_ONCE(ctx->local_id, -1); return ctx; } @@ -1966,14 +1967,14 @@ static void subflow_ulp_clone(const struct request_sock *req, new_ctx->idsn = subflow_req->idsn; /* this is the first subflow, id is always 0 */ - new_ctx->local_id_valid = 1; + subflow_set_local_id(new_ctx, 0); } else if (subflow_req->mp_join) { new_ctx->ssn_offset = subflow_req->ssn_offset; new_ctx->mp_join = 1; new_ctx->fully_established = 1; new_ctx->remote_key_valid = 1; new_ctx->backup = subflow_req->backup; - new_ctx->remote_id = subflow_req->remote_id; + WRITE_ONCE(new_ctx->remote_id, subflow_req->remote_id); new_ctx->token = subflow_req->token; new_ctx->thmac = subflow_req->thmac; diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c index 920a5a29ae1d..a0571339239c 100644 --- a/net/netfilter/nf_flow_table_core.c +++ b/net/netfilter/nf_flow_table_core.c @@ -87,12 +87,22 @@ static u32 flow_offload_dst_cookie(struct flow_offload_tuple *flow_tuple) return 0; } +static struct dst_entry *nft_route_dst_fetch(struct nf_flow_route *route, + enum flow_offload_tuple_dir dir) +{ + struct dst_entry *dst = route->tuple[dir].dst; + + route->tuple[dir].dst = NULL; + + return dst; +} + static int flow_offload_fill_route(struct flow_offload *flow, - const struct nf_flow_route *route, + struct nf_flow_route *route, enum flow_offload_tuple_dir dir) { struct flow_offload_tuple *flow_tuple = &flow->tuplehash[dir].tuple; - struct dst_entry *dst = route->tuple[dir].dst; + struct dst_entry *dst = nft_route_dst_fetch(route, dir); int i, j = 0; switch (flow_tuple->l3proto) { @@ -122,6 +132,7 @@ static int flow_offload_fill_route(struct flow_offload *flow, ETH_ALEN); flow_tuple->out.ifidx = route->tuple[dir].out.ifindex; flow_tuple->out.hw_ifidx = route->tuple[dir].out.hw_ifindex; + dst_release(dst); break; case FLOW_OFFLOAD_XMIT_XFRM: case FLOW_OFFLOAD_XMIT_NEIGH: @@ -146,7 +157,7 @@ static void nft_flow_dst_release(struct flow_offload *flow, } void flow_offload_route_init(struct flow_offload *flow, - const struct nf_flow_route *route) + struct nf_flow_route *route) { flow_offload_fill_route(flow, route, FLOW_OFFLOAD_DIR_ORIGINAL); flow_offload_fill_route(flow, route, FLOW_OFFLOAD_DIR_REPLY); diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index f8e3f70c35bd..7e938c7397dd 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -684,15 +684,16 @@ static int nft_delobj(struct nft_ctx *ctx, struct nft_object *obj) return err; } -static int nft_trans_flowtable_add(struct nft_ctx *ctx, int msg_type, - struct nft_flowtable *flowtable) +static struct nft_trans * +nft_trans_flowtable_add(struct nft_ctx *ctx, int msg_type, + struct nft_flowtable *flowtable) { struct nft_trans *trans; trans = nft_trans_alloc(ctx, msg_type, sizeof(struct nft_trans_flowtable)); if (trans == NULL) - return -ENOMEM; + return ERR_PTR(-ENOMEM); if (msg_type == NFT_MSG_NEWFLOWTABLE) nft_activate_next(ctx->net, flowtable); @@ -701,22 +702,22 @@ static int nft_trans_flowtable_add(struct nft_ctx *ctx, int msg_type, nft_trans_flowtable(trans) = flowtable; nft_trans_commit_list_add_tail(ctx->net, trans); - return 0; + return trans; } static int nft_delflowtable(struct nft_ctx *ctx, struct nft_flowtable *flowtable) { - int err; + struct nft_trans *trans; - err = nft_trans_flowtable_add(ctx, NFT_MSG_DELFLOWTABLE, flowtable); - if (err < 0) - return err; + trans = nft_trans_flowtable_add(ctx, NFT_MSG_DELFLOWTABLE, flowtable); + if (IS_ERR(trans)) + return PTR_ERR(trans); nft_deactivate_next(ctx->net, flowtable); nft_use_dec(&ctx->table->use); - return err; + return 0; } static void __nft_reg_track_clobber(struct nft_regs_track *track, u8 dreg) @@ -1251,6 +1252,7 @@ static int nf_tables_updtable(struct nft_ctx *ctx) return 0; err_register_hooks: + ctx->table->flags |= NFT_TABLE_F_DORMANT; nft_trans_destroy(trans); return ret; } @@ -2080,7 +2082,7 @@ static struct nft_hook *nft_netdev_hook_alloc(struct net *net, struct nft_hook *hook; int err; - hook = kmalloc(sizeof(struct nft_hook), GFP_KERNEL_ACCOUNT); + hook = kzalloc(sizeof(struct nft_hook), GFP_KERNEL_ACCOUNT); if (!hook) { err = -ENOMEM; goto err_hook_alloc; @@ -2503,19 +2505,15 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask, RCU_INIT_POINTER(chain->blob_gen_0, blob); RCU_INIT_POINTER(chain->blob_gen_1, blob); - err = nf_tables_register_hook(net, table, chain); - if (err < 0) - goto err_destroy_chain; - if (!nft_use_inc(&table->use)) { err = -EMFILE; - goto err_use; + goto err_destroy_chain; } trans = nft_trans_chain_add(ctx, NFT_MSG_NEWCHAIN); if (IS_ERR(trans)) { err = PTR_ERR(trans); - goto err_unregister_hook; + goto err_trans; } nft_trans_chain_policy(trans) = NFT_CHAIN_POLICY_UNSET; @@ -2523,17 +2521,22 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask, nft_trans_chain_policy(trans) = policy; err = nft_chain_add(table, chain); - if (err < 0) { - nft_trans_destroy(trans); - goto err_unregister_hook; - } + if (err < 0) + goto err_chain_add; + + /* This must be LAST to ensure no packets are walking over this chain. */ + err = nf_tables_register_hook(net, table, chain); + if (err < 0) + goto err_register_hook; return 0; -err_unregister_hook: +err_register_hook: + nft_chain_del(chain); +err_chain_add: + nft_trans_destroy(trans); +err_trans: nft_use_dec_restore(&table->use); -err_use: - nf_tables_unregister_hook(net, table, chain); err_destroy_chain: nf_tables_chain_destroy(ctx); @@ -8455,9 +8458,9 @@ static int nf_tables_newflowtable(struct sk_buff *skb, u8 family = info->nfmsg->nfgen_family; const struct nf_flowtable_type *type; struct nft_flowtable *flowtable; - struct nft_hook *hook, *next; struct net *net = info->net; struct nft_table *table; + struct nft_trans *trans; struct nft_ctx ctx; int err; @@ -8537,34 +8540,34 @@ static int nf_tables_newflowtable(struct sk_buff *skb, err = nft_flowtable_parse_hook(&ctx, nla, &flowtable_hook, flowtable, extack, true); if (err < 0) - goto err4; + goto err_flowtable_parse_hooks; list_splice(&flowtable_hook.list, &flowtable->hook_list); flowtable->data.priority = flowtable_hook.priority; flowtable->hooknum = flowtable_hook.num; + trans = nft_trans_flowtable_add(&ctx, NFT_MSG_NEWFLOWTABLE, flowtable); + if (IS_ERR(trans)) { + err = PTR_ERR(trans); + goto err_flowtable_trans; + } + + /* This must be LAST to ensure no packets are walking over this flowtable. */ err = nft_register_flowtable_net_hooks(ctx.net, table, &flowtable->hook_list, flowtable); - if (err < 0) { - nft_hooks_destroy(&flowtable->hook_list); - goto err4; - } - - err = nft_trans_flowtable_add(&ctx, NFT_MSG_NEWFLOWTABLE, flowtable); if (err < 0) - goto err5; + goto err_flowtable_hooks; list_add_tail_rcu(&flowtable->list, &table->flowtables); return 0; -err5: - list_for_each_entry_safe(hook, next, &flowtable->hook_list, list) { - nft_unregister_flowtable_hook(net, flowtable, hook); - list_del_rcu(&hook->list); - kfree_rcu(hook, rcu); - } -err4: + +err_flowtable_hooks: + nft_trans_destroy(trans); +err_flowtable_trans: + nft_hooks_destroy(&flowtable->hook_list); +err_flowtable_parse_hooks: flowtable->data.type->free(&flowtable->data); err3: module_put(type->owner); diff --git a/net/phonet/datagram.c b/net/phonet/datagram.c index 3aa50dc7535b..976fe250b509 100644 --- a/net/phonet/datagram.c +++ b/net/phonet/datagram.c @@ -34,10 +34,10 @@ static int pn_ioctl(struct sock *sk, int cmd, int *karg) switch (cmd) { case SIOCINQ: - lock_sock(sk); + spin_lock_bh(&sk->sk_receive_queue.lock); skb = skb_peek(&sk->sk_receive_queue); *karg = skb ? skb->len : 0; - release_sock(sk); + spin_unlock_bh(&sk->sk_receive_queue.lock); return 0; case SIOCPNADDRESOURCE: diff --git a/net/phonet/pep.c b/net/phonet/pep.c index faba31f2eff2..3dd5f52bc1b5 100644 --- a/net/phonet/pep.c +++ b/net/phonet/pep.c @@ -917,6 +917,37 @@ static int pep_sock_enable(struct sock *sk, struct sockaddr *addr, int len) return 0; } +static unsigned int pep_first_packet_length(struct sock *sk) +{ + struct pep_sock *pn = pep_sk(sk); + struct sk_buff_head *q; + struct sk_buff *skb; + unsigned int len = 0; + bool found = false; + + if (sock_flag(sk, SOCK_URGINLINE)) { + q = &pn->ctrlreq_queue; + spin_lock_bh(&q->lock); + skb = skb_peek(q); + if (skb) { + len = skb->len; + found = true; + } + spin_unlock_bh(&q->lock); + } + + if (likely(!found)) { + q = &sk->sk_receive_queue; + spin_lock_bh(&q->lock); + skb = skb_peek(q); + if (skb) + len = skb->len; + spin_unlock_bh(&q->lock); + } + + return len; +} + static int pep_ioctl(struct sock *sk, int cmd, int *karg) { struct pep_sock *pn = pep_sk(sk); @@ -929,15 +960,7 @@ static int pep_ioctl(struct sock *sk, int cmd, int *karg) break; } - lock_sock(sk); - if (sock_flag(sk, SOCK_URGINLINE) && - !skb_queue_empty(&pn->ctrlreq_queue)) - *karg = skb_peek(&pn->ctrlreq_queue)->len; - else if (!skb_queue_empty(&sk->sk_receive_queue)) - *karg = skb_peek(&sk->sk_receive_queue)->len; - else - *karg = 0; - release_sock(sk); + *karg = pep_first_packet_length(sk); ret = 0; break; diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index 0a1a9e40f237..6faa7d00da09 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -232,18 +232,14 @@ release_idr: return err; } -static bool is_mirred_nested(void) -{ - return unlikely(__this_cpu_read(mirred_nest_level) > 1); -} - -static int tcf_mirred_forward(bool want_ingress, struct sk_buff *skb) +static int +tcf_mirred_forward(bool at_ingress, bool want_ingress, struct sk_buff *skb) { int err; if (!want_ingress) err = tcf_dev_queue_xmit(skb, dev_queue_xmit); - else if (is_mirred_nested()) + else if (!at_ingress) err = netif_rx(skb); else err = netif_receive_skb(skb); @@ -270,8 +266,7 @@ static int tcf_mirred_to_dev(struct sk_buff *skb, struct tcf_mirred *m, if (unlikely(!(dev->flags & IFF_UP)) || !netif_carrier_ok(dev)) { net_notice_ratelimited("tc mirred to Houston: device %s is down\n", dev->name); - err = -ENODEV; - goto out; + goto err_cant_do; } /* we could easily avoid the clone only if called by ingress and clsact; @@ -283,10 +278,8 @@ static int tcf_mirred_to_dev(struct sk_buff *skb, struct tcf_mirred *m, tcf_mirred_can_reinsert(retval); if (!dont_clone) { skb_to_send = skb_clone(skb, GFP_ATOMIC); - if (!skb_to_send) { - err = -ENOMEM; - goto out; - } + if (!skb_to_send) + goto err_cant_do; } want_ingress = tcf_mirred_act_wants_ingress(m_eaction); @@ -319,19 +312,20 @@ static int tcf_mirred_to_dev(struct sk_buff *skb, struct tcf_mirred *m, skb_set_redirected(skb_to_send, skb_to_send->tc_at_ingress); - err = tcf_mirred_forward(want_ingress, skb_to_send); + err = tcf_mirred_forward(at_ingress, want_ingress, skb_to_send); } else { - err = tcf_mirred_forward(want_ingress, skb_to_send); + err = tcf_mirred_forward(at_ingress, want_ingress, skb_to_send); } - - if (err) { -out: + if (err) tcf_action_inc_overlimit_qstats(&m->common); - if (is_redirect) - retval = TC_ACT_SHOT; - } return retval; + +err_cant_do: + if (is_redirect) + retval = TC_ACT_SHOT; + tcf_action_inc_overlimit_qstats(&m->common); + return retval; } static int tcf_blockcast_redir(struct sk_buff *skb, struct tcf_mirred *m, diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index efb9d2811b73..6ee7064c82fc 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -2460,8 +2460,11 @@ unbind_filter: } errout_idr: - if (!fold) + if (!fold) { + spin_lock(&tp->lock); idr_remove(&head->handle_idr, fnew->handle); + spin_unlock(&tp->lock); + } __fl_put(fnew); errout_tb: kfree(tb); diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c index 5b045284849e..c9189a970eec 100644 --- a/net/switchdev/switchdev.c +++ b/net/switchdev/switchdev.c @@ -19,6 +19,35 @@ #include <linux/rtnetlink.h> #include <net/switchdev.h> +static bool switchdev_obj_eq(const struct switchdev_obj *a, + const struct switchdev_obj *b) +{ + const struct switchdev_obj_port_vlan *va, *vb; + const struct switchdev_obj_port_mdb *ma, *mb; + + if (a->id != b->id || a->orig_dev != b->orig_dev) + return false; + + switch (a->id) { + case SWITCHDEV_OBJ_ID_PORT_VLAN: + va = SWITCHDEV_OBJ_PORT_VLAN(a); + vb = SWITCHDEV_OBJ_PORT_VLAN(b); + return va->flags == vb->flags && + va->vid == vb->vid && + va->changed == vb->changed; + case SWITCHDEV_OBJ_ID_PORT_MDB: + case SWITCHDEV_OBJ_ID_HOST_MDB: + ma = SWITCHDEV_OBJ_PORT_MDB(a); + mb = SWITCHDEV_OBJ_PORT_MDB(b); + return ma->vid == mb->vid && + ether_addr_equal(ma->addr, mb->addr); + default: + break; + } + + BUG(); +} + static LIST_HEAD(deferred); static DEFINE_SPINLOCK(deferred_lock); @@ -307,6 +336,50 @@ int switchdev_port_obj_del(struct net_device *dev, } EXPORT_SYMBOL_GPL(switchdev_port_obj_del); +/** + * switchdev_port_obj_act_is_deferred - Is object action pending? + * + * @dev: port device + * @nt: type of action; add or delete + * @obj: object to test + * + * Returns true if a deferred item is pending, which is + * equivalent to the action @nt on an object @obj. + * + * rtnl_lock must be held. + */ +bool switchdev_port_obj_act_is_deferred(struct net_device *dev, + enum switchdev_notifier_type nt, + const struct switchdev_obj *obj) +{ + struct switchdev_deferred_item *dfitem; + bool found = false; + + ASSERT_RTNL(); + + spin_lock_bh(&deferred_lock); + + list_for_each_entry(dfitem, &deferred, list) { + if (dfitem->dev != dev) + continue; + + if ((dfitem->func == switchdev_port_obj_add_deferred && + nt == SWITCHDEV_PORT_OBJ_ADD) || + (dfitem->func == switchdev_port_obj_del_deferred && + nt == SWITCHDEV_PORT_OBJ_DEL)) { + if (switchdev_obj_eq((const void *)dfitem->data, obj)) { + found = true; + break; + } + } + } + + spin_unlock_bh(&deferred_lock); + + return found; +} +EXPORT_SYMBOL_GPL(switchdev_port_obj_act_is_deferred); + static ATOMIC_NOTIFIER_HEAD(switchdev_notif_chain); static BLOCKING_NOTIFIER_HEAD(switchdev_blocking_notif_chain); diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c index 1c2c6800949d..b4674f03d71a 100644 --- a/net/tls/tls_main.c +++ b/net/tls/tls_main.c @@ -1003,7 +1003,7 @@ static u16 tls_user_config(struct tls_context *ctx, bool tx) return 0; } -static int tls_get_info(const struct sock *sk, struct sk_buff *skb) +static int tls_get_info(struct sock *sk, struct sk_buff *skb) { u16 version, cipher_type; struct tls_context *ctx; diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index 9fbc70200cd0..de96959336c4 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -1772,7 +1772,8 @@ static int process_rx_list(struct tls_sw_context_rx *ctx, u8 *control, size_t skip, size_t len, - bool is_peek) + bool is_peek, + bool *more) { struct sk_buff *skb = skb_peek(&ctx->rx_list); struct tls_msg *tlm; @@ -1785,7 +1786,7 @@ static int process_rx_list(struct tls_sw_context_rx *ctx, err = tls_record_content_type(msg, tlm, control); if (err <= 0) - goto out; + goto more; if (skip < rxm->full_len) break; @@ -1803,12 +1804,12 @@ static int process_rx_list(struct tls_sw_context_rx *ctx, err = tls_record_content_type(msg, tlm, control); if (err <= 0) - goto out; + goto more; err = skb_copy_datagram_msg(skb, rxm->offset + skip, msg, chunk); if (err < 0) - goto out; + goto more; len = len - chunk; copied = copied + chunk; @@ -1844,6 +1845,10 @@ static int process_rx_list(struct tls_sw_context_rx *ctx, out: return copied ? : err; +more: + if (more) + *more = true; + goto out; } static bool @@ -1947,6 +1952,7 @@ int tls_sw_recvmsg(struct sock *sk, int target, err; bool is_kvec = iov_iter_is_kvec(&msg->msg_iter); bool is_peek = flags & MSG_PEEK; + bool rx_more = false; bool released = true; bool bpf_strp_enabled; bool zc_capable; @@ -1966,12 +1972,12 @@ int tls_sw_recvmsg(struct sock *sk, goto end; /* Process pending decrypted records. It must be non-zero-copy */ - err = process_rx_list(ctx, msg, &control, 0, len, is_peek); + err = process_rx_list(ctx, msg, &control, 0, len, is_peek, &rx_more); if (err < 0) goto end; copied = err; - if (len <= copied) + if (len <= copied || (copied && control != TLS_RECORD_TYPE_DATA) || rx_more) goto end; target = sock_rcvlowat(sk, flags & MSG_WAITALL, len); @@ -2064,6 +2070,8 @@ put_on_rx_list: decrypted += chunk; len -= chunk; __skb_queue_tail(&ctx->rx_list, skb); + if (unlikely(control != TLS_RECORD_TYPE_DATA)) + break; continue; } @@ -2128,10 +2136,10 @@ recv_end: /* Drain records from the rx_list & copy if required */ if (is_peek || is_kvec) err = process_rx_list(ctx, msg, &control, copied, - decrypted, is_peek); + decrypted, is_peek, NULL); else err = process_rx_list(ctx, msg, &control, 0, - async_copy_bytes, is_peek); + async_copy_bytes, is_peek, NULL); } copied += decrypted; diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 30b178ebba60..0748e7ea5210 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -782,19 +782,6 @@ static int unix_seqpacket_sendmsg(struct socket *, struct msghdr *, size_t); static int unix_seqpacket_recvmsg(struct socket *, struct msghdr *, size_t, int); -static int unix_set_peek_off(struct sock *sk, int val) -{ - struct unix_sock *u = unix_sk(sk); - - if (mutex_lock_interruptible(&u->iolock)) - return -EINTR; - - WRITE_ONCE(sk->sk_peek_off, val); - mutex_unlock(&u->iolock); - - return 0; -} - #ifdef CONFIG_PROC_FS static int unix_count_nr_fds(struct sock *sk) { @@ -862,7 +849,7 @@ static const struct proto_ops unix_stream_ops = { .read_skb = unix_stream_read_skb, .mmap = sock_no_mmap, .splice_read = unix_stream_splice_read, - .set_peek_off = unix_set_peek_off, + .set_peek_off = sk_set_peek_off, .show_fdinfo = unix_show_fdinfo, }; @@ -886,7 +873,7 @@ static const struct proto_ops unix_dgram_ops = { .read_skb = unix_read_skb, .recvmsg = unix_dgram_recvmsg, .mmap = sock_no_mmap, - .set_peek_off = unix_set_peek_off, + .set_peek_off = sk_set_peek_off, .show_fdinfo = unix_show_fdinfo, }; @@ -909,7 +896,7 @@ static const struct proto_ops unix_seqpacket_ops = { .sendmsg = unix_seqpacket_sendmsg, .recvmsg = unix_seqpacket_recvmsg, .mmap = sock_no_mmap, - .set_peek_off = unix_set_peek_off, + .set_peek_off = sk_set_peek_off, .show_fdinfo = unix_show_fdinfo, }; diff --git a/net/unix/garbage.c b/net/unix/garbage.c index 2ff7ddbaa782..2a81880dac7b 100644 --- a/net/unix/garbage.c +++ b/net/unix/garbage.c @@ -284,9 +284,17 @@ void unix_gc(void) * which are creating the cycle(s). */ skb_queue_head_init(&hitlist); - list_for_each_entry(u, &gc_candidates, link) + list_for_each_entry(u, &gc_candidates, link) { scan_children(&u->sk, inc_inflight, &hitlist); +#if IS_ENABLED(CONFIG_AF_UNIX_OOB) + if (u->oob_skb) { + kfree_skb(u->oob_skb); + u->oob_skb = NULL; + } +#endif + } + /* not_cycle_list contains those sockets which do not make up a * cycle. Restore these to the inflight list. */ @@ -314,18 +322,6 @@ void unix_gc(void) /* Here we are. Hitlist is filled. Die. */ __skb_queue_purge(&hitlist); -#if IS_ENABLED(CONFIG_AF_UNIX_OOB) - while (!list_empty(&gc_candidates)) { - u = list_entry(gc_candidates.next, struct unix_sock, link); - if (u->oob_skb) { - struct sk_buff *skb = u->oob_skb; - - u->oob_skb = NULL; - kfree_skb(skb); - } - } -#endif - spin_lock(&unix_gc_lock); /* There could be io_uring registered files, just push them back to diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index 1eadfac03cc4..b78c0e095e22 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -722,7 +722,8 @@ static struct sk_buff *xsk_build_skb(struct xdp_sock *xs, memcpy(vaddr, buffer, len); kunmap_local(vaddr); - skb_add_rx_frag(skb, nr_frags, page, 0, len, 0); + skb_add_rx_frag(skb, nr_frags, page, 0, len, PAGE_SIZE); + refcount_add(PAGE_SIZE, &xs->sk.sk_wmem_alloc); } if (first_frag && desc->options & XDP_TX_METADATA) { diff --git a/scripts/bpf_doc.py b/scripts/bpf_doc.py index 61b7dddedc46..0669bac5e900 100755 --- a/scripts/bpf_doc.py +++ b/scripts/bpf_doc.py @@ -513,7 +513,7 @@ eBPF programs can have an associated license, passed along with the bytecode instructions to the kernel when the programs are loaded. The format for that string is identical to the one in use for kernel modules (Dual licenses, such as "Dual BSD/GPL", may be used). Some helper functions are only accessible to -programs that are compatible with the GNU Privacy License (GPL). +programs that are compatible with the GNU General Public License (GNU GPL). In order to use such helpers, the eBPF program must be loaded with the correct license string passed (via **attr**) to the **bpf**\\ () system call, and this diff --git a/tools/net/ynl/lib/ynl.c b/tools/net/ynl/lib/ynl.c index c82a7f41b31c..6e6d474c8366 100644 --- a/tools/net/ynl/lib/ynl.c +++ b/tools/net/ynl/lib/ynl.c @@ -466,6 +466,8 @@ ynl_gemsg_start_dump(struct ynl_sock *ys, __u32 id, __u8 cmd, __u8 version) int ynl_recv_ack(struct ynl_sock *ys, int ret) { + struct ynl_parse_arg yarg = { .ys = ys, }; + if (!ret) { yerr(ys, YNL_ERROR_EXPECT_ACK, "Expecting an ACK but nothing received"); @@ -478,7 +480,7 @@ int ynl_recv_ack(struct ynl_sock *ys, int ret) return ret; } return mnl_cb_run(ys->rx_buf, ret, ys->seq, ys->portid, - ynl_cb_null, ys); + ynl_cb_null, &yarg); } int ynl_cb_null(const struct nlmsghdr *nlh, void *data) @@ -586,7 +588,13 @@ static int ynl_sock_read_family(struct ynl_sock *ys, const char *family_name) return err; } - return ynl_recv_ack(ys, err); + err = ynl_recv_ack(ys, err); + if (err < 0) { + free(ys->mcast_groups); + return err; + } + + return 0; } struct ynl_sock * @@ -741,11 +749,14 @@ err_free: static int ynl_ntf_trampoline(const struct nlmsghdr *nlh, void *data) { - return ynl_ntf_parse((struct ynl_sock *)data, nlh); + struct ynl_parse_arg *yarg = data; + + return ynl_ntf_parse(yarg->ys, nlh); } int ynl_ntf_check(struct ynl_sock *ys) { + struct ynl_parse_arg yarg = { .ys = ys, }; ssize_t len; int err; @@ -767,7 +778,7 @@ int ynl_ntf_check(struct ynl_sock *ys) return len; err = mnl_cb_run2(ys->rx_buf, len, ys->seq, ys->portid, - ynl_ntf_trampoline, ys, + ynl_ntf_trampoline, &yarg, ynl_cb_array, NLMSG_MIN_TYPE); if (err < 0) return err; diff --git a/tools/testing/selftests/bpf/prog_tests/iters.c b/tools/testing/selftests/bpf/prog_tests/iters.c index bf84d4a1d9ae..3c440370c1f0 100644 --- a/tools/testing/selftests/bpf/prog_tests/iters.c +++ b/tools/testing/selftests/bpf/prog_tests/iters.c @@ -193,6 +193,7 @@ static void subtest_task_iters(void) ASSERT_EQ(skel->bss->procs_cnt, 1, "procs_cnt"); ASSERT_EQ(skel->bss->threads_cnt, thread_num + 1, "threads_cnt"); ASSERT_EQ(skel->bss->proc_threads_cnt, thread_num + 1, "proc_threads_cnt"); + ASSERT_EQ(skel->bss->invalid_cnt, 0, "invalid_cnt"); pthread_mutex_unlock(&do_nothing_mutex); for (int i = 0; i < thread_num; i++) ASSERT_OK(pthread_join(thread_ids[i], &ret), "pthread_join"); diff --git a/tools/testing/selftests/bpf/prog_tests/read_vsyscall.c b/tools/testing/selftests/bpf/prog_tests/read_vsyscall.c new file mode 100644 index 000000000000..3405923fe4e6 --- /dev/null +++ b/tools/testing/selftests/bpf/prog_tests/read_vsyscall.c @@ -0,0 +1,57 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (C) 2024. Huawei Technologies Co., Ltd */ +#include "test_progs.h" +#include "read_vsyscall.skel.h" + +#if defined(__x86_64__) +/* For VSYSCALL_ADDR */ +#include <asm/vsyscall.h> +#else +/* To prevent build failure on non-x86 arch */ +#define VSYSCALL_ADDR 0UL +#endif + +struct read_ret_desc { + const char *name; + int ret; +} all_read[] = { + { .name = "probe_read_kernel", .ret = -ERANGE }, + { .name = "probe_read_kernel_str", .ret = -ERANGE }, + { .name = "probe_read", .ret = -ERANGE }, + { .name = "probe_read_str", .ret = -ERANGE }, + { .name = "probe_read_user", .ret = -EFAULT }, + { .name = "probe_read_user_str", .ret = -EFAULT }, + { .name = "copy_from_user", .ret = -EFAULT }, + { .name = "copy_from_user_task", .ret = -EFAULT }, +}; + +void test_read_vsyscall(void) +{ + struct read_vsyscall *skel; + unsigned int i; + int err; + +#if !defined(__x86_64__) + test__skip(); + return; +#endif + skel = read_vsyscall__open_and_load(); + if (!ASSERT_OK_PTR(skel, "read_vsyscall open_load")) + return; + + skel->bss->target_pid = getpid(); + err = read_vsyscall__attach(skel); + if (!ASSERT_EQ(err, 0, "read_vsyscall attach")) + goto out; + + /* userspace may don't have vsyscall page due to LEGACY_VSYSCALL_NONE, + * but it doesn't affect the returned error codes. + */ + skel->bss->user_ptr = (void *)VSYSCALL_ADDR; + usleep(1); + + for (i = 0; i < ARRAY_SIZE(all_read); i++) + ASSERT_EQ(skel->bss->read_ret[i], all_read[i].ret, all_read[i].name); +out: + read_vsyscall__destroy(skel); +} diff --git a/tools/testing/selftests/bpf/prog_tests/timer.c b/tools/testing/selftests/bpf/prog_tests/timer.c index 760ad96b4be0..d66687f1ee6a 100644 --- a/tools/testing/selftests/bpf/prog_tests/timer.c +++ b/tools/testing/selftests/bpf/prog_tests/timer.c @@ -4,10 +4,29 @@ #include "timer.skel.h" #include "timer_failure.skel.h" +#define NUM_THR 8 + +static void *spin_lock_thread(void *arg) +{ + int i, err, prog_fd = *(int *)arg; + LIBBPF_OPTS(bpf_test_run_opts, topts); + + for (i = 0; i < 10000; i++) { + err = bpf_prog_test_run_opts(prog_fd, &topts); + if (!ASSERT_OK(err, "test_run_opts err") || + !ASSERT_OK(topts.retval, "test_run_opts retval")) + break; + } + + pthread_exit(arg); +} + static int timer(struct timer *timer_skel) { - int err, prog_fd; + int i, err, prog_fd; LIBBPF_OPTS(bpf_test_run_opts, topts); + pthread_t thread_id[NUM_THR]; + void *ret; err = timer__attach(timer_skel); if (!ASSERT_OK(err, "timer_attach")) @@ -43,6 +62,20 @@ static int timer(struct timer *timer_skel) /* check that code paths completed */ ASSERT_EQ(timer_skel->bss->ok, 1 | 2 | 4, "ok"); + prog_fd = bpf_program__fd(timer_skel->progs.race); + for (i = 0; i < NUM_THR; i++) { + err = pthread_create(&thread_id[i], NULL, + &spin_lock_thread, &prog_fd); + if (!ASSERT_OK(err, "pthread_create")) + break; + } + + while (i) { + err = pthread_join(thread_id[--i], &ret); + if (ASSERT_OK(err, "pthread_join")) + ASSERT_EQ(ret, (void *)&prog_fd, "pthread_join"); + } + return 0; } diff --git a/tools/testing/selftests/bpf/progs/iters_task.c b/tools/testing/selftests/bpf/progs/iters_task.c index c9b4055cd410..e4d53e40ff20 100644 --- a/tools/testing/selftests/bpf/progs/iters_task.c +++ b/tools/testing/selftests/bpf/progs/iters_task.c @@ -10,7 +10,7 @@ char _license[] SEC("license") = "GPL"; pid_t target_pid; -int procs_cnt, threads_cnt, proc_threads_cnt; +int procs_cnt, threads_cnt, proc_threads_cnt, invalid_cnt; void bpf_rcu_read_lock(void) __ksym; void bpf_rcu_read_unlock(void) __ksym; @@ -26,6 +26,16 @@ int iter_task_for_each_sleep(void *ctx) procs_cnt = threads_cnt = proc_threads_cnt = 0; bpf_rcu_read_lock(); + bpf_for_each(task, pos, NULL, ~0U) { + /* Below instructions shouldn't be executed for invalid flags */ + invalid_cnt++; + } + + bpf_for_each(task, pos, NULL, BPF_TASK_ITER_PROC_THREADS) { + /* Below instructions shouldn't be executed for invalid task__nullable */ + invalid_cnt++; + } + bpf_for_each(task, pos, NULL, BPF_TASK_ITER_ALL_PROCS) if (pos->pid == target_pid) procs_cnt++; diff --git a/tools/testing/selftests/bpf/progs/read_vsyscall.c b/tools/testing/selftests/bpf/progs/read_vsyscall.c new file mode 100644 index 000000000000..986f96687ae1 --- /dev/null +++ b/tools/testing/selftests/bpf/progs/read_vsyscall.c @@ -0,0 +1,45 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (C) 2024. Huawei Technologies Co., Ltd */ +#include <linux/types.h> +#include <bpf/bpf_helpers.h> + +#include "bpf_misc.h" + +int target_pid = 0; +void *user_ptr = 0; +int read_ret[8]; + +char _license[] SEC("license") = "GPL"; + +SEC("fentry/" SYS_PREFIX "sys_nanosleep") +int do_probe_read(void *ctx) +{ + char buf[8]; + + if ((bpf_get_current_pid_tgid() >> 32) != target_pid) + return 0; + + read_ret[0] = bpf_probe_read_kernel(buf, sizeof(buf), user_ptr); + read_ret[1] = bpf_probe_read_kernel_str(buf, sizeof(buf), user_ptr); + read_ret[2] = bpf_probe_read(buf, sizeof(buf), user_ptr); + read_ret[3] = bpf_probe_read_str(buf, sizeof(buf), user_ptr); + read_ret[4] = bpf_probe_read_user(buf, sizeof(buf), user_ptr); + read_ret[5] = bpf_probe_read_user_str(buf, sizeof(buf), user_ptr); + + return 0; +} + +SEC("fentry.s/" SYS_PREFIX "sys_nanosleep") +int do_copy_from_user(void *ctx) +{ + char buf[8]; + + if ((bpf_get_current_pid_tgid() >> 32) != target_pid) + return 0; + + read_ret[6] = bpf_copy_from_user(buf, sizeof(buf), user_ptr); + read_ret[7] = bpf_copy_from_user_task(buf, sizeof(buf), user_ptr, + bpf_get_current_task_btf(), 0); + + return 0; +} diff --git a/tools/testing/selftests/bpf/progs/timer.c b/tools/testing/selftests/bpf/progs/timer.c index 8b946c8188c6..f615da97df26 100644 --- a/tools/testing/selftests/bpf/progs/timer.c +++ b/tools/testing/selftests/bpf/progs/timer.c @@ -51,7 +51,8 @@ struct { __uint(max_entries, 1); __type(key, int); __type(value, struct elem); -} abs_timer SEC(".maps"), soft_timer_pinned SEC(".maps"), abs_timer_pinned SEC(".maps"); +} abs_timer SEC(".maps"), soft_timer_pinned SEC(".maps"), abs_timer_pinned SEC(".maps"), + race_array SEC(".maps"); __u64 bss_data; __u64 abs_data; @@ -390,3 +391,34 @@ int BPF_PROG2(test5, int, a) return 0; } + +static int race_timer_callback(void *race_array, int *race_key, struct bpf_timer *timer) +{ + bpf_timer_start(timer, 1000000, 0); + return 0; +} + +SEC("syscall") +int race(void *ctx) +{ + struct bpf_timer *timer; + int err, race_key = 0; + struct elem init; + + __builtin_memset(&init, 0, sizeof(struct elem)); + bpf_map_update_elem(&race_array, &race_key, &init, BPF_ANY); + + timer = bpf_map_lookup_elem(&race_array, &race_key); + if (!timer) + return 1; + + err = bpf_timer_init(timer, &race_array, CLOCK_MONOTONIC); + if (err && err != -EBUSY) + return 1; + + bpf_timer_set_callback(timer, race_timer_callback); + bpf_timer_start(timer, 0, 0); + bpf_timer_cancel(timer); + + return 0; +} diff --git a/tools/testing/selftests/drivers/net/bonding/bond_options.sh b/tools/testing/selftests/drivers/net/bonding/bond_options.sh index d508486cc0bd..9a3d3c389dad 100755 --- a/tools/testing/selftests/drivers/net/bonding/bond_options.sh +++ b/tools/testing/selftests/drivers/net/bonding/bond_options.sh @@ -62,6 +62,8 @@ prio_test() # create bond bond_reset "${param}" + # set active_slave to primary eth1 specifically + ip -n ${s_ns} link set bond0 type bond active_slave eth1 # check bonding member prio value ip -n ${s_ns} link set eth0 type bond_slave prio 0 diff --git a/tools/testing/selftests/iommu/config b/tools/testing/selftests/iommu/config index 6c4f901d6fed..110d73917615 100644 --- a/tools/testing/selftests/iommu/config +++ b/tools/testing/selftests/iommu/config @@ -1,2 +1,3 @@ -CONFIG_IOMMUFD -CONFIG_IOMMUFD_TEST +CONFIG_IOMMUFD=y +CONFIG_FAULT_INJECTION=y +CONFIG_IOMMUFD_TEST=y diff --git a/tools/testing/selftests/iommu/iommufd.c b/tools/testing/selftests/iommu/iommufd.c index 1a881e7a21d1..edf1c99c9936 100644 --- a/tools/testing/selftests/iommu/iommufd.c +++ b/tools/testing/selftests/iommu/iommufd.c @@ -12,6 +12,7 @@ static unsigned long HUGEPAGE_SIZE; #define MOCK_PAGE_SIZE (PAGE_SIZE / 2) +#define MOCK_HUGE_PAGE_SIZE (512 * MOCK_PAGE_SIZE) static unsigned long get_huge_page_size(void) { @@ -1716,10 +1717,12 @@ FIXTURE(iommufd_dirty_tracking) FIXTURE_VARIANT(iommufd_dirty_tracking) { unsigned long buffer_size; + bool hugepages; }; FIXTURE_SETUP(iommufd_dirty_tracking) { + int mmap_flags; void *vrc; int rc; @@ -1732,25 +1735,41 @@ FIXTURE_SETUP(iommufd_dirty_tracking) variant->buffer_size, rc); } + mmap_flags = MAP_SHARED | MAP_ANONYMOUS | MAP_FIXED; + if (variant->hugepages) { + /* + * MAP_POPULATE will cause the kernel to fail mmap if THPs are + * not available. + */ + mmap_flags |= MAP_HUGETLB | MAP_POPULATE; + } assert((uintptr_t)self->buffer % HUGEPAGE_SIZE == 0); vrc = mmap(self->buffer, variant->buffer_size, PROT_READ | PROT_WRITE, - MAP_SHARED | MAP_ANONYMOUS | MAP_FIXED, -1, 0); + mmap_flags, -1, 0); assert(vrc == self->buffer); self->page_size = MOCK_PAGE_SIZE; self->bitmap_size = variant->buffer_size / self->page_size / BITS_PER_BYTE; - /* Provision with an extra (MOCK_PAGE_SIZE) for the unaligned case */ + /* Provision with an extra (PAGE_SIZE) for the unaligned case */ rc = posix_memalign(&self->bitmap, PAGE_SIZE, - self->bitmap_size + MOCK_PAGE_SIZE); + self->bitmap_size + PAGE_SIZE); assert(!rc); assert(self->bitmap); assert((uintptr_t)self->bitmap % PAGE_SIZE == 0); test_ioctl_ioas_alloc(&self->ioas_id); - test_cmd_mock_domain(self->ioas_id, &self->stdev_id, &self->hwpt_id, - &self->idev_id); + /* Enable 1M mock IOMMU hugepages */ + if (variant->hugepages) { + test_cmd_mock_domain_flags(self->ioas_id, + MOCK_FLAGS_DEVICE_HUGE_IOVA, + &self->stdev_id, &self->hwpt_id, + &self->idev_id); + } else { + test_cmd_mock_domain(self->ioas_id, &self->stdev_id, + &self->hwpt_id, &self->idev_id); + } } FIXTURE_TEARDOWN(iommufd_dirty_tracking) @@ -1784,12 +1803,26 @@ FIXTURE_VARIANT_ADD(iommufd_dirty_tracking, domain_dirty128M) .buffer_size = 128UL * 1024UL * 1024UL, }; +FIXTURE_VARIANT_ADD(iommufd_dirty_tracking, domain_dirty128M_huge) +{ + /* 4K bitmap (128M IOVA range) */ + .buffer_size = 128UL * 1024UL * 1024UL, + .hugepages = true, +}; + FIXTURE_VARIANT_ADD(iommufd_dirty_tracking, domain_dirty256M) { /* 8K bitmap (256M IOVA range) */ .buffer_size = 256UL * 1024UL * 1024UL, }; +FIXTURE_VARIANT_ADD(iommufd_dirty_tracking, domain_dirty256M_huge) +{ + /* 8K bitmap (256M IOVA range) */ + .buffer_size = 256UL * 1024UL * 1024UL, + .hugepages = true, +}; + TEST_F(iommufd_dirty_tracking, enforce_dirty) { uint32_t ioas_id, stddev_id, idev_id; @@ -1849,65 +1882,80 @@ TEST_F(iommufd_dirty_tracking, device_dirty_capability) TEST_F(iommufd_dirty_tracking, get_dirty_bitmap) { - uint32_t stddev_id; + uint32_t page_size = MOCK_PAGE_SIZE; uint32_t hwpt_id; uint32_t ioas_id; + if (variant->hugepages) + page_size = MOCK_HUGE_PAGE_SIZE; + test_ioctl_ioas_alloc(&ioas_id); test_ioctl_ioas_map_fixed_id(ioas_id, self->buffer, variant->buffer_size, MOCK_APERTURE_START); test_cmd_hwpt_alloc(self->idev_id, ioas_id, IOMMU_HWPT_ALLOC_DIRTY_TRACKING, &hwpt_id); - test_cmd_mock_domain(hwpt_id, &stddev_id, NULL, NULL); test_cmd_set_dirty_tracking(hwpt_id, true); test_mock_dirty_bitmaps(hwpt_id, variant->buffer_size, - MOCK_APERTURE_START, self->page_size, + MOCK_APERTURE_START, self->page_size, page_size, self->bitmap, self->bitmap_size, 0, _metadata); /* PAGE_SIZE unaligned bitmap */ test_mock_dirty_bitmaps(hwpt_id, variant->buffer_size, - MOCK_APERTURE_START, self->page_size, + MOCK_APERTURE_START, self->page_size, page_size, self->bitmap + MOCK_PAGE_SIZE, self->bitmap_size, 0, _metadata); - test_ioctl_destroy(stddev_id); + /* u64 unaligned bitmap */ + test_mock_dirty_bitmaps(hwpt_id, variant->buffer_size, + MOCK_APERTURE_START, self->page_size, page_size, + self->bitmap + 0xff1, self->bitmap_size, 0, + _metadata); + test_ioctl_destroy(hwpt_id); } TEST_F(iommufd_dirty_tracking, get_dirty_bitmap_no_clear) { - uint32_t stddev_id; + uint32_t page_size = MOCK_PAGE_SIZE; uint32_t hwpt_id; uint32_t ioas_id; + if (variant->hugepages) + page_size = MOCK_HUGE_PAGE_SIZE; + test_ioctl_ioas_alloc(&ioas_id); test_ioctl_ioas_map_fixed_id(ioas_id, self->buffer, variant->buffer_size, MOCK_APERTURE_START); test_cmd_hwpt_alloc(self->idev_id, ioas_id, IOMMU_HWPT_ALLOC_DIRTY_TRACKING, &hwpt_id); - test_cmd_mock_domain(hwpt_id, &stddev_id, NULL, NULL); test_cmd_set_dirty_tracking(hwpt_id, true); test_mock_dirty_bitmaps(hwpt_id, variant->buffer_size, - MOCK_APERTURE_START, self->page_size, + MOCK_APERTURE_START, self->page_size, page_size, self->bitmap, self->bitmap_size, IOMMU_HWPT_GET_DIRTY_BITMAP_NO_CLEAR, _metadata); /* Unaligned bitmap */ test_mock_dirty_bitmaps(hwpt_id, variant->buffer_size, - MOCK_APERTURE_START, self->page_size, + MOCK_APERTURE_START, self->page_size, page_size, self->bitmap + MOCK_PAGE_SIZE, self->bitmap_size, IOMMU_HWPT_GET_DIRTY_BITMAP_NO_CLEAR, _metadata); - test_ioctl_destroy(stddev_id); + /* u64 unaligned bitmap */ + test_mock_dirty_bitmaps(hwpt_id, variant->buffer_size, + MOCK_APERTURE_START, self->page_size, page_size, + self->bitmap + 0xff1, self->bitmap_size, + IOMMU_HWPT_GET_DIRTY_BITMAP_NO_CLEAR, + _metadata); + test_ioctl_destroy(hwpt_id); } diff --git a/tools/testing/selftests/iommu/iommufd_utils.h b/tools/testing/selftests/iommu/iommufd_utils.h index c646264aa41f..8d2b46b2114d 100644 --- a/tools/testing/selftests/iommu/iommufd_utils.h +++ b/tools/testing/selftests/iommu/iommufd_utils.h @@ -344,16 +344,19 @@ static int _test_cmd_mock_domain_set_dirty(int fd, __u32 hwpt_id, size_t length, page_size, bitmap, nr)) static int _test_mock_dirty_bitmaps(int fd, __u32 hwpt_id, size_t length, - __u64 iova, size_t page_size, __u64 *bitmap, + __u64 iova, size_t page_size, + size_t pte_page_size, __u64 *bitmap, __u64 bitmap_size, __u32 flags, struct __test_metadata *_metadata) { - unsigned long i, nbits = bitmap_size * BITS_PER_BYTE; - unsigned long nr = nbits / 2; + unsigned long npte = pte_page_size / page_size, pteset = 2 * npte; + unsigned long nbits = bitmap_size * BITS_PER_BYTE; + unsigned long j, i, nr = nbits / pteset ?: 1; __u64 out_dirty = 0; /* Mark all even bits as dirty in the mock domain */ - for (i = 0; i < nbits; i += 2) + memset(bitmap, 0, bitmap_size); + for (i = 0; i < nbits; i += pteset) set_bit(i, (unsigned long *)bitmap); test_cmd_mock_domain_set_dirty(fd, hwpt_id, length, iova, page_size, @@ -365,8 +368,12 @@ static int _test_mock_dirty_bitmaps(int fd, __u32 hwpt_id, size_t length, test_cmd_get_dirty_bitmap(fd, hwpt_id, length, iova, page_size, bitmap, flags); /* Beware ASSERT_EQ() is two statements -- braces are not redundant! */ - for (i = 0; i < nbits; i++) { - ASSERT_EQ(!(i % 2), test_bit(i, (unsigned long *)bitmap)); + for (i = 0; i < nbits; i += pteset) { + for (j = 0; j < pteset; j++) { + ASSERT_EQ(j < npte, + test_bit(i + j, (unsigned long *)bitmap)); + } + ASSERT_EQ(!(i % pteset), test_bit(i, (unsigned long *)bitmap)); } memset(bitmap, 0, bitmap_size); @@ -374,19 +381,23 @@ static int _test_mock_dirty_bitmaps(int fd, __u32 hwpt_id, size_t length, flags); /* It as read already -- expect all zeroes */ - for (i = 0; i < nbits; i++) { - ASSERT_EQ(!(i % 2) && (flags & - IOMMU_HWPT_GET_DIRTY_BITMAP_NO_CLEAR), - test_bit(i, (unsigned long *)bitmap)); + for (i = 0; i < nbits; i += pteset) { + for (j = 0; j < pteset; j++) { + ASSERT_EQ( + (j < npte) && + (flags & + IOMMU_HWPT_GET_DIRTY_BITMAP_NO_CLEAR), + test_bit(i + j, (unsigned long *)bitmap)); + } } return 0; } -#define test_mock_dirty_bitmaps(hwpt_id, length, iova, page_size, bitmap, \ - bitmap_size, flags, _metadata) \ +#define test_mock_dirty_bitmaps(hwpt_id, length, iova, page_size, pte_size,\ + bitmap, bitmap_size, flags, _metadata) \ ASSERT_EQ(0, _test_mock_dirty_bitmaps(self->fd, hwpt_id, length, iova, \ - page_size, bitmap, bitmap_size, \ - flags, _metadata)) + page_size, pte_size, bitmap, \ + bitmap_size, flags, _metadata)) static int _test_cmd_create_access(int fd, unsigned int ioas_id, __u32 *access_id, unsigned int flags) diff --git a/tools/testing/selftests/net/forwarding/tc_actions.sh b/tools/testing/selftests/net/forwarding/tc_actions.sh index b0f5e55d2d0b..589629636502 100755 --- a/tools/testing/selftests/net/forwarding/tc_actions.sh +++ b/tools/testing/selftests/net/forwarding/tc_actions.sh @@ -235,9 +235,6 @@ mirred_egress_to_ingress_tcp_test() check_err $? "didn't mirred redirect ICMP" tc_check_packets "dev $h1 ingress" 102 10 check_err $? "didn't drop mirred ICMP" - local overlimits=$(tc_rule_stats_get ${h1} 101 egress .overlimits) - test ${overlimits} = 10 - check_err $? "wrong overlimits, expected 10 got ${overlimits}" tc filter del dev $h1 egress protocol ip pref 100 handle 100 flower tc filter del dev $h1 egress protocol ip pref 101 handle 101 flower diff --git a/tools/testing/selftests/net/ioam6.sh b/tools/testing/selftests/net/ioam6.sh index fe59ca3e5596..12491850ae98 100755 --- a/tools/testing/selftests/net/ioam6.sh +++ b/tools/testing/selftests/net/ioam6.sh @@ -367,14 +367,12 @@ run_test() local desc=$2 local node_src=$3 local node_dst=$4 - local ip6_src=$5 - local ip6_dst=$6 - local if_dst=$7 - local trace_type=$8 - local ioam_ns=$9 - - ip netns exec $node_dst ./ioam6_parser $if_dst $name $ip6_src $ip6_dst \ - $trace_type $ioam_ns & + local ip6_dst=$5 + local trace_type=$6 + local ioam_ns=$7 + local type=$8 + + ip netns exec $node_dst ./ioam6_parser $name $trace_type $ioam_ns $type & local spid=$! sleep 0.1 @@ -489,7 +487,7 @@ out_undef_ns() trace prealloc type 0x800000 ns 0 size 4 dev veth0 run_test ${FUNCNAME[0]} "${desc} ($1 mode)" $ioam_node_alpha $ioam_node_beta \ - db01::2 db01::1 veth0 0x800000 0 + db01::1 0x800000 0 $1 [ "$1" = "encap" ] && ip -netns $ioam_node_beta link set ip6tnl0 down } @@ -509,7 +507,7 @@ out_no_room() trace prealloc type 0xc00000 ns 123 size 4 dev veth0 run_test ${FUNCNAME[0]} "${desc} ($1 mode)" $ioam_node_alpha $ioam_node_beta \ - db01::2 db01::1 veth0 0xc00000 123 + db01::1 0xc00000 123 $1 [ "$1" = "encap" ] && ip -netns $ioam_node_beta link set ip6tnl0 down } @@ -543,14 +541,14 @@ out_bits() if [ $cmd_res != 0 ] then npassed=$((npassed+1)) - log_test_passed "$descr" + log_test_passed "$descr ($1 mode)" else nfailed=$((nfailed+1)) - log_test_failed "$descr" + log_test_failed "$descr ($1 mode)" fi else run_test "out_bit$i" "$descr ($1 mode)" $ioam_node_alpha \ - $ioam_node_beta db01::2 db01::1 veth0 ${bit2type[$i]} 123 + $ioam_node_beta db01::1 ${bit2type[$i]} 123 $1 fi done @@ -574,7 +572,7 @@ out_full_supp_trace() trace prealloc type 0xfff002 ns 123 size 100 dev veth0 run_test ${FUNCNAME[0]} "${desc} ($1 mode)" $ioam_node_alpha $ioam_node_beta \ - db01::2 db01::1 veth0 0xfff002 123 + db01::1 0xfff002 123 $1 [ "$1" = "encap" ] && ip -netns $ioam_node_beta link set ip6tnl0 down } @@ -604,7 +602,7 @@ in_undef_ns() trace prealloc type 0x800000 ns 0 size 4 dev veth0 run_test ${FUNCNAME[0]} "${desc} ($1 mode)" $ioam_node_alpha $ioam_node_beta \ - db01::2 db01::1 veth0 0x800000 0 + db01::1 0x800000 0 $1 [ "$1" = "encap" ] && ip -netns $ioam_node_beta link set ip6tnl0 down } @@ -624,7 +622,7 @@ in_no_room() trace prealloc type 0xc00000 ns 123 size 4 dev veth0 run_test ${FUNCNAME[0]} "${desc} ($1 mode)" $ioam_node_alpha $ioam_node_beta \ - db01::2 db01::1 veth0 0xc00000 123 + db01::1 0xc00000 123 $1 [ "$1" = "encap" ] && ip -netns $ioam_node_beta link set ip6tnl0 down } @@ -651,7 +649,7 @@ in_bits() dev veth0 run_test "in_bit$i" "${desc/<n>/$i} ($1 mode)" $ioam_node_alpha \ - $ioam_node_beta db01::2 db01::1 veth0 ${bit2type[$i]} 123 + $ioam_node_beta db01::1 ${bit2type[$i]} 123 $1 done [ "$1" = "encap" ] && ip -netns $ioam_node_beta link set ip6tnl0 down @@ -679,7 +677,7 @@ in_oflag() trace prealloc type 0xc00000 ns 123 size 4 dev veth0 run_test ${FUNCNAME[0]} "${desc} ($1 mode)" $ioam_node_alpha $ioam_node_beta \ - db01::2 db01::1 veth0 0xc00000 123 + db01::1 0xc00000 123 $1 [ "$1" = "encap" ] && ip -netns $ioam_node_beta link set ip6tnl0 down @@ -703,7 +701,7 @@ in_full_supp_trace() trace prealloc type 0xfff002 ns 123 size 80 dev veth0 run_test ${FUNCNAME[0]} "${desc} ($1 mode)" $ioam_node_alpha $ioam_node_beta \ - db01::2 db01::1 veth0 0xfff002 123 + db01::1 0xfff002 123 $1 [ "$1" = "encap" ] && ip -netns $ioam_node_beta link set ip6tnl0 down } @@ -731,7 +729,7 @@ fwd_full_supp_trace() trace prealloc type 0xfff002 ns 123 size 244 via db01::1 dev veth0 run_test ${FUNCNAME[0]} "${desc} ($1 mode)" $ioam_node_alpha $ioam_node_gamma \ - db01::2 db02::2 veth0 0xfff002 123 + db02::2 0xfff002 123 $1 [ "$1" = "encap" ] && ip -netns $ioam_node_gamma link set ip6tnl0 down } diff --git a/tools/testing/selftests/net/ioam6_parser.c b/tools/testing/selftests/net/ioam6_parser.c index d9d1d4190126..895e5bb5044b 100644 --- a/tools/testing/selftests/net/ioam6_parser.c +++ b/tools/testing/selftests/net/ioam6_parser.c @@ -8,7 +8,6 @@ #include <errno.h> #include <limits.h> #include <linux/const.h> -#include <linux/if_ether.h> #include <linux/ioam6.h> #include <linux/ipv6.h> #include <stdlib.h> @@ -512,14 +511,6 @@ static int str2id(const char *tname) return -1; } -static int ipv6_addr_equal(const struct in6_addr *a1, const struct in6_addr *a2) -{ - return ((a1->s6_addr32[0] ^ a2->s6_addr32[0]) | - (a1->s6_addr32[1] ^ a2->s6_addr32[1]) | - (a1->s6_addr32[2] ^ a2->s6_addr32[2]) | - (a1->s6_addr32[3] ^ a2->s6_addr32[3])) == 0; -} - static int get_u32(__u32 *val, const char *arg, int base) { unsigned long res; @@ -603,70 +594,80 @@ static int (*func[__TEST_MAX])(int, struct ioam6_trace_hdr *, __u32, __u16) = { int main(int argc, char **argv) { - int fd, size, hoplen, tid, ret = 1; - struct in6_addr src, dst; + int fd, size, hoplen, tid, ret = 1, on = 1; struct ioam6_hdr *opt; - struct ipv6hdr *ip6h; - __u8 buffer[400], *p; - __u16 ioam_ns; + struct cmsghdr *cmsg; + struct msghdr msg; + struct iovec iov; + __u8 buffer[512]; __u32 tr_type; + __u16 ioam_ns; + __u8 *ptr; - if (argc != 7) + if (argc != 5) goto out; - tid = str2id(argv[2]); + tid = str2id(argv[1]); if (tid < 0 || !func[tid]) goto out; - if (inet_pton(AF_INET6, argv[3], &src) != 1 || - inet_pton(AF_INET6, argv[4], &dst) != 1) + if (get_u32(&tr_type, argv[2], 16) || + get_u16(&ioam_ns, argv[3], 0)) goto out; - if (get_u32(&tr_type, argv[5], 16) || - get_u16(&ioam_ns, argv[6], 0)) + fd = socket(PF_INET6, SOCK_RAW, + !strcmp(argv[4], "encap") ? IPPROTO_IPV6 : IPPROTO_ICMPV6); + if (fd < 0) goto out; - fd = socket(AF_PACKET, SOCK_DGRAM, __cpu_to_be16(ETH_P_IPV6)); - if (!fd) - goto out; + setsockopt(fd, IPPROTO_IPV6, IPV6_RECVHOPOPTS, &on, sizeof(on)); - if (setsockopt(fd, SOL_SOCKET, SO_BINDTODEVICE, - argv[1], strlen(argv[1]))) + iov.iov_len = 1; + iov.iov_base = malloc(CMSG_SPACE(sizeof(buffer))); + if (!iov.iov_base) goto close; - recv: - size = recv(fd, buffer, sizeof(buffer), 0); + memset(&msg, 0, sizeof(msg)); + msg.msg_iov = &iov; + msg.msg_iovlen = 1; + msg.msg_control = buffer; + msg.msg_controllen = CMSG_SPACE(sizeof(buffer)); + + size = recvmsg(fd, &msg, 0); if (size <= 0) goto close; - ip6h = (struct ipv6hdr *)buffer; + for (cmsg = CMSG_FIRSTHDR(&msg); cmsg; cmsg = CMSG_NXTHDR(&msg, cmsg)) { + if (cmsg->cmsg_level != IPPROTO_IPV6 || + cmsg->cmsg_type != IPV6_HOPOPTS || + cmsg->cmsg_len < sizeof(struct ipv6_hopopt_hdr)) + continue; - if (!ipv6_addr_equal(&ip6h->saddr, &src) || - !ipv6_addr_equal(&ip6h->daddr, &dst)) - goto recv; + ptr = (__u8 *)CMSG_DATA(cmsg); - if (ip6h->nexthdr != IPPROTO_HOPOPTS) - goto close; + hoplen = (ptr[1] + 1) << 3; + ptr += sizeof(struct ipv6_hopopt_hdr); - p = buffer + sizeof(*ip6h); - hoplen = (p[1] + 1) << 3; - p += sizeof(struct ipv6_hopopt_hdr); + while (hoplen > 0) { + opt = (struct ioam6_hdr *)ptr; - while (hoplen > 0) { - opt = (struct ioam6_hdr *)p; + if (opt->opt_type == IPV6_TLV_IOAM && + opt->type == IOAM6_TYPE_PREALLOC) { + ptr += sizeof(*opt); + ret = func[tid](tid, + (struct ioam6_trace_hdr *)ptr, + tr_type, ioam_ns); + goto close; + } - if (opt->opt_type == IPV6_TLV_IOAM && - opt->type == IOAM6_TYPE_PREALLOC) { - p += sizeof(*opt); - ret = func[tid](tid, (struct ioam6_trace_hdr *)p, - tr_type, ioam_ns); - break; + ptr += opt->opt_len + 2; + hoplen -= opt->opt_len + 2; } - - p += opt->opt_len + 2; - hoplen -= opt->opt_len + 2; } + + goto recv; close: + free(iov.iov_base); close(fd); out: return ret; diff --git a/tools/testing/selftests/net/mptcp/diag.sh b/tools/testing/selftests/net/mptcp/diag.sh index 04fcb8a077c9..0a58ebb8b04c 100755 --- a/tools/testing/selftests/net/mptcp/diag.sh +++ b/tools/testing/selftests/net/mptcp/diag.sh @@ -62,8 +62,8 @@ __chk_nr() nr=$(eval $command) printf "%-50s" "$msg" - if [ $nr != $expected ]; then - if [ $nr = "$skip" ] && ! mptcp_lib_expect_all_features; then + if [ "$nr" != "$expected" ]; then + if [ "$nr" = "$skip" ] && ! mptcp_lib_expect_all_features; then echo "[ skip ] Feature probably not supported" mptcp_lib_result_skip "${msg}" else @@ -166,9 +166,13 @@ chk_msk_listen() chk_msk_inuse() { local expected=$1 - local msg="$2" + local msg="....chk ${2:-${expected}} msk in use" local listen_nr + if [ "${expected}" -eq 0 ]; then + msg+=" after flush" + fi + listen_nr=$(ss -N "${ns}" -Ml | grep -c LISTEN) expected=$((expected + listen_nr)) @@ -179,16 +183,21 @@ chk_msk_inuse() sleep 0.1 done - __chk_nr get_msk_inuse $expected "$msg" 0 + __chk_nr get_msk_inuse $expected "${msg}" 0 } # $1: cestab nr chk_msk_cestab() { - local cestab=$1 + local expected=$1 + local msg="....chk ${2:-${expected}} cestab" + + if [ "${expected}" -eq 0 ]; then + msg+=" after flush" + fi __chk_nr "mptcp_lib_get_counter ${ns} MPTcpExtMPCurrEstab" \ - "${cestab}" "....chk ${cestab} cestab" "" + "${expected}" "${msg}" "" } wait_connected() @@ -227,12 +236,12 @@ wait_connected $ns 10000 chk_msk_nr 2 "after MPC handshake " chk_msk_remote_key_nr 2 "....chk remote_key" chk_msk_fallback_nr 0 "....chk no fallback" -chk_msk_inuse 2 "....chk 2 msk in use" +chk_msk_inuse 2 chk_msk_cestab 2 flush_pids -chk_msk_inuse 0 "....chk 0 msk in use after flush" -chk_msk_cestab 0 +chk_msk_inuse 0 "2->0" +chk_msk_cestab 0 "2->0" echo "a" | \ timeout ${timeout_test} \ @@ -247,12 +256,12 @@ echo "b" | \ 127.0.0.1 >/dev/null & wait_connected $ns 10001 chk_msk_fallback_nr 1 "check fallback" -chk_msk_inuse 1 "....chk 1 msk in use" +chk_msk_inuse 1 chk_msk_cestab 1 flush_pids -chk_msk_inuse 0 "....chk 0 msk in use after flush" -chk_msk_cestab 0 +chk_msk_inuse 0 "1->0" +chk_msk_cestab 0 "1->0" NR_CLIENTS=100 for I in `seq 1 $NR_CLIENTS`; do @@ -273,12 +282,12 @@ for I in `seq 1 $NR_CLIENTS`; do done wait_msk_nr $((NR_CLIENTS*2)) "many msk socket present" -chk_msk_inuse $((NR_CLIENTS*2)) "....chk many msk in use" -chk_msk_cestab $((NR_CLIENTS*2)) +chk_msk_inuse $((NR_CLIENTS*2)) "many" +chk_msk_cestab $((NR_CLIENTS*2)) "many" flush_pids -chk_msk_inuse 0 "....chk 0 msk in use after flush" -chk_msk_cestab 0 +chk_msk_inuse 0 "many->0" +chk_msk_cestab 0 "many->0" mptcp_lib_result_print_all_tap exit $ret diff --git a/tools/testing/selftests/net/mptcp/pm_netlink.sh b/tools/testing/selftests/net/mptcp/pm_netlink.sh index 8f4ff123a7eb..71899a3ffa7a 100755 --- a/tools/testing/selftests/net/mptcp/pm_netlink.sh +++ b/tools/testing/selftests/net/mptcp/pm_netlink.sh @@ -183,7 +183,7 @@ check "ip netns exec $ns1 ./pm_nl_ctl dump" "id 1 flags \ subflow 10.0.1.1" " (nobackup)" # fullmesh support has been added later -ip netns exec $ns1 ./pm_nl_ctl set id 1 flags fullmesh +ip netns exec $ns1 ./pm_nl_ctl set id 1 flags fullmesh 2>/dev/null if ip netns exec $ns1 ./pm_nl_ctl dump | grep -q "fullmesh" || mptcp_lib_expect_all_features; then check "ip netns exec $ns1 ./pm_nl_ctl dump" "id 1 flags \ @@ -194,6 +194,12 @@ subflow 10.0.1.1" " (nofullmesh)" ip netns exec $ns1 ./pm_nl_ctl set id 1 flags backup,fullmesh check "ip netns exec $ns1 ./pm_nl_ctl dump" "id 1 flags \ subflow,backup,fullmesh 10.0.1.1" " (backup,fullmesh)" +else + for st in fullmesh nofullmesh backup,fullmesh; do + st=" (${st})" + printf "%-50s%s\n" "${st}" "[SKIP]" + mptcp_lib_result_skip "${st}" + done fi mptcp_lib_result_print_all_tap diff --git a/tools/testing/selftests/net/mptcp/simult_flows.sh b/tools/testing/selftests/net/mptcp/simult_flows.sh index 0cc964e6f2c1..8f9ddb3ad4fe 100755 --- a/tools/testing/selftests/net/mptcp/simult_flows.sh +++ b/tools/testing/selftests/net/mptcp/simult_flows.sh @@ -250,7 +250,8 @@ run_test() [ $bail -eq 0 ] || exit $ret fi - printf "%-60s" "$msg - reverse direction" + msg+=" - reverse direction" + printf "%-60s" "${msg}" do_transfer $large $small $time lret=$? mptcp_lib_result_code "${lret}" "${msg}" diff --git a/tools/testing/selftests/net/mptcp/userspace_pm.sh b/tools/testing/selftests/net/mptcp/userspace_pm.sh index 6167837f48e1..1b94a75604fe 100755 --- a/tools/testing/selftests/net/mptcp/userspace_pm.sh +++ b/tools/testing/selftests/net/mptcp/userspace_pm.sh @@ -75,7 +75,7 @@ print_test() { test_name="${1}" - _printf "%-63s" "${test_name}" + _printf "%-68s" "${test_name}" } print_results() @@ -542,7 +542,7 @@ verify_subflow_events() local remid local info - info="${e_saddr} (${e_from}) => ${e_daddr} (${e_to})" + info="${e_saddr} (${e_from}) => ${e_daddr}:${e_dport} (${e_to})" if [ "$e_type" = "$SUB_ESTABLISHED" ] then diff --git a/tools/testing/selftests/net/tls.c b/tools/testing/selftests/net/tls.c index 49c84602707f..b95c249f81c2 100644 --- a/tools/testing/selftests/net/tls.c +++ b/tools/testing/selftests/net/tls.c @@ -1485,6 +1485,51 @@ TEST_F(tls, control_msg) EXPECT_EQ(memcmp(buf, test_str, send_len), 0); } +TEST_F(tls, control_msg_nomerge) +{ + char *rec1 = "1111"; + char *rec2 = "2222"; + int send_len = 5; + char buf[15]; + + if (self->notls) + SKIP(return, "no TLS support"); + + EXPECT_EQ(tls_send_cmsg(self->fd, 100, rec1, send_len, 0), send_len); + EXPECT_EQ(tls_send_cmsg(self->fd, 100, rec2, send_len, 0), send_len); + + EXPECT_EQ(tls_recv_cmsg(_metadata, self->cfd, 100, buf, sizeof(buf), MSG_PEEK), send_len); + EXPECT_EQ(memcmp(buf, rec1, send_len), 0); + + EXPECT_EQ(tls_recv_cmsg(_metadata, self->cfd, 100, buf, sizeof(buf), MSG_PEEK), send_len); + EXPECT_EQ(memcmp(buf, rec1, send_len), 0); + + EXPECT_EQ(tls_recv_cmsg(_metadata, self->cfd, 100, buf, sizeof(buf), 0), send_len); + EXPECT_EQ(memcmp(buf, rec1, send_len), 0); + + EXPECT_EQ(tls_recv_cmsg(_metadata, self->cfd, 100, buf, sizeof(buf), 0), send_len); + EXPECT_EQ(memcmp(buf, rec2, send_len), 0); +} + +TEST_F(tls, data_control_data) +{ + char *rec1 = "1111"; + char *rec2 = "2222"; + char *rec3 = "3333"; + int send_len = 5; + char buf[15]; + + if (self->notls) + SKIP(return, "no TLS support"); + + EXPECT_EQ(send(self->fd, rec1, send_len, 0), send_len); + EXPECT_EQ(tls_send_cmsg(self->fd, 100, rec2, send_len, 0), send_len); + EXPECT_EQ(send(self->fd, rec3, send_len, 0), send_len); + + EXPECT_EQ(recv(self->cfd, buf, sizeof(buf), MSG_PEEK), send_len); + EXPECT_EQ(recv(self->cfd, buf, sizeof(buf), MSG_PEEK), send_len); +} + TEST_F(tls, shutdown) { char const *test_str = "test_read"; |