The following commit has been merged in the master branch: commit 33c55730cec5d4676660819729b0a151aa9fca37 Merge: 27a12342bb6c408f425ec2af679e019ffb64ab65 ec2f877856e0af3889940e00b160f7f20f8d774f Author: Stephen Rothwell sfr@canb.auug.org.au Date: Thu Oct 31 15:20:29 2019 +1100

Merge remote-tracking branch 'kspp/for-next/kspp'

diff --combined Documentation/process/coding-style.rst index ada573b7d703,146b3a2c661c..e7c60f5339b2 --- a/Documentation/process/coding-style.rst +++ b/Documentation/process/coding-style.rst @@@ -56,7 -56,7 +56,7 @@@ instead of ``double-indenting`` the ``c case 'K': case 'k': mem <<= 10; - /* fall through */ + fallthrough; default: break; } @@@ -988,7 -988,7 +988,7 @@@ Similarly, if you need to calculate th

.. code-block:: c

- #define FIELD_SIZEOF(t, f) (sizeof(((t*)0)->f)) + #define sizeof_member(t, f) (sizeof(((t*)0)->f))

There are also min() and max() macros that do strict type checking if you need them. Feel free to peruse that header file to see what else is already diff --combined arch/arm64/include/asm/processor.h index 8899d26f73ff,2d61a909984d..b5000e7cd59f --- a/arch/arm64/include/asm/processor.h +++ b/arch/arm64/include/asm/processor.h @@@ -26,12 -26,10 +26,12 @@@ #include <linux/init.h> #include <linux/stddef.h> #include <linux/string.h> +#include <linux/thread_info.h>

#include <asm/alternative.h> #include <asm/cpufeature.h> #include <asm/hw_breakpoint.h> +#include <asm/kasan.h> #include <asm/lse.h> #include <asm/pgtable-hwdef.h> #include <asm/pointer_auth.h> @@@ -154,13 -152,13 +154,13 @@@ static inline void arch_thread_struct_w unsigned long *size) { /* Verify that there is no padding among the whitelisted fields: */ - BUILD_BUG_ON(sizeof_field(struct thread_struct, uw) != - sizeof_field(struct thread_struct, uw.tp_value) + - sizeof_field(struct thread_struct, uw.tp2_value) + - sizeof_field(struct thread_struct, uw.fpsimd_state)); + BUILD_BUG_ON(sizeof_member(struct thread_struct, uw) != + sizeof_member(struct thread_struct, uw.tp_value) + + sizeof_member(struct thread_struct, uw.tp2_value) + + sizeof_member(struct thread_struct, uw.fpsimd_state));

*offset = offsetof(struct thread_struct, uw); - *size = sizeof_field(struct thread_struct, uw); + *size = sizeof_member(struct thread_struct, uw); }

#ifdef CONFIG_COMPAT @@@ -216,18 -214,6 +216,18 @@@ static inline void start_thread(struct regs->sp = sp; }

+static inline bool is_ttbr0_addr(unsigned long addr) +{ + /* entry assembly clears tags for TTBR0 addrs */ + return addr < TASK_SIZE; +} + +static inline bool is_ttbr1_addr(unsigned long addr) +{ + /* TTBR1 addresses may have a tag if KASAN_SW_TAGS is in use */ + return arch_kasan_reset_tag(addr) >= PAGE_OFFSET; +} + #ifdef CONFIG_COMPAT static inline void compat_start_thread(struct pt_regs *regs, unsigned long pc, unsigned long sp) diff --combined block/blk-core.c index 1d3880e1c436,fd6b31d400e7..f2d845aea77f --- a/block/blk-core.c +++ b/block/blk-core.c @@@ -184,22 -184,6 +184,22 @@@ static const struct [BLK_STS_IOERR] = { -EIO, "I/O" }, };

+#ifdef CONFIG_BLK_NOTIFICATIONS +static const +enum block_notification_type blk_notifications[ARRAY_SIZE(blk_errors)] = { + [BLK_STS_TIMEOUT] = NOTIFY_BLOCK_ERROR_TIMEOUT, + [BLK_STS_NOSPC] = NOTIFY_BLOCK_ERROR_NO_SPACE, + [BLK_STS_TRANSPORT] = NOTIFY_BLOCK_ERROR_RECOVERABLE_TRANSPORT, + [BLK_STS_TARGET] = NOTIFY_BLOCK_ERROR_CRITICAL_TARGET, + [BLK_STS_NEXUS] = NOTIFY_BLOCK_ERROR_CRITICAL_NEXUS, + [BLK_STS_MEDIUM] = NOTIFY_BLOCK_ERROR_CRITICAL_MEDIUM, + [BLK_STS_PROTECTION] = NOTIFY_BLOCK_ERROR_PROTECTION, + [BLK_STS_RESOURCE] = NOTIFY_BLOCK_ERROR_KERNEL_RESOURCE, + [BLK_STS_DEV_RESOURCE] = NOTIFY_BLOCK_ERROR_DEVICE_RESOURCE, + [BLK_STS_IOERR] = NOTIFY_BLOCK_ERROR_IO, +}; +#endif + blk_status_t errno_to_blk_status(int errno) { int i; @@@ -240,19 -224,6 +240,19 @@@ static void print_req_error(struct requ req->cmd_flags & ~REQ_OP_MASK, req->nr_phys_segments, IOPRIO_PRIO_CLASS(req->ioprio)); + +#ifdef CONFIG_BLK_NOTIFICATIONS + if (blk_notifications[idx]) { + struct block_notification n = { + .watch.type = WATCH_TYPE_BLOCK_NOTIFY, + .watch.subtype = blk_notifications[idx], + .watch.info = watch_sizeof(n), + .dev = req->rq_disk ? disk_devt(req->rq_disk) : 0, + .sector = blk_rq_pos(req), + }; + post_block_notification(&n); + } +#endif }

static void req_bio_endio(struct request *rq, struct bio *bio, @@@ -365,14 -336,14 +365,14 @@@ EXPORT_SYMBOL_GPL(blk_set_queue_dying) */ void blk_cleanup_queue(struct request_queue *q) { + WARN_ON_ONCE(blk_queue_registered(q)); + /* mark @q DYING, no new request or merges will be allowed afterwards */ - mutex_lock(&q->sysfs_lock); blk_set_queue_dying(q);

blk_queue_flag_set(QUEUE_FLAG_NOMERGES, q); blk_queue_flag_set(QUEUE_FLAG_NOXMERGES, q); blk_queue_flag_set(QUEUE_FLAG_DYING, q); - mutex_unlock(&q->sysfs_lock);

/* * Drain all requests queued before DYING marking. Set DEAD flag to @@@ -1819,9 -1790,9 +1819,9 @@@ int __init blk_dev_init(void { BUILD_BUG_ON(REQ_OP_LAST >= (1 << REQ_OP_BITS)); BUILD_BUG_ON(REQ_OP_BITS + REQ_FLAG_BITS > 8 * - FIELD_SIZEOF(struct request, cmd_flags)); + sizeof_member(struct request, cmd_flags)); BUILD_BUG_ON(REQ_OP_BITS + REQ_FLAG_BITS > 8 * - FIELD_SIZEOF(struct bio, bi_opf)); + sizeof_member(struct bio, bi_opf));

/* used for unplugging and affects IO latency/throughput - HIGHPRI */ kblockd_workqueue = alloc_workqueue("kblockd", diff --combined drivers/firmware/efi/efi.c index 69f00f7453a3,17d32fb72c9a..e3c8b51e7000 --- a/drivers/firmware/efi/efi.c +++ b/drivers/firmware/efi/efi.c @@@ -267,9 -267,6 +267,9 @@@ static __init int efivar_ssdt_load(void void *data; int ret;

+ if (!efivar_ssdt[0]) + return 0; + ret = efivar_init(efivar_ssdt_iter, &entries, true, &entries);

list_for_each_entry_safe(entry, aux, &entries, list) { @@@ -673,7 -670,7 +673,7 @@@ device_initcall(efi_load_efivars) { name }, \ { prop }, \ offsetof(struct efi_fdt_params, field), \ - FIELD_SIZEOF(struct efi_fdt_params, field) \ + sizeof_member(struct efi_fdt_params, field) \ }

struct params { diff --combined drivers/gpu/drm/i915/gvt/scheduler.c index 36bb7639e82f,76c2db58adcd..508a90bee72a --- a/drivers/gpu/drm/i915/gvt/scheduler.c +++ b/drivers/gpu/drm/i915/gvt/scheduler.c @@@ -365,8 -365,7 +365,8 @@@ static void set_context_ppgtt_from_shad struct i915_gem_context *ctx) { struct intel_vgpu_mm *mm = workload->shadow_mm; - struct i915_ppgtt *ppgtt = i915_vm_to_ppgtt(ctx->vm); + struct i915_ppgtt *ppgtt = + i915_vm_to_ppgtt(i915_gem_context_get_vm_rcu(ctx)); int i = 0;

if (mm->ppgtt_mm.root_entry_type == GTT_TYPE_PPGTT_ROOT_L4_ENTRY) { @@@ -379,8 -378,6 +379,8 @@@ px_dma(pd) = mm->ppgtt_mm.shadow_pdps[i]; } } + + i915_vm_put(&ppgtt->vm); }

static int @@@ -388,8 -385,11 +388,8 @@@ intel_gvt_workload_req_alloc(struct int { struct intel_vgpu *vgpu = workload->vgpu; struct intel_vgpu_submission *s = &vgpu->submission; - struct drm_i915_private *dev_priv = vgpu->gvt->dev_priv; struct i915_request *rq;

- lockdep_assert_held(&dev_priv->drm.struct_mutex); - if (workload->req) return 0;

@@@ -415,9 -415,10 +415,9 @@@ int intel_gvt_scan_and_shadow_workload( { struct intel_vgpu *vgpu = workload->vgpu; struct intel_vgpu_submission *s = &vgpu->submission; - struct drm_i915_private *dev_priv = vgpu->gvt->dev_priv; int ret;

- lockdep_assert_held(&dev_priv->drm.struct_mutex); + lockdep_assert_held(&vgpu->vgpu_lock);

if (workload->shadow) return 0; @@@ -579,6 -580,8 +579,6 @@@ static void update_vreg_in_ctx(struct i

static void release_shadow_batch_buffer(struct intel_vgpu_workload *workload) { - struct intel_vgpu *vgpu = workload->vgpu; - struct drm_i915_private *dev_priv = vgpu->gvt->dev_priv; struct intel_vgpu_shadow_bb *bb, *pos;

if (list_empty(&workload->shadow_bb)) @@@ -587,6 -590,8 +587,6 @@@ bb = list_first_entry(&workload->shadow_bb, struct intel_vgpu_shadow_bb, list);

- mutex_lock(&dev_priv->drm.struct_mutex); - list_for_each_entry_safe(bb, pos, &workload->shadow_bb, list) { if (bb->obj) { if (bb->accessing) @@@ -604,6 -609,8 +604,6 @@@ list_del(&bb->list); kfree(bb); } - - mutex_unlock(&dev_priv->drm.struct_mutex); }

static int prepare_workload(struct intel_vgpu_workload *workload) @@@ -678,6 -685,7 +678,6 @@@ err_unpin_mm static int dispatch_workload(struct intel_vgpu_workload *workload) { struct intel_vgpu *vgpu = workload->vgpu; - struct drm_i915_private *dev_priv = vgpu->gvt->dev_priv; struct i915_request *rq; int ring_id = workload->ring_id; int ret; @@@ -686,6 -694,7 +686,6 @@@ ring_id, workload);

mutex_lock(&vgpu->vgpu_lock); - mutex_lock(&dev_priv->drm.struct_mutex);

ret = intel_gvt_workload_req_alloc(workload); if (ret) @@@ -720,6 -729,7 +720,6 @@@ out err_req: if (ret) workload->status = ret; - mutex_unlock(&dev_priv->drm.struct_mutex); mutex_unlock(&vgpu->vgpu_lock); return ret; } @@@ -877,7 -887,7 +877,7 @@@ void intel_vgpu_clean_workloads(struct intel_engine_mask_t tmp;

/* free the unsubmited workloads in the queues. */ - for_each_engine_masked(engine, dev_priv, engine_mask, tmp) { + for_each_engine_masked(engine, &dev_priv->gt, engine_mask, tmp) { list_for_each_entry_safe(pos, n, &s->workload_q_head[engine->id], list) { list_del_init(&pos->list); @@@ -1223,18 -1233,20 +1223,18 @@@ int intel_vgpu_setup_submission(struct struct intel_vgpu_submission *s = &vgpu->submission; struct intel_engine_cs *engine; struct i915_gem_context *ctx; + struct i915_ppgtt *ppgtt; enum intel_engine_id i; int ret;

- mutex_lock(&i915->drm.struct_mutex); - ctx = i915_gem_context_create_kernel(i915, I915_PRIORITY_MAX); - if (IS_ERR(ctx)) { - ret = PTR_ERR(ctx); - goto out_unlock; - } + if (IS_ERR(ctx)) + return PTR_ERR(ctx);

i915_gem_context_set_force_single_submission(ctx);

- i915_context_ppgtt_root_save(s, i915_vm_to_ppgtt(ctx->vm)); + ppgtt = i915_vm_to_ppgtt(i915_gem_context_get_vm_rcu(ctx)); + i915_context_ppgtt_root_save(s, ppgtt);

for_each_engine(engine, i915, i) { struct intel_context *ce; @@@ -1268,7 -1280,7 +1268,7 @@@ sizeof(struct intel_vgpu_workload), 0, SLAB_HWCACHE_ALIGN, offsetof(struct intel_vgpu_workload, rb_tail), - sizeof_field(struct intel_vgpu_workload, rb_tail), + sizeof_member(struct intel_vgpu_workload, rb_tail), NULL);

if (!s->workloads) { @@@ -1279,12 -1291,12 +1279,12 @@@ atomic_set(&s->running_workload_num, 0); bitmap_zero(s->tlb_handle_pending, I915_NUM_ENGINES);

+ i915_vm_put(&ppgtt->vm); i915_gem_context_put(ctx); - mutex_unlock(&i915->drm.struct_mutex); return 0;

out_shadow_ctx: - i915_context_ppgtt_root_restore(s, i915_vm_to_ppgtt(ctx->vm)); + i915_context_ppgtt_root_restore(s, ppgtt); for_each_engine(engine, i915, i) { if (IS_ERR(s->shadow[i])) break; @@@ -1292,8 -1304,9 +1292,8 @@@ intel_context_unpin(s->shadow[i]); intel_context_put(s->shadow[i]); } + i915_vm_put(&ppgtt->vm); i915_gem_context_put(ctx); -out_unlock: - mutex_unlock(&i915->drm.struct_mutex); return ret; }

@@@ -1584,9 -1597,9 +1584,9 @@@ intel_vgpu_create_workload(struct intel */ if (list_empty(workload_q_head(vgpu, ring_id))) { intel_runtime_pm_get(&dev_priv->runtime_pm); - mutex_lock(&dev_priv->drm.struct_mutex); + mutex_lock(&vgpu->vgpu_lock); ret = intel_gvt_scan_and_shadow_workload(workload); - mutex_unlock(&dev_priv->drm.struct_mutex); + mutex_unlock(&vgpu->vgpu_lock); intel_runtime_pm_put_unchecked(&dev_priv->runtime_pm); }

diff --combined drivers/infiniband/hw/hfi1/sdma.c index c61b6022575e,a772955bd2ad..f87acd4af819 --- a/drivers/infiniband/hw/hfi1/sdma.c +++ b/drivers/infiniband/hw/hfi1/sdma.c @@@ -65,7 -65,6 +65,7 @@@ #define SDMA_DESCQ_CNT 2048 #define SDMA_DESC_INTR 64 #define INVALID_TAIL 0xffff +#define SDMA_PAD max_t(size_t, MAX_16B_PADDING, sizeof(u32))

static uint sdma_descq_cnt = SDMA_DESCQ_CNT; module_param(sdma_descq_cnt, uint, S_IRUGO); @@@ -848,7 -847,7 +848,7 @@@ static const struct rhashtable_params s .nelem_hint = NR_CPUS_HINT, .head_offset = offsetof(struct sdma_rht_node, node), .key_offset = offsetof(struct sdma_rht_node, cpu_id), - .key_len = FIELD_SIZEOF(struct sdma_rht_node, cpu_id), + .key_len = sizeof_member(struct sdma_rht_node, cpu_id), .max_size = NR_CPUS, .min_size = 8, .automatic_shrinking = true, @@@ -1297,7 -1296,7 +1297,7 @@@ void sdma_clean(struct hfi1_devdata *dd struct sdma_engine *sde;

if (dd->sdma_pad_dma) { - dma_free_coherent(&dd->pcidev->dev, 4, + dma_free_coherent(&dd->pcidev->dev, SDMA_PAD, (void *)dd->sdma_pad_dma, dd->sdma_pad_phys); dd->sdma_pad_dma = NULL; @@@ -1492,7 -1491,7 +1492,7 @@@ int sdma_init(struct hfi1_devdata *dd, }

/* Allocate memory for pad */ - dd->sdma_pad_dma = dma_alloc_coherent(&dd->pcidev->dev, sizeof(u32), + dd->sdma_pad_dma = dma_alloc_coherent(&dd->pcidev->dev, SDMA_PAD, &dd->sdma_pad_phys, GFP_KERNEL); if (!dd->sdma_pad_dma) { dd_dev_err(dd, "failed to allocate SendDMA pad memory\n"); @@@ -1527,11 -1526,8 +1527,11 @@@ }

ret = rhashtable_init(tmp_sdma_rht, &sdma_rht_params); - if (ret < 0) + if (ret < 0) { + kfree(tmp_sdma_rht); goto bail; + } + dd->sdma_rht = tmp_sdma_rht;

dd_dev_info(dd, "SDMA num_sdma: %u\n", dd->num_sdma); diff --combined drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index bf6bca26c337,491acfe19e2a..a477fe75bc9c --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@@ -55,8 -55,6 +55,8 @@@

#define HCLGE_LINK_STATUS_MS 10

+#define HCLGE_VF_VPORT_START_NUM 1 + static int hclge_set_mac_mtu(struct hclge_dev *hdev, int new_mps); static int hclge_init_vlan_config(struct hclge_dev *hdev); static void hclge_sync_vlan_filter(struct hclge_dev *hdev); @@@ -325,7 -323,8 +325,7 @@@ static const struct hclge_mac_mgr_tbl_e { .flags = HCLGE_MAC_MGR_MASK_VLAN_B, .ethter_type = cpu_to_le16(ETH_P_LLDP), - .mac_addr_hi32 = cpu_to_le32(htonl(0x0180C200)), - .mac_addr_lo16 = cpu_to_le16(htons(0x000E)), + .mac_addr = {0x01, 0x80, 0xc2, 0x00, 0x00, 0x0e}, .i_port_bitmap = 0x1, }, }; @@@ -907,9 -906,6 +907,9 @@@ static int hclge_query_pf_resource(stru hnae3_get_field(__le16_to_cpu(req->pf_intr_vector_number), HCLGE_PF_VEC_NUM_M, HCLGE_PF_VEC_NUM_S);

+ /* nic's msix numbers is always equals to the roce's. */ + hdev->num_nic_msi = hdev->num_roce_msi; + /* PF should have NIC vectors and Roce vectors, * NIC vectors are queued before Roce vectors. */ @@@ -919,15 -915,6 +919,15 @@@ hdev->num_msi = hnae3_get_field(__le16_to_cpu(req->pf_intr_vector_number), HCLGE_PF_VEC_NUM_M, HCLGE_PF_VEC_NUM_S); + + hdev->num_nic_msi = hdev->num_msi; + } + + if (hdev->num_nic_msi < HNAE3_MIN_VECTOR_NUM) { + dev_err(&hdev->pdev->dev, + "Just %u msi resources, not enough for pf(min:2).\n", + hdev->num_nic_msi); + return -EINVAL; }

return 0; @@@ -1195,35 -1182,6 +1195,35 @@@ static void hclge_parse_link_mode(struc hclge_parse_backplane_link_mode(hdev, speed_ability); }

+static u32 hclge_get_max_speed(u8 speed_ability) +{ + if (speed_ability & HCLGE_SUPPORT_100G_BIT) + return HCLGE_MAC_SPEED_100G; + + if (speed_ability & HCLGE_SUPPORT_50G_BIT) + return HCLGE_MAC_SPEED_50G; + + if (speed_ability & HCLGE_SUPPORT_40G_BIT) + return HCLGE_MAC_SPEED_40G; + + if (speed_ability & HCLGE_SUPPORT_25G_BIT) + return HCLGE_MAC_SPEED_25G; + + if (speed_ability & HCLGE_SUPPORT_10G_BIT) + return HCLGE_MAC_SPEED_10G; + + if (speed_ability & HCLGE_SUPPORT_1G_BIT) + return HCLGE_MAC_SPEED_1G; + + if (speed_ability & HCLGE_SUPPORT_100M_BIT) + return HCLGE_MAC_SPEED_100M; + + if (speed_ability & HCLGE_SUPPORT_10M_BIT) + return HCLGE_MAC_SPEED_10M; + + return HCLGE_MAC_SPEED_1G; +} + static void hclge_parse_cfg(struct hclge_cfg *cfg, struct hclge_desc *desc) { struct hclge_cfg_param_cmd *req; @@@ -1394,8 -1352,6 +1394,8 @@@ static int hclge_configure(struct hclge

hclge_parse_link_mode(hdev, cfg.speed_ability);

+ hdev->hw.mac.max_speed = hclge_get_max_speed(cfg.speed_ability); + if ((hdev->tc_max > HNAE3_MAX_TC) || (hdev->tc_max < 1)) { dev_warn(&hdev->pdev->dev, "TC num = %d.\n", @@@ -1551,10 -1507,6 +1551,10 @@@ static int hclge_assign_tqp(struct hcl kinfo->rss_size = min_t(u16, hdev->rss_size_max, vport->alloc_tqps / hdev->tm_info.num_tc);

+ /* ensure one to one mapping between irq and queue at default */ + kinfo->rss_size = min_t(u16, kinfo->rss_size, + (hdev->num_nic_msi - 1) / hdev->tm_info.num_tc); + return 0; }

@@@ -1681,7 -1633,6 +1681,7 @@@ static int hclge_alloc_vport(struct hcl for (i = 0; i < num_vport; i++) { vport->back = hdev; vport->vport_id = i; + vport->vf_info.link_state = IFLA_VF_LINK_STATE_AUTO; vport->mps = HCLGE_MAC_DEFAULT_FRAME; vport->port_base_vlan_cfg.state = HNAE3_PORT_BASE_VLAN_DISABLE; vport->rxvlan_cfg.rx_vlan_offload_en = true; @@@ -2334,8 -2285,7 +2334,8 @@@ static int hclge_init_msi(struct hclge_ int vectors; int i;

- vectors = pci_alloc_irq_vectors(pdev, 1, hdev->num_msi, + vectors = pci_alloc_irq_vectors(pdev, HNAE3_MIN_VECTOR_NUM, + hdev->num_msi, PCI_IRQ_MSI | PCI_IRQ_MSIX); if (vectors < 0) { dev_err(&pdev->dev, @@@ -2350,7 -2300,6 +2350,7 @@@

hdev->num_msi = vectors; hdev->num_msi_left = vectors; + hdev->base_msi_vector = pdev->irq; hdev->roce_base_vector = hdev->base_msi_vector + hdev->roce_base_msix_offset; @@@ -2904,62 -2853,6 +2904,62 @@@ static int hclge_get_status(struct hnae return hdev->hw.mac.link; }

+static struct hclge_vport *hclge_get_vf_vport(struct hclge_dev *hdev, int vf) +{ + if (pci_num_vf(hdev->pdev) == 0) { + dev_err(&hdev->pdev->dev, + "SRIOV is disabled, can not get vport(%d) info.\n", vf); + return NULL; + } + + if (vf < 0 || vf >= pci_num_vf(hdev->pdev)) { + dev_err(&hdev->pdev->dev, + "vf id(%d) is out of range(0 <= vfid < %d)\n", + vf, pci_num_vf(hdev->pdev)); + return NULL; + } + + /* VF start from 1 in vport */ + vf += HCLGE_VF_VPORT_START_NUM; + return &hdev->vport[vf]; +} + +static int hclge_get_vf_config(struct hnae3_handle *handle, int vf, + struct ifla_vf_info *ivf) +{ + struct hclge_vport *vport = hclge_get_vport(handle); + struct hclge_dev *hdev = vport->back; + + vport = hclge_get_vf_vport(hdev, vf); + if (!vport) + return -EINVAL; + + ivf->vf = vf; + ivf->linkstate = vport->vf_info.link_state; + ivf->spoofchk = vport->vf_info.spoofchk; + ivf->trusted = vport->vf_info.trusted; + ivf->min_tx_rate = 0; + ivf->max_tx_rate = vport->vf_info.max_tx_rate; + ether_addr_copy(ivf->mac, vport->vf_info.mac); + + return 0; +} + +static int hclge_set_vf_link_state(struct hnae3_handle *handle, int vf, + int link_state) +{ + struct hclge_vport *vport = hclge_get_vport(handle); + struct hclge_dev *hdev = vport->back; + + vport = hclge_get_vf_vport(hdev, vf); + if (!vport) + return -EINVAL; + + vport->vf_info.link_state = link_state; + + return 0; +} + static u32 hclge_check_event_cause(struct hclge_dev *hdev, u32 *clearval) { u32 rst_src_reg, cmdq_src_reg, msix_src_reg; @@@ -4010,7 -3903,6 +4010,7 @@@ static int hclge_get_vector(struct hnae int alloc = 0; int i, j;

+ vector_num = min_t(u16, hdev->num_nic_msi - 1, vector_num); vector_num = min(hdev->num_msi_left, vector_num);

for (j = 0; j < vector_num; j++) { @@@ -4666,8 -4558,8 +4666,8 @@@ static int hclge_unmap_ring_frm_vector( return ret; }

-int hclge_cmd_set_promisc_mode(struct hclge_dev *hdev, - struct hclge_promisc_param *param) +static int hclge_cmd_set_promisc_mode(struct hclge_dev *hdev, + struct hclge_promisc_param *param) { struct hclge_promisc_cfg_cmd *req; struct hclge_desc desc; @@@ -4694,9 -4586,8 +4694,9 @@@ return ret; }

-void hclge_promisc_param_init(struct hclge_promisc_param *param, bool en_uc, - bool en_mc, bool en_bc, int vport_id) +static void hclge_promisc_param_init(struct hclge_promisc_param *param, + bool en_uc, bool en_mc, bool en_bc, + int vport_id) { if (!param) return; @@@ -4711,21 -4602,12 +4711,21 @@@ param->vf_id = vport_id; }

+int hclge_set_vport_promisc_mode(struct hclge_vport *vport, bool en_uc_pmc, + bool en_mc_pmc, bool en_bc_pmc) +{ + struct hclge_dev *hdev = vport->back; + struct hclge_promisc_param param; + + hclge_promisc_param_init(&param, en_uc_pmc, en_mc_pmc, en_bc_pmc, + vport->vport_id); + return hclge_cmd_set_promisc_mode(hdev, &param); +} + static int hclge_set_promisc_mode(struct hnae3_handle *handle, bool en_uc_pmc, bool en_mc_pmc) { struct hclge_vport *vport = hclge_get_vport(handle); - struct hclge_dev *hdev = vport->back; - struct hclge_promisc_param param; bool en_bc_pmc = true;

/* For revision 0x20, if broadcast promisc enabled, vlan filter is @@@ -4735,8 -4617,9 +4735,8 @@@ if (handle->pdev->revision == 0x20) en_bc_pmc = handle->netdev_flags & HNAE3_BPE ? true : false;

- hclge_promisc_param_init(&param, en_uc_pmc, en_mc_pmc, en_bc_pmc, - vport->vport_id); - return hclge_cmd_set_promisc_mode(hdev, &param); + return hclge_set_vport_promisc_mode(vport, en_uc_pmc, en_mc_pmc, + en_bc_pmc); }

static int hclge_get_fd_mode(struct hclge_dev *hdev, u8 *fd_mode) @@@ -7508,67 -7391,6 +7508,67 @@@ static int hclge_get_mac_ethertype_cmd_ return return_status; }

+static bool hclge_check_vf_mac_exist(struct hclge_vport *vport, int vf_idx, + u8 *mac_addr) +{ + struct hclge_mac_vlan_tbl_entry_cmd req; + struct hclge_dev *hdev = vport->back; + struct hclge_desc desc; + u16 egress_port = 0; + int i; + + if (is_zero_ether_addr(mac_addr)) + return false; + + memset(&req, 0, sizeof(req)); + hnae3_set_field(egress_port, HCLGE_MAC_EPORT_VFID_M, + HCLGE_MAC_EPORT_VFID_S, vport->vport_id); + req.egress_port = cpu_to_le16(egress_port); + hclge_prepare_mac_addr(&req, mac_addr, false); + + if (hclge_lookup_mac_vlan_tbl(vport, &req, &desc, false) != -ENOENT) + return true; + + vf_idx += HCLGE_VF_VPORT_START_NUM; + for (i = hdev->num_vmdq_vport + 1; i < hdev->num_alloc_vport; i++) + if (i != vf_idx && + ether_addr_equal(mac_addr, hdev->vport[i].vf_info.mac)) + return true; + + return false; +} + +static int hclge_set_vf_mac(struct hnae3_handle *handle, int vf, + u8 *mac_addr) +{ + struct hclge_vport *vport = hclge_get_vport(handle); + struct hclge_dev *hdev = vport->back; + + vport = hclge_get_vf_vport(hdev, vf); + if (!vport) + return -EINVAL; + + if (ether_addr_equal(mac_addr, vport->vf_info.mac)) { + dev_info(&hdev->pdev->dev, + "Specified MAC(=%pM) is same as before, no change committed!\n", + mac_addr); + return 0; + } + + if (hclge_check_vf_mac_exist(vport, vf, mac_addr)) { + dev_err(&hdev->pdev->dev, "Specified MAC(=%pM) exists!\n", + mac_addr); + return -EEXIST; + } + + ether_addr_copy(vport->vf_info.mac, mac_addr); + dev_info(&hdev->pdev->dev, + "MAC of VF %d has been set to %pM, and it will be reinitialized!\n", + vf, mac_addr); + + return hclge_inform_reset_assert_to_vf(vport); +} + static int hclge_add_mgr_tbl(struct hclge_dev *hdev, const struct hclge_mac_mgr_tbl_entry_cmd *req) { @@@ -7742,8 -7564,6 +7742,8 @@@ static int hclge_set_vf_vlan_common(str __be16 proto) { #define HCLGE_MAX_VF_BYTES 16 + + struct hclge_vport *vport = &hdev->vport[vfid]; struct hclge_vlan_filter_vf_cfg_cmd *req0; struct hclge_vlan_filter_vf_cfg_cmd *req1; struct hclge_desc desc[2]; @@@ -7752,18 -7572,10 +7752,18 @@@ int ret;

/* if vf vlan table is full, firmware will close vf vlan filter, it - * is unable and unnecessary to add new vlan id to vf vlan filter + * is unable and unnecessary to add new vlan id to vf vlan filter. + * If spoof check is enable, and vf vlan is full, it shouldn't add + * new vlan, because tx packets with these vlan id will be dropped. */ - if (test_bit(vfid, hdev->vf_vlan_full) && !is_kill) + if (test_bit(vfid, hdev->vf_vlan_full) && !is_kill) { + if (vport->vf_info.spoofchk && vlan) { + dev_err(&hdev->pdev->dev, + "Can't add vlan due to spoof check is on and vf vlan table is full\n"); + return -EPERM; + } return 0; + }

hclge_cmd_setup_basic_desc(&desc[0], HCLGE_OPC_VLAN_FILTER_VF_CFG, false); @@@ -8260,15 -8072,12 +8260,15 @@@ static void hclge_restore_vlan_table(st }

list_for_each_entry_safe(vlan, tmp, &vport->vlan_list, node) { - if (vlan->hd_tbl_status) - hclge_set_vlan_filter_hw(hdev, - htons(ETH_P_8021Q), - vport->vport_id, - vlan->vlan_id, - false); + int ret; + + if (!vlan->hd_tbl_status) + continue; + ret = hclge_set_vlan_filter_hw(hdev, htons(ETH_P_8021Q), + vport->vport_id, + vlan->vlan_id, false); + if (ret) + break; } }

@@@ -9510,219 -9319,6 +9510,219 @@@ static void hclge_stats_clear(struct hc memset(&hdev->hw_stats, 0, sizeof(hdev->hw_stats)); }

+static int hclge_set_mac_spoofchk(struct hclge_dev *hdev, int vf, bool enable) +{ + return hclge_config_switch_param(hdev, vf, enable, + HCLGE_SWITCH_ANTI_SPOOF_MASK); +} + +static int hclge_set_vlan_spoofchk(struct hclge_dev *hdev, int vf, bool enable) +{ + return hclge_set_vlan_filter_ctrl(hdev, HCLGE_FILTER_TYPE_VF, + HCLGE_FILTER_FE_NIC_INGRESS_B, + enable, vf); +} + +static int hclge_set_vf_spoofchk_hw(struct hclge_dev *hdev, int vf, bool enable) +{ + int ret; + + ret = hclge_set_mac_spoofchk(hdev, vf, enable); + if (ret) { + dev_err(&hdev->pdev->dev, + "Set vf %d mac spoof check %s failed, ret=%d\n", + vf, enable ? "on" : "off", ret); + return ret; + } + + ret = hclge_set_vlan_spoofchk(hdev, vf, enable); + if (ret) + dev_err(&hdev->pdev->dev, + "Set vf %d vlan spoof check %s failed, ret=%d\n", + vf, enable ? "on" : "off", ret); + + return ret; +} + +static int hclge_set_vf_spoofchk(struct hnae3_handle *handle, int vf, + bool enable) +{ + struct hclge_vport *vport = hclge_get_vport(handle); + struct hclge_dev *hdev = vport->back; + u32 new_spoofchk = enable ? 1 : 0; + int ret; + + if (hdev->pdev->revision == 0x20) + return -EOPNOTSUPP; + + vport = hclge_get_vf_vport(hdev, vf); + if (!vport) + return -EINVAL; + + if (vport->vf_info.spoofchk == new_spoofchk) + return 0; + + if (enable && test_bit(vport->vport_id, hdev->vf_vlan_full)) + dev_warn(&hdev->pdev->dev, + "vf %d vlan table is full, enable spoof check may cause its packet send fail\n", + vf); + else if (enable && hclge_is_umv_space_full(vport)) + dev_warn(&hdev->pdev->dev, + "vf %d mac table is full, enable spoof check may cause its packet send fail\n", + vf); + + ret = hclge_set_vf_spoofchk_hw(hdev, vport->vport_id, enable); + if (ret) + return ret; + + vport->vf_info.spoofchk = new_spoofchk; + return 0; +} + +static int hclge_reset_vport_spoofchk(struct hclge_dev *hdev) +{ + struct hclge_vport *vport = hdev->vport; + int ret; + int i; + + if (hdev->pdev->revision == 0x20) + return 0; + + /* resume the vf spoof check state after reset */ + for (i = 0; i < hdev->num_alloc_vport; i++) { + ret = hclge_set_vf_spoofchk_hw(hdev, vport->vport_id, + vport->vf_info.spoofchk); + if (ret) + return ret; + + vport++; + } + + return 0; +} + +static int hclge_set_vf_trust(struct hnae3_handle *handle, int vf, bool enable) +{ + struct hclge_vport *vport = hclge_get_vport(handle); + struct hclge_dev *hdev = vport->back; + u32 new_trusted = enable ? 1 : 0; + bool en_bc_pmc; + int ret; + + vport = hclge_get_vf_vport(hdev, vf); + if (!vport) + return -EINVAL; + + if (vport->vf_info.trusted == new_trusted) + return 0; + + /* Disable promisc mode for VF if it is not trusted any more. */ + if (!enable && vport->vf_info.promisc_enable) { + en_bc_pmc = hdev->pdev->revision != 0x20; + ret = hclge_set_vport_promisc_mode(vport, false, false, + en_bc_pmc); + if (ret) + return ret; + vport->vf_info.promisc_enable = 0; + hclge_inform_vf_promisc_info(vport); + } + + vport->vf_info.trusted = new_trusted; + + return 0; +} + +static void hclge_reset_vf_rate(struct hclge_dev *hdev) +{ + int ret; + int vf; + + /* reset vf rate to default value */ + for (vf = HCLGE_VF_VPORT_START_NUM; vf < hdev->num_alloc_vport; vf++) { + struct hclge_vport *vport = &hdev->vport[vf]; + + vport->vf_info.max_tx_rate = 0; + ret = hclge_tm_qs_shaper_cfg(vport, vport->vf_info.max_tx_rate); + if (ret) + dev_err(&hdev->pdev->dev, + "vf%d failed to reset to default, ret=%d\n", + vf - HCLGE_VF_VPORT_START_NUM, ret); + } +} + +static int hclge_vf_rate_param_check(struct hclge_dev *hdev, int vf, + int min_tx_rate, int max_tx_rate) +{ + if (min_tx_rate != 0 || + max_tx_rate < 0 || max_tx_rate > hdev->hw.mac.max_speed) { + dev_err(&hdev->pdev->dev, + "min_tx_rate:%d [0], max_tx_rate:%d [0, %u]\n", + min_tx_rate, max_tx_rate, hdev->hw.mac.max_speed); + return -EINVAL; + } + + return 0; +} + +static int hclge_set_vf_rate(struct hnae3_handle *handle, int vf, + int min_tx_rate, int max_tx_rate, bool force) +{ + struct hclge_vport *vport = hclge_get_vport(handle); + struct hclge_dev *hdev = vport->back; + int ret; + + ret = hclge_vf_rate_param_check(hdev, vf, min_tx_rate, max_tx_rate); + if (ret) + return ret; + + vport = hclge_get_vf_vport(hdev, vf); + if (!vport) + return -EINVAL; + + if (!force && max_tx_rate == vport->vf_info.max_tx_rate) + return 0; + + ret = hclge_tm_qs_shaper_cfg(vport, max_tx_rate); + if (ret) + return ret; + + vport->vf_info.max_tx_rate = max_tx_rate; + + return 0; +} + +static int hclge_resume_vf_rate(struct hclge_dev *hdev) +{ + struct hnae3_handle *handle = &hdev->vport->nic; + struct hclge_vport *vport; + int ret; + int vf; + + /* resume the vf max_tx_rate after reset */ + for (vf = 0; vf < pci_num_vf(hdev->pdev); vf++) { + vport = hclge_get_vf_vport(hdev, vf); + if (!vport) + return -EINVAL; + + /* zero means max rate, after reset, firmware already set it to + * max rate, so just continue. + */ + if (!vport->vf_info.max_tx_rate) + continue; + + ret = hclge_set_vf_rate(handle, vf, 0, + vport->vf_info.max_tx_rate, true); + if (ret) { + dev_err(&hdev->pdev->dev, + "vf%d failed to resume tx_rate:%u, ret=%d\n", + vf, vport->vf_info.max_tx_rate, ret); + return ret; + } + } + + return 0; +} + static void hclge_reset_vport_state(struct hclge_dev *hdev) { struct hclge_vport *vport = hdev->vport; @@@ -9800,9 -9396,6 +9800,9 @@@ static int hclge_reset_ae_dev(struct hn return ret; }

+ /* Log and clear the hw errors those already occurred */ + hclge_handle_all_hns_hw_errors(ae_dev); + /* Re-enable the hw error interrupts because * the interrupts get disabled on global reset. */ @@@ -9825,13 -9418,6 +9825,13 @@@ }

hclge_reset_vport_state(hdev); + ret = hclge_reset_vport_spoofchk(hdev); + if (ret) + return ret; + + ret = hclge_resume_vf_rate(hdev); + if (ret) + return ret;

dev_info(&pdev->dev, "Reset done, %s driver initialization finished.\n", HCLGE_DRIVER_NAME); @@@ -9844,7 -9430,6 +9844,7 @@@ static void hclge_uninit_ae_dev(struct struct hclge_dev *hdev = ae_dev->priv; struct hclge_mac *mac = &hdev->hw.mac;

+ hclge_reset_vf_rate(hdev); hclge_misc_affinity_teardown(hdev); hclge_state_uninit(hdev);

@@@ -10213,7 -9798,7 +10213,7 @@@ static int hclge_get_dfx_reg_len(struc return ret; }

- data_len_per_desc = FIELD_SIZEOF(struct hclge_desc, data); + data_len_per_desc = sizeof_member(struct hclge_desc, data); *len = 0; for (i = 0; i < dfx_reg_type_num; i++) { bd_num = bd_num_list[i]; @@@ -10567,12 -10152,6 +10567,12 @@@ static const struct hnae3_ae_ops hclge_ .mac_connect_phy = hclge_mac_connect_phy, .mac_disconnect_phy = hclge_mac_disconnect_phy, .restore_vlan_table = hclge_restore_vlan_table, + .get_vf_config = hclge_get_vf_config, + .set_vf_link_state = hclge_set_vf_link_state, + .set_vf_spoofchk = hclge_set_vf_spoofchk, + .set_vf_trust = hclge_set_vf_trust, + .set_vf_rate = hclge_set_vf_rate, + .set_vf_mac = hclge_set_vf_mac, };

static struct hnae3_ae_algo ae_algo = { diff --combined drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c index b3c30e5f9aa5,a0f08f94b12b..c5e9d0604f09 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c @@@ -46,7 -46,7 +46,7 @@@ static int hclge_shaper_para_calc(u32 i #define DIVISOR_CLK (1000 * 8) #define DIVISOR_IR_B_126 (126 * DIVISOR_CLK)

- const u16 tick_array[HCLGE_SHAPER_LVL_CNT] = { + static const u16 tick_array[HCLGE_SHAPER_LVL_CNT] = { 6 * 256, /* Prioriy level */ 6 * 32, /* Prioriy group level */ 6 * 8, /* Port level */ @@@ -511,49 -511,6 +511,49 @@@ static int hclge_tm_qs_bp_cfg(struct hc return hclge_cmd_send(&hdev->hw, &desc, 1); }

+int hclge_tm_qs_shaper_cfg(struct hclge_vport *vport, int max_tx_rate) +{ + struct hnae3_knic_private_info *kinfo = &vport->nic.kinfo; + struct hclge_qs_shapping_cmd *shap_cfg_cmd; + struct hclge_dev *hdev = vport->back; + struct hclge_desc desc; + u8 ir_b, ir_u, ir_s; + u32 shaper_para; + int ret, i; + + if (!max_tx_rate) + max_tx_rate = HCLGE_ETHER_MAX_RATE; + + ret = hclge_shaper_para_calc(max_tx_rate, HCLGE_SHAPER_LVL_QSET, + &ir_b, &ir_u, &ir_s); + if (ret) + return ret; + + shaper_para = hclge_tm_get_shapping_para(ir_b, ir_u, ir_s, + HCLGE_SHAPER_BS_U_DEF, + HCLGE_SHAPER_BS_S_DEF); + + for (i = 0; i < kinfo->num_tc; i++) { + hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_QCN_SHAPPING_CFG, + false); + + shap_cfg_cmd = (struct hclge_qs_shapping_cmd *)desc.data; + shap_cfg_cmd->qs_id = cpu_to_le16(vport->qs_offset + i); + shap_cfg_cmd->qs_shapping_para = cpu_to_le32(shaper_para); + + ret = hclge_cmd_send(&hdev->hw, &desc, 1); + if (ret) { + dev_err(&hdev->pdev->dev, + "vf%d, qs%u failed to set tx_rate:%d, ret=%d\n", + vport->vport_id, shap_cfg_cmd->qs_id, + max_tx_rate, ret); + return ret; + } + } + + return 0; +} + static void hclge_tm_vport_tc_info_update(struct hclge_vport *vport) { struct hnae3_knic_private_info *kinfo = &vport->nic.kinfo; @@@ -580,16 -537,9 +580,16 @@@ kinfo->rss_size = kinfo->req_rss_size; } else if (kinfo->rss_size > max_rss_size || (!kinfo->req_rss_size && kinfo->rss_size < max_rss_size)) { + /* if user not set rss, the rss_size should compare with the + * valid msi numbers to ensure one to one map between tqp and + * irq as default. + */ + if (!kinfo->req_rss_size) + max_rss_size = min_t(u16, max_rss_size, + (hdev->num_nic_msi - 1) / + kinfo->num_tc); + /* Set to the maximum specification value (max_rss_size). */ - dev_info(&hdev->pdev->dev, "rss changes from %d to %d\n", - kinfo->rss_size, max_rss_size); kinfo->rss_size = max_rss_size; }

@@@ -614,7 -564,7 +614,7 @@@ }

memcpy(kinfo->prio_tc, hdev->tm_info.prio_tc, - FIELD_SIZEOF(struct hnae3_knic_private_info, prio_tc)); + sizeof_member(struct hnae3_knic_private_info, prio_tc)); }

static void hclge_tm_vport_info_update(struct hclge_dev *hdev) diff --combined drivers/net/ethernet/intel/i40e/i40e_ethtool.c index d24d8731bef0,8b0c60d754e1..990e29ff7ac4 --- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c +++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c @@@ -43,7 -43,7 +43,7 @@@ struct i40e_stats */ #define I40E_STAT(_type, _name, _stat) { \ .stat_string = _name, \ - .sizeof_stat = FIELD_SIZEOF(_type, _stat), \ + .sizeof_stat = sizeof_member(_type, _stat), \ .stat_offset = offsetof(_type, _stat) \ }

@@@ -722,14 -722,7 +722,14 @@@ static void i40e_get_settings_link_up_f ethtool_link_ksettings_add_link_mode(ks, supported, FEC_RS); ethtool_link_ksettings_add_link_mode(ks, supported, FEC_BASER);

- if (I40E_AQ_SET_FEC_REQUEST_RS & req_fec_info) { + if ((I40E_AQ_SET_FEC_REQUEST_RS & req_fec_info) && + (I40E_AQ_SET_FEC_REQUEST_KR & req_fec_info)) { + ethtool_link_ksettings_add_link_mode(ks, advertising, + FEC_NONE); + ethtool_link_ksettings_add_link_mode(ks, advertising, + FEC_BASER); + ethtool_link_ksettings_add_link_mode(ks, advertising, FEC_RS); + } else if (I40E_AQ_SET_FEC_REQUEST_RS & req_fec_info) { ethtool_link_ksettings_add_link_mode(ks, advertising, FEC_RS); } else if (I40E_AQ_SET_FEC_REQUEST_KR & req_fec_info) { ethtool_link_ksettings_add_link_mode(ks, advertising, @@@ -737,6 -730,12 +737,6 @@@ } else { ethtool_link_ksettings_add_link_mode(ks, advertising, FEC_NONE); - if (I40E_AQ_SET_FEC_AUTO & req_fec_info) { - ethtool_link_ksettings_add_link_mode(ks, advertising, - FEC_RS); - ethtool_link_ksettings_add_link_mode(ks, advertising, - FEC_BASER); - } } }

@@@ -1438,7 -1437,6 +1438,7 @@@ static int i40e_get_fec_param(struct ne struct i40e_hw *hw = &pf->hw; i40e_status status = 0; int err = 0; + u8 fec_cfg;

/* Get the current phy config */ memset(&abilities, 0, sizeof(abilities)); @@@ -1450,16 -1448,18 +1450,16 @@@ }

fecparam->fec = 0; - if (abilities.fec_cfg_curr_mod_ext_info & I40E_AQ_SET_FEC_AUTO) + fec_cfg = abilities.fec_cfg_curr_mod_ext_info; + if (fec_cfg & I40E_AQ_SET_FEC_AUTO) fecparam->fec |= ETHTOOL_FEC_AUTO; - if ((abilities.fec_cfg_curr_mod_ext_info & - I40E_AQ_SET_FEC_REQUEST_RS) || - (abilities.fec_cfg_curr_mod_ext_info & - I40E_AQ_SET_FEC_ABILITY_RS)) + else if (fec_cfg & (I40E_AQ_SET_FEC_REQUEST_RS | + I40E_AQ_SET_FEC_ABILITY_RS)) fecparam->fec |= ETHTOOL_FEC_RS; - if ((abilities.fec_cfg_curr_mod_ext_info & - I40E_AQ_SET_FEC_REQUEST_KR) || - (abilities.fec_cfg_curr_mod_ext_info & I40E_AQ_SET_FEC_ABILITY_KR)) + else if (fec_cfg & (I40E_AQ_SET_FEC_REQUEST_KR | + I40E_AQ_SET_FEC_ABILITY_KR)) fecparam->fec |= ETHTOOL_FEC_BASER; - if (abilities.fec_cfg_curr_mod_ext_info == 0) + if (fec_cfg == 0) fecparam->fec |= ETHTOOL_FEC_OFF;

if (hw->phy.link_info.fec_info & I40E_AQ_CONFIG_FEC_KR_ENA) @@@ -5112,7 -5112,7 +5112,7 @@@ static int i40e_get_module_info(struct case I40E_MODULE_TYPE_SFP: status = i40e_aq_get_phy_register(hw, I40E_AQ_PHY_REG_ACCESS_EXTERNAL_MODULE, - I40E_I2C_EEPROM_DEV_ADDR, + I40E_I2C_EEPROM_DEV_ADDR, true, I40E_MODULE_SFF_8472_COMP, &sff8472_comp, NULL); if (status) @@@ -5120,7 -5120,7 +5120,7 @@@

status = i40e_aq_get_phy_register(hw, I40E_AQ_PHY_REG_ACCESS_EXTERNAL_MODULE, - I40E_I2C_EEPROM_DEV_ADDR, + I40E_I2C_EEPROM_DEV_ADDR, true, I40E_MODULE_SFF_8472_SWAP, &sff8472_swap, NULL); if (status) @@@ -5152,7 -5152,7 +5152,7 @@@ /* Read from memory page 0. */ status = i40e_aq_get_phy_register(hw, I40E_AQ_PHY_REG_ACCESS_EXTERNAL_MODULE, - 0, + 0, true, I40E_MODULE_REVISION_ADDR, &sff8636_rev, NULL); if (status) @@@ -5223,7 -5223,7 +5223,7 @@@ static int i40e_get_module_eeprom(struc

status = i40e_aq_get_phy_register(hw, I40E_AQ_PHY_REG_ACCESS_EXTERNAL_MODULE, - addr, offset, &value, NULL); + true, addr, offset, &value, NULL); if (status) return -EIO; data[i] = value; @@@ -5242,7 -5242,6 +5242,7 @@@ static int i40e_set_eee(struct net_devi }

static const struct ethtool_ops i40e_ethtool_recovery_mode_ops = { + .get_drvinfo = i40e_get_drvinfo, .set_eeprom = i40e_set_eeprom, .get_eeprom_len = i40e_get_eeprom_len, .get_eeprom = i40e_get_eeprom, diff --combined drivers/net/ethernet/netronome/nfp/bpf/jit.c index c80bb83c8ac9,276af07a2841..a2c02be6e34c --- a/drivers/net/ethernet/netronome/nfp/bpf/jit.c +++ b/drivers/net/ethernet/netronome/nfp/bpf/jit.c @@@ -2652,17 -2652,17 +2652,17 @@@ static int mem_ldx_skb(struct nfp_prog

switch (meta->insn.off) { case offsetof(struct __sk_buff, len): - if (size != FIELD_SIZEOF(struct __sk_buff, len)) + if (size != sizeof_member(struct __sk_buff, len)) return -EOPNOTSUPP; wrp_mov(nfp_prog, dst, plen_reg(nfp_prog)); break; case offsetof(struct __sk_buff, data): - if (size != FIELD_SIZEOF(struct __sk_buff, data)) + if (size != sizeof_member(struct __sk_buff, data)) return -EOPNOTSUPP; wrp_mov(nfp_prog, dst, pptr_reg(nfp_prog)); break; case offsetof(struct __sk_buff, data_end): - if (size != FIELD_SIZEOF(struct __sk_buff, data_end)) + if (size != sizeof_member(struct __sk_buff, data_end)) return -EOPNOTSUPP; emit_alu(nfp_prog, dst, plen_reg(nfp_prog), ALU_OP_ADD, pptr_reg(nfp_prog)); @@@ -2683,12 -2683,12 +2683,12 @@@ static int mem_ldx_xdp(struct nfp_prog

switch (meta->insn.off) { case offsetof(struct xdp_md, data): - if (size != FIELD_SIZEOF(struct xdp_md, data)) + if (size != sizeof_member(struct xdp_md, data)) return -EOPNOTSUPP; wrp_mov(nfp_prog, dst, pptr_reg(nfp_prog)); break; case offsetof(struct xdp_md, data_end): - if (size != FIELD_SIZEOF(struct xdp_md, data_end)) + if (size != sizeof_member(struct xdp_md, data_end)) return -EOPNOTSUPP; emit_alu(nfp_prog, dst, plen_reg(nfp_prog), ALU_OP_ADD, pptr_reg(nfp_prog)); @@@ -3952,7 -3952,7 +3952,7 @@@ static void nfp_bpf_opt_neg_add_sub(str static void nfp_bpf_opt_ld_mask(struct nfp_prog *nfp_prog) { struct nfp_insn_meta *meta1, *meta2; - const s32 exp_mask[] = { + static const s32 exp_mask[] = { [BPF_B] = 0x000000ffU, [BPF_H] = 0x0000ffffU, [BPF_W] = 0xffffffffU, diff --combined drivers/net/hyperv/netvsc_drv.c index fd4fff57fd6e,6102264d9978..83c3c78e9f05 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@@ -571,7 -571,7 +571,7 @@@ static int netvsc_start_xmit(struct sk_

/* Use the skb control buffer for building up the packet */ BUILD_BUG_ON(sizeof(struct hv_netvsc_packet) > - FIELD_SIZEOF(struct sk_buff, cb)); + sizeof_member(struct sk_buff, cb)); packet = (struct hv_netvsc_packet *)skb->cb;

packet->q_idx = skb_get_queue_mapping(skb); @@@ -2335,6 -2335,8 +2335,6 @@@ static int netvsc_probe(struct hv_devic NETIF_F_HW_VLAN_CTAG_RX; net->vlan_features = net->features;

- netdev_lockdep_set_classes(net); - /* MTU range: 68 - 1500 or 65521 */ net->min_mtu = NETVSC_MTU_MIN; if (nvdev->nvsp_version >= NVSP_PROTOCOL_VERSION_2) diff --combined drivers/net/vxlan.c index 8869154fad88,27bfde225a73..4700191d1adc --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@@ -2487,11 -2487,9 +2487,11 @@@ static void vxlan_xmit_one(struct sk_bu vni = tunnel_id_to_key32(info->key.tun_id); ifindex = 0; dst_cache = &info->dst_cache; - if (info->options_len && - info->key.tun_flags & TUNNEL_VXLAN_OPT) + if (info->key.tun_flags & TUNNEL_VXLAN_OPT) { + if (info->options_len < sizeof(*md)) + goto drop; md = ip_tunnel_info_opts(info); + } ttl = info->key.ttl; tos = info->key.tos; label = info->key.label; @@@ -3072,10 -3070,10 +3072,10 @@@ static void vxlan_raw_setup(struct net_

static const struct nla_policy vxlan_policy[IFLA_VXLAN_MAX + 1] = { [IFLA_VXLAN_ID] = { .type = NLA_U32 }, - [IFLA_VXLAN_GROUP] = { .len = FIELD_SIZEOF(struct iphdr, daddr) }, + [IFLA_VXLAN_GROUP] = { .len = sizeof_member(struct iphdr, daddr) }, [IFLA_VXLAN_GROUP6] = { .len = sizeof(struct in6_addr) }, [IFLA_VXLAN_LINK] = { .type = NLA_U32 }, - [IFLA_VXLAN_LOCAL] = { .len = FIELD_SIZEOF(struct iphdr, saddr) }, + [IFLA_VXLAN_LOCAL] = { .len = sizeof_member(struct iphdr, saddr) }, [IFLA_VXLAN_LOCAL6] = { .len = sizeof(struct in6_addr) }, [IFLA_VXLAN_TOS] = { .type = NLA_U8 }, [IFLA_VXLAN_TTL] = { .type = NLA_U8 }, @@@ -3568,13 -3566,10 +3568,13 @@@ static int __vxlan_dev_create(struct ne { struct vxlan_net *vn = net_generic(net, vxlan_net_id); struct vxlan_dev *vxlan = netdev_priv(dev); + struct net_device *remote_dev = NULL; struct vxlan_fdb *f = NULL; bool unregister = false; + struct vxlan_rdst *dst; int err;

+ dst = &vxlan->default_dst; err = vxlan_dev_configure(net, dev, conf, false, extack); if (err) return err; @@@ -3582,14 -3577,14 +3582,14 @@@ dev->ethtool_ops = &vxlan_ethtool_ops;

/* create an fdb entry for a valid default destination */ - if (!vxlan_addr_any(&vxlan->default_dst.remote_ip)) { + if (!vxlan_addr_any(&dst->remote_ip)) { err = vxlan_fdb_create(vxlan, all_zeros_mac, - &vxlan->default_dst.remote_ip, + &dst->remote_ip, NUD_REACHABLE | NUD_PERMANENT, vxlan->cfg.dst_port, - vxlan->default_dst.remote_vni, - vxlan->default_dst.remote_vni, - vxlan->default_dst.remote_ifindex, + dst->remote_vni, + dst->remote_vni, + dst->remote_ifindex, NTF_SELF, &f); if (err) return err; @@@ -3600,41 -3595,26 +3600,41 @@@ goto errout; unregister = true;

+ if (dst->remote_ifindex) { + remote_dev = __dev_get_by_index(net, dst->remote_ifindex); + if (!remote_dev) + goto errout; + + err = netdev_upper_dev_link(remote_dev, dev, extack); + if (err) + goto errout; + } + err = rtnl_configure_link(dev, NULL); if (err) - goto errout; + goto unlink;

if (f) { - vxlan_fdb_insert(vxlan, all_zeros_mac, - vxlan->default_dst.remote_vni, f); + vxlan_fdb_insert(vxlan, all_zeros_mac, dst->remote_vni, f);

/* notify default fdb entry */ err = vxlan_fdb_notify(vxlan, f, first_remote_rtnl(f), RTM_NEWNEIGH, true, extack); if (err) { vxlan_fdb_destroy(vxlan, f, false, false); + if (remote_dev) + netdev_upper_dev_unlink(remote_dev, dev); goto unregister; } }

list_add(&vxlan->next, &vn->vxlan_list); + if (remote_dev) + dst->remote_dev = remote_dev; return 0; - +unlink: + if (remote_dev) + netdev_upper_dev_unlink(remote_dev, dev); errout: /* unregister_netdevice() destroys the default FDB entry with deletion * notification. But the addition notification was not sent yet, so @@@ -3952,12 -3932,11 +3952,12 @@@ static int vxlan_changelink(struct net_ struct netlink_ext_ack *extack) { struct vxlan_dev *vxlan = netdev_priv(dev); - struct vxlan_rdst *dst = &vxlan->default_dst; struct net_device *lowerdev; struct vxlan_config conf; + struct vxlan_rdst *dst; int err;

+ dst = &vxlan->default_dst; err = vxlan_nl2conf(tb, data, dev, &conf, true, extack); if (err) return err; @@@ -3967,14 -3946,6 +3967,14 @@@ if (err) return err;

+ if (dst->remote_dev == lowerdev) + lowerdev = NULL; + + err = netdev_adjacent_change_prepare(dst->remote_dev, lowerdev, dev, + extack); + if (err) + return err; + /* handle default dst entry */ if (!vxlan_addr_equal(&conf.remote_ip, &dst->remote_ip)) { u32 hash_index = fdb_head_index(vxlan, all_zeros_mac, conf.vni); @@@ -3991,8 -3962,6 +3991,8 @@@ NTF_SELF, true, extack); if (err) { spin_unlock_bh(&vxlan->hash_lock[hash_index]); + netdev_adjacent_change_abort(dst->remote_dev, + lowerdev, dev); return err; } } @@@ -4010,11 -3979,6 +4010,11 @@@ if (conf.age_interval != vxlan->cfg.age_interval) mod_timer(&vxlan->age_timer, jiffies);

+ netdev_adjacent_change_commit(dst->remote_dev, lowerdev, dev); + if (lowerdev && lowerdev != dst->remote_dev) { + dst->remote_dev = lowerdev; + netdev_update_lockdep_key(lowerdev); + } vxlan_config_apply(dev, &conf, lowerdev, vxlan->net, true); return 0; } @@@ -4027,8 -3991,6 +4027,8 @@@ static void vxlan_dellink(struct net_de

list_del(&vxlan->next); unregister_netdevice_queue(dev, head); + if (vxlan->default_dst.remote_dev) + netdev_upper_dev_unlink(vxlan->default_dst.remote_dev, dev); }

static size_t vxlan_get_size(const struct net_device *dev) diff --combined drivers/scsi/aacraid/aachba.c index e36608ce937a,f30fe29b5701..3b232b6a3eff --- a/drivers/scsi/aacraid/aachba.c +++ b/drivers/scsi/aacraid/aachba.c @@@ -535,7 -535,7 +535,7 @@@ static void get_container_name_callback if ((le32_to_cpu(get_name_reply->status) == CT_OK) && (get_name_reply->data[0] != '\0')) { char *sp = get_name_reply->data; - int data_size = FIELD_SIZEOF(struct aac_get_name_resp, data); + int data_size = sizeof_member(struct aac_get_name_resp, data);

sp[data_size - 1] = '\0'; while (*sp == ' ') @@@ -574,7 -574,7 +574,7 @@@ static int aac_get_container_name(struc

dev = (struct aac_dev *)scsicmd->device->host->hostdata;

- data_size = FIELD_SIZEOF(struct aac_get_name_resp, data); + data_size = sizeof_member(struct aac_get_name_resp, data);

cmd_fibcontext = aac_fib_alloc_tag(dev, scsicmd);

@@@ -1477,7 -1477,6 +1477,7 @@@ static struct aac_srb * aac_scsi_common struct aac_srb * srbcmd; u32 flag; u32 timeout; + struct aac_dev *dev = fib->dev;

aac_fib_init(fib); switch(cmd->sc_data_direction){ @@@ -1504,7 -1503,7 +1504,7 @@@ srbcmd->flags = cpu_to_le32(flag); timeout = cmd->request->timeout/HZ; if (timeout == 0) - timeout = 1; + timeout = (dev->sa_firmware ? AAC_SA_TIMEOUT : AAC_ARC_TIMEOUT); srbcmd->timeout = cpu_to_le32(timeout); // timeout in seconds srbcmd->retry_limit = 0; /* Obsolete parameter */ srbcmd->cdb_size = cpu_to_le32(cmd->cmd_len); @@@ -2468,13 -2467,13 +2468,13 @@@ static int aac_read(struct scsi_cmnd * scsicmd->result = DID_OK << 16 | COMMAND_COMPLETE << 8 | SAM_STAT_CHECK_CONDITION; set_sense(&dev->fsa_dev[cid].sense_data, - HARDWARE_ERROR, SENCODE_INTERNAL_TARGET_FAILURE, + ILLEGAL_REQUEST, SENCODE_LBA_OUT_OF_RANGE, ASENCODE_INTERNAL_TARGET_FAILURE, 0, 0); memcpy(scsicmd->sense_buffer, &dev->fsa_dev[cid].sense_data, min_t(size_t, sizeof(dev->fsa_dev[cid].sense_data), SCSI_SENSE_BUFFERSIZE)); scsicmd->scsi_done(scsicmd); - return 1; + return 0; }

dprintk((KERN_DEBUG "aac_read[cpu %d]: lba = %llu, t = %ld.\n", @@@ -2560,13 -2559,13 +2560,13 @@@ static int aac_write(struct scsi_cmnd scsicmd->result = DID_OK << 16 | COMMAND_COMPLETE << 8 | SAM_STAT_CHECK_CONDITION; set_sense(&dev->fsa_dev[cid].sense_data, - HARDWARE_ERROR, SENCODE_INTERNAL_TARGET_FAILURE, + ILLEGAL_REQUEST, SENCODE_LBA_OUT_OF_RANGE, ASENCODE_INTERNAL_TARGET_FAILURE, 0, 0); memcpy(scsicmd->sense_buffer, &dev->fsa_dev[cid].sense_data, min_t(size_t, sizeof(dev->fsa_dev[cid].sense_data), SCSI_SENSE_BUFFERSIZE)); scsicmd->scsi_done(scsicmd); - return 1; + return 0; }

dprintk((KERN_DEBUG "aac_write[cpu %d]: lba = %llu, t = %ld.\n", diff --combined drivers/scsi/cxgbi/libcxgbi.c index 0d044c165960,cf261e1ae9d4..e7143b257117 --- a/drivers/scsi/cxgbi/libcxgbi.c +++ b/drivers/scsi/cxgbi/libcxgbi.c @@@ -2284,6 -2284,34 +2284,6 @@@ int cxgbi_set_conn_param(struct iscsi_c } EXPORT_SYMBOL_GPL(cxgbi_set_conn_param);

-static inline int csk_print_port(struct cxgbi_sock *csk, char *buf) -{ - int len; - - cxgbi_sock_get(csk); - len = sprintf(buf, "%hu\n", ntohs(csk->daddr.sin_port)); - cxgbi_sock_put(csk); - - return len; -} - -static inline int csk_print_ip(struct cxgbi_sock *csk, char *buf) -{ - int len; - - cxgbi_sock_get(csk); - if (csk->csk_family == AF_INET) - len = sprintf(buf, "%pI4", - &csk->daddr.sin_addr.s_addr); - else - len = sprintf(buf, "%pI6", - &csk->daddr6.sin6_addr); - - cxgbi_sock_put(csk); - - return len; -} - int cxgbi_get_ep_param(struct iscsi_endpoint *ep, enum iscsi_param param, char *buf) { @@@ -2746,7 -2774,7 +2746,7 @@@ static int __init libcxgbi_init_module( { pr_info("%s", version);

- BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, cb) < + BUILD_BUG_ON(sizeof_member(struct sk_buff, cb) < sizeof(struct cxgbi_skb_cb)); return 0; } diff --combined drivers/scsi/smartpqi/smartpqi_init.c index 7b7ef3acb504,fafa4c1c2fea..e1499626cbbd --- a/drivers/scsi/smartpqi/smartpqi_init.c +++ b/drivers/scsi/smartpqi/smartpqi_init.c @@@ -33,11 -33,11 +33,11 @@@ #define BUILD_TIMESTAMP #endif

-#define DRIVER_VERSION "1.2.8-026" +#define DRIVER_VERSION "1.2.10-025" #define DRIVER_MAJOR 1 #define DRIVER_MINOR 2 -#define DRIVER_RELEASE 8 -#define DRIVER_REVISION 26 +#define DRIVER_RELEASE 10 +#define DRIVER_REVISION 25

#define DRIVER_NAME "Microsemi PQI Driver (v" \ DRIVER_VERSION BUILD_TIMESTAMP ")" @@@ -211,11 -211,6 +211,11 @@@ static inline bool pqi_is_external_raid return scsi3addr[2] != 0; }

+static inline bool pqi_ctrl_offline(struct pqi_ctrl_info *ctrl_info) +{ + return !ctrl_info->controller_online; +} + static inline void pqi_check_ctrl_health(struct pqi_ctrl_info *ctrl_info) { if (ctrl_info->controller_online) @@@ -240,21 -235,6 +240,21 @@@ static inline void pqi_save_ctrl_mode(s sis_write_driver_scratch(ctrl_info, mode); }

+static inline void pqi_ctrl_block_device_reset(struct pqi_ctrl_info *ctrl_info) +{ + ctrl_info->block_device_reset = true; +} + +static inline bool pqi_device_reset_blocked(struct pqi_ctrl_info *ctrl_info) +{ + return ctrl_info->block_device_reset; +} + +static inline bool pqi_ctrl_blocked(struct pqi_ctrl_info *ctrl_info) +{ + return ctrl_info->block_requests; +} + static inline void pqi_ctrl_block_requests(struct pqi_ctrl_info *ctrl_info) { ctrl_info->block_requests = true; @@@ -351,16 -331,6 +351,16 @@@ static inline bool pqi_device_in_remove return device->in_remove && !ctrl_info->in_shutdown; }

+static inline void pqi_ctrl_shutdown_start(struct pqi_ctrl_info *ctrl_info) +{ + ctrl_info->in_shutdown = true; +} + +static inline bool pqi_ctrl_in_shutdown(struct pqi_ctrl_info *ctrl_info) +{ + return ctrl_info->in_shutdown; +} + static inline void pqi_schedule_rescan_worker_with_delay( struct pqi_ctrl_info *ctrl_info, unsigned long delay) { @@@ -390,11 -360,6 +390,11 @@@ static inline void pqi_cancel_rescan_wo cancel_delayed_work_sync(&ctrl_info->rescan_work); }

+static inline void pqi_cancel_event_worker(struct pqi_ctrl_info *ctrl_info) +{ + cancel_work_sync(&ctrl_info->event_work); +} + static inline u32 pqi_read_heartbeat_counter(struct pqi_ctrl_info *ctrl_info) { if (!ctrl_info->heartbeat_counter) @@@ -412,7 -377,7 +412,7 @@@ static inline u8 pqi_read_soft_reset_st }

static inline void pqi_clear_soft_reset_status(struct pqi_ctrl_info *ctrl_info, - u8 clear) + u8 clear) { u8 status;

@@@ -497,9 -462,9 +497,9 @@@ static int pqi_build_raid_path_request( request->data_direction = SOP_READ_FLAG; cdb[0] = cmd; if (cmd == CISS_REPORT_PHYS) - cdb[1] = CISS_REPORT_PHYS_EXTENDED; + cdb[1] = CISS_REPORT_PHYS_FLAG_OTHER; else - cdb[1] = CISS_REPORT_LOG_EXTENDED; + cdb[1] = CISS_REPORT_LOG_FLAG_UNIQUE_LUN_ID; put_unaligned_be32(cdb_length, &cdb[6]); break; case CISS_GET_RAID_MAP: @@@ -602,12 -567,13 +602,12 @@@ static void pqi_free_io_request(struct }

static int pqi_send_scsi_raid_request(struct pqi_ctrl_info *ctrl_info, u8 cmd, - u8 *scsi3addr, void *buffer, size_t buffer_length, u16 vpd_page, - struct pqi_raid_error_info *error_info, - unsigned long timeout_msecs) + u8 *scsi3addr, void *buffer, size_t buffer_length, u16 vpd_page, + struct pqi_raid_error_info *error_info, unsigned long timeout_msecs) { int rc; - enum dma_data_direction dir; struct pqi_raid_path_request request; + enum dma_data_direction dir;

rc = pqi_build_raid_path_request(ctrl_info, &request, cmd, scsi3addr, buffer, @@@ -615,44 -581,44 +615,44 @@@ if (rc) return rc;

- rc = pqi_submit_raid_request_synchronous(ctrl_info, &request.header, - 0, error_info, timeout_msecs); + rc = pqi_submit_raid_request_synchronous(ctrl_info, &request.header, 0, + error_info, timeout_msecs);

pqi_pci_unmap(ctrl_info->pci_dev, request.sg_descriptors, 1, dir); + return rc; }

-/* Helper functions for pqi_send_scsi_raid_request */ +/* helper functions for pqi_send_scsi_raid_request */

static inline int pqi_send_ctrl_raid_request(struct pqi_ctrl_info *ctrl_info, - u8 cmd, void *buffer, size_t buffer_length) + u8 cmd, void *buffer, size_t buffer_length) { return pqi_send_scsi_raid_request(ctrl_info, cmd, RAID_CTLR_LUNID, - buffer, buffer_length, 0, NULL, NO_TIMEOUT); + buffer, buffer_length, 0, NULL, NO_TIMEOUT); }

static inline int pqi_send_ctrl_raid_with_error(struct pqi_ctrl_info *ctrl_info, - u8 cmd, void *buffer, size_t buffer_length, - struct pqi_raid_error_info *error_info) + u8 cmd, void *buffer, size_t buffer_length, + struct pqi_raid_error_info *error_info) { return pqi_send_scsi_raid_request(ctrl_info, cmd, RAID_CTLR_LUNID, - buffer, buffer_length, 0, error_info, NO_TIMEOUT); + buffer, buffer_length, 0, error_info, NO_TIMEOUT); }

- static inline int pqi_identify_controller(struct pqi_ctrl_info *ctrl_info, - struct bmic_identify_controller *buffer) + struct bmic_identify_controller *buffer) { return pqi_send_ctrl_raid_request(ctrl_info, BMIC_IDENTIFY_CONTROLLER, - buffer, sizeof(*buffer)); + buffer, sizeof(*buffer)); }

static inline int pqi_sense_subsystem_info(struct pqi_ctrl_info *ctrl_info, - struct bmic_sense_subsystem_info *sense_info) + struct bmic_sense_subsystem_info *sense_info) { return pqi_send_ctrl_raid_request(ctrl_info, - BMIC_SENSE_SUBSYSTEM_INFORMATION, - sense_info, sizeof(*sense_info)); + BMIC_SENSE_SUBSYSTEM_INFORMATION, sense_info, + sizeof(*sense_info)); }

static inline int pqi_scsi_inquiry(struct pqi_ctrl_info *ctrl_info, @@@ -662,9 -628,83 +662,9 @@@ buffer, buffer_length, vpd_page, NULL, NO_TIMEOUT); }

-static bool pqi_vpd_page_supported(struct pqi_ctrl_info *ctrl_info, - u8 *scsi3addr, u16 vpd_page) -{ - int rc; - int i; - int pages; - unsigned char *buf, bufsize; - - buf = kzalloc(256, GFP_KERNEL); - if (!buf) - return false; - - /* Get the size of the page list first */ - rc = pqi_scsi_inquiry(ctrl_info, scsi3addr, - VPD_PAGE | SCSI_VPD_SUPPORTED_PAGES, - buf, SCSI_VPD_HEADER_SZ); - if (rc != 0) - goto exit_unsupported; - - pages = buf[3]; - if ((pages + SCSI_VPD_HEADER_SZ) <= 255) - bufsize = pages + SCSI_VPD_HEADER_SZ; - else - bufsize = 255; - - /* Get the whole VPD page list */ - rc = pqi_scsi_inquiry(ctrl_info, scsi3addr, - VPD_PAGE | SCSI_VPD_SUPPORTED_PAGES, - buf, bufsize); - if (rc != 0) - goto exit_unsupported; - - pages = buf[3]; - for (i = 1; i <= pages; i++) - if (buf[3 + i] == vpd_page) - goto exit_supported; - -exit_unsupported: - kfree(buf); - return false; - -exit_supported: - kfree(buf); - return true; -} - -static int pqi_get_device_id(struct pqi_ctrl_info *ctrl_info, - u8 *scsi3addr, u8 *device_id, int buflen) -{ - int rc; - unsigned char *buf; - - if (!pqi_vpd_page_supported(ctrl_info, scsi3addr, SCSI_VPD_DEVICE_ID)) - return 1; /* function not supported */ - - buf = kzalloc(64, GFP_KERNEL); - if (!buf) - return -ENOMEM; - - rc = pqi_scsi_inquiry(ctrl_info, scsi3addr, - VPD_PAGE | SCSI_VPD_DEVICE_ID, - buf, 64); - if (rc == 0) { - if (buflen > 16) - buflen = 16; - memcpy(device_id, &buf[SCSI_VPD_DEVICE_ID_IDX], buflen); - } - - kfree(buf); - - return rc; -} - static int pqi_identify_physical_device(struct pqi_ctrl_info *ctrl_info, struct pqi_scsi_dev *device, - struct bmic_identify_physical_device *buffer, - size_t buffer_length) + struct bmic_identify_physical_device *buffer, size_t buffer_length) { int rc; enum dma_data_direction dir; @@@ -685,7 -725,6 +685,7 @@@ 0, NULL, NO_TIMEOUT);

pqi_pci_unmap(ctrl_info->pci_dev, request.sg_descriptors, 1, dir); + return rc; }

@@@ -724,7 -763,7 +724,7 @@@ int pqi_csmi_smp_passthru(struct pqi_ct buffer, buffer_length, error_info); }

-#define PQI_FETCH_PTRAID_DATA (1UL<<31) +#define PQI_FETCH_PTRAID_DATA (1 << 31)

static int pqi_set_diag_rescan(struct pqi_ctrl_info *ctrl_info) { @@@ -736,15 -775,14 +736,15 @@@ return -ENOMEM;

rc = pqi_send_ctrl_raid_request(ctrl_info, BMIC_SENSE_DIAG_OPTIONS, - diag, sizeof(*diag)); + diag, sizeof(*diag)); if (rc) goto out;

diag->options |= cpu_to_le32(PQI_FETCH_PTRAID_DATA);

- rc = pqi_send_ctrl_raid_request(ctrl_info, BMIC_SET_DIAG_OPTIONS, - diag, sizeof(*diag)); + rc = pqi_send_ctrl_raid_request(ctrl_info, BMIC_SET_DIAG_OPTIONS, diag, + sizeof(*diag)); + out: kfree(diag);

@@@ -755,7 -793,7 +755,7 @@@ static inline int pqi_write_host_wellne void *buffer, size_t buffer_length) { return pqi_send_ctrl_raid_request(ctrl_info, BMIC_WRITE_HOST_WELLNESS, - buffer, buffer_length); + buffer, buffer_length); }

#pragma pack(1) @@@ -908,7 -946,7 +908,7 @@@ static inline int pqi_report_luns(struc void *buffer, size_t buffer_length) { return pqi_send_ctrl_raid_request(ctrl_info, cmd, buffer, - buffer_length); + buffer_length); }

static int pqi_report_phys_logical_luns(struct pqi_ctrl_info *ctrl_info, u8 cmd, @@@ -1242,9 -1280,9 +1242,9 @@@ static void pqi_get_raid_bypass_status( if (rc) goto out;

-#define RAID_BYPASS_STATUS 4 -#define RAID_BYPASS_CONFIGURED 0x1 -#define RAID_BYPASS_ENABLED 0x2 +#define RAID_BYPASS_STATUS 4 +#define RAID_BYPASS_CONFIGURED 0x1 +#define RAID_BYPASS_ENABLED 0x2

bypass_status = buffer[RAID_BYPASS_STATUS]; device->raid_bypass_configured = @@@ -1347,6 -1385,14 +1347,6 @@@ static int pqi_get_device_info(struct p } }

- if (pqi_get_device_id(ctrl_info, device->scsi3addr, - device->unique_id, sizeof(device->unique_id)) < 0) - dev_warn(&ctrl_info->pci_dev->dev, - "Can't get device id for scsi %d:%d:%d:%d\n", - ctrl_info->scsi_host->host_no, - device->bus, device->target, - device->lun); - out: kfree(buffer);

@@@ -1367,7 -1413,6 +1367,7 @@@ static void pqi_get_physical_disk_info( device->queue_depth = PQI_PHYSICAL_DISK_DEFAULT_MAX_QUEUE_DEPTH; return; } + device->box_index = id_phys->box_index; device->phys_box_on_bus = id_phys->phys_box_on_bus; device->phy_connected_dev_type = id_phys->phy_connected_dev_type[0]; @@@ -1783,7 -1828,7 +1783,7 @@@ static void pqi_update_device_list(stru device = new_device_list[i];

find_result = pqi_scsi_find_entry(ctrl_info, device, - &matching_device); + &matching_device);

switch (find_result) { case DEVICE_SAME: @@@ -2012,8 -2057,9 +2012,8 @@@ static int pqi_update_scsi_devices(stru rc = -ENOMEM; goto out; } - if (pqi_hide_vsep) { - int i;

+ if (pqi_hide_vsep) { for (i = num_physicals - 1; i >= 0; i--) { phys_lun_ext_entry = &physdev_list->lun_entries[i]; @@@ -2086,7 -2132,7 +2086,7 @@@ device->is_physical_device = is_physical_device; if (is_physical_device) { if (phys_lun_ext_entry->device_type == - SA_EXPANDER_SMP_DEVICE) + SA_DEVICE_TYPE_EXPANDER_SMP) device->is_expander_smp_device = true; } else { device->is_external_raid_device = @@@ -2123,13 -2169,16 +2123,13 @@@ if (device->is_physical_device) { device->wwid = phys_lun_ext_entry->wwid; if ((phys_lun_ext_entry->device_flags & - REPORT_PHYS_LUN_DEV_FLAG_AIO_ENABLED) && + CISS_REPORT_PHYS_DEV_FLAG_AIO_ENABLED) && phys_lun_ext_entry->aio_handle) { device->aio_enabled = true; - device->aio_handle = - phys_lun_ext_entry->aio_handle; + device->aio_handle = + phys_lun_ext_entry->aio_handle; } - - pqi_get_physical_disk_info(ctrl_info, - device, id_phys); - + pqi_get_physical_disk_info(ctrl_info, device, id_phys); } else { memcpy(device->volume_id, log_lun_ext_entry->volume_id, sizeof(device->volume_id)); @@@ -3109,7 -3158,7 +3109,7 @@@ static enum pqi_soft_reset_status pqi_p }

static void pqi_process_soft_reset(struct pqi_ctrl_info *ctrl_info, - enum pqi_soft_reset_status reset_status) + enum pqi_soft_reset_status reset_status) { int rc;

@@@ -3153,8 -3202,8 +3153,8 @@@ static void pqi_ofa_process_event(struc

if (event_id == PQI_EVENT_OFA_QUIESCE) { dev_info(&ctrl_info->pci_dev->dev, - "Received Online Firmware Activation quiesce event for controller %u\n", - ctrl_info->ctrl_id); + "Received Online Firmware Activation quiesce event for controller %u\n", + ctrl_info->ctrl_id); pqi_ofa_ctrl_quiesce(ctrl_info); pqi_acknowledge_event(ctrl_info, event); if (ctrl_info->soft_reset_handshake_supported) { @@@ -3174,8 -3223,8 +3174,8 @@@ pqi_ofa_free_host_buffer(ctrl_info); pqi_acknowledge_event(ctrl_info, event); dev_info(&ctrl_info->pci_dev->dev, - "Online Firmware Activation(%u) cancel reason : %u\n", - ctrl_info->ctrl_id, event->ofa_cancel_reason); + "Online Firmware Activation(%u) cancel reason : %u\n", + ctrl_info->ctrl_id, event->ofa_cancel_reason); }

mutex_unlock(&ctrl_info->ofa_mutex); @@@ -3354,7 -3403,7 +3354,7 @@@ static unsigned int pqi_process_event_i #define PQI_LEGACY_INTX_MASK 0x1

static inline void pqi_configure_legacy_intx(struct pqi_ctrl_info *ctrl_info, - bool enable_intx) + bool enable_intx) { u32 intx_mask; struct pqi_device_registers __iomem *pqi_registers; @@@ -3792,7 -3841,7 +3792,7 @@@ static int pqi_create_admin_queues(stru &pqi_registers->admin_oq_pi_addr);

reg = PQI_ADMIN_IQ_NUM_ELEMENTS | - (PQI_ADMIN_OQ_NUM_ELEMENTS) << 8 | + (PQI_ADMIN_OQ_NUM_ELEMENTS << 8) | (admin_queues->int_msg_num << 16); writel(reg, &pqi_registers->admin_iq_num_elements); writel(PQI_CREATE_ADMIN_QUEUE_PAIR, @@@ -3999,8 -4048,8 +3999,8 @@@ static void pqi_raid_synchronous_comple complete(waiting); }

-static int pqi_process_raid_io_error_synchronous(struct pqi_raid_error_info - *error_info) +static int pqi_process_raid_io_error_synchronous( + struct pqi_raid_error_info *error_info) { int rc = -EIO;

@@@ -4073,8 -4122,6 +4073,8 @@@ static int pqi_submit_raid_request_sync goto out; }

+ atomic_inc(&ctrl_info->sync_cmds_outstanding); + io_request = pqi_alloc_io_request(ctrl_info);

put_unaligned_le16(io_request->index, @@@ -4121,7 -4168,6 +4121,7 @@@

pqi_free_io_request(io_request);

+ atomic_dec(&ctrl_info->sync_cmds_outstanding); out: up(&ctrl_info->sync_request_sem);

@@@ -4619,11 -4665,11 +4619,11 @@@ static void pqi_free_all_io_requests(st

static inline int pqi_alloc_error_buffer(struct pqi_ctrl_info *ctrl_info) { - ctrl_info->error_buffer = dma_alloc_coherent(&ctrl_info->pci_dev->dev, - ctrl_info->error_buffer_length, - &ctrl_info->error_buffer_dma_handle, - GFP_KERNEL);

+ ctrl_info->error_buffer = dma_alloc_coherent(&ctrl_info->pci_dev->dev, + ctrl_info->error_buffer_length, + &ctrl_info->error_buffer_dma_handle, + GFP_KERNEL); if (!ctrl_info->error_buffer) return -ENOMEM;

@@@ -5356,7 -5402,7 +5356,7 @@@ static int pqi_scsi_queue_command(struc

pqi_ctrl_busy(ctrl_info); if (pqi_ctrl_blocked(ctrl_info) || pqi_device_in_reset(device) || - pqi_ctrl_in_ofa(ctrl_info)) { + pqi_ctrl_in_ofa(ctrl_info) || pqi_ctrl_in_shutdown(ctrl_info)) { rc = SCSI_MLQUEUE_HOST_BUSY; goto out; } @@@ -5373,7 -5419,7 +5373,7 @@@ if (pqi_is_logical_device(device)) { raid_bypassed = false; if (device->raid_bypass_enabled && - !blk_rq_is_passthrough(scmd->request)) { + !blk_rq_is_passthrough(scmd->request)) { rc = pqi_raid_bypass_submit_scsi_cmd(ctrl_info, device, scmd, queue_group); if (rc == 0 || rc == SCSI_MLQUEUE_HOST_BUSY) @@@ -5604,18 -5650,6 +5604,18 @@@ static int pqi_ctrl_wait_for_pending_io return 0; }

+static int pqi_ctrl_wait_for_pending_sync_cmds(struct pqi_ctrl_info *ctrl_info) +{ + while (atomic_read(&ctrl_info->sync_cmds_outstanding)) { + pqi_check_ctrl_health(ctrl_info); + if (pqi_ctrl_offline(ctrl_info)) + return -ENXIO; + usleep_range(1000, 2000); + } + + return 0; +} + static void pqi_lun_reset_complete(struct pqi_io_request *io_request, void *context) { @@@ -5624,8 -5658,7 +5624,8 @@@ complete(waiting); }

-#define PQI_LUN_RESET_TIMEOUT_SECS 10 +#define PQI_LUN_RESET_TIMEOUT_SECS 30 +#define PQI_LUN_RESET_POLL_COMPLETION_SECS 10

static int pqi_wait_for_lun_reset_completion(struct pqi_ctrl_info *ctrl_info, struct pqi_scsi_dev *device, struct completion *wait) @@@ -5634,7 -5667,7 +5634,7 @@@

while (1) { if (wait_for_completion_io_timeout(wait, - PQI_LUN_RESET_TIMEOUT_SECS * PQI_HZ)) { + PQI_LUN_RESET_POLL_COMPLETION_SECS * PQI_HZ)) { rc = 0; break; } @@@ -5671,9 -5704,6 +5671,9 @@@ static int pqi_lun_reset(struct pqi_ctr memcpy(request->lun_number, device->scsi3addr, sizeof(request->lun_number)); request->task_management_function = SOP_TASK_MANAGEMENT_LUN_RESET; + if (ctrl_info->tmf_iu_timeout_supported) + put_unaligned_le16(PQI_LUN_RESET_TIMEOUT_SECS, + &request->timeout);

pqi_start_io(ctrl_info, &ctrl_info->queue_groups[PQI_DEFAULT_QUEUE_GROUP], RAID_PATH, @@@ -5703,7 -5733,7 +5703,7 @@@ static int _pqi_device_reset(struct pqi

for (retries = 0;;) { rc = pqi_lun_reset(ctrl_info, device); - if (rc != -EAGAIN || ++retries > PQI_LUN_RESET_RETRIES) + if (rc == 0 || ++retries > PQI_LUN_RESET_RETRIES) break; msleep(PQI_LUN_RESET_RETRY_INTERVAL_MSECS); } @@@ -5757,17 -5787,17 +5757,17 @@@ static int pqi_eh_device_reset_handler( shost->host_no, device->bus, device->target, device->lun);

pqi_check_ctrl_health(ctrl_info); - if (pqi_ctrl_offline(ctrl_info)) { - dev_err(&ctrl_info->pci_dev->dev, - "controller %u offlined - cannot send device reset\n", - ctrl_info->ctrl_id); + if (pqi_ctrl_offline(ctrl_info) || + pqi_device_reset_blocked(ctrl_info)) { rc = FAILED; goto out; }

pqi_wait_until_ofa_finished(ctrl_info);

+ atomic_inc(&ctrl_info->sync_cmds_outstanding); rc = pqi_device_reset(ctrl_info, device); + atomic_dec(&ctrl_info->sync_cmds_outstanding);

out: dev_err(&ctrl_info->pci_dev->dev, @@@ -6036,9 -6066,6 +6036,9 @@@ static int pqi_passthru_ioctl(struct pq

put_unaligned_le16(iu_length, &request.header.iu_length);

+ if (ctrl_info->raid_iu_timeout_supported) + put_unaligned_le32(iocommand.Request.Timeout, &request.timeout); + rc = pqi_submit_raid_request_synchronous(ctrl_info, &request.header, PQI_SYNC_FLAGS_INTERRUPTABLE, &pqi_error_info, NO_TIMEOUT);

@@@ -6092,7 -6119,7 +6092,7 @@@ static int pqi_ioctl(struct scsi_devic

ctrl_info = shost_to_hba(sdev->host);

- if (pqi_ctrl_in_ofa(ctrl_info)) + if (pqi_ctrl_in_ofa(ctrl_info) || pqi_ctrl_in_shutdown(ctrl_info)) return -EBUSY;

switch (cmd) { @@@ -6133,8 -6160,14 +6133,8 @@@ static ssize_t pqi_firmware_version_sho static ssize_t pqi_driver_version_show(struct device *dev, struct device_attribute *attr, char *buffer) { - struct Scsi_Host *shost; - struct pqi_ctrl_info *ctrl_info; - - shost = class_to_shost(dev); - ctrl_info = shost_to_hba(shost); - - return snprintf(buffer, PAGE_SIZE, - "%s\n", DRIVER_VERSION BUILD_TIMESTAMP); + return snprintf(buffer, PAGE_SIZE, "%s\n", + DRIVER_VERSION BUILD_TIMESTAMP); }

static ssize_t pqi_serial_number_show(struct device *dev, @@@ -6250,7 -6283,7 +6250,7 @@@ static ssize_t pqi_unique_id_show(struc struct scsi_device *sdev; struct pqi_scsi_dev *device; unsigned long flags; - unsigned char uid[16]; + u8 unique_id[16];

sdev = to_scsi_device(dev); ctrl_info = shost_to_hba(sdev->host); @@@ -6263,22 -6296,16 +6263,22 @@@ flags); return -ENODEV; } - memcpy(uid, device->unique_id, sizeof(uid)); + + if (device->is_physical_device) { + memset(unique_id, 0, 8); + memcpy(unique_id + 8, &device->wwid, sizeof(device->wwid)); + } else { + memcpy(unique_id, device->volume_id, sizeof(device->volume_id)); + }

spin_unlock_irqrestore(&ctrl_info->scsi_device_list_lock, flags);

return snprintf(buffer, PAGE_SIZE, "%02X%02X%02X%02X%02X%02X%02X%02X%02X%02X%02X%02X%02X%02X%02X%02X\n", - uid[0], uid[1], uid[2], uid[3], - uid[4], uid[5], uid[6], uid[7], - uid[8], uid[9], uid[10], uid[11], - uid[12], uid[13], uid[14], uid[15]); + unique_id[0], unique_id[1], unique_id[2], unique_id[3], + unique_id[4], unique_id[5], unique_id[6], unique_id[7], + unique_id[8], unique_id[9], unique_id[10], unique_id[11], + unique_id[12], unique_id[13], unique_id[14], unique_id[15]); }

static ssize_t pqi_lunid_show(struct device *dev, @@@ -6301,7 -6328,6 +6301,7 @@@ flags); return -ENODEV; } + memcpy(lunid, device->scsi3addr, sizeof(lunid));

spin_unlock_irqrestore(&ctrl_info->scsi_device_list_lock, flags); @@@ -6309,8 -6335,7 +6309,8 @@@ return snprintf(buffer, PAGE_SIZE, "0x%8phN\n", lunid); }

-#define MAX_PATHS 8 +#define MAX_PATHS 8 + static ssize_t pqi_path_info_show(struct device *dev, struct device_attribute *attr, char *buf) { @@@ -6322,9 -6347,9 +6322,9 @@@ int output_len = 0; u8 box; u8 bay; - u8 path_map_index = 0; + u8 path_map_index; char *active; - unsigned char phys_connector[2]; + u8 phys_connector[2];

sdev = to_scsi_device(dev); ctrl_info = shost_to_hba(sdev->host); @@@ -6340,7 -6365,7 +6340,7 @@@

bay = device->bay; for (i = 0; i < MAX_PATHS; i++) { - path_map_index = 1<<i; + path_map_index = 1 << i; if (i == device->active_path_index) active = "Active"; else if (device->path_map & path_map_index) @@@ -6391,10 -6416,10 +6391,10 @@@ end_buffer }

spin_unlock_irqrestore(&ctrl_info->scsi_device_list_lock, flags); + return output_len; }

- static ssize_t pqi_sas_address_show(struct device *dev, struct device_attribute *attr, char *buffer) { @@@ -6415,7 -6440,6 +6415,7 @@@ flags); return -ENODEV; } + sas_address = device->sas_address;

spin_unlock_irqrestore(&ctrl_info->scsi_device_list_lock, flags); @@@ -6820,27 -6844,6 +6820,27 @@@ static void pqi_firmware_feature_status firmware_feature->feature_name); }

+static void pqi_ctrl_update_feature_flags(struct pqi_ctrl_info *ctrl_info, + struct pqi_firmware_feature *firmware_feature) +{ + switch (firmware_feature->feature_bit) { + case PQI_FIRMWARE_FEATURE_SOFT_RESET_HANDSHAKE: + ctrl_info->soft_reset_handshake_supported = + firmware_feature->enabled; + break; + case PQI_FIRMWARE_FEATURE_RAID_IU_TIMEOUT: + ctrl_info->raid_iu_timeout_supported = + firmware_feature->enabled; + break; + case PQI_FIRMWARE_FEATURE_TMF_IU_TIMEOUT: + ctrl_info->tmf_iu_timeout_supported = + firmware_feature->enabled; + break; + } + + pqi_firmware_feature_status(ctrl_info, firmware_feature); +} + static inline void pqi_firmware_feature_update(struct pqi_ctrl_info *ctrl_info, struct pqi_firmware_feature *firmware_feature) { @@@ -6864,17 -6867,7 +6864,17 @@@ static struct pqi_firmware_feature pqi_ { .feature_name = "New Soft Reset Handshake", .feature_bit = PQI_FIRMWARE_FEATURE_SOFT_RESET_HANDSHAKE, - .feature_status = pqi_firmware_feature_status, + .feature_status = pqi_ctrl_update_feature_flags, + }, + { + .feature_name = "RAID IU Timeout", + .feature_bit = PQI_FIRMWARE_FEATURE_RAID_IU_TIMEOUT, + .feature_status = pqi_ctrl_update_feature_flags, + }, + { + .feature_name = "TMF IU Timeout", + .feature_bit = PQI_FIRMWARE_FEATURE_TMF_IU_TIMEOUT, + .feature_status = pqi_ctrl_update_feature_flags, }, };

@@@ -6928,6 -6921,7 +6928,6 @@@ static void pqi_process_firmware_featur return; }

- ctrl_info->soft_reset_handshake_supported = false; for (i = 0; i < ARRAY_SIZE(pqi_firmware_features); i++) { if (!pqi_firmware_features[i].supported) continue; @@@ -6935,6 -6929,10 +6935,6 @@@ firmware_features_iomem_addr, pqi_firmware_features[i].feature_bit)) { pqi_firmware_features[i].enabled = true; - if (pqi_firmware_features[i].feature_bit == - PQI_FIRMWARE_FEATURE_SOFT_RESET_HANDSHAKE) - ctrl_info->soft_reset_handshake_supported = - true; } pqi_firmware_feature_update(ctrl_info, &pqi_firmware_features[i]); @@@ -7076,20 -7074,13 +7076,20 @@@ static int pqi_force_sis_mode(struct pq return pqi_revert_to_sis_mode(ctrl_info); }

+#define PQI_POST_RESET_DELAY_B4_MSGU_READY 5000 + static int pqi_ctrl_init(struct pqi_ctrl_info *ctrl_info) { int rc;

- rc = pqi_force_sis_mode(ctrl_info); - if (rc) - return rc; + if (reset_devices) { + sis_soft_reset(ctrl_info); + msleep(PQI_POST_RESET_DELAY_B4_MSGU_READY); + } else { + rc = pqi_force_sis_mode(ctrl_info); + if (rc) + return rc; + }

/* * Wait until the controller is ready to start accepting SIS @@@ -7395,7 -7386,7 +7395,7 @@@ static int pqi_ctrl_init_resume(struct rc = pqi_get_ctrl_product_details(ctrl_info); if (rc) { dev_err(&ctrl_info->pci_dev->dev, - "error obtaining product detail\n"); + "error obtaining product details\n"); return rc; }

@@@ -7523,7 -7514,6 +7523,7 @@@ static struct pqi_ctrl_info *pqi_alloc_

INIT_WORK(&ctrl_info->event_work, pqi_event_worker); atomic_set(&ctrl_info->num_interrupts, 0); + atomic_set(&ctrl_info->sync_cmds_outstanding, 0);

INIT_DELAYED_WORK(&ctrl_info->rescan_work, pqi_rescan_worker); INIT_DELAYED_WORK(&ctrl_info->update_time_work, pqi_update_time_worker); @@@ -7731,8 -7721,6 +7731,8 @@@ static void pqi_ofa_setup_host_buffer(s dev_err(dev, "Failed to allocate host buffer of size = %u", bytes_requested); } + + return; }

static void pqi_ofa_free_host_buffer(struct pqi_ctrl_info *ctrl_info) @@@ -7799,6 -7787,8 +7799,6 @@@ static int pqi_ofa_host_memory_update(s 0, NULL, NO_TIMEOUT); }

-#define PQI_POST_RESET_DELAY_B4_MSGU_READY 5000 - static int pqi_ofa_ctrl_restart(struct pqi_ctrl_info *ctrl_info) { msleep(PQI_POST_RESET_DELAY_B4_MSGU_READY); @@@ -7966,73 -7956,28 +7966,73 @@@ static void pqi_pci_remove(struct pci_d pqi_remove_ctrl(ctrl_info); }

+static void pqi_crash_if_pending_command(struct pqi_ctrl_info *ctrl_info) +{ + unsigned int i; + struct pqi_io_request *io_request; + struct scsi_cmnd *scmd; + + for (i = 0; i < ctrl_info->max_io_slots; i++) { + io_request = &ctrl_info->io_request_pool[i]; + if (atomic_read(&io_request->refcount) == 0) + continue; + scmd = io_request->scmd; + WARN_ON(scmd != NULL); /* IO command from SML */ + WARN_ON(scmd == NULL); /* Non-IO cmd or driver initiated*/ + } +} + static void pqi_shutdown(struct pci_dev *pci_dev) { int rc; struct pqi_ctrl_info *ctrl_info;

ctrl_info = pci_get_drvdata(pci_dev); - if (!ctrl_info) - goto error; + if (!ctrl_info) { + dev_err(&pci_dev->dev, + "cache could not be flushed\n"); + return; + } + + pqi_disable_events(ctrl_info); + pqi_wait_until_ofa_finished(ctrl_info); + pqi_cancel_update_time_worker(ctrl_info); + pqi_cancel_rescan_worker(ctrl_info); + pqi_cancel_event_worker(ctrl_info); + + pqi_ctrl_shutdown_start(ctrl_info); + pqi_ctrl_wait_until_quiesced(ctrl_info); + + rc = pqi_ctrl_wait_for_pending_io(ctrl_info, NO_TIMEOUT); + if (rc) { + dev_err(&pci_dev->dev, + "wait for pending I/O failed\n"); + return; + } + + pqi_ctrl_block_device_reset(ctrl_info); + pqi_wait_until_lun_reset_finished(ctrl_info);

/* * Write all data in the controller's battery-backed cache to * storage. */ rc = pqi_flush_cache(ctrl_info, SHUTDOWN); - pqi_free_interrupts(ctrl_info); - pqi_reset(ctrl_info); - if (rc == 0) + if (rc) + dev_err(&pci_dev->dev, + "unable to flush controller cache\n"); + + pqi_ctrl_block_requests(ctrl_info); + + rc = pqi_ctrl_wait_for_pending_sync_cmds(ctrl_info); + if (rc) { + dev_err(&pci_dev->dev, + "wait for pending sync cmds failed\n"); return; + }

-error: - dev_warn(&pci_dev->dev, - "unable to flush controller cache\n"); + pqi_crash_if_pending_command(ctrl_info); + pqi_reset(ctrl_info); }

static void pqi_process_lockup_action_param(void) @@@ -8689,11 -8634,11 +8689,11 @@@ static void __attribute__((unused)) ver BUILD_BUG_ON(offsetof(struct pqi_general_admin_request, data.delete_operational_queue.queue_id) != 12); BUILD_BUG_ON(sizeof(struct pqi_general_admin_request) != 64); - BUILD_BUG_ON(FIELD_SIZEOF(struct pqi_general_admin_request, + BUILD_BUG_ON(sizeof_member(struct pqi_general_admin_request, data.create_operational_iq) != 64 - 11); - BUILD_BUG_ON(FIELD_SIZEOF(struct pqi_general_admin_request, + BUILD_BUG_ON(sizeof_member(struct pqi_general_admin_request, data.create_operational_oq) != 64 - 11); - BUILD_BUG_ON(FIELD_SIZEOF(struct pqi_general_admin_request, + BUILD_BUG_ON(sizeof_member(struct pqi_general_admin_request, data.delete_operational_queue) != 64 - 11);

BUILD_BUG_ON(offsetof(struct pqi_general_admin_response, @@@ -8740,8 -8685,6 +8740,8 @@@ error_index) != 27); BUILD_BUG_ON(offsetof(struct pqi_raid_path_request, cdb) != 32); + BUILD_BUG_ON(offsetof(struct pqi_raid_path_request, + timeout) != 60); BUILD_BUG_ON(offsetof(struct pqi_raid_path_request, sg_descriptors) != 64); BUILD_BUG_ON(sizeof(struct pqi_raid_path_request) != @@@ -8897,8 -8840,6 +8897,8 @@@ BUILD_BUG_ON(offsetof(struct pqi_task_management_request, nexus_id) != 10); BUILD_BUG_ON(offsetof(struct pqi_task_management_request, + timeout) != 14); + BUILD_BUG_ON(offsetof(struct pqi_task_management_request, lun_number) != 16); BUILD_BUG_ON(offsetof(struct pqi_task_management_request, protocol_specific) != 24); diff --combined drivers/usb/gadget/function/f_fs.c index ce1d0235969c,2539ea40e94c..b0f3aa67a040 --- a/drivers/usb/gadget/function/f_fs.c +++ b/drivers/usb/gadget/function/f_fs.c @@@ -1352,6 -1352,14 +1352,6 @@@ static long ffs_epfile_ioctl(struct fil return ret; }

-#ifdef CONFIG_COMPAT -static long ffs_epfile_compat_ioctl(struct file *file, unsigned code, - unsigned long value) -{ - return ffs_epfile_ioctl(file, code, value); -} -#endif - static const struct file_operations ffs_epfile_operations = { .llseek = no_llseek,

@@@ -1360,7 -1368,9 +1360,7 @@@ .read_iter = ffs_epfile_read_iter, .release = ffs_epfile_release, .unlocked_ioctl = ffs_epfile_ioctl, -#ifdef CONFIG_COMPAT - .compat_ioctl = ffs_epfile_compat_ioctl, -#endif + .compat_ioctl = compat_ptr_ioctl, };

@@@ -3509,7 -3519,7 +3509,7 @@@ static void ffs_free_inst(struct usb_fu

static int ffs_set_inst_name(struct usb_function_instance *fi, const char *name) { - if (strlen(name) >= FIELD_SIZEOF(struct ffs_dev, name)) + if (strlen(name) >= sizeof_member(struct ffs_dev, name)) return -ENAMETOOLONG; return ffs_name_dev(to_f_fs_opts(fi)->dev, name); } diff --combined fs/fuse/virtio_fs.c index a5c86048b96e,13f67ae37257..b77acea065d0 --- a/fs/fuse/virtio_fs.c +++ b/fs/fuse/virtio_fs.c @@@ -30,7 -30,6 +30,7 @@@ struct virtio_fs_vq struct virtqueue *vq; /* protected by ->lock */ struct work_struct done_work; struct list_head queued_reqs; + struct list_head end_reqs; /* End these requests */ struct delayed_work dispatch_work; struct fuse_dev *fud; bool connected; @@@ -55,9 -54,6 +55,9 @@@ struct virtio_fs_forget struct list_head list; };

+static int virtio_fs_enqueue_req(struct virtio_fs_vq *fsvq, + struct fuse_req *req, bool in_flight); + static inline struct virtio_fs_vq *vq_to_fsvq(struct virtqueue *vq) { struct virtio_fs *fs = vq->vdev->priv; @@@ -70,19 -66,6 +70,19 @@@ static inline struct fuse_pqueue *vq_to return &vq_to_fsvq(vq)->fud->pq; }

+/* Should be called with fsvq->lock held. */ +static inline void inc_in_flight_req(struct virtio_fs_vq *fsvq) +{ + fsvq->in_flight++; +} + +/* Should be called with fsvq->lock held. */ +static inline void dec_in_flight_req(struct virtio_fs_vq *fsvq) +{ + WARN_ON(fsvq->in_flight <= 0); + fsvq->in_flight--; +} + static void release_virtio_fs_obj(struct kref *ref) { struct virtio_fs *vfs = container_of(ref, struct virtio_fs, refcount); @@@ -126,6 -109,22 +126,6 @@@ static void virtio_fs_drain_queue(struc flush_delayed_work(&fsvq->dispatch_work); }

-static inline void drain_hiprio_queued_reqs(struct virtio_fs_vq *fsvq) -{ - struct virtio_fs_forget *forget; - - spin_lock(&fsvq->lock); - while (1) { - forget = list_first_entry_or_null(&fsvq->queued_reqs, - struct virtio_fs_forget, list); - if (!forget) - break; - list_del(&forget->list); - kfree(forget); - } - spin_unlock(&fsvq->lock); -} - static void virtio_fs_drain_all_queues(struct virtio_fs *fs) { struct virtio_fs_vq *fsvq; @@@ -133,6 -132,9 +133,6 @@@

for (i = 0; i < fs->nvqs; i++) { fsvq = &fs->vqs[i]; - if (i == VQ_HIPRIO) - drain_hiprio_queued_reqs(fsvq); - virtio_fs_drain_queue(fsvq); } } @@@ -213,7 -215,7 +213,7 @@@ static void virtio_fs_free_devs(struct /* Read filesystem name from virtio config into fs->tag (must kfree()). */ static int virtio_fs_read_tag(struct virtio_device *vdev, struct virtio_fs *fs) { - char tag_buf[sizeof_field(struct virtio_fs_config, tag)]; + char tag_buf[sizeof_member(struct virtio_fs_config, tag)]; char *end; size_t len;

@@@ -251,66 -253,14 +251,66 @@@ static void virtio_fs_hiprio_done_work(

while ((req = virtqueue_get_buf(vq, &len)) != NULL) { kfree(req); - fsvq->in_flight--; + dec_in_flight_req(fsvq); } } while (!virtqueue_enable_cb(vq) && likely(!virtqueue_is_broken(vq))); spin_unlock(&fsvq->lock); }

-static void virtio_fs_dummy_dispatch_work(struct work_struct *work) +static void virtio_fs_request_dispatch_work(struct work_struct *work) { + struct fuse_req *req; + struct virtio_fs_vq *fsvq = container_of(work, struct virtio_fs_vq, + dispatch_work.work); + struct fuse_conn *fc = fsvq->fud->fc; + int ret; + + pr_debug("virtio-fs: worker %s called.\n", __func__); + while (1) { + spin_lock(&fsvq->lock); + req = list_first_entry_or_null(&fsvq->end_reqs, struct fuse_req, + list); + if (!req) { + spin_unlock(&fsvq->lock); + break; + } + + list_del_init(&req->list); + spin_unlock(&fsvq->lock); + fuse_request_end(fc, req); + } + + /* Dispatch pending requests */ + while (1) { + spin_lock(&fsvq->lock); + req = list_first_entry_or_null(&fsvq->queued_reqs, + struct fuse_req, list); + if (!req) { + spin_unlock(&fsvq->lock); + return; + } + list_del_init(&req->list); + spin_unlock(&fsvq->lock); + + ret = virtio_fs_enqueue_req(fsvq, req, true); + if (ret < 0) { + if (ret == -ENOMEM || ret == -ENOSPC) { + spin_lock(&fsvq->lock); + list_add_tail(&req->list, &fsvq->queued_reqs); + schedule_delayed_work(&fsvq->dispatch_work, + msecs_to_jiffies(1)); + spin_unlock(&fsvq->lock); + return; + } + req->out.h.error = ret; + spin_lock(&fsvq->lock); + dec_in_flight_req(fsvq); + spin_unlock(&fsvq->lock); + pr_err("virtio-fs: virtio_fs_enqueue_req() failed %d\n", + ret); + fuse_request_end(fc, req); + } + } }

static void virtio_fs_hiprio_dispatch_work(struct work_struct *work) @@@ -336,7 -286,6 +336,7 @@@

list_del(&forget->list); if (!fsvq->connected) { + dec_in_flight_req(fsvq); spin_unlock(&fsvq->lock); kfree(forget); continue; @@@ -358,13 -307,13 +358,13 @@@ } else { pr_debug("virtio-fs: Could not queue FORGET: err=%d. Dropping it.\n", ret); + dec_in_flight_req(fsvq); kfree(forget); } spin_unlock(&fsvq->lock); return; }

- fsvq->in_flight++; notify = virtqueue_kick_prepare(vq); spin_unlock(&fsvq->lock);

@@@ -503,7 -452,7 +503,7 @@@ static void virtio_fs_requests_done_wor

fuse_request_end(fc, req); spin_lock(&fsvq->lock); - fsvq->in_flight--; + dec_in_flight_req(fsvq); spin_unlock(&fsvq->lock); } } @@@ -553,7 -502,6 +553,7 @@@ static int virtio_fs_setup_vqs(struct v names[VQ_HIPRIO] = fs->vqs[VQ_HIPRIO].name; INIT_WORK(&fs->vqs[VQ_HIPRIO].done_work, virtio_fs_hiprio_done_work); INIT_LIST_HEAD(&fs->vqs[VQ_HIPRIO].queued_reqs); + INIT_LIST_HEAD(&fs->vqs[VQ_HIPRIO].end_reqs); INIT_DELAYED_WORK(&fs->vqs[VQ_HIPRIO].dispatch_work, virtio_fs_hiprio_dispatch_work); spin_lock_init(&fs->vqs[VQ_HIPRIO].lock); @@@ -563,9 -511,8 +563,9 @@@ spin_lock_init(&fs->vqs[i].lock); INIT_WORK(&fs->vqs[i].done_work, virtio_fs_requests_done_work); INIT_DELAYED_WORK(&fs->vqs[i].dispatch_work, - virtio_fs_dummy_dispatch_work); + virtio_fs_request_dispatch_work); INIT_LIST_HEAD(&fs->vqs[i].queued_reqs); + INIT_LIST_HEAD(&fs->vqs[i].end_reqs); snprintf(fs->vqs[i].name, sizeof(fs->vqs[i].name), "requests.%u", i - VQ_REQUEST); callbacks[i] = virtio_fs_vq_done; @@@ -761,7 -708,6 +761,7 @@@ __releases(fiq->lock list_add_tail(&forget->list, &fsvq->queued_reqs); schedule_delayed_work(&fsvq->dispatch_work, msecs_to_jiffies(1)); + inc_in_flight_req(fsvq); } else { pr_debug("virtio-fs: Could not queue FORGET: err=%d. Dropping it.\n", ret); @@@ -771,7 -717,7 +771,7 @@@ goto out; }

- fsvq->in_flight++; + inc_in_flight_req(fsvq); notify = virtqueue_kick_prepare(vq);

spin_unlock(&fsvq->lock); @@@ -873,7 -819,7 +873,7 @@@ static unsigned int sg_init_fuse_args(s

/* Add a request to a virtqueue and kick the device */ static int virtio_fs_enqueue_req(struct virtio_fs_vq *fsvq, - struct fuse_req *req) + struct fuse_req *req, bool in_flight) { /* requests need at least 4 elements */ struct scatterlist *stack_sgs[6]; @@@ -889,7 -835,6 +889,7 @@@ unsigned int i; int ret; bool notify; + struct fuse_pqueue *fpq;

/* Does the sglist fit on the stack? */ total_sgs = sg_count_fuse_req(req); @@@ -944,17 -889,7 +944,17 @@@ goto out; }

- fsvq->in_flight++; + /* Request successfully sent. */ + fpq = &fsvq->fud->pq; + spin_lock(&fpq->lock); + list_add_tail(&req->list, fpq->processing); + spin_unlock(&fpq->lock); + set_bit(FR_SENT, &req->flags); + /* matches barrier in request_wait_answer() */ + smp_mb__after_atomic(); + + if (!in_flight) + inc_in_flight_req(fsvq); notify = virtqueue_kick_prepare(vq);

spin_unlock(&fsvq->lock); @@@ -980,8 -915,9 +980,8 @@@ __releases(fiq->lock { unsigned int queue_id = VQ_REQUEST; /* TODO multiqueue */ struct virtio_fs *fs; - struct fuse_conn *fc; struct fuse_req *req; - struct fuse_pqueue *fpq; + struct virtio_fs_vq *fsvq; int ret;

WARN_ON(list_empty(&fiq->pending)); @@@ -992,36 -928,44 +992,36 @@@ spin_unlock(&fiq->lock);

fs = fiq->priv; - fc = fs->vqs[queue_id].fud->fc;

pr_debug("%s: opcode %u unique %#llx nodeid %#llx in.len %u out.len %u\n", __func__, req->in.h.opcode, req->in.h.unique, req->in.h.nodeid, req->in.h.len, fuse_len_args(req->args->out_numargs, req->args->out_args));

- fpq = &fs->vqs[queue_id].fud->pq; - spin_lock(&fpq->lock); - if (!fpq->connected) { - spin_unlock(&fpq->lock); - req->out.h.error = -ENODEV; - pr_err("virtio-fs: %s disconnected\n", __func__); - fuse_request_end(fc, req); - return; - } - list_add_tail(&req->list, fpq->processing); - spin_unlock(&fpq->lock); - set_bit(FR_SENT, &req->flags); - /* matches barrier in request_wait_answer() */ - smp_mb__after_atomic(); - -retry: - ret = virtio_fs_enqueue_req(&fs->vqs[queue_id], req); + fsvq = &fs->vqs[queue_id]; + ret = virtio_fs_enqueue_req(fsvq, req, false); if (ret < 0) { if (ret == -ENOMEM || ret == -ENOSPC) { - /* Virtqueue full. Retry submission */ - /* TODO use completion instead of timeout */ - usleep_range(20, 30); - goto retry; + /* + * Virtqueue full. Retry submission from worker + * context as we might be holding fc->bg_lock. + */ + spin_lock(&fsvq->lock); + list_add_tail(&req->list, &fsvq->queued_reqs); + inc_in_flight_req(fsvq); + schedule_delayed_work(&fsvq->dispatch_work, + msecs_to_jiffies(1)); + spin_unlock(&fsvq->lock); + return; } req->out.h.error = ret; pr_err("virtio-fs: virtio_fs_enqueue_req() failed %d\n", ret); - spin_lock(&fpq->lock); - clear_bit(FR_SENT, &req->flags); - list_del_init(&req->list); - spin_unlock(&fpq->lock); - fuse_request_end(fc, req); + + /* Can't end request in submission context. Use a worker */ + spin_lock(&fsvq->lock); + list_add_tail(&req->list, &fsvq->end_reqs); + schedule_delayed_work(&fsvq->dispatch_work, 0); + spin_unlock(&fsvq->lock); return; } } @@@ -1048,7 -992,6 +1048,7 @@@ static int virtio_fs_fill_super(struct .destroy = true, .no_control = true, .no_force_umount = true, + .no_mount_options = true, };

mutex_lock(&virtio_fs_mutex); diff --combined include/linux/filter.h index 7a6f8f6f1da4,fa2d921d7a22..d17f8eab899c --- a/include/linux/filter.h +++ b/include/linux/filter.h @@@ -65,9 -65,6 +65,9 @@@ struct ctl_table_header /* unused opcode to mark special call to bpf_tail_call() helper */ #define BPF_TAIL_CALL 0xf0

+/* unused opcode to mark special load instruction. Same as BPF_ABS */ +#define BPF_PROBE_MEM 0x20 + /* unused opcode to mark call to interpreter with arguments */ #define BPF_CALL_ARGS 0xe0

@@@ -420,7 -417,7 +420,7 @@@ static inline bool insn_is_zext(const s

#define BPF_FIELD_SIZEOF(type, field) \ ({ \ - const int __size = bytes_to_bpf_size(FIELD_SIZEOF(type, field)); \ + const int __size = bytes_to_bpf_size(sizeof_member(type, field)); \ BUILD_BUG_ON(__size < 0); \ __size; \ }) @@@ -467,11 -464,10 +467,11 @@@ #define BPF_CALL_x(x, name, ...) \ static __always_inline \ u64 ____##name(__BPF_MAP(x, __BPF_DECL_ARGS, __BPF_V, __VA_ARGS__)); \ + typedef u64 (*btf_##name)(__BPF_MAP(x, __BPF_DECL_ARGS, __BPF_V, __VA_ARGS__)); \ u64 name(__BPF_REG(x, __BPF_DECL_REGS, __BPF_N, __VA_ARGS__)); \ u64 name(__BPF_REG(x, __BPF_DECL_REGS, __BPF_N, __VA_ARGS__)) \ { \ - return ____##name(__BPF_MAP(x,__BPF_CAST,__BPF_N,__VA_ARGS__));\ + return ((btf_##name)____##name)(__BPF_MAP(x,__BPF_CAST,__BPF_N,__VA_ARGS__));\ } \ static __always_inline \ u64 ____##name(__BPF_MAP(x, __BPF_DECL_ARGS, __BPF_V, __VA_ARGS__)) @@@ -497,7 -493,7 +497,7 @@@

#define bpf_target_off(TYPE, MEMBER, SIZE, PTR_SIZE) \ ({ \ - BUILD_BUG_ON(FIELD_SIZEOF(TYPE, MEMBER) != (SIZE)); \ + BUILD_BUG_ON(sizeof_member(TYPE, MEMBER) != (SIZE)); \ *(PTR_SIZE) = (SIZE); \ offsetof(TYPE, MEMBER); \ }) @@@ -606,7 -602,7 +606,7 @@@ static inline void bpf_compute_data_poi { struct bpf_skb_data_end *cb = (struct bpf_skb_data_end *)skb->cb;

- BUILD_BUG_ON(sizeof(*cb) > FIELD_SIZEOF(struct sk_buff, cb)); + BUILD_BUG_ON(sizeof(*cb) > sizeof_member(struct sk_buff, cb)); cb->data_meta = skb->data - skb_metadata_len(skb); cb->data_end = skb->data + skb_headlen(skb); } @@@ -644,9 -640,9 +644,9 @@@ static inline u8 *bpf_skb_cb(struct sk_ * attached to sockets, we need to clear the bpf_skb_cb() area * to not leak previous contents to user space. */ - BUILD_BUG_ON(FIELD_SIZEOF(struct __sk_buff, cb) != BPF_SKB_CB_LEN); - BUILD_BUG_ON(FIELD_SIZEOF(struct __sk_buff, cb) != - FIELD_SIZEOF(struct qdisc_skb_cb, data)); + BUILD_BUG_ON(sizeof_member(struct __sk_buff, cb) != BPF_SKB_CB_LEN); + BUILD_BUG_ON(sizeof_member(struct __sk_buff, cb) != + sizeof_member(struct qdisc_skb_cb, data));

return qdisc_skb_cb(skb)->data; } @@@ -1103,6 -1099,7 +1103,6 @@@ static inline void bpf_get_prog_name(co

#endif /* CONFIG_BPF_JIT */

-void bpf_prog_kallsyms_del_subprogs(struct bpf_prog *fp); void bpf_prog_kallsyms_del_all(struct bpf_prog *fp);

#define BPF_ANC BIT(15) diff --combined include/linux/kvm_host.h index 7a26d5513471,ebbf4f1a221a..a1531ac88453 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@@ -149,7 -149,7 +149,7 @@@ static inline bool is_error_page(struc #define KVM_REQUEST_ARCH_BASE 8

#define KVM_ARCH_REQ_FLAGS(nr, flags) ({ \ - BUILD_BUG_ON((unsigned)(nr) >= (FIELD_SIZEOF(struct kvm_vcpu, requests) * 8) - KVM_REQUEST_ARCH_BASE); \ + BUILD_BUG_ON((unsigned)(nr) >= (sizeof_member(struct kvm_vcpu, requests) * 8) - KVM_REQUEST_ARCH_BASE); \ (unsigned)(((nr) + KVM_REQUEST_ARCH_BASE) | (flags)); \ }) #define KVM_ARCH_REQ(nr) KVM_ARCH_REQ_FLAGS(nr, 0) @@@ -746,28 -746,6 +746,28 @@@ int kvm_write_guest_offset_cached(struc unsigned long len); int kvm_gfn_to_hva_cache_init(struct kvm *kvm, struct gfn_to_hva_cache *ghc, gpa_t gpa, unsigned long len); + +#define __kvm_put_guest(kvm, gfn, offset, value, type) \ +({ \ + unsigned long __addr = gfn_to_hva(kvm, gfn); \ + type __user *__uaddr = (type __user *)(__addr + offset); \ + int __ret = -EFAULT; \ + \ + if (!kvm_is_error_hva(__addr)) \ + __ret = put_user(value, __uaddr); \ + if (!__ret) \ + mark_page_dirty(kvm, gfn); \ + __ret; \ +}) + +#define kvm_put_guest(kvm, gpa, value, type) \ +({ \ + gpa_t __gpa = gpa; \ + struct kvm *__kvm = kvm; \ + __kvm_put_guest(__kvm, __gpa >> PAGE_SHIFT, \ + offset_in_page(__gpa), (value), type); \ +}) + int kvm_clear_guest_page(struct kvm *kvm, gfn_t gfn, int offset, int len); int kvm_clear_guest(struct kvm *kvm, gpa_t gpa, unsigned long len); struct kvm_memory_slot *gfn_to_memslot(struct kvm *kvm, gfn_t gfn); @@@ -1262,7 -1240,7 +1262,7 @@@ extern unsigned int halt_poll_ns_grow_s extern unsigned int halt_poll_ns_shrink;

struct kvm_device { - struct kvm_device_ops *ops; + const struct kvm_device_ops *ops; struct kvm *kvm; void *private; struct list_head vm_node; @@@ -1315,7 -1293,7 +1315,7 @@@ struct kvm_device_ops void kvm_device_get(struct kvm_device *dev); void kvm_device_put(struct kvm_device *dev); struct kvm_device *kvm_device_from_filp(struct file *filp); -int kvm_register_device_ops(struct kvm_device_ops *ops, u32 type); +int kvm_register_device_ops(const struct kvm_device_ops *ops, u32 type); void kvm_unregister_device_ops(u32 type);

extern struct kvm_device_ops kvm_mpic_ops; diff --combined include/linux/slab.h index 4d2a2fa55ed5,2afb630bce2a..6d52953dbdf0 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@@ -179,7 -179,7 +179,7 @@@ void memcg_deactivate_kmem_caches(struc sizeof(struct __struct), \ __alignof__(struct __struct), (__flags), \ offsetof(struct __struct, __field), \ - sizeof_field(struct __struct, __field), NULL) + sizeof_member(struct __struct, __field), NULL)

/* * Common kmalloc functions provided by all allocators @@@ -493,10 -493,6 +493,10 @@@ static __always_inline void *kmalloc_la * kmalloc is the normal method of allocating memory * for objects smaller than page size in the kernel. * + * The allocated object address is aligned to at least ARCH_KMALLOC_MINALIGN + * bytes. For @size of power of two bytes, the alignment is also guaranteed + * to be at least to the size. + * * The @flags argument may be one of the GFP flags defined at * include/linux/gfp.h and described at * :ref:`Documentation/core-api/mm-api.rst <mm-api-gfp-flags>` diff --combined include/net/sock.h index f49d7a552f02,6a5a386410ff..1a0ed5a2e55b --- a/include/net/sock.h +++ b/include/net/sock.h @@@ -66,6 -66,7 +66,6 @@@ #include <net/checksum.h> #include <net/tcp_states.h> #include <linux/net_tstamp.h> -#include <net/smc.h> #include <net/l3mdev.h>

/* @@@ -877,17 -878,12 +877,17 @@@ static inline bool sk_acceptq_is_full(c */ static inline int sk_stream_min_wspace(const struct sock *sk) { - return sk->sk_wmem_queued >> 1; + return READ_ONCE(sk->sk_wmem_queued) >> 1; }

static inline int sk_stream_wspace(const struct sock *sk) { - return sk->sk_sndbuf - sk->sk_wmem_queued; + return READ_ONCE(sk->sk_sndbuf) - READ_ONCE(sk->sk_wmem_queued); +} + +static inline void sk_wmem_queued_add(struct sock *sk, int val) +{ + WRITE_ONCE(sk->sk_wmem_queued, sk->sk_wmem_queued + val); }

void sk_stream_write_space(struct sock *sk); @@@ -1211,7 -1207,7 +1211,7 @@@ static inline void sk_refcnt_debug_rele

static inline bool __sk_stream_memory_free(const struct sock *sk, int wake) { - if (sk->sk_wmem_queued >= sk->sk_sndbuf) + if (READ_ONCE(sk->sk_wmem_queued) >= READ_ONCE(sk->sk_sndbuf)) return false;

return sk->sk_prot->stream_memory_free ? @@@ -1471,7 -1467,7 +1471,7 @@@ DECLARE_STATIC_KEY_FALSE(tcp_tx_skb_cac static inline void sk_wmem_free_skb(struct sock *sk, struct sk_buff *skb) { sock_set_flag(sk, SOCK_QUEUE_SHRUNK); - sk->sk_wmem_queued -= skb->truesize; + sk_wmem_queued_add(sk, -skb->truesize); sk_mem_uncharge(sk, skb->truesize); if (static_branch_unlikely(&tcp_tx_skb_cache_key) && !sk->sk_tx_skb_cache && !skb_cloned(skb)) { @@@ -1488,7 -1484,7 +1488,7 @@@ static inline void sock_release_ownersh sk->sk_lock.owned = 0;

/* The sk_lock has mutex_unlock() semantics: */ - mutex_release(&sk->sk_lock.dep_map, 1, _RET_IP_); + mutex_release(&sk->sk_lock.dep_map, _RET_IP_); } }

@@@ -2018,7 -2014,7 +2018,7 @@@ static inline int skb_copy_to_page_noca skb->len += copy; skb->data_len += copy; skb->truesize += copy; - sk->sk_wmem_queued += copy; + sk_wmem_queued_add(sk, copy); sk_mem_charge(sk, copy); return 0; } @@@ -2224,14 -2220,10 +2224,14 @@@ static inline void sk_wake_async(const

static inline void sk_stream_moderate_sndbuf(struct sock *sk) { - if (!(sk->sk_userlocks & SOCK_SNDBUF_LOCK)) { - sk->sk_sndbuf = min(sk->sk_sndbuf, sk->sk_wmem_queued >> 1); - sk->sk_sndbuf = max_t(u32, sk->sk_sndbuf, SOCK_MIN_SNDBUF); - } + u32 val; + + if (sk->sk_userlocks & SOCK_SNDBUF_LOCK) + return; + + val = min(sk->sk_sndbuf, sk->sk_wmem_queued >> 1); + + WRITE_ONCE(sk->sk_sndbuf, max_t(u32, val, SOCK_MIN_SNDBUF)); }

struct sk_buff *sk_stream_alloc_skb(struct sock *sk, int size, gfp_t gfp, @@@ -2241,17 -2233,12 +2241,17 @@@ * sk_page_frag - return an appropriate page_frag * @sk: socket * - * If socket allocation mode allows current thread to sleep, it means its - * safe to use the per task page_frag instead of the per socket one. + * Use the per task page_frag instead of the per socket one for + * optimization when we know that we're in the normal context and owns + * everything that's associated with %current. + * + * gfpflags_allow_blocking() isn't enough here as direct reclaim may nest + * inside other socket operations and end up recursing into sk_page_frag() + * while it's already in use. */ static inline struct page_frag *sk_page_frag(struct sock *sk) { - if (gfpflags_allow_blocking(sk->sk_allocation)) + if (gfpflags_normal_context(sk->sk_allocation)) return &current->task_frag;

return &sk->sk_frag; @@@ -2264,7 -2251,7 +2264,7 @@@ bool sk_page_frag_refill(struct sock *s */ static inline bool sock_writeable(const struct sock *sk) { - return refcount_read(&sk->sk_wmem_alloc) < (sk->sk_sndbuf >> 1); + return refcount_read(&sk->sk_wmem_alloc) < (READ_ONCE(sk->sk_sndbuf) >> 1); }

static inline gfp_t gfp_any(void) @@@ -2284,9 -2271,7 +2284,9 @@@ static inline long sock_sndtimeo(const

static inline int sock_rcvlowat(const struct sock *sk, int waitall, int len) { - return (waitall ? len : min_t(int, sk->sk_rcvlowat, len)) ? : 1; + int v = waitall ? len : min_t(int, READ_ONCE(sk->sk_rcvlowat), len); + + return v ?: 1; }

/* Alas, with timeout socket operations are not restartable. @@@ -2305,7 -2290,7 +2305,7 @@@ struct sock_skb_cb * using skb->cb[] would keep using it directly and utilize its * alignement guarantee. */ - #define SOCK_SKB_CB_OFFSET ((FIELD_SIZEOF(struct sk_buff, cb) - \ + #define SOCK_SKB_CB_OFFSET ((sizeof_member(struct sk_buff, cb) - \ sizeof(struct sock_skb_cb)))

#define SOCK_SKB_CB(__skb) ((struct sock_skb_cb *)((__skb)->cb + \ @@@ -2527,7 -2512,7 +2527,7 @@@ static inline bool sk_listener(const st return (1 << sk->sk_state) & (TCPF_LISTEN | TCPF_NEW_SYN_RECV); }

-void sock_enable_timestamp(struct sock *sk, int flag); +void sock_enable_timestamp(struct sock *sk, enum sock_flags flag); int sock_recv_errqueue(struct sock *sk, struct msghdr *msg, int len, int level, int type);

diff --combined kernel/bpf/cgroup.c index 9f90d3c92bda,3ff6df3ab022..b0adc5e83638 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@@ -180,8 -180,8 +180,8 @@@ static void activate_effective_progs(st enum bpf_attach_type type, struct bpf_prog_array *old_array) { - rcu_swap_protected(cgrp->bpf.effective[type], old_array, - lockdep_is_held(&cgroup_mutex)); + old_array = rcu_replace_pointer(cgrp->bpf.effective[type], old_array, + lockdep_is_held(&cgroup_mutex)); /* free prog array after grace period, since __cgroup_bpf_run_*() * might be still walking the array */ @@@ -1311,12 -1311,12 +1311,12 @@@ static bool sysctl_is_valid_access(int return false;

switch (off) { - case offsetof(struct bpf_sysctl, write): + case bpf_ctx_range(struct bpf_sysctl, write): if (type != BPF_READ) return false; bpf_ctx_record_field_size(info, size_default); return bpf_ctx_narrow_access_ok(off, size, size_default); - case offsetof(struct bpf_sysctl, file_pos): + case bpf_ctx_range(struct bpf_sysctl, file_pos): if (type == BPF_READ) { bpf_ctx_record_field_size(info, size_default); return bpf_ctx_narrow_access_ok(off, size, size_default); @@@ -1341,7 -1341,7 +1341,7 @@@ static u32 sysctl_convert_ctx_access(en *insn++ = BPF_LDX_MEM( BPF_SIZE(si->code), si->dst_reg, si->src_reg, bpf_target_off(struct bpf_sysctl_kern, write, - FIELD_SIZEOF(struct bpf_sysctl_kern, + sizeof_member(struct bpf_sysctl_kern, write), target_size)); break; diff --combined kernel/fork.c index bcdf53125210,1b45b28d4bf5..58cdbd95ef9a --- a/kernel/fork.c +++ b/kernel/fork.c @@@ -2688,7 -2688,7 +2688,7 @@@ void __init proc_caches_init(void mm_size, ARCH_MIN_MMSTRUCT_ALIGN, SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_ACCOUNT, offsetof(struct mm_struct, saved_auxv), - sizeof_field(struct mm_struct, saved_auxv), + sizeof_member(struct mm_struct, saved_auxv), NULL); vm_area_cachep = KMEM_CACHE(vm_area_struct, SLAB_PANIC|SLAB_ACCOUNT); mmap_init(); @@@ -2925,7 -2925,7 +2925,7 @@@ int sysctl_max_threads(struct ctl_tabl struct ctl_table t; int ret; int threads = max_threads; - int min = MIN_THREADS; + int min = 1; int max = MAX_THREADS;

t = *table; @@@ -2937,7 -2937,7 +2937,7 @@@ if (ret || !write) return ret;

- set_max_threads(threads); + max_threads = threads;

return 0; } diff --combined kernel/signal.c index bcd46f547db3,52628a975705..4c1a171eb68f --- a/kernel/signal.c +++ b/kernel/signal.c @@@ -2205,8 -2205,8 +2205,8 @@@ static void ptrace_stop(int exit_code, */ preempt_disable(); read_unlock(&tasklist_lock); - preempt_enable_no_resched(); cgroup_enter_frozen(); + preempt_enable_no_resched(); freezable_schedule(); cgroup_leave_frozen(true); } else { @@@ -4548,11 -4548,11 +4548,11 @@@ static inline void siginfo_buildtime_ch BUILD_BUG_ON(offsetof(struct siginfo, si_pid) != offsetof(struct siginfo, si_addr)); if (sizeof(int) == sizeof(void __user *)) { - BUILD_BUG_ON(sizeof_field(struct siginfo, si_pid) != + BUILD_BUG_ON(sizeof_member(struct siginfo, si_pid) != sizeof(void __user *)); } else { - BUILD_BUG_ON((sizeof_field(struct siginfo, si_pid) + - sizeof_field(struct siginfo, si_uid)) != + BUILD_BUG_ON((sizeof_member(struct siginfo, si_pid) + + sizeof_member(struct siginfo, si_uid)) != sizeof(void __user *)); BUILD_BUG_ON(offsetofend(struct siginfo, si_pid) != offsetof(struct siginfo, si_uid)); @@@ -4560,10 -4560,10 +4560,10 @@@ #ifdef CONFIG_COMPAT BUILD_BUG_ON(offsetof(struct compat_siginfo, si_pid) != offsetof(struct compat_siginfo, si_addr)); - BUILD_BUG_ON(sizeof_field(struct compat_siginfo, si_pid) != + BUILD_BUG_ON(sizeof_member(struct compat_siginfo, si_pid) != sizeof(compat_uptr_t)); - BUILD_BUG_ON(sizeof_field(struct compat_siginfo, si_pid) != - sizeof_field(struct siginfo, si_pid)); + BUILD_BUG_ON(sizeof_member(struct compat_siginfo, si_pid) != + sizeof_member(struct siginfo, si_pid)); #endif }

diff --combined net/caif/caif_socket.c index ef14da50a981,0dbd93bb1939..61bd13d3d637 --- a/net/caif/caif_socket.c +++ b/net/caif/caif_socket.c @@@ -953,7 -953,7 +953,7 @@@ static __poll_t caif_poll(struct file * mask |= EPOLLRDHUP;

/* readable? */ - if (!skb_queue_empty(&sk->sk_receive_queue) || + if (!skb_queue_empty_lockless(&sk->sk_receive_queue) || (sk->sk_shutdown & RCV_SHUTDOWN)) mask |= EPOLLIN | EPOLLRDNORM;

@@@ -1033,7 -1033,7 +1033,7 @@@ static int caif_create(struct net *net .owner = THIS_MODULE, .obj_size = sizeof(struct caifsock), .useroffset = offsetof(struct caifsock, conn_req.param), - .usersize = sizeof_field(struct caifsock, conn_req.param) + .usersize = sizeof_member(struct caifsock, conn_req.param) };

if (!capable(CAP_SYS_ADMIN) && !capable(CAP_NET_ADMIN)) diff --combined net/core/dev.c index af4c5430dd57,c434e94167ca..e6e8d5eaf672 --- a/net/core/dev.c +++ b/net/core/dev.c @@@ -146,7 -146,6 +146,7 @@@ #include "net-sysfs.h"

#define MAX_GRO_SKBS 8 +#define MAX_NEST_DEV 8

/* This should be increased if a protocol with a bigger head is added. */ #define GRO_MAX_HEAD (MAX_HEADER + 128) @@@ -229,122 -228,6 +229,122 @@@ static inline void rps_unlock(struct so #endif }

+static struct netdev_name_node *netdev_name_node_alloc(struct net_device *dev, + const char *name) +{ + struct netdev_name_node *name_node; + + name_node = kmalloc(sizeof(*name_node), GFP_KERNEL); + if (!name_node) + return NULL; + INIT_HLIST_NODE(&name_node->hlist); + name_node->dev = dev; + name_node->name = name; + return name_node; +} + +static struct netdev_name_node * +netdev_name_node_head_alloc(struct net_device *dev) +{ + struct netdev_name_node *name_node; + + name_node = netdev_name_node_alloc(dev, dev->name); + if (!name_node) + return NULL; + INIT_LIST_HEAD(&name_node->list); + return name_node; +} + +static void netdev_name_node_free(struct netdev_name_node *name_node) +{ + kfree(name_node); +} + +static void netdev_name_node_add(struct net *net, + struct netdev_name_node *name_node) +{ + hlist_add_head_rcu(&name_node->hlist, + dev_name_hash(net, name_node->name)); +} + +static void netdev_name_node_del(struct netdev_name_node *name_node) +{ + hlist_del_rcu(&name_node->hlist); +} + +static struct netdev_name_node *netdev_name_node_lookup(struct net *net, + const char *name) +{ + struct hlist_head *head = dev_name_hash(net, name); + struct netdev_name_node *name_node; + + hlist_for_each_entry(name_node, head, hlist) + if (!strcmp(name_node->name, name)) + return name_node; + return NULL; +} + +static struct netdev_name_node *netdev_name_node_lookup_rcu(struct net *net, + const char *name) +{ + struct hlist_head *head = dev_name_hash(net, name); + struct netdev_name_node *name_node; + + hlist_for_each_entry_rcu(name_node, head, hlist) + if (!strcmp(name_node->name, name)) + return name_node; + return NULL; +} + +int netdev_name_node_alt_create(struct net_device *dev, const char *name) +{ + struct netdev_name_node *name_node; + struct net *net = dev_net(dev); + + name_node = netdev_name_node_lookup(net, name); + if (name_node) + return -EEXIST; + name_node = netdev_name_node_alloc(dev, name); + if (!name_node) + return -ENOMEM; + netdev_name_node_add(net, name_node); + /* The node that holds dev->name acts as a head of per-device list. */ + list_add_tail(&name_node->list, &dev->name_node->list); + + return 0; +} +EXPORT_SYMBOL(netdev_name_node_alt_create); + +static void __netdev_name_node_alt_destroy(struct netdev_name_node *name_node) +{ + list_del(&name_node->list); + netdev_name_node_del(name_node); + kfree(name_node->name); + netdev_name_node_free(name_node); +} + +int netdev_name_node_alt_destroy(struct net_device *dev, const char *name) +{ + struct netdev_name_node *name_node; + struct net *net = dev_net(dev); + + name_node = netdev_name_node_lookup(net, name); + if (!name_node) + return -ENOENT; + __netdev_name_node_alt_destroy(name_node); + + return 0; +} +EXPORT_SYMBOL(netdev_name_node_alt_destroy); + +static void netdev_name_node_alt_flush(struct net_device *dev) +{ + struct netdev_name_node *name_node, *tmp; + + list_for_each_entry_safe(name_node, tmp, &dev->name_node->list, list) + __netdev_name_node_alt_destroy(name_node); +} + /* Device list insertion */ static void list_netdevice(struct net_device *dev) { @@@ -354,7 -237,7 +354,7 @@@

write_lock_bh(&dev_base_lock); list_add_tail_rcu(&dev->dev_list, &net->dev_base_head); - hlist_add_head_rcu(&dev->name_hlist, dev_name_hash(net, dev->name)); + netdev_name_node_add(net, dev->name_node); hlist_add_head_rcu(&dev->index_hlist, dev_index_hash(net, dev->ifindex)); write_unlock_bh(&dev_base_lock); @@@ -372,7 -255,7 +372,7 @@@ static void unlist_netdevice(struct net /* Unlink dev from the device chain */ write_lock_bh(&dev_base_lock); list_del_rcu(&dev->dev_list); - hlist_del_rcu(&dev->name_hlist); + netdev_name_node_del(dev->name_node); hlist_del_rcu(&dev->index_hlist); write_unlock_bh(&dev_base_lock);

@@@ -393,6 -276,88 +393,6 @@@ static RAW_NOTIFIER_HEAD(netdev_chain) DEFINE_PER_CPU_ALIGNED(struct softnet_data, softnet_data); EXPORT_PER_CPU_SYMBOL(softnet_data);

-#ifdef CONFIG_LOCKDEP -/* - * register_netdevice() inits txq->_xmit_lock and sets lockdep class - * according to dev->type - */ -static const unsigned short netdev_lock_type[] = { - ARPHRD_NETROM, ARPHRD_ETHER, ARPHRD_EETHER, ARPHRD_AX25, - ARPHRD_PRONET, ARPHRD_CHAOS, ARPHRD_IEEE802, ARPHRD_ARCNET, - ARPHRD_APPLETLK, ARPHRD_DLCI, ARPHRD_ATM, ARPHRD_METRICOM, - ARPHRD_IEEE1394, ARPHRD_EUI64, ARPHRD_INFINIBAND, ARPHRD_SLIP, - ARPHRD_CSLIP, ARPHRD_SLIP6, ARPHRD_CSLIP6, ARPHRD_RSRVD, - ARPHRD_ADAPT, ARPHRD_ROSE, ARPHRD_X25, ARPHRD_HWX25, - ARPHRD_PPP, ARPHRD_CISCO, ARPHRD_LAPB, ARPHRD_DDCMP, - ARPHRD_RAWHDLC, ARPHRD_TUNNEL, ARPHRD_TUNNEL6, ARPHRD_FRAD, - ARPHRD_SKIP, ARPHRD_LOOPBACK, ARPHRD_LOCALTLK, ARPHRD_FDDI, - ARPHRD_BIF, ARPHRD_SIT, ARPHRD_IPDDP, ARPHRD_IPGRE, - ARPHRD_PIMREG, ARPHRD_HIPPI, ARPHRD_ASH, ARPHRD_ECONET, - ARPHRD_IRDA, ARPHRD_FCPP, ARPHRD_FCAL, ARPHRD_FCPL, - ARPHRD_FCFABRIC, ARPHRD_IEEE80211, ARPHRD_IEEE80211_PRISM, - ARPHRD_IEEE80211_RADIOTAP, ARPHRD_PHONET, ARPHRD_PHONET_PIPE, - ARPHRD_IEEE802154, ARPHRD_VOID, ARPHRD_NONE}; - -static const char *const netdev_lock_name[] = { - "_xmit_NETROM", "_xmit_ETHER", "_xmit_EETHER", "_xmit_AX25", - "_xmit_PRONET", "_xmit_CHAOS", "_xmit_IEEE802", "_xmit_ARCNET", - "_xmit_APPLETLK", "_xmit_DLCI", "_xmit_ATM", "_xmit_METRICOM", - "_xmit_IEEE1394", "_xmit_EUI64", "_xmit_INFINIBAND", "_xmit_SLIP", - "_xmit_CSLIP", "_xmit_SLIP6", "_xmit_CSLIP6", "_xmit_RSRVD", - "_xmit_ADAPT", "_xmit_ROSE", "_xmit_X25", "_xmit_HWX25", - "_xmit_PPP", "_xmit_CISCO", "_xmit_LAPB", "_xmit_DDCMP", - "_xmit_RAWHDLC", "_xmit_TUNNEL", "_xmit_TUNNEL6", "_xmit_FRAD", - "_xmit_SKIP", "_xmit_LOOPBACK", "_xmit_LOCALTLK", "_xmit_FDDI", - "_xmit_BIF", "_xmit_SIT", "_xmit_IPDDP", "_xmit_IPGRE", - "_xmit_PIMREG", "_xmit_HIPPI", "_xmit_ASH", "_xmit_ECONET", - "_xmit_IRDA", "_xmit_FCPP", "_xmit_FCAL", "_xmit_FCPL", - "_xmit_FCFABRIC", "_xmit_IEEE80211", "_xmit_IEEE80211_PRISM", - "_xmit_IEEE80211_RADIOTAP", "_xmit_PHONET", "_xmit_PHONET_PIPE", - "_xmit_IEEE802154", "_xmit_VOID", "_xmit_NONE"}; - -static struct lock_class_key netdev_xmit_lock_key[ARRAY_SIZE(netdev_lock_type)]; -static struct lock_class_key netdev_addr_lock_key[ARRAY_SIZE(netdev_lock_type)]; - -static inline unsigned short netdev_lock_pos(unsigned short dev_type) -{ - int i; - - for (i = 0; i < ARRAY_SIZE(netdev_lock_type); i++) - if (netdev_lock_type[i] == dev_type) - return i; - /* the last key is used by default */ - return ARRAY_SIZE(netdev_lock_type) - 1; -} - -static inline void netdev_set_xmit_lockdep_class(spinlock_t *lock, - unsigned short dev_type) -{ - int i; - - i = netdev_lock_pos(dev_type); - lockdep_set_class_and_name(lock, &netdev_xmit_lock_key[i], - netdev_lock_name[i]); -} - -static inline void netdev_set_addr_lockdep_class(struct net_device *dev) -{ - int i; - - i = netdev_lock_pos(dev->type); - lockdep_set_class_and_name(&dev->addr_list_lock, - &netdev_addr_lock_key[i], - netdev_lock_name[i]); -} -#else -static inline void netdev_set_xmit_lockdep_class(spinlock_t *lock, - unsigned short dev_type) -{ -} -static inline void netdev_set_addr_lockdep_class(struct net_device *dev) -{ -} -#endif - /******************************************************************************* * * Protocol management and registration routines @@@ -768,10 -733,14 +768,10 @@@ EXPORT_SYMBOL_GPL(dev_fill_metadata_dst

struct net_device *__dev_get_by_name(struct net *net, const char *name) { - struct net_device *dev; - struct hlist_head *head = dev_name_hash(net, name); - - hlist_for_each_entry(dev, head, name_hlist) - if (!strncmp(dev->name, name, IFNAMSIZ)) - return dev; + struct netdev_name_node *node_name;

- return NULL; + node_name = netdev_name_node_lookup(net, name); + return node_name ? node_name->dev : NULL; } EXPORT_SYMBOL(__dev_get_by_name);

@@@ -789,10 -758,14 +789,10 @@@

struct net_device *dev_get_by_name_rcu(struct net *net, const char *name) { - struct net_device *dev; - struct hlist_head *head = dev_name_hash(net, name); + struct netdev_name_node *node_name;

- hlist_for_each_entry_rcu(dev, head, name_hlist) - if (!strncmp(dev->name, name, IFNAMSIZ)) - return dev; - - return NULL; + node_name = netdev_name_node_lookup_rcu(net, name); + return node_name ? node_name->dev : NULL; } EXPORT_SYMBOL(dev_get_by_name_rcu);

@@@ -1168,8 -1141,8 +1168,8 @@@ int dev_alloc_name(struct net_device *d } EXPORT_SYMBOL(dev_alloc_name);

-int dev_get_valid_name(struct net *net, struct net_device *dev, - const char *name) +static int dev_get_valid_name(struct net *net, struct net_device *dev, + const char *name) { BUG_ON(!net);

@@@ -1185,6 -1158,7 +1185,6 @@@

return 0; } -EXPORT_SYMBOL(dev_get_valid_name);

/** * dev_change_name - change name of a device @@@ -1258,13 -1232,13 +1258,13 @@@ rollback netdev_adjacent_rename_links(dev, oldname);

write_lock_bh(&dev_base_lock); - hlist_del_rcu(&dev->name_hlist); + netdev_name_node_del(dev->name_node); write_unlock_bh(&dev_base_lock);

synchronize_rcu();

write_lock_bh(&dev_base_lock); - hlist_add_head_rcu(&dev->name_hlist, dev_name_hash(net, dev->name)); + netdev_name_node_add(net, dev->name_node); write_unlock_bh(&dev_base_lock);

ret = call_netdevice_notifiers(NETDEV_CHANGENAME, dev); @@@ -1314,8 -1288,8 +1314,8 @@@ int dev_set_alias(struct net_device *de }

mutex_lock(&ifalias_mutex); - rcu_swap_protected(dev->ifalias, new_alias, - mutex_is_locked(&ifalias_mutex)); + new_alias = rcu_replace_pointer(dev->ifalias, new_alias, + mutex_is_locked(&ifalias_mutex)); mutex_unlock(&ifalias_mutex);

if (new_alias) @@@ -1643,62 -1617,6 +1643,62 @@@ static int call_netdevice_notifier(stru return nb->notifier_call(nb, val, &info); }

+static int call_netdevice_register_notifiers(struct notifier_block *nb, + struct net_device *dev) +{ + int err; + + err = call_netdevice_notifier(nb, NETDEV_REGISTER, dev); + err = notifier_to_errno(err); + if (err) + return err; + + if (!(dev->flags & IFF_UP)) + return 0; + + call_netdevice_notifier(nb, NETDEV_UP, dev); + return 0; +} + +static void call_netdevice_unregister_notifiers(struct notifier_block *nb, + struct net_device *dev) +{ + if (dev->flags & IFF_UP) { + call_netdevice_notifier(nb, NETDEV_GOING_DOWN, + dev); + call_netdevice_notifier(nb, NETDEV_DOWN, dev); + } + call_netdevice_notifier(nb, NETDEV_UNREGISTER, dev); +} + +static int call_netdevice_register_net_notifiers(struct notifier_block *nb, + struct net *net) +{ + struct net_device *dev; + int err; + + for_each_netdev(net, dev) { + err = call_netdevice_register_notifiers(nb, dev); + if (err) + goto rollback; + } + return 0; + +rollback: + for_each_netdev_continue_reverse(net, dev) + call_netdevice_unregister_notifiers(nb, dev); + return err; +} + +static void call_netdevice_unregister_net_notifiers(struct notifier_block *nb, + struct net *net) +{ + struct net_device *dev; + + for_each_netdev(net, dev) + call_netdevice_unregister_notifiers(nb, dev); +} + static int dev_boot_phase = 1;

/** @@@ -1717,6 -1635,8 +1717,6 @@@

int register_netdevice_notifier(struct notifier_block *nb) { - struct net_device *dev; - struct net_device *last; struct net *net; int err;

@@@ -1729,9 -1649,17 +1729,9 @@@ if (dev_boot_phase) goto unlock; for_each_net(net) { - for_each_netdev(net, dev) { - err = call_netdevice_notifier(nb, NETDEV_REGISTER, dev); - err = notifier_to_errno(err); - if (err) - goto rollback; - - if (!(dev->flags & IFF_UP)) - continue; - - call_netdevice_notifier(nb, NETDEV_UP, dev); - } + err = call_netdevice_register_net_notifiers(nb, net); + if (err) + goto rollback; }

unlock: @@@ -1740,9 -1668,22 +1740,9 @@@ return err;

rollback: - last = dev; - for_each_net(net) { - for_each_netdev(net, dev) { - if (dev == last) - goto outroll; - - if (dev->flags & IFF_UP) { - call_netdevice_notifier(nb, NETDEV_GOING_DOWN, - dev); - call_netdevice_notifier(nb, NETDEV_DOWN, dev); - } - call_netdevice_notifier(nb, NETDEV_UNREGISTER, dev); - } - } + for_each_net_continue_reverse(net) + call_netdevice_unregister_net_notifiers(nb, net);

-outroll: raw_notifier_chain_unregister(&netdev_chain, nb); goto unlock; } @@@ -1792,80 -1733,6 +1792,80 @@@ unlock } EXPORT_SYMBOL(unregister_netdevice_notifier);

+/** + * register_netdevice_notifier_net - register a per-netns network notifier block + * @net: network namespace + * @nb: notifier + * + * Register a notifier to be called when network device events occur. + * The notifier passed is linked into the kernel structures and must + * not be reused until it has been unregistered. A negative errno code + * is returned on a failure. + * + * When registered all registration and up events are replayed + * to the new notifier to allow device to have a race free + * view of the network device list. + */ + +int register_netdevice_notifier_net(struct net *net, struct notifier_block *nb) +{ + int err; + + rtnl_lock(); + err = raw_notifier_chain_register(&net->netdev_chain, nb); + if (err) + goto unlock; + if (dev_boot_phase) + goto unlock; + + err = call_netdevice_register_net_notifiers(nb, net); + if (err) + goto chain_unregister; + +unlock: + rtnl_unlock(); + return err; + +chain_unregister: + raw_notifier_chain_unregister(&netdev_chain, nb); + goto unlock; +} +EXPORT_SYMBOL(register_netdevice_notifier_net); + +/** + * unregister_netdevice_notifier_net - unregister a per-netns + * network notifier block + * @net: network namespace + * @nb: notifier + * + * Unregister a notifier previously registered by + * register_netdevice_notifier(). The notifier is unlinked into the + * kernel structures and may then be reused. A negative errno code + * is returned on a failure. + * + * After unregistering unregister and down device events are synthesized + * for all devices on the device list to the removed notifier to remove + * the need for special case cleanup code. + */ + +int unregister_netdevice_notifier_net(struct net *net, + struct notifier_block *nb) +{ + int err; + + rtnl_lock(); + err = raw_notifier_chain_unregister(&net->netdev_chain, nb); + if (err) + goto unlock; + + call_netdevice_unregister_net_notifiers(nb, net); + +unlock: + rtnl_unlock(); + return err; +} +EXPORT_SYMBOL(unregister_netdevice_notifier_net); + /** * call_netdevice_notifiers_info - call all network notifier blocks * @val: value passed unmodified to notifier function @@@ -1878,18 -1745,7 +1878,18 @@@ static int call_netdevice_notifiers_info(unsigned long val, struct netdev_notifier_info *info) { + struct net *net = dev_net(info->dev); + int ret; + ASSERT_RTNL(); + + /* Run per-netns notifier block chain first, then run the global one. + * Hopefully, one day, the global one is going to be removed after + * all notifier block registrators get converted to be per-netns. + */ + ret = raw_notifier_call_chain(&net->netdev_chain, val, info); + if (ret & NOTIFY_STOP_MASK) + return ret; return raw_notifier_call_chain(&netdev_chain, val, info); }

@@@ -2915,7 -2771,7 +2915,7 @@@ static struct dev_kfree_skb_cb *get_kfr void netif_schedule_queue(struct netdev_queue *txq) { rcu_read_lock(); - if (!(txq->state & QUEUE_STATE_ANY_XOFF)) { + if (!netif_xmit_stopped(txq)) { struct Qdisc *q = rcu_dereference(txq->qdisc);

__netif_schedule(q); @@@ -3083,9 -2939,12 +3083,9 @@@ int skb_checksum_help(struct sk_buff *s offset += skb->csum_offset; BUG_ON(offset + sizeof(__sum16) > skb_headlen(skb));

- if (skb_cloned(skb) && - !skb_clone_writable(skb, offset + sizeof(__sum16))) { - ret = pskb_expand_head(skb, 0, 0, GFP_ATOMIC); - if (ret) - goto out; - } + ret = skb_ensure_writable(skb, offset + sizeof(__sum16)); + if (ret) + goto out;

*(__sum16 *)(skb->data + offset) = csum_fold(csum) ?: CSUM_MANGLED_0; out_set_summed: @@@ -3120,11 -2979,12 +3120,11 @@@ int skb_crc32c_csum_help(struct sk_buf ret = -EINVAL; goto out; } - if (skb_cloned(skb) && - !skb_clone_writable(skb, offset + sizeof(__le32))) { - ret = pskb_expand_head(skb, 0, 0, GFP_ATOMIC); - if (ret) - goto out; - } + + ret = skb_ensure_writable(skb, offset + sizeof(__le32)); + if (ret) + goto out; + crc32c_csum = cpu_to_le32(~__skb_checksum(skb, start, skb->len - start, ~(__u32)0, crc32c_csum_stub)); @@@ -5803,26 -5663,6 +5803,26 @@@ struct packet_offload *gro_find_complet } EXPORT_SYMBOL(gro_find_complete_by_type);

+/* Pass the currently batched GRO_NORMAL SKBs up to the stack. */ +static void gro_normal_list(struct napi_struct *napi) +{ + if (!napi->rx_count) + return; + netif_receive_skb_list_internal(&napi->rx_list); + INIT_LIST_HEAD(&napi->rx_list); + napi->rx_count = 0; +} + +/* Queue one GRO_NORMAL SKB up for list processing. If batch size exceeded, + * pass the whole batch up to the stack. + */ +static void gro_normal_one(struct napi_struct *napi, struct sk_buff *skb) +{ + list_add_tail(&skb->list, &napi->rx_list); + if (++napi->rx_count >= gro_normal_batch) + gro_normal_list(napi); +} + static void napi_skb_free_stolen_head(struct sk_buff *skb) { skb_dst_drop(skb); @@@ -5830,13 -5670,12 +5830,13 @@@ kmem_cache_free(skbuff_head_cache, skb); }

-static gro_result_t napi_skb_finish(gro_result_t ret, struct sk_buff *skb) +static gro_result_t napi_skb_finish(struct napi_struct *napi, + struct sk_buff *skb, + gro_result_t ret) { switch (ret) { case GRO_NORMAL: - if (netif_receive_skb_internal(skb)) - ret = GRO_DROP; + gro_normal_one(napi, skb); break;

case GRO_DROP: @@@ -5868,7 -5707,7 +5868,7 @@@ gro_result_t napi_gro_receive(struct na

skb_gro_reset_offset(skb);

- ret = napi_skb_finish(dev_gro_receive(napi, skb), skb); + ret = napi_skb_finish(napi, skb, dev_gro_receive(napi, skb)); trace_napi_gro_receive_exit(ret);

return ret; @@@ -5914,6 -5753,26 +5914,6 @@@ struct sk_buff *napi_get_frags(struct n } EXPORT_SYMBOL(napi_get_frags);

-/* Pass the currently batched GRO_NORMAL SKBs up to the stack. */ -static void gro_normal_list(struct napi_struct *napi) -{ - if (!napi->rx_count) - return; - netif_receive_skb_list_internal(&napi->rx_list); - INIT_LIST_HEAD(&napi->rx_list); - napi->rx_count = 0; -} - -/* Queue one GRO_NORMAL SKB up for list processing. If batch size exceeded, - * pass the whole batch up to the stack. - */ -static void gro_normal_one(struct napi_struct *napi, struct sk_buff *skb) -{ - list_add_tail(&skb->list, &napi->rx_list); - if (++napi->rx_count >= gro_normal_batch) - gro_normal_list(napi); -} - static gro_result_t napi_frags_finish(struct napi_struct *napi, struct sk_buff *skb, gro_result_t ret) @@@ -6630,9 -6489,6 +6630,9 @@@ struct netdev_adjacent /* upper master flag, there can only be one master device per list */ bool master;

+ /* lookup ignore flag */ + bool ignore; + /* counter for the number of times this device was added to us */ u16 ref_nr;

@@@ -6655,7 -6511,7 +6655,7 @@@ static struct netdev_adjacent *__netdev return NULL; }

-static int __netdev_has_upper_dev(struct net_device *upper_dev, void *data) +static int ____netdev_has_upper_dev(struct net_device *upper_dev, void *data) { struct net_device *dev = data;

@@@ -6676,7 -6532,7 +6676,7 @@@ bool netdev_has_upper_dev(struct net_de { ASSERT_RTNL();

- return netdev_walk_all_upper_dev_rcu(dev, __netdev_has_upper_dev, + return netdev_walk_all_upper_dev_rcu(dev, ____netdev_has_upper_dev, upper_dev); } EXPORT_SYMBOL(netdev_has_upper_dev); @@@ -6694,7 -6550,7 +6694,7 @@@ bool netdev_has_upper_dev_all_rcu(struct net_device *dev, struct net_device *upper_dev) { - return !!netdev_walk_all_upper_dev_rcu(dev, __netdev_has_upper_dev, + return !!netdev_walk_all_upper_dev_rcu(dev, ____netdev_has_upper_dev, upper_dev); } EXPORT_SYMBOL(netdev_has_upper_dev_all_rcu); @@@ -6738,22 -6594,6 +6738,22 @@@ struct net_device *netdev_master_upper_ } EXPORT_SYMBOL(netdev_master_upper_dev_get);

+static struct net_device *__netdev_master_upper_dev_get(struct net_device *dev) +{ + struct netdev_adjacent *upper; + + ASSERT_RTNL(); + + if (list_empty(&dev->adj_list.upper)) + return NULL; + + upper = list_first_entry(&dev->adj_list.upper, + struct netdev_adjacent, list); + if (likely(upper->master) && !upper->ignore) + return upper->dev; + return NULL; +} + /** * netdev_has_any_lower_dev - Check if device is linked to some device * @dev: device @@@ -6804,23 -6644,6 +6804,23 @@@ struct net_device *netdev_upper_get_nex } EXPORT_SYMBOL(netdev_upper_get_next_dev_rcu);

+static struct net_device *__netdev_next_upper_dev(struct net_device *dev, + struct list_head **iter, + bool *ignore) +{ + struct netdev_adjacent *upper; + + upper = list_entry((*iter)->next, struct netdev_adjacent, list); + + if (&upper->list == &dev->adj_list.upper) + return NULL; + + *iter = &upper->list; + *ignore = upper->ignore; + + return upper->dev; +} + static struct net_device *netdev_next_upper_dev_rcu(struct net_device *dev, struct list_head **iter) { @@@ -6838,111 -6661,34 +6838,111 @@@ return upper->dev; }

+static int __netdev_walk_all_upper_dev(struct net_device *dev, + int (*fn)(struct net_device *dev, + void *data), + void *data) +{ + struct net_device *udev, *next, *now, *dev_stack[MAX_NEST_DEV + 1]; + struct list_head *niter, *iter, *iter_stack[MAX_NEST_DEV + 1]; + int ret, cur = 0; + bool ignore; + + now = dev; + iter = &dev->adj_list.upper; + + while (1) { + if (now != dev) { + ret = fn(now, data); + if (ret) + return ret; + } + + next = NULL; + while (1) { + udev = __netdev_next_upper_dev(now, &iter, &ignore); + if (!udev) + break; + if (ignore) + continue; + + next = udev; + niter = &udev->adj_list.upper; + dev_stack[cur] = now; + iter_stack[cur++] = iter; + break; + } + + if (!next) { + if (!cur) + return 0; + next = dev_stack[--cur]; + niter = iter_stack[cur]; + } + + now = next; + iter = niter; + } + + return 0; +} + int netdev_walk_all_upper_dev_rcu(struct net_device *dev, int (*fn)(struct net_device *dev, void *data), void *data) { - struct net_device *udev; - struct list_head *iter; - int ret; + struct net_device *udev, *next, *now, *dev_stack[MAX_NEST_DEV + 1]; + struct list_head *niter, *iter, *iter_stack[MAX_NEST_DEV + 1]; + int ret, cur = 0;

- for (iter = &dev->adj_list.upper, - udev = netdev_next_upper_dev_rcu(dev, &iter); - udev; - udev = netdev_next_upper_dev_rcu(dev, &iter)) { - /* first is the upper device itself */ - ret = fn(udev, data); - if (ret) - return ret; + now = dev; + iter = &dev->adj_list.upper;

- /* then look at all of its upper devices */ - ret = netdev_walk_all_upper_dev_rcu(udev, fn, data); - if (ret) - return ret; + while (1) { + if (now != dev) { + ret = fn(now, data); + if (ret) + return ret; + } + + next = NULL; + while (1) { + udev = netdev_next_upper_dev_rcu(now, &iter); + if (!udev) + break; + + next = udev; + niter = &udev->adj_list.upper; + dev_stack[cur] = now; + iter_stack[cur++] = iter; + break; + } + + if (!next) { + if (!cur) + return 0; + next = dev_stack[--cur]; + niter = iter_stack[cur]; + } + + now = next; + iter = niter; }

return 0; } EXPORT_SYMBOL_GPL(netdev_walk_all_upper_dev_rcu);

+static bool __netdev_has_upper_dev(struct net_device *dev, + struct net_device *upper_dev) +{ + ASSERT_RTNL(); + + return __netdev_walk_all_upper_dev(dev, ____netdev_has_upper_dev, + upper_dev); +} + /** * netdev_lower_get_next_private - Get the next ->private from the * lower neighbour list @@@ -7039,119 -6785,34 +7039,119 @@@ static struct net_device *netdev_next_l return lower->dev; }

+static struct net_device *__netdev_next_lower_dev(struct net_device *dev, + struct list_head **iter, + bool *ignore) +{ + struct netdev_adjacent *lower; + + lower = list_entry((*iter)->next, struct netdev_adjacent, list); + + if (&lower->list == &dev->adj_list.lower) + return NULL; + + *iter = &lower->list; + *ignore = lower->ignore; + + return lower->dev; +} + int netdev_walk_all_lower_dev(struct net_device *dev, int (*fn)(struct net_device *dev, void *data), void *data) { - struct net_device *ldev; - struct list_head *iter; - int ret; + struct net_device *ldev, *next, *now, *dev_stack[MAX_NEST_DEV + 1]; + struct list_head *niter, *iter, *iter_stack[MAX_NEST_DEV + 1]; + int ret, cur = 0;

- for (iter = &dev->adj_list.lower, - ldev = netdev_next_lower_dev(dev, &iter); - ldev; - ldev = netdev_next_lower_dev(dev, &iter)) { - /* first is the lower device itself */ - ret = fn(ldev, data); - if (ret) - return ret; + now = dev; + iter = &dev->adj_list.lower;

- /* then look at all of its lower devices */ - ret = netdev_walk_all_lower_dev(ldev, fn, data); - if (ret) - return ret; + while (1) { + if (now != dev) { + ret = fn(now, data); + if (ret) + return ret; + } + + next = NULL; + while (1) { + ldev = netdev_next_lower_dev(now, &iter); + if (!ldev) + break; + + next = ldev; + niter = &ldev->adj_list.lower; + dev_stack[cur] = now; + iter_stack[cur++] = iter; + break; + } + + if (!next) { + if (!cur) + return 0; + next = dev_stack[--cur]; + niter = iter_stack[cur]; + } + + now = next; + iter = niter; }

return 0; } EXPORT_SYMBOL_GPL(netdev_walk_all_lower_dev);

+static int __netdev_walk_all_lower_dev(struct net_device *dev, + int (*fn)(struct net_device *dev, + void *data), + void *data) +{ + struct net_device *ldev, *next, *now, *dev_stack[MAX_NEST_DEV + 1]; + struct list_head *niter, *iter, *iter_stack[MAX_NEST_DEV + 1]; + int ret, cur = 0; + bool ignore; + + now = dev; + iter = &dev->adj_list.lower; + + while (1) { + if (now != dev) { + ret = fn(now, data); + if (ret) + return ret; + } + + next = NULL; + while (1) { + ldev = __netdev_next_lower_dev(now, &iter, &ignore); + if (!ldev) + break; + if (ignore) + continue; + + next = ldev; + niter = &ldev->adj_list.lower; + dev_stack[cur] = now; + iter_stack[cur++] = iter; + break; + } + + if (!next) { + if (!cur) + return 0; + next = dev_stack[--cur]; + niter = iter_stack[cur]; + } + + now = next; + iter = niter; + } + + return 0; +} + static struct net_device *netdev_next_lower_dev_rcu(struct net_device *dev, struct list_head **iter) { @@@ -7166,99 -6827,28 +7166,99 @@@ return lower->dev; }

-int netdev_walk_all_lower_dev_rcu(struct net_device *dev, - int (*fn)(struct net_device *dev, - void *data), - void *data) +static u8 __netdev_upper_depth(struct net_device *dev) +{ + struct net_device *udev; + struct list_head *iter; + u8 max_depth = 0; + bool ignore; + + for (iter = &dev->adj_list.upper, + udev = __netdev_next_upper_dev(dev, &iter, &ignore); + udev; + udev = __netdev_next_upper_dev(dev, &iter, &ignore)) { + if (ignore) + continue; + if (max_depth < udev->upper_level) + max_depth = udev->upper_level; + } + + return max_depth; +} + +static u8 __netdev_lower_depth(struct net_device *dev) { struct net_device *ldev; struct list_head *iter; - int ret; + u8 max_depth = 0; + bool ignore;

for (iter = &dev->adj_list.lower, - ldev = netdev_next_lower_dev_rcu(dev, &iter); + ldev = __netdev_next_lower_dev(dev, &iter, &ignore); ldev; - ldev = netdev_next_lower_dev_rcu(dev, &iter)) { - /* first is the lower device itself */ - ret = fn(ldev, data); - if (ret) - return ret; + ldev = __netdev_next_lower_dev(dev, &iter, &ignore)) { + if (ignore) + continue; + if (max_depth < ldev->lower_level) + max_depth = ldev->lower_level; + }

- /* then look at all of its lower devices */ - ret = netdev_walk_all_lower_dev_rcu(ldev, fn, data); - if (ret) - return ret; + return max_depth; +} + +static int __netdev_update_upper_level(struct net_device *dev, void *data) +{ + dev->upper_level = __netdev_upper_depth(dev) + 1; + return 0; +} + +static int __netdev_update_lower_level(struct net_device *dev, void *data) +{ + dev->lower_level = __netdev_lower_depth(dev) + 1; + return 0; +} + +int netdev_walk_all_lower_dev_rcu(struct net_device *dev, + int (*fn)(struct net_device *dev, + void *data), + void *data) +{ + struct net_device *ldev, *next, *now, *dev_stack[MAX_NEST_DEV + 1]; + struct list_head *niter, *iter, *iter_stack[MAX_NEST_DEV + 1]; + int ret, cur = 0; + + now = dev; + iter = &dev->adj_list.lower; + + while (1) { + if (now != dev) { + ret = fn(now, data); + if (ret) + return ret; + } + + next = NULL; + while (1) { + ldev = netdev_next_lower_dev_rcu(now, &iter); + if (!ldev) + break; + + next = ldev; + niter = &ldev->adj_list.lower; + dev_stack[cur] = now; + iter_stack[cur++] = iter; + break; + } + + if (!next) { + if (!cur) + return 0; + next = dev_stack[--cur]; + niter = iter_stack[cur]; + } + + now = next; + iter = niter; }

return 0; @@@ -7362,7 -6952,6 +7362,7 @@@ static int __netdev_adjacent_dev_insert adj->master = master; adj->ref_nr = 1; adj->private = private; + adj->ignore = false; dev_hold(adj_dev);

pr_debug("Insert adjacency: dev %s adj_dev %s adj->ref_nr %d; dev_hold on %s\n", @@@ -7513,17 -7102,14 +7513,17 @@@ static int __netdev_upper_dev_link(stru return -EBUSY;

/* To prevent loops, check if dev is not upper device to upper_dev. */ - if (netdev_has_upper_dev(upper_dev, dev)) + if (__netdev_has_upper_dev(upper_dev, dev)) return -EBUSY;

+ if ((dev->lower_level + upper_dev->upper_level) > MAX_NEST_DEV) + return -EMLINK; + if (!master) { - if (netdev_has_upper_dev(dev, upper_dev)) + if (__netdev_has_upper_dev(dev, upper_dev)) return -EEXIST; } else { - master_dev = netdev_master_upper_dev_get(dev); + master_dev = __netdev_master_upper_dev_get(dev); if (master_dev) return master_dev == upper_dev ? -EEXIST : -EBUSY; } @@@ -7545,13 -7131,6 +7545,13 @@@ if (ret) goto rollback;

+ __netdev_update_upper_level(dev, NULL); + __netdev_walk_all_lower_dev(dev, __netdev_update_upper_level, NULL); + + __netdev_update_lower_level(upper_dev, NULL); + __netdev_walk_all_upper_dev(upper_dev, __netdev_update_lower_level, + NULL); + return 0;

rollback: @@@ -7634,96 -7213,9 +7634,96 @@@ void netdev_upper_dev_unlink(struct net

call_netdevice_notifiers_info(NETDEV_CHANGEUPPER, &changeupper_info.info); + + __netdev_update_upper_level(dev, NULL); + __netdev_walk_all_lower_dev(dev, __netdev_update_upper_level, NULL); + + __netdev_update_lower_level(upper_dev, NULL); + __netdev_walk_all_upper_dev(upper_dev, __netdev_update_lower_level, + NULL); } EXPORT_SYMBOL(netdev_upper_dev_unlink);

+static void __netdev_adjacent_dev_set(struct net_device *upper_dev, + struct net_device *lower_dev, + bool val) +{ + struct netdev_adjacent *adj; + + adj = __netdev_find_adj(lower_dev, &upper_dev->adj_list.lower); + if (adj) + adj->ignore = val; + + adj = __netdev_find_adj(upper_dev, &lower_dev->adj_list.upper); + if (adj) + adj->ignore = val; +} + +static void netdev_adjacent_dev_disable(struct net_device *upper_dev, + struct net_device *lower_dev) +{ + __netdev_adjacent_dev_set(upper_dev, lower_dev, true); +} + +static void netdev_adjacent_dev_enable(struct net_device *upper_dev, + struct net_device *lower_dev) +{ + __netdev_adjacent_dev_set(upper_dev, lower_dev, false); +} + +int netdev_adjacent_change_prepare(struct net_device *old_dev, + struct net_device *new_dev, + struct net_device *dev, + struct netlink_ext_ack *extack) +{ + int err; + + if (!new_dev) + return 0; + + if (old_dev && new_dev != old_dev) + netdev_adjacent_dev_disable(dev, old_dev); + + err = netdev_upper_dev_link(new_dev, dev, extack); + if (err) { + if (old_dev && new_dev != old_dev) + netdev_adjacent_dev_enable(dev, old_dev); + return err; + } + + return 0; +} +EXPORT_SYMBOL(netdev_adjacent_change_prepare); + +void netdev_adjacent_change_commit(struct net_device *old_dev, + struct net_device *new_dev, + struct net_device *dev) +{ + if (!new_dev || !old_dev) + return; + + if (new_dev == old_dev) + return; + + netdev_adjacent_dev_enable(dev, old_dev); + netdev_upper_dev_unlink(old_dev, dev); +} +EXPORT_SYMBOL(netdev_adjacent_change_commit); + +void netdev_adjacent_change_abort(struct net_device *old_dev, + struct net_device *new_dev, + struct net_device *dev) +{ + if (!new_dev) + return; + + if (old_dev && new_dev != old_dev) + netdev_adjacent_dev_enable(dev, old_dev); + + netdev_upper_dev_unlink(new_dev, dev); +} +EXPORT_SYMBOL(netdev_adjacent_change_abort); + /** * netdev_bonding_info_change - Dispatch event about slave change * @dev: device @@@ -7837,6 -7329,25 +7837,6 @@@ void *netdev_lower_dev_get_private(stru EXPORT_SYMBOL(netdev_lower_dev_get_private);

-int dev_get_nest_level(struct net_device *dev) -{ - struct net_device *lower = NULL; - struct list_head *iter; - int max_nest = -1; - int nest; - - ASSERT_RTNL(); - - netdev_for_each_lower_dev(dev, lower, iter) { - nest = dev_get_nest_level(lower); - if (max_nest < nest) - max_nest = nest; - } - - return max_nest + 1; -} -EXPORT_SYMBOL(dev_get_nest_level); - /** * netdev_lower_change - Dispatch event about lower device state change * @lower_dev: device @@@ -8753,9 -8264,6 +8753,9 @@@ static void rollback_registered_many(st dev_uc_flush(dev); dev_mc_flush(dev);

+ netdev_name_node_alt_flush(dev); + netdev_name_node_free(dev->name_node); + if (dev->netdev_ops->ndo_uninit) dev->netdev_ops->ndo_uninit(dev);

@@@ -9111,7 -8619,7 +9111,7 @@@ static void netdev_init_one_queue(struc { /* Initialize queue lock */ spin_lock_init(&queue->_xmit_lock); - netdev_set_xmit_lockdep_class(&queue->_xmit_lock, dev->type); + lockdep_set_class(&queue->_xmit_lock, &dev->qdisc_xmit_lock_key); queue->xmit_lock_owner = -1; netdev_queue_numa_node_write(queue, NUMA_NO_NODE); queue->dev = dev; @@@ -9158,43 -8666,6 +9158,43 @@@ void netif_tx_stop_all_queues(struct ne } EXPORT_SYMBOL(netif_tx_stop_all_queues);

+static void netdev_register_lockdep_key(struct net_device *dev) +{ + lockdep_register_key(&dev->qdisc_tx_busylock_key); + lockdep_register_key(&dev->qdisc_running_key); + lockdep_register_key(&dev->qdisc_xmit_lock_key); + lockdep_register_key(&dev->addr_list_lock_key); +} + +static void netdev_unregister_lockdep_key(struct net_device *dev) +{ + lockdep_unregister_key(&dev->qdisc_tx_busylock_key); + lockdep_unregister_key(&dev->qdisc_running_key); + lockdep_unregister_key(&dev->qdisc_xmit_lock_key); + lockdep_unregister_key(&dev->addr_list_lock_key); +} + +void netdev_update_lockdep_key(struct net_device *dev) +{ + struct netdev_queue *queue; + int i; + + lockdep_unregister_key(&dev->qdisc_xmit_lock_key); + lockdep_unregister_key(&dev->addr_list_lock_key); + + lockdep_register_key(&dev->qdisc_xmit_lock_key); + lockdep_register_key(&dev->addr_list_lock_key); + + lockdep_set_class(&dev->addr_list_lock, &dev->addr_list_lock_key); + for (i = 0; i < dev->num_tx_queues; i++) { + queue = netdev_get_tx_queue(dev, i); + + lockdep_set_class(&queue->_xmit_lock, + &dev->qdisc_xmit_lock_key); + } +} +EXPORT_SYMBOL(netdev_update_lockdep_key); + /** * register_netdevice - register a network device * @dev: device to register @@@ -9229,17 -8700,12 +9229,17 @@@ int register_netdevice(struct net_devic BUG_ON(!net);

spin_lock_init(&dev->addr_list_lock); - netdev_set_addr_lockdep_class(dev); + lockdep_set_class(&dev->addr_list_lock, &dev->addr_list_lock_key);

ret = dev_get_valid_name(net, dev, dev->name); if (ret < 0) goto out;

+ ret = -ENOMEM; + dev->name_node = netdev_name_node_head_alloc(dev); + if (!dev->name_node) + goto out; + /* Init, if this function is available */ if (dev->netdev_ops->ndo_init) { ret = dev->netdev_ops->ndo_init(dev); @@@ -9361,8 -8827,6 +9361,8 @@@ out return ret;

err_uninit: + if (dev->name_node) + netdev_name_node_free(dev->name_node); if (dev->netdev_ops->ndo_uninit) dev->netdev_ops->ndo_uninit(dev); if (dev->priv_destructor) @@@ -9746,12 -9210,8 +9746,12 @@@ struct net_device *alloc_netdev_mqs(in

dev_net_set(dev, &init_net);

+ netdev_register_lockdep_key(dev); + dev->gso_max_size = GSO_MAX_SIZE; dev->gso_max_segs = GSO_MAX_SEGS; + dev->upper_level = 1; + dev->lower_level = 1;

INIT_LIST_HEAD(&dev->napi_list); INIT_LIST_HEAD(&dev->unreg_list); @@@ -9832,8 -9292,6 +9832,8 @@@ void free_netdev(struct net_device *dev free_percpu(dev->pcpu_refcnt); dev->pcpu_refcnt = NULL;

+ netdev_unregister_lockdep_key(dev); + /* Compatibility with error handling in drivers */ if (dev->reg_state == NETREG_UNINITIALIZED) { netdev_freemem(dev); @@@ -10002,7 -9460,7 +10002,7 @@@ int dev_change_net_namespace(struct net call_netdevice_notifiers(NETDEV_UNREGISTER, dev); rcu_barrier();

- new_nsid = peernet2id_alloc(dev_net(dev), net); + new_nsid = peernet2id_alloc(dev_net(dev), net, GFP_KERNEL); /* If there is an ifindex conflict assign a new one */ if (__dev_get_by_index(net, dev->ifindex)) new_ifindex = dev_new_index(net); @@@ -10164,7 -9622,7 +10164,7 @@@ static struct hlist_head * __net_init n static int __net_init netdev_init(struct net *net) { BUILD_BUG_ON(GRO_HASH_BUCKETS > - 8 * FIELD_SIZEOF(struct napi_struct, gro_bitmask)); + 8 * sizeof_member(struct napi_struct, gro_bitmask));

if (net != &init_net) INIT_LIST_HEAD(&net->dev_base_head); @@@ -10177,8 -9635,6 +10177,8 @@@ if (net->dev_index_head == NULL) goto err_idx;

+ RAW_INIT_NOTIFIER_HEAD(&net->netdev_chain); + return 0;

err_idx: diff --combined net/core/filter.c index fc303abec8fa,284f60695ba9..6644f1c56be9 --- a/net/core/filter.c +++ b/net/core/filter.c @@@ -274,7 -274,7 +274,7 @@@ static u32 convert_skb_access(int skb_f

switch (skb_field) { case SKF_AD_MARK: - BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, mark) != 4); + BUILD_BUG_ON(sizeof_member(struct sk_buff, mark) != 4);

*insn++ = BPF_LDX_MEM(BPF_W, dst_reg, src_reg, offsetof(struct sk_buff, mark)); @@@ -289,14 -289,14 +289,14 @@@ break;

case SKF_AD_QUEUE: - BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, queue_mapping) != 2); + BUILD_BUG_ON(sizeof_member(struct sk_buff, queue_mapping) != 2);

*insn++ = BPF_LDX_MEM(BPF_H, dst_reg, src_reg, offsetof(struct sk_buff, queue_mapping)); break;

case SKF_AD_VLAN_TAG: - BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, vlan_tci) != 2); + BUILD_BUG_ON(sizeof_member(struct sk_buff, vlan_tci) != 2);

/* dst_reg = *(u16 *) (src_reg + offsetof(vlan_tci)) */ *insn++ = BPF_LDX_MEM(BPF_H, dst_reg, src_reg, @@@ -322,7 -322,7 +322,7 @@@ static bool convert_bpf_extensions(stru

switch (fp->k) { case SKF_AD_OFF + SKF_AD_PROTOCOL: - BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, protocol) != 2); + BUILD_BUG_ON(sizeof_member(struct sk_buff, protocol) != 2);

/* A = *(u16 *) (CTX + offsetof(protocol)) */ *insn++ = BPF_LDX_MEM(BPF_H, BPF_REG_A, BPF_REG_CTX, @@@ -338,8 -338,8 +338,8 @@@

case SKF_AD_OFF + SKF_AD_IFINDEX: case SKF_AD_OFF + SKF_AD_HATYPE: - BUILD_BUG_ON(FIELD_SIZEOF(struct net_device, ifindex) != 4); - BUILD_BUG_ON(FIELD_SIZEOF(struct net_device, type) != 2); + BUILD_BUG_ON(sizeof_member(struct net_device, ifindex) != 4); + BUILD_BUG_ON(sizeof_member(struct net_device, type) != 2);

*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, dev), BPF_REG_TMP, BPF_REG_CTX, @@@ -361,7 -361,7 +361,7 @@@ break;

case SKF_AD_OFF + SKF_AD_RXHASH: - BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, hash) != 4); + BUILD_BUG_ON(sizeof_member(struct sk_buff, hash) != 4);

*insn = BPF_LDX_MEM(BPF_W, BPF_REG_A, BPF_REG_CTX, offsetof(struct sk_buff, hash)); @@@ -385,7 -385,7 +385,7 @@@ break;

case SKF_AD_OFF + SKF_AD_VLAN_TPID: - BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, vlan_proto) != 2); + BUILD_BUG_ON(sizeof_member(struct sk_buff, vlan_proto) != 2);

/* A = *(u16 *) (CTX + offsetof(vlan_proto)) */ *insn++ = BPF_LDX_MEM(BPF_H, BPF_REG_A, BPF_REG_CTX, @@@ -2245,7 -2245,7 +2245,7 @@@ BPF_CALL_4(bpf_msg_pull_data, struct sk * account for the headroom. */ bytes_sg_total = start - offset + bytes; - if (!msg->sg.copy[i] && bytes_sg_total <= len) + if (!test_bit(i, &msg->sg.copy) && bytes_sg_total <= len) goto out;

/* At this point we need to linearize multiple scatterlist @@@ -2450,7 -2450,7 +2450,7 @@@ BPF_CALL_4(bpf_msg_push_data, struct sk /* Place newly allocated data buffer */ sk_mem_charge(msg->sk, len); msg->sg.size += len; - msg->sg.copy[new] = false; + __clear_bit(new, &msg->sg.copy); sg_set_page(&msg->sg.data[new], page, len + copy, 0); if (rsge.length) { get_page(sg_page(&rsge)); @@@ -3798,7 -3798,7 +3798,7 @@@ BPF_CALL_5(bpf_skb_event_output, struc

if (unlikely(flags & ~(BPF_F_CTXLEN_MASK | BPF_F_INDEX_MASK))) return -EINVAL; - if (unlikely(skb_size > skb->len)) + if (unlikely(!skb || skb_size > skb->len)) return -EFAULT;

return bpf_event_output(map, flags, meta, meta_size, skb, skb_size, @@@ -3816,19 -3816,6 +3816,19 @@@ static const struct bpf_func_proto bpf_ .arg5_type = ARG_CONST_SIZE_OR_ZERO, };

+static u32 bpf_skb_output_btf_ids[5]; +const struct bpf_func_proto bpf_skb_output_proto = { + .func = bpf_skb_event_output, + .gpl_only = true, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_BTF_ID, + .arg2_type = ARG_CONST_MAP_PTR, + .arg3_type = ARG_ANYTHING, + .arg4_type = ARG_PTR_TO_MEM, + .arg5_type = ARG_CONST_SIZE_OR_ZERO, + .btf_id = bpf_skb_output_btf_ids, +}; + static unsigned short bpf_tunnel_key_af(u64 flags) { return flags & BPF_F_TUNINFO_IPV6 ? AF_INET6 : AF_INET; @@@ -4265,14 -4252,12 +4265,14 @@@ BPF_CALL_5(bpf_setsockopt, struct bpf_s case SO_RCVBUF: val = min_t(u32, val, sysctl_rmem_max); sk->sk_userlocks |= SOCK_RCVBUF_LOCK; - sk->sk_rcvbuf = max_t(int, val * 2, SOCK_MIN_RCVBUF); + WRITE_ONCE(sk->sk_rcvbuf, + max_t(int, val * 2, SOCK_MIN_RCVBUF)); break; case SO_SNDBUF: val = min_t(u32, val, sysctl_wmem_max); sk->sk_userlocks |= SOCK_SNDBUF_LOCK; - sk->sk_sndbuf = max_t(int, val * 2, SOCK_MIN_SNDBUF); + WRITE_ONCE(sk->sk_sndbuf, + max_t(int, val * 2, SOCK_MIN_SNDBUF)); break; case SO_MAX_PACING_RATE: /* 32bit version */ if (val != ~0U) @@@ -4289,7 -4274,7 +4289,7 @@@ case SO_RCVLOWAT: if (val < 0) val = INT_MAX; - sk->sk_rcvlowat = val ? : 1; + WRITE_ONCE(sk->sk_rcvlowat, val ? : 1); break; case SO_MARK: if (sk->sk_mark != val) { @@@ -5589,8 -5574,8 +5589,8 @@@ u32 bpf_tcp_sock_convert_ctx_access(enu

#define BPF_TCP_SOCK_GET_COMMON(FIELD) \ do { \ - BUILD_BUG_ON(FIELD_SIZEOF(struct tcp_sock, FIELD) > \ - FIELD_SIZEOF(struct bpf_tcp_sock, FIELD)); \ + BUILD_BUG_ON(sizeof_member(struct tcp_sock, FIELD) > \ + sizeof_member(struct bpf_tcp_sock, FIELD)); \ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct tcp_sock, FIELD),\ si->dst_reg, si->src_reg, \ offsetof(struct tcp_sock, FIELD)); \ @@@ -5598,9 -5583,9 +5598,9 @@@

#define BPF_INET_SOCK_GET_COMMON(FIELD) \ do { \ - BUILD_BUG_ON(FIELD_SIZEOF(struct inet_connection_sock, \ + BUILD_BUG_ON(sizeof_member(struct inet_connection_sock, \ FIELD) > \ - FIELD_SIZEOF(struct bpf_tcp_sock, FIELD)); \ + sizeof_member(struct bpf_tcp_sock, FIELD)); \ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( \ struct inet_connection_sock, \ FIELD), \ @@@ -5615,7 -5600,7 +5615,7 @@@

switch (si->off) { case offsetof(struct bpf_tcp_sock, rtt_min): - BUILD_BUG_ON(FIELD_SIZEOF(struct tcp_sock, rtt_min) != + BUILD_BUG_ON(sizeof_member(struct tcp_sock, rtt_min) != sizeof(struct minmax)); BUILD_BUG_ON(sizeof(struct minmax) < sizeof(struct minmax_sample)); @@@ -5780,8 -5765,8 +5780,8 @@@ u32 bpf_xdp_sock_convert_ctx_access(enu

#define BPF_XDP_SOCK_GET(FIELD) \ do { \ - BUILD_BUG_ON(FIELD_SIZEOF(struct xdp_sock, FIELD) > \ - FIELD_SIZEOF(struct bpf_xdp_sock, FIELD)); \ + BUILD_BUG_ON(sizeof_member(struct xdp_sock, FIELD) > \ + sizeof_member(struct bpf_xdp_sock, FIELD)); \ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct xdp_sock, FIELD),\ si->dst_reg, si->src_reg, \ offsetof(struct xdp_sock, FIELD)); \ @@@ -7344,7 -7329,7 +7344,7 @@@ static u32 bpf_convert_ctx_access(enum

case offsetof(struct __sk_buff, cb[0]) ... offsetofend(struct __sk_buff, cb[4]) - 1: - BUILD_BUG_ON(FIELD_SIZEOF(struct qdisc_skb_cb, data) < 20); + BUILD_BUG_ON(sizeof_member(struct qdisc_skb_cb, data) < 20); BUILD_BUG_ON((offsetof(struct sk_buff, cb) + offsetof(struct qdisc_skb_cb, data)) % sizeof(__u64)); @@@ -7363,7 -7348,7 +7363,7 @@@ break;

case offsetof(struct __sk_buff, tc_classid): - BUILD_BUG_ON(FIELD_SIZEOF(struct qdisc_skb_cb, tc_classid) != 2); + BUILD_BUG_ON(sizeof_member(struct qdisc_skb_cb, tc_classid) != 2);

off = si->off; off -= offsetof(struct __sk_buff, tc_classid); @@@ -7434,7 -7419,7 +7434,7 @@@ #endif break; case offsetof(struct __sk_buff, family): - BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, skc_family) != 2); + BUILD_BUG_ON(sizeof_member(struct sock_common, skc_family) != 2);

*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, sk), si->dst_reg, si->src_reg, @@@ -7445,7 -7430,7 +7445,7 @@@ 2, target_size)); break; case offsetof(struct __sk_buff, remote_ip4): - BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, skc_daddr) != 4); + BUILD_BUG_ON(sizeof_member(struct sock_common, skc_daddr) != 4);

*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, sk), si->dst_reg, si->src_reg, @@@ -7456,7 -7441,7 +7456,7 @@@ 4, target_size)); break; case offsetof(struct __sk_buff, local_ip4): - BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, + BUILD_BUG_ON(sizeof_member(struct sock_common, skc_rcv_saddr) != 4);

*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, sk), @@@ -7470,7 -7455,7 +7470,7 @@@ case offsetof(struct __sk_buff, remote_ip6[0]) ... offsetof(struct __sk_buff, remote_ip6[3]): #if IS_ENABLED(CONFIG_IPV6) - BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, + BUILD_BUG_ON(sizeof_member(struct sock_common, skc_v6_daddr.s6_addr32[0]) != 4);

off = si->off; @@@ -7490,7 -7475,7 +7490,7 @@@ case offsetof(struct __sk_buff, local_ip6[0]) ... offsetof(struct __sk_buff, local_ip6[3]): #if IS_ENABLED(CONFIG_IPV6) - BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, + BUILD_BUG_ON(sizeof_member(struct sock_common, skc_v6_rcv_saddr.s6_addr32[0]) != 4);

off = si->off; @@@ -7509,7 -7494,7 +7509,7 @@@ break;

case offsetof(struct __sk_buff, remote_port): - BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, skc_dport) != 2); + BUILD_BUG_ON(sizeof_member(struct sock_common, skc_dport) != 2);

*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, sk), si->dst_reg, si->src_reg, @@@ -7524,7 -7509,7 +7524,7 @@@ break;

case offsetof(struct __sk_buff, local_port): - BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, skc_num) != 2); + BUILD_BUG_ON(sizeof_member(struct sock_common, skc_num) != 2);

*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, sk), si->dst_reg, si->src_reg, @@@ -7535,7 -7520,7 +7535,7 @@@ break;

case offsetof(struct __sk_buff, tstamp): - BUILD_BUG_ON(FIELD_SIZEOF(struct sk_buff, tstamp) != 8); + BUILD_BUG_ON(sizeof_member(struct sk_buff, tstamp) != 8);

if (type == BPF_WRITE) *insn++ = BPF_STX_MEM(BPF_DW, @@@ -7573,7 -7558,7 +7573,7 @@@ target_size)); break; case offsetof(struct __sk_buff, wire_len): - BUILD_BUG_ON(FIELD_SIZEOF(struct qdisc_skb_cb, pkt_len) != 4); + BUILD_BUG_ON(sizeof_member(struct qdisc_skb_cb, pkt_len) != 4);

off = si->off; off -= offsetof(struct __sk_buff, wire_len); @@@ -7603,7 -7588,7 +7603,7 @@@ u32 bpf_sock_convert_ctx_access(enum bp

switch (si->off) { case offsetof(struct bpf_sock, bound_dev_if): - BUILD_BUG_ON(FIELD_SIZEOF(struct sock, sk_bound_dev_if) != 4); + BUILD_BUG_ON(sizeof_member(struct sock, sk_bound_dev_if) != 4);

if (type == BPF_WRITE) *insn++ = BPF_STX_MEM(BPF_W, si->dst_reg, si->src_reg, @@@ -7614,7 -7599,7 +7614,7 @@@ break;

case offsetof(struct bpf_sock, mark): - BUILD_BUG_ON(FIELD_SIZEOF(struct sock, sk_mark) != 4); + BUILD_BUG_ON(sizeof_member(struct sock, sk_mark) != 4);

if (type == BPF_WRITE) *insn++ = BPF_STX_MEM(BPF_W, si->dst_reg, si->src_reg, @@@ -7625,7 -7610,7 +7625,7 @@@ break;

case offsetof(struct bpf_sock, priority): - BUILD_BUG_ON(FIELD_SIZEOF(struct sock, sk_priority) != 4); + BUILD_BUG_ON(sizeof_member(struct sock, sk_priority) != 4);

if (type == BPF_WRITE) *insn++ = BPF_STX_MEM(BPF_W, si->dst_reg, si->src_reg, @@@ -7641,7 -7626,7 +7641,7 @@@ si->dst_reg, si->src_reg, bpf_target_off(struct sock_common, skc_family, - FIELD_SIZEOF(struct sock_common, + sizeof_member(struct sock_common, skc_family), target_size)); break; @@@ -7668,7 -7653,7 +7668,7 @@@ *insn++ = BPF_LDX_MEM( BPF_SIZE(si->code), si->dst_reg, si->src_reg, bpf_target_off(struct sock_common, skc_rcv_saddr, - FIELD_SIZEOF(struct sock_common, + sizeof_member(struct sock_common, skc_rcv_saddr), target_size)); break; @@@ -7677,7 -7662,7 +7677,7 @@@ *insn++ = BPF_LDX_MEM( BPF_SIZE(si->code), si->dst_reg, si->src_reg, bpf_target_off(struct sock_common, skc_daddr, - FIELD_SIZEOF(struct sock_common, + sizeof_member(struct sock_common, skc_daddr), target_size)); break; @@@ -7691,7 -7676,7 +7691,7 @@@ bpf_target_off( struct sock_common, skc_v6_rcv_saddr.s6_addr32[0], - FIELD_SIZEOF(struct sock_common, + sizeof_member(struct sock_common, skc_v6_rcv_saddr.s6_addr32[0]), target_size) + off); #else @@@ -7708,7 -7693,7 +7708,7 @@@ BPF_SIZE(si->code), si->dst_reg, si->src_reg, bpf_target_off(struct sock_common, skc_v6_daddr.s6_addr32[0], - FIELD_SIZEOF(struct sock_common, + sizeof_member(struct sock_common, skc_v6_daddr.s6_addr32[0]), target_size) + off); #else @@@ -7722,7 -7707,7 +7722,7 @@@ BPF_FIELD_SIZEOF(struct sock_common, skc_num), si->dst_reg, si->src_reg, bpf_target_off(struct sock_common, skc_num, - FIELD_SIZEOF(struct sock_common, + sizeof_member(struct sock_common, skc_num), target_size)); break; @@@ -7732,7 -7717,7 +7732,7 @@@ BPF_FIELD_SIZEOF(struct sock_common, skc_dport), si->dst_reg, si->src_reg, bpf_target_off(struct sock_common, skc_dport, - FIELD_SIZEOF(struct sock_common, + sizeof_member(struct sock_common, skc_dport), target_size)); break; @@@ -7742,7 -7727,7 +7742,7 @@@ BPF_FIELD_SIZEOF(struct sock_common, skc_state), si->dst_reg, si->src_reg, bpf_target_off(struct sock_common, skc_state, - FIELD_SIZEOF(struct sock_common, + sizeof_member(struct sock_common, skc_state), target_size)); break; @@@ -7837,7 -7822,7 +7837,7 @@@ static u32 xdp_convert_ctx_access(enum si->src_reg, offsetof(S, F)); \ *insn++ = BPF_LDX_MEM( \ SIZE, si->dst_reg, si->dst_reg, \ - bpf_target_off(NS, NF, FIELD_SIZEOF(NS, NF), \ + bpf_target_off(NS, NF, sizeof_member(NS, NF), \ target_size) \ + OFF); \ } while (0) @@@ -7868,7 -7853,7 +7868,7 @@@ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(S, F), tmp_reg, \ si->dst_reg, offsetof(S, F)); \ *insn++ = BPF_STX_MEM(SIZE, tmp_reg, si->src_reg, \ - bpf_target_off(NS, NF, FIELD_SIZEOF(NS, NF), \ + bpf_target_off(NS, NF, sizeof_member(NS, NF), \ target_size) \ + OFF); \ *insn++ = BPF_LDX_MEM(BPF_DW, tmp_reg, si->dst_reg, \ @@@ -7930,8 -7915,8 +7930,8 @@@ static u32 sock_addr_convert_ctx_access */ BUILD_BUG_ON(offsetof(struct sockaddr_in, sin_port) != offsetof(struct sockaddr_in6, sin6_port)); - BUILD_BUG_ON(FIELD_SIZEOF(struct sockaddr_in, sin_port) != - FIELD_SIZEOF(struct sockaddr_in6, sin6_port)); + BUILD_BUG_ON(sizeof_member(struct sockaddr_in, sin_port) != + sizeof_member(struct sockaddr_in6, sin6_port)); SOCK_ADDR_LOAD_OR_STORE_NESTED_FIELD(struct bpf_sock_addr_kern, struct sockaddr_in6, uaddr, sin6_port, tmp_reg); @@@ -7997,8 -7982,8 +7997,8 @@@ static u32 sock_ops_convert_ctx_access( /* Helper macro for adding read access to tcp_sock or sock fields. */ #define SOCK_OPS_GET_FIELD(BPF_FIELD, OBJ_FIELD, OBJ) \ do { \ - BUILD_BUG_ON(FIELD_SIZEOF(OBJ, OBJ_FIELD) > \ - FIELD_SIZEOF(struct bpf_sock_ops, BPF_FIELD)); \ + BUILD_BUG_ON(sizeof_member(OBJ, OBJ_FIELD) > \ + sizeof_member(struct bpf_sock_ops, BPF_FIELD)); \ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( \ struct bpf_sock_ops_kern, \ is_fullsock), \ @@@ -8031,8 -8016,8 +8031,8 @@@ #define SOCK_OPS_SET_FIELD(BPF_FIELD, OBJ_FIELD, OBJ) \ do { \ int reg = BPF_REG_9; \ - BUILD_BUG_ON(FIELD_SIZEOF(OBJ, OBJ_FIELD) > \ - FIELD_SIZEOF(struct bpf_sock_ops, BPF_FIELD)); \ + BUILD_BUG_ON(sizeof_member(OBJ, OBJ_FIELD) > \ + sizeof_member(struct bpf_sock_ops, BPF_FIELD)); \ if (si->dst_reg == reg || si->src_reg == reg) \ reg--; \ if (si->dst_reg == reg || si->src_reg == reg) \ @@@ -8073,12 -8058,12 +8073,12 @@@ switch (si->off) { case offsetof(struct bpf_sock_ops, op) ... offsetof(struct bpf_sock_ops, replylong[3]): - BUILD_BUG_ON(FIELD_SIZEOF(struct bpf_sock_ops, op) != - FIELD_SIZEOF(struct bpf_sock_ops_kern, op)); - BUILD_BUG_ON(FIELD_SIZEOF(struct bpf_sock_ops, reply) != - FIELD_SIZEOF(struct bpf_sock_ops_kern, reply)); - BUILD_BUG_ON(FIELD_SIZEOF(struct bpf_sock_ops, replylong) != - FIELD_SIZEOF(struct bpf_sock_ops_kern, replylong)); + BUILD_BUG_ON(sizeof_member(struct bpf_sock_ops, op) != + sizeof_member(struct bpf_sock_ops_kern, op)); + BUILD_BUG_ON(sizeof_member(struct bpf_sock_ops, reply) != + sizeof_member(struct bpf_sock_ops_kern, reply)); + BUILD_BUG_ON(sizeof_member(struct bpf_sock_ops, replylong) != + sizeof_member(struct bpf_sock_ops_kern, replylong)); off = si->off; off -= offsetof(struct bpf_sock_ops, op); off += offsetof(struct bpf_sock_ops_kern, op); @@@ -8091,7 -8076,7 +8091,7 @@@ break;

case offsetof(struct bpf_sock_ops, family): - BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, skc_family) != 2); + BUILD_BUG_ON(sizeof_member(struct sock_common, skc_family) != 2);

*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct bpf_sock_ops_kern, sk), @@@ -8102,7 -8087,7 +8102,7 @@@ break;

case offsetof(struct bpf_sock_ops, remote_ip4): - BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, skc_daddr) != 4); + BUILD_BUG_ON(sizeof_member(struct sock_common, skc_daddr) != 4);

*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct bpf_sock_ops_kern, sk), @@@ -8113,7 -8098,7 +8113,7 @@@ break;

case offsetof(struct bpf_sock_ops, local_ip4): - BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, + BUILD_BUG_ON(sizeof_member(struct sock_common, skc_rcv_saddr) != 4);

*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( @@@ -8128,7 -8113,7 +8128,7 @@@ case offsetof(struct bpf_sock_ops, remote_ip6[0]) ... offsetof(struct bpf_sock_ops, remote_ip6[3]): #if IS_ENABLED(CONFIG_IPV6) - BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, + BUILD_BUG_ON(sizeof_member(struct sock_common, skc_v6_daddr.s6_addr32[0]) != 4);

off = si->off; @@@ -8149,7 -8134,7 +8149,7 @@@ case offsetof(struct bpf_sock_ops, local_ip6[0]) ... offsetof(struct bpf_sock_ops, local_ip6[3]): #if IS_ENABLED(CONFIG_IPV6) - BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, + BUILD_BUG_ON(sizeof_member(struct sock_common, skc_v6_rcv_saddr.s6_addr32[0]) != 4);

off = si->off; @@@ -8168,7 -8153,7 +8168,7 @@@ break;

case offsetof(struct bpf_sock_ops, remote_port): - BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, skc_dport) != 2); + BUILD_BUG_ON(sizeof_member(struct sock_common, skc_dport) != 2);

*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct bpf_sock_ops_kern, sk), @@@ -8182,7 -8167,7 +8182,7 @@@ break;

case offsetof(struct bpf_sock_ops, local_port): - BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, skc_num) != 2); + BUILD_BUG_ON(sizeof_member(struct sock_common, skc_num) != 2);

*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct bpf_sock_ops_kern, sk), @@@ -8202,7 -8187,7 +8202,7 @@@ break;

case offsetof(struct bpf_sock_ops, state): - BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, skc_state) != 1); + BUILD_BUG_ON(sizeof_member(struct sock_common, skc_state) != 1);

*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct bpf_sock_ops_kern, sk), @@@ -8213,7 -8198,7 +8213,7 @@@ break;

case offsetof(struct bpf_sock_ops, rtt_min): - BUILD_BUG_ON(FIELD_SIZEOF(struct tcp_sock, rtt_min) != + BUILD_BUG_ON(sizeof_member(struct tcp_sock, rtt_min) != sizeof(struct minmax)); BUILD_BUG_ON(sizeof(struct minmax) < sizeof(struct minmax_sample)); @@@ -8224,7 -8209,7 +8224,7 @@@ offsetof(struct bpf_sock_ops_kern, sk)); *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->dst_reg, offsetof(struct tcp_sock, rtt_min) + - FIELD_SIZEOF(struct minmax_sample, t)); + sizeof_member(struct minmax_sample, t)); break;

case offsetof(struct bpf_sock_ops, bpf_sock_ops_cb_flags): @@@ -8366,7 -8351,7 +8366,7 @@@ static u32 sk_msg_convert_ctx_access(en offsetof(struct sk_msg, data_end)); break; case offsetof(struct sk_msg_md, family): - BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, skc_family) != 2); + BUILD_BUG_ON(sizeof_member(struct sock_common, skc_family) != 2);

*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct sk_msg, sk), @@@ -8377,7 -8362,7 +8377,7 @@@ break;

case offsetof(struct sk_msg_md, remote_ip4): - BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, skc_daddr) != 4); + BUILD_BUG_ON(sizeof_member(struct sock_common, skc_daddr) != 4);

*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct sk_msg, sk), @@@ -8388,7 -8373,7 +8388,7 @@@ break;

case offsetof(struct sk_msg_md, local_ip4): - BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, + BUILD_BUG_ON(sizeof_member(struct sock_common, skc_rcv_saddr) != 4);

*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( @@@ -8403,7 -8388,7 +8403,7 @@@ case offsetof(struct sk_msg_md, remote_ip6[0]) ... offsetof(struct sk_msg_md, remote_ip6[3]): #if IS_ENABLED(CONFIG_IPV6) - BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, + BUILD_BUG_ON(sizeof_member(struct sock_common, skc_v6_daddr.s6_addr32[0]) != 4);

off = si->off; @@@ -8424,7 -8409,7 +8424,7 @@@ case offsetof(struct sk_msg_md, local_ip6[0]) ... offsetof(struct sk_msg_md, local_ip6[3]): #if IS_ENABLED(CONFIG_IPV6) - BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, + BUILD_BUG_ON(sizeof_member(struct sock_common, skc_v6_rcv_saddr.s6_addr32[0]) != 4);

off = si->off; @@@ -8443,7 -8428,7 +8443,7 @@@ break;

case offsetof(struct sk_msg_md, remote_port): - BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, skc_dport) != 2); + BUILD_BUG_ON(sizeof_member(struct sock_common, skc_dport) != 2);

*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct sk_msg, sk), @@@ -8457,7 -8442,7 +8457,7 @@@ break;

case offsetof(struct sk_msg_md, local_port): - BUILD_BUG_ON(FIELD_SIZEOF(struct sock_common, skc_num) != 2); + BUILD_BUG_ON(sizeof_member(struct sock_common, skc_num) != 2);

*insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF( struct sk_msg, sk), @@@ -8857,7 -8842,7 +8857,7 @@@ sk_reuseport_is_valid_access(int off, i

/* Fields that allow narrowing */ case bpf_ctx_range(struct sk_reuseport_md, eth_protocol): - if (size < FIELD_SIZEOF(struct sk_buff, protocol)) + if (size < sizeof_member(struct sk_buff, protocol)) return false; /* fall through */ case bpf_ctx_range(struct sk_reuseport_md, ip_protocol): @@@ -8875,7 -8860,7 +8875,7 @@@ *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_reuseport_kern, F), \ si->dst_reg, si->src_reg, \ bpf_target_off(struct sk_reuseport_kern, F, \ - FIELD_SIZEOF(struct sk_reuseport_kern, F), \ + sizeof_member(struct sk_reuseport_kern, F), \ target_size)); \ })

diff --combined net/core/flow_dissector.c index 9a14b19c008f,3f5f61bc2bfa..57b884717851 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@@ -114,50 -114,19 +114,50 @@@ int skb_flow_dissector_bpf_prog_attach( { struct bpf_prog *attached; struct net *net; + int ret = 0;

net = current->nsproxy->net_ns; mutex_lock(&flow_dissector_mutex); + + if (net == &init_net) { + /* BPF flow dissector in the root namespace overrides + * any per-net-namespace one. When attaching to root, + * make sure we don't have any BPF program attached + * to the non-root namespaces. + */ + struct net *ns; + + for_each_net(ns) { + if (ns == &init_net) + continue; + if (rcu_access_pointer(ns->flow_dissector_prog)) { + ret = -EEXIST; + goto out; + } + } + } else { + /* Make sure root flow dissector is not attached + * when attaching to the non-root namespace. + */ + if (rcu_access_pointer(init_net.flow_dissector_prog)) { + ret = -EEXIST; + goto out; + } + } + attached = rcu_dereference_protected(net->flow_dissector_prog, lockdep_is_held(&flow_dissector_mutex)); - if (attached) { - /* Only one BPF program can be attached at a time */ - mutex_unlock(&flow_dissector_mutex); - return -EEXIST; + if (attached == prog) { + /* The same program cannot be attached twice */ + ret = -EINVAL; + goto out; } rcu_assign_pointer(net->flow_dissector_prog, prog); + if (attached) + bpf_prog_put(attached); +out: mutex_unlock(&flow_dissector_mutex); - return 0; + return ret; }

int skb_flow_dissector_bpf_prog_detach(const union bpf_attr *attr) @@@ -554,8 -523,8 +554,8 @@@ __skb_flow_dissect_gre(const struct sk_ offset += sizeof(struct gre_base_hdr);

if (hdr->flags & GRE_CSUM) - offset += FIELD_SIZEOF(struct gre_full_hdr, csum) + - FIELD_SIZEOF(struct gre_full_hdr, reserved1); + offset += sizeof_member(struct gre_full_hdr, csum) + + sizeof_member(struct gre_full_hdr, reserved1);

if (hdr->flags & GRE_KEY) { const __be32 *keyid; @@@ -577,11 -546,11 +577,11 @@@ else key_keyid->keyid = *keyid & GRE_PPTP_KEY_MASK; } - offset += FIELD_SIZEOF(struct gre_full_hdr, key); + offset += sizeof_member(struct gre_full_hdr, key); }

if (hdr->flags & GRE_SEQ) - offset += FIELD_SIZEOF(struct pptp_gre_header, seq); + offset += sizeof_member(struct pptp_gre_header, seq);

if (gre_ver == 0) { if (*p_proto == htons(ETH_P_TEB)) { @@@ -608,7 -577,7 +608,7 @@@ u8 *ppp_hdr;

if (hdr->flags & GRE_ACK) - offset += FIELD_SIZEOF(struct pptp_gre_header, ack); + offset += sizeof_member(struct pptp_gre_header, ack);

ppp_hdr = __skb_header_pointer(skb, *p_nhoff + offset, sizeof(_ppp_hdr), @@@ -941,10 -910,7 +941,10 @@@ bool __skb_flow_dissect(const struct ne WARN_ON_ONCE(!net); if (net) { rcu_read_lock(); - attached = rcu_dereference(net->flow_dissector_prog); + attached = rcu_dereference(init_net.flow_dissector_prog); + + if (!attached) + attached = rcu_dereference(net->flow_dissector_prog);

if (attached) { struct bpf_flow_keys flow_keys; @@@ -1384,21 -1350,30 +1384,21 @@@ out_bad } EXPORT_SYMBOL(__skb_flow_dissect);

-static u32 hashrnd __read_mostly; +static siphash_key_t hashrnd __read_mostly; static __always_inline void __flow_hash_secret_init(void) { net_get_random_once(&hashrnd, sizeof(hashrnd)); }

-static __always_inline u32 __flow_hash_words(const u32 *words, u32 length, - u32 keyval) +static const void *flow_keys_hash_start(const struct flow_keys *flow) { - return jhash2(words, length, keyval); -} - -static inline const u32 *flow_keys_hash_start(const struct flow_keys *flow) -{ - const void *p = flow; - - BUILD_BUG_ON(FLOW_KEYS_HASH_OFFSET % sizeof(u32)); - return (const u32 *)(p + FLOW_KEYS_HASH_OFFSET); + BUILD_BUG_ON(FLOW_KEYS_HASH_OFFSET % SIPHASH_ALIGNMENT); + return &flow->FLOW_KEYS_HASH_START_FIELD; }

static inline size_t flow_keys_hash_length(const struct flow_keys *flow) { size_t diff = FLOW_KEYS_HASH_OFFSET + sizeof(flow->addrs); - BUILD_BUG_ON((sizeof(*flow) - FLOW_KEYS_HASH_OFFSET) % sizeof(u32)); BUILD_BUG_ON(offsetof(typeof(*flow), addrs) != sizeof(*flow) - sizeof(flow->addrs));

@@@ -1413,7 -1388,7 +1413,7 @@@ diff -= sizeof(flow->addrs.tipckey); break; } - return (sizeof(*flow) - diff) / sizeof(u32); + return sizeof(*flow) - diff; }

__be32 flow_get_u32_src(const struct flow_keys *flow) @@@ -1479,15 -1454,14 +1479,15 @@@ static inline void __flow_hash_consiste } }

-static inline u32 __flow_hash_from_keys(struct flow_keys *keys, u32 keyval) +static inline u32 __flow_hash_from_keys(struct flow_keys *keys, + const siphash_key_t *keyval) { u32 hash;

__flow_hash_consistentify(keys);

- hash = __flow_hash_words(flow_keys_hash_start(keys), - flow_keys_hash_length(keys), keyval); + hash = siphash(flow_keys_hash_start(keys), + flow_keys_hash_length(keys), keyval); if (!hash) hash = 1;

@@@ -1497,13 -1471,12 +1497,13 @@@ u32 flow_hash_from_keys(struct flow_keys *keys) { __flow_hash_secret_init(); - return __flow_hash_from_keys(keys, hashrnd); + return __flow_hash_from_keys(keys, &hashrnd); } EXPORT_SYMBOL(flow_hash_from_keys);

static inline u32 ___skb_get_hash(const struct sk_buff *skb, - struct flow_keys *keys, u32 keyval) + struct flow_keys *keys, + const siphash_key_t *keyval) { skb_flow_dissect_flow_keys(skb, keys, FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL); @@@ -1551,7 -1524,7 +1551,7 @@@ u32 __skb_get_hash_symmetric(const stru &keys, NULL, 0, 0, 0, FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL);

- return __flow_hash_from_keys(&keys, hashrnd); + return __flow_hash_from_keys(&keys, &hashrnd); } EXPORT_SYMBOL_GPL(__skb_get_hash_symmetric);

@@@ -1571,14 -1544,13 +1571,14 @@@ void __skb_get_hash(struct sk_buff *skb

__flow_hash_secret_init();

- hash = ___skb_get_hash(skb, &keys, hashrnd); + hash = ___skb_get_hash(skb, &keys, &hashrnd);

__skb_set_sw_hash(skb, hash, flow_keys_have_l4(&keys)); } EXPORT_SYMBOL(__skb_get_hash);

-__u32 skb_get_hash_perturb(const struct sk_buff *skb, u32 perturb) +__u32 skb_get_hash_perturb(const struct sk_buff *skb, + const siphash_key_t *perturb) { struct flow_keys keys;

diff --combined net/core/skbuff.c index 867e61df00db,6054465875d8..31b8539c72c1 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@@ -4148,7 -4148,7 +4148,7 @@@ void __init skb_init(void 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, offsetof(struct sk_buff, cb), - sizeof_field(struct sk_buff, cb), + sizeof_member(struct sk_buff, cb), NULL); skbuff_fclone_cache = kmem_cache_create("skbuff_fclone_cache", sizeof(struct sk_buff_fclones), @@@ -4415,7 -4415,7 +4415,7 @@@ static void skb_set_err_queue(struct sk int sock_queue_err_skb(struct sock *sk, struct sk_buff *skb) { if (atomic_read(&sk->sk_rmem_alloc) + skb->truesize >= - (unsigned int)sk->sk_rcvbuf) + (unsigned int)READ_ONCE(sk->sk_rcvbuf)) return -ENOMEM;

skb_orphan(skb); @@@ -5477,14 -5477,12 +5477,14 @@@ static void skb_mod_eth_type(struct sk_ * @skb: buffer * @mpls_lse: MPLS label stack entry to push * @mpls_proto: ethertype of the new MPLS header (expects 0x8847 or 0x8848) + * @mac_len: length of the MAC header * * Expects skb->data at mac header. * * Returns 0 on success, -errno otherwise. */ -int skb_mpls_push(struct sk_buff *skb, __be32 mpls_lse, __be16 mpls_proto) +int skb_mpls_push(struct sk_buff *skb, __be32 mpls_lse, __be16 mpls_proto, + int mac_len) { struct mpls_shim_hdr *lse; int err; @@@ -5501,15 -5499,15 +5501,15 @@@ return err;

if (!skb->inner_protocol) { - skb_set_inner_network_header(skb, skb->mac_len); + skb_set_inner_network_header(skb, mac_len); skb_set_inner_protocol(skb, skb->protocol); }

skb_push(skb, MPLS_HLEN); memmove(skb_mac_header(skb) - MPLS_HLEN, skb_mac_header(skb), - skb->mac_len); + mac_len); skb_reset_mac_header(skb); - skb_set_network_header(skb, skb->mac_len); + skb_set_network_header(skb, mac_len);

lse = mpls_hdr(skb); lse->label_stack_entry = mpls_lse; @@@ -5528,30 -5526,29 +5528,30 @@@ EXPORT_SYMBOL_GPL(skb_mpls_push) * * @skb: buffer * @next_proto: ethertype of header after popped MPLS header + * @mac_len: length of the MAC header * * Expects skb->data at mac header. * * Returns 0 on success, -errno otherwise. */ -int skb_mpls_pop(struct sk_buff *skb, __be16 next_proto) +int skb_mpls_pop(struct sk_buff *skb, __be16 next_proto, int mac_len) { int err;

if (unlikely(!eth_p_mpls(skb->protocol))) - return -EINVAL; + return 0;

- err = skb_ensure_writable(skb, skb->mac_len + MPLS_HLEN); + err = skb_ensure_writable(skb, mac_len + MPLS_HLEN); if (unlikely(err)) return err;

skb_postpull_rcsum(skb, mpls_hdr(skb), MPLS_HLEN); memmove(skb_mac_header(skb) + MPLS_HLEN, skb_mac_header(skb), - skb->mac_len); + mac_len);

__skb_pull(skb, MPLS_HLEN); skb_reset_mac_header(skb); - skb_set_network_header(skb, skb->mac_len); + skb_set_network_header(skb, mac_len);

if (skb->dev && skb->dev->type == ARPHRD_ETHER) { struct ethhdr *hdr; diff --combined net/core/xdp.c index 20781ad5f9c3,621d6148b07a..cb6cc14c6455 --- a/net/core/xdp.c +++ b/net/core/xdp.c @@@ -36,7 -36,7 +36,7 @@@ static u32 xdp_mem_id_hashfn(const voi const u32 *k = data; const u32 key = *k;

- BUILD_BUG_ON(FIELD_SIZEOF(struct xdp_mem_allocator, mem.id) + BUILD_BUG_ON(sizeof_member(struct xdp_mem_allocator, mem.id) != sizeof(u32));

/* Use cyclic increasing ID as direct hash key */ @@@ -56,7 -56,7 +56,7 @@@ static const struct rhashtable_params m .nelem_hint = 64, .head_offset = offsetof(struct xdp_mem_allocator, node), .key_offset = offsetof(struct xdp_mem_allocator, mem.id), - .key_len = FIELD_SIZEOF(struct xdp_mem_allocator, mem.id), + .key_len = sizeof_member(struct xdp_mem_allocator, mem.id), .max_size = MEM_ID_MAX, .min_size = 8, .automatic_shrinking = true, @@@ -386,7 -386,7 +386,7 @@@ EXPORT_SYMBOL_GPL(xdp_rxq_info_reg_mem_

/* XDP RX runs under NAPI protection, and in different delivery error * scenarios (e.g. queue full), it is possible to return the xdp_frame - * while still leveraging this protection. The @napi_direct boolian + * while still leveraging this protection. The @napi_direct boolean * is used for those calls sites. Thus, allowing for faster recycling * of xdp_frames/pages in those cases. */ diff --combined net/ipv4/ip_gre.c index 10636fb6093e,9c9716f7ccdb..eabd38be7d43 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@@ -509,9 -509,9 +509,9 @@@ static void erspan_fb_xmit(struct sk_bu key = &tun_info->key; if (!(tun_info->key.tun_flags & TUNNEL_ERSPAN_OPT)) goto err_free_skb; - md = ip_tunnel_info_opts(tun_info); - if (!md) + if (tun_info->options_len < sizeof(*md)) goto err_free_skb; + md = ip_tunnel_info_opts(tun_info);

/* ERSPAN has fixed 8 byte GRE header */ version = md->version; @@@ -1460,8 -1460,8 +1460,8 @@@ static const struct nla_policy ipgre_po [IFLA_GRE_OFLAGS] = { .type = NLA_U16 }, [IFLA_GRE_IKEY] = { .type = NLA_U32 }, [IFLA_GRE_OKEY] = { .type = NLA_U32 }, - [IFLA_GRE_LOCAL] = { .len = FIELD_SIZEOF(struct iphdr, saddr) }, - [IFLA_GRE_REMOTE] = { .len = FIELD_SIZEOF(struct iphdr, daddr) }, + [IFLA_GRE_LOCAL] = { .len = sizeof_member(struct iphdr, saddr) }, + [IFLA_GRE_REMOTE] = { .len = sizeof_member(struct iphdr, daddr) }, [IFLA_GRE_TTL] = { .type = NLA_U8 }, [IFLA_GRE_TOS] = { .type = NLA_U8 }, [IFLA_GRE_PMTUDISC] = { .type = NLA_U8 }, diff --combined net/ipv4/tcp.c index 1dd25189d83f,7d23503a1d2d..82ba960747b2 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@@ -326,7 -326,7 +326,7 @@@ void tcp_enter_memory_pressure(struct s { unsigned long val;

- if (tcp_memory_pressure) + if (READ_ONCE(tcp_memory_pressure)) return; val = jiffies;

@@@ -341,7 -341,7 +341,7 @@@ void tcp_leave_memory_pressure(struct s { unsigned long val;

- if (!tcp_memory_pressure) + if (!READ_ONCE(tcp_memory_pressure)) return; val = xchg(&tcp_memory_pressure, 0); if (val) @@@ -450,8 -450,8 +450,8 @@@ void tcp_init_sock(struct sock *sk

icsk->icsk_sync_mss = tcp_sync_mss;

- sk->sk_sndbuf = sock_net(sk)->ipv4.sysctl_tcp_wmem[1]; - sk->sk_rcvbuf = sock_net(sk)->ipv4.sysctl_tcp_rmem[1]; + WRITE_ONCE(sk->sk_sndbuf, sock_net(sk)->ipv4.sysctl_tcp_wmem[1]); + WRITE_ONCE(sk->sk_rcvbuf, sock_net(sk)->ipv4.sysctl_tcp_rmem[1]);

sk_sockets_allocated_inc(sk); sk->sk_route_forced_caps = NETIF_F_GSO; @@@ -477,7 -477,7 +477,7 @@@ static void tcp_tx_timestamp(struct soc static inline bool tcp_stream_is_readable(const struct tcp_sock *tp, int target, struct sock *sk) { - return (tp->rcv_nxt - tp->copied_seq >= target) || + return (READ_ONCE(tp->rcv_nxt) - READ_ONCE(tp->copied_seq) >= target) || (sk->sk_prot->stream_memory_read ? sk->sk_prot->stream_memory_read(sk) : false); } @@@ -543,10 -543,10 +543,10 @@@ __poll_t tcp_poll(struct file *file, st

/* Connected or passive Fast Open socket? */ if (state != TCP_SYN_SENT && - (state != TCP_SYN_RECV || tp->fastopen_rsk)) { + (state != TCP_SYN_RECV || rcu_access_pointer(tp->fastopen_rsk))) { int target = sock_rcvlowat(sk, 0, INT_MAX);

- if (tp->urg_seq == tp->copied_seq && + if (READ_ONCE(tp->urg_seq) == READ_ONCE(tp->copied_seq) && !sock_flag(sk, SOCK_URGINLINE) && tp->urg_data) target++; @@@ -584,7 -584,7 +584,7 @@@ } /* This barrier is coupled with smp_wmb() in tcp_reset() */ smp_rmb(); - if (sk->sk_err || !skb_queue_empty(&sk->sk_error_queue)) + if (sk->sk_err || !skb_queue_empty_lockless(&sk->sk_error_queue)) mask |= EPOLLERR;

return mask; @@@ -607,8 -607,7 +607,8 @@@ int tcp_ioctl(struct sock *sk, int cmd unlock_sock_fast(sk, slow); break; case SIOCATMARK: - answ = tp->urg_data && tp->urg_seq == tp->copied_seq; + answ = tp->urg_data && + READ_ONCE(tp->urg_seq) == READ_ONCE(tp->copied_seq); break; case SIOCOUTQ: if (sk->sk_state == TCP_LISTEN) @@@ -617,7 -616,7 +617,7 @@@ if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) answ = 0; else - answ = tp->write_seq - tp->snd_una; + answ = READ_ONCE(tp->write_seq) - tp->snd_una; break; case SIOCOUTQNSD: if (sk->sk_state == TCP_LISTEN) @@@ -626,8 -625,7 +626,8 @@@ if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) answ = 0; else - answ = tp->write_seq - tp->snd_nxt; + answ = READ_ONCE(tp->write_seq) - + READ_ONCE(tp->snd_nxt); break; default: return -ENOIOCTLCMD; @@@ -659,7 -657,7 +659,7 @@@ static void skb_entail(struct sock *sk tcb->sacked = 0; __skb_header_release(skb); tcp_add_write_queue_tail(sk, skb); - sk->sk_wmem_queued += skb->truesize; + sk_wmem_queued_add(sk, skb->truesize); sk_mem_charge(sk, skb->truesize); if (tp->nonagle & TCP_NAGLE_PUSH) tp->nonagle &= ~TCP_NAGLE_PUSH; @@@ -1034,10 -1032,10 +1034,10 @@@ new_segment skb->len += copy; skb->data_len += copy; skb->truesize += copy; - sk->sk_wmem_queued += copy; + sk_wmem_queued_add(sk, copy); sk_mem_charge(sk, copy); skb->ip_summed = CHECKSUM_PARTIAL; - tp->write_seq += copy; + WRITE_ONCE(tp->write_seq, tp->write_seq + copy); TCP_SKB_CB(skb)->end_seq += copy; tcp_skb_pcount_set(skb, 0);

@@@ -1364,7 -1362,7 +1364,7 @@@ new_segment if (!copied) TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_PSH;

- tp->write_seq += copy; + WRITE_ONCE(tp->write_seq, tp->write_seq + copy); TCP_SKB_CB(skb)->end_seq += copy; tcp_skb_pcount_set(skb, 0);

@@@ -1670,9 -1668,9 +1670,9 @@@ int tcp_read_sock(struct sock *sk, read sk_eat_skb(sk, skb); if (!desc->count) break; - tp->copied_seq = seq; + WRITE_ONCE(tp->copied_seq, seq); } - tp->copied_seq = seq; + WRITE_ONCE(tp->copied_seq, seq);

tcp_rcv_space_adjust(sk);

@@@ -1701,7 -1699,7 +1701,7 @@@ int tcp_set_rcvlowat(struct sock *sk, i else cap = sock_net(sk)->ipv4.sysctl_tcp_rmem[2] >> 1; val = min(val, cap); - sk->sk_rcvlowat = val ? : 1; + WRITE_ONCE(sk->sk_rcvlowat, val ? : 1);

/* Check if we need to signal EPOLLIN right now */ tcp_data_ready(sk); @@@ -1711,7 -1709,7 +1711,7 @@@

val <<= 1; if (val > sk->sk_rcvbuf) { - sk->sk_rcvbuf = val; + WRITE_ONCE(sk->sk_rcvbuf, val); tcp_sk(sk)->window_clamp = tcp_win_from_space(sk, val); } return 0; @@@ -1741,8 -1739,8 +1741,8 @@@ static int tcp_zerocopy_receive(struct struct tcp_zerocopy_receive *zc) { unsigned long address = (unsigned long)zc->address; + u32 length = 0, seq, offset, zap_len; const skb_frag_t *frags = NULL; - u32 length = 0, seq, offset; struct vm_area_struct *vma; struct sk_buff *skb = NULL; struct tcp_sock *tp; @@@ -1769,12 -1767,12 +1769,12 @@@ seq = tp->copied_seq; inq = tcp_inq(sk); zc->length = min_t(u32, zc->length, inq); - zc->length &= ~(PAGE_SIZE - 1); - if (zc->length) { - zap_page_range(vma, address, zc->length); + zap_len = zc->length & ~(PAGE_SIZE - 1); + if (zap_len) { + zap_page_range(vma, address, zap_len); zc->recv_skip_hint = 0; } else { - zc->recv_skip_hint = inq; + zc->recv_skip_hint = zc->length; } ret = 0; while (length + PAGE_SIZE <= zc->length) { @@@ -1821,7 -1819,7 +1821,7 @@@ out: up_read(&current->mm->mmap_sem); if (length) { - tp->copied_seq = seq; + WRITE_ONCE(tp->copied_seq, seq); tcp_rcv_space_adjust(sk);

/* Clean up data we have read: This will do ACK frames. */ @@@ -1964,7 -1962,7 +1964,7 @@@ int tcp_recvmsg(struct sock *sk, struc if (unlikely(flags & MSG_ERRQUEUE)) return inet_recv_error(sk, msg, len, addr_len);

- if (sk_can_busy_loop(sk) && skb_queue_empty(&sk->sk_receive_queue) && + if (sk_can_busy_loop(sk) && skb_queue_empty_lockless(&sk->sk_receive_queue) && (sk->sk_state == TCP_ESTABLISHED)) sk_busy_loop(sk, nonblock);

@@@ -2119,7 -2117,7 +2119,7 @@@ found_ok_skb if (urg_offset < used) { if (!urg_offset) { if (!sock_flag(sk, SOCK_URGINLINE)) { - ++*seq; + WRITE_ONCE(*seq, *seq + 1); urg_hole++; offset++; used--; @@@ -2141,7 -2139,7 +2141,7 @@@ } }

- *seq += used; + WRITE_ONCE(*seq, *seq + used); copied += used; len -= used;

@@@ -2168,7 -2166,7 +2168,7 @@@ skip_copy

found_fin_ok: /* Process the FIN. */ - ++*seq; + WRITE_ONCE(*seq, *seq + 1); if (!(flags & MSG_PEEK)) sk_eat_skb(sk, skb); break; @@@ -2489,10 -2487,7 +2489,10 @@@ adjudge_to_death }

if (sk->sk_state == TCP_CLOSE) { - struct request_sock *req = tcp_sk(sk)->fastopen_rsk; + struct request_sock *req; + + req = rcu_dereference_protected(tcp_sk(sk)->fastopen_rsk, + lockdep_sock_is_held(sk)); /* We could get here with a non-NULL req if the socket is * aborted (e.g., closed with unread data) before 3WHS * finishes. @@@ -2564,7 -2559,6 +2564,7 @@@ int tcp_disconnect(struct sock *sk, in struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); int old_state = sk->sk_state; + u32 seq;

if (old_state != TCP_CLOSE) tcp_set_state(sk, TCP_CLOSE); @@@ -2591,7 -2585,7 +2591,7 @@@ __kfree_skb(sk->sk_rx_skb_cache); sk->sk_rx_skb_cache = NULL; } - tp->copied_seq = tp->rcv_nxt; + WRITE_ONCE(tp->copied_seq, tp->rcv_nxt); tp->urg_data = 0; tcp_write_queue_purge(sk); tcp_fastopen_active_disable_ofo_check(sk); @@@ -2607,12 -2601,9 +2607,12 @@@ tp->srtt_us = 0; tp->mdev_us = jiffies_to_usecs(TCP_TIMEOUT_INIT); tp->rcv_rtt_last_tsecr = 0; - tp->write_seq += tp->max_window + 2; - if (tp->write_seq == 0) - tp->write_seq = 1; + + seq = tp->write_seq + tp->max_window + 2; + if (!seq) + seq = 1; + WRITE_ONCE(tp->write_seq, seq); + icsk->icsk_backoff = 0; tp->snd_cwnd = 2; icsk->icsk_probes_out = 0; @@@ -2666,7 -2657,6 +2666,7 @@@ /* Clean up fastopen related fields */ tcp_free_fastopen_req(tp); inet->defer_connect = 0; + tp->fastopen_client_fail = 0;

WARN_ON(inet->inet_num && !icsk->icsk_bind_hash);

@@@ -2940,9 -2930,9 +2940,9 @@@ static int do_tcp_setsockopt(struct soc if (sk->sk_state != TCP_CLOSE) err = -EPERM; else if (tp->repair_queue == TCP_SEND_QUEUE) - tp->write_seq = val; + WRITE_ONCE(tp->write_seq, val); else if (tp->repair_queue == TCP_RECV_QUEUE) - tp->rcv_nxt = val; + WRITE_ONCE(tp->rcv_nxt, val); else err = -EINVAL; break; @@@ -3306,7 -3296,6 +3306,7 @@@ void tcp_get_info(struct sock *sk, stru info->tcpi_reord_seen = tp->reord_seen; info->tcpi_rcv_ooopack = tp->rcv_ooopack; info->tcpi_snd_wnd = tp->snd_wnd; + info->tcpi_fastopen_client_fail = tp->fastopen_client_fail; unlock_sock_fast(sk, slow); } EXPORT_SYMBOL_GPL(tcp_get_info); @@@ -3842,13 -3831,7 +3842,13 @@@ EXPORT_SYMBOL(tcp_md5_hash_key)

void tcp_done(struct sock *sk) { - struct request_sock *req = tcp_sk(sk)->fastopen_rsk; + struct request_sock *req; + + /* We might be called with a new socket, after + * inet_csk_prepare_forced_close() has been called + * so we can not use lockdep_sock_is_held(sk) + */ + req = rcu_dereference_protected(tcp_sk(sk)->fastopen_rsk, 1);

if (sk->sk_state == TCP_SYN_SENT || sk->sk_state == TCP_SYN_RECV) TCP_INC_STATS(sock_net(sk), TCP_MIB_ATTEMPTFAILS); @@@ -3947,7 -3930,7 +3947,7 @@@ void __init tcp_init(void

BUILD_BUG_ON(TCP_MIN_SND_MSS <= MAX_TCP_OPTION_SPACE); BUILD_BUG_ON(sizeof(struct tcp_skb_cb) > - FIELD_SIZEOF(struct sk_buff, cb)); + sizeof_member(struct sk_buff, cb));

percpu_counter_init(&tcp_sockets_allocated, 0, GFP_KERNEL); percpu_counter_init(&tcp_orphan_count, 0, GFP_KERNEL); diff --combined net/ipv6/ip6_gre.c index 923034c52ce4,be1a8c823b2a..f20561b7f667 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@@ -980,9 -980,9 +980,9 @@@ static netdev_tx_t ip6erspan_tunnel_xmi dsfield = key->tos; if (!(tun_info->key.tun_flags & TUNNEL_ERSPAN_OPT)) goto tx_err; - md = ip_tunnel_info_opts(tun_info); - if (!md) + if (tun_info->options_len < sizeof(*md)) goto tx_err; + md = ip_tunnel_info_opts(tun_info);

tun_id = tunnel_id_to_key32(key->tun_id); if (md->version == 1) { @@@ -2170,8 -2170,8 +2170,8 @@@ static const struct nla_policy ip6gre_p [IFLA_GRE_OFLAGS] = { .type = NLA_U16 }, [IFLA_GRE_IKEY] = { .type = NLA_U32 }, [IFLA_GRE_OKEY] = { .type = NLA_U32 }, - [IFLA_GRE_LOCAL] = { .len = FIELD_SIZEOF(struct ipv6hdr, saddr) }, - [IFLA_GRE_REMOTE] = { .len = FIELD_SIZEOF(struct ipv6hdr, daddr) }, + [IFLA_GRE_LOCAL] = { .len = sizeof_member(struct ipv6hdr, saddr) }, + [IFLA_GRE_REMOTE] = { .len = sizeof_member(struct ipv6hdr, daddr) }, [IFLA_GRE_TTL] = { .type = NLA_U8 }, [IFLA_GRE_ENCAP_LIMIT] = { .type = NLA_U8 }, [IFLA_GRE_FLOWINFO] = { .type = NLA_U32 }, @@@ -2192,7 -2192,6 +2192,7 @@@ static void ip6erspan_tap_setup(struct { ether_setup(dev);

+ dev->max_mtu = 0; dev->netdev_ops = &ip6erspan_netdev_ops; dev->needs_free_netdev = true; dev->priv_destructor = ip6gre_dev_free; diff --combined net/netfilter/nf_tables_api.c index 8f1e8c6a5cfd,ec252362d2ab..fa2574fc444e --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@@ -151,64 -151,11 +151,64 @@@ static void nft_set_trans_bind(const st } }

+static int nft_netdev_register_hooks(struct net *net, + struct list_head *hook_list) +{ + struct nft_hook *hook; + int err, j; + + j = 0; + list_for_each_entry(hook, hook_list, list) { + err = nf_register_net_hook(net, &hook->ops); + if (err < 0) + goto err_register; + + j++; + } + return 0; + +err_register: + list_for_each_entry(hook, hook_list, list) { + if (j-- <= 0) + break; + + nf_unregister_net_hook(net, &hook->ops); + } + return err; +} + +static void nft_netdev_unregister_hooks(struct net *net, + struct list_head *hook_list) +{ + struct nft_hook *hook; + + list_for_each_entry(hook, hook_list, list) + nf_unregister_net_hook(net, &hook->ops); +} + +static int nft_register_basechain_hooks(struct net *net, int family, + struct nft_base_chain *basechain) +{ + if (family == NFPROTO_NETDEV) + return nft_netdev_register_hooks(net, &basechain->hook_list); + + return nf_register_net_hook(net, &basechain->ops); +} + +static void nft_unregister_basechain_hooks(struct net *net, int family, + struct nft_base_chain *basechain) +{ + if (family == NFPROTO_NETDEV) + nft_netdev_unregister_hooks(net, &basechain->hook_list); + else + nf_unregister_net_hook(net, &basechain->ops); +} + static int nf_tables_register_hook(struct net *net, const struct nft_table *table, struct nft_chain *chain) { - const struct nft_base_chain *basechain; + struct nft_base_chain *basechain; const struct nf_hook_ops *ops;

if (table->flags & NFT_TABLE_F_DORMANT || @@@ -221,14 -168,14 +221,14 @@@ if (basechain->type->ops_register) return basechain->type->ops_register(net, ops);

- return nf_register_net_hook(net, ops); + return nft_register_basechain_hooks(net, table->family, basechain); }

static void nf_tables_unregister_hook(struct net *net, const struct nft_table *table, struct nft_chain *chain) { - const struct nft_base_chain *basechain; + struct nft_base_chain *basechain; const struct nf_hook_ops *ops;

if (table->flags & NFT_TABLE_F_DORMANT || @@@ -240,7 -187,7 +240,7 @@@ if (basechain->type->ops_unregister) return basechain->type->ops_unregister(net, ops);

- nf_unregister_net_hook(net, ops); + nft_unregister_basechain_hooks(net, table->family, basechain); }

static int nft_trans_table_add(struct nft_ctx *ctx, int msg_type) @@@ -795,8 -742,7 +795,8 @@@ static void nft_table_disable(struct ne if (cnt && i++ == cnt) break;

- nf_unregister_net_hook(net, &nft_base_chain(chain)->ops); + nft_unregister_basechain_hooks(net, table->family, + nft_base_chain(chain)); } }

@@@ -811,16 -757,14 +811,16 @@@ static int nf_tables_table_enable(struc if (!nft_is_base_chain(chain)) continue;

- err = nf_register_net_hook(net, &nft_base_chain(chain)->ops); + err = nft_register_basechain_hooks(net, table->family, + nft_base_chain(chain)); if (err < 0) - goto err; + goto err_register_hooks;

i++; } return 0; -err: + +err_register_hooks: if (i) nft_table_disable(net, table, i); return err; @@@ -1281,46 -1225,6 +1281,46 @@@ nla_put_failure return -ENOSPC; }

+static int nft_dump_basechain_hook(struct sk_buff *skb, int family, + const struct nft_base_chain *basechain) +{ + const struct nf_hook_ops *ops = &basechain->ops; + struct nft_hook *hook, *first = NULL; + struct nlattr *nest, *nest_devs; + int n = 0; + + nest = nla_nest_start_noflag(skb, NFTA_CHAIN_HOOK); + if (nest == NULL) + goto nla_put_failure; + if (nla_put_be32(skb, NFTA_HOOK_HOOKNUM, htonl(ops->hooknum))) + goto nla_put_failure; + if (nla_put_be32(skb, NFTA_HOOK_PRIORITY, htonl(ops->priority))) + goto nla_put_failure; + + if (family == NFPROTO_NETDEV) { + nest_devs = nla_nest_start_noflag(skb, NFTA_HOOK_DEVS); + list_for_each_entry(hook, &basechain->hook_list, list) { + if (!first) + first = hook; + + if (nla_put_string(skb, NFTA_DEVICE_NAME, + hook->ops.dev->name)) + goto nla_put_failure; + n++; + } + nla_nest_end(skb, nest_devs); + + if (n == 1 && + nla_put_string(skb, NFTA_HOOK_DEV, first->ops.dev->name)) + goto nla_put_failure; + } + nla_nest_end(skb, nest); + + return 0; +nla_put_failure: + return -1; +} + static int nf_tables_fill_chain_info(struct sk_buff *skb, struct net *net, u32 portid, u32 seq, int event, u32 flags, int family, const struct nft_table *table, @@@ -1349,10 -1253,21 +1349,10 @@@

if (nft_is_base_chain(chain)) { const struct nft_base_chain *basechain = nft_base_chain(chain); - const struct nf_hook_ops *ops = &basechain->ops; struct nft_stats __percpu *stats; - struct nlattr *nest;

- nest = nla_nest_start_noflag(skb, NFTA_CHAIN_HOOK); - if (nest == NULL) + if (nft_dump_basechain_hook(skb, family, basechain)) goto nla_put_failure; - if (nla_put_be32(skb, NFTA_HOOK_HOOKNUM, htonl(ops->hooknum))) - goto nla_put_failure; - if (nla_put_be32(skb, NFTA_HOOK_PRIORITY, htonl(ops->priority))) - goto nla_put_failure; - if (basechain->dev_name[0] && - nla_put_string(skb, NFTA_HOOK_DEV, basechain->dev_name)) - goto nla_put_failure; - nla_nest_end(skb, nest);

if (nla_put_be32(skb, NFTA_CHAIN_POLICY, htonl(basechain->policy))) @@@ -1546,9 -1461,8 +1546,9 @@@ static void nft_chain_stats_replace(str if (!nft_trans_chain_stats(trans)) return;

- rcu_swap_protected(chain->stats, nft_trans_chain_stats(trans), - lockdep_commit_lock_is_held(trans->ctx.net)); + nft_trans_chain_stats(trans) = + rcu_replace_pointer(chain->stats, nft_trans_chain_stats(trans), + lockdep_commit_lock_is_held(trans->ctx.net));

if (!nft_trans_chain_stats(trans)) static_branch_inc(&nft_counters_enabled); @@@ -1571,7 -1485,6 +1571,7 @@@ static void nf_tables_chain_free_chain_ static void nf_tables_chain_destroy(struct nft_ctx *ctx) { struct nft_chain *chain = ctx->chain; + struct nft_hook *hook, *next;

if (WARN_ON(chain->use > 0)) return; @@@ -1582,13 -1495,6 +1582,13 @@@ if (nft_is_base_chain(chain)) { struct nft_base_chain *basechain = nft_base_chain(chain);

+ if (ctx->family == NFPROTO_NETDEV) { + list_for_each_entry_safe(hook, next, + &basechain->hook_list, list) { + list_del_rcu(&hook->list); + kfree_rcu(hook, rcu); + } + } module_put(basechain->type->owner); if (rcu_access_pointer(basechain->stats)) { static_branch_dec(&nft_counters_enabled); @@@ -1602,125 -1508,13 +1602,125 @@@ } }

+static struct nft_hook *nft_netdev_hook_alloc(struct net *net, + const struct nlattr *attr) +{ + struct net_device *dev; + char ifname[IFNAMSIZ]; + struct nft_hook *hook; + int err; + + hook = kmalloc(sizeof(struct nft_hook), GFP_KERNEL); + if (!hook) { + err = -ENOMEM; + goto err_hook_alloc; + } + + nla_strlcpy(ifname, attr, IFNAMSIZ); + dev = __dev_get_by_name(net, ifname); + if (!dev) { + err = -ENOENT; + goto err_hook_dev; + } + hook->ops.dev = dev; + + return hook; + +err_hook_dev: + kfree(hook); +err_hook_alloc: + return ERR_PTR(err); +} + +static bool nft_hook_list_find(struct list_head *hook_list, + const struct nft_hook *this) +{ + struct nft_hook *hook; + + list_for_each_entry(hook, hook_list, list) { + if (this->ops.dev == hook->ops.dev) + return true; + } + + return false; +} + +static int nf_tables_parse_netdev_hooks(struct net *net, + const struct nlattr *attr, + struct list_head *hook_list) +{ + struct nft_hook *hook, *next; + const struct nlattr *tmp; + int rem, n = 0, err; + + nla_for_each_nested(tmp, attr, rem) { + if (nla_type(tmp) != NFTA_DEVICE_NAME) { + err = -EINVAL; + goto err_hook; + } + + hook = nft_netdev_hook_alloc(net, tmp); + if (IS_ERR(hook)) { + err = PTR_ERR(hook); + goto err_hook; + } + if (nft_hook_list_find(hook_list, hook)) { + err = -EEXIST; + goto err_hook; + } + list_add_tail(&hook->list, hook_list); + n++; + + if (n == NFT_NETDEVICE_MAX) { + err = -EFBIG; + goto err_hook; + } + } + if (!n) + return -EINVAL; + + return 0; + +err_hook: + list_for_each_entry_safe(hook, next, hook_list, list) { + list_del(&hook->list); + kfree(hook); + } + return err; +} + struct nft_chain_hook { u32 num; s32 priority; const struct nft_chain_type *type; - struct net_device *dev; + struct list_head list; };

+static int nft_chain_parse_netdev(struct net *net, + struct nlattr *tb[], + struct list_head *hook_list) +{ + struct nft_hook *hook; + int err; + + if (tb[NFTA_HOOK_DEV]) { + hook = nft_netdev_hook_alloc(net, tb[NFTA_HOOK_DEV]); + if (IS_ERR(hook)) + return PTR_ERR(hook); + + list_add_tail(&hook->list, hook_list); + } else if (tb[NFTA_HOOK_DEVS]) { + err = nf_tables_parse_netdev_hooks(net, tb[NFTA_HOOK_DEVS], + hook_list); + if (err < 0) + return err; + } else { + return -EINVAL; + } + + return 0; +} + static int nft_chain_parse_hook(struct net *net, const struct nlattr * const nla[], struct nft_chain_hook *hook, u8 family, @@@ -1728,6 -1522,7 +1728,6 @@@ { struct nlattr *ha[NFTA_HOOK_MAX + 1]; const struct nft_chain_type *type; - struct net_device *dev; int err;

lockdep_assert_held(&net->nft.commit_mutex); @@@ -1765,14 -1560,23 +1765,14 @@@

hook->type = type;

- hook->dev = NULL; + INIT_LIST_HEAD(&hook->list); if (family == NFPROTO_NETDEV) { - char ifname[IFNAMSIZ]; - - if (!ha[NFTA_HOOK_DEV]) { - module_put(type->owner); - return -EOPNOTSUPP; - } - - nla_strlcpy(ifname, ha[NFTA_HOOK_DEV], IFNAMSIZ); - dev = __dev_get_by_name(net, ifname); - if (!dev) { + err = nft_chain_parse_netdev(net, ha, &hook->list); + if (err < 0) { module_put(type->owner); - return -ENOENT; + return err; } - hook->dev = dev; - } else if (ha[NFTA_HOOK_DEV]) { + } else if (ha[NFTA_HOOK_DEV] || ha[NFTA_HOOK_DEVS]) { module_put(type->owner); return -EOPNOTSUPP; } @@@ -1782,12 -1586,6 +1782,12 @@@

static void nft_chain_release_hook(struct nft_chain_hook *hook) { + struct nft_hook *h, *next; + + list_for_each_entry_safe(h, next, &hook->list, list) { + list_del(&h->list); + kfree(h); + } module_put(hook->type->owner); }

@@@ -1812,49 -1610,6 +1812,49 @@@ static struct nft_rule **nf_tables_chai return kvmalloc(alloc, GFP_KERNEL); }

+static void nft_basechain_hook_init(struct nf_hook_ops *ops, u8 family, + const struct nft_chain_hook *hook, + struct nft_chain *chain) +{ + ops->pf = family; + ops->hooknum = hook->num; + ops->priority = hook->priority; + ops->priv = chain; + ops->hook = hook->type->hooks[ops->hooknum]; +} + +static int nft_basechain_init(struct nft_base_chain *basechain, u8 family, + struct nft_chain_hook *hook, u32 flags) +{ + struct nft_chain *chain; + struct nft_hook *h; + + basechain->type = hook->type; + INIT_LIST_HEAD(&basechain->hook_list); + chain = &basechain->chain; + + if (family == NFPROTO_NETDEV) { + list_splice_init(&hook->list, &basechain->hook_list); + list_for_each_entry(h, &basechain->hook_list, list) + nft_basechain_hook_init(&h->ops, family, hook, chain); + + basechain->ops.hooknum = hook->num; + basechain->ops.priority = hook->priority; + } else { + nft_basechain_hook_init(&basechain->ops, family, hook, chain); + } + + chain->flags |= NFT_BASE_CHAIN | flags; + basechain->policy = NF_ACCEPT; + if (chain->flags & NFT_CHAIN_HW_OFFLOAD && + nft_chain_offload_priority(basechain) < 0) + return -EOPNOTSUPP; + + flow_block_init(&basechain->flow_block); + + return 0; +} + static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask, u8 policy, u32 flags) { @@@ -1873,6 -1628,7 +1873,6 @@@

if (nla[NFTA_CHAIN_HOOK]) { struct nft_chain_hook hook; - struct nf_hook_ops *ops;

err = nft_chain_parse_hook(net, nla, &hook, family, true); if (err < 0) @@@ -1883,7 -1639,9 +1883,7 @@@ nft_chain_release_hook(&hook); return -ENOMEM; } - - if (hook.dev != NULL) - strncpy(basechain->dev_name, hook.dev->name, IFNAMSIZ); + chain = &basechain->chain;

if (nla[NFTA_CHAIN_COUNTERS]) { stats = nft_stats_alloc(nla[NFTA_CHAIN_COUNTERS]); @@@ -1896,12 -1654,24 +1896,12 @@@ static_branch_inc(&nft_counters_enabled); }

- basechain->type = hook.type; - chain = &basechain->chain; - - ops = &basechain->ops; - ops->pf = family; - ops->hooknum = hook.num; - ops->priority = hook.priority; - ops->priv = chain; - ops->hook = hook.type->hooks[ops->hooknum]; - ops->dev = hook.dev; - - chain->flags |= NFT_BASE_CHAIN | flags; - basechain->policy = NF_ACCEPT; - if (chain->flags & NFT_CHAIN_HW_OFFLOAD && - nft_chain_offload_priority(basechain) < 0) - return -EOPNOTSUPP; - - flow_block_init(&basechain->flow_block); + err = nft_basechain_init(basechain, family, &hook, flags); + if (err < 0) { + nft_chain_release_hook(&hook); + kfree(basechain); + return err; + } } else { chain = kzalloc(sizeof(*chain), GFP_KERNEL); if (chain == NULL) @@@ -1961,25 -1731,6 +1961,25 @@@ err1 return err; }

+static bool nft_hook_list_equal(struct list_head *hook_list1, + struct list_head *hook_list2) +{ + struct nft_hook *hook; + int n = 0, m = 0; + + n = 0; + list_for_each_entry(hook, hook_list2, list) { + if (!nft_hook_list_find(hook_list1, hook)) + return false; + + n++; + } + list_for_each_entry(hook, hook_list1, list) + m++; + + return n == m; +} + static int nf_tables_updchain(struct nft_ctx *ctx, u8 genmask, u8 policy, u32 flags) { @@@ -2011,19 -1762,12 +2011,19 @@@ return -EBUSY; }

- ops = &basechain->ops; - if (ops->hooknum != hook.num || - ops->priority != hook.priority || - ops->dev != hook.dev) { - nft_chain_release_hook(&hook); - return -EBUSY; + if (ctx->family == NFPROTO_NETDEV) { + if (!nft_hook_list_equal(&basechain->hook_list, + &hook.list)) { + nft_chain_release_hook(&hook); + return -EBUSY; + } + } else { + ops = &basechain->ops; + if (ops->hooknum != hook.num || + ops->priority != hook.priority) { + nft_chain_release_hook(&hook); + return -EBUSY; + } } nft_chain_release_hook(&hook); } @@@ -5884,6 -5628,43 +5884,6 @@@ nft_flowtable_lookup_byhandle(const str return ERR_PTR(-ENOENT); }

-static int nf_tables_parse_devices(const struct nft_ctx *ctx, - const struct nlattr *attr, - struct net_device *dev_array[], int *len) -{ - const struct nlattr *tmp; - struct net_device *dev; - char ifname[IFNAMSIZ]; - int rem, n = 0, err; - - nla_for_each_nested(tmp, attr, rem) { - if (nla_type(tmp) != NFTA_DEVICE_NAME) { - err = -EINVAL; - goto err1; - } - - nla_strlcpy(ifname, tmp, IFNAMSIZ); - dev = __dev_get_by_name(ctx->net, ifname); - if (!dev) { - err = -ENOENT; - goto err1; - } - - dev_array[n++] = dev; - if (n == NFT_FLOWTABLE_DEVICE_MAX) { - err = -EFBIG; - goto err1; - } - } - if (!len) - return -EINVAL; - - err = 0; -err1: - *len = n; - return err; -} - static const struct nla_policy nft_flowtable_hook_policy[NFTA_FLOWTABLE_HOOK_MAX + 1] = { [NFTA_FLOWTABLE_HOOK_NUM] = { .type = NLA_U32 }, [NFTA_FLOWTABLE_HOOK_PRIORITY] = { .type = NLA_U32 }, @@@ -5894,10 -5675,11 +5894,10 @@@ static int nf_tables_flowtable_parse_ho const struct nlattr *attr, struct nft_flowtable *flowtable) { - struct net_device *dev_array[NFT_FLOWTABLE_DEVICE_MAX]; struct nlattr *tb[NFTA_FLOWTABLE_HOOK_MAX + 1]; - struct nf_hook_ops *ops; + struct nft_hook *hook; int hooknum, priority; - int err, n = 0, i; + int err;

err = nla_parse_nested_deprecated(tb, NFTA_FLOWTABLE_HOOK_MAX, attr, nft_flowtable_hook_policy, NULL); @@@ -5915,21 -5697,27 +5915,21 @@@

priority = ntohl(nla_get_be32(tb[NFTA_FLOWTABLE_HOOK_PRIORITY]));

- err = nf_tables_parse_devices(ctx, tb[NFTA_FLOWTABLE_HOOK_DEVS], - dev_array, &n); + err = nf_tables_parse_netdev_hooks(ctx->net, + tb[NFTA_FLOWTABLE_HOOK_DEVS], + &flowtable->hook_list); if (err < 0) return err;

- ops = kcalloc(n, sizeof(struct nf_hook_ops), GFP_KERNEL); - if (!ops) - return -ENOMEM; - - flowtable->hooknum = hooknum; - flowtable->priority = priority; - flowtable->ops = ops; - flowtable->ops_len = n; + flowtable->hooknum = hooknum; + flowtable->data.priority = priority;

- for (i = 0; i < n; i++) { - flowtable->ops[i].pf = NFPROTO_NETDEV; - flowtable->ops[i].hooknum = hooknum; - flowtable->ops[i].priority = priority; - flowtable->ops[i].priv = &flowtable->data; - flowtable->ops[i].hook = flowtable->data.type->hook; - flowtable->ops[i].dev = dev_array[i]; + list_for_each_entry(hook, &flowtable->hook_list, list) { + hook->ops.pf = NFPROTO_NETDEV; + hook->ops.hooknum = hooknum; + hook->ops.priority = priority; + hook->ops.priv = &flowtable->data; + hook->ops.hook = flowtable->data.type->hook; }

return err; @@@ -5969,51 -5757,14 +5969,51 @@@ nft_flowtable_type_get(struct net *net static void nft_unregister_flowtable_net_hooks(struct net *net, struct nft_flowtable *flowtable) { - int i; + struct nft_hook *hook;

- for (i = 0; i < flowtable->ops_len; i++) { - if (!flowtable->ops[i].dev) - continue; + list_for_each_entry(hook, &flowtable->hook_list, list) + nf_unregister_net_hook(net, &hook->ops); +}

- nf_unregister_net_hook(net, &flowtable->ops[i]); +static int nft_register_flowtable_net_hooks(struct net *net, + struct nft_table *table, + struct nft_flowtable *flowtable) +{ + struct nft_hook *hook, *hook2, *next; + struct nft_flowtable *ft; + int err, i = 0; + + list_for_each_entry(hook, &flowtable->hook_list, list) { + list_for_each_entry(ft, &table->flowtables, list) { + list_for_each_entry(hook2, &ft->hook_list, list) { + if (hook->ops.dev == hook2->ops.dev && + hook->ops.pf == hook2->ops.pf) { + err = -EBUSY; + goto err_unregister_net_hooks; + } + } + } + + err = nf_register_net_hook(net, &hook->ops); + if (err < 0) + goto err_unregister_net_hooks; + + i++; } + + return 0; + +err_unregister_net_hooks: + list_for_each_entry_safe(hook, next, &flowtable->hook_list, list) { + if (i-- <= 0) + break; + + nf_unregister_net_hook(net, &hook->ops); + list_del_rcu(&hook->list); + kfree_rcu(hook, rcu); + } + + return err; }

static int nf_tables_newflowtable(struct net *net, struct sock *nlsk, @@@ -6024,13 -5775,12 +6024,13 @@@ { const struct nfgenmsg *nfmsg = nlmsg_data(nlh); const struct nf_flowtable_type *type; - struct nft_flowtable *flowtable, *ft; u8 genmask = nft_genmask_next(net); int family = nfmsg->nfgen_family; + struct nft_flowtable *flowtable; + struct nft_hook *hook, *next; struct nft_table *table; struct nft_ctx ctx; - int err, i, k; + int err;

if (!nla[NFTA_FLOWTABLE_TABLE] || !nla[NFTA_FLOWTABLE_NAME] || @@@ -6069,7 -5819,6 +6069,7 @@@

flowtable->table = table; flowtable->handle = nf_tables_alloc_handle(table); + INIT_LIST_HEAD(&flowtable->hook_list);

flowtable->name = nla_strdup(nla[NFTA_FLOWTABLE_NAME], GFP_KERNEL); if (!flowtable->name) { @@@ -6093,24 -5842,43 +6093,24 @@@ if (err < 0) goto err4;

- for (i = 0; i < flowtable->ops_len; i++) { - if (!flowtable->ops[i].dev) - continue; - - list_for_each_entry(ft, &table->flowtables, list) { - for (k = 0; k < ft->ops_len; k++) { - if (!ft->ops[k].dev) - continue; - - if (flowtable->ops[i].dev == ft->ops[k].dev && - flowtable->ops[i].pf == ft->ops[k].pf) { - err = -EBUSY; - goto err5; - } - } - } - - err = nf_register_net_hook(net, &flowtable->ops[i]); - if (err < 0) - goto err5; - } + err = nft_register_flowtable_net_hooks(ctx.net, table, flowtable); + if (err < 0) + goto err4;

err = nft_trans_flowtable_add(&ctx, NFT_MSG_NEWFLOWTABLE, flowtable); if (err < 0) - goto err6; + goto err5;

list_add_tail_rcu(&flowtable->list, &table->flowtables); table->use++;

return 0; -err6: - i = flowtable->ops_len; err5: - for (k = i - 1; k >= 0; k--) - nf_unregister_net_hook(net, &flowtable->ops[k]); - - kfree(flowtable->ops); + list_for_each_entry_safe(hook, next, &flowtable->hook_list, list) { + nf_unregister_net_hook(net, &hook->ops); + list_del_rcu(&hook->list); + kfree_rcu(hook, rcu); + } err4: flowtable->data.type->free(&flowtable->data); err3: @@@ -6177,8 -5945,8 +6177,8 @@@ static int nf_tables_fill_flowtable_inf { struct nlattr *nest, *nest_devs; struct nfgenmsg *nfmsg; + struct nft_hook *hook; struct nlmsghdr *nlh; - int i;

event = nfnl_msg_type(NFNL_SUBSYS_NFTABLES, event); nlh = nlmsg_put(skb, portid, seq, event, sizeof(struct nfgenmsg), flags); @@@ -6201,15 -5969,18 +6201,15 @@@ if (!nest) goto nla_put_failure; if (nla_put_be32(skb, NFTA_FLOWTABLE_HOOK_NUM, htonl(flowtable->hooknum)) || - nla_put_be32(skb, NFTA_FLOWTABLE_HOOK_PRIORITY, htonl(flowtable->priority))) + nla_put_be32(skb, NFTA_FLOWTABLE_HOOK_PRIORITY, htonl(flowtable->data.priority))) goto nla_put_failure;

nest_devs = nla_nest_start_noflag(skb, NFTA_FLOWTABLE_HOOK_DEVS); if (!nest_devs) goto nla_put_failure;

- for (i = 0; i < flowtable->ops_len; i++) { - const struct net_device *dev = READ_ONCE(flowtable->ops[i].dev); - - if (dev && - nla_put_string(skb, NFTA_DEVICE_NAME, dev->name)) + list_for_each_entry_rcu(hook, &flowtable->hook_list, list) { + if (nla_put_string(skb, NFTA_DEVICE_NAME, hook->ops.dev->name)) goto nla_put_failure; } nla_nest_end(skb, nest_devs); @@@ -6400,12 -6171,7 +6400,12 @@@ err

static void nf_tables_flowtable_destroy(struct nft_flowtable *flowtable) { - kfree(flowtable->ops); + struct nft_hook *hook, *next; + + list_for_each_entry_safe(hook, next, &flowtable->hook_list, list) { + list_del_rcu(&hook->list); + kfree(hook); + } kfree(flowtable->name); flowtable->data.type->free(&flowtable->data); module_put(flowtable->data.type->owner); @@@ -6445,15 -6211,14 +6445,15 @@@ nla_put_failure static void nft_flowtable_event(unsigned long event, struct net_device *dev, struct nft_flowtable *flowtable) { - int i; + struct nft_hook *hook;

- for (i = 0; i < flowtable->ops_len; i++) { - if (flowtable->ops[i].dev != dev) + list_for_each_entry(hook, &flowtable->hook_list, list) { + if (hook->ops.dev != dev) continue;

- nf_unregister_net_hook(dev_net(dev), &flowtable->ops[i]); - flowtable->ops[i].dev = NULL; + nf_unregister_net_hook(dev_net(dev), &hook->ops); + list_del_rcu(&hook->list); + kfree_rcu(hook, rcu); break; } } @@@ -7556,7 -7321,7 +7556,7 @@@ int nft_validate_register_load(enum nft return -EINVAL; if (len == 0) return -EINVAL; - if (reg * NFT_REG32_SIZE + len > FIELD_SIZEOF(struct nft_regs, data)) + if (reg * NFT_REG32_SIZE + len > sizeof_member(struct nft_regs, data)) return -ERANGE;

return 0; @@@ -7604,7 -7369,7 +7604,7 @@@ int nft_validate_register_store(const s if (len == 0) return -EINVAL; if (reg * NFT_REG32_SIZE + len > - FIELD_SIZEOF(struct nft_regs, data)) + sizeof_member(struct nft_regs, data)) return -ERANGE;

if (data != NULL && type != NFT_DATA_VALUE) diff --combined net/openvswitch/datapath.c index d8c364d637b1,4c412b2b27b4..4ebcb4d5af6f --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@@ -1881,7 -1881,7 +1881,7 @@@ static struct genl_family dp_datapath_g /* Called with ovs_mutex or RCU read lock. */ static int ovs_vport_cmd_fill_info(struct vport *vport, struct sk_buff *skb, struct net *net, u32 portid, u32 seq, - u32 flags, u8 cmd) + u32 flags, u8 cmd, gfp_t gfp) { struct ovs_header *ovs_header; struct ovs_vport_stats vport_stats; @@@ -1902,7 -1902,7 +1902,7 @@@ goto nla_put_failure;

if (!net_eq(net, dev_net(vport->dev))) { - int id = peernet2id_alloc(net, dev_net(vport->dev)); + int id = peernet2id_alloc(net, dev_net(vport->dev), gfp);

if (nla_put_s32(skb, OVS_VPORT_ATTR_NETNSID, id)) goto nla_put_failure; @@@ -1943,12 -1943,11 +1943,12 @@@ struct sk_buff *ovs_vport_cmd_build_inf struct sk_buff *skb; int retval;

- skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_ATOMIC); + skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!skb) return ERR_PTR(-ENOMEM);

- retval = ovs_vport_cmd_fill_info(vport, skb, net, portid, seq, 0, cmd); + retval = ovs_vport_cmd_fill_info(vport, skb, net, portid, seq, 0, cmd, + GFP_KERNEL); BUG_ON(retval < 0);

return skb; @@@ -2090,7 -2089,7 +2090,7 @@@ restart

err = ovs_vport_cmd_fill_info(vport, reply, genl_info_net(info), info->snd_portid, info->snd_seq, 0, - OVS_VPORT_CMD_NEW); + OVS_VPORT_CMD_NEW, GFP_KERNEL);

new_headroom = netdev_get_fwd_headroom(vport->dev);

@@@ -2151,7 -2150,7 +2151,7 @@@ static int ovs_vport_cmd_set(struct sk_

err = ovs_vport_cmd_fill_info(vport, reply, genl_info_net(info), info->snd_portid, info->snd_seq, 0, - OVS_VPORT_CMD_SET); + OVS_VPORT_CMD_SET, GFP_KERNEL); BUG_ON(err < 0);

ovs_unlock(); @@@ -2191,7 -2190,7 +2191,7 @@@ static int ovs_vport_cmd_del(struct sk_

err = ovs_vport_cmd_fill_info(vport, reply, genl_info_net(info), info->snd_portid, info->snd_seq, 0, - OVS_VPORT_CMD_DEL); + OVS_VPORT_CMD_DEL, GFP_KERNEL); BUG_ON(err < 0);

/* the vport deletion may trigger dp headroom update */ @@@ -2238,7 -2237,7 +2238,7 @@@ static int ovs_vport_cmd_get(struct sk_ goto exit_unlock_free; err = ovs_vport_cmd_fill_info(vport, reply, genl_info_net(info), info->snd_portid, info->snd_seq, 0, - OVS_VPORT_CMD_GET); + OVS_VPORT_CMD_GET, GFP_ATOMIC); BUG_ON(err < 0); rcu_read_unlock();

@@@ -2274,8 -2273,7 +2274,8 @@@ static int ovs_vport_cmd_dump(struct sk NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, - OVS_VPORT_CMD_GET) < 0) + OVS_VPORT_CMD_GET, + GFP_ATOMIC) < 0) goto out;

j++; @@@ -2451,7 -2449,7 +2451,7 @@@ static int __init dp_init(void { int err;

- BUILD_BUG_ON(sizeof(struct ovs_skb_cb) > FIELD_SIZEOF(struct sk_buff, cb)); + BUILD_BUG_ON(sizeof(struct ovs_skb_cb) > sizeof_member(struct sk_buff, cb));

pr_info("Open vSwitch switching datapath\n");

diff --combined net/sched/act_ct.c index 2d5ab233349e,3ee22bbac3ff..e6df8da29383 --- a/net/sched/act_ct.c +++ b/net/sched/act_ct.c @@@ -312,7 -312,7 +312,7 @@@ static void tcf_ct_act_set_labels(struc u32 *labels_m) { #if IS_ENABLED(CONFIG_NF_CONNTRACK_LABELS) - size_t labels_sz = FIELD_SIZEOF(struct tcf_ct_params, labels); + size_t labels_sz = sizeof_member(struct tcf_ct_params, labels);

if (!memchr_inv(labels_m, 0, labels_sz)) return; @@@ -722,8 -722,7 +722,8 @@@ static int tcf_ct_init(struct net *net

spin_lock_bh(&c->tcf_lock); goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch); - rcu_swap_protected(c->params, params, lockdep_is_held(&c->tcf_lock)); + params = rcu_replace_pointer(c->params, params, + lockdep_is_held(&c->tcf_lock)); spin_unlock_bh(&c->tcf_lock);

if (goto_ch) @@@ -930,7 -929,7 +930,7 @@@ static struct tc_action_ops act_ct_ops

static __net_init int ct_init_net(struct net *net) { - unsigned int n_bits = FIELD_SIZEOF(struct tcf_ct_params, labels) * 8; + unsigned int n_bits = sizeof_member(struct tcf_ct_params, labels) * 8; struct tc_ct_action_net *tn = net_generic(net, ct_net_id);

if (nf_connlabels_get(net, n_bits - 1)) { diff --combined net/sctp/socket.c index ca81e06df165,4c3105d96dce..1d6ebc13ed35 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@@ -8476,7 -8476,7 +8476,7 @@@ __poll_t sctp_poll(struct file *file, s mask = 0;

/* Is there any exceptional events? */ - if (sk->sk_err || !skb_queue_empty(&sk->sk_error_queue)) + if (sk->sk_err || !skb_queue_empty_lockless(&sk->sk_error_queue)) mask |= EPOLLERR | (sock_flag(sk, SOCK_SELECT_ERR_QUEUE) ? EPOLLPRI : 0); if (sk->sk_shutdown & RCV_SHUTDOWN) @@@ -8485,7 -8485,7 +8485,7 @@@ mask |= EPOLLHUP;

/* Is it readable? Reconsider this code with TCP-style support. */ - if (!skb_queue_empty(&sk->sk_receive_queue)) + if (!skb_queue_empty_lockless(&sk->sk_receive_queue)) mask |= EPOLLIN | EPOLLRDNORM;

/* The association is either gone or not ready. */ @@@ -8871,7 -8871,7 +8871,7 @@@ struct sk_buff *sctp_skb_recv_datagram( if (sk_can_busy_loop(sk)) { sk_busy_loop(sk, noblock);

- if (!skb_queue_empty(&sk->sk_receive_queue)) + if (!skb_queue_empty_lockless(&sk->sk_receive_queue)) continue; }

@@@ -9500,12 -9500,12 +9500,12 @@@ struct proto sctp_prot = .backlog_rcv = sctp_backlog_rcv, .hash = sctp_hash, .unhash = sctp_unhash, - .get_port = sctp_get_port, + .no_autobind = true, .obj_size = sizeof(struct sctp_sock), .useroffset = offsetof(struct sctp_sock, subscribe), .usersize = offsetof(struct sctp_sock, initmsg) - offsetof(struct sctp_sock, subscribe) + - sizeof_field(struct sctp_sock, initmsg), + sizeof_member(struct sctp_sock, initmsg), .sysctl_mem = sysctl_sctp_mem, .sysctl_rmem = sysctl_sctp_rmem, .sysctl_wmem = sysctl_sctp_wmem, @@@ -9542,12 -9542,12 +9542,12 @@@ struct proto sctpv6_prot = .backlog_rcv = sctp_backlog_rcv, .hash = sctp_hash, .unhash = sctp_unhash, - .get_port = sctp_get_port, + .no_autobind = true, .obj_size = sizeof(struct sctp6_sock), .useroffset = offsetof(struct sctp6_sock, sctp.subscribe), .usersize = offsetof(struct sctp6_sock, sctp.initmsg) - offsetof(struct sctp6_sock, sctp.subscribe) + - sizeof_field(struct sctp6_sock, sctp.initmsg), + sizeof_member(struct sctp6_sock, sctp.initmsg), .sysctl_mem = sysctl_sctp_mem, .sysctl_rmem = sysctl_sctp_rmem, .sysctl_wmem = sysctl_sctp_wmem, diff --combined net/unix/af_unix.c index 7cfdce10de36,ee9b2d8684c3..f0a074356012 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@@ -284,9 -284,11 +284,9 @@@ static struct sock *__unix_find_socket_

if (u->addr->len == len && !memcmp(u->addr->name, sunname, len)) - goto found; + return s; } - s = NULL; -found: - return s; + return NULL; }

static inline struct sock *unix_find_socket_byname(struct net *net, @@@ -644,9 -646,6 +644,9 @@@ static __poll_t unix_poll(struct file * static __poll_t unix_dgram_poll(struct file *, struct socket *, poll_table *); static int unix_ioctl(struct socket *, unsigned int, unsigned long); +#ifdef CONFIG_COMPAT +static int unix_compat_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg); +#endif static int unix_shutdown(struct socket *, int); static int unix_stream_sendmsg(struct socket *, struct msghdr *, size_t); static int unix_stream_recvmsg(struct socket *, struct msghdr *, size_t, int); @@@ -688,9 -687,6 +688,9 @@@ static const struct proto_ops unix_stre .getname = unix_getname, .poll = unix_poll, .ioctl = unix_ioctl, +#ifdef CONFIG_COMPAT + .compat_ioctl = unix_compat_ioctl, +#endif .listen = unix_listen, .shutdown = unix_shutdown, .setsockopt = sock_no_setsockopt, @@@ -714,9 -710,6 +714,9 @@@ static const struct proto_ops unix_dgra .getname = unix_getname, .poll = unix_dgram_poll, .ioctl = unix_ioctl, +#ifdef CONFIG_COMPAT + .compat_ioctl = unix_compat_ioctl, +#endif .listen = sock_no_listen, .shutdown = unix_shutdown, .setsockopt = sock_no_setsockopt, @@@ -739,9 -732,6 +739,9 @@@ static const struct proto_ops unix_seqp .getname = unix_getname, .poll = unix_dgram_poll, .ioctl = unix_ioctl, +#ifdef CONFIG_COMPAT + .compat_ioctl = unix_compat_ioctl, +#endif .listen = unix_listen, .shutdown = unix_shutdown, .setsockopt = sock_no_setsockopt, @@@ -2592,13 -2582,6 +2592,13 @@@ static int unix_ioctl(struct socket *so return err; }

+#ifdef CONFIG_COMPAT +static int unix_compat_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) +{ + return unix_ioctl(sock, cmd, (unsigned long)compat_ptr(arg)); +} +#endif + static __poll_t unix_poll(struct file *file, struct socket *sock, poll_table *wait) { struct sock *sk = sock->sk; @@@ -2616,7 -2599,7 +2616,7 @@@ mask |= EPOLLRDHUP | EPOLLIN | EPOLLRDNORM;

/* readable? */ - if (!skb_queue_empty(&sk->sk_receive_queue)) + if (!skb_queue_empty_lockless(&sk->sk_receive_queue)) mask |= EPOLLIN | EPOLLRDNORM;

/* Connection-based need to check for termination and startup */ @@@ -2645,7 -2628,7 +2645,7 @@@ static __poll_t unix_dgram_poll(struct mask = 0;

/* exceptional events? */ - if (sk->sk_err || !skb_queue_empty(&sk->sk_error_queue)) + if (sk->sk_err || !skb_queue_empty_lockless(&sk->sk_error_queue)) mask |= EPOLLERR | (sock_flag(sk, SOCK_SELECT_ERR_QUEUE) ? EPOLLPRI : 0);

@@@ -2655,7 -2638,7 +2655,7 @@@ mask |= EPOLLHUP;

/* readable? */ - if (!skb_queue_empty(&sk->sk_receive_queue)) + if (!skb_queue_empty_lockless(&sk->sk_receive_queue)) mask |= EPOLLIN | EPOLLRDNORM;

/* Connection-based need to check for termination and startup */ @@@ -2865,7 -2848,7 +2865,7 @@@ static int __init af_unix_init(void { int rc = -1;

- BUILD_BUG_ON(sizeof(struct unix_skb_parms) > FIELD_SIZEOF(struct sk_buff, cb)); + BUILD_BUG_ON(sizeof(struct unix_skb_parms) > sizeof_member(struct sk_buff, cb));

rc = proto_register(&unix_proto, 1); if (rc != 0) { diff --combined sound/soc/codecs/hdmi-codec.c index f8b5b960e597,c8b1ac22b2b2..841d1c608fe4 --- a/sound/soc/codecs/hdmi-codec.c +++ b/sound/soc/codecs/hdmi-codec.c @@@ -274,7 -274,7 +274,7 @@@ struct hdmi_codec_priv uint8_t eld[MAX_ELD_BYTES]; struct snd_pcm_chmap *chmap_info; unsigned int chmap_idx; - struct mutex lock; + unsigned long busy; struct snd_soc_jack *jack; unsigned int jack_status; }; @@@ -292,7 -292,7 +292,7 @@@ static int hdmi_eld_ctl_info(struct snd struct snd_ctl_elem_info *uinfo) { uinfo->type = SNDRV_CTL_ELEM_TYPE_BYTES; - uinfo->count = FIELD_SIZEOF(struct hdmi_codec_priv, eld); + uinfo->count = sizeof_member(struct hdmi_codec_priv, eld);

return 0; } @@@ -390,8 -390,8 +390,8 @@@ static int hdmi_codec_startup(struct sn struct hdmi_codec_priv *hcp = snd_soc_dai_get_drvdata(dai); int ret = 0;

- ret = mutex_trylock(&hcp->lock); - if (!ret) { + ret = test_and_set_bit(0, &hcp->busy); + if (ret) { dev_err(dai->dev, "Only one simultaneous stream supported!\n"); return -EINVAL; } @@@ -419,7 -419,7 +419,7 @@@

err: /* Release the exclusive lock on error */ - mutex_unlock(&hcp->lock); + clear_bit(0, &hcp->busy); return ret; }

@@@ -431,7 -431,7 +431,7 @@@ static void hdmi_codec_shutdown(struct hcp->chmap_idx = HDMI_CODEC_CHMAP_IDX_UNKNOWN; hcp->hcd.ops->audio_shutdown(dai->dev->parent, hcp->hcd.data);

- mutex_unlock(&hcp->lock); + clear_bit(0, &hcp->busy); }

static int hdmi_codec_hw_params(struct snd_pcm_substream *substream, @@@ -811,6 -811,8 +811,6 @@@ static int hdmi_codec_probe(struct plat return -ENOMEM;

hcp->hcd = *hcd; - mutex_init(&hcp->lock); - daidrv = devm_kcalloc(dev, dai_count, sizeof(*daidrv), GFP_KERNEL); if (!daidrv) return -ENOMEM; diff --combined virt/kvm/kvm_main.c index e9eb666eb6e8,777d3b125072..4df0aa6b8e5c --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@@ -2360,23 -2360,20 +2360,23 @@@ out kvm_arch_vcpu_unblocking(vcpu); block_ns = ktime_to_ns(cur) - ktime_to_ns(start);

- if (!vcpu_valid_wakeup(vcpu)) - shrink_halt_poll_ns(vcpu); - else if (halt_poll_ns) { - if (block_ns <= vcpu->halt_poll_ns) - ; - /* we had a long block, shrink polling */ - else if (vcpu->halt_poll_ns && block_ns > halt_poll_ns) + if (!kvm_arch_no_poll(vcpu)) { + if (!vcpu_valid_wakeup(vcpu)) { shrink_halt_poll_ns(vcpu); - /* we had a short halt and our poll time is too small */ - else if (vcpu->halt_poll_ns < halt_poll_ns && - block_ns < halt_poll_ns) - grow_halt_poll_ns(vcpu); - } else - vcpu->halt_poll_ns = 0; + } else if (halt_poll_ns) { + if (block_ns <= vcpu->halt_poll_ns) + ; + /* we had a long block, shrink polling */ + else if (vcpu->halt_poll_ns && block_ns > halt_poll_ns) + shrink_halt_poll_ns(vcpu); + /* we had a short halt and our poll time is too small */ + else if (vcpu->halt_poll_ns < halt_poll_ns && + block_ns < halt_poll_ns) + grow_halt_poll_ns(vcpu); + } else { + vcpu->halt_poll_ns = 0; + } + }

trace_kvm_vcpu_wakeup(block_ns, waited, vcpu_valid_wakeup(vcpu)); kvm_arch_vcpu_block_finish(vcpu); @@@ -3049,14 -3046,14 +3049,14 @@@ struct kvm_device *kvm_device_from_filp return filp->private_data; }

-static struct kvm_device_ops *kvm_device_ops_table[KVM_DEV_TYPE_MAX] = { +static const struct kvm_device_ops *kvm_device_ops_table[KVM_DEV_TYPE_MAX] = { #ifdef CONFIG_KVM_MPIC [KVM_DEV_TYPE_FSL_MPIC_20] = &kvm_mpic_ops, [KVM_DEV_TYPE_FSL_MPIC_42] = &kvm_mpic_ops, #endif };

-int kvm_register_device_ops(struct kvm_device_ops *ops, u32 type) +int kvm_register_device_ops(const struct kvm_device_ops *ops, u32 type) { if (type >= ARRAY_SIZE(kvm_device_ops_table)) return -ENOSPC; @@@ -3077,7 -3074,7 +3077,7 @@@ void kvm_unregister_device_ops(u32 type static int kvm_ioctl_create_device(struct kvm *kvm, struct kvm_create_device *cd) { - struct kvm_device_ops *ops = NULL; + const struct kvm_device_ops *ops = NULL; struct kvm_device *dev; bool test = cd->flags & KVM_CREATE_DEVICE_TEST; int type; @@@ -4296,7 -4293,7 +4296,7 @@@ int kvm_init(void *opaque, unsigned vcp kmem_cache_create_usercopy("kvm_vcpu", vcpu_size, vcpu_align, SLAB_ACCOUNT, offsetof(struct kvm_vcpu, arch), - sizeof_field(struct kvm_vcpu, arch), + sizeof_member(struct kvm_vcpu, arch), NULL); if (!kvm_vcpu_cache) { r = -ENOMEM;