Re: Linux 6.6.107

diff --git a/Documentation/devicetree/bindings/serial/brcm,bcm7271-uart.yaml b/Documentation/devicetree/bindings/serial/brcm,bcm7271-uart.yaml index 89c462653e2d..8cc848ae11cb 100644 --- a/Documentation/devicetree/bindings/serial/brcm,bcm7271-uart.yaml +++ b/Documentation/devicetree/bindings/serial/brcm,bcm7271-uart.yaml @@ -41,7 +41,7 @@ properties: - const: dma_intr2

clocks: - minItems: 1 + maxItems: 1

clock-names: const: sw_baud diff --git a/Documentation/networking/can.rst b/Documentation/networking/can.rst index d7e1ada905b2..3bdd15583810 100644 --- a/Documentation/networking/can.rst +++ b/Documentation/networking/can.rst @@ -740,7 +740,7 @@ The broadcast manager sends responses to user space in the same form: struct timeval ival1, ival2; /* count and subsequent interval */ canid_t can_id; /* unique can_id for task */ __u32 nframes; /* number of can_frames following */ - struct can_frame frames[0]; + struct can_frame frames[]; };

The aligned payload 'frames' uses the same basic CAN frame structure defined diff --git a/Makefile b/Makefile index b934846659ee..9c9e272f48b8 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 6 PATCHLEVEL = 6 -SUBLEVEL = 106 +SUBLEVEL = 107 EXTRAVERSION = NAME = Pinguïn Aangedreven

diff --git a/arch/riscv/include/asm/compat.h b/arch/riscv/include/asm/compat.h index 2ac955b51148..6b79287baecc 100644 --- a/arch/riscv/include/asm/compat.h +++ b/arch/riscv/include/asm/compat.h @@ -9,7 +9,6 @@ */ #include <linux/types.h> #include <linux/sched.h> -#include <linux/sched/task_stack.h> #include <asm-generic/compat.h>

static inline int is_compat_task(void) diff --git a/arch/s390/kernel/perf_cpum_cf.c b/arch/s390/kernel/perf_cpum_cf.c index 65a66df5bb86..771e1cb17540 100644 --- a/arch/s390/kernel/perf_cpum_cf.c +++ b/arch/s390/kernel/perf_cpum_cf.c @@ -757,8 +757,6 @@ static int __hw_perf_event_init(struct perf_event *event, unsigned int type) break;

case PERF_TYPE_HARDWARE: - if (is_sampling_event(event)) /* No sampling support */ - return -ENOENT; ev = attr->config; if (!attr->exclude_user && attr->exclude_kernel) { /* @@ -856,6 +854,8 @@ static int cpumf_pmu_event_init(struct perf_event *event) unsigned int type = event->attr.type; int err;

+ if (is_sampling_event(event)) /* No sampling support */ + return err; if (type == PERF_TYPE_HARDWARE || type == PERF_TYPE_RAW) err = __hw_perf_event_init(event, type); else if (event->pmu->type == type) diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S index c57d5df1abc6..0929d7fe7e27 100644 --- a/arch/x86/kernel/vmlinux.lds.S +++ b/arch/x86/kernel/vmlinux.lds.S @@ -500,10 +500,18 @@ SECTIONS PROVIDE(__ref_stack_chk_guard = __stack_chk_guard);

/* - * The ASSERT() sink to . is intentional, for binutils 2.14 compatibility: + * COMPILE_TEST kernels can be large - CONFIG_KASAN, for example, can cause + * this. Let's assume that nobody will be running a COMPILE_TEST kernel and + * let's assert that fuller build coverage is more valuable than being able to + * run a COMPILE_TEST kernel. + */ +#ifndef CONFIG_COMPILE_TEST +/* + * The ASSERT() sync to . is intentional, for binutils 2.14 compatibility: */ . = ASSERT((_end - LOAD_OFFSET <= KERNEL_IMAGE_SIZE), "kernel image bigger than KERNEL_IMAGE_SIZE"); +#endif

#ifdef CONFIG_X86_64 /* diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 288db3516772..2c0bc6a93ec3 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -791,10 +791,15 @@ void kvm_set_cpu_caps(void) F(PERFMON_V2) );

+ kvm_cpu_cap_check_and_set(X86_FEATURE_VERW_CLEAR); + kvm_cpu_cap_init_kvm_defined(CPUID_8000_0021_ECX, F(TSA_SQ_NO) | F(TSA_L1_NO) );

+ kvm_cpu_cap_check_and_set(X86_FEATURE_TSA_SQ_NO); + kvm_cpu_cap_check_and_set(X86_FEATURE_TSA_L1_NO); + /* * Synthesize "LFENCE is serializing" into the AMD-defined entry in * KVM's supported CPUID if the feature is reported as supported by the diff --git a/drivers/dma/dw/rzn1-dmamux.c b/drivers/dma/dw/rzn1-dmamux.c index 4fb8508419db..deadf135681b 100644 --- a/drivers/dma/dw/rzn1-dmamux.c +++ b/drivers/dma/dw/rzn1-dmamux.c @@ -48,12 +48,16 @@ static void *rzn1_dmamux_route_allocate(struct of_phandle_args *dma_spec, u32 mask; int ret;

- if (dma_spec->args_count != RNZ1_DMAMUX_NCELLS) - return ERR_PTR(-EINVAL); + if (dma_spec->args_count != RNZ1_DMAMUX_NCELLS) { + ret = -EINVAL; + goto put_device; + }

map = kzalloc(sizeof(*map), GFP_KERNEL); - if (!map) - return ERR_PTR(-ENOMEM); + if (!map) { + ret = -ENOMEM; + goto put_device; + }

chan = dma_spec->args[0]; map->req_idx = dma_spec->args[4]; @@ -94,12 +98,15 @@ static void *rzn1_dmamux_route_allocate(struct of_phandle_args *dma_spec, if (ret) goto clear_bitmap;

+ put_device(&pdev->dev); return map;

clear_bitmap: clear_bit(map->req_idx, dmamux->used_chans); free_map: kfree(map); +put_device: + put_device(&pdev->dev);

return ERR_PTR(ret); } diff --git a/drivers/dma/idxd/init.c b/drivers/dma/idxd/init.c index 92e86ae9db29..4b999c5802f4 100644 --- a/drivers/dma/idxd/init.c +++ b/drivers/dma/idxd/init.c @@ -179,27 +179,30 @@ static int idxd_setup_wqs(struct idxd_device *idxd) idxd->wq_enable_map = bitmap_zalloc_node(idxd->max_wqs, GFP_KERNEL, dev_to_node(dev)); if (!idxd->wq_enable_map) { rc = -ENOMEM; - goto err_bitmap; + goto err_free_wqs; }

for (i = 0; i < idxd->max_wqs; i++) { wq = kzalloc_node(sizeof(*wq), GFP_KERNEL, dev_to_node(dev)); if (!wq) { rc = -ENOMEM; - goto err; + goto err_unwind; }

idxd_dev_set_type(&wq->idxd_dev, IDXD_DEV_WQ); conf_dev = wq_confdev(wq); wq->id = i; wq->idxd = idxd; - device_initialize(wq_confdev(wq)); + device_initialize(conf_dev); conf_dev->parent = idxd_confdev(idxd); conf_dev->bus = &dsa_bus_type; conf_dev->type = &idxd_wq_device_type; rc = dev_set_name(conf_dev, "wq%d.%d", idxd->id, wq->id); - if (rc < 0) - goto err; + if (rc < 0) { + put_device(conf_dev); + kfree(wq); + goto err_unwind; + }

mutex_init(&wq->wq_lock); init_waitqueue_head(&wq->err_queue); @@ -210,15 +213,20 @@ static int idxd_setup_wqs(struct idxd_device *idxd) wq->enqcmds_retries = IDXD_ENQCMDS_RETRIES; wq->wqcfg = kzalloc_node(idxd->wqcfg_size, GFP_KERNEL, dev_to_node(dev)); if (!wq->wqcfg) { + put_device(conf_dev); + kfree(wq); rc = -ENOMEM; - goto err; + goto err_unwind; }

if (idxd->hw.wq_cap.op_config) { wq->opcap_bmap = bitmap_zalloc(IDXD_MAX_OPCAP_BITS, GFP_KERNEL); if (!wq->opcap_bmap) { + kfree(wq->wqcfg); + put_device(conf_dev); + kfree(wq); rc = -ENOMEM; - goto err_opcap_bmap; + goto err_unwind; } bitmap_copy(wq->opcap_bmap, idxd->opcap_bmap, IDXD_MAX_OPCAP_BITS); } @@ -229,13 +237,7 @@ static int idxd_setup_wqs(struct idxd_device *idxd)

return 0;

-err_opcap_bmap: - kfree(wq->wqcfg); - -err: - put_device(conf_dev); - kfree(wq); - +err_unwind: while (--i >= 0) { wq = idxd->wqs[i]; if (idxd->hw.wq_cap.op_config) @@ -244,11 +246,10 @@ static int idxd_setup_wqs(struct idxd_device *idxd) conf_dev = wq_confdev(wq); put_device(conf_dev); kfree(wq); - } bitmap_free(idxd->wq_enable_map);

-err_bitmap: +err_free_wqs: kfree(idxd->wqs);

return rc; @@ -904,10 +905,12 @@ static void idxd_remove(struct pci_dev *pdev) device_unregister(idxd_confdev(idxd)); idxd_shutdown(pdev); idxd_device_remove_debugfs(idxd); - idxd_cleanup(idxd); + perfmon_pmu_remove(idxd); + idxd_cleanup_interrupts(idxd); + if (device_pasid_enabled(idxd)) + idxd_disable_system_pasid(idxd); pci_iounmap(pdev, idxd->reg_base); put_device(idxd_confdev(idxd)); - idxd_free(idxd); pci_disable_device(pdev); }

diff --git a/drivers/dma/qcom/bam_dma.c b/drivers/dma/qcom/bam_dma.c index 4c3eb972039d..d5882c8537e5 100644 --- a/drivers/dma/qcom/bam_dma.c +++ b/drivers/dma/qcom/bam_dma.c @@ -1283,13 +1283,17 @@ static int bam_dma_probe(struct platform_device *pdev) if (!bdev->bamclk) { ret = of_property_read_u32(pdev->dev.of_node, "num-channels", &bdev->num_channels); - if (ret) + if (ret) { dev_err(bdev->dev, "num-channels unspecified in dt\n"); + return ret; + }

ret = of_property_read_u32(pdev->dev.of_node, "qcom,num-ees", &bdev->num_ees); - if (ret) + if (ret) { dev_err(bdev->dev, "num-ees unspecified in dt\n"); + return ret; + } }

ret = clk_prepare_enable(bdev->bamclk); diff --git a/drivers/dma/ti/edma.c b/drivers/dma/ti/edma.c index c0fa54132467..f7ddf588b7f9 100644 --- a/drivers/dma/ti/edma.c +++ b/drivers/dma/ti/edma.c @@ -2063,8 +2063,8 @@ static int edma_setup_from_hw(struct device *dev, struct edma_soc_info *pdata, * priority. So Q0 is the highest priority queue and the last queue has * the lowest priority. */ - queue_priority_map = devm_kcalloc(dev, ecc->num_tc + 1, sizeof(s8), - GFP_KERNEL); + queue_priority_map = devm_kcalloc(dev, ecc->num_tc + 1, + sizeof(*queue_priority_map), GFP_KERNEL); if (!queue_priority_map) return -ENOMEM;

diff --git a/drivers/edac/altera_edac.c b/drivers/edac/altera_edac.c index 54ec89415093..233e58278943 100644 --- a/drivers/edac/altera_edac.c +++ b/drivers/edac/altera_edac.c @@ -127,7 +127,6 @@ static ssize_t altr_sdr_mc_err_inject_write(struct file *file,

ptemp = dma_alloc_coherent(mci->pdev, 16, &dma_handle, GFP_KERNEL); if (!ptemp) { - dma_free_coherent(mci->pdev, 16, ptemp, dma_handle); edac_printk(KERN_ERR, EDAC_MC, "Inject: Buffer Allocation error\n"); return -ENOMEM; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c index f44b303ae287..eebac2e1a6c7 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c @@ -396,9 +396,6 @@ void amdgpu_ring_fini(struct amdgpu_ring *ring) dma_fence_put(ring->vmid_wait); ring->vmid_wait = NULL; ring->me = 0; - - if (!ring->is_mes_queue) - ring->adev->rings[ring->idx] = NULL; }

/** diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c index a61ecefdafc5..710328f12194 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v3_0.c @@ -1765,15 +1765,19 @@ static int vcn_v3_0_limit_sched(struct amdgpu_cs_parser *p, struct amdgpu_job *job) { struct drm_gpu_scheduler **scheds; - - /* The create msg must be in the first IB submitted */ - if (atomic_read(&job->base.entity->fence_seq)) - return -EINVAL; + struct dma_fence *fence;

/* if VCN0 is harvested, we can't support AV1 */ if (p->adev->vcn.harvest_config & AMDGPU_VCN_HARVEST_VCN0) return -EINVAL;

+ /* wait for all jobs to finish before switching to instance 0 */ + fence = amdgpu_ctx_get_fence(p->ctx, job->base.entity, ~0ull); + if (fence) { + dma_fence_wait(fence, false); + dma_fence_put(fence); + } + scheds = p->adev->gpu_sched[AMDGPU_HW_IP_VCN_DEC] [AMDGPU_RING_PRIO_DEFAULT].sched; drm_sched_entity_modify_sched(job->base.entity, scheds, 1); diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c index 29164289c5f3..43249e9f66d7 100644 --- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c +++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c @@ -1644,15 +1644,19 @@ static int vcn_v4_0_limit_sched(struct amdgpu_cs_parser *p, struct amdgpu_job *job) { struct drm_gpu_scheduler **scheds; - - /* The create msg must be in the first IB submitted */ - if (atomic_read(&job->base.entity->fence_seq)) - return -EINVAL; + struct dma_fence *fence;

/* if VCN0 is harvested, we can't support AV1 */ if (p->adev->vcn.harvest_config & AMDGPU_VCN_HARVEST_VCN0) return -EINVAL;

+ /* wait for all jobs to finish before switching to instance 0 */ + fence = amdgpu_ctx_get_fence(p->ctx, job->base.entity, ~0ull); + if (fence) { + dma_fence_wait(fence, false); + dma_fence_put(fence); + } + scheds = p->adev->gpu_sched[AMDGPU_HW_IP_VCN_ENC] [AMDGPU_RING_PRIO_0].sched; drm_sched_entity_modify_sched(job->base.entity, scheds, 1); @@ -1743,22 +1747,16 @@ static int vcn_v4_0_dec_msg(struct amdgpu_cs_parser *p, struct amdgpu_job *job,

#define RADEON_VCN_ENGINE_TYPE_ENCODE (0x00000002) #define RADEON_VCN_ENGINE_TYPE_DECODE (0x00000003) - #define RADEON_VCN_ENGINE_INFO (0x30000001) -#define RADEON_VCN_ENGINE_INFO_MAX_OFFSET 16 - #define RENCODE_ENCODE_STANDARD_AV1 2 #define RENCODE_IB_PARAM_SESSION_INIT 0x00000003 -#define RENCODE_IB_PARAM_SESSION_INIT_MAX_OFFSET 64

-/* return the offset in ib if id is found, -1 otherwise - * to speed up the searching we only search upto max_offset - */ -static int vcn_v4_0_enc_find_ib_param(struct amdgpu_ib *ib, uint32_t id, int max_offset) +/* return the offset in ib if id is found, -1 otherwise */ +static int vcn_v4_0_enc_find_ib_param(struct amdgpu_ib *ib, uint32_t id, int start) { int i;

- for (i = 0; i < ib->length_dw && i < max_offset && ib->ptr[i] >= 8; i += ib->ptr[i]/4) { + for (i = start; i < ib->length_dw && ib->ptr[i] >= 8; i += ib->ptr[i] / 4) { if (ib->ptr[i + 1] == id) return i; } @@ -1773,33 +1771,29 @@ static int vcn_v4_0_ring_patch_cs_in_place(struct amdgpu_cs_parser *p, struct amdgpu_vcn_decode_buffer *decode_buffer; uint64_t addr; uint32_t val; - int idx; + int idx = 0, sidx;

/* The first instance can decode anything */ if (!ring->me) return 0;

- /* RADEON_VCN_ENGINE_INFO is at the top of ib block */ - idx = vcn_v4_0_enc_find_ib_param(ib, RADEON_VCN_ENGINE_INFO, - RADEON_VCN_ENGINE_INFO_MAX_OFFSET); - if (idx < 0) /* engine info is missing */ - return 0; - - val = amdgpu_ib_get_value(ib, idx + 2); /* RADEON_VCN_ENGINE_TYPE */ - if (val == RADEON_VCN_ENGINE_TYPE_DECODE) { - decode_buffer = (struct amdgpu_vcn_decode_buffer *)&ib->ptr[idx + 6]; - - if (!(decode_buffer->valid_buf_flag & 0x1)) - return 0; - - addr = ((u64)decode_buffer->msg_buffer_address_hi) << 32 | - decode_buffer->msg_buffer_address_lo; - return vcn_v4_0_dec_msg(p, job, addr); - } else if (val == RADEON_VCN_ENGINE_TYPE_ENCODE) { - idx = vcn_v4_0_enc_find_ib_param(ib, RENCODE_IB_PARAM_SESSION_INIT, - RENCODE_IB_PARAM_SESSION_INIT_MAX_OFFSET); - if (idx >= 0 && ib->ptr[idx + 2] == RENCODE_ENCODE_STANDARD_AV1) - return vcn_v4_0_limit_sched(p, job); + while ((idx = vcn_v4_0_enc_find_ib_param(ib, RADEON_VCN_ENGINE_INFO, idx)) >= 0) { + val = amdgpu_ib_get_value(ib, idx + 2); /* RADEON_VCN_ENGINE_TYPE */ + if (val == RADEON_VCN_ENGINE_TYPE_DECODE) { + decode_buffer = (struct amdgpu_vcn_decode_buffer *)&ib->ptr[idx + 6]; + + if (!(decode_buffer->valid_buf_flag & 0x1)) + return 0; + + addr = ((u64)decode_buffer->msg_buffer_address_hi) << 32 | + decode_buffer->msg_buffer_address_lo; + return vcn_v4_0_dec_msg(p, job, addr); + } else if (val == RADEON_VCN_ENGINE_TYPE_ENCODE) { + sidx = vcn_v4_0_enc_find_ib_param(ib, RENCODE_IB_PARAM_SESSION_INIT, idx); + if (sidx >= 0 && ib->ptr[sidx + 2] == RENCODE_ENCODE_STANDARD_AV1) + return vcn_v4_0_limit_sched(p, job); + } + idx += ib->ptr[idx] / 4; } return 0; } diff --git a/drivers/gpu/drm/i915/display/intel_display_power.c b/drivers/gpu/drm/i915/display/intel_display_power.c index 9e01054c2430..8beeda343981 100644 --- a/drivers/gpu/drm/i915/display/intel_display_power.c +++ b/drivers/gpu/drm/i915/display/intel_display_power.c @@ -1170,7 +1170,7 @@ static void icl_mbus_init(struct drm_i915_private *dev_priv) if (DISPLAY_VER(dev_priv) == 12) abox_regs |= BIT(0);

- for_each_set_bit(i, &abox_regs, sizeof(abox_regs)) + for_each_set_bit(i, &abox_regs, BITS_PER_TYPE(abox_regs)) intel_de_rmw(dev_priv, MBUS_ABOX_CTL(i), mask, val); }

@@ -1623,11 +1623,11 @@ static void tgl_bw_buddy_init(struct drm_i915_private *dev_priv) if (table[config].page_mask == 0) { drm_dbg(&dev_priv->drm, "Unknown memory configuration; disabling address buddy logic.\n"); - for_each_set_bit(i, &abox_mask, sizeof(abox_mask)) + for_each_set_bit(i, &abox_mask, BITS_PER_TYPE(abox_mask)) intel_de_write(dev_priv, BW_BUDDY_CTL(i), BW_BUDDY_DISABLE); } else { - for_each_set_bit(i, &abox_mask, sizeof(abox_mask)) { + for_each_set_bit(i, &abox_mask, BITS_PER_TYPE(abox_mask)) { intel_de_write(dev_priv, BW_BUDDY_PAGE_MASK(i), table[config].page_mask);

diff --git a/drivers/gpu/drm/mediatek/mtk_drm_drv.c b/drivers/gpu/drm/mediatek/mtk_drm_drv.c index bfa1070a5f08..f1f73c1e7b5c 100644 --- a/drivers/gpu/drm/mediatek/mtk_drm_drv.c +++ b/drivers/gpu/drm/mediatek/mtk_drm_drv.c @@ -365,11 +365,11 @@ static bool mtk_drm_get_all_drm_priv(struct device *dev)

of_id = of_match_node(mtk_drm_of_ids, node); if (!of_id) - goto next_put_node; + continue;

pdev = of_find_device_by_node(node); if (!pdev) - goto next_put_node; + continue;

drm_dev = device_find_child(&pdev->dev, NULL, mtk_drm_match); if (!drm_dev) @@ -395,11 +395,10 @@ static bool mtk_drm_get_all_drm_priv(struct device *dev) next_put_device_pdev_dev: put_device(&pdev->dev);

-next_put_node: - of_node_put(node); - - if (cnt == MAX_CRTC) + if (cnt == MAX_CRTC) { + of_node_put(node); break; + } }

if (drm_priv->data->mmsys_dev_num == cnt) { diff --git a/drivers/i2c/busses/i2c-i801.c b/drivers/i2c/busses/i2c-i801.c index 18c04f5e41d9..89fdc75cdcfa 100644 --- a/drivers/i2c/busses/i2c-i801.c +++ b/drivers/i2c/busses/i2c-i801.c @@ -1051,7 +1051,7 @@ static const struct pci_device_id i801_ids[] = { { PCI_DEVICE_DATA(INTEL, METEOR_LAKE_P_SMBUS, FEATURES_ICH5 | FEATURE_TCO_CNL) }, { PCI_DEVICE_DATA(INTEL, METEOR_LAKE_SOC_S_SMBUS, FEATURES_ICH5 | FEATURE_TCO_CNL) }, { PCI_DEVICE_DATA(INTEL, METEOR_LAKE_PCH_S_SMBUS, FEATURES_ICH5 | FEATURE_TCO_CNL) }, - { PCI_DEVICE_DATA(INTEL, BIRCH_STREAM_SMBUS, FEATURES_ICH5 | FEATURE_TCO_CNL) }, + { PCI_DEVICE_DATA(INTEL, BIRCH_STREAM_SMBUS, FEATURES_ICH5) }, { PCI_DEVICE_DATA(INTEL, ARROW_LAKE_H_SMBUS, FEATURES_ICH5 | FEATURE_TCO_CNL) }, { PCI_DEVICE_DATA(INTEL, PANTHER_LAKE_H_SMBUS, FEATURES_ICH5 | FEATURE_TCO_CNL) }, { PCI_DEVICE_DATA(INTEL, PANTHER_LAKE_P_SMBUS, FEATURES_ICH5 | FEATURE_TCO_CNL) }, diff --git a/drivers/input/misc/iqs7222.c b/drivers/input/misc/iqs7222.c index ce7e977cc8a7..eb0e0b37eb41 100644 --- a/drivers/input/misc/iqs7222.c +++ b/drivers/input/misc/iqs7222.c @@ -2430,6 +2430,9 @@ static int iqs7222_parse_chan(struct iqs7222_private *iqs7222, if (error) return error;

+ if (!iqs7222->kp_type[chan_index][i]) + continue; + if (!dev_desc->event_offset) continue;

diff --git a/drivers/input/serio/i8042-acpipnpio.h b/drivers/input/serio/i8042-acpipnpio.h index 8813db7eec39..630cdd5a1328 100644 --- a/drivers/input/serio/i8042-acpipnpio.h +++ b/drivers/input/serio/i8042-acpipnpio.h @@ -1155,6 +1155,20 @@ static const struct dmi_system_id i8042_dmi_quirk_table[] __initconst = { .driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS | SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP) }, + { + .matches = { + DMI_MATCH(DMI_BOARD_NAME, "XxHP4NAx"), + }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS | + SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP) + }, + { + .matches = { + DMI_MATCH(DMI_BOARD_NAME, "XxKK4NAx_XxSP4NAx"), + }, + .driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS | + SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP) + }, /* * A lot of modern Clevo barebones have touchpad and/or keyboard issues * after suspend fixable with the forcenorestore quirk. diff --git a/drivers/media/i2c/imx214.c b/drivers/media/i2c/imx214.c index 2f9c8582f940..db40008f31cf 100644 --- a/drivers/media/i2c/imx214.c +++ b/drivers/media/i2c/imx214.c @@ -20,7 +20,9 @@ #include <media/v4l2-subdev.h>

#define IMX214_DEFAULT_CLK_FREQ 24000000 -#define IMX214_DEFAULT_LINK_FREQ 480000000 +#define IMX214_DEFAULT_LINK_FREQ 600000000 +/* Keep wrong link frequency for backward compatibility */ +#define IMX214_DEFAULT_LINK_FREQ_LEGACY 480000000 #define IMX214_DEFAULT_PIXEL_RATE ((IMX214_DEFAULT_LINK_FREQ * 8LL) / 10) #define IMX214_FPS 30 #define IMX214_MBUS_CODE MEDIA_BUS_FMT_SRGGB10_1X10 @@ -892,17 +894,26 @@ static int imx214_parse_fwnode(struct device *dev) goto done; }

- for (i = 0; i < bus_cfg.nr_of_link_frequencies; i++) + if (bus_cfg.nr_of_link_frequencies != 1) + dev_warn(dev, "Only one link-frequency supported, please review your DT. Continuing anyway\n"); + + for (i = 0; i < bus_cfg.nr_of_link_frequencies; i++) { if (bus_cfg.link_frequencies[i] == IMX214_DEFAULT_LINK_FREQ) break; - - if (i == bus_cfg.nr_of_link_frequencies) { - dev_err(dev, "link-frequencies %d not supported, Please review your DT\n", - IMX214_DEFAULT_LINK_FREQ); - ret = -EINVAL; - goto done; + if (bus_cfg.link_frequencies[i] == + IMX214_DEFAULT_LINK_FREQ_LEGACY) { + dev_warn(dev, + "link-frequencies %d not supported, please review your DT. Continuing anyway\n", + IMX214_DEFAULT_LINK_FREQ); + break; + } }

+ if (i == bus_cfg.nr_of_link_frequencies) + ret = dev_err_probe(dev, -EINVAL, + "link-frequencies %d not supported, please review your DT\n", + IMX214_DEFAULT_LINK_FREQ); + done: v4l2_fwnode_endpoint_free(&bus_cfg); fwnode_handle_put(endpoint); diff --git a/drivers/mtd/nand/raw/atmel/nand-controller.c b/drivers/mtd/nand/raw/atmel/nand-controller.c index d4fd1302008e..c5aff27ec4a8 100644 --- a/drivers/mtd/nand/raw/atmel/nand-controller.c +++ b/drivers/mtd/nand/raw/atmel/nand-controller.c @@ -1378,13 +1378,23 @@ static int atmel_smc_nand_prepare_smcconf(struct atmel_nand *nand, return ret;

/* - * The write cycle timing is directly matching tWC, but is also + * Read setup timing depends on the operation done on the NAND: + * + * NRD_SETUP = max(tAR, tCLR) + */ + timeps = max(conf->timings.sdr.tAR_min, conf->timings.sdr.tCLR_min); + ncycles = DIV_ROUND_UP(timeps, mckperiodps); + totalcycles += ncycles; + ret = atmel_smc_cs_conf_set_setup(smcconf, ATMEL_SMC_NRD_SHIFT, ncycles); + if (ret) + return ret; + + /* + * The read cycle timing is directly matching tRC, but is also * dependent on the setup and hold timings we calculated earlier, * which gives: * - * NRD_CYCLE = max(tRC, NRD_PULSE + NRD_HOLD) - * - * NRD_SETUP is always 0. + * NRD_CYCLE = max(tRC, NRD_SETUP + NRD_PULSE + NRD_HOLD) */ ncycles = DIV_ROUND_UP(conf->timings.sdr.tRC_min, mckperiodps); ncycles = max(totalcycles, ncycles); diff --git a/drivers/mtd/nand/raw/stm32_fmc2_nand.c b/drivers/mtd/nand/raw/stm32_fmc2_nand.c index 88811139aaf5..c79562983971 100644 --- a/drivers/mtd/nand/raw/stm32_fmc2_nand.c +++ b/drivers/mtd/nand/raw/stm32_fmc2_nand.c @@ -263,6 +263,7 @@ struct stm32_fmc2_nfc { struct sg_table dma_data_sg; struct sg_table dma_ecc_sg; u8 *ecc_buf; + dma_addr_t dma_ecc_addr; int dma_ecc_len;

struct completion complete; @@ -885,17 +886,10 @@ static int stm32_fmc2_nfc_xfer(struct nand_chip *chip, const u8 *buf,

if (!write_data && !raw) { /* Configure DMA ECC status */ - p = nfc->ecc_buf; for_each_sg(nfc->dma_ecc_sg.sgl, sg, eccsteps, s) { - sg_set_buf(sg, p, nfc->dma_ecc_len); - p += nfc->dma_ecc_len; - } - - ret = dma_map_sg(nfc->dev, nfc->dma_ecc_sg.sgl, - eccsteps, dma_data_dir); - if (!ret) { - ret = -EIO; - goto err_unmap_data; + sg_dma_address(sg) = nfc->dma_ecc_addr + + s * nfc->dma_ecc_len; + sg_dma_len(sg) = nfc->dma_ecc_len; }

desc_ecc = dmaengine_prep_slave_sg(nfc->dma_ecc_ch, @@ -904,7 +898,7 @@ static int stm32_fmc2_nfc_xfer(struct nand_chip *chip, const u8 *buf, DMA_PREP_INTERRUPT); if (!desc_ecc) { ret = -ENOMEM; - goto err_unmap_ecc; + goto err_unmap_data; }

reinit_completion(&nfc->dma_ecc_complete); @@ -912,7 +906,7 @@ static int stm32_fmc2_nfc_xfer(struct nand_chip *chip, const u8 *buf, desc_ecc->callback_param = &nfc->dma_ecc_complete; ret = dma_submit_error(dmaengine_submit(desc_ecc)); if (ret) - goto err_unmap_ecc; + goto err_unmap_data;

dma_async_issue_pending(nfc->dma_ecc_ch); } @@ -932,7 +926,7 @@ static int stm32_fmc2_nfc_xfer(struct nand_chip *chip, const u8 *buf, if (!write_data && !raw) dmaengine_terminate_all(nfc->dma_ecc_ch); ret = -ETIMEDOUT; - goto err_unmap_ecc; + goto err_unmap_data; }

/* Wait DMA data transfer completion */ @@ -952,11 +946,6 @@ static int stm32_fmc2_nfc_xfer(struct nand_chip *chip, const u8 *buf, } }

-err_unmap_ecc: - if (!write_data && !raw) - dma_unmap_sg(nfc->dev, nfc->dma_ecc_sg.sgl, - eccsteps, dma_data_dir); - err_unmap_data: dma_unmap_sg(nfc->dev, nfc->dma_data_sg.sgl, eccsteps, dma_data_dir);

@@ -979,9 +968,21 @@ static int stm32_fmc2_nfc_seq_write(struct nand_chip *chip, const u8 *buf,

/* Write oob */ if (oob_required) { - ret = nand_change_write_column_op(chip, mtd->writesize, - chip->oob_poi, mtd->oobsize, - false); + unsigned int offset_in_page = mtd->writesize; + const void *buf = chip->oob_poi; + unsigned int len = mtd->oobsize; + + if (!raw) { + struct mtd_oob_region oob_free; + + mtd_ooblayout_free(mtd, 0, &oob_free); + offset_in_page += oob_free.offset; + buf += oob_free.offset; + len = oob_free.length; + } + + ret = nand_change_write_column_op(chip, offset_in_page, + buf, len, false); if (ret) return ret; } @@ -1582,7 +1583,8 @@ static int stm32_fmc2_nfc_dma_setup(struct stm32_fmc2_nfc *nfc) return ret;

/* Allocate a buffer to store ECC status registers */ - nfc->ecc_buf = devm_kzalloc(nfc->dev, FMC2_MAX_ECC_BUF_LEN, GFP_KERNEL); + nfc->ecc_buf = dmam_alloc_coherent(nfc->dev, FMC2_MAX_ECC_BUF_LEN, + &nfc->dma_ecc_addr, GFP_KERNEL); if (!nfc->ecc_buf) return -ENOMEM;

diff --git a/drivers/net/can/xilinx_can.c b/drivers/net/can/xilinx_can.c index abe58f103043..57d1209134f1 100644 --- a/drivers/net/can/xilinx_can.c +++ b/drivers/net/can/xilinx_can.c @@ -628,14 +628,6 @@ static void xcan_write_frame(struct net_device *ndev, struct sk_buff *skb, dlc |= XCAN_DLCR_EDL_MASK; }

- if (!(priv->devtype.flags & XCAN_FLAG_TX_MAILBOXES) && - (priv->devtype.flags & XCAN_FLAG_TXFEMP)) - can_put_echo_skb(skb, ndev, priv->tx_head % priv->tx_max, 0); - else - can_put_echo_skb(skb, ndev, 0, 0); - - priv->tx_head++; - priv->write_reg(priv, XCAN_FRAME_ID_OFFSET(frame_offset), id); /* If the CAN frame is RTR frame this write triggers transmission * (not on CAN FD) @@ -668,6 +660,14 @@ static void xcan_write_frame(struct net_device *ndev, struct sk_buff *skb, data[1]); } } + + if (!(priv->devtype.flags & XCAN_FLAG_TX_MAILBOXES) && + (priv->devtype.flags & XCAN_FLAG_TXFEMP)) + can_put_echo_skb(skb, ndev, priv->tx_head % priv->tx_max, 0); + else + can_put_echo_skb(skb, ndev, 0, 0); + + priv->tx_head++; }

/** diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index 2a8b5429df59..8352d9b6469f 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -2300,7 +2300,8 @@ static void fec_enet_phy_reset_after_clk_enable(struct net_device *ndev) */ phy_dev = of_phy_find_device(fep->phy_node); phy_reset_after_clk_enable(phy_dev); - put_device(&phy_dev->mdio.dev); + if (phy_dev) + put_device(&phy_dev->mdio.dev); } }

diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index b749aa3e783f..72869336e3a9 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -4210,7 +4210,7 @@ static int i40e_vsi_request_irq_msix(struct i40e_vsi *vsi, char *basename) irq_num = pf->msix_entries[base + vector].vector; irq_set_affinity_notifier(irq_num, NULL); irq_update_affinity_hint(irq_num, NULL); - free_irq(irq_num, &vsi->q_vectors[vector]); + free_irq(irq_num, vsi->q_vectors[vector]); } return err; } diff --git a/drivers/net/ethernet/intel/igb/igb_ethtool.c b/drivers/net/ethernet/intel/igb/igb_ethtool.c index 92b2be06a6e9..f11cba65e5d8 100644 --- a/drivers/net/ethernet/intel/igb/igb_ethtool.c +++ b/drivers/net/ethernet/intel/igb/igb_ethtool.c @@ -2081,11 +2081,8 @@ static void igb_diag_test(struct net_device *netdev, } else { dev_info(&adapter->pdev->dev, "online testing starting\n");

- /* PHY is powered down when interface is down */ - if (if_running && igb_link_test(adapter, &data[TEST_LINK])) + if (igb_link_test(adapter, &data[TEST_LINK])) eth_test->flags |= ETH_TEST_FL_FAILED; - else - data[TEST_LINK] = 0;

/* Online tests aren't run; pass by default */ data[TEST_REG] = 0; diff --git a/drivers/net/phy/mdio_bus.c b/drivers/net/phy/mdio_bus.c index e02706b7cc1e..f1fac89721ed 100644 --- a/drivers/net/phy/mdio_bus.c +++ b/drivers/net/phy/mdio_bus.c @@ -99,6 +99,7 @@ int mdiobus_unregister_device(struct mdio_device *mdiodev) if (mdiodev->bus->mdio_map[mdiodev->addr] != mdiodev) return -EINVAL;

+ gpiod_put(mdiodev->reset_gpio); reset_control_put(mdiodev->reset_ctrl);

mdiodev->bus->mdio_map[mdiodev->addr] = NULL; @@ -775,9 +776,6 @@ void mdiobus_unregister(struct mii_bus *bus) if (!mdiodev) continue;

- if (mdiodev->reset_gpio) - gpiod_put(mdiodev->reset_gpio); - mdiodev->device_remove(mdiodev); mdiodev->device_free(mdiodev); } diff --git a/drivers/phy/tegra/xusb-tegra210.c b/drivers/phy/tegra/xusb-tegra210.c index ebc8a7e21a31..3409924498e9 100644 --- a/drivers/phy/tegra/xusb-tegra210.c +++ b/drivers/phy/tegra/xusb-tegra210.c @@ -3164,18 +3164,22 @@ tegra210_xusb_padctl_probe(struct device *dev, }

pdev = of_find_device_by_node(np); + of_node_put(np); if (!pdev) { dev_warn(dev, "PMC device is not available\n"); goto out; }

- if (!platform_get_drvdata(pdev)) + if (!platform_get_drvdata(pdev)) { + put_device(&pdev->dev); return ERR_PTR(-EPROBE_DEFER); + }

padctl->regmap = dev_get_regmap(&pdev->dev, "usb_sleepwalk"); if (!padctl->regmap) dev_info(dev, "failed to find PMC regmap\n");

+ put_device(&pdev->dev); out: return &padctl->base; } diff --git a/drivers/phy/ti/phy-ti-pipe3.c b/drivers/phy/ti/phy-ti-pipe3.c index 507e1552db5e..3127f3702c3a 100644 --- a/drivers/phy/ti/phy-ti-pipe3.c +++ b/drivers/phy/ti/phy-ti-pipe3.c @@ -666,12 +666,20 @@ static int ti_pipe3_get_clk(struct ti_pipe3 *phy) return 0; }

+static void ti_pipe3_put_device(void *_dev) +{ + struct device *dev = _dev; + + put_device(dev); +} + static int ti_pipe3_get_sysctrl(struct ti_pipe3 *phy) { struct device *dev = phy->dev; struct device_node *node = dev->of_node; struct device_node *control_node; struct platform_device *control_pdev; + int ret;

phy->phy_power_syscon = syscon_regmap_lookup_by_phandle(node, "syscon-phy-power"); @@ -703,6 +711,11 @@ static int ti_pipe3_get_sysctrl(struct ti_pipe3 *phy) }

phy->control_dev = &control_pdev->dev; + + ret = devm_add_action_or_reset(dev, ti_pipe3_put_device, + phy->control_dev); + if (ret) + return ret; }

if (phy->mode == PIPE3_MODE_PCIE) { diff --git a/drivers/regulator/sy7636a-regulator.c b/drivers/regulator/sy7636a-regulator.c index d1e7ba1fb3e1..27e3d939b7bb 100644 --- a/drivers/regulator/sy7636a-regulator.c +++ b/drivers/regulator/sy7636a-regulator.c @@ -83,9 +83,11 @@ static int sy7636a_regulator_probe(struct platform_device *pdev) if (!regmap) return -EPROBE_DEFER;

- gdp = devm_gpiod_get(pdev->dev.parent, "epd-pwr-good", GPIOD_IN); + device_set_of_node_from_dev(&pdev->dev, pdev->dev.parent); + + gdp = devm_gpiod_get(&pdev->dev, "epd-pwr-good", GPIOD_IN); if (IS_ERR(gdp)) { - dev_err(pdev->dev.parent, "Power good GPIO fault %ld\n", PTR_ERR(gdp)); + dev_err(&pdev->dev, "Power good GPIO fault %ld\n", PTR_ERR(gdp)); return PTR_ERR(gdp); }

@@ -105,7 +107,6 @@ static int sy7636a_regulator_probe(struct platform_device *pdev) }

config.dev = &pdev->dev; - config.dev->of_node = pdev->dev.parent->of_node; config.regmap = regmap;

rdev = devm_regulator_register(&pdev->dev, &desc, &config); diff --git a/drivers/tty/hvc/hvc_console.c b/drivers/tty/hvc/hvc_console.c index 959fae54ca39..4c252bbbf8e2 100644 --- a/drivers/tty/hvc/hvc_console.c +++ b/drivers/tty/hvc/hvc_console.c @@ -543,10 +543,10 @@ static ssize_t hvc_write(struct tty_struct *tty, const u8 *buf, size_t count) }

/* - * Racy, but harmless, kick thread if there is still pending data. + * Kick thread to flush if there's still pending data + * or to wakeup the write queue. */ - if (hp->n_outbuf) - hvc_kick(); + hvc_kick();

return written; } diff --git a/drivers/tty/serial/sc16is7xx.c b/drivers/tty/serial/sc16is7xx.c index 8a2ce2ca6b39..66a88bba8f15 100644 --- a/drivers/tty/serial/sc16is7xx.c +++ b/drivers/tty/serial/sc16is7xx.c @@ -1163,17 +1163,6 @@ static int sc16is7xx_startup(struct uart_port *port) sc16is7xx_port_write(port, SC16IS7XX_FCR_REG, SC16IS7XX_FCR_FIFO_BIT);

- /* Enable EFR */ - sc16is7xx_port_write(port, SC16IS7XX_LCR_REG, - SC16IS7XX_LCR_CONF_MODE_B); - - regcache_cache_bypass(one->regmap, true); - - /* Enable write access to enhanced features and internal clock div */ - sc16is7xx_port_update(port, SC16IS7XX_EFR_REG, - SC16IS7XX_EFR_ENABLE_BIT, - SC16IS7XX_EFR_ENABLE_BIT); - /* Enable TCR/TLR */ sc16is7xx_port_update(port, SC16IS7XX_MCR_REG, SC16IS7XX_MCR_TCRTLR_BIT, @@ -1185,7 +1174,8 @@ static int sc16is7xx_startup(struct uart_port *port) SC16IS7XX_TCR_RX_RESUME(24) | SC16IS7XX_TCR_RX_HALT(48));

- regcache_cache_bypass(one->regmap, false); + /* Disable TCR/TLR access */ + sc16is7xx_port_update(port, SC16IS7XX_MCR_REG, SC16IS7XX_MCR_TCRTLR_BIT, 0);

/* Now, initialize the UART */ sc16is7xx_port_write(port, SC16IS7XX_LCR_REG, SC16IS7XX_LCR_WORD_LEN_8); diff --git a/drivers/usb/gadget/function/f_midi2.c b/drivers/usb/gadget/function/f_midi2.c index 90536f47906c..d7ed50ff380c 100644 --- a/drivers/usb/gadget/function/f_midi2.c +++ b/drivers/usb/gadget/function/f_midi2.c @@ -1601,6 +1601,7 @@ static int f_midi2_create_card(struct f_midi2 *midi2) strscpy(fb->info.name, ump_fb_name(b), sizeof(fb->info.name)); } + snd_ump_update_group_attrs(ump); }

for (i = 0; i < midi2->num_eps; i++) { @@ -1738,9 +1739,12 @@ static int f_midi2_create_usb_configs(struct f_midi2 *midi2, case USB_SPEED_HIGH: midi2_midi1_ep_out_desc.wMaxPacketSize = cpu_to_le16(512); midi2_midi1_ep_in_desc.wMaxPacketSize = cpu_to_le16(512); - for (i = 0; i < midi2->num_eps; i++) + for (i = 0; i < midi2->num_eps; i++) { midi2_midi2_ep_out_desc[i].wMaxPacketSize = cpu_to_le16(512); + midi2_midi2_ep_in_desc[i].wMaxPacketSize = + cpu_to_le16(512); + } fallthrough; case USB_SPEED_FULL: midi1_in_eps = midi2_midi1_ep_in_descs; @@ -1749,9 +1753,12 @@ static int f_midi2_create_usb_configs(struct f_midi2 *midi2, case USB_SPEED_SUPER: midi2_midi1_ep_out_desc.wMaxPacketSize = cpu_to_le16(1024); midi2_midi1_ep_in_desc.wMaxPacketSize = cpu_to_le16(1024); - for (i = 0; i < midi2->num_eps; i++) + for (i = 0; i < midi2->num_eps; i++) { midi2_midi2_ep_out_desc[i].wMaxPacketSize = cpu_to_le16(1024); + midi2_midi2_ep_in_desc[i].wMaxPacketSize = + cpu_to_le16(1024); + } midi1_in_eps = midi2_midi1_ep_in_ss_descs; midi1_out_eps = midi2_midi1_ep_out_ss_descs; break; diff --git a/drivers/usb/gadget/udc/dummy_hcd.c b/drivers/usb/gadget/udc/dummy_hcd.c index d5d89fadde43..a06f56c08e19 100644 --- a/drivers/usb/gadget/udc/dummy_hcd.c +++ b/drivers/usb/gadget/udc/dummy_hcd.c @@ -764,8 +764,7 @@ static int dummy_dequeue(struct usb_ep *_ep, struct usb_request *_req) if (!dum->driver) return -ESHUTDOWN;

- local_irq_save(flags); - spin_lock(&dum->lock); + spin_lock_irqsave(&dum->lock, flags); list_for_each_entry(iter, &ep->queue, queue) { if (&iter->req != _req) continue; @@ -775,15 +774,16 @@ static int dummy_dequeue(struct usb_ep *_ep, struct usb_request *_req) retval = 0; break; } - spin_unlock(&dum->lock);

if (retval == 0) { dev_dbg(udc_dev(dum), "dequeued req %p from %s, len %d buf %p\n", req, _ep->name, _req->length, _req->buf); + spin_unlock(&dum->lock); usb_gadget_giveback_request(_ep, _req); + spin_lock(&dum->lock); } - local_irq_restore(flags); + spin_unlock_irqrestore(&dum->lock, flags); return retval; }

diff --git a/drivers/usb/host/xhci-mem.c b/drivers/usb/host/xhci-mem.c index 04718048b74b..621f12c11cbc 100644 --- a/drivers/usb/host/xhci-mem.c +++ b/drivers/usb/host/xhci-mem.c @@ -945,7 +945,7 @@ static void xhci_free_virt_devices_depth_first(struct xhci_hcd *xhci, int slot_i out: /* we are now at a leaf device */ xhci_debugfs_remove_slot(xhci, slot_id); - xhci_free_virt_device(xhci, vdev, slot_id); + xhci_free_virt_device(xhci, xhci->devs[slot_id], slot_id); }

int xhci_alloc_virt_device(struct xhci_hcd *xhci, int slot_id, diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c index ac72b04c997b..ef546f660b99 100644 --- a/drivers/usb/serial/option.c +++ b/drivers/usb/serial/option.c @@ -1322,7 +1322,18 @@ static const struct usb_device_id option_ids[] = { .driver_info = NCTRL(0) | RSVD(3) }, { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1033, 0xff), /* Telit LE910C1-EUX (ECM) */ .driver_info = NCTRL(0) }, + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1034, 0xff), /* Telit LE910C4-WWX (rmnet) */ + .driver_info = RSVD(2) }, { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1035, 0xff) }, /* Telit LE910C4-WWX (ECM) */ + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1036, 0xff) }, /* Telit LE910C4-WWX */ + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1037, 0xff), /* Telit LE910C4-WWX (rmnet) */ + .driver_info = NCTRL(0) | NCTRL(1) | RSVD(4) }, + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1038, 0xff), /* Telit LE910C4-WWX (rmnet) */ + .driver_info = NCTRL(0) | RSVD(3) }, + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x103b, 0xff), /* Telit LE910C4-WWX */ + .driver_info = NCTRL(0) | NCTRL(1) }, + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x103c, 0xff), /* Telit LE910C4-WWX */ + .driver_info = NCTRL(0) }, { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE922_USBCFG0), .driver_info = RSVD(0) | RSVD(1) | NCTRL(2) | RSVD(3) }, { USB_DEVICE(TELIT_VENDOR_ID, TELIT_PRODUCT_LE922_USBCFG1), @@ -1369,6 +1380,12 @@ static const struct usb_device_id option_ids[] = { .driver_info = NCTRL(0) | RSVD(1) }, { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1075, 0xff), /* Telit FN990A (PCIe) */ .driver_info = RSVD(0) }, + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1077, 0xff), /* Telit FN990A (rmnet + audio) */ + .driver_info = NCTRL(0) | RSVD(1) | RSVD(2) }, + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1078, 0xff), /* Telit FN990A (MBIM + audio) */ + .driver_info = NCTRL(0) | RSVD(1) }, + { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1079, 0xff), /* Telit FN990A (RNDIS + audio) */ + .driver_info = NCTRL(2) | RSVD(3) }, { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1080, 0xff), /* Telit FE990A (rmnet) */ .driver_info = NCTRL(0) | RSVD(1) | RSVD(2) }, { USB_DEVICE_INTERFACE_CLASS(TELIT_VENDOR_ID, 0x1081, 0xff), /* Telit FE990A (MBIM) */ diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c index 48b06459bc48..ccf94c5fbfdf 100644 --- a/fs/btrfs/extent_io.c +++ b/fs/btrfs/extent_io.c @@ -103,6 +103,25 @@ struct btrfs_bio_ctrl { blk_opf_t opf; btrfs_bio_end_io_t end_io_func; struct writeback_control *wbc; + struct readahead_control *ractl; + + /* + * The start offset of the last used extent map by a read operation. + * + * This is for proper compressed read merge. + * U64_MAX means we are starting the read and have made no progress yet. + * + * The current btrfs_bio_is_contig() only uses disk_bytenr as + * the condition to check if the read can be merged with previous + * bio, which is not correct. E.g. two file extents pointing to the + * same extent but with different offset. + * + * So here we need to do extra checks to only merge reads that are + * covered by the same extent map. + * Just extent_map::start will be enough, as they are unique + * inside the same inode. + */ + u64 last_em_start; };

static void submit_one_bio(struct btrfs_bio_ctrl *bio_ctrl) @@ -952,6 +971,23 @@ __get_extent_map(struct inode *inode, struct page *page, size_t pg_offset, } return em; } + +static void btrfs_readahead_expand(struct readahead_control *ractl, + const struct extent_map *em) +{ + const u64 ra_pos = readahead_pos(ractl); + const u64 ra_end = ra_pos + readahead_length(ractl); + const u64 em_end = em->start + em->ram_bytes; + + /* No expansion for holes and inline extents. */ + if (em->block_start > EXTENT_MAP_LAST_BYTE) + return; + + ASSERT(em_end >= ra_pos); + if (em_end > ra_end) + readahead_expand(ractl, ra_pos, em_end - ra_pos); +} + /* * basic readpage implementation. Locked extent state structs are inserted * into the tree that are removed when the IO is done (by the end_io @@ -960,7 +996,7 @@ __get_extent_map(struct inode *inode, struct page *page, size_t pg_offset, * return 0 on success, otherwise return error */ static int btrfs_do_readpage(struct page *page, struct extent_map **em_cached, - struct btrfs_bio_ctrl *bio_ctrl, u64 *prev_em_start) + struct btrfs_bio_ctrl *bio_ctrl) { struct inode *inode = page->mapping->host; struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb); @@ -1023,6 +1059,17 @@ static int btrfs_do_readpage(struct page *page, struct extent_map **em_cached,

iosize = min(extent_map_end(em) - cur, end - cur + 1); iosize = ALIGN(iosize, blocksize); + + /* + * Only expand readahead for extents which are already creating + * the pages anyway in add_ra_bio_pages, which is compressed + * extents in the non subpage case. + */ + if (bio_ctrl->ractl && + !btrfs_is_subpage(fs_info, page) && + compress_type != BTRFS_COMPRESS_NONE) + btrfs_readahead_expand(bio_ctrl->ractl, em); + if (compress_type != BTRFS_COMPRESS_NONE) disk_bytenr = em->block_start; else @@ -1066,12 +1113,11 @@ static int btrfs_do_readpage(struct page *page, struct extent_map **em_cached, * non-optimal behavior (submitting 2 bios for the same extent). */ if (test_bit(EXTENT_FLAG_COMPRESSED, &em->flags) && - prev_em_start && *prev_em_start != (u64)-1 && - *prev_em_start != em->start) + bio_ctrl->last_em_start != (u64)-1 && + bio_ctrl->last_em_start != em->start) force_bio_submit = true;

- if (prev_em_start) - *prev_em_start = em->start; + bio_ctrl->last_em_start = em->start;

free_extent_map(em); em = NULL; @@ -1117,12 +1163,15 @@ int btrfs_read_folio(struct file *file, struct folio *folio) struct btrfs_inode *inode = BTRFS_I(page->mapping->host); u64 start = page_offset(page); u64 end = start + PAGE_SIZE - 1; - struct btrfs_bio_ctrl bio_ctrl = { .opf = REQ_OP_READ }; + struct btrfs_bio_ctrl bio_ctrl = { + .opf = REQ_OP_READ, + .last_em_start = (u64)-1, + }; int ret;

btrfs_lock_and_flush_ordered_range(inode, start, end, NULL);

- ret = btrfs_do_readpage(page, NULL, &bio_ctrl, NULL); + ret = btrfs_do_readpage(page, NULL, &bio_ctrl); /* * If btrfs_do_readpage() failed we will want to submit the assembled * bio to do the cleanup. @@ -1134,8 +1183,7 @@ int btrfs_read_folio(struct file *file, struct folio *folio) static inline void contiguous_readpages(struct page *pages[], int nr_pages, u64 start, u64 end, struct extent_map **em_cached, - struct btrfs_bio_ctrl *bio_ctrl, - u64 *prev_em_start) + struct btrfs_bio_ctrl *bio_ctrl) { struct btrfs_inode *inode = BTRFS_I(pages[0]->mapping->host); int index; @@ -1143,8 +1191,7 @@ static inline void contiguous_readpages(struct page *pages[], int nr_pages, btrfs_lock_and_flush_ordered_range(inode, start, end, NULL);

for (index = 0; index < nr_pages; index++) { - btrfs_do_readpage(pages[index], em_cached, bio_ctrl, - prev_em_start); + btrfs_do_readpage(pages[index], em_cached, bio_ctrl); put_page(pages[index]); } } @@ -2224,10 +2271,13 @@ int extent_writepages(struct address_space *mapping,

void extent_readahead(struct readahead_control *rac) { - struct btrfs_bio_ctrl bio_ctrl = { .opf = REQ_OP_READ | REQ_RAHEAD }; + struct btrfs_bio_ctrl bio_ctrl = { + .opf = REQ_OP_READ | REQ_RAHEAD, + .ractl = rac, + .last_em_start = (u64)-1, + }; struct page *pagepool[16]; struct extent_map *em_cached = NULL; - u64 prev_em_start = (u64)-1; int nr;

while ((nr = readahead_page_batch(rac, pagepool))) { @@ -2235,7 +2285,7 @@ void extent_readahead(struct readahead_control *rac) u64 contig_end = contig_start + readahead_batch_length(rac) - 1;

contiguous_readpages(pagepool, nr, contig_start, contig_end, - &em_cached, &bio_ctrl, &prev_em_start); + &em_cached, &bio_ctrl); }

if (em_cached) diff --git a/fs/fuse/file.c b/fs/fuse/file.c index 3e4c3fcb588b..952c99fcb636 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -3106,7 +3106,7 @@ static ssize_t __fuse_copy_file_range(struct file *file_in, loff_t pos_in, .nodeid_out = ff_out->nodeid, .fh_out = ff_out->fh, .off_out = pos_out, - .len = len, + .len = min_t(size_t, len, UINT_MAX & PAGE_MASK), .flags = flags }; struct fuse_write_out outarg; @@ -3172,6 +3172,9 @@ static ssize_t __fuse_copy_file_range(struct file *file_in, loff_t pos_in, fc->no_copy_file_range = 1; err = -EOPNOTSUPP; } + if (!err && outarg.size > len) + err = -EIO; + if (err) goto out;

diff --git a/fs/kernfs/file.c b/fs/kernfs/file.c index 6b90fea6cca2..257ba5398387 100644 --- a/fs/kernfs/file.c +++ b/fs/kernfs/file.c @@ -70,6 +70,24 @@ static struct kernfs_open_node *of_on(struct kernfs_open_file *of) !list_empty(&of->list)); }

+/* Get active reference to kernfs node for an open file */ +static struct kernfs_open_file *kernfs_get_active_of(struct kernfs_open_file *of) +{ + /* Skip if file was already released */ + if (unlikely(of->released)) + return NULL; + + if (!kernfs_get_active(of->kn)) + return NULL; + + return of; +} + +static void kernfs_put_active_of(struct kernfs_open_file *of) +{ + return kernfs_put_active(of->kn); +} + /** * kernfs_deref_open_node_locked - Get kernfs_open_node corresponding to @kn * @@ -139,7 +157,7 @@ static void kernfs_seq_stop_active(struct seq_file *sf, void *v)

if (ops->seq_stop) ops->seq_stop(sf, v); - kernfs_put_active(of->kn); + kernfs_put_active_of(of); }

static void *kernfs_seq_start(struct seq_file *sf, loff_t *ppos) @@ -152,7 +170,7 @@ static void *kernfs_seq_start(struct seq_file *sf, loff_t *ppos) * the ops aren't called concurrently for the same open file. */ mutex_lock(&of->mutex); - if (!kernfs_get_active(of->kn)) + if (!kernfs_get_active_of(of)) return ERR_PTR(-ENODEV);

ops = kernfs_ops(of->kn); @@ -238,7 +256,7 @@ static ssize_t kernfs_file_read_iter(struct kiocb *iocb, struct iov_iter *iter) * the ops aren't called concurrently for the same open file. */ mutex_lock(&of->mutex); - if (!kernfs_get_active(of->kn)) { + if (!kernfs_get_active_of(of)) { len = -ENODEV; mutex_unlock(&of->mutex); goto out_free; @@ -252,7 +270,7 @@ static ssize_t kernfs_file_read_iter(struct kiocb *iocb, struct iov_iter *iter) else len = -EINVAL;

- kernfs_put_active(of->kn); + kernfs_put_active_of(of); mutex_unlock(&of->mutex);

if (len < 0) @@ -323,7 +341,7 @@ static ssize_t kernfs_fop_write_iter(struct kiocb *iocb, struct iov_iter *iter) * the ops aren't called concurrently for the same open file. */ mutex_lock(&of->mutex); - if (!kernfs_get_active(of->kn)) { + if (!kernfs_get_active_of(of)) { mutex_unlock(&of->mutex); len = -ENODEV; goto out_free; @@ -335,7 +353,7 @@ static ssize_t kernfs_fop_write_iter(struct kiocb *iocb, struct iov_iter *iter) else len = -EINVAL;

- kernfs_put_active(of->kn); + kernfs_put_active_of(of); mutex_unlock(&of->mutex);

if (len > 0) @@ -357,13 +375,13 @@ static void kernfs_vma_open(struct vm_area_struct *vma) if (!of->vm_ops) return;

- if (!kernfs_get_active(of->kn)) + if (!kernfs_get_active_of(of)) return;

if (of->vm_ops->open) of->vm_ops->open(vma);

- kernfs_put_active(of->kn); + kernfs_put_active_of(of); }

static vm_fault_t kernfs_vma_fault(struct vm_fault *vmf) @@ -375,14 +393,14 @@ static vm_fault_t kernfs_vma_fault(struct vm_fault *vmf) if (!of->vm_ops) return VM_FAULT_SIGBUS;

- if (!kernfs_get_active(of->kn)) + if (!kernfs_get_active_of(of)) return VM_FAULT_SIGBUS;

ret = VM_FAULT_SIGBUS; if (of->vm_ops->fault) ret = of->vm_ops->fault(vmf);

- kernfs_put_active(of->kn); + kernfs_put_active_of(of); return ret; }

@@ -395,7 +413,7 @@ static vm_fault_t kernfs_vma_page_mkwrite(struct vm_fault *vmf) if (!of->vm_ops) return VM_FAULT_SIGBUS;

- if (!kernfs_get_active(of->kn)) + if (!kernfs_get_active_of(of)) return VM_FAULT_SIGBUS;

ret = 0; @@ -404,7 +422,7 @@ static vm_fault_t kernfs_vma_page_mkwrite(struct vm_fault *vmf) else file_update_time(file);

- kernfs_put_active(of->kn); + kernfs_put_active_of(of); return ret; }

@@ -418,14 +436,14 @@ static int kernfs_vma_access(struct vm_area_struct *vma, unsigned long addr, if (!of->vm_ops) return -EINVAL;

- if (!kernfs_get_active(of->kn)) + if (!kernfs_get_active_of(of)) return -EINVAL;

ret = -EINVAL; if (of->vm_ops->access) ret = of->vm_ops->access(vma, addr, buf, len, write);

- kernfs_put_active(of->kn); + kernfs_put_active_of(of); return ret; }

@@ -504,7 +522,7 @@ static int kernfs_fop_mmap(struct file *file, struct vm_area_struct *vma) mutex_lock(&of->mutex);

rc = -ENODEV; - if (!kernfs_get_active(of->kn)) + if (!kernfs_get_active_of(of)) goto out_unlock;

ops = kernfs_ops(of->kn); @@ -539,7 +557,7 @@ static int kernfs_fop_mmap(struct file *file, struct vm_area_struct *vma) } vma->vm_ops = &kernfs_vm_ops; out_put: - kernfs_put_active(of->kn); + kernfs_put_active_of(of); out_unlock: mutex_unlock(&of->mutex);

@@ -894,7 +912,7 @@ static __poll_t kernfs_fop_poll(struct file *filp, poll_table *wait) struct kernfs_node *kn = kernfs_dentry_node(filp->f_path.dentry); __poll_t ret;

- if (!kernfs_get_active(kn)) + if (!kernfs_get_active_of(of)) return DEFAULT_POLLMASK|EPOLLERR|EPOLLPRI;

if (kn->attr.ops->poll) @@ -902,7 +920,7 @@ static __poll_t kernfs_fop_poll(struct file *filp, poll_table *wait) else ret = kernfs_generic_poll(of, wait);

- kernfs_put_active(kn); + kernfs_put_active_of(of); return ret; }

diff --git a/fs/nfs/client.c b/fs/nfs/client.c index cc764da581c4..1bcdaee7e856 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -873,6 +873,8 @@ static void nfs_server_set_fsinfo(struct nfs_server *server,

if (fsinfo->xattr_support) server->caps |= NFS_CAP_XATTR; + else + server->caps &= ~NFS_CAP_XATTR; #endif }

diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index a1ff4a4f5380..4e53708dfcf4 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -469,8 +469,16 @@ ssize_t nfs_file_direct_read(struct kiocb *iocb, struct iov_iter *iter, if (user_backed_iter(iter)) dreq->flags = NFS_ODIRECT_SHOULD_DIRTY;

- if (!swap) - nfs_start_io_direct(inode); + if (!swap) { + result = nfs_start_io_direct(inode); + if (result) { + /* release the reference that would usually be + * consumed by nfs_direct_read_schedule_iovec() + */ + nfs_direct_req_release(dreq); + goto out_release; + } + }

NFS_I(inode)->read_io += count; requested = nfs_direct_read_schedule_iovec(dreq, iter, iocb->ki_pos); @@ -1023,7 +1031,14 @@ ssize_t nfs_file_direct_write(struct kiocb *iocb, struct iov_iter *iter, requested = nfs_direct_write_schedule_iovec(dreq, iter, pos, FLUSH_STABLE); } else { - nfs_start_io_direct(inode); + result = nfs_start_io_direct(inode); + if (result) { + /* release the reference that would usually be + * consumed by nfs_direct_write_schedule_iovec() + */ + nfs_direct_req_release(dreq); + goto out_release; + }

requested = nfs_direct_write_schedule_iovec(dreq, iter, pos, FLUSH_COND_STABLE); diff --git a/fs/nfs/file.c b/fs/nfs/file.c index 003dda001840..2f4db026f8d6 100644 --- a/fs/nfs/file.c +++ b/fs/nfs/file.c @@ -167,7 +167,10 @@ nfs_file_read(struct kiocb *iocb, struct iov_iter *to) iocb->ki_filp, iov_iter_count(to), (unsigned long) iocb->ki_pos);

- nfs_start_io_read(inode); + result = nfs_start_io_read(inode); + if (result) + return result; + result = nfs_revalidate_mapping(inode, iocb->ki_filp->f_mapping); if (!result) { result = generic_file_read_iter(iocb, to); @@ -188,7 +191,10 @@ nfs_file_splice_read(struct file *in, loff_t *ppos, struct pipe_inode_info *pipe

dprintk("NFS: splice_read(%pD2, %zu@%llu)\n", in, len, *ppos);

- nfs_start_io_read(inode); + result = nfs_start_io_read(inode); + if (result) + return result; + result = nfs_revalidate_mapping(inode, in->f_mapping); if (!result) { result = filemap_splice_read(in, ppos, pipe, len, flags); @@ -668,7 +674,9 @@ ssize_t nfs_file_write(struct kiocb *iocb, struct iov_iter *from) nfs_clear_invalid_mapping(file->f_mapping);

since = filemap_sample_wb_err(file->f_mapping); - nfs_start_io_write(inode); + error = nfs_start_io_write(inode); + if (error) + return error; result = generic_write_checks(iocb, from); if (result > 0) result = generic_perform_write(iocb, from); diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c index 7354b6b10478..42c73c647a27 100644 --- a/fs/nfs/flexfilelayout/flexfilelayout.c +++ b/fs/nfs/flexfilelayout/flexfilelayout.c @@ -276,7 +276,7 @@ ff_lseg_match_mirrors(struct pnfs_layout_segment *l1, struct pnfs_layout_segment *l2) { const struct nfs4_ff_layout_segment *fl1 = FF_LAYOUT_LSEG(l1); - const struct nfs4_ff_layout_segment *fl2 = FF_LAYOUT_LSEG(l1); + const struct nfs4_ff_layout_segment *fl2 = FF_LAYOUT_LSEG(l2); u32 i;

if (fl1->mirror_array_cnt != fl2->mirror_array_cnt) @@ -756,8 +756,11 @@ ff_layout_choose_ds_for_read(struct pnfs_layout_segment *lseg, continue;

if (check_device && - nfs4_test_deviceid_unavailable(&mirror->mirror_ds->id_node)) + nfs4_test_deviceid_unavailable(&mirror->mirror_ds->id_node)) { + // reinitialize the error state in case if this is the last iteration + ds = ERR_PTR(-EINVAL); continue; + }

*best_idx = idx; break; @@ -787,7 +790,7 @@ ff_layout_choose_best_ds_for_read(struct pnfs_layout_segment *lseg, struct nfs4_pnfs_ds *ds;

ds = ff_layout_choose_valid_ds_for_read(lseg, start_idx, best_idx); - if (ds) + if (!IS_ERR(ds)) return ds; return ff_layout_choose_any_ds_for_read(lseg, start_idx, best_idx); } @@ -801,7 +804,7 @@ ff_layout_get_ds_for_read(struct nfs_pageio_descriptor *pgio,

ds = ff_layout_choose_best_ds_for_read(lseg, pgio->pg_mirror_idx, best_idx); - if (ds || !pgio->pg_mirror_idx) + if (!IS_ERR(ds) || !pgio->pg_mirror_idx) return ds; return ff_layout_choose_best_ds_for_read(lseg, 0, best_idx); } @@ -859,7 +862,7 @@ ff_layout_pg_init_read(struct nfs_pageio_descriptor *pgio, req->wb_nio = 0;

ds = ff_layout_get_ds_for_read(pgio, &ds_idx); - if (!ds) { + if (IS_ERR(ds)) { if (!ff_layout_no_fallback_to_mds(pgio->pg_lseg)) goto out_mds; pnfs_generic_pg_cleanup(pgio); @@ -1063,11 +1066,13 @@ static void ff_layout_resend_pnfs_read(struct nfs_pgio_header *hdr) { u32 idx = hdr->pgio_mirror_idx + 1; u32 new_idx = 0; + struct nfs4_pnfs_ds *ds;

- if (ff_layout_choose_any_ds_for_read(hdr->lseg, idx, &new_idx)) - ff_layout_send_layouterror(hdr->lseg); - else + ds = ff_layout_choose_any_ds_for_read(hdr->lseg, idx, &new_idx); + if (IS_ERR(ds)) pnfs_error_mark_layout_for_return(hdr->inode, hdr->lseg); + else + ff_layout_send_layouterror(hdr->lseg); pnfs_read_resend_pnfs(hdr, new_idx); }

diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index 7e7dd2aab449..5cd5e4226db3 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -645,8 +645,10 @@ nfs_setattr(struct mnt_idmap *idmap, struct dentry *dentry, trace_nfs_setattr_enter(inode);

/* Write all dirty data */ - if (S_ISREG(inode->i_mode)) + if (S_ISREG(inode->i_mode)) { + nfs_file_block_o_direct(NFS_I(inode)); nfs_sync_inode(inode); + }

fattr = nfs_alloc_fattr_with_label(NFS_SERVER(inode)); if (fattr == NULL) { diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index 4eea91d054b2..bde81e0abf0a 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -6,6 +6,7 @@ #include "nfs4_fs.h" #include <linux/fs_context.h> #include <linux/security.h> +#include <linux/compiler_attributes.h> #include <linux/crc32.h> #include <linux/sunrpc/addr.h> #include <linux/nfs_page.h> @@ -461,11 +462,11 @@ extern const struct netfs_request_ops nfs_netfs_ops; #endif

/* io.c */ -extern void nfs_start_io_read(struct inode *inode); +extern __must_check int nfs_start_io_read(struct inode *inode); extern void nfs_end_io_read(struct inode *inode); -extern void nfs_start_io_write(struct inode *inode); +extern __must_check int nfs_start_io_write(struct inode *inode); extern void nfs_end_io_write(struct inode *inode); -extern void nfs_start_io_direct(struct inode *inode); +extern __must_check int nfs_start_io_direct(struct inode *inode); extern void nfs_end_io_direct(struct inode *inode);

static inline bool nfs_file_io_is_buffered(struct nfs_inode *nfsi) @@ -473,6 +474,16 @@ static inline bool nfs_file_io_is_buffered(struct nfs_inode *nfsi) return test_bit(NFS_INO_ODIRECT, &nfsi->flags) == 0; }

+/* Must be called with exclusively locked inode->i_rwsem */ +static inline void nfs_file_block_o_direct(struct nfs_inode *nfsi) +{ + if (test_bit(NFS_INO_ODIRECT, &nfsi->flags)) { + clear_bit(NFS_INO_ODIRECT, &nfsi->flags); + inode_dio_wait(&nfsi->vfs_inode); + } +} + + /* namespace.c */ #define NFS_PATH_CANONICAL 1 extern char *nfs_path(char **p, struct dentry *dentry, diff --git a/fs/nfs/io.c b/fs/nfs/io.c index b5551ed8f648..d275b0a250bf 100644 --- a/fs/nfs/io.c +++ b/fs/nfs/io.c @@ -14,15 +14,6 @@

#include "internal.h"

-/* Call with exclusively locked inode->i_rwsem */ -static void nfs_block_o_direct(struct nfs_inode *nfsi, struct inode *inode) -{ - if (test_bit(NFS_INO_ODIRECT, &nfsi->flags)) { - clear_bit(NFS_INO_ODIRECT, &nfsi->flags); - inode_dio_wait(inode); - } -} - /** * nfs_start_io_read - declare the file is being used for buffered reads * @inode: file inode @@ -39,19 +30,28 @@ static void nfs_block_o_direct(struct nfs_inode *nfsi, struct inode *inode) * Note that buffered writes and truncates both take a write lock on * inode->i_rwsem, meaning that those are serialised w.r.t. the reads. */ -void +int nfs_start_io_read(struct inode *inode) { struct nfs_inode *nfsi = NFS_I(inode); + int err; + /* Be an optimist! */ - down_read(&inode->i_rwsem); + err = down_read_killable(&inode->i_rwsem); + if (err) + return err; if (test_bit(NFS_INO_ODIRECT, &nfsi->flags) == 0) - return; + return 0; up_read(&inode->i_rwsem); + /* Slow path.... */ - down_write(&inode->i_rwsem); - nfs_block_o_direct(nfsi, inode); + err = down_write_killable(&inode->i_rwsem); + if (err) + return err; + nfs_file_block_o_direct(nfsi); downgrade_write(&inode->i_rwsem); + + return 0; }

/** @@ -74,11 +74,15 @@ nfs_end_io_read(struct inode *inode) * Declare that a buffered read operation is about to start, and ensure * that we block all direct I/O. */ -void +int nfs_start_io_write(struct inode *inode) { - down_write(&inode->i_rwsem); - nfs_block_o_direct(NFS_I(inode), inode); + int err; + + err = down_write_killable(&inode->i_rwsem); + if (!err) + nfs_file_block_o_direct(NFS_I(inode)); + return err; }

/** @@ -119,19 +123,28 @@ static void nfs_block_buffered(struct nfs_inode *nfsi, struct inode *inode) * Note that buffered writes and truncates both take a write lock on * inode->i_rwsem, meaning that those are serialised w.r.t. O_DIRECT. */ -void +int nfs_start_io_direct(struct inode *inode) { struct nfs_inode *nfsi = NFS_I(inode); + int err; + /* Be an optimist! */ - down_read(&inode->i_rwsem); + err = down_read_killable(&inode->i_rwsem); + if (err) + return err; if (test_bit(NFS_INO_ODIRECT, &nfsi->flags) != 0) - return; + return 0; up_read(&inode->i_rwsem); + /* Slow path.... */ - down_write(&inode->i_rwsem); + err = down_write_killable(&inode->i_rwsem); + if (err) + return err; nfs_block_buffered(nfsi, inode); downgrade_write(&inode->i_rwsem); + + return 0; }

/** diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c index 9f0d69e65264..582cf8a46956 100644 --- a/fs/nfs/nfs42proc.c +++ b/fs/nfs/nfs42proc.c @@ -112,6 +112,7 @@ static int nfs42_proc_fallocate(struct rpc_message *msg, struct file *filep, exception.inode = inode; exception.state = lock->open_context->state;

+ nfs_file_block_o_direct(NFS_I(inode)); err = nfs_sync_inode(inode); if (err) goto out; @@ -355,6 +356,7 @@ static ssize_t _nfs42_proc_copy(struct file *src, return status; }

+ nfs_file_block_o_direct(NFS_I(dst_inode)); status = nfs_sync_inode(dst_inode); if (status) return status; diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c index 02788c3c85e5..befdb0f4e6dc 100644 --- a/fs/nfs/nfs4file.c +++ b/fs/nfs/nfs4file.c @@ -282,9 +282,11 @@ static loff_t nfs42_remap_file_range(struct file *src_file, loff_t src_off,

/* flush all pending writes on both src and dst so that server * has the latest data */ + nfs_file_block_o_direct(NFS_I(src_inode)); ret = nfs_sync_inode(src_inode); if (ret) goto out_unlock; + nfs_file_block_o_direct(NFS_I(dst_inode)); ret = nfs_sync_inode(dst_inode); if (ret) goto out_unlock; diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 6debcfc63222..124b9cee6fed 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -3882,8 +3882,9 @@ static int _nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *f res.attr_bitmask[2] &= FATTR4_WORD2_NFS42_MASK; } memcpy(server->attr_bitmask, res.attr_bitmask, sizeof(server->attr_bitmask)); - server->caps &= ~(NFS_CAP_ACLS | NFS_CAP_HARDLINKS | - NFS_CAP_SYMLINKS| NFS_CAP_SECURITY_LABEL); + server->caps &= + ~(NFS_CAP_ACLS | NFS_CAP_HARDLINKS | NFS_CAP_SYMLINKS | + NFS_CAP_SECURITY_LABEL | NFS_CAP_FS_LOCATIONS); server->fattr_valid = NFS_ATTR_FATTR_V4; if (res.attr_bitmask[0] & FATTR4_WORD0_ACL && res.acl_bitmask & ACL4_SUPPORT_ALLOW_ACL) @@ -3951,7 +3952,6 @@ int nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *fhandle) }; int err;

- nfs_server_set_init_caps(server); do { err = nfs4_handle_exception(server, _nfs4_server_capabilities(server, fhandle), diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index b2bbf3d6d177..cd78b7ecbd43 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -1131,6 +1131,7 @@ nfsd4_setattr(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, }; struct inode *inode; __be32 status = nfs_ok; + bool save_no_wcc; int err;

if (setattr->sa_iattr.ia_valid & ATTR_SIZE) { @@ -1156,8 +1157,11 @@ nfsd4_setattr(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,

if (status) goto out; + save_no_wcc = cstate->current_fh.fh_no_wcc; + cstate->current_fh.fh_no_wcc = true; status = nfsd_setattr(rqstp, &cstate->current_fh, &attrs, 0, (time64_t)0); + cstate->current_fh.fh_no_wcc = save_no_wcc; if (!status) status = nfserrno(attrs.na_labelerr); if (!status) diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index b3e51d88faff..5ee7149ceaa5 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -480,7 +480,7 @@ nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, int accmode = NFSD_MAY_SATTR; umode_t ftype = 0; __be32 err; - int host_err; + int host_err = 0; bool get_write_count; bool size_change = (iap->ia_valid & ATTR_SIZE); int retries; @@ -538,6 +538,9 @@ nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, }

inode_lock(inode); + err = fh_fill_pre_attrs(fhp); + if (err) + goto out_unlock; for (retries = 1;;) { struct iattr attrs;

@@ -565,13 +568,15 @@ nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, attr->na_aclerr = set_posix_acl(&nop_mnt_idmap, dentry, ACL_TYPE_DEFAULT, attr->na_dpacl); + fh_fill_post_attrs(fhp); +out_unlock: inode_unlock(inode); if (size_change) put_write_access(inode); out: if (!host_err) host_err = commit_metadata(fhp); - return nfserrno(host_err); + return err != 0 ? err : nfserrno(host_err); }

#if defined(CONFIG_NFSD_V4) @@ -1965,11 +1970,9 @@ nfsd_unlink(struct svc_rqst *rqstp, struct svc_fh *fhp, int type, err = nfserr_file_open; else err = nfserr_acces; - } else { - err = nfserrno(host_err); } out: - return err; + return err != nfs_ok ? err : nfserrno(host_err); out_unlock: inode_unlock(dirp); goto out_drop_write; diff --git a/fs/ocfs2/extent_map.c b/fs/ocfs2/extent_map.c index f7672472fa82..5e86c7e2c821 100644 --- a/fs/ocfs2/extent_map.c +++ b/fs/ocfs2/extent_map.c @@ -696,6 +696,8 @@ int ocfs2_extent_map_get_blocks(struct inode *inode, u64 v_blkno, u64 *p_blkno, * it not only handles the fiemap for inlined files, but also deals * with the fast symlink, cause they have no difference for extent * mapping per se. + * + * Must be called with ip_alloc_sem semaphore held. */ static int ocfs2_fiemap_inline(struct inode *inode, struct buffer_head *di_bh, struct fiemap_extent_info *fieinfo, @@ -707,6 +709,7 @@ static int ocfs2_fiemap_inline(struct inode *inode, struct buffer_head *di_bh, u64 phys; u32 flags = FIEMAP_EXTENT_DATA_INLINE|FIEMAP_EXTENT_LAST; struct ocfs2_inode_info *oi = OCFS2_I(inode); + lockdep_assert_held_read(&oi->ip_alloc_sem);

di = (struct ocfs2_dinode *)di_bh->b_data; if (ocfs2_inode_is_fast_symlink(inode)) @@ -722,8 +725,11 @@ static int ocfs2_fiemap_inline(struct inode *inode, struct buffer_head *di_bh, phys += offsetof(struct ocfs2_dinode, id2.i_data.id_data);

+ /* Release the ip_alloc_sem to prevent deadlock on page fault */ + up_read(&OCFS2_I(inode)->ip_alloc_sem); ret = fiemap_fill_next_extent(fieinfo, 0, phys, id_count, flags); + down_read(&OCFS2_I(inode)->ip_alloc_sem); if (ret < 0) return ret; } @@ -792,9 +798,11 @@ int ocfs2_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, len_bytes = (u64)le16_to_cpu(rec.e_leaf_clusters) << osb->s_clustersize_bits; phys_bytes = le64_to_cpu(rec.e_blkno) << osb->sb->s_blocksize_bits; virt_bytes = (u64)le32_to_cpu(rec.e_cpos) << osb->s_clustersize_bits; - + /* Release the ip_alloc_sem to prevent deadlock on page fault */ + up_read(&OCFS2_I(inode)->ip_alloc_sem); ret = fiemap_fill_next_extent(fieinfo, virt_bytes, phys_bytes, len_bytes, fe_flags); + down_read(&OCFS2_I(inode)->ip_alloc_sem); if (ret) break;

diff --git a/fs/proc/generic.c b/fs/proc/generic.c index db3f2c6abc16..4cadd2fd23d8 100644 --- a/fs/proc/generic.c +++ b/fs/proc/generic.c @@ -388,7 +388,8 @@ struct proc_dir_entry *proc_register(struct proc_dir_entry *dir, if (proc_alloc_inum(&dp->low_ino)) goto out_free_entry;

- pde_set_flags(dp); + if (!S_ISDIR(dp->mode)) + pde_set_flags(dp);

write_lock(&proc_subdir_lock); dp->parent = dir; diff --git a/fs/smb/client/file.c b/fs/smb/client/file.c index 7a2b81fbd9cf..1058066913dd 100644 --- a/fs/smb/client/file.c +++ b/fs/smb/client/file.c @@ -2884,17 +2884,21 @@ static ssize_t cifs_write_back_from_locked_folio(struct address_space *mapping, rc = cifs_get_writable_file(CIFS_I(inode), FIND_WR_ANY, &cfile); if (rc) { cifs_dbg(VFS, "No writable handle in writepages rc=%d\n", rc); + folio_unlock(folio); goto err_xid; }

rc = server->ops->wait_mtu_credits(server, cifs_sb->ctx->wsize, &wsize, credits); - if (rc != 0) + if (rc != 0) { + folio_unlock(folio); goto err_close; + }

wdata = cifs_writedata_alloc(cifs_writev_complete); if (!wdata) { rc = -ENOMEM; + folio_unlock(folio); goto err_uncredit; }

@@ -3041,17 +3045,22 @@ static ssize_t cifs_writepages_begin(struct address_space *mapping, lock_again: if (wbc->sync_mode != WB_SYNC_NONE) { ret = folio_lock_killable(folio); - if (ret < 0) + if (ret < 0) { + folio_put(folio); return ret; + } } else { - if (!folio_trylock(folio)) + if (!folio_trylock(folio)) { + folio_put(folio); goto search_again; + } }

if (folio->mapping != mapping || !folio_test_dirty(folio)) { start += folio_size(folio); folio_unlock(folio); + folio_put(folio); goto search_again; }

@@ -3081,6 +3090,7 @@ static ssize_t cifs_writepages_begin(struct address_space *mapping, out: if (ret > 0) *_start = start + ret; + folio_put(folio); return ret; }

diff --git a/fs/smb/server/connection.h b/fs/smb/server/connection.h index 29ba91fc5407..45421269ddd8 100644 --- a/fs/smb/server/connection.h +++ b/fs/smb/server/connection.h @@ -27,6 +27,7 @@ enum { KSMBD_SESS_EXITING, KSMBD_SESS_NEED_RECONNECT, KSMBD_SESS_NEED_NEGOTIATE, + KSMBD_SESS_NEED_SETUP, KSMBD_SESS_RELEASING };

@@ -195,6 +196,11 @@ static inline bool ksmbd_conn_need_negotiate(struct ksmbd_conn *conn) return READ_ONCE(conn->status) == KSMBD_SESS_NEED_NEGOTIATE; }

+static inline bool ksmbd_conn_need_setup(struct ksmbd_conn *conn) +{ + return READ_ONCE(conn->status) == KSMBD_SESS_NEED_SETUP; +} + static inline bool ksmbd_conn_need_reconnect(struct ksmbd_conn *conn) { return READ_ONCE(conn->status) == KSMBD_SESS_NEED_RECONNECT; @@ -225,6 +231,11 @@ static inline void ksmbd_conn_set_need_negotiate(struct ksmbd_conn *conn) WRITE_ONCE(conn->status, KSMBD_SESS_NEED_NEGOTIATE); }

+static inline void ksmbd_conn_set_need_setup(struct ksmbd_conn *conn) +{ + WRITE_ONCE(conn->status, KSMBD_SESS_NEED_SETUP); +} + static inline void ksmbd_conn_set_need_reconnect(struct ksmbd_conn *conn) { WRITE_ONCE(conn->status, KSMBD_SESS_NEED_RECONNECT); diff --git a/fs/smb/server/mgmt/user_session.c b/fs/smb/server/mgmt/user_session.c index 82dcc86a32c5..408f47220c07 100644 --- a/fs/smb/server/mgmt/user_session.c +++ b/fs/smb/server/mgmt/user_session.c @@ -373,12 +373,12 @@ void destroy_previous_session(struct ksmbd_conn *conn, ksmbd_all_conn_set_status(id, KSMBD_SESS_NEED_RECONNECT); err = ksmbd_conn_wait_idle_sess_id(conn, id); if (err) { - ksmbd_all_conn_set_status(id, KSMBD_SESS_NEED_NEGOTIATE); + ksmbd_all_conn_set_status(id, KSMBD_SESS_NEED_SETUP); goto out; } ksmbd_destroy_file_table(&prev_sess->file_table); prev_sess->state = SMB2_SESSION_EXPIRED; - ksmbd_all_conn_set_status(id, KSMBD_SESS_NEED_NEGOTIATE); + ksmbd_all_conn_set_status(id, KSMBD_SESS_NEED_SETUP); out: up_write(&conn->session_lock); up_write(&sessions_table_lock); diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c index 85e7bc3a2bd3..ae47450dc40f 100644 --- a/fs/smb/server/smb2pdu.c +++ b/fs/smb/server/smb2pdu.c @@ -1252,7 +1252,7 @@ int smb2_handle_negotiate(struct ksmbd_work *work) }

conn->srv_sec_mode = le16_to_cpu(rsp->SecurityMode); - ksmbd_conn_set_need_negotiate(conn); + ksmbd_conn_set_need_setup(conn);

err_out: if (rc) @@ -1273,6 +1273,9 @@ static int alloc_preauth_hash(struct ksmbd_session *sess, if (sess->Preauth_HashValue) return 0;

+ if (!conn->preauth_info) + return -ENOMEM; + sess->Preauth_HashValue = kmemdup(conn->preauth_info->Preauth_HashValue, PREAUTH_HASHVALUE_SIZE, GFP_KERNEL); if (!sess->Preauth_HashValue) @@ -1688,6 +1691,11 @@ int smb2_sess_setup(struct ksmbd_work *work)

ksmbd_debug(SMB, "Received request for session setup\n");

+ if (!ksmbd_conn_need_setup(conn) && !ksmbd_conn_good(conn)) { + work->send_no_response = 1; + return rc; + } + WORK_BUFFERS(work, req, rsp);

rsp->StructureSize = cpu_to_le16(9); @@ -1919,7 +1927,7 @@ int smb2_sess_setup(struct ksmbd_work *work) if (try_delay) { ksmbd_conn_set_need_reconnect(conn); ssleep(5); - ksmbd_conn_set_need_negotiate(conn); + ksmbd_conn_set_need_setup(conn); } } smb2_set_err_rsp(work); @@ -2249,7 +2257,7 @@ int smb2_session_logoff(struct ksmbd_work *work) ksmbd_free_user(sess->user); sess->user = NULL; } - ksmbd_all_conn_set_status(sess_id, KSMBD_SESS_NEED_NEGOTIATE); + ksmbd_all_conn_set_status(sess_id, KSMBD_SESS_NEED_SETUP);

rsp->StructureSize = cpu_to_le16(4); err = ksmbd_iov_pin_rsp(work, rsp, sizeof(struct smb2_logoff_rsp)); diff --git a/include/linux/compiler-clang.h b/include/linux/compiler-clang.h index 9b673fefcef8..f9de53fff3ac 100644 --- a/include/linux/compiler-clang.h +++ b/include/linux/compiler-clang.h @@ -23,23 +23,42 @@ #define KASAN_ABI_VERSION 5

/* + * Clang 22 added preprocessor macros to match GCC, in hopes of eventually + * dropping __has_feature support for sanitizers: + * https://github.com/llvm/llvm-project/commit/568c23bbd3303518c5056d7f03444dae... + * Create these macros for older versions of clang so that it is easy to clean + * up once the minimum supported version of LLVM for building the kernel always + * creates these macros. + * * Note: Checking __has_feature(*_sanitizer) is only true if the feature is * enabled. Therefore it is not required to additionally check defined(CONFIG_*) * to avoid adding redundant attributes in other configurations. */ +#if __has_feature(address_sanitizer) && !defined(__SANITIZE_ADDRESS__) +#define __SANITIZE_ADDRESS__ +#endif +#if __has_feature(hwaddress_sanitizer) && !defined(__SANITIZE_HWADDRESS__) +#define __SANITIZE_HWADDRESS__ +#endif +#if __has_feature(thread_sanitizer) && !defined(__SANITIZE_THREAD__) +#define __SANITIZE_THREAD__ +#endif

-#if __has_feature(address_sanitizer) || __has_feature(hwaddress_sanitizer) -/* Emulate GCC's __SANITIZE_ADDRESS__ flag */ +/* + * Treat __SANITIZE_HWADDRESS__ the same as __SANITIZE_ADDRESS__ in the kernel. + */ +#ifdef __SANITIZE_HWADDRESS__ #define __SANITIZE_ADDRESS__ +#endif + +#ifdef __SANITIZE_ADDRESS__ #define __no_sanitize_address \ __attribute__((no_sanitize("address", "hwaddress"))) #else #define __no_sanitize_address #endif

-#if __has_feature(thread_sanitizer) -/* emulate gcc's __SANITIZE_THREAD__ flag */ -#define __SANITIZE_THREAD__ +#ifdef __SANITIZE_THREAD__ #define __no_sanitize_thread \ __attribute__((no_sanitize("thread"))) #else diff --git a/include/linux/pgalloc.h b/include/linux/pgalloc.h new file mode 100644 index 000000000000..9174fa59bbc5 --- /dev/null +++ b/include/linux/pgalloc.h @@ -0,0 +1,29 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_PGALLOC_H +#define _LINUX_PGALLOC_H + +#include <linux/pgtable.h> +#include <asm/pgalloc.h> + +/* + * {pgd,p4d}_populate_kernel() are defined as macros to allow + * compile-time optimization based on the configured page table levels. + * Without this, linking may fail because callers (e.g., KASAN) may rely + * on calls to these functions being optimized away when passing symbols + * that exist only for certain page table levels. + */ +#define pgd_populate_kernel(addr, pgd, p4d) \ + do { \ + pgd_populate(&init_mm, pgd, p4d); \ + if (ARCH_PAGE_TABLE_SYNC_MASK & PGTBL_PGD_MODIFIED) \ + arch_sync_kernel_mappings(addr, addr); \ + } while (0) + +#define p4d_populate_kernel(addr, p4d, pud) \ + do { \ + p4d_populate(&init_mm, p4d, pud); \ + if (ARCH_PAGE_TABLE_SYNC_MASK & PGTBL_P4D_MODIFIED) \ + arch_sync_kernel_mappings(addr, addr); \ + } while (0) + +#endif /* _LINUX_PGALLOC_H */ diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h index e42388b6998b..78a518129e8f 100644 --- a/include/linux/pgtable.h +++ b/include/linux/pgtable.h @@ -1467,8 +1467,8 @@ static inline int pmd_protnone(pmd_t pmd)

/* * Architectures can set this mask to a combination of PGTBL_P?D_MODIFIED values - * and let generic vmalloc and ioremap code know when arch_sync_kernel_mappings() - * needs to be called. + * and let generic vmalloc, ioremap and page table update code know when + * arch_sync_kernel_mappings() needs to be called. */ #ifndef ARCH_PAGE_TABLE_SYNC_MASK #define ARCH_PAGE_TABLE_SYNC_MASK 0 @@ -1601,10 +1601,11 @@ static inline bool arch_has_pfn_modify_check(void) /* * Page Table Modification bits for pgtbl_mod_mask. * - * These are used by the p?d_alloc_track*() set of functions an in the generic - * vmalloc/ioremap code to track at which page-table levels entries have been - * modified. Based on that the code can better decide when vmalloc and ioremap - * mapping changes need to be synchronized to other page-tables in the system. + * These are used by the p?d_alloc_track*() and p*d_populate_kernel() + * functions in the generic vmalloc, ioremap and page table update code + * to track at which page-table levels entries have been modified. + * Based on that the code can better decide when page table changes need + * to be synchronized to other page-tables in the system. */ #define __PGTBL_PGD_MODIFIED 0 #define __PGTBL_P4D_MODIFIED 1 diff --git a/include/net/sock.h b/include/net/sock.h index b5f7208a9ec3..f8e029cc48cc 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -353,6 +353,8 @@ struct sk_filter; * @sk_txtime_unused: unused txtime flags * @ns_tracker: tracker for netns reference * @sk_bind2_node: bind node in the bhash2 table + * @sk_owner: reference to the real owner of the socket that calls + * sock_lock_init_class_and_name(). */ struct sock { /* @@ -545,6 +547,10 @@ struct sock { struct rcu_head sk_rcu; netns_tracker ns_tracker; struct hlist_node sk_bind2_node; + +#if IS_ENABLED(CONFIG_PROVE_LOCKING) && IS_ENABLED(CONFIG_MODULES) + struct module *sk_owner; +#endif };

enum sk_pacing { @@ -1699,6 +1705,35 @@ static inline void sk_mem_uncharge(struct sock *sk, int size) sk_mem_reclaim(sk); }

+#if IS_ENABLED(CONFIG_PROVE_LOCKING) && IS_ENABLED(CONFIG_MODULES) +static inline void sk_owner_set(struct sock *sk, struct module *owner) +{ + __module_get(owner); + sk->sk_owner = owner; +} + +static inline void sk_owner_clear(struct sock *sk) +{ + sk->sk_owner = NULL; +} + +static inline void sk_owner_put(struct sock *sk) +{ + module_put(sk->sk_owner); +} +#else +static inline void sk_owner_set(struct sock *sk, struct module *owner) +{ +} + +static inline void sk_owner_clear(struct sock *sk) +{ +} + +static inline void sk_owner_put(struct sock *sk) +{ +} +#endif /* * Macro so as to not evaluate some arguments when * lockdep is not enabled. @@ -1708,13 +1743,14 @@ static inline void sk_mem_uncharge(struct sock *sk, int size) */ #define sock_lock_init_class_and_name(sk, sname, skey, name, key) \ do { \ + sk_owner_set(sk, THIS_MODULE); \ sk->sk_lock.owned = 0; \ init_waitqueue_head(&sk->sk_lock.wq); \ spin_lock_init(&(sk)->sk_lock.slock); \ debug_check_no_locks_freed((void *)&(sk)->sk_lock, \ - sizeof((sk)->sk_lock)); \ + sizeof((sk)->sk_lock)); \ lockdep_set_class_and_name(&(sk)->sk_lock.slock, \ - (skey), (sname)); \ + (skey), (sname)); \ lockdep_init_map(&(sk)->sk_lock.dep_map, (name), (key), 0); \ } while (0)

diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c index 4b20a72ab8cf..90c281e1379e 100644 --- a/kernel/bpf/helpers.c +++ b/kernel/bpf/helpers.c @@ -1204,8 +1204,11 @@ static int __bpf_async_init(struct bpf_async_kern *async, struct bpf_map *map, u goto out; }

- /* allocate hrtimer via map_kmalloc to use memcg accounting */ - cb = bpf_map_kmalloc_node(map, size, GFP_ATOMIC, map->numa_node); + /* Allocate via bpf_map_kmalloc_node() for memcg accounting. Until + * kmalloc_nolock() is available, avoid locking issues by using + * __GFP_HIGH (GFP_ATOMIC & ~__GFP_RECLAIM). + */ + cb = bpf_map_kmalloc_node(map, size, __GFP_HIGH, map->numa_node); if (!cb) { ret = -ENOMEM; goto out; diff --git a/kernel/rcu/tasks.h b/kernel/rcu/tasks.h index 3fcd9f92d386..9189ccd4fee4 100644 --- a/kernel/rcu/tasks.h +++ b/kernel/rcu/tasks.h @@ -150,8 +150,6 @@ static struct rcu_tasks rt_name = \ }

#ifdef CONFIG_TASKS_RCU -/* Track exiting tasks in order to allow them to be waited for. */ -DEFINE_STATIC_SRCU(tasks_rcu_exit_srcu);

/* Report delay in synchronize_srcu() completion in rcu_tasks_postscan(). */ static void tasks_rcu_exit_srcu_stall(struct timer_list *unused); @@ -879,10 +877,12 @@ static void rcu_tasks_wait_gp(struct rcu_tasks *rtp) // number of voluntary context switches, and add that task to the // holdout list. // rcu_tasks_postscan(): -// Invoke synchronize_srcu() to ensure that all tasks that were -// in the process of exiting (and which thus might not know to -// synchronize with this RCU Tasks grace period) have completed -// exiting. +// Gather per-CPU lists of tasks in do_exit() to ensure that all +// tasks that were in the process of exiting (and which thus might +// not know to synchronize with this RCU Tasks grace period) have +// completed exiting. The synchronize_rcu() in rcu_tasks_postgp() +// will take care of any tasks stuck in the non-preemptible region +// of do_exit() following its call to exit_tasks_rcu_stop(). // check_all_holdout_tasks(), repeatedly until holdout list is empty: // Scans the holdout list, attempting to identify a quiescent state // for each task on the list. If there is a quiescent state, the @@ -895,8 +895,10 @@ static void rcu_tasks_wait_gp(struct rcu_tasks *rtp) // with interrupts disabled. // // For each exiting task, the exit_tasks_rcu_start() and -// exit_tasks_rcu_finish() functions begin and end, respectively, the SRCU -// read-side critical sections waited for by rcu_tasks_postscan(). +// exit_tasks_rcu_finish() functions add and remove, respectively, the +// current task to a per-CPU list of tasks that rcu_tasks_postscan() must +// wait on. This is necessary because rcu_tasks_postscan() must wait on +// tasks that have already been removed from the global list of tasks. // // Pre-grace-period update-side code is ordered before the grace // via the raw_spin_lock.*rcu_node(). Pre-grace-period read-side code @@ -960,9 +962,13 @@ static void rcu_tasks_pertask(struct task_struct *t, struct list_head *hop) } }

+void call_rcu_tasks(struct rcu_head *rhp, rcu_callback_t func); +DEFINE_RCU_TASKS(rcu_tasks, rcu_tasks_wait_gp, call_rcu_tasks, "RCU Tasks"); + /* Processing between scanning taskslist and draining the holdout list. */ static void rcu_tasks_postscan(struct list_head *hop) { + int cpu; int rtsi = READ_ONCE(rcu_task_stall_info);

if (!IS_ENABLED(CONFIG_TINY_RCU)) { @@ -976,9 +982,9 @@ static void rcu_tasks_postscan(struct list_head *hop) * this, divide the fragile exit path part in two intersecting * read side critical sections: * - * 1) An _SRCU_ read side starting before calling exit_notify(), - * which may remove the task from the tasklist, and ending after - * the final preempt_disable() call in do_exit(). + * 1) A task_struct list addition before calling exit_notify(), + * which may remove the task from the tasklist, with the + * removal after the final preempt_disable() call in do_exit(). * * 2) An _RCU_ read side starting with the final preempt_disable() * call in do_exit() and ending with the final call to schedule() @@ -987,7 +993,37 @@ static void rcu_tasks_postscan(struct list_head *hop) * This handles the part 1). And postgp will handle part 2) with a * call to synchronize_rcu(). */ - synchronize_srcu(&tasks_rcu_exit_srcu); + + for_each_possible_cpu(cpu) { + unsigned long j = jiffies + 1; + struct rcu_tasks_percpu *rtpcp = per_cpu_ptr(rcu_tasks.rtpcpu, cpu); + struct task_struct *t; + struct task_struct *t1; + struct list_head tmp; + + raw_spin_lock_irq_rcu_node(rtpcp); + list_for_each_entry_safe(t, t1, &rtpcp->rtp_exit_list, rcu_tasks_exit_list) { + if (list_empty(&t->rcu_tasks_holdout_list)) + rcu_tasks_pertask(t, hop); + + // RT kernels need frequent pauses, otherwise + // pause at least once per pair of jiffies. + if (!IS_ENABLED(CONFIG_PREEMPT_RT) && time_before(jiffies, j)) + continue; + + // Keep our place in the list while pausing. + // Nothing else traverses this list, so adding a + // bare list_head is OK. + list_add(&tmp, &t->rcu_tasks_exit_list); + raw_spin_unlock_irq_rcu_node(rtpcp); + cond_resched(); // For CONFIG_PREEMPT=n kernels + raw_spin_lock_irq_rcu_node(rtpcp); + t1 = list_entry(tmp.next, struct task_struct, rcu_tasks_exit_list); + list_del(&tmp); + j = jiffies + 1; + } + raw_spin_unlock_irq_rcu_node(rtpcp); + }

if (!IS_ENABLED(CONFIG_TINY_RCU)) del_timer_sync(&tasks_rcu_exit_srcu_stall_timer); @@ -1055,7 +1091,6 @@ static void rcu_tasks_postgp(struct rcu_tasks *rtp) * * In addition, this synchronize_rcu() waits for exiting tasks * to complete their final preempt_disable() region of execution, - * cleaning up after synchronize_srcu(&tasks_rcu_exit_srcu), * enforcing the whole region before tasklist removal until * the final schedule() with TASK_DEAD state to be an RCU TASKS * read side critical section. @@ -1063,9 +1098,6 @@ static void rcu_tasks_postgp(struct rcu_tasks *rtp) synchronize_rcu(); }

-void call_rcu_tasks(struct rcu_head *rhp, rcu_callback_t func); -DEFINE_RCU_TASKS(rcu_tasks, rcu_tasks_wait_gp, call_rcu_tasks, "RCU Tasks"); - static void tasks_rcu_exit_srcu_stall(struct timer_list *unused) { #ifndef CONFIG_TINY_RCU @@ -1175,25 +1207,48 @@ struct task_struct *get_rcu_tasks_gp_kthread(void) EXPORT_SYMBOL_GPL(get_rcu_tasks_gp_kthread);

/* - * Contribute to protect against tasklist scan blind spot while the - * task is exiting and may be removed from the tasklist. See - * corresponding synchronize_srcu() for further details. + * Protect against tasklist scan blind spot while the task is exiting and + * may be removed from the tasklist. Do this by adding the task to yet + * another list. + * + * Note that the task will remove itself from this list, so there is no + * need for get_task_struct(), except in the case where rcu_tasks_pertask() + * adds it to the holdout list, in which case rcu_tasks_pertask() supplies + * the needed get_task_struct(). */ -void exit_tasks_rcu_start(void) __acquires(&tasks_rcu_exit_srcu) +void exit_tasks_rcu_start(void) { - current->rcu_tasks_idx = __srcu_read_lock(&tasks_rcu_exit_srcu); + unsigned long flags; + struct rcu_tasks_percpu *rtpcp; + struct task_struct *t = current; + + WARN_ON_ONCE(!list_empty(&t->rcu_tasks_exit_list)); + preempt_disable(); + rtpcp = this_cpu_ptr(rcu_tasks.rtpcpu); + t->rcu_tasks_exit_cpu = smp_processor_id(); + raw_spin_lock_irqsave_rcu_node(rtpcp, flags); + if (!rtpcp->rtp_exit_list.next) + INIT_LIST_HEAD(&rtpcp->rtp_exit_list); + list_add(&t->rcu_tasks_exit_list, &rtpcp->rtp_exit_list); + raw_spin_unlock_irqrestore_rcu_node(rtpcp, flags); + preempt_enable(); }

/* - * Contribute to protect against tasklist scan blind spot while the - * task is exiting and may be removed from the tasklist. See - * corresponding synchronize_srcu() for further details. + * Remove the task from the "yet another list" because do_exit() is now + * non-preemptible, allowing synchronize_rcu() to wait beyond this point. */ -void exit_tasks_rcu_stop(void) __releases(&tasks_rcu_exit_srcu) +void exit_tasks_rcu_stop(void) { + unsigned long flags; + struct rcu_tasks_percpu *rtpcp; struct task_struct *t = current;

- __srcu_read_unlock(&tasks_rcu_exit_srcu, t->rcu_tasks_idx); + WARN_ON_ONCE(list_empty(&t->rcu_tasks_exit_list)); + rtpcp = per_cpu_ptr(rcu_tasks.rtpcpu, t->rcu_tasks_exit_cpu); + raw_spin_lock_irqsave_rcu_node(rtpcp, flags); + list_del_init(&t->rcu_tasks_exit_list); + raw_spin_unlock_irqrestore_rcu_node(rtpcp, flags); }

/* diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c index 6d9da768604d..ccea52adcba6 100644 --- a/kernel/time/hrtimer.c +++ b/kernel/time/hrtimer.c @@ -671,17 +671,12 @@ static inline ktime_t hrtimer_update_base(struct hrtimer_cpu_base *base) /* * Is the high resolution mode active ? */ -static inline int __hrtimer_hres_active(struct hrtimer_cpu_base *cpu_base) +static inline int hrtimer_hres_active(struct hrtimer_cpu_base *cpu_base) { return IS_ENABLED(CONFIG_HIGH_RES_TIMERS) ? cpu_base->hres_active : 0; }

-static inline int hrtimer_hres_active(void) -{ - return __hrtimer_hres_active(this_cpu_ptr(&hrtimer_bases)); -} - static void __hrtimer_reprogram(struct hrtimer_cpu_base *cpu_base, struct hrtimer *next_timer, ktime_t expires_next) @@ -705,7 +700,7 @@ static void __hrtimer_reprogram(struct hrtimer_cpu_base *cpu_base, * set. So we'd effectively block all timers until the T2 event * fires. */ - if (!__hrtimer_hres_active(cpu_base) || cpu_base->hang_detected) + if (!hrtimer_hres_active(cpu_base) || cpu_base->hang_detected) return;

tick_program_event(expires_next, 1); @@ -813,13 +808,13 @@ static void retrigger_next_event(void *arg) * of the next expiring timer is enough. The return from the SMP * function call will take care of the reprogramming in case the * CPU was in a NOHZ idle sleep. + * + * In periodic low resolution mode, the next softirq expiration + * must also be updated. */ - if (!__hrtimer_hres_active(base) && !tick_nohz_active) - return; - raw_spin_lock(&base->lock); hrtimer_update_base(base); - if (__hrtimer_hres_active(base)) + if (hrtimer_hres_active(base)) hrtimer_force_reprogram(base, 0); else hrtimer_update_next_event(base); @@ -976,7 +971,7 @@ void clock_was_set(unsigned int bases) cpumask_var_t mask; int cpu;

- if (!__hrtimer_hres_active(cpu_base) && !tick_nohz_active) + if (!hrtimer_hres_active(cpu_base) && !tick_nohz_active) goto out_timerfd;

if (!zalloc_cpumask_var(&mask, GFP_KERNEL)) { @@ -1554,7 +1549,7 @@ u64 hrtimer_get_next_event(void)

raw_spin_lock_irqsave(&cpu_base->lock, flags);

- if (!__hrtimer_hres_active(cpu_base)) + if (!hrtimer_hres_active(cpu_base)) expires = __hrtimer_get_next_event(cpu_base, HRTIMER_ACTIVE_ALL);

raw_spin_unlock_irqrestore(&cpu_base->lock, flags); @@ -1577,7 +1572,7 @@ u64 hrtimer_next_event_without(const struct hrtimer *exclude)

raw_spin_lock_irqsave(&cpu_base->lock, flags);

- if (__hrtimer_hres_active(cpu_base)) { + if (hrtimer_hres_active(cpu_base)) { unsigned int active;

if (!cpu_base->softirq_activated) { @@ -1938,25 +1933,7 @@ void hrtimer_interrupt(struct clock_event_device *dev) tick_program_event(expires_next, 1); pr_warn_once("hrtimer: interrupt took %llu ns\n", ktime_to_ns(delta)); } - -/* called with interrupts disabled */ -static inline void __hrtimer_peek_ahead_timers(void) -{ - struct tick_device *td; - - if (!hrtimer_hres_active()) - return; - - td = this_cpu_ptr(&tick_cpu_device); - if (td && td->evtdev) - hrtimer_interrupt(td->evtdev); -} - -#else /* CONFIG_HIGH_RES_TIMERS */ - -static inline void __hrtimer_peek_ahead_timers(void) { } - -#endif /* !CONFIG_HIGH_RES_TIMERS */ +#endif /* !CONFIG_HIGH_RES_TIMERS */

/* * Called from run_local_timers in hardirq context every jiffy @@ -1967,7 +1944,7 @@ void hrtimer_run_queues(void) unsigned long flags; ktime_t now;

- if (__hrtimer_hres_active(cpu_base)) + if (hrtimer_hres_active(cpu_base)) return;

/* @@ -2312,11 +2289,6 @@ int hrtimers_cpu_dying(unsigned int dying_cpu) &new_base->clock_base[i]); }

- /* - * The migration might have changed the first expiring softirq - * timer on this CPU. Update it. - */ - __hrtimer_get_next_event(new_base, HRTIMER_ACTIVE_SOFT); /* Tell the other CPU to retrigger the next event */ smp_call_function_single(ncpu, retrigger_next_event, NULL, 0);

diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index a32c8637503d..a111be83c369 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -750,7 +750,10 @@ int trace_pid_write(struct trace_pid_list *filtered_pids, /* copy the current bits to the new max */ ret = trace_pid_list_first(filtered_pids, &pid); while (!ret) { - trace_pid_list_set(pid_list, pid); + ret = trace_pid_list_set(pid_list, pid); + if (ret < 0) + goto out; + ret = trace_pid_list_next(filtered_pids, pid + 1, &pid); nr_pids++; } @@ -787,6 +790,7 @@ int trace_pid_write(struct trace_pid_list *filtered_pids, trace_parser_clear(&parser); ret = 0; } + out: trace_parser_put(&parser);

if (ret < 0) { @@ -7226,7 +7230,7 @@ tracing_mark_write(struct file *filp, const char __user *ubuf, entry = ring_buffer_event_data(event); entry->ip = _THIS_IP_;

- len = __copy_from_user_inatomic(&entry->buf, ubuf, cnt); + len = copy_from_user_nofault(&entry->buf, ubuf, cnt); if (len) { memcpy(&entry->buf, FAULTED_STR, FAULTED_SIZE); cnt = FAULTED_SIZE; @@ -7301,7 +7305,7 @@ tracing_mark_raw_write(struct file *filp, const char __user *ubuf,

entry = ring_buffer_event_data(event);

- len = __copy_from_user_inatomic(&entry->id, ubuf, cnt); + len = copy_from_user_nofault(&entry->id, ubuf, cnt); if (len) { entry->id = -1; memcpy(&entry->buf, FAULTED_STR, FAULTED_SIZE); diff --git a/mm/Kconfig b/mm/Kconfig index c11cd01169e8..046c32686fc4 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -280,7 +280,7 @@ config SLAB

config SLUB_TINY bool "Configure SLUB for minimal memory footprint" - depends on SLUB && EXPERT + depends on SLUB && EXPERT && !COMPILE_TEST select SLAB_MERGE_DEFAULT help Configures the SLUB allocator in a way to achieve minimal memory diff --git a/mm/damon/core.c b/mm/damon/core.c index 43e4fe7ef17e..48747236c21c 100644 --- a/mm/damon/core.c +++ b/mm/damon/core.c @@ -1043,6 +1043,10 @@ static void damos_adjust_quota(struct damon_ctx *c, struct damos *s) if (!quota->ms && !quota->sz) return;

+ /* First charge window */ + if (!quota->total_charged_sz && !quota->charged_from) + quota->charged_from = jiffies; + /* New charge window starts */ if (time_after_eq(jiffies, quota->charged_from + msecs_to_jiffies(quota->reset_interval))) { diff --git a/mm/damon/lru_sort.c b/mm/damon/lru_sort.c index 3de2916a65c3..b4032538b22c 100644 --- a/mm/damon/lru_sort.c +++ b/mm/damon/lru_sort.c @@ -203,6 +203,9 @@ static int damon_lru_sort_apply_parameters(void) unsigned int hot_thres, cold_thres; int err = 0;

+ if (!damon_lru_sort_mon_attrs.sample_interval) + return -EINVAL; + err = damon_set_attrs(ctx, &damon_lru_sort_mon_attrs); if (err) return err; diff --git a/mm/damon/reclaim.c b/mm/damon/reclaim.c index 66e190f0374a..586daa2cefe4 100644 --- a/mm/damon/reclaim.c +++ b/mm/damon/reclaim.c @@ -167,6 +167,9 @@ static int damon_reclaim_apply_parameters(void) struct damos_filter *filter; int err = 0;

+ if (!damon_reclaim_mon_attrs.aggr_interval) + return -EINVAL; + err = damon_set_attrs(ctx, &damon_reclaim_mon_attrs); if (err) return err; diff --git a/mm/damon/sysfs.c b/mm/damon/sysfs.c index b317f51dcc98..91893543d47c 100644 --- a/mm/damon/sysfs.c +++ b/mm/damon/sysfs.c @@ -1055,14 +1055,18 @@ static ssize_t state_show(struct kobject *kobj, struct kobj_attribute *attr, { struct damon_sysfs_kdamond *kdamond = container_of(kobj, struct damon_sysfs_kdamond, kobj); - struct damon_ctx *ctx = kdamond->damon_ctx; - bool running; + struct damon_ctx *ctx; + bool running = false;

- if (!ctx) - running = false; - else + if (!mutex_trylock(&damon_sysfs_lock)) + return -EBUSY; + + ctx = kdamond->damon_ctx; + if (ctx) running = damon_sysfs_ctx_running(ctx);

+ mutex_unlock(&damon_sysfs_lock); + return sysfs_emit(buf, "%s\n", running ? damon_sysfs_cmd_strs[DAMON_SYSFS_CMD_ON] : damon_sysfs_cmd_strs[DAMON_SYSFS_CMD_OFF]); diff --git a/mm/kasan/init.c b/mm/kasan/init.c index 89895f38f722..afecc04b486a 100644 --- a/mm/kasan/init.c +++ b/mm/kasan/init.c @@ -13,9 +13,9 @@ #include <linux/mm.h> #include <linux/pfn.h> #include <linux/slab.h> +#include <linux/pgalloc.h>

#include <asm/page.h> -#include <asm/pgalloc.h>

#include "kasan.h"

@@ -197,7 +197,7 @@ static int __ref zero_p4d_populate(pgd_t *pgd, unsigned long addr, pud_t *pud; pmd_t *pmd;

- p4d_populate(&init_mm, p4d, + p4d_populate_kernel(addr, p4d, lm_alias(kasan_early_shadow_pud)); pud = pud_offset(p4d, addr); pud_populate(&init_mm, pud, @@ -218,7 +218,7 @@ static int __ref zero_p4d_populate(pgd_t *pgd, unsigned long addr, } else { p = early_alloc(PAGE_SIZE, NUMA_NO_NODE); pud_init(p); - p4d_populate(&init_mm, p4d, p); + p4d_populate_kernel(addr, p4d, p); } } zero_pud_populate(p4d, addr, next); @@ -257,10 +257,10 @@ int __ref kasan_populate_early_shadow(const void *shadow_start, * puds,pmds, so pgd_populate(), pud_populate() * is noops. */ - pgd_populate(&init_mm, pgd, + pgd_populate_kernel(addr, pgd, lm_alias(kasan_early_shadow_p4d)); p4d = p4d_offset(pgd, addr); - p4d_populate(&init_mm, p4d, + p4d_populate_kernel(addr, p4d, lm_alias(kasan_early_shadow_pud)); pud = pud_offset(p4d, addr); pud_populate(&init_mm, pud, @@ -279,7 +279,7 @@ int __ref kasan_populate_early_shadow(const void *shadow_start, if (!p) return -ENOMEM; } else { - pgd_populate(&init_mm, pgd, + pgd_populate_kernel(addr, pgd, early_alloc(PAGE_SIZE, NUMA_NO_NODE)); } } diff --git a/mm/kasan/kasan_test.c b/mm/kasan/kasan_test.c index ecf9f5aa3520..9ca21d1e10ac 100644 --- a/mm/kasan/kasan_test.c +++ b/mm/kasan/kasan_test.c @@ -1053,6 +1053,7 @@ static void kasan_strings(struct kunit *test)

ptr = kmalloc(size, GFP_KERNEL | __GFP_ZERO); KUNIT_ASSERT_NOT_ERR_OR_NULL(test, ptr); + OPTIMIZER_HIDE_VAR(ptr);

kfree(ptr);

diff --git a/mm/khugepaged.c b/mm/khugepaged.c index f227b39ae4cf..16d29ee602c7 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -1240,6 +1240,7 @@ static int hpage_collapse_scan_pmd(struct mm_struct *mm, int result = SCAN_FAIL, referenced = 0; int none_or_zero = 0, shared = 0; struct page *page = NULL; + struct folio *folio = NULL; unsigned long _address; spinlock_t *ptl; int node = NUMA_NO_NODE, unmapped = 0; @@ -1326,29 +1327,28 @@ static int hpage_collapse_scan_pmd(struct mm_struct *mm, } }

- page = compound_head(page); - + folio = page_folio(page); /* * Record which node the original page is from and save this * information to cc->node_load[]. * Khugepaged will allocate hugepage from the node has the max * hit record. */ - node = page_to_nid(page); + node = folio_nid(folio); if (hpage_collapse_scan_abort(node, cc)) { result = SCAN_SCAN_ABORT; goto out_unmap; } cc->node_load[node]++; - if (!PageLRU(page)) { + if (!folio_test_lru(folio)) { result = SCAN_PAGE_LRU; goto out_unmap; } - if (PageLocked(page)) { + if (folio_test_locked(folio)) { result = SCAN_PAGE_LOCK; goto out_unmap; } - if (!PageAnon(page)) { + if (!folio_test_anon(folio)) { result = SCAN_PAGE_ANON; goto out_unmap; } @@ -1363,7 +1363,7 @@ static int hpage_collapse_scan_pmd(struct mm_struct *mm, * has excessive GUP pins (i.e. 512). Anyway the same check * will be done again later the risk seems low. */ - if (!is_refcount_suitable(page)) { + if (!is_refcount_suitable(&folio->page)) { result = SCAN_PAGE_COUNT; goto out_unmap; } @@ -1373,9 +1373,9 @@ static int hpage_collapse_scan_pmd(struct mm_struct *mm, * enough young pte to justify collapsing the page */ if (cc->is_khugepaged && - (pte_young(pteval) || page_is_young(page) || - PageReferenced(page) || mmu_notifier_test_young(vma->vm_mm, - address))) + (pte_young(pteval) || folio_test_young(folio) || + folio_test_referenced(folio) || + mmu_notifier_test_young(vma->vm_mm, _address))) referenced++; } if (!writable) { @@ -1396,7 +1396,7 @@ static int hpage_collapse_scan_pmd(struct mm_struct *mm, *mmap_locked = false; } out: - trace_mm_khugepaged_scan_pmd(mm, page, writable, referenced, + trace_mm_khugepaged_scan_pmd(mm, &folio->page, writable, referenced, none_or_zero, result, unmapped); return result; } diff --git a/mm/memory-failure.c b/mm/memory-failure.c index dae5e60d64e2..8bedcd288a0c 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -2535,10 +2535,9 @@ int unpoison_memory(unsigned long pfn) static DEFINE_RATELIMIT_STATE(unpoison_rs, DEFAULT_RATELIMIT_INTERVAL, DEFAULT_RATELIMIT_BURST);

- if (!pfn_valid(pfn)) - return -ENXIO; - - p = pfn_to_page(pfn); + p = pfn_to_online_page(pfn); + if (!p) + return -EIO; folio = page_folio(p);

mutex_lock(&mf_mutex); diff --git a/mm/percpu.c b/mm/percpu.c index d287cebd58ca..38d5121c2b65 100644 --- a/mm/percpu.c +++ b/mm/percpu.c @@ -3157,7 +3157,7 @@ int __init pcpu_embed_first_chunk(size_t reserved_size, size_t dyn_size, #endif /* BUILD_EMBED_FIRST_CHUNK */

#ifdef BUILD_PAGE_FIRST_CHUNK -#include <asm/pgalloc.h> +#include <linux/pgalloc.h>

#ifndef P4D_TABLE_SIZE #define P4D_TABLE_SIZE PAGE_SIZE @@ -3185,7 +3185,7 @@ void __init __weak pcpu_populate_pte(unsigned long addr) p4d = memblock_alloc(P4D_TABLE_SIZE, P4D_TABLE_SIZE); if (!p4d) goto err_alloc; - pgd_populate(&init_mm, pgd, p4d); + pgd_populate_kernel(addr, pgd, p4d); }

p4d = p4d_offset(pgd, addr); @@ -3193,7 +3193,7 @@ void __init __weak pcpu_populate_pte(unsigned long addr) pud = memblock_alloc(PUD_TABLE_SIZE, PUD_TABLE_SIZE); if (!pud) goto err_alloc; - p4d_populate(&init_mm, p4d, pud); + p4d_populate_kernel(addr, p4d, pud); }

pud = pud_offset(p4d, addr); diff --git a/mm/sparse-vmemmap.c b/mm/sparse-vmemmap.c index a2cbe44c48e1..589d6a262b6d 100644 --- a/mm/sparse-vmemmap.c +++ b/mm/sparse-vmemmap.c @@ -27,9 +27,9 @@ #include <linux/spinlock.h> #include <linux/vmalloc.h> #include <linux/sched.h> +#include <linux/pgalloc.h>

#include <asm/dma.h> -#include <asm/pgalloc.h>

/* * Allocate a block of memory to be used to back the virtual memory map @@ -225,7 +225,7 @@ p4d_t * __meminit vmemmap_p4d_populate(pgd_t *pgd, unsigned long addr, int node) if (!p) return NULL; pud_init(p); - p4d_populate(&init_mm, p4d, p); + p4d_populate_kernel(addr, p4d, p); } return p4d; } @@ -237,7 +237,7 @@ pgd_t * __meminit vmemmap_pgd_populate(unsigned long addr, int node) void *p = vmemmap_alloc_block_zero(PAGE_SIZE, node); if (!p) return NULL; - pgd_populate(&init_mm, pgd, p); + pgd_populate_kernel(addr, pgd, p); } return pgd; } diff --git a/net/bridge/br.c b/net/bridge/br.c index a6e94ceb7c9a..a45db6719722 100644 --- a/net/bridge/br.c +++ b/net/bridge/br.c @@ -312,6 +312,13 @@ int br_boolopt_multi_toggle(struct net_bridge *br, int err = 0; int opt_id;

+ opt_id = find_next_bit(&bitmap, BITS_PER_LONG, BR_BOOLOPT_MAX); + if (opt_id != BITS_PER_LONG) { + NL_SET_ERR_MSG_FMT_MOD(extack, "Unknown boolean option %d", + opt_id); + return -EINVAL; + } + for_each_set_bit(opt_id, &bitmap, BR_BOOLOPT_MAX) { bool on = !!(bm->optval & BIT(opt_id));

diff --git a/net/can/j1939/bus.c b/net/can/j1939/bus.c index 486687901602..e0b966c2517c 100644 --- a/net/can/j1939/bus.c +++ b/net/can/j1939/bus.c @@ -290,8 +290,11 @@ int j1939_local_ecu_get(struct j1939_priv *priv, name_t name, u8 sa) if (!ecu) ecu = j1939_ecu_create_locked(priv, name); err = PTR_ERR_OR_ZERO(ecu); - if (err) + if (err) { + if (j1939_address_is_unicast(sa)) + priv->ents[sa].nusers--; goto done; + }

ecu->nusers++; /* TODO: do we care if ecu->addr != sa? */ diff --git a/net/can/j1939/socket.c b/net/can/j1939/socket.c index cf9a12d8da6f..7bf4d4fb9673 100644 --- a/net/can/j1939/socket.c +++ b/net/can/j1939/socket.c @@ -520,6 +520,9 @@ static int j1939_sk_bind(struct socket *sock, struct sockaddr *uaddr, int len) ret = j1939_local_ecu_get(priv, jsk->addr.src_name, jsk->addr.sa); if (ret) { j1939_netdev_stop(priv); + jsk->priv = NULL; + synchronize_rcu(); + j1939_priv_put(priv); goto out_release_sock; }

diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index 3c8b78d9c4d1..8add91385375 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -1524,7 +1524,7 @@ static void con_fault_finish(struct ceph_connection *con) * in case we faulted due to authentication, invalidate our * current tickets so that we can get new ones. */ - if (con->v1.auth_retry) { + if (!ceph_msgr2(from_msgr(con->msgr)) && con->v1.auth_retry) { dout("auth_retry %d, invalidating\n", con->v1.auth_retry); if (con->ops->invalidate_authorizer) con->ops->invalidate_authorizer(con); @@ -1714,9 +1714,10 @@ static void clear_standby(struct ceph_connection *con) { /* come back from STANDBY? */ if (con->state == CEPH_CON_S_STANDBY) { - dout("clear_standby %p and ++connect_seq\n", con); + dout("clear_standby %p\n", con); con->state = CEPH_CON_S_PREOPEN; - con->v1.connect_seq++; + if (!ceph_msgr2(from_msgr(con->msgr))) + con->v1.connect_seq++; WARN_ON(ceph_con_flag_test(con, CEPH_CON_F_WRITE_PENDING)); WARN_ON(ceph_con_flag_test(con, CEPH_CON_F_KEEPALIVE_PENDING)); } diff --git a/net/core/sock.c b/net/core/sock.c index b74bc8175937..9918a9a337b6 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -2029,6 +2029,8 @@ int sk_getsockopt(struct sock *sk, int level, int optname, */ static inline void sock_lock_init(struct sock *sk) { + sk_owner_clear(sk); + if (sk->sk_kern_sock) sock_lock_init_class_and_name( sk, @@ -2124,6 +2126,9 @@ static void sk_prot_free(struct proto *prot, struct sock *sk) cgroup_sk_free(&sk->sk_cgrp_data); mem_cgroup_sk_free(sk); security_sk_free(sk); + + sk_owner_put(sk); + if (slab != NULL) kmem_cache_free(slab, sk); else diff --git a/net/hsr/hsr_device.c b/net/hsr/hsr_device.c index 906c38b9d66f..5514b5bedc92 100644 --- a/net/hsr/hsr_device.c +++ b/net/hsr/hsr_device.c @@ -59,7 +59,7 @@ static bool hsr_check_carrier(struct hsr_port *master)

ASSERT_RTNL();

- hsr_for_each_port(master->hsr, port) { + hsr_for_each_port_rtnl(master->hsr, port) { if (port->type != HSR_PT_MASTER && is_slave_up(port->dev)) { netif_carrier_on(master->dev); return true; @@ -109,7 +109,7 @@ int hsr_get_max_mtu(struct hsr_priv *hsr) struct hsr_port *port;

mtu_max = ETH_DATA_LEN; - hsr_for_each_port(hsr, port) + hsr_for_each_port_rtnl(hsr, port) if (port->type != HSR_PT_MASTER) mtu_max = min(port->dev->mtu, mtu_max);

@@ -144,7 +144,7 @@ static int hsr_dev_open(struct net_device *dev) hsr = netdev_priv(dev); designation = '\0';

- hsr_for_each_port(hsr, port) { + hsr_for_each_port_rtnl(hsr, port) { if (port->type == HSR_PT_MASTER) continue; switch (port->type) { @@ -170,7 +170,24 @@ static int hsr_dev_open(struct net_device *dev)

static int hsr_dev_close(struct net_device *dev) { - /* Nothing to do here. */ + struct hsr_port *port; + struct hsr_priv *hsr; + + hsr = netdev_priv(dev); + hsr_for_each_port_rtnl(hsr, port) { + if (port->type == HSR_PT_MASTER) + continue; + switch (port->type) { + case HSR_PT_SLAVE_A: + case HSR_PT_SLAVE_B: + dev_uc_unsync(port->dev, dev); + dev_mc_unsync(port->dev, dev); + break; + default: + break; + } + } + return 0; }

@@ -190,7 +207,7 @@ static netdev_features_t hsr_features_recompute(struct hsr_priv *hsr, * may become enabled. */ features &= ~NETIF_F_ONE_FOR_ALL; - hsr_for_each_port(hsr, port) + hsr_for_each_port_rtnl(hsr, port) features = netdev_increment_features(features, port->dev->features, mask); @@ -211,6 +228,7 @@ static netdev_tx_t hsr_dev_xmit(struct sk_buff *skb, struct net_device *dev) struct hsr_priv *hsr = netdev_priv(dev); struct hsr_port *master;

+ rcu_read_lock(); master = hsr_port_get_hsr(hsr, HSR_PT_MASTER); if (master) { skb->dev = master->dev; @@ -223,6 +241,8 @@ static netdev_tx_t hsr_dev_xmit(struct sk_buff *skb, struct net_device *dev) dev_core_stats_tx_dropped_inc(dev); dev_kfree_skb_any(skb); } + rcu_read_unlock(); + return NETDEV_TX_OK; }

@@ -401,12 +421,133 @@ void hsr_del_ports(struct hsr_priv *hsr) hsr_del_port(port); }

+static void hsr_set_rx_mode(struct net_device *dev) +{ + struct hsr_port *port; + struct hsr_priv *hsr; + + hsr = netdev_priv(dev); + + hsr_for_each_port_rtnl(hsr, port) { + if (port->type == HSR_PT_MASTER) + continue; + switch (port->type) { + case HSR_PT_SLAVE_A: + case HSR_PT_SLAVE_B: + dev_mc_sync_multiple(port->dev, dev); + dev_uc_sync_multiple(port->dev, dev); + break; + default: + break; + } + } +} + +static void hsr_change_rx_flags(struct net_device *dev, int change) +{ + struct hsr_port *port; + struct hsr_priv *hsr; + + hsr = netdev_priv(dev); + + hsr_for_each_port_rtnl(hsr, port) { + if (port->type == HSR_PT_MASTER) + continue; + switch (port->type) { + case HSR_PT_SLAVE_A: + case HSR_PT_SLAVE_B: + if (change & IFF_ALLMULTI) + dev_set_allmulti(port->dev, + dev->flags & + IFF_ALLMULTI ? 1 : -1); + break; + default: + break; + } + } +} + +static int hsr_ndo_vlan_rx_add_vid(struct net_device *dev, + __be16 proto, u16 vid) +{ + bool is_slave_a_added = false; + bool is_slave_b_added = false; + struct hsr_port *port; + struct hsr_priv *hsr; + int ret = 0; + + hsr = netdev_priv(dev); + + hsr_for_each_port_rtnl(hsr, port) { + if (port->type == HSR_PT_MASTER || + port->type == HSR_PT_INTERLINK) + continue; + + ret = vlan_vid_add(port->dev, proto, vid); + switch (port->type) { + case HSR_PT_SLAVE_A: + if (ret) { + /* clean up Slave-B */ + netdev_err(dev, "add vid failed for Slave-A\n"); + if (is_slave_b_added) + vlan_vid_del(port->dev, proto, vid); + return ret; + } + + is_slave_a_added = true; + break; + + case HSR_PT_SLAVE_B: + if (ret) { + /* clean up Slave-A */ + netdev_err(dev, "add vid failed for Slave-B\n"); + if (is_slave_a_added) + vlan_vid_del(port->dev, proto, vid); + return ret; + } + + is_slave_b_added = true; + break; + default: + break; + } + } + + return 0; +} + +static int hsr_ndo_vlan_rx_kill_vid(struct net_device *dev, + __be16 proto, u16 vid) +{ + struct hsr_port *port; + struct hsr_priv *hsr; + + hsr = netdev_priv(dev); + + hsr_for_each_port_rtnl(hsr, port) { + switch (port->type) { + case HSR_PT_SLAVE_A: + case HSR_PT_SLAVE_B: + vlan_vid_del(port->dev, proto, vid); + break; + default: + break; + } + } + + return 0; +} + static const struct net_device_ops hsr_device_ops = { .ndo_change_mtu = hsr_dev_change_mtu, .ndo_open = hsr_dev_open, .ndo_stop = hsr_dev_close, .ndo_start_xmit = hsr_dev_xmit, + .ndo_change_rx_flags = hsr_change_rx_flags, .ndo_fix_features = hsr_fix_features, + .ndo_set_rx_mode = hsr_set_rx_mode, + .ndo_vlan_rx_add_vid = hsr_ndo_vlan_rx_add_vid, + .ndo_vlan_rx_kill_vid = hsr_ndo_vlan_rx_kill_vid, };

static struct device_type hsr_type = { @@ -447,7 +588,8 @@ void hsr_dev_setup(struct net_device *dev)

dev->hw_features = NETIF_F_SG | NETIF_F_FRAGLIST | NETIF_F_HIGHDMA | NETIF_F_GSO_MASK | NETIF_F_HW_CSUM | - NETIF_F_HW_VLAN_CTAG_TX; + NETIF_F_HW_VLAN_CTAG_TX | + NETIF_F_HW_VLAN_CTAG_FILTER;

dev->features = dev->hw_features;

@@ -533,6 +675,10 @@ int hsr_dev_finalize(struct net_device *hsr_dev, struct net_device *slave[2], (slave[1]->features & NETIF_F_HW_HSR_FWD)) hsr->fwd_offloaded = true;

+ if ((slave[0]->features & NETIF_F_HW_VLAN_CTAG_FILTER) && + (slave[1]->features & NETIF_F_HW_VLAN_CTAG_FILTER)) + hsr_dev->features |= NETIF_F_HW_VLAN_CTAG_FILTER; + res = register_netdevice(hsr_dev); if (res) goto err_unregister; diff --git a/net/hsr/hsr_main.c b/net/hsr/hsr_main.c index 257b50124cee..76a1958609e2 100644 --- a/net/hsr/hsr_main.c +++ b/net/hsr/hsr_main.c @@ -22,7 +22,7 @@ static bool hsr_slave_empty(struct hsr_priv *hsr) { struct hsr_port *port;

- hsr_for_each_port(hsr, port) + hsr_for_each_port_rtnl(hsr, port) if (port->type != HSR_PT_MASTER) return false; return true; @@ -125,7 +125,7 @@ struct hsr_port *hsr_port_get_hsr(struct hsr_priv *hsr, enum hsr_port_type pt) { struct hsr_port *port;

- hsr_for_each_port(hsr, port) + hsr_for_each_port_rtnl(hsr, port) if (port->type == pt) return port; return NULL; diff --git a/net/hsr/hsr_main.h b/net/hsr/hsr_main.h index 18e01791ad79..2fcabe39e61f 100644 --- a/net/hsr/hsr_main.h +++ b/net/hsr/hsr_main.h @@ -221,6 +221,9 @@ struct hsr_priv { #define hsr_for_each_port(hsr, port) \ list_for_each_entry_rcu((port), &(hsr)->ports, port_list)

+#define hsr_for_each_port_rtnl(hsr, port) \ + list_for_each_entry_rcu((port), &(hsr)->ports, port_list, lockdep_rtnl_is_held()) + struct hsr_port *hsr_port_get_hsr(struct hsr_priv *hsr, enum hsr_port_type pt);

/* Caller must ensure skb is a valid HSR frame */ diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c index deb08cab4464..75e3d7501752 100644 --- a/net/ipv4/ip_tunnel_core.c +++ b/net/ipv4/ip_tunnel_core.c @@ -203,6 +203,9 @@ static int iptunnel_pmtud_build_icmp(struct sk_buff *skb, int mtu) if (!pskb_may_pull(skb, ETH_HLEN + sizeof(struct iphdr))) return -EINVAL;

+ if (skb_is_gso(skb)) + skb_gso_reset(skb); + skb_copy_bits(skb, skb_mac_offset(skb), &eh, ETH_HLEN); pskb_pull(skb, ETH_HLEN); skb_reset_network_header(skb); @@ -297,6 +300,9 @@ static int iptunnel_pmtud_build_icmpv6(struct sk_buff *skb, int mtu) if (!pskb_may_pull(skb, ETH_HLEN + sizeof(struct ipv6hdr))) return -EINVAL;

+ if (skb_is_gso(skb)) + skb_gso_reset(skb); + skb_copy_bits(skb, skb_mac_offset(skb), &eh, ETH_HLEN); pskb_pull(skb, ETH_HLEN); skb_reset_network_header(skb); diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c index 5312237e8040..7518d2af6308 100644 --- a/net/ipv4/tcp_bpf.c +++ b/net/ipv4/tcp_bpf.c @@ -408,8 +408,11 @@ static int tcp_bpf_send_verdict(struct sock *sk, struct sk_psock *psock, if (!psock->cork) { psock->cork = kzalloc(sizeof(*psock->cork), GFP_ATOMIC | __GFP_NOWARN); - if (!psock->cork) + if (!psock->cork) { + sk_msg_free(sk, msg); + *copied = 0; return -ENOMEM; + } } memcpy(psock->cork, msg, sizeof(*msg)); return 0; diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c index 31f6899ef71a..b31ba9f905e3 100644 --- a/net/mptcp/sockopt.c +++ b/net/mptcp/sockopt.c @@ -1471,13 +1471,12 @@ static void sync_socket_options(struct mptcp_sock *msk, struct sock *ssk) { static const unsigned int tx_rx_locks = SOCK_RCVBUF_LOCK | SOCK_SNDBUF_LOCK; struct sock *sk = (struct sock *)msk; + bool keep_open;

- if (ssk->sk_prot->keepalive) { - if (sock_flag(sk, SOCK_KEEPOPEN)) - ssk->sk_prot->keepalive(ssk, 1); - else - ssk->sk_prot->keepalive(ssk, 0); - } + keep_open = sock_flag(sk, SOCK_KEEPOPEN); + if (ssk->sk_prot->keepalive) + ssk->sk_prot->keepalive(ssk, keep_open); + sock_valbool_flag(ssk, SOCK_KEEPOPEN, keep_open);

ssk->sk_priority = sk->sk_priority; ssk->sk_bound_dev_if = sk->sk_bound_dev_if; diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c index 73bc39281ef5..9b45fbdc90ca 100644 --- a/net/sunrpc/sched.c +++ b/net/sunrpc/sched.c @@ -276,8 +276,6 @@ EXPORT_SYMBOL_GPL(rpc_destroy_wait_queue);

static int rpc_wait_bit_killable(struct wait_bit_key *key, int mode) { - if (unlikely(current->flags & PF_EXITING)) - return -EINTR; schedule(); if (signal_pending_state(mode, current)) return -ERESTARTSYS; diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 8b27a21f3b42..3660ef264711 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -407,9 +407,9 @@ xs_sock_recv_cmsg(struct socket *sock, unsigned int *msg_flags, int flags) iov_iter_kvec(&msg.msg_iter, ITER_DEST, &alert_kvec, 1, alert_kvec.iov_len); ret = sock_recvmsg(sock, &msg, flags); - if (ret > 0 && - tls_get_record_type(sock->sk, &u.cmsg) == TLS_RECORD_TYPE_ALERT) { - iov_iter_revert(&msg.msg_iter, ret); + if (ret > 0) { + if (tls_get_record_type(sock->sk, &u.cmsg) == TLS_RECORD_TYPE_ALERT) + iov_iter_revert(&msg.msg_iter, ret); ret = xs_sock_process_cmsg(sock, &msg, msg_flags, &u.cmsg, -EAGAIN); } diff --git a/samples/ftrace/ftrace-direct-modify.c b/samples/ftrace/ftrace-direct-modify.c index e2a6a69352df..b40f85e3806f 100644 --- a/samples/ftrace/ftrace-direct-modify.c +++ b/samples/ftrace/ftrace-direct-modify.c @@ -40,8 +40,8 @@ asm ( CALL_DEPTH_ACCOUNT " call my_direct_func1\n" " leave\n" -" .size my_tramp1, .-my_tramp1\n" ASM_RET +" .size my_tramp1, .-my_tramp1\n"

" .type my_tramp2, @function\n" " .globl my_tramp2\n" diff --git a/scripts/Makefile.kasan b/scripts/Makefile.kasan index 390658a2d5b7..a57c24c12972 100644 --- a/scripts/Makefile.kasan +++ b/scripts/Makefile.kasan @@ -68,10 +68,14 @@ CFLAGS_KASAN := -fsanitize=kernel-hwaddress \ $(call cc-param,hwasan-inline-all-checks=0) \ $(instrumentation_flags)

-# Instrument memcpy/memset/memmove calls by using instrumented __hwasan_mem*(). -ifeq ($(call clang-min-version, 150000)$(call gcc-min-version, 130000),y) -CFLAGS_KASAN += $(call cc-param,hwasan-kernel-mem-intrinsic-prefix=1) -endif +# Instrument memcpy/memset/memmove calls by using instrumented __(hw)asan_mem*(). +ifdef CONFIG_CC_HAS_KASAN_MEMINTRINSIC_PREFIX + ifdef CONFIG_CC_IS_GCC + CFLAGS_KASAN += $(call cc-param,asan-kernel-mem-intrinsic-prefix=1) + else + CFLAGS_KASAN += $(call cc-param,hwasan-kernel-mem-intrinsic-prefix=1) + endif +endif # CONFIG_CC_HAS_KASAN_MEMINTRINSIC_PREFIX

endif # CONFIG_KASAN_SW_TAGS

diff --git a/security/integrity/ima/ima_main.c b/security/integrity/ima/ima_main.c index 068edb0d79f7..3b734a4dfcbe 100644 --- a/security/integrity/ima/ima_main.c +++ b/security/integrity/ima/ima_main.c @@ -128,16 +128,22 @@ static void ima_rdwr_violation_check(struct file *file, if (atomic_read(&inode->i_readcount) && IS_IMA(inode)) { if (!iint) iint = integrity_iint_find(inode); + /* IMA_MEASURE is set from reader side */ - if (iint && test_bit(IMA_MUST_MEASURE, - &iint->atomic_flags)) + if (iint && test_and_clear_bit(IMA_MAY_EMIT_TOMTOU, + &iint->atomic_flags)) send_tomtou = true; } } else { if (must_measure) - set_bit(IMA_MUST_MEASURE, &iint->atomic_flags); - if (inode_is_open_for_write(inode) && must_measure) - send_writers = true; + set_bit(IMA_MAY_EMIT_TOMTOU, &iint->atomic_flags); + + /* Limit number of open_writers violations */ + if (inode_is_open_for_write(inode) && must_measure) { + if (!test_and_set_bit(IMA_EMITTED_OPENWRITERS, + &iint->atomic_flags)) + send_writers = true; + } }

if (!send_tomtou && !send_writers) diff --git a/security/integrity/integrity.h b/security/integrity/integrity.h index ad20ff7f5dfa..a007edae938a 100644 --- a/security/integrity/integrity.h +++ b/security/integrity/integrity.h @@ -74,7 +74,8 @@ #define IMA_UPDATE_XATTR 1 #define IMA_CHANGE_ATTR 2 #define IMA_DIGSIG 3 -#define IMA_MUST_MEASURE 4 +#define IMA_MAY_EMIT_TOMTOU 4 +#define IMA_EMITTED_OPENWRITERS 5

enum evm_ima_xattr_type { IMA_XATTR_DIGEST = 0x01,