From dca3f53c02e325bb19dfc05b1571b9a706226fea Mon Sep 17 00:00:00 2001 From: Phil Sutter Date: Thu, 4 Aug 2016 12:11:55 +0200 Subject: sctp: Export struct sctp_info to userspace This is required to correctly interpret INET_DIAG_INFO messages exported by sctp_diag module. Signed-off-by: Phil Sutter Signed-off-by: David S. Miller --- include/linux/sctp.h | 64 ---------------------------------------------------- 1 file changed, 64 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sctp.h b/include/linux/sctp.h index de1f64318fc4..fcb4c3646173 100644 --- a/include/linux/sctp.h +++ b/include/linux/sctp.h @@ -705,70 +705,6 @@ typedef struct sctp_auth_chunk { sctp_authhdr_t auth_hdr; } __packed sctp_auth_chunk_t; -struct sctp_info { - __u32 sctpi_tag; - __u32 sctpi_state; - __u32 sctpi_rwnd; - __u16 sctpi_unackdata; - __u16 sctpi_penddata; - __u16 sctpi_instrms; - __u16 sctpi_outstrms; - __u32 sctpi_fragmentation_point; - __u32 sctpi_inqueue; - __u32 sctpi_outqueue; - __u32 sctpi_overall_error; - __u32 sctpi_max_burst; - __u32 sctpi_maxseg; - __u32 sctpi_peer_rwnd; - __u32 sctpi_peer_tag; - __u8 sctpi_peer_capable; - __u8 sctpi_peer_sack; - __u16 __reserved1; - - /* assoc status info */ - __u64 sctpi_isacks; - __u64 sctpi_osacks; - __u64 sctpi_opackets; - __u64 sctpi_ipackets; - __u64 sctpi_rtxchunks; - __u64 sctpi_outofseqtsns; - __u64 sctpi_idupchunks; - __u64 sctpi_gapcnt; - __u64 sctpi_ouodchunks; - __u64 sctpi_iuodchunks; - __u64 sctpi_oodchunks; - __u64 sctpi_iodchunks; - __u64 sctpi_octrlchunks; - __u64 sctpi_ictrlchunks; - - /* primary transport info */ - struct sockaddr_storage sctpi_p_address; - __s32 sctpi_p_state; - __u32 sctpi_p_cwnd; - __u32 sctpi_p_srtt; - __u32 sctpi_p_rto; - __u32 sctpi_p_hbinterval; - __u32 sctpi_p_pathmaxrxt; - __u32 sctpi_p_sackdelay; - __u32 sctpi_p_sackfreq; - __u32 sctpi_p_ssthresh; - __u32 sctpi_p_partial_bytes_acked; - __u32 sctpi_p_flight_size; - __u16 sctpi_p_error; - __u16 __reserved2; - - /* sctp sock info */ - __u32 sctpi_s_autoclose; - __u32 sctpi_s_adaptation_ind; - __u32 sctpi_s_pd_point; - __u8 sctpi_s_nodelay; - __u8 sctpi_s_disable_fragments; - __u8 sctpi_s_v4mapped; - __u8 sctpi_s_frag_interleave; - __u32 sctpi_s_type; - __u32 __reserved3; -}; - struct sctp_infox { struct sctp_info *sctpinfo; struct sctp_association *asoc; -- cgit v1.2.3-71-gd317 From 479ffcccefd7b04442b0e949f8779b0612e8c75f Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Fri, 5 Aug 2016 00:11:12 +0200 Subject: bpf: fix checksum fixups on bpf_skb_store_bytes bpf_skb_store_bytes() invocations above L2 header need BPF_F_RECOMPUTE_CSUM flag for updates, so that CHECKSUM_COMPLETE will be fixed up along the way. Where we ran into an issue with bpf_skb_store_bytes() is when we did a single-byte update on the IPv6 hoplimit despite using BPF_F_RECOMPUTE_CSUM flag; simple ping via ICMPv6 triggered a hw csum failure as a result. The underlying issue has been tracked down to a buffer alignment issue. Meaning, that csum_partial() computations via skb_postpull_rcsum() and skb_postpush_rcsum() pair invoked had a wrong result since they operated on an odd address for the hoplimit, while other computations were done on an even address. This mix doesn't work as-is with skb_postpull_rcsum(), skb_postpush_rcsum() pair as it always expects at least half-word alignment of input buffers, which is normally the case. Thus, instead of these helpers using csum_sub() and (implicitly) csum_add(), we need to use csum_block_sub(), csum_block_add(), respectively. For unaligned offsets, they rotate the sum to align it to a half-word boundary again, otherwise they work the same as csum_sub() and csum_add(). Adding __skb_postpull_rcsum(), __skb_postpush_rcsum() variants that take the offset as an input and adapting bpf_skb_store_bytes() to them fixes the hw csum failures again. The skb_postpull_rcsum(), skb_postpush_rcsum() helpers use a 0 constant for offset so that the compiler optimizes the offset & 1 test away and generates the same code as with csum_sub()/_add(). Fixes: 608cd71a9c7c ("tc: bpf: generalize pedit action") Signed-off-by: Daniel Borkmann Acked-by: Alexei Starovoitov Signed-off-by: David S. Miller --- include/linux/skbuff.h | 52 ++++++++++++++++++++++++++++++++------------------ net/core/filter.c | 4 ++-- 2 files changed, 35 insertions(+), 21 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 6f0b3e0adc73..0f665cb26b50 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -2847,6 +2847,18 @@ static inline int skb_linearize_cow(struct sk_buff *skb) __skb_linearize(skb) : 0; } +static __always_inline void +__skb_postpull_rcsum(struct sk_buff *skb, const void *start, unsigned int len, + unsigned int off) +{ + if (skb->ip_summed == CHECKSUM_COMPLETE) + skb->csum = csum_block_sub(skb->csum, + csum_partial(start, len, 0), off); + else if (skb->ip_summed == CHECKSUM_PARTIAL && + skb_checksum_start_offset(skb) < 0) + skb->ip_summed = CHECKSUM_NONE; +} + /** * skb_postpull_rcsum - update checksum for received skb after pull * @skb: buffer to update @@ -2857,36 +2869,38 @@ static inline int skb_linearize_cow(struct sk_buff *skb) * update the CHECKSUM_COMPLETE checksum, or set ip_summed to * CHECKSUM_NONE so that it can be recomputed from scratch. */ - static inline void skb_postpull_rcsum(struct sk_buff *skb, const void *start, unsigned int len) { - if (skb->ip_summed == CHECKSUM_COMPLETE) - skb->csum = csum_sub(skb->csum, csum_partial(start, len, 0)); - else if (skb->ip_summed == CHECKSUM_PARTIAL && - skb_checksum_start_offset(skb) < 0) - skb->ip_summed = CHECKSUM_NONE; + __skb_postpull_rcsum(skb, start, len, 0); } -unsigned char *skb_pull_rcsum(struct sk_buff *skb, unsigned int len); +static __always_inline void +__skb_postpush_rcsum(struct sk_buff *skb, const void *start, unsigned int len, + unsigned int off) +{ + if (skb->ip_summed == CHECKSUM_COMPLETE) + skb->csum = csum_block_add(skb->csum, + csum_partial(start, len, 0), off); +} +/** + * skb_postpush_rcsum - update checksum for received skb after push + * @skb: buffer to update + * @start: start of data after push + * @len: length of data pushed + * + * After doing a push on a received packet, you need to call this to + * update the CHECKSUM_COMPLETE checksum. + */ static inline void skb_postpush_rcsum(struct sk_buff *skb, const void *start, unsigned int len) { - /* For performing the reverse operation to skb_postpull_rcsum(), - * we can instead of ... - * - * skb->csum = csum_add(skb->csum, csum_partial(start, len, 0)); - * - * ... just use this equivalent version here to save a few - * instructions. Feeding csum of 0 in csum_partial() and later - * on adding skb->csum is equivalent to feed skb->csum in the - * first place. - */ - if (skb->ip_summed == CHECKSUM_COMPLETE) - skb->csum = csum_partial(start, len, skb->csum); + __skb_postpush_rcsum(skb, start, len, 0); } +unsigned char *skb_pull_rcsum(struct sk_buff *skb, unsigned int len); + /** * skb_push_rcsum - push skb and update receive checksum * @skb: buffer to update diff --git a/net/core/filter.c b/net/core/filter.c index c46244f83a8f..5ecd5c9836c3 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -1401,7 +1401,7 @@ static u64 bpf_skb_store_bytes(u64 r1, u64 r2, u64 r3, u64 r4, u64 flags) return -EFAULT; if (flags & BPF_F_RECOMPUTE_CSUM) - skb_postpull_rcsum(skb, ptr, len); + __skb_postpull_rcsum(skb, ptr, len, offset); memcpy(ptr, from, len); @@ -1410,7 +1410,7 @@ static u64 bpf_skb_store_bytes(u64 r1, u64 r2, u64 r3, u64 r4, u64 flags) skb_store_bits(skb, offset, ptr, len); if (flags & BPF_F_RECOMPUTE_CSUM) - skb_postpush_rcsum(skb, ptr, len); + __skb_postpush_rcsum(skb, ptr, len, offset); if (flags & BPF_F_INVALIDATE_HASH) skb_clear_hash(skb); -- cgit v1.2.3-71-gd317 From 59bcb7972fc5d53a621ee6b2c3cf1654cebb3dc5 Mon Sep 17 00:00:00 2001 From: Sudarsana Reddy Kalluru Date: Mon, 8 Aug 2016 21:57:42 -0400 Subject: qed: Add dcbx app support for IEEE Selection Field. MFW now supports the Selection field for IEEE mode. Add driver changes to use the newer MFW masks to read/write the port-id value. Signed-off-by: Sudarsana Reddy Kalluru Signed-off-by: Yuval Mintz Signed-off-by: David S. Miller --- drivers/net/ethernet/qlogic/qed/qed_dcbx.c | 124 ++++++++++++++++++++++++----- include/linux/qed/qed_if.h | 8 ++ 2 files changed, 112 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/qlogic/qed/qed_dcbx.c b/drivers/net/ethernet/qlogic/qed/qed_dcbx.c index f07f0ac239f6..b157a6aba277 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_dcbx.c +++ b/drivers/net/ethernet/qlogic/qed/qed_dcbx.c @@ -69,6 +69,17 @@ static bool qed_dcbx_app_port(u32 app_info_bitmap) DCBX_APP_SF_PORT); } +static bool qed_dcbx_ieee_app_port(u32 app_info_bitmap, u8 type) +{ + u8 mfw_val = QED_MFW_GET_FIELD(app_info_bitmap, DCBX_APP_SF_IEEE); + + /* Old MFW */ + if (mfw_val == DCBX_APP_SF_IEEE_RESERVED) + return qed_dcbx_app_port(app_info_bitmap); + + return !!(mfw_val == type || mfw_val == DCBX_APP_SF_IEEE_TCP_UDP_PORT); +} + static bool qed_dcbx_default_tlv(u32 app_info_bitmap, u16 proto_id, bool ieee) { bool ethtype; @@ -81,10 +92,17 @@ static bool qed_dcbx_default_tlv(u32 app_info_bitmap, u16 proto_id, bool ieee) return !!(ethtype && (proto_id == QED_ETH_TYPE_DEFAULT)); } -static bool qed_dcbx_iscsi_tlv(u32 app_info_bitmap, u16 proto_id) +static bool qed_dcbx_iscsi_tlv(u32 app_info_bitmap, u16 proto_id, bool ieee) { - return !!(qed_dcbx_app_port(app_info_bitmap) && - proto_id == QED_TCP_PORT_ISCSI); + bool port; + + if (ieee) + port = qed_dcbx_ieee_app_port(app_info_bitmap, + DCBX_APP_SF_IEEE_TCP_PORT); + else + port = qed_dcbx_app_port(app_info_bitmap); + + return !!(port && (proto_id == QED_TCP_PORT_ISCSI)); } static bool qed_dcbx_fcoe_tlv(u32 app_info_bitmap, u16 proto_id, bool ieee) @@ -111,10 +129,17 @@ static bool qed_dcbx_roce_tlv(u32 app_info_bitmap, u16 proto_id, bool ieee) return !!(ethtype && (proto_id == QED_ETH_TYPE_ROCE)); } -static bool qed_dcbx_roce_v2_tlv(u32 app_info_bitmap, u16 proto_id) +static bool qed_dcbx_roce_v2_tlv(u32 app_info_bitmap, u16 proto_id, bool ieee) { - return !!(qed_dcbx_app_port(app_info_bitmap) && - proto_id == QED_UDP_PORT_TYPE_ROCE_V2); + bool port; + + if (ieee) + port = qed_dcbx_ieee_app_port(app_info_bitmap, + DCBX_APP_SF_IEEE_UDP_PORT); + else + port = qed_dcbx_app_port(app_info_bitmap); + + return !!(port && (proto_id == QED_UDP_PORT_TYPE_ROCE_V2)); } static void @@ -199,11 +224,11 @@ qed_dcbx_get_app_protocol_type(struct qed_hwfn *p_hwfn, *type = DCBX_PROTOCOL_FCOE; } else if (qed_dcbx_roce_tlv(app_prio_bitmap, id, ieee)) { *type = DCBX_PROTOCOL_ROCE; - } else if (qed_dcbx_iscsi_tlv(app_prio_bitmap, id)) { + } else if (qed_dcbx_iscsi_tlv(app_prio_bitmap, id, ieee)) { *type = DCBX_PROTOCOL_ISCSI; } else if (qed_dcbx_default_tlv(app_prio_bitmap, id, ieee)) { *type = DCBX_PROTOCOL_ETH; - } else if (qed_dcbx_roce_v2_tlv(app_prio_bitmap, id)) { + } else if (qed_dcbx_roce_v2_tlv(app_prio_bitmap, id, ieee)) { *type = DCBX_PROTOCOL_ROCE_V2; } else { *type = DCBX_MAX_PROTOCOL_TYPE; @@ -441,8 +466,39 @@ qed_dcbx_get_app_data(struct qed_hwfn *p_hwfn, DCBX_APP_NUM_ENTRIES); for (i = 0; i < DCBX_MAX_APP_PROTOCOL; i++) { entry = &p_params->app_entry[i]; - entry->ethtype = !(QED_MFW_GET_FIELD(p_tbl[i].entry, - DCBX_APP_SF)); + if (ieee) { + u8 sf_ieee; + u32 val; + + sf_ieee = QED_MFW_GET_FIELD(p_tbl[i].entry, + DCBX_APP_SF_IEEE); + switch (sf_ieee) { + case DCBX_APP_SF_IEEE_RESERVED: + /* Old MFW */ + val = QED_MFW_GET_FIELD(p_tbl[i].entry, + DCBX_APP_SF); + entry->sf_ieee = val ? + QED_DCBX_SF_IEEE_TCP_UDP_PORT : + QED_DCBX_SF_IEEE_ETHTYPE; + break; + case DCBX_APP_SF_IEEE_ETHTYPE: + entry->sf_ieee = QED_DCBX_SF_IEEE_ETHTYPE; + break; + case DCBX_APP_SF_IEEE_TCP_PORT: + entry->sf_ieee = QED_DCBX_SF_IEEE_TCP_PORT; + break; + case DCBX_APP_SF_IEEE_UDP_PORT: + entry->sf_ieee = QED_DCBX_SF_IEEE_UDP_PORT; + break; + case DCBX_APP_SF_IEEE_TCP_UDP_PORT: + entry->sf_ieee = QED_DCBX_SF_IEEE_TCP_UDP_PORT; + break; + } + } else { + entry->ethtype = !(QED_MFW_GET_FIELD(p_tbl[i].entry, + DCBX_APP_SF)); + } + pri_map = QED_MFW_GET_FIELD(p_tbl[i].entry, DCBX_APP_PRI_MAP); entry->prio = ffs(pri_map) - 1; entry->proto_id = QED_MFW_GET_FIELD(p_tbl[i].entry, @@ -981,7 +1037,7 @@ qed_dcbx_set_ets_data(struct qed_hwfn *p_hwfn, static void qed_dcbx_set_app_data(struct qed_hwfn *p_hwfn, struct dcbx_app_priority_feature *p_app, - struct qed_dcbx_params *p_params) + struct qed_dcbx_params *p_params, bool ieee) { u32 *entry; int i; @@ -1002,12 +1058,36 @@ qed_dcbx_set_app_data(struct qed_hwfn *p_hwfn, for (i = 0; i < DCBX_MAX_APP_PROTOCOL; i++) { entry = &p_app->app_pri_tbl[i].entry; - *entry &= ~DCBX_APP_SF_MASK; - if (p_params->app_entry[i].ethtype) - *entry |= ((u32)DCBX_APP_SF_ETHTYPE << - DCBX_APP_SF_SHIFT); - else - *entry |= ((u32)DCBX_APP_SF_PORT << DCBX_APP_SF_SHIFT); + if (ieee) { + *entry &= ~DCBX_APP_SF_IEEE_MASK; + switch (p_params->app_entry[i].sf_ieee) { + case QED_DCBX_SF_IEEE_ETHTYPE: + *entry |= ((u32)DCBX_APP_SF_IEEE_ETHTYPE << + DCBX_APP_SF_IEEE_SHIFT); + break; + case QED_DCBX_SF_IEEE_TCP_PORT: + *entry |= ((u32)DCBX_APP_SF_IEEE_TCP_PORT << + DCBX_APP_SF_IEEE_SHIFT); + break; + case QED_DCBX_SF_IEEE_UDP_PORT: + *entry |= ((u32)DCBX_APP_SF_IEEE_UDP_PORT << + DCBX_APP_SF_IEEE_SHIFT); + break; + case QED_DCBX_SF_IEEE_TCP_UDP_PORT: + *entry |= ((u32)DCBX_APP_SF_IEEE_TCP_UDP_PORT << + DCBX_APP_SF_IEEE_SHIFT); + break; + } + } else { + *entry &= ~DCBX_APP_SF_MASK; + if (p_params->app_entry[i].ethtype) + *entry |= ((u32)DCBX_APP_SF_ETHTYPE << + DCBX_APP_SF_SHIFT); + else + *entry |= ((u32)DCBX_APP_SF_PORT << + DCBX_APP_SF_SHIFT); + } + *entry &= ~DCBX_APP_PROTOCOL_ID_MASK; *entry |= ((u32)p_params->app_entry[i].proto_id << DCBX_APP_PROTOCOL_ID_SHIFT); @@ -1022,15 +1102,19 @@ qed_dcbx_set_local_params(struct qed_hwfn *p_hwfn, struct dcbx_local_params *local_admin, struct qed_dcbx_set *params) { + bool ieee = false; + local_admin->flags = 0; memcpy(&local_admin->features, &p_hwfn->p_dcbx_info->operational.features, sizeof(local_admin->features)); - if (params->enabled) + if (params->enabled) { local_admin->config = params->ver_num; - else + ieee = !!(params->ver_num & DCBX_CONFIG_VERSION_IEEE); + } else { local_admin->config = DCBX_CONFIG_VERSION_DISABLED; + } if (params->override_flags & QED_DCBX_OVERRIDE_PFC_CFG) qed_dcbx_set_pfc_data(p_hwfn, &local_admin->features.pfc, @@ -1042,7 +1126,7 @@ qed_dcbx_set_local_params(struct qed_hwfn *p_hwfn, if (params->override_flags & QED_DCBX_OVERRIDE_APP_CFG) qed_dcbx_set_app_data(p_hwfn, &local_admin->features.app, - ¶ms->config.params); + ¶ms->config.params, ieee); } int qed_dcbx_config_params(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index b1e3c57c7117..d6c4177df7cb 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -70,8 +70,16 @@ struct qed_dbcx_pfc_params { u8 max_tc; }; +enum qed_dcbx_sf_ieee_type { + QED_DCBX_SF_IEEE_ETHTYPE, + QED_DCBX_SF_IEEE_TCP_PORT, + QED_DCBX_SF_IEEE_UDP_PORT, + QED_DCBX_SF_IEEE_TCP_UDP_PORT +}; + struct qed_app_entry { bool ethtype; + enum qed_dcbx_sf_ieee_type sf_ieee; bool enabled; u8 prio; u16 proto_id; -- cgit v1.2.3-71-gd317 From fd837b08d98c0c9f4f31998f2ed55b9d8694082c Mon Sep 17 00:00:00 2001 From: Andre Przywara Date: Mon, 8 Aug 2016 17:29:28 +0100 Subject: KVM: arm64: ITS: return 1 on successful MSI injection According to the KVM API documentation a successful MSI injection should return a value > 0 on success. Return possible errors in vgic_its_trigger_msi() and report a successful injection back to userland, while also reporting the case where the MSI could not be delivered due to the guest not having the LPI mapped, for instance. Signed-off-by: Andre Przywara Reviewed-by: Eric Auger Reviewed-by: Christoffer Dall Signed-off-by: Christoffer Dall --- include/linux/irqchip/arm-gic-v3.h | 1 + virt/kvm/arm/vgic/vgic-its.c | 56 +++++++++++++++++++++++++------------- 2 files changed, 38 insertions(+), 19 deletions(-) (limited to 'include/linux') diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h index 56b0b7ec66aa..99ac022edc60 100644 --- a/include/linux/irqchip/arm-gic-v3.h +++ b/include/linux/irqchip/arm-gic-v3.h @@ -337,6 +337,7 @@ */ #define E_ITS_MOVI_UNMAPPED_INTERRUPT 0x010107 #define E_ITS_MOVI_UNMAPPED_COLLECTION 0x010109 +#define E_ITS_INT_UNMAPPED_INTERRUPT 0x010307 #define E_ITS_CLEAR_UNMAPPED_INTERRUPT 0x010507 #define E_ITS_MAPD_DEVICE_OOR 0x010801 #define E_ITS_MAPC_PROCNUM_OOR 0x010902 diff --git a/virt/kvm/arm/vgic/vgic-its.c b/virt/kvm/arm/vgic/vgic-its.c index 07411cf967b9..1bd8adbeae26 100644 --- a/virt/kvm/arm/vgic/vgic-its.c +++ b/virt/kvm/arm/vgic/vgic-its.c @@ -441,39 +441,48 @@ static unsigned long vgic_mmio_read_its_idregs(struct kvm *kvm, * Find the target VCPU and the LPI number for a given devid/eventid pair * and make this IRQ pending, possibly injecting it. * Must be called with the its_lock mutex held. + * Returns 0 on success, a positive error value for any ITS mapping + * related errors and negative error values for generic errors. */ -static void vgic_its_trigger_msi(struct kvm *kvm, struct vgic_its *its, - u32 devid, u32 eventid) +static int vgic_its_trigger_msi(struct kvm *kvm, struct vgic_its *its, + u32 devid, u32 eventid) { + struct kvm_vcpu *vcpu; struct its_itte *itte; if (!its->enabled) - return; + return -EBUSY; itte = find_itte(its, devid, eventid); - /* Triggering an unmapped IRQ gets silently dropped. */ - if (itte && its_is_collection_mapped(itte->collection)) { - struct kvm_vcpu *vcpu; - - vcpu = kvm_get_vcpu(kvm, itte->collection->target_addr); - if (vcpu && vcpu->arch.vgic_cpu.lpis_enabled) { - spin_lock(&itte->irq->irq_lock); - itte->irq->pending = true; - vgic_queue_irq_unlock(kvm, itte->irq); - } - } + if (!itte || !its_is_collection_mapped(itte->collection)) + return E_ITS_INT_UNMAPPED_INTERRUPT; + + vcpu = kvm_get_vcpu(kvm, itte->collection->target_addr); + if (!vcpu) + return E_ITS_INT_UNMAPPED_INTERRUPT; + + if (!vcpu->arch.vgic_cpu.lpis_enabled) + return -EBUSY; + + spin_lock(&itte->irq->irq_lock); + itte->irq->pending = true; + vgic_queue_irq_unlock(kvm, itte->irq); + + return 0; } /* * Queries the KVM IO bus framework to get the ITS pointer from the given * doorbell address. * We then call vgic_its_trigger_msi() with the decoded data. + * According to the KVM_SIGNAL_MSI API description returns 1 on success. */ int vgic_its_inject_msi(struct kvm *kvm, struct kvm_msi *msi) { u64 address; struct kvm_io_device *kvm_io_dev; struct vgic_io_device *iodev; + int ret; if (!vgic_has_its(kvm)) return -ENODEV; @@ -490,10 +499,21 @@ int vgic_its_inject_msi(struct kvm *kvm, struct kvm_msi *msi) iodev = container_of(kvm_io_dev, struct vgic_io_device, dev); mutex_lock(&iodev->its->its_lock); - vgic_its_trigger_msi(kvm, iodev->its, msi->devid, msi->data); + ret = vgic_its_trigger_msi(kvm, iodev->its, msi->devid, msi->data); mutex_unlock(&iodev->its->its_lock); - return 0; + if (ret < 0) + return ret; + + /* + * KVM_SIGNAL_MSI demands a return value > 0 for success and 0 + * if the guest has blocked the MSI. So we map any LPI mapping + * related error to that. + */ + if (ret) + return 0; + else + return 1; } /* Requires the its_lock to be held. */ @@ -981,9 +1001,7 @@ static int vgic_its_cmd_handle_int(struct kvm *kvm, struct vgic_its *its, u32 msi_data = its_cmd_get_id(its_cmd); u64 msi_devid = its_cmd_get_deviceid(its_cmd); - vgic_its_trigger_msi(kvm, its, msi_devid, msi_data); - - return 0; + return vgic_its_trigger_msi(kvm, its, msi_devid, msi_data); } /* -- cgit v1.2.3-71-gd317 From 1766e7b3763a0707c2fda9689a7866dceed07b7a Mon Sep 17 00:00:00 2001 From: David Lechner Date: Wed, 10 Aug 2016 18:49:27 +0530 Subject: mfd: da8xx-cfgchip: New header file for CFGCHIP registers Create a new header file for TI DA8XX SoC CFGCHIPx registers. This will be used by a number of planned drivers including a new USB PHY driver and common clock framework drivers. The same defines *will* be removed from the platform_data header, once all the users start using the new syscon device header. This also fixes the following compiler error caused due to a dependent patch not merged. drivers/phy/phy-da8xx-usb.c:19:37: fatal error: linux/mfd/da8xx-cfgchip.h: No such file or directory #include Signed-off-by: David Lechner Acked-by: Lee Jones Reported-by: Arnd Bergmann Signed-off-by: Kishon Vijay Abraham I --- include/linux/mfd/da8xx-cfgchip.h | 153 ++++++++++++++++++++++++++++++++++++++ 1 file changed, 153 insertions(+) create mode 100644 include/linux/mfd/da8xx-cfgchip.h (limited to 'include/linux') diff --git a/include/linux/mfd/da8xx-cfgchip.h b/include/linux/mfd/da8xx-cfgchip.h new file mode 100644 index 000000000000..304985e288d2 --- /dev/null +++ b/include/linux/mfd/da8xx-cfgchip.h @@ -0,0 +1,153 @@ +/* + * TI DaVinci DA8xx CHIPCFGx registers for syscon consumers. + * + * Copyright (C) 2016 David Lechner + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + */ + +#ifndef __LINUX_MFD_DA8XX_CFGCHIP_H +#define __LINUX_MFD_DA8XX_CFGCHIP_H + +#include + +/* register offset (32-bit registers) */ +#define CFGCHIP(n) ((n) * 4) + +/* CFGCHIP0 (PLL0/EDMA3_0) register bits */ +#define CFGCHIP0_PLL_MASTER_LOCK BIT(4) +#define CFGCHIP0_EDMA30TC1DBS(n) ((n) << 2) +#define CFGCHIP0_EDMA30TC1DBS_MASK CFGCHIP0_EDMA30TC1DBS(0x3) +#define CFGCHIP0_EDMA30TC1DBS_16 CFGCHIP0_EDMA30TC1DBS(0x0) +#define CFGCHIP0_EDMA30TC1DBS_32 CFGCHIP0_EDMA30TC1DBS(0x1) +#define CFGCHIP0_EDMA30TC1DBS_64 CFGCHIP0_EDMA30TC1DBS(0x2) +#define CFGCHIP0_EDMA30TC0DBS(n) ((n) << 0) +#define CFGCHIP0_EDMA30TC0DBS_MASK CFGCHIP0_EDMA30TC0DBS(0x3) +#define CFGCHIP0_EDMA30TC0DBS_16 CFGCHIP0_EDMA30TC0DBS(0x0) +#define CFGCHIP0_EDMA30TC0DBS_32 CFGCHIP0_EDMA30TC0DBS(0x1) +#define CFGCHIP0_EDMA30TC0DBS_64 CFGCHIP0_EDMA30TC0DBS(0x2) + +/* CFGCHIP1 (eCAP/HPI/EDMA3_1/eHRPWM TBCLK/McASP0 AMUTEIN) register bits */ +#define CFGCHIP1_CAP2SRC(n) ((n) << 27) +#define CFGCHIP1_CAP2SRC_MASK CFGCHIP1_CAP2SRC(0x1f) +#define CFGCHIP1_CAP2SRC_ECAP_PIN CFGCHIP1_CAP2SRC(0x0) +#define CFGCHIP1_CAP2SRC_MCASP0_TX CFGCHIP1_CAP2SRC(0x1) +#define CFGCHIP1_CAP2SRC_MCASP0_RX CFGCHIP1_CAP2SRC(0x2) +#define CFGCHIP1_CAP2SRC_EMAC_C0_RX_THRESHOLD CFGCHIP1_CAP2SRC(0x7) +#define CFGCHIP1_CAP2SRC_EMAC_C0_RX CFGCHIP1_CAP2SRC(0x8) +#define CFGCHIP1_CAP2SRC_EMAC_C0_TX CFGCHIP1_CAP2SRC(0x9) +#define CFGCHIP1_CAP2SRC_EMAC_C0_MISC CFGCHIP1_CAP2SRC(0xa) +#define CFGCHIP1_CAP2SRC_EMAC_C1_RX_THRESHOLD CFGCHIP1_CAP2SRC(0xb) +#define CFGCHIP1_CAP2SRC_EMAC_C1_RX CFGCHIP1_CAP2SRC(0xc) +#define CFGCHIP1_CAP2SRC_EMAC_C1_TX CFGCHIP1_CAP2SRC(0xd) +#define CFGCHIP1_CAP2SRC_EMAC_C1_MISC CFGCHIP1_CAP2SRC(0xe) +#define CFGCHIP1_CAP2SRC_EMAC_C2_RX_THRESHOLD CFGCHIP1_CAP2SRC(0xf) +#define CFGCHIP1_CAP2SRC_EMAC_C2_RX CFGCHIP1_CAP2SRC(0x10) +#define CFGCHIP1_CAP2SRC_EMAC_C2_TX CFGCHIP1_CAP2SRC(0x11) +#define CFGCHIP1_CAP2SRC_EMAC_C2_MISC CFGCHIP1_CAP2SRC(0x12) +#define CFGCHIP1_CAP1SRC(n) ((n) << 22) +#define CFGCHIP1_CAP1SRC_MASK CFGCHIP1_CAP1SRC(0x1f) +#define CFGCHIP1_CAP1SRC_ECAP_PIN CFGCHIP1_CAP1SRC(0x0) +#define CFGCHIP1_CAP1SRC_MCASP0_TX CFGCHIP1_CAP1SRC(0x1) +#define CFGCHIP1_CAP1SRC_MCASP0_RX CFGCHIP1_CAP1SRC(0x2) +#define CFGCHIP1_CAP1SRC_EMAC_C0_RX_THRESHOLD CFGCHIP1_CAP1SRC(0x7) +#define CFGCHIP1_CAP1SRC_EMAC_C0_RX CFGCHIP1_CAP1SRC(0x8) +#define CFGCHIP1_CAP1SRC_EMAC_C0_TX CFGCHIP1_CAP1SRC(0x9) +#define CFGCHIP1_CAP1SRC_EMAC_C0_MISC CFGCHIP1_CAP1SRC(0xa) +#define CFGCHIP1_CAP1SRC_EMAC_C1_RX_THRESHOLD CFGCHIP1_CAP1SRC(0xb) +#define CFGCHIP1_CAP1SRC_EMAC_C1_RX CFGCHIP1_CAP1SRC(0xc) +#define CFGCHIP1_CAP1SRC_EMAC_C1_TX CFGCHIP1_CAP1SRC(0xd) +#define CFGCHIP1_CAP1SRC_EMAC_C1_MISC CFGCHIP1_CAP1SRC(0xe) +#define CFGCHIP1_CAP1SRC_EMAC_C2_RX_THRESHOLD CFGCHIP1_CAP1SRC(0xf) +#define CFGCHIP1_CAP1SRC_EMAC_C2_RX CFGCHIP1_CAP1SRC(0x10) +#define CFGCHIP1_CAP1SRC_EMAC_C2_TX CFGCHIP1_CAP1SRC(0x11) +#define CFGCHIP1_CAP1SRC_EMAC_C2_MISC CFGCHIP1_CAP1SRC(0x12) +#define CFGCHIP1_CAP0SRC(n) ((n) << 17) +#define CFGCHIP1_CAP0SRC_MASK CFGCHIP1_CAP0SRC(0x1f) +#define CFGCHIP1_CAP0SRC_ECAP_PIN CFGCHIP1_CAP0SRC(0x0) +#define CFGCHIP1_CAP0SRC_MCASP0_TX CFGCHIP1_CAP0SRC(0x1) +#define CFGCHIP1_CAP0SRC_MCASP0_RX CFGCHIP1_CAP0SRC(0x2) +#define CFGCHIP1_CAP0SRC_EMAC_C0_RX_THRESHOLD CFGCHIP1_CAP0SRC(0x7) +#define CFGCHIP1_CAP0SRC_EMAC_C0_RX CFGCHIP1_CAP0SRC(0x8) +#define CFGCHIP1_CAP0SRC_EMAC_C0_TX CFGCHIP1_CAP0SRC(0x9) +#define CFGCHIP1_CAP0SRC_EMAC_C0_MISC CFGCHIP1_CAP0SRC(0xa) +#define CFGCHIP1_CAP0SRC_EMAC_C1_RX_THRESHOLD CFGCHIP1_CAP0SRC(0xb) +#define CFGCHIP1_CAP0SRC_EMAC_C1_RX CFGCHIP1_CAP0SRC(0xc) +#define CFGCHIP1_CAP0SRC_EMAC_C1_TX CFGCHIP1_CAP0SRC(0xd) +#define CFGCHIP1_CAP0SRC_EMAC_C1_MISC CFGCHIP1_CAP0SRC(0xe) +#define CFGCHIP1_CAP0SRC_EMAC_C2_RX_THRESHOLD CFGCHIP1_CAP0SRC(0xf) +#define CFGCHIP1_CAP0SRC_EMAC_C2_RX CFGCHIP1_CAP0SRC(0x10) +#define CFGCHIP1_CAP0SRC_EMAC_C2_TX CFGCHIP1_CAP0SRC(0x11) +#define CFGCHIP1_CAP0SRC_EMAC_C2_MISC CFGCHIP1_CAP0SRC(0x12) +#define CFGCHIP1_HPIBYTEAD BIT(16) +#define CFGCHIP1_HPIENA BIT(15) +#define CFGCHIP0_EDMA31TC0DBS(n) ((n) << 13) +#define CFGCHIP0_EDMA31TC0DBS_MASK CFGCHIP0_EDMA31TC0DBS(0x3) +#define CFGCHIP0_EDMA31TC0DBS_16 CFGCHIP0_EDMA31TC0DBS(0x0) +#define CFGCHIP0_EDMA31TC0DBS_32 CFGCHIP0_EDMA31TC0DBS(0x1) +#define CFGCHIP0_EDMA31TC0DBS_64 CFGCHIP0_EDMA31TC0DBS(0x2) +#define CFGCHIP1_TBCLKSYNC BIT(12) +#define CFGCHIP1_AMUTESEL0(n) ((n) << 0) +#define CFGCHIP1_AMUTESEL0_MASK CFGCHIP1_AMUTESEL0(0xf) +#define CFGCHIP1_AMUTESEL0_LOW CFGCHIP1_AMUTESEL0(0x0) +#define CFGCHIP1_AMUTESEL0_BANK_0 CFGCHIP1_AMUTESEL0(0x1) +#define CFGCHIP1_AMUTESEL0_BANK_1 CFGCHIP1_AMUTESEL0(0x2) +#define CFGCHIP1_AMUTESEL0_BANK_2 CFGCHIP1_AMUTESEL0(0x3) +#define CFGCHIP1_AMUTESEL0_BANK_3 CFGCHIP1_AMUTESEL0(0x4) +#define CFGCHIP1_AMUTESEL0_BANK_4 CFGCHIP1_AMUTESEL0(0x5) +#define CFGCHIP1_AMUTESEL0_BANK_5 CFGCHIP1_AMUTESEL0(0x6) +#define CFGCHIP1_AMUTESEL0_BANK_6 CFGCHIP1_AMUTESEL0(0x7) +#define CFGCHIP1_AMUTESEL0_BANK_7 CFGCHIP1_AMUTESEL0(0x8) + +/* CFGCHIP2 (USB PHY) register bits */ +#define CFGCHIP2_PHYCLKGD BIT(17) +#define CFGCHIP2_VBUSSENSE BIT(16) +#define CFGCHIP2_RESET BIT(15) +#define CFGCHIP2_OTGMODE(n) ((n) << 13) +#define CFGCHIP2_OTGMODE_MASK CFGCHIP2_OTGMODE(0x3) +#define CFGCHIP2_OTGMODE_NO_OVERRIDE CFGCHIP2_OTGMODE(0x0) +#define CFGCHIP2_OTGMODE_FORCE_HOST CFGCHIP2_OTGMODE(0x1) +#define CFGCHIP2_OTGMODE_FORCE_DEVICE CFGCHIP2_OTGMODE(0x2) +#define CFGCHIP2_OTGMODE_FORCE_HOST_VBUS_LOW CFGCHIP2_OTGMODE(0x3) +#define CFGCHIP2_USB1PHYCLKMUX BIT(12) +#define CFGCHIP2_USB2PHYCLKMUX BIT(11) +#define CFGCHIP2_PHYPWRDN BIT(10) +#define CFGCHIP2_OTGPWRDN BIT(9) +#define CFGCHIP2_DATPOL BIT(8) +#define CFGCHIP2_USB1SUSPENDM BIT(7) +#define CFGCHIP2_PHY_PLLON BIT(6) +#define CFGCHIP2_SESENDEN BIT(5) +#define CFGCHIP2_VBDTCTEN BIT(4) +#define CFGCHIP2_REFFREQ(n) ((n) << 0) +#define CFGCHIP2_REFFREQ_MASK CFGCHIP2_REFFREQ(0xf) +#define CFGCHIP2_REFFREQ_12MHZ CFGCHIP2_REFFREQ(0x1) +#define CFGCHIP2_REFFREQ_24MHZ CFGCHIP2_REFFREQ(0x2) +#define CFGCHIP2_REFFREQ_48MHZ CFGCHIP2_REFFREQ(0x3) +#define CFGCHIP2_REFFREQ_19_2MHZ CFGCHIP2_REFFREQ(0x4) +#define CFGCHIP2_REFFREQ_38_4MHZ CFGCHIP2_REFFREQ(0x5) +#define CFGCHIP2_REFFREQ_13MHZ CFGCHIP2_REFFREQ(0x6) +#define CFGCHIP2_REFFREQ_26MHZ CFGCHIP2_REFFREQ(0x7) +#define CFGCHIP2_REFFREQ_20MHZ CFGCHIP2_REFFREQ(0x8) +#define CFGCHIP2_REFFREQ_40MHZ CFGCHIP2_REFFREQ(0x9) + +/* CFGCHIP3 (EMAC/uPP/PLL1/ASYNC3/PRU/DIV4.5/EMIFA) register bits */ +#define CFGCHIP3_RMII_SEL BIT(8) +#define CFGCHIP3_UPP_TX_CLKSRC BIT(6) +#define CFGCHIP3_PLL1_MASTER_LOCK BIT(5) +#define CFGCHIP3_ASYNC3_CLKSRC BIT(4) +#define CFGCHIP3_PRUEVTSEL BIT(3) +#define CFGCHIP3_DIV45PENA BIT(2) +#define CFGCHIP3_EMA_CLKSRC BIT(1) + +/* CFGCHIP4 (McASP0 AMUNTEIN) register bits */ +#define CFGCHIP4_AMUTECLR0 BIT(0) + +#endif /* __LINUX_MFD_DA8XX_CFGCHIP_H */ -- cgit v1.2.3-71-gd317 From 952fcfd08c8109951622579d0ae7b9cd6cafd688 Mon Sep 17 00:00:00 2001 From: Sabrina Dubroca Date: Fri, 12 Aug 2016 16:10:33 +0200 Subject: net: remove type_check from dev_get_nest_level() The idea for type_check in dev_get_nest_level() was to count the number of nested devices of the same type (currently, only macvlan or vlan devices). This prevented the false positive lockdep warning on configurations such as: eth0 <--- macvlan0 <--- vlan0 <--- macvlan1 However, this doesn't prevent a warning on a configuration such as: eth0 <--- macvlan0 <--- vlan0 eth1 <--- vlan1 <--- macvlan1 In this case, all the locks end up with a nesting subclass of 1, so lockdep thinks that there is still a deadlock: - in the first case we have (macvlan_netdev_addr_lock_key, 1) and then take (vlan_netdev_xmit_lock_key, 1) - in the second case, we have (vlan_netdev_xmit_lock_key, 1) and then take (macvlan_netdev_addr_lock_key, 1) By removing the linktype check in dev_get_nest_level() and always incrementing the nesting depth, lockdep considers this configuration valid. Signed-off-by: Sabrina Dubroca Signed-off-by: David S. Miller --- drivers/net/macsec.c | 2 +- drivers/net/macvlan.c | 2 +- include/linux/netdevice.h | 3 +-- net/8021q/vlan.c | 2 +- net/core/dev.c | 10 +++------- 5 files changed, 7 insertions(+), 12 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/macsec.c b/drivers/net/macsec.c index 2043e8c97a81..351e701eb043 100644 --- a/drivers/net/macsec.c +++ b/drivers/net/macsec.c @@ -3201,7 +3201,7 @@ static int macsec_newlink(struct net *net, struct net_device *dev, dev_hold(real_dev); - macsec->nest_level = dev_get_nest_level(real_dev, netif_is_macsec) + 1; + macsec->nest_level = dev_get_nest_level(real_dev) + 1; netdev_lockdep_set_classes(dev); lockdep_set_class_and_subclass(&dev->addr_list_lock, &macsec_netdev_addr_lock_key, diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c index cd9b53834bf6..3234fcdea317 100644 --- a/drivers/net/macvlan.c +++ b/drivers/net/macvlan.c @@ -1315,7 +1315,7 @@ int macvlan_common_newlink(struct net *src_net, struct net_device *dev, vlan->dev = dev; vlan->port = port; vlan->set_features = MACVLAN_FEATURES; - vlan->nest_level = dev_get_nest_level(lowerdev, netif_is_macvlan) + 1; + vlan->nest_level = dev_get_nest_level(lowerdev) + 1; vlan->mode = MACVLAN_MODE_VEPA; if (data && data[IFLA_MACVLAN_MODE]) diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 076df5360ba5..3a788bf0affd 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3891,8 +3891,7 @@ void netdev_default_l2upper_neigh_destroy(struct net_device *dev, extern u8 netdev_rss_key[NETDEV_RSS_KEY_LEN] __read_mostly; void netdev_rss_key_fill(void *buffer, size_t len); -int dev_get_nest_level(struct net_device *dev, - bool (*type_check)(const struct net_device *dev)); +int dev_get_nest_level(struct net_device *dev); int skb_checksum_help(struct sk_buff *skb); struct sk_buff *__skb_gso_segment(struct sk_buff *skb, netdev_features_t features, bool tx_path); diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c index 82a116ba590e..8de138d3306b 100644 --- a/net/8021q/vlan.c +++ b/net/8021q/vlan.c @@ -169,7 +169,7 @@ int register_vlan_dev(struct net_device *dev) if (err < 0) goto out_uninit_mvrp; - vlan->nest_level = dev_get_nest_level(real_dev, is_vlan_dev) + 1; + vlan->nest_level = dev_get_nest_level(real_dev) + 1; err = register_netdevice(dev); if (err < 0) goto out_uninit_mvrp; diff --git a/net/core/dev.c b/net/core/dev.c index 4ce07dc25573..dd6ce598de89 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -6045,8 +6045,7 @@ void *netdev_lower_dev_get_private(struct net_device *dev, EXPORT_SYMBOL(netdev_lower_dev_get_private); -int dev_get_nest_level(struct net_device *dev, - bool (*type_check)(const struct net_device *dev)) +int dev_get_nest_level(struct net_device *dev) { struct net_device *lower = NULL; struct list_head *iter; @@ -6056,15 +6055,12 @@ int dev_get_nest_level(struct net_device *dev, ASSERT_RTNL(); netdev_for_each_lower_dev(dev, lower, iter) { - nest = dev_get_nest_level(lower, type_check); + nest = dev_get_nest_level(lower); if (max_nest < nest) max_nest = nest; } - if (type_check(dev)) - max_nest++; - - return max_nest; + return max_nest + 1; } EXPORT_SYMBOL(dev_get_nest_level); -- cgit v1.2.3-71-gd317 From b2f0c09664b72b2f8c581383a9337ac3092e42c8 Mon Sep 17 00:00:00 2001 From: Lars-Peter Clausen Date: Mon, 11 Jul 2016 13:50:01 +0200 Subject: iio: sw-trigger: Fix config group initialization Use the IS_ENABLED() helper macro to ensure that the configfs group is initialized either when configfs is built-in or when configfs is built as a module. Otherwise software trigger creation will result in undefined behaviour when configfs is built as a mdoule since the configfs group for the trigger is not properly initialized. Fixes: b662f809d410 ("iio: core: Introduce IIO software triggers") Signed-off-by: Lars-Peter Clausen Acked-by: Daniel Baluta Cc: Signed-off-by: Jonathan Cameron --- include/linux/iio/sw_trigger.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/iio/sw_trigger.h b/include/linux/iio/sw_trigger.h index 5198f8ed08a4..c97eab67558f 100644 --- a/include/linux/iio/sw_trigger.h +++ b/include/linux/iio/sw_trigger.h @@ -62,7 +62,7 @@ void iio_swt_group_init_type_name(struct iio_sw_trigger *t, const char *name, struct config_item_type *type) { -#ifdef CONFIG_CONFIGFS_FS +#if IS_ENABLED(CONFIG_CONFIGFS_FS) config_group_init_type_name(&t->group, name, type); #endif } -- cgit v1.2.3-71-gd317 From 7afafc8a44bf0ab841b17d450b02aedb3a138985 Mon Sep 17 00:00:00 2001 From: Adrian Hunter Date: Tue, 16 Aug 2016 10:59:35 +0300 Subject: block: Fix secure erase Commit 288dab8a35a0 ("block: add a separate operation type for secure erase") split REQ_OP_SECURE_ERASE from REQ_OP_DISCARD without considering all the places REQ_OP_DISCARD was being used to mean either. Fix those. Signed-off-by: Adrian Hunter Fixes: 288dab8a35a0 ("block: add a separate operation type for secure erase") Signed-off-by: Jens Axboe --- block/bio.c | 21 +++++++++++---------- block/blk-merge.c | 33 +++++++++++++++++++-------------- block/elevator.c | 2 +- drivers/mmc/card/block.c | 1 + drivers/mmc/card/queue.c | 3 ++- drivers/mmc/card/queue.h | 4 +++- include/linux/bio.h | 10 ++++++++-- include/linux/blkdev.h | 6 ++++-- kernel/trace/blktrace.c | 2 +- 9 files changed, 50 insertions(+), 32 deletions(-) (limited to 'include/linux') diff --git a/block/bio.c b/block/bio.c index f39477538fef..aa7354088008 100644 --- a/block/bio.c +++ b/block/bio.c @@ -667,18 +667,19 @@ struct bio *bio_clone_bioset(struct bio *bio_src, gfp_t gfp_mask, bio->bi_iter.bi_sector = bio_src->bi_iter.bi_sector; bio->bi_iter.bi_size = bio_src->bi_iter.bi_size; - if (bio_op(bio) == REQ_OP_DISCARD) - goto integrity_clone; - - if (bio_op(bio) == REQ_OP_WRITE_SAME) { + switch (bio_op(bio)) { + case REQ_OP_DISCARD: + case REQ_OP_SECURE_ERASE: + break; + case REQ_OP_WRITE_SAME: bio->bi_io_vec[bio->bi_vcnt++] = bio_src->bi_io_vec[0]; - goto integrity_clone; + break; + default: + bio_for_each_segment(bv, bio_src, iter) + bio->bi_io_vec[bio->bi_vcnt++] = bv; + break; } - bio_for_each_segment(bv, bio_src, iter) - bio->bi_io_vec[bio->bi_vcnt++] = bv; - -integrity_clone: if (bio_integrity(bio_src)) { int ret; @@ -1788,7 +1789,7 @@ struct bio *bio_split(struct bio *bio, int sectors, * Discards need a mutable bio_vec to accommodate the payload * required by the DSM TRIM and UNMAP commands. */ - if (bio_op(bio) == REQ_OP_DISCARD) + if (bio_op(bio) == REQ_OP_DISCARD || bio_op(bio) == REQ_OP_SECURE_ERASE) split = bio_clone_bioset(bio, gfp, bs); else split = bio_clone_fast(bio, gfp, bs); diff --git a/block/blk-merge.c b/block/blk-merge.c index 3eec75a9e91d..72627e3cf91e 100644 --- a/block/blk-merge.c +++ b/block/blk-merge.c @@ -172,12 +172,18 @@ void blk_queue_split(struct request_queue *q, struct bio **bio, struct bio *split, *res; unsigned nsegs; - if (bio_op(*bio) == REQ_OP_DISCARD) + switch (bio_op(*bio)) { + case REQ_OP_DISCARD: + case REQ_OP_SECURE_ERASE: split = blk_bio_discard_split(q, *bio, bs, &nsegs); - else if (bio_op(*bio) == REQ_OP_WRITE_SAME) + break; + case REQ_OP_WRITE_SAME: split = blk_bio_write_same_split(q, *bio, bs, &nsegs); - else + break; + default: split = blk_bio_segment_split(q, *bio, q->bio_split, &nsegs); + break; + } /* physical segments can be figured out during splitting */ res = split ? split : *bio; @@ -213,7 +219,7 @@ static unsigned int __blk_recalc_rq_segments(struct request_queue *q, * This should probably be returning 0, but blk_add_request_payload() * (Christoph!!!!) */ - if (bio_op(bio) == REQ_OP_DISCARD) + if (bio_op(bio) == REQ_OP_DISCARD || bio_op(bio) == REQ_OP_SECURE_ERASE) return 1; if (bio_op(bio) == REQ_OP_WRITE_SAME) @@ -385,7 +391,9 @@ static int __blk_bios_map_sg(struct request_queue *q, struct bio *bio, nsegs = 0; cluster = blk_queue_cluster(q); - if (bio_op(bio) == REQ_OP_DISCARD) { + switch (bio_op(bio)) { + case REQ_OP_DISCARD: + case REQ_OP_SECURE_ERASE: /* * This is a hack - drivers should be neither modifying the * biovec, nor relying on bi_vcnt - but because of @@ -393,19 +401,16 @@ static int __blk_bios_map_sg(struct request_queue *q, struct bio *bio, * a payload we need to set up here (thank you Christoph) and * bi_vcnt is really the only way of telling if we need to. */ - - if (bio->bi_vcnt) - goto single_segment; - - return 0; - } - - if (bio_op(bio) == REQ_OP_WRITE_SAME) { -single_segment: + if (!bio->bi_vcnt) + return 0; + /* Fall through */ + case REQ_OP_WRITE_SAME: *sg = sglist; bvec = bio_iovec(bio); sg_set_page(*sg, bvec.bv_page, bvec.bv_len, bvec.bv_offset); return 1; + default: + break; } for_each_bio(bio) diff --git a/block/elevator.c b/block/elevator.c index 7096c22041e7..f7d973a56fd7 100644 --- a/block/elevator.c +++ b/block/elevator.c @@ -366,7 +366,7 @@ void elv_dispatch_sort(struct request_queue *q, struct request *rq) list_for_each_prev(entry, &q->queue_head) { struct request *pos = list_entry_rq(entry); - if ((req_op(rq) == REQ_OP_DISCARD) != (req_op(pos) == REQ_OP_DISCARD)) + if (req_op(rq) != req_op(pos)) break; if (rq_data_dir(rq) != rq_data_dir(pos)) break; diff --git a/drivers/mmc/card/block.c b/drivers/mmc/card/block.c index 48a5dd740f3b..82503e6f04b3 100644 --- a/drivers/mmc/card/block.c +++ b/drivers/mmc/card/block.c @@ -1726,6 +1726,7 @@ static u8 mmc_blk_prep_packed_list(struct mmc_queue *mq, struct request *req) break; if (req_op(next) == REQ_OP_DISCARD || + req_op(next) == REQ_OP_SECURE_ERASE || req_op(next) == REQ_OP_FLUSH) break; diff --git a/drivers/mmc/card/queue.c b/drivers/mmc/card/queue.c index bf14642a576a..29578e98603d 100644 --- a/drivers/mmc/card/queue.c +++ b/drivers/mmc/card/queue.c @@ -33,7 +33,8 @@ static int mmc_prep_request(struct request_queue *q, struct request *req) /* * We only like normal block requests and discards. */ - if (req->cmd_type != REQ_TYPE_FS && req_op(req) != REQ_OP_DISCARD) { + if (req->cmd_type != REQ_TYPE_FS && req_op(req) != REQ_OP_DISCARD && + req_op(req) != REQ_OP_SECURE_ERASE) { blk_dump_rq_flags(req, "MMC bad request"); return BLKPREP_KILL; } diff --git a/drivers/mmc/card/queue.h b/drivers/mmc/card/queue.h index d62531124d54..fee5e1271465 100644 --- a/drivers/mmc/card/queue.h +++ b/drivers/mmc/card/queue.h @@ -4,7 +4,9 @@ static inline bool mmc_req_is_special(struct request *req) { return req && - (req_op(req) == REQ_OP_FLUSH || req_op(req) == REQ_OP_DISCARD); + (req_op(req) == REQ_OP_FLUSH || + req_op(req) == REQ_OP_DISCARD || + req_op(req) == REQ_OP_SECURE_ERASE); } struct request; diff --git a/include/linux/bio.h b/include/linux/bio.h index 59ffaa68b11b..23ddf4b46a9b 100644 --- a/include/linux/bio.h +++ b/include/linux/bio.h @@ -71,7 +71,8 @@ static inline bool bio_has_data(struct bio *bio) { if (bio && bio->bi_iter.bi_size && - bio_op(bio) != REQ_OP_DISCARD) + bio_op(bio) != REQ_OP_DISCARD && + bio_op(bio) != REQ_OP_SECURE_ERASE) return true; return false; @@ -79,7 +80,9 @@ static inline bool bio_has_data(struct bio *bio) static inline bool bio_no_advance_iter(struct bio *bio) { - return bio_op(bio) == REQ_OP_DISCARD || bio_op(bio) == REQ_OP_WRITE_SAME; + return bio_op(bio) == REQ_OP_DISCARD || + bio_op(bio) == REQ_OP_SECURE_ERASE || + bio_op(bio) == REQ_OP_WRITE_SAME; } static inline bool bio_is_rw(struct bio *bio) @@ -199,6 +202,9 @@ static inline unsigned bio_segments(struct bio *bio) if (bio_op(bio) == REQ_OP_DISCARD) return 1; + if (bio_op(bio) == REQ_OP_SECURE_ERASE) + return 1; + if (bio_op(bio) == REQ_OP_WRITE_SAME) return 1; diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 2c210b6a7bcf..e79055c8b577 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -882,7 +882,7 @@ static inline unsigned int blk_rq_cur_sectors(const struct request *rq) static inline unsigned int blk_queue_get_max_sectors(struct request_queue *q, int op) { - if (unlikely(op == REQ_OP_DISCARD)) + if (unlikely(op == REQ_OP_DISCARD || op == REQ_OP_SECURE_ERASE)) return min(q->limits.max_discard_sectors, UINT_MAX >> 9); if (unlikely(op == REQ_OP_WRITE_SAME)) @@ -913,7 +913,9 @@ static inline unsigned int blk_rq_get_max_sectors(struct request *rq, if (unlikely(rq->cmd_type != REQ_TYPE_FS)) return q->limits.max_hw_sectors; - if (!q->limits.chunk_sectors || (req_op(rq) == REQ_OP_DISCARD)) + if (!q->limits.chunk_sectors || + req_op(rq) == REQ_OP_DISCARD || + req_op(rq) == REQ_OP_SECURE_ERASE) return blk_queue_get_max_sectors(q, req_op(rq)); return min(blk_max_size_offset(q, offset), diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c index 7598e6ca817a..dbafc5df03f3 100644 --- a/kernel/trace/blktrace.c +++ b/kernel/trace/blktrace.c @@ -223,7 +223,7 @@ static void __blk_add_trace(struct blk_trace *bt, sector_t sector, int bytes, what |= MASK_TC_BIT(op_flags, META); what |= MASK_TC_BIT(op_flags, PREFLUSH); what |= MASK_TC_BIT(op_flags, FUA); - if (op == REQ_OP_DISCARD) + if (op == REQ_OP_DISCARD || op == REQ_OP_SECURE_ERASE) what |= BLK_TC_ACT(BLK_TC_DISCARD); if (op == REQ_OP_FLUSH) what |= BLK_TC_ACT(BLK_TC_FLUSH); -- cgit v1.2.3-71-gd317 From 4fe0d154880bb6eb833cbe84fa6f385f400f0b9c Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Thu, 11 Aug 2016 07:11:04 -0700 Subject: PCI: Use positive flags in pci_alloc_irq_vectors() Instead of passing negative flags like PCI_IRQ_NOMSI to prevent use of certain interrupt types, pass positive flags like PCI_IRQ_LEGACY, PCI_IRQ_MSI, etc., to specify the acceptable interrupt types. This is based on a number of pending driver conversions that just happend to be a whole more obvious to read this way, and given that we have no users in the tree yet it can still easily be done. I've also added a PCI_IRQ_ALL_TYPES catchall to keep the case of accepting all interrupt types very simple. [bhelgaas: changelog, fix PCI_IRQ_AFFINITY doc typo, remove mention of PCI_IRQ_NOLEGACY] Signed-off-by: Christoph Hellwig Signed-off-by: Bjorn Helgaas Reviewed-by: Alexander Gordeev --- Documentation/PCI/MSI-HOWTO.txt | 24 ++++++++++-------------- drivers/pci/msi.c | 15 +++++++-------- include/linux/pci.h | 10 ++++++---- 3 files changed, 23 insertions(+), 26 deletions(-) (limited to 'include/linux') diff --git a/Documentation/PCI/MSI-HOWTO.txt b/Documentation/PCI/MSI-HOWTO.txt index c55df2911136..cd9c9f6a7cd9 100644 --- a/Documentation/PCI/MSI-HOWTO.txt +++ b/Documentation/PCI/MSI-HOWTO.txt @@ -94,14 +94,11 @@ has a requirements for a minimum number of vectors the driver can pass a min_vecs argument set to this limit, and the PCI core will return -ENOSPC if it can't meet the minimum number of vectors. -The flags argument should normally be set to 0, but can be used to pass the -PCI_IRQ_NOMSI and PCI_IRQ_NOMSIX flag in case a device claims to support -MSI or MSI-X, but the support is broken, or to pass PCI_IRQ_NOLEGACY in -case the device does not support legacy interrupt lines. - -By default this function will spread the interrupts around the available -CPUs, but this feature can be disabled by passing the PCI_IRQ_NOAFFINITY -flag. +The flags argument is used to specify which type of interrupt can be used +by the device and the driver (PCI_IRQ_LEGACY, PCI_IRQ_MSI, PCI_IRQ_MSIX). +A convenient short-hand (PCI_IRQ_ALL_TYPES) is also available to ask for +any possible kind of interrupt. If the PCI_IRQ_AFFINITY flag is set, +pci_alloc_irq_vectors() will spread the interrupts around the available CPUs. To get the Linux IRQ numbers passed to request_irq() and free_irq() and the vectors, use the following function: @@ -131,7 +128,7 @@ larger than the number supported by the device it will automatically be capped to the supported limit, so there is no need to query the number of vectors supported beforehand: - nvec = pci_alloc_irq_vectors(pdev, 1, nvec, 0); + nvec = pci_alloc_irq_vectors(pdev, 1, nvec, PCI_IRQ_ALL_TYPES) if (nvec < 0) goto out_err; @@ -140,7 +137,7 @@ interrupts it can request a particular number of interrupts by passing that number to pci_alloc_irq_vectors() function as both 'min_vecs' and 'max_vecs' parameters: - ret = pci_alloc_irq_vectors(pdev, nvec, nvec, 0); + ret = pci_alloc_irq_vectors(pdev, nvec, nvec, PCI_IRQ_ALL_TYPES); if (ret < 0) goto out_err; @@ -148,15 +145,14 @@ The most notorious example of the request type described above is enabling the single MSI mode for a device. It could be done by passing two 1s as 'min_vecs' and 'max_vecs': - ret = pci_alloc_irq_vectors(pdev, 1, 1, 0); + ret = pci_alloc_irq_vectors(pdev, 1, 1, PCI_IRQ_ALL_TYPES); if (ret < 0) goto out_err; Some devices might not support using legacy line interrupts, in which case -the PCI_IRQ_NOLEGACY flag can be used to fail the request if the platform -can't provide MSI or MSI-X interrupts: +the driver can specify that only MSI or MSI-X is acceptable: - nvec = pci_alloc_irq_vectors(pdev, 1, nvec, PCI_IRQ_NOLEGACY); + nvec = pci_alloc_irq_vectors(pdev, 1, nvec, PCI_IRQ_MSI | PCI_IRQ_MSIX); if (nvec < 0) goto out_err; diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c index a02981efdad5..9233e7f62f47 100644 --- a/drivers/pci/msi.c +++ b/drivers/pci/msi.c @@ -1069,7 +1069,7 @@ static int __pci_enable_msi_range(struct pci_dev *dev, int minvec, int maxvec, nvec = maxvec; for (;;) { - if (!(flags & PCI_IRQ_NOAFFINITY)) { + if (flags & PCI_IRQ_AFFINITY) { dev->irq_affinity = irq_create_affinity_mask(&nvec); if (nvec < minvec) return -ENOSPC; @@ -1105,7 +1105,7 @@ static int __pci_enable_msi_range(struct pci_dev *dev, int minvec, int maxvec, **/ int pci_enable_msi_range(struct pci_dev *dev, int minvec, int maxvec) { - return __pci_enable_msi_range(dev, minvec, maxvec, PCI_IRQ_NOAFFINITY); + return __pci_enable_msi_range(dev, minvec, maxvec, 0); } EXPORT_SYMBOL(pci_enable_msi_range); @@ -1120,7 +1120,7 @@ static int __pci_enable_msix_range(struct pci_dev *dev, return -ERANGE; for (;;) { - if (!(flags & PCI_IRQ_NOAFFINITY)) { + if (flags & PCI_IRQ_AFFINITY) { dev->irq_affinity = irq_create_affinity_mask(&nvec); if (nvec < minvec) return -ENOSPC; @@ -1160,8 +1160,7 @@ static int __pci_enable_msix_range(struct pci_dev *dev, int pci_enable_msix_range(struct pci_dev *dev, struct msix_entry *entries, int minvec, int maxvec) { - return __pci_enable_msix_range(dev, entries, minvec, maxvec, - PCI_IRQ_NOAFFINITY); + return __pci_enable_msix_range(dev, entries, minvec, maxvec, 0); } EXPORT_SYMBOL(pci_enable_msix_range); @@ -1187,21 +1186,21 @@ int pci_alloc_irq_vectors(struct pci_dev *dev, unsigned int min_vecs, { int vecs = -ENOSPC; - if (!(flags & PCI_IRQ_NOMSIX)) { + if (flags & PCI_IRQ_MSIX) { vecs = __pci_enable_msix_range(dev, NULL, min_vecs, max_vecs, flags); if (vecs > 0) return vecs; } - if (!(flags & PCI_IRQ_NOMSI)) { + if (flags & PCI_IRQ_MSI) { vecs = __pci_enable_msi_range(dev, min_vecs, max_vecs, flags); if (vecs > 0) return vecs; } /* use legacy irq if allowed */ - if (!(flags & PCI_IRQ_NOLEGACY) && min_vecs == 1) + if ((flags & PCI_IRQ_LEGACY) && min_vecs == 1) return 1; return vecs; } diff --git a/include/linux/pci.h b/include/linux/pci.h index 2599a980340f..fbc1fa625c3e 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1251,10 +1251,12 @@ resource_size_t pcibios_iov_resource_alignment(struct pci_dev *dev, int resno); int pci_set_vga_state(struct pci_dev *pdev, bool decode, unsigned int command_bits, u32 flags); -#define PCI_IRQ_NOLEGACY (1 << 0) /* don't use legacy interrupts */ -#define PCI_IRQ_NOMSI (1 << 1) /* don't use MSI interrupts */ -#define PCI_IRQ_NOMSIX (1 << 2) /* don't use MSI-X interrupts */ -#define PCI_IRQ_NOAFFINITY (1 << 3) /* don't auto-assign affinity */ +#define PCI_IRQ_LEGACY (1 << 0) /* allow legacy interrupts */ +#define PCI_IRQ_MSI (1 << 1) /* allow MSI interrupts */ +#define PCI_IRQ_MSIX (1 << 2) /* allow MSI-X interrupts */ +#define PCI_IRQ_AFFINITY (1 << 3) /* auto-assign affinity */ +#define PCI_IRQ_ALL_TYPES \ + (PCI_IRQ_LEGACY | PCI_IRQ_MSI | PCI_IRQ_MSIX) /* kmem_cache style wrapper around pci_alloc_consistent() */ -- cgit v1.2.3-71-gd317 From aca300183ed4f723837f6619facff0890c46d313 Mon Sep 17 00:00:00 2001 From: Liping Zhang Date: Sat, 13 Aug 2016 23:13:02 +0800 Subject: netfilter: nfnetlink_acct: report overquota to the right netns We should report the over quota message to the right net namespace instead of the init netns. Signed-off-by: Liping Zhang Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter/nfnetlink_acct.h | 4 ++-- net/netfilter/nfnetlink_acct.c | 9 +++++---- net/netfilter/xt_nfacct.c | 2 +- 3 files changed, 8 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter/nfnetlink_acct.h b/include/linux/netfilter/nfnetlink_acct.h index 80ca889b164e..664da0048625 100644 --- a/include/linux/netfilter/nfnetlink_acct.h +++ b/include/linux/netfilter/nfnetlink_acct.h @@ -15,6 +15,6 @@ struct nf_acct; struct nf_acct *nfnl_acct_find_get(struct net *net, const char *filter_name); void nfnl_acct_put(struct nf_acct *acct); void nfnl_acct_update(const struct sk_buff *skb, struct nf_acct *nfacct); -extern int nfnl_acct_overquota(const struct sk_buff *skb, - struct nf_acct *nfacct); +int nfnl_acct_overquota(struct net *net, const struct sk_buff *skb, + struct nf_acct *nfacct); #endif /* _NFNL_ACCT_H */ diff --git a/net/netfilter/nfnetlink_acct.c b/net/netfilter/nfnetlink_acct.c index 1b4de4bd6958..796605b76d6b 100644 --- a/net/netfilter/nfnetlink_acct.c +++ b/net/netfilter/nfnetlink_acct.c @@ -443,7 +443,7 @@ void nfnl_acct_update(const struct sk_buff *skb, struct nf_acct *nfacct) } EXPORT_SYMBOL_GPL(nfnl_acct_update); -static void nfnl_overquota_report(struct nf_acct *nfacct) +static void nfnl_overquota_report(struct net *net, struct nf_acct *nfacct) { int ret; struct sk_buff *skb; @@ -458,11 +458,12 @@ static void nfnl_overquota_report(struct nf_acct *nfacct) kfree_skb(skb); return; } - netlink_broadcast(init_net.nfnl, skb, 0, NFNLGRP_ACCT_QUOTA, + netlink_broadcast(net->nfnl, skb, 0, NFNLGRP_ACCT_QUOTA, GFP_ATOMIC); } -int nfnl_acct_overquota(const struct sk_buff *skb, struct nf_acct *nfacct) +int nfnl_acct_overquota(struct net *net, const struct sk_buff *skb, + struct nf_acct *nfacct) { u64 now; u64 *quota; @@ -480,7 +481,7 @@ int nfnl_acct_overquota(const struct sk_buff *skb, struct nf_acct *nfacct) if (now >= *quota && !test_and_set_bit(NFACCT_OVERQUOTA_BIT, &nfacct->flags)) { - nfnl_overquota_report(nfacct); + nfnl_overquota_report(net, nfacct); } return ret; diff --git a/net/netfilter/xt_nfacct.c b/net/netfilter/xt_nfacct.c index 3048a7e3a90a..cf327593852a 100644 --- a/net/netfilter/xt_nfacct.c +++ b/net/netfilter/xt_nfacct.c @@ -26,7 +26,7 @@ static bool nfacct_mt(const struct sk_buff *skb, struct xt_action_param *par) nfnl_acct_update(skb, info->nfacct); - overquota = nfnl_acct_overquota(skb, info->nfacct); + overquota = nfnl_acct_overquota(par->net, skb, info->nfacct); return overquota == NFACCT_UNDERQUOTA ? false : true; } -- cgit v1.2.3-71-gd317 From 112dc0c8069e5554e0ad29c58228f1e6ca49e13d Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Thu, 11 Aug 2016 11:50:22 +0200 Subject: locking/barriers: Suppress sparse warnings in lockless_dereference() After Peter's commit: 331b6d8c7afc ("locking/barriers: Validate lockless_dereference() is used on a pointer type") ... we get a lot of sparse warnings (one for every rcu_dereference, and more) since the expression here is assigning to the wrong address space. Instead of validating that 'p' is a pointer this way, instead make it fail compilation when it's not by using sizeof(*(p)). This will not cause any sparse warnings (tested, likely since the address space is irrelevant for sizeof), and will fail compilation when 'p' isn't a pointer type. Tested-by: Paul E. McKenney Signed-off-by: Johannes Berg Signed-off-by: Peter Zijlstra (Intel) Cc: Andrew Morton Cc: Chris Wilson Cc: Daniel Vetter Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Fixes: 331b6d8c7afc ("locking/barriers: Validate lockless_dereference() is used on a pointer type") Link: http://lkml.kernel.org/r/1470909022-687-2-git-send-email-johannes@sipsolutions.net Signed-off-by: Ingo Molnar --- include/linux/compiler.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 1bb954842725..436aa4e42221 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -527,13 +527,13 @@ static __always_inline void __write_once_size(volatile void *p, void *res, int s * object's lifetime is managed by something other than RCU. That * "something other" might be reference counting or simple immortality. * - * The seemingly unused void * variable is to validate @p is indeed a pointer - * type. All pointer types silently cast to void *. + * The seemingly unused size_t variable is to validate @p is indeed a pointer + * type by making sure it can be dereferenced. */ #define lockless_dereference(p) \ ({ \ typeof(p) _________p1 = READ_ONCE(p); \ - __maybe_unused const void * const _________p2 = _________p1; \ + size_t __maybe_unused __size_of_ptr = sizeof(*(p)); \ smp_read_barrier_depends(); /* Dependency order vs. p above. */ \ (_________p1); \ }) -- cgit v1.2.3-71-gd317 From 7a665d2f60b457c0d77b3e4f01e21c55ffc57069 Mon Sep 17 00:00:00 2001 From: Daniel Verkamp Date: Tue, 28 Jun 2016 11:20:23 -0700 Subject: nvme-fabrics: change NQN UUID to big-endian format NVM Express 1.2.1 section 7.9, NVMe Qualified Names, specifies that the UUID format of NQN uses a UUID based on RFC 4122. RFC 4122 specifies that the UUID is encoded in big-endian byte order. Switch the NVMe over Fabrics host ID field from little-endian UUID to big-endian UUID to match the specification. Signed-off-by: Daniel Verkamp Reviewed-by: Jay Freyensee Signed-off-by: Sagi Grimberg --- drivers/nvme/host/fabrics.c | 10 +++++----- drivers/nvme/host/fabrics.h | 2 +- include/linux/nvme.h | 2 +- 3 files changed, 7 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/drivers/nvme/host/fabrics.c b/drivers/nvme/host/fabrics.c index 020302c6ea57..be0b1067c9fa 100644 --- a/drivers/nvme/host/fabrics.c +++ b/drivers/nvme/host/fabrics.c @@ -56,7 +56,7 @@ static struct nvmf_host *nvmf_host_add(const char *hostnqn) kref_init(&host->ref); memcpy(host->nqn, hostnqn, NVMF_NQN_SIZE); - uuid_le_gen(&host->id); + uuid_be_gen(&host->id); list_add_tail(&host->list, &nvmf_hosts); out_unlock: @@ -73,9 +73,9 @@ static struct nvmf_host *nvmf_host_default(void) return NULL; kref_init(&host->ref); - uuid_le_gen(&host->id); + uuid_be_gen(&host->id); snprintf(host->nqn, NVMF_NQN_SIZE, - "nqn.2014-08.org.nvmexpress:NVMf:uuid:%pUl", &host->id); + "nqn.2014-08.org.nvmexpress:NVMf:uuid:%pUb", &host->id); mutex_lock(&nvmf_hosts_mutex); list_add_tail(&host->list, &nvmf_hosts); @@ -382,7 +382,7 @@ int nvmf_connect_admin_queue(struct nvme_ctrl *ctrl) if (!data) return -ENOMEM; - memcpy(&data->hostid, &ctrl->opts->host->id, sizeof(uuid_le)); + memcpy(&data->hostid, &ctrl->opts->host->id, sizeof(uuid_be)); data->cntlid = cpu_to_le16(0xffff); strncpy(data->subsysnqn, ctrl->opts->subsysnqn, NVMF_NQN_SIZE); strncpy(data->hostnqn, ctrl->opts->host->nqn, NVMF_NQN_SIZE); @@ -441,7 +441,7 @@ int nvmf_connect_io_queue(struct nvme_ctrl *ctrl, u16 qid) if (!data) return -ENOMEM; - memcpy(&data->hostid, &ctrl->opts->host->id, sizeof(uuid_le)); + memcpy(&data->hostid, &ctrl->opts->host->id, sizeof(uuid_be)); data->cntlid = cpu_to_le16(ctrl->cntlid); strncpy(data->subsysnqn, ctrl->opts->subsysnqn, NVMF_NQN_SIZE); strncpy(data->hostnqn, ctrl->opts->host->nqn, NVMF_NQN_SIZE); diff --git a/drivers/nvme/host/fabrics.h b/drivers/nvme/host/fabrics.h index 89df52c8be97..46e460aee52d 100644 --- a/drivers/nvme/host/fabrics.h +++ b/drivers/nvme/host/fabrics.h @@ -34,7 +34,7 @@ struct nvmf_host { struct kref ref; struct list_head list; char nqn[NVMF_NQN_SIZE]; - uuid_le id; + uuid_be id; }; /** diff --git a/include/linux/nvme.h b/include/linux/nvme.h index d8b37bab2887..7676557ce357 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -794,7 +794,7 @@ struct nvmf_connect_command { }; struct nvmf_connect_data { - uuid_le hostid; + uuid_be hostid; __le16 cntlid; char resv4[238]; char subsysnqn[NVMF_NQN_FIELD_LEN]; -- cgit v1.2.3-71-gd317 From c0678b2d6648ab65b68703044709e367799ba9f9 Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Mon, 15 Aug 2016 15:52:23 -0700 Subject: include/linux: fix excess fence.h kernel-doc notation Fix excess fields in kernel-doc notation in after some struct fields were removed. Fixes these kernel-doc warnings: ..//include/linux/fence.h:85: warning: Excess struct/union/enum/typedef member 'child_list' description in 'fence' ..//include/linux/fence.h:85: warning: Excess struct/union/enum/typedef member 'active_list' description in 'fence' Fixes: 0431b9065f28 ("staging/android: bring struct sync_pt back") Cc: Daniel Vetter Cc: Sumit Semwal Cc: Luis de Bethencourt Signed-off-by: Randy Dunlap Reviewed-by: Gustavo Padovan Signed-off-by: Greg Kroah-Hartman --- include/linux/fence.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/fence.h b/include/linux/fence.h index 8cc719a63728..2ac6fa5f4712 100644 --- a/include/linux/fence.h +++ b/include/linux/fence.h @@ -49,8 +49,6 @@ struct fence_cb; * @timestamp: Timestamp when the fence was signaled. * @status: Optional, only valid if < 0, must be set before calling * fence_signal, indicates that the fence has completed with an error. - * @child_list: list of children fences - * @active_list: list of active fences * * the flags member must be manipulated and read using the appropriate * atomic ops (bit_*), so taking the spinlock will not be needed most -- cgit v1.2.3-71-gd317 From 7175cce1c3f1d8c8840d2004f78f96a3904249b5 Mon Sep 17 00:00:00 2001 From: Vignesh R Date: Wed, 17 Aug 2016 17:43:01 +0530 Subject: iio: adc: ti_am335x_adc: Increase timeout value waiting for ADC sample Now that open delay and sample delay for each channel is configurable via DT, the default IDLE_TIMEOUT value is not enough as this is calculated based on hardcoded macros. This results in driver returning EBUSY sometimes. Fix this by increasing the timeout value based on maximum value possible to open delay and sample delays for each channel. Fixes: 5dc11e810676e ("iio: adc: ti_am335x_adc: make sample delay, open delay, averaging DT parameters") Signed-off-by: Vignesh R Acked-by: Lee Jones Cc: Signed-off-by: Jonathan Cameron --- drivers/iio/adc/ti_am335x_adc.c | 2 +- include/linux/mfd/ti_am335x_tscadc.h | 8 ++++---- 2 files changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/drivers/iio/adc/ti_am335x_adc.c b/drivers/iio/adc/ti_am335x_adc.c index bed9977a1863..c3cfacca2541 100644 --- a/drivers/iio/adc/ti_am335x_adc.c +++ b/drivers/iio/adc/ti_am335x_adc.c @@ -381,7 +381,7 @@ static int tiadc_read_raw(struct iio_dev *indio_dev, am335x_tsc_se_set_once(adc_dev->mfd_tscadc, step_en); - timeout = jiffies + usecs_to_jiffies + timeout = jiffies + msecs_to_jiffies (IDLE_TIMEOUT * adc_dev->channels); /* Wait for Fifo threshold interrupt */ while (1) { diff --git a/include/linux/mfd/ti_am335x_tscadc.h b/include/linux/mfd/ti_am335x_tscadc.h index 2567a87872b0..7f55b8b41032 100644 --- a/include/linux/mfd/ti_am335x_tscadc.h +++ b/include/linux/mfd/ti_am335x_tscadc.h @@ -138,16 +138,16 @@ /* * time in us for processing a single channel, calculated as follows: * - * num cycles = open delay + (sample delay + conv time) * averaging + * max num cycles = open delay + (sample delay + conv time) * averaging * - * num cycles: 152 + (1 + 13) * 16 = 376 + * max num cycles: 262143 + (255 + 13) * 16 = 266431 * * clock frequency: 26MHz / 8 = 3.25MHz * clock period: 1 / 3.25MHz = 308ns * - * processing time: 376 * 308ns = 116us + * max processing time: 266431 * 308ns = 83ms(approx) */ -#define IDLE_TIMEOUT 116 /* microsec */ +#define IDLE_TIMEOUT 83 /* milliseconds */ #define TSCADC_CELLS 2 -- cgit v1.2.3-71-gd317 From 87904c3e82319cf2bad8d656d79c5030dab9490e Mon Sep 17 00:00:00 2001 From: Thierry Reding Date: Fri, 12 Aug 2016 16:00:53 +0200 Subject: drm/tegra: dsi: Enhance runtime power management The MIPI DSI output on Tegra SoCs requires some external logic to calibrate the MIPI pads before a video signal can be transmitted. This MIPI calibration logic requires to be powered on while the MIPI pads are being used, which is currently done as part of the DSI driver's probe implementation. This is suboptimal because it will leave the MIPI calibration logic powered up even if the DSI output is never used. On Tegra114 and earlier this behaviour also causes the driver to hang while trying to power up the MIPI calibration logic because the power partition that contains the MIPI calibration logic will be powered on by the display controller at output pipeline configuration time. Thus the power up sequence for the MIPI calibration logic happens before it's power partition is guaranteed to be enabled. Fix this by splitting up the API into a request/free pair of functions that manage the runtime dependency between the DSI and the calibration modules (no registers are accessed) and a set of enable, calibrate and disable functions that program the MIPI calibration logic at points in time where the power partition is really enabled. While at it, make sure that the runtime power management also works in ganged mode, which is currently also broken. Reported-by: Jonathan Hunter Tested-by: Jonathan Hunter Signed-off-by: Thierry Reding --- drivers/gpu/drm/tegra/dsi.c | 43 ++++++++++++++++++++++++++----- drivers/gpu/host1x/mipi.c | 63 ++++++++++++++++++++++----------------------- include/linux/host1x.h | 2 ++ 3 files changed, 69 insertions(+), 39 deletions(-) (limited to 'include/linux') diff --git a/drivers/gpu/drm/tegra/dsi.c b/drivers/gpu/drm/tegra/dsi.c index 3d228ad90e0f..3dea1216bafd 100644 --- a/drivers/gpu/drm/tegra/dsi.c +++ b/drivers/gpu/drm/tegra/dsi.c @@ -840,6 +840,21 @@ static const struct drm_encoder_funcs tegra_dsi_encoder_funcs = { .destroy = tegra_output_encoder_destroy, }; +static void tegra_dsi_unprepare(struct tegra_dsi *dsi) +{ + int err; + + if (dsi->slave) + tegra_dsi_unprepare(dsi->slave); + + err = tegra_mipi_disable(dsi->mipi); + if (err < 0) + dev_err(dsi->dev, "failed to disable MIPI calibration: %d\n", + err); + + pm_runtime_put(dsi->dev); +} + static void tegra_dsi_encoder_disable(struct drm_encoder *encoder) { struct tegra_output *output = encoder_to_output(encoder); @@ -876,7 +891,26 @@ static void tegra_dsi_encoder_disable(struct drm_encoder *encoder) tegra_dsi_disable(dsi); - pm_runtime_put(dsi->dev); + tegra_dsi_unprepare(dsi); +} + +static void tegra_dsi_prepare(struct tegra_dsi *dsi) +{ + int err; + + pm_runtime_get_sync(dsi->dev); + + err = tegra_mipi_enable(dsi->mipi); + if (err < 0) + dev_err(dsi->dev, "failed to enable MIPI calibration: %d\n", + err); + + err = tegra_dsi_pad_calibrate(dsi); + if (err < 0) + dev_err(dsi->dev, "MIPI calibration failed: %d\n", err); + + if (dsi->slave) + tegra_dsi_prepare(dsi->slave); } static void tegra_dsi_encoder_enable(struct drm_encoder *encoder) @@ -887,13 +921,8 @@ static void tegra_dsi_encoder_enable(struct drm_encoder *encoder) struct tegra_dsi *dsi = to_dsi(output); struct tegra_dsi_state *state; u32 value; - int err; - - pm_runtime_get_sync(dsi->dev); - err = tegra_dsi_pad_calibrate(dsi); - if (err < 0) - dev_err(dsi->dev, "MIPI calibration failed: %d\n", err); + tegra_dsi_prepare(dsi); state = tegra_dsi_get_state(dsi); diff --git a/drivers/gpu/host1x/mipi.c b/drivers/gpu/host1x/mipi.c index 52a6fd224127..e00809d996a2 100644 --- a/drivers/gpu/host1x/mipi.c +++ b/drivers/gpu/host1x/mipi.c @@ -242,20 +242,6 @@ struct tegra_mipi_device *tegra_mipi_request(struct device *device) dev->pads = args.args[0]; dev->device = device; - mutex_lock(&dev->mipi->lock); - - if (dev->mipi->usage_count++ == 0) { - err = tegra_mipi_power_up(dev->mipi); - if (err < 0) { - dev_err(dev->mipi->dev, - "failed to power up MIPI bricks: %d\n", - err); - return ERR_PTR(err); - } - } - - mutex_unlock(&dev->mipi->lock); - return dev; put: @@ -270,29 +256,42 @@ EXPORT_SYMBOL(tegra_mipi_request); void tegra_mipi_free(struct tegra_mipi_device *device) { - int err; + platform_device_put(device->pdev); + kfree(device); +} +EXPORT_SYMBOL(tegra_mipi_free); - mutex_lock(&device->mipi->lock); +int tegra_mipi_enable(struct tegra_mipi_device *dev) +{ + int err = 0; - if (--device->mipi->usage_count == 0) { - err = tegra_mipi_power_down(device->mipi); - if (err < 0) { - /* - * Not much that can be done here, so an error message - * will have to do. - */ - dev_err(device->mipi->dev, - "failed to power down MIPI bricks: %d\n", - err); - } - } + mutex_lock(&dev->mipi->lock); - mutex_unlock(&device->mipi->lock); + if (dev->mipi->usage_count++ == 0) + err = tegra_mipi_power_up(dev->mipi); + + mutex_unlock(&dev->mipi->lock); + + return err; - platform_device_put(device->pdev); - kfree(device); } -EXPORT_SYMBOL(tegra_mipi_free); +EXPORT_SYMBOL(tegra_mipi_enable); + +int tegra_mipi_disable(struct tegra_mipi_device *dev) +{ + int err = 0; + + mutex_lock(&dev->mipi->lock); + + if (--dev->mipi->usage_count == 0) + err = tegra_mipi_power_down(dev->mipi); + + mutex_unlock(&dev->mipi->lock); + + return err; + +} +EXPORT_SYMBOL(tegra_mipi_disable); static int tegra_mipi_wait(struct tegra_mipi *mipi) { diff --git a/include/linux/host1x.h b/include/linux/host1x.h index d2ba7d334039..1ffbf2a8cb99 100644 --- a/include/linux/host1x.h +++ b/include/linux/host1x.h @@ -304,6 +304,8 @@ struct tegra_mipi_device; struct tegra_mipi_device *tegra_mipi_request(struct device *device); void tegra_mipi_free(struct tegra_mipi_device *device); +int tegra_mipi_enable(struct tegra_mipi_device *device); +int tegra_mipi_disable(struct tegra_mipi_device *device); int tegra_mipi_calibrate(struct tegra_mipi_device *device); #endif -- cgit v1.2.3-71-gd317 From 101b29a204f87c99377faa53bd378f101ebb1824 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Thu, 25 Aug 2016 15:16:45 -0700 Subject: byteswap: don't use __builtin_bswap*() with sparse Although sparse declares __builtin_bswap*(), it can't actually do constant folding inside them (yet). As such, things like switch (protocol) { case htons(ETH_P_IP): break; } which we do all over the place cause sparse to warn that it expects a constant instead of a function call. Disable __HAVE_BUILTIN_BSWAP*__ if __CHECKER__ is defined to avoid this. Fixes: 7322dd755e7d ("byteswap: try to avoid __builtin_constant_p gcc bug") Link: http://lkml.kernel.org/r/1470914102-26389-1-git-send-email-johannes@sipsolutions.net Signed-off-by: Johannes Berg Acked-by: Arnd Bergmann Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/compiler-gcc.h | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index e2949397c19b..8dbc8929a6a0 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -242,7 +242,11 @@ */ #define asm_volatile_goto(x...) do { asm goto(x); asm (""); } while (0) -#ifdef CONFIG_ARCH_USE_BUILTIN_BSWAP +/* + * sparse (__CHECKER__) pretends to be gcc, but can't do constant + * folding in __builtin_bswap*() (yet), so don't set these for it. + */ +#if defined(CONFIG_ARCH_USE_BUILTIN_BSWAP) && !defined(__CHECKER__) #if GCC_VERSION >= 40400 #define __HAVE_BUILTIN_BSWAP32__ #define __HAVE_BUILTIN_BSWAP64__ @@ -250,7 +254,7 @@ #if GCC_VERSION >= 40800 #define __HAVE_BUILTIN_BSWAP16__ #endif -#endif /* CONFIG_ARCH_USE_BUILTIN_BSWAP */ +#endif /* CONFIG_ARCH_USE_BUILTIN_BSWAP && !__CHECKER__ */ #if GCC_VERSION >= 50000 #define KASAN_ABI_VERSION 4 -- cgit v1.2.3-71-gd317 From e7d316a02f683864a12389f8808570e37fb90aa3 Mon Sep 17 00:00:00 2001 From: Subash Abhinov Kasiviswanathan Date: Thu, 25 Aug 2016 15:16:51 -0700 Subject: sysctl: handle error writing UINT_MAX to u32 fields We have scripts which write to certain fields on 3.18 kernels but this seems to be failing on 4.4 kernels. An entry which we write to here is xfrm_aevent_rseqth which is u32. echo 4294967295 > /proc/sys/net/core/xfrm_aevent_rseqth Commit 230633d109e3 ("kernel/sysctl.c: detect overflows when converting to int") prevented writing to sysctl entries when integer overflow occurs. However, this does not apply to unsigned integers. Heinrich suggested that we introduce a new option to handle 64 bit limits and set min as 0 and max as UINT_MAX. This might not work as it leads to issues similar to __do_proc_doulongvec_minmax. Alternatively, we would need to change the datatype of the entry to 64 bit. static int __do_proc_doulongvec_minmax(void *data, struct ctl_table { i = (unsigned long *) data; //This cast is causing to read beyond the size of data (u32) vleft = table->maxlen / sizeof(unsigned long); //vleft is 0 because maxlen is sizeof(u32) which is lesser than sizeof(unsigned long) on x86_64. Introduce a new proc handler proc_douintvec. Individual proc entries will need to be updated to use the new handler. [akpm@linux-foundation.org: coding-style fixes] Fixes: 230633d109e3 ("kernel/sysctl.c:detect overflows when converting to int") Link: http://lkml.kernel.org/r/1471479806-5252-1-git-send-email-subashab@codeaurora.org Signed-off-by: Subash Abhinov Kasiviswanathan Cc: Heinrich Schuchardt Cc: Kees Cook Cc: "David S. Miller" Cc: Ingo Molnar Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/sysctl.h | 2 ++ kernel/sysctl.c | 45 +++++++++++++++++++++++++++++++++++++++++++-- 2 files changed, 45 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h index 697e160c78d0..a4f7203a9017 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -42,6 +42,8 @@ extern int proc_dostring(struct ctl_table *, int, void __user *, size_t *, loff_t *); extern int proc_dointvec(struct ctl_table *, int, void __user *, size_t *, loff_t *); +extern int proc_douintvec(struct ctl_table *, int, + void __user *, size_t *, loff_t *); extern int proc_dointvec_minmax(struct ctl_table *, int, void __user *, size_t *, loff_t *); extern int proc_dointvec_jiffies(struct ctl_table *, int, diff --git a/kernel/sysctl.c b/kernel/sysctl.c index b43d0b27c1fe..a13bbdaab47d 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -2140,6 +2140,21 @@ static int do_proc_dointvec_conv(bool *negp, unsigned long *lvalp, return 0; } +static int do_proc_douintvec_conv(bool *negp, unsigned long *lvalp, + int *valp, + int write, void *data) +{ + if (write) { + if (*negp) + return -EINVAL; + *valp = *lvalp; + } else { + unsigned int val = *valp; + *lvalp = (unsigned long)val; + } + return 0; +} + static const char proc_wspace_sep[] = { ' ', '\t', '\n' }; static int __do_proc_dointvec(void *tbl_data, struct ctl_table *table, @@ -2259,8 +2274,27 @@ static int do_proc_dointvec(struct ctl_table *table, int write, int proc_dointvec(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { - return do_proc_dointvec(table,write,buffer,lenp,ppos, - NULL,NULL); + return do_proc_dointvec(table, write, buffer, lenp, ppos, NULL, NULL); +} + +/** + * proc_douintvec - read a vector of unsigned integers + * @table: the sysctl table + * @write: %TRUE if this is a write to the sysctl file + * @buffer: the user buffer + * @lenp: the size of the user buffer + * @ppos: file position + * + * Reads/writes up to table->maxlen/sizeof(unsigned int) unsigned integer + * values from/to the user buffer, treated as an ASCII string. + * + * Returns 0 on success. + */ +int proc_douintvec(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + return do_proc_dointvec(table, write, buffer, lenp, ppos, + do_proc_douintvec_conv, NULL); } /* @@ -2858,6 +2892,12 @@ int proc_dointvec(struct ctl_table *table, int write, return -ENOSYS; } +int proc_douintvec(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + return -ENOSYS; +} + int proc_dointvec_minmax(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { @@ -2903,6 +2943,7 @@ int proc_doulongvec_ms_jiffies_minmax(struct ctl_table *table, int write, * exception granted :-) */ EXPORT_SYMBOL(proc_dointvec); +EXPORT_SYMBOL(proc_douintvec); EXPORT_SYMBOL(proc_dointvec_jiffies); EXPORT_SYMBOL(proc_dointvec_minmax); EXPORT_SYMBOL(proc_dointvec_userhz_jiffies); -- cgit v1.2.3-71-gd317 From 17de0a9ff3df8f54f2f47746d118112d4e61d973 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Mon, 29 Aug 2016 11:33:58 +1000 Subject: iomap: don't set FIEMAP_EXTENT_MERGED for extent based filesystems Filesystems like XFS that use extents should not set the FIEMAP_EXTENT_MERGED flag in the fiemap extent structures. To allow for both behaviors for the upcoming gfs2 usage split the iomap type field into type and flags, and only set FIEMAP_EXTENT_MERGED if the IOMAP_F_MERGED flag is set. The flags field will also come in handy for future features such as shared extents on reflink-enabled file systems. Reported-by: Andreas Gruenbacher Signed-off-by: Christoph Hellwig Acked-by: Darrick J. Wong Signed-off-by: Dave Chinner --- fs/iomap.c | 5 ++++- include/linux/iomap.h | 8 +++++++- 2 files changed, 11 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/fs/iomap.c b/fs/iomap.c index 0342254646e3..706270f21b35 100644 --- a/fs/iomap.c +++ b/fs/iomap.c @@ -428,9 +428,12 @@ static int iomap_to_fiemap(struct fiemap_extent_info *fi, break; } + if (iomap->flags & IOMAP_F_MERGED) + flags |= FIEMAP_EXTENT_MERGED; + return fiemap_fill_next_extent(fi, iomap->offset, iomap->blkno != IOMAP_NULL_BLOCK ? iomap->blkno << 9: 0, - iomap->length, flags | FIEMAP_EXTENT_MERGED); + iomap->length, flags); } diff --git a/include/linux/iomap.h b/include/linux/iomap.h index 3267df461012..3d70ece10313 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -18,6 +18,11 @@ struct vm_fault; #define IOMAP_MAPPED 0x03 /* blocks allocated @blkno */ #define IOMAP_UNWRITTEN 0x04 /* blocks allocated @blkno in unwritten state */ +/* + * Flags for iomap mappings: + */ +#define IOMAP_F_MERGED 0x01 /* contains multiple blocks/extents */ + /* * Magic value for blkno: */ @@ -27,7 +32,8 @@ struct iomap { sector_t blkno; /* 1st sector of mapping, 512b units */ loff_t offset; /* file offset of mapping, bytes */ u64 length; /* length of mapping, bytes */ - int type; /* type of mapping */ + u16 type; /* type of mapping */ + u16 flags; /* flags for mapping */ struct block_device *bdev; /* block device for I/O */ }; -- cgit v1.2.3-71-gd317 From 2fb04fdf30192ff1e2b5834e9b7745889ea8bbcb Mon Sep 17 00:00:00 2001 From: Russell King Date: Sat, 27 Aug 2016 17:33:03 +0100 Subject: net: smc91x: fix SMC accesses Commit b70661c70830 ("net: smc91x: use run-time configuration on all ARM machines") broke some ARM platforms through several mistakes. Firstly, the access size must correspond to the following rule: (a) at least one of 16-bit or 8-bit access size must be supported (b) 32-bit accesses are optional, and may be enabled in addition to the above. Secondly, it provides no emulation of 16-bit accesses, instead blindly making 16-bit accesses even when the platform specifies that only 8-bit is supported. Reorganise smc91x.h so we can make use of the existing 16-bit access emulation already provided - if 16-bit accesses are supported, use 16-bit accesses directly, otherwise if 8-bit accesses are supported, use the provided 16-bit access emulation. If neither, BUG(). This exactly reflects the driver behaviour prior to the commit being fixed. Since the conversion incorrectly cut down the available access sizes on several platforms, we also need to go through every platform and fix up the overly-restrictive access size: Arnd assumed that if a platform can perform 32-bit, 16-bit and 8-bit accesses, then only a 32-bit access size needed to be specified - not so, all available access sizes must be specified. This likely fixes some performance regressions in doing this: if a platform does not support 8-bit accesses, 8-bit accesses have been emulated by performing a 16-bit read-modify-write access. Tested on the Intel Assabet/Neponset platform, which supports only 8-bit accesses, which was broken by the original commit. Fixes: b70661c70830 ("net: smc91x: use run-time configuration on all ARM machines") Signed-off-by: Russell King Tested-by: Robert Jarzmik Signed-off-by: David S. Miller --- arch/arm/mach-pxa/idp.c | 3 +- arch/arm/mach-pxa/xcep.c | 3 +- arch/arm/mach-realview/core.c | 3 +- arch/arm/mach-sa1100/pleb.c | 2 +- arch/blackfin/mach-bf561/boards/cm_bf561.c | 3 +- arch/blackfin/mach-bf561/boards/ezkit.c | 3 +- drivers/net/ethernet/smsc/smc91x.c | 7 ++++ drivers/net/ethernet/smsc/smc91x.h | 65 +++++++++++++++++++++--------- include/linux/smc91x.h | 10 +++++ 9 files changed, 73 insertions(+), 26 deletions(-) (limited to 'include/linux') diff --git a/arch/arm/mach-pxa/idp.c b/arch/arm/mach-pxa/idp.c index c410d84b243d..66070acaa888 100644 --- a/arch/arm/mach-pxa/idp.c +++ b/arch/arm/mach-pxa/idp.c @@ -83,7 +83,8 @@ static struct resource smc91x_resources[] = { }; static struct smc91x_platdata smc91x_platdata = { - .flags = SMC91X_USE_32BIT | SMC91X_USE_DMA | SMC91X_NOWAIT, + .flags = SMC91X_USE_8BIT | SMC91X_USE_16BIT | SMC91X_USE_32BIT | + SMC91X_USE_DMA | SMC91X_NOWAIT, }; static struct platform_device smc91x_device = { diff --git a/arch/arm/mach-pxa/xcep.c b/arch/arm/mach-pxa/xcep.c index 3f06cd90567a..056369ef250e 100644 --- a/arch/arm/mach-pxa/xcep.c +++ b/arch/arm/mach-pxa/xcep.c @@ -120,7 +120,8 @@ static struct resource smc91x_resources[] = { }; static struct smc91x_platdata xcep_smc91x_info = { - .flags = SMC91X_USE_32BIT | SMC91X_NOWAIT | SMC91X_USE_DMA, + .flags = SMC91X_USE_8BIT | SMC91X_USE_16BIT | SMC91X_USE_32BIT | + SMC91X_NOWAIT | SMC91X_USE_DMA, }; static struct platform_device smc91x_device = { diff --git a/arch/arm/mach-realview/core.c b/arch/arm/mach-realview/core.c index baf174542e36..a0ead0ae23d6 100644 --- a/arch/arm/mach-realview/core.c +++ b/arch/arm/mach-realview/core.c @@ -93,7 +93,8 @@ static struct smsc911x_platform_config smsc911x_config = { }; static struct smc91x_platdata smc91x_platdata = { - .flags = SMC91X_USE_32BIT | SMC91X_NOWAIT, + .flags = SMC91X_USE_8BIT | SMC91X_USE_16BIT | SMC91X_USE_32BIT | + SMC91X_NOWAIT, }; static struct platform_device realview_eth_device = { diff --git a/arch/arm/mach-sa1100/pleb.c b/arch/arm/mach-sa1100/pleb.c index 1525d7b5f1b7..88149f85bc49 100644 --- a/arch/arm/mach-sa1100/pleb.c +++ b/arch/arm/mach-sa1100/pleb.c @@ -45,7 +45,7 @@ static struct resource smc91x_resources[] = { }; static struct smc91x_platdata smc91x_platdata = { - .flags = SMC91X_USE_16BIT | SMC91X_NOWAIT, + .flags = SMC91X_USE_16BIT | SMC91X_USE_8BIT | SMC91X_NOWAIT, }; static struct platform_device smc91x_device = { diff --git a/arch/blackfin/mach-bf561/boards/cm_bf561.c b/arch/blackfin/mach-bf561/boards/cm_bf561.c index c6db52ba3a06..10c57771822d 100644 --- a/arch/blackfin/mach-bf561/boards/cm_bf561.c +++ b/arch/blackfin/mach-bf561/boards/cm_bf561.c @@ -146,7 +146,8 @@ static struct platform_device hitachi_fb_device = { #include static struct smc91x_platdata smc91x_info = { - .flags = SMC91X_USE_32BIT | SMC91X_NOWAIT, + .flags = SMC91X_USE_8BIT | SMC91X_USE_16BIT | SMC91X_USE_32BIT | + SMC91X_NOWAIT, .leda = RPC_LED_100_10, .ledb = RPC_LED_TX_RX, }; diff --git a/arch/blackfin/mach-bf561/boards/ezkit.c b/arch/blackfin/mach-bf561/boards/ezkit.c index f35525b55819..57d1c43726d9 100644 --- a/arch/blackfin/mach-bf561/boards/ezkit.c +++ b/arch/blackfin/mach-bf561/boards/ezkit.c @@ -134,7 +134,8 @@ static struct platform_device net2272_bfin_device = { #include static struct smc91x_platdata smc91x_info = { - .flags = SMC91X_USE_32BIT | SMC91X_NOWAIT, + .flags = SMC91X_USE_8BIT | SMC91X_USE_16BIT | SMC91X_USE_32BIT | + SMC91X_NOWAIT, .leda = RPC_LED_100_10, .ledb = RPC_LED_TX_RX, }; diff --git a/drivers/net/ethernet/smsc/smc91x.c b/drivers/net/ethernet/smsc/smc91x.c index 726b80f45906..503a3b6dce91 100644 --- a/drivers/net/ethernet/smsc/smc91x.c +++ b/drivers/net/ethernet/smsc/smc91x.c @@ -2275,6 +2275,13 @@ static int smc_drv_probe(struct platform_device *pdev) if (pd) { memcpy(&lp->cfg, pd, sizeof(lp->cfg)); lp->io_shift = SMC91X_IO_SHIFT(lp->cfg.flags); + + if (!SMC_8BIT(lp) && !SMC_16BIT(lp)) { + dev_err(&pdev->dev, + "at least one of 8-bit or 16-bit access support is required.\n"); + ret = -ENXIO; + goto out_free_netdev; + } } #if IS_BUILTIN(CONFIG_OF) diff --git a/drivers/net/ethernet/smsc/smc91x.h b/drivers/net/ethernet/smsc/smc91x.h index 1a55c7976df0..e17671c9d1b0 100644 --- a/drivers/net/ethernet/smsc/smc91x.h +++ b/drivers/net/ethernet/smsc/smc91x.h @@ -36,6 +36,27 @@ #include #include +/* + * Any 16-bit access is performed with two 8-bit accesses if the hardware + * can't do it directly. Most registers are 16-bit so those are mandatory. + */ +#define SMC_outw_b(x, a, r) \ + do { \ + unsigned int __val16 = (x); \ + unsigned int __reg = (r); \ + SMC_outb(__val16, a, __reg); \ + SMC_outb(__val16 >> 8, a, __reg + (1 << SMC_IO_SHIFT)); \ + } while (0) + +#define SMC_inw_b(a, r) \ + ({ \ + unsigned int __val16; \ + unsigned int __reg = r; \ + __val16 = SMC_inb(a, __reg); \ + __val16 |= SMC_inb(a, __reg + (1 << SMC_IO_SHIFT)) << 8; \ + __val16; \ + }) + /* * Define your architecture specific bus configuration parameters here. */ @@ -55,10 +76,30 @@ #define SMC_IO_SHIFT (lp->io_shift) #define SMC_inb(a, r) readb((a) + (r)) -#define SMC_inw(a, r) readw((a) + (r)) +#define SMC_inw(a, r) \ + ({ \ + unsigned int __smc_r = r; \ + SMC_16BIT(lp) ? readw((a) + __smc_r) : \ + SMC_8BIT(lp) ? SMC_inw_b(a, __smc_r) : \ + ({ BUG(); 0; }); \ + }) + #define SMC_inl(a, r) readl((a) + (r)) #define SMC_outb(v, a, r) writeb(v, (a) + (r)) +#define SMC_outw(v, a, r) \ + do { \ + unsigned int __v = v, __smc_r = r; \ + if (SMC_16BIT(lp)) \ + __SMC_outw(__v, a, __smc_r); \ + else if (SMC_8BIT(lp)) \ + SMC_outw_b(__v, a, __smc_r); \ + else \ + BUG(); \ + } while (0) + #define SMC_outl(v, a, r) writel(v, (a) + (r)) +#define SMC_insb(a, r, p, l) readsb((a) + (r), p, l) +#define SMC_outsb(a, r, p, l) writesb((a) + (r), p, l) #define SMC_insw(a, r, p, l) readsw((a) + (r), p, l) #define SMC_outsw(a, r, p, l) writesw((a) + (r), p, l) #define SMC_insl(a, r, p, l) readsl((a) + (r), p, l) @@ -66,7 +107,7 @@ #define SMC_IRQ_FLAGS (-1) /* from resource */ /* We actually can't write halfwords properly if not word aligned */ -static inline void SMC_outw(u16 val, void __iomem *ioaddr, int reg) +static inline void __SMC_outw(u16 val, void __iomem *ioaddr, int reg) { if ((machine_is_mainstone() || machine_is_stargate2() || machine_is_pxa_idp()) && reg & 2) { @@ -416,24 +457,8 @@ smc_pxa_dma_insw(void __iomem *ioaddr, struct smc_local *lp, int reg, int dma, #if ! SMC_CAN_USE_16BIT -/* - * Any 16-bit access is performed with two 8-bit accesses if the hardware - * can't do it directly. Most registers are 16-bit so those are mandatory. - */ -#define SMC_outw(x, ioaddr, reg) \ - do { \ - unsigned int __val16 = (x); \ - SMC_outb( __val16, ioaddr, reg ); \ - SMC_outb( __val16 >> 8, ioaddr, reg + (1 << SMC_IO_SHIFT));\ - } while (0) -#define SMC_inw(ioaddr, reg) \ - ({ \ - unsigned int __val16; \ - __val16 = SMC_inb( ioaddr, reg ); \ - __val16 |= SMC_inb( ioaddr, reg + (1 << SMC_IO_SHIFT)) << 8; \ - __val16; \ - }) - +#define SMC_outw(x, ioaddr, reg) SMC_outw_b(x, ioaddr, reg) +#define SMC_inw(ioaddr, reg) SMC_inw_b(ioaddr, reg) #define SMC_insw(a, r, p, l) BUG() #define SMC_outsw(a, r, p, l) BUG() diff --git a/include/linux/smc91x.h b/include/linux/smc91x.h index 76199b75d584..e302c447e057 100644 --- a/include/linux/smc91x.h +++ b/include/linux/smc91x.h @@ -1,6 +1,16 @@ #ifndef __SMC91X_H__ #define __SMC91X_H__ +/* + * These bits define which access sizes a platform can support, rather + * than the maximal access size. So, if your platform can do 16-bit + * and 32-bit accesses to the SMC91x device, but not 8-bit, set both + * SMC91X_USE_16BIT and SMC91X_USE_32BIT. + * + * The SMC91x driver requires at least one of SMC91X_USE_8BIT or + * SMC91X_USE_16BIT to be supported - just setting SMC91X_USE_32BIT is + * an invalid configuration. + */ #define SMC91X_USE_8BIT (1 << 0) #define SMC91X_USE_16BIT (1 << 1) #define SMC91X_USE_32BIT (1 << 2) -- cgit v1.2.3-71-gd317 From 0d025d271e55f3de21f0aaaf54b42d20404d2b23 Mon Sep 17 00:00:00 2001 From: Josh Poimboeuf Date: Tue, 30 Aug 2016 08:04:16 -0500 Subject: mm/usercopy: get rid of CONFIG_DEBUG_STRICT_USER_COPY_CHECKS There are three usercopy warnings which are currently being silenced for gcc 4.6 and newer: 1) "copy_from_user() buffer size is too small" compile warning/error This is a static warning which happens when object size and copy size are both const, and copy size > object size. I didn't see any false positives for this one. So the function warning attribute seems to be working fine here. Note this scenario is always a bug and so I think it should be changed to *always* be an error, regardless of CONFIG_DEBUG_STRICT_USER_COPY_CHECKS. 2) "copy_from_user() buffer size is not provably correct" compile warning This is another static warning which happens when I enable __compiletime_object_size() for new compilers (and CONFIG_DEBUG_STRICT_USER_COPY_CHECKS). It happens when object size is const, but copy size is *not*. In this case there's no way to compare the two at build time, so it gives the warning. (Note the warning is a byproduct of the fact that gcc has no way of knowing whether the overflow function will be called, so the call isn't dead code and the warning attribute is activated.) So this warning seems to only indicate "this is an unusual pattern, maybe you should check it out" rather than "this is a bug". I get 102(!) of these warnings with allyesconfig and the __compiletime_object_size() gcc check removed. I don't know if there are any real bugs hiding in there, but from looking at a small sample, I didn't see any. According to Kees, it does sometimes find real bugs. But the false positive rate seems high. 3) "Buffer overflow detected" runtime warning This is a runtime warning where object size is const, and copy size > object size. All three warnings (both static and runtime) were completely disabled for gcc 4.6 with the following commit: 2fb0815c9ee6 ("gcc4: disable __compiletime_object_size for GCC 4.6+") That commit mistakenly assumed that the false positives were caused by a gcc bug in __compiletime_object_size(). But in fact, __compiletime_object_size() seems to be working fine. The false positives were instead triggered by #2 above. (Though I don't have an explanation for why the warnings supposedly only started showing up in gcc 4.6.) So remove warning #2 to get rid of all the false positives, and re-enable warnings #1 and #3 by reverting the above commit. Furthermore, since #1 is a real bug which is detected at compile time, upgrade it to always be an error. Having done all that, CONFIG_DEBUG_STRICT_USER_COPY_CHECKS is no longer needed. Signed-off-by: Josh Poimboeuf Cc: Kees Cook Cc: Thomas Gleixner Cc: Ingo Molnar Cc: "H . Peter Anvin" Cc: Andy Lutomirski Cc: Steven Rostedt Cc: Brian Gerst Cc: Peter Zijlstra Cc: Frederic Weisbecker Cc: Byungchul Park Cc: Nilay Vaish Signed-off-by: Linus Torvalds --- arch/parisc/Kconfig | 1 - arch/parisc/configs/c8000_defconfig | 1 - arch/parisc/configs/generic-64bit_defconfig | 1 - arch/parisc/include/asm/uaccess.h | 22 ++++----- arch/s390/Kconfig | 1 - arch/s390/configs/default_defconfig | 1 - arch/s390/configs/gcov_defconfig | 1 - arch/s390/configs/performance_defconfig | 1 - arch/s390/defconfig | 1 - arch/s390/include/asm/uaccess.h | 19 +++++--- arch/tile/Kconfig | 1 - arch/tile/include/asm/uaccess.h | 22 +++++---- arch/x86/Kconfig | 1 - arch/x86/include/asm/uaccess.h | 69 ++++------------------------- include/asm-generic/uaccess.h | 1 + include/linux/compiler-gcc.h | 2 +- lib/Kconfig.debug | 18 -------- lib/Makefile | 1 - lib/usercopy.c | 9 ---- 19 files changed, 45 insertions(+), 128 deletions(-) delete mode 100644 lib/usercopy.c (limited to 'include/linux') diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig index cd8778103165..af12c2db9bb8 100644 --- a/arch/parisc/Kconfig +++ b/arch/parisc/Kconfig @@ -1,6 +1,5 @@ config PARISC def_bool y - select ARCH_HAS_DEBUG_STRICT_USER_COPY_CHECKS select ARCH_MIGHT_HAVE_PC_PARPORT select HAVE_IDE select HAVE_OPROFILE diff --git a/arch/parisc/configs/c8000_defconfig b/arch/parisc/configs/c8000_defconfig index 1a8f6f95689e..f6a4c016304b 100644 --- a/arch/parisc/configs/c8000_defconfig +++ b/arch/parisc/configs/c8000_defconfig @@ -245,7 +245,6 @@ CONFIG_DEBUG_RT_MUTEXES=y CONFIG_PROVE_RCU_DELAY=y CONFIG_DEBUG_BLOCK_EXT_DEVT=y CONFIG_LATENCYTOP=y -CONFIG_DEBUG_STRICT_USER_COPY_CHECKS=y CONFIG_KEYS=y # CONFIG_CRYPTO_HW is not set CONFIG_FONTS=y diff --git a/arch/parisc/configs/generic-64bit_defconfig b/arch/parisc/configs/generic-64bit_defconfig index 7e0792658952..c564e6e1fa23 100644 --- a/arch/parisc/configs/generic-64bit_defconfig +++ b/arch/parisc/configs/generic-64bit_defconfig @@ -291,7 +291,6 @@ CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC=y CONFIG_BOOTPARAM_HUNG_TASK_PANIC=y # CONFIG_SCHED_DEBUG is not set CONFIG_TIMER_STATS=y -CONFIG_DEBUG_STRICT_USER_COPY_CHECKS=y CONFIG_CRYPTO_MANAGER=y CONFIG_CRYPTO_ECB=m CONFIG_CRYPTO_PCBC=m diff --git a/arch/parisc/include/asm/uaccess.h b/arch/parisc/include/asm/uaccess.h index 0f59fd9ca205..e9150487e20d 100644 --- a/arch/parisc/include/asm/uaccess.h +++ b/arch/parisc/include/asm/uaccess.h @@ -208,13 +208,13 @@ unsigned long copy_in_user(void __user *dst, const void __user *src, unsigned lo #define __copy_to_user_inatomic __copy_to_user #define __copy_from_user_inatomic __copy_from_user -extern void copy_from_user_overflow(void) -#ifdef CONFIG_DEBUG_STRICT_USER_COPY_CHECKS - __compiletime_error("copy_from_user() buffer size is not provably correct") -#else - __compiletime_warning("copy_from_user() buffer size is not provably correct") -#endif -; +extern void __compiletime_error("usercopy buffer size is too small") +__bad_copy_user(void); + +static inline void copy_user_overflow(int size, unsigned long count) +{ + WARN(1, "Buffer overflow detected (%d < %lu)!\n", size, count); +} static inline unsigned long __must_check copy_from_user(void *to, const void __user *from, @@ -223,10 +223,12 @@ static inline unsigned long __must_check copy_from_user(void *to, int sz = __compiletime_object_size(to); int ret = -EFAULT; - if (likely(sz == -1 || !__builtin_constant_p(n) || sz >= n)) + if (likely(sz == -1 || sz >= n)) ret = __copy_from_user(to, from, n); - else - copy_from_user_overflow(); + else if (!__builtin_constant_p(n)) + copy_user_overflow(sz, n); + else + __bad_copy_user(); return ret; } diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig index e751fe25d6ab..c109f073d454 100644 --- a/arch/s390/Kconfig +++ b/arch/s390/Kconfig @@ -68,7 +68,6 @@ config DEBUG_RODATA config S390 def_bool y select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE - select ARCH_HAS_DEBUG_STRICT_USER_COPY_CHECKS select ARCH_HAS_DEVMEM_IS_ALLOWED select ARCH_HAS_ELF_RANDOMIZE select ARCH_HAS_GCOV_PROFILE_ALL diff --git a/arch/s390/configs/default_defconfig b/arch/s390/configs/default_defconfig index 26e0c7f08814..412b1bd21029 100644 --- a/arch/s390/configs/default_defconfig +++ b/arch/s390/configs/default_defconfig @@ -602,7 +602,6 @@ CONFIG_FAIL_FUTEX=y CONFIG_FAULT_INJECTION_DEBUG_FS=y CONFIG_FAULT_INJECTION_STACKTRACE_FILTER=y CONFIG_LATENCYTOP=y -CONFIG_DEBUG_STRICT_USER_COPY_CHECKS=y CONFIG_IRQSOFF_TRACER=y CONFIG_PREEMPT_TRACER=y CONFIG_SCHED_TRACER=y diff --git a/arch/s390/configs/gcov_defconfig b/arch/s390/configs/gcov_defconfig index 24879dab47bc..bec279eb4b93 100644 --- a/arch/s390/configs/gcov_defconfig +++ b/arch/s390/configs/gcov_defconfig @@ -552,7 +552,6 @@ CONFIG_NOTIFIER_ERROR_INJECTION=m CONFIG_CPU_NOTIFIER_ERROR_INJECT=m CONFIG_PM_NOTIFIER_ERROR_INJECT=m CONFIG_LATENCYTOP=y -CONFIG_DEBUG_STRICT_USER_COPY_CHECKS=y CONFIG_BLK_DEV_IO_TRACE=y # CONFIG_KPROBE_EVENT is not set CONFIG_TRACE_ENUM_MAP_FILE=y diff --git a/arch/s390/configs/performance_defconfig b/arch/s390/configs/performance_defconfig index a5c1e5f2a0ca..1751446a5bbb 100644 --- a/arch/s390/configs/performance_defconfig +++ b/arch/s390/configs/performance_defconfig @@ -549,7 +549,6 @@ CONFIG_TIMER_STATS=y CONFIG_RCU_TORTURE_TEST=m CONFIG_RCU_CPU_STALL_TIMEOUT=60 CONFIG_LATENCYTOP=y -CONFIG_DEBUG_STRICT_USER_COPY_CHECKS=y CONFIG_SCHED_TRACER=y CONFIG_FTRACE_SYSCALLS=y CONFIG_STACK_TRACER=y diff --git a/arch/s390/defconfig b/arch/s390/defconfig index 73610f2e3b4f..2d40ef0a6295 100644 --- a/arch/s390/defconfig +++ b/arch/s390/defconfig @@ -172,7 +172,6 @@ CONFIG_DEBUG_NOTIFIERS=y CONFIG_RCU_CPU_STALL_TIMEOUT=60 CONFIG_RCU_TRACE=y CONFIG_LATENCYTOP=y -CONFIG_DEBUG_STRICT_USER_COPY_CHECKS=y CONFIG_SCHED_TRACER=y CONFIG_FTRACE_SYSCALLS=y CONFIG_TRACER_SNAPSHOT_PER_CPU_SWAP=y diff --git a/arch/s390/include/asm/uaccess.h b/arch/s390/include/asm/uaccess.h index 9b49cf1daa8f..95aefdba4be2 100644 --- a/arch/s390/include/asm/uaccess.h +++ b/arch/s390/include/asm/uaccess.h @@ -311,6 +311,14 @@ int __get_user_bad(void) __attribute__((noreturn)); #define __put_user_unaligned __put_user #define __get_user_unaligned __get_user +extern void __compiletime_error("usercopy buffer size is too small") +__bad_copy_user(void); + +static inline void copy_user_overflow(int size, unsigned long count) +{ + WARN(1, "Buffer overflow detected (%d < %lu)!\n", size, count); +} + /** * copy_to_user: - Copy a block of data into user space. * @to: Destination address, in user space. @@ -332,12 +340,6 @@ copy_to_user(void __user *to, const void *from, unsigned long n) return __copy_to_user(to, from, n); } -void copy_from_user_overflow(void) -#ifdef CONFIG_DEBUG_STRICT_USER_COPY_CHECKS -__compiletime_warning("copy_from_user() buffer size is not provably correct") -#endif -; - /** * copy_from_user: - Copy a block of data from user space. * @to: Destination address, in kernel space. @@ -362,7 +364,10 @@ copy_from_user(void *to, const void __user *from, unsigned long n) might_fault(); if (unlikely(sz != -1 && sz < n)) { - copy_from_user_overflow(); + if (!__builtin_constant_p(n)) + copy_user_overflow(sz, n); + else + __bad_copy_user(); return n; } return __copy_from_user(to, from, n); diff --git a/arch/tile/Kconfig b/arch/tile/Kconfig index 4820a02838ac..78da75b670bc 100644 --- a/arch/tile/Kconfig +++ b/arch/tile/Kconfig @@ -4,7 +4,6 @@ config TILE def_bool y select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE - select ARCH_HAS_DEBUG_STRICT_USER_COPY_CHECKS select ARCH_HAS_DEVMEM_IS_ALLOWED select ARCH_HAVE_NMI_SAFE_CMPXCHG select ARCH_WANT_FRAME_POINTERS diff --git a/arch/tile/include/asm/uaccess.h b/arch/tile/include/asm/uaccess.h index 0a9c4265763b..a77369e91e54 100644 --- a/arch/tile/include/asm/uaccess.h +++ b/arch/tile/include/asm/uaccess.h @@ -416,14 +416,13 @@ _copy_from_user(void *to, const void __user *from, unsigned long n) return n; } -#ifdef CONFIG_DEBUG_STRICT_USER_COPY_CHECKS -/* - * There are still unprovable places in the generic code as of 2.6.34, so this - * option is not really compatible with -Werror, which is more useful in - * general. - */ -extern void copy_from_user_overflow(void) - __compiletime_warning("copy_from_user() size is not provably correct"); +extern void __compiletime_error("usercopy buffer size is too small") +__bad_copy_user(void); + +static inline void copy_user_overflow(int size, unsigned long count) +{ + WARN(1, "Buffer overflow detected (%d < %lu)!\n", size, count); +} static inline unsigned long __must_check copy_from_user(void *to, const void __user *from, @@ -433,14 +432,13 @@ static inline unsigned long __must_check copy_from_user(void *to, if (likely(sz == -1 || sz >= n)) n = _copy_from_user(to, from, n); + else if (!__builtin_constant_p(n)) + copy_user_overflow(sz, n); else - copy_from_user_overflow(); + __bad_copy_user(); return n; } -#else -#define copy_from_user _copy_from_user -#endif #ifdef __tilegx__ /** diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index c580d8c33562..2a1f0ce7c59a 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -24,7 +24,6 @@ config X86 select ARCH_DISCARD_MEMBLOCK select ARCH_HAS_ACPI_TABLE_UPGRADE if ACPI select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE - select ARCH_HAS_DEBUG_STRICT_USER_COPY_CHECKS select ARCH_HAS_DEVMEM_IS_ALLOWED select ARCH_HAS_ELF_RANDOMIZE select ARCH_HAS_FAST_MULTIPLIER diff --git a/arch/x86/include/asm/uaccess.h b/arch/x86/include/asm/uaccess.h index a0ae610b9280..c3f291195294 100644 --- a/arch/x86/include/asm/uaccess.h +++ b/arch/x86/include/asm/uaccess.h @@ -697,43 +697,14 @@ unsigned long __must_check _copy_from_user(void *to, const void __user *from, unsigned long __must_check _copy_to_user(void __user *to, const void *from, unsigned n); -#ifdef CONFIG_DEBUG_STRICT_USER_COPY_CHECKS -# define copy_user_diag __compiletime_error -#else -# define copy_user_diag __compiletime_warning -#endif - -extern void copy_user_diag("copy_from_user() buffer size is too small") -copy_from_user_overflow(void); -extern void copy_user_diag("copy_to_user() buffer size is too small") -copy_to_user_overflow(void) __asm__("copy_from_user_overflow"); - -#undef copy_user_diag - -#ifdef CONFIG_DEBUG_STRICT_USER_COPY_CHECKS - -extern void -__compiletime_warning("copy_from_user() buffer size is not provably correct") -__copy_from_user_overflow(void) __asm__("copy_from_user_overflow"); -#define __copy_from_user_overflow(size, count) __copy_from_user_overflow() - -extern void -__compiletime_warning("copy_to_user() buffer size is not provably correct") -__copy_to_user_overflow(void) __asm__("copy_from_user_overflow"); -#define __copy_to_user_overflow(size, count) __copy_to_user_overflow() - -#else +extern void __compiletime_error("usercopy buffer size is too small") +__bad_copy_user(void); -static inline void -__copy_from_user_overflow(int size, unsigned long count) +static inline void copy_user_overflow(int size, unsigned long count) { WARN(1, "Buffer overflow detected (%d < %lu)!\n", size, count); } -#define __copy_to_user_overflow __copy_from_user_overflow - -#endif - static inline unsigned long __must_check copy_from_user(void *to, const void __user *from, unsigned long n) { @@ -743,31 +714,13 @@ copy_from_user(void *to, const void __user *from, unsigned long n) kasan_check_write(to, n); - /* - * While we would like to have the compiler do the checking for us - * even in the non-constant size case, any false positives there are - * a problem (especially when DEBUG_STRICT_USER_COPY_CHECKS, but even - * without - the [hopefully] dangerous looking nature of the warning - * would make people go look at the respecitive call sites over and - * over again just to find that there's no problem). - * - * And there are cases where it's just not realistic for the compiler - * to prove the count to be in range. For example when multiple call - * sites of a helper function - perhaps in different source files - - * all doing proper range checking, yet the helper function not doing - * so again. - * - * Therefore limit the compile time checking to the constant size - * case, and do only runtime checking for non-constant sizes. - */ - if (likely(sz < 0 || sz >= n)) { check_object_size(to, n, false); n = _copy_from_user(to, from, n); - } else if (__builtin_constant_p(n)) - copy_from_user_overflow(); + } else if (!__builtin_constant_p(n)) + copy_user_overflow(sz, n); else - __copy_from_user_overflow(sz, n); + __bad_copy_user(); return n; } @@ -781,21 +734,17 @@ copy_to_user(void __user *to, const void *from, unsigned long n) might_fault(); - /* See the comment in copy_from_user() above. */ if (likely(sz < 0 || sz >= n)) { check_object_size(from, n, true); n = _copy_to_user(to, from, n); - } else if (__builtin_constant_p(n)) - copy_to_user_overflow(); + } else if (!__builtin_constant_p(n)) + copy_user_overflow(sz, n); else - __copy_to_user_overflow(sz, n); + __bad_copy_user(); return n; } -#undef __copy_from_user_overflow -#undef __copy_to_user_overflow - /* * We rely on the nested NMI work to allow atomic faults from the NMI path; the * nested NMI paths are careful to preserve CR2. diff --git a/include/asm-generic/uaccess.h b/include/asm-generic/uaccess.h index 1bfa602958f2..5dea1fb6979c 100644 --- a/include/asm-generic/uaccess.h +++ b/include/asm-generic/uaccess.h @@ -72,6 +72,7 @@ struct exception_table_entry /* Returns 0 if exception not found and fixup otherwise. */ extern unsigned long search_exception_table(unsigned long); + /* * architectures with an MMU should override these two */ diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h index 8dbc8929a6a0..573c5a18908f 100644 --- a/include/linux/compiler-gcc.h +++ b/include/linux/compiler-gcc.h @@ -158,7 +158,7 @@ #define __compiler_offsetof(a, b) \ __builtin_offsetof(a, b) -#if GCC_VERSION >= 40100 && GCC_VERSION < 40600 +#if GCC_VERSION >= 40100 # define __compiletime_object_size(obj) __builtin_object_size(obj, 0) #endif diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug index 2307d7c89dac..2e2cca509231 100644 --- a/lib/Kconfig.debug +++ b/lib/Kconfig.debug @@ -1686,24 +1686,6 @@ config LATENCYTOP Enable this option if you want to use the LatencyTOP tool to find out which userspace is blocking on what kernel operations. -config ARCH_HAS_DEBUG_STRICT_USER_COPY_CHECKS - bool - -config DEBUG_STRICT_USER_COPY_CHECKS - bool "Strict user copy size checks" - depends on ARCH_HAS_DEBUG_STRICT_USER_COPY_CHECKS - depends on DEBUG_KERNEL && !TRACE_BRANCH_PROFILING - help - Enabling this option turns a certain set of sanity checks for user - copy operations into compile time failures. - - The copy_from_user() etc checks are there to help test if there - are sufficient security checks on the length argument of - the copy operation, by having gcc prove that the argument is - within bounds. - - If unsure, say N. - source kernel/trace/Kconfig menu "Runtime Testing" diff --git a/lib/Makefile b/lib/Makefile index cfa68eb269e4..5dc77a8ec297 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -24,7 +24,6 @@ lib-y := ctype.o string.o vsprintf.o cmdline.o \ is_single_threaded.o plist.o decompress.o kobject_uevent.o \ earlycpio.o seq_buf.o nmi_backtrace.o nodemask.o -obj-$(CONFIG_ARCH_HAS_DEBUG_STRICT_USER_COPY_CHECKS) += usercopy.o lib-$(CONFIG_MMU) += ioremap.o lib-$(CONFIG_SMP) += cpumask.o lib-$(CONFIG_HAS_DMA) += dma-noop.o diff --git a/lib/usercopy.c b/lib/usercopy.c deleted file mode 100644 index 4f5b1ddbcd25..000000000000 --- a/lib/usercopy.c +++ /dev/null @@ -1,9 +0,0 @@ -#include -#include -#include - -void copy_from_user_overflow(void) -{ - WARN(1, "Buffer overflow detected!\n"); -} -EXPORT_SYMBOL(copy_from_user_overflow); -- cgit v1.2.3-71-gd317 From 5db4f7f80d165fc9725f356e99feec409e446baa Mon Sep 17 00:00:00 2001 From: Andy Shevchenko Date: Tue, 16 Aug 2016 15:06:54 +0300 Subject: Revert "tty/serial/8250: use mctrl_gpio helpers" Serial console is broken in v4.8-rcX. Mika and I independently bisected down to commit 4ef03d328769 ("tty/serial/8250: use mctrl_gpio helpers"). Since neither author nor anyone else didn't propose a solution we better revert it for now. This reverts commit 4ef03d328769eddbfeca1f1c958fdb181a69c341. Link: https://lkml.kernel.org/r/20160809130229.GN1729@lahna.fi.intel.com Signed-off-by: Andy Shevchenko Tested-by: Heikki Krogerus Tested-by: Mika Westerberg Signed-off-by: Greg Kroah-Hartman --- Documentation/devicetree/bindings/serial/8250.txt | 19 ------------ drivers/tty/serial/8250/8250.h | 35 +---------------------- drivers/tty/serial/8250/8250_core.c | 9 ------ drivers/tty/serial/8250/8250_omap.c | 31 +++++++++----------- drivers/tty/serial/8250/8250_port.c | 7 +---- drivers/tty/serial/8250/Kconfig | 1 - include/linux/serial_8250.h | 1 - 7 files changed, 15 insertions(+), 88 deletions(-) (limited to 'include/linux') diff --git a/Documentation/devicetree/bindings/serial/8250.txt b/Documentation/devicetree/bindings/serial/8250.txt index f5561ac7e17e..936ab5b87324 100644 --- a/Documentation/devicetree/bindings/serial/8250.txt +++ b/Documentation/devicetree/bindings/serial/8250.txt @@ -42,9 +42,6 @@ Optional properties: - auto-flow-control: one way to enable automatic flow control support. The driver is allowed to detect support for the capability even without this property. -- {rts,cts,dtr,dsr,rng,dcd}-gpios: specify a GPIO for RTS/CTS/DTR/DSR/RI/DCD - line respectively. It will use specified GPIO instead of the peripheral - function pin for the UART feature. If unsure, don't specify this property. Note: * fsl,ns16550: @@ -66,19 +63,3 @@ Example: interrupts = <10>; reg-shift = <2>; }; - -Example for OMAP UART using GPIO-based modem control signals: - - uart4: serial@49042000 { - compatible = "ti,omap3-uart"; - reg = <0x49042000 0x400>; - interrupts = <80>; - ti,hwmods = "uart4"; - clock-frequency = <48000000>; - cts-gpios = <&gpio3 5 GPIO_ACTIVE_LOW>; - rts-gpios = <&gpio3 6 GPIO_ACTIVE_LOW>; - dtr-gpios = <&gpio1 12 GPIO_ACTIVE_LOW>; - dsr-gpios = <&gpio1 13 GPIO_ACTIVE_LOW>; - dcd-gpios = <&gpio1 14 GPIO_ACTIVE_LOW>; - rng-gpios = <&gpio1 15 GPIO_ACTIVE_LOW>; - }; diff --git a/drivers/tty/serial/8250/8250.h b/drivers/tty/serial/8250/8250.h index 122e0e4029fe..1a16feac9a36 100644 --- a/drivers/tty/serial/8250/8250.h +++ b/drivers/tty/serial/8250/8250.h @@ -15,8 +15,6 @@ #include #include -#include "../serial_mctrl_gpio.h" - struct uart_8250_dma { int (*tx_dma)(struct uart_8250_port *p); int (*rx_dma)(struct uart_8250_port *p); @@ -133,43 +131,12 @@ void serial8250_em485_destroy(struct uart_8250_port *p); static inline void serial8250_out_MCR(struct uart_8250_port *up, int value) { - int mctrl_gpio = 0; - serial_out(up, UART_MCR, value); - - if (value & UART_MCR_RTS) - mctrl_gpio |= TIOCM_RTS; - if (value & UART_MCR_DTR) - mctrl_gpio |= TIOCM_DTR; - - mctrl_gpio_set(up->gpios, mctrl_gpio); } static inline int serial8250_in_MCR(struct uart_8250_port *up) { - int mctrl, mctrl_gpio = 0; - - mctrl = serial_in(up, UART_MCR); - - /* save current MCR values */ - if (mctrl & UART_MCR_RTS) - mctrl_gpio |= TIOCM_RTS; - if (mctrl & UART_MCR_DTR) - mctrl_gpio |= TIOCM_DTR; - - mctrl_gpio = mctrl_gpio_get_outputs(up->gpios, &mctrl_gpio); - - if (mctrl_gpio & TIOCM_RTS) - mctrl |= UART_MCR_RTS; - else - mctrl &= ~UART_MCR_RTS; - - if (mctrl_gpio & TIOCM_DTR) - mctrl |= UART_MCR_DTR; - else - mctrl &= ~UART_MCR_DTR; - - return mctrl; + return serial_in(up, UART_MCR); } #if defined(__alpha__) && !defined(CONFIG_PCI) diff --git a/drivers/tty/serial/8250/8250_core.c b/drivers/tty/serial/8250/8250_core.c index 13ad5c3d2e68..dcf43f66404f 100644 --- a/drivers/tty/serial/8250/8250_core.c +++ b/drivers/tty/serial/8250/8250_core.c @@ -974,8 +974,6 @@ int serial8250_register_8250_port(struct uart_8250_port *up) uart = serial8250_find_match_or_unused(&up->port); if (uart && uart->port.type != PORT_8250_CIR) { - struct mctrl_gpios *gpios; - if (uart->port.dev) uart_remove_one_port(&serial8250_reg, &uart->port); @@ -1013,13 +1011,6 @@ int serial8250_register_8250_port(struct uart_8250_port *up) if (up->port.flags & UPF_FIXED_TYPE) uart->port.type = up->port.type; - gpios = mctrl_gpio_init(&uart->port, 0); - if (IS_ERR(gpios)) { - if (PTR_ERR(gpios) != -ENOSYS) - return PTR_ERR(gpios); - } else - uart->gpios = gpios; - serial8250_set_defaults(uart); /* Possibly override default I/O functions. */ diff --git a/drivers/tty/serial/8250/8250_omap.c b/drivers/tty/serial/8250/8250_omap.c index e14982f36a04..61ad6c3b20a0 100644 --- a/drivers/tty/serial/8250/8250_omap.c +++ b/drivers/tty/serial/8250/8250_omap.c @@ -134,21 +134,18 @@ static void omap8250_set_mctrl(struct uart_port *port, unsigned int mctrl) serial8250_do_set_mctrl(port, mctrl); - if (IS_ERR_OR_NULL(mctrl_gpio_to_gpiod(up->gpios, - UART_GPIO_RTS))) { - /* - * Turn off autoRTS if RTS is lowered and restore autoRTS - * setting if RTS is raised - */ - lcr = serial_in(up, UART_LCR); - serial_out(up, UART_LCR, UART_LCR_CONF_MODE_B); - if ((mctrl & TIOCM_RTS) && (port->status & UPSTAT_AUTORTS)) - priv->efr |= UART_EFR_RTS; - else - priv->efr &= ~UART_EFR_RTS; - serial_out(up, UART_EFR, priv->efr); - serial_out(up, UART_LCR, lcr); - } + /* + * Turn off autoRTS if RTS is lowered and restore autoRTS setting + * if RTS is raised + */ + lcr = serial_in(up, UART_LCR); + serial_out(up, UART_LCR, UART_LCR_CONF_MODE_B); + if ((mctrl & TIOCM_RTS) && (port->status & UPSTAT_AUTORTS)) + priv->efr |= UART_EFR_RTS; + else + priv->efr &= ~UART_EFR_RTS; + serial_out(up, UART_EFR, priv->efr); + serial_out(up, UART_LCR, lcr); } /* @@ -449,9 +446,7 @@ static void omap_8250_set_termios(struct uart_port *port, priv->efr = 0; up->port.status &= ~(UPSTAT_AUTOCTS | UPSTAT_AUTORTS | UPSTAT_AUTOXOFF); - if (termios->c_cflag & CRTSCTS && up->port.flags & UPF_HARD_FLOW - && IS_ERR_OR_NULL(mctrl_gpio_to_gpiod(up->gpios, - UART_GPIO_RTS))) { + if (termios->c_cflag & CRTSCTS && up->port.flags & UPF_HARD_FLOW) { /* Enable AUTOCTS (autoRTS is enabled when RTS is raised) */ up->port.status |= UPSTAT_AUTOCTS | UPSTAT_AUTORTS; priv->efr |= UART_EFR_CTS; diff --git a/drivers/tty/serial/8250/8250_port.c b/drivers/tty/serial/8250/8250_port.c index 7481b95c6d84..bdfa659b9606 100644 --- a/drivers/tty/serial/8250/8250_port.c +++ b/drivers/tty/serial/8250/8250_port.c @@ -1618,8 +1618,6 @@ static void serial8250_disable_ms(struct uart_port *port) if (up->bugs & UART_BUG_NOMSR) return; - mctrl_gpio_disable_ms(up->gpios); - up->ier &= ~UART_IER_MSI; serial_port_out(port, UART_IER, up->ier); } @@ -1632,8 +1630,6 @@ static void serial8250_enable_ms(struct uart_port *port) if (up->bugs & UART_BUG_NOMSR) return; - mctrl_gpio_enable_ms(up->gpios); - up->ier |= UART_IER_MSI; serial8250_rpm_get(up); @@ -1917,8 +1913,7 @@ unsigned int serial8250_do_get_mctrl(struct uart_port *port) ret |= TIOCM_DSR; if (status & UART_MSR_CTS) ret |= TIOCM_CTS; - - return mctrl_gpio_get(up->gpios, &ret); + return ret; } EXPORT_SYMBOL_GPL(serial8250_do_get_mctrl); diff --git a/drivers/tty/serial/8250/Kconfig b/drivers/tty/serial/8250/Kconfig index c9ec839a5ddf..7c6f7afca5dd 100644 --- a/drivers/tty/serial/8250/Kconfig +++ b/drivers/tty/serial/8250/Kconfig @@ -6,7 +6,6 @@ config SERIAL_8250 tristate "8250/16550 and compatible serial support" select SERIAL_CORE - select SERIAL_MCTRL_GPIO if GPIOLIB ---help--- This selects whether you want to include the driver for the standard serial ports. The standard answer is Y. People who might say N diff --git a/include/linux/serial_8250.h b/include/linux/serial_8250.h index 923266cd294a..48ec7651989b 100644 --- a/include/linux/serial_8250.h +++ b/include/linux/serial_8250.h @@ -111,7 +111,6 @@ struct uart_8250_port { * if no_console_suspend */ unsigned char probe; - struct mctrl_gpios *gpios; #define UART_PROBE_RSA (1 << 0) /* -- cgit v1.2.3-71-gd317 From cd81a9170e69e018bbaba547c1fd85a585f5697a Mon Sep 17 00:00:00 2001 From: Mateusz Guzik Date: Tue, 23 Aug 2016 16:20:38 +0200 Subject: mm: introduce get_task_exe_file For more convenient access if one has a pointer to the task. As a minor nit take advantage of the fact that only task lock + rcu are needed to safely grab ->exe_file. This saves mm refcount dance. Use the helper in proc_exe_link. Signed-off-by: Mateusz Guzik Acked-by: Konstantin Khlebnikov Acked-by: Richard Guy Briggs Cc: # 4.3.x Signed-off-by: Paul Moore --- fs/proc/base.c | 7 +------ include/linux/mm.h | 1 + kernel/fork.c | 23 +++++++++++++++++++++++ 3 files changed, 25 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/fs/proc/base.c b/fs/proc/base.c index 0d163a84082d..da8b1943ba04 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -1552,18 +1552,13 @@ static const struct file_operations proc_pid_set_comm_operations = { static int proc_exe_link(struct dentry *dentry, struct path *exe_path) { struct task_struct *task; - struct mm_struct *mm; struct file *exe_file; task = get_proc_task(d_inode(dentry)); if (!task) return -ENOENT; - mm = get_task_mm(task); + exe_file = get_task_exe_file(task); put_task_struct(task); - if (!mm) - return -ENOENT; - exe_file = get_mm_exe_file(mm); - mmput(mm); if (exe_file) { *exe_path = exe_file->f_path; path_get(&exe_file->f_path); diff --git a/include/linux/mm.h b/include/linux/mm.h index 8f468e0d2534..004c73a988b7 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1987,6 +1987,7 @@ extern void mm_drop_all_locks(struct mm_struct *mm); extern void set_mm_exe_file(struct mm_struct *mm, struct file *new_exe_file); extern struct file *get_mm_exe_file(struct mm_struct *mm); +extern struct file *get_task_exe_file(struct task_struct *task); extern bool may_expand_vm(struct mm_struct *, vm_flags_t, unsigned long npages); extern void vm_stat_account(struct mm_struct *, vm_flags_t, long npages); diff --git a/kernel/fork.c b/kernel/fork.c index d277e83ed3e0..42451aeb245f 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -773,6 +773,29 @@ struct file *get_mm_exe_file(struct mm_struct *mm) } EXPORT_SYMBOL(get_mm_exe_file); +/** + * get_task_exe_file - acquire a reference to the task's executable file + * + * Returns %NULL if task's mm (if any) has no associated executable file or + * this is a kernel thread with borrowed mm (see the comment above get_task_mm). + * User must release file via fput(). + */ +struct file *get_task_exe_file(struct task_struct *task) +{ + struct file *exe_file = NULL; + struct mm_struct *mm; + + task_lock(task); + mm = task->mm; + if (mm) { + if (!(task->flags & PF_KTHREAD)) + exe_file = get_mm_exe_file(mm); + } + task_unlock(task); + return exe_file; +} +EXPORT_SYMBOL(get_task_exe_file); + /** * get_task_mm - acquire a reference to the task's mm * -- cgit v1.2.3-71-gd317 From 2a3a2a3f35249412e35fbb48b743348c40373409 Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Thu, 1 Sep 2016 11:11:59 +0200 Subject: ovl: don't cache acl on overlay layer Some operations (setxattr/chmod) can make the cached acl stale. We either need to clear overlay's acl cache for the affected inode or prevent acl caching on the overlay altogether. Preventing caching has the following advantages: - no double caching, less memory used - overlay cache doesn't go stale when fs clears it's own cache Possible disadvantage is performance loss. If that becomes a problem get_acl() can be optimized for overlayfs. This patch disables caching by pre setting i_*acl to a value that - has bit 0 set, so is_uncached_acl() will return true - is not equal to ACL_NOT_CACHED, so get_acl() will not overwrite it The constant -3 was chosen for this purpose. Fixes: 39a25b2b3762 ("ovl: define ->get_acl() for overlay inodes") Signed-off-by: Miklos Szeredi --- fs/overlayfs/inode.c | 3 +++ include/linux/fs.h | 1 + 2 files changed, 4 insertions(+) (limited to 'include/linux') diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c index d50d1ead1b6f..47a4f33df47b 100644 --- a/fs/overlayfs/inode.c +++ b/fs/overlayfs/inode.c @@ -416,6 +416,9 @@ static void ovl_fill_inode(struct inode *inode, umode_t mode) inode->i_ino = get_next_ino(); inode->i_mode = mode; inode->i_flags |= S_NOCMTIME; +#ifdef CONFIG_FS_POSIX_ACL + inode->i_acl = inode->i_default_acl = ACL_DONT_CACHE; +#endif mode &= S_IFMT; switch (mode) { diff --git a/include/linux/fs.h b/include/linux/fs.h index 3523bf62f328..901e25d495cc 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -574,6 +574,7 @@ static inline void mapping_allow_writable(struct address_space *mapping) struct posix_acl; #define ACL_NOT_CACHED ((void *)(-1)) +#define ACL_DONT_CACHE ((void *)(-3)) static inline struct posix_acl * uncached_acl_sentinel(struct task_struct *task) -- cgit v1.2.3-71-gd317 From 6aa303defb7454a2520c4ddcdf6b081f62a15890 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Thu, 1 Sep 2016 16:14:55 -0700 Subject: mm, vmscan: only allocate and reclaim from zones with pages managed by the buddy allocator Firmware Assisted Dump (FA_DUMP) on ppc64 reserves substantial amounts of memory when booting a secondary kernel. Srikar Dronamraju reported that multiple nodes may have no memory managed by the buddy allocator but still return true for populated_zone(). Commit 1d82de618ddd ("mm, vmscan: make kswapd reclaim in terms of nodes") was reported to cause kswapd to spin at 100% CPU usage when fadump was enabled. The old code happened to deal with the situation of a populated node with zero free pages by co-incidence but the current code tries to reclaim populated zones without realising that is impossible. We cannot just convert populated_zone() as many existing users really need to check for present_pages. This patch introduces a managed_zone() helper and uses it in the few cases where it is critical that the check is made for managed pages -- zonelist construction and page reclaim. Link: http://lkml.kernel.org/r/20160831195104.GB8119@techsingularity.net Signed-off-by: Mel Gorman Reported-by: Srikar Dronamraju Tested-by: Srikar Dronamraju Acked-by: Michal Hocko Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 16 ++++++++++++++-- mm/page_alloc.c | 4 ++-- mm/vmscan.c | 22 +++++++++++----------- 3 files changed, 27 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index d572b78b65e1..7f2ae99e5daf 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -828,9 +828,21 @@ unsigned long __init node_memmap_size_bytes(int, unsigned long, unsigned long); */ #define zone_idx(zone) ((zone) - (zone)->zone_pgdat->node_zones) -static inline int populated_zone(struct zone *zone) +/* + * Returns true if a zone has pages managed by the buddy allocator. + * All the reclaim decisions have to use this function rather than + * populated_zone(). If the whole zone is reserved then we can easily + * end up with populated_zone() && !managed_zone(). + */ +static inline bool managed_zone(struct zone *zone) +{ + return zone->managed_pages; +} + +/* Returns true if a zone has memory */ +static inline bool populated_zone(struct zone *zone) { - return (!!zone->present_pages); + return zone->present_pages; } extern int movable_zone; diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 7791a03f8deb..a2214c64ed3c 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -4360,7 +4360,7 @@ static int build_zonelists_node(pg_data_t *pgdat, struct zonelist *zonelist, do { zone_type--; zone = pgdat->node_zones + zone_type; - if (populated_zone(zone)) { + if (managed_zone(zone)) { zoneref_set_zone(zone, &zonelist->_zonerefs[nr_zones++]); check_highest_zone(zone_type); @@ -4598,7 +4598,7 @@ static void build_zonelists_in_zone_order(pg_data_t *pgdat, int nr_nodes) for (j = 0; j < nr_nodes; j++) { node = node_order[j]; z = &NODE_DATA(node)->node_zones[zone_type]; - if (populated_zone(z)) { + if (managed_zone(z)) { zoneref_set_zone(z, &zonelist->_zonerefs[pos++]); check_highest_zone(zone_type); diff --git a/mm/vmscan.c b/mm/vmscan.c index 374d95d04178..b1e12a1ea9cf 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1665,7 +1665,7 @@ static bool inactive_reclaimable_pages(struct lruvec *lruvec, for (zid = sc->reclaim_idx; zid >= 0; zid--) { zone = &pgdat->node_zones[zid]; - if (!populated_zone(zone)) + if (!managed_zone(zone)) continue; if (zone_page_state_snapshot(zone, NR_ZONE_LRU_BASE + @@ -2036,7 +2036,7 @@ static bool inactive_list_is_low(struct lruvec *lruvec, bool file, struct zone *zone = &pgdat->node_zones[zid]; unsigned long inactive_zone, active_zone; - if (!populated_zone(zone)) + if (!managed_zone(zone)) continue; inactive_zone = zone_page_state(zone, @@ -2171,7 +2171,7 @@ static void get_scan_count(struct lruvec *lruvec, struct mem_cgroup *memcg, for (z = 0; z < MAX_NR_ZONES; z++) { struct zone *zone = &pgdat->node_zones[z]; - if (!populated_zone(zone)) + if (!managed_zone(zone)) continue; total_high_wmark += high_wmark_pages(zone); @@ -2510,7 +2510,7 @@ static inline bool should_continue_reclaim(struct pglist_data *pgdat, /* If compaction would go ahead or the allocation would succeed, stop */ for (z = 0; z <= sc->reclaim_idx; z++) { struct zone *zone = &pgdat->node_zones[z]; - if (!populated_zone(zone)) + if (!managed_zone(zone)) continue; switch (compaction_suitable(zone, sc->order, 0, sc->reclaim_idx)) { @@ -2840,7 +2840,7 @@ static bool pfmemalloc_watermark_ok(pg_data_t *pgdat) for (i = 0; i <= ZONE_NORMAL; i++) { zone = &pgdat->node_zones[i]; - if (!populated_zone(zone) || + if (!managed_zone(zone) || pgdat_reclaimable_pages(pgdat) == 0) continue; @@ -3141,7 +3141,7 @@ static bool prepare_kswapd_sleep(pg_data_t *pgdat, int order, int classzone_idx) for (i = 0; i <= classzone_idx; i++) { struct zone *zone = pgdat->node_zones + i; - if (!populated_zone(zone)) + if (!managed_zone(zone)) continue; if (!zone_balanced(zone, order, classzone_idx)) @@ -3169,7 +3169,7 @@ static bool kswapd_shrink_node(pg_data_t *pgdat, sc->nr_to_reclaim = 0; for (z = 0; z <= sc->reclaim_idx; z++) { zone = pgdat->node_zones + z; - if (!populated_zone(zone)) + if (!managed_zone(zone)) continue; sc->nr_to_reclaim += max(high_wmark_pages(zone), SWAP_CLUSTER_MAX); @@ -3242,7 +3242,7 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int classzone_idx) if (buffer_heads_over_limit) { for (i = MAX_NR_ZONES - 1; i >= 0; i--) { zone = pgdat->node_zones + i; - if (!populated_zone(zone)) + if (!managed_zone(zone)) continue; sc.reclaim_idx = i; @@ -3262,7 +3262,7 @@ static int balance_pgdat(pg_data_t *pgdat, int order, int classzone_idx) */ for (i = classzone_idx; i >= 0; i--) { zone = pgdat->node_zones + i; - if (!populated_zone(zone)) + if (!managed_zone(zone)) continue; if (zone_balanced(zone, sc.order, classzone_idx)) @@ -3508,7 +3508,7 @@ void wakeup_kswapd(struct zone *zone, int order, enum zone_type classzone_idx) pg_data_t *pgdat; int z; - if (!populated_zone(zone)) + if (!managed_zone(zone)) return; if (!cpuset_zone_allowed(zone, GFP_KERNEL | __GFP_HARDWALL)) @@ -3522,7 +3522,7 @@ void wakeup_kswapd(struct zone *zone, int order, enum zone_type classzone_idx) /* Only wake kswapd if all zones are unbalanced */ for (z = 0; z <= classzone_idx; z++) { zone = pgdat->node_zones + z; - if (!populated_zone(zone)) + if (!managed_zone(zone)) continue; if (zone_balanced(zone, order, classzone_idx)) -- cgit v1.2.3-71-gd317 From 7e932159901183283cd82d797bc9a7c681e48e9c Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Thu, 1 Sep 2016 16:15:01 -0700 Subject: treewide: remove references to the now unnecessary DEFINE_PCI_DEVICE_TABLE It's been eliminated from the sources, remove it from everywhere else. Link: http://lkml.kernel.org/r/076eff466fd7edb550c25c8b25d76924ca0eba62.1472660229.git.joe@perches.com Signed-off-by: Joe Perches Cc: "James E.J. Bottomley" Cc: "Martin K. Petersen" Cc: Bjorn Helgaas Cc: Andy Whitcroft Cc: Jonathan Corbet Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/PCI/pci.txt | 1 - include/linux/pci.h | 9 --------- scripts/checkpatch.pl | 9 --------- scripts/tags.sh | 1 - 4 files changed, 20 deletions(-) (limited to 'include/linux') diff --git a/Documentation/PCI/pci.txt b/Documentation/PCI/pci.txt index 123881f62219..77f49dc5be23 100644 --- a/Documentation/PCI/pci.txt +++ b/Documentation/PCI/pci.txt @@ -124,7 +124,6 @@ initialization with a pointer to a structure describing the driver The ID table is an array of struct pci_device_id entries ending with an all-zero entry. Definitions with static const are generally preferred. -Use of the deprecated macro DEFINE_PCI_DEVICE_TABLE should be avoided. Each entry consists of: diff --git a/include/linux/pci.h b/include/linux/pci.h index fbc1fa625c3e..0ab835965669 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -682,15 +682,6 @@ struct pci_driver { #define to_pci_driver(drv) container_of(drv, struct pci_driver, driver) -/** - * DEFINE_PCI_DEVICE_TABLE - macro used to describe a pci device table - * @_table: device table name - * - * This macro is deprecated and should not be used in new code. - */ -#define DEFINE_PCI_DEVICE_TABLE(_table) \ - const struct pci_device_id _table[] - /** * PCI_DEVICE - macro used to describe a specific pci device * @vend: the 16 bit PCI Vendor ID diff --git a/scripts/checkpatch.pl b/scripts/checkpatch.pl index 4de3cc42fc50..206a6b346a8d 100755 --- a/scripts/checkpatch.pl +++ b/scripts/checkpatch.pl @@ -3570,15 +3570,6 @@ sub process { } } -# check for uses of DEFINE_PCI_DEVICE_TABLE - if ($line =~ /\bDEFINE_PCI_DEVICE_TABLE\s*\(\s*(\w+)\s*\)\s*=/) { - if (WARN("DEFINE_PCI_DEVICE_TABLE", - "Prefer struct pci_device_id over deprecated DEFINE_PCI_DEVICE_TABLE\n" . $herecurr) && - $fix) { - $fixed[$fixlinenr] =~ s/\b(?:static\s+|)DEFINE_PCI_DEVICE_TABLE\s*\(\s*(\w+)\s*\)\s*=\s*/static const struct pci_device_id $1\[\] = /; - } - } - # check for new typedefs, only function parameters and sparse annotations # make sense. if ($line =~ /\btypedef\s/ && diff --git a/scripts/tags.sh b/scripts/tags.sh index ed7eef24ef89..b3775a9604ea 100755 --- a/scripts/tags.sh +++ b/scripts/tags.sh @@ -206,7 +206,6 @@ regex_c=( '/\ Date: Thu, 1 Sep 2016 16:15:07 -0700 Subject: mm, mempolicy: task->mempolicy must be NULL before dropping final reference KASAN allocates memory from the page allocator as part of kmem_cache_free(), and that can reference current->mempolicy through any number of allocation functions. It needs to be NULL'd out before the final reference is dropped to prevent a use-after-free bug: BUG: KASAN: use-after-free in alloc_pages_current+0x363/0x370 at addr ffff88010b48102c CPU: 0 PID: 15425 Comm: trinity-c2 Not tainted 4.8.0-rc2+ #140 ... Call Trace: dump_stack kasan_object_err kasan_report_error __asan_report_load2_noabort alloc_pages_current <-- use after free depot_save_stack save_stack kasan_slab_free kmem_cache_free __mpol_put <-- free do_exit This patch sets current->mempolicy to NULL before dropping the final reference. Link: http://lkml.kernel.org/r/alpine.DEB.2.10.1608301442180.63329@chino.kir.corp.google.com Fixes: cd11016e5f52 ("mm, kasan: stackdepot implementation. Enable stackdepot for SLAB") Signed-off-by: David Rientjes Reported-by: Vegard Nossum Acked-by: Andrey Ryabinin Cc: Alexander Potapenko Cc: Dmitry Vyukov Cc: [4.6+] Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mempolicy.h | 4 ++++ kernel/exit.c | 7 +------ mm/mempolicy.c | 17 +++++++++++++++++ 3 files changed, 22 insertions(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h index 4429d255c8ab..5e5b2969d931 100644 --- a/include/linux/mempolicy.h +++ b/include/linux/mempolicy.h @@ -195,6 +195,7 @@ static inline bool vma_migratable(struct vm_area_struct *vma) } extern int mpol_misplaced(struct page *, struct vm_area_struct *, unsigned long); +extern void mpol_put_task_policy(struct task_struct *); #else @@ -297,5 +298,8 @@ static inline int mpol_misplaced(struct page *page, struct vm_area_struct *vma, return -1; /* no node preference */ } +static inline void mpol_put_task_policy(struct task_struct *task) +{ +} #endif /* CONFIG_NUMA */ #endif diff --git a/kernel/exit.c b/kernel/exit.c index 2f974ae042a6..091a78be3b09 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -848,12 +848,7 @@ void do_exit(long code) TASKS_RCU(preempt_enable()); exit_notify(tsk, group_dead); proc_exit_connector(tsk); -#ifdef CONFIG_NUMA - task_lock(tsk); - mpol_put(tsk->mempolicy); - tsk->mempolicy = NULL; - task_unlock(tsk); -#endif + mpol_put_task_policy(tsk); #ifdef CONFIG_FUTEX if (unlikely(current->pi_state_cache)) kfree(current->pi_state_cache); diff --git a/mm/mempolicy.c b/mm/mempolicy.c index d8c4e38fb5f4..2da72a5b6ecc 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -2336,6 +2336,23 @@ out: return ret; } +/* + * Drop the (possibly final) reference to task->mempolicy. It needs to be + * dropped after task->mempolicy is set to NULL so that any allocation done as + * part of its kmem_cache_free(), such as by KASAN, doesn't reference a freed + * policy. + */ +void mpol_put_task_policy(struct task_struct *task) +{ + struct mempolicy *pol; + + task_lock(task); + pol = task->mempolicy; + task->mempolicy = NULL; + task_unlock(task); + mpol_put(pol); +} + static void sp_delete(struct shared_policy *sp, struct sp_node *n) { pr_debug("deleting %lx-l%lx\n", n->start, n->end); -- cgit v1.2.3-71-gd317 From 3feab13c919f99b0a17d0ca22ae00cf90f5d3fd1 Mon Sep 17 00:00:00 2001 From: Lorenzo Pieralisi Date: Tue, 16 Aug 2016 16:59:52 +0100 Subject: ACPI / drivers: fix typo in ACPI_DECLARE_PROBE_ENTRY macro When the ACPI_DECLARE_PROBE_ENTRY macro was added in commit e647b532275b ("ACPI: Add early device probing infrastructure"), a stub macro adding an unused entry was added for the !CONFIG_ACPI Kconfig option case to make sure kernel code making use of the macro did not require to be guarded within CONFIG_ACPI in order to be compiled. The stub macro was never used since all kernel code that defines ACPI_DECLARE_PROBE_ENTRY entries is currently guarded within CONFIG_ACPI; it contains a typo that should be nonetheless fixed. Fix the typo in the stub (ie !CONFIG_ACPI) ACPI_DECLARE_PROBE_ENTRY() macro so that it can actually be used if needed. Signed-off-by: Lorenzo Pieralisi Fixes: e647b532275b (ACPI: Add early device probing infrastructure) Cc: 4.4+ # 4.4+ Signed-off-by: Rafael J. Wysocki --- include/linux/acpi.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 4d8452c2384b..c5eaf2f80a4c 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -1056,7 +1056,7 @@ static inline struct fwnode_handle *acpi_get_next_subnode(struct device *dev, return NULL; } -#define ACPI_DECLARE_PROBE_ENTRY(table, name, table_id, subtable, validate, data, fn) \ +#define ACPI_DECLARE_PROBE_ENTRY(table, name, table_id, subtable, valid, data, fn) \ static const void * __acpi_table_##name[] \ __attribute__((unused)) \ = { (void *) table_id, \ -- cgit v1.2.3-71-gd317