- Kernel - mailweb.openeuler.org

[PATCH openEuler-1.0-LTS 1/6] vfs: add rcu argument to ->get_acl() callback
by Yongqiang Liu 28 Apr '23

28 Apr '23

From: Miklos Szeredi <mszeredi(a)redhat.com> mainline inclusion from mainline-v5.15-rc1 commit 0cad6246621b5887d5b33fea84219d2a71f2f99a category: perf bugzilla: https://gitee.com/openeuler/kernel/issues/I6ZCW0 CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- Add a rcu argument to the ->get_acl() callback to allow get_cached_acl_rcu() to call the ->get_acl() method in the next patch. Signed-off-by: Miklos Szeredi <mszeredi(a)redhat.com> [chengzhihao: rename get_acl to get_acl2 to prevent KABI changes, and only backport(realize) overlayfs] Conflicts: fs/overlayfs/dir.c fs/overlayfs/inode.c fs/overlayfs/overlayfs.h fs/posix_acl.c include/linux/fs.h Signed-off-by: Zhihao Cheng <chengzhihao1(a)huawei.com> Reviewed-by: Zhang Yi <yi.zhang(a)huawei.com> Signed-off-by: Yongqiang Liu <liuyongqiang13(a)huawei.com> --- fs/overlayfs/dir.c | 2 +- fs/overlayfs/inode.c | 9 ++++++--- fs/overlayfs/overlayfs.h | 2 +- fs/posix_acl.c | 7 +++++-- include/linux/fs.h | 1 + 5 files changed, 14 insertions(+), 7 deletions(-) diff --git a/fs/overlayfs/dir.c b/fs/overlayfs/dir.c index 8570e755a392..cdbb916aa636 100644 --- a/fs/overlayfs/dir.c +++ b/fs/overlayfs/dir.c @@ -1292,6 +1292,6 @@ const struct inode_operations ovl_dir_inode_operations = { .permission = ovl_permission, .getattr = ovl_getattr, .listxattr = ovl_listxattr, - .get_acl = ovl_get_acl, + .get_acl2 = ovl_get_acl, .update_time = ovl_update_time, }; diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c index 3eabe457a5d5..3aa33c18cb80 100644 --- a/fs/overlayfs/inode.c +++ b/fs/overlayfs/inode.c @@ -421,12 +421,15 @@ ssize_t ovl_listxattr(struct dentry *dentry, char *list, size_t size) return res; } -struct posix_acl *ovl_get_acl(struct inode *inode, int type) +struct posix_acl *ovl_get_acl(struct inode *inode, int type, bool rcu) { struct inode *realinode = ovl_inode_real(inode); const struct cred *old_cred; struct posix_acl *acl; + if (rcu) + return ERR_PTR(-ECHILD); + if (!IS_ENABLED(CONFIG_FS_POSIX_ACL) || !IS_POSIXACL(realinode)) return NULL; @@ -480,7 +483,7 @@ static const struct inode_operations ovl_file_inode_operations = { .permission = ovl_permission, .getattr = ovl_getattr, .listxattr = ovl_listxattr, - .get_acl = ovl_get_acl, + .get_acl2 = ovl_get_acl, .update_time = ovl_update_time, .fiemap = ovl_fiemap, }; @@ -498,7 +501,7 @@ static const struct inode_operations ovl_special_inode_operations = { .permission = ovl_permission, .getattr = ovl_getattr, .listxattr = ovl_listxattr, - .get_acl = ovl_get_acl, + .get_acl2 = ovl_get_acl, .update_time = ovl_update_time, }; diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h index 76e096ad2ef9..38fada5fa552 100644 --- a/fs/overlayfs/overlayfs.h +++ b/fs/overlayfs/overlayfs.h @@ -358,7 +358,7 @@ int ovl_xattr_set(struct dentry *dentry, struct inode *inode, const char *name, int ovl_xattr_get(struct dentry *dentry, struct inode *inode, const char *name, void *value, size_t size); ssize_t ovl_listxattr(struct dentry *dentry, char *list, size_t size); -struct posix_acl *ovl_get_acl(struct inode *inode, int type); +struct posix_acl *ovl_get_acl(struct inode *inode, int type, bool rcu); int ovl_update_time(struct inode *inode, struct timespec64 *ts, int flags); bool ovl_is_private_xattr(const char *name); diff --git a/fs/posix_acl.c b/fs/posix_acl.c index 2fd0fde16fe1..8e3fe9cbb28c 100644 --- a/fs/posix_acl.c +++ b/fs/posix_acl.c @@ -133,11 +133,14 @@ struct posix_acl *get_acl(struct inode *inode, int type) * If the filesystem doesn't have a get_acl() function at all, we'll * just create the negative cache entry. */ - if (!inode->i_op->get_acl) { + if (!inode->i_op->get_acl && !inode->i_op->get_acl2) { set_cached_acl(inode, type, NULL); return NULL; } - acl = inode->i_op->get_acl(inode, type); + if (inode->i_op->get_acl) + acl = inode->i_op->get_acl(inode, type); + else + acl = inode->i_op->get_acl2(inode, type, false); if (IS_ERR(acl)) { /* diff --git a/include/linux/fs.h b/include/linux/fs.h index 6363c0a67af5..bd3e09a3c9a9 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1838,6 +1838,7 @@ struct inode_operations { const char * (*get_link) (struct dentry *, struct inode *, struct delayed_call *); int (*permission) (struct inode *, int); struct posix_acl * (*get_acl)(struct inode *, int); + struct posix_acl * (*get_acl2)(struct inode *, int, bool); int (*readlink) (struct dentry *, char __user *,int); -- 2.25.1

1 5

[PATCH OLK-5.10 1/1] scsi: hisi_sas: Configure the initialization registers according to HBA model
by Yihang Li 28 Apr '23

28 Apr '23

driver inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I6ZGK8 CVE: NA ---------------------------------------------------------------------- We use init_reg_v3_hw() to set some registers, for the latest HBA devices, some of these HW registers are set through firmware. Therefore, different HBA models are distinguished through pci_dev->revision. Signed-off-by: Yihang Li <liyihang9(a)huawei.com> Reviewed-by: Xiang Chen <chenxiang66(a)hisilicon.com> Signed-off-by: xiabing <xiabing12(a)h-partners.com> --- drivers/scsi/hisi_sas/hisi_sas_v3_hw.c | 17 ++++++++++++----- 1 file changed, 12 insertions(+), 5 deletions(-) diff --git a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c index eeb40ad079c8..6e40c4c06650 100644 --- a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c +++ b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c @@ -617,12 +617,12 @@ static void interrupt_enable_v3_hw(struct hisi_hba *hisi_hba) static void init_reg_v3_hw(struct hisi_hba *hisi_hba) { + struct pci_dev *pdev = hisi_hba->pci_dev; int i, j; /* Global registers init */ hisi_sas_write32(hisi_hba, DLVRY_QUEUE_ENABLE, (u32)((1ULL << hisi_hba->queue_count) - 1)); - hisi_sas_write32(hisi_hba, SAS_AXI_USER3, 0); hisi_sas_write32(hisi_hba, CFG_MAX_TAG, 0xfff0400); hisi_sas_write32(hisi_hba, HGC_SAS_TXFAIL_RETRY_CTRL, 0x108); hisi_sas_write32(hisi_hba, CFG_AGING_TIME, 0x1); @@ -642,6 +642,9 @@ static void init_reg_v3_hw(struct hisi_hba *hisi_hba) hisi_sas_write32(hisi_hba, ARQOS_ARCACHE_CFG, 0xf0f0); hisi_sas_write32(hisi_hba, HYPER_STREAM_ID_EN_CFG, 1); + if (pdev->revision < 0x30) + hisi_sas_write32(hisi_hba, SAS_AXI_USER3, 0); + interrupt_enable_v3_hw(hisi_hba); for (i = 0; i < hisi_hba->n_phy; i++) { enum sas_linkrate max; @@ -659,7 +662,6 @@ static void init_reg_v3_hw(struct hisi_hba *hisi_hba) prog_phy_link_rate |= hisi_sas_get_prog_phy_linkrate_mask(max); hisi_sas_phy_write32(hisi_hba, i, PROG_PHY_LINK_RATE, prog_phy_link_rate); - hisi_sas_phy_write32(hisi_hba, i, SERDES_CFG, 0xffc00); hisi_sas_phy_write32(hisi_hba, i, SAS_RX_TRAIN_TIMER, 0x13e80); hisi_sas_phy_write32(hisi_hba, i, CHL_INT0, 0xffffffff); hisi_sas_phy_write32(hisi_hba, i, CHL_INT1, 0xffffffff); @@ -670,13 +672,18 @@ static void init_reg_v3_hw(struct hisi_hba *hisi_hba) hisi_sas_phy_write32(hisi_hba, i, PHYCTRL_OOB_RESTART_MSK, 0x1); hisi_sas_phy_write32(hisi_hba, i, STP_LINK_TIMER, 0x7f7a120); hisi_sas_phy_write32(hisi_hba, i, CON_CFG_DRIVER, 0x2a0a01); - hisi_sas_phy_write32(hisi_hba, i, SAS_SSP_CON_TIMER_CFG, 0x32); hisi_sas_phy_write32(hisi_hba, i, SAS_EC_INT_COAL_TIME, 0x30f4240); - /* used for 12G negotiate */ - hisi_sas_phy_write32(hisi_hba, i, COARSETUNE_TIME, 0x1e); hisi_sas_phy_write32(hisi_hba, i, AIP_LIMIT, 0x2ffff); + /* set value through firmware for the latest HBA */ + if (pdev->revision < 0x30) { + hisi_sas_phy_write32(hisi_hba, i, SAS_SSP_CON_TIMER_CFG, 0x32); + hisi_sas_phy_write32(hisi_hba, i, SERDES_CFG, 0xffc00); + /* used for 12G negotiate */ + hisi_sas_phy_write32(hisi_hba, i, COARSETUNE_TIME, 0x1e); + } + /* get default FFE configuration for BIST */ for (j = 0; j < FFE_CFG_MAX; j++) { u32 val = hisi_sas_phy_read32(hisi_hba, i, -- 2.30.0

1 0

[PATCH OLK-5.10 0/3] Introduce QOS_SMT_EXPELL priority reversion mechanism
by Hui Tang 28 Apr '23

28 Apr '23

From: Guan Jing <guanjing6(a)huawei.com> Guan Jing (3): sched/fair: Start tracking qos_offline tasks count in cfs_rq sched/fair: Introduce QOS_SMT_EXPELL priority reversion mechanism sched/fair: Add cmdline nosmtexpell kernel/sched/fair.c | 150 +++++++++++++++++++++++++++++++++++++------ kernel/sched/sched.h | 20 ++++++ 2 files changed, 152 insertions(+), 18 deletions(-) -- 2.17.1

1 3

[OLK-5.10 v3 00/16] bugfix for bonding
by Chengchang Tang 27 Apr '23

27 Apr '23

From: Juan Zhou <zhoujuan51(a)h-partners.com> This group of patches fix bonding-related errors. Junxian Huang (16): RDMA/hns: Move bond_work from hns_roce_dev to hns_roce_bond_group RDMA/hns: Apply XArray for Bond ID allocation RDMA/hns: Delete a useless assignment to bond_state RDMA/hns: Initial value assignment cleanup for RoCE Bonding variables RDMA/hns: Remove the struct member 'bond_grp' from hns_roce_dev RDMA/hns: Simplify the slave uninit logic of RoCE bonding operations RDMA/hns: Fix the driver uninit order during bond setting RDMA/hns: Fix the counting error of slave number RDMA/hns: Support reset recovery for RoCE bonding RDMA/hns: Rename hns_roce_bond_info_record() to make sense RDMA/hns: Fix the repetitive workqueue mission in RoCE Bonding RDMA/hns: Fix the counting error of bonding with more than 2 slaves RDMA/hns: Get real-time port state of bonding slave RDMA/hns: Set IB port state depending on upper device for RoCE bonding RDMA/hns: Support dispatching IB event for RoCE bonding RDMA/hns: Fix a missing constraint for slave num in RoCE Bonding drivers/infiniband/hw/hns/hns_roce_bond.c | 540 +++++++++++--------- drivers/infiniband/hw/hns/hns_roce_bond.h | 15 +- drivers/infiniband/hw/hns/hns_roce_device.h | 5 +- drivers/infiniband/hw/hns/hns_roce_hw_v2.c | 79 ++- drivers/infiniband/hw/hns/hns_roce_hw_v2.h | 10 +- drivers/infiniband/hw/hns/hns_roce_main.c | 58 ++- 6 files changed, 421 insertions(+), 286 deletions(-) -- 2.30.0

1 17

[OLK-5.10 v2 0/2] bugfix for rq inline
by Chengchang Tang 27 Apr '23

27 Apr '23

From: Juan Zhou <zhoujuan51(a)h-partners.com> Luoyouming (2): RDMA/hns: Fix the inconsistency between the rq inline bit and the community RDMA/hns: Fix the compatibility flag problem drivers/infiniband/hw/hns/hns_roce_device.h | 4 +--- drivers/infiniband/hw/hns/hns_roce_main.c | 6 ++++-- 2 files changed, 5 insertions(+), 5 deletions(-) -- 2.30.0

1 2

[PATCH OLK-5.10 v2] net: hns3: add support handling tx dhcp packets for ROH
by Ke Chen 27 Apr '23

27 Apr '23

driver inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I6BSMN ----------------------------------------------------------------------- For ROH distributed scenario, EID is allocated by DHCP mode. Driver needs to convert the origin MAC address to EID format, and updates the destination MAC, chaddr and client id(if exists) when transmit DHCP packets. Meantime, the chaddr field should follow the source mac address, in order to make the dhcp server reply to the right client. For the payload of dhcp packet changed, so the checksum of L4 should be calculated too. Signed-off-by: Jian Shen <shenjian15(a)huawei.com> Signed-off-by: Ke Chen <chenke54(a)huawei.com> --- .../net/ethernet/hisilicon/hns3/hns3_enet.c | 174 +++++++++++++++++- .../net/ethernet/hisilicon/hns3/hns3_enet.h | 50 +++++ .../hisilicon/hns3/hns3pf/hclge_main.c | 16 ++ 3 files changed, 235 insertions(+), 5 deletions(-) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c index cf79cd69c..95cd61b1f 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c @@ -1165,6 +1165,142 @@ static void hns3_tx_spare_reclaim_cb(struct hns3_enet_ring *ring, } } +static struct hns3_dhcp_packet *hns3_get_dhcp_packet(struct sk_buff *skb, + int *dhcp_len) +{ + struct hns3_dhcp_packet *dhcp; + union l4_hdr_info l4; + int l4_payload_len; + + l4.hdr = skb_transport_header(skb); + if (l4.udp->dest != htons(HNS3_DHCP_CLIENT_PORT) || + l4.udp->source != htons(HNS3_DHCP_SERVER_PORT)) + return NULL; + + dhcp = (struct hns3_dhcp_packet *)(l4.hdr + sizeof(struct udphdr)); + l4_payload_len = ntohs(l4.udp->len) - sizeof(struct udphdr); + if (l4_payload_len < offsetof(struct hns3_dhcp_packet, options) || + dhcp->hlen != ETH_ALEN || + dhcp->cookie != htonl(HNS3_DHCP_MAGIC)) + return NULL; + + *dhcp_len = l4_payload_len; + return dhcp; +} + +static u8 *hns3_dhcp_option_scan(struct hns3_dhcp_packet *packet, + struct hns3_dhcp_opt_state *opt_state) +{ + int opt_len; + u8 *cur_opt; + + /* option bytes: [code][len][data0~data[len-1]] */ + while (opt_state->rem > 0) { + switch (opt_state->opt_ptr[DHCP_OPT_CODE]) { + /* option padding and end have no len and data byte. */ + case DHCP_OPT_PADDING: + opt_state->rem--; + opt_state->opt_ptr++; + break; + case DHCP_OPT_END: + if (DHCP_OVERLOAD_USE_FILE(opt_state->overload_flag)) { + opt_state->overload_flag |= + DHCP_OVERLOAD_FILE_USED; + opt_state->opt_ptr = packet->file; + opt_state->rem = sizeof(packet->file); + break; + } + if (DHCP_OVERLOAD_USE_SNAME(opt_state->overload_flag)) { + opt_state->overload_flag |= + DHCP_OVERLOAD_SNAME_USED; + opt_state->opt_ptr = packet->sname; + opt_state->rem = sizeof(packet->sname); + break; + } + return NULL; + default: + if (opt_state->rem <= DHCP_OPT_LEN) + return NULL; + /* opt_len includes code, len and data bytes */ + opt_len = opt_state->opt_ptr[DHCP_OPT_LEN] + + DHCP_OPT_DATA; + cur_opt = opt_state->opt_ptr; + if (opt_state->rem < opt_len) + return NULL; + + opt_state->opt_ptr += opt_len; + opt_state->rem -= opt_len; + if (cur_opt[DHCP_OPT_CODE] == DHCP_OPT_OVERLOAD) { + opt_state->overload_flag |= + cur_opt[DHCP_OPT_DATA]; + break; + } + return cur_opt; + } + } + + return NULL; +} + +static void hns3_dhcp_update_option61(struct hns3_nic_priv *priv, + struct hns3_dhcp_packet *packet, + int dhcp_len) +{ + struct hns3_dhcp_opt_state opt_state; + u8 *cur_opt; + + opt_state.opt_ptr = packet->options; + opt_state.rem = dhcp_len - offsetof(struct hns3_dhcp_packet, options); + opt_state.overload_flag = 0; + + cur_opt = hns3_dhcp_option_scan(packet, &opt_state); + while (cur_opt) { + if (cur_opt[DHCP_OPT_CODE] != DHCP_OPT_CLIENT_ID) { + cur_opt = hns3_dhcp_option_scan(packet, &opt_state); + continue; + } + if (cur_opt[DHCP_OPT_LEN] > ETH_ALEN) + ether_addr_copy(&cur_opt[DHCP_CLIENT_ID_MAC_OFT], + priv->roh_perm_mac); + break; + } +} + +static void hns3_dhcp_cal_l4_csum(struct sk_buff *skb) +{ + union l3_hdr_info l3; + union l4_hdr_info l4; + __wsum csum = 0; + int offset; + + if (skb->ip_summed == CHECKSUM_PARTIAL) + return; + + l3.hdr = skb_network_header(skb); + l4.hdr = skb_transport_header(skb); + offset = skb_transport_offset(skb); + l4.udp->check = 0; + csum = csum_partial(l4.udp, ntohs(l4.udp->len), 0); + l4.udp->check = csum_tcpudp_magic(l3.v4->saddr, l3.v4->daddr, + skb->len - offset, IPPROTO_UDP, csum); +} + +static void hns3_dhcp_packet_convert(struct hns3_nic_priv *priv, + struct sk_buff *skb, + struct hns3_dhcp_packet *dhcp, + int dhcp_len) +{ + struct ethhdr *l2hdr = eth_hdr(skb); + + if (!dhcp) + return; + + ether_addr_copy(dhcp->chaddr, l2hdr->h_source); + hns3_dhcp_update_option61(priv, dhcp, dhcp_len); + /* for l4 payload changed, need to re-calculate the csum */ + hns3_dhcp_cal_l4_csum(skb); +} + static int hns3_set_tso(struct sk_buff *skb, u32 *paylen_fdop_ol4cs, u16 *mss, u32 *type_cs_vlan_tso, u32 *send_bytes) { @@ -1716,7 +1852,20 @@ static int hns3_handle_csum_partial(struct hns3_enet_ring *ring, return 0; } -static int hns3_fill_skb_desc(struct hns3_enet_ring *ring, +static bool hns3_roh_check_udpv4(struct sk_buff *skb) +{ + union l3_hdr_info l3; + + l3.hdr = skb_network_header(skb); + if (skb->protocol != htons(ETH_P_IP) || + l3.v4->version != IP_VERSION_IPV4) + return false; + + return l3.v4->protocol == IPPROTO_UDP; +} + +static int hns3_fill_skb_desc(struct hns3_nic_priv *priv, + struct hns3_enet_ring *ring, struct sk_buff *skb, struct hns3_desc *desc, struct hns3_desc_cb *desc_cb) { @@ -1741,6 +1890,15 @@ static int hns3_fill_skb_desc(struct hns3_enet_ring *ring, hnae3_set_field(param.paylen_fdop_ol4cs, HNS3_TXD_FD_OP_M, HNS3_TXD_FD_OP_S, fd_op); + if (hnae3_check_roh_mac_type(priv->ae_handle) && + hns3_roh_check_udpv4(skb)) { + struct hns3_dhcp_packet *dhcp; + int dhcp_len; + + dhcp = hns3_get_dhcp_packet(skb, &dhcp_len); + hns3_dhcp_packet_convert(priv, skb, dhcp, dhcp_len); + } + /* Set txbd */ desc->tx.ol_type_vlan_len_msec = cpu_to_le32(param.ol_type_vlan_len_msec); @@ -2338,15 +2496,16 @@ static int hns3_handle_desc_filling(struct hns3_enet_ring *ring, return hns3_fill_skb_to_desc(ring, skb, DESC_TYPE_SKB); } -static int hns3_handle_skb_desc(struct hns3_enet_ring *ring, +static int hns3_handle_skb_desc(struct hns3_nic_priv *priv, + struct hns3_enet_ring *ring, struct sk_buff *skb, struct hns3_desc_cb *desc_cb, int next_to_use_head) { int ret; - ret = hns3_fill_skb_desc(ring, skb, &ring->desc[ring->next_to_use], - desc_cb); + ret = hns3_fill_skb_desc(priv, ring, skb, + &ring->desc[ring->next_to_use], desc_cb); if (unlikely(ret < 0)) goto fill_err; @@ -2395,7 +2554,7 @@ netdev_tx_t hns3_nic_net_xmit(struct sk_buff *skb, struct net_device *netdev) goto out_err_tx_ok; } - ret = hns3_handle_skb_desc(ring, skb, desc_cb, ring->next_to_use); + ret = hns3_handle_skb_desc(priv, ring, skb, desc_cb, ring->next_to_use); if (unlikely(ret <= 0)) goto out_err_tx_ok; @@ -5226,6 +5385,10 @@ static int hns3_init_mac_addr(struct net_device *netdev) return 0; } + if (hnae3_check_roh_mac_type(h) && + is_zero_ether_addr(priv->roh_perm_mac)) + ether_addr_copy(priv->roh_perm_mac, netdev->dev_addr); + if (h->ae_algo->ops->set_mac_addr) ret = h->ae_algo->ops->set_mac_addr(h, netdev->dev_addr, true); @@ -5377,6 +5540,7 @@ static int hns3_client_init(struct hnae3_handle *handle) priv->tx_timeout_count = 0; priv->max_non_tso_bd_num = ae_dev->dev_specs.max_non_tso_bd_num; set_bit(HNS3_NIC_STATE_DOWN, &priv->state); + eth_zero_addr(priv->roh_perm_mac); handle->msg_enable = netif_msg_init(debug, DEFAULT_MSG_LEVEL); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h index ccfd38b00..85c352fff 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h @@ -604,6 +604,56 @@ struct hns3_nic_priv { struct hns3_enet_coalesce rx_coal; u32 tx_copybreak; u32 rx_copybreak; + u8 roh_perm_mac[ETH_ALEN]; +}; + +#define HNS3_DHCP_SERVER_PORT 68 +#define HNS3_DHCP_CLIENT_PORT 67 +#define HNS3_DHCP_MAGIC 0x63825363 +#define DHCP_OPT_CODE 0 +#define DHCP_OPT_LEN 1 +#define DHCP_OPT_DATA 2 +#define DHCP_CLIENT_ID_LEN 7 +#define DHCP_CLIENT_ID_MAC_OFT 3 +#define DHCP_OVERLOAD_FILE 0x1 +#define DHCP_OVERLOAD_SNAME 0x2 +#define DHCP_OVERLOAD_FILE_USED 0x101 +#define DHCP_OVERLOAD_SNAME_USED 0x202 +#define DHCP_OVERLOAD_USE_FILE(x) \ + (((x) & DHCP_OVERLOAD_FILE_USED) == DHCP_OVERLOAD_FILE) +#define DHCP_OVERLOAD_USE_SNAME(x) \ + (((x) & DHCP_OVERLOAD_SNAME_USED) == DHCP_OVERLOAD_SNAME) + +enum DHCP_OPTION_CODES { + DHCP_OPT_PADDING = 0, + DHCP_OPT_OVERLOAD = 52, + DHCP_OPT_CLIENT_ID = 61, + DHCP_OPT_END = 255 +}; + +struct hns3_dhcp_packet { + u8 op; + u8 htype; + u8 hlen; + u8 hops; + u32 xid; + u16 secs; + u16 flags; + u32 ciaddr; + u32 yiaddr; + u32 siaddr_nip; + u32 gateway_nip; + u8 chaddr[16]; /* link-layer client hardware address (MAC) */ + u8 sname[64]; + u8 file[128]; + u32 cookie; /* DHCP magic bytes: 0x63825363 */ + u8 options[312]; +}; + +struct hns3_dhcp_opt_state { + u8 *opt_ptr; /* refer to current option item */ + int rem; /* remain bytes in options */ + u32 overload_flag; /* whether use file and sname field as options */ }; union l3_hdr_info { diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index eea175484..947ffde02 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -2866,12 +2866,28 @@ static void hclge_get_fec(struct hnae3_handle *handle, u8 *fec_ability, if (fec_mode) *fec_mode = mac->fec_mode; } + +static void hclge_roh_convert_mac_addr(struct hclge_dev *hdev) +{ +#define HCLGE_ROH_EID_MASK_BYTE 3 + + struct hclge_vport *vport = &hdev->vport[0]; + struct hnae3_handle *handle = &vport->nic; + + if (hnae3_check_roh_mac_type(handle)) { + if (!is_valid_ether_addr(hdev->hw.mac.mac_addr)) + random_ether_addr(hdev->hw.mac.mac_addr); + memset(hdev->hw.mac.mac_addr, 0, HCLGE_ROH_EID_MASK_BYTE); + } +} + static int hclge_mac_init(struct hclge_dev *hdev) { struct hclge_mac *mac = &hdev->hw.mac; int ret; hclge_mac_type_init(hdev); + hclge_roh_convert_mac_addr(hdev); hdev->support_sfp_query = true; hdev->hw.mac.duplex = HCLGE_MAC_FULL; -- 2.30.0

1 0

[PATCH openEuler-5.10-LTS 01/20] io_uring: add missing lock in io_get_file_fixed
by Jialin Zhang 26 Apr '23

26 Apr '23

From: Bing-Jhong Billy Jheng <billy(a)starlabs.sg> stable inclusion from stable-v5.10.171 commit 08681391b84da27133deefaaddefd0acfa90c2be category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I6V7V1 CVE: CVE-2023-1872 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- io_get_file_fixed will access io_uring's context. Lock it if it is invoked unlocked (eg via io-wq) to avoid a race condition with fixed files getting unregistered. No single upstream patch exists for this issue, it was fixed as part of the file assignment changes that went into the 5.18 cycle. Signed-off-by: Jheng, Bing-Jhong Billy <billy(a)starlabs.sg> Signed-off-by: Jens Axboe <axboe(a)kernel.dk> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: ZhaoLong Wang <wangzhaolong1(a)huawei.com> Reviewed-by: Zhang Yi <yi.zhang(a)huawei.com> Reviewed-by: Xiu Jianfeng <xiujianfeng(a)huawei.com> Signed-off-by: Jialin Zhang <zhangjialin11(a)huawei.com> --- io_uring/io_uring.c | 25 ++++++++++++++++--------- 1 file changed, 16 insertions(+), 9 deletions(-) diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index a200750b536c..98cf1c413691 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -1090,7 +1090,8 @@ static int __io_register_rsrc_update(struct io_ring_ctx *ctx, unsigned type, unsigned nr_args); static void io_clean_op(struct io_kiocb *req); static struct file *io_file_get(struct io_ring_ctx *ctx, - struct io_kiocb *req, int fd, bool fixed); + struct io_kiocb *req, int fd, bool fixed, + unsigned int issue_flags); static void __io_queue_sqe(struct io_kiocb *req); static void io_rsrc_put_work(struct work_struct *work); @@ -3914,7 +3915,7 @@ static int io_tee(struct io_kiocb *req, unsigned int issue_flags) return -EAGAIN; in = io_file_get(req->ctx, req, sp->splice_fd_in, - (sp->flags & SPLICE_F_FD_IN_FIXED)); + (sp->flags & SPLICE_F_FD_IN_FIXED), issue_flags); if (!in) { ret = -EBADF; goto done; @@ -3954,7 +3955,7 @@ static int io_splice(struct io_kiocb *req, unsigned int issue_flags) return -EAGAIN; in = io_file_get(req->ctx, req, sp->splice_fd_in, - (sp->flags & SPLICE_F_FD_IN_FIXED)); + (sp->flags & SPLICE_F_FD_IN_FIXED), issue_flags); if (!in) { ret = -EBADF; goto done; @@ -6742,13 +6743,16 @@ static void io_fixed_file_set(struct io_fixed_file *file_slot, struct file *file } static inline struct file *io_file_get_fixed(struct io_ring_ctx *ctx, - struct io_kiocb *req, int fd) + struct io_kiocb *req, int fd, + unsigned int issue_flags) { - struct file *file; + struct file *file = NULL; unsigned long file_ptr; + io_ring_submit_lock(ctx, !(issue_flags & IO_URING_F_NONBLOCK)); + if (unlikely((unsigned int)fd >= ctx->nr_user_files)) - return NULL; + goto out; fd = array_index_nospec(fd, ctx->nr_user_files); file_ptr = io_fixed_file_slot(&ctx->file_table, fd)->file_ptr; file = (struct file *) (file_ptr & FFS_MASK); @@ -6756,6 +6760,8 @@ static inline struct file *io_file_get_fixed(struct io_ring_ctx *ctx, /* mask in overlapping REQ_F and FFS bits */ req->flags |= (file_ptr << REQ_F_NOWAIT_READ_BIT); io_req_set_rsrc_node(req); +out: + io_ring_submit_unlock(ctx, !(issue_flags & IO_URING_F_NONBLOCK)); return file; } @@ -6773,10 +6779,11 @@ static struct file *io_file_get_normal(struct io_ring_ctx *ctx, } static inline struct file *io_file_get(struct io_ring_ctx *ctx, - struct io_kiocb *req, int fd, bool fixed) + struct io_kiocb *req, int fd, bool fixed, + unsigned int issue_flags) { if (fixed) - return io_file_get_fixed(ctx, req, fd); + return io_file_get_fixed(ctx, req, fd, issue_flags); else return io_file_get_normal(ctx, req, fd); } @@ -6998,7 +7005,7 @@ static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req, if (io_op_defs[req->opcode].needs_file) { req->file = io_file_get(ctx, req, READ_ONCE(sqe->fd), - (sqe_flags & IOSQE_FIXED_FILE)); + (sqe_flags & IOSQE_FIXED_FILE), 0); if (unlikely(!req->file)) ret = -EBADF; } -- 2.25.1

1 19

[PATCH openEuler-5.10-LTS-SP1 01/21] io_uring: add missing lock in io_get_file_fixed
by Jialin Zhang 26 Apr '23

26 Apr '23

From: Bing-Jhong Billy Jheng <billy(a)starlabs.sg> stable inclusion from stable-v5.10.171 commit 08681391b84da27133deefaaddefd0acfa90c2be category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I6V7V1 CVE: CVE-2023-1872 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- io_get_file_fixed will access io_uring's context. Lock it if it is invoked unlocked (eg via io-wq) to avoid a race condition with fixed files getting unregistered. No single upstream patch exists for this issue, it was fixed as part of the file assignment changes that went into the 5.18 cycle. Signed-off-by: Jheng, Bing-Jhong Billy <billy(a)starlabs.sg> Signed-off-by: Jens Axboe <axboe(a)kernel.dk> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: ZhaoLong Wang <wangzhaolong1(a)huawei.com> Reviewed-by: Zhang Yi <yi.zhang(a)huawei.com> Reviewed-by: Xiu Jianfeng <xiujianfeng(a)huawei.com> Signed-off-by: Jialin Zhang <zhangjialin11(a)huawei.com> --- io_uring/io_uring.c | 25 ++++++++++++++++--------- 1 file changed, 16 insertions(+), 9 deletions(-) diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index 315031bb38e2..ded2faa66f84 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -1090,7 +1090,8 @@ static int __io_register_rsrc_update(struct io_ring_ctx *ctx, unsigned type, unsigned nr_args); static void io_clean_op(struct io_kiocb *req); static struct file *io_file_get(struct io_ring_ctx *ctx, - struct io_kiocb *req, int fd, bool fixed); + struct io_kiocb *req, int fd, bool fixed, + unsigned int issue_flags); static void __io_queue_sqe(struct io_kiocb *req); static void io_rsrc_put_work(struct work_struct *work); @@ -3914,7 +3915,7 @@ static int io_tee(struct io_kiocb *req, unsigned int issue_flags) return -EAGAIN; in = io_file_get(req->ctx, req, sp->splice_fd_in, - (sp->flags & SPLICE_F_FD_IN_FIXED)); + (sp->flags & SPLICE_F_FD_IN_FIXED), issue_flags); if (!in) { ret = -EBADF; goto done; @@ -3954,7 +3955,7 @@ static int io_splice(struct io_kiocb *req, unsigned int issue_flags) return -EAGAIN; in = io_file_get(req->ctx, req, sp->splice_fd_in, - (sp->flags & SPLICE_F_FD_IN_FIXED)); + (sp->flags & SPLICE_F_FD_IN_FIXED), issue_flags); if (!in) { ret = -EBADF; goto done; @@ -6742,13 +6743,16 @@ static void io_fixed_file_set(struct io_fixed_file *file_slot, struct file *file } static inline struct file *io_file_get_fixed(struct io_ring_ctx *ctx, - struct io_kiocb *req, int fd) + struct io_kiocb *req, int fd, + unsigned int issue_flags) { - struct file *file; + struct file *file = NULL; unsigned long file_ptr; + io_ring_submit_lock(ctx, !(issue_flags & IO_URING_F_NONBLOCK)); + if (unlikely((unsigned int)fd >= ctx->nr_user_files)) - return NULL; + goto out; fd = array_index_nospec(fd, ctx->nr_user_files); file_ptr = io_fixed_file_slot(&ctx->file_table, fd)->file_ptr; file = (struct file *) (file_ptr & FFS_MASK); @@ -6756,6 +6760,8 @@ static inline struct file *io_file_get_fixed(struct io_ring_ctx *ctx, /* mask in overlapping REQ_F and FFS bits */ req->flags |= (file_ptr << REQ_F_NOWAIT_READ_BIT); io_req_set_rsrc_node(req); +out: + io_ring_submit_unlock(ctx, !(issue_flags & IO_URING_F_NONBLOCK)); return file; } @@ -6773,10 +6779,11 @@ static struct file *io_file_get_normal(struct io_ring_ctx *ctx, } static inline struct file *io_file_get(struct io_ring_ctx *ctx, - struct io_kiocb *req, int fd, bool fixed) + struct io_kiocb *req, int fd, bool fixed, + unsigned int issue_flags) { if (fixed) - return io_file_get_fixed(ctx, req, fd); + return io_file_get_fixed(ctx, req, fd, issue_flags); else return io_file_get_normal(ctx, req, fd); } @@ -6998,7 +7005,7 @@ static int io_init_req(struct io_ring_ctx *ctx, struct io_kiocb *req, if (io_op_defs[req->opcode].needs_file) { req->file = io_file_get(ctx, req, READ_ONCE(sqe->fd), - (sqe_flags & IOSQE_FIXED_FILE)); + (sqe_flags & IOSQE_FIXED_FILE), 0); if (unlikely(!req->file)) ret = -EBADF; } -- 2.25.1

1 20

[PATCH openEuler-1.0-LTS] RDMA/hns: Add check for user-configured max_inline_data value
by Zhang Changzhong 26 Apr '23

26 Apr '23

From: zhaoweibo <zhaoweibo3(a)huawei.com> driver inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I51UWX CVE: NA ------------------------------------------------------------- When the user-configured max_inline_data value exceeds the hardware specification, an err needs to be returned. Fixes: 87d3b87b92b9 ("RDMA/hns: Optimize qp param setup flow") Signed-off-by: zhaoweibo <zhaoweibo3(a)huawei.com> Reviewed-by: Chunzhi Hu <huchunzhi(a)huawei.com> Signed-off-by: Zhang Changzhong <zhangchangzhong(a)huawei.com> --- drivers/infiniband/hw/hns/hns_roce_qp.c | 20 ++++++++++++++++++++ 1 file changed, 20 insertions(+) diff --git a/drivers/infiniband/hw/hns/hns_roce_qp.c b/drivers/infiniband/hw/hns/hns_roce_qp.c index 6f26693..df14a69 100644 --- a/drivers/infiniband/hw/hns/hns_roce_qp.c +++ b/drivers/infiniband/hw/hns/hns_roce_qp.c @@ -756,6 +756,22 @@ static void free_qp_buf(struct hns_roce_qp *hr_qp, struct ib_pd *ib_pd) hns_roce_free_recv_inline_buffer(hr_qp); } +static int set_max_inline_data(struct hns_roce_dev *hr_dev, + struct ib_qp_init_attr *init_attr) +{ + if (init_attr->cap.max_inline_data > hr_dev->caps.max_sq_inline) + return -EINVAL; + + if (init_attr->qp_type == IB_QPT_UD) + init_attr->cap.max_inline_data = 0; + + if (init_attr->cap.max_inline_data) + init_attr->cap.max_inline_data = roundup_pow_of_two( + init_attr->cap.max_inline_data); + + return 0; +} + static int set_qp_param(struct hns_roce_dev *hr_dev, struct hns_roce_qp *hr_qp, struct ib_qp_init_attr *init_attr, struct ib_udata *udata, @@ -763,6 +779,10 @@ static int set_qp_param(struct hns_roce_dev *hr_dev, struct hns_roce_qp *hr_qp, { int ret; + ret = set_max_inline_data(hr_dev, init_attr); + if (ret != 0) + return -EINVAL; + hr_qp->ibqp.qp_type = init_attr->qp_type; if (init_attr->sq_sig_type == IB_SIGNAL_ALL_WR) -- 2.9.5

1 0

4.19内核无修复方案CVE的规避方案
by wangyibo＠uniontech.com 26 Apr '23

26 Apr '23

1 0

[PATCH openEuler-1.0-LTS 0/2] irqchip/gic-v3-its: Balance LPI affinity across CPUs
by Zhang Changzhong 25 Apr '23

25 Apr '23

Marc Zyngier (2): irqchip/gic-v3-its: Track LPI distribution on a per CPU basis irqchip/gic-v3-its: Balance initial LPI affinity across CPUs drivers/irqchip/irq-gic-v3-its.c | 171 ++++++++++++++++++++++++++++++++------- 1 file changed, 144 insertions(+), 27 deletions(-) -- 2.9.5

1 2

[PATCH openEuler-1.0-LTS 0/2] irqchip/gic-v3-its: Balance LPI affinity across CPUs
by Zhang Changzhong 25 Apr '23

25 Apr '23

Marc Zyngier (2): irqchip/gic-v3-its: Track LPI distribution on a per CPU basis irqchip/gic-v3-its: Balance initial LPI affinity across CPUs drivers/irqchip/irq-gic-v3-its.c | 171 ++++++++++++++++++++++++++++++++------- 1 file changed, 144 insertions(+), 27 deletions(-) -- 2.9.5

1 2

Re: [OLK-5.10] net: hns3: add support handling tx dhcp packets for ROH
by patchwork bot 25 Apr '23

25 Apr '23

your patch has been converted to a pull request, pull request link is: https://gitee.com/openeuler/kernel/pulls/626

1 0

[PATCH OLK-5.10] net: hns3: add support handling tx dhcp packets for ROH
by Ke Chen 25 Apr '23

25 Apr '23

driver inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I6BSMN ----------------------------------------------------------------------- For ROH distributed scenario, EID is allocated by DHCP mode. Driver needs to convert the origin MAC address to EID format, and updates the destination MAC, chaddr and client id(if exists) when transmit DHCP packets. Meantime, the chaddr field should follow the source mac address, in order to make the dhcp server reply to the right client. For the payload of dhcp packet changed, so the checksum of L4 should be calculated too. Signed-off-by: Jian Shen <shenjian15(a)huawei.com> Signed-off-by: Ke Chen <chenke54(a)huawei.com> Reviewed-by: Yonglong Liu <liuyonglong(a)huawei.com> Reviewed-by: Guangbin Huang <huangguangbin2(a)huawei.com> Reviewed-by: Hao Lan <lanhao(a)huawei.com> --- .../net/ethernet/hisilicon/hns3/hns3_enet.c | 160 +++++++++++++++++- .../net/ethernet/hisilicon/hns3/hns3_enet.h | 50 ++++++ .../hisilicon/hns3/hns3pf/hclge_main.c | 16 ++ 3 files changed, 221 insertions(+), 5 deletions(-) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c index cf79cd69c..35d6b2f20 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c @@ -1165,6 +1165,128 @@ static void hns3_tx_spare_reclaim_cb(struct hns3_enet_ring *ring, } } +static struct hns3_dhcp_packet *hns3_get_dhcp_packet(struct sk_buff *skb, + int *dhcp_len) +{ + struct hns3_dhcp_packet *dhcp; + union l4_hdr_info l4; + int l4_payload_len; + + l4.hdr = skb_transport_header(skb); + if (l4.udp->dest != htons(HNS3_DHCP_CLIENT_PORT) || + l4.udp->source != htons(HNS3_DHCP_SERVER_PORT)) + return NULL; + + dhcp = (struct hns3_dhcp_packet *)(l4.hdr + sizeof(struct udphdr)); + l4_payload_len = ntohs(l4.udp->len) - sizeof(struct udphdr); + if (l4_payload_len < offsetof(struct hns3_dhcp_packet, options) || + dhcp->hlen != ETH_ALEN || + dhcp->cookie != htonl(HNS3_DHCP_MAGIC)) + return NULL; + + *dhcp_len = l4_payload_len; + return dhcp; +} + +static u8 *hns3_dhcp_option_scan(struct hns3_dhcp_packet *packet, + struct hns3_dhcp_opt_state *opt_state) +{ + int opt_len; + u8 *cur_opt; + + /* option bytes: [code][len][data0~data[len-1]] */ + while (1) { + if (opt_state->rem <= 0) + break; + + switch (opt_state->opt_ptr[DHCP_OPT_CODE]) { + /* option padding and end have no len and data byte. */ + case DHCP_OPT_PADDING: + opt_state->rem--; + opt_state->opt_ptr++; + break; + case DHCP_OPT_END: + if (DHCP_OVERLOAD_USE_FILE(opt_state->overload_flag)) { + opt_state->overload_flag |= + DHCP_OVERLOAD_FILE_USED; + opt_state->opt_ptr = packet->file; + opt_state->rem = sizeof(packet->file); + break; + } + if (DHCP_OVERLOAD_USE_SNAME(opt_state->overload_flag)) { + opt_state->overload_flag |= + DHCP_OVERLOAD_SNAME_USED; + opt_state->opt_ptr = packet->sname; + opt_state->rem = sizeof(packet->sname); + break; + } + return NULL; + default: + if (opt_state->rem <= DHCP_OPT_LEN) + return NULL; + /* opt_len includes code, len and data bytes */ + opt_len = opt_state->opt_ptr[DHCP_OPT_LEN] + + DHCP_OPT_DATA; + cur_opt = opt_state->opt_ptr; + if (opt_state->rem < opt_len) + return NULL; + + opt_state->opt_ptr += opt_len; + opt_state->rem -= opt_len; + if (cur_opt[DHCP_OPT_CODE] == DHCP_OPT_OVERLOAD) { + opt_state->overload_flag |= + cur_opt[DHCP_OPT_DATA]; + break; + } + return cur_opt; + } + } + + return NULL; +} + +static void hns3_udhcp_update_option61(struct hns3_nic_priv *priv, + struct hns3_dhcp_packet *packet, + int dhcp_len) +{ + struct hns3_dhcp_opt_state opt_state; + u8 *cur_opt; + + opt_state.opt_ptr = packet->options; + opt_state.rem = dhcp_len - offsetof(struct hns3_dhcp_packet, options); + opt_state.overload_flag = 0; + + cur_opt = hns3_dhcp_option_scan(packet, &opt_state); + while (cur_opt) { + if (cur_opt[DHCP_OPT_CODE] != DHCP_OPT_CLIENT_ID) { + cur_opt = hns3_dhcp_option_scan(packet, &opt_state); + continue; + } + if (cur_opt[DHCP_OPT_LEN] > ETH_ALEN) + ether_addr_copy(&cur_opt[DHCP_CLIENT_ID_MAC_OFT], + priv->roh_perm_mac); + break; + } +} + +static void hns3_dhcp_packet_convert(struct hns3_nic_priv *priv, + struct sk_buff *skb, + struct hns3_dhcp_packet *dhcp, + int dhcp_len) +{ + const u8 roh_dhcp_mac[ETH_ALEN] = {0x0, 0x0, 0x0, 0xFF, 0xFF, 0x04}; + struct ethhdr *l2hdr = eth_hdr(skb); + + if (!dhcp) + return; + + ether_addr_copy(dhcp->chaddr, priv->roh_perm_mac); + hns3_udhcp_update_option61(priv, dhcp, dhcp_len); + + if (is_broadcast_ether_addr(l2hdr->h_source)) + ether_addr_copy(l2hdr->h_source, roh_dhcp_mac); +} + static int hns3_set_tso(struct sk_buff *skb, u32 *paylen_fdop_ol4cs, u16 *mss, u32 *type_cs_vlan_tso, u32 *send_bytes) { @@ -1716,7 +1838,20 @@ static int hns3_handle_csum_partial(struct hns3_enet_ring *ring, return 0; } -static int hns3_fill_skb_desc(struct hns3_enet_ring *ring, +static bool hns3_roh_check_udpv4(struct sk_buff *skb) +{ + union l3_hdr_info l3; + + l3.hdr = skb_network_header(skb); + if (skb->protocol != htons(ETH_P_IP) || + l3.v4->version != IP_VERSION_IPV4) + return false; + + return l3.v4->protocol == IPPROTO_UDP; +} + +static int hns3_fill_skb_desc(struct hns3_nic_priv *priv, + struct hns3_enet_ring *ring, struct sk_buff *skb, struct hns3_desc *desc, struct hns3_desc_cb *desc_cb) { @@ -1741,6 +1876,15 @@ static int hns3_fill_skb_desc(struct hns3_enet_ring *ring, hnae3_set_field(param.paylen_fdop_ol4cs, HNS3_TXD_FD_OP_M, HNS3_TXD_FD_OP_S, fd_op); + if (hnae3_check_roh_mac_type(priv->ae_handle) && + hns3_roh_check_udpv4(skb)) { + struct hns3_dhcp_packet *dhcp; + int dhcp_len; + + dhcp = hns3_get_dhcp_packet(skb, &dhcp_len); + hns3_dhcp_packet_convert(priv, skb, dhcp, dhcp_len); + } + /* Set txbd */ desc->tx.ol_type_vlan_len_msec = cpu_to_le32(param.ol_type_vlan_len_msec); @@ -2338,15 +2482,16 @@ static int hns3_handle_desc_filling(struct hns3_enet_ring *ring, return hns3_fill_skb_to_desc(ring, skb, DESC_TYPE_SKB); } -static int hns3_handle_skb_desc(struct hns3_enet_ring *ring, +static int hns3_handle_skb_desc(struct hns3_nic_priv *priv, + struct hns3_enet_ring *ring, struct sk_buff *skb, struct hns3_desc_cb *desc_cb, int next_to_use_head) { int ret; - ret = hns3_fill_skb_desc(ring, skb, &ring->desc[ring->next_to_use], - desc_cb); + ret = hns3_fill_skb_desc(priv, ring, skb, + &ring->desc[ring->next_to_use], desc_cb); if (unlikely(ret < 0)) goto fill_err; @@ -2395,7 +2540,7 @@ netdev_tx_t hns3_nic_net_xmit(struct sk_buff *skb, struct net_device *netdev) goto out_err_tx_ok; } - ret = hns3_handle_skb_desc(ring, skb, desc_cb, ring->next_to_use); + ret = hns3_handle_skb_desc(priv, ring, skb, desc_cb, ring->next_to_use); if (unlikely(ret <= 0)) goto out_err_tx_ok; @@ -5226,6 +5371,10 @@ static int hns3_init_mac_addr(struct net_device *netdev) return 0; } + if (hnae3_check_roh_mac_type(h) && + is_zero_ether_addr(priv->roh_perm_mac)) + ether_addr_copy(priv->roh_perm_mac, netdev->dev_addr); + if (h->ae_algo->ops->set_mac_addr) ret = h->ae_algo->ops->set_mac_addr(h, netdev->dev_addr, true); @@ -5377,6 +5526,7 @@ static int hns3_client_init(struct hnae3_handle *handle) priv->tx_timeout_count = 0; priv->max_non_tso_bd_num = ae_dev->dev_specs.max_non_tso_bd_num; set_bit(HNS3_NIC_STATE_DOWN, &priv->state); + eth_zero_addr(priv->roh_perm_mac); handle->msg_enable = netif_msg_init(debug, DEFAULT_MSG_LEVEL); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h index ccfd38b00..85c352fff 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h @@ -604,6 +604,56 @@ struct hns3_nic_priv { struct hns3_enet_coalesce rx_coal; u32 tx_copybreak; u32 rx_copybreak; + u8 roh_perm_mac[ETH_ALEN]; +}; + +#define HNS3_DHCP_SERVER_PORT 68 +#define HNS3_DHCP_CLIENT_PORT 67 +#define HNS3_DHCP_MAGIC 0x63825363 +#define DHCP_OPT_CODE 0 +#define DHCP_OPT_LEN 1 +#define DHCP_OPT_DATA 2 +#define DHCP_CLIENT_ID_LEN 7 +#define DHCP_CLIENT_ID_MAC_OFT 3 +#define DHCP_OVERLOAD_FILE 0x1 +#define DHCP_OVERLOAD_SNAME 0x2 +#define DHCP_OVERLOAD_FILE_USED 0x101 +#define DHCP_OVERLOAD_SNAME_USED 0x202 +#define DHCP_OVERLOAD_USE_FILE(x) \ + (((x) & DHCP_OVERLOAD_FILE_USED) == DHCP_OVERLOAD_FILE) +#define DHCP_OVERLOAD_USE_SNAME(x) \ + (((x) & DHCP_OVERLOAD_SNAME_USED) == DHCP_OVERLOAD_SNAME) + +enum DHCP_OPTION_CODES { + DHCP_OPT_PADDING = 0, + DHCP_OPT_OVERLOAD = 52, + DHCP_OPT_CLIENT_ID = 61, + DHCP_OPT_END = 255 +}; + +struct hns3_dhcp_packet { + u8 op; + u8 htype; + u8 hlen; + u8 hops; + u32 xid; + u16 secs; + u16 flags; + u32 ciaddr; + u32 yiaddr; + u32 siaddr_nip; + u32 gateway_nip; + u8 chaddr[16]; /* link-layer client hardware address (MAC) */ + u8 sname[64]; + u8 file[128]; + u32 cookie; /* DHCP magic bytes: 0x63825363 */ + u8 options[312]; +}; + +struct hns3_dhcp_opt_state { + u8 *opt_ptr; /* refer to current option item */ + int rem; /* remain bytes in options */ + u32 overload_flag; /* whether use file and sname field as options */ }; union l3_hdr_info { diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index eea175484..947ffde02 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -2866,12 +2866,28 @@ static void hclge_get_fec(struct hnae3_handle *handle, u8 *fec_ability, if (fec_mode) *fec_mode = mac->fec_mode; } + +static void hclge_roh_convert_mac_addr(struct hclge_dev *hdev) +{ +#define HCLGE_ROH_EID_MASK_BYTE 3 + + struct hclge_vport *vport = &hdev->vport[0]; + struct hnae3_handle *handle = &vport->nic; + + if (hnae3_check_roh_mac_type(handle)) { + if (!is_valid_ether_addr(hdev->hw.mac.mac_addr)) + random_ether_addr(hdev->hw.mac.mac_addr); + memset(hdev->hw.mac.mac_addr, 0, HCLGE_ROH_EID_MASK_BYTE); + } +} + static int hclge_mac_init(struct hclge_dev *hdev) { struct hclge_mac *mac = &hdev->hw.mac; int ret; hclge_mac_type_init(hdev); + hclge_roh_convert_mac_addr(hdev); hdev->support_sfp_query = true; hdev->hw.mac.duplex = HCLGE_MAC_FULL; -- 2.30.0

1 0

[PATCH openEuler-1.0-LTS] power: supply: da9150: Fix use after free bug in da9150_charger_remove due to race condition
by Yongqiang Liu 25 Apr '23

25 Apr '23

From: Zheng Wang <zyytlz.wz(a)163.com> stable inclusion from stable-v4.19.280 commit 533d915899b4a5a7b5b5a99eec24b2920ccd1f11 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I6W80A CVE: CVE-2023-30772 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit 06615d11cc78162dfd5116efb71f29eb29502d37 ] In da9150_charger_probe, &charger->otg_work is bound with da9150_charger_otg_work. da9150_charger_otg_ncb may be called to start the work. If we remove the module which will call da9150_charger_remove to make cleanup, there may be a unfinished work. The possible sequence is as follows: Fix it by canceling the work before cleanup in the da9150_charger_remove CPU0 CPUc1 |da9150_charger_otg_work da9150_charger_remove | power_supply_unregister | device_unregister | power_supply_dev_release| kfree(psy) | | | power_supply_changed(charger->usb); | //use Fixes: c1a281e34dae ("power: Add support for DA9150 Charger") Signed-off-by: Zheng Wang <zyytlz.wz(a)163.com> Signed-off-by: Sebastian Reichel <sebastian.reichel(a)collabora.com> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Guo Mengqi <guomengqi3(a)huawei.com> Reviewed-by: Wang Weiyang <wangweiyang2(a)huawei.com> Reviewed-by: Weilong Chen <chenweilong(a)huawei.com> Signed-off-by: Yongqiang Liu <liuyongqiang13(a)huawei.com> --- drivers/power/supply/da9150-charger.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/power/supply/da9150-charger.c b/drivers/power/supply/da9150-charger.c index 60099815296e..b2d38eb32288 100644 --- a/drivers/power/supply/da9150-charger.c +++ b/drivers/power/supply/da9150-charger.c @@ -666,6 +666,7 @@ static int da9150_charger_remove(struct platform_device *pdev) if (!IS_ERR_OR_NULL(charger->usb_phy)) usb_unregister_notifier(charger->usb_phy, &charger->otg_nb); + cancel_work_sync(&charger->otg_work); power_supply_unregister(charger->battery); power_supply_unregister(charger->usb); -- 2.25.1

1 0

[OLK-5.10 v3] RDMA/hns: Support getting xrcd num from firmware
by Chengchang Tang 24 Apr '23

24 Apr '23

From: Luoyouming <luoyouming(a)huawei.com> driver inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I6WAZI --------------------------------------------------------------- Support driver gets the num_xrcds and reserved_xrcds from firmware. Signed-off-by: Luoyouming <luoyouming(a)huawei.com> Signed-off-by: Chengchang Tang <tangchengchang(a)huawei.com> Reviewed-by: Chengchang Tang <tangchengchang(a)huawei.com> --- drivers/infiniband/hw/hns/hns_roce_hw_v2.c | 5 ++--- drivers/infiniband/hw/hns/hns_roce_hw_v2.h | 4 ++-- 2 files changed, 4 insertions(+), 5 deletions(-) diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c index 36397517e679..042e19fa4039 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c +++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c @@ -2310,9 +2310,6 @@ static void apply_func_caps(struct hns_roce_dev *hr_dev) caps->qpc_timer_hop_num = HNS_ROCE_HOP_NUM_0; caps->cqc_timer_hop_num = HNS_ROCE_HOP_NUM_0; - caps->num_xrcds = HNS_ROCE_V2_MAX_XRCD_NUM; - caps->reserved_xrcds = HNS_ROCE_V2_RSV_XRCD_NUM; - caps->num_mtt_segs = HNS_ROCE_V2_MAX_MTT_SEGS; caps->num_srqwqe_segs = HNS_ROCE_V2_MAX_SRQWQE_SEGS; caps->num_idx_segs = HNS_ROCE_V2_MAX_IDX_SEGS; @@ -2440,6 +2437,7 @@ static int hns_roce_query_caps(struct hns_roce_dev *hr_dev) caps->num_cqs = 1 << hr_reg_read(resp_c, PF_CAPS_C_NUM_CQS); caps->gid_table_len[0] = hr_reg_read(resp_c, PF_CAPS_C_MAX_GID); caps->max_cqes = 1 << hr_reg_read(resp_c, PF_CAPS_C_CQ_DEPTH); + caps->num_xrcds = 1 << hr_reg_read(resp_c, PF_CAPS_C_NUM_XRCDS); caps->num_mtpts = 1 << hr_reg_read(resp_c, PF_CAPS_C_NUM_MRWS); caps->num_qps = 1 << hr_reg_read(resp_c, PF_CAPS_C_NUM_QPS); caps->max_qp_init_rdma = hr_reg_read(resp_c, PF_CAPS_C_MAX_ORD); @@ -2461,6 +2459,7 @@ static int hns_roce_query_caps(struct hns_roce_dev *hr_dev) caps->reserved_mrws = hr_reg_read(resp_e, PF_CAPS_E_RSV_MRWS); caps->chunk_sz = 1 << hr_reg_read(resp_e, PF_CAPS_E_CHUNK_SIZE_SHIFT); caps->reserved_cqs = hr_reg_read(resp_e, PF_CAPS_E_RSV_CQS); + caps->reserved_xrcds = hr_reg_read(resp_e, PF_CAPS_E_RSV_XRCDS); caps->reserved_srqs = hr_reg_read(resp_e, PF_CAPS_E_RSV_SRQS); caps->reserved_lkey = hr_reg_read(resp_e, PF_CAPS_E_RSV_LKEYS); diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.h b/drivers/infiniband/hw/hns/hns_roce_hw_v2.h index 1605a093dae8..6223cc66f065 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.h +++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.h @@ -42,8 +42,6 @@ #define HNS_ROCE_V2_MAX_MTT_SEGS 0x1000000 #define HNS_ROCE_V2_MAX_SRQWQE_SEGS 0x1000000 #define HNS_ROCE_V2_MAX_IDX_SEGS 0x1000000 -#define HNS_ROCE_V2_MAX_XRCD_NUM 0x1000000 -#define HNS_ROCE_V2_RSV_XRCD_NUM 0 #define HNS_ROCE_V3_SCCC_SZ 64 #define HNS_ROCE_V3_GMV_ENTRY_SZ 32 @@ -1214,6 +1212,7 @@ struct hns_roce_query_pf_caps_c { #define PF_CAPS_C_NUM_CQS PF_CAPS_C_FIELD_LOC(51, 32) #define PF_CAPS_C_MAX_GID PF_CAPS_C_FIELD_LOC(60, 52) #define PF_CAPS_C_CQ_DEPTH PF_CAPS_C_FIELD_LOC(86, 64) +#define PF_CAPS_C_NUM_XRCDS PF_CAPS_C_FIELD_LOC(91, 87) #define PF_CAPS_C_NUM_MRWS PF_CAPS_C_FIELD_LOC(115, 96) #define PF_CAPS_C_NUM_QPS PF_CAPS_C_FIELD_LOC(147, 128) #define PF_CAPS_C_MAX_ORD PF_CAPS_C_FIELD_LOC(155, 148) @@ -1273,6 +1272,7 @@ struct hns_roce_query_pf_caps_e { #define PF_CAPS_E_RSV_MRWS PF_CAPS_E_FIELD_LOC(19, 0) #define PF_CAPS_E_CHUNK_SIZE_SHIFT PF_CAPS_E_FIELD_LOC(31, 20) #define PF_CAPS_E_RSV_CQS PF_CAPS_E_FIELD_LOC(51, 32) +#define PF_CAPS_E_RSV_XRCDS PF_CAPS_E_FIELD_LOC(63, 52) #define PF_CAPS_E_RSV_SRQS PF_CAPS_E_FIELD_LOC(83, 64) #define PF_CAPS_E_RSV_LKEYS PF_CAPS_E_FIELD_LOC(115, 96) -- 2.30.0

1 0

[PATCH openEuler-1.0-LTS] i2c: xgene-slimpro: Fix out-of-bounds bug in xgene_slimpro_i2c_xfer()
by Yongqiang Liu 23 Apr '23

23 Apr '23

From: Wei Chen <harperchen1110(a)gmail.com> mainline inclusion from mainline-v6.3-rc4 commit 92fbb6d1296f81f41f65effd7f5f8c0f74943d15 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I6XHPL CVE: CVE-2023-2194 -------------------------------- The data->block[0] variable comes from user and is a number between 0-255. Without proper check, the variable may be very large to cause an out-of-bounds when performing memcpy in slimpro_i2c_blkwr. Fix this bug by checking the value of writelen. Fixes: f6505fbabc42 ("i2c: add SLIMpro I2C device driver on APM X-Gene platform") Signed-off-by: Wei Chen <harperchen1110(a)gmail.com> Cc: stable(a)vger.kernel.org Reviewed-by: Andi Shyti <andi.shyti(a)kernel.org> Signed-off-by: Wolfram Sang <wsa(a)kernel.org> Signed-off-by: Yang Jihong <yangjihong1(a)huawei.com> Reviewed-by: Xu Kuohai <xukuohai(a)huawei.com> Reviewed-by: Wang Weiyang <wangweiyang2(a)huawei.com> Signed-off-by: Yongqiang Liu <liuyongqiang13(a)huawei.com> --- drivers/i2c/busses/i2c-xgene-slimpro.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/i2c/busses/i2c-xgene-slimpro.c b/drivers/i2c/busses/i2c-xgene-slimpro.c index a7ac746018ad..7a746f413535 100644 --- a/drivers/i2c/busses/i2c-xgene-slimpro.c +++ b/drivers/i2c/busses/i2c-xgene-slimpro.c @@ -321,6 +321,9 @@ static int slimpro_i2c_blkwr(struct slimpro_i2c_dev *ctx, u32 chip, u32 msg[3]; int rc; + if (writelen > I2C_SMBUS_BLOCK_MAX) + return -EINVAL; + memcpy(ctx->dma_buffer, data, writelen); paddr = dma_map_single(ctx->dev, ctx->dma_buffer, writelen, DMA_TO_DEVICE); -- 2.25.1

1 0

[openEuler-22.03-LTS] rxrpc: Fix race between conn bundle lookup and bundle removal [ZDI-CAN-15975]
by Wang Yufen 23 Apr '23

23 Apr '23

From: David Howells <dhowells(a)redhat.com> stable inclusion from stable-v5.10.157 commit 3535c632e6d16c98f76e615da8dc0cb2750c66cc category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I6VK2H CVE: CVE-2023-2006 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit 3bcd6c7eaa53b56c3f584da46a1f7652e759d0e5 ] After rxrpc_unbundle_conn() has removed a connection from a bundle, it checks to see if there are any conns with available channels and, if not, removes and attempts to destroy the bundle. Whilst it does check after grabbing client_bundles_lock that there are no connections attached, this races with rxrpc_look_up_bundle() retrieving the bundle, but not attaching a connection for the connection to be attached later. There is therefore a window in which the bundle can get destroyed before we manage to attach a new connection to it. Fix this by adding an "active" counter to struct rxrpc_bundle: (1) rxrpc_connect_call() obtains an active count by prepping/looking up a bundle and ditches it before returning. (2) If, during rxrpc_connect_call(), a connection is added to the bundle, this obtains an active count, which is held until the connection is discarded. (3) rxrpc_deactivate_bundle() is created to drop an active count on a bundle and destroy it when the active count reaches 0. The active count is checked inside client_bundles_lock() to prevent a race with rxrpc_look_up_bundle(). (4) rxrpc_unbundle_conn() then calls rxrpc_deactivate_bundle(). Fixes: 245500d853e9 ("rxrpc: Rewrite the client connection manager") Reported-by: zdi-disclosures(a)trendmicro.com # ZDI-CAN-15975 Signed-off-by: David Howells <dhowells(a)redhat.com> Tested-by: zdi-disclosures(a)trendmicro.com cc: Marc Dionne <marc.dionne(a)auristor.com> cc: linux-afs(a)lists.infradead.org Signed-off-by: David S. Miller <davem(a)davemloft.net> Conflicts: net/rxrpc/ar-internal.h net/rxrpc/conn_client.c Signed-off-by: Wang Yufen <wangyufen(a)huawei.com> --- net/rxrpc/ar-internal.h | 1 + net/rxrpc/conn_client.c | 36 ++++++++++++++++++++++-------------- 2 files changed, 23 insertions(+), 14 deletions(-) diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index ccb6541..90ab125 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -392,6 +392,7 @@ enum rxrpc_conn_proto_state { struct rxrpc_bundle { struct rxrpc_conn_parameters params; atomic_t usage; + atomic_t active; /* Number of active users */ unsigned int debug_id; bool try_upgrade; /* True if the bundle is attempting upgrade */ bool alloc_conn; /* True if someone's getting a conn */ diff --git a/net/rxrpc/conn_client.c b/net/rxrpc/conn_client.c index f5fb223..34430cc 100644 --- a/net/rxrpc/conn_client.c +++ b/net/rxrpc/conn_client.c @@ -40,6 +40,8 @@ DEFINE_IDR(rxrpc_client_conn_ids); static DEFINE_SPINLOCK(rxrpc_conn_id_lock); +static void rxrpc_deactivate_bundle(struct rxrpc_bundle *bundle); + /* * Get a connection ID and epoch for a client connection from the global pool. * The connection struct pointer is then recorded in the idr radix tree. The @@ -123,6 +125,7 @@ static struct rxrpc_bundle *rxrpc_alloc_bundle(struct rxrpc_conn_parameters *cp, bundle->params = *cp; rxrpc_get_peer(bundle->params.peer); atomic_set(&bundle->usage, 1); + atomic_set(&bundle->active, 1); spin_lock_init(&bundle->channel_lock); INIT_LIST_HEAD(&bundle->waiting_calls); } @@ -341,6 +344,7 @@ static struct rxrpc_bundle *rxrpc_look_up_bundle(struct rxrpc_conn_parameters *c rxrpc_free_bundle(candidate); found_bundle: rxrpc_get_bundle(bundle); + atomic_inc(&bundle->active); spin_unlock(&local->client_bundles_lock); _leave(" = %u [found]", bundle->debug_id); return bundle; @@ -438,6 +442,7 @@ static void rxrpc_add_conn_to_bundle(struct rxrpc_bundle *bundle, gfp_t gfp) if (old) trace_rxrpc_client(old, -1, rxrpc_client_replace); candidate->bundle_shift = shift; + atomic_inc(&bundle->active); bundle->conns[i] = candidate; for (j = 0; j < RXRPC_MAXCALLS; j++) set_bit(shift + j, &bundle->avail_chans); @@ -728,6 +733,7 @@ int rxrpc_connect_call(struct rxrpc_sock *rx, smp_rmb(); out_put_bundle: + rxrpc_deactivate_bundle(bundle); rxrpc_put_bundle(bundle); out: _leave(" = %d", ret); @@ -903,9 +909,8 @@ void rxrpc_disconnect_client_call(struct rxrpc_bundle *bundle, struct rxrpc_call static void rxrpc_unbundle_conn(struct rxrpc_connection *conn) { struct rxrpc_bundle *bundle = conn->bundle; - struct rxrpc_local *local = bundle->params.local; unsigned int bindex; - bool need_drop = false, need_put = false; + bool need_drop = false; int i; _enter("C=%x", conn->debug_id); @@ -924,15 +929,22 @@ static void rxrpc_unbundle_conn(struct rxrpc_connection *conn) } spin_unlock(&bundle->channel_lock); - /* If there are no more connections, remove the bundle */ - if (!bundle->avail_chans) { - _debug("maybe unbundle"); - spin_lock(&local->client_bundles_lock); + if (need_drop) { + rxrpc_deactivate_bundle(bundle); + rxrpc_put_connection(conn); + } +} - for (i = 0; i < ARRAY_SIZE(bundle->conns); i++) - if (bundle->conns[i]) - break; - if (i == ARRAY_SIZE(bundle->conns) && !bundle->params.exclusive) { +/* + * Drop the active count on a bundle. + */ +static void rxrpc_deactivate_bundle(struct rxrpc_bundle *bundle) +{ + struct rxrpc_local *local = bundle->params.local; + bool need_put = false; + + if (atomic_dec_and_lock(&bundle->active, &local->client_bundles_lock)) { + if (!bundle->params.exclusive) { _debug("erase bundle"); rb_erase(&bundle->local_node, &local->client_bundles); need_put = true; @@ -942,10 +954,6 @@ static void rxrpc_unbundle_conn(struct rxrpc_connection *conn) if (need_put) rxrpc_put_bundle(bundle); } - - if (need_drop) - rxrpc_put_connection(conn); - _leave(""); } /* -- 1.8.3.1

1 0

[OLK-5.10] rxrpc: Fix race between conn bundle lookup and bundle removal [ZDI-CAN-15975]
by Wang Yufen 23 Apr '23

23 Apr '23

From: David Howells <dhowells(a)redhat.com> stable inclusion from stable-v5.10.157 commit 3535c632e6d16c98f76e615da8dc0cb2750c66cc category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I6VK2H CVE: CVE-2023-2006 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit 3bcd6c7eaa53b56c3f584da46a1f7652e759d0e5 ] After rxrpc_unbundle_conn() has removed a connection from a bundle, it checks to see if there are any conns with available channels and, if not, removes and attempts to destroy the bundle. Whilst it does check after grabbing client_bundles_lock that there are no connections attached, this races with rxrpc_look_up_bundle() retrieving the bundle, but not attaching a connection for the connection to be attached later. There is therefore a window in which the bundle can get destroyed before we manage to attach a new connection to it. Fix this by adding an "active" counter to struct rxrpc_bundle: (1) rxrpc_connect_call() obtains an active count by prepping/looking up a bundle and ditches it before returning. (2) If, during rxrpc_connect_call(), a connection is added to the bundle, this obtains an active count, which is held until the connection is discarded. (3) rxrpc_deactivate_bundle() is created to drop an active count on a bundle and destroy it when the active count reaches 0. The active count is checked inside client_bundles_lock() to prevent a race with rxrpc_look_up_bundle(). (4) rxrpc_unbundle_conn() then calls rxrpc_deactivate_bundle(). Fixes: 245500d853e9 ("rxrpc: Rewrite the client connection manager") Reported-by: zdi-disclosures(a)trendmicro.com # ZDI-CAN-15975 Signed-off-by: David Howells <dhowells(a)redhat.com> Tested-by: zdi-disclosures(a)trendmicro.com cc: Marc Dionne <marc.dionne(a)auristor.com> cc: linux-afs(a)lists.infradead.org Signed-off-by: David S. Miller <davem(a)davemloft.net> Conflicts: net/rxrpc/ar-internal.h net/rxrpc/conn_client.c Signed-off-by: Wang Yufen <wangyufen(a)huawei.com> --- net/rxrpc/ar-internal.h | 1 + net/rxrpc/conn_client.c | 36 ++++++++++++++++++++++-------------- 2 files changed, 23 insertions(+), 14 deletions(-) diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index ccb6541..90ab125 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -392,6 +392,7 @@ enum rxrpc_conn_proto_state { struct rxrpc_bundle { struct rxrpc_conn_parameters params; atomic_t usage; + atomic_t active; /* Number of active users */ unsigned int debug_id; bool try_upgrade; /* True if the bundle is attempting upgrade */ bool alloc_conn; /* True if someone's getting a conn */ diff --git a/net/rxrpc/conn_client.c b/net/rxrpc/conn_client.c index f5fb223..34430cc 100644 --- a/net/rxrpc/conn_client.c +++ b/net/rxrpc/conn_client.c @@ -40,6 +40,8 @@ DEFINE_IDR(rxrpc_client_conn_ids); static DEFINE_SPINLOCK(rxrpc_conn_id_lock); +static void rxrpc_deactivate_bundle(struct rxrpc_bundle *bundle); + /* * Get a connection ID and epoch for a client connection from the global pool. * The connection struct pointer is then recorded in the idr radix tree. The @@ -123,6 +125,7 @@ static struct rxrpc_bundle *rxrpc_alloc_bundle(struct rxrpc_conn_parameters *cp, bundle->params = *cp; rxrpc_get_peer(bundle->params.peer); atomic_set(&bundle->usage, 1); + atomic_set(&bundle->active, 1); spin_lock_init(&bundle->channel_lock); INIT_LIST_HEAD(&bundle->waiting_calls); } @@ -341,6 +344,7 @@ static struct rxrpc_bundle *rxrpc_look_up_bundle(struct rxrpc_conn_parameters *c rxrpc_free_bundle(candidate); found_bundle: rxrpc_get_bundle(bundle); + atomic_inc(&bundle->active); spin_unlock(&local->client_bundles_lock); _leave(" = %u [found]", bundle->debug_id); return bundle; @@ -438,6 +442,7 @@ static void rxrpc_add_conn_to_bundle(struct rxrpc_bundle *bundle, gfp_t gfp) if (old) trace_rxrpc_client(old, -1, rxrpc_client_replace); candidate->bundle_shift = shift; + atomic_inc(&bundle->active); bundle->conns[i] = candidate; for (j = 0; j < RXRPC_MAXCALLS; j++) set_bit(shift + j, &bundle->avail_chans); @@ -728,6 +733,7 @@ int rxrpc_connect_call(struct rxrpc_sock *rx, smp_rmb(); out_put_bundle: + rxrpc_deactivate_bundle(bundle); rxrpc_put_bundle(bundle); out: _leave(" = %d", ret); @@ -903,9 +909,8 @@ void rxrpc_disconnect_client_call(struct rxrpc_bundle *bundle, struct rxrpc_call static void rxrpc_unbundle_conn(struct rxrpc_connection *conn) { struct rxrpc_bundle *bundle = conn->bundle; - struct rxrpc_local *local = bundle->params.local; unsigned int bindex; - bool need_drop = false, need_put = false; + bool need_drop = false; int i; _enter("C=%x", conn->debug_id); @@ -924,15 +929,22 @@ static void rxrpc_unbundle_conn(struct rxrpc_connection *conn) } spin_unlock(&bundle->channel_lock); - /* If there are no more connections, remove the bundle */ - if (!bundle->avail_chans) { - _debug("maybe unbundle"); - spin_lock(&local->client_bundles_lock); + if (need_drop) { + rxrpc_deactivate_bundle(bundle); + rxrpc_put_connection(conn); + } +} - for (i = 0; i < ARRAY_SIZE(bundle->conns); i++) - if (bundle->conns[i]) - break; - if (i == ARRAY_SIZE(bundle->conns) && !bundle->params.exclusive) { +/* + * Drop the active count on a bundle. + */ +static void rxrpc_deactivate_bundle(struct rxrpc_bundle *bundle) +{ + struct rxrpc_local *local = bundle->params.local; + bool need_put = false; + + if (atomic_dec_and_lock(&bundle->active, &local->client_bundles_lock)) { + if (!bundle->params.exclusive) { _debug("erase bundle"); rb_erase(&bundle->local_node, &local->client_bundles); need_put = true; @@ -942,10 +954,6 @@ static void rxrpc_unbundle_conn(struct rxrpc_connection *conn) if (need_put) rxrpc_put_bundle(bundle); } - - if (need_drop) - rxrpc_put_connection(conn); - _leave(""); } /* -- 1.8.3.1

1 0

[PATCH OLK-5.10 v2] KVM: nVMX: Inject #GP, not #UD, if "generic" VMXON CR0/CR4 check fails
by 任敏敏(联通集团联通数字科技有限公司本部) 23 Apr '23

23 Apr '23

From: Sean Christopherson <seanjc(a)google.com> stable inclusion from stable-v5.10.163 commit 43dd254853aa274d356bb1d3ab01a8ca880b07b0 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I6XQ34 CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- commit 9cc409325ddd776f6fd6293d5ce93ce1248af6e4 upstream Inject #GP for if VMXON is attempting with a CR0/CR4 that fails the generic "is CRx valid" check, but passes the CR4.VMXE check, and do the generic checks _after_ handling the post-VMXON VM-Fail. The CR4.VMXE check, and all other #UD cases, are special pre-conditions that are enforced prior to pivoting on the current VMX mode, i.e. occur before interception if VMXON is attempted in VMX non-root mode. All other CR0/CR4 checks generate #GP and effectively have lower priority than the post-VMXON check. Per the SDM: IF (register operand) or (CR0.PE = 0) or (CR4.VMXE = 0) or ... THEN #UD; ELSIF not in VMX operation THEN IF (CPL > 0) or (in A20M mode) or (the values of CR0 and CR4 are not supported in VMX operation) THEN #GP(0); ELSIF in VMX non-root operation THEN VMexit; ELSIF CPL > 0 THEN #GP(0); ELSE VMfail("VMXON executed in VMX root operation"); FI; which, if re-written without ELSIF, yields: IF (register operand) or (CR0.PE = 0) or (CR4.VMXE = 0) or ... THEN #UD IF in VMX non-root operation THEN VMexit; IF CPL > 0 THEN #GP(0) IF in VMX operation THEN VMfail("VMXON executed in VMX root operation"); IF (in A20M mode) or (the values of CR0 and CR4 are not supported in VMX operation) THEN #GP(0); Note, KVM unconditionally forwards VMXON VM-Exits that occur in L2 to L1, i.e. there is no need to check the vCPU is not in VMX non-root mode. Add a comment to explain why unconditionally forwarding such exits is functionally correct. Reported-by: Eric Li <ercli(a)ucdavis.edu> Fixes: c7d855c2aff2 ("KVM: nVMX: Inject #UD if VMXON is attempted with incompatible CR0/CR4") Cc: stable(a)vger.kernel.org Signed-off-by: Sean Christopherson <seanjc(a)google.com> Link: https://lore.kernel.org/r/20221006001956.329314-1-seanjc@google.com Signed-off-by: rminmin <renmm6(a)chinaunicom.cn> --- arch/x86/kvm/vmx/nested.c | 44 +++++++++++++++++++++++++++++---------- 1 file changed, 33 insertions(+), 11 deletions(-) diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index 9003b14d72ca..40225b770942 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -4899,24 +4899,35 @@ static int handle_vmon(struct kvm_vcpu *vcpu) | FEAT_CTL_VMX_ENABLED_OUTSIDE_SMX; /* - * Note, KVM cannot rely on hardware to perform the CR0/CR4 #UD checks - * that have higher priority than VM-Exit (see Intel SDM's pseudocode - * for VMXON), as KVM must load valid CR0/CR4 values into hardware while - * running the guest, i.e. KVM needs to check the _guest_ values. + * Manually check CR4.VMXE checks, KVM must force CR4.VMXE=1 to enter + * the guest and so cannot rely on hardware to perform the check, + * which has higher priority than VM-Exit (see Intel SDM's pseudocode + * for VMXON). * - * Rely on hardware for the other two pre-VM-Exit checks, !VM86 and - * !COMPATIBILITY modes. KVM may run the guest in VM86 to emulate Real - * Mode, but KVM will never take the guest out of those modes. + * Rely on hardware for the other pre-VM-Exit checks, CR0.PE=1, !VM86 + * and !COMPATIBILITY modes. For an unrestricted guest, KVM doesn't + * force any of the relevant guest state. For a restricted guest, KVM + * does force CR0.PE=1, but only to also force VM86 in order to emulate + * Real Mode, and so there's no need to check CR0.PE manually. */ - if (!nested_host_cr0_valid(vcpu, kvm_read_cr0(vcpu)) || - !nested_host_cr4_valid(vcpu, kvm_read_cr4(vcpu))) { + if (!kvm_read_cr4_bits(vcpu, X86_CR4_VMXE)) { kvm_queue_exception(vcpu, UD_VECTOR); return 1; } /* - * CPL=0 and all other checks that are lower priority than VM-Exit must - * be checked manually. + * The CPL is checked for "not in VMX operation" and for "in VMX root", + * and has higher priority than the VM-Fail due to being post-VMXON, + * i.e. VMXON #GPs outside of VMX non-root if CPL!=0. In VMX non-root, + * VMXON causes VM-Exit and KVM unconditionally forwards VMXON VM-Exits + * from L2 to L1, i.e. there's no need to check for the vCPU being in + * VMX non-root. + * + * Forwarding the VM-Exit unconditionally, i.e. without performing the + * #UD checks (see above), is functionally ok because KVM doesn't allow + * L1 to run L2 without CR4.VMXE=0, and because KVM never modifies L2's + * CR0 or CR4, i.e. it's L2's responsibility to emulate #UDs that are + * missed by hardware due to shadowing CR0 and/or CR4. */ if (vmx_get_cpl(vcpu)) { kvm_inject_gp(vcpu, 0); @@ -4926,6 +4937,17 @@ static int handle_vmon(struct kvm_vcpu *vcpu) if (vmx->nested.vmxon) return nested_vmx_fail(vcpu, VMXERR_VMXON_IN_VMX_ROOT_OPERATION); + /* + * Invalid CR0/CR4 generates #GP. These checks are performed if and + * only if the vCPU isn't already in VMX operation, i.e. effectively + * have lower priority than the VM-Fail above. + */ + if (!nested_host_cr0_valid(vcpu, kvm_read_cr0(vcpu)) || + !nested_host_cr4_valid(vcpu, kvm_read_cr4(vcpu))) { + kvm_inject_gp(vcpu, 0); + return 1; + } + if ((vmx->msr_ia32_feature_control & VMXON_NEEDED_FEATURES) != VMXON_NEEDED_FEATURES) { kvm_inject_gp(vcpu, 0); -- 2.33.0 Èç¹ûÄúŽíÎóœÓÊÕÁËžÃÓÊŒþ£¬ÇëÍš¹ýµç×ÓÓÊŒþÁ¢ŒŽÍšÖªÎÒÃÇ¡£Çë»ØžŽÓÊŒþµœ hqs-spmc@chinaunicom.cn£¬ŒŽ¿ÉÒÔÍË¶©ŽËÓÊŒþ¡£ÎÒÃÇœ«Á¢ŒŽœ«ÄúµÄÐÅÏ¢ŽÓÎÒÃÇµÄ·¢ËÍÄ¿ÂŒÖÐÉŸ³ý¡£ If you have received this email in error please notify us immediately by e-mail. Please reply to hqs-spmc(a)chinaunicom.cn ,you can unsubscribe from this mail. We will immediately remove your information from send catalogue of our.

1 0

[PATCH OLK-5.10] KVM: nVMX: Inject #GP, not #UD, if "generic" VMXON CR0/CR4 check fails
by 任敏敏(联通集团联通数字科技有限公司本部) 23 Apr '23

23 Apr '23

From: Sean Christopherson <seanjc(a)google.com> stable inclusion from stable-v6.2 commit 9cc409325ddd776f6fd6293d5ce93ce1248af6e4 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I6XQ34 CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- commit 9cc409325ddd776f6fd6293d5ce93ce1248af6e4 upstream Inject #GP for if VMXON is attempting with a CR0/CR4 that fails the generic "is CRx valid" check, but passes the CR4.VMXE check, and do the generic checks _after_ handling the post-VMXON VM-Fail. The CR4.VMXE check, and all other #UD cases, are special pre-conditions that are enforced prior to pivoting on the current VMX mode, i.e. occur before interception if VMXON is attempted in VMX non-root mode. All other CR0/CR4 checks generate #GP and effectively have lower priority than the post-VMXON check. Per the SDM: IF (register operand) or (CR0.PE = 0) or (CR4.VMXE = 0) or ... THEN #UD; ELSIF not in VMX operation THEN IF (CPL > 0) or (in A20M mode) or (the values of CR0 and CR4 are not supported in VMX operation) THEN #GP(0); ELSIF in VMX non-root operation THEN VMexit; ELSIF CPL > 0 THEN #GP(0); ELSE VMfail("VMXON executed in VMX root operation"); FI; which, if re-written without ELSIF, yields: IF (register operand) or (CR0.PE = 0) or (CR4.VMXE = 0) or ... THEN #UD IF in VMX non-root operation THEN VMexit; IF CPL > 0 THEN #GP(0) IF in VMX operation THEN VMfail("VMXON executed in VMX root operation"); IF (in A20M mode) or (the values of CR0 and CR4 are not supported in VMX operation) THEN #GP(0); Note, KVM unconditionally forwards VMXON VM-Exits that occur in L2 to L1, i.e. there is no need to check the vCPU is not in VMX non-root mode. Add a comment to explain why unconditionally forwarding such exits is functionally correct. Reported-by: Eric Li <ercli(a)ucdavis.edu> Fixes: c7d855c2aff2 ("KVM: nVMX: Inject #UD if VMXON is attempted with incompatible CR0/CR4") Cc: stable(a)vger.kernel.org Signed-off-by: Sean Christopherson <seanjc(a)google.com> Link: https://lore.kernel.org/r/20221006001956.329314-1-seanjc@google.com Signed-off-by: rminmin <renmm6(a)chinaunicom.cn> --- arch/x86/kvm/vmx/nested.c | 44 +++++++++++++++++++++++++++++---------- 1 file changed, 33 insertions(+), 11 deletions(-) diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index 9003b14d72ca..40225b770942 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -4899,24 +4899,35 @@ static int handle_vmon(struct kvm_vcpu *vcpu) | FEAT_CTL_VMX_ENABLED_OUTSIDE_SMX; /* - * Note, KVM cannot rely on hardware to perform the CR0/CR4 #UD checks - * that have higher priority than VM-Exit (see Intel SDM's pseudocode - * for VMXON), as KVM must load valid CR0/CR4 values into hardware while - * running the guest, i.e. KVM needs to check the _guest_ values. + * Manually check CR4.VMXE checks, KVM must force CR4.VMXE=1 to enter + * the guest and so cannot rely on hardware to perform the check, + * which has higher priority than VM-Exit (see Intel SDM's pseudocode + * for VMXON). * - * Rely on hardware for the other two pre-VM-Exit checks, !VM86 and - * !COMPATIBILITY modes. KVM may run the guest in VM86 to emulate Real - * Mode, but KVM will never take the guest out of those modes. + * Rely on hardware for the other pre-VM-Exit checks, CR0.PE=1, !VM86 + * and !COMPATIBILITY modes. For an unrestricted guest, KVM doesn't + * force any of the relevant guest state. For a restricted guest, KVM + * does force CR0.PE=1, but only to also force VM86 in order to emulate + * Real Mode, and so there's no need to check CR0.PE manually. */ - if (!nested_host_cr0_valid(vcpu, kvm_read_cr0(vcpu)) || - !nested_host_cr4_valid(vcpu, kvm_read_cr4(vcpu))) { + if (!kvm_read_cr4_bits(vcpu, X86_CR4_VMXE)) { kvm_queue_exception(vcpu, UD_VECTOR); return 1; } /* - * CPL=0 and all other checks that are lower priority than VM-Exit must - * be checked manually. + * The CPL is checked for "not in VMX operation" and for "in VMX root", + * and has higher priority than the VM-Fail due to being post-VMXON, + * i.e. VMXON #GPs outside of VMX non-root if CPL!=0. In VMX non-root, + * VMXON causes VM-Exit and KVM unconditionally forwards VMXON VM-Exits + * from L2 to L1, i.e. there's no need to check for the vCPU being in + * VMX non-root. + * + * Forwarding the VM-Exit unconditionally, i.e. without performing the + * #UD checks (see above), is functionally ok because KVM doesn't allow + * L1 to run L2 without CR4.VMXE=0, and because KVM never modifies L2's + * CR0 or CR4, i.e. it's L2's responsibility to emulate #UDs that are + * missed by hardware due to shadowing CR0 and/or CR4. */ if (vmx_get_cpl(vcpu)) { kvm_inject_gp(vcpu, 0); @@ -4926,6 +4937,17 @@ static int handle_vmon(struct kvm_vcpu *vcpu) if (vmx->nested.vmxon) return nested_vmx_fail(vcpu, VMXERR_VMXON_IN_VMX_ROOT_OPERATION); + /* + * Invalid CR0/CR4 generates #GP. These checks are performed if and + * only if the vCPU isn't already in VMX operation, i.e. effectively + * have lower priority than the VM-Fail above. + */ + if (!nested_host_cr0_valid(vcpu, kvm_read_cr0(vcpu)) || + !nested_host_cr4_valid(vcpu, kvm_read_cr4(vcpu))) { + kvm_inject_gp(vcpu, 0); + return 1; + } + if ((vmx->msr_ia32_feature_control & VMXON_NEEDED_FEATURES) != VMXON_NEEDED_FEATURES) { kvm_inject_gp(vcpu, 0); -- 2.33.0 Èç¹ûÄúŽíÎóœÓÊÕÁËžÃÓÊŒþ£¬ÇëÍš¹ýµç×ÓÓÊŒþÁ¢ŒŽÍšÖªÎÒÃÇ¡£Çë»ØžŽÓÊŒþµœ hqs-spmc@chinaunicom.cn£¬ŒŽ¿ÉÒÔÍË¶©ŽËÓÊŒþ¡£ÎÒÃÇœ«Á¢ŒŽœ«ÄúµÄÐÅÏ¢ŽÓÎÒÃÇµÄ·¢ËÍÄ¿ÂŒÖÐÉŸ³ý¡£ If you have received this email in error please notify us immediately by e-mail. Please reply to hqs-spmc(a)chinaunicom.cn ,you can unsubscribe from this mail. We will immediately remove your information from send catalogue of our.

2 1

Re: [openEuler-22.03-LTS,v1,0/6] Add perf metricgroup support for HiSilicon hip08 platform
by patchwork bot 23 Apr '23

23 Apr '23

your patch has been converted to a pull request, pull request link is: https://gitee.com/openeuler/kernel/pulls/609

1 0

[PATCH openEuler-22.03-LTS v1 0/6] Add perf metricgroup support for HiSilicon hip08 platform
by Wei Li 23 Apr '23

23 Apr '23

Add perf metricgroup support for HiSilicon hip08 platform, tested on Huawei D06 board. John Garry (6): perf metricgroup: Make find_metric() public with name change perf test: Handle metric reuse in pmu-events parsing test perf pmu: Add pmu_events_map__find() function to find the common PMU map for the system perf vendor events arm64: Add Hisi hip08 L1 metrics perf vendor events arm64: Add Hisi hip08 L2 metrics perf vendor events arm64: Add Hisi hip08 L3 metrics tools/perf/arch/arm64/util/Build | 1 + tools/perf/arch/arm64/util/pmu.c | 25 ++ .../arch/arm64/hisilicon/hip08/metrics.json | 233 ++++++++++++++++++ tools/perf/tests/pmu-events.c | 83 ++++++- tools/perf/util/metricgroup.c | 11 +- tools/perf/util/metricgroup.h | 3 +- tools/perf/util/pmu.c | 5 + tools/perf/util/pmu.h | 1 + tools/perf/util/s390-sample-raw.c | 4 +- 9 files changed, 356 insertions(+), 10 deletions(-) create mode 100644 tools/perf/arch/arm64/util/pmu.c create mode 100644 tools/perf/pmu-events/arch/arm64/hisilicon/hip08/metrics.json -- 2.25.1

1 6

[PATCH openEuler-1.0-LTS] audit: fix a memleak caused by auditing load module
by Yongqiang Liu 23 Apr '23

23 Apr '23

From: Li RongQing <lirongqing(a)baidu.com> mainline inclusion from mainline-v5.2-rc1 commit 95e0b46fcebd7dbf6850dee96046e4c4ddc7f69c category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I6X2LV CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- module.name will be allocated unconditionally when auditing load module, and audit_log_start() can fail with other reasons, or audit_log_exit maybe not called, caused module.name is not freed so free module.name in audit_free_context and __audit_syscall_exit unreferenced object 0xffff88af90837d20 (size 8): comm "modprobe", pid 1036, jiffies 4294704867 (age 3069.138s) hex dump (first 8 bytes): 69 78 67 62 65 00 ff ff ixgbe... backtrace: [<0000000008da28fe>] __audit_log_kern_module+0x33/0x80 [<00000000c1491e61>] load_module+0x64f/0x3850 [<000000007fc9ae3f>] __do_sys_init_module+0x218/0x250 [<0000000000d4a478>] do_syscall_64+0x117/0x400 [<000000004924ded8>] entry_SYSCALL_64_after_hwframe+0x49/0xbe [<000000007dc331dd>] 0xffffffffffffffff Fixes: ca86cad7380e3 ("audit: log module name on init_module") Signed-off-by: Zhang Yu <zhangyu31(a)baidu.com> Signed-off-by: Li RongQing <lirongqing(a)baidu.com> [PM: manual merge fixup in __audit_syscall_exit()] Signed-off-by: Paul Moore <paul(a)paul-moore.com> conflict: kernel/auditsc.c Signed-off-by: Yi Yang <yiyang13(a)huawei.com> Reviewed-by: cuigaosheng <cuigaosheng1(a)huawei.com> Reviewed-by: guozihua <guozihua(a)huawei.com> Reviewed-by: Wang Weiyang <wangweiyang2(a)huawei.com> Signed-off-by: Yongqiang Liu <liuyongqiang13(a)huawei.com> --- kernel/auditsc.c | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) diff --git a/kernel/auditsc.c b/kernel/auditsc.c index 1513873e23bd..57d30b75f7a2 100644 --- a/kernel/auditsc.c +++ b/kernel/auditsc.c @@ -881,6 +881,13 @@ static inline void audit_proctitle_free(struct audit_context *context) context->proctitle.len = 0; } +static inline void audit_free_module(struct audit_context *context) +{ + if (context->type == AUDIT_KERN_MODULE) { + kfree(context->module.name); + context->module.name = NULL; + } +} static inline void audit_free_names(struct audit_context *context) { struct audit_names *n, *next; @@ -964,6 +971,7 @@ int audit_alloc(struct task_struct *tsk) static inline void audit_free_context(struct audit_context *context) { + audit_free_module(context); audit_free_names(context); unroll_tree_refs(context, NULL, 0); free_tree_refs(context); @@ -1281,7 +1289,6 @@ static void show_special(struct audit_context *context, int *call_panic) audit_log_format(ab, "name="); if (context->module.name) { audit_log_untrustedstring(ab, context->module.name); - kfree(context->module.name); } else audit_log_format(ab, "(null)"); @@ -1583,6 +1590,7 @@ void __audit_syscall_exit(int success, long return_code) if (!list_empty(&context->killed_trees)) audit_kill_trees(&context->killed_trees); + audit_free_module(context); audit_free_names(context); unroll_tree_refs(context, NULL, 0); audit_free_aux(context); -- 2.25.1

1 0

[PATCH OLK-5.10 v1 0/6] Add perf metricgroup support for HiSilicon hip08 platform
by Wei Li 23 Apr '23

23 Apr '23

Add perf metricgroup support for HiSilicon hip08 platform, tested on Huawei D06 board. John Garry (6): perf metricgroup: Make find_metric() public with name change perf test: Handle metric reuse in pmu-events parsing test perf pmu: Add pmu_events_map__find() function to find the common PMU map for the system perf vendor events arm64: Add Hisi hip08 L1 metrics perf vendor events arm64: Add Hisi hip08 L2 metrics perf vendor events arm64: Add Hisi hip08 L3 metrics tools/perf/arch/arm64/util/Build | 1 + tools/perf/arch/arm64/util/pmu.c | 25 ++ .../arch/arm64/hisilicon/hip08/metrics.json | 233 ++++++++++++++++++ tools/perf/tests/pmu-events.c | 83 ++++++- tools/perf/util/metricgroup.c | 11 +- tools/perf/util/metricgroup.h | 3 +- tools/perf/util/pmu.c | 5 + tools/perf/util/pmu.h | 1 + tools/perf/util/s390-sample-raw.c | 4 +- 9 files changed, 356 insertions(+), 10 deletions(-) create mode 100644 tools/perf/arch/arm64/util/pmu.c create mode 100644 tools/perf/pmu-events/arch/arm64/hisilicon/hip08/metrics.json -- 2.25.1

2 7

Re: [PATCH v3] mm: oom: move memcg_print_bad_task() out of mem_cgroup_scan_tasks()
by Zheng Zengkai 22 Apr '23

22 Apr '23

在 2023/4/17 21:12, Kefeng Wang 写道: > + Zengkai > > Could you merge this patch? +zhangjialin Hi Kefeng and Kang Chen Is this patch same as the one in PR #582(https://gitee.com/openeuler/kernel/pulls/582) ? If so，let's tracking it via the gitee PR, Here are some notices about contribution to openEuler kernel: https://gitee.com/openeuler/kernel/issues/I6WKLA Thank you! > > On 2023/4/17 19:13, Kang Chen wrote: >> hulk inclusion >> category: bugfix >> bugzilla: https://gitee.com/src-openeuler/kernel/issues/I6NYW4 >> CVE: NA >> >> -------------------------------- >> >> raw call flow: >> >> oom_kill_process >> -> mem_cgroup_scan_tasks(.., .., message) >> -> memcg_print_bad_task(message, ..) >> >> message is "const char*" type, and incorrectly cast to >> "oom_control*" type in memcg_print_bad_task. > > a blank line, > >> Fix it by moving memcg_print_bad_task out of mem_cgroup_scan_tasks >> and call it in select_bad_process and dump_tasks. Furthermore, >> use struct oom_control* directly and remove the useless parm `ret`. >> > > Reviewed-by: Kefeng Wang <wangkefeng.wang(a)huawei.com> > >> Signed-off-by: Kang Chen <void0red(a)hust.edu.cn> >> --- >> v3 -> v2: use type `struct oom_control *` directly and fix bugs >> v2 -> v1: remove parm `ret` and create a memcg_print_bad_task stub >> >> mm/memcontrol.c | 16 +++++++++------- >> mm/oom_kill.c | 14 ++++++++------ >> 2 files changed, 17 insertions(+), 13 deletions(-) >> >> diff --git a/mm/memcontrol.c b/mm/memcontrol.c >> index 635cb8b65b86..6b4f70d090d6 100644 >> --- a/mm/memcontrol.c >> +++ b/mm/memcontrol.c >> @@ -1214,9 +1214,6 @@ int mem_cgroup_scan_tasks(struct mem_cgroup >> *memcg, >> break; >> } >> } >> -#ifdef CONFIG_MEMCG_QOS >> - memcg_print_bad_task(arg, ret); >> -#endif >> return ret; >> } >> @@ -4004,14 +4001,12 @@ bool memcg_low_priority_scan_tasks(int >> (*fn)(struct task_struct *, void *), >> return oc->chosen ? true : false; >> } >> -void memcg_print_bad_task(void *arg, int ret) >> +void memcg_print_bad_task(struct oom_control *oc) >> { >> - struct oom_control *oc = arg; >> - >> if (!static_branch_likely(&memcg_qos_stat_key)) >> return; >> - if (!ret && oc->chosen) { >> + if (oc->chosen) { >> struct mem_cgroup *memcg; >> memcg = mem_cgroup_from_task(oc->chosen); >> @@ -4042,6 +4037,13 @@ int sysctl_memcg_qos_handler(struct ctl_table >> *table, int write, >> return ret; >> } >> + >> +#else >> + >> +void memcg_print_bad_task(struct oom_control *oc) >> +{ >> +} >> + >> #endif >> #ifdef CONFIG_NUMA >> diff --git a/mm/oom_kill.c b/mm/oom_kill.c >> index 0f77eb4c6644..9d595265bbf5 100644 >> --- a/mm/oom_kill.c >> +++ b/mm/oom_kill.c >> @@ -408,9 +408,10 @@ static void select_bad_process(struct >> oom_control *oc) >> { >> oc->chosen_points = LONG_MIN; >> - if (is_memcg_oom(oc)) >> - mem_cgroup_scan_tasks(oc->memcg, oom_evaluate_task, oc); >> - else { >> + if (is_memcg_oom(oc)) { >> + if (!mem_cgroup_scan_tasks(oc->memcg, oom_evaluate_task, oc)) >> + memcg_print_bad_task(oc); >> + } else { >> struct task_struct *p; >> #ifdef CONFIG_MEMCG_QOS >> @@ -473,9 +474,10 @@ static void dump_tasks(struct oom_control *oc) >> pr_info("Tasks state (memory values in pages):\n"); >> pr_info("[ pid ] uid tgid total_vm rss pgtables_bytes >> swapents oom_score_adj name\n"); >> - if (is_memcg_oom(oc)) >> - mem_cgroup_scan_tasks(oc->memcg, dump_task, oc); >> - else { >> + if (is_memcg_oom(oc)) { >> + if (!mem_cgroup_scan_tasks(oc->memcg, dump_task, oc)) >> + memcg_print_bad_task(oc); >> + } else { >> struct task_struct *p; >> rcu_read_lock(); > . >

3 2

[PATCH openEuler-1.0-LTS 0/6] efi: fix crash due to EFI runtime service page faults
by Ding Hui 20 Apr '23

20 Apr '23

For both arm64 and x86, handle and recovery from page faults due to EFI runtime service, and disable subsequent invoking, we can avoid crash the whole system when running on buggy EFI firmware, and get log like this: kernel: [Firmware Bug]: Unable to handle paging request in EFI runtime service kernel: CPU: 54 PID: 8 Comm: kworker/u256:0 Kdump: loaded Tainted: G IOE 4.19.90-2112.8.0.0131.oe1.aarch64.debug #66 kernel: Hardware name: O.D.M FT-2500 Platform/T1DMFT-E4 , BIOS KL4.26.ODM.S.032.210904.R 09/04/21 13:28:40 kernel: Workqueue: efi_rts_wq efi_call_rts kernel: Call trace: kernel: dump_backtrace+0x0/0x170 kernel: show_stack+0x24/0x30 kernel: dump_stack+0xa4/0xe8 kernel: efi_runtime_fixup_exception+0x74/0x8c kernel: __do_kernel_fault+0x8c/0x150 kernel: do_page_fault+0x78/0x4c8 kernel: do_translation_fault+0xa8/0xbc kernel: do_mem_abort+0x50/0xe0 kernel: el1_da+0x20/0x94 kernel: 0x213f0c24 kernel: 0x213f0d64 kernel: 0x213f044c kernel: 0x213f04b4 kernel: 0x213f0178 kernel: 0x212e0664 kernel: __efi_rt_asm_wrapper+0x50/0x6c kernel: efi_call_rts+0x414/0x430 kernel: process_one_work+0x1f8/0x490 kernel: worker_thread+0x50/0x4b8 kernel: kthread+0x134/0x138 kernel: ret_from_fork+0x10/0x18 kernel: [Firmware Bug]: Synchronous exception occurred in EFI runtime service get_time() kernel: rtc-efi rtc-efi: can't read time kernel: efi: EFI Runtime Services are disabled! Anders Roxell (1): efi: Fix build error due to enum collision between efi.h and ima.h Ard Biesheuvel (1): arm64: efi: Recover from synchronous exceptions occurring in firmware Sai Praneeth (2): efi: Make efi_rts_work accessible to efi page fault handler efi/x86: Handle page faults occurring while running EFI runtime services Sami Tolvanen (1): arm64: efi: Restore register x18 if it was corrupted Waiman Long (1): efi: Fix debugobjects warning on 'efi_rts_work' arch/arm64/include/asm/efi.h | 9 ++ arch/arm64/kernel/efi-rt-wrapper.S | 46 +++++++++- arch/arm64/kernel/efi.c | 26 ++++++ arch/arm64/mm/fault.c | 4 + arch/x86/include/asm/efi.h | 1 + arch/x86/mm/fault.c | 9 ++ arch/x86/platform/efi/quirks.c | 78 +++++++++++++++++ drivers/firmware/efi/runtime-wrappers.c | 107 +++++++++--------------- include/linux/efi.h | 42 ++++++++++ 9 files changed, 252 insertions(+), 70 deletions(-) -- 2.17.1

1 6

[PATCH openEuler-1.0-LTS] iommu/arm-smmu-v3: Fix UAF when handle evt during iommu group removing
by Ding Hui 20 Apr '23

20 Apr '23

driver inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I6WKM7 CVE: NA -------- A use-after-free issue like following: [ 2257.819189] arm-smmu-v3 arm-smmu-v3.4.auto: EVTQ overflow detected -- events lost [ 2257.819197] arm-smmu-v3 arm-smmu-v3.4.auto: event 0x10 received: [ 2257.819199] arm-smmu-v3 arm-smmu-v3.4.auto: 0x0000820000000010 [ 2257.819201] arm-smmu-v3 arm-smmu-v3.4.auto: 0x0000020000000000 [ 2257.819202] arm-smmu-v3 arm-smmu-v3.4.auto: 0x00000000dfea7218 [ 2257.819206] iommu: Removing device 0000:82:00.0 from group 49 [ 2257.819207] arm-smmu-v3 arm-smmu-v3.4.auto: 0x00000000dfea7000 [ 2257.819211] arm-smmu-v3 arm-smmu-v3.4.auto: event 0x10 received: [ 2257.819212] arm-smmu-v3 arm-smmu-v3.4.auto: 0x0000820000000010 [ 2257.819214] arm-smmu-v3 arm-smmu-v3.4.auto: 0x0000020000000000 [ 2257.819215] arm-smmu-v3 arm-smmu-v3.4.auto: 0x00000000dfea722c [ 2257.819216] arm-smmu-v3 arm-smmu-v3.4.auto: 0x00000000dfea7000 [ 2257.819218] ================================================================== [ 2257.819228] BUG: KASAN: use-after-free in iommu_report_device_fault+0x520/0x5c0 [ 2257.819230] Read of size 8 at addr ffffa02c516c1320 by task irq/63-arm-smmu/483 [ 2257.819231] [ 2257.819235] CPU: 25 PID: 483 Comm: irq/63-arm-smmu Kdump: loaded Tainted: G OE 4.19.90-2205.3.0.0149.oe1.aarch64+debug #1 [ 2257.819236] Hardware name: Huawei S920S00/BC82AMDGK, BIOS 1.68 11/10/2020 [ 2257.819237] Call trace: [ 2257.819240] dump_backtrace+0x0/0x320 [ 2257.819242] show_stack+0x24/0x30 [ 2257.819246] dump_stack+0xdc/0x128 [ 2257.819251] print_address_description+0x68/0x278 [ 2257.819253] kasan_report+0x1e4/0x308 [ 2257.819254] __asan_report_load8_noabort+0x30/0x40 [ 2257.819257] iommu_report_device_fault+0x520/0x5c0 [ 2257.819260] arm_smmu_handle_evt+0x300/0x428 [ 2257.819261] arm_smmu_evtq_thread+0x27c/0x460 [ 2257.819264] irq_thread_fn+0x88/0x140 [ 2257.819266] irq_thread+0x190/0x318 [ 2257.819268] kthread+0x2a4/0x320 [ 2257.819270] ret_from_fork+0x10/0x18 [ 2257.819271] [ 2257.819273] Allocated by task 95166: [ 2257.819275] kasan_kmalloc+0xd0/0x178 [ 2257.819277] kmem_cache_alloc_trace+0x100/0x210 [ 2257.819279] iommu_group_add_device+0x254/0xe18 [ 2257.819280] iommu_group_get_for_dev+0x198/0x480 [ 2257.819282] arm_smmu_add_device+0x424/0x988 [ 2257.819284] iort_iommu_configure+0x33c/0x5b8 [ 2257.819287] acpi_dma_configure+0x9c/0xf8 [ 2257.819289] pci_dma_configure+0x124/0x158 [ 2257.819291] dma_configure+0x5c/0x80 [ 2257.819294] really_probe+0xcc/0x920 [ 2257.819296] driver_probe_device+0x224/0x308 [ 2257.819298] __device_attach_driver+0x154/0x260 [ 2257.819299] bus_for_each_drv+0xe4/0x178 [ 2257.819301] __device_attach+0x1bc/0x2a8 [ 2257.819302] device_attach+0x24/0x30 [ 2257.819304] pci_bus_add_device+0x7c/0xe8 [ 2257.819305] pci_bus_add_devices+0x70/0x168 [ 2257.819307] pci_bus_add_devices+0x114/0x168 [ 2257.819308] pci_rescan_bus+0x38/0x48 [ 2257.819310] bus_rescan_store+0xc4/0xe8 [ 2257.819312] bus_attr_store+0x70/0x98 [ 2257.819314] sysfs_kf_write+0x104/0x170 [ 2257.819316] kernfs_fop_write+0x23c/0x430 [ 2257.819319] __vfs_write+0x7c/0xe8 [ 2257.819320] vfs_write+0x12c/0x3d0 [ 2257.819321] ksys_write+0xd4/0x1d8 [ 2257.819322] __arm64_sys_write+0x70/0xa0 [ 2257.819325] el0_svc_common+0xfc/0x278 [ 2257.819327] el0_svc_handler+0x50/0xc0 [ 2257.819329] el0_svc+0x8/0x1b0 [ 2257.819329] [ 2257.819330] Freed by task 95166: [ 2257.819332] __kasan_slab_free+0x114/0x200 [ 2257.819334] kasan_slab_free+0x10/0x18 [ 2257.819335] kfree+0x80/0x1f0 [ 2257.819337] iommu_group_remove_device+0x27c/0x560 [ 2257.819338] arm_smmu_remove_device+0xe8/0x190 [ 2257.819339] iommu_bus_notifier+0x134/0x248 [ 2257.819342] notifier_call_chain+0xb0/0x140 [ 2257.819343] blocking_notifier_call_chain+0x6c/0xd8 [ 2257.819344] device_del+0x578/0x940 [ 2257.819346] pci_remove_bus_device+0x114/0x290 [ 2257.819347] pci_stop_and_remove_bus_device_locked+0x2c/0x40 [ 2257.819349] remove_store+0xdc/0xe8 [ 2257.819352] dev_attr_store+0x60/0x80 [ 2257.819353] sysfs_kf_write+0x104/0x170 [ 2257.819354] kernfs_fop_write+0x23c/0x430 [ 2257.819355] __vfs_write+0x7c/0xe8 [ 2257.819357] vfs_write+0x12c/0x3d0 [ 2257.819358] ksys_write+0xd4/0x1d8 [ 2257.819359] __arm64_sys_write+0x70/0xa0 [ 2257.819361] el0_svc_common+0xfc/0x278 [ 2257.819362] el0_svc_handler+0x50/0xc0 [ 2257.819364] el0_svc+0x8/0x1b0 [ 2257.819364] T0 T1 --------------------------------- --------------------------------- |- arm_smmu_evtq_thread |- arm_smmu_remove_device |- arm_smmu_handle_evt |- iommu_group_remove_device |- kfree(dev->iommu_param) |- arm_smmu_find_master |- iommu_report_device_fault |- arm_smmu_remove_master |- mutex_lock( \ &dev->iommu_param->lock) // UAF Reference upstream mainline commit 395ad89d11fd93f79a6b942e91fc409807a63c4b, move arm_smmu_remove_master() before iommu_group_remove_device(), and hold mutex to protect finding master and subsequent handling. Fixes: b525f0a6f9b0 ("iommu/arm-smmu-v3: Add stall support for platform devices") Signed-off-by: Ding Hui <dinghui(a)sangfor.com.cn> --- drivers/iommu/arm-smmu-v3.c | 15 ++++++++++----- 1 file changed, 10 insertions(+), 5 deletions(-) diff --git a/drivers/iommu/arm-smmu-v3.c b/drivers/iommu/arm-smmu-v3.c index 3309ae6ebc0b..05cb92da6836 100644 --- a/drivers/iommu/arm-smmu-v3.c +++ b/drivers/iommu/arm-smmu-v3.c @@ -1742,7 +1742,8 @@ arm_smmu_find_master(struct arm_smmu_device *smmu, u32 sid) struct arm_smmu_stream *stream; struct arm_smmu_master_data *master = NULL; - mutex_lock(&smmu->streams_mutex); + lockdep_assert_held(&smmu->streams_mutex); + node = smmu->streams.rb_node; while (node) { stream = rb_entry(node, struct arm_smmu_stream, node); @@ -1755,7 +1756,6 @@ arm_smmu_find_master(struct arm_smmu_device *smmu, u32 sid) break; } } - mutex_unlock(&smmu->streams_mutex); return master; } @@ -1791,9 +1791,12 @@ static int arm_smmu_handle_evt(struct arm_smmu_device *smmu, u64 *evt) if (evt[1] & EVTQ_1_S2) return -EFAULT; + mutex_lock(&smmu->streams_mutex); master = arm_smmu_find_master(smmu, sid); - if (!master) - return -EINVAL; + if (!master) { + ret = -EINVAL; + goto out_unlock; + } /* * The domain is valid until the fault returns, because detach() flushes @@ -1833,6 +1836,8 @@ static int arm_smmu_handle_evt(struct arm_smmu_device *smmu, u64 *evt) arm_smmu_page_response(master->dev, &resp); } +out_unlock: + mutex_unlock(&smmu->streams_mutex); return ret; } @@ -2935,8 +2940,8 @@ static void arm_smmu_remove_device(struct device *dev) iopf_queue_remove_device(dev); if (master->ste.assigned) arm_smmu_detach_dev(dev); - iommu_group_remove_device(dev); arm_smmu_remove_master(smmu, master); + iommu_group_remove_device(dev); iommu_device_unlink(&smmu->iommu, dev); kfree(master); iommu_fwspec_free(dev); -- 2.17.1

1 0

ODD2023-Kernel SIG 开放工作会议
by openEuler conference 19 Apr '23

19 Apr '23

您好！ Kernel SIG 邀请您参加 2023-04-21 16:00 召开的Zoom会议(自动录制) 会议主题：ODD2023-Kernel SIG 开放工作会议会议内容： 1. 华中大网安学院内核贡献团队组建经验分享 2. 互联网领域的挑战与技术 3. ext4文件系统问题（一致性、稳定性）的挖掘和定位 4. 可编程内核技术落地场景分享和未来畅想欢迎继续申报议题~ 会议链接：https://us06web.zoom.us/j/88277699752?pwd=VTB3ZjhFR1pKd0syc3NpMDVDcVRvZz09 会议纪要：https://etherpad.openeuler.org/p/ODD2023_Kernel_SIG 温馨提醒：建议接入会议后修改参会人的姓名，也可以使用您在gitee.com的ID 更多资讯尽在：https://openeuler.org/zh/ Hello! openEuler Kernel SIG invites you to attend the Zoom conference(auto recording) will be held at 2023-04-21 16:00, The subject of the conference is ODD2023-Kernel SIG 开放工作会议, Summary: 1. 华中大网安学院内核贡献团队组建经验分享 2. 互联网领域的挑战与技术 3. ext4文件系统问题（一致性、稳定性）的挖掘和定位 4. 可编程内核技术落地场景分享和未来畅想欢迎继续申报议题~ You can join the meeting at https://us06web.zoom.us/j/88277699752?pwd=VTB3ZjhFR1pKd0syc3NpMDVDcVRvZz09. Add topics at https://etherpad.openeuler.org/p/ODD2023_Kernel_SIG. Note: You are advised to change the participant name after joining the conference or use your ID at gitee.com. More information: https://openeuler.org/en/

1 0

一文解锁 → openEuler Developer Day 2023 游玩指南
by openEuler 19 Apr '23

19 Apr '23

1 0

[PATCH openEuler-1.0-LTS 1/2] x86/speculation: Allow enabling STIBP with legacy IBRS
by Yongqiang Liu 19 Apr '23

19 Apr '23

From: KP Singh <kpsingh(a)kernel.org> stable inclusion from stable-v4.19.276 commit 10543fb3c9b019e45e2045f08f46fdf526add593 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I6V7TU CVE: CVE-2023-1998 -------------------------------- commit 6921ed9049bc7457f66c1596c5b78aec0dae4a9d upstream. When plain IBRS is enabled (not enhanced IBRS), the logic in spectre_v2_user_select_mitigation() determines that STIBP is not needed. The IBRS bit implicitly protects against cross-thread branch target injection. However, with legacy IBRS, the IBRS bit is cleared on returning to userspace for performance reasons which leaves userspace threads vulnerable to cross-thread branch target injection against which STIBP protects. Exclude IBRS from the spectre_v2_in_ibrs_mode() check to allow for enabling STIBP (through seccomp/prctl() by default or always-on, if selected by spectre_v2_user kernel cmdline parameter). [ bp: Massage. ] Fixes: 7c693f54c873 ("x86/speculation: Add spectre_v2=ibrs option to support Kernel IBRS") Reported-by: José Oliveira <joseloliveira11(a)gmail.com> Reported-by: Rodrigo Branco <rodrigo(a)kernelhacking.com> Signed-off-by: KP Singh <kpsingh(a)kernel.org> Signed-off-by: Borislav Petkov (AMD) <bp(a)alien8.de> Cc: stable(a)vger.kernel.org Link: https://lore.kernel.org/r/20230220120127.1975241-1-kpsingh@kernel.org Link: https://lore.kernel.org/r/20230221184908.2349578-1-kpsingh@kernel.org Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Wei Li <liwei391(a)huawei.com> Reviewed-by: Wang Weiyang <wangweiyang2(a)huawei.com> Reviewed-by: Xiongfeng Wang <wangxiongfeng2(a)huawei.com> Signed-off-by: Yongqiang Liu <liuyongqiang13(a)huawei.com> --- arch/x86/kernel/cpu/bugs.c | 25 ++++++++++++++++++------- 1 file changed, 18 insertions(+), 7 deletions(-) diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 836000481438..a7becbe9a890 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -973,14 +973,18 @@ spectre_v2_parse_user_cmdline(void) return SPECTRE_V2_USER_CMD_AUTO; } -static inline bool spectre_v2_in_ibrs_mode(enum spectre_v2_mitigation mode) +static inline bool spectre_v2_in_eibrs_mode(enum spectre_v2_mitigation mode) { - return mode == SPECTRE_V2_IBRS || - mode == SPECTRE_V2_EIBRS || + return mode == SPECTRE_V2_EIBRS || mode == SPECTRE_V2_EIBRS_RETPOLINE || mode == SPECTRE_V2_EIBRS_LFENCE; } +static inline bool spectre_v2_in_ibrs_mode(enum spectre_v2_mitigation mode) +{ + return spectre_v2_in_eibrs_mode(mode) || mode == SPECTRE_V2_IBRS; +} + static void __init spectre_v2_user_select_mitigation(void) { @@ -1043,12 +1047,19 @@ spectre_v2_user_select_mitigation(void) } /* - * If no STIBP, IBRS or enhanced IBRS is enabled, or SMT impossible, - * STIBP is not required. + * If no STIBP, enhanced IBRS is enabled, or SMT impossible, STIBP + * is not required. + * + * Enhanced IBRS also protects against cross-thread branch target + * injection in user-mode as the IBRS bit remains always set which + * implicitly enables cross-thread protections. However, in legacy IBRS + * mode, the IBRS bit is set only on kernel entry and cleared on return + * to userspace. This disables the implicit cross-thread protection, + * so allow for STIBP to be selected in that case. */ if (!boot_cpu_has(X86_FEATURE_STIBP) || !smt_possible || - spectre_v2_in_ibrs_mode(spectre_v2_enabled)) + spectre_v2_in_eibrs_mode(spectre_v2_enabled)) return; /* @@ -2084,7 +2095,7 @@ static ssize_t mmio_stale_data_show_state(char *buf) static char *stibp_state(void) { - if (spectre_v2_in_ibrs_mode(spectre_v2_enabled)) + if (spectre_v2_in_eibrs_mode(spectre_v2_enabled)) return ""; switch (spectre_v2_user_stibp) { -- 2.25.1

1 1

[PATCH openEuler-22.03-LTS 00/26] Backport CVEs and bugfixes
by Jialin Zhang 18 Apr '23

18 Apr '23

Pull new CVEs: CVE-2023-1829 CVE-2022-36280 CVE-2022-1015 CVE-2023-1989 CVE-2023-30456 CVE-2023-1990 xfs bugfixes from Long Li and yangerkun

1 26

[PATCH openEuler-22.03-LTS-SP1 00/26] Backport CVEs and bugfixes
by Jialin Zhang 18 Apr '23

18 Apr '23

Pull new CVEs: CVE-2023-1829 CVE-2022-36280 CVE-2022-1015 CVE-2023-1989 CVE-2023-30456 CVE-2023-1990 xfs bugfixes from Long Li and yangerkun

1 26

[PATCH OLK-5.10 00/26] Backport CVEs and bugfixes
by Jialin Zhang 18 Apr '23

18 Apr '23

Pull new CVEs: CVE-2023-1829 CVE-2022-36280 CVE-2022-1015 CVE-2023-1989 CVE-2023-30456 CVE-2023-1990 xfs bugfixes from Long Li and yangerkun

1 26

[PATCH OLK-5.10 000/370] Backport 5.10.150 LTS
by Jialin Zhang 18 Apr '23

18 Apr '23

Backport 5.10.150 LTS patches from upstream. Conflicts: Already merged(19): f039b43cbaea inet: fully convert sk->sk_rx_dst to RCU rules 45c33966759e mm: hugetlb: fix UAF in hugetlb_handle_userfault c378c479c517 io_uring/af_unix: defer registered files gc to io_uring release 67cbc8865a66 io_uring: correct pinned_vm accounting 904f881b5736 arm64: topology: fix possible overflow in amu_fie_setup() dbcca76435a6 HID: roccat: Fix use-after-free in roccat_read() 484400d433ca r8152: Rate limit overflow messages d88b88514ef2 crypto: hisilicon/zip - fix mismatch in get/set sgl_sge_nr 657de36c72f5 arm64: ftrace: fix module PLTs with mcount 29f50bcf0f8b net: mvpp2: fix mvpp2 debugfs leak 6cc0e2afc6a1 bnx2x: fix potential memory leak in bnx2x_tpa_stop() 2a1d03632085 mISDN: fix use-after-free bugs in l1oip timer handlers 0cf6c09dafee ring-buffer: Fix race between reset page and reading page fbb0e601bd51 ext4: ext4_read_bh_lock() should submit IO if the buffer isn't uptodate 483831ad0440 ext4: fix check for block being out of directory size f34ab9516276 ext4: fix null-ptr-deref in ext4_write_info e50472949604 fbdev: smscufx: Fix use-after-free in ufx_ops_open() 7d551b7d6114 block: fix inflight statistics of part0 6b7ae4a904a4 quota: Check next/prev free block number after reading from quota file Context conflict(1): c13d0d2f5a48 usb: host: xhci-plat: suspend and resume clocks Total patches: 389 - 19 = 370

1 370

[PATCH OLK-5.10] x86/speculation: Allow enabling STIBP with legacy IBRS
by Wei Li 18 Apr '23

18 Apr '23

From: KP Singh <kpsingh(a)kernel.org> stable inclusion from stable-v5.10.173 commit abfed855f05863d292de2d0ebab4656791bab9c8 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I6V7TU CVE: CVE-2023-1998 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- commit 6921ed9049bc7457f66c1596c5b78aec0dae4a9d upstream. When plain IBRS is enabled (not enhanced IBRS), the logic in spectre_v2_user_select_mitigation() determines that STIBP is not needed. The IBRS bit implicitly protects against cross-thread branch target injection. However, with legacy IBRS, the IBRS bit is cleared on returning to userspace for performance reasons which leaves userspace threads vulnerable to cross-thread branch target injection against which STIBP protects. Exclude IBRS from the spectre_v2_in_ibrs_mode() check to allow for enabling STIBP (through seccomp/prctl() by default or always-on, if selected by spectre_v2_user kernel cmdline parameter). [ bp: Massage. ] Fixes: 7c693f54c873 ("x86/speculation: Add spectre_v2=ibrs option to support Kernel IBRS") Reported-by: José Oliveira <joseloliveira11(a)gmail.com> Reported-by: Rodrigo Branco <rodrigo(a)kernelhacking.com> Signed-off-by: KP Singh <kpsingh(a)kernel.org> Signed-off-by: Borislav Petkov (AMD) <bp(a)alien8.de> Cc: stable(a)vger.kernel.org Link: https://lore.kernel.org/r/20230220120127.1975241-1-kpsingh@kernel.org Link: https://lore.kernel.org/r/20230221184908.2349578-1-kpsingh@kernel.org Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Wei Li <liwei391(a)huawei.com> --- arch/x86/kernel/cpu/bugs.c | 25 ++++++++++++++++++------- 1 file changed, 18 insertions(+), 7 deletions(-) diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 25f3fad210e0..0dd4f8a8d821 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -1051,14 +1051,18 @@ spectre_v2_parse_user_cmdline(void) return SPECTRE_V2_USER_CMD_AUTO; } -static inline bool spectre_v2_in_ibrs_mode(enum spectre_v2_mitigation mode) +static inline bool spectre_v2_in_eibrs_mode(enum spectre_v2_mitigation mode) { - return mode == SPECTRE_V2_IBRS || - mode == SPECTRE_V2_EIBRS || + return mode == SPECTRE_V2_EIBRS || mode == SPECTRE_V2_EIBRS_RETPOLINE || mode == SPECTRE_V2_EIBRS_LFENCE; } +static inline bool spectre_v2_in_ibrs_mode(enum spectre_v2_mitigation mode) +{ + return spectre_v2_in_eibrs_mode(mode) || mode == SPECTRE_V2_IBRS; +} + static void __init spectre_v2_user_select_mitigation(void) { @@ -1121,12 +1125,19 @@ spectre_v2_user_select_mitigation(void) } /* - * If no STIBP, IBRS or enhanced IBRS is enabled, or SMT impossible, - * STIBP is not required. + * If no STIBP, enhanced IBRS is enabled, or SMT impossible, STIBP + * is not required. + * + * Enhanced IBRS also protects against cross-thread branch target + * injection in user-mode as the IBRS bit remains always set which + * implicitly enables cross-thread protections. However, in legacy IBRS + * mode, the IBRS bit is set only on kernel entry and cleared on return + * to userspace. This disables the implicit cross-thread protection, + * so allow for STIBP to be selected in that case. */ if (!boot_cpu_has(X86_FEATURE_STIBP) || !smt_possible || - spectre_v2_in_ibrs_mode(spectre_v2_enabled)) + spectre_v2_in_eibrs_mode(spectre_v2_enabled)) return; /* @@ -2220,7 +2231,7 @@ static ssize_t mmio_stale_data_show_state(char *buf) static char *stibp_state(void) { - if (spectre_v2_in_ibrs_mode(spectre_v2_enabled)) + if (spectre_v2_in_eibrs_mode(spectre_v2_enabled)) return ""; switch (spectre_v2_user_stibp) { -- 2.25.1

1 0

[PATCH v3] mm: oom: move memcg_print_bad_task() out of mem_cgroup_scan_tasks()
by Kang Chen 17 Apr '23

17 Apr '23

hulk inclusion category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I6NYW4 CVE: NA -------------------------------- raw call flow: oom_kill_process -> mem_cgroup_scan_tasks(.., .., message) -> memcg_print_bad_task(message, ..) message is "const char*" type, and incorrectly cast to "oom_control*" type in memcg_print_bad_task. Fix it by moving memcg_print_bad_task out of mem_cgroup_scan_tasks and call it in select_bad_process and dump_tasks. Furthermore, use struct oom_control* directly and remove the useless parm `ret`. Signed-off-by: Kang Chen <void0red(a)hust.edu.cn> --- v3 -> v2: use type `struct oom_control *` directly and fix bugs v2 -> v1: remove parm `ret` and create a memcg_print_bad_task stub mm/memcontrol.c | 16 +++++++++------- mm/oom_kill.c | 14 ++++++++------ 2 files changed, 17 insertions(+), 13 deletions(-) diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 635cb8b65b86..6b4f70d090d6 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -1214,9 +1214,6 @@ int mem_cgroup_scan_tasks(struct mem_cgroup *memcg, break; } } -#ifdef CONFIG_MEMCG_QOS - memcg_print_bad_task(arg, ret); -#endif return ret; } @@ -4004,14 +4001,12 @@ bool memcg_low_priority_scan_tasks(int (*fn)(struct task_struct *, void *), return oc->chosen ? true : false; } -void memcg_print_bad_task(void *arg, int ret) +void memcg_print_bad_task(struct oom_control *oc) { - struct oom_control *oc = arg; - if (!static_branch_likely(&memcg_qos_stat_key)) return; - if (!ret && oc->chosen) { + if (oc->chosen) { struct mem_cgroup *memcg; memcg = mem_cgroup_from_task(oc->chosen); @@ -4042,6 +4037,13 @@ int sysctl_memcg_qos_handler(struct ctl_table *table, int write, return ret; } + +#else + +void memcg_print_bad_task(struct oom_control *oc) +{ +} + #endif #ifdef CONFIG_NUMA diff --git a/mm/oom_kill.c b/mm/oom_kill.c index 0f77eb4c6644..9d595265bbf5 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -408,9 +408,10 @@ static void select_bad_process(struct oom_control *oc) { oc->chosen_points = LONG_MIN; - if (is_memcg_oom(oc)) - mem_cgroup_scan_tasks(oc->memcg, oom_evaluate_task, oc); - else { + if (is_memcg_oom(oc)) { + if (!mem_cgroup_scan_tasks(oc->memcg, oom_evaluate_task, oc)) + memcg_print_bad_task(oc); + } else { struct task_struct *p; #ifdef CONFIG_MEMCG_QOS @@ -473,9 +474,10 @@ static void dump_tasks(struct oom_control *oc) pr_info("Tasks state (memory values in pages):\n"); pr_info("[ pid ] uid tgid total_vm rss pgtables_bytes swapents oom_score_adj name\n"); - if (is_memcg_oom(oc)) - mem_cgroup_scan_tasks(oc->memcg, dump_task, oc); - else { + if (is_memcg_oom(oc)) { + if (!mem_cgroup_scan_tasks(oc->memcg, dump_task, oc)) + memcg_print_bad_task(oc); + } else { struct task_struct *p; rcu_read_lock(); -- 2.34.1

1 0

[PATCH openEuler-1.0-LTS] nfc: st-nci: Fix use after free bug in ndlc_remove due to race condition
by Yongqiang Liu 17 Apr '23

17 Apr '23

From: Zheng Wang <zyytlz.wz(a)163.com> mainline inclusion from mainline-v6.3-rc3 commit 5000fe6c27827a61d8250a7e4a1d26c3298ef4f6 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I6UW64 CVE: CVE-2023-1990 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit?i… -------------------------------- This bug influences both st_nci_i2c_remove and st_nci_spi_remove. Take st_nci_i2c_remove as an example. In st_nci_i2c_probe, it called ndlc_probe and bound &ndlc->sm_work with llt_ndlc_sm_work. When it calls ndlc_recv or timeout handler, it will finally call schedule_work to start the work. When we call st_nci_i2c_remove to remove the driver, there may be a sequence as follows: Fix it by finishing the work before cleanup in ndlc_remove CPU0 CPU1 |llt_ndlc_sm_work st_nci_i2c_remove | ndlc_remove | st_nci_remove | nci_free_device| kfree(ndev) | //free ndlc->ndev | |llt_ndlc_rcv_queue |nci_recv_frame |//use ndlc->ndev Fixes: 35630df68d60 ("NFC: st21nfcb: Add driver for STMicroelectronics ST21NFCB NFC chip") Signed-off-by: Zheng Wang <zyytlz.wz(a)163.com> Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski(a)linaro.org> Link: https://lore.kernel.org/r/20230312160837.2040857-1-zyytlz.wz@163.com Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> Signed-off-by: Wei Li <liwei391(a)huawei.com> Reviewed-by: Xiongfeng Wang <wangxiongfeng2(a)huawei.com> Reviewed-by: Wang Weiyang <wangweiyang2(a)huawei.com> Signed-off-by: Yongqiang Liu <liuyongqiang13(a)huawei.com> --- drivers/nfc/st-nci/ndlc.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/nfc/st-nci/ndlc.c b/drivers/nfc/st-nci/ndlc.c index f26d938d240f..12d73f9dbe9f 100644 --- a/drivers/nfc/st-nci/ndlc.c +++ b/drivers/nfc/st-nci/ndlc.c @@ -297,13 +297,15 @@ EXPORT_SYMBOL(ndlc_probe); void ndlc_remove(struct llt_ndlc *ndlc) { - st_nci_remove(ndlc->ndev); - /* cancel timers */ del_timer_sync(&ndlc->t1_timer); del_timer_sync(&ndlc->t2_timer); ndlc->t2_active = false; ndlc->t1_active = false; + /* cancel work */ + cancel_work_sync(&ndlc->sm_work); + + st_nci_remove(ndlc->ndev); skb_queue_purge(&ndlc->rcv_q); skb_queue_purge(&ndlc->send_q); -- 2.25.1

1 0

[PATCH v2] mm: oom: move memcg_print_bad_task() out of mem_cgroup_scan_tasks()
by Kang Chen 17 Apr '23

17 Apr '23

hulk inclusion category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I6NYW4 CVE: NA -------------------------------- raw call flow: oom_kill_process -> mem_cgroup_scan_tasks(.., .., message) -> memcg_print_bad_task(message, ..) message is "const char*" type, and incorrectly cast to "oom_control*" type in memcg_print_bad_task. Fix it by moving memcg_print_bad_task out of mem_cgroup_scan_tasks and call it in select_bad_process and dump_tasks. Furthermore, remove the useless parm `ret`. Signed-off-by: Kang Chen <void0red(a)hust.edu.cn> --- v2 -> v1: remove parm `ret` and create a memcg_print_bad_task stub mm/memcontrol.c | 14 +++++++++----- mm/oom_kill.c | 14 ++++++++------ 2 files changed, 17 insertions(+), 11 deletions(-) diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 635cb8b65b86..e87a96a6c712 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -1214,9 +1214,6 @@ int mem_cgroup_scan_tasks(struct mem_cgroup *memcg, break; } } -#ifdef CONFIG_MEMCG_QOS - memcg_print_bad_task(arg, ret); -#endif return ret; } @@ -4004,14 +4001,14 @@ bool memcg_low_priority_scan_tasks(int (*fn)(struct task_struct *, void *), return oc->chosen ? true : false; } -void memcg_print_bad_task(void *arg, int ret) +void memcg_print_bad_task(void *arg) { struct oom_control *oc = arg; if (!static_branch_likely(&memcg_qos_stat_key)) return; - if (!ret && oc->chosen) { + if (oc->chosen) { struct mem_cgroup *memcg; memcg = mem_cgroup_from_task(oc->chosen); @@ -4042,6 +4039,13 @@ int sysctl_memcg_qos_handler(struct ctl_table *table, int write, return ret; } + +#else + +void memcg_print_bad_task(void *arg) +{ +} + #endif #ifdef CONFIG_NUMA diff --git a/mm/oom_kill.c b/mm/oom_kill.c index 0f77eb4c6644..03df1a9093b5 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -408,9 +408,10 @@ static void select_bad_process(struct oom_control *oc) { oc->chosen_points = LONG_MIN; - if (is_memcg_oom(oc)) - mem_cgroup_scan_tasks(oc->memcg, oom_evaluate_task, oc); - else { + if (is_memcg_oom(oc)) { + if (mem_cgroup_scan_tasks(oc->memcg, oom_evaluate_task, oc)) + memcg_print_bad_task(oc); + } else { struct task_struct *p; #ifdef CONFIG_MEMCG_QOS @@ -473,9 +474,10 @@ static void dump_tasks(struct oom_control *oc) pr_info("Tasks state (memory values in pages):\n"); pr_info("[ pid ] uid tgid total_vm rss pgtables_bytes swapents oom_score_adj name\n"); - if (is_memcg_oom(oc)) - mem_cgroup_scan_tasks(oc->memcg, dump_task, oc); - else { + if (is_memcg_oom(oc)) { + if (mem_cgroup_scan_tasks(oc->memcg, dump_task, oc)) + memcg_print_bad_task(oc); + } else { struct task_struct *p; rcu_read_lock(); -- 2.34.1

1 0

[PATCH openEuler-1.0-LTS] Bluetooth: btsdio: fix use after free bug in btsdio_remove due to race condition
by Yongqiang Liu 17 Apr '23

17 Apr '23

From: Zheng Wang <zyytlz.wz(a)163.com> mainline inclusion from mainline-v6.3-rc7 commit 73f7b171b7c09139eb3c6a5677c200dc1be5f318 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I6UW68 CVE: CVE-2023-1989 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… --------------------------- In btsdio_probe, the data->work is bound with btsdio_work. It will be started in btsdio_send_frame. If the btsdio_remove runs with a unfinished work, there may be a race condition that hdev is freed but used in btsdio_work. Fix it by canceling the work before do cleanup in btsdio_remove. Signed-off-by: Zheng Wang <zyytlz.wz(a)163.com> Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz(a)intel.com> Signed-off-by: Liu Jian <liujian56(a)huawei.com> Reviewed-by: Yue Haibing <yuehaibing(a)huawei.com> Reviewed-by: Wang Weiyang <wangweiyang2(a)huawei.com> Signed-off-by: Yongqiang Liu <liuyongqiang13(a)huawei.com> --- drivers/bluetooth/btsdio.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/bluetooth/btsdio.c b/drivers/bluetooth/btsdio.c index 20142bc77554..1325b1df4a8e 100644 --- a/drivers/bluetooth/btsdio.c +++ b/drivers/bluetooth/btsdio.c @@ -356,6 +356,7 @@ static void btsdio_remove(struct sdio_func *func) if (!data) return; + cancel_work_sync(&data->work); hdev = data->hdev; sdio_set_drvdata(func, NULL); -- 2.25.1

1 0

[PATCH openEuler-1.0-LTS] Bluetooth: btsdio: fix use after free bug in btsdio_remove due to race condition
by Yongqiang Liu 17 Apr '23

17 Apr '23

From: Zheng Wang <zyytlz.wz(a)163.com> mainline inclusion from mainline-v6.3-rc7 commit 73f7b171b7c09139eb3c6a5677c200dc1be5f318 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I6UW68 CVE: CVE-2023-1989 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… --------------------------- In btsdio_probe, the data->work is bound with btsdio_work. It will be started in btsdio_send_frame. If the btsdio_remove runs with a unfinished work, there may be a race condition that hdev is freed but used in btsdio_work. Fix it by canceling the work before do cleanup in btsdio_remove. Signed-off-by: Zheng Wang <zyytlz.wz(a)163.com> Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz(a)intel.com> Signed-off-by: Liu Jian <liujian56(a)huawei.com> Reviewed-by: Yue Haibing <yuehaibing(a)huawei.com> Reviewed-by: Wang Weiyang <wangweiyang2(a)huawei.com> Signed-off-by: Yongqiang Liu <liuyongqiang13(a)huawei.com> --- drivers/bluetooth/btsdio.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/bluetooth/btsdio.c b/drivers/bluetooth/btsdio.c index 20142bc77554..1325b1df4a8e 100644 --- a/drivers/bluetooth/btsdio.c +++ b/drivers/bluetooth/btsdio.c @@ -356,6 +356,7 @@ static void btsdio_remove(struct sdio_func *func) if (!data) return; + cancel_work_sync(&data->work); hdev = data->hdev; sdio_set_drvdata(func, NULL); -- 2.25.1

1 0

[PATCH rdma-core v3 0/2] Add support for SVE Direct WQE
by Chengchang Tang 17 Apr '23

17 Apr '23

From: Juan Zhou <zhoujuan51(a)h-partners.com> Yixing Liu (2): Update kernel headers libhns: Add support for SVE Direct WQE CMakeLists.txt | 1 + buildlib/RDMA_EnableCStd.cmake | 17 +++++++++++++++++ kernel-headers/rdma/hns-abi.h | 1 + providers/hns/CMakeLists.txt | 5 +++++ providers/hns/hns_roce_u_hw_v2.c | 21 ++++++++++++++++++++- 5 files changed, 44 insertions(+), 1 deletion(-) -- 2.30.0

1 0

[PATCH v4] eulerfs: fix wrong dereferencing in eufs_lookup
by Kang Chen 17 Apr '23

17 Apr '23

uniontech inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I6TN56 CVE: NA -------------------------------- smatch report: fs/eulerfs/namei.c:118 eufs_lookup() error: 'inode' dereferencing possible ERR_PTR() fix it by using the ino above in eufs_err. Signed-off-by: Kang Chen <void0red(a)hust.edu.cn> --- I think we need use IS_ERR to handle all errors, the err can't pass to BUG_ON line later. v4 -> v3: fix some bugs and return EIO/ENOMEM anyway. v3 -> v2: use IS_ERR to handle all kind err v2 -> v1: use correct string format fs/eulerfs/namei.c | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/fs/eulerfs/namei.c b/fs/eulerfs/namei.c index e4c6c36575f2..7064de644b34 100644 --- a/fs/eulerfs/namei.c +++ b/fs/eulerfs/namei.c @@ -114,9 +114,11 @@ static struct dentry *eufs_lookup(struct inode *dir, struct dentry *dentry, goto not_found; inode = eufs_iget(dir->i_sb, s2p(dir->i_sb, de->inode)); - if (inode == ERR_PTR(-ESTALE)) { - eufs_err(dir->i_sb, "deleted inode referenced: 0x%lx", - inode->i_ino); + if (IS_ERR(inode)) { + eufs_err(dir->i_sb, "eufs_iget failed ino 0x%llx err %d\n", + le64_to_cpu(de->inode), PTR_ERR(inode)); + if (inode == ERR_PTR(-ENOMEM)) + return ERR_PTR(-ENOMEM); return ERR_PTR(-EIO); } not_found: -- 2.34.1

3 2

[PATCH] mm: move memcg_print_bad_task out of mem_cgroup_scan_tasks to avoid wrong type cast
by Kang Chen 16 Apr '23

16 Apr '23

hulk inclusion category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I6NYW4 CVE: NA -------------------------------- raw call flow: oom_kill_process -> mem_cgroup_scan_tasks(.., .., message) -> memcg_print_bad_task(message, ..) message is "const char*" type, and incorrectly cast to "oom_control*" type in memcg_print_bad_task. Fix it by moving memcg_print_bad_task out of mem_cgroup_scan_tasks and call it in select_bad_process and dump_tasks. Signed-off-by: Kang Chen <void0red(a)hust.edu.cn> --- mm/memcontrol.c | 3 --- mm/oom_kill.c | 24 ++++++++++++++++++------ 2 files changed, 18 insertions(+), 9 deletions(-) diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 635cb8b65b86..8e0d5d484153 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -1214,9 +1214,6 @@ int mem_cgroup_scan_tasks(struct mem_cgroup *memcg, break; } } -#ifdef CONFIG_MEMCG_QOS - memcg_print_bad_task(arg, ret); -#endif return ret; } diff --git a/mm/oom_kill.c b/mm/oom_kill.c index 0f77eb4c6644..1e3ba16dd748 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -406,11 +406,17 @@ static int oom_evaluate_task(struct task_struct *task, void *arg) */ static void select_bad_process(struct oom_control *oc) { + int ret; oc->chosen_points = LONG_MIN; - if (is_memcg_oom(oc)) - mem_cgroup_scan_tasks(oc->memcg, oom_evaluate_task, oc); - else { + if (is_memcg_oom(oc)) { + ret = mem_cgroup_scan_tasks(oc->memcg, oom_evaluate_task, oc); + +#ifdef CONFIG_MEMCG_QOS + memcg_print_bad_task(oc, ret); +#endif + + } else { struct task_struct *p; #ifdef CONFIG_MEMCG_QOS @@ -470,12 +476,18 @@ static int dump_task(struct task_struct *p, void *arg) */ static void dump_tasks(struct oom_control *oc) { + int ret; pr_info("Tasks state (memory values in pages):\n"); pr_info("[ pid ] uid tgid total_vm rss pgtables_bytes swapents oom_score_adj name\n"); - if (is_memcg_oom(oc)) - mem_cgroup_scan_tasks(oc->memcg, dump_task, oc); - else { + if (is_memcg_oom(oc)) { + ret = mem_cgroup_scan_tasks(oc->memcg, dump_task, oc); + +#ifdef CONFIG_MEMCG_QOS + memcg_print_bad_task(oc, ret); +#endif + + } else { struct task_struct *p; rcu_read_lock(); -- 2.34.1

1 0

[PATCH OLK-5.10 0/8] SAS-related bugfix
by Yihang Li 14 Apr '23

14 Apr '23

From: xiabing <xiabing12(a)h-partners.com> *** BLURB HERE *** Jie Zhan (3): scsi: libsas: Add smp_ata_check_ready_type() scsi: hisi_sas: Fix SATA devices missing issue during I_T nexus reset scsi: libsas: Do not export sas_ata_wait_after_reset() Martin K. Petersen (1): scsi: sd: Reorganize DIF/DIX code to avoid calling revalidate twice Xingui Yang (1): scsi: sd: Update DIX config every time sd_revalidate_disk() is called Yihang Li (3): scsi: hisi_sas: Set a port invalid only if there are no devices attached when refreshing port id scsi: hisi_sas: Exit suspending state when usage count is greater than 0 scsi: hisi_sas: Ensure all enabled PHYs up during controller reset drivers/scsi/hisi_sas/hisi_sas_main.c | 42 ++++++++++++--- drivers/scsi/hisi_sas/hisi_sas_v3_hw.c | 73 ++++++++++++++++++++------ drivers/scsi/libsas/sas_ata.c | 28 +++++++++- drivers/scsi/libsas/sas_expander.c | 4 +- drivers/scsi/libsas/sas_internal.h | 2 + drivers/scsi/sd.c | 59 +++++++++++---------- drivers/scsi/sd_dif.c | 12 ++--- include/scsi/sas_ata.h | 7 ++- 8 files changed, 161 insertions(+), 66 deletions(-) -- 2.30.0

1 8

快看，内核&编译器领域 SIG组来啦！诚邀您参加 openEuler Developer Day 2023
by openEuler 14 Apr '23

14 Apr '23

1 0

[PATCH openEuler-22.03-LTS-SP1 0/5] Backport 5.10.150 LTS
by Jialin Zhang 13 Apr '23

13 Apr '23

Backport 5.10.151 LTS patches from upstream. Makefile | 3 +++ scripts/link-vmlinux.sh | 2 +- scripts/pahole-flags.sh | 21 +++++++++++++++++++++ 3 files changed, 25 insertions(+), 1 deletion(-) create mode 100755 scripts/pahole-flags.sh -- 2.25.1

1 5

[PATCH openEuler-22.03-LTS-SP1 v2 000/370] Backport 5.10.150 LTS
by Jialin Zhang 13 Apr '23

13 Apr '23

1 370

[OLK-5.10 0/2]
by zhoujiadong 13 Apr '23

13 Apr '23

*** BLURB HERE *** zhoujiadong (2): net/hinic3: Huawei Interface Card driver first commit net/hinic3: Huawei Interface Card hw driver first commit drivers/net/ethernet/huawei/Kconfig | 1 + drivers/net/ethernet/huawei/Makefile | 1 + drivers/net/ethernet/huawei/hinic3/Kconfig | 15 + drivers/net/ethernet/huawei/hinic3/Makefile | 45 + .../ethernet/huawei/hinic3/cfg_mgt_comm_pub.h | 212 ++ .../ethernet/huawei/hinic3/comm_cmdq_intf.h | 235 ++ .../net/ethernet/huawei/hinic3/comm_defs.h | 102 + .../ethernet/huawei/hinic3/comm_msg_intf.h | 663 +++++ .../ethernet/huawei/hinic3/hinic3_comm_cmd.h | 181 ++ .../ethernet/huawei/hinic3/hinic3_common.h | 125 + .../net/ethernet/huawei/hinic3/hinic3_crm.h | 1166 +++++++++ .../net/ethernet/huawei/hinic3/hinic3_dbg.c | 983 ++++++++ .../net/ethernet/huawei/hinic3/hinic3_dcb.c | 405 +++ .../net/ethernet/huawei/hinic3/hinic3_dcb.h | 78 + .../ethernet/huawei/hinic3/hinic3_ethtool.c | 1331 ++++++++++ .../huawei/hinic3/hinic3_ethtool_stats.c | 1233 ++++++++++ .../ethernet/huawei/hinic3/hinic3_filter.c | 483 ++++ .../net/ethernet/huawei/hinic3/hinic3_hw.h | 832 +++++++ .../net/ethernet/huawei/hinic3/hinic3_irq.c | 189 ++ .../net/ethernet/huawei/hinic3/hinic3_lld.h | 205 ++ .../ethernet/huawei/hinic3/hinic3_mag_cfg.c | 953 ++++++++ .../net/ethernet/huawei/hinic3/hinic3_main.c | 1125 +++++++++ .../huawei/hinic3/hinic3_mgmt_interface.h | 1245 ++++++++++ .../net/ethernet/huawei/hinic3/hinic3_mt.h | 665 +++++ .../huawei/hinic3/hinic3_netdev_ops.c | 1975 +++++++++++++++ .../net/ethernet/huawei/hinic3/hinic3_nic.h | 183 ++ .../ethernet/huawei/hinic3/hinic3_nic_cfg.c | 1608 ++++++++++++ .../ethernet/huawei/hinic3/hinic3_nic_cfg.h | 621 +++++ .../huawei/hinic3/hinic3_nic_cfg_vf.c | 638 +++++ .../ethernet/huawei/hinic3/hinic3_nic_cmd.h | 162 ++ .../ethernet/huawei/hinic3/hinic3_nic_dbg.c | 146 ++ .../ethernet/huawei/hinic3/hinic3_nic_dbg.h | 21 + .../ethernet/huawei/hinic3/hinic3_nic_dev.h | 387 +++ .../ethernet/huawei/hinic3/hinic3_nic_event.c | 580 +++++ .../ethernet/huawei/hinic3/hinic3_nic_io.c | 1122 +++++++++ .../ethernet/huawei/hinic3/hinic3_nic_io.h | 326 +++ .../ethernet/huawei/hinic3/hinic3_nic_prof.c | 47 + .../ethernet/huawei/hinic3/hinic3_nic_prof.h | 60 + .../ethernet/huawei/hinic3/hinic3_nic_qp.h | 385 +++ .../ethernet/huawei/hinic3/hinic3_ntuple.c | 907 +++++++ .../ethernet/huawei/hinic3/hinic3_prepare.sh | 262 ++ .../ethernet/huawei/hinic3/hinic3_profile.h | 147 ++ .../net/ethernet/huawei/hinic3/hinic3_rss.c | 978 ++++++++ .../net/ethernet/huawei/hinic3/hinic3_rss.h | 100 + .../ethernet/huawei/hinic3/hinic3_rss_cfg.c | 384 +++ .../net/ethernet/huawei/hinic3/hinic3_rx.c | 1344 ++++++++++ .../net/ethernet/huawei/hinic3/hinic3_rx.h | 155 ++ .../ethernet/huawei/hinic3/hinic3_srv_nic.h | 213 ++ .../net/ethernet/huawei/hinic3/hinic3_tx.c | 1016 ++++++++ .../net/ethernet/huawei/hinic3/hinic3_tx.h | 159 ++ .../net/ethernet/huawei/hinic3/hinic3_wq.h | 134 + .../huawei/hinic3/hw/hinic3_api_cmd.c | 1211 +++++++++ .../huawei/hinic3/hw/hinic3_api_cmd.h | 286 +++ .../ethernet/huawei/hinic3/hw/hinic3_cmdq.c | 1543 ++++++++++++ .../ethernet/huawei/hinic3/hw/hinic3_cmdq.h | 204 ++ .../ethernet/huawei/hinic3/hw/hinic3_common.c | 93 + .../ethernet/huawei/hinic3/hw/hinic3_csr.h | 187 ++ .../huawei/hinic3/hw/hinic3_dev_mgmt.c | 803 ++++++ .../huawei/hinic3/hw/hinic3_dev_mgmt.h | 105 + .../huawei/hinic3/hw/hinic3_devlink.c | 431 ++++ .../huawei/hinic3/hw/hinic3_devlink.h | 149 ++ .../ethernet/huawei/hinic3/hw/hinic3_eqs.c | 1385 +++++++++++ .../ethernet/huawei/hinic3/hw/hinic3_eqs.h | 165 ++ .../ethernet/huawei/hinic3/hw/hinic3_hw_api.c | 453 ++++ .../ethernet/huawei/hinic3/hw/hinic3_hw_api.h | 141 ++ .../ethernet/huawei/hinic3/hw/hinic3_hw_cfg.c | 1480 +++++++++++ .../ethernet/huawei/hinic3/hw/hinic3_hw_cfg.h | 332 +++ .../huawei/hinic3/hw/hinic3_hw_comm.c | 1540 ++++++++++++ .../huawei/hinic3/hw/hinic3_hw_comm.h | 51 + .../ethernet/huawei/hinic3/hw/hinic3_hw_mt.c | 599 +++++ .../ethernet/huawei/hinic3/hw/hinic3_hw_mt.h | 49 + .../ethernet/huawei/hinic3/hw/hinic3_hwdev.c | 2141 ++++++++++++++++ .../ethernet/huawei/hinic3/hw/hinic3_hwdev.h | 175 ++ .../ethernet/huawei/hinic3/hw/hinic3_hwif.c | 994 ++++++++ .../ethernet/huawei/hinic3/hw/hinic3_hwif.h | 113 + .../ethernet/huawei/hinic3/hw/hinic3_lld.c | 1413 +++++++++++ .../ethernet/huawei/hinic3/hw/hinic3_mbox.c | 1842 ++++++++++++++ .../ethernet/huawei/hinic3/hw/hinic3_mbox.h | 267 ++ .../ethernet/huawei/hinic3/hw/hinic3_mgmt.c | 1515 ++++++++++++ .../ethernet/huawei/hinic3/hw/hinic3_mgmt.h | 179 ++ .../huawei/hinic3/hw/hinic3_nictool.c | 974 ++++++++ .../huawei/hinic3/hw/hinic3_nictool.h | 35 + .../huawei/hinic3/hw/hinic3_pci_id_tbl.h | 15 + .../huawei/hinic3/hw/hinic3_prof_adap.c | 44 + .../huawei/hinic3/hw/hinic3_prof_adap.h | 111 + .../ethernet/huawei/hinic3/hw/hinic3_sm_lt.h | 160 ++ .../ethernet/huawei/hinic3/hw/hinic3_sml_lt.c | 160 ++ .../ethernet/huawei/hinic3/hw/hinic3_sriov.c | 267 ++ .../ethernet/huawei/hinic3/hw/hinic3_sriov.h | 35 + .../net/ethernet/huawei/hinic3/hw/hinic3_wq.c | 159 ++ .../huawei/hinic3/hw/ossl_knl_linux.c | 533 ++++ drivers/net/ethernet/huawei/hinic3/mag_cmd.h | 879 +++++++ .../ethernet/huawei/hinic3/mgmt_msg_base.h | 27 + .../net/ethernet/huawei/hinic3/nic_cfg_comm.h | 66 + drivers/net/ethernet/huawei/hinic3/ossl_knl.h | 38 + .../ethernet/huawei/hinic3/ossl_knl_linux.h | 2178 +++++++++++++++++ 96 files changed, 52060 insertions(+) create mode 100644 drivers/net/ethernet/huawei/hinic3/Kconfig create mode 100644 drivers/net/ethernet/huawei/hinic3/Makefile create mode 100644 drivers/net/ethernet/huawei/hinic3/cfg_mgt_comm_pub.h create mode 100644 drivers/net/ethernet/huawei/hinic3/comm_cmdq_intf.h create mode 100644 drivers/net/ethernet/huawei/hinic3/comm_defs.h create mode 100644 drivers/net/ethernet/huawei/hinic3/comm_msg_intf.h create mode 100644 drivers/net/ethernet/huawei/hinic3/hinic3_comm_cmd.h create mode 100644 drivers/net/ethernet/huawei/hinic3/hinic3_common.h create mode 100644 drivers/net/ethernet/huawei/hinic3/hinic3_crm.h create mode 100644 drivers/net/ethernet/huawei/hinic3/hinic3_dbg.c create mode 100644 drivers/net/ethernet/huawei/hinic3/hinic3_dcb.c create mode 100644 drivers/net/ethernet/huawei/hinic3/hinic3_dcb.h create mode 100644 drivers/net/ethernet/huawei/hinic3/hinic3_ethtool.c create mode 100644 drivers/net/ethernet/huawei/hinic3/hinic3_ethtool_stats.c create mode 100644 drivers/net/ethernet/huawei/hinic3/hinic3_filter.c create mode 100644 drivers/net/ethernet/huawei/hinic3/hinic3_hw.h create mode 100644 drivers/net/ethernet/huawei/hinic3/hinic3_irq.c create mode 100644 drivers/net/ethernet/huawei/hinic3/hinic3_lld.h create mode 100644 drivers/net/ethernet/huawei/hinic3/hinic3_mag_cfg.c create mode 100644 drivers/net/ethernet/huawei/hinic3/hinic3_main.c create mode 100644 drivers/net/ethernet/huawei/hinic3/hinic3_mgmt_interface.h create mode 100644 drivers/net/ethernet/huawei/hinic3/hinic3_mt.h create mode 100644 drivers/net/ethernet/huawei/hinic3/hinic3_netdev_ops.c create mode 100644 drivers/net/ethernet/huawei/hinic3/hinic3_nic.h create mode 100644 drivers/net/ethernet/huawei/hinic3/hinic3_nic_cfg.c create mode 100644 drivers/net/ethernet/huawei/hinic3/hinic3_nic_cfg.h create mode 100644 drivers/net/ethernet/huawei/hinic3/hinic3_nic_cfg_vf.c create mode 100644 drivers/net/ethernet/huawei/hinic3/hinic3_nic_cmd.h create mode 100644 drivers/net/ethernet/huawei/hinic3/hinic3_nic_dbg.c create mode 100644 drivers/net/ethernet/huawei/hinic3/hinic3_nic_dbg.h create mode 100644 drivers/net/ethernet/huawei/hinic3/hinic3_nic_dev.h create mode 100644 drivers/net/ethernet/huawei/hinic3/hinic3_nic_event.c create mode 100644 drivers/net/ethernet/huawei/hinic3/hinic3_nic_io.c create mode 100644 drivers/net/ethernet/huawei/hinic3/hinic3_nic_io.h create mode 100644 drivers/net/ethernet/huawei/hinic3/hinic3_nic_prof.c create mode 100644 drivers/net/ethernet/huawei/hinic3/hinic3_nic_prof.h create mode 100644 drivers/net/ethernet/huawei/hinic3/hinic3_nic_qp.h create mode 100644 drivers/net/ethernet/huawei/hinic3/hinic3_ntuple.c create mode 100644 drivers/net/ethernet/huawei/hinic3/hinic3_prepare.sh create mode 100644 drivers/net/ethernet/huawei/hinic3/hinic3_profile.h create mode 100644 drivers/net/ethernet/huawei/hinic3/hinic3_rss.c create mode 100644 drivers/net/ethernet/huawei/hinic3/hinic3_rss.h create mode 100644 drivers/net/ethernet/huawei/hinic3/hinic3_rss_cfg.c create mode 100644 drivers/net/ethernet/huawei/hinic3/hinic3_rx.c create mode 100644 drivers/net/ethernet/huawei/hinic3/hinic3_rx.h create mode 100644 drivers/net/ethernet/huawei/hinic3/hinic3_srv_nic.h create mode 100644 drivers/net/ethernet/huawei/hinic3/hinic3_tx.c create mode 100644 drivers/net/ethernet/huawei/hinic3/hinic3_tx.h create mode 100644 drivers/net/ethernet/huawei/hinic3/hinic3_wq.h create mode 100644 drivers/net/ethernet/huawei/hinic3/hw/hinic3_api_cmd.c create mode 100644 drivers/net/ethernet/huawei/hinic3/hw/hinic3_api_cmd.h create mode 100644 drivers/net/ethernet/huawei/hinic3/hw/hinic3_cmdq.c create mode 100644 drivers/net/ethernet/huawei/hinic3/hw/hinic3_cmdq.h create mode 100644 drivers/net/ethernet/huawei/hinic3/hw/hinic3_common.c create mode 100644 drivers/net/ethernet/huawei/hinic3/hw/hinic3_csr.h create mode 100644 drivers/net/ethernet/huawei/hinic3/hw/hinic3_dev_mgmt.c create mode 100644 drivers/net/ethernet/huawei/hinic3/hw/hinic3_dev_mgmt.h create mode 100644 drivers/net/ethernet/huawei/hinic3/hw/hinic3_devlink.c create mode 100644 drivers/net/ethernet/huawei/hinic3/hw/hinic3_devlink.h create mode 100644 drivers/net/ethernet/huawei/hinic3/hw/hinic3_eqs.c create mode 100644 drivers/net/ethernet/huawei/hinic3/hw/hinic3_eqs.h create mode 100644 drivers/net/ethernet/huawei/hinic3/hw/hinic3_hw_api.c create mode 100644 drivers/net/ethernet/huawei/hinic3/hw/hinic3_hw_api.h create mode 100644 drivers/net/ethernet/huawei/hinic3/hw/hinic3_hw_cfg.c create mode 100644 drivers/net/ethernet/huawei/hinic3/hw/hinic3_hw_cfg.h create mode 100644 drivers/net/ethernet/huawei/hinic3/hw/hinic3_hw_comm.c create mode 100644 drivers/net/ethernet/huawei/hinic3/hw/hinic3_hw_comm.h create mode 100644 drivers/net/ethernet/huawei/hinic3/hw/hinic3_hw_mt.c create mode 100644 drivers/net/ethernet/huawei/hinic3/hw/hinic3_hw_mt.h create mode 100644 drivers/net/ethernet/huawei/hinic3/hw/hinic3_hwdev.c create mode 100644 drivers/net/ethernet/huawei/hinic3/hw/hinic3_hwdev.h create mode 100644 drivers/net/ethernet/huawei/hinic3/hw/hinic3_hwif.c create mode 100644 drivers/net/ethernet/huawei/hinic3/hw/hinic3_hwif.h create mode 100644 drivers/net/ethernet/huawei/hinic3/hw/hinic3_lld.c create mode 100644 drivers/net/ethernet/huawei/hinic3/hw/hinic3_mbox.c create mode 100644 drivers/net/ethernet/huawei/hinic3/hw/hinic3_mbox.h create mode 100644 drivers/net/ethernet/huawei/hinic3/hw/hinic3_mgmt.c create mode 100644 drivers/net/ethernet/huawei/hinic3/hw/hinic3_mgmt.h create mode 100644 drivers/net/ethernet/huawei/hinic3/hw/hinic3_nictool.c create mode 100644 drivers/net/ethernet/huawei/hinic3/hw/hinic3_nictool.h create mode 100644 drivers/net/ethernet/huawei/hinic3/hw/hinic3_pci_id_tbl.h create mode 100644 drivers/net/ethernet/huawei/hinic3/hw/hinic3_prof_adap.c create mode 100644 drivers/net/ethernet/huawei/hinic3/hw/hinic3_prof_adap.h create mode 100644 drivers/net/ethernet/huawei/hinic3/hw/hinic3_sm_lt.h create mode 100644 drivers/net/ethernet/huawei/hinic3/hw/hinic3_sml_lt.c create mode 100644 drivers/net/ethernet/huawei/hinic3/hw/hinic3_sriov.c create mode 100644 drivers/net/ethernet/huawei/hinic3/hw/hinic3_sriov.h create mode 100644 drivers/net/ethernet/huawei/hinic3/hw/hinic3_wq.c create mode 100644 drivers/net/ethernet/huawei/hinic3/hw/ossl_knl_linux.c create mode 100644 drivers/net/ethernet/huawei/hinic3/mag_cmd.h create mode 100644 drivers/net/ethernet/huawei/hinic3/mgmt_msg_base.h create mode 100644 drivers/net/ethernet/huawei/hinic3/nic_cfg_comm.h create mode 100644 drivers/net/ethernet/huawei/hinic3/ossl_knl.h create mode 100644 drivers/net/ethernet/huawei/hinic3/ossl_knl_linux.h -- 2.24.0

1 2

[PATCH openEuler-22.03-LTS-SP1 000/371] Backport 5.10.150 LTS
by Jialin Zhang 13 Apr '23

13 Apr '23

Backport 5.10.150 LTS patches from upstream. Conflicts: Already merged(18): f039b43cbaea inet: fully convert sk->sk_rx_dst to RCU rules 45c33966759e mm: hugetlb: fix UAF in hugetlb_handle_userfault 67cbc8865a66 io_uring: correct pinned_vm accounting 904f881b5736 arm64: topology: fix possible overflow in amu_fie_setup() dbcca76435a6 HID: roccat: Fix use-after-free in roccat_read() 484400d433ca r8152: Rate limit overflow messages d88b88514ef2 crypto: hisilicon/zip - fix mismatch in get/set sgl_sge_nr 657de36c72f5 arm64: ftrace: fix module PLTs with mcount 29f50bcf0f8b net: mvpp2: fix mvpp2 debugfs leak 6cc0e2afc6a1 bnx2x: fix potential memory leak in bnx2x_tpa_stop() 2a1d03632085 mISDN: fix use-after-free bugs in l1oip timer handlers 0cf6c09dafee ring-buffer: Fix race between reset page and reading page fbb0e601bd51 ext4: ext4_read_bh_lock() should submit IO if the buffer isn't uptodate 483831ad0440 ext4: fix check for block being out of directory size f34ab9516276 ext4: fix null-ptr-deref in ext4_write_info e50472949604 fbdev: smscufx: Fix use-after-free in ufx_ops_open() 7d551b7d6114 block: fix inflight statistics of part0 6b7ae4a904a4 quota: Check next/prev free block number after reading from quota file Context conflict(1): c13d0d2f5a48 usb: host: xhci-plat: suspend and resume clocks Total patches: 389 - 18 = 371 Adrian Hunter (1): perf intel-pt: Fix segfault in intel_pt_print_info() with uClibc Adrián Larumbe (1): drm/meson: explicitly remove aggregate driver at module unload time Albert Briscoe (1): usb: gadget: function: fix dangling pnp_string in f_printer.c Alex Deucher (1): Revert "drm/amdgpu: make sure to init common IP before gmc" Alexander Aring (4): fs: dlm: fix race between test_bit() and queue_work() fs: dlm: handle -EBUSY first in lock arg validation net: ieee802154: return -EINVAL for unknown addr type Revert "net/ieee802154: reject zero-sized raw_sendmsg()" Alexander Coffin (1): wifi: brcmfmac: fix use-after-free bug in brcmf_netdev_start_xmit() Alexander Stein (6): ARM: dts: imx6q: add missing properties for sram ARM: dts: imx6dl: add missing properties for sram ARM: dts: imx6qp: add missing properties for sram ARM: dts: imx6sl: add missing properties for sram ARM: dts: imx6sll: add missing properties for sram ARM: dts: imx6sx: add missing properties for sram Alvin Šipraga (1): drm: bridge: adv7511: fix CEC power down control register offset Andreas Pape (1): ALSA: dmaengine: increment buffer pointer atomically Andrew Bresticker (2): riscv: Allow PROT_WRITE-only mmap() riscv: Make VM_WRITE imply VM_READ Andrew Perepechko (1): jbd2: wake up journal waiters in FIFO order, not LIFO Andri Yngvason (1): HID: multitouch: Add memory barriers Anna Schumaker (1): NFSD: Return nfserr_serverfault if splice_ok but buf->pages have data Anssi Hannula (4): can: kvaser_usb: Fix use of uninitialized completion can: kvaser_usb_leaf: Fix overread with an invalid command can: kvaser_usb_leaf: Fix TX queue out of sync after restart can: kvaser_usb_leaf: Fix CAN state after restart Ard Biesheuvel (1): efi: libstub: drop pointless get_memory_map() call Aric Cyr (1): drm/amd/display: Remove interface for periodic interrupt 1 Arnd Bergmann (1): Bluetooth: btusb: fix excessive stack usage Arvid Norlander (1): ACPI: video: Add Toshiba Satellite/Portege Z830 quirk Asmaa Mnebhi (1): i2c: mlxbf: support lock mechanism Bernard Metzler (1): RDMA/siw: Always consume all skbuf data in sk_data_ready() upcall. Bitterblue Smith (4): wifi: rtl8xxxu: Fix skb misuse in TX queue selection wifi: rtl8xxxu: gen2: Fix mistake in path B IQ calibration wifi: rtl8xxxu: Remove copy-paste leftover in gen2_update_rate_mask wifi: rtl8xxxu: Fix AIFS written to REG_EDCA_*_PARAM Callum Osmotherly (1): ALSA: hda/realtek: remove ALC289_FIXUP_DUAL_SPK for Dell 5530 Carlos Llamas (1): mm/mmap: undo ->mmap() when arch_validate_flags() fails Chao Qin (1): powercap: intel_rapl: fix UBSAN shift-out-of-bounds issue Chao Yu (5): f2fs: fix to do sanity check on destination blkaddr during recovery f2fs: fix to do sanity check on summary info f2fs: fix to avoid REQ_TIME and CP_TIME collision f2fs: fix to account FS_CP_DATA_IO correctly f2fs: fix wrong condition to trigger background checkpoint correctly Chen-Yu Tsai (2): drm/bridge: parade-ps8640: Fix regulator supply order clk: mediatek: mt8183: mfgcfg: Propagate rate changes to parent Christophe JAILLET (11): MIPS: SGI-IP27: Free some unused memory nfsd: Fix a memory leak in an error handling path spi: mt7621: Fix an error message in mt7621_spi_probe() mmc: au1xmmc: Fix an error handling path in au1xmmc_probe() ASoC: da7219: Fix an error handling path in da7219_register_dai_clks() mmc: wmt-sdmmc: Fix an error handling path in wmt_mci_probe() serial: 8250: Add an empty line and remove some useless {} mfd: intel_soc_pmic: Fix an error handling path in intel_soc_pmic_i2c_probe() mfd: fsl-imx25: Fix an error handling path in mx25_tsadc_setup_irq() mfd: lp8788: Fix an error handling path in lp8788_probe() mfd: lp8788: Fix an error handling path in lp8788_irq_init() and lp8788_irq_init() Chunfeng Yun (2): usb: common: add function to get interval expressed in us unit usb: common: move function's kerneldoc next to its definition Claudiu Beznea (4): iio: adc: at91-sama5d2_adc: fix AT91_SAMA5D2_MR_TRACKTIM_MAX iio: adc: at91-sama5d2_adc: check return status for pressure and touch iio: adc: at91-sama5d2_adc: lock around oversampling and sample freq iio: adc: at91-sama5d2_adc: disable/prepare buffer on suspend/resume Coly Li (1): bcache: fix set_at_max_writeback_rate() for multiple attached devices Dai Ngo (1): NFSD: fix use-after-free on source server when doing inter-server copy Daisuke Matsuda (1): IB: Set IOVA/LENGTH on IB_MR in core/uverbs layers Damian Muszynski (1): crypto: qat - fix DMA transfer direction Dan Carpenter (10): wifi: rtl8xxxu: tighten bounds checking in rtl8xxxu_read_efuse() drm/bridge: Avoid uninitialized variable warning platform/chrome: fix memory corruption in ioctl fpga: prevent integer overflow in dfl_feature_ioctl_set_irq() mtd: rawnand: meson: fix bit map use in meson_nfc_ecc_correct() drivers: serial: jsm: fix some leaks in probe mfd: fsl-imx25: Fix check for platform_get_irq() errors iommu/omap: Fix buffer overflow in debugfs crypto: marvell/octeontx - prevent integer overflows crypto: cavium - prevent integer overflow loading firmware Daniel Golle (5): wifi: rt2x00: don't run Rt5592 IQ calibration on MT7620 wifi: rt2x00: set correct TX_SW_CFG1 MAC register for MT7620 wifi: rt2x00: set VGC gain for both chains of MT7620 wifi: rt2x00: set SoC wmac clock register wifi: rt2x00: correctly set BBP register 86 for MT7620 Dave Jiang (1): dmaengine: ioat: stop mod_timer from resurrecting deleted timer in __cleanup() David Collins (1): spmi: pmic-arb: correct duplicate APID to PPID mapping logic David Gow (1): drm/amd/display: fix overflow on MIN_I64 definition Dmitry Baryshkov (1): drm/msm/dpu: index dpu_kms->hw_vbif using vbif_idx Dmitry Osipenko (3): drm/virtio: Check whether transferred 2D BO is shmem media: cedrus: Set the platform driver data earlier soc/tegra: fuse: Drop Kconfig dependency on TEGRA20_APB_DMA Dmitry Torokhov (2): ARM: dts: exynos: correct s5k6a3 reset polarity on Midas family ARM: dts: exynos: fix polarity of VBUS GPIO of Origen Dongliang Mu (2): phy: qualcomm: call clk_disable_unprepare in the error handling usb: idmouse: fix an uninit-value in idmouse_open Duoming Zhou (1): scsi: libsas: Fix use-after-free bug in smp_execute_task_sg() Eddie James (2): iio: pressure: dps310: Refactor startup procedure iio: pressure: dps310: Reset chip after timeout Eric Dumazet (2): once: add DO_ONCE_SLOW() for sleepable contexts tcp: annotate data-race around tcp_md5sig_pool_populated Fangrui Song (1): riscv: Pass -mno-relax only on lld < 15.0.0 Filipe Manana (1): btrfs: fix race between quota enable and quota rescan ioctl Geert Uytterhoeven (1): ARM: Drop CMDLINE_* dependency on ATAGS Giovanni Cabiddu (1): crypto: qat - use pre-allocated buffers in datapath Greg Kroah-Hartman (2): staging: greybus: audio_helper: remove unused and wrong debugfs usage selinux: use "grep -E" instead of "egrep" Guilherme G. Piccoli (1): firmware: google: Test spinlock on panic path to avoid lockups Haibo Chen (1): ARM: dts: imx7d-sdb: config the max pressure for tsc2046 Hangyu Hua (1): misc: ocxl: fix possible refcount leak in afu_ioctl() Hans de Goede (3): platform/x86: msi-laptop: Fix old-ec check for backlight registering platform/x86: msi-laptop: Fix resource cleanup platform/x86: msi-laptop: Change DMI match / alias strings to fix module autoloading Hari Chandrakanthan (1): wifi: mac80211: allow bw change during channel switch in mesh Helge Deller (1): parisc: fbdev/stifb: Align graphics memory size to 4MB Huacai Chen (1): UM: cpuinfo: Fix a warning for CONFIG_CPUMASK_OFFSTACK Hui Tang (1): crypto: qat - fix use of 'dma_map_single' Ian Nam (1): clk: zynqmp: Fix stack-out-of-bounds in strncpy` Ian Rogers (1): selftests/xsk: Avoid use-after-free on ctx Ignat Korchagin (1): crypto: akcipher - default implementation for setting a private key Ilpo Järvinen (1): serial: 8250: Toggle IER bits on only after irq has been set up Jack Wang (2): HSI: omap_ssi_port: Fix dma_map_sg error check mailbox: bcm-ferxrm-mailbox: Fix error check for dma_map_sg Jaegeuk Kim (1): f2fs: increase the limit for reserve_root Jairaj Arava (1): ASoC: SOF: pci: Change DMI match info to support all Chrome platforms Jameson Thies (1): platform/chrome: cros_ec: Notify the PM of wake events during resume Jan Kara (1): ext4: avoid crash when inline data creation follows DIO write Janis Schoetterl-Glausch (1): kbuild: rpm-pkg: fix breakage when V=1 is used Javier Martinez Canillas (2): drm: Use size_t type for len variable in drm_copy_field() drm: Prevent drm_copy_field() to attempt copying a NULL pointer Jean-Francois Le Fillatre (1): usb: add quirks for Lenovo OneLink+ Dock Jerry Lee 李修賢 (1): ext4: continue to expand file system when the target size doesn't reach Jesus Fernandez Manzano (1): wifi: ath11k: fix number of VHT beamformee spatial streams Jianglei Nie (3): drm/nouveau: fix a use-after-free in nouveau_gem_prime_import_sg_table() drm/nouveau/nouveau_bo: fix potential memory leak in nouveau_bo_alloc() usb: host: xhci: Fix potential memory leak in xhci_alloc_stream_info() Jiasheng Jiang (3): ASoC: rsnd: Add check for rsnd_mod_power_on fsi: core: Check error number after calling ida_simple_get mfd: sm501: Add check for platform_driver_register() Jie Hai (3): dmaengine: hisilicon: Disable channels when unregister hisi_dma dmaengine: hisilicon: Fix CQ head update dmaengine: hisilicon: Add multi-thread support for a DMA channel Jim Cromie (4): dyndbg: fix static_branch manipulation dyndbg: fix module.dyndbg handling dyndbg: let query-modname override actual module name dyndbg: drop EXPORTed dynamic_debug_exec_queries Jinke Han (1): ext4: place buffer head allocation before handle start Joel Stanley (1): clk: ast2600: BCLK comes from EPLL Jonathan Cameron (1): iio: ABI: Fix wrong format of differential capacitance channel ABI. Junichi Uekawa (1): vhost/vsock: Use kvmalloc/kvfree for larger packets. Justin Chen (2): usb: host: xhci-plat: suspend and resume clocks usb: host: xhci-plat: suspend/resume clks for brcm Kees Cook (7): hardening: Clarify Kconfig text for auto-var-init hardening: Avoid harmless Clang option under CONFIG_INIT_STACK_ALL_ZERO hardening: Remove Clang's enable flag for -ftrivial-auto-var-init=zero sh: machvec: Use char[] for section boundaries x86/microcode/AMD: Track patch allocation size explicitly MIPS: BCM47XX: Cast memcmp() of function to (void *) x86/entry: Work around Clang __bdos() bug Keith Busch (1): nvme: copy firmware_rev on each init Khaled Almahallawy (1): drm/dp: Don't rewrite link config when setting phy test pattern Khalid Masum (1): xfrm: Update ipcomp_scratches with NULL when freed Koba Ko (1): crypto: ccp - Release dma channels before dmaengine unrgister Kohei Tarumizu (1): x86/resctrl: Fix to restore to original value when re-enabling hardware prefetch register Krzysztof Kozlowski (2): ASoC: wcd9335: fix order of Slimbus unprepare/disable ASoC: wcd934x: fix order of Slimbus unprepare/disable Kshitiz Varshney (1): hwrng: imx-rngc - Moving IRQ handler registering after imx_rngc_irq_mask_clear() Kuogee Hsieh (1): drm/msm/dp: correct 1.62G link rate at dp_catalog_ctrl_config_msa() Lalith Rajendran (1): ext4: make ext4_lazyinit_thread freezable Lam Thai (1): bpftool: Fix a wrong type cast in btf_dumper_int Lee Jones (1): bpf: Ensure correct locking around vulnerable function find_vpid() Letu Ren (1): scsi: 3w-9xxx: Avoid disabling device if failing to enable it Liang He (17): hwmon: (gsc-hwmon) Call of_node_get() before of_find_xxx API drm:pl111: Add of_node_put() when breaking out of for_each_available_child_of_node() drm/omap: dss: Fix refcount leak bugs ASoC: eureka-tlv320: Hold reference returned from of_find_xxx API memory: pl353-smc: Fix refcount leak bug in pl353_smc_probe() memory: of: Fix refcount leak bug in of_get_ddr_timings() memory: of: Fix refcount leak bug in of_lpddr3_get_ddr_timings() soc: qcom: smsm: Fix refcount leak bugs in qcom_smsm_probe() soc: qcom: smem_state: Add refcounting for the 'state->of_node' clk: meson: Hold reference returned by of_get_parent() clk: oxnas: Hold reference returned by of_get_parent() clk: qoriq: Hold reference returned by of_get_parent() clk: berlin: Add of_node_put() for of_get_parent() clk: sprd: Hold reference returned by of_get_parent() media: exynos4-is: fimc-is: Add of_node_put() when breaking out of loop powerpc/sysdev/fsl_msi: Add missing of_node_put() powerpc/pci_dn: Add missing of_node_put() Lin Yujun (1): MIPS: SGI-IP27: Fix platform-device leak in bridge_platform_create() Linus Walleij (1): regulator: qcom_rpm: Fix circular deferral regression Liu Jian (1): net: If sock is dead don't access sock's sk_wq in sk_stream_wait_memory Logan Gunthorpe (2): md/raid5: Ensure stripe_fill happens on non-read IO with journal md/raid5: Wait for MD_SB_CHANGE_PENDING in raid5d Lorenz Bauer (1): bpf: btf: fix truncated last_member_type_id in btf_struct_resolve Lucas Stach (1): drm: bridge: dw_hdmi: only trigger hotplug event on link change Luciano Leão (1): x86/cpu: Include the header of init_ia32_feat_ctl()'s prototype Luiz Augusto von Dentz (3): Bluetooth: hci_core: Fix not handling link timeouts propertly Bluetooth: hci_sysfs: Fix attempting to call device_add multiple times Bluetooth: L2CAP: Fix user-after-free Lukas Czerner (1): ext4: don't increase iversion counter for ea_inodes Luke D. Jones (2): ALSA: hda/realtek: Correct pin configs for ASUS G533Z ALSA: hda/realtek: Add quirk for ASUS GV601R laptop Lyude Paul (1): drm/nouveau/kms/nv140-: Disable interlacing Maciej W. Rozycki (2): RISC-V: Make port I/O string accessors actually work PCI: Sanitise firmware BAR assignments behind a PCI-PCI bridge Marek Behún (1): ARM: dts: turris-omnia: Fix mpp26 pin name and comment Marek Szyprowski (1): spi: Ensure that sg_table won't be used after being freed Mario Limonciello (2): thunderbolt: Explicitly enable lane adapter hotplug events at startup xhci: Don't show warning for reinit on known broken suspend Mark Brown (1): kselftest/arm64: Fix validatation termination record after EXTRA_CONTEXT Mark Chen (1): Bluetooth: btusb: Fine-tune mt7663 mechanism. Mark Zhang (1): RDMA/cm: Use SLID in the work completion as the DLID in responder side Martin Liska (1): gcov: support GCC 12.1 and newer compilers Martin Povišer (3): ASoC: tas2764: Allow mono streams ASoC: tas2764: Drop conflicting set_bias_level power setting ASoC: tas2764: Fix mute/unmute Masahiro Yamada (1): kbuild: remove the target in signal traps when interrupted Mateusz Kwiatkowski (1): drm/vc4: vec: Fix timings for VEC modes Maxime Ripard (2): drm/mipi-dsi: Detach devices when removing the host clk: bcm2835: Make peripheral PLLC critical Maya Matuszczyk (1): drm: panel-orientation-quirks: Add quirk for Anbernic Win600 Miaoqian Lin (6): clk: tegra: Fix refcount leak in tegra210_clock_init clk: tegra: Fix refcount leak in tegra114_clock_init clk: tegra20: Fix refcount leak in tegra20_clock_init HSI: omap_ssi: Fix refcount leak in ssi_probe media: xilinx: vipp: Fix refcount leak in xvip_graph_dma_init clk: ti: dra7-atl: Fix reference leak in of_dra7_atl_clk_probe Michael Hennerich (1): iio: dac: ad5593r: Fix i2c read protocol requirements Michael Walle (2): ARM: dts: kirkwood: lsxl: fix serial line ARM: dts: kirkwood: lsxl: remove first ethernet port Michal Hocko (1): rcu: Back off upon fill_page_cache_func() allocation failure Michal Luczaj (1): KVM: x86/emulator: Fix handing of POP SS to correctly set interruptibility Mike Christie (1): scsi: iscsi: iscsi_tcp: Fix null-ptr-deref while calling getpeername() Mike Pattrick (2): openvswitch: Fix double reporting of drops in dropwatch openvswitch: Fix overreporting of drops in dropwatch Nam Cao (2): staging: vt6655: fix some erroneous memory clean-up loops staging: vt6655: fix potential memory leak Nathan Chancellor (1): powerpc/math_emu/efp: Include module.h Neal Cardwell (1): tcp: fix tcp_cwnd_validate() to not forget is_cwnd_limited Neil Armstrong (1): spi: meson-spicc: do not rely on busy flag in pow2 clk ops Nicholas Piggin (1): powerpc/64s: Fix GENERIC_CPU build flags for PPC970 / G5 Niklas Cassel (4): ata: fix ata_id_sense_reporting_enabled() and ata_id_has_sense_reporting() ata: fix ata_id_has_devslp() ata: fix ata_id_has_ncq_autosense() ata: fix ata_id_has_dipm() Nuno Sá (2): iio: adc: ad7923: fix channel readings for some variants iio: inkern: only release the device node when done with it Ondrej Mosnacek (1): userfaultfd: open userfaultfds with O_RDONLY Pali Rohár (4): powerpc/boot: Explicitly disable usage of SPE instructions mtd: rawnand: fsl_elbc: Fix none ECC mode serial: 8250: Fix restoring termios speed after suspend powerpc: Fix SPE Power ISA properties for e500v1 platforms Patrick Rudolph (1): regulator: core: Prevent integer underflow Patryk Duda (1): platform/chrome: cros_ec_proto: Update version on GET_NEXT_EVENT failure Pavel Begunkov (1): io_uring/af_unix: defer registered files gc to io_uring release Peter Harliman Liem (1): crypto: inside-secure - Change swab to swab32 Phil Sutter (1): netfilter: nft_fib: Fix for rpath check with VRF devices Pierre-Louis Bossart (1): soundwire: intel: fix error handling on dai registration issues Qu Wenruo (1): btrfs: scrub: try to fix super block errors Quanyang Wang (1): clk: zynqmp: pll: rectify rate rounding in zynqmp_pll_round_rate Quentin Monnet (1): bpftool: Clear errno after libcap's checks Rafael J. Wysocki (1): thermal: intel_powerclamp: Use first online CPU as control_cpu Randy Dunlap (2): drm: fix drm_mipi_dbi build errors ia64: export memory_add_physaddr_to_nid to fix cxl build error Richard Acayan (1): mmc: sdhci-msm: add compatible string check for sdm670 Richard Fitzgerald (1): soundwire: cadence: Don't overwrite msg->buf during write commands Rik van Riel (1): livepatch: fix race between fork and KLP transition Rishabh Bhatnagar (1): nvme-pci: set min_align_mask before calculating max_hw_sectors Robert Marko (1): clk: qcom: apss-ipq6018: mark apcs_alias0_core_clk as critical Robin Guo (1): usb: musb: Fix musb_gadget.c rxstate overflow bug Robin Murphy (1): iommu/iova: Fix module config properly Ronnie Sahlberg (1): cifs: destage dirty pages before re-reading them for cache=none Rustam Subkhankulov (1): platform/chrome: fix double-free in chromeos_laptop_prepare() Sami Tolvanen (1): objtool: Preserve special st_shndx indexes in elf_update_symbol Saranya Gopal (1): ALSA: hda/realtek: Add Intel Reference SSID to support headset keys Saurabh Sengar (1): md: Replace snprintf with scnprintf Saurav Kashyap (1): scsi: qedf: Populate sysfs attributes for vport Sean Christopherson (2): KVM: nVMX: Unconditionally purge queued/injected events on nested "exit" KVM: VMX: Drop bits 31:16 when shoving exception error code into VMCS Sean Wang (1): Bluetooth: btusb: mediatek: fix WMT failure during runtime suspend Sebastian Krzyszkowiak (1): arm64: dts: imx8mq-librem5: Add bq25895 as max17055's power supply Serge Semin (5): clk: vc5: Fix 5P49V6901 outputs disabling when enabling FOD clk: baikal-t1: Fix invalid xGMAC PTP clock divider clk: baikal-t1: Add shared xGMAC ref/ptp clocks internal parent clk: baikal-t1: Add SATA internal ref clock buffer ata: libahci_platform: Sanity check the DT child nodes number Sherry Sun (1): tty: serial: fsl_lpuart: disable dma rx/tx use flags in lpuart_dma_shutdown Shigeru Yoshida (1): nbd: Fix hung when signal interrupts nbd_start_device_ioctl() Shuah Khan (2): Revert "drm/amdgpu: move nbio sdma_doorbell_range() into sdma code for vega" Revert "drm/amdgpu: use dirty framebuffer helper" Shuai Xue (1): ACPI: APEI: do not add task_work to kernel thread to avoid memory leak Shubhrajyoti Datta (1): tty: xilinx_uartps: Fix the ignore_status Simon Ser (1): drm/dp_mst: fix drm_dp_dpcd_read return value checks Srinivas Pandruvada (1): thermal: intel_powerclamp: Use get_cpu() instead of smp_processor_id() to avoid crash Stefan Berger (1): selftest: tpm2: Add Client.__del__() to close /dev/tpm* handle Stefan Wahren (1): clk: bcm2835: fix bcm2835_clock_rate_from_divisor declaration Steve French (1): smb3: must initialize two ACL struct fields to zero Steven Rostedt (Google) (4): ring-buffer: Allow splice to read previous partially read pages ring-buffer: Have the shortest_full queue be the shortest not longest ring-buffer: Check pending waiters when doing wake ups as well ring-buffer: Add ring_buffer_wake_waiters() Takashi Iwai (7): ALSA: oss: Fix potential deadlock at unregistration ALSA: rawmidi: Drop register_mutex in snd_rawmidi_free() ALSA: usb-audio: Fix potential memory leaks ALSA: usb-audio: Fix NULL dererence at error path drm/udl: Restore display mode on resume ALSA: hda: beep: Simplify keep-power-at-enable behavior ALSA: hda/hdmi: Don't skip notification handling during PM operation Tetsuo Handa (6): Bluetooth: hci_{ldisc,serdev}: check percpu_init_rwsem() failure net: rds: don't hold sock lock when cancelling work from rds_tcp_reset_callbacks() net/ieee802154: reject zero-sized raw_sendmsg() wifi: ath9k: avoid uninit memory read in ath9k_htc_rx_msg() Bluetooth: L2CAP: initialize delayed works at l2cap_chan_create() net/ieee802154: don't warn zero-sized raw_sendmsg() Thinh Nguyen (3): usb: ch9: Add USB 3.2 SSP attributes usb: common: Parse for USB SSP genXxY usb: common: debug: Check non-standard control requests Tudor Ambarus (1): mtd: rawnand: atmel: Unmap streaming DMA mappings Uwe Kleine-König (2): iio: ltc2497: Fix reading conversion results leds: lm3601x: Don't use mutex after it was destroyed Varun Prakash (1): nvmet-tcp: add bounds check on Transfer Tag Ville Syrjälä (2): drm/i915: Fix watermark calculations for gen12+ RC CCS modifier drm/i915: Fix watermark calculations for gen12+ MC CCS modifier Vincent Knecht (1): thermal/drivers/qcom/tsens-v0_1: Fix MSM8939 fourth sensor hw_id Vincent Whitchurch (1): spi: s3c64xx: Fix large transfers with DMA Vitaly Kuznetsov (1): x86/hyperv: Fix 'struct hv_enlightened_vmcs' definition Vivek Kasireddy (1): udmabuf: Set ubuf->sg = NULL if the creation of sg table fails Waiman Long (2): tracing: Disable interrupt or preemption before acquiring arch_spinlock_t cgroup/cpuset: Enable update_tasks_cpumask() on top_cpuset Wang Kefeng (2): ARM: 9244/1: dump: Fix wrong pg_level in walk_pmd() ARM: 9247/1: mm: set readonly for MT_MEMORY_RO with ARM_LPAE Wei Yongjun (1): power: supply: adp5061: fix out-of-bounds read in adp5061_get_chg_type() Wen Gong (1): wifi: ath10k: add peer map clean up for peer delete in ath10k_sta_state() Wenchao Chen (1): mmc: sdhci-sprd: Fix minimum clock limit William Dean (1): mtd: devices: docg3: check the return value of devm_ioremap() in the probe Wright Feng (1): wifi: brcmfmac: fix invalid address access when enabling SCAN log level Xiaoke Wang (1): staging: rtl8723bs: fix a potential memory leak in rtw_init_cmd_priv() Xin Long (1): sctp: handle the error returned from sctp_auth_asoc_init_active_key Xu Qiang (3): spi: qup: add missing clk_disable_unprepare on error in spi_qup_resume() spi: qup: add missing clk_disable_unprepare on error in spi_qup_pm_resume_runtime() media: meson: vdec: add missing clk_disable_unprepare on error in vdec_hevc_start() Ye Bin (7): jbd2: fix potential buffer head reference count leak jbd2: fix potential use-after-free in jbd2_fc_wait_bufs jbd2: add miss release buffer head in fc_do_one_pass() ext4: fix miss release buffer head in ext4_fc_write_inode ext4: fix potential memory leak in ext4_fc_record_modified_inode() ext4: fix potential memory leak in ext4_fc_record_regions() ext4: update 'state->fc_regions_size' after successful memory allocation Yipeng Zou (2): tracing: kprobe: Fix kprobe event gen test module on exit tracing: kprobe: Make gen test module work in arm and riscv Yu Kuai (1): blk-throttle: prevent overflow while calculating wait time Zeng Jingxiang (1): gpu: lontium-lt9611: Fix NULL pointer dereference in lt9611_connector_init() Zhang Qilong (7): spi: dw: Fix PM disable depth imbalance in dw_spi_bt1_probe spi/omap100k:Fix PM disable depth imbalance in omap1_spi100k_probe ASoC: wm8997: Fix PM disable depth imbalance in wm8997_probe ASoC: wm5110: Fix PM disable depth imbalance in wm5110_probe ASoC: wm5102: Fix PM disable depth imbalance in wm5102_probe ASoC: mt6660: Fix PM disable depth imbalance in mt6660_i2c_probe f2fs: fix race condition on setting FI_NO_EXTENT flag Zhang Rui (1): powercap: intel_rapl: Use standard Energy Unit for SPR Dram RAPL domain Zhang Xiaoxu (1): cifs: Fix the error length of VALIDATE_NEGOTIATE_INFO message Zheng Yejian (1): ftrace: Properly unset FTRACE_HASH_FL_MOD Zheng Yongjun (2): net: fs_enet: Fix wrong check in do_pd_setup powerpc/powernv: add missing of_node_put() in opal_export_attrs() Zhengchao Shao (1): crypto: sahara - don't sleep when in softirq Zheyu Ma (2): drm/bridge: megachips: Fix a null pointer dereference bug media: cx88: Fix a null-ptr-deref bug in buffer_prepare() Zhu Yanjun (2): RDMA/rxe: Fix "kernel NULL pointer dereference" error RDMA/rxe: Fix the error caused by qp->sk Ziyang Xuan (1): can: bcm: check the result of can_send() in bcm_can_tx() Zqiang (1): rcu-tasks: Convert RCU_LOCKDEP_WARN() to WARN_ONCE() hongao (1): drm/amdgpu: fix initial connector audio value sunghwan jung (1): Revert "usb: storage: Add quirk for Samsung Fit flash" Documentation/ABI/testing/sysfs-bus-iio | 2 +- Makefile | 6 +- arch/arm/Kconfig | 1 - arch/arm/boot/dts/armada-385-turris-omnia.dts | 4 +- arch/arm/boot/dts/exynos4412-midas.dtsi | 2 +- arch/arm/boot/dts/exynos4412-origen.dts | 2 +- arch/arm/boot/dts/imx6dl.dtsi | 3 + arch/arm/boot/dts/imx6q.dtsi | 3 + arch/arm/boot/dts/imx6qp.dtsi | 6 + arch/arm/boot/dts/imx6sl.dtsi | 3 + arch/arm/boot/dts/imx6sll.dtsi | 3 + arch/arm/boot/dts/imx6sx.dtsi | 6 + arch/arm/boot/dts/imx7d-sdb.dts | 7 +- arch/arm/boot/dts/kirkwood-lsxl.dtsi | 16 +- arch/arm/mm/dump.c | 2 +- arch/arm/mm/mmu.c | 4 + .../boot/dts/freescale/imx8mq-librem5.dtsi | 1 + arch/ia64/mm/numa.c | 1 + arch/mips/bcm47xx/prom.c | 4 +- arch/mips/sgi-ip27/ip27-xtalk.c | 74 +++-- arch/powerpc/Makefile | 2 +- arch/powerpc/boot/Makefile | 1 + .../boot/dts/fsl/e500v1_power_isa.dtsi | 51 ++++ arch/powerpc/boot/dts/fsl/mpc8540ads.dts | 2 +- arch/powerpc/boot/dts/fsl/mpc8541cds.dts | 2 +- arch/powerpc/boot/dts/fsl/mpc8555cds.dts | 2 +- arch/powerpc/boot/dts/fsl/mpc8560ads.dts | 2 +- arch/powerpc/kernel/pci_dn.c | 1 + arch/powerpc/math-emu/math_efp.c | 1 + arch/powerpc/platforms/powernv/opal.c | 1 + arch/powerpc/sysdev/fsl_msi.c | 2 + arch/riscv/Makefile | 2 + arch/riscv/include/asm/io.h | 16 +- arch/riscv/kernel/sys_riscv.c | 3 - arch/riscv/mm/fault.c | 3 +- arch/sh/include/asm/sections.h | 2 +- arch/sh/kernel/machvec.c | 10 +- arch/um/kernel/um_arch.c | 2 +- arch/x86/include/asm/hyperv-tlfs.h | 4 +- arch/x86/include/asm/microcode.h | 1 + arch/x86/kernel/cpu/feat_ctl.c | 2 +- arch/x86/kernel/cpu/microcode/amd.c | 3 +- arch/x86/kernel/cpu/resctrl/pseudo_lock.c | 12 +- arch/x86/kvm/emulate.c | 2 +- arch/x86/kvm/vmx/nested.c | 30 +- arch/x86/kvm/vmx/vmx.c | 12 +- arch/x86/xen/enlighten_pv.c | 3 +- block/blk-throttle.c | 8 +- crypto/akcipher.c | 8 + drivers/acpi/acpi_video.c | 16 ++ drivers/acpi/apei/ghes.c | 2 +- drivers/ata/libahci_platform.c | 14 +- drivers/block/nbd.c | 6 +- drivers/bluetooth/btusb.c | 47 +++- drivers/bluetooth/hci_ldisc.c | 7 +- drivers/bluetooth/hci_serdev.c | 10 +- drivers/char/hw_random/imx-rngc.c | 14 +- drivers/clk/baikal-t1/ccu-div.c | 65 +++++ drivers/clk/baikal-t1/ccu-div.h | 10 + drivers/clk/baikal-t1/clk-ccu-div.c | 26 +- drivers/clk/bcm/clk-bcm2835.c | 8 +- drivers/clk/berlin/bg2.c | 5 +- drivers/clk/berlin/bg2q.c | 6 +- drivers/clk/clk-ast2600.c | 2 +- drivers/clk/clk-oxnas.c | 6 +- drivers/clk/clk-qoriq.c | 10 +- drivers/clk/clk-versaclock5.c | 2 +- drivers/clk/mediatek/clk-mt8183-mfgcfg.c | 6 +- drivers/clk/meson/meson-aoclk.c | 5 +- drivers/clk/meson/meson-eeclk.c | 5 +- drivers/clk/meson/meson8b.c | 5 +- drivers/clk/qcom/apss-ipq6018.c | 2 +- drivers/clk/sprd/common.c | 9 +- drivers/clk/tegra/clk-tegra114.c | 1 + drivers/clk/tegra/clk-tegra20.c | 1 + drivers/clk/tegra/clk-tegra210.c | 1 + drivers/clk/ti/clk-dra7-atl.c | 9 +- drivers/clk/zynqmp/clkc.c | 7 + drivers/clk/zynqmp/pll.c | 31 +-- drivers/crypto/cavium/cpt/cptpf_main.c | 6 +- drivers/crypto/ccp/ccp-dmaengine.c | 6 +- drivers/crypto/inside-secure/safexcel_hash.c | 8 +- .../crypto/marvell/octeontx/otx_cptpf_ucode.c | 18 +- drivers/crypto/qat/qat_common/qat_algs.c | 109 +++++--- drivers/crypto/qat/qat_common/qat_crypto.h | 24 ++ drivers/crypto/sahara.c | 18 +- drivers/dma-buf/udmabuf.c | 9 +- drivers/dma/hisi_dma.c | 28 +- drivers/dma/ioat/dma.c | 6 +- drivers/firmware/efi/libstub/fdt.c | 8 - drivers/firmware/google/gsmi.c | 9 + drivers/fpga/dfl.c | 2 +- drivers/fsi/fsi-core.c | 3 + drivers/gpu/drm/Kconfig | 1 + .../gpu/drm/amd/amdgpu/amdgpu_connectors.c | 7 +- drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 14 +- drivers/gpu/drm/amd/amdgpu/amdgpu_display.c | 2 - drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c | 5 - drivers/gpu/drm/amd/amdgpu/soc15.c | 25 ++ .../gpu/drm/amd/display/dc/calcs/bw_fixed.c | 6 +- drivers/gpu/drm/amd/display/dc/core/dc.c | 16 +- drivers/gpu/drm/amd/display/dc/dc_stream.h | 6 +- .../amd/display/dc/dcn10/dcn10_hw_sequencer.c | 35 +-- .../amd/display/dc/dcn10/dcn10_hw_sequencer.h | 3 +- .../gpu/drm/amd/display/dc/inc/hw_sequencer.h | 8 +- drivers/gpu/drm/bridge/adv7511/adv7511.h | 5 +- drivers/gpu/drm/bridge/adv7511/adv7511_cec.c | 4 +- drivers/gpu/drm/bridge/lontium-lt9611.c | 3 +- .../bridge/megachips-stdpxxxx-ge-b850v3-fw.c | 4 +- drivers/gpu/drm/bridge/parade-ps8640.c | 4 +- drivers/gpu/drm/bridge/synopsys/dw-hdmi.c | 13 +- drivers/gpu/drm/drm_bridge.c | 4 +- drivers/gpu/drm/drm_dp_helper.c | 9 - drivers/gpu/drm/drm_dp_mst_topology.c | 6 +- drivers/gpu/drm/drm_ioctl.c | 8 +- drivers/gpu/drm/drm_mipi_dsi.c | 1 + .../gpu/drm/drm_panel_orientation_quirks.c | 6 + drivers/gpu/drm/i915/intel_pm.c | 8 +- drivers/gpu/drm/meson/meson_drv.c | 8 + drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c | 12 +- drivers/gpu/drm/msm/disp/dpu1/dpu_vbif.c | 29 +- drivers/gpu/drm/msm/dp/dp_catalog.c | 2 +- drivers/gpu/drm/nouveau/nouveau_bo.c | 4 +- drivers/gpu/drm/nouveau/nouveau_connector.c | 3 +- drivers/gpu/drm/nouveau/nouveau_prime.c | 1 - drivers/gpu/drm/omapdrm/dss/dss.c | 3 + drivers/gpu/drm/pl111/pl111_versatile.c | 1 + drivers/gpu/drm/udl/udl_modeset.c | 3 - drivers/gpu/drm/vc4/vc4_vec.c | 4 +- drivers/gpu/drm/virtio/virtgpu_vq.c | 2 +- drivers/hid/hid-multitouch.c | 8 +- drivers/hsi/controllers/omap_ssi_core.c | 1 + drivers/hsi/controllers/omap_ssi_port.c | 8 +- drivers/hwmon/gsc-hwmon.c | 1 + drivers/i2c/busses/i2c-mlxbf.c | 44 ++- drivers/iio/adc/ad7923.c | 4 +- drivers/iio/adc/at91-sama5d2_adc.c | 28 +- drivers/iio/adc/ltc2497.c | 13 + drivers/iio/dac/ad5593r.c | 46 +-- drivers/iio/inkern.c | 6 +- drivers/iio/pressure/dps310.c | 262 +++++++++++------- drivers/infiniband/core/cm.c | 14 +- drivers/infiniband/core/uverbs_cmd.c | 5 +- drivers/infiniband/core/verbs.c | 2 + drivers/infiniband/hw/hns/hns_roce_mr.c | 1 - drivers/infiniband/hw/mlx4/mr.c | 1 - drivers/infiniband/sw/rxe/rxe_qp.c | 10 +- drivers/infiniband/sw/siw/siw_qp_rx.c | 27 +- drivers/iommu/omap-iommu-debug.c | 6 +- drivers/leds/leds-lm3601x.c | 2 - drivers/mailbox/bcm-flexrm-mailbox.c | 8 +- drivers/md/bcache/writeback.c | 73 +++-- drivers/md/raid0.c | 2 +- drivers/md/raid5.c | 14 +- drivers/media/pci/cx88/cx88-vbi.c | 9 +- drivers/media/pci/cx88/cx88-video.c | 43 +-- drivers/media/platform/exynos4-is/fimc-is.c | 1 + drivers/media/platform/xilinx/xilinx-vipp.c | 9 +- drivers/memory/of_memory.c | 2 + drivers/memory/pl353-smc.c | 1 + drivers/mfd/fsl-imx25-tsadc.c | 34 ++- drivers/mfd/intel_soc_pmic_core.c | 1 + drivers/mfd/lp8788-irq.c | 3 + drivers/mfd/lp8788.c | 12 +- drivers/mfd/sm501.c | 7 +- drivers/misc/ocxl/file.c | 2 + drivers/mmc/host/au1xmmc.c | 3 +- drivers/mmc/host/sdhci-msm.c | 1 + drivers/mmc/host/sdhci-sprd.c | 2 +- drivers/mmc/host/wmt-sdmmc.c | 5 +- drivers/mtd/devices/docg3.c | 7 +- drivers/mtd/nand/raw/atmel/nand-controller.c | 1 + drivers/mtd/nand/raw/fsl_elbc_nand.c | 28 +- drivers/mtd/nand/raw/meson_nand.c | 4 +- drivers/net/can/usb/kvaser_usb/kvaser_usb.h | 2 + .../net/can/usb/kvaser_usb/kvaser_usb_core.c | 3 +- .../net/can/usb/kvaser_usb/kvaser_usb_hydra.c | 2 +- .../net/can/usb/kvaser_usb/kvaser_usb_leaf.c | 79 ++++++ .../net/ethernet/freescale/fs_enet/mac-fec.c | 2 +- drivers/net/wireless/ath/ath10k/mac.c | 54 ++-- drivers/net/wireless/ath/ath11k/mac.c | 25 +- drivers/net/wireless/ath/ath9k/htc_hst.c | 43 ++- .../broadcom/brcm80211/brcmfmac/core.c | 3 +- .../broadcom/brcm80211/brcmfmac/pno.c | 12 +- .../net/wireless/ralink/rt2x00/rt2800lib.c | 34 ++- .../wireless/realtek/rtl8xxxu/rtl8xxxu_core.c | 75 ++++- drivers/nvme/host/core.c | 3 +- drivers/nvme/host/pci.c | 3 +- drivers/nvme/target/tcp.c | 11 +- drivers/pci/setup-res.c | 11 + drivers/phy/qualcomm/phy-qcom-usb-hsic.c | 6 +- drivers/platform/chrome/chromeos_laptop.c | 24 +- drivers/platform/chrome/cros_ec.c | 8 +- drivers/platform/chrome/cros_ec_chardev.c | 3 + drivers/platform/chrome/cros_ec_proto.c | 32 +++ drivers/platform/x86/msi-laptop.c | 14 +- drivers/power/supply/adp5061.c | 6 +- drivers/powercap/intel_rapl_common.c | 4 +- drivers/regulator/core.c | 2 +- drivers/regulator/qcom_rpm-regulator.c | 24 +- drivers/scsi/3w-9xxx.c | 2 +- drivers/scsi/iscsi_tcp.c | 73 +++-- drivers/scsi/iscsi_tcp.h | 2 + drivers/scsi/libsas/sas_expander.c | 2 +- drivers/scsi/qedf/qedf_main.c | 21 ++ drivers/soc/qcom/smem_state.c | 3 +- drivers/soc/qcom/smsm.c | 20 +- drivers/soc/tegra/Kconfig | 1 - drivers/soundwire/cadence_master.c | 9 +- drivers/soundwire/intel.c | 1 - drivers/spi/spi-dw-bt1.c | 4 +- drivers/spi/spi-meson-spicc.c | 6 +- drivers/spi/spi-mt7621.c | 8 +- drivers/spi/spi-omap-100k.c | 1 + drivers/spi/spi-qup.c | 21 +- drivers/spi/spi-s3c64xx.c | 9 + drivers/spi/spi.c | 2 + drivers/spmi/spmi-pmic-arb.c | 13 +- drivers/staging/greybus/audio_helper.c | 11 - drivers/staging/media/meson/vdec/vdec_hevc.c | 6 +- drivers/staging/media/sunxi/cedrus/cedrus.c | 4 +- drivers/staging/rtl8723bs/core/rtw_cmd.c | 16 +- drivers/staging/vt6655/device_main.c | 8 +- drivers/thermal/intel/intel_powerclamp.c | 4 +- drivers/thermal/qcom/tsens-v0_1.c | 2 +- drivers/thunderbolt/switch.c | 24 ++ drivers/thunderbolt/tb.h | 1 + drivers/thunderbolt/tb_regs.h | 1 + drivers/thunderbolt/usb4.c | 20 ++ drivers/tty/serial/8250/8250_core.c | 19 +- drivers/tty/serial/8250/8250_port.c | 15 +- drivers/tty/serial/fsl_lpuart.c | 2 + drivers/tty/serial/jsm/jsm_driver.c | 3 +- drivers/tty/serial/xilinx_uartps.c | 2 + drivers/usb/common/common.c | 102 ++++++- drivers/usb/common/debug.c | 78 +++++- drivers/usb/core/devices.c | 21 +- drivers/usb/core/endpoint.c | 35 +-- drivers/usb/core/quirks.c | 4 + drivers/usb/gadget/function/f_printer.c | 12 +- drivers/usb/host/xhci-mem.c | 7 +- drivers/usb/host/xhci-plat.c | 18 +- drivers/usb/host/xhci.c | 3 +- drivers/usb/host/xhci.h | 1 + drivers/usb/misc/idmouse.c | 8 +- drivers/usb/musb/musb_gadget.c | 3 + drivers/usb/storage/unusual_devs.h | 6 - drivers/vhost/vsock.c | 2 +- drivers/video/fbdev/stifb.c | 2 +- fs/btrfs/qgroup.c | 15 + fs/btrfs/scrub.c | 36 +++ fs/cifs/file.c | 9 + fs/cifs/smb2pdu.c | 7 +- fs/dlm/ast.c | 6 +- fs/dlm/lock.c | 16 +- fs/ext4/fast_commit.c | 40 +-- fs/ext4/file.c | 6 + fs/ext4/inode.c | 14 +- fs/ext4/resize.c | 2 +- fs/ext4/super.c | 1 + fs/f2fs/checkpoint.c | 23 +- fs/f2fs/data.c | 4 +- fs/f2fs/extent_cache.c | 3 +- fs/f2fs/f2fs.h | 27 +- fs/f2fs/gc.c | 10 +- fs/f2fs/recovery.c | 23 +- fs/f2fs/segment.c | 47 ++-- fs/f2fs/super.c | 4 +- fs/jbd2/commit.c | 2 +- fs/jbd2/journal.c | 10 +- fs/jbd2/recovery.c | 1 + fs/jbd2/transaction.c | 6 +- fs/nfsd/nfs4recover.c | 4 +- fs/nfsd/nfs4state.c | 5 + fs/nfsd/nfs4xdr.c | 2 +- fs/userfaultfd.c | 4 +- include/linux/ata.h | 39 +-- include/linux/dynamic_debug.h | 11 +- include/linux/iova.h | 2 +- include/linux/once.h | 28 ++ include/linux/ring_buffer.h | 2 +- include/linux/serial_8250.h | 1 + include/linux/skbuff.h | 2 + include/linux/tcp.h | 2 +- include/linux/usb/ch9.h | 62 +---- include/net/ieee802154_netdev.h | 12 +- include/net/tcp.h | 5 +- include/uapi/linux/usb/ch9.h | 13 + kernel/bpf/btf.c | 2 +- kernel/bpf/syscall.c | 2 + kernel/cgroup/cpuset.c | 18 +- kernel/gcov/gcc_4_7.c | 18 +- kernel/livepatch/transition.c | 18 +- kernel/rcu/tasks.h | 2 +- kernel/rcu/tree.c | 17 +- kernel/trace/ftrace.c | 8 +- kernel/trace/kprobe_event_gen_test.c | 49 +++- kernel/trace/ring_buffer.c | 54 +++- kernel/trace/trace.c | 23 ++ lib/dynamic_debug.c | 45 +-- lib/once.c | 30 ++ mm/mmap.c | 5 +- net/bluetooth/hci_core.c | 34 ++- net/bluetooth/hci_sysfs.c | 3 + net/bluetooth/l2cap_core.c | 17 +- net/can/bcm.c | 7 +- net/core/stream.c | 3 +- net/ieee802154/socket.c | 4 + net/ipv4/inet_hashtables.c | 4 +- net/ipv4/netfilter/nft_fib_ipv4.c | 3 + net/ipv4/tcp.c | 16 +- net/ipv4/tcp_output.c | 19 +- net/ipv6/netfilter/nft_fib_ipv6.c | 6 +- net/mac80211/cfg.c | 3 - net/openvswitch/datapath.c | 18 +- net/rds/tcp.c | 2 +- net/sctp/auth.c | 18 +- net/vmw_vsock/virtio_transport_common.c | 2 +- net/xfrm/xfrm_ipcomp.c | 1 + scripts/Kbuild.include | 23 +- scripts/package/mkspec | 4 +- scripts/selinux/install_policy.sh | 2 +- security/Kconfig.hardening | 63 +++-- sound/core/pcm_dmaengine.c | 8 +- sound/core/rawmidi.c | 2 - sound/core/sound_oss.c | 13 +- sound/pci/hda/hda_beep.c | 15 +- sound/pci/hda/hda_beep.h | 1 + sound/pci/hda/patch_hdmi.c | 6 - sound/pci/hda/patch_realtek.c | 11 +- sound/pci/hda/patch_sigmatel.c | 25 +- sound/soc/codecs/da7219.c | 5 +- sound/soc/codecs/mt6660.c | 8 +- sound/soc/codecs/tas2764.c | 78 ++---- sound/soc/codecs/wcd9335.c | 2 +- sound/soc/codecs/wcd934x.c | 2 +- sound/soc/codecs/wm5102.c | 6 +- sound/soc/codecs/wm5110.c | 6 +- sound/soc/codecs/wm8997.c | 6 +- sound/soc/fsl/eukrea-tlv320.c | 8 +- sound/soc/sh/rcar/ctu.c | 6 +- sound/soc/sh/rcar/dvc.c | 6 +- sound/soc/sh/rcar/mix.c | 6 +- sound/soc/sh/rcar/src.c | 5 +- sound/soc/sh/rcar/ssi.c | 4 +- sound/soc/sof/sof-pci-dev.c | 2 +- sound/usb/endpoint.c | 6 +- tools/bpf/bpftool/btf_dumper.c | 2 +- tools/bpf/bpftool/main.c | 10 + tools/lib/bpf/xsk.c | 6 +- tools/objtool/elf.c | 7 +- tools/perf/util/intel-pt.c | 9 +- .../arm64/signal/testcases/testcases.c | 2 +- tools/testing/selftests/tpm2/tpm2.py | 4 + 354 files changed, 3018 insertions(+), 1399 deletions(-) create mode 100644 arch/powerpc/boot/dts/fsl/e500v1_power_isa.dtsi -- 2.25.1

1 371

[PATCH v2] eulerfs: fix wrong dereferencing in eufs_lookup
by Kang Chen 12 Apr '23

12 Apr '23

uniontech inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I6TN56 CVE: NA -------------------------------- smatch report: fs/eulerfs/namei.c:118 eufs_lookup() error: 'inode' dereferencing possible ERR_PTR() fix it by using the ino above in eufs_err. Signed-off-by: Kang Chen <void0red(a)hust.edu.cn> --- v2 -> v1: use correct string format fs/eulerfs/namei.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/eulerfs/namei.c b/fs/eulerfs/namei.c index e4c6c36575f2..dd3bbc0b453c 100644 --- a/fs/eulerfs/namei.c +++ b/fs/eulerfs/namei.c @@ -115,8 +115,8 @@ static struct dentry *eufs_lookup(struct inode *dir, struct dentry *dentry, inode = eufs_iget(dir->i_sb, s2p(dir->i_sb, de->inode)); if (inode == ERR_PTR(-ESTALE)) { - eufs_err(dir->i_sb, "deleted inode referenced: 0x%lx", - inode->i_ino); + eufs_err(dir->i_sb, "deleted inode referenced: 0x%llx", + le64_to_cpu(de->inode)); return ERR_PTR(-EIO); } not_found: -- 2.34.1

3 7

[PATCH rdma-core v4 0/2] Support congestion control algorithm
by Chengchang Tang 12 Apr '23

12 Apr '23

From: Juan Zhou <zhoujuan51(a)h-partners.com> Yixing Liu (2): Update kernel headers libhns: Support congestion control algorithm configuration kernel-headers/rdma/hns-abi.h | 18 ++++- providers/hns/hns_roce_u.c | 1 + providers/hns/hns_roce_u.h | 6 ++ providers/hns/hns_roce_u_verbs.c | 114 +++++++++++++++++++++++++++++-- providers/hns/hnsdv.h | 24 ++++++- providers/hns/libhns.map | 1 + 6 files changed, 156 insertions(+), 8 deletions(-) -- 2.30.0

1 2

[OLK-5.10 v5 0/2] Support congestion control algorithm
by Chengchang Tang 12 Apr '23

12 Apr '23

From: Juan Zhou <zhoujuan51(a)h-partners.com> This group of patches implements the congestion control algorithm configuration. Yixing Liu (2): RDMA/hns: Modify congestion abbreviation RDMA/hns: Support congestion control algorithm configuration at QP granularity drivers/infiniband/hw/hns/hns_roce_device.h | 16 +-- drivers/infiniband/hw/hns/hns_roce_hw_v2.c | 113 ++++++++++---------- drivers/infiniband/hw/hns/hns_roce_hw_v2.h | 11 +- drivers/infiniband/hw/hns/hns_roce_main.c | 4 + drivers/infiniband/hw/hns/hns_roce_qp.c | 46 ++++++++ drivers/infiniband/hw/hns/hns_roce_sysfs.c | 2 +- include/uapi/rdma/hns-abi.h | 18 +++- 7 files changed, 142 insertions(+), 68 deletions(-) -- 2.30.0

1 2

[PATCH openEuler-5.10-LTS 01/27] xfs: log worker needs to start before intent/unlink recovery
by Jialin Zhang 12 Apr '23

12 Apr '23

From: Dave Chinner <dchinner(a)redhat.com> mainline inclusion from mainline-v5.17-rc6 commit a9a4bc8c76d747aa40b30e2dfc176c781f353a08 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I4KIAO CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- After 963 iterations of generic/530, it deadlocked during recovery on a pinned inode cluster buffer like so: XFS (pmem1): Starting recovery (logdev: internal) INFO: task kworker/8:0:306037 blocked for more than 122 seconds. Not tainted 5.17.0-rc6-dgc+ #975 "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. task:kworker/8:0 state:D stack:13024 pid:306037 ppid: 2 flags:0x00004000 Workqueue: xfs-inodegc/pmem1 xfs_inodegc_worker Call Trace: <TASK> __schedule+0x30d/0x9e0 schedule+0x55/0xd0 schedule_timeout+0x114/0x160 __down+0x99/0xf0 down+0x5e/0x70 xfs_buf_lock+0x36/0xf0 xfs_buf_find+0x418/0x850 xfs_buf_get_map+0x47/0x380 xfs_buf_read_map+0x54/0x240 xfs_trans_read_buf_map+0x1bd/0x490 xfs_imap_to_bp+0x4f/0x70 xfs_iunlink_map_ino+0x66/0xd0 xfs_iunlink_map_prev.constprop.0+0x148/0x2f0 xfs_iunlink_remove_inode+0xf2/0x1d0 xfs_inactive_ifree+0x1a3/0x900 xfs_inode_unlink+0xcc/0x210 xfs_inodegc_worker+0x1ac/0x2f0 process_one_work+0x1ac/0x390 worker_thread+0x56/0x3c0 kthread+0xf6/0x120 ret_from_fork+0x1f/0x30 </TASK> task:mount state:D stack:13248 pid:324509 ppid:324233 flags:0x00004000 Call Trace: <TASK> __schedule+0x30d/0x9e0 schedule+0x55/0xd0 schedule_timeout+0x114/0x160 __down+0x99/0xf0 down+0x5e/0x70 xfs_buf_lock+0x36/0xf0 xfs_buf_find+0x418/0x850 xfs_buf_get_map+0x47/0x380 xfs_buf_read_map+0x54/0x240 xfs_trans_read_buf_map+0x1bd/0x490 xfs_imap_to_bp+0x4f/0x70 xfs_iget+0x300/0xb40 xlog_recover_process_one_iunlink+0x4c/0x170 xlog_recover_process_iunlinks.isra.0+0xee/0x130 xlog_recover_finish+0x57/0x110 xfs_log_mount_finish+0xfc/0x1e0 xfs_mountfs+0x540/0x910 xfs_fs_fill_super+0x495/0x850 get_tree_bdev+0x171/0x270 xfs_fs_get_tree+0x15/0x20 vfs_get_tree+0x24/0xc0 path_mount+0x304/0xba0 __x64_sys_mount+0x108/0x140 do_syscall_64+0x35/0x80 entry_SYSCALL_64_after_hwframe+0x44/0xae </TASK> task:xfsaild/pmem1 state:D stack:14544 pid:324525 ppid: 2 flags:0x00004000 Call Trace: <TASK> __schedule+0x30d/0x9e0 schedule+0x55/0xd0 io_schedule+0x4b/0x80 xfs_buf_wait_unpin+0x9e/0xf0 __xfs_buf_submit+0x14a/0x230 xfs_buf_delwri_submit_buffers+0x107/0x280 xfs_buf_delwri_submit_nowait+0x10/0x20 xfsaild+0x27e/0x9d0 kthread+0xf6/0x120 ret_from_fork+0x1f/0x30 We have the mount process waiting on an inode cluster buffer read, inodegc doing unlink waiting on the same inode cluster buffer, and the AIL push thread blocked in writeback waiting for the inode cluster buffer to become unpinned. What has happened here is that the AIL push thread has raced with the inodegc process modifying, committing and pinning the inode cluster buffer here in xfs_buf_delwri_submit_buffers() here: blk_start_plug(&plug); list_for_each_entry_safe(bp, n, buffer_list, b_list) { if (!wait_list) { if (xfs_buf_ispinned(bp)) { pinned++; continue; } Here >>>>>> if (!xfs_buf_trylock(bp)) continue; Basically, the AIL has found the buffer wasn't pinned and got the lock without blocking, but then the buffer was pinned. This implies the processing here was pre-empted between the pin check and the lock, because the pin count can only be increased while holding the buffer locked. Hence when it has gone to submit the IO, it has blocked waiting for the buffer to be unpinned. With all executing threads now waiting on the buffer to be unpinned, we normally get out of situations like this via the background log worker issuing a log force which will unpinned stuck buffers like this. But at this point in recovery, we haven't started the log worker. In fact, the first thing we do after processing intents and unlinked inodes is *start the log worker*. IOWs, we start it too late to have it break deadlocks like this. Avoid this and any other similar deadlock vectors in intent and unlinked inode recovery by starting the log worker before we recover intents and unlinked inodes. This part of recovery runs as though the filesystem is fully active, so we really should have the same infrastructure running as we normally do at runtime. Signed-off-by: Dave Chinner <dchinner(a)redhat.com> Reviewed-by: Darrick J. Wong <djwong(a)kernel.org> Reviewed-by: Chandan Babu R <chandan.babu(a)oracle.com> Signed-off-by: Darrick J. Wong <djwong(a)kernel.org> Signed-off-by: Long Li <leo.lilong(a)huawei.com> Reviewed-by: Yang Erkun <yangerkun(a)huawei.com> Reviewed-by: Zhang Yi <yi.zhang(a)huawei.com> Signed-off-by: Jialin Zhang <zhangjialin11(a)huawei.com> --- fs/xfs/xfs_log.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c index 92c5d6ef47d6..e154c0d44f9c 100644 --- a/fs/xfs/xfs_log.c +++ b/fs/xfs/xfs_log.c @@ -782,10 +782,9 @@ xfs_log_mount_finish( * mount failure occurs. */ mp->m_super->s_flags |= SB_ACTIVE; + xfs_log_work_queue(mp); if (xlog_recovery_needed(log)) error = xlog_recover_finish(log); - if (!error) - xfs_log_work_queue(mp); mp->m_super->s_flags &= ~SB_ACTIVE; evict_inodes(mp->m_super); -- 2.25.1

1 26

[PATCH openEuler-5.10-LTS-SP1 01/33] xfs: log worker needs to start before intent/unlink recovery
by Jialin Zhang 12 Apr '23

12 Apr '23

From: Dave Chinner <dchinner(a)redhat.com> mainline inclusion from mainline-v5.17-rc6 commit a9a4bc8c76d747aa40b30e2dfc176c781f353a08 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I4KIAO CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- After 963 iterations of generic/530, it deadlocked during recovery on a pinned inode cluster buffer like so: XFS (pmem1): Starting recovery (logdev: internal) INFO: task kworker/8:0:306037 blocked for more than 122 seconds. Not tainted 5.17.0-rc6-dgc+ #975 "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. task:kworker/8:0 state:D stack:13024 pid:306037 ppid: 2 flags:0x00004000 Workqueue: xfs-inodegc/pmem1 xfs_inodegc_worker Call Trace: <TASK> __schedule+0x30d/0x9e0 schedule+0x55/0xd0 schedule_timeout+0x114/0x160 __down+0x99/0xf0 down+0x5e/0x70 xfs_buf_lock+0x36/0xf0 xfs_buf_find+0x418/0x850 xfs_buf_get_map+0x47/0x380 xfs_buf_read_map+0x54/0x240 xfs_trans_read_buf_map+0x1bd/0x490 xfs_imap_to_bp+0x4f/0x70 xfs_iunlink_map_ino+0x66/0xd0 xfs_iunlink_map_prev.constprop.0+0x148/0x2f0 xfs_iunlink_remove_inode+0xf2/0x1d0 xfs_inactive_ifree+0x1a3/0x900 xfs_inode_unlink+0xcc/0x210 xfs_inodegc_worker+0x1ac/0x2f0 process_one_work+0x1ac/0x390 worker_thread+0x56/0x3c0 kthread+0xf6/0x120 ret_from_fork+0x1f/0x30 </TASK> task:mount state:D stack:13248 pid:324509 ppid:324233 flags:0x00004000 Call Trace: <TASK> __schedule+0x30d/0x9e0 schedule+0x55/0xd0 schedule_timeout+0x114/0x160 __down+0x99/0xf0 down+0x5e/0x70 xfs_buf_lock+0x36/0xf0 xfs_buf_find+0x418/0x850 xfs_buf_get_map+0x47/0x380 xfs_buf_read_map+0x54/0x240 xfs_trans_read_buf_map+0x1bd/0x490 xfs_imap_to_bp+0x4f/0x70 xfs_iget+0x300/0xb40 xlog_recover_process_one_iunlink+0x4c/0x170 xlog_recover_process_iunlinks.isra.0+0xee/0x130 xlog_recover_finish+0x57/0x110 xfs_log_mount_finish+0xfc/0x1e0 xfs_mountfs+0x540/0x910 xfs_fs_fill_super+0x495/0x850 get_tree_bdev+0x171/0x270 xfs_fs_get_tree+0x15/0x20 vfs_get_tree+0x24/0xc0 path_mount+0x304/0xba0 __x64_sys_mount+0x108/0x140 do_syscall_64+0x35/0x80 entry_SYSCALL_64_after_hwframe+0x44/0xae </TASK> task:xfsaild/pmem1 state:D stack:14544 pid:324525 ppid: 2 flags:0x00004000 Call Trace: <TASK> __schedule+0x30d/0x9e0 schedule+0x55/0xd0 io_schedule+0x4b/0x80 xfs_buf_wait_unpin+0x9e/0xf0 __xfs_buf_submit+0x14a/0x230 xfs_buf_delwri_submit_buffers+0x107/0x280 xfs_buf_delwri_submit_nowait+0x10/0x20 xfsaild+0x27e/0x9d0 kthread+0xf6/0x120 ret_from_fork+0x1f/0x30 We have the mount process waiting on an inode cluster buffer read, inodegc doing unlink waiting on the same inode cluster buffer, and the AIL push thread blocked in writeback waiting for the inode cluster buffer to become unpinned. What has happened here is that the AIL push thread has raced with the inodegc process modifying, committing and pinning the inode cluster buffer here in xfs_buf_delwri_submit_buffers() here: blk_start_plug(&plug); list_for_each_entry_safe(bp, n, buffer_list, b_list) { if (!wait_list) { if (xfs_buf_ispinned(bp)) { pinned++; continue; } Here >>>>>> if (!xfs_buf_trylock(bp)) continue; Basically, the AIL has found the buffer wasn't pinned and got the lock without blocking, but then the buffer was pinned. This implies the processing here was pre-empted between the pin check and the lock, because the pin count can only be increased while holding the buffer locked. Hence when it has gone to submit the IO, it has blocked waiting for the buffer to be unpinned. With all executing threads now waiting on the buffer to be unpinned, we normally get out of situations like this via the background log worker issuing a log force which will unpinned stuck buffers like this. But at this point in recovery, we haven't started the log worker. In fact, the first thing we do after processing intents and unlinked inodes is *start the log worker*. IOWs, we start it too late to have it break deadlocks like this. Avoid this and any other similar deadlock vectors in intent and unlinked inode recovery by starting the log worker before we recover intents and unlinked inodes. This part of recovery runs as though the filesystem is fully active, so we really should have the same infrastructure running as we normally do at runtime. Signed-off-by: Dave Chinner <dchinner(a)redhat.com> Reviewed-by: Darrick J. Wong <djwong(a)kernel.org> Reviewed-by: Chandan Babu R <chandan.babu(a)oracle.com> Signed-off-by: Darrick J. Wong <djwong(a)kernel.org> Signed-off-by: Long Li <leo.lilong(a)huawei.com> Reviewed-by: Yang Erkun <yangerkun(a)huawei.com> Reviewed-by: Zhang Yi <yi.zhang(a)huawei.com> Signed-off-by: Jialin Zhang <zhangjialin11(a)huawei.com> --- fs/xfs/xfs_log.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c index 92c5d6ef47d6..e154c0d44f9c 100644 --- a/fs/xfs/xfs_log.c +++ b/fs/xfs/xfs_log.c @@ -782,10 +782,9 @@ xfs_log_mount_finish( * mount failure occurs. */ mp->m_super->s_flags |= SB_ACTIVE; + xfs_log_work_queue(mp); if (xlog_recovery_needed(log)) error = xlog_recover_finish(log); - if (!error) - xfs_log_work_queue(mp); mp->m_super->s_flags &= ~SB_ACTIVE; evict_inodes(mp->m_super); -- 2.25.1

1 32

[PATCH openEuler-1.0-LTS] hwmon: (xgene) Fix use after free bug in xgene_hwmon_remove due to race condition
by Yongqiang Liu 11 Apr '23

11 Apr '23

From: Zheng Wang <zyytlz.wz(a)163.com> mainline inclusion from mainline-v6.3-rc3 commit cb090e64cf25602b9adaf32d5dfc9c8bec493cd1 category: bugfix bugzilla: 188657, https://gitee.com/src-openeuler/kernel/issues/I6T36A CVE: CVE-2023-1855 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- In xgene_hwmon_probe, &ctx->workq is bound with xgene_hwmon_evt_work. Then it will be started. If we remove the driver which will call xgene_hwmon_remove to clean up, there may be unfinished work. The possible sequence is as follows: Fix it by finishing the work before cleanup in xgene_hwmon_remove. CPU0 CPU1 |xgene_hwmon_evt_work xgene_hwmon_remove | kfifo_free(&ctx->async_msg_fifo);| | |kfifo_out_spinlocked |//use &ctx->async_msg_fifo Fixes: 2ca492e22cb7 ("hwmon: (xgene) Fix crash when alarm occurs before driver probe") Signed-off-by: Zheng Wang <zyytlz.wz(a)163.com> Link: https://lore.kernel.org/r/20230310084007.1403388-1-zyytlz.wz@163.com Signed-off-by: Guenter Roeck <linux(a)roeck-us.net> Signed-off-by: Zhao Wenhui <zhaowenhui8(a)huawei.com> Reviewed-by: songping yu <yusongping(a)huawei.com> Reviewed-by: Zhang Qiao <zhangqiao22(a)huawei.com> Reviewed-by: Xiu Jianfeng <xiujianfeng(a)huawei.com> Signed-off-by: Yongqiang Liu <liuyongqiang13(a)huawei.com> --- drivers/hwmon/xgene-hwmon.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/hwmon/xgene-hwmon.c b/drivers/hwmon/xgene-hwmon.c index a3cd91f23267..2dd19a420305 100644 --- a/drivers/hwmon/xgene-hwmon.c +++ b/drivers/hwmon/xgene-hwmon.c @@ -780,6 +780,7 @@ static int xgene_hwmon_remove(struct platform_device *pdev) { struct xgene_hwmon_dev *ctx = platform_get_drvdata(pdev); + cancel_work_sync(&ctx->workq); hwmon_device_unregister(ctx->hwmon_dev); kfifo_free(&ctx->async_msg_fifo); if (acpi_disabled) -- 2.25.1

1 0

[Dev] Kernel SIG邀请您参加2023年4月20日~21日 openEuler Developer Day SIG组开放工作会议
by Zhengzengkai 11 Apr '23

11 Apr '23

��ã� openEuler Developer Day 2023(�� ODD 2023�� openEuler��ȶ��飬 �ǿ��ԭ�ӿ�Դ�� openEuler ��Ŀ��߷�ᡣ ODD 2023��2023��4��20��~21��Ϻ��ֶ��Ƶ��У��ӭ��ұ��λᡣ ��̼��Ϣ�ɲο��ӣ�https://www.openeuler.org/zh/interaction/summit-list/devday2023/ ��ӣ�https://e-campaign.huawei.com/m/RNN3Yz ��openEuler Kernel SIG��μ�4��21��16��00 �C 17��30��е�ODD 2023 Kernel SIG��¿��Ź��飬 ��ʱ��ߣ��潻�� ¿��Ź��ǰ�ռ��⣬�밴��+��+��ˡ��ʽ�ύ��etherpad�� https://etherpad.openeuler.org/p/ODD2023_Kernel_SIG

1 0

[PATCH] fs: eulerfs: fix wrong dereferencing in eufs_lookup
by Kang Chen 10 Apr '23

10 Apr '23

inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I6TN56 -------------------------------- smatch report: fs/eulerfs/namei.c:118 eufs_lookup() error: 'inode' dereferencing possible ERR_PTR() Signed-off-by: Kang Chen <void0red(a)hust.edu.cn> --- I run smatch on the openEuler-2203-sp1 source and find some bugs. But I have on idea on the fields of the commit message template. Please let me know if there is anything that can be improved. fs/eulerfs/namei.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/eulerfs/namei.c b/fs/eulerfs/namei.c index e4c6c36575f2..cfba6eefbcc8 100644 --- a/fs/eulerfs/namei.c +++ b/fs/eulerfs/namei.c @@ -116,7 +116,7 @@ static struct dentry *eufs_lookup(struct inode *dir, struct dentry *dentry, inode = eufs_iget(dir->i_sb, s2p(dir->i_sb, de->inode)); if (inode == ERR_PTR(-ESTALE)) { eufs_err(dir->i_sb, "deleted inode referenced: 0x%lx", - inode->i_ino); + le64_to_cpu(de->inode)); return ERR_PTR(-EIO); } not_found: -- 2.34.1

2 1

[PATCH openEuler-1.0-LTS] xirc2ps_cs: Fix use after free bug in xirc2ps_detach
by Yongqiang Liu 10 Apr '23

10 Apr '23

From: Zheng Wang <zyytlz.wz(a)163.com> stable inclusion from stable-v4.19.279 commit 526660c25d3b93b1232a525b75469048388f0928 category: bugfix bugzilla: 188641, https://gitee.com/src-openeuler/kernel/issues/I6R4MM CVE: CVE-2023-1670 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit e8d20c3ded59a092532513c9bd030d1ea66f5f44 ] In xirc2ps_probe, the local->tx_timeout_task was bounded with xirc2ps_tx_timeout_task. When timeout occurs, it will call xirc_tx_timeout->schedule_work to start the work. When we call xirc2ps_detach to remove the driver, there may be a sequence as follows: Stop responding to timeout tasks and complete scheduled tasks before cleanup in xirc2ps_detach, which will fix the problem. CPU0 CPU1 |xirc2ps_tx_timeout_task xirc2ps_detach | free_netdev | kfree(dev); | | | do_reset | //use dev Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Zheng Wang <zyytlz.wz(a)163.com> Signed-off-by: David S. Miller <davem(a)davemloft.net> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Dong Chenchen <dongchenchen2(a)huawei.com> Reviewed-by: Liu Jian <liujian56(a)huawei.com> Reviewed-by: Wang Weiyang <wangweiyang2(a)huawei.com> Signed-off-by: Yongqiang Liu <liuyongqiang13(a)huawei.com> --- drivers/net/ethernet/xircom/xirc2ps_cs.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/net/ethernet/xircom/xirc2ps_cs.c b/drivers/net/ethernet/xircom/xirc2ps_cs.c index fd5288ff53b5..e3438cef5f9c 100644 --- a/drivers/net/ethernet/xircom/xirc2ps_cs.c +++ b/drivers/net/ethernet/xircom/xirc2ps_cs.c @@ -503,6 +503,11 @@ static void xirc2ps_detach(struct pcmcia_device *link) { struct net_device *dev = link->priv; + struct local_info *local = netdev_priv(dev); + + netif_carrier_off(dev); + netif_tx_disable(dev); + cancel_work_sync(&local->tx_timeout_task); dev_dbg(&link->dev, "detach\n"); -- 2.25.1

1 0

[PATCH openEuler-1.0-LTS] 9p/xen : Fix use after free bug in xen_9pfs_front_remove due to race condition
by Yongqiang Liu 10 Apr '23

10 Apr '23

From: Zheng Wang <zyytlz.wz(a)163.com> maillist inclusion category: bugfix bugzilla: 188655, https://gitee.com/src-openeuler/kernel/issues/I6T36H CVE: CVE-2023-1859 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/next/linux-next.git/commit/… ---------------------------------------- In xen_9pfs_front_probe, it calls xen_9pfs_front_alloc_dataring to init priv->rings and bound &ring->work with p9_xen_response. When it calls xen_9pfs_front_event_handler to handle IRQ requests, it will finally call schedule_work to start the work. When we call xen_9pfs_front_remove to remove the driver, there may be a sequence as follows: Fix it by finishing the work before cleanup in xen_9pfs_front_free. Note that, this bug is found by static analysis, which might be false positive. CPU0 CPU1 |p9_xen_response xen_9pfs_front_remove| xen_9pfs_front_free| kfree(priv) | //free priv | |p9_tag_lookup |//use priv->client Fixes: 71ebd71921e4 ("xen/9pfs: connect to the backend") Signed-off-by: Zheng Wang <zyytlz.wz(a)163.com> Reviewed-by: Michal Swiatkowski <michal.swiatkowski(a)linux.intel.com> Signed-off-by: Eric Van Hensbergen <ericvh(a)kernel.org> Signed-off-by: Lu Wei <luwei32(a)huawei.com> Reviewed-by: Yue Haibing <yuehaibing(a)huawei.com> Reviewed-by: Xiu Jianfeng <xiujianfeng(a)huawei.com> Signed-off-by: Yongqiang Liu <liuyongqiang13(a)huawei.com> --- net/9p/trans_xen.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/net/9p/trans_xen.c b/net/9p/trans_xen.c index 81002cba88b3..8e158f09cba8 100644 --- a/net/9p/trans_xen.c +++ b/net/9p/trans_xen.c @@ -290,6 +290,10 @@ static void xen_9pfs_front_free(struct xen_9pfs_front_priv *priv) write_unlock(&xen_9pfs_lock); for (i = 0; i < priv->num_rings; i++) { + struct xen_9pfs_dataring *ring = &priv->rings[i]; + + cancel_work_sync(&ring->work); + if (!priv->rings[i].intf) break; if (priv->rings[i].irq > 0) -- 2.25.1

1 0

[PATCH OLK-5.10] KVM: nVMX: Set LDTR to its architecturally defined value on nested VM-Exit
by 任敏敏(联通集团联通数字科技有限公司本部) 10 Apr '23

10 Apr '23

From: Sean Christopherson <seanjc(a)google.com> stable inclusion from stable-v5.15 commit afc8de0118be84f4058b9977d481aeb3e0758dbb category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I6SN2F CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… ------------------------------ commit afc8de0118be84f4058b9977d481aeb3e0758dbb upstream Set L1's LDTR on VM-Exit per the Intel SDM: The host-state area does not contain a selector field for LDTR. LDTR is established as follows on all VM exits: the selector is cleared to 0000H, the segment is marked unusable and is otherwise undefined (although the base address is always canonical). This is likely a benign bug since the LDTR is unusable, as it means the L1 VMM is conditioned to reload its LDTR in order to function properly on bare metal. Fixes: 4704d0befb07 ("KVM: nVMX: Exiting from L2 to L1") Reviewed-by: Reiji Watanabe <reijiw(a)google.com> Signed-off-by: Sean Christopherson <seanjc(a)google.com> Message-Id: <20210713163324.627647-3-seanjc(a)google.com> Signed-off-by: Paolo Bonzini <pbonzini(a)redhat.com> Signed-off-by: rminmin <renmm6(a)chinaunicom.cn> --- arch/x86/kvm/vmx/nested.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c index 9003b14d72ca..05284589c14d 100644 --- a/arch/x86/kvm/vmx/nested.c +++ b/arch/x86/kvm/vmx/nested.c @@ -4326,6 +4326,10 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu, }; vmx_set_segment(vcpu, &seg, VCPU_SREG_TR); + memset(&seg, 0, sizeof(seg)); + seg.unusable = 1; + vmx_set_segment(vcpu, &seg, VCPU_SREG_LDTR); + kvm_set_dr(vcpu, 7, 0x400); vmcs_write64(GUEST_IA32_DEBUGCTL, 0); -- 2.33.0 Èç¹ûÄúŽíÎóœÓÊÕÁËžÃÓÊŒþ£¬ÇëÍš¹ýµç×ÓÓÊŒþÁ¢ŒŽÍšÖªÎÒÃÇ¡£Çë»ØžŽÓÊŒþµœ hqs-spmc@chinaunicom.cn£¬ŒŽ¿ÉÒÔÍË¶©ŽËÓÊŒþ¡£ÎÒÃÇœ«Á¢ŒŽœ«ÄúµÄÐÅÏ¢ŽÓÎÒÃÇµÄ·¢ËÍÄ¿ÂŒÖÐÉŸ³ý¡£ If you have received this email in error please notify us immediately by e-mail. Please reply to hqs-spmc(a)chinaunicom.cn ,you can unsubscribe from this mail. We will immediately remove your information from send catalogue of our.

1 0

[PATCH 0/2] support dynamic affinity
by Hui Tang 08 Apr '23

08 Apr '23

test report: [root@localhost at]# bash -x dyn_affinity_interface.sh + ret=0 ++ cat /proc/sys/kernel/sched_util_low_pct + default_sched_util_low_pct=85 + read_default_val /proc/sys/kernel/sched_util_low_pct 85 + local interface=/proc/sys/kernel/sched_util_low_pct + local expect_val=85 + echo 'TINFO: test /proc/sys/kernel/sched_util_low_pct default value is 85' TINFO: test /proc/sys/kernel/sched_util_low_pct default value is 85 + '[' '!' -f /proc/sys/kernel/sched_util_low_pct ']' ++ cat /proc/sys/kernel/sched_util_low_pct + '[' 85 '!=' 85 ']' + '[' 0 -ne 0 ']' + echo 'TPASS: dyn_affinity_interface test success' TPASS: dyn_affinity_interface test success + write_some_val /proc/sys/kernel/sched_util_low_pct -1 1 + write_some_val /proc/sys/kernel/sched_util_low_pct 101 1 + write_some_val /proc/sys/kernel/sched_util_low_pct abc 1 + write_some_val /proc/sys/kernel/sched_util_low_pct 100 0 + local interface=/proc/sys/kernel/sched_util_low_pct + local write_val=100 + local expect_ret=0 + echo 'TINFO: write 100 to /proc/sys/kernel/sched_util_low_pct, expect ret: 0' TINFO: write 100 to /proc/sys/kernel/sched_util_low_pct, expect ret: 0 + echo 100 + '[' 0 -ne 0 ']' + echo 'TPASS: write 100 to /proc/sys/kernel/sched_util_low_pct success' TPASS: write 100 to /proc/sys/kernel/sched_util_low_pct success + write_some_val /proc/sys/kernel/sched_util_low_pct 0 0 + local interface=/proc/sys/kernel/sched_util_low_pct + local write_val=0 + local expect_ret=0 + echo 'TINFO: write 0 to /proc/sys/kernel/sched_util_low_pct, expect ret: 0' TINFO: write 0 to /proc/sys/kernel/sched_util_low_pct, expect ret: 0 + echo 0 + '[' 0 -ne 0 ']' + echo 'TPASS: write 0 to /proc/sys/kernel/sched_util_low_pct success' TPASS: write 0 to /proc/sys/kernel/sched_util_low_pct success + cleanup + echo 85 + exit 0 [root@localhost at]# [root@localhost at]# bash -x dyn_affinity_low_load.sh + TEST_CPUSET_PATH=/sys/fs/cgroup/cpuset/cloud + TEST_CPU_PATH=/sys/fs/cgroup/cpu/cloud + ret=0 ++ seq 1 1 + for i in $(seq 1 1) + setup + '[' -d /sys/fs/cgroup/cpuset/cloud ']' + mkdir -p /sys/fs/cgroup/cpuset/cloud /sys/fs/cgroup/cpu/cloud + echo 0 + echo 0-7 + echo 1 + do_test + echo 4166 + echo 4166 + local pid=0 ++ seq 1 3 + for i in $(seq 1 3) + pid=4170 + echo 4170 + echo 4170 + for i in $(seq 1 3) + pid=4171 + echo 4171 + echo 4171 + ./cpu_load_not_while + for i in $(seq 1 3) + pid=4172 + ./cpu_load_not_while + echo 4172 + ./cpu_load_not_while + echo 4172 + echo 4166 + echo 4166 + sleep 0.1 ++ seq 1 100 + for i in $(seq 1 100) ++ ps -o psr,comm,pid ++ grep load ++ egrep 1 -w ++ wc -l + local count=3 + '[' 3 -ne 3 ']' + for i in $(seq 1 100) ++ ps -o psr,comm,pid ++ grep load ++ egrep 1 -w ++ wc -l + local count=3 + '[' 3 -ne 3 ']' + for i in $(seq 1 100) ++ ps -o psr,comm,pid ++ grep load ++ egrep 1 -w ++ wc -l + local count=3 + '[' 3 -ne 3 ']' + for i in $(seq 1 100) ++ ps -o psr,comm,pid ++ grep load ++ egrep 1 -w ++ wc -l + local count=3 + '[' 3 -ne 3 ']' + for i in $(seq 1 100) ++ ps -o psr,comm,pid ++ grep load ++ egrep 1 -w ++ wc -l + local count=3 + '[' 3 -ne 3 ']' + for i in $(seq 1 100) ++ ps -o psr,comm,pid ++ grep load ++ egrep 1 -w ++ wc -l + local count=3 + '[' 3 -ne 3 ']' + for i in $(seq 1 100) ++ ps -o psr,comm,pid ++ grep load ++ egrep 1 -w ++ wc -l + local count=3 + '[' 3 -ne 3 ']' + for i in $(seq 1 100) ++ ps -o psr,comm,pid ++ grep load ++ egrep 1 -w ++ wc -l + local count=3 + '[' 3 -ne 3 ']' + for i in $(seq 1 100) ++ ps -o psr,comm,pid ++ grep load ++ egrep 1 -w ++ wc -l + local count=3 + '[' 3 -ne 3 ']' + for i in $(seq 1 100) ++ ps -o psr,comm,pid ++ grep load ++ egrep 1 -w ++ wc -l + local count=3 + '[' 3 -ne 3 ']' + for i in $(seq 1 100) ++ ps -o psr,comm,pid ++ grep load ++ egrep 1 -w ++ wc -l + local count=3 + '[' 3 -ne 3 ']' + for i in $(seq 1 100) ++ ps -o psr,comm,pid ++ grep load ++ egrep 1 -w ++ wc -l + local count=3 + '[' 3 -ne 3 ']' + for i in $(seq 1 100) ++ ps -o psr,comm,pid ++ grep load ++ egrep 1 -w ++ wc -l + local count=3 + '[' 3 -ne 3 ']' + for i in $(seq 1 100) ++ ps -o psr,comm,pid ++ grep load ++ egrep 1 -w ++ wc -l + local count=3 + '[' 3 -ne 3 ']' + for i in $(seq 1 100) ++ ps -o psr,comm,pid ++ grep load ++ egrep 1 -w ++ wc -l + local count=3 + '[' 3 -ne 3 ']' + for i in $(seq 1 100) ++ ps -o psr,comm,pid ++ grep load ++ egrep 1 -w ++ wc -l + local count=3 + '[' 3 -ne 3 ']' + for i in $(seq 1 100) ++ ps -o psr,comm,pid ++ grep load ++ egrep 1 -w ++ wc -l + local count=3 + '[' 3 -ne 3 ']' + for i in $(seq 1 100) ++ ps -o psr,comm,pid ++ grep load ++ egrep 1 -w ++ wc -l + local count=3 + '[' 3 -ne 3 ']' + for i in $(seq 1 100) ++ ps -o psr,comm,pid ++ grep load ++ egrep 1 -w ++ wc -l + local count=3 + '[' 3 -ne 3 ']' + for i in $(seq 1 100) ++ ps -o psr,comm,pid ++ grep load ++ egrep 1 -w ++ wc -l + local count=3 + '[' 3 -ne 3 ']' + for i in $(seq 1 100) ++ ps -o psr,comm,pid ++ grep load ++ egrep 1 -w ++ wc -l + local count=3 + '[' 3 -ne 3 ']' + for i in $(seq 1 100) ++ ps -o psr,comm,pid ++ grep load ++ egrep 1 -w ++ wc -l + local count=3 + '[' 3 -ne 3 ']' + for i in $(seq 1 100) ++ ps -o psr,comm,pid ++ grep load ++ egrep 1 -w ++ wc -l + local count=3 + '[' 3 -ne 3 ']' + for i in $(seq 1 100) ++ ps -o psr,comm,pid ++ grep load ++ egrep 1 -w ++ wc -l + local count=3 + '[' 3 -ne 3 ']' + for i in $(seq 1 100) ++ ps -o psr,comm,pid ++ egrep 1 -w ++ grep load ++ wc -l + local count=3 + '[' 3 -ne 3 ']' + for i in $(seq 1 100) ++ ps -o psr,comm,pid ++ grep load ++ egrep 1 -w ++ wc -l + local count=3 + '[' 3 -ne 3 ']' + for i in $(seq 1 100) ++ ps -o psr,comm,pid ++ grep load ++ egrep 1 -w ++ wc -l + local count=3 + '[' 3 -ne 3 ']' + for i in $(seq 1 100) ++ ps -o psr,comm,pid ++ grep load ++ egrep 1 -w ++ wc -l + local count=3 + '[' 3 -ne 3 ']' + for i in $(seq 1 100) ++ ps -o psr,comm,pid ++ grep load ++ egrep 1 -w ++ wc -l + local count=3 + '[' 3 -ne 3 ']' + for i in $(seq 1 100) ++ ps -o psr,comm,pid ++ grep load ++ egrep 1 -w ++ wc -l + local count=3 + '[' 3 -ne 3 ']' + for i in $(seq 1 100) ++ ps -o psr,comm,pid ++ grep load ++ egrep 1 -w ++ wc -l + local count=3 + '[' 3 -ne 3 ']' + for i in $(seq 1 100) ++ ps -o psr,comm,pid ++ grep load ++ egrep 1 -w ++ wc -l + local count=3 + '[' 3 -ne 3 ']' + for i in $(seq 1 100) ++ ps -o psr,comm,pid ++ grep load ++ egrep 1 -w ++ wc -l + local count=3 + '[' 3 -ne 3 ']' + for i in $(seq 1 100) ++ ps -o psr,comm,pid ++ grep load ++ egrep 1 -w ++ wc -l + local count=3 + '[' 3 -ne 3 ']' + for i in $(seq 1 100) ++ ps -o psr,comm,pid ++ grep load ++ egrep 1 -w ++ wc -l + local count=3 + '[' 3 -ne 3 ']' + for i in $(seq 1 100) ++ ps -o psr,comm,pid ++ grep load ++ egrep 1 -w ++ wc -l + local count=3 + '[' 3 -ne 3 ']' + for i in $(seq 1 100) ++ ps -o psr,comm,pid ++ grep load ++ egrep 1 -w ++ wc -l + local count=3 + '[' 3 -ne 3 ']' + for i in $(seq 1 100) ++ ps -o psr,comm,pid ++ grep load ++ egrep 1 -w ++ wc -l + local count=3 + '[' 3 -ne 3 ']' + for i in $(seq 1 100) ++ ps -o psr,comm,pid ++ grep load ++ egrep 1 -w ++ wc -l + local count=3 + '[' 3 -ne 3 ']' + for i in $(seq 1 100) ++ ps -o psr,comm,pid ++ grep load ++ egrep 1 -w ++ wc -l + local count=3 + '[' 3 -ne 3 ']' + for i in $(seq 1 100) ++ ps -o psr,comm,pid ++ grep load ++ egrep 1 -w ++ wc -l + local count=3 + '[' 3 -ne 3 ']' + for i in $(seq 1 100) ++ ps -o psr,comm,pid ++ grep load ++ egrep 1 -w ++ wc -l + local count=3 + '[' 3 -ne 3 ']' + for i in $(seq 1 100) ++ ps -o psr,comm,pid ++ grep load ++ egrep 1 -w ++ wc -l + local count=3 + '[' 3 -ne 3 ']' + for i in $(seq 1 100) ++ ps -o psr,comm,pid ++ grep load ++ egrep 1 -w ++ wc -l + local count=3 + '[' 3 -ne 3 ']' + for i in $(seq 1 100) ++ ps -o psr,comm,pid ++ grep load ++ egrep 1 -w ++ wc -l + local count=3 + '[' 3 -ne 3 ']' + for i in $(seq 1 100) ++ ps -o psr,comm,pid ++ grep load ++ egrep 1 -w ++ wc -l + local count=3 + '[' 3 -ne 3 ']' + for i in $(seq 1 100) ++ ps -o psr,comm,pid ++ grep load ++ egrep 1 -w ++ wc -l + local count=3 + '[' 3 -ne 3 ']' + for i in $(seq 1 100) ++ ps -o psr,comm,pid ++ grep load ++ egrep 1 -w ++ wc -l + local count=3 + '[' 3 -ne 3 ']' + for i in $(seq 1 100) ++ ps -o psr,comm,pid ++ grep load ++ egrep 1 -w ++ wc -l + local count=3 + '[' 3 -ne 3 ']' + for i in $(seq 1 100) ++ ps -o psr,comm,pid ++ grep load ++ egrep 1 -w ++ wc -l + local count=3 + '[' 3 -ne 3 ']' + for i in $(seq 1 100) ++ ps -o psr,comm,pid ++ grep load ++ egrep 1 -w ++ wc -l + local count=3 + '[' 3 -ne 3 ']' + for i in $(seq 1 100) ++ ps -o psr,comm,pid ++ grep load ++ egrep 1 -w ++ wc -l + local count=3 + '[' 3 -ne 3 ']' + for i in $(seq 1 100) ++ ps -o psr,comm,pid ++ grep load ++ egrep 1 -w ++ wc -l + local count=3 + '[' 3 -ne 3 ']' + for i in $(seq 1 100) ++ ps -o psr,comm,pid ++ grep load ++ egrep 1 -w ++ wc -l + local count=3 + '[' 3 -ne 3 ']' + for i in $(seq 1 100) ++ ps -o psr,comm,pid ++ grep load ++ egrep 1 -w ++ wc -l + local count=3 + '[' 3 -ne 3 ']' + for i in $(seq 1 100) ++ ps -o psr,comm,pid ++ grep load ++ egrep 1 -w ++ wc -l + local count=3 + '[' 3 -ne 3 ']' + for i in $(seq 1 100) ++ ps -o psr,comm,pid ++ grep load ++ egrep 1 -w ++ wc -l + local count=3 + '[' 3 -ne 3 ']' + for i in $(seq 1 100) ++ ps -o psr,comm,pid ++ grep load ++ egrep 1 -w ++ wc -l + local count=3 + '[' 3 -ne 3 ']' + for i in $(seq 1 100) ++ ps -o psr,comm,pid ++ grep load ++ egrep 1 -w ++ wc -l + local count=3 + '[' 3 -ne 3 ']' + for i in $(seq 1 100) ++ ps -o psr,comm,pid ++ grep load ++ egrep 1 -w ++ wc -l + local count=3 + '[' 3 -ne 3 ']' + for i in $(seq 1 100) ++ ps -o psr,comm,pid ++ grep load ++ egrep 1 -w ++ wc -l + local count=3 + '[' 3 -ne 3 ']' + for i in $(seq 1 100) ++ ps -o psr,comm,pid ++ grep load ++ egrep 1 -w ++ wc -l + local count=3 + '[' 3 -ne 3 ']' + for i in $(seq 1 100) ++ ps -o psr,comm,pid ++ grep load ++ egrep 1 -w ++ wc -l + local count=3 + '[' 3 -ne 3 ']' + for i in $(seq 1 100) ++ ps -o psr,comm,pid ++ grep load ++ egrep 1 -w ++ wc -l + local count=3 + '[' 3 -ne 3 ']' + for i in $(seq 1 100) ++ ps -o psr,comm,pid ++ grep load ++ egrep 1 -w ++ wc -l + local count=3 + '[' 3 -ne 3 ']' + for i in $(seq 1 100) ++ ps -o psr,comm,pid ++ grep load ++ egrep 1 -w ++ wc -l + local count=3 + '[' 3 -ne 3 ']' + for i in $(seq 1 100) ++ ps -o psr,comm,pid ++ grep load ++ egrep 1 -w ++ wc -l + local count=3 + '[' 3 -ne 3 ']' + for i in $(seq 1 100) ++ ps -o psr,comm,pid ++ grep load ++ egrep 1 -w ++ wc -l + local count=3 + '[' 3 -ne 3 ']' + for i in $(seq 1 100) ++ ps -o psr,comm,pid ++ grep load ++ egrep 1 -w ++ wc -l + local count=3 + '[' 3 -ne 3 ']' + for i in $(seq 1 100) ++ ps -o psr,comm,pid ++ grep load ++ egrep 1 -w ++ wc -l + local count=3 + '[' 3 -ne 3 ']' + for i in $(seq 1 100) ++ ps -o psr,comm,pid ++ grep load ++ egrep 1 -w ++ wc -l + local count=3 + '[' 3 -ne 3 ']' + for i in $(seq 1 100) ++ ps -o psr,comm,pid ++ grep load ++ egrep 1 -w ++ wc -l + local count=3 + '[' 3 -ne 3 ']' + for i in $(seq 1 100) ++ ps -o psr,comm,pid ++ grep load ++ egrep 1 -w ++ wc -l + local count=3 + '[' 3 -ne 3 ']' + for i in $(seq 1 100) ++ ps -o psr,comm,pid ++ grep load ++ egrep 1 -w ++ wc -l + local count=3 + '[' 3 -ne 3 ']' + for i in $(seq 1 100) ++ ps -o psr,comm,pid ++ grep load ++ egrep 1 -w ++ wc -l + local count=3 + '[' 3 -ne 3 ']' + for i in $(seq 1 100) ++ ps -o psr,comm,pid ++ grep load ++ egrep 1 -w ++ wc -l + local count=3 + '[' 3 -ne 3 ']' + for i in $(seq 1 100) ++ ps -o psr,comm,pid ++ grep load ++ egrep 1 -w ++ wc -l + local count=3 + '[' 3 -ne 3 ']' + for i in $(seq 1 100) ++ ps -o psr,comm,pid ++ grep load ++ egrep 1 -w ++ wc -l + local count=3 + '[' 3 -ne 3 ']' + for i in $(seq 1 100) ++ ps -o psr,comm,pid ++ grep load ++ egrep 1 -w ++ wc -l + local count=3 + '[' 3 -ne 3 ']' + for i in $(seq 1 100) ++ ps -o psr,comm,pid ++ grep load ++ egrep 1 -w ++ wc -l + local count=3 + '[' 3 -ne 3 ']' + for i in $(seq 1 100) ++ ps -o psr,comm,pid ++ grep load ++ egrep 1 -w ++ wc -l + local count=3 + '[' 3 -ne 3 ']' + for i in $(seq 1 100) ++ ps -o psr,comm,pid ++ grep load ++ egrep 1 -w ++ wc -l + local count=3 + '[' 3 -ne 3 ']' + for i in $(seq 1 100) ++ ps -o psr,comm,pid ++ grep load ++ egrep 1 -w ++ wc -l + local count=3 + '[' 3 -ne 3 ']' + for i in $(seq 1 100) ++ ps -o psr,comm,pid ++ grep load ++ egrep 1 -w ++ wc -l + local count=3 + '[' 3 -ne 3 ']' + for i in $(seq 1 100) ++ ps -o psr,comm,pid ++ grep load ++ egrep 1 -w ++ wc -l + local count=3 + '[' 3 -ne 3 ']' + for i in $(seq 1 100) ++ ps -o psr,comm,pid ++ grep load ++ wc -l ++ egrep 1 -w + local count=3 + '[' 3 -ne 3 ']' + for i in $(seq 1 100) ++ ps -o psr,comm,pid ++ grep load ++ egrep 1 -w ++ wc -l + local count=3 + '[' 3 -ne 3 ']' + for i in $(seq 1 100) ++ ps -o psr,comm,pid ++ grep load ++ egrep 1 -w ++ wc -l + local count=3 + '[' 3 -ne 3 ']' + for i in $(seq 1 100) ++ ps -o psr,comm,pid ++ grep load ++ egrep 1 -w ++ wc -l + local count=3 + '[' 3 -ne 3 ']' + for i in $(seq 1 100) ++ ps -o psr,comm,pid ++ grep load ++ egrep 1 -w ++ wc -l + local count=3 + '[' 3 -ne 3 ']' + for i in $(seq 1 100) ++ ps -o psr,comm,pid ++ grep load ++ egrep 1 -w ++ wc -l + local count=3 + '[' 3 -ne 3 ']' + for i in $(seq 1 100) ++ ps -o psr,comm,pid ++ grep load ++ egrep 1 -w ++ wc -l + local count=3 + '[' 3 -ne 3 ']' + for i in $(seq 1 100) ++ ps -o psr,comm,pid ++ grep load ++ egrep 1 -w ++ wc -l + local count=3 + '[' 3 -ne 3 ']' + for i in $(seq 1 100) ++ ps -o psr,comm,pid ++ grep load ++ egrep 1 -w ++ wc -l + local count=3 + '[' 3 -ne 3 ']' + for i in $(seq 1 100) ++ ps -o psr,comm,pid ++ egrep 1 -w ++ wc -l ++ grep load + local count=3 + '[' 3 -ne 3 ']' + for i in $(seq 1 100) ++ ps -o psr,comm,pid ++ grep load ++ egrep 1 -w ++ wc -l + local count=3 + '[' 3 -ne 3 ']' + for i in $(seq 1 100) ++ ps -o psr,comm,pid ++ grep load ++ egrep 1 -w ++ wc -l + local count=3 + '[' 3 -ne 3 ']' + for i in $(seq 1 100) ++ ps -o psr,comm,pid ++ grep load ++ egrep 1 -w ++ wc -l + local count=3 + '[' 3 -ne 3 ']' + for i in $(seq 1 100) ++ ps -o psr,comm,pid ++ grep load ++ egrep 1 -w ++ wc -l + local count=3 + '[' 3 -ne 3 ']' + for i in $(seq 1 100) ++ ps -o psr,comm,pid ++ grep load ++ egrep 1 -w ++ wc -l + local count=3 + '[' 3 -ne 3 ']' + '[' 0 -eq 0 ']' + ps -o psr,comm,pid + grep cpu_load 1 cpu_load_not_wh 4170 1 cpu_load_not_wh 4171 1 cpu_load_not_wh 4172 + echo 'TPASS: test success' TPASS: test success + cleanup + killall cpu_load_not_while + sleep 0.1 + rmdir /sys/fs/cgroup/cpuset/cloud /sys/fs/cgroup/cpu/cloud + exit 0 [root@localhost at]# bash -x dyn_affinity_high_load.sh + TEST_CPUSET_PATH=/sys/fs/cgroup/cpuset/cloud + TEST_CPU_PATH=/sys/fs/cgroup/cpu/cloud + ret=0 ++ seq 1 1 + for i in $(seq 1 1) + setup + '[' -d /sys/fs/cgroup/cpuset/cloud ']' + mkdir -p /sys/fs/cgroup/cpuset/cloud /sys/fs/cgroup/cpu/cloud + echo 0 + echo 0-7 + echo 1 + do_test + echo 4121 + echo 4121 + local pid=0 ++ seq 1 30 + for i in $(seq 1 30) + pid=4125 + echo 4125 + echo 4125 + for i in $(seq 1 30) + pid=4126 + echo 4126 + ./cpu_load_not_while + echo 4126 + for i in $(seq 1 30) + pid=4127 + echo 4127 + ./cpu_load_not_while + ./cpu_load_not_while + echo 4127 + for i in $(seq 1 30) + pid=4128 + ./cpu_load_not_while + echo 4128 + echo 4128 + for i in $(seq 1 30) + pid=4129 + echo 4129 + echo 4129 + for i in $(seq 1 30) + ./cpu_load_not_while + pid=4130 + echo 4130 + ./cpu_load_not_while + echo 4130 + for i in $(seq 1 30) + pid=4131 + ./cpu_load_not_while + echo 4131 + echo 4131 + for i in $(seq 1 30) + pid=4132 + echo 4132 + echo 4132 + ./cpu_load_not_while + for i in $(seq 1 30) + pid=4133 + ./cpu_load_not_while + echo 4133 + echo 4133 + for i in $(seq 1 30) + pid=4134 + ./cpu_load_not_while + echo 4134 + echo 4134 + for i in $(seq 1 30) + pid=4135 + ./cpu_load_not_while + echo 4135 + echo 4135 + for i in $(seq 1 30) + pid=4136 + ./cpu_load_not_while + echo 4136 + echo 4136 + for i in $(seq 1 30) + pid=4137 + ./cpu_load_not_while + echo 4137 + echo 4137 + for i in $(seq 1 30) + pid=4138 + echo 4138 + ./cpu_load_not_while + echo 4138 + for i in $(seq 1 30) + pid=4139 + ./cpu_load_not_while + echo 4139 + echo 4139 + for i in $(seq 1 30) + pid=4140 + ./cpu_load_not_while + echo 4140 + echo 4140 + for i in $(seq 1 30) + pid=4141 + echo 4141 + ./cpu_load_not_while + echo 4141 + for i in $(seq 1 30) + pid=4142 + echo 4142 + ./cpu_load_not_while + echo 4142 + for i in $(seq 1 30) + pid=4143 + echo 4143 + ./cpu_load_not_while + echo 4143 + for i in $(seq 1 30) + pid=4144 + ./cpu_load_not_while + echo 4144 + echo 4144 + for i in $(seq 1 30) + pid=4145 + ./cpu_load_not_while + echo 4145 + echo 4145 + for i in $(seq 1 30) + pid=4146 + echo 4146 + echo 4146 + ./cpu_load_not_while + for i in $(seq 1 30) + pid=4147 + echo 4147 + echo 4147 + ./cpu_load_not_while + for i in $(seq 1 30) + pid=4148 + echo 4148 + echo 4148 + ./cpu_load_not_while + for i in $(seq 1 30) + pid=4149 + echo 4149 + echo 4149 + ./cpu_load_not_while + for i in $(seq 1 30) + pid=4150 + echo 4150 + echo 4150 + ./cpu_load_not_while + for i in $(seq 1 30) + pid=4151 + echo 4151 + echo 4151 + ./cpu_load_not_while + for i in $(seq 1 30) + pid=4152 + echo 4152 + ./cpu_load_not_while + echo 4152 + for i in $(seq 1 30) + pid=4153 + ./cpu_load_not_while + echo 4153 + echo 4153 + for i in $(seq 1 30) + pid=4154 + ./cpu_load_not_while + echo 4154 + echo 4154 + echo 4121 + echo 4121 + sleep 0.1 ++ seq 1 100 + for i in $(seq 1 100) ++ ps -o psr,comm,pid ++ grep load ++ egrep 1 -w ++ wc -l + local count=19 + '[' 19 -ne 30 ']' + ps -o psr,comm,pid + grep cpu_load 1 cpu_load_not_wh 4125 6 cpu_load_not_wh 4126 1 cpu_load_not_wh 4127 1 cpu_load_not_wh 4128 1 cpu_load_not_wh 4129 1 cpu_load_not_wh 4130 1 cpu_load_not_wh 4131 1 cpu_load_not_wh 4132 1 cpu_load_not_wh 4133 1 cpu_load_not_wh 4134 7 cpu_load_not_wh 4135 1 cpu_load_not_wh 4136 1 cpu_load_not_wh 4137 4 cpu_load_not_wh 4138 1 cpu_load_not_wh 4139 1 cpu_load_not_wh 4140 1 cpu_load_not_wh 4141 5 cpu_load_not_wh 4142 1 cpu_load_not_wh 4143 1 cpu_load_not_wh 4144 1 cpu_load_not_wh 4145 1 cpu_load_not_wh 4146 1 cpu_load_not_wh 4147 3 cpu_load_not_wh 4148 5 cpu_load_not_wh 4149 1 cpu_load_not_wh 4150 1 cpu_load_not_wh 4151 1 cpu_load_not_wh 4152 5 cpu_load_not_wh 4153 6 cpu_load_not_wh 4154 + echo 'TPASS: test success' TPASS: test success + exit tanghui (2): sched: Add statistics for scheduler dynamic affinity config: enable CONFIG_QOS_SCHED_DYNAMIC_AFFINITY by default arch/arm64/configs/openeuler_defconfig | 1 + arch/x86/configs/openeuler_defconfig | 1 + include/linux/sched.h | 6 ++++++ kernel/sched/debug.c | 4 ++++ kernel/sched/fair.c | 11 +++++++++-- 5 files changed, 21 insertions(+), 2 deletions(-) -- 2.17.1

1 2

[PATCH openEuler-1.0-LTS] bpf: add missing header file include
by Yongqiang Liu 08 Apr '23

08 Apr '23

From: Linus Torvalds <torvalds(a)linux-foundation.org> stable inclusion from stable-v4.19.274 commit c7603df97635954165fb599e64e197efc353979b category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I6TIG1 CVE: NA -------------------------------- commit f3dd0c53370e70c0f9b7e931bbec12916f3bb8cc upstream. Commit 74e19ef0ff80 ("uaccess: Add speculation barrier to copy_from_user()") built fine on x86-64 and arm64, and that's the extent of my local build testing. It turns out those got the <linux/nospec.h> include incidentally through other header files (<linux/kvm_host.h> in particular), but that was not true of other architectures, resulting in build errors kernel/bpf/core.c: In function ‘___bpf_prog_run’: kernel/bpf/core.c:1913:3: error: implicit declaration of function ‘barrier_nospec’ so just make sure to explicitly include the proper <linux/nospec.h> header file to make everybody see it. Fixes: 74e19ef0ff80 ("uaccess: Add speculation barrier to copy_from_user()") Reported-by: kernel test robot <lkp(a)intel.com> Reported-by: Viresh Kumar <viresh.kumar(a)linaro.org> Reported-by: Huacai Chen <chenhuacai(a)loongson.cn> Tested-by: Geert Uytterhoeven <geert(a)linux-m68k.org> Tested-by: Dave Hansen <dave.hansen(a)linux.intel.com> Acked-by: Alexei Starovoitov <alexei.starovoitov(a)gmail.com> Signed-off-by: Linus Torvalds <torvalds(a)linux-foundation.org> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Yongqiang Liu <liuyongqiang13(a)huawei.com> --- kernel/bpf/core.c | 1 + 1 file changed, 1 insertion(+) diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index abf30609e0d9..56a60d483c8d 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -32,6 +32,7 @@ #include <linux/kallsyms.h> #include <linux/rcupdate.h> #include <linux/perf_event.h> +#include <linux/nospec.h> #include <asm/barrier.h> #include <asm/unaligned.h> -- 2.25.1

1 0

[PATCH openEuler-1.0-LTS 00/19] linux-4.19.y inclusion
by Yongqiang Liu 07 Apr '23

07 Apr '23

*** BLURB HERE *** Armin Wolf (1): ACPI: battery: Fix missing NUL-termination with large strings Baokun Li (1): ext4: fail ext4_iget if special inode unallocated Breno Leitao (1): x86/bugs: Reset speculation control settings on init Daniil Tatianin (1): ACPICA: nsrepair: handle cases without a return value correctly Dave Hansen (1): uaccess: Add speculation barrier to copy_from_user() Herbert Xu (2): crypto: seqiv - Handle EBUSY correctly crypto: rsa-pkcs1pad - Use akcipher_request_complete Jann Horn (1): timers: Prevent union confusion from unexpected restart_syscall() Jason A. Donenfeld (1): random: always mix cycle counter in add_latent_entropy() Johan Hovold (3): irqdomain: Fix association race irqdomain: Fix disassociation race irqdomain: Drop bogus fwspec-mapping error handling Nikita Zhandarovich (1): x86/mm: Fix use of uninitialized buffer in sme_enable() Thomas Gleixner (1): alarmtimer: Prevent starvation by small intervals and SIG_IGN Vishal Verma (1): ACPI: NFIT: fix a potential deadlock during NFIT teardown Yang Jihong (2): x86/kprobes: Fix __recover_optprobed_insn check optimizing logic x86/kprobes: Fix arch_check_optimized_kprobe check within optimized_kprobe range Zhen Lei (1): genirq: Fix the return type of kstat_cpu_irqs_sum() Zhihao Cheng (1): ext4: zero i_disksize when initializing the bootloader inode arch/x86/include/asm/msr-index.h | 4 ++++ arch/x86/kernel/cpu/bugs.c | 10 ++++++++- arch/x86/kernel/kprobes/opt.c | 6 +++--- arch/x86/mm/mem_encrypt_identity.c | 3 ++- crypto/rsa-pkcs1pad.c | 34 +++++++++++++----------------- crypto/seqiv.c | 2 +- drivers/acpi/acpica/nsrepair.c | 12 ++++++----- drivers/acpi/battery.c | 2 +- drivers/acpi/nfit/core.c | 2 +- fs/ext4/inode.c | 18 +++++++--------- fs/ext4/ioctl.c | 1 + include/linux/kernel_stat.h | 2 +- include/linux/kprobes.h | 2 ++ include/linux/nospec.h | 4 ++++ include/linux/random.h | 6 +++--- kernel/bpf/core.c | 2 -- kernel/irq/irqdomain.c | 31 +++++++++++++++++---------- kernel/kprobes.c | 6 +++--- kernel/time/alarmtimer.c | 33 +++++++++++++++++++++++++---- kernel/time/hrtimer.c | 2 ++ kernel/time/posix-stubs.c | 2 ++ kernel/time/posix-timers.c | 2 ++ lib/usercopy.c | 7 ++++++ 23 files changed, 127 insertions(+), 66 deletions(-) -- 2.25.1

1 19

[PATCH openEuler-1.0-LTS 01/19] alarmtimer: Prevent starvation by small intervals and SIG_IGN
by Yongqiang Liu 07 Apr '23

07 Apr '23

From: Thomas Gleixner <tglx(a)linutronix.de> stable inclusion from stable-v4.19.274 commit d6a300076d11a6e27b4d4f7fd986ec66ee97a3e1 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I6TIG1 CVE: NA -------------------------------- commit d125d1349abeb46945dc5e98f7824bf688266f13 upstream. syzbot reported a RCU stall which is caused by setting up an alarmtimer with a very small interval and ignoring the signal. The reproducer arms the alarm timer with a relative expiry of 8ns and an interval of 9ns. Not a problem per se, but that's an issue when the signal is ignored because then the timer is immediately rearmed because there is no way to delay that rearming to the signal delivery path. See posix_timer_fn() and commit 58229a189942 ("posix-timers: Prevent softirq starvation by small intervals and SIG_IGN") for details. The reproducer does not set SIG_IGN explicitely, but it sets up the timers signal with SIGCONT. That has the same effect as explicitely setting SIG_IGN for a signal as SIGCONT is ignored if there is no handler set and the task is not ptraced. The log clearly shows that: [pid 5102] --- SIGCONT {si_signo=SIGCONT, si_code=SI_TIMER, si_timerid=0, si_overrun=316014, si_int=0, si_ptr=NULL} --- It works because the tasks are traced and therefore the signal is queued so the tracer can see it, which delays the restart of the timer to the signal delivery path. But then the tracer is killed: [pid 5087] kill(-5102, SIGKILL <unfinished ...> ... ./strace-static-x86_64: Process 5107 detached and after it's gone the stall can be observed: syzkaller login: [ 79.439102][ C0] hrtimer: interrupt took 68471 ns [ 184.460538][ C1] rcu: INFO: rcu_preempt detected stalls on CPUs/tasks: ... [ 184.658237][ C1] rcu: Stack dump where RCU GP kthread last ran: [ 184.664574][ C1] Sending NMI from CPU 1 to CPUs 0: [ 184.669821][ C0] NMI backtrace for cpu 0 [ 184.669831][ C0] CPU: 0 PID: 5108 Comm: syz-executor192 Not tainted 6.2.0-rc6-next-20230203-syzkaller #0 ... [ 184.670036][ C0] Call Trace: [ 184.670041][ C0] <IRQ> [ 184.670045][ C0] alarmtimer_fired+0x327/0x670 posix_timer_fn() prevents that by checking whether the interval for timers which have the signal ignored is smaller than a jiffie and artifically delay it by shifting the next expiry out by a jiffie. That's accurate vs. the overrun accounting, but slightly inaccurate vs. timer_gettimer(2). The comment in that function says what needs to be done and there was a fix available for the regular userspace induced SIG_IGN mechanism, but that did not work due to the implicit ignore for SIGCONT and similar signals. This needs to be worked on, but for now the only available workaround is to do exactly what posix_timer_fn() does: Increase the interval of self-rearming timers, which have their signal ignored, to at least a jiffie. Interestingly this has been fixed before via commit ff86bf0c65f1 ("alarmtimer: Rate limit periodic intervals") already, but that fix got lost in a later rework. Reported-by: syzbot+b9564ba6e8e00694511b(a)syzkaller.appspotmail.com Fixes: f2c45807d399 ("alarmtimer: Switch over to generic set/get/rearm routine") Signed-off-by: Thomas Gleixner <tglx(a)linutronix.de> Acked-by: John Stultz <jstultz(a)google.com> Cc: stable(a)vger.kernel.org Link: https://lore.kernel.org/r/87k00q1no2.ffs@tglx Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Yongqiang Liu <liuyongqiang13(a)huawei.com> --- kernel/time/alarmtimer.c | 33 +++++++++++++++++++++++++++++---- 1 file changed, 29 insertions(+), 4 deletions(-) diff --git a/kernel/time/alarmtimer.c b/kernel/time/alarmtimer.c index 6a2ba39889bd..56af8a97cf2d 100644 --- a/kernel/time/alarmtimer.c +++ b/kernel/time/alarmtimer.c @@ -476,11 +476,35 @@ u64 alarm_forward(struct alarm *alarm, ktime_t now, ktime_t interval) } EXPORT_SYMBOL_GPL(alarm_forward); -u64 alarm_forward_now(struct alarm *alarm, ktime_t interval) +static u64 __alarm_forward_now(struct alarm *alarm, ktime_t interval, bool throttle) { struct alarm_base *base = &alarm_bases[alarm->type]; + ktime_t now = base->gettime(); + + if (IS_ENABLED(CONFIG_HIGH_RES_TIMERS) && throttle) { + /* + * Same issue as with posix_timer_fn(). Timers which are + * periodic but the signal is ignored can starve the system + * with a very small interval. The real fix which was + * promised in the context of posix_timer_fn() never + * materialized, but someone should really work on it. + * + * To prevent DOS fake @now to be 1 jiffie out which keeps + * the overrun accounting correct but creates an + * inconsistency vs. timer_gettime(2). + */ + ktime_t kj = NSEC_PER_SEC / HZ; + + if (interval < kj) + now = ktime_add(now, kj); + } + + return alarm_forward(alarm, now, interval); +} - return alarm_forward(alarm, base->gettime(), interval); +u64 alarm_forward_now(struct alarm *alarm, ktime_t interval) +{ + return __alarm_forward_now(alarm, interval, false); } EXPORT_SYMBOL_GPL(alarm_forward_now); @@ -554,9 +578,10 @@ static enum alarmtimer_restart alarm_handle_timer(struct alarm *alarm, if (posix_timer_event(ptr, si_private) && ptr->it_interval) { /* * Handle ignored signals and rearm the timer. This will go - * away once we handle ignored signals proper. + * away once we handle ignored signals proper. Ensure that + * small intervals cannot starve the system. */ - ptr->it_overrun += alarm_forward_now(alarm, ptr->it_interval); + ptr->it_overrun += __alarm_forward_now(alarm, ptr->it_interval, true); ++ptr->it_requeue_pending; ptr->it_active = 1; result = ALARMTIMER_RESTART; -- 2.25.1

1 18

[PATCH openEuler-1.0-LTS 1/7] Revert "cgroup: Add missing cpus_read_lock() to cgroup_attach_task_all()"
by Yongqiang Liu 07 Apr '23

07 Apr '23

From: Cai Xinchen <caixinchen1(a)huawei.com> hulk inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I6TI3Y CVE: NA -------------------------------- This reverts commit c2d8355618485dd9108ee9077799a227771af307. Signed-off-by: Cai Xinchen <caixinchen1(a)huawei.com> Reviewed-by: Wang Weiyang <wangweiyang2(a)huawei.com> Signed-off-by: Yongqiang Liu <liuyongqiang13(a)huawei.com> --- kernel/cgroup/cgroup-internal.h | 2 -- kernel/cgroup/cgroup-v1.c | 4 ++-- kernel/cgroup/cgroup.c | 4 ++-- 3 files changed, 4 insertions(+), 6 deletions(-) diff --git a/kernel/cgroup/cgroup-internal.h b/kernel/cgroup/cgroup-internal.h index edb45e2f7f54..2e65e4c4d6e7 100644 --- a/kernel/cgroup/cgroup-internal.h +++ b/kernel/cgroup/cgroup-internal.h @@ -226,8 +226,6 @@ int cgroup_migrate(struct task_struct *leader, bool threadgroup, int cgroup_attach_task(struct cgroup *dst_cgrp, struct task_struct *leader, bool threadgroup); -void cgroup_attach_lock(void); -void cgroup_attach_unlock(void); struct task_struct *cgroup_procs_write_start(char *buf, bool threadgroup) __acquires(&cgroup_threadgroup_rwsem); void cgroup_procs_write_finish(struct task_struct *task) diff --git a/kernel/cgroup/cgroup-v1.c b/kernel/cgroup/cgroup-v1.c index 8bd36f2143eb..c4cc6c1ddacd 100644 --- a/kernel/cgroup/cgroup-v1.c +++ b/kernel/cgroup/cgroup-v1.c @@ -55,7 +55,7 @@ int cgroup_attach_task_all(struct task_struct *from, struct task_struct *tsk) int retval = 0; mutex_lock(&cgroup_mutex); - cgroup_attach_lock(); + percpu_down_write(&cgroup_threadgroup_rwsem); for_each_root(root) { struct cgroup *from_cgrp; @@ -70,7 +70,7 @@ int cgroup_attach_task_all(struct task_struct *from, struct task_struct *tsk) if (retval) break; } - cgroup_attach_unlock(); + percpu_up_write(&cgroup_threadgroup_rwsem); mutex_unlock(&cgroup_mutex); return retval; diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index 4a4d8a3f06ab..6487df9a6be0 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -2236,7 +2236,7 @@ EXPORT_SYMBOL_GPL(task_cgroup_path); * write-locking cgroup_threadgroup_rwsem. This allows ->attach() to assume that * CPU hotplug is disabled on entry. */ -void cgroup_attach_lock(void) +static void cgroup_attach_lock(void) { cpus_read_lock(); percpu_down_write(&cgroup_threadgroup_rwsem); @@ -2246,7 +2246,7 @@ void cgroup_attach_lock(void) * cgroup_attach_unlock - Undo cgroup_attach_lock() * @lock_threadgroup: whether to up_write cgroup_threadgroup_rwsem */ -void cgroup_attach_unlock(void) +static void cgroup_attach_unlock(void) { percpu_up_write(&cgroup_threadgroup_rwsem); cpus_read_unlock(); -- 2.25.1

1 6

[PATCH openEuler-22.03-LTS] net/smc: align the connect behaviour with TCP
by Litao Jiao 07 Apr '23

07 Apr '23

mainline inclusion from mainline-v5.19.rc1 commit 3aba103006bcc4a7472b7c9506b3bc065ffb7992 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I6TK1U CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- Connect with O_NONBLOCK will not be completed immediately and returns -EINPROGRESS. It is possible to use selector/poll for completion by selecting the socket for writing. After select indicates writability, a second connect function call will return 0 to indicate connected successfully as TCP does, but smc returns -EISCONN. Use socket state for smc to indicate connect state, which can help smc aligning the connect behaviour with TCP. Signed-off-by: Guangguan Wang <guangguan.wang(a)linux.alibaba.com> Acked-by: Karsten Graul <kgraul(a)linux.ibm.com> Signed-off-by: David S. Miller <davem(a)davemloft.net> Signed-off-by: Litao Jiao <jiaolitao(a)sangfor.com.cn> --- net/smc/af_smc.c | 51 ++++++++++++++++++++++++++++++++++++++++++++---- 1 file changed, 47 insertions(+), 4 deletions(-) diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index 5d7710dd9514..8f73da1ee7b4 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -1097,9 +1097,29 @@ static int smc_connect(struct socket *sock, struct sockaddr *addr, goto out_err; lock_sock(sk); + switch (sock->state) { + default: + rc = -EINVAL; + goto out; + case SS_CONNECTED: + rc = sk->sk_state == SMC_ACTIVE ? -EISCONN : -EINVAL; + goto out; + case SS_CONNECTING: + if (sk->sk_state == SMC_ACTIVE) + goto connected; + break; + case SS_UNCONNECTED: + sock->state = SS_CONNECTING; + break; + } + switch (sk->sk_state) { default: goto out; + case SMC_CLOSED: + rc = sock_error(sk) ? : -ECONNABORTED; + sock->state = SS_UNCONNECTED; + goto out; case SMC_ACTIVE: rc = -EISCONN; goto out; @@ -1118,21 +1138,26 @@ static int smc_connect(struct socket *sock, struct sockaddr *addr, if (rc && rc != -EINPROGRESS) goto out; - if (smc->use_fallback) + if (smc->use_fallback) { + sock->state = rc ? SS_CONNECTING : SS_CONNECTED; goto out; + } sock_hold(&smc->sk); /* sock put in passive closing */ + if (flags & O_NONBLOCK) { if (queue_work(smc_hs_wq, &smc->connect_work)) smc->connect_nonblock = 1; rc = -EINPROGRESS; + goto out; } else { rc = __smc_connect(smc); if (rc < 0) goto out; - else - rc = 0; /* success cases including fallback */ } +connected: + rc = 0; + sock->state = SS_CONNECTED; out: release_sock(sk); out_err: @@ -1234,6 +1259,7 @@ struct sock *smc_accept_dequeue(struct sock *parent, } if (new_sock) { sock_graft(new_sk, new_sock); + new_sock->state = SS_CONNECTED; if (isk->use_fallback) { smc_sk(new_sk)->clcsock->file = new_sock->file; isk->clcsock->file->private_data = isk->clcsock; @@ -1865,7 +1891,7 @@ static int smc_listen(struct socket *sock, int backlog) rc = -EINVAL; if ((sk->sk_state != SMC_INIT && sk->sk_state != SMC_LISTEN) || - smc->connect_nonblock) + smc->connect_nonblock || sock->state != SS_UNCONNECTED) goto out; rc = 0; @@ -2135,6 +2161,17 @@ static int smc_shutdown(struct socket *sock, int how) lock_sock(sk); + if (sock->state == SS_CONNECTING) { + if (sk->sk_state == SMC_ACTIVE) + sock->state = SS_CONNECTED; + else if (sk->sk_state == SMC_PEERCLOSEWAIT1 || + sk->sk_state == SMC_PEERCLOSEWAIT2 || + sk->sk_state == SMC_APPCLOSEWAIT1 || + sk->sk_state == SMC_APPCLOSEWAIT2 || + sk->sk_state == SMC_APPFINCLOSEWAIT) + sock->state = SS_DISCONNECTING; + } + rc = -ENOTCONN; if ((sk->sk_state != SMC_ACTIVE) && (sk->sk_state != SMC_PEERCLOSEWAIT1) && @@ -2148,6 +2185,7 @@ static int smc_shutdown(struct socket *sock, int how) sk->sk_shutdown = smc->clcsock->sk->sk_shutdown; if (sk->sk_shutdown == SHUTDOWN_MASK) { sk->sk_state = SMC_CLOSED; + sk->sk_socket->state = SS_UNCONNECTED; sock_put(sk); } goto out; @@ -2173,6 +2211,10 @@ static int smc_shutdown(struct socket *sock, int how) /* map sock_shutdown_cmd constants to sk_shutdown value range */ sk->sk_shutdown |= how + 1; + if (sk->sk_state == SMC_CLOSED) + sock->state = SS_UNCONNECTED; + else + sock->state = SS_DISCONNECTING; out: release_sock(sk); return rc ? rc : rc1; @@ -2464,6 +2506,7 @@ static int smc_create(struct net *net, struct socket *sock, int protocol, rc = -ENOBUFS; sock->ops = &smc_sock_ops; + sock->state = SS_UNCONNECTED; sk = smc_sock_alloc(net, sock, protocol); if (!sk) goto out; -- 2.18.0.windows.1

1 0

[PATCH openEuler-1.0-LTS 01/13] mm: mem_reliable: Initialize reliable_nr_page when mm_init()
by Yongqiang Liu 07 Apr '23

07 Apr '23

From: Ma Wupeng <mawupeng1(a)huawei.com> hulk inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I6RKHX CVE: NA -------------------------------- After the fork operation, it is erroneous for the child process to have a reliable page size twice that of its parent process. Upon examining the mm_struct structure, it was discovered that reliable_nr_page should be initialized to 0, similar to how RSS is initialized during mm_init(). This particular problem that arises during forking is merely one such example. To resolve this issue, it is recommended to set reliable_nr_page to 0 during the mm_init() operation. Fixes: 094eaabb3fe8 ("proc: Count reliable memory usage of reliable tasks") Signed-off-by: Ma Wupeng <mawupeng1(a)huawei.com> Reviewed-by: Kefeng Wang <wangkefeng.wang(a)huawei.com> Signed-off-by: Yongqiang Liu <liuyongqiang13(a)huawei.com> --- include/linux/mem_reliable.h | 8 ++++++++ kernel/fork.c | 1 + 2 files changed, 9 insertions(+) diff --git a/include/linux/mem_reliable.h b/include/linux/mem_reliable.h index 6d57c36fb676..aa3fe77c8a72 100644 --- a/include/linux/mem_reliable.h +++ b/include/linux/mem_reliable.h @@ -123,6 +123,13 @@ static inline bool mem_reliable_shmem_limit_check(void) shmem_reliable_nr_page; } +static inline void reliable_clear_page_counter(struct mm_struct *mm) +{ + if (!mem_reliable_is_enabled()) + return; + + atomic_long_set(&mm->reliable_nr_page, 0); +} #else #define reliable_enabled 0 #define reliable_allow_fb_enabled() false @@ -171,6 +178,7 @@ static inline void reliable_lru_add_batch(int zid, enum lru_list lru, int val) {} static inline bool mem_reliable_counter_initialized(void) { return false; } +static inline void reliable_clear_page_counter(struct mm_struct *mm) {} #endif #endif diff --git a/kernel/fork.c b/kernel/fork.c index b5453a26655e..c256525d4ce5 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -1007,6 +1007,7 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p, atomic_long_set(&mm->locked_vm, 0); mm->pinned_vm = 0; memset(&mm->rss_stat, 0, sizeof(mm->rss_stat)); + reliable_clear_page_counter(mm); spin_lock_init(&mm->page_table_lock); spin_lock_init(&mm->arg_lock); mm_init_cpumask(mm); -- 2.25.1

1 12

[PATCH openEuler-1.0-LTS 1/5] loop: Add parm check in loop_control_ioctl
by Yongqiang Liu 07 Apr '23

07 Apr '23

From: Zhong Jinghua <zhongjinghua(a)huawei.com> hulk inclusion category: bugfix bugzilla: 188586, https://gitee.com/openeuler/kernel/issues/I6TFPJ CVE: NA ---------------------------------------- We found that in loop_control_ioctl, the kernel panic can be easily caused: 1. syscall(__NR_ioctl, r[1], 0x4c80, 0x80000200000ul); Create a loop device 0x80000200000ul. In fact, in the code, it is used as the first_minor number, and the first_minor number is 0. So the created loop device number is 7:0. 2. syscall(__NR_ioctl, r[2], 0x4c80, 0ul); Create a loop device 0x0ul. Since the 7:0 device has been created in 1, add_disk will fail because the major and first_minor numbers are consistent. 3. syscall(__NR_ioctl, r[5], 0x4c81, 0ul); Delete the device that failed to create, the kernel panics. Panic like below: BUG: KASAN: null-ptr-deref in device_del+0xb3/0x840 drivers/base/core.c:3107 Call Trace: kill_device drivers/base/core.c:3079 [inline] device_del+0xb3/0x840 drivers/base/core.c:3107 del_gendisk+0x463/0x5f0 block/genhd.c:971 loop_remove drivers/block/loop.c:2190 [inline] loop_control_ioctl drivers/block/loop.c:2289 [inline] The stack like below: Create loop device: loop_control_ioctl loop_add add_disk device_add_disk bdi_register bdi_register_va device_create device_create_groups_vargs device_add kfree(dev->p); dev->p = NULL; Remove loop device: loop_control_ioctl loop_remove del_gendisk device_del kill_device if (dev->p->dead) // p is null Fix it by adding a check for parm. Fixes: 770fe30a46a1 ("loop: add management interface for on-demand device allocation") Signed-off-by: Zhong Jinghua <zhongjinghua(a)huawei.com> Reviewed-by: Yu Kuai <yukuai3(a)huawei.com> Reviewed-by: Hou Tao <houtao1(a)huawei.com> Signed-off-by: Yongqiang Liu <liuyongqiang13(a)huawei.com> --- drivers/block/loop.c | 14 +++++++++++++- 1 file changed, 13 insertions(+), 1 deletion(-) diff --git a/drivers/block/loop.c b/drivers/block/loop.c index 108a4ff27bcd..826633aa328c 100644 --- a/drivers/block/loop.c +++ b/drivers/block/loop.c @@ -1972,6 +1972,17 @@ static int loop_add(struct loop_device **l, int i) struct gendisk *disk; int err; + /* + * i << part_shift is actually used as the first_minor. + * So here should avoid i << part_shift overflow. + * And, MKDEV() expect that the max bits of + * first_minor is 20. + */ + if (i > 0 && i > MINORMASK >> part_shift) { + err = -EINVAL; + goto out; + } + err = -ENOMEM; lo = kzalloc(sizeof(*lo), GFP_KERNEL); if (!lo) @@ -1985,7 +1996,8 @@ static int loop_add(struct loop_device **l, int i) if (err == -ENOSPC) err = -EEXIST; } else { - err = idr_alloc(&loop_index_idr, lo, 0, 0, GFP_KERNEL); + err = idr_alloc(&loop_index_idr, lo, 0, + (MINORMASK >> part_shift) + 1, GFP_KERNEL); } if (err < 0) goto out_free_dev; -- 2.25.1

1 4

[PATCH openEuler-1.0-LTS] block/wbt: enable wbt after switching cfq to other schedulers
by Zhang Changzhong 07 Apr '23

07 Apr '23

From: Li Lingfeng <lilingfeng3(a)huawei.com> hulk inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I6LH5K CVE: NA -------------------------------- Commit 80061216078b ("block/wbt: fix negative inflight counter when remove scsi device") move wbt_enable_default() from elv_unregister_queue() to bfq_exit_queue(). As the result of it, wbt can't be enabled when we switch cfq to other schedulers. Fixes: 80061216078b ("block/wbt: fix negative inflight counter when remove scsi device") Signed-off-by: Li Lingfeng <lilingfeng3(a)huawei.com> Reviewed-by: Yu Kuai <yukuai3(a)huawei.com> Reviewed-by: Hou Tao <houtao1(a)huawei.com> Signed-off-by: Zhang Changzhong <zhangchangzhong(a)huawei.com> --- block/cfq-iosched.c | 1 + 1 file changed, 1 insertion(+) diff --git a/block/cfq-iosched.c b/block/cfq-iosched.c index 88bae55..130854a 100644 --- a/block/cfq-iosched.c +++ b/block/cfq-iosched.c @@ -4563,6 +4563,7 @@ static void cfq_exit_queue(struct elevator_queue *e) kfree(cfqd->root_group); #endif kfree(cfqd); + wbt_enable_default(q); } static int cfq_init_queue(struct request_queue *q, struct elevator_type *e) -- 2.9.5

1 0

[PATCH openEuler-1.0-LTS] Fix double fget() in vhost_net_set_backend()
by Yongqiang Liu 06 Apr '23

06 Apr '23

From: Al Viro <viro(a)zeniv.linux.org.uk> stable inclusion from stable-v4.19.245 commit 6ca70982c646cc32e458150ee7f2530a24369b8c category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I6T1EY CVE: CVE-2023-1838 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- commit fb4554c2232e44d595920f4d5c66cf8f7d13f9bc upstream. Descriptor table is a shared resource; two fget() on the same descriptor may return different struct file references. get_tap_ptr_ring() is called after we'd found (and pinned) the socket we'll be using and it tries to find the private tun/tap data structures associated with it. Redoing the lookup by the same file descriptor we'd used to get the socket is racy - we need to same struct file. Thanks to Jason for spotting a braino in the original variant of patch - I'd missed the use of fd == -1 for disabling backend, and in that case we can end up with sock == NULL and sock != oldsock. Cc: stable(a)kernel.org Acked-by: Michael S. Tsirkin <mst(a)redhat.com> Signed-off-by: Jason Wang <jasowang(a)redhat.com> Signed-off-by: Al Viro <viro(a)zeniv.linux.org.uk> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Zhengchao Shao <shaozhengchao(a)huawei.com> Reviewed-by: Yue Haibing <yuehaibing(a)huawei.com> Reviewed-by: Xiu Jianfeng <xiujianfeng(a)huawei.com> Signed-off-by: Yongqiang Liu <liuyongqiang13(a)huawei.com> --- drivers/vhost/net.c | 15 +++++++-------- 1 file changed, 7 insertions(+), 8 deletions(-) diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c index 1d99f5c443ee..4b9151474a24 100644 --- a/drivers/vhost/net.c +++ b/drivers/vhost/net.c @@ -1211,13 +1211,9 @@ static struct socket *get_raw_socket(int fd) return ERR_PTR(r); } -static struct ptr_ring *get_tap_ptr_ring(int fd) +static struct ptr_ring *get_tap_ptr_ring(struct file *file) { struct ptr_ring *ring; - struct file *file = fget(fd); - - if (!file) - return NULL; ring = tun_get_tx_ring(file); if (!IS_ERR(ring)) goto out; @@ -1226,7 +1222,6 @@ static struct ptr_ring *get_tap_ptr_ring(int fd) goto out; ring = NULL; out: - fput(file); return ring; } @@ -1313,8 +1308,12 @@ static long vhost_net_set_backend(struct vhost_net *n, unsigned index, int fd) r = vhost_net_enable_vq(n, vq); if (r) goto err_used; - if (index == VHOST_NET_VQ_RX) - nvq->rx_ring = get_tap_ptr_ring(fd); + if (index == VHOST_NET_VQ_RX) { + if (sock) + nvq->rx_ring = get_tap_ptr_ring(sock->file); + else + nvq->rx_ring = NULL; + } oldubufs = nvq->ubufs; nvq->ubufs = ubufs; -- 2.25.1

1 0

[PATCH openEuler-1.0-LTS 1/4] btrfs: fix race between quota disable and quota assign ioctls
by Yongqiang Liu 06 Apr '23

06 Apr '23

From: Filipe Manana <fdmanana(a)suse.com> mainline inclusion from mainline-v6.2-rc8 commit 2f1a6be12ab6c8470d5776e68644726c94257c54 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I6PQCT CVE: CVE-2023-1611 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- The quota assign ioctl can currently run in parallel with a quota disable ioctl call. The assign ioctl uses the quota root, while the disable ioctl frees that root, and therefore we can have a use-after-free triggered in the assign ioctl, leading to a trace like the following when KASAN is enabled: [672.723][T736] BUG: KASAN: slab-use-after-free in btrfs_search_slot+0x2962/0x2db0 [672.723][T736] Read of size 8 at addr ffff888022ec0208 by task btrfs_search_sl/27736 [672.724][T736] [672.725][T736] CPU: 1 PID: 27736 Comm: btrfs_search_sl Not tainted 6.3.0-rc3 #37 [672.723][T736] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.15.0-1 04/01/2014 [672.727][T736] Call Trace: [672.728][T736] <TASK> [672.728][T736] dump_stack_lvl+0xd9/0x150 [672.725][T736] print_report+0xc1/0x5e0 [672.720][T736] ? __virt_addr_valid+0x61/0x2e0 [672.727][T736] ? __phys_addr+0xc9/0x150 [672.725][T736] ? btrfs_search_slot+0x2962/0x2db0 [672.722][T736] kasan_report+0xc0/0xf0 [672.729][T736] ? btrfs_search_slot+0x2962/0x2db0 [672.724][T736] btrfs_search_slot+0x2962/0x2db0 [672.723][T736] ? fs_reclaim_acquire+0xba/0x160 [672.722][T736] ? split_leaf+0x13d0/0x13d0 [672.726][T736] ? rcu_is_watching+0x12/0xb0 [672.723][T736] ? kmem_cache_alloc+0x338/0x3c0 [672.722][T736] update_qgroup_status_item+0xf7/0x320 [672.724][T736] ? add_qgroup_rb+0x3d0/0x3d0 [672.739][T736] ? do_raw_spin_lock+0x12d/0x2b0 [672.730][T736] ? spin_bug+0x1d0/0x1d0 [672.737][T736] btrfs_run_qgroups+0x5de/0x840 [672.730][T736] ? btrfs_qgroup_rescan_worker+0xa70/0xa70 [672.738][T736] ? __del_qgroup_relation+0x4ba/0xe00 [672.738][T736] btrfs_ioctl+0x3d58/0x5d80 [672.735][T736] ? tomoyo_path_number_perm+0x16a/0x550 [672.737][T736] ? tomoyo_execute_permission+0x4a0/0x4a0 [672.731][T736] ? btrfs_ioctl_get_supported_features+0x50/0x50 [672.737][T736] ? __sanitizer_cov_trace_switch+0x54/0x90 [672.734][T736] ? do_vfs_ioctl+0x132/0x1660 [672.730][T736] ? vfs_fileattr_set+0xc40/0xc40 [672.730][T736] ? _raw_spin_unlock_irq+0x2e/0x50 [672.732][T736] ? sigprocmask+0xf2/0x340 [672.737][T736] ? __fget_files+0x26a/0x480 [672.732][T736] ? bpf_lsm_file_ioctl+0x9/0x10 [672.738][T736] ? btrfs_ioctl_get_supported_features+0x50/0x50 [672.736][T736] __x64_sys_ioctl+0x198/0x210 [672.736][T736] do_syscall_64+0x39/0xb0 [672.731][T736] entry_SYSCALL_64_after_hwframe+0x63/0xcd [672.739][T736] RIP: 0033:0x4556ad [672.742][T736] </TASK> [672.743][T736] [672.748][T736] Allocated by task 27677: [672.743][T736] kasan_save_stack+0x22/0x40 [672.741][T736] kasan_set_track+0x25/0x30 [672.741][T736] __kasan_kmalloc+0xa4/0xb0 [672.749][T736] btrfs_alloc_root+0x48/0x90 [672.746][T736] btrfs_create_tree+0x146/0xa20 [672.744][T736] btrfs_quota_enable+0x461/0x1d20 [672.743][T736] btrfs_ioctl+0x4a1c/0x5d80 [672.747][T736] __x64_sys_ioctl+0x198/0x210 [672.749][T736] do_syscall_64+0x39/0xb0 [672.744][T736] entry_SYSCALL_64_after_hwframe+0x63/0xcd [672.756][T736] [672.757][T736] Freed by task 27677: [672.759][T736] kasan_save_stack+0x22/0x40 [672.759][T736] kasan_set_track+0x25/0x30 [672.756][T736] kasan_save_free_info+0x2e/0x50 [672.751][T736] ____kasan_slab_free+0x162/0x1c0 [672.758][T736] slab_free_freelist_hook+0x89/0x1c0 [672.752][T736] __kmem_cache_free+0xaf/0x2e0 [672.752][T736] btrfs_put_root+0x1ff/0x2b0 [672.759][T736] btrfs_quota_disable+0x80a/0xbc0 [672.752][T736] btrfs_ioctl+0x3e5f/0x5d80 [672.756][T736] __x64_sys_ioctl+0x198/0x210 [672.753][T736] do_syscall_64+0x39/0xb0 [672.765][T736] entry_SYSCALL_64_after_hwframe+0x63/0xcd [672.769][T736] [672.768][T736] The buggy address belongs to the object at ffff888022ec0000 [672.768][T736] which belongs to the cache kmalloc-4k of size 4096 [672.769][T736] The buggy address is located 520 bytes inside of [672.769][T736] freed 4096-byte region [ffff888022ec0000, ffff888022ec1000) [672.760][T736] [672.764][T736] The buggy address belongs to the physical page: [672.761][T736] page:ffffea00008bb000 refcount:1 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x22ec0 [672.766][T736] head:ffffea00008bb000 order:3 entire_mapcount:0 nr_pages_mapped:0 pincount:0 [672.779][T736] flags: 0xfff00000010200(slab|head|node=0|zone=1|lastcpupid=0x7ff) [672.770][T736] raw: 00fff00000010200 ffff888012842140 ffffea000054ba00 dead000000000002 [672.770][T736] raw: 0000000000000000 0000000000040004 00000001ffffffff 0000000000000000 [672.771][T736] page dumped because: kasan: bad access detected [672.778][T736] page_owner tracks the page as allocated [672.777][T736] page last allocated via order 3, migratetype Unmovable, gfp_mask 0xd2040(__GFP_IO|__GFP_NOWARN|__GFP_NORETRY|__GFP_COMP|__GFP_NOMEMALLOC), pid 88 [672.779][T736] get_page_from_freelist+0x119c/0x2d50 [672.779][T736] __alloc_pages+0x1cb/0x4a0 [672.776][T736] alloc_pages+0x1aa/0x270 [672.773][T736] allocate_slab+0x260/0x390 [672.771][T736] ___slab_alloc+0xa9a/0x13e0 [672.778][T736] __slab_alloc.constprop.0+0x56/0xb0 [672.771][T736] __kmem_cache_alloc_node+0x136/0x320 [672.789][T736] __kmalloc+0x4e/0x1a0 [672.783][T736] tomoyo_realpath_from_path+0xc3/0x600 [672.781][T736] tomoyo_path_perm+0x22f/0x420 [672.782][T736] tomoyo_path_unlink+0x92/0xd0 [672.780][T736] security_path_unlink+0xdb/0x150 [672.788][T736] do_unlinkat+0x377/0x680 [672.788][T736] __x64_sys_unlink+0xca/0x110 [672.789][T736] do_syscall_64+0x39/0xb0 [672.783][T736] entry_SYSCALL_64_after_hwframe+0x63/0xcd [672.784][T736] page last free stack trace: [672.787][T736] free_pcp_prepare+0x4e5/0x920 [672.787][T736] free_unref_page+0x1d/0x4e0 [672.784][T736] __unfreeze_partials+0x17c/0x1a0 [672.797][T736] qlist_free_all+0x6a/0x180 [672.796][T736] kasan_quarantine_reduce+0x189/0x1d0 [672.797][T736] __kasan_slab_alloc+0x64/0x90 [672.793][T736] kmem_cache_alloc+0x17c/0x3c0 [672.799][T736] getname_flags.part.0+0x50/0x4e0 [672.799][T736] getname_flags+0x9e/0xe0 [672.792][T736] vfs_fstatat+0x77/0xb0 [672.791][T736] __do_sys_newlstat+0x84/0x100 [672.798][T736] do_syscall_64+0x39/0xb0 [672.796][T736] entry_SYSCALL_64_after_hwframe+0x63/0xcd [672.790][T736] [672.791][T736] Memory state around the buggy address: [672.799][T736] ffff888022ec0100: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [672.805][T736] ffff888022ec0180: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [672.802][T736] >ffff888022ec0200: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [672.809][T736] ^ [672.809][T736] ffff888022ec0280: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb [672.809][T736] ffff888022ec0300: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb Fix this by having the qgroup assign ioctl take the qgroup ioctl mutex before calling btrfs_run_qgroups(), which is what all qgroup ioctls should call. Reported-by: butt3rflyh4ck <butterflyhuangxx(a)gmail.com> Link: https://lore.kernel.org/linux-btrfs/CAFcO6XN3VD8ogmHwqRk4kbiwtpUSNySu2VAxN8… CC: stable(a)vger.kernel.org # 5.10+ Reviewed-by: Qu Wenruo <wqu(a)suse.com> Signed-off-by: Filipe Manana <fdmanana(a)suse.com> Reviewed-by: David Sterba <dsterba(a)suse.com> Signed-off-by: David Sterba <dsterba(a)suse.com> Conflicts: fs/btrfs/qgroup.c Signed-off-by: Long Li <leo.lilong(a)huawei.com> Reviewed-by: Zhang Yi <yi.zhang(a)huawei.com> Reviewed-by: Wang Weiyang <wangweiyang2(a)huawei.com> Signed-off-by: Yongqiang Liu <liuyongqiang13(a)huawei.com> --- fs/btrfs/ioctl.c | 2 ++ fs/btrfs/qgroup.c | 11 ++++++++++- 2 files changed, 12 insertions(+), 1 deletion(-) diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c index a5ae02bf3652..00424d3f3464 100644 --- a/fs/btrfs/ioctl.c +++ b/fs/btrfs/ioctl.c @@ -5240,7 +5240,9 @@ static long btrfs_ioctl_qgroup_assign(struct file *file, void __user *arg) } /* update qgroup status and info */ + mutex_lock(&fs_info->qgroup_ioctl_lock); err = btrfs_run_qgroups(trans); + mutex_unlock(&fs_info->qgroup_ioctl_lock); if (err < 0) btrfs_handle_fs_error(fs_info, err, "failed to update qgroup status and info"); diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index 7916f711daf5..8e58c58f73a3 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -2196,7 +2196,8 @@ int btrfs_qgroup_account_extents(struct btrfs_trans_handle *trans) } /* - * called from commit_transaction. Writes all changed qgroups to disk. + * Writes all changed qgroups to disk. + * Called by the transaction commit path and the qgroup assign ioctl. */ int btrfs_run_qgroups(struct btrfs_trans_handle *trans) { @@ -2204,6 +2205,14 @@ int btrfs_run_qgroups(struct btrfs_trans_handle *trans) struct btrfs_root *quota_root = fs_info->quota_root; int ret = 0; + /* + * In case we are called from the qgroup assign ioctl, assert that we + * are holding the qgroup_ioctl_lock, otherwise we can race with a quota + * disable operation (ioctl) and access a freed quota root. + */ + if (trans->transaction->state != TRANS_STATE_COMMIT_DOING) + lockdep_assert_held(&fs_info->qgroup_ioctl_lock); + if (!quota_root) return ret; -- 2.25.1

1 3

Kernel sig 4.7 14:00-15:30 例会议题情况//答复: openEuler Kernel SIG双周例会
by liaotao (C) 06 Apr '23

06 Apr '23

当前例会议题：议题一：进展update --- 张伽琳 & 郑增凯议题二：openEuler-22.03-LTS-SP2需求评审 ---张伽琳欢迎大家继续申报~ -----原始约会----- 发件人: openEuler conference <public(a)openeuler.org> 发送时间: 2023年4月7日 9:30 收件人: dev@openeuler.org,kernel-discuss@openeuler.org,kernel@openeuler.org 主题: openEuler Kernel SIG双周例会时间: 2023年4月7日星期五 14:00-15:30(UTC+08:00) 北京，重庆，香港特别行政区，乌鲁木齐。地点: 您好！ Kernel SIG 邀请您参加 2023-04-07 14:00 召开的Zoom会议(自动录制) 会议主题：openEuler Kernel SIG双周例会会议内容： 1.进展update 2.议题征集中欢迎大家积极申报议题（新增议题可以直接回复邮件，或录入会议看板）会议链接：https://us06web.zoom.us/j/88353599877?pwd=aFZtMjJwUHl1UmNTZFV4eUJQM2xVdz09 会议纪要：https://etherpad.openeuler.org/p/Kernel-meetings 温馨提醒：建议接入会议后修改参会人的姓名，也可以使用您在gitee.com的ID 更多资讯尽在：https://openeuler.org/zh/ Hello! openEuler Kernel SIG invites you to attend the Zoom conference(auto recording) will be held at 2023-04-07 14:00, The subject of the conference is openEuler Kernel SIG双周例会, Summary: 1.进展update 2.议题征集中欢迎大家积极申报议题（新增议题可以直接回复邮件，或录入会议看板） You can join the meeting at https://us06web.zoom.us/j/88353599877?pwd=aFZtMjJwUHl1UmNTZFV4eUJQM2xVdz09. Add topics at https://etherpad.openeuler.org/p/Kernel-meetings. Note: You are advised to change the participant name after joining the conference or use your ID at gitee.com. More information: https://openeuler.org/en/

1 0

[PATCH openEuler-1.0-LTS 1/4] ext4: fix race between writepages and remount
by Yongqiang Liu 04 Apr '23

04 Apr '23

From: Baokun Li <libaokun1(a)huawei.com> hulk inclusion category: bugfix bugzilla: 188500, https://gitee.com/openeuler/kernel/issues/I6RJ0V CVE: NA -------------------------------- We got a WARNING in ext4_add_complete_io: ================================================================== WARNING: at fs/ext4/page-io.c:231 ext4_put_io_end_defer+0x182/0x250 CPU: 10 PID: 77 Comm: ksoftirqd/10 Tainted: 6.3.0-rc2 #85 RIP: 0010:ext4_put_io_end_defer+0x182/0x250 [ext4] [...] Call Trace: <TASK> ext4_end_bio+0xa8/0x240 [ext4] bio_endio+0x195/0x310 blk_update_request+0x184/0x770 scsi_end_request+0x2f/0x240 scsi_io_completion+0x75/0x450 scsi_finish_command+0xef/0x160 scsi_complete+0xa3/0x180 blk_complete_reqs+0x60/0x80 blk_done_softirq+0x25/0x40 __do_softirq+0x119/0x4c8 run_ksoftirqd+0x42/0x70 smpboot_thread_fn+0x136/0x3c0 kthread+0x140/0x1a0 ret_from_fork+0x2c/0x50 ================================================================== Above issue may happen as follows: cpu1 cpu2 ----------------------------|---------------------------- mount -o dioread_lock ext4_writepages ext4_do_writepages *if (ext4_should_dioread_nolock(inode))* // rsv_blocks is not assigned here mount -o remount,dioread_nolock ext4_journal_start_with_reserve __ext4_journal_start __ext4_journal_start_sb jbd2__journal_start *if (rsv_blocks)* // h_rsv_handle is not initialized here mpage_map_and_submit_extent mpage_map_one_extent dioread_nolock = ext4_should_dioread_nolock(inode) if (dioread_nolock && (map->m_flags & EXT4_MAP_UNWRITTEN)) mpd->io_submit.io_end->handle = handle->h_rsv_handle ext4_set_io_unwritten_flag io_end->flag |= EXT4_IO_END_UNWRITTEN // now io_end->handle is NULL but has EXT4_IO_END_UNWRITTEN flag scsi_finish_command scsi_io_completion scsi_io_completion_action scsi_end_request blk_update_request req_bio_endio bio_endio bio->bi_end_io > ext4_end_bio ext4_put_io_end_defer ext4_add_complete_io // trigger WARN_ON(!io_end->handle && sbi->s_journal); The immediate cause of this problem is that ext4_should_dioread_nolock() function returns inconsistent values in the ext4_do_writepages() and mpage_map_one_extent(). There are four conditions in this function that can be changed at mount time to cause this problem. These four conditions can be divided into two categories: (1) journal_data and EXT4_EXTENTS_FL, which can be changed by ioctl (2) DELALLOC and DIOREAD_NOLOCK, which can be changed by remount The two in the first category have been fixed by commit c8585c6fcaf2 ("ext4: fix races between changing inode journal mode and ext4_writepages") and commit cb85f4d23f79 ("ext4: fix race between writepages and enabling EXT4_EXTENTS_FL") respectively. Two cases in the other category have not yet been fixed, and the above issue is caused by this situation. We refer to the fix for the first category, when applying options during remount, we grab s_writepages_rwsem to avoid racing with writepages ops to trigger this problem. Fixes: 6b523df4fb5a ("ext4: use transaction reservation for extent conversion in ext4_end_io") Cc: stable(a)vger.kernel.org Signed-off-by: Baokun Li <libaokun1(a)huawei.com> Reviewed-by: Zhang Yi <yi.zhang(a)huawei.com> Reviewed-by: Yang Erkun <yangerkun(a)huawei.com> Signed-off-by: Yongqiang Liu <liuyongqiang13(a)huawei.com> --- fs/ext4/ext4.h | 3 ++- fs/ext4/super.c | 13 +++++++++++++ 2 files changed, 15 insertions(+), 1 deletion(-) diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 4c88e75180a2..6df919b154b4 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -1530,7 +1530,8 @@ struct ext4_sb_info { /* * Barrier between writepages ops and changing any inode's JOURNAL_DATA - * or EXTENTS flag. + * or EXTENTS flag or between writepages ops and changing DIOREAD_NOLOCK + * mount option on remount. */ struct percpu_rw_semaphore s_writepages_rwsem; struct dax_device *s_daxdev; diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 8029a6f6471c..df07222f1cc5 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -5605,10 +5605,20 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) vfs_flags = SB_LAZYTIME | SB_I_VERSION; sb->s_flags = (sb->s_flags & ~vfs_flags) | (*flags & vfs_flags); + /* + * Changing the DIOREAD_NOLOCK mount option may cause two calls to + * ext4_should_dioread_nolock() to return inconsistent values, + * triggering WARN_ON in ext4_add_complete_io(). we grab here + * s_writepages_rwsem to avoid race between writepages ops and + * remount. + */ + percpu_down_write(&sbi->s_writepages_rwsem); if (!parse_options(data, sb, NULL, &journal_ioprio, 1)) { err = -EINVAL; + percpu_up_write(&sbi->s_writepages_rwsem); goto restore_opts; } + percpu_up_write(&sbi->s_writepages_rwsem); if ((old_opts.s_mount_opt & EXT4_MOUNT_JOURNAL_CHECKSUM) ^ test_opt(sb, JOURNAL_CHECKSUM)) { @@ -5833,6 +5843,7 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) return 0; restore_opts: + percpu_down_write(&sbi->s_writepages_rwsem); sb->s_flags = old_sb_flags; sbi->s_mount_opt = old_opts.s_mount_opt; sbi->s_mount_opt2 = old_opts.s_mount_opt2; @@ -5841,6 +5852,8 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) sbi->s_commit_interval = old_opts.s_commit_interval; sbi->s_min_batch_time = old_opts.s_min_batch_time; sbi->s_max_batch_time = old_opts.s_max_batch_time; + percpu_up_write(&sbi->s_writepages_rwsem); + if (!test_opt(sb, BLOCK_VALIDITY) && sbi->system_blks) ext4_release_system_zone(sb); #ifdef CONFIG_QUOTA -- 2.25.1

1 6

[PATCH openEuler-5.10-LTS 01/15] scsi: scsi_dh_alua: fix memleak for 'qdata' in alua_activate()
by Jialin Zhang 04 Apr '23

04 Apr '23

From: Yu Kuai <yukuai3(a)huawei.com> hulk inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I6NBAZ CVE: NA -------------------------------- If alua_rtpg_queue() failed from alua_activate(), then 'qdata' is not freed, which will cause following memleak: unreferenced object 0xffff88810b2c6980 (size 32): comm "kworker/u16:2", pid 635322, jiffies 4355801099 (age 1216426.076s) hex dump (first 32 bytes): 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ 40 39 24 c1 ff ff ff ff 00 f8 ea 0a 81 88 ff ff @9$............. backtrace: [<0000000098f3a26d>] alua_activate+0xb0/0x320 [<000000003b529641>] scsi_dh_activate+0xb2/0x140 [<000000007b296db3>] activate_path_work+0xc6/0xe0 [dm_multipath] [<000000007adc9ace>] process_one_work+0x3c5/0x730 [<00000000c457a985>] worker_thread+0x93/0x650 [<00000000cb80e628>] kthread+0x1ba/0x210 [<00000000a1e61077>] ret_from_fork+0x22/0x30 Fix the problem by freeing 'qdata' in error path. Fixes: 625fe857e4fa ("scsi: scsi_dh_alua: Check scsi_device_get() return value") Signed-off-by: Yu Kuai <yukuai3(a)huawei.com> Reviewed-by: Hou Tao <houtao1(a)huawei.com> Signed-off-by: Jialin Zhang <zhangjialin11(a)huawei.com> --- drivers/scsi/device_handler/scsi_dh_alua.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/scsi/device_handler/scsi_dh_alua.c b/drivers/scsi/device_handler/scsi_dh_alua.c index fe8a5e5c0df8..bf0b3178f84d 100644 --- a/drivers/scsi/device_handler/scsi_dh_alua.c +++ b/drivers/scsi/device_handler/scsi_dh_alua.c @@ -1036,10 +1036,12 @@ static int alua_activate(struct scsi_device *sdev, rcu_read_unlock(); mutex_unlock(&h->init_mutex); - if (alua_rtpg_queue(pg, sdev, qdata, true)) + if (alua_rtpg_queue(pg, sdev, qdata, true)) { fn = NULL; - else + } else { + kfree(qdata); err = SCSI_DH_DEV_OFFLINED; + } kref_put(&pg->kref, release_port_group); out: if (fn) -- 2.25.1

1 14

[PATCH openEuler-5.10-LTS-SP1 01/16] scsi: scsi_dh_alua: fix memleak for 'qdata' in alua_activate()
by Jialin Zhang 04 Apr '23

04 Apr '23

From: Yu Kuai <yukuai3(a)huawei.com> hulk inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I6NBAZ CVE: NA -------------------------------- If alua_rtpg_queue() failed from alua_activate(), then 'qdata' is not freed, which will cause following memleak: unreferenced object 0xffff88810b2c6980 (size 32): comm "kworker/u16:2", pid 635322, jiffies 4355801099 (age 1216426.076s) hex dump (first 32 bytes): 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ 40 39 24 c1 ff ff ff ff 00 f8 ea 0a 81 88 ff ff @9$............. backtrace: [<0000000098f3a26d>] alua_activate+0xb0/0x320 [<000000003b529641>] scsi_dh_activate+0xb2/0x140 [<000000007b296db3>] activate_path_work+0xc6/0xe0 [dm_multipath] [<000000007adc9ace>] process_one_work+0x3c5/0x730 [<00000000c457a985>] worker_thread+0x93/0x650 [<00000000cb80e628>] kthread+0x1ba/0x210 [<00000000a1e61077>] ret_from_fork+0x22/0x30 Fix the problem by freeing 'qdata' in error path. Fixes: 625fe857e4fa ("scsi: scsi_dh_alua: Check scsi_device_get() return value") Signed-off-by: Yu Kuai <yukuai3(a)huawei.com> Reviewed-by: Hou Tao <houtao1(a)huawei.com> Signed-off-by: Jialin Zhang <zhangjialin11(a)huawei.com> --- drivers/scsi/device_handler/scsi_dh_alua.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/drivers/scsi/device_handler/scsi_dh_alua.c b/drivers/scsi/device_handler/scsi_dh_alua.c index fe8a5e5c0df8..bf0b3178f84d 100644 --- a/drivers/scsi/device_handler/scsi_dh_alua.c +++ b/drivers/scsi/device_handler/scsi_dh_alua.c @@ -1036,10 +1036,12 @@ static int alua_activate(struct scsi_device *sdev, rcu_read_unlock(); mutex_unlock(&h->init_mutex); - if (alua_rtpg_queue(pg, sdev, qdata, true)) + if (alua_rtpg_queue(pg, sdev, qdata, true)) { fn = NULL; - else + } else { + kfree(qdata); err = SCSI_DH_DEV_OFFLINED; + } kref_put(&pg->kref, release_port_group); out: if (fn) -- 2.25.1

1 15

openEuler Kernel SIG双周例会
by openEuler conference 04 Apr '23

04 Apr '23

您好！ Kernel SIG 邀请您参加 2023-04-07 14:00 召开的Zoom会议(自动录制) 会议主题：openEuler Kernel SIG双周例会会议内容： 1.进展update 2.议题征集中欢迎大家积极申报议题（新增议题可以直接回复邮件，或录入会议看板）会议链接：https://us06web.zoom.us/j/88353599877?pwd=aFZtMjJwUHl1UmNTZFV4eUJQM2xVdz09 会议纪要：https://etherpad.openeuler.org/p/Kernel-meetings 温馨提醒：建议接入会议后修改参会人的姓名，也可以使用您在gitee.com的ID 更多资讯尽在：https://openeuler.org/zh/ Hello! openEuler Kernel SIG invites you to attend the Zoom conference(auto recording) will be held at 2023-04-07 14:00, The subject of the conference is openEuler Kernel SIG双周例会, Summary: 1.进展update 2.议题征集中欢迎大家积极申报议题（新增议题可以直接回复邮件，或录入会议看板） You can join the meeting at https://us06web.zoom.us/j/88353599877?pwd=aFZtMjJwUHl1UmNTZFV4eUJQM2xVdz09. Add topics at https://etherpad.openeuler.org/p/Kernel-meetings. Note: You are advised to change the participant name after joining the conference or use your ID at gitee.com. More information: https://openeuler.org/en/

1 0

[PATCH openEuler-1.0-LTS 1/4] ext4: fix race between writepages and remount
by Yongqiang Liu 03 Apr '23

03 Apr '23

From: Baokun Li <libaokun1(a)huawei.com> hulk inclusion category: bugfix bugzilla: 188500, https://gitee.com/openeuler/kernel/issues/I6RJ0V CVE: NA -------------------------------- We got a WARNING in ext4_add_complete_io: ================================================================== WARNING: at fs/ext4/page-io.c:231 ext4_put_io_end_defer+0x182/0x250 CPU: 10 PID: 77 Comm: ksoftirqd/10 Tainted: 6.3.0-rc2 #85 RIP: 0010:ext4_put_io_end_defer+0x182/0x250 [ext4] [...] Call Trace: <TASK> ext4_end_bio+0xa8/0x240 [ext4] bio_endio+0x195/0x310 blk_update_request+0x184/0x770 scsi_end_request+0x2f/0x240 scsi_io_completion+0x75/0x450 scsi_finish_command+0xef/0x160 scsi_complete+0xa3/0x180 blk_complete_reqs+0x60/0x80 blk_done_softirq+0x25/0x40 __do_softirq+0x119/0x4c8 run_ksoftirqd+0x42/0x70 smpboot_thread_fn+0x136/0x3c0 kthread+0x140/0x1a0 ret_from_fork+0x2c/0x50 ================================================================== Above issue may happen as follows: cpu1 cpu2 ----------------------------|---------------------------- mount -o dioread_lock ext4_writepages ext4_do_writepages *if (ext4_should_dioread_nolock(inode))* // rsv_blocks is not assigned here mount -o remount,dioread_nolock ext4_journal_start_with_reserve __ext4_journal_start __ext4_journal_start_sb jbd2__journal_start *if (rsv_blocks)* // h_rsv_handle is not initialized here mpage_map_and_submit_extent mpage_map_one_extent dioread_nolock = ext4_should_dioread_nolock(inode) if (dioread_nolock && (map->m_flags & EXT4_MAP_UNWRITTEN)) mpd->io_submit.io_end->handle = handle->h_rsv_handle ext4_set_io_unwritten_flag io_end->flag |= EXT4_IO_END_UNWRITTEN // now io_end->handle is NULL but has EXT4_IO_END_UNWRITTEN flag scsi_finish_command scsi_io_completion scsi_io_completion_action scsi_end_request blk_update_request req_bio_endio bio_endio bio->bi_end_io > ext4_end_bio ext4_put_io_end_defer ext4_add_complete_io // trigger WARN_ON(!io_end->handle && sbi->s_journal); The immediate cause of this problem is that ext4_should_dioread_nolock() function returns inconsistent values in the ext4_do_writepages() and mpage_map_one_extent(). There are four conditions in this function that can be changed at mount time to cause this problem. These four conditions can be divided into two categories: (1) journal_data and EXT4_EXTENTS_FL, which can be changed by ioctl (2) DELALLOC and DIOREAD_NOLOCK, which can be changed by remount The two in the first category have been fixed by commit c8585c6fcaf2 ("ext4: fix races between changing inode journal mode and ext4_writepages") and commit cb85f4d23f79 ("ext4: fix race between writepages and enabling EXT4_EXTENTS_FL") respectively. Two cases in the other category have not yet been fixed, and the above issue is caused by this situation. We refer to the fix for the first category, when applying options during remount, we grab s_writepages_rwsem to avoid racing with writepages ops to trigger this problem. Fixes: 6b523df4fb5a ("ext4: use transaction reservation for extent conversion in ext4_end_io") Cc: stable(a)vger.kernel.org Signed-off-by: Baokun Li <libaokun1(a)huawei.com> Reviewed-by: Zhang Yi <yi.zhang(a)huawei.com> Reviewed-by: Yang Erkun <yangerkun(a)huawei.com> Signed-off-by: Yongqiang Liu <liuyongqiang13(a)huawei.com> --- fs/ext4/ext4.h | 3 ++- fs/ext4/super.c | 13 +++++++++++++ 2 files changed, 15 insertions(+), 1 deletion(-) diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 4c88e75180a2..6df919b154b4 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -1530,7 +1530,8 @@ struct ext4_sb_info { /* * Barrier between writepages ops and changing any inode's JOURNAL_DATA - * or EXTENTS flag. + * or EXTENTS flag or between writepages ops and changing DIOREAD_NOLOCK + * mount option on remount. */ struct percpu_rw_semaphore s_writepages_rwsem; struct dax_device *s_daxdev; diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 8029a6f6471c..df07222f1cc5 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -5605,10 +5605,20 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) vfs_flags = SB_LAZYTIME | SB_I_VERSION; sb->s_flags = (sb->s_flags & ~vfs_flags) | (*flags & vfs_flags); + /* + * Changing the DIOREAD_NOLOCK mount option may cause two calls to + * ext4_should_dioread_nolock() to return inconsistent values, + * triggering WARN_ON in ext4_add_complete_io(). we grab here + * s_writepages_rwsem to avoid race between writepages ops and + * remount. + */ + percpu_down_write(&sbi->s_writepages_rwsem); if (!parse_options(data, sb, NULL, &journal_ioprio, 1)) { err = -EINVAL; + percpu_up_write(&sbi->s_writepages_rwsem); goto restore_opts; } + percpu_up_write(&sbi->s_writepages_rwsem); if ((old_opts.s_mount_opt & EXT4_MOUNT_JOURNAL_CHECKSUM) ^ test_opt(sb, JOURNAL_CHECKSUM)) { @@ -5833,6 +5843,7 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) return 0; restore_opts: + percpu_down_write(&sbi->s_writepages_rwsem); sb->s_flags = old_sb_flags; sbi->s_mount_opt = old_opts.s_mount_opt; sbi->s_mount_opt2 = old_opts.s_mount_opt2; @@ -5841,6 +5852,8 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data) sbi->s_commit_interval = old_opts.s_commit_interval; sbi->s_min_batch_time = old_opts.s_min_batch_time; sbi->s_max_batch_time = old_opts.s_max_batch_time; + percpu_up_write(&sbi->s_writepages_rwsem); + if (!test_opt(sb, BLOCK_VALIDITY) && sbi->system_blks) ext4_release_system_zone(sb); #ifdef CONFIG_QUOTA -- 2.25.1

1 3

[PATCH] ALSA: pcm: Move rwsem lock inside snd_ctl_elem_read to prevent UAF
by Hui Tang 31 Mar '23

31 Mar '23

From: Clement Lecigne <clecigne(a)google.com> stable inclusion from stable-v5.10.162 commit df02234e6b87d2a9a82acd3198e44bdeff8488c6 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I6AOWP CVE: CVE-2023-0266 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Note: this is a fix that works around the bug equivalently as the two upstream commits: 1fa4445f9adf ("ALSA: control - introduce snd_ctl_notify_one() helper") 56b88b50565c ("ALSA: pcm: Move rwsem lock inside snd_ctl_elem_read to prevent UAF") but in a simpler way to fit with older stable trees -- tiwai ] Add missing locking in ctl_elem_read_user/ctl_elem_write_user which can be easily triggered and turned into an use-after-free. Example code paths with SNDRV_CTL_IOCTL_ELEM_READ: 64-bits: snd_ctl_ioctl snd_ctl_elem_read_user [takes controls_rwsem] snd_ctl_elem_read [lock properly held, all good] [drops controls_rwsem] 32-bits (compat): snd_ctl_ioctl_compat snd_ctl_elem_write_read_compat ctl_elem_write_read snd_ctl_elem_read [missing lock, not good] CVE-2023-0266 was assigned for this issue. Signed-off-by: Clement Lecigne <clecigne(a)google.com> Cc: stable(a)kernel.org # 5.12 and older Signed-off-by: Takashi Iwai <tiwai(a)suse.de> Reviewed-by: Jaroslav Kysela <perex(a)perex.cz> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Hui Tang <tanghui20(a)huawei.com> --- sound/core/control_compat.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/sound/core/control_compat.c b/sound/core/control_compat.c index 507fd5210c1c..f5e51f5e3437 100644 --- a/sound/core/control_compat.c +++ b/sound/core/control_compat.c @@ -316,7 +316,9 @@ static int ctl_elem_read_user(struct snd_card *card, err = snd_power_wait(card, SNDRV_CTL_POWER_D0); if (err < 0) goto error; + down_read(&card->controls_rwsem); err = snd_ctl_elem_read(card, data); + up_read(&card->controls_rwsem); if (err < 0) goto error; err = copy_ctl_value_to_user(userdata, valuep, data, type, count); @@ -344,7 +346,9 @@ static int ctl_elem_write_user(struct snd_ctl_file *file, err = snd_power_wait(card, SNDRV_CTL_POWER_D0); if (err < 0) goto error; + down_write(&card->controls_rwsem); err = snd_ctl_elem_write(card, file, data); + up_write(&card->controls_rwsem); if (err < 0) goto error; err = copy_ctl_value_to_user(userdata, valuep, data, type, count); -- 2.17.1

1 0

[PATCH openEuler-1.0-LTS] ALSA: pcm: Move rwsem lock inside snd_ctl_elem_read to prevent UAF
by Zhang Changzhong 31 Mar '23

31 Mar '23

From: Clement Lecigne <clecigne(a)google.com> stable inclusion from stable-v5.10.162 commit df02234e6b87d2a9a82acd3198e44bdeff8488c6 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I6AOWP CVE: CVE-2023-0266 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Note: this is a fix that works around the bug equivalently as the two upstream commits: 1fa4445f9adf ("ALSA: control - introduce snd_ctl_notify_one() helper") 56b88b50565c ("ALSA: pcm: Move rwsem lock inside snd_ctl_elem_read to prevent UAF") but in a simpler way to fit with older stable trees -- tiwai ] Add missing locking in ctl_elem_read_user/ctl_elem_write_user which can be easily triggered and turned into an use-after-free. Example code paths with SNDRV_CTL_IOCTL_ELEM_READ: 64-bits: snd_ctl_ioctl snd_ctl_elem_read_user [takes controls_rwsem] snd_ctl_elem_read [lock properly held, all good] [drops controls_rwsem] 32-bits (compat): snd_ctl_ioctl_compat snd_ctl_elem_write_read_compat ctl_elem_write_read snd_ctl_elem_read [missing lock, not good] CVE-2023-0266 was assigned for this issue. Signed-off-by: Clement Lecigne <clecigne(a)google.com> Cc: stable(a)kernel.org # 5.12 and older Signed-off-by: Takashi Iwai <tiwai(a)suse.de> Reviewed-by: Jaroslav Kysela <perex(a)perex.cz> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Hui Tang <tanghui20(a)huawei.com> Reviewed-by: Xiu Jianfeng <xiujianfeng(a)huawei.com> Reviewed-by: songping yu <yusongping(a)huawei.com> Signed-off-by: Zhang Changzhong <zhangchangzhong(a)huawei.com> --- sound/core/control_compat.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/sound/core/control_compat.c b/sound/core/control_compat.c index 507fd52..f5e51f5 100644 --- a/sound/core/control_compat.c +++ b/sound/core/control_compat.c @@ -316,7 +316,9 @@ static int ctl_elem_read_user(struct snd_card *card, err = snd_power_wait(card, SNDRV_CTL_POWER_D0); if (err < 0) goto error; + down_read(&card->controls_rwsem); err = snd_ctl_elem_read(card, data); + up_read(&card->controls_rwsem); if (err < 0) goto error; err = copy_ctl_value_to_user(userdata, valuep, data, type, count); @@ -344,7 +346,9 @@ static int ctl_elem_write_user(struct snd_ctl_file *file, err = snd_power_wait(card, SNDRV_CTL_POWER_D0); if (err < 0) goto error; + down_write(&card->controls_rwsem); err = snd_ctl_elem_write(card, file, data); + up_write(&card->controls_rwsem); if (err < 0) goto error; err = copy_ctl_value_to_user(userdata, valuep, data, type, count); -- 2.9.5

1 0

【重要】openEuler-22.03-LTS-SP2需求收集
by zhangjialin (F) 30 Mar '23

30 Mar '23

openEuler-22.03-LTS-SP2需求收集截止日期：2023年4月7日星期五 openEuler-22.03-LTS-SP2需求合入截止日期：2023年5月19日星期五目前是需求收集阶段，如果您有合入openEuler-22.03-LTS-SP2的需求，请您尽快向openEuler社区提交需求issue 需求issue提交链接：https://gitee.com/openeuler/kernel/issues，issue类型选择需求，issue标题以[… 我们将在2023年4月7日kernel sig双周例会上集中讨论，采纳的需求将纳入里程碑规划

1 0

[PATCH openEuler-1.0-LTS 1/4] RDMA/core: Don't infoleak GRH fields
by Yongqiang Liu 30 Mar '23

30 Mar '23

From: Leon Romanovsky <leonro(a)nvidia.com> stable inclusion from stable-v4.19.225 commit 153843e270459b08529f80a0a0d8258d91597594 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I6Q364 CVE: CVE-2021-3923 -------------------------------- commit b35a0f4dd544eaa6162b6d2f13a2557a121ae5fd upstream. If dst->is_global field is not set, the GRH fields are not cleared and the following infoleak is reported. ===================================================== BUG: KMSAN: kernel-infoleak in instrument_copy_to_user include/linux/instrumented.h:121 [inline] BUG: KMSAN: kernel-infoleak in _copy_to_user+0x1c9/0x270 lib/usercopy.c:33 instrument_copy_to_user include/linux/instrumented.h:121 [inline] _copy_to_user+0x1c9/0x270 lib/usercopy.c:33 copy_to_user include/linux/uaccess.h:209 [inline] ucma_init_qp_attr+0x8c7/0xb10 drivers/infiniband/core/ucma.c:1242 ucma_write+0x637/0x6c0 drivers/infiniband/core/ucma.c:1732 vfs_write+0x8ce/0x2030 fs/read_write.c:588 ksys_write+0x28b/0x510 fs/read_write.c:643 __do_sys_write fs/read_write.c:655 [inline] __se_sys_write fs/read_write.c:652 [inline] __ia32_sys_write+0xdb/0x120 fs/read_write.c:652 do_syscall_32_irqs_on arch/x86/entry/common.c:114 [inline] __do_fast_syscall_32+0x96/0xf0 arch/x86/entry/common.c:180 do_fast_syscall_32+0x34/0x70 arch/x86/entry/common.c:205 do_SYSENTER_32+0x1b/0x20 arch/x86/entry/common.c:248 entry_SYSENTER_compat_after_hwframe+0x4d/0x5c Local variable resp created at: ucma_init_qp_attr+0xa4/0xb10 drivers/infiniband/core/ucma.c:1214 ucma_write+0x637/0x6c0 drivers/infiniband/core/ucma.c:1732 Bytes 40-59 of 144 are uninitialized Memory access of size 144 starts at ffff888167523b00 Data copied to user address 0000000020000100 CPU: 1 PID: 25910 Comm: syz-executor.1 Not tainted 5.16.0-rc5-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 ===================================================== Fixes: 4ba66093bdc6 ("IB/core: Check for global flag when using ah_attr") Link: https://lore.kernel.org/r/0e9dd51f93410b7b2f4f5562f52befc878b71afa.16412988… Reported-by: syzbot+6d532fa8f9463da290bc(a)syzkaller.appspotmail.com Signed-off-by: Leon Romanovsky <leonro(a)nvidia.com> Signed-off-by: Jason Gunthorpe <jgg(a)nvidia.com> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Baisong Zhong <zhongbaisong(a)huawei.com> Reviewed-by: Yue Haibing <yuehaibing(a)huawei.com> Reviewed-by: Xiu Jianfeng <xiujianfeng(a)huawei.com> Signed-off-by: Yongqiang Liu <liuyongqiang13(a)huawei.com> --- drivers/infiniband/core/uverbs_marshall.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/infiniband/core/uverbs_marshall.c b/drivers/infiniband/core/uverbs_marshall.c index b8d715c68ca4..11a080646916 100644 --- a/drivers/infiniband/core/uverbs_marshall.c +++ b/drivers/infiniband/core/uverbs_marshall.c @@ -66,7 +66,7 @@ void ib_copy_ah_attr_to_user(struct ib_device *device, struct rdma_ah_attr *src = ah_attr; struct rdma_ah_attr conv_ah; - memset(&dst->grh.reserved, 0, sizeof(dst->grh.reserved)); + memset(&dst->grh, 0, sizeof(dst->grh)); if ((ah_attr->type == RDMA_AH_ATTR_TYPE_OPA) && (rdma_ah_get_dlid(ah_attr) > be16_to_cpu(IB_LID_PERMISSIVE)) && -- 2.25.1

1 3

[PATCH openEuler-1.0-LTS 1/2] RDMA/core: Don't infoleak GRH fields
by Yongqiang Liu 30 Mar '23

30 Mar '23

From: Leon Romanovsky <leonro(a)nvidia.com> stable inclusion from stable-v4.19.225 commit 153843e270459b08529f80a0a0d8258d91597594 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I6Q364 CVE: CVE-2021-3923 -------------------------------- commit b35a0f4dd544eaa6162b6d2f13a2557a121ae5fd upstream. If dst->is_global field is not set, the GRH fields are not cleared and the following infoleak is reported. ===================================================== BUG: KMSAN: kernel-infoleak in instrument_copy_to_user include/linux/instrumented.h:121 [inline] BUG: KMSAN: kernel-infoleak in _copy_to_user+0x1c9/0x270 lib/usercopy.c:33 instrument_copy_to_user include/linux/instrumented.h:121 [inline] _copy_to_user+0x1c9/0x270 lib/usercopy.c:33 copy_to_user include/linux/uaccess.h:209 [inline] ucma_init_qp_attr+0x8c7/0xb10 drivers/infiniband/core/ucma.c:1242 ucma_write+0x637/0x6c0 drivers/infiniband/core/ucma.c:1732 vfs_write+0x8ce/0x2030 fs/read_write.c:588 ksys_write+0x28b/0x510 fs/read_write.c:643 __do_sys_write fs/read_write.c:655 [inline] __se_sys_write fs/read_write.c:652 [inline] __ia32_sys_write+0xdb/0x120 fs/read_write.c:652 do_syscall_32_irqs_on arch/x86/entry/common.c:114 [inline] __do_fast_syscall_32+0x96/0xf0 arch/x86/entry/common.c:180 do_fast_syscall_32+0x34/0x70 arch/x86/entry/common.c:205 do_SYSENTER_32+0x1b/0x20 arch/x86/entry/common.c:248 entry_SYSENTER_compat_after_hwframe+0x4d/0x5c Local variable resp created at: ucma_init_qp_attr+0xa4/0xb10 drivers/infiniband/core/ucma.c:1214 ucma_write+0x637/0x6c0 drivers/infiniband/core/ucma.c:1732 Bytes 40-59 of 144 are uninitialized Memory access of size 144 starts at ffff888167523b00 Data copied to user address 0000000020000100 CPU: 1 PID: 25910 Comm: syz-executor.1 Not tainted 5.16.0-rc5-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 ===================================================== Fixes: 4ba66093bdc6 ("IB/core: Check for global flag when using ah_attr") Link: https://lore.kernel.org/r/0e9dd51f93410b7b2f4f5562f52befc878b71afa.16412988… Reported-by: syzbot+6d532fa8f9463da290bc(a)syzkaller.appspotmail.com Signed-off-by: Leon Romanovsky <leonro(a)nvidia.com> Signed-off-by: Jason Gunthorpe <jgg(a)nvidia.com> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Baisong Zhong <zhongbaisong(a)huawei.com> Reviewed-by: Yue Haibing <yuehaibing(a)huawei.com> Reviewed-by: Xiu Jianfeng <xiujianfeng(a)huawei.com> Signed-off-by: Yongqiang Liu <liuyongqiang13(a)huawei.com> --- drivers/infiniband/core/uverbs_marshall.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/infiniband/core/uverbs_marshall.c b/drivers/infiniband/core/uverbs_marshall.c index b8d715c68ca4..11a080646916 100644 --- a/drivers/infiniband/core/uverbs_marshall.c +++ b/drivers/infiniband/core/uverbs_marshall.c @@ -66,7 +66,7 @@ void ib_copy_ah_attr_to_user(struct ib_device *device, struct rdma_ah_attr *src = ah_attr; struct rdma_ah_attr conv_ah; - memset(&dst->grh.reserved, 0, sizeof(dst->grh.reserved)); + memset(&dst->grh, 0, sizeof(dst->grh)); if ((ah_attr->type == RDMA_AH_ATTR_TYPE_OPA) && (rdma_ah_get_dlid(ah_attr) > be16_to_cpu(IB_LID_PERMISSIVE)) && -- 2.25.1

1 1

[PATCH openEuler-1.0-LTS 1/3] cgroup/cpuset: Change cpuset_rwsem and hotplug lock order
by Yongqiang Liu 29 Mar '23

29 Mar '23

From: Juri Lelli <juri.lelli(a)redhat.com> mainline inclusion from mainline-v5.4-rc1 commit d74b27d63a8bebe2fe634944e4ebdc7b10db7a39 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I6L46J CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- cpuset_rwsem is going to be acquired from sched_setscheduler() with a following patch. There are however paths (e.g., spawn_ksoftirqd) in which sched_scheduler() is eventually called while holding hotplug lock; this creates a dependecy between hotplug lock (to be always acquired first) and cpuset_rwsem (to be always acquired after hotplug lock). Fix paths which currently take the two locks in the wrong order (after a following patch is applied). Tested-by: Dietmar Eggemann <dietmar.eggemann(a)arm.com> Signed-off-by: Juri Lelli <juri.lelli(a)redhat.com> Signed-off-by: Peter Zijlstra (Intel) <peterz(a)infradead.org> Cc: Linus Torvalds <torvalds(a)linux-foundation.org> Cc: Peter Zijlstra <peterz(a)infradead.org> Cc: Thomas Gleixner <tglx(a)linutronix.de> Cc: bristot(a)redhat.com Cc: claudio(a)evidence.eu.com Cc: lizefan(a)huawei.com Cc: longman(a)redhat.com Cc: luca.abeni(a)santannapisa.it Cc: mathieu.poirier(a)linaro.org Cc: rostedt(a)goodmis.org Cc: tj(a)kernel.org Cc: tommaso.cucinotta(a)santannapisa.it Link: https://lkml.kernel.org/r/20190719140000.31694-7-juri.lelli@redhat.com Signed-off-by: Ingo Molnar <mingo(a)kernel.org> conflicts: kernel/cgroup/cpuset.c Signed-off-by: Cai Xinchen <caixinchen1(a)huawei.com> Reviewed-by: Wang Weiyang <wangweiyang2(a)huawei.com> Reviewed-by: Xiu Jianfeng <xiujianfeng(a)huawei.com> Signed-off-by: Yongqiang Liu <liuyongqiang13(a)huawei.com> --- include/linux/cpuset.h | 8 ++++---- kernel/cgroup/cpuset.c | 24 +++++++++++++++++------- 2 files changed, 21 insertions(+), 11 deletions(-) diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h index 934633a05d20..7f1478c26a33 100644 --- a/include/linux/cpuset.h +++ b/include/linux/cpuset.h @@ -40,14 +40,14 @@ static inline bool cpusets_enabled(void) static inline void cpuset_inc(void) { - static_branch_inc(&cpusets_pre_enable_key); - static_branch_inc(&cpusets_enabled_key); + static_branch_inc_cpuslocked(&cpusets_pre_enable_key); + static_branch_inc_cpuslocked(&cpusets_enabled_key); } static inline void cpuset_dec(void) { - static_branch_dec(&cpusets_enabled_key); - static_branch_dec(&cpusets_pre_enable_key); + static_branch_dec_cpuslocked(&cpusets_enabled_key); + static_branch_dec_cpuslocked(&cpusets_pre_enable_key); } extern int cpuset_init(void); diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index 55bfbc4cdb16..def36c3fc524 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -914,8 +914,8 @@ static void rebuild_sched_domains_locked(void) cpumask_var_t *doms; int ndoms; + lockdep_assert_cpus_held(); lockdep_assert_held(&cpuset_mutex); - get_online_cpus(); /* * We have raced with CPU hotplug. Don't do anything to avoid @@ -923,15 +923,13 @@ static void rebuild_sched_domains_locked(void) * Anyways, hotplug work item will rebuild sched domains. */ if (!cpumask_equal(top_cpuset.effective_cpus, cpu_active_mask)) - goto out; + return; /* Generate domain masks and attrs */ ndoms = generate_sched_domains(&doms, &attr); /* Have scheduler rebuild the domains */ partition_sched_domains(ndoms, doms, attr); -out: - put_online_cpus(); } #else /* !CONFIG_SMP */ static void rebuild_sched_domains_locked(void) @@ -941,9 +939,11 @@ static void rebuild_sched_domains_locked(void) void rebuild_sched_domains(void) { + get_online_cpus(); mutex_lock(&cpuset_mutex); rebuild_sched_domains_locked(); mutex_unlock(&cpuset_mutex); + put_online_cpus(); } /** @@ -1612,13 +1612,13 @@ static void cpuset_attach(struct cgroup_taskset *tset) cgroup_taskset_first(tset, &css); cs = css_cs(css); - mutex_lock(&cpuset_mutex); - /* * It should hold cpus lock because a cpu offline event can * cause set_cpus_allowed_ptr() failed. */ get_online_cpus(); + mutex_lock(&cpuset_mutex); + /* prepare for attach */ if (cs == &top_cpuset) cpumask_copy(cpus_attach, cpu_possible_mask); @@ -1644,7 +1644,6 @@ static void cpuset_attach(struct cgroup_taskset *tset) cpuset_change_task_nodemask(task, &cpuset_attach_nodemask_to); cpuset_update_task_spread_flag(cs, task); } - put_online_cpus(); /* * Change mm for all threadgroup leaders. This is expensive and may @@ -1680,6 +1679,7 @@ static void cpuset_attach(struct cgroup_taskset *tset) wake_up(&cpuset_attach_wq); mutex_unlock(&cpuset_mutex); + put_online_cpus(); } /* The various types of files and directories in a cpuset file system */ @@ -1711,6 +1711,7 @@ static int cpuset_write_u64(struct cgroup_subsys_state *css, struct cftype *cft, cpuset_filetype_t type = cft->private; int retval = 0; + get_online_cpus(); mutex_lock(&cpuset_mutex); if (!is_cpuset_online(cs)) { retval = -ENODEV; @@ -1748,6 +1749,7 @@ static int cpuset_write_u64(struct cgroup_subsys_state *css, struct cftype *cft, } out_unlock: mutex_unlock(&cpuset_mutex); + put_online_cpus(); return retval; } @@ -1758,6 +1760,7 @@ static int cpuset_write_s64(struct cgroup_subsys_state *css, struct cftype *cft, cpuset_filetype_t type = cft->private; int retval = -ENODEV; + get_online_cpus(); mutex_lock(&cpuset_mutex); if (!is_cpuset_online(cs)) goto out_unlock; @@ -1772,6 +1775,7 @@ static int cpuset_write_s64(struct cgroup_subsys_state *css, struct cftype *cft, } out_unlock: mutex_unlock(&cpuset_mutex); + put_online_cpus(); return retval; } @@ -1810,6 +1814,7 @@ static ssize_t cpuset_write_resmask(struct kernfs_open_file *of, kernfs_break_active_protection(of->kn); flush_work(&cpuset_hotplug_work); + get_online_cpus(); mutex_lock(&cpuset_mutex); if (!is_cpuset_online(cs)) goto out_unlock; @@ -1840,6 +1845,7 @@ static ssize_t cpuset_write_resmask(struct kernfs_open_file *of, free_trial_cpuset(trialcs); out_unlock: mutex_unlock(&cpuset_mutex); + put_online_cpus(); kernfs_unbreak_active_protection(of->kn); css_put(&cs->css); flush_workqueue(cpuset_migrate_mm_wq); @@ -2108,6 +2114,7 @@ static int cpuset_css_online(struct cgroup_subsys_state *css) if (!parent) return 0; + get_online_cpus(); mutex_lock(&cpuset_mutex); set_bit(CS_ONLINE, &cs->flags); @@ -2161,6 +2168,7 @@ static int cpuset_css_online(struct cgroup_subsys_state *css) spin_unlock_irq(&callback_lock); out_unlock: mutex_unlock(&cpuset_mutex); + put_online_cpus(); return 0; } @@ -2174,6 +2182,7 @@ static void cpuset_css_offline(struct cgroup_subsys_state *css) { struct cpuset *cs = css_cs(css); + get_online_cpus(); mutex_lock(&cpuset_mutex); if (is_sched_load_balance(cs)) @@ -2183,6 +2192,7 @@ static void cpuset_css_offline(struct cgroup_subsys_state *css) clear_bit(CS_ONLINE, &cs->flags); mutex_unlock(&cpuset_mutex); + put_online_cpus(); } static void cpuset_css_free(struct cgroup_subsys_state *css) -- 2.25.1

1 2

[PATCH openEuler-5.10-LTS-SP1 01/36] bpf, sockmap: Fix an infinite loop error when len is 0 in tcp_bpf_recvmsg_parser()
by Jialin Zhang 29 Mar '23

29 Mar '23

From: Liu Jian <liujian56(a)huawei.com> mainline inclusion from mainline-v6.3-rc2 commit d900f3d20cc3169ce42ec72acc850e662a4d4db2 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I65HYE CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… --------------------------- When the buffer length of the recvmsg system call is 0, we got the flollowing soft lockup problem: watchdog: BUG: soft lockup - CPU#3 stuck for 27s! [a.out:6149] CPU: 3 PID: 6149 Comm: a.out Kdump: loaded Not tainted 6.2.0+ #30 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.15.0-1 04/01/2014 RIP: 0010:remove_wait_queue+0xb/0xc0 Code: 5e 41 5f c3 cc cc cc cc 0f 1f 80 00 00 00 00 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 f3 0f 1e fa 0f 1f 44 00 00 41 57 <41> 56 41 55 41 54 55 48 89 fd 53 48 89 f3 4c 8d 6b 18 4c 8d 73 20 RSP: 0018:ffff88811b5978b8 EFLAGS: 00000246 RAX: 0000000000000000 RBX: ffff88811a7d3780 RCX: ffffffffb7a4d768 RDX: dffffc0000000000 RSI: ffff88811b597908 RDI: ffff888115408040 RBP: 1ffff110236b2f1b R08: 0000000000000000 R09: ffff88811a7d37e7 R10: ffffed10234fa6fc R11: 0000000000000001 R12: ffff88811179b800 R13: 0000000000000001 R14: ffff88811a7d38a8 R15: ffff88811a7d37e0 FS: 00007f6fb5398740(0000) GS:ffff888237180000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000020000000 CR3: 000000010b6ba002 CR4: 0000000000370ee0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: <TASK> tcp_msg_wait_data+0x279/0x2f0 tcp_bpf_recvmsg_parser+0x3c6/0x490 inet_recvmsg+0x280/0x290 sock_recvmsg+0xfc/0x120 ____sys_recvmsg+0x160/0x3d0 ___sys_recvmsg+0xf0/0x180 __sys_recvmsg+0xea/0x1a0 do_syscall_64+0x3f/0x90 entry_SYSCALL_64_after_hwframe+0x72/0xdc The logic in tcp_bpf_recvmsg_parser is as follows: msg_bytes_ready: copied = sk_msg_recvmsg(sk, psock, msg, len, flags); if (!copied) { wait data; goto msg_bytes_ready; } In this case, "copied" always is 0, the infinite loop occurs. According to the Linux system call man page, 0 should be returned in this case. Therefore, in tcp_bpf_recvmsg_parser(), if the length is 0, directly return. Also modify several other functions with the same problem. Fixes: 1f5be6b3b063 ("udp: Implement udp_bpf_recvmsg() for sockmap") Fixes: 9825d866ce0d ("af_unix: Implement unix_dgram_bpf_recvmsg()") Fixes: c5d2177a72a1 ("bpf, sockmap: Fix race in ingress receive verdict with redirect to self") Fixes: 604326b41a6f ("bpf, sockmap: convert to generic sk_msg interface") Signed-off-by: Liu Jian <liujian56(a)huawei.com> Signed-off-by: Daniel Borkmann <daniel(a)iogearbox.net> Acked-by: John Fastabend <john.fastabend(a)gmail.com> Cc: Jakub Sitnicki <jakub(a)cloudflare.com> Link: https://lore.kernel.org/bpf/20230303080946.1146638-1-liujian56@huawei.com (cherry picked from commit d900f3d20cc3169ce42ec72acc850e662a4d4db2) Signed-off-by: Liu Jian <liujian56(a)huawei.com> Conflicts: net/ipv4/udp_bpf.c net/unix/unix_bpf.c net/ipv4/tcp_bpf.c Reviewed-by: Yue Haibing <yuehaibing(a)huawei.com> Signed-off-by: Jialin Zhang <zhangjialin11(a)huawei.com> --- net/ipv4/tcp_bpf.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c index 1a8f129fb309..89bbb8ee1634 100644 --- a/net/ipv4/tcp_bpf.c +++ b/net/ipv4/tcp_bpf.c @@ -275,6 +275,9 @@ static int tcp_bpf_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, if (unlikely(flags & MSG_ERRQUEUE)) return inet_recv_error(sk, msg, len, addr_len); + if (!len) + return 0; + psock = sk_psock_get(sk); if (unlikely(!psock)) return tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len); -- 2.25.1

1 35

[PATCH openEuler-5.10-LTS 01/36] bpf, sockmap: Fix an infinite loop error when len is 0 in tcp_bpf_recvmsg_parser()
by Jialin Zhang 29 Mar '23

29 Mar '23

From: Liu Jian <liujian56(a)huawei.com> mainline inclusion from mainline-v6.3-rc2 commit d900f3d20cc3169ce42ec72acc850e662a4d4db2 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I65HYE CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… --------------------------- When the buffer length of the recvmsg system call is 0, we got the flollowing soft lockup problem: watchdog: BUG: soft lockup - CPU#3 stuck for 27s! [a.out:6149] CPU: 3 PID: 6149 Comm: a.out Kdump: loaded Not tainted 6.2.0+ #30 Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.15.0-1 04/01/2014 RIP: 0010:remove_wait_queue+0xb/0xc0 Code: 5e 41 5f c3 cc cc cc cc 0f 1f 80 00 00 00 00 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 90 f3 0f 1e fa 0f 1f 44 00 00 41 57 <41> 56 41 55 41 54 55 48 89 fd 53 48 89 f3 4c 8d 6b 18 4c 8d 73 20 RSP: 0018:ffff88811b5978b8 EFLAGS: 00000246 RAX: 0000000000000000 RBX: ffff88811a7d3780 RCX: ffffffffb7a4d768 RDX: dffffc0000000000 RSI: ffff88811b597908 RDI: ffff888115408040 RBP: 1ffff110236b2f1b R08: 0000000000000000 R09: ffff88811a7d37e7 R10: ffffed10234fa6fc R11: 0000000000000001 R12: ffff88811179b800 R13: 0000000000000001 R14: ffff88811a7d38a8 R15: ffff88811a7d37e0 FS: 00007f6fb5398740(0000) GS:ffff888237180000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000020000000 CR3: 000000010b6ba002 CR4: 0000000000370ee0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: <TASK> tcp_msg_wait_data+0x279/0x2f0 tcp_bpf_recvmsg_parser+0x3c6/0x490 inet_recvmsg+0x280/0x290 sock_recvmsg+0xfc/0x120 ____sys_recvmsg+0x160/0x3d0 ___sys_recvmsg+0xf0/0x180 __sys_recvmsg+0xea/0x1a0 do_syscall_64+0x3f/0x90 entry_SYSCALL_64_after_hwframe+0x72/0xdc The logic in tcp_bpf_recvmsg_parser is as follows: msg_bytes_ready: copied = sk_msg_recvmsg(sk, psock, msg, len, flags); if (!copied) { wait data; goto msg_bytes_ready; } In this case, "copied" always is 0, the infinite loop occurs. According to the Linux system call man page, 0 should be returned in this case. Therefore, in tcp_bpf_recvmsg_parser(), if the length is 0, directly return. Also modify several other functions with the same problem. Fixes: 1f5be6b3b063 ("udp: Implement udp_bpf_recvmsg() for sockmap") Fixes: 9825d866ce0d ("af_unix: Implement unix_dgram_bpf_recvmsg()") Fixes: c5d2177a72a1 ("bpf, sockmap: Fix race in ingress receive verdict with redirect to self") Fixes: 604326b41a6f ("bpf, sockmap: convert to generic sk_msg interface") Signed-off-by: Liu Jian <liujian56(a)huawei.com> Signed-off-by: Daniel Borkmann <daniel(a)iogearbox.net> Acked-by: John Fastabend <john.fastabend(a)gmail.com> Cc: Jakub Sitnicki <jakub(a)cloudflare.com> Link: https://lore.kernel.org/bpf/20230303080946.1146638-1-liujian56@huawei.com (cherry picked from commit d900f3d20cc3169ce42ec72acc850e662a4d4db2) Signed-off-by: Liu Jian <liujian56(a)huawei.com> Conflicts: net/ipv4/udp_bpf.c net/unix/unix_bpf.c net/ipv4/tcp_bpf.c Reviewed-by: Yue Haibing <yuehaibing(a)huawei.com> Signed-off-by: Jialin Zhang <zhangjialin11(a)huawei.com> --- net/ipv4/tcp_bpf.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c index eaf2308c355a..ddb1730cdf9b 100644 --- a/net/ipv4/tcp_bpf.c +++ b/net/ipv4/tcp_bpf.c @@ -273,6 +273,9 @@ static int tcp_bpf_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, if (unlikely(flags & MSG_ERRQUEUE)) return inet_recv_error(sk, msg, len, addr_len); + if (!len) + return 0; + psock = sk_psock_get(sk); if (unlikely(!psock)) return tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len); -- 2.25.1

1 35

[PATCH openEuler-22.03-LTS-SP1 00/39] ascend features send to
by Zhang Zekun 29 Mar '23

29 Mar '23

Push some of ascend features to openEuler Bixuan Cui (1): open modules for sig Chen Jun (4): mm/sharepool: Fix a double free problem caused by init_local_group mm/sharepool: use delete_spg_node to replace some repetitive code mm/sharepool: extract group_add_task mm/sharepool: check permission of task to operate spg_node->proc_node Fang Lijun (2): enable fdm in panic HZ 12 Jian Zhang (5): drivers: add RAS support for multiple die cpu bugfix for RAS acpi map add SDMA support for 1980B using mm's pasid rather than a random value when using SDMA kernel/sdei: enable SDEI for nmi Lijun Fang (1): modify ascend910 ARCH_NR_GPIOS Wang Wensheng (11): char/sdma: Add driver framework for sdma char/sdma: Implement probe function for sdma device char/sdma: Implement sdma_memcpy for kernel-space usage char/sdma: Export the sdma features to userspace via ioctl char/sdma: Add support for ACPI char/sdma: Support multiple sdma devices char/sdma: Add deffer probe feature char/sdma: Add discrete memcpy interface for userspace char/sdma: Pin pages when copying user memory memcg/ascend: Support not account pages of cdm for memcg mm/cdm: Extend cdm-nodes to support more nodes than 64 Xiang Rui (1): Add kernel securec support for 1980. Xingang Wang (1): ascend_mpam: Add dts driver to traverse accelerators Xu Qiang (1): Fix kernel boot failed in fpga. Yuan Can (4): driver/iommu: Introduce IOMMU_SVA_FEAT_SVSP feature driver/svm: save svsp_mm in mm and release it in __mmput Add bootdot support for ascend 310B Set bootdot base to 10 Zhang Jian (2): drivers: apci parse apei table drivers: acpi register irq Zhou Guanghui (5): Modify memblock number driver/svm: support SVSP feature, interface definition driver/svm: reserve address range for svsp efi: when kaslr is enabled, restrict the random address range. mm/hugetlb: support disable clear hugepage chenjunwei (1): ascend310B_defconfig .../admin-guide/kernel-parameters.txt | 1 + arch/arm64/Kconfig | 30 + arch/arm64/configs/ascend310B_defconfig | 7040 +++++++++++++++++ arch/arm64/kernel/acpi.c | 5 + arch/arm64/kernel/sdei.c | 11 - arch/arm64/mm/init.c | 5 + arch/arm64/mm/numa.c | 39 +- certs/Makefile | 3 +- drivers/Kconfig | 3 + drivers/Makefile | 2 + drivers/acpi/Kconfig | 11 + drivers/acpi/Makefile | 1 + drivers/acpi/apei/ghes.c | 47 +- drivers/acpi/apei/hest.c | 35 + drivers/acpi/dt_apei.c | 201 + drivers/bootdot/Kconfig | 7 + drivers/bootdot/Makefile | 2 + drivers/bootdot/bootdot.c | 447 ++ drivers/char/Kconfig | 6 + drivers/char/Makefile | 1 + drivers/char/sdma.c | 1088 +++ .../firmware/efi/libstub/efi-stub-helper.c | 3 + drivers/firmware/efi/libstub/efistub.h | 1 + drivers/firmware/efi/libstub/randomalloc.c | 11 + drivers/gpio/gpiolib.c | 45 +- drivers/hisi/Kconfig | 16 + drivers/hisi/Makefile | 1 + drivers/hisi/securec/Kconfig | 1 + drivers/hisi/securec/Makefile | 1 + drivers/hisi/securec/src | 1 + drivers/iommu/Kconfig | 7 + drivers/iommu/Makefile | 1 + .../iommu/arm/arm-smmu-v3/arm-smmu-v3-sva.c | 35 + drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 16 + drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h | 8 + drivers/iommu/ascend_mpam.c | 286 + drivers/irqchip/irq-gic-v3-its.c | 13 +- fs/hugetlbfs/inode.c | 12 +- include/acpi/apei.h | 7 + include/acpi/dt_apei.h | 31 + include/asm-generic/gpio.h | 13 + include/linux/ascend_smmu.h | 38 + include/linux/bootdot.h | 40 + include/linux/hisi_sdma.h | 42 + include/linux/init.h | 1 + include/linux/iommu.h | 1 + include/linux/kernel.h | 6 + include/linux/mm_types.h | 4 + include/linux/mman.h | 46 + include/linux/securec.h | 1 + include/linux/securectype.h | 1 + include/uapi/asm-generic/mman-common.h | 1 + kernel/Kconfig.hz | 6 + kernel/fork.c | 13 + kernel/panic.c | 31 + mm/hugetlb.c | 2 + mm/memblock.c | 2 +- mm/memcontrol.c | 8 + mm/mmap.c | 32 +- mm/share_pool.c | 105 +- 60 files changed, 9806 insertions(+), 68 deletions(-) create mode 100644 arch/arm64/configs/ascend310B_defconfig create mode 100644 drivers/acpi/dt_apei.c create mode 100644 drivers/bootdot/Kconfig create mode 100644 drivers/bootdot/Makefile create mode 100644 drivers/bootdot/bootdot.c create mode 100644 drivers/char/sdma.c create mode 100644 drivers/hisi/Kconfig create mode 100644 drivers/hisi/Makefile create mode 100644 drivers/hisi/securec/Kconfig create mode 100644 drivers/hisi/securec/Makefile create mode 120000 drivers/hisi/securec/src create mode 100644 drivers/iommu/ascend_mpam.c create mode 100644 include/acpi/dt_apei.h create mode 100644 include/linux/bootdot.h create mode 100644 include/linux/hisi_sdma.h create mode 120000 include/linux/securec.h create mode 120000 include/linux/securectype.h -- 2.17.1

1 39

[PATCH openEuler-1.0-LTS 0/3] CVE-2023-1281
by Zhang Changzhong 28 Mar '23

28 Mar '23

Paul E. McKenney (1): rcu: Upgrade rcu_swap_protected() to rcu_replace_pointer() Pedro Tammela (2): net/sched: tcindex: update imperfect hash filters respecting rcu net/sched: tcindex: search key must be 16 bits include/linux/rcupdate.h | 18 ++++++++++++++++++ net/sched/cls_tcindex.c | 34 ++++++++++++++++++++++++++++++---- 2 files changed, 48 insertions(+), 4 deletions(-) -- 2.9.5

1 3

[PATCH OLK-5.10 v2 00/14] test patchwork->PR function v2
by Jialin Zhang 27 Mar '23

27 Mar '23

Send 14 patches to test patchwork->PR function Baisong Zhong (1): media: dvb-usb: az6027: fix null-ptr-deref in az6027_i2c_xfer() Chen Zhongjin (1): ftrace: Fix invalid address access in lookup_rec() when index is 0 Darrick J. Wong (1): ext4: fix another off-by-one fsmap error on 1k block filesystems David Hildenbrand (2): mm: optimize do_wp_page() for exclusive pages in the swapcache mm: optimize do_wp_page() for fresh pages in local LRU pagevecs Kuniyuki Iwashima (1): seccomp: Move copy_seccomp() to no failure path. Luke D. Jones (1): HID: asus: Remove check for same LED brightness on set Nicholas Piggin (1): mm/vmalloc: huge vmalloc backing pages should be split rather than compound Pietro Borrello (2): HID: asus: use spinlock to protect concurrent accesses HID: asus: use spinlock to safely schedule workers Xin Long (2): tipc: set con sock in tipc_conn_alloc tipc: add an extra conn_get in tipc_conn_alloc Zheng Yejian (1): livepatch/core: Fix hungtask against cpu hotplug on x86 Zhihao Cheng (1): jbd2: fix data missing when reusing bh which is ready to be checkpointed drivers/hid/hid-asus.c | 38 ++++++++++++++++++----- drivers/media/usb/dvb-usb/az6027.c | 4 +++ fs/ext4/fsmap.c | 2 ++ fs/jbd2/transaction.c | 50 +++++++++++++++++------------- kernel/fork.c | 17 ++++++---- kernel/livepatch/core.c | 36 ++++++++++++++------- kernel/trace/ftrace.c | 3 +- mm/memory.c | 28 +++++++++++++---- mm/vmalloc.c | 22 ++++++++++--- net/tipc/topsrv.c | 20 ++++++------ 10 files changed, 154 insertions(+), 66 deletions(-) -- 2.25.1

1 14

[PATCH openEuler-1.0-LTS 00/35] CVE-2022-29901
by Yongqiang Liu 25 Mar '23

25 Mar '23

CVE-2022-29901 Alexandre Chartre (2): x86/bugs: Report AMD retbleed vulnerability x86/bugs: Add AMD retbleed= boot parameter Andrew Cooper (1): x86/cpu/amd: Enumerate BTC_NO Daniel Sneddon (1): x86/speculation: Add RSB VM Exit protections Ingo Molnar (1): x86/cpufeature: Fix various quality problems in the <asm/cpu_device_hd.h> header Josh Poimboeuf (8): x86/speculation: Fix RSB filling with CONFIG_RETPOLINE=n x86/speculation: Fix firmware entry SPEC_CTRL handling x86/speculation: Fix SPEC_CTRL write on SMT state change x86/speculation: Use cached host SPEC_CTRL value for guest entry/exit x86/speculation: Remove x86_spec_ctrl_mask KVM: VMX: Prevent guest RSB poisoning attacks with eIBRS KVM: VMX: Fix IBRS handling after vmexit x86/speculation: Fill RSB on vmexit for IBRS Kan Liang (1): x86/cpufeature: Add facility to check for min microcode revisions Mark Gross (1): x86/cpu: Add a steppings field to struct x86_cpu_id Nathan Chancellor (1): x86/speculation: Use DECLARE_PER_CPU for x86_spec_ctrl_current Pawan Gupta (4): x86/speculation: Add spectre_v2=ibrs option to support Kernel IBRS x86/bugs: Add Cannon lake to RETBleed affected CPU list x86/speculation: Disable RRSBA behavior x86/bugs: Warn when "ibrs" mitigation is selected on Enhanced IBRS parts Peter Zijlstra (11): x86/nospec: Fix i386 RSB stuffing x86/cpufeatures: Move RETPOLINE flags to word 11 x86/bugs: Keep a per-CPU IA32_SPEC_CTRL value x86/entry: Remove skip_r11rcx x86/entry: Add kernel IBRS implementation x86/bugs: Optimize SPEC_CTRL MSR writes x86/bugs: Split spectre_v2_select_mitigation() and spectre_v2_user_select_mitigation() x86/bugs: Report Intel retbleed vulnerability intel_idle: Disable IBRS during long idle x86/speculation: Change FILL_RETURN_BUFFER to work with objtool x86/common: Stamp out the stepping madness Suleiman Souhlal (2): Revert "x86/speculation: Add RSB VM Exit protections" Revert "x86/cpu: Add a steppings field to struct x86_cpu_id" Thomas Gleixner (2): x86/devicetable: Move x86 specific macro out of generic code x86/cpu: Add consistent CPU match macros .../admin-guide/kernel-parameters.txt | 13 + arch/x86/entry/calling.h | 68 +++- arch/x86/entry/entry_32.S | 2 - arch/x86/entry/entry_64.S | 34 +- arch/x86/entry/entry_64_compat.S | 11 +- arch/x86/include/asm/cpu_device_id.h | 168 +++++++- arch/x86/include/asm/cpufeatures.h | 18 +- arch/x86/include/asm/intel-family.h | 6 + arch/x86/include/asm/msr-index.h | 10 + arch/x86/include/asm/nospec-branch.h | 67 ++-- arch/x86/kernel/cpu/amd.c | 21 +- arch/x86/kernel/cpu/bugs.c | 368 ++++++++++++++---- arch/x86/kernel/cpu/common.c | 72 ++-- arch/x86/kernel/cpu/match.c | 44 ++- arch/x86/kernel/cpu/scattered.c | 1 + arch/x86/kernel/process.c | 2 +- arch/x86/kvm/svm.c | 1 + arch/x86/kvm/vmx.c | 53 ++- arch/x86/kvm/x86.c | 2 +- drivers/base/cpu.c | 8 + drivers/cpufreq/acpi-cpufreq.c | 1 + drivers/cpufreq/amd_freq_sensitivity.c | 1 + drivers/idle/intel_idle.c | 43 +- include/linux/cpu.h | 2 + include/linux/kvm_host.h | 2 +- include/linux/mod_devicetable.h | 4 +- tools/arch/x86/include/asm/cpufeatures.h | 2 +- 27 files changed, 832 insertions(+), 192 deletions(-) -- 2.25.1

1 35

[PATCH openEuler-1.0-LTS 1/2] ext4: commit super block if fs record error when journal record without error
by Yongqiang Liu 25 Mar '23

25 Mar '23

From: Ye Bin <yebin10(a)huawei.com> mainline inclusion from mainline-v6.3-rc2 commit eee00237fa5ec8f704f7323b54e48cc34e2d9168 category: bugfix bugzilla: 188471,https://gitee.com/openeuler/kernel/issues/I6MR1V CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- Now, 'es->s_state' maybe covered by recover journal. And journal errno maybe not recorded in journal sb as IO error. ext4_update_super() only update error information when 'sbi->s_add_error_count' large than zero. Then 'EXT4_ERROR_FS' flag maybe lost. To solve above issue just recover 'es->s_state' error flag after journal replay like error info. Signed-off-by: Ye Bin <yebin10(a)huawei.com> Reviewed-by: Baokun Li <libaokun1(a)huawei.com> Reviewed-by: Jan Kara <jack(a)suse.cz> Link: https://lore.kernel.org/r/20230307061703.245965-2-yebin@huaweicloud.com Signed-off-by: Baokun Li <libaokun1(a)huawei.com> Reviewed-by: Zhang Yi <yi.zhang(a)huawei.com> Reviewed-by: Yang Erkun <yangerkun(a)huawei.com> Signed-off-by: Yongqiang Liu <liuyongqiang13(a)huawei.com> --- fs/ext4/super.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/fs/ext4/super.c b/fs/ext4/super.c index 594fc6dd0e9f..31a4725da745 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -5161,6 +5161,7 @@ static int ext4_load_journal(struct super_block *sb, err = jbd2_journal_wipe(journal, !really_read_only); if (!err) { char *save = kmalloc(EXT4_S_ERR_LEN, GFP_KERNEL); + if (save) memcpy(save, ((char *) es) + EXT4_S_ERR_START, EXT4_S_ERR_LEN); @@ -5169,6 +5170,14 @@ static int ext4_load_journal(struct super_block *sb, memcpy(((char *) es) + EXT4_S_ERR_START, save, EXT4_S_ERR_LEN); kfree(save); + es->s_state |= cpu_to_le16(EXT4_SB(sb)->s_mount_state & + EXT4_ERROR_FS); + /* Write out restored error information to the superblock */ + if (!bdev_read_only(sb->s_bdev)) { + int err2; + err2 = ext4_commit_super(sb); + err = err ? : err2; + } } if (err) { -- 2.25.1

1 1

[PATCH openEuler-1.0-LTS 01/10] scsi: hisi_sas: Grab sas_dev lock when traversing the members of sas_dev.list
by Yongqiang Liu 25 Mar '23

25 Mar '23

From: Xingui Yang <yangxingui(a)huawei.com> driver inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I6J1SI CVE: NA ---------------------------- When the IO complete and free slot in function slot_complete_v3_hw(), it is possible that sas_dev.list is being traversed elsewhere, and it may trigger a null pointer exception, such as follows: ==>cq thread ==>scsi_eh_6 ==>scsi_error_handler() ==>sas_eh_handle_sas_errors() ==>sas_scsi_find_task() ==>lldd_abort_task() ==>slot_complete_v3_hw() ==>hisi_sas_abort_task() ==>hisi_sas_slot_task_free() ==>dereg_device_v3_hw() ==>list_del_init() ==>list_for_each_entry_safe() [ 7165.434918] sas: Enter sas_scsi_recover_host busy: 32 failed: 32 [ 7165.434926] sas: trying to find task 0x00000000769b5ba5 [ 7165.434927] sas: sas_scsi_find_task: aborting task 0x00000000769b5ba5 [ 7165.434940] hisi_sas_v3_hw 0000:b4:02.0: slot complete: task(00000000769b5ba5) aborted [ 7165.434964] hisi_sas_v3_hw 0000:b4:02.0: slot complete: task(00000000c9f7aa07) ignored [ 7165.434965] hisi_sas_v3_hw 0000:b4:02.0: slot complete: task(00000000e2a1cf01) ignored [ 7165.434968] Unable to handle kernel NULL pointer dereference at virtual address 0000000000000000 [ 7165.434972] hisi_sas_v3_hw 0000:b4:02.0: slot complete: task(0000000022d52d93) ignored [ 7165.434975] hisi_sas_v3_hw 0000:b4:02.0: slot complete: task(0000000066a7516c) ignored [ 7165.434976] Mem abort info: [ 7165.434982] ESR = 0x96000004 [ 7165.434991] Exception class = DABT (current EL), IL = 32 bits [ 7165.434992] SET = 0, FnV = 0 [ 7165.434993] EA = 0, S1PTW = 0 [ 7165.434994] Data abort info: [ 7165.434994] ISV = 0, ISS = 0x00000004 [ 7165.434995] CM = 0, WnR = 0 [ 7165.434997] user pgtable: 4k pages, 48-bit VAs, pgdp = 00000000f29543f2 [ 7165.434998] [0000000000000000] pgd=0000000000000000 [ 7165.435003] Internal error: Oops: 96000004 [#1] SMP [ 7165.439863] Process scsi_eh_6 (pid: 4109, stack limit = 0x00000000c43818d5) [ 7165.468862] pstate: 00c00009 (nzcv daif +PAN +UAO) [ 7165.473637] pc : dereg_device_v3_hw+0x68/0xa8 [hisi_sas_v3_hw] [ 7165.479443] lr : dereg_device_v3_hw+0x2c/0xa8 [hisi_sas_v3_hw] [ 7165.485247] sp : ffff00001d623bc0 [ 7165.488546] x29: ffff00001d623bc0 x28: ffffa027d03b9508 [ 7165.493835] x27: ffff80278ed50af0 x26: ffffa027dd31e0a8 [ 7165.499123] x25: ffffa027d9b27f88 x24: ffffa027d9b209f8 [ 7165.504411] x23: ffffa027c45b0d60 x22: ffff80278ec07c00 [ 7165.509700] x21: 0000000000000008 x20: ffffa027d9b209f8 [ 7165.514988] x19: ffffa027d9b27f88 x18: ffffffffffffffff [ 7165.520276] x17: 0000000000000000 x16: 0000000000000000 [ 7165.525564] x15: ffff0000091d9708 x14: ffff0000093b7dc8 [ 7165.530852] x13: ffff0000093b7a23 x12: 6e7265746e692067 [ 7165.536140] x11: 0000000000000000 x10: 0000000000000bb0 [ 7165.541429] x9 : ffff00001d6238f0 x8 : ffffa027d877af00 [ 7165.546718] x7 : ffffa027d6329600 x6 : ffff7e809f58ca00 [ 7165.552006] x5 : 0000000000001f8a x4 : 000000000000088e [ 7165.557295] x3 : ffffa027d9b27fa8 x2 : 0000000000000000 [ 7165.562583] x1 : 0000000000000000 x0 : 000000003000188e [ 7165.567872] Call trace: [ 7165.570309] dereg_device_v3_hw+0x68/0xa8 [hisi_sas_v3_hw] [ 7165.575775] hisi_sas_abort_task+0x248/0x358 [hisi_sas_main] [ 7165.581415] sas_eh_handle_sas_errors+0x258/0x8e0 [libsas] [ 7165.586876] sas_scsi_recover_host+0x134/0x458 [libsas] [ 7165.592082] scsi_error_handler+0xb4/0x488 [ 7165.596163] kthread+0x134/0x138 [ 7165.599380] ret_from_fork+0x10/0x18 [ 7165.602940] Code: d5033e9f b9000040 aa0103e2 eb03003f (f9400021) [ 7165.609004] kernel fault(0x1) notification starting on CPU 75 [ 7165.700728] ---[ end trace fc042cbbea224efc ]--- [ 7165.705326] Kernel panic - not syncing: Fatal exception So grab sas_dev lock when traversing the members of sas_dev.list in dereg_device_v3_hw() and hisi_sas_release_tasks() to avoid concurrency of adding and deleting member, which may cause an exception. And when hisi_sas_release_tasks() call hisi_sas_do_release_task() to free slot, the lock cannot be grabbed again in hisi_sas_slot_task_free(), then a bool parameter need_lock is added. Signed-off-by: Xingui Yang <yangxingui(a)huawei.com> Reviewed-by: kang fenglong <kangfenglong(a)huawei.com> Signed-off-by: Yongqiang Liu <liuyongqiang13(a)huawei.com> --- drivers/scsi/hisi_sas/hisi_sas.h | 3 ++- drivers/scsi/hisi_sas/hisi_sas_main.c | 26 +++++++++++++++++--------- drivers/scsi/hisi_sas/hisi_sas_v1_hw.c | 2 +- drivers/scsi/hisi_sas/hisi_sas_v2_hw.c | 2 +- drivers/scsi/hisi_sas/hisi_sas_v3_hw.c | 5 ++++- 5 files changed, 25 insertions(+), 13 deletions(-) diff --git a/drivers/scsi/hisi_sas/hisi_sas.h b/drivers/scsi/hisi_sas/hisi_sas.h index 533408277156..2880e4e22a73 100644 --- a/drivers/scsi/hisi_sas/hisi_sas.h +++ b/drivers/scsi/hisi_sas/hisi_sas.h @@ -601,7 +601,8 @@ extern void hisi_sas_phy_enable(struct hisi_hba *hisi_hba, int phy_no, extern void hisi_sas_phy_down(struct hisi_hba *hisi_hba, int phy_no, int rdy); extern void hisi_sas_slot_task_free(struct hisi_hba *hisi_hba, struct sas_task *task, - struct hisi_sas_slot *slot); + struct hisi_sas_slot *slot, + bool need_lock); extern void hisi_sas_init_mem(struct hisi_hba *hisi_hba); extern void hisi_sas_rst_work_handler(struct work_struct *work); extern void hisi_sas_sync_rst_work_handler(struct work_struct *work); diff --git a/drivers/scsi/hisi_sas/hisi_sas_main.c b/drivers/scsi/hisi_sas/hisi_sas_main.c index e6ccaedcd8b9..b00bf3b0f418 100644 --- a/drivers/scsi/hisi_sas/hisi_sas_main.c +++ b/drivers/scsi/hisi_sas/hisi_sas_main.c @@ -229,7 +229,7 @@ static void hisi_sas_slot_index_init(struct hisi_hba *hisi_hba) } void hisi_sas_slot_task_free(struct hisi_hba *hisi_hba, struct sas_task *task, - struct hisi_sas_slot *slot) + struct hisi_sas_slot *slot, bool need_lock) { unsigned long flags; int device_id = slot->device_id; @@ -260,9 +260,13 @@ void hisi_sas_slot_task_free(struct hisi_hba *hisi_hba, struct sas_task *task, } } - spin_lock_irqsave(&sas_dev->lock, flags); - list_del_init(&slot->entry); - spin_unlock_irqrestore(&sas_dev->lock, flags); + if (need_lock) { + spin_lock_irqsave(&sas_dev->lock, flags); + list_del_init(&slot->entry); + spin_unlock_irqrestore(&sas_dev->lock, flags); + } else { + list_del_init(&slot->entry); + } memset(slot, 0, offsetof(struct hisi_sas_slot, buf)); @@ -989,7 +993,7 @@ static void hisi_sas_port_notify_formed(struct asd_sas_phy *sas_phy) } static void hisi_sas_do_release_task(struct hisi_hba *hisi_hba, struct sas_task *task, - struct hisi_sas_slot *slot) + struct hisi_sas_slot *slot, bool need_lock) { if (task) { unsigned long flags; @@ -1011,7 +1015,7 @@ static void hisi_sas_do_release_task(struct hisi_hba *hisi_hba, struct sas_task task->task_done(task); } - hisi_sas_slot_task_free(hisi_hba, task, slot); + hisi_sas_slot_task_free(hisi_hba, task, slot, need_lock); } static void hisi_sas_release_task(struct hisi_hba *hisi_hba, @@ -1019,9 +1023,13 @@ static void hisi_sas_release_task(struct hisi_hba *hisi_hba, { struct hisi_sas_slot *slot, *slot2; struct hisi_sas_device *sas_dev = device->lldd_dev; + unsigned long flags; + spin_lock_irqsave(&sas_dev->lock, flags); list_for_each_entry_safe(slot, slot2, &sas_dev->list, entry) - hisi_sas_do_release_task(hisi_hba, slot->task, slot); + hisi_sas_do_release_task(hisi_hba, slot->task, slot, false); + + spin_unlock_irqrestore(&sas_dev->lock, flags); } void hisi_sas_release_tasks(struct hisi_hba *hisi_hba) @@ -1701,7 +1709,7 @@ static int hisi_sas_abort_task(struct sas_task *task) */ if (rc == TMF_RESP_FUNC_COMPLETE && rc2 != TMF_RESP_FUNC_SUCC) { if (task->lldd_task) - hisi_sas_do_release_task(hisi_hba, task, slot); + hisi_sas_do_release_task(hisi_hba, task, slot, true); } } else if (task->task_proto & SAS_PROTOCOL_SATA || task->task_proto & SAS_PROTOCOL_STP) { @@ -1722,7 +1730,7 @@ static int hisi_sas_abort_task(struct sas_task *task) */ if ((sas_dev->dev_status == HISI_SAS_DEV_NCQ_ERR) && qc && qc->scsicmd) { - hisi_sas_do_release_task(hisi_hba, task, slot); + hisi_sas_do_release_task(hisi_hba, task, slot, true); rc = TMF_RESP_FUNC_COMPLETE; } else { rc = hisi_sas_softreset_ata_disk(device); diff --git a/drivers/scsi/hisi_sas/hisi_sas_v1_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v1_hw.c index 452665c641a6..6485e2b6456c 100644 --- a/drivers/scsi/hisi_sas/hisi_sas_v1_hw.c +++ b/drivers/scsi/hisi_sas/hisi_sas_v1_hw.c @@ -1320,7 +1320,7 @@ static int slot_complete_v1_hw(struct hisi_hba *hisi_hba, } out: - hisi_sas_slot_task_free(hisi_hba, task, slot); + hisi_sas_slot_task_free(hisi_hba, task, slot, true); sts = ts->stat; if (task->task_done) diff --git a/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c index 46d274582684..2df70c4873f5 100644 --- a/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c +++ b/drivers/scsi/hisi_sas/hisi_sas_v2_hw.c @@ -2480,7 +2480,7 @@ slot_complete_v2_hw(struct hisi_hba *hisi_hba, struct hisi_sas_slot *slot) } task->task_state_flags |= SAS_TASK_STATE_DONE; spin_unlock_irqrestore(&task->task_state_lock, flags); - hisi_sas_slot_task_free(hisi_hba, task, slot); + hisi_sas_slot_task_free(hisi_hba, task, slot, true); if (!is_internal && (task->task_proto != SAS_PROTOCOL_SMP)) { spin_lock_irqsave(&device->done_lock, flags); diff --git a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c index 77f451040c4c..de88dead4b72 100644 --- a/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c +++ b/drivers/scsi/hisi_sas/hisi_sas_v3_hw.c @@ -914,9 +914,11 @@ static void dereg_device_v3_hw(struct hisi_hba *hisi_hba, struct hisi_sas_slot *slot, *slot2; struct hisi_sas_device *sas_dev = device->lldd_dev; u32 cfg_abt_set_query_iptt; + unsigned long flags; cfg_abt_set_query_iptt = hisi_sas_read32(hisi_hba, CFG_ABT_SET_QUERY_IPTT); + spin_lock_irqsave(&sas_dev->lock, flags); list_for_each_entry_safe(slot, slot2, &sas_dev->list, entry) { cfg_abt_set_query_iptt &= ~CFG_SET_ABORTED_IPTT_MSK; cfg_abt_set_query_iptt |= (1 << CFG_SET_ABORTED_EN_OFF) | @@ -924,6 +926,7 @@ static void dereg_device_v3_hw(struct hisi_hba *hisi_hba, hisi_sas_write32(hisi_hba, CFG_ABT_SET_QUERY_IPTT, cfg_abt_set_query_iptt); } + spin_unlock_irqrestore(&sas_dev->lock, flags); cfg_abt_set_query_iptt &= ~(1 << CFG_SET_ABORTED_EN_OFF); hisi_sas_write32(hisi_hba, CFG_ABT_SET_QUERY_IPTT, cfg_abt_set_query_iptt); @@ -2558,7 +2561,7 @@ slot_complete_v3_hw(struct hisi_hba *hisi_hba, struct hisi_sas_slot *slot) } task->task_state_flags |= SAS_TASK_STATE_DONE; spin_unlock_irqrestore(&task->task_state_lock, flags); - hisi_sas_slot_task_free(hisi_hba, task, slot); + hisi_sas_slot_task_free(hisi_hba, task, slot, true); if (!is_internal && (task->task_proto != SAS_PROTOCOL_SMP)) { spin_lock_irqsave(&device->done_lock, flags); -- 2.25.1

1 9

[PATCH openEuler-1.0-LTS 1/6] net: tls: fix possible race condition between do_tls_getsockopt_conf() and do_tls_setsockopt_conf()
by Yongqiang Liu 25 Mar '23

25 Mar '23

From: Hangyu Hua <hbh25y(a)gmail.com> mainline inclusion from mainline-v6.3-rc2 commit 49c47cc21b5b7a3d8deb18fc57b0aa2ab1286962 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I6NIUR CVE: CVE-2023-28466 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… --------------------------- ctx->crypto_send.info is not protected by lock_sock in do_tls_getsockopt_conf(). A race condition between do_tls_getsockopt_conf() and error paths of do_tls_setsockopt_conf() may lead to a use-after-free or null-deref. More discussion: https://lore.kernel.org/all/Y/ht6gQL+u6fj3dG@hog/ Fixes: 3c4d7559159b ("tls: kernel TLS support") Signed-off-by: Hangyu Hua <hbh25y(a)gmail.com> Link: https://lore.kernel.org/r/20230228023344.9623-1-hbh25y@gmail.com Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> Signed-off-by: Liu Jian <liujian56(a)huawei.com> Conflicts: net/tls/tls_main.c Reviewed-by: Yue Haibing <yuehaibing(a)huawei.com> Reviewed-by: Wang Weiyang <wangweiyang2(a)huawei.com> Signed-off-by: Yongqiang Liu <liuyongqiang13(a)huawei.com> --- net/tls/tls_main.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c index 3cf4916c541b..19646ef9f6f6 100644 --- a/net/tls/tls_main.c +++ b/net/tls/tls_main.c @@ -364,13 +364,11 @@ static int do_tls_getsockopt_tx(struct sock *sk, char __user *optval, rc = -EINVAL; goto out; } - lock_sock(sk); memcpy(crypto_info_aes_gcm_128->iv, ctx->tx.iv + TLS_CIPHER_AES_GCM_128_SALT_SIZE, TLS_CIPHER_AES_GCM_128_IV_SIZE); memcpy(crypto_info_aes_gcm_128->rec_seq, ctx->tx.rec_seq, TLS_CIPHER_AES_GCM_128_REC_SEQ_SIZE); - release_sock(sk); if (copy_to_user(optval, crypto_info_aes_gcm_128, sizeof(*crypto_info_aes_gcm_128))) @@ -390,6 +388,8 @@ static int do_tls_getsockopt(struct sock *sk, int optname, { int rc = 0; + lock_sock(sk); + switch (optname) { case TLS_TX: rc = do_tls_getsockopt_tx(sk, optval, optlen); @@ -398,6 +398,9 @@ static int do_tls_getsockopt(struct sock *sk, int optname, rc = -ENOPROTOOPT; break; } + + release_sock(sk); + return rc; } -- 2.25.1

1 5

[PATCH openEuler-1.0-LTS] wifi: brcmfmac: slab-out-of-bounds read in brcmf_get_assoc_ies()
by Yongqiang Liu 23 Mar '23

23 Mar '23

From: Jisoo Jang <jisoo.jang(a)yonsei.ac.kr> maillist inclusion category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I6NCVX CVE: CVE-2023-1380 Reference: https://patchwork.kernel.org/project/linux-wireless/patch/20230309104457.22… -------------------------------- Fix a slab-out-of-bounds read that occurs in kmemdup() called from brcmf_get_assoc_ies(). The bug could occur when assoc_info->req_len, data from a URB provided by a USB device, is bigger than the size of buffer which is defined as WL_EXTRA_BUF_MAX. Add the size check for req_len/resp_len of assoc_info. Found by a modified version of syzkaller. [ 46.592467][ T7] ================================================================== [ 46.594687][ T7] BUG: KASAN: slab-out-of-bounds in kmemdup+0x3e/0x50 [ 46.596572][ T7] Read of size 3014656 at addr ffff888019442000 by task kworker/0:1/7 [ 46.598575][ T7] [ 46.599157][ T7] CPU: 0 PID: 7 Comm: kworker/0:1 Tainted: G O 5.14.0+ #145 [ 46.601333][ T7] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.12.1-0-ga5cab58e9a3f-prebuilt.qemu.org 04/01/2014 [ 46.604360][ T7] Workqueue: events brcmf_fweh_event_worker [ 46.605943][ T7] Call Trace: [ 46.606584][ T7] dump_stack_lvl+0x8e/0xd1 [ 46.607446][ T7] print_address_description.constprop.0.cold+0x93/0x334 [ 46.608610][ T7] ? kmemdup+0x3e/0x50 [ 46.609341][ T7] kasan_report.cold+0x79/0xd5 [ 46.610151][ T7] ? kmemdup+0x3e/0x50 [ 46.610796][ T7] kasan_check_range+0x14e/0x1b0 [ 46.611691][ T7] memcpy+0x20/0x60 [ 46.612323][ T7] kmemdup+0x3e/0x50 [ 46.612987][ T7] brcmf_get_assoc_ies+0x967/0xf60 [ 46.613904][ T7] ? brcmf_notify_vif_event+0x3d0/0x3d0 [ 46.614831][ T7] ? lock_chain_count+0x20/0x20 [ 46.615683][ T7] ? mark_lock.part.0+0xfc/0x2770 [ 46.616552][ T7] ? lock_chain_count+0x20/0x20 [ 46.617409][ T7] ? mark_lock.part.0+0xfc/0x2770 [ 46.618244][ T7] ? lock_chain_count+0x20/0x20 [ 46.619024][ T7] brcmf_bss_connect_done.constprop.0+0x241/0x2e0 [ 46.620019][ T7] ? brcmf_parse_configure_security.isra.0+0x2a0/0x2a0 [ 46.620818][ T7] ? __lock_acquire+0x181f/0x5790 [ 46.621462][ T7] brcmf_notify_connect_status+0x448/0x1950 [ 46.622134][ T7] ? rcu_read_lock_bh_held+0xb0/0xb0 [ 46.622736][ T7] ? brcmf_cfg80211_join_ibss+0x7b0/0x7b0 [ 46.623390][ T7] ? find_held_lock+0x2d/0x110 [ 46.623962][ T7] ? brcmf_fweh_event_worker+0x19f/0xc60 [ 46.624603][ T7] ? mark_held_locks+0x9f/0xe0 [ 46.625145][ T7] ? lockdep_hardirqs_on_prepare+0x3e0/0x3e0 [ 46.625871][ T7] ? brcmf_cfg80211_join_ibss+0x7b0/0x7b0 [ 46.626545][ T7] brcmf_fweh_call_event_handler.isra.0+0x90/0x100 [ 46.627338][ T7] brcmf_fweh_event_worker+0x557/0xc60 [ 46.627962][ T7] ? brcmf_fweh_call_event_handler.isra.0+0x100/0x100 [ 46.628736][ T7] ? rcu_read_lock_sched_held+0xa1/0xd0 [ 46.629396][ T7] ? rcu_read_lock_bh_held+0xb0/0xb0 [ 46.629970][ T7] ? lockdep_hardirqs_on_prepare+0x273/0x3e0 [ 46.630649][ T7] process_one_work+0x92b/0x1460 [ 46.631205][ T7] ? pwq_dec_nr_in_flight+0x330/0x330 [ 46.631821][ T7] ? rwlock_bug.part.0+0x90/0x90 [ 46.632347][ T7] worker_thread+0x95/0xe00 [ 46.632832][ T7] ? __kthread_parkme+0x115/0x1e0 [ 46.633393][ T7] ? process_one_work+0x1460/0x1460 [ 46.633957][ T7] kthread+0x3a1/0x480 [ 46.634369][ T7] ? set_kthread_struct+0x120/0x120 [ 46.634933][ T7] ret_from_fork+0x1f/0x30 [ 46.635431][ T7] [ 46.635687][ T7] Allocated by task 7: [ 46.636151][ T7] kasan_save_stack+0x1b/0x40 [ 46.636628][ T7] __kasan_kmalloc+0x7c/0x90 [ 46.637108][ T7] kmem_cache_alloc_trace+0x19e/0x330 [ 46.637696][ T7] brcmf_cfg80211_attach+0x4a0/0x4040 [ 46.638275][ T7] brcmf_attach+0x389/0xd40 [ 46.638739][ T7] brcmf_usb_probe+0x12de/0x1690 [ 46.639279][ T7] usb_probe_interface+0x2aa/0x760 [ 46.639820][ T7] really_probe+0x205/0xb70 [ 46.640342][ T7] __driver_probe_device+0x311/0x4b0 [ 46.640876][ T7] driver_probe_device+0x4e/0x150 [ 46.641445][ T7] __device_attach_driver+0x1cc/0x2a0 [ 46.642000][ T7] bus_for_each_drv+0x156/0x1d0 [ 46.642543][ T7] __device_attach+0x23f/0x3a0 [ 46.643065][ T7] bus_probe_device+0x1da/0x290 [ 46.643644][ T7] device_add+0xb7b/0x1eb0 [ 46.644130][ T7] usb_set_configuration+0xf59/0x16f0 [ 46.644720][ T7] usb_generic_driver_probe+0x82/0xa0 [ 46.645295][ T7] usb_probe_device+0xbb/0x250 [ 46.645786][ T7] really_probe+0x205/0xb70 [ 46.646258][ T7] __driver_probe_device+0x311/0x4b0 [ 46.646804][ T7] driver_probe_device+0x4e/0x150 [ 46.647387][ T7] __device_attach_driver+0x1cc/0x2a0 [ 46.647926][ T7] bus_for_each_drv+0x156/0x1d0 [ 46.648454][ T7] __device_attach+0x23f/0x3a0 [ 46.648939][ T7] bus_probe_device+0x1da/0x290 [ 46.649478][ T7] device_add+0xb7b/0x1eb0 [ 46.649936][ T7] usb_new_device.cold+0x49c/0x1029 [ 46.650526][ T7] hub_event+0x1c98/0x3950 [ 46.650975][ T7] process_one_work+0x92b/0x1460 [ 46.651535][ T7] worker_thread+0x95/0xe00 [ 46.651991][ T7] kthread+0x3a1/0x480 [ 46.652413][ T7] ret_from_fork+0x1f/0x30 [ 46.652885][ T7] [ 46.653131][ T7] The buggy address belongs to the object at ffff888019442000 [ 46.653131][ T7] which belongs to the cache kmalloc-2k of size 2048 [ 46.654669][ T7] The buggy address is located 0 bytes inside of [ 46.654669][ T7] 2048-byte region [ffff888019442000, ffff888019442800) [ 46.656137][ T7] The buggy address belongs to the page: [ 46.656720][ T7] page:ffffea0000651000 refcount:1 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x19440 [ 46.657792][ T7] head:ffffea0000651000 order:3 compound_mapcount:0 compound_pincount:0 [ 46.658673][ T7] flags: 0x100000000010200(slab|head|node=0|zone=1) [ 46.659422][ T7] raw: 0100000000010200 0000000000000000 dead000000000122 ffff888100042000 [ 46.660363][ T7] raw: 0000000000000000 0000000000080008 00000001ffffffff 0000000000000000 [ 46.661236][ T7] page dumped because: kasan: bad access detected [ 46.661956][ T7] page_owner tracks the page as allocated [ 46.662588][ T7] page last allocated via order 3, migratetype Unmovable, gfp_mask 0x52a20(GFP_ATOMIC|__GFP_NOWARN|__GFP_NORETRY|__GFP_COMP), pid 7, ts 31136961085, free_ts 0 [ 46.664271][ T7] prep_new_page+0x1aa/0x240 [ 46.664763][ T7] get_page_from_freelist+0x159a/0x27c0 [ 46.665340][ T7] __alloc_pages+0x2da/0x6a0 [ 46.665847][ T7] alloc_pages+0xec/0x1e0 [ 46.666308][ T7] allocate_slab+0x380/0x4e0 [ 46.666770][ T7] ___slab_alloc+0x5bc/0x940 [ 46.667264][ T7] __slab_alloc+0x6d/0x80 [ 46.667712][ T7] kmem_cache_alloc_trace+0x30a/0x330 [ 46.668299][ T7] brcmf_usbdev_qinit.constprop.0+0x50/0x470 [ 46.668885][ T7] brcmf_usb_probe+0xc97/0x1690 [ 46.669438][ T7] usb_probe_interface+0x2aa/0x760 [ 46.669988][ T7] really_probe+0x205/0xb70 [ 46.670487][ T7] __driver_probe_device+0x311/0x4b0 [ 46.671031][ T7] driver_probe_device+0x4e/0x150 [ 46.671604][ T7] __device_attach_driver+0x1cc/0x2a0 [ 46.672192][ T7] bus_for_each_drv+0x156/0x1d0 [ 46.672739][ T7] page_owner free stack trace missing [ 46.673335][ T7] [ 46.673620][ T7] Memory state around the buggy address: [ 46.674213][ T7] ffff888019442700: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 [ 46.675083][ T7] ffff888019442780: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 [ 46.675994][ T7] >ffff888019442800: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc [ 46.676875][ T7] ^ [ 46.677323][ T7] ffff888019442880: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc [ 46.678190][ T7] ffff888019442900: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc [ 46.679052][ T7] ================================================================== [ 46.679945][ T7] Disabling lock debugging due to kernel taint [ 46.680725][ T7] Kernel panic - not syncing: Reviewed-by: Arend van Spriel <arend.vanspriel(a)broadcom.com> Signed-off-by: Jisoo Jang <jisoo.jang(a)yonsei.ac.kr> Signed-off-by: Kalle Valo <kvalo(a)kernel.org> Link: https://lore.kernel.org/r/20230309104457.22628-1-jisoo.jang@yonsei.ac.kr Signed-off-by: Baisong Zhong <zhongbaisong(a)huawei.com> Reviewed-by: Liu Jian <liujian56(a)huawei.com> Reviewed-by: Xiu Jianfeng <xiujianfeng(a)huawei.com> Signed-off-by: Yongqiang Liu <liuyongqiang13(a)huawei.com> --- drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c index bbdc6000afb9..4e1bd049dd06 100644 --- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c +++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c @@ -5356,6 +5356,11 @@ static s32 brcmf_get_assoc_ies(struct brcmf_cfg80211_info *cfg, (struct brcmf_cfg80211_assoc_ielen_le *)cfg->extra_buf; req_len = le32_to_cpu(assoc_info->req_len); resp_len = le32_to_cpu(assoc_info->resp_len); + if (req_len > WL_EXTRA_BUF_MAX || resp_len > WL_EXTRA_BUF_MAX) { + brcmf_err("invalid lengths in assoc info: req %u resp %u\n", + req_len, resp_len); + return -EINVAL; + } if (req_len) { err = brcmf_fil_iovar_data_get(ifp, "assoc_req_ies", cfg->extra_buf, -- 2.25.1

1 0

[RFC PATCH openEuler-1.0-LTS v2] sched: memqos: add memqos for dynamic affinity
by Wang ShaoBo 23 Mar '23

23 Mar '23

Add debug memband interface to dynamic affinity, this would be useful for those threads sensitive to memory bandwidth. Signed-off-by: Wang ShaoBo <bobo.shaobowang(a)huawei.com> v2: Fix update thread's mpamid failed. --- arch/arm64/include/asm/mpam.h | 2 + arch/arm64/include/asm/mpam_sched.h | 2 + arch/arm64/kernel/mpam/mpam_device.c | 58 ++- arch/arm64/kernel/mpam/mpam_resctrl.c | 37 ++ arch/arm64/kernel/process.c | 2 +- include/linux/memqos.h | 142 +++++++ include/linux/sched.h | 15 +- include/linux/sysctl.h | 2 + kernel/cgroup/cpuset.c | 1 + kernel/exit.c | 3 + kernel/fork.c | 4 + kernel/sched/Makefile | 1 + kernel/sched/core.c | 52 ++- kernel/sched/fair.c | 14 +- kernel/sched/memqos/Makefile | 6 + kernel/sched/memqos/memqos.c | 297 +++++++++++++++ kernel/sched/memqos/phase_feature_sysctl.c | 183 +++++++++ kernel/sched/memqos/phase_memband.c | 179 +++++++++ kernel/sched/memqos/phase_perf.c | 412 +++++++++++++++++++++ kernel/sched/memqos/phase_sim_knn.c | 92 +++++ kernel/sysctl.c | 7 + mm/mempolicy.c | 10 +- 22 files changed, 1500 insertions(+), 21 deletions(-) create mode 100644 include/linux/memqos.h create mode 100644 kernel/sched/memqos/Makefile create mode 100644 kernel/sched/memqos/memqos.c create mode 100644 kernel/sched/memqos/phase_feature_sysctl.c create mode 100644 kernel/sched/memqos/phase_memband.c create mode 100644 kernel/sched/memqos/phase_perf.c create mode 100644 kernel/sched/memqos/phase_sim_knn.c diff --git a/arch/arm64/include/asm/mpam.h b/arch/arm64/include/asm/mpam.h index 6338eab817e75..269a91d8ca907 100644 --- a/arch/arm64/include/asm/mpam.h +++ b/arch/arm64/include/asm/mpam.h @@ -4,6 +4,8 @@ #ifdef CONFIG_MPAM extern int mpam_rmid_to_partid_pmg(int rmid, int *partid, int *pmg); + +void mpam_component_config_mbwu_mon(int partid, int pmg, int monitor, int *result, int nr); #endif #endif /* _ASM_ARM64_MPAM_H */ diff --git a/arch/arm64/include/asm/mpam_sched.h b/arch/arm64/include/asm/mpam_sched.h index 08ed349b6efa1..32d08cf654b31 100644 --- a/arch/arm64/include/asm/mpam_sched.h +++ b/arch/arm64/include/asm/mpam_sched.h @@ -40,6 +40,8 @@ static inline void mpam_sched_in(void) __mpam_sched_in(); } +void __mpam_sched_in_v2(struct task_struct *tsk); + #else static inline void mpam_sched_in(void) {} diff --git a/arch/arm64/kernel/mpam/mpam_device.c b/arch/arm64/kernel/mpam/mpam_device.c index 6455c69f132fd..48de3982a0b9a 100644 --- a/arch/arm64/kernel/mpam/mpam_device.c +++ b/arch/arm64/kernel/mpam/mpam_device.c @@ -84,14 +84,14 @@ void mpam_class_list_lock_held(void) static inline u32 mpam_read_reg(struct mpam_device *dev, u16 reg) { WARN_ON_ONCE(reg > SZ_MPAM_DEVICE); - assert_spin_locked(&dev->lock); + //assert_spin_locked(&dev->lock); /* * If we touch a device that isn't accessible from this CPU we may get * an external-abort. */ - WARN_ON_ONCE(preemptible()); - WARN_ON_ONCE(!cpumask_test_cpu(smp_processor_id(), &dev->fw_affinity)); + //WARN_ON_ONCE(preemptible()); + //WARN_ON_ONCE(!cpumask_test_cpu(smp_processor_id(), &dev->fw_affinity)); return readl_relaxed(dev->mapped_hwpage + reg); } @@ -99,14 +99,14 @@ static inline u32 mpam_read_reg(struct mpam_device *dev, u16 reg) static inline void mpam_write_reg(struct mpam_device *dev, u16 reg, u32 val) { WARN_ON_ONCE(reg > SZ_MPAM_DEVICE); - assert_spin_locked(&dev->lock); + //assert_spin_locked(&dev->lock); /* * If we touch a device that isn't accessible from this CPU we may get * an external-abort. If we're lucky, we corrupt another mpam:component. */ - WARN_ON_ONCE(preemptible()); - WARN_ON_ONCE(!cpumask_test_cpu(smp_processor_id(), &dev->fw_affinity)); + //WARN_ON_ONCE(preemptible()); + //WARN_ON_ONCE(!cpumask_test_cpu(smp_processor_id(), &dev->fw_affinity)); writel_relaxed(val, dev->mapped_hwpage + reg); } @@ -1208,6 +1208,7 @@ static u32 mpam_device_read_mbwu_mon(struct mpam_device *dev, { u16 mon; u32 clt, flt, cur_clt, cur_flt; + u32 total = 0; mon = args->mon; @@ -1249,7 +1250,12 @@ static u32 mpam_device_read_mbwu_mon(struct mpam_device *dev, wmb(); } - return mpam_read_reg(dev, MSMON_MBWU); + total += mpam_read_reg(dev, MSMON_MBWU); + total += mpam_read_reg(dev, MSMON_MBWU); + total += mpam_read_reg(dev, MSMON_MBWU); + total += mpam_read_reg(dev, MSMON_MBWU); + total += mpam_read_reg(dev, MSMON_MBWU); + return total / 5; } static int mpam_device_frob_mon(struct mpam_device *dev, @@ -1470,6 +1476,44 @@ static void mpam_component_device_sync(void *__ctx) cpumask_set_cpu(smp_processor_id(), &ctx->updated_on); } +static DEFINE_SPINLOCK(mpam_tmp_lock); + +void mpam_component_config_mbwu_mon(int partid, int pmg, int monitor, int *result, int nr) +{ + struct mpam_class *class; + struct mpam_component *comp; + struct mpam_device *dev; + struct sync_args args; + int i = 0; + + args.pmg = pmg; + args.mon = monitor; + args.closid.reqpartid = partid; + args.match_pmg = 1; + + spin_lock(&mpam_tmp_lock); + list_for_each_entry(class, &mpam_classes, classes_list) { + if (class->type != MPAM_CLASS_MEMORY) + continue; + + list_for_each_entry(comp, &class->components, class_list) { + if (i >= nr) { + pr_err_once("error, i > result nr"); + break; + } + result[i] = 0; + list_for_each_entry(dev, &comp->devices, comp_list) { + result[i] += mpam_device_read_mbwu_mon(dev, &args); + } + i++; + } + break; + } + spin_unlock(&mpam_tmp_lock); + +} +EXPORT_SYMBOL(mpam_component_config_mbwu_mon); + /** * in some cases/platforms the MSC register access is only possible with * the associated CPUs. And need to check if those CPUS are online before diff --git a/arch/arm64/kernel/mpam/mpam_resctrl.c b/arch/arm64/kernel/mpam/mpam_resctrl.c index 60d3d8706a38b..26258f7508ac4 100644 --- a/arch/arm64/kernel/mpam/mpam_resctrl.c +++ b/arch/arm64/kernel/mpam/mpam_resctrl.c @@ -2226,6 +2226,43 @@ int mpam_resctrl_init(void) return resctrl_group_init(); } + +void __mpam_sched_in_v2(struct task_struct *tsk) +{ + struct intel_pqr_state *state = this_cpu_ptr(&pqr_state); + u64 rmid = state->default_rmid; + u64 closid = state->default_closid; + + /* + * If this task has a closid/rmid assigned, use it. + * Else use the closid/rmid assigned to this cpu. + */ + if (tsk->closid) + closid = tsk->closid; + + if (tsk->rmid) + rmid = tsk->rmid; + + if (closid != state->cur_closid || rmid != state->cur_rmid) { + u64 reg; + + /* set in EL0 */ + reg = mpam_read_sysreg_s(SYS_MPAM0_EL1, "SYS_MPAM0_EL1"); + reg = PARTID_SET(reg, closid); + reg = PMG_SET(reg, rmid); + mpam_write_sysreg_s(reg, SYS_MPAM0_EL1, "SYS_MPAM0_EL1"); + + /* set in EL1 */ + reg = mpam_read_sysreg_s(SYS_MPAM1_EL1, "SYS_MPAM1_EL1"); + reg = PARTID_SET(reg, closid); + reg = PMG_SET(reg, rmid); + mpam_write_sysreg_s(reg, SYS_MPAM1_EL1, "SYS_MPAM1_EL1"); + + state->cur_rmid = rmid; + state->cur_closid = closid; + } +} + /* * __intel_rdt_sched_in() - Writes the task's CLOSid/RMID to IA32_PQR_MSR * diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c index e5be78915632c..7896bb74ecc49 100644 --- a/arch/arm64/kernel/process.c +++ b/arch/arm64/kernel/process.c @@ -531,7 +531,7 @@ __notrace_funcgraph struct task_struct *__switch_to(struct task_struct *prev, /* the actual thread switch */ last = cpu_switch_to(prev, next); - mpam_sched_in(); + //mpam_sched_in(); return last; } diff --git a/include/linux/memqos.h b/include/linux/memqos.h new file mode 100644 index 0000000000000..814e9935590d3 --- /dev/null +++ b/include/linux/memqos.h @@ -0,0 +1,142 @@ +#ifndef _MEMQOS_H +#define _MEMQOS_H + +#include <linux/vmstat.h> +#include <linux/rbtree.h> +//#include <linux/sched.h> + +struct task_struct; + +struct memqos_domain { + int dom_id; + int total_memband_div_10; + int total_out_memband_div_10; + + //record 10 timers + int memband_ringpos; + int memband_div_10_history[4][10]; +}; + +struct memqos_mpam_profile { + int partid; + int pmg; + int monitor; + + struct task_struct *tsk; + int used; +}; + +struct memqos_wait_profile { + struct memqos_mpam_profile *profile; + struct list_head wait_list; +}; + +struct memqos_class { + struct list_head turbo_list; + struct list_head tasks_list; +}; + +#include <linux/topology.h> +//embed in task_struct + +struct task_memqos { + int ipc_ringpos; + int ipcx10; + int ipcx10_total[4]; + int ipcx10_history[10]; + + int memband_div_10; + int memband_ringpos; + int memband_div_10_total[4]; + int memband_div_10_history[4][10]; + + u32 sample_times; + int account_ready; + int numa_score[4]; + int turbo; + + struct memqos_wait_profile mpam_profile; + + struct list_head turbo_list; + struct list_head task_list; + + struct cpumask *advise_mem_node_mask; + int preferred_nid; + + int class_id; + + int corrupt; +}; + +#define PHASE_PEVENT_NUM 10 + +struct phase_event_pcount { + u64 data[PHASE_PEVENT_NUM]; +}; + +struct phase_event_count { + struct phase_event_pcount pcount; +}; + +void phase_update_mpam_label(struct task_struct *tsk); + +void phase_release_mpam_label(struct task_struct *tsk); + +static inline void memqos_update_mpam_label(struct task_struct *tsk) +{ + phase_update_mpam_label(tsk); +} + +static inline void memqos_release_mpam_label(struct task_struct *tsk) +{ + phase_release_mpam_label(tsk); +} + +void phase_destroy_waitqueue(struct task_struct *tsk); + +void phase_get_memband(struct memqos_mpam_profile *pm, int *result, int nr); + +DECLARE_STATIC_KEY_FALSE(sched_phase); +DECLARE_STATIC_KEY_FALSE(sched_phase_printk); + +int phase_perf_create(void); + +void phase_perf_release(void); + +void memqos_account_task(struct task_struct *p, int cpu); + +void memqos_drop_class(struct task_struct *p); + +void phase_account_task(struct task_struct *p, int cpu); + +static inline void memqos_task_collect_data(struct task_struct *p, int cpu) +{ + phase_account_task(p, cpu); +} + +static inline void memqos_task_account(struct task_struct *p, int cpu) +{ + memqos_account_task(p, cpu); +} + +static inline void memqos_task_exit(struct task_struct *p) +{ + + memqos_drop_class(p); + phase_destroy_waitqueue(p); +} + +void memqos_select_nicest_cpus(struct task_struct *p); + +void memqos_exclude_low_level_task_single(struct task_struct *p); + +int knn_get_tag(int ipcx10, int memband_div_10); + +void memqos_init_class(struct task_struct *p); + +void phase_trace_printk(struct task_struct *p); +static inline void memqos_trace_printk(struct task_struct *p) +{ + phase_trace_printk(p); +} +#endif diff --git a/include/linux/sched.h b/include/linux/sched.h index 928186f161000..c5b74cd0c5830 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -29,6 +29,7 @@ #include <linux/task_io_accounting.h> #include <linux/rseq.h> #include <linux/thread_bits.h> +#include <linux/memqos.h> /* task_struct member predeclarations (sorted alphabetically): */ struct audit_context; @@ -1268,7 +1269,7 @@ struct task_struct { #if !defined(__GENKSYMS__) #if defined(CONFIG_QOS_SCHED_DYNAMIC_AFFINITY) cpumask_t *prefer_cpus; - const cpumask_t *select_cpus; + cpumask_t *select_cpus; #else KABI_RESERVE(6) KABI_RESERVE(7) @@ -1279,6 +1280,10 @@ struct task_struct { #endif KABI_RESERVE(8) +#ifdef CONFIG_QOS_SCHED_DYNAMIC_AFFINITY + struct task_memqos sched_memqos; +#endif + /* CPU-specific state of this task: */ struct thread_struct thread; @@ -1998,6 +2003,14 @@ int set_prefer_cpus_ptr(struct task_struct *p, const struct cpumask *new_mask); int sched_prefer_cpus_fork(struct task_struct *p, struct task_struct *orig); void sched_prefer_cpus_free(struct task_struct *p); +static inline bool prefer_cpus_valid(struct task_struct *p) +{ + return p->prefer_cpus && + !cpumask_empty(p->prefer_cpus) && + !cpumask_equal(p->prefer_cpus, &p->cpus_allowed) && + cpumask_subset(p->prefer_cpus, &p->cpus_allowed); +} +void sched_memqos_task_collect_data_range(int start_cpu, int end_cpu); #endif #endif diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h index b769ecfcc3bd4..73bce39107cb3 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -230,6 +230,8 @@ static inline void setup_sysctl_set(struct ctl_table_set *p, #endif /* CONFIG_SYSCTL */ +extern struct ctl_table phase_table[]; + int sysctl_max_threads(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos); diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index 55bfbc4cdb16c..d94a9065a5605 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -106,6 +106,7 @@ struct cpuset { nodemask_t mems_allowed; #ifdef CONFIG_QOS_SCHED_DYNAMIC_AFFINITY cpumask_var_t prefer_cpus; + int mem_turbo; #endif /* effective CPUs and Memory Nodes allow to tasks */ diff --git a/kernel/exit.c b/kernel/exit.c index 2a32d32bdc03d..b731c19618176 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -699,6 +699,8 @@ static void check_stack_usage(void) static inline void check_stack_usage(void) {} #endif +#include <linux/memqos.h> + void __noreturn do_exit(long code) { struct task_struct *tsk = current; @@ -806,6 +808,7 @@ void __noreturn do_exit(long code) * because of cgroup mode, must be called before cgroup_exit() */ perf_event_exit_task(tsk); + memqos_task_exit(tsk); sched_autogroup_exit_task(tsk); cgroup_exit(tsk); diff --git a/kernel/fork.c b/kernel/fork.c index b5453a26655e2..0a762b92dc814 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -841,6 +841,8 @@ void set_task_stack_end_magic(struct task_struct *tsk) *stackend = STACK_END_MAGIC; /* for overflow detection */ } + +#include <linux/memqos.h> static struct task_struct *dup_task_struct(struct task_struct *orig, int node) { struct task_struct *tsk; @@ -923,6 +925,8 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node) kcov_task_init(tsk); + memqos_init_class(tsk); + #ifdef CONFIG_FAULT_INJECTION tsk->fail_nth = 0; #endif diff --git a/kernel/sched/Makefile b/kernel/sched/Makefile index 7fe183404c383..471380d6686e3 100644 --- a/kernel/sched/Makefile +++ b/kernel/sched/Makefile @@ -29,3 +29,4 @@ obj-$(CONFIG_CPU_FREQ) += cpufreq.o obj-$(CONFIG_CPU_FREQ_GOV_SCHEDUTIL) += cpufreq_schedutil.o obj-$(CONFIG_MEMBARRIER) += membarrier.o obj-$(CONFIG_CPU_ISOLATION) += isolation.o +obj-$(CONFIG_QOS_SCHED_DYNAMIC_AFFINITY) += memqos/ diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 970616070da86..15c7e1e3408cb 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -2787,6 +2787,8 @@ asmlinkage __visible void schedule_tail(struct task_struct *prev) calculate_sigpending(); } +#include <linux/memqos.h> + /* * context_switch - switch to the new MM and the new thread's register state. */ @@ -2794,6 +2796,8 @@ static __always_inline struct rq * context_switch(struct rq *rq, struct task_struct *prev, struct task_struct *next, struct rq_flags *rf) { + struct rq *ret; + prepare_task_switch(rq, prev, next); /* @@ -2837,6 +2841,18 @@ context_switch(struct rq *rq, struct task_struct *prev, } } + //account and release + memqos_task_account(prev, smp_processor_id()); + + if (prefer_cpus_valid(prev)) + memqos_trace_printk(prev); + + memqos_release_mpam_label(prev); + + //label new task's mpamid + if (prefer_cpus_valid(next)) + memqos_update_mpam_label(next); + rq->clock_update_flags &= ~(RQCF_ACT_SKIP|RQCF_REQ_SKIP); prepare_lock_switch(rq, next, rf); @@ -2845,7 +2861,9 @@ context_switch(struct rq *rq, struct task_struct *prev, switch_to(prev, next, prev); barrier(); - return finish_task_switch(prev); + ret = finish_task_switch(prev); + + return ret; } /* @@ -3051,6 +3069,20 @@ unsigned long long task_sched_runtime(struct task_struct *p) return ns; } +void sched_memqos_task_collect_data_range(int start_cpu, int end_cpu) +{ + int cpu; + struct task_struct *curr; + struct rq *rq_curr; + + for (cpu = start_cpu; cpu <= end_cpu; cpu++) { + rq_curr = cpu_rq(cpu); + curr = rq_curr->curr; + if (curr && prefer_cpus_valid(curr)) + memqos_task_collect_data(curr, cpu); + } +} + /* * This function gets called by the timer code, with HZ frequency. * We call it with interrupts disabled. @@ -3058,8 +3090,12 @@ unsigned long long task_sched_runtime(struct task_struct *p) void scheduler_tick(void) { int cpu = smp_processor_id(); + //memqos clooect next cpu's memband and perf + //int cpu_memqos = (cpu + 1) % nr_cpu_ids; struct rq *rq = cpu_rq(cpu); + //struct rq *rq_next = cpu_rq(cpu_memqos); struct task_struct *curr = rq->curr; + //struct task_struct *curr_memqos = rq_next->curr; struct rq_flags rf; sched_clock_tick(); @@ -3075,6 +3111,10 @@ void scheduler_tick(void) perf_event_task_tick(); + //only monitor task enabled dynamic affinity + //if (curr_memqos && prefer_cpus_valid(curr_memqos)) + // memqos_task_collect_data(curr_memqos, cpu_memqos); + #ifdef CONFIG_SMP rq->idle_balance = idle_cpu(cpu); trigger_load_balance(rq); @@ -3524,6 +3564,16 @@ static void __sched notrace __schedule(bool preempt) /* Also unlocks the rq: */ rq = context_switch(rq, prev, next, &rf); } else { + memqos_task_account(prev, smp_processor_id()); + + if (prefer_cpus_valid(prev)) + memqos_trace_printk(prev); + + memqos_release_mpam_label(prev); + //relabel this task's mpamid + if (prefer_cpus_valid(prev)) + memqos_update_mpam_label(prev); + rq->clock_update_flags &= ~(RQCF_ACT_SKIP|RQCF_REQ_SKIP); rq_unlock_irq(rq, &rf); } diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index af55a26d11fcb..12e9675495d2c 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -6675,6 +6675,7 @@ static int wake_cap(struct task_struct *p, int cpu, int prev_cpu) } #ifdef CONFIG_QOS_SCHED_DYNAMIC_AFFINITY +#include <linux/memqos.h> /* * Low utilization threshold for CPU * @@ -6749,14 +6750,6 @@ static inline int cpu_vutil_of(int cpu) return cputime->vutil; } -static inline bool prefer_cpus_valid(struct task_struct *p) -{ - return p->prefer_cpus && - !cpumask_empty(p->prefer_cpus) && - !cpumask_equal(p->prefer_cpus, &p->cpus_allowed) && - cpumask_subset(p->prefer_cpus, &p->cpus_allowed); -} - /* * set_task_select_cpus: select the cpu range for task * @p: the task whose available cpu range will to set @@ -6828,8 +6821,13 @@ static void set_task_select_cpus(struct task_struct *p, int *idlest_cpu, if (util_avg_sum < sysctl_sched_util_low_pct * cpumask_weight(p->prefer_cpus)) { p->select_cpus = p->prefer_cpus; + memqos_select_nicest_cpus(p); if (sd_flag & SD_BALANCE_WAKE) schedstat_inc(p->se.dyn_affi_stats->nr_wakeups_preferred_cpus); + } else { + //select trubo task + //select low class task + memqos_exclude_low_level_task_single(p); } } #endif diff --git a/kernel/sched/memqos/Makefile b/kernel/sched/memqos/Makefile new file mode 100644 index 0000000000000..ed8f42649a8a7 --- /dev/null +++ b/kernel/sched/memqos/Makefile @@ -0,0 +1,6 @@ +# SPDX-License-Identifier: GPL-2.0 +# These files are disabled because they produce non-interesting flaky coverage +# that is not a function of syscall inputs. E.g. involuntary context switches. +KCOV_INSTRUMENT := n + +obj-y := memqos.o phase_feature_sysctl.o phase_memband.o phase_perf.o phase_sim_knn.o diff --git a/kernel/sched/memqos/memqos.c b/kernel/sched/memqos/memqos.c new file mode 100644 index 0000000000000..29fc6af1f02c1 --- /dev/null +++ b/kernel/sched/memqos/memqos.c @@ -0,0 +1,297 @@ +#include <linux/memqos.h> +#include <linux/cpumask.h> +#include <linux/sched.h> + +static void memqos_set_task_classid(struct task_struct *p) +{ + int class_id; + int memband_div_10 = p->sched_memqos.memband_div_10; + int ipcx10 = p->sched_memqos.ipcx10; + + class_id = knn_get_tag((u64)ipcx10, (u64)memband_div_10); + p->sched_memqos.class_id = class_id; +} + +//static memqos_domain mq_domains[] = { +// {.dom_id = 0, .total_memband = 0, .total_out_memband = 0,}, +// {.dom_id = 1, .total_memband = 0, .total_out_memband = 0,}, +// {.dom_id = 2, .total_memband = 0, .total_out_memband = 0,}, +// {.dom_id = 3, .total_memband = 0, .total_out_memband = 0,}, +//}; + +static DEFINE_PER_CPU(struct memqos_class, memqos_classes[8]); +//static DEFINE_PER_CPU(spinlock_t, memqos_class_lock); +static DEFINE_SPINLOCK(memqos_class_lock); + +static int memqos_class_online(unsigned int cpu) +{ + int class_id = 0; + struct memqos_class *class; + + for (class_id = 0; class_id < 8; class_id++) { + class = &per_cpu(memqos_classes, cpu)[class_id]; + INIT_LIST_HEAD(&class->tasks_list); + INIT_LIST_HEAD(&class->turbo_list); + } + return 0; +} + +static int memqos_class_offline(unsigned int cpu) +{ + return 0; +} + +#include <linux/cpu.h> +#include <linux/cacheinfo.h> + +static void memqos_init(void) +{ + int cpuhp_state = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, + "memqos:online", memqos_class_online, + memqos_class_offline); + if (cpuhp_state <= 0) { + pr_err("Failed to register 'dyn' cpuhp callbacks"); + return; + } +} +late_initcall(memqos_init); + +static void memqos_insert_to_class(struct task_struct *p, int cpu) +{ + unsigned long flag; + int class_id = p->sched_memqos.class_id; + struct memqos_class *class; + struct task_memqos *memqos; + + if (class_id >= 8) + return; + + memqos = &p->sched_memqos; + + class = &per_cpu(memqos_classes, cpu)[class_id]; + + spin_lock_irqsave(&memqos_class_lock, flag); + if (p->sched_memqos.corrupt) { + spin_unlock_irqrestore(&memqos_class_lock, flag); + return; + } + + list_move_tail(&p->sched_memqos.task_list, &class->tasks_list); + if (memqos->turbo) + list_move_tail(&p->sched_memqos.turbo_list, &class->turbo_list); + spin_unlock_irqrestore(&memqos_class_lock, flag); +} + +static void memqos_drop_class_without_lock(struct task_struct *p) +{ + list_del_init(&p->sched_memqos.task_list); + list_del_init(&p->sched_memqos.turbo_list); +} + +static void memqos_score(struct task_struct *p) +{ + int total_n1 = p->sched_memqos.memband_div_10_total[0]; + int total_n2 = p->sched_memqos.memband_div_10_total[1]; + int total_n3 = p->sched_memqos.memband_div_10_total[2]; + int total_n4 = p->sched_memqos.memband_div_10_total[3]; + + p->sched_memqos.numa_score[0] = (total_n1 - (total_n2 + total_n3 + total_n4)) * 10 / total_n1; + p->sched_memqos.numa_score[1] = (total_n2 - (total_n1 + total_n3 + total_n4)) * 10 / total_n2; + p->sched_memqos.numa_score[2] = (total_n3 - (total_n1 + total_n2 + total_n4)) * 10 / total_n3; + p->sched_memqos.numa_score[3] = (total_n4 - (total_n1 + total_n2 + total_n3)) * 10 / total_n4; + + //over x% percent + if (p->sched_memqos.numa_score[0] > 0) + p->sched_memqos.turbo = 1; + else if (p->sched_memqos.numa_score[1] > 0) + p->sched_memqos.turbo = 2; + else if (p->sched_memqos.numa_score[2] > 0) + p->sched_memqos.turbo = 3; + else if (p->sched_memqos.numa_score[3] > 0) + p->sched_memqos.turbo = 4; + else + p->sched_memqos.turbo = 0; +} + +void memqos_account_task(struct task_struct *p, int cpu) +{ + if (!p->sched_memqos.account_ready || + p->sched_memqos.corrupt) + return; + memqos_set_task_classid(p); + memqos_insert_to_class(p, cpu); + memqos_score(p); + p->sched_memqos.account_ready = 0; +} + +void memqos_init_class(struct task_struct *p) +{ + memset(&p->sched_memqos, 0, sizeof(struct task_memqos)); + spin_lock(&memqos_class_lock); + INIT_LIST_HEAD(&p->sched_memqos.task_list); + INIT_LIST_HEAD(&p->sched_memqos.turbo_list); + INIT_LIST_HEAD(&p->sched_memqos.mpam_profile.wait_list); + spin_unlock(&memqos_class_lock); + + p->closid = 0; + p->rmid = 0; +} + +//destroy ? +void memqos_drop_class(struct task_struct *p) +{ + spin_lock(&memqos_class_lock); + memqos_drop_class_without_lock(p); + p->sched_memqos.corrupt = 1; + spin_unlock(&memqos_class_lock); +} + +void memqos_select_nicest_cpus(struct task_struct *p) +{ + int i = 0; + int max_score = -10000; + int select_node = 0; + struct task_memqos *memqos = &p->sched_memqos; + + if (!memqos->turbo) { + for (i = 0; i < 4; i++) { + if (!cpumask_intersects(cpumask_of_node(i), p->select_cpus)) + continue; + + if (memqos->numa_score[i] > max_score) { + select_node = i; + max_score = memqos->numa_score[i]; + } + } + + cpumask_and(p->select_cpus, p->select_cpus, cpumask_of_node(select_node)); + //p->sched_memqos.advise_mem_node_mask = cpumask_of_node(select_node); + p->sched_memqos.preferred_nid = memqos->turbo; + return; + } + + select_node = memqos->turbo - 1; + if (cpumask_intersects(cpumask_of_node(select_node), p->select_cpus)) { + cpumask_and(p->select_cpus, p->select_cpus, cpumask_of_node(select_node)); + //p->sched_memqos.advise_mem_node_mask = cpumask_of_node(select_node); + p->sched_memqos.preferred_nid = memqos->turbo; + } + + //if turbo another cpus, wait... + return; +} + +void memqos_exclude_low_level_task_single(struct task_struct *p) +{ + int i, j, cpu; + int find = 0; + int select_node = 0; + const struct cpumask *cpumask; + struct cpumask cpumask_med; + struct memqos_class *class; + struct task_memqos *memqos = &p->sched_memqos;; + struct task_struct *tsk = NULL; + int max_score = -100000; + + if (memqos->turbo) { + select_node = memqos->turbo - 1; + cpumask = cpumask_of_node(select_node); + if (!cpumask_intersects(cpumask, p->prefer_cpus) && + (cpumask_intersects(&p->cpus_allowed, cpumask))) { + cpumask_and(p->select_cpus, &p->cpus_allowed, cpumask); + //go out! + spin_lock(&memqos_class_lock); + memqos_drop_class_without_lock(p); + spin_unlock(&memqos_class_lock); + //p->sched_memqos.advise_mem_node_mask = cpumask_of_node(select_node); + p->sched_memqos.preferred_nid = memqos->turbo; + return; + } else if (cpumask_intersects(p->prefer_cpus, cpumask)) { + cpumask_and(p->select_cpus, p->prefer_cpus, cpumask); + //p->sched_memqos.advise_mem_node_mask = cpumask_of_node(select_node); + p->sched_memqos.preferred_nid = memqos->turbo; + } + } + + //select turbo one + for (cpu = 0; cpu < nr_cpu_ids; cpu++) { + if (!cpumask_test_cpu(cpu, p->prefer_cpus)) + continue; + + spin_lock(&memqos_class_lock); + for (i = 7; i >= 0; i--) { + class = &per_cpu(memqos_classes, cpu)[i]; + list_for_each_entry(memqos, &class->turbo_list, turbo_list) { + if (!memqos->turbo) + continue; + select_node = memqos->turbo - 1; + cpumask = cpumask_of_node(select_node); + if (!cpumask_intersects(cpumask, p->prefer_cpus)) { + tsk = container_of(memqos, struct task_struct, sched_memqos); + if (!cpumask_intersects(cpumask, &tsk->cpus_allowed)) + continue; + cpumask_and(tsk->select_cpus, &tsk->cpus_allowed, cpumask); + //mem prefered + //tsk->sched_memqos.advise_mem_node_mask = cpumask_of_node(select_node); + tsk->sched_memqos.preferred_nid = memqos->turbo; + find = 1; + break; + } + } + if (find) { + memqos_drop_class_without_lock(tsk); + spin_unlock(&memqos_class_lock); + return; + } + } + spin_unlock(&memqos_class_lock); + } + + find = 0; + + //if not, select lower class's tsk + for (cpu = 0; cpu < nr_cpu_ids; cpu++) { + if (!cpumask_test_cpu(cpu, p->prefer_cpus)) + continue; + + spin_lock(&memqos_class_lock); + //only find below class tsk + for (i = 0; i < memqos->class_id; i++) { + class = &per_cpu(memqos_classes, cpu)[i]; + list_for_each_entry(memqos, &class->tasks_list, task_list) { + if (memqos->turbo) + continue; + + tsk = container_of(memqos, struct task_struct, sched_memqos); + for (j = 0; j < 4; j++) { + if (!cpumask_intersects(cpumask_of_node(i), &tsk->cpus_allowed)) + continue; + if (memqos->numa_score[j] > max_score) { + select_node = j; + max_score = memqos->numa_score[j]; + } + find = 1; + } + if (!find) + continue; + + cpumask_and(&cpumask_med, cpumask_of_node(select_node), &tsk->cpus_allowed); + cpumask_andnot(&cpumask_med, &cpumask_med, p->prefer_cpus); + if (cpumask_empty(&cpumask_med)) + continue; + cpumask_copy(tsk->select_cpus, &cpumask_med); + //mem prefered + //tsk->sched_memqos.advise_mem_node_mask = cpumask_of_node(select_node); + tsk->sched_memqos.preferred_nid = memqos->turbo; + memqos_drop_class_without_lock(tsk); + spin_unlock(&memqos_class_lock); + return; + } + } + spin_unlock(&memqos_class_lock); + } + + //do not care, this task may out + return; +} + diff --git a/kernel/sched/memqos/phase_feature_sysctl.c b/kernel/sched/memqos/phase_feature_sysctl.c new file mode 100644 index 0000000000000..9106a90868a3d --- /dev/null +++ b/kernel/sched/memqos/phase_feature_sysctl.c @@ -0,0 +1,183 @@ +#include <linux/sched.h> +#include <linux/sysctl.h> +#include <linux/capability.h> +#include <linux/cpumask.h> +#include <linux/topology.h> +#include <linux/sched/task.h> + +#include <linux/memqos.h> + +#ifdef CONFIG_PROC_SYSCTL + +//setup timer for counting +#include <linux/sched.h> +#include <linux/timer.h> +#include <asm/ioctl.h> + +//at least 2 cpu +static enum hrtimer_restart timer_fn_twin_a(struct hrtimer *timer_data) +{ + sched_memqos_task_collect_data_range(0, nr_cpu_ids / 2 - 1); + hrtimer_forward_now(timer_data, 1 * NSEC_PER_MSEC); + return HRTIMER_RESTART; +} + +static enum hrtimer_restart timer_fn_twin_b(struct hrtimer *timer_data) +{ + sched_memqos_task_collect_data_range(nr_cpu_ids / 2, nr_cpu_ids - 1); + hrtimer_forward_now(timer_data, 1 * NSEC_PER_MSEC); + return HRTIMER_RESTART; +} + +static struct hrtimer timer_twin_a; +static struct hrtimer timer_twin_b; + +static void memqos_timer_init_func_a(void *info) { + hrtimer_init(&timer_twin_a, CLOCK_MONOTONIC, HRTIMER_MODE_ABS); + timer_twin_a.function = timer_fn_twin_a; + hrtimer_start(&timer_twin_a, ktime_add_ns(ktime_get(), 10000000), HRTIMER_MODE_ABS); +} + +static void memqos_timer_init_func_b(void *info) { + hrtimer_init(&timer_twin_b, CLOCK_MONOTONIC, HRTIMER_MODE_ABS); + timer_twin_b.function = timer_fn_twin_b; + hrtimer_start(&timer_twin_b, ktime_add_ns(ktime_get(), 10000000), HRTIMER_MODE_ABS); +} + +static void memqos_timer_init_a(void) +{ + smp_call_function_single(0, memqos_timer_init_func_b, NULL, 0); +} + +static void memqos_timer_init_b(void) +{ + smp_call_function_single(nr_cpu_ids / 2, memqos_timer_init_func_a, NULL, 0); +} + +static void memqos_timer_twin_init(void) { + memqos_timer_init_a(); + memqos_timer_init_b(); +} + +static void memqos_timer_twin_exit(void) { + hrtimer_cancel(&timer_twin_a); + hrtimer_cancel(&timer_twin_b); +} + +DEFINE_STATIC_KEY_FALSE(sched_phase); +DEFINE_STATIC_KEY_FALSE(sched_phase_printk); + +static int set_phase_state(bool enabled) +{ + int err; + int state = static_branch_likely(&sched_phase); + + if (enabled == state) { + pr_warn("phase has already %s\n", state ? "enabled" : "disabled"); + return 0; + } + + if (enabled) { + err = phase_perf_create(); + if (err) { + pr_err("phase enable failed\n"); + return err; + } + static_branch_enable(&sched_phase); + pr_info("phase enabled\n"); + memqos_timer_twin_init(); + } else { + static_branch_disable(&sched_phase); + phase_perf_release(); + pr_info("phase disabled\n"); + memqos_timer_twin_exit(); + } + + return 0; +} + +/* + * the other procfs files of phase cannot be modified if sched_phase is already enabled + */ +static int phase_proc_state(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + struct ctl_table t; + int err; + int state = static_branch_likely(&sched_phase); + + if (write && !capable(CAP_SYS_ADMIN)) + return -EPERM; + + t = *table; + t.data = &state; + err = proc_dointvec_minmax(&t, write, buffer, lenp, ppos); + if (err < 0) + return err; + if (write) + err = set_phase_state(state); + + return err; +} + +static int set_phase_state_printk(bool enabled) +{ + if (enabled) { + static_branch_enable(&sched_phase_printk); + } else { + static_branch_disable(&sched_phase_printk); + } + + return 0; +} + +/* + * the other procfs files of phase cannot be modified if sched_phase is already enabled + */ +static int phase_proc_state_printk(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + struct ctl_table t; + int err; + int state = static_branch_likely(&sched_phase); + + if (write && !capable(CAP_SYS_ADMIN)) + return -EPERM; + + t = *table; + t.data = &state; + err = proc_dointvec_minmax(&t, write, buffer, lenp, ppos); + if (err < 0) + return err; + if (write) + err = set_phase_state_printk(state); + + return err; +} + + +static int __maybe_unused zero; +static int __maybe_unused one = 1; + +struct ctl_table phase_table[] = { + { + .procname = "enabled", + .data = NULL, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = phase_proc_state, + .extra1 = &zero, + .extra2 = &one, + }, + { + .procname = "trace_enabled", + .data = NULL, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = phase_proc_state_printk, + .extra1 = &zero, + .extra2 = &one, + }, + { } +}; +#endif /* CONFIG_PROC_SYSCTL */ diff --git a/kernel/sched/memqos/phase_memband.c b/kernel/sched/memqos/phase_memband.c new file mode 100644 index 0000000000000..df8b2811f6ab7 --- /dev/null +++ b/kernel/sched/memqos/phase_memband.c @@ -0,0 +1,179 @@ +#include <linux/types.h> +#include <linux/cpu.h> +#include <linux/memqos.h> + +#include <asm/cpu.h> +#include <asm/cputype.h> +#include <asm/cpufeature.h> +#include <asm/mpam_sched.h> + +static const int nr_partid = 15; +static const int nr_monitor = 4; + +static LIST_HEAD(phase_mpam_waitqueue); + +//mpam_profile_res[0] not used +struct memqos_mpam_profile mpam_profile_res[16] = { + { .partid = 0, .monitor = 0, .used = 1}, + { .partid = 1, .monitor = 0,}, + { .partid = 2, .monitor = 1,}, + { .partid = 3, .monitor = 2,}, + { .partid = 4, .monitor = 3,}, + { .partid = 5, .monitor = 0,}, + { .partid = 6, .monitor = 1,}, + { .partid = 7, .monitor = 2,}, + { .partid = 8, .monitor = 3,}, + { .partid = 9, .monitor = 0,}, + { .partid = 10, .monitor = 1,}, + { .partid = 11, .monitor = 2,}, + { .partid = 12, .monitor = 3,}, + { .partid = 13, .monitor = 0,}, + { .partid = 14, .monitor = 1,}, + { .partid = 15, .monitor = 2,}, +}; + +static DEFINE_SPINLOCK(phase_partid_lock); + +void phase_update_mpam_label(struct task_struct *tsk) +{ + int i = 0; + //unsigned long flag; + + WARN_ON_ONCE(tsk->closid); + + if (tsk->sched_memqos.corrupt) { + phase_release_mpam_label(tsk); + return; + } + + spin_lock(&phase_partid_lock); + if (tsk->sched_memqos.mpam_profile.profile != &mpam_profile_res[0] && + tsk->sched_memqos.mpam_profile.profile != NULL) { + tsk->closid = tsk->sched_memqos.mpam_profile.profile->partid; + tsk->sched_memqos.mpam_profile.profile->tsk = tsk; + //tsk->sched_memqos.mpam_profile.profile->used = 1; + tsk->rmid = 0; + spin_unlock(&phase_partid_lock); + //if (static_branch_unlikely(&sched_phase_printk)) { + // trace_printk("task pid:%d get partid%d succeed\n", tsk->pid, tsk->closid); + //} + __mpam_sched_in_v2(tsk); + return; + } + + //is in profile queue, wait... + if (tsk->sched_memqos.mpam_profile.profile == &mpam_profile_res[0]) { + spin_unlock(&phase_partid_lock); + return; + } + + for (i = 1; i < 16; i++) { + if (mpam_profile_res[i].used) { + if (static_branch_unlikely(&sched_phase_printk)) { + //if (mpam_profile_res[i].tsk) + // trace_printk("i%d want get partid, butpartid:%d get by pid:%d closid:%d\n", + //tsk->pid, i, mpam_profile_res[i].tsk->pid, mpam_profile_res[i].tsk->closid); + //else + // trace_printk("i%d want get partid, butpartid:%d get by pid:%d(NULL)\n", + //tsk->pid, i, tsk->pid); + } + + continue; + } + + tsk->sched_memqos.mpam_profile.profile = NULL; + break; + } + + if (i == 16) { + list_move_tail(&tsk->sched_memqos.mpam_profile.wait_list, &phase_mpam_waitqueue); + tsk->sched_memqos.mpam_profile.profile = &mpam_profile_res[0]; + spin_unlock(&phase_partid_lock); + //if (static_branch_unlikely(&sched_phase_printk)) { + // trace_printk("task pid:%d no partid found, go to list\n", tsk->pid); + //} + //wait... + return; + } + + mpam_profile_res[i].used = 1; + tsk->closid = mpam_profile_res[i].partid; + mpam_profile_res[i].tsk = tsk; + tsk->sched_memqos.mpam_profile.profile = &mpam_profile_res[i]; + tsk->rmid = 0; + spin_unlock(&phase_partid_lock); + //if (static_branch_unlikely(&sched_phase_printk)) { + //trace_printk("task pid:%d get partid%d succeed\n", tsk->pid, i); + //} + + __mpam_sched_in_v2(tsk); +} + +static void phase_release_mpam_label_without_lock(struct task_struct *tsk) +{ + int closid; + struct memqos_wait_profile *next; + + //assert locked + + if (tsk->sched_memqos.mpam_profile.profile && + tsk->sched_memqos.mpam_profile.profile->partid) { + closid = tsk->sched_memqos.mpam_profile.profile->partid; + } else if (tsk->closid == 0) { + return; + } else { + closid = tsk->closid; + } + + tsk->closid = 0; + tsk->sched_memqos.mpam_profile.profile = NULL; + mpam_profile_res[closid].used = 0; + mpam_profile_res[closid].tsk = NULL; + + //if (static_branch_unlikely(&sched_phase_printk)) { + // trace_printk("task pid:%d release partid%d, list empty:%d\n", tsk->pid, closid, list_empty(&phase_mpam_waitqueue)); + //} + + next = list_first_entry_or_null(&phase_mpam_waitqueue, struct memqos_wait_profile, wait_list); + if (next) { + list_del_init(&next->wait_list); + mpam_profile_res[closid].used = 1; + next->profile = &mpam_profile_res[closid]; + } + + return; +} + +//task shutdown +void phase_destroy_waitqueue(struct task_struct *tsk) +{ + spin_lock(&phase_partid_lock); + + //if (tsk->sched_memqos.mpam_profile.profile == &mpam_profile_res[0]) { + list_del_init(&tsk->sched_memqos.mpam_profile.wait_list); + //} else { + phase_release_mpam_label_without_lock(tsk); + //} + spin_unlock(&phase_partid_lock); +} + +void phase_release_mpam_label(struct task_struct *tsk) +{ + spin_lock(&phase_partid_lock); + phase_release_mpam_label_without_lock(tsk); + spin_unlock(&phase_partid_lock); +} + +#include <asm/mpam.h> +void phase_get_memband(struct memqos_mpam_profile *pm, int *result, int nr) +{ + if (pm == &mpam_profile_res[0] || pm == NULL) { + result[0] = 0; + result[1] = 0; + result[2] = 0; + result[3] = 0; + return; + } + + mpam_component_config_mbwu_mon(pm->partid, pm->pmg, pm->monitor, result, nr); +} diff --git a/kernel/sched/memqos/phase_perf.c b/kernel/sched/memqos/phase_perf.c new file mode 100644 index 0000000000000..7b7f37e46f76c --- /dev/null +++ b/kernel/sched/memqos/phase_perf.c @@ -0,0 +1,412 @@ +#include <linux/kernel.h> +#include <linux/perf_event.h> +#include <linux/percpu-defs.h> +#include <linux/slab.h> +#include <linux/stop_machine.h> +#include <linux/memqos.h> +#include <linux/sched.h> + +#define PHASE_FEVENT_NUM 3 + +int *phase_perf_pevents = NULL; + +static DEFINE_PER_CPU(__typeof__(struct perf_event *)[PHASE_PEVENT_NUM], cpu_phase_perf_events); + +/****************************************** + * Helpers for phase perf event + *****************************************/ +static inline struct perf_event *perf_event_of_cpu(int cpu, int index) +{ + return per_cpu(cpu_phase_perf_events, cpu)[index]; +} + +static inline struct perf_event **perf_events_of_cpu(int cpu) +{ + return per_cpu(cpu_phase_perf_events, cpu); +} + +static inline u64 perf_event_local_pmu_read(struct perf_event *event) +{ + return 0; + if (event->state == PERF_EVENT_STATE_ACTIVE) + event->pmu->read(event); + return local64_read(&event->count); +} + +/****************************************** + * Helpers for cpu counters + *****************************************/ +static inline u64 read_cpu_counter(int cpu, int index) +{ + struct perf_event *event = perf_event_of_cpu(cpu, index); + + if (!event || !event->pmu) + return 0; + + return perf_event_local_pmu_read(event); +} + +static struct perf_event_attr *alloc_attr(int event_id) +{ + struct perf_event_attr *attr; + + attr = kzalloc(sizeof(struct perf_event_attr), GFP_KERNEL); + if (!attr) + return ERR_PTR(-ENOMEM); + + attr->type = PERF_TYPE_RAW; + attr->config = event_id; + attr->size = sizeof(struct perf_event_attr); + attr->pinned = 1; + attr->disabled = 1; + //attr->exclude_hv; + //attr->exclude_idle; + //attr->exclude_kernel; + + return attr; +} + +static int create_cpu_counter(int cpu, int event_id, int index) +{ + struct perf_event_attr *attr = NULL; + struct perf_event **events = perf_events_of_cpu(cpu); + struct perf_event *event = NULL; + + return 0; + attr = alloc_attr(event_id); + if (IS_ERR(attr)) + return PTR_ERR(attr); + + event = perf_event_create_kernel_counter(attr, cpu, NULL, NULL, NULL); + if (IS_ERR(event)) { + pr_err("unable to create perf event (cpu:%i-type:%d-pinned:%d-config:0x%llx) : %ld", + cpu, attr->type, attr->pinned, attr->config, PTR_ERR(event)); + kfree(attr); + return PTR_ERR(event); + } else { + events[index] = event; + perf_event_enable(events[index]); + if (event->hw.idx == -1) { + pr_err("pinned event unable to get onto hardware, perf event (cpu:%i-type:%d-config:0x%llx)", + cpu, attr->type, attr->config); + kfree(attr); + return -EINVAL; + } + pr_info("create perf_event (cpu:%i-idx:%d-type:%d-pinned:%d-exclude_hv:%d" + "-exclude_idle:%d-exclude_kernel:%d-config:0x%llx-addr:%px)", + event->cpu, event->hw.idx, + event->attr.type, event->attr.pinned, event->attr.exclude_hv, + event->attr.exclude_idle, event->attr.exclude_kernel, + event->attr.config, event); + } + + kfree(attr); + return 0; +} + +static int release_cpu_counter(int cpu, int event_id, int index) +{ + struct perf_event **events = perf_events_of_cpu(cpu); + struct perf_event *event = NULL; + + return 0; + event = events[index]; + + if (!event) + return 0; + + pr_info("release perf_event (cpu:%i-idx:%d-type:%d-pinned:%d-exclude_hv:%d" + "-exclude_idle:%d-exclude_kernel:%d-config:0x%llx)", + event->cpu, event->hw.idx, + event->attr.type, event->attr.pinned, event->attr.exclude_hv, + event->attr.exclude_idle, event->attr.exclude_kernel, + event->attr.config); + + perf_event_release_kernel(event); + events[index] = NULL; + + return 0; +} + +enum { + CYCLES_INDEX = 0, + INST_RETIRED_INDEX, + PHASE_EVENT_FINAL_TERMINATOR +}; + +#define CYCLES 0x0011 +#define INST_RETIRED 0x0008 + +static int pevents[PHASE_PEVENT_NUM] = { + CYCLES, + INST_RETIRED, + PHASE_EVENT_FINAL_TERMINATOR, +}; + +#define for_each_phase_pevents(index, events) \ + for (index = 0; events != NULL && index < PHASE_PEVENT_NUM && \ + events[index] != PHASE_EVENT_FINAL_TERMINATOR; index++) + + +/****************************************** + * Helpers for phase perf + *****************************************/ +static int do_pevents(int (*fn)(int, int, int), int cpu) +{ + int index; + int err; + + for_each_phase_pevents(index, phase_perf_pevents) { + err = fn(cpu, phase_perf_pevents[index], index); + if (err) + return err; + } + + return 0; +} + +static int __phase_perf_create(void *args) +{ + int err; + int cpu = raw_smp_processor_id(); + + /* create pinned events */ + pr_info("create pinned events\n"); + err = do_pevents(create_cpu_counter, cpu); + if (err) { + pr_err("create pinned events failed\n"); + do_pevents(release_cpu_counter, cpu); + return err; + } + + pr_info("[%d] phase class event create success\n", cpu); + return 0; +} + +static int do_phase_perf_create(int *pevents, const struct cpumask *cpus) +{ + phase_perf_pevents = pevents; + return stop_machine(__phase_perf_create, NULL, cpus); +} + +static int __do_phase_perf_release(void *args) +{ + int cpu = raw_smp_processor_id(); + + /* release pinned events */ + pr_info("release pinned events\n"); + do_pevents(release_cpu_counter, cpu); + + pr_info("[%d] phase class event release success\n", cpu); + return 0; +} + +static void do_phase_perf_release(const struct cpumask *cpus) +{ + stop_machine(__do_phase_perf_release, NULL, cpus); + phase_perf_pevents = NULL; +} + +int phase_perf_create(void) +{ + return do_phase_perf_create(pevents, cpu_possible_mask); +} + +void phase_perf_release(void) +{ + do_phase_perf_release(cpu_possible_mask); +} + +DECLARE_STATIC_KEY_FALSE(sched_phase); +DECLARE_STATIC_KEY_FALSE(sched_phase_printk); + +#define PHASE_EVENT_OVERFLOW (~0ULL) + +static inline u64 phase_event_count_sub(u64 curr, u64 prev) +{ + if (curr < prev) { /* ovewrflow */ + u64 tmp = PHASE_EVENT_OVERFLOW - prev; + return curr + tmp; + } else { + return curr - prev; + } +} + +static inline void phase_calc_delta(struct task_struct *p, + struct phase_event_count *prev, + struct phase_event_count *curr, + struct phase_event_count *delta) +{ + int *pevents = phase_perf_pevents; + int index; + + for_each_phase_pevents(index, pevents) { + delta->pcount.data[index] = phase_event_count_sub(curr->pcount.data[index], prev->pcount.data[index]); + } +} + +static inline u64 phase_data_of_pevent(struct phase_event_pcount *counter, int event_id) +{ + int index; + int *events = phase_perf_pevents; + + for_each_phase_pevents(index, events) { + if (event_id == events[index]) + return counter->data[index]; + } + + return 0; +} + +static int cal_ring_history_average(int *history, int nr, int s_pos, int c_nr) +{ + int average = 0; + int start = ((s_pos - c_nr) + nr) % nr; + + if (start < 0) + return 0; + + for (;start != s_pos;) { + if (history[start] == 0) { + c_nr--; + if (c_nr == 0) + return 0; + continue; + } + average += history[start]; + start = (start + 1) % nr; + } + + return start / c_nr; +} + +static void __phase_cal_ipcx10(struct task_struct *p, struct phase_event_count *delta) +{ + u64 ins; + u64 cycles; + //invalid zero + int ipcx10 = 0; + + ins = phase_data_of_pevent(&delta->pcount, INST_RETIRED_INDEX); + cycles = phase_data_of_pevent(&delta->pcount, CYCLES_INDEX); + + if (cycles) + ipcx10 = (ins * 10) / cycles; + + //if (static_branch_unlikely(&sched_phase_printk)) { + // trace_printk("ins:%lld cycles:%lld\n", ins, cycles); + //} + + p->sched_memqos.ipcx10_history[p->sched_memqos.ipc_ringpos] = ipcx10; + p->sched_memqos.ipc_ringpos = (p->sched_memqos.ipc_ringpos + 1) % 10; + cal_ring_history_average(p->sched_memqos.ipcx10_history, 10, p->sched_memqos.ipc_ringpos, 5); +} + +static void __phase_cal_memband_div_10(struct task_struct *p) +{ + int pos; + int result[4]; + + pos = p->sched_memqos.memband_ringpos; + + phase_get_memband(p->sched_memqos.mpam_profile.profile, result, 4); + + //if (static_branch_unlikely(&sched_phase_printk)) { + // trace_printk("memband:%d %d %d %d profile:%llx\n", result[0], result[1], result[2], result[3], p->sched_memqos.mpam_profile.profile); + //} + + p->sched_memqos.memband_div_10_total[0] = p->sched_memqos.memband_div_10_total[0] - p->sched_memqos.memband_div_10_history[0][pos]; + p->sched_memqos.memband_div_10_total[0] = p->sched_memqos.memband_div_10_total[0] + result[0] / 10; + p->sched_memqos.memband_div_10_history[0][p->sched_memqos.memband_ringpos] = result[0] / 10; + + p->sched_memqos.memband_div_10_total[1] = p->sched_memqos.memband_div_10_total[1] - p->sched_memqos.memband_div_10_history[1][pos]; + p->sched_memqos.memband_div_10_total[1] = p->sched_memqos.memband_div_10_total[1] + result[1] / 10; + p->sched_memqos.memband_div_10_history[1][p->sched_memqos.memband_ringpos] = result[1] / 10; + + p->sched_memqos.memband_div_10_total[2] = p->sched_memqos.memband_div_10_total[2] - p->sched_memqos.memband_div_10_history[2][pos]; + p->sched_memqos.memband_div_10_total[2] = p->sched_memqos.memband_div_10_total[2] + result[2] / 10; + p->sched_memqos.memband_div_10_history[2][p->sched_memqos.memband_ringpos] = result[2] / 10; + + p->sched_memqos.memband_div_10_total[3] = p->sched_memqos.memband_div_10_total[3] - p->sched_memqos.memband_div_10_history[3][pos]; + p->sched_memqos.memband_div_10_total[3] = p->sched_memqos.memband_div_10_total[3] + result[3] / 10; + p->sched_memqos.memband_div_10_history[3][p->sched_memqos.memband_ringpos] = result[3] / 10; + + p->sched_memqos.memband_ringpos = (pos + 1) % 10; + + cal_ring_history_average(p->sched_memqos.memband_div_10_history[0], 10, pos, 5); + cal_ring_history_average(p->sched_memqos.memband_div_10_history[1], 10, pos, 5); + cal_ring_history_average(p->sched_memqos.memband_div_10_history[2], 10, pos, 5); + cal_ring_history_average(p->sched_memqos.memband_div_10_history[3], 10, pos, 5); +} + +static DEFINE_PER_CPU(struct phase_event_count, prev_phase_event_count); +static DEFINE_PER_CPU(struct phase_event_count, curr_phase_event_count); + +static void phase_perf_read_events(int cpu, u64 *pdata) +{ + int index; + + for_each_phase_pevents(index, phase_perf_pevents) { + pdata[index] = read_cpu_counter(cpu, index); + } +} + +static inline struct phase_event_count *phase_read_prev(unsigned int cpu) +{ + return &per_cpu(prev_phase_event_count, cpu); +} + +static inline struct phase_event_count *phase_read_curr(unsigned int cpu) +{ + struct phase_event_count *curr = &per_cpu(curr_phase_event_count, cpu); + + phase_perf_read_events(cpu, curr->pcount.data); + + return curr; +} + +void phase_account_task(struct task_struct *p, int cpu) +{ + struct phase_event_count delta; + struct phase_event_count *prev, *curr; + + if (!static_branch_likely(&sched_phase)) + return; + + //if (!sched_core_enabled(cpu_rq(cpu))) + // return; + + /* update phase_event_count */ + prev = phase_read_prev(cpu); + curr = phase_read_curr(cpu); + phase_calc_delta(p, prev, curr, &delta); + *prev = *curr; + + /* calculate phase */ + __phase_cal_ipcx10(p, &delta); + __phase_cal_memband_div_10(p); + p->sched_memqos.sample_times++; + if ((p->sched_memqos.sample_times % 3) == 0) + p->sched_memqos.account_ready = 1; +} + + +void phase_trace_printk(struct task_struct *p) +{ + if (!static_branch_unlikely(&sched_phase_printk)) + return; + + trace_printk("p->comm:%s(%d) ipcpos:%d ipcx10:%d membandpos:%d memband_div_10:%d numa_score[0]:%d numa_score[1]:%d numa_score[2]:%d numa_score[3]:%d turbo:%d prefered_nid:%d classid:%d partid:%d\n", + p->comm, p->pid, p->sched_memqos.ipc_ringpos,\ + p->sched_memqos.ipcx10, \ + p->sched_memqos.memband_ringpos,\ + p->sched_memqos.memband_div_10, \ + p->sched_memqos.numa_score[0], \ + p->sched_memqos.numa_score[1], \ + p->sched_memqos.numa_score[2], \ + p->sched_memqos.numa_score[3], \ + p->sched_memqos.turbo, \ + p->sched_memqos.preferred_nid, \ + p->sched_memqos.class_id, \ + p->closid); +} diff --git a/kernel/sched/memqos/phase_sim_knn.c b/kernel/sched/memqos/phase_sim_knn.c new file mode 100644 index 0000000000000..b80bb6b9ae0a3 --- /dev/null +++ b/kernel/sched/memqos/phase_sim_knn.c @@ -0,0 +1,92 @@ +#include <linux/types.h> + +#define DATA_ROW 20 +void QuickSort(u64 arr[DATA_ROW][2], int L, int R) { + int i = L; + int j = R; + int kk = (L + R) / 2; + u64 pivot = arr[kk][0]; + + while (i <= j) { + while (pivot > arr[i][0]) { + i++; + } + while (pivot < arr[j][0]) { + j--; + } + if (i <= j) { + u64 temp = arr[i][0]; + + arr[i][0] = arr[j][0]; + arr[j][0] = temp; + i++; j--; + } + } + if (L < j) { + QuickSort(arr, L, j); + } + if (i < R) { + QuickSort(arr, i, R); + } +} + +u64 euclidean_distance(u64 *row1, u64 *row2, int col) { + u64 distance = 0; + int i; + + for (i = 0; i < col - 1; i++) { + distance += ((row1[i] - row2[i]) * (row1[i] - row2[i])); + } + return distance; +} + +#define num_neighbors 6 +#define MAX_TAG 8 + +int get_neighbors_tag(u64 train_data[DATA_ROW][3], int train_row, int col, u64 *test_row) { + int i; + u64 neighbors[MAX_TAG] = {0}; + int max_tag = 0; + u64 distances[DATA_ROW][2]; + + for (i = 0; i < train_row; i++) { + distances[i][0] = euclidean_distance(train_data[i], test_row, col); + distances[i][1] = train_data[i][col - 1]; + } + QuickSort(distances, 0, train_row - 1); + for (i = 0; i < num_neighbors; i++) { + neighbors[distances[i][1]]++; + if (neighbors[distances[i][1]] > neighbors[max_tag]) + max_tag = distances[i][1]; + } + return max_tag; +} + +static u64 train_data[DATA_ROW][3] = { + {0, 1, 0}, + {0, 9, 0}, + {0, 20, 1}, + {0, 30, 1}, + {0, 40, 2}, + {0, 50, 3}, + {0, 60, 3}, + {0, 70, 3}, + {0, 80, 4}, + {0, 90, 4}, + {0, 100, 4}, + {0, 110, 5}, + {0, 120, 5}, + {0, 130, 6}, + {0, 140, 6}, + {0, 150, 7}, +}; + +int knn_get_tag(int ipcx10, int memband_div_10) +{ + u64 test_data[2]; + + test_data[0] = ipcx10; + test_data[1] = memband_div_10; + + return get_neighbors_tag(train_data, DATA_ROW, 3, test_data); +} diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 685f9881b8e23..0d2764c4449ce 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -465,6 +465,13 @@ static struct ctl_table kern_table[] = { .extra2 = &one, }, #endif /* CONFIG_NUMA_BALANCING */ +#ifdef CONFIG_QOS_SCHED_DYNAMIC_AFFINITY + { + .procname = "phase", + .mode = 0555, + .child = phase_table, + }, +#endif #endif /* CONFIG_SCHED_DEBUG */ { .procname = "sched_rt_period_us", diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 4cac46d56f387..d748c291e7047 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -2164,12 +2164,15 @@ alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma, { struct mempolicy *pol; struct page *page; - int preferred_nid; + int preferred_nid = -1; nodemask_t *nmask; + if (current->sched_memqos.preferred_nid) + preferred_nid = current->sched_memqos.preferred_nid - 1; + pol = get_vma_policy(vma, addr); - if (pol->mode == MPOL_INTERLEAVE) { + if (pol->mode == MPOL_INTERLEAVE && preferred_nid != -1) { unsigned nid; nid = interleave_nid(pol, vma, addr, PAGE_SHIFT + order); @@ -2233,7 +2236,8 @@ alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma, } nmask = policy_nodemask(gfp, pol); - preferred_nid = policy_node(gfp, pol, node); + if (preferred_nid == -1) + preferred_nid = policy_node(gfp, pol, node); page = __alloc_pages_nodemask(gfp, order, preferred_nid, nmask); mark_vma_cdm(nmask, page, vma); mpol_cond_put(pol); -- 2.25.1

1 0

[OLK-5.10] RDMA/hns: Add new command to support query vf caps
by Chengchang Tang 23 Mar '23

23 Mar '23

From: Yixing Liu <liuyixing1(a)huawei.com> mainline inclusion form mainline-master category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I6K9B6 CVE: NA Reference: https://patchwork.kernel.org/project/linux-rdma/cover/20230304091555.224129… --------------------------------------------------------------- The current resource query for vf caps is driven by the driver, which is unreasonable. This patch adds a new command HNS_ROCE_OPC_QUERY_PF_CAPS_NUM to support obtaining vf caps information from firmware. Signed-off-by: Yixing Liu <liuyixing1(a)huawei.com> Signed-off-by: Haoyue Xu <xuhaoyue1(a)hisilicon.com> Reviewed-by: Yangyang Li <liyangyang20(a)huawei.com> --- drivers/infiniband/hw/hns/hns_roce_hw_v2.c | 203 +++++++-------------- drivers/infiniband/hw/hns/hns_roce_hw_v2.h | 33 +--- 2 files changed, 64 insertions(+), 172 deletions(-) diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c index c9826a010f38..cba78f0eac14 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c +++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c @@ -2157,102 +2157,6 @@ static int hns_roce_v2_set_bt(struct hns_roce_dev *hr_dev) return hns_roce_cmq_send(hr_dev, &desc, 1); } -/* Use default caps when hns_roce_query_pf_caps() failed or init VF profile */ -static void set_default_caps(struct hns_roce_dev *hr_dev) -{ - struct hns_roce_caps *caps = &hr_dev->caps; - - caps->num_qps = HNS_ROCE_V2_MAX_QP_NUM; - caps->max_wqes = HNS_ROCE_V2_MAX_WQE_NUM; - caps->num_cqs = HNS_ROCE_V2_MAX_CQ_NUM; - caps->num_srqs = HNS_ROCE_V2_MAX_SRQ_NUM; - caps->min_cqes = HNS_ROCE_MIN_CQE_NUM; - caps->max_cqes = HNS_ROCE_V2_MAX_CQE_NUM; - caps->max_sq_sg = HNS_ROCE_V2_MAX_SQ_SGE_NUM; - caps->max_extend_sg = HNS_ROCE_V2_MAX_EXTEND_SGE_NUM; - caps->max_rq_sg = HNS_ROCE_V2_MAX_RQ_SGE_NUM; - - caps->num_uars = HNS_ROCE_V2_UAR_NUM; - caps->phy_num_uars = HNS_ROCE_V2_PHY_UAR_NUM; - caps->num_aeq_vectors = HNS_ROCE_V2_AEQE_VEC_NUM; - caps->num_other_vectors = HNS_ROCE_V2_ABNORMAL_VEC_NUM; - caps->num_comp_vectors = 0; - - caps->num_mtpts = HNS_ROCE_V2_MAX_MTPT_NUM; - caps->num_pds = HNS_ROCE_V2_MAX_PD_NUM; - caps->num_qpc_timer = HNS_ROCE_V2_MAX_QPC_TIMER_NUM; - caps->cqc_timer_bt_num = HNS_ROCE_V2_MAX_CQC_TIMER_BT_NUM; - - caps->max_qp_init_rdma = HNS_ROCE_V2_MAX_QP_INIT_RDMA; - caps->max_qp_dest_rdma = HNS_ROCE_V2_MAX_QP_DEST_RDMA; - caps->max_sq_desc_sz = HNS_ROCE_V2_MAX_SQ_DESC_SZ; - caps->max_rq_desc_sz = HNS_ROCE_V2_MAX_RQ_DESC_SZ; - caps->max_srq_desc_sz = HNS_ROCE_V2_MAX_SRQ_DESC_SZ; - caps->irrl_entry_sz = HNS_ROCE_V2_IRRL_ENTRY_SZ; - caps->trrl_entry_sz = HNS_ROCE_V2_EXT_ATOMIC_TRRL_ENTRY_SZ; - caps->cqc_entry_sz = HNS_ROCE_V2_CQC_ENTRY_SZ; - caps->srqc_entry_sz = HNS_ROCE_V2_SRQC_ENTRY_SZ; - caps->mtpt_entry_sz = HNS_ROCE_V2_MTPT_ENTRY_SZ; - caps->idx_entry_sz = HNS_ROCE_V2_IDX_ENTRY_SZ; - caps->page_size_cap = HNS_ROCE_V2_PAGE_SIZE_SUPPORTED; - caps->reserved_lkey = 0; - caps->reserved_pds = 0; - caps->reserved_mrws = 1; - caps->reserved_uars = 0; - caps->reserved_cqs = 0; - caps->reserved_srqs = 0; - caps->reserved_qps = HNS_ROCE_V2_RSV_QPS; - - caps->qpc_hop_num = HNS_ROCE_CONTEXT_HOP_NUM; - caps->srqc_hop_num = HNS_ROCE_CONTEXT_HOP_NUM; - caps->cqc_hop_num = HNS_ROCE_CONTEXT_HOP_NUM; - caps->mpt_hop_num = HNS_ROCE_CONTEXT_HOP_NUM; - caps->sccc_hop_num = HNS_ROCE_SCCC_HOP_NUM; - - caps->mtt_hop_num = HNS_ROCE_MTT_HOP_NUM; - caps->wqe_sq_hop_num = HNS_ROCE_SQWQE_HOP_NUM; - caps->wqe_sge_hop_num = HNS_ROCE_EXT_SGE_HOP_NUM; - caps->wqe_rq_hop_num = HNS_ROCE_RQWQE_HOP_NUM; - caps->cqe_hop_num = HNS_ROCE_CQE_HOP_NUM; - caps->srqwqe_hop_num = HNS_ROCE_SRQWQE_HOP_NUM; - caps->idx_hop_num = HNS_ROCE_IDX_HOP_NUM; - caps->chunk_sz = HNS_ROCE_V2_TABLE_CHUNK_SIZE; - - caps->flags = HNS_ROCE_CAP_FLAG_REREG_MR | - HNS_ROCE_CAP_FLAG_ROCE_V1_V2 | - HNS_ROCE_CAP_FLAG_CQ_RECORD_DB | - HNS_ROCE_CAP_FLAG_QP_RECORD_DB; - - caps->pkey_table_len[0] = 1; - caps->ceqe_depth = HNS_ROCE_V2_COMP_EQE_NUM; - caps->aeqe_depth = HNS_ROCE_V2_ASYNC_EQE_NUM; - caps->local_ca_ack_delay = 0; - caps->max_mtu = IB_MTU_4096; - - caps->max_srq_wrs = HNS_ROCE_V2_MAX_SRQ_WR; - caps->max_srq_sges = HNS_ROCE_V2_MAX_SRQ_SGE; - - caps->flags |= HNS_ROCE_CAP_FLAG_ATOMIC | HNS_ROCE_CAP_FLAG_MW | - HNS_ROCE_CAP_FLAG_SRQ | HNS_ROCE_CAP_FLAG_FRMR | - HNS_ROCE_CAP_FLAG_QP_FLOW_CTRL | HNS_ROCE_CAP_FLAG_XRC; - - caps->gid_table_len[0] = HNS_ROCE_V2_GID_INDEX_NUM; - - if (hr_dev->pci_dev->revision >= PCI_REVISION_ID_HIP09) { - caps->flags |= HNS_ROCE_CAP_FLAG_STASH | - HNS_ROCE_CAP_FLAG_DIRECT_WQE | - HNS_ROCE_CAP_FLAG_DCA_MODE; - caps->max_sq_inline = HNS_ROCE_V3_MAX_SQ_INLINE; - } else { - caps->max_sq_inline = HNS_ROCE_V2_MAX_SQ_INLINE; - - /* The following configuration are only valid for HIP08 */ - caps->qpc_sz = HNS_ROCE_V2_QPC_SZ; - caps->sccc_sz = HNS_ROCE_V2_SCCC_SZ; - caps->cqe_sz = HNS_ROCE_V2_CQE_SIZE; - } -} - static void calc_pg_sz(u32 obj_num, u32 obj_size, u32 hop_num, u32 ctx_bt_num, u32 *buf_page_size, u32 *bt_page_size, u32 hem_type) { @@ -2395,7 +2299,8 @@ static void apply_func_caps(struct hns_roce_dev *hr_dev) if (!caps->num_comp_vectors) caps->num_comp_vectors = min_t(u32, caps->eqc_bt_num - 1, - (u32)priv->handle->rinfo.num_vectors - 2); + (u32)priv->handle->rinfo.num_vectors - + (HNS_ROCE_V2_AEQE_VEC_NUM + HNS_ROCE_V2_ABNORMAL_VEC_NUM)); if (hr_dev->pci_dev->revision >= PCI_REVISION_ID_HIP09) { caps->eqe_hop_num = HNS_ROCE_V3_EQE_HOP_NUM; @@ -2437,7 +2342,7 @@ static void apply_func_caps(struct hns_roce_dev *hr_dev) set_hem_page_size(hr_dev); } -static int hns_roce_query_pf_caps(struct hns_roce_dev *hr_dev) +static int hns_roce_query_caps(struct hns_roce_dev *hr_dev) { struct hns_roce_cmq_desc desc[HNS_ROCE_QUERY_PF_CAPS_CMD_NUM]; struct hns_roce_caps *caps = &hr_dev->caps; @@ -2446,15 +2351,17 @@ static int hns_roce_query_pf_caps(struct hns_roce_dev *hr_dev) struct hns_roce_query_pf_caps_c *resp_c; struct hns_roce_query_pf_caps_d *resp_d; struct hns_roce_query_pf_caps_e *resp_e; + enum hns_roce_opcode_type cmd; int ctx_hop_num; int pbl_hop_num; int ret; int i; + cmd = hr_dev->is_vf ? HNS_ROCE_OPC_QUERY_VF_CAPS_NUM : + HNS_ROCE_OPC_QUERY_PF_CAPS_NUM; + for (i = 0; i < HNS_ROCE_QUERY_PF_CAPS_CMD_NUM; i++) { - hns_roce_cmq_setup_basic_desc(&desc[i], - HNS_ROCE_OPC_QUERY_PF_CAPS_NUM, - true); + hns_roce_cmq_setup_basic_desc(&desc[i], cmd, true); if (i < (HNS_ROCE_QUERY_PF_CAPS_CMD_NUM - 1)) desc[i].flag |= cpu_to_le16(HNS_ROCE_CMD_FLAG_NEXT); else @@ -2471,38 +2378,38 @@ static int hns_roce_query_pf_caps(struct hns_roce_dev *hr_dev) resp_d = (struct hns_roce_query_pf_caps_d *)desc[3].data; resp_e = (struct hns_roce_query_pf_caps_e *)desc[4].data; - caps->local_ca_ack_delay = resp_a->local_ca_ack_delay; - caps->max_sq_sg = le16_to_cpu(resp_a->max_sq_sg); - caps->max_sq_inline = le16_to_cpu(resp_a->max_sq_inline); - caps->max_rq_sg = le16_to_cpu(resp_a->max_rq_sg); + caps->local_ca_ack_delay = resp_a->local_ca_ack_delay; + caps->max_sq_sg = le16_to_cpu(resp_a->max_sq_sg); + caps->max_sq_inline = le16_to_cpu(resp_a->max_sq_inline); + caps->max_rq_sg = le16_to_cpu(resp_a->max_rq_sg); caps->max_rq_sg = roundup_pow_of_two(caps->max_rq_sg); - caps->max_extend_sg = le32_to_cpu(resp_a->max_extend_sg); - caps->num_qpc_timer = le16_to_cpu(resp_a->num_qpc_timer); - caps->max_srq_sges = le16_to_cpu(resp_a->max_srq_sges); + caps->max_extend_sg = le32_to_cpu(resp_a->max_extend_sg); + caps->num_qpc_timer = le16_to_cpu(resp_a->num_qpc_timer); + caps->max_srq_sges = le16_to_cpu(resp_a->max_srq_sges); caps->max_srq_sges = roundup_pow_of_two(caps->max_srq_sges); - caps->num_aeq_vectors = resp_a->num_aeq_vectors; - caps->num_other_vectors = resp_a->num_other_vectors; - caps->max_sq_desc_sz = resp_a->max_sq_desc_sz; - caps->max_rq_desc_sz = resp_a->max_rq_desc_sz; - caps->max_srq_desc_sz = resp_a->max_srq_desc_sz; - caps->cqe_sz = resp_a->cqe_sz; - - caps->mtpt_entry_sz = resp_b->mtpt_entry_sz; - caps->irrl_entry_sz = resp_b->irrl_entry_sz; - caps->trrl_entry_sz = resp_b->trrl_entry_sz; - caps->cqc_entry_sz = resp_b->cqc_entry_sz; - caps->srqc_entry_sz = resp_b->srqc_entry_sz; - caps->idx_entry_sz = resp_b->idx_entry_sz; - caps->sccc_sz = resp_b->sccc_sz; - caps->max_mtu = resp_b->max_mtu; - caps->qpc_sz = le16_to_cpu(resp_b->qpc_sz); - caps->min_cqes = resp_b->min_cqes; - caps->min_wqes = resp_b->min_wqes; - caps->page_size_cap = le32_to_cpu(resp_b->page_size_cap); - caps->pkey_table_len[0] = resp_b->pkey_table_len; - caps->phy_num_uars = resp_b->phy_num_uars; - ctx_hop_num = resp_b->ctx_hop_num; - pbl_hop_num = resp_b->pbl_hop_num; + caps->num_aeq_vectors = resp_a->num_aeq_vectors; + caps->num_other_vectors = resp_a->num_other_vectors; + caps->max_sq_desc_sz = resp_a->max_sq_desc_sz; + caps->max_rq_desc_sz = resp_a->max_rq_desc_sz; + caps->max_srq_desc_sz = resp_a->max_srq_desc_sz; + caps->cqe_sz = resp_a->cqe_sz; + + caps->mtpt_entry_sz = resp_b->mtpt_entry_sz; + caps->irrl_entry_sz = resp_b->irrl_entry_sz; + caps->trrl_entry_sz = resp_b->trrl_entry_sz; + caps->cqc_entry_sz = resp_b->cqc_entry_sz; + caps->srqc_entry_sz = resp_b->srqc_entry_sz; + caps->idx_entry_sz = resp_b->idx_entry_sz; + caps->sccc_sz = resp_b->sccc_sz; + caps->max_mtu = resp_b->max_mtu; + caps->qpc_sz = le16_to_cpu(resp_b->qpc_sz); + caps->min_cqes = resp_b->min_cqes; + caps->min_wqes = resp_b->min_wqes; + caps->page_size_cap = le32_to_cpu(resp_b->page_size_cap); + caps->pkey_table_len[0] = resp_b->pkey_table_len; + caps->phy_num_uars = resp_b->phy_num_uars; + ctx_hop_num = resp_b->ctx_hop_num; + pbl_hop_num = resp_b->pbl_hop_num; caps->num_pds = 1 << hr_reg_read(resp_c, PF_CAPS_C_NUM_PDS); @@ -2525,8 +2432,6 @@ static int hns_roce_query_pf_caps(struct hns_roce_dev *hr_dev) caps->ceqe_depth = 1 << hr_reg_read(resp_d, PF_CAPS_D_CEQ_DEPTH); caps->num_comp_vectors = hr_reg_read(resp_d, PF_CAPS_D_NUM_CEQS); caps->aeqe_depth = 1 << hr_reg_read(resp_d, PF_CAPS_D_AEQ_DEPTH); - caps->default_aeq_arm_st = hr_reg_read(resp_d, PF_CAPS_D_AEQ_ARM_ST); - caps->default_ceq_arm_st = hr_reg_read(resp_d, PF_CAPS_D_CEQ_ARM_ST); caps->reserved_pds = hr_reg_read(resp_d, PF_CAPS_D_RSV_PDS); caps->num_uars = 1 << hr_reg_read(resp_d, PF_CAPS_D_NUM_UARS); caps->reserved_qps = hr_reg_read(resp_d, PF_CAPS_D_RSV_QPS); @@ -2537,10 +2442,6 @@ static int hns_roce_query_pf_caps(struct hns_roce_dev *hr_dev) caps->reserved_cqs = hr_reg_read(resp_e, PF_CAPS_E_RSV_CQS); caps->reserved_srqs = hr_reg_read(resp_e, PF_CAPS_E_RSV_SRQS); caps->reserved_lkey = hr_reg_read(resp_e, PF_CAPS_E_RSV_LKEYS); - caps->default_ceq_max_cnt = le16_to_cpu(resp_e->ceq_max_cnt); - caps->default_ceq_period = le16_to_cpu(resp_e->ceq_period); - caps->default_aeq_max_cnt = le16_to_cpu(resp_e->aeq_max_cnt); - caps->default_aeq_period = le16_to_cpu(resp_e->aeq_period); caps->qpc_hop_num = ctx_hop_num; caps->sccc_hop_num = ctx_hop_num; @@ -2557,6 +2458,20 @@ static int hns_roce_query_pf_caps(struct hns_roce_dev *hr_dev) if (!(caps->page_size_cap & PAGE_SIZE)) caps->page_size_cap = HNS_ROCE_V2_PAGE_SIZE_SUPPORTED; + + if (!hr_dev->is_vf) { + caps->cqe_sz = resp_a->cqe_sz; + caps->qpc_sz = le16_to_cpu(resp_b->qpc_sz); + caps->default_aeq_arm_st = + hr_reg_read(resp_d, PF_CAPS_D_AEQ_ARM_ST); + caps->default_ceq_arm_st = + hr_reg_read(resp_d, PF_CAPS_D_CEQ_ARM_ST); + caps->default_ceq_max_cnt = le16_to_cpu(resp_e->ceq_max_cnt); + caps->default_ceq_period = le16_to_cpu(resp_e->ceq_period); + caps->default_aeq_max_cnt = le16_to_cpu(resp_e->aeq_max_cnt); + caps->default_aeq_period = le16_to_cpu(resp_e->aeq_period); + } + return 0; } @@ -2626,7 +2541,11 @@ static int hns_roce_v2_vf_profile(struct hns_roce_dev *hr_dev) hr_dev->func_num = 1; - set_default_caps(hr_dev); + ret = hns_roce_query_caps(hr_dev); + if (ret) { + dev_err(dev, "failed to query VF caps, ret = %d.\n", ret); + return ret; + } ret = hns_roce_query_vf_resource(hr_dev); if (ret) { @@ -2666,9 +2585,11 @@ static int hns_roce_v2_pf_profile(struct hns_roce_dev *hr_dev) return ret; } - ret = hns_roce_query_pf_caps(hr_dev); - if (ret) - set_default_caps(hr_dev); + ret = hns_roce_query_caps(hr_dev); + if (ret) { + dev_err(dev, "failed to query PF caps, ret = %d.\n", ret); + return ret; + } ret = hns_roce_query_pf_resource(hr_dev); if (ret) { diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.h b/drivers/infiniband/hw/hns/hns_roce_hw_v2.h index 90401577865e..e5f3a4639bf3 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.h +++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.h @@ -35,46 +35,16 @@ #include <linux/bitops.h> -#define HNS_ROCE_V2_MAX_QP_NUM 0x1000 -#define HNS_ROCE_V2_MAX_QPC_TIMER_NUM 0x200 -#define HNS_ROCE_V2_MAX_WQE_NUM 0x8000 -#define HNS_ROCE_V2_MAX_SRQ_WR 0x8000 -#define HNS_ROCE_V2_MAX_SRQ_SGE 64 -#define HNS_ROCE_V2_MAX_CQ_NUM 0x100000 -#define HNS_ROCE_V2_MAX_CQC_TIMER_BT_NUM 0x100 -#define HNS_ROCE_V2_MAX_SRQ_NUM 0x100000 -#define HNS_ROCE_V2_MAX_CQE_NUM 0x400000 -#define HNS_ROCE_V2_MAX_RQ_SGE_NUM 64 -#define HNS_ROCE_V2_MAX_SQ_SGE_NUM 64 -#define HNS_ROCE_V2_MAX_EXTEND_SGE_NUM 0x200000 -#define HNS_ROCE_V2_MAX_SQ_INLINE 0x20 -#define HNS_ROCE_V3_MAX_SQ_INLINE 0x400 #define HNS_ROCE_V2_MAX_RC_INL_INN_SZ 32 -#define HNS_ROCE_V2_UAR_NUM 256 -#define HNS_ROCE_V2_PHY_UAR_NUM 1 +#define HNS_ROCE_V2_MTT_ENTRY_SZ 64 #define HNS_ROCE_V2_AEQE_VEC_NUM 1 #define HNS_ROCE_V2_ABNORMAL_VEC_NUM 1 -#define HNS_ROCE_V2_MAX_MTPT_NUM 0x100000 #define HNS_ROCE_V2_MAX_MTT_SEGS 0x1000000 #define HNS_ROCE_V2_MAX_SRQWQE_SEGS 0x1000000 #define HNS_ROCE_V2_MAX_IDX_SEGS 0x1000000 -#define HNS_ROCE_V2_MAX_PD_NUM 0x1000000 #define HNS_ROCE_V2_MAX_XRCD_NUM 0x1000000 #define HNS_ROCE_V2_RSV_XRCD_NUM 0 -#define HNS_ROCE_V2_MAX_QP_INIT_RDMA 128 -#define HNS_ROCE_V2_MAX_QP_DEST_RDMA 128 -#define HNS_ROCE_V2_MAX_SQ_DESC_SZ 64 -#define HNS_ROCE_V2_MAX_RQ_DESC_SZ 16 -#define HNS_ROCE_V2_MAX_SRQ_DESC_SZ 64 -#define HNS_ROCE_V2_IRRL_ENTRY_SZ 64 -#define HNS_ROCE_V2_EXT_ATOMIC_TRRL_ENTRY_SZ 100 -#define HNS_ROCE_V2_CQC_ENTRY_SZ 64 -#define HNS_ROCE_V2_SRQC_ENTRY_SZ 64 -#define HNS_ROCE_V2_MTPT_ENTRY_SZ 64 -#define HNS_ROCE_V2_MTT_ENTRY_SZ 64 -#define HNS_ROCE_V2_IDX_ENTRY_SZ 4 -#define HNS_ROCE_V2_SCCC_SZ 32 #define HNS_ROCE_V3_SCCC_SZ 64 #define HNS_ROCE_V3_GMV_ENTRY_SZ 32 @@ -242,6 +212,7 @@ enum hns_roce_opcode_type { HNS_ROCE_OPC_QUERY_FUNC_INFO = 0x8407, HNS_ROCE_OPC_QUERY_PF_CAPS_NUM = 0x8408, HNS_ROCE_OPC_CFG_ENTRY_SIZE = 0x8409, + HNS_ROCE_OPC_QUERY_VF_CAPS_NUM = 0x8410, HNS_ROCE_OPC_CFG_SGID_TB = 0x8500, HNS_ROCE_OPC_CFG_SMAC_TB = 0x8501, HNS_ROCE_OPC_POST_MB = 0x8504, -- 2.30.0

1 0

[RFC PATCH openEuler-1.0-LTS] sched: memqos: add memqos for dynamic affinity
by Wang ShaoBo 22 Mar '23

22 Mar '23

Add debug memband interface to dynamic affinity, this would be useful for those threads sensitive to memory bandwidth. Signed-off-by: Wang ShaoBo <bobo.shaobowang(a)huawei.com> --- arch/arm64/include/asm/mpam.h | 2 + arch/arm64/include/asm/mpam_sched.h | 2 + arch/arm64/kernel/mpam/mpam_device.c | 58 ++- arch/arm64/kernel/mpam/mpam_resctrl.c | 65 ++++ include/linux/memqos.h | 142 +++++++ include/linux/sched.h | 14 +- include/linux/sysctl.h | 2 + kernel/cgroup/cpuset.c | 1 + kernel/exit.c | 3 + kernel/fork.c | 4 + kernel/sched/Makefile | 1 + kernel/sched/core.c | 29 +- kernel/sched/fair.c | 14 +- kernel/sched/memqos/Makefile | 6 + kernel/sched/memqos/memqos.c | 297 +++++++++++++++ kernel/sched/memqos/phase_feature_sysctl.c | 126 +++++++ kernel/sched/memqos/phase_memband.c | 145 ++++++++ kernel/sched/memqos/phase_perf.c | 409 +++++++++++++++++++++ kernel/sched/memqos/phase_sim_knn.c | 92 +++++ kernel/sysctl.c | 7 + mm/mempolicy.c | 10 +- 21 files changed, 1409 insertions(+), 20 deletions(-) create mode 100644 include/linux/memqos.h create mode 100644 kernel/sched/memqos/Makefile create mode 100644 kernel/sched/memqos/memqos.c create mode 100644 kernel/sched/memqos/phase_feature_sysctl.c create mode 100644 kernel/sched/memqos/phase_memband.c create mode 100644 kernel/sched/memqos/phase_perf.c create mode 100644 kernel/sched/memqos/phase_sim_knn.c diff --git a/arch/arm64/include/asm/mpam.h b/arch/arm64/include/asm/mpam.h index 6338eab817e75..269a91d8ca907 100644 --- a/arch/arm64/include/asm/mpam.h +++ b/arch/arm64/include/asm/mpam.h @@ -4,6 +4,8 @@ #ifdef CONFIG_MPAM extern int mpam_rmid_to_partid_pmg(int rmid, int *partid, int *pmg); + +void mpam_component_config_mbwu_mon(int partid, int pmg, int monitor, int *result, int nr); #endif #endif /* _ASM_ARM64_MPAM_H */ diff --git a/arch/arm64/include/asm/mpam_sched.h b/arch/arm64/include/asm/mpam_sched.h index 08ed349b6efa1..32d08cf654b31 100644 --- a/arch/arm64/include/asm/mpam_sched.h +++ b/arch/arm64/include/asm/mpam_sched.h @@ -40,6 +40,8 @@ static inline void mpam_sched_in(void) __mpam_sched_in(); } +void __mpam_sched_in_v2(struct task_struct *tsk); + #else static inline void mpam_sched_in(void) {} diff --git a/arch/arm64/kernel/mpam/mpam_device.c b/arch/arm64/kernel/mpam/mpam_device.c index 6455c69f132fd..48de3982a0b9a 100644 --- a/arch/arm64/kernel/mpam/mpam_device.c +++ b/arch/arm64/kernel/mpam/mpam_device.c @@ -84,14 +84,14 @@ void mpam_class_list_lock_held(void) static inline u32 mpam_read_reg(struct mpam_device *dev, u16 reg) { WARN_ON_ONCE(reg > SZ_MPAM_DEVICE); - assert_spin_locked(&dev->lock); + //assert_spin_locked(&dev->lock); /* * If we touch a device that isn't accessible from this CPU we may get * an external-abort. */ - WARN_ON_ONCE(preemptible()); - WARN_ON_ONCE(!cpumask_test_cpu(smp_processor_id(), &dev->fw_affinity)); + //WARN_ON_ONCE(preemptible()); + //WARN_ON_ONCE(!cpumask_test_cpu(smp_processor_id(), &dev->fw_affinity)); return readl_relaxed(dev->mapped_hwpage + reg); } @@ -99,14 +99,14 @@ static inline u32 mpam_read_reg(struct mpam_device *dev, u16 reg) static inline void mpam_write_reg(struct mpam_device *dev, u16 reg, u32 val) { WARN_ON_ONCE(reg > SZ_MPAM_DEVICE); - assert_spin_locked(&dev->lock); + //assert_spin_locked(&dev->lock); /* * If we touch a device that isn't accessible from this CPU we may get * an external-abort. If we're lucky, we corrupt another mpam:component. */ - WARN_ON_ONCE(preemptible()); - WARN_ON_ONCE(!cpumask_test_cpu(smp_processor_id(), &dev->fw_affinity)); + //WARN_ON_ONCE(preemptible()); + //WARN_ON_ONCE(!cpumask_test_cpu(smp_processor_id(), &dev->fw_affinity)); writel_relaxed(val, dev->mapped_hwpage + reg); } @@ -1208,6 +1208,7 @@ static u32 mpam_device_read_mbwu_mon(struct mpam_device *dev, { u16 mon; u32 clt, flt, cur_clt, cur_flt; + u32 total = 0; mon = args->mon; @@ -1249,7 +1250,12 @@ static u32 mpam_device_read_mbwu_mon(struct mpam_device *dev, wmb(); } - return mpam_read_reg(dev, MSMON_MBWU); + total += mpam_read_reg(dev, MSMON_MBWU); + total += mpam_read_reg(dev, MSMON_MBWU); + total += mpam_read_reg(dev, MSMON_MBWU); + total += mpam_read_reg(dev, MSMON_MBWU); + total += mpam_read_reg(dev, MSMON_MBWU); + return total / 5; } static int mpam_device_frob_mon(struct mpam_device *dev, @@ -1470,6 +1476,44 @@ static void mpam_component_device_sync(void *__ctx) cpumask_set_cpu(smp_processor_id(), &ctx->updated_on); } +static DEFINE_SPINLOCK(mpam_tmp_lock); + +void mpam_component_config_mbwu_mon(int partid, int pmg, int monitor, int *result, int nr) +{ + struct mpam_class *class; + struct mpam_component *comp; + struct mpam_device *dev; + struct sync_args args; + int i = 0; + + args.pmg = pmg; + args.mon = monitor; + args.closid.reqpartid = partid; + args.match_pmg = 1; + + spin_lock(&mpam_tmp_lock); + list_for_each_entry(class, &mpam_classes, classes_list) { + if (class->type != MPAM_CLASS_MEMORY) + continue; + + list_for_each_entry(comp, &class->components, class_list) { + if (i >= nr) { + pr_err_once("error, i > result nr"); + break; + } + result[i] = 0; + list_for_each_entry(dev, &comp->devices, comp_list) { + result[i] += mpam_device_read_mbwu_mon(dev, &args); + } + i++; + } + break; + } + spin_unlock(&mpam_tmp_lock); + +} +EXPORT_SYMBOL(mpam_component_config_mbwu_mon); + /** * in some cases/platforms the MSC register access is only possible with * the associated CPUs. And need to check if those CPUS are online before diff --git a/arch/arm64/kernel/mpam/mpam_resctrl.c b/arch/arm64/kernel/mpam/mpam_resctrl.c index 60d3d8706a38b..f4d87964616f2 100644 --- a/arch/arm64/kernel/mpam/mpam_resctrl.c +++ b/arch/arm64/kernel/mpam/mpam_resctrl.c @@ -2226,6 +2226,71 @@ int mpam_resctrl_init(void) return resctrl_group_init(); } + +void __mpam_sched_in_v2(struct task_struct *tsk) +{ + struct intel_pqr_state *state = this_cpu_ptr(&pqr_state); + u64 partid_d, partid_i; + u64 rmid = state->default_rmid; + u64 closid = state->default_closid; + u64 reqpartid = 0; + u64 pmg = 0; + + /* + * If this task has a closid/rmid assigned, use it. + * Else use the closid/rmid assigned to this cpu. + */ + if (static_branch_likely(&resctrl_alloc_enable_key)) { + if (tsk->closid) + closid = tsk->closid; + } + + if (static_branch_likely(&resctrl_mon_enable_key)) { + if (tsk->rmid) + rmid = tsk->rmid; + } + + if (closid != state->cur_closid || rmid != state->cur_rmid) { + u64 reg; + + resctrl_navie_rmid_partid_pmg(rmid, (int *)&reqpartid, (int *)&pmg); + + if (resctrl_cdp_enabled) { + resctrl_cdp_mpamid_map_val(reqpartid, CDP_DATA, partid_d); + resctrl_cdp_mpamid_map_val(reqpartid, CDP_CODE, partid_i); + + /* set in EL0 */ + reg = mpam_read_sysreg_s(SYS_MPAM0_EL1, "SYS_MPAM0_EL1"); + reg = PARTID_D_SET(reg, partid_d); + reg = PARTID_I_SET(reg, partid_i); + reg = PMG_SET(reg, pmg); + mpam_write_sysreg_s(reg, SYS_MPAM0_EL1, "SYS_MPAM0_EL1"); + + /* set in EL1 */ + reg = mpam_read_sysreg_s(SYS_MPAM1_EL1, "SYS_MPAM1_EL1"); + reg = PARTID_D_SET(reg, partid_d); + reg = PARTID_I_SET(reg, partid_i); + reg = PMG_SET(reg, pmg); + mpam_write_sysreg_s(reg, SYS_MPAM1_EL1, "SYS_MPAM1_EL1"); + } else { + /* set in EL0 */ + reg = mpam_read_sysreg_s(SYS_MPAM0_EL1, "SYS_MPAM0_EL1"); + reg = PARTID_SET(reg, reqpartid); + reg = PMG_SET(reg, pmg); + mpam_write_sysreg_s(reg, SYS_MPAM0_EL1, "SYS_MPAM0_EL1"); + + /* set in EL1 */ + reg = mpam_read_sysreg_s(SYS_MPAM1_EL1, "SYS_MPAM1_EL1"); + reg = PARTID_SET(reg, reqpartid); + reg = PMG_SET(reg, pmg); + mpam_write_sysreg_s(reg, SYS_MPAM1_EL1, "SYS_MPAM1_EL1"); + } + + state->cur_rmid = rmid; + state->cur_closid = closid; + } +} + /* * __intel_rdt_sched_in() - Writes the task's CLOSid/RMID to IA32_PQR_MSR * diff --git a/include/linux/memqos.h b/include/linux/memqos.h new file mode 100644 index 0000000000000..814e9935590d3 --- /dev/null +++ b/include/linux/memqos.h @@ -0,0 +1,142 @@ +#ifndef _MEMQOS_H +#define _MEMQOS_H + +#include <linux/vmstat.h> +#include <linux/rbtree.h> +//#include <linux/sched.h> + +struct task_struct; + +struct memqos_domain { + int dom_id; + int total_memband_div_10; + int total_out_memband_div_10; + + //record 10 timers + int memband_ringpos; + int memband_div_10_history[4][10]; +}; + +struct memqos_mpam_profile { + int partid; + int pmg; + int monitor; + + struct task_struct *tsk; + int used; +}; + +struct memqos_wait_profile { + struct memqos_mpam_profile *profile; + struct list_head wait_list; +}; + +struct memqos_class { + struct list_head turbo_list; + struct list_head tasks_list; +}; + +#include <linux/topology.h> +//embed in task_struct + +struct task_memqos { + int ipc_ringpos; + int ipcx10; + int ipcx10_total[4]; + int ipcx10_history[10]; + + int memband_div_10; + int memband_ringpos; + int memband_div_10_total[4]; + int memband_div_10_history[4][10]; + + u32 sample_times; + int account_ready; + int numa_score[4]; + int turbo; + + struct memqos_wait_profile mpam_profile; + + struct list_head turbo_list; + struct list_head task_list; + + struct cpumask *advise_mem_node_mask; + int preferred_nid; + + int class_id; + + int corrupt; +}; + +#define PHASE_PEVENT_NUM 10 + +struct phase_event_pcount { + u64 data[PHASE_PEVENT_NUM]; +}; + +struct phase_event_count { + struct phase_event_pcount pcount; +}; + +void phase_update_mpam_label(struct task_struct *tsk); + +void phase_release_mpam_label(struct task_struct *tsk); + +static inline void memqos_update_mpam_label(struct task_struct *tsk) +{ + phase_update_mpam_label(tsk); +} + +static inline void memqos_release_mpam_label(struct task_struct *tsk) +{ + phase_release_mpam_label(tsk); +} + +void phase_destroy_waitqueue(struct task_struct *tsk); + +void phase_get_memband(struct memqos_mpam_profile *pm, int *result, int nr); + +DECLARE_STATIC_KEY_FALSE(sched_phase); +DECLARE_STATIC_KEY_FALSE(sched_phase_printk); + +int phase_perf_create(void); + +void phase_perf_release(void); + +void memqos_account_task(struct task_struct *p, int cpu); + +void memqos_drop_class(struct task_struct *p); + +void phase_account_task(struct task_struct *p, int cpu); + +static inline void memqos_task_collect_data(struct task_struct *p, int cpu) +{ + phase_account_task(p, cpu); +} + +static inline void memqos_task_account(struct task_struct *p, int cpu) +{ + memqos_account_task(p, cpu); +} + +static inline void memqos_task_exit(struct task_struct *p) +{ + + memqos_drop_class(p); + phase_destroy_waitqueue(p); +} + +void memqos_select_nicest_cpus(struct task_struct *p); + +void memqos_exclude_low_level_task_single(struct task_struct *p); + +int knn_get_tag(int ipcx10, int memband_div_10); + +void memqos_init_class(struct task_struct *p); + +void phase_trace_printk(struct task_struct *p); +static inline void memqos_trace_printk(struct task_struct *p) +{ + phase_trace_printk(p); +} +#endif diff --git a/include/linux/sched.h b/include/linux/sched.h index 928186f161000..5f710dc5bc03b 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -29,6 +29,7 @@ #include <linux/task_io_accounting.h> #include <linux/rseq.h> #include <linux/thread_bits.h> +#include <linux/memqos.h> /* task_struct member predeclarations (sorted alphabetically): */ struct audit_context; @@ -1268,7 +1269,7 @@ struct task_struct { #if !defined(__GENKSYMS__) #if defined(CONFIG_QOS_SCHED_DYNAMIC_AFFINITY) cpumask_t *prefer_cpus; - const cpumask_t *select_cpus; + cpumask_t *select_cpus; #else KABI_RESERVE(6) KABI_RESERVE(7) @@ -1279,6 +1280,10 @@ struct task_struct { #endif KABI_RESERVE(8) +#ifdef CONFIG_QOS_SCHED_DYNAMIC_AFFINITY + struct task_memqos sched_memqos; +#endif + /* CPU-specific state of this task: */ struct thread_struct thread; @@ -1998,6 +2003,13 @@ int set_prefer_cpus_ptr(struct task_struct *p, const struct cpumask *new_mask); int sched_prefer_cpus_fork(struct task_struct *p, struct task_struct *orig); void sched_prefer_cpus_free(struct task_struct *p); +static inline bool prefer_cpus_valid(struct task_struct *p) +{ + return p->prefer_cpus && + !cpumask_empty(p->prefer_cpus) && + !cpumask_equal(p->prefer_cpus, &p->cpus_allowed) && + cpumask_subset(p->prefer_cpus, &p->cpus_allowed); +} #endif #endif diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h index b769ecfcc3bd4..73bce39107cb3 100644 --- a/include/linux/sysctl.h +++ b/include/linux/sysctl.h @@ -230,6 +230,8 @@ static inline void setup_sysctl_set(struct ctl_table_set *p, #endif /* CONFIG_SYSCTL */ +extern struct ctl_table phase_table[]; + int sysctl_max_threads(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos); diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c index 55bfbc4cdb16c..d94a9065a5605 100644 --- a/kernel/cgroup/cpuset.c +++ b/kernel/cgroup/cpuset.c @@ -106,6 +106,7 @@ struct cpuset { nodemask_t mems_allowed; #ifdef CONFIG_QOS_SCHED_DYNAMIC_AFFINITY cpumask_var_t prefer_cpus; + int mem_turbo; #endif /* effective CPUs and Memory Nodes allow to tasks */ diff --git a/kernel/exit.c b/kernel/exit.c index 2a32d32bdc03d..b731c19618176 100644 --- a/kernel/exit.c +++ b/kernel/exit.c @@ -699,6 +699,8 @@ static void check_stack_usage(void) static inline void check_stack_usage(void) {} #endif +#include <linux/memqos.h> + void __noreturn do_exit(long code) { struct task_struct *tsk = current; @@ -806,6 +808,7 @@ void __noreturn do_exit(long code) * because of cgroup mode, must be called before cgroup_exit() */ perf_event_exit_task(tsk); + memqos_task_exit(tsk); sched_autogroup_exit_task(tsk); cgroup_exit(tsk); diff --git a/kernel/fork.c b/kernel/fork.c index b5453a26655e2..0a762b92dc814 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -841,6 +841,8 @@ void set_task_stack_end_magic(struct task_struct *tsk) *stackend = STACK_END_MAGIC; /* for overflow detection */ } + +#include <linux/memqos.h> static struct task_struct *dup_task_struct(struct task_struct *orig, int node) { struct task_struct *tsk; @@ -923,6 +925,8 @@ static struct task_struct *dup_task_struct(struct task_struct *orig, int node) kcov_task_init(tsk); + memqos_init_class(tsk); + #ifdef CONFIG_FAULT_INJECTION tsk->fail_nth = 0; #endif diff --git a/kernel/sched/Makefile b/kernel/sched/Makefile index 7fe183404c383..471380d6686e3 100644 --- a/kernel/sched/Makefile +++ b/kernel/sched/Makefile @@ -29,3 +29,4 @@ obj-$(CONFIG_CPU_FREQ) += cpufreq.o obj-$(CONFIG_CPU_FREQ_GOV_SCHEDUTIL) += cpufreq_schedutil.o obj-$(CONFIG_MEMBARRIER) += membarrier.o obj-$(CONFIG_CPU_ISOLATION) += isolation.o +obj-$(CONFIG_QOS_SCHED_DYNAMIC_AFFINITY) += memqos/ diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 970616070da86..1171025aaa440 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -2787,6 +2787,8 @@ asmlinkage __visible void schedule_tail(struct task_struct *prev) calculate_sigpending(); } +#include <linux/memqos.h> + /* * context_switch - switch to the new MM and the new thread's register state. */ @@ -2794,6 +2796,8 @@ static __always_inline struct rq * context_switch(struct rq *rq, struct task_struct *prev, struct task_struct *next, struct rq_flags *rf) { + struct rq *ret; + prepare_task_switch(rq, prev, next); /* @@ -2837,6 +2841,18 @@ context_switch(struct rq *rq, struct task_struct *prev, } } + //account and release + memqos_task_account(prev, smp_processor_id()); + + if (prefer_cpus_valid(prev)) + memqos_trace_printk(prev); + + memqos_release_mpam_label(prev); + + //label new task's mpamid + if (prefer_cpus_valid(next)) + memqos_update_mpam_label(next); + rq->clock_update_flags &= ~(RQCF_ACT_SKIP|RQCF_REQ_SKIP); prepare_lock_switch(rq, next, rf); @@ -2845,7 +2861,9 @@ context_switch(struct rq *rq, struct task_struct *prev, switch_to(prev, next, prev); barrier(); - return finish_task_switch(prev); + ret = finish_task_switch(prev); + + return ret; } /* @@ -3058,8 +3076,12 @@ unsigned long long task_sched_runtime(struct task_struct *p) void scheduler_tick(void) { int cpu = smp_processor_id(); + //memqos clooect next cpu's memband and perf + int cpu_memqos = (cpu + 1) % nr_cpu_ids; struct rq *rq = cpu_rq(cpu); + struct rq *rq_next = cpu_rq(cpu_memqos); struct task_struct *curr = rq->curr; + struct task_struct *curr_memqos = rq_next->curr; struct rq_flags rf; sched_clock_tick(); @@ -3075,6 +3097,10 @@ void scheduler_tick(void) perf_event_task_tick(); + //only monitor task enabled dynamic affinity + if (curr_memqos && prefer_cpus_valid(curr_memqos)) + memqos_task_collect_data(curr_memqos, cpu_memqos); + #ifdef CONFIG_SMP rq->idle_balance = idle_cpu(cpu); trigger_load_balance(rq); @@ -3524,6 +3550,7 @@ static void __sched notrace __schedule(bool preempt) /* Also unlocks the rq: */ rq = context_switch(rq, prev, next, &rf); } else { + memqos_task_account(prev, smp_processor_id()); rq->clock_update_flags &= ~(RQCF_ACT_SKIP|RQCF_REQ_SKIP); rq_unlock_irq(rq, &rf); } diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index af55a26d11fcb..12e9675495d2c 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -6675,6 +6675,7 @@ static int wake_cap(struct task_struct *p, int cpu, int prev_cpu) } #ifdef CONFIG_QOS_SCHED_DYNAMIC_AFFINITY +#include <linux/memqos.h> /* * Low utilization threshold for CPU * @@ -6749,14 +6750,6 @@ static inline int cpu_vutil_of(int cpu) return cputime->vutil; } -static inline bool prefer_cpus_valid(struct task_struct *p) -{ - return p->prefer_cpus && - !cpumask_empty(p->prefer_cpus) && - !cpumask_equal(p->prefer_cpus, &p->cpus_allowed) && - cpumask_subset(p->prefer_cpus, &p->cpus_allowed); -} - /* * set_task_select_cpus: select the cpu range for task * @p: the task whose available cpu range will to set @@ -6828,8 +6821,13 @@ static void set_task_select_cpus(struct task_struct *p, int *idlest_cpu, if (util_avg_sum < sysctl_sched_util_low_pct * cpumask_weight(p->prefer_cpus)) { p->select_cpus = p->prefer_cpus; + memqos_select_nicest_cpus(p); if (sd_flag & SD_BALANCE_WAKE) schedstat_inc(p->se.dyn_affi_stats->nr_wakeups_preferred_cpus); + } else { + //select trubo task + //select low class task + memqos_exclude_low_level_task_single(p); } } #endif diff --git a/kernel/sched/memqos/Makefile b/kernel/sched/memqos/Makefile new file mode 100644 index 0000000000000..ed8f42649a8a7 --- /dev/null +++ b/kernel/sched/memqos/Makefile @@ -0,0 +1,6 @@ +# SPDX-License-Identifier: GPL-2.0 +# These files are disabled because they produce non-interesting flaky coverage +# that is not a function of syscall inputs. E.g. involuntary context switches. +KCOV_INSTRUMENT := n + +obj-y := memqos.o phase_feature_sysctl.o phase_memband.o phase_perf.o phase_sim_knn.o diff --git a/kernel/sched/memqos/memqos.c b/kernel/sched/memqos/memqos.c new file mode 100644 index 0000000000000..ddf8785439aa6 --- /dev/null +++ b/kernel/sched/memqos/memqos.c @@ -0,0 +1,297 @@ +#include <linux/memqos.h> +#include <linux/cpumask.h> +#include <linux/sched.h> + +static void memqos_set_task_classid(struct task_struct *p) +{ + int class_id; + int memband_div_10 = p->sched_memqos.memband_div_10; + int ipcx10 = p->sched_memqos.ipcx10; + + class_id = knn_get_tag((u64)ipcx10, (u64)memband_div_10); + p->sched_memqos.class_id = class_id; +} + +//static memqos_domain mq_domains[] = { +// {.dom_id = 0, .total_memband = 0, .total_out_memband = 0,}, +// {.dom_id = 1, .total_memband = 0, .total_out_memband = 0,}, +// {.dom_id = 2, .total_memband = 0, .total_out_memband = 0,}, +// {.dom_id = 3, .total_memband = 0, .total_out_memband = 0,}, +//}; + +static DEFINE_PER_CPU(struct memqos_class, memqos_classes[8]); +//static DEFINE_PER_CPU(spinlock_t, memqos_class_lock); +static DEFINE_SPINLOCK(memqos_class_lock); + +static int memqos_class_online(unsigned int cpu) +{ + int class_id = 0; + struct memqos_class *class; + + for (class_id = 0; class_id < 8; class_id++) { + class = &per_cpu(memqos_classes, cpu)[class_id]; + INIT_LIST_HEAD(&class->tasks_list); + INIT_LIST_HEAD(&class->turbo_list); + } + return 0; +} + +static int memqos_class_offline(unsigned int cpu) +{ + return 0; +} + +#include <linux/cpu.h> +#include <linux/cacheinfo.h> + +static void memqos_init(void) +{ + int cpuhp_state = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, + "memqos:online", memqos_class_online, + memqos_class_offline); + if (cpuhp_state <= 0) { + pr_err("Failed to register 'dyn' cpuhp callbacks"); + return; + } +} +late_initcall(memqos_init); + +static void memqos_insert_to_class(struct task_struct *p, int cpu) +{ + unsigned long flag; + int class_id = p->sched_memqos.class_id; + struct memqos_class *class; + struct task_memqos *memqos; + + if (class_id >= 8) + return; + + memqos = &p->sched_memqos; + + class = &per_cpu(memqos_classes, cpu)[class_id]; + + spin_lock_irqsave(&memqos_class_lock, flag); + if (p->sched_memqos.corrupt) { + spin_unlock_irqrestore(&memqos_class_lock, flag); + return; + } + + //pr_info("count:%d %d add (%llx) %llx %llx to list %llx!!!!!!!!!!!!!\n", count, p->pid, &p->sched_memqos.task_list, p->sched_memqos.task_list.next, p->sched_memqos.task_list.prev, &class->tasks_list); + list_move_tail(&p->sched_memqos.task_list, &class->tasks_list); + if (memqos->turbo) + list_move_tail(&p->sched_memqos.turbo_list, &class->turbo_list); + spin_unlock_irqrestore(&memqos_class_lock, flag); +} + +static void memqos_drop_class_without_lock(struct task_struct *p) +{ + //pr_info("%d drop (%llx) %llx %llx to list %llx!!!!!!!!!!!!!\n", p->pid, &p->sched_memqos.task_list, p->sched_memqos.task_list.next, p->sched_memqos.task_list.prev); + list_del_init(&p->sched_memqos.task_list); + list_del_init(&p->sched_memqos.turbo_list); +} + +static void memqos_score(struct task_struct *p) +{ + int total_n1 = p->sched_memqos.memband_div_10_total[0]; + int total_n2 = p->sched_memqos.memband_div_10_total[1]; + int total_n3 = p->sched_memqos.memband_div_10_total[2]; + int total_n4 = p->sched_memqos.memband_div_10_total[3]; + + p->sched_memqos.numa_score[0] = (total_n1 - (total_n2 + total_n3 + total_n4)) * 10 / total_n1; + p->sched_memqos.numa_score[1] = (total_n2 - (total_n1 + total_n3 + total_n4)) * 10 / total_n2; + p->sched_memqos.numa_score[2] = (total_n3 - (total_n1 + total_n2 + total_n4)) * 10 / total_n3; + p->sched_memqos.numa_score[3] = (total_n4 - (total_n1 + total_n2 + total_n3)) * 10 / total_n4; + + //over x% percent + if (p->sched_memqos.numa_score[0] > 0) + p->sched_memqos.turbo = 1; + else if (p->sched_memqos.numa_score[1] > 0) + p->sched_memqos.turbo = 2; + else if (p->sched_memqos.numa_score[2] > 0) + p->sched_memqos.turbo = 3; + else if (p->sched_memqos.numa_score[3] > 0) + p->sched_memqos.turbo = 4; + else + p->sched_memqos.turbo = 0; +} + +void memqos_account_task(struct task_struct *p, int cpu) +{ + if (!p->sched_memqos.account_ready || + p->sched_memqos.corrupt) + return; + memqos_set_task_classid(p); + memqos_insert_to_class(p, cpu); + memqos_score(p); + p->sched_memqos.account_ready = 0; +} + +void memqos_init_class(struct task_struct *p) +{ + memset(&p->sched_memqos, 0, sizeof(struct task_memqos)); + spin_lock(&memqos_class_lock); + INIT_LIST_HEAD(&p->sched_memqos.task_list); + INIT_LIST_HEAD(&p->sched_memqos.turbo_list); + INIT_LIST_HEAD(&p->sched_memqos.mpam_profile.wait_list); + spin_unlock(&memqos_class_lock); + + p->closid = 0; + p->rmid = 0; +} + +//destroy ? +void memqos_drop_class(struct task_struct *p) +{ + spin_lock(&memqos_class_lock); + memqos_drop_class_without_lock(p); + p->sched_memqos.corrupt = 1; + spin_unlock(&memqos_class_lock); +} + +void memqos_select_nicest_cpus(struct task_struct *p) +{ + int i = 0; + int max_score = -10000; + int select_node = 0; + struct task_memqos *memqos = &p->sched_memqos; + + if (!memqos->turbo) { + for (i = 0; i < 4; i++) { + if (!cpumask_intersects(cpumask_of_node(i), p->select_cpus)) + continue; + + if (memqos->numa_score[i] > max_score) { + select_node = i; + max_score = memqos->numa_score[i]; + } + } + + cpumask_and(p->select_cpus, p->select_cpus, cpumask_of_node(select_node)); + //p->sched_memqos.advise_mem_node_mask = cpumask_of_node(select_node); + p->sched_memqos.preferred_nid = memqos->turbo; + return; + } + + select_node = memqos->turbo - 1; + if (cpumask_intersects(cpumask_of_node(select_node), p->select_cpus)) { + cpumask_and(p->select_cpus, p->select_cpus, cpumask_of_node(select_node)); + //p->sched_memqos.advise_mem_node_mask = cpumask_of_node(select_node); + p->sched_memqos.preferred_nid = memqos->turbo; + } + + return; + + //if turbo another cpus, wait... +} + +void memqos_exclude_low_level_task_single(struct task_struct *p) +{ + int i, j, cpu; + int find = 0; + int select_node = 0; + const struct cpumask *cpumask; + struct cpumask *cpumask_med; + struct memqos_class *class; + struct task_memqos *memqos = &p->sched_memqos;; + struct task_struct *tsk = NULL; + int max_score = -100000; + + if (memqos->turbo) { + select_node = memqos->turbo - 1; + cpumask = cpumask_of_node(select_node); + if (!cpumask_intersects(cpumask, p->prefer_cpus) && + (cpumask_intersects(&p->cpus_allowed, cpumask))) { + cpumask_and(p->select_cpus, &p->cpus_allowed, cpumask); + memqos_drop_class(p); + //p->sched_memqos.advise_mem_node_mask = cpumask_of_node(select_node); + p->sched_memqos.preferred_nid = memqos->turbo; + return; + } else if (cpumask_intersects(p->prefer_cpus, cpumask)) { + cpumask_and(p->select_cpus, p->prefer_cpus, cpumask); + //p->sched_memqos.advise_mem_node_mask = cpumask_of_node(select_node); + p->sched_memqos.preferred_nid = memqos->turbo; + } + } + + //select turbo one + for (cpu = 0; cpu < nr_cpu_ids; i++) { + if (!cpumask_test_cpu(cpu, p->prefer_cpus)) + continue; + + spin_lock(&memqos_class_lock); + for (i = 7; i >= 0; i--) { + class = &per_cpu(memqos_classes, cpu)[i]; + list_for_each_entry(memqos, &class->turbo_list, turbo_list) { + if (!memqos->turbo) + continue; + select_node = memqos->turbo - 1; + cpumask = cpumask_of_node(select_node); + if (!cpumask_intersects(cpumask, p->prefer_cpus)) { + tsk = container_of(memqos, struct task_struct, sched_memqos); + if (!cpumask_intersects(cpumask, &tsk->cpus_allowed)) + continue; + cpumask_and(tsk->select_cpus, &tsk->cpus_allowed, cpumask); + //mem prefered + //tsk->sched_memqos.advise_mem_node_mask = cpumask_of_node(select_node); + tsk->sched_memqos.preferred_nid = memqos->turbo; + find = 1; + break; + } + } + if (find) { + memqos_drop_class_without_lock(tsk); + spin_unlock(&memqos_class_lock); + return; + } + } + spin_unlock(&memqos_class_lock); + } + + find = 0; + + //if not, select lower class's tsk + for (cpu = 0; cpu < nr_cpu_ids; i++) { + if (!cpumask_test_cpu(cpu, p->prefer_cpus)) + continue; + + spin_lock(&memqos_class_lock); + //only find below class tsk + for (i = 0; i < memqos->class_id; i++) { + class = &per_cpu(memqos_classes, cpu)[i]; + list_for_each_entry(memqos, &class->tasks_list, task_list) { + if (memqos->turbo) + continue; + + tsk = container_of(memqos, struct task_struct, sched_memqos); + for (j = 0; j < 4; j++) { + if (!cpumask_intersects(cpumask_of_node(i), &tsk->cpus_allowed)) + continue; + if (memqos->numa_score[j] > max_score) { + select_node = j; + max_score = memqos->numa_score[j]; + } + find = 1; + } + if (!find) + continue; + + cpumask_and(cpumask_med, cpumask_of_node(select_node), &tsk->cpus_allowed); + cpumask_andnot(cpumask_med, cpumask_med, p->prefer_cpus); + if (cpumask_empty(cpumask_med)) + continue; + cpumask_copy(tsk->select_cpus, cpumask_med); + //mem prefered + //tsk->sched_memqos.advise_mem_node_mask = cpumask_of_node(select_node); + tsk->sched_memqos.preferred_nid = memqos->turbo; + memqos_drop_class_without_lock(tsk); + spin_unlock(&memqos_class_lock); + return; + } + } + spin_unlock(&memqos_class_lock); + } + + //do not care, this task may out + return; +} + diff --git a/kernel/sched/memqos/phase_feature_sysctl.c b/kernel/sched/memqos/phase_feature_sysctl.c new file mode 100644 index 0000000000000..443ae03275605 --- /dev/null +++ b/kernel/sched/memqos/phase_feature_sysctl.c @@ -0,0 +1,126 @@ +#include <linux/sched.h> +#include <linux/sysctl.h> +#include <linux/capability.h> +#include <linux/cpumask.h> +#include <linux/topology.h> +#include <linux/sched/task.h> + +#include <linux/memqos.h> + +#ifdef CONFIG_PROC_SYSCTL + +DEFINE_STATIC_KEY_FALSE(sched_phase); +DEFINE_STATIC_KEY_FALSE(sched_phase_printk); + +static int set_phase_state(bool enabled) +{ + int err; + int state = static_branch_likely(&sched_phase); + + if (enabled == state) { + pr_warn("phase has already %s\n", state ? "enabled" : "disabled"); + return 0; + } + + if (enabled) { + err = phase_perf_create(); + if (err) { + pr_err("phase enable failed\n"); + return err; + } + static_branch_enable(&sched_phase); + pr_info("phase enabled\n"); + } else { + static_branch_disable(&sched_phase); + phase_perf_release(); + pr_info("phase disabled\n"); + } + + return 0; +} + +/* + * the other procfs files of phase cannot be modified if sched_phase is already enabled + */ +static int phase_proc_state(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + struct ctl_table t; + int err; + int state = static_branch_likely(&sched_phase); + + if (write && !capable(CAP_SYS_ADMIN)) + return -EPERM; + + t = *table; + t.data = &state; + err = proc_dointvec_minmax(&t, write, buffer, lenp, ppos); + if (err < 0) + return err; + if (write) + err = set_phase_state(state); + + return err; +} + +static int set_phase_state_printk(bool enabled) +{ + if (enabled) { + static_branch_enable(&sched_phase_printk); + } else { + static_branch_disable(&sched_phase_printk); + } + + return 0; +} + +/* + * the other procfs files of phase cannot be modified if sched_phase is already enabled + */ +static int phase_proc_state_printk(struct ctl_table *table, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + struct ctl_table t; + int err; + int state = static_branch_likely(&sched_phase); + + if (write && !capable(CAP_SYS_ADMIN)) + return -EPERM; + + t = *table; + t.data = &state; + err = proc_dointvec_minmax(&t, write, buffer, lenp, ppos); + if (err < 0) + return err; + if (write) + err = set_phase_state_printk(state); + + return err; +} + + +static int __maybe_unused zero; +static int __maybe_unused one = 1; + +struct ctl_table phase_table[] = { + { + .procname = "enabled", + .data = NULL, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = phase_proc_state, + .extra1 = &zero, + .extra2 = &one, + }, + { + .procname = "trace_enabled", + .data = NULL, + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = phase_proc_state_printk, + .extra1 = &zero, + .extra2 = &one, + }, + { } +}; +#endif /* CONFIG_PROC_SYSCTL */ diff --git a/kernel/sched/memqos/phase_memband.c b/kernel/sched/memqos/phase_memband.c new file mode 100644 index 0000000000000..d83909c8eca45 --- /dev/null +++ b/kernel/sched/memqos/phase_memband.c @@ -0,0 +1,145 @@ +#include <linux/types.h> +#include <linux/cpu.h> +#include <linux/memqos.h> + +#include <asm/cpu.h> +#include <asm/cputype.h> +#include <asm/cpufeature.h> +#include <asm/mpam_sched.h> + +static const int nr_partid = 15; +static const int nr_monitor = 4; + +static LIST_HEAD(phase_mpam_waitqueue); + +//mpam_profile_res[0] not used +struct memqos_mpam_profile mpam_profile_res[16] = { + { .partid = 0, .monitor = 0, .used = 1}, + { .partid = 1, .monitor = 0,}, + { .partid = 2, .monitor = 1,}, + { .partid = 3, .monitor = 2,}, + { .partid = 4, .monitor = 3,}, + { .partid = 5, .monitor = 0,}, + { .partid = 6, .monitor = 1,}, + { .partid = 7, .monitor = 2,}, + { .partid = 8, .monitor = 3,}, + { .partid = 9, .monitor = 0,}, + { .partid = 10, .monitor = 1,}, + { .partid = 11, .monitor = 2,}, + { .partid = 12, .monitor = 3,}, + { .partid = 13, .monitor = 0,}, + { .partid = 14, .monitor = 1,}, + { .partid = 15, .monitor = 2,}, +}; + +static DEFINE_SPINLOCK(phase_partid_lock); + +void phase_update_mpam_label(struct task_struct *tsk) +{ + int i = 0; + //unsigned long flag; + + WARN_ON_ONCE(tsk->closid); + + if (tsk->sched_memqos.mpam_profile.profile != &mpam_profile_res[0] && + tsk->sched_memqos.mpam_profile.profile != NULL) { + tsk->closid = tsk->sched_memqos.mpam_profile.profile->partid; + tsk->rmid = 0; + mpam_profile_res[tsk->closid].tsk = tsk; + __mpam_sched_in_v2(tsk); + return; + } + + spin_lock(&phase_partid_lock); + //is in profile queue, wait... + if (tsk->sched_memqos.mpam_profile.profile == &mpam_profile_res[0]) { + spin_unlock(&phase_partid_lock); + return; + } + + for (i = 1; i < 16; i++) { + if (mpam_profile_res[i].used) { + continue; + } + + tsk->sched_memqos.mpam_profile.profile = NULL; + break; + } + + if (i == 16) { + list_move_tail(&tsk->sched_memqos.mpam_profile.wait_list, &phase_mpam_waitqueue); + tsk->sched_memqos.mpam_profile.profile = &mpam_profile_res[0]; + spin_unlock(&phase_partid_lock); + //wait... + return; + } + + mpam_profile_res[i].used = 1; + spin_unlock(&phase_partid_lock); + + tsk->closid = mpam_profile_res[i].partid; + mpam_profile_res[i].tsk = tsk; + tsk->sched_memqos.mpam_profile.profile = &mpam_profile_res[i]; + tsk->rmid = 0; + __mpam_sched_in_v2(tsk); +} + +static void phase_release_mpam_label_without_lock(struct task_struct *tsk) +{ + int closid; + struct memqos_wait_profile *next; + + //assert locked + + if (tsk->closid == 0) + return; + + closid = tsk->closid; + tsk->closid = 0; + tsk->sched_memqos.mpam_profile.profile = NULL; + mpam_profile_res[closid].used = 0; + mpam_profile_res[closid].tsk = NULL; + + next = list_first_entry_or_null(&phase_mpam_waitqueue, struct memqos_wait_profile, wait_list); + if (next) { + list_del_init(&next->wait_list); + next->profile = &mpam_profile_res[closid]; + mpam_profile_res[closid].used = 1; + } + + return; +} + +//task shutdown +void phase_destroy_waitqueue(struct task_struct *tsk) +{ + spin_lock(&phase_partid_lock); + + //if (tsk->sched_memqos.mpam_profile.profile == &mpam_profile_res[0]) { + list_del_init(&tsk->sched_memqos.mpam_profile.wait_list); + //} else { + phase_release_mpam_label_without_lock(tsk); + //} + spin_unlock(&phase_partid_lock); +} + +void phase_release_mpam_label(struct task_struct *tsk) +{ + spin_lock(&phase_partid_lock); + phase_release_mpam_label_without_lock(tsk); + spin_unlock(&phase_partid_lock); +} + +#include <asm/mpam.h> +void phase_get_memband(struct memqos_mpam_profile *pm, int *result, int nr) +{ + if (pm == &mpam_profile_res[0] || pm == NULL) { + result[0] = 0; + result[1] = 0; + result[2] = 0; + result[3] = 0; + return; + } + + mpam_component_config_mbwu_mon(pm->partid, pm->pmg, pm->monitor, result, nr); +} diff --git a/kernel/sched/memqos/phase_perf.c b/kernel/sched/memqos/phase_perf.c new file mode 100644 index 0000000000000..9b450a20e808f --- /dev/null +++ b/kernel/sched/memqos/phase_perf.c @@ -0,0 +1,409 @@ +#include <linux/kernel.h> +#include <linux/perf_event.h> +#include <linux/percpu-defs.h> +#include <linux/slab.h> +#include <linux/stop_machine.h> +#include <linux/memqos.h> +#include <linux/sched.h> + +#define PHASE_FEVENT_NUM 3 + +int *phase_perf_pevents = NULL; + +static DEFINE_PER_CPU(__typeof__(struct perf_event *)[PHASE_PEVENT_NUM], cpu_phase_perf_events); + +/****************************************** + * Helpers for phase perf event + *****************************************/ +static inline struct perf_event *perf_event_of_cpu(int cpu, int index) +{ + return per_cpu(cpu_phase_perf_events, cpu)[index]; +} + +static inline struct perf_event **perf_events_of_cpu(int cpu) +{ + return per_cpu(cpu_phase_perf_events, cpu); +} + +static inline u64 perf_event_local_pmu_read(struct perf_event *event) +{ + if (event->state == PERF_EVENT_STATE_ACTIVE) + event->pmu->read(event); + return local64_read(&event->count); +} + +/****************************************** + * Helpers for cpu counters + *****************************************/ +static inline u64 read_cpu_counter(int cpu, int index) +{ + struct perf_event *event = perf_event_of_cpu(cpu, index); + + if (!event || !event->pmu) + return 0; + + return perf_event_local_pmu_read(event); +} + +static struct perf_event_attr *alloc_attr(int event_id) +{ + struct perf_event_attr *attr; + + attr = kzalloc(sizeof(struct perf_event_attr), GFP_KERNEL); + if (!attr) + return ERR_PTR(-ENOMEM); + + attr->type = PERF_TYPE_RAW; + attr->config = event_id; + attr->size = sizeof(struct perf_event_attr); + attr->pinned = 1; + attr->disabled = 1; + //attr->exclude_hv; + //attr->exclude_idle; + //attr->exclude_kernel; + + return attr; +} + +static int create_cpu_counter(int cpu, int event_id, int index) +{ + struct perf_event_attr *attr = NULL; + struct perf_event **events = perf_events_of_cpu(cpu); + struct perf_event *event = NULL; + + attr = alloc_attr(event_id); + if (IS_ERR(attr)) + return PTR_ERR(attr); + + event = perf_event_create_kernel_counter(attr, cpu, NULL, NULL, NULL); + if (IS_ERR(event)) { + pr_err("unable to create perf event (cpu:%i-type:%d-pinned:%d-config:0x%llx) : %ld", + cpu, attr->type, attr->pinned, attr->config, PTR_ERR(event)); + kfree(attr); + return PTR_ERR(event); + } else { + events[index] = event; + perf_event_enable(events[index]); + if (event->hw.idx == -1) { + pr_err("pinned event unable to get onto hardware, perf event (cpu:%i-type:%d-config:0x%llx)", + cpu, attr->type, attr->config); + kfree(attr); + return -EINVAL; + } + pr_info("create perf_event (cpu:%i-idx:%d-type:%d-pinned:%d-exclude_hv:%d" + "-exclude_idle:%d-exclude_kernel:%d-config:0x%llx-addr:%px)", + event->cpu, event->hw.idx, + event->attr.type, event->attr.pinned, event->attr.exclude_hv, + event->attr.exclude_idle, event->attr.exclude_kernel, + event->attr.config, event); + } + + kfree(attr); + return 0; +} + +static int release_cpu_counter(int cpu, int event_id, int index) +{ + struct perf_event **events = perf_events_of_cpu(cpu); + struct perf_event *event = NULL; + + event = events[index]; + + if (!event) + return 0; + + pr_info("release perf_event (cpu:%i-idx:%d-type:%d-pinned:%d-exclude_hv:%d" + "-exclude_idle:%d-exclude_kernel:%d-config:0x%llx)", + event->cpu, event->hw.idx, + event->attr.type, event->attr.pinned, event->attr.exclude_hv, + event->attr.exclude_idle, event->attr.exclude_kernel, + event->attr.config); + + perf_event_release_kernel(event); + events[index] = NULL; + + return 0; +} + +enum { + CYCLES_INDEX = 0, + INST_RETIRED_INDEX, + PHASE_EVENT_FINAL_TERMINATOR +}; + +#define CYCLES 0x0011 +#define INST_RETIRED 0x0008 + +static int pevents[PHASE_PEVENT_NUM] = { + CYCLES, + INST_RETIRED, + PHASE_EVENT_FINAL_TERMINATOR, +}; + +#define for_each_phase_pevents(index, events) \ + for (index = 0; events != NULL && index < PHASE_PEVENT_NUM && \ + events[index] != PHASE_EVENT_FINAL_TERMINATOR; index++) + + +/****************************************** + * Helpers for phase perf + *****************************************/ +static int do_pevents(int (*fn)(int, int, int), int cpu) +{ + int index; + int err; + + for_each_phase_pevents(index, phase_perf_pevents) { + err = fn(cpu, phase_perf_pevents[index], index); + if (err) + return err; + } + + return 0; +} + +static int __phase_perf_create(void *args) +{ + int err; + int cpu = raw_smp_processor_id(); + + /* create pinned events */ + pr_info("create pinned events\n"); + err = do_pevents(create_cpu_counter, cpu); + if (err) { + pr_err("create pinned events failed\n"); + do_pevents(release_cpu_counter, cpu); + return err; + } + + pr_info("[%d] phase class event create success\n", cpu); + return 0; +} + +static int do_phase_perf_create(int *pevents, const struct cpumask *cpus) +{ + phase_perf_pevents = pevents; + return stop_machine(__phase_perf_create, NULL, cpus); +} + +static int __do_phase_perf_release(void *args) +{ + int cpu = raw_smp_processor_id(); + + /* release pinned events */ + pr_info("release pinned events\n"); + do_pevents(release_cpu_counter, cpu); + + pr_info("[%d] phase class event release success\n", cpu); + return 0; +} + +static void do_phase_perf_release(const struct cpumask *cpus) +{ + stop_machine(__do_phase_perf_release, NULL, cpus); + phase_perf_pevents = NULL; +} + +int phase_perf_create(void) +{ + return do_phase_perf_create(pevents, cpu_possible_mask); +} + +void phase_perf_release(void) +{ + do_phase_perf_release(cpu_possible_mask); +} + +DECLARE_STATIC_KEY_FALSE(sched_phase); +DECLARE_STATIC_KEY_FALSE(sched_phase_printk); + +#define PHASE_EVENT_OVERFLOW (~0ULL) + +static inline u64 phase_event_count_sub(u64 curr, u64 prev) +{ + if (curr < prev) { /* ovewrflow */ + u64 tmp = PHASE_EVENT_OVERFLOW - prev; + return curr + tmp; + } else { + return curr - prev; + } +} + +static inline void phase_calc_delta(struct task_struct *p, + struct phase_event_count *prev, + struct phase_event_count *curr, + struct phase_event_count *delta) +{ + int *pevents = phase_perf_pevents; + int index; + + for_each_phase_pevents(index, pevents) { + delta->pcount.data[index] = phase_event_count_sub(curr->pcount.data[index], prev->pcount.data[index]); + } +} + +static inline u64 phase_data_of_pevent(struct phase_event_pcount *counter, int event_id) +{ + int index; + int *events = phase_perf_pevents; + + for_each_phase_pevents(index, events) { + if (event_id == events[index]) + return counter->data[index]; + } + + return 0; +} + +static int cal_ring_history_average(int *history, int nr, int s_pos, int c_nr) +{ + int average = 0; + int start = ((s_pos - c_nr) + nr) % nr; + + if (start < 0) + return 0; + + for (;start != s_pos;) { + if (history[start] == 0) { + c_nr--; + if (c_nr == 0) + return 0; + continue; + } + average += history[start]; + start = (start + 1) % nr; + } + + return start / c_nr; +} + +static void __phase_cal_ipcx10(struct task_struct *p, struct phase_event_count *delta) +{ + u64 ins; + u64 cycles; + //invalid zero + int ipcx10 = 0; + + ins = phase_data_of_pevent(&delta->pcount, INST_RETIRED_INDEX); + cycles = phase_data_of_pevent(&delta->pcount, CYCLES_INDEX); + + if (cycles) + ipcx10 = (ins * 10) / cycles; + + if (static_branch_unlikely(&sched_phase_printk)) { + trace_printk("ins:%lld cycles:%lld\n", ins, cycles); + } + + p->sched_memqos.ipcx10_history[p->sched_memqos.ipc_ringpos] = ipcx10; + p->sched_memqos.ipc_ringpos = (p->sched_memqos.ipc_ringpos + 1) % 10; + cal_ring_history_average(p->sched_memqos.ipcx10_history, 10, p->sched_memqos.ipc_ringpos, 5); +} + +static void __phase_cal_memband_div_10(struct task_struct *p) +{ + int pos; + int result[4]; + + pos = p->sched_memqos.memband_ringpos; + + phase_get_memband(p->sched_memqos.mpam_profile.profile, result, 4); + + if (static_branch_unlikely(&sched_phase_printk)) { + trace_printk("memband:%d %d %d %d profile:%llx\n", result[0], result[1], result[2], result[3], p->sched_memqos.mpam_profile.profile); + } + + p->sched_memqos.memband_div_10_total[0] = p->sched_memqos.memband_div_10_total[0] - p->sched_memqos.memband_div_10_history[0][pos]; + p->sched_memqos.memband_div_10_total[0] = p->sched_memqos.memband_div_10_total[0] + result[0] / 10; + p->sched_memqos.memband_div_10_history[0][p->sched_memqos.memband_ringpos] = result[0] / 10; + + p->sched_memqos.memband_div_10_total[1] = p->sched_memqos.memband_div_10_total[1] - p->sched_memqos.memband_div_10_history[1][pos]; + p->sched_memqos.memband_div_10_total[1] = p->sched_memqos.memband_div_10_total[1] + result[1] / 10; + p->sched_memqos.memband_div_10_history[1][p->sched_memqos.memband_ringpos] = result[1] / 10; + + p->sched_memqos.memband_div_10_total[2] = p->sched_memqos.memband_div_10_total[2] - p->sched_memqos.memband_div_10_history[2][pos]; + p->sched_memqos.memband_div_10_total[2] = p->sched_memqos.memband_div_10_total[2] + result[2] / 10; + p->sched_memqos.memband_div_10_history[2][p->sched_memqos.memband_ringpos] = result[2] / 10; + + p->sched_memqos.memband_div_10_total[3] = p->sched_memqos.memband_div_10_total[3] - p->sched_memqos.memband_div_10_history[3][pos]; + p->sched_memqos.memband_div_10_total[3] = p->sched_memqos.memband_div_10_total[3] + result[3] / 10; + p->sched_memqos.memband_div_10_history[3][p->sched_memqos.memband_ringpos] = result[3] / 10; + + p->sched_memqos.memband_ringpos = (pos + 1) % 10; + + cal_ring_history_average(p->sched_memqos.memband_div_10_history[0], 10, pos, 5); + cal_ring_history_average(p->sched_memqos.memband_div_10_history[1], 10, pos, 5); + cal_ring_history_average(p->sched_memqos.memband_div_10_history[2], 10, pos, 5); + cal_ring_history_average(p->sched_memqos.memband_div_10_history[3], 10, pos, 5); +} + +static DEFINE_PER_CPU(struct phase_event_count, prev_phase_event_count); +static DEFINE_PER_CPU(struct phase_event_count, curr_phase_event_count); + +static void phase_perf_read_events(int cpu, u64 *pdata) +{ + int index; + + for_each_phase_pevents(index, phase_perf_pevents) { + pdata[index] = read_cpu_counter(cpu, index); + } +} + +static inline struct phase_event_count *phase_read_prev(unsigned int cpu) +{ + return &per_cpu(prev_phase_event_count, cpu); +} + +static inline struct phase_event_count *phase_read_curr(unsigned int cpu) +{ + struct phase_event_count *curr = &per_cpu(curr_phase_event_count, cpu); + + phase_perf_read_events(cpu, curr->pcount.data); + + return curr; +} + +void phase_account_task(struct task_struct *p, int cpu) +{ + struct phase_event_count delta; + struct phase_event_count *prev, *curr; + + if (!static_branch_likely(&sched_phase)) + return; + + //if (!sched_core_enabled(cpu_rq(cpu))) + // return; + + /* update phase_event_count */ + prev = phase_read_prev(cpu); + curr = phase_read_curr(cpu); + phase_calc_delta(p, prev, curr, &delta); + *prev = *curr; + + /* calculate phase */ + __phase_cal_ipcx10(p, &delta); + __phase_cal_memband_div_10(p); + p->sched_memqos.sample_times++; + if ((p->sched_memqos.sample_times % 3) == 0) + p->sched_memqos.account_ready = 1; +} + + +void phase_trace_printk(struct task_struct *p) +{ + if (!static_branch_unlikely(&sched_phase_printk)) + return; + + trace_printk("p->comm:%s(%d) ipcpos:%d ipcx10:%d membandpos:%d memband_div_10:%d numa_score[0]:%d numa_score[1]:%d numa_score[2]:%d numa_score[3]:%d turbo:%d prefered_nid:%d classid:%d partid:%d\n", + p->comm, p->pid, p->sched_memqos.ipc_ringpos,\ + p->sched_memqos.ipcx10, \ + p->sched_memqos.memband_ringpos,\ + p->sched_memqos.memband_div_10, \ + p->sched_memqos.numa_score[0], \ + p->sched_memqos.numa_score[1], \ + p->sched_memqos.numa_score[2], \ + p->sched_memqos.numa_score[3], \ + p->sched_memqos.turbo, \ + p->sched_memqos.preferred_nid, \ + p->sched_memqos.class_id, \ + p->closid); +} diff --git a/kernel/sched/memqos/phase_sim_knn.c b/kernel/sched/memqos/phase_sim_knn.c new file mode 100644 index 0000000000000..b80bb6b9ae0a3 --- /dev/null +++ b/kernel/sched/memqos/phase_sim_knn.c @@ -0,0 +1,92 @@ +#include <linux/types.h> + +#define DATA_ROW 20 +void QuickSort(u64 arr[DATA_ROW][2], int L, int R) { + int i = L; + int j = R; + int kk = (L + R) / 2; + u64 pivot = arr[kk][0]; + + while (i <= j) { + while (pivot > arr[i][0]) { + i++; + } + while (pivot < arr[j][0]) { + j--; + } + if (i <= j) { + u64 temp = arr[i][0]; + + arr[i][0] = arr[j][0]; + arr[j][0] = temp; + i++; j--; + } + } + if (L < j) { + QuickSort(arr, L, j); + } + if (i < R) { + QuickSort(arr, i, R); + } +} + +u64 euclidean_distance(u64 *row1, u64 *row2, int col) { + u64 distance = 0; + int i; + + for (i = 0; i < col - 1; i++) { + distance += ((row1[i] - row2[i]) * (row1[i] - row2[i])); + } + return distance; +} + +#define num_neighbors 6 +#define MAX_TAG 8 + +int get_neighbors_tag(u64 train_data[DATA_ROW][3], int train_row, int col, u64 *test_row) { + int i; + u64 neighbors[MAX_TAG] = {0}; + int max_tag = 0; + u64 distances[DATA_ROW][2]; + + for (i = 0; i < train_row; i++) { + distances[i][0] = euclidean_distance(train_data[i], test_row, col); + distances[i][1] = train_data[i][col - 1]; + } + QuickSort(distances, 0, train_row - 1); + for (i = 0; i < num_neighbors; i++) { + neighbors[distances[i][1]]++; + if (neighbors[distances[i][1]] > neighbors[max_tag]) + max_tag = distances[i][1]; + } + return max_tag; +} + +static u64 train_data[DATA_ROW][3] = { + {0, 1, 0}, + {0, 9, 0}, + {0, 20, 1}, + {0, 30, 1}, + {0, 40, 2}, + {0, 50, 3}, + {0, 60, 3}, + {0, 70, 3}, + {0, 80, 4}, + {0, 90, 4}, + {0, 100, 4}, + {0, 110, 5}, + {0, 120, 5}, + {0, 130, 6}, + {0, 140, 6}, + {0, 150, 7}, +}; + +int knn_get_tag(int ipcx10, int memband_div_10) +{ + u64 test_data[2]; + + test_data[0] = ipcx10; + test_data[1] = memband_div_10; + + return get_neighbors_tag(train_data, DATA_ROW, 3, test_data); +} diff --git a/kernel/sysctl.c b/kernel/sysctl.c index 685f9881b8e23..0d2764c4449ce 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -465,6 +465,13 @@ static struct ctl_table kern_table[] = { .extra2 = &one, }, #endif /* CONFIG_NUMA_BALANCING */ +#ifdef CONFIG_QOS_SCHED_DYNAMIC_AFFINITY + { + .procname = "phase", + .mode = 0555, + .child = phase_table, + }, +#endif #endif /* CONFIG_SCHED_DEBUG */ { .procname = "sched_rt_period_us", diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 4cac46d56f387..d748c291e7047 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -2164,12 +2164,15 @@ alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma, { struct mempolicy *pol; struct page *page; - int preferred_nid; + int preferred_nid = -1; nodemask_t *nmask; + if (current->sched_memqos.preferred_nid) + preferred_nid = current->sched_memqos.preferred_nid - 1; + pol = get_vma_policy(vma, addr); - if (pol->mode == MPOL_INTERLEAVE) { + if (pol->mode == MPOL_INTERLEAVE && preferred_nid != -1) { unsigned nid; nid = interleave_nid(pol, vma, addr, PAGE_SHIFT + order); @@ -2233,7 +2236,8 @@ alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma, } nmask = policy_nodemask(gfp, pol); - preferred_nid = policy_node(gfp, pol, node); + if (preferred_nid == -1) + preferred_nid = policy_node(gfp, pol, node); page = __alloc_pages_nodemask(gfp, order, preferred_nid, nmask); mark_vma_cdm(nmask, page, vma); mpol_cond_put(pol); -- 2.25.1

1 0

[PATCH PR openEuler-22.03-LTS 00/16] test patchwork->PR function
by Jialin Zhang 22 Mar '23

22 Mar '23

Send 16 patches to test patchwork->PR function Baisong Zhong (1): media: dvb-usb: az6027: fix null-ptr-deref in az6027_i2c_xfer() Chen Zhongjin (1): ftrace: Fix invalid address access in lookup_rec() when index is 0 Darrick J. Wong (1): ext4: fix another off-by-one fsmap error on 1k block filesystems David Hildenbrand (2): mm: optimize do_wp_page() for exclusive pages in the swapcache mm: optimize do_wp_page() for fresh pages in local LRU pagevecs Kuniyuki Iwashima (1): seccomp: Move copy_seccomp() to no failure path. Li Huafei (2): livepatch: Cleanup klp_mem_prepare() livepatch: Narrow the scope of the 'text_mutex' lock Luke D. Jones (1): HID: asus: Remove check for same LED brightness on set Nicholas Piggin (1): mm/vmalloc: huge vmalloc backing pages should be split rather than compound Pietro Borrello (2): HID: asus: use spinlock to protect concurrent accesses HID: asus: use spinlock to safely schedule workers Xin Long (2): tipc: set con sock in tipc_conn_alloc tipc: add an extra conn_get in tipc_conn_alloc Zheng Yejian (1): livepatch/core: Fix hungtask against cpu hotplug on x86 Zhihao Cheng (1): jbd2: fix data missing when reusing bh which is ready to be checkpointed arch/x86/kernel/livepatch.c | 11 +++++-- drivers/hid/hid-asus.c | 38 ++++++++++++++++++----- drivers/media/usb/dvb-usb/az6027.c | 4 +++ fs/ext4/fsmap.c | 2 ++ fs/jbd2/transaction.c | 50 +++++++++++++++++------------- kernel/fork.c | 17 ++++++---- kernel/livepatch/core.c | 49 ++++++++++++++++++++--------- kernel/trace/ftrace.c | 3 +- mm/memory.c | 28 +++++++++++++---- mm/vmalloc.c | 22 ++++++++++--- net/tipc/topsrv.c | 20 ++++++------ 11 files changed, 172 insertions(+), 72 deletions(-) -- 2.25.1

1 16

[PATCH openEuler-5.10-LTS-SP1 01/16] jbd2: fix data missing when reusing bh which is ready to be checkpointed
by Jialin Zhang 22 Mar '23

22 Mar '23

From: Zhihao Cheng <chengzhihao1(a)huawei.com> mainline inclusion from mainline-v6.3-rc1 commit e6b9bd7290d334451ce054e98e752abc055e0034 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I6C5HV CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- Following process will make data lost and could lead to a filesystem corrupted problem: 1. jh(bh) is inserted into T1->t_checkpoint_list, bh is dirty, and jh->b_transaction = NULL 2. T1 is added into journal->j_checkpoint_transactions. 3. Get bh prepare to write while doing checkpoing: PA PB do_get_write_access jbd2_log_do_checkpoint spin_lock(&jh->b_state_lock) if (buffer_dirty(bh)) clear_buffer_dirty(bh) // clear buffer dirty set_buffer_jbddirty(bh) transaction = journal->j_checkpoint_transactions jh = transaction->t_checkpoint_list if (!buffer_dirty(bh)) __jbd2_journal_remove_checkpoint(jh) // bh won't be flushed jbd2_cleanup_journal_tail __jbd2_journal_file_buffer(jh, transaction, BJ_Reserved) 4. Aborting journal/Power-cut before writing latest bh on journal area. In this way we get a corrupted filesystem with bh's data lost. Fix it by moving the clearing of buffer_dirty bit just before the call to __jbd2_journal_file_buffer(), both bit clearing and jh->b_transaction assignment are under journal->j_list_lock locked, so that jbd2_log_do_checkpoint() will wait until jh's new transaction fininshed even bh is currently not dirty. And journal_shrink_one_cp_list() won't remove jh from checkpoint list if the buffer head is reused in do_get_write_access(). Fetch a reproducer in [Link]. Link: https://bugzilla.kernel.org/show_bug.cgi?id=216898 Cc: <stable(a)kernel.org> Signed-off-by: Zhihao Cheng <chengzhihao1(a)huawei.com> Signed-off-by: zhanchengbin <zhanchengbin1(a)huawei.com> Suggested-by: Jan Kara <jack(a)suse.cz> Reviewed-by: Jan Kara <jack(a)suse.cz> Link: https://lore.kernel.org/r/20230110015327.1181863-1-chengzhihao1@huawei.com Signed-off-by: Theodore Ts'o <tytso(a)mit.edu> Reviewed-by: Yang Erkun <yangerkun(a)huawei.com> Reviewed-by: Zhang Yi <yi.zhang(a)huawei.com> Signed-off-by: Jialin Zhang <zhangjialin11(a)huawei.com> --- fs/jbd2/transaction.c | 50 +++++++++++++++++++++++++------------------ 1 file changed, 29 insertions(+), 21 deletions(-) diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c index cefee2dead54..8fa88c42fcb4 100644 --- a/fs/jbd2/transaction.c +++ b/fs/jbd2/transaction.c @@ -984,36 +984,28 @@ do_get_write_access(handle_t *handle, struct journal_head *jh, * ie. locked but not dirty) or tune2fs (which may actually have * the buffer dirtied, ugh.) */ - if (buffer_dirty(bh)) { + if (buffer_dirty(bh) && jh->b_transaction) { + warn_dirty_buffer(bh); /* - * First question: is this buffer already part of the current - * transaction or the existing committing transaction? - */ - if (jh->b_transaction) { - J_ASSERT_JH(jh, - jh->b_transaction == transaction || - jh->b_transaction == - journal->j_committing_transaction); - if (jh->b_next_transaction) - J_ASSERT_JH(jh, jh->b_next_transaction == - transaction); - warn_dirty_buffer(bh); - } - /* - * In any case we need to clean the dirty flag and we must - * do it under the buffer lock to be sure we don't race - * with running write-out. + * We need to clean the dirty flag and we must do it under the + * buffer lock to be sure we don't race with running write-out. */ JBUFFER_TRACE(jh, "Journalling dirty buffer"); clear_buffer_dirty(bh); + /* + * The buffer is going to be added to BJ_Reserved list now and + * nothing guarantees jbd2_journal_dirty_metadata() will be + * ever called for it. So we need to set jbddirty bit here to + * make sure the buffer is dirtied and written out when the + * journaling machinery is done with it. + */ set_buffer_jbddirty(bh); } - unlock_buffer(bh); - error = -EROFS; if (is_handle_aborted(handle)) { spin_unlock(&jh->b_state_lock); + unlock_buffer(bh); goto out; } error = 0; @@ -1023,8 +1015,10 @@ do_get_write_access(handle_t *handle, struct journal_head *jh, * b_next_transaction points to it */ if (jh->b_transaction == transaction || - jh->b_next_transaction == transaction) + jh->b_next_transaction == transaction) { + unlock_buffer(bh); goto done; + } /* * this is the first time this transaction is touching this buffer, @@ -1048,10 +1042,24 @@ do_get_write_access(handle_t *handle, struct journal_head *jh, */ smp_wmb(); spin_lock(&journal->j_list_lock); + if (test_clear_buffer_dirty(bh)) { + /* + * Execute buffer dirty clearing and jh->b_transaction + * assignment under journal->j_list_lock locked to + * prevent bh being removed from checkpoint list if + * the buffer is in an intermediate state (not dirty + * and jh->b_transaction is NULL). + */ + JBUFFER_TRACE(jh, "Journalling dirty buffer"); + set_buffer_jbddirty(bh); + } __jbd2_journal_file_buffer(jh, transaction, BJ_Reserved); spin_unlock(&journal->j_list_lock); + unlock_buffer(bh); goto done; } + unlock_buffer(bh); + /* * If there is already a copy-out version of this buffer, then we don't * need to make another one -- 2.25.1

1 15

[PATCH openEuler-5.10-LTS-SP1 01/14] jbd2: fix data missing when reusing bh which is ready to be checkpointed
by Jialin Zhang 22 Mar '23

22 Mar '23

From: Zhihao Cheng <chengzhihao1(a)huawei.com> mainline inclusion from mainline-v6.3-rc1 commit e6b9bd7290d334451ce054e98e752abc055e0034 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I6C5HV CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- Following process will make data lost and could lead to a filesystem corrupted problem: 1. jh(bh) is inserted into T1->t_checkpoint_list, bh is dirty, and jh->b_transaction = NULL 2. T1 is added into journal->j_checkpoint_transactions. 3. Get bh prepare to write while doing checkpoing: PA PB do_get_write_access jbd2_log_do_checkpoint spin_lock(&jh->b_state_lock) if (buffer_dirty(bh)) clear_buffer_dirty(bh) // clear buffer dirty set_buffer_jbddirty(bh) transaction = journal->j_checkpoint_transactions jh = transaction->t_checkpoint_list if (!buffer_dirty(bh)) __jbd2_journal_remove_checkpoint(jh) // bh won't be flushed jbd2_cleanup_journal_tail __jbd2_journal_file_buffer(jh, transaction, BJ_Reserved) 4. Aborting journal/Power-cut before writing latest bh on journal area. In this way we get a corrupted filesystem with bh's data lost. Fix it by moving the clearing of buffer_dirty bit just before the call to __jbd2_journal_file_buffer(), both bit clearing and jh->b_transaction assignment are under journal->j_list_lock locked, so that jbd2_log_do_checkpoint() will wait until jh's new transaction fininshed even bh is currently not dirty. And journal_shrink_one_cp_list() won't remove jh from checkpoint list if the buffer head is reused in do_get_write_access(). Fetch a reproducer in [Link]. Link: https://bugzilla.kernel.org/show_bug.cgi?id=216898 Cc: <stable(a)kernel.org> Signed-off-by: Zhihao Cheng <chengzhihao1(a)huawei.com> Signed-off-by: zhanchengbin <zhanchengbin1(a)huawei.com> Suggested-by: Jan Kara <jack(a)suse.cz> Reviewed-by: Jan Kara <jack(a)suse.cz> Link: https://lore.kernel.org/r/20230110015327.1181863-1-chengzhihao1@huawei.com Signed-off-by: Theodore Ts'o <tytso(a)mit.edu> Reviewed-by: Yang Erkun <yangerkun(a)huawei.com> Reviewed-by: Zhang Yi <yi.zhang(a)huawei.com> Signed-off-by: Jialin Zhang <zhangjialin11(a)huawei.com> --- fs/jbd2/transaction.c | 50 +++++++++++++++++++++++++------------------ 1 file changed, 29 insertions(+), 21 deletions(-) diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c index cefee2dead54..8fa88c42fcb4 100644 --- a/fs/jbd2/transaction.c +++ b/fs/jbd2/transaction.c @@ -984,36 +984,28 @@ do_get_write_access(handle_t *handle, struct journal_head *jh, * ie. locked but not dirty) or tune2fs (which may actually have * the buffer dirtied, ugh.) */ - if (buffer_dirty(bh)) { + if (buffer_dirty(bh) && jh->b_transaction) { + warn_dirty_buffer(bh); /* - * First question: is this buffer already part of the current - * transaction or the existing committing transaction? - */ - if (jh->b_transaction) { - J_ASSERT_JH(jh, - jh->b_transaction == transaction || - jh->b_transaction == - journal->j_committing_transaction); - if (jh->b_next_transaction) - J_ASSERT_JH(jh, jh->b_next_transaction == - transaction); - warn_dirty_buffer(bh); - } - /* - * In any case we need to clean the dirty flag and we must - * do it under the buffer lock to be sure we don't race - * with running write-out. + * We need to clean the dirty flag and we must do it under the + * buffer lock to be sure we don't race with running write-out. */ JBUFFER_TRACE(jh, "Journalling dirty buffer"); clear_buffer_dirty(bh); + /* + * The buffer is going to be added to BJ_Reserved list now and + * nothing guarantees jbd2_journal_dirty_metadata() will be + * ever called for it. So we need to set jbddirty bit here to + * make sure the buffer is dirtied and written out when the + * journaling machinery is done with it. + */ set_buffer_jbddirty(bh); } - unlock_buffer(bh); - error = -EROFS; if (is_handle_aborted(handle)) { spin_unlock(&jh->b_state_lock); + unlock_buffer(bh); goto out; } error = 0; @@ -1023,8 +1015,10 @@ do_get_write_access(handle_t *handle, struct journal_head *jh, * b_next_transaction points to it */ if (jh->b_transaction == transaction || - jh->b_next_transaction == transaction) + jh->b_next_transaction == transaction) { + unlock_buffer(bh); goto done; + } /* * this is the first time this transaction is touching this buffer, @@ -1048,10 +1042,24 @@ do_get_write_access(handle_t *handle, struct journal_head *jh, */ smp_wmb(); spin_lock(&journal->j_list_lock); + if (test_clear_buffer_dirty(bh)) { + /* + * Execute buffer dirty clearing and jh->b_transaction + * assignment under journal->j_list_lock locked to + * prevent bh being removed from checkpoint list if + * the buffer is in an intermediate state (not dirty + * and jh->b_transaction is NULL). + */ + JBUFFER_TRACE(jh, "Journalling dirty buffer"); + set_buffer_jbddirty(bh); + } __jbd2_journal_file_buffer(jh, transaction, BJ_Reserved); spin_unlock(&journal->j_list_lock); + unlock_buffer(bh); goto done; } + unlock_buffer(bh); + /* * If there is already a copy-out version of this buffer, then we don't * need to make another one -- 2.25.1

1 13

[PATCH openEuler-1.0-LTS] ext4: fix another off-by-one fsmap error on 1k block filesystems
by Yongqiang Liu 22 Mar '23

22 Mar '23

From: "Darrick J. Wong" <djwong(a)kernel.org> mainline inclusion from mainline-v6.3-rc2 commit c993799baf9c5861f8df91beb80e1611b12efcbd category: bugfix bugzilla: 188522,https://gitee.com/openeuler/kernel/issues/I6N7ZP CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- Apparently syzbot figured out that issuing this FSMAP call: struct fsmap_head cmd = { .fmh_count = ...; .fmh_keys = { { .fmr_device = /* ext4 dev */, .fmr_physical = 0, }, { .fmr_device = /* ext4 dev */, .fmr_physical = 0, }, }, ... }; ret = ioctl(fd, FS_IOC_GETFSMAP, &cmd); Produces this crash if the underlying filesystem is a 1k-block ext4 filesystem: kernel BUG at fs/ext4/ext4.h:3331! invalid opcode: 0000 [#1] PREEMPT SMP CPU: 3 PID: 3227965 Comm: xfs_io Tainted: G W O 6.2.0-rc8-achx Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.15.0-1 04/01/2014 RIP: 0010:ext4_mb_load_buddy_gfp+0x47c/0x570 [ext4] RSP: 0018:ffffc90007c03998 EFLAGS: 00010246 RAX: ffff888004978000 RBX: ffffc90007c03a20 RCX: ffff888041618000 RDX: 0000000000000000 RSI: 00000000000005a4 RDI: ffffffffa0c99b11 RBP: ffff888012330000 R08: ffffffffa0c2b7d0 R09: 0000000000000400 R10: ffffc90007c03950 R11: 0000000000000000 R12: 0000000000000001 R13: 00000000ffffffff R14: 0000000000000c40 R15: ffff88802678c398 FS: 00007fdf2020c880(0000) GS:ffff88807e100000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 00007ffd318a5fe8 CR3: 000000007f80f001 CR4: 00000000001706e0 Call Trace: <TASK> ext4_mballoc_query_range+0x4b/0x210 [ext4 dfa189daddffe8fecd3cdfd00564e0f265a8ab80] ext4_getfsmap_datadev+0x713/0x890 [ext4 dfa189daddffe8fecd3cdfd00564e0f265a8ab80] ext4_getfsmap+0x2b7/0x330 [ext4 dfa189daddffe8fecd3cdfd00564e0f265a8ab80] ext4_ioc_getfsmap+0x153/0x2b0 [ext4 dfa189daddffe8fecd3cdfd00564e0f265a8ab80] __ext4_ioctl+0x2a7/0x17e0 [ext4 dfa189daddffe8fecd3cdfd00564e0f265a8ab80] __x64_sys_ioctl+0x82/0xa0 do_syscall_64+0x2b/0x80 entry_SYSCALL_64_after_hwframe+0x46/0xb0 RIP: 0033:0x7fdf20558aff RSP: 002b:00007ffd318a9e30 EFLAGS: 00000246 ORIG_RAX: 0000000000000010 RAX: ffffffffffffffda RBX: 00000000000200c0 RCX: 00007fdf20558aff RDX: 00007fdf1feb2010 RSI: 00000000c0c0583b RDI: 0000000000000003 RBP: 00005625c0634be0 R08: 00005625c0634c40 R09: 0000000000000001 R10: 0000000000000000 R11: 0000000000000246 R12: 00007fdf1feb2010 R13: 00005625be70d994 R14: 0000000000000800 R15: 0000000000000000 For GETFSMAP calls, the caller selects a physical block device by writing its block number into fsmap_head.fmh_keys[01].fmr_device. To query mappings for a subrange of the device, the starting byte of the range is written to fsmap_head.fmh_keys[0].fmr_physical and the last byte of the range goes in fsmap_head.fmh_keys[1].fmr_physical. IOWs, to query what mappings overlap with bytes 3-14 of /dev/sda, you'd set the inputs as follows: fmh_keys[0] = { .fmr_device = major(8, 0), .fmr_physical = 3}, fmh_keys[1] = { .fmr_device = major(8, 0), .fmr_physical = 14}, Which would return you whatever is mapped in the 12 bytes starting at physical offset 3. The crash is due to insufficient range validation of keys[1] in ext4_getfsmap_datadev. On 1k-block filesystems, block 0 is not part of the filesystem, which means that s_first_data_block is nonzero. ext4_get_group_no_and_offset subtracts this quantity from the blocknr argument before cracking it into a group number and a block number within a group. IOWs, block group 0 spans blocks 1-8192 (1-based) instead of 0-8191 (0-based) like what happens with larger blocksizes. The net result of this encoding is that blocknr < s_first_data_block is not a valid input to this function. The end_fsb variable is set from the keys that are copied from userspace, which means that in the above example, its value is zero. That leads to an underflow here: blocknr = blocknr - le32_to_cpu(es->s_first_data_block); The division then operates on -1: offset = do_div(blocknr, EXT4_BLOCKS_PER_GROUP(sb)) >> EXT4_SB(sb)->s_cluster_bits; Leaving an impossibly large group number (2^32-1) in blocknr. ext4_getfsmap_check_keys checked that keys[0].fmr_physical and keys[1].fmr_physical are in increasing order, but ext4_getfsmap_datadev adjusts keys[0].fmr_physical to be at least s_first_data_block. This implies that we have to check it again after the adjustment, which is the piece that I forgot. Reported-by: syzbot+6be2b977c89f79b6b153(a)syzkaller.appspotmail.com Fixes: 4a4956249dac ("ext4: fix off-by-one fsmap error on 1k block filesystems") Link: https://syzkaller.appspot.com/bug?id=79d5768e9bfe362911ac1a5057a36fc6b5c300… Cc: stable(a)vger.kernel.org Signed-off-by: Darrick J. Wong <djwong(a)kernel.org> Link: https://lore.kernel.org/r/Y+58NPTH7VNGgzdd@magnolia Signed-off-by: Theodore Ts'o <tytso(a)mit.edu> Signed-off-by: Baokun Li <libaokun1(a)huawei.com> Reviewed-by: Zhihao Cheng <chengzhihao1(a)huawei.com> Reviewed-by: Zhang Yi <yi.zhang(a)huawei.com> Signed-off-by: Yongqiang Liu <liuyongqiang13(a)huawei.com> --- fs/ext4/fsmap.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/fs/ext4/fsmap.c b/fs/ext4/fsmap.c index 6f3f245f3a80..6b52ace1463c 100644 --- a/fs/ext4/fsmap.c +++ b/fs/ext4/fsmap.c @@ -486,6 +486,8 @@ static int ext4_getfsmap_datadev(struct super_block *sb, keys[0].fmr_physical = bofs; if (keys[1].fmr_physical >= eofs) keys[1].fmr_physical = eofs - 1; + if (keys[1].fmr_physical < keys[0].fmr_physical) + return 0; start_fsb = keys[0].fmr_physical; end_fsb = keys[1].fmr_physical; -- 2.25.1

1 0

openEuler Kernel SIG双周例会
by openEuler conference 22 Mar '23

22 Mar '23

您好！ Kernel SIG 邀请您参加 2023-03-24 14:00 召开的Zoom会议(自动录制) 会议主题：openEuler Kernel SIG双周例会会议内容： 1. 进展update 2. 议题征集中欢迎大家积极申报议题（新增议题可以直接回复邮件，或录入会议看板）会议链接：https://us06web.zoom.us/j/85131900036?pwd=RFZVYlZFK3B1RVhpTHROOW82OTdLQT09 会议纪要：https://etherpad.openeuler.org/p/Kernel-meetings 温馨提醒：建议接入会议后修改参会人的姓名，也可以使用您在gitee.com的ID 更多资讯尽在：https://openeuler.org/zh/ Hello! openEuler Kernel SIG invites you to attend the Zoom conference(auto recording) will be held at 2023-03-24 14:00, The subject of the conference is openEuler Kernel SIG双周例会, Summary: 1. 进展update 2. 议题征集中欢迎大家积极申报议题（新增议题可以直接回复邮件，或录入会议看板） You can join the meeting at https://us06web.zoom.us/j/85131900036?pwd=RFZVYlZFK3B1RVhpTHROOW82OTdLQT09. Add topics at https://etherpad.openeuler.org/p/Kernel-meetings. Note: You are advised to change the participant name after joining the conference or use your ID at gitee.com. More information: https://openeuler.org/en/

1 0

[PATCH openEuler-1.0-LTS 1/2] tipc: set con sock in tipc_conn_alloc
by Yongqiang Liu 21 Mar '23

21 Mar '23

From: Xin Long <lucien.xin(a)gmail.com> stable inclusion from stable-v4.19.268 commit 2c9c64a95d97727c9ada0d35abc90ee5fdbaeff7 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I6NCRH CVE: CVE-2023-1382 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit 0e5d56c64afcd6fd2d132ea972605b66f8a7d3c4 ] A crash was reported by Wei Chen: BUG: kernel NULL pointer dereference, address: 0000000000000018 RIP: 0010:tipc_conn_close+0x12/0x100 Call Trace: tipc_topsrv_exit_net+0x139/0x320 ops_exit_list.isra.9+0x49/0x80 cleanup_net+0x31a/0x540 process_one_work+0x3fa/0x9f0 worker_thread+0x42/0x5c0 It was caused by !con->sock in tipc_conn_close(). In tipc_topsrv_accept(), con is allocated in conn_idr then its sock is set: con = tipc_conn_alloc(); ... <----[1] con->sock = newsock; If tipc_conn_close() is called in anytime of [1], the null-pointer-def is triggered by con->sock->sk due to con->sock is not yet set. This patch fixes it by moving the con->sock setting to tipc_conn_alloc() under s->idr_lock. So that con->sock can never be NULL when getting the con from s->conn_idr. It will be also safer to move con->server and flag CF_CONNECTED setting under s->idr_lock, as they should all be set before tipc_conn_alloc() is called. Fixes: c5fa7b3cf3cb ("tipc: introduce new TIPC server infrastructure") Reported-by: Wei Chen <harperchen1110(a)gmail.com> Signed-off-by: Xin Long <lucien.xin(a)gmail.com> Acked-by: Jon Maloy <jmaloy(a)redhat.com> Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> conflict: net/tipc/topsrv.c Signed-off-by: Lu Wei <luwei32(a)huawei.com> Reviewed-by: Liu Jian <liujian56(a)huawei.com> Reviewed-by: Xiu Jianfeng <xiujianfeng(a)huawei.com> Signed-off-by: Yongqiang Liu <liuyongqiang13(a)huawei.com> --- net/tipc/topsrv.c | 11 +++++------ 1 file changed, 5 insertions(+), 6 deletions(-) diff --git a/net/tipc/topsrv.c b/net/tipc/topsrv.c index 1c4733153d74..89a1f127dfaf 100644 --- a/net/tipc/topsrv.c +++ b/net/tipc/topsrv.c @@ -184,7 +184,7 @@ static void tipc_conn_close(struct tipc_conn *con) conn_put(con); } -static struct tipc_conn *tipc_conn_alloc(struct tipc_topsrv *s) +static struct tipc_conn *tipc_conn_alloc(struct tipc_topsrv *s, struct socket *sock) { struct tipc_conn *con; int ret; @@ -210,10 +210,11 @@ static struct tipc_conn *tipc_conn_alloc(struct tipc_topsrv *s) } con->conid = ret; s->idr_in_use++; - spin_unlock_bh(&s->idr_lock); set_bit(CF_CONNECTED, &con->flags); con->server = s; + con->sock = sock; + spin_unlock_bh(&s->idr_lock); return con; } @@ -467,7 +468,7 @@ static void tipc_topsrv_accept(struct work_struct *work) ret = kernel_accept(lsock, &newsock, O_NONBLOCK); if (ret < 0) return; - con = tipc_conn_alloc(srv); + con = tipc_conn_alloc(srv, newsock); if (IS_ERR(con)) { ret = PTR_ERR(con); sock_release(newsock); @@ -479,7 +480,6 @@ static void tipc_topsrv_accept(struct work_struct *work) newsk->sk_data_ready = tipc_conn_data_ready; newsk->sk_write_space = tipc_conn_write_space; newsk->sk_user_data = con; - con->sock = newsock; write_unlock_bh(&newsk->sk_callback_lock); /* Wake up receive process in case of 'SYN+' message */ @@ -577,12 +577,11 @@ bool tipc_topsrv_kern_subscr(struct net *net, u32 port, u32 type, u32 lower, sub.filter = filter; *(u32 *)&sub.usr_handle = port; - con = tipc_conn_alloc(tipc_topsrv(net)); + con = tipc_conn_alloc(tipc_topsrv(net), NULL); if (IS_ERR(con)) return false; *conid = con->conid; - con->sock = NULL; rc = tipc_conn_rcv_sub(tipc_topsrv(net), con, &sub); if (rc >= 0) return true; -- 2.25.1

1 1

[PATCH PR openEuler-22.03-LTS-SP1] mm/vmalloc: huge vmalloc backing pages should be split rather than compound
by Jialin Zhang 21 Mar '23

21 Mar '23

From: Nicholas Piggin <npiggin(a)gmail.com> mainline inclusion from mainline-v5.18-rc4 commit 3b8000ae185cb068adbda5f966a3835053c85fd4 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I6LD0S CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- Huge vmalloc higher-order backing pages were allocated with __GFP_COMP in order to allow the sub-pages to be refcounted by callers such as "remap_vmalloc_page [sic]" (remap_vmalloc_range). However a similar problem exists for other struct page fields callers use, for example fb_deferred_io_fault() takes a vmalloc'ed page and not only refcounts it but uses ->lru, ->mapping, ->index. This is not compatible with compound sub-pages, and can cause bad page state issues like BUG: Bad page state in process swapper/0 pfn:00743 page:(____ptrval____) refcount:0 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x743 flags: 0x7ffff000000000(node=0|zone=0|lastcpupid=0x7ffff) raw: 007ffff000000000 c00c00000001d0c8 c00c00000001d0c8 0000000000000000 raw: 0000000000000000 0000000000000000 00000000ffffffff 0000000000000000 page dumped because: corrupted mapping in tail page Modules linked in: CPU: 0 PID: 1 Comm: swapper/0 Not tainted 5.18.0-rc3-00082-gfc6fff4a7ce1-dirty #2810 Call Trace: dump_stack_lvl+0x74/0xa8 (unreliable) bad_page+0x12c/0x170 free_tail_pages_check+0xe8/0x190 free_pcp_prepare+0x31c/0x4e0 free_unref_page+0x40/0x1b0 __vunmap+0x1d8/0x420 ... The correct approach is to use split high-order pages for the huge vmalloc backing. These allow callers to treat them in exactly the same way as individually-allocated order-0 pages. Link: https://lore.kernel.org/all/14444103-d51b-0fb3-ee63-c3f182f0b546@molgen.mpg… Signed-off-by: Nicholas Piggin <npiggin(a)gmail.com> Cc: Paul Menzel <pmenzel(a)molgen.mpg.de> Cc: Song Liu <songliubraving(a)fb.com> Cc: Rick Edgecombe <rick.p.edgecombe(a)intel.com> Signed-off-by: Linus Torvalds <torvalds(a)linux-foundation.org> conflicts: mm/vmalloc.c Signed-off-by: ZhangPeng <zhangpeng362(a)huawei.com> Reviewed-by: Kefeng Wang <wangkefeng.wang(a)huawei.com> Signed-off-by: Jialin Zhang <zhangjialin11(a)huawei.com> --- mm/vmalloc.c | 22 +++++++++++++++++----- 1 file changed, 17 insertions(+), 5 deletions(-) diff --git a/mm/vmalloc.c b/mm/vmalloc.c index e27cd716ca95..2ca2c1bc0db9 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -2641,14 +2641,17 @@ static void __vunmap(const void *addr, int deallocate_pages) vm_remove_mappings(area, deallocate_pages); if (deallocate_pages) { - unsigned int page_order = vm_area_page_order(area); int i; - for (i = 0; i < area->nr_pages; i += 1U << page_order) { + for (i = 0; i < area->nr_pages; i++) { struct page *page = area->pages[i]; BUG_ON(!page); - __free_pages(page, page_order); + /* + * High-order allocs for huge vmallocs are split, so + * can be freed as an array of order-0 allocations + */ + __free_pages(page, 0); } atomic_long_sub(area->nr_pages, &nr_vmalloc_pages); @@ -2930,8 +2933,7 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask, struct page *page; int p; - /* Compound pages required for remap_vmalloc_page */ - page = alloc_pages_node(node, gfp_mask | __GFP_COMP, page_order); + page = alloc_pages_node(node, gfp_mask, page_order); if (unlikely(!page)) { /* Successfully allocated i pages, free them in __vfree() */ area->nr_pages = i; @@ -2943,6 +2945,16 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask, goto fail; } + /* + * Higher order allocations must be able to be treated as + * indepdenent small pages by callers (as they can with + * small-page vmallocs). Some drivers do their own refcounting + * on vmalloc_to_page() pages, some use page->mapping, + * page->lru, etc. + */ + if (page_order) + split_page(page, page_order); + for (p = 0; p < (1U << page_order); p++) area->pages[i + p] = page + p; -- 2.25.1

1 0

[PATCH openEuler-23.03] Fix CVE-2023-23005, CVE-2023-0597 and CVE-2022-4269
by Jialin Zhang 18 Mar '23

18 Mar '23

Signed-off-by: Jialin Zhang <zhangjialin11(a)huawei.com> --- ...NULL-vs-IS_ERR-checking-in-memory_ti.patch | 50 +++++ ...-x86-mm-Randomize-per-cpu-entry-area.patch | 172 ++++++++++++++++++ ...ap-shadow-for-percpu-pages-on-demand.patch | 126 +++++++++++++ ...-physical-address-for-every-page-of-.patch | 50 +++++ ...KASAN-shadow-for-entire-per-CPU-rang.patch | 121 ++++++++++++ ...-local-CPU_ENTRY_AREA-variables-to-s.patch | 88 +++++++++ ...lpers-to-align-shadow-addresses-up-a.patch | 113 ++++++++++++ ...te-shadow-for-shared-chunk-of-the-CP.patch | 99 ++++++++++ ...rred-better-wording-on-protection-ag.patch | 97 ++++++++++ ...he-backlog-for-nested-calls-to-mirre.patch | 149 +++++++++++++++ kernel.spec | 27 ++- 11 files changed, 1090 insertions(+), 2 deletions(-) create mode 100644 0015-mm-demotion-fix-NULL-vs-IS_ERR-checking-in-memory_ti.patch create mode 100644 0016-x86-mm-Randomize-per-cpu-entry-area.patch create mode 100644 0017-x86-kasan-Map-shadow-for-percpu-pages-on-demand.patch create mode 100644 0018-x86-mm-Recompute-physical-address-for-every-page-of-.patch create mode 100644 0019-x86-mm-Populate-KASAN-shadow-for-entire-per-CPU-rang.patch create mode 100644 0020-x86-kasan-Rename-local-CPU_ENTRY_AREA-variables-to-s.patch create mode 100644 0021-x86-kasan-Add-helpers-to-align-shadow-addresses-up-a.patch create mode 100644 0022-x86-kasan-Populate-shadow-for-shared-chunk-of-the-CP.patch create mode 100644 0023-net-sched-act_mirred-better-wording-on-protection-ag.patch create mode 100644 0024-act_mirred-use-the-backlog-for-nested-calls-to-mirre.patch diff --git a/0015-mm-demotion-fix-NULL-vs-IS_ERR-checking-in-memory_ti.patch b/0015-mm-demotion-fix-NULL-vs-IS_ERR-checking-in-memory_ti.patch new file mode 100644 index 0000000..f598fc5 --- /dev/null +++ b/0015-mm-demotion-fix-NULL-vs-IS_ERR-checking-in-memory_ti.patch @@ -0,0 +1,50 @@ +From e11c121e73d4e98ed13259d6b19830f33ca60d76 Mon Sep 17 00:00:00 2001 +From: Miaoqian Lin <linmq006(a)gmail.com> +Date: Fri, 17 Mar 2023 10:05:08 +0800 +Subject: [PATCH 15/24] mm/demotion: fix NULL vs IS_ERR checking in + memory_tier_init + +mainline inclusion +from mainline-v6.2-rc1 +commit 4a625ceee8a0ab0273534cb6b432ce6b331db5ee +category: bugfix +bugzilla: https://gitee.com/src-openeuler/kernel/issues/I6IXO8 +CVE: CVE-2023-23005 + +Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… + +-------------------------------- + +alloc_memory_type() returns error pointers on error instead of NULL. Use +IS_ERR() to check the return value to fix this. + +Link: https://lkml.kernel.org/r/20221110030751.1627266-1-linmq006@gmail.com +Fixes: 7b88bda3761b ("mm/demotion/dax/kmem: set node's abstract distance to MEMTIER_DEFAULT_DAX_ADISTANCE") +Signed-off-by: Miaoqian Lin <linmq006(a)gmail.com> +Reviewed-by: "Huang, Ying" <ying.huang(a)intel.com> +Cc: Aneesh Kumar K.V <aneesh.kumar(a)linux.ibm.com> +Cc: Wei Xu <weixugc(a)google.com> +Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> +Signed-off-by: Ma Wupeng <mawupeng1(a)huawei.com> +Reviewed-by: tong tiangen <tongtiangen(a)huawei.com> +Signed-off-by: Jialin Zhang <zhangjialin11(a)huawei.com> +--- + mm/memory-tiers.c | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +diff --git a/mm/memory-tiers.c b/mm/memory-tiers.c +index ba863f46759d..96022973c9ba 100644 +--- a/mm/memory-tiers.c ++++ b/mm/memory-tiers.c +@@ -645,7 +645,7 @@ static int __init memory_tier_init(void) + * than default DRAM tier. + */ + default_dram_type = alloc_memory_type(MEMTIER_ADISTANCE_DRAM); +- if (!default_dram_type) ++ if (IS_ERR(default_dram_type)) + panic("%s() failed to allocate default DRAM tier\n", __func__); + + /* +-- +2.25.1 + diff --git a/0016-x86-mm-Randomize-per-cpu-entry-area.patch b/0016-x86-mm-Randomize-per-cpu-entry-area.patch new file mode 100644 index 0000000..6f5dd2d --- /dev/null +++ b/0016-x86-mm-Randomize-per-cpu-entry-area.patch @@ -0,0 +1,172 @@ +From 0324d3cd1b57c06b0cf31b6db643ced5b29b0947 Mon Sep 17 00:00:00 2001 +From: Peter Zijlstra <peterz(a)infradead.org> +Date: Fri, 17 Mar 2023 03:07:41 +0000 +Subject: [PATCH 16/24] x86/mm: Randomize per-cpu entry area + +mainline inclusion +from mainline-v6.2-rc1 +commit 97e3d26b5e5f371b3ee223d94dd123e6c442ba80 +category: bugfix +bugzilla: 188336 +CVE: CVE-2023-0597 + +Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… + +-------------------------------- + +Seth found that the CPU-entry-area; the piece of per-cpu data that is +mapped into the userspace page-tables for kPTI is not subject to any +randomization -- irrespective of kASLR settings. + +On x86_64 a whole P4D (512 GB) of virtual address space is reserved for +this structure, which is plenty large enough to randomize things a +little. + +As such, use a straight forward randomization scheme that avoids +duplicates to spread the existing CPUs over the available space. + + [ bp: Fix le build. ] + +Reported-by: Seth Jenkins <sethjenkins(a)google.com> +Reviewed-by: Kees Cook <keescook(a)chromium.org> +Signed-off-by: Peter Zijlstra (Intel) <peterz(a)infradead.org> +Signed-off-by: Dave Hansen <dave.hansen(a)linux.intel.com> +Signed-off-by: Borislav Petkov <bp(a)suse.de> +Signed-off-by: Tong Tiangen <tongtiangen(a)huawei.com> +Reviewed-by: Nanyong Sun <sunnanyong(a)huawei.com> +Reviewed-by: Kefeng Wang <wangkefeng.wang(a)huawei.com> +Signed-off-by: Jialin Zhang <zhangjialin11(a)huawei.com> +--- + arch/x86/include/asm/cpu_entry_area.h | 4 --- + arch/x86/include/asm/pgtable_areas.h | 8 ++++- + arch/x86/kernel/hw_breakpoint.c | 2 +- + arch/x86/mm/cpu_entry_area.c | 46 ++++++++++++++++++++++++--- + 4 files changed, 50 insertions(+), 10 deletions(-) + +diff --git a/arch/x86/include/asm/cpu_entry_area.h b/arch/x86/include/asm/cpu_entry_area.h +index 75efc4c6f076..462fc34f1317 100644 +--- a/arch/x86/include/asm/cpu_entry_area.h ++++ b/arch/x86/include/asm/cpu_entry_area.h +@@ -130,10 +130,6 @@ struct cpu_entry_area { + }; + + #define CPU_ENTRY_AREA_SIZE (sizeof(struct cpu_entry_area)) +-#define CPU_ENTRY_AREA_ARRAY_SIZE (CPU_ENTRY_AREA_SIZE * NR_CPUS) +- +-/* Total size includes the readonly IDT mapping page as well: */ +-#define CPU_ENTRY_AREA_TOTAL_SIZE (CPU_ENTRY_AREA_ARRAY_SIZE + PAGE_SIZE) + + DECLARE_PER_CPU(struct cpu_entry_area *, cpu_entry_area); + DECLARE_PER_CPU(struct cea_exception_stacks *, cea_exception_stacks); +diff --git a/arch/x86/include/asm/pgtable_areas.h b/arch/x86/include/asm/pgtable_areas.h +index d34cce1b995c..4f056fb88174 100644 +--- a/arch/x86/include/asm/pgtable_areas.h ++++ b/arch/x86/include/asm/pgtable_areas.h +@@ -11,6 +11,12 @@ + + #define CPU_ENTRY_AREA_RO_IDT_VADDR ((void *)CPU_ENTRY_AREA_RO_IDT) + +-#define CPU_ENTRY_AREA_MAP_SIZE (CPU_ENTRY_AREA_PER_CPU + CPU_ENTRY_AREA_ARRAY_SIZE - CPU_ENTRY_AREA_BASE) ++#ifdef CONFIG_X86_32 ++#define CPU_ENTRY_AREA_MAP_SIZE (CPU_ENTRY_AREA_PER_CPU + \ ++ (CPU_ENTRY_AREA_SIZE * NR_CPUS) - \ ++ CPU_ENTRY_AREA_BASE) ++#else ++#define CPU_ENTRY_AREA_MAP_SIZE P4D_SIZE ++#endif + + #endif /* _ASM_X86_PGTABLE_AREAS_H */ +diff --git a/arch/x86/kernel/hw_breakpoint.c b/arch/x86/kernel/hw_breakpoint.c +index 668a4a6533d9..bbb0f737aab1 100644 +--- a/arch/x86/kernel/hw_breakpoint.c ++++ b/arch/x86/kernel/hw_breakpoint.c +@@ -266,7 +266,7 @@ static inline bool within_cpu_entry(unsigned long addr, unsigned long end) + + /* CPU entry erea is always used for CPU entry */ + if (within_area(addr, end, CPU_ENTRY_AREA_BASE, +- CPU_ENTRY_AREA_TOTAL_SIZE)) ++ CPU_ENTRY_AREA_MAP_SIZE)) + return true; + + /* +diff --git a/arch/x86/mm/cpu_entry_area.c b/arch/x86/mm/cpu_entry_area.c +index 6c2f1b76a0b6..20844cf141fb 100644 +--- a/arch/x86/mm/cpu_entry_area.c ++++ b/arch/x86/mm/cpu_entry_area.c +@@ -15,16 +15,53 @@ static DEFINE_PER_CPU_PAGE_ALIGNED(struct entry_stack_page, entry_stack_storage) + #ifdef CONFIG_X86_64 + static DEFINE_PER_CPU_PAGE_ALIGNED(struct exception_stacks, exception_stacks); + DEFINE_PER_CPU(struct cea_exception_stacks*, cea_exception_stacks); +-#endif + +-#ifdef CONFIG_X86_32 ++static DEFINE_PER_CPU_READ_MOSTLY(unsigned long, _cea_offset); ++ ++static __always_inline unsigned int cea_offset(unsigned int cpu) ++{ ++ return per_cpu(_cea_offset, cpu); ++} ++ ++static __init void init_cea_offsets(void) ++{ ++ unsigned int max_cea; ++ unsigned int i, j; ++ ++ max_cea = (CPU_ENTRY_AREA_MAP_SIZE - PAGE_SIZE) / CPU_ENTRY_AREA_SIZE; ++ ++ /* O(sodding terrible) */ ++ for_each_possible_cpu(i) { ++ unsigned int cea; ++ ++again: ++ cea = prandom_u32_max(max_cea); ++ ++ for_each_possible_cpu(j) { ++ if (cea_offset(j) == cea) ++ goto again; ++ ++ if (i == j) ++ break; ++ } ++ ++ per_cpu(_cea_offset, i) = cea; ++ } ++} ++#else /* !X86_64 */ + DECLARE_PER_CPU_PAGE_ALIGNED(struct doublefault_stack, doublefault_stack); ++ ++static __always_inline unsigned int cea_offset(unsigned int cpu) ++{ ++ return cpu; ++} ++static inline void init_cea_offsets(void) { } + #endif + + /* Is called from entry code, so must be noinstr */ + noinstr struct cpu_entry_area *get_cpu_entry_area(int cpu) + { +- unsigned long va = CPU_ENTRY_AREA_PER_CPU + cpu * CPU_ENTRY_AREA_SIZE; ++ unsigned long va = CPU_ENTRY_AREA_PER_CPU + cea_offset(cpu) * CPU_ENTRY_AREA_SIZE; + BUILD_BUG_ON(sizeof(struct cpu_entry_area) % PAGE_SIZE != 0); + + return (struct cpu_entry_area *) va; +@@ -205,7 +242,6 @@ static __init void setup_cpu_entry_area_ptes(void) + + /* The +1 is for the readonly IDT: */ + BUILD_BUG_ON((CPU_ENTRY_AREA_PAGES+1)*PAGE_SIZE != CPU_ENTRY_AREA_MAP_SIZE); +- BUILD_BUG_ON(CPU_ENTRY_AREA_TOTAL_SIZE != CPU_ENTRY_AREA_MAP_SIZE); + BUG_ON(CPU_ENTRY_AREA_BASE & ~PMD_MASK); + + start = CPU_ENTRY_AREA_BASE; +@@ -221,6 +257,8 @@ void __init setup_cpu_entry_areas(void) + { + unsigned int cpu; + ++ init_cea_offsets(); ++ + setup_cpu_entry_area_ptes(); + + for_each_possible_cpu(cpu) +-- +2.25.1 + diff --git a/0017-x86-kasan-Map-shadow-for-percpu-pages-on-demand.patch b/0017-x86-kasan-Map-shadow-for-percpu-pages-on-demand.patch new file mode 100644 index 0000000..b9129b6 --- /dev/null +++ b/0017-x86-kasan-Map-shadow-for-percpu-pages-on-demand.patch @@ -0,0 +1,126 @@ +From 68992563c4b6b1776bd90dafe76caa88ff6dbfe8 Mon Sep 17 00:00:00 2001 +From: Andrey Ryabinin <ryabinin.a.a(a)gmail.com> +Date: Fri, 17 Mar 2023 03:07:42 +0000 +Subject: [PATCH 17/24] x86/kasan: Map shadow for percpu pages on demand + +mainline inclusion +from mainline-v6.2-rc1 +commit 3f148f3318140035e87decc1214795ff0755757b +category: bugfix +bugzilla: 188336 +CVE: CVE-2023-0597 + +Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… + +-------------------------------- + +KASAN maps shadow for the entire CPU-entry-area: + [CPU_ENTRY_AREA_BASE, CPU_ENTRY_AREA_BASE + CPU_ENTRY_AREA_MAP_SIZE] + +This will explode once the per-cpu entry areas are randomized since it +will increase CPU_ENTRY_AREA_MAP_SIZE to 512 GB and KASAN fails to +allocate shadow for such big area. + +Fix this by allocating KASAN shadow only for really used cpu entry area +addresses mapped by cea_map_percpu_pages() + +Thanks to the 0day folks for finding and reporting this to be an issue. + +[ dhansen: tweak changelog since this will get committed before peterz's + actual cpu-entry-area randomization ] + +Signed-off-by: Andrey Ryabinin <ryabinin.a.a(a)gmail.com> +Signed-off-by: Dave Hansen <dave.hansen(a)linux.intel.com> +Tested-by: Yujie Liu <yujie.liu(a)intel.com> +Cc: kernel test robot <yujie.liu(a)intel.com> +Link: https://lore.kernel.org/r/202210241508.2e203c3d-yujie.liu@intel.com +Signed-off-by: Tong Tiangen <tongtiangen(a)huawei.com> +Reviewed-by: Nanyong Sun <sunnanyong(a)huawei.com> +Reviewed-by: Kefeng Wang <wangkefeng.wang(a)huawei.com> +Signed-off-by: Jialin Zhang <zhangjialin11(a)huawei.com> +--- + arch/x86/include/asm/kasan.h | 3 +++ + arch/x86/mm/cpu_entry_area.c | 8 +++++++- + arch/x86/mm/kasan_init_64.c | 15 ++++++++++++--- + 3 files changed, 22 insertions(+), 4 deletions(-) + +diff --git a/arch/x86/include/asm/kasan.h b/arch/x86/include/asm/kasan.h +index 13e70da38bed..de75306b932e 100644 +--- a/arch/x86/include/asm/kasan.h ++++ b/arch/x86/include/asm/kasan.h +@@ -28,9 +28,12 @@ + #ifdef CONFIG_KASAN + void __init kasan_early_init(void); + void __init kasan_init(void); ++void __init kasan_populate_shadow_for_vaddr(void *va, size_t size, int nid); + #else + static inline void kasan_early_init(void) { } + static inline void kasan_init(void) { } ++static inline void kasan_populate_shadow_for_vaddr(void *va, size_t size, ++ int nid) { } + #endif + + #endif +diff --git a/arch/x86/mm/cpu_entry_area.c b/arch/x86/mm/cpu_entry_area.c +index 20844cf141fb..dff9001e5e12 100644 +--- a/arch/x86/mm/cpu_entry_area.c ++++ b/arch/x86/mm/cpu_entry_area.c +@@ -9,6 +9,7 @@ + #include <asm/cpu_entry_area.h> + #include <asm/fixmap.h> + #include <asm/desc.h> ++#include <asm/kasan.h> + + static DEFINE_PER_CPU_PAGE_ALIGNED(struct entry_stack_page, entry_stack_storage); + +@@ -90,8 +91,13 @@ void cea_set_pte(void *cea_vaddr, phys_addr_t pa, pgprot_t flags) + static void __init + cea_map_percpu_pages(void *cea_vaddr, void *ptr, int pages, pgprot_t prot) + { ++ phys_addr_t pa = per_cpu_ptr_to_phys(ptr); ++ ++ kasan_populate_shadow_for_vaddr(cea_vaddr, pages * PAGE_SIZE, ++ early_pfn_to_nid(PFN_DOWN(pa))); ++ + for ( ; pages; pages--, cea_vaddr+= PAGE_SIZE, ptr += PAGE_SIZE) +- cea_set_pte(cea_vaddr, per_cpu_ptr_to_phys(ptr), prot); ++ cea_set_pte(cea_vaddr, pa, prot); + } + + static void __init percpu_setup_debug_store(unsigned int cpu) +diff --git a/arch/x86/mm/kasan_init_64.c b/arch/x86/mm/kasan_init_64.c +index e7b9b464a82f..d1416926ad52 100644 +--- a/arch/x86/mm/kasan_init_64.c ++++ b/arch/x86/mm/kasan_init_64.c +@@ -316,6 +316,18 @@ void __init kasan_early_init(void) + kasan_map_early_shadow(init_top_pgt); + } + ++void __init kasan_populate_shadow_for_vaddr(void *va, size_t size, int nid) ++{ ++ unsigned long shadow_start, shadow_end; ++ ++ shadow_start = (unsigned long)kasan_mem_to_shadow(va); ++ shadow_start = round_down(shadow_start, PAGE_SIZE); ++ shadow_end = (unsigned long)kasan_mem_to_shadow(va + size); ++ shadow_end = round_up(shadow_end, PAGE_SIZE); ++ ++ kasan_populate_shadow(shadow_start, shadow_end, nid); ++} ++ + void __init kasan_init(void) + { + int i; +@@ -393,9 +405,6 @@ void __init kasan_init(void) + kasan_mem_to_shadow((void *)VMALLOC_END + 1), + shadow_cpu_entry_begin); + +- kasan_populate_shadow((unsigned long)shadow_cpu_entry_begin, +- (unsigned long)shadow_cpu_entry_end, 0); +- + kasan_populate_early_shadow(shadow_cpu_entry_end, + kasan_mem_to_shadow((void *)__START_KERNEL_map)); + +-- +2.25.1 + diff --git a/0018-x86-mm-Recompute-physical-address-for-every-page-of-.patch b/0018-x86-mm-Recompute-physical-address-for-every-page-of-.patch new file mode 100644 index 0000000..2696052 --- /dev/null +++ b/0018-x86-mm-Recompute-physical-address-for-every-page-of-.patch @@ -0,0 +1,50 @@ +From 12867b242d6e431f6f947e53abd1094cd0075b55 Mon Sep 17 00:00:00 2001 +From: Sean Christopherson <seanjc(a)google.com> +Date: Fri, 17 Mar 2023 03:07:43 +0000 +Subject: [PATCH 18/24] x86/mm: Recompute physical address for every page of + per-CPU CEA mapping + +mainline inclusion +from mainline-v6.2-rc1 +commit 80d72a8f76e8f3f0b5a70b8c7022578e17bde8e7 +category: bugfix +bugzilla: 188336 +CVE: CVE-2023-0597 + +Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… + +-------------------------------- + +Recompute the physical address for each per-CPU page in the CPU entry +area, a recent commit inadvertantly modified cea_map_percpu_pages() such +that every PTE is mapped to the physical address of the first page. + +Fixes: 9fd429c28073 ("x86/kasan: Map shadow for percpu pages on demand") +Signed-off-by: Sean Christopherson <seanjc(a)google.com> +Signed-off-by: Peter Zijlstra (Intel) <peterz(a)infradead.org> +Reviewed-by: Andrey Ryabinin <ryabinin.a.a(a)gmail.com> +Link: https://lkml.kernel.org/r/20221110203504.1985010-2-seanjc@google.com +Signed-off-by: Tong Tiangen <tongtiangen(a)huawei.com> +Reviewed-by: Nanyong Sun <sunnanyong(a)huawei.com> +Reviewed-by: Kefeng Wang <wangkefeng.wang(a)huawei.com> +Signed-off-by: Jialin Zhang <zhangjialin11(a)huawei.com> +--- + arch/x86/mm/cpu_entry_area.c | 2 +- + 1 file changed, 1 insertion(+), 1 deletion(-) + +diff --git a/arch/x86/mm/cpu_entry_area.c b/arch/x86/mm/cpu_entry_area.c +index dff9001e5e12..d831aae94b41 100644 +--- a/arch/x86/mm/cpu_entry_area.c ++++ b/arch/x86/mm/cpu_entry_area.c +@@ -97,7 +97,7 @@ cea_map_percpu_pages(void *cea_vaddr, void *ptr, int pages, pgprot_t prot) + early_pfn_to_nid(PFN_DOWN(pa))); + + for ( ; pages; pages--, cea_vaddr+= PAGE_SIZE, ptr += PAGE_SIZE) +- cea_set_pte(cea_vaddr, pa, prot); ++ cea_set_pte(cea_vaddr, per_cpu_ptr_to_phys(ptr), prot); + } + + static void __init percpu_setup_debug_store(unsigned int cpu) +-- +2.25.1 + diff --git a/0019-x86-mm-Populate-KASAN-shadow-for-entire-per-CPU-rang.patch b/0019-x86-mm-Populate-KASAN-shadow-for-entire-per-CPU-rang.patch new file mode 100644 index 0000000..8fa96dd --- /dev/null +++ b/0019-x86-mm-Populate-KASAN-shadow-for-entire-per-CPU-rang.patch @@ -0,0 +1,121 @@ +From 91bb861cfc95653af4223af2e00b9e637c501d5a Mon Sep 17 00:00:00 2001 +From: Sean Christopherson <seanjc(a)google.com> +Date: Fri, 17 Mar 2023 03:07:44 +0000 +Subject: [PATCH 19/24] x86/mm: Populate KASAN shadow for entire per-CPU range + of CPU entry area + +mainline inclusion +from mainline-v6.2-rc1 +commit 97650148a15e0b30099d6175ffe278b9f55ec66a +category: bugfix +bugzilla: 188336 +CVE: CVE-2023-0597 + +Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… + +-------------------------------- + +Populate a KASAN shadow for the entire possible per-CPU range of the CPU +entry area instead of requiring that each individual chunk map a shadow. +Mapping shadows individually is error prone, e.g. the per-CPU GDT mapping +was left behind, which can lead to not-present page faults during KASAN +validation if the kernel performs a software lookup into the GDT. The DS +buffer is also likely affected. + +The motivation for mapping the per-CPU areas on-demand was to avoid +mapping the entire 512GiB range that's reserved for the CPU entry area, +shaving a few bytes by not creating shadows for potentially unused memory +was not a goal. + +The bug is most easily reproduced by doing a sigreturn with a garbage +CS in the sigcontext, e.g. + + int main(void) + { + struct sigcontext regs; + + syscall(__NR_mmap, 0x1ffff000ul, 0x1000ul, 0ul, 0x32ul, -1, 0ul); + syscall(__NR_mmap, 0x20000000ul, 0x1000000ul, 7ul, 0x32ul, -1, 0ul); + syscall(__NR_mmap, 0x21000000ul, 0x1000ul, 0ul, 0x32ul, -1, 0ul); + + memset(&regs, 0, sizeof(regs)); + regs.cs = 0x1d0; + syscall(__NR_rt_sigreturn); + return 0; + } + +to coerce the kernel into doing a GDT lookup to compute CS.base when +reading the instruction bytes on the subsequent #GP to determine whether +or not the #GP is something the kernel should handle, e.g. to fixup UMIP +violations or to emulate CLI/STI for IOPL=3 applications. + + BUG: unable to handle page fault for address: fffffbc8379ace00 + #PF: supervisor read access in kernel mode + #PF: error_code(0x0000) - not-present page + PGD 16c03a067 P4D 16c03a067 PUD 15b990067 PMD 15b98f067 PTE 0 + Oops: 0000 [#1] PREEMPT SMP KASAN + CPU: 3 PID: 851 Comm: r2 Not tainted 6.1.0-rc3-next-20221103+ #432 + Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 0.0.0 02/06/2015 + RIP: 0010:kasan_check_range+0xdf/0x190 + Call Trace: + <TASK> + get_desc+0xb0/0x1d0 + insn_get_seg_base+0x104/0x270 + insn_fetch_from_user+0x66/0x80 + fixup_umip_exception+0xb1/0x530 + exc_general_protection+0x181/0x210 + asm_exc_general_protection+0x22/0x30 + RIP: 0003:0x0 + Code: Unable to access opcode bytes at 0xffffffffffffffd6. + RSP: 0003:0000000000000000 EFLAGS: 00000202 + RAX: 0000000000000000 RBX: 0000000000000000 RCX: 00000000000001d0 + RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000000 + RBP: 0000000000000000 R08: 0000000000000000 R09: 0000000000000000 + R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000000000 + R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000 + </TASK> + +Fixes: 9fd429c28073 ("x86/kasan: Map shadow for percpu pages on demand") +Reported-by: syzbot+ffb4f000dc2872c93f62(a)syzkaller.appspotmail.com +Suggested-by: Andrey Ryabinin <ryabinin.a.a(a)gmail.com> +Signed-off-by: Sean Christopherson <seanjc(a)google.com> +Signed-off-by: Peter Zijlstra (Intel) <peterz(a)infradead.org> +Reviewed-by: Andrey Ryabinin <ryabinin.a.a(a)gmail.com> +Link: https://lkml.kernel.org/r/20221110203504.1985010-3-seanjc@google.com +Signed-off-by: Tong Tiangen <tongtiangen(a)huawei.com> +Reviewed-by: Nanyong Sun <sunnanyong(a)huawei.com> +Reviewed-by: Kefeng Wang <wangkefeng.wang(a)huawei.com> +Signed-off-by: Jialin Zhang <zhangjialin11(a)huawei.com> +--- + arch/x86/mm/cpu_entry_area.c | 8 +++----- + 1 file changed, 3 insertions(+), 5 deletions(-) + +diff --git a/arch/x86/mm/cpu_entry_area.c b/arch/x86/mm/cpu_entry_area.c +index d831aae94b41..7c855dffcdc2 100644 +--- a/arch/x86/mm/cpu_entry_area.c ++++ b/arch/x86/mm/cpu_entry_area.c +@@ -91,11 +91,6 @@ void cea_set_pte(void *cea_vaddr, phys_addr_t pa, pgprot_t flags) + static void __init + cea_map_percpu_pages(void *cea_vaddr, void *ptr, int pages, pgprot_t prot) + { +- phys_addr_t pa = per_cpu_ptr_to_phys(ptr); +- +- kasan_populate_shadow_for_vaddr(cea_vaddr, pages * PAGE_SIZE, +- early_pfn_to_nid(PFN_DOWN(pa))); +- + for ( ; pages; pages--, cea_vaddr+= PAGE_SIZE, ptr += PAGE_SIZE) + cea_set_pte(cea_vaddr, per_cpu_ptr_to_phys(ptr), prot); + } +@@ -195,6 +190,9 @@ static void __init setup_cpu_entry_area(unsigned int cpu) + pgprot_t tss_prot = PAGE_KERNEL; + #endif + ++ kasan_populate_shadow_for_vaddr(cea, CPU_ENTRY_AREA_SIZE, ++ early_cpu_to_node(cpu)); ++ + cea_set_pte(&cea->gdt, get_cpu_gdt_paddr(cpu), gdt_prot); + + cea_map_percpu_pages(&cea->entry_stack_page, +-- +2.25.1 + diff --git a/0020-x86-kasan-Rename-local-CPU_ENTRY_AREA-variables-to-s.patch b/0020-x86-kasan-Rename-local-CPU_ENTRY_AREA-variables-to-s.patch new file mode 100644 index 0000000..e4f9f63 --- /dev/null +++ b/0020-x86-kasan-Rename-local-CPU_ENTRY_AREA-variables-to-s.patch @@ -0,0 +1,88 @@ +From 0560fceb4d3c76133f1a89decbf1c3334afdbd00 Mon Sep 17 00:00:00 2001 +From: Sean Christopherson <seanjc(a)google.com> +Date: Fri, 17 Mar 2023 03:07:45 +0000 +Subject: [PATCH 20/24] x86/kasan: Rename local CPU_ENTRY_AREA variables to + shorten names + +mainline inclusion +from mainline-v6.2-rc1 +commit 7077d2ccb94dafd00b29cc2d601c9f6891648f5b +category: bugfix +bugzilla: 188336 +CVE: CVE-2023-0597 + +Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… + +-------------------------------- + +Rename the CPU entry area variables in kasan_init() to shorten their +names, a future fix will reference the beginning of the per-CPU portion +of the CPU entry area, and shadow_cpu_entry_per_cpu_begin is a bit much. + +No functional change intended. + +Signed-off-by: Sean Christopherson <seanjc(a)google.com> +Signed-off-by: Peter Zijlstra (Intel) <peterz(a)infradead.org> +Reviewed-by: Andrey Ryabinin <ryabinin.a.a(a)gmail.com> +Link: https://lkml.kernel.org/r/20221110203504.1985010-4-seanjc@google.com +Signed-off-by: Tong Tiangen <tongtiangen(a)huawei.com> +Reviewed-by: Nanyong Sun <sunnanyong(a)huawei.com> +Reviewed-by: Kefeng Wang <wangkefeng.wang(a)huawei.com> +Signed-off-by: Jialin Zhang <zhangjialin11(a)huawei.com> +--- + arch/x86/mm/kasan_init_64.c | 22 +++++++++++----------- + 1 file changed, 11 insertions(+), 11 deletions(-) + +diff --git a/arch/x86/mm/kasan_init_64.c b/arch/x86/mm/kasan_init_64.c +index d1416926ad52..ad7872ae10ed 100644 +--- a/arch/x86/mm/kasan_init_64.c ++++ b/arch/x86/mm/kasan_init_64.c +@@ -331,7 +331,7 @@ void __init kasan_populate_shadow_for_vaddr(void *va, size_t size, int nid) + void __init kasan_init(void) + { + int i; +- void *shadow_cpu_entry_begin, *shadow_cpu_entry_end; ++ void *shadow_cea_begin, *shadow_cea_end; + + memcpy(early_top_pgt, init_top_pgt, sizeof(early_top_pgt)); + +@@ -372,16 +372,16 @@ void __init kasan_init(void) + map_range(&pfn_mapped[i]); + } + +- shadow_cpu_entry_begin = (void *)CPU_ENTRY_AREA_BASE; +- shadow_cpu_entry_begin = kasan_mem_to_shadow(shadow_cpu_entry_begin); +- shadow_cpu_entry_begin = (void *)round_down( +- (unsigned long)shadow_cpu_entry_begin, PAGE_SIZE); ++ shadow_cea_begin = (void *)CPU_ENTRY_AREA_BASE; ++ shadow_cea_begin = kasan_mem_to_shadow(shadow_cea_begin); ++ shadow_cea_begin = (void *)round_down( ++ (unsigned long)shadow_cea_begin, PAGE_SIZE); + +- shadow_cpu_entry_end = (void *)(CPU_ENTRY_AREA_BASE + ++ shadow_cea_end = (void *)(CPU_ENTRY_AREA_BASE + + CPU_ENTRY_AREA_MAP_SIZE); +- shadow_cpu_entry_end = kasan_mem_to_shadow(shadow_cpu_entry_end); +- shadow_cpu_entry_end = (void *)round_up( +- (unsigned long)shadow_cpu_entry_end, PAGE_SIZE); ++ shadow_cea_end = kasan_mem_to_shadow(shadow_cea_end); ++ shadow_cea_end = (void *)round_up( ++ (unsigned long)shadow_cea_end, PAGE_SIZE); + + kasan_populate_early_shadow( + kasan_mem_to_shadow((void *)PAGE_OFFSET + MAXMEM), +@@ -403,9 +403,9 @@ void __init kasan_init(void) + + kasan_populate_early_shadow( + kasan_mem_to_shadow((void *)VMALLOC_END + 1), +- shadow_cpu_entry_begin); ++ shadow_cea_begin); + +- kasan_populate_early_shadow(shadow_cpu_entry_end, ++ kasan_populate_early_shadow(shadow_cea_end, + kasan_mem_to_shadow((void *)__START_KERNEL_map)); + + kasan_populate_shadow((unsigned long)kasan_mem_to_shadow(_stext), +-- +2.25.1 + diff --git a/0021-x86-kasan-Add-helpers-to-align-shadow-addresses-up-a.patch b/0021-x86-kasan-Add-helpers-to-align-shadow-addresses-up-a.patch new file mode 100644 index 0000000..5f3f362 --- /dev/null +++ b/0021-x86-kasan-Add-helpers-to-align-shadow-addresses-up-a.patch @@ -0,0 +1,113 @@ +From ec4ebad1a3ed5a1ff3301de4df9a12ebf81b09c1 Mon Sep 17 00:00:00 2001 +From: Sean Christopherson <seanjc(a)google.com> +Date: Fri, 17 Mar 2023 03:07:46 +0000 +Subject: [PATCH 21/24] x86/kasan: Add helpers to align shadow addresses up and + down + +mainline inclusion +from mainline-v6.2-rc1 +commit bde258d97409f2a45243cb393a55ea9ecfc7aba5 +category: bugfix +bugzilla: 188336 +CVE: CVE-2023-0597 + +Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… + +-------------------------------- + +Add helpers to dedup code for aligning shadow address up/down to page +boundaries when translating an address to its shadow. + +No functional change intended. + +Signed-off-by: Sean Christopherson <seanjc(a)google.com> +Signed-off-by: Peter Zijlstra (Intel) <peterz(a)infradead.org> +Reviewed-by: Andrey Ryabinin <ryabinin.a.a(a)gmail.com> +Link: https://lkml.kernel.org/r/20221110203504.1985010-5-seanjc@google.com +Signed-off-by: Tong Tiangen <tongtiangen(a)huawei.com> +Reviewed-by: Nanyong Sun <sunnanyong(a)huawei.com> +Reviewed-by: Kefeng Wang <wangkefeng.wang(a)huawei.com> +Signed-off-by: Jialin Zhang <zhangjialin11(a)huawei.com> +--- + arch/x86/mm/kasan_init_64.c | 40 ++++++++++++++++++++----------------- + 1 file changed, 22 insertions(+), 18 deletions(-) + +diff --git a/arch/x86/mm/kasan_init_64.c b/arch/x86/mm/kasan_init_64.c +index ad7872ae10ed..afc5e129ca7b 100644 +--- a/arch/x86/mm/kasan_init_64.c ++++ b/arch/x86/mm/kasan_init_64.c +@@ -316,22 +316,33 @@ void __init kasan_early_init(void) + kasan_map_early_shadow(init_top_pgt); + } + ++static unsigned long kasan_mem_to_shadow_align_down(unsigned long va) ++{ ++ unsigned long shadow = (unsigned long)kasan_mem_to_shadow((void *)va); ++ ++ return round_down(shadow, PAGE_SIZE); ++} ++ ++static unsigned long kasan_mem_to_shadow_align_up(unsigned long va) ++{ ++ unsigned long shadow = (unsigned long)kasan_mem_to_shadow((void *)va); ++ ++ return round_up(shadow, PAGE_SIZE); ++} ++ + void __init kasan_populate_shadow_for_vaddr(void *va, size_t size, int nid) + { + unsigned long shadow_start, shadow_end; + +- shadow_start = (unsigned long)kasan_mem_to_shadow(va); +- shadow_start = round_down(shadow_start, PAGE_SIZE); +- shadow_end = (unsigned long)kasan_mem_to_shadow(va + size); +- shadow_end = round_up(shadow_end, PAGE_SIZE); +- ++ shadow_start = kasan_mem_to_shadow_align_down((unsigned long)va); ++ shadow_end = kasan_mem_to_shadow_align_up((unsigned long)va + size); + kasan_populate_shadow(shadow_start, shadow_end, nid); + } + + void __init kasan_init(void) + { ++ unsigned long shadow_cea_begin, shadow_cea_end; + int i; +- void *shadow_cea_begin, *shadow_cea_end; + + memcpy(early_top_pgt, init_top_pgt, sizeof(early_top_pgt)); + +@@ -372,16 +383,9 @@ void __init kasan_init(void) + map_range(&pfn_mapped[i]); + } + +- shadow_cea_begin = (void *)CPU_ENTRY_AREA_BASE; +- shadow_cea_begin = kasan_mem_to_shadow(shadow_cea_begin); +- shadow_cea_begin = (void *)round_down( +- (unsigned long)shadow_cea_begin, PAGE_SIZE); +- +- shadow_cea_end = (void *)(CPU_ENTRY_AREA_BASE + +- CPU_ENTRY_AREA_MAP_SIZE); +- shadow_cea_end = kasan_mem_to_shadow(shadow_cea_end); +- shadow_cea_end = (void *)round_up( +- (unsigned long)shadow_cea_end, PAGE_SIZE); ++ shadow_cea_begin = kasan_mem_to_shadow_align_down(CPU_ENTRY_AREA_BASE); ++ shadow_cea_end = kasan_mem_to_shadow_align_up(CPU_ENTRY_AREA_BASE + ++ CPU_ENTRY_AREA_MAP_SIZE); + + kasan_populate_early_shadow( + kasan_mem_to_shadow((void *)PAGE_OFFSET + MAXMEM), +@@ -403,9 +407,9 @@ void __init kasan_init(void) + + kasan_populate_early_shadow( + kasan_mem_to_shadow((void *)VMALLOC_END + 1), +- shadow_cea_begin); ++ (void *)shadow_cea_begin); + +- kasan_populate_early_shadow(shadow_cea_end, ++ kasan_populate_early_shadow((void *)shadow_cea_end, + kasan_mem_to_shadow((void *)__START_KERNEL_map)); + + kasan_populate_shadow((unsigned long)kasan_mem_to_shadow(_stext), +-- +2.25.1 + diff --git a/0022-x86-kasan-Populate-shadow-for-shared-chunk-of-the-CP.patch b/0022-x86-kasan-Populate-shadow-for-shared-chunk-of-the-CP.patch new file mode 100644 index 0000000..d6f9b77 --- /dev/null +++ b/0022-x86-kasan-Populate-shadow-for-shared-chunk-of-the-CP.patch @@ -0,0 +1,99 @@ +From 885cbab14224aca9bcf6df23a432a84e55b55dd5 Mon Sep 17 00:00:00 2001 +From: Sean Christopherson <seanjc(a)google.com> +Date: Fri, 17 Mar 2023 03:07:47 +0000 +Subject: [PATCH 22/24] x86/kasan: Populate shadow for shared chunk of the CPU + entry area + +mainline inclusion +from mainline-v6.2-rc1 +commit 1cfaac2400c73378e78182a706be0f3ac8b93cd7 +category: bugfix +bugzilla: 188336 +CVE: CVE-2023-0597 + +Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… + +-------------------------------- + +Popuplate the shadow for the shared portion of the CPU entry area, i.e. +the read-only IDT mapping, during KASAN initialization. A recent change +modified KASAN to map the per-CPU areas on-demand, but forgot to keep a +shadow for the common area that is shared amongst all CPUs. + +Map the common area in KASAN init instead of letting idt_map_in_cea() do +the dirty work so that it Just Works in the unlikely event more shared +data is shoved into the CPU entry area. + +The bug manifests as a not-present #PF when software attempts to lookup +an IDT entry, e.g. when KVM is handling IRQs on Intel CPUs (KVM performs +direct CALL to the IRQ handler to avoid the overhead of INTn): + + BUG: unable to handle page fault for address: fffffbc0000001d8 + #PF: supervisor read access in kernel mode + #PF: error_code(0x0000) - not-present page + PGD 16c03a067 P4D 16c03a067 PUD 0 + Oops: 0000 [#1] PREEMPT SMP KASAN + CPU: 5 PID: 901 Comm: repro Tainted: G W 6.1.0-rc3+ #410 + Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 0.0.0 02/06/2015 + RIP: 0010:kasan_check_range+0xdf/0x190 + vmx_handle_exit_irqoff+0x152/0x290 [kvm_intel] + vcpu_run+0x1d89/0x2bd0 [kvm] + kvm_arch_vcpu_ioctl_run+0x3ce/0xa70 [kvm] + kvm_vcpu_ioctl+0x349/0x900 [kvm] + __x64_sys_ioctl+0xb8/0xf0 + do_syscall_64+0x2b/0x50 + entry_SYSCALL_64_after_hwframe+0x46/0xb0 + +Fixes: 9fd429c28073 ("x86/kasan: Map shadow for percpu pages on demand") +Reported-by: syzbot+8cdd16fd5a6c0565e227(a)syzkaller.appspotmail.com +Signed-off-by: Sean Christopherson <seanjc(a)google.com> +Signed-off-by: Peter Zijlstra (Intel) <peterz(a)infradead.org> +Link: https://lkml.kernel.org/r/20221110203504.1985010-6-seanjc@google.com +Signed-off-by: Tong Tiangen <tongtiangen(a)huawei.com> +Reviewed-by: Nanyong Sun <sunnanyong(a)huawei.com> +Reviewed-by: Kefeng Wang <wangkefeng.wang(a)huawei.com> +Signed-off-by: Jialin Zhang <zhangjialin11(a)huawei.com> +--- + arch/x86/mm/kasan_init_64.c | 12 +++++++++++- + 1 file changed, 11 insertions(+), 1 deletion(-) + +diff --git a/arch/x86/mm/kasan_init_64.c b/arch/x86/mm/kasan_init_64.c +index afc5e129ca7b..0302491d799d 100644 +--- a/arch/x86/mm/kasan_init_64.c ++++ b/arch/x86/mm/kasan_init_64.c +@@ -341,7 +341,7 @@ void __init kasan_populate_shadow_for_vaddr(void *va, size_t size, int nid) + + void __init kasan_init(void) + { +- unsigned long shadow_cea_begin, shadow_cea_end; ++ unsigned long shadow_cea_begin, shadow_cea_per_cpu_begin, shadow_cea_end; + int i; + + memcpy(early_top_pgt, init_top_pgt, sizeof(early_top_pgt)); +@@ -384,6 +384,7 @@ void __init kasan_init(void) + } + + shadow_cea_begin = kasan_mem_to_shadow_align_down(CPU_ENTRY_AREA_BASE); ++ shadow_cea_per_cpu_begin = kasan_mem_to_shadow_align_up(CPU_ENTRY_AREA_PER_CPU); + shadow_cea_end = kasan_mem_to_shadow_align_up(CPU_ENTRY_AREA_BASE + + CPU_ENTRY_AREA_MAP_SIZE); + +@@ -409,6 +410,15 @@ void __init kasan_init(void) + kasan_mem_to_shadow((void *)VMALLOC_END + 1), + (void *)shadow_cea_begin); + ++ /* ++ * Populate the shadow for the shared portion of the CPU entry area. ++ * Shadows for the per-CPU areas are mapped on-demand, as each CPU's ++ * area is randomly placed somewhere in the 512GiB range and mapping ++ * the entire 512GiB range is prohibitively expensive. ++ */ ++ kasan_populate_shadow(shadow_cea_begin, ++ shadow_cea_per_cpu_begin, 0); ++ + kasan_populate_early_shadow((void *)shadow_cea_end, + kasan_mem_to_shadow((void *)__START_KERNEL_map)); + +-- +2.25.1 + diff --git a/0023-net-sched-act_mirred-better-wording-on-protection-ag.patch b/0023-net-sched-act_mirred-better-wording-on-protection-ag.patch new file mode 100644 index 0000000..8065822 --- /dev/null +++ b/0023-net-sched-act_mirred-better-wording-on-protection-ag.patch @@ -0,0 +1,97 @@ +From 1420d4aeb4cecca648b494e6d875c222da1d9309 Mon Sep 17 00:00:00 2001 +From: Davide Caratti <dcaratti(a)redhat.com> +Date: Sat, 18 Mar 2023 16:46:22 +0800 +Subject: [PATCH 23/24] net/sched: act_mirred: better wording on protection + against excessive stack growth + +mainline inclusion +from mainline-v6.3-rc1 +commit 78dcdffe0418ac8f3f057f26fe71ccf4d8ed851f +category: bugfix +bugzilla: https://gitee.com/src-openeuler/kernel/issues/I64END +CVE: CVE-2022-4269 + +Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… + +-------------------------------- + +with commit e2ca070f89ec ("net: sched: protect against stack overflow in +TC act_mirred"), act_mirred protected itself against excessive stack growth +using per_cpu counter of nested calls to tcf_mirred_act(), and capping it +to MIRRED_RECURSION_LIMIT. However, such protection does not detect +recursion/loops in case the packet is enqueued to the backlog (for example, +when the mirred target device has RPS or skb timestamping enabled). Change +the wording from "recursion" to "nesting" to make it more clear to readers. + +CC: Jamal Hadi Salim <jhs(a)mojatatu.com> +Signed-off-by: Davide Caratti <dcaratti(a)redhat.com> +Reviewed-by: Marcelo Ricardo Leitner <marcelo.leitner(a)gmail.com> +Acked-by: Jamal Hadi Salim <jhs(a)mojatatu.com> +Signed-off-by: Paolo Abeni <pabeni(a)redhat.com> +Signed-off-by: Ziyang Xuan <william.xuanziyang(a)huawei.com> +Reviewed-by: Yue Haibing <yuehaibing(a)huawei.com> +Signed-off-by: Jialin Zhang <zhangjialin11(a)huawei.com> +--- + net/sched/act_mirred.c | 16 ++++++++-------- + 1 file changed, 8 insertions(+), 8 deletions(-) + +diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c +index b8ad6ae282c0..ded6ee054be1 100644 +--- a/net/sched/act_mirred.c ++++ b/net/sched/act_mirred.c +@@ -28,8 +28,8 @@ + static LIST_HEAD(mirred_list); + static DEFINE_SPINLOCK(mirred_list_lock); + +-#define MIRRED_RECURSION_LIMIT 4 +-static DEFINE_PER_CPU(unsigned int, mirred_rec_level); ++#define MIRRED_NEST_LIMIT 4 ++static DEFINE_PER_CPU(unsigned int, mirred_nest_level); + + static bool tcf_mirred_is_act_redirect(int action) + { +@@ -224,7 +224,7 @@ static int tcf_mirred_act(struct sk_buff *skb, const struct tc_action *a, + struct sk_buff *skb2 = skb; + bool m_mac_header_xmit; + struct net_device *dev; +- unsigned int rec_level; ++ unsigned int nest_level; + int retval, err = 0; + bool use_reinsert; + bool want_ingress; +@@ -235,11 +235,11 @@ static int tcf_mirred_act(struct sk_buff *skb, const struct tc_action *a, + int mac_len; + bool at_nh; + +- rec_level = __this_cpu_inc_return(mirred_rec_level); +- if (unlikely(rec_level > MIRRED_RECURSION_LIMIT)) { ++ nest_level = __this_cpu_inc_return(mirred_nest_level); ++ if (unlikely(nest_level > MIRRED_NEST_LIMIT)) { + net_warn_ratelimited("Packet exceeded mirred recursion limit on dev %s\n", + netdev_name(skb->dev)); +- __this_cpu_dec(mirred_rec_level); ++ __this_cpu_dec(mirred_nest_level); + return TC_ACT_SHOT; + } + +@@ -308,7 +308,7 @@ static int tcf_mirred_act(struct sk_buff *skb, const struct tc_action *a, + err = tcf_mirred_forward(want_ingress, skb); + if (err) + tcf_action_inc_overlimit_qstats(&m->common); +- __this_cpu_dec(mirred_rec_level); ++ __this_cpu_dec(mirred_nest_level); + return TC_ACT_CONSUMED; + } + } +@@ -320,7 +320,7 @@ static int tcf_mirred_act(struct sk_buff *skb, const struct tc_action *a, + if (tcf_mirred_is_act_redirect(m_eaction)) + retval = TC_ACT_SHOT; + } +- __this_cpu_dec(mirred_rec_level); ++ __this_cpu_dec(mirred_nest_level); + + return retval; + } +-- +2.25.1 + diff --git a/0024-act_mirred-use-the-backlog-for-nested-calls-to-mirre.patch b/0024-act_mirred-use-the-backlog-for-nested-calls-to-mirre.patch new file mode 100644 index 0000000..edfc0ba --- /dev/null +++ b/0024-act_mirred-use-the-backlog-for-nested-calls-to-mirre.patch @@ -0,0 +1,149 @@ +From a6bb3989ccb7d3493c20e709179904733c6db856 Mon Sep 17 00:00:00 2001 +From: Davide Caratti <dcaratti(a)redhat.com> +Date: Sat, 18 Mar 2023 16:46:40 +0800 +Subject: [PATCH 24/24] act_mirred: use the backlog for nested calls to mirred + ingress + +mainline inclusion +from mainline-v6.3-rc1 +commit ca22da2fbd693b54dc8e3b7b54ccc9f7e9ba3640 +category: bugfix +bugzilla: https://gitee.com/src-openeuler/kernel/issues/I64END +CVE: CVE-2022-4269 + +Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… + +-------------------------------- + +William reports kernel soft-lockups on some OVS topologies when TC mirred +egress->ingress action is hit by local TCP traffic [1]. +The same can also be reproduced with SCTP (thanks Xin for verifying), when +client and server reach themselves through mirred egress to ingress, and +one of the two peers sends a "heartbeat" packet (from within a timer). + +Enqueueing to backlog proved to fix this soft lockup; however, as Cong +noticed [2], we should preserve - when possible - the current mirred +behavior that counts as "overlimits" any eventual packet drop subsequent to +the mirred forwarding action [3]. A compromise solution might use the +backlog only when tcf_mirred_act() has a nest level greater than one: +change tcf_mirred_forward() accordingly. + +Also, add a kselftest that can reproduce the lockup and verifies TC mirred +ability to account for further packet drops after TC mirred egress->ingress +(when the nest level is 1). + + [1] https://lore.kernel.org/netdev/33dc43f587ec1388ba456b4915c75f02a8aae226.166… + [2] https://lore.kernel.org/netdev/Y0w%2FWWY60gqrtGLp@pop-os.localdomain/ + [3] such behavior is not guaranteed: for example, if RPS or skb RX + timestamping is enabled on the mirred target device, the kernel + can defer receiving the skb and return NET_RX_SUCCESS inside + tcf_mirred_forward(). + +Reported-by: William Zhao <wizhao(a)redhat.com> +CC: Xin Long <lucien.xin(a)gmail.com> +Signed-off-by: Davide Caratti <dcaratti(a)redhat.com> +Reviewed-by: Marcelo Ricardo Leitner <marcelo.leitner(a)gmail.com> +Acked-by: Jamal Hadi Salim <jhs(a)mojatatu.com> +Signed-off-by: Paolo Abeni <pabeni(a)redhat.com> +Signed-off-by: Ziyang Xuan <william.xuanziyang(a)huawei.com> +Reviewed-by: Yue Haibing <yuehaibing(a)huawei.com> +Signed-off-by: Jialin Zhang <zhangjialin11(a)huawei.com> +--- + net/sched/act_mirred.c | 7 +++ + .../selftests/net/forwarding/tc_actions.sh | 49 ++++++++++++++++++- + 2 files changed, 55 insertions(+), 1 deletion(-) + +diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c +index ded6ee054be1..baeae5e5c8f0 100644 +--- a/net/sched/act_mirred.c ++++ b/net/sched/act_mirred.c +@@ -205,12 +205,19 @@ static int tcf_mirred_init(struct net *net, struct nlattr *nla, + return err; + } + ++static bool is_mirred_nested(void) ++{ ++ return unlikely(__this_cpu_read(mirred_nest_level) > 1); ++} ++ + static int tcf_mirred_forward(bool want_ingress, struct sk_buff *skb) + { + int err; + + if (!want_ingress) + err = tcf_dev_queue_xmit(skb, dev_queue_xmit); ++ else if (is_mirred_nested()) ++ err = netif_rx(skb); + else + err = netif_receive_skb(skb); + +diff --git a/tools/testing/selftests/net/forwarding/tc_actions.sh b/tools/testing/selftests/net/forwarding/tc_actions.sh +index 1e0a62f638fe..919c0dd9fe4b 100755 +--- a/tools/testing/selftests/net/forwarding/tc_actions.sh ++++ b/tools/testing/selftests/net/forwarding/tc_actions.sh +@@ -3,7 +3,8 @@ + + ALL_TESTS="gact_drop_and_ok_test mirred_egress_redirect_test \ + mirred_egress_mirror_test matchall_mirred_egress_mirror_test \ +- gact_trap_test mirred_egress_to_ingress_test" ++ gact_trap_test mirred_egress_to_ingress_test \ ++ mirred_egress_to_ingress_tcp_test" + NUM_NETIFS=4 + source tc_common.sh + source lib.sh +@@ -198,6 +199,52 @@ mirred_egress_to_ingress_test() + log_test "mirred_egress_to_ingress ($tcflags)" + } + ++mirred_egress_to_ingress_tcp_test() ++{ ++ local tmpfile=$(mktemp) tmpfile1=$(mktemp) ++ ++ RET=0 ++ dd conv=sparse status=none if=/dev/zero bs=1M count=2 of=$tmpfile ++ tc filter add dev $h1 protocol ip pref 100 handle 100 egress flower \ ++ $tcflags ip_proto tcp src_ip 192.0.2.1 dst_ip 192.0.2.2 \ ++ action ct commit nat src addr 192.0.2.2 pipe \ ++ action ct clear pipe \ ++ action ct commit nat dst addr 192.0.2.1 pipe \ ++ action ct clear pipe \ ++ action skbedit ptype host pipe \ ++ action mirred ingress redirect dev $h1 ++ tc filter add dev $h1 protocol ip pref 101 handle 101 egress flower \ ++ $tcflags ip_proto icmp \ ++ action mirred ingress redirect dev $h1 ++ tc filter add dev $h1 protocol ip pref 102 handle 102 ingress flower \ ++ ip_proto icmp \ ++ action drop ++ ++ ip vrf exec v$h1 nc --recv-only -w10 -l -p 12345 -o $tmpfile1 & ++ local rpid=$! ++ ip vrf exec v$h1 nc -w1 --send-only 192.0.2.2 12345 <$tmpfile ++ wait -n $rpid ++ cmp -s $tmpfile $tmpfile1 ++ check_err $? "server output check failed" ++ ++ $MZ $h1 -c 10 -p 64 -a $h1mac -b $h1mac -A 192.0.2.1 -B 192.0.2.1 \ ++ -t icmp "ping,id=42,seq=5" -q ++ tc_check_packets "dev $h1 egress" 101 10 ++ check_err $? "didn't mirred redirect ICMP" ++ tc_check_packets "dev $h1 ingress" 102 10 ++ check_err $? "didn't drop mirred ICMP" ++ local overlimits=$(tc_rule_stats_get ${h1} 101 egress .overlimits) ++ test ${overlimits} = 10 ++ check_err $? "wrong overlimits, expected 10 got ${overlimits}" ++ ++ tc filter del dev $h1 egress protocol ip pref 100 handle 100 flower ++ tc filter del dev $h1 egress protocol ip pref 101 handle 101 flower ++ tc filter del dev $h1 ingress protocol ip pref 102 handle 102 flower ++ ++ rm -f $tmpfile $tmpfile1 ++ log_test "mirred_egress_to_ingress_tcp ($tcflags)" ++} ++ + setup_prepare() + { + h1=${NETIFS[p1]} +-- +2.25.1 + diff --git a/kernel.spec b/kernel.spec index 0eb5b16..f4bc7a4 100644 --- a/kernel.spec +++ b/kernel.spec @@ -10,9 +10,9 @@ %global upstream_version 6.1 %global upstream_sublevel 19 -%global devel_release 6 +%global devel_release 7 %global maintenance_release .0.0 -%global pkg_release .16 +%global pkg_release .17 %define with_debuginfo 0 # Do not recompute the build-id of vmlinux in find-debuginfo.sh @@ -84,6 +84,16 @@ Patch0011: 0011-bpf-Two-helper-functions-are-introduced-to-parse-use.patch Patch0012: 0012-net-bpf-Add-a-writeable_tracepoint-to-inet_stream_co.patch Patch0013: 0013-nfs-client-multipath.patch Patch0014: 0014-nfs-client-multipath-config.patch +Patch0015: 0015-mm-demotion-fix-NULL-vs-IS_ERR-checking-in-memory_ti.patch +Patch0016: 0016-x86-mm-Randomize-per-cpu-entry-area.patch +Patch0017: 0017-x86-kasan-Map-shadow-for-percpu-pages-on-demand.patch +Patch0018: 0018-x86-mm-Recompute-physical-address-for-every-page-of-.patch +Patch0019: 0019-x86-mm-Populate-KASAN-shadow-for-entire-per-CPU-rang.patch +Patch0020: 0020-x86-kasan-Rename-local-CPU_ENTRY_AREA-variables-to-s.patch +Patch0021: 0021-x86-kasan-Add-helpers-to-align-shadow-addresses-up-a.patch +Patch0022: 0022-x86-kasan-Populate-shadow-for-shared-chunk-of-the-CP.patch +Patch0023: 0023-net-sched-act_mirred-better-wording-on-protection-ag.patch +Patch0024: 0024-act_mirred-use-the-backlog-for-nested-calls-to-mirre.patch #BuildRequires: @@ -323,6 +333,16 @@ Applypatches series.conf %{_builddir}/kernel-%{version}/linux-%{KernelVer} %patch0012 -p1 %patch0013 -p1 %patch0014 -p1 +%patch0015 -p1 +%patch0016 -p1 +%patch0017 -p1 +%patch0018 -p1 +%patch0019 -p1 +%patch0020 -p1 +%patch0021 -p1 +%patch0022 -p1 +%patch0023 -p1 +%patch0024 -p1 touch .scmversion find . $ -name "*.orig" -o -name "*~" $ -exec rm -f {} \; >/dev/null @@ -905,6 +925,9 @@ fi %endif %changelog +* Fri Mar 18 2023 Jialin Zhang <zhangjialin11(a)huawei.com> - 6.1.19-7.0.0.17 +- Fix CVE-2023-23005, CVE-2023-0597 and CVE-2022-4269 + * Fri Mar 17 2023 Zheng Zengkai <zhengzengkai(a)huawei.com> - 6.1.19-6.0.0.16 - Fix kernel rpm build failure that libperf-jvmti.so is missing -- 2.25.1

1 0

[PATCH PR openEuler-22.03-LTS-SP1] mm/vmalloc: huge vmalloc backing pages should be split rather than compound
by Jialin Zhang 17 Mar '23

17 Mar '23

From: Nicholas Piggin <npiggin(a)gmail.com> mainline inclusion from mainline-v5.18-rc4 commit 3b8000ae185cb068adbda5f966a3835053c85fd4 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I6LD0S CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- Huge vmalloc higher-order backing pages were allocated with __GFP_COMP in order to allow the sub-pages to be refcounted by callers such as "remap_vmalloc_page [sic]" (remap_vmalloc_range). However a similar problem exists for other struct page fields callers use, for example fb_deferred_io_fault() takes a vmalloc'ed page and not only refcounts it but uses ->lru, ->mapping, ->index. This is not compatible with compound sub-pages, and can cause bad page state issues like BUG: Bad page state in process swapper/0 pfn:00743 page:(____ptrval____) refcount:0 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x743 flags: 0x7ffff000000000(node=0|zone=0|lastcpupid=0x7ffff) raw: 007ffff000000000 c00c00000001d0c8 c00c00000001d0c8 0000000000000000 raw: 0000000000000000 0000000000000000 00000000ffffffff 0000000000000000 page dumped because: corrupted mapping in tail page Modules linked in: CPU: 0 PID: 1 Comm: swapper/0 Not tainted 5.18.0-rc3-00082-gfc6fff4a7ce1-dirty #2810 Call Trace: dump_stack_lvl+0x74/0xa8 (unreliable) bad_page+0x12c/0x170 free_tail_pages_check+0xe8/0x190 free_pcp_prepare+0x31c/0x4e0 free_unref_page+0x40/0x1b0 __vunmap+0x1d8/0x420 ... The correct approach is to use split high-order pages for the huge vmalloc backing. These allow callers to treat them in exactly the same way as individually-allocated order-0 pages. Link: https://lore.kernel.org/all/14444103-d51b-0fb3-ee63-c3f182f0b546@molgen.mpg… Signed-off-by: Nicholas Piggin <npiggin(a)gmail.com> Cc: Paul Menzel <pmenzel(a)molgen.mpg.de> Cc: Song Liu <songliubraving(a)fb.com> Cc: Rick Edgecombe <rick.p.edgecombe(a)intel.com> Signed-off-by: Linus Torvalds <torvalds(a)linux-foundation.org> conflicts: mm/vmalloc.c Signed-off-by: ZhangPeng <zhangpeng362(a)huawei.com> Reviewed-by: Kefeng Wang <wangkefeng.wang(a)huawei.com> Signed-off-by: Jialin Zhang <zhangjialin11(a)huawei.com> --- mm/vmalloc.c | 22 +++++++++++++++++----- 1 file changed, 17 insertions(+), 5 deletions(-) diff --git a/mm/vmalloc.c b/mm/vmalloc.c index e27cd716ca95..2ca2c1bc0db9 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -2641,14 +2641,17 @@ static void __vunmap(const void *addr, int deallocate_pages) vm_remove_mappings(area, deallocate_pages); if (deallocate_pages) { - unsigned int page_order = vm_area_page_order(area); int i; - for (i = 0; i < area->nr_pages; i += 1U << page_order) { + for (i = 0; i < area->nr_pages; i++) { struct page *page = area->pages[i]; BUG_ON(!page); - __free_pages(page, page_order); + /* + * High-order allocs for huge vmallocs are split, so + * can be freed as an array of order-0 allocations + */ + __free_pages(page, 0); } atomic_long_sub(area->nr_pages, &nr_vmalloc_pages); @@ -2930,8 +2933,7 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask, struct page *page; int p; - /* Compound pages required for remap_vmalloc_page */ - page = alloc_pages_node(node, gfp_mask | __GFP_COMP, page_order); + page = alloc_pages_node(node, gfp_mask, page_order); if (unlikely(!page)) { /* Successfully allocated i pages, free them in __vfree() */ area->nr_pages = i; @@ -2943,6 +2945,16 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask, goto fail; } + /* + * Higher order allocations must be able to be treated as + * indepdenent small pages by callers (as they can with + * small-page vmallocs). Some drivers do their own refcounting + * on vmalloc_to_page() pages, some use page->mapping, + * page->lru, etc. + */ + if (page_order) + split_page(page, page_order); + for (p = 0; p < (1U << page_order); p++) area->pages[i + p] = page + p; -- 2.25.1

1 0

[PATCH openEuler-1.0-LTS 01/10] media: dvb-usb: az6027: fix null-ptr-deref in az6027_i2c_xfer()
by Yongqiang Liu 17 Mar '23

17 Mar '23

From: Baisong Zhong <zhongbaisong(a)huawei.com> mainline inclusion from mainline-v6.2-rc1 commit 0ed554fd769a19ea8464bb83e9ac201002ef74ad category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I6NCQH CVE: CVE-2023-28328 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- Wei Chen reports a kernel bug as blew: general protection fault, probably for non-canonical address KASAN: null-ptr-deref in range [0x0000000000000010-0x0000000000000017] ... Call Trace: <TASK> __i2c_transfer+0x77e/0x1930 drivers/i2c/i2c-core-base.c:2109 i2c_transfer+0x1d5/0x3d0 drivers/i2c/i2c-core-base.c:2170 i2cdev_ioctl_rdwr+0x393/0x660 drivers/i2c/i2c-dev.c:297 i2cdev_ioctl+0x75d/0x9f0 drivers/i2c/i2c-dev.c:458 vfs_ioctl fs/ioctl.c:51 [inline] __do_sys_ioctl fs/ioctl.c:870 [inline] __se_sys_ioctl+0xfb/0x170 fs/ioctl.c:856 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x3d/0x90 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x63/0xcd RIP: 0033:0x7fd834a8bded In az6027_i2c_xfer(), if msg[i].addr is 0x99, a null-ptr-deref will caused when accessing msg[i].buf. For msg[i].len is 0 and msg[i].buf is null. Fix this by checking msg[i].len in az6027_i2c_xfer(). Link: https://lore.kernel.org/lkml/CAO4mrfcPHB5aQJO=mpqV+p8mPLNg-Fok0gw8gZ=zemAfM… Link: https://lore.kernel.org/linux-media/20221120065918.2160782-1-zhongbaisong@h… Fixes: 76f9a820c867 ("V4L/DVB: AZ6027: Initial import of the driver") Reported-by: Wei Chen <harperchen1110(a)gmail.com> Signed-off-by: Baisong Zhong <zhongbaisong(a)huawei.com> Signed-off-by: Mauro Carvalho Chehab <mchehab(a)kernel.org> Signed-off-by: ZhangPeng <zhangpeng362(a)huawei.com> Reviewed-by: Kefeng Wang <wangkefeng.wang(a)huawei.com> Reviewed-by: Nanyong Sun <sunnanyong(a)huawei.com> Reviewed-by: Xiu Jianfeng <xiujianfeng(a)huawei.com> Signed-off-by: Yongqiang Liu <liuyongqiang13(a)huawei.com> --- drivers/media/usb/dvb-usb/az6027.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/drivers/media/usb/dvb-usb/az6027.c b/drivers/media/usb/dvb-usb/az6027.c index 6321b8e30261..555c8ac44881 100644 --- a/drivers/media/usb/dvb-usb/az6027.c +++ b/drivers/media/usb/dvb-usb/az6027.c @@ -977,6 +977,10 @@ static int az6027_i2c_xfer(struct i2c_adapter *adap, struct i2c_msg msg[], int n if (msg[i].addr == 0x99) { req = 0xBE; index = 0; + if (msg[i].len < 1) { + i = -EOPNOTSUPP; + break; + } value = msg[i].buf[0] & 0x00ff; length = 1; az6027_usb_out_op(d, req, value, index, data, length); -- 2.25.1

1 9

[PATCH OLK-5.10] Revert "scsi: hisi_sas: Disable SATA disk phy for severe I_T nexus reset failure"
by Yihang Li 17 Mar '23

17 Mar '23

driver inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I6NX2M CVE: NA ---------------------------------------------------------------------- This fix commit c723ada86707c6afe524b51126c301d689c64d8e. In that commit, if the softreset fails upon certain conditions, just disable the PHY associated with the disk. The user needs to restore the PHY. SATA disks do not support simultaneous connection of multiple hosts. Therefore, when multiple controllers are connected to a SATA disk at the same time, the controller which is connected later failed to issue an ATA softreset to the SATA disk. As a result, the PHY associated with the disk is disabled and cannot be automatically recovered. Now that, we will not focus on the execution result of softreset. No matter whether the execution is successful or not, we will directly carry out I_T_nexus_reset. Signed-off-by: Yihang Li <liyihang9(a)huawei.com> Signed-off-by: xiabing <xiabing12(a)h-partners.com> --- drivers/scsi/hisi_sas/hisi_sas_main.c | 29 +++++---------------------- 1 file changed, 5 insertions(+), 24 deletions(-) diff --git a/drivers/scsi/hisi_sas/hisi_sas_main.c b/drivers/scsi/hisi_sas/hisi_sas_main.c index b8249a055fbb..0f5578e52558 100644 --- a/drivers/scsi/hisi_sas/hisi_sas_main.c +++ b/drivers/scsi/hisi_sas/hisi_sas_main.c @@ -1895,33 +1895,14 @@ static int hisi_sas_I_T_nexus_reset(struct domain_device *device) } hisi_sas_dereg_device(hisi_hba, device); - rc = hisi_sas_debug_I_T_nexus_reset(device); - if (rc == TMF_RESP_FUNC_COMPLETE && dev_is_sata(device)) { - struct sas_phy *local_phy; - + if (dev_is_sata(device)) { rc = hisi_sas_softreset_ata_disk(device); - switch (rc) { - case -ECOMM: - rc = -ENODEV; - break; - case TMF_RESP_FUNC_FAILED: - case -EMSGSIZE: - case -EIO: - local_phy = sas_get_local_phy(device); - rc = sas_phy_enable(local_phy, 0); - if (!rc) { - local_phy->enabled = 0; - dev_err(dev, "Disabled local phy of ATA disk %016llx due to softreset fail (%d)\n", - SAS_ADDR(device->sas_addr), rc); - rc = -ENODEV; - } - sas_put_local_phy(local_phy); - break; - default: - break; - } + if (rc == TMF_RESP_FUNC_FAILED) + dev_err(dev, "ata disk %016llx reset (%d)\n", + SAS_ADDR(device->sas_addr), rc); } + rc = hisi_sas_debug_I_T_nexus_reset(device); if ((rc == TMF_RESP_FUNC_COMPLETE) || (rc == -ENODEV)) hisi_sas_release_task(hisi_hba, device); -- 2.30.0

1 0

[PATCH openEuler-1.0-LTS 1/8] fs/proc: task_mmu.c: don't read mapcount for migration entry
by Yongqiang Liu 17 Mar '23

17 Mar '23

From: Yang Shi <shy828301(a)gmail.com> stable inclusion from stable-v5.10.102 commit db3f3636e4aed2cba3e4e7897a053323f7a62249 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I6EVUJ Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- commit 24d7275ce2791829953ed4e72f68277ceb2571c6 upstream. The syzbot reported the below BUG: kernel BUG at include/linux/page-flags.h:785! invalid opcode: 0000 [#1] PREEMPT SMP KASAN CPU: 1 PID: 4392 Comm: syz-executor560 Not tainted 5.16.0-rc6-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 RIP: 0010:PageDoubleMap include/linux/page-flags.h:785 [inline] RIP: 0010:__page_mapcount+0x2d2/0x350 mm/util.c:744 Call Trace: page_mapcount include/linux/mm.h:837 [inline] smaps_account+0x470/0xb10 fs/proc/task_mmu.c:466 smaps_pte_entry fs/proc/task_mmu.c:538 [inline] smaps_pte_range+0x611/0x1250 fs/proc/task_mmu.c:601 walk_pmd_range mm/pagewalk.c:128 [inline] walk_pud_range mm/pagewalk.c:205 [inline] walk_p4d_range mm/pagewalk.c:240 [inline] walk_pgd_range mm/pagewalk.c:277 [inline] __walk_page_range+0xe23/0x1ea0 mm/pagewalk.c:379 walk_page_vma+0x277/0x350 mm/pagewalk.c:530 smap_gather_stats.part.0+0x148/0x260 fs/proc/task_mmu.c:768 smap_gather_stats fs/proc/task_mmu.c:741 [inline] show_smap+0xc6/0x440 fs/proc/task_mmu.c:822 seq_read_iter+0xbb0/0x1240 fs/seq_file.c:272 seq_read+0x3e0/0x5b0 fs/seq_file.c:162 vfs_read+0x1b5/0x600 fs/read_write.c:479 ksys_read+0x12d/0x250 fs/read_write.c:619 do_syscall_x64 arch/x86/entry/common.c:50 [inline] do_syscall_64+0x35/0xb0 arch/x86/entry/common.c:80 entry_SYSCALL_64_after_hwframe+0x44/0xae The reproducer was trying to read /proc/$PID/smaps when calling MADV_FREE at the mean time. MADV_FREE may split THPs if it is called for partial THP. It may trigger the below race: CPU A CPU B ----- ----- smaps walk: MADV_FREE: page_mapcount() PageCompound() split_huge_page() page = compound_head(page) PageDoubleMap(page) When calling PageDoubleMap() this page is not a tail page of THP anymore so the BUG is triggered. This could be fixed by elevated refcount of the page before calling mapcount, but that would prevent it from counting migration entries, and it seems overkilling because the race just could happen when PMD is split so all PTE entries of tail pages are actually migration entries, and smaps_account() does treat migration entries as mapcount == 1 as Kirill pointed out. Add a new parameter for smaps_account() to tell this entry is migration entry then skip calling page_mapcount(). Don't skip getting mapcount for device private entries since they do track references with mapcount. Pagemap also has the similar issue although it was not reported. Fixed it as well. [shy828301(a)gmail.com: v4] Link: https://lkml.kernel.org/r/20220203182641.824731-1-shy828301@gmail.com [nathan(a)kernel.org: avoid unused variable warning in pagemap_pmd_range()] Link: https://lkml.kernel.org/r/20220207171049.1102239-1-nathan@kernel.org Link: https://lkml.kernel.org/r/20220120202805.3369-1-shy828301@gmail.com Fixes: e9b61f19858a ("thp: reintroduce split_huge_page()") Signed-off-by: Yang Shi <shy828301(a)gmail.com> Signed-off-by: Nathan Chancellor <nathan(a)kernel.org> Reported-by: syzbot+1f52b3a18d5633fa7f82(a)syzkaller.appspotmail.com Acked-by: David Hildenbrand <david(a)redhat.com> Cc: "Kirill A. Shutemov" <kirill.shutemov(a)linux.intel.com> Cc: Jann Horn <jannh(a)google.com> Cc: Matthew Wilcox <willy(a)infradead.org> Cc: Alexey Dobriyan <adobriyan(a)gmail.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds(a)linux-foundation.org> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> conflicts: fs/proc/task_mmu.c Signed-off-by: Zhang Peng <zhangpeng362(a)huawei.com> Reviewed-by: Kefeng Wang <wangkefeng.wang(a)huawei.com> Signed-off-by: Yongqiang Liu <liuyongqiang13(a)huawei.com> --- fs/proc/task_mmu.c | 37 +++++++++++++++++++++++++++---------- 1 file changed, 27 insertions(+), 10 deletions(-) diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 93815b2b8440..0175fd7b3598 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -429,7 +429,8 @@ struct mem_size_stats { }; static void smaps_account(struct mem_size_stats *mss, struct page *page, - bool compound, bool young, bool dirty, bool locked) + bool compound, bool young, bool dirty, bool locked, + bool migration) { int i, nr = compound ? 1 << compound_order(page) : 1; unsigned long size = nr * PAGE_SIZE; @@ -449,8 +450,15 @@ static void smaps_account(struct mem_size_stats *mss, struct page *page, * page_count(page) == 1 guarantees the page is mapped exactly once. * If any subpage of the compound page mapped with PTE it would elevate * page_count(). + * + * The page_mapcount() is called to get a snapshot of the mapcount. + * Without holding the page lock this snapshot can be slightly wrong as + * we cannot always read the mapcount atomically. It is not safe to + * call page_mapcount() even with PTL held if the page is not mapped, + * especially for migration entries. Treat regular migration entries + * as mapcount == 1. */ - if (page_count(page) == 1) { + if ((page_count(page) == 1) || migration) { if (dirty || PageDirty(page)) mss->private_dirty += size; else @@ -505,6 +513,7 @@ static void smaps_pte_entry(pte_t *pte, unsigned long addr, struct vm_area_struct *vma = walk->vma; bool locked = !!(vma->vm_flags & VM_LOCKED); struct page *page = NULL; + bool migration = false; if (pte_present(*pte)) { page = vm_normal_page(vma, addr, *pte); @@ -524,9 +533,10 @@ static void smaps_pte_entry(pte_t *pte, unsigned long addr, } else { mss->swap_pss += (u64)PAGE_SIZE << PSS_SHIFT; } - } else if (is_migration_entry(swpent)) + } else if (is_migration_entry(swpent)) { + migration = true; page = migration_entry_to_page(swpent); - else if (is_device_private_entry(swpent)) + } else if (is_device_private_entry(swpent)) page = device_private_entry_to_page(swpent); } else if (unlikely(IS_ENABLED(CONFIG_SHMEM) && mss->check_shmem_swap && pte_none(*pte))) { @@ -546,7 +556,8 @@ static void smaps_pte_entry(pte_t *pte, unsigned long addr, if (!page) return; - smaps_account(mss, page, false, pte_young(*pte), pte_dirty(*pte), locked); + smaps_account(mss, page, false, pte_young(*pte), pte_dirty(*pte), + locked, migration); } #ifdef CONFIG_TRANSPARENT_HUGEPAGE @@ -570,7 +581,8 @@ static void smaps_pmd_entry(pmd_t *pmd, unsigned long addr, /* pass */; else VM_BUG_ON_PAGE(1, page); - smaps_account(mss, page, true, pmd_young(*pmd), pmd_dirty(*pmd), locked); + smaps_account(mss, page, true, pmd_young(*pmd), pmd_dirty(*pmd), + locked, false); } #else static void smaps_pmd_entry(pmd_t *pmd, unsigned long addr, @@ -1285,6 +1297,7 @@ static pagemap_entry_t pte_to_pagemap_entry(struct pagemapread *pm, { u64 frame = 0, flags = 0; struct page *page = NULL; + bool migration = false; if (pte_present(pte)) { if (pm->show_pfn) @@ -1302,8 +1315,10 @@ static pagemap_entry_t pte_to_pagemap_entry(struct pagemapread *pm, frame = swp_type(entry) | (swp_offset(entry) << MAX_SWAPFILES_SHIFT); flags |= PM_SWAP; - if (is_migration_entry(entry)) + if (is_migration_entry(entry)) { + migration = true; page = migration_entry_to_page(entry); + } if (is_device_private_entry(entry)) page = device_private_entry_to_page(entry); @@ -1311,7 +1326,7 @@ static pagemap_entry_t pte_to_pagemap_entry(struct pagemapread *pm, if (page && !PageAnon(page)) flags |= PM_FILE; - if (page && page_mapcount(page) == 1) + if (page && !migration && page_mapcount(page) == 1) flags |= PM_MMAP_EXCLUSIVE; if (vma->vm_flags & VM_SOFTDIRTY) flags |= PM_SOFT_DIRTY; @@ -1327,8 +1342,9 @@ static int pagemap_pmd_range(pmd_t *pmdp, unsigned long addr, unsigned long end, spinlock_t *ptl; pte_t *pte, *orig_pte; int err = 0; - #ifdef CONFIG_TRANSPARENT_HUGEPAGE + bool migration = false; + ptl = pmd_trans_huge_lock(pmdp, vma); if (ptl) { u64 flags = 0, frame = 0; @@ -1363,11 +1379,12 @@ static int pagemap_pmd_range(pmd_t *pmdp, unsigned long addr, unsigned long end, if (pmd_swp_soft_dirty(pmd)) flags |= PM_SOFT_DIRTY; VM_BUG_ON(!is_pmd_migration_entry(pmd)); + migration = is_migration_entry(entry); page = migration_entry_to_page(entry); } #endif - if (page && page_mapcount(page) == 1) + if (page && !migration && page_mapcount(page) == 1) flags |= PM_MMAP_EXCLUSIVE; for (; addr != end; addr += PAGE_SIZE) { -- 2.25.1

2 9

[PATCH OLK-5.10 0/8] SAS-related bugfix
by Yihang Li 16 Mar '23

16 Mar '23

From: xiabing <xiabing12(a)h-partners.com> 1. In the NCQ scenario, if multiple I/Os are delivered and one of the I/Os is faulty, a group of slow disks will always occur. 2. During I/O running, a null pointer exception occurs during the pressure test when a disk is removed. 3. When the length of the DMA Setup frame returned by the disk is abnormal, a group of slow disks are triggered. John Garry (2): scsi: libsas: Add sas_ata_device_link_abort() scsi: libsas: Update SATA dev FIS in sas_ata_task_done() Xingui Yang (6): scsi: hisi_sas: Move slot variable definition in hisi_sas_abort_task() scsi: hisi_sas: Add SATA_DISK_ERR bit handling for v3 hw scsi: hisi_sas: Use abort task set to reset SAS disks when discovered scsi: libsas: Grab the ATA port lock in sas_ata_device_link_abort() {topost} scsi: hisi_sas: Handle NCQ error when IPTT is valid {topost} scsi: hisi_sas: Grab sas_dev lock when traversing the members of sas_dev.list drivers/scsi/hisi_sas/hisi_sas.h | 4 +- drivers/scsi/hisi_sas/hisi_sas_main.c | 52 ++++++++++++++++------- drivers/scsi/hisi_sas/hisi_sas_v1_hw.c | 8 +++- drivers/scsi/hisi_sas/hisi_sas_v2_hw.c | 8 +++- drivers/scsi/hisi_sas/hisi_sas_v3_hw.c | 58 ++++++++++++++++++++++++-- drivers/scsi/libsas/sas_ata.c | 22 +++++++++- include/scsi/sas_ata.h | 6 +++ 7 files changed, 132 insertions(+), 26 deletions(-) -- 2.30.0

1 8

订阅
by 乄語 16 Mar '23

16 Mar '23

subscribe

1 0

[PATCH OLK-5.10 0/8] SAS-related bugfix
by Yihang Li 16 Mar '23

16 Mar '23

From: xiabing <xiabing12(a)h-partners.com> 1. In the NCQ scenario, if multiple I/Os are delivered and one of the I/Os is faulty, a group of slow disks will always occur. 2. During I/O running, a null pointer exception occurs during the pressure test when a disk is removed. 3. When the length of the DMA Setup frame returned by the disk is abnormal, a group of slow disks are triggered. John Garry (2): scsi: libsas: Add sas_ata_device_link_abort() scsi: libsas: Update SATA dev FIS in sas_ata_task_done() Xingui Yang (6): scsi: hisi_sas: Move slot variable definition in hisi_sas_abort_task() scsi: hisi_sas: Add SATA_DISK_ERR bit handling for v3 hw scsi: hisi_sas: Use abort task set to reset SAS disks when discovered scsi: libsas: Grab the ATA port lock in sas_ata_device_link_abort() {topost} scsi: hisi_sas: Handle NCQ error when IPTT is valid {topost} scsi: hisi_sas: Grab sas_dev lock when traversing the members of sas_dev.list drivers/scsi/hisi_sas/hisi_sas.h | 4 +- drivers/scsi/hisi_sas/hisi_sas_main.c | 52 ++++++++++++++++------- drivers/scsi/hisi_sas/hisi_sas_v1_hw.c | 8 +++- drivers/scsi/hisi_sas/hisi_sas_v2_hw.c | 8 +++- drivers/scsi/hisi_sas/hisi_sas_v3_hw.c | 58 ++++++++++++++++++++++++-- drivers/scsi/libsas/sas_ata.c | 22 +++++++++- include/scsi/sas_ata.h | 6 +++ 7 files changed, 132 insertions(+), 26 deletions(-) -- 2.30.0

1 8

[PATCH PR openEuler-22.03-LTS-SP1] mm/vmalloc: huge vmalloc backing pages should be split rather than compound
by Jialin Zhang 16 Mar '23

16 Mar '23

From: Nicholas Piggin <npiggin(a)gmail.com> mainline inclusion from mainline-v5.18-rc4 commit 3b8000ae185cb068adbda5f966a3835053c85fd4 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I6LD0S CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- Huge vmalloc higher-order backing pages were allocated with __GFP_COMP in order to allow the sub-pages to be refcounted by callers such as "remap_vmalloc_page [sic]" (remap_vmalloc_range). However a similar problem exists for other struct page fields callers use, for example fb_deferred_io_fault() takes a vmalloc'ed page and not only refcounts it but uses ->lru, ->mapping, ->index. This is not compatible with compound sub-pages, and can cause bad page state issues like BUG: Bad page state in process swapper/0 pfn:00743 page:(____ptrval____) refcount:0 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x743 flags: 0x7ffff000000000(node=0|zone=0|lastcpupid=0x7ffff) raw: 007ffff000000000 c00c00000001d0c8 c00c00000001d0c8 0000000000000000 raw: 0000000000000000 0000000000000000 00000000ffffffff 0000000000000000 page dumped because: corrupted mapping in tail page Modules linked in: CPU: 0 PID: 1 Comm: swapper/0 Not tainted 5.18.0-rc3-00082-gfc6fff4a7ce1-dirty #2810 Call Trace: dump_stack_lvl+0x74/0xa8 (unreliable) bad_page+0x12c/0x170 free_tail_pages_check+0xe8/0x190 free_pcp_prepare+0x31c/0x4e0 free_unref_page+0x40/0x1b0 __vunmap+0x1d8/0x420 ... The correct approach is to use split high-order pages for the huge vmalloc backing. These allow callers to treat them in exactly the same way as individually-allocated order-0 pages. Link: https://lore.kernel.org/all/14444103-d51b-0fb3-ee63-c3f182f0b546@molgen.mpg… Signed-off-by: Nicholas Piggin <npiggin(a)gmail.com> Cc: Paul Menzel <pmenzel(a)molgen.mpg.de> Cc: Song Liu <songliubraving(a)fb.com> Cc: Rick Edgecombe <rick.p.edgecombe(a)intel.com> Signed-off-by: Linus Torvalds <torvalds(a)linux-foundation.org> conflicts: mm/vmalloc.c Signed-off-by: ZhangPeng <zhangpeng362(a)huawei.com> Reviewed-by: Kefeng Wang <wangkefeng.wang(a)huawei.com> Signed-off-by: Jialin Zhang <zhangjialin11(a)huawei.com> --- mm/vmalloc.c | 22 +++++++++++++++++----- 1 file changed, 17 insertions(+), 5 deletions(-) diff --git a/mm/vmalloc.c b/mm/vmalloc.c index e27cd716ca95..2ca2c1bc0db9 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -2641,14 +2641,17 @@ static void __vunmap(const void *addr, int deallocate_pages) vm_remove_mappings(area, deallocate_pages); if (deallocate_pages) { - unsigned int page_order = vm_area_page_order(area); int i; - for (i = 0; i < area->nr_pages; i += 1U << page_order) { + for (i = 0; i < area->nr_pages; i++) { struct page *page = area->pages[i]; BUG_ON(!page); - __free_pages(page, page_order); + /* + * High-order allocs for huge vmallocs are split, so + * can be freed as an array of order-0 allocations + */ + __free_pages(page, 0); } atomic_long_sub(area->nr_pages, &nr_vmalloc_pages); @@ -2930,8 +2933,7 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask, struct page *page; int p; - /* Compound pages required for remap_vmalloc_page */ - page = alloc_pages_node(node, gfp_mask | __GFP_COMP, page_order); + page = alloc_pages_node(node, gfp_mask, page_order); if (unlikely(!page)) { /* Successfully allocated i pages, free them in __vfree() */ area->nr_pages = i; @@ -2943,6 +2945,16 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask, goto fail; } + /* + * Higher order allocations must be able to be treated as + * indepdenent small pages by callers (as they can with + * small-page vmallocs). Some drivers do their own refcounting + * on vmalloc_to_page() pages, some use page->mapping, + * page->lru, etc. + */ + if (page_order) + split_page(page, page_order); + for (p = 0; p < (1U << page_order); p++) area->pages[i + p] = page + p; -- 2.25.1

1 0

[PATCH PR OLK-5.10] mm/vmalloc: huge vmalloc backing pages should be split rather than compound
by Jialin Zhang 16 Mar '23

16 Mar '23

From: Nicholas Piggin <npiggin(a)gmail.com> mainline inclusion from mainline-v5.18-rc4 commit 3b8000ae185cb068adbda5f966a3835053c85fd4 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I6LD0S CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- Huge vmalloc higher-order backing pages were allocated with __GFP_COMP in order to allow the sub-pages to be refcounted by callers such as "remap_vmalloc_page [sic]" (remap_vmalloc_range). However a similar problem exists for other struct page fields callers use, for example fb_deferred_io_fault() takes a vmalloc'ed page and not only refcounts it but uses ->lru, ->mapping, ->index. This is not compatible with compound sub-pages, and can cause bad page state issues like BUG: Bad page state in process swapper/0 pfn:00743 page:(____ptrval____) refcount:0 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x743 flags: 0x7ffff000000000(node=0|zone=0|lastcpupid=0x7ffff) raw: 007ffff000000000 c00c00000001d0c8 c00c00000001d0c8 0000000000000000 raw: 0000000000000000 0000000000000000 00000000ffffffff 0000000000000000 page dumped because: corrupted mapping in tail page Modules linked in: CPU: 0 PID: 1 Comm: swapper/0 Not tainted 5.18.0-rc3-00082-gfc6fff4a7ce1-dirty #2810 Call Trace: dump_stack_lvl+0x74/0xa8 (unreliable) bad_page+0x12c/0x170 free_tail_pages_check+0xe8/0x190 free_pcp_prepare+0x31c/0x4e0 free_unref_page+0x40/0x1b0 __vunmap+0x1d8/0x420 ... The correct approach is to use split high-order pages for the huge vmalloc backing. These allow callers to treat them in exactly the same way as individually-allocated order-0 pages. Link: https://lore.kernel.org/all/14444103-d51b-0fb3-ee63-c3f182f0b546@molgen.mpg… Signed-off-by: Nicholas Piggin <npiggin(a)gmail.com> Cc: Paul Menzel <pmenzel(a)molgen.mpg.de> Cc: Song Liu <songliubraving(a)fb.com> Cc: Rick Edgecombe <rick.p.edgecombe(a)intel.com> Signed-off-by: Linus Torvalds <torvalds(a)linux-foundation.org> conflicts: mm/vmalloc.c Signed-off-by: ZhangPeng <zhangpeng362(a)huawei.com> Reviewed-by: Kefeng Wang <wangkefeng.wang(a)huawei.com> Signed-off-by: Jialin Zhang <zhangjialin11(a)huawei.com> --- mm/vmalloc.c | 22 +++++++++++++++++----- 1 file changed, 17 insertions(+), 5 deletions(-) diff --git a/mm/vmalloc.c b/mm/vmalloc.c index e27cd716ca95..2ca2c1bc0db9 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -2641,14 +2641,17 @@ static void __vunmap(const void *addr, int deallocate_pages) vm_remove_mappings(area, deallocate_pages); if (deallocate_pages) { - unsigned int page_order = vm_area_page_order(area); int i; - for (i = 0; i < area->nr_pages; i += 1U << page_order) { + for (i = 0; i < area->nr_pages; i++) { struct page *page = area->pages[i]; BUG_ON(!page); - __free_pages(page, page_order); + /* + * High-order allocs for huge vmallocs are split, so + * can be freed as an array of order-0 allocations + */ + __free_pages(page, 0); } atomic_long_sub(area->nr_pages, &nr_vmalloc_pages); @@ -2930,8 +2933,7 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask, struct page *page; int p; - /* Compound pages required for remap_vmalloc_page */ - page = alloc_pages_node(node, gfp_mask | __GFP_COMP, page_order); + page = alloc_pages_node(node, gfp_mask, page_order); if (unlikely(!page)) { /* Successfully allocated i pages, free them in __vfree() */ area->nr_pages = i; @@ -2943,6 +2945,16 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask, goto fail; } + /* + * Higher order allocations must be able to be treated as + * indepdenent small pages by callers (as they can with + * small-page vmallocs). Some drivers do their own refcounting + * on vmalloc_to_page() pages, some use page->mapping, + * page->lru, etc. + */ + if (page_order) + split_page(page, page_order); + for (p = 0; p < (1U << page_order); p++) area->pages[i + p] = page + p; -- 2.25.1

1 0

[PATCH openEuler-5.10-LTS 01/13] ext4: fix incorrect options show of original mount_opt and extend mount_opt2
by Jialin Zhang 15 Mar '23

15 Mar '23

From: Zhang Yi <yi.zhang(a)huawei.com> maillist inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I6D5XF Reference: https://lore.kernel.org/linux-ext4/20230130111138.76tp6pij3yhh4brh@quack3/T… -------------------------------- Current _ext4_show_options() do not distinguish MOPT_2 flag, so it mixed extend sbi->s_mount_opt2 options with sbi->s_mount_opt, it could lead to show incorrect options, e.g. show fc_debug_force if we mount with errors=continue mode and miss it if we set. $ mkfs.ext4 /dev/pmem0 $ mount -o errors=remount-ro /dev/pmem0 /mnt $ cat /proc/fs/ext4/pmem0/options | grep fc_debug_force #empty $ mount -o remount,errors=continue /mnt $ cat /proc/fs/ext4/pmem0/options | grep fc_debug_force fc_debug_force $ mount -o remount,errors=remount-ro,fc_debug_force /mnt $ cat /proc/fs/ext4/pmem0/options | grep fc_debug_force #empty Fixes: 995a3ed67fc8 ("ext4: add fast_commit feature and handling for extended mount options") Signed-off-by: Zhang Yi <yi.zhang(a)huawei.com> Conflict: fs/ext4/super.c Reviewed-by: Zhihao Cheng <chengzhihao1(a)huawei.com> Reviewed-by: Zhang Xiaoxu <zhangxiaoxu5(a)huawei.com> Signed-off-by: Jialin Zhang <zhangjialin11(a)huawei.com> --- fs/ext4/ext4.h | 1 + fs/ext4/super.c | 28 +++++++++++++++++++++------- 2 files changed, 22 insertions(+), 7 deletions(-) diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index c470a5fb2f20..7e5abaa31fea 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -1459,6 +1459,7 @@ struct ext4_sb_info { unsigned int s_mount_opt2; unsigned long s_mount_flags; unsigned int s_def_mount_opt; + unsigned int s_def_mount_opt2; ext4_fsblk_t s_sb_block; atomic64_t s_resv_clusters; kuid_t s_resuid; diff --git a/fs/ext4/super.c b/fs/ext4/super.c index dd3b72ba67e8..da8bd8031119 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -2585,7 +2585,7 @@ static int _ext4_show_options(struct seq_file *seq, struct super_block *sb, { struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_super_block *es = sbi->s_es; - int def_errors, def_mount_opt = sbi->s_def_mount_opt; + int def_errors; const struct mount_opts *m; char sep = nodefs ? '\n' : ','; @@ -2597,15 +2597,28 @@ static int _ext4_show_options(struct seq_file *seq, struct super_block *sb, for (m = ext4_mount_opts; m->token != Opt_err; m++) { int want_set = m->flags & MOPT_SET; + int opt_2 = m->flags & MOPT_2; + unsigned int mount_opt, def_mount_opt; + if (((m->flags & (MOPT_SET|MOPT_CLEAR)) == 0) || (m->flags & MOPT_CLEAR_ERR) || m->flags & MOPT_SKIP) continue; - if (!nodefs && !(m->mount_opt & (sbi->s_mount_opt ^ def_mount_opt))) - continue; /* skip if same as the default */ + + if (opt_2) { + mount_opt = sbi->s_mount_opt2; + def_mount_opt = sbi->s_def_mount_opt2; + } else { + mount_opt = sbi->s_mount_opt; + def_mount_opt = sbi->s_def_mount_opt; + } + /* skip if same as the default */ + if (!nodefs && !(m->mount_opt & (mount_opt ^ def_mount_opt))) + continue; + /* select Opt_noFoo vs Opt_Foo */ if ((want_set && - (sbi->s_mount_opt & m->mount_opt) != m->mount_opt) || - (!want_set && (sbi->s_mount_opt & m->mount_opt))) - continue; /* select Opt_noFoo vs Opt_Foo */ + (mount_opt & m->mount_opt) != m->mount_opt) || + (!want_set && (mount_opt & m->mount_opt))) + continue; SEQ_OPTS_PRINT("%s", token2str(m->token)); } @@ -2635,7 +2648,7 @@ static int _ext4_show_options(struct seq_file *seq, struct super_block *sb, if (nodefs || sbi->s_stripe) SEQ_OPTS_PRINT("stripe=%lu", sbi->s_stripe); if (nodefs || EXT4_MOUNT_DATA_FLAGS & - (sbi->s_mount_opt ^ def_mount_opt)) { + (sbi->s_mount_opt ^ sbi->s_def_mount_opt)) { if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA) SEQ_OPTS_PUTS("data=journal"); else if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_ORDERED_DATA) @@ -4340,6 +4353,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) kfree(s_mount_opts); } sbi->s_def_mount_opt = sbi->s_mount_opt; + sbi->s_def_mount_opt2 = sbi->s_mount_opt2; if (!parse_options((char *) data, sb, &journal_devnum, &journal_ioprio, 0)) goto failed_mount; -- 2.25.1

1 12

[PATCH openEuler-5.10-LTS-SP1 01/13] ext4: fix incorrect options show of original mount_opt and extend mount_opt2
by Jialin Zhang 15 Mar '23

15 Mar '23

From: Zhang Yi <yi.zhang(a)huawei.com> maillist inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I6D5XF Reference: https://lore.kernel.org/linux-ext4/20230130111138.76tp6pij3yhh4brh@quack3/T… -------------------------------- Current _ext4_show_options() do not distinguish MOPT_2 flag, so it mixed extend sbi->s_mount_opt2 options with sbi->s_mount_opt, it could lead to show incorrect options, e.g. show fc_debug_force if we mount with errors=continue mode and miss it if we set. $ mkfs.ext4 /dev/pmem0 $ mount -o errors=remount-ro /dev/pmem0 /mnt $ cat /proc/fs/ext4/pmem0/options | grep fc_debug_force #empty $ mount -o remount,errors=continue /mnt $ cat /proc/fs/ext4/pmem0/options | grep fc_debug_force fc_debug_force $ mount -o remount,errors=remount-ro,fc_debug_force /mnt $ cat /proc/fs/ext4/pmem0/options | grep fc_debug_force #empty Fixes: 995a3ed67fc8 ("ext4: add fast_commit feature and handling for extended mount options") Signed-off-by: Zhang Yi <yi.zhang(a)huawei.com> Conflict: fs/ext4/super.c Reviewed-by: Zhihao Cheng <chengzhihao1(a)huawei.com> Reviewed-by: Zhang Xiaoxu <zhangxiaoxu5(a)huawei.com> Signed-off-by: Jialin Zhang <zhangjialin11(a)huawei.com> --- fs/ext4/ext4.h | 1 + fs/ext4/super.c | 28 +++++++++++++++++++++------- 2 files changed, 22 insertions(+), 7 deletions(-) diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 8245b94d8fc6..f1d36671bc2b 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -1462,6 +1462,7 @@ struct ext4_sb_info { unsigned int s_mount_opt2; unsigned long s_mount_flags; unsigned int s_def_mount_opt; + unsigned int s_def_mount_opt2; ext4_fsblk_t s_sb_block; atomic64_t s_resv_clusters; kuid_t s_resuid; diff --git a/fs/ext4/super.c b/fs/ext4/super.c index c94ea845ea57..4fd680507948 100644 --- a/fs/ext4/super.c +++ b/fs/ext4/super.c @@ -2586,7 +2586,7 @@ static int _ext4_show_options(struct seq_file *seq, struct super_block *sb, { struct ext4_sb_info *sbi = EXT4_SB(sb); struct ext4_super_block *es = sbi->s_es; - int def_errors, def_mount_opt = sbi->s_def_mount_opt; + int def_errors; const struct mount_opts *m; char sep = nodefs ? '\n' : ','; @@ -2598,15 +2598,28 @@ static int _ext4_show_options(struct seq_file *seq, struct super_block *sb, for (m = ext4_mount_opts; m->token != Opt_err; m++) { int want_set = m->flags & MOPT_SET; + int opt_2 = m->flags & MOPT_2; + unsigned int mount_opt, def_mount_opt; + if (((m->flags & (MOPT_SET|MOPT_CLEAR)) == 0) || (m->flags & MOPT_CLEAR_ERR) || m->flags & MOPT_SKIP) continue; - if (!nodefs && !(m->mount_opt & (sbi->s_mount_opt ^ def_mount_opt))) - continue; /* skip if same as the default */ + + if (opt_2) { + mount_opt = sbi->s_mount_opt2; + def_mount_opt = sbi->s_def_mount_opt2; + } else { + mount_opt = sbi->s_mount_opt; + def_mount_opt = sbi->s_def_mount_opt; + } + /* skip if same as the default */ + if (!nodefs && !(m->mount_opt & (mount_opt ^ def_mount_opt))) + continue; + /* select Opt_noFoo vs Opt_Foo */ if ((want_set && - (sbi->s_mount_opt & m->mount_opt) != m->mount_opt) || - (!want_set && (sbi->s_mount_opt & m->mount_opt))) - continue; /* select Opt_noFoo vs Opt_Foo */ + (mount_opt & m->mount_opt) != m->mount_opt) || + (!want_set && (mount_opt & m->mount_opt))) + continue; SEQ_OPTS_PRINT("%s", token2str(m->token)); } @@ -2636,7 +2649,7 @@ static int _ext4_show_options(struct seq_file *seq, struct super_block *sb, if (nodefs || sbi->s_stripe) SEQ_OPTS_PRINT("stripe=%lu", sbi->s_stripe); if (nodefs || EXT4_MOUNT_DATA_FLAGS & - (sbi->s_mount_opt ^ def_mount_opt)) { + (sbi->s_mount_opt ^ sbi->s_def_mount_opt)) { if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA) SEQ_OPTS_PUTS("data=journal"); else if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_ORDERED_DATA) @@ -4341,6 +4354,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent) kfree(s_mount_opts); } sbi->s_def_mount_opt = sbi->s_mount_opt; + sbi->s_def_mount_opt2 = sbi->s_mount_opt2; if (!parse_options((char *) data, sb, &journal_devnum, &journal_ioprio, 0)) goto failed_mount; -- 2.25.1

1 12

[RFC PATCH openEuler-1.0-LTS v2] sched: optimise the way to get util
by Wang ShaoBo 15 Mar '23

15 Mar '23

From: tanghui <tanghui20(a)huawei.com> optimise the way to get util. Signed-off-by: tanghui <tanghui20(a)huawei.com> Signed-off-by: Wang ShaoBo <bobo.shaobowang(a)huawei.com> v2: refresh low_pct change way through sysctl. --- fs/proc/stat.c | 4 ++ include/linux/sched/cputime.h | 3 ++ include/linux/sched/sysctl.h | 2 + kernel/sched/fair.c | 83 +++++++++++++++++++++++++++++++++++ kernel/sched/sched.h | 1 + kernel/sysctl.c | 9 ++++ 6 files changed, 102 insertions(+) diff --git a/fs/proc/stat.c b/fs/proc/stat.c index 7e832b24847dd..3fe60a77b0b4d 100644 --- a/fs/proc/stat.c +++ b/fs/proc/stat.c @@ -63,7 +63,11 @@ u64 get_idle_time(int cpu) return idle; } +#ifdef CONFIG_QOS_SCHED_DYNAMIC_AFFINITY +u64 get_iowait_time(int cpu) +#else static u64 get_iowait_time(int cpu) +#endif { u64 iowait, iowait_usecs = -1ULL; diff --git a/include/linux/sched/cputime.h b/include/linux/sched/cputime.h index 6b1793606fc95..4a092e006f5b2 100644 --- a/include/linux/sched/cputime.h +++ b/include/linux/sched/cputime.h @@ -189,6 +189,9 @@ task_sched_runtime(struct task_struct *task); extern int use_sched_idle_time; extern int sched_idle_time_adjust(int cpu, u64 *utime, u64 *stime); extern unsigned long long sched_get_idle_time(int cpu); +#ifdef CONFIG_QOS_SCHED_DYNAMIC_AFFINITY +extern u64 get_iowait_time(int cpu); +#endif #ifdef CONFIG_PROC_FS extern u64 get_idle_time(int cpu); diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h index 04eb5b127867b..8223a1fce176c 100644 --- a/include/linux/sched/sysctl.h +++ b/include/linux/sched/sysctl.h @@ -31,6 +31,8 @@ extern unsigned int sysctl_sched_latency; extern unsigned int sysctl_sched_min_granularity; extern unsigned int sysctl_sched_wakeup_granularity; extern unsigned int sysctl_sched_child_runs_first; +extern int sysctl_sched_util_update_interval; +extern unsigned long sysctl_sched_util_update_interval_max; #ifdef CONFIG_QOS_SCHED_DYNAMIC_AFFINITY extern int sysctl_sched_util_low_pct; diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index ad6a7923c9edb..af55a26d11fcb 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -6682,6 +6682,73 @@ static int wake_cap(struct task_struct *p, int cpu, int prev_cpu) */ int sysctl_sched_util_low_pct = 85; +struct cpu_timeinfo { + u64 systime; + u64 idletime; + unsigned long next_update; + int vutil; +}; + +/* + * The time interval to update CPU utilization + * (default 1ms, max 10min) + */ +int sysctl_sched_util_update_interval = 1; +unsigned long sysctl_sched_util_update_interval_max = 600000; + +static DEFINE_PER_CPU(struct cpu_timeinfo, qos_cputime); + +static inline u64 cpu_systime(int cpu) +{ + u64 user, nice, system, idle, iowait, irq, softirq, steal; + + user = kcpustat_cpu(cpu).cpustat[CPUTIME_USER]; + system = kcpustat_cpu(cpu).cpustat[CPUTIME_SYSTEM]; + iowait = get_iowait_time(cpu); + irq = kcpustat_cpu(cpu).cpustat[CPUTIME_IRQ]; + softirq = kcpustat_cpu(cpu).cpustat[CPUTIME_SOFTIRQ]; + nice = kcpustat_cpu(cpu).cpustat[CPUTIME_NICE]; + steal = kcpustat_cpu(cpu).cpustat[CPUTIME_STEAL]; + idle = get_idle_time(cpu); + + return user + system + iowait + irq + softirq + nice + idle + steal; +} + +static inline u64 cpu_idletime(int cpu) +{ + return get_idle_time(cpu) + get_iowait_time(cpu); +} + +static inline void update_cpu_vutil(void) +{ + struct cpu_timeinfo *cputime = per_cpu_ptr(&qos_cputime, smp_processor_id()); + u64 delta_systime, delta_idle, systime, idletime; + int cpu = smp_processor_id(); + unsigned long interval; + + if (time_after(jiffies, cputime->next_update)) { + interval = msecs_to_jiffies(sysctl_sched_util_update_interval); + cputime->next_update = jiffies + interval; + systime = cpu_systime(cpu); + idletime = cpu_idletime(cpu); + delta_systime = systime - cputime->systime; + delta_idle = idletime - cputime->idletime; + if (!delta_systime) + return; + + cputime->systime = systime; + cputime->idletime = idletime; + cputime->vutil = (delta_systime - delta_idle) * 100 / delta_systime; + } +} + +static inline int cpu_vutil_of(int cpu) +{ + struct cpu_timeinfo *cputime = per_cpu_ptr(&qos_cputime, cpu); + + return cputime->vutil; +} + static inline bool prefer_cpus_valid(struct task_struct *p) { return p->prefer_cpus && @@ -6741,17 +6808,29 @@ static void set_task_select_cpus(struct task_struct *p, int *idlest_cpu, return; } +#if 0 util_avg_sum += tg->se[cpu]->avg.util_avg; tg_capacity += capacity_of(cpu); +#endif + util_avg_sum += cpu_vutil_of(cpu); } rcu_read_unlock(); +#if 0 if (tg_capacity > cpumask_weight(p->prefer_cpus) && util_avg_sum * 100 <= tg_capacity * sysctl_sched_util_low_pct) { p->select_cpus = p->prefer_cpus; if (sd_flag & SD_BALANCE_WAKE) schedstat_inc(p->se.dyn_affi_stats->nr_wakeups_preferred_cpus); } +#endif + + if (util_avg_sum < sysctl_sched_util_low_pct * + cpumask_weight(p->prefer_cpus)) { + p->select_cpus = p->prefer_cpus; + if (sd_flag & SD_BALANCE_WAKE) + schedstat_inc(p->se.dyn_affi_stats->nr_wakeups_preferred_cpus); + } } #endif @@ -10610,6 +10689,10 @@ static void task_tick_fair(struct rq *rq, struct task_struct *curr, int queued) if (static_branch_unlikely(&sched_numa_balancing)) task_tick_numa(rq, curr); + +#ifdef CONFIG_QOS_SCHED_DYNAMIC_AFFINITY + update_cpu_vutil(); +#endif } /* diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index ae30681530938..045fbb3871bbe 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -2354,3 +2354,4 @@ static inline void membarrier_switch_mm(struct rq *rq, { } #endif + diff --git a/kernel/sysctl.c b/kernel/sysctl.c index ad62ea156afd9..685f9881b8e23 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -352,6 +352,15 @@ static struct ctl_table kern_table[] = { .mode = 0644, .proc_handler = proc_dointvec, }, + { + .procname = "sched_util_update_interval_ms", + .data = &sysctl_sched_util_update_interval, + .maxlen = sizeof(sysctl_sched_util_update_interval), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &one, + .extra2 = &sysctl_sched_util_update_interval_max, + }, #ifdef CONFIG_SCHED_DEBUG { .procname = "sched_min_granularity_ns", -- 2.25.1

1 0

[PATCH] sched: optimise the way to get util
by Wang ShaoBo 15 Mar '23

15 Mar '23

From: tanghui <tanghui20(a)huawei.com> sched: optimise the way to get util, which only canbe used when CONFIG_QOS_SCHED_DYNAMIC_AFFINITY is set. Signed-off-by: tanghui <tanghui20(a)huawei.com> --- fs/proc/stat.c | 4 ++ include/linux/sched/cputime.h | 3 ++ include/linux/sched/sysctl.h | 2 + kernel/sched/fair.c | 97 ++++++++++++++++++++++++++++++----- kernel/sched/sched.h | 1 + kernel/sysctl.c | 9 ++++ 6 files changed, 104 insertions(+), 12 deletions(-) diff --git a/fs/proc/stat.c b/fs/proc/stat.c index c83a10e895f4..2eaba2b78f47 100644 --- a/fs/proc/stat.c +++ b/fs/proc/stat.c @@ -63,7 +63,11 @@ u64 get_idle_time(int cpu) return idle; } +#ifdef CONFIG_QOS_SCHED_DYNAMIC_AFFINITY +u64 get_iowait_time(int cpu) +#else static u64 get_iowait_time(int cpu) +#endif { u64 iowait, iowait_usecs = -1ULL; diff --git a/include/linux/sched/cputime.h b/include/linux/sched/cputime.h index 1ebbeec02051..f6244d48f357 100644 --- a/include/linux/sched/cputime.h +++ b/include/linux/sched/cputime.h @@ -190,5 +190,8 @@ extern int use_sched_idle_time; extern int sched_idle_time_adjust(int cpu, u64 *utime, u64 *stime); extern unsigned long long sched_get_idle_time(int cpu); extern u64 get_idle_time(int cpu); +#ifdef CONFIG_QOS_SCHED_DYNAMIC_AFFINITY +extern u64 get_iowait_time(int cpu); +#endif #endif /* _LINUX_SCHED_CPUTIME_H */ diff --git a/include/linux/sched/sysctl.h b/include/linux/sched/sysctl.h index f5031a607df8..386ef53017ca 100644 --- a/include/linux/sched/sysctl.h +++ b/include/linux/sched/sysctl.h @@ -28,6 +28,8 @@ extern unsigned int sysctl_sched_child_runs_first; extern int sysctl_sched_util_low_pct; extern int sysctl_sched_util_higher_pct; extern int sysctl_sched_load_higher_pct; +extern int sysctl_sched_util_update_interval; +extern unsigned long sysctl_sched_util_update_interval_max; #endif enum sched_tunable_scaling { diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index 5344a68a463e..3217e3998fdf 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -6458,6 +6458,15 @@ static int wake_cap(struct task_struct *p, int cpu, int prev_cpu) } #ifdef CONFIG_QOS_SCHED_DYNAMIC_AFFINITY +#define UTIL_PCT_HIGH 85 + +struct cpu_timeinfo { + u64 systime; + u64 idletime; + unsigned long next_update; + int vutil; +}; + /* * Light load threshold for CPU: just use cpu Utilization to measure * @@ -6484,15 +6493,75 @@ int sysctl_sched_util_higher_pct = 100; */ int sysctl_sched_load_higher_pct = 10; +/* + * The time interval to update CPU utilization + * (default 1ms, max 10min) + */ +int sysctl_sched_util_update_interval = 1; +unsigned long sysctl_sched_util_update_interval_max = 600000; + +static DEFINE_PER_CPU(struct cpu_timeinfo, qos_cputime); + +static inline u64 cpu_systime(int cpu) +{ + u64 user, nice, system, idle, iowait, irq, softirq, steal; + + user = kcpustat_cpu(cpu).cpustat[CPUTIME_USER]; + system = kcpustat_cpu(cpu).cpustat[CPUTIME_SYSTEM]; + iowait = get_iowait_time(cpu); + irq = kcpustat_cpu(cpu).cpustat[CPUTIME_IRQ]; + softirq = kcpustat_cpu(cpu).cpustat[CPUTIME_SOFTIRQ]; + nice = kcpustat_cpu(cpu).cpustat[CPUTIME_NICE]; + steal = kcpustat_cpu(cpu).cpustat[CPUTIME_STEAL]; + idle = get_idle_time(cpu); + + return user + system + iowait + irq + softirq + nice + idle + steal; +} + +static inline u64 cpu_idletime(int cpu) +{ + return get_idle_time(cpu) + get_iowait_time(cpu); +} + +static inline void update_cpu_vutil(void) +{ + struct cpu_timeinfo *cputime = per_cpu_ptr(&qos_cputime, smp_processor_id()); + u64 delta_systime, delta_idle, systime, idletime; + int cpu = smp_processor_id(); + unsigned long interval; + + if (time_after(jiffies, cputime->next_update)) { + interval = msecs_to_jiffies(sysctl_sched_util_update_interval); + cputime->next_update = jiffies + interval; + systime = cpu_systime(cpu); + idletime = cpu_idletime(cpu); + delta_systime = systime - cputime->systime; + delta_idle = idletime - cputime->idletime; + if (!delta_systime) + return; + + cputime->systime = systime; + cputime->idletime = idletime; + cputime->vutil = (delta_systime - delta_idle) * 100 / delta_systime; + } +} + +static inline int cpu_vutil_of(int cpu) +{ + struct cpu_timeinfo *cputime = per_cpu_ptr(&qos_cputime, cpu); + + return cputime->vutil; +} + static inline bool prefer_cpu_util_low(int cpu) { unsigned long capacity = capacity_of(cpu); - unsigned long util = cpu_util(cpu); + unsigned long util_pct = cpu_vutil_of(cpu); - if (util >= capacity || capacity <= 1) + if (util_pct >= 100 || capacity <= 1) return sysctl_sched_util_low_pct == 100; - return util * 100 <= capacity * sysctl_sched_util_low_pct; + return util_pct <= sysctl_sched_util_low_pct; } /* @@ -6504,8 +6573,8 @@ static inline int compare_cpu_util(int preferred_cpu, int external_cpu) { unsigned long capacity_cpux = capacity_of(preferred_cpu); unsigned long capacity_cpuy = capacity_of(external_cpu); - unsigned long cpu_util_x = cpu_util(preferred_cpu); - unsigned long cpu_util_y = cpu_util(external_cpu); + unsigned long cpu_util_x = cpu_vutil_of(preferred_cpu); + unsigned long cpu_util_y = cpu_vutil_of(external_cpu); int ratio; /* @@ -6519,7 +6588,7 @@ static inline int compare_cpu_util(int preferred_cpu, int external_cpu) if (capacity_cpux <= 1) return 1; - if (cpu_util_x >= capacity_cpux && available_idle_cpu(external_cpu)) + if (cpu_util_x >= UTIL_PCT_HIGH && available_idle_cpu(external_cpu)) return 1; if (!cpu_util_x) @@ -6529,12 +6598,12 @@ static inline int compare_cpu_util(int preferred_cpu, int external_cpu) * The lower the CPU utilization, the larger the ratio of * CPU utilization gap. */ - ratio = cpu_util_x >= capacity_cpux ? 1 : capacity_cpux / cpu_util_x; + ratio = cpu_util_x >= 100 ? 0 : 100 / cpu_util_x; if (ratio > 10) ratio = 10; - return (sysctl_sched_util_higher_pct * ratio + 100) * cpu_util_y * - capacity_cpux < 100 * cpu_util_x * capacity_cpuy; + return (sysctl_sched_util_higher_pct * ratio + 100) * + cpu_util_y * capacity_cpux < 100 * cpu_util_x * capacity_cpuy; } static inline bool prefer_cpus_valid(struct task_struct *p) @@ -6549,7 +6618,7 @@ static inline bool prefer_cpus_valid(struct task_struct *p) * @p: the task whose available cpu range will to set * @idlest_cpu: the cpu which is the idlest in prefer cpus * - * x: the cpu of min util_avg from preferred set + * x: the cpu of min util from preferred set * y: the cpu from allowed set but exclude preferred set * * If x's utilization is low, select preferred cpu range for task @@ -6578,7 +6647,7 @@ static void set_task_select_cpus(struct task_struct *p, int *idlest_cpu, goto cpus_allowed; cpu = cpumask_first(p->se.prefer_cpus); - min_util = cpu_util(cpu); + min_util = cpu_vutil_of(cpu); for_each_cpu(i, p->se.prefer_cpus) { if (prefer_cpu_util_low(i) || available_idle_cpu(i)) { cpu = i; @@ -6589,7 +6658,7 @@ static void set_task_select_cpus(struct task_struct *p, int *idlest_cpu, if (capacity_of(i) <= 1) continue; - c_util = cpu_util(i); + c_util = cpu_vutil_of(i); if (min_util * capacity_of(i) > c_util * capacity_of(cpu)) { min_util = c_util; cpu = i; @@ -10278,6 +10347,10 @@ static void task_tick_fair(struct rq *rq, struct task_struct *curr, int queued) if (static_branch_unlikely(&sched_numa_balancing)) task_tick_numa(rq, curr); + +#ifdef CONFIG_QOS_SCHED_DYNAMIC_AFFINITY + update_cpu_vutil(); +#endif } /* diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 55216a03d327..4de9c966da01 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -2348,3 +2348,4 @@ static inline void membarrier_switch_mm(struct rq *rq, { } #endif + diff --git a/kernel/sysctl.c b/kernel/sysctl.c index b309aa206697..d52e003f3f56 100644 --- a/kernel/sysctl.c +++ b/kernel/sysctl.c @@ -1274,6 +1274,15 @@ static struct ctl_table kern_table[] = { .extra1 = &zero, .extra2 = &one_hundred, }, + { + .procname = "sched_util_update_interval_ms", + .data = &sysctl_sched_util_update_interval, + .maxlen = sizeof(sysctl_sched_util_update_interval), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &one, + .extra2 = &sysctl_sched_util_update_interval_max, + }, #endif #endif { } -- 2.23.0

1 0

[PATCH openEuler-1.0-LTS 1/2] scsi: fix use-after-free problem in scsi_remove_target
by Yongqiang Liu 13 Mar '23

13 Mar '23

From: Zhong Jinghua <zhongjinghua(a)huawei.com> hulk inclusion category: bugfix bugzilla: 188355, https://gitee.com/openeuler/kernel/issues/I6E4JF CVE: NA ---------------------------------------- A use-after-free problem like below: BUG: KASAN: use-after-free in scsi_target_reap+0x6c/0x70 Workqueue: scsi_wq_1 __iscsi_unbind_session [scsi_transport_iscsi] Call trace: dump_backtrace+0x0/0x320 show_stack+0x24/0x30 dump_stack+0xdc/0x128 print_address_description+0x68/0x278 kasan_report+0x1e4/0x308 __asan_report_load4_noabort+0x30/0x40 scsi_target_reap+0x6c/0x70 scsi_remove_target+0x430/0x640 __iscsi_unbind_session+0x164/0x268 [scsi_transport_iscsi] process_one_work+0x67c/0x1350 worker_thread+0x370/0xf90 kthread+0x2a4/0x320 ret_from_fork+0x10/0x18 The problem is caused by a concurrency scenario: T0: delete target // echo 1 > /sys/devices/platform/host1/session1/target1:0:0/1:0:0:1/delete T1: logout // iscsiadm -m node --logout T0 T1 sdev_store_delete scsi_remove_device device_remove_file __scsi_remove_device __iscsi_unbind_session scsi_remove_target spin_lock_irqsave list_for_each_entry scsi_target_reap // starget->reap_ref 1 -> 0 kref_get(&starget->reap_ref); // warn use-after-free. spin_unlock_irqrestore scsi_target_reap_ref_release scsi_target_destroy ... // delete starget scsi_target_reap // UAF When T0 reduces the reference count to 0, but has not been released, T1 can still enter list_for_each_entry, and then kref_get reports UAF. Fix it by using kref_get_unless_zero() to check for a reference count of 0. Signed-off-by: Zhong Jinghua <zhongjinghua(a)huawei.com> Reviewed-by: Hou Tao <houtao1(a)huawei.com> Signed-off-by: Yongqiang Liu <liuyongqiang13(a)huawei.com> --- drivers/scsi/scsi_sysfs.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/drivers/scsi/scsi_sysfs.c b/drivers/scsi/scsi_sysfs.c index 4030e1fa57e5..453f5a6fb96b 100644 --- a/drivers/scsi/scsi_sysfs.c +++ b/drivers/scsi/scsi_sysfs.c @@ -1500,7 +1500,16 @@ void scsi_remove_target(struct device *dev) starget->state == STARGET_CREATED_REMOVE) continue; if (starget->dev.parent == dev || &starget->dev == dev) { - kref_get(&starget->reap_ref); + /* + * If the reference count is already zero, skip + * this target. Calling kref_get_unless_zero() if + * the reference count is zero is safe because + * scsi_target_destroy() will wait until the host + * lock has been released before freeing starget. + */ + if (!kref_get_unless_zero(&starget->reap_ref)) + continue; + if (starget->state == STARGET_CREATED) starget->state = STARGET_CREATED_REMOVE; else -- 2.25.1

1 1

[OLK-5.10 v1] RDMA/hns: Support congestion control algorithm parameter configuration
by Chengchang Tang 13 Mar '23

13 Mar '23

driver inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I6J5O7 --------------------------------------------------------------- hns roce support 4 congestion control algorithms. Each algorihm involves multiple parameters. This patch add port sysfs directory for each algorithm, which allows users to modify the parameters of these algorithms. Signed-off-by: Chengchang Tang <tangchengchang(a)huawei.com> Reviewed-by: Yangyang Li <liyangyang20(a)huawei.com> --- drivers/infiniband/hw/hns/Makefile | 2 +- drivers/infiniband/hw/hns/hns_roce_device.h | 42 +- drivers/infiniband/hw/hns/hns_roce_hw_v2.c | 77 ++++ drivers/infiniband/hw/hns/hns_roce_hw_v2.h | 132 ++++++ drivers/infiniband/hw/hns/hns_roce_main.c | 2 + drivers/infiniband/hw/hns/hns_roce_sysfs.c | 445 ++++++++++++++++++++ 6 files changed, 695 insertions(+), 5 deletions(-) create mode 100644 drivers/infiniband/hw/hns/hns_roce_sysfs.c diff --git a/drivers/infiniband/hw/hns/Makefile b/drivers/infiniband/hw/hns/Makefile index 77d8e41ffe7b..09f95fedd15d 100644 --- a/drivers/infiniband/hw/hns/Makefile +++ b/drivers/infiniband/hw/hns/Makefile @@ -10,7 +10,7 @@ ccflags-y += -I $(srctree)/drivers/net/ethernet/hisilicon/hns3/hns3_common hns-roce-objs := hns_roce_main.o hns_roce_cmd.o hns_roce_pd.o \ hns_roce_ah.o hns_roce_hem.o hns_roce_mr.o hns_roce_qp.o \ hns_roce_cq.o hns_roce_alloc.o hns_roce_db.o hns_roce_srq.o hns_roce_restrack.o \ - hns_roce_bond.o hns_roce_dca.o hns_roce_debugfs.o + hns_roce_bond.o hns_roce_dca.o hns_roce_debugfs.o hns_roce_sysfs.o ifdef CONFIG_INFINIBAND_HNS_HIP08 hns-roce-hw-v2-objs := hns_roce_hw_v2.o $(hns-roce-objs) diff --git a/drivers/infiniband/hw/hns/hns_roce_device.h b/drivers/infiniband/hw/hns/hns_roce_device.h index 869d952b32b2..9d5580040e6b 100644 --- a/drivers/infiniband/hw/hns/hns_roce_device.h +++ b/drivers/infiniband/hw/hns/hns_roce_device.h @@ -767,11 +767,19 @@ struct hns_roce_eq_table { struct hns_roce_eq *eq; }; +enum hns_roce_scc_algo { + HNS_ROCE_SCC_ALGO_DCQCN = 0, + HNS_ROCE_SCC_ALGO_LDCP, + HNS_ROCE_SCC_ALGO_HC3, + HNS_ROCE_SCC_ALGO_DIP, + HNS_ROCE_SCC_ALGO_TOTAL, +}; + enum cong_type { - CONG_TYPE_DCQCN, - CONG_TYPE_LDCP, - CONG_TYPE_HC3, - CONG_TYPE_DIP, + CONG_TYPE_DCQCN = 1 << HNS_ROCE_SCC_ALGO_DCQCN, + CONG_TYPE_LDCP = 1 << HNS_ROCE_SCC_ALGO_LDCP, + CONG_TYPE_HC3 = 1 << HNS_ROCE_SCC_ALGO_HC3, + CONG_TYPE_DIP = 1 << HNS_ROCE_SCC_ALGO_DIP, }; struct hns_roce_caps { @@ -1016,6 +1024,28 @@ struct hns_roce_hw { int (*bond_init)(struct hns_roce_dev *hr_dev); bool (*bond_is_active)(struct hns_roce_dev *hr_dev); struct net_device *(*get_bond_netdev)(struct hns_roce_dev *hr_dev); + int (*config_scc_param)(struct hns_roce_dev *hr_dev, u8 port_num, + enum hns_roce_scc_algo algo); + int (*query_scc_param)(struct hns_roce_dev *hr_dev, u8 port_num, + enum hns_roce_scc_algo alog); +}; + +#define HNS_ROCE_SCC_PARAM_SIZE 4 +struct hns_roce_scc_param { + __le32 param[HNS_ROCE_SCC_PARAM_SIZE]; + u32 lifespan; + unsigned long timestamp; + enum hns_roce_scc_algo algo_type; + struct delayed_work scc_cfg_dwork; + struct hns_roce_dev *hr_dev; + u8 port_num; +}; + +struct hns_roce_port { + struct hns_roce_dev *hr_dev; + u8 port_num; + struct kobject kobj; + struct hns_roce_scc_param *scc_param; }; struct hns_roce_dev { @@ -1094,6 +1124,7 @@ struct hns_roce_dev { struct delayed_work bond_work; struct hns_roce_bond_group *bond_grp; struct netdev_lag_lower_state_info slave_state; + struct hns_roce_port port_data[HNS_ROCE_MAX_PORTS]; atomic64_t *dfx_cnt; }; @@ -1379,4 +1410,7 @@ struct hns_user_mmap_entry * hns_roce_user_mmap_entry_insert(struct ib_ucontext *ucontext, u64 address, size_t length, enum hns_roce_mmap_type mmap_type); +int hns_roce_create_port_files(struct ib_device *ibdev, u8 port_num, + struct kobject *kobj); +void hns_roce_unregister_sysfs(struct hns_roce_dev *hr_dev); #endif /* _HNS_ROCE_DEVICE_H */ diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c index a76a57c7e36a..c9826a010f38 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c +++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c @@ -7146,6 +7146,81 @@ static void hns_roce_v2_cleanup_eq_table(struct hns_roce_dev *hr_dev) kfree(eq_table->eq); } +static enum hns_roce_opcode_type scc_opcode[] = { + HNS_ROCE_OPC_CFG_DCQCN_PARAM, + HNS_ROCE_OPC_CFG_LDCP_PARAM, + HNS_ROCE_OPC_CFG_HC3_PARAM, + HNS_ROCE_OPC_CFG_DIP_PARAM, +}; + +static int hns_roce_v2_config_scc_param(struct hns_roce_dev *hr_dev, + u8 port_num, + enum hns_roce_scc_algo algo) +{ + struct hns_roce_scc_param *scc_param; + struct hns_roce_cmq_desc desc; + struct hns_roce_port *pdata; + int ret; + + if (port_num > hr_dev->caps.num_ports) { + ibdev_err_ratelimited(&hr_dev->ib_dev, + "invalid port num %u.\n", port_num); + return -ENODEV; + } + + if (algo >= HNS_ROCE_SCC_ALGO_TOTAL) { + ibdev_err_ratelimited(&hr_dev->ib_dev, "invalid SCC algo.\n"); + return -EINVAL; + } + + hns_roce_cmq_setup_basic_desc(&desc, scc_opcode[algo], false); + pdata = &hr_dev->port_data[port_num - 1]; + scc_param = &pdata->scc_param[algo]; + memcpy(&desc.data, scc_param, sizeof(scc_param->param)); + + ret = hns_roce_cmq_send(hr_dev, &desc, 1); + if (ret) + ibdev_err_ratelimited(&hr_dev->ib_dev, + "failed to configure scc param, opcode: 0x%x, ret = %d.\n", + le16_to_cpu(desc.opcode), ret); + return ret; +} + +static int hns_roce_v2_query_scc_param(struct hns_roce_dev *hr_dev, + u8 port_num, enum hns_roce_scc_algo algo) +{ + struct hns_roce_scc_param *scc_param; + struct hns_roce_cmq_desc desc; + struct hns_roce_port *pdata; + int ret; + + if (port_num > hr_dev->caps.num_ports) { + ibdev_err_ratelimited(&hr_dev->ib_dev, + "invalid port num %u.\n", port_num); + return -ENODEV; + } + + if (algo >= HNS_ROCE_SCC_ALGO_TOTAL) { + ibdev_err_ratelimited(&hr_dev->ib_dev, "invalid SCC algo.\n"); + return -EINVAL; + } + + hns_roce_cmq_setup_basic_desc(&desc, scc_opcode[algo], true); + ret = hns_roce_cmq_send(hr_dev, &desc, 1); + if (ret) { + ibdev_err_ratelimited(&hr_dev->ib_dev, + "failed to query scc param, opcode: 0x%x, ret = %d.\n", + le16_to_cpu(desc.opcode), ret); + return ret; + } + + pdata = &hr_dev->port_data[port_num - 1]; + scc_param = &pdata->scc_param[algo]; + memcpy(scc_param, &desc.data, sizeof(scc_param->param)); + + return 0; +} + static const struct ib_device_ops hns_roce_v2_dev_ops = { .destroy_qp = hns_roce_v2_destroy_qp, .modify_cq = hns_roce_v2_modify_cq, @@ -7198,6 +7273,8 @@ static const struct hns_roce_hw hns_roce_hw_v2 = { .bond_is_active = hns_roce_bond_is_active, .get_bond_netdev = hns_roce_get_bond_netdev, .query_hw_counter = hns_roce_hw_v2_query_counter, + .config_scc_param = hns_roce_v2_config_scc_param, + .query_scc_param = hns_roce_v2_query_scc_param, }; static const struct pci_device_id hns_roce_hw_v2_pci_tbl[] = { diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.h b/drivers/infiniband/hw/hns/hns_roce_hw_v2.h index 7d5c304a8342..90401577865e 100644 --- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.h +++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.h @@ -227,6 +227,10 @@ enum { enum hns_roce_opcode_type { HNS_QUERY_FW_VER = 0x0001, HNS_QUERY_MAC_TYPE = 0x0389, + HNS_ROCE_OPC_CFG_DCQCN_PARAM = 0x1A80, + HNS_ROCE_OPC_CFG_LDCP_PARAM = 0x1A81, + HNS_ROCE_OPC_CFG_HC3_PARAM = 0x1A82, + HNS_ROCE_OPC_CFG_DIP_PARAM = 0x1A83, HNS_ROCE_OPC_QUERY_HW_VER = 0x8000, HNS_ROCE_OPC_CFG_GLOBAL_PARAM = 0x8001, HNS_ROCE_OPC_ALLOC_PF_RES = 0x8004, @@ -1468,6 +1472,134 @@ struct hns_roce_wqe_atomic_seg { __le64 cmp_data; }; +#define HNS_ROCE_DCQCN_AI_OFS 0 +#define HNS_ROCE_DCQCN_AI_SZ sizeof(u16) +#define HNS_ROCE_DCQCN_AI_MAX ((u16)(~0U)) +#define HNS_ROCE_DCQCN_F_OFS (HNS_ROCE_DCQCN_AI_OFS + HNS_ROCE_DCQCN_AI_SZ) +#define HNS_ROCE_DCQCN_F_SZ sizeof(u8) +#define HNS_ROCE_DCQCN_F_MAX ((u8)(~0U)) +#define HNS_ROCE_DCQCN_TKP_OFS (HNS_ROCE_DCQCN_F_OFS + HNS_ROCE_DCQCN_F_SZ) +#define HNS_ROCE_DCQCN_TKP_SZ sizeof(u8) +#define HNS_ROCE_DCQCN_TKP_MAX 15 +#define HNS_ROCE_DCQCN_TMP_OFS (HNS_ROCE_DCQCN_TKP_OFS + HNS_ROCE_DCQCN_TKP_SZ) +#define HNS_ROCE_DCQCN_TMP_SZ sizeof(u16) +#define HNS_ROCE_DCQCN_TMP_MAX 15 +#define HNS_ROCE_DCQCN_ALP_OFS (HNS_ROCE_DCQCN_TMP_OFS + HNS_ROCE_DCQCN_TMP_SZ) +#define HNS_ROCE_DCQCN_ALP_SZ sizeof(u16) +#define HNS_ROCE_DCQCN_ALP_MAX ((u16)(~0U)) +#define HNS_ROCE_DCQCN_MAX_SPEED_OFS (HNS_ROCE_DCQCN_ALP_OFS + \ + HNS_ROCE_DCQCN_ALP_SZ) +#define HNS_ROCE_DCQCN_MAX_SPEED_SZ sizeof(u32) +#define HNS_ROCE_DCQCN_MAX_SPEED_MAX ((u32)(~0U)) +#define HNS_ROCE_DCQCN_G_OFS (HNS_ROCE_DCQCN_MAX_SPEED_OFS + \ + HNS_ROCE_DCQCN_MAX_SPEED_SZ) +#define HNS_ROCE_DCQCN_G_SZ sizeof(u8) +#define HNS_ROCE_DCQCN_G_MAX 15 +#define HNS_ROCE_DCQCN_AL_OFS (HNS_ROCE_DCQCN_G_OFS + HNS_ROCE_DCQCN_G_SZ) +#define HNS_ROCE_DCQCN_AL_SZ sizeof(u8) +#define HNS_ROCE_DCQCN_AL_MAX ((u8)(~0U)) +#define HNS_ROCE_DCQCN_CNP_TIME_OFS (HNS_ROCE_DCQCN_AL_OFS + \ + HNS_ROCE_DCQCN_AL_SZ) +#define HNS_ROCE_DCQCN_CNP_TIME_SZ sizeof(u8) +#define HNS_ROCE_DCQCN_CNP_TIME_MAX ((u8)(~0U)) +#define HNS_ROCE_DCQCN_ASHIFT_OFS (HNS_ROCE_DCQCN_CNP_TIME_OFS + \ + HNS_ROCE_DCQCN_CNP_TIME_SZ) +#define HNS_ROCE_DCQCN_ASHIFT_SZ sizeof(u8) +#define HNS_ROCE_DCQCN_ASHIFT_MAX 15 +#define HNS_ROCE_DCQCN_LIFESPAN_OFS (HNS_ROCE_DCQCN_ASHIFT_OFS + \ + HNS_ROCE_DCQCN_ASHIFT_SZ) +#define HNS_ROCE_DCQCN_LIFESPAN_SZ sizeof(u32) +#define HNS_ROCE_DCQCN_LIFESPAN_MAX 1000 + +#define HNS_ROCE_LDCP_CWD0_OFS 0 +#define HNS_ROCE_LDCP_CWD0_SZ sizeof(u32) +#define HNS_ROCE_LDCP_CWD0_MAX ((u32)(~0U)) +#define HNS_ROCE_LDCP_ALPHA_OFS (HNS_ROCE_LDCP_CWD0_OFS + HNS_ROCE_LDCP_CWD0_SZ) +#define HNS_ROCE_LDCP_ALPHA_SZ sizeof(u8) +#define HNS_ROCE_LDCP_ALPHA_MAX ((u8)(~0U)) +#define HNS_ROCE_LDCP_GAMMA_OFS (HNS_ROCE_LDCP_ALPHA_OFS + \ + HNS_ROCE_LDCP_ALPHA_SZ) +#define HNS_ROCE_LDCP_GAMMA_SZ sizeof(u8) +#define HNS_ROCE_LDCP_GAMMA_MAX ((u8)(~0U)) +#define HNS_ROCE_LDCP_BETA_OFS (HNS_ROCE_LDCP_GAMMA_OFS + \ + HNS_ROCE_LDCP_GAMMA_SZ) +#define HNS_ROCE_LDCP_BETA_SZ sizeof(u8) +#define HNS_ROCE_LDCP_BETA_MAX ((u8)(~0U)) +#define HNS_ROCE_LDCP_ETA_OFS (HNS_ROCE_LDCP_BETA_OFS + HNS_ROCE_LDCP_BETA_SZ) +#define HNS_ROCE_LDCP_ETA_SZ sizeof(u8) +#define HNS_ROCE_LDCP_ETA_MAX ((u8)(~0U)) +#define HNS_ROCE_LDCP_LIFESPAN_OFS (4 * sizeof(u32)) +#define HNS_ROCE_LDCP_LIFESPAN_SZ sizeof(u32) +#define HNS_ROCE_LDCP_LIFESPAN_MAX 1000 + +#define HNS_ROCE_HC3_INITIAL_WINDOW_OFS 0 +#define HNS_ROCE_HC3_INITIAL_WINDOW_SZ sizeof(u32) +#define HNS_ROCE_HC3_INITIAL_WINDOW_MAX ((u32)(~0U)) +#define HNS_ROCE_HC3_BANDWIDTH_OFS (HNS_ROCE_HC3_INITIAL_WINDOW_OFS + \ + HNS_ROCE_HC3_INITIAL_WINDOW_SZ) +#define HNS_ROCE_HC3_BANDWIDTH_SZ sizeof(u32) +#define HNS_ROCE_HC3_BANDWIDTH_MAX ((u32)(~0U)) +#define HNS_ROCE_HC3_QLEN_SHIFT_OFS (HNS_ROCE_HC3_BANDWIDTH_OFS + \ + HNS_ROCE_HC3_BANDWIDTH_SZ) +#define HNS_ROCE_HC3_QLEN_SHIFT_SZ sizeof(u8) +#define HNS_ROCE_HC3_QLEN_SHIFT_MAX ((u8)(~0U)) +#define HNS_ROCE_HC3_PORT_USAGE_SHIFT_OFS (HNS_ROCE_HC3_QLEN_SHIFT_OFS + \ + HNS_ROCE_HC3_QLEN_SHIFT_SZ) +#define HNS_ROCE_HC3_PORT_USAGE_SHIFT_SZ sizeof(u8) +#define HNS_ROCE_HC3_PORT_USAGE_SHIFT_MAX ((u8)(~0U)) +#define HNS_ROCE_HC3_OVER_PERIOD_OFS (HNS_ROCE_HC3_PORT_USAGE_SHIFT_OFS + \ + HNS_ROCE_HC3_PORT_USAGE_SHIFT_SZ) +#define HNS_ROCE_HC3_OVER_PERIOD_SZ sizeof(u8) +#define HNS_ROCE_HC3_OVER_PERIOD_MAX ((u8)(~0U)) +#define HNS_ROCE_HC3_MAX_STAGE_OFS (HNS_ROCE_HC3_OVER_PERIOD_OFS + \ + HNS_ROCE_HC3_OVER_PERIOD_SZ) +#define HNS_ROCE_HC3_MAX_STAGE_SZ sizeof(u8) +#define HNS_ROCE_HC3_MAX_STAGE_MAX ((u8)(~0U)) +#define HNS_ROCE_HC3_GAMMA_SHIFT_OFS (HNS_ROCE_HC3_MAX_STAGE_OFS + \ + HNS_ROCE_HC3_MAX_STAGE_SZ) +#define HNS_ROCE_HC3_GAMMA_SHIFT_SZ sizeof(u8) +#define HNS_ROCE_HC3_GAMMA_SHIFT_MAX 15 +#define HNS_ROCE_HC3_LIFESPAN_OFS (4 * sizeof(u32)) +#define HNS_ROCE_HC3_LIFESPAN_SZ sizeof(u32) +#define HNS_ROCE_HC3_LIFESPAN_MAX 1000 + +#define HNS_ROCE_DIP_AI_OFS 0 +#define HNS_ROCE_DIP_AI_SZ sizeof(u16) +#define HNS_ROCE_DIP_AI_MAX ((u16)(~0U)) +#define HNS_ROCE_DIP_F_OFS (HNS_ROCE_DIP_AI_OFS + HNS_ROCE_DIP_AI_SZ) +#define HNS_ROCE_DIP_F_SZ sizeof(u8) +#define HNS_ROCE_DIP_F_MAX ((u8)(~0U)) +#define HNS_ROCE_DIP_TKP_OFS (HNS_ROCE_DIP_F_OFS + HNS_ROCE_DIP_F_SZ) +#define HNS_ROCE_DIP_TKP_SZ sizeof(u8) +#define HNS_ROCE_DIP_TKP_MAX 15 +#define HNS_ROCE_DIP_TMP_OFS (HNS_ROCE_DIP_TKP_OFS + HNS_ROCE_DIP_TKP_SZ) +#define HNS_ROCE_DIP_TMP_SZ sizeof(u16) +#define HNS_ROCE_DIP_TMP_MAX 15 +#define HNS_ROCE_DIP_ALP_OFS (HNS_ROCE_DIP_TMP_OFS + HNS_ROCE_DIP_TMP_SZ) +#define HNS_ROCE_DIP_ALP_SZ sizeof(u16) +#define HNS_ROCE_DIP_ALP_MAX ((u16)(~0U)) +#define HNS_ROCE_DIP_MAX_SPEED_OFS (HNS_ROCE_DIP_ALP_OFS + HNS_ROCE_DIP_ALP_SZ) +#define HNS_ROCE_DIP_MAX_SPEED_SZ sizeof(u32) +#define HNS_ROCE_DIP_MAX_SPEED_MAX ((u32)(~0U)) +#define HNS_ROCE_DIP_G_OFS (HNS_ROCE_DIP_MAX_SPEED_OFS + \ + HNS_ROCE_DIP_MAX_SPEED_SZ) +#define HNS_ROCE_DIP_G_SZ sizeof(u8) +#define HNS_ROCE_DIP_G_MAX 15 +#define HNS_ROCE_DIP_AL_OFS (HNS_ROCE_DIP_G_OFS + HNS_ROCE_DIP_G_SZ) +#define HNS_ROCE_DIP_AL_SZ sizeof(u8) +#define HNS_ROCE_DIP_AL_MAX ((u8)(~0U)) +#define HNS_ROCE_DIP_CNP_TIME_OFS (HNS_ROCE_DIP_AL_OFS + HNS_ROCE_DIP_AL_SZ) +#define HNS_ROCE_DIP_CNP_TIME_SZ sizeof(u8) +#define HNS_ROCE_DIP_CNP_TIME_MAX ((u8)(~0U)) +#define HNS_ROCE_DIP_ASHIFT_OFS (HNS_ROCE_DIP_CNP_TIME_OFS + \ + HNS_ROCE_DIP_CNP_TIME_SZ) +#define HNS_ROCE_DIP_ASHIFT_SZ sizeof(u8) +#define HNS_ROCE_DIP_ASHIFT_MAX 15 +#define HNS_ROCE_DIP_LIFESPAN_OFS (HNS_ROCE_DIP_ASHIFT_OFS + \ + HNS_ROCE_DIP_ASHIFT_SZ) +#define HNS_ROCE_DIP_LIFESPAN_SZ sizeof(u32) +#define HNS_ROCE_DIP_LIFESPAN_MAX 1000 + struct hns_roce_sccc_clr { __le32 qpn; __le32 rsv[5]; diff --git a/drivers/infiniband/hw/hns/hns_roce_main.c b/drivers/infiniband/hw/hns/hns_roce_main.c index d98825154a82..4d1d2629d8f0 100644 --- a/drivers/infiniband/hw/hns/hns_roce_main.c +++ b/drivers/infiniband/hw/hns/hns_roce_main.c @@ -870,6 +870,7 @@ static const struct ib_device_ops hns_roce_dev_ops = { .reg_user_mr = hns_roce_reg_user_mr, .alloc_hw_stats = hns_roce_alloc_hw_port_stats, .get_hw_stats = hns_roce_get_hw_stats, + .init_port = hns_roce_create_port_files, INIT_RDMA_OBJ_SIZE(ib_ah, hns_roce_ah, ibah), INIT_RDMA_OBJ_SIZE(ib_cq, hns_roce_cq, ib_cq), @@ -1441,6 +1442,7 @@ int hns_roce_init(struct hns_roce_dev *hr_dev) void hns_roce_exit(struct hns_roce_dev *hr_dev) { + hns_roce_unregister_sysfs(hr_dev); hns_roce_unregister_device(hr_dev); hns_roce_unregister_debugfs(hr_dev); diff --git a/drivers/infiniband/hw/hns/hns_roce_sysfs.c b/drivers/infiniband/hw/hns/hns_roce_sysfs.c new file mode 100644 index 000000000000..507cc7147a2e --- /dev/null +++ b/drivers/infiniband/hw/hns/hns_roce_sysfs.c @@ -0,0 +1,445 @@ +// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB +/* + * Copyright (c) 2023 Hisilicon Limited. + */ + +#include "hnae3.h" +#include "hns_roce_device.h" +#include "hns_roce_hw_v2.h" + +struct hns_port_attribute { + struct attribute attr; + ssize_t (*show)(struct hns_roce_port *pdata, + struct hns_port_attribute *attr, char *buf); + ssize_t (*store)(struct hns_roce_port *pdata, + struct hns_port_attribute *attr, const char *buf, + size_t count); +}; + +static void scc_param_config_work(struct work_struct *work) +{ + struct hns_roce_scc_param *scc_param = container_of(work, + struct hns_roce_scc_param, scc_cfg_dwork.work); + struct hns_roce_dev *hr_dev = scc_param->hr_dev; + + hr_dev->hw->config_scc_param(hr_dev, scc_param->port_num, + scc_param->algo_type); +} + +static int alloc_scc_param(struct hns_roce_dev *hr_dev, + struct hns_roce_port *pdata) +{ + struct hns_roce_scc_param *scc_param; + int i; + + scc_param = kcalloc(HNS_ROCE_SCC_ALGO_TOTAL, sizeof(*scc_param), + GFP_KERNEL); + if (!scc_param) + return -ENOMEM; + + for (i = 0; i < HNS_ROCE_SCC_ALGO_TOTAL; i++) { + scc_param[i].algo_type = i; + scc_param[i].timestamp = jiffies; + scc_param[i].hr_dev = hr_dev; + scc_param[i].port_num = pdata->port_num; + INIT_DELAYED_WORK(&scc_param[i].scc_cfg_dwork, + scc_param_config_work); + } + + pdata->scc_param = scc_param; + return 0; +} + +struct hns_port_cc_attr { + struct hns_port_attribute port_attr; + enum hns_roce_scc_algo algo_type; + u32 offset; + u32 size; + u32 max; + u32 min; +}; + +static int scc_attr_check(struct hns_port_cc_attr *scc_attr) +{ + if (WARN_ON(scc_attr->size > sizeof(u32))) + return -EINVAL; + + if (WARN_ON(scc_attr->algo_type >= HNS_ROCE_SCC_ALGO_TOTAL)) + return -EINVAL; + return 0; +} + +static ssize_t scc_attr_show(struct hns_roce_port *pdata, + struct hns_port_attribute *attr, char *buf) +{ + struct hns_port_cc_attr *scc_attr = + container_of(attr, struct hns_port_cc_attr, port_attr); + struct hns_roce_scc_param *scc_param; + unsigned long exp_time; + __le32 val = 0; + int ret; + + ret = scc_attr_check(scc_attr); + if (ret) + return ret; + + scc_param = &pdata->scc_param[scc_attr->algo_type]; + + /* Only HW param need be queried */ + if (scc_attr->offset < offsetof(typeof(*scc_param), lifespan)) { + exp_time = scc_param->timestamp + + msecs_to_jiffies(scc_param->lifespan); + + if (time_is_before_eq_jiffies(exp_time)) { + scc_param->timestamp = jiffies; + pdata->hr_dev->hw->query_scc_param(pdata->hr_dev, + pdata->port_num, scc_attr->algo_type); + } + } + + memcpy(&val, (void *)scc_param + scc_attr->offset, scc_attr->size); + + return sysfs_emit(buf, "%u\n", le32_to_cpu(val)); +} + +static ssize_t scc_attr_store(struct hns_roce_port *pdata, + struct hns_port_attribute *attr, + const char *buf, size_t count) +{ + struct hns_port_cc_attr *scc_attr = + container_of(attr, struct hns_port_cc_attr, port_attr); + struct hns_roce_scc_param *scc_param; + unsigned long lifespan_jiffies; + unsigned long exp_time; + __le32 attr_val; + u32 val; + int ret; + + ret = scc_attr_check(scc_attr); + if (ret) + return ret; + + if (kstrtou32(buf, 0, &val)) + return -EINVAL; + + if (val > scc_attr->max || val < scc_attr->min) + return -EINVAL; + + attr_val = cpu_to_le32(val); + scc_param = &pdata->scc_param[scc_attr->algo_type]; + memcpy((void *)scc_param + scc_attr->offset, &attr_val, + scc_attr->size); + + /* lifespan is only used for driver */ + if (scc_attr->offset >= offsetof(typeof(*scc_param), lifespan)) + return count; + + lifespan_jiffies = msecs_to_jiffies(scc_param->lifespan); + exp_time = scc_param->timestamp + lifespan_jiffies; + + if (time_is_before_eq_jiffies(exp_time)) { + scc_param->timestamp = jiffies; + queue_delayed_work(pdata->hr_dev->irq_workq, + &scc_param->scc_cfg_dwork, lifespan_jiffies); + } + + return count; +} + +static umode_t scc_attr_is_visible(struct kobject *kobj, + struct attribute *attr, int i) +{ + struct hns_port_attribute *port_attr = + container_of(attr, struct hns_port_attribute, attr); + struct hns_port_cc_attr *scc_attr = + container_of(port_attr, struct hns_port_cc_attr, port_attr); + struct hns_roce_port *pdata = + container_of(kobj, struct hns_roce_port, kobj); + struct hns_roce_dev *hr_dev = pdata->hr_dev; + + if (hr_dev->is_vf || + !(hr_dev->caps.flags & HNS_ROCE_CAP_FLAG_QP_FLOW_CTRL)) + return 0; + + if (!(hr_dev->caps.cong_type & (1 << scc_attr->algo_type))) + return 0; + + return 0644; +} + +#define __HNS_SCC_ATTR(_name, _type, _offset, _size, _min, _max) { \ + .port_attr = __ATTR(_name, 0644, scc_attr_show, scc_attr_store), \ + .algo_type = _type, \ + .offset = _offset, \ + .size = _size, \ + .min = _min, \ + .max = _max, \ +} + +#define HNS_PORT_DCQCN_CC_ATTR_RW(_name, NAME) \ + struct hns_port_cc_attr hns_roce_port_attr_dcqcn_##_name = \ + __HNS_SCC_ATTR(_name, HNS_ROCE_SCC_ALGO_DCQCN, \ + HNS_ROCE_DCQCN_##NAME##_OFS, \ + HNS_ROCE_DCQCN_##NAME##_SZ, \ + 0, HNS_ROCE_DCQCN_##NAME##_MAX) + +HNS_PORT_DCQCN_CC_ATTR_RW(ai, AI); +HNS_PORT_DCQCN_CC_ATTR_RW(f, F); +HNS_PORT_DCQCN_CC_ATTR_RW(tkp, TKP); +HNS_PORT_DCQCN_CC_ATTR_RW(tmp, TMP); +HNS_PORT_DCQCN_CC_ATTR_RW(alp, ALP); +HNS_PORT_DCQCN_CC_ATTR_RW(max_speed, MAX_SPEED); +HNS_PORT_DCQCN_CC_ATTR_RW(g, G); +HNS_PORT_DCQCN_CC_ATTR_RW(al, AL); +HNS_PORT_DCQCN_CC_ATTR_RW(cnp_time, CNP_TIME); +HNS_PORT_DCQCN_CC_ATTR_RW(ashift, ASHIFT); +HNS_PORT_DCQCN_CC_ATTR_RW(lifespan, LIFESPAN); + +static struct attribute *dcqcn_param_attrs[] = { + &hns_roce_port_attr_dcqcn_ai.port_attr.attr, + &hns_roce_port_attr_dcqcn_f.port_attr.attr, + &hns_roce_port_attr_dcqcn_tkp.port_attr.attr, + &hns_roce_port_attr_dcqcn_tmp.port_attr.attr, + &hns_roce_port_attr_dcqcn_alp.port_attr.attr, + &hns_roce_port_attr_dcqcn_max_speed.port_attr.attr, + &hns_roce_port_attr_dcqcn_g.port_attr.attr, + &hns_roce_port_attr_dcqcn_al.port_attr.attr, + &hns_roce_port_attr_dcqcn_cnp_time.port_attr.attr, + &hns_roce_port_attr_dcqcn_ashift.port_attr.attr, + &hns_roce_port_attr_dcqcn_lifespan.port_attr.attr, + NULL, +}; + +static const struct attribute_group dcqcn_cc_param_group = { + .name = "dcqcn_cc_param", + .attrs = dcqcn_param_attrs, + .is_visible = scc_attr_is_visible, +}; + +#define HNS_PORT_LDCP_CC_ATTR_RW(_name, NAME) \ + struct hns_port_cc_attr hns_roce_port_attr_ldcp_##_name = \ + __HNS_SCC_ATTR(_name, HNS_ROCE_SCC_ALGO_LDCP, \ + HNS_ROCE_LDCP_##NAME##_OFS, \ + HNS_ROCE_LDCP_##NAME##_SZ, \ + 0, HNS_ROCE_LDCP_##NAME##_MAX) + +HNS_PORT_LDCP_CC_ATTR_RW(cwd0, CWD0); +HNS_PORT_LDCP_CC_ATTR_RW(alpha, ALPHA); +HNS_PORT_LDCP_CC_ATTR_RW(gamma, GAMMA); +HNS_PORT_LDCP_CC_ATTR_RW(beta, BETA); +HNS_PORT_LDCP_CC_ATTR_RW(eta, ETA); +HNS_PORT_LDCP_CC_ATTR_RW(lifespan, LIFESPAN); + +static struct attribute *ldcp_param_attrs[] = { + &hns_roce_port_attr_ldcp_cwd0.port_attr.attr, + &hns_roce_port_attr_ldcp_alpha.port_attr.attr, + &hns_roce_port_attr_ldcp_gamma.port_attr.attr, + &hns_roce_port_attr_ldcp_beta.port_attr.attr, + &hns_roce_port_attr_ldcp_eta.port_attr.attr, + &hns_roce_port_attr_ldcp_lifespan.port_attr.attr, + NULL, +}; + +static const struct attribute_group ldcp_cc_param_group = { + .name = "ldcp_cc_param", + .attrs = ldcp_param_attrs, + .is_visible = scc_attr_is_visible, +}; + +#define HNS_PORT_HC3_CC_ATTR_RW(_name, NAME) \ + struct hns_port_cc_attr hns_roce_port_attr_hc3_##_name = \ + __HNS_SCC_ATTR(_name, HNS_ROCE_SCC_ALGO_HC3, \ + HNS_ROCE_HC3_##NAME##_OFS, \ + HNS_ROCE_HC3_##NAME##_SZ, \ + 0, HNS_ROCE_HC3_##NAME##_MAX) + +HNS_PORT_HC3_CC_ATTR_RW(initial_window, INITIAL_WINDOW); +HNS_PORT_HC3_CC_ATTR_RW(bandwidth, BANDWIDTH); +HNS_PORT_HC3_CC_ATTR_RW(qlen_shift, QLEN_SHIFT); +HNS_PORT_HC3_CC_ATTR_RW(port_usage_shift, PORT_USAGE_SHIFT); +HNS_PORT_HC3_CC_ATTR_RW(over_period, OVER_PERIOD); +HNS_PORT_HC3_CC_ATTR_RW(max_stage, MAX_STAGE); +HNS_PORT_HC3_CC_ATTR_RW(gamma_shift, GAMMA_SHIFT); +HNS_PORT_HC3_CC_ATTR_RW(lifespan, LIFESPAN); + +static struct attribute *hc3_param_attrs[] = { + &hns_roce_port_attr_hc3_initial_window.port_attr.attr, + &hns_roce_port_attr_hc3_bandwidth.port_attr.attr, + &hns_roce_port_attr_hc3_qlen_shift.port_attr.attr, + &hns_roce_port_attr_hc3_port_usage_shift.port_attr.attr, + &hns_roce_port_attr_hc3_over_period.port_attr.attr, + &hns_roce_port_attr_hc3_max_stage.port_attr.attr, + &hns_roce_port_attr_hc3_gamma_shift.port_attr.attr, + &hns_roce_port_attr_hc3_lifespan.port_attr.attr, + NULL, +}; + +static const struct attribute_group hc3_cc_param_group = { + .name = "hc3_cc_param", + .attrs = hc3_param_attrs, + .is_visible = scc_attr_is_visible, +}; + +#define HNS_PORT_DIP_CC_ATTR_RW(_name, NAME) \ + struct hns_port_cc_attr hns_roce_port_attr_dip_##_name = \ + __HNS_SCC_ATTR(_name, HNS_ROCE_SCC_ALGO_DIP, \ + HNS_ROCE_DIP_##NAME##_OFS, \ + HNS_ROCE_DIP_##NAME##_SZ, \ + 0, HNS_ROCE_DIP_##NAME##_MAX) + +HNS_PORT_DIP_CC_ATTR_RW(ai, AI); +HNS_PORT_DIP_CC_ATTR_RW(f, F); +HNS_PORT_DIP_CC_ATTR_RW(tkp, TKP); +HNS_PORT_DIP_CC_ATTR_RW(tmp, TMP); +HNS_PORT_DIP_CC_ATTR_RW(alp, ALP); +HNS_PORT_DIP_CC_ATTR_RW(max_speed, MAX_SPEED); +HNS_PORT_DIP_CC_ATTR_RW(g, G); +HNS_PORT_DIP_CC_ATTR_RW(al, AL); +HNS_PORT_DIP_CC_ATTR_RW(cnp_time, CNP_TIME); +HNS_PORT_DIP_CC_ATTR_RW(ashift, ASHIFT); +HNS_PORT_DIP_CC_ATTR_RW(lifespan, LIFESPAN); + +static struct attribute *dip_param_attrs[] = { + &hns_roce_port_attr_dip_ai.port_attr.attr, + &hns_roce_port_attr_dip_f.port_attr.attr, + &hns_roce_port_attr_dip_tkp.port_attr.attr, + &hns_roce_port_attr_dip_tmp.port_attr.attr, + &hns_roce_port_attr_dip_alp.port_attr.attr, + &hns_roce_port_attr_dip_max_speed.port_attr.attr, + &hns_roce_port_attr_dip_g.port_attr.attr, + &hns_roce_port_attr_dip_al.port_attr.attr, + &hns_roce_port_attr_dip_cnp_time.port_attr.attr, + &hns_roce_port_attr_dip_ashift.port_attr.attr, + &hns_roce_port_attr_dip_lifespan.port_attr.attr, + NULL, +}; + +static const struct attribute_group dip_cc_param_group = { + .name = "dip_cc_param", + .attrs = dip_param_attrs, + .is_visible = scc_attr_is_visible, +}; + +const struct attribute_group *hns_attr_port_groups[] = { + &dcqcn_cc_param_group, + &ldcp_cc_param_group, + &hc3_cc_param_group, + &dip_cc_param_group, + NULL, +}; + +static ssize_t hns_roce_port_attr_show(struct kobject *kobj, + struct attribute *attr, char *buf) +{ + struct hns_port_attribute *port_attr = + container_of(attr, struct hns_port_attribute, attr); + struct hns_roce_port *p = + container_of(kobj, struct hns_roce_port, kobj); + + if (!port_attr->show) + return -EIO; + + return port_attr->show(p, port_attr, buf); +} + +static ssize_t hns_roce_port_attr_store(struct kobject *kobj, + struct attribute *attr, + const char *buf, size_t count) +{ + struct hns_port_attribute *port_attr = + container_of(attr, struct hns_port_attribute, attr); + struct hns_roce_port *p = + container_of(kobj, struct hns_roce_port, kobj); + + if (!port_attr->store) + return -EIO; + + return port_attr->store(p, port_attr, buf, count); +} + +static void hns_roce_port_release(struct kobject *kobj) +{ + struct hns_roce_port *pdata = + container_of(kobj, struct hns_roce_port, kobj); + + kfree(pdata->scc_param); +} + +static const struct sysfs_ops hns_roce_port_ops = { + .show = hns_roce_port_attr_show, + .store = hns_roce_port_attr_store, +}; + +static struct kobj_type hns_roce_port_ktype = { + .release = hns_roce_port_release, + .sysfs_ops = &hns_roce_port_ops, +}; + +int hns_roce_create_port_files(struct ib_device *ibdev, u8 port_num, + struct kobject *kobj) +{ + struct hns_roce_dev *hr_dev = to_hr_dev(ibdev); + struct hns_roce_port *pdata; + int ret; + + if (!port_num || port_num > hr_dev->caps.num_ports) { + ibdev_err(ibdev, "fail to create port sysfs for invalid port %u.\n", + port_num); + return -ENODEV; + } + + pdata = &hr_dev->port_data[port_num - 1]; + pdata->hr_dev = hr_dev; + pdata->port_num = port_num; + ret = kobject_init_and_add(&pdata->kobj, &hns_roce_port_ktype, + kobj, "cc_param"); + if (ret) { + ibdev_err(ibdev, "fail to create port(%u) sysfs, ret = %d.\n", + port_num, ret); + goto fail_kobj; + } + kobject_uevent(&pdata->kobj, KOBJ_ADD); + + ret = sysfs_create_groups(&pdata->kobj, hns_attr_port_groups); + if (ret) { + ibdev_err(ibdev, + "fail to create port(%u) cc param sysfs, ret = %d.\n", + port_num, ret); + goto fail_kobj; + } + + ret = alloc_scc_param(hr_dev, pdata); + if (ret) { + dev_err(hr_dev->dev, "alloc scc param failed, ret = %d!\n", + ret); + goto fail_group; + } + + return ret; + +fail_group: + sysfs_remove_groups(&pdata->kobj, hns_attr_port_groups); + +fail_kobj: + kobject_put(&pdata->kobj); + + return ret; +} + +static void hns_roce_unregister_port_sysfs(struct hns_roce_dev *hr_dev, + u8 port_num) +{ + struct hns_roce_port *pdata; + + pdata = &hr_dev->port_data[port_num]; + sysfs_remove_groups(&pdata->kobj, hns_attr_port_groups); + kobject_put(&pdata->kobj); +} + +void hns_roce_unregister_sysfs(struct hns_roce_dev *hr_dev) +{ + int i; + + for (i = 0; i < hr_dev->caps.num_ports; i++) + hns_roce_unregister_port_sysfs(hr_dev, i); +} -- 2.30.0

1 0

Kernel sig 3.10 14:00-15:30 例会议题情况//答复: openEuler Kernel SIG双周例会
by liaotao (C) 10 Mar '23

10 Mar '23

当前例会议题：议题一：进展update（10min） --- 张伽琳 & 郑增凯议题二：内核热升级使用及技术探讨和规划 --- 桑琰欢迎大家继续申报~ 上期遗留问题： 1、openEuler缺陷issue处理流程介绍 2、内核热升级下一步规划，需求讨论 -----原始约会----- 发件人: openEuler conference <public(a)openeuler.org> 发送时间: 2023年3月7日 15:49 收件人: dev@openeuler.org,kernel-discuss@openeuler.org,kernel@openeuler.org 主题: openEuler Kernel SIG双周例会时间: 2023年3月10日星期五 14:00-15:30(UTC+08:00) 北京，重庆，香港特别行政区，乌鲁木齐。地点: 您好！ Kernel SIG 邀请您参加 2023-03-10 14:00 召开的Zoom会议(自动录制) 会议主题：openEuler Kernel SIG双周例会会议内容：欢迎您参加 Kernel SIG 双周例会，当前议题： 1. 进展update 2. 议题征集中欢迎大家积极申报议题（新增议题可以直接回复邮件，或录入会议看板）会议链接：https://us06web.zoom.us/j/87191608489?pwd=eG96T0p2Y0NDRUdHOW9SYys5SElTQT09 会议纪要：https://etherpad.openeuler.org/p/Kernel-meetings 温馨提醒：建议接入会议后修改参会人的姓名，也可以使用您在gitee.com的ID 更多资讯尽在：https://openeuler.org/zh/ Hello! openEuler Kernel SIG invites you to attend the Zoom conference(auto recording) will be held at 2023-03-10 14:00, The subject of the conference is openEuler Kernel SIG双周例会, Summary: 欢迎您参加 Kernel SIG 双周例会，当前议题： 1. 进展update 2. 议题征集中欢迎大家积极申报议题（新增议题可以直接回复邮件，或录入会议看板） You can join the meeting at https://us06web.zoom.us/j/87191608489?pwd=eG96T0p2Y0NDRUdHOW9SYys5SElTQT09. Add topics at https://etherpad.openeuler.org/p/Kernel-meetings. Note: You are advised to change the participant name after joining the conference or use your ID at gitee.com. More information: https://openeuler.org/en/

1 0

[PATCH openEuler-5.10-LTS-SP1] Revert "scsi: fix iscsi rescan fails to create block"
by Jialin Zhang 09 Mar '23

09 Mar '23

From: Zhong Jinghua <zhongjinghua(a)huawei.com> hulk inclusion category: bugfix bugzilla: 188150, https://gitee.com/openeuler/kernel/issues/I643OL ---------------------------------------- This reverts commit 7f10ea522db56188ae46c5bbee7052a2b2797515. This commit has a soft lock problem: watchdog: BUG: soft lockup - CPU#22 stuck for 67s! [iscsid:16369] Call Trace: scsi_remove_target+0x548/0x7b0 ? sdev_store_delete+0x90/0x90 ? __mutex_lock_slowpath+0x10/0x10 ? device_remove_class_symlinks+0x1b0/0x1b0 __iscsi_unbind_session+0x16b/0x250 [scsi_transport_iscsi] iscsi_remove_session+0x1d3/0x2f0 [scsi_transport_iscsi] iscsi_session_remove+0x5c/0x80 [libiscsi] iscsi_sw_tcp_session_destroy+0xd3/0x160 [iscsi_tcp] iscsi_if_rx+0x2369/0x5060 [scsi_transport_iscsi] The reason is that if other threads hold the reference count of the kobject while waiting for the device to be released, it will keep waiting in a loop. Fixes: 7f10ea522db5 ("scsi: fix iscsi rescan fails to create block") Signed-off-by: Zhong Jinghua <zhongjinghua(a)huawei.com> Reviewed-by: Hou Tao <houtao1(a)huawei.com> Signed-off-by: Jialin Zhang <zhangjialin11(a)huawei.com> --- drivers/scsi/scsi_sysfs.c | 11 +++-------- 1 file changed, 3 insertions(+), 8 deletions(-) diff --git a/drivers/scsi/scsi_sysfs.c b/drivers/scsi/scsi_sysfs.c index e7893835b99a..42db9c52208e 100644 --- a/drivers/scsi/scsi_sysfs.c +++ b/drivers/scsi/scsi_sysfs.c @@ -1503,13 +1503,6 @@ void scsi_remove_device(struct scsi_device *sdev) } EXPORT_SYMBOL(scsi_remove_device); -static int scsi_device_try_get(struct scsi_device *sdev) -{ - if (!kobject_get_unless_zero(&sdev->sdev_gendev.kobj)) - return -ENXIO; - return 0; -} - static void __scsi_remove_target(struct scsi_target *starget) { struct Scsi_Host *shost = dev_to_shost(starget->dev.parent); @@ -1528,7 +1521,9 @@ static void __scsi_remove_target(struct scsi_target *starget) if (sdev->channel != starget->channel || sdev->id != starget->id) continue; - if (scsi_device_try_get(sdev)) + if (sdev->sdev_state == SDEV_DEL || + sdev->sdev_state == SDEV_CANCEL || + !get_device(&sdev->sdev_gendev)) continue; spin_unlock_irqrestore(shost->host_lock, flags); scsi_remove_device(sdev); -- 2.25.1

1 0

[PATCH openEuler-1.0-LTS 1/3] HID: asus: Remove check for same LED brightness on set
by Yongqiang Liu 09 Mar '23

09 Mar '23

From: "Luke D. Jones" <luke(a)ljones.dev> mainline inclusion from mainline-v5.14-rc4 commit 3fdcf7cdfc229346d028242e73562704ad644dd0 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I6I7U9 CVE: CVE-2023-1079 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- Remove the early return on LED brightness set so that any controller application, daemon, or desktop may set the same brightness at any stage. This is required because many ASUS ROG keyboards will default to max brightness on laptop resume if the LEDs were set to off before sleep. Signed-off-by: Luke D Jones <luke(a)ljones.dev> Signed-off-by: Jiri Kosina <jkosina(a)suse.cz> Signed-off-by: Yuyao Lin <linyuyao1(a)huawei.com> Reviewed-by: Wang Weiyang <wangweiyang2(a)huawei.com> Reviewed-by: Xiongfeng Wang <wangxiongfeng2(a)huawei.com> Signed-off-by: Yongqiang Liu <liuyongqiang13(a)huawei.com> --- drivers/hid/hid-asus.c | 3 --- 1 file changed, 3 deletions(-) diff --git a/drivers/hid/hid-asus.c b/drivers/hid/hid-asus.c index 800b2364e29e..9ae8e3d5edf1 100644 --- a/drivers/hid/hid-asus.c +++ b/drivers/hid/hid-asus.c @@ -318,9 +318,6 @@ static void asus_kbd_backlight_set(struct led_classdev *led_cdev, { struct asus_kbd_leds *led = container_of(led_cdev, struct asus_kbd_leds, cdev); - if (led->brightness == brightness) - return; - led->brightness = brightness; schedule_work(&led->work); } -- 2.25.1

1 2

[PATCH openEuler-1.0-LTS 01/16] netfilter: conntrack: do not renew entry stuck in tcp SYN_SENT state
by Yongqiang Liu 08 Mar '23

08 Mar '23

From: Florian Westphal <fw(a)strlen.de> stable inclusion from stable-v4.19.272 commit 01687e35df44dd09cc6943306db35d9efc507907 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I6KOHU CVE: NA -------------------------------- [ Upstream commit e15d4cdf27cb0c1e977270270b2cea12e0955edd ] Consider: client -----> conntrack ---> Host client sends a SYN, but $Host is unreachable/silent. Client eventually gives up and the conntrack entry will time out. However, if the client is restarted with same addr/port pair, it may prevent the conntrack entry from timing out. This is noticeable when the existing conntrack entry has no NAT transformation or an outdated one and port reuse happens either on client or due to a NAT middlebox. This change prevents refresh of the timeout for SYN retransmits, so entry is going away after nf_conntrack_tcp_timeout_syn_sent seconds (default: 60). Entry will be re-created on next connection attempt, but then nat rules will be evaluated again. Signed-off-by: Florian Westphal <fw(a)strlen.de> Signed-off-by: Pablo Neira Ayuso <pablo(a)netfilter.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Yongqiang Liu <liuyongqiang13(a)huawei.com> --- net/netfilter/nf_conntrack_proto_tcp.c | 10 ++++++++++ 1 file changed, 10 insertions(+) diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c index aab532b8c8c6..1600f35bfd49 100644 --- a/net/netfilter/nf_conntrack_proto_tcp.c +++ b/net/netfilter/nf_conntrack_proto_tcp.c @@ -1089,6 +1089,16 @@ static int tcp_packet(struct nf_conn *ct, nf_ct_kill_acct(ct, ctinfo, skb); return NF_ACCEPT; } + + if (index == TCP_SYN_SET && old_state == TCP_CONNTRACK_SYN_SENT) { + /* do not renew timeout on SYN retransmit. + * + * Else port reuse by client or NAT middlebox can keep + * entry alive indefinitely (including nat info). + */ + return NF_ACCEPT; + } + /* ESTABLISHED without SEEN_REPLY, i.e. mid-connection * pickup with loose=1. Avoid large ESTABLISHED timeout. */ -- 2.25.1

1 15

[PATCH openEuler-1.0-LTS 01/31] binder: use standard functions to allocate fds
by Yongqiang Liu 08 Mar '23

08 Mar '23

From: Todd Kjos <tkjos(a)android.com> mainline inclusion from mainline-v4.20-rc1 commit 44d8047f1d87adc2fd7eccc88533794f6d88c15e category: bugfix bugzilla: 188431, https://gitee.com/src-openeuler/kernel/issues/I6DKVG CVE: CVE-2023-20938 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- Binder uses internal fs interfaces to allocate and install fds: __alloc_fd __fd_install __close_fd get_files_struct put_files_struct These were used to support the passing of fds between processes as part of a transaction. The actual allocation and installation of the fds in the target process was handled by the sending process so the standard functions, alloc_fd() and fd_install() which assume task==current couldn't be used. This patch refactors this mechanism so that the fds are allocated and installed by the target process allowing the standard functions to be used. The sender now creates a list of fd fixups that contains the struct *file and the address to fixup with the new fd once it is allocated. This list is processed by the target process when the transaction is dequeued. A new error case is introduced by this change. If an async transaction with file descriptors cannot allocate new fds in the target (probably due to out of file descriptors), the transaction is discarded with a log message. In the old implementation this would have been detected in the sender context and failed prior to sending. Signed-off-by: Todd Kjos <tkjos(a)google.com> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Conflicts: drivers/android/binder.c Signed-off-by: Li Huafei <lihuafei1(a)huawei.com> Reviewed-by: Wang Weiyang <wangweiyang2(a)huawei.com> Reviewed-by: Zheng Yejian <zhengyejian1(a)huawei.com> Signed-off-by: Yongqiang Liu <liuyongqiang13(a)huawei.com> --- drivers/android/Kconfig | 2 +- drivers/android/binder.c | 391 ++++++++++++++++++++------------- drivers/android/binder_trace.h | 36 ++- 3 files changed, 262 insertions(+), 167 deletions(-) diff --git a/drivers/android/Kconfig b/drivers/android/Kconfig index 432e9ad77070..51e8250d113f 100644 --- a/drivers/android/Kconfig +++ b/drivers/android/Kconfig @@ -10,7 +10,7 @@ if ANDROID config ANDROID_BINDER_IPC bool "Android Binder IPC Driver" - depends on MMU + depends on MMU && !CPU_CACHE_VIVT default n ---help--- Binder is used in Android for both communication between processes, diff --git a/drivers/android/binder.c b/drivers/android/binder.c index c5a39b8ae886..8a72aacd7a39 100644 --- a/drivers/android/binder.c +++ b/drivers/android/binder.c @@ -71,6 +71,7 @@ #include <linux/security.h> #include <linux/spinlock.h> #include <linux/ratelimit.h> +#include <linux/syscalls.h> #include <uapi/linux/android/binder.h> @@ -457,9 +458,8 @@ struct binder_ref { }; enum binder_deferred_state { - BINDER_DEFERRED_PUT_FILES = 0x01, - BINDER_DEFERRED_FLUSH = 0x02, - BINDER_DEFERRED_RELEASE = 0x04, + BINDER_DEFERRED_FLUSH = 0x01, + BINDER_DEFERRED_RELEASE = 0x02, }; /** @@ -480,9 +480,6 @@ enum binder_deferred_state { * (invariant after initialized) * @tsk task_struct for group_leader of process * (invariant after initialized) - * @files files_struct for process - * (protected by @files_lock) - * @files_lock mutex to protect @files * @cred struct cred associated with the `struct file` * in binder_open() * (invariant after initialized) @@ -530,8 +527,6 @@ struct binder_proc { struct list_head waiting_threads; int pid; struct task_struct *tsk; - struct files_struct *files; - struct mutex files_lock; const struct cred *cred; struct hlist_node deferred_work_node; int deferred_work; @@ -615,6 +610,23 @@ struct binder_thread { bool is_dead; }; +/** + * struct binder_txn_fd_fixup - transaction fd fixup list element + * @fixup_entry: list entry + * @file: struct file to be associated with new fd + * @offset: offset in buffer data to this fixup + * + * List element for fd fixups in a transaction. Since file + * descriptors need to be allocated in the context of the + * target process, we pass each fd to be processed in this + * struct. + */ +struct binder_txn_fd_fixup { + struct list_head fixup_entry; + struct file *file; + size_t offset; +}; + struct binder_transaction { int debug_id; struct binder_work work; @@ -632,6 +644,7 @@ struct binder_transaction { long priority; long saved_priority; kuid_t sender_euid; + struct list_head fd_fixups; /** * @lock: protects @from, @to_proc, and @to_thread * @@ -905,66 +918,6 @@ static void binder_free_thread(struct binder_thread *thread); static void binder_free_proc(struct binder_proc *proc); static void binder_inc_node_tmpref_ilocked(struct binder_node *node); -static int task_get_unused_fd_flags(struct binder_proc *proc, int flags) -{ - unsigned long rlim_cur; - unsigned long irqs; - int ret; - - mutex_lock(&proc->files_lock); - if (proc->files == NULL) { - ret = -ESRCH; - goto err; - } - if (!lock_task_sighand(proc->tsk, &irqs)) { - ret = -EMFILE; - goto err; - } - rlim_cur = task_rlimit(proc->tsk, RLIMIT_NOFILE); - unlock_task_sighand(proc->tsk, &irqs); - - ret = __alloc_fd(proc->files, 0, rlim_cur, flags); -err: - mutex_unlock(&proc->files_lock); - return ret; -} - -/* - * copied from fd_install - */ -static void task_fd_install( - struct binder_proc *proc, unsigned int fd, struct file *file) -{ - mutex_lock(&proc->files_lock); - if (proc->files) - __fd_install(proc->files, fd, file); - mutex_unlock(&proc->files_lock); -} - -/* - * copied from sys_close - */ -static long task_close_fd(struct binder_proc *proc, unsigned int fd) -{ - int retval; - - mutex_lock(&proc->files_lock); - if (proc->files == NULL) { - retval = -ESRCH; - goto err; - } - retval = __close_fd(proc->files, fd); - /* can't restart close syscall because file table entry was cleared */ - if (unlikely(retval == -ERESTARTSYS || - retval == -ERESTARTNOINTR || - retval == -ERESTARTNOHAND || - retval == -ERESTART_RESTARTBLOCK)) - retval = -EINTR; -err: - mutex_unlock(&proc->files_lock); - return retval; -} - static bool binder_has_work_ilocked(struct binder_thread *thread, bool do_proc_work) { @@ -1948,6 +1901,27 @@ static struct binder_thread *binder_get_txn_from_and_acq_inner( return NULL; } +/** + * binder_free_txn_fixups() - free unprocessed fd fixups + * @t: binder transaction for t->from + * + * If the transaction is being torn down prior to being + * processed by the target process, free all of the + * fd fixups and fput the file structs. It is safe to + * call this function after the fixups have been + * processed -- in that case, the list will be empty. + */ +static void binder_free_txn_fixups(struct binder_transaction *t) +{ + struct binder_txn_fd_fixup *fixup, *tmp; + + list_for_each_entry_safe(fixup, tmp, &t->fd_fixups, fixup_entry) { + fput(fixup->file); + list_del(&fixup->fixup_entry); + kfree(fixup); + } +} + static void binder_free_transaction(struct binder_transaction *t) { struct binder_proc *target_proc = t->to_proc; @@ -1962,6 +1936,7 @@ static void binder_free_transaction(struct binder_transaction *t) * If the transaction has no target_proc, then * t->buffer->transaction has already been cleared. */ + binder_free_txn_fixups(t); kfree(t); binder_stats_deleted(BINDER_STAT_TRANSACTION); } @@ -2262,12 +2237,17 @@ static void binder_transaction_buffer_release(struct binder_proc *proc, } break; case BINDER_TYPE_FD: { - struct binder_fd_object *fp = to_binder_fd_object(hdr); - - binder_debug(BINDER_DEBUG_TRANSACTION, - " fd %d\n", fp->fd); - if (failed_at) - task_close_fd(proc, fp->fd); + /* + * No need to close the file here since user-space + * closes it for for successfully delivered + * transactions. For transactions that weren't + * delivered, the new fd was never allocated so + * there is no need to close and the fput on the + * file is done when the transaction is torn + * down. + */ + WARN_ON(failed_at && + proc->tsk == current->group_leader); } break; case BINDER_TYPE_PTR: /* @@ -2283,6 +2263,15 @@ static void binder_transaction_buffer_release(struct binder_proc *proc, size_t fd_index; binder_size_t fd_buf_size; + if (proc->tsk != current->group_leader) { + /* + * Nothing to do if running in sender context + * The fd fixups have not been applied so no + * fds need to be closed. + */ + continue; + } + fda = to_binder_fd_array_object(hdr); parent = binder_validate_ptr(buffer, fda->parent, off_start, @@ -2315,7 +2304,7 @@ static void binder_transaction_buffer_release(struct binder_proc *proc, } fd_array = (u32 *)(parent_buffer + (uintptr_t)fda->parent_offset); for (fd_index = 0; fd_index < fda->num_fds; fd_index++) - task_close_fd(proc, fd_array[fd_index]); + ksys_close(fd_array[fd_index]); } break; default: pr_err("transaction release %d bad object type %x\n", @@ -2447,17 +2436,18 @@ static int binder_translate_handle(struct flat_binder_object *fp, return ret; } -static int binder_translate_fd(int fd, +static int binder_translate_fd(u32 *fdp, struct binder_transaction *t, struct binder_thread *thread, struct binder_transaction *in_reply_to) { struct binder_proc *proc = thread->proc; struct binder_proc *target_proc = t->to_proc; - int target_fd; + struct binder_txn_fd_fixup *fixup; struct file *file; - int ret; + int ret = 0; bool target_allows_fd; + int fd = *fdp; if (in_reply_to) target_allows_fd = !!(in_reply_to->flags & TF_ACCEPT_FDS); @@ -2485,19 +2475,24 @@ static int binder_translate_fd(int fd, goto err_security; } - target_fd = task_get_unused_fd_flags(target_proc, O_CLOEXEC); - if (target_fd < 0) { + /* + * Add fixup record for this transaction. The allocation + * of the fd in the target needs to be done from a + * target thread. + */ + fixup = kzalloc(sizeof(*fixup), GFP_KERNEL); + if (!fixup) { ret = -ENOMEM; - goto err_get_unused_fd; + goto err_alloc; } - task_fd_install(target_proc, target_fd, file); - trace_binder_transaction_fd(t, fd, target_fd); - binder_debug(BINDER_DEBUG_TRANSACTION, " fd %d -> %d\n", - fd, target_fd); + fixup->file = file; + fixup->offset = (uintptr_t)fdp - (uintptr_t)t->buffer->data; + trace_binder_transaction_fd_send(t, fd, fixup->offset); + list_add_tail(&fixup->fixup_entry, &t->fd_fixups); - return target_fd; + return ret; -err_get_unused_fd: +err_alloc: err_security: fput(file); err_fget: @@ -2511,8 +2506,7 @@ static int binder_translate_fd_array(struct binder_fd_array_object *fda, struct binder_thread *thread, struct binder_transaction *in_reply_to) { - binder_size_t fdi, fd_buf_size, num_installed_fds; - int target_fd; + binder_size_t fdi, fd_buf_size; uintptr_t parent_buffer; u32 *fd_array; struct binder_proc *proc = thread->proc; @@ -2544,23 +2538,12 @@ static int binder_translate_fd_array(struct binder_fd_array_object *fda, return -EINVAL; } for (fdi = 0; fdi < fda->num_fds; fdi++) { - target_fd = binder_translate_fd(fd_array[fdi], t, thread, + int ret = binder_translate_fd(&fd_array[fdi], t, thread, in_reply_to); - if (target_fd < 0) - goto err_translate_fd_failed; - fd_array[fdi] = target_fd; + if (ret < 0) + return ret; } return 0; - -err_translate_fd_failed: - /* - * Failed to allocate fd or security error, free fds - * installed so far. - */ - num_installed_fds = fdi; - for (fdi = 0; fdi < num_installed_fds; fdi++) - task_close_fd(target_proc, fd_array[fdi]); - return target_fd; } static int binder_fixup_parent(struct binder_transaction *t, @@ -2935,6 +2918,7 @@ static void binder_transaction(struct binder_proc *proc, return_error_line = __LINE__; goto err_alloc_t_failed; } + INIT_LIST_HEAD(&t->fd_fixups); binder_stats_created(BINDER_STAT_TRANSACTION); spin_lock_init(&t->lock); @@ -3089,17 +3073,16 @@ static void binder_transaction(struct binder_proc *proc, case BINDER_TYPE_FD: { struct binder_fd_object *fp = to_binder_fd_object(hdr); - int target_fd = binder_translate_fd(fp->fd, t, thread, - in_reply_to); + int ret = binder_translate_fd(&fp->fd, t, thread, + in_reply_to); - if (target_fd < 0) { + if (ret < 0) { return_error = BR_FAILED_REPLY; - return_error_param = target_fd; + return_error_param = ret; return_error_line = __LINE__; goto err_translate_failed; } fp->pad_binder = 0; - fp->fd = target_fd; } break; case BINDER_TYPE_FDA: { struct binder_fd_array_object *fda = @@ -3256,6 +3239,7 @@ static void binder_transaction(struct binder_proc *proc, err_bad_offset: err_bad_parent: err_copy_data_failed: + binder_free_txn_fixups(t); trace_binder_transaction_failed_buffer_release(t->buffer); binder_transaction_buffer_release(target_proc, t->buffer, offp); if (target_node) @@ -3318,6 +3302,49 @@ static void binder_transaction(struct binder_proc *proc, } } +/** + * binder_free_buf() - free the specified buffer + * @proc: binder proc that owns buffer + * @buffer: buffer to be freed + * + * If buffer for an async transaction, enqueue the next async + * transaction from the node. + * + * Cleanup buffer and free it. + */ +void +binder_free_buf(struct binder_proc *proc, struct binder_buffer *buffer) +{ + binder_inner_proc_lock(proc); + if (buffer->transaction) { + buffer->transaction->buffer = NULL; + buffer->transaction = NULL; + } + binder_inner_proc_unlock(proc); + if (buffer->async_transaction && buffer->target_node) { + struct binder_node *buf_node; + struct binder_work *w; + + buf_node = buffer->target_node; + binder_node_inner_lock(buf_node); + BUG_ON(!buf_node->has_async_transaction); + BUG_ON(buf_node->proc != proc); + w = binder_dequeue_work_head_ilocked( + &buf_node->async_todo); + if (!w) { + buf_node->has_async_transaction = false; + } else { + binder_enqueue_work_ilocked( + w, &proc->todo); + binder_wakeup_proc_ilocked(proc); + } + binder_node_inner_unlock(buf_node); + } + trace_binder_transaction_buffer_release(buffer); + binder_transaction_buffer_release(proc, buffer, NULL); + binder_alloc_free_buf(&proc->alloc, buffer); +} + static int binder_thread_write(struct binder_proc *proc, struct binder_thread *thread, binder_uintptr_t binder_buffer, size_t size, @@ -3508,35 +3535,7 @@ static int binder_thread_write(struct binder_proc *proc, proc->pid, thread->pid, (u64)data_ptr, buffer->debug_id, buffer->transaction ? "active" : "finished"); - - binder_inner_proc_lock(proc); - if (buffer->transaction) { - buffer->transaction->buffer = NULL; - buffer->transaction = NULL; - } - binder_inner_proc_unlock(proc); - if (buffer->async_transaction && buffer->target_node) { - struct binder_node *buf_node; - struct binder_work *w; - - buf_node = buffer->target_node; - binder_node_inner_lock(buf_node); - BUG_ON(!buf_node->has_async_transaction); - BUG_ON(buf_node->proc != proc); - w = binder_dequeue_work_head_ilocked( - &buf_node->async_todo); - if (!w) { - buf_node->has_async_transaction = false; - } else { - binder_enqueue_work_ilocked( - w, &proc->todo); - binder_wakeup_proc_ilocked(proc); - } - binder_node_inner_unlock(buf_node); - } - trace_binder_transaction_buffer_release(buffer); - binder_transaction_buffer_release(proc, buffer, NULL); - binder_alloc_free_buf(&proc->alloc, buffer); + binder_free_buf(proc, buffer); break; } @@ -3859,6 +3858,76 @@ static int binder_wait_for_work(struct binder_thread *thread, return ret; } +/** + * binder_apply_fd_fixups() - finish fd translation + * @t: binder transaction with list of fd fixups + * + * Now that we are in the context of the transaction target + * process, we can allocate and install fds. Process the + * list of fds to translate and fixup the buffer with the + * new fds. + * + * If we fail to allocate an fd, then free the resources by + * fput'ing files that have not been processed and ksys_close'ing + * any fds that have already been allocated. + */ +static int binder_apply_fd_fixups(struct binder_transaction *t) +{ + struct binder_txn_fd_fixup *fixup, *tmp; + int ret = 0; + + list_for_each_entry(fixup, &t->fd_fixups, fixup_entry) { + int fd = get_unused_fd_flags(O_CLOEXEC); + u32 *fdp; + + if (fd < 0) { + binder_debug(BINDER_DEBUG_TRANSACTION, + "failed fd fixup txn %d fd %d\n", + t->debug_id, fd); + ret = -ENOMEM; + break; + } + binder_debug(BINDER_DEBUG_TRANSACTION, + "fd fixup txn %d fd %d\n", + t->debug_id, fd); + trace_binder_transaction_fd_recv(t, fd, fixup->offset); + fd_install(fd, fixup->file); + fixup->file = NULL; + fdp = (u32 *)(t->buffer->data + fixup->offset); + /* + * This store can cause problems for CPUs with a + * VIVT cache (eg ARMv5) since the cache cannot + * detect virtual aliases to the same physical cacheline. + * To support VIVT, this address and the user-space VA + * would both need to be flushed. Since this kernel + * VA is not constructed via page_to_virt(), we can't + * use flush_dcache_page() on it, so we'd have to use + * an internal function. If devices with VIVT ever + * need to run Android, we'll either need to go back + * to patching the translated fd from the sender side + * (using the non-standard kernel functions), or rework + * how the kernel uses the buffer to use page_to_virt() + * addresses instead of allocating in our own vm area. + * + * For now, we disable compilation if CONFIG_CPU_CACHE_VIVT. + */ + *fdp = fd; + } + list_for_each_entry_safe(fixup, tmp, &t->fd_fixups, fixup_entry) { + if (fixup->file) { + fput(fixup->file); + } else if (ret) { + u32 *fdp = (u32 *)(t->buffer->data + fixup->offset); + + ksys_close(*fdp); + } + list_del(&fixup->fixup_entry); + kfree(fixup); + } + + return ret; +} + static int binder_thread_read(struct binder_proc *proc, struct binder_thread *thread, binder_uintptr_t binder_buffer, size_t size, @@ -4140,6 +4209,34 @@ static int binder_thread_read(struct binder_proc *proc, tr.sender_pid = 0; } + ret = binder_apply_fd_fixups(t); + if (ret) { + struct binder_buffer *buffer = t->buffer; + bool oneway = !!(t->flags & TF_ONE_WAY); + int tid = t->debug_id; + + if (t_from) + binder_thread_dec_tmpref(t_from); + buffer->transaction = NULL; + binder_cleanup_transaction(t, "fd fixups failed", + BR_FAILED_REPLY); + binder_free_buf(proc, buffer); + binder_debug(BINDER_DEBUG_FAILED_TRANSACTION, + "%d:%d %stransaction %d fd fixups failed %d/%d, line %d\n", + proc->pid, thread->pid, + oneway ? "async " : + (cmd == BR_REPLY ? "reply " : ""), + tid, BR_FAILED_REPLY, ret, __LINE__); + if (cmd == BR_REPLY) { + cmd = BR_FAILED_REPLY; + if (put_user(cmd, (uint32_t __user *)ptr)) + return -EFAULT; + ptr += sizeof(uint32_t); + binder_stat_br(proc, thread, cmd); + break; + } + continue; + } tr.data_size = t->buffer->data_size; tr.offsets_size = t->buffer->offsets_size; tr.data.ptr.buffer = (binder_uintptr_t) @@ -4730,7 +4827,6 @@ static void binder_vma_close(struct vm_area_struct *vma) (vma->vm_end - vma->vm_start) / SZ_1K, vma->vm_flags, (unsigned long)pgprot_val(vma->vm_page_prot)); binder_alloc_vma_close(&proc->alloc); - binder_defer_work(proc, BINDER_DEFERRED_PUT_FILES); } static vm_fault_t binder_vm_fault(struct vm_fault *vmf) @@ -4776,9 +4872,6 @@ static int binder_mmap(struct file *filp, struct vm_area_struct *vma) ret = binder_alloc_mmap_handler(&proc->alloc, vma); if (ret) return ret; - mutex_lock(&proc->files_lock); - proc->files = get_files_struct(current); - mutex_unlock(&proc->files_lock); return 0; err_bad_arg: @@ -4802,7 +4895,6 @@ static int binder_open(struct inode *nodp, struct file *filp) spin_lock_init(&proc->outer_lock); get_task_struct(current->group_leader); proc->tsk = current->group_leader; - mutex_init(&proc->files_lock); proc->cred = get_cred(filp->f_cred); INIT_LIST_HEAD(&proc->todo); proc->default_priority = task_nice(current); @@ -4953,8 +5045,6 @@ static void binder_deferred_release(struct binder_proc *proc) struct rb_node *n; int threads, nodes, incoming_refs, outgoing_refs, active_transactions; - BUG_ON(proc->files); - mutex_lock(&binder_procs_lock); hlist_del(&proc->proc_node); mutex_unlock(&binder_procs_lock); @@ -5036,7 +5126,6 @@ static void binder_deferred_release(struct binder_proc *proc) static void binder_deferred_func(struct work_struct *work) { struct binder_proc *proc; - struct files_struct *files; int defer; @@ -5054,23 +5143,11 @@ static void binder_deferred_func(struct work_struct *work) } mutex_unlock(&binder_deferred_lock); - files = NULL; - if (defer & BINDER_DEFERRED_PUT_FILES) { - mutex_lock(&proc->files_lock); - files = proc->files; - if (files) - proc->files = NULL; - mutex_unlock(&proc->files_lock); - } - if (defer & BINDER_DEFERRED_FLUSH) binder_deferred_flush(proc); if (defer & BINDER_DEFERRED_RELEASE) binder_deferred_release(proc); /* frees proc */ - - if (files) - put_files_struct(files); } while (proc); } static DECLARE_WORK(binder_deferred_work, binder_deferred_func); diff --git a/drivers/android/binder_trace.h b/drivers/android/binder_trace.h index 588eb3ec3507..14de7ac57a34 100644 --- a/drivers/android/binder_trace.h +++ b/drivers/android/binder_trace.h @@ -223,22 +223,40 @@ TRACE_EVENT(binder_transaction_ref_to_ref, __entry->dest_ref_debug_id, __entry->dest_ref_desc) ); -TRACE_EVENT(binder_transaction_fd, - TP_PROTO(struct binder_transaction *t, int src_fd, int dest_fd), - TP_ARGS(t, src_fd, dest_fd), +TRACE_EVENT(binder_transaction_fd_send, + TP_PROTO(struct binder_transaction *t, int fd, size_t offset), + TP_ARGS(t, fd, offset), TP_STRUCT__entry( __field(int, debug_id) - __field(int, src_fd) - __field(int, dest_fd) + __field(int, fd) + __field(size_t, offset) + ), + TP_fast_assign( + __entry->debug_id = t->debug_id; + __entry->fd = fd; + __entry->offset = offset; + ), + TP_printk("transaction=%d src_fd=%d offset=%zu", + __entry->debug_id, __entry->fd, __entry->offset) +); + +TRACE_EVENT(binder_transaction_fd_recv, + TP_PROTO(struct binder_transaction *t, int fd, size_t offset), + TP_ARGS(t, fd, offset), + + TP_STRUCT__entry( + __field(int, debug_id) + __field(int, fd) + __field(size_t, offset) ), TP_fast_assign( __entry->debug_id = t->debug_id; - __entry->src_fd = src_fd; - __entry->dest_fd = dest_fd; + __entry->fd = fd; + __entry->offset = offset; ), - TP_printk("transaction=%d src_fd=%d ==> dest_fd=%d", - __entry->debug_id, __entry->src_fd, __entry->dest_fd) + TP_printk("transaction=%d dest_fd=%d offset=%zu", + __entry->debug_id, __entry->fd, __entry->offset) ); DECLARE_EVENT_CLASS(binder_buffer_class, -- 2.25.1

1 30

[PATCH openEuler-1.0-LTS 1/7] sctp: fail if no bound addresses can be used for a given scope
by Yongqiang Liu 08 Mar '23

08 Mar '23

From: Marcelo Ricardo Leitner <marcelo.leitner(a)gmail.com> stable inclusion from stable-v4.19.271 commit 26436553aabfd9b40e1daa537a099bf5bb13fb55 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I6I7U3 CVE: CVE-2023-1074 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit 458e279f861d3f61796894cd158b780765a1569f ] Currently, if you bind the socket to something like: servaddr.sin6_family = AF_INET6; servaddr.sin6_port = htons(0); servaddr.sin6_scope_id = 0; inet_pton(AF_INET6, "::1", &servaddr.sin6_addr); And then request a connect to: connaddr.sin6_family = AF_INET6; connaddr.sin6_port = htons(20000); connaddr.sin6_scope_id = if_nametoindex("lo"); inet_pton(AF_INET6, "fe88::1", &connaddr.sin6_addr); What the stack does is: - bind the socket - create a new asoc - to handle the connect - copy the addresses that can be used for the given scope - try to connect But the copy returns 0 addresses, and the effect is that it ends up trying to connect as if the socket wasn't bound, which is not the desired behavior. This unexpected behavior also allows KASLR leaks through SCTP diag interface. The fix here then is, if when trying to copy the addresses that can be used for the scope used in connect() it returns 0 addresses, bail out. This is what TCP does with a similar reproducer. Reported-by: Pietro Borrello <borrello(a)diag.uniroma1.it> Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner(a)gmail.com> Reviewed-by: Xin Long <lucien.xin(a)gmail.com> Link: https://lore.kernel.org/r/9fcd182f1099f86c6661f3717f63712ddd1c676c.16744967… Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Dong Chenchen <dongchenchen2(a)huawei.com> Reviewed-by: Yue Haibing <yuehaibing(a)huawei.com> Reviewed-by: Wang Weiyang <wangweiyang2(a)huawei.com> Signed-off-by: Yongqiang Liu <liuyongqiang13(a)huawei.com> --- net/sctp/bind_addr.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/net/sctp/bind_addr.c b/net/sctp/bind_addr.c index f8a283245672..d723942e5e65 100644 --- a/net/sctp/bind_addr.c +++ b/net/sctp/bind_addr.c @@ -88,6 +88,12 @@ int sctp_bind_addr_copy(struct net *net, struct sctp_bind_addr *dest, } } + /* If somehow no addresses were found that can be used with this + * scope, it's an error. + */ + if (list_empty(&dest->address_list)) + error = -ENETUNREACH; + out: if (error) sctp_bind_addr_clean(dest); -- 2.25.1

1 6

[PATCH openEuler-1.0-LTS] sctp: fail if no bound addresses can be used for a given scope
by Yongqiang Liu 08 Mar '23

08 Mar '23

From: Marcelo Ricardo Leitner <marcelo.leitner(a)gmail.com> stable inclusion from stable-v4.19.271 commit 26436553aabfd9b40e1daa537a099bf5bb13fb55 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I6I7U3 CVE: CVE-2023-1074 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit 458e279f861d3f61796894cd158b780765a1569f ] Currently, if you bind the socket to something like: servaddr.sin6_family = AF_INET6; servaddr.sin6_port = htons(0); servaddr.sin6_scope_id = 0; inet_pton(AF_INET6, "::1", &servaddr.sin6_addr); And then request a connect to: connaddr.sin6_family = AF_INET6; connaddr.sin6_port = htons(20000); connaddr.sin6_scope_id = if_nametoindex("lo"); inet_pton(AF_INET6, "fe88::1", &connaddr.sin6_addr); What the stack does is: - bind the socket - create a new asoc - to handle the connect - copy the addresses that can be used for the given scope - try to connect But the copy returns 0 addresses, and the effect is that it ends up trying to connect as if the socket wasn't bound, which is not the desired behavior. This unexpected behavior also allows KASLR leaks through SCTP diag interface. The fix here then is, if when trying to copy the addresses that can be used for the scope used in connect() it returns 0 addresses, bail out. This is what TCP does with a similar reproducer. Reported-by: Pietro Borrello <borrello(a)diag.uniroma1.it> Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Marcelo Ricardo Leitner <marcelo.leitner(a)gmail.com> Reviewed-by: Xin Long <lucien.xin(a)gmail.com> Link: https://lore.kernel.org/r/9fcd182f1099f86c6661f3717f63712ddd1c676c.16744967… Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Dong Chenchen <dongchenchen2(a)huawei.com> Reviewed-by: Yue Haibing <yuehaibing(a)huawei.com> Reviewed-by: Wang Weiyang <wangweiyang2(a)huawei.com> Signed-off-by: Yongqiang Liu <liuyongqiang13(a)huawei.com> --- net/sctp/bind_addr.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/net/sctp/bind_addr.c b/net/sctp/bind_addr.c index f8a283245672..d723942e5e65 100644 --- a/net/sctp/bind_addr.c +++ b/net/sctp/bind_addr.c @@ -88,6 +88,12 @@ int sctp_bind_addr_copy(struct net *net, struct sctp_bind_addr *dest, } } + /* If somehow no addresses were found that can be used with this + * scope, it's an error. + */ + if (list_empty(&dest->address_list)) + error = -ENETUNREACH; + out: if (error) sctp_bind_addr_clean(dest); -- 2.25.1

1 0

[PATCH openEuler-5.10-LTS-SP1 01/30] ovl: fix use inode directly in rcu-walk mode
by Zheng Zengkai 08 Mar '23

08 Mar '23

From: Chen Zhongjin <chenzhongjin(a)huawei.com> stable inclusion from stable-v5.10.163 commit 740c537f52c1f54aff9094744483d1515c7c8b7b category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I6GCCV Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- commit 672e4268b2863d7e4978dfed29552b31c2f9bd4e upstream. ovl_dentry_revalidate_common() can be called in rcu-walk mode. As document said, "in rcu-walk mode, d_parent and d_inode should not be used without care". Check inode here to protect access under rcu-walk mode. Fixes: bccece1ead36 ("ovl: allow remote upper") Reported-and-tested-by: syzbot+a4055c78774bbf3498bb(a)syzkaller.appspotmail.com Signed-off-by: Chen Zhongjin <chenzhongjin(a)huawei.com> Cc: <stable(a)vger.kernel.org> # v5.7 Signed-off-by: Miklos Szeredi <mszeredi(a)redhat.com> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Zhihao Cheng <chengzhihao1(a)huawei.com> Reviewed-by: Yang Erkun <yangerkun(a)huawei.com> Reviewed-by: Zhang Yi <yi.zhang(a)huawei.com> Signed-off-by: Jialin Zhang <zhangjialin11(a)huawei.com> --- fs/overlayfs/super.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c index 45c596dfe3a3..e3cd5a00f880 100644 --- a/fs/overlayfs/super.c +++ b/fs/overlayfs/super.c @@ -138,11 +138,16 @@ static int ovl_dentry_revalidate_common(struct dentry *dentry, unsigned int flags, bool weak) { struct ovl_entry *oe = dentry->d_fsdata; + struct inode *inode = d_inode_rcu(dentry); struct dentry *upper; unsigned int i; int ret = 1; - upper = ovl_dentry_upper(dentry); + /* Careful in RCU mode */ + if (!inode) + return -ECHILD; + + upper = ovl_i_dentry_upper(inode); if (upper) ret = ovl_revalidate_real(upper, flags, weak); -- 2.25.1

1 29

[PATCH openEuler-5.10-LTS 01/30] ovl: fix use inode directly in rcu-walk mode
by Zheng Zengkai 08 Mar '23

08 Mar '23

From: Chen Zhongjin <chenzhongjin(a)huawei.com> stable inclusion from stable-v5.10.163 commit 740c537f52c1f54aff9094744483d1515c7c8b7b category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I6GCCV Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- commit 672e4268b2863d7e4978dfed29552b31c2f9bd4e upstream. ovl_dentry_revalidate_common() can be called in rcu-walk mode. As document said, "in rcu-walk mode, d_parent and d_inode should not be used without care". Check inode here to protect access under rcu-walk mode. Fixes: bccece1ead36 ("ovl: allow remote upper") Reported-and-tested-by: syzbot+a4055c78774bbf3498bb(a)syzkaller.appspotmail.com Signed-off-by: Chen Zhongjin <chenzhongjin(a)huawei.com> Cc: <stable(a)vger.kernel.org> # v5.7 Signed-off-by: Miklos Szeredi <mszeredi(a)redhat.com> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Zhihao Cheng <chengzhihao1(a)huawei.com> Reviewed-by: Yang Erkun <yangerkun(a)huawei.com> Reviewed-by: Zhang Yi <yi.zhang(a)huawei.com> Signed-off-by: Jialin Zhang <zhangjialin11(a)huawei.com> --- fs/overlayfs/super.c | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c index 45c596dfe3a3..e3cd5a00f880 100644 --- a/fs/overlayfs/super.c +++ b/fs/overlayfs/super.c @@ -138,11 +138,16 @@ static int ovl_dentry_revalidate_common(struct dentry *dentry, unsigned int flags, bool weak) { struct ovl_entry *oe = dentry->d_fsdata; + struct inode *inode = d_inode_rcu(dentry); struct dentry *upper; unsigned int i; int ret = 1; - upper = ovl_dentry_upper(dentry); + /* Careful in RCU mode */ + if (!inode) + return -ECHILD; + + upper = ovl_i_dentry_upper(inode); if (upper) ret = ovl_revalidate_real(upper, flags, weak); -- 2.25.1

1 28

[PATCH openEuler-1.0-LTS 1/2] dhugetlb: use mutex lock in update_reserve_pages()
by Yongqiang Liu 07 Mar '23

07 Mar '23

From: Liu Shixin <liushixin2(a)huawei.com> hulk inclusion category: bugfix bugzilla: 46904, https://gitee.com/openeuler/kernel/issues/I6KOXL CVE: NA -------------------------------- When memory is fragmented, update_reserve_pages() may call migrate_pages() to collect continuous memory. This function can sleep, so we should use mutex lock instead of spin lock. Fixes: 3eb69101b5e6 ("mm: Add two interface for dhugetlb") Signed-off-by: Liu Shixin <liushixin2(a)huawei.com> Reviewed-by: Nanyong Sun <sunnanyong(a)huawei.com> Reviewed-by: tong tiangen <tongtiangen(a)huawei.com> Reviewed-by: Kefeng Wang <wangkefeng.wang(a)huawei.com> Signed-off-by: Yongqiang Liu <liuyongqiang13(a)huawei.com> --- include/linux/hugetlb.h | 2 +- mm/hugetlb.c | 2 +- mm/memcontrol.c | 4 ++-- 3 files changed, 4 insertions(+), 4 deletions(-) diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index d44eea25c0d6..dfd9a8c945e1 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -696,7 +696,7 @@ struct small_page_pool { struct dhugetlb_pool { int nid; spinlock_t lock; - spinlock_t reserved_lock; + struct mutex reserved_lock; atomic_t refcnt; struct mem_cgroup *attach_memcg; diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 9f974270c84d..a468d94bc16a 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -3327,7 +3327,7 @@ struct dhugetlb_pool *hpool_alloc(unsigned long nid) return NULL; spin_lock_init(&hpool->lock); - spin_lock_init(&hpool->reserved_lock); + mutex_init(&hpool->reserved_lock); hpool->nid = nid; atomic_set(&hpool->refcnt, 1); INIT_LIST_HEAD(&hpool->dhugetlb_1G_freelists); diff --git a/mm/memcontrol.c b/mm/memcontrol.c index fd40fef49e45..886d6b0a4fce 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -4950,9 +4950,9 @@ static int update_reserve_pages(struct kernfs_open_file *of, hpool = get_dhugetlb_pool_from_memcg(memcg); if (!hpool) return -EINVAL; - spin_lock(&hpool->reserved_lock); + mutex_lock(&hpool->reserved_lock); dhugetlb_reserve_hugepages(hpool, size, gigantic); - spin_unlock(&hpool->reserved_lock); + mutex_unlock(&hpool->reserved_lock); dhugetlb_pool_put(hpool); return 0; } -- 2.25.1

1 1

[PATCH openEuler-1.0-LTS 1/2] ntfs: fix use-after-free in ntfs_ucsncmp()
by Yongqiang Liu 07 Mar '23

07 Mar '23

From: ChenXiaoSong <chenxiaosong2(a)huawei.com> stable inclusion from stable-v4.19.254 commit 6c0355ca7ac434d84d8b93336462b698573ca3b3 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I6HWOS CVE: CVE-2023-26607 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?h=… -------------------------------- commit 38c9c22a85aeed28d0831f230136e9cf6fa2ed44 upstream. Syzkaller reported use-after-free bug as follows: ================================================================== BUG: KASAN: use-after-free in ntfs_ucsncmp+0x123/0x130 Read of size 2 at addr ffff8880751acee8 by task a.out/879 CPU: 7 PID: 879 Comm: a.out Not tainted 5.19.0-rc4-next-20220630-00001-gcc5218c8bd2c-dirty #7 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.16.0-0-gd239552ce722-prebuilt.qemu.org 04/01/2014 Call Trace: <TASK> dump_stack_lvl+0x1c0/0x2b0 print_address_description.constprop.0.cold+0xd4/0x484 print_report.cold+0x55/0x232 kasan_report+0xbf/0xf0 ntfs_ucsncmp+0x123/0x130 ntfs_are_names_equal.cold+0x2b/0x41 ntfs_attr_find+0x43b/0xb90 ntfs_attr_lookup+0x16d/0x1e0 ntfs_read_locked_attr_inode+0x4aa/0x2360 ntfs_attr_iget+0x1af/0x220 ntfs_read_locked_inode+0x246c/0x5120 ntfs_iget+0x132/0x180 load_system_files+0x1cc6/0x3480 ntfs_fill_super+0xa66/0x1cf0 mount_bdev+0x38d/0x460 legacy_get_tree+0x10d/0x220 vfs_get_tree+0x93/0x300 do_new_mount+0x2da/0x6d0 path_mount+0x496/0x19d0 __x64_sys_mount+0x284/0x300 do_syscall_64+0x3b/0xc0 entry_SYSCALL_64_after_hwframe+0x46/0xb0 RIP: 0033:0x7f3f2118d9ea Code: 48 8b 0d a9 f4 0b 00 f7 d8 64 89 01 48 83 c8 ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 49 89 ca b8 a5 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d 76 f4 0b 00 f7 d8 64 89 01 48 RSP: 002b:00007ffc269deac8 EFLAGS: 00000202 ORIG_RAX: 00000000000000a5 RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00007f3f2118d9ea RDX: 0000000020000000 RSI: 0000000020000100 RDI: 00007ffc269dec00 RBP: 00007ffc269dec80 R08: 00007ffc269deb00 R09: 00007ffc269dec44 R10: 0000000000000000 R11: 0000000000000202 R12: 000055f81ab1d220 R13: 0000000000000000 R14: 0000000000000000 R15: 0000000000000000 </TASK> The buggy address belongs to the physical page: page:0000000085430378 refcount:1 mapcount:1 mapping:0000000000000000 index:0x555c6a81d pfn:0x751ac memcg:ffff888101f7e180 anon flags: 0xfffffc00a0014(uptodate|lru|mappedtodisk|swapbacked|node=0|zone=1|lastcpupid=0x1fffff) raw: 000fffffc00a0014 ffffea0001bf2988 ffffea0001de2448 ffff88801712e201 raw: 0000000555c6a81d 0000000000000000 0000000100000000 ffff888101f7e180 page dumped because: kasan: bad access detected Memory state around the buggy address: ffff8880751acd80: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ffff8880751ace00: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 >ffff8880751ace80: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ^ ffff8880751acf00: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ffff8880751acf80: 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ================================================================== The reason is that struct ATTR_RECORD->name_offset is 6485, end address of name string is out of bounds. Fix this by adding sanity check on end address of attribute name string. [akpm(a)linux-foundation.org: coding-style cleanups] [chenxiaosong2(a)huawei.com: cleanup suggested by Hawkins Jiawei] Link: https://lkml.kernel.org/r/20220709064511.3304299-1-chenxiaosong2@huawei.com Link: https://lkml.kernel.org/r/20220707105329.4020708-1-chenxiaosong2@huawei.com Signed-off-by: ChenXiaoSong <chenxiaosong2(a)huawei.com> Signed-off-by: Hawkins Jiawei <yin31149(a)gmail.com> Cc: Anton Altaparmakov <anton(a)tuxera.com> Cc: ChenXiaoSong <chenxiaosong2(a)huawei.com> Cc: Yongqiang Liu <liuyongqiang13(a)huawei.com> Cc: Zhang Yi <yi.zhang(a)huawei.com> Cc: Zhang Xiaoxu <zhangxiaoxu5(a)huawei.com> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Long Li <leo.lilong(a)huawei.com> Reviewed-by: Zhang Yi <yi.zhang(a)huawei.com> Reviewed-by: Xiu Jianfeng <xiujianfeng(a)huawei.com> Signed-off-by: Yongqiang Liu <liuyongqiang13(a)huawei.com> --- fs/ntfs/attrib.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/fs/ntfs/attrib.c b/fs/ntfs/attrib.c index 44a39a099b54..62b49197e5f6 100644 --- a/fs/ntfs/attrib.c +++ b/fs/ntfs/attrib.c @@ -606,8 +606,12 @@ static int ntfs_attr_find(const ATTR_TYPE type, const ntfschar *name, a = (ATTR_RECORD*)((u8*)ctx->attr + le32_to_cpu(ctx->attr->length)); for (;; a = (ATTR_RECORD*)((u8*)a + le32_to_cpu(a->length))) { - if ((u8*)a < (u8*)ctx->mrec || (u8*)a > (u8*)ctx->mrec + - le32_to_cpu(ctx->mrec->bytes_allocated)) + u8 *mrec_end = (u8 *)ctx->mrec + + le32_to_cpu(ctx->mrec->bytes_allocated); + u8 *name_end = (u8 *)a + le16_to_cpu(a->name_offset) + + a->name_length * sizeof(ntfschar); + if ((u8*)a < (u8*)ctx->mrec || (u8*)a > mrec_end || + name_end > mrec_end) break; ctx->attr = a; if (unlikely(le32_to_cpu(a->type) > le32_to_cpu(type) || -- 2.25.1

1 1

[PATCH openEuler-1.0-LTS 1/4] tcp: Fix listen() regression in 5.15.88.
by Yongqiang Liu 07 Mar '23

07 Mar '23

From: Kuniyuki Iwashima <kuniyu(a)amazon.com> stable inclusion from stable-v5.15.95 commit fdaf88531cfd17b2a710cceb3141ef6f9085ff40 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I6H3MB CVE: CVE-2023-0461 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… --------------------------- When we backport dadd0dcaa67d ("net/ulp: prevent ULP without clone op from entering the LISTEN status"), we have accidentally backported a part of 7a7160edf1bf ("net: Return errno in sk->sk_prot->get_port().") and removed err = -EADDRINUSE in inet_csk_listen_start(). Thus, listen() no longer returns -EADDRINUSE even if ->get_port() failed as reported in [0]. We set -EADDRINUSE to err just before ->get_port() to fix the regression. [0]: https://lore.kernel.org/stable/EF8A45D0-768A-4CD5-9A8A-0FA6E610ABF7@winter.… Reported-by: Winter <winter(a)winter.cafe> Signed-off-by: Kuniyuki Iwashima <kuniyu(a)amazon.com> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Liu Jian <liujian56(a)huawei.com> Reviewed-by: Yue Haibing <yuehaibing(a)huawei.com> Reviewed-by: Xiu Jianfeng <xiujianfeng(a)huawei.com> Signed-off-by: Yongqiang Liu <liuyongqiang13(a)huawei.com> --- net/ipv4/inet_connection_sock.c | 1 + 1 file changed, 1 insertion(+) diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index f1f3dc6a7d63..0d85871b5cda 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -941,6 +941,7 @@ int inet_csk_listen_start(struct sock *sk, int backlog) * It is OK, because this socket enters to hash table only * after validation is complete. */ + err = -EADDRINUSE; inet_sk_state_store(sk, TCP_LISTEN); if (!sk->sk_prot->get_port(sk, inet->inet_num)) { inet->inet_sport = htons(inet->inet_num); -- 2.25.1

1 3

openEuler Kernel SIG双周例会
by openEuler conference 07 Mar '23

07 Mar '23

您好！ Kernel SIG 邀请您参加 2023-03-10 14:00 召开的Zoom会议(自动录制) 会议主题：openEuler Kernel SIG双周例会会议内容：欢迎您参加 Kernel SIG 双周例会，当前议题： 1. 进展update 2. 议题征集中欢迎大家积极申报议题（新增议题可以直接回复邮件，或录入会议看板）会议链接：https://us06web.zoom.us/j/87191608489?pwd=eG96T0p2Y0NDRUdHOW9SYys5SElTQT09 会议纪要：https://etherpad.openeuler.org/p/Kernel-meetings 温馨提醒：建议接入会议后修改参会人的姓名，也可以使用您在gitee.com的ID 更多资讯尽在：https://openeuler.org/zh/ Hello! openEuler Kernel SIG invites you to attend the Zoom conference(auto recording) will be held at 2023-03-10 14:00, The subject of the conference is openEuler Kernel SIG双周例会, Summary: 欢迎您参加 Kernel SIG 双周例会，当前议题： 1. 进展update 2. 议题征集中欢迎大家积极申报议题（新增议题可以直接回复邮件，或录入会议看板） You can join the meeting at https://us06web.zoom.us/j/87191608489?pwd=eG96T0p2Y0NDRUdHOW9SYys5SElTQT09. Add topics at https://etherpad.openeuler.org/p/Kernel-meetings. Note: You are advised to change the participant name after joining the conference or use your ID at gitee.com. More information: https://openeuler.org/en/

1 0

[OLK-5.10] phy: tegra: xusb: Fix return value of tegra_xusb_find_port_node function
by Wang Yufen 06 Mar '23

06 Mar '23

From: Miaoqian Lin <linmq006(a)gmail.com> mainline inclusion from mainline-v5.17-rc1 commit 045a31b95509c8f25f5f04ec5e0dec5cd09f2c5f category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I6IXQP CVE: CVE-2023-23000 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- callers of tegra_xusb_find_port_node() function only do NULL checking for the return value. return NULL instead of ERR_PTR(-ENOMEM) to keep consistent. Signed-off-by: Miaoqian Lin <linmq006(a)gmail.com> Acked-by: Thierry Reding <treding(a)nvidia.com> Link: https://lore.kernel.org/r/20211213020507.1458-1-linmq006@gmail.com Signed-off-by: Vinod Koul <vkoul(a)kernel.org> Signed-off-by: Wang Yufen <wangyufen(a)huawei.com> --- drivers/phy/tegra/xusb.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/phy/tegra/xusb.c b/drivers/phy/tegra/xusb.c index 181a1be..02da8c0 100644 --- a/drivers/phy/tegra/xusb.c +++ b/drivers/phy/tegra/xusb.c @@ -449,7 +449,7 @@ struct tegra_xusb_lane * name = kasprintf(GFP_KERNEL, "%s-%u", type, index); if (!name) { of_node_put(ports); - return ERR_PTR(-ENOMEM); + return NULL; } np = of_get_child_by_name(ports, name); kfree(name); -- 1.8.3.1

1 0

[openEuler-22.03-LTS] phy: tegra: xusb: Fix return value of tegra_xusb_find_port_node function
by Wang Yufen 06 Mar '23

06 Mar '23

From: Miaoqian Lin <linmq006(a)gmail.com> mainline inclusion from mainline-v5.17-rc1 commit 045a31b95509c8f25f5f04ec5e0dec5cd09f2c5f category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I6IXQP CVE: CVE-2023-23000 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- callers of tegra_xusb_find_port_node() function only do NULL checking for the return value. return NULL instead of ERR_PTR(-ENOMEM) to keep consistent. Signed-off-by: Miaoqian Lin <linmq006(a)gmail.com> Acked-by: Thierry Reding <treding(a)nvidia.com> Link: https://lore.kernel.org/r/20211213020507.1458-1-linmq006@gmail.com Signed-off-by: Vinod Koul <vkoul(a)kernel.org> Signed-off-by: Wang Yufen <wangyufen(a)huawei.com> --- drivers/phy/tegra/xusb.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/phy/tegra/xusb.c b/drivers/phy/tegra/xusb.c index 181a1be..02da8c0 100644 --- a/drivers/phy/tegra/xusb.c +++ b/drivers/phy/tegra/xusb.c @@ -449,7 +449,7 @@ struct tegra_xusb_lane * name = kasprintf(GFP_KERNEL, "%s-%u", type, index); if (!name) { of_node_put(ports); - return ERR_PTR(-ENOMEM); + return NULL; } np = of_get_child_by_name(ports, name); kfree(name); -- 1.8.3.1

1 0

[openEuler-1.0-LTS] phy: tegra: xusb: Fix return value of tegra_xusb_find_port_node function
by Wang Yufen 06 Mar '23

06 Mar '23

From: Miaoqian Lin <linmq006(a)gmail.com> mainline inclusion from mainline-v5.17-rc1 commit 045a31b95509c8f25f5f04ec5e0dec5cd09f2c5f category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I6IXQP CVE: CVE-2023-23000 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- callers of tegra_xusb_find_port_node() function only do NULL checking for the return value. return NULL instead of ERR_PTR(-ENOMEM) to keep consistent. Signed-off-by: Miaoqian Lin <linmq006(a)gmail.com> Acked-by: Thierry Reding <treding(a)nvidia.com> Link: https://lore.kernel.org/r/20211213020507.1458-1-linmq006@gmail.com Signed-off-by: Vinod Koul <vkoul(a)kernel.org> Signed-off-by: Wang Yufen <wangyufen(a)huawei.com> --- drivers/phy/tegra/xusb.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/phy/tegra/xusb.c b/drivers/phy/tegra/xusb.c index de1b4eb..9e8fa18 100644 --- a/drivers/phy/tegra/xusb.c +++ b/drivers/phy/tegra/xusb.c @@ -441,7 +441,7 @@ struct tegra_xusb_lane * name = kasprintf(GFP_KERNEL, "%s-%u", type, index); if (!name) { of_node_put(ports); - return ERR_PTR(-ENOMEM); + return NULL; } np = of_get_child_by_name(ports, name); kfree(name); -- 1.8.3.1

1 0

[PATCH openEuler-1.0-LTS 1/4] rds: rds_rm_zerocopy_callback() use list_first_entry()
by Yongqiang Liu 06 Mar '23

06 Mar '23

From: Pietro Borrello <borrello(a)diag.uniroma1.it> stable inclusion from stable-v4.19.273 commit 909d5eef5ce792bb76d7b5a9b7a6852b813d8cac category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I6I7UF CVE: CVE-2023-1078 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… ------------------------------------------------- [ Upstream commit f753a68980cf4b59a80fe677619da2b1804f526d ] rds_rm_zerocopy_callback() uses list_entry() on the head of a list causing a type confusion. Use list_first_entry() to actually access the first element of the rs_zcookie_queue list. Fixes: 9426bbc6de99 ("rds: use list structure to track information for zerocopy completion notification") Reviewed-by: Willem de Bruijn <willemb(a)google.com> Signed-off-by: Pietro Borrello <borrello(a)diag.uniroma1.it> Link: https://lore.kernel.org/r/20230202-rds-zerocopy-v3-1-83b0df974f9a@diag.unir… Signed-off-by: Paolo Abeni <pabeni(a)redhat.com> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Lu Wei <luwei32(a)huawei.com> Reviewed-by: Liu Jian <liujian56(a)huawei.com> Reviewed-by: Wang Weiyang <wangweiyang2(a)huawei.com> Reviewed-by: Yue Haibing <yuehaibing(a)huawei.com> Signed-off-by: Yongqiang Liu <liuyongqiang13(a)huawei.com> --- net/rds/message.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/net/rds/message.c b/net/rds/message.c index 4b00b1152a5f..309b54cc62ae 100644 --- a/net/rds/message.c +++ b/net/rds/message.c @@ -104,9 +104,9 @@ static void rds_rm_zerocopy_callback(struct rds_sock *rs, spin_lock_irqsave(&q->lock, flags); head = &q->zcookie_head; if (!list_empty(head)) { - info = list_entry(head, struct rds_msg_zcopy_info, - rs_zcookie_next); - if (info && rds_zcookie_add(info, cookie)) { + info = list_first_entry(head, struct rds_msg_zcopy_info, + rs_zcookie_next); + if (rds_zcookie_add(info, cookie)) { spin_unlock_irqrestore(&q->lock, flags); kfree(rds_info_from_znotifier(znotif)); /* caller invokes rds_wake_sk_sleep() */ -- 2.25.1

1 3

[PATCH v7 OLK-5.10 0/8] Add support for hbm memory device and hbm cache
by Zhang Zekun 04 Mar '23

04 Mar '23

v7: - change there is a container(PNP0A06) has a memory device (PNP0C80) before create device attributes under container subsys v6: - get container device form container_subsys v5: - check the container have PNP0C80 before create attribute files v4: - prettify the code v3: - prettify the code - add a hisi_internal.h to hold common code v2: - remove the !adev judge in patch 9, as it will always be true. patch 1-3: Add support for iterate through the child devices in the acpi device. patch 4-9: Add support for hbm memory device and hbm cache support Rafael J. Wysocki (3): ACPI: bus: Introduce acpi_dev_for_each_child() ACPI: bus: Avoid non-ACPI device objects in walks over children ACPI: bus: Export acpi_dev_for_each_child() to modules Zhang Zekun (5): ACPI: OSL: Export the symbol of acpi_hotplug_schedule soc: hisilicon: hisi_hbmdev: Add power domain control methods ACPI: memhotplug: export the state of each hotplug device soc: hisilicon: hisi_hbmdev: Provide extra memory topology information soc: hbmcache: Add support for online and offline the hbm cache drivers/acpi/acpi_memhotplug.c | 6 + drivers/acpi/bus.c | 27 +++ drivers/acpi/internal.h | 1 - drivers/acpi/osl.c | 1 + drivers/base/container.c | 1 + drivers/soc/Kconfig | 1 + drivers/soc/Makefile | 1 + drivers/soc/hisilicon/Kconfig | 33 +++ drivers/soc/hisilicon/Makefile | 4 + drivers/soc/hisilicon/hisi_hbmcache.c | 147 +++++++++++++ drivers/soc/hisilicon/hisi_hbmdev.c | 301 ++++++++++++++++++++++++++ drivers/soc/hisilicon/hisi_internal.h | 31 +++ include/acpi/acpi_bus.h | 2 + include/linux/acpi.h | 1 + include/linux/memory_hotplug.h | 2 + 15 files changed, 558 insertions(+), 1 deletion(-) create mode 100644 drivers/soc/hisilicon/Kconfig create mode 100644 drivers/soc/hisilicon/Makefile create mode 100644 drivers/soc/hisilicon/hisi_hbmcache.c create mode 100644 drivers/soc/hisilicon/hisi_hbmdev.c create mode 100644 drivers/soc/hisilicon/hisi_internal.h -- 2.17.1

1 8

[PATCH v2 OLK-5.10 00/37] backport patches of share_pool and
by Zhang Zekun 04 Mar '23

04 Mar '23

v2: - remove patch "mm/sharepool: Add mg_sp_alloc_nodemask" Chen Jun (3): mm/sharepool: Fix a double free problem caused by init_local_group mm/sharepool: extract group_add_task mm/sharepool: use delete_spg_node to replace some repetitive code Guo Mengqi (1): mm: sharepool: add static modifier to find_spg_node_by_spg() Wang Wensheng (8): mm/sharepool: Fix NULL pointer dereference in mg_sp_group_del_task mm/sharepool: Reorganize create_spg() mm/sharepool: Simplify sp_make_share_k2u() mm/sharepool: Rename sp_group operations mm/sharepool: Simplify sp_unshare_uva() mm/sharepool: Fix null-pointer-deference in sp_free_area mm/sharepool: Modify error message in mg_sp_group_del_task mm/sharepool: Fix double delete list in sp_group_exit Xu Qiang (17): mm/sharepool: Refactoring proc file interface similar code mm/sharepool: Add helper for master_list mm/sharepool: Delete unused spg_id and hugepage_failures. mm/sharepool: Delete unused mm in sp_proc_stat. mm/sharepool: Move spa_num field to sp_group. mm/sharepool: Rename sp_spg_stat to sp_meminfo. mm/sharepool: Split meminfo_update into meminfo_inc_usage and meminfo_dec_usage. mm/sharepool: split meminfo_update_k2u into meminfo_inc_k2u and meminfo_dec_k2u. mm/sharepool: Delete redundant tgid in sp_proc_stat. mm/sharepool: Move comm from sp_proc_stat to sp_group_master. mm/sharepool: replace sp_proc_stat with sp_meminfo. mm/sharepool: Delete unused tgid and spg_id in spg_proc_stat. mm/sharepool: Replace spg_proc_stat with sp_meminfo. mm/sharepool: Add meminfo_alloc_sum_byKB and meminfo_alloc_sum. mm/sharepool: Add meminfo_k2u_size. mm/sharepool: Delete unused kthread_stat. mm/sharepool: Delete redundant size and alloc_size in sp_meminfo. Zhang Zekun (6): perf: hisi: Add configs for PMU isolation driver: Add CONFIG_ACPI_APEI_GHES_TS_CORE for code isolation ACPI / APEI: Add config to isolate Notify all ras err vmalloc: Add config for Extend for hugepages mapping iommu/arm-smmu-v3: Add config to Add support for suspend and resume hugetlbfs: Add config to isolate the code of share_pool Zhou Guanghui (2): mm/sharepool: Don't display sharepool statistics in the container mm: sharepool: Charge Buddy hugepage to memcg arch/arm64/Kconfig | 2 +- arch/arm64/configs/openeuler_defconfig | 6 + drivers/acpi/apei/Kconfig | 14 + drivers/acpi/apei/ghes.c | 10 +- drivers/iommu/Kconfig | 7 + drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c | 9 +- drivers/perf/hisilicon/Kconfig | 19 + drivers/perf/hisilicon/Makefile | 6 +- fs/hugetlbfs/inode.c | 21 +- include/acpi/ghes.h | 2 + include/linux/cper.h | 3 + include/linux/mm.h | 2 + include/linux/vmalloc.h | 7 + mm/Kconfig | 6 + mm/hugetlb.c | 2 + mm/share_pool.c | 1027 ++++++++----------- mm/share_pool_internal.h | 22 + mm/vmalloc.c | 16 + 18 files changed, 569 insertions(+), 612 deletions(-) create mode 100644 mm/share_pool_internal.h -- 2.17.1

1 37

Re: [PATCH v5 OLK-5.10 5/8] soc: hisilicon: hisi_hbmdev: Add power domain control methods
by zhangzekun (A) 03 Mar '23

03 Mar '23

在 2023/3/3 14:19, Kefeng Wang 写道: > > > On 2023/3/3 11:49, Zhang Zekun wrote: >> Offering: HULK >> hulk inclusion >> category: feature >> bugzilla: https://gitee.com/openeuler/kernel/issues/I67QNJ >> CVE: NA >> >> ------------------------------------------------------------------ >> >> Platform devices which supports power control are often required to be >> power off/on together with the devices in the same power domain. >> However, >> there isn't a generic driver that support the power control logic of >> these devices. >> >> ACPI container seems to be a good place to hold these control logic. Add >> platform devices in the same power domain in a ACPI container, we can >> easily get the locality information about these devices and can moniter >> the power of these devices in the same power domain together. >> >> This patch provide three userspace control interface to control the >> power >> of devices together in the container: >> - state: Echo online to state to power up the devices in the >> container and >> then online these devices which will be triggered by BIOS. Echo >> offline >> to the state to offline and eject the child devices in the container >> which are ejectable. >> - pxms: show the pxms of devices which are present in the container. >> >> In our scenario, we need to control the power of HBM memory devices >> which >> can be power consuming and will only be used in some specialized >> scenarios, >> such as HPC. HBM memory devices in a socket are in the same power >> domain, >> and should be power off/on together. We have come up with an idea >> that put >> these power control logic in a specialized driver, but ACPI container >> seems >> to be a more generic place to hold these control logic. >> >> Signed-off-by: Zhang Zekun <zhangzekun11(a)huawei.com> >> --- >> v6: >> - get container dev form container_subsys >> >> v5: >> - check containers have PNP0C80 before create attibute >> files >> >> v4: >> - prettify the code >> >> v3: >> - move the common code to hisi_internal.h >> >> drivers/base/container.c | 1 + >> drivers/soc/Kconfig | 1 + >> drivers/soc/Makefile | 1 + >> drivers/soc/hisilicon/Kconfig | 19 +++ >> drivers/soc/hisilicon/Makefile | 3 + >> drivers/soc/hisilicon/hisi_hbmdev.c | 196 ++++++++++++++++++++++++++ >> drivers/soc/hisilicon/hisi_internal.h | 31 ++++ >> 7 files changed, 252 insertions(+) >> create mode 100644 drivers/soc/hisilicon/Kconfig >> create mode 100644 drivers/soc/hisilicon/Makefile >> create mode 100644 drivers/soc/hisilicon/hisi_hbmdev.c >> create mode 100644 drivers/soc/hisilicon/hisi_internal.h >> >> diff --git a/drivers/base/container.c b/drivers/base/container.c >> index 1ba42d2d3532..12e572d0c69b 100644 >> --- a/drivers/base/container.c >> +++ b/drivers/base/container.c >> @@ -30,6 +30,7 @@ struct bus_type container_subsys = { >> .online = trivial_online, >> .offline = container_offline, >> }; >> +EXPORT_SYMBOL_GPL(container_subsys); >> void __init container_dev_init(void) >> { >> diff --git a/drivers/soc/Kconfig b/drivers/soc/Kconfig >> index 425ab6f7e375..f7c59b063321 100644 >> --- a/drivers/soc/Kconfig >> +++ b/drivers/soc/Kconfig >> @@ -23,5 +23,6 @@ source "drivers/soc/versatile/Kconfig" >> source "drivers/soc/xilinx/Kconfig" >> source "drivers/soc/zte/Kconfig" >> source "drivers/soc/kendryte/Kconfig" >> +source "drivers/soc/hisilicon/Kconfig" >> endmenu >> diff --git a/drivers/soc/Makefile b/drivers/soc/Makefile >> index 36452bed86ef..68f186e00e44 100644 >> --- a/drivers/soc/Makefile >> +++ b/drivers/soc/Makefile >> @@ -29,3 +29,4 @@ obj-$(CONFIG_PLAT_VERSATILE) += versatile/ >> obj-y += xilinx/ >> obj-$(CONFIG_ARCH_ZX) += zte/ >> obj-$(CONFIG_SOC_KENDRYTE) += kendryte/ >> +obj-y += hisilicon/ >> diff --git a/drivers/soc/hisilicon/Kconfig >> b/drivers/soc/hisilicon/Kconfig >> new file mode 100644 >> index 000000000000..497787af004e >> --- /dev/null >> +++ b/drivers/soc/hisilicon/Kconfig >> @@ -0,0 +1,19 @@ >> +# SPDX-License-Identifier: GPL-2.0 >> +# >> +# Hisilicon SoC drivers >> +# >> +menu "Hisilicon SoC driver support" >> + >> +config HISI_HBMDEV >> + tristate "add extra support for hbm memory device" >> + depends on ACPI_HOTPLUG_MEMORY >> + select ACPI_CONTAINER >> + help >> + This driver add extra supports for memory devices. The driver >> + provides methods for userpace to control the power of memory >> + devices in a container. >> + >> + To compile this driver as a module, choose M here: >> + the module will be called hisi_hbmdev. >> + >> +endmenu >> diff --git a/drivers/soc/hisilicon/Makefile >> b/drivers/soc/hisilicon/Makefile >> new file mode 100644 >> index 000000000000..22e87acb1ab3 >> --- /dev/null >> +++ b/drivers/soc/hisilicon/Makefile >> @@ -0,0 +1,3 @@ >> +# SPDX-License-Identifier: GPL-2.0 >> + >> +obj-$(CONFIG_HISI_HBMDEV) += hisi_hbmdev.o >> diff --git a/drivers/soc/hisilicon/hisi_hbmdev.c >> b/drivers/soc/hisilicon/hisi_hbmdev.c >> new file mode 100644 >> index 000000000000..8485efc00684 >> --- /dev/null >> +++ b/drivers/soc/hisilicon/hisi_hbmdev.c >> @@ -0,0 +1,196 @@ >> +// SPDX-License-Identifier: GPL-2.0 >> +/* >> + * Copyright (C) Huawei Technologies Co., Ltd. 2023. All rights >> reserved. >> + */ >> + >> +#include <linux/kobject.h> >> +#include <linux/module.h> >> +#include <linux/nodemask.h> >> +#include <linux/acpi.h> >> +#include <linux/container.h> >> + >> +#include "hisi_internal.h" >> + >> +#define ACPI_MEMORY_DEVICE_HID "PNP0C80" >> +#define ACPI_GENERIC_CONTAINER_DEVICE_HID "PNP0A06" >> + >> +struct memory_dev { >> + struct kobject *memdev_kobj; >> +}; >> + >> +static struct memory_dev *mdev; >> + >> +static int hbmdev_find(struct acpi_device *adev, void *arg) >> +{ >> + const char *hid = acpi_device_hid(adev); >> + bool *found = arg; >> + >> + if (!strcmp(hid, ACPI_MEMORY_DEVICE_HID)) { >> + *found = true; >> + return -1; >> + } >> + >> + return 0; >> +} >> + >> +static bool has_hbmdev(struct device *dev) >> +{ >> + struct acpi_device *adev = ACPI_COMPANION(dev); >> + const char *hid = acpi_device_hid(adev); >> + bool found = false; >> + >> + if (strcmp(hid, ACPI_GENERIC_CONTAINER_DEVICE_HID)) >> + return found; >> + >> + acpi_dev_for_each_child(adev, hbmdev_find, &found); >> + >> + return found; >> +} >> + >> +static int get_pxm(struct acpi_device *acpi_device, void *arg) >> +{ >> + acpi_handle handle = acpi_device->handle; >> + nodemask_t *mask = arg; >> + unsigned long long sta; >> + acpi_status status; >> + int nid; >> + >> + status = acpi_evaluate_integer(handle, "_STA", NULL, &sta); >> + if (ACPI_SUCCESS(status) && (sta & ACPI_STA_DEVICE_ENABLED)) { >> + nid = acpi_get_node(handle); >> + if (nid >= 0) >> + node_set(nid, *mask); >> + } >> + >> + return 0; >> +} >> + >> +static ssize_t pxms_show(struct device *dev, >> + struct device_attribute *attr, >> + char *buf) >> +{ >> + struct acpi_device *adev = ACPI_COMPANION(dev); >> + nodemask_t mask; >> + >> + nodes_clear(mask); >> + acpi_dev_for_each_child(adev, get_pxm, &mask); >> + >> + return sysfs_emit(buf, "%*pbl\n", >> + nodemask_pr_args(&mask)); >> +} >> +static DEVICE_ATTR_RO(pxms); >> + >> +static int memdev_power_on(struct acpi_device *adev) >> +{ >> + acpi_handle handle = adev->handle; >> + acpi_status status; >> + >> + status = acpi_evaluate_object(handle, "_ON", NULL, NULL); >> + if (ACPI_FAILURE(status)) { >> + acpi_handle_warn(handle, "Power on failed (0x%x)\n", status); >> + return -ENODEV; >> + } >> + >> + return 0; >> +} >> + >> +static int eject_device(struct acpi_device *acpi_device, void >> *not_used) >> +{ >> + acpi_object_type unused; >> + acpi_status status; >> + >> + status = acpi_get_type(acpi_device->handle, &unused); >> + if (ACPI_FAILURE(status) || !acpi_device->flags.ejectable) >> + return -ENODEV; >> + >> + get_device(&acpi_device->dev); >> + status = acpi_hotplug_schedule(acpi_device, >> ACPI_OST_EC_OSPM_EJECT); >> + if (ACPI_SUCCESS(status)) >> + return 0; >> + >> + put_device(&acpi_device->dev); >> + acpi_evaluate_ost(acpi_device->handle, ACPI_OST_EC_OSPM_EJECT, >> + ACPI_OST_SC_NON_SPECIFIC_FAILURE, NULL); >> + >> + return status == AE_NO_MEMORY ? -ENOMEM : -EAGAIN; >> +} >> + >> +static int memdev_power_off(struct acpi_device *adev) >> +{ >> + return acpi_dev_for_each_child(adev, eject_device, NULL); >> +} >> + >> +static ssize_t state_store(struct device *dev, struct >> device_attribute *attr, >> + const char *buf, size_t count) >> +{ >> + struct acpi_device *adev = ACPI_COMPANION(dev); >> + const int type = online_type_from_str(buf); >> + int ret = -EINVAL; >> + >> + switch (type) { >> + case STATE_ONLINE: >> + ret = memdev_power_on(adev); >> + break; >> + case STATE_OFFLINE: >> + ret = memdev_power_off(adev); >> + break; >> + default: >> + break; >> + } >> + >> + if (ret) >> + return ret; >> + >> + return count; >> +} >> +static DEVICE_ATTR_WO(state); >> + >> +static int container_add(struct device *dev, void *data) >> +{ >> + if (!has_hbmdev(dev)) >> + return 0; >> + >> + device_create_file(dev, &dev_attr_state); >> + device_create_file(dev, &dev_attr_pxms); >> + >> + return 0; >> +} >> + >> +static int container_remove(struct device *dev, void *data) >> +{ >> + if (!has_hbmdev(dev)) >> + return 0; >> + >> + device_remove_file(dev, &dev_attr_state); >> + device_remove_file(dev, &dev_attr_pxms); >> + >> + return 0; >> +} >> + >> +static int __init mdev_init(void) >> +{ >> + mdev = kzalloc(sizeof(struct memory_dev), GFP_KERNEL); >> + if (!mdev) >> + return -ENOMEM; >> + >> + mdev->memdev_kobj = kobject_create_and_add("hbm_memory", >> kernel_kobj); >> + if (!mdev->memdev_kobj) { >> + kfree(mdev); >> + return -ENOMEM; >> + } >> + >> + bus_for_each_dev(&container_subsys, NULL, NULL, container_add); >> + return 0; >> +} > > 这个还是没有解决是否加载的问题； > 1）通过遍历，你已经拿到了所有的container device， > 后面移除的时候就不需要再次遍历了；这里可以搞个链表； > 2）另外判断是否有hbm，搞个全局变量，如果有了，才继续执行后面的初始化，否则就直接返回了； > 按照这个思路这里可以改成这样： module_init 1. 首先判断所有容器中是否有hbm device，构建链表 2. 如果链表不为空那么执行模块的初始化，创建hbm_memory目录如果链表为空直接返回，释放链表 module_exit 释放链表中的资源，释放链表 >> +module_init(mdev_init); >> + >> +static void __exit mdev_exit(void) >> +{ >> + bus_for_each_dev(&container_subsys, NULL, NULL, container_remove); >> + kobject_put(mdev->memdev_kobj); >> + kfree(mdev); >> +} >> +module_exit(mdev_exit); >> + >> +MODULE_LICENSE("GPL v2"); >> +MODULE_AUTHOR("Zhang Zekun <zhangzekun11(a)huawei.com>"); >> diff --git a/drivers/soc/hisilicon/hisi_internal.h >> b/drivers/soc/hisilicon/hisi_internal.h >> new file mode 100644 >> index 000000000000..5345174f6b84 >> --- /dev/null >> +++ b/drivers/soc/hisilicon/hisi_internal.h >> @@ -0,0 +1,31 @@ >> +/* SPDX-License-Identifier: GPL-2.0 */ >> +/* >> + * Copyright (C) Huawei Technologies Co., Ltd. 2023. All rights >> reserved. >> + */ >> + >> +#ifndef _HISI_INTERNAL_H >> +#define _HISI_INTERNAL_H >> + >> +enum { >> + STATE_ONLINE, >> + STATE_OFFLINE, >> +}; >> + >> +static const char *const online_type_to_str[] = { >> + [STATE_ONLINE] = "online", >> + [STATE_OFFLINE] = "offline", >> +}; >> + >> +static inline int online_type_from_str(const char *str) >> +{ >> + int i; >> + >> + for (i = 0; i < ARRAY_SIZE(online_type_to_str); i++) { >> + if (sysfs_streq(str, online_type_to_str[i])) >> + return i; >> + } >> + >> + return -EINVAL; >> +} >> + >> +#endif

1 0

[PATCH v5 OLK-5.10 0/8] Add support for hbm memory device and hbm cache
by Zhang Zekun 03 Mar '23

03 Mar '23

v6: - get container device form container_subsys v5: - check the container have PNP0C80 before create attribute files v4: - prettify the code v3: - prettify the code - add a hisi_internal.h to hold common code v2: - remove the !adev judge in patch 9, as it will always be true. patch 1-3: Add support for iterate through the child devices in the acpi device. patch 4-9: Add support for hbm memory device and hbm cache support Rafael J. Wysocki (3): ACPI: bus: Introduce acpi_dev_for_each_child() ACPI: bus: Avoid non-ACPI device objects in walks over children ACPI: bus: Export acpi_dev_for_each_child() to modules Zhang Zekun (5): ACPI: OSL: Export the symbol of acpi_hotplug_schedule soc: hisilicon: hisi_hbmdev: Add power domain control methods ACPI: memhotplug: export the state of each hotplug device soc: hisilicon: hisi_hbmdev: Provide extra memory topology information ACPI: hbmcache: Add support for online and offline the hbm cache drivers/acpi/acpi_memhotplug.c | 6 + drivers/acpi/bus.c | 27 +++ drivers/acpi/internal.h | 1 - drivers/acpi/osl.c | 1 + drivers/base/container.c | 1 + drivers/soc/Kconfig | 1 + drivers/soc/Makefile | 1 + drivers/soc/hisilicon/Kconfig | 33 ++++ drivers/soc/hisilicon/Makefile | 4 + drivers/soc/hisilicon/hisi_hbmcache.c | 147 +++++++++++++++ drivers/soc/hisilicon/hisi_hbmdev.c | 257 ++++++++++++++++++++++++++ drivers/soc/hisilicon/hisi_internal.h | 31 ++++ include/acpi/acpi_bus.h | 2 + include/linux/acpi.h | 1 + include/linux/memory_hotplug.h | 2 + 15 files changed, 514 insertions(+), 1 deletion(-) create mode 100644 drivers/soc/hisilicon/Kconfig create mode 100644 drivers/soc/hisilicon/Makefile create mode 100644 drivers/soc/hisilicon/hisi_hbmcache.c create mode 100644 drivers/soc/hisilicon/hisi_hbmdev.c create mode 100644 drivers/soc/hisilicon/hisi_internal.h -- 2.17.1

1 8

[PATCH v5 OLK-5.10 0/9] Add support for hbm memory device and hbm cache
by Zhang Zekun 02 Mar '23

02 Mar '23

v5: - check the container have PNP0C80 before create attribute files v4: - prettify the code v3: - prettify the code - add a hisi_internal.h to hold common code v2: - remove the !adev judge in patch 9, as it will always be true. patch 1-3: Add support for iterate through the child devices in the acpi device. patch 4-9: Add support for hbm memory device and hbm cache support Rafael J. Wysocki (3): ACPI: bus: Introduce acpi_dev_for_each_child() ACPI: bus: Avoid non-ACPI device objects in walks over children ACPI: bus: Export acpi_dev_for_each_child() to modules Zhang Zekun (6): ACPI: container: export the container list in the system ACPI: OSL: Export the symbol of acpi_hotplug_schedule soc: hisilicon: hisi_hbmdev: Add power domain control methods ACPI: memhotplug: export the state of each hotplug device soc: hisilicon: hisi_hbmdev: Provide extra memory topology information ACPI: hbmcache: Add support for online and offline the hbm cache drivers/acpi/acpi_memhotplug.c | 6 + drivers/acpi/bus.c | 27 +++ drivers/acpi/container.c | 51 ++++++ drivers/acpi/internal.h | 1 - drivers/acpi/osl.c | 1 + drivers/soc/Kconfig | 1 + drivers/soc/Makefile | 1 + drivers/soc/hisilicon/Kconfig | 33 ++++ drivers/soc/hisilicon/Makefile | 4 + drivers/soc/hisilicon/hisi_hbmcache.c | 147 ++++++++++++++++ drivers/soc/hisilicon/hisi_hbmdev.c | 245 ++++++++++++++++++++++++++ drivers/soc/hisilicon/hisi_internal.h | 33 ++++ include/acpi/acpi_bus.h | 2 + include/linux/acpi.h | 1 + include/linux/container.h | 8 + include/linux/memory_hotplug.h | 2 + 16 files changed, 562 insertions(+), 1 deletion(-) create mode 100644 drivers/soc/hisilicon/Kconfig create mode 100644 drivers/soc/hisilicon/Makefile create mode 100644 drivers/soc/hisilicon/hisi_hbmcache.c create mode 100644 drivers/soc/hisilicon/hisi_hbmdev.c create mode 100644 drivers/soc/hisilicon/hisi_internal.h -- 2.17.1

1 9

[PATCH v4 OLK-5.10 0/9] Add support for hbm memory device and
by Zhang Zekun 02 Mar '23

02 Mar '23

v4: - prettify the code v3: - prettify the code - add a hisi_internal.h to hold common code v2: - remove the !adev judge in patch 9, as it will always be true. patch 1-3: Add support for iterate through the child devices in the acpi device. patch 4-9: Add support for hbm memory device and hbm cache support Rafael J. Wysocki (3): ACPI: bus: Introduce acpi_dev_for_each_child() ACPI: bus: Avoid non-ACPI device objects in walks over children ACPI: bus: Export acpi_dev_for_each_child() to modules Zhang Zekun (6): ACPI: container: export the container list in the system ACPI: OSL: Export the symbol of acpi_hotplug_schedule soc: hisilicon: hisi_hbmdev: Add power domain control methods ACPI: memhotplug: export the state of each hotplug device soc: hisilicon: hisi_hbmdev: Provide extra memory topology information ACPI: hbmcache: Add support for online and offline the hbm cache drivers/acpi/acpi_memhotplug.c | 6 + drivers/acpi/bus.c | 27 ++++ drivers/acpi/container.c | 51 ++++++ drivers/acpi/internal.h | 1 - drivers/acpi/osl.c | 1 + drivers/soc/Kconfig | 1 + drivers/soc/Makefile | 1 + drivers/soc/hisilicon/Kconfig | 33 ++++ drivers/soc/hisilicon/Makefile | 4 + drivers/soc/hisilicon/hisi_hbmcache.c | 147 +++++++++++++++++ drivers/soc/hisilicon/hisi_hbmdev.c | 218 ++++++++++++++++++++++++++ drivers/soc/hisilicon/hisi_internal.h | 31 ++++ include/acpi/acpi_bus.h | 2 + include/linux/acpi.h | 1 + include/linux/container.h | 8 + include/linux/memory_hotplug.h | 2 + 16 files changed, 533 insertions(+), 1 deletion(-) create mode 100644 drivers/soc/hisilicon/Kconfig create mode 100644 drivers/soc/hisilicon/Makefile create mode 100644 drivers/soc/hisilicon/hisi_hbmcache.c create mode 100644 drivers/soc/hisilicon/hisi_hbmdev.c create mode 100644 drivers/soc/hisilicon/hisi_internal.h -- 2.17.1

1 9

Re: [PATCH v3 OLK-5.10 6/9] soc: hisilicon: hisi_hbmdev: Add power domain control methods
by zhangzekun (A) 02 Mar '23

02 Mar '23

在 2023/3/2 15:12, Kefeng Wang 写道: > > > On 2023/3/2 14:51, Zhang Zekun wrote: >> Offering: HULK >> hulk inclusion >> category: feature >> bugzilla: https://gitee.com/openeuler/kernel/issues/I67QNJ >> CVE: NA >> >> ------------------------------------------------------------------ >> >> Platform devices which supports power control are often required to be >> power off/on together with the devices in the same power domain. >> However, >> there isn't a generic driver that support the power control logic of >> these devices. >> >> ACPI container seems to be a good place to hold these control logic. Add >> platform devices in the same power domain in a ACPI container, we can >> easily get the locality information about these devices and can moniter >> the power of these devices in the same power domain together. >> >> This patch provide three userspace control interface to control the >> power >> of devices together in the container: >> - state: Echo online to state to power up the devices in the >> container and >> then online these devices which will be triggered by BIOS. Echo >> offline >> to the state to offline and eject the child devices in the container >> which are ejectable. >> - pxms: show the pxms of devices which are present in the container. >> >> In our scenario, we need to control the power of HBM memory devices >> which >> can be power consuming and will only be used in some specialized >> scenarios, >> such as HPC. HBM memory devices in a socket are in the same power >> domain, >> and should be power off/on together. We have come up with an idea >> that put >> these power control logic in a specialized driver, but ACPI container >> seems >> to be a more generic place to hold these control logic. >> >> Signed-off-by: Zhang Zekun <zhangzekun11(a)huawei.com> >> --- >> v3: >> - move the common code to hisi_internal.h >> >> drivers/soc/Kconfig | 1 + >> drivers/soc/Makefile | 1 + >> drivers/soc/hisilicon/Kconfig | 19 +++ >> drivers/soc/hisilicon/Makefile | 3 + >> drivers/soc/hisilicon/hisi_hbmdev.c | 166 ++++++++++++++++++++++++++ >> drivers/soc/hisilicon/hisi_internal.h | 31 +++++ >> 6 files changed, 221 insertions(+) >> create mode 100644 drivers/soc/hisilicon/Kconfig >> create mode 100644 drivers/soc/hisilicon/Makefile >> create mode 100644 drivers/soc/hisilicon/hisi_hbmdev.c >> create mode 100644 drivers/soc/hisilicon/hisi_internal.h >> >> diff --git a/drivers/soc/Kconfig b/drivers/soc/Kconfig >> index 425ab6f7e375..f7c59b063321 100644 >> --- a/drivers/soc/Kconfig >> +++ b/drivers/soc/Kconfig >> @@ -23,5 +23,6 @@ source "drivers/soc/versatile/Kconfig" >> source "drivers/soc/xilinx/Kconfig" >> source "drivers/soc/zte/Kconfig" >> source "drivers/soc/kendryte/Kconfig" >> +source "drivers/soc/hisilicon/Kconfig" >> endmenu >> diff --git a/drivers/soc/Makefile b/drivers/soc/Makefile >> index 36452bed86ef..68f186e00e44 100644 >> --- a/drivers/soc/Makefile >> +++ b/drivers/soc/Makefile >> @@ -29,3 +29,4 @@ obj-$(CONFIG_PLAT_VERSATILE) += versatile/ >> obj-y += xilinx/ >> obj-$(CONFIG_ARCH_ZX) += zte/ >> obj-$(CONFIG_SOC_KENDRYTE) += kendryte/ >> +obj-y += hisilicon/ >> diff --git a/drivers/soc/hisilicon/Kconfig >> b/drivers/soc/hisilicon/Kconfig >> new file mode 100644 >> index 000000000000..497787af004e >> --- /dev/null >> +++ b/drivers/soc/hisilicon/Kconfig >> @@ -0,0 +1,19 @@ >> +# SPDX-License-Identifier: GPL-2.0 >> +# >> +# Hisilicon SoC drivers >> +# >> +menu "Hisilicon SoC driver support" >> + >> +config HISI_HBMDEV >> + tristate "add extra support for hbm memory device" >> + depends on ACPI_HOTPLUG_MEMORY >> + select ACPI_CONTAINER >> + help >> + This driver add extra supports for memory devices. The driver >> + provides methods for userpace to control the power of memory >> + devices in a container. >> + >> + To compile this driver as a module, choose M here: >> + the module will be called hisi_hbmdev. >> + >> +endmenu >> diff --git a/drivers/soc/hisilicon/Makefile >> b/drivers/soc/hisilicon/Makefile >> new file mode 100644 >> index 000000000000..22e87acb1ab3 >> --- /dev/null >> +++ b/drivers/soc/hisilicon/Makefile >> @@ -0,0 +1,3 @@ >> +# SPDX-License-Identifier: GPL-2.0 >> + >> +obj-$(CONFIG_HISI_HBMDEV) += hisi_hbmdev.o >> diff --git a/drivers/soc/hisilicon/hisi_hbmdev.c >> b/drivers/soc/hisilicon/hisi_hbmdev.c >> new file mode 100644 >> index 000000000000..82943cd35fa2 >> --- /dev/null >> +++ b/drivers/soc/hisilicon/hisi_hbmdev.c >> @@ -0,0 +1,166 @@ >> +// SPDX-License-Identifier: GPL-2.0 >> +/* >> + * Copyright (C) Huawei Technologies Co., Ltd. 2023. All rights >> reserved. >> + */ >> + >> +#include <linux/kobject.h> >> +#include <linux/module.h> >> +#include <linux/nodemask.h> >> +#include <linux/acpi.h> >> +#include <linux/container.h> >> + >> +#include "hisi_internal.h" >> + >> +struct memory_dev { >> + struct kobject *memdev_kobj; >> +}; >> + >> +static struct memory_dev *mdev; >> + >> +static int get_pxm(struct acpi_device *acpi_device, void *arg) >> +{ >> + int nid; >> + unsigned long long sta; >> + acpi_handle handle; >> + nodemask_t *mask; >> + acpi_status status; >> + >> + mask = arg; >> + handle = acpi_device->handle; > > 按照倒金字塔， > acpi_handle handle = acpi_device->handle; > nodemask_t *mask = arg; > unsigned long long sta; > acpi_status status; > int nid; >> + >> + status = acpi_evaluate_integer(handle, "_STA", NULL, &sta); >> + if (ACPI_SUCCESS(status) && (sta & ACPI_STA_DEVICE_ENABLED)) { >> + nid = acpi_get_node(handle); >> + if (nid >= 0) >> + node_set(nid, *mask); >> + } >> + >> + return 0; >> +} >> + >> +static ssize_t pxms_show(struct device *dev, >> + struct device_attribute *attr, >> + char *buf) >> +{ >> + nodemask_t mask; >> + struct acpi_device *adev; >> + >> + adev = to_acpi_device(dev); > 同上 > >> + nodes_clear(mask); >> + acpi_dev_for_each_child(adev, get_pxm, &mask); >> + >> + return sysfs_emit(buf, "%*pbl\n", >> + nodemask_pr_args(&mask)); >> +} >> +static DEVICE_ATTR_RO(pxms); >> + >> +static int memdev_power_on(struct acpi_device *adev) >> +{ >> + acpi_status status; >> + acpi_handle handle; >> + >> + handle = adev->handle; > ... >> + status = acpi_evaluate_object(handle, "_ON", NULL, NULL); >> + if (ACPI_FAILURE(status)) { >> + acpi_handle_warn(handle, "Power on failed (0x%x)\n", status); >> + return -ENODEV; >> + } >> + >> + return 0; >> +} >> + >> +static int eject_device(struct acpi_device *acpi_device, void >> *not_used) >> +{ >> + acpi_object_type unused; >> + acpi_status status; >> + >> + status = acpi_get_type(acpi_device->handle, &unused); >> + if (ACPI_FAILURE(status) || !acpi_device->flags.ejectable) >> + return -ENODEV; >> + >> + get_device(&acpi_device->dev); >> + status = acpi_hotplug_schedule(acpi_device, >> ACPI_OST_EC_OSPM_EJECT); >> + if (ACPI_SUCCESS(status)) >> + return 0; >> + >> + put_device(&acpi_device->dev); >> + acpi_evaluate_ost(acpi_device->handle, ACPI_OST_EC_OSPM_EJECT, >> + ACPI_OST_SC_NON_SPECIFIC_FAILURE, NULL); >> + >> + return status == AE_NO_MEMORY ? -ENOMEM : -EAGAIN; >> +} >> + >> +static int memdev_power_off(struct acpi_device *adev) >> +{ >> + return acpi_dev_for_each_child(adev, eject_device, NULL); >> +} >> + >> +static ssize_t state_store(struct device *d, struct device_attribute >> *attr, >> + const char *buf, size_t count) >> +{ >> + int ret; >> + struct acpi_device *adev; >> + const int online_type = online_type_from_str(buf); >> + >> + if (online_type < 0) >> + return -EINVAL; >> + >> + adev = to_acpi_device(d); > > > const int online_type = online_type_from_str(buf); > struct acpi_device *adev = to_acpi_device(d); > int ret; > ... > > >> + switch (online_type) { >> + case STATE_ONLINE: >> + ret = memdev_power_on(adev); >> + if (!ret) >> + return count; >> + break; >> + case STATE_OFFLINE: >> + ret = memdev_power_off(adev); >> + if (!ret) >> + return count; >> + break; >> + default: >> + return -EINVAL; >> + } > 这个有点奇怪，hbm cache和mem的热插拔的函数不能搞成类似的逻辑吗这里改成这样吧 { struct acpi_device *adev = to_acpi_device(d); const int type = online_type_from_str(buf); int ret = -EINVAL; switch (type) { case STATE_ONLINE: ret = memdev_power_on(adev); break; case STATE_OFFLINE: ret = memdev_power_off(adev); break; default: break; } if (ret) return ret; return count; } >> + >> + return ret; >> +} >> +static DEVICE_ATTR_WO(state); >> + >> +static int __init mdev_init(void) >> +{ >> + struct cdev_node *cnode; >> + >> + mdev = kzalloc(sizeof(struct memory_dev), GFP_KERNEL); >> + if (!mdev) >> + return -ENOMEM; >> + >> + mdev->memdev_kobj = kobject_create_and_add("hbm_memory", >> kernel_kobj); >> + if (!mdev->memdev_kobj) { >> + kfree(mdev); >> + return -ENOMEM; >> + } >> + >> + list_for_each_entry(cnode, &cdev_list->clist, clist) { >> + device_create_file(cnode->dev, &dev_attr_state); >> + device_create_file(cnode->dev, &dev_attr_pxms); >> + } >> + >> + return 0; >> +} >> +module_init(mdev_init); >> + >> +static void __exit mdev_exit(void) >> +{ >> + struct cdev_node *cnode; >> + >> + list_for_each_entry(cnode, &cdev_list->clist, clist) { >> + device_remove_file(cnode->dev, &dev_attr_state); >> + device_remove_file(cnode->dev, &dev_attr_pxms); >> + } >> + >> + kobject_put(mdev->memdev_kobj); >> + kfree(mdev); >> +} >> +module_exit(mdev_exit); >> + >> +MODULE_LICENSE("GPL v2"); >> +MODULE_AUTHOR("Zhang Zekun <zhangzekun11(a)huawei.com>"); >> diff --git a/drivers/soc/hisilicon/hisi_internal.h >> b/drivers/soc/hisilicon/hisi_internal.h >> new file mode 100644 >> index 000000000000..f14596f58a05 >> --- /dev/null >> +++ b/drivers/soc/hisilicon/hisi_internal.h >> @@ -0,0 +1,31 @@ >> +/* SPDX-License-Identifier: GPL-2.0 */ >> +/* >> + * Copyright (C) Huawei Technologies Co., Ltd. 2023. All rights >> reserved. >> + */ >> + >> +#ifndef _HISI_INTERNAL_H >> +#define _HISI_INTERNAL_H >> + >> +enum { >> + STATE_ONLINE, >> + STATE_OFFLINE, >> +}; >> + >> +static const char *const online_type_to_str[] = { >> + [STATE_ONLINE] = "online", >> + [STATE_OFFLINE] = "offline", >> +}; >> + >> +static int online_type_from_str(const char *str) > 不需要inline吗 >> +{ >> + int i; >> + >> + for (i = 0; i < ARRAY_SIZE(online_type_to_str); i++) { >> + if (sysfs_streq(str, online_type_to_str[i])) >> + return i; >> + } >> + >> + return -EINVAL; >> +} >> + >> +#endif

1 0

[PATCH v3 OLK-5.10 0/9] Add support for hbm memory device and
by Zhang Zekun 02 Mar '23

02 Mar '23

v3: - prettify the code - add a hisi_internal.h to hold common code v2: - remove the !adev judge in patch 9, as it will always be true. patch 1-3: Add support for iterate through the child devices in the acpi device. patch 4-9: Add support for hbm memory device and hbm cache support Rafael J. Wysocki (3): ACPI: bus: Introduce acpi_dev_for_each_child() ACPI: bus: Avoid non-ACPI device objects in walks over children ACPI: bus: Export acpi_dev_for_each_child() to modules Zhang Zekun (6): ACPI: container: export the container list in the system ACPI: OSL: Export the symbol of acpi_hotplug_schedule soc: hisilicon: hisi_hbmdev: Add power domain control methods ACPI: memhotplug: export the state of each hotplug device soc: hisilicon: hisi_hbmdev: Provide extra memory topology information ACPI: hbmcache: Add support for online and offline the hbm cache drivers/acpi/acpi_memhotplug.c | 6 + drivers/acpi/bus.c | 27 +++ drivers/acpi/container.c | 51 ++++++ drivers/acpi/internal.h | 1 - drivers/acpi/osl.c | 1 + drivers/soc/Kconfig | 1 + drivers/soc/Makefile | 1 + drivers/soc/hisilicon/Kconfig | 33 ++++ drivers/soc/hisilicon/Makefile | 4 + drivers/soc/hisilicon/hisi_hbmcache.c | 147 +++++++++++++++++ drivers/soc/hisilicon/hisi_hbmdev.c | 229 ++++++++++++++++++++++++++ drivers/soc/hisilicon/hisi_internal.h | 31 ++++ include/acpi/acpi_bus.h | 2 + include/linux/acpi.h | 1 + include/linux/container.h | 8 + include/linux/memory_hotplug.h | 2 + 16 files changed, 544 insertions(+), 1 deletion(-) create mode 100644 drivers/soc/hisilicon/Kconfig create mode 100644 drivers/soc/hisilicon/Makefile create mode 100644 drivers/soc/hisilicon/hisi_hbmcache.c create mode 100644 drivers/soc/hisilicon/hisi_hbmdev.c create mode 100644 drivers/soc/hisilicon/hisi_internal.h -- 2.17.1

1 9

[PATCH] Revert "scsi: fix iscsi rescan fails to create block"
by Zhong Jinghua 02 Mar '23

02 Mar '23

hulk inclusion category: bugfix bugzilla: 188150, https://gitee.com/openeuler/kernel/issues/I643OL ---------------------------------------- This reverts commit 7f10ea522db56188ae46c5bbee7052a2b2797515. This commit has a soft lock problem: watchdog: BUG: soft lockup - CPU#22 stuck for 67s! [iscsid:16369] Call Trace: scsi_remove_target+0x548/0x7b0 ? sdev_store_delete+0x90/0x90 ? __mutex_lock_slowpath+0x10/0x10 ? device_remove_class_symlinks+0x1b0/0x1b0 __iscsi_unbind_session+0x16b/0x250 [scsi_transport_iscsi] iscsi_remove_session+0x1d3/0x2f0 [scsi_transport_iscsi] iscsi_session_remove+0x5c/0x80 [libiscsi] iscsi_sw_tcp_session_destroy+0xd3/0x160 [iscsi_tcp] iscsi_if_rx+0x2369/0x5060 [scsi_transport_iscsi] The reason is that if other threads hold the reference count of the kobject while waiting for the device to be released, it will keep waiting in a loop. Fixes: 7f10ea522db5 ("scsi: fix iscsi rescan fails to create block") Signed-off-by: Zhong Jinghua <zhongjinghua(a)huawei.com> --- drivers/scsi/scsi_sysfs.c | 11 +++-------- 1 file changed, 3 insertions(+), 8 deletions(-) diff --git a/drivers/scsi/scsi_sysfs.c b/drivers/scsi/scsi_sysfs.c index 4468b92bf83b..6433476d3e67 100644 --- a/drivers/scsi/scsi_sysfs.c +++ b/drivers/scsi/scsi_sysfs.c @@ -1507,13 +1507,6 @@ void scsi_remove_device(struct scsi_device *sdev) } EXPORT_SYMBOL(scsi_remove_device); -static int scsi_device_try_get(struct scsi_device *sdev) -{ - if (!kobject_get_unless_zero(&sdev->sdev_gendev.kobj)) - return -ENXIO; - return 0; -} - static void __scsi_remove_target(struct scsi_target *starget) { struct Scsi_Host *shost = dev_to_shost(starget->dev.parent); @@ -1532,7 +1525,9 @@ static void __scsi_remove_target(struct scsi_target *starget) if (sdev->channel != starget->channel || sdev->id != starget->id) continue; - if (scsi_device_try_get(sdev)) + if (sdev->sdev_state == SDEV_DEL || + sdev->sdev_state == SDEV_CANCEL || + !get_device(&sdev->sdev_gendev)) continue; spin_unlock_irqrestore(shost->host_lock, flags); scsi_remove_device(sdev); -- 2.31.1

1 0

[OLK-5.10 0/2] Supports the feature of querying stats
by Chengchang Tang 01 Mar '23

01 Mar '23

From: Juan Zhou <zhoujuan51(a)h-partners.com> 1.Support hns HW stats 2.Add dfx cnt stats Chengchang Tang (2): RDMA/hns: Support hns HW stats RDMA/hns: Add dfx cnt stats drivers/infiniband/hw/hns/hns_roce_ah.c | 8 +- drivers/infiniband/hw/hns/hns_roce_cmd.c | 17 ++- drivers/infiniband/hw/hns/hns_roce_cq.c | 17 ++- drivers/infiniband/hw/hns/hns_roce_device.h | 50 +++++++ drivers/infiniband/hw/hns/hns_roce_hw_v2.c | 59 ++++++++ drivers/infiniband/hw/hns/hns_roce_hw_v2.h | 1 + drivers/infiniband/hw/hns/hns_roce_main.c | 146 +++++++++++++++++++- drivers/infiniband/hw/hns/hns_roce_mr.c | 22 ++- drivers/infiniband/hw/hns/hns_roce_pd.c | 10 +- drivers/infiniband/hw/hns/hns_roce_qp.c | 16 ++- drivers/infiniband/hw/hns/hns_roce_srq.c | 7 +- 11 files changed, 320 insertions(+), 33 deletions(-) -- 2.30.0

1 2

[PATCH openEuler-1.0-LTS 1/2] scsi: iscsi_tcp: Fix UAF during logout when accessing the shost ipaddress
by Yongqiang Liu 28 Feb '23

28 Feb '23

From: Mike Christie <michael.christie(a)oracle.com> mainline inclusion from mainline-v6.2-rc6~31 commit 6f1d64b13097e85abda0f91b5638000afc5f9a06 category: bugfix bugzilla: 188443, https://gitee.com/openeuler/kernel/issues/I6I8YD CVE: NA ---------------------------------------- Bug report and analysis from Ding Hui. During iSCSI session logout, if another task accesses the shost ipaddress attr, we can get a KASAN UAF report like this: [ 276.942144] BUG: KASAN: use-after-free in _raw_spin_lock_bh+0x78/0xe0 [ 276.942535] Write of size 4 at addr ffff8881053b45b8 by task cat/4088 [ 276.943511] CPU: 2 PID: 4088 Comm: cat Tainted: G E 6.1.0-rc8+ #3 [ 276.943997] Hardware name: VMware, Inc. VMware Virtual Platform/440BX Desktop Reference Platform, BIOS 6.00 11/12/2020 [ 276.944470] Call Trace: [ 276.944943] <TASK> [ 276.945397] dump_stack_lvl+0x34/0x48 [ 276.945887] print_address_description.constprop.0+0x86/0x1e7 [ 276.946421] print_report+0x36/0x4f [ 276.947358] kasan_report+0xad/0x130 [ 276.948234] kasan_check_range+0x35/0x1c0 [ 276.948674] _raw_spin_lock_bh+0x78/0xe0 [ 276.949989] iscsi_sw_tcp_host_get_param+0xad/0x2e0 [iscsi_tcp] [ 276.951765] show_host_param_ISCSI_HOST_PARAM_IPADDRESS+0xe9/0x130 [scsi_transport_iscsi] [ 276.952185] dev_attr_show+0x3f/0x80 [ 276.953005] sysfs_kf_seq_show+0x1fb/0x3e0 [ 276.953401] seq_read_iter+0x402/0x1020 [ 276.954260] vfs_read+0x532/0x7b0 [ 276.955113] ksys_read+0xed/0x1c0 [ 276.955952] do_syscall_64+0x38/0x90 [ 276.956347] entry_SYSCALL_64_after_hwframe+0x63/0xcd [ 276.956769] RIP: 0033:0x7f5d3a679222 [ 276.957161] Code: c0 e9 b2 fe ff ff 50 48 8d 3d 32 c0 0b 00 e8 a5 fe 01 00 0f 1f 44 00 00 f3 0f 1e fa 64 8b 04 25 18 00 00 00 85 c0 75 10 0f 05 <48> 3d 00 f0 ff ff 77 56 c3 0f 1f 44 00 00 48 83 ec 28 48 89 54 24 [ 276.958009] RSP: 002b:00007ffc864d16a8 EFLAGS: 00000246 ORIG_RAX: 0000000000000000 [ 276.958431] RAX: ffffffffffffffda RBX: 0000000000020000 RCX: 00007f5d3a679222 [ 276.958857] RDX: 0000000000020000 RSI: 00007f5d3a4fe000 RDI: 0000000000000003 [ 276.959281] RBP: 00007f5d3a4fe000 R08: 00000000ffffffff R09: 0000000000000000 [ 276.959682] R10: 0000000000000022 R11: 0000000000000246 R12: 0000000000020000 [ 276.960126] R13: 0000000000000003 R14: 0000000000000000 R15: 0000557a26dada58 [ 276.960536] </TASK> [ 276.961357] Allocated by task 2209: [ 276.961756] kasan_save_stack+0x1e/0x40 [ 276.962170] kasan_set_track+0x21/0x30 [ 276.962557] __kasan_kmalloc+0x7e/0x90 [ 276.962923] __kmalloc+0x5b/0x140 [ 276.963308] iscsi_alloc_session+0x28/0x840 [scsi_transport_iscsi] [ 276.963712] iscsi_session_setup+0xda/0xba0 [libiscsi] [ 276.964078] iscsi_sw_tcp_session_create+0x1fd/0x330 [iscsi_tcp] [ 276.964431] iscsi_if_create_session.isra.0+0x50/0x260 [scsi_transport_iscsi] [ 276.964793] iscsi_if_recv_msg+0xc5a/0x2660 [scsi_transport_iscsi] [ 276.965153] iscsi_if_rx+0x198/0x4b0 [scsi_transport_iscsi] [ 276.965546] netlink_unicast+0x4d5/0x7b0 [ 276.965905] netlink_sendmsg+0x78d/0xc30 [ 276.966236] sock_sendmsg+0xe5/0x120 [ 276.966576] ____sys_sendmsg+0x5fe/0x860 [ 276.966923] ___sys_sendmsg+0xe0/0x170 [ 276.967300] __sys_sendmsg+0xc8/0x170 [ 276.967666] do_syscall_64+0x38/0x90 [ 276.968028] entry_SYSCALL_64_after_hwframe+0x63/0xcd [ 276.968773] Freed by task 2209: [ 276.969111] kasan_save_stack+0x1e/0x40 [ 276.969449] kasan_set_track+0x21/0x30 [ 276.969789] kasan_save_free_info+0x2a/0x50 [ 276.970146] __kasan_slab_free+0x106/0x190 [ 276.970470] __kmem_cache_free+0x133/0x270 [ 276.970816] device_release+0x98/0x210 [ 276.971145] kobject_cleanup+0x101/0x360 [ 276.971462] iscsi_session_teardown+0x3fb/0x530 [libiscsi] [ 276.971775] iscsi_sw_tcp_session_destroy+0xd8/0x130 [iscsi_tcp] [ 276.972143] iscsi_if_recv_msg+0x1bf1/0x2660 [scsi_transport_iscsi] [ 276.972485] iscsi_if_rx+0x198/0x4b0 [scsi_transport_iscsi] [ 276.972808] netlink_unicast+0x4d5/0x7b0 [ 276.973201] netlink_sendmsg+0x78d/0xc30 [ 276.973544] sock_sendmsg+0xe5/0x120 [ 276.973864] ____sys_sendmsg+0x5fe/0x860 [ 276.974248] ___sys_sendmsg+0xe0/0x170 [ 276.974583] __sys_sendmsg+0xc8/0x170 [ 276.974891] do_syscall_64+0x38/0x90 [ 276.975216] entry_SYSCALL_64_after_hwframe+0x63/0xcd We can easily reproduce by two tasks: 1. while :; do iscsiadm -m node --login; iscsiadm -m node --logout; done 2. while :; do cat \ /sys/devices/platform/host*/iscsi_host/host*/ipaddress; done iscsid | cat --------------------------------+--------------------------------------- |- iscsi_sw_tcp_session_destroy | |- iscsi_session_teardown | |- device_release | |- iscsi_session_release ||- dev_attr_show |- kfree | |- show_host_param_ | ISCSI_HOST_PARAM_IPADDRESS | |- iscsi_sw_tcp_host_get_param | |- r/w tcp_sw_host->session (UAF) |- iscsi_host_remove | |- iscsi_host_free | Fix the above bug by splitting the session removal into 2 parts: 1. removal from iSCSI class which includes sysfs and removal from host tracking. 2. freeing of session. During iscsi_tcp host and session removal we can remove the session from sysfs then remove the host from sysfs. At this point we know userspace is not accessing the kernel via sysfs so we can free the session and host. Link: https://lore.kernel.org/r/20230117193937.21244-2-michael.christie@oracle.com Signed-off-by: Mike Christie <michael.christie(a)oracle.com> Reviewed-by: Lee Duncan <lduncan(a)suse.com> Acked-by: Ding Hui <dinghui(a)sangfor.com.cn> Signed-off-by: Martin K. Petersen <martin.petersen(a)oracle.com> Signed-off-by: Wenchao Hao <haowenchao2(a)huawei.com> Signed-off-by: Zhong Jinghua <zhongjinghua(a)huawei.com> Reviewed-by: Hou Tao <houtao1(a)huawei.com> Signed-off-by: Yongqiang Liu <liuyongqiang13(a)huawei.com> --- drivers/scsi/iscsi_tcp.c | 11 +++++++++-- drivers/scsi/libiscsi.c | 39 +++++++++++++++++++++++++++++++-------- include/scsi/libiscsi.h | 2 ++ 3 files changed, 42 insertions(+), 10 deletions(-) diff --git a/drivers/scsi/iscsi_tcp.c b/drivers/scsi/iscsi_tcp.c index 241b1a310519..a5259fd39d6d 100644 --- a/drivers/scsi/iscsi_tcp.c +++ b/drivers/scsi/iscsi_tcp.c @@ -910,10 +910,17 @@ static void iscsi_sw_tcp_session_destroy(struct iscsi_cls_session *cls_session) if (WARN_ON_ONCE(session->leadconn)) return; + iscsi_session_remove(cls_session); + /* + * Our get_host_param needs to access the session, so remove the + * host from sysfs before freeing the session to make sure userspace + * is no longer accessing the callout. + */ + iscsi_host_remove(shost); + iscsi_tcp_r2tpool_free(cls_session->dd_data); - iscsi_session_teardown(cls_session); - iscsi_host_remove(shost); + iscsi_session_free(cls_session); iscsi_host_free(shost); } diff --git a/drivers/scsi/libiscsi.c b/drivers/scsi/libiscsi.c index 9f625a4d53c0..72463874d7b4 100644 --- a/drivers/scsi/libiscsi.c +++ b/drivers/scsi/libiscsi.c @@ -3018,20 +3018,34 @@ iscsi_session_setup(struct iscsi_transport *iscsit, struct Scsi_Host *shost, } EXPORT_SYMBOL_GPL(iscsi_session_setup); +/* + * issi_session_remove - Remove session from iSCSI class. + */ +void iscsi_session_remove(struct iscsi_cls_session *cls_session) +{ + struct iscsi_session *session = cls_session->dd_data; + struct Scsi_Host *shost = session->host; + + iscsi_remove_session(cls_session); + /* + * host removal only has to wait for its children to be removed from + * sysfs, and iscsi_tcp needs to do iscsi_host_remove before freeing + * the session, so drop the session count here. + */ + iscsi_host_dec_session_cnt(shost); +} +EXPORT_SYMBOL_GPL(iscsi_session_remove); + /** - * iscsi_session_teardown - destroy session, host, and cls_session + * iscsi_session_free - Free iscsi session and it's resources * @cls_session: iscsi session */ -void iscsi_session_teardown(struct iscsi_cls_session *cls_session) +void iscsi_session_free(struct iscsi_cls_session *cls_session) { struct iscsi_session *session = cls_session->dd_data; struct module *owner = cls_session->transport->owner; - struct Scsi_Host *shost = session->host; iscsi_pool_free(&session->cmdpool); - - iscsi_remove_session(cls_session); - kfree(session->password); kfree(session->password_in); kfree(session->username); @@ -3047,10 +3061,19 @@ void iscsi_session_teardown(struct iscsi_cls_session *cls_session) kfree(session->discovery_parent_type); iscsi_free_session(cls_session); - - iscsi_host_dec_session_cnt(shost); module_put(owner); } +EXPORT_SYMBOL_GPL(iscsi_session_free); + +/** + * iscsi_session_teardown - destroy session and cls_session + * @cls_session: iscsi session + */ +void iscsi_session_teardown(struct iscsi_cls_session *cls_session) +{ + iscsi_session_remove(cls_session); + iscsi_session_free(cls_session); +} EXPORT_SYMBOL_GPL(iscsi_session_teardown); /** diff --git a/include/scsi/libiscsi.h b/include/scsi/libiscsi.h index 254e72b46d10..2a8d1de70290 100644 --- a/include/scsi/libiscsi.h +++ b/include/scsi/libiscsi.h @@ -425,6 +425,8 @@ extern int iscsi_host_get_max_scsi_cmds(struct Scsi_Host *shost, extern struct iscsi_cls_session * iscsi_session_setup(struct iscsi_transport *, struct Scsi_Host *shost, uint16_t, int, int, uint32_t, unsigned int); +void iscsi_session_remove(struct iscsi_cls_session *cls_session); +void iscsi_session_free(struct iscsi_cls_session *cls_session); extern void iscsi_session_teardown(struct iscsi_cls_session *); extern void iscsi_session_recovery_timedout(struct iscsi_cls_session *); extern int iscsi_set_param(struct iscsi_cls_conn *cls_conn, -- 2.25.1

1 1

[PATCH openEuler-1.0-LTS] pciehp: fix the problem that the slot is powered on again after being powered off
by jiazhenyuan＠uniontech.com 28 Feb '23

28 Feb '23

From: jiazhenyuan <jiazhenyuan(a)uniontech.com> mainline inclusion from mainline-4.19-lts commit 32a8cef274feacd00b748a4f13b84d60aa6d82ff category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I6ICDL CVE: NA ---------------------------------------- The DISABLE_SLOT event is lost when the slot is powered off. Signed-off-by: jiazhenyuan <jiazhenyuan(a)uniontech.com> --- drivers/pci/hotplug/pciehp_ctrl.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/pci/hotplug/pciehp_ctrl.c b/drivers/pci/hotplug/pciehp_ctrl.c index 2d549c97ac42..dd67dc540279 100644 --- a/drivers/pci/hotplug/pciehp_ctrl.c +++ b/drivers/pci/hotplug/pciehp_ctrl.c @@ -463,6 +463,7 @@ int pciehp_sysfs_disable_slot(struct slot *p_slot) mutex_unlock(&p_slot->lock); pci_config_pm_runtime_get(pdev); down_read(&ctrl->reset_lock); + atomic_or(DISABLE_SLOT, &ctrl->pending_events); pciehp_handle_disable_request(p_slot); up_read(&ctrl->reset_lock); pci_config_pm_runtime_put(pdev); -- 2.27.0

1 0

[PATCH openEuler-1.0-LTS] net: mpls: fix stale pointer if allocation fails during device rename
by Yongqiang Liu 28 Feb '23

28 Feb '23

From: Jakub Kicinski <kuba(a)kernel.org> stable inclusion from stable-v4.19.273 commit aa07c86e43ed8780d610ecfb2ce13da326729201 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I6HZHU CVE: CVE-2023-26545 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- commit fda6c89fe3d9aca073495a664e1d5aea28cd4377 upstream. lianhui reports that when MPLS fails to register the sysctl table under new location (during device rename) the old pointers won't get overwritten and may be freed again (double free). Handle this gracefully. The best option would be unregistering the MPLS from the device completely on failure, but unfortunately mpls_ifdown() can fail. So failing fully is also unreliable. Another option is to register the new table first then only remove old one if the new one succeeds. That requires more code, changes order of notifications and two tables may be visible at the same time. sysctl point is not used in the rest of the code - set to NULL on failures and skip unregister if already NULL. Reported-by: lianhui tang <bluetlh(a)gmail.com> Fixes: 0fae3bf018d9 ("mpls: handle device renames for per-device sysctls") Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> Signed-off-by: David S. Miller <davem(a)davemloft.net> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Zhengchao Shao <shaozhengchao(a)huawei.com> Reviewed-by: Liu Jian <liujian56(a)huawei.com> Reviewed-by: Wang Weiyang <wangweiyang2(a)huawei.com> Reviewed-by: Yue Haibing <yuehaibing(a)huawei.com> Signed-off-by: Yongqiang Liu <liuyongqiang13(a)huawei.com> --- net/mpls/af_mpls.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c index 7623d9aec636..c7fd387baa61 100644 --- a/net/mpls/af_mpls.c +++ b/net/mpls/af_mpls.c @@ -1375,6 +1375,7 @@ static int mpls_dev_sysctl_register(struct net_device *dev, free: kfree(table); out: + mdev->sysctl = NULL; return -ENOBUFS; } @@ -1384,6 +1385,9 @@ static void mpls_dev_sysctl_unregister(struct net_device *dev, struct net *net = dev_net(dev); struct ctl_table *table; + if (!mdev->sysctl) + return; + table = mdev->sysctl->ctl_table_arg; unregister_net_sysctl_table(mdev->sysctl); kfree(table); -- 2.25.1

1 0

[PATCH openEuler-5.10-LTS-SP1] net: mpls: fix stale pointer if allocation fails during device rename
by Jialin Zhang 28 Feb '23

28 Feb '23

From: Jakub Kicinski <kuba(a)kernel.org> stable inclusion from stable-v5.10.169 commit 7ff0fdba82298d1f456c685e24930da89703c0fb category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I6HZHU CVE: CVE-2023-26545 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- commit fda6c89fe3d9aca073495a664e1d5aea28cd4377 upstream. lianhui reports that when MPLS fails to register the sysctl table under new location (during device rename) the old pointers won't get overwritten and may be freed again (double free). Handle this gracefully. The best option would be unregistering the MPLS from the device completely on failure, but unfortunately mpls_ifdown() can fail. So failing fully is also unreliable. Another option is to register the new table first then only remove old one if the new one succeeds. That requires more code, changes order of notifications and two tables may be visible at the same time. sysctl point is not used in the rest of the code - set to NULL on failures and skip unregister if already NULL. Reported-by: lianhui tang <bluetlh(a)gmail.com> Fixes: 0fae3bf018d9 ("mpls: handle device renames for per-device sysctls") Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> Signed-off-by: David S. Miller <davem(a)davemloft.net> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Zhengchao Shao <shaozhengchao(a)huawei.com> Reviewed-by: Liu Jian <liujian56(a)huawei.com> Reviewed-by: Wang Weiyang <wangweiyang2(a)huawei.com> Signed-off-by: Jialin Zhang <zhangjialin11(a)huawei.com> --- net/mpls/af_mpls.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c index 72398149e4d4..1dcbdab9319b 100644 --- a/net/mpls/af_mpls.c +++ b/net/mpls/af_mpls.c @@ -1427,6 +1427,7 @@ static int mpls_dev_sysctl_register(struct net_device *dev, free: kfree(table); out: + mdev->sysctl = NULL; return -ENOBUFS; } @@ -1436,6 +1437,9 @@ static void mpls_dev_sysctl_unregister(struct net_device *dev, struct net *net = dev_net(dev); struct ctl_table *table; + if (!mdev->sysctl) + return; + table = mdev->sysctl->ctl_table_arg; unregister_net_sysctl_table(mdev->sysctl); kfree(table); -- 2.25.1

1 0

[PATCH openEuler-5.10-LTS 01/50] Revert "[Huawei] io_uring:drop identity before creating a private one"
by Jialin Zhang 28 Feb '23

28 Feb '23

From: Li Lingfeng <lilingfeng3(a)huawei.com> Offering: HULK hulk inclusion category: feature bugzilla: https://gitee.com/src-openeuler/kernel/issues/I6BTWC ------------------------------- This reverts commit ab45921343c63dc9d461740e23003098697e0333. We need to apply patch 788d0824269bef (io_uring: import 5.15-stable io_uring) to move io_uring to separate directory and solve the problem of CVE-2023-0240. This patch fix a uaf problem of io_identity, and it can be reverted since io_identity is removed in patch 788d0824269bef. Signed-off-by: Li Lingfeng <lilingfeng3(a)huawei.com> Reviewed-by: Zhang Yi <yi.zhang(a)huawei.com> Reviewed-by: Wang Weiyang <wangweiyang2(a)huawei.com> Signed-off-by: Jialin Zhang <zhangjialin11(a)huawei.com> --- fs/io_uring.c | 42 ------------------------------------------ 1 file changed, 42 deletions(-) diff --git a/fs/io_uring.c b/fs/io_uring.c index 4ace89ae4832..2397c2a1d919 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -1364,47 +1364,6 @@ static bool io_identity_cow(struct io_kiocb *req) return true; } -static void io_drop_identity(struct io_kiocb *req) -{ - struct io_identity *id = req->work.identity; - - if (req->work.flags & IO_WQ_WORK_MM) { - mmdrop(id->mm); - req->work.flags &= ~IO_WQ_WORK_MM; - } -#ifdef CONFIG_BLK_CGROUP - if (req->work.flags & IO_WQ_WORK_BLKCG) { - css_put(id->blkcg_css); - req->work.flags &= ~IO_WQ_WORK_BLKCG; - } -#endif - if (req->work.flags & IO_WQ_WORK_CREDS) { - put_cred(id->creds); - req->work.flags &= ~IO_WQ_WORK_CREDS; - } - if (req->work.flags & IO_WQ_WORK_FILES) { - put_files_struct(req->work.identity->files); - put_nsproxy(req->work.identity->nsproxy); - req->work.flags &= ~IO_WQ_WORK_FILES; - } - if (req->work.flags & IO_WQ_WORK_CANCEL) - req->work.flags &= ~IO_WQ_WORK_CANCEL; - if (req->work.flags & IO_WQ_WORK_FS) { - struct fs_struct *fs = id->fs; - - spin_lock(&id->fs->lock); - if (--fs->users) - fs = NULL; - spin_unlock(&id->fs->lock); - - if (fs) - free_fs_struct(fs); - req->work.flags &= ~IO_WQ_WORK_FS; - } - if (req->work.flags & IO_WQ_WORK_FSIZE) - req->work.flags &= ~IO_WQ_WORK_FSIZE; -} - static bool io_grab_identity(struct io_kiocb *req) { const struct io_op_def *def = &io_op_defs[req->opcode]; @@ -1510,7 +1469,6 @@ static void io_prep_async_work(struct io_kiocb *req) if (io_grab_identity(req)) return; - io_drop_identity(req); if (!io_identity_cow(req)) return; -- 2.25.1

1 49

[PATCH openEuler-5.10-LTS-SP1 01/52] Revert "[Huawei] io_uring:drop identity before creating a private one"
by Jialin Zhang 28 Feb '23

28 Feb '23

From: Li Lingfeng <lilingfeng3(a)huawei.com> Offering: HULK hulk inclusion category: feature bugzilla: https://gitee.com/src-openeuler/kernel/issues/I6BTWC ------------------------------- This reverts commit 6d9aaec1edb197ca7e05873c1930c418b7ecaa1e. We need to apply patch 788d0824269bef (io_uring: import 5.15-stable io_uring) to move io_uring to separate directory and solve the problem of CVE-2023-0240. This patch fix a uaf problem of io_identity, and it can be reverted since io_identity is removed in patch 788d0824269bef. Signed-off-by: Li Lingfeng <lilingfeng3(a)huawei.com> Reviewed-by: Zhang Yi <yi.zhang(a)huawei.com> Reviewed-by: Wang Weiyang <wangweiyang2(a)huawei.com> Signed-off-by: Jialin Zhang <zhangjialin11(a)huawei.com> --- fs/io_uring.c | 42 ------------------------------------------ 1 file changed, 42 deletions(-) diff --git a/fs/io_uring.c b/fs/io_uring.c index 21adb7ff7b2e..adb8fcef738a 100644 --- a/fs/io_uring.c +++ b/fs/io_uring.c @@ -1364,47 +1364,6 @@ static bool io_identity_cow(struct io_kiocb *req) return true; } -static void io_drop_identity(struct io_kiocb *req) -{ - struct io_identity *id = req->work.identity; - - if (req->work.flags & IO_WQ_WORK_MM) { - mmdrop(id->mm); - req->work.flags &= ~IO_WQ_WORK_MM; - } -#ifdef CONFIG_BLK_CGROUP - if (req->work.flags & IO_WQ_WORK_BLKCG) { - css_put(id->blkcg_css); - req->work.flags &= ~IO_WQ_WORK_BLKCG; - } -#endif - if (req->work.flags & IO_WQ_WORK_CREDS) { - put_cred(id->creds); - req->work.flags &= ~IO_WQ_WORK_CREDS; - } - if (req->work.flags & IO_WQ_WORK_FILES) { - put_files_struct(req->work.identity->files); - put_nsproxy(req->work.identity->nsproxy); - req->work.flags &= ~IO_WQ_WORK_FILES; - } - if (req->work.flags & IO_WQ_WORK_CANCEL) - req->work.flags &= ~IO_WQ_WORK_CANCEL; - if (req->work.flags & IO_WQ_WORK_FS) { - struct fs_struct *fs = id->fs; - - spin_lock(&id->fs->lock); - if (--fs->users) - fs = NULL; - spin_unlock(&id->fs->lock); - - if (fs) - free_fs_struct(fs); - req->work.flags &= ~IO_WQ_WORK_FS; - } - if (req->work.flags & IO_WQ_WORK_FSIZE) - req->work.flags &= ~IO_WQ_WORK_FSIZE; -} - static bool io_grab_identity(struct io_kiocb *req) { const struct io_op_def *def = &io_op_defs[req->opcode]; @@ -1510,7 +1469,6 @@ static void io_prep_async_work(struct io_kiocb *req) if (io_grab_identity(req)) return; - io_drop_identity(req); if (!io_identity_cow(req)) return; -- 2.25.1

1 51

[PATCH openEuler-1.0-LTS 1/3] selinux: further adjust init order for file_alloc_security hook
by Yongqiang Liu 27 Feb '23

27 Feb '23

From: "GONG, Ruiqi" <gongruiqi1(a)huawei.com> hulk inclusion category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I6DRJ1 CVE: NA ---------------------------------------- After backporting commit cfff75d8973a ("selinux: reorder hooks to make runtime disable less broken") to the 4.19 kernel of openEuler-1.0-LTS, another kernel panic was triggered by running the POC of the aforementioned commit: BUG: unable to handle kernel NULL pointer dereference at 0000000000000008 PGD 800000001840b067 P4D 800000001840b067 PUD 1840c067 PMD 0 Oops: 0002 [#1] SMP PTI CPU: 7 PID: 273 Comm: exe Tainted: G OE 4.19.90+ #6 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS rel-1.15.0-0-g2dd4b9b3f840-prebuilt.qemu.org 04/01/2014 RIP: 0010:selinux_file_open+0x49/0xf0 Code: 00 00 00 65 48 8b 04 25 28 00 00 00 48 89 44 24 20 31 c0 4c 89 e7 e8 a6 ec ff ff 49 8b 44 24 38 48 c7 c7 e0 a5 13 97 8b 40 1c <89> 45 08 e8 6f 80 ff ff ba 02 00 00 00 89 45 0c 8b 43 44 8b 73 40 RSP: 0018:ffffbb7300867ba0 EFLAGS: 00010246 RAX: 0000000000000003 RBX: ffff9dc301961400 RCX: 00000000000081ed RDX: 0000000000000001 RSI: 0000000000000000 RDI: ffffffff9713a5e0 RBP: 0000000000000000 R08: 0000000000000001 R09: ffff9dc301fedcb0 R10: 0000000000000007 R11: 7fffffffffffffff R12: ffff9dc30204fd70 R13: 0000000000000000 R14: ffff9dc301961410 R15: ffffbb7300867c70 FS: 0000000000d258c0(0000) GS:ffff9dc33e9c0000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000008 CR3: 00000000022bc000 CR4: 00000000000006e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: ? generic_permission+0x10a/0x190 security_file_open+0x26/0x90 do_dentry_open+0xd9/0x380 do_last+0x197/0x8d0 path_openat+0x89/0x280 do_filp_open+0x91/0x100 do_open_execat+0x79/0x180 __do_execve_file.isra.0+0x6dd/0x8b0 __x64_sys_execve+0x35/0x40 do_syscall_64+0x63/0x250 ? async_page_fault+0x8/0x30 entry_SYSCALL_64_after_hwframe+0x44/0xa9 RIP: 0033:0x49a5db Code: 41 89 01 eb da 66 2e 0f 1f 84 00 00 00 00 00 f7 d8 64 41 89 01 eb d6 0f 1f 84 00 00 00 00 00 f3 0f 1e fa b8 3b 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 e0 ff ff ff f7 d8 64 89 01 48 RSP: 002b:00007ffe7b1cebd8 EFLAGS: 00000246 ORIG_RAX: 000000000000003b RAX: ffffffffffffffda RBX: 0000000000d27ee0 RCX: 000000000049a5db RDX: 0000000000d27f08 RSI: 0000000000d27ee0 RDI: 0000000000d27f48 RBP: 0000000000d27f48 R08: fefefefefefefeff R09: fefefeff666d686f R10: 0000000000d25b90 R11: 0000000000000246 R12: 0000000000d27f08 R13: 0000000000655894 R14: 0000000000d27f08 R15: 0000000000d26ed0 Modules linked in: e1000(OE) CR2: 0000000000000008 ---[ end trace e4eb884974c22e2d ]--- RIP: 0010:selinux_file_open+0x49/0xf0 Code: 00 00 00 65 48 8b 04 25 28 00 00 00 48 89 44 24 20 31 c0 4c 89 e7 e8 a6 ec ff ff 49 8b 44 24 38 48 c7 c7 e0 a5 13 97 8b 40 1c <89> 45 08 e8 6f 80 ff ff ba 02 00 00 00 89 45 0c 8b 43 44 8b 73 40 RSP: 0018:ffffbb7300867ba0 EFLAGS: 00010246 RAX: 0000000000000003 RBX: ffff9dc301961400 RCX: 00000000000081ed RDX: 0000000000000001 RSI: 0000000000000000 RDI: ffffffff9713a5e0 RBP: 0000000000000000 R08: 0000000000000001 R09: ffff9dc301fedcb0 R10: 0000000000000007 R11: 7fffffffffffffff R12: ffff9dc30204fd70 R13: 0000000000000000 R14: ffff9dc301961410 R15: ffffbb7300867c70 FS: 0000000000d258c0(0000) GS:ffff9dc33e9c0000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000008 CR3: 00000000022bc000 CR4: 00000000000006e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Kernel panic - not syncing: Fatal exception Kernel Offset: 0x14400000 from 0xffffffff81000000 (relocation range: 0xffffffff80000000-0xffffffffbfffffff) ---[ end Kernel panic - not syncing: Fatal exception ]--- The problem was caused by selinux_file_open() accessing a file's fsec being NULL, which indicated that the file_alloc_security hook should be deleted later (at least after the file_open hook) when disabling SELinux at runtime. Here I put it into the "allocating" part. Signed-off-by: GONG, Ruiqi <gongruiqi1(a)huawei.com> Reviewed-by: Wang Weiyang <wangweiyang2(a)huawei.com> Reviewed-by: Xiu Jianfeng <xiujianfeng(a)huawei.com> Signed-off-by: Yongqiang Liu <liuyongqiang13(a)huawei.com> --- security/selinux/hooks.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index cd26c1199353..85ac12d6b2f4 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -7040,7 +7040,6 @@ static struct security_hook_list selinux_hooks[] __lsm_ro_after_init = { LSM_HOOK_INIT(inode_copy_up_xattr, selinux_inode_copy_up_xattr), LSM_HOOK_INIT(file_permission, selinux_file_permission), - LSM_HOOK_INIT(file_alloc_security, selinux_file_alloc_security), LSM_HOOK_INIT(file_free_security, selinux_file_free_security), LSM_HOOK_INIT(file_ioctl, selinux_file_ioctl), LSM_HOOK_INIT(mmap_file, selinux_mmap_file), @@ -7207,6 +7206,7 @@ static struct security_hook_list selinux_hooks[] __lsm_ro_after_init = { LSM_HOOK_INIT(shm_alloc_security, selinux_shm_alloc_security), LSM_HOOK_INIT(sb_alloc_security, selinux_sb_alloc_security), LSM_HOOK_INIT(inode_alloc_security, selinux_inode_alloc_security), + LSM_HOOK_INIT(file_alloc_security, selinux_file_alloc_security), LSM_HOOK_INIT(cred_alloc_blank, selinux_cred_alloc_blank), LSM_HOOK_INIT(sem_alloc_security, selinux_sem_alloc_security), LSM_HOOK_INIT(secid_to_secctx, selinux_secid_to_secctx), -- 2.25.1

1 2

[PATCH openEuler-1.0-LTS 1/1] nbd: fix assignment error for first_minor in nbd_dev_add
by Yongqiang Liu 25 Feb '23

25 Feb '23

From: Zhong Jinghua <zhongjinghua(a)huawei.com> hulk inclusion category: bugfix bugzilla: 188413, https://gitee.com/openeuler/kernel/issues/I6GWYG CVE: NA ---------------------------------------- A panic error is like below: nbd_genl_connect nbd_dev_add first_minor = index << part_shift; // index =-1 ... __device_add_disk blk_alloc_devt *devt = MKDEV(disk->major, disk->first_minor + part->partno); // part->partno = 0， first_minor = 11...110000 major is covered There, index < 0 will reassign an index, but here disk->first_minor is assigned -1 << part_shift. This causes to the creation of the device with the same major and minor device numbers each time the incoming index<0, and this will lead to creation of kobject failed: Warning: kobject_add_internal failed for 4095:1048544 with -EEXIST, don't try to register things with the same name in the same directory. Fix it by moving the first_minor assignment down to after getting the new index. Fixes: 01f7594e62e9 ("nbd: Fix use-after-free in blk_mq_free_rqs") Signed-off-by: Zhong Jinghua <zhongjinghua(a)huawei.com> Reviewed-by: Yu Kuai <yukuai3(a)huawei.com> Reviewed-by: Hou Tao <houtao1(a)huawei.com> Signed-off-by: Yongqiang Liu <liuyongqiang13(a)huawei.com> --- drivers/block/nbd.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c index 8dbbd676d275..551b2f7da8ef 100644 --- a/drivers/block/nbd.c +++ b/drivers/block/nbd.c @@ -1706,7 +1706,6 @@ static int nbd_dev_add(int index) struct gendisk *disk; struct request_queue *q; int err = -ENOMEM; - int first_minor = index << part_shift; nbd = kzalloc(sizeof(struct nbd_device), GFP_KERNEL); if (!nbd) @@ -1770,7 +1769,7 @@ static int nbd_dev_add(int index) refcount_set(&nbd->refs, 1); INIT_LIST_HEAD(&nbd->list); disk->major = NBD_MAJOR; - disk->first_minor = first_minor; + disk->first_minor = index << part_shift; disk->fops = &nbd_fops; disk->private_data = nbd; sprintf(disk->disk_name, "nbd%d", index); -- 2.25.1

2 1

openEuler缺陷issue处理流程_修正
by zhangjialin (F) 23 Feb '23

23 Feb '23

1 0

openEuler缺陷issue处理流程图
by zhangjialin (F) 23 Feb '23

23 Feb '23

1 0

[PATCH openEuler-1.0-LTS 00/13] mainline bugfix backport
by Yongqiang Liu 23 Feb '23

23 Feb '23

*** BLURB HERE *** Andy Shevchenko (1): ipmi: use %*ph to print small buffer Dan Carpenter (1): evm: Fix a small race in init_desc() Eric Biggers (1): crypto: rsa-pkcs1pad - fix buffer overread in pkcs1pad_verify_complete() Greg Kroah-Hartman (1): iommu: Properly export iommu_group_get_for_dev() Herbert Xu (2): crypto: algif_skcipher - EBUSY on aio should be an error crypto: algif_skcipher - Use chunksize instead of blocksize Lubomir Rintel (1): component: do not dereference opaque pointer in debugfs Nishka Dasgupta (2): of: unittest: Add of_node_put() before return of: resolver: Add of_node_put() before return and break Ondrej Mosnacek (1): selinux: reorder hooks to make runtime disable less broken Roberto Sassu (1): evm: Check also if *tfm is an error pointer in init_desc() Will Deacon (2): drivers/iommu: Export core IOMMU API symbols to permit modular drivers drivers/iommu: Allow IOMMU bus ops to be unregistered crypto/algif_skcipher.c | 4 +- crypto/rsa-pkcs1pad.c | 2 + drivers/base/component.c | 8 +-- drivers/char/ipmi/ipmi_msghandler.c | 27 ++------- drivers/iommu/iommu-sysfs.c | 5 ++ drivers/iommu/iommu.c | 12 ++++ drivers/of/resolver.c | 12 +++- drivers/of/unittest.c | 4 +- security/integrity/evm/evm_crypto.c | 45 +++++++------- security/selinux/hooks.c | 93 ++++++++++++++++++++--------- 10 files changed, 129 insertions(+), 83 deletions(-) -- 2.25.1

1 13

openEuler缺陷issue处理流程
by zhangjialin (F) 23 Feb '23

23 Feb '23

1 0

议题征集//答复: openEuler Kernel SIG双周例会
by liaotao (C) 23 Feb '23

23 Feb '23

当前例会议题：议题一：进展update（10min） -- 张伽琳 & 郑增凯议题二：openeuler 实时内核（PREEMPT_RT）规划讨论 --丁翔欢迎大家继续申报~ -----原始约会----- 发件人: openEuler conference <public(a)openeuler.org> 发送时间: 2023年2月21日 10:06 收件人: dev@openeuler.org,kernel-discuss@openeuler.org,kernel@openeuler.org 主题: openEuler Kernel SIG双周例会时间: 2023年2月24日星期五 14:00-15:30(UTC+08:00) 北京，重庆，香港特别行政区，乌鲁木齐。地点: 您好！ Kernel SIG 邀请您参加 2023-02-24 14:00 召开的Zoom会议(自动录制) 会议主题：openEuler Kernel SIG双周例会会议内容：欢迎您参加Kernel SIG双周例会，当前议题： 1. 进展update 2. 议题征集中欢迎大家积极申报议题（新增议题可以直接回复邮件，或录入会议看板）会议链接：https://us06web.zoom.us/j/82111503728?pwd=TWRGa2REc0V2ZmlGZ2ZreUF1OXA3dz09 会议纪要：https://etherpad.openeuler.org/p/Kernel-meetings 温馨提醒：建议接入会议后修改参会人的姓名，也可以使用您在gitee.com的ID 更多资讯尽在：https://openeuler.org/zh/ Hello! openEuler Kernel SIG invites you to attend the Zoom conference(auto recording) will be held at 2023-02-24 14:00, The subject of the conference is openEuler Kernel SIG双周例会, Summary: 欢迎您参加Kernel SIG双周例会，当前议题： 1. 进展update 2. 议题征集中欢迎大家积极申报议题（新增议题可以直接回复邮件，或录入会议看板） You can join the meeting at https://us06web.zoom.us/j/82111503728?pwd=TWRGa2REc0V2ZmlGZ2ZreUF1OXA3dz09. Add topics at https://etherpad.openeuler.org/p/Kernel-meetings. Note: You are advised to change the participant name after joining the conference or use your ID at gitee.com. More information: https://openeuler.org/en/

1 0

[PATCH openEuler-1.0-LTS] dhugetlb: isolate hwpoison hugepage when release
by Yongqiang Liu 23 Feb '23

23 Feb '23

From: Liu Shixin <liushixin2(a)huawei.com> hulk inclusion category: bugfix bugzilla: 46904, https://gitee.com/openeuler/kernel/issues/I6GSKP CVE: NA -------------------------------- For a hwpoison hugetlb page, the page will be freed firstly. If succeed, it will be dissolved and released to buddy system, then isolate the hwpoison page. For a hwpoison hugepage belong to dynamic hugetlb, we isolate the hugepage without dissolve it. Add a check in free_huge_page_to_dhugetlb_pool() to isolate the hwpoison hugepage directly. And keep HUGETLB_PAGE_DTOR after free to ensure the PageHuge() check return true in dissolve_free_huge_page(). Fixes: 0f0535e57da("dhugetlb: skip dissolve hugepage belonging to dynamic hugetlb") Signed-off-by: Liu Shixin <liushixin2(a)huawei.com> Reviewed-by: Kefeng Wang <wangkefeng.wang(a)huawei.com> Signed-off-by: Yongqiang Liu <liuyongqiang13(a)huawei.com> --- mm/hugetlb.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/mm/hugetlb.c b/mm/hugetlb.c index ed89df6fc5de..9f974270c84d 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1348,8 +1348,9 @@ static void free_huge_page_to_dhugetlb_pool(struct page *page, } spin_lock(&hpool->lock); + if (PageHWPoison(page)) + goto out; ClearPagePool(page); - set_compound_page_dtor(page, NULL_COMPOUND_DTOR); if (!hstate_is_gigantic(h)) { list_add(&page->lru, &hpool->dhugetlb_2M_freelists); hpool->free_reserved_2M++; @@ -1375,6 +1376,7 @@ static void free_huge_page_to_dhugetlb_pool(struct page *page, trace_dhugetlb_alloc_free(hpool, page, hpool->free_reserved_1G, DHUGETLB_FREE_1G); } +out: spin_unlock(&hpool->lock); dhugetlb_pool_put(hpool); } -- 2.25.1

1 0

[PATCH openEuler-5.10-LTS-SP1 01/29] media: vivid: fix compose size exceed boundary
by Jialin Zhang 22 Feb '23

22 Feb '23

From: Liu Shixin <liushixin2(a)huawei.com> stable inclusion from stable-v5.10.163 commit f9d19f3a044ca651b0be52a4bf951ffe74259b9f category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I6CIF8 CVE: CVE-2023-0615 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit 94a7ad9283464b75b12516c5512541d467cefcf8 ] syzkaller found a bug: BUG: unable to handle page fault for address: ffffc9000a3b1000 #PF: supervisor write access in kernel mode #PF: error_code(0x0002) - not-present page PGD 100000067 P4D 100000067 PUD 10015f067 PMD 1121ca067 PTE 0 Oops: 0002 [#1] PREEMPT SMP CPU: 0 PID: 23489 Comm: vivid-000-vid-c Not tainted 6.1.0-rc1+ #512 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.13.0-1ubuntu1.1 04/01/2014 RIP: 0010:memcpy_erms+0x6/0x10 [...] Call Trace: <TASK> ? tpg_fill_plane_buffer+0x856/0x15b0 vivid_fillbuff+0x8ac/0x1110 vivid_thread_vid_cap_tick+0x361/0xc90 vivid_thread_vid_cap+0x21a/0x3a0 kthread+0x143/0x180 ret_from_fork+0x1f/0x30 </TASK> This is because we forget to check boundary after adjust compose->height int V4L2_SEL_TGT_CROP case. Add v4l2_rect_map_inside() to fix this problem for this case. Fixes: ef834f7836ec ("[media] vivid: add the video capture and output parts") Signed-off-by: Liu Shixin <liushixin2(a)huawei.com> Signed-off-by: Hans Verkuil <hverkuil-cisco(a)xs4all.nl> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Wang Hai <wanghai38(a)huawei.com> Signed-off-by: Longlong Xia <xialonglong1(a)huawei.com> Reviewed-by: Xiu Jianfeng <xiujianfeng(a)huawei.com> Reviewed-by: Kefeng Wang <wangkefeng.wang(a)huawei.com> Signed-off-by: Jialin Zhang <zhangjialin11(a)huawei.com> --- drivers/media/test-drivers/vivid/vivid-vid-cap.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/media/test-drivers/vivid/vivid-vid-cap.c b/drivers/media/test-drivers/vivid/vivid-vid-cap.c index eadf28ab1e39..eeb0aeb62f79 100644 --- a/drivers/media/test-drivers/vivid/vivid-vid-cap.c +++ b/drivers/media/test-drivers/vivid/vivid-vid-cap.c @@ -953,6 +953,7 @@ int vivid_vid_cap_s_selection(struct file *file, void *fh, struct v4l2_selection if (dev->has_compose_cap) { v4l2_rect_set_min_size(compose, &min_rect); v4l2_rect_set_max_size(compose, &max_rect); + v4l2_rect_map_inside(compose, &fmt); } dev->fmt_cap_rect = fmt; tpg_s_buf_height(&dev->tpg, fmt.height); -- 2.25.1

1 28

[PATCH openEuler-5.10-LTS 01/18] media: vivid: fix compose size exceed boundary
by Jialin Zhang 22 Feb '23

22 Feb '23

From: Liu Shixin <liushixin2(a)huawei.com> stable inclusion from stable-v5.10.163 commit f9d19f3a044ca651b0be52a4bf951ffe74259b9f category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I6CIF8 CVE: CVE-2023-0615 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit 94a7ad9283464b75b12516c5512541d467cefcf8 ] syzkaller found a bug: BUG: unable to handle page fault for address: ffffc9000a3b1000 #PF: supervisor write access in kernel mode #PF: error_code(0x0002) - not-present page PGD 100000067 P4D 100000067 PUD 10015f067 PMD 1121ca067 PTE 0 Oops: 0002 [#1] PREEMPT SMP CPU: 0 PID: 23489 Comm: vivid-000-vid-c Not tainted 6.1.0-rc1+ #512 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.13.0-1ubuntu1.1 04/01/2014 RIP: 0010:memcpy_erms+0x6/0x10 [...] Call Trace: <TASK> ? tpg_fill_plane_buffer+0x856/0x15b0 vivid_fillbuff+0x8ac/0x1110 vivid_thread_vid_cap_tick+0x361/0xc90 vivid_thread_vid_cap+0x21a/0x3a0 kthread+0x143/0x180 ret_from_fork+0x1f/0x30 </TASK> This is because we forget to check boundary after adjust compose->height int V4L2_SEL_TGT_CROP case. Add v4l2_rect_map_inside() to fix this problem for this case. Fixes: ef834f7836ec ("[media] vivid: add the video capture and output parts") Signed-off-by: Liu Shixin <liushixin2(a)huawei.com> Signed-off-by: Hans Verkuil <hverkuil-cisco(a)xs4all.nl> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Wang Hai <wanghai38(a)huawei.com> Signed-off-by: Longlong Xia <xialonglong1(a)huawei.com> Reviewed-by: Xiu Jianfeng <xiujianfeng(a)huawei.com> Reviewed-by: Kefeng Wang <wangkefeng.wang(a)huawei.com> Signed-off-by: Jialin Zhang <zhangjialin11(a)huawei.com> --- drivers/media/test-drivers/vivid/vivid-vid-cap.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/media/test-drivers/vivid/vivid-vid-cap.c b/drivers/media/test-drivers/vivid/vivid-vid-cap.c index eadf28ab1e39..eeb0aeb62f79 100644 --- a/drivers/media/test-drivers/vivid/vivid-vid-cap.c +++ b/drivers/media/test-drivers/vivid/vivid-vid-cap.c @@ -953,6 +953,7 @@ int vivid_vid_cap_s_selection(struct file *file, void *fh, struct v4l2_selection if (dev->has_compose_cap) { v4l2_rect_set_min_size(compose, &min_rect); v4l2_rect_set_max_size(compose, &max_rect); + v4l2_rect_map_inside(compose, &fmt); } dev->fmt_cap_rect = fmt; tpg_s_buf_height(&dev->tpg, fmt.height); -- 2.25.1

1 17

[PATCH openEuler-5.10-LTS 01/18] media: vivid: fix compose size exceed boundary
by Jialin Zhang 22 Feb '23

22 Feb '23

From: Liu Shixin <liushixin2(a)huawei.com> stable inclusion from stable-v5.10.163 commit f9d19f3a044ca651b0be52a4bf951ffe74259b9f category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I6CIF8 CVE: CVE-2023-0615 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit 94a7ad9283464b75b12516c5512541d467cefcf8 ] syzkaller found a bug: BUG: unable to handle page fault for address: ffffc9000a3b1000 #PF: supervisor write access in kernel mode #PF: error_code(0x0002) - not-present page PGD 100000067 P4D 100000067 PUD 10015f067 PMD 1121ca067 PTE 0 Oops: 0002 [#1] PREEMPT SMP CPU: 0 PID: 23489 Comm: vivid-000-vid-c Not tainted 6.1.0-rc1+ #512 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.13.0-1ubuntu1.1 04/01/2014 RIP: 0010:memcpy_erms+0x6/0x10 [...] Call Trace: <TASK> ? tpg_fill_plane_buffer+0x856/0x15b0 vivid_fillbuff+0x8ac/0x1110 vivid_thread_vid_cap_tick+0x361/0xc90 vivid_thread_vid_cap+0x21a/0x3a0 kthread+0x143/0x180 ret_from_fork+0x1f/0x30 </TASK> This is because we forget to check boundary after adjust compose->height int V4L2_SEL_TGT_CROP case. Add v4l2_rect_map_inside() to fix this problem for this case. Fixes: ef834f7836ec ("[media] vivid: add the video capture and output parts") Signed-off-by: Liu Shixin <liushixin2(a)huawei.com> Signed-off-by: Hans Verkuil <hverkuil-cisco(a)xs4all.nl> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Wang Hai <wanghai38(a)huawei.com> Signed-off-by: Longlong Xia <xialonglong1(a)huawei.com> Reviewed-by: Xiu Jianfeng <xiujianfeng(a)huawei.com> Reviewed-by: Kefeng Wang <wangkefeng.wang(a)huawei.com> Signed-off-by: Jialin Zhang <zhangjialin11(a)huawei.com> --- drivers/media/test-drivers/vivid/vivid-vid-cap.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/media/test-drivers/vivid/vivid-vid-cap.c b/drivers/media/test-drivers/vivid/vivid-vid-cap.c index eadf28ab1e39..eeb0aeb62f79 100644 --- a/drivers/media/test-drivers/vivid/vivid-vid-cap.c +++ b/drivers/media/test-drivers/vivid/vivid-vid-cap.c @@ -953,6 +953,7 @@ int vivid_vid_cap_s_selection(struct file *file, void *fh, struct v4l2_selection if (dev->has_compose_cap) { v4l2_rect_set_min_size(compose, &min_rect); v4l2_rect_set_max_size(compose, &max_rect); + v4l2_rect_map_inside(compose, &fmt); } dev->fmt_cap_rect = fmt; tpg_s_buf_height(&dev->tpg, fmt.height); -- 2.25.1

1 17

[PATCH openEuler-5.10-LTS-SP1 01/29] media: vivid: fix compose size exceed boundary
by Jialin Zhang 22 Feb '23

22 Feb '23

From: Liu Shixin <liushixin2(a)huawei.com> stable inclusion from stable-v5.10.163 commit f9d19f3a044ca651b0be52a4bf951ffe74259b9f category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I6CIF8 CVE: CVE-2023-0615 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit 94a7ad9283464b75b12516c5512541d467cefcf8 ] syzkaller found a bug: BUG: unable to handle page fault for address: ffffc9000a3b1000 #PF: supervisor write access in kernel mode #PF: error_code(0x0002) - not-present page PGD 100000067 P4D 100000067 PUD 10015f067 PMD 1121ca067 PTE 0 Oops: 0002 [#1] PREEMPT SMP CPU: 0 PID: 23489 Comm: vivid-000-vid-c Not tainted 6.1.0-rc1+ #512 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.13.0-1ubuntu1.1 04/01/2014 RIP: 0010:memcpy_erms+0x6/0x10 [...] Call Trace: <TASK> ? tpg_fill_plane_buffer+0x856/0x15b0 vivid_fillbuff+0x8ac/0x1110 vivid_thread_vid_cap_tick+0x361/0xc90 vivid_thread_vid_cap+0x21a/0x3a0 kthread+0x143/0x180 ret_from_fork+0x1f/0x30 </TASK> This is because we forget to check boundary after adjust compose->height int V4L2_SEL_TGT_CROP case. Add v4l2_rect_map_inside() to fix this problem for this case. Fixes: ef834f7836ec ("[media] vivid: add the video capture and output parts") Signed-off-by: Liu Shixin <liushixin2(a)huawei.com> Signed-off-by: Hans Verkuil <hverkuil-cisco(a)xs4all.nl> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Wang Hai <wanghai38(a)huawei.com> Signed-off-by: Longlong Xia <xialonglong1(a)huawei.com> Reviewed-by: Xiu Jianfeng <xiujianfeng(a)huawei.com> Reviewed-by: Kefeng Wang <wangkefeng.wang(a)huawei.com> Signed-off-by: Jialin Zhang <zhangjialin11(a)huawei.com> --- drivers/media/test-drivers/vivid/vivid-vid-cap.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/media/test-drivers/vivid/vivid-vid-cap.c b/drivers/media/test-drivers/vivid/vivid-vid-cap.c index eadf28ab1e39..eeb0aeb62f79 100644 --- a/drivers/media/test-drivers/vivid/vivid-vid-cap.c +++ b/drivers/media/test-drivers/vivid/vivid-vid-cap.c @@ -953,6 +953,7 @@ int vivid_vid_cap_s_selection(struct file *file, void *fh, struct v4l2_selection if (dev->has_compose_cap) { v4l2_rect_set_min_size(compose, &min_rect); v4l2_rect_set_max_size(compose, &max_rect); + v4l2_rect_map_inside(compose, &fmt); } dev->fmt_cap_rect = fmt; tpg_s_buf_height(&dev->tpg, fmt.height); -- 2.25.1

1 28

[PATCH openEuler-1.0-LTS] mm/sharepool: Fix null-pointer-deference in sp_free_area
by Yongqiang Liu 22 Feb '23

22 Feb '23

From: Wang Wensheng <wangwensheng4(a)huawei.com> hulk inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I6G76L CVE: NA ---------------------------------------------- When a process is deleted from a group, the process does not apply for memory from the shared group. Otherwise, the UAF problem occurs. We checked this, but it didn't do a good job of preventing sp_alloc and del_task concurrency. The process applies for memory after passing the check, which violates our requirements and causes problems. The solution is to place the checked code in the critical area to ensure that no memory can be allocated after the check is passed. [ T7596] Unable to handle kernel NULL pointer dereference at virtual address 0000000000000098 [ T7596] Mem abort info: [ T7596] ESR = 0x96000004 [ T7596] EC = 0x25: DABT (current EL), IL = 32 bits [ T7596] SET = 0, FnV = 0 [ T7596] EA = 0, S1PTW = 0 [ T7596] Data abort info: [ T7596] ISV = 0, ISS = 0x00000004 [ T7596] CM = 0, WnR = 0 [ T7596] user pgtable: 4k pages, 48-bit VAs, pgdp=00000001040a3000 [ T7596] [0000000000000098] pgd=0000000000000000, p4d=0000000000000000 [ T7596] Internal error: Oops: 96000004 [#1] SMP [ T7596] Modules linked in: sharepool_dev(OE) [last unloaded: demo] [ T7596] CPU: 1 PID: 7596 Comm: test_sp_group_d Tainted: G OE 5.10.0+ #8 [ T7596] Hardware name: linux,dummy-virt (DT) [ T7596] pstate: 20000005 (nzCv daif -PAN -UAO -TCO BTYPE=--) [ T7596] pc : sp_free_area+0x34/0x120 [ T7596] lr : sp_free_area+0x30/0x120 [ T7596] sp : ffff80001c6a3b20 [ T7596] x29: ffff80001c6a3b20 x28: 0000000000000009 [ T7596] x27: 0000000000000000 x26: ffff800011c49d20 [ T7596] x25: ffff0000c227f6c0 x24: 0000000000000008 [ T7596] x23: ffff0000c0cf0ce8 x22: 0000000000000001 [ T7596] x21: ffff0000c4082b30 x20: 0000000000000000 [ T7596] x19: ffff0000c4082b00 x18: 0000000000000000 [ T7596] x17: 0000000000000000 x16: 0000000000000000 [ T7596] x15: 0000000000000000 x14: 0000000000000000 [ T7596] x13: 0000000000000000 x12: ffff0005fffe12c0 [ T7596] x11: 0000000000000008 x10: ffff0005fffe12c0 [ T7596] x9 : ffff8000103eb690 x8 : 0000000000000001 [ T7596] x7 : 0000000000210d00 x6 : 0000000000000000 [ T7596] x5 : ffff8000123edea0 x4 : 0000000000000030 [ T7596] x3 : ffffeff000000000 x2 : 0000eff000000000 [ T7596] x1 : 0000e80000000000 x0 : 0000000000000000 [ T7596] Call trace: [ T7596] sp_free_area+0x34/0x120 [ T7596] __sp_area_drop_locked+0x3c/0x60 [ T7596] sp_area_drop+0x80/0xbc [ T7596] remove_vma+0x54/0x70 [ T7596] exit_mmap+0x114/0x1d0 [ T7596] mmput+0x90/0x1ec [ T7596] exit_mm+0x1d0/0x2f0 [ T7596] do_exit+0x180/0x400 [ T7596] do_group_exit+0x40/0x114 [ T7596] get_signal+0x1e8/0x720 [ T7596] do_signal+0x11c/0x1e4 [ T7596] do_notify_resume+0x15c/0x250 [ T7596] work_pending+0xc/0x6d8 [ T7596] Code: f9400001 f9402c00 97fff0e5 aa0003f4 (f9404c00) [ T7596] ---[ end trace 3c8368d77e758ebd ]--- Signed-off-by: Wang Wensheng <wangwensheng4(a)huawei.com> Reviewed-by: Weilong Chen <chenweilong(a)huawei.com> Signed-off-by: Yongqiang Liu <liuyongqiang13(a)huawei.com> --- mm/share_pool.c | 17 +++++++++-------- 1 file changed, 9 insertions(+), 8 deletions(-) diff --git a/mm/share_pool.c b/mm/share_pool.c index 5d8344fe805a..a136c70b7588 100644 --- a/mm/share_pool.c +++ b/mm/share_pool.c @@ -1712,14 +1712,6 @@ int mg_sp_group_del_task(int pid, int spg_id) ret = -EINVAL; goto out; } - - if (!list_empty(&spg->spa_list)) { - up_write(&sp_group_sem); - pr_err_ratelimited("spa is not empty"); - ret = -EINVAL; - goto out; - } - ret = get_task(pid, &tsk); if (ret) { up_write(&sp_group_sem); @@ -1743,6 +1735,15 @@ int mg_sp_group_del_task(int pid, int spg_id) } down_write(&spg->rw_lock); + + if (!list_empty(&spg->spa_list)) { + up_write(&spg->rw_lock); + up_write(&sp_group_sem); + pr_err_ratelimited("spa is not empty"); + ret = -EINVAL; + goto out_put_mm; + } + if (list_is_singular(&spg->procs)) is_alive = spg->is_alive = false; spg->proc_num--; -- 2.25.1

1 0

openEuler Kernel SIG双周例会
by openEuler conference 21 Feb '23

21 Feb '23

您好！ Kernel SIG 邀请您参加 2023-02-24 14:00 召开的Zoom会议(自动录制) 会议主题：openEuler Kernel SIG双周例会会议内容：欢迎您参加Kernel SIG双周例会，当前议题： 1. 进展update 2. 议题征集中欢迎大家积极申报议题（新增议题可以直接回复邮件，或录入会议看板）会议链接：https://us06web.zoom.us/j/82111503728?pwd=TWRGa2REc0V2ZmlGZ2ZreUF1OXA3dz09 会议纪要：https://etherpad.openeuler.org/p/Kernel-meetings 温馨提醒：建议接入会议后修改参会人的姓名，也可以使用您在gitee.com的ID 更多资讯尽在：https://openeuler.org/zh/ Hello! openEuler Kernel SIG invites you to attend the Zoom conference(auto recording) will be held at 2023-02-24 14:00, The subject of the conference is openEuler Kernel SIG双周例会, Summary: 欢迎您参加Kernel SIG双周例会，当前议题： 1. 进展update 2. 议题征集中欢迎大家积极申报议题（新增议题可以直接回复邮件，或录入会议看板） You can join the meeting at https://us06web.zoom.us/j/82111503728?pwd=TWRGa2REc0V2ZmlGZ2ZreUF1OXA3dz09. Add topics at https://etherpad.openeuler.org/p/Kernel-meetings. Note: You are advised to change the participant name after joining the conference or use your ID at gitee.com. More information: https://openeuler.org/en/

1 0

Intel Arch SIG 例会
by openEuler conference 20 Feb '23

20 Feb '23

您好！ sig-Intel-Arch SIG 邀请您参加 2023-02-21 10:00 召开的Zoom会议会议主题：Intel Arch SIG 例会会议内容： 1. Intel几个复杂特性的支持计划 2. QEMU和kernel选型对未来lntel平台支持和release安排讨论 3. openEuler在SPR上的用户诉求和反馈会议链接：https://us06web.zoom.us/j/87058792984?pwd=UFlzSzA4OHNyMEIvRkpCdWFwdEdRQT09 会议纪要：https://etherpad.openeuler.org/p/sig-Intel-Arch-meetings 温馨提醒：建议接入会议后修改参会人的姓名，也可以使用您在gitee.com的ID 更多资讯尽在：https://openeuler.org/zh/ Hello! openEuler sig-Intel-Arch SIG invites you to attend the Zoom conference will be held at 2023-02-21 10:00, The subject of the conference is Intel Arch SIG 例会, Summary: 1. Intel几个复杂特性的支持计划 2. QEMU和kernel选型对未来lntel平台支持和release安排讨论 3. openEuler在SPR上的用户诉求和反馈 You can join the meeting at https://us06web.zoom.us/j/87058792984?pwd=UFlzSzA4OHNyMEIvRkpCdWFwdEdRQT09. Add topics at https://etherpad.openeuler.org/p/sig-Intel-Arch-meetings. Note: You are advised to change the participant name after joining the conference or use your ID at gitee.com. More information: https://openeuler.org/en/

1 0

None
by guofeng.yang＠amicro.com.cn 20 Feb '23

20 Feb '23

kernel-leave(a)openeuler.org Best Regards 嵌入式软件开发部杨国锋珠海一微半导体股份有限公司 / Amicro Semiconductor Co., Ltd. 横琴总部中心：珠海市横琴新区ICC横琴国际商务中心2座27楼香洲研发中心：香洲区红山路26号阳光大厦13楼深圳办公中心：深圳市南山区国家工程实验室大楼A座1102室电话：0756-2666456 邮编：519000 Phone：18814181955 E-Mail：guofeng.yang(a)amicro.com.cn This email may contain confidential and/or privileged information from Amicro,and is intended solely for the attention and use of the person(s) named above. If you are not the intended recipient (or have received this email in error), please notify the sender immediately and destroy this email. Any unauthorized copying, disclosure or distribution of the material in this email is strictly forbidden. The content provided in this email can not be guaranteed and assured to be accurate, appropriate for all, and complete by Amicro, and Amicro can not be held responsible forany error or negligence derived therefrom. (此电子邮件包含来自一微半导体的信息，而且是机密的或者专用的信息。这些信息是供所有以上列出的个人或者团体使用的。如果您不是此邮件的预期收件人，请勿阅读、复制、转发或存储此邮件。如果已误收此邮件，请通知发件人。本公司不担保本电子邮件中信息的准确性、适当性或完整性，并且对此产生的任何错误或疏忽不承担任何责任.)

1 0

[PATCH openEuler-1.0-LTS 1/5] mm/memcg_memfs_info: fix potential oom_lock recursion deadlock
by Yongqiang Liu 16 Feb '23

16 Feb '23

From: Liu Shixin <liushixin2(a)huawei.com> hulk inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I6AXGS CVE: NA -------------------------------- syzbot is reporting GFP_KERNEL allocation with oom_lock held when reporting memcg OOM [1]. If this allocation triggers the global OOM situation then the system can livelock because the GFP_KERNEL allocation with oom_lock held cannot trigger the global OOM killer because __alloc_pages_may_oom() fails to hold oom_lock. The problem mentioned above has been fixed by patch[2]. The is the same problem in memcg_memfs_info feature too. Refer to the patch[2], fix it by removing the allocation from mem_cgroup_print_memfs_info() completely, and pass static buffer when calling from memcg OOM path. Link: https://syzkaller.appspot.com/bug?extid=2d2aeadc6ce1e1f11d45 [1] Link: https://lkml.kernel.org/r/86afb39f-8c65-bec2-6cfc-c5e3cd600c0b@I-love.SAKUR… [2] Fixes: 6b1d4d3a3713 ("mm/memcg_memfs_info: show files that having pages charged in mem_cgroup") Signed-off-by: Liu Shixin <liushixin2(a)huawei.com> Reviewed-by: Kefeng Wang <wangkefeng.wang(a)huawei.com> Signed-off-by: Yongqiang Liu <liuyongqiang13(a)huawei.com> --- include/linux/memcg_memfs_info.h | 4 +++- mm/memcg_memfs_info.c | 20 ++++++++++---------- mm/memcontrol.c | 3 ++- 3 files changed, 15 insertions(+), 12 deletions(-) diff --git a/include/linux/memcg_memfs_info.h b/include/linux/memcg_memfs_info.h index 658a91e22bd7..b5e3709baa9e 100644 --- a/include/linux/memcg_memfs_info.h +++ b/include/linux/memcg_memfs_info.h @@ -6,11 +6,13 @@ #include <linux/seq_file.h> #ifdef CONFIG_MEMCG_MEMFS_INFO -void mem_cgroup_print_memfs_info(struct mem_cgroup *memcg, struct seq_file *m); +void mem_cgroup_print_memfs_info(struct mem_cgroup *memcg, char *pathbuf, + struct seq_file *m); int mem_cgroup_memfs_files_show(struct seq_file *m, void *v); void mem_cgroup_memfs_info_init(void); #else static inline void mem_cgroup_print_memfs_info(struct mem_cgroup *memcg, + char *pathbuf, struct seq_file *m) { } diff --git a/mm/memcg_memfs_info.c b/mm/memcg_memfs_info.c index 346175026cae..632e03da673b 100644 --- a/mm/memcg_memfs_info.c +++ b/mm/memcg_memfs_info.c @@ -162,7 +162,8 @@ static void memfs_show_files_in_mem_cgroup(struct super_block *sb, void *data) mntput(pfc->vfsmnt); } -void mem_cgroup_print_memfs_info(struct mem_cgroup *memcg, struct seq_file *m) +void mem_cgroup_print_memfs_info(struct mem_cgroup *memcg, char *pathbuf, + struct seq_file *m) { struct print_files_control pfc = { .memcg = memcg, @@ -170,17 +171,11 @@ void mem_cgroup_print_memfs_info(struct mem_cgroup *memcg, struct seq_file *m) .max_print_files = memfs_max_print_files, .size_threshold = memfs_size_threshold, }; - char *pathbuf; int i; if (!memfs_enable || !memcg) return; - pathbuf = kmalloc(PATH_MAX, GFP_KERNEL); - if (!pathbuf) { - SEQ_printf(m, "Show memfs failed due to OOM\n"); - return; - } pfc.pathbuf = pathbuf; pfc.pathbuf_size = PATH_MAX; @@ -197,15 +192,20 @@ void mem_cgroup_print_memfs_info(struct mem_cgroup *memcg, struct seq_file *m) SEQ_printf(m, "total files: %lu, total memory-size: %lukB\n", pfc.total_print_files, pfc.total_files_size >> 10); } - - kfree(pfc.pathbuf); } int mem_cgroup_memfs_files_show(struct seq_file *m, void *v) { struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(m)); + char *pathbuf; - mem_cgroup_print_memfs_info(memcg, m); + pathbuf = kmalloc(PATH_MAX, GFP_KERNEL); + if (!pathbuf) { + SEQ_printf(m, "Show memfs abort: failed to allocate memory\n"); + return 0; + } + mem_cgroup_print_memfs_info(memcg, pathbuf, m); + kfree(pathbuf); return 0; } diff --git a/mm/memcontrol.c b/mm/memcontrol.c index bdc90e6fc082..fd40fef49e45 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -1490,6 +1490,7 @@ void mem_cgroup_print_oom_meminfo(struct mem_cgroup *memcg) { struct mem_cgroup *iter; unsigned int i; + static char pathbuf[PATH_MAX]; pr_info("memory: usage %llukB, limit %llukB, failcnt %lu\n", K((u64)page_counter_read(&memcg->memory)), @@ -1522,7 +1523,7 @@ void mem_cgroup_print_oom_meminfo(struct mem_cgroup *memcg) pr_cont("\n"); } - mem_cgroup_print_memfs_info(memcg, NULL); + mem_cgroup_print_memfs_info(memcg, pathbuf, NULL); } /* -- 2.25.1

1 4

[PATCH openEuler-5.10-LTS-SP1 001/263] KVM: PPC: Book3S HV: Context tracking exit guest context before enabling irqs
by Jialin Zhang 15 Feb '23

15 Feb '23

From: Nicholas Piggin <npiggin(a)gmail.com> stable inclusion from stable-v5.10.145 commit 6bae47548188ae957578e6d92d4b8753dec435e4 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I6D0VF Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit 112665286d08c87e66d699e7cba43c1497ad165f ] Interrupts that occur in kernel mode expect that context tracking is set to kernel. Enabling local irqs before context tracking switches from guest to host means interrupts can come in and trigger warnings about wrong context, and possibly worse. Signed-off-by: Nicholas Piggin <npiggin(a)gmail.com> Signed-off-by: Michael Ellerman <mpe(a)ellerman.id.au> Link: https://lore.kernel.org/r/20210130130852.2952424-3-npiggin@gmail.com Stable-dep-of: 235cee162459 ("KVM: PPC: Tick accounting should defer vtime accounting 'til after IRQ handling") Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Jialin Zhang <zhangjialin11(a)huawei.com> Reviewed-by: Zheng Zengkai <zhengzengkai(a)huawei.com> --- arch/powerpc/kvm/book3s_hv.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c index 38b7a3491aac..d6c4e27f7ed9 100644 --- a/arch/powerpc/kvm/book3s_hv.c +++ b/arch/powerpc/kvm/book3s_hv.c @@ -3399,8 +3399,9 @@ static noinline void kvmppc_run_core(struct kvmppc_vcore *vc) kvmppc_set_host_core(pcpu); + guest_exit_irqoff(); + local_irq_enable(); - guest_exit(); /* Let secondaries go back to the offline loop */ for (i = 0; i < controlled_threads; ++i) { @@ -4235,8 +4236,9 @@ int kvmhv_run_single_vcpu(struct kvm_vcpu *vcpu, u64 time_limit, kvmppc_set_host_core(pcpu); + guest_exit_irqoff(); + local_irq_enable(); - guest_exit(); cpumask_clear_cpu(pcpu, &kvm->arch.cpu_in_guest); -- 2.25.1

1 262

[PATCH openEuler-1.0-LTS 1/2] net: bridge: mcast: add and enforce startup query interval minimum
by Yongqiang Liu 15 Feb '23

15 Feb '23

From: Nikolay Aleksandrov <nikolay(a)nvidia.com> mainline inclusion from mainline-v5.16-rc8 commit f83a112bd91a494cdee671aec74e777470fb4a07 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I6DKZJ CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- As reported[1] if startup query interval is set too low in combination with large number of startup queries and we have multiple bridges or even a single bridge with multiple querier vlans configured we can crash the machine. Add a 1 second minimum which must be enforced by overwriting the value if set lower (i.e. without returning an error) to avoid breaking user-space. If that happens a log message is emitted to let the admin know that the startup interval has been set to the minimum. It doesn't make sense to make the startup interval lower than the normal query interval so use the same value of 1 second. The issue has been present since these intervals could be user-controlled. [1] https://lore.kernel.org/netdev/e8b9ce41-57b9-b6e2-a46a-ff9c791cf0ba@gmail.c… Fixes: d902eee43f19 ("bridge: Add multicast count/interval sysfs entries") Reported-by: Eric Dumazet <eric.dumazet(a)gmail.com> Signed-off-by: Nikolay Aleksandrov <nikolay(a)nvidia.com> Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> Conflicts: net/bridge/br_multicast.c net/bridge/br_netlink.c net/bridge/br_private.h net/bridge/br_sysfs_br.c Signed-off-by: Zhengchao Shao <shaozhengchao(a)huawei.com> Reviewed-by: Yue Haibing <yuehaibing(a)huawei.com> Signed-off-by: Yongqiang Liu <liuyongqiang13(a)huawei.com> --- net/bridge/br_multicast.c | 16 ++++++++++++++++ net/bridge/br_netlink.c | 2 +- net/bridge/br_private.h | 5 +++++ net/bridge/br_sysfs_br.c | 2 +- 4 files changed, 23 insertions(+), 2 deletions(-) diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index 3504c3acd38f..ed67a43efdef 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -2351,6 +2351,22 @@ int br_multicast_set_mld_version(struct net_bridge *br, unsigned long val) } #endif +void br_multicast_set_startup_query_intvl(struct net_bridge *br, + unsigned long val) +{ + unsigned long intvl_jiffies = clock_t_to_jiffies(val); + + if (intvl_jiffies < BR_MULTICAST_STARTUP_QUERY_INTVL_MIN) { + br_info(br, + "trying to set multicast startup query interval below minimum, setting to %lu (%ums)\n", + jiffies_to_clock_t(BR_MULTICAST_STARTUP_QUERY_INTVL_MIN), + jiffies_to_msecs(BR_MULTICAST_STARTUP_QUERY_INTVL_MIN)); + intvl_jiffies = BR_MULTICAST_STARTUP_QUERY_INTVL_MIN; + } + + br->multicast_startup_query_interval = intvl_jiffies; +} + /** * br_multicast_list_adjacent - Returns snooped multicast addresses * @dev: The bridge port adjacent to which to retrieve addresses diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index c00cb376263a..b3bcfb77077a 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -1237,7 +1237,7 @@ static int br_changelink(struct net_device *brdev, struct nlattr *tb[], if (data[IFLA_BR_MCAST_STARTUP_QUERY_INTVL]) { u64 val = nla_get_u64(data[IFLA_BR_MCAST_STARTUP_QUERY_INTVL]); - br->multicast_startup_query_interval = clock_t_to_jiffies(val); + br_multicast_set_startup_query_intvl(br, val); } if (data[IFLA_BR_MCAST_STATS_ENABLED]) { diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 23fed55942fa..877fbc65a2fe 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -31,6 +31,9 @@ #define BR_PORT_BITS 10 #define BR_MAX_PORTS (1<<BR_PORT_BITS) +#define BR_MULTICAST_QUERY_INTVL_MIN msecs_to_jiffies(1000) +#define BR_MULTICAST_STARTUP_QUERY_INTVL_MIN BR_MULTICAST_QUERY_INTVL_MIN + #define BR_VERSION "2.3" /* Control of forwarding link local multicast */ @@ -1200,4 +1203,6 @@ void br_do_proxy_suppress_arp(struct sk_buff *skb, struct net_bridge *br, void br_do_suppress_nd(struct sk_buff *skb, struct net_bridge *br, u16 vid, struct net_bridge_port *p, struct nd_msg *msg); struct nd_msg *br_is_nd_neigh_msg(struct sk_buff *skb, struct nd_msg *m); +void br_multicast_set_startup_query_intvl(struct net_bridge *br, + unsigned long val); #endif diff --git a/net/bridge/br_sysfs_br.c b/net/bridge/br_sysfs_br.c index 0318a69888d4..bfbffc5088ac 100644 --- a/net/bridge/br_sysfs_br.c +++ b/net/bridge/br_sysfs_br.c @@ -618,7 +618,7 @@ static ssize_t multicast_startup_query_interval_show( static int set_startup_query_interval(struct net_bridge *br, unsigned long val) { - br->multicast_startup_query_interval = clock_t_to_jiffies(val); + br_multicast_set_startup_query_intvl(br, val); return 0; } -- 2.25.1

1 1

[PATCH openEuler-5.10-LTS 1/6] cifs: sanitize multiple delimiters in prepath
by Jialin Zhang 14 Feb '23

14 Feb '23

From: Thiago Rafael Becker <trbecker(a)gmail.com> mainline inclusion from mainline-v5.16-rc6 commit a31080899d5fdafcccf7f39dd214a814a2c82626 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I6D6RL CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- mount.cifs can pass a device with multiple delimiters in it. This will cause rename(2) to fail with ENOENT. V2: - Make sanitize_path more readable. - Fix multiple delimiters between UNC and prepath. - Avoid a memory leak if a bad user starts putting a lot of delimiters in the path on purpose. BugLink: https://bugzilla.redhat.com/show_bug.cgi?id=2031200 Fixes: 24e0a1eff9e2 ("cifs: switch to new mount api") Cc: stable(a)vger.kernel.org # 5.11+ Acked-by: Ronnie Sahlberg <lsahlber(a)redhat.com> Signed-off-by: Thiago Rafael Becker <trbecker(a)gmail.com> Signed-off-by: Steve French <stfrench(a)microsoft.com> conflicts: fs/cifs/fs_context.c Signed-off-by: ZhaoLong Wang <wangzhaolong1(a)huawei.com> Reviewed-by: Zhang Xiaoxu <zhangxiaoxu5(a)huawei.com> Signed-off-by: Jialin Zhang <zhangjialin11(a)huawei.com> --- fs/cifs/connect.c | 38 +++++++++++++++++++++++++++++++++++++- 1 file changed, 37 insertions(+), 1 deletion(-) diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c index 7f5d173760cf..0a2eced46e35 100644 --- a/fs/cifs/connect.c +++ b/fs/cifs/connect.c @@ -1316,6 +1316,42 @@ static int get_option_gid(substring_t args[], kgid_t *result) return 0; } +/* + * Remove duplicate path delimiters. Windows is supposed to do that + * but there are some bugs that prevent rename from working if there are + * multiple delimiters. + * + * Returns a sanitized duplicate of @path. The caller is responsible for + * cleaning up the original. + */ +#define IS_DELIM(c) ((c) == '/' || (c) == '\\') +static char *sanitize_path(char *path) +{ + char *cursor1 = path, *cursor2 = path; + + /* skip all prepended delimiters */ + while (IS_DELIM(*cursor1)) + cursor1++; + + /* copy the first letter */ + *cursor2 = *cursor1; + + /* copy the remainder... */ + while (*(cursor1++)) { + /* ... skipping all duplicated delimiters */ + if (IS_DELIM(*cursor1) && IS_DELIM(*cursor2)) + continue; + *(++cursor2) = *cursor1; + } + + /* if the last character is a delimiter, skip it */ + if (IS_DELIM(*(cursor2 - 1))) + cursor2--; + + *(cursor2) = '\0'; + return kstrdup(path, GFP_KERNEL); +} + /* * Parse a devname into substrings and populate the vol->UNC and vol->prepath * fields with the result. Returns 0 on success and an error otherwise. @@ -1364,7 +1400,7 @@ cifs_parse_devname(const char *devname, struct smb_vol *vol) if (!*pos) return 0; - vol->prepath = kstrdup(pos, GFP_KERNEL); + vol->prepath = sanitize_path(pos); if (!vol->prepath) return -ENOMEM; -- 2.25.1

1 5

[PATCH openEuler-5.10-LTS-SP1 1/8] bpf, sockmap: Fix sk->sk_forward_alloc warn_on in sk_stream_kill_queues
by Jialin Zhang 14 Feb '23

14 Feb '23

From: Wang Yufen <wangyufen(a)huawei.com> mainline inclusion from mainline-v6.0-rc1 commit d8616ee2affcff37c5d315310da557a694a3303d category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I6BRTY CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- During TCP sockmap redirect pressure test, the following warning is triggered: WARNING: CPU: 3 PID: 2145 at net/core/stream.c:205 sk_stream_kill_queues+0xbc/0xd0 CPU: 3 PID: 2145 Comm: iperf Kdump: loaded Tainted: G W 5.10.0+ #9 Call Trace: inet_csk_destroy_sock+0x55/0x110 inet_csk_listen_stop+0xbb/0x380 tcp_close+0x41b/0x480 inet_release+0x42/0x80 __sock_release+0x3d/0xa0 sock_close+0x11/0x20 __fput+0x9d/0x240 task_work_run+0x62/0x90 exit_to_user_mode_prepare+0x110/0x120 syscall_exit_to_user_mode+0x27/0x190 entry_SYSCALL_64_after_hwframe+0x44/0xa9 The reason we observed is that: When the listener is closing, a connection may have completed the three-way handshake but not accepted, and the client has sent some packets. The child sks in accept queue release by inet_child_forget()->inet_csk_destroy_sock(), but psocks of child sks have not released. To fix, add sock_map_destroy to release psocks. Signed-off-by: Wang Yufen <wangyufen(a)huawei.com> Signed-off-by: Daniel Borkmann <daniel(a)iogearbox.net> Signed-off-by: Andrii Nakryiko <andrii(a)kernel.org> Acked-by: Jakub Sitnicki <jakub(a)cloudflare.com> Acked-by: John Fastabend <john.fastabend(a)gmail.com> Link: https://lore.kernel.org/bpf/20220524075311.649153-1-wangyufen@huawei.com Signed-off-by: Liu Jian <liujian56(a)huawei.com> Conflicts: include/linux/bpf.h Reviewed-by: Wang Yufen <wangyufen(a)huawei.com> Reviewed-by: Yue Haibing <yuehaibing(a)huawei.com> Signed-off-by: Jialin Zhang <zhangjialin11(a)huawei.com> --- include/linux/bpf.h | 1 + include/linux/skmsg.h | 1 + net/core/skmsg.c | 1 + net/core/sock_map.c | 23 +++++++++++++++++++++++ net/ipv4/tcp_bpf.c | 1 + 5 files changed, 27 insertions(+) diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 8d95f4c66275..79fb7c1be8fd 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -1845,6 +1845,7 @@ static inline bool bpf_map_is_dev_bound(struct bpf_map *map) struct bpf_map *bpf_map_offload_map_alloc(union bpf_attr *attr); void bpf_map_offload_map_free(struct bpf_map *map); +void sock_map_destroy(struct sock *sk); #else static inline int bpf_prog_offload_init(struct bpf_prog *prog, union bpf_attr *attr) diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index 1899a1c8421c..a83885c5bb86 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -105,6 +105,7 @@ struct sk_psock { spinlock_t link_lock; refcount_t refcnt; void (*saved_unhash)(struct sock *sk); + void (*saved_destroy)(struct sock *sk); void (*saved_close)(struct sock *sk, long timeout); void (*saved_write_space)(struct sock *sk); struct proto *sk_proto; diff --git a/net/core/skmsg.c b/net/core/skmsg.c index 622d93d56953..925863fab5bd 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -616,6 +616,7 @@ struct sk_psock *sk_psock_init(struct sock *sk, int node) psock->eval = __SK_NONE; psock->sk_proto = prot; psock->saved_unhash = prot->unhash; + psock->saved_destroy = prot->destroy; psock->saved_close = prot->close; psock->saved_write_space = sk->sk_write_space; diff --git a/net/core/sock_map.c b/net/core/sock_map.c index 28e518da4bcb..85df06298c98 100644 --- a/net/core/sock_map.c +++ b/net/core/sock_map.c @@ -1560,6 +1560,29 @@ void sock_map_unhash(struct sock *sk) saved_unhash(sk); } +void sock_map_destroy(struct sock *sk) +{ + void (*saved_destroy)(struct sock *sk); + struct sk_psock *psock; + + rcu_read_lock(); + psock = sk_psock_get(sk); + if (unlikely(!psock)) { + rcu_read_unlock(); + if (sk->sk_prot->destroy) + sk->sk_prot->destroy(sk); + return; + } + + saved_destroy = psock->saved_destroy; + sock_map_remove_links(sk, psock); + rcu_read_unlock(); + sk_psock_stop(psock, true); + sk_psock_put(sk, psock); + saved_destroy(sk); +} +EXPORT_SYMBOL_GPL(sock_map_destroy); + void sock_map_close(struct sock *sk, long timeout) { void (*saved_close)(struct sock *sk, long timeout); diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c index afeaf35194de..1a8f129fb309 100644 --- a/net/ipv4/tcp_bpf.c +++ b/net/ipv4/tcp_bpf.c @@ -577,6 +577,7 @@ static void tcp_bpf_rebuild_protos(struct proto prot[TCP_BPF_NUM_CFGS], struct proto *base) { prot[TCP_BPF_BASE] = *base; + prot[TCP_BPF_BASE].destroy = sock_map_destroy; prot[TCP_BPF_BASE].close = sock_map_close; prot[TCP_BPF_BASE].recvmsg = tcp_bpf_recvmsg; prot[TCP_BPF_BASE].stream_memory_read = tcp_bpf_stream_read; -- 2.25.1

1 7

[PATCH openEuler-1.0-LTS 1/2] x86/bugs: Flush IBP in ib_prctl_set()
by Yongqiang Liu 14 Feb '23

14 Feb '23

From: Rodrigo Branco <bsdaemon(a)google.com> stable inclusion from stable-v4.19.270 commit 940ede60d74d2fc7291b96cb38072d705333c8e0 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I6CU98 CVE: CVE-2023-0045 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?h=… -------------------------------- commit a664ec9158eeddd75121d39c9a0758016097fa96 upstream. We missed the window between the TIF flag update and the next reschedule. Signed-off-by: Rodrigo Branco <bsdaemon(a)google.com> Reviewed-by: Borislav Petkov (AMD) <bp(a)alien8.de> Signed-off-by: Ingo Molnar <mingo(a)kernel.org> Cc: <stable(a)vger.kernel.org> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Yuyao Lin <linyuyao1(a)huawei.com> Reviewed-by: Wei Li <liwei391(a)huawei.com> Reviewed-by: Xiu Jianfeng <xiujianfeng(a)huawei.com> Signed-off-by: Yongqiang Liu <liuyongqiang13(a)huawei.com> --- arch/x86/kernel/cpu/bugs.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 3ba948bbd77d..d4d114d62e2e 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -1547,6 +1547,8 @@ static int ib_prctl_set(struct task_struct *task, unsigned long ctrl) if (ctrl == PR_SPEC_FORCE_DISABLE) task_set_spec_ib_force_disable(task); task_update_spec_tif(task); + if (task == current) + indirect_branch_prediction_barrier(); break; default: return -ERANGE; -- 2.25.1

1 1

[PATCH] vfio/migration: Modify the vf id acquisition method
by Longfang Liu 14 Feb '23

14 Feb '23

driver inclusion category:feature bugzilla: https://gitee.com/openeuler/kernel/issues/I6DRLU CVE: NA When using the old PCI_FUNC method to obtain the vf id, if the number of vf big than 8, the obtained id number will be wrong, and the new method needs to be used to correct it. Signed-off-by: Longfang Liu <liulongfang(a)huawei.com> Signed-off-by: JiangShui Yang <yangjiangshui(a)h-partners.com> --- .../hisilicon/migration/acc_vf_migration.c | 17 ++++++++++-- .../hisilicon/migration/acc_vf_migration.h | 26 +++++++++++++++++++ 2 files changed, 41 insertions(+), 2 deletions(-) diff --git a/drivers/crypto/hisilicon/migration/acc_vf_migration.c b/drivers/crypto/hisilicon/migration/acc_vf_migration.c index 920f19916fea..7c5fc4eb02ac 100644 --- a/drivers/crypto/hisilicon/migration/acc_vf_migration.c +++ b/drivers/crypto/hisilicon/migration/acc_vf_migration.c @@ -1610,6 +1610,19 @@ static int acc_vf_dev_init(struct pci_dev *pdev, struct hisi_qm *pf_qm, return -ENOMEM; } +static int hisi_acc_get_vf_id(struct pci_dev *dev) +{ + struct pci_dev *pf; + + if (!dev->is_virtfn) + return -EINVAL; + + pf = pci_physfn(dev); + return (((dev->bus->number << 8) + dev->devfn) - + ((pf->bus->number << 8) + pf->devfn + pf->sriov->offset)) / + pf->sriov->stride; +} + static void *acc_vf_probe(struct pci_dev *pdev) { struct acc_vf_migration *acc_vf_dev; @@ -1635,7 +1648,7 @@ static void *acc_vf_probe(struct pci_dev *pdev) return ERR_PTR(-EINVAL); } - vf_id = PCI_FUNC(vf_dev->devfn); + vf_id = hisi_acc_get_vf_id(vf_dev); if (vf_id < 0) { dev_info(&pdev->dev, "vf device: %s, vf id: %d\n", pf_qm->dev_name, vf_id); @@ -1652,7 +1665,7 @@ static void *acc_vf_probe(struct pci_dev *pdev) return ERR_PTR(-ENOMEM); } - acc_vf_dev->vf_id = vf_id; + acc_vf_dev->vf_id = vf_id + 1; acc_vf_dev->vf_vendor = pdev->vendor; acc_vf_dev->vf_device = pdev->device; acc_vf_dev->pf_dev = pf_dev; diff --git a/drivers/crypto/hisilicon/migration/acc_vf_migration.h b/drivers/crypto/hisilicon/migration/acc_vf_migration.h index 2f459eecb8f0..8b38b9943d35 100644 --- a/drivers/crypto/hisilicon/migration/acc_vf_migration.h +++ b/drivers/crypto/hisilicon/migration/acc_vf_migration.h @@ -215,6 +215,32 @@ struct acc_vf_region_ops { struct vfio_info_cap *caps); }; +/* Single Root I/O Virtualization */ +struct pci_sriov { + int pos; /* Capability position */ + int nres; /* Number of resources */ + u32 cap; /* SR-IOV Capabilities */ + u16 ctrl; /* SR-IOV Control */ + u16 total_VFs; /* Total VFs associated with the PF */ + u16 initial_VFs; /* Initial VFs associated with the PF */ + u16 num_VFs; /* Number of VFs available */ + u16 offset; /* First VF Routing ID offset */ + u16 stride; /* Following VF stride */ + u16 vf_device; /* VF device ID */ + u32 pgsz; /* Page size for BAR alignment */ + u8 link; /* Function Dependency Link */ + u8 max_VF_buses; /* Max buses consumed by VFs */ + u16 driver_max_VFs; /* Max num VFs driver supports */ + struct pci_dev *dev; /* Lowest numbered PF */ + struct pci_dev *self; /* This PF */ + u32 class; /* VF device */ + u8 hdr_type; /* VF header type */ + u16 subsystem_vendor; /* VF subsystem vendor */ + u16 subsystem_device; /* VF subsystem device */ + resource_size_t barsz[PCI_SRIOV_NUM_BARS]; /* VF BAR size */ + bool drivers_autoprobe; /* Auto probing of VFs by driver */ +}; + struct acc_vf_region { u32 type; u32 subtype; -- 2.33.0

1 0

Intel Arch SIG 例会
by openEuler conference 14 Feb '23

14 Feb '23

您好！ sig-Intel-Arch SIG 邀请您参加 2023-02-21 10:00 召开的Zoom会议会议主题：Intel Arch SIG 例会会议内容： 1. Intel几个复杂特性的支持计划 2. QEMU和kernel选型对未来lntel平台支持和release安排讨论 3. openEuler在SPR上的用户诉求和反馈会议链接：https://us06web.zoom.us/j/87058792984?pwd=UFlzSzA4OHNyMEIvRkpCdWFwdEdRQT09 会议纪要：https://etherpad.openeuler.org/p/sig-Intel-Arch-meetings 温馨提醒：建议接入会议后修改参会人的姓名，也可以使用您在gitee.com的ID 更多资讯尽在：https://openeuler.org/zh/ Hello! openEuler sig-Intel-Arch SIG invites you to attend the Zoom conference will be held at 2023-02-21 10:00, The subject of the conference is Intel Arch SIG 例会, Summary: 1. Intel几个复杂特性的支持计划 2. QEMU和kernel选型对未来lntel平台支持和release安排讨论 3. openEuler在SPR上的用户诉求和反馈 You can join the meeting at https://us06web.zoom.us/j/87058792984?pwd=UFlzSzA4OHNyMEIvRkpCdWFwdEdRQT09. Add topics at https://etherpad.openeuler.org/p/sig-Intel-Arch-meetings. Note: You are advised to change the participant name after joining the conference or use your ID at gitee.com. More information: https://openeuler.org/en/

1 0

[Cancel] Intel Arch SIG 例会
by openEuler conference 14 Feb '23

14 Feb '23

Sorry! The Zoom meeting will be held at 2023-02-20 10:00 scheduled by openEuler sig-Intel-Arch SIG has been cancelled.

1 0

Intel Arch SIG 例会
by openEuler conference 14 Feb '23

14 Feb '23

您好！ sig-Intel-Arch SIG 邀请您参加 2023-02-20 10:00 召开的Zoom会议会议主题：Intel Arch SIG 例会会议内容： 1. Intel几个复杂特性的支持计划 2. QEMU和kernel选型对未来lntel平台支持和release安排讨论 3. openEuler在SPR上的用户诉求和反馈会议链接：https://us06web.zoom.us/j/87427026722?pwd=eE9lQXBNck9KS0kzek9Da2VYV2VRdz09 会议纪要：https://etherpad.openeuler.org/p/sig-Intel-Arch-meetings 温馨提醒：建议接入会议后修改参会人的姓名，也可以使用您在gitee.com的ID 更多资讯尽在：https://openeuler.org/zh/ Hello! openEuler sig-Intel-Arch SIG invites you to attend the Zoom conference will be held at 2023-02-20 10:00, The subject of the conference is Intel Arch SIG 例会, Summary: 1. Intel几个复杂特性的支持计划 2. QEMU和kernel选型对未来lntel平台支持和release安排讨论 3. openEuler在SPR上的用户诉求和反馈 You can join the meeting at https://us06web.zoom.us/j/87427026722?pwd=eE9lQXBNck9KS0kzek9Da2VYV2VRdz09. Add topics at https://etherpad.openeuler.org/p/sig-Intel-Arch-meetings. Note: You are advised to change the participant name after joining the conference or use your ID at gitee.com. More information: https://openeuler.org/en/

1 0

[PATCH openEuler-1.0-LTS] media: vivid: fix compose size exceed boundary
by Yongqiang Liu 13 Feb '23

13 Feb '23

From: Liu Shixin <liushixin2(a)huawei.com> stable inclusion from stable-v4.19.270 commit 9c7fba9503b826f0c061d136f8f0c9f953ed18b9 category: bugfix bugzilla: https://gitee.com/src-openeuler/risc-v-kernel/issues/I6CIGU CVE: CVE-2023-0615 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit 94a7ad9283464b75b12516c5512541d467cefcf8 ] syzkaller found a bug: BUG: unable to handle page fault for address: ffffc9000a3b1000 #PF: supervisor write access in kernel mode #PF: error_code(0x0002) - not-present page PGD 100000067 P4D 100000067 PUD 10015f067 PMD 1121ca067 PTE 0 Oops: 0002 [#1] PREEMPT SMP CPU: 0 PID: 23489 Comm: vivid-000-vid-c Not tainted 6.1.0-rc1+ #512 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.13.0-1ubuntu1.1 04/01/2014 RIP: 0010:memcpy_erms+0x6/0x10 [...] Call Trace: <TASK> ? tpg_fill_plane_buffer+0x856/0x15b0 vivid_fillbuff+0x8ac/0x1110 vivid_thread_vid_cap_tick+0x361/0xc90 vivid_thread_vid_cap+0x21a/0x3a0 kthread+0x143/0x180 ret_from_fork+0x1f/0x30 </TASK> This is because we forget to check boundary after adjust compose->height int V4L2_SEL_TGT_CROP case. Add v4l2_rect_map_inside() to fix this problem for this case. Fixes: ef834f7836ec ("[media] vivid: add the video capture and output parts") Signed-off-by: Liu Shixin <liushixin2(a)huawei.com> Signed-off-by: Hans Verkuil <hverkuil-cisco(a)xs4all.nl> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Longlong Xia <xialonglong1(a)huawei.com> Reviewed-by: Nanyong Sun <sunnanyong(a)huawei.com> Reviewed-by: Kefeng Wang <wangkefeng.wang(a)huawei.com> Reviewed-by: Xiu Jianfeng <xiujianfeng(a)huawei.com> Signed-off-by: Yongqiang Liu <liuyongqiang13(a)huawei.com> --- drivers/media/platform/vivid/vivid-vid-cap.c | 1 + 1 file changed, 1 insertion(+) diff --git a/drivers/media/platform/vivid/vivid-vid-cap.c b/drivers/media/platform/vivid/vivid-vid-cap.c index c58ae489f39c..9eaac497ec34 100644 --- a/drivers/media/platform/vivid/vivid-vid-cap.c +++ b/drivers/media/platform/vivid/vivid-vid-cap.c @@ -915,6 +915,7 @@ int vivid_vid_cap_s_selection(struct file *file, void *fh, struct v4l2_selection if (dev->has_compose_cap) { v4l2_rect_set_min_size(compose, &min_rect); v4l2_rect_set_max_size(compose, &max_rect); + v4l2_rect_map_inside(compose, &fmt); } dev->fmt_cap_rect = fmt; tpg_s_buf_height(&dev->tpg, fmt.height); -- 2.25.1

1 0

[PATCH openEuler-5.10-LTS-SP1 01/87] NFSD: Fix verifier returned in stable WRITEs
by Jialin Zhang 13 Feb '23

13 Feb '23

From: Chuck Lever <chuck.lever(a)oracle.com> stable inclusion from stable-v5.10.143 commit d3d885507b52b28f54770a42d650251876d433a3 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I6D0U6 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- commit f11ad7aa653130b71e2e89bed207f387718216d5 upstream. RFC 8881 explains the purpose of the write verifier this way: > The final portion of the result is the field writeverf. This field > is the write verifier and is a cookie that the client can use to > determine whether a server has changed instance state (e.g., server > restart) between a call to WRITE and a subsequent call to either > WRITE or COMMIT. But then it says: > This cookie MUST be unchanged during a single instance of the > NFSv4.1 server and MUST be unique between instances of the NFSv4.1 > server. If the cookie changes, then the client MUST assume that > any data written with an UNSTABLE4 value for committed and an old > writeverf in the reply has been lost and will need to be > recovered. RFC 1813 has similar language for NFSv3. NFSv2 does not have a write verifier since it doesn't implement the COMMIT procedure. Since commit 19e0663ff9bc ("nfsd: Ensure sampling of the write verifier is atomic with the write"), the Linux NFS server has returned a boot-time-based verifier for UNSTABLE WRITEs, but a zero verifier for FILE_SYNC and DATA_SYNC WRITEs. FILE_SYNC and DATA_SYNC WRITEs are not followed up with a COMMIT, so there's no need for clients to compare verifiers for stable writes. However, by returning a different verifier for stable and unstable writes, the above commit puts the Linux NFS server a step farther out of compliance with the first MUST above. At least one NFS client (FreeBSD) noticed the difference, making this a potential regression. [Removed down_write to fix the conflict in the cherry-pick. The down_write functionality was no longer needed there. Upstream commit 555dbf1a9aac6d3150c8b52fa35f768a692f4eeb titled nfsd: Replace use of rwsem with errseq_t removed those and replace it with new functionality that was more scalable. This commit is already backported onto 5.10 and so removing down_write ensures consistency with that change. Tested by compiling and booting successfully. - kochera] Reported-by: Rick Macklem <rmacklem(a)uoguelph.ca> Link: https://lore.kernel.org/linux-nfs/YQXPR0101MB096857EEACF04A6DF1FC6D9BDD749@… Fixes: 19e0663ff9bc ("nfsd: Ensure sampling of the write verifier is atomic with the write") Signed-off-by: Chuck Lever <chuck.lever(a)oracle.com> Signed-off-by: Michael Kochera <kochera(a)google.com> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Jialin Zhang <zhangjialin11(a)huawei.com> Reviewed-by: Zheng Zengkai <zhengzengkai(a)huawei.com> --- fs/nfsd/vfs.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index c852bb5ff212..a4ae1fcd2ab1 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -1014,6 +1014,10 @@ nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct nfsd_file *nf, iov_iter_kvec(&iter, WRITE, vec, vlen, *cnt); since = READ_ONCE(file->f_wb_err); if (flags & RWF_SYNC) { + if (verf) + nfsd_copy_boot_verifier(verf, + net_generic(SVC_NET(rqstp), + nfsd_net_id)); host_err = vfs_iter_write(file, &iter, &pos, flags); if (host_err < 0) nfsd_reset_boot_verifier(net_generic(SVC_NET(rqstp), -- 2.25.1

1 86

openEuler Kernel SIG双周例会
by openEuler conference 10 Feb '23

10 Feb '23

您好！ Kernel SIG 邀请您参加 2023-02-10 14:00 召开的Zoom会议(自动录制) 会议主题：openEuler Kernel SIG双周例会会议内容：欢迎您参加年后第一次Kernel SIG 双周例会： 1. 进展update 2. 议题征集中欢迎大家积极申报议题（新增议题可以直接回复邮件，或录入会议看板）会议链接：https://us06web.zoom.us/j/89146789515?pwd=NVN5RmdCSFh2Y1g4SXUwK2NCRnFEZz09 会议纪要：https://etherpad.openeuler.org/p/Kernel-meetings 温馨提醒：建议接入会议后修改参会人的姓名，也可以使用您在gitee.com的ID 更多资讯尽在：https://openeuler.org/zh/ Hello! openEuler Kernel SIG invites you to attend the Zoom conference(auto recording) will be held at 2023-02-10 14:00, The subject of the conference is openEuler Kernel SIG双周例会, Summary: 欢迎您参加年后第一次Kernel SIG 双周例会： 1. 进展update 2. 议题征集中欢迎大家积极申报议题（新增议题可以直接回复邮件，或录入会议看板） You can join the meeting at https://us06web.zoom.us/j/89146789515?pwd=NVN5RmdCSFh2Y1g4SXUwK2NCRnFEZz09. Add topics at https://etherpad.openeuler.org/p/Kernel-meetings. Note: You are advised to change the participant name after joining the conference or use your ID at gitee.com. More information: https://openeuler.org/en/

4 3

[PATCH openEuler-5.10-LTS 1/5] crypto: hisilicon/qm - add functions for releasing resources
by Zheng Zengkai 09 Feb '23

09 Feb '23

From: Weili Qian <qianweili(a)huawei.com> mainline inclusion from mainline-v6.0-rc1 commit bf081d6fa8e9 category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I6DRLU CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… ---------------------------------------------------------------------- The resources allocated by hisi_qm_memory_init() are released by hisi_qm_uninit(). Add hisi_qm_memory_uninit() to release resources, no functional change. conficts: drivers/crypto/hisilicon/qm.c Signed-off-by: Weili Qian <qianweili(a)huawei.com> Signed-off-by: JiangShui Yang <yangjiangshui(a)h-partners.com> Reviewed-by: Xiu Jianfeng <xiujianfeng(a)huawei.com> --- drivers/crypto/hisilicon/qm.c | 30 +++++++++++++++++------------- 1 file changed, 17 insertions(+), 13 deletions(-) diff --git a/drivers/crypto/hisilicon/qm.c b/drivers/crypto/hisilicon/qm.c index 57de083e8967..ef09e45bdc3e 100644 --- a/drivers/crypto/hisilicon/qm.c +++ b/drivers/crypto/hisilicon/qm.c @@ -3480,6 +3480,21 @@ static void hisi_qm_pci_uninit(struct hisi_qm *qm) pci_disable_device(pdev); } +static void hisi_qm_memory_uninit(struct hisi_qm *qm) +{ + struct device *dev = &qm->pdev->dev; + + hisi_qp_memory_uninit(qm, qm->qp_num); + if (qm->qdma.va) { + hisi_qm_cache_wb(qm); + dma_free_coherent(dev, qm->qdma.size, + qm->qdma.va, qm->qdma.dma); + } + + idr_destroy(&qm->qp_idr); + kfree(qm->factor); +} + /** * hisi_qm_uninit() - Uninitialize qm. * @qm: The qm needed uninit. @@ -3488,26 +3503,15 @@ static void hisi_qm_pci_uninit(struct hisi_qm *qm) */ void hisi_qm_uninit(struct hisi_qm *qm) { - struct pci_dev *pdev = qm->pdev; - struct device *dev = &pdev->dev; - qm_cmd_uninit(qm); - kfree(qm->factor); - down_write(&qm->qps_lock); + down_write(&qm->qps_lock); if (!qm_avail_state(qm, QM_CLOSE)) { up_write(&qm->qps_lock); return; } - hisi_qp_memory_uninit(qm, qm->qp_num); - idr_destroy(&qm->qp_idr); - - if (qm->qdma.va) { - hisi_qm_cache_wb(qm); - dma_free_coherent(dev, qm->qdma.size, - qm->qdma.va, qm->qdma.dma); - } + hisi_qm_memory_uninit(qm); up_write(&qm->qps_lock); hisi_qm_set_state(qm, VF_NOT_READY); -- 2.20.1

1 4

[PATCH openEuler-1.0-LTS 00/49] linux-4.19.y inclusion
by Yongqiang Liu 09 Feb '23

09 Feb '23

Chen Zhongjin (1): perf: Fix possible memleak in pmu_dev_alloc() Christian Brauner (1): pnode: terminate at peers of source Chuck Lever (1): SUNRPC: Don't leak netobj memory when gss_read_proxy_verf() fails Dan Carpenter (2): bonding: uninitialized variable in bond_miimon_inspect() ipmi: fix use after free in _ipmi_destroy_user() Enzo Matsumiya (1): cifs: do not include page data when checking signature Eric Dumazet (1): net: stream: purge sk_error_queue in sk_stream_kill_queues() Greg Kroah-Hartman (1): prlimit: do_prlimit needs to have a speculation check Huaxin Lu (1): ima: Fix a potential NULL pointer access in ima_restore_measurement_list Isaac J. Manjarres (1): driver core: Fix bus_type.match() error handling in __driver_attach() Jakub Kicinski (2): bpf: pull before calling skb_postpull_rcsum() net: stream: don't purge sk_error_queue in sk_stream_kill_queues() Jan Kara (2): mbcache: automatically delete entries from cache on freeing ext4: fix deadlock due to mbcache entry corruption Jann Horn (2): mm/khugepaged: fix GUP-fast interaction by sending IPI mm/khugepaged: invoke MMU notifiers in shmem/file collapse paths Jiamei Xie (1): serial: amba-pl011: avoid SBSA UART accessing DMACR register Jiang Li (1): md/raid1: stop mdx_raid1 thread when raid1 array run failed Li Zetao (1): ACPICA: Fix use-after-free in acpi_ut_copy_ipackage_to_ipackage() Mark Rutland (1): arm64: cmpxchg_double*: hazard against entire exchange variable Michael S. Tsirkin (1): PCI: Fix pci_device_is_present() for VFs by checking PF Mikulas Patocka (1): md: fix a crash in mempool_free Paolo Abeni (1): net/ulp: prevent ULP without clone op from entering the LISTEN status Rafael J. Wysocki (1): ACPICA: Fix error code path in acpi_ds_call_control_method() Sascha Hauer (1): PCI/sysfs: Fix double free in error path Schspa Shi (1): mrp: introduce active flags to prevent UAF when applicant uninit Stanislav Fomichev (1): bpf: make sure skb->len != 0 when redirecting to a tunneling device Stephen Boyd (1): pstore: Avoid kcore oops by vmap()ing with VM_IOREMAP Subash Abhinov Kasiviswanathan (1): skbuff: Account for tail adjustment during pull operations Ulf Hansson (1): cpuidle: dt: Return the correct numbers of parsed idle states Volker Lendecke (1): cifs: Fix uninitialized memory read for smb311 posix symlink create Wang ShaoBo (1): SUNRPC: Fix missing release socket in rpc_sockname() Wang Weiyang (1): device_cgroup: Roll back to original exceptions after copy failure Wang Yufen (2): pstore/ram: Fix error return code in ramoops_probe() binfmt: Fix error return code in load_elf_fdpic_binary() Xiu Jianfeng (1): ima: Fix misuse of dereference of pointer in template_desc_init_fields() Yang Jihong (1): blktrace: Fix output non-blktrace event when blk_classic option enabled Yang Shi (1): mm: gup: fix the fast GUP race against THP collapse Yang Yingliang (2): class: fix possible memory leak in __class_register() chardev: fix error handling in cdev_device_add() Ye Bin (1): blk-mq: fix possible memleak when register 'hctx' failed Yuan Can (1): perf: arm_dsu: Fix hotplug callback leak in dsu_pmu_init() Zhang Tianci (1): ovl: Use ovl mounter's fsuid and fsgid in ovl_link() Zhang Yiqun (1): crypto: tcrypt - Fix multibuffer skcipher speed test mem leak Zhang Yuchen (2): ipmi: fix memleak when unload ipmi driver ipmi: fix long wait in unload when IPMI disconnect ZhangPeng (1): pinctrl: pinconf-generic: add missing of_node_put() delisun (1): serial: pl011: Do not clear RX FIFO & RX interrupt in unthrottle. minoura makoto (1): SUNRPC: ensure the matching upcall is in-flight upon downcall arch/arm64/include/asm/atomic_ll_sc.h | 2 +- arch/arm64/include/asm/atomic_lse.h | 2 +- block/blk-mq-sysfs.c | 11 ++- crypto/tcrypt.c | 9 -- drivers/acpi/acpica/dsmethod.c | 10 ++- drivers/acpi/acpica/utcopy.c | 7 -- drivers/base/class.c | 5 ++ drivers/base/dd.c | 8 +- drivers/char/ipmi/ipmi_msghandler.c | 12 ++- drivers/char/ipmi/ipmi_si_intf.c | 27 ++++-- drivers/cpuidle/dt_idle_states.c | 2 +- drivers/md/md.c | 9 +- drivers/md/raid1.c | 1 + drivers/net/bonding/bond_main.c | 2 +- drivers/pci/pci-sysfs.c | 13 ++- drivers/pci/pci.c | 2 + drivers/perf/arm_dsu_pmu.c | 6 +- drivers/pinctrl/pinconf-generic.c | 4 +- drivers/tty/serial/amba-pl011.c | 14 ++- fs/binfmt_elf_fdpic.c | 5 +- fs/char_dev.c | 2 +- fs/cifs/link.c | 1 + fs/cifs/smb2pdu.c | 15 ++-- fs/ext4/xattr.c | 4 +- fs/mbcache.c | 118 ++++++++++---------------- fs/overlayfs/dir.c | 46 ++++++---- fs/pnode.c | 2 +- fs/pstore/ram.c | 2 + fs/pstore/ram_core.c | 6 +- include/asm-generic/tlb.h | 6 ++ include/linux/mbcache.h | 33 ++++--- include/linux/sunrpc/rpc_pipe_fs.h | 5 ++ include/net/mrp.h | 1 + kernel/events/core.c | 8 +- kernel/sys.c | 2 + kernel/trace/blktrace.c | 3 +- mm/gup.c | 34 ++++++-- mm/khugepaged.c | 34 ++++++-- mm/memory.c | 1 + mm/mmu_gather.c | 5 ++ net/802/mrp.c | 18 ++-- net/core/filter.c | 11 ++- net/core/skbuff.c | 3 + net/core/stream.c | 7 +- net/ipv4/inet_connection_sock.c | 16 +++- net/sunrpc/auth_gss/auth_gss.c | 19 ++++- net/sunrpc/auth_gss/svcauth_gss.c | 4 +- net/sunrpc/clnt.c | 2 +- security/device_cgroup.c | 33 ++++++- security/integrity/ima/ima_template.c | 9 +- 50 files changed, 406 insertions(+), 195 deletions(-) -- 2.25.1

1 49

[PATCH openEuler-1.0-LTS 0/5] mainline backport
by Yongqiang Liu 09 Feb '23

09 Feb '23

Ard Biesheuvel (1): crypto: tcrypt - avoid signed overflow in byte count Guenter Roeck (1): lib/list_debug.c: Detect uninitialized lists Guoqing Jiang (1): md: protect md_unregister_thread from reentrancy Konstantin Khlebnikov (1): sched/rt: Optimize checking group RT scheduler constraints Sean Christopherson (1): hugetlbfs: fix off-by-one error in hugetlb_vmdelete_list() crypto/tcrypt.c | 20 ++++++++++---------- drivers/md/md.c | 15 ++++++++++----- fs/hugetlbfs/inode.c | 7 ++++--- kernel/sched/rt.c | 24 +++++++++++------------- lib/list_debug.c | 12 ++++++++++-- 5 files changed, 45 insertions(+), 33 deletions(-) -- 2.25.1

1 5

[PATCH openEuler-1.0-LTS] mm: sharepool: fix hugepage_rsvd count increase error
by Yongqiang Liu 09 Feb '23

09 Feb '23

From: Guo Mengqi <guomengqi3(a)huawei.com> hulk inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I5RO2H CVE: NA -------------------------------- When nr_hugepages is configured, sharepool allocates hugepages first from hugetlb pool, then from buddy system if the pool had been used up. Current page release function treat the buddy system hugepages as hugetlb pages, which caused HugePages_Rsvd to increase improperly. Add a check in page release function: if the page is temporary, do not call hugetlb_unreserve_pages. Signed-off-by: Guo Mengqi <guomengqi3(a)huawei.com> Reviewed-by: Weilong Chen <chenweilong(a)huawei.com> Signed-off-by: Yongqiang Liu <liuyongqiang13(a)huawei.com> --- fs/hugetlbfs/inode.c | 20 +++++++++++++++++--- 1 file changed, 17 insertions(+), 3 deletions(-) diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index f29d6d2fb052..d70c8aaf5acc 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -448,6 +448,14 @@ hugetlb_vmdelete_list(struct rb_root_cached *root, pgoff_t start, pgoff_t end) } } +static inline bool PageHugeTemporary(struct page *page) +{ + if (!PageHuge(page)) + return false; + + return (unsigned long)page[2].mapping == -1U; +} + /* * remove_inode_hugepages handles two distinct cases: truncation and hole * punch. There are subtle differences in operation for each case. @@ -532,11 +540,17 @@ static void remove_inode_hugepages(struct inode *inode, loff_t lstart, */ VM_BUG_ON(PagePrivate(page)); remove_huge_page(page); - freed++; - if (!truncate_op) { - if (unlikely(hugetlb_unreserve_pages(inode, + /* + * if the page is from buddy system, do not add to freed. + * because freed is used for hugetlbfs reservation accounting. + */ + if (!PageHugeTemporary(page)) { + freed++; + if (!truncate_op) { + if (unlikely(hugetlb_unreserve_pages(inode, index, index + 1, 1))) hugetlb_fix_reserve_counts(inode); + } } unlock_page(page); -- 2.25.1

1 0

[PATCH openEuler-5.10-LTS 1/5] crypto: hisilicon/qm - add functions for releasing resources
by Zheng Zengkai 09 Feb '23

09 Feb '23

From: Weili Qian <qianweili(a)huawei.com> mainline inclusion from mainline-v6.0-rc1 commit bf081d6fa8e9 category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I6DRLU CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… ---------------------------------------------------------------------- The resources allocated by hisi_qm_memory_init() are released by hisi_qm_uninit(). Add hisi_qm_memory_uninit() to release resources, no functional change. conficts: drivers/crypto/hisilicon/qm.c Signed-off-by: Weili Qian <qianweili(a)huawei.com> Signed-off-by: JiangShui Yang <yangjiangshui(a)h-partners.com> Reviewed-by: Xiu Jianfeng <xiujianfeng(a)huawei.com> --- drivers/crypto/hisilicon/qm.c | 30 +++++++++++++++++------------- 1 file changed, 17 insertions(+), 13 deletions(-) diff --git a/drivers/crypto/hisilicon/qm.c b/drivers/crypto/hisilicon/qm.c index 57de083e8967..ef09e45bdc3e 100644 --- a/drivers/crypto/hisilicon/qm.c +++ b/drivers/crypto/hisilicon/qm.c @@ -3480,6 +3480,21 @@ static void hisi_qm_pci_uninit(struct hisi_qm *qm) pci_disable_device(pdev); } +static void hisi_qm_memory_uninit(struct hisi_qm *qm) +{ + struct device *dev = &qm->pdev->dev; + + hisi_qp_memory_uninit(qm, qm->qp_num); + if (qm->qdma.va) { + hisi_qm_cache_wb(qm); + dma_free_coherent(dev, qm->qdma.size, + qm->qdma.va, qm->qdma.dma); + } + + idr_destroy(&qm->qp_idr); + kfree(qm->factor); +} + /** * hisi_qm_uninit() - Uninitialize qm. * @qm: The qm needed uninit. @@ -3488,26 +3503,15 @@ static void hisi_qm_pci_uninit(struct hisi_qm *qm) */ void hisi_qm_uninit(struct hisi_qm *qm) { - struct pci_dev *pdev = qm->pdev; - struct device *dev = &pdev->dev; - qm_cmd_uninit(qm); - kfree(qm->factor); - down_write(&qm->qps_lock); + down_write(&qm->qps_lock); if (!qm_avail_state(qm, QM_CLOSE)) { up_write(&qm->qps_lock); return; } - hisi_qp_memory_uninit(qm, qm->qp_num); - idr_destroy(&qm->qp_idr); - - if (qm->qdma.va) { - hisi_qm_cache_wb(qm); - dma_free_coherent(dev, qm->qdma.size, - qm->qdma.va, qm->qdma.dma); - } + hisi_qm_memory_uninit(qm); up_write(&qm->qps_lock); hisi_qm_set_state(qm, VF_NOT_READY); -- 2.20.1

1 4

[PATCH openEuler-1.0-LTS 1/3] irqchip/gic-v3-its: introduce CONFIG_GENERIC_PENDING_IRQ
by Yongqiang Liu 09 Feb '23

09 Feb '23

From: Yipeng Zou <zouyipeng(a)huawei.com> hulk inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I6BO2R CVE: NA -------------------------------- Now, There is some issues about LPI migration on ARM SMP platform. For example, NIC device generates MSI and sends LPI to CPU0 via ITS, meanwhile irqbalance running on CPU1 set irq affinty of NIC to CPU1, the next interrupt will be sent to CPU2, due to the state of irq is still in progress, kernel does not end up performing irq handler on CPU2, which results in some userland service timeouts, the sequence of events is shown as follows: NIC CPU0 CPU1 Generate IRQ#1 READ_IAR Lock irq_desc Set IRQD_IN_PROGRESS Unlock irq_desc Lock irq_desc Change LPI Affinity Unlock irq_desc Call irq_handler Generate IRQ#2 READ_IAR Lock irq_desc Check IRQD_IN_PROGRESS Unlock irq_desc Return from interrupt#2 Lock irq_desc Clear IRQD_IN_PROGRESS Unlock irq_desc return from interrupt#1 For this scenario, We can enable CONFIG_GENERIC_PENDING_IRQ to avoid this. The CONFIG_GENERIC_PENDING_IRQ will delay all action that modify LPI affinity until the next interrupt eoi handler. Signed-off-by: Yipeng Zou <zouyipeng(a)huawei.com> Reviewed-by: Liao Chang <liaochang1(a)huawei.com> Reviewed-by: Zhang Jianhua <chris.zjh(a)huawei.com> Signed-off-by: Yongqiang Liu <liuyongqiang13(a)huawei.com> --- drivers/irqchip/irq-gic-v3-its.c | 8 +++++++- kernel/irq/Kconfig | 4 +++- kernel/irq/migration.c | 2 ++ 3 files changed, 12 insertions(+), 2 deletions(-) diff --git a/drivers/irqchip/irq-gic-v3-its.c b/drivers/irqchip/irq-gic-v3-its.c index 15a0292e8e61..7a0adf67761e 100644 --- a/drivers/irqchip/irq-gic-v3-its.c +++ b/drivers/irqchip/irq-gic-v3-its.c @@ -1162,6 +1162,12 @@ static void its_unmask_irq(struct irq_data *d) lpi_update_config(d, 0, LPI_PROP_ENABLED); } +static void its_irq_chip_eoi(struct irq_data *d) +{ + irq_move_irq(d); + irq_chip_eoi_parent(d); +} + static int its_set_affinity(struct irq_data *d, const struct cpumask *mask_val, bool force) { @@ -1485,7 +1491,7 @@ static struct irq_chip its_irq_chip = { .name = "ITS", .irq_mask = its_mask_irq, .irq_unmask = its_unmask_irq, - .irq_eoi = irq_chip_eoi_parent, + .irq_eoi = its_irq_chip_eoi, .irq_set_affinity = its_set_affinity, .irq_compose_msi_msg = its_irq_compose_msi_msg, .irq_set_irqchip_state = its_irq_set_irqchip_state, diff --git a/kernel/irq/Kconfig b/kernel/irq/Kconfig index 14a85d0161ea..eebbced84e44 100644 --- a/kernel/irq/Kconfig +++ b/kernel/irq/Kconfig @@ -32,7 +32,9 @@ config GENERIC_IRQ_LEGACY_ALLOC_HWIRQ # Support for delayed migration from interrupt context config GENERIC_PENDING_IRQ - bool + bool "Support for delayed migration from interrupt context" + depends on SMP + default n # Support for generic irq migrating off cpu before the cpu is offline. config GENERIC_IRQ_MIGRATION diff --git a/kernel/irq/migration.c b/kernel/irq/migration.c index def48589ea48..bcb61ee69c20 100644 --- a/kernel/irq/migration.c +++ b/kernel/irq/migration.c @@ -117,3 +117,5 @@ void __irq_move_irq(struct irq_data *idata) if (!masked) idata->chip->irq_unmask(idata); } + +void __weak irq_force_complete_move(struct irq_desc *desc) { } -- 2.25.1

1 2

[PATCH openEuler-1.0-LTS 1/3] jbd2: Fix data missing when reusing bh which is ready to be checkpointed
by Yongqiang Liu 09 Feb '23

09 Feb '23

From: Zhihao Cheng <chengzhihao1(a)huawei.com> maillist inclusion category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I6C5HV CVE: NA Reference: https://lore.kernel.org/lkml/20230110015327.1181863-1-chengzhihao1@huawei.c… -------------------------------- Following process will make data lost and could lead to a filesystem corrupted problem: 1. jh(bh) is inserted into T1->t_checkpoint_list, bh is dirty, and jh->b_transaction = NULL 2. T1 is added into journal->j_checkpoint_transactions. 3. Get bh prepare to write while doing checkpoing: PA PB do_get_write_access jbd2_log_do_checkpoint spin_lock(&jh->b_state_lock) if (buffer_dirty(bh)) clear_buffer_dirty(bh) // clear buffer dirty set_buffer_jbddirty(bh) transaction = journal->j_checkpoint_transactions jh = transaction->t_checkpoint_list if (!buffer_dirty(bh)) __jbd2_journal_remove_checkpoint(jh) // bh won't be flushed jbd2_cleanup_journal_tail __jbd2_journal_file_buffer(jh, transaction, BJ_Reserved) 4. Aborting journal/Power-cut before writing latest bh on journal area. In this way we get a corrupted filesystem with bh's data lost. Fix it by moving the clearing of buffer_dirty bit just before the call to __jbd2_journal_file_buffer(), both bit clearing and jh->b_transaction assignment are under journal->j_list_lock locked, so that jbd2_log_do_checkpoint() will wait until jh's new transaction fininshed even bh is currently not dirty. And journal_shrink_one_cp_list() won't remove jh from checkpoint list if the buffer head is reused in do_get_write_access(). Fetch a reproducer in [Link]. Link: https://bugzilla.kernel.org/show_bug.cgi?id=216898 Cc: <stable(a)kernel.org> Signed-off-by: Zhihao Cheng <chengzhihao1(a)huawei.com> Signed-off-by: zhanchengbin <zhanchengbin1(a)huawei.com> Suggested-by: Jan Kara <jack(a)suse.cz> Conflicts: fs/jbd2/transaction.c [ 464170647b5648bb8("jbd2: Make state lock a spinlock") is not applied. ] Signed-off-by: Zhihao Cheng <chengzhihao1(a)huawei.com> Reviewed-by: Yang Erkun <yangerkun(a)huawei.com> Reviewed-by: Zhang Yi <yi.zhang(a)huawei.com> Signed-off-by: Yongqiang Liu <liuyongqiang13(a)huawei.com> --- fs/jbd2/transaction.c | 50 +++++++++++++++++++++++++------------------ 1 file changed, 29 insertions(+), 21 deletions(-) diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c index 3b31bd1f7b77..149190c2ac89 100644 --- a/fs/jbd2/transaction.c +++ b/fs/jbd2/transaction.c @@ -935,36 +935,28 @@ do_get_write_access(handle_t *handle, struct journal_head *jh, * ie. locked but not dirty) or tune2fs (which may actually have * the buffer dirtied, ugh.) */ - if (buffer_dirty(bh)) { + if (buffer_dirty(bh) && jh->b_transaction) { + warn_dirty_buffer(bh); /* - * First question: is this buffer already part of the current - * transaction or the existing committing transaction? - */ - if (jh->b_transaction) { - J_ASSERT_JH(jh, - jh->b_transaction == transaction || - jh->b_transaction == - journal->j_committing_transaction); - if (jh->b_next_transaction) - J_ASSERT_JH(jh, jh->b_next_transaction == - transaction); - warn_dirty_buffer(bh); - } - /* - * In any case we need to clean the dirty flag and we must - * do it under the buffer lock to be sure we don't race - * with running write-out. + * We need to clean the dirty flag and we must do it under the + * buffer lock to be sure we don't race with running write-out. */ JBUFFER_TRACE(jh, "Journalling dirty buffer"); clear_buffer_dirty(bh); + /* + * The buffer is going to be added to BJ_Reserved list now and + * nothing guarantees jbd2_journal_dirty_metadata() will be + * ever called for it. So we need to set jbddirty bit here to + * make sure the buffer is dirtied and written out when the + * journaling machinery is done with it. + */ set_buffer_jbddirty(bh); } - unlock_buffer(bh); - error = -EROFS; if (is_handle_aborted(handle)) { jbd_unlock_bh_state(bh); + unlock_buffer(bh); goto out; } error = 0; @@ -974,8 +966,10 @@ do_get_write_access(handle_t *handle, struct journal_head *jh, * b_next_transaction points to it */ if (jh->b_transaction == transaction || - jh->b_next_transaction == transaction) + jh->b_next_transaction == transaction) { + unlock_buffer(bh); goto done; + } /* * this is the first time this transaction is touching this buffer, @@ -999,10 +993,24 @@ do_get_write_access(handle_t *handle, struct journal_head *jh, */ smp_wmb(); spin_lock(&journal->j_list_lock); + if (test_clear_buffer_dirty(bh)) { + /* + * Execute buffer dirty clearing and jh->b_transaction + * assignment under journal->j_list_lock locked to + * prevent bh being removed from checkpoint list if + * the buffer is in an intermediate state (not dirty + * and jh->b_transaction is NULL). + */ + JBUFFER_TRACE(jh, "Journalling dirty buffer"); + set_buffer_jbddirty(bh); + } __jbd2_journal_file_buffer(jh, transaction, BJ_Reserved); spin_unlock(&journal->j_list_lock); + unlock_buffer(bh); goto done; } + unlock_buffer(bh); + /* * If there is already a copy-out version of this buffer, then we don't * need to make another one -- 2.25.1

1 2

[PATCH openEuler-1.0-LTS] x86/unwind: Fix orc entry for paravirt {save,restore}_fl
by Yongqiang Liu 08 Feb '23

08 Feb '23

From: Chen Zhongjin <chenzhongjin(a)huawei.com> hulk inclusion category: bugfix bugzilla: 187818, https://gitee.com/openeuler/kernel/issues/I6DK3O CVE: NA -------------------------------- When CONFIG_PARAVIRT is enabled, the code of {save,restore}_fl is defined as: ff 14 25 00 00 00 00 callq *0x0 which will be patched to call the xen paravirt function, or native implementation, in 'paravirt_patch_64.c': pushfq; popq %rax // for native_save_fl pushq %rdi; popfq // for native_restore_fl The orc metadata is generated with insn 'callq', so it can become inconsistent with the real insn 'push;pop'. This makes stacktrace on the 'pop' insn fail and incorrect stacktrace result can be returned. To prevent reliable stacktrace broken, check the insns when unwind pt_regs stack frame: When there are 'push;pop' combination and both insns don't change orc entry, it means the stack state is inconsistent with orc on pop. Add one slot to sp_offset for on original orc entry to get the correct orc entry. Signed-off-by: Chen Zhongjin <chenzhongjin(a)huawei.com> Reviewed-by: Xu Kuohai <xukuohai(a)huawei.com> Signed-off-by: Yongqiang Liu <liuyongqiang13(a)huawei.com> --- arch/x86/kernel/unwind_orc.c | 43 ++++++++++++++++++++++++++++++++++++ 1 file changed, 43 insertions(+) diff --git a/arch/x86/kernel/unwind_orc.c b/arch/x86/kernel/unwind_orc.c index 0402bc0b5851..ec4a14e4f639 100644 --- a/arch/x86/kernel/unwind_orc.c +++ b/arch/x86/kernel/unwind_orc.c @@ -138,6 +138,34 @@ static struct orc_entry null_orc_entry = { .type = ORC_TYPE_CALL }; +#ifdef CONFIG_PARAVIRT +static bool check_paravirt(struct unwind_state *state, struct orc_entry *orc) +{ + u8 *ip = (u8 *)state->ip; + + /* + * In paravirt_patch_64.c, patched paravirt opcode should be: + * pushfq; popq %rax // 0x9c 0x58 + * pushq %rdi; popfq // 0x57 0x9d + * + * Error unwinding only happens when: + * 1. In irq or preempt context. + * 2. Current insn is popq, and it doesn't change orc. + * 3. Last insn doesn't change orc, checking it first to + * promise ip - 1 is valid. + * 4. Last byte fits pushf. + */ + if (state->regs && orc->type == ORC_TYPE_CALL && + (ip[0] == 0x58 || ip[0] == 0x9d) && + orc == orc_find((unsigned long)(ip + 1)) && + orc == orc_find((unsigned long)(ip - 1)) && + (ip[-1] == 0x9c || ip[-1] == 0x57)) + return true; + + return false; +} +#endif + static struct orc_entry *orc_find(unsigned long ip) { static struct orc_entry *orc; @@ -415,6 +443,9 @@ bool unwind_next_frame(struct unwind_state *state) enum stack_type prev_type = state->stack_info.type; struct orc_entry *orc; bool indirect = false; +#ifdef CONFIG_PARAVIRT + struct orc_entry para_orc; +#endif if (unwind_done(state)) return false; @@ -436,6 +467,18 @@ bool unwind_next_frame(struct unwind_state *state) if (!orc) goto err; +#ifdef CONFIG_PARAVIRT + /* + * When hitting paravirt POP insn, the orc entry should add + * one slot for PUSH insn. + */ + if (!state->error && check_paravirt(state, orc)) { + para_orc = *orc; + para_orc.sp_offset += sizeof(long); + orc = &para_orc; + } +#endif + /* End-of-stack check for kernel threads: */ if (orc->sp_reg == ORC_REG_UNDEFINED) { if (!orc->end) -- 2.25.1

1 0

[PATCH openEuler-1.0-LTS 1/2] drm/i915/gvt: fix double free bug in split_2MB_gtt_entry
by Yongqiang Liu 07 Feb '23

07 Feb '23

From: Zheng Wang <zyytlz.wz(a)163.com> mainline inclusion from mainline-v6.2-rc3 commit 4a61648af68f5ba4884f0e3b494ee1cabc4b6620 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/I5XXFF CVE: CVE-2022-3707 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- If intel_gvt_dma_map_guest_page failed, it will call ppgtt_invalidate_spt, which will finally free the spt. But the caller function ppgtt_populate_spt_by_guest_entry does not notice that, it will free spt again in its error path. Fix this by canceling the mapping of DMA address and freeing sub_spt. Besides, leave the handle of spt destroy to caller function instead of callee function when error occurs. Fixes: b901b252b6cf ("drm/i915/gvt: Add 2M huge gtt support") Signed-off-by: Zheng Wang <zyytlz.wz(a)163.com> Reviewed-by: Zhenyu Wang <zhenyuw(a)linux.intel.com> Signed-off-by: Zhenyu Wang <zhenyuw(a)linux.intel.com> Link: http://patchwork.freedesktop.org/patch/msgid/20221229165641.1192455-1-zyytl… conflicts: drivers/gpu/drm/i915/gvt/gtt.c Signed-off-by: Wang ShaoBo <bobo.shaobowang(a)huawei.com> Reviewed-by: Xiu Jianfeng <xiujianfeng(a)huawei.com> Reviewed-by: Wei Li <liwei391(a)huawei.com> Signed-off-by: Yongqiang Liu <liuyongqiang13(a)huawei.com> --- drivers/gpu/drm/i915/gvt/gtt.c | 17 +++++++++++++---- 1 file changed, 13 insertions(+), 4 deletions(-) diff --git a/drivers/gpu/drm/i915/gvt/gtt.c b/drivers/gpu/drm/i915/gvt/gtt.c index 40b32b4d1d98..afbc648befec 100644 --- a/drivers/gpu/drm/i915/gvt/gtt.c +++ b/drivers/gpu/drm/i915/gvt/gtt.c @@ -1155,10 +1155,8 @@ static int split_2MB_gtt_entry(struct intel_vgpu *vgpu, for_each_shadow_entry(sub_spt, &sub_se, sub_index) { ret = intel_gvt_hypervisor_dma_map_guest_page(vgpu, start_gfn + sub_index, PAGE_SIZE, &dma_addr); - if (ret) { - ppgtt_invalidate_spt(spt); - return ret; - } + if (ret) + goto err; sub_se.val64 = se->val64; /* Copy the PAT field from PDE. */ @@ -1177,6 +1175,17 @@ static int split_2MB_gtt_entry(struct intel_vgpu *vgpu, ops->set_pfn(se, sub_spt->shadow_page.mfn); ppgtt_set_shadow_entry(spt, se, index); return 0; +err: + /* Cancel the existing addess mappings of DMA addr. */ + for_each_present_shadow_entry(sub_spt, &sub_se, sub_index) { + gvt_vdbg_mm("invalidate 4K entry\n"); + ppgtt_invalidate_pte(sub_spt, &sub_se); + } + /* Release the new allocated spt. */ + trace_spt_change(sub_spt->vgpu->id, "release", sub_spt, + sub_spt->guest_page.gfn, sub_spt->shadow_page.type); + ppgtt_free_spt(sub_spt); + return ret; } static int split_64KB_gtt_entry(struct intel_vgpu *vgpu, -- 2.25.1

1 1

[PATCH openEuler-5.10-LTS 01/10] xfs: fix potential log item leak
by Jialin Zhang 07 Feb '23

07 Feb '23

From: Dave Chinner <dchinner(a)redhat.com> mainline inclusion from mainline-v5.19-rc1 commit c230a4a85bcdbfc1a7415deec6caf04e8fca1301 category: bugfix bugzilla: 187372, https://gitee.com/openeuler/kernel/issues/I5K0OM CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- Ever since we added shadown format buffers to the log items, log items need to handle the item being released with shadow buffers attached. Due to the fact this requirement was added at the same time we added new rmap/reflink intents, we missed the cleanup of those items. In theory, this means shadow buffers can be leaked in a very small window when a shutdown is initiated. Testing with KASAN shows this leak does not happen in practice - we haven't identified a single leak in several years of shutdown testing since ~v4.8 kernels. However, the intent whiteout cleanup mechanism results in every cancelled intent in exactly the same state as this tiny race window creates and so if intents down clean up shadow buffers on final release we will leak the shadow buffer for just about every intent we create. Hence we start with this patch to close this condition off and ensure that when whiteouts start to be used we don't leak lots of memory. Signed-off-by: Dave Chinner <dchinner(a)redhat.com> Reviewed-by: Darrick J. Wong <djwong(a)kernel.org> Reviewed-by: Allison Henderson <allison.henderson(a)oracle.com> Signed-off-by: Dave Chinner <david(a)fromorbit.com> conflicts: fs/xfs/xfs_bmap_item.c fs/xfs/xfs_icreate_item.c fs/xfs/xfs_refcount_item.c fs/xfs/xfs_rmap_item.c Signed-off-by: Li Nan <linan122(a)huawei.com> Reviewed-by: Yang Erkun <yangerkun(a)huawei.com> Reviewed-by: Zhang Yi <yi.zhang(a)huawei.com> Signed-off-by: Jialin Zhang <zhangjialin11(a)huawei.com> --- fs/xfs/xfs_bmap_item.c | 2 ++ fs/xfs/xfs_icreate_item.c | 1 + fs/xfs/xfs_refcount_item.c | 2 ++ fs/xfs/xfs_rmap_item.c | 2 ++ 4 files changed, 7 insertions(+) diff --git a/fs/xfs/xfs_bmap_item.c b/fs/xfs/xfs_bmap_item.c index 44ec0f2d5253..e6de8081451f 100644 --- a/fs/xfs/xfs_bmap_item.c +++ b/fs/xfs/xfs_bmap_item.c @@ -40,6 +40,7 @@ STATIC void xfs_bui_item_free( struct xfs_bui_log_item *buip) { + kmem_free(buip->bui_item.li_lv_shadow); kmem_cache_free(xfs_bui_zone, buip); } @@ -199,6 +200,7 @@ xfs_bud_item_release( struct xfs_bud_log_item *budp = BUD_ITEM(lip); xfs_bui_release(budp->bud_buip); + kmem_free(budp->bud_item.li_lv_shadow); kmem_cache_free(xfs_bud_zone, budp); } diff --git a/fs/xfs/xfs_icreate_item.c b/fs/xfs/xfs_icreate_item.c index 9b3994b9c716..aa8c7c261d24 100644 --- a/fs/xfs/xfs_icreate_item.c +++ b/fs/xfs/xfs_icreate_item.c @@ -63,6 +63,7 @@ STATIC void xfs_icreate_item_release( struct xfs_log_item *lip) { + kmem_free(ICR_ITEM(lip)->ic_item.li_lv_shadow); kmem_cache_free(xfs_icreate_zone, ICR_ITEM(lip)); } diff --git a/fs/xfs/xfs_refcount_item.c b/fs/xfs/xfs_refcount_item.c index 0dee316283a9..9f4ff45c7a93 100644 --- a/fs/xfs/xfs_refcount_item.c +++ b/fs/xfs/xfs_refcount_item.c @@ -35,6 +35,7 @@ STATIC void xfs_cui_item_free( struct xfs_cui_log_item *cuip) { + kmem_free(cuip->cui_item.li_lv_shadow); if (cuip->cui_format.cui_nextents > XFS_CUI_MAX_FAST_EXTENTS) kmem_free(cuip); else @@ -204,6 +205,7 @@ xfs_cud_item_release( struct xfs_cud_log_item *cudp = CUD_ITEM(lip); xfs_cui_release(cudp->cud_cuip); + kmem_free(cudp->cud_item.li_lv_shadow); kmem_cache_free(xfs_cud_zone, cudp); } diff --git a/fs/xfs/xfs_rmap_item.c b/fs/xfs/xfs_rmap_item.c index 20905953fe76..b5447ac7cb9b 100644 --- a/fs/xfs/xfs_rmap_item.c +++ b/fs/xfs/xfs_rmap_item.c @@ -35,6 +35,7 @@ STATIC void xfs_rui_item_free( struct xfs_rui_log_item *ruip) { + kmem_free(ruip->rui_item.li_lv_shadow); if (ruip->rui_format.rui_nextents > XFS_RUI_MAX_FAST_EXTENTS) kmem_free(ruip); else @@ -227,6 +228,7 @@ xfs_rud_item_release( struct xfs_rud_log_item *rudp = RUD_ITEM(lip); xfs_rui_release(rudp->rud_ruip); + kmem_free(rudp->rud_item.li_lv_shadow); kmem_cache_free(xfs_rud_zone, rudp); } -- 2.25.1

1 9

[PATCH openEuler-5.10-LTS-SP1 01/20] xfs: fix potential log item leak
by Jialin Zhang 07 Feb '23

07 Feb '23

From: Dave Chinner <dchinner(a)redhat.com> mainline inclusion from mainline-v5.19-rc1 commit c230a4a85bcdbfc1a7415deec6caf04e8fca1301 category: bugfix bugzilla: 187372, https://gitee.com/openeuler/kernel/issues/I5K0OM CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- Ever since we added shadown format buffers to the log items, log items need to handle the item being released with shadow buffers attached. Due to the fact this requirement was added at the same time we added new rmap/reflink intents, we missed the cleanup of those items. In theory, this means shadow buffers can be leaked in a very small window when a shutdown is initiated. Testing with KASAN shows this leak does not happen in practice - we haven't identified a single leak in several years of shutdown testing since ~v4.8 kernels. However, the intent whiteout cleanup mechanism results in every cancelled intent in exactly the same state as this tiny race window creates and so if intents down clean up shadow buffers on final release we will leak the shadow buffer for just about every intent we create. Hence we start with this patch to close this condition off and ensure that when whiteouts start to be used we don't leak lots of memory. Signed-off-by: Dave Chinner <dchinner(a)redhat.com> Reviewed-by: Darrick J. Wong <djwong(a)kernel.org> Reviewed-by: Allison Henderson <allison.henderson(a)oracle.com> Signed-off-by: Dave Chinner <david(a)fromorbit.com> conflicts: fs/xfs/xfs_bmap_item.c fs/xfs/xfs_icreate_item.c fs/xfs/xfs_refcount_item.c fs/xfs/xfs_rmap_item.c Signed-off-by: Li Nan <linan122(a)huawei.com> Reviewed-by: Yang Erkun <yangerkun(a)huawei.com> Reviewed-by: Zhang Yi <yi.zhang(a)huawei.com> Signed-off-by: Jialin Zhang <zhangjialin11(a)huawei.com> --- fs/xfs/xfs_bmap_item.c | 2 ++ fs/xfs/xfs_icreate_item.c | 1 + fs/xfs/xfs_refcount_item.c | 2 ++ fs/xfs/xfs_rmap_item.c | 2 ++ 4 files changed, 7 insertions(+) diff --git a/fs/xfs/xfs_bmap_item.c b/fs/xfs/xfs_bmap_item.c index 44ec0f2d5253..e6de8081451f 100644 --- a/fs/xfs/xfs_bmap_item.c +++ b/fs/xfs/xfs_bmap_item.c @@ -40,6 +40,7 @@ STATIC void xfs_bui_item_free( struct xfs_bui_log_item *buip) { + kmem_free(buip->bui_item.li_lv_shadow); kmem_cache_free(xfs_bui_zone, buip); } @@ -199,6 +200,7 @@ xfs_bud_item_release( struct xfs_bud_log_item *budp = BUD_ITEM(lip); xfs_bui_release(budp->bud_buip); + kmem_free(budp->bud_item.li_lv_shadow); kmem_cache_free(xfs_bud_zone, budp); } diff --git a/fs/xfs/xfs_icreate_item.c b/fs/xfs/xfs_icreate_item.c index 9b3994b9c716..aa8c7c261d24 100644 --- a/fs/xfs/xfs_icreate_item.c +++ b/fs/xfs/xfs_icreate_item.c @@ -63,6 +63,7 @@ STATIC void xfs_icreate_item_release( struct xfs_log_item *lip) { + kmem_free(ICR_ITEM(lip)->ic_item.li_lv_shadow); kmem_cache_free(xfs_icreate_zone, ICR_ITEM(lip)); } diff --git a/fs/xfs/xfs_refcount_item.c b/fs/xfs/xfs_refcount_item.c index 0dee316283a9..9f4ff45c7a93 100644 --- a/fs/xfs/xfs_refcount_item.c +++ b/fs/xfs/xfs_refcount_item.c @@ -35,6 +35,7 @@ STATIC void xfs_cui_item_free( struct xfs_cui_log_item *cuip) { + kmem_free(cuip->cui_item.li_lv_shadow); if (cuip->cui_format.cui_nextents > XFS_CUI_MAX_FAST_EXTENTS) kmem_free(cuip); else @@ -204,6 +205,7 @@ xfs_cud_item_release( struct xfs_cud_log_item *cudp = CUD_ITEM(lip); xfs_cui_release(cudp->cud_cuip); + kmem_free(cudp->cud_item.li_lv_shadow); kmem_cache_free(xfs_cud_zone, cudp); } diff --git a/fs/xfs/xfs_rmap_item.c b/fs/xfs/xfs_rmap_item.c index 20905953fe76..b5447ac7cb9b 100644 --- a/fs/xfs/xfs_rmap_item.c +++ b/fs/xfs/xfs_rmap_item.c @@ -35,6 +35,7 @@ STATIC void xfs_rui_item_free( struct xfs_rui_log_item *ruip) { + kmem_free(ruip->rui_item.li_lv_shadow); if (ruip->rui_format.rui_nextents > XFS_RUI_MAX_FAST_EXTENTS) kmem_free(ruip); else @@ -227,6 +228,7 @@ xfs_rud_item_release( struct xfs_rud_log_item *rudp = RUD_ITEM(lip); xfs_rui_release(rudp->rud_ruip); + kmem_free(rudp->rud_item.li_lv_shadow); kmem_cache_free(xfs_rud_zone, rudp); } -- 2.25.1

1 19

[PATCH openEuler-5.10-LTS-SP1 01/74] drm/msm/dsi: fix the inconsistent indenting
by Jialin Zhang 07 Feb '23

07 Feb '23

From: sunliming <sunliming(a)kylinos.cn> stable inclusion from stable-v5.10.142 commit 631fbefd877721d15c4f525cc71e851e0e588c8e category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I6CSFH Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- [ Upstream commit 2f25a1fb4ec516c5ad67afd754334b491b9f09a5 ] Fix the inconsistent indenting in function msm_dsi_dphy_timing_calc_v3(). Fix the following smatch warnings: drivers/gpu/drm/msm/dsi/phy/dsi_phy.c:350 msm_dsi_dphy_timing_calc_v3() warn: inconsistent indenting Fixes: f1fa7ff44056 ("drm/msm/dsi: implement auto PHY timing calculator for 10nm PHY") Reported-by: kernel test robot <lkp(a)intel.com> Signed-off-by: sunliming <sunliming(a)kylinos.cn> Reviewed-by: Abhinav Kumar <quic_abhinavk(a)quicinc.com> Patchwork: https://patchwork.freedesktop.org/patch/494662/ Link: https://lore.kernel.org/r/20220719015622.646718-1-sunliming@kylinos.cn Signed-off-by: Abhinav Kumar <quic_abhinavk(a)quicinc.com> Signed-off-by: Sasha Levin <sashal(a)kernel.org> Signed-off-by: Jialin Zhang <zhangjialin11(a)huawei.com> Reviewed-by: Zheng Zengkai <zhengzengkai(a)huawei.com> --- drivers/gpu/drm/msm/dsi/phy/dsi_phy.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c index e07986ab52c2..2e0be85ec394 100644 --- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c +++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy.c @@ -345,7 +345,7 @@ int msm_dsi_dphy_timing_calc_v3(struct msm_dsi_dphy_timing *timing, } else { timing->shared_timings.clk_pre = linear_inter(tmax, tmin, pcnt2, 0, false); - timing->shared_timings.clk_pre_inc_by_2 = 0; + timing->shared_timings.clk_pre_inc_by_2 = 0; } timing->ta_go = 3; -- 2.25.1

1 73

[PATCH openEuler-1.0-LTS 1/2] block: don't allow a disk link holder to itself
by Yongqiang Liu 07 Feb '23

07 Feb '23

From: Yu Kuai <yukuai3(a)huawei.com> mainline inclusion from mainline-v6.2-rc1 commit 077a4033541fc96fb0a955985aab7d1f353da831 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I6B4N7 CVE: NA -------------------------------- After creating a dm device, then user can reload such dm with itself, and dead loop will be triggered because dm keep looking up to itself. Test procedures: 1) dmsetup create test --table "xxx sda", assume dm-0 is created 2) dmsetup suspend test 3) dmsetup reload test --table "xxx dm-0" 4) dmsetup resume test Test result: BUG: TASK stack guard page was hit at 00000000736a261f (stack is 000000008d12c88d..00000000c8dd82d5) stack guard page: 0000 [#1] PREEMPT SMP CPU: 29 PID: 946 Comm: systemd-udevd Not tainted 6.1.0-rc3-next-20221101-00006-g17640ca3b0ee #1295 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS ?-20190727_073836-buildvm-ppc64le-16.ppc.fedoraproject.org-3.fc31 04/01/2014 RIP: 0010:dm_prepare_ioctl+0xf/0x1e0 Code: da 48 83 05 4a 7c 99 0b 01 41 89 c4 eb cd e8 b8 1f 40 00 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 41 57 48 83 05 a1 5a 99 0b 01 <41> 56 49 89 d6 41 55 4c 8d af 90 02 00 00 9 RSP: 0018:ffffc90002090000 EFLAGS: 00010206 RAX: ffff8881049d6800 RBX: ffff88817e589000 RCX: 0000000000000000 RDX: ffffc90002090010 RSI: ffffc9000209001c RDI: ffff88817e589000 RBP: 00000000484a101d R08: 0000000000000000 R09: 0000000000000007 R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000005331 R13: 0000000000005331 R14: 0000000000000000 R15: 0000000000000000 FS: 00007fddf9609200(0000) GS:ffff889fbfd40000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: ffffc9000208fff8 CR3: 0000000179043000 CR4: 00000000000006e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Call Trace: <TASK> dm_blk_ioctl+0x50/0x1c0 ? dm_prepare_ioctl+0xe0/0x1e0 dm_blk_ioctl+0x88/0x1c0 dm_blk_ioctl+0x88/0x1c0 ......(a lot of same lines) dm_blk_ioctl+0x88/0x1c0 dm_blk_ioctl+0x88/0x1c0 blkdev_ioctl+0x184/0x3e0 __x64_sys_ioctl+0xa3/0x110 do_syscall_64+0x35/0x80 entry_SYSCALL_64_after_hwframe+0x63/0xcd RIP: 0033:0x7fddf7306577 Code: b3 66 90 48 8b 05 11 89 2c 00 64 c7 00 26 00 00 00 48 c7 c0 ff ff ff ff c3 66 2e 0f 1f 84 00 00 00 00 00 b8 10 00 00 00 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 8b 0d e1 88 8 RSP: 002b:00007ffd0b2ec318 EFLAGS: 00000246 ORIG_RAX: 0000000000000010 RAX: ffffffffffffffda RBX: 00005634ef478320 RCX: 00007fddf7306577 RDX: 0000000000000000 RSI: 0000000000005331 RDI: 0000000000000007 RBP: 0000000000000007 R08: 00005634ef4843e0 R09: 0000000000000080 R10: 00007fddf75cfb38 R11: 0000000000000246 R12: 00000000030d4000 R13: 0000000000000000 R14: 0000000000000000 R15: 00005634ef48b800 </TASK> Modules linked in: ---[ end trace 0000000000000000 ]--- RIP: 0010:dm_prepare_ioctl+0xf/0x1e0 Code: da 48 83 05 4a 7c 99 0b 01 41 89 c4 eb cd e8 b8 1f 40 00 0f 1f 84 00 00 00 00 00 0f 1f 44 00 00 41 57 48 83 05 a1 5a 99 0b 01 <41> 56 49 89 d6 41 55 4c 8d af 90 02 00 00 9 RSP: 0018:ffffc90002090000 EFLAGS: 00010206 RAX: ffff8881049d6800 RBX: ffff88817e589000 RCX: 0000000000000000 RDX: ffffc90002090010 RSI: ffffc9000209001c RDI: ffff88817e589000 RBP: 00000000484a101d R08: 0000000000000000 R09: 0000000000000007 R10: 0000000000000000 R11: 0000000000000000 R12: 0000000000005331 R13: 0000000000005331 R14: 0000000000000000 R15: 0000000000000000 FS: 00007fddf9609200(0000) GS:ffff889fbfd40000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: ffffc9000208fff8 CR3: 0000000179043000 CR4: 00000000000006e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 Kernel panic - not syncing: Fatal exception in interrupt Kernel Offset: disabled ---[ end Kernel panic - not syncing: Fatal exception in interrupt ]--- Fix the problem by forbidding a disk to create link to itself. Signed-off-by: Yu Kuai <yukuai3(a)huawei.com> Reviewed-by: Christoph Hellwig <hch(a)lst.de> Link: https://lore.kernel.org/r/20221115141054.1051801-11-yukuai1@huaweicloud.com Signed-off-by: Jens Axboe <axboe(a)kernel.dk> Signed-off-by: Li Lingfeng <lilingfeng3(a)huawei.com> Reviewed-by: Yang Erkun <yangerkun(a)huawei.com> Reviewed-by: Zhang Yi <yi.zhang(a)huawei.com> Signed-off-by: Yongqiang Liu <liuyongqiang13(a)huawei.com> --- fs/block_dev.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/fs/block_dev.c b/fs/block_dev.c index 2680092c022d..6ba91b97753f 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -1305,6 +1305,8 @@ int bd_link_disk_holder(struct block_device *bdev, struct gendisk *disk) struct bd_holder_disk *holder; int ret = 0; + if (bdev->bd_disk == disk) + return -EINVAL; /* * bdev could be deleted beneath us which would implicitly destroy * the holder directory. Hold on to it. -- 2.25.1

1 1

[PATCH openEuler-1.0-LTS 1/3] ipv6: raw: Deduct extension header length in rawv6_push_pending_frames
by Yongqiang Liu 06 Feb '23

06 Feb '23

From: Herbert Xu <herbert(a)gondor.apana.org.au> stable inclusion from stable-v4.19.270 commit f487d636e49bc1fdfbd8105bc1ab159164e2d8bd category: bugfix bugzilla: 188291, https://gitee.com/src-openeuler/kernel/issues/I6B1V2 CVE: CVE-2023-0394 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?h=… -------------------------------- commit cb3e9864cdbe35ff6378966660edbcbac955fe17 upstream. The total cork length created by ip6_append_data includes extension headers, so we must exclude them when comparing them against the IPV6_CHECKSUM offset which does not include extension headers. Reported-by: Kyle Zeng <zengyhkyle(a)gmail.com> Fixes: 357b40a18b04 ("[IPV6]: IPV6_CHECKSUM socket option can corrupt kernel memory") Signed-off-by: Herbert Xu <herbert(a)gondor.apana.org.au> Signed-off-by: David S. Miller <davem(a)davemloft.net> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Lu Wei <luwei32(a)huawei.com> Reviewed-by: Yue Haibing <yuehaibing(a)huawei.com> Reviewed-by: Xiu Jianfeng <xiujianfeng(a)huawei.com> Signed-off-by: Yongqiang Liu <liuyongqiang13(a)huawei.com> --- net/ipv6/raw.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index 412d4f60a408..8ce6414edd88 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -543,6 +543,7 @@ static int rawv6_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, static int rawv6_push_pending_frames(struct sock *sk, struct flowi6 *fl6, struct raw6_sock *rp) { + struct ipv6_txoptions *opt; struct sk_buff *skb; int err = 0; int offset; @@ -560,6 +561,9 @@ static int rawv6_push_pending_frames(struct sock *sk, struct flowi6 *fl6, offset = rp->offset; total_len = inet_sk(sk)->cork.base.length; + opt = inet6_sk(sk)->cork.opt; + total_len -= opt ? opt->opt_flen : 0; + if (offset >= total_len - 1) { err = -EINVAL; ip6_flush_pending_frames(sk); -- 2.25.1

1 2

[openEuler-5.10 1/4] SUNRPC: Clean up the handling of page padding in rpc_prepare_reply_pages()
by Zheng Zengkai 06 Feb '23

06 Feb '23

From: Trond Myklebust <trond.myklebust(a)hammerspace.com> mainline inclusion from mainline-v5.11-rc1 commit 9ed5af268e88f6e5b65376be98d652b37cb20d7b bugzilla: https://gitee.com/openeuler/kernel/issues/I6D0MJ Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- rpc_prepare_reply_pages() currently expects the 'hdrsize' argument to contain the length of the data that we expect to want placed in the head kvec plus a count of 1 word of padding that is placed after the page data. This is very confusing when trying to read the code, and sometimes leads to callers adding an arbitrary value of '1' just in order to satisfy the requirement (whether or not the page data actually needs such padding). This patch aims to clarify the code by changing the 'hdrsize' argument to remove that 1 word of padding. This means we need to subtract the padding from all the existing callers. Fixes: 02ef04e432ba ("NFS: Account for XDR pad of buf->pages") Signed-off-by: Trond Myklebust <trond.myklebust(a)hammerspace.com> Signed-off-by: Zheng Zengkai <zhengzengkai(a)huawei.com> --- fs/nfs/nfs2xdr.c | 19 ++++++++++--------- fs/nfs/nfs3xdr.c | 29 ++++++++++++++++------------- fs/nfs/nfs4xdr.c | 36 +++++++++++++++++++----------------- net/sunrpc/clnt.c | 5 +---- net/sunrpc/xdr.c | 3 --- 5 files changed, 46 insertions(+), 46 deletions(-) diff --git a/fs/nfs/nfs2xdr.c b/fs/nfs/nfs2xdr.c index 5e6453e9b307..3d5ba43f44bb 100644 --- a/fs/nfs/nfs2xdr.c +++ b/fs/nfs/nfs2xdr.c @@ -34,6 +34,7 @@ * Declare the space requirements for NFS arguments and replies as * number of 32bit-words */ +#define NFS_pagepad_sz (1) /* Page padding */ #define NFS_fhandle_sz (8) #define NFS_sattr_sz (8) #define NFS_filename_sz (1+(NFS2_MAXNAMLEN>>2)) @@ -56,11 +57,11 @@ #define NFS_attrstat_sz (1+NFS_fattr_sz) #define NFS_diropres_sz (1+NFS_fhandle_sz+NFS_fattr_sz) -#define NFS_readlinkres_sz (2+1) -#define NFS_readres_sz (1+NFS_fattr_sz+1+1) +#define NFS_readlinkres_sz (2+NFS_pagepad_sz) +#define NFS_readres_sz (1+NFS_fattr_sz+1+NFS_pagepad_sz) #define NFS_writeres_sz (NFS_attrstat_sz) #define NFS_stat_sz (1) -#define NFS_readdirres_sz (1+1) +#define NFS_readdirres_sz (1+NFS_pagepad_sz) #define NFS_statfsres_sz (1+NFS_info_sz) static int nfs_stat_to_errno(enum nfs_stat); @@ -592,8 +593,8 @@ static void nfs2_xdr_enc_readlinkargs(struct rpc_rqst *req, const struct nfs_readlinkargs *args = data; encode_fhandle(xdr, args->fh); - rpc_prepare_reply_pages(req, args->pages, args->pgbase, - args->pglen, NFS_readlinkres_sz); + rpc_prepare_reply_pages(req, args->pages, args->pgbase, args->pglen, + NFS_readlinkres_sz - NFS_pagepad_sz); } /* @@ -628,8 +629,8 @@ static void nfs2_xdr_enc_readargs(struct rpc_rqst *req, const struct nfs_pgio_args *args = data; encode_readargs(xdr, args); - rpc_prepare_reply_pages(req, args->pages, args->pgbase, - args->count, NFS_readres_sz); + rpc_prepare_reply_pages(req, args->pages, args->pgbase, args->count, + NFS_readres_sz - NFS_pagepad_sz); req->rq_rcv_buf.flags |= XDRBUF_READ; } @@ -786,8 +787,8 @@ static void nfs2_xdr_enc_readdirargs(struct rpc_rqst *req, const struct nfs_readdirargs *args = data; encode_readdirargs(xdr, args); - rpc_prepare_reply_pages(req, args->pages, 0, - args->count, NFS_readdirres_sz); + rpc_prepare_reply_pages(req, args->pages, 0, args->count, + NFS_readdirres_sz - NFS_pagepad_sz); } /* diff --git a/fs/nfs/nfs3xdr.c b/fs/nfs/nfs3xdr.c index b5a9379b1450..2c0cad7c51d6 100644 --- a/fs/nfs/nfs3xdr.c +++ b/fs/nfs/nfs3xdr.c @@ -33,6 +33,7 @@ * Declare the space requirements for NFS arguments and replies as * number of 32bit-words */ +#define NFS3_pagepad_sz (1) /* Page padding */ #define NFS3_fhandle_sz (1+16) #define NFS3_fh_sz (NFS3_fhandle_sz) /* shorthand */ #define NFS3_post_op_fh_sz (1+NFS3_fh_sz) @@ -70,13 +71,13 @@ #define NFS3_removeres_sz (NFS3_setattrres_sz) #define NFS3_lookupres_sz (1+NFS3_fh_sz+(2 * NFS3_post_op_attr_sz)) #define NFS3_accessres_sz (1+NFS3_post_op_attr_sz+1) -#define NFS3_readlinkres_sz (1+NFS3_post_op_attr_sz+1+1) -#define NFS3_readres_sz (1+NFS3_post_op_attr_sz+3+1) +#define NFS3_readlinkres_sz (1+NFS3_post_op_attr_sz+1+NFS3_pagepad_sz) +#define NFS3_readres_sz (1+NFS3_post_op_attr_sz+3+NFS3_pagepad_sz) #define NFS3_writeres_sz (1+NFS3_wcc_data_sz+4) #define NFS3_createres_sz (1+NFS3_post_op_fh_sz+NFS3_post_op_attr_sz+NFS3_wcc_data_sz) #define NFS3_renameres_sz (1+(2 * NFS3_wcc_data_sz)) #define NFS3_linkres_sz (1+NFS3_post_op_attr_sz+NFS3_wcc_data_sz) -#define NFS3_readdirres_sz (1+NFS3_post_op_attr_sz+2+1) +#define NFS3_readdirres_sz (1+NFS3_post_op_attr_sz+2+NFS3_pagepad_sz) #define NFS3_fsstatres_sz (1+NFS3_post_op_attr_sz+13) #define NFS3_fsinfores_sz (1+NFS3_post_op_attr_sz+12) #define NFS3_pathconfres_sz (1+NFS3_post_op_attr_sz+6) @@ -86,7 +87,8 @@ #define ACL3_setaclargs_sz (NFS3_fh_sz+1+ \ XDR_QUADLEN(NFS_ACL_INLINE_BUFSIZE)) #define ACL3_getaclres_sz (1+NFS3_post_op_attr_sz+1+ \ - XDR_QUADLEN(NFS_ACL_INLINE_BUFSIZE)+1) + XDR_QUADLEN(NFS_ACL_INLINE_BUFSIZE)+\ + NFS3_pagepad_sz) #define ACL3_setaclres_sz (1+NFS3_post_op_attr_sz) static int nfs3_stat_to_errno(enum nfs_stat); @@ -910,8 +912,8 @@ static void nfs3_xdr_enc_readlink3args(struct rpc_rqst *req, const struct nfs3_readlinkargs *args = data; encode_nfs_fh3(xdr, args->fh); - rpc_prepare_reply_pages(req, args->pages, args->pgbase, - args->pglen, NFS3_readlinkres_sz); + rpc_prepare_reply_pages(req, args->pages, args->pgbase, args->pglen, + NFS3_readlinkres_sz - NFS3_pagepad_sz); } /* @@ -940,7 +942,8 @@ static void nfs3_xdr_enc_read3args(struct rpc_rqst *req, const void *data) { const struct nfs_pgio_args *args = data; - unsigned int replen = args->replen ? args->replen : NFS3_readres_sz; + unsigned int replen = args->replen ? args->replen : + NFS3_readres_sz - NFS3_pagepad_sz; encode_read3args(xdr, args); rpc_prepare_reply_pages(req, args->pages, args->pgbase, @@ -1240,8 +1243,8 @@ static void nfs3_xdr_enc_readdir3args(struct rpc_rqst *req, const struct nfs3_readdirargs *args = data; encode_readdir3args(xdr, args); - rpc_prepare_reply_pages(req, args->pages, 0, - args->count, NFS3_readdirres_sz); + rpc_prepare_reply_pages(req, args->pages, 0, args->count, + NFS3_readdirres_sz - NFS3_pagepad_sz); } /* @@ -1282,8 +1285,8 @@ static void nfs3_xdr_enc_readdirplus3args(struct rpc_rqst *req, const struct nfs3_readdirargs *args = data; encode_readdirplus3args(xdr, args); - rpc_prepare_reply_pages(req, args->pages, 0, - args->count, NFS3_readdirres_sz); + rpc_prepare_reply_pages(req, args->pages, 0, args->count, + NFS3_readdirres_sz - NFS3_pagepad_sz); } /* @@ -1329,7 +1332,7 @@ static void nfs3_xdr_enc_getacl3args(struct rpc_rqst *req, if (args->mask & (NFS_ACL | NFS_DFACL)) { rpc_prepare_reply_pages(req, args->pages, 0, NFSACL_MAXPAGES << PAGE_SHIFT, - ACL3_getaclres_sz); + ACL3_getaclres_sz - NFS3_pagepad_sz); req->rq_rcv_buf.flags |= XDRBUF_SPARSE_PAGES; } } @@ -1649,7 +1652,7 @@ static int nfs3_xdr_dec_read3res(struct rpc_rqst *req, struct xdr_stream *xdr, result->op_status = status; if (status != NFS3_OK) goto out_status; - result->replen = 4 + ((xdr_stream_pos(xdr) - pos) >> 2); + result->replen = 3 + ((xdr_stream_pos(xdr) - pos) >> 2); error = decode_read3resok(xdr, result); out: return error; diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index e2f0e3446e22..f64b28d5bc22 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -84,6 +84,7 @@ static int decode_layoutget(struct xdr_stream *xdr, struct rpc_rqst *req, /* lock,open owner id: * we currently use size 2 (u64) out of (NFS4_OPAQUE_LIMIT >> 2) */ +#define pagepad_maxsz (1) #define open_owner_id_maxsz (1 + 2 + 1 + 1 + 2) #define lock_owner_id_maxsz (1 + 1 + 4) #define decode_lockowner_maxsz (1 + XDR_QUADLEN(IDMAP_NAMESZ)) @@ -215,14 +216,14 @@ static int decode_layoutget(struct xdr_stream *xdr, struct rpc_rqst *req, nfs4_fattr_bitmap_maxsz) #define encode_read_maxsz (op_encode_hdr_maxsz + \ encode_stateid_maxsz + 3) -#define decode_read_maxsz (op_decode_hdr_maxsz + 2 + 1) +#define decode_read_maxsz (op_decode_hdr_maxsz + 2 + pagepad_maxsz) #define encode_readdir_maxsz (op_encode_hdr_maxsz + \ 2 + encode_verifier_maxsz + 5 + \ nfs4_label_maxsz) #define decode_readdir_maxsz (op_decode_hdr_maxsz + \ - decode_verifier_maxsz + 1) + decode_verifier_maxsz + pagepad_maxsz) #define encode_readlink_maxsz (op_encode_hdr_maxsz) -#define decode_readlink_maxsz (op_decode_hdr_maxsz + 1 + 1) +#define decode_readlink_maxsz (op_decode_hdr_maxsz + 1 + pagepad_maxsz) #define encode_write_maxsz (op_encode_hdr_maxsz + \ encode_stateid_maxsz + 4) #define decode_write_maxsz (op_decode_hdr_maxsz + \ @@ -284,14 +285,14 @@ static int decode_layoutget(struct xdr_stream *xdr, struct rpc_rqst *req, #define decode_delegreturn_maxsz (op_decode_hdr_maxsz) #define encode_getacl_maxsz (encode_getattr_maxsz) #define decode_getacl_maxsz (op_decode_hdr_maxsz + \ - nfs4_fattr_bitmap_maxsz + 1 + 1) + nfs4_fattr_bitmap_maxsz + 1 + pagepad_maxsz) #define encode_setacl_maxsz (op_encode_hdr_maxsz + \ encode_stateid_maxsz + 3) #define decode_setacl_maxsz (decode_setattr_maxsz) #define encode_fs_locations_maxsz \ (encode_getattr_maxsz) #define decode_fs_locations_maxsz \ - (1) + (pagepad_maxsz) #define encode_secinfo_maxsz (op_encode_hdr_maxsz + nfs4_name_maxsz) #define decode_secinfo_maxsz (op_decode_hdr_maxsz + 1 + ((NFS_MAX_SECFLAVORS * (16 + GSS_OID_MAX_LEN)) / 4)) @@ -393,12 +394,13 @@ static int decode_layoutget(struct xdr_stream *xdr, struct rpc_rqst *req, /* devaddr4 payload is read into page */ \ 1 /* notification bitmap length */ + \ 1 /* notification bitmap, word 0 */ + \ - 1 /* possible XDR padding */) + pagepad_maxsz /* possible XDR padding */) #define encode_layoutget_maxsz (op_encode_hdr_maxsz + 10 + \ encode_stateid_maxsz) #define decode_layoutget_maxsz (op_decode_hdr_maxsz + 8 + \ decode_stateid_maxsz + \ - XDR_QUADLEN(PNFS_LAYOUT_MAXSIZE) + 1) + XDR_QUADLEN(PNFS_LAYOUT_MAXSIZE) + \ + pagepad_maxsz) #define encode_layoutcommit_maxsz (op_encode_hdr_maxsz + \ 2 /* offset */ + \ 2 /* length */ + \ @@ -2342,7 +2344,7 @@ static void nfs4_xdr_enc_open(struct rpc_rqst *req, struct xdr_stream *xdr, encode_layoutget(xdr, args->lg_args, &hdr); rpc_prepare_reply_pages(req, args->lg_args->layout.pages, 0, args->lg_args->layout.pglen, - hdr.replen); + hdr.replen - pagepad_maxsz); } encode_nops(&hdr); } @@ -2388,7 +2390,7 @@ static void nfs4_xdr_enc_open_noattr(struct rpc_rqst *req, encode_layoutget(xdr, args->lg_args, &hdr); rpc_prepare_reply_pages(req, args->lg_args->layout.pages, 0, args->lg_args->layout.pglen, - hdr.replen); + hdr.replen - pagepad_maxsz); } encode_nops(&hdr); } @@ -2499,7 +2501,7 @@ static void nfs4_xdr_enc_readlink(struct rpc_rqst *req, struct xdr_stream *xdr, encode_readlink(xdr, args, req, &hdr); rpc_prepare_reply_pages(req, args->pages, args->pgbase, - args->pglen, hdr.replen); + args->pglen, hdr.replen - pagepad_maxsz); encode_nops(&hdr); } @@ -2520,7 +2522,7 @@ static void nfs4_xdr_enc_readdir(struct rpc_rqst *req, struct xdr_stream *xdr, encode_readdir(xdr, args, req, &hdr); rpc_prepare_reply_pages(req, args->pages, args->pgbase, - args->count, hdr.replen); + args->count, hdr.replen - pagepad_maxsz); encode_nops(&hdr); } @@ -2541,7 +2543,7 @@ static void nfs4_xdr_enc_read(struct rpc_rqst *req, struct xdr_stream *xdr, encode_read(xdr, args, &hdr); rpc_prepare_reply_pages(req, args->pages, args->pgbase, - args->count, hdr.replen); + args->count, hdr.replen - pagepad_maxsz); req->rq_rcv_buf.flags |= XDRBUF_READ; encode_nops(&hdr); } @@ -2588,7 +2590,7 @@ static void nfs4_xdr_enc_getacl(struct rpc_rqst *req, struct xdr_stream *xdr, ARRAY_SIZE(nfs4_acl_bitmap), &hdr); rpc_prepare_reply_pages(req, args->acl_pages, 0, - args->acl_len, replen + 1); + args->acl_len, replen); encode_nops(&hdr); } @@ -2810,7 +2812,7 @@ static void nfs4_xdr_enc_fs_locations(struct rpc_rqst *req, } rpc_prepare_reply_pages(req, (struct page **)&args->page, 0, - PAGE_SIZE, replen + 1); + PAGE_SIZE, replen); encode_nops(&hdr); } @@ -3014,14 +3016,14 @@ static void nfs4_xdr_enc_getdeviceinfo(struct rpc_rqst *req, encode_compound_hdr(xdr, req, &hdr); encode_sequence(xdr, &args->seq_args, &hdr); - replen = hdr.replen + op_decode_hdr_maxsz; + replen = hdr.replen + op_decode_hdr_maxsz + 2; encode_getdeviceinfo(xdr, args, &hdr); /* set up reply kvec. device_addr4 opaque data is read into the * pages */ rpc_prepare_reply_pages(req, args->pdev->pages, args->pdev->pgbase, - args->pdev->pglen, replen + 2 + 1); + args->pdev->pglen, replen); encode_nops(&hdr); } @@ -3043,7 +3045,7 @@ static void nfs4_xdr_enc_layoutget(struct rpc_rqst *req, encode_layoutget(xdr, args, &hdr); rpc_prepare_reply_pages(req, args->layout.pages, 0, - args->layout.pglen, hdr.replen); + args->layout.pglen, hdr.replen - pagepad_maxsz); encode_nops(&hdr); } diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index 78c6648af782..88a4dff14666 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -1251,10 +1251,7 @@ void rpc_prepare_reply_pages(struct rpc_rqst *req, struct page **pages, unsigned int base, unsigned int len, unsigned int hdrsize) { - /* Subtract one to force an extra word of buffer space for the - * payload's XDR pad to fall into the rcv_buf's tail iovec. - */ - hdrsize += RPC_REPHDRSIZE + req->rq_cred->cr_auth->au_ralign - 1; + hdrsize += RPC_REPHDRSIZE + req->rq_cred->cr_auth->au_ralign; xdr_inline_pages(&req->rq_rcv_buf, hdrsize << 2, pages, base, len); trace_rpc_xdr_reply_pages(req->rq_task, &req->rq_rcv_buf); diff --git a/net/sunrpc/xdr.c b/net/sunrpc/xdr.c index d84bb5037bb5..b1684b19b6d5 100644 --- a/net/sunrpc/xdr.c +++ b/net/sunrpc/xdr.c @@ -193,9 +193,6 @@ xdr_inline_pages(struct xdr_buf *xdr, unsigned int offset, tail->iov_base = buf + offset; tail->iov_len = buflen - offset; - if ((xdr->page_len & 3) == 0) - tail->iov_len -= sizeof(__be32); - xdr->buflen += len; } EXPORT_SYMBOL_GPL(xdr_inline_pages); -- 2.20.1

1 3

[PATCH OLK-5.10] net: hns3: add support handling tx dhcp packets for ROH
by Ke Chen 06 Feb '23

06 Feb '23

driver inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I6BSMN ----------------------------------------------------------------------- For ROH distributed scenario, EID is allocated by DHCP mode. Driver needs to convert the origin MAC address to EID format, and updates the destination MAC, chaddr and client id(if exists) when transmit DHCP packets. Meantime, the chaddr field should follow the source mac address, in order to make the dhcp server reply to the right client. For the payload of dhcp packet changed, so the checksum of L4 should be calculated too. Signed-off-by: Jian Shen <shenjian15(a)huawei.com> Signed-off-by: Ke Chen <chenke54(a)huawei.com> --- .../net/ethernet/hisilicon/hns3/hns3_enet.c | 172 +++++++++++++++++- .../net/ethernet/hisilicon/hns3/hns3_enet.h | 50 +++++ .../hisilicon/hns3/hns3pf/hclge_main.c | 9 + 3 files changed, 226 insertions(+), 5 deletions(-) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c index cf79cd69c766..460f9d217a18 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c @@ -1165,6 +1165,142 @@ static void hns3_tx_spare_reclaim_cb(struct hns3_enet_ring *ring, } } +static struct hns3_dhcp_packet *hns3_get_dhcp_packet(struct sk_buff *skb, + int *dhcp_len) +{ + struct hns3_dhcp_packet *dhcp; + union l4_hdr_info l4; + int l4_payload_len; + + l4.hdr = skb_transport_header(skb); + if (l4.udp->dest != htons(HNS3_DHCP_CLIENT_PORT) || + l4.udp->source != htons(HNS3_DHCP_SERVER_PORT)) + return NULL; + + dhcp = (struct hns3_dhcp_packet *)(l4.hdr + sizeof(struct udphdr)); + l4_payload_len = ntohs(l4.udp->len) - sizeof(struct udphdr); + if (l4_payload_len < offsetof(struct hns3_dhcp_packet, options) || + dhcp->hlen != ETH_ALEN || + dhcp->cookie != htonl(HNS3_DHCP_MAGIC)) + return NULL; + + *dhcp_len = l4_payload_len; + return dhcp; +} + +static u8 *hns3_dhcp_option_scan(struct hns3_dhcp_packet *packet, + struct hns3_dhcp_opt_state *opt_state) +{ + int opt_len; + u8 *cur_opt; + + /* option bytes: [code][len][data0~data[len-1]] */ + while (opt_state->rem > 0) { + switch (opt_state->opt_ptr[DHCP_OPT_CODE]) { + /* option padding and end have no len and data byte. */ + case DHCP_OPT_PADDING: + opt_state->rem--; + opt_state->opt_ptr++; + break; + case DHCP_OPT_END: + if (DHCP_OVERLOAD_USE_FILE(opt_state->overload_flag)) { + opt_state->overload_flag |= + DHCP_OVERLOAD_FILE_USED; + opt_state->opt_ptr = packet->file; + opt_state->rem = sizeof(packet->file); + break; + } + if (DHCP_OVERLOAD_USE_SNAME(opt_state->overload_flag)) { + opt_state->overload_flag |= + DHCP_OVERLOAD_SNAME_USED; + opt_state->opt_ptr = packet->sname; + opt_state->rem = sizeof(packet->sname); + break; + } + return NULL; + default: + if (opt_state->rem <= DHCP_OPT_LEN) + return NULL; + /* opt_len includes code, len and data bytes */ + opt_len = opt_state->opt_ptr[DHCP_OPT_LEN] + + DHCP_OPT_DATA; + cur_opt = opt_state->opt_ptr; + if (opt_state->rem < opt_len) + return NULL; + + opt_state->opt_ptr += opt_len; + opt_state->rem -= opt_len; + if (cur_opt[DHCP_OPT_CODE] == DHCP_OPT_OVERLOAD) { + opt_state->overload_flag |= + cur_opt[DHCP_OPT_DATA]; + break; + } + return cur_opt; + } + } + + return NULL; +} + +static void hns3_dhcp_update_option61(struct hns3_nic_priv *priv, + struct hns3_dhcp_packet *packet, + int dhcp_len) +{ + struct hns3_dhcp_opt_state opt_state; + u8 *cur_opt; + + opt_state.opt_ptr = packet->options; + opt_state.rem = dhcp_len - offsetof(struct hns3_dhcp_packet, options); + opt_state.overload_flag = 0; + + cur_opt = hns3_dhcp_option_scan(packet, &opt_state); + while (cur_opt) { + if (cur_opt[DHCP_OPT_CODE] != DHCP_OPT_CLIENT_ID) { + cur_opt = hns3_dhcp_option_scan(packet, &opt_state); + continue; + } + if (cur_opt[DHCP_OPT_LEN] > ETH_ALEN) + ether_addr_copy(&cur_opt[DHCP_CLIENT_ID_MAC_OFT], + priv->roh_perm_mac); + break; + } +} + +static void hns3_dhcp_cal_l4_csum(struct sk_buff *skb) +{ + union l3_hdr_info l3; + union l4_hdr_info l4; + __wsum csum = 0; + int offset; + + if (skb->ip_summed == CHECKSUM_PARTIAL) + return; + + l3.hdr = skb_network_header(skb); + l4.hdr = skb_transport_header(skb); + offset = skb_transport_offset(skb); + l4.udp->check = 0; + csum = csum_partial(l4.udp, ntohs(l4.udp->len), 0); + l4.udp->check = csum_tcpudp_magic(l3.v4->saddr, l3.v4->daddr, + skb->len - offset, IPPROTO_UDP, csum); +} + +static void hns3_dhcp_packet_convert(struct hns3_nic_priv *priv, + struct sk_buff *skb, + struct hns3_dhcp_packet *dhcp, + int dhcp_len) +{ + struct ethhdr *l2hdr = eth_hdr(skb); + + if (!dhcp) + return; + + ether_addr_copy(dhcp->chaddr, l2hdr->h_source); + hns3_dhcp_update_option61(priv, dhcp, dhcp_len); + /* for l4 payload changed, need to re-calculate the csum */ + hns3_dhcp_cal_l4_csum(skb); +} + static int hns3_set_tso(struct sk_buff *skb, u32 *paylen_fdop_ol4cs, u16 *mss, u32 *type_cs_vlan_tso, u32 *send_bytes) { @@ -1716,7 +1852,20 @@ static int hns3_handle_csum_partial(struct hns3_enet_ring *ring, return 0; } -static int hns3_fill_skb_desc(struct hns3_enet_ring *ring, +static bool hns3_roh_check_udpv4(struct sk_buff *skb) +{ + union l3_hdr_info l3; + + l3.hdr = skb_network_header(skb); + if (skb->protocol != htons(ETH_P_IP) || + l3.v4->version != IP_VERSION_IPV4) + return false; + + return l3.v4->protocol == IPPROTO_UDP; +} + +static int hns3_fill_skb_desc(struct hns3_nic_priv *priv, + struct hns3_enet_ring *ring, struct sk_buff *skb, struct hns3_desc *desc, struct hns3_desc_cb *desc_cb) { @@ -1741,6 +1890,14 @@ static int hns3_fill_skb_desc(struct hns3_enet_ring *ring, hnae3_set_field(param.paylen_fdop_ol4cs, HNS3_TXD_FD_OP_M, HNS3_TXD_FD_OP_S, fd_op); + if (hns3_roh_check_udpv4(skb)) { + struct hns3_dhcp_packet *dhcp; + int dhcp_len; + + dhcp = hns3_get_dhcp_packet(skb, &dhcp_len); + hns3_dhcp_packet_convert(priv, skb, dhcp, dhcp_len); + } + /* Set txbd */ desc->tx.ol_type_vlan_len_msec = cpu_to_le32(param.ol_type_vlan_len_msec); @@ -2338,15 +2495,16 @@ static int hns3_handle_desc_filling(struct hns3_enet_ring *ring, return hns3_fill_skb_to_desc(ring, skb, DESC_TYPE_SKB); } -static int hns3_handle_skb_desc(struct hns3_enet_ring *ring, +static int hns3_handle_skb_desc(struct hns3_nic_priv *priv, + struct hns3_enet_ring *ring, struct sk_buff *skb, struct hns3_desc_cb *desc_cb, int next_to_use_head) { int ret; - ret = hns3_fill_skb_desc(ring, skb, &ring->desc[ring->next_to_use], - desc_cb); + ret = hns3_fill_skb_desc(priv, ring, skb, + &ring->desc[ring->next_to_use], desc_cb); if (unlikely(ret < 0)) goto fill_err; @@ -2395,7 +2553,7 @@ netdev_tx_t hns3_nic_net_xmit(struct sk_buff *skb, struct net_device *netdev) goto out_err_tx_ok; } - ret = hns3_handle_skb_desc(ring, skb, desc_cb, ring->next_to_use); + ret = hns3_handle_skb_desc(priv, ring, skb, desc_cb, ring->next_to_use); if (unlikely(ret <= 0)) goto out_err_tx_ok; @@ -5226,6 +5384,9 @@ static int hns3_init_mac_addr(struct net_device *netdev) return 0; } + if (is_zero_ether_addr(priv->roh_perm_mac)) + ether_addr_copy(priv->roh_perm_mac, netdev->dev_addr); + if (h->ae_algo->ops->set_mac_addr) ret = h->ae_algo->ops->set_mac_addr(h, netdev->dev_addr, true); @@ -5377,6 +5538,7 @@ static int hns3_client_init(struct hnae3_handle *handle) priv->tx_timeout_count = 0; priv->max_non_tso_bd_num = ae_dev->dev_specs.max_non_tso_bd_num; set_bit(HNS3_NIC_STATE_DOWN, &priv->state); + eth_zero_addr(priv->roh_perm_mac); handle->msg_enable = netif_msg_init(debug, DEFAULT_MSG_LEVEL); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h index ccfd38b0028e..85c352fff83b 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.h @@ -604,6 +604,56 @@ struct hns3_nic_priv { struct hns3_enet_coalesce rx_coal; u32 tx_copybreak; u32 rx_copybreak; + u8 roh_perm_mac[ETH_ALEN]; +}; + +#define HNS3_DHCP_SERVER_PORT 68 +#define HNS3_DHCP_CLIENT_PORT 67 +#define HNS3_DHCP_MAGIC 0x63825363 +#define DHCP_OPT_CODE 0 +#define DHCP_OPT_LEN 1 +#define DHCP_OPT_DATA 2 +#define DHCP_CLIENT_ID_LEN 7 +#define DHCP_CLIENT_ID_MAC_OFT 3 +#define DHCP_OVERLOAD_FILE 0x1 +#define DHCP_OVERLOAD_SNAME 0x2 +#define DHCP_OVERLOAD_FILE_USED 0x101 +#define DHCP_OVERLOAD_SNAME_USED 0x202 +#define DHCP_OVERLOAD_USE_FILE(x) \ + (((x) & DHCP_OVERLOAD_FILE_USED) == DHCP_OVERLOAD_FILE) +#define DHCP_OVERLOAD_USE_SNAME(x) \ + (((x) & DHCP_OVERLOAD_SNAME_USED) == DHCP_OVERLOAD_SNAME) + +enum DHCP_OPTION_CODES { + DHCP_OPT_PADDING = 0, + DHCP_OPT_OVERLOAD = 52, + DHCP_OPT_CLIENT_ID = 61, + DHCP_OPT_END = 255 +}; + +struct hns3_dhcp_packet { + u8 op; + u8 htype; + u8 hlen; + u8 hops; + u32 xid; + u16 secs; + u16 flags; + u32 ciaddr; + u32 yiaddr; + u32 siaddr_nip; + u32 gateway_nip; + u8 chaddr[16]; /* link-layer client hardware address (MAC) */ + u8 sname[64]; + u8 file[128]; + u32 cookie; /* DHCP magic bytes: 0x63825363 */ + u8 options[312]; +}; + +struct hns3_dhcp_opt_state { + u8 *opt_ptr; /* refer to current option item */ + int rem; /* remain bytes in options */ + u32 overload_flag; /* whether use file and sname field as options */ }; union l3_hdr_info { diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index eea17548416b..5c8a821aa61a 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -2866,12 +2866,21 @@ static void hclge_get_fec(struct hnae3_handle *handle, u8 *fec_ability, if (fec_mode) *fec_mode = mac->fec_mode; } + +static void hclge_roh_convert_mac_addr(struct hclge_dev *hdev) +{ +#define HCLGE_ROH_EID_MASK_BYTE 3 + + memset(hdev->hw.mac.mac_addr, 0, HCLGE_ROH_EID_MASK_BYTE); +} + static int hclge_mac_init(struct hclge_dev *hdev) { struct hclge_mac *mac = &hdev->hw.mac; int ret; hclge_mac_type_init(hdev); + hclge_roh_convert_mac_addr(hdev); hdev->support_sfp_query = true; hdev->hw.mac.duplex = HCLGE_MAC_FULL; -- 2.30.0

1 0

[OLK-5.10 v2 1/3] net: Use u64_stats_fetch_begin_irq() for stats fetch.
by Wang Yufen 06 Feb '23

06 Feb '23

From: Sebastian Andrzej Siewior <bigeasy(a)linutronix.de> stable inclusion from stable-v5.10.142 commit d71a1c9fce184718d1b3a51a9e8a6e31cbbb45ce category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I6D0ZE Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… ------------------------------------------------- commit 278d3ba61563ceed3cb248383ced19e14ec7bc1f upstream. On 32bit-UP u64_stats_fetch_begin() disables only preemption. If the reader is in preemptible context and the writer side (u64_stats_update_begin*()) runs in an interrupt context (IRQ or softirq) then the writer can update the stats during the read operation. This update remains undetected. Use u64_stats_fetch_begin_irq() to ensure the stats fetch on 32bit-UP are not interrupted by a writer. 32bit-SMP remains unaffected by this change. Cc: "David S. Miller" <davem(a)davemloft.net> Cc: Catherine Sullivan <csully(a)google.com> Cc: David Awogbemila <awogbemila(a)google.com> Cc: Dimitris Michailidis <dmichail(a)fungible.com> Cc: Eric Dumazet <edumazet(a)google.com> Cc: Hans Ulli Kroll <ulli.kroll(a)googlemail.com> Cc: Jakub Kicinski <kuba(a)kernel.org> Cc: Jeroen de Borst <jeroendb(a)google.com> Cc: Johannes Berg <johannes(a)sipsolutions.net> Cc: Linus Walleij <linus.walleij(a)linaro.org> Cc: Paolo Abeni <pabeni(a)redhat.com> Cc: Simon Horman <simon.horman(a)corigine.com> Cc: linux-arm-kernel(a)lists.infradead.org Cc: linux-wireless(a)vger.kernel.org Cc: netdev(a)vger.kernel.org Cc: oss-drivers(a)corigine.com Cc: stable(a)vger.kernel.org Signed-off-by: Sebastian Andrzej Siewior <bigeasy(a)linutronix.de> Reviewed-by: Simon Horman <simon.horman(a)corigine.com> Signed-off-by: David S. Miller <davem(a)davemloft.net> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> (cherry picked from commit d71a1c9fce184718d1b3a51a9e8a6e31cbbb45ce) Signed-off-by: Wang Yufen <wangyufen(a)huawei.com> Conflicts: drivers/net/ethernet/huawei/hinic/hinic_rx.c drivers/net/ethernet/huawei/hinic/hinic_tx.c Signed-off-by: Wang Yufen <wangyufen(a)huawei.com> --- drivers/net/ethernet/cortina/gemini.c | 24 +++++++++++----------- drivers/net/ethernet/google/gve/gve_ethtool.c | 16 +++++++-------- drivers/net/ethernet/google/gve/gve_main.c | 12 +++++------ drivers/net/ethernet/huawei/hinic/hinic_rx.c | 4 ++-- drivers/net/ethernet/huawei/hinic/hinic_tx.c | 4 ++-- .../net/ethernet/netronome/nfp/nfp_net_common.c | 8 ++++---- .../net/ethernet/netronome/nfp/nfp_net_ethtool.c | 8 ++++---- drivers/net/netdevsim/netdev.c | 4 ++-- net/mac80211/sta_info.c | 8 ++++---- net/mpls/af_mpls.c | 4 ++-- 10 files changed, 46 insertions(+), 46 deletions(-) diff --git a/drivers/net/ethernet/cortina/gemini.c b/drivers/net/ethernet/cortina/gemini.c index 3685878..b22ea40 100644 --- a/drivers/net/ethernet/cortina/gemini.c +++ b/drivers/net/ethernet/cortina/gemini.c @@ -1920,7 +1920,7 @@ static void gmac_get_stats64(struct net_device *netdev, /* Racing with RX NAPI */ do { - start = u64_stats_fetch_begin(&port->rx_stats_syncp); + start = u64_stats_fetch_begin_irq(&port->rx_stats_syncp); stats->rx_packets = port->stats.rx_packets; stats->rx_bytes = port->stats.rx_bytes; @@ -1932,11 +1932,11 @@ static void gmac_get_stats64(struct net_device *netdev, stats->rx_crc_errors = port->stats.rx_crc_errors; stats->rx_frame_errors = port->stats.rx_frame_errors; - } while (u64_stats_fetch_retry(&port->rx_stats_syncp, start)); + } while (u64_stats_fetch_retry_irq(&port->rx_stats_syncp, start)); /* Racing with MIB and TX completion interrupts */ do { - start = u64_stats_fetch_begin(&port->ir_stats_syncp); + start = u64_stats_fetch_begin_irq(&port->ir_stats_syncp); stats->tx_errors = port->stats.tx_errors; stats->tx_packets = port->stats.tx_packets; @@ -1946,15 +1946,15 @@ static void gmac_get_stats64(struct net_device *netdev, stats->rx_missed_errors = port->stats.rx_missed_errors; stats->rx_fifo_errors = port->stats.rx_fifo_errors; - } while (u64_stats_fetch_retry(&port->ir_stats_syncp, start)); + } while (u64_stats_fetch_retry_irq(&port->ir_stats_syncp, start)); /* Racing with hard_start_xmit */ do { - start = u64_stats_fetch_begin(&port->tx_stats_syncp); + start = u64_stats_fetch_begin_irq(&port->tx_stats_syncp); stats->tx_dropped = port->stats.tx_dropped; - } while (u64_stats_fetch_retry(&port->tx_stats_syncp, start)); + } while (u64_stats_fetch_retry_irq(&port->tx_stats_syncp, start)); stats->rx_dropped += stats->rx_missed_errors; } @@ -2032,18 +2032,18 @@ static void gmac_get_ethtool_stats(struct net_device *netdev, /* Racing with MIB interrupt */ do { p = values; - start = u64_stats_fetch_begin(&port->ir_stats_syncp); + start = u64_stats_fetch_begin_irq(&port->ir_stats_syncp); for (i = 0; i < RX_STATS_NUM; i++) *p++ = port->hw_stats[i]; - } while (u64_stats_fetch_retry(&port->ir_stats_syncp, start)); + } while (u64_stats_fetch_retry_irq(&port->ir_stats_syncp, start)); values = p; /* Racing with RX NAPI */ do { p = values; - start = u64_stats_fetch_begin(&port->rx_stats_syncp); + start = u64_stats_fetch_begin_irq(&port->rx_stats_syncp); for (i = 0; i < RX_STATUS_NUM; i++) *p++ = port->rx_stats[i]; @@ -2051,13 +2051,13 @@ static void gmac_get_ethtool_stats(struct net_device *netdev, *p++ = port->rx_csum_stats[i]; *p++ = port->rx_napi_exits; - } while (u64_stats_fetch_retry(&port->rx_stats_syncp, start)); + } while (u64_stats_fetch_retry_irq(&port->rx_stats_syncp, start)); values = p; /* Racing with TX start_xmit */ do { p = values; - start = u64_stats_fetch_begin(&port->tx_stats_syncp); + start = u64_stats_fetch_begin_irq(&port->tx_stats_syncp); for (i = 0; i < TX_MAX_FRAGS; i++) { *values++ = port->tx_frag_stats[i]; @@ -2066,7 +2066,7 @@ static void gmac_get_ethtool_stats(struct net_device *netdev, *values++ = port->tx_frags_linearized; *values++ = port->tx_hw_csummed; - } while (u64_stats_fetch_retry(&port->tx_stats_syncp, start)); + } while (u64_stats_fetch_retry_irq(&port->tx_stats_syncp, start)); } static int gmac_get_ksettings(struct net_device *netdev, diff --git a/drivers/net/ethernet/google/gve/gve_ethtool.c b/drivers/net/ethernet/google/gve/gve_ethtool.c index 66f9b37..80a8c0c 100644 --- a/drivers/net/ethernet/google/gve/gve_ethtool.c +++ b/drivers/net/ethernet/google/gve/gve_ethtool.c @@ -172,14 +172,14 @@ static int gve_get_sset_count(struct net_device *netdev, int sset) struct gve_rx_ring *rx = &priv->rx[ring]; start = - u64_stats_fetch_begin(&priv->rx[ring].statss); + u64_stats_fetch_begin_irq(&priv->rx[ring].statss); tmp_rx_pkts = rx->rpackets; tmp_rx_bytes = rx->rbytes; tmp_rx_skb_alloc_fail = rx->rx_skb_alloc_fail; tmp_rx_buf_alloc_fail = rx->rx_buf_alloc_fail; tmp_rx_desc_err_dropped_pkt = rx->rx_desc_err_dropped_pkt; - } while (u64_stats_fetch_retry(&priv->rx[ring].statss, + } while (u64_stats_fetch_retry_irq(&priv->rx[ring].statss, start)); rx_pkts += tmp_rx_pkts; rx_bytes += tmp_rx_bytes; @@ -193,10 +193,10 @@ static int gve_get_sset_count(struct net_device *netdev, int sset) if (priv->tx) { do { start = - u64_stats_fetch_begin(&priv->tx[ring].statss); + u64_stats_fetch_begin_irq(&priv->tx[ring].statss); tmp_tx_pkts = priv->tx[ring].pkt_done; tmp_tx_bytes = priv->tx[ring].bytes_done; - } while (u64_stats_fetch_retry(&priv->tx[ring].statss, + } while (u64_stats_fetch_retry_irq(&priv->tx[ring].statss, start)); tx_pkts += tmp_tx_pkts; tx_bytes += tmp_tx_bytes; @@ -254,13 +254,13 @@ static int gve_get_sset_count(struct net_device *netdev, int sset) data[i++] = rx->cnt; do { start = - u64_stats_fetch_begin(&priv->rx[ring].statss); + u64_stats_fetch_begin_irq(&priv->rx[ring].statss); tmp_rx_bytes = rx->rbytes; tmp_rx_skb_alloc_fail = rx->rx_skb_alloc_fail; tmp_rx_buf_alloc_fail = rx->rx_buf_alloc_fail; tmp_rx_desc_err_dropped_pkt = rx->rx_desc_err_dropped_pkt; - } while (u64_stats_fetch_retry(&priv->rx[ring].statss, + } while (u64_stats_fetch_retry_irq(&priv->rx[ring].statss, start)); data[i++] = tmp_rx_bytes; /* rx dropped packets */ @@ -313,9 +313,9 @@ static int gve_get_sset_count(struct net_device *netdev, int sset) data[i++] = tx->done; do { start = - u64_stats_fetch_begin(&priv->tx[ring].statss); + u64_stats_fetch_begin_irq(&priv->tx[ring].statss); tmp_tx_bytes = tx->bytes_done; - } while (u64_stats_fetch_retry(&priv->tx[ring].statss, + } while (u64_stats_fetch_retry_irq(&priv->tx[ring].statss, start)); data[i++] = tmp_tx_bytes; data[i++] = tx->wake_queue; diff --git a/drivers/net/ethernet/google/gve/gve_main.c b/drivers/net/ethernet/google/gve/gve_main.c index 6cb75bb..f0c1e6c8 100644 --- a/drivers/net/ethernet/google/gve/gve_main.c +++ b/drivers/net/ethernet/google/gve/gve_main.c @@ -40,10 +40,10 @@ static void gve_get_stats(struct net_device *dev, struct rtnl_link_stats64 *s) for (ring = 0; ring < priv->rx_cfg.num_queues; ring++) { do { start = - u64_stats_fetch_begin(&priv->rx[ring].statss); + u64_stats_fetch_begin_irq(&priv->rx[ring].statss); packets = priv->rx[ring].rpackets; bytes = priv->rx[ring].rbytes; - } while (u64_stats_fetch_retry(&priv->rx[ring].statss, + } while (u64_stats_fetch_retry_irq(&priv->rx[ring].statss, start)); s->rx_packets += packets; s->rx_bytes += bytes; @@ -53,10 +53,10 @@ static void gve_get_stats(struct net_device *dev, struct rtnl_link_stats64 *s) for (ring = 0; ring < priv->tx_cfg.num_queues; ring++) { do { start = - u64_stats_fetch_begin(&priv->tx[ring].statss); + u64_stats_fetch_begin_irq(&priv->tx[ring].statss); packets = priv->tx[ring].pkt_done; bytes = priv->tx[ring].bytes_done; - } while (u64_stats_fetch_retry(&priv->tx[ring].statss, + } while (u64_stats_fetch_retry_irq(&priv->tx[ring].statss, start)); s->tx_packets += packets; s->tx_bytes += bytes; @@ -1041,9 +1041,9 @@ void gve_handle_report_stats(struct gve_priv *priv) if (priv->tx) { for (idx = 0; idx < priv->tx_cfg.num_queues; idx++) { do { - start = u64_stats_fetch_begin(&priv->tx[idx].statss); + start = u64_stats_fetch_begin_irq(&priv->tx[idx].statss); tx_bytes = priv->tx[idx].bytes_done; - } while (u64_stats_fetch_retry(&priv->tx[idx].statss, start)); + } while (u64_stats_fetch_retry_irq(&priv->tx[idx].statss, start)); stats[stats_idx++] = (struct stats) { .stat_name = cpu_to_be32(TX_WAKE_CNT), .value = cpu_to_be64(priv->tx[idx].wake_queue), diff --git a/drivers/net/ethernet/huawei/hinic/hinic_rx.c b/drivers/net/ethernet/huawei/hinic/hinic_rx.c index 57d5d79..1b57b67 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_rx.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_rx.c @@ -375,7 +375,7 @@ void hinic_rxq_get_stats(struct hinic_rxq *rxq, u64_stats_update_begin(&stats->syncp); do { - start = u64_stats_fetch_begin(&rxq_stats->syncp); + start = u64_stats_fetch_begin_irq(&rxq_stats->syncp); stats->bytes = rxq_stats->bytes; stats->packets = rxq_stats->packets; stats->errors = rxq_stats->csum_errors + @@ -384,7 +384,7 @@ void hinic_rxq_get_stats(struct hinic_rxq *rxq, stats->other_errors = rxq_stats->other_errors; stats->dropped = rxq_stats->dropped; stats->rx_buf_empty = rxq_stats->rx_buf_empty; - } while (u64_stats_fetch_retry(&rxq_stats->syncp, start)); + } while (u64_stats_fetch_retry_irq(&rxq_stats->syncp, start)); u64_stats_update_end(&stats->syncp); } diff --git a/drivers/net/ethernet/huawei/hinic/hinic_tx.c b/drivers/net/ethernet/huawei/hinic/hinic_tx.c index 75fa344..ff37b6f 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_tx.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_tx.c @@ -61,7 +61,7 @@ void hinic_txq_get_stats(struct hinic_txq *txq, u64_stats_update_begin(&stats->syncp); do { - start = u64_stats_fetch_begin(&txq_stats->syncp); + start = u64_stats_fetch_begin_irq(&txq_stats->syncp); stats->bytes = txq_stats->bytes; stats->packets = txq_stats->packets; stats->busy = txq_stats->busy; @@ -69,7 +69,7 @@ void hinic_txq_get_stats(struct hinic_txq *txq, stats->dropped = txq_stats->dropped; stats->big_frags_pkts = txq_stats->big_frags_pkts; stats->big_udp_pkts = txq_stats->big_udp_pkts; - } while (u64_stats_fetch_retry(&txq_stats->syncp, start)); + } while (u64_stats_fetch_retry_irq(&txq_stats->syncp, start)); u64_stats_update_end(&stats->syncp); } diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c index dfc1f32..5ab230aa 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c @@ -3373,21 +3373,21 @@ static void nfp_net_stat64(struct net_device *netdev, unsigned int start; do { - start = u64_stats_fetch_begin(&r_vec->rx_sync); + start = u64_stats_fetch_begin_irq(&r_vec->rx_sync); data[0] = r_vec->rx_pkts; data[1] = r_vec->rx_bytes; data[2] = r_vec->rx_drops; - } while (u64_stats_fetch_retry(&r_vec->rx_sync, start)); + } while (u64_stats_fetch_retry_irq(&r_vec->rx_sync, start)); stats->rx_packets += data[0]; stats->rx_bytes += data[1]; stats->rx_dropped += data[2]; do { - start = u64_stats_fetch_begin(&r_vec->tx_sync); + start = u64_stats_fetch_begin_irq(&r_vec->tx_sync); data[0] = r_vec->tx_pkts; data[1] = r_vec->tx_bytes; data[2] = r_vec->tx_errors; - } while (u64_stats_fetch_retry(&r_vec->tx_sync, start)); + } while (u64_stats_fetch_retry_irq(&r_vec->tx_sync, start)); stats->tx_packets += data[0]; stats->tx_bytes += data[1]; stats->tx_errors += data[2]; diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c index bfcd90f..d4136d3 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_ethtool.c @@ -498,7 +498,7 @@ static u64 *nfp_vnic_get_sw_stats(struct net_device *netdev, u64 *data) unsigned int start; do { - start = u64_stats_fetch_begin(&nn->r_vecs[i].rx_sync); + start = u64_stats_fetch_begin_irq(&nn->r_vecs[i].rx_sync); data[0] = nn->r_vecs[i].rx_pkts; tmp[0] = nn->r_vecs[i].hw_csum_rx_ok; tmp[1] = nn->r_vecs[i].hw_csum_rx_inner_ok; @@ -506,10 +506,10 @@ static u64 *nfp_vnic_get_sw_stats(struct net_device *netdev, u64 *data) tmp[3] = nn->r_vecs[i].hw_csum_rx_error; tmp[4] = nn->r_vecs[i].rx_replace_buf_alloc_fail; tmp[5] = nn->r_vecs[i].hw_tls_rx; - } while (u64_stats_fetch_retry(&nn->r_vecs[i].rx_sync, start)); + } while (u64_stats_fetch_retry_irq(&nn->r_vecs[i].rx_sync, start)); do { - start = u64_stats_fetch_begin(&nn->r_vecs[i].tx_sync); + start = u64_stats_fetch_begin_irq(&nn->r_vecs[i].tx_sync); data[1] = nn->r_vecs[i].tx_pkts; data[2] = nn->r_vecs[i].tx_busy; tmp[6] = nn->r_vecs[i].hw_csum_tx; @@ -519,7 +519,7 @@ static u64 *nfp_vnic_get_sw_stats(struct net_device *netdev, u64 *data) tmp[10] = nn->r_vecs[i].hw_tls_tx; tmp[11] = nn->r_vecs[i].tls_tx_fallback; tmp[12] = nn->r_vecs[i].tls_tx_no_fallback; - } while (u64_stats_fetch_retry(&nn->r_vecs[i].tx_sync, start)); + } while (u64_stats_fetch_retry_irq(&nn->r_vecs[i].tx_sync, start)); data += NN_RVEC_PER_Q_STATS; diff --git a/drivers/net/netdevsim/netdev.c b/drivers/net/netdevsim/netdev.c index ad6dbf01..4fb0638 100644 --- a/drivers/net/netdevsim/netdev.c +++ b/drivers/net/netdevsim/netdev.c @@ -67,10 +67,10 @@ static int nsim_change_mtu(struct net_device *dev, int new_mtu) unsigned int start; do { - start = u64_stats_fetch_begin(&ns->syncp); + start = u64_stats_fetch_begin_irq(&ns->syncp); stats->tx_bytes = ns->tx_bytes; stats->tx_packets = ns->tx_packets; - } while (u64_stats_fetch_retry(&ns->syncp, start)); + } while (u64_stats_fetch_retry_irq(&ns->syncp, start)); } static int diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index 461c037..cee39ae 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -2175,9 +2175,9 @@ static inline u64 sta_get_tidstats_msdu(struct ieee80211_sta_rx_stats *rxstats, u64 value; do { - start = u64_stats_fetch_begin(&rxstats->syncp); + start = u64_stats_fetch_begin_irq(&rxstats->syncp); value = rxstats->msdu[tid]; - } while (u64_stats_fetch_retry(&rxstats->syncp, start)); + } while (u64_stats_fetch_retry_irq(&rxstats->syncp, start)); return value; } @@ -2241,9 +2241,9 @@ static inline u64 sta_get_stats_bytes(struct ieee80211_sta_rx_stats *rxstats) u64 value; do { - start = u64_stats_fetch_begin(&rxstats->syncp); + start = u64_stats_fetch_begin_irq(&rxstats->syncp); value = rxstats->bytes; - } while (u64_stats_fetch_retry(&rxstats->syncp, start)); + } while (u64_stats_fetch_retry_irq(&rxstats->syncp, start)); return value; } diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c index 9c047c1..7239814 100644 --- a/net/mpls/af_mpls.c +++ b/net/mpls/af_mpls.c @@ -1078,9 +1078,9 @@ static void mpls_get_stats(struct mpls_dev *mdev, p = per_cpu_ptr(mdev->stats, i); do { - start = u64_stats_fetch_begin(&p->syncp); + start = u64_stats_fetch_begin_irq(&p->syncp); local = p->stats; - } while (u64_stats_fetch_retry(&p->syncp, start)); + } while (u64_stats_fetch_retry_irq(&p->syncp, start)); stats->rx_packets += local.rx_packets; stats->rx_bytes += local.rx_bytes; -- 1.8.3.1

1 2

[PATCH openEuler-1.0-LTS 1/3] mm: hwpoison: refactor refcount check handling
by Yongqiang Liu 04 Feb '23

04 Feb '23

From: Yang Shi <shy828301(a)gmail.com> stable inclusion from stable-v5.15.86 commit a62b1bc603a1ded739e7cf543da29a3eb93cc534 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/I6AR36 CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… -------------------------------- commit dd0f230a0a80ff396c7ce587f16429f2a8131344 upstream. Memory failure will report failure if the page still has extra pinned refcount other than from hwpoison after the handler is done. Actually the check is not necessary for all handlers, so move the check into specific handlers. This would make the following keeping shmem page in page cache patch easier. There may be expected extra pin for some cases, for example, when the page is dirty and in swapcache. Link: https://lkml.kernel.org/r/20211020210755.23964-5-shy828301@gmail.com Signed-off-by: Yang Shi <shy828301(a)gmail.com> Signed-off-by: Naoya Horiguchi <naoya.horiguchi(a)nec.com> Suggested-by: Naoya Horiguchi <naoya.horiguchi(a)nec.com> Cc: Hugh Dickins <hughd(a)google.com> Cc: Kirill A. Shutemov <kirill.shutemov(a)linux.intel.com> Cc: Matthew Wilcox <willy(a)infradead.org> Cc: Oscar Salvador <osalvador(a)suse.de> Cc: Peter Xu <peterx(a)redhat.com> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds(a)linux-foundation.org> Cc: Naoya Horiguchi <naoya.horiguchi(a)linux.dev> Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> Signed-off-by: Ze Zuo <zuoze1(a)huawei.com> Reviewed-by: Kefeng Wang <wangkefeng.wang(a)huawei.com> Signed-off-by: Yongqiang Liu <liuyongqiang13(a)huawei.com> --- mm/memory-failure.c | 93 +++++++++++++++++++++++++++++++-------------- 1 file changed, 64 insertions(+), 29 deletions(-) diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 9a816fdf812d..b653637d5a00 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -655,12 +655,44 @@ static int truncate_error_page(struct page *p, unsigned long pfn, return ret; } +struct page_state { + unsigned long mask; + unsigned long res; + enum mf_action_page_type type; + + /* Callback ->action() has to unlock the relevant page inside it. */ + int (*action)(struct page_state *ps, struct page *p); +}; + +/* + * Return true if page is still referenced by others, otherwise return + * false. + * + * The extra_pins is true when one extra refcount is expected. + */ +static bool has_extra_refcount(struct page_state *ps, struct page *p, + bool extra_pins) +{ + int count = page_count(p) - 1; + + if (extra_pins) + count -= 1; + + if (count > 0) { + pr_err("Memory failure: %#lx: %s still referenced by %d users\n", + page_to_pfn(p), action_page_types[ps->type], count); + return true; + } + + return false; +} + /* * Error hit kernel page. * Do nothing, try to be lucky and not touch this instead. For a few cases we * could be more sophisticated. */ -static int me_kernel(struct page *p, unsigned long pfn) +static int me_kernel(struct page_state *ps, struct page *p) { unlock_page(p); return MF_IGNORED; @@ -669,9 +701,9 @@ static int me_kernel(struct page *p, unsigned long pfn) /* * Page in unknown state. Do nothing. */ -static int me_unknown(struct page *p, unsigned long pfn) +static int me_unknown(struct page_state *ps, struct page *p) { - pr_err("Memory failure: %#lx: Unknown page state\n", pfn); + pr_err("Memory failure: %#lx: Unknown page state\n", page_to_pfn(p)); unlock_page(p); return MF_FAILED; } @@ -679,7 +711,7 @@ static int me_unknown(struct page *p, unsigned long pfn) /* * Clean (or cleaned) page cache page. */ -static int me_pagecache_clean(struct page *p, unsigned long pfn) +static int me_pagecache_clean(struct page_state *ps, struct page *p) { int ret; struct address_space *mapping; @@ -716,9 +748,13 @@ static int me_pagecache_clean(struct page *p, unsigned long pfn) * * Open: to take i_mutex or not for this? Right now we don't. */ - ret = truncate_error_page(p, pfn, mapping); + ret = truncate_error_page(p, page_to_pfn(p), mapping); out: unlock_page(p); + + if (has_extra_refcount(ps, p, false)) + ret = MF_FAILED; + return ret; } @@ -727,7 +763,7 @@ static int me_pagecache_clean(struct page *p, unsigned long pfn) * Issues: when the error hit a hole page the error is not properly * propagated. */ -static int me_pagecache_dirty(struct page *p, unsigned long pfn) +static int me_pagecache_dirty(struct page_state *ps, struct page *p) { struct address_space *mapping = page_mapping(p); @@ -771,7 +807,7 @@ static int me_pagecache_dirty(struct page *p, unsigned long pfn) mapping_set_error(mapping, -EIO); } - return me_pagecache_clean(p, pfn); + return me_pagecache_clean(ps, p); } /* @@ -793,9 +829,10 @@ static int me_pagecache_dirty(struct page *p, unsigned long pfn) * Clean swap cache pages can be directly isolated. A later page fault will * bring in the known good data from disk. */ -static int me_swapcache_dirty(struct page *p, unsigned long pfn) +static int me_swapcache_dirty(struct page_state *ps, struct page *p) { int ret; + bool extra_pins = false; ClearPageDirty(p); /* Trigger EIO in shmem: */ @@ -803,10 +840,17 @@ static int me_swapcache_dirty(struct page *p, unsigned long pfn) ret = delete_from_lru_cache(p) ? MF_FAILED : MF_DELAYED; unlock_page(p); + + if (ret == MF_DELAYED) + extra_pins = true; + + if (has_extra_refcount(ps, p, extra_pins)) + ret = MF_FAILED; + return ret; } -static int me_swapcache_clean(struct page *p, unsigned long pfn) +static int me_swapcache_clean(struct page_state *ps, struct page *p) { int ret; @@ -814,6 +858,10 @@ static int me_swapcache_clean(struct page *p, unsigned long pfn) ret = delete_from_lru_cache(p) ? MF_FAILED : MF_RECOVERED; unlock_page(p); + + if (has_extra_refcount(ps, p, false)) + ret = MF_FAILED; + return ret; } @@ -823,7 +871,7 @@ static int me_swapcache_clean(struct page *p, unsigned long pfn) * - Error on hugepage is contained in hugepage unit (not in raw page unit.) * To narrow down kill region to one page, we need to break up pmd. */ -static int me_huge_page(struct page *p, unsigned long pfn) +static int me_huge_page(struct page_state *ps, struct page *p) { int res; struct page *hpage = compound_head(p); @@ -834,7 +882,7 @@ static int me_huge_page(struct page *p, unsigned long pfn) mapping = page_mapping(hpage); if (mapping) { - res = truncate_error_page(hpage, pfn, mapping); + res = truncate_error_page(hpage, page_to_pfn(p), mapping); unlock_page(hpage); } else { res = MF_FAILED; @@ -852,6 +900,9 @@ static int me_huge_page(struct page *p, unsigned long pfn) } } + if (has_extra_refcount(ps, p, false)) + res = MF_FAILED; + return res; } @@ -878,14 +929,7 @@ static int me_huge_page(struct page *p, unsigned long pfn) #define slab (1UL << PG_slab) #define reserved (1UL << PG_reserved) -static struct page_state { - unsigned long mask; - unsigned long res; - enum mf_action_page_type type; - - /* Callback ->action() has to unlock the relevant page inside it. */ - int (*action)(struct page *p, unsigned long pfn); -} error_states[] = { +static struct page_state error_states[] = { { reserved, reserved, MF_MSG_KERNEL, me_kernel }, /* * free pages are specially detected outside this table: @@ -946,19 +990,10 @@ static int page_action(struct page_state *ps, struct page *p, unsigned long pfn) { int result; - int count; /* page p should be unlocked after returning from ps->action(). */ - result = ps->action(p, pfn); + result = ps->action(ps, p); - count = page_count(p) - 1; - if (ps->action == me_swapcache_dirty && result == MF_DELAYED) - count--; - if (count > 0) { - pr_err("Memory failure: %#lx: %s still referenced by %d users\n", - pfn, action_page_types[ps->type], count); - result = MF_FAILED; - } action_result(pfn, ps->type, result); /* Could do more checks here if page looks ok */ -- 2.25.1

1 2