- Kernel - mailweb.openeuler.org

[openeuler:openEuler-1.0-LTS 1732/1732] drivers/mailbox/phytium_mailbox.c:122:34: warning: unused variable 'phytium_mbox_of_match'
by kernel test robot 18 Jul '25

18 Jul '25

tree: https://gitee.com/openeuler/kernel.git openEuler-1.0-LTS head: 700db19c02e9c8dcf291aa7a6a29337c97ea1805 commit: 1ae9436b02e93f1f2b9cfc10226812197fbfcd04 [1732/1732] mailbox: add phytium mailbox driver config: x86_64-buildonly-randconfig-005-20250718 (https://download.01.org/0day-ci/archive/20250718/202507182149.MLClqzfv-lkp@…) compiler: clang version 20.1.8 (https://github.com/llvm/llvm-project 87f0227cb60147a26a1eeb4fb06e3b505e9c7261) reproduce (this is a W=1 build): (https://download.01.org/0day-ci/archive/20250718/202507182149.MLClqzfv-lkp@…) If you fix the issue in a separate patch/commit (i.e. not just a new version of the same patch/commit), kindly add following tags | Reported-by: kernel test robot <lkp(a)intel.com> | Closes: https://lore.kernel.org/oe-kbuild-all/202507182149.MLClqzfv-lkp@intel.com/ All warnings (new ones prefixed by >>): >> drivers/mailbox/phytium_mailbox.c:122:34: warning: unused variable 'phytium_mbox_of_match' [-Wunused-const-variable] 122 | static const struct of_device_id phytium_mbox_of_match[] = { | ^~~~~~~~~~~~~~~~~~~~~ 1 warning generated. vim +/phytium_mbox_of_match +122 drivers/mailbox/phytium_mailbox.c 121 > 122 static const struct of_device_id phytium_mbox_of_match[] = { 123 { .compatible = "phytium,mbox", }, 124 { }, 125 }; 126 MODULE_DEVICE_TABLE(of, phytium_mbox_of_match); 127 -- 0-DAY CI Kernel Test Service https://github.com/intel/lkp-tests/wiki

1 0

[openeuler:openEuler-1.0-LTS 1732/1732] drivers/scsi/sssraid/sssraid_os.c:1704:2: error: implicit declaration of function 'for_each_pci_msi_entry'
by kernel test robot 18 Jul '25

18 Jul '25

tree: https://gitee.com/openeuler/kernel.git openEuler-1.0-LTS head: 700db19c02e9c8dcf291aa7a6a29337c97ea1805 commit: 2e2a4edd9d4a725c5474dc278b090913d9b5bfd5 [1732/1732] SCSI: SSSRAID: Support 3SNIC 3S5XX serial RAID/HBA controllers config: x86_64-buildonly-randconfig-005-20250718 (https://download.01.org/0day-ci/archive/20250718/202507181741.tfXG7WLG-lkp@…) compiler: clang version 20.1.8 (https://github.com/llvm/llvm-project 87f0227cb60147a26a1eeb4fb06e3b505e9c7261) reproduce (this is a W=1 build): (https://download.01.org/0day-ci/archive/20250718/202507181741.tfXG7WLG-lkp@…) If you fix the issue in a separate patch/commit (i.e. not just a new version of the same patch/commit), kindly add following tags | Reported-by: kernel test robot <lkp(a)intel.com> | Closes: https://lore.kernel.org/oe-kbuild-all/202507181741.tfXG7WLG-lkp@intel.com/ All errors (new ones prefixed by >>): >> drivers/scsi/sssraid/sssraid_os.c:1704:2: error: implicit declaration of function 'for_each_pci_msi_entry' [-Werror,-Wimplicit-function-declaration] 1704 | for_each_pci_msi_entry(entry, pdev) { | ^ >> drivers/scsi/sssraid/sssraid_os.c:1704:37: error: expected ';' after expression 1704 | for_each_pci_msi_entry(entry, pdev) { | ^ | ; >> drivers/scsi/sssraid/sssraid_os.c:1705:43: error: no member named 'msi_list' in 'struct device' 1705 | struct list_head *msi_list = &pdev->dev.msi_list; | ~~~~~~~~~ ^ drivers/scsi/sssraid/sssraid_os.c:1716:5: error: 'continue' statement not in loop statement 1716 | continue; | ^ drivers/scsi/sssraid/sssraid_os.c:1726:3: error: 'continue' statement not in loop statement 1726 | continue; | ^ 5 errors generated. vim +/for_each_pci_msi_entry +1704 drivers/scsi/sssraid/sssraid_os.c 1689 1690 static int sssraid_map_queues(struct Scsi_Host *shost) 1691 { 1692 struct sssraid_ioc *sdioc = shost_priv(shost); 1693 struct pci_dev *pdev = sdioc->pdev; 1694 struct msi_desc *entry = NULL; 1695 struct blk_mq_tag_set *tag_set = &shost->tag_set; 1696 unsigned int *map = tag_set->mq_map; 1697 const struct cpumask *node_mask = NULL; 1698 unsigned int nr_queues = tag_set->nr_hw_queues; 1699 unsigned int node_id, node_id_last = 0xFFFFFFFF; 1700 int cpu, queue = 0; 1701 u8 node_count = 0, i; 1702 unsigned int node_id_array[100]; 1703 > 1704 for_each_pci_msi_entry(entry, pdev) { > 1705 struct list_head *msi_list = &pdev->dev.msi_list; 1706 1707 if (list_is_last(msi_list, &entry->list)) 1708 goto get_next_numa_node; 1709 1710 if (entry->irq) { 1711 node_mask = entry->affinity; 1712 1713 cpu = cpumask_first(node_mask); 1714 node_id = cpu_to_node(cpu); 1715 if (node_id_last == node_id) 1716 continue; 1717 1718 for (i = 0; i < node_count; i++) { 1719 if (node_id == node_id_array[i]) 1720 goto get_next_numa_node; 1721 } 1722 node_id_array[node_count++] = node_id; 1723 node_id_last = node_id; 1724 } 1725 get_next_numa_node: 1726 continue; 1727 } 1728 1729 for (i = 0; i < node_count; i++) { 1730 node_mask = cpumask_of_node(node_id_array[i]); 1731 dbgprint(sdioc, "NUMA_node = %d\n", node_id_array[i]); 1732 for_each_cpu(cpu, node_mask) { 1733 map[cpu] = (queue < nr_queues) ? queue++ : 0; 1734 dbgprint(sdioc, "map[%d] = %d\n", cpu, map[cpu]); 1735 } 1736 } 1737 1738 return 0; 1739 } 1740 -- 0-DAY CI Kernel Test Service https://github.com/intel/lkp-tests/wiki

1 0

[PATCH openEuler-1.0-LTS] net/sched: Abort __tc_modify_qdisc if parent class does not exist
by Dong Chenchen 18 Jul '25

18 Jul '25

From: Victor Nogueira <victor(a)mojatatu.com> mainline inclusion from mainline-v6.16-rc6 commit ffdde7bf5a439aaa1955ebd581f5c64ab1533963 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/ICMJHK CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- Lion's patch [1] revealed an ancient bug in the qdisc API. Whenever a user creates/modifies a qdisc specifying as a parent another qdisc, the qdisc API will, during grafting, detect that the user is not trying to attach to a class and reject. However grafting is performed after qdisc_create (and thus the qdiscs' init callback) is executed. In qdiscs that eventually call qdisc_tree_reduce_backlog during init or change (such as fq, hhf, choke, etc), an issue arises. For example, executing the following commands: sudo tc qdisc add dev lo root handle a: htb default 2 sudo tc qdisc add dev lo parent a: handle beef fq Qdiscs such as fq, hhf, choke, etc unconditionally invoke qdisc_tree_reduce_backlog() in their control path init() or change() which then causes a failure to find the child class; however, that does not stop the unconditional invocation of the assumed child qdisc's qlen_notify with a null class. All these qdiscs make the assumption that class is non-null. The solution is ensure that qdisc_leaf() which looks up the parent class, and is invoked prior to qdisc_create(), should return failure on not finding the class. In this patch, we leverage qdisc_leaf to return ERR_PTRs whenever the parentid doesn't correspond to a class, so that we can detect it earlier on and abort before qdisc_create is called. [1] https://lore.kernel.org/netdev/d912cbd7-193b-4269-9857-525bee8bbb6a@gmail.c… Fixes: 5e50da01d0ce ("[NET_SCHED]: Fix endless loops (part 2): "simple" qdiscs") Reported-by: syzbot+d8b58d7b0ad89a678a16(a)syzkaller.appspotmail.com Closes: https://lore.kernel.org/netdev/68663c93.a70a0220.5d25f.0857.GAE@google.com/ Reported-by: syzbot+5eccb463fa89309d8bdc(a)syzkaller.appspotmail.com Closes: https://lore.kernel.org/netdev/68663c94.a70a0220.5d25f.0858.GAE@google.com/ Reported-by: syzbot+1261670bbdefc5485a06(a)syzkaller.appspotmail.com Closes: https://lore.kernel.org/netdev/686764a5.a00a0220.c7b3.0013.GAE@google.com/ Reported-by: syzbot+15b96fc3aac35468fe77(a)syzkaller.appspotmail.com Closes: https://lore.kernel.org/netdev/686764a5.a00a0220.c7b3.0014.GAE@google.com/ Reported-by: syzbot+4dadc5aecf80324d5a51(a)syzkaller.appspotmail.com Closes: https://lore.kernel.org/netdev/68679e81.a70a0220.29cf51.0016.GAE@google.com/ Acked-by: Jamal Hadi Salim <jhs(a)mojatatu.com> Reviewed-by: Cong Wang <xiyou.wangcong(a)gmail.com> Signed-off-by: Victor Nogueira <victor(a)mojatatu.com> Link: https://patch.msgid.link/20250707210801.372995-1-victor@mojatatu.com Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> Conflicts: net/sched/sch_api.c [commit d636fc5dd692 and 2561f97267d6 is not backport] Signed-off-by: Dong Chenchen <dongchenchen2(a)huawei.com> --- net/sched/sch_api.c | 23 ++++++++++++++++------- 1 file changed, 16 insertions(+), 7 deletions(-) diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index 976908642263..05bed30b0a6a 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -333,18 +333,23 @@ struct Qdisc *qdisc_lookup_rcu(struct net_device *dev, u32 handle) return q; } -static struct Qdisc *qdisc_leaf(struct Qdisc *p, u32 classid) +static struct Qdisc *qdisc_leaf(struct Qdisc *p, u32 classid, + struct netlink_ext_ack *extack) { unsigned long cl; struct Qdisc *leaf; const struct Qdisc_class_ops *cops = p->ops->cl_ops; - if (cops == NULL) - return NULL; + if (cops == NULL) { + NL_SET_ERR_MSG(extack, "Parent qdisc is not classful"); + return ERR_PTR(-EOPNOTSUPP); + } cl = cops->find(p, classid); - if (cl == 0) - return NULL; + if (cl == 0) { + NL_SET_ERR_MSG(extack, "Specified class not found"); + return ERR_PTR(-ENOENT); + } leaf = cops->leaf(p, cl); return leaf; } @@ -1378,7 +1383,7 @@ static int tc_get_qdisc(struct sk_buff *skb, struct nlmsghdr *n, NL_SET_ERR_MSG(extack, "Failed to find qdisc with specified classid"); return -ENOENT; } - q = qdisc_leaf(p, clid); + q = qdisc_leaf(p, clid, extack); } else if (dev_ingress_queue(dev)) { q = dev_ingress_queue(dev)->qdisc_sleeping; } @@ -1389,6 +1394,8 @@ static int tc_get_qdisc(struct sk_buff *skb, struct nlmsghdr *n, NL_SET_ERR_MSG(extack, "Cannot find specified qdisc on specified device"); return -ENOENT; } + if (IS_ERR(q)) + return PTR_ERR(q); if (tcm->tcm_handle && q->handle != tcm->tcm_handle) { NL_SET_ERR_MSG(extack, "Invalid handle"); @@ -1485,7 +1492,9 @@ static int tc_modify_qdisc(struct sk_buff *skb, struct nlmsghdr *n, NL_SET_ERR_MSG(extack, "Failed to find specified qdisc"); return -ENOENT; } - q = qdisc_leaf(p, clid); + q = qdisc_leaf(p, clid, extack); + if (IS_ERR(q)) + return PTR_ERR(q); } else if (dev_ingress_queue_create(dev)) { q = dev_ingress_queue(dev)->qdisc_sleeping; } -- 2.25.1

2 1

[openeuler:openEuler-1.0-LTS 1732/1732] drivers/i2c/busses/i2c-phytium-common.o: warning: objtool: missing symbol for section .text
by kernel test robot 18 Jul '25

18 Jul '25

tree: https://gitee.com/openeuler/kernel.git openEuler-1.0-LTS head: 700db19c02e9c8dcf291aa7a6a29337c97ea1805 commit: 777b12afb6187fc712f365df57982275e9ef244f [1732/1732] i2c: add Phytium i2c driver config: x86_64-buildonly-randconfig-005-20250718 (https://download.01.org/0day-ci/archive/20250718/202507181640.hu6zFNEJ-lkp@…) compiler: clang version 20.1.8 (https://github.com/llvm/llvm-project 87f0227cb60147a26a1eeb4fb06e3b505e9c7261) reproduce (this is a W=1 build): (https://download.01.org/0day-ci/archive/20250718/202507181640.hu6zFNEJ-lkp@…) If you fix the issue in a separate patch/commit (i.e. not just a new version of the same patch/commit), kindly add following tags | Reported-by: kernel test robot <lkp(a)intel.com> | Closes: https://lore.kernel.org/oe-kbuild-all/202507181640.hu6zFNEJ-lkp@intel.com/ All warnings (new ones prefixed by >>): >> drivers/i2c/busses/i2c-phytium-common.o: warning: objtool: missing symbol for section .text -- 0-DAY CI Kernel Test Service https://github.com/intel/lkp-tests/wiki

1 0

[PATCH OLK-6.6] drm: phytium: fix NULL dereference issue in drm_gem_object_free
by Li Chen 18 Jul '25

18 Jul '25

From: Li Chen <chenl311(a)chinatelecom.cn> driver inclusion category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/ICGG2A ---------------------------------------------------------------------- Syzkaller crashed kernel in drm path. The root cause is that phytium_drm_gem_object_funcs is not assigned before phytium_gem_create_object enters the failed_dma_alloc label. Let's fix this issue by assigning the function earlier. Below is the crash log: ``` [ 9042.703078] [drm:phytium_gem_create_object [phytium_dc_drm]] *ERROR* fail to allocate vram buffer with size 3de4000 [ 9042.717862] Unable to handle kernel NULL pointer dereference at virtual address 0000000000000000 [ 9042.727173] fuse: Unknown parameter '0xffffffffffffffff<r00000000000000000000' [ 9042.730383] Mem abort info: [ 9042.745443] ESR = 0x0000000096000006 [ 9042.745446] EC = 0x25: DABT (current EL), IL = 32 bits [ 9042.745448] SET = 0, FnV = 0 [ 9042.745450] EA = 0, S1PTW = 0 [ 9042.745451] FSC = 0x06: level 2 translation fault [ 9042.745453] Data abort info: [ 9042.745455] ISV = 0, ISS = 0x00000006, ISS2 = 0x00000000 [ 9042.745457] CM = 0, WnR = 0, TnD = 0, TagAccess = 0 [ 9042.745459] GCS = 0, Overlay = 0, DirtyBit = 0, Xs = 0 [ 9042.745462] user pgtable: 4k pages, 48-bit VAs, pgdp=00003000894ca000 [ 9042.745464] [0000000000000000] pgd=08003000894cb403, p4d=08003000894cb403, pud=0800300085320403, pmd=0000000000000000 [ 9042.830042] Internal error: Oops: 0000000096000006 [#1] SMP [ 9042.838310] Modules linked in: cramfs camellia_generic serpent_generic blowfish_generic blowfish_common cast5_generic cast_common des_generic libdes rmd160 tcp_bic unix_diag ansi_cprng tcp_dctcp ppp_synctty ip_set_hash_ip n_hdlc cmac pps_ldisc n_gsm nfnetlink_log slcan tcp_diag nfnetlink_cthelper atm nfsd auth_rpcgss nfs_acl twofish_generic twofish_common ccm md4 ppp_async msdos nfs lockd grace fscache crc32_generic netfs smc_diag tcp_westwood smc nfnetlink_osf vfio_iommu_type1 vfio vhost_vsock iommufd squashfs ib_core gfs2 snd_timer snd soundcore uhid nfnetlink_cttimeout pppoe ip_vs cuse can_bcm loop can_raw can vsock_loopback inet_diag vmw_vsock_virtio_transport_common vhost_net vhost ieee802154_socket vsock cfg80211 uinput ieee802154 vhost_iotlb pptp crypto_user l2tp_ppp pppox sctp ppp_generic slhc af_key ip6_vti ip_vti ipip sit geneve macvtap tap ipvlan macvlan hsr xfrm_interface xfrm6_tunnel tunnel4 wireguard libchacha20poly1305 chacha_neon poly1305_neon libcurve25519_generic libchacha nlmon team vcan can_dev tun [ 9042.838608] xt_conntrack nft_chain_nat xt_MASQUERADE nf_nat nf_conntrack_netlink nf_conntrack nf_defrag_ipv6 nf_defrag_ipv4 xt_addrtype nft_compat nf_tables overlay nfnetlink_queue authenc echainiv cls_matchall esp6 l2tp_ip6 l2tp_eth l2tp_ip l2tp_netlink l2tp_core br_netfilter sch_etf sch_fq dccp_ipv6 dccp_ipv4 dccp sch_ingress act_mirred cls_basic veth bonding tls esp4_offload esp4 psample macsec vxlan ip6_udp_tunnel udp_tunnel vrf 8021q garp mrp ip6_gre ip6_tunnel tunnel6 ip_gre ip_tunnel gre cls_u32 sch_htb dummy binfmt_misc bridge stp llc rfkill ip_set libcrc32c sunrpc vfat fat ipmi_si ipmi_devintf phytium_dc_drm ses enclosure ipmi_msghandler drm_display_helper scsi_transport_sas cec drm_kms_helper cppc_cpufreq sg drm fuse nfnetlink ext4 mbcache jbd2 sd_mod t10_pi crc64_rocksoft_generic crc64_rocksoft crc64 crct10dif_ce ghash_ce sm4_ce_gcm sm4_ce_ccm sm4_ce sm4_ce_cipher sm4 sm3_ce sha3_ce sha512_ce ahci sha512_arm64 sha2_ce libahci sha256_arm64 ice sha1_ce igb sbsa_gwdt libata megaraid_sas i2c_algo_bit i2c_core [ 9042.958095] dm_mirror dm_region_hash dm_log dm_multipath dm_mod aes_neon_bs aes_neon_blk aes_ce_blk aes_ce_cipher [last unloaded: nf_tables] [ 9043.094331] CPU: 39 PID: 127275 Comm: syz-executor.3 Kdump: loaded Not tainted 6.6.0-0001.rc3.ctl4.aarch64 #1 [ 9043.108430] Hardware name: vclusters VSFT5000 B/VSFT5000 B, BIOS KL4.2A.RC.D.170.240314.D.DX 03/14/2024 18:01:48 [ 9043.122832] pstate: 60400009 (nZCv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--) [ 9043.132983] pc : drm_gem_object_free+0xc/0x40 [drm] [ 9043.140480] lr : phytium_gem_create_object+0x2ac/0x338 [phytium_dc_drm] [ 9043.150238] sp : ffff80009cd83bd0 [ 9043.155639] x29: ffff80009cd83bd0 x28: 00000000000000b2 x27: ffff80009cd83ce8 [ 9043.166023] x26: 0000000000000020 x25: 0000000000000020 x24: ffff80007b4b2d78 [ 9043.176292] x23: ffff00ff8de5b000 x22: 0000000003de4000 x21: 0000000000000000 [ 9043.186548] x20: ffff00ff8df94c80 x19: fffffffffffffff4 x18: ffffffffffffffff [ 9043.196768] x17: 6f74206c69616620 x16: 2a524f5252452a20 x15: 5d5d6d72645f6364 [ 9043.207193] x14: 5f6d756974796870 x13: 205d353732373231 x12: 545b5d3837303330 [ 9043.217647] x11: 00000000ffff7fff x10: ffff80008223b900 x9 : ffff80007b5cdcb4 [ 9043.228070] x8 : 00000000000bffe8 x7 : c0000000ffff7fff x6 : 00000000002bffa8 [ 9043.238522] x5 : ffff80008345bd08 x4 : 0000000000000000 x3 : 0000000000000000 [ 9043.248718] x2 : 0000000000000000 x1 : 0000000000000000 x0 : ffff200014f5b800 [ 9043.258874] Call trace: [ 9043.263132] drm_gem_object_free+0xc/0x40 [drm] [ 9043.270239] phytium_gem_dumb_create+0x60/0x160 [phytium_dc_drm] [ 9043.279194] drm_mode_create_dumb_ioctl+0x98/0xc0 [drm] [ 9043.287188] drm_ioctl_kernel+0xdc/0x188 [drm] [ 9043.294188] drm_ioctl+0x274/0x540 [drm] [ 9043.300456] __arm64_sys_ioctl+0xb4/0x100 [ 9043.306777] invoke_syscall+0x50/0x128 [ 9043.312774] el0_svc_common.constprop.0+0xc8/0xf0 [ 9043.319953] do_el0_svc+0x24/0x38 [ 9043.325324] el0_svc+0x44/0x1b8 [ 9043.330517] el0t_64_sync_handler+0x100/0x130 [ 9043.337369] el0t_64_sync+0x188/0x190 [ 9043.343315] Code: ffff00ff aa1e03e9 952fe875 f940a001 (f9400021) [ 9043.352351] SMP: stopping secondary CPUs [ 9043.412513] Starting crashdump kernel... [ 9044.001381] Bye! ``` Disassembler drm_gem_object_free: ``` 0xffff80007b437398 <drm_gem_object_free>: mov x9, x30 0xffff80007b43739c <drm_gem_object_free+4>: bl 0xffff800080031570 <ftrace_caller> 0xffff80007b4373a0 <drm_gem_object_free+8>: ldr x1, [x0, #320] 0xffff80007b4373a4 <drm_gem_object_free+12>: ldr x1, [x1] 0xffff80007b4373a8 <drm_gem_object_free+16>: cbz x1, 0xffff80007b4373c8 <drm_gem_object_free+48> 0xffff80007b4373ac <drm_gem_object_free+20>: paciasp 0xffff80007b4373b0 <drm_gem_object_free+24>: stp x29, x30, [sp, #-16]! 0xffff80007b4373b4 <drm_gem_object_free+28>: mov x29, sp 0xffff80007b4373b8 <drm_gem_object_free+32>: blr x1 0xffff80007b4373bc <drm_gem_object_free+36>: ldp x29, x30, [sp], #16 0xffff80007b4373c0 <drm_gem_object_free+40>: autiasp 0xffff80007b4373c4 <drm_gem_object_free+44>: ret 0xffff80007b4373c8 <drm_gem_object_free+48>: brk #0x800 0xffff80007b4373cc <drm_gem_object_free+52>: ret 0xffff80007b4373d0 <drm_gem_object_free+56>: .inst 0x865baea8 ; undefined 0xffff80007b4373d4 <drm_gem_object_free+60>: .inst 0xffff00ff ; undefined ``` ldr x1, [x1] <-- trapping instruction Signed-off-by: Li Chen <chenl311(a)chinatelecom.cn> Reviewed-by: Bin Lai <laib2(a)chinatelecom.cn> Reviewed-by: Shuo Li <lishuo(a)phytium.com.cn> --- drivers/gpu/drm/phytium/phytium_gem.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/phytium/phytium_gem.c b/drivers/gpu/drm/phytium/phytium_gem.c index 2cbbcd9fbd112..95b6b0360c065 100644 --- a/drivers/gpu/drm/phytium/phytium_gem.c +++ b/drivers/gpu/drm/phytium/phytium_gem.c @@ -432,6 +432,8 @@ struct phytium_gem_object *phytium_gem_create_object(struct drm_device *dev, uns goto failed_object_init; } + phytium_gem_obj->base.funcs = &phytium_drm_gem_object_funcs; + if (priv->support_memory_type & (MEMORY_TYPE_VRAM_WC | MEMORY_TYPE_VRAM_DEVICE)) { ret = phytium_memory_pool_alloc(priv, &phytium_gem_obj->vaddr, &phytium_gem_obj->phys_addr, size); @@ -475,8 +477,6 @@ struct phytium_gem_object *phytium_gem_create_object(struct drm_device *dev, uns goto failed_dma_alloc; } - phytium_gem_obj->base.funcs = &phytium_drm_gem_object_funcs; - phytium_gem_obj->size = size; list_add_tail(&phytium_gem_obj->list, &priv->gem_list_head); DRM_DEBUG_KMS("phytium_gem_obj iova:0x%pa size:0x%lx\n", -- 2.49.0

1 0

[PATCH openEuler-1.0-LTS 0/2] Fix the race of lock/unlock and open for nfs
by Li Lingfeng 18 Jul '25

18 Jul '25

Fix the race of lock/unlock and open for nfs. Li Lingfeng (2): nfs: fix the race of lock/unlock and open nfs: do not unlock when no lock is held fs/nfs/delegation.c | 5 ++++- fs/nfs/nfs4proc.c | 8 +++++++- 2 files changed, 11 insertions(+), 2 deletions(-) -- 2.31.1

2 3

[openeuler:OLK-6.6 2527/2527] drivers/media/v4l2-core/v4l2-subdev.c:2253:10: error: call to undeclared function 'v4l2_subdev_get_locked_active_state'; ISO C99 and later do not support implicit function declarations
by kernel test robot 18 Jul '25

18 Jul '25

tree: https://gitee.com/openeuler/kernel.git OLK-6.6 head: cbc572af8c3daa87a87df19c570fb3fd3ed99022 commit: c1be6d998806425f28600e867a8e9a2dd9bac741 [2527/2527] media: subdev: Add v4l2_subdev_is_streaming() config: x86_64-buildonly-randconfig-004-20250718 (https://download.01.org/0day-ci/archive/20250718/202507181525.PYgxRhvq-lkp@…) compiler: clang version 20.1.8 (https://github.com/llvm/llvm-project 87f0227cb60147a26a1eeb4fb06e3b505e9c7261) reproduce (this is a W=1 build): (https://download.01.org/0day-ci/archive/20250718/202507181525.PYgxRhvq-lkp@…) If you fix the issue in a separate patch/commit (i.e. not just a new version of the same patch/commit), kindly add following tags | Reported-by: kernel test robot <lkp(a)intel.com> | Closes: https://lore.kernel.org/oe-kbuild-all/202507181525.PYgxRhvq-lkp@intel.com/ All errors (new ones prefixed by >>): >> drivers/media/v4l2-core/v4l2-subdev.c:2253:10: error: call to undeclared function 'v4l2_subdev_get_locked_active_state'; ISO C99 and later do not support implicit function declarations [-Wimplicit-function-declaration] 2253 | state = v4l2_subdev_get_locked_active_state(sd); | ^ >> drivers/media/v4l2-core/v4l2-subdev.c:2253:8: error: incompatible integer to pointer conversion assigning to 'struct v4l2_subdev_state *' from 'int' [-Wint-conversion] 2253 | state = v4l2_subdev_get_locked_active_state(sd); | ^ ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ 2 errors generated. vim +/v4l2_subdev_get_locked_active_state +2253 drivers/media/v4l2-core/v4l2-subdev.c 2242 2243 bool v4l2_subdev_is_streaming(struct v4l2_subdev *sd) 2244 { 2245 struct v4l2_subdev_state *state; 2246 2247 if (!v4l2_subdev_has_op(sd, pad, enable_streams)) 2248 return sd->s_stream_enabled; 2249 2250 if (!(sd->flags & V4L2_SUBDEV_FL_STREAMS)) 2251 return !!sd->enabled_pads; 2252 > 2253 state = v4l2_subdev_get_locked_active_state(sd); 2254 2255 for (unsigned int i = 0; i < state->stream_configs.num_configs; ++i) { 2256 const struct v4l2_subdev_stream_config *cfg; 2257 2258 cfg = &state->stream_configs.configs[i]; 2259 2260 if (cfg->enabled) 2261 return true; 2262 } 2263 2264 return false; 2265 } 2266 EXPORT_SYMBOL_GPL(v4l2_subdev_is_streaming); 2267 -- 0-DAY CI Kernel Test Service https://github.com/intel/lkp-tests/wiki

1 0

[PATCH openEuler-1.0-LTS] net/sched: Abort __tc_modify_qdisc if parent class does not exist
by Dong Chenchen 18 Jul '25

18 Jul '25

From: Victor Nogueira <victor(a)mojatatu.com> mainline inclusion from mainline-v6.16-rc6 commit ffdde7bf5a439aaa1955ebd581f5c64ab1533963 category: bugfix bugzilla: 190701 CVE: NA Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?… -------------------------------- Lion's patch [1] revealed an ancient bug in the qdisc API. Whenever a user creates/modifies a qdisc specifying as a parent another qdisc, the qdisc API will, during grafting, detect that the user is not trying to attach to a class and reject. However grafting is performed after qdisc_create (and thus the qdiscs' init callback) is executed. In qdiscs that eventually call qdisc_tree_reduce_backlog during init or change (such as fq, hhf, choke, etc), an issue arises. For example, executing the following commands: sudo tc qdisc add dev lo root handle a: htb default 2 sudo tc qdisc add dev lo parent a: handle beef fq Qdiscs such as fq, hhf, choke, etc unconditionally invoke qdisc_tree_reduce_backlog() in their control path init() or change() which then causes a failure to find the child class; however, that does not stop the unconditional invocation of the assumed child qdisc's qlen_notify with a null class. All these qdiscs make the assumption that class is non-null. The solution is ensure that qdisc_leaf() which looks up the parent class, and is invoked prior to qdisc_create(), should return failure on not finding the class. In this patch, we leverage qdisc_leaf to return ERR_PTRs whenever the parentid doesn't correspond to a class, so that we can detect it earlier on and abort before qdisc_create is called. [1] https://lore.kernel.org/netdev/d912cbd7-193b-4269-9857-525bee8bbb6a@gmail.c… Fixes: 5e50da01d0ce ("[NET_SCHED]: Fix endless loops (part 2): "simple" qdiscs") Reported-by: syzbot+d8b58d7b0ad89a678a16(a)syzkaller.appspotmail.com Closes: https://lore.kernel.org/netdev/68663c93.a70a0220.5d25f.0857.GAE@google.com/ Reported-by: syzbot+5eccb463fa89309d8bdc(a)syzkaller.appspotmail.com Closes: https://lore.kernel.org/netdev/68663c94.a70a0220.5d25f.0858.GAE@google.com/ Reported-by: syzbot+1261670bbdefc5485a06(a)syzkaller.appspotmail.com Closes: https://lore.kernel.org/netdev/686764a5.a00a0220.c7b3.0013.GAE@google.com/ Reported-by: syzbot+15b96fc3aac35468fe77(a)syzkaller.appspotmail.com Closes: https://lore.kernel.org/netdev/686764a5.a00a0220.c7b3.0014.GAE@google.com/ Reported-by: syzbot+4dadc5aecf80324d5a51(a)syzkaller.appspotmail.com Closes: https://lore.kernel.org/netdev/68679e81.a70a0220.29cf51.0016.GAE@google.com/ Acked-by: Jamal Hadi Salim <jhs(a)mojatatu.com> Reviewed-by: Cong Wang <xiyou.wangcong(a)gmail.com> Signed-off-by: Victor Nogueira <victor(a)mojatatu.com> Link: https://patch.msgid.link/20250707210801.372995-1-victor@mojatatu.com Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> Conflicts: net/sched/sch_api.c [commit d636fc5dd692 and 2561f97267d6 is not backport] Signed-off-by: Dong Chenchen <dongchenchen2(a)huawei.com> --- net/sched/sch_api.c | 23 ++++++++++++++++------- 1 file changed, 16 insertions(+), 7 deletions(-) diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index 976908642263..05bed30b0a6a 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -333,18 +333,23 @@ struct Qdisc *qdisc_lookup_rcu(struct net_device *dev, u32 handle) return q; } -static struct Qdisc *qdisc_leaf(struct Qdisc *p, u32 classid) +static struct Qdisc *qdisc_leaf(struct Qdisc *p, u32 classid, + struct netlink_ext_ack *extack) { unsigned long cl; struct Qdisc *leaf; const struct Qdisc_class_ops *cops = p->ops->cl_ops; - if (cops == NULL) - return NULL; + if (cops == NULL) { + NL_SET_ERR_MSG(extack, "Parent qdisc is not classful"); + return ERR_PTR(-EOPNOTSUPP); + } cl = cops->find(p, classid); - if (cl == 0) - return NULL; + if (cl == 0) { + NL_SET_ERR_MSG(extack, "Specified class not found"); + return ERR_PTR(-ENOENT); + } leaf = cops->leaf(p, cl); return leaf; } @@ -1378,7 +1383,7 @@ static int tc_get_qdisc(struct sk_buff *skb, struct nlmsghdr *n, NL_SET_ERR_MSG(extack, "Failed to find qdisc with specified classid"); return -ENOENT; } - q = qdisc_leaf(p, clid); + q = qdisc_leaf(p, clid, extack); } else if (dev_ingress_queue(dev)) { q = dev_ingress_queue(dev)->qdisc_sleeping; } @@ -1389,6 +1394,8 @@ static int tc_get_qdisc(struct sk_buff *skb, struct nlmsghdr *n, NL_SET_ERR_MSG(extack, "Cannot find specified qdisc on specified device"); return -ENOENT; } + if (IS_ERR(q)) + return PTR_ERR(q); if (tcm->tcm_handle && q->handle != tcm->tcm_handle) { NL_SET_ERR_MSG(extack, "Invalid handle"); @@ -1485,7 +1492,9 @@ static int tc_modify_qdisc(struct sk_buff *skb, struct nlmsghdr *n, NL_SET_ERR_MSG(extack, "Failed to find specified qdisc"); return -ENOENT; } - q = qdisc_leaf(p, clid); + q = qdisc_leaf(p, clid, extack); + if (IS_ERR(q)) + return PTR_ERR(q); } else if (dev_ingress_queue_create(dev)) { q = dev_ingress_queue(dev)->qdisc_sleeping; } -- 2.25.1

2 1

[PATCH OLK-6.6 0/2] CVE-2025-38052
by Wang Liang 18 Jul '25

18 Jul '25

Charalampos Mitrodimas (1): net: tipc: fix refcount warning in tipc_aead_encrypt Wang Liang (1): net/tipc: fix slab-use-after-free Read in tipc_aead_encrypt_done net/tipc/crypto.c | 9 +++++++++ 1 file changed, 9 insertions(+) -- 2.34.1

2 3

[PATCH OLK-6.6] ioinf: inflight based weighted relative controller
by Yu Kuai 18 Jul '25

18 Jul '25

hulk inclusion category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/ICN84T -------------------------------- The demo version 2. Signed-off-by: Yu Kuai <yukuai3(a)huawei.com> --- block/Kconfig | 5 + block/Makefile | 1 + block/blk-ioinf.c | 1280 ++++++++++++++++++++++++++++++++++++++++ block/blk-mq-debugfs.c | 2 + block/blk-rq-qos.h | 1 + include/linux/blk-mq.h | 3 + 6 files changed, 1292 insertions(+) create mode 100644 block/blk-ioinf.c diff --git a/block/Kconfig b/block/Kconfig index 7018fdcaa459..fc57f790d353 100644 --- a/block/Kconfig +++ b/block/Kconfig @@ -204,6 +204,11 @@ config BLK_CGROUP_LEGACY_IOCOST If unsure, say N. ++config BLK_CGROUP_IOINFLIGHT ++ bool "Enable support for inflight based cgroup IO controller" ++ help ++ xxxx + config BLK_CGROUP_IOPRIO bool "Cgroup I/O controller for assigning an I/O priority class" depends on BLK_CGROUP diff --git a/block/Makefile b/block/Makefile index bfba1d2afc0e..eeea4092a5c0 100644 --- a/block/Makefile +++ b/block/Makefile @@ -21,6 +21,7 @@ obj-$(CONFIG_BLK_DEV_THROTTLING) += blk-throttle.o obj-$(CONFIG_BLK_CGROUP_IOPRIO) += blk-ioprio.o obj-$(CONFIG_BLK_CGROUP_IOLATENCY) += blk-iolatency.o obj-$(CONFIG_BLK_CGROUP_IOCOST) += blk-iocost.o +obj-$(CONFIG_BLK_CGROUP_IOINFLIGHT) += blk-ioinf.o obj-$(CONFIG_MQ_IOSCHED_DEADLINE) += mq-deadline.o obj-$(CONFIG_MQ_IOSCHED_KYBER) += kyber-iosched.o bfq-y := bfq-iosched.o bfq-wf2q.o bfq-cgroup.o diff --git a/block/blk-ioinf.c b/block/blk-ioinf.c new file mode 100644 index 000000000000..5b0f422c0310 --- /dev/null +++ b/block/blk-ioinf.c @@ -0,0 +1,1280 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * IO inflight relative controller + */ + +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/timer.h> +#include <linux/time64.h> +#include <linux/parser.h> +#include <linux/blk-cgroup.h> + +#include "blk-cgroup.h" +#include "blk-rq-qos.h" +#include "blk-mq.h" + +/* default weight for each cgroup */ +#define IOINF_DFL_WEIGHT 10 +/* default wake up time in jiffies for backgroup job, see ioinf_timer_fn() */ +#define IOINF_TIMER_PERID 500 +/* default time in jiffies that cgroup will idle without any IO */ +#define INFG_DFL_EXPIRE 100 +/* minimal number of samples for congestion control */ +#define MIN_SAMPLES 100 +/* io.inf.qos controls */ +enum { + INF_ENABLE, + INF_INFLIGHT, + + QOS_ENABLE, + QOS_RLAT, + QOS_WLAT, + QOS_RPCT, + QOS_WPCT, + + NR_QOS_CTRL_PARAMS, +}; + +/* ioinf_gq flags */ +enum { + INFG_EXHAUSTED, + INFG_LEND, + INFG_BORROW, + INFG_OFFLINE, +}; + +/* qos control params */ +struct ioinf_params { + bool enabled; + bool qos_enabled; + u32 inflight; + u64 rlat; + u64 wlat; + u32 rpct; + u32 wpct; +}; + +struct ioinf_lat_stat { + u64 rmet; + u64 wmet; + u64 rmissed; + u64 wmissed; +}; + +struct infg_lat_stat { + atomic_long_t latency; +}; + +/* the global conrtol structure */ +struct ioinf { + struct rq_qos rqos; + + struct ioinf_params params; + /* real inflight with consideration of busy_level */ + u32 inflight; + + /* default time for ioinf_timer_fn */ + unsigned long inf_timer_perid; + struct timer_list inf_timer; + + /* default time for infg_expire_fn */ + unsigned long infg_expire_jiffies; + + /* global lock */ + spinlock_t lock; + /* list of active infgs */ + struct list_head active_infgs; + /* list of active infgs that lend inflight budget to other infgs */ + struct list_head lend_infgs; + /* list of active infgs that borrow inflight budget from other infgs */ + struct list_head borrow_infgs; + + /* for offline cgroups */ + u32 offline_hinflight; + struct rq_wait offline_rqw; + + struct ioinf_lat_stat last_stat; + struct ioinf_lat_stat __percpu *stat; + + int busy_level; + int old_scale; +}; + +/* per disk-cgroup pair structure */ +struct ioinf_gq { + struct blkg_policy_data pd; + struct ioinf *inf; + + unsigned long flags; + /* head of the list is inf->active_infgs */ + struct list_head active; + /* head of the list is inf->lend_infgs */ + struct list_head lend; + /* head of the list is inf->borrow_infgs */ + struct list_head borrow; + + /* configured by user */ + u32 weight; + /* normalized weight */ + u32 hweight; + /* normalized inflight budget */ + u32 hinflight; + /* inuse inflight budget */ + u32 hinflight_inuse; + /* IO beyond budget will wait here */ + struct rq_wait rqw; + + struct timer_list expire_timer; + + /* max inflight in current perid */ + u32 max_inflight; + /* max inflight in last perid, will gradual reduction */ + u32 last_max_inflight; + + /* to calculate avgqu size */ + struct infg_lat_stat stat; +}; + +/* per cgroup structure, used to record default weight for all disks */ +struct ioinf_cgrp { + struct blkcg_policy_data cpd; + + /* if def_weight is 0, means it's offline */ + u32 dfl_weight; +}; + +/* scale inflight according to busy_level, from 1/10 to 10 */ +static const u8 scale_table[20] = { + [0] = 100, /* -90 */ + [1] = 90, /* -80 */ + [2] = 80, /* -70 */ + [3] = 70, /* -60 */ + [4] = 60, /* -50 */ + [5] = 50, /* -40 */ + [6] = 40, /* -30 */ + [7] = 30, /* -20 */ + [8] = 20, /* -10 */ + [9] = 10, /* 0 */ + [10] = 9, /* 10 */ + [11] = 8, /* 20 */ + [12] = 7, /* 30 */ + [13] = 6, /* 40 */ + [14] = 5, /* 50 */ + [15] = 4, /* 60 */ + [16] = 3, /* 70 */ + [17] = 2, /* 80 */ + [18] = 1, /* 90 */ +}; + +static struct blkcg_policy blkcg_policy_ioinf; + +static struct ioinf *rqos_to_inf(struct rq_qos *rqos) +{ + return container_of(rqos, struct ioinf, rqos); +} + +static struct ioinf *q_to_inf(struct request_queue *q) +{ + return rqos_to_inf(rq_qos_id(q, RQ_QOS_INFLIGHT)); +} + +static struct ioinf_gq *pd_to_infg(struct blkg_policy_data *pd) +{ + if (!pd) + return NULL; + + return container_of(pd, struct ioinf_gq, pd); +} + +static struct ioinf_gq *blkg_to_infg(struct blkcg_gq *blkg) +{ + return pd_to_infg(blkg_to_pd(blkg, &blkcg_policy_ioinf)); +} + +static struct blkcg_gq *infg_to_blkg(struct ioinf_gq *infg) +{ + return pd_to_blkg(&infg->pd); +} + +static struct ioinf_cgrp *blkcg_to_infcg(struct blkcg *blkcg) +{ + struct blkcg_policy_data *cpd = + blkcg_to_cpd(blkcg, &blkcg_policy_ioinf); + + return container_of(cpd, struct ioinf_cgrp, cpd); +} + +static struct blkcg_gq *ioinf_bio_blkg(struct bio *bio) +{ + struct blkcg_gq *blkg = bio->bi_blkg; + + if (!blkg || !blkg->online) + return NULL; + + if (blkg->blkcg->css.cgroup->level == 0) + return NULL; + + return blkg; +} + +static struct ioinf_gq *ioinf_bio_infg(struct bio *bio) +{ + struct ioinf_gq *infg; + struct blkcg_gq *blkg = ioinf_bio_blkg(bio); + + if (!blkg) + return NULL; + + infg = blkg_to_infg(blkg); + if (!infg) + return NULL; + + return infg; +} + +static u32 infg_weight(struct ioinf_gq *infg) +{ + struct ioinf_cgrp *infcg; + struct blkcg_gq *blkg; + + if (infg->weight) + return infg->weight; + + /* if user doen't set per disk weight, use the cgroup default weight */ + blkg = infg_to_blkg(infg); + infcg = blkcg_to_infcg(blkg->blkcg); + + return infcg->dfl_weight; +} + +static void infg_clear_loan(struct ioinf_gq *infg) +{ + if (!list_empty(&infg->lend)) { + clear_bit(INFG_LEND, &infg->flags); + list_del_init(&infg->lend); + } + + if (!list_empty(&infg->borrow)) { + clear_bit(INFG_BORROW, &infg->flags); + list_del_init(&infg->borrow); + } +} + +/* + * called when infg is activate or deactivate + * TODO: support cgroup hierarchy, each infg is independent for now + */ +static void __propagate_weights(struct ioinf *inf) +{ + struct ioinf_gq *infg; + u32 total = 0; + + if (list_empty(&inf->active_infgs)) + return; + + /* + * TODO: instead of clearing loan and reinitializing everything, it's + * better to keep loan and do minor incremental modification. + */ + list_for_each_entry(infg, &inf->active_infgs, active) { + total += infg_weight(infg); + infg->max_inflight = 0; + infg->last_max_inflight = 0; + infg_clear_loan(infg); + } + + list_for_each_entry(infg, &inf->active_infgs, active) { + u32 weight = infg_weight(infg); + + infg->hweight = weight * 100 / total; + infg->hinflight = infg->inf->inflight * infg->hweight / 100; + if (!infg->hinflight) + infg->hinflight = 1; + infg->hinflight_inuse = infg->hinflight; + } + + mod_timer(&inf->inf_timer, jiffies + inf->inf_timer_perid); +} + +static void propagate_weights(struct ioinf *inf) +{ + spin_lock_irq(&inf->lock); + __propagate_weights(inf); + spin_unlock_irq(&inf->lock); +} + +static void ioinf_active_infg(struct ioinf_gq *infg) +{ + struct ioinf *inf = infg->inf; + + spin_lock_irq(&inf->lock); + if (list_empty(&infg->active)) { + list_add(&infg->active, &inf->active_infgs); + __propagate_weights(inf); + } + spin_unlock_irq(&inf->lock); +} + +static unsigned int atomic_inc_below_return(atomic_t *v, unsigned int below) +{ + unsigned int cur = atomic_read(v); + + for (;;) { + unsigned int old; + + if (cur >= below) + return below + 1; + + old = atomic_cmpxchg(v, cur, cur + 1); + if (old == cur) + break; + cur = old; + } + + return cur + 1; +} + +/* + * Called from io fast path, return false means inflight IO is full, and the + * forground thread will wait inflight IO to be done. + */ +static bool ioinf_inflight_cb(struct rq_wait *rqw, void *private_data) +{ + struct ioinf_gq *infg = private_data; + unsigned int inflight; + unsigned int limit; + +retry: + limit = infg->hinflight_inuse; + inflight = atomic_inc_below_return(&infg->rqw.inflight, limit); + + if (inflight > infg->max_inflight) + infg->max_inflight = inflight; + + if (inflight <= limit) + return true; + + if (infg->hinflight_inuse == limit) { + /* + * This infg want more inflight budget, set INFG_EXHAUSTED, and + * later ioinf_timer_fn() will check, if other infg can lend + * budget. + */ + if (test_bit(INFG_EXHAUSTED, &infg->flags)) + return false; + + set_bit(INFG_EXHAUSTED, &infg->flags); + return false; + } + + /* Stop lend inflight budget to other infgs */ + infg->hinflight_inuse = infg->hinflight; + /* wake up ioinf_timer_fn() immediately to inform other infgs */ + timer_reduce(&infg->inf->inf_timer, jiffies + 1); + goto retry; +} + +void ioinf_done(struct ioinf_gq *infg) +{ + int inflight = atomic_dec_return(&infg->rqw.inflight); + + BUG_ON(inflight < 0); + + if (inflight < infg->hinflight && wq_has_sleeper(&infg->rqw.wait)) + wake_up_all(&infg->rqw.wait); + + /* deactivate infg if there is no IO for infg_expire_jiffies */ + if (inflight == 0) + mod_timer(&infg->expire_timer, + jiffies + infg->inf->infg_expire_jiffies); +} + +void ioinf_offline_done(struct ioinf *inf) +{ + int inflight = atomic_dec_return(&inf->offline_rqw.inflight); + + if (inflight < inf->offline_hinflight && + wq_has_sleeper(&inf->offline_rqw.wait)) + wake_up_all(&inf->offline_rqw.wait); +} + +static void ioinf_cleanup_cb(struct rq_wait *rqw, void *private_data) +{ + ioinf_done(private_data); +} + +static bool infg_offline(struct ioinf_gq *infg) +{ + struct ioinf_cgrp *infcg; + struct blkcg_gq *blkg; + + if (test_bit(INFG_OFFLINE, &infg->flags)) + return true; + + if (infg->weight != 0) + return false; + + /* if user doen't set per disk weight, use the cgroup default weight */ + blkg = infg_to_blkg(infg); + infcg = blkcg_to_infcg(blkg->blkcg); + + return infcg->dfl_weight == 0; +} + +static bool ioinf_offline_inflight_cb(struct rq_wait *rqw, void *private_data) +{ + struct ioinf *inf = private_data; + + return rq_wait_inc_below(rqw, inf->offline_hinflight); +} + +static void ioinf_offline_cleanup_cb(struct rq_wait *rqw, void *private_data) +{ + struct ioinf *inf = private_data; + + ioinf_offline_done(inf); +} + +static void ioinf_throttle_offline(struct ioinf *inf, struct bio *bio) +{ + rq_qos_wait(&inf->offline_rqw, inf, ioinf_offline_inflight_cb, + ioinf_offline_cleanup_cb, NULL); + + /* + * In case no online cgroup is active, daemon will adjuct all the + * budget to offline cgroup. + */ + timer_reduce(&inf->inf_timer, jiffies + inf->inf_timer_perid); +} + +static void ioinf_rqos_throttle(struct rq_qos *rqos, struct bio *bio) +{ + struct ioinf *inf = rqos_to_inf(rqos); + struct ioinf_gq *infg = ioinf_bio_infg(bio); + + if (!inf->params.enabled || !infg) + return; + + if (infg_offline(infg)) { + ioinf_throttle_offline(inf, bio); + return; + } + + if (list_empty_careful(&infg->active)) + ioinf_active_infg(infg); + + rq_qos_wait(&infg->rqw, infg, ioinf_inflight_cb, ioinf_cleanup_cb, + NULL); +} + +static void ioinf_rqos_track(struct rq_qos *rqos, struct request *rq, + struct bio *bio) +{ + struct blkcg_gq *blkg = ioinf_bio_blkg(bio); + + if (!blkg) + return; + + rq->blkg = blkg; +} + +static void ioinf_rqos_cleanup(struct rq_qos *rqos, struct bio *bio) +{ + struct ioinf_gq *infg = ioinf_bio_infg(bio); + + if (!infg || infg->inf->params.enabled || + list_empty_careful(&infg->active)) + return; + + ioinf_done(infg); +} + +static void ioinf_record_lat(struct ioinf_gq *infg, struct request *rq) +{ + struct ioinf *inf = infg->inf; + u64 lat; + + lat = rq->io_end_time_ns ? rq->io_end_time_ns : blk_time_get_ns(); + lat -= rq->alloc_time_ns; + atomic_long_add(lat, &infg->stat.latency); + + if (!inf->params.qos_enabled) + return; + + switch (req_op(rq)) { + case REQ_OP_READ: + if (lat > inf->params.rlat) + this_cpu_inc(inf->stat->rmissed); + else + this_cpu_inc(inf->stat->rmet); + break; + case REQ_OP_WRITE: + if (lat > inf->params.wlat) + this_cpu_inc(inf->stat->wmissed); + else + this_cpu_inc(inf->stat->wmet); + break; + default: + break; + } +} + +static struct ioinf_lat_stat ioinf_get_lat(struct ioinf *inf) +{ + struct ioinf_lat_stat stat = {0}; + int cpu; + + for_each_possible_cpu(cpu) { + struct ioinf_lat_stat *pstat = per_cpu_ptr(inf->stat, cpu); + + stat.rmet += pstat->rmet; + stat.rmissed += pstat->rmissed; + stat.wmet += pstat->wmet; + stat.wmissed += pstat->wmissed; + } + + return stat; +} + +static void ioinf_rqos_done(struct rq_qos *rqos, struct request *rq) +{ + struct blkcg_gq *blkg = rq->blkg; + struct ioinf_gq *infg; + + if (!blkg) + return; + + infg = blkg_to_infg(blkg); + if (infg_offline(infg)) { + ioinf_offline_done(infg->inf); + } else { + ioinf_done(infg); + ioinf_record_lat(infg, rq); + } + + rq->blkg = NULL; +} + +static void ioinf_rqos_exit(struct rq_qos *rqos) +{ + struct ioinf *inf = rqos_to_inf(rqos); + + blkcg_deactivate_policy(rqos->disk, &blkcg_policy_ioinf); + + del_timer_sync(&inf->inf_timer); + free_percpu(inf->stat); + kfree(inf); +} + +static int ioinf_stat_show(void *data, struct seq_file *m) +{ + struct rq_qos *rqos = data; + struct ioinf *inf = rqos_to_inf(rqos); + struct ioinf_gq *infg; + char path[32]; + + spin_lock_irq(&inf->lock); + + seq_printf(m, "busy_level %d inflight %u->%u\n", inf->busy_level, + inf->params.inflight, inf->inflight); + + list_for_each_entry(infg, &inf->active_infgs, active) { + blkg_path(infg_to_blkg(infg), path, sizeof(path)); + seq_printf(m, "%s: hweight %u", path, infg->hweight); + + if (test_bit(INFG_LEND, &infg->flags)) + seq_puts(m, " lend"); + if (test_bit(INFG_BORROW, &infg->flags)) + seq_puts(m, " borrow"); + if (test_bit(INFG_EXHAUSTED, &infg->flags)) + seq_puts(m, " exhausted"); + + seq_printf(m, " inflight %d/(%d->%d) %u->%u\n", + atomic_read(&infg->rqw.inflight), + infg->hinflight, infg->hinflight_inuse, + infg->last_max_inflight, + infg->max_inflight); + } + + seq_printf(m, "offline inflight %u/%d\n", + atomic_read(&inf->offline_rqw.inflight), + inf->offline_hinflight); + + spin_unlock_irq(&inf->lock); + + return 0; +} + +static int ioinf_lat_show(void *data, struct seq_file *m) +{ + struct rq_qos *rqos = data; + struct ioinf *inf = rqos_to_inf(rqos); + struct ioinf_lat_stat stat = ioinf_get_lat(inf); + struct ioinf_gq *infg; + char path[32]; + + seq_printf(m, "qos lat: %llu %llu %llu %llu\n", + stat.rmet, stat.rmissed, stat.wmet, stat.wmissed); + + spin_lock_irq(&inf->lock); + list_for_each_entry(infg, &inf->active_infgs, active) { + blkg_path(infg_to_blkg(infg), path, sizeof(path)); + seq_printf(m, "%s latency %lu\n", path, + atomic_long_read(&infg->stat.latency)); + } + spin_unlock_irq(&inf->lock); + + return 0; +} + +static const struct blk_mq_debugfs_attr ioinf_debugfs_attrs[] = { + {"stat", 0400, ioinf_stat_show}, + {"lat", 0400, ioinf_lat_show}, + {}, +}; + +static struct rq_qos_ops ioinf_rqos_ops = { + .throttle = ioinf_rqos_throttle, + .done = ioinf_rqos_done, + .track = ioinf_rqos_track, + .cleanup = ioinf_rqos_cleanup, + .exit = ioinf_rqos_exit, + +#ifdef CONFIG_BLK_DEBUG_FS + .debugfs_attrs = ioinf_debugfs_attrs, +#endif +}; + +static void infg_update_inflight(struct ioinf_gq *infg, u32 *exhausted_count) +{ + unsigned int last_max_inflight = infg->last_max_inflight; + + infg->hinflight_inuse = max(last_max_inflight, infg->max_inflight); + + infg->last_max_inflight = max(last_max_inflight >> 1, infg->max_inflight); + infg->max_inflight = infg->max_inflight >> 1; + + if (infg->hinflight_inuse < infg->hinflight) { + clear_bit(INFG_EXHAUSTED, &infg->flags); + clear_bit(INFG_BORROW, &infg->flags); + set_bit(INFG_LEND, &infg->flags); + + if (!list_empty(&infg->borrow)) + list_del_init(&infg->borrow); + if (list_empty(&infg->lend)) + list_add_tail(&infg->lend, &infg->inf->lend_infgs); + } else if (test_bit(INFG_EXHAUSTED, &infg->flags)) { + (*exhausted_count)++; + + if (list_empty(&infg->borrow)) { + set_bit(INFG_BORROW, &infg->flags); + list_add_tail(&infg->borrow, &infg->inf->borrow_infgs); + } + } +} + +static void ioinf_set_offline_inflight(struct ioinf *inf, u32 inflight) +{ + inf->offline_hinflight = inflight; + + if (wq_has_sleeper(&inf->offline_rqw.wait)) + wake_up_all(&inf->offline_rqw.wait); +} + +static bool ioinf_online_busy(struct ioinf *inf) +{ + struct ioinf_lat_stat stat; + u32 met, missed; + bool ret = false; + + if (!inf->params.qos_enabled) + return false; + + stat = ioinf_get_lat(inf); + met = stat.rmet - inf->last_stat.rmet; + missed = stat.rmissed - inf->last_stat.rmissed; + + if (met + missed >= MIN_SAMPLES && + met * 100 < (met + missed) * inf->params.rpct) { + ret = true; + goto out; + } + + met = stat.wmet - inf->last_stat.wmet; + missed = stat.wmissed - inf->last_stat.wmissed; + + if (met + missed >= MIN_SAMPLES && + met * 100 < (met + missed) * inf->params.wpct) + ret = true; + +out: + inf->last_stat = stat; + return ret; +} + +static void inf_clear_exhausted(struct ioinf *inf, u32 borrow) +{ + struct ioinf_gq *infg; + + list_for_each_entry(infg, &inf->borrow_infgs, borrow) + if (test_and_clear_bit(INFG_EXHAUSTED, &infg->flags)) + infg->hinflight_inuse += borrow; +} + +static void ioinf_adjust_busy_level(struct ioinf *inf, u32 old_busy_level) +{ + struct ioinf_gq *infg; + int scale; + + inf->busy_level = clamp(inf->busy_level, -90, 90); + + if (inf->busy_level == old_busy_level) + return; + + scale = (inf->busy_level + 90) / 10; + if (scale == inf->old_scale) + return; + + scale = scale_table[scale]; + inf->old_scale = scale; + + inf->inflight = inf->params.inflight * scale / 10; + + list_for_each_entry(infg, &inf->active_infgs, active) { + infg->hinflight = inf->inflight * infg->hweight / 100; + if (!infg->hinflight) + infg->hinflight = 1; + if (infg->hinflight_inuse < infg->hinflight) { + infg->hinflight_inuse = infg->hinflight; + if (wq_has_sleeper(&infg->rqw.wait)) + wake_up_all(&infg->rqw.wait); + } + } +} + +static void infg_clear_borrow(struct ioinf *inf, int borrow) +{ + struct ioinf_gq *infg; + int count = 0; + +retry: + list_for_each_entry(infg, &inf->borrow_infgs, borrow) { + if (infg->hinflight_inuse > infg->hinflight) { + infg->hinflight_inuse--; + count++; + } + } + + borrow -= count; + if (count && borrow > 0) + goto retry; +} + +static void ioinf_timer_fn(struct timer_list *timer) +{ + struct ioinf *inf = container_of(timer, struct ioinf, inf_timer); + int exhausted_count = 0, lend_total = 0, borrow_total = 0; + u32 old_busy_level = inf->busy_level; + bool busy = ioinf_online_busy(inf); + struct ioinf_gq *infg; + unsigned long flags; + + /* only offline cgroup is active */ + if (list_empty_careful(&inf->active_infgs)) { + ioinf_set_offline_inflight(inf, inf->inflight); + return; + } + + spin_lock_irqsave(&inf->lock, flags); + + list_for_each_entry(infg, &inf->active_infgs, active) + infg_update_inflight(infg, &exhausted_count); + + list_for_each_entry(infg, &inf->lend_infgs, lend) + lend_total += infg->hinflight - infg->hinflight_inuse; + + list_for_each_entry(infg, &inf->borrow_infgs, borrow) + borrow_total += infg->hinflight_inuse - infg->hinflight; + + if (lend_total < 0) + lend_total = 0; + if (borrow_total < 0) + borrow_total = 0; + if (lend_total >= borrow_total) { + lend_total -= borrow_total; + } else { + borrow_total -= lend_total; + lend_total = 0; + infg_clear_borrow(inf, borrow_total); + } + /* + * TODO: handle loan gracefully, equal division for now. + */ + if (exhausted_count) { + u32 borrow; + + if (inf->offline_hinflight > 1) { + ioinf_set_offline_inflight(inf, 1); + goto unlock; + } + + borrow = lend_total / exhausted_count; + if (borrow > 0) + inf_clear_exhausted(inf, borrow); + else if (busy) /* slow down */ + inf->busy_level += exhausted_count; + else if (inf->params.qos_enabled) + inf->busy_level--; + } else { + if (busy) { /* too much budget */ + if (inf->offline_hinflight > 1) + inf->offline_hinflight <<= 1; + inf->busy_level++; + } else { /* everything is fine, upgrade offline */ + if (inf->params.qos_enabled) + inf->busy_level--; + if (lend_total > inf->offline_hinflight) + ioinf_set_offline_inflight(inf, lend_total); + } + } + + ioinf_adjust_busy_level(inf, old_busy_level); + +unlock: + spin_unlock_irqrestore(&inf->lock, flags); + + if (!list_empty_careful(&inf->active_infgs)) + mod_timer(&inf->inf_timer, jiffies + inf->inf_timer_perid); +} + +static u32 ioinf_default_inflight(struct gendisk *disk) +{ + return max(disk->queue->nr_requests / 10, 30); +} + +static int blk_ioinf_init(struct gendisk *disk) +{ + struct ioinf *inf; + int ret; + + inf = kzalloc(sizeof(*inf), GFP_KERNEL); + if (!inf) + return -ENOMEM; + + inf->stat = alloc_percpu(struct ioinf_lat_stat); + if (!inf->stat) { + kfree(inf); + return -ENOMEM; + } + + spin_lock_init(&inf->lock); + inf->params.inflight = ioinf_default_inflight(disk); + inf->inflight = inf->params.inflight; + inf->infg_expire_jiffies = INFG_DFL_EXPIRE; + inf->inf_timer_perid = IOINF_TIMER_PERID; + inf->offline_hinflight = 1; + inf->old_scale = 9; + rq_wait_init(&inf->offline_rqw); + + INIT_LIST_HEAD(&inf->active_infgs); + INIT_LIST_HEAD(&inf->lend_infgs); + INIT_LIST_HEAD(&inf->borrow_infgs); + timer_setup(&inf->inf_timer, ioinf_timer_fn, 0); + + ret = rq_qos_add(&inf->rqos, disk, RQ_QOS_INFLIGHT, &ioinf_rqos_ops); + if (ret) + goto err_free_inf; + + ret = blkcg_activate_policy(disk, &blkcg_policy_ioinf); + if (ret) + goto err_del_qos; + return 0; + +err_del_qos: + rq_qos_del(&inf->rqos); +err_free_inf: + free_percpu(inf->stat); + kfree(inf); + return ret; +} + +static struct blkcg_policy_data *ioinf_cpd_alloc(gfp_t gfp) +{ + struct ioinf_cgrp *infcg = kzalloc(sizeof(*infcg), gfp); + + if (!infcg) + return NULL; + + infcg->dfl_weight = IOINF_DFL_WEIGHT; + return &infcg->cpd; +} + +static void ioinf_cpd_free(struct blkcg_policy_data *cpd) +{ + kfree(container_of(cpd, struct ioinf_cgrp, cpd)); +} + +static struct blkg_policy_data *ioinf_pd_alloc(struct gendisk *disk, + struct blkcg *blkcg, gfp_t gfp) +{ + struct ioinf_gq *infg = kzalloc_node(sizeof(*infg), gfp, disk->node_id); + + if (!infg) + return NULL; + + return &infg->pd; +} + +static void infg_expire_fn(struct timer_list *timer) +{ + struct ioinf_gq *infg = + container_of(timer, struct ioinf_gq, expire_timer); + struct ioinf *inf = infg->inf; + unsigned long flags; + + if (atomic_read(&infg->rqw.inflight) > 0) + return; + + spin_lock_irqsave(&inf->lock, flags); + if (atomic_read(&infg->rqw.inflight) == 0) { + list_del_init(&infg->active); + if (atomic_read(&infg->rqw.inflight) == 0) { + infg_clear_loan(infg); + __propagate_weights(inf); + } else { + list_add(&infg->active, &inf->active_infgs); + } + } + spin_unlock_irqrestore(&inf->lock, flags); +} + +static void ioinf_pd_init(struct blkg_policy_data *pd) +{ + struct ioinf_gq *infg = pd_to_infg(pd); + struct blkcg_gq *blkg = pd_to_blkg(pd); + + INIT_LIST_HEAD(&infg->active); + INIT_LIST_HEAD(&infg->lend); + INIT_LIST_HEAD(&infg->borrow); + infg->inf = q_to_inf(blkg->q); + rq_wait_init(&infg->rqw); + timer_setup(&infg->expire_timer, infg_expire_fn, 0); +} + +static void ioinf_pd_offline(struct blkg_policy_data *pd) +{ + struct ioinf_gq *infg = pd_to_infg(pd); + struct ioinf *inf = infg->inf; + + if (list_empty_careful(&infg->active)) + return; + + del_timer_sync(&infg->expire_timer); + + spin_lock_irq(&inf->lock); + + if (!list_empty(&infg->lend)) + list_del_init(&infg->lend); + + if (!list_empty(&infg->borrow)) + list_del_init(&infg->borrow); + + if (!list_empty(&infg->active)) { + list_del_init(&infg->active); + __propagate_weights(inf); + } + + spin_unlock_irq(&inf->lock); +} + +static void ioinf_pd_free(struct blkg_policy_data *pd) +{ + struct ioinf_gq *infg = pd_to_infg(pd); + + kfree(infg); +} + +static u64 ioinf_weight_prfill(struct seq_file *sf, struct blkg_policy_data *pd, + int off) +{ + const char *dname = blkg_dev_name(pd->blkg); + struct ioinf_gq *infg = pd_to_infg(pd); + + if (dname && infg->weight) + seq_printf(sf, "%s %u\n", dname, infg->weight); + + return 0; +} + +static int ioinf_weight_show(struct seq_file *sf, void *v) +{ + struct blkcg *blkcg = css_to_blkcg(seq_css(sf)); + struct ioinf_cgrp *infcg = blkcg_to_infcg(blkcg); + + seq_printf(sf, "default %u\n", infcg->dfl_weight); + blkcg_print_blkgs(sf, blkcg, ioinf_weight_prfill, &blkcg_policy_ioinf, + seq_cft(sf)->private, false); + + return 0; +} + +static ssize_t ioinf_weight_write(struct kernfs_open_file *of, char *buf, + size_t nbytes, loff_t off) +{ + struct blkcg *blkcg = css_to_blkcg(of_css(of)); + struct ioinf_cgrp *infcg = blkcg_to_infcg(blkcg); + struct blkg_conf_ctx ctx; + struct ioinf_gq *infg; + int ret; + u32 v; + + if (!strchr(buf, ':')) { + if (!sscanf(buf, "default %u", &v) && !sscanf(buf, "%u", &v)) + return -EINVAL; + if (v < 0) + return -EINVAL; + + infcg->dfl_weight = v; + + return nbytes; + } + + blkg_conf_init(&ctx, buf); + ret = blkg_conf_prep(blkcg, &blkcg_policy_ioinf, &ctx); + if (ret) + return ret; + + infg = blkg_to_infg(ctx.blkg); + if (!strncmp(ctx.body, "default", 7)) { + v = IOINF_DFL_WEIGHT; + } else if (!sscanf(ctx.body, "%u", &v) || + v < 0 || v > CGROUP_WEIGHT_MAX) { + blkg_conf_exit(&ctx); + return -EINVAL; + } + + infg->weight = v; + if (v == 0) + set_bit(INFG_OFFLINE, &infg->flags); + else + clear_bit(INFG_OFFLINE, &infg->flags); + blkg_conf_exit(&ctx); + propagate_weights(infg->inf); + return nbytes; +} + +static u64 ioinf_qos_prfill(struct seq_file *sf, struct blkg_policy_data *pd, + int off) +{ + const char *dname = blkg_dev_name(pd->blkg); + struct ioinf *inf = q_to_inf(pd->blkg->q); + struct ioinf_params params; + + if (!dname) + return 0; + + params = inf->params; + seq_printf(sf, "%s enable=%d inflight=%u qos_enable=%d", dname, + params.enabled, params.inflight, params.qos_enabled); + + if (inf->params.qos_enabled) + seq_printf(sf, " rlat=%llu rpct=%u wlat=%llu wpct=%u", + params.rlat, params.rpct, params.wlat, params.wpct); + + seq_putc(sf, '\n'); + return 0; +} + +static int ioinf_qos_show(struct seq_file *sf, void *v) +{ + struct blkcg *blkcg = css_to_blkcg(seq_css(sf)); + + blkcg_print_blkgs(sf, blkcg, ioinf_qos_prfill, + &blkcg_policy_ioinf, seq_cft(sf)->private, false); + return 0; +} + +static const match_table_t qos_ctrl_tokens = { + { INF_ENABLE, "enable=%u" }, + { INF_INFLIGHT, "inflight=%u" }, + { QOS_ENABLE, "qos_enable=%u" }, + { QOS_RLAT, "rlat=%u" }, + { QOS_WLAT, "wlat=%u" }, + { QOS_RPCT, "rpct=%u" }, + { QOS_WPCT, "wpct=%u" }, + { NR_QOS_CTRL_PARAMS, NULL }, +}; + +static ssize_t ioinf_qos_write(struct kernfs_open_file *of, char *input, + size_t nbytes, loff_t off) +{ + struct blkg_conf_ctx ctx; + struct gendisk *disk; + struct ioinf *inf; + struct ioinf_params params; + char *body, *p; + int ret; + + blkg_conf_init(&ctx, input); + + ret = blkg_conf_open_bdev(&ctx); + if (ret) + goto err; + + body = ctx.body; + disk = ctx.bdev->bd_disk; + if (!queue_is_mq(disk->queue)) { + ret = -EOPNOTSUPP; + goto err; + } + + inf = q_to_inf(disk->queue); + if (!inf) { + ret = blk_ioinf_init(disk); + if (ret) + goto err; + + inf = q_to_inf(disk->queue); + } + + params = inf->params; + + while ((p = strsep(&body, " \t\n"))) { + substring_t args[MAX_OPT_ARGS]; + s64 v; + + if (!*p) + continue; + + switch (match_token(p, qos_ctrl_tokens, args)) { + case INF_ENABLE: + if (match_u64(&args[0], &v)) + goto einval; + params.enabled = !!v; + continue; + case QOS_ENABLE: + if (match_u64(&args[0], &v)) + goto einval; + params.qos_enabled = !!v; + continue; + case INF_INFLIGHT: + if (match_u64(&args[0], &v)) + goto einval; + params.inflight = v; + continue; + case QOS_RLAT: + if (match_u64(&args[0], &v) || v == 0) + goto einval; + params.rlat = v; + continue; + case QOS_WLAT: + if (match_u64(&args[0], &v) || v == 0) + goto einval; + params.wlat = v; + continue; + case QOS_RPCT: + if (match_u64(&args[0], &v) || v == 0 || v >= 100) + goto einval; + params.rpct = v; + continue; + case QOS_WPCT: + if (match_u64(&args[0], &v) || v == 0 || v >= 100) + goto einval; + params.wpct = v; + continue; + default: + goto einval; + } + } + + if (params.qos_enabled && + (params.rlat == 0 || params.wlat == 0 || + params.rpct == 0 || params.rpct >= 100 || + params.wpct == 0 || params.wpct >= 100)) + goto einval; + + if (params.inflight == 0) + params.inflight = ioinf_default_inflight(disk); + + if (params.qos_enabled && !inf->params.qos_enabled) { + blk_stat_enable_accounting(disk->queue); + blk_queue_flag_set(QUEUE_FLAG_RQ_ALLOC_TIME, disk->queue); + } else if (!params.qos_enabled && inf->params.qos_enabled) { + blk_stat_disable_accounting(disk->queue); + blk_queue_flag_clear(QUEUE_FLAG_RQ_ALLOC_TIME, disk->queue); + } + + inf->params = params; + inf->busy_level = 0; + inf->old_scale = 9; + inf->inflight = params.inflight; + propagate_weights(inf); + + blkg_conf_exit(&ctx); + return nbytes; + +einval: + ret = -EINVAL; +err: + blkg_conf_exit(&ctx); + return ret; +} + +static struct cftype ioinf_files[] = { + { + .name = "inf.weight", + .flags = CFTYPE_NOT_ON_ROOT, + .seq_show = ioinf_weight_show, + .write = ioinf_weight_write, + }, + { + .name = "inf.qos", + .flags = CFTYPE_ONLY_ON_ROOT, + .seq_show = ioinf_qos_show, + .write = ioinf_qos_write, + }, + {} +}; + +static struct cftype ioinf_legacy_files[] = { + { + .name = "inf.weight", + .flags = CFTYPE_NOT_ON_ROOT, + .seq_show = ioinf_weight_show, + .write = ioinf_weight_write, + }, + { + .name = "inf.qos", + .flags = CFTYPE_ONLY_ON_ROOT, + .seq_show = ioinf_qos_show, + .write = ioinf_qos_write, + }, + {} +}; + +static struct blkcg_policy blkcg_policy_ioinf = { + .dfl_cftypes = ioinf_files, + .legacy_cftypes = ioinf_legacy_files, + + .cpd_alloc_fn = ioinf_cpd_alloc, + .cpd_free_fn = ioinf_cpd_free, + + .pd_alloc_fn = ioinf_pd_alloc, + .pd_init_fn = ioinf_pd_init, + .pd_offline_fn = ioinf_pd_offline, + .pd_free_fn = ioinf_pd_free, +}; + +static int __init ioinf_init(void) +{ + return blkcg_policy_register(&blkcg_policy_ioinf); +} + +static void __exit ioinf_exit(void) +{ + blkcg_policy_unregister(&blkcg_policy_ioinf); +} + +module_init(ioinf_init); +module_exit(ioinf_exit); diff --git a/block/blk-mq-debugfs.c b/block/blk-mq-debugfs.c index efe99cfae51d..b5af47bf99d4 100644 --- a/block/blk-mq-debugfs.c +++ b/block/blk-mq-debugfs.c @@ -798,6 +798,8 @@ static const char *rq_qos_id_to_name(enum rq_qos_id id) return "latency"; case RQ_QOS_COST: return "cost"; + case RQ_QOS_INFLIGHT: + return "inflight"; } return "unknown"; } diff --git a/block/blk-rq-qos.h b/block/blk-rq-qos.h index 93d1ba692973..d504a302ca0f 100644 --- a/block/blk-rq-qos.h +++ b/block/blk-rq-qos.h @@ -17,6 +17,7 @@ enum rq_qos_id { RQ_QOS_WBT, RQ_QOS_LATENCY, RQ_QOS_COST, + RQ_QOS_INFLIGHT, }; struct rq_wait { diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 4c4416fd2df7..81a733e1bef9 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -115,6 +115,9 @@ struct request { #ifdef CONFIG_BLK_WBT unsigned short wbt_flags; +#endif +#ifdef CONFIG_BLK_CGROUP_IOINFLIGHT + struct blkcg_gq *blkg; #endif /* * rq sectors used for blk stats. It has the same value -- 2.39.2

2 1