avoid acquiring mptcp_data_lock() twice in the receive path #141

pabeni · 2021-01-20T10:24:07Z

processing MPTCP data packets carrying a DSS ack require the acquisition of the mptcp_data_lock() twice:

the first one in mptcp_incoming_options(), when processing the DSS ack, to cleanup the send queue and ev. push the pending data
the second one in subflow_data_ready() to enqueue the ingress data inside the msk receive queue.

Performing both operation at subflow_data_ready() time - for data packet pure ack will still get processed by mptcp_incoming_options() - would be beneficial for performance and fairness.

There are a few shortcoming:

processing of MPTCP-level ack carried by TCP out-of-order data packet will be delayed until the relevant out of sequence data will be processed
MPTCP-level ack carried by out-of-window TCP packet will be lost (currently they are not, and TCP level ack are processed).

When 'nicstar_init_one' fails, 'ns_init_card_error' will be executed for error handling, but the correct memory free function should be used, otherwise it will cause an error. Since 'card->rsq.org' and 'card->tsq.org' are allocated using 'dma_alloc_coherent' function, they should be freed using 'dma_free_coherent'. Fix this by using 'dma_free_coherent' instead of 'kfree' This log reveals it: [ 3.440294] kernel BUG at mm/slub.c:4206! [ 3.441059] invalid opcode: 0000 [#1] PREEMPT SMP PTI [ 3.441430] CPU: 2 PID: 1 Comm: swapper/0 Not tainted 5.12.4-g70e7f0549188-dirty #141 [ 3.441986] Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS rel-1.12.0-59-gc9ba5276e321-prebuilt.qemu.org 04/01/2014 [ 3.442780] RIP: 0010:kfree+0x26a/0x300 [ 3.443065] Code: e8 3a c3 b9 ff e9 d6 fd ff ff 49 8b 45 00 31 db a9 00 00 01 00 75 4d 49 8b 45 00 a9 00 00 01 00 75 0a 49 8b 45 08 a8 01 75 02 <0f> 0b 89 d9 b8 00 10 00 00 be 06 00 00 00 48 d3 e0 f7 d8 48 63 d0 [ 3.443396] RSP: 0000:ffffc90000017b70 EFLAGS: 00010246 [ 3.443396] RAX: dead000000000100 RBX: 0000000000000000 RCX: 0000000000000000 [ 3.443396] RDX: 0000000000000000 RSI: ffffffff85d3df94 RDI: ffffffff85df38e6 [ 3.443396] RBP: ffffc90000017b90 R08: 0000000000000001 R09: 0000000000000001 [ 3.443396] R10: 0000000000000000 R11: 0000000000000001 R12: ffff888107dc0000 [ 3.443396] R13: ffffea00001f0100 R14: ffff888101a8bf00 R15: ffff888107dc0160 [ 3.443396] FS: 0000000000000000(0000) GS:ffff88817bc80000(0000) knlGS:0000000000000000 [ 3.443396] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 3.443396] CR2: 0000000000000000 CR3: 000000000642e000 CR4: 00000000000006e0 [ 3.443396] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 3.443396] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 3.443396] Call Trace: [ 3.443396] ns_init_card_error+0x12c/0x220 [ 3.443396] nicstar_init_one+0x10d2/0x1130 [ 3.443396] local_pci_probe+0x4a/0xb0 [ 3.443396] pci_device_probe+0x126/0x1d0 [ 3.443396] ? pci_device_remove+0x100/0x100 [ 3.443396] really_probe+0x27e/0x650 [ 3.443396] driver_probe_device+0x84/0x1d0 [ 3.443396] ? mutex_lock_nested+0x16/0x20 [ 3.443396] device_driver_attach+0x63/0x70 [ 3.443396] __driver_attach+0x117/0x1a0 [ 3.443396] ? device_driver_attach+0x70/0x70 [ 3.443396] bus_for_each_dev+0xb6/0x110 [ 3.443396] ? rdinit_setup+0x40/0x40 [ 3.443396] driver_attach+0x22/0x30 [ 3.443396] bus_add_driver+0x1e6/0x2a0 [ 3.443396] driver_register+0xa4/0x180 [ 3.443396] __pci_register_driver+0x77/0x80 [ 3.443396] ? uPD98402_module_init+0xd/0xd [ 3.443396] nicstar_init+0x1f/0x75 [ 3.443396] do_one_initcall+0x7a/0x3d0 [ 3.443396] ? rdinit_setup+0x40/0x40 [ 3.443396] ? rcu_read_lock_sched_held+0x4a/0x70 [ 3.443396] kernel_init_freeable+0x2a7/0x2f9 [ 3.443396] ? rest_init+0x2c0/0x2c0 [ 3.443396] kernel_init+0x13/0x180 [ 3.443396] ? rest_init+0x2c0/0x2c0 [ 3.443396] ? rest_init+0x2c0/0x2c0 [ 3.443396] ret_from_fork+0x1f/0x30 [ 3.443396] Modules linked in: [ 3.443396] Dumping ftrace buffer: [ 3.443396] (ftrace buffer empty) [ 3.458593] ---[ end trace 3c6f8f0d8ef59bcd ]--- [ 3.458922] RIP: 0010:kfree+0x26a/0x300 [ 3.459198] Code: e8 3a c3 b9 ff e9 d6 fd ff ff 49 8b 45 00 31 db a9 00 00 01 00 75 4d 49 8b 45 00 a9 00 00 01 00 75 0a 49 8b 45 08 a8 01 75 02 <0f> 0b 89 d9 b8 00 10 00 00 be 06 00 00 00 48 d3 e0 f7 d8 48 63 d0 [ 3.460499] RSP: 0000:ffffc90000017b70 EFLAGS: 00010246 [ 3.460870] RAX: dead000000000100 RBX: 0000000000000000 RCX: 0000000000000000 [ 3.461371] RDX: 0000000000000000 RSI: ffffffff85d3df94 RDI: ffffffff85df38e6 [ 3.461873] RBP: ffffc90000017b90 R08: 0000000000000001 R09: 0000000000000001 [ 3.462372] R10: 0000000000000000 R11: 0000000000000001 R12: ffff888107dc0000 [ 3.462871] R13: ffffea00001f0100 R14: ffff888101a8bf00 R15: ffff888107dc0160 [ 3.463368] FS: 0000000000000000(0000) GS:ffff88817bc80000(0000) knlGS:0000000000000000 [ 3.463949] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 3.464356] CR2: 0000000000000000 CR3: 000000000642e000 CR4: 00000000000006e0 [ 3.464856] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 3.465356] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 3.465860] Kernel panic - not syncing: Fatal exception [ 3.466370] Dumping ftrace buffer: [ 3.466616] (ftrace buffer empty) [ 3.466871] Kernel Offset: disabled [ 3.467122] Rebooting in 1 seconds.. Signed-off-by: Zheyu Ma <zheyuma97@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>

Add selftests for nested_strust to check whehter PTR_UNTRUSTED is cleared as expected, the result as follows: #141/1 nested_trust/test_read_cpumask:OK #141/2 nested_trust/test_skb_field:OK <<<< #141/3 nested_trust/test_invalid_nested_user_cpus:OK #141/4 nested_trust/test_invalid_nested_offset:OK #141/5 nested_trust/test_invalid_skb_field:OK <<<< #141 nested_trust:OK The #141/2 and #141/5 are newly added. Signed-off-by: Yafang Shao <laoar.shao@gmail.com> Link: https://lore.kernel.org/r/20230713025642.27477-3-laoar.shao@gmail.com Signed-off-by: Alexei Starovoitov <ast@kernel.org>

Inject fault while probing kunit-example-test.ko, if kzalloc fails in kunit_parse_glob_filter(), strcpy() or strncpy() to NULL will cause below null-ptr-deref bug. So check NULL for kzalloc() and return int instead of void for kunit_parse_glob_filter(). Unable to handle kernel paging request at virtual address dfff800000000000 KASAN: null-ptr-deref in range [0x0000000000000000-0x0000000000000007] Mem abort info: ESR = 0x0000000096000005 EC = 0x25: DABT (current EL), IL = 32 bits SET = 0, FnV = 0 EA = 0, S1PTW = 0 FSC = 0x05: level 1 translation fault Data abort info: ISV = 0, ISS = 0x00000005, ISS2 = 0x00000000 CM = 0, WnR = 0, TnD = 0, TagAccess = 0 GCS = 0, Overlay = 0, DirtyBit = 0, Xs = 0 [dfff800000000000] address between user and kernel address ranges Internal error: Oops: 0000000096000005 [#1] PREEMPT SMP Modules linked in: kunit_example_test cfg80211 rfkill 8021q garp mrp stp llc ipv6 [last unloaded: kunit_example_test] CPU: 4 PID: 6047 Comm: modprobe Tainted: G W N 6.5.0-next-20230829+ #141 Hardware name: linux,dummy-virt (DT) pstate: 80000005 (Nzcv daif -PAN -UAO -TCO -DIT -SSBS BTYPE=--) pc : strncpy+0x58/0xc0 lr : kunit_filter_suites+0x15c/0xa84 sp : ffff800082a17420 x29: ffff800082a17420 x28: 0000000000000000 x27: 0000000000000004 x26: 0000000000000000 x25: ffffa847e40a5320 x24: 0000000000000001 x23: 0000000000000000 x22: 0000000000000001 x21: dfff800000000000 x20: 000000000000002a x19: 0000000000000000 x18: 00000000750b3b54 x17: 0000000000000000 x16: 0000000000000000 x15: 0000000000000000 x14: 0000000000000000 x13: 34393178302f3039 x12: ffff7508fcea4ec1 x11: 1ffff508fcea4ec0 x10: ffff7508fcea4ec0 x9 : dfff800000000000 x8 : ffff6051b1a7f86a x7 : ffff800082a17270 x6 : 0000000000000002 x5 : 0000000000000098 x4 : ffff028d9817b250 x3 : 0000000000000000 x2 : 0000000000000000 x1 : ffffa847e40a5320 x0 : 0000000000000000 Call trace: strncpy+0x58/0xc0 kunit_filter_suites+0x15c/0xa84 kunit_module_notify+0x1b0/0x3ac blocking_notifier_call_chain+0xc4/0x128 do_init_module+0x250/0x594 load_module+0x37b0/0x44b4 init_module_from_file+0xd4/0x128 idempotent_init_module+0x2c8/0x524 __arm64_sys_finit_module+0xac/0x100 invoke_syscall+0x6c/0x258 el0_svc_common.constprop.0+0x160/0x22c do_el0_svc+0x44/0x5c el0_svc+0x38/0x78 el0t_64_sync_handler+0x13c/0x158 el0t_64_sync+0x190/0x194 Code: 5400028a d343fe63 12000a62 39400034 (38f56863) ---[ end trace 0000000000000000 ]--- Kernel panic - not syncing: Oops: Fatal exception SMP: stopping secondary CPUs Kernel Offset: 0x284761400000 from 0xffff800080000000 PHYS_OFFSET: 0xfffffd7380000000 CPU features: 0x88000203,3c020000,1000421b Memory Limit: none Rebooting in 1 seconds.. Fixes: a127b15 ("kunit: tool: allow filtering test cases via glob") Signed-off-by: Jinjie Ruan <ruanjinjie@huawei.com> Reviewed-by: Rae Moar <rmoar@google.com> Reviewed-by: David Gow <davidgow@google.com> Signed-off-by: Shuah Khan <skhan@linuxfoundation.org>

This will add eBPF JIT support to the 32-bit ARCv2 processors. The implementation is qualified by running the BPF tests on a Synopsys HSDK board with "ARC HS38 v2.1c at 500 MHz" as the 4-core CPU. The test_bpf.ko reports 2-10 fold improvements in execution time of its tests. For instance: test_bpf: #33 tcpdump port 22 jited:0 704 1766 2104 PASS test_bpf: #33 tcpdump port 22 jited:1 120 224 260 PASS test_bpf: #141 ALU_DIV_X: 4294967295 / 4294967295 = 1 jited:0 238 PASS test_bpf: #141 ALU_DIV_X: 4294967295 / 4294967295 = 1 jited:1 23 PASS test_bpf: #776 JMP32_JGE_K: all ... magnitudes jited:0 2034681 PASS test_bpf: #776 JMP32_JGE_K: all ... magnitudes jited:1 1020022 PASS Deployment and structure ------------------------ The related codes are added to "arch/arc/net": - bpf_jit.h -- The interface that a back-end translator must provide - bpf_jit_core.c -- Knows how to handle the input eBPF byte stream - bpf_jit_arcv2.c -- The back-end code that knows the translation logic The bpf_int_jit_compile() at the end of bpf_jit_core.c is the entrance to the whole process. Normally, the translation is done in one pass, namely the "normal pass". In case some relocations are not known during this pass, some data (arc_jit_data) is allocated for the next pass to come. This possible next (and last) pass is called the "extra pass". 1. Normal pass # The necessary pass 1a. Dry run # Get the whole JIT length, epilogue offset, etc. 1b. Emit phase # Allocate memory and start emitting instructions 2. Extra pass # Only needed if there are relocations to be fixed 2a. Patch relocations Support status -------------- The JIT compiler supports BPF instructions up to "cpu=v4". However, it does not yet provide support for: - Tail calls - Atomic operations - 64-bit division/remainder - BPF_PROBE_MEM* (exception table) The result of "test_bpf" test suite on an HSDK board is: hsdk-lnx# insmod test_bpf.ko test_suite=test_bpf test_bpf: Summary: 863 PASSED, 186 FAILED, [851/851 JIT'ed] All the failing test cases are due to the ones that were not JIT'ed. Categorically, they can be represented as: .-----------.------------.-------------. | test type | opcodes | # of cases | |-----------+------------+-------------| | atomic | 0xC3, 0xDB | 149 | | div64 | 0x37, 0x3F | 22 | | mod64 | 0x97, 0x9F | 15 | `-----------^------------+-------------| | (total) 186 | `-------------' Setup: build config ------------------- The following configs must be set to have a working JIT test: CONFIG_BPF_JIT=y CONFIG_BPF_JIT_ALWAYS_ON=y CONFIG_TEST_BPF=m The following options are not necessary for the tests module, but are good to have: CONFIG_DEBUG_INFO=y # prerequisite for below CONFIG_DEBUG_INFO_BTF=y # so bpftool can generate vmlinux.h CONFIG_FTRACE=y # CONFIG_BPF_SYSCALL=y # all these options lead to CONFIG_KPROBE_EVENTS=y # having CONFIG_BPF_EVENTS=y CONFIG_PERF_EVENTS=y # Some BPF programs provide data through /sys/kernel/debug: CONFIG_DEBUG_FS=y arc# mount -t debugfs debugfs /sys/kernel/debug Setup: elfutils --------------- The libdw.{so,a} library that is used by pahole for processing the final binary must come from elfutils 0.189 or newer. The support for ARCv2 [1] has been added since that version. [1] https://sourceware.org/git/?p=elfutils.git;a=commit;h=de3d46b3e7 Setup: pahole ------------- The line below in linux/scripts/Makefile.btf must be commented out: pahole-flags-$(call test-ge, $(pahole-ver), 121) += --btf_gen_floats Or else, the build will fail: $ make V=1 ... BTF .btf.vmlinux.bin.o pahole -J --btf_gen_floats \ -j --lang_exclude=rust \ --skip_encoding_btf_inconsistent_proto \ --btf_gen_optimized .tmp_vmlinux.btf Complex, interval and imaginary float types are not supported Encountered error while encoding BTF. ... BTFIDS vmlinux ./tools/bpf/resolve_btfids/resolve_btfids vmlinux libbpf: failed to find '.BTF' ELF section in vmlinux FAILED: load BTF from vmlinux: No data available This is due to the fact that the ARC toolchains generate "complex float" DIE entries in libgcc and at the moment, pahole can't handle such entries. Running the tests ----------------- host$ scp /bld/linux/lib/test_bpf.ko arc: arc # sysctl net.core.bpf_jit_enable=1 arc # insmod test_bpf.ko test_suite=test_bpf ... test_bpf: #1048 Staggered jumps: JMP32_JSLE_X jited:1 697811 PASS test_bpf: Summary: 863 PASSED, 186 FAILED, [851/851 JIT'ed] Acknowledgments --------------- - Claudiu Zissulescu for his unwavering support - Yuriy Kolerov for testing and troubleshooting - Vladimir Isaev for the pahole workaround - Sergey Matyukevich for paving the road by adding the interpreter support Signed-off-by: Shahab Vahedi <shahab@synopsys.com> Link: https://lore.kernel.org/r/20240430145604.38592-1-list+bpf@vahedi.org Signed-off-by: Alexei Starovoitov <ast@kernel.org>

…low() There are code paths from which the function is called without holding the RCU read lock, resulting in a suspicious RCU usage warning [1]. Fix by using l3mdev_master_upper_ifindex_by_index() which will acquire the RCU read lock before calling l3mdev_master_upper_ifindex_by_index_rcu(). [1] WARNING: suspicious RCU usage 6.12.0-rc3-custom-gac8f72681cf2 #141 Not tainted ----------------------------- net/core/dev.c:876 RCU-list traversed in non-reader section!! other info that might help us debug this: rcu_scheduler_active = 2, debug_locks = 1 1 lock held by ip/361: #0: ffffffff86fc7cb0 (rtnl_mutex){+.+.}-{3:3}, at: rtnetlink_rcv_msg+0x377/0xf60 stack backtrace: CPU: 3 UID: 0 PID: 361 Comm: ip Not tainted 6.12.0-rc3-custom-gac8f72681cf2 #141 Hardware name: Bochs Bochs, BIOS Bochs 01/01/2011 Call Trace: <TASK> dump_stack_lvl+0xba/0x110 lockdep_rcu_suspicious.cold+0x4f/0xd6 dev_get_by_index_rcu+0x1d3/0x210 l3mdev_master_upper_ifindex_by_index_rcu+0x2b/0xf0 ip_tunnel_bind_dev+0x72f/0xa00 ip_tunnel_newlink+0x368/0x7a0 ipgre_newlink+0x14c/0x170 __rtnl_newlink+0x1173/0x19c0 rtnl_newlink+0x6c/0xa0 rtnetlink_rcv_msg+0x3cc/0xf60 netlink_rcv_skb+0x171/0x450 netlink_unicast+0x539/0x7f0 netlink_sendmsg+0x8c1/0xd80 ____sys_sendmsg+0x8f9/0xc20 ___sys_sendmsg+0x197/0x1e0 __sys_sendmsg+0x122/0x1f0 do_syscall_64+0xbb/0x1d0 entry_SYSCALL_64_after_hwframe+0x77/0x7f Fixes: db53cd3 ("net: Handle l3mdev in ip_tunnel_init_flow") Signed-off-by: Ido Schimmel <idosch@nvidia.com> Reviewed-by: David Ahern <dsahern@kernel.org> Link: https://patch.msgid.link/20241022063822.462057-1-idosch@nvidia.com Signed-off-by: Jakub Kicinski <kuba@kernel.org>

The last reference for `cache_head` can be reduced to zero in `c_show` and `e_show`(using `rcu_read_lock` and `rcu_read_unlock`). Consequently, `svc_export_put` and `expkey_put` will be invoked, leading to two issues: 1. The `svc_export_put` will directly free ex_uuid. However, `e_show`/`c_show` will access `ex_uuid` after `cache_put`, which can trigger a use-after-free issue, shown below. ================================================================== BUG: KASAN: slab-use-after-free in svc_export_show+0x362/0x430 [nfsd] Read of size 1 at addr ff11000010fdc120 by task cat/870 CPU: 1 UID: 0 PID: 870 Comm: cat Not tainted 6.12.0-rc3+ #1 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.16.1-2.fc37 04/01/2014 Call Trace: <TASK> dump_stack_lvl+0x53/0x70 print_address_description.constprop.0+0x2c/0x3a0 print_report+0xb9/0x280 kasan_report+0xae/0xe0 svc_export_show+0x362/0x430 [nfsd] c_show+0x161/0x390 [sunrpc] seq_read_iter+0x589/0x770 seq_read+0x1e5/0x270 proc_reg_read+0xe1/0x140 vfs_read+0x125/0x530 ksys_read+0xc1/0x160 do_syscall_64+0x5f/0x170 entry_SYSCALL_64_after_hwframe+0x76/0x7e Allocated by task 830: kasan_save_stack+0x20/0x40 kasan_save_track+0x14/0x30 __kasan_kmalloc+0x8f/0xa0 __kmalloc_node_track_caller_noprof+0x1bc/0x400 kmemdup_noprof+0x22/0x50 svc_export_parse+0x8a9/0xb80 [nfsd] cache_do_downcall+0x71/0xa0 [sunrpc] cache_write_procfs+0x8e/0xd0 [sunrpc] proc_reg_write+0xe1/0x140 vfs_write+0x1a5/0x6d0 ksys_write+0xc1/0x160 do_syscall_64+0x5f/0x170 entry_SYSCALL_64_after_hwframe+0x76/0x7e Freed by task 868: kasan_save_stack+0x20/0x40 kasan_save_track+0x14/0x30 kasan_save_free_info+0x3b/0x60 __kasan_slab_free+0x37/0x50 kfree+0xf3/0x3e0 svc_export_put+0x87/0xb0 [nfsd] cache_purge+0x17f/0x1f0 [sunrpc] nfsd_destroy_serv+0x226/0x2d0 [nfsd] nfsd_svc+0x125/0x1e0 [nfsd] write_threads+0x16a/0x2a0 [nfsd] nfsctl_transaction_write+0x74/0xa0 [nfsd] vfs_write+0x1a5/0x6d0 ksys_write+0xc1/0x160 do_syscall_64+0x5f/0x170 entry_SYSCALL_64_after_hwframe+0x76/0x7e 2. We cannot sleep while using `rcu_read_lock`/`rcu_read_unlock`. However, `svc_export_put`/`expkey_put` will call path_put, which subsequently triggers a sleeping operation due to the following `dput`. ============================= WARNING: suspicious RCU usage 5.10.0-dirty #141 Not tainted ----------------------------- ... Call Trace: dump_stack+0x9a/0xd0 ___might_sleep+0x231/0x240 dput+0x39/0x600 path_put+0x1b/0x30 svc_export_put+0x17/0x80 e_show+0x1c9/0x200 seq_read_iter+0x63f/0x7c0 seq_read+0x226/0x2d0 vfs_read+0x113/0x2c0 ksys_read+0xc9/0x170 do_syscall_64+0x33/0x40 entry_SYSCALL_64_after_hwframe+0x67/0xd1 Fix these issues by using `rcu_work` to help release `svc_expkey`/`svc_export`. This approach allows for an asynchronous context to invoke `path_put` and also facilitates the freeing of `uuid/exp/key` after an RCU grace period. Fixes: 9ceddd9 ("knfsd: Allow lockless lookups of the exports") Signed-off-by: Yang Erkun <yangerkun@huawei.com> Reviewed-by: Jeff Layton <jlayton@kernel.org> Signed-off-by: Chuck Lever <chuck.lever@oracle.com>

matttbe added bug enhancement and removed bug labels Jan 20, 2021

matttbe moved this to Needs triage in MPTCP Upstream: Future Feb 22, 2023

matttbe added this to MPTCP Upstream: Future Feb 22, 2023

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

avoid acquiring mptcp_data_lock() twice in the receive path #141

avoid acquiring mptcp_data_lock() twice in the receive path #141

pabeni commented Jan 20, 2021 •

edited

Loading

avoid acquiring mptcp_data_lock() twice in the receive path #141

avoid acquiring mptcp_data_lock() twice in the receive path #141

Comments

pabeni commented Jan 20, 2021 • edited Loading

pabeni commented Jan 20, 2021 •

edited

Loading