- 05 Mar, 2019 1 commit
-
-
Slavomir Kaslev authored
The current implementation of splice() and tee() ignores O_NONBLOCK set on pipe file descriptors and checks only the SPLICE_F_NONBLOCK flag for blocking on pipe arguments. This is inconsistent since splice()-ing from/to non-pipe file descriptors does take O_NONBLOCK into consideration. Fix this by promoting O_NONBLOCK, when set on a pipe, to SPLICE_F_NONBLOCK. Some context for how the current implementation of splice() leads to inconsistent behavior. In the ongoing work[1] to add VM tracing capability to trace-cmd we stream tracing data over named FIFOs or vsockets from guests back to the host. When we receive SIGINT from user to stop tracing, we set O_NONBLOCK on the input file descriptor and set SPLICE_F_NONBLOCK for the next call to splice(). If splice() was blocked waiting on data from the input FIFO, after SIGINT splice() restarts with the same arguments (no SPLICE_F_NONBLOCK) and blocks again instead of returning -EAGAIN when no data is available. This differs from the splice() behavior when reading from a vsocket or when we're doing a traditional read()/write() loop (trace-cmd's --nosplice argument). With this patch applied we get the same behavior in all situations after setting O_NONBLOCK which also matches the behavior of doing a read()/write() loop instead of splice(). This change does have potential of breaking users who don't expect EAGAIN from splice() when SPLICE_F_NONBLOCK is not set. OTOH programs that set O_NONBLOCK and don't anticipate EAGAIN are arguably buggy[2]. [1] https://github.com/skaslev/trace-cmd/tree/vsock [2] https://github.com/torvalds/linux/blob/d47e3da1759230e394096fd742aad423c291ba48/fs/read_write.c#L1425Signed-off-by:
Slavomir Kaslev <kaslevs@vmware.com> Reviewed-by:
Steven Rostedt (VMware) <rostedt@goodmis.org> Signed-off-by:
Linus Torvalds <torvalds@linux-foundation.org>
-
- 04 Mar, 2019 4 commits
-
-
git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfsLinus Torvalds authored
Pull vfs fixes from Al Viro: "Assorted fixes that sat in -next for a while, all over the place" * 'fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs: aio: Fix locking in aio_poll() exec: Fix mem leak in kernel_read_file copy_mount_string: Limit string length to PATH_MAX cgroup: saner refcounting for cgroup_root fix cgroup_do_mount() handling of failure exits
-
Linus Torvalds authored
Every in-kernel use of this function defined it to KERNEL_DS (either as an actual define, or as an inline function). It's an entirely historical artifact, and long long long ago used to actually read the segment selector valueof '%ds' on x86. Which in the kernel is always KERNEL_DS. Inspired by a patch from Jann Horn that just did this for a very small subset of users (the ones in fs/), along with Al who suggested a script. I then just took it to the logical extreme and removed all the remaining gunk. Roughly scripted with git grep -l '(get_ds())' -- :^tools/ | xargs sed -i 's/(get_ds())/(KERNEL_DS)/' git grep -lw 'get_ds' -- :^tools/ | xargs sed -i '/^#define get_ds()/d' plus manual fixups to remove a few unusual usage patterns, the couple of inline function cases and to fix up a comment that had become stale. The 'get_ds()' function remains in an x86 kvm selftest, since in user space it actually does something relevant. Inspired-by:
Jann Horn <jannh@google.com> Inspired-by:
Al Viro <viro@zeniv.linux.org.uk> Signed-off-by:
Linus Torvalds <torvalds@linux-foundation.org>
-
Linus Torvalds authored
Al Viro root-caused a race where the IOCB_CMD_POLL handling of fget/fput() could cause us to access the file pointer after it had already been freed: "In more details - normally IOCB_CMD_POLL handling looks so: 1) io_submit(2) allocates aio_kiocb instance and passes it to aio_poll() 2) aio_poll() resolves the descriptor to struct file by req->file = fget(iocb->aio_fildes) 3) aio_poll() sets ->woken to false and raises ->ki_refcnt of that aio_kiocb to 2 (bumps by 1, that is). 4) aio_poll() calls vfs_poll(). After sanity checks (basically, "poll_wait() had been called and only once") it locks the queue. That's what the extra reference to iocb had been for - we know we can safely access it. 5) With queue locked, we check if ->woken has already been set to true (by aio_poll_wake()) and, if it had been, we unlock the queue, drop a reference to aio_kiocb and bugger off - at that point it's a responsibility to aio_poll_wake() and the stuff called/scheduled by it. That code will drop the reference to file in req->file, along with the other reference to our aio_kiocb. 6) otherwise, we see whether we need to wait. If we do, we unlock the queue, drop one reference to aio_kiocb and go away - eventual wakeup (or cancel) will deal with the reference to file and with the other reference to aio_kiocb 7) otherwise we remove ourselves from waitqueue (still under the queue lock), so that wakeup won't get us. No async activity will be happening, so we can safely drop req->file and iocb ourselves. If wakeup happens while we are in vfs_poll(), we are fine - aio_kiocb won't get freed under us, so we can do all the checks and locking safely. And we don't touch ->file if we detect that case. However, vfs_poll() most certainly *does* touch the file it had been given. So wakeup coming while we are still in ->poll() might end up doing fput() on that file. That case is not too rare, and usually we are saved by the still present reference from descriptor table - that fput() is not the final one. But if another thread closes that descriptor right after our fget() and wakeup does happen before ->poll() returns, we are in trouble - final fput() done while we are in the middle of a method: Al also wrote a patch to take an extra reference to the file descriptor to fix this, but I instead suggested we just streamline the whole file pointer handling by submit_io() so that the generic aio submission code simply keeps the file pointer around until the aio has completed. Fixes: bfe4037e ("aio: implement IOCB_CMD_POLL") Acked-by:
Al Viro <viro@zeniv.linux.org.uk> Reported-by: syzbot+503d4cc169fcec1cb18c@syzkaller.appspotmail.com Signed-off-by:
Linus Torvalds <torvalds@linux-foundation.org>
-
Linus Torvalds authored
This adds a warning (once) for any kernel dereference that has a user exception handler, but accesses a non-canonical address. It basically is a simpler - and more limited - version of commit 9da3f2b7 ("x86/fault: BUG() when uaccess helpers fault on kernel addresses") that got reverted. Note that unlike that original commit, this only causes a warning, because there are real situations where we currently can do this (notably speculative argument fetching for uprobes etc). Also, unlike that original commit, this _only_ triggers for #GP accesses, so the cases of valid kernel pointers that cross into a non-mapped page aren't affected. The intent of this is two-fold: - the uprobe/tracing accesses really do need to be more careful. In particular, from a portability standpoint it's just wrong to think that "a pointer is a pointer", and use the same logic for any random pointer value you find on the stack. It may _work_ on x86-64, but it doesn't necessarily work on other architectures (where the same pointer value can be either a kernel pointer _or_ a user pointer, and you really need to be much more careful in how you try to access it) The warning can hopefully end up being a reminder that just any random pointer access won't do. - Kees in particular wanted a way to actually report invalid uses of wild pointers to user space accessors, instead of just silently failing them. Automated fuzzers want a way to get reports if the kernel ever uses invalid values that the fuzzer fed it. The non-canonical address range is a fair chunk of the address space, and with this you can teach syzkaller to feed in invalid pointer values and find cases where we do not properly validate user addresses (possibly due to bad uses of "set_fs()"). Acked-by:
Kees Cook <keescook@chromium.org> Cc: Jann Horn <jannh@google.com> Cc: Andy Lutomirski <luto@kernel.org> Cc: Borislav Petkov <bp@alien8.de> Cc: Peter Zijlstra <peterz@infradead.org> Signed-off-by:
Linus Torvalds <torvalds@linux-foundation.org>
-
- 03 Mar, 2019 2 commits
-
-
Linus Torvalds authored
-
git://git.kernel.org/pub/scm/linux/kernel/git/soc/socLinus Torvalds authored
Pull ARM SoC fixes from Arnd Bergmann: "One more set of simple ARM platform fixes: - A boot regression on qualcomm msm8998 - Gemini display controllers got turned off by accident - incorrect reference counting in optee" * tag 'armsoc-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/soc/soc: tee: optee: add missing of_node_put after of_device_is_available arm64: dts: qcom: msm8998: Extend TZ reserved memory area ARM: dts: gemini: Re-enable display controller
-
- 02 Mar, 2019 11 commits
-
-
git://git.kernel.org/pub/scm/linux/kernel/git/tip/tipLinus Torvalds authored
Pull x86 fixes from Thomas Gleixner: "Two last minute fixes: - Prevent value evaluation via functions happening in the user access enabled region of __put_user() (put another way: make sure to evaluate the value to be stored in user space _before_ enabling user space accesses) - Correct the definition of a Hyper-V hypercall constant" * 'x86-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: x86/hyper-v: Fix definition of HV_MAX_FLUSH_REP_COUNT x86/uaccess: Don't leak the AC flag into __put_user() value evaluation
-
git://git.kernel.org/pub/scm/linux/kernel/git/jejb/scsiLinus Torvalds authored
Pull SCSI fixes from James Bottomley: "Nine small fixes. The resume fix is a cosmetic removal of a warning with an incorrect condition causing it to alarm people wrongly. The other eight patches correct a thinko in Christoph Hellwig's DMA conversion series. Without it all these drivers end up with 32 bit DMA masks meaning they bounce any page over 4GB before sending it to the controller. Nowadays, even laptops mostly have memory above 4GB, so this can lead to significant performance degradation with all the bouncing" * tag 'scsi-fixes' of git://git.kernel.org/pub/scm/linux/kernel/git/jejb/scsi: scsi: core: Avoid that system resume triggers a kernel warning scsi: hptiop: fix calls to dma_set_mask() scsi: hisi_sas: fix calls to dma_set_mask_and_coherent() scsi: csiostor: fix calls to dma_set_mask_and_coherent() scsi: bfa: fix calls to dma_set_mask_and_coherent() scsi: aic94xx: fix calls to dma_set_mask_and_coherent() scsi: 3w-sas: fix calls to dma_set_mask_and_coherent() scsi: 3w-9xxx: fix calls to dma_set_mask_and_coherent() scsi: lpfc: fix calls to dma_set_mask_and_coherent()
-
git://git.kernel.org/pub/scm/linux/kernel/git/davem/netLinus Torvalds authored
Pull networking fixes from David Miller: 1) Fix refcount leak in act_ipt during replace, from Davide Caratti. 2) Set task state properly in tun during blocking reads, from Timur Celik. 3) Leaked reference in DSA, from Wen Yang. 4) NULL deref in act_tunnel_key, from Vlad Buslov. 5) cipso_v4_erro can reference the skb IPCB in inappropriate contexts thus referencing garbage, from Nazarov Sergey. 6) Don't accept RTA_VIA and RTA_GATEWAY in contexts where those attributes make no sense. 7) Fix hung sendto in tipc, from Tung Nguyen. 8) Out-of-bounds access in netlabel, from Paul Moore. 9) Grant reference leak in xen-netback, from Igor Druzhinin. 10) Fix tx stalls with lan743x, from Bryan Whitehead. 11) Fix interrupt storm with mv88e6xxx, from Hein Kallweit. 12) Memory leak in sit on device registry failure, from Mao Wenan. * git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (44 commits) net: sit: fix memory leak in sit_init_net() net: dsa: mv88e6xxx: Fix statistics on mv88e6161 geneve: correctly handle ipv6.disable module parameter net: dsa: mv88e6xxx: prevent interrupt storm caused by mv88e6390x_port_set_cmode bpf: fix sanitation rewrite in case of non-pointers ipv4: Add ICMPv6 support when parse route ipproto MIPS: eBPF: Fix icache flush end address lan743x: Fix TX Stall Issue net: phy: phylink: fix uninitialized variable in phylink_get_mac_state net: aquantia: regression on cpus with high cores: set mode with 8 queues selftests: fixes for UDP GRO bpf: drop refcount if bpf_map_new_fd() fails in map_create() net: dsa: mv88e6xxx: power serdes on/off for 10G interfaces on 6390X net: dsa: mv88e6xxx: Fix u64 statistics xen-netback: don't populate the hash cache on XenBus disconnect xen-netback: fix occasional leak of grant ref mappings under memory pressure sctp: chunk.c: correct format string for size_t in printk net: netem: fix skb length BUG_ON in __skb_to_sgvec netlabel: fix out-of-bounds memory accesses ipv4: Pass original device to ip_rcv_finish_core ...
-
git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6Linus Torvalds authored
Pull more crypto fixes from Herbert Xu: "This fixes a couple of issues in arm64/chacha that was introduced in 5.0" * 'linus' of git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6: crypto: arm64/chacha - fix hchacha_block_neon() for big endian crypto: arm64/chacha - fix chacha_4block_xor_neon() for big endian
-
Mao Wenan authored
If register_netdev() is failed to register sitn->fb_tunnel_dev, it will go to err_reg_dev and forget to free netdev(sitn->fb_tunnel_dev). BUG: memory leak unreferenced object 0xffff888378daad00 (size 512): comm "syz-executor.1", pid 4006, jiffies 4295121142 (age 16.115s) hex dump (first 32 bytes): 00 e6 ed c0 83 88 ff ff 00 00 00 00 00 00 00 00 ................ 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 ................ backtrace: [<00000000d6dcb63e>] kvmalloc include/linux/mm.h:577 [inline] [<00000000d6dcb63e>] kvzalloc include/linux/mm.h:585 [inline] [<00000000d6dcb63e>] netif_alloc_netdev_queues net/core/dev.c:8380 [inline] [<00000000d6dcb63e>] alloc_netdev_mqs+0x600/0xcc0 net/core/dev.c:8970 [<00000000867e172f>] sit_init_net+0x295/0xa40 net/ipv6/sit.c:1848 [<00000000871019fa>] ops_init+0xad/0x3e0 net/core/net_namespace.c:129 [<00000000319507f6>] setup_net+0x2ba/0x690 net/core/net_namespace.c:314 [<0000000087db4f96>] copy_net_ns+0x1dc/0x330 net/core/net_namespace.c:437 [<0000000057efc651>] create_new_namespaces+0x382/0x730 kernel/nsproxy.c:107 [<00000000676f83de>] copy_namespaces+0x2ed/0x3d0 kernel/nsproxy.c:165 [<0000000030b74bac>] copy_process.part.27+0x231e/0x6db0 kernel/fork.c:1919 [<00000000fff78746>] copy_process kernel/fork.c:1713 [inline] [<00000000fff78746>] _do_fork+0x1bc/0xe90 kernel/fork.c:2224 [<000000001c2e0d1c>] do_syscall_64+0xc8/0x580 arch/x86/entry/common.c:290 [<00000000ec48bd44>] entry_SYSCALL_64_after_hwframe+0x49/0xbe [<0000000039acff8a>] 0xffffffffffffffff Signed-off-by:
Mao Wenan <maowenan@huawei.com> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
Andrew Lunn authored
Despite what the datesheet says, the silicon implements the older way of snapshoting the statistics. Change the op. Reported-by: Chris.Healy@zii.aero Tested-by: Chris.Healy@zii.aero Fixes: 0ac64c39 ("net: dsa: mv88e6xxx: mv88e6161 uses mv88e6320 stats snapshot") Signed-off-by:
Andrew Lunn <andrew@lunn.ch> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
Jiri Benc authored
When IPv6 is compiled but disabled at runtime, geneve_sock_add returns -EAFNOSUPPORT. For metadata based tunnels, this causes failure of the whole operation of bringing up the tunnel. Ignore failure of IPv6 socket creation for metadata based tunnels caused by IPv6 not being available. This is the same fix as what commit d074bf96 ("vxlan: correctly handle ipv6.disable module parameter") is doing for vxlan. Note there's also commit c0a47e44 ("geneve: should not call rt6_lookup() when ipv6 was disabled") which fixes a similar issue but for regular tunnels, while this patch is needed for metadata based tunnels. Signed-off-by:
Jiri Benc <jbenc@redhat.com> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpfDavid S. Miller authored
Alexei Starovoitov says: ==================== pull-request: bpf 2019-03-01 The following pull-request contains BPF updates for your *net* tree. The main changes are: 1) fix sanitation rewrite, from Daniel. 2) fix error path on map_new_fd, from Peng. 3) fix icache flush address, from Paul. ==================== Signed-off-by:
David S. Miller <davem@davemloft.net>
-
Heiner Kallweit authored
When debugging another issue I faced an interrupt storm in this driver (88E6390, port 9 in SGMII mode), consisting of alternating link-up / link-down interrupts. Analysis showed that the driver wanted to set a cmode that was set already. But so far mv88e6390x_port_set_cmode() doesn't check this and powers down SERDES, what causes the link to break, and eventually results in the described interrupt storm. Fix this by checking whether the cmode actually changes. We want that the very first call to mv88e6390x_port_set_cmode() always configures the registers, therefore initialize port.cmode with a value that is different from any supported cmode value. We have to take care that we only init the ports cmode once chip->info->num_ports is set. v2: - add small helper and init the number of actual ports only Fixes: 364e9d77 ("net: dsa: mv88e6xxx: Power on/off SERDES on cmode change") Signed-off-by:
Heiner Kallweit <hkallweit1@gmail.com> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
Daniel Borkmann authored
Marek reported that he saw an issue with the below snippet in that timing measurements where off when loaded as unpriv while results were reasonable when loaded as privileged: [...] uint64_t a = bpf_ktime_get_ns(); uint64_t b = bpf_ktime_get_ns(); uint64_t delta = b - a; if ((int64_t)delta > 0) { [...] Turns out there is a bug where a corner case is missing in the fix d3bd7413 ("bpf: fix sanitation of alu op with pointer / scalar type from different paths"), namely fixup_bpf_calls() only checks whether aux has a non-zero alu_state, but it also needs to test for the case of BPF_ALU_NON_POINTER since in both occasions we need to skip the masking rewrite (as there is nothing to mask). Fixes: d3bd7413 ("bpf: fix sanitation of alu op with pointer / scalar type from different paths") Reported-by:
Marek Majkowski <marek@cloudflare.com> Reported-by:
Arthur Fabre <afabre@cloudflare.com> Signed-off-by:
Daniel Borkmann <daniel@iogearbox.net> Link: https://lore.kernel.org/netdev/CAJPywTJqP34cK20iLM5YmUMz9KXQOdu1-+BZrGMAGgLuBWz7fg@mail.gmail.com/T/Acked-by:
Song Liu <songliubraving@fb.com> Signed-off-by:
Alexei Starovoitov <ast@kernel.org>
-
Hangbin Liu authored
For ip rules, we need to use 'ipproto ipv6-icmp' to match ICMPv6 headers. But for ip -6 route, currently we only support tcp, udp and icmp. Add ICMPv6 support so we can match ipv6-icmp rules for route lookup. v2: As David Ahern and Sabrina Dubroca suggested, Add an argument to rtm_getroute_parse_ip_proto() to handle ICMP/ICMPv6 with different family. Reported-by:
Jianlin Shi <jishi@redhat.com> Fixes: eacb9384 ("ipv6: support sport, dport and ip_proto in RTM_GETROUTE") Signed-off-by:
Hangbin Liu <liuhangbin@gmail.com> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
- 01 Mar, 2019 13 commits
-
-
Paul Burton authored
The MIPS eBPF JIT calls flush_icache_range() in order to ensure the icache observes the code that we just wrote. Unfortunately it gets the end address calculation wrong due to some bad pointer arithmetic. The struct jit_ctx target field is of type pointer to u32, and as such adding one to it will increment the address being pointed to by 4 bytes. Therefore in order to find the address of the end of the code we simply need to add the number of 4 byte instructions emitted, but we mistakenly add the number of instructions multiplied by 4. This results in the call to flush_icache_range() operating on a memory region 4x larger than intended, which is always wasteful and can cause crashes if we overrun into an unmapped page. Fix this by correcting the pointer arithmetic to remove the bogus multiplication, and use braces to remove the need for a set of brackets whilst also making it obvious that the target field is a pointer. Signed-off-by:
Paul Burton <paul.burton@mips.com> Fixes: b6bd53f9 ("MIPS: Add missing file for eBPF JIT.") Cc: Alexei Starovoitov <ast@kernel.org> Cc: Daniel Borkmann <daniel@iogearbox.net> Cc: Martin KaFai Lau <kafai@fb.com> Cc: Song Liu <songliubraving@fb.com> Cc: Yonghong Song <yhs@fb.com> Cc: netdev@vger.kernel.org Cc: bpf@vger.kernel.org Cc: linux-mips@vger.kernel.org Cc: stable@vger.kernel.org # v4.13+ Signed-off-by:
Daniel Borkmann <daniel@iogearbox.net>
-
Bryan Whitehead authored
It has been observed that tx queue stalls while downloading from certain web sites (example www.speedtest.net) The cause has been tracked down to a corner case where dma descriptors where not setup properly. And there for a tx completion interrupt was not signaled. This fix corrects the problem by properly marking the end of a multi descriptor transmission. Fixes: 23f0703c ("lan743x: Add main source files for new lan743x driver") Signed-off-by:
Bryan Whitehead <Bryan.Whitehead@microchip.com> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
Heiner Kallweit authored
When debugging an issue I found implausible values in state->pause. Reason in that state->pause isn't initialized and later only single bits are changed. Also the struct itself isn't initialized in phylink_resolve(). So better initialize state->pause and other not yet initialized fields. v2: - use right function name in subject v3: - initialize additional fields Fixes: 9525ae83 ("phylink: add phylink infrastructure") Signed-off-by:
Heiner Kallweit <hkallweit1@gmail.com> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
Dmitry Bogdanov authored
Recently the maximum number of queues was increased up to 8, but NIC was not fully configured for 8 queues. In setups with more than 4 CPU cores parts of TX traffic gets lost if the kernel routes it to queues 4th-8th. This patch sets a tx hw traffic mode with 8 queues. Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=202651 Fixes: 71a963cf ("net: aquantia: increase max number of hw queues") Reported-by:
Nicholas Johnson <nicholas.johnson@outlook.com.au> Signed-off-by:
Dmitry Bogdanov <dmitry.bogdanov@aquantia.com> Signed-off-by:
Igor Russkikh <igor.russkikh@aquantia.com> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
Paolo Abeni authored
The current implementation for UDP GRO tests is racy: the receiver may flush the RX queue while the sending is still transmitting and incorrectly report RX errors, with a wrong number of packet received. Add explicit timeouts to the receiver for both connection activation (first packet received for UDP) and reception completion, so that in the above critical scenario the receiver will wait for the transfer completion. Fixes: 3327a9c4 ("selftests: add functionals test for UDP GRO") Signed-off-by:
Paolo Abeni <pabeni@redhat.com> Acked-by:
Willem de Bruijn <willemb@google.com> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommuLinus Torvalds authored
Pull IOMMU fix from Joerg Roedel: "One important fix for a memory corruption issue in the Intel VT-d driver that triggers on hardware with deep PCI hierarchies" * tag 'iommu-fix-v5.0-rc8' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu: iommu/dmar: Fix buffer overflow during PCI bus notification
-
Linus Torvalds authored
Merge misc fixes from Andrew Morton: "2 fixes" * emailed patches from Andrew Morton <akpm@linux-foundation.org>: hugetlbfs: fix races and page leaks during migration kasan: turn off asan-stack for clang-8 and earlier
-
Mike Kravetz authored
hugetlb pages should only be migrated if they are 'active'. The routines set/clear_page_huge_active() modify the active state of hugetlb pages. When a new hugetlb page is allocated at fault time, set_page_huge_active is called before the page is locked. Therefore, another thread could race and migrate the page while it is being added to page table by the fault code. This race is somewhat hard to trigger, but can be seen by strategically adding udelay to simulate worst case scheduling behavior. Depending on 'how' the code races, various BUG()s could be triggered. To address this issue, simply delay the set_page_huge_active call until after the page is successfully added to the page table. Hugetlb pages can also be leaked at migration time if the pages are associated with a file in an explicitly mounted hugetlbfs filesystem. For example, consider a two node system with 4GB worth of huge pages available. A program mmaps a 2G file in a hugetlbfs filesystem. It then migrates the pages associated with the file from one node to another. When the program exits, huge page counts are as follows: node0 1024 free_hugepages 1024 nr_hugepages node1 0 free_hugepages 1024 nr_hugepages Filesystem Size Used Avail Use% Mounted on nodev 4.0G 2.0G 2.0G 50% /var/opt/hugepool That is as expected. 2G of huge pages are taken from the free_hugepages counts, and 2G is the size of the file in the explicitly mounted filesystem. If the file is then removed, the counts become: node0 1024 free_hugepages 1024 nr_hugepages node1 1024 free_hugepages 1024 nr_hugepages Filesystem Size Used Avail Use% Mounted on nodev 4.0G 2.0G 2.0G 50% /var/opt/hugepool Note that the filesystem still shows 2G of pages used, while there actually are no huge pages in use. The only way to 'fix' the filesystem accounting is to unmount the filesystem If a hugetlb page is associated with an explicitly mounted filesystem, this information in contained in the page_private field. At migration time, this information is not preserved. To fix, simply transfer page_private from old to new page at migration time if necessary. There is a related race with removing a huge page from a file and migration. When a huge page is removed from the pagecache, the page_mapping() field is cleared, yet page_private remains set until the page is actually freed by free_huge_page(). A page could be migrated while in this state. However, since page_mapping() is not set the hugetlbfs specific routine to transfer page_private is not called and we leak the page count in the filesystem. To fix that, check for this condition before migrating a huge page. If the condition is detected, return EBUSY for the page. Link: http://lkml.kernel.org/r/74510272-7319-7372-9ea6-ec914734c179@oracle.com Link: http://lkml.kernel.org/r/20190212221400.3512-1-mike.kravetz@oracle.com Fixes: bcc54222 ("mm: hugetlb: introduce page_huge_active") Signed-off-by:
Mike Kravetz <mike.kravetz@oracle.com> Reviewed-by:
Naoya Horiguchi <n-horiguchi@ah.jp.nec.com> Cc: Michal Hocko <mhocko@kernel.org> Cc: Andrea Arcangeli <aarcange@redhat.com> Cc: "Kirill A . Shutemov" <kirill.shutemov@linux.intel.com> Cc: Mel Gorman <mgorman@techsingularity.net> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: <stable@vger.kernel.org> [mike.kravetz@oracle.com: v2] Link: http://lkml.kernel.org/r/7534d322-d782-8ac6-1c8d-a8dc380eb3ab@oracle.com [mike.kravetz@oracle.com: update comment and changelog] Link: http://lkml.kernel.org/r/420bcfd6-158b-38e4-98da-26d0cd85bd01@oracle.comSigned-off-by:
Andrew Morton <akpm@linux-foundation.org> Signed-off-by:
Linus Torvalds <torvalds@linux-foundation.org>
-
Arnd Bergmann authored
Building an arm64 allmodconfig kernel with clang results in over 140 warnings about overly large stack frames, the worst ones being: drivers/gpu/drm/panel/panel-sitronix-st7789v.c:196:12: error: stack frame size of 20224 bytes in function 'st7789v_prepare' drivers/video/fbdev/omap2/omapfb/displays/panel-tpo-td028ttec1.c:196:12: error: stack frame size of 13120 bytes in function 'td028ttec1_panel_enable' drivers/usb/host/max3421-hcd.c:1395:1: error: stack frame size of 10048 bytes in function 'max3421_spi_thread' drivers/net/wan/slic_ds26522.c:209:12: error: stack frame size of 9664 bytes in function 'slic_ds26522_probe' drivers/crypto/ccp/ccp-ops.c:2434:5: error: stack frame size of 8832 bytes in function 'ccp_run_cmd' drivers/media/dvb-frontends/stv0367.c:1005:12: error: stack frame size of 7840 bytes in function 'stv0367ter_algo' None of these happen with gcc today, and almost all of these are the result of a single known issue in llvm. Hopefully it will eventually get fixed with the clang-9 release. In the meantime, the best idea I have is to turn off asan-stack for clang-8 and earlier, so we can produce a kernel that is safe to run. I have posted three patches that address the frame overflow warnings that are not addressed by turning off asan-stack, so in combination with this change, we get much closer to a clean allmodconfig build, which in turn is necessary to do meaningful build regression testing. It is still possible to turn on the CONFIG_ASAN_STACK option on all versions of clang, and it's always enabled for gcc, but when CONFIG_COMPILE_TEST is set, the option remains invisible, so allmodconfig and randconfig builds (which are normally done with a forced CONFIG_COMPILE_TEST) will still result in a mostly clean build. Link: http://lkml.kernel.org/r/20190222222950.3997333-1-arnd@arndb.de Link: https://bugs.llvm.org/show_bug.cgi?id=38809Signed-off-by:
Arnd Bergmann <arnd@arndb.de> Reviewed-by:
Qian Cai <cai@lca.pw> Reviewed-by:
Mark Brown <broonie@kernel.org> Acked-by:
Andrey Ryabinin <aryabinin@virtuozzo.com> Cc: Dmitry Vyukov <dvyukov@google.com> Cc: Nick Desaulniers <ndesaulniers@google.com> Cc: Kostya Serebryany <kcc@google.com> Cc: Andrey Konovalov <andreyknvl@google.com> Signed-off-by:
Andrew Morton <akpm@linux-foundation.org> Signed-off-by:
Linus Torvalds <torvalds@linux-foundation.org>
-
git://anongit.freedesktop.org/drm/drmLinus Torvalds authored
Pull drm fixes from Dave Airlie: "Three final fixes, one for a feature that is new in this kernel, one bochs fix for qemu riscv and one atomic modesetting fix. I've left a few of the other late fixes until next as I didn't want to throw in anything that wasn't really necessary" * tag 'drm-fixes-2019-03-01' of git://anongit.freedesktop.org/drm/drm: drm/bochs: Fix the ID mismatch error drm: Block fb changes for async plane updates drm/amd/display: Use vrr friendly pageflip throttling in DC.
-
Peng Sun authored
In bpf/syscall.c, map_create() first set map->usercnt to 1, a file descriptor is supposed to return to userspace. When bpf_map_new_fd() fails, drop the refcount. Fixes: bd5f5f4e ("bpf: Add BPF_MAP_GET_FD_BY_ID") Signed-off-by:
Peng Sun <sironhide0null@gmail.com> Acked-by:
Martin KaFai Lau <kafai@fb.com> Signed-off-by:
Alexei Starovoitov <ast@kernel.org> Signed-off-by:
Daniel Borkmann <daniel@iogearbox.net>
-
Arnd Bergmann authored
Merge tag 'qcom-fixes-for-5.0-rc8' of git://git.kernel.org/pub/scm/linux/kernel/git/agross/linux into arm/fixes Qualcomm ARM64 Fixes for 5.0-rc8 * Fix TZ memory area size to avoid crashes during boot * tag 'qcom-fixes-for-5.0-rc8' of git://git.kernel.org/pub/scm/linux/kernel/git/agross/linux: arm64: dts: qcom: msm8998: Extend TZ reserved memory area
-
Arnd Bergmann authored
Merge tag 'tee-fix-for-v5.0' of https://git.linaro.org/people/jens.wiklander/linux-tee into arm/fixes OP-TEE driver - add missing of_node_put after of_device_is_available * tag 'tee-fix-for-v5.0' of https://git.linaro.org/people/jens.wiklander/linux-tee: tee: optee: add missing of_node_put after of_device_is_available
-
- 28 Feb, 2019 9 commits
-
-
git://git.kernel.org/pub/scm/linux/kernel/git/mips/linuxLinus Torvalds authored
Pull MIPS fixes from Paul Burton: "A few more MIPS fixes: - Fix 16b cmpxchg() operations which could erroneously fail if bits 15:8 of the old value are non-zero. In practice I'm not aware of any actual users of 16b cmpxchg() on MIPS, but this fixes the support for it was was introduced in v4.13. - Provide a struct device to dma_alloc_coherent for Lantiq XWAY systems with a "Voice MIPS Macro Core" (VMMC) device. - Provide DMA masks for BCM63xx ethernet devices, fixing a regression introduced in v4.19. - Fix memblock reservation for the kernel when the system has a non-zero PHYS_OFFSET, correcting the memblock conversion performed in v4.20" * tag 'mips_fixes_5.0_4' of git://git.kernel.org/pub/scm/linux/kernel/git/mips/linux: MIPS: fix memory setup for platforms with PHYS_OFFSET != 0 MIPS: BCM63XX: provide DMA masks for ethernet devices MIPS: lantiq: pass struct device to DMA API functions MIPS: fix truncation in __cmpxchg_small for short values
-
git://git.kernel.org/pub/scm/linux/kernel/git/hubcap/linuxLinus Torvalds authored
Pull orangefs fixlet from Mike Marshall: "Remove two un-needed BUG_ONs" * tag 'for-linus-5.0-ofs1' of git://git.kernel.org/pub/scm/linux/kernel/git/hubcap/linux: orangefs: remove two un-needed BUG_ONs...
-
Maxime Chevallier authored
Upon setting the cmode on 6390 and 6390X, the associated serdes interfaces must be powered off/on. Both 6390X and 6390 share code to do so, but it currently uses the 6390 specific helper mv88e6390_serdes_power() to disable and enable the serdes interface. This call will fail silently on 6390X when trying so set a 10G interface such as XAUI or RXAUI, since mv88e6390_serdes_power() internally grabs the lane number based on modes supported by the 6390, and returns 0 when getting -ENODEV as a lane number. Using mv88e6390x_serdes_power() should be safe here, since we explicitly rule-out all ports but the 9 and 10, and because modes supported by 6390 ports 9 and 10 are a subset of those supported on 6390X. This was tested on 6390X using RXAUI mode. Fixes: 364e9d77 ("net: dsa: mv88e6xxx: Power on/off SERDES on cmode change") Signed-off-by:
Maxime Chevallier <maxime.chevallier@bootlin.com> Reviewed-by:
Andrew Lunn <andrew@lunn.ch> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
Andrew Lunn authored
The switch maintains u64 counters for the number of octets sent and received. These are kept as two u32's which need to be combined. Fix the combing, which wrongly worked on u16's. Fixes: 80c4627b ("dsa: mv88x6xxx: Refactor getting a single statistic") Reported-by:
Chris Healy <Chris.Healy@zii.aero> Signed-off-by:
Andrew Lunn <andrew@lunn.ch> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
Igor Druzhinin authored
Occasionally, during the disconnection procedure on XenBus which includes hash cache deinitialization there might be some packets still in-flight on other processors. Handling of these packets includes hashing and hash cache population that finally results in hash cache data structure corruption. In order to avoid this we prevent hashing of those packets if there are no queues initialized. In that case RCU protection of queues guards the hash cache as well. Signed-off-by:
Igor Druzhinin <igor.druzhinin@citrix.com> Reviewed-by:
Paul Durrant <paul.durrant@citrix.com> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
Igor Druzhinin authored
Zero-copy callback flag is not yet set on frag list skb at the moment xenvif_handle_frag_list() returns -ENOMEM. This eventually results in leaking grant ref mappings since xenvif_zerocopy_callback() is never called for these fragments. Those eventually build up and cause Xen to kill Dom0 as the slots get reused for new mappings: "d0v0 Attempt to implicitly unmap a granted PTE c010000329fce005" That behavior is observed under certain workloads where sudden spikes of page cache writes coexist with active atomic skb allocations from network traffic. Additionally, rework the logic to deal with frag_list deallocation in a single place. Signed-off-by:
Paul Durrant <paul.durrant@citrix.com> Signed-off-by:
Igor Druzhinin <igor.druzhinin@citrix.com> Acked-by:
Wei Liu <wei.liu2@citrix.com> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
Matthias Maennich authored
According to Documentation/core-api/printk-formats.rst, size_t should be printed with %zu, rather than %Zu. In addition, using %Zu triggers a warning on clang (-Wformat-extra-args): net/sctp/chunk.c:196:25: warning: data argument not used by format string [-Wformat-extra-args] __func__, asoc, max_data); ~~~~~~~~~~~~~~~~^~~~~~~~~ ./include/linux/printk.h:440:49: note: expanded from macro 'pr_warn_ratelimited' printk_ratelimited(KERN_WARNING pr_fmt(fmt), ##__VA_ARGS__) ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^~~~~~~~~~~~ ./include/linux/printk.h:424:17: note: expanded from macro 'printk_ratelimited' printk(fmt, ##__VA_ARGS__); \ ~~~ ^ Fixes: 5b5e0928 ("lib/vsprintf.c: remove %Z support") Link: https://github.com/ClangBuiltLinux/linux/issues/378Signed-off-by:
Matthias Maennich <maennich@google.com> Acked-by:
Marcelo Ricardo Leitner <marcelo.leitner@gmail.com> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
Sheng Lan authored
It can be reproduced by following steps: 1. virtio_net NIC is configured with gso/tso on 2. configure nginx as http server with an index file bigger than 1M bytes 3. use tc netem to produce duplicate packets and delay: tc qdisc add dev eth0 root netem delay 100ms 10ms 30% duplicate 90% 4. continually curl the nginx http server to get index file on client 5. BUG_ON is seen quickly [10258690.371129] kernel BUG at net/core/skbuff.c:4028! [10258690.371748] invalid opcode: 0000 [#1] SMP PTI [10258690.372094] CPU: 5 PID: 0 Comm: swapper/5 Tainted: G W 5.0.0-rc6 #2 [10258690.372094] RSP: 0018:ffffa05797b43da0 EFLAGS: 00010202 [10258690.372094] RBP: 00000000000005ea R08: 0000000000000000 R09: 00000000000005ea [10258690.372094] R10: ffffa0579334d800 R11: 00000000000002c0 R12: 0000000000000002 [10258690.372094] R13: 0000000000000000 R14: ffffa05793122900 R15: ffffa0578f7cb028 [10258690.372094] FS: 0000000000000000(0000) GS:ffffa05797b40000(0000) knlGS:0000000000000000 [10258690.372094] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [10258690.372094] CR2: 00007f1a6dc00868 CR3: 000000001000e000 CR4: 00000000000006e0 [10258690.372094] Call Trace: [10258690.372094] <IRQ> [10258690.372094] skb_to_sgvec+0x11/0x40 [10258690.372094] start_xmit+0x38c/0x520 [virtio_net] [10258690.372094] dev_hard_start_xmit+0x9b/0x200 [10258690.372094] sch_direct_xmit+0xff/0x260 [10258690.372094] __qdisc_run+0x15e/0x4e0 [10258690.372094] net_tx_action+0x137/0x210 [10258690.372094] __do_softirq+0xd6/0x2a9 [10258690.372094] irq_exit+0xde/0xf0 [10258690.372094] smp_apic_timer_interrupt+0x74/0x140 [10258690.372094] apic_timer_interrupt+0xf/0x20 [10258690.372094] </IRQ> In __skb_to_sgvec(), the skb->len is not equal to the sum of the skb's linear data size and nonlinear data size, thus BUG_ON triggered. Because the skb is cloned and a part of nonlinear data is split off. Duplicate packet is cloned in netem_enqueue() and may be delayed some time in qdisc. When qdisc len reached the limit and returns NET_XMIT_DROP, the skb will be retransmit later in write queue. the skb will be fragmented by tso_fragment(), the limit size that depends on cwnd and mss decrease, the skb's nonlinear data will be split off. The length of the skb cloned by netem will not be updated. When we use virtio_net NIC and invoke skb_to_sgvec(), the BUG_ON trigger. To fix it, netem returns NET_XMIT_SUCCESS to upper stack when it clones a duplicate packet. Fixes: 35d889d1 ("sch_netem: fix skb leak in netem_enqueue()") Signed-off-by:
Sheng Lan <lansheng@huawei.com> Reported-by:
Qin Ji <jiqin.ji@huawei.com> Suggested-by:
Eric Dumazet <eric.dumazet@gmail.com> Signed-off-by:
Eric Dumazet <edumazet@google.com> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
git://git.kernel.org/pub/scm/linux/kernel/git/ulfh/mmcLinus Torvalds authored
Pull MMC fixes from Ulf Hansson: "MMC core: - Fix NULL ptr crash for a special test case - Align max segment size with logical block size to prevent bugs in v5.1-rc1. MMC host: - cqhci: Minor fixes - tmio: Prevent interrupt storm - tmio: Fixup SD/MMC card initialization - spi: Allow card to be detected during probe - sdhci-esdhc-imx: Fixup fix for ERR004536" * tag 'mmc-v5.0-rc8' of git://git.kernel.org/pub/scm/linux/kernel/git/ulfh/mmc: mmc: sdhci-esdhc-imx: correct the fix of ERR004536 mmc: core: align max segment size with logical block size mmc: cqhci: Fix a tiny potential memory leak on error condition mmc: cqhci: fix space allocated for transfer descriptor mmc: core: Fix NULL ptr crash from mmc_should_fail_request mmc: tmio: fix access width of Block Count Register mmc: tmio_mmc_core: don't claim spurious interrupts mmc: spi: Fix card detection during probe
-