From 653997eeecef95c3ead4fba1b2d27e6a5854d6cd Mon Sep 17 00:00:00 2001 From: Ran Bi Date: Wed, 11 Dec 2019 17:43:54 +0800 Subject: rtc: mt6397: fix alarm register overwrite Alarm registers high byte was reserved for other functions. This add mask in alarm registers operation functions. This also fix error condition in interrupt handler. Fixes: fc2979118f3f ("rtc: mediatek: Add MT6397 RTC driver") Signed-off-by: Ran Bi Signed-off-by: Hsin-Hsiung Wang Link: https://lore.kernel.org/r/1576057435-3561-6-git-send-email-hsin-hsiung.wang@mediatek.com Signed-off-by: Alexandre Belloni --- include/linux/mfd/mt6397/rtc.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mfd/mt6397/rtc.h b/include/linux/mfd/mt6397/rtc.h index f84b9163c0ee..7dfb63b81373 100644 --- a/include/linux/mfd/mt6397/rtc.h +++ b/include/linux/mfd/mt6397/rtc.h @@ -46,6 +46,14 @@ #define RTC_AL_SEC 0x0018 +#define RTC_AL_SEC_MASK 0x003f +#define RTC_AL_MIN_MASK 0x003f +#define RTC_AL_HOU_MASK 0x001f +#define RTC_AL_DOM_MASK 0x001f +#define RTC_AL_DOW_MASK 0x0007 +#define RTC_AL_MTH_MASK 0x000f +#define RTC_AL_YEA_MASK 0x007f + #define RTC_PDN2 0x002e #define RTC_PDN2_PWRON_ALARM BIT(4) -- cgit v1.2.3 From 463f550fb47bede3a5d7d5177f363a6c3b45d50b Mon Sep 17 00:00:00 2001 From: Mathieu Desnoyers Date: Wed, 11 Dec 2019 11:17:12 -0500 Subject: rseq: Unregister rseq for clone CLONE_VM It has been reported by Google that rseq is not behaving properly with respect to clone when CLONE_VM is used without CLONE_THREAD. It keeps the prior thread's rseq TLS registered when the TLS of the thread has moved, so the kernel can corrupt the TLS of the parent. The approach of clearing the per task-struct rseq registration on clone with CLONE_THREAD flag is incomplete. It does not cover the use-case of clone with CLONE_VM set, but without CLONE_THREAD. Here is the rationale for unregistering rseq on clone with CLONE_VM flag set: 1) CLONE_THREAD requires CLONE_SIGHAND, which requires CLONE_VM to be set. Therefore, just checking for CLONE_VM covers all CLONE_THREAD uses. There is no point in checking for both CLONE_THREAD and CLONE_VM, 2) There is the possibility of an unlikely scenario where CLONE_SETTLS is used without CLONE_VM. In order to be an issue, it would require that the rseq TLS is in a shared memory area. I do not plan on adding CLONE_SETTLS to the set of clone flags which unregister RSEQ, because it would require that we also unregister RSEQ on set_thread_area(2) and arch_prctl(2) ARCH_SET_FS for completeness. So rather than doing a partial solution, it appears better to let user-space explicitly perform rseq unregistration across clone if needed in scenarios where CLONE_VM is not set. Signed-off-by: Mathieu Desnoyers Signed-off-by: Peter Zijlstra (Intel) Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Link: https://lkml.kernel.org/r/20191211161713.4490-3-mathieu.desnoyers@efficios.com Signed-off-by: Ingo Molnar --- include/linux/sched.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 467d26046416..716ad1d8d95e 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -1929,11 +1929,11 @@ static inline void rseq_migrate(struct task_struct *t) /* * If parent process has a registered restartable sequences area, the - * child inherits. Only applies when forking a process, not a thread. + * child inherits. Unregister rseq for a clone with CLONE_VM set. */ static inline void rseq_fork(struct task_struct *t, unsigned long clone_flags) { - if (clone_flags & CLONE_THREAD) { + if (clone_flags & CLONE_VM) { t->rseq = NULL; t->rseq_sig = 0; t->rseq_event_mask = 0; -- cgit v1.2.3 From 862dd2a946aa1417f013fb748e2aa0f4349b405b Mon Sep 17 00:00:00 2001 From: Vladimir Oltean Date: Fri, 27 Dec 2019 03:24:17 +0200 Subject: spi: Don't look at TX buffer for PTP system timestamping The API for PTP system timestamping (associating a SPI transaction with the system time at which it was transferred) is flawed: it assumes that the xfer->tx_buf pointer will always be present. This is, of course, not always the case. So introduce a "progress" variable that denotes how many word have been transferred. Fix the Freescale DSPI driver, the only user of the API so far, in the same patch. Fixes: b42faeee718c ("spi: Add a PTP system timestamp to the transfer structure") Fixes: d6b71dfaeeba ("spi: spi-fsl-dspi: Implement the PTP system timestamping for TCFQ mode") Signed-off-by: Vladimir Oltean Link: https://lore.kernel.org/r/20191227012417.1057-1-olteanv@gmail.com Signed-off-by: Mark Brown --- include/linux/spi/spi.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h index 98fe8663033a..3a67a7e45633 100644 --- a/include/linux/spi/spi.h +++ b/include/linux/spi/spi.h @@ -689,10 +689,10 @@ extern void spi_finalize_current_transfer(struct spi_controller *ctlr); /* Helper calls for driver to timestamp transfer */ void spi_take_timestamp_pre(struct spi_controller *ctlr, struct spi_transfer *xfer, - const void *tx, bool irqs_off); + size_t progress, bool irqs_off); void spi_take_timestamp_post(struct spi_controller *ctlr, struct spi_transfer *xfer, - const void *tx, bool irqs_off); + size_t progress, bool irqs_off); /* the spi driver core manages memory for the spi_controller classdev */ extern struct spi_controller *__spi_alloc_controller(struct device *host, -- cgit v1.2.3 From e7153bf70c3496bac00e7e4f395bb8d8394ac0ea Mon Sep 17 00:00:00 2001 From: Oliver Hartkopp Date: Sat, 7 Dec 2019 19:34:18 +0100 Subject: can: can_dropped_invalid_skb(): ensure an initialized headroom in outgoing CAN sk_buffs KMSAN sysbot detected a read access to an untinitialized value in the headroom of an outgoing CAN related sk_buff. When using CAN sockets this area is filled appropriately - but when using a packet socket this initialization is missing. The problematic read access occurs in the CAN receive path which can only be triggered when the sk_buff is sent through a (virtual) CAN interface. So we check in the sending path whether we need to perform the missing initializations. Fixes: d3b58c47d330d ("can: replace timestamp as unique skb attribute") Reported-by: syzbot+b02ff0707a97e4e79ebb@syzkaller.appspotmail.com Signed-off-by: Oliver Hartkopp Tested-by: Oliver Hartkopp Cc: linux-stable # >= v4.1 Signed-off-by: Marc Kleine-Budde --- include/linux/can/dev.h | 34 ++++++++++++++++++++++++++++++++++ 1 file changed, 34 insertions(+) (limited to 'include/linux') diff --git a/include/linux/can/dev.h b/include/linux/can/dev.h index 9b3c720a31b1..5e3d45525bd3 100644 --- a/include/linux/can/dev.h +++ b/include/linux/can/dev.h @@ -18,6 +18,7 @@ #include #include #include +#include #include /* @@ -91,6 +92,36 @@ struct can_priv { #define get_can_dlc(i) (min_t(__u8, (i), CAN_MAX_DLC)) #define get_canfd_dlc(i) (min_t(__u8, (i), CANFD_MAX_DLC)) +/* Check for outgoing skbs that have not been created by the CAN subsystem */ +static inline bool can_skb_headroom_valid(struct net_device *dev, + struct sk_buff *skb) +{ + /* af_packet creates a headroom of HH_DATA_MOD bytes which is fine */ + if (WARN_ON_ONCE(skb_headroom(skb) < sizeof(struct can_skb_priv))) + return false; + + /* af_packet does not apply CAN skb specific settings */ + if (skb->ip_summed == CHECKSUM_NONE) { + /* init headroom */ + can_skb_prv(skb)->ifindex = dev->ifindex; + can_skb_prv(skb)->skbcnt = 0; + + skb->ip_summed = CHECKSUM_UNNECESSARY; + + /* preform proper loopback on capable devices */ + if (dev->flags & IFF_ECHO) + skb->pkt_type = PACKET_LOOPBACK; + else + skb->pkt_type = PACKET_HOST; + + skb_reset_mac_header(skb); + skb_reset_network_header(skb); + skb_reset_transport_header(skb); + } + + return true; +} + /* Drop a given socketbuffer if it does not contain a valid CAN frame. */ static inline bool can_dropped_invalid_skb(struct net_device *dev, struct sk_buff *skb) @@ -108,6 +139,9 @@ static inline bool can_dropped_invalid_skb(struct net_device *dev, } else goto inval_skb; + if (!can_skb_headroom_valid(dev, skb)) + goto inval_skb; + return false; inval_skb: -- cgit v1.2.3 From 57415790f405534e5578d0106d806630c325dcb3 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Fri, 3 Jan 2020 21:09:35 -0700 Subject: block: remove unused mp_bvec_last_segment After commit 85a8ce62c2ea ("block: add bio_truncate to fix guard_bio_eod") this function is unused, remove it. Reviewed-by: Ming Lei Signed-off-by: Jens Axboe --- include/linux/bvec.h | 22 ---------------------- 1 file changed, 22 deletions(-) (limited to 'include/linux') diff --git a/include/linux/bvec.h b/include/linux/bvec.h index 679a42253170..a81c13ac1972 100644 --- a/include/linux/bvec.h +++ b/include/linux/bvec.h @@ -153,26 +153,4 @@ static inline void bvec_advance(const struct bio_vec *bvec, } } -/* - * Get the last single-page segment from the multi-page bvec and store it - * in @seg - */ -static inline void mp_bvec_last_segment(const struct bio_vec *bvec, - struct bio_vec *seg) -{ - unsigned total = bvec->bv_offset + bvec->bv_len; - unsigned last_page = (total - 1) / PAGE_SIZE; - - seg->bv_page = bvec->bv_page + last_page; - - /* the whole segment is inside the last page */ - if (bvec->bv_offset >= last_page * PAGE_SIZE) { - seg->bv_offset = bvec->bv_offset % PAGE_SIZE; - seg->bv_len = bvec->bv_len; - } else { - seg->bv_offset = 0; - seg->bv_len = total - last_page * PAGE_SIZE; - } -} - #endif /* __LINUX_BVEC_ITER_H */ -- cgit v1.2.3 From 5adcb8b18611c69577fd0f35337ab8d2573712fa Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Sat, 4 Jan 2020 16:21:06 +0100 Subject: net: ethernet: sxgbe: Rename Samsung to lowercase Fix up inconsistent usage of upper and lowercase letters in "Samsung" name. "SAMSUNG" is not an abbreviation but a regular trademarked name. Therefore it should be written with lowercase letters starting with capital letter. Although advertisement materials usually use uppercase "SAMSUNG", the lowercase version is used in all legal aspects (e.g. on Wikipedia and in privacy/legal statements on https://www.samsung.com/semiconductor/privacy-global/). Signed-off-by: Krzysztof Kozlowski Signed-off-by: David S. Miller --- include/linux/sxgbe_platform.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sxgbe_platform.h b/include/linux/sxgbe_platform.h index 85ec745767bd..966146f7267a 100644 --- a/include/linux/sxgbe_platform.h +++ b/include/linux/sxgbe_platform.h @@ -1,6 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0-only */ /* - * 10G controller driver for Samsung EXYNOS SoCs + * 10G controller driver for Samsung Exynos SoCs * * Copyright (C) 2013 Samsung Electronics Co., Ltd. * http://www.samsung.com -- cgit v1.2.3 From 96cc4b69581db68efc9749ef32e9cf8e0160c509 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 6 Jan 2020 12:30:48 -0800 Subject: macvlan: do not assume mac_header is set in macvlan_broadcast() Use of eth_hdr() in tx path is error prone. Many drivers call skb_reset_mac_header() before using it, but others do not. Commit 6d1ccff62780 ("net: reset mac header in dev_start_xmit()") attempted to fix this generically, but commit d346a3fae3ff ("packet: introduce PACKET_QDISC_BYPASS socket option") brought back the macvlan bug. Lets add a new helper, so that tx paths no longer have to call skb_reset_mac_header() only to get a pointer to skb->data. Hopefully we will be able to revert 6d1ccff62780 ("net: reset mac header in dev_start_xmit()") and save few cycles in transmit fast path. BUG: KASAN: use-after-free in __get_unaligned_cpu32 include/linux/unaligned/packed_struct.h:19 [inline] BUG: KASAN: use-after-free in mc_hash drivers/net/macvlan.c:251 [inline] BUG: KASAN: use-after-free in macvlan_broadcast+0x547/0x620 drivers/net/macvlan.c:277 Read of size 4 at addr ffff8880a4932401 by task syz-executor947/9579 CPU: 0 PID: 9579 Comm: syz-executor947 Not tainted 5.5.0-rc4-syzkaller #0 Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011 Call Trace: __dump_stack lib/dump_stack.c:77 [inline] dump_stack+0x197/0x210 lib/dump_stack.c:118 print_address_description.constprop.0.cold+0xd4/0x30b mm/kasan/report.c:374 __kasan_report.cold+0x1b/0x41 mm/kasan/report.c:506 kasan_report+0x12/0x20 mm/kasan/common.c:639 __asan_report_load_n_noabort+0xf/0x20 mm/kasan/generic_report.c:145 __get_unaligned_cpu32 include/linux/unaligned/packed_struct.h:19 [inline] mc_hash drivers/net/macvlan.c:251 [inline] macvlan_broadcast+0x547/0x620 drivers/net/macvlan.c:277 macvlan_queue_xmit drivers/net/macvlan.c:520 [inline] macvlan_start_xmit+0x402/0x77f drivers/net/macvlan.c:559 __netdev_start_xmit include/linux/netdevice.h:4447 [inline] netdev_start_xmit include/linux/netdevice.h:4461 [inline] dev_direct_xmit+0x419/0x630 net/core/dev.c:4079 packet_direct_xmit+0x1a9/0x250 net/packet/af_packet.c:240 packet_snd net/packet/af_packet.c:2966 [inline] packet_sendmsg+0x260d/0x6220 net/packet/af_packet.c:2991 sock_sendmsg_nosec net/socket.c:639 [inline] sock_sendmsg+0xd7/0x130 net/socket.c:659 __sys_sendto+0x262/0x380 net/socket.c:1985 __do_sys_sendto net/socket.c:1997 [inline] __se_sys_sendto net/socket.c:1993 [inline] __x64_sys_sendto+0xe1/0x1a0 net/socket.c:1993 do_syscall_64+0xfa/0x790 arch/x86/entry/common.c:294 entry_SYSCALL_64_after_hwframe+0x49/0xbe RIP: 0033:0x442639 Code: 18 89 d0 c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 0f 83 5b 10 fc ff c3 66 2e 0f 1f 84 00 00 00 00 RSP: 002b:00007ffc13549e08 EFLAGS: 00000246 ORIG_RAX: 000000000000002c RAX: ffffffffffffffda RBX: 0000000000000003 RCX: 0000000000442639 RDX: 000000000000000e RSI: 0000000020000080 RDI: 0000000000000003 RBP: 0000000000000004 R08: 0000000000000000 R09: 0000000000000000 R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000 R13: 0000000000403bb0 R14: 0000000000000000 R15: 0000000000000000 Allocated by task 9389: save_stack+0x23/0x90 mm/kasan/common.c:72 set_track mm/kasan/common.c:80 [inline] __kasan_kmalloc mm/kasan/common.c:513 [inline] __kasan_kmalloc.constprop.0+0xcf/0xe0 mm/kasan/common.c:486 kasan_kmalloc+0x9/0x10 mm/kasan/common.c:527 __do_kmalloc mm/slab.c:3656 [inline] __kmalloc+0x163/0x770 mm/slab.c:3665 kmalloc include/linux/slab.h:561 [inline] tomoyo_realpath_from_path+0xc5/0x660 security/tomoyo/realpath.c:252 tomoyo_get_realpath security/tomoyo/file.c:151 [inline] tomoyo_path_perm+0x230/0x430 security/tomoyo/file.c:822 tomoyo_inode_getattr+0x1d/0x30 security/tomoyo/tomoyo.c:129 security_inode_getattr+0xf2/0x150 security/security.c:1222 vfs_getattr+0x25/0x70 fs/stat.c:115 vfs_statx_fd+0x71/0xc0 fs/stat.c:145 vfs_fstat include/linux/fs.h:3265 [inline] __do_sys_newfstat+0x9b/0x120 fs/stat.c:378 __se_sys_newfstat fs/stat.c:375 [inline] __x64_sys_newfstat+0x54/0x80 fs/stat.c:375 do_syscall_64+0xfa/0x790 arch/x86/entry/common.c:294 entry_SYSCALL_64_after_hwframe+0x49/0xbe Freed by task 9389: save_stack+0x23/0x90 mm/kasan/common.c:72 set_track mm/kasan/common.c:80 [inline] kasan_set_free_info mm/kasan/common.c:335 [inline] __kasan_slab_free+0x102/0x150 mm/kasan/common.c:474 kasan_slab_free+0xe/0x10 mm/kasan/common.c:483 __cache_free mm/slab.c:3426 [inline] kfree+0x10a/0x2c0 mm/slab.c:3757 tomoyo_realpath_from_path+0x1a7/0x660 security/tomoyo/realpath.c:289 tomoyo_get_realpath security/tomoyo/file.c:151 [inline] tomoyo_path_perm+0x230/0x430 security/tomoyo/file.c:822 tomoyo_inode_getattr+0x1d/0x30 security/tomoyo/tomoyo.c:129 security_inode_getattr+0xf2/0x150 security/security.c:1222 vfs_getattr+0x25/0x70 fs/stat.c:115 vfs_statx_fd+0x71/0xc0 fs/stat.c:145 vfs_fstat include/linux/fs.h:3265 [inline] __do_sys_newfstat+0x9b/0x120 fs/stat.c:378 __se_sys_newfstat fs/stat.c:375 [inline] __x64_sys_newfstat+0x54/0x80 fs/stat.c:375 do_syscall_64+0xfa/0x790 arch/x86/entry/common.c:294 entry_SYSCALL_64_after_hwframe+0x49/0xbe The buggy address belongs to the object at ffff8880a4932000 which belongs to the cache kmalloc-4k of size 4096 The buggy address is located 1025 bytes inside of 4096-byte region [ffff8880a4932000, ffff8880a4933000) The buggy address belongs to the page: page:ffffea0002924c80 refcount:1 mapcount:0 mapping:ffff8880aa402000 index:0x0 compound_mapcount: 0 raw: 00fffe0000010200 ffffea0002846208 ffffea00028f3888 ffff8880aa402000 raw: 0000000000000000 ffff8880a4932000 0000000100000001 0000000000000000 page dumped because: kasan: bad access detected Memory state around the buggy address: ffff8880a4932300: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff8880a4932380: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb >ffff8880a4932400: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ^ ffff8880a4932480: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb ffff8880a4932500: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb Fixes: b863ceb7ddce ("[NET]: Add macvlan driver") Signed-off-by: Eric Dumazet Reported-by: syzbot Signed-off-by: David S. Miller --- include/linux/if_ether.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/if_ether.h b/include/linux/if_ether.h index 76cf11e905e1..8a9792a6427a 100644 --- a/include/linux/if_ether.h +++ b/include/linux/if_ether.h @@ -24,6 +24,14 @@ static inline struct ethhdr *eth_hdr(const struct sk_buff *skb) return (struct ethhdr *)skb_mac_header(skb); } +/* Prefer this version in TX path, instead of + * skb_reset_mac_header() + eth_hdr() + */ +static inline struct ethhdr *skb_eth_hdr(const struct sk_buff *skb) +{ + return (struct ethhdr *)skb->data; +} + static inline struct ethhdr *inner_eth_hdr(const struct sk_buff *skb) { return (struct ethhdr *)skb_inner_mac_header(skb); -- cgit v1.2.3 From 44f45994f438b4f4e0ba977b173980268983c60f Mon Sep 17 00:00:00 2001 From: Amir Mahdi Ghorbanian Date: Thu, 2 Jan 2020 12:10:08 -0500 Subject: mtd: onenand: omap2: Fix errors in style Correct mispelling, spacing, and coding style flaws caught by checkpatch.pl script in the Omap2 Onenand driver . Signed-off-by: Amir Mahdi Ghorbanian Signed-off-by: Miquel Raynal --- include/linux/mtd/flashchip.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mtd/flashchip.h b/include/linux/mtd/flashchip.h index ecc88a41792a..c04f690871ca 100644 --- a/include/linux/mtd/flashchip.h +++ b/include/linux/mtd/flashchip.h @@ -40,7 +40,7 @@ typedef enum { FL_READING, FL_CACHEDPRG, /* These 4 come from onenand_state_t, which has been unified here */ - FL_RESETING, + FL_RESETTING, FL_OTPING, FL_PREPARING_ERASE, FL_VERIFYING_ERASE, -- cgit v1.2.3 From 4a87e2a25dc27131c3cce5e94421622193305638 Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Mon, 13 Jan 2020 16:29:16 -0800 Subject: mm: memcg/slab: fix percpu slab vmstats flushing Currently slab percpu vmstats are flushed twice: during the memcg offlining and just before freeing the memcg structure. Each time percpu counters are summed, added to the atomic counterparts and propagated up by the cgroup tree. The second flushing is required due to how recursive vmstats are implemented: counters are batched in percpu variables on a local level, and once a percpu value is crossing some predefined threshold, it spills over to atomic values on the local and each ascendant levels. It means that without flushing some numbers cached in percpu variables will be dropped on floor each time a cgroup is destroyed. And with uptime the error on upper levels might become noticeable. The first flushing aims to make counters on ancestor levels more precise. Dying cgroups may resume in the dying state for a long time. After kmem_cache reparenting which is performed during the offlining slab counters of the dying cgroup don't have any chances to be updated, because any slab operations will be performed on the parent level. It means that the inaccuracy caused by percpu batching will not decrease up to the final destruction of the cgroup. By the original idea flushing slab counters during the offlining should minimize the visible inaccuracy of slab counters on the parent level. The problem is that percpu counters are not zeroed after the first flushing. So every cached percpu value is summed twice. It creates a small error (up to 32 pages per cpu, but usually less) which accumulates on parent cgroup level. After creating and destroying of thousands of child cgroups, slab counter on parent level can be way off the real value. For now, let's just stop flushing slab counters on memcg offlining. It can't be done correctly without scheduling a work on each cpu: reading and zeroing it during css offlining can race with an asynchronous update, which doesn't expect values to be changed underneath. With this change, slab counters on parent level will become eventually consistent. Once all dying children are gone, values are correct. And if not, the error is capped by 32 * NR_CPUS pages per dying cgroup. It's not perfect, as slab are reparented, so any updates after the reparenting will happen on the parent level. It means that if a slab page was allocated, a counter on child level was bumped, then the page was reparented and freed, the annihilation of positive and negative counter values will not happen until the child cgroup is released. It makes slab counters different from others, and it might want us to implement flushing in a correct form again. But it's also a question of performance: scheduling a work on each cpu isn't free, and it's an open question if the benefit of having more accurate counters is worth it. We might also consider flushing all counters on offlining, not only slab counters. So let's fix the main problem now: make the slab counters eventually consistent, so at least the error won't grow with uptime (or more precisely the number of created and destroyed cgroups). And think about the accuracy of counters separately. Link: http://lkml.kernel.org/r/20191220042728.1045881-1-guro@fb.com Fixes: bee07b33db78 ("mm: memcontrol: flush percpu slab vmstats on kmem offlining") Signed-off-by: Roman Gushchin Acked-by: Johannes Weiner Acked-by: Michal Hocko Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mmzone.h | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 89d8ff06c9ce..5334ad8fc7bd 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -215,9 +215,8 @@ enum node_stat_item { NR_INACTIVE_FILE, /* " " " " " */ NR_ACTIVE_FILE, /* " " " " " */ NR_UNEVICTABLE, /* " " " " " */ - NR_SLAB_RECLAIMABLE, /* Please do not reorder this item */ - NR_SLAB_UNRECLAIMABLE, /* and this one without looking at - * memcg_flush_percpu_vmstats() first. */ + NR_SLAB_RECLAIMABLE, + NR_SLAB_UNRECLAIMABLE, NR_ISOLATED_ANON, /* Temporary isolated pages from anon lru */ NR_ISOLATED_FILE, /* Temporary isolated pages from file lru */ WORKINGSET_NODES, -- cgit v1.2.3 From 8e57f8acbbd121ecfb0c9dc13b8b030f86c6bd3b Mon Sep 17 00:00:00 2001 From: Vlastimil Babka Date: Mon, 13 Jan 2020 16:29:20 -0800 Subject: mm, debug_pagealloc: don't rely on static keys too early Commit 96a2b03f281d ("mm, debug_pagelloc: use static keys to enable debugging") has introduced a static key to reduce overhead when debug_pagealloc is compiled in but not enabled. It relied on the assumption that jump_label_init() is called before parse_early_param() as in start_kernel(), so when the "debug_pagealloc=on" option is parsed, it is safe to enable the static key. However, it turns out multiple architectures call parse_early_param() earlier from their setup_arch(). x86 also calls jump_label_init() even earlier, so no issue was found while testing the commit, but same is not true for e.g. ppc64 and s390 where the kernel would not boot with debug_pagealloc=on as found by our QA. To fix this without tricky changes to init code of multiple architectures, this patch partially reverts the static key conversion from 96a2b03f281d. Init-time and non-fastpath calls (such as in arch code) of debug_pagealloc_enabled() will again test a simple bool variable. Fastpath mm code is converted to a new debug_pagealloc_enabled_static() variant that relies on the static key, which is enabled in a well-defined point in mm_init() where it's guaranteed that jump_label_init() has been called, regardless of architecture. [sfr@canb.auug.org.au: export _debug_pagealloc_enabled_early] Link: http://lkml.kernel.org/r/20200106164944.063ac07b@canb.auug.org.au Link: http://lkml.kernel.org/r/20191219130612.23171-1-vbabka@suse.cz Fixes: 96a2b03f281d ("mm, debug_pagelloc: use static keys to enable debugging") Signed-off-by: Vlastimil Babka Signed-off-by: Stephen Rothwell Cc: Joonsoo Kim Cc: "Kirill A. Shutemov" Cc: Michal Hocko Cc: Vlastimil Babka Cc: Matthew Wilcox Cc: Mel Gorman Cc: Peter Zijlstra Cc: Borislav Petkov Cc: Qian Cai Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm.h | 18 +++++++++++++++--- 1 file changed, 15 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 80a9162b406c..cfaa8feecfe8 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2658,13 +2658,25 @@ static inline bool want_init_on_free(void) !page_poisoning_enabled(); } -#ifdef CONFIG_DEBUG_PAGEALLOC_ENABLE_DEFAULT -DECLARE_STATIC_KEY_TRUE(_debug_pagealloc_enabled); +#ifdef CONFIG_DEBUG_PAGEALLOC +extern void init_debug_pagealloc(void); #else -DECLARE_STATIC_KEY_FALSE(_debug_pagealloc_enabled); +static inline void init_debug_pagealloc(void) {} #endif +extern bool _debug_pagealloc_enabled_early; +DECLARE_STATIC_KEY_FALSE(_debug_pagealloc_enabled); static inline bool debug_pagealloc_enabled(void) +{ + return IS_ENABLED(CONFIG_DEBUG_PAGEALLOC) && + _debug_pagealloc_enabled_early; +} + +/* + * For use in fast paths after init_debug_pagealloc() has run, or when a + * false negative result is not harmful when called too early. + */ +static inline bool debug_pagealloc_enabled_static(void) { if (!IS_ENABLED(CONFIG_DEBUG_PAGEALLOC)) return false; -- cgit v1.2.3 From c64cd6e34ea340adbb2a0a2f99cc884b96dcdca5 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Fri, 10 Jan 2020 17:17:19 -0500 Subject: reimplement path_mountpoint() with less magic ... and get rid of a bunch of bugs in it. Background: the reason for path_mountpoint() is that umount() really doesn't want attempts to revalidate the root of what it's trying to umount. The thing we want to avoid actually happen from complete_walk(); solution was to do something parallel to normal path_lookupat() and it both went overboard and got the boilerplate subtly (and not so subtly) wrong. A better solution is to do pretty much what the normal path_lookupat() does, but instead of complete_walk() do unlazy_walk(). All it takes to avoid that ->d_weak_revalidate() call... mountpoint_last() goes away, along with everything it got wrong, and so does the magic around LOOKUP_NO_REVAL. Another source of bugs is that when we traverse mounts at the final location (and we need to do that - umount . expects to get whatever's overmounting ., if any, out of the lookup) we really ought to take care of ->d_manage() - as it is, manual umount of autofs automount in progress can lead to unpleasant surprises for the daemon. Easily solved by using handle_lookup_down() instead of follow_mount(). Tested-by: Ian Kent Signed-off-by: Al Viro --- include/linux/namei.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/namei.h b/include/linux/namei.h index 7fe7b87a3ded..07bfb0874033 100644 --- a/include/linux/namei.h +++ b/include/linux/namei.h @@ -34,7 +34,6 @@ enum {LAST_NORM, LAST_ROOT, LAST_DOT, LAST_DOTDOT, LAST_BIND}; /* internal use only */ #define LOOKUP_PARENT 0x0010 -#define LOOKUP_NO_REVAL 0x0080 #define LOOKUP_JUMPED 0x1000 #define LOOKUP_ROOT 0x2000 #define LOOKUP_ROOT_GRABBED 0x0008 -- cgit v1.2.3 From 0af2ffc93a4b50948f9dad2786b7f1bd253bf0b9 Mon Sep 17 00:00:00 2001 From: Daniel Borkmann Date: Wed, 15 Jan 2020 21:47:33 +0100 Subject: bpf: Fix incorrect verifier simulation of ARSH under ALU32 Anatoly has been fuzzing with kBdysch harness and reported a hang in one of the outcomes: 0: R1=ctx(id=0,off=0,imm=0) R10=fp0 0: (85) call bpf_get_socket_cookie#46 1: R0_w=invP(id=0) R10=fp0 1: (57) r0 &= 808464432 2: R0_w=invP(id=0,umax_value=808464432,var_off=(0x0; 0x30303030)) R10=fp0 2: (14) w0 -= 810299440 3: R0_w=invP(id=0,umax_value=4294967295,var_off=(0xcf800000; 0x3077fff0)) R10=fp0 3: (c4) w0 s>>= 1 4: R0_w=invP(id=0,umin_value=1740636160,umax_value=2147221496,var_off=(0x67c00000; 0x183bfff8)) R10=fp0 4: (76) if w0 s>= 0x30303030 goto pc+216 221: R0_w=invP(id=0,umin_value=1740636160,umax_value=2147221496,var_off=(0x67c00000; 0x183bfff8)) R10=fp0 221: (95) exit processed 6 insns (limit 1000000) [...] Taking a closer look, the program was xlated as follows: # ./bpftool p d x i 12 0: (85) call bpf_get_socket_cookie#7800896 1: (bf) r6 = r0 2: (57) r6 &= 808464432 3: (14) w6 -= 810299440 4: (c4) w6 s>>= 1 5: (76) if w6 s>= 0x30303030 goto pc+216 6: (05) goto pc-1 7: (05) goto pc-1 8: (05) goto pc-1 [...] 220: (05) goto pc-1 221: (05) goto pc-1 222: (95) exit Meaning, the visible effect is very similar to f54c7898ed1c ("bpf: Fix precision tracking for unbounded scalars"), that is, the fall-through branch in the instruction 5 is considered to be never taken given the conclusion from the min/max bounds tracking in w6, and therefore the dead-code sanitation rewrites it as goto pc-1. However, real-life input disagrees with verification analysis since a soft-lockup was observed. The bug sits in the analysis of the ARSH. The definition is that we shift the target register value right by K bits through shifting in copies of its sign bit. In adjust_scalar_min_max_vals(), we do first coerce the register into 32 bit mode, same happens after simulating the operation. However, for the case of simulating the actual ARSH, we don't take the mode into account and act as if it's always 64 bit, but location of sign bit is different: dst_reg->smin_value >>= umin_val; dst_reg->smax_value >>= umin_val; dst_reg->var_off = tnum_arshift(dst_reg->var_off, umin_val); Consider an unknown R0 where bpf_get_socket_cookie() (or others) would for example return 0xffff. With the above ARSH simulation, we'd see the following results: [...] 1: R1=ctx(id=0,off=0,imm=0) R2_w=invP65535 R10=fp0 1: (85) call bpf_get_socket_cookie#46 2: R0_w=invP(id=0) R10=fp0 2: (57) r0 &= 808464432 -> R0_runtime = 0x3030 3: R0_w=invP(id=0,umax_value=808464432,var_off=(0x0; 0x30303030)) R10=fp0 3: (14) w0 -= 810299440 -> R0_runtime = 0xcfb40000 4: R0_w=invP(id=0,umax_value=4294967295,var_off=(0xcf800000; 0x3077fff0)) R10=fp0 (0xffffffff) 4: (c4) w0 s>>= 1 -> R0_runtime = 0xe7da0000 5: R0_w=invP(id=0,umin_value=1740636160,umax_value=2147221496,var_off=(0x67c00000; 0x183bfff8)) R10=fp0 (0x67c00000) (0x7ffbfff8) [...] In insn 3, we have a runtime value of 0xcfb40000, which is '1100 1111 1011 0100 0000 0000 0000 0000', the result after the shift has 0xe7da0000 that is '1110 0111 1101 1010 0000 0000 0000 0000', where the sign bit is correctly retained in 32 bit mode. In insn4, the umax was 0xffffffff, and changed into 0x7ffbfff8 after the shift, that is, '0111 1111 1111 1011 1111 1111 1111 1000' and means here that the simulation didn't retain the sign bit. With above logic, the updates happen on the 64 bit min/max bounds and given we coerced the register, the sign bits of the bounds are cleared as well, meaning, we need to force the simulation into s32 space for 32 bit alu mode. Verification after the fix below. We're first analyzing the fall-through branch on 32 bit signed >= test eventually leading to rejection of the program in this specific case: 0: R1=ctx(id=0,off=0,imm=0) R10=fp0 0: (b7) r2 = 808464432 1: R1=ctx(id=0,off=0,imm=0) R2_w=invP808464432 R10=fp0 1: (85) call bpf_get_socket_cookie#46 2: R0_w=invP(id=0) R10=fp0 2: (bf) r6 = r0 3: R0_w=invP(id=0) R6_w=invP(id=0) R10=fp0 3: (57) r6 &= 808464432 4: R0_w=invP(id=0) R6_w=invP(id=0,umax_value=808464432,var_off=(0x0; 0x30303030)) R10=fp0 4: (14) w6 -= 810299440 5: R0_w=invP(id=0) R6_w=invP(id=0,umax_value=4294967295,var_off=(0xcf800000; 0x3077fff0)) R10=fp0 5: (c4) w6 s>>= 1 6: R0_w=invP(id=0) R6_w=invP(id=0,umin_value=3888119808,umax_value=4294705144,var_off=(0xe7c00000; 0x183bfff8)) R10=fp0 (0x67c00000) (0xfffbfff8) 6: (76) if w6 s>= 0x30303030 goto pc+216 7: R0_w=invP(id=0) R6_w=invP(id=0,umin_value=3888119808,umax_value=4294705144,var_off=(0xe7c00000; 0x183bfff8)) R10=fp0 7: (30) r0 = *(u8 *)skb[808464432] BPF_LD_[ABS|IND] uses reserved fields processed 8 insns (limit 1000000) [...] Fixes: 9cbe1f5a32dc ("bpf/verifier: improve register value range tracking with ARSH") Reported-by: Anatoly Trosinenko Signed-off-by: Daniel Borkmann Acked-by: Yonghong Song Signed-off-by: Alexei Starovoitov Link: https://lore.kernel.org/bpf/20200115204733.16648-1-daniel@iogearbox.net --- include/linux/tnum.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/tnum.h b/include/linux/tnum.h index c17af77f3fae..ea627d1ab7e3 100644 --- a/include/linux/tnum.h +++ b/include/linux/tnum.h @@ -30,7 +30,7 @@ struct tnum tnum_lshift(struct tnum a, u8 shift); /* Shift (rsh) a tnum right (by a fixed shift) */ struct tnum tnum_rshift(struct tnum a, u8 shift); /* Shift (arsh) a tnum right (by a fixed min_shift) */ -struct tnum tnum_arshift(struct tnum a, u8 min_shift); +struct tnum tnum_arshift(struct tnum a, u8 min_shift, u8 insn_bitness); /* Add two tnums, return @a + @b */ struct tnum tnum_add(struct tnum a, struct tnum b); /* Subtract two tnums, return @a - @b */ -- cgit v1.2.3 From 4da6a196f93b1af7612340e8c1ad8ce71e18f955 Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Sat, 11 Jan 2020 06:11:59 +0000 Subject: bpf: Sockmap/tls, during free we may call tcp_bpf_unhash() in loop When a sockmap is free'd and a socket in the map is enabled with tls we tear down the bpf context on the socket, the psock struct and state, and then call tcp_update_ulp(). The tcp_update_ulp() call is to inform the tls stack it needs to update its saved sock ops so that when the tls socket is later destroyed it doesn't try to call the now destroyed psock hooks. This is about keeping stacked ULPs in good shape so they always have the right set of stacked ops. However, recently unhash() hook was removed from TLS side. But, the sockmap/bpf side is not doing any extra work to update the unhash op when is torn down instead expecting TLS side to manage it. So both TLS and sockmap believe the other side is managing the op and instead no one updates the hook so it continues to point at tcp_bpf_unhash(). When unhash hook is called we call tcp_bpf_unhash() which detects the psock has already been destroyed and calls sk->sk_prot_unhash() which calls tcp_bpf_unhash() yet again and so on looping and hanging the core. To fix have sockmap tear down logic fixup the stale pointer. Fixes: 5d92e631b8be ("net/tls: partially revert fix transition through disconnect with close") Reported-by: syzbot+83979935eb6304f8cd46@syzkaller.appspotmail.com Signed-off-by: John Fastabend Signed-off-by: Daniel Borkmann Reviewed-by: Jakub Sitnicki Acked-by: Song Liu Cc: stable@vger.kernel.org Link: https://lore.kernel.org/bpf/20200111061206.8028-2-john.fastabend@gmail.com --- include/linux/skmsg.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index ef7031f8a304..b6afe01f8592 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -358,6 +358,7 @@ static inline void sk_psock_update_proto(struct sock *sk, static inline void sk_psock_restore_proto(struct sock *sk, struct sk_psock *psock) { + sk->sk_prot->unhash = psock->saved_unhash; sk->sk_write_space = psock->saved_write_space; if (psock->sk_proto) { -- cgit v1.2.3 From 33bfe20dd7117dd81fd896a53f743a233e1ad64f Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Sat, 11 Jan 2020 06:12:01 +0000 Subject: bpf: Sockmap/tls, push write_space updates through ulp updates When sockmap sock with TLS enabled is removed we cleanup bpf/psock state and call tcp_update_ulp() to push updates to TLS ULP on top. However, we don't push the write_space callback up and instead simply overwrite the op with the psock stored previous op. This may or may not be correct so to ensure we don't overwrite the TLS write space hook pass this field to the ULP and have it fixup the ctx. This completes a previous fix that pushed the ops through to the ULP but at the time missed doing this for write_space, presumably because write_space TLS hook was added around the same time. Fixes: 95fa145479fbc ("bpf: sockmap/tls, close can race with map free") Signed-off-by: John Fastabend Signed-off-by: Daniel Borkmann Reviewed-by: Jakub Sitnicki Acked-by: Jonathan Lemon Cc: stable@vger.kernel.org Link: https://lore.kernel.org/bpf/20200111061206.8028-4-john.fastabend@gmail.com --- include/linux/skmsg.h | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skmsg.h b/include/linux/skmsg.h index b6afe01f8592..14d61bba0b79 100644 --- a/include/linux/skmsg.h +++ b/include/linux/skmsg.h @@ -359,17 +359,21 @@ static inline void sk_psock_restore_proto(struct sock *sk, struct sk_psock *psock) { sk->sk_prot->unhash = psock->saved_unhash; - sk->sk_write_space = psock->saved_write_space; if (psock->sk_proto) { struct inet_connection_sock *icsk = inet_csk(sk); bool has_ulp = !!icsk->icsk_ulp_data; - if (has_ulp) - tcp_update_ulp(sk, psock->sk_proto); - else + if (has_ulp) { + tcp_update_ulp(sk, psock->sk_proto, + psock->saved_write_space); + } else { sk->sk_prot = psock->sk_proto; + sk->sk_write_space = psock->saved_write_space; + } psock->sk_proto = NULL; + } else { + sk->sk_write_space = psock->saved_write_space; } } -- cgit v1.2.3 From ad6bf88a6c19a39fb3b0045d78ea880325dfcf15 Mon Sep 17 00:00:00 2001 From: Mikulas Patocka Date: Wed, 15 Jan 2020 08:35:25 -0500 Subject: block: fix an integer overflow in logical block size Logical block size has type unsigned short. That means that it can be at most 32768. However, there are architectures that can run with 64k pages (for example arm64) and on these architectures, it may be possible to create block devices with 64k block size. For exmaple (run this on an architecture with 64k pages): Mount will fail with this error because it tries to read the superblock using 2-sector access: device-mapper: writecache: I/O is not aligned, sector 2, size 1024, block size 65536 EXT4-fs (dm-0): unable to read superblock This patch changes the logical block size from unsigned short to unsigned int to avoid the overflow. Cc: stable@vger.kernel.org Reviewed-by: Martin K. Petersen Reviewed-by: Ming Lei Signed-off-by: Mikulas Patocka Signed-off-by: Jens Axboe --- include/linux/blkdev.h | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index 47eb22a3b7f9..4c636c42ad68 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -328,6 +328,7 @@ struct queue_limits { unsigned int max_sectors; unsigned int max_segment_size; unsigned int physical_block_size; + unsigned int logical_block_size; unsigned int alignment_offset; unsigned int io_min; unsigned int io_opt; @@ -338,7 +339,6 @@ struct queue_limits { unsigned int discard_granularity; unsigned int discard_alignment; - unsigned short logical_block_size; unsigned short max_segments; unsigned short max_integrity_segments; unsigned short max_discard_segments; @@ -1077,7 +1077,7 @@ extern void blk_queue_max_write_same_sectors(struct request_queue *q, unsigned int max_write_same_sectors); extern void blk_queue_max_write_zeroes_sectors(struct request_queue *q, unsigned int max_write_same_sectors); -extern void blk_queue_logical_block_size(struct request_queue *, unsigned short); +extern void blk_queue_logical_block_size(struct request_queue *, unsigned int); extern void blk_queue_physical_block_size(struct request_queue *, unsigned int); extern void blk_queue_alignment_offset(struct request_queue *q, unsigned int alignment); @@ -1291,7 +1291,7 @@ static inline unsigned int queue_max_segment_size(const struct request_queue *q) return q->limits.max_segment_size; } -static inline unsigned short queue_logical_block_size(const struct request_queue *q) +static inline unsigned queue_logical_block_size(const struct request_queue *q) { int retval = 512; @@ -1301,7 +1301,7 @@ static inline unsigned short queue_logical_block_size(const struct request_queue return retval; } -static inline unsigned short bdev_logical_block_size(struct block_device *bdev) +static inline unsigned int bdev_logical_block_size(struct block_device *bdev) { return queue_logical_block_size(bdev_get_queue(bdev)); } -- cgit v1.2.3