From 03c57747a7020a28a200e7e920fb48ecdc9b0fb8 Mon Sep 17 00:00:00 2001 From: Robert Shearman Date: Wed, 22 Apr 2015 11:14:37 +0100 Subject: mpls: Per-device MPLS state Add per-device MPLS state to supported interfaces. Use the presence of this state in mpls_route_add to determine that this is a supported interface. Use the presence of mpls_dev to drop packets that arrived on an unsupported interface - previously they were allowed through. Cc: "Eric W. Biederman" Signed-off-by: Robert Shearman Reviewed-by: "Eric W. Biederman" Signed-off-by: David S. Miller --- include/linux/netdevice.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index bcbde799ec69..dae106a3a998 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -60,6 +60,7 @@ struct phy_device; struct wireless_dev; /* 802.15.4 specific */ struct wpan_dev; +struct mpls_dev; void netdev_set_default_ethtool_ops(struct net_device *dev, const struct ethtool_ops *ops); @@ -1627,6 +1628,9 @@ struct net_device { void *ax25_ptr; struct wireless_dev *ieee80211_ptr; struct wpan_dev *ieee802154_ptr; +#if IS_ENABLED(CONFIG_MPLS_ROUTING) + struct mpls_dev __rcu *mpls_ptr; +#endif /* * Cache lines mostly used on receive path (including eth_type_trans()) -- cgit v1.2.3 From 7e01b5acd88b3f3108d8c4ce44e3205d67437202 Mon Sep 17 00:00:00 2001 From: Martin Schwidefsky Date: Thu, 16 Apr 2015 14:47:33 +0200 Subject: kexec: allocate the kexec control page with KEXEC_CONTROL_MEMORY_GFP Introduce KEXEC_CONTROL_MEMORY_GFP to allow the architecture code to override the gfp flags of the allocation for the kexec control page. The loop in kimage_alloc_normal_control_pages allocates pages with GFP_KERNEL until a page is found that happens to have an address smaller than the KEXEC_CONTROL_MEMORY_LIMIT. On systems with a large memory size but a small KEXEC_CONTROL_MEMORY_LIMIT the loop will keep allocating memory until the oom killer steps in. Signed-off-by: Martin Schwidefsky --- arch/s390/include/asm/kexec.h | 3 +++ include/linux/kexec.h | 4 ++++ kernel/kexec.c | 2 +- 3 files changed, 8 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/arch/s390/include/asm/kexec.h b/arch/s390/include/asm/kexec.h index 694bcd6bd927..2f924bc30e35 100644 --- a/arch/s390/include/asm/kexec.h +++ b/arch/s390/include/asm/kexec.h @@ -26,6 +26,9 @@ /* Not more than 2GB */ #define KEXEC_CONTROL_MEMORY_LIMIT (1UL<<31) +/* Allocate control page with GFP_DMA */ +#define KEXEC_CONTROL_MEMORY_GFP GFP_DMA + /* Maximum address we can use for the crash control pages */ #define KEXEC_CRASH_CONTROL_MEMORY_LIMIT (-1UL) diff --git a/include/linux/kexec.h b/include/linux/kexec.h index e60a745ac198..e804306ef5e8 100644 --- a/include/linux/kexec.h +++ b/include/linux/kexec.h @@ -40,6 +40,10 @@ #error KEXEC_CONTROL_MEMORY_LIMIT not defined #endif +#ifndef KEXEC_CONTROL_MEMORY_GFP +#define KEXEC_CONTROL_MEMORY_GFP GFP_KERNEL +#endif + #ifndef KEXEC_CONTROL_PAGE_SIZE #error KEXEC_CONTROL_PAGE_SIZE not defined #endif diff --git a/kernel/kexec.c b/kernel/kexec.c index 38c25b1f2fd5..7a36fdcca5bf 100644 --- a/kernel/kexec.c +++ b/kernel/kexec.c @@ -707,7 +707,7 @@ static struct page *kimage_alloc_normal_control_pages(struct kimage *image, do { unsigned long pfn, epfn, addr, eaddr; - pages = kimage_alloc_pages(GFP_KERNEL, order); + pages = kimage_alloc_pages(KEXEC_CONTROL_MEMORY_GFP, order); if (!pages) break; pfn = page_to_pfn(pages); -- cgit v1.2.3 From ec65aafb9e3f316ff9167289e288856a7d528773 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Thu, 23 Apr 2015 12:06:30 +0200 Subject: netdev_alloc_pcpu_stats: use less common iterator variable With the CPU iteration variable called 'i', it's relatively easy to have variable shadowing which sparse will warn about. Avoid that by renaming the variable to __cpu which is less likely to be used in the surrounding context. Signed-off-by: Johannes Berg Signed-off-by: David S. Miller --- include/linux/netdevice.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index dae106a3a998..dbad4d728b4b 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2025,10 +2025,10 @@ struct pcpu_sw_netstats { ({ \ typeof(type) __percpu *pcpu_stats = alloc_percpu(type); \ if (pcpu_stats) { \ - int i; \ - for_each_possible_cpu(i) { \ + int __cpu; \ + for_each_possible_cpu(__cpu) { \ typeof(type) *stat; \ - stat = per_cpu_ptr(pcpu_stats, i); \ + stat = per_cpu_ptr(pcpu_stats, __cpu); \ u64_stats_init(&stat->syncp); \ } \ } \ -- cgit v1.2.3 From 1d8dc3d3c8f1d8ee1da9d54c5d7c8694419ade42 Mon Sep 17 00:00:00 2001 From: Johannes Berg Date: Thu, 23 Apr 2015 16:38:43 +0200 Subject: rhashtable: don't attempt to grow when at max_size The conversion of mac80211's station table to rhashtable had a bug that I found by accident in code review, that hadn't been found as rhashtable apparently managed to have a maximum hash chain length of one (!) in all our testing. In order to test the bug and verify the fix I set my rhashtable's max_size very low (4) in order to force getting hash collisions. At that point, rhashtable WARNed in rhashtable_insert_rehash() but didn't actually reject the hash table insertion. This caused it to lose insertions - my master list of stations would have 9 entries, but the rhashtable only had 5. This may warrant a deeper look, but that WARN_ON() just shouldn't happen. Fix this by not returning true from rht_grow_above_100() when the rhashtable's max_size has been reached - in this case the user is explicitly configuring it to be at most that big, so even if it's now above 100% it shouldn't attempt to resize. This fixes the "lost insertion" issue and consequently allows my code to display its error (and verify my fix for it.) Signed-off-by: Johannes Berg Acked-by: Thomas Graf Signed-off-by: David S. Miller --- include/linux/rhashtable.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h index e23d242d1230..dbcbcc59aa92 100644 --- a/include/linux/rhashtable.h +++ b/include/linux/rhashtable.h @@ -282,7 +282,8 @@ static inline bool rht_shrink_below_30(const struct rhashtable *ht, static inline bool rht_grow_above_100(const struct rhashtable *ht, const struct bucket_table *tbl) { - return atomic_read(&ht->nelems) > tbl->size; + return atomic_read(&ht->nelems) > tbl->size && + (!ht->p.max_size || tbl->size < ht->p.max_size); } /* The bucket lock is selected based on the hash and protects mutations -- cgit v1.2.3 From 547c4b547e07dcc60874b6ef6252dd49ff74aec1 Mon Sep 17 00:00:00 2001 From: Florian Westphal Date: Mon, 20 Apr 2015 12:35:47 +0200 Subject: netfilter: bridge: fix NULL deref in physin/out ifindex helpers Might not have an outdev yet. We'll oops when iface goes down while skbs are still nfqueue'd: RIP: 0010:[] [] dev_cmp+0x4f/0x80 nfqnl_rcv_dev_event+0xe2/0x150 notifier_call_chain+0x53/0xa0 Fixes: c737b7c4510026 ("netfilter: bridge: add helpers for fetching physin/outdev") Signed-off-by: Florian Westphal Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter_bridge.h | 16 ++++++++++++++-- 1 file changed, 14 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netfilter_bridge.h b/include/linux/netfilter_bridge.h index ab8f76dba668..f2fdb5a52070 100644 --- a/include/linux/netfilter_bridge.h +++ b/include/linux/netfilter_bridge.h @@ -39,12 +39,24 @@ static inline void br_drop_fake_rtable(struct sk_buff *skb) static inline int nf_bridge_get_physinif(const struct sk_buff *skb) { - return skb->nf_bridge ? skb->nf_bridge->physindev->ifindex : 0; + struct nf_bridge_info *nf_bridge; + + if (skb->nf_bridge == NULL) + return 0; + + nf_bridge = skb->nf_bridge; + return nf_bridge->physindev ? nf_bridge->physindev->ifindex : 0; } static inline int nf_bridge_get_physoutif(const struct sk_buff *skb) { - return skb->nf_bridge ? skb->nf_bridge->physoutdev->ifindex : 0; + struct nf_bridge_info *nf_bridge; + + if (skb->nf_bridge == NULL) + return 0; + + nf_bridge = skb->nf_bridge; + return nf_bridge->physoutdev ? nf_bridge->physoutdev->ifindex : 0; } static inline struct net_device * -- cgit v1.2.3 From 2ea2f62c8bda242433809c7f4e9eae1c52c40bbe Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Fri, 24 Apr 2015 16:05:01 -0700 Subject: net: fix crash in build_skb() When I added pfmemalloc support in build_skb(), I forgot netlink was using build_skb() with a vmalloc() area. In this patch I introduce __build_skb() for netlink use, and build_skb() is a wrapper handling both skb->head_frag and skb->pfmemalloc This means netlink no longer has to hack skb->head_frag [ 1567.700067] kernel BUG at arch/x86/mm/physaddr.c:26! [ 1567.700067] invalid opcode: 0000 [#1] PREEMPT SMP KASAN [ 1567.700067] Dumping ftrace buffer: [ 1567.700067] (ftrace buffer empty) [ 1567.700067] Modules linked in: [ 1567.700067] CPU: 9 PID: 16186 Comm: trinity-c182 Not tainted 4.0.0-next-20150424-sasha-00037-g4796e21 #2167 [ 1567.700067] task: ffff880127efb000 ti: ffff880246770000 task.ti: ffff880246770000 [ 1567.700067] RIP: __phys_addr (arch/x86/mm/physaddr.c:26 (discriminator 3)) [ 1567.700067] RSP: 0018:ffff8802467779d8 EFLAGS: 00010202 [ 1567.700067] RAX: 000041000ed8e000 RBX: ffffc9008ed8e000 RCX: 000000000000002c [ 1567.700067] RDX: 0000000000000004 RSI: 0000000000000000 RDI: ffffffffb3fd6049 [ 1567.700067] RBP: ffff8802467779f8 R08: 0000000000000019 R09: ffff8801d0168000 [ 1567.700067] R10: ffff8801d01680c7 R11: ffffed003a02d019 R12: ffffc9000ed8e000 [ 1567.700067] R13: 0000000000000f40 R14: 0000000000001180 R15: ffffc9000ed8e000 [ 1567.700067] FS: 00007f2a7da3f700(0000) GS:ffff8801d1000000(0000) knlGS:0000000000000000 [ 1567.700067] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 1567.700067] CR2: 0000000000738308 CR3: 000000022e329000 CR4: 00000000000007e0 [ 1567.700067] Stack: [ 1567.700067] ffffc9000ed8e000 ffff8801d0168000 ffffc9000ed8e000 ffff8801d0168000 [ 1567.700067] ffff880246777a28 ffffffffad7c0a21 0000000000001080 ffff880246777c08 [ 1567.700067] ffff88060d302e68 ffff880246777b58 ffff880246777b88 ffffffffad9a6821 [ 1567.700067] Call Trace: [ 1567.700067] build_skb (include/linux/mm.h:508 net/core/skbuff.c:316) [ 1567.700067] netlink_sendmsg (net/netlink/af_netlink.c:1633 net/netlink/af_netlink.c:2329) [ 1567.774369] ? sched_clock_cpu (kernel/sched/clock.c:311) [ 1567.774369] ? netlink_unicast (net/netlink/af_netlink.c:2273) [ 1567.774369] ? netlink_unicast (net/netlink/af_netlink.c:2273) [ 1567.774369] sock_sendmsg (net/socket.c:614 net/socket.c:623) [ 1567.774369] sock_write_iter (net/socket.c:823) [ 1567.774369] ? sock_sendmsg (net/socket.c:806) [ 1567.774369] __vfs_write (fs/read_write.c:479 fs/read_write.c:491) [ 1567.774369] ? get_lock_stats (kernel/locking/lockdep.c:249) [ 1567.774369] ? default_llseek (fs/read_write.c:487) [ 1567.774369] ? vtime_account_user (kernel/sched/cputime.c:701) [ 1567.774369] ? rw_verify_area (fs/read_write.c:406 (discriminator 4)) [ 1567.774369] vfs_write (fs/read_write.c:539) [ 1567.774369] SyS_write (fs/read_write.c:586 fs/read_write.c:577) [ 1567.774369] ? SyS_read (fs/read_write.c:577) [ 1567.774369] ? __this_cpu_preempt_check (lib/smp_processor_id.c:63) [ 1567.774369] ? trace_hardirqs_on_caller (kernel/locking/lockdep.c:2594 kernel/locking/lockdep.c:2636) [ 1567.774369] ? trace_hardirqs_on_thunk (arch/x86/lib/thunk_64.S:42) [ 1567.774369] system_call_fastpath (arch/x86/kernel/entry_64.S:261) Fixes: 79930f5892e ("net: do not deplete pfmemalloc reserve") Signed-off-by: Eric Dumazet Reported-by: Sasha Levin Signed-off-by: David S. Miller --- include/linux/skbuff.h | 1 + net/core/skbuff.c | 31 ++++++++++++++++++++++--------- net/netlink/af_netlink.c | 6 ++---- 3 files changed, 25 insertions(+), 13 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 06793b598f44..66e374d62f64 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -773,6 +773,7 @@ bool skb_try_coalesce(struct sk_buff *to, struct sk_buff *from, struct sk_buff *__alloc_skb(unsigned int size, gfp_t priority, int flags, int node); +struct sk_buff *__build_skb(void *data, unsigned int frag_size); struct sk_buff *build_skb(void *data, unsigned int frag_size); static inline struct sk_buff *alloc_skb(unsigned int size, gfp_t priority) diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 456ead534e10..3cfff2a3d651 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -280,13 +280,14 @@ nodata: EXPORT_SYMBOL(__alloc_skb); /** - * build_skb - build a network buffer + * __build_skb - build a network buffer * @data: data buffer provided by caller - * @frag_size: size of fragment, or 0 if head was kmalloced + * @frag_size: size of data, or 0 if head was kmalloced * * Allocate a new &sk_buff. Caller provides space holding head and * skb_shared_info. @data must have been allocated by kmalloc() only if - * @frag_size is 0, otherwise data should come from the page allocator. + * @frag_size is 0, otherwise data should come from the page allocator + * or vmalloc() * The return is the new skb buffer. * On a failure the return is %NULL, and @data is not freed. * Notes : @@ -297,7 +298,7 @@ EXPORT_SYMBOL(__alloc_skb); * before giving packet to stack. * RX rings only contains data buffers, not full skbs. */ -struct sk_buff *build_skb(void *data, unsigned int frag_size) +struct sk_buff *__build_skb(void *data, unsigned int frag_size) { struct skb_shared_info *shinfo; struct sk_buff *skb; @@ -311,11 +312,6 @@ struct sk_buff *build_skb(void *data, unsigned int frag_size) memset(skb, 0, offsetof(struct sk_buff, tail)); skb->truesize = SKB_TRUESIZE(size); - if (frag_size) { - skb->head_frag = 1; - if (virt_to_head_page(data)->pfmemalloc) - skb->pfmemalloc = 1; - } atomic_set(&skb->users, 1); skb->head = data; skb->data = data; @@ -332,6 +328,23 @@ struct sk_buff *build_skb(void *data, unsigned int frag_size) return skb; } + +/* build_skb() is wrapper over __build_skb(), that specifically + * takes care of skb->head and skb->pfmemalloc + * This means that if @frag_size is not zero, then @data must be backed + * by a page fragment, not kmalloc() or vmalloc() + */ +struct sk_buff *build_skb(void *data, unsigned int frag_size) +{ + struct sk_buff *skb = __build_skb(data, frag_size); + + if (skb && frag_size) { + skb->head_frag = 1; + if (virt_to_head_page(data)->pfmemalloc) + skb->pfmemalloc = 1; + } + return skb; +} EXPORT_SYMBOL(build_skb); struct netdev_alloc_cache { diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 19909d0786a2..ec4adbdcb9b4 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -1629,13 +1629,11 @@ static struct sk_buff *netlink_alloc_large_skb(unsigned int size, if (data == NULL) return NULL; - skb = build_skb(data, size); + skb = __build_skb(data, size); if (skb == NULL) vfree(data); - else { - skb->head_frag = 0; + else skb->destructor = netlink_skb_destructor; - } return skb; } -- cgit v1.2.3 From 73459e2a1ada09a68c02cc5b73f3116fc8194b3d Mon Sep 17 00:00:00 2001 From: Paolo Bonzini Date: Thu, 23 Apr 2015 13:20:18 +0200 Subject: x86: pvclock: Really remove the sched notifier for cross-cpu migrations This reverts commits 0a4e6be9ca17c54817cf814b4b5aa60478c6df27 and 80f7fdb1c7f0f9266421f823964fd1962681f6ce. The task migration notifier was originally introduced in order to support the pvclock vsyscall with non-synchronized TSC, but KVM only supports it with synchronized TSC. Hence, on KVM the race condition is only needed due to a bad implementation on the host side, and even then it's so rare that it's mostly theoretical. As far as KVM is concerned it's possible to fix the host, avoiding the additional complexity in the vDSO and the (re)introduction of the task migration notifier. Xen, on the other hand, hasn't yet implemented vsyscall support at all, so we do not care about its plans for non-synchronized TSC. Reported-by: Peter Zijlstra Suggested-by: Marcelo Tosatti Signed-off-by: Paolo Bonzini --- arch/x86/include/asm/pvclock.h | 1 - arch/x86/kernel/pvclock.c | 44 ------------------------------------------ arch/x86/vdso/vclock_gettime.c | 34 ++++++++++++++------------------ include/linux/sched.h | 8 -------- kernel/sched/core.c | 15 -------------- 5 files changed, 15 insertions(+), 87 deletions(-) (limited to 'include/linux') diff --git a/arch/x86/include/asm/pvclock.h b/arch/x86/include/asm/pvclock.h index 25b1cc07d496..d6b078e9fa28 100644 --- a/arch/x86/include/asm/pvclock.h +++ b/arch/x86/include/asm/pvclock.h @@ -95,7 +95,6 @@ unsigned __pvclock_read_cycles(const struct pvclock_vcpu_time_info *src, struct pvclock_vsyscall_time_info { struct pvclock_vcpu_time_info pvti; - u32 migrate_count; } __attribute__((__aligned__(SMP_CACHE_BYTES))); #define PVTI_SIZE sizeof(struct pvclock_vsyscall_time_info) diff --git a/arch/x86/kernel/pvclock.c b/arch/x86/kernel/pvclock.c index e5ecd20e72dd..2f355d229a58 100644 --- a/arch/x86/kernel/pvclock.c +++ b/arch/x86/kernel/pvclock.c @@ -141,46 +141,7 @@ void pvclock_read_wallclock(struct pvclock_wall_clock *wall_clock, set_normalized_timespec(ts, now.tv_sec, now.tv_nsec); } -static struct pvclock_vsyscall_time_info *pvclock_vdso_info; - -static struct pvclock_vsyscall_time_info * -pvclock_get_vsyscall_user_time_info(int cpu) -{ - if (!pvclock_vdso_info) { - BUG(); - return NULL; - } - - return &pvclock_vdso_info[cpu]; -} - -struct pvclock_vcpu_time_info *pvclock_get_vsyscall_time_info(int cpu) -{ - return &pvclock_get_vsyscall_user_time_info(cpu)->pvti; -} - #ifdef CONFIG_X86_64 -static int pvclock_task_migrate(struct notifier_block *nb, unsigned long l, - void *v) -{ - struct task_migration_notifier *mn = v; - struct pvclock_vsyscall_time_info *pvti; - - pvti = pvclock_get_vsyscall_user_time_info(mn->from_cpu); - - /* this is NULL when pvclock vsyscall is not initialized */ - if (unlikely(pvti == NULL)) - return NOTIFY_DONE; - - pvti->migrate_count++; - - return NOTIFY_DONE; -} - -static struct notifier_block pvclock_migrate = { - .notifier_call = pvclock_task_migrate, -}; - /* * Initialize the generic pvclock vsyscall state. This will allocate * a/some page(s) for the per-vcpu pvclock information, set up a @@ -194,17 +155,12 @@ int __init pvclock_init_vsyscall(struct pvclock_vsyscall_time_info *i, WARN_ON (size != PVCLOCK_VSYSCALL_NR_PAGES*PAGE_SIZE); - pvclock_vdso_info = i; - for (idx = 0; idx <= (PVCLOCK_FIXMAP_END-PVCLOCK_FIXMAP_BEGIN); idx++) { __set_fixmap(PVCLOCK_FIXMAP_BEGIN + idx, __pa(i) + (idx*PAGE_SIZE), PAGE_KERNEL_VVAR); } - - register_task_migration_notifier(&pvclock_migrate); - return 0; } #endif diff --git a/arch/x86/vdso/vclock_gettime.c b/arch/x86/vdso/vclock_gettime.c index 40d2473836c9..9793322751e0 100644 --- a/arch/x86/vdso/vclock_gettime.c +++ b/arch/x86/vdso/vclock_gettime.c @@ -82,15 +82,18 @@ static notrace cycle_t vread_pvclock(int *mode) cycle_t ret; u64 last; u32 version; - u32 migrate_count; u8 flags; unsigned cpu, cpu1; /* - * When looping to get a consistent (time-info, tsc) pair, we - * also need to deal with the possibility we can switch vcpus, - * so make sure we always re-fetch time-info for the current vcpu. + * Note: hypervisor must guarantee that: + * 1. cpu ID number maps 1:1 to per-CPU pvclock time info. + * 2. that per-CPU pvclock time info is updated if the + * underlying CPU changes. + * 3. that version is increased whenever underlying CPU + * changes. + * */ do { cpu = __getcpu() & VGETCPU_CPU_MASK; @@ -99,27 +102,20 @@ static notrace cycle_t vread_pvclock(int *mode) * __getcpu() calls (Gleb). */ - /* Make sure migrate_count will change if we leave the VCPU. */ - do { - pvti = get_pvti(cpu); - migrate_count = pvti->migrate_count; - - cpu1 = cpu; - cpu = __getcpu() & VGETCPU_CPU_MASK; - } while (unlikely(cpu != cpu1)); + pvti = get_pvti(cpu); version = __pvclock_read_cycles(&pvti->pvti, &ret, &flags); /* * Test we're still on the cpu as well as the version. - * - We must read TSC of pvti's VCPU. - * - KVM doesn't follow the versioning protocol, so data could - * change before version if we left the VCPU. + * We could have been migrated just after the first + * vgetcpu but before fetching the version, so we + * wouldn't notice a version change. */ - smp_rmb(); - } while (unlikely((pvti->pvti.version & 1) || - pvti->pvti.version != version || - pvti->migrate_count != migrate_count)); + cpu1 = __getcpu() & VGETCPU_CPU_MASK; + } while (unlikely(cpu != cpu1 || + (pvti->pvti.version & 1) || + pvti->pvti.version != version)); if (unlikely(!(flags & PVCLOCK_TSC_STABLE_BIT))) *mode = VCLOCK_NONE; diff --git a/include/linux/sched.h b/include/linux/sched.h index 8222ae40ecb0..26a2e6122734 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -175,14 +175,6 @@ extern void get_iowait_load(unsigned long *nr_waiters, unsigned long *load); extern void calc_global_load(unsigned long ticks); extern void update_cpu_load_nohz(void); -/* Notifier for when a task gets migrated to a new CPU */ -struct task_migration_notifier { - struct task_struct *task; - int from_cpu; - int to_cpu; -}; -extern void register_task_migration_notifier(struct notifier_block *n); - extern unsigned long get_parent_ip(unsigned long addr); extern void dump_cpu_task(int cpu); diff --git a/kernel/sched/core.c b/kernel/sched/core.c index f9123a82cbb6..fe22f7510bce 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -1016,13 +1016,6 @@ void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags) rq_clock_skip_update(rq, true); } -static ATOMIC_NOTIFIER_HEAD(task_migration_notifier); - -void register_task_migration_notifier(struct notifier_block *n) -{ - atomic_notifier_chain_register(&task_migration_notifier, n); -} - #ifdef CONFIG_SMP void set_task_cpu(struct task_struct *p, unsigned int new_cpu) { @@ -1053,18 +1046,10 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu) trace_sched_migrate_task(p, new_cpu); if (task_cpu(p) != new_cpu) { - struct task_migration_notifier tmn; - if (p->sched_class->migrate_task_rq) p->sched_class->migrate_task_rq(p, new_cpu); p->se.nr_migrations++; perf_sw_event_sched(PERF_COUNT_SW_CPU_MIGRATIONS, 1, 0); - - tmn.task = p; - tmn.from_cpu = task_cpu(p); - tmn.to_cpu = new_cpu; - - atomic_notifier_call_chain(&task_migration_notifier, 0, &tmn); } __set_task_cpu(p, new_cpu); -- cgit v1.2.3 From ee136af4a064c2f61e2025873584d2c7ec93f4ae Mon Sep 17 00:00:00 2001 From: Hans de Goede Date: Tue, 21 Apr 2015 11:20:31 +0200 Subject: uas: Add US_FL_MAX_SECTORS_240 flag The usb-storage driver sets max_sectors = 240 in its scsi-host template, for uas we do not want to do that for all devices, but testing has shown that some devices need it. This commit adds a US_FL_MAX_SECTORS_240 flag for such devices, and implements support for it in uas.c, while at it it also adds support for US_FL_MAX_SECTORS_64 to uas.c. Cc: stable@vger.kernel.org # 3.16 Signed-off-by: Hans de Goede Acked-by: Alan Stern Signed-off-by: Greg Kroah-Hartman --- Documentation/kernel-parameters.txt | 2 ++ drivers/usb/storage/uas.c | 10 +++++++++- drivers/usb/storage/usb.c | 6 +++++- include/linux/usb_usual.h | 2 ++ 4 files changed, 18 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index f6befa9855c1..61ab1628a057 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -3787,6 +3787,8 @@ bytes respectively. Such letter suffixes can also be entirely omitted. READ_CAPACITY_16 command); f = NO_REPORT_OPCODES (don't use report opcodes command, uas only); + g = MAX_SECTORS_240 (don't transfer more than + 240 sectors at a time, uas only); h = CAPACITY_HEURISTICS (decrease the reported device capacity by one sector if the number is odd); diff --git a/drivers/usb/storage/uas.c b/drivers/usb/storage/uas.c index c6109c111aab..6d3122afeed3 100644 --- a/drivers/usb/storage/uas.c +++ b/drivers/usb/storage/uas.c @@ -759,7 +759,10 @@ static int uas_eh_bus_reset_handler(struct scsi_cmnd *cmnd) static int uas_slave_alloc(struct scsi_device *sdev) { - sdev->hostdata = (void *)sdev->host->hostdata; + struct uas_dev_info *devinfo = + (struct uas_dev_info *)sdev->host->hostdata; + + sdev->hostdata = devinfo; /* USB has unusual DMA-alignment requirements: Although the * starting address of each scatter-gather element doesn't matter, @@ -778,6 +781,11 @@ static int uas_slave_alloc(struct scsi_device *sdev) */ blk_queue_update_dma_alignment(sdev->request_queue, (512 - 1)); + if (devinfo->flags & US_FL_MAX_SECTORS_64) + blk_queue_max_hw_sectors(sdev->request_queue, 64); + else if (devinfo->flags & US_FL_MAX_SECTORS_240) + blk_queue_max_hw_sectors(sdev->request_queue, 240); + return 0; } diff --git a/drivers/usb/storage/usb.c b/drivers/usb/storage/usb.c index db6f6b5ec745..6c10c888f35f 100644 --- a/drivers/usb/storage/usb.c +++ b/drivers/usb/storage/usb.c @@ -479,7 +479,8 @@ void usb_stor_adjust_quirks(struct usb_device *udev, unsigned long *fflags) US_FL_SINGLE_LUN | US_FL_NO_WP_DETECT | US_FL_NO_READ_DISC_INFO | US_FL_NO_READ_CAPACITY_16 | US_FL_INITIAL_READ10 | US_FL_WRITE_CACHE | - US_FL_NO_ATA_1X | US_FL_NO_REPORT_OPCODES); + US_FL_NO_ATA_1X | US_FL_NO_REPORT_OPCODES | + US_FL_MAX_SECTORS_240); p = quirks; while (*p) { @@ -520,6 +521,9 @@ void usb_stor_adjust_quirks(struct usb_device *udev, unsigned long *fflags) case 'f': f |= US_FL_NO_REPORT_OPCODES; break; + case 'g': + f |= US_FL_MAX_SECTORS_240; + break; case 'h': f |= US_FL_CAPACITY_HEURISTICS; break; diff --git a/include/linux/usb_usual.h b/include/linux/usb_usual.h index a7f2604c5f25..7f5f78bd15ad 100644 --- a/include/linux/usb_usual.h +++ b/include/linux/usb_usual.h @@ -77,6 +77,8 @@ /* Cannot handle ATA_12 or ATA_16 CDBs */ \ US_FLAG(NO_REPORT_OPCODES, 0x04000000) \ /* Cannot handle MI_REPORT_SUPPORTED_OPERATION_CODES */ \ + US_FLAG(MAX_SECTORS_240, 0x08000000) \ + /* Sets max_sectors to 240 */ \ #define US_FLAG(name, value) US_FL_##name = value , enum { US_DO_ALL_FLAGS }; -- cgit v1.2.3 From b00f5c2dc01450bed9fed1a41a637fa917e03c5c Mon Sep 17 00:00:00 2001 From: Frederic Danis Date: Fri, 10 Apr 2015 15:13:05 +0200 Subject: tty: Re-add external interface for tty_set_termios() This is needed by Bluetooth hci_uart module to be able to change speed of Bluetooth controller and local UART. Signed-off-by: Frederic Danis Reviewed-by: Peter Hurley Cc: Marcel Holtmann Signed-off-by: Greg Kroah-Hartman --- drivers/tty/tty_ioctl.c | 3 ++- include/linux/tty.h | 1 + 2 files changed, 3 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/drivers/tty/tty_ioctl.c b/drivers/tty/tty_ioctl.c index 632fc8152061..8e53fe469664 100644 --- a/drivers/tty/tty_ioctl.c +++ b/drivers/tty/tty_ioctl.c @@ -536,7 +536,7 @@ EXPORT_SYMBOL(tty_termios_hw_change); * Locking: termios_rwsem */ -static int tty_set_termios(struct tty_struct *tty, struct ktermios *new_termios) +int tty_set_termios(struct tty_struct *tty, struct ktermios *new_termios) { struct ktermios old_termios; struct tty_ldisc *ld; @@ -569,6 +569,7 @@ static int tty_set_termios(struct tty_struct *tty, struct ktermios *new_termios) up_write(&tty->termios_rwsem); return 0; } +EXPORT_SYMBOL_GPL(tty_set_termios); /** * set_termios - set termios values for a tty diff --git a/include/linux/tty.h b/include/linux/tty.h index 358a337af598..fe5623c9af71 100644 --- a/include/linux/tty.h +++ b/include/linux/tty.h @@ -491,6 +491,7 @@ static inline speed_t tty_get_baud_rate(struct tty_struct *tty) extern void tty_termios_copy_hw(struct ktermios *new, struct ktermios *old); extern int tty_termios_hw_change(struct ktermios *a, struct ktermios *b); +extern int tty_set_termios(struct tty_struct *tty, struct ktermios *kt); extern struct tty_ldisc *tty_ldisc_ref(struct tty_struct *); extern void tty_ldisc_deref(struct tty_ldisc *); -- cgit v1.2.3 From 46c264daaaa569e24f8aba877d0fd8167c42a9a4 Mon Sep 17 00:00:00 2001 From: Nicolas Dichtel Date: Tue, 28 Apr 2015 18:33:49 +0200 Subject: bridge/nl: remove wrong use of NLM_F_MULTI NLM_F_MULTI must be used only when a NLMSG_DONE message is sent. In fact, it is sent only at the end of a dump. Libraries like libnl will wait forever for NLMSG_DONE. Fixes: e5a55a898720 ("net: create generic bridge ops") Fixes: 815cccbf10b2 ("ixgbe: add setlink, getlink support to ixgbe and ixgbevf") CC: John Fastabend CC: Sathya Perla CC: Subbu Seetharaman CC: Ajit Khaparde CC: Jeff Kirsher CC: intel-wired-lan@lists.osuosl.org CC: Jiri Pirko CC: Scott Feldman CC: Stephen Hemminger CC: bridge@lists.linux-foundation.org Signed-off-by: Nicolas Dichtel Signed-off-by: David S. Miller --- drivers/net/ethernet/emulex/benet/be_main.c | 5 +++-- drivers/net/ethernet/intel/i40e/i40e_main.c | 7 ++++--- drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 4 ++-- drivers/net/ethernet/rocker/rocker.c | 5 +++-- include/linux/netdevice.h | 6 ++++-- include/linux/rtnetlink.h | 2 +- net/bridge/br_netlink.c | 4 ++-- net/bridge/br_private.h | 2 +- net/core/rtnetlink.c | 12 +++++++----- 9 files changed, 27 insertions(+), 20 deletions(-) (limited to 'include/linux') diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c index fb0bc3c3620e..a6dcbf850c1f 100644 --- a/drivers/net/ethernet/emulex/benet/be_main.c +++ b/drivers/net/ethernet/emulex/benet/be_main.c @@ -4846,7 +4846,8 @@ err: } static int be_ndo_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq, - struct net_device *dev, u32 filter_mask) + struct net_device *dev, u32 filter_mask, + int nlflags) { struct be_adapter *adapter = netdev_priv(dev); int status = 0; @@ -4868,7 +4869,7 @@ static int be_ndo_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq, return ndo_dflt_bridge_getlink(skb, pid, seq, dev, hsw_mode == PORT_FWD_TYPE_VEPA ? BRIDGE_MODE_VEPA : BRIDGE_MODE_VEB, - 0, 0); + 0, 0, nlflags); } #ifdef CONFIG_BE2NET_VXLAN diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 24481cd7e59a..a54c14491e3b 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -8053,10 +8053,10 @@ static int i40e_ndo_bridge_setlink(struct net_device *dev, #ifdef HAVE_BRIDGE_FILTER static int i40e_ndo_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq, struct net_device *dev, - u32 __always_unused filter_mask) + u32 __always_unused filter_mask, int nlflags) #else static int i40e_ndo_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq, - struct net_device *dev) + struct net_device *dev, int nlflags) #endif /* HAVE_BRIDGE_FILTER */ { struct i40e_netdev_priv *np = netdev_priv(dev); @@ -8078,7 +8078,8 @@ static int i40e_ndo_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq, if (!veb) return 0; - return ndo_dflt_bridge_getlink(skb, pid, seq, dev, veb->bridge_mode); + return ndo_dflt_bridge_getlink(skb, pid, seq, dev, veb->bridge_mode, + nlflags); } #endif /* HAVE_BRIDGE_ATTRIBS */ diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index d3f4b0ceb3f7..5be12a00e1f4 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -8044,7 +8044,7 @@ static int ixgbe_ndo_bridge_setlink(struct net_device *dev, static int ixgbe_ndo_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq, struct net_device *dev, - u32 filter_mask) + u32 filter_mask, int nlflags) { struct ixgbe_adapter *adapter = netdev_priv(dev); @@ -8052,7 +8052,7 @@ static int ixgbe_ndo_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq, return 0; return ndo_dflt_bridge_getlink(skb, pid, seq, dev, - adapter->bridge_mode, 0, 0); + adapter->bridge_mode, 0, 0, nlflags); } static void *ixgbe_fwd_add(struct net_device *pdev, struct net_device *vdev) diff --git a/drivers/net/ethernet/rocker/rocker.c b/drivers/net/ethernet/rocker/rocker.c index a570a60533be..ec251531bd9f 100644 --- a/drivers/net/ethernet/rocker/rocker.c +++ b/drivers/net/ethernet/rocker/rocker.c @@ -4176,14 +4176,15 @@ static int rocker_port_bridge_setlink(struct net_device *dev, static int rocker_port_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq, struct net_device *dev, - u32 filter_mask) + u32 filter_mask, int nlflags) { struct rocker_port *rocker_port = netdev_priv(dev); u16 mode = BRIDGE_MODE_UNDEF; u32 mask = BR_LEARNING | BR_LEARNING_SYNC; return ndo_dflt_bridge_getlink(skb, pid, seq, dev, mode, - rocker_port->brport_flags, mask); + rocker_port->brport_flags, mask, + nlflags); } static int rocker_port_get_phys_port_name(struct net_device *dev, diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index dbad4d728b4b..1899c74a7127 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -977,7 +977,8 @@ typedef u16 (*select_queue_fallback_t)(struct net_device *dev, * int (*ndo_bridge_setlink)(struct net_device *dev, struct nlmsghdr *nlh, * u16 flags) * int (*ndo_bridge_getlink)(struct sk_buff *skb, u32 pid, u32 seq, - * struct net_device *dev, u32 filter_mask) + * struct net_device *dev, u32 filter_mask, + * int nlflags) * int (*ndo_bridge_dellink)(struct net_device *dev, struct nlmsghdr *nlh, * u16 flags); * @@ -1173,7 +1174,8 @@ struct net_device_ops { int (*ndo_bridge_getlink)(struct sk_buff *skb, u32 pid, u32 seq, struct net_device *dev, - u32 filter_mask); + u32 filter_mask, + int nlflags); int (*ndo_bridge_dellink)(struct net_device *dev, struct nlmsghdr *nlh, u16 flags); diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h index 2da5d1081ad9..7b8e260c4a27 100644 --- a/include/linux/rtnetlink.h +++ b/include/linux/rtnetlink.h @@ -122,5 +122,5 @@ extern int ndo_dflt_fdb_del(struct ndmsg *ndm, extern int ndo_dflt_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq, struct net_device *dev, u16 mode, - u32 flags, u32 mask); + u32 flags, u32 mask, int nlflags); #endif /* __LINUX_RTNETLINK_H */ diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index 0e4ddb81610d..4b5c236998ff 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -394,7 +394,7 @@ errout: * Dump information about all ports, in response to GETLINK */ int br_getlink(struct sk_buff *skb, u32 pid, u32 seq, - struct net_device *dev, u32 filter_mask) + struct net_device *dev, u32 filter_mask, int nlflags) { struct net_bridge_port *port = br_port_get_rtnl(dev); @@ -402,7 +402,7 @@ int br_getlink(struct sk_buff *skb, u32 pid, u32 seq, !(filter_mask & RTEXT_FILTER_BRVLAN_COMPRESSED)) return 0; - return br_fill_ifinfo(skb, port, pid, seq, RTM_NEWLINK, NLM_F_MULTI, + return br_fill_ifinfo(skb, port, pid, seq, RTM_NEWLINK, nlflags, filter_mask, dev); } diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 6ca0251cb478..3362c29400f1 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -828,7 +828,7 @@ void br_ifinfo_notify(int event, struct net_bridge_port *port); int br_setlink(struct net_device *dev, struct nlmsghdr *nlmsg, u16 flags); int br_dellink(struct net_device *dev, struct nlmsghdr *nlmsg, u16 flags); int br_getlink(struct sk_buff *skb, u32 pid, u32 seq, struct net_device *dev, - u32 filter_mask); + u32 filter_mask, int nlflags); #ifdef CONFIG_SYSFS /* br_sysfs_if.c */ diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 358d52a38533..666e0928ba40 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -2854,7 +2854,7 @@ static int brport_nla_put_flag(struct sk_buff *skb, u32 flags, u32 mask, int ndo_dflt_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq, struct net_device *dev, u16 mode, - u32 flags, u32 mask) + u32 flags, u32 mask, int nlflags) { struct nlmsghdr *nlh; struct ifinfomsg *ifm; @@ -2863,7 +2863,7 @@ int ndo_dflt_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq, u8 operstate = netif_running(dev) ? dev->operstate : IF_OPER_DOWN; struct net_device *br_dev = netdev_master_upper_dev_get(dev); - nlh = nlmsg_put(skb, pid, seq, RTM_NEWLINK, sizeof(*ifm), NLM_F_MULTI); + nlh = nlmsg_put(skb, pid, seq, RTM_NEWLINK, sizeof(*ifm), nlflags); if (nlh == NULL) return -EMSGSIZE; @@ -2969,7 +2969,8 @@ static int rtnl_bridge_getlink(struct sk_buff *skb, struct netlink_callback *cb) if (br_dev && br_dev->netdev_ops->ndo_bridge_getlink) { if (idx >= cb->args[0] && br_dev->netdev_ops->ndo_bridge_getlink( - skb, portid, seq, dev, filter_mask) < 0) + skb, portid, seq, dev, filter_mask, + NLM_F_MULTI) < 0) break; idx++; } @@ -2977,7 +2978,8 @@ static int rtnl_bridge_getlink(struct sk_buff *skb, struct netlink_callback *cb) if (ops->ndo_bridge_getlink) { if (idx >= cb->args[0] && ops->ndo_bridge_getlink(skb, portid, seq, dev, - filter_mask) < 0) + filter_mask, + NLM_F_MULTI) < 0) break; idx++; } @@ -3018,7 +3020,7 @@ static int rtnl_bridge_notify(struct net_device *dev) goto errout; } - err = dev->netdev_ops->ndo_bridge_getlink(skb, 0, 0, dev, 0); + err = dev->netdev_ops->ndo_bridge_getlink(skb, 0, 0, dev, 0, 0); if (err < 0) goto errout; -- cgit v1.2.3