From 694e096fd7c2a7d40760fc9c9dfc826bdd495ea4 Mon Sep 17 00:00:00 2001 From: Anna Schumaker Date: Wed, 13 Nov 2013 12:29:08 -0500 Subject: NFS: Enabling v4.2 should not recompile nfsd and lockd When CONFIG_NFS_V4_2 is toggled nfsd and lockd will be recompiled, instead of only the nfs client. This patch moves a small amount of code into the client directory to avoid unnecessary recompiles. Signed-off-by: Anna Schumaker Signed-off-by: Trond Myklebust --- include/linux/nfs4.h | 10 ---------- include/linux/nfs_fs.h | 18 ------------------ 2 files changed, 28 deletions(-) (limited to 'include/linux') diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h index c6f41b616965..ddd84871c0ad 100644 --- a/include/linux/nfs4.h +++ b/include/linux/nfs4.h @@ -410,16 +410,6 @@ enum lock_type4 { #define NFS4_VERSION 4 #define NFS4_MINOR_VERSION 0 -#if defined(CONFIG_NFS_V4_2) -#define NFS4_MAX_MINOR_VERSION 2 -#else -#if defined(CONFIG_NFS_V4_1) -#define NFS4_MAX_MINOR_VERSION 1 -#else -#define NFS4_MAX_MINOR_VERSION 0 -#endif /* CONFIG_NFS_V4_1 */ -#endif /* CONFIG_NFS_V4_2 */ - #define NFS4_DEBUG 1 /* Index of predefined Linux client operations */ diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 14a48207a304..48997374eaf0 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -506,24 +506,6 @@ extern const struct inode_operations nfs_referral_inode_operations; extern int nfs_mountpoint_expiry_timeout; extern void nfs_release_automount_timer(void); -/* - * linux/fs/nfs/nfs4proc.c - */ -#ifdef CONFIG_NFS_V4_SECURITY_LABEL -extern struct nfs4_label *nfs4_label_alloc(struct nfs_server *server, gfp_t flags); -static inline void nfs4_label_free(struct nfs4_label *label) -{ - if (label) { - kfree(label->label); - kfree(label); - } - return; -} -#else -static inline struct nfs4_label *nfs4_label_alloc(struct nfs_server *server, gfp_t flags) { return NULL; } -static inline void nfs4_label_free(void *label) {} -#endif - /* * linux/fs/nfs/unlink.c */ -- cgit v1.2.2 From ecf61c78bd787b9dfb4a6b1dfb7561c2a95c5c17 Mon Sep 17 00:00:00 2001 From: Michal Marek Date: Mon, 11 Nov 2013 14:40:35 +0100 Subject: PCI: Omit PCI ID macro strings to shorten quirk names Pasting the verbatim PCI_(VENDOR|DEVICE)_* macros in the __pci_fixup_* symbol names results in insanely long names such as __pci_fixup_resumePCI_VENDOR_ID_SERVERWORKSPCI_DEVICE_ID_SERVERWORKS_HT1000SBquirk_disable_broadcom_boot_interrupt When Link-Time Optimization adds its numeric suffix to such symbol, it overflows the namebuf[KSYM_NAME_LEN] array in kernel/kallsyms.c. Use the line number instead to create (nearly) unique symbol names. Reported-by: Joe Mario Signed-off-by: Michal Marek Signed-off-by: Bjorn Helgaas Cc: Andi Kleen --- include/linux/pci.h | 30 +++++++++++++++--------------- 1 file changed, 15 insertions(+), 15 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 1084a15175e0..eb8078aeadc8 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1567,65 +1567,65 @@ enum pci_fixup_pass { /* Anonymous variables would be nice... */ #define DECLARE_PCI_FIXUP_SECTION(section, name, vendor, device, class, \ class_shift, hook) \ - static const struct pci_fixup __pci_fixup_##name __used \ + static const struct pci_fixup __PASTE(__pci_fixup_##name,__LINE__) __used \ __attribute__((__section__(#section), aligned((sizeof(void *))))) \ = { vendor, device, class, class_shift, hook }; #define DECLARE_PCI_FIXUP_CLASS_EARLY(vendor, device, class, \ class_shift, hook) \ DECLARE_PCI_FIXUP_SECTION(.pci_fixup_early, \ - vendor##device##hook, vendor, device, class, class_shift, hook) + hook, vendor, device, class, class_shift, hook) #define DECLARE_PCI_FIXUP_CLASS_HEADER(vendor, device, class, \ class_shift, hook) \ DECLARE_PCI_FIXUP_SECTION(.pci_fixup_header, \ - vendor##device##hook, vendor, device, class, class_shift, hook) + hook, vendor, device, class, class_shift, hook) #define DECLARE_PCI_FIXUP_CLASS_FINAL(vendor, device, class, \ class_shift, hook) \ DECLARE_PCI_FIXUP_SECTION(.pci_fixup_final, \ - vendor##device##hook, vendor, device, class, class_shift, hook) + hook, vendor, device, class, class_shift, hook) #define DECLARE_PCI_FIXUP_CLASS_ENABLE(vendor, device, class, \ class_shift, hook) \ DECLARE_PCI_FIXUP_SECTION(.pci_fixup_enable, \ - vendor##device##hook, vendor, device, class, class_shift, hook) + hook, vendor, device, class, class_shift, hook) #define DECLARE_PCI_FIXUP_CLASS_RESUME(vendor, device, class, \ class_shift, hook) \ DECLARE_PCI_FIXUP_SECTION(.pci_fixup_resume, \ - resume##vendor##device##hook, vendor, device, class, \ + resume##hook, vendor, device, class, \ class_shift, hook) #define DECLARE_PCI_FIXUP_CLASS_RESUME_EARLY(vendor, device, class, \ class_shift, hook) \ DECLARE_PCI_FIXUP_SECTION(.pci_fixup_resume_early, \ - resume_early##vendor##device##hook, vendor, device, \ + resume_early##hook, vendor, device, \ class, class_shift, hook) #define DECLARE_PCI_FIXUP_CLASS_SUSPEND(vendor, device, class, \ class_shift, hook) \ DECLARE_PCI_FIXUP_SECTION(.pci_fixup_suspend, \ - suspend##vendor##device##hook, vendor, device, class, \ + suspend##hook, vendor, device, class, \ class_shift, hook) #define DECLARE_PCI_FIXUP_EARLY(vendor, device, hook) \ DECLARE_PCI_FIXUP_SECTION(.pci_fixup_early, \ - vendor##device##hook, vendor, device, PCI_ANY_ID, 0, hook) + hook, vendor, device, PCI_ANY_ID, 0, hook) #define DECLARE_PCI_FIXUP_HEADER(vendor, device, hook) \ DECLARE_PCI_FIXUP_SECTION(.pci_fixup_header, \ - vendor##device##hook, vendor, device, PCI_ANY_ID, 0, hook) + hook, vendor, device, PCI_ANY_ID, 0, hook) #define DECLARE_PCI_FIXUP_FINAL(vendor, device, hook) \ DECLARE_PCI_FIXUP_SECTION(.pci_fixup_final, \ - vendor##device##hook, vendor, device, PCI_ANY_ID, 0, hook) + hook, vendor, device, PCI_ANY_ID, 0, hook) #define DECLARE_PCI_FIXUP_ENABLE(vendor, device, hook) \ DECLARE_PCI_FIXUP_SECTION(.pci_fixup_enable, \ - vendor##device##hook, vendor, device, PCI_ANY_ID, 0, hook) + hook, vendor, device, PCI_ANY_ID, 0, hook) #define DECLARE_PCI_FIXUP_RESUME(vendor, device, hook) \ DECLARE_PCI_FIXUP_SECTION(.pci_fixup_resume, \ - resume##vendor##device##hook, vendor, device, \ + resume##hook, vendor, device, \ PCI_ANY_ID, 0, hook) #define DECLARE_PCI_FIXUP_RESUME_EARLY(vendor, device, hook) \ DECLARE_PCI_FIXUP_SECTION(.pci_fixup_resume_early, \ - resume_early##vendor##device##hook, vendor, device, \ + resume_early##hook, vendor, device, \ PCI_ANY_ID, 0, hook) #define DECLARE_PCI_FIXUP_SUSPEND(vendor, device, hook) \ DECLARE_PCI_FIXUP_SECTION(.pci_fixup_suspend, \ - suspend##vendor##device##hook, vendor, device, \ + suspend##hook, vendor, device, \ PCI_ANY_ID, 0, hook) #ifdef CONFIG_PCI_QUIRKS -- cgit v1.2.2 From 5a87182aa21d6d5d306840feab9321818dd3e2a3 Mon Sep 17 00:00:00 2001 From: Viresh Kumar Date: Wed, 27 Nov 2013 09:09:42 +0530 Subject: cpufreq: suspend governors on system suspend/hibernate This patch adds cpufreq suspend/resume calls to dpm_{suspend|resume}_noirq() for handling suspend/resume of cpufreq governors. Lan Tianyu (Intel) & Jinhyuk Choi (Broadcom) found anr issue where tunables configuration for clusters/sockets with non-boot CPUs was getting lost after suspend/resume, as we were notifying governors with CPUFREQ_GOV_POLICY_EXIT on removal of the last cpu for that policy and so deallocating memory for tunables. This is fixed by this patch as we don't allow any operation on governors after device suspend and before device resume now. Reported-and-tested-by: Lan Tianyu Reported-by: Jinhyuk Choi Signed-off-by: Viresh Kumar [rjw: Changelog, minor cleanups] Signed-off-by: Rafael J. Wysocki --- include/linux/cpufreq.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include/linux') diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index 5bd6ab9b0c27..91716658e9a1 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -272,6 +272,14 @@ cpufreq_verify_within_cpu_limits(struct cpufreq_policy *policy) policy->cpuinfo.max_freq); } +#ifdef CONFIG_CPU_FREQ +void cpufreq_suspend(void); +void cpufreq_resume(void); +#else +static inline void cpufreq_suspend(void) {} +static inline void cpufreq_resume(void) {} +#endif + /********************************************************************* * CPUFREQ NOTIFIER INTERFACE * *********************************************************************/ -- cgit v1.2.2 From e0d59733f6b1796b8d6692642c87d7dd862c3e3a Mon Sep 17 00:00:00 2001 From: Seiji Aguchi Date: Wed, 30 Oct 2013 15:27:26 -0400 Subject: efivars, efi-pstore: Hold off deletion of sysfs entry until the scan is completed Currently, when mounting pstore file system, a read callback of efi_pstore driver runs mutiple times as below. - In the first read callback, scan efivar_sysfs_list from head and pass a kmsg buffer of a entry to an upper pstore layer. - In the second read callback, rescan efivar_sysfs_list from the entry and pass another kmsg buffer to it. - Repeat the scan and pass until the end of efivar_sysfs_list. In this process, an entry is read across the multiple read function calls. To avoid race between the read and erasion, the whole process above is protected by a spinlock, holding in open() and releasing in close(). At the same time, kmemdup() is called to pass the buffer to pstore filesystem during it. And then, it causes a following lockdep warning. To make the dynamic memory allocation runnable without taking spinlock, holding off a deletion of sysfs entry if it happens while scanning it via efi_pstore, and deleting it after the scan is completed. To implement it, this patch introduces two flags, scanning and deleting, to efivar_entry. On the code basis, it seems that all the scanning and deleting logic is not needed because __efivars->lock are not dropped when reading from the EFI variable store. But, the scanning and deleting logic is still needed because an efi-pstore and a pstore filesystem works as follows. In case an entry(A) is found, the pointer is saved to psi->data. And efi_pstore_read() passes the entry(A) to a pstore filesystem by releasing __efivars->lock. And then, the pstore filesystem calls efi_pstore_read() again and the same entry(A), which is saved to psi->data, is used for resuming to scan a sysfs-list. So, to protect the entry(A), the logic is needed. [ 1.143710] ------------[ cut here ]------------ [ 1.144058] WARNING: CPU: 1 PID: 1 at kernel/lockdep.c:2740 lockdep_trace_alloc+0x104/0x110() [ 1.144058] DEBUG_LOCKS_WARN_ON(irqs_disabled_flags(flags)) [ 1.144058] Modules linked in: [ 1.144058] CPU: 1 PID: 1 Comm: systemd Not tainted 3.11.0-rc5 #2 [ 1.144058] 0000000000000009 ffff8800797e9ae0 ffffffff816614a5 ffff8800797e9b28 [ 1.144058] ffff8800797e9b18 ffffffff8105510d 0000000000000080 0000000000000046 [ 1.144058] 00000000000000d0 00000000000003af ffffffff81ccd0c0 ffff8800797e9b78 [ 1.144058] Call Trace: [ 1.144058] [] dump_stack+0x54/0x74 [ 1.144058] [] warn_slowpath_common+0x7d/0xa0 [ 1.144058] [] warn_slowpath_fmt+0x4c/0x50 [ 1.144058] [] ? vsscanf+0x57f/0x7b0 [ 1.144058] [] lockdep_trace_alloc+0x104/0x110 [ 1.144058] [] __kmalloc_track_caller+0x50/0x280 [ 1.144058] [] ? efi_pstore_read_func.part.1+0x12b/0x170 [ 1.144058] [] kmemdup+0x20/0x50 [ 1.144058] [] efi_pstore_read_func.part.1+0x12b/0x170 [ 1.144058] [] ? efi_pstore_read_func.part.1+0x170/0x170 [ 1.144058] [] efi_pstore_read_func+0xb4/0xe0 [ 1.144058] [] __efivar_entry_iter+0xfb/0x120 [ 1.144058] [] efi_pstore_read+0x3f/0x50 [ 1.144058] [] pstore_get_records+0x9a/0x150 [ 1.158207] [] ? selinux_d_instantiate+0x1c/0x20 [ 1.158207] [] ? parse_options+0x80/0x80 [ 1.158207] [] pstore_fill_super+0xa5/0xc0 [ 1.158207] [] mount_single+0xa2/0xd0 [ 1.158207] [] pstore_mount+0x18/0x20 [ 1.158207] [] mount_fs+0x39/0x1b0 [ 1.158207] [] ? __alloc_percpu+0x10/0x20 [ 1.158207] [] vfs_kern_mount+0x63/0xf0 [ 1.158207] [] do_mount+0x23e/0xa20 [ 1.158207] [] ? strndup_user+0x4b/0xf0 [ 1.158207] [] SyS_mount+0x83/0xc0 [ 1.158207] [] system_call_fastpath+0x16/0x1b [ 1.158207] ---[ end trace 61981bc62de9f6f4 ]--- Signed-off-by: Seiji Aguchi Tested-by: Madper Xie Cc: stable@kernel.org Signed-off-by: Matt Fleming --- include/linux/efi.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/efi.h b/include/linux/efi.h index bc5687d0f315..11ce6784a196 100644 --- a/include/linux/efi.h +++ b/include/linux/efi.h @@ -801,6 +801,8 @@ struct efivar_entry { struct efi_variable var; struct list_head list; struct kobject kobj; + bool scanning; + bool deleting; }; @@ -866,6 +868,8 @@ void efivar_run_worker(void); #if defined(CONFIG_EFI_VARS) || defined(CONFIG_EFI_VARS_MODULE) int efivars_sysfs_init(void); +#define EFIVARS_DATA_SIZE_MAX 1024 + #endif /* CONFIG_EFI_VARS */ #endif /* _LINUX_EFI_H */ -- cgit v1.2.2 From 23fd78d76415729b338ff1802a0066b4a62f7fb8 Mon Sep 17 00:00:00 2001 From: David Howells Date: Mon, 2 Dec 2013 11:24:18 +0000 Subject: KEYS: Fix multiple key add into associative array If sufficient keys (or keyrings) are added into a keyring such that a node in the associative array's tree overflows (each node has a capacity N, currently 16) and such that all N+1 keys have the same index key segment for that level of the tree (the level'th nibble of the index key), then assoc_array_insert() calls ops->diff_objects() to indicate at which bit position the two index keys vary. However, __key_link_begin() passes a NULL object to assoc_array_insert() with the intention of supplying the correct pointer later before we commit the change. This means that keyring_diff_objects() is given a NULL pointer as one of its arguments which it does not expect. This results in an oops like the attached. With the previous patch to fix the keyring hash function, this can be forced much more easily by creating a keyring and only adding keyrings to it. Add any other sort of key and a different insertion path is taken - all 16+1 objects must want to cluster in the same node slot. This can be tested by: r=`keyctl newring sandbox @s` for ((i=0; i<=16; i++)); do keyctl newring ring$i $r; done This should work fine, but oopses when the 17th keyring is added. Since ops->diff_objects() is always called with the first pointer pointing to the object to be inserted (ie. the NULL pointer), we can fix the problem by changing the to-be-inserted object pointer to point to the index key passed into assoc_array_insert() instead. Whilst we're at it, we also switch the arguments so that they are the same as for ->compare_object(). BUG: unable to handle kernel NULL pointer dereference at 0000000000000088 IP: [] hash_key_type_and_desc+0x18/0xb0 ... RIP: 0010:[] hash_key_type_and_desc+0x18/0xb0 ... Call Trace: [] keyring_diff_objects+0x21/0xd2 [] assoc_array_insert+0x3b6/0x908 [] __key_link_begin+0x78/0xe5 [] key_create_or_update+0x17d/0x36a [] SyS_add_key+0x123/0x183 [] tracesys+0xdd/0xe2 Signed-off-by: David Howells Tested-by: Stephen Gallagher --- include/linux/assoc_array.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/assoc_array.h b/include/linux/assoc_array.h index 9a193b84238a..a89df3be1686 100644 --- a/include/linux/assoc_array.h +++ b/include/linux/assoc_array.h @@ -41,10 +41,10 @@ struct assoc_array_ops { /* Is this the object we're looking for? */ bool (*compare_object)(const void *object, const void *index_key); - /* How different are two objects, to a bit position in their keys? (or - * -1 if they're the same) + /* How different is an object from an index key, to a bit position in + * their keys? (or -1 if they're the same) */ - int (*diff_objects)(const void *a, const void *b); + int (*diff_objects)(const void *object, const void *index_key); /* Method to free an object. */ void (*free_object)(void *object); -- cgit v1.2.2 From c7277090927a5e71871e799a355ed2940f6c8fc6 Mon Sep 17 00:00:00 2001 From: Eric Paris Date: Mon, 2 Dec 2013 11:24:19 +0000 Subject: security: shmem: implement kernel private shmem inodes We have a problem where the big_key key storage implementation uses a shmem backed inode to hold the key contents. Because of this detail of implementation LSM checks are being done between processes trying to read the keys and the tmpfs backed inode. The LSM checks are already being handled on the key interface level and should not be enforced at the inode level (since the inode is an implementation detail, not a part of the security model) This patch implements a new function shmem_kernel_file_setup() which returns the equivalent to shmem_file_setup() only the underlying inode has S_PRIVATE set. This means that all LSM checks for the inode in question are skipped. It should only be used for kernel internal operations where the inode is not exposed to userspace without proper LSM checking. It is possible that some other users of shmem_file_setup() should use the new interface, but this has not been explored. Reproducing this bug is a little bit difficult. The steps I used on Fedora are: (1) Turn off selinux enforcing: setenforce 0 (2) Create a huge key k=`dd if=/dev/zero bs=8192 count=1 | keyctl padd big_key test-key @s` (3) Access the key in another context: runcon system_u:system_r:httpd_t:s0-s0:c0.c1023 keyctl print $k >/dev/null (4) Examine the audit logs: ausearch -m AVC -i --subject httpd_t | audit2allow If the last command's output includes a line that looks like: allow httpd_t user_tmpfs_t:file { open read }; There was an inode check between httpd and the tmpfs filesystem. With this patch no such denial will be seen. (NOTE! you should clear your audit log if you have tested for this previously) (Please return you box to enforcing) Signed-off-by: Eric Paris Signed-off-by: David Howells cc: Hugh Dickins cc: linux-mm@kvack.org --- include/linux/shmem_fs.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h index 30aa0dc60d75..9d55438bc4ad 100644 --- a/include/linux/shmem_fs.h +++ b/include/linux/shmem_fs.h @@ -47,6 +47,8 @@ extern int shmem_init(void); extern int shmem_fill_super(struct super_block *sb, void *data, int silent); extern struct file *shmem_file_setup(const char *name, loff_t size, unsigned long flags); +extern struct file *shmem_kernel_file_setup(const char *name, loff_t size, + unsigned long flags); extern int shmem_zero_setup(struct vm_area_struct *); extern int shmem_lock(struct file *file, int lock, struct user_struct *user); extern void shmem_unlock_mapping(struct address_space *mapping); -- cgit v1.2.2 From 35773dac5f862cb1c82ea151eba3e2f6de51ec3e Mon Sep 17 00:00:00 2001 From: David Laight Date: Mon, 11 Nov 2013 12:26:54 +0000 Subject: usb: xhci: Link TRB must not occur within a USB payload burst Section 4.11.7.1 of rev 1.0 of the xhci specification states that a link TRB can only occur at a boundary between underlying USB frames (512 bytes for high speed devices). If this isn't done the USB frames aren't formatted correctly and, for example, the USB3 ethernet ax88179_178a card will stop sending (while still receiving) when running a netperf tcp transmit test with (say) and 8k buffer. This should be a candidate for stable, the ax88179_178a driver defaults to gso and tso enabled so it passes a lot of fragmented skb to the USB stack. Notes from Sarah: Discussion: http://marc.info/?l=linux-usb&m=138384509604981&w=2 This patch fixes a long-standing xHCI driver bug that was revealed by a change in 3.12 in the usb-net driver. Commit 638c5115a794981441246fa8fa5d95c1875af5ba "USBNET: support DMA SG" added support to use bulk endpoint scatter-gather (urb->sg). Only the USB ethernet drivers trigger this bug, because the mass storage driver sends sg list entries in page-sized chunks. This patch only fixes the issue for bulk endpoint scatter-gather. The problem will still occur for periodic endpoints, because hosts will interpret no-op transfers as a request to skip a service interval, which is not what we want. Luckily, the USB core isn't set up for scatter-gather on isochronous endpoints, and no USB drivers use scatter-gather for interrupt endpoints. Document this known limitation so that developers won't try to use urb->sg for interrupt endpoints until this issue is fixed. The more comprehensive fix would be to allow link TRBs in the middle of the endpoint ring and revert this patch, but that fix would touch too much code to be allowed in for stable. This patch should be backported to kernels as old as 3.12, that contain the commit 638c5115a794981441246fa8fa5d95c1875af5ba "USBNET: support DMA SG". Without this patch, the USB network device gets wedged, and stops sending packets. Mark Lord confirms this patch fixes the regression: http://marc.info/?l=linux-netdev&m=138487107625966&w=2 Signed-off-by: David Laight Signed-off-by: Sarah Sharp Tested-by: Mark Lord Cc: stable@vger.kernel.org --- include/linux/usb.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb.h b/include/linux/usb.h index 7454865ad148..512ab162832c 100644 --- a/include/linux/usb.h +++ b/include/linux/usb.h @@ -1264,6 +1264,8 @@ typedef void (*usb_complete_t)(struct urb *); * @sg: scatter gather buffer list, the buffer size of each element in * the list (except the last) must be divisible by the endpoint's * max packet size if no_sg_constraint isn't set in 'struct usb_bus' + * (FIXME: scatter-gather under xHCI is broken for periodic transfers. + * Do not use urb->sg for interrupt endpoints for now, only bulk.) * @num_mapped_sgs: (internal) number of mapped sg entries * @num_sgs: number of entries in the sg list * @transfer_buffer_length: How big is transfer_buffer. The transfer may -- cgit v1.2.2 From 8496e85c20e7836b3dec97780e40f420a3ae2801 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Sun, 1 Dec 2013 02:34:37 +0100 Subject: PCI / tg3: Give up chip reset and carrier loss handling if PCI device is not present Modify tg3_chip_reset() and tg3_close() to check if the PCI network adapter device is accessible at all in order to skip poking it or trying to handle a carrier loss in vain when that's not the case. Introduce a special PCI helper function pci_device_is_present() for this purpose. Of course, this uncovers the lack of the appropriate RTNL locking in tg3_suspend() and tg3_resume(), so add that locking in there too. These changes prevent tg3 from burning a CPU at 100% load level for solid several seconds after the Thunderbolt link is disconnected from a Matrox DS1 docking station. Signed-off-by: Rafael J. Wysocki Acked-by: Michael Chan Signed-off-by: David S. Miller --- include/linux/pci.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index 1084a15175e0..25a389566e47 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -960,6 +960,7 @@ void pci_update_resource(struct pci_dev *dev, int resno); int __must_check pci_assign_resource(struct pci_dev *dev, int i); int __must_check pci_reassign_resource(struct pci_dev *dev, int i, resource_size_t add_size, resource_size_t align); int pci_select_bars(struct pci_dev *dev, unsigned long flags); +bool pci_device_is_present(struct pci_dev *pdev); /* ROM control related routines */ int pci_enable_rom(struct pci_dev *pdev); -- cgit v1.2.2 From 9f740ffa8134aaef770f964485dac3ed6780d8b7 Mon Sep 17 00:00:00 2001 From: Srinivas Pandruvada Date: Wed, 27 Nov 2013 22:19:00 +0000 Subject: HID: hid-sensor-hub: Add logical min and max Exporting logical minimum and maximum of HID fields as part of the hid sensor attribute info. This can be used for range checking and to calculate enumeration base for NAry fields of HID sensor hub. Signed-off-by: Srinivas Pandruvada Signed-off-by: Jonathan Cameron --- include/linux/hid-sensor-hub.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hid-sensor-hub.h b/include/linux/hid-sensor-hub.h index 206a2af6b62b..b914ca3f57ba 100644 --- a/include/linux/hid-sensor-hub.h +++ b/include/linux/hid-sensor-hub.h @@ -42,6 +42,8 @@ struct hid_sensor_hub_attribute_info { s32 units; s32 unit_expo; s32 size; + s32 logical_minimum; + s32 logical_maximum; }; /** -- cgit v1.2.2 From 751d17e23a9f7c8e0bca5c0b2e8d39af655ecd2a Mon Sep 17 00:00:00 2001 From: Srinivas Pandruvada Date: Wed, 27 Nov 2013 22:19:00 +0000 Subject: iio: hid-sensors: Fix power and report state In the original HID sensor hub firmwares all Named array enums were to 0-based. But the most recent hub implemented as 1-based, because of the implementation by one of the major OS vendor. Using logical minimum for the field as the base of enum. So we add logical minimum to the selector values before setting those fields. Some sensor hub FWs already changed logical minimum from 0 to 1 to reflect this and hope every other vendor will follow. There is no easy way to add a common HID quirk for NAry elements, even if the standard specifies these field as NAry, the collection used to describe selectors is still just "logical". Signed-off-by: Srinivas Pandruvada Signed-off-by: Jonathan Cameron --- include/linux/hid-sensor-ids.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include/linux') diff --git a/include/linux/hid-sensor-ids.h b/include/linux/hid-sensor-ids.h index 4f945d3ed49f..8323775ac21d 100644 --- a/include/linux/hid-sensor-ids.h +++ b/include/linux/hid-sensor-ids.h @@ -117,4 +117,16 @@ #define HID_USAGE_SENSOR_PROP_REPORT_STATE 0x200316 #define HID_USAGE_SENSOR_PROY_POWER_STATE 0x200319 +/* Power state enumerations */ +#define HID_USAGE_SENSOR_PROP_POWER_STATE_UNDEFINED_ENUM 0x00 +#define HID_USAGE_SENSOR_PROP_POWER_STATE_D0_FULL_POWER_ENUM 0x01 +#define HID_USAGE_SENSOR_PROP_POWER_STATE_D1_LOW_POWER_ENUM 0x02 +#define HID_USAGE_SENSOR_PROP_POWER_STATE_D2_STANDBY_WITH_WAKE_ENUM 0x03 +#define HID_USAGE_SENSOR_PROP_POWER_STATE_D3_SLEEP_WITH_WAKE_ENUM 0x04 +#define HID_USAGE_SENSOR_PROP_POWER_STATE_D4_POWER_OFF_ENUM 0x05 + +/* Report State enumerations */ +#define HID_USAGE_SENSOR_PROP_REPORTING_STATE_NO_EVENTS_ENUM 0x00 +#define HID_USAGE_SENSOR_PROP_REPORTING_STATE_ALL_EVENTS_ENUM 0x01 + #endif -- cgit v1.2.2 From 7ce5a27f2ef8ed4f8f892f46391f933c0e2ac0f1 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Mon, 2 Dec 2013 17:26:05 -0500 Subject: Revert "net: Handle CHECKSUM_COMPLETE more adequately in pskb_trim_rcsum()." This reverts commit 018c5bba052b3a383d83cf0c756da0e7bc748397. It causes regressions for people using chips driven by the sungem driver. Suspicion is that the skb->csum value isn't being adjusted properly. The change also has a bug in that if __pskb_trim() fails, we'll leave a corruped skb->csum value in there. We would really need to revert it to it's original value in that case. Signed-off-by: David S. Miller --- include/linux/skbuff.h | 39 ++++++++++++++++++--------------------- 1 file changed, 18 insertions(+), 21 deletions(-) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index bec1cc7d5e3c..215b5ea1cb30 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -2263,6 +2263,24 @@ static inline void skb_postpull_rcsum(struct sk_buff *skb, unsigned char *skb_pull_rcsum(struct sk_buff *skb, unsigned int len); +/** + * pskb_trim_rcsum - trim received skb and update checksum + * @skb: buffer to trim + * @len: new length + * + * This is exactly the same as pskb_trim except that it ensures the + * checksum of received packets are still valid after the operation. + */ + +static inline int pskb_trim_rcsum(struct sk_buff *skb, unsigned int len) +{ + if (likely(len >= skb->len)) + return 0; + if (skb->ip_summed == CHECKSUM_COMPLETE) + skb->ip_summed = CHECKSUM_NONE; + return __pskb_trim(skb, len); +} + #define skb_queue_walk(queue, skb) \ for (skb = (queue)->next; \ skb != (struct sk_buff *)(queue); \ @@ -2360,27 +2378,6 @@ __wsum __skb_checksum(const struct sk_buff *skb, int offset, int len, __wsum skb_checksum(const struct sk_buff *skb, int offset, int len, __wsum csum); -/** - * pskb_trim_rcsum - trim received skb and update checksum - * @skb: buffer to trim - * @len: new length - * - * This is exactly the same as pskb_trim except that it ensures the - * checksum of received packets are still valid after the operation. - */ - -static inline int pskb_trim_rcsum(struct sk_buff *skb, unsigned int len) -{ - if (likely(len >= skb->len)) - return 0; - if (skb->ip_summed == CHECKSUM_COMPLETE) { - __wsum adj = skb_checksum(skb, len, skb->len - len, 0); - - skb->csum = csum_sub(skb->csum, adj); - } - return __pskb_trim(skb, len); -} - static inline void *skb_header_pointer(const struct sk_buff *skb, int offset, int len, void *buffer) { -- cgit v1.2.2 From 471e42ad148c05d091219096726d751684ebf918 Mon Sep 17 00:00:00 2001 From: Thomas Pugliese Date: Mon, 2 Dec 2013 15:39:45 -0600 Subject: usb: wusbcore: fix deadlock in wusbhc_gtk_rekey When multiple wireless USB devices are connected and one of the devices disconnects, the host will distribute a new group key to the remaining devicese using wusbhc_gtk_rekey. wusbhc_gtk_rekey takes the wusbhc->mutex and holds it while it submits a URB to set the new key. This causes a deadlock in wa_urb_enqueue when it calls a device lookup helper function that takes the same lock. This patch changes wusbhc_gtk_rekey to submit a work item to set the GTK so that the URB is submitted without holding wusbhc->mutex. Signed-off-by: Thomas Pugliese Signed-off-by: Greg Kroah-Hartman --- include/linux/usb/wusb.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/usb/wusb.h b/include/linux/usb/wusb.h index 0c4d4ca370ec..eeb28329fa3c 100644 --- a/include/linux/usb/wusb.h +++ b/include/linux/usb/wusb.h @@ -271,6 +271,8 @@ static inline u8 wusb_key_index(int index, int type, int originator) #define WUSB_KEY_INDEX_TYPE_GTK 2 #define WUSB_KEY_INDEX_ORIGINATOR_HOST 0 #define WUSB_KEY_INDEX_ORIGINATOR_DEVICE 1 +/* bits 0-3 used for the key index. */ +#define WUSB_KEY_INDEX_MAX 15 /* A CCM Nonce, defined in WUSB1.0[6.4.1] */ struct aes_ccm_nonce { -- cgit v1.2.2 From c9a9972b6f093e4e2f81f58892a7523df894144d Mon Sep 17 00:00:00 2001 From: Alexandre Courbot Date: Mon, 25 Nov 2013 18:34:24 +0900 Subject: gpiolib: add missing declarations Add declaration of 'struct of_phandle_args' to avoid the following warning: In file included from arch/arm/mach-tegra/board-paz00.c:21:0: include/linux/gpio/driver.h:102:17: warning: 'struct of_phandle_args' declared inside parameter list include/linux/gpio/driver.h:102:17: warning: its scope is only this definition or declaration, which is probably not what you want Also proactively add other definitions/includes that could be missing in other contexts. Signed-off-by: Alexandre Courbot Reported-by: Stephen Warren Reviewed-by: Mika Westerberg Signed-off-by: Linus Walleij --- include/linux/gpio/driver.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h index 82eac610ce1a..3ea2cf6b0e6c 100644 --- a/include/linux/gpio/driver.h +++ b/include/linux/gpio/driver.h @@ -2,9 +2,12 @@ #define __LINUX_GPIO_DRIVER_H #include +#include struct device; struct gpio_desc; +struct of_phandle_args; +struct device_node; struct seq_file; /** -- cgit v1.2.2 From b1a0fbfdde65dffd83c84c006f84fa12041907c5 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Wed, 4 Dec 2013 10:12:40 -0500 Subject: percpu: fix spurious sparse warnings from DEFINE_PER_CPU() When CONFIG_DEBUG_FORCE_WEAK_PER_CPU or CONFIG_ARCH_NEEDS_WEAK_PER_CPU is set, DEFINE_PER_CPU() explodes into cryptic series of definitions to still allow using "static" for percpu variables while keeping all per-cpu symbols unique in the kernel image which is required for weak symbols. This ultimately converts the actual symbol to global whether DEFINE_PER_CPU() is prefixed with static or not. Unfortunately, the macro forgot to add explicit extern declartion of the actual symbol ending up defining global symbol without preceding declaration for static definitions which naturally don't have matching DECLARE_PER_CPU(). The only ill effect is triggering of the following warnings. fs/inode.c:74:8: warning: symbol 'nr_inodes' was not declared. Should it be static? fs/inode.c:75:8: warning: symbol 'nr_unused' was not declared. Should it be static? Fix it by adding extern declaration in the DEFINE_PER_CPU() macro. Signed-off-by: Tejun Heo Reported-by: Wanlong Gao Tested-by: Wanlong Gao --- include/linux/percpu-defs.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/percpu-defs.h b/include/linux/percpu-defs.h index 57e890abe1f0..a5fc7d01aad6 100644 --- a/include/linux/percpu-defs.h +++ b/include/linux/percpu-defs.h @@ -69,6 +69,7 @@ __PCPU_DUMMY_ATTRS char __pcpu_scope_##name; \ extern __PCPU_DUMMY_ATTRS char __pcpu_unique_##name; \ __PCPU_DUMMY_ATTRS char __pcpu_unique_##name; \ + extern __PCPU_ATTRS(sec) __typeof__(type) name; \ __PCPU_ATTRS(sec) PER_CPU_DEF_ATTRIBUTES __weak \ __typeof__(type) name #else -- cgit v1.2.2 From 1431fb31ecbaba1b5718006128f0f2ed0b94e1c3 Mon Sep 17 00:00:00 2001 From: Paul Durrant Date: Tue, 3 Dec 2013 17:39:29 +0000 Subject: xen-netback: fix fragment detection in checksum setup The code to detect fragments in checksum_setup() was missing for IPv4 and too eager for IPv6. (It transpires that Windows seems to send IPv6 packets with a fragment header even if they are not a fragment - i.e. offset is zero, and M bit is not set). This patch also incorporates a fix to callers of maybe_pull_tail() where skb->network_header was being erroneously added to the length argument. Signed-off-by: Paul Durrant Signed-off-by: Zoltan Kiss Cc: Wei Liu Cc: Ian Campbell Cc: David Vrabel cc: David Miller Acked-by: Wei Liu Signed-off-by: David S. Miller --- include/linux/ipv6.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h index 5d89d1b808a6..c56c350324e4 100644 --- a/include/linux/ipv6.h +++ b/include/linux/ipv6.h @@ -4,6 +4,7 @@ #include #define ipv6_optlen(p) (((p)->hdrlen+1) << 3) +#define ipv6_authlen(p) (((p)->hdrlen+2) << 2) /* * This structure contains configuration options per IPv6 link. */ -- cgit v1.2.2 From 4fc9bbf98fd66f879e628d8537ba7c240be2b58e Mon Sep 17 00:00:00 2001 From: Khalid Aziz Date: Wed, 27 Nov 2013 15:19:25 -0700 Subject: PCI: Disable Bus Master only on kexec reboot Add a flag to tell the PCI subsystem that kernel is shutting down in preparation to kexec a kernel. Add code in PCI subsystem to use this flag to clear Bus Master bit on PCI devices only in case of kexec reboot. This fixes a power-off problem on Acer Aspire V5-573G and likely other machines and avoids any other issues caused by clearing Bus Master bit on PCI devices in normal shutdown path. The problem was introduced by b566a22c2332 ("PCI: disable Bus Master on PCI device shutdown"). This patch is based on discussion at http://marc.info/?l=linux-pci&m=138425645204355&w=2 Link: https://bugzilla.kernel.org/show_bug.cgi?id=63861 Reported-by: Chang Liu Signed-off-by: Khalid Aziz Signed-off-by: Bjorn Helgaas Acked-by: Konstantin Khlebnikov Cc: stable@vger.kernel.org # v3.5+ --- include/linux/kexec.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kexec.h b/include/linux/kexec.h index d78d28a733b1..5fd33dc1fe3a 100644 --- a/include/linux/kexec.h +++ b/include/linux/kexec.h @@ -198,6 +198,9 @@ extern u32 vmcoreinfo_note[VMCOREINFO_NOTE_SIZE/4]; extern size_t vmcoreinfo_size; extern size_t vmcoreinfo_max_size; +/* flag to track if kexec reboot is in progress */ +extern bool kexec_in_progress; + int __init parse_crashkernel(char *cmdline, unsigned long long system_ram, unsigned long long *crash_size, unsigned long long *crash_base); int parse_crashkernel_high(char *cmdline, unsigned long long system_ram, -- cgit v1.2.2 From 12205a4b79bef56ef618a4b7caa840c5c971cff2 Mon Sep 17 00:00:00 2001 From: "Rafael J. Wysocki" Date: Sun, 8 Dec 2013 01:04:17 +0100 Subject: Revert "cpufreq: suspend governors on system suspend/hibernate" MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Commit 5a87182aa21d (cpufreq: suspend governors on system suspend/hibernate) causes hibernation problems to happen on Bjørn Mork's and Paul Bolle's systems, so revert it. Fixes: 5a87182aa21d (cpufreq: suspend governors on system suspend/hibernate) Reported-by: Bjørn Mork Reported-by: Paul Bolle Signed-off-by: Rafael J. Wysocki --- include/linux/cpufreq.h | 8 -------- 1 file changed, 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cpufreq.h b/include/linux/cpufreq.h index ee5fe9d77ae8..dc196bbcf227 100644 --- a/include/linux/cpufreq.h +++ b/include/linux/cpufreq.h @@ -280,14 +280,6 @@ cpufreq_verify_within_cpu_limits(struct cpufreq_policy *policy) policy->cpuinfo.max_freq); } -#ifdef CONFIG_CPU_FREQ -void cpufreq_suspend(void); -void cpufreq_resume(void); -#else -static inline void cpufreq_suspend(void) {} -static inline void cpufreq_resume(void) {} -#endif - /********************************************************************* * CPUFREQ NOTIFIER INTERFACE * *********************************************************************/ -- cgit v1.2.2 From 503cf95c061a0551eb684da364509297efbe55d9 Mon Sep 17 00:00:00 2001 From: "H. Peter Anvin" Date: Tue, 10 Dec 2013 14:56:06 -0800 Subject: x86, build, icc: Remove uninitialized_var() from compiler-intel.h When compiling with icc, ends up included because the icc environment defines __GNUC__. Thus, we neither need nor want to have this macro defined in both compiler-gcc.h and compiler-intel.h, and the fact that they are inconsistent just makes the compiler spew warnings. Reported-by: Sunil K. Pandey Cc: Kevin B. Smith Signed-off-by: H. Peter Anvin Link: http://lkml.kernel.org/n/tip-0mbwou1zt7pafij09b897lg3@git.kernel.org Cc: --- include/linux/compiler-intel.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/compiler-intel.h b/include/linux/compiler-intel.h index 973ce10c40b6..dc1bd3dcf11f 100644 --- a/include/linux/compiler-intel.h +++ b/include/linux/compiler-intel.h @@ -28,8 +28,6 @@ #endif -#define uninitialized_var(x) x - #ifndef __HAVE_BUILTIN_BSWAP16__ /* icc has this, but it's called _bswap16 */ #define __HAVE_BUILTIN_BSWAP16__ -- cgit v1.2.2 From 12663bfc97c8b3fdb292428105dd92d563164050 Mon Sep 17 00:00:00 2001 From: Sasha Levin Date: Sat, 7 Dec 2013 17:26:27 -0500 Subject: net: unix: allow set_peek_off to fail unix_dgram_recvmsg() will hold the readlock of the socket until recv is complete. In the same time, we may try to setsockopt(SO_PEEK_OFF) which will hang until unix_dgram_recvmsg() will complete (which can take a while) without allowing us to break out of it, triggering a hung task spew. Instead, allow set_peek_off to fail, this way userspace will not hang. Signed-off-by: Sasha Levin Acked-by: Pavel Emelyanov Signed-off-by: David S. Miller --- include/linux/net.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/net.h b/include/linux/net.h index 4bcee94cef93..69be3e6079c8 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -181,7 +181,7 @@ struct proto_ops { int offset, size_t size, int flags); ssize_t (*splice_read)(struct socket *sock, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags); - void (*set_peek_off)(struct sock *sk, int val); + int (*set_peek_off)(struct sock *sk, int val); }; #define DECLARE_SOCKADDR(type, dst, src) \ -- cgit v1.2.2 From ba1f14fbe70965ae0fb1655a5275a62723f65b77 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Thu, 28 Nov 2013 14:26:41 +0100 Subject: sched: Remove PREEMPT_NEED_RESCHED from generic code While hunting a preemption issue with Alexander, Ben noticed that the currently generic PREEMPT_NEED_RESCHED stuff is horribly broken for load-store architectures. We currently rely on the IPI to fold TIF_NEED_RESCHED into PREEMPT_NEED_RESCHED, but when this IPI lands while we already have a load for the preempt-count but before the store, the store will erase the PREEMPT_NEED_RESCHED change. The current preempt-count only works on load-store archs because interrupts are assumed to be completely balanced wrt their preempt_count fiddling; the previous preempt_count load will match the preempt_count state after the interrupt and therefore nothing gets lost. This patch removes the PREEMPT_NEED_RESCHED usage from generic code and pushes it into x86 arch code; the generic code goes back to relying on TIF_NEED_RESCHED. Boot tested on x86_64 and compile tested on ppc64. Reported-by: Benjamin Herrenschmidt Reported-and-Tested-by: Alexander Graf Signed-off-by: Peter Zijlstra Cc: Linus Torvalds Link: http://lkml.kernel.org/r/20131128132641.GP10022@twins.programming.kicks-ass.net Signed-off-by: Ingo Molnar --- include/linux/sched.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 768b037dfacb..96d674ba3876 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -440,8 +440,6 @@ struct task_cputime { .sum_exec_runtime = 0, \ } -#define PREEMPT_ENABLED (PREEMPT_NEED_RESCHED) - #ifdef CONFIG_PREEMPT_COUNT #define PREEMPT_DISABLED (1 + PREEMPT_ENABLED) #else -- cgit v1.2.2 From be5e610c0fd6ef772cafb9e0bd4128134804aef3 Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 18 Nov 2013 18:27:06 +0100 Subject: math64: Add mul_u64_u32_shr() Introduce mul_u64_u32_shr() as proposed by Andy a while back; it allows using 64x64->128 muls on 64bit archs and recent GCC which defines __SIZEOF_INT128__ and __int128. (This new method will be used by the scheduler.) Signed-off-by: Peter Zijlstra Cc: fweisbec@gmail.com Cc: Andy Lutomirski Cc: Linus Torvalds Link: http://lkml.kernel.org/n/tip-hxjoeuzmrcaumR0uZwjpe2pv@git.kernel.org Signed-off-by: Ingo Molnar --- include/linux/math64.h | 30 ++++++++++++++++++++++++++++++ 1 file changed, 30 insertions(+) (limited to 'include/linux') diff --git a/include/linux/math64.h b/include/linux/math64.h index 69ed5f5e9f6e..c45c089bfdac 100644 --- a/include/linux/math64.h +++ b/include/linux/math64.h @@ -133,4 +133,34 @@ __iter_div_u64_rem(u64 dividend, u32 divisor, u64 *remainder) return ret; } +#if defined(CONFIG_ARCH_SUPPORTS_INT128) && defined(__SIZEOF_INT128__) + +#ifndef mul_u64_u32_shr +static inline u64 mul_u64_u32_shr(u64 a, u32 mul, unsigned int shift) +{ + return (u64)(((unsigned __int128)a * mul) >> shift); +} +#endif /* mul_u64_u32_shr */ + +#else + +#ifndef mul_u64_u32_shr +static inline u64 mul_u64_u32_shr(u64 a, u32 mul, unsigned int shift) +{ + u32 ah, al; + u64 ret; + + al = a; + ah = a >> 32; + + ret = ((u64)al * mul) >> shift; + if (ah) + ret += ((u64)ah * mul) << (32 - shift); + + return ret; +} +#endif /* mul_u64_u32_shr */ + +#endif + #endif /* _LINUX_MATH64_H */ -- cgit v1.2.2 From 9dbdb155532395ba000c5d5d187658b0e17e529f Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Mon, 18 Nov 2013 18:27:06 +0100 Subject: sched/fair: Rework sched_fair time accounting Christian suffers from a bad BIOS that wrecks his i5's TSC sync. This results in him occasionally seeing time going backwards - which crashes the scheduler ... Most of our time accounting can actually handle that except the most common one; the tick time update of sched_fair. There is a further problem with that code; previously we assumed that because we get a tick every TICK_NSEC our time delta could never exceed 32bits and math was simpler. However, ever since Frederic managed to get NO_HZ_FULL merged; this is no longer the case since now a task can run for a long time indeed without getting a tick. It only takes about ~4.2 seconds to overflow our u32 in nanoseconds. This means we not only need to better deal with time going backwards; but also means we need to be able to deal with large deltas. This patch reworks the entire code and uses mul_u64_u32_shr() as proposed by Andy a long while ago. We express our virtual time scale factor in a u32 multiplier and shift right and the 32bit mul_u64_u32_shr() implementation reduces to a single 32x32->64 multiply if the time delta is still short (common case). For 64bit a 64x64->128 multiply can be used if ARCH_SUPPORTS_INT128. Reported-and-Tested-by: Christian Engelmayer Signed-off-by: Peter Zijlstra Cc: fweisbec@gmail.com Cc: Paul Turner Cc: Stanislaw Gruszka Cc: Andy Lutomirski Cc: Linus Torvalds Cc: Andrew Morton Link: http://lkml.kernel.org/r/20131118172706.GI3866@twins.programming.kicks-ass.net Signed-off-by: Ingo Molnar --- include/linux/sched.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/sched.h b/include/linux/sched.h index 96d674ba3876..53f97eb8dbc7 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -930,7 +930,8 @@ struct pipe_inode_info; struct uts_namespace; struct load_weight { - unsigned long weight, inv_weight; + unsigned long weight; + u32 inv_weight; }; struct sched_avg { -- cgit v1.2.2 From 4bd7b5127bd02c12c1cc837a7a0b6ce295eb2505 Mon Sep 17 00:00:00 2001 From: Sergei Shtylyov Date: Tue, 10 Dec 2013 02:20:41 +0300 Subject: micrel: add support for KSZ8041RNLI Renesas R-Car development boards use KSZ8041RNLI PHY which for some reason has ID of 0x00221537 that is not documented for KSZ8041-family PHYs and does not match the documented ID of 0x0022151x (where 'x' is the revision). We have to add the new #define PHY_ID_* and new ksphy_driver[] entry, almost the same as KSZ8041 one, differing only in the 'phy_id' and 'name' fields. Signed-off-by: Sergei Shtylyov Tested-by: Geert Uytterhoeven Signed-off-by: David S. Miller --- include/linux/micrel_phy.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/micrel_phy.h b/include/linux/micrel_phy.h index ad05ce60c1c9..2e5b194b9b19 100644 --- a/include/linux/micrel_phy.h +++ b/include/linux/micrel_phy.h @@ -22,6 +22,8 @@ #define PHY_ID_KSZ8021 0x00221555 #define PHY_ID_KSZ8031 0x00221556 #define PHY_ID_KSZ8041 0x00221510 +/* undocumented */ +#define PHY_ID_KSZ8041RNLI 0x00221537 #define PHY_ID_KSZ8051 0x00221550 /* same id: ks8001 Rev. A/B, and ks8721 Rev 3. */ #define PHY_ID_KSZ8001 0x0022161A -- cgit v1.2.2 From a5c21dcefa1c3d759457a604b3cfc4af29c8713f Mon Sep 17 00:00:00 2001 From: Will Deacon Date: Thu, 12 Dec 2013 17:40:21 +0000 Subject: dcache: allow word-at-a-time name hashing with big-endian CPUs When explicitly hashing the end of a string with the word-at-a-time interface, we have to be careful which end of the word we pick up. On big-endian CPUs, the upper-bits will contain the data we're after, so ensure we generate our masks accordingly (and avoid hashing whatever random junk may have been sitting after the string). This patch adds a new dcache helper, bytemask_from_count, which creates a mask appropriate for the CPU endianness. Cc: Al Viro Signed-off-by: Will Deacon Signed-off-by: Linus Torvalds --- include/linux/dcache.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/dcache.h b/include/linux/dcache.h index 57e87e749a48..bf72e9ac6de0 100644 --- a/include/linux/dcache.h +++ b/include/linux/dcache.h @@ -29,8 +29,10 @@ struct vfsmount; /* The hash is always the low bits of hash_len */ #ifdef __LITTLE_ENDIAN #define HASH_LEN_DECLARE u32 hash; u32 len; + #define bytemask_from_count(cnt) (~(~0ul << (cnt)*8)) #else #define HASH_LEN_DECLARE u32 len; u32 hash; + #define bytemask_from_count(cnt) (~(~0ul >> (cnt)*8)) #endif /* -- cgit v1.2.2 From a0a9663dd2146d54339237764e1bfc60e8a39328 Mon Sep 17 00:00:00 2001 From: Sebastian Siewior Date: Thu, 12 Dec 2013 10:15:59 +0100 Subject: net: make neigh_priv_len in struct net_device 16bit instead of 8bit neigh_priv_len is defined as u8. With all debug enabled struct ipoib_neigh has 200 bytes. The largest part is sk_buff_head with 96 bytes and here the spinlock with 72 bytes. The size value still fits in this u8 leaving some room for more. On -RT struct ipoib_neigh put on weight and has 392 bytes. The main reason is sk_buff_head with 288 and the fatty here is spinlock with 192 bytes. This does no longer fit into into neigh_priv_len and gcc complains. This patch changes neigh_priv_len from being 8bit to 16bit. Since the following element (dev_id) is 16bit followed by a spinlock which is aligned, the struct remains with a total size of 3200 (allmodconfig) / 2048 (with as much debug off as possible) bytes on x86-64. On x86-32 the struct is 1856 (allmodconfig) / 1216 (with as much debug off as possible) bytes long. The numbers were gained with and without the patch to prove that this change does not increase the size of the struct. Cc: Steven Rostedt Cc: Thomas Gleixner Signed-off-by: Sebastian Andrzej Siewior Signed-off-by: David S. Miller --- include/linux/netdevice.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 7f0ed423a360..d9a550bf3e8e 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1255,7 +1255,7 @@ struct net_device { unsigned char perm_addr[MAX_ADDR_LEN]; /* permanent hw address */ unsigned char addr_assign_type; /* hw address assignment type */ unsigned char addr_len; /* hardware address length */ - unsigned char neigh_priv_len; + unsigned short neigh_priv_len; unsigned short dev_id; /* Used to differentiate devices * that share the same link * layer address -- cgit v1.2.2 From f40386a4e976acb2bd3e0f9ead11e8e769acbe98 Mon Sep 17 00:00:00 2001 From: Naoya Horiguchi Date: Thu, 12 Dec 2013 17:12:19 -0800 Subject: include/linux/hugetlb.h: make isolate_huge_page() an inline With CONFIG_HUGETLBFS=n: mm/migrate.c: In function `do_move_page_to_node_array': include/linux/hugetlb.h:140:33: warning: statement with no effect [-Wunused-value] #define isolate_huge_page(p, l) false ^ mm/migrate.c:1170:4: note: in expansion of macro `isolate_huge_page' isolate_huge_page(page, &pagelist); Reported-by: Borislav Petkov Tested-by: Borislav Petkov Signed-off-by: Naoya Horiguchi Acked-by: David Rientjes Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/hugetlb.h | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index 9649ff0c63f8..bd7e98752222 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -142,7 +142,10 @@ static inline int dequeue_hwpoisoned_huge_page(struct page *page) return 0; } -#define isolate_huge_page(p, l) false +static inline bool isolate_huge_page(struct page *page, struct list_head *list) +{ + return false; +} #define putback_active_hugepage(p) do {} while (0) #define is_hugepage_active(x) false -- cgit v1.2.2 From 386e79066f04850352f144e67edfd5b636c0f95c Mon Sep 17 00:00:00 2001 From: Axel Lin Date: Thu, 12 Dec 2013 17:12:24 -0800 Subject: include/linux/kernel.h: make might_fault() a nop for !MMU The machine cannot fault if !MUU, so make might_fault() a nop for !MMU. This fixes below build error if !CONFIG_MMU && (CONFIG_PROVE_LOCKING=y || CONFIG_DEBUG_ATOMIC_SLEEP=y): arch/arm/kernel/built-in.o: In function `arch_ptrace': arch/arm/kernel/ptrace.c:852: undefined reference to `might_fault' arch/arm/kernel/built-in.o: In function `restore_sigframe': arch/arm/kernel/signal.c:173: undefined reference to `might_fault' ... arch/arm/kernel/built-in.o:arch/arm/kernel/signal.c:177: more undefined references to `might_fault' follow make: *** [vmlinux] Error 1 Signed-off-by: Axel Lin Acked-by: Michael S. Tsirkin Cc: Peter Zijlstra Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/kernel.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/kernel.h b/include/linux/kernel.h index d4e98d13eff4..ecb87544cc5d 100644 --- a/include/linux/kernel.h +++ b/include/linux/kernel.h @@ -193,7 +193,8 @@ extern int _cond_resched(void); (__x < 0) ? -__x : __x; \ }) -#if defined(CONFIG_PROVE_LOCKING) || defined(CONFIG_DEBUG_ATOMIC_SLEEP) +#if defined(CONFIG_MMU) && \ + (defined(CONFIG_PROVE_LOCKING) || defined(CONFIG_DEBUG_ATOMIC_SLEEP)) void might_fault(void); #else static inline void might_fault(void) { } -- cgit v1.2.2 From 3e1e4a5f3a324502c27c4e8808e06ac2ea842360 Mon Sep 17 00:00:00 2001 From: Krzysztof Kozlowski Date: Thu, 12 Dec 2013 17:12:31 -0800 Subject: mfd/rtc: s5m: fix register updating by adding regmap for RTC Rename old regmap field of "struct sec_pmic_dev" to "regmap_pmic" and add new regmap for RTC. On S5M8767A registers were not properly updated and read due to usage of the same regmap as the PMIC. This could be observed in various hangs, e.g. in infinite loop during waiting for UDR field change. On this chip family the RTC has different I2C address than PMIC so additional regmap is needed. Signed-off-by: Krzysztof Kozlowski Signed-off-by: Kyungmin Park Reviewed-by: Mark Brown Acked-by: Sangbeom Kim Cc: Samuel Ortiz Cc: Lee Jones Cc: Liam Girdwood Cc: Alessandro Zummo Cc: Marek Szyprowski Cc: Geert Uytterhoeven Cc: Kyungmin Park Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mfd/samsung/core.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mfd/samsung/core.h b/include/linux/mfd/samsung/core.h index 2d0c9071bcfb..cab2dd279076 100644 --- a/include/linux/mfd/samsung/core.h +++ b/include/linux/mfd/samsung/core.h @@ -39,7 +39,8 @@ enum sec_device_type { struct sec_pmic_dev { struct device *dev; struct sec_platform_data *pdata; - struct regmap *regmap; + struct regmap *regmap_pmic; + struct regmap *regmap_rtc; struct i2c_client *i2c; struct i2c_client *rtc; -- cgit v1.2.2 From f78dea064c5f7de07de4912a6e5136dbc443d614 Mon Sep 17 00:00:00 2001 From: Marc Carino Date: Mon, 16 Dec 2013 18:15:53 -0800 Subject: libata: implement ATA_HORKAGE_NO_NCQ_TRIM and apply it to Micro M500 SSDs Certain drives cannot handle queued TRIM commands properly, even though support is indicated in the IDENTIFY DEVICE buffer. This patch allows for disabling the commands for the affected drives and apply it to the Micron/Crucial M500 SSDs which exhibit incorrect protocol behavior when issued queued TRIM commands, which could lead to silent data corruption. tj: Merged two unnecessarily split patches and made minor edits including shortening horkage name. Signed-off-by: Marc Carino Signed-off-by: Tejun Heo Link: http://lkml.kernel.org/g/1387246554-7311-1-git-send-email-marc.ceeeee@gmail.com Cc: stable@vger.kernel.org # 3.12+ --- include/linux/libata.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/libata.h b/include/linux/libata.h index 0e23c26485f4..9b503376738f 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -418,6 +418,7 @@ enum { ATA_HORKAGE_DUMP_ID = (1 << 16), /* dump IDENTIFY data */ ATA_HORKAGE_MAX_SEC_LBA48 = (1 << 17), /* Set max sects to 65535 */ ATA_HORKAGE_ATAPI_DMADIR = (1 << 18), /* device requires dmadir */ + ATA_HORKAGE_NO_NCQ_TRIM = (1 << 19), /* don't use queued TRIM */ /* DMA mask for user DMA control: User visible values; DO NOT renumber */ -- cgit v1.2.2 From 85328240c625f322af9f69c7b60e619717101d77 Mon Sep 17 00:00:00 2001 From: John Fastabend Date: Tue, 26 Nov 2013 06:33:52 +0000 Subject: net: allow netdev_all_upper_get_next_dev_rcu with rtnl lock held It is useful to be able to walk all upper devices when bringing a device online where the RTNL lock is held. In this case it is safe to walk the all_adj_list because the RTNL lock is used to protect the write side as well. This patch adds a check to see if the rtnl lock is held before throwing a warning in netdev_all_upper_get_next_dev_rcu(). Also because we now have a call site for lockdep_rtnl_is_held() outside COFIG_LOCK_PROVING an inline definition returning 1 is needed. Similar to the rcu_read_lock_is_held(). Fixes: 2a47fa45d4df ("ixgbe: enable l2 forwarding acceleration for macvlans") CC: Veaceslav Falico Reported-by: Yuanhan Liu Signed-off-by: John Fastabend Tested-by: Phil Schmitt Signed-off-by: Jeff Kirsher --- include/linux/rtnetlink.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/rtnetlink.h b/include/linux/rtnetlink.h index 939428ad25ac..8e3e66ac0a52 100644 --- a/include/linux/rtnetlink.h +++ b/include/linux/rtnetlink.h @@ -24,6 +24,11 @@ extern int rtnl_trylock(void); extern int rtnl_is_locked(void); #ifdef CONFIG_PROVE_LOCKING extern int lockdep_rtnl_is_held(void); +#else +static inline int lockdep_rtnl_is_held(void) +{ + return 1; +} #endif /* #ifdef CONFIG_PROVE_LOCKING */ /** -- cgit v1.2.2 From 0e3da5bb8da45890b1dc413404e0f978ab71173e Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Timo=20Ter=C3=A4s?= Date: Mon, 16 Dec 2013 11:02:09 +0200 Subject: ip_gre: fix msg_name parsing for recvfrom/recvmsg MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit ipgre_header_parse() needs to parse the tunnel's ip header and it uses mac_header to locate the iphdr. This got broken when gre tunneling was refactored as mac_header is no longer updated to point to iphdr. Introduce skb_pop_mac_header() helper to do the mac_header assignment and use it in ipgre_rcv() to fix msg_name parsing. Bug introduced in commit c54419321455 (GRE: Refactor GRE tunneling code.) Cc: Pravin B Shelar Signed-off-by: Timo Teräs Signed-off-by: David S. Miller --- include/linux/skbuff.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 215b5ea1cb30..6aae83890520 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1638,6 +1638,11 @@ static inline void skb_set_mac_header(struct sk_buff *skb, const int offset) skb->mac_header += offset; } +static inline void skb_pop_mac_header(struct sk_buff *skb) +{ + skb->mac_header = skb->network_header; +} + static inline void skb_probe_transport_header(struct sk_buff *skb, const int offset_hint) { -- cgit v1.2.2 From c97102ba96324da330078ad8619ba4dfe840dbe3 Mon Sep 17 00:00:00 2001 From: Vivek Goyal Date: Wed, 18 Dec 2013 17:08:31 -0800 Subject: kexec: migrate to reboot cpu Commit 1b3a5d02ee07 ("reboot: move arch/x86 reboot= handling to generic kernel") moved reboot= handling to generic code. In the process it also removed the code in native_machine_shutdown() which are moving reboot process to reboot_cpu/cpu0. I guess that thought must have been that all reboot paths are calling migrate_to_reboot_cpu(), so we don't need this special handling. But kexec reboot path (kernel_kexec()) is not calling migrate_to_reboot_cpu() so above change broke kexec. Now reboot can happen on non-boot cpu and when INIT is sent in second kerneo to bring up BP, it brings down the machine. So start calling migrate_to_reboot_cpu() in kexec reboot path to avoid this problem. Bisected by WANG Chao. Reported-by: Matthew Whitehead Reported-by: Dave Young Signed-off-by: Vivek Goyal Tested-by: Baoquan He Tested-by: WANG Chao Acked-by: H. Peter Anvin Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/reboot.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/reboot.h b/include/linux/reboot.h index 8e00f9f6f963..9e7db9e73cc1 100644 --- a/include/linux/reboot.h +++ b/include/linux/reboot.h @@ -43,6 +43,7 @@ extern int unregister_reboot_notifier(struct notifier_block *); * Architecture-specific implementations of sys_reboot commands. */ +extern void migrate_to_reboot_cpu(void); extern void machine_restart(char *cmd); extern void machine_halt(void); extern void machine_power_off(void); -- cgit v1.2.2 From de466bd628e8d663fdf3f791bc8db318ee85c714 Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Wed, 18 Dec 2013 17:08:42 -0800 Subject: mm: numa: avoid unnecessary disruption of NUMA hinting during migration do_huge_pmd_numa_page() handles the case where there is parallel THP migration. However, by the time it is checked the NUMA hinting information has already been disrupted. This patch adds an earlier check with some helpers. Signed-off-by: Mel Gorman Reviewed-by: Rik van Riel Cc: Alex Thorlton Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/migrate.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/migrate.h b/include/linux/migrate.h index f5096b58b20d..b7717d74da7f 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -90,10 +90,19 @@ static inline int migrate_huge_page_move_mapping(struct address_space *mapping, #endif /* CONFIG_MIGRATION */ #ifdef CONFIG_NUMA_BALANCING +extern bool pmd_trans_migrating(pmd_t pmd); +extern void wait_migrate_huge_page(struct anon_vma *anon_vma, pmd_t *pmd); extern int migrate_misplaced_page(struct page *page, struct vm_area_struct *vma, int node); extern bool migrate_ratelimited(int node); #else +static inline bool pmd_trans_migrating(pmd_t pmd) +{ + return false; +} +static inline void wait_migrate_huge_page(struct anon_vma *anon_vma, pmd_t *pmd) +{ +} static inline int migrate_misplaced_page(struct page *page, struct vm_area_struct *vma, int node) { -- cgit v1.2.2 From 20841405940e7be0617612d521e206e4b6b325db Mon Sep 17 00:00:00 2001 From: Rik van Riel Date: Wed, 18 Dec 2013 17:08:44 -0800 Subject: mm: fix TLB flush race between migration, and change_protection_range There are a few subtle races, between change_protection_range (used by mprotect and change_prot_numa) on one side, and NUMA page migration and compaction on the other side. The basic race is that there is a time window between when the PTE gets made non-present (PROT_NONE or NUMA), and the TLB is flushed. During that time, a CPU may continue writing to the page. This is fine most of the time, however compaction or the NUMA migration code may come in, and migrate the page away. When that happens, the CPU may continue writing, through the cached translation, to what is no longer the current memory location of the process. This only affects x86, which has a somewhat optimistic pte_accessible. All other architectures appear to be safe, and will either always flush, or flush whenever there is a valid mapping, even with no permissions (SPARC). The basic race looks like this: CPU A CPU B CPU C load TLB entry make entry PTE/PMD_NUMA fault on entry read/write old page start migrating page change PTE/PMD to new page read/write old page [*] flush TLB reload TLB from new entry read/write new page lose data [*] the old page may belong to a new user at this point! The obvious fix is to flush remote TLB entries, by making sure that pte_accessible aware of the fact that PROT_NONE and PROT_NUMA memory may still be accessible if there is a TLB flush pending for the mm. This should fix both NUMA migration and compaction. [mgorman@suse.de: fix build] Signed-off-by: Rik van Riel Signed-off-by: Mel Gorman Cc: Alex Thorlton Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm_types.h | 44 ++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 44 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index bd299418a934..e5c49c30460f 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -442,6 +442,14 @@ struct mm_struct { /* numa_scan_seq prevents two threads setting pte_numa */ int numa_scan_seq; +#endif +#if defined(CONFIG_NUMA_BALANCING) || defined(CONFIG_COMPACTION) + /* + * An operation with batched TLB flushing is going on. Anything that + * can move process memory needs to flush the TLB when moving a + * PROT_NONE or PROT_NUMA mapped page. + */ + bool tlb_flush_pending; #endif struct uprobes_state uprobes_state; }; @@ -459,4 +467,40 @@ static inline cpumask_t *mm_cpumask(struct mm_struct *mm) return mm->cpu_vm_mask_var; } +#if defined(CONFIG_NUMA_BALANCING) || defined(CONFIG_COMPACTION) +/* + * Memory barriers to keep this state in sync are graciously provided by + * the page table locks, outside of which no page table modifications happen. + * The barriers below prevent the compiler from re-ordering the instructions + * around the memory barriers that are already present in the code. + */ +static inline bool mm_tlb_flush_pending(struct mm_struct *mm) +{ + barrier(); + return mm->tlb_flush_pending; +} +static inline void set_tlb_flush_pending(struct mm_struct *mm) +{ + mm->tlb_flush_pending = true; + barrier(); +} +/* Clearing is done after a TLB flush, which also provides a barrier. */ +static inline void clear_tlb_flush_pending(struct mm_struct *mm) +{ + barrier(); + mm->tlb_flush_pending = false; +} +#else +static inline bool mm_tlb_flush_pending(struct mm_struct *mm) +{ + return false; +} +static inline void set_tlb_flush_pending(struct mm_struct *mm) +{ +} +static inline void clear_tlb_flush_pending(struct mm_struct *mm) +{ +} +#endif + #endif /* _LINUX_MM_TYPES_H */ -- cgit v1.2.2 From af2c1401e6f9177483be4fad876d0073669df9df Mon Sep 17 00:00:00 2001 From: Mel Gorman Date: Wed, 18 Dec 2013 17:08:45 -0800 Subject: mm: numa: guarantee that tlb_flush_pending updates are visible before page table updates According to documentation on barriers, stores issued before a LOCK can complete after the lock implying that it's possible tlb_flush_pending can be visible after a page table update. As per revised documentation, this patch adds a smp_mb__before_spinlock to guarantee the correct ordering. Signed-off-by: Mel Gorman Acked-by: Paul E. McKenney Reviewed-by: Rik van Riel Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/mm_types.h | 7 ++++++- 1 file changed, 6 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index e5c49c30460f..ad0616f2fe2c 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -482,7 +482,12 @@ static inline bool mm_tlb_flush_pending(struct mm_struct *mm) static inline void set_tlb_flush_pending(struct mm_struct *mm) { mm->tlb_flush_pending = true; - barrier(); + + /* + * Guarantee that the tlb_flush_pending store does not leak into the + * critical section updating the page tables + */ + smp_mb__before_spinlock(); } /* Clearing is done after a TLB flush, which also provides a barrier. */ static inline void clear_tlb_flush_pending(struct mm_struct *mm) -- cgit v1.2.2 From 597d795a2a786d22dd872332428e2b9439ede639 Mon Sep 17 00:00:00 2001 From: "Kirill A. Shutemov" Date: Fri, 20 Dec 2013 13:35:58 +0200 Subject: mm: do not allocate page->ptl dynamically, if spinlock_t fits to long In struct page we have enough space to fit long-size page->ptl there, but we use dynamically-allocated page->ptl if size(spinlock_t) is larger than sizeof(int). It hurts 64-bit architectures with CONFIG_GENERIC_LOCKBREAK, where sizeof(spinlock_t) == 8, but it easily fits into struct page. Signed-off-by: Kirill A. Shutemov Acked-by: Hugh Dickins Signed-off-by: Linus Torvalds --- include/linux/lockref.h | 2 +- include/linux/mm.h | 6 +++--- include/linux/mm_types.h | 3 ++- 3 files changed, 6 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/lockref.h b/include/linux/lockref.h index c8929c3832db..4bfde0e99ed5 100644 --- a/include/linux/lockref.h +++ b/include/linux/lockref.h @@ -19,7 +19,7 @@ #define USE_CMPXCHG_LOCKREF \ (IS_ENABLED(CONFIG_ARCH_USE_CMPXCHG_LOCKREF) && \ - IS_ENABLED(CONFIG_SMP) && !BLOATED_SPINLOCKS) + IS_ENABLED(CONFIG_SMP) && SPINLOCK_SIZE <= 4) struct lockref { union { diff --git a/include/linux/mm.h b/include/linux/mm.h index 1cedd000cf29..35527173cf50 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1317,7 +1317,7 @@ static inline pmd_t *pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long a #endif /* CONFIG_MMU && !__ARCH_HAS_4LEVEL_HACK */ #if USE_SPLIT_PTE_PTLOCKS -#if BLOATED_SPINLOCKS +#if ALLOC_SPLIT_PTLOCKS extern bool ptlock_alloc(struct page *page); extern void ptlock_free(struct page *page); @@ -1325,7 +1325,7 @@ static inline spinlock_t *ptlock_ptr(struct page *page) { return page->ptl; } -#else /* BLOATED_SPINLOCKS */ +#else /* ALLOC_SPLIT_PTLOCKS */ static inline bool ptlock_alloc(struct page *page) { return true; @@ -1339,7 +1339,7 @@ static inline spinlock_t *ptlock_ptr(struct page *page) { return &page->ptl; } -#endif /* BLOATED_SPINLOCKS */ +#endif /* ALLOC_SPLIT_PTLOCKS */ static inline spinlock_t *pte_lockptr(struct mm_struct *mm, pmd_t *pmd) { diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index ad0616f2fe2c..290901a8c1de 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -26,6 +26,7 @@ struct address_space; #define USE_SPLIT_PTE_PTLOCKS (NR_CPUS >= CONFIG_SPLIT_PTLOCK_CPUS) #define USE_SPLIT_PMD_PTLOCKS (USE_SPLIT_PTE_PTLOCKS && \ IS_ENABLED(CONFIG_ARCH_ENABLE_SPLIT_PMD_PTLOCK)) +#define ALLOC_SPLIT_PTLOCKS (SPINLOCK_SIZE > BITS_PER_LONG/8) /* * Each physical page in the system has a struct page associated with @@ -155,7 +156,7 @@ struct page { * system if PG_buddy is set. */ #if USE_SPLIT_PTE_PTLOCKS -#if BLOATED_SPINLOCKS +#if ALLOC_SPLIT_PTLOCKS spinlock_t *ptl; #else spinlock_t ptl; -- cgit v1.2.2 From df36ac1bc2a166eef90785d584e4cfed6f52bd32 Mon Sep 17 00:00:00 2001 From: "Luck, Tony" Date: Wed, 18 Dec 2013 15:17:10 -0800 Subject: pstore: Don't allow high traffic options on fragile devices Some pstore backing devices use on board flash as persistent storage. These have limited numbers of write cycles so it is a poor idea to use them from high frequency operations. Signed-off-by: Tony Luck Signed-off-by: Linus Torvalds --- include/linux/pstore.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pstore.h b/include/linux/pstore.h index abd437d0a8a7..ece0c6bbfcc5 100644 --- a/include/linux/pstore.h +++ b/include/linux/pstore.h @@ -51,6 +51,7 @@ struct pstore_info { char *buf; size_t bufsize; struct mutex read_mutex; /* serialize open/read/close */ + int flags; int (*open)(struct pstore_info *psi); int (*close)(struct pstore_info *psi); ssize_t (*read)(u64 *id, enum pstore_type_id *type, @@ -70,6 +71,8 @@ struct pstore_info { void *data; }; +#define PSTORE_FLAGS_FRAGILE 1 + #ifdef CONFIG_PSTORE extern int pstore_register(struct pstore_info *); extern bool pstore_cannot_block_path(enum kmsg_dump_reason reason); -- cgit v1.2.2 From 8e321fefb0e60bae4e2a28d20fc4fa30758d27c6 Mon Sep 17 00:00:00 2001 From: Benjamin LaHaise Date: Sat, 21 Dec 2013 17:56:08 -0500 Subject: aio/migratepages: make aio migrate pages sane The arbitrary restriction on page counts offered by the core migrate_page_move_mapping() code results in rather suspicious looking fiddling with page reference counts in the aio_migratepage() operation. To fix this, make migrate_page_move_mapping() take an extra_count parameter that allows aio to tell the code about its own reference count on the page being migrated. While cleaning up aio_migratepage(), make it validate that the old page being passed in is actually what aio_migratepage() expects to prevent misbehaviour in the case of races. Signed-off-by: Benjamin LaHaise --- include/linux/migrate.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/migrate.h b/include/linux/migrate.h index b7717d74da7f..f015c059e159 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -55,7 +55,8 @@ extern int migrate_huge_page_move_mapping(struct address_space *mapping, struct page *newpage, struct page *page); extern int migrate_page_move_mapping(struct address_space *mapping, struct page *newpage, struct page *page, - struct buffer_head *head, enum migrate_mode mode); + struct buffer_head *head, enum migrate_mode mode, + int extra_count); #else static inline void putback_lru_pages(struct list_head *l) {} -- cgit v1.2.2 From f60900f2609e893c7f8d0bccc7ada4947dac4cd5 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel Date: Mon, 23 Dec 2013 18:49:30 +0100 Subject: auxvec.h: account for AT_HWCAP2 in AT_VECTOR_SIZE_BASE Commit 2171364d1a92 ("powerpc: Add HWCAP2 aux entry") introduced a new AT_ auxv entry type AT_HWCAP2 but failed to update AT_VECTOR_SIZE_BASE accordingly. Signed-off-by: Ard Biesheuvel Fixes: 2171364d1a92 (powerpc: Add HWCAP2 aux entry) Cc: stable@vger.kernel.org Acked-by: Michael Neuling Cc: Nishanth Aravamudan Cc: Benjamin Herrenschmidt Signed-off-by: Linus Torvalds --- include/linux/auxvec.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/auxvec.h b/include/linux/auxvec.h index 669fef5c745a..3e0fbe441763 100644 --- a/include/linux/auxvec.h +++ b/include/linux/auxvec.h @@ -3,6 +3,6 @@ #include -#define AT_VECTOR_SIZE_BASE 19 /* NEW_AUX_ENT entries in auxiliary table */ +#define AT_VECTOR_SIZE_BASE 20 /* NEW_AUX_ENT entries in auxiliary table */ /* number of "#define AT_.*" above, minus {AT_NULL, AT_IGNORE, AT_NOTELF} */ #endif /* _LINUX_AUXVEC_H */ -- cgit v1.2.2 From 73409f3b0ff0ae7bc1f647936b23e6d5d5dcbe28 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Fri, 27 Dec 2013 13:04:33 -0500 Subject: net: Add some clarification to skb_tx_timestamp() comment. We've seen so many instances of people invoking skb_tx_timestamp() after the device already has been given the packet, that it's worth being a little bit more verbose and explicit in this comment. Signed-off-by: David S. Miller --- include/linux/skbuff.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 6aae83890520..6f69b3f914fb 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -2531,6 +2531,10 @@ static inline void sw_tx_timestamp(struct sk_buff *skb) * Ethernet MAC Drivers should call this function in their hard_xmit() * function immediately before giving the sk_buff to the MAC hardware. * + * Specifically, one should make absolutely sure that this function is + * called before TX completion of this packet can trigger. Otherwise + * the packet could potentially already be freed. + * * @skb: A socket buffer. */ static inline void skb_tx_timestamp(struct sk_buff *skb) -- cgit v1.2.2 From 2205369a314e12fcec4781cc73ac9c08fc2b47de Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Tue, 31 Dec 2013 16:23:35 -0500 Subject: vlan: Fix header ops passthru when doing TX VLAN offload. When the vlan code detects that the real device can do TX VLAN offloads in hardware, it tries to arrange for the real device's header_ops to be invoked directly. But it does so illegally, by simply hooking the real device's header_ops up to the VLAN device. This doesn't work because we will end up invoking a set of header_ops routines which expect a device type which matches the real device, but will see a VLAN device instead. Fix this by providing a pass-thru set of header_ops which will arrange to pass the proper real device instead. To facilitate this add a dev_rebuild_header(). There are implementations which provide a ->cache and ->create but not a ->rebuild (f.e. PLIP). So we need a helper function just like dev_hard_header() to avoid crashes. Use this helper in the one existing place where the header_ops->rebuild was being invoked, the neighbour code. With lots of help from Florian Westphal. Signed-off-by: David S. Miller --- include/linux/netdevice.h | 9 +++++++++ 1 file changed, 9 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index d9a550bf3e8e..7514b9c37a39 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1912,6 +1912,15 @@ static inline int dev_parse_header(const struct sk_buff *skb, return dev->header_ops->parse(skb, haddr); } +static inline int dev_rebuild_header(struct sk_buff *skb) +{ + const struct net_device *dev = skb->dev; + + if (!dev->header_ops || !dev->header_ops->rebuild) + return 0; + return dev->header_ops->rebuild(skb); +} + typedef int gifconf_func_t(struct net_device * dev, char __user * bufptr, int len); int register_gifconf(unsigned int family, gifconf_func_t *gifconf); static inline int unregister_gifconf(unsigned int family) -- cgit v1.2.2 From 7a7ffbabf99445704be01bff5d7e360da908cf8e Mon Sep 17 00:00:00 2001 From: Wei-Chun Chao Date: Thu, 26 Dec 2013 13:10:22 -0800 Subject: ipv4: fix tunneled VM traffic over hw VXLAN/GRE GSO NIC VM to VM GSO traffic is broken if it goes through VXLAN or GRE tunnel and the physical NIC on the host supports hardware VXLAN/GRE GSO offload (e.g. bnx2x and next-gen mlx4). Two issues - (VXLAN) VM traffic has SKB_GSO_DODGY and SKB_GSO_UDP_TUNNEL with SKB_GSO_TCP/UDP set depending on the inner protocol. GSO header integrity check fails in udp4_ufo_fragment if inner protocol is TCP. Also gso_segs is calculated incorrectly using skb->len that includes tunnel header. Fix: robust check should only be applied to the inner packet. (VXLAN & GRE) Once GSO header integrity check passes, NULL segs is returned and the original skb is sent to hardware. However the tunnel header is already pulled. Fix: tunnel header needs to be restored so that hardware can perform GSO properly on the original packet. Signed-off-by: Wei-Chun Chao Signed-off-by: David S. Miller --- include/linux/netdevice.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 7514b9c37a39..5faaadb0c74f 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3017,6 +3017,19 @@ static inline void netif_set_gso_max_size(struct net_device *dev, dev->gso_max_size = size; } +static inline void skb_gso_error_unwind(struct sk_buff *skb, __be16 protocol, + int pulled_hlen, u16 mac_offset, + int mac_len) +{ + skb->protocol = protocol; + skb->encapsulation = 1; + skb_push(skb, pulled_hlen); + skb_reset_transport_header(skb); + skb->mac_header = mac_offset; + skb->network_header = skb->mac_header + mac_len; + skb->mac_len = mac_len; +} + static inline bool netif_is_macvlan(struct net_device *dev) { return dev->priv_flags & IFF_MACVLAN; -- cgit v1.2.2 From f663dd9aaf9ed124f25f0f8452edf238f087ad50 Mon Sep 17 00:00:00 2001 From: Jason Wang Date: Fri, 10 Jan 2014 16:18:26 +0800 Subject: net: core: explicitly select a txq before doing l2 forwarding Currently, the tx queue were selected implicitly in ndo_dfwd_start_xmit(). The will cause several issues: - NETIF_F_LLTX were removed for macvlan, so txq lock were done for macvlan instead of lower device which misses the necessary txq synchronization for lower device such as txq stopping or frozen required by dev watchdog or control path. - dev_hard_start_xmit() was called with NULL txq which bypasses the net device watchdog. - dev_hard_start_xmit() does not check txq everywhere which will lead a crash when tso is disabled for lower device. Fix this by explicitly introducing a new param for .ndo_select_queue() for just selecting queues in the case of l2 forwarding offload. netdev_pick_tx() was also extended to accept this parameter and dev_queue_xmit_accel() was used to do l2 forwarding transmission. With this fixes, NETIF_F_LLTX could be preserved for macvlan and there's no need to check txq against NULL in dev_hard_start_xmit(). Also there's no need to keep a dedicated ndo_dfwd_start_xmit() and we can just reuse the code of dev_queue_xmit() to do the transmission. In the future, it was also required for macvtap l2 forwarding support since it provides a necessary synchronization method. Cc: John Fastabend Cc: Neil Horman Cc: e1000-devel@lists.sourceforge.net Signed-off-by: Jason Wang Acked-by: Neil Horman Acked-by: John Fastabend Signed-off-by: David S. Miller --- include/linux/netdevice.h | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 5faaadb0c74f..ce2a1f5f9a1e 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -769,7 +769,8 @@ struct netdev_phys_port_id { * (can also return NETDEV_TX_LOCKED iff NETIF_F_LLTX) * Required can not be NULL. * - * u16 (*ndo_select_queue)(struct net_device *dev, struct sk_buff *skb); + * u16 (*ndo_select_queue)(struct net_device *dev, struct sk_buff *skb, + * void *accel_priv); * Called to decide which queue to when device supports multiple * transmit queues. * @@ -990,7 +991,8 @@ struct net_device_ops { netdev_tx_t (*ndo_start_xmit) (struct sk_buff *skb, struct net_device *dev); u16 (*ndo_select_queue)(struct net_device *dev, - struct sk_buff *skb); + struct sk_buff *skb, + void *accel_priv); void (*ndo_change_rx_flags)(struct net_device *dev, int flags); void (*ndo_set_rx_mode)(struct net_device *dev); @@ -1529,7 +1531,8 @@ static inline void netdev_for_each_tx_queue(struct net_device *dev, } struct netdev_queue *netdev_pick_tx(struct net_device *dev, - struct sk_buff *skb); + struct sk_buff *skb, + void *accel_priv); u16 __netdev_pick_tx(struct net_device *dev, struct sk_buff *skb); /* @@ -1819,6 +1822,7 @@ int dev_close(struct net_device *dev); void dev_disable_lro(struct net_device *dev); int dev_loopback_xmit(struct sk_buff *newskb); int dev_queue_xmit(struct sk_buff *skb); +int dev_queue_xmit_accel(struct sk_buff *skb, void *accel_priv); int register_netdevice(struct net_device *dev); void unregister_netdevice_queue(struct net_device *dev, struct list_head *head); void unregister_netdevice_many(struct list_head *head); @@ -2426,7 +2430,7 @@ int dev_change_carrier(struct net_device *, bool new_carrier); int dev_get_phys_port_id(struct net_device *dev, struct netdev_phys_port_id *ppid); int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, - struct netdev_queue *txq, void *accel_priv); + struct netdev_queue *txq); int dev_forward_skb(struct net_device *dev, struct sk_buff *skb); extern int netdev_budget; -- cgit v1.2.2