From 45cd0faae3715e305bc46e23b34c5ed4d185ceb8 Mon Sep 17 00:00:00 2001 From: Amir Goldstein Date: Mon, 27 Aug 2018 15:56:02 +0300 Subject: vfs: add the fadvise() file operation This is going to be used by overlayfs and possibly useful for other filesystems. Signed-off-by: Amir Goldstein Signed-off-by: Miklos Szeredi --- include/linux/fs.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fs.h b/include/linux/fs.h index 33322702c910..6c0b4a1c22ff 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1763,6 +1763,7 @@ struct file_operations { u64); int (*dedupe_file_range)(struct file *, loff_t, struct file *, loff_t, u64); + int (*fadvise)(struct file *, loff_t, loff_t, int); } __randomize_layout; struct inode_operations { @@ -3459,4 +3460,8 @@ static inline bool dir_relax_shared(struct inode *inode) extern bool path_noexec(const struct path *path); extern void inode_nohighmem(struct inode *inode); +/* mm/fadvise.c */ +extern int vfs_fadvise(struct file *file, loff_t offset, loff_t len, + int advice); + #endif /* _LINUX_FS_H */ -- cgit v1.2.3 From d23df2dc56325c72b51670b1fb400ddd23dc17cd Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Mon, 3 Sep 2018 12:51:59 -0700 Subject: linux/mod_devicetable.h: fix kernel-doc missing notation for typec_device_id Fix kernel-doc warning for missing struct member description: ../include/linux/mod_devicetable.h:763: warning: Function parameter or member 'driver_data' not described in 'typec_device_id' Fixes: 8a37d87d72f0c ("usb: typec: Bus type for alternate modes") Signed-off-by: Randy Dunlap Cc: Heikki Krogerus Reviewed-by: Heikki Krogerus Signed-off-by: Greg Kroah-Hartman --- include/linux/mod_devicetable.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/mod_devicetable.h b/include/linux/mod_devicetable.h index 1298a7daa57d..01797cb4587e 100644 --- a/include/linux/mod_devicetable.h +++ b/include/linux/mod_devicetable.h @@ -754,6 +754,7 @@ struct tb_service_id { * struct typec_device_id - USB Type-C alternate mode identifiers * @svid: Standard or Vendor ID * @mode: Mode index + * @driver_data: Driver specific data */ struct typec_device_id { __u16 svid; -- cgit v1.2.3 From 01c5f85aebaaddfd7e6051fb2ec80c1d4b463554 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Tue, 11 Sep 2018 10:59:53 -0600 Subject: blk-cgroup: increase number of supported policies After merging the iolatency policy, we potentially now have 4 policies being registered, but only support 3. This causes one of them to fail loading. Takashi reports that BFQ no longer works for him, because it fails to load due to policy registration failure. Bump to 5 policies, and also add a warning for when we have exceeded the global amount. If we have to touch this again, we should switch to a dynamic scheme instead. Reported-by: Takashi Iwai Reviewed-by: Jeff Moyer Tested-by: Takashi Iwai Signed-off-by: Jens Axboe --- block/blk-cgroup.c | 4 +++- include/linux/blkdev.h | 2 +- 2 files changed, 4 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/block/blk-cgroup.c b/block/blk-cgroup.c index c19f9078da1e..c630e02836a8 100644 --- a/block/blk-cgroup.c +++ b/block/blk-cgroup.c @@ -1510,8 +1510,10 @@ int blkcg_policy_register(struct blkcg_policy *pol) for (i = 0; i < BLKCG_MAX_POLS; i++) if (!blkcg_policy[i]) break; - if (i >= BLKCG_MAX_POLS) + if (i >= BLKCG_MAX_POLS) { + pr_warn("blkcg_policy_register: BLKCG_MAX_POLS too small\n"); goto err_unlock; + } /* Make sure cpd/pd_alloc_fn and cpd/pd_free_fn in pairs */ if ((!pol->cpd_alloc_fn ^ !pol->cpd_free_fn) || diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h index d6869e0e2b64..6980014357d4 100644 --- a/include/linux/blkdev.h +++ b/include/linux/blkdev.h @@ -54,7 +54,7 @@ struct blk_stat_callback; * Maximum number of blkcg policies allowed to be registered concurrently. * Defined here to simplify include dependency. */ -#define BLKCG_MAX_POLS 3 +#define BLKCG_MAX_POLS 5 typedef void (rq_end_io_fn)(struct request *, blk_status_t); -- cgit v1.2.3 From bfc456060d0cbcf6902a436d358b60cb1534668c Mon Sep 17 00:00:00 2001 From: Dennis Dalessandro Date: Fri, 31 Aug 2018 10:34:14 -0700 Subject: IB/hfi1,PCI: Allow bus reset while probing Calling into the new API to reset the secondary bus results in a deadlock. This occurs because the device/bus is already locked at probe time. Reverting back to the old behavior while the API is improved. Link: https://bugzilla.kernel.org/show_bug.cgi?id=200985 Fixes: c6a44ba950d1 ("PCI: Rename pci_try_reset_bus() to pci_reset_bus()") Fixes: 409888e0966e ("IB/hfi1: Use pci_try_reset_bus() for initiating PCI Secondary Bus Reset") Signed-off-by: Dennis Dalessandro Signed-off-by: Bjorn Helgaas Reviewed-by: Michael J. Ruhl Cc: Sinan Kaya --- drivers/infiniband/hw/hfi1/pcie.c | 11 ++++------- drivers/pci/pci.c | 1 + include/linux/pci.h | 3 +++ 3 files changed, 8 insertions(+), 7 deletions(-) (limited to 'include/linux') diff --git a/drivers/infiniband/hw/hfi1/pcie.c b/drivers/infiniband/hw/hfi1/pcie.c index eec83757d55f..6c967dde58e7 100644 --- a/drivers/infiniband/hw/hfi1/pcie.c +++ b/drivers/infiniband/hw/hfi1/pcie.c @@ -893,14 +893,11 @@ static int trigger_sbr(struct hfi1_devdata *dd) } /* - * A secondary bus reset (SBR) issues a hot reset to our device. - * The following routine does a 1s wait after the reset is dropped - * per PCI Trhfa (recovery time). PCIe 3.0 section 6.6.1 - - * Conventional Reset, paragraph 3, line 35 also says that a 1s - * delay after a reset is required. Per spec requirements, - * the link is either working or not after that point. + * This is an end around to do an SBR during probe time. A new API needs + * to be implemented to have cleaner interface but this fixes the + * current brokenness */ - return pci_reset_bus(dev); + return pci_bridge_secondary_bus_reset(dev->bus->self); } /* diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index 30b260332a10..1835f3a7aa8d 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -4547,6 +4547,7 @@ int pci_bridge_secondary_bus_reset(struct pci_dev *dev) return pci_dev_wait(dev, "bus reset", PCIE_RESET_READY_POLL_MS); } +EXPORT_SYMBOL_GPL(pci_bridge_secondary_bus_reset); static int pci_parent_bus_reset(struct pci_dev *dev, int probe) { diff --git a/include/linux/pci.h b/include/linux/pci.h index e72ca8dd6241..6925828f9f25 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1235,6 +1235,9 @@ void pci_bus_remove_resources(struct pci_bus *bus); int devm_request_pci_bus_resources(struct device *dev, struct list_head *resources); +/* Temporary until new and working PCI SBR API in place */ +int pci_bridge_secondary_bus_reset(struct pci_dev *dev); + #define pci_bus_for_each_resource(bus, res, i) \ for (i = 0; \ (res = pci_bus_resource_n(bus, i)) || i < PCI_BRIDGE_RESOURCE_NUM; \ -- cgit v1.2.3 From 7a9cdebdcc17e426fb5287e4a82db1dfe86339b2 Mon Sep 17 00:00:00 2001 From: Linus Torvalds Date: Wed, 12 Sep 2018 23:57:48 -1000 Subject: mm: get rid of vmacache_flush_all() entirely Jann Horn points out that the vmacache_flush_all() function is not only potentially expensive, it's buggy too. It also happens to be entirely unnecessary, because the sequence number overflow case can be avoided by simply making the sequence number be 64-bit. That doesn't even grow the data structures in question, because the other adjacent fields are already 64-bit. So simplify the whole thing by just making the sequence number overflow case go away entirely, which gets rid of all the complications and makes the code faster too. Win-win. [ Oleg Nesterov points out that the VMACACHE_FULL_FLUSHES statistics also just goes away entirely with this ] Reported-by: Jann Horn Suggested-by: Will Deacon Acked-by: Davidlohr Bueso Cc: Oleg Nesterov Cc: stable@kernel.org Signed-off-by: Linus Torvalds --- include/linux/mm_types.h | 2 +- include/linux/mm_types_task.h | 2 +- include/linux/vm_event_item.h | 1 - include/linux/vmacache.h | 5 ----- mm/debug.c | 4 ++-- mm/vmacache.c | 38 -------------------------------------- 6 files changed, 4 insertions(+), 48 deletions(-) (limited to 'include/linux') diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index cd2bc939efd0..5ed8f6292a53 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -341,7 +341,7 @@ struct mm_struct { struct { struct vm_area_struct *mmap; /* list of VMAs */ struct rb_root mm_rb; - u32 vmacache_seqnum; /* per-thread vmacache */ + u64 vmacache_seqnum; /* per-thread vmacache */ #ifdef CONFIG_MMU unsigned long (*get_unmapped_area) (struct file *filp, unsigned long addr, unsigned long len, diff --git a/include/linux/mm_types_task.h b/include/linux/mm_types_task.h index 5fe87687664c..d7016dcb245e 100644 --- a/include/linux/mm_types_task.h +++ b/include/linux/mm_types_task.h @@ -32,7 +32,7 @@ #define VMACACHE_MASK (VMACACHE_SIZE - 1) struct vmacache { - u32 seqnum; + u64 seqnum; struct vm_area_struct *vmas[VMACACHE_SIZE]; }; diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h index 5c7f010676a7..47a3441cf4c4 100644 --- a/include/linux/vm_event_item.h +++ b/include/linux/vm_event_item.h @@ -105,7 +105,6 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT, #ifdef CONFIG_DEBUG_VM_VMACACHE VMACACHE_FIND_CALLS, VMACACHE_FIND_HITS, - VMACACHE_FULL_FLUSHES, #endif #ifdef CONFIG_SWAP SWAP_RA, diff --git a/include/linux/vmacache.h b/include/linux/vmacache.h index 3e9a963edd6a..6fce268a4588 100644 --- a/include/linux/vmacache.h +++ b/include/linux/vmacache.h @@ -10,7 +10,6 @@ static inline void vmacache_flush(struct task_struct *tsk) memset(tsk->vmacache.vmas, 0, sizeof(tsk->vmacache.vmas)); } -extern void vmacache_flush_all(struct mm_struct *mm); extern void vmacache_update(unsigned long addr, struct vm_area_struct *newvma); extern struct vm_area_struct *vmacache_find(struct mm_struct *mm, unsigned long addr); @@ -24,10 +23,6 @@ extern struct vm_area_struct *vmacache_find_exact(struct mm_struct *mm, static inline void vmacache_invalidate(struct mm_struct *mm) { mm->vmacache_seqnum++; - - /* deal with overflows */ - if (unlikely(mm->vmacache_seqnum == 0)) - vmacache_flush_all(mm); } #endif /* __LINUX_VMACACHE_H */ diff --git a/mm/debug.c b/mm/debug.c index 38c926520c97..bd10aad8539a 100644 --- a/mm/debug.c +++ b/mm/debug.c @@ -114,7 +114,7 @@ EXPORT_SYMBOL(dump_vma); void dump_mm(const struct mm_struct *mm) { - pr_emerg("mm %px mmap %px seqnum %d task_size %lu\n" + pr_emerg("mm %px mmap %px seqnum %llu task_size %lu\n" #ifdef CONFIG_MMU "get_unmapped_area %px\n" #endif @@ -142,7 +142,7 @@ void dump_mm(const struct mm_struct *mm) "tlb_flush_pending %d\n" "def_flags: %#lx(%pGv)\n", - mm, mm->mmap, mm->vmacache_seqnum, mm->task_size, + mm, mm->mmap, (long long) mm->vmacache_seqnum, mm->task_size, #ifdef CONFIG_MMU mm->get_unmapped_area, #endif diff --git a/mm/vmacache.c b/mm/vmacache.c index ea517bef7dc5..cdc32a3b02fa 100644 --- a/mm/vmacache.c +++ b/mm/vmacache.c @@ -19,44 +19,6 @@ #endif #define VMACACHE_HASH(addr) ((addr >> VMACACHE_SHIFT) & VMACACHE_MASK) -/* - * Flush vma caches for threads that share a given mm. - * - * The operation is safe because the caller holds the mmap_sem - * exclusively and other threads accessing the vma cache will - * have mmap_sem held at least for read, so no extra locking - * is required to maintain the vma cache. - */ -void vmacache_flush_all(struct mm_struct *mm) -{ - struct task_struct *g, *p; - - count_vm_vmacache_event(VMACACHE_FULL_FLUSHES); - - /* - * Single threaded tasks need not iterate the entire - * list of process. We can avoid the flushing as well - * since the mm's seqnum was increased and don't have - * to worry about other threads' seqnum. Current's - * flush will occur upon the next lookup. - */ - if (atomic_read(&mm->mm_users) == 1) - return; - - rcu_read_lock(); - for_each_process_thread(g, p) { - /* - * Only flush the vmacache pointers as the - * mm seqnum is already set and curr's will - * be set upon invalidation when the next - * lookup is done. - */ - if (mm == p->mm) - vmacache_flush(p); - } - rcu_read_unlock(); -} - /* * This task may be accessing a foreign mm via (for example) * get_user_pages()->find_vma(). The vmacache is task-local and this -- cgit v1.2.3