From b7ec35b304b64af2830027350cc99d31e6e537c2 Mon Sep 17 00:00:00 2001 From: Ilya Dryomov Date: Thu, 28 Apr 2016 16:07:25 +0200 Subject: libceph: change ceph_osdmap_flag() to take osdc For the benefit of every single caller, take osdc instead of map. Also, now that osdc->osdmap can't ever be NULL, drop the check. Signed-off-by: Ilya Dryomov --- include/linux/ceph/osd_client.h | 5 +++++ include/linux/ceph/osdmap.h | 5 ----- 2 files changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/ceph/osd_client.h b/include/linux/ceph/osd_client.h index 19b14862d3e0..1b3b6e155392 100644 --- a/include/linux/ceph/osd_client.h +++ b/include/linux/ceph/osd_client.h @@ -279,6 +279,11 @@ struct ceph_osd_client { struct workqueue_struct *notify_wq; }; +static inline bool ceph_osdmap_flag(struct ceph_osd_client *osdc, int flag) +{ + return osdc->osdmap->flags & flag; +} + extern int ceph_osdc_setup(void); extern void ceph_osdc_cleanup(void); diff --git a/include/linux/ceph/osdmap.h b/include/linux/ceph/osdmap.h index ddc426b22d81..9ccf4dbe55f8 100644 --- a/include/linux/ceph/osdmap.h +++ b/include/linux/ceph/osdmap.h @@ -189,11 +189,6 @@ static inline bool ceph_osd_is_down(struct ceph_osdmap *map, int osd) return !ceph_osd_is_up(map, osd); } -static inline bool ceph_osdmap_flag(struct ceph_osdmap *map, int flag) -{ - return map && (map->flags & flag); -} - extern char *ceph_osdmap_state_str(char *str, int len, int state); extern u32 ceph_get_primary_affinity(struct ceph_osdmap *map, int osd); -- cgit v1.2.3 From e2082e3ab801b989d8d5337b2ecbfc61d09781cb Mon Sep 17 00:00:00 2001 From: Rob Clark Date: Thu, 31 Mar 2016 16:26:50 -0400 Subject: dma-buf: headerdoc fixes Apparently nobody noticed that dma-buf.h wasn't actually pulled into docbook build. And as a result the headerdoc comments bitrot a bit. Add missing params/fields. Signed-off-by: Rob Clark Signed-off-by: Sumit Semwal --- include/linux/dma-buf.h | 13 ++++++++++--- 1 file changed, 10 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/dma-buf.h b/include/linux/dma-buf.h index 3fe90d494edb..4551c6f2a6c4 100644 --- a/include/linux/dma-buf.h +++ b/include/linux/dma-buf.h @@ -112,19 +112,24 @@ struct dma_buf_ops { * @file: file pointer used for sharing buffers across, and for refcounting. * @attachments: list of dma_buf_attachment that denotes all devices attached. * @ops: dma_buf_ops associated with this buffer object. + * @lock: used internally to serialize list manipulation, attach/detach and vmap/unmap + * @vmapping_counter: used internally to refcnt the vmaps + * @vmap_ptr: the current vmap ptr if vmapping_counter > 0 * @exp_name: name of the exporter; useful for debugging. * @owner: pointer to exporter module; used for refcounting when exporter is a * kernel module. * @list_node: node for dma_buf accounting and debugging. * @priv: exporter specific private data for this buffer object. * @resv: reservation object linked to this dma-buf + * @poll: for userspace poll support + * @cb_excl: for userspace poll support + * @cb_shared: for userspace poll support */ struct dma_buf { size_t size; struct file *file; struct list_head attachments; const struct dma_buf_ops *ops; - /* mutex to serialize list manipulation, attach/detach and vmap/unmap */ struct mutex lock; unsigned vmapping_counter; void *vmap_ptr; @@ -188,9 +193,11 @@ struct dma_buf_export_info { /** * helper macro for exporters; zeros and fills in most common values + * + * @name: export-info name */ -#define DEFINE_DMA_BUF_EXPORT_INFO(a) \ - struct dma_buf_export_info a = { .exp_name = KBUILD_MODNAME, \ +#define DEFINE_DMA_BUF_EXPORT_INFO(name) \ + struct dma_buf_export_info name = { .exp_name = KBUILD_MODNAME, \ .owner = THIS_MODULE } /** -- cgit v1.2.3 From dad6c3945fd25384c2b92306a90ba033e1130428 Mon Sep 17 00:00:00 2001 From: Rob Clark Date: Thu, 31 Mar 2016 16:26:51 -0400 Subject: reservation: add headerdoc comments Signed-off-by: Rob Clark Signed-off-by: Sumit Semwal --- drivers/dma-buf/reservation.c | 72 ++++++++++++++++++++++++++++++++++++++++--- include/linux/reservation.h | 53 +++++++++++++++++++++++++++++++ 2 files changed, 121 insertions(+), 4 deletions(-) (limited to 'include/linux') diff --git a/drivers/dma-buf/reservation.c b/drivers/dma-buf/reservation.c index c0bd5722c997..9566a62ad8e3 100644 --- a/drivers/dma-buf/reservation.c +++ b/drivers/dma-buf/reservation.c @@ -35,6 +35,17 @@ #include #include +/** + * DOC: Reservation Object Overview + * + * The reservation object provides a mechanism to manage shared and + * exclusive fences associated with a buffer. A reservation object + * can have attached one exclusive fence (normally associated with + * write operations) or N shared fences (read operations). The RCU + * mechanism is used to protect read access to fences from locked + * write-side updates. + */ + DEFINE_WW_CLASS(reservation_ww_class); EXPORT_SYMBOL(reservation_ww_class); @@ -43,9 +54,17 @@ EXPORT_SYMBOL(reservation_seqcount_class); const char reservation_seqcount_string[] = "reservation_seqcount"; EXPORT_SYMBOL(reservation_seqcount_string); -/* - * Reserve space to add a shared fence to a reservation_object, - * must be called with obj->lock held. + +/** + * reservation_object_reserve_shared - Reserve space to add a shared + * fence to a reservation_object. + * @obj: reservation object + * + * Should be called before reservation_object_add_shared_fence(). Must + * be called with obj->lock held. + * + * RETURNS + * Zero for success, or -errno */ int reservation_object_reserve_shared(struct reservation_object *obj) { @@ -180,7 +199,11 @@ done: fence_put(old_fence); } -/* +/** + * reservation_object_add_shared_fence - Add a fence to a shared slot + * @obj: the reservation object + * @fence: the shared fence to add + * * Add a fence to a shared slot, obj->lock must be held, and * reservation_object_reserve_shared_fence has been called. */ @@ -200,6 +223,13 @@ void reservation_object_add_shared_fence(struct reservation_object *obj, } EXPORT_SYMBOL(reservation_object_add_shared_fence); +/** + * reservation_object_add_excl_fence - Add an exclusive fence. + * @obj: the reservation object + * @fence: the shared fence to add + * + * Add a fence to the exclusive slot. The obj->lock must be held. + */ void reservation_object_add_excl_fence(struct reservation_object *obj, struct fence *fence) { @@ -233,6 +263,18 @@ void reservation_object_add_excl_fence(struct reservation_object *obj, } EXPORT_SYMBOL(reservation_object_add_excl_fence); +/** + * reservation_object_get_fences_rcu - Get an object's shared and exclusive + * fences without update side lock held + * @obj: the reservation object + * @pfence_excl: the returned exclusive fence (or NULL) + * @pshared_count: the number of shared fences returned + * @pshared: the array of shared fence ptrs returned (array is krealloc'd to + * the required size, and must be freed by caller) + * + * RETURNS + * Zero or -errno + */ int reservation_object_get_fences_rcu(struct reservation_object *obj, struct fence **pfence_excl, unsigned *pshared_count, @@ -319,6 +361,18 @@ unlock: } EXPORT_SYMBOL_GPL(reservation_object_get_fences_rcu); +/** + * reservation_object_wait_timeout_rcu - Wait on reservation's objects + * shared and/or exclusive fences. + * @obj: the reservation object + * @wait_all: if true, wait on all fences, else wait on just exclusive fence + * @intr: if true, do interruptible wait + * @timeout: timeout value in jiffies or zero to return immediately + * + * RETURNS + * Returns -ERESTARTSYS if interrupted, 0 if the wait timed out, or + * greater than zer on success. + */ long reservation_object_wait_timeout_rcu(struct reservation_object *obj, bool wait_all, bool intr, unsigned long timeout) @@ -416,6 +470,16 @@ reservation_object_test_signaled_single(struct fence *passed_fence) return ret; } +/** + * reservation_object_test_signaled_rcu - Test if a reservation object's + * fences have been signaled. + * @obj: the reservation object + * @test_all: if true, test all fences, otherwise only test the exclusive + * fence + * + * RETURNS + * true if all fences signaled, else false + */ bool reservation_object_test_signaled_rcu(struct reservation_object *obj, bool test_all) { diff --git a/include/linux/reservation.h b/include/linux/reservation.h index 49d057655d62..b0f305e77b7f 100644 --- a/include/linux/reservation.h +++ b/include/linux/reservation.h @@ -49,12 +49,27 @@ extern struct ww_class reservation_ww_class; extern struct lock_class_key reservation_seqcount_class; extern const char reservation_seqcount_string[]; +/** + * struct reservation_object_list - a list of shared fences + * @rcu: for internal use + * @shared_count: table of shared fences + * @shared_max: for growing shared fence table + * @shared: shared fence table + */ struct reservation_object_list { struct rcu_head rcu; u32 shared_count, shared_max; struct fence __rcu *shared[]; }; +/** + * struct reservation_object - a reservation object manages fences for a buffer + * @lock: update side lock + * @seq: sequence count for managing RCU read-side synchronization + * @fence_excl: the exclusive fence, if there is one currently + * @fence: list of current shared fences + * @staged: staged copy of shared fences for RCU updates + */ struct reservation_object { struct ww_mutex lock; seqcount_t seq; @@ -68,6 +83,10 @@ struct reservation_object { #define reservation_object_assert_held(obj) \ lockdep_assert_held(&(obj)->lock.base) +/** + * reservation_object_init - initialize a reservation object + * @obj: the reservation object + */ static inline void reservation_object_init(struct reservation_object *obj) { @@ -79,6 +98,10 @@ reservation_object_init(struct reservation_object *obj) obj->staged = NULL; } +/** + * reservation_object_fini - destroys a reservation object + * @obj: the reservation object + */ static inline void reservation_object_fini(struct reservation_object *obj) { @@ -106,6 +129,14 @@ reservation_object_fini(struct reservation_object *obj) ww_mutex_destroy(&obj->lock); } +/** + * reservation_object_get_list - get the reservation object's + * shared fence list, with update-side lock held + * @obj: the reservation object + * + * Returns the shared fence list. Does NOT take references to + * the fence. The obj->lock must be held. + */ static inline struct reservation_object_list * reservation_object_get_list(struct reservation_object *obj) { @@ -113,6 +144,17 @@ reservation_object_get_list(struct reservation_object *obj) reservation_object_held(obj)); } +/** + * reservation_object_get_excl - get the reservation object's + * exclusive fence, with update-side lock held + * @obj: the reservation object + * + * Returns the exclusive fence (if any). Does NOT take a + * reference. The obj->lock must be held. + * + * RETURNS + * The exclusive fence or NULL + */ static inline struct fence * reservation_object_get_excl(struct reservation_object *obj) { @@ -120,6 +162,17 @@ reservation_object_get_excl(struct reservation_object *obj) reservation_object_held(obj)); } +/** + * reservation_object_get_excl_rcu - get the reservation object's + * exclusive fence, without lock held. + * @obj: the reservation object + * + * If there is an exclusive fence, this atomically increments it's + * reference count and returns it. + * + * RETURNS + * The exclusive fence or NULL if none + */ static inline struct fence * reservation_object_get_excl_rcu(struct reservation_object *obj) { -- cgit v1.2.3 From 4320c2a22df12f954edd4997f71ca3a4216312b2 Mon Sep 17 00:00:00 2001 From: Luis de Bethencourt Date: Mon, 11 Apr 2016 12:48:55 +0100 Subject: fence: add missing descriptions for fence The members child_list and active_list were added to the fence struct without descriptions for the Documentation. Adding these. Fixes: b55b54b5db33 ("staging/android: remove struct sync_pt") Signed-off-by: Luis de Bethencourt Reviewed-by: Javier Martinez Canillas Reviewed-by: Gustavo Padovan Signed-off-by: Sumit Semwal --- include/linux/fence.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/fence.h b/include/linux/fence.h index 2b17698b60b8..2056e9fd0138 100644 --- a/include/linux/fence.h +++ b/include/linux/fence.h @@ -49,6 +49,8 @@ struct fence_cb; * @timestamp: Timestamp when the fence was signaled. * @status: Optional, only valid if < 0, must be set before calling * fence_signal, indicates that the fence has completed with an error. + * @child_list: list of children fences + * @active_list: list of active fences * * the flags member must be manipulated and read using the appropriate * atomic ops (bit_*), so taking the spinlock will not be needed most -- cgit v1.2.3 From 40eb90e9ccc3f96f937ea1db79d0f9cb61553ed5 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Sun, 29 May 2016 17:42:13 +0800 Subject: sctp: sctp_diag should dump sctp socket type Now we cannot distinguish that one sk is a udp or sctp style when we use ss to dump sctp_info. it's necessary to dump it as well. For sctp_diag, ss support is not officially available, thus there are no official users of this yet, so we can add this field in the middle of sctp_info without breaking user API. v1->v2: - move 'sctpi_s_type' field to the end of struct sctp_info, so that it won't cause incompatibility with applications already built. - add __reserved3 in sctp_info to make sure sctp_info is 8-byte alignment. Signed-off-by: Xin Long Acked-by: Marcelo Ricardo Leitner Acked-by: Neil Horman Signed-off-by: David S. Miller --- include/linux/sctp.h | 2 ++ net/sctp/socket.c | 1 + 2 files changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/sctp.h b/include/linux/sctp.h index dacb5e711994..de1f64318fc4 100644 --- a/include/linux/sctp.h +++ b/include/linux/sctp.h @@ -765,6 +765,8 @@ struct sctp_info { __u8 sctpi_s_disable_fragments; __u8 sctpi_s_v4mapped; __u8 sctpi_s_frag_interleave; + __u32 sctpi_s_type; + __u32 __reserved3; }; struct sctp_infox { diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 777d0324594a..67154b848aa9 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -4220,6 +4220,7 @@ int sctp_get_sctp_info(struct sock *sk, struct sctp_association *asoc, info->sctpi_s_disable_fragments = sp->disable_fragments; info->sctpi_s_v4mapped = sp->v4mapped; info->sctpi_s_frag_interleave = sp->frag_interleave; + info->sctpi_s_type = sp->type; return 0; } -- cgit v1.2.3 From 480ce08a70e4179f34808a3bdbfe6627f624cf54 Mon Sep 17 00:00:00 2001 From: "Yan, Zheng" Date: Fri, 20 May 2016 18:32:31 +0800 Subject: FS-Cache: make check_consistency callback return int __fscache_check_consistency() calls check_consistency() callback and return the callback's return value. But the return type of check_consistency() is bool. So __fscache_check_consistency() return 1 if the cache is inconsistent. This is inconsistent with the document. Signed-off-by: Yan, Zheng Acked-by: David Howells --- fs/cachefiles/interface.c | 2 +- include/linux/fscache-cache.h | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/fs/cachefiles/interface.c b/fs/cachefiles/interface.c index 861d611b8c05..ce5f345d70f5 100644 --- a/fs/cachefiles/interface.c +++ b/fs/cachefiles/interface.c @@ -380,7 +380,7 @@ static void cachefiles_sync_cache(struct fscache_cache *_cache) * check if the backing cache is updated to FS-Cache * - called by FS-Cache when evaluates if need to invalidate the cache */ -static bool cachefiles_check_consistency(struct fscache_operation *op) +static int cachefiles_check_consistency(struct fscache_operation *op) { struct cachefiles_object *object; struct cachefiles_cache *cache; diff --git a/include/linux/fscache-cache.h b/include/linux/fscache-cache.h index 604e1526cd00..13ba552e6c09 100644 --- a/include/linux/fscache-cache.h +++ b/include/linux/fscache-cache.h @@ -241,7 +241,7 @@ struct fscache_cache_ops { /* check the consistency between the backing cache and the FS-Cache * cookie */ - bool (*check_consistency)(struct fscache_operation *op); + int (*check_consistency)(struct fscache_operation *op); /* store the updated auxiliary data on an object */ void (*update_object)(struct fscache_object *object); -- cgit v1.2.3 From dfc2507b26af22b0bbc85251b8545b36d8bc5d72 Mon Sep 17 00:00:00 2001 From: John Stultz Date: Wed, 1 Jun 2016 11:53:26 -0700 Subject: time: Make settimeofday error checking work again In commit 86d3473224b0 some of the checking for a valid timeval was subtley changed which caused -EINVAL to be returned whenever the timeval was null. However, it is possible to set the timezone data while specifying a NULL timeval, which is usually done to handle systems where the RTC keeps local time instead of UTC. Thus the patch causes such systems to have the time incorrectly set. This patch addresses the issue by handling the error conditionals in the same way as was done previously. Fixes: 86d3473224b0 "time: Introduce do_sys_settimeofday64()" Reported-by: Mika Westerberg Signed-off-by: John Stultz Tested-by: Mika Westerberg Cc: Prarit Bhargava Cc: Arnd Bergmann Cc: Baolin Wang Cc: Richard Cochran Cc: Shuah Khan Link: http://lkml.kernel.org/r/1464807207-16530-2-git-send-email-john.stultz@linaro.org Signed-off-by: Thomas Gleixner --- include/linux/timekeeping.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h index 37dbacf84849..816b7543f81b 100644 --- a/include/linux/timekeeping.h +++ b/include/linux/timekeeping.h @@ -21,6 +21,9 @@ static inline int do_sys_settimeofday(const struct timespec *tv, struct timespec64 ts64; if (!tv) + return do_sys_settimeofday64(NULL, tz); + + if (!timespec_valid(tv)) return -EINVAL; ts64 = timespec_to_timespec64(*tv); -- cgit v1.2.3 From dd5f1b049dc139876801db3cdd0f20d21fd428cc Mon Sep 17 00:00:00 2001 From: Marc Zyngier Date: Thu, 2 Jun 2016 09:00:28 +0100 Subject: irqchip/gic-v3: Fix ICC_SGI1R_EL1.INTID decoding mask The INTID mask is wrong, and is made a signed value, which has nteresting effects in the KVM emulation. Let's sanitize it. Cc: stable@vger.kernel.org Signed-off-by: Marc Zyngier --- include/linux/irqchip/arm-gic-v3.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h index bfbd707de390..85a8c2acdef5 100644 --- a/include/linux/irqchip/arm-gic-v3.h +++ b/include/linux/irqchip/arm-gic-v3.h @@ -305,7 +305,7 @@ #define ICC_SGI1R_AFFINITY_1_SHIFT 16 #define ICC_SGI1R_AFFINITY_1_MASK (0xff << ICC_SGI1R_AFFINITY_1_SHIFT) #define ICC_SGI1R_SGI_ID_SHIFT 24 -#define ICC_SGI1R_SGI_ID_MASK (0xff << ICC_SGI1R_SGI_ID_SHIFT) +#define ICC_SGI1R_SGI_ID_MASK (0xfULL << ICC_SGI1R_SGI_ID_SHIFT) #define ICC_SGI1R_AFFINITY_2_SHIFT 32 #define ICC_SGI1R_AFFINITY_2_MASK (0xffULL << ICC_SGI1R_AFFINITY_1_SHIFT) #define ICC_SGI1R_IRQ_ROUTING_MODE_BIT 40 -- cgit v1.2.3 From fab0cdc30d81694d2d5524b24e42c43414971719 Mon Sep 17 00:00:00 2001 From: Andrew Jones Date: Thu, 12 May 2016 10:46:34 +0200 Subject: irqchip/gic-v3: Fix copy+paste mistakes in defines ICC_SGI1R_AFFINITY_{2,3}_MASK are unused, which is good because they were defined with the wrong shifts. Signed-off-by: Andrew Jones Signed-off-by: Marc Zyngier --- include/linux/irqchip/arm-gic-v3.h | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'include/linux') diff --git a/include/linux/irqchip/arm-gic-v3.h b/include/linux/irqchip/arm-gic-v3.h index 85a8c2acdef5..dc493e0f0ff7 100644 --- a/include/linux/irqchip/arm-gic-v3.h +++ b/include/linux/irqchip/arm-gic-v3.h @@ -307,10 +307,10 @@ #define ICC_SGI1R_SGI_ID_SHIFT 24 #define ICC_SGI1R_SGI_ID_MASK (0xfULL << ICC_SGI1R_SGI_ID_SHIFT) #define ICC_SGI1R_AFFINITY_2_SHIFT 32 -#define ICC_SGI1R_AFFINITY_2_MASK (0xffULL << ICC_SGI1R_AFFINITY_1_SHIFT) +#define ICC_SGI1R_AFFINITY_2_MASK (0xffULL << ICC_SGI1R_AFFINITY_2_SHIFT) #define ICC_SGI1R_IRQ_ROUTING_MODE_BIT 40 #define ICC_SGI1R_AFFINITY_3_SHIFT 48 -#define ICC_SGI1R_AFFINITY_3_MASK (0xffULL << ICC_SGI1R_AFFINITY_1_SHIFT) +#define ICC_SGI1R_AFFINITY_3_MASK (0xffULL << ICC_SGI1R_AFFINITY_3_SHIFT) #include -- cgit v1.2.3 From f86e4271978bd93db466d6a95dad4b0fdcdb04f6 Mon Sep 17 00:00:00 2001 From: Yang Shi Date: Fri, 3 Jun 2016 14:55:38 -0700 Subject: mm: check the return value of lookup_page_ext for all call sites Per the discussion with Joonsoo Kim [1], we need check the return value of lookup_page_ext() for all call sites since it might return NULL in some cases, although it is unlikely, i.e. memory hotplug. Tested with ltp with "page_owner=0". [1] http://lkml.kernel.org/r/20160519002809.GA10245@js1304-P5Q-DELUXE [akpm@linux-foundation.org: fix build-breaking typos] [arnd@arndb.de: fix build problems from lookup_page_ext] Link: http://lkml.kernel.org/r/6285269.2CksypHdYp@wuerfel [akpm@linux-foundation.org: coding-style fixes] Link: http://lkml.kernel.org/r/1464023768-31025-1-git-send-email-yang.shi@linaro.org Signed-off-by: Yang Shi Signed-off-by: Arnd Bergmann Cc: Joonsoo Kim Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/page_idle.h | 43 ++++++++++++++++++++++++++++++++++++------- mm/page_alloc.c | 6 ++++++ mm/page_owner.c | 26 ++++++++++++++++++++++++++ mm/page_poison.c | 8 +++++++- mm/vmstat.c | 2 ++ 5 files changed, 77 insertions(+), 8 deletions(-) (limited to 'include/linux') diff --git a/include/linux/page_idle.h b/include/linux/page_idle.h index bf268fa92c5b..fec40271339f 100644 --- a/include/linux/page_idle.h +++ b/include/linux/page_idle.h @@ -46,33 +46,62 @@ extern struct page_ext_operations page_idle_ops; static inline bool page_is_young(struct page *page) { - return test_bit(PAGE_EXT_YOUNG, &lookup_page_ext(page)->flags); + struct page_ext *page_ext = lookup_page_ext(page); + + if (unlikely(!page_ext)) + return false; + + return test_bit(PAGE_EXT_YOUNG, &page_ext->flags); } static inline void set_page_young(struct page *page) { - set_bit(PAGE_EXT_YOUNG, &lookup_page_ext(page)->flags); + struct page_ext *page_ext = lookup_page_ext(page); + + if (unlikely(!page_ext)) + return; + + set_bit(PAGE_EXT_YOUNG, &page_ext->flags); } static inline bool test_and_clear_page_young(struct page *page) { - return test_and_clear_bit(PAGE_EXT_YOUNG, - &lookup_page_ext(page)->flags); + struct page_ext *page_ext = lookup_page_ext(page); + + if (unlikely(!page_ext)) + return false; + + return test_and_clear_bit(PAGE_EXT_YOUNG, &page_ext->flags); } static inline bool page_is_idle(struct page *page) { - return test_bit(PAGE_EXT_IDLE, &lookup_page_ext(page)->flags); + struct page_ext *page_ext = lookup_page_ext(page); + + if (unlikely(!page_ext)) + return false; + + return test_bit(PAGE_EXT_IDLE, &page_ext->flags); } static inline void set_page_idle(struct page *page) { - set_bit(PAGE_EXT_IDLE, &lookup_page_ext(page)->flags); + struct page_ext *page_ext = lookup_page_ext(page); + + if (unlikely(!page_ext)) + return; + + set_bit(PAGE_EXT_IDLE, &page_ext->flags); } static inline void clear_page_idle(struct page *page) { - clear_bit(PAGE_EXT_IDLE, &lookup_page_ext(page)->flags); + struct page_ext *page_ext = lookup_page_ext(page); + + if (unlikely(!page_ext)) + return; + + clear_bit(PAGE_EXT_IDLE, &page_ext->flags); } #endif /* CONFIG_64BIT */ diff --git a/mm/page_alloc.c b/mm/page_alloc.c index f8f3bfc435ee..d27e8b968ac3 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -656,6 +656,9 @@ static inline void set_page_guard(struct zone *zone, struct page *page, return; page_ext = lookup_page_ext(page); + if (unlikely(!page_ext)) + return; + __set_bit(PAGE_EXT_DEBUG_GUARD, &page_ext->flags); INIT_LIST_HEAD(&page->lru); @@ -673,6 +676,9 @@ static inline void clear_page_guard(struct zone *zone, struct page *page, return; page_ext = lookup_page_ext(page); + if (unlikely(!page_ext)) + return; + __clear_bit(PAGE_EXT_DEBUG_GUARD, &page_ext->flags); set_page_private(page, 0); diff --git a/mm/page_owner.c b/mm/page_owner.c index 792b56da13d8..c6cda3e36212 100644 --- a/mm/page_owner.c +++ b/mm/page_owner.c @@ -55,6 +55,8 @@ void __reset_page_owner(struct page *page, unsigned int order) for (i = 0; i < (1 << order); i++) { page_ext = lookup_page_ext(page + i); + if (unlikely(!page_ext)) + continue; __clear_bit(PAGE_EXT_OWNER, &page_ext->flags); } } @@ -62,6 +64,7 @@ void __reset_page_owner(struct page *page, unsigned int order) void __set_page_owner(struct page *page, unsigned int order, gfp_t gfp_mask) { struct page_ext *page_ext = lookup_page_ext(page); + struct stack_trace trace = { .nr_entries = 0, .max_entries = ARRAY_SIZE(page_ext->trace_entries), @@ -69,6 +72,9 @@ void __set_page_owner(struct page *page, unsigned int order, gfp_t gfp_mask) .skip = 3, }; + if (unlikely(!page_ext)) + return; + save_stack_trace(&trace); page_ext->order = order; @@ -82,6 +88,8 @@ void __set_page_owner(struct page *page, unsigned int order, gfp_t gfp_mask) void __set_page_owner_migrate_reason(struct page *page, int reason) { struct page_ext *page_ext = lookup_page_ext(page); + if (unlikely(!page_ext)) + return; page_ext->last_migrate_reason = reason; } @@ -89,6 +97,12 @@ void __set_page_owner_migrate_reason(struct page *page, int reason) gfp_t __get_page_owner_gfp(struct page *page) { struct page_ext *page_ext = lookup_page_ext(page); + if (unlikely(!page_ext)) + /* + * The caller just returns 0 if no valid gfp + * So return 0 here too. + */ + return 0; return page_ext->gfp_mask; } @@ -99,6 +113,9 @@ void __copy_page_owner(struct page *oldpage, struct page *newpage) struct page_ext *new_ext = lookup_page_ext(newpage); int i; + if (unlikely(!old_ext || !new_ext)) + return; + new_ext->order = old_ext->order; new_ext->gfp_mask = old_ext->gfp_mask; new_ext->nr_entries = old_ext->nr_entries; @@ -193,6 +210,11 @@ void __dump_page_owner(struct page *page) gfp_t gfp_mask = page_ext->gfp_mask; int mt = gfpflags_to_migratetype(gfp_mask); + if (unlikely(!page_ext)) { + pr_alert("There is not page extension available.\n"); + return; + } + if (!test_bit(PAGE_EXT_OWNER, &page_ext->flags)) { pr_alert("page_owner info is not active (free page?)\n"); return; @@ -251,6 +273,8 @@ read_page_owner(struct file *file, char __user *buf, size_t count, loff_t *ppos) } page_ext = lookup_page_ext(page); + if (unlikely(!page_ext)) + continue; /* * Some pages could be missed by concurrent allocation or free, @@ -317,6 +341,8 @@ static void init_pages_in_zone(pg_data_t *pgdat, struct zone *zone) continue; page_ext = lookup_page_ext(page); + if (unlikely(!page_ext)) + continue; /* Maybe overraping zone */ if (test_bit(PAGE_EXT_OWNER, &page_ext->flags)) diff --git a/mm/page_poison.c b/mm/page_poison.c index 1eae5fad2446..2e647c65916b 100644 --- a/mm/page_poison.c +++ b/mm/page_poison.c @@ -54,6 +54,9 @@ static inline void set_page_poison(struct page *page) struct page_ext *page_ext; page_ext = lookup_page_ext(page); + if (unlikely(!page_ext)) + return; + __set_bit(PAGE_EXT_DEBUG_POISON, &page_ext->flags); } @@ -62,6 +65,9 @@ static inline void clear_page_poison(struct page *page) struct page_ext *page_ext; page_ext = lookup_page_ext(page); + if (unlikely(!page_ext)) + return; + __clear_bit(PAGE_EXT_DEBUG_POISON, &page_ext->flags); } @@ -70,7 +76,7 @@ bool page_is_poisoned(struct page *page) struct page_ext *page_ext; page_ext = lookup_page_ext(page); - if (!page_ext) + if (unlikely(!page_ext)) return false; return test_bit(PAGE_EXT_DEBUG_POISON, &page_ext->flags); diff --git a/mm/vmstat.c b/mm/vmstat.c index 77e42ef388c2..cb2a67bb4158 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -1061,6 +1061,8 @@ static void pagetypeinfo_showmixedcount_print(struct seq_file *m, continue; page_ext = lookup_page_ext(page); + if (unlikely(!page_ext)) + continue; if (!test_bit(PAGE_EXT_OWNER, &page_ext->flags)) continue; -- cgit v1.2.3 From eedf265aa003b4781de24cfed40a655a664457e6 Mon Sep 17 00:00:00 2001 From: "Eric W. Biederman" Date: Thu, 2 Jun 2016 10:29:47 -0500 Subject: devpts: Make each mount of devpts an independent filesystem. The /dev/ptmx device node is changed to lookup the directory entry "pts" in the same directory as the /dev/ptmx device node was opened in. If there is a "pts" entry and that entry is a devpts filesystem /dev/ptmx uses that filesystem. Otherwise the open of /dev/ptmx fails. The DEVPTS_MULTIPLE_INSTANCES configuration option is removed, so that userspace can now safely depend on each mount of devpts creating a new instance of the filesystem. Each mount of devpts is now a separate and equal filesystem. Reserved ttys are now available to all instances of devpts where the mounter is in the initial mount namespace. A new vfs helper path_pts is introduced that finds a directory entry named "pts" in the directory of the passed in path, and changes the passed in path to point to it. The helper path_pts uses a function path_parent_directory that was factored out of follow_dotdot. In the implementation of devpts: - devpts_mnt is killed as it is no longer meaningful if all mounts of devpts are equal. - pts_sb_from_inode is replaced by just inode->i_sb as all cached inodes in the tty layer are now from the devpts filesystem. - devpts_add_ref is rolled into the new function devpts_ptmx. And the unnecessary inode hold is removed. - devpts_del_ref is renamed devpts_release and reduced to just a deacrivate_super. - The newinstance mount option continues to be accepted but is now ignored. In devpts_fs.h definitions for when !CONFIG_UNIX98_PTYS are removed as they are never used. Documentation/filesystems/devices.txt is updated to describe the current situation. This has been verified to work properly on openwrt-15.05, centos5, centos6, centos7, debian-6.0.2, debian-7.9, debian-8.2, ubuntu-14.04.3, ubuntu-15.10, fedora23, magia-5, mint-17.3, opensuse-42.1, slackware-14.1, gentoo-20151225 (13.0?), archlinux-2015-12-01. With the caveat that on centos6 and on slackware-14.1 that there wind up being two instances of the devpts filesystem mounted on /dev/pts, the lower copy does not end up getting used. Signed-off-by: "Eric W. Biederman" Cc: Greg KH Cc: Peter Hurley Cc: Peter Anvin Cc: Andy Lutomirski Cc: Al Viro Cc: Serge Hallyn Cc: Willy Tarreau Cc: Aurelien Jarno Cc: One Thousand Gnomes Cc: Jann Horn Cc: Jiri Slaby Cc: Florian Weimer Cc: Konstantin Khlebnikov Signed-off-by: Linus Torvalds --- Documentation/filesystems/devpts.txt | 145 +++----------------------- drivers/tty/Kconfig | 11 -- drivers/tty/pty.c | 15 +-- fs/devpts/inode.c | 191 ++++++++++------------------------- fs/namei.c | 49 +++++++-- include/linux/devpts_fs.h | 9 +- include/linux/namei.h | 2 + 7 files changed, 126 insertions(+), 296 deletions(-) (limited to 'include/linux') diff --git a/Documentation/filesystems/devpts.txt b/Documentation/filesystems/devpts.txt index 30d2fcb32f72..9f94fe276dea 100644 --- a/Documentation/filesystems/devpts.txt +++ b/Documentation/filesystems/devpts.txt @@ -1,141 +1,26 @@ +Each mount of the devpts filesystem is now distinct such that ptys +and their indicies allocated in one mount are independent from ptys +and their indicies in all other mounts. -To support containers, we now allow multiple instances of devpts filesystem, -such that indices of ptys allocated in one instance are independent of indices -allocated in other instances of devpts. +All mounts of the devpts filesystem now create a /dev/pts/ptmx node +with permissions 0000. -To preserve backward compatibility, this support for multiple instances is -enabled only if: +To retain backwards compatibility the a ptmx device node (aka any node +created with "mknod name c 5 2") when opened will look for an instance +of devpts under the name "pts" in the same directory as the ptmx device +node. - - CONFIG_DEVPTS_MULTIPLE_INSTANCES=y, and - - '-o newinstance' mount option is specified while mounting devpts - -IOW, devpts now supports both single-instance and multi-instance semantics. - -If CONFIG_DEVPTS_MULTIPLE_INSTANCES=n, there is no change in behavior and -this referred to as the "legacy" mode. In this mode, the new mount options -(-o newinstance and -o ptmxmode) will be ignored with a 'bogus option' message -on console. - -If CONFIG_DEVPTS_MULTIPLE_INSTANCES=y and devpts is mounted without the -'newinstance' option (as in current start-up scripts) the new mount binds -to the initial kernel mount of devpts. This mode is referred to as the -'single-instance' mode and the current, single-instance semantics are -preserved, i.e PTYs are common across the system. - -The only difference between this single-instance mode and the legacy mode -is the presence of new, '/dev/pts/ptmx' node with permissions 0000, which -can safely be ignored. - -If CONFIG_DEVPTS_MULTIPLE_INSTANCES=y and 'newinstance' option is specified, -the mount is considered to be in the multi-instance mode and a new instance -of the devpts fs is created. Any ptys created in this instance are independent -of ptys in other instances of devpts. Like in the single-instance mode, the -/dev/pts/ptmx node is present. To effectively use the multi-instance mode, -open of /dev/ptmx must be a redirected to '/dev/pts/ptmx' using a symlink or -bind-mount. - -Eg: A container startup script could do the following: - - $ chmod 0666 /dev/pts/ptmx - $ rm /dev/ptmx - $ ln -s pts/ptmx /dev/ptmx - $ ns_exec -cm /bin/bash - - # We are now in new container - - $ umount /dev/pts - $ mount -t devpts -o newinstance lxcpts /dev/pts - $ sshd -p 1234 - -where 'ns_exec -cm /bin/bash' calls clone() with CLONE_NEWNS flag and execs -/bin/bash in the child process. A pty created by the sshd is not visible in -the original mount of /dev/pts. +As an option instead of placing a /dev/ptmx device node at /dev/ptmx +it is possible to place a symlink to /dev/pts/ptmx at /dev/ptmx or +to bind mount /dev/ptx/ptmx to /dev/ptmx. If you opt for using +the devpts filesystem in this manner devpts should be mounted with +the ptmxmode=0666, or chmod 0666 /dev/pts/ptmx should be called. Total count of pty pairs in all instances is limited by sysctls: kernel.pty.max = 4096 - global limit -kernel.pty.reserve = 1024 - reserve for initial instance +kernel.pty.reserve = 1024 - reserved for filesystems mounted from the initial mount namespace kernel.pty.nr - current count of ptys Per-instance limit could be set by adding mount option "max=". This feature was added in kernel 3.4 together with sysctl kernel.pty.reserve. In kernels older than 3.4 sysctl kernel.pty.max works as per-instance limit. - -User-space changes ------------------- - -In multi-instance mode (i.e '-o newinstance' mount option is specified at least -once), following user-space issues should be noted. - -1. If -o newinstance mount option is never used, /dev/pts/ptmx can be ignored - and no change is needed to system-startup scripts. - -2. To effectively use multi-instance mode (i.e -o newinstance is specified) - administrators or startup scripts should "redirect" open of /dev/ptmx to - /dev/pts/ptmx using either a bind mount or symlink. - - $ mount -t devpts -o newinstance devpts /dev/pts - - followed by either - - $ rm /dev/ptmx - $ ln -s pts/ptmx /dev/ptmx - $ chmod 666 /dev/pts/ptmx - or - $ mount -o bind /dev/pts/ptmx /dev/ptmx - -3. The '/dev/ptmx -> pts/ptmx' symlink is the preferred method since it - enables better error-reporting and treats both single-instance and - multi-instance mounts similarly. - - But this method requires that system-startup scripts set the mode of - /dev/pts/ptmx correctly (default mode is 0000). The scripts can set the - mode by, either - - - adding ptmxmode mount option to devpts entry in /etc/fstab, or - - using 'chmod 0666 /dev/pts/ptmx' - -4. If multi-instance mode mount is needed for containers, but the system - startup scripts have not yet been updated, container-startup scripts - should bind mount /dev/ptmx to /dev/pts/ptmx to avoid breaking single- - instance mounts. - - Or, in general, container-startup scripts should use: - - mount -t devpts -o newinstance -o ptmxmode=0666 devpts /dev/pts - if [ ! -L /dev/ptmx ]; then - mount -o bind /dev/pts/ptmx /dev/ptmx - fi - - When all devpts mounts are multi-instance, /dev/ptmx can permanently be - a symlink to pts/ptmx and the bind mount can be ignored. - -5. A multi-instance mount that is not accompanied by the /dev/ptmx to - /dev/pts/ptmx redirection would result in an unusable/unreachable pty. - - mount -t devpts -o newinstance lxcpts /dev/pts - - immediately followed by: - - open("/dev/ptmx") - - would create a pty, say /dev/pts/7, in the initial kernel mount. - But /dev/pts/7 would be invisible in the new mount. - -6. The permissions for /dev/pts/ptmx node should be specified when mounting - /dev/pts, using the '-o ptmxmode=%o' mount option (default is 0000). - - mount -t devpts -o newinstance -o ptmxmode=0644 devpts /dev/pts - - The permissions can be later be changed as usual with 'chmod'. - - chmod 666 /dev/pts/ptmx - -7. A mount of devpts without the 'newinstance' option results in binding to - initial kernel mount. This behavior while preserving legacy semantics, - does not provide strict isolation in a container environment. i.e by - mounting devpts without the 'newinstance' option, a container could - get visibility into the 'host' or root container's devpts. - - To workaround this and have strict isolation, all mounts of devpts, - including the mount in the root container, should use the newinstance - option. diff --git a/drivers/tty/Kconfig b/drivers/tty/Kconfig index 82c4d2e45319..95103054c0e4 100644 --- a/drivers/tty/Kconfig +++ b/drivers/tty/Kconfig @@ -120,17 +120,6 @@ config UNIX98_PTYS All modern Linux systems use the Unix98 ptys. Say Y unless you're on an embedded system and want to conserve memory. -config DEVPTS_MULTIPLE_INSTANCES - bool "Support multiple instances of devpts" - depends on UNIX98_PTYS - default n - ---help--- - Enable support for multiple instances of devpts filesystem. - If you want to have isolated PTY namespaces (eg: in containers), - say Y here. Otherwise, say N. If enabled, each mount of devpts - filesystem with the '-o newinstance' option will create an - independent PTY namespace. - config LEGACY_PTYS bool "Legacy (BSD) PTY support" default y diff --git a/drivers/tty/pty.c b/drivers/tty/pty.c index dd4b8417e7f4..f856c4544eea 100644 --- a/drivers/tty/pty.c +++ b/drivers/tty/pty.c @@ -668,7 +668,7 @@ static void pty_unix98_remove(struct tty_driver *driver, struct tty_struct *tty) else fsi = tty->link->driver_data; devpts_kill_index(fsi, tty->index); - devpts_put_ref(fsi); + devpts_release(fsi); } static const struct tty_operations ptm_unix98_ops = { @@ -733,10 +733,11 @@ static int ptmx_open(struct inode *inode, struct file *filp) if (retval) return retval; - fsi = devpts_get_ref(inode, filp); - retval = -ENODEV; - if (!fsi) + fsi = devpts_acquire(filp); + if (IS_ERR(fsi)) { + retval = PTR_ERR(fsi); goto out_free_file; + } /* find a device that is not in use. */ mutex_lock(&devpts_mutex); @@ -745,7 +746,7 @@ static int ptmx_open(struct inode *inode, struct file *filp) retval = index; if (index < 0) - goto out_put_ref; + goto out_put_fsi; mutex_lock(&tty_mutex); @@ -789,8 +790,8 @@ err_release: return retval; out: devpts_kill_index(fsi, index); -out_put_ref: - devpts_put_ref(fsi); +out_put_fsi: + devpts_release(fsi); out_free_file: tty_free_file(filp); return retval; diff --git a/fs/devpts/inode.c b/fs/devpts/inode.c index 0b2954d7172d..37c134a132c7 100644 --- a/fs/devpts/inode.c +++ b/fs/devpts/inode.c @@ -95,8 +95,6 @@ static struct ctl_table pty_root_table[] = { static DEFINE_MUTEX(allocated_ptys_lock); -static struct vfsmount *devpts_mnt; - struct pts_mount_opts { int setuid; int setgid; @@ -104,7 +102,7 @@ struct pts_mount_opts { kgid_t gid; umode_t mode; umode_t ptmxmode; - int newinstance; + int reserve; int max; }; @@ -117,11 +115,9 @@ static const match_table_t tokens = { {Opt_uid, "uid=%u"}, {Opt_gid, "gid=%u"}, {Opt_mode, "mode=%o"}, -#ifdef CONFIG_DEVPTS_MULTIPLE_INSTANCES {Opt_ptmxmode, "ptmxmode=%o"}, {Opt_newinstance, "newinstance"}, {Opt_max, "max=%d"}, -#endif {Opt_err, NULL} }; @@ -137,15 +133,48 @@ static inline struct pts_fs_info *DEVPTS_SB(struct super_block *sb) return sb->s_fs_info; } -static inline struct super_block *pts_sb_from_inode(struct inode *inode) +struct pts_fs_info *devpts_acquire(struct file *filp) { -#ifdef CONFIG_DEVPTS_MULTIPLE_INSTANCES - if (inode->i_sb->s_magic == DEVPTS_SUPER_MAGIC) - return inode->i_sb; -#endif - if (!devpts_mnt) - return NULL; - return devpts_mnt->mnt_sb; + struct pts_fs_info *result; + struct path path; + struct super_block *sb; + int err; + + path = filp->f_path; + path_get(&path); + + /* Has the devpts filesystem already been found? */ + sb = path.mnt->mnt_sb; + if (sb->s_magic != DEVPTS_SUPER_MAGIC) { + /* Is a devpts filesystem at "pts" in the same directory? */ + err = path_pts(&path); + if (err) { + result = ERR_PTR(err); + goto out; + } + + /* Is the path the root of a devpts filesystem? */ + result = ERR_PTR(-ENODEV); + sb = path.mnt->mnt_sb; + if ((sb->s_magic != DEVPTS_SUPER_MAGIC) || + (path.mnt->mnt_root != sb->s_root)) + goto out; + } + + /* + * pty code needs to hold extra references in case of last /dev/tty close + */ + atomic_inc(&sb->s_active); + result = DEVPTS_SB(sb); + +out: + path_put(&path); + return result; +} + +void devpts_release(struct pts_fs_info *fsi) +{ + deactivate_super(fsi->sb); } #define PARSE_MOUNT 0 @@ -154,9 +183,7 @@ static inline struct super_block *pts_sb_from_inode(struct inode *inode) /* * parse_mount_options(): * Set @opts to mount options specified in @data. If an option is not - * specified in @data, set it to its default value. The exception is - * 'newinstance' option which can only be set/cleared on a mount (i.e. - * cannot be changed during remount). + * specified in @data, set it to its default value. * * Note: @data may be NULL (in which case all options are set to default). */ @@ -174,9 +201,12 @@ static int parse_mount_options(char *data, int op, struct pts_mount_opts *opts) opts->ptmxmode = DEVPTS_DEFAULT_PTMX_MODE; opts->max = NR_UNIX98_PTY_MAX; - /* newinstance makes sense only on initial mount */ + /* Only allow instances mounted from the initial mount + * namespace to tap the reserve pool of ptys. + */ if (op == PARSE_MOUNT) - opts->newinstance = 0; + opts->reserve = + (current->nsproxy->mnt_ns == init_task.nsproxy->mnt_ns); while ((p = strsep(&data, ",")) != NULL) { substring_t args[MAX_OPT_ARGS]; @@ -211,16 +241,12 @@ static int parse_mount_options(char *data, int op, struct pts_mount_opts *opts) return -EINVAL; opts->mode = option & S_IALLUGO; break; -#ifdef CONFIG_DEVPTS_MULTIPLE_INSTANCES case Opt_ptmxmode: if (match_octal(&args[0], &option)) return -EINVAL; opts->ptmxmode = option & S_IALLUGO; break; case Opt_newinstance: - /* newinstance makes sense only on initial mount */ - if (op == PARSE_MOUNT) - opts->newinstance = 1; break; case Opt_max: if (match_int(&args[0], &option) || @@ -228,7 +254,6 @@ static int parse_mount_options(char *data, int op, struct pts_mount_opts *opts) return -EINVAL; opts->max = option; break; -#endif default: pr_err("called with bogus options\n"); return -EINVAL; @@ -238,7 +263,6 @@ static int parse_mount_options(char *data, int op, struct pts_mount_opts *opts) return 0; } -#ifdef CONFIG_DEVPTS_MULTIPLE_INSTANCES static int mknod_ptmx(struct super_block *sb) { int mode; @@ -305,12 +329,6 @@ static void update_ptmx_mode(struct pts_fs_info *fsi) inode->i_mode = S_IFCHR|fsi->mount_opts.ptmxmode; } } -#else -static inline void update_ptmx_mode(struct pts_fs_info *fsi) -{ - return; -} -#endif static int devpts_remount(struct super_block *sb, int *flags, char *data) { @@ -344,11 +362,9 @@ static int devpts_show_options(struct seq_file *seq, struct dentry *root) seq_printf(seq, ",gid=%u", from_kgid_munged(&init_user_ns, opts->gid)); seq_printf(seq, ",mode=%03o", opts->mode); -#ifdef CONFIG_DEVPTS_MULTIPLE_INSTANCES seq_printf(seq, ",ptmxmode=%03o", opts->ptmxmode); if (opts->max < NR_UNIX98_PTY_MAX) seq_printf(seq, ",max=%d", opts->max); -#endif return 0; } @@ -410,40 +426,11 @@ fail: return -ENOMEM; } -#ifdef CONFIG_DEVPTS_MULTIPLE_INSTANCES -static int compare_init_pts_sb(struct super_block *s, void *p) -{ - if (devpts_mnt) - return devpts_mnt->mnt_sb == s; - return 0; -} - /* * devpts_mount() * - * If the '-o newinstance' mount option was specified, mount a new - * (private) instance of devpts. PTYs created in this instance are - * independent of the PTYs in other devpts instances. - * - * If the '-o newinstance' option was not specified, mount/remount the - * initial kernel mount of devpts. This type of mount gives the - * legacy, single-instance semantics. - * - * The 'newinstance' option is needed to support multiple namespace - * semantics in devpts while preserving backward compatibility of the - * current 'single-namespace' semantics. i.e all mounts of devpts - * without the 'newinstance' mount option should bind to the initial - * kernel mount, like mount_single(). - * - * Mounts with 'newinstance' option create a new, private namespace. - * - * NOTE: - * - * For single-mount semantics, devpts cannot use mount_single(), - * because mount_single()/sget() find and use the super-block from - * the most recent mount of devpts. But that recent mount may be a - * 'newinstance' mount and mount_single() would pick the newinstance - * super-block instead of the initial super-block. + * Mount a new (private) instance of devpts. PTYs created in this + * instance are independent of the PTYs in other devpts instances. */ static struct dentry *devpts_mount(struct file_system_type *fs_type, int flags, const char *dev_name, void *data) @@ -456,18 +443,7 @@ static struct dentry *devpts_mount(struct file_system_type *fs_type, if (error) return ERR_PTR(error); - /* Require newinstance for all user namespace mounts to ensure - * the mount options are not changed. - */ - if ((current_user_ns() != &init_user_ns) && !opts.newinstance) - return ERR_PTR(-EINVAL); - - if (opts.newinstance) - s = sget(fs_type, NULL, set_anon_super, flags, NULL); - else - s = sget(fs_type, compare_init_pts_sb, set_anon_super, flags, - NULL); - + s = sget(fs_type, NULL, set_anon_super, flags, NULL); if (IS_ERR(s)) return ERR_CAST(s); @@ -491,18 +467,6 @@ out_undo_sget: return ERR_PTR(error); } -#else -/* - * This supports only the legacy single-instance semantics (no - * multiple-instance semantics) - */ -static struct dentry *devpts_mount(struct file_system_type *fs_type, int flags, - const char *dev_name, void *data) -{ - return mount_single(fs_type, flags, data, devpts_fill_super); -} -#endif - static void devpts_kill_sb(struct super_block *sb) { struct pts_fs_info *fsi = DEVPTS_SB(sb); @@ -516,9 +480,7 @@ static struct file_system_type devpts_fs_type = { .name = "devpts", .mount = devpts_mount, .kill_sb = devpts_kill_sb, -#ifdef CONFIG_DEVPTS_MULTIPLE_INSTANCES .fs_flags = FS_USERNS_MOUNT | FS_USERNS_DEV_MOUNT, -#endif }; /* @@ -531,16 +493,13 @@ int devpts_new_index(struct pts_fs_info *fsi) int index; int ida_ret; - if (!fsi) - return -ENODEV; - retry: if (!ida_pre_get(&fsi->allocated_ptys, GFP_KERNEL)) return -ENOMEM; mutex_lock(&allocated_ptys_lock); - if (pty_count >= pty_limit - - (fsi->mount_opts.newinstance ? pty_reserve : 0)) { + if (pty_count >= (pty_limit - + (fsi->mount_opts.reserve ? 0 : pty_reserve))) { mutex_unlock(&allocated_ptys_lock); return -ENOSPC; } @@ -571,30 +530,6 @@ void devpts_kill_index(struct pts_fs_info *fsi, int idx) mutex_unlock(&allocated_ptys_lock); } -/* - * pty code needs to hold extra references in case of last /dev/tty close - */ -struct pts_fs_info *devpts_get_ref(struct inode *ptmx_inode, struct file *file) -{ - struct super_block *sb; - struct pts_fs_info *fsi; - - sb = pts_sb_from_inode(ptmx_inode); - if (!sb) - return NULL; - fsi = DEVPTS_SB(sb); - if (!fsi) - return NULL; - - atomic_inc(&sb->s_active); - return fsi; -} - -void devpts_put_ref(struct pts_fs_info *fsi) -{ - deactivate_super(fsi->sb); -} - /** * devpts_pty_new -- create a new inode in /dev/pts/ * @ptmx_inode: inode of the master @@ -607,16 +542,12 @@ void devpts_put_ref(struct pts_fs_info *fsi) struct dentry *devpts_pty_new(struct pts_fs_info *fsi, int index, void *priv) { struct dentry *dentry; - struct super_block *sb; + struct super_block *sb = fsi->sb; struct inode *inode; struct dentry *root; struct pts_mount_opts *opts; char s[12]; - if (!fsi) - return ERR_PTR(-ENODEV); - - sb = fsi->sb; root = sb->s_root; opts = &fsi->mount_opts; @@ -676,20 +607,8 @@ void devpts_pty_kill(struct dentry *dentry) static int __init init_devpts_fs(void) { int err = register_filesystem(&devpts_fs_type); - struct ctl_table_header *table; - if (!err) { - struct vfsmount *mnt; - - table = register_sysctl_table(pty_root_table); - mnt = kern_mount(&devpts_fs_type); - if (IS_ERR(mnt)) { - err = PTR_ERR(mnt); - unregister_filesystem(&devpts_fs_type); - unregister_sysctl_table(table); - } else { - devpts_mnt = mnt; - } + register_sysctl_table(pty_root_table); } return err; } diff --git a/fs/namei.c b/fs/namei.c index 4c4f95ac8aa5..6a82fb7e2127 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -1416,21 +1416,28 @@ static void follow_mount(struct path *path) } } +static int path_parent_directory(struct path *path) +{ + struct dentry *old = path->dentry; + /* rare case of legitimate dget_parent()... */ + path->dentry = dget_parent(path->dentry); + dput(old); + if (unlikely(!path_connected(path))) + return -ENOENT; + return 0; +} + static int follow_dotdot(struct nameidata *nd) { while(1) { - struct dentry *old = nd->path.dentry; - if (nd->path.dentry == nd->root.dentry && nd->path.mnt == nd->root.mnt) { break; } if (nd->path.dentry != nd->path.mnt->mnt_root) { - /* rare case of legitimate dget_parent()... */ - nd->path.dentry = dget_parent(nd->path.dentry); - dput(old); - if (unlikely(!path_connected(&nd->path))) - return -ENOENT; + int ret = path_parent_directory(&nd->path); + if (ret) + return ret; break; } if (!follow_up(&nd->path)) @@ -2514,6 +2521,34 @@ struct dentry *lookup_one_len_unlocked(const char *name, } EXPORT_SYMBOL(lookup_one_len_unlocked); +#ifdef CONFIG_UNIX98_PTYS +int path_pts(struct path *path) +{ + /* Find something mounted on "pts" in the same directory as + * the input path. + */ + struct dentry *child, *parent; + struct qstr this; + int ret; + + ret = path_parent_directory(path); + if (ret) + return ret; + + parent = path->dentry; + this.name = "pts"; + this.len = 3; + child = d_hash_and_lookup(parent, &this); + if (!child) + return -ENOENT; + + path->dentry = child; + dput(parent); + follow_mount(path); + return 0; +} +#endif + int user_path_at_empty(int dfd, const char __user *name, unsigned flags, struct path *path, int *empty) { diff --git a/include/linux/devpts_fs.h b/include/linux/devpts_fs.h index 5871f292b596..277ab9af9ac2 100644 --- a/include/linux/devpts_fs.h +++ b/include/linux/devpts_fs.h @@ -15,13 +15,12 @@ #include -struct pts_fs_info; - #ifdef CONFIG_UNIX98_PTYS -/* Look up a pts fs info and get a ref to it */ -struct pts_fs_info *devpts_get_ref(struct inode *, struct file *); -void devpts_put_ref(struct pts_fs_info *); +struct pts_fs_info; + +struct pts_fs_info *devpts_acquire(struct file *); +void devpts_release(struct pts_fs_info *); int devpts_new_index(struct pts_fs_info *); void devpts_kill_index(struct pts_fs_info *, int); diff --git a/include/linux/namei.h b/include/linux/namei.h index ec5ec2818a28..d3d0398f2a1b 100644 --- a/include/linux/namei.h +++ b/include/linux/namei.h @@ -45,6 +45,8 @@ enum {LAST_NORM, LAST_ROOT, LAST_DOT, LAST_DOTDOT, LAST_BIND}; #define LOOKUP_ROOT 0x2000 #define LOOKUP_EMPTY 0x4000 +extern int path_pts(struct path *path); + extern int user_path_at_empty(int, const char __user *, unsigned, struct path *, int *empty); static inline int user_path_at(int dfd, const char __user *name, unsigned flags, -- cgit v1.2.3