From 292d2e626592e25ade59585815e7b3aa138b25f8 Mon Sep 17 00:00:00 2001 From: Alexander Aring Date: Thu, 11 Nov 2021 22:09:16 -0500 Subject: net: ieee802154: handle iftypes as u32 [ Upstream commit 451dc48c806a7ce9fbec5e7a24ccf4b2c936e834 ] This patch fixes an issue that an u32 netlink value is handled as a signed enum value which doesn't fit into the range of u32 netlink type. If it's handled as -1 value some BIT() evaluation ends in a shift-out-of-bounds issue. To solve the issue we set the to u32 max which is s32 "-1" value to keep backwards compatibility and let the followed enum values start counting at 0. This brings the compiler to never handle the enum as signed and a check if the value is above NL802154_IFTYPE_MAX should filter -1 out. Fixes: f3ea5e44231a ("ieee802154: add new interface command") Signed-off-by: Alexander Aring Link: https://lore.kernel.org/r/20211112030916.685793-1-aahringo@redhat.com Signed-off-by: Stefan Schmidt Signed-off-by: Sasha Levin --- include/net/nl802154.h | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/net/nl802154.h b/include/net/nl802154.h index 32cb3e591e07..53f140fc1983 100644 --- a/include/net/nl802154.h +++ b/include/net/nl802154.h @@ -19,6 +19,8 @@ * */ +#include + #define NL802154_GENL_NAME "nl802154" enum nl802154_commands { @@ -143,10 +145,9 @@ enum nl802154_attrs { }; enum nl802154_iftype { - /* for backwards compatibility TODO */ - NL802154_IFTYPE_UNSPEC = -1, + NL802154_IFTYPE_UNSPEC = (~(__u32)0), - NL802154_IFTYPE_NODE, + NL802154_IFTYPE_NODE = 0, NL802154_IFTYPE_MONITOR, NL802154_IFTYPE_COORD, -- cgit v1.2.3 From 8a8ae093b52ba76b650b493848d67e7b526c8751 Mon Sep 17 00:00:00 2001 From: Nadav Amit Date: Sun, 21 Nov 2021 12:40:07 -0800 Subject: hugetlbfs: flush TLBs correctly after huge_pmd_unshare commit a4a118f2eead1d6c49e00765de89878288d4b890 upstream. When __unmap_hugepage_range() calls to huge_pmd_unshare() succeed, a TLB flush is missing. This TLB flush must be performed before releasing the i_mmap_rwsem, in order to prevent an unshared PMDs page from being released and reused before the TLB flush took place. Arguably, a comprehensive solution would use mmu_gather interface to batch the TLB flushes and the PMDs page release, however it is not an easy solution: (1) try_to_unmap_one() and try_to_migrate_one() also call huge_pmd_unshare() and they cannot use the mmu_gather interface; and (2) deferring the release of the page reference for the PMDs page until after i_mmap_rwsem is dropeed can confuse huge_pmd_unshare() into thinking PMDs are shared when they are not. Fix __unmap_hugepage_range() by adding the missing TLB flush, and forcing a flush when unshare is successful. Fixes: 24669e58477e ("hugetlb: use mmu_gather instead of a temporary linked list for accumulating pages)" # 3.6 Signed-off-by: Nadav Amit Reviewed-by: Mike Kravetz Cc: Aneesh Kumar K.V Cc: KAMEZAWA Hiroyuki Cc: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- include/asm-generic/tlb.h | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'include') diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h index 9dbb739cafa0..5f794f6ec6c7 100644 --- a/include/asm-generic/tlb.h +++ b/include/asm-generic/tlb.h @@ -165,6 +165,13 @@ static inline void __tlb_reset_range(struct mmu_gather *tlb) #define tlb_end_vma __tlb_end_vma #endif +static inline void tlb_flush_pmd_range(struct mmu_gather *tlb, + unsigned long address, unsigned long size) +{ + tlb->start = min(tlb->start, address); + tlb->end = max(tlb->end, address + size); +} + #ifndef __tlb_remove_tlb_entry #define __tlb_remove_tlb_entry(tlb, ptep, address) do { } while (0) #endif -- cgit v1.2.3 From 6f195c7691089c56cd1553a9ca3ca22790c0fe07 Mon Sep 17 00:00:00 2001 From: Lin Ma Date: Tue, 16 Nov 2021 23:27:32 +0800 Subject: NFC: add NCI_UNREG flag to eliminate the race commit 48b71a9e66c2eab60564b1b1c85f4928ed04e406 upstream. There are two sites that calls queue_work() after the destroy_workqueue() and lead to possible UAF. The first site is nci_send_cmd(), which can happen after the nci_close_device as below nfcmrvl_nci_unregister_dev | nfc_genl_dev_up nci_close_device | flush_workqueue | del_timer_sync | nci_unregister_device | nfc_get_device destroy_workqueue | nfc_dev_up nfc_unregister_device | nci_dev_up device_del | nci_open_device | __nci_request | nci_send_cmd | queue_work !!! Another site is nci_cmd_timer, awaked by the nci_cmd_work from the nci_send_cmd. ... | ... nci_unregister_device | queue_work destroy_workqueue | nfc_unregister_device | ... device_del | nci_cmd_work | mod_timer | ... | nci_cmd_timer | queue_work !!! For the above two UAF, the root cause is that the nfc_dev_up can race between the nci_unregister_device routine. Therefore, this patch introduce NCI_UNREG flag to easily eliminate the possible race. In addition, the mutex_lock in nci_close_device can act as a barrier. Signed-off-by: Lin Ma Fixes: 6a2968aaf50c ("NFC: basic NCI protocol implementation") Reviewed-by: Jakub Kicinski Reviewed-by: Krzysztof Kozlowski Link: https://lore.kernel.org/r/20211116152732.19238-1-linma@zju.edu.cn Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- include/net/nfc/nci_core.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include') diff --git a/include/net/nfc/nci_core.h b/include/net/nfc/nci_core.h index f0e951292de8..53bd3c952ed4 100644 --- a/include/net/nfc/nci_core.h +++ b/include/net/nfc/nci_core.h @@ -42,6 +42,7 @@ enum nci_flag { NCI_UP, NCI_DATA_EXCHANGE, NCI_DATA_EXCHANGE_TO, + NCI_UNREG, }; /* NCI device states */ -- cgit v1.2.3 From c233bb6234e13a50184626bf00cd8cbe58b8bc8d Mon Sep 17 00:00:00 2001 From: Alexander Mikhalitsyn Date: Fri, 19 Nov 2021 16:43:21 -0800 Subject: shm: extend forced shm destroy to support objects from several IPC nses commit 85b6d24646e4125c591639841169baa98a2da503 upstream. Currently, the exit_shm() function not designed to work properly when task->sysvshm.shm_clist holds shm objects from different IPC namespaces. This is a real pain when sysctl kernel.shm_rmid_forced = 1, because it leads to use-after-free (reproducer exists). This is an attempt to fix the problem by extending exit_shm mechanism to handle shm's destroy from several IPC ns'es. To achieve that we do several things: 1. add a namespace (non-refcounted) pointer to the struct shmid_kernel 2. during new shm object creation (newseg()/shmget syscall) we initialize this pointer by current task IPC ns 3. exit_shm() fully reworked such that it traverses over all shp's in task->sysvshm.shm_clist and gets IPC namespace not from current task as it was before but from shp's object itself, then call shm_destroy(shp, ns). Note: We need to be really careful here, because as it was said before (1), our pointer to IPC ns non-refcnt'ed. To be on the safe side we using special helper get_ipc_ns_not_zero() which allows to get IPC ns refcounter only if IPC ns not in the "state of destruction". Q/A Q: Why can we access shp->ns memory using non-refcounted pointer? A: Because shp object lifetime is always shorther than IPC namespace lifetime, so, if we get shp object from the task->sysvshm.shm_clist while holding task_lock(task) nobody can steal our namespace. Q: Does this patch change semantics of unshare/setns/clone syscalls? A: No. It's just fixes non-covered case when process may leave IPC namespace without getting task->sysvshm.shm_clist list cleaned up. Link: https://lkml.kernel.org/r/67bb03e5-f79c-1815-e2bf-949c67047418@colorfullife.com Link: https://lkml.kernel.org/r/20211109151501.4921-1-manfred@colorfullife.com Fixes: ab602f79915 ("shm: make exit_shm work proportional to task activity") Co-developed-by: Manfred Spraul Signed-off-by: Manfred Spraul Signed-off-by: Alexander Mikhalitsyn Cc: "Eric W. Biederman" Cc: Davidlohr Bueso Cc: Greg KH Cc: Andrei Vagin Cc: Pavel Tikhomirov Cc: Vasily Averin Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- include/linux/ipc_namespace.h | 15 +++++++++++++++ include/linux/sched.h | 2 +- include/linux/shm.h | 13 +++++++++++-- 3 files changed, 27 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/include/linux/ipc_namespace.h b/include/linux/ipc_namespace.h index 1eee6bcfcf76..cf1a1c126e89 100644 --- a/include/linux/ipc_namespace.h +++ b/include/linux/ipc_namespace.h @@ -123,6 +123,16 @@ static inline struct ipc_namespace *get_ipc_ns(struct ipc_namespace *ns) return ns; } +static inline struct ipc_namespace *get_ipc_ns_not_zero(struct ipc_namespace *ns) +{ + if (ns) { + if (atomic_inc_not_zero(&ns->count)) + return ns; + } + + return NULL; +} + extern void put_ipc_ns(struct ipc_namespace *ns); #else static inline struct ipc_namespace *copy_ipcs(unsigned long flags, @@ -139,6 +149,11 @@ static inline struct ipc_namespace *get_ipc_ns(struct ipc_namespace *ns) return ns; } +static inline struct ipc_namespace *get_ipc_ns_not_zero(struct ipc_namespace *ns) +{ + return ns; +} + static inline void put_ipc_ns(struct ipc_namespace *ns) { } diff --git a/include/linux/sched.h b/include/linux/sched.h index 8c10e97f94fe..eea75f519421 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -2792,7 +2792,7 @@ static inline int thread_group_empty(struct task_struct *p) * Protects ->fs, ->files, ->mm, ->group_info, ->comm, keyring * subscriptions and synchronises with wait4(). Also used in procfs. Also * pins the final release of task.io_context. Also protects ->cpuset and - * ->cgroup.subsys[]. And ->vfork_done. + * ->cgroup.subsys[]. And ->vfork_done. And ->sysvshm.shm_clist. * * Nests both inside and outside of read_lock(&tasklist_lock). * It must not be nested with write_lock_irq(&tasklist_lock), diff --git a/include/linux/shm.h b/include/linux/shm.h index 6fb801686ad6..fbb74824f0df 100644 --- a/include/linux/shm.h +++ b/include/linux/shm.h @@ -19,9 +19,18 @@ struct shmid_kernel /* private to the kernel */ pid_t shm_lprid; struct user_struct *mlock_user; - /* The task created the shm object. NULL if the task is dead. */ + /* + * The task created the shm object, for + * task_lock(shp->shm_creator) + */ struct task_struct *shm_creator; - struct list_head shm_clist; /* list by creator */ + + /* + * List by creator. task_lock(->shm_creator) required for read/write. + * If list_empty(), then the creator is dead already. + */ + struct list_head shm_clist; + struct ipc_namespace *ns; }; /* shm_mode upper byte flags */ -- cgit v1.2.3 From 4f5a2093238e438c2a196823e2f5da088a97d37b Mon Sep 17 00:00:00 2001 From: Juergen Gross Date: Mon, 29 Nov 2021 13:37:27 +0100 Subject: xen: sync include/xen/interface/io/ring.h with Xen's newest version commit 629a5d87e26fe96bcaab44cbb81f5866af6f7008 upstream. Sync include/xen/interface/io/ring.h with Xen's newest version in order to get the RING_COPY_RESPONSE() and RING_RESPONSE_PROD_OVERFLOW() macros. Signed-off-by: Juergen Gross Signed-off-by: Greg Kroah-Hartman --- include/xen/interface/io/ring.h | 257 +++++++++++++++++++--------------------- 1 file changed, 124 insertions(+), 133 deletions(-) (limited to 'include') diff --git a/include/xen/interface/io/ring.h b/include/xen/interface/io/ring.h index 7dc685b4057d..4076d1c407d8 100644 --- a/include/xen/interface/io/ring.h +++ b/include/xen/interface/io/ring.h @@ -24,82 +24,79 @@ typedef unsigned int RING_IDX; * A ring contains as many entries as will fit, rounded down to the nearest * power of two (so we can mask with (size-1) to loop around). */ -#define __CONST_RING_SIZE(_s, _sz) \ - (__RD32(((_sz) - offsetof(struct _s##_sring, ring)) / \ - sizeof(((struct _s##_sring *)0)->ring[0]))) - +#define __CONST_RING_SIZE(_s, _sz) \ + (__RD32(((_sz) - offsetof(struct _s##_sring, ring)) / \ + sizeof(((struct _s##_sring *)0)->ring[0]))) /* * The same for passing in an actual pointer instead of a name tag. */ -#define __RING_SIZE(_s, _sz) \ - (__RD32(((_sz) - (long)&(_s)->ring + (long)(_s)) / sizeof((_s)->ring[0]))) +#define __RING_SIZE(_s, _sz) \ + (__RD32(((_sz) - (long)(_s)->ring + (long)(_s)) / sizeof((_s)->ring[0]))) /* * Macros to make the correct C datatypes for a new kind of ring. * * To make a new ring datatype, you need to have two message structures, - * let's say struct request, and struct response already defined. + * let's say request_t, and response_t already defined. * * In a header where you want the ring datatype declared, you then do: * - * DEFINE_RING_TYPES(mytag, struct request, struct response); + * DEFINE_RING_TYPES(mytag, request_t, response_t); * * These expand out to give you a set of types, as you can see below. * The most important of these are: * - * struct mytag_sring - The shared ring. - * struct mytag_front_ring - The 'front' half of the ring. - * struct mytag_back_ring - The 'back' half of the ring. + * mytag_sring_t - The shared ring. + * mytag_front_ring_t - The 'front' half of the ring. + * mytag_back_ring_t - The 'back' half of the ring. * * To initialize a ring in your code you need to know the location and size * of the shared memory area (PAGE_SIZE, for instance). To initialise * the front half: * - * struct mytag_front_ring front_ring; - * SHARED_RING_INIT((struct mytag_sring *)shared_page); - * FRONT_RING_INIT(&front_ring, (struct mytag_sring *)shared_page, - * PAGE_SIZE); + * mytag_front_ring_t front_ring; + * SHARED_RING_INIT((mytag_sring_t *)shared_page); + * FRONT_RING_INIT(&front_ring, (mytag_sring_t *)shared_page, PAGE_SIZE); * * Initializing the back follows similarly (note that only the front * initializes the shared ring): * - * struct mytag_back_ring back_ring; - * BACK_RING_INIT(&back_ring, (struct mytag_sring *)shared_page, - * PAGE_SIZE); + * mytag_back_ring_t back_ring; + * BACK_RING_INIT(&back_ring, (mytag_sring_t *)shared_page, PAGE_SIZE); */ -#define DEFINE_RING_TYPES(__name, __req_t, __rsp_t) \ - \ -/* Shared ring entry */ \ -union __name##_sring_entry { \ - __req_t req; \ - __rsp_t rsp; \ -}; \ - \ -/* Shared ring page */ \ -struct __name##_sring { \ - RING_IDX req_prod, req_event; \ - RING_IDX rsp_prod, rsp_event; \ - uint8_t pad[48]; \ - union __name##_sring_entry ring[1]; /* variable-length */ \ -}; \ - \ -/* "Front" end's private variables */ \ -struct __name##_front_ring { \ - RING_IDX req_prod_pvt; \ - RING_IDX rsp_cons; \ - unsigned int nr_ents; \ - struct __name##_sring *sring; \ -}; \ - \ -/* "Back" end's private variables */ \ -struct __name##_back_ring { \ - RING_IDX rsp_prod_pvt; \ - RING_IDX req_cons; \ - unsigned int nr_ents; \ - struct __name##_sring *sring; \ -}; - +#define DEFINE_RING_TYPES(__name, __req_t, __rsp_t) \ + \ +/* Shared ring entry */ \ +union __name##_sring_entry { \ + __req_t req; \ + __rsp_t rsp; \ +}; \ + \ +/* Shared ring page */ \ +struct __name##_sring { \ + RING_IDX req_prod, req_event; \ + RING_IDX rsp_prod, rsp_event; \ + uint8_t __pad[48]; \ + union __name##_sring_entry ring[1]; /* variable-length */ \ +}; \ + \ +/* "Front" end's private variables */ \ +struct __name##_front_ring { \ + RING_IDX req_prod_pvt; \ + RING_IDX rsp_cons; \ + unsigned int nr_ents; \ + struct __name##_sring *sring; \ +}; \ + \ +/* "Back" end's private variables */ \ +struct __name##_back_ring { \ + RING_IDX rsp_prod_pvt; \ + RING_IDX req_cons; \ + unsigned int nr_ents; \ + struct __name##_sring *sring; \ +}; \ + \ /* * Macros for manipulating rings. * @@ -116,105 +113,99 @@ struct __name##_back_ring { \ */ /* Initialising empty rings */ -#define SHARED_RING_INIT(_s) do { \ - (_s)->req_prod = (_s)->rsp_prod = 0; \ - (_s)->req_event = (_s)->rsp_event = 1; \ - memset((_s)->pad, 0, sizeof((_s)->pad)); \ +#define SHARED_RING_INIT(_s) do { \ + (_s)->req_prod = (_s)->rsp_prod = 0; \ + (_s)->req_event = (_s)->rsp_event = 1; \ + (void)memset((_s)->__pad, 0, sizeof((_s)->__pad)); \ } while(0) -#define FRONT_RING_INIT(_r, _s, __size) do { \ - (_r)->req_prod_pvt = 0; \ - (_r)->rsp_cons = 0; \ - (_r)->nr_ents = __RING_SIZE(_s, __size); \ - (_r)->sring = (_s); \ +#define FRONT_RING_ATTACH(_r, _s, _i, __size) do { \ + (_r)->req_prod_pvt = (_i); \ + (_r)->rsp_cons = (_i); \ + (_r)->nr_ents = __RING_SIZE(_s, __size); \ + (_r)->sring = (_s); \ } while (0) -#define BACK_RING_INIT(_r, _s, __size) do { \ - (_r)->rsp_prod_pvt = 0; \ - (_r)->req_cons = 0; \ - (_r)->nr_ents = __RING_SIZE(_s, __size); \ - (_r)->sring = (_s); \ -} while (0) +#define FRONT_RING_INIT(_r, _s, __size) FRONT_RING_ATTACH(_r, _s, 0, __size) -/* Initialize to existing shared indexes -- for recovery */ -#define FRONT_RING_ATTACH(_r, _s, __size) do { \ - (_r)->sring = (_s); \ - (_r)->req_prod_pvt = (_s)->req_prod; \ - (_r)->rsp_cons = (_s)->rsp_prod; \ - (_r)->nr_ents = __RING_SIZE(_s, __size); \ +#define BACK_RING_ATTACH(_r, _s, _i, __size) do { \ + (_r)->rsp_prod_pvt = (_i); \ + (_r)->req_cons = (_i); \ + (_r)->nr_ents = __RING_SIZE(_s, __size); \ + (_r)->sring = (_s); \ } while (0) -#define BACK_RING_ATTACH(_r, _s, __size) do { \ - (_r)->sring = (_s); \ - (_r)->rsp_prod_pvt = (_s)->rsp_prod; \ - (_r)->req_cons = (_s)->req_prod; \ - (_r)->nr_ents = __RING_SIZE(_s, __size); \ -} while (0) +#define BACK_RING_INIT(_r, _s, __size) BACK_RING_ATTACH(_r, _s, 0, __size) /* How big is this ring? */ -#define RING_SIZE(_r) \ +#define RING_SIZE(_r) \ ((_r)->nr_ents) /* Number of free requests (for use on front side only). */ -#define RING_FREE_REQUESTS(_r) \ +#define RING_FREE_REQUESTS(_r) \ (RING_SIZE(_r) - ((_r)->req_prod_pvt - (_r)->rsp_cons)) /* Test if there is an empty slot available on the front ring. * (This is only meaningful from the front. ) */ -#define RING_FULL(_r) \ +#define RING_FULL(_r) \ (RING_FREE_REQUESTS(_r) == 0) /* Test if there are outstanding messages to be processed on a ring. */ -#define RING_HAS_UNCONSUMED_RESPONSES(_r) \ +#define RING_HAS_UNCONSUMED_RESPONSES(_r) \ ((_r)->sring->rsp_prod - (_r)->rsp_cons) -#define RING_HAS_UNCONSUMED_REQUESTS(_r) \ - ({ \ - unsigned int req = (_r)->sring->req_prod - (_r)->req_cons; \ - unsigned int rsp = RING_SIZE(_r) - \ - ((_r)->req_cons - (_r)->rsp_prod_pvt); \ - req < rsp ? req : rsp; \ - }) +#define RING_HAS_UNCONSUMED_REQUESTS(_r) ({ \ + unsigned int req = (_r)->sring->req_prod - (_r)->req_cons; \ + unsigned int rsp = RING_SIZE(_r) - \ + ((_r)->req_cons - (_r)->rsp_prod_pvt); \ + req < rsp ? req : rsp; \ +}) /* Direct access to individual ring elements, by index. */ -#define RING_GET_REQUEST(_r, _idx) \ +#define RING_GET_REQUEST(_r, _idx) \ (&((_r)->sring->ring[((_idx) & (RING_SIZE(_r) - 1))].req)) +#define RING_GET_RESPONSE(_r, _idx) \ + (&((_r)->sring->ring[((_idx) & (RING_SIZE(_r) - 1))].rsp)) + /* - * Get a local copy of a request. + * Get a local copy of a request/response. * - * Use this in preference to RING_GET_REQUEST() so all processing is + * Use this in preference to RING_GET_{REQUEST,RESPONSE}() so all processing is * done on a local copy that cannot be modified by the other end. * * Note that https://gcc.gnu.org/bugzilla/show_bug.cgi?id=58145 may cause this - * to be ineffective where _req is a struct which consists of only bitfields. + * to be ineffective where dest is a struct which consists of only bitfields. */ -#define RING_COPY_REQUEST(_r, _idx, _req) do { \ - /* Use volatile to force the copy into _req. */ \ - *(_req) = *(volatile typeof(_req))RING_GET_REQUEST(_r, _idx); \ +#define RING_COPY_(type, r, idx, dest) do { \ + /* Use volatile to force the copy into dest. */ \ + *(dest) = *(volatile typeof(dest))RING_GET_##type(r, idx); \ } while (0) -#define RING_GET_RESPONSE(_r, _idx) \ - (&((_r)->sring->ring[((_idx) & (RING_SIZE(_r) - 1))].rsp)) +#define RING_COPY_REQUEST(r, idx, req) RING_COPY_(REQUEST, r, idx, req) +#define RING_COPY_RESPONSE(r, idx, rsp) RING_COPY_(RESPONSE, r, idx, rsp) /* Loop termination condition: Would the specified index overflow the ring? */ -#define RING_REQUEST_CONS_OVERFLOW(_r, _cons) \ +#define RING_REQUEST_CONS_OVERFLOW(_r, _cons) \ (((_cons) - (_r)->rsp_prod_pvt) >= RING_SIZE(_r)) /* Ill-behaved frontend determination: Can there be this many requests? */ -#define RING_REQUEST_PROD_OVERFLOW(_r, _prod) \ +#define RING_REQUEST_PROD_OVERFLOW(_r, _prod) \ (((_prod) - (_r)->rsp_prod_pvt) > RING_SIZE(_r)) +/* Ill-behaved backend determination: Can there be this many responses? */ +#define RING_RESPONSE_PROD_OVERFLOW(_r, _prod) \ + (((_prod) - (_r)->rsp_cons) > RING_SIZE(_r)) -#define RING_PUSH_REQUESTS(_r) do { \ - wmb(); /* back sees requests /before/ updated producer index */ \ - (_r)->sring->req_prod = (_r)->req_prod_pvt; \ +#define RING_PUSH_REQUESTS(_r) do { \ + wmb(); /* back sees requests /before/ updated producer index */ \ + (_r)->sring->req_prod = (_r)->req_prod_pvt; \ } while (0) -#define RING_PUSH_RESPONSES(_r) do { \ - wmb(); /* front sees responses /before/ updated producer index */ \ - (_r)->sring->rsp_prod = (_r)->rsp_prod_pvt; \ +#define RING_PUSH_RESPONSES(_r) do { \ + wmb(); /* front sees resps /before/ updated producer index */ \ + (_r)->sring->rsp_prod = (_r)->rsp_prod_pvt; \ } while (0) /* @@ -247,40 +238,40 @@ struct __name##_back_ring { \ * field appropriately. */ -#define RING_PUSH_REQUESTS_AND_CHECK_NOTIFY(_r, _notify) do { \ - RING_IDX __old = (_r)->sring->req_prod; \ - RING_IDX __new = (_r)->req_prod_pvt; \ - wmb(); /* back sees requests /before/ updated producer index */ \ - (_r)->sring->req_prod = __new; \ - mb(); /* back sees new requests /before/ we check req_event */ \ - (_notify) = ((RING_IDX)(__new - (_r)->sring->req_event) < \ - (RING_IDX)(__new - __old)); \ +#define RING_PUSH_REQUESTS_AND_CHECK_NOTIFY(_r, _notify) do { \ + RING_IDX __old = (_r)->sring->req_prod; \ + RING_IDX __new = (_r)->req_prod_pvt; \ + wmb(); /* back sees requests /before/ updated producer index */ \ + (_r)->sring->req_prod = __new; \ + mb(); /* back sees new requests /before/ we check req_event */ \ + (_notify) = ((RING_IDX)(__new - (_r)->sring->req_event) < \ + (RING_IDX)(__new - __old)); \ } while (0) -#define RING_PUSH_RESPONSES_AND_CHECK_NOTIFY(_r, _notify) do { \ - RING_IDX __old = (_r)->sring->rsp_prod; \ - RING_IDX __new = (_r)->rsp_prod_pvt; \ - wmb(); /* front sees responses /before/ updated producer index */ \ - (_r)->sring->rsp_prod = __new; \ - mb(); /* front sees new responses /before/ we check rsp_event */ \ - (_notify) = ((RING_IDX)(__new - (_r)->sring->rsp_event) < \ - (RING_IDX)(__new - __old)); \ +#define RING_PUSH_RESPONSES_AND_CHECK_NOTIFY(_r, _notify) do { \ + RING_IDX __old = (_r)->sring->rsp_prod; \ + RING_IDX __new = (_r)->rsp_prod_pvt; \ + wmb(); /* front sees resps /before/ updated producer index */ \ + (_r)->sring->rsp_prod = __new; \ + mb(); /* front sees new resps /before/ we check rsp_event */ \ + (_notify) = ((RING_IDX)(__new - (_r)->sring->rsp_event) < \ + (RING_IDX)(__new - __old)); \ } while (0) -#define RING_FINAL_CHECK_FOR_REQUESTS(_r, _work_to_do) do { \ - (_work_to_do) = RING_HAS_UNCONSUMED_REQUESTS(_r); \ - if (_work_to_do) break; \ - (_r)->sring->req_event = (_r)->req_cons + 1; \ - mb(); \ - (_work_to_do) = RING_HAS_UNCONSUMED_REQUESTS(_r); \ +#define RING_FINAL_CHECK_FOR_REQUESTS(_r, _work_to_do) do { \ + (_work_to_do) = RING_HAS_UNCONSUMED_REQUESTS(_r); \ + if (_work_to_do) break; \ + (_r)->sring->req_event = (_r)->req_cons + 1; \ + mb(); \ + (_work_to_do) = RING_HAS_UNCONSUMED_REQUESTS(_r); \ } while (0) -#define RING_FINAL_CHECK_FOR_RESPONSES(_r, _work_to_do) do { \ - (_work_to_do) = RING_HAS_UNCONSUMED_RESPONSES(_r); \ - if (_work_to_do) break; \ - (_r)->sring->rsp_event = (_r)->rsp_cons + 1; \ - mb(); \ - (_work_to_do) = RING_HAS_UNCONSUMED_RESPONSES(_r); \ +#define RING_FINAL_CHECK_FOR_RESPONSES(_r, _work_to_do) do { \ + (_work_to_do) = RING_HAS_UNCONSUMED_RESPONSES(_r); \ + if (_work_to_do) break; \ + (_r)->sring->rsp_event = (_r)->rsp_cons + 1; \ + mb(); \ + (_work_to_do) = RING_HAS_UNCONSUMED_RESPONSES(_r); \ } while (0) #endif /* __XEN_PUBLIC_IO_RING_H__ */ -- cgit v1.2.3 From fd923d7ca043932727a401111d37193342a1d76c Mon Sep 17 00:00:00 2001 From: Masami Hiramatsu Date: Wed, 1 Dec 2021 23:45:50 +0900 Subject: kprobes: Limit max data_size of the kretprobe instances commit 6bbfa44116689469267f1a6e3d233b52114139d2 upstream. The 'kprobe::data_size' is unsigned, thus it can not be negative. But if user sets it enough big number (e.g. (size_t)-8), the result of 'data_size + sizeof(struct kretprobe_instance)' becomes smaller than sizeof(struct kretprobe_instance) or zero. In result, the kretprobe_instance are allocated without enough memory, and kretprobe accesses outside of allocated memory. To avoid this issue, introduce a max limitation of the kretprobe::data_size. 4KB per instance should be OK. Link: https://lkml.kernel.org/r/163836995040.432120.10322772773821182925.stgit@devnote2 Cc: stable@vger.kernel.org Fixes: f47cd9b553aa ("kprobes: kretprobe user entry-handler") Reported-by: zhangyue Signed-off-by: Masami Hiramatsu Signed-off-by: Steven Rostedt (VMware) Signed-off-by: Greg Kroah-Hartman --- include/linux/kprobes.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/kprobes.h b/include/linux/kprobes.h index 4db62045f01a..006ef813959b 100644 --- a/include/linux/kprobes.h +++ b/include/linux/kprobes.h @@ -192,6 +192,8 @@ struct kretprobe { raw_spinlock_t lock; }; +#define KRETPROBE_MAX_DATA_SIZE 4096 + struct kretprobe_instance { struct hlist_node hlist; struct kretprobe *rp; -- cgit v1.2.3 From d9e7b466d2cfc56406d412d4e9c86c2fde9c0b61 Mon Sep 17 00:00:00 2001 From: Jens Axboe Date: Wed, 21 Nov 2018 10:32:39 -0700 Subject: fs: add fget_many() and fput_many() commit 091141a42e15fe47ada737f3996b317072afcefb upstream. Some uses cases repeatedly get and put references to the same file, but the only exposed interface is doing these one at the time. As each of these entail an atomic inc or dec on a shared structure, that cost can add up. Add fget_many(), which works just like fget(), except it takes an argument for how many references to get on the file. Ditto fput_many(), which can drop an arbitrary number of references to a file. Reviewed-by: Hannes Reinecke Reviewed-by: Christoph Hellwig Signed-off-by: Jens Axboe Signed-off-by: Greg Kroah-Hartman --- include/linux/file.h | 2 ++ include/linux/fs.h | 4 +++- 2 files changed, 5 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/file.h b/include/linux/file.h index f87d30882a24..67f0888abdde 100644 --- a/include/linux/file.h +++ b/include/linux/file.h @@ -12,6 +12,7 @@ struct file; extern void fput(struct file *); +extern void fput_many(struct file *, unsigned int); struct file_operations; struct vfsmount; @@ -40,6 +41,7 @@ static inline void fdput(struct fd fd) } extern struct file *fget(unsigned int fd); +extern struct file *fget_many(unsigned int fd, unsigned int refs); extern struct file *fget_raw(unsigned int fd); extern unsigned long __fdget(unsigned int fd); extern unsigned long __fdget_raw(unsigned int fd); diff --git a/include/linux/fs.h b/include/linux/fs.h index cdcef9b3bc60..4865c722ded8 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -923,7 +923,9 @@ static inline struct file *get_file(struct file *f) atomic_long_inc(&f->f_count); return f; } -#define get_file_rcu(x) atomic_long_inc_not_zero(&(x)->f_count) +#define get_file_rcu_many(x, cnt) \ + atomic_long_add_unless(&(x)->f_count, (cnt), 0) +#define get_file_rcu(x) get_file_rcu_many((x), 1) #define fput_atomic(x) atomic_long_add_unless(&(x)->f_count, -1, 1) #define file_count(x) atomic_long_read(&(x)->f_count) -- cgit v1.2.3 From d0d310c2aa400b67a24a1934cb9de6d26e083666 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Mon, 29 Nov 2021 10:39:29 -0500 Subject: siphash: use _unaligned version by default commit f7e5b9bfa6c8820407b64eabc1f29c9a87e8993d upstream. On ARM v6 and later, we define CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS because the ordinary load/store instructions (ldr, ldrh, ldrb) can tolerate any misalignment of the memory address. However, load/store double and load/store multiple instructions (ldrd, ldm) may still only be used on memory addresses that are 32-bit aligned, and so we have to use the CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS macro with care, or we may end up with a severe performance hit due to alignment traps that require fixups by the kernel. Testing shows that this currently happens with clang-13 but not gcc-11. In theory, any compiler version can produce this bug or other problems, as we are dealing with undefined behavior in C99 even on architectures that support this in hardware, see also https://gcc.gnu.org/bugzilla/show_bug.cgi?id=100363. Fortunately, the get_unaligned() accessors do the right thing: when building for ARMv6 or later, the compiler will emit unaligned accesses using the ordinary load/store instructions (but avoid the ones that require 32-bit alignment). When building for older ARM, those accessors will emit the appropriate sequence of ldrb/mov/orr instructions. And on architectures that can truly tolerate any kind of misalignment, the get_unaligned() accessors resolve to the leXX_to_cpup accessors that operate on aligned addresses. Since the compiler will in fact emit ldrd or ldm instructions when building this code for ARM v6 or later, the solution is to use the unaligned accessors unconditionally on architectures where this is known to be fast. The _aligned version of the hash function is however still needed to get the best performance on architectures that cannot do any unaligned access in hardware. This new version avoids the undefined behavior and should produce the fastest hash on all architectures we support. Link: https://lore.kernel.org/linux-arm-kernel/20181008211554.5355-4-ard.biesheuvel@linaro.org/ Link: https://lore.kernel.org/linux-crypto/CAK8P3a2KfmmGDbVHULWevB0hv71P2oi2ZCHEAqT=8dQfa0=cqQ@mail.gmail.com/ Reported-by: Ard Biesheuvel Fixes: 2c956a60778c ("siphash: add cryptographically secure PRF") Signed-off-by: Arnd Bergmann Reviewed-by: Jason A. Donenfeld Acked-by: Ard Biesheuvel Signed-off-by: Jason A. Donenfeld Signed-off-by: Jakub Kicinski Signed-off-by: Greg Kroah-Hartman --- include/linux/siphash.h | 14 ++++---------- 1 file changed, 4 insertions(+), 10 deletions(-) (limited to 'include') diff --git a/include/linux/siphash.h b/include/linux/siphash.h index bf21591a9e5e..0cda61855d90 100644 --- a/include/linux/siphash.h +++ b/include/linux/siphash.h @@ -27,9 +27,7 @@ static inline bool siphash_key_is_zero(const siphash_key_t *key) } u64 __siphash_aligned(const void *data, size_t len, const siphash_key_t *key); -#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS u64 __siphash_unaligned(const void *data, size_t len, const siphash_key_t *key); -#endif u64 siphash_1u64(const u64 a, const siphash_key_t *key); u64 siphash_2u64(const u64 a, const u64 b, const siphash_key_t *key); @@ -82,10 +80,9 @@ static inline u64 ___siphash_aligned(const __le64 *data, size_t len, static inline u64 siphash(const void *data, size_t len, const siphash_key_t *key) { -#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS - if (!IS_ALIGNED((unsigned long)data, SIPHASH_ALIGNMENT)) + if (IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) || + !IS_ALIGNED((unsigned long)data, SIPHASH_ALIGNMENT)) return __siphash_unaligned(data, len, key); -#endif return ___siphash_aligned(data, len, key); } @@ -96,10 +93,8 @@ typedef struct { u32 __hsiphash_aligned(const void *data, size_t len, const hsiphash_key_t *key); -#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS u32 __hsiphash_unaligned(const void *data, size_t len, const hsiphash_key_t *key); -#endif u32 hsiphash_1u32(const u32 a, const hsiphash_key_t *key); u32 hsiphash_2u32(const u32 a, const u32 b, const hsiphash_key_t *key); @@ -135,10 +130,9 @@ static inline u32 ___hsiphash_aligned(const __le32 *data, size_t len, static inline u32 hsiphash(const void *data, size_t len, const hsiphash_key_t *key) { -#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS - if (!IS_ALIGNED((unsigned long)data, HSIPHASH_ALIGNMENT)) + if (IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) || + !IS_ALIGNED((unsigned long)data, HSIPHASH_ALIGNMENT)) return __hsiphash_unaligned(data, len, key); -#endif return ___hsiphash_aligned(data, len, key); } -- cgit v1.2.3