From 29ebbba744cf8951202b5f4ea62b4a297f4662c1 Mon Sep 17 00:00:00 2001 From: Sagi Grimberg Date: Thu, 31 Mar 2016 19:03:25 +0300 Subject: IB/mlx5: Expose correct max_sge_rd limit commit 986ef95ecdd3eb6fa29433e68faa94c7624083be upstream. mlx5 devices (Connect-IB, ConnectX-4, ConnectX-4-LX) has a limitation where rdma read work queue entries cannot exceed 512 bytes. A rdma_read wqe needs to fit in 512 bytes: - wqe control segment (16 bytes) - rdma segment (16 bytes) - scatter elements (16 bytes each) So max_sge_rd should be: (512 - 16 - 16) / 16 = 30. Reported-by: Christoph Hellwig Tested-by: Christoph Hellwig Signed-off-by: Sagi Grimberg Signed-off-by: Leon Romanovsky Signed-off-by: Doug Ledford Signed-off-by: Greg Kroah-Hartman --- include/linux/mlx5/device.h | 11 +++++++++++ 1 file changed, 11 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h index 0b473cbfa7ef..a91b67b18a73 100644 --- a/include/linux/mlx5/device.h +++ b/include/linux/mlx5/device.h @@ -334,6 +334,17 @@ enum { MLX5_CAP_OFF_CMDIF_CSUM = 46, }; +enum { + /* + * Max wqe size for rdma read is 512 bytes, so this + * limits our max_sge_rd as the wqe needs to fit: + * - ctrl segment (16 bytes) + * - rdma segment (16 bytes) + * - scatter elements (16 bytes each) + */ + MLX5_MAX_SGE_RD = (512 - 16 - 16) / 16 +}; + struct mlx5_inbox_hdr { __be16 opcode; u8 rsvd[4]; -- cgit v1.2.3 From d52097476caeb14f4d7e3417dda08220d2813cc4 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Thu, 21 Apr 2016 19:06:48 -0400 Subject: cgroup, cpuset: replace cpuset_post_attach_flush() with cgroup_subsys->post_attach callback commit 5cf1cacb49aee39c3e02ae87068fc3c6430659b0 upstream. Since e93ad19d0564 ("cpuset: make mm migration asynchronous"), cpuset kicks off asynchronous NUMA node migration if necessary during task migration and flushes it from cpuset_post_attach_flush() which is called at the end of __cgroup_procs_write(). This is to avoid performing migration with cgroup_threadgroup_rwsem write-locked which can lead to deadlock through dependency on kworker creation. memcg has a similar issue with charge moving, so let's convert it to an official callback rather than the current one-off cpuset specific function. This patch adds cgroup_subsys->post_attach callback and makes cpuset register cpuset_post_attach_flush() as its ->post_attach. The conversion is mostly one-to-one except that the new callback is called under cgroup_mutex. This is to guarantee that no other migration operations are started before ->post_attach callbacks are finished. cgroup_mutex is one of the outermost mutex in the system and has never been and shouldn't be a problem. We can add specialized synchronization around __cgroup_procs_write() but I don't think there's any noticeable benefit. Signed-off-by: Tejun Heo Cc: Li Zefan Cc: Johannes Weiner Cc: Michal Hocko Signed-off-by: Greg Kroah-Hartman --- include/linux/cgroup-defs.h | 1 + include/linux/cpuset.h | 6 ------ 2 files changed, 1 insertion(+), 6 deletions(-) (limited to 'include/linux') diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index a7c7f74808a4..8da263299754 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -434,6 +434,7 @@ struct cgroup_subsys { int (*can_attach)(struct cgroup_taskset *tset); void (*cancel_attach)(struct cgroup_taskset *tset); void (*attach)(struct cgroup_taskset *tset); + void (*post_attach)(void); int (*can_fork)(struct task_struct *task, void **priv_p); void (*cancel_fork)(struct task_struct *task, void *priv); void (*fork)(struct task_struct *task, void *priv); diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h index fea160ee5803..85a868ccb493 100644 --- a/include/linux/cpuset.h +++ b/include/linux/cpuset.h @@ -137,8 +137,6 @@ static inline void set_mems_allowed(nodemask_t nodemask) task_unlock(current); } -extern void cpuset_post_attach_flush(void); - #else /* !CONFIG_CPUSETS */ static inline bool cpusets_enabled(void) { return false; } @@ -245,10 +243,6 @@ static inline bool read_mems_allowed_retry(unsigned int seq) return false; } -static inline void cpuset_post_attach_flush(void) -{ -} - #endif /* !CONFIG_CPUSETS */ #endif /* _LINUX_CPUSET_H */ -- cgit v1.2.3 From e513b90a9aef91e6399decb8e9592f2d75f7ebad Mon Sep 17 00:00:00 2001 From: Gerald Schaefer Date: Thu, 28 Apr 2016 16:18:35 -0700 Subject: numa: fix /proc//numa_maps for THP commit 28093f9f34cedeaea0f481c58446d9dac6dd620f upstream. In gather_pte_stats() a THP pmd is cast into a pte, which is wrong because the layouts may differ depending on the architecture. On s390 this will lead to inaccurate numa_maps accounting in /proc because of misguided pte_present() and pte_dirty() checks on the fake pte. On other architectures pte_present() and pte_dirty() may work by chance, but there may be an issue with direct-access (dax) mappings w/o underlying struct pages when HAVE_PTE_SPECIAL is set and THP is available. In vm_normal_page() the fake pte will be checked with pte_special() and because there is no "special" bit in a pmd, this will always return false and the VM_PFNMAP | VM_MIXEDMAP checking will be skipped. On dax mappings w/o struct pages, an invalid struct page pointer would then be returned that can crash the kernel. This patch fixes the numa_maps THP handling by introducing new "_pmd" variants of the can_gather_numa_stats() and vm_normal_page() functions. Signed-off-by: Gerald Schaefer Cc: Naoya Horiguchi Cc: "Kirill A . Shutemov" Cc: Konstantin Khlebnikov Cc: Michal Hocko Cc: Vlastimil Babka Cc: Jerome Marchand Cc: Johannes Weiner Cc: Dave Hansen Cc: Mel Gorman Cc: Dan Williams Cc: Martin Schwidefsky Cc: Heiko Carstens Cc: Michael Holzheu Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds Signed-off-by: Greg Kroah-Hartman --- include/linux/mm.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux') diff --git a/include/linux/mm.h b/include/linux/mm.h index 00bad7793788..fb8b20e5d021 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -1084,6 +1084,8 @@ struct zap_details { struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr, pte_t pte); +struct page *vm_normal_page_pmd(struct vm_area_struct *vma, unsigned long addr, + pmd_t pmd); int zap_vma_ptes(struct vm_area_struct *vma, unsigned long address, unsigned long size); -- cgit v1.2.3