litmus-rt-ext-res.git - LITMUS^RT with extended reservations for Forbidden Zones paper @ RTAS'20

diff options

author	Devesh Sharma <devesh.sharma@avagotech.com>	2015-08-03 13:05:04 -0400
committer	Anna Schumaker <Anna.Schumaker@Netapp.com>	2015-08-05 16:22:56 -0400
commit	d0f36c46deea97bd16b9277be2f1acac74d76037 (patch)
tree	1c78cb9d5315bf05c43de4e49fb645e5ff085207 /tools/perf/scripts/python/export-to-postgresql.py
parent	1241d7bf2ac8838d0d2d0b54a6173ac3eb3747a4 (diff)

xprtrdma: take HCA driver refcount at client

This is a rework of the following patch sent almost a year back: http://www.mail-archive.com/linux-rdma%40vger.kernel.org/msg20730.html In presence of active mount if someone tries to rmmod vendor-driver, the command remains stuck forever waiting for destruction of all rdma-cm-id. in worst case client can crash during shutdown with active mounts. The existing code assumes that ia->ri_id->device cannot change during the lifetime of a transport. xprtrdma do not have support for DEVICE_REMOVAL event either. Lifting that assumption and adding support for DEVICE_REMOVAL event is a long chain of work, and is in plan. The community decided that preventing the hang right now is more important than waiting for architectural changes. Thus, this patch introduces a temporary workaround to acquire HCA driver module reference count during the mount of a nfs-rdma mount point. Signed-off-by: Devesh Sharma <devesh.sharma@avagotech.com> Signed-off-by: Chuck Lever <chuck.lever@oracle.com> Reviewed-by: Sagi Grimberg <sagig@dev.mellanox.co.il> Signed-off-by: Anna Schumaker <Anna.Schumaker@Netapp.com>

Diffstat (limited to 'tools/perf/scripts/python/export-to-postgresql.py')

0 files changed, 0 insertions, 0 deletions

/* * * Copyright IBM Corporation, 2012 * Author Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> * * This program is free software; you can redistribute it and/or modify it * under the terms of version 2.1 of the GNU Lesser General Public License * as published by the Free Software Foundation. * * This program is distributed in the hope that it would be useful, but * WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. * */ #include <linux/cgroup.h> #include <linux/page_counter.h> #include <linux/slab.h> #include <linux/hugetlb.h> #include <linux/hugetlb_cgroup.h> struct hugetlb_cgroup { struct cgroup_subsys_state css; /* * the counter to account for hugepages from hugetlb. */ struct page_counter hugepage[HUGE_MAX_HSTATE]; }; #define MEMFILE_PRIVATE(x, val) (((x) << 16) | (val)) #define MEMFILE_IDX(val) (((val) >> 16) & 0xffff) #define MEMFILE_ATTR(val) ((val) & 0xffff) static struct hugetlb_cgroup *root_h_cgroup __read_mostly; static inline struct hugetlb_cgroup *hugetlb_cgroup_from_css(struct cgroup_subsys_state *s) { return s ? container_of(s, struct hugetlb_cgroup, css) : NULL; } static inline struct hugetlb_cgroup *hugetlb_cgroup_from_task(struct task_struct *task) { return hugetlb_cgroup_from_css(task_css(task, hugetlb_cgrp_id)); } static inline bool hugetlb_cgroup_is_root(struct hugetlb_cgroup *h_cg) { return (h_cg == root_h_cgroup); } static inline struct hugetlb_cgroup * parent_hugetlb_cgroup(struct hugetlb_cgroup *h_cg) { return hugetlb_cgroup_from_css(h_cg->css.parent); } static inline bool hugetlb_cgroup_have_usage(struct hugetlb_cgroup *h_cg) { int idx; for (idx = 0; idx < hugetlb_max_hstate; idx++) { if (page_counter_read(&h_cg->hugepage[idx])) return true; } return false; } static void hugetlb_cgroup_init(struct hugetlb_cgroup *h_cgroup, struct hugetlb_cgroup *parent_h_cgroup) { int idx; for (idx = 0; idx < HUGE_MAX_HSTATE; idx++) { struct page_counter *counter = &h_cgroup->hugepage[idx]; struct page_counter *parent = NULL; unsigned long limit; int ret; if (parent_h_cgroup) parent = &parent_h_cgroup->hugepage[idx]; page_counter_init(counter, parent); limit = round_down(PAGE_COUNTER_MAX, 1 << huge_page_order(&hstates[idx])); ret = page_counter_limit(counter, limit); VM_BUG_ON(ret); } } static struct cgroup_subsys_state * hugetlb_cgroup_css_alloc(struct cgroup_subsys_state *parent_css) { struct hugetlb_cgroup *parent_h_cgroup = hugetlb_cgroup_from_css(parent_css); struct hugetlb_cgroup *h_cgroup; h_cgroup = kzalloc(sizeof(*h_cgroup), GFP_KERNEL); if (!h_cgroup) return ERR_PTR(-ENOMEM); if (!parent_h_cgroup) root_h_cgroup = h_cgroup; hugetlb_cgroup_init(h_cgroup, parent_h_cgroup); return &h_cgroup->css; } static void hugetlb_cgroup_css_free(struct cgroup_subsys_state *css) { struct hugetlb_cgroup *h_cgroup; h_cgroup = hugetlb_cgroup_from_css(css); kfree(h_cgroup); } /* * Should be called with hugetlb_lock held. * Since we are holding hugetlb_lock, pages cannot get moved from * active list or uncharged from the cgroup, So no need to get * page reference and test for page active here. This function * cannot fail. */ static void hugetlb_cgroup_move_parent(int idx, struct hugetlb_cgroup *h_cg, struct page *page) { unsigned int nr_pages; struct page_counter *counter; struct hugetlb_cgroup *page_hcg; struct hugetlb_cgroup *parent = parent_hugetlb_cgroup(h_cg); page_hcg = hugetlb_cgroup_from_page(page); /* * We can have pages in active list without any cgroup * ie, hugepage with less than 3 pages. We can safely * ignore those pages. */ if (!page_hcg || page_hcg != h_cg) goto out; nr_pages = 1 << compound_order(page); if (!parent) { parent = root_h_cgroup; /* root has no limit */ page_counter_charge(&parent->hugepage[idx], nr_pages); } counter = &h_cg->hugepage[idx]; /* Take the pages off the local counter */ page_counter_cancel(counter, nr_pages); set_hugetlb_cgroup(page, parent); out: return; } /* * Force the hugetlb cgroup to empty the hugetlb resources by moving them to * the parent cgroup. */ static void hugetlb_cgroup_css_offline(struct cgroup_subsys_state *css) { struct hugetlb_cgroup *h_cg = hugetlb_cgroup_from_css(css); struct hstate *h; struct page *page; int idx = 0; do { for_each_hstate(h) { spin_lock(&hugetlb_lock); list_for_each_entry(page, &h->hugepage_activelist, lru) hugetlb_cgroup_move_parent(idx, h_cg, page); spin_unlock(&hugetlb_lock); idx++; } cond_resched(); } while (hugetlb_cgroup_have_usage(h_cg)); } int hugetlb_cgroup_charge_cgroup(int idx, unsigned long nr_pages, struct hugetlb_cgroup **ptr) { int ret = 0; struct page_counter *counter; struct hugetlb_cgroup *h_cg = NULL; if (hugetlb_cgroup_disabled()) goto done; /* * We don't charge any cgroup if the compound page have less * than 3 pages. */ if (huge_page_order(&hstates[idx]) < HUGETLB_CGROUP_MIN_ORDER) goto done; again: rcu_read_lock(); h_cg = hugetlb_cgroup_from_task(current); if (!css_tryget_online(&h_cg->css)) { rcu_read_unlock(); goto again; } rcu_read_unlock(); if (!page_counter_try_charge(&h_cg->hugepage[idx], nr_pages, &counter)) ret = -ENOMEM; css_put(&h_cg->css); done: *ptr = h_cg; return ret; } /* Should be called with hugetlb_lock held */ void hugetlb_cgroup_commit_charge(int idx, unsigned long nr_pages, struct hugetlb_cgroup *h_cg, struct page *page) { if (hugetlb_cgroup_disabled() || !h_cg) return; set_hugetlb_cgroup(page, h_cg); return;


context:
space:
mode: