diff options
Diffstat (limited to 'drivers/staging/lustre/lnet/libcfs/linux')
| -rw-r--r-- | drivers/staging/lustre/lnet/libcfs/linux/linux-cpu.c | 1040 | ||||
| -rw-r--r-- | drivers/staging/lustre/lnet/libcfs/linux/linux-crypto-adler.c | 137 | ||||
| -rw-r--r-- | drivers/staging/lustre/lnet/libcfs/linux/linux-crypto.c | 297 | ||||
| -rw-r--r-- | drivers/staging/lustre/lnet/libcfs/linux/linux-crypto.h | 29 | ||||
| -rw-r--r-- | drivers/staging/lustre/lnet/libcfs/linux/linux-curproc.c | 111 | ||||
| -rw-r--r-- | drivers/staging/lustre/lnet/libcfs/linux/linux-debug.c | 200 | ||||
| -rw-r--r-- | drivers/staging/lustre/lnet/libcfs/linux/linux-mem.c | 59 | ||||
| -rw-r--r-- | drivers/staging/lustre/lnet/libcfs/linux/linux-module.c | 159 | ||||
| -rw-r--r-- | drivers/staging/lustre/lnet/libcfs/linux/linux-prim.c | 147 | ||||
| -rw-r--r-- | drivers/staging/lustre/lnet/libcfs/linux/linux-tracefile.c | 259 |
10 files changed, 2438 insertions, 0 deletions
diff --git a/drivers/staging/lustre/lnet/libcfs/linux/linux-cpu.c b/drivers/staging/lustre/lnet/libcfs/linux/linux-cpu.c new file mode 100644 index 000000000000..389fb9eeea75 --- /dev/null +++ b/drivers/staging/lustre/lnet/libcfs/linux/linux-cpu.c @@ -0,0 +1,1040 @@ +/* + * GPL HEADER START + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 only, + * as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License version 2 for more details (a copy is included + * in the LICENSE file that accompanied this code). + * + * GPL HEADER END + */ +/* + * Copyright (c) 2010, Oracle and/or its affiliates. All rights reserved. + * + * Copyright (c) 2012, 2015 Intel Corporation. + */ +/* + * This file is part of Lustre, http://www.lustre.org/ + * Lustre is a trademark of Sun Microsystems, Inc. + * + * Author: liang@whamcloud.com + */ + +#define DEBUG_SUBSYSTEM S_LNET + +#include <linux/cpu.h> +#include <linux/sched.h> +#include "../../../include/linux/libcfs/libcfs.h" + +#ifdef CONFIG_SMP + +/** + * modparam for setting number of partitions + * + * 0 : estimate best value based on cores or NUMA nodes + * 1 : disable multiple partitions + * >1 : specify number of partitions + */ +static int cpu_npartitions; +module_param(cpu_npartitions, int, 0444); +MODULE_PARM_DESC(cpu_npartitions, "# of CPU partitions"); + +/** + * modparam for setting CPU partitions patterns: + * + * i.e: "0[0,1,2,3] 1[4,5,6,7]", number before bracket is CPU partition ID, + * number in bracket is processor ID (core or HT) + * + * i.e: "N 0[0,1] 1[2,3]" the first character 'N' means numbers in bracket + * are NUMA node ID, number before bracket is CPU partition ID. + * + * NB: If user specified cpu_pattern, cpu_npartitions will be ignored + */ +static char *cpu_pattern = ""; +module_param(cpu_pattern, charp, 0444); +MODULE_PARM_DESC(cpu_pattern, "CPU partitions pattern"); + +struct cfs_cpt_data { + /* serialize hotplug etc */ + spinlock_t cpt_lock; + /* reserved for hotplug */ + unsigned long cpt_version; + /* mutex to protect cpt_cpumask */ + struct mutex cpt_mutex; + /* scratch buffer for set/unset_node */ + cpumask_t *cpt_cpumask; +}; + +static struct cfs_cpt_data cpt_data; + +void +cfs_cpt_table_free(struct cfs_cpt_table *cptab) +{ + int i; + + if (cptab->ctb_cpu2cpt) { + LIBCFS_FREE(cptab->ctb_cpu2cpt, + num_possible_cpus() * + sizeof(cptab->ctb_cpu2cpt[0])); + } + + for (i = 0; cptab->ctb_parts && i < cptab->ctb_nparts; i++) { + struct cfs_cpu_partition *part = &cptab->ctb_parts[i]; + + if (part->cpt_nodemask) { + LIBCFS_FREE(part->cpt_nodemask, + sizeof(*part->cpt_nodemask)); + } + + if (part->cpt_cpumask) + LIBCFS_FREE(part->cpt_cpumask, cpumask_size()); + } + + if (cptab->ctb_parts) { + LIBCFS_FREE(cptab->ctb_parts, + cptab->ctb_nparts * sizeof(cptab->ctb_parts[0])); + } + + if (cptab->ctb_nodemask) + LIBCFS_FREE(cptab->ctb_nodemask, sizeof(*cptab->ctb_nodemask)); + if (cptab->ctb_cpumask) + LIBCFS_FREE(cptab->ctb_cpumask, cpumask_size()); + + LIBCFS_FREE(cptab, sizeof(*cptab)); +} +EXPORT_SYMBOL(cfs_cpt_table_free); + +struct cfs_cpt_table * +cfs_cpt_table_alloc(unsigned int ncpt) +{ + struct cfs_cpt_table *cptab; + int i; + + LIBCFS_ALLOC(cptab, sizeof(*cptab)); + if (!cptab) + return NULL; + + cptab->ctb_nparts = ncpt; + + LIBCFS_ALLOC(cptab->ctb_cpumask, cpumask_size()); + LIBCFS_ALLOC(cptab->ctb_nodemask, sizeof(*cptab->ctb_nodemask)); + + if (!cptab->ctb_cpumask || !cptab->ctb_nodemask) + goto failed; + + LIBCFS_ALLOC(cptab->ctb_cpu2cpt, + num_possible_cpus() * sizeof(cptab->ctb_cpu2cpt[0])); + if (!cptab->ctb_cpu2cpt) + goto failed; + + memset(cptab->ctb_cpu2cpt, -1, + num_possible_cpus() * sizeof(cptab->ctb_cpu2cpt[0])); + + LIBCFS_ALLOC(cptab->ctb_parts, ncpt * sizeof(cptab->ctb_parts[0])); + if (!cptab->ctb_parts) + goto failed; + + for (i = 0; i < ncpt; i++) { + struct cfs_cpu_partition *part = &cptab->ctb_parts[i]; + + LIBCFS_ALLOC(part->cpt_cpumask, cpumask_size()); + LIBCFS_ALLOC(part->cpt_nodemask, sizeof(*part->cpt_nodemask)); + if (!part->cpt_cpumask || !part->cpt_nodemask) + goto failed; + } + + spin_lock(&cpt_data.cpt_lock); + /* Reserved for hotplug */ + cptab->ctb_version = cpt_data.cpt_version; + spin_unlock(&cpt_data.cpt_lock); + + return cptab; + + failed: + cfs_cpt_table_free(cptab); + return NULL; +} +EXPORT_SYMBOL(cfs_cpt_table_alloc); + +int +cfs_cpt_table_print(struct cfs_cpt_table *cptab, char *buf, int len) +{ + char *tmp = buf; + int rc = 0; + int i; + int j; + + for (i = 0; i < cptab->ctb_nparts; i++) { + if (len > 0) { + rc = snprintf(tmp, len, "%d\t: ", i); + len -= rc; + } + + if (len <= 0) { + rc = -EFBIG; + goto out; + } + + tmp += rc; + for_each_cpu(j, cptab->ctb_parts[i].cpt_cpumask) { + rc = snprintf(tmp, len, "%d ", j); + len -= rc; + if (len <= 0) { + rc = -EFBIG; + goto out; + } + tmp += rc; + } + + *tmp = '\n'; + tmp++; + len--; + } + + out: + if (rc < 0) + return rc; + + return tmp - buf; +} +EXPORT_SYMBOL(cfs_cpt_table_print); + +int +cfs_cpt_number(struct cfs_cpt_table *cptab) +{ + return cptab->ctb_nparts; +} +EXPORT_SYMBOL(cfs_cpt_number); + +int +cfs_cpt_weight(struct cfs_cpt_table *cptab, int cpt) +{ + LASSERT(cpt == CFS_CPT_ANY || (cpt >= 0 && cpt < cptab->ctb_nparts)); + + return cpt == CFS_CPT_ANY ? + cpumask_weight(cptab->ctb_cpumask) : + cpumask_weight(cptab->ctb_parts[cpt].cpt_cpumask); +} +EXPORT_SYMBOL(cfs_cpt_weight); + +int +cfs_cpt_online(struct cfs_cpt_table *cptab, int cpt) +{ + LASSERT(cpt == CFS_CPT_ANY || (cpt >= 0 && cpt < cptab->ctb_nparts)); + + return cpt == CFS_CPT_ANY ? + cpumask_any_and(cptab->ctb_cpumask, + cpu_online_mask) < nr_cpu_ids : + cpumask_any_and(cptab->ctb_parts[cpt].cpt_cpumask, + cpu_online_mask) < nr_cpu_ids; +} +EXPORT_SYMBOL(cfs_cpt_online); + +cpumask_t * +cfs_cpt_cpumask(struct cfs_cpt_table *cptab, int cpt) +{ + LASSERT(cpt == CFS_CPT_ANY || (cpt >= 0 && cpt < cptab->ctb_nparts)); + + return cpt == CFS_CPT_ANY ? + cptab->ctb_cpumask : cptab->ctb_parts[cpt].cpt_cpumask; +} +EXPORT_SYMBOL(cfs_cpt_cpumask); + +nodemask_t * +cfs_cpt_nodemask(struct cfs_cpt_table *cptab, int cpt) +{ + LASSERT(cpt == CFS_CPT_ANY || (cpt >= 0 && cpt < cptab->ctb_nparts)); + + return cpt == CFS_CPT_ANY ? + cptab->ctb_nodemask : cptab->ctb_parts[cpt].cpt_nodemask; +} +EXPORT_SYMBOL(cfs_cpt_nodemask); + +int +cfs_cpt_set_cpu(struct cfs_cpt_table *cptab, int cpt, int cpu) +{ + int node; + + LASSERT(cpt >= 0 && cpt < cptab->ctb_nparts); + + if (cpu < 0 || cpu >= nr_cpu_ids || !cpu_online(cpu)) { + CDEBUG(D_INFO, "CPU %d is invalid or it's offline\n", cpu); + return 0; + } + + if (cptab->ctb_cpu2cpt[cpu] != -1) { + CDEBUG(D_INFO, "CPU %d is already in partition %d\n", + cpu, cptab->ctb_cpu2cpt[cpu]); + return 0; + } + + cptab->ctb_cpu2cpt[cpu] = cpt; + + LASSERT(!cpumask_test_cpu(cpu, cptab->ctb_cpumask)); + LASSERT(!cpumask_test_cpu(cpu, cptab->ctb_parts[cpt].cpt_cpumask)); + + cpumask_set_cpu(cpu, cptab->ctb_cpumask); + cpumask_set_cpu(cpu, cptab->ctb_parts[cpt].cpt_cpumask); + + node = cpu_to_node(cpu); + + /* first CPU of @node in this CPT table */ + if (!node_isset(node, *cptab->ctb_nodemask)) + node_set(node, *cptab->ctb_nodemask); + + /* first CPU of @node in this partition */ + if (!node_isset(node, *cptab->ctb_parts[cpt].cpt_nodemask)) + node_set(node, *cptab->ctb_parts[cpt].cpt_nodemask); + + return 1; +} +EXPORT_SYMBOL(cfs_cpt_set_cpu); + +void +cfs_cpt_unset_cpu(struct cfs_cpt_table *cptab, int cpt, int cpu) +{ + int node; + int i; + + LASSERT(cpt == CFS_CPT_ANY || (cpt >= 0 && cpt < cptab->ctb_nparts)); + + if (cpu < 0 || cpu >= nr_cpu_ids) { + CDEBUG(D_INFO, "Invalid CPU id %d\n", cpu); + return; + } + + if (cpt == CFS_CPT_ANY) { + /* caller doesn't know the partition ID */ + cpt = cptab->ctb_cpu2cpt[cpu]; + if (cpt < 0) { /* not set in this CPT-table */ + CDEBUG(D_INFO, "Try to unset cpu %d which is not in CPT-table %p\n", + cpt, cptab); + return; + } + + } else if (cpt != cptab->ctb_cpu2cpt[cpu]) { + CDEBUG(D_INFO, + "CPU %d is not in cpu-partition %d\n", cpu, cpt); + return; + } + + LASSERT(cpumask_test_cpu(cpu, cptab->ctb_parts[cpt].cpt_cpumask)); + LASSERT(cpumask_test_cpu(cpu, cptab->ctb_cpumask)); + + cpumask_clear_cpu(cpu, cptab->ctb_parts[cpt].cpt_cpumask); + cpumask_clear_cpu(cpu, cptab->ctb_cpumask); + cptab->ctb_cpu2cpt[cpu] = -1; + + node = cpu_to_node(cpu); + + LASSERT(node_isset(node, *cptab->ctb_parts[cpt].cpt_nodemask)); + LASSERT(node_isset(node, *cptab->ctb_nodemask)); + + for_each_cpu(i, cptab->ctb_parts[cpt].cpt_cpumask) { + /* this CPT has other CPU belonging to this node? */ + if (cpu_to_node(i) == node) + break; + } + + if (i >= nr_cpu_ids) + node_clear(node, *cptab->ctb_parts[cpt].cpt_nodemask); + + for_each_cpu(i, cptab->ctb_cpumask) { + /* this CPT-table has other CPU belonging to this node? */ + if (cpu_to_node(i) == node) + break; + } + + if (i >= nr_cpu_ids) + node_clear(node, *cptab->ctb_nodemask); +} +EXPORT_SYMBOL(cfs_cpt_unset_cpu); + +int +cfs_cpt_set_cpumask(struct cfs_cpt_table *cptab, int cpt, cpumask_t *mask) +{ + int i; + + if (cpumask_weight(mask) == 0 || + cpumask_any_and(mask, cpu_online_mask) >= nr_cpu_ids) { + CDEBUG(D_INFO, "No online CPU is found in the CPU mask for CPU partition %d\n", + cpt); + return 0; + } + + for_each_cpu(i, mask) { + if (!cfs_cpt_set_cpu(cptab, cpt, i)) + return 0; + } + + return 1; +} +EXPORT_SYMBOL(cfs_cpt_set_cpumask); + +void +cfs_cpt_unset_cpumask(struct cfs_cpt_table *cptab, int cpt, cpumask_t *mask) +{ + int i; + + for_each_cpu(i, mask) + cfs_cpt_unset_cpu(cptab, cpt, i); +} +EXPORT_SYMBOL(cfs_cpt_unset_cpumask); + +int +cfs_cpt_set_node(struct cfs_cpt_table *cptab, int cpt, int node) +{ + cpumask_t *mask; + int rc; + + if (node < 0 || node >= MAX_NUMNODES) { + CDEBUG(D_INFO, + "Invalid NUMA id %d for CPU partition %d\n", node, cpt); + return 0; + } + + mutex_lock(&cpt_data.cpt_mutex); + + mask = cpt_data.cpt_cpumask; + cpumask_copy(mask, cpumask_of_node(node)); + + rc = cfs_cpt_set_cpumask(cptab, cpt, mask); + + mutex_unlock(&cpt_data.cpt_mutex); + + return rc; +} +EXPORT_SYMBOL(cfs_cpt_set_node); + +void +cfs_cpt_unset_node(struct cfs_cpt_table *cptab, int cpt, int node) +{ + cpumask_t *mask; + + if (node < 0 || node >= MAX_NUMNODES) { + CDEBUG(D_INFO, + "Invalid NUMA id %d for CPU partition %d\n", node, cpt); + return; + } + + mutex_lock(&cpt_data.cpt_mutex); + + mask = cpt_data.cpt_cpumask; + cpumask_copy(mask, cpumask_of_node(node)); + + cfs_cpt_unset_cpumask(cptab, cpt, mask); + + mutex_unlock(&cpt_data.cpt_mutex); +} +EXPORT_SYMBOL(cfs_cpt_unset_node); + +int +cfs_cpt_set_nodemask(struct cfs_cpt_table *cptab, int cpt, nodemask_t *mask) +{ + int i; + + for_each_node_mask(i, *mask) { + if (!cfs_cpt_set_node(cptab, cpt, i)) + return 0; + } + + return 1; +} +EXPORT_SYMBOL(cfs_cpt_set_nodemask); + +void +cfs_cpt_unset_nodemask(struct cfs_cpt_table *cptab, int cpt, nodemask_t *mask) +{ + int i; + + for_each_node_mask(i, *mask) + cfs_cpt_unset_node(cptab, cpt, i); +} +EXPORT_SYMBOL(cfs_cpt_unset_nodemask); + +void +cfs_cpt_clear(struct cfs_cpt_table *cptab, int cpt) +{ + int last; + int i; + + if (cpt == CFS_CPT_ANY) { + last = cptab->ctb_nparts - 1; + cpt = 0; + } else { + last = cpt; + } + + for (; cpt <= last; cpt++) { + for_each_cpu(i, cptab->ctb_parts[cpt].cpt_cpumask) + cfs_cpt_unset_cpu(cptab, cpt, i); + } +} +EXPORT_SYMBOL(cfs_cpt_clear); + +int +cfs_cpt_spread_node(struct cfs_cpt_table *cptab, int cpt) +{ + nodemask_t *mask; + int weight; + int rotor; + int node; + + /* convert CPU partition ID to HW node id */ + + if (cpt < 0 || cpt >= cptab->ctb_nparts) { + mask = cptab->ctb_nodemask; + rotor = cptab->ctb_spread_rotor++; + } else { + mask = cptab->ctb_parts[cpt].cpt_nodemask; + rotor = cptab->ctb_parts[cpt].cpt_spread_rotor++; + } + + weight = nodes_weight(*mask); + LASSERT(weight > 0); + + rotor %= weight; + + for_each_node_mask(node, *mask) { + if (rotor-- == 0) + return node; + } + + LBUG(); + return 0; +} +EXPORT_SYMBOL(cfs_cpt_spread_node); + +int +cfs_cpt_current(struct cfs_cpt_table *cptab, int remap) +{ + int cpu = smp_processor_id(); + int cpt = cptab->ctb_cpu2cpt[cpu]; + + if (cpt < 0) { + if (!remap) + return cpt; + + /* don't return negative value for safety of upper layer, + * instead we shadow the unknown cpu to a valid partition ID + */ + cpt = cpu % cptab->ctb_nparts; + } + + return cpt; +} +EXPORT_SYMBOL(cfs_cpt_current); + +int +cfs_cpt_of_cpu(struct cfs_cpt_table *cptab, int cpu) +{ + LASSERT(cpu >= 0 && cpu < nr_cpu_ids); + + return cptab->ctb_cpu2cpt[cpu]; +} +EXPORT_SYMBOL(cfs_cpt_of_cpu); + +int +cfs_cpt_bind(struct cfs_cpt_table *cptab, int cpt) +{ + cpumask_t *cpumask; + nodemask_t *nodemask; + int rc; + int i; + + LASSERT(cpt == CFS_CPT_ANY || (cpt >= 0 && cpt < cptab->ctb_nparts)); + + if (cpt == CFS_CPT_ANY) { + cpumask = cptab->ctb_cpumask; + nodemask = cptab->ctb_nodemask; + } else { + cpumask = cptab->ctb_parts[cpt].cpt_cpumask; + nodemask = cptab->ctb_parts[cpt].cpt_nodemask; + } + + if (cpumask_any_and(cpumask, cpu_online_mask) >= nr_cpu_ids) { + CERROR("No online CPU found in CPU partition %d, did someone do CPU hotplug on system? You might need to reload Lustre modules to keep system working well.\n", + cpt); + return -EINVAL; + } + + for_each_online_cpu(i) { + if (cpumask_test_cpu(i, cpumask)) + continue; + + rc = set_cpus_allowed_ptr(current, cpumask); + set_mems_allowed(*nodemask); + if (rc == 0) + schedule(); /* switch to allowed CPU */ + + return rc; + } + + /* don't need to set affinity because all online CPUs are covered */ + return 0; +} +EXPORT_SYMBOL(cfs_cpt_bind); + +/** + * Choose max to \a number CPUs from \a node and set them in \a cpt. + * We always prefer to choose CPU in the same core/socket. + */ +static int +cfs_cpt_choose_ncpus(struct cfs_cpt_table *cptab, int cpt, + cpumask_t *node, int number) +{ + cpumask_t *socket = NULL; + cpumask_t *core = NULL; + int rc = 0; + int cpu; + + LASSERT(number > 0); + + if (number >= cpumask_weight(node)) { + while (!cpumask_empty(node)) { + cpu = cpumask_first(node); + + rc = cfs_cpt_set_cpu(cptab, cpt, cpu); + if (!rc) + return -EINVAL; + cpumask_clear_cpu(cpu, node); + } + return 0; + } + + /* allocate scratch buffer */ + LIBCFS_ALLOC(socket, cpumask_size()); + LIBCFS_ALLOC(core, cpumask_size()); + if (!socket || !core) { + rc = -ENOMEM; + goto out; + } + + while (!cpumask_empty(node)) { + cpu = cpumask_first(node); + + /* get cpumask for cores in the same socket */ + cpumask_copy(socket, topology_core_cpumask(cpu)); + cpumask_and(socket, socket, node); + + LASSERT(!cpumask_empty(socket)); + + while (!cpumask_empty(socket)) { + int i; + + /* get cpumask for hts in the same core */ + cpumask_copy(core, topology_sibling_cpumask(cpu)); + cpumask_and(core, core, node); + + LASSERT(!cpumask_empty(core)); + + for_each_cpu(i, core) { + cpumask_clear_cpu(i, socket); + cpumask_clear_cpu(i, node); + + rc = cfs_cpt_set_cpu(cptab, cpt, i); + if (!rc) { + rc = -EINVAL; + goto out; + } + + if (--number == 0) + goto out; + } + cpu = cpumask_first(socket); + } + } + + out: + if (socket) + LIBCFS_FREE(socket, cpumask_size()); + if (core) + LIBCFS_FREE(core, cpumask_size()); + return rc; +} + +#define CPT_WEIGHT_MIN 4u + +static unsigned int +cfs_cpt_num_estimate(void) +{ + unsigned nnode = num_online_nodes(); + unsigned ncpu = num_online_cpus(); + unsigned ncpt; + + if (ncpu <= CPT_WEIGHT_MIN) { + ncpt = 1; + goto out; + } + + /* generate reasonable number of CPU partitions based on total number + * of CPUs, Preferred N should be power2 and match this condition: + * 2 * (N - 1)^2 < NCPUS <= 2 * N^2 + */ + for (ncpt = 2; ncpu > 2 * ncpt * ncpt; ncpt <<= 1) + ; + + if (ncpt <= nnode) { /* fat numa system */ + while (nnode > ncpt) + nnode >>= 1; + + } else { /* ncpt > nnode */ + while ((nnode << 1) <= ncpt) + nnode <<= 1; + } + + ncpt = nnode; + + out: +#if (BITS_PER_LONG == 32) + /* config many CPU partitions on 32-bit system could consume + * too much memory + */ + ncpt = min(2U, ncpt); +#endif + while (ncpu % ncpt != 0) + ncpt--; /* worst case is 1 */ + + return ncpt; +} + +static struct cfs_cpt_table * +cfs_cpt_table_create(int ncpt) +{ + struct cfs_cpt_table *cptab = NULL; + cpumask_t *mask = NULL; + int cpt = 0; + int num; + int rc; + int i; + + rc = cfs_cpt_num_estimate(); + if (ncpt <= 0) + ncpt = rc; + + if (ncpt > num_online_cpus() || ncpt > 4 * rc) { + CWARN("CPU partition number %d is larger than suggested value (%d), your system may have performance issue or run out of memory while under pressure\n", + ncpt, rc); + } + + if (num_online_cpus() % ncpt != 0) { + CERROR("CPU number %d is not multiple of cpu_npartition %d, please try different cpu_npartitions value or set pattern string by cpu_pattern=STRING\n", + (int)num_online_cpus(), ncpt); + goto failed; + } + + cptab = cfs_cpt_table_alloc(ncpt); + if (!cptab) { + CERROR("Failed to allocate CPU map(%d)\n", ncpt); + goto failed; + } + + num = num_online_cpus() / ncpt; + if (num == 0) { + CERROR("CPU changed while setting CPU partition\n"); + goto failed; + } + + LIBCFS_ALLOC(mask, cpumask_size()); + if (!mask) { + CERROR("Failed to allocate scratch cpumask\n"); + goto failed; + } + + for_each_online_node(i) { + cpumask_copy(mask, cpumask_of_node(i)); + + while (!cpumask_empty(mask)) { + struct cfs_cpu_partition *part; + int n; + + if (cpt >= ncpt) + goto failed; + + part = &cptab->ctb_parts[cpt]; + + n = num - cpumask_weight(part->cpt_cpumask); + LASSERT(n > 0); + + rc = cfs_cpt_choose_ncpus(cptab, cpt, mask, n); + if (rc < 0) + goto failed; + + LASSERT(num >= cpumask_weight(part->cpt_cpumask)); + if (num == cpumask_weight(part->cpt_cpumask)) + cpt++; + } + } + + if (cpt != ncpt || + num != cpumask_weight(cptab->ctb_parts[ncpt - 1].cpt_cpumask)) { + CERROR("Expect %d(%d) CPU partitions but got %d(%d), CPU hotplug/unplug while setting?\n", + cptab->ctb_nparts, num, cpt, + cpumask_weight(cptab->ctb_parts[ncpt - 1].cpt_cpumask)); + goto failed; + } + + LIBCFS_FREE(mask, cpumask_size()); + + return cptab; + + failed: + CERROR("Failed to setup CPU-partition-table with %d CPU-partitions, online HW nodes: %d, HW cpus: %d.\n", + ncpt, num_online_nodes(), num_online_cpus()); + + if (mask) + LIBCFS_FREE(mask, cpumask_size()); + + if (cptab) + cfs_cpt_table_free(cptab); + + return NULL; +} + +static struct cfs_cpt_table * +cfs_cpt_table_create_pattern(char *pattern) +{ + struct cfs_cpt_table *cptab; + char *str = pattern; + int node = 0; + int high; + int ncpt; + int c; + + for (ncpt = 0;; ncpt++) { /* quick scan bracket */ + str = strchr(str, '['); + if (!str) + break; + str++; + } + + str = cfs_trimwhite(pattern); + if (*str == 'n' || *str == 'N') { + pattern = str + 1; + node = 1; + } + + if (ncpt == 0 || + (node && ncpt > num_online_nodes()) || + (!node && ncpt > num_online_cpus())) { + CERROR("Invalid pattern %s, or too many partitions %d\n", + pattern, ncpt); + return NULL; + } + + high = node ? MAX_NUMNODES - 1 : nr_cpu_ids - 1; + + cptab = cfs_cpt_table_alloc(ncpt); + if (!cptab) { + CERROR("Failed to allocate cpu partition table\n"); + return NULL; + } + + for (str = cfs_trimwhite(pattern), c = 0;; c++) { + struct cfs_range_expr *range; + struct cfs_expr_list *el; + char *bracket = strchr(str, '['); + int cpt; + int rc; + int i; + int n; + + if (!bracket) { + if (*str != 0) { + CERROR("Invalid pattern %s\n", str); + goto failed; + } + if (c != ncpt) { + CERROR("expect %d partitions but found %d\n", + ncpt, c); + goto failed; + } + break; + } + + if (sscanf(str, "%d%n", &cpt, &n) < 1) { + CERROR("Invalid cpu pattern %s\n", str); + goto failed; + } + + if (cpt < 0 || cpt >= ncpt) { + CERROR("Invalid partition id %d, total partitions %d\n", + cpt, ncpt); + goto failed; + } + + if (cfs_cpt_weight(cptab, cpt) != 0) { + CERROR("Partition %d has already been set.\n", cpt); + goto failed; + } + + str = cfs_trimwhite(str + n); + if (str != bracket) { + CERROR("Invalid pattern %s\n", str); + goto failed; + } + + bracket = strchr(str, ']'); + if (!bracket) { + CERROR("missing right bracket for cpt %d, %s\n", + cpt, str); + goto failed; + } + + if (cfs_expr_list_parse(str, (bracket - str) + 1, + 0, high, &el) != 0) { + CERROR("Can't parse number range: %s\n", str); + goto failed; + } + + list_for_each_entry(range, &el->el_exprs, re_link) { + for (i = range->re_lo; i <= range->re_hi; i++) { + if ((i - range->re_lo) % range->re_stride != 0) + continue; + + rc = node ? cfs_cpt_set_node(cptab, cpt, i) : + cfs_cpt_set_cpu(cptab, cpt, i); + if (!rc) { + cfs_expr_list_free(el); + goto failed; + } + } + } + + cfs_expr_list_free(el); + + if (!cfs_cpt_online(cptab, cpt)) { + CERROR("No online CPU is found on partition %d\n", cpt); + goto failed; + } + + str = cfs_trimwhite(bracket + 1); + } + + return cptab; + + failed: + cfs_cpt_table_free(cptab); + return NULL; +} + +#ifdef CONFIG_HOTPLUG_CPU +static int +cfs_cpu_notify(struct notifier_block *self, unsigned long action, void *hcpu) +{ + unsigned int cpu = (unsigned long)hcpu; + bool warn; + + switch (action) { + case CPU_DEAD: + case CPU_DEAD_FROZEN: + case CPU_ONLINE: + case CPU_ONLINE_FROZEN: + spin_lock(&cpt_data.cpt_lock); + cpt_data.cpt_version++; + spin_unlock(&cpt_data.cpt_lock); + /* Fall through */ + default: + if (action != CPU_DEAD && action != CPU_DEAD_FROZEN) { + CDEBUG(D_INFO, "CPU changed [cpu %u action %lx]\n", + cpu, action); + break; + } + + mutex_lock(&cpt_data.cpt_mutex); + /* if all HTs in a core are offline, it may break affinity */ + cpumask_copy(cpt_data.cpt_cpumask, + topology_sibling_cpumask(cpu)); + warn = cpumask_any_and(cpt_data.cpt_cpumask, + cpu_online_mask) >= nr_cpu_ids; + mutex_unlock(&cpt_data.cpt_mutex); + CDEBUG(warn ? D_WARNING : D_INFO, + "Lustre: can't support CPU plug-out well now, performance and stability could be impacted [CPU %u action: %lx]\n", + cpu, action); + } + + return NOTIFY_OK; +} + +static struct notifier_block cfs_cpu_notifier = { + .notifier_call = cfs_cpu_notify, + .priority = 0 +}; + +#endif + +void +cfs_cpu_fini(void) +{ + if (cfs_cpt_table) + cfs_cpt_table_free(cfs_cpt_table); + +#ifdef CONFIG_HOTPLUG_CPU + unregister_hotcpu_notifier(&cfs_cpu_notifier); +#endif + if (cpt_data.cpt_cpumask) + LIBCFS_FREE(cpt_data.cpt_cpumask, cpumask_size()); +} + +int +cfs_cpu_init(void) +{ + LASSERT(!cfs_cpt_table); + + memset(&cpt_data, 0, sizeof(cpt_data)); + + LIBCFS_ALLOC(cpt_data.cpt_cpumask, cpumask_size()); + if (!cpt_data.cpt_cpumask) { + CERROR("Failed to allocate scratch buffer\n"); + return -1; + } + + spin_lock_init(&cpt_data.cpt_lock); + mutex_init(&cpt_data.cpt_mutex); + +#ifdef CONFIG_HOTPLUG_CPU + register_hotcpu_notifier(&cfs_cpu_notifier); +#endif + + if (*cpu_pattern != 0) { + cfs_cpt_table = cfs_cpt_table_create_pattern(cpu_pattern); + if (!cfs_cpt_table) { + CERROR("Failed to create cptab from pattern %s\n", + cpu_pattern); + goto failed; + } + + } else { + cfs_cpt_table = cfs_cpt_table_create(cpu_npartitions); + if (!cfs_cpt_table) { + CERROR("Failed to create ptable with npartitions %d\n", + cpu_npartitions); + goto failed; + } + } + + spin_lock(&cpt_data.cpt_lock); + if (cfs_cpt_table->ctb_version != cpt_data.cpt_version) { + spin_unlock(&cpt_data.cpt_lock); + CERROR("CPU hotplug/unplug during setup\n"); + goto failed; + } + spin_unlock(&cpt_data.cpt_lock); + + LCONSOLE(0, "HW CPU cores: %d, npartitions: %d\n", + num_online_cpus(), cfs_cpt_number(cfs_cpt_table)); + return 0; + + failed: + cfs_cpu_fini(); + return -1; +} + +#endif diff --git a/drivers/staging/lustre/lnet/libcfs/linux/linux-crypto-adler.c b/drivers/staging/lustre/lnet/libcfs/linux/linux-crypto-adler.c new file mode 100644 index 000000000000..db0572733712 --- /dev/null +++ b/drivers/staging/lustre/lnet/libcfs/linux/linux-crypto-adler.c @@ -0,0 +1,137 @@ +/* GPL HEADER START + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 only, + * as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License version 2 for more details (a copy is included + * in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU General Public License + * version 2 along with this program; If not, see http://www.gnu.org/licenses + * + * Please visit http://www.xyratex.com/contact if you need additional + * information or have any questions. + * + * GPL HEADER END + */ + +/* + * Copyright 2012 Xyratex Technology Limited + */ + +/* + * This is crypto api shash wrappers to zlib_adler32. + */ + +#include <linux/module.h> +#include <linux/zutil.h> +#include <crypto/internal/hash.h> +#include "linux-crypto.h" + +#define CHKSUM_BLOCK_SIZE 1 +#define CHKSUM_DIGEST_SIZE 4 + +static int adler32_cra_init(struct crypto_tfm *tfm) +{ + u32 *key = crypto_tfm_ctx(tfm); + + *key = 1; + + return 0; +} + +static int adler32_setkey(struct crypto_shash *hash, const u8 *key, + unsigned int keylen) +{ + u32 *mctx = crypto_shash_ctx(hash); + + if (keylen != sizeof(u32)) { + crypto_shash_set_flags(hash, CRYPTO_TFM_RES_BAD_KEY_LEN); + return -EINVAL; + } + *mctx = *(u32 *)key; + return 0; +} + +static int adler32_init(struct shash_desc *desc) +{ + u32 *mctx = crypto_shash_ctx(desc->tfm); + u32 *cksump = shash_desc_ctx(desc); + + *cksump = *mctx; + + return 0; +} + +static int adler32_update(struct shash_desc *desc, const u8 *data, + unsigned int len) +{ + u32 *cksump = shash_desc_ctx(desc); + + *cksump = zlib_adler32(*cksump, data, len); + return 0; +} + +static int __adler32_finup(u32 *cksump, const u8 *data, unsigned int len, + u8 *out) +{ + *(u32 *)out = zlib_adler32(*cksump, data, len); + return 0; +} + +static int adler32_finup(struct shash_desc *desc, const u8 *data, + unsigned int len, u8 *out) +{ + return __adler32_finup(shash_desc_ctx(desc), data, len, out); +} + +static int adler32_final(struct shash_desc *desc, u8 *out) +{ + u32 *cksump = shash_desc_ctx(desc); + + *(u32 *)out = *cksump; + return 0; +} + +static int adler32_digest(struct shash_desc *desc, const u8 *data, + unsigned int len, u8 *out) +{ + return __adler32_finup(crypto_shash_ctx(desc->tfm), data, len, + out); +} + +static struct shash_alg alg = { + .setkey = adler32_setkey, + .init = adler32_init, + .update = adler32_update, + .final = adler32_final, + .finup = adler32_finup, + .digest = adler32_digest, + .descsize = sizeof(u32), + .digestsize = CHKSUM_DIGEST_SIZE, + .base = { + .cra_name = "adler32", + .cra_driver_name = "adler32-zlib", + .cra_priority = 100, + .cra_blocksize = CHKSUM_BLOCK_SIZE, + .cra_ctxsize = sizeof(u32), + .cra_module = THIS_MODULE, + .cra_init = adler32_cra_init, + } +}; + +int cfs_crypto_adler32_register(void) +{ + return crypto_register_shash(&alg); +} + +void cfs_crypto_adler32_unregister(void) +{ + crypto_unregister_shash(&alg); +} diff --git a/drivers/staging/lustre/lnet/libcfs/linux/linux-crypto.c b/drivers/staging/lustre/lnet/libcfs/linux/linux-crypto.c new file mode 100644 index 000000000000..8c9377ed850c --- /dev/null +++ b/drivers/staging/lustre/lnet/libcfs/linux/linux-crypto.c @@ -0,0 +1,297 @@ +/* GPL HEADER START + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 only, + * as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License version 2 for more details (a copy is included + * in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU General Public License + * version 2 along with this program; If not, see http://www.gnu.org/licenses + * + * Please visit http://www.xyratex.com/contact if you need additional + * information or have any questions. + * + * GPL HEADER END + */ + +/* + * Copyright 2012 Xyratex Technology Limited + * + * Copyright (c) 2012, Intel Corporation. + */ + +#include <crypto/hash.h> +#include <linux/scatterlist.h> +#include "../../../include/linux/libcfs/libcfs.h" +#include "linux-crypto.h" +/** + * Array of hash algorithm speed in MByte per second + */ +static int cfs_crypto_hash_speeds[CFS_HASH_ALG_MAX]; + +static int cfs_crypto_hash_alloc(unsigned char alg_id, + const struct cfs_crypto_hash_type **type, + struct ahash_request **req, + unsigned char *key, + unsigned int key_len) +{ + struct crypto_ahash *tfm; + int err = 0; + + *type = cfs_crypto_hash_type(alg_id); + + if (!*type) { + CWARN("Unsupported hash algorithm id = %d, max id is %d\n", + alg_id, CFS_HASH_ALG_MAX); + return -EINVAL; + } + tfm = crypto_alloc_ahash((*type)->cht_name, 0, CRYPTO_ALG_ASYNC); + + if (IS_ERR(tfm)) { + CDEBUG(D_INFO, "Failed to alloc crypto hash %s\n", + (*type)->cht_name); + return PTR_ERR(tfm); + } + + *req = ahash_request_alloc(tfm, GFP_KERNEL); + if (!*req) { + CDEBUG(D_INFO, "Failed to alloc ahash_request for %s\n", + (*type)->cht_name); + crypto_free_ahash(tfm); + return -ENOMEM; + } + + ahash_request_set_callback(*req, 0, NULL, NULL); + + /** Shash have different logic for initialization then digest + * shash: crypto_hash_setkey, crypto_hash_init + * digest: crypto_digest_init, crypto_digest_setkey + * Skip this function for digest, because we use shash logic at + * cfs_crypto_hash_alloc. + */ + if (key) + err = crypto_ahash_setkey(tfm, key, key_len); + else if ((*type)->cht_key != 0) + err = crypto_ahash_setkey(tfm, + (unsigned char *)&((*type)->cht_key), + (*type)->cht_size); + + if (err != 0) { + crypto_free_ahash(tfm); + return err; + } + + CDEBUG(D_INFO, "Using crypto hash: %s (%s) speed %d MB/s\n", + crypto_ahash_alg_name(tfm), crypto_ahash_driver_name(tfm), + cfs_crypto_hash_speeds[alg_id]); + + err = crypto_ahash_init(*req); + if (err) { + ahash_request_free(*req); + crypto_free_ahash(tfm); + } + return err; +} + +int cfs_crypto_hash_digest(unsigned char alg_id, + const void *buf, unsigned int buf_len, + unsigned char *key, unsigned int key_len, + unsigned char *hash, unsigned int *hash_len) +{ + struct scatterlist sl; + struct ahash_request *req; + int err; + const struct cfs_crypto_hash_type *type; + + if (!buf || buf_len == 0 || !hash_len) + return -EINVAL; + + err = cfs_crypto_hash_alloc(alg_id, &type, &req, key, key_len); + if (err != 0) + return err; + + if (!hash || *hash_len < type->cht_size) { + *hash_len = type->cht_size; + crypto_free_ahash(crypto_ahash_reqtfm(req)); + ahash_request_free(req); + return -ENOSPC; + } + sg_init_one(&sl, buf, buf_len); + + ahash_request_set_crypt(req, &sl, hash, sl.length); + err = crypto_ahash_digest(req); + crypto_free_ahash(crypto_ahash_reqtfm(req)); + ahash_request_free(req); + + return err; +} +EXPORT_SYMBOL(cfs_crypto_hash_digest); + +struct cfs_crypto_hash_desc * + cfs_crypto_hash_init(unsigned char alg_id, + unsigned char *key, unsigned int key_len) +{ + struct ahash_request *req; + int err; + const struct cfs_crypto_hash_type *type; + + err = cfs_crypto_hash_alloc(alg_id, &type, &req, key, key_len); + + if (err) + return ERR_PTR(err); + return (struct cfs_crypto_hash_desc *)req; +} +EXPORT_SYMBOL(cfs_crypto_hash_init); + +int cfs_crypto_hash_update_page(struct cfs_crypto_hash_desc *hdesc, + struct page *page, unsigned int offset, + unsigned int len) +{ + struct ahash_request *req = (void *)hdesc; + struct scatterlist sl; + + sg_init_table(&sl, 1); + sg_set_page(&sl, page, len, offset & ~CFS_PAGE_MASK); + + ahash_request_set_crypt(req, &sl, NULL, sl.length); + return crypto_ahash_update(req); +} +EXPORT_SYMBOL(cfs_crypto_hash_update_page); + +int cfs_crypto_hash_update(struct cfs_crypto_hash_desc *hdesc, + const void *buf, unsigned int buf_len) +{ + struct ahash_request *req = (void *)hdesc; + struct scatterlist sl; + + sg_init_one(&sl, buf, buf_len); + + ahash_request_set_crypt(req, &sl, NULL, sl.length); + return crypto_ahash_update(req); +} +EXPORT_SYMBOL(cfs_crypto_hash_update); + +/* If hash_len pointer is NULL - destroy descriptor. */ +int cfs_crypto_hash_final(struct cfs_crypto_hash_desc *hdesc, + unsigned char *hash, unsigned int *hash_len) +{ + int err; + struct ahash_request *req = (void *)hdesc; + int size = crypto_ahash_digestsize(crypto_ahash_reqtfm(req)); + + if (!hash_len) { + crypto_free_ahash(crypto_ahash_reqtfm(req)); + ahash_request_free(req); + return 0; + } + if (!hash || *hash_len < size) { + *hash_len = size; + return -ENOSPC; + } + ahash_request_set_crypt(req, NULL, hash, 0); + err = crypto_ahash_final(req); + + if (err < 0) { + /* May be caller can fix error */ + return err; + } + crypto_free_ahash(crypto_ahash_reqtfm(req)); + ahash_request_free(req); + return err; +} +EXPORT_SYMBOL(cfs_crypto_hash_final); + +static void cfs_crypto_performance_test(unsigned char alg_id, + const unsigned char *buf, + unsigned int buf_len) +{ + unsigned long start, end; + int bcount, err = 0; + int sec = 1; /* do test only 1 sec */ + unsigned char hash[64]; + unsigned int hash_len = 64; + + for (start = jiffies, end = start + sec * HZ, bcount = 0; + time_before(jiffies, end); bcount++) { + err = cfs_crypto_hash_digest(alg_id, buf, buf_len, NULL, 0, + hash, &hash_len); + if (err) + break; + } + end = jiffies; + + if (err) { + cfs_crypto_hash_speeds[alg_id] = -1; + CDEBUG(D_INFO, "Crypto hash algorithm %s, err = %d\n", + cfs_crypto_hash_name(alg_id), err); + } else { + unsigned long tmp; + + tmp = ((bcount * buf_len / jiffies_to_msecs(end - start)) * + 1000) / (1024 * 1024); + cfs_crypto_hash_speeds[alg_id] = (int)tmp; + } + CDEBUG(D_INFO, "Crypto hash algorithm %s speed = %d MB/s\n", + cfs_crypto_hash_name(alg_id), cfs_crypto_hash_speeds[alg_id]); +} + +int cfs_crypto_hash_speed(unsigned char hash_alg) +{ + if (hash_alg < CFS_HASH_ALG_MAX) + return cfs_crypto_hash_speeds[hash_alg]; + return -1; +} +EXPORT_SYMBOL(cfs_crypto_hash_speed); + +/** + * Do performance test for all hash algorithms. + */ +static int cfs_crypto_test_hashes(void) +{ + unsigned char i; + unsigned char *data; + unsigned int j; + /* Data block size for testing hash. Maximum + * kmalloc size for 2.6.18 kernel is 128K + */ + unsigned int data_len = 1 * 128 * 1024; + + data = kmalloc(data_len, 0); + if (!data) + return -ENOMEM; + + for (j = 0; j < data_len; j++) + data[j] = j & 0xff; + + for (i = 0; i < CFS_HASH_ALG_MAX; i++) + cfs_crypto_performance_test(i, data, data_len); + + kfree(data); + return 0; +} + +static int adler32; + +int cfs_crypto_register(void) +{ + request_module("crc32c"); + + adler32 = cfs_crypto_adler32_register(); + + /* check all algorithms and do performance test */ + cfs_crypto_test_hashes(); + return 0; +} + +void cfs_crypto_unregister(void) +{ + if (adler32 == 0) + cfs_crypto_adler32_unregister(); +} diff --git a/drivers/staging/lustre/lnet/libcfs/linux/linux-crypto.h b/drivers/staging/lustre/lnet/libcfs/linux/linux-crypto.h new file mode 100644 index 000000000000..18e8cd4d8758 --- /dev/null +++ b/drivers/staging/lustre/lnet/libcfs/linux/linux-crypto.h @@ -0,0 +1,29 @@ + /* + * GPL HEADER START + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 only, + * as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License version 2 for more details (a copy is included + * in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU General Public License + * version 2 along with this program; If not, see http://www.gnu.org/licenses + * + * Please visit http://www.xyratex.com/contact if you need additional + * information or have any questions. + * + * GPL HEADER END + */ + +/** + * Functions for start/stop shash adler32 algorithm. + */ +int cfs_crypto_adler32_register(void); +void cfs_crypto_adler32_unregister(void); diff --git a/drivers/staging/lustre/lnet/libcfs/linux/linux-curproc.c b/drivers/staging/lustre/lnet/libcfs/linux/linux-curproc.c new file mode 100644 index 000000000000..13d31e8a931d --- /dev/null +++ b/drivers/staging/lustre/lnet/libcfs/linux/linux-curproc.c @@ -0,0 +1,111 @@ +/* + * GPL HEADER START + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 only, + * as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License version 2 for more details (a copy is included + * in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU General Public License + * version 2 along with this program; If not, see + * http://www.sun.com/software/products/lustre/docs/GPLv2.pdf + * + * Please contact Sun Microsystems, Inc., 4150 Network Circle, Santa Clara, + * CA 95054 USA or visit www.sun.com if you need additional information or + * have any questions. + * + * GPL HEADER END + */ +/* + * Copyright (c) 2008, 2010, Oracle and/or its affiliates. All rights reserved. + * Use is subject to license terms. + * + * Copyright (c) 2011, 2015, Intel Corporation. + */ +/* + * This file is part of Lustre, http://www.lustre.org/ + * Lustre is a trademark of Sun Microsystems, Inc. + * + * libcfs/libcfs/linux/linux-curproc.c + * + * Lustre curproc API implementation for Linux kernel + * + * Author: Nikita Danilov <nikita@clusterfs.com> + */ + +#include <linux/sched.h> +#include <linux/fs_struct.h> + +#include <linux/compat.h> +#include <linux/thread_info.h> + +#define DEBUG_SUBSYSTEM S_LNET + +#include "../../../include/linux/libcfs/libcfs.h" + +/* + * Implementation of cfs_curproc API (see portals/include/libcfs/curproc.h) + * for Linux kernel. + */ + +void cfs_cap_raise(cfs_cap_t cap) +{ + struct cred *cred; + + cred = prepare_creds(); + if (cred) { + cap_raise(cred->cap_effective, cap); + commit_creds(cred); + } +} +EXPORT_SYMBOL(cfs_cap_raise); + +void cfs_cap_lower(cfs_cap_t cap) +{ + struct cred *cred; + + cred = prepare_creds(); + if (cred) { + cap_lower(cred->cap_effective, cap); + commit_creds(cred); + } +} +EXPORT_SYMBOL(cfs_cap_lower); + +int cfs_cap_raised(cfs_cap_t cap) +{ + return cap_raised(current_cap(), cap); +} +EXPORT_SYMBOL(cfs_cap_raised); + +static void cfs_kernel_cap_pack(kernel_cap_t kcap, cfs_cap_t *cap) +{ + /* XXX lost high byte */ + *cap = kcap.cap[0]; +} + +cfs_cap_t cfs_curproc_cap_pack(void) +{ + cfs_cap_t cap; + + cfs_kernel_cap_pack(current_cap(), &cap); + return cap; +} +EXPORT_SYMBOL(cfs_curproc_cap_pack); + +/* + * Local variables: + * c-indentation-style: "K&R" + * c-basic-offset: 8 + * tab-width: 8 + * fill-column: 80 + * scroll-step: 1 + * End: + */ diff --git a/drivers/staging/lustre/lnet/libcfs/linux/linux-debug.c b/drivers/staging/lustre/lnet/libcfs/linux/linux-debug.c new file mode 100644 index 000000000000..638e4b33d3a9 --- /dev/null +++ b/drivers/staging/lustre/lnet/libcfs/linux/linux-debug.c @@ -0,0 +1,200 @@ +/* + * GPL HEADER START + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 only, + * as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License version 2 for more details (a copy is included + * in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU General Public License + * version 2 along with this program; If not, see + * http://www.sun.com/software/products/lustre/docs/GPLv2.pdf + * + * Please contact Sun Microsystems, Inc., 4150 Network Circle, Santa Clara, + * CA 95054 USA or visit www.sun.com if you need additional information or + * have any questions. + * + * GPL HEADER END + */ +/* + * Copyright (c) 2008, 2010, Oracle and/or its affiliates. All rights reserved. + * Use is subject to license terms. + * + * Copyright (c) 2012, Intel Corporation. + */ +/* + * This file is part of Lustre, http://www.lustre.org/ + * Lustre is a trademark of Sun Microsystems, Inc. + * + * libcfs/libcfs/linux/linux-debug.c + * + * Author: Phil Schwan <phil@clusterfs.com> + */ + +#include <linux/module.h> +#include <linux/kmod.h> +#include <linux/notifier.h> +#include <linux/kernel.h> +#include <linux/mm.h> +#include <linux/string.h> +#include <linux/stat.h> +#include <linux/errno.h> +#include <linux/unistd.h> +#include <linux/interrupt.h> +#include <linux/completion.h> +#include <linux/fs.h> +#include <linux/uaccess.h> +#include <linux/miscdevice.h> + +# define DEBUG_SUBSYSTEM S_LNET + +#include "../../../include/linux/libcfs/libcfs.h" + +#include "../tracefile.h" + +#include <linux/kallsyms.h> + +char lnet_upcall[1024] = "/usr/lib/lustre/lnet_upcall"; +char lnet_debug_log_upcall[1024] = "/usr/lib/lustre/lnet_debug_log_upcall"; + +/** + * Upcall function once a Lustre log has been dumped. + * + * \param file path of the dumped log + */ +void libcfs_run_debug_log_upcall(char *file) +{ + char *argv[3]; + int rc; + char *envp[] = { + "HOME=/", + "PATH=/sbin:/bin:/usr/sbin:/usr/bin", + NULL}; + + argv[0] = lnet_debug_log_upcall; + + LASSERTF(file, "called on a null filename\n"); + argv[1] = file; /* only need to pass the path of the file */ + + argv[2] = NULL; + + rc = call_usermodehelper(argv[0], argv, envp, 1); + if (rc < 0 && rc != -ENOENT) { + CERROR("Error %d invoking LNET debug log upcall %s %s; check /sys/kernel/debug/lnet/debug_log_upcall\n", + rc, argv[0], argv[1]); + } else { + CDEBUG(D_HA, "Invoked LNET debug log upcall %s %s\n", + argv[0], argv[1]); + } +} + +void libcfs_run_upcall(char **argv) +{ + int rc; + int argc; + char *envp[] = { + "HOME=/", + "PATH=/sbin:/bin:/usr/sbin:/usr/bin", + NULL}; + + argv[0] = lnet_upcall; + argc = 1; + while (argv[argc]) + argc++; + + LASSERT(argc >= 2); + + rc = call_usermodehelper(argv[0], argv, envp, 1); + if (rc < 0 && rc != -ENOENT) { + CERROR("Error %d invoking LNET upcall %s %s%s%s%s%s%s%s%s; check /sys/kernel/debug/lnet/upcall\n", + rc, argv[0], argv[1], + argc < 3 ? "" : ",", argc < 3 ? "" : argv[2], + argc < 4 ? "" : ",", argc < 4 ? "" : argv[3], + argc < 5 ? "" : ",", argc < 5 ? "" : argv[4], + argc < 6 ? "" : ",..."); + } else { + CDEBUG(D_HA, "Invoked LNET upcall %s %s%s%s%s%s%s%s%s\n", + argv[0], argv[1], + argc < 3 ? "" : ",", argc < 3 ? "" : argv[2], + argc < 4 ? "" : ",", argc < 4 ? "" : argv[3], + argc < 5 ? "" : ",", argc < 5 ? "" : argv[4], + argc < 6 ? "" : ",..."); + } +} + +void libcfs_run_lbug_upcall(struct libcfs_debug_msg_data *msgdata) +{ + char *argv[6]; + char buf[32]; + + snprintf(buf, sizeof(buf), "%d", msgdata->msg_line); + + argv[1] = "LBUG"; + argv[2] = (char *)msgdata->msg_file; + argv[3] = (char *)msgdata->msg_fn; + argv[4] = buf; + argv[5] = NULL; + + libcfs_run_upcall(argv); +} +EXPORT_SYMBOL(libcfs_run_lbug_upcall); + +/* coverity[+kill] */ +void __noreturn lbug_with_loc(struct libcfs_debug_msg_data *msgdata) +{ + libcfs_catastrophe = 1; + libcfs_debug_msg(msgdata, "LBUG\n"); + + if (in_interrupt()) { + panic("LBUG in interrupt.\n"); + /* not reached */ + } + + dump_stack(); + if (!libcfs_panic_on_lbug) + libcfs_debug_dumplog(); + libcfs_run_lbug_upcall(msgdata); + if (libcfs_panic_on_lbug) + panic("LBUG"); + set_task_state(current, TASK_UNINTERRUPTIBLE); + while (1) + schedule(); +} +EXPORT_SYMBOL(lbug_with_loc); + +static int panic_notifier(struct notifier_block *self, unsigned long unused1, + void *unused2) +{ + if (libcfs_panic_in_progress) + return 0; + + libcfs_panic_in_progress = 1; + mb(); + + return 0; +} + +static struct notifier_block libcfs_panic_notifier = { + .notifier_call = panic_notifier, + .next = NULL, + .priority = 10000, +}; + +void libcfs_register_panic_notifier(void) +{ + atomic_notifier_chain_register(&panic_notifier_list, + &libcfs_panic_notifier); +} + +void libcfs_unregister_panic_notifier(void) +{ + atomic_notifier_chain_unregister(&panic_notifier_list, + &libcfs_panic_notifier); +} diff --git a/drivers/staging/lustre/lnet/libcfs/linux/linux-mem.c b/drivers/staging/lustre/lnet/libcfs/linux/linux-mem.c new file mode 100644 index 000000000000..86f32ffc5d04 --- /dev/null +++ b/drivers/staging/lustre/lnet/libcfs/linux/linux-mem.c @@ -0,0 +1,59 @@ +/* + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 only, + * as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License version 2 for more details (a copy is included + * in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU General Public License + * version 2 along with this program; If not, see + * http://www.sun.com/software/products/lustre/docs/GPLv2.pdf + * + */ +/* + * This file creates a memory allocation primitive for Lustre, that + * allows to fallback to vmalloc allocations should regular kernel allocations + * fail due to size or system memory fragmentation. + * + * Author: Oleg Drokin <green@linuxhacker.ru> + * + */ +/* + * This file is part of Lustre, http://www.lustre.org/ + * Lustre is a trademark of Seagate Technology. + */ +#include <linux/slab.h> +#include <linux/vmalloc.h> + +#include "../../../include/linux/libcfs/libcfs.h" + +void *libcfs_kvzalloc(size_t size, gfp_t flags) +{ + void *ret; + + ret = kzalloc(size, flags | __GFP_NOWARN); + if (!ret) + ret = __vmalloc(size, flags | __GFP_ZERO, PAGE_KERNEL); + return ret; +} +EXPORT_SYMBOL(libcfs_kvzalloc); + +void *libcfs_kvzalloc_cpt(struct cfs_cpt_table *cptab, int cpt, size_t size, + gfp_t flags) +{ + void *ret; + + ret = kzalloc_node(size, flags | __GFP_NOWARN, + cfs_cpt_spread_node(cptab, cpt)); + if (!ret) { + WARN_ON(!(flags & (__GFP_FS | __GFP_HIGH))); + ret = vmalloc_node(size, cfs_cpt_spread_node(cptab, cpt)); + } + + return ret; +} +EXPORT_SYMBOL(libcfs_kvzalloc_cpt); diff --git a/drivers/staging/lustre/lnet/libcfs/linux/linux-module.c b/drivers/staging/lustre/lnet/libcfs/linux/linux-module.c new file mode 100644 index 000000000000..ebc60ac9bb7a --- /dev/null +++ b/drivers/staging/lustre/lnet/libcfs/linux/linux-module.c @@ -0,0 +1,159 @@ +/* + * GPL HEADER START + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 only, + * as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License version 2 for more details (a copy is included + * in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU General Public License + * version 2 along with this program; If not, see + * http://www.sun.com/software/products/lustre/docs/GPLv2.pdf + * + * Please contact Sun Microsystems, Inc., 4150 Network Circle, Santa Clara, + * CA 95054 USA or visit www.sun.com if you need additional information or + * have any questions. + * + * GPL HEADER END + */ +/* + * Copyright (c) 2008, 2010, Oracle and/or its affiliates. All rights reserved. + * Use is subject to license terms. + * + * Copyright (c) 2012, Intel Corporation. + */ +/* + * This file is part of Lustre, http://www.lustre.org/ + * Lustre is a trademark of Sun Microsystems, Inc. + */ + +#define DEBUG_SUBSYSTEM S_LNET + +#include "../../../include/linux/libcfs/libcfs.h" + +#define LNET_MINOR 240 + +int libcfs_ioctl_data_adjust(struct libcfs_ioctl_data *data) +{ + if (libcfs_ioctl_is_invalid(data)) { + CERROR("LNET: ioctl not correctly formatted\n"); + return -EINVAL; + } + + if (data->ioc_inllen1) + data->ioc_inlbuf1 = &data->ioc_bulk[0]; + + if (data->ioc_inllen2) + data->ioc_inlbuf2 = &data->ioc_bulk[0] + + cfs_size_round(data->ioc_inllen1); + + return 0; +} + +int libcfs_ioctl_getdata_len(const struct libcfs_ioctl_hdr __user *arg, + __u32 *len) +{ + struct libcfs_ioctl_hdr hdr; + + if (copy_from_user(&hdr, arg, sizeof(hdr))) + return -EFAULT; + + if (hdr.ioc_version != LIBCFS_IOCTL_VERSION && + hdr.ioc_version != LIBCFS_IOCTL_VERSION2) { + CERROR("LNET: version mismatch expected %#x, got %#x\n", + LIBCFS_IOCTL_VERSION, hdr.ioc_version); + return -EINVAL; + } + + *len = hdr.ioc_len; + + return 0; +} + +int libcfs_ioctl_popdata(void __user *arg, void *data, int size) +{ + if (copy_to_user(arg, data, size)) + return -EFAULT; + return 0; +} + +static int +libcfs_psdev_open(struct inode *inode, struct file *file) +{ + int rc = 0; + + if (!inode) + return -EINVAL; + if (libcfs_psdev_ops.p_open) + rc = libcfs_psdev_ops.p_open(0, NULL); + else + return -EPERM; + return rc; +} + +/* called when closing /dev/device */ +static int +libcfs_psdev_release(struct inode *inode, struct file *file) +{ + int rc = 0; + + if (!inode) + return -EINVAL; + if (libcfs_psdev_ops.p_close) + rc = libcfs_psdev_ops.p_close(0, NULL); + else + rc = -EPERM; + return rc; +} + +static long libcfs_ioctl(struct file *file, + unsigned int cmd, unsigned long arg) +{ + struct cfs_psdev_file pfile; + int rc = 0; + + if (!capable(CAP_SYS_ADMIN)) + return -EACCES; + + if (_IOC_TYPE(cmd) != IOC_LIBCFS_TYPE || + _IOC_NR(cmd) < IOC_LIBCFS_MIN_NR || + _IOC_NR(cmd) > IOC_LIBCFS_MAX_NR) { + CDEBUG(D_IOCTL, "invalid ioctl ( type %d, nr %d, size %d )\n", + _IOC_TYPE(cmd), _IOC_NR(cmd), _IOC_SIZE(cmd)); + return -EINVAL; + } + + /* Handle platform-dependent IOC requests */ + switch (cmd) { + case IOC_LIBCFS_PANIC: + if (!capable(CFS_CAP_SYS_BOOT)) + return -EPERM; + panic("debugctl-invoked panic"); + return 0; + } + + if (libcfs_psdev_ops.p_ioctl) + rc = libcfs_psdev_ops.p_ioctl(&pfile, cmd, (void __user *)arg); + else + rc = -EPERM; + return rc; +} + +static const struct file_operations libcfs_fops = { + .unlocked_ioctl = libcfs_ioctl, + .open = libcfs_psdev_open, + .release = libcfs_psdev_release, +}; + +struct miscdevice libcfs_dev = { + .minor = LNET_MINOR, + .name = "lnet", + .fops = &libcfs_fops, +}; diff --git a/drivers/staging/lustre/lnet/libcfs/linux/linux-prim.c b/drivers/staging/lustre/lnet/libcfs/linux/linux-prim.c new file mode 100644 index 000000000000..89084460231a --- /dev/null +++ b/drivers/staging/lustre/lnet/libcfs/linux/linux-prim.c @@ -0,0 +1,147 @@ +/* + * GPL HEADER START + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 only, + * as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License version 2 for more details (a copy is included + * in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU General Public License + * version 2 along with this program; If not, see + * http://www.sun.com/software/products/lustre/docs/GPLv2.pdf + * + * Please contact Sun Microsystems, Inc., 4150 Network Circle, Santa Clara, + * CA 95054 USA or visit www.sun.com if you need additional information or + * have any questions. + * + * GPL HEADER END + */ +/* + * Copyright (c) 2008, 2010, Oracle and/or its affiliates. All rights reserved. + * Use is subject to license terms. + * + * Copyright (c) 2011, 2012, Intel Corporation. + */ +/* + * This file is part of Lustre, http://www.lustre.org/ + * Lustre is a trademark of Sun Microsystems, Inc. + */ + +#define DEBUG_SUBSYSTEM S_LNET +#include <linux/module.h> +#include <linux/kernel.h> +#include <linux/fs_struct.h> +#include <linux/sched.h> + +#include "../../../include/linux/libcfs/libcfs.h" + +#if defined(CONFIG_KGDB) +#include <linux/kgdb.h> +#endif + +/** + * wait_queue_t of Linux (version < 2.6.34) is a FIFO list for exclusively + * waiting threads, which is not always desirable because all threads will + * be waken up again and again, even user only needs a few of them to be + * active most time. This is not good for performance because cache can + * be polluted by different threads. + * + * LIFO list can resolve this problem because we always wakeup the most + * recent active thread by default. + * + * NB: please don't call non-exclusive & exclusive wait on the same + * waitq if add_wait_queue_exclusive_head is used. + */ +void +add_wait_queue_exclusive_head(wait_queue_head_t *waitq, wait_queue_t *link) +{ + unsigned long flags; + + spin_lock_irqsave(&waitq->lock, flags); + __add_wait_queue_exclusive(waitq, link); + spin_unlock_irqrestore(&waitq->lock, flags); +} +EXPORT_SYMBOL(add_wait_queue_exclusive_head); + +sigset_t +cfs_block_allsigs(void) +{ + unsigned long flags; + sigset_t old; + + spin_lock_irqsave(¤t->sighand->siglock, flags); + old = current->blocked; + sigfillset(¤t->blocked); + recalc_sigpending(); + spin_unlock_irqrestore(¤t->sighand->siglock, flags); + + return old; +} +EXPORT_SYMBOL(cfs_block_allsigs); + +sigset_t cfs_block_sigs(unsigned long sigs) +{ + unsigned long flags; + sigset_t old; + + spin_lock_irqsave(¤t->sighand->siglock, flags); + old = current->blocked; + sigaddsetmask(¤t->blocked, sigs); + recalc_sigpending(); + spin_unlock_irqrestore(¤t->sighand->siglock, flags); + return old; +} +EXPORT_SYMBOL(cfs_block_sigs); + +/* Block all signals except for the @sigs */ +sigset_t cfs_block_sigsinv(unsigned long sigs) +{ + unsigned long flags; + sigset_t old; + + spin_lock_irqsave(¤t->sighand->siglock, flags); + old = current->blocked; + sigaddsetmask(¤t->blocked, ~sigs); + recalc_sigpending(); + spin_unlock_irqrestore(¤t->sighand->siglock, flags); + + return old; +} +EXPORT_SYMBOL(cfs_block_sigsinv); + +void +cfs_restore_sigs(sigset_t old) +{ + unsigned long flags; + + spin_lock_irqsave(¤t->sighand->siglock, flags); + current->blocked = old; + recalc_sigpending(); + spin_unlock_irqrestore(¤t->sighand->siglock, flags); +} +EXPORT_SYMBOL(cfs_restore_sigs); + +int +cfs_signal_pending(void) +{ + return signal_pending(current); +} +EXPORT_SYMBOL(cfs_signal_pending); + +void +cfs_clear_sigpending(void) +{ + unsigned long flags; + + spin_lock_irqsave(¤t->sighand->siglock, flags); + clear_tsk_thread_flag(current, TIF_SIGPENDING); + spin_unlock_irqrestore(¤t->sighand->siglock, flags); +} +EXPORT_SYMBOL(cfs_clear_sigpending); diff --git a/drivers/staging/lustre/lnet/libcfs/linux/linux-tracefile.c b/drivers/staging/lustre/lnet/libcfs/linux/linux-tracefile.c new file mode 100644 index 000000000000..91c2ae8f9d67 --- /dev/null +++ b/drivers/staging/lustre/lnet/libcfs/linux/linux-tracefile.c @@ -0,0 +1,259 @@ +/* + * GPL HEADER START + * + * DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 only, + * as published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, but + * WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * General Public License version 2 for more details (a copy is included + * in the LICENSE file that accompanied this code). + * + * You should have received a copy of the GNU General Public License + * version 2 along with this program; If not, see + * http://www.sun.com/software/products/lustre/docs/GPLv2.pdf + * + * Please contact Sun Microsystems, Inc., 4150 Network Circle, Santa Clara, + * CA 95054 USA or visit www.sun.com if you need additional information or + * have any questions. + * + * GPL HEADER END + */ +/* + * Copyright (c) 2008, 2010, Oracle and/or its affiliates. All rights reserved. + * Use is subject to license terms. + * + * Copyright (c) 2012, Intel Corporation. + */ +/* + * This file is part of Lustre, http://www.lustre.org/ + * Lustre is a trademark of Sun Microsystems, Inc. + */ + +#define DEBUG_SUBSYSTEM S_LNET +#define LUSTRE_TRACEFILE_PRIVATE + +#include "../../../include/linux/libcfs/libcfs.h" +#include "../tracefile.h" + +/* percents to share the total debug memory for each type */ +static unsigned int pages_factor[CFS_TCD_TYPE_MAX] = { + 80, /* 80% pages for CFS_TCD_TYPE_PROC */ + 10, /* 10% pages for CFS_TCD_TYPE_SOFTIRQ */ + 10 /* 10% pages for CFS_TCD_TYPE_IRQ */ +}; + +char *cfs_trace_console_buffers[NR_CPUS][CFS_TCD_TYPE_MAX]; + +static DECLARE_RWSEM(cfs_tracefile_sem); + +int cfs_tracefile_init_arch(void) +{ + int i; + int j; + struct cfs_trace_cpu_data *tcd; + + /* initialize trace_data */ + memset(cfs_trace_data, 0, sizeof(cfs_trace_data)); + for (i = 0; i < CFS_TCD_TYPE_MAX; i++) { + cfs_trace_data[i] = + kmalloc(sizeof(union cfs_trace_data_union) * + num_possible_cpus(), GFP_KERNEL); + if (!cfs_trace_data[i]) + goto out; + } + + /* arch related info initialized */ + cfs_tcd_for_each(tcd, i, j) { + spin_lock_init(&tcd->tcd_lock); + tcd->tcd_pages_factor = pages_factor[i]; + tcd->tcd_type = i; + tcd->tcd_cpu = j; + } + + for (i = 0; i < num_possible_cpus(); i++) + for (j = 0; j < 3; j++) { + cfs_trace_console_buffers[i][j] = + kmalloc(CFS_TRACE_CONSOLE_BUFFER_SIZE, + GFP_KERNEL); + + if (!cfs_trace_console_buffers[i][j]) + goto out; + } + + return 0; + +out: + cfs_tracefile_fini_arch(); + printk(KERN_ERR "lnet: Not enough memory\n"); + return -ENOMEM; +} + +void cfs_tracefile_fini_arch(void) +{ + int i; + int j; + + for (i = 0; i < num_possible_cpus(); i++) + for (j = 0; j < 3; j++) { + kfree(cfs_trace_console_buffers[i][j]); + cfs_trace_console_buffers[i][j] = NULL; + } + + for (i = 0; cfs_trace_data[i]; i++) { + kfree(cfs_trace_data[i]); + cfs_trace_data[i] = NULL; + } +} + +void cfs_tracefile_read_lock(void) +{ + down_read(&cfs_tracefile_sem); +} + +void cfs_tracefile_read_unlock(void) +{ + up_read(&cfs_tracefile_sem); +} + +void cfs_tracefile_write_lock(void) +{ + down_write(&cfs_tracefile_sem); +} + +void cfs_tracefile_write_unlock(void) +{ + up_write(&cfs_tracefile_sem); +} + +enum cfs_trace_buf_type cfs_trace_buf_idx_get(void) +{ + if (in_irq()) + return CFS_TCD_TYPE_IRQ; + if (in_softirq()) + return CFS_TCD_TYPE_SOFTIRQ; + return CFS_TCD_TYPE_PROC; +} + +/* + * The walking argument indicates the locking comes from all tcd types + * iterator and we must lock it and dissable local irqs to avoid deadlocks + * with other interrupt locks that might be happening. See LU-1311 + * for details. + */ +int cfs_trace_lock_tcd(struct cfs_trace_cpu_data *tcd, int walking) + __acquires(&tcd->tc_lock) +{ + __LASSERT(tcd->tcd_type < CFS_TCD_TYPE_MAX); + if (tcd->tcd_type == CFS_TCD_TYPE_IRQ) + spin_lock_irqsave(&tcd->tcd_lock, tcd->tcd_lock_flags); + else if (tcd->tcd_type == CFS_TCD_TYPE_SOFTIRQ) + spin_lock_bh(&tcd->tcd_lock); + else if (unlikely(walking)) + spin_lock_irq(&tcd->tcd_lock); + else + spin_lock(&tcd->tcd_lock); + return 1; +} + +void cfs_trace_unlock_tcd(struct cfs_trace_cpu_data *tcd, int walking) + __releases(&tcd->tcd_lock) +{ + __LASSERT(tcd->tcd_type < CFS_TCD_TYPE_MAX); + if (tcd->tcd_type == CFS_TCD_TYPE_IRQ) + spin_unlock_irqrestore(&tcd->tcd_lock, tcd->tcd_lock_flags); + else if (tcd->tcd_type == CFS_TCD_TYPE_SOFTIRQ) + spin_unlock_bh(&tcd->tcd_lock); + else if (unlikely(walking)) + spin_unlock_irq(&tcd->tcd_lock); + else + spin_unlock(&tcd->tcd_lock); +} + +void +cfs_set_ptldebug_header(struct ptldebug_header *header, + struct libcfs_debug_msg_data *msgdata, + unsigned long stack) +{ + struct timespec64 ts; + + ktime_get_real_ts64(&ts); + + header->ph_subsys = msgdata->msg_subsys; + header->ph_mask = msgdata->msg_mask; + header->ph_cpu_id = smp_processor_id(); + header->ph_type = cfs_trace_buf_idx_get(); + /* y2038 safe since all user space treats this as unsigned, but + * will overflow in 2106 + */ + header->ph_sec = (u32)ts.tv_sec; + header->ph_usec = ts.tv_nsec / NSEC_PER_USEC; + header->ph_stack = stack; + header->ph_pid = current->pid; + header->ph_line_num = msgdata->msg_line; + header->ph_extern_pid = 0; +} + +static char * +dbghdr_to_err_string(struct ptldebug_header *hdr) +{ + switch (hdr->ph_subsys) { + case S_LND: + case S_LNET: + return "LNetError"; + default: + return "LustreError"; + } +} + +static char * +dbghdr_to_info_string(struct ptldebug_header *hdr) +{ + switch (hdr->ph_subsys) { + case S_LND: + case S_LNET: + return "LNet"; + default: + return "Lustre"; + } +} + +void cfs_print_to_console(struct ptldebug_header *hdr, int mask, + const char *buf, int len, const char *file, + const char *fn) +{ + char *prefix = "Lustre", *ptype = NULL; + + if ((mask & D_EMERG) != 0) { + prefix = dbghdr_to_err_string(hdr); + ptype = KERN_EMERG; + } else if ((mask & D_ERROR) != 0) { + prefix = dbghdr_to_err_string(hdr); + ptype = KERN_ERR; + } else if ((mask & D_WARNING) != 0) { + prefix = dbghdr_to_info_string(hdr); + ptype = KERN_WARNING; + } else if ((mask & (D_CONSOLE | libcfs_printk)) != 0) { + prefix = dbghdr_to_info_string(hdr); + ptype = KERN_INFO; + } + + if ((mask & D_CONSOLE) != 0) { + printk("%s%s: %.*s", ptype, prefix, len, buf); + } else { + printk("%s%s: %d:%d:(%s:%d:%s()) %.*s", ptype, prefix, + hdr->ph_pid, hdr->ph_extern_pid, file, hdr->ph_line_num, + fn, len, buf); + } +} + +int cfs_trace_max_debug_mb(void) +{ + int total_mb = (totalram_pages >> (20 - PAGE_SHIFT)); + + return max(512, (total_mb * 80) / 100); +} |