Revision 89c38422e072bb453e3045b8f1b962a344c3edea authored by John Garry on 08 November 2018, 10:17:03 UTC, committed by Rob Herring on 08 November 2018, 18:44:34 UTC
Currently the NUMA distance map parsing does not validate the distance table for the distance-matrix rules 1-2 in [1]. However the arch NUMA code may enforce some of these rules, but not all. Such is the case for the arm64 port, which does not enforce the rule that the distance between separates nodes cannot equal LOCAL_DISTANCE. The patch adds the following rules validation: - distance of node to self equals LOCAL_DISTANCE - distance of separate nodes > LOCAL_DISTANCE This change avoids a yet-unresolved crash reported in [2]. A note on dealing with symmetrical distances between nodes: Validating symmetrical distances between nodes is difficult. If it were mandated in the bindings that every distance must be recorded in the table, then it would be easy. However, it isn't. In addition to this, it is also possible to record [b, a] distance only (and not [a, b]). So, when processing the table for [b, a], we cannot assert that current distance of [a, b] != [b, a] as invalid, as [a, b] distance may not be present in the table and current distance would be default at REMOTE_DISTANCE. As such, we maintain the policy that we overwrite distance [a, b] = [b, a] for b > a. This policy is different to kernel ACPI SLIT validation, which allows non-symmetrical distances (ACPI spec SLIT rules allow it). However, the distance debug message is dropped as it may be misleading (for a distance which is later overwritten). Some final notes on semantics: - It is implied that it is the responsibility of the arch NUMA code to reset the NUMA distance map for an error in distance map parsing. - It is the responsibility of the FW NUMA topology parsing (whether OF or ACPI) to enforce NUMA distance rules, and not arch NUMA code. [1] Documents/devicetree/bindings/numa.txt [2] https://www.spinics.net/lists/arm-kernel/msg683304.html Cc: stable@vger.kernel.org # 4.7 Signed-off-by: John Garry <john.garry@huawei.com> Acked-by: Will Deacon <will.deacon@arm.com> Signed-off-by: Rob Herring <robh@kernel.org>
1 parent 6778be4
ipc_sysctl.c
/*
* Copyright (C) 2007
*
* Author: Eric Biederman <ebiederm@xmision.com>
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License as
* published by the Free Software Foundation, version 2 of the
* License.
*/
#include <linux/module.h>
#include <linux/ipc.h>
#include <linux/nsproxy.h>
#include <linux/sysctl.h>
#include <linux/uaccess.h>
#include <linux/ipc_namespace.h>
#include <linux/msg.h>
#include "util.h"
static void *get_ipc(struct ctl_table *table)
{
char *which = table->data;
struct ipc_namespace *ipc_ns = current->nsproxy->ipc_ns;
which = (which - (char *)&init_ipc_ns) + (char *)ipc_ns;
return which;
}
#ifdef CONFIG_PROC_SYSCTL
static int proc_ipc_dointvec(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
struct ctl_table ipc_table;
memcpy(&ipc_table, table, sizeof(ipc_table));
ipc_table.data = get_ipc(table);
return proc_dointvec(&ipc_table, write, buffer, lenp, ppos);
}
static int proc_ipc_dointvec_minmax(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
struct ctl_table ipc_table;
memcpy(&ipc_table, table, sizeof(ipc_table));
ipc_table.data = get_ipc(table);
return proc_dointvec_minmax(&ipc_table, write, buffer, lenp, ppos);
}
static int proc_ipc_dointvec_minmax_orphans(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
struct ipc_namespace *ns = current->nsproxy->ipc_ns;
int err = proc_ipc_dointvec_minmax(table, write, buffer, lenp, ppos);
if (err < 0)
return err;
if (ns->shm_rmid_forced)
shm_destroy_orphaned(ns);
return err;
}
static int proc_ipc_doulongvec_minmax(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
struct ctl_table ipc_table;
memcpy(&ipc_table, table, sizeof(ipc_table));
ipc_table.data = get_ipc(table);
return proc_doulongvec_minmax(&ipc_table, write, buffer,
lenp, ppos);
}
static int proc_ipc_auto_msgmni(struct ctl_table *table, int write,
void __user *buffer, size_t *lenp, loff_t *ppos)
{
struct ctl_table ipc_table;
int dummy = 0;
memcpy(&ipc_table, table, sizeof(ipc_table));
ipc_table.data = &dummy;
if (write)
pr_info_once("writing to auto_msgmni has no effect");
return proc_dointvec_minmax(&ipc_table, write, buffer, lenp, ppos);
}
#else
#define proc_ipc_doulongvec_minmax NULL
#define proc_ipc_dointvec NULL
#define proc_ipc_dointvec_minmax NULL
#define proc_ipc_dointvec_minmax_orphans NULL
#define proc_ipc_auto_msgmni NULL
#endif
static int zero;
static int one = 1;
static int int_max = INT_MAX;
static struct ctl_table ipc_kern_table[] = {
{
.procname = "shmmax",
.data = &init_ipc_ns.shm_ctlmax,
.maxlen = sizeof(init_ipc_ns.shm_ctlmax),
.mode = 0644,
.proc_handler = proc_ipc_doulongvec_minmax,
},
{
.procname = "shmall",
.data = &init_ipc_ns.shm_ctlall,
.maxlen = sizeof(init_ipc_ns.shm_ctlall),
.mode = 0644,
.proc_handler = proc_ipc_doulongvec_minmax,
},
{
.procname = "shmmni",
.data = &init_ipc_ns.shm_ctlmni,
.maxlen = sizeof(init_ipc_ns.shm_ctlmni),
.mode = 0644,
.proc_handler = proc_ipc_dointvec,
},
{
.procname = "shm_rmid_forced",
.data = &init_ipc_ns.shm_rmid_forced,
.maxlen = sizeof(init_ipc_ns.shm_rmid_forced),
.mode = 0644,
.proc_handler = proc_ipc_dointvec_minmax_orphans,
.extra1 = &zero,
.extra2 = &one,
},
{
.procname = "msgmax",
.data = &init_ipc_ns.msg_ctlmax,
.maxlen = sizeof(init_ipc_ns.msg_ctlmax),
.mode = 0644,
.proc_handler = proc_ipc_dointvec_minmax,
.extra1 = &zero,
.extra2 = &int_max,
},
{
.procname = "msgmni",
.data = &init_ipc_ns.msg_ctlmni,
.maxlen = sizeof(init_ipc_ns.msg_ctlmni),
.mode = 0644,
.proc_handler = proc_ipc_dointvec_minmax,
.extra1 = &zero,
.extra2 = &int_max,
},
{
.procname = "auto_msgmni",
.data = NULL,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_ipc_auto_msgmni,
.extra1 = &zero,
.extra2 = &one,
},
{
.procname = "msgmnb",
.data = &init_ipc_ns.msg_ctlmnb,
.maxlen = sizeof(init_ipc_ns.msg_ctlmnb),
.mode = 0644,
.proc_handler = proc_ipc_dointvec_minmax,
.extra1 = &zero,
.extra2 = &int_max,
},
{
.procname = "sem",
.data = &init_ipc_ns.sem_ctls,
.maxlen = 4*sizeof(int),
.mode = 0644,
.proc_handler = proc_ipc_dointvec,
},
#ifdef CONFIG_CHECKPOINT_RESTORE
{
.procname = "sem_next_id",
.data = &init_ipc_ns.ids[IPC_SEM_IDS].next_id,
.maxlen = sizeof(init_ipc_ns.ids[IPC_SEM_IDS].next_id),
.mode = 0644,
.proc_handler = proc_ipc_dointvec_minmax,
.extra1 = &zero,
.extra2 = &int_max,
},
{
.procname = "msg_next_id",
.data = &init_ipc_ns.ids[IPC_MSG_IDS].next_id,
.maxlen = sizeof(init_ipc_ns.ids[IPC_MSG_IDS].next_id),
.mode = 0644,
.proc_handler = proc_ipc_dointvec_minmax,
.extra1 = &zero,
.extra2 = &int_max,
},
{
.procname = "shm_next_id",
.data = &init_ipc_ns.ids[IPC_SHM_IDS].next_id,
.maxlen = sizeof(init_ipc_ns.ids[IPC_SHM_IDS].next_id),
.mode = 0644,
.proc_handler = proc_ipc_dointvec_minmax,
.extra1 = &zero,
.extra2 = &int_max,
},
#endif
{}
};
static struct ctl_table ipc_root_table[] = {
{
.procname = "kernel",
.mode = 0555,
.child = ipc_kern_table,
},
{}
};
static int __init ipc_sysctl_init(void)
{
register_sysctl_table(ipc_root_table);
return 0;
}
device_initcall(ipc_sysctl_init);
Computing file changes ...
