summaryrefslogtreecommitdiffstats
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/bpf/verifier.c43
-rw-r--r--kernel/cred.c6
-rw-r--r--kernel/exit.c12
-rw-r--r--kernel/irq/cpuhotplug.c21
-rw-r--r--kernel/irq/irqdesc.c1
-rw-r--r--kernel/irq/manage.c45
-rw-r--r--kernel/irq/spurious.c1
-rw-r--r--kernel/sched/isolation.c6
-rw-r--r--kernel/seccomp.c7
-rw-r--r--kernel/taskstats.c30
-rw-r--r--kernel/time/posix-clock.c31
11 files changed, 141 insertions, 62 deletions
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 4983940cbdca..6f63ae7a370c 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -907,7 +907,8 @@ static const int caller_saved[CALLER_SAVED_REGS] = {
BPF_REG_0, BPF_REG_1, BPF_REG_2, BPF_REG_3, BPF_REG_4, BPF_REG_5
};
-static void __mark_reg_not_init(struct bpf_reg_state *reg);
+static void __mark_reg_not_init(const struct bpf_verifier_env *env,
+ struct bpf_reg_state *reg);
/* Mark the unknown part of a register (variable offset or scalar value) as
* known to have the value @imm.
@@ -945,7 +946,7 @@ static void mark_reg_known_zero(struct bpf_verifier_env *env,
verbose(env, "mark_reg_known_zero(regs, %u)\n", regno);
/* Something bad happened, let's kill all regs */
for (regno = 0; regno < MAX_BPF_REG; regno++)
- __mark_reg_not_init(regs + regno);
+ __mark_reg_not_init(env, regs + regno);
return;
}
__mark_reg_known_zero(regs + regno);
@@ -1054,7 +1055,8 @@ static void __mark_reg_unbounded(struct bpf_reg_state *reg)
}
/* Mark a register as having a completely unknown (scalar) value. */
-static void __mark_reg_unknown(struct bpf_reg_state *reg)
+static void __mark_reg_unknown(const struct bpf_verifier_env *env,
+ struct bpf_reg_state *reg)
{
/*
* Clear type, id, off, and union(map_ptr, range) and
@@ -1064,6 +1066,8 @@ static void __mark_reg_unknown(struct bpf_reg_state *reg)
reg->type = SCALAR_VALUE;
reg->var_off = tnum_unknown;
reg->frameno = 0;
+ reg->precise = env->subprog_cnt > 1 || !env->allow_ptr_leaks ?
+ true : false;
__mark_reg_unbounded(reg);
}
@@ -1074,19 +1078,16 @@ static void mark_reg_unknown(struct bpf_verifier_env *env,
verbose(env, "mark_reg_unknown(regs, %u)\n", regno);
/* Something bad happened, let's kill all regs except FP */
for (regno = 0; regno < BPF_REG_FP; regno++)
- __mark_reg_not_init(regs + regno);
+ __mark_reg_not_init(env, regs + regno);
return;
}
- regs += regno;
- __mark_reg_unknown(regs);
- /* constant backtracking is enabled for root without bpf2bpf calls */
- regs->precise = env->subprog_cnt > 1 || !env->allow_ptr_leaks ?
- true : false;
+ __mark_reg_unknown(env, regs + regno);
}
-static void __mark_reg_not_init(struct bpf_reg_state *reg)
+static void __mark_reg_not_init(const struct bpf_verifier_env *env,
+ struct bpf_reg_state *reg)
{
- __mark_reg_unknown(reg);
+ __mark_reg_unknown(env, reg);
reg->type = NOT_INIT;
}
@@ -1097,10 +1098,10 @@ static void mark_reg_not_init(struct bpf_verifier_env *env,
verbose(env, "mark_reg_not_init(regs, %u)\n", regno);
/* Something bad happened, let's kill all regs except FP */
for (regno = 0; regno < BPF_REG_FP; regno++)
- __mark_reg_not_init(regs + regno);
+ __mark_reg_not_init(env, regs + regno);
return;
}
- __mark_reg_not_init(regs + regno);
+ __mark_reg_not_init(env, regs + regno);
}
#define DEF_NOT_SUBREG (0)
@@ -3234,7 +3235,7 @@ static int check_stack_boundary(struct bpf_verifier_env *env, int regno,
}
if (state->stack[spi].slot_type[0] == STACK_SPILL &&
state->stack[spi].spilled_ptr.type == SCALAR_VALUE) {
- __mark_reg_unknown(&state->stack[spi].spilled_ptr);
+ __mark_reg_unknown(env, &state->stack[spi].spilled_ptr);
for (j = 0; j < BPF_REG_SIZE; j++)
state->stack[spi].slot_type[j] = STACK_MISC;
goto mark;
@@ -3892,7 +3893,7 @@ static void __clear_all_pkt_pointers(struct bpf_verifier_env *env,
if (!reg)
continue;
if (reg_is_pkt_pointer_any(reg))
- __mark_reg_unknown(reg);
+ __mark_reg_unknown(env, reg);
}
}
@@ -3920,7 +3921,7 @@ static void release_reg_references(struct bpf_verifier_env *env,
if (!reg)
continue;
if (reg->ref_obj_id == ref_obj_id)
- __mark_reg_unknown(reg);
+ __mark_reg_unknown(env, reg);
}
}
@@ -4582,7 +4583,7 @@ static int adjust_ptr_min_max_vals(struct bpf_verifier_env *env,
/* Taint dst register if offset had invalid bounds derived from
* e.g. dead branches.
*/
- __mark_reg_unknown(dst_reg);
+ __mark_reg_unknown(env, dst_reg);
return 0;
}
@@ -4834,13 +4835,13 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env,
/* Taint dst register if offset had invalid bounds derived from
* e.g. dead branches.
*/
- __mark_reg_unknown(dst_reg);
+ __mark_reg_unknown(env, dst_reg);
return 0;
}
if (!src_known &&
opcode != BPF_ADD && opcode != BPF_SUB && opcode != BPF_AND) {
- __mark_reg_unknown(dst_reg);
+ __mark_reg_unknown(env, dst_reg);
return 0;
}
@@ -6982,7 +6983,7 @@ static void clean_func_state(struct bpf_verifier_env *env,
/* since the register is unused, clear its state
* to make further comparison simpler
*/
- __mark_reg_not_init(&st->regs[i]);
+ __mark_reg_not_init(env, &st->regs[i]);
}
for (i = 0; i < st->allocated_stack / BPF_REG_SIZE; i++) {
@@ -6990,7 +6991,7 @@ static void clean_func_state(struct bpf_verifier_env *env,
/* liveness must not touch this stack slot anymore */
st->stack[i].spilled_ptr.live |= REG_LIVE_DONE;
if (!(live & REG_LIVE_READ)) {
- __mark_reg_not_init(&st->stack[i].spilled_ptr);
+ __mark_reg_not_init(env, &st->stack[i].spilled_ptr);
for (j = 0; j < BPF_REG_SIZE; j++)
st->stack[i].slot_type[j] = STACK_INVALID;
}
diff --git a/kernel/cred.c b/kernel/cred.c
index c0a4c12d38b2..9ed51b70ed80 100644
--- a/kernel/cred.c
+++ b/kernel/cred.c
@@ -223,7 +223,7 @@ struct cred *cred_alloc_blank(void)
new->magic = CRED_MAGIC;
#endif
- if (security_cred_alloc_blank(new, GFP_KERNEL) < 0)
+ if (security_cred_alloc_blank(new, GFP_KERNEL_ACCOUNT) < 0)
goto error;
return new;
@@ -282,7 +282,7 @@ struct cred *prepare_creds(void)
new->security = NULL;
#endif
- if (security_prepare_creds(new, old, GFP_KERNEL) < 0)
+ if (security_prepare_creds(new, old, GFP_KERNEL_ACCOUNT) < 0)
goto error;
validate_creds(new);
return new;
@@ -715,7 +715,7 @@ struct cred *prepare_kernel_cred(struct task_struct *daemon)
#ifdef CONFIG_SECURITY
new->security = NULL;
#endif
- if (security_prepare_creds(new, old, GFP_KERNEL) < 0)
+ if (security_prepare_creds(new, old, GFP_KERNEL_ACCOUNT) < 0)
goto error;
put_cred(old);
diff --git a/kernel/exit.c b/kernel/exit.c
index bcbd59888e67..2833ffb0c211 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -517,10 +517,6 @@ static struct task_struct *find_child_reaper(struct task_struct *father,
}
write_unlock_irq(&tasklist_lock);
- if (unlikely(pid_ns == &init_pid_ns)) {
- panic("Attempted to kill init! exitcode=0x%08x\n",
- father->signal->group_exit_code ?: father->exit_code);
- }
list_for_each_entry_safe(p, n, dead, ptrace_entry) {
list_del_init(&p->ptrace_entry);
@@ -766,6 +762,14 @@ void __noreturn do_exit(long code)
acct_update_integrals(tsk);
group_dead = atomic_dec_and_test(&tsk->signal->live);
if (group_dead) {
+ /*
+ * If the last thread of global init has exited, panic
+ * immediately to get a useable coredump.
+ */
+ if (unlikely(is_global_init(tsk)))
+ panic("Attempted to kill init! exitcode=0x%08x\n",
+ tsk->signal->group_exit_code ?: (int)code);
+
#ifdef CONFIG_POSIX_TIMERS
hrtimer_cancel(&tsk->signal->real_timer);
exit_itimers(tsk->signal);
diff --git a/kernel/irq/cpuhotplug.c b/kernel/irq/cpuhotplug.c
index 6c7ca2e983a5..02236b13b359 100644
--- a/kernel/irq/cpuhotplug.c
+++ b/kernel/irq/cpuhotplug.c
@@ -12,6 +12,7 @@
#include <linux/interrupt.h>
#include <linux/ratelimit.h>
#include <linux/irq.h>
+#include <linux/sched/isolation.h>
#include "internals.h"
@@ -171,6 +172,20 @@ void irq_migrate_all_off_this_cpu(void)
}
}
+static bool hk_should_isolate(struct irq_data *data, unsigned int cpu)
+{
+ const struct cpumask *hk_mask;
+
+ if (!housekeeping_enabled(HK_FLAG_MANAGED_IRQ))
+ return false;
+
+ hk_mask = housekeeping_cpumask(HK_FLAG_MANAGED_IRQ);
+ if (cpumask_subset(irq_data_get_effective_affinity_mask(data), hk_mask))
+ return false;
+
+ return cpumask_test_cpu(cpu, hk_mask);
+}
+
static void irq_restore_affinity_of_irq(struct irq_desc *desc, unsigned int cpu)
{
struct irq_data *data = irq_desc_get_irq_data(desc);
@@ -188,9 +203,11 @@ static void irq_restore_affinity_of_irq(struct irq_desc *desc, unsigned int cpu)
/*
* If the interrupt can only be directed to a single target
* CPU then it is already assigned to a CPU in the affinity
- * mask. No point in trying to move it around.
+ * mask. No point in trying to move it around unless the
+ * isolation mechanism requests to move it to an upcoming
+ * housekeeping CPU.
*/
- if (!irqd_is_single_target(data))
+ if (!irqd_is_single_target(data) || hk_should_isolate(data, cpu))
irq_set_affinity_locked(data, affinity, false);
}
diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c
index 5b8fdd659e54..98a5f10d1900 100644
--- a/kernel/irq/irqdesc.c
+++ b/kernel/irq/irqdesc.c
@@ -891,6 +891,7 @@ __irq_get_desc_lock(unsigned int irq, unsigned long *flags, bool bus,
}
void __irq_put_desc_unlock(struct irq_desc *desc, unsigned long flags, bool bus)
+ __releases(&desc->lock)
{
raw_spin_unlock_irqrestore(&desc->lock, flags);
if (bus)
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 1753486b440c..818b2802d3e7 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -18,6 +18,7 @@
#include <linux/sched.h>
#include <linux/sched/rt.h>
#include <linux/sched/task.h>
+#include <linux/sched/isolation.h>
#include <uapi/linux/sched/types.h>
#include <linux/task_work.h>
@@ -217,7 +218,45 @@ int irq_do_set_affinity(struct irq_data *data, const struct cpumask *mask,
if (!chip || !chip->irq_set_affinity)
return -EINVAL;
- ret = chip->irq_set_affinity(data, mask, force);
+ /*
+ * If this is a managed interrupt and housekeeping is enabled on
+ * it check whether the requested affinity mask intersects with
+ * a housekeeping CPU. If so, then remove the isolated CPUs from
+ * the mask and just keep the housekeeping CPU(s). This prevents
+ * the affinity setter from routing the interrupt to an isolated
+ * CPU to avoid that I/O submitted from a housekeeping CPU causes
+ * interrupts on an isolated one.
+ *
+ * If the masks do not intersect or include online CPU(s) then
+ * keep the requested mask. The isolated target CPUs are only
+ * receiving interrupts when the I/O operation was submitted
+ * directly from them.
+ *
+ * If all housekeeping CPUs in the affinity mask are offline, the
+ * interrupt will be migrated by the CPU hotplug code once a
+ * housekeeping CPU which belongs to the affinity mask comes
+ * online.
+ */
+ if (irqd_affinity_is_managed(data) &&
+ housekeeping_enabled(HK_FLAG_MANAGED_IRQ)) {
+ const struct cpumask *hk_mask, *prog_mask;
+
+ static DEFINE_RAW_SPINLOCK(tmp_mask_lock);
+ static struct cpumask tmp_mask;
+
+ hk_mask = housekeeping_cpumask(HK_FLAG_MANAGED_IRQ);
+
+ raw_spin_lock(&tmp_mask_lock);
+ cpumask_and(&tmp_mask, mask, hk_mask);
+ if (!cpumask_intersects(&tmp_mask, cpu_online_mask))
+ prog_mask = mask;
+ else
+ prog_mask = &tmp_mask;
+ ret = chip->irq_set_affinity(data, prog_mask, force);
+ raw_spin_unlock(&tmp_mask_lock);
+ } else {
+ ret = chip->irq_set_affinity(data, mask, force);
+ }
switch (ret) {
case IRQ_SET_MASK_OK:
case IRQ_SET_MASK_OK_DONE:
@@ -1500,8 +1539,8 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
* has. The type flags are unreliable as the
* underlying chip implementation can override them.
*/
- pr_err("Threaded irq requested with handler=NULL and !ONESHOT for irq %d\n",
- irq);
+ pr_err("Threaded irq requested with handler=NULL and !ONESHOT for %s (irq %d)\n",
+ new->name, irq);
ret = -EINVAL;
goto out_unlock;
}
diff --git a/kernel/irq/spurious.c b/kernel/irq/spurious.c
index 2ed97a7c9b2a..f865e5f4d382 100644
--- a/kernel/irq/spurious.c
+++ b/kernel/irq/spurious.c
@@ -34,6 +34,7 @@ static atomic_t irq_poll_active;
* true and let the handler run.
*/
bool irq_wait_for_poll(struct irq_desc *desc)
+ __must_hold(&desc->lock)
{
if (WARN_ONCE(irq_poll_cpu == smp_processor_id(),
"irq poll in progress on cpu %d for irq %d\n",
diff --git a/kernel/sched/isolation.c b/kernel/sched/isolation.c
index 9fcb2a695a41..008d6ac2342b 100644
--- a/kernel/sched/isolation.c
+++ b/kernel/sched/isolation.c
@@ -163,6 +163,12 @@ static int __init housekeeping_isolcpus_setup(char *str)
continue;
}
+ if (!strncmp(str, "managed_irq,", 12)) {
+ str += 12;
+ flags |= HK_FLAG_MANAGED_IRQ;
+ continue;
+ }
+
pr_warn("isolcpus: Error, unknown flag\n");
return 0;
}
diff --git a/kernel/seccomp.c b/kernel/seccomp.c
index 12d2227e5786..b6ea3dcb57bf 100644
--- a/kernel/seccomp.c
+++ b/kernel/seccomp.c
@@ -1026,6 +1026,13 @@ static long seccomp_notify_recv(struct seccomp_filter *filter,
struct seccomp_notif unotif;
ssize_t ret;
+ /* Verify that we're not given garbage to keep struct extensible. */
+ ret = check_zeroed_user(buf, sizeof(unotif));
+ if (ret < 0)
+ return ret;
+ if (!ret)
+ return -EINVAL;
+
memset(&unotif, 0, sizeof(unotif));
ret = down_interruptible(&filter->notif->request);
diff --git a/kernel/taskstats.c b/kernel/taskstats.c
index 13a0f2e6ebc2..e2ac0e37c4ae 100644
--- a/kernel/taskstats.c
+++ b/kernel/taskstats.c
@@ -554,25 +554,33 @@ static int taskstats_user_cmd(struct sk_buff *skb, struct genl_info *info)
static struct taskstats *taskstats_tgid_alloc(struct task_struct *tsk)
{
struct signal_struct *sig = tsk->signal;
- struct taskstats *stats;
+ struct taskstats *stats_new, *stats;
- if (sig->stats || thread_group_empty(tsk))
- goto ret;
+ /* Pairs with smp_store_release() below. */
+ stats = smp_load_acquire(&sig->stats);
+ if (stats || thread_group_empty(tsk))
+ return stats;
/* No problem if kmem_cache_zalloc() fails */
- stats = kmem_cache_zalloc(taskstats_cache, GFP_KERNEL);
+ stats_new = kmem_cache_zalloc(taskstats_cache, GFP_KERNEL);
spin_lock_irq(&tsk->sighand->siglock);
- if (!sig->stats) {
- sig->stats = stats;
- stats = NULL;
+ stats = sig->stats;
+ if (!stats) {
+ /*
+ * Pairs with smp_store_release() above and order the
+ * kmem_cache_zalloc().
+ */
+ smp_store_release(&sig->stats, stats_new);
+ stats = stats_new;
+ stats_new = NULL;
}
spin_unlock_irq(&tsk->sighand->siglock);
- if (stats)
- kmem_cache_free(taskstats_cache, stats);
-ret:
- return sig->stats;
+ if (stats_new)
+ kmem_cache_free(taskstats_cache, stats_new);
+
+ return stats;
}
/* Send pid data out on exit */
diff --git a/kernel/time/posix-clock.c b/kernel/time/posix-clock.c
index ec960bb939fd..200fb2d3be99 100644
--- a/kernel/time/posix-clock.c
+++ b/kernel/time/posix-clock.c
@@ -14,8 +14,6 @@
#include "posix-timers.h"
-static void delete_clock(struct kref *kref);
-
/*
* Returns NULL if the posix_clock instance attached to 'fp' is old and stale.
*/
@@ -125,7 +123,7 @@ static int posix_clock_open(struct inode *inode, struct file *fp)
err = 0;
if (!err) {
- kref_get(&clk->kref);
+ get_device(clk->dev);
fp->private_data = clk;
}
out:
@@ -141,7 +139,7 @@ static int posix_clock_release(struct inode *inode, struct file *fp)
if (clk->ops.release)
err = clk->ops.release(clk);
- kref_put(&clk->kref, delete_clock);
+ put_device(clk->dev);
fp->private_data = NULL;
@@ -161,38 +159,35 @@ static const struct file_operations posix_clock_file_operations = {
#endif
};
-int posix_clock_register(struct posix_clock *clk, dev_t devid)
+int posix_clock_register(struct posix_clock *clk, struct device *dev)
{
int err;
- kref_init(&clk->kref);
init_rwsem(&clk->rwsem);
cdev_init(&clk->cdev, &posix_clock_file_operations);
+ err = cdev_device_add(&clk->cdev, dev);
+ if (err) {
+ pr_err("%s unable to add device %d:%d\n",
+ dev_name(dev), MAJOR(dev->devt), MINOR(dev->devt));
+ return err;
+ }
clk->cdev.owner = clk->ops.owner;
- err = cdev_add(&clk->cdev, devid, 1);
+ clk->dev = dev;
- return err;
+ return 0;
}
EXPORT_SYMBOL_GPL(posix_clock_register);
-static void delete_clock(struct kref *kref)
-{
- struct posix_clock *clk = container_of(kref, struct posix_clock, kref);
-
- if (clk->release)
- clk->release(clk);
-}
-
void posix_clock_unregister(struct posix_clock *clk)
{
- cdev_del(&clk->cdev);
+ cdev_device_del(&clk->cdev, clk->dev);
down_write(&clk->rwsem);
clk->zombie = true;
up_write(&clk->rwsem);
- kref_put(&clk->kref, delete_clock);
+ put_device(clk->dev);
}
EXPORT_SYMBOL_GPL(posix_clock_unregister);
generated by cgit v1.2.3 (git 2.25.1) at 2024-09-07 01:16:59 +0000