Revision 9cc02ede696272c5271a401e4f27c262359bc2f6 authored by Duoming Zhou on 29 June 2022, 00:26:40 UTC, committed by Paolo Abeni on 30 June 2022, 09:07:30 UTC
There are UAF bugs in rose_heartbeat_expiry(), rose_timer_expiry() and rose_idletimer_expiry(). The root cause is that del_timer() could not stop the timer handler that is running and the refcount of sock is not managed properly. One of the UAF bugs is shown below: (thread 1) | (thread 2) | rose_bind | rose_connect | rose_start_heartbeat rose_release | (wait a time) case ROSE_STATE_0 | rose_destroy_socket | rose_heartbeat_expiry rose_stop_heartbeat | sock_put(sk) | ... sock_put(sk) // FREE | | bh_lock_sock(sk) // USE The sock is deallocated by sock_put() in rose_release() and then used by bh_lock_sock() in rose_heartbeat_expiry(). Although rose_destroy_socket() calls rose_stop_heartbeat(), it could not stop the timer that is running. The KASAN report triggered by POC is shown below: BUG: KASAN: use-after-free in _raw_spin_lock+0x5a/0x110 Write of size 4 at addr ffff88800ae59098 by task swapper/3/0 ... Call Trace: <IRQ> dump_stack_lvl+0xbf/0xee print_address_description+0x7b/0x440 print_report+0x101/0x230 ? irq_work_single+0xbb/0x140 ? _raw_spin_lock+0x5a/0x110 kasan_report+0xed/0x120 ? _raw_spin_lock+0x5a/0x110 kasan_check_range+0x2bd/0x2e0 _raw_spin_lock+0x5a/0x110 rose_heartbeat_expiry+0x39/0x370 ? rose_start_heartbeat+0xb0/0xb0 call_timer_fn+0x2d/0x1c0 ? rose_start_heartbeat+0xb0/0xb0 expire_timers+0x1f3/0x320 __run_timers+0x3ff/0x4d0 run_timer_softirq+0x41/0x80 __do_softirq+0x233/0x544 irq_exit_rcu+0x41/0xa0 sysvec_apic_timer_interrupt+0x8c/0xb0 </IRQ> <TASK> asm_sysvec_apic_timer_interrupt+0x1b/0x20 RIP: 0010:default_idle+0xb/0x10 RSP: 0018:ffffc9000012fea0 EFLAGS: 00000202 RAX: 000000000000bcae RBX: ffff888006660f00 RCX: 000000000000bcae RDX: 0000000000000001 RSI: ffffffff843a11c0 RDI: ffffffff843a1180 RBP: dffffc0000000000 R08: dffffc0000000000 R09: ffffed100da36d46 R10: dfffe9100da36d47 R11: ffffffff83cf0950 R12: 0000000000000000 R13: 1ffff11000ccc1e0 R14: ffffffff8542af28 R15: dffffc0000000000 ... Allocated by task 146: __kasan_kmalloc+0xc4/0xf0 sk_prot_alloc+0xdd/0x1a0 sk_alloc+0x2d/0x4e0 rose_create+0x7b/0x330 __sock_create+0x2dd/0x640 __sys_socket+0xc7/0x270 __x64_sys_socket+0x71/0x80 do_syscall_64+0x43/0x90 entry_SYSCALL_64_after_hwframe+0x46/0xb0 Freed by task 152: kasan_set_track+0x4c/0x70 kasan_set_free_info+0x1f/0x40 ____kasan_slab_free+0x124/0x190 kfree+0xd3/0x270 __sk_destruct+0x314/0x460 rose_release+0x2fa/0x3b0 sock_close+0xcb/0x230 __fput+0x2d9/0x650 task_work_run+0xd6/0x160 exit_to_user_mode_loop+0xc7/0xd0 exit_to_user_mode_prepare+0x4e/0x80 syscall_exit_to_user_mode+0x20/0x40 do_syscall_64+0x4f/0x90 entry_SYSCALL_64_after_hwframe+0x46/0xb0 This patch adds refcount of sock when we use functions such as rose_start_heartbeat() and so on to start timer, and decreases the refcount of sock when timer is finished or deleted by functions such as rose_stop_heartbeat() and so on. As a result, the UAF bugs could be mitigated. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Duoming Zhou <duoming@zju.edu.cn> Tested-by: Duoming Zhou <duoming@zju.edu.cn> Link: https://lore.kernel.org/r/20220629002640.5693-1-duoming@zju.edu.cn Signed-off-by: Paolo Abeni <pabeni@redhat.com>
1 parent f8ebb3a
cpu_rmap.c
// SPDX-License-Identifier: GPL-2.0-only
/*
* cpu_rmap.c: CPU affinity reverse-map support
* Copyright 2011 Solarflare Communications Inc.
*/
#include <linux/cpu_rmap.h>
#include <linux/interrupt.h>
#include <linux/export.h>
/*
* These functions maintain a mapping from CPUs to some ordered set of
* objects with CPU affinities. This can be seen as a reverse-map of
* CPU affinity. However, we do not assume that the object affinities
* cover all CPUs in the system. For those CPUs not directly covered
* by object affinities, we attempt to find a nearest object based on
* CPU topology.
*/
/**
* alloc_cpu_rmap - allocate CPU affinity reverse-map
* @size: Number of objects to be mapped
* @flags: Allocation flags e.g. %GFP_KERNEL
*/
struct cpu_rmap *alloc_cpu_rmap(unsigned int size, gfp_t flags)
{
struct cpu_rmap *rmap;
unsigned int cpu;
size_t obj_offset;
/* This is a silly number of objects, and we use u16 indices. */
if (size > 0xffff)
return NULL;
/* Offset of object pointer array from base structure */
obj_offset = ALIGN(offsetof(struct cpu_rmap, near[nr_cpu_ids]),
sizeof(void *));
rmap = kzalloc(obj_offset + size * sizeof(rmap->obj[0]), flags);
if (!rmap)
return NULL;
kref_init(&rmap->refcount);
rmap->obj = (void **)((char *)rmap + obj_offset);
/* Initially assign CPUs to objects on a rota, since we have
* no idea where the objects are. Use infinite distance, so
* any object with known distance is preferable. Include the
* CPUs that are not present/online, since we definitely want
* any newly-hotplugged CPUs to have some object assigned.
*/
for_each_possible_cpu(cpu) {
rmap->near[cpu].index = cpu % size;
rmap->near[cpu].dist = CPU_RMAP_DIST_INF;
}
rmap->size = size;
return rmap;
}
EXPORT_SYMBOL(alloc_cpu_rmap);
/**
* cpu_rmap_release - internal reclaiming helper called from kref_put
* @ref: kref to struct cpu_rmap
*/
static void cpu_rmap_release(struct kref *ref)
{
struct cpu_rmap *rmap = container_of(ref, struct cpu_rmap, refcount);
kfree(rmap);
}
/**
* cpu_rmap_get - internal helper to get new ref on a cpu_rmap
* @rmap: reverse-map allocated with alloc_cpu_rmap()
*/
static inline void cpu_rmap_get(struct cpu_rmap *rmap)
{
kref_get(&rmap->refcount);
}
/**
* cpu_rmap_put - release ref on a cpu_rmap
* @rmap: reverse-map allocated with alloc_cpu_rmap()
*/
int cpu_rmap_put(struct cpu_rmap *rmap)
{
return kref_put(&rmap->refcount, cpu_rmap_release);
}
EXPORT_SYMBOL(cpu_rmap_put);
/* Reevaluate nearest object for given CPU, comparing with the given
* neighbours at the given distance.
*/
static bool cpu_rmap_copy_neigh(struct cpu_rmap *rmap, unsigned int cpu,
const struct cpumask *mask, u16 dist)
{
int neigh;
for_each_cpu(neigh, mask) {
if (rmap->near[cpu].dist > dist &&
rmap->near[neigh].dist <= dist) {
rmap->near[cpu].index = rmap->near[neigh].index;
rmap->near[cpu].dist = dist;
return true;
}
}
return false;
}
#ifdef DEBUG
static void debug_print_rmap(const struct cpu_rmap *rmap, const char *prefix)
{
unsigned index;
unsigned int cpu;
pr_info("cpu_rmap %p, %s:\n", rmap, prefix);
for_each_possible_cpu(cpu) {
index = rmap->near[cpu].index;
pr_info("cpu %d -> obj %u (distance %u)\n",
cpu, index, rmap->near[cpu].dist);
}
}
#else
static inline void
debug_print_rmap(const struct cpu_rmap *rmap, const char *prefix)
{
}
#endif
/**
* cpu_rmap_add - add object to a rmap
* @rmap: CPU rmap allocated with alloc_cpu_rmap()
* @obj: Object to add to rmap
*
* Return index of object.
*/
int cpu_rmap_add(struct cpu_rmap *rmap, void *obj)
{
u16 index;
BUG_ON(rmap->used >= rmap->size);
index = rmap->used++;
rmap->obj[index] = obj;
return index;
}
EXPORT_SYMBOL(cpu_rmap_add);
/**
* cpu_rmap_update - update CPU rmap following a change of object affinity
* @rmap: CPU rmap to update
* @index: Index of object whose affinity changed
* @affinity: New CPU affinity of object
*/
int cpu_rmap_update(struct cpu_rmap *rmap, u16 index,
const struct cpumask *affinity)
{
cpumask_var_t update_mask;
unsigned int cpu;
if (unlikely(!zalloc_cpumask_var(&update_mask, GFP_KERNEL)))
return -ENOMEM;
/* Invalidate distance for all CPUs for which this used to be
* the nearest object. Mark those CPUs for update.
*/
for_each_online_cpu(cpu) {
if (rmap->near[cpu].index == index) {
rmap->near[cpu].dist = CPU_RMAP_DIST_INF;
cpumask_set_cpu(cpu, update_mask);
}
}
debug_print_rmap(rmap, "after invalidating old distances");
/* Set distance to 0 for all CPUs in the new affinity mask.
* Mark all CPUs within their NUMA nodes for update.
*/
for_each_cpu(cpu, affinity) {
rmap->near[cpu].index = index;
rmap->near[cpu].dist = 0;
cpumask_or(update_mask, update_mask,
cpumask_of_node(cpu_to_node(cpu)));
}
debug_print_rmap(rmap, "after updating neighbours");
/* Update distances based on topology */
for_each_cpu(cpu, update_mask) {
if (cpu_rmap_copy_neigh(rmap, cpu,
topology_sibling_cpumask(cpu), 1))
continue;
if (cpu_rmap_copy_neigh(rmap, cpu,
topology_core_cpumask(cpu), 2))
continue;
if (cpu_rmap_copy_neigh(rmap, cpu,
cpumask_of_node(cpu_to_node(cpu)), 3))
continue;
/* We could continue into NUMA node distances, but for now
* we give up.
*/
}
debug_print_rmap(rmap, "after copying neighbours");
free_cpumask_var(update_mask);
return 0;
}
EXPORT_SYMBOL(cpu_rmap_update);
/* Glue between IRQ affinity notifiers and CPU rmaps */
struct irq_glue {
struct irq_affinity_notify notify;
struct cpu_rmap *rmap;
u16 index;
};
/**
* free_irq_cpu_rmap - free a CPU affinity reverse-map used for IRQs
* @rmap: Reverse-map allocated with alloc_irq_cpu_map(), or %NULL
*
* Must be called in process context, before freeing the IRQs.
*/
void free_irq_cpu_rmap(struct cpu_rmap *rmap)
{
struct irq_glue *glue;
u16 index;
if (!rmap)
return;
for (index = 0; index < rmap->used; index++) {
glue = rmap->obj[index];
irq_set_affinity_notifier(glue->notify.irq, NULL);
}
cpu_rmap_put(rmap);
}
EXPORT_SYMBOL(free_irq_cpu_rmap);
/**
* irq_cpu_rmap_notify - callback for IRQ subsystem when IRQ affinity updated
* @notify: struct irq_affinity_notify passed by irq/manage.c
* @mask: cpu mask for new SMP affinity
*
* This is executed in workqueue context.
*/
static void
irq_cpu_rmap_notify(struct irq_affinity_notify *notify, const cpumask_t *mask)
{
struct irq_glue *glue =
container_of(notify, struct irq_glue, notify);
int rc;
rc = cpu_rmap_update(glue->rmap, glue->index, mask);
if (rc)
pr_warn("irq_cpu_rmap_notify: update failed: %d\n", rc);
}
/**
* irq_cpu_rmap_release - reclaiming callback for IRQ subsystem
* @ref: kref to struct irq_affinity_notify passed by irq/manage.c
*/
static void irq_cpu_rmap_release(struct kref *ref)
{
struct irq_glue *glue =
container_of(ref, struct irq_glue, notify.kref);
cpu_rmap_put(glue->rmap);
kfree(glue);
}
/**
* irq_cpu_rmap_add - add an IRQ to a CPU affinity reverse-map
* @rmap: The reverse-map
* @irq: The IRQ number
*
* This adds an IRQ affinity notifier that will update the reverse-map
* automatically.
*
* Must be called in process context, after the IRQ is allocated but
* before it is bound with request_irq().
*/
int irq_cpu_rmap_add(struct cpu_rmap *rmap, int irq)
{
struct irq_glue *glue = kzalloc(sizeof(*glue), GFP_KERNEL);
int rc;
if (!glue)
return -ENOMEM;
glue->notify.notify = irq_cpu_rmap_notify;
glue->notify.release = irq_cpu_rmap_release;
glue->rmap = rmap;
cpu_rmap_get(rmap);
glue->index = cpu_rmap_add(rmap, glue);
rc = irq_set_affinity_notifier(irq, &glue->notify);
if (rc) {
cpu_rmap_put(glue->rmap);
kfree(glue);
}
return rc;
}
EXPORT_SYMBOL(irq_cpu_rmap_add);
Computing file changes ...