summaryrefslogtreecommitdiff
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/Makefile1
-rw-r--r--kernel/auditsc.c13
-rw-r--r--kernel/bpf/arraymap.c2
-rw-r--r--kernel/bpf/btf.c60
-rw-r--r--kernel/bpf/cgroup.c54
-rw-r--r--kernel/bpf/core.c39
-rw-r--r--kernel/bpf/cpumap.c15
-rw-r--r--kernel/bpf/devmap.c33
-rw-r--r--kernel/bpf/hashtab.c16
-rw-r--r--kernel/bpf/sockmap.c306
-rw-r--r--kernel/bpf/syscall.c115
-rw-r--r--kernel/bpf/verifier.c11
-rw-r--r--kernel/cpu.c2
-rw-r--r--kernel/dma/Kconfig50
-rw-r--r--kernel/dma/Makefile11
-rw-r--r--kernel/dma/coherent.c434
-rw-r--r--kernel/dma/contiguous.c278
-rw-r--r--kernel/dma/debug.c1773
-rw-r--r--kernel/dma/direct.c204
-rw-r--r--kernel/dma/mapping.c345
-rw-r--r--kernel/dma/noncoherent.c102
-rw-r--r--kernel/dma/swiotlb.c1088
-rw-r--r--kernel/dma/virt.c59
-rw-r--r--kernel/events/core.c12
-rw-r--r--kernel/events/ring_buffer.c6
-rw-r--r--kernel/fork.c33
-rw-r--r--kernel/irq/debugfs.c1
-rw-r--r--kernel/irq/manage.c9
-rw-r--r--kernel/kthread.c38
-rw-r--r--kernel/locking/lockdep.c12
-rw-r--r--kernel/locking/rtmutex.c29
-rw-r--r--kernel/locking/rwsem.c1
-rw-r--r--kernel/memremap.c22
-rw-r--r--kernel/rseq.c48
-rw-r--r--kernel/sched/core.c67
-rw-r--r--kernel/sched/cpufreq_schedutil.c2
-rw-r--r--kernel/sched/deadline.c19
-rw-r--r--kernel/sched/fair.c45
-rw-r--r--kernel/sched/rt.c18
-rw-r--r--kernel/sched/sched.h11
-rw-r--r--kernel/sched/topology.c2
-rw-r--r--kernel/softirq.c20
-rw-r--r--kernel/stop_machine.c14
-rw-r--r--kernel/time/hrtimer.c2
-rw-r--r--kernel/time/posix-cpu-timers.c2
-rw-r--r--kernel/time/tick-common.c3
-rw-r--r--kernel/time/tick-sched.c2
-rw-r--r--kernel/time/time.c6
-rw-r--r--kernel/trace/ftrace.c13
-rw-r--r--kernel/trace/ring_buffer.c16
-rw-r--r--kernel/trace/trace.c25
-rw-r--r--kernel/trace/trace.h4
-rw-r--r--kernel/trace/trace_events_filter.c15
-rw-r--r--kernel/trace/trace_events_hist.c2
-rw-r--r--kernel/trace/trace_events_trigger.c18
-rw-r--r--kernel/trace/trace_functions_graph.c5
-rw-r--r--kernel/trace/trace_kprobe.c21
-rw-r--r--kernel/trace/trace_output.c5
58 files changed, 5155 insertions, 404 deletions
diff --git a/kernel/Makefile b/kernel/Makefile
index d2001624fe7a..04bc07c2b42a 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -41,6 +41,7 @@ obj-y += printk/
obj-y += irq/
obj-y += rcu/
obj-y += livepatch/
+obj-y += dma/
obj-$(CONFIG_CHECKPOINT_RESTORE) += kcmp.o
obj-$(CONFIG_FREEZER) += freezer.o
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index ceb1c4596c51..80d672a11088 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -1279,8 +1279,12 @@ static void show_special(struct audit_context *context, int *call_panic)
break;
case AUDIT_KERN_MODULE:
audit_log_format(ab, "name=");
- audit_log_untrustedstring(ab, context->module.name);
- kfree(context->module.name);
+ if (context->module.name) {
+ audit_log_untrustedstring(ab, context->module.name);
+ kfree(context->module.name);
+ } else
+ audit_log_format(ab, "(null)");
+
break;
}
audit_log_end(ab);
@@ -2411,8 +2415,9 @@ void __audit_log_kern_module(char *name)
{
struct audit_context *context = audit_context();
- context->module.name = kmalloc(strlen(name) + 1, GFP_KERNEL);
- strcpy(context->module.name, name);
+ context->module.name = kstrdup(name, GFP_KERNEL);
+ if (!context->module.name)
+ audit_log_lost("out of memory in __audit_log_kern_module");
context->type = AUDIT_KERN_MODULE;
}
diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index 544e58f5f642..2aa55d030c77 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -378,7 +378,7 @@ static int array_map_check_btf(const struct bpf_map *map, const struct btf *btf,
return -EINVAL;
value_type = btf_type_id_size(btf, &btf_value_id, &value_size);
- if (!value_type || value_size > map->value_size)
+ if (!value_type || value_size != map->value_size)
return -EINVAL;
return 0;
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 2d49d18b793a..2590700237c1 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -450,7 +450,7 @@ static const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id)
*/
static bool btf_type_int_is_regular(const struct btf_type *t)
{
- u16 nr_bits, nr_bytes;
+ u8 nr_bits, nr_bytes;
u32 int_data;
int_data = btf_type_int(t);
@@ -991,38 +991,38 @@ static void btf_int_bits_seq_show(const struct btf *btf,
void *data, u8 bits_offset,
struct seq_file *m)
{
+ u16 left_shift_bits, right_shift_bits;
u32 int_data = btf_type_int(t);
- u16 nr_bits = BTF_INT_BITS(int_data);
- u16 total_bits_offset;
- u16 nr_copy_bytes;
- u16 nr_copy_bits;
- u8 nr_upper_bits;
- union {
- u64 u64_num;
- u8 u8_nums[8];
- } print_num;
+ u8 nr_bits = BTF_INT_BITS(int_data);
+ u8 total_bits_offset;
+ u8 nr_copy_bytes;
+ u8 nr_copy_bits;
+ u64 print_num;
+ /*
+ * bits_offset is at most 7.
+ * BTF_INT_OFFSET() cannot exceed 64 bits.
+ */
total_bits_offset = bits_offset + BTF_INT_OFFSET(int_data);
data += BITS_ROUNDDOWN_BYTES(total_bits_offset);
bits_offset = BITS_PER_BYTE_MASKED(total_bits_offset);
nr_copy_bits = nr_bits + bits_offset;
nr_copy_bytes = BITS_ROUNDUP_BYTES(nr_copy_bits);
- print_num.u64_num = 0;
- memcpy(&print_num.u64_num, data, nr_copy_bytes);
-
- /* Ditch the higher order bits */
- nr_upper_bits = BITS_PER_BYTE_MASKED(nr_copy_bits);
- if (nr_upper_bits) {
- /* We need to mask out some bits of the upper byte. */
- u8 mask = (1 << nr_upper_bits) - 1;
+ print_num = 0;
+ memcpy(&print_num, data, nr_copy_bytes);
- print_num.u8_nums[nr_copy_bytes - 1] &= mask;
- }
+#ifdef __BIG_ENDIAN_BITFIELD
+ left_shift_bits = bits_offset;
+#else
+ left_shift_bits = BITS_PER_U64 - nr_copy_bits;
+#endif
+ right_shift_bits = BITS_PER_U64 - nr_bits;
- print_num.u64_num >>= bits_offset;
+ print_num <<= left_shift_bits;
+ print_num >>= right_shift_bits;
- seq_printf(m, "0x%llx", print_num.u64_num);
+ seq_printf(m, "0x%llx", print_num);
}
static void btf_int_seq_show(const struct btf *btf, const struct btf_type *t,
@@ -1032,7 +1032,7 @@ static void btf_int_seq_show(const struct btf *btf, const struct btf_type *t,
u32 int_data = btf_type_int(t);
u8 encoding = BTF_INT_ENCODING(int_data);
bool sign = encoding & BTF_INT_SIGNED;
- u32 nr_bits = BTF_INT_BITS(int_data);
+ u8 nr_bits = BTF_INT_BITS(int_data);
if (bits_offset || BTF_INT_OFFSET(int_data) ||
BITS_PER_BYTE_MASKED(nr_bits)) {
@@ -1519,9 +1519,9 @@ static s32 btf_struct_check_meta(struct btf_verifier_env *env,
{
bool is_union = BTF_INFO_KIND(t->info) == BTF_KIND_UNION;
const struct btf_member *member;
+ u32 meta_needed, last_offset;
struct btf *btf = env->btf;
u32 struct_size = t->size;
- u32 meta_needed;
u16 i;
meta_needed = btf_type_vlen(t) * sizeof(*member);
@@ -1534,6 +1534,7 @@ static s32 btf_struct_check_meta(struct btf_verifier_env *env,
btf_verifier_log_type(env, t, NULL);
+ last_offset = 0;
for_each_member(i, t, member) {
if (!btf_name_offset_valid(btf, member->name_off)) {
btf_verifier_log_member(env, t, member,
@@ -1555,6 +1556,16 @@ static s32 btf_struct_check_meta(struct btf_verifier_env *env,
return -EINVAL;
}
+ /*
+ * ">" instead of ">=" because the last member could be
+ * "char a[0];"
+ */
+ if (last_offset > member->offset) {
+ btf_verifier_log_member(env, t, member,
+ "Invalid member bits_offset");
+ return -EINVAL;
+ }
+
if (BITS_ROUNDUP_BYTES(member->offset) > struct_size) {
btf_verifier_log_member(env, t, member,
"Memmber bits_offset exceeds its struct size");
@@ -1562,6 +1573,7 @@ static s32 btf_struct_check_meta(struct btf_verifier_env *env,
}
btf_verifier_log_member(env, t, member, NULL);
+ last_offset = member->offset;
}
return meta_needed;
diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
index f7c00bd6f8e4..3d83ee7df381 100644
--- a/kernel/bpf/cgroup.c
+++ b/kernel/bpf/cgroup.c
@@ -428,6 +428,60 @@ int __cgroup_bpf_query(struct cgroup *cgrp, const union bpf_attr *attr,
return ret;
}
+int cgroup_bpf_prog_attach(const union bpf_attr *attr,
+ enum bpf_prog_type ptype, struct bpf_prog *prog)
+{
+ struct cgroup *cgrp;
+ int ret;
+
+ cgrp = cgroup_get_from_fd(attr->target_fd);
+ if (IS_ERR(cgrp))
+ return PTR_ERR(cgrp);
+
+ ret = cgroup_bpf_attach(cgrp, prog, attr->attach_type,
+ attr->attach_flags);
+ cgroup_put(cgrp);
+ return ret;
+}
+
+int cgroup_bpf_prog_detach(const union bpf_attr *attr, enum bpf_prog_type ptype)
+{
+ struct bpf_prog *prog;
+ struct cgroup *cgrp;
+ int ret;
+
+ cgrp = cgroup_get_from_fd(attr->target_fd);
+ if (IS_ERR(cgrp))
+ return PTR_ERR(cgrp);
+
+ prog = bpf_prog_get_type(attr->attach_bpf_fd, ptype);
+ if (IS_ERR(prog))
+ prog = NULL;
+
+ ret = cgroup_bpf_detach(cgrp, prog, attr->attach_type, 0);
+ if (prog)
+ bpf_prog_put(prog);
+
+ cgroup_put(cgrp);
+ return ret;
+}
+
+int cgroup_bpf_prog_query(const union bpf_attr *attr,
+ union bpf_attr __user *uattr)
+{
+ struct cgroup *cgrp;
+ int ret;
+
+ cgrp = cgroup_get_from_fd(attr->query.target_fd);
+ if (IS_ERR(cgrp))
+ return PTR_ERR(cgrp);
+
+ ret = cgroup_bpf_query(cgrp, attr, uattr);
+
+ cgroup_put(cgrp);
+ return ret;
+}
+
/**
* __cgroup_bpf_run_filter_skb() - Run a program for packet filtering
* @sk: The socket sending or receiving traffic
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 9f1493705f40..1e5625d46414 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -350,6 +350,20 @@ struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off,
return prog_adj;
}
+void bpf_prog_kallsyms_del_subprogs(struct bpf_prog *fp)
+{
+ int i;
+
+ for (i = 0; i < fp->aux->func_cnt; i++)
+ bpf_prog_kallsyms_del(fp->aux->func[i]);
+}
+
+void bpf_prog_kallsyms_del_all(struct bpf_prog *fp)
+{
+ bpf_prog_kallsyms_del_subprogs(fp);
+ bpf_prog_kallsyms_del(fp);
+}
+
#ifdef CONFIG_BPF_JIT
/* All BPF JIT sysctl knobs here. */
int bpf_jit_enable __read_mostly = IS_BUILTIN(CONFIG_BPF_JIT_ALWAYS_ON);
@@ -1434,6 +1448,17 @@ static int bpf_check_tail_call(const struct bpf_prog *fp)
return 0;
}
+static void bpf_prog_select_func(struct bpf_prog *fp)
+{
+#ifndef CONFIG_BPF_JIT_ALWAYS_ON
+ u32 stack_depth = max_t(u32, fp->aux->stack_depth, 1);
+
+ fp->bpf_func = interpreters[(round_up(stack_depth, 32) / 32) - 1];
+#else
+ fp->bpf_func = __bpf_prog_ret0_warn;
+#endif
+}
+
/**
* bpf_prog_select_runtime - select exec runtime for BPF program
* @fp: bpf_prog populated with internal BPF program
@@ -1444,13 +1469,13 @@ static int bpf_check_tail_call(const struct bpf_prog *fp)
*/
struct bpf_prog *bpf_prog_select_runtime(struct bpf_prog *fp, int *err)
{
-#ifndef CONFIG_BPF_JIT_ALWAYS_ON
- u32 stack_depth = max_t(u32, fp->aux->stack_depth, 1);
+ /* In case of BPF to BPF calls, verifier did all the prep
+ * work with regards to JITing, etc.
+ */
+ if (fp->bpf_func)
+ goto finalize;
- fp->bpf_func = interpreters[(round_up(stack_depth, 32) / 32) - 1];
-#else
- fp->bpf_func = __bpf_prog_ret0_warn;
-#endif
+ bpf_prog_select_func(fp);
/* eBPF JITs can rewrite the program in case constant
* blinding is active. However, in case of error during
@@ -1471,6 +1496,8 @@ struct bpf_prog *bpf_prog_select_runtime(struct bpf_prog *fp, int *err)
if (*err)
return fp;
}
+
+finalize:
bpf_prog_lock_ro(fp);
/* The tail call compatibility check can only be done at
diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c
index e0918d180f08..46f5f29605d4 100644
--- a/kernel/bpf/cpumap.c
+++ b/kernel/bpf/cpumap.c
@@ -69,7 +69,7 @@ struct bpf_cpu_map {
};
static int bq_flush_to_queue(struct bpf_cpu_map_entry *rcpu,
- struct xdp_bulk_queue *bq);
+ struct xdp_bulk_queue *bq, bool in_napi_ctx);
static u64 cpu_map_bitmap_size(const union bpf_attr *attr)
{
@@ -375,7 +375,7 @@ static void __cpu_map_entry_free(struct rcu_head *rcu)
struct xdp_bulk_queue *bq = per_cpu_ptr(rcpu->bulkq, cpu);
/* No concurrent bq_enqueue can run at this point */
- bq_flush_to_queue(rcpu, bq);
+ bq_flush_to_queue(rcpu, bq, false);
}
free_percpu(rcpu->bulkq);
/* Cannot kthread_stop() here, last put free rcpu resources */
@@ -558,7 +558,7 @@ const struct bpf_map_ops cpu_map_ops = {
};
static int bq_flush_to_queue(struct bpf_cpu_map_entry *rcpu,
- struct xdp_bulk_queue *bq)
+ struct xdp_bulk_queue *bq, bool in_napi_ctx)
{
unsigned int processed = 0, drops = 0;
const int to_cpu = rcpu->cpu;
@@ -578,7 +578,10 @@ static int bq_flush_to_queue(struct bpf_cpu_map_entry *rcpu,
err = __ptr_ring_produce(q, xdpf);
if (err) {
drops++;
- xdp_return_frame_rx_napi(xdpf);
+ if (likely(in_napi_ctx))
+ xdp_return_frame_rx_napi(xdpf);
+ else
+ xdp_return_frame(xdpf);
}
processed++;
}
@@ -598,7 +601,7 @@ static int bq_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_frame *xdpf)
struct xdp_bulk_queue *bq = this_cpu_ptr(rcpu->bulkq);
if (unlikely(bq->count == CPU_MAP_BULK_SIZE))
- bq_flush_to_queue(rcpu, bq);
+ bq_flush_to_queue(rcpu, bq, true);
/* Notice, xdp_buff/page MUST be queued here, long enough for
* driver to code invoking us to finished, due to driver
@@ -661,7 +664,7 @@ void __cpu_map_flush(struct bpf_map *map)
/* Flush all frames in bulkq to real queue */
bq = this_cpu_ptr(rcpu->bulkq);
- bq_flush_to_queue(rcpu, bq);
+ bq_flush_to_queue(rcpu, bq, true);
/* If already running, costs spin_lock_irqsave + smb_mb */
wake_up_process(rcpu->kthread);
diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c
index a7cc7b3494a9..750d45edae79 100644
--- a/kernel/bpf/devmap.c
+++ b/kernel/bpf/devmap.c
@@ -217,7 +217,8 @@ void __dev_map_insert_ctx(struct bpf_map *map, u32 bit)
}
static int bq_xmit_all(struct bpf_dtab_netdev *obj,
- struct xdp_bulk_queue *bq, u32 flags)
+ struct xdp_bulk_queue *bq, u32 flags,
+ bool in_napi_ctx)
{
struct net_device *dev = obj->dev;
int sent = 0, drops = 0, err = 0;
@@ -254,7 +255,10 @@ error:
struct xdp_frame *xdpf = bq->q[i];
/* RX path under NAPI protection, can return frames faster */
- xdp_return_frame_rx_napi(xdpf);
+ if (likely(in_napi_ctx))
+ xdp_return_frame_rx_napi(xdpf);
+ else
+ xdp_return_frame(xdpf);
drops++;
}
goto out;
@@ -286,7 +290,7 @@ void __dev_map_flush(struct bpf_map *map)
__clear_bit(bit, bitmap);
bq = this_cpu_ptr(dev->bulkq);
- bq_xmit_all(dev, bq, XDP_XMIT_FLUSH);
+ bq_xmit_all(dev, bq, XDP_XMIT_FLUSH, true);
}
}
@@ -316,7 +320,7 @@ static int bq_enqueue(struct bpf_dtab_netdev *obj, struct xdp_frame *xdpf,
struct xdp_bulk_queue *bq = this_cpu_ptr(obj->bulkq);
if (unlikely(bq->count == DEV_MAP_BULK_SIZE))
- bq_xmit_all(obj, bq, 0);
+ bq_xmit_all(obj, bq, 0, true);
/* Ingress dev_rx will be the same for all xdp_frame's in
* bulk_queue, because bq stored per-CPU and must be flushed
@@ -334,10 +338,15 @@ int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp,
{
struct net_device *dev = dst->dev;
struct xdp_frame *xdpf;
+ int err;
if (!dev->netdev_ops->ndo_xdp_xmit)
return -EOPNOTSUPP;
+ err = xdp_ok_fwd_dev(dev, xdp->data_end - xdp->data);
+ if (unlikely(err))
+ return err;
+
xdpf = convert_to_xdp_frame(xdp);
if (unlikely(!xdpf))
return -EOVERFLOW;
@@ -345,6 +354,20 @@ int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp,
return bq_enqueue(dst, xdpf, dev_rx);
}
+int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb,
+ struct bpf_prog *xdp_prog)
+{
+ int err;
+
+ err = xdp_ok_fwd_dev(dst->dev, skb->len);
+ if (unlikely(err))
+ return err;
+ skb->dev = dst->dev;
+ generic_xdp_tx(skb, xdp_prog);
+
+ return 0;
+}
+
static void *dev_map_lookup_elem(struct bpf_map *map, void *key)
{
struct bpf_dtab_netdev *obj = __dev_map_lookup_elem(map, *(u32 *)key);
@@ -366,7 +389,7 @@ static void dev_map_flush_old(struct bpf_dtab_netdev *dev)
__clear_bit(dev->bit, bitmap);
bq = per_cpu_ptr(dev->bulkq, cpu);
- bq_xmit_all(dev, bq, XDP_XMIT_FLUSH);
+ bq_xmit_all(dev, bq, XDP_XMIT_FLUSH, false);
}
}
}
diff --git a/kernel/bpf/hashtab.c b/kernel/bpf/hashtab.c
index 3ca2198a6d22..513d9dfcf4ee 100644
--- a/kernel/bpf/hashtab.c
+++ b/kernel/bpf/hashtab.c
@@ -747,13 +747,15 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key,
* old element will be freed immediately.
* Otherwise return an error
*/
- atomic_dec(&htab->count);
- return ERR_PTR(-E2BIG);
+ l_new = ERR_PTR(-E2BIG);
+ goto dec_count;
}
l_new = kmalloc_node(htab->elem_size, GFP_ATOMIC | __GFP_NOWARN,
htab->map.numa_node);
- if (!l_new)
- return ERR_PTR(-ENOMEM);
+ if (!l_new) {
+ l_new = ERR_PTR(-ENOMEM);
+ goto dec_count;
+ }
}
memcpy(l_new->key, key, key_size);
@@ -766,7 +768,8 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key,
GFP_ATOMIC | __GFP_NOWARN);
if (!pptr) {
kfree(l_new);
- return ERR_PTR(-ENOMEM);
+ l_new = ERR_PTR(-ENOMEM);
+ goto dec_count;
}
}
@@ -780,6 +783,9 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key,
l_new->hash = hash;
return l_new;
+dec_count:
+ atomic_dec(&htab->count);
+ return l_new;
}
static int check_flags(struct bpf_htab *htab, struct htab_elem *l_old,
diff --git a/kernel/bpf/sockmap.c b/kernel/bpf/sockmap.c
index 52a91d816c0e..c4d75c52b4fc 100644
--- a/kernel/bpf/sockmap.c
+++ b/kernel/bpf/sockmap.c
@@ -72,6 +72,7 @@ struct bpf_htab {
u32 n_buckets;
u32 elem_size;
struct bpf_sock_progs progs;
+ struct rcu_head rcu;
};
struct htab_elem {
@@ -89,8 +90,8 @@ enum smap_psock_state {
struct smap_psock_map_entry {
struct list_head list;
struct sock **entry;
- struct htab_elem *hash_link;
- struct bpf_htab *htab;
+ struct htab_elem __rcu *hash_link;
+ struct bpf_htab __rcu *htab;
};
struct smap_psock {
@@ -120,6 +121,7 @@ struct smap_psock {
struct bpf_prog *bpf_parse;
struct bpf_prog *bpf_verdict;
struct list_head maps;
+ spinlock_t maps_lock;
/* Back reference used when sock callback trigger sockmap operations */
struct sock *sock;
@@ -140,6 +142,7 @@ static int bpf_tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
static int bpf_tcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size);
static int bpf_tcp_sendpage(struct sock *sk, struct page *page,
int offset, size_t size, int flags);
+static void bpf_tcp_close(struct sock *sk, long timeout);
static inline struct smap_psock *smap_psock_sk(const struct sock *sk)
{
@@ -161,7 +164,42 @@ out:
return !empty;
}
-static struct proto tcp_bpf_proto;
+enum {
+ SOCKMAP_IPV4,
+ SOCKMAP_IPV6,
+ SOCKMAP_NUM_PROTS,
+};
+
+enum {
+ SOCKMAP_BASE,
+ SOCKMAP_TX,
+ SOCKMAP_NUM_CONFIGS,
+};
+
+static struct proto *saved_tcpv6_prot __read_mostly;
+static DEFINE_SPINLOCK(tcpv6_prot_lock);
+static struct proto bpf_tcp_prots[SOCKMAP_NUM_PROTS][SOCKMAP_NUM_CONFIGS];
+static void build_protos(struct proto prot[SOCKMAP_NUM_CONFIGS],
+ struct proto *base)
+{
+ prot[SOCKMAP_BASE] = *base;
+ prot[SOCKMAP_BASE].close = bpf_tcp_close;
+ prot[SOCKMAP_BASE].recvmsg = bpf_tcp_recvmsg;
+ prot[SOCKMAP_BASE].stream_memory_read = bpf_tcp_stream_read;
+
+ prot[SOCKMAP_TX] = prot[SOCKMAP_BASE];
+ prot[SOCKMAP_TX].sendmsg = bpf_tcp_sendmsg;
+ prot[SOCKMAP_TX].sendpage = bpf_tcp_sendpage;
+}
+
+static void update_sk_prot(struct sock *sk, struct smap_psock *psock)
+{
+ int family = sk->sk_family == AF_INET6 ? SOCKMAP_IPV6 : SOCKMAP_IPV4;
+ int conf = psock->bpf_tx_msg ? SOCKMAP_TX : SOCKMAP_BASE;
+
+ sk->sk_prot = &bpf_tcp_prots[family][conf];
+}
+
static int bpf_tcp_init(struct sock *sk)
{
struct smap_psock *psock;
@@ -181,14 +219,17 @@ static int bpf_tcp_init(struct sock *sk)
psock->save_close = sk->sk_prot->close;
psock->sk_proto = sk->sk_prot;
- if (psock->bpf_tx_msg) {
- tcp_bpf_proto.sendmsg = bpf_tcp_sendmsg;
- tcp_bpf_proto.sendpage = bpf_tcp_sendpage;
- tcp_bpf_proto.recvmsg = bpf_tcp_recvmsg;
- tcp_bpf_proto.stream_memory_read = bpf_tcp_stream_read;
+ /* Build IPv6 sockmap whenever the address of tcpv6_prot changes */
+ if (sk->sk_family == AF_INET6 &&
+ unlikely(sk->sk_prot != smp_load_acquire(&saved_tcpv6_prot))) {
+ spin_lock_bh(&tcpv6_prot_lock);
+ if (likely(sk->sk_prot != saved_tcpv6_prot)) {
+ build_protos(bpf_tcp_prots[SOCKMAP_IPV6], sk->sk_prot);
+ smp_store_release(&saved_tcpv6_prot, sk->sk_prot);
+ }
+ spin_unlock_bh(&tcpv6_prot_lock);
}
-
- sk->sk_prot = &tcp_bpf_proto;
+ update_sk_prot(sk, psock);
rcu_read_unlock();
return 0;
}
@@ -219,24 +260,64 @@ out:
rcu_read_unlock();
}
+static struct htab_elem *lookup_elem_raw(struct hlist_head *head,
+ u32 hash, void *key, u32 key_size)
+{
+ struct htab_elem *l;
+
+ hlist_for_each_entry_rcu(l, head, hash_node) {
+ if (l->hash == hash && !memcmp(&l->key, key, key_size))
+ return l;
+ }
+
+ return NULL;
+}
+
+static inline struct bucket *__select_bucket(struct bpf_htab *htab, u32 hash)
+{
+ return &htab->buckets[hash & (htab->n_buckets - 1)];
+}
+
+static inline struct hlist_head *select_bucket(struct bpf_htab *htab, u32 hash)
+{
+ return &__select_bucket(htab, hash)->head;
+}
+
static void free_htab_elem(struct bpf_htab *htab, struct htab_elem *l)
{
atomic_dec(&htab->count);
kfree_rcu(l, rcu);
}
+static struct smap_psock_map_entry *psock_map_pop(struct sock *sk,
+ struct smap_psock *psock)
+{
+ struct smap_psock_map_entry *e;
+
+ spin_lock_bh(&psock->maps_lock);
+ e = list_first_entry_or_null(&psock->maps,
+ struct smap_psock_map_entry,
+ list);
+ if (e)
+ list_del(&e->list);
+ spin_unlock_bh(&psock->maps_lock);
+ return e;
+}
+
static void bpf_tcp_close(struct sock *sk, long timeout)
{
void (*close_fun)(struct sock *sk, long timeout);
- struct smap_psock_map_entry *e, *tmp;
+ struct smap_psock_map_entry *e;
struct sk_msg_buff *md, *mtmp;
struct smap_psock *psock;
struct sock *osk;
+ lock_sock(sk);
rcu_read_lock();
psock = smap_psock_sk(sk);
if (unlikely(!psock)) {
rcu_read_unlock();
+ release_sock(sk);
return sk->sk_prot->close(sk, timeout);
}
@@ -247,7 +328,6 @@ static void bpf_tcp_close(struct sock *sk, long timeout)
*/
close_fun = psock->save_close;
- write_lock_bh(&sk->sk_callback_lock);
if (psock->cork) {
free_start_sg(psock->sock, psock->cork);
kfree(psock->cork);
@@ -260,21 +340,40 @@ static void bpf_tcp_close(struct sock *sk, long timeout)
kfree(md);
}
- list_for_each_entry_safe(e, tmp, &psock->maps, list) {
+ e = psock_map_pop(sk, psock);
+ while (e) {
if (e->entry) {
osk = cmpxchg(e->entry, sk, NULL);
if (osk == sk) {
- list_del(&e->list);
smap_release_sock(psock, sk);
}
} else {
- hlist_del_rcu(&e->hash_link->hash_node);
- smap_release_sock(psock, e->hash_link->sk);
- free_htab_elem(e->htab, e->hash_link);
+ struct htab_elem *link = rcu_dereference(e->hash_link);
+ struct bpf_htab *htab = rcu_dereference(e->htab);
+ struct hlist_head *head;
+ struct htab_elem *l;
+ struct bucket *b;
+
+ b = __select_bucket(htab, link->hash);
+ head = &b->head;
+ raw_spin_lock_bh(&b->lock);
+ l = lookup_elem_raw(head,
+ link->hash, link->key,
+ htab->map.key_size);
+ /* If another thread deleted this object skip deletion.
+ * The refcnt on psock may or may not be zero.
+ */
+ if (l) {
+ hlist_del_rcu(&link->hash_node);
+ smap_release_sock(psock, link->sk);
+ free_htab_elem(htab, link);
+ }
+ raw_spin_unlock_bh(&b->lock);
}
+ e = psock_map_pop(sk, psock);
}
- write_unlock_bh(&sk->sk_callback_lock);
rcu_read_unlock();
+ release_sock(sk);
close_fun(sk, timeout);
}
@@ -472,7 +571,8 @@ static int free_sg(struct sock *sk, int start, struct sk_msg_buff *md)
while (sg[i].length) {
free += sg[i].length;
sk_mem_uncharge(sk, sg[i].length);
- put_page(sg_page(&sg[i]));
+ if (!md->skb)
+ put_page(sg_page(&sg[i]));
sg[i].length = 0;
sg[i].page_link = 0;
sg[i].offset = 0;
@@ -481,6 +581,8 @@ static int free_sg(struct sock *sk, int start, struct sk_msg_buff *md)
if (i == MAX_SKB_FRAGS)
i = 0;
}
+ if (md->skb)
+ consume_skb(md->skb);
return free;
}
@@ -946,12 +1048,12 @@ static int bpf_tcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT);
while (msg_data_left(msg)) {
- struct sk_msg_buff *m;
+ struct sk_msg_buff *m = NULL;
bool enospc = false;
int copy;
if (sk->sk_err) {
- err = sk->sk_err;
+ err = -sk->sk_err;
goto out_err;
}
@@ -1014,8 +1116,11 @@ wait_for_sndbuf:
set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
wait_for_memory:
err = sk_stream_wait_memory(sk, &timeo);
- if (err)
+ if (err) {
+ if (m && m != psock->cork)
+ free_start_sg(sk, m);
goto out_err;
+ }
}
out_err:
if (err < 0)
@@ -1111,8 +1216,7 @@ static void bpf_tcp_msg_add(struct smap_psock *psock,
static int bpf_tcp_ulp_register(void)
{
- tcp_bpf_proto = tcp_prot;
- tcp_bpf_proto.close = bpf_tcp_close;
+ build_protos(bpf_tcp_prots[SOCKMAP_IPV4], &tcp_prot);
/* Once BPF TX ULP is registered it is never unregistered. It
* will be in the ULP list for the lifetime of the system. Doing
* duplicate registers is not a problem.
@@ -1135,7 +1239,7 @@ static int smap_verdict_func(struct smap_psock *psock, struct sk_buff *skb)
*/
TCP_SKB_CB(skb)->bpf.sk_redir = NULL;
skb->sk = psock->sock;
- bpf_compute_data_pointers(skb);
+ bpf_compute_data_end_sk_skb(skb);
preempt_disable();
rc = (*prog->bpf_func)(skb, prog->insnsi);
preempt_enable();
@@ -1357,7 +1461,9 @@ static void smap_release_sock(struct smap_psock *psock, struct sock *sock)
{
if (refcount_dec_and_test(&psock->refcnt)) {
tcp_cleanup_ulp(sock);
+ write_lock_bh(&sock->sk_callback_lock);
smap_stop_sock(psock, sock);
+ write_unlock_bh(&sock->sk_callback_lock);
clear_bit(SMAP_TX_RUNNING, &psock->state);
rcu_assign_sk_user_data(sock, NULL);
call_rcu_sched(&psock->rcu, smap_destroy_psock);
@@ -1388,7 +1494,7 @@ static int smap_parse_func_strparser(struct strparser *strp,
* any socket yet.
*/
skb->sk = psock->sock;
- bpf_compute_data_pointers(skb);
+ bpf_compute_data_end_sk_skb(skb);
rc = (*prog->bpf_func)(skb, prog->insnsi);
skb->sk = NULL;
rcu_read_unlock();
@@ -1508,6 +1614,7 @@ static struct smap_psock *smap_init_psock(struct sock *sock, int node)
INIT_LIST_HEAD(&psock->maps);
INIT_LIST_HEAD(&psock->ingress);
refcount_set(&psock->refcnt, 1);
+ spin_lock_init(&psock->maps_lock);
rcu_assign_sk_user_data(sock, psock);
sock_hold(sock);
@@ -1564,18 +1671,32 @@ free_stab:
return ERR_PTR(err);
}
-static void smap_list_remove(struct smap_psock *psock,
- struct sock **entry,
- struct htab_elem *hash_link)
+static void smap_list_map_remove(struct smap_psock *psock,
+ struct sock **entry)
{
struct smap_psock_map_entry *e, *tmp;
+ spin_lock_bh(&psock->maps_lock);
list_for_each_entry_safe(e, tmp, &psock->maps, list) {
- if (e->entry == entry || e->hash_link == hash_link) {
+ if (e->entry == entry)
list_del(&e->list);
- break;
- }
}
+ spin_unlock_bh(&psock->maps_lock);
+}
+
+static void smap_list_hash_remove(struct smap_psock *psock,
+ struct htab_elem *hash_link)
+{
+ struct smap_psock_map_entry *e, *tmp;
+
+ spin_lock_bh(&psock->maps_lock);
+ list_for_each_entry_safe(e, tmp, &psock->maps, list) {
+ struct htab_elem *c = rcu_dereference(e->hash_link);
+
+ if (c == hash_link)
+ list_del(&e->list);
+ }
+ spin_unlock_bh(&psock->maps_lock);
}
static void sock_map_free(struct bpf_map *map)
@@ -1601,7 +1722,6 @@ static void sock_map_free(struct bpf_map *map)
if (!sock)
continue;
- write_lock_bh(&sock->sk_callback_lock);
psock = smap_psock_sk(sock);
/* This check handles a racing sock event that can get the
* sk_callback_lock before this case but after xchg happens
@@ -1609,10 +1729,9 @@ static void sock_map_free(struct bpf_map *map)
* to be null and queued for garbage collection.
*/
if (likely(psock)) {
- smap_list_remove(psock, &stab->sock_map[i], NULL);
+ smap_list_map_remove(psock, &stab->sock_map[i]);
smap_release_sock(psock, sock);
}
- write_unlock_bh(&sock->sk_callback_lock);
}
rcu_read_unlock();
@@ -1661,17 +1780,15 @@ static int sock_map_delete_elem(struct bpf_map *map, void *key)
if (!sock)
return -EINVAL;
- write_lock_bh(&sock->sk_callback_lock);
psock = smap_psock_sk(sock);
if (!psock)
goto out;
if (psock->bpf_parse)
smap_stop_sock(psock, sock);
- smap_list_remove(psock, &stab->sock_map[k], NULL);
+ smap_list_map_remove(psock, &stab->sock_map[k]);
smap_release_sock(psock, sock);
out:
- write_unlock_bh(&sock->sk_callback_lock);
return 0;
}
@@ -1752,7 +1869,6 @@ static int __sock_map_ctx_update_elem(struct bpf_map *map,
}
}
- write_lock_bh(&sock->sk_callback_lock);
psock = smap_psock_sk(sock);
/* 2. Do not allow inheriting programs if psock exists and has
@@ -1789,7 +1905,7 @@ static int __sock_map_ctx_update_elem(struct bpf_map *map,
e = kzalloc(sizeof(*e), GFP_ATOMIC | __GFP_NOWARN);
if (!e) {
err = -ENOMEM;
- goto out_progs;
+ goto out_free;
}
}
@@ -1809,7 +1925,9 @@ static int __sock_map_ctx_update_elem(struct bpf_map *map,
if (err)
goto out_free;
smap_init_progs(psock, verdict, parse);
+ write_lock_bh(&sock->sk_callback_lock);
smap_start_sock(psock, sock);
+ write_unlock_bh(&sock->sk_callback_lock);
}
/* 4. Place psock in sockmap for use and stop any programs on
@@ -1819,9 +1937,10 @@ static int __sock_map_ctx_update_elem(struct bpf_map *map,
*/
if (map_link) {
e->entry = map_link;
+ spin_lock_bh(&psock->maps_lock);
list_add_tail(&e->list, &psock->maps);
+ spin_unlock_bh(&psock->maps_lock);
}
- write_unlock_bh(&sock->sk_callback_lock);
return err;
out_free:
smap_release_sock(psock, sock);
@@ -1832,7 +1951,6 @@ out_progs:
}
if (tx_msg)
bpf_prog_put(tx_msg);
- write_unlock_bh(&sock->sk_callback_lock);
kfree(e);
return err;
}
@@ -1869,10 +1987,8 @@ static int sock_map_ctx_update_elem(struct bpf_sock_ops_kern *skops,
if (osock) {
struct smap_psock *opsock = smap_psock_sk(osock);
- write_lock_bh(&osock->sk_callback_lock);
- smap_list_remove(opsock, &stab->sock_map[i], NULL);
+ smap_list_map_remove(opsock, &stab->sock_map[i]);
smap_release_sock(opsock, osock);
- write_unlock_bh(&osock->sk_callback_lock);
}
out:
return err;
@@ -1915,6 +2031,24 @@ int sock_map_prog(struct bpf_map *map, struct bpf_prog *prog, u32 type)
return 0;
}
+int sockmap_get_from_fd(const union bpf_attr *attr, int type,
+ struct bpf_prog *prog)
+{
+ int ufd = attr->target_fd;
+ struct bpf_map *map;
+ struct fd f;
+ int err;
+
+ f = fdget(ufd);
+ map = __bpf_map_get(f);
+ if (IS_ERR(map))
+ return PTR_ERR(map);
+
+ err = sock_map_prog(map, prog, attr->attach_type);
+ fdput(f);
+ return err;
+}
+
static void *sock_map_lookup(struct bpf_map *map, void *key)
{
return NULL;
@@ -1944,7 +2078,13 @@ static int sock_map_update_elem(struct bpf_map *map,
return -EOPNOTSUPP;
}
+ lock_sock(skops.sk);
+ preempt_disable();
+ rcu_read_lock();
err = sock_map_ctx_update_elem(&skops, map, key, flags);
+ rcu_read_unlock();
+ preempt_enable();
+ release_sock(skops.sk);
fput(socket->file);
return err;
}
@@ -2043,14 +2183,13 @@ free_htab:
return ERR_PTR(err);
}
-static inline struct bucket *__select_bucket(struct bpf_htab *htab, u32 hash)
+static void __bpf_htab_free(struct rcu_head *rcu)
{
- return &htab->buckets[hash & (htab->n_buckets - 1)];
-}
+ struct bpf_htab *htab;
-static inline struct hlist_head *select_bucket(struct bpf_htab *htab, u32 hash)
-{
- return &__select_bucket(htab, hash)->head;
+ htab = container_of(rcu, struct bpf_htab, rcu);
+ bpf_map_area_free(htab->buckets);
+ kfree(htab);
}
static void sock_hash_free(struct bpf_map *map)
@@ -2069,16 +2208,18 @@ static void sock_hash_free(struct bpf_map *map)
*/
rcu_read_lock();
for (i = 0; i < htab->n_buckets; i++) {
- struct hlist_head *head = select_bucket(htab, i);
+ struct bucket *b = __select_bucket(htab, i);
+ struct hlist_head *head;
struct hlist_node *n;
struct htab_elem *l;
+ raw_spin_lock_bh(&b->lock);
+ head = &b->head;
hlist_for_each_entry_safe(l, n, head, hash_node) {
struct sock *sock = l->sk;
struct smap_psock *psock;
hlist_del_rcu(&l->hash_node);
- write_lock_bh(&sock->sk_callback_lock);
psock = smap_psock_sk(sock);
/* This check handles a racing sock event that can get
* the sk_callback_lock before this case but after xchg
@@ -2086,16 +2227,15 @@ static void sock_hash_free(struct bpf_map *map)
* (psock) to be null and queued for garbage collection.
*/
if (likely(psock)) {
- smap_list_remove(psock, NULL, l);
+ smap_list_hash_remove(psock, l);
smap_release_sock(psock, sock);
}
- write_unlock_bh(&sock->sk_callback_lock);
- kfree(l);
+ free_htab_elem(htab, l);
}
+ raw_spin_unlock_bh(&b->lock);
}
rcu_read_unlock();
- bpf_map_area_free(htab->buckets);
- kfree(htab);
+ call_rcu(&htab->rcu, __bpf_htab_free);
}
static struct htab_elem *alloc_sock_hash_elem(struct bpf_htab *htab,
@@ -2122,19 +2262,6 @@ static struct htab_elem *alloc_sock_hash_elem(struct bpf_htab *htab,
return l_new;
}
-static struct htab_elem *lookup_elem_raw(struct hlist_head *head,
- u32 hash, void *key, u32 key_size)
-{
- struct htab_elem *l;
-
- hlist_for_each_entry_rcu(l, head, hash_node) {
- if (l->hash == hash && !memcmp(&l->key, key, key_size))
- return l;
- }
-
- return NULL;
-}
-
static inline u32 htab_map_hash(const void *key, u32 key_len)
{
return jhash(key, key_len, 0);
@@ -2230,7 +2357,10 @@ static int sock_hash_ctx_update_elem(struct bpf_sock_ops_kern *skops,
if (err)
goto err;
- /* bpf_map_update_elem() can be called in_irq() */
+ /* psock is valid here because otherwise above *ctx_update_elem would
+ * have thrown an error. It is safe to skip error check.
+ */
+ psock = smap_psock_sk(sock);
raw_spin_lock_bh(&b->lock);
l_old = lookup_elem_raw(head, hash, key, key_size);
if (l_old && map_flags == BPF_NOEXIST) {
@@ -2248,15 +2378,12 @@ static int sock_hash_ctx_update_elem(struct bpf_sock_ops_kern *skops,
goto bucket_err;
}
- psock = smap_psock_sk(sock);
- if (unlikely(!psock)) {
- err = -EINVAL;
- goto bucket_err;
- }
-
- e->hash_link = l_new;
- e->htab = container_of(map, struct bpf_htab, map);
+ rcu_assign_pointer(e->hash_link, l_new);
+ rcu_assign_pointer(e->htab,
+ container_of(map, struct bpf_htab, map));
+ spin_lock_bh(&psock->maps_lock);
list_add_tail(&e->list, &psock->maps);
+ spin_unlock_bh(&psock->maps_lock);
/* add new element to the head of the list, so that
* concurrent search will find it before old elem
@@ -2266,19 +2393,17 @@ static int sock_hash_ctx_update_elem(struct bpf_sock_ops_kern *skops,
psock = smap_psock_sk(l_old->sk);
hlist_del_rcu(&l_old->hash_node);
- smap_list_remove(psock, NULL, l_old);
+ smap_list_hash_remove(psock, l_old);
smap_release_sock(psock, l_old->sk);
free_htab_elem(htab, l_old);
}
raw_spin_unlock_bh(&b->lock);
return 0;
bucket_err:
+ smap_release_sock(psock, sock);
raw_spin_unlock_bh(&b->lock);
err:
kfree(e);
- psock = smap_psock_sk(sock);
- if (psock)
- smap_release_sock(psock, sock);
return err;
}
@@ -2300,7 +2425,13 @@ static int sock_hash_update_elem(struct bpf_map *map,
return -EINVAL;
}
+ lock_sock(skops.sk);
+ preempt_disable();
+ rcu_read_lock();
err = sock_hash_ctx_update_elem(&skops, map, key, flags);
+ rcu_read_unlock();
+ preempt_enable();
+ release_sock(skops.sk);
fput(socket->file);
return err;
}
@@ -2326,7 +2457,6 @@ static int sock_hash_delete_elem(struct bpf_map *map, void *key)
struct smap_psock *psock;
hlist_del_rcu(&l->hash_node);
- write_lock_bh(&sock->sk_callback_lock);
psock = smap_psock_sk(sock);
/* This check handles a racing sock event that can get the
* sk_callback_lock before this case but after xchg happens
@@ -2334,10 +2464,9 @@ static int sock_hash_delete_elem(struct bpf_map *map, void *key)
* to be null and queued for garbage collection.
*/
if (likely(psock)) {
- smap_list_remove(psock, NULL, l);
+ smap_list_hash_remove(psock, l);
smap_release_sock(psock, sock);
}
- write_unlock_bh(&sock->sk_callback_lock);
free_htab_elem(htab, l);
ret = 0;
}
@@ -2359,10 +2488,8 @@ struct sock *__sock_hash_lookup_elem(struct bpf_map *map, void *key)
b = __select_bucket(htab, hash);
head = &b->head;
- raw_spin_lock_bh(&b->lock);
l = lookup_elem_raw(head, hash, key, key_size);
sk = l ? l->sk : NULL;
- raw_spin_unlock_bh(&b->lock);
return sk;
}
@@ -2383,6 +2510,7 @@ const struct bpf_map_ops sock_hash_ops = {
.map_get_next_key = sock_hash_get_next_key,
.map_update_elem = sock_hash_update_elem,
.map_delete_elem = sock_hash_delete_elem,
+ .map_release_uref = sock_map_release,
};
BPF_CALL_4(bpf_sock_map_update, struct bpf_sock_ops_kern *, bpf_sock,
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 0fa20624707f..a31a1ba0f8ea 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -735,7 +735,9 @@ static int map_update_elem(union bpf_attr *attr)
if (bpf_map_is_dev_bound(map)) {
err = bpf_map_offload_update_elem(map, key, value, attr->flags);
goto out;
- } else if (map->map_type == BPF_MAP_TYPE_CPUMAP) {
+ } else if (map->map_type == BPF_MAP_TYPE_CPUMAP ||
+ map->map_type == BPF_MAP_TYPE_SOCKHASH ||
+ map->map_type == BPF_MAP_TYPE_SOCKMAP) {
err = map->ops->map_update_elem(map, key, value, attr->flags);
goto out;
}
@@ -1034,14 +1036,9 @@ static void __bpf_prog_put_rcu(struct rcu_head *rcu)
static void __bpf_prog_put(struct bpf_prog *prog, bool do_idr_lock)
{
if (atomic_dec_and_test(&prog->aux->refcnt)) {
- int i;
-
/* bpf_prog_free_id() must be called first */
bpf_prog_free_id(prog, do_idr_lock);
-
- for (i = 0; i < prog->aux->func_cnt; i++)
- bpf_prog_kallsyms_del(prog->aux->func[i]);
- bpf_prog_kallsyms_del(prog);
+ bpf_prog_kallsyms_del_all(prog);
call_rcu(&prog->aux->rcu, __bpf_prog_put_rcu);
}
@@ -1358,9 +1355,7 @@ static int bpf_prog_load(union bpf_attr *attr)
if (err < 0)
goto free_used_maps;
- /* eBPF program is ready to be JITed */
- if (!prog->bpf_func)
- prog = bpf_prog_select_runtime(prog, &err);
+ prog = bpf_prog_select_runtime(prog, &err);
if (err < 0)
goto free_used_maps;
@@ -1384,6 +1379,7 @@ static int bpf_prog_load(union bpf_attr *attr)
return err;
free_used_maps:
+ bpf_prog_kallsyms_del_subprogs(prog);
free_used_maps(prog->aux);
free_prog:
bpf_prog_uncharge_memlock(prog);
@@ -1489,8 +1485,6 @@ out_free_tp:
return err;
}
-#ifdef CONFIG_CGROUP_BPF
-
static int bpf_prog_attach_check_attach_type(const struct bpf_prog *prog,
enum bpf_attach_type attach_type)
{
@@ -1505,40 +1499,6 @@ static int bpf_prog_attach_check_attach_type(const struct bpf_prog *prog,
#define BPF_PROG_ATTACH_LAST_FIELD attach_flags
-static int sockmap_get_from_fd(const union bpf_attr *attr,
- int type, bool attach)
-{
- struct bpf_prog *prog = NULL;
- int ufd = attr->target_fd;
- struct bpf_map *map;
- struct fd f;
- int err;
-
- f = fdget(ufd);
- map = __bpf_map_get(f);
- if (IS_ERR(map))
- return PTR_ERR(map);
-
- if (attach) {
- prog = bpf_prog_get_type(attr->attach_bpf_fd, type);
- if (IS_ERR(prog)) {
- fdput(f);
- return PTR_ERR(prog);
- }
- }
-
- err = sock_map_prog(map, prog, attr->attach_type);
- if (err) {
- fdput(f);
- if (prog)
- bpf_prog_put(prog);
- return err;
- }
-
- fdput(f);
- return 0;
-}
-
#define BPF_F_ATTACH_MASK \
(BPF_F_ALLOW_OVERRIDE | BPF_F_ALLOW_MULTI)
@@ -1546,7 +1506,6 @@ static int bpf_prog_attach(const union bpf_attr *attr)
{
enum bpf_prog_type ptype;
struct bpf_prog *prog;
- struct cgroup *cgrp;
int ret;
if (!capable(CAP_NET_ADMIN))
@@ -1583,12 +1542,15 @@ static int bpf_prog_attach(const union bpf_attr *attr)
ptype = BPF_PROG_TYPE_CGROUP_DEVICE;
break;
case BPF_SK_MSG_VERDICT:
- return sockmap_get_from_fd(attr, BPF_PROG_TYPE_SK_MSG, true);
+ ptype = BPF_PROG_TYPE_SK_MSG;
+ break;
case BPF_SK_SKB_STREAM_PARSER:
case BPF_SK_SKB_STREAM_VERDICT:
- return sockmap_get_from_fd(attr, BPF_PROG_TYPE_SK_SKB, true);
+ ptype = BPF_PROG_TYPE_SK_SKB;
+ break;
case BPF_LIRC_MODE2:
- return lirc_prog_attach(attr);
+ ptype = BPF_PROG_TYPE_LIRC_MODE2;
+ break;
default:
return -EINVAL;
}
@@ -1602,18 +1564,20 @@ static int bpf_prog_attach(const union bpf_attr *attr)
return -EINVAL;
}
- cgrp = cgroup_get_from_fd(attr->target_fd);
- if (IS_ERR(cgrp)) {
- bpf_prog_put(prog);
- return PTR_ERR(cgrp);
+ switch (ptype) {
+ case BPF_PROG_TYPE_SK_SKB:
+ case BPF_PROG_TYPE_SK_MSG:
+ ret = sockmap_get_from_fd(attr, ptype, prog);
+ break;
+ case BPF_PROG_TYPE_LIRC_MODE2:
+ ret = lirc_prog_attach(attr, prog);
+ break;
+ default:
+ ret = cgroup_bpf_prog_attach(attr, ptype, prog);
}
- ret = cgroup_bpf_attach(cgrp, prog, attr->attach_type,
- attr->attach_flags);
if (ret)
bpf_prog_put(prog);
- cgroup_put(cgrp);
-
return ret;
}
@@ -1622,9 +1586,6 @@ static int bpf_prog_attach(const union bpf_attr *attr)
static int bpf_prog_detach(const union bpf_attr *attr)
{
enum bpf_prog_type ptype;
- struct bpf_prog *prog;
- struct cgroup *cgrp;
- int ret;
if (!capable(CAP_NET_ADMIN))
return -EPERM;
@@ -1657,29 +1618,17 @@ static int bpf_prog_detach(const union bpf_attr *attr)
ptype = BPF_PROG_TYPE_CGROUP_DEVICE;
break;
case BPF_SK_MSG_VERDICT:
- return sockmap_get_from_fd(attr, BPF_PROG_TYPE_SK_MSG, false);
+ return sockmap_get_from_fd(attr, BPF_PROG_TYPE_SK_MSG, NULL);
case BPF_SK_SKB_STREAM_PARSER:
case BPF_SK_SKB_STREAM_VERDICT:
- return sockmap_get_from_fd(attr, BPF_PROG_TYPE_SK_SKB, false);
+ return sockmap_get_from_fd(attr, BPF_PROG_TYPE_SK_SKB, NULL);
case BPF_LIRC_MODE2:
return lirc_prog_detach(attr);
default:
return -EINVAL;
}
- cgrp = cgroup_get_from_fd(attr->target_fd);
- if (IS_ERR(cgrp))
- return PTR_ERR(cgrp);
-
- prog = bpf_prog_get_type(attr->attach_bpf_fd, ptype);
- if (IS_ERR(prog))
- prog = NULL;
-
- ret = cgroup_bpf_detach(cgrp, prog, attr->attach_type, 0);
- if (prog)
- bpf_prog_put(prog);
- cgroup_put(cgrp);
- return ret;
+ return cgroup_bpf_prog_detach(attr, ptype);
}
#define BPF_PROG_QUERY_LAST_FIELD query.prog_cnt
@@ -1687,9 +1636,6 @@ static int bpf_prog_detach(const union bpf_attr *attr)
static int bpf_prog_query(const union bpf_attr *attr,
union bpf_attr __user *uattr)
{
- struct cgroup *cgrp;
- int ret;
-
if (!capable(CAP_NET_ADMIN))
return -EPERM;
if (CHECK_ATTR(BPF_PROG_QUERY))
@@ -1717,14 +1663,9 @@ static int bpf_prog_query(const union bpf_attr *attr,
default:
return -EINVAL;
}
- cgrp = cgroup_get_from_fd(attr->query.target_fd);
- if (IS_ERR(cgrp))
- return PTR_ERR(cgrp);
- ret = cgroup_bpf_query(cgrp, attr, uattr);
- cgroup_put(cgrp);
- return ret;
+
+ return cgroup_bpf_prog_query(attr, uattr);
}
-#endif /* CONFIG_CGROUP_BPF */
#define BPF_PROG_TEST_RUN_LAST_FIELD test.duration
@@ -2371,7 +2312,6 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz
case BPF_OBJ_GET:
err = bpf_obj_get(&attr);
break;
-#ifdef CONFIG_CGROUP_BPF
case BPF_PROG_ATTACH:
err = bpf_prog_attach(&attr);
break;
@@ -2381,7 +2321,6 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz
case BPF_PROG_QUERY:
err = bpf_prog_query(&attr, uattr);
break;
-#endif
case BPF_PROG_TEST_RUN:
err = bpf_prog_test_run(&attr, uattr);
break;
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 9e2bf834f13a..63aaac52a265 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -5430,6 +5430,10 @@ static int jit_subprogs(struct bpf_verifier_env *env)
if (insn->code != (BPF_JMP | BPF_CALL) ||
insn->src_reg != BPF_PSEUDO_CALL)
continue;
+ /* Upon error here we cannot fall back to interpreter but
+ * need a hard reject of the program. Thus -EFAULT is
+ * propagated in any case.
+ */
subprog = find_subprog(env, i + insn->imm + 1);
if (subprog < 0) {
WARN_ONCE(1, "verifier bug. No program starts at insn %d\n",
@@ -5450,7 +5454,7 @@ static int jit_subprogs(struct bpf_verifier_env *env)
func = kcalloc(env->subprog_cnt, sizeof(prog), GFP_KERNEL);
if (!func)
- return -ENOMEM;
+ goto out_undo_insn;
for (i = 0; i < env->subprog_cnt; i++) {
subprog_start = subprog_end;
@@ -5515,7 +5519,7 @@ static int jit_subprogs(struct bpf_verifier_env *env)
tmp = bpf_int_jit_compile(func[i]);
if (tmp != func[i] || func[i]->bpf_func != old_bpf_func) {
verbose(env, "JIT doesn't support bpf-to-bpf calls\n");
- err = -EFAULT;
+ err = -ENOTSUPP;
goto out_free;
}
cond_resched();
@@ -5552,6 +5556,7 @@ out_free:
if (func[i])
bpf_jit_free(func[i]);
kfree(func);
+out_undo_insn:
/* cleanup main prog to be interpreted */
prog->jit_requested = 0;
for (i = 0, insn = prog->insnsi; i < prog->len; i++, insn++) {
@@ -5578,6 +5583,8 @@ static int fixup_call_args(struct bpf_verifier_env *env)
err = jit_subprogs(env);
if (err == 0)
return 0;
+ if (err == -EFAULT)
+ return err;
}
#ifndef CONFIG_BPF_JIT_ALWAYS_ON
for (i = 0; i < prog->len; i++, insn++) {
diff --git a/kernel/cpu.c b/kernel/cpu.c
index 0db8938fbb23..2f8f338e77cf 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -2010,7 +2010,7 @@ void __init boot_cpu_init(void)
/*
* Must be called _AFTER_ setting up the per_cpu areas
*/
-void __init boot_cpu_state_init(void)
+void __init boot_cpu_hotplug_init(void)
{
per_cpu_ptr(&cpuhp_state, smp_processor_id())->state = CPUHP_ONLINE;
}
diff --git a/kernel/dma/Kconfig b/kernel/dma/Kconfig
new file mode 100644
index 000000000000..9bd54304446f
--- /dev/null
+++ b/kernel/dma/Kconfig
@@ -0,0 +1,50 @@
+
+config HAS_DMA
+ bool
+ depends on !NO_DMA
+ default y
+
+config NEED_SG_DMA_LENGTH
+ bool
+
+config NEED_DMA_MAP_STATE
+ bool
+
+config ARCH_DMA_ADDR_T_64BIT
+ def_bool 64BIT || PHYS_ADDR_T_64BIT
+
+config HAVE_GENERIC_DMA_COHERENT
+ bool
+
+config ARCH_HAS_SYNC_DMA_FOR_DEVICE
+ bool
+
+config ARCH_HAS_SYNC_DMA_FOR_CPU
+ bool
+ select NEED_DMA_MAP_STATE
+
+config DMA_DIRECT_OPS
+ bool
+ depends on HAS_DMA
+
+config DMA_NONCOHERENT_OPS
+ bool
+ depends on HAS_DMA
+ select DMA_DIRECT_OPS
+
+config DMA_NONCOHERENT_MMAP
+ bool
+ depends on DMA_NONCOHERENT_OPS
+
+config DMA_NONCOHERENT_CACHE_SYNC
+ bool
+ depends on DMA_NONCOHERENT_OPS
+
+config DMA_VIRT_OPS
+ bool
+ depends on HAS_DMA
+
+config SWIOTLB
+ bool
+ select DMA_DIRECT_OPS
+ select NEED_DMA_MAP_STATE
diff --git a/kernel/dma/Makefile b/kernel/dma/Makefile
new file mode 100644
index 000000000000..6de44e4eb454
--- /dev/null
+++ b/kernel/dma/Makefile
@@ -0,0 +1,11 @@
+# SPDX-License-Identifier: GPL-2.0
+
+obj-$(CONFIG_HAS_DMA) += mapping.o
+obj-$(CONFIG_DMA_CMA) += contiguous.o
+obj-$(CONFIG_HAVE_GENERIC_DMA_COHERENT) += coherent.o
+obj-$(CONFIG_DMA_DIRECT_OPS) += direct.o
+obj-$(CONFIG_DMA_NONCOHERENT_OPS) += noncoherent.o
+obj-$(CONFIG_DMA_VIRT_OPS) += virt.o
+obj-$(CONFIG_DMA_API_DEBUG) += debug.o
+obj-$(CONFIG_SWIOTLB) += swiotlb.o
+
diff --git a/kernel/dma/coherent.c b/kernel/dma/coherent.c
new file mode 100644
index 000000000000..597d40893862
--- /dev/null
+++ b/kernel/dma/coherent.c
@@ -0,0 +1,434 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Coherent per-device memory handling.
+ * Borrowed from i386
+ */
+#include <linux/io.h>
+#include <linux/slab.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/dma-mapping.h>
+
+struct dma_coherent_mem {
+ void *virt_base;
+ dma_addr_t device_base;
+ unsigned long pfn_base;
+ int size;
+ int flags;
+ unsigned long *bitmap;
+ spinlock_t spinlock;
+ bool use_dev_dma_pfn_offset;
+};
+
+static struct dma_coherent_mem *dma_coherent_default_memory __ro_after_init;
+
+static inline struct dma_coherent_mem *dev_get_coherent_memory(struct device *dev)
+{
+ if (dev && dev->dma_mem)
+ return dev->dma_mem;
+ return NULL;
+}
+
+static inline dma_addr_t dma_get_device_base(struct device *dev,
+ struct dma_coherent_mem * mem)
+{
+ if (mem->use_dev_dma_pfn_offset)
+ return (mem->pfn_base - dev->dma_pfn_offset) << PAGE_SHIFT;
+ else
+ return mem->device_base;
+}
+
+static int dma_init_coherent_memory(
+ phys_addr_t phys_addr, dma_addr_t device_addr, size_t size, int flags,
+ struct dma_coherent_mem **mem)
+{
+ struct dma_coherent_mem *dma_mem = NULL;
+ void __iomem *mem_base = NULL;
+ int pages = size >> PAGE_SHIFT;
+ int bitmap_size = BITS_TO_LONGS(pages) * sizeof(long);
+ int ret;
+
+ if (!size) {
+ ret = -EINVAL;
+ goto out;
+ }
+
+ mem_base = memremap(phys_addr, size, MEMREMAP_WC);
+ if (!mem_base) {
+ ret = -EINVAL;
+ goto out;
+ }
+ dma_mem = kzalloc(sizeof(struct dma_coherent_mem), GFP_KERNEL);
+ if (!dma_mem) {
+ ret = -ENOMEM;
+ goto out;
+ }
+ dma_mem->bitmap = kzalloc(bitmap_size, GFP_KERNEL);
+ if (!dma_mem->bitmap) {
+ ret = -ENOMEM;
+ goto out;
+ }
+
+ dma_mem->virt_base = mem_base;
+ dma_mem->device_base = device_addr;
+ dma_mem->pfn_base = PFN_DOWN(phys_addr);
+ dma_mem->size = pages;
+ dma_mem->flags = flags;
+ spin_lock_init(&dma_mem->spinlock);
+
+ *mem = dma_mem;
+ return 0;
+
+out:
+ kfree(dma_mem);
+ if (mem_base)
+ memunmap(mem_base);
+ return ret;
+}
+
+static void dma_release_coherent_memory(struct dma_coherent_mem *mem)
+{
+ if (!mem)
+ return;
+
+ memunmap(mem->virt_base);
+ kfree(mem->bitmap);
+ kfree(mem);
+}
+
+static int dma_assign_coherent_memory(struct device *dev,
+ struct dma_coherent_mem *mem)
+{
+ if (!dev)
+ return -ENODEV;
+
+ if (dev->dma_mem)
+ return -EBUSY;
+
+ dev->dma_mem = mem;
+ return 0;
+}
+
+int dma_declare_coherent_memory(struct device *dev, phys_addr_t phys_addr,
+ dma_addr_t device_addr, size_t size, int flags)
+{
+ struct dma_coherent_mem *mem;
+ int ret;
+
+ ret = dma_init_coherent_memory(phys_addr, device_addr, size, flags, &mem);
+ if (ret)
+ return ret;
+
+ ret = dma_assign_coherent_memory(dev, mem);
+ if (ret)
+ dma_release_coherent_memory(mem);
+ return ret;
+}
+EXPORT_SYMBOL(dma_declare_coherent_memory);
+
+void dma_release_declared_memory(struct device *dev)
+{
+ struct dma_coherent_mem *mem = dev->dma_mem;
+
+ if (!mem)
+ return;
+ dma_release_coherent_memory(mem);
+ dev->dma_mem = NULL;
+}
+EXPORT_SYMBOL(dma_release_declared_memory);
+
+void *dma_mark_declared_memory_occupied(struct device *dev,
+ dma_addr_t device_addr, size_t size)
+{
+ struct dma_coherent_mem *mem = dev->dma_mem;
+ unsigned long flags;
+ int pos, err;
+
+ size += device_addr & ~PAGE_MASK;
+
+ if (!mem)
+ return ERR_PTR(-EINVAL);
+
+ spin_lock_irqsave(&mem->spinlock, flags);
+ pos = PFN_DOWN(device_addr - dma_get_device_base(dev, mem));
+ err = bitmap_allocate_region(mem->bitmap, pos, get_order(size));
+ spin_unlock_irqrestore(&mem->spinlock, flags);
+
+ if (err != 0)
+ return ERR_PTR(err);
+ return mem->virt_base + (pos << PAGE_SHIFT);
+}
+EXPORT_SYMBOL(dma_mark_declared_memory_occupied);
+
+static void *__dma_alloc_from_coherent(struct dma_coherent_mem *mem,
+ ssize_t size, dma_addr_t *dma_handle)
+{
+ int order = get_order(size);
+ unsigned long flags;
+ int pageno;
+ void *ret;
+
+ spin_lock_irqsave(&mem->spinlock, flags);
+
+ if (unlikely(size > (mem->size << PAGE_SHIFT)))
+ goto err;
+
+ pageno = bitmap_find_free_region(mem->bitmap, mem->size, order);
+ if (unlikely(pageno < 0))
+ goto err;
+
+ /*
+ * Memory was found in the coherent area.
+ */
+ *dma_handle = mem->device_base + (pageno << PAGE_SHIFT);
+ ret = mem->virt_base + (pageno << PAGE_SHIFT);
+ spin_unlock_irqrestore(&mem->spinlock, flags);
+ memset(ret, 0, size);
+ return ret;
+err:
+ spin_unlock_irqrestore(&mem->spinlock, flags);
+ return NULL;
+}
+
+/**
+ * dma_alloc_from_dev_coherent() - allocate memory from device coherent pool
+ * @dev: device from which we allocate memory
+ * @size: size of requested memory area
+ * @dma_handle: This will be filled with the correct dma handle
+ * @ret: This pointer will be filled with the virtual address
+ * to allocated area.
+ *
+ * This function should be only called from per-arch dma_alloc_coherent()
+ * to support allocation from per-device coherent memory pools.
+ *
+ * Returns 0 if dma_alloc_coherent should continue with allocating from
+ * generic memory areas, or !0 if dma_alloc_coherent should return @ret.
+ */
+int dma_alloc_from_dev_coherent(struct device *dev, ssize_t size,
+ dma_addr_t *dma_handle, void **ret)
+{
+ struct dma_coherent_mem *mem = dev_get_coherent_memory(dev);
+
+ if (!mem)
+ return 0;
+
+ *ret = __dma_alloc_from_coherent(mem, size, dma_handle);
+ if (*ret)
+ return 1;
+
+ /*
+ * In the case where the allocation can not be satisfied from the
+ * per-device area, try to fall back to generic memory if the
+ * constraints allow it.
+ */
+ return mem->flags & DMA_MEMORY_EXCLUSIVE;
+}
+EXPORT_SYMBOL(dma_alloc_from_dev_coherent);
+
+void *dma_alloc_from_global_coherent(ssize_t size, dma_addr_t *dma_handle)
+{
+ if (!dma_coherent_default_memory)
+ return NULL;
+
+ return __dma_alloc_from_coherent(dma_coherent_default_memory, size,
+ dma_handle);
+}
+
+static int __dma_release_from_coherent(struct dma_coherent_mem *mem,
+ int order, void *vaddr)
+{
+ if (mem && vaddr >= mem->virt_base && vaddr <
+ (mem->virt_base + (mem->size << PAGE_SHIFT))) {
+ int page = (vaddr - mem->virt_base) >> PAGE_SHIFT;
+ unsigned long flags;
+
+ spin_lock_irqsave(&mem->spinlock, flags);
+ bitmap_release_region(mem->bitmap, page, order);
+ spin_unlock_irqrestore(&mem->spinlock, flags);
+ return 1;
+ }
+ return 0;
+}
+
+/**
+ * dma_release_from_dev_coherent() - free memory to device coherent memory pool
+ * @dev: device from which the memory was allocated
+ * @order: the order of pages allocated
+ * @vaddr: virtual address of allocated pages
+ *
+ * This checks whether the memory was allocated from the per-device
+ * coherent memory pool and if so, releases that memory.
+ *
+ * Returns 1 if we correctly released the memory, or 0 if the caller should
+ * proceed with releasing memory from generic pools.
+ */
+int dma_release_from_dev_coherent(struct device *dev, int order, void *vaddr)
+{
+ struct dma_coherent_mem *mem = dev_get_coherent_memory(dev);
+
+ return __dma_release_from_coherent(mem, order, vaddr);
+}
+EXPORT_SYMBOL(dma_release_from_dev_coherent);
+
+int dma_release_from_global_coherent(int order, void *vaddr)
+{
+ if (!dma_coherent_default_memory)
+ return 0;
+
+ return __dma_release_from_coherent(dma_coherent_default_memory, order,
+ vaddr);
+}
+
+static int __dma_mmap_from_coherent(struct dma_coherent_mem *mem,
+ struct vm_area_struct *vma, void *vaddr, size_t size, int *ret)
+{
+ if (mem && vaddr >= mem->virt_base && vaddr + size <=
+ (mem->virt_base + (mem->size << PAGE_SHIFT))) {
+ unsigned long off = vma->vm_pgoff;
+ int start = (vaddr - mem->virt_base) >> PAGE_SHIFT;
+ int user_count = vma_pages(vma);
+ int count = PAGE_ALIGN(size) >> PAGE_SHIFT;
+
+ *ret = -ENXIO;
+ if (off < count && user_count <= count - off) {
+ unsigned long pfn = mem->pfn_base + start + off;
+ *ret = remap_pfn_range(vma, vma->vm_start, pfn,
+ user_count << PAGE_SHIFT,
+ vma->vm_page_prot);
+ }
+ return 1;
+ }
+ return 0;
+}
+
+/**
+ * dma_mmap_from_dev_coherent() - mmap memory from the device coherent pool
+ * @dev: device from which the memory was allocated
+ * @vma: vm_area for the userspace memory
+ * @vaddr: cpu address returned by dma_alloc_from_dev_coherent
+ * @size: size of the memory buffer allocated
+ * @ret: result from remap_pfn_range()
+ *
+ * This checks whether the memory was allocated from the per-device
+ * coherent memory pool and if so, maps that memory to the provided vma.
+ *
+ * Returns 1 if @vaddr belongs to the device coherent pool and the caller
+ * should return @ret, or 0 if they should proceed with mapping memory from
+ * generic areas.
+ */
+int dma_mmap_from_dev_coherent(struct device *dev, struct vm_area_struct *vma,
+ void *vaddr, size_t size, int *ret)
+{
+ struct dma_coherent_mem *mem = dev_get_coherent_memory(dev);
+
+ return __dma_mmap_from_coherent(mem, vma, vaddr, size, ret);
+}
+EXPORT_SYMBOL(dma_mmap_from_dev_coherent);
+
+int dma_mmap_from_global_coherent(struct vm_area_struct *vma, void *vaddr,
+ size_t size, int *ret)
+{
+ if (!dma_coherent_default_memory)
+ return 0;
+
+ return __dma_mmap_from_coherent(dma_coherent_default_memory, vma,
+ vaddr, size, ret);
+}
+
+/*
+ * Support for reserved memory regions defined in device tree
+ */
+#ifdef CONFIG_OF_RESERVED_MEM
+#include <linux/of.h>
+#include <linux/of_fdt.h>
+#include <linux/of_reserved_mem.h>
+
+static struct reserved_mem *dma_reserved_default_memory __initdata;
+
+static int rmem_dma_device_init(struct reserved_mem *rmem, struct device *dev)
+{
+ struct dma_coherent_mem *mem = rmem->priv;
+ int ret;
+
+ if (!mem) {
+ ret = dma_init_coherent_memory(rmem->base, rmem->base,
+ rmem->size,
+ DMA_MEMORY_EXCLUSIVE, &mem);
+ if (ret) {
+ pr_err("Reserved memory: failed to init DMA memory pool at %pa, size %ld MiB\n",
+ &rmem->base, (unsigned long)rmem->size / SZ_1M);
+ return ret;
+ }
+ }
+ mem->use_dev_dma_pfn_offset = true;
+ rmem->priv = mem;
+ dma_assign_coherent_memory(dev, mem);
+ return 0;
+}
+
+static void rmem_dma_device_release(struct reserved_mem *rmem,
+ struct device *dev)
+{
+ if (dev)
+ dev->dma_mem = NULL;
+}
+
+static const struct reserved_mem_ops rmem_dma_ops = {
+ .device_init = rmem_dma_device_init,
+ .device_release = rmem_dma_device_release,
+};
+
+static int __init rmem_dma_setup(struct reserved_mem *rmem)
+{
+ unsigned long node = rmem->fdt_node;
+
+ if (of_get_flat_dt_prop(node, "reusable", NULL))
+ return -EINVAL;
+
+#ifdef CONFIG_ARM
+ if (!of_get_flat_dt_prop(node, "no-map", NULL)) {
+ pr_err("Reserved memory: regions without no-map are not yet supported\n");
+ return -EINVAL;
+ }
+
+ if (of_get_flat_dt_prop(node, "linux,dma-default", NULL)) {
+ WARN(dma_reserved_default_memory,
+ "Reserved memory: region for default DMA coherent area is redefined\n");
+ dma_reserved_default_memory = rmem;
+ }
+#endif
+
+ rmem->ops = &rmem_dma_ops;
+ pr_info("Reserved memory: created DMA memory pool at %pa, size %ld MiB\n",
+ &rmem->base, (unsigned long)rmem->size / SZ_1M);
+ return 0;
+}
+
+static int __init dma_init_reserved_memory(void)
+{
+ const struct reserved_mem_ops *ops;
+ int ret;
+
+ if (!dma_reserved_default_memory)
+ return -ENOMEM;
+
+ ops = dma_reserved_default_memory->ops;
+
+ /*
+ * We rely on rmem_dma_device_init() does not propagate error of
+ * dma_assign_coherent_memory() for "NULL" device.
+ */
+ ret = ops->device_init(dma_reserved_default_memory, NULL);
+
+ if (!ret) {
+ dma_coherent_default_memory = dma_reserved_default_memory->priv;
+ pr_info("DMA: default coherent area is set\n");
+ }
+
+ return ret;
+}
+
+core_initcall(dma_init_reserved_memory);
+
+RESERVEDMEM_OF_DECLARE(dma, "shared-dma-pool", rmem_dma_setup);
+#endif
diff --git a/kernel/dma/contiguous.c b/kernel/dma/contiguous.c
new file mode 100644
index 000000000000..d987dcd1bd56
--- /dev/null
+++ b/kernel/dma/contiguous.c
@@ -0,0 +1,278 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * Contiguous Memory Allocator for DMA mapping framework
+ * Copyright (c) 2010-2011 by Samsung Electronics.
+ * Written by:
+ * Marek Szyprowski <m.szyprowski@samsung.com>
+ * Michal Nazarewicz <mina86@mina86.com>
+ */
+
+#define pr_fmt(fmt) "cma: " fmt
+
+#ifdef CONFIG_CMA_DEBUG
+#ifndef DEBUG
+# define DEBUG
+#endif
+#endif
+
+#include <asm/page.h>
+#include <asm/dma-contiguous.h>
+
+#include <linux/memblock.h>
+#include <linux/err.h>
+#include <linux/sizes.h>
+#include <linux/dma-contiguous.h>
+#include <linux/cma.h>
+
+#ifdef CONFIG_CMA_SIZE_MBYTES
+#define CMA_SIZE_MBYTES CONFIG_CMA_SIZE_MBYTES
+#else
+#define CMA_SIZE_MBYTES 0
+#endif
+
+struct cma *dma_contiguous_default_area;
+
+/*
+ * Default global CMA area size can be defined in kernel's .config.
+ * This is useful mainly for distro maintainers to create a kernel
+ * that works correctly for most supported systems.
+ * The size can be set in bytes or as a percentage of the total memory
+ * in the system.
+ *
+ * Users, who want to set the size of global CMA area for their system
+ * should use cma= kernel parameter.
+ */
+static const phys_addr_t size_bytes = (phys_addr_t)CMA_SIZE_MBYTES * SZ_1M;
+static phys_addr_t size_cmdline = -1;
+static phys_addr_t base_cmdline;
+static phys_addr_t limit_cmdline;
+
+static int __init early_cma(char *p)
+{
+ pr_debug("%s(%s)\n", __func__, p);
+ size_cmdline = memparse(p, &p);
+ if (*p != '@')
+ return 0;
+ base_cmdline = memparse(p + 1, &p);
+ if (*p != '-') {
+ limit_cmdline = base_cmdline + size_cmdline;
+ return 0;
+ }
+ limit_cmdline = memparse(p + 1, &p);
+
+ return 0;
+}
+early_param("cma", early_cma);
+
+#ifdef CONFIG_CMA_SIZE_PERCENTAGE
+
+static phys_addr_t __init __maybe_unused cma_early_percent_memory(void)
+{
+ struct memblock_region *reg;
+ unsigned long total_pages = 0;
+
+ /*
+ * We cannot use memblock_phys_mem_size() here, because
+ * memblock_analyze() has not been called yet.
+ */
+ for_each_memblock(memory, reg)
+ total_pages += memblock_region_memory_end_pfn(reg) -
+ memblock_region_memory_base_pfn(reg);
+
+ return (total_pages * CONFIG_CMA_SIZE_PERCENTAGE / 100) << PAGE_SHIFT;
+}
+
+#else
+
+static inline __maybe_unused phys_addr_t cma_early_percent_memory(void)
+{
+ return 0;
+}
+
+#endif
+
+/**
+ * dma_contiguous_reserve() - reserve area(s) for contiguous memory handling
+ * @limit: End address of the reserved memory (optional, 0 for any).
+ *
+ * This function reserves memory from early allocator. It should be
+ * called by arch specific code once the early allocator (memblock or bootmem)
+ * has been activated and all other subsystems have already allocated/reserved
+ * memory.
+ */
+void __init dma_contiguous_reserve(phys_addr_t limit)
+{
+ phys_addr_t selected_size = 0;
+ phys_addr_t selected_base = 0;
+ phys_addr_t selected_limit = limit;
+ bool fixed = false;
+
+ pr_debug("%s(limit %08lx)\n", __func__, (unsigned long)limit);
+
+ if (size_cmdline != -1) {
+ selected_size = size_cmdline;
+ selected_base = base_cmdline;
+ selected_limit = min_not_zero(limit_cmdline, limit);
+ if (base_cmdline + size_cmdline == limit_cmdline)
+ fixed = true;
+ } else {
+#ifdef CONFIG_CMA_SIZE_SEL_MBYTES
+ selected_size = size_bytes;
+#elif defined(CONFIG_CMA_SIZE_SEL_PERCENTAGE)
+ selected_size = cma_early_percent_memory();
+#elif defined(CONFIG_CMA_SIZE_SEL_MIN)
+ selected_size = min(size_bytes, cma_early_percent_memory());
+#elif defined(CONFIG_CMA_SIZE_SEL_MAX)
+ selected_size = max(size_bytes, cma_early_percent_memory());
+#endif
+ }
+
+ if (selected_size && !dma_contiguous_default_area) {
+ pr_debug("%s: reserving %ld MiB for global area\n", __func__,
+ (unsigned long)selected_size / SZ_1M);
+
+ dma_contiguous_reserve_area(selected_size, selected_base,
+ selected_limit,
+ &dma_contiguous_default_area,
+ fixed);
+ }
+}
+
+/**
+ * dma_contiguous_reserve_area() - reserve custom contiguous area
+ * @size: Size of the reserved area (in bytes),
+ * @base: Base address of the reserved area optional, use 0 for any
+ * @limit: End address of the reserved memory (optional, 0 for any).
+ * @res_cma: Pointer to store the created cma region.
+ * @fixed: hint about where to place the reserved area
+ *
+ * This function reserves memory from early allocator. It should be
+ * called by arch specific code once the early allocator (memblock or bootmem)
+ * has been activated and all other subsystems have already allocated/reserved
+ * memory. This function allows to create custom reserved areas for specific
+ * devices.
+ *
+ * If @fixed is true, reserve contiguous area at exactly @base. If false,
+ * reserve in range from @base to @limit.
+ */
+int __init dma_contiguous_reserve_area(phys_addr_t size, phys_addr_t base,
+ phys_addr_t limit, struct cma **res_cma,
+ bool fixed)
+{
+ int ret;
+
+ ret = cma_declare_contiguous(base, size, limit, 0, 0, fixed,
+ "reserved", res_cma);
+ if (ret)
+ return ret;
+
+ /* Architecture specific contiguous memory fixup. */
+ dma_contiguous_early_fixup(cma_get_base(*res_cma),
+ cma_get_size(*res_cma));
+
+ return 0;
+}
+
+/**
+ * dma_alloc_from_contiguous() - allocate pages from contiguous area
+ * @dev: Pointer to device for which the allocation is performed.
+ * @count: Requested number of pages.
+ * @align: Requested alignment of pages (in PAGE_SIZE order).
+ * @gfp_mask: GFP flags to use for this allocation.
+ *
+ * This function allocates memory buffer for specified device. It uses
+ * device specific contiguous memory area if available or the default
+ * global one. Requires architecture specific dev_get_cma_area() helper
+ * function.
+ */
+struct page *dma_alloc_from_contiguous(struct device *dev, size_t count,
+ unsigned int align, gfp_t gfp_mask)
+{
+ if (align > CONFIG_CMA_ALIGNMENT)
+ align = CONFIG_CMA_ALIGNMENT;
+
+ return cma_alloc(dev_get_cma_area(dev), count, align, gfp_mask);
+}
+
+/**
+ * dma_release_from_contiguous() - release allocated pages
+ * @dev: Pointer to device for which the pages were allocated.
+ * @pages: Allocated pages.
+ * @count: Number of allocated pages.
+ *
+ * This function releases memory allocated by dma_alloc_from_contiguous().
+ * It returns false when provided pages do not belong to contiguous area and
+ * true otherwise.
+ */
+bool dma_release_from_contiguous(struct device *dev, struct page *pages,
+ int count)
+{
+ return cma_release(dev_get_cma_area(dev), pages, count);
+}
+
+/*
+ * Support for reserved memory regions defined in device tree
+ */
+#ifdef CONFIG_OF_RESERVED_MEM
+#include <linux/of.h>
+#include <linux/of_fdt.h>
+#include <linux/of_reserved_mem.h>
+
+#undef pr_fmt
+#define pr_fmt(fmt) fmt
+
+static int rmem_cma_device_init(struct reserved_mem *rmem, struct device *dev)
+{
+ dev_set_cma_area(dev, rmem->priv);
+ return 0;
+}
+
+static void rmem_cma_device_release(struct reserved_mem *rmem,
+ struct device *dev)
+{
+ dev_set_cma_area(dev, NULL);
+}
+
+static const struct reserved_mem_ops rmem_cma_ops = {
+ .device_init = rmem_cma_device_init,
+ .device_release = rmem_cma_device_release,
+};
+
+static int __init rmem_cma_setup(struct reserved_mem *rmem)
+{
+ phys_addr_t align = PAGE_SIZE << max(MAX_ORDER - 1, pageblock_order);
+ phys_addr_t mask = align - 1;
+ unsigned long node = rmem->fdt_node;
+ struct cma *cma;
+ int err;
+
+ if (!of_get_flat_dt_prop(node, "reusable", NULL) ||
+ of_get_flat_dt_prop(node, "no-map", NULL))
+ return -EINVAL;
+
+ if ((rmem->base & mask) || (rmem->size & mask)) {
+ pr_err("Reserved memory: incorrect alignment of CMA region\n");
+ return -EINVAL;
+ }
+
+ err = cma_init_reserved_mem(rmem->base, rmem->size, 0, rmem->name, &cma);
+ if (err) {
+ pr_err("Reserved memory: unable to setup CMA region\n");
+ return err;
+ }
+ /* Architecture specific contiguous memory fixup. */
+ dma_contiguous_early_fixup(rmem->base, rmem->size);
+
+ if (of_get_flat_dt_prop(node, "linux,cma-default", NULL))
+ dma_contiguous_set_default(cma);
+
+ rmem->ops = &rmem_cma_ops;
+ rmem->priv = cma;
+
+ pr_info("Reserved memory: created CMA memory pool at %pa, size %ld MiB\n",
+ &rmem->base, (unsigned long)rmem->size / SZ_1M);
+
+ return 0;
+}
+RESERVEDMEM_OF_DECLARE(cma, "shared-dma-pool", rmem_cma_setup);
+#endif
diff --git a/kernel/dma/debug.c b/kernel/dma/debug.c
new file mode 100644
index 000000000000..c007d25bee09
--- /dev/null
+++ b/kernel/dma/debug.c
@@ -0,0 +1,1773 @@
+/*
+ * Copyright (C) 2008 Advanced Micro Devices, Inc.
+ *
+ * Author: Joerg Roedel <joerg.roedel@amd.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 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 for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+ */
+
+#include <linux/sched/task_stack.h>
+#include <linux/scatterlist.h>
+#include <linux/dma-mapping.h>
+#include <linux/sched/task.h>
+#include <linux/stacktrace.h>
+#include <linux/dma-debug.h>
+#include <linux/spinlock.h>
+#include <linux/vmalloc.h>
+#include <linux/debugfs.h>
+#include <linux/uaccess.h>
+#include <linux/export.h>
+#include <linux/device.h>
+#include <linux/types.h>
+#include <linux/sched.h>
+#include <linux/ctype.h>
+#include <linux/list.h>
+#include <linux/slab.h>
+
+#include <asm/sections.h>
+
+#define HASH_SIZE 1024ULL
+#define HASH_FN_SHIFT 13
+#define HASH_FN_MASK (HASH_SIZE - 1)
+
+/* allow architectures to override this if absolutely required */
+#ifndef PREALLOC_DMA_DEBUG_ENTRIES
+#define PREALLOC_DMA_DEBUG_ENTRIES (1 << 16)
+#endif
+
+enum {
+ dma_debug_single,
+ dma_debug_page,
+ dma_debug_sg,
+ dma_debug_coherent,
+ dma_debug_resource,
+};
+
+enum map_err_types {
+ MAP_ERR_CHECK_NOT_APPLICABLE,
+ MAP_ERR_NOT_CHECKED,
+ MAP_ERR_CHECKED,
+};
+
+#define DMA_DEBUG_STACKTRACE_ENTRIES 5
+
+/**
+ * struct dma_debug_entry - track a dma_map* or dma_alloc_coherent mapping
+ * @list: node on pre-allocated free_entries list
+ * @dev: 'dev' argument to dma_map_{page|single|sg} or dma_alloc_coherent
+ * @type: single, page, sg, coherent
+ * @pfn: page frame of the start address
+ * @offset: offset of mapping relative to pfn
+ * @size: length of the mapping
+ * @direction: enum dma_data_direction
+ * @sg_call_ents: 'nents' from dma_map_sg
+ * @sg_mapped_ents: 'mapped_ents' from dma_map_sg
+ * @map_err_type: track whether dma_mapping_error() was checked
+ * @stacktrace: support backtraces when a violation is detected
+ */
+struct dma_debug_entry {
+ struct list_head list;
+ struct device *dev;
+ int type;
+ unsigned long pfn;
+ size_t offset;
+ u64 dev_addr;
+ u64 size;
+ int direction;
+ int sg_call_ents;
+ int sg_mapped_ents;
+ enum map_err_types map_err_type;
+#ifdef CONFIG_STACKTRACE
+ struct stack_trace stacktrace;
+ unsigned long st_entries[DMA_DEBUG_STACKTRACE_ENTRIES];
+#endif
+};
+
+typedef bool (*match_fn)(struct dma_debug_entry *, struct dma_debug_entry *);
+
+struct hash_bucket {
+ struct list_head list;
+ spinlock_t lock;
+} ____cacheline_aligned_in_smp;
+
+/* Hash list to save the allocated dma addresses */
+static struct hash_bucket dma_entry_hash[HASH_SIZE];
+/* List of pre-allocated dma_debug_entry's */
+static LIST_HEAD(free_entries);
+/* Lock for the list above */
+static DEFINE_SPINLOCK(free_entries_lock);
+
+/* Global disable flag - will be set in case of an error */
+static bool global_disable __read_mostly;
+
+/* Early initialization disable flag, set at the end of dma_debug_init */
+static bool dma_debug_initialized __read_mostly;
+
+static inline bool dma_debug_disabled(void)
+{
+ return global_disable || !dma_debug_initialized;
+}
+
+/* Global error count */
+static u32 error_count;
+
+/* Global error show enable*/
+static u32 show_all_errors __read_mostly;
+/* Number of errors to show */
+static u32 show_num_errors = 1;
+
+static u32 num_free_entries;
+static u32 min_free_entries;
+static u32 nr_total_entries;
+
+/* number of preallocated entries requested by kernel cmdline */
+static u32 nr_prealloc_entries = PREALLOC_DMA_DEBUG_ENTRIES;
+
+/* debugfs dentry's for the stuff above */
+static struct dentry *dma_debug_dent __read_mostly;
+static struct dentry *global_disable_dent __read_mostly;
+static struct dentry *error_count_dent __read_mostly;
+static struct dentry *show_all_errors_dent __read_mostly;
+static struct dentry *show_num_errors_dent __read_mostly;
+static struct dentry *num_free_entries_dent __read_mostly;
+static struct dentry *min_free_entries_dent __read_mostly;
+static struct dentry *filter_dent __read_mostly;
+
+/* per-driver filter related state */
+
+#define NAME_MAX_LEN 64
+
+static char current_driver_name[NAME_MAX_LEN] __read_mostly;
+static struct device_driver *current_driver __read_mostly;
+
+static DEFINE_RWLOCK(driver_name_lock);
+
+static const char *const maperr2str[] = {
+ [MAP_ERR_CHECK_NOT_APPLICABLE] = "dma map error check not applicable",
+ [MAP_ERR_NOT_CHECKED] = "dma map error not checked",
+ [MAP_ERR_CHECKED] = "dma map error checked",
+};
+
+static const char *type2name[5] = { "single", "page",
+ "scather-gather", "coherent",
+ "resource" };
+
+static const char *dir2name[4] = { "DMA_BIDIRECTIONAL", "DMA_TO_DEVICE",
+ "DMA_FROM_DEVICE", "DMA_NONE" };
+
+/*
+ * The access to some variables in this macro is racy. We can't use atomic_t
+ * here because all these variables are exported to debugfs. Some of them even
+ * writeable. This is also the reason why a lock won't help much. But anyway,
+ * the races are no big deal. Here is why:
+ *
+ * error_count: the addition is racy, but the worst thing that can happen is
+ * that we don't count some errors
+ * show_num_errors: the subtraction is racy. Also no big deal because in
+ * worst case this will result in one warning more in the
+ * system log than the user configured. This variable is
+ * writeable via debugfs.
+ */
+static inline void dump_entry_trace(struct dma_debug_entry *entry)
+{
+#ifdef CONFIG_STACKTRACE
+ if (entry) {
+ pr_warning("Mapped at:\n");
+ print_stack_trace(&entry->stacktrace, 0);
+ }
+#endif
+}
+
+static bool driver_filter(struct device *dev)
+{
+ struct device_driver *drv;
+ unsigned long flags;
+ bool ret;
+
+ /* driver filter off */
+ if (likely(!current_driver_name[0]))
+ return true;
+
+ /* driver filter on and initialized */
+ if (current_driver && dev && dev->driver == current_driver)
+ return true;
+
+ /* driver filter on, but we can't filter on a NULL device... */
+ if (!dev)
+ return false;
+
+ if (current_driver || !current_driver_name[0])
+ return false;
+
+ /* driver filter on but not yet initialized */
+ drv = dev->driver;
+ if (!drv)
+ return false;
+
+ /* lock to protect against change of current_driver_name */
+ read_lock_irqsave(&driver_name_lock, flags);
+
+ ret = false;
+ if (drv->name &&
+ strncmp(current_driver_name, drv->name, NAME_MAX_LEN - 1) == 0) {
+ current_driver = drv;
+ ret = true;
+ }
+
+ read_unlock_irqrestore(&driver_name_lock, flags);
+
+ return ret;
+}
+
+#define err_printk(dev, entry, format, arg...) do { \
+ error_count += 1; \
+ if (driver_filter(dev) && \
+ (show_all_errors || show_num_errors > 0)) { \
+ WARN(1, "%s %s: " format, \
+ dev ? dev_driver_string(dev) : "NULL", \
+ dev ? dev_name(dev) : "NULL", ## arg); \
+ dump_entry_trace(entry); \
+ } \
+ if (!show_all_errors && show_num_errors > 0) \
+ show_num_errors -= 1; \
+ } while (0);
+
+/*
+ * Hash related functions
+ *
+ * Every DMA-API request is saved into a struct dma_debug_entry. To
+ * have quick access to these structs they are stored into a hash.
+ */
+static int hash_fn(struct dma_debug_entry *entry)
+{
+ /*
+ * Hash function is based on the dma address.
+ * We use bits 20-27 here as the index into the hash
+ */
+ return (entry->dev_addr >> HASH_FN_SHIFT) & HASH_FN_MASK;
+}
+
+/*
+ * Request exclusive access to a hash bucket for a given dma_debug_entry.
+ */
+static struct hash_bucket *get_hash_bucket(struct dma_debug_entry *entry,
+ unsigned long *flags)
+ __acquires(&dma_entry_hash[idx].lock)
+{
+ int idx = hash_fn(entry);
+ unsigned long __flags;
+
+ spin_lock_irqsave(&dma_entry_hash[idx].lock, __flags);
+ *flags = __flags;
+ return &dma_entry_hash[idx];
+}
+
+/*
+ * Give up exclusive access to the hash bucket
+ */
+static void put_hash_bucket(struct hash_bucket *bucket,
+ unsigned long *flags)
+ __releases(&bucket->lock)
+{
+ unsigned long __flags = *flags;
+
+ spin_unlock_irqrestore(&bucket->lock, __flags);
+}
+
+static bool exact_match(struct dma_debug_entry *a, struct dma_debug_entry *b)
+{
+ return ((a->dev_addr == b->dev_addr) &&
+ (a->dev == b->dev)) ? true : false;
+}
+
+static bool containing_match(struct dma_debug_entry *a,
+ struct dma_debug_entry *b)
+{
+ if (a->dev != b->dev)
+ return false;
+
+ if ((b->dev_addr <= a->dev_addr) &&
+ ((b->dev_addr + b->size) >= (a->dev_addr + a->size)))
+ return true;
+
+ return false;
+}
+
+/*
+ * Search a given entry in the hash bucket list
+ */
+static struct dma_debug_entry *__hash_bucket_find(struct hash_bucket *bucket,
+ struct dma_debug_entry *ref,
+ match_fn match)
+{
+ struct dma_debug_entry *entry, *ret = NULL;
+ int matches = 0, match_lvl, last_lvl = -1;
+
+ list_for_each_entry(entry, &bucket->list, list) {
+ if (!match(ref, entry))
+ continue;
+
+ /*
+ * Some drivers map the same physical address multiple
+ * times. Without a hardware IOMMU this results in the
+ * same device addresses being put into the dma-debug
+ * hash multiple times too. This can result in false
+ * positives being reported. Therefore we implement a
+ * best-fit algorithm here which returns the entry from
+ * the hash which fits best to the reference value
+ * instead of the first-fit.
+ */
+ matches += 1;
+ match_lvl = 0;
+ entry->size == ref->size ? ++match_lvl : 0;
+ entry->type == ref->type ? ++match_lvl : 0;
+ entry->direction == ref->direction ? ++match_lvl : 0;
+ entry->sg_call_ents == ref->sg_call_ents ? ++match_lvl : 0;
+
+ if (match_lvl == 4) {
+ /* perfect-fit - return the result */
+ return entry;
+ } else if (match_lvl > last_lvl) {
+ /*
+ * We found an entry that fits better then the
+ * previous one or it is the 1st match.
+ */
+ last_lvl = match_lvl;
+ ret = entry;
+ }
+ }
+
+ /*
+ * If we have multiple matches but no perfect-fit, just return
+ * NULL.
+ */
+ ret = (matches == 1) ? ret : NULL;
+
+ return ret;
+}
+
+static struct dma_debug_entry *bucket_find_exact(struct hash_bucket *bucket,
+ struct dma_debug_entry *ref)
+{
+ return __hash_bucket_find(bucket, ref, exact_match);
+}
+
+static struct dma_debug_entry *bucket_find_contain(struct hash_bucket **bucket,
+ struct dma_debug_entry *ref,
+ unsigned long *flags)
+{
+
+ unsigned int max_range = dma_get_max_seg_size(ref->dev);
+ struct dma_debug_entry *entry, index = *ref;
+ unsigned int range = 0;
+
+ while (range <= max_range) {
+ entry = __hash_bucket_find(*bucket, ref, containing_match);
+
+ if (entry)
+ return entry;
+
+ /*
+ * Nothing found, go back a hash bucket
+ */
+ put_hash_bucket(*bucket, flags);
+ range += (1 << HASH_FN_SHIFT);
+ index.dev_addr -= (1 << HASH_FN_SHIFT);
+ *bucket = get_hash_bucket(&index, flags);
+ }
+
+ return NULL;
+}
+
+/*
+ * Add an entry to a hash bucket
+ */
+static void hash_bucket_add(struct hash_bucket *bucket,
+ struct dma_debug_entry *entry)
+{
+ list_add_tail(&entry->list, &bucket->list);
+}
+
+/*
+ * Remove entry from a hash bucket list
+ */
+static void hash_bucket_del(struct dma_debug_entry *entry)
+{
+ list_del(&entry->list);
+}
+
+static unsigned long long phys_addr(struct dma_debug_entry *entry)
+{
+ if (entry->type == dma_debug_resource)
+ return __pfn_to_phys(entry->pfn) + entry->offset;
+
+ return page_to_phys(pfn_to_page(entry->pfn)) + entry->offset;
+}
+
+/*
+ * Dump mapping entries for debugging purposes
+ */
+void debug_dma_dump_mappings(struct device *dev)
+{
+ int idx;
+
+ for (idx = 0; idx < HASH_SIZE; idx++) {
+ struct hash_bucket *bucket = &dma_entry_hash[idx];
+ struct dma_debug_entry *entry;
+ unsigned long flags;
+
+ spin_lock_irqsave(&bucket->lock, flags);
+
+ list_for_each_entry(entry, &bucket->list, list) {
+ if (!dev || dev == entry->dev) {
+ dev_info(entry->dev,
+ "%s idx %d P=%Lx N=%lx D=%Lx L=%Lx %s %s\n",
+ type2name[entry->type], idx,
+ phys_addr(entry), entry->pfn,
+ entry->dev_addr, entry->size,
+ dir2name[entry->direction],
+ maperr2str[entry->map_err_type]);
+ }
+ }
+
+ spin_unlock_irqrestore(&bucket->lock, flags);
+ }
+}
+
+/*
+ * For each mapping (initial cacheline in the case of
+ * dma_alloc_coherent/dma_map_page, initial cacheline in each page of a
+ * scatterlist, or the cacheline specified in dma_map_single) insert
+ * into this tree using the cacheline as the key. At
+ * dma_unmap_{single|sg|page} or dma_free_coherent delete the entry. If
+ * the entry already exists at insertion time add a tag as a reference
+ * count for the overlapping mappings. For now, the overlap tracking
+ * just ensures that 'unmaps' balance 'maps' before marking the
+ * cacheline idle, but we should also be flagging overlaps as an API
+ * violation.
+ *
+ * Memory usage is mostly constrained by the maximum number of available
+ * dma-debug entries in that we need a free dma_debug_entry before
+ * inserting into the tree. In the case of dma_map_page and
+ * dma_alloc_coherent there is only one dma_debug_entry and one
+ * dma_active_cacheline entry to track per event. dma_map_sg(), on the
+ * other hand, consumes a single dma_debug_entry, but inserts 'nents'
+ * entries into the tree.
+ *
+ * At any time debug_dma_assert_idle() can be called to trigger a
+ * warning if any cachelines in the given page are in the active set.
+ */
+static RADIX_TREE(dma_active_cacheline, GFP_NOWAIT);
+static DEFINE_SPINLOCK(radix_lock);
+#define ACTIVE_CACHELINE_MAX_OVERLAP ((1 << RADIX_TREE_MAX_TAGS) - 1)
+#define CACHELINE_PER_PAGE_SHIFT (PAGE_SHIFT - L1_CACHE_SHIFT)
+#define CACHELINES_PER_PAGE (1 << CACHELINE_PER_PAGE_SHIFT)
+
+static phys_addr_t to_cacheline_number(struct dma_debug_entry *entry)
+{
+ return (entry->pfn << CACHELINE_PER_PAGE_SHIFT) +
+ (entry->offset >> L1_CACHE_SHIFT);
+}
+
+static int active_cacheline_read_overlap(phys_addr_t cln)
+{
+ int overlap = 0, i;
+
+ for (i = RADIX_TREE_MAX_TAGS - 1; i >= 0; i--)
+ if (radix_tree_tag_get(&dma_active_cacheline, cln, i))
+ overlap |= 1 << i;
+ return overlap;
+}
+
+static int active_cacheline_set_overlap(phys_addr_t cln, int overlap)
+{
+ int i;
+
+ if (overlap > ACTIVE_CACHELINE_MAX_OVERLAP || overlap < 0)
+ return overlap;
+
+ for (i = RADIX_TREE_MAX_TAGS - 1; i >= 0; i--)
+ if (overlap & 1 << i)
+ radix_tree_tag_set(&dma_active_cacheline, cln, i);
+ else
+ radix_tree_tag_clear(&dma_active_cacheline, cln, i);
+
+ return overlap;
+}
+
+static void active_cacheline_inc_overlap(phys_addr_t cln)
+{
+ int overlap = active_cacheline_read_overlap(cln);
+
+ overlap = active_cacheline_set_overlap(cln, ++overlap);
+
+ /* If we overflowed the overlap counter then we're potentially
+ * leaking dma-mappings. Otherwise, if maps and unmaps are
+ * balanced then this overflow may cause false negatives in
+ * debug_dma_assert_idle() as the cacheline may be marked idle
+ * prematurely.
+ */
+ WARN_ONCE(overlap > ACTIVE_CACHELINE_MAX_OVERLAP,
+ "DMA-API: exceeded %d overlapping mappings of cacheline %pa\n",
+ ACTIVE_CACHELINE_MAX_OVERLAP, &cln);
+}
+
+static int active_cacheline_dec_overlap(phys_addr_t cln)
+{
+ int overlap = active_cacheline_read_overlap(cln);
+
+ return active_cacheline_set_overlap(cln, --overlap);
+}
+
+static int active_cacheline_insert(struct dma_debug_entry *entry)
+{
+ phys_addr_t cln = to_cacheline_number(entry);
+ unsigned long flags;
+ int rc;
+
+ /* If the device is not writing memory then we don't have any
+ * concerns about the cpu consuming stale data. This mitigates
+ * legitimate usages of overlapping mappings.
+ */
+ if (entry->direction == DMA_TO_DEVICE)
+ return 0;
+
+ spin_lock_irqsave(&radix_lock, flags);
+ rc = radix_tree_insert(&dma_active_cacheline, cln, entry);
+ if (rc == -EEXIST)
+ active_cacheline_inc_overlap(cln);
+ spin_unlock_irqrestore(&radix_lock, flags);
+
+ return rc;
+}
+
+static void active_cacheline_remove(struct dma_debug_entry *entry)
+{
+ phys_addr_t cln = to_cacheline_number(entry);
+ unsigned long flags;
+
+ /* ...mirror the insert case */
+ if (entry->direction == DMA_TO_DEVICE)
+ return;
+
+ spin_lock_irqsave(&radix_lock, flags);
+ /* since we are counting overlaps the final put of the
+ * cacheline will occur when the overlap count is 0.
+ * active_cacheline_dec_overlap() returns -1 in that case
+ */
+ if (active_cacheline_dec_overlap(cln) < 0)
+ radix_tree_delete(&dma_active_cacheline, cln);
+ spin_unlock_irqrestore(&radix_lock, flags);
+}
+
+/**
+ * debug_dma_assert_idle() - assert that a page is not undergoing dma
+ * @page: page to lookup in the dma_active_cacheline tree
+ *
+ * Place a call to this routine in cases where the cpu touching the page
+ * before the dma completes (page is dma_unmapped) will lead to data
+ * corruption.
+ */
+void debug_dma_assert_idle(struct page *page)
+{
+ static struct dma_debug_entry *ents[CACHELINES_PER_PAGE];
+ struct dma_debug_entry *entry = NULL;
+ void **results = (void **) &ents;
+ unsigned int nents, i;
+ unsigned long flags;
+ phys_addr_t cln;
+
+ if (dma_debug_disabled())
+ return;
+
+ if (!page)
+ return;
+
+ cln = (phys_addr_t) page_to_pfn(page) << CACHELINE_PER_PAGE_SHIFT;
+ spin_lock_irqsave(&radix_lock, flags);
+ nents = radix_tree_gang_lookup(&dma_active_cacheline, results, cln,
+ CACHELINES_PER_PAGE);
+ for (i = 0; i < nents; i++) {
+ phys_addr_t ent_cln = to_cacheline_number(ents[i]);
+
+ if (ent_cln == cln) {
+ entry = ents[i];
+ break;
+ } else if (ent_cln >= cln + CACHELINES_PER_PAGE)
+ break;
+ }
+ spin_unlock_irqrestore(&radix_lock, flags);
+
+ if (!entry)
+ return;
+
+ cln = to_cacheline_number(entry);
+ err_printk(entry->dev, entry,
+ "DMA-API: cpu touching an active dma mapped cacheline [cln=%pa]\n",
+ &cln);
+}
+
+/*
+ * Wrapper function for adding an entry to the hash.
+ * This function takes care of locking itself.
+ */
+static void add_dma_entry(struct dma_debug_entry *entry)
+{
+ struct hash_bucket *bucket;
+ unsigned long flags;
+ int rc;
+
+ bucket = get_hash_bucket(entry, &flags);
+ hash_bucket_add(bucket, entry);
+ put_hash_bucket(bucket, &flags);
+
+ rc = active_cacheline_insert(entry);
+ if (rc == -ENOMEM) {
+ pr_err("DMA-API: cacheline tracking ENOMEM, dma-debug disabled\n");
+ global_disable = true;
+ }
+
+ /* TODO: report -EEXIST errors here as overlapping mappings are
+ * not supported by the DMA API
+ */
+}
+
+static struct dma_debug_entry *__dma_entry_alloc(void)
+{
+ struct dma_debug_entry *entry;
+
+ entry = list_entry(free_entries.next, struct dma_debug_entry, list);
+ list_del(&entry->list);
+ memset(entry, 0, sizeof(*entry));
+
+ num_free_entries -= 1;
+ if (num_free_entries < min_free_entries)
+ min_free_entries = num_free_entries;
+
+ return entry;
+}
+
+/* struct dma_entry allocator
+ *
+ * The next two functions implement the allocator for
+ * struct dma_debug_entries.
+ */
+static struct dma_debug_entry *dma_entry_alloc(void)
+{
+ struct dma_debug_entry *entry;
+ unsigned long flags;
+
+ spin_lock_irqsave(&free_entries_lock, flags);
+
+ if (list_empty(&free_entries)) {
+ global_disable = true;
+ spin_unlock_irqrestore(&free_entries_lock, flags);
+ pr_err("DMA-API: debugging out of memory - disabling\n");
+ return NULL;
+ }
+
+ entry = __dma_entry_alloc();
+
+ spin_unlock_irqrestore(&free_entries_lock, flags);
+
+#ifdef CONFIG_STACKTRACE
+ entry->stacktrace.max_entries = DMA_DEBUG_STACKTRACE_ENTRIES;
+ entry->stacktrace.entries = entry->st_entries;
+ entry->stacktrace.skip = 2;
+ save_stack_trace(&entry->stacktrace);
+#endif
+
+ return entry;
+}
+
+static void dma_entry_free(struct dma_debug_entry *entry)
+{
+ unsigned long flags;
+
+ active_cacheline_remove(entry);
+
+ /*
+ * add to beginning of the list - this way the entries are
+ * more likely cache hot when they are reallocated.
+ */
+ spin_lock_irqsave(&free_entries_lock, flags);
+ list_add(&entry->list, &free_entries);
+ num_free_entries += 1;
+ spin_unlock_irqrestore(&free_entries_lock, flags);
+}
+
+int dma_debug_resize_entries(u32 num_entries)
+{
+ int i, delta, ret = 0;
+ unsigned long flags;
+ struct dma_debug_entry *entry;
+ LIST_HEAD(tmp);
+
+ spin_lock_irqsave(&free_entries_lock, flags);
+
+ if (nr_total_entries < num_entries) {
+ delta = num_entries - nr_total_entries;
+
+ spin_unlock_irqrestore(&free_entries_lock, flags);
+
+ for (i = 0; i < delta; i++) {
+ entry = kzalloc(sizeof(*entry), GFP_KERNEL);
+ if (!entry)
+ break;
+
+ list_add_tail(&entry->list, &tmp);
+ }
+
+ spin_lock_irqsave(&free_entries_lock, flags);
+
+ list_splice(&tmp, &free_entries);
+ nr_total_entries += i;
+ num_free_entries += i;
+ } else {
+ delta = nr_total_entries - num_entries;
+
+ for (i = 0; i < delta && !list_empty(&free_entries); i++) {
+ entry = __dma_entry_alloc();
+ kfree(entry);
+ }
+
+ nr_total_entries -= i;
+ }
+
+ if (nr_total_entries != num_entries)
+ ret = 1;
+
+ spin_unlock_irqrestore(&free_entries_lock, flags);
+
+ return ret;
+}
+
+/*
+ * DMA-API debugging init code
+ *
+ * The init code does two things:
+ * 1. Initialize core data structures
+ * 2. Preallocate a given number of dma_debug_entry structs
+ */
+
+static int prealloc_memory(u32 num_entries)
+{
+ struct dma_debug_entry *entry, *next_entry;
+ int i;
+
+ for (i = 0; i < num_entries; ++i) {
+ entry = kzalloc(sizeof(*entry), GFP_KERNEL);
+ if (!entry)
+ goto out_err;
+
+ list_add_tail(&entry->list, &free_entries);
+ }
+
+ num_free_entries = num_entries;
+ min_free_entries = num_entries;
+
+ pr_info("DMA-API: preallocated %d debug entries\n", num_entries);
+
+ return 0;
+
+out_err:
+
+ list_for_each_entry_safe(entry, next_entry, &free_entries, list) {
+ list_del(&entry->list);
+ kfree(entry);
+ }
+
+ return -ENOMEM;
+}
+
+static ssize_t filter_read(struct file *file, char __user *user_buf,
+ size_t count, loff_t *ppos)
+{
+ char buf[NAME_MAX_LEN + 1];
+ unsigned long flags;
+ int len;
+
+ if (!current_driver_name[0])
+ return 0;
+
+ /*
+ * We can't copy to userspace directly because current_driver_name can
+ * only be read under the driver_name_lock with irqs disabled. So
+ * create a temporary copy first.
+ */
+ read_lock_irqsave(&driver_name_lock, flags);
+ len = scnprintf(buf, NAME_MAX_LEN + 1, "%s\n", current_driver_name);
+ read_unlock_irqrestore(&driver_name_lock, flags);
+
+ return simple_read_from_buffer(user_buf, count, ppos, buf, len);
+}
+
+static ssize_t filter_write(struct file *file, const char __user *userbuf,
+ size_t count, loff_t *ppos)
+{
+ char buf[NAME_MAX_LEN];
+ unsigned long flags;
+ size_t len;
+ int i;
+
+ /*
+ * We can't copy from userspace directly. Access to
+ * current_driver_name is protected with a write_lock with irqs
+ * disabled. Since copy_from_user can fault and may sleep we
+ * need to copy to temporary buffer first
+ */
+ len = min(count, (size_t)(NAME_MAX_LEN - 1));
+ if (copy_from_user(buf, userbuf, len))
+ return -EFAULT;
+
+ buf[len] = 0;
+
+ write_lock_irqsave(&driver_name_lock, flags);
+
+ /*
+ * Now handle the string we got from userspace very carefully.
+ * The rules are:
+ * - only use the first token we got
+ * - token delimiter is everything looking like a space
+ * character (' ', '\n', '\t' ...)
+ *
+ */
+ if (!isalnum(buf[0])) {
+ /*
+ * If the first character userspace gave us is not
+ * alphanumerical then assume the filter should be
+ * switched off.
+ */
+ if (current_driver_name[0])
+ pr_info("DMA-API: switching off dma-debug driver filter\n");
+ current_driver_name[0] = 0;
+ current_driver = NULL;
+ goto out_unlock;
+ }
+
+ /*
+ * Now parse out the first token and use it as the name for the
+ * driver to filter for.
+ */
+ for (i = 0; i < NAME_MAX_LEN - 1; ++i) {
+ current_driver_name[i] = buf[i];
+ if (isspace(buf[i]) || buf[i] == ' ' || buf[i] == 0)
+ break;
+ }
+ current_driver_name[i] = 0;
+ current_driver = NULL;
+
+ pr_info("DMA-API: enable driver filter for driver [%s]\n",
+ current_driver_name);
+
+out_unlock:
+ write_unlock_irqrestore(&driver_name_lock, flags);
+
+ return count;
+}
+
+static const struct file_operations filter_fops = {
+ .read = filter_read,
+ .write = filter_write,
+ .llseek = default_llseek,
+};
+
+static int dma_debug_fs_init(void)
+{
+ dma_debug_dent = debugfs_create_dir("dma-api", NULL);
+ if (!dma_debug_dent) {
+ pr_err("DMA-API: can not create debugfs directory\n");
+ return -ENOMEM;
+ }
+
+ global_disable_dent = debugfs_create_bool("disabled", 0444,
+ dma_debug_dent,
+ &global_disable);
+ if (!global_disable_dent)
+ goto out_err;
+
+ error_count_dent = debugfs_create_u32("error_count", 0444,
+ dma_debug_dent, &error_count);
+ if (!error_count_dent)
+ goto out_err;
+
+ show_all_errors_dent = debugfs_create_u32("all_errors", 0644,
+ dma_debug_dent,
+ &show_all_errors);
+ if (!show_all_errors_dent)
+ goto out_err;
+
+ show_num_errors_dent = debugfs_create_u32("num_errors", 0644,
+ dma_debug_dent,
+ &show_num_errors);
+ if (!show_num_errors_dent)
+ goto out_err;
+
+ num_free_entries_dent = debugfs_create_u32("num_free_entries", 0444,
+ dma_debug_dent,
+ &num_free_entries);
+ if (!num_free_entries_dent)
+ goto out_err;
+
+ min_free_entries_dent = debugfs_create_u32("min_free_entries", 0444,
+ dma_debug_dent,
+ &min_free_entries);
+ if (!min_free_entries_dent)
+ goto out_err;
+
+ filter_dent = debugfs_create_file("driver_filter", 0644,
+ dma_debug_dent, NULL, &filter_fops);
+ if (!filter_dent)
+ goto out_err;
+
+ return 0;
+
+out_err:
+ debugfs_remove_recursive(dma_debug_dent);
+
+ return -ENOMEM;
+}
+
+static int device_dma_allocations(struct device *dev, struct dma_debug_entry **out_entry)
+{
+ struct dma_debug_entry *entry;
+ unsigned long flags;
+ int count = 0, i;
+
+ for (i = 0; i < HASH_SIZE; ++i) {
+ spin_lock_irqsave(&dma_entry_hash[i].lock, flags);
+ list_for_each_entry(entry, &dma_entry_hash[i].list, list) {
+ if (entry->dev == dev) {
+ count += 1;
+ *out_entry = entry;
+ }
+ }
+ spin_unlock_irqrestore(&dma_entry_hash[i].lock, flags);
+ }
+
+ return count;
+}
+
+static int dma_debug_device_change(struct notifier_block *nb, unsigned long action, void *data)
+{
+ struct device *dev = data;
+ struct dma_debug_entry *uninitialized_var(entry);
+ int count;
+
+ if (dma_debug_disabled())
+ return 0;
+
+ switch (action) {
+ case BUS_NOTIFY_UNBOUND_DRIVER:
+ count = device_dma_allocations(dev, &entry);
+ if (count == 0)
+ break;
+ err_printk(dev, entry, "DMA-API: device driver has pending "
+ "DMA allocations while released from device "
+ "[count=%d]\n"
+ "One of leaked entries details: "
+ "[device address=0x%016llx] [size=%llu bytes] "
+ "[mapped with %s] [mapped as %s]\n",
+ count, entry->dev_addr, entry->size,
+ dir2name[entry->direction], type2name[entry->type]);
+ break;
+ default:
+ break;
+ }
+
+ return 0;
+}
+
+void dma_debug_add_bus(struct bus_type *bus)
+{
+ struct notifier_block *nb;
+
+ if (dma_debug_disabled())
+ return;
+
+ nb = kzalloc(sizeof(struct notifier_block), GFP_KERNEL);
+ if (nb == NULL) {
+ pr_err("dma_debug_add_bus: out of memory\n");
+ return;
+ }
+
+ nb->notifier_call = dma_debug_device_change;
+
+ bus_register_notifier(bus, nb);
+}
+
+static int dma_debug_init(void)
+{
+ int i;
+
+ /* Do not use dma_debug_initialized here, since we really want to be
+ * called to set dma_debug_initialized
+ */
+ if (global_disable)
+ return 0;
+
+ for (i = 0; i < HASH_SIZE; ++i) {
+ INIT_LIST_HEAD(&dma_entry_hash[i].list);
+ spin_lock_init(&dma_entry_hash[i].lock);
+ }
+
+ if (dma_debug_fs_init() != 0) {
+ pr_err("DMA-API: error creating debugfs entries - disabling\n");
+ global_disable = true;
+
+ return 0;
+ }
+
+ if (prealloc_memory(nr_prealloc_entries) != 0) {
+ pr_err("DMA-API: debugging out of memory error - disabled\n");
+ global_disable = true;
+
+ return 0;
+ }
+
+ nr_total_entries = num_free_entries;
+
+ dma_debug_initialized = true;
+
+ pr_info("DMA-API: debugging enabled by kernel config\n");
+ return 0;
+}
+core_initcall(dma_debug_init);
+
+static __init int dma_debug_cmdline(char *str)
+{
+ if (!str)
+ return -EINVAL;
+
+ if (strncmp(str, "off", 3) == 0) {
+ pr_info("DMA-API: debugging disabled on kernel command line\n");
+ global_disable = true;
+ }
+
+ return 0;
+}
+
+static __init int dma_debug_entries_cmdline(char *str)
+{
+ if (!str)
+ return -EINVAL;
+ if (!get_option(&str, &nr_prealloc_entries))
+ nr_prealloc_entries = PREALLOC_DMA_DEBUG_ENTRIES;
+ return 0;
+}
+
+__setup("dma_debug=", dma_debug_cmdline);
+__setup("dma_debug_entries=", dma_debug_entries_cmdline);
+
+static void check_unmap(struct dma_debug_entry *ref)
+{
+ struct dma_debug_entry *entry;
+ struct hash_bucket *bucket;
+ unsigned long flags;
+
+ bucket = get_hash_bucket(ref, &flags);
+ entry = bucket_find_exact(bucket, ref);
+
+ if (!entry) {
+ /* must drop lock before calling dma_mapping_error */
+ put_hash_bucket(bucket, &flags);
+
+ if (dma_mapping_error(ref->dev, ref->dev_addr)) {
+ err_printk(ref->dev, NULL,
+ "DMA-API: device driver tries to free an "
+ "invalid DMA memory address\n");
+ } else {
+ err_printk(ref->dev, NULL,
+ "DMA-API: device driver tries to free DMA "
+ "memory it has not allocated [device "
+ "address=0x%016llx] [size=%llu bytes]\n",
+ ref->dev_addr, ref->size);
+ }
+ return;
+ }
+
+ if (ref->size != entry->size) {
+ err_printk(ref->dev, entry, "DMA-API: device driver frees "
+ "DMA memory with different size "
+ "[device address=0x%016llx] [map size=%llu bytes] "
+ "[unmap size=%llu bytes]\n",
+ ref->dev_addr, entry->size, ref->size);
+ }
+
+ if (ref->type != entry->type) {
+ err_printk(ref->dev, entry, "DMA-API: device driver frees "
+ "DMA memory with wrong function "
+ "[device address=0x%016llx] [size=%llu bytes] "
+ "[mapped as %s] [unmapped as %s]\n",
+ ref->dev_addr, ref->size,
+ type2name[entry->type], type2name[ref->type]);
+ } else if ((entry->type == dma_debug_coherent) &&
+ (phys_addr(ref) != phys_addr(entry))) {
+ err_printk(ref->dev, entry, "DMA-API: device driver frees "
+ "DMA memory with different CPU address "
+ "[device address=0x%016llx] [size=%llu bytes] "
+ "[cpu alloc address=0x%016llx] "
+ "[cpu free address=0x%016llx]",
+ ref->dev_addr, ref->size,
+ phys_addr(entry),
+ phys_addr(ref));
+ }
+
+ if (ref->sg_call_ents && ref->type == dma_debug_sg &&
+ ref->sg_call_ents != entry->sg_call_ents) {
+ err_printk(ref->dev, entry, "DMA-API: device driver frees "
+ "DMA sg list with different entry count "
+ "[map count=%d] [unmap count=%d]\n",
+ entry->sg_call_ents, ref->sg_call_ents);
+ }
+
+ /*
+ * This may be no bug in reality - but most implementations of the
+ * DMA API don't handle this properly, so check for it here
+ */
+ if (ref->direction != entry->direction) {
+ err_printk(ref->dev, entry, "DMA-API: device driver frees "
+ "DMA memory with different direction "
+ "[device address=0x%016llx] [size=%llu bytes] "
+ "[mapped with %s] [unmapped with %s]\n",
+ ref->dev_addr, ref->size,
+ dir2name[entry->direction],
+ dir2name[ref->direction]);
+ }
+
+ /*
+ * Drivers should use dma_mapping_error() to check the returned
+ * addresses of dma_map_single() and dma_map_page().
+ * If not, print this warning message. See Documentation/DMA-API.txt.
+ */
+ if (entry->map_err_type == MAP_ERR_NOT_CHECKED) {
+ err_printk(ref->dev, entry,
+ "DMA-API: device driver failed to check map error"
+ "[device address=0x%016llx] [size=%llu bytes] "
+ "[mapped as %s]",
+ ref->dev_addr, ref->size,
+ type2name[entry->type]);
+ }
+
+ hash_bucket_del(entry);
+ dma_entry_free(entry);
+
+ put_hash_bucket(bucket, &flags);
+}
+
+static void check_for_stack(struct device *dev,
+ struct page *page, size_t offset)
+{
+ void *addr;
+ struct vm_struct *stack_vm_area = task_stack_vm_area(current);
+
+ if (!stack_vm_area) {
+ /* Stack is direct-mapped. */
+ if (PageHighMem(page))
+ return;
+ addr = page_address(page) + offset;
+ if (object_is_on_stack(addr))
+ err_printk(dev, NULL, "DMA-API: device driver maps memory from stack [addr=%p]\n", addr);
+ } else {
+ /* Stack is vmalloced. */
+ int i;
+
+ for (i = 0; i < stack_vm_area->nr_pages; i++) {
+ if (page != stack_vm_area->pages[i])
+ continue;
+
+ addr = (u8 *)current->stack + i * PAGE_SIZE + offset;
+ err_printk(dev, NULL, "DMA-API: device driver maps memory from stack [probable addr=%p]\n", addr);
+ break;
+ }
+ }
+}
+
+static inline bool overlap(void *addr, unsigned long len, void *start, void *end)
+{
+ unsigned long a1 = (unsigned long)addr;
+ unsigned long b1 = a1 + len;
+ unsigned long a2 = (unsigned long)start;
+ unsigned long b2 = (unsigned long)end;
+
+ return !(b1 <= a2 || a1 >= b2);
+}
+
+static void check_for_illegal_area(struct device *dev, void *addr, unsigned long len)
+{
+ if (overlap(addr, len, _stext, _etext) ||
+ overlap(addr, len, __start_rodata, __end_rodata))
+ err_printk(dev, NULL, "DMA-API: device driver maps memory from kernel text or rodata [addr=%p] [len=%lu]\n", addr, len);
+}
+
+static void check_sync(struct device *dev,
+ struct dma_debug_entry *ref,
+ bool to_cpu)
+{
+ struct dma_debug_entry *entry;
+ struct hash_bucket *bucket;
+ unsigned long flags;
+
+ bucket = get_hash_bucket(ref, &flags);
+
+ entry = bucket_find_contain(&bucket, ref, &flags);
+
+ if (!entry) {
+ err_printk(dev, NULL, "DMA-API: device driver tries "
+ "to sync DMA memory it has not allocated "
+ "[device address=0x%016llx] [size=%llu bytes]\n",
+ (unsigned long long)ref->dev_addr, ref->size);
+ goto out;
+ }
+
+ if (ref->size > entry->size) {
+ err_printk(dev, entry, "DMA-API: device driver syncs"
+ " DMA memory outside allocated range "
+ "[device address=0x%016llx] "
+ "[allocation size=%llu bytes] "
+ "[sync offset+size=%llu]\n",
+ entry->dev_addr, entry->size,
+ ref->size);
+ }
+
+ if (entry->direction == DMA_BIDIRECTIONAL)
+ goto out;
+
+ if (ref->direction != entry->direction) {
+ err_printk(dev, entry, "DMA-API: device driver syncs "
+ "DMA memory with different direction "
+ "[device address=0x%016llx] [size=%llu bytes] "
+ "[mapped with %s] [synced with %s]\n",
+ (unsigned long long)ref->dev_addr, entry->size,
+ dir2name[entry->direction],
+ dir2name[ref->direction]);
+ }
+
+ if (to_cpu && !(entry->direction == DMA_FROM_DEVICE) &&
+ !(ref->direction == DMA_TO_DEVICE))
+ err_printk(dev, entry, "DMA-API: device driver syncs "
+ "device read-only DMA memory for cpu "
+ "[device address=0x%016llx] [size=%llu bytes] "
+ "[mapped with %s] [synced with %s]\n",
+ (unsigned long long)ref->dev_addr, entry->size,
+ dir2name[entry->direction],
+ dir2name[ref->direction]);
+
+ if (!to_cpu && !(entry->direction == DMA_TO_DEVICE) &&
+ !(ref->direction == DMA_FROM_DEVICE))
+ err_printk(dev, entry, "DMA-API: device driver syncs "
+ "device write-only DMA memory to device "
+ "[device address=0x%016llx] [size=%llu bytes] "
+ "[mapped with %s] [synced with %s]\n",
+ (unsigned long long)ref->dev_addr, entry->size,
+ dir2name[entry->direction],
+ dir2name[ref->direction]);
+
+ if (ref->sg_call_ents && ref->type == dma_debug_sg &&
+ ref->sg_call_ents != entry->sg_call_ents) {
+ err_printk(ref->dev, entry, "DMA-API: device driver syncs "
+ "DMA sg list with different entry count "
+ "[map count=%d] [sync count=%d]\n",
+ entry->sg_call_ents, ref->sg_call_ents);
+ }
+
+out:
+ put_hash_bucket(bucket, &flags);
+}
+
+static void check_sg_segment(struct device *dev, struct scatterlist *sg)
+{
+#ifdef CONFIG_DMA_API_DEBUG_SG
+ unsigned int max_seg = dma_get_max_seg_size(dev);
+ u64 start, end, boundary = dma_get_seg_boundary(dev);
+
+ /*
+ * Either the driver forgot to set dma_parms appropriately, or
+ * whoever generated the list forgot to check them.
+ */
+ if (sg->length > max_seg)
+ err_printk(dev, NULL, "DMA-API: mapping sg segment longer than device claims to support [len=%u] [max=%u]\n",
+ sg->length, max_seg);
+ /*
+ * In some cases this could potentially be the DMA API
+ * implementation's fault, but it would usually imply that
+ * the scatterlist was built inappropriately to begin with.
+ */
+ start = sg_dma_address(sg);
+ end = start + sg_dma_len(sg) - 1;
+ if ((start ^ end) & ~boundary)
+ err_printk(dev, NULL, "DMA-API: mapping sg segment across boundary [start=0x%016llx] [end=0x%016llx] [boundary=0x%016llx]\n",
+ start, end, boundary);
+#endif
+}
+
+void debug_dma_map_page(struct device *dev, struct page *page, size_t offset,
+ size_t size, int direction, dma_addr_t dma_addr,
+ bool map_single)
+{
+ struct dma_debug_entry *entry;
+
+ if (unlikely(dma_debug_disabled()))
+ return;
+
+ if (dma_mapping_error(dev, dma_addr))
+ return;
+
+ entry = dma_entry_alloc();
+ if (!entry)
+ return;
+
+ entry->dev = dev;
+ entry->type = dma_debug_page;
+ entry->pfn = page_to_pfn(page);
+ entry->offset = offset,
+ entry->dev_addr = dma_addr;
+ entry->size = size;
+ entry->direction = direction;
+ entry->map_err_type = MAP_ERR_NOT_CHECKED;
+
+ if (map_single)
+ entry->type = dma_debug_single;
+
+ check_for_stack(dev, page, offset);
+
+ if (!PageHighMem(page)) {
+ void *addr = page_address(page) + offset;
+
+ check_for_illegal_area(dev, addr, size);
+ }
+
+ add_dma_entry(entry);
+}
+EXPORT_SYMBOL(debug_dma_map_page);
+
+void debug_dma_mapping_error(struct device *dev, dma_addr_t dma_addr)
+{
+ struct dma_debug_entry ref;
+ struct dma_debug_entry *entry;
+ struct hash_bucket *bucket;
+ unsigned long flags;
+
+ if (unlikely(dma_debug_disabled()))
+ return;
+
+ ref.dev = dev;
+ ref.dev_addr = dma_addr;
+ bucket = get_hash_bucket(&ref, &flags);
+
+ list_for_each_entry(entry, &bucket->list, list) {
+ if (!exact_match(&ref, entry))
+ continue;
+
+ /*
+ * The same physical address can be mapped multiple
+ * times. Without a hardware IOMMU this results in the
+ * same device addresses being put into the dma-debug
+ * hash multiple times too. This can result in false
+ * positives being reported. Therefore we implement a
+ * best-fit algorithm here which updates the first entry
+ * from the hash which fits the reference value and is
+ * not currently listed as being checked.
+ */
+ if (entry->map_err_type == MAP_ERR_NOT_CHECKED) {
+ entry->map_err_type = MAP_ERR_CHECKED;
+ break;
+ }
+ }
+
+ put_hash_bucket(bucket, &flags);
+}
+EXPORT_SYMBOL(debug_dma_mapping_error);
+
+void debug_dma_unmap_page(struct device *dev, dma_addr_t addr,
+ size_t size, int direction, bool map_single)
+{
+ struct dma_debug_entry ref = {
+ .type = dma_debug_page,
+ .dev = dev,
+ .dev_addr = addr,
+ .size = size,
+ .direction = direction,
+ };
+
+ if (unlikely(dma_debug_disabled()))
+ return;
+
+ if (map_single)
+ ref.type = dma_debug_single;
+
+ check_unmap(&ref);
+}
+EXPORT_SYMBOL(debug_dma_unmap_page);
+
+void debug_dma_map_sg(struct device *dev, struct scatterlist *sg,
+ int nents, int mapped_ents, int direction)
+{
+ struct dma_debug_entry *entry;
+ struct scatterlist *s;
+ int i;
+
+ if (unlikely(dma_debug_disabled()))
+ return;
+
+ for_each_sg(sg, s, mapped_ents, i) {
+ entry = dma_entry_alloc();
+ if (!entry)
+ return;
+
+ entry->type = dma_debug_sg;
+ entry->dev = dev;
+ entry->pfn = page_to_pfn(sg_page(s));
+ entry->offset = s->offset,
+ entry->size = sg_dma_len(s);
+ entry->dev_addr = sg_dma_address(s);
+ entry->direction = direction;
+ entry->sg_call_ents = nents;
+ entry->sg_mapped_ents = mapped_ents;
+
+ check_for_stack(dev, sg_page(s), s->offset);
+
+ if (!PageHighMem(sg_page(s))) {
+ check_for_illegal_area(dev, sg_virt(s), sg_dma_len(s));
+ }
+
+ check_sg_segment(dev, s);
+
+ add_dma_entry(entry);
+ }
+}
+EXPORT_SYMBOL(debug_dma_map_sg);
+
+static int get_nr_mapped_entries(struct device *dev,
+ struct dma_debug_entry *ref)
+{
+ struct dma_debug_entry *entry;
+ struct hash_bucket *bucket;
+ unsigned long flags;
+ int mapped_ents;
+
+ bucket = get_hash_bucket(ref, &flags);
+ entry = bucket_find_exact(bucket, ref);
+ mapped_ents = 0;
+
+ if (entry)
+ mapped_ents = entry->sg_mapped_ents;
+ put_hash_bucket(bucket, &flags);
+
+ return mapped_ents;
+}
+
+void debug_dma_unmap_sg(struct device *dev, struct scatterlist *sglist,
+ int nelems, int dir)
+{
+ struct scatterlist *s;
+ int mapped_ents = 0, i;
+
+ if (unlikely(dma_debug_disabled()))
+ return;
+
+ for_each_sg(sglist, s, nelems, i) {
+
+ struct dma_debug_entry ref = {
+ .type = dma_debug_sg,
+ .dev = dev,
+ .pfn = page_to_pfn(sg_page(s)),
+ .offset = s->offset,
+ .dev_addr = sg_dma_address(s),
+ .size = sg_dma_len(s),
+ .direction = dir,
+ .sg_call_ents = nelems,
+ };
+
+ if (mapped_ents && i >= mapped_ents)
+ break;
+
+ if (!i)
+ mapped_ents = get_nr_mapped_entries(dev, &ref);
+
+ check_unmap(&ref);
+ }
+}
+EXPORT_SYMBOL(debug_dma_unmap_sg);
+
+void debug_dma_alloc_coherent(struct device *dev, size_t size,
+ dma_addr_t dma_addr, void *virt)
+{
+ struct dma_debug_entry *entry;
+
+ if (unlikely(dma_debug_disabled()))
+ return;
+
+ if (unlikely(virt == NULL))
+ return;
+
+ /* handle vmalloc and linear addresses */
+ if (!is_vmalloc_addr(virt) && !virt_addr_valid(virt))
+ return;
+
+ entry = dma_entry_alloc();
+ if (!entry)
+ return;
+
+ entry->type = dma_debug_coherent;
+ entry->dev = dev;
+ entry->offset = offset_in_page(virt);
+ entry->size = size;
+ entry->dev_addr = dma_addr;
+ entry->direction = DMA_BIDIRECTIONAL;
+
+ if (is_vmalloc_addr(virt))
+ entry->pfn = vmalloc_to_pfn(virt);
+ else
+ entry->pfn = page_to_pfn(virt_to_page(virt));
+
+ add_dma_entry(entry);
+}
+EXPORT_SYMBOL(debug_dma_alloc_coherent);
+
+void debug_dma_free_coherent(struct device *dev, size_t size,
+ void *virt, dma_addr_t addr)
+{
+ struct dma_debug_entry ref = {
+ .type = dma_debug_coherent,
+ .dev = dev,
+ .offset = offset_in_page(virt),
+ .dev_addr = addr,
+ .size = size,
+ .direction = DMA_BIDIRECTIONAL,
+ };
+
+ /* handle vmalloc and linear addresses */
+ if (!is_vmalloc_addr(virt) && !virt_addr_valid(virt))
+ return;
+
+ if (is_vmalloc_addr(virt))
+ ref.pfn = vmalloc_to_pfn(virt);
+ else
+ ref.pfn = page_to_pfn(virt_to_page(virt));
+
+ if (unlikely(dma_debug_disabled()))
+ return;
+
+ check_unmap(&ref);
+}
+EXPORT_SYMBOL(debug_dma_free_coherent);
+
+void debug_dma_map_resource(struct device *dev, phys_addr_t addr, size_t size,
+ int direction, dma_addr_t dma_addr)
+{
+ struct dma_debug_entry *entry;
+
+ if (unlikely(dma_debug_disabled()))
+ return;
+
+ entry = dma_entry_alloc();
+ if (!entry)
+ return;
+
+ entry->type = dma_debug_resource;
+ entry->dev = dev;
+ entry->pfn = PHYS_PFN(addr);
+ entry->offset = offset_in_page(addr);
+ entry->size = size;
+ entry->dev_addr = dma_addr;
+ entry->direction = direction;
+ entry->map_err_type = MAP_ERR_NOT_CHECKED;
+
+ add_dma_entry(entry);
+}
+EXPORT_SYMBOL(debug_dma_map_resource);
+
+void debug_dma_unmap_resource(struct device *dev, dma_addr_t dma_addr,
+ size_t size, int direction)
+{
+ struct dma_debug_entry ref = {
+ .type = dma_debug_resource,
+ .dev = dev,
+ .dev_addr = dma_addr,
+ .size = size,
+ .direction = direction,
+ };
+
+ if (unlikely(dma_debug_disabled()))
+ return;
+
+ check_unmap(&ref);
+}
+EXPORT_SYMBOL(debug_dma_unmap_resource);
+
+void debug_dma_sync_single_for_cpu(struct device *dev, dma_addr_t dma_handle,
+ size_t size, int direction)
+{
+ struct dma_debug_entry ref;
+
+ if (unlikely(dma_debug_disabled()))
+ return;
+
+ ref.type = dma_debug_single;
+ ref.dev = dev;
+ ref.dev_addr = dma_handle;
+ ref.size = size;
+ ref.direction = direction;
+ ref.sg_call_ents = 0;
+
+ check_sync(dev, &ref, true);
+}
+EXPORT_SYMBOL(debug_dma_sync_single_for_cpu);
+
+void debug_dma_sync_single_for_device(struct device *dev,
+ dma_addr_t dma_handle, size_t size,
+ int direction)
+{
+ struct dma_debug_entry ref;
+
+ if (unlikely(dma_debug_disabled()))
+ return;
+
+ ref.type = dma_debug_single;
+ ref.dev = dev;
+ ref.dev_addr = dma_handle;
+ ref.size = size;
+ ref.direction = direction;
+ ref.sg_call_ents = 0;
+
+ check_sync(dev, &ref, false);
+}
+EXPORT_SYMBOL(debug_dma_sync_single_for_device);
+
+void debug_dma_sync_single_range_for_cpu(struct device *dev,
+ dma_addr_t dma_handle,
+ unsigned long offset, size_t size,
+ int direction)
+{
+ struct dma_debug_entry ref;
+
+ if (unlikely(dma_debug_disabled()))
+ return;
+
+ ref.type = dma_debug_single;
+ ref.dev = dev;
+ ref.dev_addr = dma_handle;
+ ref.size = offset + size;
+ ref.direction = direction;
+ ref.sg_call_ents = 0;
+
+ check_sync(dev, &ref, true);
+}
+EXPORT_SYMBOL(debug_dma_sync_single_range_for_cpu);
+
+void debug_dma_sync_single_range_for_device(struct device *dev,
+ dma_addr_t dma_handle,
+ unsigned long offset,
+ size_t size, int direction)
+{
+ struct dma_debug_entry ref;
+
+ if (unlikely(dma_debug_disabled()))
+ return;
+
+ ref.type = dma_debug_single;
+ ref.dev = dev;
+ ref.dev_addr = dma_handle;
+ ref.size = offset + size;
+ ref.direction = direction;
+ ref.sg_call_ents = 0;
+
+ check_sync(dev, &ref, false);
+}
+EXPORT_SYMBOL(debug_dma_sync_single_range_for_device);
+
+void debug_dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg,
+ int nelems, int direction)
+{
+ struct scatterlist *s;
+ int mapped_ents = 0, i;
+
+ if (unlikely(dma_debug_disabled()))
+ return;
+
+ for_each_sg(sg, s, nelems, i) {
+
+ struct dma_debug_entry ref = {
+ .type = dma_debug_sg,
+ .dev = dev,
+ .pfn = page_to_pfn(sg_page(s)),
+ .offset = s->offset,
+ .dev_addr = sg_dma_address(s),
+ .size = sg_dma_len(s),
+ .direction = direction,
+ .sg_call_ents = nelems,
+ };
+
+ if (!i)
+ mapped_ents = get_nr_mapped_entries(dev, &ref);
+
+ if (i >= mapped_ents)
+ break;
+
+ check_sync(dev, &ref, true);
+ }
+}
+EXPORT_SYMBOL(debug_dma_sync_sg_for_cpu);
+
+void debug_dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg,
+ int nelems, int direction)
+{
+ struct scatterlist *s;
+ int mapped_ents = 0, i;
+
+ if (unlikely(dma_debug_disabled()))
+ return;
+
+ for_each_sg(sg, s, nelems, i) {
+
+ struct dma_debug_entry ref = {
+ .type = dma_debug_sg,
+ .dev = dev,
+ .pfn = page_to_pfn(sg_page(s)),
+ .offset = s->offset,
+ .dev_addr = sg_dma_address(s),
+ .size = sg_dma_len(s),
+ .direction = direction,
+ .sg_call_ents = nelems,
+ };
+ if (!i)
+ mapped_ents = get_nr_mapped_entries(dev, &ref);
+
+ if (i >= mapped_ents)
+ break;
+
+ check_sync(dev, &ref, false);
+ }
+}
+EXPORT_SYMBOL(debug_dma_sync_sg_for_device);
+
+static int __init dma_debug_driver_setup(char *str)
+{
+ int i;
+
+ for (i = 0; i < NAME_MAX_LEN - 1; ++i, ++str) {
+ current_driver_name[i] = *str;
+ if (*str == 0)
+ break;
+ }
+
+ if (current_driver_name[0])
+ pr_info("DMA-API: enable driver filter for driver [%s]\n",
+ current_driver_name);
+
+
+ return 1;
+}
+__setup("dma_debug_driver=", dma_debug_driver_setup);
diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c
new file mode 100644
index 000000000000..8be8106270c2
--- /dev/null
+++ b/kernel/dma/direct.c
@@ -0,0 +1,204 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * DMA operations that map physical memory directly without using an IOMMU or
+ * flushing caches.
+ */
+#include <linux/export.h>
+#include <linux/mm.h>
+#include <linux/dma-direct.h>
+#include <linux/scatterlist.h>
+#include <linux/dma-contiguous.h>
+#include <linux/pfn.h>
+#include <linux/set_memory.h>
+
+#define DIRECT_MAPPING_ERROR 0
+
+/*
+ * Most architectures use ZONE_DMA for the first 16 Megabytes, but
+ * some use it for entirely different regions:
+ */
+#ifndef ARCH_ZONE_DMA_BITS
+#define ARCH_ZONE_DMA_BITS 24
+#endif
+
+/*
+ * For AMD SEV all DMA must be to unencrypted addresses.
+ */
+static inline bool force_dma_unencrypted(void)
+{
+ return sev_active();
+}
+
+static bool
+check_addr(struct device *dev, dma_addr_t dma_addr, size_t size,
+ const char *caller)
+{
+ if (unlikely(dev && !dma_capable(dev, dma_addr, size))) {
+ if (!dev->dma_mask) {
+ dev_err(dev,
+ "%s: call on device without dma_mask\n",
+ caller);
+ return false;
+ }
+
+ if (*dev->dma_mask >= DMA_BIT_MASK(32)) {
+ dev_err(dev,
+ "%s: overflow %pad+%zu of device mask %llx\n",
+ caller, &dma_addr, size, *dev->dma_mask);
+ }
+ return false;
+ }
+ return true;
+}
+
+static bool dma_coherent_ok(struct device *dev, phys_addr_t phys, size_t size)
+{
+ dma_addr_t addr = force_dma_unencrypted() ?
+ __phys_to_dma(dev, phys) : phys_to_dma(dev, phys);
+ return addr + size - 1 <= dev->coherent_dma_mask;
+}
+
+void *dma_direct_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle,
+ gfp_t gfp, unsigned long attrs)
+{
+ unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT;
+ int page_order = get_order(size);
+ struct page *page = NULL;
+ void *ret;
+
+ /* we always manually zero the memory once we are done: */
+ gfp &= ~__GFP_ZERO;
+
+ /* GFP_DMA32 and GFP_DMA are no ops without the corresponding zones: */
+ if (dev->coherent_dma_mask <= DMA_BIT_MASK(ARCH_ZONE_DMA_BITS))
+ gfp |= GFP_DMA;
+ if (dev->coherent_dma_mask <= DMA_BIT_MASK(32) && !(gfp & GFP_DMA))
+ gfp |= GFP_DMA32;
+
+again:
+ /* CMA can be used only in the context which permits sleeping */
+ if (gfpflags_allow_blocking(gfp)) {
+ page = dma_alloc_from_contiguous(dev, count, page_order, gfp);
+ if (page && !dma_coherent_ok(dev, page_to_phys(page), size)) {
+ dma_release_from_contiguous(dev, page, count);
+ page = NULL;
+ }
+ }
+ if (!page)
+ page = alloc_pages_node(dev_to_node(dev), gfp, page_order);
+
+ if (page && !dma_coherent_ok(dev, page_to_phys(page), size)) {
+ __free_pages(page, page_order);
+ page = NULL;
+
+ if (IS_ENABLED(CONFIG_ZONE_DMA32) &&
+ dev->coherent_dma_mask < DMA_BIT_MASK(64) &&
+ !(gfp & (GFP_DMA32 | GFP_DMA))) {
+ gfp |= GFP_DMA32;
+ goto again;
+ }
+
+ if (IS_ENABLED(CONFIG_ZONE_DMA) &&
+ dev->coherent_dma_mask < DMA_BIT_MASK(32) &&
+ !(gfp & GFP_DMA)) {
+ gfp = (gfp & ~GFP_DMA32) | GFP_DMA;
+ goto again;
+ }
+ }
+
+ if (!page)
+ return NULL;
+ ret = page_address(page);
+ if (force_dma_unencrypted()) {
+ set_memory_decrypted((unsigned long)ret, 1 << page_order);
+ *dma_handle = __phys_to_dma(dev, page_to_phys(page));
+ } else {
+ *dma_handle = phys_to_dma(dev, page_to_phys(page));
+ }
+ memset(ret, 0, size);
+ return ret;
+}
+
+/*
+ * NOTE: this function must never look at the dma_addr argument, because we want
+ * to be able to use it as a helper for iommu implementations as well.
+ */
+void dma_direct_free(struct device *dev, size_t size, void *cpu_addr,
+ dma_addr_t dma_addr, unsigned long attrs)
+{
+ unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT;
+ unsigned int page_order = get_order(size);
+
+ if (force_dma_unencrypted())
+ set_memory_encrypted((unsigned long)cpu_addr, 1 << page_order);
+ if (!dma_release_from_contiguous(dev, virt_to_page(cpu_addr), count))
+ free_pages((unsigned long)cpu_addr, page_order);
+}
+
+dma_addr_t dma_direct_map_page(struct device *dev, struct page *page,
+ unsigned long offset, size_t size, enum dma_data_direction dir,
+ unsigned long attrs)
+{
+ dma_addr_t dma_addr = phys_to_dma(dev, page_to_phys(page)) + offset;
+
+ if (!check_addr(dev, dma_addr, size, __func__))
+ return DIRECT_MAPPING_ERROR;
+ return dma_addr;
+}
+
+int dma_direct_map_sg(struct device *dev, struct scatterlist *sgl, int nents,
+ enum dma_data_direction dir, unsigned long attrs)
+{
+ int i;
+ struct scatterlist *sg;
+
+ for_each_sg(sgl, sg, nents, i) {
+ BUG_ON(!sg_page(sg));
+
+ sg_dma_address(sg) = phys_to_dma(dev, sg_phys(sg));
+ if (!check_addr(dev, sg_dma_address(sg), sg->length, __func__))
+ return 0;
+ sg_dma_len(sg) = sg->length;
+ }
+
+ return nents;
+}
+
+int dma_direct_supported(struct device *dev, u64 mask)
+{
+#ifdef CONFIG_ZONE_DMA
+ if (mask < DMA_BIT_MASK(ARCH_ZONE_DMA_BITS))
+ return 0;
+#else
+ /*
+ * Because 32-bit DMA masks are so common we expect every architecture
+ * to be able to satisfy them - either by not supporting more physical
+ * memory, or by providing a ZONE_DMA32. If neither is the case, the
+ * architecture needs to use an IOMMU instead of the direct mapping.
+ */
+ if (mask < DMA_BIT_MASK(32))
+ return 0;
+#endif
+ /*
+ * Various PCI/PCIe bridges have broken support for > 32bit DMA even
+ * if the device itself might support it.
+ */
+ if (dev->dma_32bit_limit && mask > DMA_BIT_MASK(32))
+ return 0;
+ return 1;
+}
+
+int dma_direct_mapping_error(struct device *dev, dma_addr_t dma_addr)
+{
+ return dma_addr == DIRECT_MAPPING_ERROR;
+}
+
+const struct dma_map_ops dma_direct_ops = {
+ .alloc = dma_direct_alloc,
+ .free = dma_direct_free,
+ .map_page = dma_direct_map_page,
+ .map_sg = dma_direct_map_sg,
+ .dma_supported = dma_direct_supported,
+ .mapping_error = dma_direct_mapping_error,
+};
+EXPORT_SYMBOL(dma_direct_ops);
diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c
new file mode 100644
index 000000000000..d2a92ddaac4d
--- /dev/null
+++ b/kernel/dma/mapping.c
@@ -0,0 +1,345 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * arch-independent dma-mapping routines
+ *
+ * Copyright (c) 2006 SUSE Linux Products GmbH
+ * Copyright (c) 2006 Tejun Heo <teheo@suse.de>
+ */
+
+#include <linux/acpi.h>
+#include <linux/dma-mapping.h>
+#include <linux/export.h>
+#include <linux/gfp.h>
+#include <linux/of_device.h>
+#include <linux/slab.h>
+#include <linux/vmalloc.h>
+
+/*
+ * Managed DMA API
+ */
+struct dma_devres {
+ size_t size;
+ void *vaddr;
+ dma_addr_t dma_handle;
+ unsigned long attrs;
+};
+
+static void dmam_release(struct device *dev, void *res)
+{
+ struct dma_devres *this = res;
+
+ dma_free_attrs(dev, this->size, this->vaddr, this->dma_handle,
+ this->attrs);
+}
+
+static int dmam_match(struct device *dev, void *res, void *match_data)
+{
+ struct dma_devres *this = res, *match = match_data;
+
+ if (this->vaddr == match->vaddr) {
+ WARN_ON(this->size != match->size ||
+ this->dma_handle != match->dma_handle);
+ return 1;
+ }
+ return 0;
+}
+
+/**
+ * dmam_alloc_coherent - Managed dma_alloc_coherent()
+ * @dev: Device to allocate coherent memory for
+ * @size: Size of allocation
+ * @dma_handle: Out argument for allocated DMA handle
+ * @gfp: Allocation flags
+ *
+ * Managed dma_alloc_coherent(). Memory allocated using this function
+ * will be automatically released on driver detach.
+ *
+ * RETURNS:
+ * Pointer to allocated memory on success, NULL on failure.
+ */
+void *dmam_alloc_coherent(struct device *dev, size_t size,
+ dma_addr_t *dma_handle, gfp_t gfp)
+{
+ struct dma_devres *dr;
+ void *vaddr;
+
+ dr = devres_alloc(dmam_release, sizeof(*dr), gfp);
+ if (!dr)
+ return NULL;
+
+ vaddr = dma_alloc_coherent(dev, size, dma_handle, gfp);
+ if (!vaddr) {
+ devres_free(dr);
+ return NULL;
+ }
+
+ dr->vaddr = vaddr;
+ dr->dma_handle = *dma_handle;
+ dr->size = size;
+
+ devres_add(dev, dr);
+
+ return vaddr;
+}
+EXPORT_SYMBOL(dmam_alloc_coherent);
+
+/**
+ * dmam_free_coherent - Managed dma_free_coherent()
+ * @dev: Device to free coherent memory for
+ * @size: Size of allocation
+ * @vaddr: Virtual address of the memory to free
+ * @dma_handle: DMA handle of the memory to free
+ *
+ * Managed dma_free_coherent().
+ */
+void dmam_free_coherent(struct device *dev, size_t size, void *vaddr,
+ dma_addr_t dma_handle)
+{
+ struct dma_devres match_data = { size, vaddr, dma_handle };
+
+ dma_free_coherent(dev, size, vaddr, dma_handle);
+ WARN_ON(devres_destroy(dev, dmam_release, dmam_match, &match_data));
+}
+EXPORT_SYMBOL(dmam_free_coherent);
+
+/**
+ * dmam_alloc_attrs - Managed dma_alloc_attrs()
+ * @dev: Device to allocate non_coherent memory for
+ * @size: Size of allocation
+ * @dma_handle: Out argument for allocated DMA handle
+ * @gfp: Allocation flags
+ * @attrs: Flags in the DMA_ATTR_* namespace.
+ *
+ * Managed dma_alloc_attrs(). Memory allocated using this function will be
+ * automatically released on driver detach.
+ *
+ * RETURNS:
+ * Pointer to allocated memory on success, NULL on failure.
+ */
+void *dmam_alloc_attrs(struct device *dev, size_t size, dma_addr_t *dma_handle,
+ gfp_t gfp, unsigned long attrs)
+{
+ struct dma_devres *dr;
+ void *vaddr;
+
+ dr = devres_alloc(dmam_release, sizeof(*dr), gfp);
+ if (!dr)
+ return NULL;
+
+ vaddr = dma_alloc_attrs(dev, size, dma_handle, gfp, attrs);
+ if (!vaddr) {
+ devres_free(dr);
+ return NULL;
+ }
+
+ dr->vaddr = vaddr;
+ dr->dma_handle = *dma_handle;
+ dr->size = size;
+ dr->attrs = attrs;
+
+ devres_add(dev, dr);
+
+ return vaddr;
+}
+EXPORT_SYMBOL(dmam_alloc_attrs);
+
+#ifdef CONFIG_HAVE_GENERIC_DMA_COHERENT
+
+static void dmam_coherent_decl_release(struct device *dev, void *res)
+{
+ dma_release_declared_memory(dev);
+}
+
+/**
+ * dmam_declare_coherent_memory - Managed dma_declare_coherent_memory()
+ * @dev: Device to declare coherent memory for
+ * @phys_addr: Physical address of coherent memory to be declared
+ * @device_addr: Device address of coherent memory to be declared
+ * @size: Size of coherent memory to be declared
+ * @flags: Flags
+ *
+ * Managed dma_declare_coherent_memory().
+ *
+ * RETURNS:
+ * 0 on success, -errno on failure.
+ */
+int dmam_declare_coherent_memory(struct device *dev, phys_addr_t phys_addr,
+ dma_addr_t device_addr, size_t size, int flags)
+{
+ void *res;
+ int rc;
+
+ res = devres_alloc(dmam_coherent_decl_release, 0, GFP_KERNEL);
+ if (!res)
+ return -ENOMEM;
+
+ rc = dma_declare_coherent_memory(dev, phys_addr, device_addr, size,
+ flags);
+ if (!rc)
+ devres_add(dev, res);
+ else
+ devres_free(res);
+
+ return rc;
+}
+EXPORT_SYMBOL(dmam_declare_coherent_memory);
+
+/**
+ * dmam_release_declared_memory - Managed dma_release_declared_memory().
+ * @dev: Device to release declared coherent memory for
+ *
+ * Managed dmam_release_declared_memory().
+ */
+void dmam_release_declared_memory(struct device *dev)
+{
+ WARN_ON(devres_destroy(dev, dmam_coherent_decl_release, NULL, NULL));
+}
+EXPORT_SYMBOL(dmam_release_declared_memory);
+
+#endif
+
+/*
+ * Create scatter-list for the already allocated DMA buffer.
+ */
+int dma_common_get_sgtable(struct device *dev, struct sg_table *sgt,
+ void *cpu_addr, dma_addr_t handle, size_t size)
+{
+ struct page *page = virt_to_page(cpu_addr);
+ int ret;
+
+ ret = sg_alloc_table(sgt, 1, GFP_KERNEL);
+ if (unlikely(ret))
+ return ret;
+
+ sg_set_page(sgt->sgl, page, PAGE_ALIGN(size), 0);
+ return 0;
+}
+EXPORT_SYMBOL(dma_common_get_sgtable);
+
+/*
+ * Create userspace mapping for the DMA-coherent memory.
+ */
+int dma_common_mmap(struct device *dev, struct vm_area_struct *vma,
+ void *cpu_addr, dma_addr_t dma_addr, size_t size)
+{
+ int ret = -ENXIO;
+#ifndef CONFIG_ARCH_NO_COHERENT_DMA_MMAP
+ unsigned long user_count = vma_pages(vma);
+ unsigned long count = PAGE_ALIGN(size) >> PAGE_SHIFT;
+ unsigned long off = vma->vm_pgoff;
+
+ vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
+
+ if (dma_mmap_from_dev_coherent(dev, vma, cpu_addr, size, &ret))
+ return ret;
+
+ if (off < count && user_count <= (count - off))
+ ret = remap_pfn_range(vma, vma->vm_start,
+ page_to_pfn(virt_to_page(cpu_addr)) + off,
+ user_count << PAGE_SHIFT,
+ vma->vm_page_prot);
+#endif /* !CONFIG_ARCH_NO_COHERENT_DMA_MMAP */
+
+ return ret;
+}
+EXPORT_SYMBOL(dma_common_mmap);
+
+#ifdef CONFIG_MMU
+static struct vm_struct *__dma_common_pages_remap(struct page **pages,
+ size_t size, unsigned long vm_flags, pgprot_t prot,
+ const void *caller)
+{
+ struct vm_struct *area;
+
+ area = get_vm_area_caller(size, vm_flags, caller);
+ if (!area)
+ return NULL;
+
+ if (map_vm_area(area, prot, pages)) {
+ vunmap(area->addr);
+ return NULL;
+ }
+
+ return area;
+}
+
+/*
+ * remaps an array of PAGE_SIZE pages into another vm_area
+ * Cannot be used in non-sleeping contexts
+ */
+void *dma_common_pages_remap(struct page **pages, size_t size,
+ unsigned long vm_flags, pgprot_t prot,
+ const void *caller)
+{
+ struct vm_struct *area;
+
+ area = __dma_common_pages_remap(pages, size, vm_flags, prot, caller);
+ if (!area)
+ return NULL;
+
+ area->pages = pages;
+
+ return area->addr;
+}
+
+/*
+ * remaps an allocated contiguous region into another vm_area.
+ * Cannot be used in non-sleeping contexts
+ */
+
+void *dma_common_contiguous_remap(struct page *page, size_t size,
+ unsigned long vm_flags,
+ pgprot_t prot, const void *caller)
+{
+ int i;
+ struct page **pages;
+ struct vm_struct *area;
+
+ pages = kmalloc(sizeof(struct page *) << get_order(size), GFP_KERNEL);
+ if (!pages)
+ return NULL;
+
+ for (i = 0; i < (size >> PAGE_SHIFT); i++)
+ pages[i] = nth_page(page, i);
+
+ area = __dma_common_pages_remap(pages, size, vm_flags, prot, caller);
+
+ kfree(pages);
+
+ if (!area)
+ return NULL;
+ return area->addr;
+}
+
+/*
+ * unmaps a range previously mapped by dma_common_*_remap
+ */
+void dma_common_free_remap(void *cpu_addr, size_t size, unsigned long vm_flags)
+{
+ struct vm_struct *area = find_vm_area(cpu_addr);
+
+ if (!area || (area->flags & vm_flags) != vm_flags) {
+ WARN(1, "trying to free invalid coherent area: %p\n", cpu_addr);
+ return;
+ }
+
+ unmap_kernel_range((unsigned long)cpu_addr, PAGE_ALIGN(size));
+ vunmap(cpu_addr);
+}
+#endif
+
+/*
+ * enables DMA API use for a device
+ */
+int dma_configure(struct device *dev)
+{
+ if (dev->bus->dma_configure)
+ return dev->bus->dma_configure(dev);
+ return 0;
+}
+
+void dma_deconfigure(struct device *dev)
+{
+ of_dma_deconfigure(dev);
+ acpi_dma_deconfigure(dev);
+}
diff --git a/kernel/dma/noncoherent.c b/kernel/dma/noncoherent.c
new file mode 100644
index 000000000000..79e9a757387f
--- /dev/null
+++ b/kernel/dma/noncoherent.c
@@ -0,0 +1,102 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2018 Christoph Hellwig.
+ *
+ * DMA operations that map physical memory directly without providing cache
+ * coherence.
+ */
+#include <linux/export.h>
+#include <linux/mm.h>
+#include <linux/dma-direct.h>
+#include <linux/dma-noncoherent.h>
+#include <linux/scatterlist.h>
+
+static void dma_noncoherent_sync_single_for_device(struct device *dev,
+ dma_addr_t addr, size_t size, enum dma_data_direction dir)
+{
+ arch_sync_dma_for_device(dev, dma_to_phys(dev, addr), size, dir);
+}
+
+static void dma_noncoherent_sync_sg_for_device(struct device *dev,
+ struct scatterlist *sgl, int nents, enum dma_data_direction dir)
+{
+ struct scatterlist *sg;
+ int i;
+
+ for_each_sg(sgl, sg, nents, i)
+ arch_sync_dma_for_device(dev, sg_phys(sg), sg->length, dir);
+}
+
+static dma_addr_t dma_noncoherent_map_page(struct device *dev, struct page *page,
+ unsigned long offset, size_t size, enum dma_data_direction dir,
+ unsigned long attrs)
+{
+ dma_addr_t addr;
+
+ addr = dma_direct_map_page(dev, page, offset, size, dir, attrs);
+ if (!dma_mapping_error(dev, addr) && !(attrs & DMA_ATTR_SKIP_CPU_SYNC))
+ arch_sync_dma_for_device(dev, page_to_phys(page) + offset,
+ size, dir);
+ return addr;
+}
+
+static int dma_noncoherent_map_sg(struct device *dev, struct scatterlist *sgl,
+ int nents, enum dma_data_direction dir, unsigned long attrs)
+{
+ nents = dma_direct_map_sg(dev, sgl, nents, dir, attrs);
+ if (nents > 0 && !(attrs & DMA_ATTR_SKIP_CPU_SYNC))
+ dma_noncoherent_sync_sg_for_device(dev, sgl, nents, dir);
+ return nents;
+}
+
+#ifdef CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU
+static void dma_noncoherent_sync_single_for_cpu(struct device *dev,
+ dma_addr_t addr, size_t size, enum dma_data_direction dir)
+{
+ arch_sync_dma_for_cpu(dev, dma_to_phys(dev, addr), size, dir);
+}
+
+static void dma_noncoherent_sync_sg_for_cpu(struct device *dev,
+ struct scatterlist *sgl, int nents, enum dma_data_direction dir)
+{
+ struct scatterlist *sg;
+ int i;
+
+ for_each_sg(sgl, sg, nents, i)
+ arch_sync_dma_for_cpu(dev, sg_phys(sg), sg->length, dir);
+}
+
+static void dma_noncoherent_unmap_page(struct device *dev, dma_addr_t addr,
+ size_t size, enum dma_data_direction dir, unsigned long attrs)
+{
+ if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
+ dma_noncoherent_sync_single_for_cpu(dev, addr, size, dir);
+}
+
+static void dma_noncoherent_unmap_sg(struct device *dev, struct scatterlist *sgl,
+ int nents, enum dma_data_direction dir, unsigned long attrs)
+{
+ if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC))
+ dma_noncoherent_sync_sg_for_cpu(dev, sgl, nents, dir);
+}
+#endif
+
+const struct dma_map_ops dma_noncoherent_ops = {
+ .alloc = arch_dma_alloc,
+ .free = arch_dma_free,
+ .mmap = arch_dma_mmap,
+ .sync_single_for_device = dma_noncoherent_sync_single_for_device,
+ .sync_sg_for_device = dma_noncoherent_sync_sg_for_device,
+ .map_page = dma_noncoherent_map_page,
+ .map_sg = dma_noncoherent_map_sg,
+#ifdef CONFIG_ARCH_HAS_SYNC_DMA_FOR_CPU
+ .sync_single_for_cpu = dma_noncoherent_sync_single_for_cpu,
+ .sync_sg_for_cpu = dma_noncoherent_sync_sg_for_cpu,
+ .unmap_page = dma_noncoherent_unmap_page,
+ .unmap_sg = dma_noncoherent_unmap_sg,
+#endif
+ .dma_supported = dma_direct_supported,
+ .mapping_error = dma_direct_mapping_error,
+ .cache_sync = arch_dma_cache_sync,
+};
+EXPORT_SYMBOL(dma_noncoherent_ops);
diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c
new file mode 100644
index 000000000000..904541055792
--- /dev/null
+++ b/kernel/dma/swiotlb.c
@@ -0,0 +1,1088 @@
+/*
+ * Dynamic DMA mapping support.
+ *
+ * This implementation is a fallback for platforms that do not support
+ * I/O TLBs (aka DMA address translation hardware).
+ * Copyright (C) 2000 Asit Mallick <Asit.K.Mallick@intel.com>
+ * Copyright (C) 2000 Goutham Rao <goutham.rao@intel.com>
+ * Copyright (C) 2000, 2003 Hewlett-Packard Co
+ * David Mosberger-Tang <davidm@hpl.hp.com>
+ *
+ * 03/05/07 davidm Switch from PCI-DMA to generic device DMA API.
+ * 00/12/13 davidm Rename to swiotlb.c and add mark_clean() to avoid
+ * unnecessary i-cache flushing.
+ * 04/07/.. ak Better overflow handling. Assorted fixes.
+ * 05/09/10 linville Add support for syncing ranges, support syncing for
+ * DMA_BIDIRECTIONAL mappings, miscellaneous cleanup.
+ * 08/12/11 beckyb Add highmem support
+ */
+
+#include <linux/cache.h>
+#include <linux/dma-direct.h>
+#include <linux/mm.h>
+#include <linux/export.h>
+#include <linux/spinlock.h>
+#include <linux/string.h>
+#include <linux/swiotlb.h>
+#include <linux/pfn.h>
+#include <linux/types.h>
+#include <linux/ctype.h>
+#include <linux/highmem.h>
+#include <linux/gfp.h>
+#include <linux/scatterlist.h>
+#include <linux/mem_encrypt.h>
+#include <linux/set_memory.h>
+
+#include <asm/io.h>
+#include <asm/dma.h>
+
+#include <linux/init.h>
+#include <linux/bootmem.h>
+#include <linux/iommu-helper.h>
+
+#define CREATE_TRACE_POINTS
+#include <trace/events/swiotlb.h>
+
+#define OFFSET(val,align) ((unsigned long) \
+ ( (val) & ( (align) - 1)))
+
+#define SLABS_PER_PAGE (1 << (PAGE_SHIFT - IO_TLB_SHIFT))
+
+/*
+ * Minimum IO TLB size to bother booting with. Systems with mainly
+ * 64bit capable cards will only lightly use the swiotlb. If we can't
+ * allocate a contiguous 1MB, we're probably in trouble anyway.
+ */
+#define IO_TLB_MIN_SLABS ((1<<20) >> IO_TLB_SHIFT)
+
+enum swiotlb_force swiotlb_force;
+
+/*
+ * Used to do a quick range check in swiotlb_tbl_unmap_single and
+ * swiotlb_tbl_sync_single_*, to see if the memory was in fact allocated by this
+ * API.
+ */
+static phys_addr_t io_tlb_start, io_tlb_end;
+
+/*
+ * The number of IO TLB blocks (in groups of 64) between io_tlb_start and
+ * io_tlb_end. This is command line adjustable via setup_io_tlb_npages.
+ */
+static unsigned long io_tlb_nslabs;
+
+/*
+ * When the IOMMU overflows we return a fallback buffer. This sets the size.
+ */
+static unsigned long io_tlb_overflow = 32*1024;
+
+static phys_addr_t io_tlb_overflow_buffer;
+
+/*
+ * This is a free list describing the number of free entries available from
+ * each index
+ */
+static unsigned int *io_tlb_list;
+static unsigned int io_tlb_index;
+
+/*
+ * Max segment that we can provide which (if pages are contingous) will
+ * not be bounced (unless SWIOTLB_FORCE is set).
+ */
+unsigned int max_segment;
+
+/*
+ * We need to save away the original address corresponding to a mapped entry
+ * for the sync operations.
+ */
+#define INVALID_PHYS_ADDR (~(phys_addr_t)0)
+static phys_addr_t *io_tlb_orig_addr;
+
+/*
+ * Protect the above data structures in the map and unmap calls
+ */
+static DEFINE_SPINLOCK(io_tlb_lock);
+
+static int late_alloc;
+
+static int __init
+setup_io_tlb_npages(char *str)
+{
+ if (isdigit(*str)) {
+ io_tlb_nslabs = simple_strtoul(str, &str, 0);
+ /* avoid tail segment of size < IO_TLB_SEGSIZE */
+ io_tlb_nslabs = ALIGN(io_tlb_nslabs, IO_TLB_SEGSIZE);
+ }
+ if (*str == ',')
+ ++str;
+ if (!strcmp(str, "force")) {
+ swiotlb_force = SWIOTLB_FORCE;
+ } else if (!strcmp(str, "noforce")) {
+ swiotlb_force = SWIOTLB_NO_FORCE;
+ io_tlb_nslabs = 1;
+ }
+
+ return 0;
+}
+early_param("swiotlb", setup_io_tlb_npages);
+/* make io_tlb_overflow tunable too? */
+
+unsigned long swiotlb_nr_tbl(void)
+{
+ return io_tlb_nslabs;
+}
+EXPORT_SYMBOL_GPL(swiotlb_nr_tbl);
+
+unsigned int swiotlb_max_segment(void)
+{
+ return max_segment;
+}
+EXPORT_SYMBOL_GPL(swiotlb_max_segment);
+
+void swiotlb_set_max_segment(unsigned int val)
+{
+ if (swiotlb_force == SWIOTLB_FORCE)
+ max_segment = 1;
+ else
+ max_segment = rounddown(val, PAGE_SIZE);
+}
+
+/* default to 64MB */
+#define IO_TLB_DEFAULT_SIZE (64UL<<20)
+unsigned long swiotlb_size_or_default(void)
+{
+ unsigned long size;
+
+ size = io_tlb_nslabs << IO_TLB_SHIFT;
+
+ return size ? size : (IO_TLB_DEFAULT_SIZE);
+}
+
+static bool no_iotlb_memory;
+
+void swiotlb_print_info(void)
+{
+ unsigned long bytes = io_tlb_nslabs << IO_TLB_SHIFT;
+ unsigned char *vstart, *vend;
+
+ if (no_iotlb_memory) {
+ pr_warn("software IO TLB: No low mem\n");
+ return;
+ }
+
+ vstart = phys_to_virt(io_tlb_start);
+ vend = phys_to_virt(io_tlb_end);
+
+ printk(KERN_INFO "software IO TLB [mem %#010llx-%#010llx] (%luMB) mapped at [%p-%p]\n",
+ (unsigned long long)io_tlb_start,
+ (unsigned long long)io_tlb_end,
+ bytes >> 20, vstart, vend - 1);
+}
+
+/*
+ * Early SWIOTLB allocation may be too early to allow an architecture to
+ * perform the desired operations. This function allows the architecture to
+ * call SWIOTLB when the operations are possible. It needs to be called
+ * before the SWIOTLB memory is used.
+ */
+void __init swiotlb_update_mem_attributes(void)
+{
+ void *vaddr;
+ unsigned long bytes;
+
+ if (no_iotlb_memory || late_alloc)
+ return;
+
+ vaddr = phys_to_virt(io_tlb_start);
+ bytes = PAGE_ALIGN(io_tlb_nslabs << IO_TLB_SHIFT);
+ set_memory_decrypted((unsigned long)vaddr, bytes >> PAGE_SHIFT);
+ memset(vaddr, 0, bytes);
+
+ vaddr = phys_to_virt(io_tlb_overflow_buffer);
+ bytes = PAGE_ALIGN(io_tlb_overflow);
+ set_memory_decrypted((unsigned long)vaddr, bytes >> PAGE_SHIFT);
+ memset(vaddr, 0, bytes);
+}
+
+int __init swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose)
+{
+ void *v_overflow_buffer;
+ unsigned long i, bytes;
+
+ bytes = nslabs << IO_TLB_SHIFT;
+
+ io_tlb_nslabs = nslabs;
+ io_tlb_start = __pa(tlb);
+ io_tlb_end = io_tlb_start + bytes;
+
+ /*
+ * Get the overflow emergency buffer
+ */
+ v_overflow_buffer = memblock_virt_alloc_low_nopanic(
+ PAGE_ALIGN(io_tlb_overflow),
+ PAGE_SIZE);
+ if (!v_overflow_buffer)
+ return -ENOMEM;
+
+ io_tlb_overflow_buffer = __pa(v_overflow_buffer);
+
+ /*
+ * Allocate and initialize the free list array. This array is used
+ * to find contiguous free memory regions of size up to IO_TLB_SEGSIZE
+ * between io_tlb_start and io_tlb_end.
+ */
+ io_tlb_list = memblock_virt_alloc(
+ PAGE_ALIGN(io_tlb_nslabs * sizeof(int)),
+ PAGE_SIZE);
+ io_tlb_orig_addr = memblock_virt_alloc(
+ PAGE_ALIGN(io_tlb_nslabs * sizeof(phys_addr_t)),
+ PAGE_SIZE);
+ for (i = 0; i < io_tlb_nslabs; i++) {
+ io_tlb_list[i] = IO_TLB_SEGSIZE - OFFSET(i, IO_TLB_SEGSIZE);
+ io_tlb_orig_addr[i] = INVALID_PHYS_ADDR;
+ }
+ io_tlb_index = 0;
+
+ if (verbose)
+ swiotlb_print_info();
+
+ swiotlb_set_max_segment(io_tlb_nslabs << IO_TLB_SHIFT);
+ return 0;
+}
+
+/*
+ * Statically reserve bounce buffer space and initialize bounce buffer data
+ * structures for the software IO TLB used to implement the DMA API.
+ */
+void __init
+swiotlb_init(int verbose)
+{
+ size_t default_size = IO_TLB_DEFAULT_SIZE;
+ unsigned char *vstart;
+ unsigned long bytes;
+
+ if (!io_tlb_nslabs) {
+ io_tlb_nslabs = (default_size >> IO_TLB_SHIFT);
+ io_tlb_nslabs = ALIGN(io_tlb_nslabs, IO_TLB_SEGSIZE);
+ }
+
+ bytes = io_tlb_nslabs << IO_TLB_SHIFT;
+
+ /* Get IO TLB memory from the low pages */
+ vstart = memblock_virt_alloc_low_nopanic(PAGE_ALIGN(bytes), PAGE_SIZE);
+ if (vstart && !swiotlb_init_with_tbl(vstart, io_tlb_nslabs, verbose))
+ return;
+
+ if (io_tlb_start)
+ memblock_free_early(io_tlb_start,
+ PAGE_ALIGN(io_tlb_nslabs << IO_TLB_SHIFT));
+ pr_warn("Cannot allocate SWIOTLB buffer");
+ no_iotlb_memory = true;
+}
+
+/*
+ * Systems with larger DMA zones (those that don't support ISA) can
+ * initialize the swiotlb later using the slab allocator if needed.
+ * This should be just like above, but with some error catching.
+ */
+int
+swiotlb_late_init_with_default_size(size_t default_size)
+{
+ unsigned long bytes, req_nslabs = io_tlb_nslabs;
+ unsigned char *vstart = NULL;
+ unsigned int order;
+ int rc = 0;
+
+ if (!io_tlb_nslabs) {
+ io_tlb_nslabs = (default_size >> IO_TLB_SHIFT);
+ io_tlb_nslabs = ALIGN(io_tlb_nslabs, IO_TLB_SEGSIZE);
+ }
+
+ /*
+ * Get IO TLB memory from the low pages
+ */
+ order = get_order(io_tlb_nslabs << IO_TLB_SHIFT);
+ io_tlb_nslabs = SLABS_PER_PAGE << order;
+ bytes = io_tlb_nslabs << IO_TLB_SHIFT;
+
+ while ((SLABS_PER_PAGE << order) > IO_TLB_MIN_SLABS) {
+ vstart = (void *)__get_free_pages(GFP_DMA | __GFP_NOWARN,
+ order);
+ if (vstart)
+ break;
+ order--;
+ }
+
+ if (!vstart) {
+ io_tlb_nslabs = req_nslabs;
+ return -ENOMEM;
+ }
+ if (order != get_order(bytes)) {
+ printk(KERN_WARNING "Warning: only able to allocate %ld MB "
+ "for software IO TLB\n", (PAGE_SIZE << order) >> 20);
+ io_tlb_nslabs = SLABS_PER_PAGE << order;
+ }
+ rc = swiotlb_late_init_with_tbl(vstart, io_tlb_nslabs);
+ if (rc)
+ free_pages((unsigned long)vstart, order);
+
+ return rc;
+}
+
+int
+swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs)
+{
+ unsigned long i, bytes;
+ unsigned char *v_overflow_buffer;
+
+ bytes = nslabs << IO_TLB_SHIFT;
+
+ io_tlb_nslabs = nslabs;
+ io_tlb_start = virt_to_phys(tlb);
+ io_tlb_end = io_tlb_start + bytes;
+
+ set_memory_decrypted((unsigned long)tlb, bytes >> PAGE_SHIFT);
+ memset(tlb, 0, bytes);
+
+ /*
+ * Get the overflow emergency buffer
+ */
+ v_overflow_buffer = (void *)__get_free_pages(GFP_DMA,
+ get_order(io_tlb_overflow));
+ if (!v_overflow_buffer)
+ goto cleanup2;
+
+ set_memory_decrypted((unsigned long)v_overflow_buffer,
+ io_tlb_overflow >> PAGE_SHIFT);
+ memset(v_overflow_buffer, 0, io_tlb_overflow);
+ io_tlb_overflow_buffer = virt_to_phys(v_overflow_buffer);
+
+ /*
+ * Allocate and initialize the free list array. This array is used
+ * to find contiguous free memory regions of size up to IO_TLB_SEGSIZE
+ * between io_tlb_start and io_tlb_end.
+ */
+ io_tlb_list = (unsigned int *)__get_free_pages(GFP_KERNEL,
+ get_order(io_tlb_nslabs * sizeof(int)));
+ if (!io_tlb_list)
+ goto cleanup3;
+
+ io_tlb_orig_addr = (phys_addr_t *)
+ __get_free_pages(GFP_KERNEL,
+ get_order(io_tlb_nslabs *
+ sizeof(phys_addr_t)));
+ if (!io_tlb_orig_addr)
+ goto cleanup4;
+
+ for (i = 0; i < io_tlb_nslabs; i++) {
+ io_tlb_list[i] = IO_TLB_SEGSIZE - OFFSET(i, IO_TLB_SEGSIZE);
+ io_tlb_orig_addr[i] = INVALID_PHYS_ADDR;
+ }
+ io_tlb_index = 0;
+
+ swiotlb_print_info();
+
+ late_alloc = 1;
+
+ swiotlb_set_max_segment(io_tlb_nslabs << IO_TLB_SHIFT);
+
+ return 0;
+
+cleanup4:
+ free_pages((unsigned long)io_tlb_list, get_order(io_tlb_nslabs *
+ sizeof(int)));
+ io_tlb_list = NULL;
+cleanup3:
+ free_pages((unsigned long)v_overflow_buffer,
+ get_order(io_tlb_overflow));
+ io_tlb_overflow_buffer = 0;
+cleanup2:
+ io_tlb_end = 0;
+ io_tlb_start = 0;
+ io_tlb_nslabs = 0;
+ max_segment = 0;
+ return -ENOMEM;
+}
+
+void __init swiotlb_exit(void)
+{
+ if (!io_tlb_orig_addr)
+ return;
+
+ if (late_alloc) {
+ free_pages((unsigned long)phys_to_virt(io_tlb_overflow_buffer),
+ get_order(io_tlb_overflow));
+ free_pages((unsigned long)io_tlb_orig_addr,
+ get_order(io_tlb_nslabs * sizeof(phys_addr_t)));
+ free_pages((unsigned long)io_tlb_list, get_order(io_tlb_nslabs *
+ sizeof(int)));
+ free_pages((unsigned long)phys_to_virt(io_tlb_start),
+ get_order(io_tlb_nslabs << IO_TLB_SHIFT));
+ } else {
+ memblock_free_late(io_tlb_overflow_buffer,
+ PAGE_ALIGN(io_tlb_overflow));
+ memblock_free_late(__pa(io_tlb_orig_addr),
+ PAGE_ALIGN(io_tlb_nslabs * sizeof(phys_addr_t)));
+ memblock_free_late(__pa(io_tlb_list),
+ PAGE_ALIGN(io_tlb_nslabs * sizeof(int)));
+ memblock_free_late(io_tlb_start,
+ PAGE_ALIGN(io_tlb_nslabs << IO_TLB_SHIFT));
+ }
+ io_tlb_nslabs = 0;
+ max_segment = 0;
+}
+
+int is_swiotlb_buffer(phys_addr_t paddr)
+{
+ return paddr >= io_tlb_start && paddr < io_tlb_end;
+}
+
+/*
+ * Bounce: copy the swiotlb buffer back to the original dma location
+ */
+static void swiotlb_bounce(phys_addr_t orig_addr, phys_addr_t tlb_addr,
+ size_t size, enum dma_data_direction dir)
+{
+ unsigned long pfn = PFN_DOWN(orig_addr);
+ unsigned char *vaddr = phys_to_virt(tlb_addr);
+
+ if (PageHighMem(pfn_to_page(pfn))) {
+ /* The buffer does not have a mapping. Map it in and copy */
+ unsigned int offset = orig_addr & ~PAGE_MASK;
+ char *buffer;
+ unsigned int sz = 0;
+ unsigned long flags;
+
+ while (size) {
+ sz = min_t(size_t, PAGE_SIZE - offset, size);
+
+ local_irq_save(flags);
+ buffer = kmap_atomic(pfn_to_page(pfn));
+ if (dir == DMA_TO_DEVICE)
+ memcpy(vaddr, buffer + offset, sz);
+ else
+ memcpy(buffer + offset, vaddr, sz);
+ kunmap_atomic(buffer);
+ local_irq_restore(flags);
+
+ size -= sz;
+ pfn++;
+ vaddr += sz;
+ offset = 0;
+ }
+ } else if (dir == DMA_TO_DEVICE) {
+ memcpy(vaddr, phys_to_virt(orig_addr), size);
+ } else {
+ memcpy(phys_to_virt(orig_addr), vaddr, size);
+ }
+}
+
+phys_addr_t swiotlb_tbl_map_single(struct device *hwdev,
+ dma_addr_t tbl_dma_addr,
+ phys_addr_t orig_addr, size_t size,
+ enum dma_data_direction dir,
+ unsigned long attrs)
+{
+ unsigned long flags;
+ phys_addr_t tlb_addr;
+ unsigned int nslots, stride, index, wrap;
+ int i;
+ unsigned long mask;
+ unsigned long offset_slots;
+ unsigned long max_slots;
+
+ if (no_iotlb_memory)
+ panic("Can not allocate SWIOTLB buffer earlier and can't now provide you with the DMA bounce buffer");
+
+ if (mem_encrypt_active())
+ pr_warn_once("%s is active and system is using DMA bounce buffers\n",
+ sme_active() ? "SME" : "SEV");
+
+ mask = dma_get_seg_boundary(hwdev);
+
+ tbl_dma_addr &= mask;
+
+ offset_slots = ALIGN(tbl_dma_addr, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT;
+
+ /*
+ * Carefully handle integer overflow which can occur when mask == ~0UL.
+ */
+ max_slots = mask + 1
+ ? ALIGN(mask + 1, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT
+ : 1UL << (BITS_PER_LONG - IO_TLB_SHIFT);
+
+ /*
+ * For mappings greater than or equal to a page, we limit the stride
+ * (and hence alignment) to a page size.
+ */
+ nslots = ALIGN(size, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT;
+ if (size >= PAGE_SIZE)
+ stride = (1 << (PAGE_SHIFT - IO_TLB_SHIFT));
+ else
+ stride = 1;
+
+ BUG_ON(!nslots);
+
+ /*
+ * Find suitable number of IO TLB entries size that will fit this
+ * request and allocate a buffer from that IO TLB pool.
+ */
+ spin_lock_irqsave(&io_tlb_lock, flags);
+ index = ALIGN(io_tlb_index, stride);
+ if (index >= io_tlb_nslabs)
+ index = 0;
+ wrap = index;
+
+ do {
+ while (iommu_is_span_boundary(index, nslots, offset_slots,
+ max_slots)) {
+ index += stride;
+ if (index >= io_tlb_nslabs)
+ index = 0;
+ if (index == wrap)
+ goto not_found;
+ }
+
+ /*
+ * If we find a slot that indicates we have 'nslots' number of
+ * contiguous buffers, we allocate the buffers from that slot
+ * and mark the entries as '0' indicating unavailable.
+ */
+ if (io_tlb_list[index] >= nslots) {
+ int count = 0;
+
+ for (i = index; i < (int) (index + nslots); i++)
+ io_tlb_list[i] = 0;
+ for (i = index - 1; (OFFSET(i, IO_TLB_SEGSIZE) != IO_TLB_SEGSIZE - 1) && io_tlb_list[i]; i--)
+ io_tlb_list[i] = ++count;
+ tlb_addr = io_tlb_start + (index << IO_TLB_SHIFT);
+
+ /*
+ * Update the indices to avoid searching in the next
+ * round.
+ */
+ io_tlb_index = ((index + nslots) < io_tlb_nslabs
+ ? (index + nslots) : 0);
+
+ goto found;
+ }
+ index += stride;
+ if (index >= io_tlb_nslabs)
+ index = 0;
+ } while (index != wrap);
+
+not_found:
+ spin_unlock_irqrestore(&io_tlb_lock, flags);
+ if (!(attrs & DMA_ATTR_NO_WARN) && printk_ratelimit())
+ dev_warn(hwdev, "swiotlb buffer is full (sz: %zd bytes)\n", size);
+ return SWIOTLB_MAP_ERROR;
+found:
+ spin_unlock_irqrestore(&io_tlb_lock, flags);
+
+ /*
+ * Save away the mapping from the original address to the DMA address.
+ * This is needed when we sync the memory. Then we sync the buffer if
+ * needed.
+ */
+ for (i = 0; i < nslots; i++)
+ io_tlb_orig_addr[index+i] = orig_addr + (i << IO_TLB_SHIFT);
+ if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC) &&
+ (dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL))
+ swiotlb_bounce(orig_addr, tlb_addr, size, DMA_TO_DEVICE);
+
+ return tlb_addr;
+}
+
+/*
+ * Allocates bounce buffer and returns its physical address.
+ */
+static phys_addr_t
+map_single(struct device *hwdev, phys_addr_t phys, size_t size,
+ enum dma_data_direction dir, unsigned long attrs)
+{
+ dma_addr_t start_dma_addr;
+
+ if (swiotlb_force == SWIOTLB_NO_FORCE) {
+ dev_warn_ratelimited(hwdev, "Cannot do DMA to address %pa\n",
+ &phys);
+ return SWIOTLB_MAP_ERROR;
+ }
+
+ start_dma_addr = __phys_to_dma(hwdev, io_tlb_start);
+ return swiotlb_tbl_map_single(hwdev, start_dma_addr, phys, size,
+ dir, attrs);
+}
+
+/*
+ * tlb_addr is the physical address of the bounce buffer to unmap.
+ */
+void swiotlb_tbl_unmap_single(struct device *hwdev, phys_addr_t tlb_addr,
+ size_t size, enum dma_data_direction dir,
+ unsigned long attrs)
+{
+ unsigned long flags;
+ int i, count, nslots = ALIGN(size, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT;
+ int index = (tlb_addr - io_tlb_start) >> IO_TLB_SHIFT;
+ phys_addr_t orig_addr = io_tlb_orig_addr[index];
+
+ /*
+ * First, sync the memory before unmapping the entry
+ */
+ if (orig_addr != INVALID_PHYS_ADDR &&
+ !(attrs & DMA_ATTR_SKIP_CPU_SYNC) &&
+ ((dir == DMA_FROM_DEVICE) || (dir == DMA_BIDIRECTIONAL)))
+ swiotlb_bounce(orig_addr, tlb_addr, size, DMA_FROM_DEVICE);
+
+ /*
+ * Return the buffer to the free list by setting the corresponding
+ * entries to indicate the number of contiguous entries available.
+ * While returning the entries to the free list, we merge the entries
+ * with slots below and above the pool being returned.
+ */
+ spin_lock_irqsave(&io_tlb_lock, flags);
+ {
+ count = ((index + nslots) < ALIGN(index + 1, IO_TLB_SEGSIZE) ?
+ io_tlb_list[index + nslots] : 0);
+ /*
+ * Step 1: return the slots to the free list, merging the
+ * slots with superceeding slots
+ */
+ for (i = index + nslots - 1; i >= index; i--) {
+ io_tlb_list[i] = ++count;
+ io_tlb_orig_addr[i] = INVALID_PHYS_ADDR;
+ }
+ /*
+ * Step 2: merge the returned slots with the preceding slots,
+ * if available (non zero)
+ */
+ for (i = index - 1; (OFFSET(i, IO_TLB_SEGSIZE) != IO_TLB_SEGSIZE -1) && io_tlb_list[i]; i--)
+ io_tlb_list[i] = ++count;
+ }
+ spin_unlock_irqrestore(&io_tlb_lock, flags);
+}
+
+void swiotlb_tbl_sync_single(struct device *hwdev, phys_addr_t tlb_addr,
+ size_t size, enum dma_data_direction dir,
+ enum dma_sync_target target)
+{
+ int index = (tlb_addr - io_tlb_start) >> IO_TLB_SHIFT;
+ phys_addr_t orig_addr = io_tlb_orig_addr[index];
+
+ if (orig_addr == INVALID_PHYS_ADDR)
+ return;
+ orig_addr += (unsigned long)tlb_addr & ((1 << IO_TLB_SHIFT) - 1);
+
+ switch (target) {
+ case SYNC_FOR_CPU:
+ if (likely(dir == DMA_FROM_DEVICE || dir == DMA_BIDIRECTIONAL))
+ swiotlb_bounce(orig_addr, tlb_addr,
+ size, DMA_FROM_DEVICE);
+ else
+ BUG_ON(dir != DMA_TO_DEVICE);
+ break;
+ case SYNC_FOR_DEVICE:
+ if (likely(dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL))
+ swiotlb_bounce(orig_addr, tlb_addr,
+ size, DMA_TO_DEVICE);
+ else
+ BUG_ON(dir != DMA_FROM_DEVICE);
+ break;
+ default:
+ BUG();
+ }
+}
+
+static inline bool dma_coherent_ok(struct device *dev, dma_addr_t addr,
+ size_t size)
+{
+ u64 mask = DMA_BIT_MASK(32);
+
+ if (dev && dev->coherent_dma_mask)
+ mask = dev->coherent_dma_mask;
+ return addr + size - 1 <= mask;
+}
+
+static void *
+swiotlb_alloc_buffer(struct device *dev, size_t size, dma_addr_t *dma_handle,
+ unsigned long attrs)
+{
+ phys_addr_t phys_addr;
+
+ if (swiotlb_force == SWIOTLB_NO_FORCE)
+ goto out_warn;
+
+ phys_addr = swiotlb_tbl_map_single(dev,
+ __phys_to_dma(dev, io_tlb_start),
+ 0, size, DMA_FROM_DEVICE, attrs);
+ if (phys_addr == SWIOTLB_MAP_ERROR)
+ goto out_warn;
+
+ *dma_handle = __phys_to_dma(dev, phys_addr);
+ if (!dma_coherent_ok(dev, *dma_handle, size))
+ goto out_unmap;
+
+ memset(phys_to_virt(phys_addr), 0, size);
+ return phys_to_virt(phys_addr);
+
+out_unmap:
+ dev_warn(dev, "hwdev DMA mask = 0x%016Lx, dev_addr = 0x%016Lx\n",
+ (unsigned long long)dev->coherent_dma_mask,
+ (unsigned long long)*dma_handle);
+
+ /*
+ * DMA_TO_DEVICE to avoid memcpy in unmap_single.
+ * DMA_ATTR_SKIP_CPU_SYNC is optional.
+ */
+ swiotlb_tbl_unmap_single(dev, phys_addr, size, DMA_TO_DEVICE,
+ DMA_ATTR_SKIP_CPU_SYNC);
+out_warn:
+ if (!(attrs & DMA_ATTR_NO_WARN) && printk_ratelimit()) {
+ dev_warn(dev,
+ "swiotlb: coherent allocation failed, size=%zu\n",
+ size);
+ dump_stack();
+ }
+ return NULL;
+}
+
+static bool swiotlb_free_buffer(struct device *dev, size_t size,
+ dma_addr_t dma_addr)
+{
+ phys_addr_t phys_addr = dma_to_phys(dev, dma_addr);
+
+ WARN_ON_ONCE(irqs_disabled());
+
+ if (!is_swiotlb_buffer(phys_addr))
+ return false;
+
+ /*
+ * DMA_TO_DEVICE to avoid memcpy in swiotlb_tbl_unmap_single.
+ * DMA_ATTR_SKIP_CPU_SYNC is optional.
+ */
+ swiotlb_tbl_unmap_single(dev, phys_addr, size, DMA_TO_DEVICE,
+ DMA_ATTR_SKIP_CPU_SYNC);
+ return true;
+}
+
+static void
+swiotlb_full(struct device *dev, size_t size, enum dma_data_direction dir,
+ int do_panic)
+{
+ if (swiotlb_force == SWIOTLB_NO_FORCE)
+ return;
+
+ /*
+ * Ran out of IOMMU space for this operation. This is very bad.
+ * Unfortunately the drivers cannot handle this operation properly.
+ * unless they check for dma_mapping_error (most don't)
+ * When the mapping is small enough return a static buffer to limit
+ * the damage, or panic when the transfer is too big.
+ */
+ dev_err_ratelimited(dev, "DMA: Out of SW-IOMMU space for %zu bytes\n",
+ size);
+
+ if (size <= io_tlb_overflow || !do_panic)
+ return;
+
+ if (dir == DMA_BIDIRECTIONAL)
+ panic("DMA: Random memory could be DMA accessed\n");
+ if (dir == DMA_FROM_DEVICE)
+ panic("DMA: Random memory could be DMA written\n");
+ if (dir == DMA_TO_DEVICE)
+ panic("DMA: Random memory could be DMA read\n");
+}
+
+/*
+ * Map a single buffer of the indicated size for DMA in streaming mode. The
+ * physical address to use is returned.
+ *
+ * Once the device is given the dma address, the device owns this memory until
+ * either swiotlb_unmap_page or swiotlb_dma_sync_single is performed.
+ */
+dma_addr_t swiotlb_map_page(struct device *dev, struct page *page,
+ unsigned long offset, size_t size,
+ enum dma_data_direction dir,
+ unsigned long attrs)
+{
+ phys_addr_t map, phys = page_to_phys(page) + offset;
+ dma_addr_t dev_addr = phys_to_dma(dev, phys);
+
+ BUG_ON(dir == DMA_NONE);
+ /*
+ * If the address happens to be in the device's DMA window,
+ * we can safely return the device addr and not worry about bounce
+ * buffering it.
+ */
+ if (dma_capable(dev, dev_addr, size) && swiotlb_force != SWIOTLB_FORCE)
+ return dev_addr;
+
+ trace_swiotlb_bounced(dev, dev_addr, size, swiotlb_force);
+
+ /* Oh well, have to allocate and map a bounce buffer. */
+ map = map_single(dev, phys, size, dir, attrs);
+ if (map == SWIOTLB_MAP_ERROR) {
+ swiotlb_full(dev, size, dir, 1);
+ return __phys_to_dma(dev, io_tlb_overflow_buffer);
+ }
+
+ dev_addr = __phys_to_dma(dev, map);
+
+ /* Ensure that the address returned is DMA'ble */
+ if (dma_capable(dev, dev_addr, size))
+ return dev_addr;
+
+ attrs |= DMA_ATTR_SKIP_CPU_SYNC;
+ swiotlb_tbl_unmap_single(dev, map, size, dir, attrs);
+
+ return __phys_to_dma(dev, io_tlb_overflow_buffer);
+}
+
+/*
+ * Unmap a single streaming mode DMA translation. The dma_addr and size must
+ * match what was provided for in a previous swiotlb_map_page call. All
+ * other usages are undefined.
+ *
+ * After this call, reads by the cpu to the buffer are guaranteed to see
+ * whatever the device wrote there.
+ */
+static void unmap_single(struct device *hwdev, dma_addr_t dev_addr,
+ size_t size, enum dma_data_direction dir,
+ unsigned long attrs)
+{
+ phys_addr_t paddr = dma_to_phys(hwdev, dev_addr);
+
+ BUG_ON(dir == DMA_NONE);
+
+ if (is_swiotlb_buffer(paddr)) {
+ swiotlb_tbl_unmap_single(hwdev, paddr, size, dir, attrs);
+ return;
+ }
+
+ if (dir != DMA_FROM_DEVICE)
+ return;
+
+ /*
+ * phys_to_virt doesn't work with hihgmem page but we could
+ * call dma_mark_clean() with hihgmem page here. However, we
+ * are fine since dma_mark_clean() is null on POWERPC. We can
+ * make dma_mark_clean() take a physical address if necessary.
+ */
+ dma_mark_clean(phys_to_virt(paddr), size);
+}
+
+void swiotlb_unmap_page(struct device *hwdev, dma_addr_t dev_addr,
+ size_t size, enum dma_data_direction dir,
+ unsigned long attrs)
+{
+ unmap_single(hwdev, dev_addr, size, dir, attrs);
+}
+
+/*
+ * Make physical memory consistent for a single streaming mode DMA translation
+ * after a transfer.
+ *
+ * If you perform a swiotlb_map_page() but wish to interrogate the buffer
+ * using the cpu, yet do not wish to teardown the dma mapping, you must
+ * call this function before doing so. At the next point you give the dma
+ * address back to the card, you must first perform a
+ * swiotlb_dma_sync_for_device, and then the device again owns the buffer
+ */
+static void
+swiotlb_sync_single(struct device *hwdev, dma_addr_t dev_addr,
+ size_t size, enum dma_data_direction dir,
+ enum dma_sync_target target)
+{
+ phys_addr_t paddr = dma_to_phys(hwdev, dev_addr);
+
+ BUG_ON(dir == DMA_NONE);
+
+ if (is_swiotlb_buffer(paddr)) {
+ swiotlb_tbl_sync_single(hwdev, paddr, size, dir, target);
+ return;
+ }
+
+ if (dir != DMA_FROM_DEVICE)
+ return;
+
+ dma_mark_clean(phys_to_virt(paddr), size);
+}
+
+void
+swiotlb_sync_single_for_cpu(struct device *hwdev, dma_addr_t dev_addr,
+ size_t size, enum dma_data_direction dir)
+{
+ swiotlb_sync_single(hwdev, dev_addr, size, dir, SYNC_FOR_CPU);
+}
+
+void
+swiotlb_sync_single_for_device(struct device *hwdev, dma_addr_t dev_addr,
+ size_t size, enum dma_data_direction dir)
+{
+ swiotlb_sync_single(hwdev, dev_addr, size, dir, SYNC_FOR_DEVICE);
+}
+
+/*
+ * Map a set of buffers described by scatterlist in streaming mode for DMA.
+ * This is the scatter-gather version of the above swiotlb_map_page
+ * interface. Here the scatter gather list elements are each tagged with the
+ * appropriate dma address and length. They are obtained via
+ * sg_dma_{address,length}(SG).
+ *
+ * NOTE: An implementation may be able to use a smaller number of
+ * DMA address/length pairs than there are SG table elements.
+ * (for example via virtual mapping capabilities)
+ * The routine returns the number of addr/length pairs actually
+ * used, at most nents.
+ *
+ * Device ownership issues as mentioned above for swiotlb_map_page are the
+ * same here.
+ */
+int
+swiotlb_map_sg_attrs(struct device *hwdev, struct scatterlist *sgl, int nelems,
+ enum dma_data_direction dir, unsigned long attrs)
+{
+ struct scatterlist *sg;
+ int i;
+
+ BUG_ON(dir == DMA_NONE);
+
+ for_each_sg(sgl, sg, nelems, i) {
+ phys_addr_t paddr = sg_phys(sg);
+ dma_addr_t dev_addr = phys_to_dma(hwdev, paddr);
+
+ if (swiotlb_force == SWIOTLB_FORCE ||
+ !dma_capable(hwdev, dev_addr, sg->length)) {
+ phys_addr_t map = map_single(hwdev, sg_phys(sg),
+ sg->length, dir, attrs);
+ if (map == SWIOTLB_MAP_ERROR) {
+ /* Don't panic here, we expect map_sg users
+ to do proper error handling. */
+ swiotlb_full(hwdev, sg->length, dir, 0);
+ attrs |= DMA_ATTR_SKIP_CPU_SYNC;
+ swiotlb_unmap_sg_attrs(hwdev, sgl, i, dir,
+ attrs);
+ sg_dma_len(sgl) = 0;
+ return 0;
+ }
+ sg->dma_address = __phys_to_dma(hwdev, map);
+ } else
+ sg->dma_address = dev_addr;
+ sg_dma_len(sg) = sg->length;
+ }
+ return nelems;
+}
+
+/*
+ * Unmap a set of streaming mode DMA translations. Again, cpu read rules
+ * concerning calls here are the same as for swiotlb_unmap_page() above.
+ */
+void
+swiotlb_unmap_sg_attrs(struct device *hwdev, struct scatterlist *sgl,
+ int nelems, enum dma_data_direction dir,
+ unsigned long attrs)
+{
+ struct scatterlist *sg;
+ int i;
+
+ BUG_ON(dir == DMA_NONE);
+
+ for_each_sg(sgl, sg, nelems, i)
+ unmap_single(hwdev, sg->dma_address, sg_dma_len(sg), dir,
+ attrs);
+}
+
+/*
+ * Make physical memory consistent for a set of streaming mode DMA translations
+ * after a transfer.
+ *
+ * The same as swiotlb_sync_single_* but for a scatter-gather list, same rules
+ * and usage.
+ */
+static void
+swiotlb_sync_sg(struct device *hwdev, struct scatterlist *sgl,
+ int nelems, enum dma_data_direction dir,
+ enum dma_sync_target target)
+{
+ struct scatterlist *sg;
+ int i;
+
+ for_each_sg(sgl, sg, nelems, i)
+ swiotlb_sync_single(hwdev, sg->dma_address,
+ sg_dma_len(sg), dir, target);
+}
+
+void
+swiotlb_sync_sg_for_cpu(struct device *hwdev, struct scatterlist *sg,
+ int nelems, enum dma_data_direction dir)
+{
+ swiotlb_sync_sg(hwdev, sg, nelems, dir, SYNC_FOR_CPU);
+}
+
+void
+swiotlb_sync_sg_for_device(struct device *hwdev, struct scatterlist *sg,
+ int nelems, enum dma_data_direction dir)
+{
+ swiotlb_sync_sg(hwdev, sg, nelems, dir, SYNC_FOR_DEVICE);
+}
+
+int
+swiotlb_dma_mapping_error(struct device *hwdev, dma_addr_t dma_addr)
+{
+ return (dma_addr == __phys_to_dma(hwdev, io_tlb_overflow_buffer));
+}
+
+/*
+ * Return whether the given device DMA address mask can be supported
+ * properly. For example, if your device can only drive the low 24-bits
+ * during bus mastering, then you would pass 0x00ffffff as the mask to
+ * this function.
+ */
+int
+swiotlb_dma_supported(struct device *hwdev, u64 mask)
+{
+ return __phys_to_dma(hwdev, io_tlb_end - 1) <= mask;
+}
+
+void *swiotlb_alloc(struct device *dev, size_t size, dma_addr_t *dma_handle,
+ gfp_t gfp, unsigned long attrs)
+{
+ void *vaddr;
+
+ /* temporary workaround: */
+ if (gfp & __GFP_NOWARN)
+ attrs |= DMA_ATTR_NO_WARN;
+
+ /*
+ * Don't print a warning when the first allocation attempt fails.
+ * swiotlb_alloc_coherent() will print a warning when the DMA memory
+ * allocation ultimately failed.
+ */
+ gfp |= __GFP_NOWARN;
+
+ vaddr = dma_direct_alloc(dev, size, dma_handle, gfp, attrs);
+ if (!vaddr)
+ vaddr = swiotlb_alloc_buffer(dev, size, dma_handle, attrs);
+ return vaddr;
+}
+
+void swiotlb_free(struct device *dev, size_t size, void *vaddr,
+ dma_addr_t dma_addr, unsigned long attrs)
+{
+ if (!swiotlb_free_buffer(dev, size, dma_addr))
+ dma_direct_free(dev, size, vaddr, dma_addr, attrs);
+}
+
+const struct dma_map_ops swiotlb_dma_ops = {
+ .mapping_error = swiotlb_dma_mapping_error,
+ .alloc = swiotlb_alloc,
+ .free = swiotlb_free,
+ .sync_single_for_cpu = swiotlb_sync_single_for_cpu,
+ .sync_single_for_device = swiotlb_sync_single_for_device,
+ .sync_sg_for_cpu = swiotlb_sync_sg_for_cpu,
+ .sync_sg_for_device = swiotlb_sync_sg_for_device,
+ .map_sg = swiotlb_map_sg_attrs,
+ .unmap_sg = swiotlb_unmap_sg_attrs,
+ .map_page = swiotlb_map_page,
+ .unmap_page = swiotlb_unmap_page,
+ .dma_supported = dma_direct_supported,
+};
+EXPORT_SYMBOL(swiotlb_dma_ops);
diff --git a/kernel/dma/virt.c b/kernel/dma/virt.c
new file mode 100644
index 000000000000..631ddec4b60a
--- /dev/null
+++ b/kernel/dma/virt.c
@@ -0,0 +1,59 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * DMA operations that map to virtual addresses without flushing memory.
+ */
+#include <linux/export.h>
+#include <linux/mm.h>
+#include <linux/dma-mapping.h>
+#include <linux/scatterlist.h>
+
+static void *dma_virt_alloc(struct device *dev, size_t size,
+ dma_addr_t *dma_handle, gfp_t gfp,
+ unsigned long attrs)
+{
+ void *ret;
+
+ ret = (void *)__get_free_pages(gfp, get_order(size));
+ if (ret)
+ *dma_handle = (uintptr_t)ret;
+ return ret;
+}
+
+static void dma_virt_free(struct device *dev, size_t size,
+ void *cpu_addr, dma_addr_t dma_addr,
+ unsigned long attrs)
+{
+ free_pages((unsigned long)cpu_addr, get_order(size));
+}
+
+static dma_addr_t dma_virt_map_page(struct device *dev, struct page *page,
+ unsigned long offset, size_t size,
+ enum dma_data_direction dir,
+ unsigned long attrs)
+{
+ return (uintptr_t)(page_address(page) + offset);
+}
+
+static int dma_virt_map_sg(struct device *dev, struct scatterlist *sgl,
+ int nents, enum dma_data_direction dir,
+ unsigned long attrs)
+{
+ int i;
+ struct scatterlist *sg;
+
+ for_each_sg(sgl, sg, nents, i) {
+ BUG_ON(!sg_page(sg));
+ sg_dma_address(sg) = (uintptr_t)sg_virt(sg);
+ sg_dma_len(sg) = sg->length;
+ }
+
+ return nents;
+}
+
+const struct dma_map_ops dma_virt_ops = {
+ .alloc = dma_virt_alloc,
+ .free = dma_virt_free,
+ .map_page = dma_virt_map_page,
+ .map_sg = dma_virt_map_sg,
+};
+EXPORT_SYMBOL(dma_virt_ops);
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 80cca2b30c4f..eec2d5fb676b 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -6343,7 +6343,7 @@ static u64 perf_virt_to_phys(u64 virt)
static struct perf_callchain_entry __empty_callchain = { .nr = 0, };
-static struct perf_callchain_entry *
+struct perf_callchain_entry *
perf_callchain(struct perf_event *event, struct pt_regs *regs)
{
bool kernel = !event->attr.exclude_callchain_kernel;
@@ -6382,7 +6382,9 @@ void perf_prepare_sample(struct perf_event_header *header,
if (sample_type & PERF_SAMPLE_CALLCHAIN) {
int size = 1;
- data->callchain = perf_callchain(event, regs);
+ if (!(sample_type & __PERF_SAMPLE_CALLCHAIN_EARLY))
+ data->callchain = perf_callchain(event, regs);
+
size += data->callchain->nr;
header->size += size * sizeof(u64);
@@ -6482,7 +6484,7 @@ void perf_prepare_sample(struct perf_event_header *header,
data->phys_addr = perf_virt_to_phys(data->addr);
}
-static void __always_inline
+static __always_inline void
__perf_event_output(struct perf_event *event,
struct perf_sample_data *data,
struct pt_regs *regs,
@@ -7335,6 +7337,10 @@ static bool perf_addr_filter_match(struct perf_addr_filter *filter,
struct file *file, unsigned long offset,
unsigned long size)
{
+ /* d_inode(NULL) won't be equal to any mapped user-space file */
+ if (!filter->path.dentry)
+ return false;
+
if (d_inode(filter->path.dentry) != file_inode(file))
return false;
diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c
index 045a37e9ddee..5d3cf407e374 100644
--- a/kernel/events/ring_buffer.c
+++ b/kernel/events/ring_buffer.c
@@ -103,7 +103,7 @@ out:
preempt_enable();
}
-static bool __always_inline
+static __always_inline bool
ring_buffer_has_space(unsigned long head, unsigned long tail,
unsigned long data_size, unsigned int size,
bool backward)
@@ -114,7 +114,7 @@ ring_buffer_has_space(unsigned long head, unsigned long tail,
return CIRC_SPACE(tail, head, data_size) >= size;
}
-static int __always_inline
+static __always_inline int
__perf_output_begin(struct perf_output_handle *handle,
struct perf_event *event, unsigned int size,
bool backward)
@@ -414,7 +414,7 @@ err:
}
EXPORT_SYMBOL_GPL(perf_aux_output_begin);
-static bool __always_inline rb_need_aux_wakeup(struct ring_buffer *rb)
+static __always_inline bool rb_need_aux_wakeup(struct ring_buffer *rb)
{
if (rb->aux_overwrite)
return false;
diff --git a/kernel/fork.c b/kernel/fork.c
index 9440d61b925c..1b27babc4c78 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -303,11 +303,36 @@ struct kmem_cache *files_cachep;
struct kmem_cache *fs_cachep;
/* SLAB cache for vm_area_struct structures */
-struct kmem_cache *vm_area_cachep;
+static struct kmem_cache *vm_area_cachep;
/* SLAB cache for mm_struct structures (tsk->mm) */
static struct kmem_cache *mm_cachep;
+struct vm_area_struct *vm_area_alloc(struct mm_struct *mm)
+{
+ struct vm_area_struct *vma = kmem_cache_zalloc(vm_area_cachep, GFP_KERNEL);
+
+ if (vma)
+ vma_init(vma, mm);
+ return vma;
+}
+
+struct vm_area_struct *vm_area_dup(struct vm_area_struct *orig)
+{
+ struct vm_area_struct *new = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL);
+
+ if (new) {
+ *new = *orig;
+ INIT_LIST_HEAD(&new->anon_vma_chain);
+ }
+ return new;
+}
+
+void vm_area_free(struct vm_area_struct *vma)
+{
+ kmem_cache_free(vm_area_cachep, vma);
+}
+
static void account_kernel_stack(struct task_struct *tsk, int account)
{
void *stack = task_stack_page(tsk);
@@ -455,11 +480,9 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm,
goto fail_nomem;
charge = len;
}
- tmp = kmem_cache_alloc(vm_area_cachep, GFP_KERNEL);
+ tmp = vm_area_dup(mpnt);
if (!tmp)
goto fail_nomem;
- *tmp = *mpnt;
- INIT_LIST_HEAD(&tmp->anon_vma_chain);
retval = vma_dup_policy(mpnt, tmp);
if (retval)
goto fail_nomem_policy;
@@ -539,7 +562,7 @@ fail_uprobe_end:
fail_nomem_anon_vma_fork:
mpol_put(vma_policy(tmp));
fail_nomem_policy:
- kmem_cache_free(vm_area_cachep, tmp);
+ vm_area_free(tmp);
fail_nomem:
retval = -ENOMEM;
vm_unacct_memory(charge);
diff --git a/kernel/irq/debugfs.c b/kernel/irq/debugfs.c
index 4dadeb3d6666..6f636136cccc 100644
--- a/kernel/irq/debugfs.c
+++ b/kernel/irq/debugfs.c
@@ -55,6 +55,7 @@ static const struct irq_bit_descr irqchip_flags[] = {
BIT_MASK_DESCR(IRQCHIP_SKIP_SET_WAKE),
BIT_MASK_DESCR(IRQCHIP_ONESHOT_SAFE),
BIT_MASK_DESCR(IRQCHIP_EOI_THREADED),
+ BIT_MASK_DESCR(IRQCHIP_SUPPORTS_LEVEL_MSI),
};
static void
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index daeabd791d58..9a8b7ba9aa88 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -1068,6 +1068,13 @@ static int irq_setup_forced_threading(struct irqaction *new)
if (new->flags & (IRQF_NO_THREAD | IRQF_PERCPU | IRQF_ONESHOT))
return 0;
+ /*
+ * No further action required for interrupts which are requested as
+ * threaded interrupts already
+ */
+ if (new->handler == irq_default_primary_handler)
+ return 0;
+
new->flags |= IRQF_ONESHOT;
/*
@@ -1075,7 +1082,7 @@ static int irq_setup_forced_threading(struct irqaction *new)
* thread handler. We force thread them as well by creating a
* secondary action.
*/
- if (new->handler != irq_default_primary_handler && new->thread_fn) {
+ if (new->handler && new->thread_fn) {
/* Allocate the secondary action */
new->secondary = kzalloc(sizeof(struct irqaction), GFP_KERNEL);
if (!new->secondary)
diff --git a/kernel/kthread.c b/kernel/kthread.c
index 481951bf091d..486dedbd9af5 100644
--- a/kernel/kthread.c
+++ b/kernel/kthread.c
@@ -177,9 +177,20 @@ void *kthread_probe_data(struct task_struct *task)
static void __kthread_parkme(struct kthread *self)
{
for (;;) {
- set_current_state(TASK_PARKED);
+ /*
+ * TASK_PARKED is a special state; we must serialize against
+ * possible pending wakeups to avoid store-store collisions on
+ * task->state.
+ *
+ * Such a collision might possibly result in the task state
+ * changin from TASK_PARKED and us failing the
+ * wait_task_inactive() in kthread_park().
+ */
+ set_special_state(TASK_PARKED);
if (!test_bit(KTHREAD_SHOULD_PARK, &self->flags))
break;
+
+ complete_all(&self->parked);
schedule();
}
__set_current_state(TASK_RUNNING);
@@ -191,11 +202,6 @@ void kthread_parkme(void)
}
EXPORT_SYMBOL_GPL(kthread_parkme);
-void kthread_park_complete(struct task_struct *k)
-{
- complete_all(&to_kthread(k)->parked);
-}
-
static int kthread(void *_create)
{
/* Copy data: it's on kthread's stack */
@@ -319,8 +325,14 @@ struct task_struct *__kthread_create_on_node(int (*threadfn)(void *data),
task = create->result;
if (!IS_ERR(task)) {
static const struct sched_param param = { .sched_priority = 0 };
+ char name[TASK_COMM_LEN];
- vsnprintf(task->comm, sizeof(task->comm), namefmt, args);
+ /*
+ * task is already visible to other tasks, so updating
+ * COMM must be protected.
+ */
+ vsnprintf(name, sizeof(name), namefmt, args);
+ set_task_comm(task, name);
/*
* root may have changed our (kthreadd's) priority or CPU mask.
* The kernel thread should not inherit these properties.
@@ -461,6 +473,9 @@ void kthread_unpark(struct task_struct *k)
reinit_completion(&kthread->parked);
clear_bit(KTHREAD_SHOULD_PARK, &kthread->flags);
+ /*
+ * __kthread_parkme() will either see !SHOULD_PARK or get the wakeup.
+ */
wake_up_state(k, TASK_PARKED);
}
EXPORT_SYMBOL_GPL(kthread_unpark);
@@ -487,7 +502,16 @@ int kthread_park(struct task_struct *k)
set_bit(KTHREAD_SHOULD_PARK, &kthread->flags);
if (k != current) {
wake_up_process(k);
+ /*
+ * Wait for __kthread_parkme() to complete(), this means we
+ * _will_ have TASK_PARKED and are about to call schedule().
+ */
wait_for_completion(&kthread->parked);
+ /*
+ * Now wait for that schedule() to complete and the task to
+ * get scheduled out.
+ */
+ WARN_ON_ONCE(!wait_task_inactive(k, TASK_PARKED));
}
return 0;
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index edcac5de7ebc..5fa4d3138bf1 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -1265,11 +1265,11 @@ unsigned long lockdep_count_forward_deps(struct lock_class *class)
this.parent = NULL;
this.class = class;
- local_irq_save(flags);
+ raw_local_irq_save(flags);
arch_spin_lock(&lockdep_lock);
ret = __lockdep_count_forward_deps(&this);
arch_spin_unlock(&lockdep_lock);
- local_irq_restore(flags);
+ raw_local_irq_restore(flags);
return ret;
}
@@ -1292,11 +1292,11 @@ unsigned long lockdep_count_backward_deps(struct lock_class *class)
this.parent = NULL;
this.class = class;
- local_irq_save(flags);
+ raw_local_irq_save(flags);
arch_spin_lock(&lockdep_lock);
ret = __lockdep_count_backward_deps(&this);
arch_spin_unlock(&lockdep_lock);
- local_irq_restore(flags);
+ raw_local_irq_restore(flags);
return ret;
}
@@ -4411,7 +4411,7 @@ void debug_check_no_locks_freed(const void *mem_from, unsigned long mem_len)
if (unlikely(!debug_locks))
return;
- local_irq_save(flags);
+ raw_local_irq_save(flags);
for (i = 0; i < curr->lockdep_depth; i++) {
hlock = curr->held_locks + i;
@@ -4422,7 +4422,7 @@ void debug_check_no_locks_freed(const void *mem_from, unsigned long mem_len)
print_freed_lock_bug(curr, mem_from, mem_from + mem_len, hlock);
break;
}
- local_irq_restore(flags);
+ raw_local_irq_restore(flags);
}
EXPORT_SYMBOL_GPL(debug_check_no_locks_freed);
diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c
index 4f014be7a4b8..2823d4163a37 100644
--- a/kernel/locking/rtmutex.c
+++ b/kernel/locking/rtmutex.c
@@ -1465,6 +1465,29 @@ rt_mutex_fastunlock(struct rt_mutex *lock,
rt_mutex_postunlock(&wake_q);
}
+static inline void __rt_mutex_lock(struct rt_mutex *lock, unsigned int subclass)
+{
+ might_sleep();
+
+ mutex_acquire(&lock->dep_map, subclass, 0, _RET_IP_);
+ rt_mutex_fastlock(lock, TASK_UNINTERRUPTIBLE, rt_mutex_slowlock);
+}
+
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+/**
+ * rt_mutex_lock_nested - lock a rt_mutex
+ *
+ * @lock: the rt_mutex to be locked
+ * @subclass: the lockdep subclass
+ */
+void __sched rt_mutex_lock_nested(struct rt_mutex *lock, unsigned int subclass)
+{
+ __rt_mutex_lock(lock, subclass);
+}
+EXPORT_SYMBOL_GPL(rt_mutex_lock_nested);
+#endif
+
+#ifndef CONFIG_DEBUG_LOCK_ALLOC
/**
* rt_mutex_lock - lock a rt_mutex
*
@@ -1472,12 +1495,10 @@ rt_mutex_fastunlock(struct rt_mutex *lock,
*/
void __sched rt_mutex_lock(struct rt_mutex *lock)
{
- might_sleep();
-
- mutex_acquire(&lock->dep_map, 0, 0, _RET_IP_);
- rt_mutex_fastlock(lock, TASK_UNINTERRUPTIBLE, rt_mutex_slowlock);
+ __rt_mutex_lock(lock, 0);
}
EXPORT_SYMBOL_GPL(rt_mutex_lock);
+#endif
/**
* rt_mutex_lock_interruptible - lock a rt_mutex interruptible
diff --git a/kernel/locking/rwsem.c b/kernel/locking/rwsem.c
index bc1e507be9ff..776308d2fa9e 100644
--- a/kernel/locking/rwsem.c
+++ b/kernel/locking/rwsem.c
@@ -181,6 +181,7 @@ void down_read_non_owner(struct rw_semaphore *sem)
might_sleep();
__down_read(sem);
+ rwsem_set_reader_owned(sem);
}
EXPORT_SYMBOL(down_read_non_owner);
diff --git a/kernel/memremap.c b/kernel/memremap.c
index 5857267a4af5..38283363da06 100644
--- a/kernel/memremap.c
+++ b/kernel/memremap.c
@@ -176,10 +176,27 @@ void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap)
unsigned long pfn, pgoff, order;
pgprot_t pgprot = PAGE_KERNEL;
int error, nid, is_ram;
+ struct dev_pagemap *conflict_pgmap;
align_start = res->start & ~(SECTION_SIZE - 1);
align_size = ALIGN(res->start + resource_size(res), SECTION_SIZE)
- align_start;
+ align_end = align_start + align_size - 1;
+
+ conflict_pgmap = get_dev_pagemap(PHYS_PFN(align_start), NULL);
+ if (conflict_pgmap) {
+ dev_WARN(dev, "Conflicting mapping in same section\n");
+ put_dev_pagemap(conflict_pgmap);
+ return ERR_PTR(-ENOMEM);
+ }
+
+ conflict_pgmap = get_dev_pagemap(PHYS_PFN(align_end), NULL);
+ if (conflict_pgmap) {
+ dev_WARN(dev, "Conflicting mapping in same section\n");
+ put_dev_pagemap(conflict_pgmap);
+ return ERR_PTR(-ENOMEM);
+ }
+
is_ram = region_intersects(align_start, align_size,
IORESOURCE_SYSTEM_RAM, IORES_DESC_NONE);
@@ -199,7 +216,6 @@ void *devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap)
mutex_lock(&pgmap_lock);
error = 0;
- align_end = align_start + align_size - 1;
foreach_order_pgoff(res, order, pgoff) {
error = __radix_tree_insert(&pgmap_radix,
@@ -305,7 +321,7 @@ EXPORT_SYMBOL_GPL(get_dev_pagemap);
#ifdef CONFIG_DEV_PAGEMAP_OPS
DEFINE_STATIC_KEY_FALSE(devmap_managed_key);
-EXPORT_SYMBOL_GPL(devmap_managed_key);
+EXPORT_SYMBOL(devmap_managed_key);
static atomic_t devmap_enable;
/*
@@ -346,5 +362,5 @@ void __put_devmap_managed_page(struct page *page)
} else if (!count)
__put_page(page);
}
-EXPORT_SYMBOL_GPL(__put_devmap_managed_page);
+EXPORT_SYMBOL(__put_devmap_managed_page);
#endif /* CONFIG_DEV_PAGEMAP_OPS */
diff --git a/kernel/rseq.c b/kernel/rseq.c
index ae306f90c514..c6242d8594dc 100644
--- a/kernel/rseq.c
+++ b/kernel/rseq.c
@@ -85,9 +85,9 @@ static int rseq_update_cpu_id(struct task_struct *t)
{
u32 cpu_id = raw_smp_processor_id();
- if (__put_user(cpu_id, &t->rseq->cpu_id_start))
+ if (put_user(cpu_id, &t->rseq->cpu_id_start))
return -EFAULT;
- if (__put_user(cpu_id, &t->rseq->cpu_id))
+ if (put_user(cpu_id, &t->rseq->cpu_id))
return -EFAULT;
trace_rseq_update(t);
return 0;
@@ -100,14 +100,14 @@ static int rseq_reset_rseq_cpu_id(struct task_struct *t)
/*
* Reset cpu_id_start to its initial state (0).
*/
- if (__put_user(cpu_id_start, &t->rseq->cpu_id_start))
+ if (put_user(cpu_id_start, &t->rseq->cpu_id_start))
return -EFAULT;
/*
* Reset cpu_id to RSEQ_CPU_ID_UNINITIALIZED, so any user coming
* in after unregistration can figure out that rseq needs to be
* registered again.
*/
- if (__put_user(cpu_id, &t->rseq->cpu_id))
+ if (put_user(cpu_id, &t->rseq->cpu_id))
return -EFAULT;
return 0;
}
@@ -115,29 +115,36 @@ static int rseq_reset_rseq_cpu_id(struct task_struct *t)
static int rseq_get_rseq_cs(struct task_struct *t, struct rseq_cs *rseq_cs)
{
struct rseq_cs __user *urseq_cs;
- unsigned long ptr;
+ u64 ptr;
u32 __user *usig;
u32 sig;
int ret;
- ret = __get_user(ptr, &t->rseq->rseq_cs);
- if (ret)
- return ret;
+ if (copy_from_user(&ptr, &t->rseq->rseq_cs.ptr64, sizeof(ptr)))
+ return -EFAULT;
if (!ptr) {
memset(rseq_cs, 0, sizeof(*rseq_cs));
return 0;
}
- urseq_cs = (struct rseq_cs __user *)ptr;
+ if (ptr >= TASK_SIZE)
+ return -EINVAL;
+ urseq_cs = (struct rseq_cs __user *)(unsigned long)ptr;
if (copy_from_user(rseq_cs, urseq_cs, sizeof(*rseq_cs)))
return -EFAULT;
- if (rseq_cs->version > 0)
- return -EINVAL;
+ if (rseq_cs->start_ip >= TASK_SIZE ||
+ rseq_cs->start_ip + rseq_cs->post_commit_offset >= TASK_SIZE ||
+ rseq_cs->abort_ip >= TASK_SIZE ||
+ rseq_cs->version > 0)
+ return -EINVAL;
+ /* Check for overflow. */
+ if (rseq_cs->start_ip + rseq_cs->post_commit_offset < rseq_cs->start_ip)
+ return -EINVAL;
/* Ensure that abort_ip is not in the critical section. */
if (rseq_cs->abort_ip - rseq_cs->start_ip < rseq_cs->post_commit_offset)
return -EINVAL;
- usig = (u32 __user *)(rseq_cs->abort_ip - sizeof(u32));
+ usig = (u32 __user *)(unsigned long)(rseq_cs->abort_ip - sizeof(u32));
ret = get_user(sig, usig);
if (ret)
return ret;
@@ -146,7 +153,7 @@ static int rseq_get_rseq_cs(struct task_struct *t, struct rseq_cs *rseq_cs)
printk_ratelimited(KERN_WARNING
"Possible attack attempt. Unexpected rseq signature 0x%x, expecting 0x%x (pid=%d, addr=%p).\n",
sig, current->rseq_sig, current->pid, usig);
- return -EPERM;
+ return -EINVAL;
}
return 0;
}
@@ -157,7 +164,7 @@ static int rseq_need_restart(struct task_struct *t, u32 cs_flags)
int ret;
/* Get thread flags. */
- ret = __get_user(flags, &t->rseq->flags);
+ ret = get_user(flags, &t->rseq->flags);
if (ret)
return ret;
@@ -195,9 +202,11 @@ static int clear_rseq_cs(struct task_struct *t)
* of code outside of the rseq assembly block. This performs
* a lazy clear of the rseq_cs field.
*
- * Set rseq_cs to NULL with single-copy atomicity.
+ * Set rseq_cs to NULL.
*/
- return __put_user(0UL, &t->rseq->rseq_cs);
+ if (clear_user(&t->rseq->rseq_cs.ptr64, sizeof(t->rseq->rseq_cs.ptr64)))
+ return -EFAULT;
+ return 0;
}
/*
@@ -251,10 +260,10 @@ static int rseq_ip_fixup(struct pt_regs *regs)
* respect to other threads scheduled on the same CPU, and with respect
* to signal handlers.
*/
-void __rseq_handle_notify_resume(struct pt_regs *regs)
+void __rseq_handle_notify_resume(struct ksignal *ksig, struct pt_regs *regs)
{
struct task_struct *t = current;
- int ret;
+ int ret, sig;
if (unlikely(t->flags & PF_EXITING))
return;
@@ -268,7 +277,8 @@ void __rseq_handle_notify_resume(struct pt_regs *regs)
return;
error:
- force_sig(SIGSEGV, t);
+ sig = ksig ? ksig->sig : 0;
+ force_sigsegv(sig, t);
}
#ifdef CONFIG_DEBUG_RSEQ
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 78d8facba456..fe365c9a08e9 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -7,7 +7,6 @@
*/
#include "sched.h"
-#include <linux/kthread.h>
#include <linux/nospec.h>
#include <linux/kcov.h>
@@ -2724,28 +2723,20 @@ static struct rq *finish_task_switch(struct task_struct *prev)
membarrier_mm_sync_core_before_usermode(mm);
mmdrop(mm);
}
- if (unlikely(prev_state & (TASK_DEAD|TASK_PARKED))) {
- switch (prev_state) {
- case TASK_DEAD:
- if (prev->sched_class->task_dead)
- prev->sched_class->task_dead(prev);
+ if (unlikely(prev_state == TASK_DEAD)) {
+ if (prev->sched_class->task_dead)
+ prev->sched_class->task_dead(prev);
- /*
- * Remove function-return probe instances associated with this
- * task and put them back on the free list.
- */
- kprobe_flush_task(prev);
-
- /* Task is done with its stack. */
- put_task_stack(prev);
+ /*
+ * Remove function-return probe instances associated with this
+ * task and put them back on the free list.
+ */
+ kprobe_flush_task(prev);
- put_task_struct(prev);
- break;
+ /* Task is done with its stack. */
+ put_task_stack(prev);
- case TASK_PARKED:
- kthread_park_complete(prev);
- break;
- }
+ put_task_struct(prev);
}
tick_nohz_task_switch();
@@ -3113,7 +3104,9 @@ static void sched_tick_remote(struct work_struct *work)
struct tick_work *twork = container_of(dwork, struct tick_work, work);
int cpu = twork->cpu;
struct rq *rq = cpu_rq(cpu);
+ struct task_struct *curr;
struct rq_flags rf;
+ u64 delta;
/*
* Handle the tick only if it appears the remote CPU is running in full
@@ -3122,24 +3115,28 @@ static void sched_tick_remote(struct work_struct *work)
* statistics and checks timeslices in a time-independent way, regardless
* of when exactly it is running.
*/
- if (!idle_cpu(cpu) && tick_nohz_tick_stopped_cpu(cpu)) {
- struct task_struct *curr;
- u64 delta;
+ if (idle_cpu(cpu) || !tick_nohz_tick_stopped_cpu(cpu))
+ goto out_requeue;
- rq_lock_irq(rq, &rf);
- update_rq_clock(rq);
- curr = rq->curr;
- delta = rq_clock_task(rq) - curr->se.exec_start;
+ rq_lock_irq(rq, &rf);
+ curr = rq->curr;
+ if (is_idle_task(curr))
+ goto out_unlock;
- /*
- * Make sure the next tick runs within a reasonable
- * amount of time.
- */
- WARN_ON_ONCE(delta > (u64)NSEC_PER_SEC * 3);
- curr->sched_class->task_tick(rq, curr, 0);
- rq_unlock_irq(rq, &rf);
- }
+ update_rq_clock(rq);
+ delta = rq_clock_task(rq) - curr->se.exec_start;
+
+ /*
+ * Make sure the next tick runs within a reasonable
+ * amount of time.
+ */
+ WARN_ON_ONCE(delta > (u64)NSEC_PER_SEC * 3);
+ curr->sched_class->task_tick(rq, curr, 0);
+
+out_unlock:
+ rq_unlock_irq(rq, &rf);
+out_requeue:
/*
* Run the remote tick once per second (1Hz). This arbitrary
* frequency is large enough to avoid overload but short enough
diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
index 3cde46483f0a..c907fde01eaa 100644
--- a/kernel/sched/cpufreq_schedutil.c
+++ b/kernel/sched/cpufreq_schedutil.c
@@ -192,7 +192,7 @@ static unsigned long sugov_aggregate_util(struct sugov_cpu *sg_cpu)
{
struct rq *rq = cpu_rq(sg_cpu->cpu);
- if (rq->rt.rt_nr_running)
+ if (rt_rq_is_runnable(&rq->rt))
return sg_cpu->max;
/*
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index fbfc3f1d368a..b5fbdde6afa9 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -2090,8 +2090,14 @@ retry:
sub_rq_bw(&next_task->dl, &rq->dl);
set_task_cpu(next_task, later_rq->cpu);
add_rq_bw(&next_task->dl, &later_rq->dl);
+
+ /*
+ * Update the later_rq clock here, because the clock is used
+ * by the cpufreq_update_util() inside __add_running_bw().
+ */
+ update_rq_clock(later_rq);
add_running_bw(&next_task->dl, &later_rq->dl);
- activate_task(later_rq, next_task, 0);
+ activate_task(later_rq, next_task, ENQUEUE_NOCLOCK);
ret = 1;
resched_curr(later_rq);
@@ -2290,8 +2296,17 @@ static void switched_from_dl(struct rq *rq, struct task_struct *p)
if (task_on_rq_queued(p) && p->dl.dl_runtime)
task_non_contending(p);
- if (!task_on_rq_queued(p))
+ if (!task_on_rq_queued(p)) {
+ /*
+ * Inactive timer is armed. However, p is leaving DEADLINE and
+ * might migrate away from this rq while continuing to run on
+ * some other class. We need to remove its contribution from
+ * this rq running_bw now, or sub_rq_bw (below) will complain.
+ */
+ if (p->dl.dl_non_contending)
+ sub_running_bw(&p->dl, &rq->dl);
sub_rq_bw(&p->dl, &rq->dl);
+ }
/*
* We cannot use inactive_task_timer() to invoke sub_running_bw()
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 1866e64792a7..2f0a0be4d344 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -3982,18 +3982,10 @@ util_est_dequeue(struct cfs_rq *cfs_rq, struct task_struct *p, bool task_sleep)
if (!sched_feat(UTIL_EST))
return;
- /*
- * Update root cfs_rq's estimated utilization
- *
- * If *p is the last task then the root cfs_rq's estimated utilization
- * of a CPU is 0 by definition.
- */
- ue.enqueued = 0;
- if (cfs_rq->nr_running) {
- ue.enqueued = cfs_rq->avg.util_est.enqueued;
- ue.enqueued -= min_t(unsigned int, ue.enqueued,
- (_task_util_est(p) | UTIL_AVG_UNCHANGED));
- }
+ /* Update root cfs_rq's estimated utilization */
+ ue.enqueued = cfs_rq->avg.util_est.enqueued;
+ ue.enqueued -= min_t(unsigned int, ue.enqueued,
+ (_task_util_est(p) | UTIL_AVG_UNCHANGED));
WRITE_ONCE(cfs_rq->avg.util_est.enqueued, ue.enqueued);
/*
@@ -4590,6 +4582,7 @@ void __refill_cfs_bandwidth_runtime(struct cfs_bandwidth *cfs_b)
now = sched_clock_cpu(smp_processor_id());
cfs_b->runtime = cfs_b->quota;
cfs_b->runtime_expires = now + ktime_to_ns(cfs_b->period);
+ cfs_b->expires_seq++;
}
static inline struct cfs_bandwidth *tg_cfs_bandwidth(struct task_group *tg)
@@ -4612,6 +4605,7 @@ static int assign_cfs_rq_runtime(struct cfs_rq *cfs_rq)
struct task_group *tg = cfs_rq->tg;
struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(tg);
u64 amount = 0, min_amount, expires;
+ int expires_seq;
/* note: this is a positive sum as runtime_remaining <= 0 */
min_amount = sched_cfs_bandwidth_slice() - cfs_rq->runtime_remaining;
@@ -4628,6 +4622,7 @@ static int assign_cfs_rq_runtime(struct cfs_rq *cfs_rq)
cfs_b->idle = 0;
}
}
+ expires_seq = cfs_b->expires_seq;
expires = cfs_b->runtime_expires;
raw_spin_unlock(&cfs_b->lock);
@@ -4637,8 +4632,10 @@ static int assign_cfs_rq_runtime(struct cfs_rq *cfs_rq)
* spread between our sched_clock and the one on which runtime was
* issued.
*/
- if ((s64)(expires - cfs_rq->runtime_expires) > 0)
+ if (cfs_rq->expires_seq != expires_seq) {
+ cfs_rq->expires_seq = expires_seq;
cfs_rq->runtime_expires = expires;
+ }
return cfs_rq->runtime_remaining > 0;
}
@@ -4664,12 +4661,9 @@ static void expire_cfs_rq_runtime(struct cfs_rq *cfs_rq)
* has not truly expired.
*
* Fortunately we can check determine whether this the case by checking
- * whether the global deadline has advanced. It is valid to compare
- * cfs_b->runtime_expires without any locks since we only care about
- * exact equality, so a partial write will still work.
+ * whether the global deadline(cfs_b->expires_seq) has advanced.
*/
-
- if (cfs_rq->runtime_expires != cfs_b->runtime_expires) {
+ if (cfs_rq->expires_seq == cfs_b->expires_seq) {
/* extend local deadline, drift is bounded above by 2 ticks */
cfs_rq->runtime_expires += TICK_NSEC;
} else {
@@ -5202,13 +5196,18 @@ static void init_cfs_rq_runtime(struct cfs_rq *cfs_rq)
void start_cfs_bandwidth(struct cfs_bandwidth *cfs_b)
{
+ u64 overrun;
+
lockdep_assert_held(&cfs_b->lock);
- if (!cfs_b->period_active) {
- cfs_b->period_active = 1;
- hrtimer_forward_now(&cfs_b->period_timer, cfs_b->period);
- hrtimer_start_expires(&cfs_b->period_timer, HRTIMER_MODE_ABS_PINNED);
- }
+ if (cfs_b->period_active)
+ return;
+
+ cfs_b->period_active = 1;
+ overrun = hrtimer_forward_now(&cfs_b->period_timer, cfs_b->period);
+ cfs_b->runtime_expires += (overrun + 1) * ktime_to_ns(cfs_b->period);
+ cfs_b->expires_seq++;
+ hrtimer_start_expires(&cfs_b->period_timer, HRTIMER_MODE_ABS_PINNED);
}
static void destroy_cfs_bandwidth(struct cfs_bandwidth *cfs_b)
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 47556b0c9a95..eaaec8364f96 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -508,8 +508,11 @@ static void sched_rt_rq_dequeue(struct rt_rq *rt_rq)
rt_se = rt_rq->tg->rt_se[cpu];
- if (!rt_se)
+ if (!rt_se) {
dequeue_top_rt_rq(rt_rq);
+ /* Kick cpufreq (see the comment in kernel/sched/sched.h). */
+ cpufreq_update_util(rq_of_rt_rq(rt_rq), 0);
+ }
else if (on_rt_rq(rt_se))
dequeue_rt_entity(rt_se, 0);
}
@@ -833,6 +836,8 @@ static int do_sched_rt_period_timer(struct rt_bandwidth *rt_b, int overrun)
* can be time-consuming. Try to avoid it when possible.
*/
raw_spin_lock(&rt_rq->rt_runtime_lock);
+ if (!sched_feat(RT_RUNTIME_SHARE) && rt_rq->rt_runtime != RUNTIME_INF)
+ rt_rq->rt_runtime = rt_b->rt_runtime;
skip = !rt_rq->rt_time && !rt_rq->rt_nr_running;
raw_spin_unlock(&rt_rq->rt_runtime_lock);
if (skip)
@@ -1001,8 +1006,6 @@ dequeue_top_rt_rq(struct rt_rq *rt_rq)
sub_nr_running(rq, rt_rq->rt_nr_running);
rt_rq->rt_queued = 0;
- /* Kick cpufreq (see the comment in kernel/sched/sched.h). */
- cpufreq_update_util(rq, 0);
}
static void
@@ -1014,11 +1017,14 @@ enqueue_top_rt_rq(struct rt_rq *rt_rq)
if (rt_rq->rt_queued)
return;
- if (rt_rq_throttled(rt_rq) || !rt_rq->rt_nr_running)
+
+ if (rt_rq_throttled(rt_rq))
return;
- add_nr_running(rq, rt_rq->rt_nr_running);
- rt_rq->rt_queued = 1;
+ if (rt_rq->rt_nr_running) {
+ add_nr_running(rq, rt_rq->rt_nr_running);
+ rt_rq->rt_queued = 1;
+ }
/* Kick cpufreq (see the comment in kernel/sched/sched.h). */
cpufreq_update_util(rq, 0);
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 6601baf2361c..c7742dcc136c 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -334,9 +334,10 @@ struct cfs_bandwidth {
u64 runtime;
s64 hierarchical_quota;
u64 runtime_expires;
+ int expires_seq;
- int idle;
- int period_active;
+ short idle;
+ short period_active;
struct hrtimer period_timer;
struct hrtimer slack_timer;
struct list_head throttled_cfs_rq;
@@ -551,6 +552,7 @@ struct cfs_rq {
#ifdef CONFIG_CFS_BANDWIDTH
int runtime_enabled;
+ int expires_seq;
u64 runtime_expires;
s64 runtime_remaining;
@@ -609,6 +611,11 @@ struct rt_rq {
#endif
};
+static inline bool rt_rq_is_runnable(struct rt_rq *rt_rq)
+{
+ return rt_rq->rt_queued && rt_rq->rt_nr_running;
+}
+
/* Deadline class' related fields in a runqueue */
struct dl_rq {
/* runqueue is an rbtree, ordered by deadline */
diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index 05a831427bc7..56a0fed30c0a 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -47,7 +47,7 @@ static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level,
if (!cpumask_test_cpu(cpu, sched_domain_span(sd))) {
printk(KERN_ERR "ERROR: domain->span does not contain CPU%d\n", cpu);
}
- if (!cpumask_test_cpu(cpu, sched_group_span(group))) {
+ if (group && !cpumask_test_cpu(cpu, sched_group_span(group))) {
printk(KERN_ERR "ERROR: domain->groups does not contain CPU%d\n", cpu);
}
diff --git a/kernel/softirq.c b/kernel/softirq.c
index de2f57fddc04..6f584861d329 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -79,12 +79,16 @@ static void wakeup_softirqd(void)
/*
* If ksoftirqd is scheduled, we do not want to process pending softirqs
- * right now. Let ksoftirqd handle this at its own rate, to get fairness.
+ * right now. Let ksoftirqd handle this at its own rate, to get fairness,
+ * unless we're doing some of the synchronous softirqs.
*/
-static bool ksoftirqd_running(void)
+#define SOFTIRQ_NOW_MASK ((1 << HI_SOFTIRQ) | (1 << TASKLET_SOFTIRQ))
+static bool ksoftirqd_running(unsigned long pending)
{
struct task_struct *tsk = __this_cpu_read(ksoftirqd);
+ if (pending & SOFTIRQ_NOW_MASK)
+ return false;
return tsk && (tsk->state == TASK_RUNNING);
}
@@ -139,9 +143,13 @@ static void __local_bh_enable(unsigned int cnt)
{
lockdep_assert_irqs_disabled();
+ if (preempt_count() == cnt)
+ trace_preempt_on(CALLER_ADDR0, get_lock_parent_ip());
+
if (softirq_count() == (cnt & SOFTIRQ_MASK))
trace_softirqs_on(_RET_IP_);
- preempt_count_sub(cnt);
+
+ __preempt_count_sub(cnt);
}
/*
@@ -324,7 +332,7 @@ asmlinkage __visible void do_softirq(void)
pending = local_softirq_pending();
- if (pending && !ksoftirqd_running())
+ if (pending && !ksoftirqd_running(pending))
do_softirq_own_stack();
local_irq_restore(flags);
@@ -351,7 +359,7 @@ void irq_enter(void)
static inline void invoke_softirq(void)
{
- if (ksoftirqd_running())
+ if (ksoftirqd_running(local_softirq_pending()))
return;
if (!force_irqthreads) {
@@ -382,7 +390,7 @@ static inline void tick_irq_exit(void)
/* Make sure that timer wheel updates are propagated */
if ((idle_cpu(cpu) && !need_resched()) || tick_nohz_full_cpu(cpu)) {
- if (!in_interrupt())
+ if (!in_irq())
tick_nohz_irq_exit();
}
#endif
diff --git a/kernel/stop_machine.c b/kernel/stop_machine.c
index f89014a2c238..e190d1ef3a23 100644
--- a/kernel/stop_machine.c
+++ b/kernel/stop_machine.c
@@ -260,6 +260,15 @@ retry:
err = 0;
__cpu_stop_queue_work(stopper1, work1, &wakeq);
__cpu_stop_queue_work(stopper2, work2, &wakeq);
+ /*
+ * The waking up of stopper threads has to happen
+ * in the same scheduling context as the queueing.
+ * Otherwise, there is a possibility of one of the
+ * above stoppers being woken up by another CPU,
+ * and preempting us. This will cause us to n ot
+ * wake up the other stopper forever.
+ */
+ preempt_disable();
unlock:
raw_spin_unlock(&stopper2->lock);
raw_spin_unlock_irq(&stopper1->lock);
@@ -270,7 +279,10 @@ unlock:
goto retry;
}
- wake_up_q(&wakeq);
+ if (!err) {
+ wake_up_q(&wakeq);
+ preempt_enable();
+ }
return err;
}
diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c
index 055a4a728c00..3e93c54bd3a1 100644
--- a/kernel/time/hrtimer.c
+++ b/kernel/time/hrtimer.c
@@ -1659,7 +1659,7 @@ EXPORT_SYMBOL_GPL(hrtimer_init_sleeper);
int nanosleep_copyout(struct restart_block *restart, struct timespec64 *ts)
{
switch(restart->nanosleep.type) {
-#ifdef CONFIG_COMPAT
+#ifdef CONFIG_COMPAT_32BIT_TIME
case TT_COMPAT:
if (compat_put_timespec64(ts, restart->nanosleep.compat_rmtp))
return -EFAULT;
diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c
index 5a6251ac6f7a..9cdf54b04ca8 100644
--- a/kernel/time/posix-cpu-timers.c
+++ b/kernel/time/posix-cpu-timers.c
@@ -604,7 +604,6 @@ static int posix_cpu_timer_set(struct k_itimer *timer, int timer_flags,
/*
* Disarm any old timer after extracting its expiry time.
*/
- lockdep_assert_irqs_disabled();
ret = 0;
old_incr = timer->it.cpu.incr;
@@ -1049,7 +1048,6 @@ static void posix_cpu_timer_rearm(struct k_itimer *timer)
/*
* Now re-arm for the new expiry time.
*/
- lockdep_assert_irqs_disabled();
arm_timer(timer);
unlock:
unlock_task_sighand(p, &flags);
diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c
index b7005dd21ec1..14de3727b18e 100644
--- a/kernel/time/tick-common.c
+++ b/kernel/time/tick-common.c
@@ -277,8 +277,7 @@ static bool tick_check_preferred(struct clock_event_device *curdev,
*/
return !curdev ||
newdev->rating > curdev->rating ||
- (!cpumask_equal(curdev->cpumask, newdev->cpumask) &&
- !tick_check_percpu(curdev, newdev, smp_processor_id()));
+ !cpumask_equal(curdev->cpumask, newdev->cpumask);
}
/*
diff --git a/kernel/time/tick-sched.c b/kernel/time/tick-sched.c
index da9455a6b42b..5b33e2f5c0ed 100644
--- a/kernel/time/tick-sched.c
+++ b/kernel/time/tick-sched.c
@@ -642,7 +642,7 @@ static void tick_nohz_restart(struct tick_sched *ts, ktime_t now)
static inline bool local_timer_softirq_pending(void)
{
- return local_softirq_pending() & TIMER_SOFTIRQ;
+ return local_softirq_pending() & BIT(TIMER_SOFTIRQ);
}
static ktime_t tick_nohz_next_event(struct tick_sched *ts, int cpu)
diff --git a/kernel/time/time.c b/kernel/time/time.c
index 6fa99213fc72..2b41e8e2d31d 100644
--- a/kernel/time/time.c
+++ b/kernel/time/time.c
@@ -28,6 +28,7 @@
*/
#include <linux/export.h>
+#include <linux/kernel.h>
#include <linux/timex.h>
#include <linux/capability.h>
#include <linux/timekeeper_internal.h>
@@ -314,9 +315,10 @@ unsigned int jiffies_to_msecs(const unsigned long j)
return (j + (HZ / MSEC_PER_SEC) - 1)/(HZ / MSEC_PER_SEC);
#else
# if BITS_PER_LONG == 32
- return (HZ_TO_MSEC_MUL32 * j) >> HZ_TO_MSEC_SHR32;
+ return (HZ_TO_MSEC_MUL32 * j + (1ULL << HZ_TO_MSEC_SHR32) - 1) >>
+ HZ_TO_MSEC_SHR32;
# else
- return (j * HZ_TO_MSEC_NUM) / HZ_TO_MSEC_DEN;
+ return DIV_ROUND_UP(j * HZ_TO_MSEC_NUM, HZ_TO_MSEC_DEN);
# endif
#endif
}
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index efed9c1cfb7e..caf9cbf35816 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -192,17 +192,6 @@ static void ftrace_pid_func(unsigned long ip, unsigned long parent_ip,
op->saved_func(ip, parent_ip, op, regs);
}
-/**
- * clear_ftrace_function - reset the ftrace function
- *
- * This NULLs the ftrace function and in essence stops
- * tracing. There may be lag
- */
-void clear_ftrace_function(void)
-{
- ftrace_trace_function = ftrace_stub;
-}
-
static void ftrace_sync(struct work_struct *work)
{
/*
@@ -6689,7 +6678,7 @@ void ftrace_kill(void)
{
ftrace_disabled = 1;
ftrace_enabled = 0;
- clear_ftrace_function();
+ ftrace_trace_function = ftrace_stub;
}
/**
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 6a46af21765c..0b0b688ea166 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -3227,6 +3227,22 @@ int ring_buffer_record_is_on(struct ring_buffer *buffer)
}
/**
+ * ring_buffer_record_is_set_on - return true if the ring buffer is set writable
+ * @buffer: The ring buffer to see if write is set enabled
+ *
+ * Returns true if the ring buffer is set writable by ring_buffer_record_on().
+ * Note that this does NOT mean it is in a writable state.
+ *
+ * It may return true when the ring buffer has been disabled by
+ * ring_buffer_record_disable(), as that is a temporary disabling of
+ * the ring buffer.
+ */
+int ring_buffer_record_is_set_on(struct ring_buffer *buffer)
+{
+ return !(atomic_read(&buffer->record_disabled) & RB_BUFFER_OFF);
+}
+
+/**
* ring_buffer_record_disable_cpu - stop all writes into the cpu_buffer
* @buffer: The ring buffer to stop writes to.
* @cpu: The CPU buffer to stop
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index c9336e98ac59..823687997b01 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -1360,8 +1360,6 @@ __update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu)
void
update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu)
{
- struct ring_buffer *buf;
-
if (tr->stop_count)
return;
@@ -1375,9 +1373,13 @@ update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu)
arch_spin_lock(&tr->max_lock);
- buf = tr->trace_buffer.buffer;
- tr->trace_buffer.buffer = tr->max_buffer.buffer;
- tr->max_buffer.buffer = buf;
+ /* Inherit the recordable setting from trace_buffer */
+ if (ring_buffer_record_is_set_on(tr->trace_buffer.buffer))
+ ring_buffer_record_on(tr->max_buffer.buffer);
+ else
+ ring_buffer_record_off(tr->max_buffer.buffer);
+
+ swap(tr->trace_buffer.buffer, tr->max_buffer.buffer);
__update_max_tr(tr, tsk, cpu);
arch_spin_unlock(&tr->max_lock);
@@ -2957,6 +2959,7 @@ out_nobuffer:
}
EXPORT_SYMBOL_GPL(trace_vbprintk);
+__printf(3, 0)
static int
__trace_array_vprintk(struct ring_buffer *buffer,
unsigned long ip, const char *fmt, va_list args)
@@ -3011,12 +3014,14 @@ out_nobuffer:
return len;
}
+__printf(3, 0)
int trace_array_vprintk(struct trace_array *tr,
unsigned long ip, const char *fmt, va_list args)
{
return __trace_array_vprintk(tr->trace_buffer.buffer, ip, fmt, args);
}
+__printf(3, 0)
int trace_array_printk(struct trace_array *tr,
unsigned long ip, const char *fmt, ...)
{
@@ -3032,6 +3037,7 @@ int trace_array_printk(struct trace_array *tr,
return ret;
}
+__printf(3, 4)
int trace_array_printk_buf(struct ring_buffer *buffer,
unsigned long ip, const char *fmt, ...)
{
@@ -3047,6 +3053,7 @@ int trace_array_printk_buf(struct ring_buffer *buffer,
return ret;
}
+__printf(2, 0)
int trace_vprintk(unsigned long ip, const char *fmt, va_list args)
{
return trace_array_vprintk(&global_trace, ip, fmt, args);
@@ -3364,8 +3371,8 @@ static void print_func_help_header(struct trace_buffer *buf, struct seq_file *m,
print_event_info(buf, m);
- seq_printf(m, "# TASK-PID CPU# %s TIMESTAMP FUNCTION\n", tgid ? "TGID " : "");
- seq_printf(m, "# | | | %s | |\n", tgid ? " | " : "");
+ seq_printf(m, "# TASK-PID %s CPU# TIMESTAMP FUNCTION\n", tgid ? "TGID " : "");
+ seq_printf(m, "# | | %s | | |\n", tgid ? " | " : "");
}
static void print_func_help_header_irq(struct trace_buffer *buf, struct seq_file *m,
@@ -3385,9 +3392,9 @@ static void print_func_help_header_irq(struct trace_buffer *buf, struct seq_file
tgid ? tgid_space : space);
seq_printf(m, "# %s||| / delay\n",
tgid ? tgid_space : space);
- seq_printf(m, "# TASK-PID CPU#%s|||| TIMESTAMP FUNCTION\n",
+ seq_printf(m, "# TASK-PID %sCPU# |||| TIMESTAMP FUNCTION\n",
tgid ? " TGID " : space);
- seq_printf(m, "# | | | %s|||| | |\n",
+ seq_printf(m, "# | | %s | |||| | |\n",
tgid ? " | " : space);
}
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 630c5a24b2b2..f8f86231ad90 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -583,9 +583,7 @@ static __always_inline void trace_clear_recursion(int bit)
static inline struct ring_buffer_iter *
trace_buffer_iter(struct trace_iterator *iter, int cpu)
{
- if (iter->buffer_iter && iter->buffer_iter[cpu])
- return iter->buffer_iter[cpu];
- return NULL;
+ return iter->buffer_iter ? iter->buffer_iter[cpu] : NULL;
}
int tracer_init(struct tracer *t, struct trace_array *tr);
diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c
index e1c818dbc0d7..893a206bcba4 100644
--- a/kernel/trace/trace_events_filter.c
+++ b/kernel/trace/trace_events_filter.c
@@ -78,7 +78,8 @@ static const char * ops[] = { OPS };
C(TOO_MANY_PREDS, "Too many terms in predicate expression"), \
C(INVALID_FILTER, "Meaningless filter expression"), \
C(IP_FIELD_ONLY, "Only 'ip' field is supported for function trace"), \
- C(INVALID_VALUE, "Invalid value (did you forget quotes)?"),
+ C(INVALID_VALUE, "Invalid value (did you forget quotes)?"), \
+ C(NO_FILTER, "No filter found"),
#undef C
#define C(a, b) FILT_ERR_##a
@@ -550,6 +551,13 @@ predicate_parse(const char *str, int nr_parens, int nr_preds,
goto out_free;
}
+ if (!N) {
+ /* No program? */
+ ret = -EINVAL;
+ parse_error(pe, FILT_ERR_NO_FILTER, ptr - str);
+ goto out_free;
+ }
+
prog[N].pred = NULL; /* #13 */
prog[N].target = 1; /* TRUE */
prog[N+1].pred = NULL;
@@ -1693,6 +1701,7 @@ static void create_filter_finish(struct filter_parse_error *pe)
* @filter_str: filter string
* @set_str: remember @filter_str and enable detailed error in filter
* @filterp: out param for created filter (always updated on return)
+ * Must be a pointer that references a NULL pointer.
*
* Creates a filter for @call with @filter_str. If @set_str is %true,
* @filter_str is copied and recorded in the new filter.
@@ -1710,6 +1719,10 @@ static int create_filter(struct trace_event_call *call,
struct filter_parse_error *pe = NULL;
int err;
+ /* filterp must point to NULL */
+ if (WARN_ON(*filterp))
+ *filterp = NULL;
+
err = create_filter_start(filter_string, set_str, &pe, filterp);
if (err)
return err;
diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c
index 046c716a6536..aae18af94c94 100644
--- a/kernel/trace/trace_events_hist.c
+++ b/kernel/trace/trace_events_hist.c
@@ -393,7 +393,7 @@ static void hist_err_event(char *str, char *system, char *event, char *var)
else if (system)
snprintf(err, MAX_FILTER_STR_VAL, "%s.%s", system, event);
else
- strncpy(err, var, MAX_FILTER_STR_VAL);
+ strscpy(err, var, MAX_FILTER_STR_VAL);
hist_err(str, err);
}
diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c
index d18249683682..5dea177cef53 100644
--- a/kernel/trace/trace_events_trigger.c
+++ b/kernel/trace/trace_events_trigger.c
@@ -679,6 +679,8 @@ event_trigger_callback(struct event_command *cmd_ops,
goto out_free;
out_reg:
+ /* Up the trigger_data count to make sure reg doesn't free it on failure */
+ event_trigger_init(trigger_ops, trigger_data);
ret = cmd_ops->reg(glob, trigger_ops, trigger_data, file);
/*
* The above returns on success the # of functions enabled,
@@ -686,11 +688,13 @@ event_trigger_callback(struct event_command *cmd_ops,
* Consider no functions a failure too.
*/
if (!ret) {
+ cmd_ops->unreg(glob, trigger_ops, trigger_data, file);
ret = -ENOENT;
- goto out_free;
- } else if (ret < 0)
- goto out_free;
- ret = 0;
+ } else if (ret > 0)
+ ret = 0;
+
+ /* Down the counter of trigger_data or free it if not used anymore */
+ event_trigger_free(trigger_ops, trigger_data);
out:
return ret;
@@ -1416,6 +1420,9 @@ int event_enable_trigger_func(struct event_command *cmd_ops,
goto out;
}
+ /* Up the trigger_data count to make sure nothing frees it on failure */
+ event_trigger_init(trigger_ops, trigger_data);
+
if (trigger) {
number = strsep(&trigger, ":");
@@ -1466,6 +1473,7 @@ int event_enable_trigger_func(struct event_command *cmd_ops,
goto out_disable;
/* Just return zero, not the number of enabled functions */
ret = 0;
+ event_trigger_free(trigger_ops, trigger_data);
out:
return ret;
@@ -1476,7 +1484,7 @@ int event_enable_trigger_func(struct event_command *cmd_ops,
out_free:
if (cmd_ops->set_filter)
cmd_ops->set_filter(NULL, trigger_data, NULL);
- kfree(trigger_data);
+ event_trigger_free(trigger_ops, trigger_data);
kfree(enable_data);
goto out;
}
diff --git a/kernel/trace/trace_functions_graph.c b/kernel/trace/trace_functions_graph.c
index 23c0b0cb5fb9..169b3c44ee97 100644
--- a/kernel/trace/trace_functions_graph.c
+++ b/kernel/trace/trace_functions_graph.c
@@ -831,6 +831,7 @@ print_graph_entry_leaf(struct trace_iterator *iter,
struct ftrace_graph_ret *graph_ret;
struct ftrace_graph_ent *call;
unsigned long long duration;
+ int cpu = iter->cpu;
int i;
graph_ret = &ret_entry->ret;
@@ -839,7 +840,6 @@ print_graph_entry_leaf(struct trace_iterator *iter,
if (data) {
struct fgraph_cpu_data *cpu_data;
- int cpu = iter->cpu;
cpu_data = per_cpu_ptr(data->cpu_data, cpu);
@@ -869,6 +869,9 @@ print_graph_entry_leaf(struct trace_iterator *iter,
trace_seq_printf(s, "%ps();\n", (void *)call->func);
+ print_graph_irq(iter, graph_ret->func, TRACE_GRAPH_RET,
+ cpu, iter->ent->pid, flags);
+
return trace_handle_return(s);
}
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index daa81571b22a..6b71860f3998 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -400,11 +400,10 @@ static struct trace_kprobe *find_trace_kprobe(const char *event,
static int
enable_trace_kprobe(struct trace_kprobe *tk, struct trace_event_file *file)
{
+ struct event_file_link *link = NULL;
int ret = 0;
if (file) {
- struct event_file_link *link;
-
link = kmalloc(sizeof(*link), GFP_KERNEL);
if (!link) {
ret = -ENOMEM;
@@ -424,6 +423,18 @@ enable_trace_kprobe(struct trace_kprobe *tk, struct trace_event_file *file)
else
ret = enable_kprobe(&tk->rp.kp);
}
+
+ if (ret) {
+ if (file) {
+ /* Notice the if is true on not WARN() */
+ if (!WARN_ON_ONCE(!link))
+ list_del_rcu(&link->list);
+ kfree(link);
+ tk->tp.flags &= ~TP_FLAG_TRACE;
+ } else {
+ tk->tp.flags &= ~TP_FLAG_PROFILE;
+ }
+ }
out:
return ret;
}
@@ -1480,8 +1491,10 @@ create_local_trace_kprobe(char *func, void *addr, unsigned long offs,
}
ret = __register_trace_kprobe(tk);
- if (ret < 0)
+ if (ret < 0) {
+ kfree(tk->tp.call.print_fmt);
goto error;
+ }
return &tk->tp.call;
error:
@@ -1501,6 +1514,8 @@ void destroy_local_trace_kprobe(struct trace_event_call *event_call)
}
__unregister_trace_kprobe(tk);
+
+ kfree(tk->tp.call.print_fmt);
free_trace_kprobe(tk);
}
#endif /* CONFIG_PERF_EVENTS */
diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
index 90db994ac900..1c8e30fda46a 100644
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -594,8 +594,7 @@ int trace_print_context(struct trace_iterator *iter)
trace_find_cmdline(entry->pid, comm);
- trace_seq_printf(s, "%16s-%-5d [%03d] ",
- comm, entry->pid, iter->cpu);
+ trace_seq_printf(s, "%16s-%-5d ", comm, entry->pid);
if (tr->trace_flags & TRACE_ITER_RECORD_TGID) {
unsigned int tgid = trace_find_tgid(entry->pid);
@@ -606,6 +605,8 @@ int trace_print_context(struct trace_iterator *iter)
trace_seq_printf(s, "(%5d) ", tgid);
}
+ trace_seq_printf(s, "[%03d] ", iter->cpu);
+
if (tr->trace_flags & TRACE_ITER_IRQ_INFO)
trace_print_lat_fmt(s, entry);