Merge tag 'bpf-next-7.0' of git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next

Pull bpf updates from Alexei Starovoitov:

 - Support associating BPF program with struct_ops (Amery Hung)

 - Switch BPF local storage to rqspinlock and remove recursion detection
   counters which were causing false positives (Amery Hung)

 - Fix live registers marking for indirect jumps (Anton Protopopov)

 - Introduce execution context detection BPF helpers (Changwoo Min)

 - Improve verifier precision for 32bit sign extension pattern
   (Cupertino Miranda)

 - Optimize BTF type lookup by sorting vmlinux BTF and doing binary
   search (Donglin Peng)

 - Allow states pruning for misc/invalid slots in iterator loops (Eduard
   Zingerman)

 - In preparation for ASAN support in BPF arenas teach libbpf to move
   global BPF variables to the end of the region and enable arena kfuncs
   while holding locks (Emil Tsalapatis)

 - Introduce support for implicit arguments in kfuncs and migrate a
   number of them to new API. This is a prerequisite for cgroup
   sub-schedulers in sched-ext (Ihor Solodrai)

 - Fix incorrect copied_seq calculation in sockmap (Jiayuan Chen)

 - Fix ORC stack unwind from kprobe_multi (Jiri Olsa)

 - Speed up fentry attach by using single ftrace direct ops in BPF
   trampolines (Jiri Olsa)

 - Require frozen map for calculating map hash (KP Singh)

 - Fix lock entry creation in TAS fallback in rqspinlock (Kumar
   Kartikeya Dwivedi)

 - Allow user space to select cpu in lookup/update operations on per-cpu
   array and hash maps (Leon Hwang)

 - Make kfuncs return trusted pointers by default (Matt Bobrowski)

 - Introduce "fsession" support where single BPF program is executed
   upon entry and exit from traced kernel function (Menglong Dong)

 - Allow bpf_timer and bpf_wq use in all programs types (Mykyta
   Yatsenko, Andrii Nakryiko, Kumar Kartikeya Dwivedi, Alexei
   Starovoitov)

 - Make KF_TRUSTED_ARGS the default for all kfuncs and clean up their
   definition across the tree (Puranjay Mohan)

 - Allow BPF arena calls from non-sleepable context (Puranjay Mohan)

 - Improve register id comparison logic in the verifier and extend
   linked registers with negative offsets (Puranjay Mohan)

 - In preparation for BPF-OOM introduce kfuncs to access memcg events
   (Roman Gushchin)

 - Use CFI compatible destructor kfunc type (Sami Tolvanen)

 - Add bitwise tracking for BPF_END in the verifier (Tianci Cao)

 - Add range tracking for BPF_DIV and BPF_MOD in the verifier (Yazhou
   Tang)

 - Make BPF selftests work with 64k page size (Yonghong Song)

* tag 'bpf-next-7.0' of git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next: (268 commits)
  selftests/bpf: Fix outdated test on storage->smap
  selftests/bpf: Choose another percpu variable in bpf for btf_dump test
  selftests/bpf: Remove test_task_storage_map_stress_lookup
  selftests/bpf: Update task_local_storage/task_storage_nodeadlock test
  selftests/bpf: Update task_local_storage/recursion test
  selftests/bpf: Update sk_storage_omem_uncharge test
  bpf: Switch to bpf_selem_unlink_nofail in bpf_local_storage_{map_free, destroy}
  bpf: Support lockless unlink when freeing map or local storage
  bpf: Prepare for bpf_selem_unlink_nofail()
  bpf: Remove unused percpu counter from bpf_local_storage_map_free
  bpf: Remove cgroup local storage percpu counter
  bpf: Remove task local storage percpu counter
  bpf: Change local_storage->lock and b->lock to rqspinlock
  bpf: Convert bpf_selem_unlink to failable
  bpf: Convert bpf_selem_link_map to failable
  bpf: Convert bpf_selem_unlink_map to failable
  bpf: Select bpf_local_storage_map_bucket based on bpf_local_storage
  selftests/xsk: fix number of Tx frags in invalid packet
  selftests/xsk: properly handle batch ending in the middle of a packet
  bpf: Prevent reentrance into call_rcu_tasks_trace()
  ...

4 files changed, 212 insertions, 1 deletions

diff --git a/mm/Makefile b/mm/Makefile
index 2d0570a16e5b..bf46fe31dc14 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -106,6 +106,9 @@ obj-$(CONFIG_MEMCG) += memcontrol.o vmpressure.o
 ifdef CONFIG_SWAP
 obj-$(CONFIG_MEMCG) += swap_cgroup.o
 endif
+ifdef CONFIG_BPF_SYSCALL
+obj-$(CONFIG_MEMCG) += bpf_memcontrol.o
+endif
 obj-$(CONFIG_CGROUP_HUGETLB) += hugetlb_cgroup.o
 obj-$(CONFIG_GUP_TEST) += gup_test.o
 obj-$(CONFIG_DMAPOOL_TEST) += dmapool_test.o
diff --git a/mm/bpf_memcontrol.c b/mm/bpf_memcontrol.c
new file mode 100644
index 000000000000..716df49d7647
--- /dev/null
+++ b/mm/bpf_memcontrol.c
@@ -0,0 +1,193 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Memory Controller-related BPF kfuncs and auxiliary code
+ *
+ * Author: Roman Gushchin <roman.gushchin@linux.dev>
+ */
+
+#include <linux/memcontrol.h>
+#include <linux/bpf.h>
+
+__bpf_kfunc_start_defs();
+
+/**
+ * bpf_get_root_mem_cgroup - Returns a pointer to the root memory cgroup
+ *
+ * The function has KF_ACQUIRE semantics, even though the root memory
+ * cgroup is never destroyed after being created and doesn't require
+ * reference counting. And it's perfectly safe to pass it to
+ * bpf_put_mem_cgroup()
+ *
+ * Return: A pointer to the root memory cgroup.
+ */
+__bpf_kfunc struct mem_cgroup *bpf_get_root_mem_cgroup(void)
+{
+	if (mem_cgroup_disabled())
+		return NULL;
+
+	/* css_get() is not needed */
+	return root_mem_cgroup;
+}
+
+/**
+ * bpf_get_mem_cgroup - Get a reference to a memory cgroup
+ * @css: pointer to the css structure
+ *
+ * It's fine to pass a css which belongs to any cgroup controller,
+ * e.g. unified hierarchy's main css.
+ *
+ * Implements KF_ACQUIRE semantics.
+ *
+ * Return: A pointer to a mem_cgroup structure after bumping
+ * the corresponding css's reference counter.
+ */
+__bpf_kfunc struct mem_cgroup *
+bpf_get_mem_cgroup(struct cgroup_subsys_state *css)
+{
+	struct mem_cgroup *memcg = NULL;
+	bool rcu_unlock = false;
+
+	if (mem_cgroup_disabled() || !root_mem_cgroup)
+		return NULL;
+
+	if (root_mem_cgroup->css.ss != css->ss) {
+		struct cgroup *cgroup = css->cgroup;
+		int ssid = root_mem_cgroup->css.ss->id;
+
+		rcu_read_lock();
+		rcu_unlock = true;
+		css = rcu_dereference_raw(cgroup->subsys[ssid]);
+	}
+
+	if (css && css_tryget(css))
+		memcg = container_of(css, struct mem_cgroup, css);
+
+	if (rcu_unlock)
+		rcu_read_unlock();
+
+	return memcg;
+}
+
+/**
+ * bpf_put_mem_cgroup - Put a reference to a memory cgroup
+ * @memcg: memory cgroup to release
+ *
+ * Releases a previously acquired memcg reference.
+ * Implements KF_RELEASE semantics.
+ */
+__bpf_kfunc void bpf_put_mem_cgroup(struct mem_cgroup *memcg)
+{
+	css_put(&memcg->css);
+}
+
+/**
+ * bpf_mem_cgroup_vm_events - Read memory cgroup's vm event counter
+ * @memcg: memory cgroup
+ * @event: event id
+ *
+ * Allows to read memory cgroup event counters.
+ *
+ * Return: The current value of the corresponding events counter.
+ */
+__bpf_kfunc unsigned long bpf_mem_cgroup_vm_events(struct mem_cgroup *memcg,
+						   enum vm_event_item event)
+{
+	if (unlikely(!memcg_vm_event_item_valid(event)))
+		return (unsigned long)-1;
+
+	return memcg_events(memcg, event);
+}
+
+/**
+ * bpf_mem_cgroup_usage - Read memory cgroup's usage
+ * @memcg: memory cgroup
+ *
+ * Please, note that the root memory cgroup it special and is exempt
+ * from the memory accounting. The returned value is a sum of sub-cgroup's
+ * usages and it not reflecting the size of the root memory cgroup itself.
+ * If you need to get an approximation, you can use root level statistics:
+ * e.g. NR_FILE_PAGES + NR_ANON_MAPPED.
+ *
+ * Return: The current memory cgroup size in bytes.
+ */
+__bpf_kfunc unsigned long bpf_mem_cgroup_usage(struct mem_cgroup *memcg)
+{
+	return page_counter_read(&memcg->memory) * PAGE_SIZE;
+}
+
+/**
+ * bpf_mem_cgroup_memory_events - Read memory cgroup's memory event value
+ * @memcg: memory cgroup
+ * @event: memory event id
+ *
+ * Return: The current value of the memory event counter.
+ */
+__bpf_kfunc unsigned long bpf_mem_cgroup_memory_events(struct mem_cgroup *memcg,
+						       enum memcg_memory_event event)
+{
+	if (unlikely(event >= MEMCG_NR_MEMORY_EVENTS))
+		return (unsigned long)-1;
+
+	return atomic_long_read(&memcg->memory_events[event]);
+}
+
+/**
+ * bpf_mem_cgroup_page_state - Read memory cgroup's page state counter
+ * @memcg: memory cgroup
+ * @idx: counter idx
+ *
+ * Allows to read memory cgroup statistics. The output is in bytes.
+ *
+ * Return: The value of the page state counter in bytes.
+ */
+__bpf_kfunc unsigned long bpf_mem_cgroup_page_state(struct mem_cgroup *memcg, int idx)
+{
+	if (unlikely(!memcg_stat_item_valid(idx)))
+		return (unsigned long)-1;
+
+	return memcg_page_state_output(memcg, idx);
+}
+
+/**
+ * bpf_mem_cgroup_flush_stats - Flush memory cgroup's statistics
+ * @memcg: memory cgroup
+ *
+ * Propagate memory cgroup's statistics up the cgroup tree.
+ */
+__bpf_kfunc void bpf_mem_cgroup_flush_stats(struct mem_cgroup *memcg)
+{
+	mem_cgroup_flush_stats(memcg);
+}
+
+__bpf_kfunc_end_defs();
+
+BTF_KFUNCS_START(bpf_memcontrol_kfuncs)
+BTF_ID_FLAGS(func, bpf_get_root_mem_cgroup, KF_ACQUIRE | KF_RET_NULL)
+BTF_ID_FLAGS(func, bpf_get_mem_cgroup, KF_ACQUIRE | KF_RET_NULL | KF_RCU)
+BTF_ID_FLAGS(func, bpf_put_mem_cgroup, KF_RELEASE)
+
+BTF_ID_FLAGS(func, bpf_mem_cgroup_vm_events)
+BTF_ID_FLAGS(func, bpf_mem_cgroup_memory_events)
+BTF_ID_FLAGS(func, bpf_mem_cgroup_usage)
+BTF_ID_FLAGS(func, bpf_mem_cgroup_page_state)
+BTF_ID_FLAGS(func, bpf_mem_cgroup_flush_stats, KF_SLEEPABLE)
+
+BTF_KFUNCS_END(bpf_memcontrol_kfuncs)
+
+static const struct btf_kfunc_id_set bpf_memcontrol_kfunc_set = {
+	.owner          = THIS_MODULE,
+	.set            = &bpf_memcontrol_kfuncs,
+};
+
+static int __init bpf_memcontrol_init(void)
+{
+	int err;
+
+	err = register_btf_kfunc_id_set(BPF_PROG_TYPE_UNSPEC,
+					&bpf_memcontrol_kfunc_set);
+	if (err)
+		pr_warn("error while registering bpf memcontrol kfuncs: %d", err);
+
+	return err;
+}
+late_initcall(bpf_memcontrol_init);
diff --git a/mm/memcontrol-v1.h b/mm/memcontrol-v1.h
index 6358464bb416..a304ad418cdf 100644
--- a/mm/memcontrol-v1.h
+++ b/mm/memcontrol-v1.h
@@ -27,7 +27,6 @@ unsigned long mem_cgroup_usage(struct mem_cgroup *memcg, bool swap);
 void drain_all_stock(struct mem_cgroup *root_memcg);
 
 unsigned long memcg_events(struct mem_cgroup *memcg, int event);
-unsigned long memcg_page_state_output(struct mem_cgroup *memcg, int item);
 int memory_stat_show(struct seq_file *m, void *v);
 
 void mem_cgroup_id_get_many(struct mem_cgroup *memcg, unsigned int n);
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 783b3b008fef..129eed3ff5bb 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -665,6 +665,14 @@ unsigned long memcg_page_state(struct mem_cgroup *memcg, int idx)
 	return x;
 }
 
+bool memcg_stat_item_valid(int idx)
+{
+	if ((u32)idx >= MEMCG_NR_STAT)
+		return false;
+
+	return !BAD_STAT_IDX(memcg_stats_index(idx));
+}
+
 static int memcg_page_state_unit(int item);
 
 /*
@@ -862,6 +870,14 @@ unsigned long memcg_events(struct mem_cgroup *memcg, int event)
 	return READ_ONCE(memcg->vmstats->events[i]);
 }
 
+bool memcg_vm_event_item_valid(enum vm_event_item idx)
+{
+	if (idx >= NR_VM_EVENT_ITEMS)
+		return false;
+
+	return !BAD_STAT_IDX(memcg_events_index(idx));
+}
+
 #ifdef CONFIG_MEMCG_V1
 unsigned long memcg_events_local(struct mem_cgroup *memcg, int event)
 {