bpf: Fix percpu address space issues

JIRA: https://issues.redhat.com/browse/RHEL-63880

commit 6d641ca50d7ec7d5e4e889c3f8ea22afebc2a403
Author: Uros Bizjak <ubizjak@gmail.com>
Date:   Sun Aug 11 18:13:33 2024 +0200

    bpf: Fix percpu address space issues

    In arraymap.c:

    In bpf_array_map_seq_start() and bpf_array_map_seq_next()
    cast return values from the __percpu address space to
    the generic address space via uintptr_t [1].

    Correct the declaration of pptr pointer in __bpf_array_map_seq_show()
    to void __percpu * and cast the value from the generic address
    space to the __percpu address space via uintptr_t [1].

    In hashtab.c:

    Assign the return value from bpf_mem_cache_alloc() to void pointer
    and cast the value to void __percpu ** (void pointer to percpu void
    pointer) before dereferencing.

    In memalloc.c:

    Explicitly declare __percpu variables.

    Cast obj to void __percpu **.

    In helpers.c:

    Cast ptr in BPF_CALL_1 and BPF_CALL_2 from generic address space
    to __percpu address space via const uintptr_t [1].

    Found by GCC's named address space checks.

    There were no changes in the resulting object files.

    [1] https://sparse.docs.kernel.org/en/latest/annotations.html#address-space-name

    Signed-off-by: Uros Bizjak <ubizjak@gmail.com>
    Cc: Alexei Starovoitov <ast@kernel.org>
    Cc: Daniel Borkmann <daniel@iogearbox.net>
    Cc: Andrii Nakryiko <andrii@kernel.org>
    Cc: Martin KaFai Lau <martin.lau@linux.dev>
    Cc: Eduard Zingerman <eddyz87@gmail.com>
    Cc: Song Liu <song@kernel.org>
    Cc: Yonghong Song <yonghong.song@linux.dev>
    Cc: John Fastabend <john.fastabend@gmail.com>
    Cc: KP Singh <kpsingh@kernel.org>
    Cc: Stanislav Fomichev <sdf@fomichev.me>
    Cc: Hao Luo <haoluo@google.com>
    Cc: Jiri Olsa <jolsa@kernel.org>
    Acked-by: Eduard Zingerman <eddyz87@gmail.com>
    Link: https://lore.kernel.org/r/20240811161414.56744-1-ubizjak@gmail.com
    Signed-off-by: Alexei Starovoitov <ast@kernel.org>

Signed-off-by: Jerome Marchand <jmarchan@redhat.com>

kernel/bpf/arraymap.c

@@ -600,7 +600,7 @@ static void *bpf_array_map_seq_start(struct seq_file *seq, loff_t *pos)
 	array = container_of(map, struct bpf_array, map);
 	index = info->index & array->index_mask;
 	if (info->percpu_value_buf)
-	       return array->pptrs[index];
+		return (void *)(uintptr_t)array->pptrs[index];
 	return array_map_elem_ptr(array, index);
 }
 
@@ -619,7 +619,7 @@ static void *bpf_array_map_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 	array = container_of(map, struct bpf_array, map);
 	index = info->index & array->index_mask;
 	if (info->percpu_value_buf)
-	       return array->pptrs[index];
+		return (void *)(uintptr_t)array->pptrs[index];
 	return array_map_elem_ptr(array, index);
 }
 
@@ -632,7 +632,7 @@ static int __bpf_array_map_seq_show(struct seq_file *seq, void *v)
 	struct bpf_iter_meta meta;
 	struct bpf_prog *prog;
 	int off = 0, cpu = 0;
-	void __percpu **pptr;
+	void __percpu *pptr;
 	u32 size;
 
 	meta.seq = seq;
@@ -648,7 +648,7 @@ static int __bpf_array_map_seq_show(struct seq_file *seq, void *v)
 		if (!info->percpu_value_buf) {
 			ctx.value = v;
 		} else {
-			pptr = v;
+			pptr = (void __percpu *)(uintptr_t)v;
 			size = array->elem_size;
 			for_each_possible_cpu(cpu) {
 				copy_map_value_long(map, info->percpu_value_buf + off,

kernel/bpf/hashtab.c

@@ -1048,14 +1048,15 @@ static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key,
 			pptr = htab_elem_get_ptr(l_new, key_size);
 		} else {
 			/* alloc_percpu zero-fills */
-			pptr = bpf_mem_cache_alloc(&htab->pcpu_ma);
-			if (!pptr) {
+			void *ptr = bpf_mem_cache_alloc(&htab->pcpu_ma);
+
+			if (!ptr) {
 				bpf_mem_cache_free(&htab->ma, l_new);
 				l_new = ERR_PTR(-ENOMEM);
 				goto dec_count;
 			}
-			l_new->ptr_to_pptr = pptr;
-			pptr = *(void **)pptr;
+			l_new->ptr_to_pptr = ptr;
+			pptr = *(void __percpu **)ptr;
 		}
 
 		pcpu_init_value(htab, pptr, value, onallcpus);

kernel/bpf/helpers.c

@@ -715,7 +715,7 @@ BPF_CALL_2(bpf_per_cpu_ptr, const void *, ptr, u32, cpu)
 	if (cpu >= nr_cpu_ids)
 		return (unsigned long)NULL;
 
-	return (unsigned long)per_cpu_ptr((const void __percpu *)ptr, cpu);
+	return (unsigned long)per_cpu_ptr((const void __percpu *)(const uintptr_t)ptr, cpu);
 }
 
 const struct bpf_func_proto bpf_per_cpu_ptr_proto = {
@@ -728,7 +728,7 @@ const struct bpf_func_proto bpf_per_cpu_ptr_proto = {
 
 BPF_CALL_1(bpf_this_cpu_ptr, const void *, percpu_ptr)
 {
-	return (unsigned long)this_cpu_ptr((const void __percpu *)percpu_ptr);
+	return (unsigned long)this_cpu_ptr((const void __percpu *)(const uintptr_t)percpu_ptr);
 }
 
 const struct bpf_func_proto bpf_this_cpu_ptr_proto = {

kernel/bpf/memalloc.c

@@ -140,8 +140,8 @@ static struct llist_node notrace *__llist_del_first(struct llist_head *head)
 static void *__alloc(struct bpf_mem_cache *c, int node, gfp_t flags)
 {
 	if (c->percpu_size) {
-		void **obj = kmalloc_node(c->percpu_size, flags, node);
-		void *pptr = __alloc_percpu_gfp(c->unit_size, 8, flags);
+		void __percpu **obj = kmalloc_node(c->percpu_size, flags, node);
+		void __percpu *pptr = __alloc_percpu_gfp(c->unit_size, 8, flags);
 
 		if (!obj || !pptr) {
 			free_percpu(pptr);
@@ -258,7 +258,7 @@ static void alloc_bulk(struct bpf_mem_cache *c, int cnt, int node, bool atomic)
 static void free_one(void *obj, bool percpu)
 {
 	if (percpu) {
-		free_percpu(((void **)obj)[1]);
+		free_percpu(((void __percpu **)obj)[1]);
 		kfree(obj);
 		return;
 	}
@@ -514,8 +514,8 @@ static void prefill_mem_cache(struct bpf_mem_cache *c, int cpu)
  */
 int bpf_mem_alloc_init(struct bpf_mem_alloc *ma, int size, bool percpu)
 {
-	struct bpf_mem_caches *cc, __percpu *pcc;
-	struct bpf_mem_cache *c, __percpu *pc;
+	struct bpf_mem_caches *cc; struct bpf_mem_caches __percpu *pcc;
+	struct bpf_mem_cache *c; struct bpf_mem_cache __percpu *pc;
 	struct obj_cgroup *objcg = NULL;
 	int cpu, i, unit_size, percpu_size = 0;
 
@@ -596,7 +596,7 @@ int bpf_mem_alloc_percpu_init(struct bpf_mem_alloc *ma, struct obj_cgroup *objcg
 
 int bpf_mem_alloc_percpu_unit_init(struct bpf_mem_alloc *ma, int size)
 {
-	struct bpf_mem_caches *cc, __percpu *pcc;
+	struct bpf_mem_caches *cc; struct bpf_mem_caches __percpu *pcc;
 	int cpu, i, unit_size, percpu_size;
 	struct obj_cgroup *objcg;
 	struct bpf_mem_cache *c;