Merge tag 'for-netdev' of https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf

Daniel Borkmann says:

====================
pull-request: bpf 2024-03-25

The following pull-request contains BPF updates for your *net* tree.

We've added 17 non-merge commits during the last 12 day(s) which contain
a total of 19 files changed, 184 insertions(+), 61 deletions(-).

The main changes are:

1) Fix an arm64 BPF JIT bug in BPF_LDX_MEMSX implementation's offset handling
   found via test_bpf module, from Puranjay Mohan.

2) Various fixups to the BPF arena code in particular in the BPF verifier and
   around BPF selftests to match latest corresponding LLVM implementation,
   from Puranjay Mohan and Alexei Starovoitov.

3) Fix xsk to not assume that metadata is always requested in TX completion,
   from Stanislav Fomichev.

4) Fix riscv BPF JIT's kfunc parameter incompatibility between BPF and the riscv
   ABI which requires sign-extension on int/uint, from Pu Lehui.

5) Fix s390x BPF JIT's bpf_plt pointer arithmetic which triggered a crash when
   testing struct_ops, from Ilya Leoshkevich.

6) Fix libbpf's arena mmap handling which had incorrect u64-to-pointer cast on
   32-bit architectures, from Andrii Nakryiko.

7) Fix libbpf to define MFD_CLOEXEC when not available, from Arnaldo Carvalho de Melo.

8) Fix arm64 BPF JIT implementation for 32bit unconditional bswap which
   resulted in an incorrect swap as indicated by test_bpf, from Artem Savkov.

9) Fix BPF man page build script to use silent mode, from Hangbin Liu.

* tag 'for-netdev' of https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf:
  riscv, bpf: Fix kfunc parameters incompatibility between bpf and riscv abi
  bpf: verifier: reject addr_space_cast insn without arena
  selftests/bpf: verifier_arena: fix mmap address for arm64
  bpf: verifier: fix addr_space_cast from as(1) to as(0)
  libbpf: Define MFD_CLOEXEC if not available
  arm64: bpf: fix 32bit unconditional bswap
  bpf, arm64: fix bug in BPF_LDX_MEMSX
  libbpf: fix u64-to-pointer cast on 32-bit arches
  s390/bpf: Fix bpf_plt pointer arithmetic
  xsk: Don't assume metadata is always requested in TX completion
  selftests/bpf: Add arena test case for 4Gbyte corner case
  selftests/bpf: Remove hard coded PAGE_SIZE macro.
  libbpf, selftests/bpf: Adjust libbpf, bpftool, selftests to match LLVM
  bpf: Clarify bpf_arena comments.
  MAINTAINERS: Update email address for Quentin Monnet
  scripts/bpf_doc: Use silent mode when exec make cmd
  bpf: Temporarily disable atomic operations in BPF arena
====================

Link: https://lore.kernel.org/r/20240325213520.26688-1-daniel@iogearbox.net
Signed-off-by: Paolo Abeni <pabeni@redhat.com>

2 files changed, 37 insertions, 10 deletions

diff --git a/kernel/bpf/arena.c b/kernel/bpf/arena.c
index 86571e760dd6..343c3456c8dd 100644
--- a/kernel/bpf/arena.c
+++ b/kernel/bpf/arena.c
@@ -38,7 +38,7 @@
 
 /* number of bytes addressable by LDX/STX insn with 16-bit 'off' field */
 #define GUARD_SZ (1ull << sizeof(((struct bpf_insn *)0)->off) * 8)
-#define KERN_VM_SZ ((1ull << 32) + GUARD_SZ)
+#define KERN_VM_SZ (SZ_4G + GUARD_SZ)
 
 struct bpf_arena {
 	struct bpf_map map;
@@ -110,7 +110,7 @@ static struct bpf_map *arena_map_alloc(union bpf_attr *attr)
 		return ERR_PTR(-EINVAL);
 
 	vm_range = (u64)attr->max_entries * PAGE_SIZE;
-	if (vm_range > (1ull << 32))
+	if (vm_range > SZ_4G)
 		return ERR_PTR(-E2BIG);
 
 	if ((attr->map_extra >> 32) != ((attr->map_extra + vm_range - 1) >> 32))
@@ -301,7 +301,7 @@ static unsigned long arena_get_unmapped_area(struct file *filp, unsigned long ad
 
 	if (pgoff)
 		return -EINVAL;
-	if (len > (1ull << 32))
+	if (len > SZ_4G)
 		return -E2BIG;
 
 	/* if user_vm_start was specified at arena creation time */
@@ -322,7 +322,7 @@ static unsigned long arena_get_unmapped_area(struct file *filp, unsigned long ad
 	if (WARN_ON_ONCE(arena->user_vm_start))
 		/* checks at map creation time should prevent this */
 		return -EFAULT;
-	return round_up(ret, 1ull << 32);
+	return round_up(ret, SZ_4G);
 }
 
 static int arena_map_mmap(struct bpf_map *map, struct vm_area_struct *vma)
@@ -346,7 +346,7 @@ static int arena_map_mmap(struct bpf_map *map, struct vm_area_struct *vma)
 		return -EBUSY;
 
 	/* Earlier checks should prevent this */
-	if (WARN_ON_ONCE(vma->vm_end - vma->vm_start > (1ull << 32) || vma->vm_pgoff))
+	if (WARN_ON_ONCE(vma->vm_end - vma->vm_start > SZ_4G || vma->vm_pgoff))
 		return -EFAULT;
 
 	if (remember_vma(arena, vma))
@@ -420,7 +420,7 @@ static long arena_alloc_pages(struct bpf_arena *arena, long uaddr, long page_cnt
 		if (uaddr & ~PAGE_MASK)
 			return 0;
 		pgoff = compute_pgoff(arena, uaddr);
-		if (pgoff + page_cnt > page_cnt_max)
+		if (pgoff > page_cnt_max - page_cnt)
 			/* requested address will be outside of user VMA */
 			return 0;
 	}
@@ -447,7 +447,13 @@ static long arena_alloc_pages(struct bpf_arena *arena, long uaddr, long page_cnt
 		goto out;
 
 	uaddr32 = (u32)(arena->user_vm_start + pgoff * PAGE_SIZE);
-	/* Earlier checks make sure that uaddr32 + page_cnt * PAGE_SIZE will not overflow 32-bit */
+	/* Earlier checks made sure that uaddr32 + page_cnt * PAGE_SIZE - 1
+	 * will not overflow 32-bit. Lower 32-bit need to represent
+	 * contiguous user address range.
+	 * Map these pages at kern_vm_start base.
+	 * kern_vm_start + uaddr32 + page_cnt * PAGE_SIZE - 1 can overflow
+	 * lower 32-bit and it's ok.
+	 */
 	ret = vm_area_map_pages(arena->kern_vm, kern_vm_start + uaddr32,
 				kern_vm_start + uaddr32 + page_cnt * PAGE_SIZE, pages);
 	if (ret) {
@@ -510,6 +516,11 @@ static void arena_free_pages(struct bpf_arena *arena, long uaddr, long page_cnt)
 		if (!page)
 			continue;
 		if (page_cnt == 1 && page_mapped(page)) /* mapped by some user process */
+			/* Optimization for the common case of page_cnt==1:
+			 * If page wasn't mapped into some user vma there
+			 * is no need to call zap_pages which is slow. When
+			 * page_cnt is big it's faster to do the batched zap.
+			 */
 			zap_pages(arena, full_uaddr, 1);
 		vm_area_unmap_pages(arena->kern_vm, kaddr, kaddr + PAGE_SIZE);
 		__free_page(page);
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 63749ad5ac6b..0bfc0050db28 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -5682,6 +5682,13 @@ static bool is_flow_key_reg(struct bpf_verifier_env *env, int regno)
 	return reg->type == PTR_TO_FLOW_KEYS;
 }
 
+static bool is_arena_reg(struct bpf_verifier_env *env, int regno)
+{
+	const struct bpf_reg_state *reg = reg_state(env, regno);
+
+	return reg->type == PTR_TO_ARENA;
+}
+
 static u32 *reg2btf_ids[__BPF_REG_TYPE_MAX] = {
 #ifdef CONFIG_NET
 	[PTR_TO_SOCKET] = &btf_sock_ids[BTF_SOCK_TYPE_SOCK],
@@ -7019,7 +7026,8 @@ static int check_atomic(struct bpf_verifier_env *env, int insn_idx, struct bpf_i
 	if (is_ctx_reg(env, insn->dst_reg) ||
 	    is_pkt_reg(env, insn->dst_reg) ||
 	    is_flow_key_reg(env, insn->dst_reg) ||
-	    is_sk_reg(env, insn->dst_reg)) {
+	    is_sk_reg(env, insn->dst_reg) ||
+	    is_arena_reg(env, insn->dst_reg)) {
 		verbose(env, "BPF_ATOMIC stores into R%d %s is not allowed\n",
 			insn->dst_reg,
 			reg_type_str(env, reg_state(env, insn->dst_reg)->type));
@@ -14014,6 +14022,10 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
 					verbose(env, "addr_space_cast insn can only convert between address space 1 and 0\n");
 					return -EINVAL;
 				}
+				if (!env->prog->aux->arena) {
+					verbose(env, "addr_space_cast insn can only be used in a program that has an associated arena\n");
+					return -EINVAL;
+				}
 			} else {
 				if ((insn->off != 0 && insn->off != 8 && insn->off != 16 &&
 				     insn->off != 32) || insn->imm) {
@@ -14046,8 +14058,11 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
 				if (insn->imm) {
 					/* off == BPF_ADDR_SPACE_CAST */
 					mark_reg_unknown(env, regs, insn->dst_reg);
-					if (insn->imm == 1) /* cast from as(1) to as(0) */
+					if (insn->imm == 1) { /* cast from as(1) to as(0) */
 						dst_reg->type = PTR_TO_ARENA;
+						/* PTR_TO_ARENA is 32-bit */
+						dst_reg->subreg_def = env->insn_idx + 1;
+					}
 				} else if (insn->off == 0) {
 					/* case: R1 = R2
 					 * copy register state to dest reg
@@ -19601,8 +19616,9 @@ static int do_misc_fixups(struct bpf_verifier_env *env)
 			    (((struct bpf_map *)env->prog->aux->arena)->map_flags & BPF_F_NO_USER_CONV)) {
 				/* convert to 32-bit mov that clears upper 32-bit */
 				insn->code = BPF_ALU | BPF_MOV | BPF_X;
-				/* clear off, so it's a normal 'wX = wY' from JIT pov */
+				/* clear off and imm, so it's a normal 'wX = wY' from JIT pov */
 				insn->off = 0;
+				insn->imm = 0;
 			} /* cast from as(0) to as(1) should be handled by JIT */
 			goto next_insn;
 		}