Merge https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf

Daniel Borkmann says:

====================
pull-request: bpf 2021-11-05

We've added 15 non-merge commits during the last 3 day(s) which contain
a total of 14 files changed, 199 insertions(+), 90 deletions(-).

The main changes are:

1) Fix regression from stack spill/fill of <8 byte scalars, from Martin KaFai Lau.

2) Fix perf's build of bpftool's bootstrap version due to missing libbpf
   headers, from Quentin Monnet.

3) Fix riscv{32,64} BPF exception tables build errors and warnings, from Björn Töpel.

4) Fix bpf fs to allow RENAME_EXCHANGE support for atomic upgrades on sk_lookup
   control planes, from Lorenz Bauer.

5) Fix libbpf's error reporting in bpf_map_lookup_and_delete_elem_flags() due to
   missing libbpf_err_errno(), from Mehrdad Arshad Rad.

6) Various fixes to make xdp_redirect_multi selftest more reliable, from Hangbin Liu.

7) Fix netcnt selftest to make it run serial and thus avoid conflicts with other
   cgroup/skb selftests run in parallel that could cause flakes, from Andrii Nakryiko.

8) Fix reuseport_bpf_numa networking selftest to skip unavailable NUMA nodes,
   from Kleber Sacilotto de Souza.

* https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf:
  riscv, bpf: Fix RV32 broken build, and silence RV64 warning
  selftests/bpf/xdp_redirect_multi: Limit the tests in netns
  selftests/bpf/xdp_redirect_multi: Give tcpdump a chance to terminate cleanly
  selftests/bpf/xdp_redirect_multi: Use arping to accurate the arp number
  selftests/bpf/xdp_redirect_multi: Put the logs to tmp folder
  libbpf: Fix lookup_and_delete_elem_flags error reporting
  bpftool: Install libbpf headers for the bootstrap version, too
  selftests/net: Fix reuseport_bpf_numa by skipping unavailable nodes
  selftests/bpf: Verifier test on refill from a smaller spill
  bpf: Do not reject when the stack read size is different from the tracked scalar size
  selftests/bpf: Make netcnt selftests serial to avoid spurious failures
  selftests/bpf: Test RENAME_EXCHANGE and RENAME_NOREPLACE on bpffs
  selftests/bpf: Convert test_bpffs to ASSERT macros
  libfs: Support RENAME_EXCHANGE in simple_rename()
  libfs: Move shmem_exchange to simple_rename_exchange
====================

Link: https://lore.kernel.org/r/20211105165803.29372-1-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

arch/riscv/mm/extable.c

@@ -11,7 +11,7 @@
 #include <linux/module.h>
 #include <linux/uaccess.h>
 
-#ifdef CONFIG_BPF_JIT
+#if defined(CONFIG_BPF_JIT) && defined(CONFIG_ARCH_RV64I)
 int rv_bpf_fixup_exception(const struct exception_table_entry *ex, struct pt_regs *regs);
 #endif
 
@@ -23,7 +23,7 @@ int fixup_exception(struct pt_regs *regs)
 	if (!fixup)
 		return 0;
 
-#ifdef CONFIG_BPF_JIT
+#if defined(CONFIG_BPF_JIT) && defined(CONFIG_ARCH_RV64I)
 	if (regs->epc >= BPF_JIT_REGION_START && regs->epc < BPF_JIT_REGION_END)
 		return rv_bpf_fixup_exception(fixup, regs);
 #endif

arch/riscv/net/bpf_jit_comp64.c

@@ -459,6 +459,8 @@ static int emit_call(bool fixed, u64 addr, struct rv_jit_context *ctx)
 #define BPF_FIXUP_OFFSET_MASK   GENMASK(26, 0)
 #define BPF_FIXUP_REG_MASK      GENMASK(31, 27)
 
+int rv_bpf_fixup_exception(const struct exception_table_entry *ex,
+				struct pt_regs *regs);
 int rv_bpf_fixup_exception(const struct exception_table_entry *ex,
 				struct pt_regs *regs)
 {

fs/libfs.c

@@ -448,16 +448,43 @@ int simple_rmdir(struct inode *dir, struct dentry *dentry)
 }
 EXPORT_SYMBOL(simple_rmdir);
 
+int simple_rename_exchange(struct inode *old_dir, struct dentry *old_dentry,
+			   struct inode *new_dir, struct dentry *new_dentry)
+{
+	bool old_is_dir = d_is_dir(old_dentry);
+	bool new_is_dir = d_is_dir(new_dentry);
+
+	if (old_dir != new_dir && old_is_dir != new_is_dir) {
+		if (old_is_dir) {
+			drop_nlink(old_dir);
+			inc_nlink(new_dir);
+		} else {
+			drop_nlink(new_dir);
+			inc_nlink(old_dir);
+		}
+	}
+	old_dir->i_ctime = old_dir->i_mtime =
+	new_dir->i_ctime = new_dir->i_mtime =
+	d_inode(old_dentry)->i_ctime =
+	d_inode(new_dentry)->i_ctime = current_time(old_dir);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(simple_rename_exchange);
+
 int simple_rename(struct user_namespace *mnt_userns, struct inode *old_dir,
 		  struct dentry *old_dentry, struct inode *new_dir,
 		  struct dentry *new_dentry, unsigned int flags)
 {
 	struct inode *inode = d_inode(old_dentry);
 	int they_are_dirs = d_is_dir(old_dentry);
 
-	if (flags & ~RENAME_NOREPLACE)
+	if (flags & ~(RENAME_NOREPLACE | RENAME_EXCHANGE))
 		return -EINVAL;
 
+	if (flags & RENAME_EXCHANGE)
+		return simple_rename_exchange(old_dir, old_dentry, new_dir, new_dentry);
+
 	if (!simple_empty(new_dentry))
 		return -ENOTEMPTY;
 

include/linux/fs.h

@@ -3383,6 +3383,8 @@ extern int simple_open(struct inode *inode, struct file *file);
 extern int simple_link(struct dentry *, struct inode *, struct dentry *);
 extern int simple_unlink(struct inode *, struct dentry *);
 extern int simple_rmdir(struct inode *, struct dentry *);
+extern int simple_rename_exchange(struct inode *old_dir, struct dentry *old_dentry,
+				  struct inode *new_dir, struct dentry *new_dentry);
 extern int simple_rename(struct user_namespace *, struct inode *,
 			 struct dentry *, struct inode *, struct dentry *,
 			 unsigned int);

kernel/bpf/verifier.c

@@ -3088,9 +3088,12 @@ static int check_stack_read_fixed_off(struct bpf_verifier_env *env,
 	reg = &reg_state->stack[spi].spilled_ptr;
 
 	if (is_spilled_reg(&reg_state->stack[spi])) {
-		if (size != BPF_REG_SIZE) {
-			u8 scalar_size = 0;
+		u8 spill_size = 1;
+
+		for (i = BPF_REG_SIZE - 1; i > 0 && stype[i - 1] == STACK_SPILL; i--)
+			spill_size++;
 
+		if (size != BPF_REG_SIZE || spill_size != BPF_REG_SIZE) {
 			if (reg->type != SCALAR_VALUE) {
 				verbose_linfo(env, env->insn_idx, "; ");
 				verbose(env, "invalid size of register fill\n");
@@ -3101,10 +3104,7 @@ static int check_stack_read_fixed_off(struct bpf_verifier_env *env,
 			if (dst_regno < 0)
 				return 0;
 
-			for (i = BPF_REG_SIZE; i > 0 && stype[i - 1] == STACK_SPILL; i--)
-				scalar_size++;
-
-			if (!(off % BPF_REG_SIZE) && size == scalar_size) {
+			if (!(off % BPF_REG_SIZE) && size == spill_size) {
 				/* The earlier check_reg_arg() has decided the
 				 * subreg_def for this insn.  Save it first.
 				 */
@@ -3128,12 +3128,6 @@ static int check_stack_read_fixed_off(struct bpf_verifier_env *env,
 			state->regs[dst_regno].live |= REG_LIVE_WRITTEN;
 			return 0;
 		}
-		for (i = 1; i < BPF_REG_SIZE; i++) {
-			if (stype[(slot - i) % BPF_REG_SIZE] != STACK_SPILL) {
-				verbose(env, "corrupted spill memory\n");
-				return -EACCES;
-			}
-		}
 
 		if (dst_regno >= 0) {
 			/* restore register state from stack */

mm/shmem.c

@@ -2947,28 +2947,6 @@ static int shmem_rmdir(struct inode *dir, struct dentry *dentry)
 	return shmem_unlink(dir, dentry);
 }
 
-static int shmem_exchange(struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry)
-{
-	bool old_is_dir = d_is_dir(old_dentry);
-	bool new_is_dir = d_is_dir(new_dentry);
-
-	if (old_dir != new_dir && old_is_dir != new_is_dir) {
-		if (old_is_dir) {
-			drop_nlink(old_dir);
-			inc_nlink(new_dir);
-		} else {
-			drop_nlink(new_dir);
-			inc_nlink(old_dir);
-		}
-	}
-	old_dir->i_ctime = old_dir->i_mtime =
-	new_dir->i_ctime = new_dir->i_mtime =
-	d_inode(old_dentry)->i_ctime =
-	d_inode(new_dentry)->i_ctime = current_time(old_dir);
-
-	return 0;
-}
-
 static int shmem_whiteout(struct user_namespace *mnt_userns,
 			  struct inode *old_dir, struct dentry *old_dentry)
 {
@@ -3014,7 +2992,7 @@ static int shmem_rename2(struct user_namespace *mnt_userns,
 		return -EINVAL;
 
 	if (flags & RENAME_EXCHANGE)
-		return shmem_exchange(old_dir, old_dentry, new_dir, new_dentry);
+		return simple_rename_exchange(old_dir, old_dentry, new_dir, new_dentry);
 
 	if (!simple_empty(new_dentry))
 		return -ENOTEMPTY;

tools/bpf/bpftool/Makefile

@@ -22,24 +22,29 @@ else
   _OUTPUT := $(CURDIR)
 endif
 BOOTSTRAP_OUTPUT := $(_OUTPUT)/bootstrap/
+
 LIBBPF_OUTPUT := $(_OUTPUT)/libbpf/
 LIBBPF_DESTDIR := $(LIBBPF_OUTPUT)
 LIBBPF_INCLUDE := $(LIBBPF_DESTDIR)/include
 LIBBPF_HDRS_DIR := $(LIBBPF_INCLUDE)/bpf
+LIBBPF := $(LIBBPF_OUTPUT)libbpf.a
 
-LIBBPF = $(LIBBPF_OUTPUT)libbpf.a
-LIBBPF_BOOTSTRAP_OUTPUT = $(BOOTSTRAP_OUTPUT)libbpf/
-LIBBPF_BOOTSTRAP = $(LIBBPF_BOOTSTRAP_OUTPUT)libbpf.a
+LIBBPF_BOOTSTRAP_OUTPUT := $(BOOTSTRAP_OUTPUT)libbpf/
+LIBBPF_BOOTSTRAP_DESTDIR := $(LIBBPF_BOOTSTRAP_OUTPUT)
+LIBBPF_BOOTSTRAP_INCLUDE := $(LIBBPF_BOOTSTRAP_DESTDIR)/include
+LIBBPF_BOOTSTRAP_HDRS_DIR := $(LIBBPF_BOOTSTRAP_INCLUDE)/bpf
+LIBBPF_BOOTSTRAP := $(LIBBPF_BOOTSTRAP_OUTPUT)libbpf.a
 
 # We need to copy hashmap.h and nlattr.h which is not otherwise exported by
 # libbpf, but still required by bpftool.
 LIBBPF_INTERNAL_HDRS := $(addprefix $(LIBBPF_HDRS_DIR)/,hashmap.h nlattr.h)
+LIBBPF_BOOTSTRAP_INTERNAL_HDRS := $(addprefix $(LIBBPF_BOOTSTRAP_HDRS_DIR)/,hashmap.h)
 
 ifeq ($(BPFTOOL_VERSION),)
 BPFTOOL_VERSION := $(shell make -rR --no-print-directory -sC ../../.. kernelversion)
 endif
 
-$(LIBBPF_OUTPUT) $(BOOTSTRAP_OUTPUT) $(LIBBPF_BOOTSTRAP_OUTPUT) $(LIBBPF_HDRS_DIR):
+$(LIBBPF_OUTPUT) $(BOOTSTRAP_OUTPUT) $(LIBBPF_BOOTSTRAP_OUTPUT) $(LIBBPF_HDRS_DIR) $(LIBBPF_BOOTSTRAP_HDRS_DIR):
 	$(QUIET_MKDIR)mkdir -p $@
 
 $(LIBBPF): $(wildcard $(BPF_DIR)/*.[ch] $(BPF_DIR)/Makefile) | $(LIBBPF_OUTPUT)
@@ -52,7 +57,12 @@ $(LIBBPF_INTERNAL_HDRS): $(LIBBPF_HDRS_DIR)/%.h: $(BPF_DIR)/%.h | $(LIBBPF_HDRS_
 
 $(LIBBPF_BOOTSTRAP): $(wildcard $(BPF_DIR)/*.[ch] $(BPF_DIR)/Makefile) | $(LIBBPF_BOOTSTRAP_OUTPUT)
 	$(Q)$(MAKE) -C $(BPF_DIR) OUTPUT=$(LIBBPF_BOOTSTRAP_OUTPUT) \
-		ARCH= CC=$(HOSTCC) LD=$(HOSTLD) $@
+		DESTDIR=$(LIBBPF_BOOTSTRAP_DESTDIR) prefix= \
+		ARCH= CC=$(HOSTCC) LD=$(HOSTLD) $@ install_headers
+
+$(LIBBPF_BOOTSTRAP_INTERNAL_HDRS): $(LIBBPF_BOOTSTRAP_HDRS_DIR)/%.h: $(BPF_DIR)/%.h | $(LIBBPF_BOOTSTRAP_HDRS_DIR)
+	$(call QUIET_INSTALL, $@)
+	$(Q)install -m 644 -t $(LIBBPF_BOOTSTRAP_HDRS_DIR) $<
 
 $(LIBBPF)-clean: FORCE | $(LIBBPF_OUTPUT)
 	$(call QUIET_CLEAN, libbpf)
@@ -172,11 +182,11 @@ else
 	$(Q)cp "$(VMLINUX_H)" $@
 endif
 
-$(OUTPUT)%.bpf.o: skeleton/%.bpf.c $(OUTPUT)vmlinux.h $(LIBBPF)
+$(OUTPUT)%.bpf.o: skeleton/%.bpf.c $(OUTPUT)vmlinux.h $(LIBBPF_BOOTSTRAP)
 	$(QUIET_CLANG)$(CLANG) \
 		-I$(if $(OUTPUT),$(OUTPUT),.) \
 		-I$(srctree)/tools/include/uapi/ \
-		-I$(LIBBPF_INCLUDE) \
+		-I$(LIBBPF_BOOTSTRAP_INCLUDE) \
 		-g -O2 -Wall -target bpf -c $< -o $@ && $(LLVM_STRIP) -g $@
 
 $(OUTPUT)%.skel.h: $(OUTPUT)%.bpf.o $(BPFTOOL_BOOTSTRAP)
@@ -209,8 +219,10 @@ $(BPFTOOL_BOOTSTRAP): $(BOOTSTRAP_OBJS) $(LIBBPF_BOOTSTRAP)
 $(OUTPUT)bpftool: $(OBJS) $(LIBBPF)
 	$(QUIET_LINK)$(CC) $(CFLAGS) $(LDFLAGS) -o $@ $(OBJS) $(LIBS)
 
-$(BOOTSTRAP_OUTPUT)%.o: %.c $(LIBBPF_INTERNAL_HDRS) | $(BOOTSTRAP_OUTPUT)
-	$(QUIET_CC)$(HOSTCC) $(CFLAGS) -c -MMD -o $@ $<
+$(BOOTSTRAP_OUTPUT)%.o: %.c $(LIBBPF_BOOTSTRAP_INTERNAL_HDRS) | $(BOOTSTRAP_OUTPUT)
+	$(QUIET_CC)$(HOSTCC) \
+		$(subst -I$(LIBBPF_INCLUDE),-I$(LIBBPF_BOOTSTRAP_INCLUDE),$(CFLAGS)) \
+		-c -MMD -o $@ $<
 
 $(OUTPUT)%.o: %.c
 	$(QUIET_CC)$(CC) $(CFLAGS) -c -MMD -o $@ $<
@@ -257,6 +269,6 @@ doc-uninstall:
 FORCE:
 
 .SECONDARY:
-.PHONY: all FORCE clean install-bin install uninstall
+.PHONY: all FORCE bootstrap clean install-bin install uninstall
 .PHONY: doc doc-clean doc-install doc-uninstall
 .DEFAULT_GOAL := all

tools/lib/bpf/bpf.c

@@ -515,14 +515,16 @@ int bpf_map_lookup_and_delete_elem(int fd, const void *key, void *value)
 int bpf_map_lookup_and_delete_elem_flags(int fd, const void *key, void *value, __u64 flags)
 {
 	union bpf_attr attr;
+	int ret;
 
 	memset(&attr, 0, sizeof(attr));
 	attr.map_fd = fd;
 	attr.key = ptr_to_u64(key);
 	attr.value = ptr_to_u64(value);
 	attr.flags = flags;
 
-	return sys_bpf(BPF_MAP_LOOKUP_AND_DELETE_ELEM, &attr, sizeof(attr));
+	ret = sys_bpf(BPF_MAP_LOOKUP_AND_DELETE_ELEM, &attr, sizeof(attr));
+	return libbpf_err_errno(ret);
 }
 
 int bpf_map_delete_elem(int fd, const void *key)

tools/testing/selftests/bpf/prog_tests/netcnt.c

@@ -8,7 +8,7 @@
 
 #define CG_NAME "/netcnt"
 
-void test_netcnt(void)
+void serial_test_netcnt(void)
 {
 	union percpu_net_cnt *percpu_netcnt = NULL;
 	struct bpf_cgroup_storage_key key;

tools/testing/selftests/bpf/prog_tests/test_bpffs.c

@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright (c) 2020 Facebook */
 #define _GNU_SOURCE
+#include <stdio.h>
 #include <sched.h>
 #include <sys/mount.h>
 #include <sys/stat.h>
@@ -29,44 +30,106 @@ static int read_iter(char *file)
 
 static int fn(void)
 {
-	int err, duration = 0;
+	struct stat a, b, c;
+	int err, map;
 
 	err = unshare(CLONE_NEWNS);
-	if (CHECK(err, "unshare", "failed: %d\n", errno))
+	if (!ASSERT_OK(err, "unshare"))
 		goto out;
 
 	err = mount("", "/", "", MS_REC | MS_PRIVATE, NULL);
-	if (CHECK(err, "mount /", "failed: %d\n", errno))
+	if (!ASSERT_OK(err, "mount /"))
 		goto out;
 
 	err = umount(TDIR);
-	if (CHECK(err, "umount " TDIR, "failed: %d\n", errno))
+	if (!ASSERT_OK(err, "umount " TDIR))
 		goto out;
 
 	err = mount("none", TDIR, "tmpfs", 0, NULL);
-	if (CHECK(err, "mount", "mount root failed: %d\n", errno))
+	if (!ASSERT_OK(err, "mount tmpfs"))
 		goto out;
 
 	err = mkdir(TDIR "/fs1", 0777);
-	if (CHECK(err, "mkdir "TDIR"/fs1", "failed: %d\n", errno))
+	if (!ASSERT_OK(err, "mkdir " TDIR "/fs1"))
 		goto out;
 	err = mkdir(TDIR "/fs2", 0777);
-	if (CHECK(err, "mkdir "TDIR"/fs2", "failed: %d\n", errno))
+	if (!ASSERT_OK(err, "mkdir " TDIR "/fs2"))
 		goto out;
 
 	err = mount("bpf", TDIR "/fs1", "bpf", 0, NULL);
-	if (CHECK(err, "mount bpffs "TDIR"/fs1", "failed: %d\n", errno))
+	if (!ASSERT_OK(err, "mount bpffs " TDIR "/fs1"))
 		goto out;
 	err = mount("bpf", TDIR "/fs2", "bpf", 0, NULL);
-	if (CHECK(err, "mount bpffs " TDIR "/fs2", "failed: %d\n", errno))
+	if (!ASSERT_OK(err, "mount bpffs " TDIR "/fs2"))
 		goto out;
 
 	err = read_iter(TDIR "/fs1/maps.debug");
-	if (CHECK(err, "reading " TDIR "/fs1/maps.debug", "failed\n"))
+	if (!ASSERT_OK(err, "reading " TDIR "/fs1/maps.debug"))
 		goto out;
 	err = read_iter(TDIR "/fs2/progs.debug");
-	if (CHECK(err, "reading " TDIR "/fs2/progs.debug", "failed\n"))
+	if (!ASSERT_OK(err, "reading " TDIR "/fs2/progs.debug"))
 		goto out;
+
+	err = mkdir(TDIR "/fs1/a", 0777);
+	if (!ASSERT_OK(err, "creating " TDIR "/fs1/a"))
+		goto out;
+	err = mkdir(TDIR "/fs1/a/1", 0777);
+	if (!ASSERT_OK(err, "creating " TDIR "/fs1/a/1"))
+		goto out;
+	err = mkdir(TDIR "/fs1/b", 0777);
+	if (!ASSERT_OK(err, "creating " TDIR "/fs1/b"))
+		goto out;
+
+	map = bpf_create_map(BPF_MAP_TYPE_ARRAY, 4, 4, 1, 0);
+	if (!ASSERT_GT(map, 0, "create_map(ARRAY)"))
+		goto out;
+	err = bpf_obj_pin(map, TDIR "/fs1/c");
+	if (!ASSERT_OK(err, "pin map"))
+		goto out;
+	close(map);
+
+	/* Check that RENAME_EXCHANGE works for directories. */
+	err = stat(TDIR "/fs1/a", &a);
+	if (!ASSERT_OK(err, "stat(" TDIR "/fs1/a)"))
+		goto out;
+	err = renameat2(0, TDIR "/fs1/a", 0, TDIR "/fs1/b", RENAME_EXCHANGE);
+	if (!ASSERT_OK(err, "renameat2(/fs1/a, /fs1/b, RENAME_EXCHANGE)"))
+		goto out;
+	err = stat(TDIR "/fs1/b", &b);
+	if (!ASSERT_OK(err, "stat(" TDIR "/fs1/b)"))
+		goto out;
+	if (!ASSERT_EQ(a.st_ino, b.st_ino, "b should have a's inode"))
+		goto out;
+	err = access(TDIR "/fs1/b/1", F_OK);
+	if (!ASSERT_OK(err, "access(" TDIR "/fs1/b/1)"))
+		goto out;
+
+	/* Check that RENAME_EXCHANGE works for mixed file types. */
+	err = stat(TDIR "/fs1/c", &c);
+	if (!ASSERT_OK(err, "stat(" TDIR "/fs1/map)"))
+		goto out;
+	err = renameat2(0, TDIR "/fs1/c", 0, TDIR "/fs1/b", RENAME_EXCHANGE);
+	if (!ASSERT_OK(err, "renameat2(/fs1/c, /fs1/b, RENAME_EXCHANGE)"))
+		goto out;
+	err = stat(TDIR "/fs1/b", &b);
+	if (!ASSERT_OK(err, "stat(" TDIR "/fs1/b)"))
+		goto out;
+	if (!ASSERT_EQ(c.st_ino, b.st_ino, "b should have c's inode"))
+		goto out;
+	err = access(TDIR "/fs1/c/1", F_OK);
+	if (!ASSERT_OK(err, "access(" TDIR "/fs1/c/1)"))
+		goto out;
+
+	/* Check that RENAME_NOREPLACE works. */
+	err = renameat2(0, TDIR "/fs1/b", 0, TDIR "/fs1/a", RENAME_NOREPLACE);
+	if (!ASSERT_ERR(err, "renameat2(RENAME_NOREPLACE)")) {
+		err = -EINVAL;
+		goto out;
+	}
+	err = access(TDIR "/fs1/b", F_OK);
+	if (!ASSERT_OK(err, "access(" TDIR "/fs1/b)"))
+		goto out;
+
 out:
 	umount(TDIR "/fs1");
 	umount(TDIR "/fs2");