[PATCH AUTOSEL 5.1 012/375] tools/bpf: fix perf build error with uClibc (seen on ARC)

[PATCH AUTOSEL 5.1 012/375] tools/bpf: fix perf build error with uClibc (seen on ARC)

[Sasha Levin]

From: Vineet Gupta <Vineet.Gupta1@synopsys.com>

[ Upstream commit ca31ca8247e2d3807ff5fa1d1760616a2292001c ]

When build perf for ARC recently, there was a build failure due to lack
of __NR_bpf.

| Auto-detecting system features:
|
| ...                     get_cpuid: [ OFF ]
| ...                           bpf: [ on  ]
|
| #  error __NR_bpf not defined. libbpf does not support your arch.
    ^~~~~
| bpf.c: In function 'sys_bpf':
| bpf.c:66:17: error: '__NR_bpf' undeclared (first use in this function)
|  return syscall(__NR_bpf, cmd, attr, size);
|                 ^~~~~~~~
|                 sys_bpf

Signed-off-by: Vineet Gupta <vgupta@synopsys.com>
Acked-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 tools/lib/bpf/bpf.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index 9cd015574e838..d82edadf75893 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -46,6 +46,8 @@
 #  define __NR_bpf 349
 # elif defined(__s390__)
 #  define __NR_bpf 351
+# elif defined(__arc__)
+#  define __NR_bpf 280
 # else
 #  error __NR_bpf not defined. libbpf does not support your arch.
 # endif
-- 
2.20.1

[PATCH AUTOSEL 5.1 014/375] libbpf: fix invalid munmap call

[Sasha Levin]

From: Björn Töpel <bjorn.topel@intel.com>

[ Upstream commit 0e6741f092979535d159d5a851f12c88bfb7cb9a ]

When unmapping the AF_XDP memory regions used for the rings, an
invalid address was passed to the munmap() calls. Instead of passing
the beginning of the memory region, the descriptor region was passed
to munmap.

When the userspace application tried to tear down an AF_XDP socket,
the operation failed and the application would still have a reference
to socket it wished to get rid of.

Reported-by: William Tu <u9012063@gmail.com>
Fixes: 1cad07884239 ("libbpf: add support for using AF_XDP sockets")
Signed-off-by: Björn Töpel <bjorn.topel@intel.com>
Tested-by: William Tu <u9012063@gmail.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 tools/lib/bpf/xsk.c | 77 +++++++++++++++++++++++----------------------
 1 file changed, 40 insertions(+), 37 deletions(-)

diff --git a/tools/lib/bpf/xsk.c b/tools/lib/bpf/xsk.c
index 8d0078b65486f..af5f310ecca1c 100644
--- a/tools/lib/bpf/xsk.c
+++ b/tools/lib/bpf/xsk.c
@@ -248,8 +248,7 @@ int xsk_umem__create(struct xsk_umem **umem_ptr, void *umem_area, __u64 size,
 	return 0;
 
 out_mmap:
-	munmap(umem->fill,
-	       off.fr.desc + umem->config.fill_size * sizeof(__u64));
+	munmap(map, off.fr.desc + umem->config.fill_size * sizeof(__u64));
 out_socket:
 	close(umem->fd);
 out_umem_alloc:
@@ -523,11 +522,11 @@ int xsk_socket__create(struct xsk_socket **xsk_ptr, const char *ifname,
 		       struct xsk_ring_cons *rx, struct xsk_ring_prod *tx,
 		       const struct xsk_socket_config *usr_config)
 {
+	void *rx_map = NULL, *tx_map = NULL;
 	struct sockaddr_xdp sxdp = {};
 	struct xdp_mmap_offsets off;
 	struct xsk_socket *xsk;
 	socklen_t optlen;
-	void *map;
 	int err;
 
 	if (!umem || !xsk_ptr || !rx || !tx)
@@ -593,40 +592,40 @@ int xsk_socket__create(struct xsk_socket **xsk_ptr, const char *ifname,
 	}
 
 	if (rx) {
-		map = xsk_mmap(NULL, off.rx.desc +
-			       xsk->config.rx_size * sizeof(struct xdp_desc),
-			       PROT_READ | PROT_WRITE,
-			       MAP_SHARED | MAP_POPULATE,
-			       xsk->fd, XDP_PGOFF_RX_RING);
-		if (map == MAP_FAILED) {
+		rx_map = xsk_mmap(NULL, off.rx.desc +
+				  xsk->config.rx_size * sizeof(struct xdp_desc),
+				  PROT_READ | PROT_WRITE,
+				  MAP_SHARED | MAP_POPULATE,
+				  xsk->fd, XDP_PGOFF_RX_RING);
+		if (rx_map == MAP_FAILED) {
 			err = -errno;
 			goto out_socket;
 		}
 
 		rx->mask = xsk->config.rx_size - 1;
 		rx->size = xsk->config.rx_size;
-		rx->producer = map + off.rx.producer;
-		rx->consumer = map + off.rx.consumer;
-		rx->ring = map + off.rx.desc;
+		rx->producer = rx_map + off.rx.producer;
+		rx->consumer = rx_map + off.rx.consumer;
+		rx->ring = rx_map + off.rx.desc;
 	}
 	xsk->rx = rx;
 
 	if (tx) {
-		map = xsk_mmap(NULL, off.tx.desc +
-			       xsk->config.tx_size * sizeof(struct xdp_desc),
-			       PROT_READ | PROT_WRITE,
-			       MAP_SHARED | MAP_POPULATE,
-			       xsk->fd, XDP_PGOFF_TX_RING);
-		if (map == MAP_FAILED) {
+		tx_map = xsk_mmap(NULL, off.tx.desc +
+				  xsk->config.tx_size * sizeof(struct xdp_desc),
+				  PROT_READ | PROT_WRITE,
+				  MAP_SHARED | MAP_POPULATE,
+				  xsk->fd, XDP_PGOFF_TX_RING);
+		if (tx_map == MAP_FAILED) {
 			err = -errno;
 			goto out_mmap_rx;
 		}
 
 		tx->mask = xsk->config.tx_size - 1;
 		tx->size = xsk->config.tx_size;
-		tx->producer = map + off.tx.producer;
-		tx->consumer = map + off.tx.consumer;
-		tx->ring = map + off.tx.desc;
+		tx->producer = tx_map + off.tx.producer;
+		tx->consumer = tx_map + off.tx.consumer;
+		tx->ring = tx_map + off.tx.desc;
 		tx->cached_cons = xsk->config.tx_size;
 	}
 	xsk->tx = tx;
@@ -653,13 +652,11 @@ int xsk_socket__create(struct xsk_socket **xsk_ptr, const char *ifname,
 
 out_mmap_tx:
 	if (tx)
-		munmap(xsk->tx,
-		       off.tx.desc +
+		munmap(tx_map, off.tx.desc +
 		       xsk->config.tx_size * sizeof(struct xdp_desc));
 out_mmap_rx:
 	if (rx)
-		munmap(xsk->rx,
-		       off.rx.desc +
+		munmap(rx_map, off.rx.desc +
 		       xsk->config.rx_size * sizeof(struct xdp_desc));
 out_socket:
 	if (--umem->refcount)
@@ -684,10 +681,12 @@ int xsk_umem__delete(struct xsk_umem *umem)
 	optlen = sizeof(off);
 	err = getsockopt(umem->fd, SOL_XDP, XDP_MMAP_OFFSETS, &off, &optlen);
 	if (!err) {
-		munmap(umem->fill->ring,
-		       off.fr.desc + umem->config.fill_size * sizeof(__u64));
-		munmap(umem->comp->ring,
-		       off.cr.desc + umem->config.comp_size * sizeof(__u64));
+		(void)munmap(umem->fill->ring - off.fr.desc,
+			     off.fr.desc +
+			     umem->config.fill_size * sizeof(__u64));
+		(void)munmap(umem->comp->ring - off.cr.desc,
+			     off.cr.desc +
+			     umem->config.comp_size * sizeof(__u64));
 	}
 
 	close(umem->fd);
@@ -698,6 +697,7 @@ int xsk_umem__delete(struct xsk_umem *umem)
 
 void xsk_socket__delete(struct xsk_socket *xsk)
 {
+	size_t desc_sz = sizeof(struct xdp_desc);
 	struct xdp_mmap_offsets off;
 	socklen_t optlen;
 	int err;
@@ -710,14 +710,17 @@ void xsk_socket__delete(struct xsk_socket *xsk)
 	optlen = sizeof(off);
 	err = getsockopt(xsk->fd, SOL_XDP, XDP_MMAP_OFFSETS, &off, &optlen);
 	if (!err) {
-		if (xsk->rx)
-			munmap(xsk->rx->ring,
-			       off.rx.desc +
-			       xsk->config.rx_size * sizeof(struct xdp_desc));
-		if (xsk->tx)
-			munmap(xsk->tx->ring,
-			       off.tx.desc +
-			       xsk->config.tx_size * sizeof(struct xdp_desc));
+		if (xsk->rx) {
+			(void)munmap(xsk->rx->ring - off.rx.desc,
+				     off.rx.desc +
+				     xsk->config.rx_size * desc_sz);
+		}
+		if (xsk->tx) {
+			(void)munmap(xsk->tx->ring - off.tx.desc,
+				     off.tx.desc +
+				     xsk->config.tx_size * desc_sz);
+		}
+
 	}
 
 	xsk->umem->refcount--;
-- 
2.20.1

[PATCH AUTOSEL 5.1 015/375] selftests/bpf: set RLIMIT_MEMLOCK properly for test_libbpf_open.c

[Sasha Levin]

From: Yonghong Song <yhs@fb.com>

[ Upstream commit 6cea33701eb024bc6c920ab83940ee22afd29139 ]

Test test_libbpf.sh failed on my development server with failure
  -bash-4.4$ sudo ./test_libbpf.sh
  [0] libbpf: Error in bpf_object__probe_name():Operation not permitted(1).
      Couldn't load basic 'r0 = 0' BPF program.
  test_libbpf: failed at file test_l4lb.o
  selftests: test_libbpf [FAILED]
  -bash-4.4$

The reason is because my machine has 64KB locked memory by default which
is not enough for this program to get locked memory.
Similar to other bpf selftests, let us increase RLIMIT_MEMLOCK
to infinity, which fixed the issue.

Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 tools/testing/selftests/bpf/test_libbpf_open.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/tools/testing/selftests/bpf/test_libbpf_open.c b/tools/testing/selftests/bpf/test_libbpf_open.c
index 65cbd30704b5a..9e9db202d218a 100644
--- a/tools/testing/selftests/bpf/test_libbpf_open.c
+++ b/tools/testing/selftests/bpf/test_libbpf_open.c
@@ -11,6 +11,8 @@ static const char *__doc__ =
 #include <bpf/libbpf.h>
 #include <getopt.h>
 
+#include "bpf_rlimit.h"
+
 static const struct option long_options[] = {
 	{"help",	no_argument,		NULL, 'h' },
 	{"debug",	no_argument,		NULL, 'D' },
-- 
2.20.1

[PATCH AUTOSEL 5.1 016/375] bpftool: exclude bash-completion/bpftool from .gitignore pattern

[Sasha Levin]

From: Masahiro Yamada <yamada.masahiro@socionext.com>

[ Upstream commit a7d006714724de4334c5e3548701b33f7b12ca96 ]

tools/bpf/bpftool/.gitignore has the "bpftool" pattern, which is
intended to ignore the following build artifact:

  tools/bpf/bpftool/bpftool

However, the .gitignore entry is effective not only for the current
directory, but also for any sub-directories.

So, from the point of .gitignore grammar, the following check-in file
is also considered to be ignored:

  tools/bpf/bpftool/bash-completion/bpftool

As the manual gitignore(5) says "Files already tracked by Git are not
affected", this is not a problem as far as Git is concerned.

However, Git is not the only program that parses .gitignore because
.gitignore is useful to distinguish build artifacts from source files.

For example, tar(1) supports the --exclude-vcs-ignore option. As of
writing, this option does not work perfectly, but it intends to create
a tarball excluding files specified by .gitignore.

So, I believe it is better to fix this issue.

You can fix it by prefixing the pattern with a slash; the leading slash
means the specified pattern is relative to the current directory.

Signed-off-by: Masahiro Yamada <yamada.masahiro@socionext.com>
Reviewed-by: Quentin Monnet <quentin.monnet@netronome.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 tools/bpf/bpftool/.gitignore | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/tools/bpf/bpftool/.gitignore b/tools/bpf/bpftool/.gitignore
index 67167e44b7266..8248b8dd89d4b 100644
--- a/tools/bpf/bpftool/.gitignore
+++ b/tools/bpf/bpftool/.gitignore
@@ -1,5 +1,5 @@
 *.d
-bpftool
+/bpftool
 bpftool*.8
 bpf-helpers.*
 FEATURE-DUMP.bpftool
-- 
2.20.1

[PATCH AUTOSEL 5.1 055/375] x86/modules: Avoid breaking W^X while loading modules

[Sasha Levin]

From: Nadav Amit <namit@vmware.com>

[ Upstream commit f2c65fb3221adc6b73b0549fc7ba892022db9797 ]

When modules and BPF filters are loaded, there is a time window in
which some memory is both writable and executable. An attacker that has
already found another vulnerability (e.g., a dangling pointer) might be
able to exploit this behavior to overwrite kernel code. Prevent having
writable executable PTEs in this stage.

In addition, avoiding having W+X mappings can also slightly simplify the
patching of modules code on initialization (e.g., by alternatives and
static-key), as would be done in the next patch. This was actually the
main motivation for this patch.

To avoid having W+X mappings, set them initially as RW (NX) and after
they are set as RO set them as X as well. Setting them as executable is
done as a separate step to avoid one core in which the old PTE is cached
(hence writable), and another which sees the updated PTE (executable),
which would break the W^X protection.

Suggested-by: Thomas Gleixner <tglx@linutronix.de>
Suggested-by: Andy Lutomirski <luto@amacapital.net>
Signed-off-by: Nadav Amit <namit@vmware.com>
Signed-off-by: Rick Edgecombe <rick.p.edgecombe@intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: <akpm@linux-foundation.org>
Cc: <ard.biesheuvel@linaro.org>
Cc: <deneen.t.dock@intel.com>
Cc: <kernel-hardening@lists.openwall.com>
Cc: <kristen@linux.intel.com>
Cc: <linux_dti@icloud.com>
Cc: <will.deacon@arm.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Jessica Yu <jeyu@kernel.org>
Cc: Kees Cook <keescook@chromium.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Rik van Riel <riel@surriel.com>
Link: https://lkml.kernel.org/r/20190426001143.4983-12-namit@vmware.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 arch/x86/kernel/alternative.c | 28 +++++++++++++++++++++-------
 arch/x86/kernel/module.c      |  2 +-
 include/linux/filter.h        |  1 +
 kernel/module.c               |  5 +++++
 4 files changed, 28 insertions(+), 8 deletions(-)

diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index 9a79c7808f9cc..d7df79fc448cd 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -667,15 +667,29 @@ void __init alternative_instructions(void)
  * handlers seeing an inconsistent instruction while you patch.
  */
 void *__init_or_module text_poke_early(void *addr, const void *opcode,
-					      size_t len)
+				       size_t len)
 {
 	unsigned long flags;
-	local_irq_save(flags);
-	memcpy(addr, opcode, len);
-	local_irq_restore(flags);
-	sync_core();
-	/* Could also do a CLFLUSH here to speed up CPU recovery; but
-	   that causes hangs on some VIA CPUs. */
+
+	if (boot_cpu_has(X86_FEATURE_NX) &&
+	    is_module_text_address((unsigned long)addr)) {
+		/*
+		 * Modules text is marked initially as non-executable, so the
+		 * code cannot be running and speculative code-fetches are
+		 * prevented. Just change the code.
+		 */
+		memcpy(addr, opcode, len);
+	} else {
+		local_irq_save(flags);
+		memcpy(addr, opcode, len);
+		local_irq_restore(flags);
+		sync_core();
+
+		/*
+		 * Could also do a CLFLUSH here to speed up CPU recovery; but
+		 * that causes hangs on some VIA CPUs.
+		 */
+	}
 	return addr;
 }
 
diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c
index b052e883dd8cc..cfa3106faee42 100644
--- a/arch/x86/kernel/module.c
+++ b/arch/x86/kernel/module.c
@@ -87,7 +87,7 @@ void *module_alloc(unsigned long size)
 	p = __vmalloc_node_range(size, MODULE_ALIGN,
 				    MODULES_VADDR + get_module_load_offset(),
 				    MODULES_END, GFP_KERNEL,
-				    PAGE_KERNEL_EXEC, 0, NUMA_NO_NODE,
+				    PAGE_KERNEL, 0, NUMA_NO_NODE,
 				    __builtin_return_address(0));
 	if (p && (kasan_module_alloc(p, size) < 0)) {
 		vfree(p);
diff --git a/include/linux/filter.h b/include/linux/filter.h
index 6074aa064b540..14ec3bdad9a90 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -746,6 +746,7 @@ static inline void bpf_prog_unlock_ro(struct bpf_prog *fp)
 static inline void bpf_jit_binary_lock_ro(struct bpf_binary_header *hdr)
 {
 	set_memory_ro((unsigned long)hdr, hdr->pages);
+	set_memory_x((unsigned long)hdr, hdr->pages);
 }
 
 static inline void bpf_jit_binary_unlock_ro(struct bpf_binary_header *hdr)
diff --git a/kernel/module.c b/kernel/module.c
index 0b9aa8ab89f08..2b2845ae983ed 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -1950,8 +1950,13 @@ void module_enable_ro(const struct module *mod, bool after_init)
 		return;
 
 	frob_text(&mod->core_layout, set_memory_ro);
+	frob_text(&mod->core_layout, set_memory_x);
+
 	frob_rodata(&mod->core_layout, set_memory_ro);
+
 	frob_text(&mod->init_layout, set_memory_ro);
+	frob_text(&mod->init_layout, set_memory_x);
+
 	frob_rodata(&mod->init_layout, set_memory_ro);
 
 	if (after_init)
-- 
2.20.1