renegade-project/linux-next
2
0
Fork 0
mirror of https://github.com/edk2-porting/linux-next.git synced 2024-09-21 16:12:33 +08:00
Code

Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf.git

Browse Source
This commit is contained in:
Stephen Rothwell 2024-03-22 09:01:15 +11:00
commit 8da25c4851
18 changed files with 153 additions and 58 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
.mailmap
View File

@ -498,7 +498,8 @@ Prasad Sodagudi <quic_psodagud@quicinc.com> <psodagud@codeaurora.org>
Punit Agrawal <punitagrawal@gmail.com> <punit.agrawal@arm.com>
Qais Yousef <qyousef@layalina.io> <qais.yousef@imgtec.com>
Qais Yousef <qyousef@layalina.io> <qais.yousef@arm.com>
Quentin Monnet <quentin@isovalent.com> <quentin.monnet@netronome.com>
Quentin Monnet <qmo@kernel.org> <quentin.monnet@netronome.com>
Quentin Monnet <qmo@kernel.org> <quentin@isovalent.com>
Quentin Perret <qperret@qperret.net> <quentin.perret@arm.com>
Rafael J. Wysocki <rjw@rjwysocki.net> <rjw@sisk.pl>
Rajeev Nandan <quic_rajeevny@quicinc.com> <rajeevny@codeaurora.org>

2
MAINTAINERS
View File

@ -3967,7 +3967,7 @@ F: kernel/bpf/bpf_lru*
F: kernel/bpf/cgroup.c
BPF [TOOLING] (bpftool)
M: Quentin Monnet <quentin@isovalent.com>
M: Quentin Monnet <qmo@kernel.org>
L: bpf@vger.kernel.org
S: Maintained
F: kernel/bpf/disasm.*

4
arch/arm64/net/bpf_jit_comp.c
View File

@ -943,7 +943,7 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx,
emit(A64_UXTH(is64, dst, dst), ctx);
break;
case 32:
emit(A64_REV32(is64, dst, dst), ctx);
emit(A64_REV32(0, dst, dst), ctx);
/* upper 32 bits already cleared */
break;
case 64:
@ -1256,7 +1256,7 @@ emit_cond_jmp:
} else {
emit_a64_mov_i(1, tmp, off, ctx);
if (sign_extend)
emit(A64_LDRSW(dst, src_adj, off_adj), ctx);
emit(A64_LDRSW(dst, src, tmp), ctx);
else
emit(A64_LDR32(dst, src, tmp), ctx);
}

46
arch/s390/net/bpf_jit_comp.c
View File

@ -516,11 +516,12 @@ static void bpf_skip(struct bpf_jit *jit, int size)
* PLT for hotpatchable calls. The calling convention is the same as for the
* ftrace hotpatch trampolines: %r0 is return address, %r1 is clobbered.
*/
extern const char bpf_plt[];
extern const char bpf_plt_ret[];
extern const char bpf_plt_target[];
extern const char bpf_plt_end[];
#define BPF_PLT_SIZE 32
struct bpf_plt {
char code[16];
void *ret;
void *target;
} __packed;
extern const struct bpf_plt bpf_plt;
asm(
".pushsection .rodata\n"
" .balign 8\n"
@ -531,15 +532,14 @@ asm(
" .balign 8\n"
"bpf_plt_ret: .quad 0\n"
"bpf_plt_target: .quad 0\n"
"bpf_plt_end:\n"
" .popsection\n"
);
static void bpf_jit_plt(void *plt, void *ret, void *target)
static void bpf_jit_plt(struct bpf_plt *plt, void *ret, void *target)
{
memcpy(plt, bpf_plt, BPF_PLT_SIZE);
*(void **)((char *)plt + (bpf_plt_ret - bpf_plt)) = ret;
*(void **)((char *)plt + (bpf_plt_target - bpf_plt)) = target ?: ret;
memcpy(plt, &bpf_plt, sizeof(*plt));
plt->ret = ret;
plt->target = target;
}
/*
@ -662,9 +662,9 @@ static void bpf_jit_epilogue(struct bpf_jit *jit, u32 stack_depth)
jit->prg = ALIGN(jit->prg, 8);
jit->prologue_plt = jit->prg;
if (jit->prg_buf)
bpf_jit_plt(jit->prg_buf + jit->prg,
bpf_jit_plt((struct bpf_plt *)(jit->prg_buf + jit->prg),
jit->prg_buf + jit->prologue_plt_ret, NULL);
jit->prg += BPF_PLT_SIZE;
jit->prg += sizeof(struct bpf_plt);
}
static int get_probe_mem_regno(const u8 *insn)
@ -2040,9 +2040,6 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *fp)
struct bpf_jit jit;
int pass;
if (WARN_ON_ONCE(bpf_plt_end - bpf_plt != BPF_PLT_SIZE))
return orig_fp;
if (!fp->jit_requested)
return orig_fp;
@ -2148,14 +2145,11 @@ bool bpf_jit_supports_far_kfunc_call(void)
int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t,
void *old_addr, void *new_addr)
{
struct bpf_plt expected_plt, current_plt, new_plt, *plt;
struct {
u16 opc;
s32 disp;
} __packed insn;
char expected_plt[BPF_PLT_SIZE];
char current_plt[BPF_PLT_SIZE];
char new_plt[BPF_PLT_SIZE];
char *plt;
char *ret;
int err;
@ -2174,18 +2168,18 @@ int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t,
*/
} else {
/* Verify the PLT. */
plt = (char *)ip + (insn.disp << 1);
err = copy_from_kernel_nofault(current_plt, plt, BPF_PLT_SIZE);
plt = ip + (insn.disp << 1);
err = copy_from_kernel_nofault(&current_plt, plt,
sizeof(current_plt));
if (err < 0)
return err;
ret = (char *)ip + 6;
bpf_jit_plt(expected_plt, ret, old_addr);
if (memcmp(current_plt, expected_plt, BPF_PLT_SIZE))
bpf_jit_plt(&expected_plt, ret, old_addr);
if (memcmp(&current_plt, &expected_plt, sizeof(current_plt)))
return -EINVAL;
/* Adjust the call address. */
bpf_jit_plt(new_plt, ret, new_addr);
s390_kernel_write(plt + (bpf_plt_target - bpf_plt),
new_plt + (bpf_plt_target - bpf_plt),
bpf_jit_plt(&new_plt, ret, new_addr);
s390_kernel_write(&plt->target, &new_plt.target,
sizeof(void *));
}

2
include/net/xdp_sock.h
View File

@ -188,6 +188,8 @@ static inline void xsk_tx_metadata_complete(struct xsk_tx_metadata_compl *compl,
{
if (!compl)
return;
if (!compl->tx_timestamp)
return;
*compl->tx_timestamp = ops->tmo_fill_timestamp(priv);
}

25
kernel/bpf/arena.c
View File

@ -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);

10
kernel/bpf/verifier.c
View File

@ -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));

4
scripts/bpf_doc.py
View File

@ -414,8 +414,8 @@ class PrinterRST(Printer):
version = version.stdout.decode().rstrip()
except:
try:
version = subprocess.run(['make', 'kernelversion'], cwd=linuxRoot,
capture_output=True, check=True)
version = subprocess.run(['make', '-s', '--no-print-directory', 'kernelversion'],
cwd=linuxRoot, capture_output=True, check=True)
version = version.stdout.decode().rstrip()
except:
return 'Linux'

2
tools/bpf/bpftool/gen.c
View File

@ -121,7 +121,7 @@ static bool get_datasec_ident(const char *sec_name, char *buf, size_t buf_sz)
int i, n;
/* recognize hard coded LLVM section name */
if (strcmp(sec_name, ".arena.1") == 0) {
if (strcmp(sec_name, ".addr_space.1") == 0) {
/* this is the name to use in skeleton */
snprintf(buf, buf_sz, "arena");
return true;

10
tools/lib/bpf/libbpf.c
View File

@ -498,7 +498,7 @@ struct bpf_struct_ops {
#define KSYMS_SEC ".ksyms"
#define STRUCT_OPS_SEC ".struct_ops"
#define STRUCT_OPS_LINK_SEC ".struct_ops.link"
#define ARENA_SEC ".arena.1"
#define ARENA_SEC ".addr_space.1"
enum libbpf_map_type {
LIBBPF_MAP_UNSPEC,
@ -1650,6 +1650,10 @@ static int sys_memfd_create(const char *name, unsigned flags)
return syscall(__NR_memfd_create, name, flags);
}
#ifndef MFD_CLOEXEC
#define MFD_CLOEXEC 0x0001U
#endif
static int create_placeholder_fd(void)
{
int fd;
@ -5352,8 +5356,8 @@ retry:
goto err_out;
}
if (map->def.type == BPF_MAP_TYPE_ARENA) {
map->mmaped = mmap((void *)map->map_extra, bpf_map_mmap_sz(map),
PROT_READ | PROT_WRITE,
map->mmaped = mmap((void *)(long)map->map_extra,
bpf_map_mmap_sz(map), PROT_READ | PROT_WRITE,
map->map_extra ? MAP_SHARED | MAP_FIXED : MAP_SHARED,
map->fd, 0);
if (map->mmaped == MAP_FAILED) {

2
tools/testing/selftests/bpf/bpf_arena_common.h
View File

@ -32,7 +32,7 @@
*/
#endif
#if defined(__BPF_FEATURE_ARENA_CAST) && !defined(BPF_ARENA_FORCE_ASM)
#if defined(__BPF_FEATURE_ADDR_SPACE_CAST) && !defined(BPF_ARENA_FORCE_ASM)
#define __arena __attribute__((address_space(1)))
#define cast_kern(ptr) /* nop for bpf prog. emitted by LLVM */
#define cast_user(ptr) /* nop for bpf prog. emitted by LLVM */

8
tools/testing/selftests/bpf/prog_tests/arena_htab.c
View File

@ -3,12 +3,14 @@
#include <test_progs.h>
#include <sys/mman.h>
#include <network_helpers.h>
#include <sys/user.h>
#ifndef PAGE_SIZE /* on some archs it comes in sys/user.h */
#include <unistd.h>
#define PAGE_SIZE getpagesize()
#endif
#include "arena_htab_asm.skel.h"
#include "arena_htab.skel.h"
#define PAGE_SIZE 4096
#include "bpf_arena_htab.h"
static void test_arena_htab_common(struct htab *htab)

7
tools/testing/selftests/bpf/prog_tests/arena_list.c
View File

@ -3,8 +3,11 @@
#include <test_progs.h>
#include <sys/mman.h>
#include <network_helpers.h>
#define PAGE_SIZE 4096
#include <sys/user.h>
#ifndef PAGE_SIZE /* on some archs it comes in sys/user.h */
#include <unistd.h>
#define PAGE_SIZE getpagesize()
#endif
#include "bpf_arena_list.h"
#include "arena_list.skel.h"

2
tools/testing/selftests/bpf/prog_tests/verifier.c
View File

@ -5,6 +5,7 @@
#include "cap_helpers.h"
#include "verifier_and.skel.h"
#include "verifier_arena.skel.h"
#include "verifier_arena_large.skel.h"
#include "verifier_array_access.skel.h"
#include "verifier_basic_stack.skel.h"
#include "verifier_bitfield_write.skel.h"
@ -120,6 +121,7 @@ static void run_tests_aux(const char *skel_name,
void test_verifier_and(void) { RUN(verifier_and); }
void test_verifier_arena(void) { RUN(verifier_arena); }
void test_verifier_arena_large(void) { RUN(verifier_arena_large); }
void test_verifier_basic_stack(void) { RUN(verifier_basic_stack); }
void test_verifier_bitfield_write(void) { RUN(verifier_bitfield_write); }
void test_verifier_bounds(void) { RUN(verifier_bounds); }

2
tools/testing/selftests/bpf/progs/arena_htab.c
View File

@ -22,7 +22,7 @@ int zero = 0;
SEC("syscall")
int arena_htab_llvm(void *ctx)
{
#if defined(__BPF_FEATURE_ARENA_CAST) || defined(BPF_ARENA_FORCE_ASM)
#if defined(__BPF_FEATURE_ADDR_SPACE_CAST) || defined(BPF_ARENA_FORCE_ASM)
struct htab __arena *htab;
__u64 i;

10
tools/testing/selftests/bpf/progs/arena_list.c
View File

@ -30,13 +30,13 @@ int list_sum;
int cnt;
bool skip = false;
#ifdef __BPF_FEATURE_ARENA_CAST
#ifdef __BPF_FEATURE_ADDR_SPACE_CAST
long __arena arena_sum;
int __arena test_val = 1;
struct arena_list_head __arena global_head;
#else
long arena_sum SEC(".arena.1");
int test_val SEC(".arena.1");
long arena_sum SEC(".addr_space.1");
int test_val SEC(".addr_space.1");
#endif
int zero;
@ -44,7 +44,7 @@ int zero;
SEC("syscall")
int arena_list_add(void *ctx)
{
#ifdef __BPF_FEATURE_ARENA_CAST
#ifdef __BPF_FEATURE_ADDR_SPACE_CAST
__u64 i;
list_head = &global_head;
@ -66,7 +66,7 @@ int arena_list_add(void *ctx)
SEC("syscall")
int arena_list_del(void *ctx)
{
#ifdef __BPF_FEATURE_ARENA_CAST
#ifdef __BPF_FEATURE_ADDR_SPACE_CAST
struct elem __arena *n;
int sum = 0;

4
tools/testing/selftests/bpf/progs/verifier_arena.c
View File

@ -19,7 +19,7 @@ SEC("syscall")
__success __retval(0)
int basic_alloc1(void *ctx)
{
#if defined(__BPF_FEATURE_ARENA_CAST)
#if defined(__BPF_FEATURE_ADDR_SPACE_CAST)
volatile int __arena *page1, *page2, *no_page, *page3;
page1 = bpf_arena_alloc_pages(&arena, NULL, 1, NUMA_NO_NODE, 0);
@ -58,7 +58,7 @@ SEC("syscall")
__success __retval(0)
int basic_alloc2(void *ctx)
{
#if defined(__BPF_FEATURE_ARENA_CAST)
#if defined(__BPF_FEATURE_ADDR_SPACE_CAST)
volatile char __arena *page1, *page2, *page3, *page4;
page1 = bpf_arena_alloc_pages(&arena, NULL, 2, NUMA_NO_NODE, 0);

68
tools/testing/selftests/bpf/progs/verifier_arena_large.c Normal file
View File

@ -0,0 +1,68 @@
// SPDX-License-Identifier: GPL-2.0
/* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */
#include <vmlinux.h>
#include <bpf/bpf_helpers.h>
#include <bpf/bpf_tracing.h>
#include "bpf_misc.h"
#include "bpf_experimental.h"
#include "bpf_arena_common.h"
#define ARENA_SIZE (1ull << 32)
struct {
__uint(type, BPF_MAP_TYPE_ARENA);
__uint(map_flags, BPF_F_MMAPABLE);
__uint(max_entries, ARENA_SIZE / PAGE_SIZE);
} arena SEC(".maps");
SEC("syscall")
__success __retval(0)
int big_alloc1(void *ctx)
{
#if defined(__BPF_FEATURE_ADDR_SPACE_CAST)
volatile char __arena *page1, *page2, *no_page, *page3;
void __arena *base;
page1 = base = bpf_arena_alloc_pages(&arena, NULL, 1, NUMA_NO_NODE, 0);
if (!page1)
return 1;
*page1 = 1;
page2 = bpf_arena_alloc_pages(&arena, base + ARENA_SIZE - PAGE_SIZE,
1, NUMA_NO_NODE, 0);
if (!page2)
return 2;
*page2 = 2;
no_page = bpf_arena_alloc_pages(&arena, base + ARENA_SIZE,
1, NUMA_NO_NODE, 0);
if (no_page)
return 3;
if (*page1 != 1)
return 4;
if (*page2 != 2)
return 5;
bpf_arena_free_pages(&arena, (void __arena *)page1, 1);
if (*page2 != 2)
return 6;
if (*page1 != 0) /* use-after-free should return 0 */
return 7;
page3 = bpf_arena_alloc_pages(&arena, NULL, 1, NUMA_NO_NODE, 0);
if (!page3)
return 8;
*page3 = 3;
if (page1 != page3)
return 9;
if (*page2 != 2)
return 10;
if (*(page1 + PAGE_SIZE) != 0)
return 11;
if (*(page1 - PAGE_SIZE) != 0)
return 12;
if (*(page2 + PAGE_SIZE) != 0)
return 13;
if (*(page2 - PAGE_SIZE) != 0)
return 14;
#endif
return 0;
}
char _license[] SEC("license") = "GPL";