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

Daniel Borkmann says:

====================
pull-request: bpf 2024-04-04

We've added 7 non-merge commits during the last 5 day(s) which contain
a total of 9 files changed, 75 insertions(+), 24 deletions(-).

The main changes are:

1) Fix x86 BPF JIT under retbleed=stuff which causes kernel panics due to
   incorrect destination IP calculation and incorrect IP for relocations,
   from Uros Bizjak and Joan Bruguera Micó.

2) Fix BPF arena file descriptor leaks in the verifier,
   from Anton Protopopov.

3) Defer bpf_link deallocation to after RCU grace period as currently
   running multi-{kprobes,uprobes} programs might still access cookie
   information from the link, from Andrii Nakryiko.

4) Fix a BPF sockmap lock inversion deadlock in map_delete_elem reported
   by syzkaller, from Jakub Sitnicki.

5) Fix resolve_btfids build with musl libc due to missing linux/types.h
   include, from Natanael Copa.

* tag 'for-netdev' of https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf:
  bpf, sockmap: Prevent lock inversion deadlock in map delete elem
  x86/bpf: Fix IP for relocating call depth accounting
  x86/bpf: Fix IP after emitting call depth accounting
  bpf: fix possible file descriptor leaks in verifier
  tools/resolve_btfids: fix build with musl libc
  bpf: support deferring bpf_link dealloc to after RCU grace period
  bpf: put uprobe link's path and task in release callback
====================

Link: https://lore.kernel.org/r/20240404183258.4401-1-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

3 files changed, 12 insertions, 15 deletions

diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h
index fcd20c6dc7f90c..67b68d0d17d1ec 100644
--- a/arch/x86/include/asm/alternative.h
+++ b/arch/x86/include/asm/alternative.h
@@ -117,7 +117,7 @@ extern void callthunks_patch_builtin_calls(void);
 extern void callthunks_patch_module_calls(struct callthunk_sites *sites,
 					  struct module *mod);
 extern void *callthunks_translate_call_dest(void *dest);
-extern int x86_call_depth_emit_accounting(u8 **pprog, void *func);
+extern int x86_call_depth_emit_accounting(u8 **pprog, void *func, void *ip);
 #else
 static __always_inline void callthunks_patch_builtin_calls(void) {}
 static __always_inline void
@@ -128,7 +128,7 @@ static __always_inline void *callthunks_translate_call_dest(void *dest)
 	return dest;
 }
 static __always_inline int x86_call_depth_emit_accounting(u8 **pprog,
-							  void *func)
+							  void *func, void *ip)
 {
 	return 0;
 }
diff --git a/arch/x86/kernel/callthunks.c b/arch/x86/kernel/callthunks.c
index 30335182b6b0ae..e92ff0c11db814 100644
--- a/arch/x86/kernel/callthunks.c
+++ b/arch/x86/kernel/callthunks.c
@@ -314,7 +314,7 @@ static bool is_callthunk(void *addr)
 	return !bcmp(pad, insn_buff, tmpl_size);
 }
 
-int x86_call_depth_emit_accounting(u8 **pprog, void *func)
+int x86_call_depth_emit_accounting(u8 **pprog, void *func, void *ip)
 {
 	unsigned int tmpl_size = SKL_TMPL_SIZE;
 	u8 insn_buff[MAX_PATCH_LEN];
@@ -327,7 +327,7 @@ int x86_call_depth_emit_accounting(u8 **pprog, void *func)
 		return 0;
 
 	memcpy(insn_buff, skl_call_thunk_template, tmpl_size);
-	apply_relocation(insn_buff, tmpl_size, *pprog,
+	apply_relocation(insn_buff, tmpl_size, ip,
 			 skl_call_thunk_template, tmpl_size);
 
 	memcpy(*pprog, insn_buff, tmpl_size);
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index a7ba8e1786452d..df5fac428408fe 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -480,7 +480,7 @@ static int emit_call(u8 **pprog, void *func, void *ip)
 static int emit_rsb_call(u8 **pprog, void *func, void *ip)
 {
 	OPTIMIZER_HIDE_VAR(func);
-	x86_call_depth_emit_accounting(pprog, func);
+	ip += x86_call_depth_emit_accounting(pprog, func, ip);
 	return emit_patch(pprog, func, ip, 0xE8);
 }
 
@@ -1972,20 +1972,17 @@ populate_extable:
 
 			/* call */
 		case BPF_JMP | BPF_CALL: {
-			int offs;
+			u8 *ip = image + addrs[i - 1];
 
 			func = (u8 *) __bpf_call_base + imm32;
 			if (tail_call_reachable) {
 				RESTORE_TAIL_CALL_CNT(bpf_prog->aux->stack_depth);
-				if (!imm32)
-					return -EINVAL;
-				offs = 7 + x86_call_depth_emit_accounting(&prog, func);
-			} else {
-				if (!imm32)
-					return -EINVAL;
-				offs = x86_call_depth_emit_accounting(&prog, func);
+				ip += 7;
 			}
-			if (emit_call(&prog, func, image + addrs[i - 1] + offs))
+			if (!imm32)
+				return -EINVAL;
+			ip += x86_call_depth_emit_accounting(&prog, func, ip);
+			if (emit_call(&prog, func, ip))
 				return -EINVAL;
 			break;
 		}
@@ -2835,7 +2832,7 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im
 		 * Direct-call fentry stub, as such it needs accounting for the
 		 * __fentry__ call.
 		 */
-		x86_call_depth_emit_accounting(&prog, NULL);
+		x86_call_depth_emit_accounting(&prog, NULL, image);
 	}
 	EMIT1(0x55);		 /* push rbp */
 	EMIT3(0x48, 0x89, 0xE5); /* mov rbp, rsp */