Merge tag 'bpf-next-6.19' of git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next

Pull bpf updates from Alexei Starovoitov:

 - Convert selftests/bpf/test_tc_edt and test_tc_tunnel from .sh to
   test_progs runner (Alexis Lothoré)

 - Convert selftests/bpf/test_xsk to test_progs runner (Bastien
   Curutchet)

 - Replace bpf memory allocator with kmalloc_nolock() in
   bpf_local_storage (Amery Hung), and in bpf streams and range tree
   (Puranjay Mohan)

 - Introduce support for indirect jumps in BPF verifier and x86 JIT
   (Anton Protopopov) and arm64 JIT (Puranjay Mohan)

 - Remove runqslower bpf tool (Hoyeon Lee)

 - Fix corner cases in the verifier to close several syzbot reports
   (Eduard Zingerman, KaFai Wan)

 - Several improvements in deadlock detection in rqspinlock (Kumar
   Kartikeya Dwivedi)

 - Implement "jmp" mode for BPF trampoline and corresponding
   DYNAMIC_FTRACE_WITH_JMP. It improves "fexit" program type performance
   from 80 M/s to 136 M/s. With Steven's Ack. (Menglong Dong)

 - Add ability to test non-linear skbs in BPF_PROG_TEST_RUN (Paul
   Chaignon)

 - Do not let BPF_PROG_TEST_RUN emit invalid GSO types to stack (Daniel
   Borkmann)

 - Generalize buildid reader into bpf_dynptr (Mykyta Yatsenko)

 - Optimize bpf_map_update_elem() for map-in-map types (Ritesh
   Oedayrajsingh Varma)

 - Introduce overwrite mode for BPF ring buffer (Xu Kuohai)

* tag 'bpf-next-6.19' of git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next: (169 commits)
  bpf: optimize bpf_map_update_elem() for map-in-map types
  bpf: make kprobe_multi_link_prog_run always_inline
  selftests/bpf: do not hardcode target rate in test_tc_edt BPF program
  selftests/bpf: remove test_tc_edt.sh
  selftests/bpf: integrate test_tc_edt into test_progs
  selftests/bpf: rename test_tc_edt.bpf.c section to expose program type
  selftests/bpf: Add success stats to rqspinlock stress test
  rqspinlock: Precede non-head waiter queueing with AA check
  rqspinlock: Disable spinning for trylock fallback
  rqspinlock: Use trylock fallback when per-CPU rqnode is busy
  rqspinlock: Perform AA checks immediately
  rqspinlock: Enclose lock/unlock within lock entry acquisitions
  bpf: Remove runqslower tool
  selftests/bpf: Remove usage of lsm/file_alloc_security in selftest
  bpf: Disable file_alloc_security hook
  bpf: check for insn arrays in check_ptr_alignment
  bpf: force BPF_F_RDONLY_PROG on insn array creation
  bpf: Fix exclusive map memory leak
  selftests/bpf: Make CS length configurable for rqspinlock stress test
  selftests/bpf: Add lock wait time stats to rqspinlock stress test
  ...

1 files changed, 6 insertions, 15 deletions

diff --git a/kernel/bpf/range_tree.c b/kernel/bpf/range_tree.c
index 37b80a23ae1a..99c63d982c5d 100644
--- a/kernel/bpf/range_tree.c
+++ b/kernel/bpf/range_tree.c
@@ -2,7 +2,6 @@
 /* Copyright (c) 2024 Meta Platforms, Inc. and affiliates. */
 #include <linux/interval_tree_generic.h>
 #include <linux/slab.h>
-#include <linux/bpf_mem_alloc.h>
 #include <linux/bpf.h>
 #include "range_tree.h"
 
@@ -21,7 +20,7 @@
  * in commit 6772fcc8890a ("xfs: convert xbitmap to interval tree").
  *
  * The implementation relies on external lock to protect rbtree-s.
- * The alloc/free of range_node-s is done via bpf_mem_alloc.
+ * The alloc/free of range_node-s is done via kmalloc_nolock().
  *
  * bpf arena is using range_tree to represent unallocated slots.
  * At init time:
@@ -150,9 +149,7 @@ int range_tree_clear(struct range_tree *rt, u32 start, u32 len)
 			range_it_insert(rn, rt);
 
 			/* Add a range */
-			migrate_disable();
-			new_rn = bpf_mem_alloc(&bpf_global_ma, sizeof(struct range_node));
-			migrate_enable();
+			new_rn = kmalloc_nolock(sizeof(struct range_node), 0, NUMA_NO_NODE);
 			if (!new_rn)
 				return -ENOMEM;
 			new_rn->rn_start = last + 1;
@@ -172,9 +169,7 @@ int range_tree_clear(struct range_tree *rt, u32 start, u32 len)
 		} else {
 			/* in the middle of the clearing range */
 			range_it_remove(rn, rt);
-			migrate_disable();
-			bpf_mem_free(&bpf_global_ma, rn);
-			migrate_enable();
+			kfree_nolock(rn);
 		}
 	}
 	return 0;
@@ -227,9 +222,7 @@ int range_tree_set(struct range_tree *rt, u32 start, u32 len)
 		range_it_remove(right, rt);
 		left->rn_last = right->rn_last;
 		range_it_insert(left, rt);
-		migrate_disable();
-		bpf_mem_free(&bpf_global_ma, right);
-		migrate_enable();
+		kfree_nolock(right);
 	} else if (left) {
 		/* Combine with the left range */
 		range_it_remove(left, rt);
@@ -241,9 +234,7 @@ int range_tree_set(struct range_tree *rt, u32 start, u32 len)
 		right->rn_start = start;
 		range_it_insert(right, rt);
 	} else {
-		migrate_disable();
-		left = bpf_mem_alloc(&bpf_global_ma, sizeof(struct range_node));
-		migrate_enable();
+		left = kmalloc_nolock(sizeof(struct range_node), 0, NUMA_NO_NODE);
 		if (!left)
 			return -ENOMEM;
 		left->rn_start = start;
@@ -259,7 +250,7 @@ void range_tree_destroy(struct range_tree *rt)
 
 	while ((rn = range_it_iter_first(rt, 0, -1U))) {
 		range_it_remove(rn, rt);
-		bpf_mem_free(&bpf_global_ma, rn);
+		kfree_nolock(rn);
 	}
 }