bpf: Adjust size_index according to the value of KMALLOC_MIN_SIZE

The following warning was reported when running "./test_progs -a
link_api -a linked_list" on a RISC-V QEMU VM:

  ------------[ cut here ]------------
  WARNING: CPU: 3 PID: 261 at kernel/bpf/memalloc.c:342 bpf_mem_refill
  Modules linked in: bpf_testmod(OE)
  CPU: 3 PID: 261 Comm: test_progs- ... 6.5.0-rc5-01743-gdcb152bb8328 #2
  Hardware name: riscv-virtio,qemu (DT)
  epc : bpf_mem_refill+0x1fc/0x206
   ra : irq_work_single+0x68/0x70
  epc : ffffffff801b1bc4 ra : ffffffff8015fe84 sp : ff2000000001be20
   gp : ffffffff82d26138 tp : ff6000008477a800 t0 : 0000000000046600
   t1 : ffffffff812b6ddc t2 : 0000000000000000 s0 : ff2000000001be70
   s1 : ff5ffffffffe8998 a0 : ff5ffffffffe8998 a1 : ff600003fef4b000
   a2 : 000000000000003f a3 : ffffffff80008250 a4 : 0000000000000060
   a5 : 0000000000000080 a6 : 0000000000000000 a7 : 0000000000735049
   s2 : ff5ffffffffe8998 s3 : 0000000000000022 s4 : 0000000000001000
   s5 : 0000000000000007 s6 : ff5ffffffffe8570 s7 : ffffffff82d6bd30
   s8 : 000000000000003f s9 : ffffffff82d2c5e8 s10: 000000000000ffff
   s11: ffffffff82d2c5d8 t3 : ffffffff81ea8f28 t4 : 0000000000000000
   t5 : ff6000008fd28278 t6 : 0000000000040000
  [<ffffffff801b1bc4>] bpf_mem_refill+0x1fc/0x206
  [<ffffffff8015fe84>] irq_work_single+0x68/0x70
  [<ffffffff8015feb4>] irq_work_run_list+0x28/0x36
  [<ffffffff8015fefa>] irq_work_run+0x38/0x66
  [<ffffffff8000828a>] handle_IPI+0x3a/0xb4
  [<ffffffff800a5c3a>] handle_percpu_devid_irq+0xa4/0x1f8
  [<ffffffff8009fafa>] generic_handle_domain_irq+0x28/0x36
  [<ffffffff800ae570>] ipi_mux_process+0xac/0xfa
  [<ffffffff8000a8ea>] sbi_ipi_handle+0x2e/0x88
  [<ffffffff8009fafa>] generic_handle_domain_irq+0x28/0x36
  [<ffffffff807ee70e>] riscv_intc_irq+0x36/0x4e
  [<ffffffff812b5d3a>] handle_riscv_irq+0x54/0x86
  [<ffffffff812b6904>] do_irq+0x66/0x98
  ---[ end trace 0000000000000000 ]---

The warning is due to WARN_ON_ONCE(tgt->unit_size != c->unit_size) in
free_bulk(). The direct reason is that a object is allocated and
freed by bpf_mem_caches with different unit_size.

The root cause is that KMALLOC_MIN_SIZE is 64 and there is no 96-bytes
slab cache in the specific VM. When linked_list test allocates a
72-bytes object through bpf_obj_new(), bpf_global_ma will allocate it
from a bpf_mem_cache with 96-bytes unit_size, but this bpf_mem_cache is
backed by 128-bytes slab cache. When the object is freed, bpf_mem_free()
uses ksize() to choose the corresponding bpf_mem_cache. Because the
object is allocated from 128-bytes slab cache, ksize() returns 128,
bpf_mem_free() chooses a 128-bytes bpf_mem_cache to free the object and
triggers the warning.

A similar warning will also be reported when using CONFIG_SLAB instead
of CONFIG_SLUB in a x86-64 kernel. Because CONFIG_SLUB defines
KMALLOC_MIN_SIZE as 8 but CONFIG_SLAB defines KMALLOC_MIN_SIZE as 32.

An alternative fix is to use kmalloc_size_round() in bpf_mem_alloc() to
choose a bpf_mem_cache which has the same unit_size with the backing
slab cache, but it may introduce performance degradation, so fix the
warning by adjusting the indexes in size_index according to the value of
KMALLOC_MIN_SIZE just like setup_kmalloc_cache_index_table() does.

Fixes: 822fb26bdb55 ("bpf: Add a hint to allocated objects.")
Reported-by: Björn Töpel <bjorn@kernel.org>
Closes: https://lore.kernel.org/bpf/87jztjmmy4.fsf@all.your.base.are.belong.to.us
Signed-off-by: Hou Tao <houtao1@huawei.com>
Link: https://lore.kernel.org/r/20230908133923.2675053-2-houtao@huaweicloud.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

diff --git a/kernel/bpf/memalloc.c b/kernel/bpf/memalloc.c
index 9c49ae53deaf81f9e22fefc376657492abd2ebb9..98d9e96fba3c5b9ab94a308519d360fc859ea0c9 100644 (file)
--- a/kernel/bpf/memalloc.c
+++ b/kernel/bpf/memalloc.c
@@ -916,3 +916,41 @@ void notrace *bpf_mem_cache_alloc_flags(struct bpf_mem_alloc *ma, gfp_t flags)
 
        return !ret ? NULL : ret + LLIST_NODE_SZ;
 }
+
+/* Most of the logic is taken from setup_kmalloc_cache_index_table() */
+static __init int bpf_mem_cache_adjust_size(void)
+{
+       unsigned int size, index;
+
+       /* Normally KMALLOC_MIN_SIZE is 8-bytes, but it can be
+        * up-to 256-bytes.
+        */
+       size = KMALLOC_MIN_SIZE;
+       if (size <= 192)
+               index = size_index[(size - 1) / 8];
+       else
+               index = fls(size - 1) - 1;
+       for (size = 8; size < KMALLOC_MIN_SIZE && size <= 192; size += 8)
+               size_index[(size - 1) / 8] = index;
+
+       /* The minimal alignment is 64-bytes, so disable 96-bytes cache and
+        * use 128-bytes cache instead.
+        */
+       if (KMALLOC_MIN_SIZE >= 64) {
+               index = size_index[(128 - 1) / 8];
+               for (size = 64 + 8; size <= 96; size += 8)
+                       size_index[(size - 1) / 8] = index;
+       }
+
+       /* The minimal alignment is 128-bytes, so disable 192-bytes cache and
+        * use 256-bytes cache instead.
+        */
+       if (KMALLOC_MIN_SIZE >= 128) {
+               index = fls(256 - 1) - 1;
+               for (size = 128 + 8; size <= 192; size += 8)
+                       size_index[(size - 1) / 8] = index;
+       }
+
+       return 0;
+}
+subsys_initcall(bpf_mem_cache_adjust_size);