From: Arnd Bergmann <[email protected]>
clang produces a build failure on x86 for some randconfig builds
after a change that moves around code to mm/mm_init.c:
Cannot find symbol for section 2: .text.
mm/mm_init.o: failed
I have not been able to figure out why this happens, but the __weak
annotation on arch_has_descending_max_zone_pfns() is the trigger here.
Removing the weak function in favor of an open-coded Kconfig option
check avoids the problem and becomes clearer as well as better to
optimize by the compiler.
Fixes: 9420f89db2dd ("mm: move most of core MM initialization to mm/mm_init.c")
Cc: [email protected]
Signed-off-by: Arnd Bergmann <[email protected]>
---
arch/arc/mm/init.c | 5 -----
include/linux/mm.h | 1 -
mm/mm_init.c | 4 ++--
3 files changed, 2 insertions(+), 8 deletions(-)
diff --git a/arch/arc/mm/init.c b/arch/arc/mm/init.c
index ce4e939a7f07..2b89b6c53801 100644
--- a/arch/arc/mm/init.c
+++ b/arch/arc/mm/init.c
@@ -74,11 +74,6 @@ void __init early_init_dt_add_memory_arch(u64 base, u64 size)
base, TO_MB(size), !in_use ? "Not used":"");
}
-bool arch_has_descending_max_zone_pfns(void)
-{
- return !IS_ENABLED(CONFIG_ARC_HAS_PAE40);
-}
-
/*
* First memory setup routine called from setup_arch()
* 1. setup swapper's mm @init_mm
diff --git a/include/linux/mm.h b/include/linux/mm.h
index ada57b11bb5a..a13cc121841d 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -3061,7 +3061,6 @@ extern void setup_per_cpu_pageset(void);
extern int min_free_kbytes;
extern int watermark_boost_factor;
extern int watermark_scale_factor;
-extern bool arch_has_descending_max_zone_pfns(void);
/* nommu.c */
extern atomic_long_t mmap_pages_allocated;
diff --git a/mm/mm_init.c b/mm/mm_init.c
index 35302b7bca83..f6165747fd3e 100644
--- a/mm/mm_init.c
+++ b/mm/mm_init.c
@@ -1754,9 +1754,9 @@ static void __init free_area_init_memoryless_node(int nid)
* Some architectures, e.g. ARC may have ZONE_HIGHMEM below ZONE_NORMAL. For
* such cases we allow max_zone_pfn sorted in the descending order
*/
-bool __weak arch_has_descending_max_zone_pfns(void)
+static bool arch_has_descending_max_zone_pfns(void)
{
- return false;
+ return !IS_ENABLED(CONFIG_ARC_HAS_PAE40);
}
/**
--
2.39.2
Hello,
kernel test robot noticed "kernel_BUG_at_lib/list_debug.c" on:
commit: c31fe5eb2ec68f6d2331fabc924e0030cc6bb2b3 ("[PATCH] mm: make arch_has_descending_max_zone_pfns() static")
url: https://github.com/intel-lab-lkp/linux/commits/Arnd-Bergmann/mm-make-arch_has_descending_max_zone_pfns-static/20230414-160608
base: https://git.kernel.org/cgit/linux/kernel/git/akpm/mm.git mm-everything
patch link: https://lore.kernel.org/all/[email protected]/
patch subject: [PATCH] mm: make arch_has_descending_max_zone_pfns() static
in testcase: boot
compiler: gcc-11
test machine: qemu-system-x86_64 -enable-kvm -cpu SandyBridge -smp 2 -m 16G
(please refer to attached dmesg/kmsg for entire log/backtrace)
+------------------------------------------+------------+------------+
| | 32ed3874f2 | c31fe5eb2e |
+------------------------------------------+------------+------------+
| boot_successes | 10 | 0 |
| boot_failures | 0 | 6 |
| kernel_BUG_at_lib/list_debug.c | 0 | 6 |
| invalid_opcode:#[##] | 0 | 6 |
| EIP:__list_add_valid | 0 | 6 |
| Kernel_panic-not_syncing:Fatal_exception | 0 | 6 |
+------------------------------------------+------------+------------+
If you fix the issue, kindly add following tag
| Reported-by: kernel test robot <[email protected]>
| Link: https://lore.kernel.org/oe-lkp/[email protected]
[ 0.004000][ T0] ------------[ cut here ]------------
[ 0.004000][ T0] kernel BUG at lib/list_debug.c:33!
[ 0.004000][ T0] invalid opcode: 0000 [#1] SMP
[ 0.004000][ T0] CPU: 0 PID: 0 Comm: swapper Not tainted 6.3.0-rc5-00613-gc31fe5eb2ec6 #42
[ 0.004000][ T0] EIP: __list_add_valid (??:?)
[ 0.004000][ T0] Code: 56 51 68 78 b0 4c c2 e8 39 c7 de ff 0f 0b b8 f4 60 a4 c2 eb 1c 39 d3 74 04 39 f3 75 19 51 50 53 68 ca b0 4c c2 e8 1b c7 de ff <0f> 0b b8 e8 60 a4 c2 e8 be 71 06 00 8d 65 f8 b0 01 5b 5e 5d 31 d2
All code
========
0: 56 push %rsi
1: 51 push %rcx
2: 68 78 b0 4c c2 pushq $0xffffffffc24cb078
7: e8 39 c7 de ff callq 0xffffffffffdec745
c: 0f 0b ud2
e: b8 f4 60 a4 c2 mov $0xc2a460f4,%eax
13: eb 1c jmp 0x31
15: 39 d3 cmp %edx,%ebx
17: 74 04 je 0x1d
19: 39 f3 cmp %esi,%ebx
1b: 75 19 jne 0x36
1d: 51 push %rcx
1e: 50 push %rax
1f: 53 push %rbx
20: 68 ca b0 4c c2 pushq $0xffffffffc24cb0ca
25: e8 1b c7 de ff callq 0xffffffffffdec745
2a:* 0f 0b ud2 <-- trapping instruction
2c: b8 e8 60 a4 c2 mov $0xc2a460e8,%eax
31: e8 be 71 06 00 callq 0x671f4
36: 8d 65 f8 lea -0x8(%rbp),%esp
39: b0 01 mov $0x1,%al
3b: 5b pop %rbx
3c: 5e pop %rsi
3d: 5d pop %rbp
3e: 31 d2 xor %edx,%edx
Code starting with the faulting instruction
===========================================
0: 0f 0b ud2
2: b8 e8 60 a4 c2 mov $0xc2a460e8,%eax
7: e8 be 71 06 00 callq 0x671ca
c: 8d 65 f8 lea -0x8(%rbp),%esp
f: b0 01 mov $0x1,%al
11: 5b pop %rbx
12: 5e pop %rsi
13: 5d pop %rbp
14: 31 d2 xor %edx,%edx
[ 0.004000][ T0] EAX: 00000040 EBX: ec373004 ECX: 00000000 EDX: 00000000
[ 0.004000][ T0] ESI: c2ba2b20 EDI: ec373004 EBP: c2689e94 ESP: c2689e7c
[ 0.004000][ T0] DS: 007b ES: 007b FS: 00d8 GS: 0000 SS: 0068 EFLAGS: 00210046
[ 0.004000][ T0] CR0: 80050033 CR2: 00000000 CR3: 02c7d000 CR4: 00040690
[ 0.004000][ T0] DR0: 00000000 DR1: 00000000 DR2: 00000000 DR3: 00000000
[ 0.004000][ T0] DR6: fffe0ff0 DR7: 00000400
[ 0.004000][ T0] Call Trace:
[ 0.004000][ T0] list_add_tail (uncore.c:?)
[ 0.004000][ T0] __free_one_page (page_alloc.c:?)
[ 0.004000][ T0] __free_pages_ok (page_alloc.c:?)
[ 0.004000][ T0] __free_pages_core (??:?)
[ 0.004000][ T0] memblock_free_pages (??:?)
[ 0.004000][ T0] memblock_free_all (??:?)
[ 0.004000][ T0] mem_init (??:?)
[ 0.004000][ T0] mm_core_init (??:?)
[ 0.004000][ T0] ? cpu_init (??:?)
[ 0.004000][ T0] start_kernel (??:?)
[ 0.004000][ T0] i386_start_kernel (??:?)
[ 0.004000][ T0] startup_32_smp (??:?)
[ 0.004000][ T0] Modules linked in:
[ 0.004000][ T0] ---[ end trace 0000000000000000 ]---
[ 0.004000][ T0] EIP: __list_add_valid (??:?)
[ 0.004000][ T0] Code: 56 51 68 78 b0 4c c2 e8 39 c7 de ff 0f 0b b8 f4 60 a4 c2 eb 1c 39 d3 74 04 39 f3 75 19 51 50 53 68 ca b0 4c c2 e8 1b c7 de ff <0f> 0b b8 e8 60 a4 c2 e8 be 71 06 00 8d 65 f8 b0 01 5b 5e 5d 31 d2
All code
========
0: 56 push %rsi
1: 51 push %rcx
2: 68 78 b0 4c c2 pushq $0xffffffffc24cb078
7: e8 39 c7 de ff callq 0xffffffffffdec745
c: 0f 0b ud2
e: b8 f4 60 a4 c2 mov $0xc2a460f4,%eax
13: eb 1c jmp 0x31
15: 39 d3 cmp %edx,%ebx
17: 74 04 je 0x1d
19: 39 f3 cmp %esi,%ebx
1b: 75 19 jne 0x36
1d: 51 push %rcx
1e: 50 push %rax
1f: 53 push %rbx
20: 68 ca b0 4c c2 pushq $0xffffffffc24cb0ca
25: e8 1b c7 de ff callq 0xffffffffffdec745
2a:* 0f 0b ud2 <-- trapping instruction
2c: b8 e8 60 a4 c2 mov $0xc2a460e8,%eax
31: e8 be 71 06 00 callq 0x671f4
36: 8d 65 f8 lea -0x8(%rbp),%esp
39: b0 01 mov $0x1,%al
3b: 5b pop %rbx
3c: 5e pop %rsi
3d: 5d pop %rbp
3e: 31 d2 xor %edx,%edx
Code starting with the faulting instruction
===========================================
0: 0f 0b ud2
2: b8 e8 60 a4 c2 mov $0xc2a460e8,%eax
7: e8 be 71 06 00 callq 0x671ca
c: 8d 65 f8 lea -0x8(%rbp),%esp
f: b0 01 mov $0x1,%al
11: 5b pop %rbx
12: 5e pop %rsi
13: 5d pop %rbp
14: 31 d2 xor %edx,%edx
To reproduce:
# build kernel
cd linux
cp config-6.3.0-rc5-00613-gc31fe5eb2ec6 .config
make HOSTCC=gcc-11 CC=gcc-11 ARCH=i386 olddefconfig prepare modules_prepare bzImage modules
make HOSTCC=gcc-11 CC=gcc-11 ARCH=i386 INSTALL_MOD_PATH=<mod-install-dir> modules_install
cd <mod-install-dir>
find lib/ | cpio -o -H newc --quiet | gzip > modules.cgz
git clone https://github.com/intel/lkp-tests.git
cd lkp-tests
bin/lkp qemu -k <bzImage> -m modules.cgz job-script # job-script is attached in this email
# if come across any failure that blocks the test,
# please remove ~/.lkp and /lkp dir to run from a clean state.
--
0-DAY CI Kernel Test Service
https://github.com/intel/lkp-tests
On Sat, Apr 15, 2023, at 08:42, kernel test robot wrote:
> Hello,
>
> kernel test robot noticed "kernel_BUG_at_lib/list_debug.c" on:
>
> commit: c31fe5eb2ec68f6d2331fabc924e0030cc6bb2b3 ("[PATCH] mm: make
> arch_has_descending_max_zone_pfns() static")
Thanks for the report, that was a logic error on my end, the fix is:
--- a/mm/mm_init.c
+++ b/mm/mm_init.c
@@ -1756,7 +1756,7 @@ static void __init free_area_init_memoryless_node(int nid)
*/
static bool arch_has_descending_max_zone_pfns(void)
{
- return !IS_ENABLED(CONFIG_ARC_HAS_PAE40);
+ return IS_ENABLED(CONFIG_ARC) && !IS_ENABLED(CONFIG_ARC_HAS_PAE40);
}
/**
I'll send a replacement v2 that has this folded in.
Arnd