From: Konrad Dybcio <konrad.dybcio@linaro.org>
To: Peter Zijlstra <peterz@infradead.org>
Cc: corbet@lwn.net, will@kernel.org, peterz@infradead.org,
boqun.feng@gmail.com, mark.rutland@arm.com,
catalin.marinas@arm.com, dennis@kernel.org, tj@kernel.org,
cl@linux.com, hca@linux.ibm.com, gor@linux.ibm.com,
agordeev@linux.ibm.com, borntraeger@linux.ibm.com,
svens@linux.ibm.com, tglx@linutronix.de, mingo@redhat.com,
bp@alien8.de, dave.hansen@linux.intel.com, x86@kernel.org,
hpa@zytor.com, joro@8bytes.org, suravee.suthikulpanit@amd.com,
robin.murphy@arm.com, dwmw2@infradead.org,
baolu.lu@linux.intel.com, Arnd Bergmann <arnd@arndb.de>,
Herbert Xu <herbert@gondor.apana.org.au>,
davem@davemloft.net, penberg@kernel.org, rientjes@google.com,
iamjoonsoo.kim@lge.com, Andrew Morton <akpm@linux-foundation.org>,
vbabka@suse.cz, roman.gushchin@linux.dev, 42.hyeyoo@gmail.com,
linux-doc@vger.kernel.org, linux-kernel@vger.kernel.org,
linux-mm@kvack.org, linux-s390@vger.kernel.org,
iommu@lists.linux.dev, linux-arch@vger.kernel.org,
linux-crypto@vger.kernel.org, sfr@canb.auug.org.au,
mpe@ellerman.id.au, James.Bottomley@hansenpartnership.com,
deller@gmx.de, linux-parisc@vger.kernel.org,
Nathan Chancellor <nathan@kernel.org>,
llvm@lists.linux.dev
Subject: Re: [PATCH v2 5/12] percpu: Add {raw,this}_cpu_try_cmpxchg()
Date: Fri, 9 Jun 2023 18:10:38 +0200 [thread overview]
Message-ID: <f320f021-88c4-c5c9-0781-c82d0b88f67d@linaro.org> (raw)
In-Reply-To: <20230531132323.587480729@infradead.org>
On 31.05.2023 15:08, Peter Zijlstra wrote:
> Add the try_cmpxchg() form to the per-cpu ops.
>
> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
> ---
+CC Nathan, llvm list
Hi all, this patch seems to break booting on Qualcomm ARM64 platforms
when compiled with clang (GCC works fine) for some reason..:
next-20230605 - works
next-20230606 - doesn't
grev -m 1 dc4e51fd9846 on next-20230606 - works again
b4 shazam <this_msgid> -P 1-4 - still works
b4 shazam <this_msgid> -P 5 - breaks
Confirmed on at least Qualcomm QCM2290, SM8250.
Checking the serial console, it hits a BUG_ON:
[ 0.000000] ------------[ cut here ]------------
[ 0.000000] kernel BUG at mm/vmalloc.c:1638!
[ 0.000000] Internal error: Oops - BUG: 00000000f2000800 [#1] SMP
[ 0.000000] Modules linked in:
[ 0.000000] CPU: 0 PID: 0 Comm: swapper/0 Not tainted [snip]
[ 0.000000] Hardware name: Qualcomm Technologies, Inc. Robotics RB1 (DT)
[ 0.000000] pstate: 000000c5 (nzcv daIF -PAN -UAO -TCO -DIT -SSBS BTYPE=--)
[ 0.000000] pc : alloc_vmap_area+0xafc/0xb08
[ 0.000000] lr : alloc_vmap_area+0x9e4/0xb08
[ 0.000000] sp : ffffa50137f53c20
[ 0.000000] x29: ffffa50137f53c60 x28: ffffa50137f30c18 x27: 0000000000000000
[ 0.000000] x26: 0000000000007fff x25: ffff800080000000 x24: 000000000000cfff
[ 0.000000] x23: ffffffffffff8000 x22: ffffa50137fef970 x21: fffffbfff0000000
[ 0.000000] x20: ffff022982003208 x19: ffff0229820031f8 x18: ffffa50137f64f70
[ 0.000000] x17: ffffa50137fef980 x16: ffffa501375e6d08 x15: 0000000000000001
[ 0.000000] x14: ffffa5013831e1a0 x13: ffffa50137f30c18 x12: 0000000000402dc2
[ 0.000000] x11: 0000000000000000 x10: ffff022982003018 x9 : ffffa5013831e188
[ 0.000000] x8 : ffffcb55ff003228 x7 : 0000000000000000 x6 : 0000000000000048
[ 0.000000] x5 : 0000000000000000 x4 : ffffa50137f53bd0 x3 : ffffa50136490000
[ 0.000000] x2 : 0000000000000001 x1 : ffffa5013831e190 x0 : ffff022982003208
[ 0.000000] Call trace:
[ 0.000000] alloc_vmap_area+0xafc/0xb08
[ 0.000000] __get_vm_area_node+0x108/0x1e8
[ 0.000000] __vmalloc_node_range+0x1fc/0x728
[ 0.000000] __vmalloc_node+0x5c/0x70
[ 0.000000] init_IRQ+0x90/0x11c
[ 0.000000] start_kernel+0x1ac/0x3bc
[ 0.000000] __primary_switched+0xc4/0xcc
[ 0.000000] Code: f000e300 91062000 943bd9ba 17ffff8f (d4210000)
[ 0.000000] ---[ end trace 0000000000000000 ]---
[ 0.000000] Kernel panic - not syncing: Attempted to kill the idle task!
Compiled with clang 15.0.7 from Arch repos, with
make ARCH=arm64 LLVM=1
Konrad
> include/asm-generic/percpu.h | 113 +++++++++++++++++++++++++++++++++++++++++--
> include/linux/percpu-defs.h | 19 +++++++
> 2 files changed, 128 insertions(+), 4 deletions(-)
>
> --- a/include/asm-generic/percpu.h
> +++ b/include/asm-generic/percpu.h
> @@ -89,16 +89,37 @@ do { \
> __ret; \
> })
>
> -#define raw_cpu_generic_cmpxchg(pcp, oval, nval) \
> +#define __cpu_fallback_try_cmpxchg(pcp, ovalp, nval, _cmpxchg) \
> +({ \
> + typeof(pcp) __val, __old = *(ovalp); \
> + __val = _cmpxchg(pcp, __old, nval); \
> + if (__val != __old) \
> + *(ovalp) = __val; \
> + __val == __old; \
> +})
> +
> +#define raw_cpu_generic_try_cmpxchg(pcp, ovalp, nval) \
> ({ \
> typeof(pcp) *__p = raw_cpu_ptr(&(pcp)); \
> - typeof(pcp) __ret; \
> - __ret = *__p; \
> - if (__ret == (oval)) \
> + typeof(pcp) __val = *__p, __old = *(ovalp); \
> + bool __ret; \
> + if (__val == __old) { \
> *__p = nval; \
> + __ret = true; \
> + } else { \
> + *(ovalp) = __val; \
> + __ret = false; \
> + } \
> __ret; \
> })
>
> +#define raw_cpu_generic_cmpxchg(pcp, oval, nval) \
> +({ \
> + typeof(pcp) __old = (oval); \
> + raw_cpu_generic_try_cmpxchg(pcp, &__old, nval); \
> + __old; \
> +})
> +
> #define raw_cpu_generic_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2) \
> ({ \
> typeof(pcp1) *__p1 = raw_cpu_ptr(&(pcp1)); \
> @@ -170,6 +191,16 @@ do { \
> __ret; \
> })
>
> +#define this_cpu_generic_try_cmpxchg(pcp, ovalp, nval) \
> +({ \
> + bool __ret; \
> + unsigned long __flags; \
> + raw_local_irq_save(__flags); \
> + __ret = raw_cpu_generic_try_cmpxchg(pcp, ovalp, nval); \
> + raw_local_irq_restore(__flags); \
> + __ret; \
> +})
> +
> #define this_cpu_generic_cmpxchg(pcp, oval, nval) \
> ({ \
> typeof(pcp) __ret; \
> @@ -282,6 +313,43 @@ do { \
> #define raw_cpu_xchg_8(pcp, nval) raw_cpu_generic_xchg(pcp, nval)
> #endif
>
> +#ifndef raw_cpu_try_cmpxchg_1
> +#ifdef raw_cpu_cmpxchg_1
> +#define raw_cpu_try_cmpxchg_1(pcp, ovalp, nval) \
> + __cpu_fallback_try_cmpxchg(pcp, ovalp, nval, raw_cpu_cmpxchg_1)
> +#else
> +#define raw_cpu_try_cmpxchg_1(pcp, ovalp, nval) \
> + raw_cpu_generic_try_cmpxchg(pcp, ovalp, nval)
> +#endif
> +#endif
> +#ifndef raw_cpu_try_cmpxchg_2
> +#ifdef raw_cpu_cmpxchg_2
> +#define raw_cpu_try_cmpxchg_2(pcp, ovalp, nval) \
> + __cpu_fallback_try_cmpxchg(pcp, ovalp, nval, raw_cpu_cmpxchg_2)
> +#else
> +#define raw_cpu_try_cmpxchg_2(pcp, ovalp, nval) \
> + raw_cpu_generic_try_cmpxchg(pcp, ovalp, nval)
> +#endif
> +#endif
> +#ifndef raw_cpu_try_cmpxchg_4
> +#ifdef raw_cpu_cmpxchg_4
> +#define raw_cpu_try_cmpxchg_4(pcp, ovalp, nval) \
> + __cpu_fallback_try_cmpxchg(pcp, ovalp, nval, raw_cpu_cmpxchg_4)
> +#else
> +#define raw_cpu_try_cmpxchg_4(pcp, ovalp, nval) \
> + raw_cpu_generic_try_cmpxchg(pcp, ovalp, nval)
> +#endif
> +#endif
> +#ifndef raw_cpu_try_cmpxchg_8
> +#ifdef raw_cpu_cmpxchg_8
> +#define raw_cpu_try_cmpxchg_8(pcp, ovalp, nval) \
> + __cpu_fallback_try_cmpxchg(pcp, ovalp, nval, raw_cpu_cmpxchg_8)
> +#else
> +#define raw_cpu_try_cmpxchg_8(pcp, ovalp, nval) \
> + raw_cpu_generic_try_cmpxchg(pcp, ovalp, nval)
> +#endif
> +#endif
> +
> #ifndef raw_cpu_cmpxchg_1
> #define raw_cpu_cmpxchg_1(pcp, oval, nval) \
> raw_cpu_generic_cmpxchg(pcp, oval, nval)
> @@ -407,6 +475,43 @@ do { \
> #define this_cpu_xchg_8(pcp, nval) this_cpu_generic_xchg(pcp, nval)
> #endif
>
> +#ifndef this_cpu_try_cmpxchg_1
> +#ifdef this_cpu_cmpxchg_1
> +#define this_cpu_try_cmpxchg_1(pcp, ovalp, nval) \
> + __cpu_fallback_try_cmpxchg(pcp, ovalp, nval, this_cpu_cmpxchg_1)
> +#else
> +#define this_cpu_try_cmpxchg_1(pcp, ovalp, nval) \
> + this_cpu_generic_try_cmpxchg(pcp, ovalp, nval)
> +#endif
> +#endif
> +#ifndef this_cpu_try_cmpxchg_2
> +#ifdef this_cpu_cmpxchg_2
> +#define this_cpu_try_cmpxchg_2(pcp, ovalp, nval) \
> + __cpu_fallback_try_cmpxchg(pcp, ovalp, nval, this_cpu_cmpxchg_2)
> +#else
> +#define this_cpu_try_cmpxchg_2(pcp, ovalp, nval) \
> + this_cpu_generic_try_cmpxchg(pcp, ovalp, nval)
> +#endif
> +#endif
> +#ifndef this_cpu_try_cmpxchg_4
> +#ifdef this_cpu_cmpxchg_4
> +#define this_cpu_try_cmpxchg_4(pcp, ovalp, nval) \
> + __cpu_fallback_try_cmpxchg(pcp, ovalp, nval, this_cpu_cmpxchg_4)
> +#else
> +#define this_cpu_try_cmpxchg_4(pcp, ovalp, nval) \
> + this_cpu_generic_try_cmpxchg(pcp, ovalp, nval)
> +#endif
> +#endif
> +#ifndef this_cpu_try_cmpxchg_8
> +#ifdef this_cpu_cmpxchg_8
> +#define this_cpu_try_cmpxchg_8(pcp, ovalp, nval) \
> + __cpu_fallback_try_cmpxchg(pcp, ovalp, nval, this_cpu_cmpxchg_8)
> +#else
> +#define this_cpu_try_cmpxchg_8(pcp, ovalp, nval) \
> + this_cpu_generic_try_cmpxchg(pcp, ovalp, nval)
> +#endif
> +#endif
> +
> #ifndef this_cpu_cmpxchg_1
> #define this_cpu_cmpxchg_1(pcp, oval, nval) \
> this_cpu_generic_cmpxchg(pcp, oval, nval)
> --- a/include/linux/percpu-defs.h
> +++ b/include/linux/percpu-defs.h
> @@ -343,6 +343,21 @@ static __always_inline void __this_cpu_p
> pscr2_ret__; \
> })
>
> +#define __pcpu_size_call_return2bool(stem, variable, ...) \
> +({ \
> + bool pscr2_ret__; \
> + __verify_pcpu_ptr(&(variable)); \
> + switch(sizeof(variable)) { \
> + case 1: pscr2_ret__ = stem##1(variable, __VA_ARGS__); break; \
> + case 2: pscr2_ret__ = stem##2(variable, __VA_ARGS__); break; \
> + case 4: pscr2_ret__ = stem##4(variable, __VA_ARGS__); break; \
> + case 8: pscr2_ret__ = stem##8(variable, __VA_ARGS__); break; \
> + default: \
> + __bad_size_call_parameter(); break; \
> + } \
> + pscr2_ret__; \
> +})
> +
> /*
> * Special handling for cmpxchg_double. cmpxchg_double is passed two
> * percpu variables. The first has to be aligned to a double word
> @@ -426,6 +441,8 @@ do { \
> #define raw_cpu_xchg(pcp, nval) __pcpu_size_call_return2(raw_cpu_xchg_, pcp, nval)
> #define raw_cpu_cmpxchg(pcp, oval, nval) \
> __pcpu_size_call_return2(raw_cpu_cmpxchg_, pcp, oval, nval)
> +#define raw_cpu_try_cmpxchg(pcp, ovalp, nval) \
> + __pcpu_size_call_return2bool(raw_cpu_try_cmpxchg_, pcp, ovalp, nval)
> #define raw_cpu_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2) \
> __pcpu_double_call_return_bool(raw_cpu_cmpxchg_double_, pcp1, pcp2, oval1, oval2, nval1, nval2)
>
> @@ -513,6 +530,8 @@ do { \
> #define this_cpu_xchg(pcp, nval) __pcpu_size_call_return2(this_cpu_xchg_, pcp, nval)
> #define this_cpu_cmpxchg(pcp, oval, nval) \
> __pcpu_size_call_return2(this_cpu_cmpxchg_, pcp, oval, nval)
> +#define this_cpu_try_cmpxchg(pcp, ovalp, nval) \
> + __pcpu_size_call_return2bool(this_cpu_try_cmpxchg_, pcp, ovalp, nval)
> #define this_cpu_cmpxchg_double(pcp1, pcp2, oval1, oval2, nval1, nval2) \
> __pcpu_double_call_return_bool(this_cpu_cmpxchg_double_, pcp1, pcp2, oval1, oval2, nval1, nval2)
>
next prev parent reply other threads:[~2023-06-09 16:10 UTC|newest]
Thread overview: 34+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-05-31 13:08 [PATCH 00/12] Introduce cmpxchg128() -- aka. the demise of cmpxchg_double() Peter Zijlstra
2023-05-31 13:08 ` [PATCH 01/12] cyrpto/b128ops: Remove struct u128 Peter Zijlstra
2023-05-31 13:08 ` [PATCH 02/12] types: Introduce [us]128 Peter Zijlstra
2023-05-31 13:08 ` [PATCH 03/12] arch: Introduce arch_{,try_}_cmpxchg128{,_local}() Peter Zijlstra
2023-05-31 13:08 ` [PATCH 04/12] instrumentation: Wire up cmpxchg128() Peter Zijlstra
2023-05-31 13:08 ` [PATCH 05/12] percpu: Add {raw,this}_cpu_try_cmpxchg() Peter Zijlstra
2023-06-09 16:10 ` Konrad Dybcio [this message]
2023-06-09 16:13 ` [PATCH v2 5/12] " Nathan Chancellor
2023-06-09 16:20 ` Konrad Dybcio
2023-05-31 13:08 ` [PATCH 06/12] percpu: Wire up cmpxchg128 Peter Zijlstra
2023-05-31 13:08 ` [PATCH 07/12] percpu: #ifndef __SIZEOF_INT128__ Peter Zijlstra
2023-05-31 14:21 ` Arnd Bergmann
2023-05-31 15:50 ` Peter Zijlstra
2023-06-01 10:14 ` [PATCH v2 07/12] parisc/percpu: Work around the lack of __SIZEOF_INT128__ Peter Zijlstra
2023-06-01 10:32 ` Helge Deller
2023-06-01 10:50 ` Peter Zijlstra
2023-06-01 21:08 ` Sam James
2023-06-01 13:29 ` Linus Torvalds
2023-06-01 17:38 ` Masahiro Yamada
2023-06-02 14:39 ` Peter Zijlstra
2023-06-02 14:50 ` Mark Rutland
2023-06-02 16:09 ` Linus Torvalds
2023-06-02 17:00 ` H. Peter Anvin
2023-06-02 19:10 ` Peter Zijlstra
2023-06-02 19:20 ` H. Peter Anvin
2023-06-02 19:40 ` Peter Zijlstra
2023-06-02 19:57 ` Linus Torvalds
2023-06-02 20:42 ` Helge Deller
2023-05-31 13:08 ` [PATCH 08/12] x86,amd_iommu: Replace cmpxchg_double() Peter Zijlstra
2023-05-31 13:08 ` [PATCH 09/12] x86,intel_iommu: " Peter Zijlstra
2023-05-31 13:08 ` [PATCH 10/12] slub: " Peter Zijlstra
2023-05-31 13:08 ` [PATCH 11/12] arch: Remove cmpxchg_double Peter Zijlstra
2023-05-31 13:08 ` [PATCH 12/12] s390/cpum_sf: Convert to cmpxchg128() Peter Zijlstra
2023-05-31 14:47 ` [PATCH 00/12] Introduce cmpxchg128() -- aka. the demise of cmpxchg_double() Mark Rutland
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=f320f021-88c4-c5c9-0781-c82d0b88f67d@linaro.org \
--to=konrad.dybcio@linaro.org \
--cc=42.hyeyoo@gmail.com \
--cc=James.Bottomley@hansenpartnership.com \
--cc=agordeev@linux.ibm.com \
--cc=akpm@linux-foundation.org \
--cc=arnd@arndb.de \
--cc=baolu.lu@linux.intel.com \
--cc=boqun.feng@gmail.com \
--cc=borntraeger@linux.ibm.com \
--cc=bp@alien8.de \
--cc=catalin.marinas@arm.com \
--cc=cl@linux.com \
--cc=corbet@lwn.net \
--cc=dave.hansen@linux.intel.com \
--cc=davem@davemloft.net \
--cc=deller@gmx.de \
--cc=dennis@kernel.org \
--cc=dwmw2@infradead.org \
--cc=gor@linux.ibm.com \
--cc=hca@linux.ibm.com \
--cc=herbert@gondor.apana.org.au \
--cc=hpa@zytor.com \
--cc=iamjoonsoo.kim@lge.com \
--cc=iommu@lists.linux.dev \
--cc=joro@8bytes.org \
--cc=linux-arch@vger.kernel.org \
--cc=linux-crypto@vger.kernel.org \
--cc=linux-doc@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=linux-parisc@vger.kernel.org \
--cc=linux-s390@vger.kernel.org \
--cc=llvm@lists.linux.dev \
--cc=mark.rutland@arm.com \
--cc=mingo@redhat.com \
--cc=mpe@ellerman.id.au \
--cc=nathan@kernel.org \
--cc=penberg@kernel.org \
--cc=peterz@infradead.org \
--cc=rientjes@google.com \
--cc=robin.murphy@arm.com \
--cc=roman.gushchin@linux.dev \
--cc=sfr@canb.auug.org.au \
--cc=suravee.suthikulpanit@amd.com \
--cc=svens@linux.ibm.com \
--cc=tglx@linutronix.de \
--cc=tj@kernel.org \
--cc=vbabka@suse.cz \
--cc=will@kernel.org \
--cc=x86@kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).