Re: [PATCH 3.16 00/76] 3.16.56-rc1 review
On Mon, 2018-03-12 at 09:45 -0700, Guenter Roeck wrote: > On Mon, Mar 12, 2018 at 08:00:53AM -0700, Guenter Roeck wrote: > > On Mon, Mar 12, 2018 at 03:06:11AM +, Ben Hutchings wrote: > > > This is the start of the stable review cycle for the 3.16.56 release. > > > There are 76 patches in this series, which will be posted as responses > > > to this one. If anyone has any issues with these being applied, please > > > let me know. > > > > > > Responses should be made by Wed Mar 14 12:00:00 UTC 2018. > > > Anything received after that time might be too late. > > > > > > > Build results: > > total: 136 pass: 136 fail:0 > > Qemu test results: > > total: 115 pass: 112 fail:3 > > Failed tests: > > mipsel:24Kf:malta_defconfig:smp:rootfs > > mipsel64:malta_defconfig:nosmp:rootfs > > mipsel64:malta_defconfig:smp:rootfs > > > > The failures are due to newly added tests; the init process crashes. > > v3.16 passes those tests, so the problem was introduced later. > > I'll run a bisect later to see if I can find the culprit. If not, > > I'll drop the new tests from this kernel version. > > > > Turns out I did the bisect kalready. Attached. It does suggest that there > may be a real problem. Maciej W. Rozycki worked out that it depends on commit 27e28e8ec47a ("MIPS: Normalise code flow in the CpU exception handler") which I mistakenly omitted. I'll include that in the next update (3.16.57). Ben. -- Ben Hutchings Time is nature's way of making sure that everything doesn't happen at once. signature.asc Description: This is a digitally signed message part
Re: [PATCH 3.16 00/76] 3.16.56-rc1 review
On Mon, Mar 12, 2018 at 08:00:53AM -0700, Guenter Roeck wrote: > On Mon, Mar 12, 2018 at 03:06:11AM +, Ben Hutchings wrote: > > This is the start of the stable review cycle for the 3.16.56 release. > > There are 76 patches in this series, which will be posted as responses > > to this one. If anyone has any issues with these being applied, please > > let me know. > > > > Responses should be made by Wed Mar 14 12:00:00 UTC 2018. > > Anything received after that time might be too late. > > > > Build results: > total: 136 pass: 136 fail:0 > Qemu test results: > total: 115 pass: 112 fail:3 > Failed tests: > mipsel:24Kf:malta_defconfig:smp:rootfs > mipsel64:malta_defconfig:nosmp:rootfs > mipsel64:malta_defconfig:smp:rootfs > > The failures are due to newly added tests; the init process crashes. > v3.16 passes those tests, so the problem was introduced later. > I'll run a bisect later to see if I can find the culprit. If not, > I'll drop the new tests from this kernel version. > Turns out I did the bisect kalready. Attached. It does suggest that there may be a real problem. Guenter --- # bad: [3e50cd97ed730bb0abfcdbc8c1a18871c2750c33] Linux 3.16.55 # good: [19583ca584d6f574384e17fe7613dfaeadcdc4a6] Linux 3.16 git bisect start 'HEAD' 'v3.16' # good: [d1afef76e102be87955151c93bd51fd04c1c0c01] arm64: mm: ensure that the zero page is visible to the page table walker git bisect good d1afef76e102be87955151c93bd51fd04c1c0c01 # good: [b6927bd60d353de044584ab9400aaccd8694fe1e] can: Fix kernel panic at security_sock_rcv_skb git bisect good b6927bd60d353de044584ab9400aaccd8694fe1e # good: [aa9a2ec0e82b64db1851d96ab1e9c83f8ea17a39] ARM: kexec: Make .text R/W in machine_kexec git bisect good aa9a2ec0e82b64db1851d96ab1e9c83f8ea17a39 # good: [bf5ac638a0ffa923ed03ba8cdb8241b812f5fe4f] can: gs_usb: fix busy loop if no more TX context is available git bisect good bf5ac638a0ffa923ed03ba8cdb8241b812f5fe4f # good: [957a3d249cb16292a199f73b7138d23ee44ca433] Revert "x86: kvmclock: Disable use from vDSO if KPTI is enabled" git bisect good 957a3d249cb16292a199f73b7138d23ee44ca433 # bad: [66fe40226beb16fb7809d275aec362f479388935] USB: serial: option: adding support for YUGA CLM920-NC5 git bisect bad 66fe40226beb16fb7809d275aec362f479388935 # good: [0b6433856a149885470f2ab3a138e99347c323a4] arm64: fpsimd: Prevent registers leaking from dead tasks git bisect good 0b6433856a149885470f2ab3a138e99347c323a4 # good: [d6e7dd39a7f036eb3e48032d68d9e70f2e9781cf] MIPS: Clear [MSA]FPE CSR.Cause after notify_die() git bisect good d6e7dd39a7f036eb3e48032d68d9e70f2e9781cf # bad: [d97c5dd698a37a6f4fcce8132853620f7390f797] MIPS: Fix an FCSR access API regression with NT_PRFPREG and MSA git bisect bad d97c5dd698a37a6f4fcce8132853620f7390f797 # bad: [b18b5d55c0e8b2bccda919f5f227ec3ba1056f2a] MIPS: Fix a preemption issue with thread's FPU defaults git bisect bad b18b5d55c0e8b2bccda919f5f227ec3ba1056f2a # good: [0efd2f915bbc608f66065c36b291d37efe0a0b0f] MIPS: Always clear FCSR cause bits after emulation git bisect good 0efd2f915bbc608f66065c36b291d37efe0a0b0f # bad: [3127c502272aca5f46b04c0b11afb464ad4fcbaf] MIPS: math-emu: Define IEEE 754-2008 feature control bits git bisect bad 3127c502272aca5f46b04c0b11afb464ad4fcbaf # bad: [8605aa2fea28c0485aeb60c114a9d52df1455915] MIPS: Set `si_code' for SIGFPE signals sent from emulation too git bisect bad 8605aa2fea28c0485aeb60c114a9d52df1455915 # first bad commit: [8605aa2fea28c0485aeb60c114a9d52df1455915] MIPS: Set `si_code' for SIGFPE signals sent from emulation too
Re: [PATCH 3.16 00/76] 3.16.56-rc1 review
On Mon, Mar 12, 2018 at 03:06:11AM +, Ben Hutchings wrote: > This is the start of the stable review cycle for the 3.16.56 release. > There are 76 patches in this series, which will be posted as responses > to this one. If anyone has any issues with these being applied, please > let me know. > > Responses should be made by Wed Mar 14 12:00:00 UTC 2018. > Anything received after that time might be too late. > Build results: total: 136 pass: 136 fail:0 Qemu test results: total: 115 pass: 112 fail:3 Failed tests: mipsel:24Kf:malta_defconfig:smp:rootfs mipsel64:malta_defconfig:nosmp:rootfs mipsel64:malta_defconfig:smp:rootfs The failures are due to newly added tests; the init process crashes. v3.16 passes those tests, so the problem was introduced later. I'll run a bisect later to see if I can find the culprit. If not, I'll drop the new tests from this kernel version. Guenter
[PATCH 3.16 00/76] 3.16.56-rc1 review
This is the start of the stable review cycle for the 3.16.56 release. There are 76 patches in this series, which will be posted as responses to this one. If anyone has any issues with these being applied, please let me know. Responses should be made by Wed Mar 14 12:00:00 UTC 2018. Anything received after that time might be too late. All the patches have also been committed to the linux-3.16.y-rc branch of https://git.kernel.org/pub/scm/linux/kernel/git/bwh/linux-stable-rc.git . A shortlog and diffstat can be found below. Ben. - Andi Kleen (3): module/retpoline: Warn about missing retpoline in module [caf7501a1b4ec964190f31f9c3f163de252273b8] x86/retpoline/irq32: Convert assembler indirect jumps [7614e913db1f40fff819b36216484dc3808995d4] x86/retpoline: Optimize inline assembler for vmexit_fill_RSB [3f7d875566d8e79c5e0b2c9a413e91b2c29e0854] Andrey Ryabinin (1): x86/asm: Use register variable to get stack pointer value [196bd485ee4f03ce4c690bfcf38138abfcd0a4bc] Andy Lutomirski (3): x86/asm: Make asm/alternative.h safe from assembly [f005f5d860e0231fe212cfda8c1a3148b99609f4] x86/cpu: Factor out application of forced CPU caps [8bf1ebca215c262e48c15a4a15f175991776f57f] x86: Clean up current_stack_pointer [83653c16da91112236292871b820cb8b367220e3] Arnd Bergmann (1): x86: fix build warnign with 32-bit PAE [not upstream; specific to KAISER] Ben Hutchings (1): x86/syscall: Sanitize syscall table de-references under speculation [2fbd7af5af8665d18bcefae3e9700be07e22b681] Borislav Petkov (6): x86/alternatives: Fix ALTERNATIVE_2 padding generation properly [dbe4058a6a44af4ca5d146aebe01b0a1f9b7fd2a] x86/alternatives: Fix optimize_nops() checking [612e8e9350fd19cae6900cf36ea0c6892d1a0dca] x86/alternatives: Guard NOPs optimization [69df353ff305805fc16082d0c5bfa6e20fa8b863] x86/bugs: Drop one "mitigation" from dmesg [55fa19d3e51f33d9cd4056d25836d93abf9438db] x86/cpu: Merge bugs.c and bugs_64.c [62a67e123e058a67db58bc6a14354dd037bafd0a] x86/nospec: Fix header guards names [7a32fc51ca938e67974cbb9db31e1a43f98345a9] Colin Ian King (1): x86/spectre: Fix spelling mistake: "vunerable"-> "vulnerable" [e698dcdfcda41efd0984de539767b4cddd235f1e] Dan Carpenter (1): x86/spectre: Fix an error message [9de29eac8d2189424d81c0d840cd0469aa3d41c8] Dan Williams (13): array_index_nospec: Sanitize speculative array de-references [f3804203306e098dae9ca51540fcd5eb700d7f40] nl80211: Sanitize array index in parse_txq_params [259d8c1e984318497c84eef547bbb6b1d9f4eb05] nospec: Include dependency [eb6174f6d1be16b19cfa43dac296bfed003ce1a6] nospec: Kill array_index_nospec_mask_check() [1d91c1d2c80cb70e2e553845e278b87a960c04da] vfs, fdtable: Prevent bounds-check bypass via speculative execution [56c30ba7b348b90484969054d561f711ba196507] x86/get_user: Use pointer masking to limit speculation [c7f631cb07e7da06ac1d231ca178452339e32a94] x86/kvm: Update spectre-v1 mitigation [085331dfc6bbe3501fb936e657331ca943827600] x86/spectre: Report get_user mitigation for spectre_v1 [edfbae53dab8348fca778531be9f4855d2ca0360] x86/uaccess: Use __uaccess_begin_nospec() and uaccess_try_nospec [304ec1b050310548db33063e567123fae8fd0301] x86/usercopy: Replace open coded stac/clac with __uaccess_{begin, end} [b5c4ae4f35325d520b230bab6eb3310613b72ac1] x86: Implement array_index_mask_nospec [babdde2698d482b6c0de1eab4f697cf5856c5859] x86: Introduce __uaccess_begin_nospec() and uaccess_try_nospec [b3bbfb3fb5d25776b8e3f361d2eedaabb0b496cd] x86: Introduce barrier_nospec [b3d7ad85b80bbc404635dca80f5b129f6242bc7a] Darren Kenny (1): x86/speculation: Fix typo IBRS_ATT, which should be IBRS_ALL [af189c95a371b59f493dbe0f50c0a09724868881] Dave Hansen (2): x86/Documentation: Add PTI description [01c9b17bf673b05bb401b76ec763e9730ccf1376] x86/cpu/intel: Introduce macros for Intel family numbers [970442c599b22ccd644ebfe94d1d303bf6f87c05] David Woodhouse (14): sysfs/cpu: Fix typos in vulnerability documentation [9ecccfaa7cb5249bd31bdceb93fcf5bedb8a24d8] x86/cpufeatures: Add X86_BUG_SPECTRE_V[12] [99c6fa2511d8a683e61468be91b83f85452115fa] x86/cpufeatures: Clean up Spectre v2 related CPUID flags [2961298efe1ea1b6fc0d7ee8b76018fa6c0bcef2] x86/retpoline/checksum32: Convert assembler indirect jumps [5096732f6f695001fa2d6f1335a2680b37912c69] x86/retpoline/crypto: Convert crypto assembler indirect jumps [9697fa39efd3fc3692f2949d4045f393ec58450b] x86/retpoline/entry: Convert entry assembler indirect jumps