This is the start of the stable review cycle for the 5.15.136 release. There are 102 patches in this series, all will be posted as a response to this one. If anyone has any issues with these being applied, please let me know.
Responses should be made by Wed, 18 Oct 2023 08:39:38 +0000. Anything received after that time might be too late.
The whole patch series can be found in one patch at: https://www.kernel.org/pub/linux/kernel/v5.x/stable-review/patch-5.15.136-rc... or in the git tree and branch at: git://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable-rc.git linux-5.15.y and the diffstat can be found below.
thanks,
greg k-h
------------- Pseudo-Shortlog of commits:
Greg Kroah-Hartman gregkh@linuxfoundation.org Linux 5.15.136-rc1
Jakub Kicinski kuba@kernel.org eth: remove remaining copies of the NAPI_POLL_WEIGHT define
Ricardo Cañuelo ricardo.canuelo@collabora.com usb: hub: Guard against accesses to uninitialized BOS descriptors
Greg Kroah-Hartman gregkh@linuxfoundation.org Revert "kernel/sched: Modify initial boot task idle setup"
Ren Zhijie renzhijie2@huawei.com arm64: armv8_deprecated: fix unused-function error
Mark Rutland mark.rutland@arm.com arm64: armv8_deprecated: rework deprected instruction handling
Mark Rutland mark.rutland@arm.com arm64: armv8_deprecated: move aarch32 helper earlier
Mark Rutland mark.rutland@arm.com arm64: armv8_deprecated move emulation functions
Mark Rutland mark.rutland@arm.com arm64: armv8_deprecated: fold ops into insn_emulation
Mark Rutland mark.rutland@arm.com arm64: rework EL0 MRS emulation
Mark Rutland mark.rutland@arm.com arm64: factor insn read out of call_undef_hook()
Mark Rutland mark.rutland@arm.com arm64: factor out EL1 SSBS emulation hook
Mark Rutland mark.rutland@arm.com arm64: split EL0/EL1 UNDEF handlers
Mark Rutland mark.rutland@arm.com arm64: allow kprobes on EL0 handlers
Mark Rutland mark.rutland@arm.com arm64: rework BTI exception handling
Mark Rutland mark.rutland@arm.com arm64: rework FPAC exception handling
Mark Rutland mark.rutland@arm.com arm64: consistently pass ESR_ELx to die()
Mark Rutland mark.rutland@arm.com arm64: die(): pass 'err' as long
Mark Rutland mark.rutland@arm.com arm64: report EL1 UNDEFs better
Christophe Leroy christophe.leroy@csgroup.eu powerpc/64e: Fix wrong test in __ptep_test_and_clear_young()
Christophe Leroy christophe.leroy@csgroup.eu powerpc/8xx: Fix pte_access_permitted() for PAGE_NONE
Duoming Zhou duoming@zju.edu.cn dmaengine: mediatek: Fix deadlock caused by synchronize_irq()
Rex Zhang rex.zhang@intel.com dmaengine: idxd: use spin_lock_irqsave before wait_event_lock_irq
Kirill A. Shutemov kirill.shutemov@linux.intel.com x86/alternatives: Disable KASAN in apply_alternatives()
Pawel Laszczak pawell@cadence.com usb: cdnsp: Fixes issue with dequeuing not queued requests
Krishna Kurapati quic_kriskura@quicinc.com usb: gadget: ncm: Handle decoding of multiple NTB's in unwrap call
Piyush Mehta piyush.mehta@amd.com usb: gadget: udc-xilinx: replace memcpy with memcpy_toio
Dharma Balasubiramani dharma.b@microchip.com counter: microchip-tcb-capture: Fix the use of internal GCLK logic
Dmitry Torokhov dmitry.torokhov@gmail.com pinctrl: avoid unsafe code pattern in find_pinctrl()
Michal Koutný mkoutny@suse.com cgroup: Remove duplicates in cgroup v1 tasks file
Rijo Thomas Rijo-john.Thomas@amd.com tee: amdtee: fix use-after-free vulnerability in amdtee_close_session
Hans de Goede hdegoede@redhat.com Input: goodix - ensure int GPIO is in input for gpio_count == 1 && gpio_int_idx == 0 case
Szilard Fabian szfabian@bluemarch.art Input: i8042 - add Fujitsu Lifebook E5411 to i8042 quirk table
Matthias Berndt matthias_berndt@gmx.de Input: xpad - add PXN V900 support
Jeffery Miller jefferymiller@google.com Input: psmouse - fix fast_reconnect function for PS/2 mode
Javier Carrasco javier.carrasco.cruz@gmail.com Input: powermate - fix use-after-free in powermate_config_complete
Dan Carpenter dan.carpenter@linaro.org ceph: fix type promotion bug on 32bit systems
Xiubo Li xiubli@redhat.com ceph: fix incorrect revoked caps assert in ceph_fill_file_size()
Jordan Rife jrife@google.com libceph: use kernel_connect()
Mika Westerberg mika.westerberg@linux.intel.com thunderbolt: Check that lane 1 is in CL0 before enabling lane bonding
Mika Westerberg mika.westerberg@linux.intel.com thunderbolt: Workaround an IOMMU fault on certain systems with Intel Maple Ridge
Jorge Sanjuan Garcia jorge.sanjuangarcia@duagon.com mcb: remove is_added flag from mcb_device struct
Borislav Petkov (AMD) bp@alien8.de x86/cpu: Fix AMD erratum #1485 on Zen4-based CPUs
Hans de Goede hdegoede@redhat.com ACPI: resource: Skip IRQ override on ASUS ExpertBook B1402CBA
Daniel Miess daniel.miess@amd.com drm/amd/display: Don't set dpms_off for seamless boot
Christian König christian.koenig@amd.com drm/amdgpu: add missing NULL check
Alexander Zangerl az@breathe-safe.com iio: pressure: ms5611: ms5611_prom_is_valid false negative bug
Lakshmi Yadlapati lakshmiy@us.ibm.com iio: pressure: dps310: Adjust Timeout Settings
Phil Elwell phil@raspberrypi.com iio: pressure: bmp280: Fix NULL pointer exception
Xingxing Luo xingxing.luo@unisoc.com usb: musb: Modify the "HWVers" register address
Xingxing Luo xingxing.luo@unisoc.com usb: musb: Get the musb_qh poniter after musb_giveback
Xiaolei Wang xiaolei.wang@windriver.com usb: cdns3: Modify the return value of cdns_set_active () to void when CONFIG_PM_SLEEP is disabled
Thinh Nguyen Thinh.Nguyen@synopsys.com usb: dwc3: Soft reset phy on probe for host
Javier Carrasco javier.carrasco.cruz@gmail.com net: usb: dm9601: fix uninitialized variable use in dm9601_mdio_read
Wesley Cheng quic_wcheng@quicinc.com usb: xhci: xhci-ring: Use sysdev for mapping bounce buffer
Hongyu Xie xy521521@gmail.com xhci: Keep interrupt disabled in initialization until host is running.
Amelie Delaunay amelie.delaunay@foss.st.com dmaengine: stm32-mdma: abort resume if no ongoing transfer
Zheng Wang zyytlz.wz@163.com media: mtk-jpeg: Fix use after free bug due to uncanceled work
Patrick Rohr prohr@google.com net: release reference to inet6_dev pointer
Patrick Rohr prohr@google.com net: change accept_ra_min_rtr_lft to affect all RA lifetimes
Patrick Rohr prohr@google.com net: add sysctl accept_ra_min_rtr_lft
Adrian Hunter adrian.hunter@intel.com perf inject: Fix GEN_ELF_TEXT_OFFSET for jit
Waiman Long longman@redhat.com workqueue: Override implicit ordered attribute in workqueue_apply_unbound_cpumask()
Jeremy Cline jeremy@jcline.org nfc: nci: assert requested protocol is valid
Ralph Siemsen ralph.siemsen@linaro.org pinctrl: renesas: rzn1: Enable missing PINMUX
Nils Hoppmann niho@linux.ibm.com net/smc: Fix pos miscalculation in statistics
Kory Maincent kory.maincent@bootlin.com ethtool: Fix mod state of verbose no_mask bitset
Eric Dumazet edumazet@google.com net: nfc: fix races in nfc_llcp_sock_get() and nfc_llcp_sock_get_sn()
Will Mortensen will@extrahop.com net/mlx5e: Again mutually exclude RX-FCS and RX-port-timestamp
Dan Carpenter dan.carpenter@linaro.org ixgbe: fix crash with empty VF macvlan list
Radu Pirea (NXP OSS) radu-nicolae.pirea@oss.nxp.com net: phy: mscc: macsec: reject PN update requests
Radu Pirea (NXP OSS) radu-nicolae.pirea@oss.nxp.com net: macsec: indicate next pn update when offloading
David Vernet void@manifault.com bpf: Fix verifier log for async callback return values
Konstantin Meskhidze konstantin.meskhidze@huawei.com drm/vmwgfx: fix typo of sizeof argument
Björn Töpel bjorn@rivosinc.com riscv, bpf: Sign-extend return values
Pu Lehui pulehui@huawei.com riscv, bpf: Factor out emit_call for kernel and bpf context
Roger Pau Monne roger.pau@citrix.com xen-netback: use default TX queue size for vifs
Jakub Kicinski kuba@kernel.org eth: remove copies of the NAPI_POLL_WEIGHT define
Dan Carpenter dan.carpenter@linaro.org mlxsw: fix mlxsw_sp2_nve_vxlan_learning_set() return type
Dinghao Liu dinghao.liu@zju.edu.cn ieee802154: ca8210: Fix a potential UAF in ca8210_probe
Yoshihiro Shimoda yoshihiro.shimoda.uh@renesas.com ravb: Fix use-after-free issue in ravb_tx_timeout_work()
Yoshihiro Shimoda yoshihiro.shimoda.uh@renesas.com ravb: Fix up dma_free_coherent() call in ravb_remove()
Abhinav Kumar quic_abhinavk@quicinc.com drm/msm/dpu: change _dpu_plane_calc_bw() to use u64 to avoid overflow
Dan Carpenter dan.carpenter@linaro.org drm/msm/dsi: fix irq_of_parse_and_map() error checking
Abhinav Kumar quic_abhinavk@quicinc.com drm/msm/dsi: skip the wait for video mode done if not applicable
Kuogee Hsieh quic_khsieh@quicinc.com drm/msm/dp: do not reinitialize phy unless retry during link training
Sumit Garg sumit.garg@linaro.org KEYS: trusted: Remove redundant static calls usage
Ahmad Fatoum a.fatoum@pengutronix.de KEYS: trusted: allow use of kernel RNG for key material
WhaleChang whalechang@google.com ALSA: usb-audio: Fix microphone sound on Opencomm2 Headset
Jordan Rife jrife@google.com net: prevent address rewrite in kernel_bind()
Jan Kara jack@suse.cz quota: Fix slow quotaoff
Hans de Goede hdegoede@redhat.com HID: logitech-hidpp: Fix kernel crash on receiver USB disconnect
Greg Kroah-Hartman gregkh@linuxfoundation.org lib/test_meminit: fix off-by-one error in test_pages()
Uwe Kleine-König u.kleine-koenig@pengutronix.de platform/x86: hp-wmi:: Mark driver struct with __refdata to prevent section mismatch warning
Armin Wolf W_Armin@gmx.de platform/x86: think-lmi: Fix reference leak
Geert Uytterhoeven geert+renesas@glider.be of: overlay: Reorder struct fragment fields kerneldoc
Jing Zhang renyu.zj@linux.alibaba.com perf/arm-cmn: Fix the unhandled overflow status of counter 4 to 7
Artem Chernyshev artem.chernyshev@red-soft.ru RDMA/cxgb4: Check skb value for failure to allocate
Bart Van Assche bvanassche@acm.org RDMA/srp: Do not call scsi_done() from srp_abort()
Bart Van Assche bvanassche@acm.org scsi: ib_srp: Call scsi_done() directly
Bart Van Assche bvanassche@acm.org scsi: core: Rename scsi_mq_done() into scsi_done() and export it
Bart Van Assche bvanassche@acm.org scsi: core: Use a structure member to track the SCSI command submitter
Zhang Rui rui.zhang@intel.com iommu/vt-d: Avoid memory allocation in iommu_suspend()
-------------
Diffstat:
Documentation/admin-guide/kernel-parameters.txt | 10 + Documentation/networking/ip-sysctl.rst | 8 + Documentation/security/keys/trusted-encrypted.rst | 20 +- Makefile | 4 +- arch/arm64/include/asm/cpufeature.h | 3 +- arch/arm64/include/asm/exception.h | 13 +- arch/arm64/include/asm/spectre.h | 2 + arch/arm64/include/asm/system_misc.h | 2 +- arch/arm64/include/asm/traps.h | 19 +- arch/arm64/kernel/armv8_deprecated.c | 572 ++++++++++----------- arch/arm64/kernel/cpufeature.c | 23 +- arch/arm64/kernel/entry-common.c | 36 +- arch/arm64/kernel/proton-pack.c | 26 +- arch/arm64/kernel/traps.c | 125 ++--- arch/powerpc/include/asm/nohash/32/pte-8xx.h | 7 + arch/powerpc/include/asm/nohash/64/pgtable.h | 2 +- arch/powerpc/include/asm/nohash/pgtable.h | 2 + arch/riscv/net/bpf_jit_comp64.c | 33 +- arch/x86/include/asm/msr-index.h | 9 +- arch/x86/kernel/alternative.c | 13 + arch/x86/kernel/cpu/amd.c | 8 + drivers/acpi/resource.c | 7 + drivers/counter/microchip-tcb-capture.c | 2 +- drivers/dma/idxd/device.c | 5 +- drivers/dma/mediatek/mtk-uart-apdma.c | 3 +- drivers/dma/stm32-mdma.c | 4 + drivers/gpu/drm/amd/amdgpu/amdgpu_object.h | 2 +- drivers/gpu/drm/amd/display/dc/core/dc.c | 3 + drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c | 12 +- drivers/gpu/drm/msm/dp/dp_ctrl.c | 13 +- drivers/gpu/drm/msm/dsi/dsi_host.c | 19 +- drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c | 2 +- drivers/hid/hid-logitech-hidpp.c | 3 +- drivers/iio/pressure/bmp280-core.c | 2 +- drivers/iio/pressure/dps310.c | 8 +- drivers/iio/pressure/ms5611_core.c | 2 +- drivers/infiniband/hw/cxgb4/cm.c | 3 + drivers/infiniband/ulp/srp/ib_srp.c | 22 +- drivers/input/joystick/xpad.c | 2 + drivers/input/misc/powermate.c | 1 + drivers/input/mouse/elantech.c | 1 + drivers/input/mouse/synaptics.c | 1 + drivers/input/serio/i8042-acpipnpio.h | 8 + drivers/input/touchscreen/goodix.c | 19 + drivers/iommu/intel/iommu.c | 16 - drivers/mcb/mcb-core.c | 10 +- drivers/mcb/mcb-parse.c | 2 - drivers/media/platform/mtk-jpeg/mtk_jpeg_core.c | 1 + drivers/net/ethernet/amazon/ena/ena_netdev.c | 4 +- drivers/net/ethernet/brocade/bna/bnad.c | 3 +- drivers/net/ethernet/cortina/gemini.c | 4 +- drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c | 5 +- drivers/net/ethernet/marvell/skge.c | 3 +- drivers/net/ethernet/marvell/sky2.c | 3 +- drivers/net/ethernet/mediatek/mtk_star_emac.c | 3 +- drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 3 +- .../ethernet/mellanox/mlxsw/spectrum_nve_vxlan.c | 4 +- drivers/net/ethernet/nvidia/forcedeth.c | 6 +- drivers/net/ethernet/renesas/ravb_main.c | 6 +- drivers/net/ethernet/ti/davinci_emac.c | 3 +- drivers/net/ethernet/ti/netcp_core.c | 5 +- drivers/net/ieee802154/ca8210.c | 17 +- drivers/net/macsec.c | 2 + drivers/net/phy/mscc/mscc_macsec.c | 6 + drivers/net/usb/dm9601.c | 7 +- drivers/net/xen-netback/interface.c | 7 +- drivers/of/overlay.c | 2 +- drivers/perf/arm-cmn.c | 2 +- drivers/pinctrl/core.c | 16 +- drivers/pinctrl/renesas/Kconfig | 1 + drivers/platform/x86/hp/hp-wmi.c | 8 +- drivers/platform/x86/think-lmi.c | 24 +- drivers/scsi/scsi_error.c | 17 +- drivers/scsi/scsi_lib.c | 15 +- drivers/scsi/scsi_priv.h | 1 + drivers/tee/amdtee/core.c | 10 +- drivers/thunderbolt/icm.c | 40 +- drivers/thunderbolt/switch.c | 7 + drivers/usb/cdns3/cdnsp-gadget.c | 3 + drivers/usb/cdns3/core.h | 3 +- drivers/usb/core/hub.c | 25 +- drivers/usb/core/hub.h | 2 +- drivers/usb/dwc3/core.c | 39 +- drivers/usb/gadget/function/f_ncm.c | 26 +- drivers/usb/gadget/udc/udc-xilinx.c | 20 +- drivers/usb/host/xhci-ring.c | 4 +- drivers/usb/host/xhci.c | 35 +- drivers/usb/musb/musb_debugfs.c | 2 +- drivers/usb/musb/musb_host.c | 9 +- fs/ceph/file.c | 2 +- fs/ceph/inode.c | 4 +- fs/quota/dquot.c | 66 ++- include/keys/trusted-type.h | 2 +- include/linux/intel-iommu.h | 2 +- include/linux/ipv6.h | 1 + include/linux/mcb.h | 1 - include/linux/quota.h | 4 +- include/linux/quotaops.h | 2 +- include/net/macsec.h | 1 + include/scsi/scsi_cmnd.h | 9 + include/uapi/linux/ipv6.h | 3 + kernel/bpf/verifier.c | 6 +- kernel/cgroup/cgroup-v1.c | 5 +- kernel/sched/core.c | 2 +- kernel/sched/idle.c | 1 - kernel/workqueue.c | 8 +- lib/test_meminit.c | 2 +- net/ceph/messenger.c | 4 +- net/ethtool/bitset.c | 32 +- net/ipv6/addrconf.c | 13 + net/ipv6/ndisc.c | 13 +- net/netfilter/ipvs/ip_vs_sync.c | 4 +- net/nfc/llcp_core.c | 30 +- net/nfc/nci/core.c | 5 + net/rds/tcp_connect.c | 2 +- net/rds/tcp_listen.c | 2 +- net/smc/smc_stats.h | 14 +- net/socket.c | 6 +- security/keys/trusted-keys/trusted_core.c | 48 +- sound/usb/quirks.c | 6 +- tools/perf/util/genelf.h | 4 +- 121 files changed, 1054 insertions(+), 762 deletions(-)
On 23/10/16 10:39AM, Greg Kroah-Hartman wrote:
This is the start of the stable review cycle for the 5.15.136 release. There are 102 patches in this series, all will be posted as a response to this one. If anyone has any issues with these being applied, please let me know.
Responses should be made by Wed, 18 Oct 2023 08:39:38 +0000. Anything received after that time might be too late.
My system runs fine, with some minor warnings:
08:42:25 rbmarliere@debian ~ $ dmesg | head -1 [ 0.000000] Linux version 5.15.136-rc1+ (rbmarliere@debian) (Debian clang version 16.0.6 (15), GNU ld (GNU Binutils for Debian) 2.41) #1 SMP Mon Oct 16 07:33:42 -03 2023 08:42:27 rbmarliere@debian ~ $ dmesg -lerr [ 3.907484] nouveau 0000:09:00.0: DRM: core notifier timeout [ 6.457694] nouveau 0000:09:00.0: DRM: core notifier timeout [ 14.533137] nouveau 0000:09:00.0: DRM: core notifier timeout [ 17.870791] nouveau 0000:09:00.0: DRM: core notifier timeout 08:42:32 rbmarliere@debian ~ $ grep warning /mnt/md0/linux/5.15.y/err.log arch/x86/kernel/smp.o: warning: objtool: sysvec_reboot()+0x43: unreachable instruction net/ipv6/seg6_local.o: warning: objtool: seg6_local_fill_encap() falls through to next function seg6_local_get_encap_size() net/ipv6/seg6_local.o: warning: objtool: seg6_local_cmp_encap() falls through to next function input_action_end()
Tested-by: Ricardo B. Marliere ricardo@marliere.net
Thanks!
On Mon, 16 Oct 2023 10:39:59 +0200, Greg Kroah-Hartman wrote:
This is the start of the stable review cycle for the 5.15.136 release. There are 102 patches in this series, all will be posted as a response to this one. If anyone has any issues with these being applied, please let me know.
Responses should be made by Wed, 18 Oct 2023 08:39:38 +0000. Anything received after that time might be too late.
The whole patch series can be found in one patch at: https://www.kernel.org/pub/linux/kernel/v5.x/stable-review/patch-5.15.136-rc... or in the git tree and branch at: git://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable-rc.git linux-5.15.y and the diffstat can be found below.
thanks,
greg k-h
All tests passing for Tegra ...
Test results for stable-v5.15: 10 builds: 10 pass, 0 fail 26 boots: 26 pass, 0 fail 102 tests: 102 pass, 0 fail
Linux version: 5.15.136-rc1-gf11fc66f963f Boards tested: tegra124-jetson-tk1, tegra186-p2771-0000, tegra194-p2972-0000, tegra194-p3509-0000+p3668-0000, tegra20-ventana, tegra210-p2371-2180, tegra210-p3450-0000, tegra30-cardhu-a04
Tested-by: Jon Hunter jonathanh@nvidia.com
Jon
Hi Greg,
On 16/10/23 2:09 pm, Greg Kroah-Hartman wrote:
This is the start of the stable review cycle for the 5.15.136 release. There are 102 patches in this series, all will be posted as a response to this one. If anyone has any issues with these being applied, please let me know.
Responses should be made by Wed, 18 Oct 2023 08:39:38 +0000. Anything received after that time might be too late.
I am seeing a build failure while compiling tools/perf/
In file included from tests/genelf.c:14: tests/../util/genelf.h:5:10: fatal error: linux/math.h: No such file or directory 5 | #include <linux/math.h> | ^~~~~~~~~~~~~~ compilation terminated.
Patch 43 in this series is causing this.
Why is this not reproducible upstream ?
Vegard bisected the commit which makes it not reproducible upstream and this commit is missing in 5.15.y: Commit: d6e6a27d960f ("tools: Fix math.h breakage")
Backport request for this was made here: https://lore.kernel.org/all/CAMVNhxS-6qNfxy8jHrY5EtZASTL9gAvZi=BdTkUA5_5CSQ2...
Thanks, Harshit
The whole patch series can be found in one patch at: https://www.kernel.org/pub/linux/kernel/v5.x/stable-review/patch-5.15.136-rc... or in the git tree and branch at: git://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable-rc.git linux-5.15.y and the diffstat can be found below.
thanks,
greg k-h
Pseudo-Shortlog of commits:
Adrian Hunter adrian.hunter@intel.com perf inject: Fix GEN_ELF_TEXT_OFFSET for jit
On Mon, Oct 16, 2023 at 07:06:20PM +0530, Harshit Mogalapalli wrote:
Hi Greg,
On 16/10/23 2:09 pm, Greg Kroah-Hartman wrote:
This is the start of the stable review cycle for the 5.15.136 release. There are 102 patches in this series, all will be posted as a response to this one. If anyone has any issues with these being applied, please let me know.
Responses should be made by Wed, 18 Oct 2023 08:39:38 +0000. Anything received after that time might be too late.
I am seeing a build failure while compiling tools/perf/
In file included from tests/genelf.c:14: tests/../util/genelf.h:5:10: fatal error: linux/math.h: No such file or directory 5 | #include <linux/math.h> | ^~~~~~~~~~~~~~ compilation terminated.
Patch 43 in this series is causing this.
What is patch 43?
Why is this not reproducible upstream ?
Vegard bisected the commit which makes it not reproducible upstream and this commit is missing in 5.15.y: Commit: d6e6a27d960f ("tools: Fix math.h breakage")
Backport request for this was made here: https://lore.kernel.org/all/CAMVNhxS-6qNfxy8jHrY5EtZASTL9gAvZi=BdTkUA5_5CSQ2...
And that commit is in this patch series, so are you sure that was correct?
thanks,
greg k-h
Hi Greg,
On 16/10/23 8:44 pm, Greg Kroah-Hartman wrote:
On Mon, Oct 16, 2023 at 07:06:20PM +0530, Harshit Mogalapalli wrote:
Hi Greg,
On 16/10/23 2:09 pm, Greg Kroah-Hartman wrote:
This is the start of the stable review cycle for the 5.15.136 release. There are 102 patches in this series, all will be posted as a response to this one. If anyone has any issues with these being applied, please let me know.
Responses should be made by Wed, 18 Oct 2023 08:39:38 +0000. Anything received after that time might be too late.
I am seeing a build failure while compiling tools/perf/
In file included from tests/genelf.c:14: tests/../util/genelf.h:5:10: fatal error: linux/math.h: No such file or directory 5 | #include <linux/math.h> | ^~~~~~~~~~~~~~ compilation terminated.
Patch 43 in this series is causing this.
Sorry for the confusion.
What is patch 43?
It is patch 42/102 in this series
https://lore.kernel.org/stable/2023101641-resource-scalding-3e1d@gregkh/T/#m...
Commit: e2bf685d7e311 ("perf inject: Fix GEN_ELF_TEXT_OFFSET for jit")
Why is this not reproducible upstream ?
Vegard bisected the commit which makes it not reproducible upstream and this commit is missing in 5.15.y: Commit: d6e6a27d960f ("tools: Fix math.h breakage")
Backport request for this was made here: https://lore.kernel.org/all/CAMVNhxS-6qNfxy8jHrY5EtZASTL9gAvZi=BdTkUA5_5CSQ2...
And that commit is in this patch series, so are you sure that was correct?
Cause for this build issue: Commit: e2bf685d7e311 ("perf inject: Fix GEN_ELF_TEXT_OFFSET for jit")
And this issue is not in upstream due to presence of commit d6e6a27d960f ("tools: Fix math.h breakage") in upstream but not in 5.15.y
Thanks, Harshit
thanks,
greg k-h
On Mon, Oct 16, 2023 at 09:23:36PM +0530, Harshit Mogalapalli wrote:
Hi Greg,
On 16/10/23 8:44 pm, Greg Kroah-Hartman wrote:
On Mon, Oct 16, 2023 at 07:06:20PM +0530, Harshit Mogalapalli wrote:
Hi Greg,
On 16/10/23 2:09 pm, Greg Kroah-Hartman wrote:
This is the start of the stable review cycle for the 5.15.136 release. There are 102 patches in this series, all will be posted as a response to this one. If anyone has any issues with these being applied, please let me know.
Responses should be made by Wed, 18 Oct 2023 08:39:38 +0000. Anything received after that time might be too late.
I am seeing a build failure while compiling tools/perf/
In file included from tests/genelf.c:14: tests/../util/genelf.h:5:10: fatal error: linux/math.h: No such file or directory 5 | #include <linux/math.h> | ^~~~~~~~~~~~~~ compilation terminated.
Patch 43 in this series is causing this.
Sorry for the confusion.
What is patch 43?
It is patch 42/102 in this series
https://lore.kernel.org/stable/2023101641-resource-scalding-3e1d@gregkh/T/#m...
Commit: e2bf685d7e311 ("perf inject: Fix GEN_ELF_TEXT_OFFSET for jit")
Why is this not reproducible upstream ?
Vegard bisected the commit which makes it not reproducible upstream and this commit is missing in 5.15.y: Commit: d6e6a27d960f ("tools: Fix math.h breakage")
Backport request for this was made here: https://lore.kernel.org/all/CAMVNhxS-6qNfxy8jHrY5EtZASTL9gAvZi=BdTkUA5_5CSQ2...
And that commit is in this patch series, so are you sure that was correct?
Cause for this build issue: Commit: e2bf685d7e311 ("perf inject: Fix GEN_ELF_TEXT_OFFSET for jit")
And this issue is not in upstream due to presence of commit d6e6a27d960f ("tools: Fix math.h breakage") in upstream but not in 5.15.y
Ok, I'll go drop the patch entirely, I can't even get perf to build at all for me on 5.15, which is why I've given up on it even mattering anymore :(
thanks,
greg k-h
On 16/10/2023 18:58, Greg Kroah-Hartman wrote:
On Mon, Oct 16, 2023 at 09:23:36PM +0530, Harshit Mogalapalli wrote:
Cause for this build issue: Commit: e2bf685d7e311 ("perf inject: Fix GEN_ELF_TEXT_OFFSET for jit")
And this issue is not in upstream due to presence of commit d6e6a27d960f ("tools: Fix math.h breakage") in upstream but not in 5.15.y
Ok, I'll go drop the patch entirely, I can't even get perf to build at all for me on 5.15, which is why I've given up on it even mattering anymore :(
Just for maximal clarity, there are several commits involved here:
1. babd04386b1d perf jit: Include program header in ELF files
This commit is already in 5.15.y but introduced a bug...
2. 89b15d00527b perf inject: Fix GEN_ELF_TEXT_OFFSET for jit
This commit is in this -rc1 and fixes the bug above, but introduces a new perf build failure on 5.15.y. [This is the one I think you've now dropped.]
3. d6e6a27d960f tools: Fix math.h breakage
This is a prerequisite for #2 and is not in 5.15.y. However, it has some conflicts on 5.15.y, i.e. it probably has some prerequisites of its own that I haven't looked into.
I guess the question is -- if we're dropping #2, should we drop #1 as well? Or... instead of dropping either of them we could also apply a minimal fix:
diff --git a/tools/perf/util/genelf.h b/tools/perf/util/genelf.h index 159c69bcc33e..6e202db6c4d9 100644 --- a/tools/perf/util/genelf.h +++ b/tools/perf/util/genelf.h @@ -2,7 +2,7 @@ #ifndef __GENELF_H__ #define __GENELF_H__
-#include <linux/math.h> +#include <linux/kernel.h>
/* genelf.c */ int jit_write_elf(int fd, uint64_t code_addr, const char *sym,
However, this is not what mainline does so technically it runs afoul of the stable rules (although arguably I think we could also just make this change to #2 and call it a backport).
Out of curiosity, Greg: what is your build error with perf? Given that it builds for us (and we actually package perf so we need it) it sounds like maybe you're missing a package in your environment or something? If you pass us your config + the output of
make -C tools/perf/
I'd be happy to look into it. Only if you want though :-)
Vegard
On Tue, Oct 17, 2023 at 10:58:22AM +0200, Vegard Nossum wrote:
On 16/10/2023 18:58, Greg Kroah-Hartman wrote:
On Mon, Oct 16, 2023 at 09:23:36PM +0530, Harshit Mogalapalli wrote:
Cause for this build issue: Commit: e2bf685d7e311 ("perf inject: Fix GEN_ELF_TEXT_OFFSET for jit")
And this issue is not in upstream due to presence of commit d6e6a27d960f ("tools: Fix math.h breakage") in upstream but not in 5.15.y
Ok, I'll go drop the patch entirely, I can't even get perf to build at all for me on 5.15, which is why I've given up on it even mattering anymore :(
Just for maximal clarity, there are several commits involved here:
- babd04386b1d perf jit: Include program header in ELF files
This commit is already in 5.15.y but introduced a bug...
- 89b15d00527b perf inject: Fix GEN_ELF_TEXT_OFFSET for jit
This commit is in this -rc1 and fixes the bug above, but introduces a new perf build failure on 5.15.y. [This is the one I think you've now dropped.]
- d6e6a27d960f tools: Fix math.h breakage
This is a prerequisite for #2 and is not in 5.15.y. However, it has some conflicts on 5.15.y, i.e. it probably has some prerequisites of its own that I haven't looked into.
I guess the question is -- if we're dropping #2, should we drop #1 as well? Or... instead of dropping either of them we could also apply a minimal fix:
I can't "drop" #1, as it's already merged.
So how about sending a set of patches that you feel should be applied to get this building for you? As again, it doesn't work at all for me.
Out of curiosity, Greg: what is your build error with perf? Given that it builds for us (and we actually package perf so we need it) it sounds like maybe you're missing a package in your environment or something? If you pass us your config + the output of
make -C tools/perf/
I'd be happy to look into it. Only if you want though :-)
Sure! Here's the output, good luck!
$ make -C tools/perf make: Entering directory '/home/gregkh/linux/stable/linux-5.15.y/tools/perf' BUILD: Doing 'make -j20' parallel build Warning: Kernel ABI header at 'tools/include/uapi/linux/const.h' differs from latest version at 'include/uapi/linux/const.h' diff -u tools/include/uapi/linux/const.h include/uapi/linux/const.h Warning: Kernel ABI header at 'tools/include/uapi/linux/in.h' differs from latest version at 'include/uapi/linux/in.h' diff -u tools/include/uapi/linux/in.h include/uapi/linux/in.h Warning: Kernel ABI header at 'tools/arch/x86/include/asm/disabled-features.h' differs from latest version at 'arch/x86/include/asm/disabled-features.h' diff -u tools/arch/x86/include/asm/disabled-features.h arch/x86/include/asm/disabled-features.h Warning: Kernel ABI header at 'tools/arch/x86/include/asm/required-features.h' differs from latest version at 'arch/x86/include/asm/required-features.h' diff -u tools/arch/x86/include/asm/required-features.h arch/x86/include/asm/required-features.h Warning: Kernel ABI header at 'tools/arch/x86/include/asm/cpufeatures.h' differs from latest version at 'arch/x86/include/asm/cpufeatures.h' diff -u tools/arch/x86/include/asm/cpufeatures.h arch/x86/include/asm/cpufeatures.h Warning: Kernel ABI header at 'tools/arch/x86/include/asm/msr-index.h' differs from latest version at 'arch/x86/include/asm/msr-index.h' diff -u tools/arch/x86/include/asm/msr-index.h arch/x86/include/asm/msr-index.h Warning: Kernel ABI header at 'tools/arch/arm64/include/uapi/asm/kvm.h' differs from latest version at 'arch/arm64/include/uapi/asm/kvm.h' diff -u tools/arch/arm64/include/uapi/asm/kvm.h arch/arm64/include/uapi/asm/kvm.h Makefile.config:1036: No libbabeltrace found, disables 'perf data' CTF format support, please install libbabeltrace-dev[el]/libbabeltrace-ctf-dev Makefile.config:1062: No alternatives command found, you need to set JDIR= to point to the root of your Java directory tests/bpf.c: In function ‘epoll_pwait_loop’: tests/bpf.c:36:17: error: argument 2 null where non-null expected [-Werror=nonnull] 36 | epoll_pwait(-(i + 1), NULL, 0, 0, NULL); | ^~~~~~~~~~~ In file included from tests/bpf.c:5: /usr/include/sys/epoll.h:134:12: note: in a call to function ‘epoll_pwait’ declared ‘nonnull’ 134 | extern int epoll_pwait (int __epfd, struct epoll_event *__events, | ^~~~~~~~~~~ CC util/jitdump.o CC util/genelf.o CC util/genelf_debug.o cc1: all warnings being treated as errors make[4]: *** [/home/gregkh/linux/stable/linux-5.15.y/tools/build/Makefile.build:96: tests/bpf.o] Error 1 make[3]: *** [/home/gregkh/linux/stable/linux-5.15.y/tools/build/Makefile.build:139: tests] Error 2 make[3]: *** Waiting for unfinished jobs.... In file included from /usr/lib/perl5/5.38/core_perl/CORE/perl.h:7811, from Context.xs:8: /usr/lib/perl5/5.38/core_perl/CORE/inline.h: In function ‘S_PerlEnv_putenv’: /usr/lib/perl5/5.38/core_perl/CORE/inline.h:295:5: error: ISO C90 forbids mixed declarations and code [-Werror=declaration-after-statement] 295 | bool retval = putenv(str); | ^~~~ In file included from /usr/lib/perl5/5.38/core_perl/CORE/perl.h:3327: /usr/lib/perl5/5.38/core_perl/CORE/inline.h: In function ‘Perl_is_utf8_valid_partial_char_flags’: /usr/lib/perl5/5.38/core_perl/CORE/handy.h:155:23: error: cast from function call of type ‘STRLEN’ {aka ‘long unsigned int’} to non-matching type ‘_Bool’ [-Werror=bad-function-cast] 155 | #define cBOOL(cbool) ((bool) (cbool)) | ^ /usr/lib/perl5/5.38/core_perl/CORE/inline.h:2334:12: note: in expansion of macro ‘cBOOL’ 2334 | return cBOOL(is_utf8_char_helper_(s0, e, flags)); | ^~~~~ /usr/lib/perl5/5.38/core_perl/CORE/inline.h: In function ‘Perl_newPADxVOP’: /usr/lib/perl5/5.38/core_perl/CORE/inline.h:3135:5: error: ISO C90 forbids mixed declarations and code [-Werror=declaration-after-statement] 3135 | OP *o = newOP(type, flags); | ^~ /usr/lib/perl5/5.38/core_perl/CORE/inline.h: In function ‘Perl_cop_file_avn’: /usr/lib/perl5/5.38/core_perl/CORE/inline.h:3500:5: error: ISO C90 forbids mixed declarations and code [-Werror=declaration-after-statement] 3500 | const char *file = CopFILE(cop); | ^~~~~ In file included from /usr/lib/perl5/5.38/core_perl/CORE/perl.h:7812: /usr/lib/perl5/5.38/core_perl/CORE/sv_inline.h: In function ‘Perl_newSV_type’: /usr/lib/perl5/5.38/core_perl/CORE/sv_inline.h:420:9: error: enumeration value ‘SVt_NULL’ not handled in switch [-Werror=switch-enum] 420 | switch(type) { | ^~~~~~ /usr/lib/perl5/5.38/core_perl/CORE/sv_inline.h:420:9: error: enumeration value ‘SVt_IV’ not handled in switch [-Werror=switch-enum] /usr/lib/perl5/5.38/core_perl/CORE/sv_inline.h:420:9: error: enumeration value ‘SVt_NV’ not handled in switch [-Werror=switch-enum] /usr/lib/perl5/5.38/core_perl/CORE/sv_inline.h:420:9: error: enumeration value ‘SVt_PV’ not handled in switch [-Werror=switch-enum] /usr/lib/perl5/5.38/core_perl/CORE/sv_inline.h:420:9: error: enumeration value ‘SVt_INVLIST’ not handled in switch [-Werror=switch-enum] /usr/lib/perl5/5.38/core_perl/CORE/sv_inline.h:420:9: error: enumeration value ‘SVt_PVIV’ not handled in switch [-Werror=switch-enum] /usr/lib/perl5/5.38/core_perl/CORE/sv_inline.h:420:9: error: enumeration value ‘SVt_PVNV’ not handled in switch [-Werror=switch-enum] /usr/lib/perl5/5.38/core_perl/CORE/sv_inline.h:420:9: error: enumeration value ‘SVt_PVMG’ not handled in switch [-Werror=switch-enum] /usr/lib/perl5/5.38/core_perl/CORE/sv_inline.h:420:9: error: enumeration value ‘SVt_REGEXP’ not handled in switch [-Werror=switch-enum] /usr/lib/perl5/5.38/core_perl/CORE/sv_inline.h:420:9: error: enumeration value ‘SVt_PVGV’ not handled in switch [-Werror=switch-enum] /usr/lib/perl5/5.38/core_perl/CORE/sv_inline.h:420:9: error: enumeration value ‘SVt_PVLV’ not handled in switch [-Werror=switch-enum] /usr/lib/perl5/5.38/core_perl/CORE/sv_inline.h:420:9: error: enumeration value ‘SVt_PVCV’ not handled in switch [-Werror=switch-enum] /usr/lib/perl5/5.38/core_perl/CORE/sv_inline.h:420:9: error: enumeration value ‘SVt_PVFM’ not handled in switch [-Werror=switch-enum] /usr/lib/perl5/5.38/core_perl/CORE/sv_inline.h:420:9: error: enumeration value ‘SVt_PVIO’ not handled in switch [-Werror=switch-enum] /usr/lib/perl5/5.38/core_perl/CORE/sv_inline.h:420:9: error: enumeration value ‘SVt_LAST’ not handled in switch [-Werror=switch-enum] /usr/lib/perl5/5.38/core_perl/CORE/sv_inline.h:383:5: error: enumeration value ‘SVt_LAST’ not handled in switch [-Werror=switch-enum] 383 | switch (type) { | ^~~~~~ /usr/lib/perl5/5.38/core_perl/CORE/sv_inline.h: In function ‘Perl_sv_setpv_freshbuf’: /usr/lib/perl5/5.38/core_perl/CORE/handy.h:155:23: error: cast from function call of type ‘long int’ to non-matching type ‘_Bool’ [-Werror=bad-function-cast] 155 | #define cBOOL(cbool) ((bool) (cbool)) | ^ /usr/lib/perl5/5.38/core_perl/CORE/perl.h:4231:62: note: in definition of macro ‘EXPECT’ 4231 | # define EXPECT(expr,val) __builtin_expect(expr,val) | ^~~~ /usr/lib/perl5/5.38/core_perl/CORE/perl.h:4252:52: note: in expansion of macro ‘cBOOL’ 4252 | #define UNLIKELY(cond) EXPECT(cBOOL(cond),FALSE) | ^~~~~ /usr/lib/perl5/5.38/core_perl/CORE/sv.h:1724:13: note: in expansion of macro ‘UNLIKELY’ 1724 | if (UNLIKELY(TAINT_get)) \ | ^~~~~~~~ /usr/lib/perl5/5.38/core_perl/CORE/perl.h:996:34: note: in expansion of macro ‘cBOOL’ 996 | # define TAINT_get (cBOOL(UNLIKELY(PL_tainted))) /* Is something tainted? */ | ^~~~~ /usr/lib/perl5/5.38/core_perl/CORE/sv.h:1724:22: note: in expansion of macro ‘TAINT_get’ 1724 | if (UNLIKELY(TAINT_get)) \ | ^~~~~~~~~ /usr/lib/perl5/5.38/core_perl/CORE/sv_inline.h:996:5: note: in expansion of macro ‘SvTAINT’ 996 | SvTAINT(sv); | ^~~~~~~ /usr/lib/perl5/5.38/core_perl/CORE/handy.h:155:23: error: cast from function call of type ‘long int’ to non-matching type ‘_Bool’ [-Werror=bad-function-cast] 155 | #define cBOOL(cbool) ((bool) (cbool)) | ^ /usr/lib/perl5/5.38/core_perl/CORE/perl.h:4231:62: note: in definition of macro ‘EXPECT’ 4231 | # define EXPECT(expr,val) __builtin_expect(expr,val) | ^~~~ /usr/lib/perl5/5.38/core_perl/CORE/perl.h:4252:52: note: in expansion of macro ‘cBOOL’ 4252 | #define UNLIKELY(cond) EXPECT(cBOOL(cond),FALSE) | ^~~~~ /usr/lib/perl5/5.38/core_perl/CORE/sv.h:1718:42: note: in expansion of macro ‘UNLIKELY’ 1718 | #define SvTAINTED_on(sv) STMT_START{ if(UNLIKELY(TAINTING_get)){sv_taint(sv);} }STMT_END | ^~~~~~~~ /usr/lib/perl5/5.38/core_perl/CORE/perl.h:997:34: note: in expansion of macro ‘cBOOL’ 997 | # define TAINTING_get (cBOOL(UNLIKELY(PL_tainting))) | ^~~~~ /usr/lib/perl5/5.38/core_perl/CORE/sv.h:1718:51: note: in expansion of macro ‘TAINTING_get’ 1718 | #define SvTAINTED_on(sv) STMT_START{ if(UNLIKELY(TAINTING_get)){sv_taint(sv);} }STMT_END | ^~~~~~~~~~~~ /usr/lib/perl5/5.38/core_perl/CORE/sv.h:1725:13: note: in expansion of macro ‘SvTAINTED_on’ 1725 | SvTAINTED_on(sv); \ | ^~~~~~~~~~~~ /usr/lib/perl5/5.38/core_perl/CORE/sv_inline.h:996:5: note: in expansion of macro ‘SvTAINT’ 996 | SvTAINT(sv); | ^~~~~~~ Context.c: In function ‘XS_Perf__Trace__Context_common_pc’: /usr/lib/perl5/5.38/core_perl/CORE/perl.h:2494:33: error: cast from function call of type ‘IV’ {aka ‘long int’} to non-matching type ‘struct scripting_context *’ [-Werror=bad-function-cast] 2494 | # define INT2PTR(any,d) (any)(d) | ^ Context.c:55:39: note: in expansion of macro ‘INT2PTR’ /usr/lib/perl5/5.38/core_perl/CORE/handy.h:155:23: error: cast from function call of type ‘long int’ to non-matching type ‘_Bool’ [-Werror=bad-function-cast] 155 | #define cBOOL(cbool) ((bool) (cbool)) | ^ /usr/lib/perl5/5.38/core_perl/CORE/perl.h:4231:62: note: in definition of macro ‘EXPECT’ 4231 | # define EXPECT(expr,val) __builtin_expect(expr,val) | ^~~~ /usr/lib/perl5/5.38/core_perl/CORE/perl.h:4251:52: note: in expansion of macro ‘cBOOL’ 4251 | #define LIKELY(cond) EXPECT(cBOOL(cond),TRUE) | ^~~~~ /usr/lib/perl5/5.38/core_perl/CORE/pp.h:429:13: note: in expansion of macro ‘LIKELY’ 429 | if (LIKELY( \ | ^~~~~~ /usr/lib/perl5/5.38/core_perl/CORE/perl.h:996:34: note: in expansion of macro ‘cBOOL’ 996 | # define TAINT_get (cBOOL(UNLIKELY(PL_tainted))) /* Is something tainted? */ | ^~~~~ /usr/lib/perl5/5.38/core_perl/CORE/pp.h:431:28: note: in expansion of macro ‘TAINT_get’ 431 | & (do_taint ? !TAINT_get : 1))) \ | ^~~~~~~~~ /usr/lib/perl5/5.38/core_perl/CORE/pp.h:495:38: note: in expansion of macro ‘TARGi’ 495 | #define PUSHi(i) STMT_START { TARGi(i,1); PUSHs(TARG); } STMT_END | ^~~~~ Context.c:60:13: note: in expansion of macro ‘PUSHi’ Context.c: In function ‘XS_Perf__Trace__Context_common_flags’: /usr/lib/perl5/5.38/core_perl/CORE/perl.h:2494:33: error: cast from function call of type ‘IV’ {aka ‘long int’} to non-matching type ‘struct scripting_context *’ [-Werror=bad-function-cast] 2494 | # define INT2PTR(any,d) (any)(d) | ^ Context.c:78:39: note: in expansion of macro ‘INT2PTR’ /usr/lib/perl5/5.38/core_perl/CORE/handy.h:155:23: error: cast from function call of type ‘long int’ to non-matching type ‘_Bool’ [-Werror=bad-function-cast] 155 | #define cBOOL(cbool) ((bool) (cbool)) | ^ /usr/lib/perl5/5.38/core_perl/CORE/perl.h:4231:62: note: in definition of macro ‘EXPECT’ 4231 | # define EXPECT(expr,val) __builtin_expect(expr,val) | ^~~~ /usr/lib/perl5/5.38/core_perl/CORE/perl.h:4251:52: note: in expansion of macro ‘cBOOL’ 4251 | #define LIKELY(cond) EXPECT(cBOOL(cond),TRUE) | ^~~~~ /usr/lib/perl5/5.38/core_perl/CORE/pp.h:429:13: note: in expansion of macro ‘LIKELY’ 429 | if (LIKELY( \ | ^~~~~~ /usr/lib/perl5/5.38/core_perl/CORE/perl.h:996:34: note: in expansion of macro ‘cBOOL’ 996 | # define TAINT_get (cBOOL(UNLIKELY(PL_tainted))) /* Is something tainted? */ | ^~~~~ /usr/lib/perl5/5.38/core_perl/CORE/pp.h:431:28: note: in expansion of macro ‘TAINT_get’ 431 | & (do_taint ? !TAINT_get : 1))) \ | ^~~~~~~~~ /usr/lib/perl5/5.38/core_perl/CORE/pp.h:495:38: note: in expansion of macro ‘TARGi’ 495 | #define PUSHi(i) STMT_START { TARGi(i,1); PUSHs(TARG); } STMT_END | ^~~~~ Context.c:83:13: note: in expansion of macro ‘PUSHi’ Context.c: In function ‘XS_Perf__Trace__Context_common_lock_depth’: /usr/lib/perl5/5.38/core_perl/CORE/perl.h:2494:33: error: cast from function call of type ‘IV’ {aka ‘long int’} to non-matching type ‘struct scripting_context *’ [-Werror=bad-function-cast] 2494 | # define INT2PTR(any,d) (any)(d) | ^ Context.c:101:39: note: in expansion of macro ‘INT2PTR’ /usr/lib/perl5/5.38/core_perl/CORE/handy.h:155:23: error: cast from function call of type ‘long int’ to non-matching type ‘_Bool’ [-Werror=bad-function-cast] 155 | #define cBOOL(cbool) ((bool) (cbool)) | ^ /usr/lib/perl5/5.38/core_perl/CORE/perl.h:4231:62: note: in definition of macro ‘EXPECT’ 4231 | # define EXPECT(expr,val) __builtin_expect(expr,val) | ^~~~ /usr/lib/perl5/5.38/core_perl/CORE/perl.h:4251:52: note: in expansion of macro ‘cBOOL’ 4251 | #define LIKELY(cond) EXPECT(cBOOL(cond),TRUE) | ^~~~~ /usr/lib/perl5/5.38/core_perl/CORE/pp.h:429:13: note: in expansion of macro ‘LIKELY’ 429 | if (LIKELY( \ | ^~~~~~ /usr/lib/perl5/5.38/core_perl/CORE/perl.h:996:34: note: in expansion of macro ‘cBOOL’ 996 | # define TAINT_get (cBOOL(UNLIKELY(PL_tainted))) /* Is something tainted? */ | ^~~~~ /usr/lib/perl5/5.38/core_perl/CORE/pp.h:431:28: note: in expansion of macro ‘TAINT_get’ 431 | & (do_taint ? !TAINT_get : 1))) \ | ^~~~~~~~~ /usr/lib/perl5/5.38/core_perl/CORE/pp.h:495:38: note: in expansion of macro ‘TARGi’ 495 | #define PUSHi(i) STMT_START { TARGi(i,1); PUSHs(TARG); } STMT_END | ^~~~~ Context.c:106:13: note: in expansion of macro ‘PUSHi’ In file included from /usr/lib/perl5/5.38/core_perl/CORE/perl.h:7811, from util/scripting-engines/trace-event-perl.c:35: /usr/lib/perl5/5.38/core_perl/CORE/inline.h: In function ‘S_PerlEnv_putenv’: /usr/lib/perl5/5.38/core_perl/CORE/inline.h:295:5: error: ISO C90 forbids mixed declarations and code [-Werror=declaration-after-statement] 295 | bool retval = putenv(str); | ^~~~ In file included from /usr/lib/perl5/5.38/core_perl/CORE/perl.h:3327: /usr/lib/perl5/5.38/core_perl/CORE/inline.h: In function ‘Perl_is_utf8_valid_partial_char_flags’: /usr/lib/perl5/5.38/core_perl/CORE/handy.h:155:23: error: cast from function call of type ‘STRLEN’ {aka ‘long unsigned int’} to non-matching type ‘_Bool’ [-Werror=bad-function-cast] 155 | #define cBOOL(cbool) ((bool) (cbool)) | ^ /usr/lib/perl5/5.38/core_perl/CORE/inline.h:2334:12: note: in expansion of macro ‘cBOOL’ 2334 | return cBOOL(is_utf8_char_helper_(s0, e, flags)); | ^~~~~ /usr/lib/perl5/5.38/core_perl/CORE/inline.h: In function ‘Perl_newPADxVOP’: /usr/lib/perl5/5.38/core_perl/CORE/inline.h:3135:5: error: ISO C90 forbids mixed declarations and code [-Werror=declaration-after-statement] 3135 | OP *o = newOP(type, flags); | ^~ /usr/lib/perl5/5.38/core_perl/CORE/inline.h: In function ‘Perl_cop_file_avn’: /usr/lib/perl5/5.38/core_perl/CORE/inline.h:3500:5: error: ISO C90 forbids mixed declarations and code [-Werror=declaration-after-statement] 3500 | const char *file = CopFILE(cop); | ^~~~~ cc1: all warnings being treated as errors In file included from /usr/lib/perl5/5.38/core_perl/CORE/perl.h:7812: /usr/lib/perl5/5.38/core_perl/CORE/sv_inline.h: In function ‘Perl_newSV_type’: /usr/lib/perl5/5.38/core_perl/CORE/sv_inline.h:420:9: error: enumeration value ‘SVt_NULL’ not handled in switch [-Werror=switch-enum] 420 | switch(type) { | ^~~~~~ /usr/lib/perl5/5.38/core_perl/CORE/sv_inline.h:420:9: error: enumeration value ‘SVt_IV’ not handled in switch [-Werror=switch-enum] /usr/lib/perl5/5.38/core_perl/CORE/sv_inline.h:420:9: error: enumeration value ‘SVt_NV’ not handled in switch [-Werror=switch-enum] /usr/lib/perl5/5.38/core_perl/CORE/sv_inline.h:420:9: error: enumeration value ‘SVt_PV’ not handled in switch [-Werror=switch-enum] /usr/lib/perl5/5.38/core_perl/CORE/sv_inline.h:420:9: error: enumeration value ‘SVt_INVLIST’ not handled in switch [-Werror=switch-enum] /usr/lib/perl5/5.38/core_perl/CORE/sv_inline.h:420:9: error: enumeration value ‘SVt_PVIV’ not handled in switch [-Werror=switch-enum] /usr/lib/perl5/5.38/core_perl/CORE/sv_inline.h:420:9: error: enumeration value ‘SVt_PVNV’ not handled in switch [-Werror=switch-enum] /usr/lib/perl5/5.38/core_perl/CORE/sv_inline.h:420:9: error: enumeration value ‘SVt_PVMG’ not handled in switch [-Werror=switch-enum] /usr/lib/perl5/5.38/core_perl/CORE/sv_inline.h:420:9: error: enumeration value ‘SVt_REGEXP’ not handled in switch [-Werror=switch-enum] /usr/lib/perl5/5.38/core_perl/CORE/sv_inline.h:420:9: error: enumeration value ‘SVt_PVGV’ not handled in switch [-Werror=switch-enum] /usr/lib/perl5/5.38/core_perl/CORE/sv_inline.h:420:9: error: enumeration value ‘SVt_PVLV’ not handled in switch [-Werror=switch-enum] /usr/lib/perl5/5.38/core_perl/CORE/sv_inline.h:420:9: error: enumeration value ‘SVt_PVCV’ not handled in switch [-Werror=switch-enum] /usr/lib/perl5/5.38/core_perl/CORE/sv_inline.h:420:9: error: enumeration value ‘SVt_PVFM’ not handled in switch [-Werror=switch-enum] /usr/lib/perl5/5.38/core_perl/CORE/sv_inline.h:420:9: error: enumeration value ‘SVt_PVIO’ not handled in switch [-Werror=switch-enum] /usr/lib/perl5/5.38/core_perl/CORE/sv_inline.h:420:9: error: enumeration value ‘SVt_LAST’ not handled in switch [-Werror=switch-enum] /usr/lib/perl5/5.38/core_perl/CORE/sv_inline.h:383:5: error: enumeration value ‘SVt_LAST’ not handled in switch [-Werror=switch-enum] 383 | switch (type) { | ^~~~~~ /usr/lib/perl5/5.38/core_perl/CORE/sv_inline.h: In function ‘Perl_sv_setpv_freshbuf’: /usr/lib/perl5/5.38/core_perl/CORE/handy.h:155:23: error: cast from function call of type ‘long int’ to non-matching type ‘_Bool’ [-Werror=bad-function-cast] 155 | #define cBOOL(cbool) ((bool) (cbool)) | ^ /usr/lib/perl5/5.38/core_perl/CORE/perl.h:4231:62: note: in definition of macro ‘EXPECT’ 4231 | # define EXPECT(expr,val) __builtin_expect(expr,val) | ^~~~ /usr/lib/perl5/5.38/core_perl/CORE/perl.h:4252:52: note: in expansion of macro ‘cBOOL’ 4252 | #define UNLIKELY(cond) EXPECT(cBOOL(cond),FALSE) | ^~~~~ /usr/lib/perl5/5.38/core_perl/CORE/sv.h:1724:13: note: in expansion of macro ‘UNLIKELY’ 1724 | if (UNLIKELY(TAINT_get)) \ | ^~~~~~~~ /usr/lib/perl5/5.38/core_perl/CORE/perl.h:996:34: note: in expansion of macro ‘cBOOL’ 996 | # define TAINT_get (cBOOL(UNLIKELY(PL_tainted))) /* Is something tainted? */ | ^~~~~ /usr/lib/perl5/5.38/core_perl/CORE/sv.h:1724:22: note: in expansion of macro ‘TAINT_get’ 1724 | if (UNLIKELY(TAINT_get)) \ | ^~~~~~~~~ /usr/lib/perl5/5.38/core_perl/CORE/sv_inline.h:996:5: note: in expansion of macro ‘SvTAINT’ 996 | SvTAINT(sv); | ^~~~~~~ /usr/lib/perl5/5.38/core_perl/CORE/handy.h:155:23: error: cast from function call of type ‘long int’ to non-matching type ‘_Bool’ [-Werror=bad-function-cast] 155 | #define cBOOL(cbool) ((bool) (cbool)) | ^ /usr/lib/perl5/5.38/core_perl/CORE/perl.h:4231:62: note: in definition of macro ‘EXPECT’ 4231 | # define EXPECT(expr,val) __builtin_expect(expr,val) | ^~~~ /usr/lib/perl5/5.38/core_perl/CORE/perl.h:4252:52: note: in expansion of macro ‘cBOOL’ 4252 | #define UNLIKELY(cond) EXPECT(cBOOL(cond),FALSE) | ^~~~~ /usr/lib/perl5/5.38/core_perl/CORE/sv.h:1718:42: note: in expansion of macro ‘UNLIKELY’ 1718 | #define SvTAINTED_on(sv) STMT_START{ if(UNLIKELY(TAINTING_get)){sv_taint(sv);} }STMT_END | ^~~~~~~~ /usr/lib/perl5/5.38/core_perl/CORE/perl.h:997:34: note: in expansion of macro ‘cBOOL’ 997 | # define TAINTING_get (cBOOL(UNLIKELY(PL_tainting))) | ^~~~~ /usr/lib/perl5/5.38/core_perl/CORE/sv.h:1718:51: note: in expansion of macro ‘TAINTING_get’ 1718 | #define SvTAINTED_on(sv) STMT_START{ if(UNLIKELY(TAINTING_get)){sv_taint(sv);} }STMT_END | ^~~~~~~~~~~~ /usr/lib/perl5/5.38/core_perl/CORE/sv.h:1725:13: note: in expansion of macro ‘SvTAINTED_on’ 1725 | SvTAINTED_on(sv); \ | ^~~~~~~~~~~~ /usr/lib/perl5/5.38/core_perl/CORE/sv_inline.h:996:5: note: in expansion of macro ‘SvTAINT’ 996 | SvTAINT(sv); | ^~~~~~~ make[5]: *** [/home/gregkh/linux/stable/linux-5.15.y/tools/build/Makefile.build:97: scripts/perl/Perf-Trace-Util/Context.o] Error 1 make[4]: *** [/home/gregkh/linux/stable/linux-5.15.y/tools/build/Makefile.build:139: perl/Perf-Trace-Util] Error 2 make[3]: *** [/home/gregkh/linux/stable/linux-5.15.y/tools/build/Makefile.build:139: scripts] Error 2 cc1: all warnings being treated as errors make[5]: *** [/home/gregkh/linux/stable/linux-5.15.y/tools/build/Makefile.build:96: util/scripting-engines/trace-event-perl.o] Error 1 make[4]: *** [/home/gregkh/linux/stable/linux-5.15.y/tools/build/Makefile.build:139: scripting-engines] Error 2 make[3]: *** [/home/gregkh/linux/stable/linux-5.15.y/tools/build/Makefile.build:139: util] Error 2 make[2]: *** [Makefile.perf:658: perf-in.o] Error 2 make[1]: *** [Makefile.perf:238: sub-make] Error 2 make: *** [Makefile:70: all] Error 2 make: Leaving directory '/home/gregkh/linux/stable/linux-5.15.y/tools/perf'
On Tue, Oct 17, 2023 at 03:57:06PM +0200, Greg Kroah-Hartman wrote:
Sure! Here's the output, good luck!
$ make -C tools/perf make: Entering directory '/home/gregkh/linux/stable/linux-5.15.y/tools/perf' BUILD: Doing 'make -j20' parallel build Warning: Kernel ABI header at 'tools/include/uapi/linux/const.h' differs from latest version at 'include/uapi/linux/const.h' diff -u tools/include/uapi/linux/const.h include/uapi/linux/const.h Warning: Kernel ABI header at 'tools/include/uapi/linux/in.h' differs from latest version at 'include/uapi/linux/in.h' diff -u tools/include/uapi/linux/in.h include/uapi/linux/in.h Warning: Kernel ABI header at 'tools/arch/x86/include/asm/disabled-features.h' differs from latest version at 'arch/x86/include/asm/disabled-features.h' diff -u tools/arch/x86/include/asm/disabled-features.h arch/x86/include/asm/disabled-features.h Warning: Kernel ABI header at 'tools/arch/x86/include/asm/required-features.h' differs from latest version at 'arch/x86/include/asm/required-features.h' diff -u tools/arch/x86/include/asm/required-features.h arch/x86/include/asm/required-features.h Warning: Kernel ABI header at 'tools/arch/x86/include/asm/cpufeatures.h' differs from latest version at 'arch/x86/include/asm/cpufeatures.h' diff -u tools/arch/x86/include/asm/cpufeatures.h arch/x86/include/asm/cpufeatures.h Warning: Kernel ABI header at 'tools/arch/x86/include/asm/msr-index.h' differs from latest version at 'arch/x86/include/asm/msr-index.h' diff -u tools/arch/x86/include/asm/msr-index.h arch/x86/include/asm/msr-index.h Warning: Kernel ABI header at 'tools/arch/arm64/include/uapi/asm/kvm.h' differs from latest version at 'arch/arm64/include/uapi/asm/kvm.h' diff -u tools/arch/arm64/include/uapi/asm/kvm.h arch/arm64/include/uapi/asm/kvm.h Makefile.config:1036: No libbabeltrace found, disables 'perf data' CTF format support, please install libbabeltrace-dev[el]/libbabeltrace-ctf-dev Makefile.config:1062: No alternatives command found, you need to set JDIR= to point to the root of your Java directory tests/bpf.c: In function ‘epoll_pwait_loop’: tests/bpf.c:36:17: error: argument 2 null where non-null expected [-Werror=nonnull] 36 | epoll_pwait(-(i + 1), NULL, 0, 0, NULL); | ^~~~~~~~~~~ In file included from tests/bpf.c:5: /usr/include/sys/epoll.h:134:12: note: in a call to function ‘epoll_pwait’ declared ‘nonnull’ 134 | extern int epoll_pwait (int __epfd, struct epoll_event *__events, | ^~~~~~~~~~~
<snip>
Also, in Linus's tree, this works just fine on my system, but I get this same error above (and only this error), when building perf on 6.1.y, and on 6.5.y. The perl errors are not present there.
thanks,
greg k-h
On 17/10/2023 16:08, Greg Kroah-Hartman wrote:
On Tue, Oct 17, 2023 at 03:57:06PM +0200, Greg Kroah-Hartman wrote:
Sure! Here's the output, good luck!
$ make -C tools/perf make: Entering directory '/home/gregkh/linux/stable/linux-5.15.y/tools/perf' BUILD: Doing 'make -j20' parallel build Warning: Kernel ABI header at 'tools/include/uapi/linux/const.h' differs from latest version at 'include/uapi/linux/const.h' diff -u tools/include/uapi/linux/const.h include/uapi/linux/const.h Warning: Kernel ABI header at 'tools/include/uapi/linux/in.h' differs from latest version at 'include/uapi/linux/in.h' diff -u tools/include/uapi/linux/in.h include/uapi/linux/in.h Warning: Kernel ABI header at 'tools/arch/x86/include/asm/disabled-features.h' differs from latest version at 'arch/x86/include/asm/disabled-features.h' diff -u tools/arch/x86/include/asm/disabled-features.h arch/x86/include/asm/disabled-features.h Warning: Kernel ABI header at 'tools/arch/x86/include/asm/required-features.h' differs from latest version at 'arch/x86/include/asm/required-features.h' diff -u tools/arch/x86/include/asm/required-features.h arch/x86/include/asm/required-features.h Warning: Kernel ABI header at 'tools/arch/x86/include/asm/cpufeatures.h' differs from latest version at 'arch/x86/include/asm/cpufeatures.h' diff -u tools/arch/x86/include/asm/cpufeatures.h arch/x86/include/asm/cpufeatures.h Warning: Kernel ABI header at 'tools/arch/x86/include/asm/msr-index.h' differs from latest version at 'arch/x86/include/asm/msr-index.h' diff -u tools/arch/x86/include/asm/msr-index.h arch/x86/include/asm/msr-index.h Warning: Kernel ABI header at 'tools/arch/arm64/include/uapi/asm/kvm.h' differs from latest version at 'arch/arm64/include/uapi/asm/kvm.h' diff -u tools/arch/arm64/include/uapi/asm/kvm.h arch/arm64/include/uapi/asm/kvm.h Makefile.config:1036: No libbabeltrace found, disables 'perf data' CTF format support, please install libbabeltrace-dev[el]/libbabeltrace-ctf-dev Makefile.config:1062: No alternatives command found, you need to set JDIR= to point to the root of your Java directory tests/bpf.c: In function ‘epoll_pwait_loop’: tests/bpf.c:36:17: error: argument 2 null where non-null expected [-Werror=nonnull] 36 | epoll_pwait(-(i + 1), NULL, 0, 0, NULL); | ^~~~~~~~~~~ In file included from tests/bpf.c:5: /usr/include/sys/epoll.h:134:12: note: in a call to function ‘epoll_pwait’ declared ‘nonnull’ 134 | extern int epoll_pwait (int __epfd, struct epoll_event *__events, | ^~~~~~~~~~~
<snip>
Also, in Linus's tree, this works just fine on my system, but I get this same error above (and only this error), when building perf on 6.1.y, and on 6.5.y. The perl errors are not present there.
So lots of those are -Werror things -- I'm guessing it's a newer compiler/toolchain/libraries on an older tree. There might be some commits in mainline fixing those... in the meantime, what happens if you just disable -Werror for now?
make -C tools/perf/ WERROR=0
If that doesn't work, maybe even:
make -C tools/perf/ WERROR=0 NO_LIBPERL=1
There are a bunch of other options to disable various things, they are all documented in tools/perf/Makefile.perf.
Vegard
On Tue, Oct 17, 2023 at 05:09:04PM +0200, Vegard Nossum wrote:
On 17/10/2023 16:08, Greg Kroah-Hartman wrote:
On Tue, Oct 17, 2023 at 03:57:06PM +0200, Greg Kroah-Hartman wrote:
Sure! Here's the output, good luck!
$ make -C tools/perf make: Entering directory '/home/gregkh/linux/stable/linux-5.15.y/tools/perf' BUILD: Doing 'make -j20' parallel build Warning: Kernel ABI header at 'tools/include/uapi/linux/const.h' differs from latest version at 'include/uapi/linux/const.h' diff -u tools/include/uapi/linux/const.h include/uapi/linux/const.h Warning: Kernel ABI header at 'tools/include/uapi/linux/in.h' differs from latest version at 'include/uapi/linux/in.h' diff -u tools/include/uapi/linux/in.h include/uapi/linux/in.h Warning: Kernel ABI header at 'tools/arch/x86/include/asm/disabled-features.h' differs from latest version at 'arch/x86/include/asm/disabled-features.h' diff -u tools/arch/x86/include/asm/disabled-features.h arch/x86/include/asm/disabled-features.h Warning: Kernel ABI header at 'tools/arch/x86/include/asm/required-features.h' differs from latest version at 'arch/x86/include/asm/required-features.h' diff -u tools/arch/x86/include/asm/required-features.h arch/x86/include/asm/required-features.h Warning: Kernel ABI header at 'tools/arch/x86/include/asm/cpufeatures.h' differs from latest version at 'arch/x86/include/asm/cpufeatures.h' diff -u tools/arch/x86/include/asm/cpufeatures.h arch/x86/include/asm/cpufeatures.h Warning: Kernel ABI header at 'tools/arch/x86/include/asm/msr-index.h' differs from latest version at 'arch/x86/include/asm/msr-index.h' diff -u tools/arch/x86/include/asm/msr-index.h arch/x86/include/asm/msr-index.h Warning: Kernel ABI header at 'tools/arch/arm64/include/uapi/asm/kvm.h' differs from latest version at 'arch/arm64/include/uapi/asm/kvm.h' diff -u tools/arch/arm64/include/uapi/asm/kvm.h arch/arm64/include/uapi/asm/kvm.h Makefile.config:1036: No libbabeltrace found, disables 'perf data' CTF format support, please install libbabeltrace-dev[el]/libbabeltrace-ctf-dev Makefile.config:1062: No alternatives command found, you need to set JDIR= to point to the root of your Java directory tests/bpf.c: In function ‘epoll_pwait_loop’: tests/bpf.c:36:17: error: argument 2 null where non-null expected [-Werror=nonnull] 36 | epoll_pwait(-(i + 1), NULL, 0, 0, NULL); | ^~~~~~~~~~~ In file included from tests/bpf.c:5: /usr/include/sys/epoll.h:134:12: note: in a call to function ‘epoll_pwait’ declared ‘nonnull’ 134 | extern int epoll_pwait (int __epfd, struct epoll_event *__events, | ^~~~~~~~~~~
<snip>
Also, in Linus's tree, this works just fine on my system, but I get this same error above (and only this error), when building perf on 6.1.y, and on 6.5.y. The perl errors are not present there.
So lots of those are -Werror things -- I'm guessing it's a newer compiler/toolchain/libraries on an older tree. There might be some commits in mainline fixing those... in the meantime, what happens if you just disable -Werror for now?
make -C tools/perf/ WERROR=0
That does, for the epoll_pwait() issue I see in 6.1.y and 6.5.y, odds are there's a fix here in Linus's tree.
Yes, all of that code is now gone, in commit 3d6dfae88917 ("perf parse-events: Remove BPF event support"), which isn't relevant for stable.
If that doesn't work, maybe even:
make -C tools/perf/ WERROR=0 NO_LIBPERL=1
What's wrong with libperl for older kernels? :)
There are a bunch of other options to disable various things, they are all documented in tools/perf/Makefile.perf.
True, but again, my system has libperl, and perf doesn't build, and neither does the bpf test, so that's why I don't ever test any of this, because it just doesn't work for me.
And yes, I do run newer compilers and libraries, but the rest of the kernel builds fine with them (I make sure of that), but given that no one seems to care about perf breaking for so long, I just apply patches when they come up and don't have conflicts and see if anyone notices any difference.
Normally, no one does :)
thanks,
greg k-h
Hello!
On Tue, 17 Oct 2023 at 10:29, Greg Kroah-Hartman gregkh@linuxfoundation.org wrote: [...]
And yes, I do run newer compilers and libraries, but the rest of the kernel builds fine with them (I make sure of that), but given that no one seems to care about perf breaking for so long, I just apply patches when they come up and don't have conflicts and see if anyone notices any difference.
Normally, no one does :)
Just for the record, we stopped building Perf on these older branches as we agreed with Guenter, for the same reason that you said before: it fails all the time with a variety of toolchains/architectures. For now, we're only building/testing Perf on latest stable (6.5) and latest stable LTS (6.1). We brought that up at the OATS call a couple of months back.
Greetings!
Daniel Díaz daniel.diaz@linaro.org
Hi Greg,
On 16/10/23 10:28 pm, Greg Kroah-Hartman wrote:
On Mon, Oct 16, 2023 at 09:23:36PM +0530, Harshit Mogalapalli wrote:
Hi Greg,
On 16/10/23 8:44 pm, Greg Kroah-Hartman wrote:
On Mon, Oct 16, 2023 at 07:06:20PM +0530, Harshit Mogalapalli wrote:
Hi Greg,
On 16/10/23 2:09 pm, Greg Kroah-Hartman wrote:
This is the start of the stable review cycle for the 5.15.136 release. There are 102 patches in this series, all will be posted as a response to this one. If anyone has any issues with these being applied, please let me know.
Responses should be made by Wed, 18 Oct 2023 08:39:38 +0000. Anything received after that time might be too late.
I am seeing a build failure while compiling tools/perf/
In file included from tests/genelf.c:14: tests/../util/genelf.h:5:10: fatal error: linux/math.h: No such file or directory 5 | #include <linux/math.h> | ^~~~~~~~~~~~~~ compilation terminated.
Patch 43 in this series is causing this.
Sorry for the confusion.
What is patch 43?
It is patch 42/102 in this series
https://lore.kernel.org/stable/2023101641-resource-scalding-3e1d@gregkh/T/#m...
Commit: e2bf685d7e311 ("perf inject: Fix GEN_ELF_TEXT_OFFSET for jit")
Why is this not reproducible upstream ?
Vegard bisected the commit which makes it not reproducible upstream and this commit is missing in 5.15.y: Commit: d6e6a27d960f ("tools: Fix math.h breakage")
Backport request for this was made here: https://lore.kernel.org/all/CAMVNhxS-6qNfxy8jHrY5EtZASTL9gAvZi=BdTkUA5_5CSQ2...
And that commit is in this patch series, so are you sure that was correct?
Cause for this build issue: Commit: e2bf685d7e311 ("perf inject: Fix GEN_ELF_TEXT_OFFSET for jit")
And this issue is not in upstream due to presence of commit d6e6a27d960f ("tools: Fix math.h breakage") in upstream but not in 5.15.y
Ok, I'll go drop the patch entirely, I can't even get perf to build at all for me on 5.15, which is why I've given up on it even mattering anymore :(
Thanks,
After reverting this patch locally, no problems seen on x86_64 and aarch64 for this rc.
Tested-by: Harshit Mogalapalli harshit.m.mogalapalli@oracle.com
Regards, Harshit
thanks,
greg k-h
On 10/16/23 01:39, Greg Kroah-Hartman wrote:
This is the start of the stable review cycle for the 5.15.136 release. There are 102 patches in this series, all will be posted as a response to this one. If anyone has any issues with these being applied, please let me know.
Responses should be made by Wed, 18 Oct 2023 08:39:38 +0000. Anything received after that time might be too late.
The whole patch series can be found in one patch at: https://www.kernel.org/pub/linux/kernel/v5.x/stable-review/patch-5.15.136-rc... or in the git tree and branch at: git://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable-rc.git linux-5.15.y and the diffstat can be found below.
thanks,
greg k-h
On ARCH_BRCMSTB using 32-bit and 64-bit ARM kernels, build tested on BMIPS_GENERIC:
Tested-by: Florian Fainelli florian.fainelli@broadcom.com
Hello,
On Mon, 16 Oct 2023 10:39:59 +0200 Greg Kroah-Hartman gregkh@linuxfoundation.org wrote:
This is the start of the stable review cycle for the 5.15.136 release. There are 102 patches in this series, all will be posted as a response to this one. If anyone has any issues with these being applied, please let me know.
Responses should be made by Wed, 18 Oct 2023 08:39:38 +0000. Anything received after that time might be too late.
The whole patch series can be found in one patch at: https://www.kernel.org/pub/linux/kernel/v5.x/stable-review/patch-5.15.136-rc... or in the git tree and branch at: git://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable-rc.git linux-5.15.y and the diffstat can be found below.
This rc kernel passes DAMON functionality test[1] on my test machine. Attaching the test results summary below. Please note that I retrieved the kernel from linux-stable-rc tree[2].
Tested-by: SeongJae Park sj@kernel.org
[1] https://github.com/awslabs/damon-tests/tree/next/corr [2] f11fc66f963f ("Linux 5.15.136-rc1")
Thanks, SJ
[...]
---
ok 1 selftests: damon: debugfs_attrs.sh ok 1 selftests: damon-tests: huge_count_read_write.sh ok 2 selftests: damon-tests: buffer_overflow.sh ok 3 selftests: damon-tests: rm_contexts.sh ok 4 selftests: damon-tests: record_null_deref.sh ok 5 selftests: damon-tests: dbgfs_target_ids_read_before_terminate_race.sh ok 6 selftests: damon-tests: dbgfs_target_ids_pid_leak.sh ok 7 selftests: damon-tests: damo_tests.sh ok 8 selftests: damon-tests: masim-record.sh ok 9 selftests: damon-tests: build_i386.sh ok 10 selftests: damon-tests: build_arm64.sh ok 11 selftests: damon-tests: build_i386_idle_flag.sh ok 12 selftests: damon-tests: build_i386_highpte.sh ok 13 selftests: damon-tests: build_nomemcg.sh
PASS
On 10/16/23 02:39, Greg Kroah-Hartman wrote:
This is the start of the stable review cycle for the 5.15.136 release. There are 102 patches in this series, all will be posted as a response to this one. If anyone has any issues with these being applied, please let me know.
Responses should be made by Wed, 18 Oct 2023 08:39:38 +0000. Anything received after that time might be too late.
The whole patch series can be found in one patch at: https://www.kernel.org/pub/linux/kernel/v5.x/stable-review/patch-5.15.136-rc... or in the git tree and branch at: git://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable-rc.git linux-5.15.y and the diffstat can be found below.
thanks,
greg k-h
Compiled and booted on my test system. No dmesg regressions.
Tested-by: Shuah Khan skhan@linuxfoundation.org
thanks, -- Shuah
On 10/16/23 1:39 AM, Greg Kroah-Hartman wrote:
This is the start of the stable review cycle for the 5.15.136 release. There are 102 patches in this series, all will be posted as a response to this one. If anyone has any issues with these being applied, please let me know.
Responses should be made by Wed, 18 Oct 2023 08:39:38 +0000. Anything received after that time might be too late.
The whole patch series can be found in one patch at: https://www.kernel.org/pub/linux/kernel/v5.x/stable-review/patch-5.15.136-rc... or in the git tree and branch at: git://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable-rc.git linux-5.15.y and the diffstat can be found below.
thanks,
greg k-h
Built and booted successfully on RISC-V RV64 (HiFive Unmatched).
Tested-by: Ron Economos re@w6rz.net
On Mon, 16 Oct 2023 at 14:14, Greg Kroah-Hartman gregkh@linuxfoundation.org wrote:
This is the start of the stable review cycle for the 5.15.136 release. There are 102 patches in this series, all will be posted as a response to this one. If anyone has any issues with these being applied, please let me know.
Responses should be made by Wed, 18 Oct 2023 08:39:38 +0000. Anything received after that time might be too late.
The whole patch series can be found in one patch at: https://www.kernel.org/pub/linux/kernel/v5.x/stable-review/patch-5.15.136-rc... or in the git tree and branch at: git://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable-rc.git linux-5.15.y and the diffstat can be found below.
thanks,
greg k-h
Results from Linaro’s test farm. No regressions on arm64, arm, x86_64, and i386.
Tested-by: Linux Kernel Functional Testing lkft@linaro.org
## Build * kernel: 5.15.136-rc1 * git: https://gitlab.com/Linaro/lkft/mirrors/stable/linux-stable-rc * git branch: linux-5.15.y * git commit: f11fc66f963fdd01d969cd3dbb90f0f775de525e * git describe: v5.15.135-103-gf11fc66f963f * test details: https://qa-reports.linaro.org/lkft/linux-stable-rc-linux-5.15.y/build/v5.15....
## Test Regressions (compared to v5.15.135)
## Metric Regressions (compared to v5.15.135)
## Test Fixes (compared to v5.15.135)
## Metric Fixes (compared to v5.15.135)
## Test result summary total: 147886, pass: 122990, fail: 2836, skip: 21902, xfail: 158
## Build Summary * arc: 10 total, 10 passed, 0 failed * arm: 227 total, 227 passed, 0 failed * arm64: 85 total, 85 passed, 0 failed * i386: 67 total, 66 passed, 1 failed * mips: 51 total, 50 passed, 1 failed * parisc: 7 total, 7 passed, 0 failed * powerpc: 50 total, 49 passed, 1 failed * riscv: 19 total, 19 passed, 0 failed * s390: 21 total, 20 passed, 1 failed * sh: 26 total, 24 passed, 2 failed * sparc: 14 total, 14 passed, 0 failed * x86_64: 72 total, 72 passed, 0 failed
## Test suites summary * boot * kselftest-android * kselftest-arm64 * kselftest-breakpoints * kselftest-capabilities * kselftest-cgroup * kselftest-clone3 * kselftest-core * kselftest-cpu-hotplug * kselftest-cpufreq * kselftest-drivers-dma-buf * kselftest-efivarfs * kselftest-exec * kselftest-filesystems * kselftest-filesystems-binderfs * kselftest-filesystems-epoll * kselftest-firmware * kselftest-fpu * kselftest-ftrace * kselftest-futex * kselftest-gpio * kselftest-intel_pstate * kselftest-ipc * kselftest-ir * kselftest-kcmp * kselftest-kexec * kselftest-kvm * kselftest-lib * kselftest-membarrier * kselftest-memfd * kselftest-memory-hotplug * kselftest-mincore * kselftest-mount * kselftest-mqueue * kselftest-net * kselftest-net-forwarding * kselftest-net-mptcp * kselftest-netfilter * kselftest-nsfs * kselftest-openat2 * kselftest-pid_namespace * kselftest-pidfd * kselftest-proc * kselftest-pstore * kselftest-ptrace * kselftest-rseq * kselftest-rtc * kselftest-seccomp * kselftest-sigaltstack * kselftest-size * kselftest-splice * kselftest-static_keys * kselftest-sync * kselftest-sysctl * kselftest-tc-testing * kselftest-timens * kselftest-tmpfs * kselftest-tpm2 * kselftest-user * kselftest-user_events * kselftest-vDSO * kselftest-vm * kselftest-watchdog * kselftest-x86 * kselftest-zram * kunit * kvm-unit-tests * libgpiod * log-parser-boot * log-parser-test * ltp-cap_bounds * ltp-commands * ltp-containers * ltp-controllers * ltp-cpuhotplug * ltp-crypto * ltp-cve * ltp-dio * ltp-fcntl-locktests * ltp-filecaps * ltp-fs * ltp-fs_bind * ltp-fs_perms_simple * ltp-fsx * ltp-hugetlb * ltp-io * ltp-ipc * ltp-math * ltp-mm * ltp-nptl * ltp-pty * ltp-sched * ltp-securebits * ltp-smoke * ltp-syscalls * ltp-tracing * perf * rcutorture
-- Linaro LKFT https://lkft.linaro.org
On Mon, 16 Oct 2023 10:39:59 +0200, Greg Kroah-Hartman wrote:
This is the start of the stable review cycle for the 5.15.136 release. There are 102 patches in this series, all will be posted as a response to this one. If anyone has any issues with these being applied, please let me know.
Responses should be made by Wed, 18 Oct 2023 08:39:38 +0000. Anything received after that time might be too late.
The whole patch series can be found in one patch at: https://www.kernel.org/pub/linux/kernel/v5.x/stable-review/patch-5.15.136-rc... or in the git tree and branch at: git://git.kernel.org/pub/scm/linux/kernel/git/stable/linux-stable-rc.git linux-5.15.y and the diffstat can be found below.
thanks,
greg k-h
All tests passing for Tegra ...
Test results for stable-v5.15: 10 builds: 10 pass, 0 fail 26 boots: 26 pass, 0 fail 102 tests: 102 pass, 0 fail
Linux version: 5.15.136-rc1-gf11fc66f963f Boards tested: tegra124-jetson-tk1, tegra186-p2771-0000, tegra194-p2972-0000, tegra194-p3509-0000+p3668-0000, tegra20-ventana, tegra210-p2371-2180, tegra210-p3450-0000, tegra30-cardhu-a04
Tested-by: Jon Hunter jonathanh@nvidia.com
Jon
-
Daniel Díaz -
Florian Fainelli -
Greg Kroah-Hartman -
Harshit Mogalapalli -
Jon Hunter -
Naresh Kamboju -
Ricardo B. Marliere -
Ron Economos -
SeongJae Park -
Shuah Khan -
Vegard Nossum