aboutsummaryrefslogtreecommitdiffstatshomepage
path: root/tools/perf/scripts/python/export-to-postgresql.py (unfollow)
AgeCommit message (Collapse)AuthorFilesLines
2023-06-13ARM: dts: qcom: msm8226: Add qfprom nodeMatti Lehtimäki1-0/+7
Add missing QFPROM definition for MSM8226 SoC. Signed-off-by: Matti Lehtimäki <matti.lehtimaki@gmail.com> Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org> Reviewed-by: Luca Weiss <luca@z3ntu.xyz> Signed-off-by: Bjorn Andersson <andersson@kernel.org> Link: https://lore.kernel.org/r/20230507201225.89694-5-matti.lehtimaki@gmail.com
2023-06-13ARM: dts: qcom: pm8941: Add thermal zone configMatti Lehtimäki1-0/+31
Add thermal zone for the PMIC thermal sensor. Signed-off-by: Matti Lehtimäki <matti.lehtimaki@gmail.com> Signed-off-by: Bjorn Andersson <andersson@kernel.org> Link: https://lore.kernel.org/r/20230529221501.43455-4-matti.lehtimaki@gmail.com
2023-06-13ARM: dts: qcom: pm8841: Add thermal zone configMatti Lehtimäki1-1/+32
Add thermal zone for the PMIC thermal sensor. Temperatures are based on downstream values, except for critical trip point where 140°C is used instead of 145°C due to limitations without a configured ADC. Signed-off-by: Matti Lehtimäki <matti.lehtimaki@gmail.com> Signed-off-by: Bjorn Andersson <andersson@kernel.org> Link: https://lore.kernel.org/r/20230529221501.43455-3-matti.lehtimaki@gmail.com
2023-06-13ARM: dts: qcom: pm8226: Add thermal sensor and thermal zone configMatti Lehtimäki1-0/+39
Add thermal sensor, which is using on chip VADC channel to report PMIC die temperature. Also add the corresponding thermal zone. Signed-off-by: Matti Lehtimäki <matti.lehtimaki@gmail.com> Signed-off-by: Bjorn Andersson <andersson@kernel.org> Link: https://lore.kernel.org/r/20230529221501.43455-2-matti.lehtimaki@gmail.com
2023-06-13ARM: dts: qcom: msm8974: rename labels for DSI nodesDmitry Baryshkov4-42/+50
Currently in board files MDSS and HDMI nodes stay apart, because labels for HDMI nodes do not have the mdss_ prefix. It was found that grouping all display-related notes is more useful. To keep all display-related nodes close in the board files, change DSI node aliases from dsi_* to mdss_dsi_*. Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org> Reviewed-by: Konrad Dybcio <konrad.dybcio@linaro.org> Signed-off-by: Bjorn Andersson <andersson@kernel.org> Link: https://lore.kernel.org/r/20230531011623.3808538-15-dmitry.baryshkov@linaro.org
2023-06-13ARM: dts: qcom: apq8074-dragonboard: add gpio keysDmitry Baryshkov1-0/+34
Add device nodes for gpio-keys (volume-up, general key) device nodes. Reviewed-by: Konrad Dybcio <konrad.dybcio@linaro.org> Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org> Signed-off-by: Bjorn Andersson <andersson@kernel.org> Link: https://lore.kernel.org/r/20230531012627.3813060-3-dmitry.baryshkov@linaro.org
2023-06-13ARM: dts: qcom: apq8074-dragonboard: add onboard ledsDmitry Baryshkov1-0/+24
The dragonboard as three LEDs: red, green and blue. Add corresponding description. Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org> Signed-off-by: Bjorn Andersson <andersson@kernel.org> Link: https://lore.kernel.org/r/20230531012627.3813060-2-dmitry.baryshkov@linaro.org
2023-06-13ARM: dts: qcom: Add Samsung Galaxy Express supportRudraksha Gupta2-0/+332
Add a very basic device tree file for the Samsung Galaxy Express SGH-I437. Currently, the following things work: UART, eMMC, SD Card, and USB. Signed-off-by: Rudraksha Gupta <guptarud@gmail.com> Signed-off-by: Bjorn Andersson <andersson@kernel.org> Link: https://lore.kernel.org/r/20230607050025.86636-5-guptarud@gmail.com
2023-06-13ARM: dts: qcom: msm8960: Add USB nodeRudraksha Gupta1-1/+33
Add the required nodes to support USB on the MSM8960 SoC. As it's very similar to the APQ8064 SoC, the nodes are almost identical Add a label to sleep_clk for the USB node to reference Signed-off-by: Rudraksha Gupta <guptarud@gmail.com> Signed-off-by: Bjorn Andersson <andersson@kernel.org> Link: https://lore.kernel.org/r/20230607050025.86636-4-guptarud@gmail.com
2023-06-13ARM: dts: qcom: adapt to LP855X bindings changesArtur Weber2-12/+12
Change underscores in ROM node names to dashes, and remove deprecated pwm-period property. Signed-off-by: Artur Weber <aweber.kernel@gmail.com> Reviewed-by: Luca Weiss <luca@z3ntu.xyz> Reviewed-by: Daniel Thompson <daniel.thompson@linaro.org> Signed-off-by: Bjorn Andersson <andersson@kernel.org> Link: https://lore.kernel.org/r/20230519180728.2281-4-aweber.kernel@gmail.com
2023-06-13ARM: dts: qcom: msm8226: Provide clocks to mmcc nodeLuca Weiss1-0/+15
The mmcc needs several clocks that are being used as parents. Provide them in dt. Signed-off-by: Luca Weiss <luca@z3ntu.xyz> Reviewed-by: Konrad Dybcio <konrad.dybcio@linaro.org> Signed-off-by: Bjorn Andersson <andersson@kernel.org> Link: https://lore.kernel.org/r/20230509-msm8226-mmcc-parents-v1-3-83a2dfc986ab@z3ntu.xyz
2023-06-13ARM: dts: qcom: msm8226: Use XO from rpmcc where possibleLuca Weiss1-5/+6
The xo clock being used everywhere actually goes via the RPM. Since the rpmcc driver recently got support for this clock we can use this now. Signed-off-by: Luca Weiss <luca@z3ntu.xyz> Reviewed-by: Konrad Dybcio <konrad.dybcio@linaro.org> Signed-off-by: Bjorn Andersson <andersson@kernel.org> Link: https://lore.kernel.org/r/20230509-msm8226-mmcc-parents-v1-1-83a2dfc986ab@z3ntu.xyz
2023-05-30ARM: dts: qcom: apq8074-dragonboard: enable DSI panelDmitry Baryshkov1-0/+51
Enable MDSS, GPU and DSI panel output on the APQ8074 dragonboard. Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org> Signed-off-by: Bjorn Andersson <andersson@kernel.org> Link: https://lore.kernel.org/r/20230507190735.2333145-5-dmitry.baryshkov@linaro.org
2023-05-30ARM: dts: qcom: apq8074-dragonboard: enable adsp and MSSDmitry Baryshkov1-0/+28
Enable ADSP and Modem DSPs on APQ8074 dragonboard. The MSS region differs from the one defined in the msm8974, so it overriden locally. The modem is specified use mba.mbn instead of mbn.b00 (for the sake of similarity with other platforms). This requires a patch for remoteproc to be applied [1]. [1] https://lore.kernel.org/all/20230507172041.2320279-1-dmitry.baryshkov@linaro.org/ Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org> Reviewed-by: Konrad Dybcio <konrad.dybcio@linaro.org> Signed-off-by: Bjorn Andersson <andersson@kernel.org> Link: https://lore.kernel.org/r/20230507190735.2333145-4-dmitry.baryshkov@linaro.org
2023-05-30ARM: dts: qcom: apq8074-dragonboard: Set DMA as remotely controlledDmitry Baryshkov1-0/+4
Add the qcom,controlled-remotely property for the blsp2_bam controller node. This board requires this, otherwise the board stalls during the boot for some reason (most probably because TZ mishandles the protection error and keeps on looping somewhere inside). Fixes: 62bc81792223 dts: msm8974: Add blsp2_bam dma node Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@linaro.org> Reviewed-by: Konrad Dybcio <konrad.dybcio@linaro.org> Signed-off-by: Bjorn Andersson <andersson@kernel.org> Link: https://lore.kernel.org/r/20230507190735.2333145-3-dmitry.baryshkov@linaro.org
2023-05-30ARM: dts: qcom: apq8026-huawei-sturgeon: Add vibratorLuca Weiss1-0/+28
The watch has a DRV2605 for haptics. Add a node for it based on the values found in the downstream board file. Signed-off-by: Luca Weiss <luca@z3ntu.xyz> Reviewed-by: Konrad Dybcio <konrad.dybcio@linaro.org> Signed-off-by: Bjorn Andersson <andersson@kernel.org> Link: https://lore.kernel.org/r/20230430-drv260x-improvements-v1-5-1fb28b4cc698@z3ntu.xyz
2023-05-30ARM: dts: qcom: msm8226: Add IMEM nodeMatti Lehtimäki1-0/+14
This enables userspace to signal the bootloader to go into the bootloader or recovery mode. The magic values can be found in both the downstream kernel and the LK kernel (bootloader). Signed-off-by: Matti Lehtimäki <matti.lehtimaki@gmail.com> Reviewed-by: Luca Weiss <luca@z3ntu.xyz> Signed-off-by: Bjorn Andersson <andersson@kernel.org> Link: https://lore.kernel.org/r/20230520121933.15533-5-matti.lehtimaki@gmail.com
2023-05-30ARM: dts: qcom: msm8226: Add rpm-stats device nodeMatti Lehtimäki1-0/+5
Add device node for the rpm-stats pseudo device. Signed-off-by: Matti Lehtimäki <matti.lehtimaki@gmail.com> Reviewed-by: Konrad Dybcio <konrad.dybcio@linaro.org> Reviewed-by: Luca Weiss <luca@z3ntu.xyz> Signed-off-by: Bjorn Andersson <andersson@kernel.org> Link: https://lore.kernel.org/r/20230520121933.15533-4-matti.lehtimaki@gmail.com
2023-05-30ARM: dts: qcom: msm8226: Add PMU nodeMatti Lehtimäki1-0/+6
Enable perf events on MSM8226 devices by adding the PMU node. Signed-off-by: Matti Lehtimäki <matti.lehtimaki@gmail.com> Reviewed-by: Luca Weiss <luca@z3ntu.xyz> Signed-off-by: Bjorn Andersson <andersson@kernel.org> Link: https://lore.kernel.org/r/20230520121933.15533-3-matti.lehtimaki@gmail.com
2023-05-30ARM: dts: qcom: sdx65-mtp: Enable PCIe EPRohit Agarwal1-0/+35
Enable PCIe Endpoint controller on the SDX65 MTP board based on Qualcomm SDX65 platform. Signed-off-by: Rohit Agarwal <quic_rohiagar@quicinc.com> Reviewed-by: Konrad Dybcio <konrad.dybcio@linaro.org> Signed-off-by: Bjorn Andersson <andersson@kernel.org> Link: https://lore.kernel.org/r/1684432073-28490-6-git-send-email-quic_rohiagar@quicinc.com
2023-05-30ARM: dts: qcom: sdx65-mtp: Enable PCIe PHYRohit Agarwal1-0/+7
Enable PCIe PHY on SDX65 MTP for PCIe EP. Signed-off-by: Rohit Agarwal <quic_rohiagar@quicinc.com> Reviewed-by: Konrad Dybcio <konrad.dybcio@linaro.org> Signed-off-by: Bjorn Andersson <andersson@kernel.org> Link: https://lore.kernel.org/r/1684432073-28490-5-git-send-email-quic_rohiagar@quicinc.com
2023-05-30ARM: dts: qcom: sdx65: Add support for PCIe EPRohit Agarwal1-0/+56
Add support for PCIe Endpoint controller on the Qualcomm SDX65 platform. Signed-off-by: Rohit Agarwal <quic_rohiagar@quicinc.com> Reviewed-by: Manivannan Sadhasivam <manivannan.sadhasivam@linaro.org> Reviewed-by: Konrad Dybcio <konrad.dybcio@linaro.org> Signed-off-by: Bjorn Andersson <andersson@kernel.org> Link: https://lore.kernel.org/r/1684432073-28490-4-git-send-email-quic_rohiagar@quicinc.com
2023-05-30ARM: dts: qcom: sdx65: Add support for PCIe PHYRohit Agarwal1-0/+31
Add devicetree support for PCIe PHY used in SDX65 platform. This PHY is used by the PCIe EP controller. Signed-off-by: Rohit Agarwal <quic_rohiagar@quicinc.com> Reviewed-by: Konrad Dybcio <konrad.dybcio@linaro.org> Signed-off-by: Bjorn Andersson <andersson@kernel.org> Link: https://lore.kernel.org/r/1684432073-28490-3-git-send-email-quic_rohiagar@quicinc.com
2023-05-30ARM: dts: qcom: msm8974: align WCNSS Bluetooth node name with bindingsKrzysztof Kozlowski1-1/+1
Bindings expect WCNSS Bluetooth child to be named "bluetooth": remoteproc@fb204000: smd-edge:wcnss: 'bt' does not match any of the regexes: 'pinctrl-[0-9]+' Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org> Reviewed-by: Konrad Dybcio <konrad.dybcio@linaro.org> Signed-off-by: Bjorn Andersson <andersson@kernel.org> Link: https://lore.kernel.org/r/20230421195437.31513-1-krzysztof.kozlowski@linaro.org
2023-05-30ARM: dts: qcom: apq8084: correct thermal sensor unit-addressKrzysztof Kozlowski1-1/+1
Match unit-address to reg entry to fix dtbs W=1 warnings: Warning (simple_bus_reg): /soc/thermal-sensor@fc4a8000: simple-bus unit address format error, expected "fc4a9000" Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org> Reviewed-by: Konrad Dybcio <konrad.dybcio@linaro.org> Signed-off-by: Bjorn Andersson <andersson@kernel.org> Link: https://lore.kernel.org/r/20230420075053.41976-10-krzysztof.kozlowski@linaro.org
2023-05-30ARM: dts: qcom: msm8960-cdp: move regulator out of simple-busKrzysztof Kozlowski1-10/+6
Regulators is not a bus, so drop incomplete simple-bus usage to fix dtbs W=1 warning: Warning (simple_bus_reg): /regulators/gpio-regulator: missing or empty reg/ranges property Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org> Reviewed-by: Konrad Dybcio <konrad.dybcio@linaro.org> Signed-off-by: Bjorn Andersson <andersson@kernel.org> Link: https://lore.kernel.org/r/20230420075053.41976-9-krzysztof.kozlowski@linaro.org
2023-05-30ARM: dts: qcom: apq8060-dragonboard: move regulators out of simple-busKrzysztof Kozlowski1-42/+38
Regulators is not a bus, so drop incomplete simple-bus usage to fix dtbs W=1 warnings: Warning (simple_bus_reg): /regulators/regulator-fixed: missing or empty reg/ranges property Warning (simple_bus_reg): /regulators/xc622a331mrg: missing or empty reg/ranges property Warning (simple_bus_reg): /regulators/nds332p: missing or empty reg/ranges property Warning (simple_bus_reg): /regulators/txb0104rgyr: missing or empty reg/ranges property Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org> Reviewed-by: Konrad Dybcio <konrad.dybcio@linaro.org> Signed-off-by: Bjorn Andersson <andersson@kernel.org> Link: https://lore.kernel.org/r/20230420075053.41976-8-krzysztof.kozlowski@linaro.org
2023-05-30ARM: dts: qcom: ipq8064: align USB node names with bindingsKrzysztof Kozlowski1-4/+4
Bindings expect USB controller node names to be named "usb". Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org> Reviewed-by: Konrad Dybcio <konrad.dybcio@linaro.org> Signed-off-by: Bjorn Andersson <andersson@kernel.org> Link: https://lore.kernel.org/r/20230420075053.41976-7-krzysztof.kozlowski@linaro.org
2023-05-30ARM: dts: qcom: ipq8064: correct LED node namesKrzysztof Kozlowski2-6/+6
GPIO LEDs is not a bus, so drop unit-address and also start suffix numbering from 0: Warning (unit_address_vs_reg): /soc/leds/led@7: node has a unit name, but no reg or ranges property Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org> Reviewed-by: Konrad Dybcio <konrad.dybcio@linaro.org> Signed-off-by: Bjorn Andersson <andersson@kernel.org> Link: https://lore.kernel.org/r/20230420075053.41976-6-krzysztof.kozlowski@linaro.org
2023-05-30ARM: dts: qcom: ipq8064: drop invalid GCC thermal-sensor unit-addressKrzysztof Kozlowski1-1/+1
GCC comes with syscon compatible so the thermal-sensor child node should not have unit-address (bindings also do not expect it): Warning (unit_address_vs_reg): /soc/clock-controller@900000/thermal-sensor@900000: node has a unit name, but no reg or ranges property Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org> Reviewed-by: Konrad Dybcio <konrad.dybcio@linaro.org> Signed-off-by: Bjorn Andersson <andersson@kernel.org> Link: https://lore.kernel.org/r/20230420075053.41976-5-krzysztof.kozlowski@linaro.org
2023-05-30ARM: dts: qcom: ipq8064: drop leading 0 from unit-addressKrzysztof Kozlowski1-1/+1
Unit-address should not start with 0: Warning (simple_bus_reg): /soc/syscon@03000000: simple-bus unit address format error, expected "3000000" Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org> Reviewed-by: Konrad Dybcio <konrad.dybcio@linaro.org> Signed-off-by: Bjorn Andersson <andersson@kernel.org> Link: https://lore.kernel.org/r/20230420075053.41976-4-krzysztof.kozlowski@linaro.org
2023-05-30ARM: dts: qcom: msm8974: correct pronto unit-addressKrzysztof Kozlowski1-1/+1
Match unit-address to reg entry to fix dtbs W=1 warnings: Warning (simple_bus_reg): /soc/remoteproc@fb21b000: simple-bus unit address format error, expected "fb204000" Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org> Reviewed-by: Konrad Dybcio <konrad.dybcio@linaro.org> Signed-off-by: Bjorn Andersson <andersson@kernel.org> Link: https://lore.kernel.org/r/20230420075053.41976-3-krzysztof.kozlowski@linaro.org
2023-05-30ARM: dts: qcom: sdx55: correct rsc unit-addressKrzysztof Kozlowski1-1/+1
Match unit-address to reg entry to fix dtbs W=1 warnings: Warning (simple_bus_reg): /soc/rsc@17840000: simple-bus unit address format error, expected "17830000" Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org> Reviewed-by: Konrad Dybcio <konrad.dybcio@linaro.org> Signed-off-by: Bjorn Andersson <andersson@kernel.org> Link: https://lore.kernel.org/r/20230420075053.41976-2-krzysztof.kozlowski@linaro.org
2023-05-30ARM: dts: qcom: ipq4019: correct syscon unit-addressKrzysztof Kozlowski1-1/+1
Match unit-address to reg entry to fix dtbs W=1 warnings: Warning (simple_bus_reg): /soc/syscon@1fcb000: simple-bus unit address format error, expected "1fc0000" Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org> Reviewed-by: Konrad Dybcio <konrad.dybcio@linaro.org> Signed-off-by: Bjorn Andersson <andersson@kernel.org> Link: https://lore.kernel.org/r/20230420075053.41976-1-krzysztof.kozlowski@linaro.org
2023-05-30ARM: dts: qcom: ipq4019: fix broken NAND controller properties overrideKrzysztof Kozlowski3-15/+15
After renaming NAND controller node name from "qpic-nand" to "nand-controller", the board DTS/DTSI also have to be updated: Warning (unit_address_vs_reg): /soc/qpic-nand@79b0000: node has a unit name, but no reg or ranges property Cc: <stable@vger.kernel.org> Fixes: 9e1e00f18afc ("ARM: dts: qcom: Fix node name for NAND controller node") Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org> Reviewed-by: Konrad Dybcio <konrad.dybcio@linaro.org> Reviewed-by: Manivannan Sadhasivam <mani@kernel.org> Signed-off-by: Bjorn Andersson <andersson@kernel.org> Link: https://lore.kernel.org/r/20230420072811.36947-1-krzysztof.kozlowski@linaro.org
2023-05-30ARM: dts: qcom: msm8974: drop unit addresses from USB physKrzysztof Kozlowski1-2/+2
The ulpi node does not allow children to have unit address: Warning (unit_address_vs_reg): /soc/usb@f9a55000/ulpi/phy@a: node has a unit name, but no reg or ranges property Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org> Reviewed-by: Konrad Dybcio <konrad.dybcio@linaro.org> Signed-off-by: Bjorn Andersson <andersson@kernel.org> Link: https://lore.kernel.org/r/20230420065318.23503-1-krzysztof.kozlowski@linaro.org
2023-05-30ARM: dts: qcom: msm8660: Fix regulator node namesLinus Walleij1-2/+2
commit 04715461abf7 altered the node names in a DTSI file used by qcom-apq8060-dragonboard.dts breaking the board. Align the node names in the DTS file and the board boots again. Cc: stable@vger.kernel.org Fixes: 85055a1eecc1 ("ARM: dts: qcom-msm8660: align RPM regulators node name with bindings") Signed-off-by: Linus Walleij <linus.walleij@linaro.org> Signed-off-by: Bjorn Andersson <andersson@kernel.org> Link: https://lore.kernel.org/r/20230414135747.34994-1-linus.walleij@linaro.org
2023-05-24ARM: dts: qcom: msm8974: do not use underscore in node name (again)Krzysztof Kozlowski1-1/+1
Align RPM requests node with DT schema by using hyphen instead of underscore. Fixes: f300826d27be ("ARM: dts: qcom-msm8974: Sort and clean up nodes") Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org> Reviewed-by: Konrad Dybcio <konrad.dybcio@linaro.org> Signed-off-by: Bjorn Andersson <andersson@kernel.org> Link: https://lore.kernel.org/r/20230410175232.22317-1-krzysztof.kozlowski@linaro.org
2023-05-24ARM: dts: qcom: msm8974-hammerhead: Add vibratorLuca Weiss1-0/+35
The Nexus 5 has a vibrator connected to the clock output of GP1_CLK which we can use with the clk-pwm driver, then we can use that pwm with pwm-vibrator to get haptics functionality. This patch is based on Brian Masney's previous patch with clk-vibrator. Signed-off-by: Luca Weiss <luca@z3ntu.xyz> Reviewed-by: Konrad Dybcio <konrad.dybcio@linaro.org> Reviewed-by: Caleb Connolly <caleb.connolly@linaro.org> Reviewed-by: Brian Masney <bmasney@redhat.com> Signed-off-by: Bjorn Andersson <andersson@kernel.org> Link: https://lore.kernel.org/r/20230427-hammerhead-vibra-v1-4-e87eeb94da51@z3ntu.xyz
2023-05-07Linux 6.4-rc1Linus Torvalds1-2/+2
2023-05-06Revert "perf build: Make BUILD_BPF_SKEL default, rename to NO_BPF_SKEL"Arnaldo Carvalho de Melo6-20/+14
This reverts commit a980755beb5aca9002e1c95ba519b83a44242b5b. We need to better polish building with BPF skels, so revert back to making it an experimental feature that has to be explicitely enabled using BUILD_BPF_SKEL=1. Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-05-06Revert "perf build: Warn for BPF skeletons if endian mismatches"Arnaldo Carvalho de Melo1-10/+7
This reverts commit 51924ae69eea5bc90b5da525fbcf4bbd5f8551b3. We need to better polish building with BPF skels, so revert back to making it an experimental feature that has to be explicitely enabled using BUILD_BPF_SKEL=1. Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2023-05-06dmapool: link blocks across pagesKeith Busch1-127/+130
The allocated dmapool pages are never freed for the lifetime of the pool. There is no need for the two level list+stack lookup for finding a free block since nothing is ever removed from the list. Just use a simple stack, reducing time complexity to constant. The implementation inserts the stack linking elements and the dma handle of the block within itself when freed. This means the smallest possible dmapool block is increased to at most 16 bytes to accommodate these fields, but there are no exisiting users requesting a dma pool smaller than that anyway. Removing the list has a significant change in performance. Using the kernel's micro-benchmarking self test: Before: # modprobe dmapool_test dmapool test: size:16 blocks:8192 time:57282 dmapool test: size:64 blocks:8192 time:172562 dmapool test: size:256 blocks:8192 time:789247 dmapool test: size:1024 blocks:2048 time:371823 dmapool test: size:4096 blocks:1024 time:362237 After: # modprobe dmapool_test dmapool test: size:16 blocks:8192 time:24997 dmapool test: size:64 blocks:8192 time:26584 dmapool test: size:256 blocks:8192 time:33542 dmapool test: size:1024 blocks:2048 time:9022 dmapool test: size:4096 blocks:1024 time:6045 The module test allocates quite a few blocks that may not accurately represent how these pools are used in real life. For a more marco level benchmark, running fio high-depth + high-batched on nvme, this patch shows submission and completion latency reduced by ~100usec each, 1% IOPs improvement, and perf record's time spent in dma_pool_alloc/free were reduced by half. [kbusch@kernel.org: push new blocks in ascending order] Link: https://lkml.kernel.org/r/20230221165400.1595247-1-kbusch@meta.com Link: https://lkml.kernel.org/r/20230126215125.4069751-12-kbusch@meta.com Fixes: 2d55c16c0c54 ("dmapool: create/destroy cleanup") Signed-off-by: Keith Busch <kbusch@kernel.org> Reviewed-by: Christoph Hellwig <hch@lst.de> Tested-by: Bryan O'Donoghue <bryan.odonoghue@linaro.org> Cc: Matthew Wilcox <willy@infradead.org> Cc: Tony Battersby <tonyb@cybernetics.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-05-06dmapool: don't memset on free twiceKeith Busch1-2/+2
If debug is enabled, dmapool will poison the range, so no need to clear it to 0 immediately before writing over it. Link: https://lkml.kernel.org/r/20230126215125.4069751-11-kbusch@meta.com Fixes: 2d55c16c0c54 ("dmapool: create/destroy cleanup") Signed-off-by: Keith Busch <kbusch@kernel.org> Reviewed-by: Christoph Hellwig <hch@lst.de> Cc: Matthew Wilcox <willy@infradead.org> Cc: Tony Battersby <tonyb@cybernetics.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-05-06dmapool: simplify freeingKeith Busch1-16/+6
The actions for busy and not busy are mostly the same, so combine these and remove the unnecessary function. Also, the pool is about to be freed so there's no need to poison the page data since we only check for poison on alloc, which can't be done on a freed pool. Link: https://lkml.kernel.org/r/20230126215125.4069751-10-kbusch@meta.com Fixes: 2d55c16c0c54 ("dmapool: create/destroy cleanup") Signed-off-by: Keith Busch <kbusch@kernel.org> Reviewed-by: Christoph Hellwig <hch@lst.de> Cc: Matthew Wilcox <willy@infradead.org> Cc: Tony Battersby <tonyb@cybernetics.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-05-06dmapool: consolidate page initializationKeith Busch1-4/+3
Various fields of the dma pool are set in different places. Move it all to one function. Link: https://lkml.kernel.org/r/20230126215125.4069751-9-kbusch@meta.com Fixes: 2d55c16c0c54 ("dmapool: create/destroy cleanup") Signed-off-by: Keith Busch <kbusch@kernel.org> Reviewed-by: Christoph Hellwig <hch@lst.de> Cc: Matthew Wilcox <willy@infradead.org> Cc: Tony Battersby <tonyb@cybernetics.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-05-06dmapool: rearrange page alloc failure handlingKeith Busch1-7/+9
Handle the error in a condition so the good path can be in the normal flow. Link: https://lkml.kernel.org/r/20230126215125.4069751-8-kbusch@meta.com Fixes: 2d55c16c0c54 ("dmapool: create/destroy cleanup") Signed-off-by: Keith Busch <kbusch@kernel.org> Reviewed-by: Christoph Hellwig <hch@lst.de> Cc: Matthew Wilcox <willy@infradead.org> Cc: Tony Battersby <tonyb@cybernetics.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-05-06dmapool: move debug code to own functionsKeith Busch1-51/+77
Clean up the normal path by moving the debug code outside it. Link: https://lkml.kernel.org/r/20230126215125.4069751-7-kbusch@meta.com Fixes: 2d55c16c0c54 ("dmapool: create/destroy cleanup") Signed-off-by: Keith Busch <kbusch@kernel.org> Reviewed-by: Christoph Hellwig <hch@lst.de> Cc: Matthew Wilcox <willy@infradead.org> Cc: Tony Battersby <tonyb@cybernetics.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-05-06dmapool: speedup DMAPOOL_DEBUG with init_on_allocTony Battersby1-1/+1
Avoid double-memset of the same allocated memory in dma_pool_alloc() when both DMAPOOL_DEBUG is enabled and init_on_alloc=1. Link: https://lkml.kernel.org/r/20230126215125.4069751-6-kbusch@meta.com Fixes: 2d55c16c0c54 ("dmapool: create/destroy cleanup") Signed-off-by: Tony Battersby <tonyb@cybernetics.com> Signed-off-by: Keith Busch <kbusch@kernel.org> Reviewed-by: Christoph Hellwig <hch@lst.de> Cc: Matthew Wilcox <willy@infradead.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2023-05-06dmapool: cleanup integer typesTony Battersby1-8/+11
To represent the size of a single allocation, dmapool currently uses 'unsigned int' in some places and 'size_t' in other places. Standardize on 'unsigned int' to reduce overhead, but use 'size_t' when counting all the blocks in the entire pool. Link: https://lkml.kernel.org/r/20230126215125.4069751-5-kbusch@meta.com Fixes: 2d55c16c0c54 ("dmapool: create/destroy cleanup") Signed-off-by: Tony Battersby <tonyb@cybernetics.com> Signed-off-by: Keith Busch <kbusch@kernel.org> Reviewed-by: Christoph Hellwig <hch@lst.de> Cc: Matthew Wilcox <willy@infradead.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Copyright © 1996 – 2023 Jason A. Donenfeld. All Rights Reverse Engineered.