diff options
304 files changed, 3067 insertions, 1714 deletions
@@ -241,11 +241,13 @@ Jisheng Zhang <jszhang@kernel.org> <Jisheng.Zhang@synaptics.com> Johan Hovold <johan@kernel.org> <jhovold@gmail.com> Johan Hovold <johan@kernel.org> <johan@hovoldconsulting.com> John Crispin <john@phrozen.org> <blogic@openwrt.org> +John Fastabend <john.fastabend@gmail.com> <john.r.fastabend@intel.com> John Keeping <john@keeping.me.uk> <john@metanate.com> John Paul Adrian Glaubitz <glaubitz@physik.fu-berlin.de> John Stultz <johnstul@us.ibm.com> <jon.toppins+linux@gmail.com> <jtoppins@cumulusnetworks.com> <jon.toppins+linux@gmail.com> <jtoppins@redhat.com> +Jonas Gorski <jonas.gorski@gmail.com> <jogo@openwrt.org> Jordan Crouse <jordan@cosmicpenguin.net> <jcrouse@codeaurora.org> <josh@joshtriplett.org> <josh@freedesktop.org> <josh@joshtriplett.org> <josh@kernel.org> @@ -453,6 +455,8 @@ Sebastian Reichel <sre@kernel.org> <sre@debian.org> Sedat Dilek <sedat.dilek@gmail.com> <sedat.dilek@credativ.de> Seth Forshee <sforshee@kernel.org> <seth.forshee@canonical.com> Shannon Nelson <shannon.nelson@amd.com> <snelson@pensando.io> +Shannon Nelson <shannon.nelson@amd.com> <shannon.nelson@intel.com> +Shannon Nelson <shannon.nelson@amd.com> <shannon.nelson@oracle.com> Shiraz Hashim <shiraz.linux.kernel@gmail.com> <shiraz.hashim@st.com> Shuah Khan <shuah@kernel.org> <shuahkhan@gmail.com> Shuah Khan <shuah@kernel.org> <shuah.khan@hp.com> diff --git a/Documentation/ABI/testing/sysfs-driver-ufs b/Documentation/ABI/testing/sysfs-driver-ufs index d5f44fc5b9dc..e487f969a15e 100644 --- a/Documentation/ABI/testing/sysfs-driver-ufs +++ b/Documentation/ABI/testing/sysfs-driver-ufs @@ -994,7 +994,7 @@ Description: This file shows the amount of physical memory needed What: /sys/bus/platform/drivers/ufshcd/*/rpm_lvl What: /sys/bus/platform/devices/*.ufs/rpm_lvl Date: September 2014 -Contact: Subhash Jadavani <subhashj@codeaurora.org> +Contact: Can Guo <quic_cang@quicinc.com> Description: This entry could be used to set or show the UFS device runtime power management level. The current driver implementation supports 7 levels with next target states: @@ -1021,7 +1021,7 @@ Description: This entry could be used to set or show the UFS device What: /sys/bus/platform/drivers/ufshcd/*/rpm_target_dev_state What: /sys/bus/platform/devices/*.ufs/rpm_target_dev_state Date: February 2018 -Contact: Subhash Jadavani <subhashj@codeaurora.org> +Contact: Can Guo <quic_cang@quicinc.com> Description: This entry shows the target power mode of an UFS device for the chosen runtime power management level. @@ -1030,7 +1030,7 @@ Description: This entry shows the target power mode of an UFS device What: /sys/bus/platform/drivers/ufshcd/*/rpm_target_link_state What: /sys/bus/platform/devices/*.ufs/rpm_target_link_state Date: February 2018 -Contact: Subhash Jadavani <subhashj@codeaurora.org> +Contact: Can Guo <quic_cang@quicinc.com> Description: This entry shows the target state of an UFS UIC link for the chosen runtime power management level. @@ -1039,7 +1039,7 @@ Description: This entry shows the target state of an UFS UIC link What: /sys/bus/platform/drivers/ufshcd/*/spm_lvl What: /sys/bus/platform/devices/*.ufs/spm_lvl Date: September 2014 -Contact: Subhash Jadavani <subhashj@codeaurora.org> +Contact: Can Guo <quic_cang@quicinc.com> Description: This entry could be used to set or show the UFS device system power management level. The current driver implementation supports 7 levels with next target states: @@ -1066,7 +1066,7 @@ Description: This entry could be used to set or show the UFS device What: /sys/bus/platform/drivers/ufshcd/*/spm_target_dev_state What: /sys/bus/platform/devices/*.ufs/spm_target_dev_state Date: February 2018 -Contact: Subhash Jadavani <subhashj@codeaurora.org> +Contact: Can Guo <quic_cang@quicinc.com> Description: This entry shows the target power mode of an UFS device for the chosen system power management level. @@ -1075,7 +1075,7 @@ Description: This entry shows the target power mode of an UFS device What: /sys/bus/platform/drivers/ufshcd/*/spm_target_link_state What: /sys/bus/platform/devices/*.ufs/spm_target_link_state Date: February 2018 -Contact: Subhash Jadavani <subhashj@codeaurora.org> +Contact: Can Guo <quic_cang@quicinc.com> Description: This entry shows the target state of an UFS UIC link for the chosen system power management level. @@ -1084,7 +1084,7 @@ Description: This entry shows the target state of an UFS UIC link What: /sys/bus/platform/drivers/ufshcd/*/monitor/monitor_enable What: /sys/bus/platform/devices/*.ufs/monitor/monitor_enable Date: January 2021 -Contact: Can Guo <cang@codeaurora.org> +Contact: Can Guo <quic_cang@quicinc.com> Description: This file shows the status of performance monitor enablement and it can be used to start/stop the monitor. When the monitor is stopped, the performance data collected is also cleared. @@ -1092,7 +1092,7 @@ Description: This file shows the status of performance monitor enablement What: /sys/bus/platform/drivers/ufshcd/*/monitor/monitor_chunk_size What: /sys/bus/platform/devices/*.ufs/monitor/monitor_chunk_size Date: January 2021 -Contact: Can Guo <cang@codeaurora.org> +Contact: Can Guo <quic_cang@quicinc.com> Description: This file tells the monitor to focus on requests transferring data of specific chunk size (in Bytes). 0 means any chunk size. It can only be changed when monitor is disabled. @@ -1100,7 +1100,7 @@ Description: This file tells the monitor to focus on requests transferring What: /sys/bus/platform/drivers/ufshcd/*/monitor/read_total_sectors What: /sys/bus/platform/devices/*.ufs/monitor/read_total_sectors Date: January 2021 -Contact: Can Guo <cang@codeaurora.org> +Contact: Can Guo <quic_cang@quicinc.com> Description: This file shows how many sectors (in 512 Bytes) have been sent from device to host after monitor gets started. @@ -1109,7 +1109,7 @@ Description: This file shows how many sectors (in 512 Bytes) have been What: /sys/bus/platform/drivers/ufshcd/*/monitor/read_total_busy What: /sys/bus/platform/devices/*.ufs/monitor/read_total_busy Date: January 2021 -Contact: Can Guo <cang@codeaurora.org> +Contact: Can Guo <quic_cang@quicinc.com> Description: This file shows how long (in micro seconds) has been spent sending data from device to host after monitor gets started. @@ -1118,7 +1118,7 @@ Description: This file shows how long (in micro seconds) has been spent What: /sys/bus/platform/drivers/ufshcd/*/monitor/read_nr_requests What: /sys/bus/platform/devices/*.ufs/monitor/read_nr_requests Date: January 2021 -Contact: Can Guo <cang@codeaurora.org> +Contact: Can Guo <quic_cang@quicinc.com> Description: This file shows how many read requests have been sent after monitor gets started. @@ -1127,7 +1127,7 @@ Description: This file shows how many read requests have been sent after What: /sys/bus/platform/drivers/ufshcd/*/monitor/read_req_latency_max What: /sys/bus/platform/devices/*.ufs/monitor/read_req_latency_max Date: January 2021 -Contact: Can Guo <cang@codeaurora.org> +Contact: Can Guo <quic_cang@quicinc.com> Description: This file shows the maximum latency (in micro seconds) of read requests after monitor gets started. @@ -1136,7 +1136,7 @@ Description: This file shows the maximum latency (in micro seconds) of What: /sys/bus/platform/drivers/ufshcd/*/monitor/read_req_latency_min What: /sys/bus/platform/devices/*.ufs/monitor/read_req_latency_min Date: January 2021 -Contact: Can Guo <cang@codeaurora.org> +Contact: Can Guo <quic_cang@quicinc.com> Description: This file shows the minimum latency (in micro seconds) of read requests after monitor gets started. @@ -1145,7 +1145,7 @@ Description: This file shows the minimum latency (in micro seconds) of What: /sys/bus/platform/drivers/ufshcd/*/monitor/read_req_latency_avg What: /sys/bus/platform/devices/*.ufs/monitor/read_req_latency_avg Date: January 2021 -Contact: Can Guo <cang@codeaurora.org> +Contact: Can Guo <quic_cang@quicinc.com> Description: This file shows the average latency (in micro seconds) of read requests after monitor gets started. @@ -1154,7 +1154,7 @@ Description: This file shows the average latency (in micro seconds) of What: /sys/bus/platform/drivers/ufshcd/*/monitor/read_req_latency_sum What: /sys/bus/platform/devices/*.ufs/monitor/read_req_latency_sum Date: January 2021 -Contact: Can Guo <cang@codeaurora.org> +Contact: Can Guo <quic_cang@quicinc.com> Description: This file shows the total latency (in micro seconds) of read requests sent after monitor gets started. @@ -1163,7 +1163,7 @@ Description: This file shows the total latency (in micro seconds) of What: /sys/bus/platform/drivers/ufshcd/*/monitor/write_total_sectors What: /sys/bus/platform/devices/*.ufs/monitor/write_total_sectors Date: January 2021 -Contact: Can Guo <cang@codeaurora.org> +Contact: Can Guo <quic_cang@quicinc.com> Description: This file shows how many sectors (in 512 Bytes) have been sent from host to device after monitor gets started. @@ -1172,7 +1172,7 @@ Description: This file shows how many sectors (in 512 Bytes) have been sent What: /sys/bus/platform/drivers/ufshcd/*/monitor/write_total_busy What: /sys/bus/platform/devices/*.ufs/monitor/write_total_busy Date: January 2021 -Contact: Can Guo <cang@codeaurora.org> +Contact: Can Guo <quic_cang@quicinc.com> Description: This file shows how long (in micro seconds) has been spent sending data from host to device after monitor gets started. @@ -1181,7 +1181,7 @@ Description: This file shows how long (in micro seconds) has been spent What: /sys/bus/platform/drivers/ufshcd/*/monitor/write_nr_requests What: /sys/bus/platform/devices/*.ufs/monitor/write_nr_requests Date: January 2021 -Contact: Can Guo <cang@codeaurora.org> +Contact: Can Guo <quic_cang@quicinc.com> Description: This file shows how many write requests have been sent after monitor gets started. @@ -1190,7 +1190,7 @@ Description: This file shows how many write requests have been sent after What: /sys/bus/platform/drivers/ufshcd/*/monitor/write_req_latency_max What: /sys/bus/platform/devices/*.ufs/monitor/write_req_latency_max Date: January 2021 -Contact: Can Guo <cang@codeaurora.org> +Contact: Can Guo <quic_cang@quicinc.com> Description: This file shows the maximum latency (in micro seconds) of write requests after monitor gets started. @@ -1199,7 +1199,7 @@ Description: This file shows the maximum latency (in micro seconds) of write What: /sys/bus/platform/drivers/ufshcd/*/monitor/write_req_latency_min What: /sys/bus/platform/devices/*.ufs/monitor/write_req_latency_min Date: January 2021 -Contact: Can Guo <cang@codeaurora.org> +Contact: Can Guo <quic_cang@quicinc.com> Description: This file shows the minimum latency (in micro seconds) of write requests after monitor gets started. @@ -1208,7 +1208,7 @@ Description: This file shows the minimum latency (in micro seconds) of write What: /sys/bus/platform/drivers/ufshcd/*/monitor/write_req_latency_avg What: /sys/bus/platform/devices/*.ufs/monitor/write_req_latency_avg Date: January 2021 -Contact: Can Guo <cang@codeaurora.org> +Contact: Can Guo <quic_cang@quicinc.com> Description: This file shows the average latency (in micro seconds) of write requests after monitor gets started. @@ -1217,7 +1217,7 @@ Description: This file shows the average latency (in micro seconds) of write What: /sys/bus/platform/drivers/ufshcd/*/monitor/write_req_latency_sum What: /sys/bus/platform/devices/*.ufs/monitor/write_req_latency_sum Date: January 2021 -Contact: Can Guo <cang@codeaurora.org> +Contact: Can Guo <quic_cang@quicinc.com> Description: This file shows the total latency (in micro seconds) of write requests after monitor gets started. @@ -1226,7 +1226,7 @@ Description: This file shows the total latency (in micro seconds) of write What: /sys/bus/platform/drivers/ufshcd/*/device_descriptor/wb_presv_us_en What: /sys/bus/platform/devices/*.ufs/device_descriptor/wb_presv_us_en Date: June 2020 -Contact: Asutosh Das <asutoshd@codeaurora.org> +Contact: Asutosh Das <quic_asutoshd@quicinc.com> Description: This entry shows if preserve user-space was configured The file is read only. @@ -1234,7 +1234,7 @@ Description: This entry shows if preserve user-space was configured What: /sys/bus/platform/drivers/ufshcd/*/device_descriptor/wb_shared_alloc_units What: /sys/bus/platform/devices/*.ufs/device_descriptor/wb_shared_alloc_units Date: June 2020 -Contact: Asutosh Das <asutoshd@codeaurora.org> +Contact: Asutosh Das <quic_asutoshd@quicinc.com> Description: This entry shows the shared allocated units of WB buffer The file is read only. @@ -1242,7 +1242,7 @@ Description: This entry shows the shared allocated units of WB buffer What: /sys/bus/platform/drivers/ufshcd/*/device_descriptor/wb_type What: /sys/bus/platform/devices/*.ufs/device_descriptor/wb_type Date: June 2020 -Contact: Asutosh Das <asutoshd@codeaurora.org> +Contact: Asutosh Das <quic_asutoshd@quicinc.com> Description: This entry shows the configured WB type. 0x1 for shared buffer mode. 0x0 for dedicated buffer mode. @@ -1251,7 +1251,7 @@ Description: This entry shows the configured WB type. What: /sys/bus/platform/drivers/ufshcd/*/geometry_descriptor/wb_buff_cap_adj What: /sys/bus/platform/devices/*.ufs/geometry_descriptor/wb_buff_cap_adj Date: June 2020 -Contact: Asutosh Das <asutoshd@codeaurora.org> +Contact: Asutosh Das <quic_asutoshd@quicinc.com> Description: This entry shows the total user-space decrease in shared buffer mode. The value of this parameter is 3 for TLC NAND when SLC mode @@ -1262,7 +1262,7 @@ Description: This entry shows the total user-space decrease in shared What: /sys/bus/platform/drivers/ufshcd/*/geometry_descriptor/wb_max_alloc_units What: /sys/bus/platform/devices/*.ufs/geometry_descriptor/wb_max_alloc_units Date: June 2020 -Contact: Asutosh Das <asutoshd@codeaurora.org> +Contact: Asutosh Das <quic_asutoshd@quicinc.com> Description: This entry shows the Maximum total WriteBooster Buffer size which is supported by the entire device. @@ -1271,7 +1271,7 @@ Description: This entry shows the Maximum total WriteBooster Buffer size What: /sys/bus/platform/drivers/ufshcd/*/geometry_descriptor/wb_max_wb_luns What: /sys/bus/platform/devices/*.ufs/geometry_descriptor/wb_max_wb_luns Date: June 2020 -Contact: Asutosh Das <asutoshd@codeaurora.org> +Contact: Asutosh Das <quic_asutoshd@quicinc.com> Description: This entry shows the maximum number of luns that can support WriteBooster. @@ -1280,7 +1280,7 @@ Description: This entry shows the maximum number of luns that can support What: /sys/bus/platform/drivers/ufshcd/*/geometry_descriptor/wb_sup_red_type What: /sys/bus/platform/devices/*.ufs/geometry_descriptor/wb_sup_red_type Date: June 2020 -Contact: Asutosh Das <asutoshd@codeaurora.org> +Contact: Asutosh Das <quic_asutoshd@quicinc.com> Description: The supportability of user space reduction mode and preserve user space mode. 00h: WriteBooster Buffer can be configured only in @@ -1295,7 +1295,7 @@ Description: The supportability of user space reduction mode What: /sys/bus/platform/drivers/ufshcd/*/geometry_descriptor/wb_sup_wb_type What: /sys/bus/platform/devices/*.ufs/geometry_descriptor/wb_sup_wb_type Date: June 2020 -Contact: Asutosh Das <asutoshd@codeaurora.org> +Contact: Asutosh Das <quic_asutoshd@quicinc.com> Description: The supportability of WriteBooster Buffer type. === ========================================================== @@ -1310,7 +1310,7 @@ Description: The supportability of WriteBooster Buffer type. What: /sys/bus/platform/drivers/ufshcd/*/flags/wb_enable What: /sys/bus/platform/devices/*.ufs/flags/wb_enable Date: June 2020 -Contact: Asutosh Das <asutoshd@codeaurora.org> +Contact: Asutosh Das <quic_asutoshd@quicinc.com> Description: This entry shows the status of WriteBooster. == ============================ @@ -1323,7 +1323,7 @@ Description: This entry shows the status of WriteBooster. What: /sys/bus/platform/drivers/ufshcd/*/flags/wb_flush_en What: /sys/bus/platform/devices/*.ufs/flags/wb_flush_en Date: June 2020 -Contact: Asutosh Das <asutoshd@codeaurora.org> +Contact: Asutosh Das <quic_asutoshd@quicinc.com> Description: This entry shows if flush is enabled. == ================================= @@ -1336,7 +1336,7 @@ Description: This entry shows if flush is enabled. What: /sys/bus/platform/drivers/ufshcd/*/flags/wb_flush_during_h8 What: /sys/bus/platform/devices/*.ufs/flags/wb_flush_during_h8 Date: June 2020 -Contact: Asutosh Das <asutoshd@codeaurora.org> +Contact: Asutosh Das <quic_asutoshd@quicinc.com> Description: Flush WriteBooster Buffer during hibernate state. == ================================================= @@ -1351,7 +1351,7 @@ Description: Flush WriteBooster Buffer during hibernate state. What: /sys/bus/platform/drivers/ufshcd/*/attributes/wb_avail_buf What: /sys/bus/platform/devices/*.ufs/attributes/wb_avail_buf Date: June 2020 -Contact: Asutosh Das <asutoshd@codeaurora.org> +Contact: Asutosh Das <quic_asutoshd@quicinc.com> Description: This entry shows the amount of unused WriteBooster buffer available. @@ -1360,7 +1360,7 @@ Description: This entry shows the amount of unused WriteBooster buffer What: /sys/bus/platform/drivers/ufshcd/*/attributes/wb_cur_buf What: /sys/bus/platform/devices/*.ufs/attributes/wb_cur_buf Date: June 2020 -Contact: Asutosh Das <asutoshd@codeaurora.org> +Contact: Asutosh Das <quic_asutoshd@quicinc.com> Description: This entry shows the amount of unused current buffer. The file is read only. @@ -1368,7 +1368,7 @@ Description: This entry shows the amount of unused current buffer. What: /sys/bus/platform/drivers/ufshcd/*/attributes/wb_flush_status What: /sys/bus/platform/devices/*.ufs/attributes/wb_flush_status Date: June 2020 -Contact: Asutosh Das <asutoshd@codeaurora.org> +Contact: Asutosh Das <quic_asutoshd@quicinc.com> Description: This entry shows the flush operation status. @@ -1385,7 +1385,7 @@ Description: This entry shows the flush operation status. What: /sys/bus/platform/drivers/ufshcd/*/attributes/wb_life_time_est What: /sys/bus/platform/devices/*.ufs/attributes/wb_life_time_est Date: June 2020 -Contact: Asutosh Das <asutoshd@codeaurora.org> +Contact: Asutosh Das <quic_asutoshd@quicinc.com> Description: This entry shows an indication of the WriteBooster Buffer lifetime based on the amount of performed program/erase cycles @@ -1399,7 +1399,7 @@ Description: This entry shows an indication of the WriteBooster Buffer What: /sys/class/scsi_device/*/device/unit_descriptor/wb_buf_alloc_units Date: June 2020 -Contact: Asutosh Das <asutoshd@codeaurora.org> +Contact: Asutosh Das <quic_asutoshd@quicinc.com> Description: This entry shows the configured size of WriteBooster buffer. 0400h corresponds to 4GB. diff --git a/Documentation/riscv/hwprobe.rst b/Documentation/riscv/hwprobe.rst index 19165ebd82ba..933c715065d6 100644 --- a/Documentation/riscv/hwprobe.rst +++ b/Documentation/riscv/hwprobe.rst @@ -49,7 +49,7 @@ The following keys are defined: privileged ISA, with the following known exceptions (more exceptions may be added, but only if it can be demonstrated that the user ABI is not broken): - * The :fence.i: instruction cannot be directly executed by userspace + * The ``fence.i`` instruction cannot be directly executed by userspace programs (it may still be executed in userspace via a kernel-controlled mechanism such as the vDSO). diff --git a/MAINTAINERS b/MAINTAINERS index 990e3fce753c..019b8017ab3c 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -4124,6 +4124,13 @@ F: Documentation/devicetree/bindings/spi/brcm,bcm63xx-hsspi.yaml F: drivers/spi/spi-bcm63xx-hsspi.c F: drivers/spi/spi-bcmbca-hsspi.c +BROADCOM BCM6348/BCM6358 SPI controller DRIVER +M: Jonas Gorski <jonas.gorski@gmail.com> +L: linux-spi@vger.kernel.org +S: Odd Fixes +F: Documentation/devicetree/bindings/spi/spi-bcm63xx.txt +F: drivers/spi/spi-bcm63xx.c + BROADCOM ETHERNET PHY DRIVERS M: Florian Fainelli <florian.fainelli@broadcom.com> R: Broadcom internal kernel review list <bcm-kernel-feedback-list@broadcom.com> @@ -8684,8 +8691,11 @@ S: Maintained F: drivers/input/touchscreen/resistive-adc-touch.c GENERIC STRING LIBRARY +M: Kees Cook <keescook@chromium.org> R: Andy Shevchenko <andy@kernel.org> -S: Maintained +L: linux-hardening@vger.kernel.org +S: Supported +T: git git://git.kernel.org/pub/scm/linux/kernel/git/kees/linux.git for-next/hardening F: include/linux/string.h F: include/linux/string_choices.h F: include/linux/string_helpers.h @@ -13980,7 +13990,7 @@ T: git https://git.kernel.org/pub/scm/linux/kernel/git/conor/linux.git/ F: drivers/soc/microchip/ MICROCHIP SPI DRIVER -M: Tudor Ambarus <tudor.ambarus@linaro.org> +M: Ryan Wanner <ryan.wanner@microchip.com> S: Supported F: drivers/spi/spi-atmel.* @@ -2,7 +2,7 @@ VERSION = 6 PATCHLEVEL = 5 SUBLEVEL = 0 -EXTRAVERSION = -rc1 +EXTRAVERSION = -rc2 NAME = Hurr durr I'ma ninja sloth # *DOCUMENTATION* diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c index 145b540ec34f..ec2174838f2a 100644 --- a/arch/arm64/net/bpf_jit_comp.c +++ b/arch/arm64/net/bpf_jit_comp.c @@ -322,7 +322,13 @@ static int build_prologue(struct jit_ctx *ctx, bool ebpf_from_cbpf) * */ - emit_bti(A64_BTI_C, ctx); + /* bpf function may be invoked by 3 instruction types: + * 1. bl, attached via freplace to bpf prog via short jump + * 2. br, attached via freplace to bpf prog via long jump + * 3. blr, working as a function pointer, used by emit_call. + * So BTI_JC should used here to support both br and blr. + */ + emit_bti(A64_BTI_JC, ctx); emit(A64_MOV(1, A64_R(9), A64_LR), ctx); emit(A64_NOP, ctx); diff --git a/arch/powerpc/include/asm/book3s/64/hash-4k.h b/arch/powerpc/include/asm/book3s/64/hash-4k.h index b6ac4f86c87b..6472b08fa1b0 100644 --- a/arch/powerpc/include/asm/book3s/64/hash-4k.h +++ b/arch/powerpc/include/asm/book3s/64/hash-4k.h @@ -136,12 +136,6 @@ static inline int hash__pmd_trans_huge(pmd_t pmd) return 0; } -static inline int hash__pmd_same(pmd_t pmd_a, pmd_t pmd_b) -{ - BUG(); - return 0; -} - static inline pmd_t hash__pmd_mkhuge(pmd_t pmd) { BUG(); diff --git a/arch/powerpc/include/asm/book3s/64/hash-64k.h b/arch/powerpc/include/asm/book3s/64/hash-64k.h index 338e62fbea0b..0bf6fd0bf42a 100644 --- a/arch/powerpc/include/asm/book3s/64/hash-64k.h +++ b/arch/powerpc/include/asm/book3s/64/hash-64k.h @@ -263,11 +263,6 @@ static inline int hash__pmd_trans_huge(pmd_t pmd) (_PAGE_PTE | H_PAGE_THP_HUGE)); } -static inline int hash__pmd_same(pmd_t pmd_a, pmd_t pmd_b) -{ - return (((pmd_raw(pmd_a) ^ pmd_raw(pmd_b)) & ~cpu_to_be64(_PAGE_HPTEFLAGS)) == 0); -} - static inline pmd_t hash__pmd_mkhuge(pmd_t pmd) { return __pmd(pmd_val(pmd) | (_PAGE_PTE | H_PAGE_THP_HUGE)); diff --git a/arch/powerpc/include/asm/book3s/64/hash.h b/arch/powerpc/include/asm/book3s/64/hash.h index 17e7a778c856..d4a19e6547ac 100644 --- a/arch/powerpc/include/asm/book3s/64/hash.h +++ b/arch/powerpc/include/asm/book3s/64/hash.h @@ -132,6 +132,11 @@ static inline int get_region_id(unsigned long ea) return region_id; } +static inline int hash__pmd_same(pmd_t pmd_a, pmd_t pmd_b) +{ + return (((pmd_raw(pmd_a) ^ pmd_raw(pmd_b)) & ~cpu_to_be64(_PAGE_HPTEFLAGS)) == 0); +} + #define hash__pmd_bad(pmd) (pmd_val(pmd) & H_PMD_BAD_BITS) #define hash__pud_bad(pud) (pud_val(pud) & H_PUD_BAD_BITS) static inline int hash__p4d_bad(p4d_t p4d) diff --git a/arch/powerpc/kernel/exceptions-64e.S b/arch/powerpc/kernel/exceptions-64e.S index 3f86091e68b3..7ab4c8c0f1ab 100644 --- a/arch/powerpc/kernel/exceptions-64e.S +++ b/arch/powerpc/kernel/exceptions-64e.S @@ -5,6 +5,7 @@ * Copyright (C) 2007 Ben. Herrenschmidt (benh@kernel.crashing.org), IBM Corp. */ +#include <linux/linkage.h> #include <linux/threads.h> #include <asm/reg.h> #include <asm/page.h> @@ -66,7 +67,7 @@ #define SPECIAL_EXC_LOAD(reg, name) \ ld reg, (SPECIAL_EXC_##name * 8 + SPECIAL_EXC_FRAME_OFFS)(r1) -special_reg_save: +SYM_CODE_START_LOCAL(special_reg_save) /* * We only need (or have stack space) to save this stuff if * we interrupted the kernel. @@ -131,8 +132,9 @@ END_FTR_SECTION_IFSET(CPU_FTR_EMB_HV) SPECIAL_EXC_STORE(r10,CSRR1) blr +SYM_CODE_END(special_reg_save) -ret_from_level_except: +SYM_CODE_START_LOCAL(ret_from_level_except) ld r3,_MSR(r1) andi. r3,r3,MSR_PR beq 1f @@ -206,6 +208,7 @@ END_FTR_SECTION_IFSET(CPU_FTR_EMB_HV) mtxer r11 blr +SYM_CODE_END(ret_from_level_except) .macro ret_from_level srr0 srr1 paca_ex scratch bl ret_from_level_except @@ -232,13 +235,15 @@ END_FTR_SECTION_IFSET(CPU_FTR_EMB_HV) mfspr r13,\scratch .endm -ret_from_crit_except: +SYM_CODE_START_LOCAL(ret_from_crit_except) ret_from_level SPRN_CSRR0 SPRN_CSRR1 PACA_EXCRIT SPRN_SPRG_CRIT_SCRATCH rfci +SYM_CODE_END(ret_from_crit_except) -ret_from_mc_except: +SYM_CODE_START_LOCAL(ret_from_mc_except) ret_from_level SPRN_MCSRR0 SPRN_MCSRR1 PACA_EXMC SPRN_SPRG_MC_SCRATCH rfmci +SYM_CODE_END(ret_from_mc_except) /* Exception prolog code for all exceptions */ #define EXCEPTION_PROLOG(n, intnum, type, addition) \ @@ -978,20 +983,22 @@ masked_interrupt_book3e_0x2c0: * r14 and r15 containing the fault address and error code, with the * original values stashed away in the PACA */ -storage_fault_common: +SYM_CODE_START_LOCAL(storage_fault_common) addi r3,r1,STACK_INT_FRAME_REGS bl do_page_fault b interrupt_return +SYM_CODE_END(storage_fault_common) /* * Alignment exception doesn't fit entirely in the 0x100 bytes so it * continues here. */ -alignment_more: +SYM_CODE_START_LOCAL(alignment_more) addi r3,r1,STACK_INT_FRAME_REGS bl alignment_exception REST_NVGPRS(r1) b interrupt_return +SYM_CODE_END(alignment_more) /* * Trampolines used when spotting a bad kernel stack pointer in @@ -1030,8 +1037,7 @@ BAD_STACK_TRAMPOLINE(0xe00) BAD_STACK_TRAMPOLINE(0xf00) BAD_STACK_TRAMPOLINE(0xf20) - .globl bad_stack_book3e -bad_stack_book3e: +_GLOBAL(bad_stack_book3e) /* XXX: Needs to make SPRN_SPRG_GEN depend on exception type */ mfspr r10,SPRN_SRR0; /* read SRR0 before touching stack */ ld r1,PACAEMERGSP(r13) @@ -1285,8 +1291,7 @@ have_hes: * ever takes any parameters, the SCOM code must also be updated to * provide them. */ - .globl a2_tlbinit_code_start -a2_tlbinit_code_start: +_GLOBAL(a2_tlbinit_code_start) ori r11,r3,MAS0_WQ_ALLWAYS oris r11,r11,MAS0_ESEL(3)@h /* Use way 3: workaround A2 erratum 376 */ @@ -1479,8 +1484,7 @@ _GLOBAL(book3e_secondary_thread_init) mflr r28 b 3b - .globl init_core_book3e -init_core_book3e: +_GLOBAL(init_core_book3e) /* Establish the interrupt vector base */ tovirt(r2,r2) LOAD_REG_ADDR(r3, interrupt_base_book3e) @@ -1488,7 +1492,7 @@ init_core_book3e: sync blr -init_thread_book3e: +SYM_CODE_START_LOCAL(init_thread_book3e) lis r3,(SPRN_EPCR_ICM | SPRN_EPCR_GICM)@h mtspr SPRN_EPCR,r3 @@ -1502,6 +1506,7 @@ init_thread_book3e: mtspr SPRN_TSR,r3 blr +SYM_CODE_END(init_thread_book3e) _GLOBAL(__setup_base_ivors) SET_IVOR(0, 0x020) /* Critical Input */ diff --git a/arch/powerpc/kernel/security.c b/arch/powerpc/kernel/security.c index 206475e3e0b4..4856e1a5161c 100644 --- a/arch/powerpc/kernel/security.c +++ b/arch/powerpc/kernel/security.c @@ -364,26 +364,27 @@ ssize_t cpu_show_spec_store_bypass(struct device *dev, struct device_attribute * static int ssb_prctl_get(struct task_struct *task) { + /* + * The STF_BARRIER feature is on by default, so if it's off that means + * firmware has explicitly said the CPU is not vulnerable via either + * the hypercall or device tree. + */ + if (!security_ftr_enabled(SEC_FTR_STF_BARRIER)) + return PR_SPEC_NOT_AFFECTED; + + /* + * If the system's CPU has no known barrier (see setup_stf_barrier()) + * then assume that the CPU is not vulnerable. + */ if (stf_enabled_flush_types == STF_BARRIER_NONE) - /* - * We don't have an explicit signal from firmware that we're - * vulnerable or not, we only have certain CPU revisions that - * are known to be vulnerable. - * - * We assume that if we're on another CPU, where the barrier is - * NONE, then we are not vulnerable. - */ return PR_SPEC_NOT_AFFECTED; - else - /* - * If we do have a barrier type then we are vulnerable. The - * barrier is not a global or per-process mitigation, so the - * only value we can report here is PR_SPEC_ENABLE, which - * appears as "vulnerable" in /proc. - */ - return PR_SPEC_ENABLE; - - return -EINVAL; + + /* + * Otherwise the CPU is vulnerable. The barrier is not a global or + * per-process mitigation, so the only value that can be reported here + * is PR_SPEC_ENABLE, which appears as "vulnerable" in /proc. + */ + return PR_SPEC_ENABLE; } int arch_prctl_spec_ctrl_get(struct task_struct *task, unsigned long which) diff --git a/arch/powerpc/mm/book3s64/hash_native.c b/arch/powerpc/mm/book3s64/hash_native.c index 9342e79870df..430d1d935a7c 100644 --- a/arch/powerpc/mm/book3s64/hash_native.c +++ b/arch/powerpc/mm/book3s64/hash_native.c @@ -328,10 +328,12 @@ static long native_hpte_insert(unsigned long hpte_group, unsigned long vpn, static long native_hpte_remove(unsigned long hpte_group) { + unsigned long hpte_v, flags; struct hash_pte *hptep; int i; int slot_offset; - unsigned long hpte_v; + + local_irq_save(flags); DBG_LOW(" remove(group=%lx)\n", hpte_group); @@ -356,13 +358,16 @@ static long native_hpte_remove(unsigned long hpte_group) slot_offset &= 0x7; } - if (i == HPTES_PER_GROUP) - return -1; + if (i == HPTES_PER_GROUP) { + i = -1; + goto out; + } /* Invalidate the hpte. NOTE: this also unlocks it */ release_hpte_lock(); hptep->v = 0; - +out: + local_irq_restore(flags); return i; } diff --git a/arch/riscv/kernel/cpufeature.c b/arch/riscv/kernel/cpufeature.c index bdcf460ea53d..a8f66c015229 100644 --- a/arch/riscv/kernel/cpufeature.c +++ b/arch/riscv/kernel/cpufeature.c @@ -318,18 +318,13 @@ void __init riscv_fill_hwcap(void) } /* - * Linux requires the following extensions, so we may as well - * always set them. - */ - set_bit(RISCV_ISA_EXT_ZICSR, isainfo->isa); - set_bit(RISCV_ISA_EXT_ZIFENCEI, isainfo->isa); - - /* * These ones were as they were part of the base ISA when the * port & dt-bindings were upstreamed, and so can be set * unconditionally where `i` is in riscv,isa on DT systems. */ if (acpi_disabled) { + set_bit(RISCV_ISA_EXT_ZICSR, isainfo->isa); + set_bit(RISCV_ISA_EXT_ZIFENCEI, isainfo->isa); set_bit(RISCV_ISA_EXT_ZICNTR, isainfo->isa); set_bit(RISCV_ISA_EXT_ZIHPM, isainfo->isa); } diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c index 70fb31960b63..9ce504737d18 100644 --- a/arch/riscv/mm/init.c +++ b/arch/riscv/mm/init.c @@ -1346,7 +1346,7 @@ static void __init reserve_crashkernel(void) */ crash_base = memblock_phys_alloc_range(crash_size, PMD_SIZE, search_start, - min(search_end, (unsigned long) SZ_4G)); + min(search_end, (unsigned long)(SZ_4G - 1))); if (crash_base == 0) { /* Try again without restricting region to 32bit addressible memory */ crash_base = memblock_phys_alloc_range(crash_size, PMD_SIZE, diff --git a/arch/sparc/include/asm/cmpxchg_32.h b/arch/sparc/include/asm/cmpxchg_32.h index 7a1339533d1d..d0af82c240b7 100644 --- a/arch/sparc/include/asm/cmpxchg_32.h +++ b/arch/sparc/include/asm/cmpxchg_32.h @@ -15,7 +15,7 @@ unsigned long __xchg_u32(volatile u32 *m, u32 new); void __xchg_called_with_bad_pointer(void); -static inline unsigned long __arch_xchg(unsigned long x, __volatile__ void * ptr, int size) +static __always_inline unsigned long __arch_xchg(unsigned long x, __volatile__ void * ptr, int size) { switch (size) { case 4: diff --git a/arch/sparc/include/asm/cmpxchg_64.h b/arch/sparc/include/asm/cmpxchg_64.h index 66cd61dde9ec..3de25262c411 100644 --- a/arch/sparc/include/asm/cmpxchg_64.h +++ b/arch/sparc/include/asm/cmpxchg_64.h @@ -87,7 +87,7 @@ xchg16(__volatile__ unsigned short *m, unsigned short val) return (load32 & mask) >> bit_shift; } -static inline unsigned long +static __always_inline unsigned long __arch_xchg(unsigned long x, __volatile__ void * ptr, int size) { switch (size) { diff --git a/arch/um/kernel/um_arch.c b/arch/um/kernel/um_arch.c index 918fed7ad4d8..b1bfed0c8528 100644 --- a/arch/um/kernel/um_arch.c +++ b/arch/um/kernel/um_arch.c @@ -437,7 +437,7 @@ void __init arch_cpu_finalize_init(void) os_check_bugs(); } -void apply_ibt_endbr(s32 *start, s32 *end) +void apply_seal_endbr(s32 *start, s32 *end) { } diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S index 91397f58ac30..6e6af42e044a 100644 --- a/arch/x86/entry/entry_32.S +++ b/arch/x86/entry/entry_32.S @@ -720,26 +720,6 @@ SYM_CODE_END(__switch_to_asm) .popsection /* - * The unwinder expects the last frame on the stack to always be at the same - * offset from the end of the page, which allows it to validate the stack. - * Calling schedule_tail() directly would break that convention because its an - * asmlinkage function so its argument has to be pushed on the stack. This - * wrapper creates a proper "end of stack" frame header before the call. - */ -.pushsection .text, "ax" -SYM_FUNC_START(schedule_tail_wrapper) - FRAME_BEGIN - - pushl %eax - call schedule_tail - popl %eax - - FRAME_END - RET -SYM_FUNC_END(schedule_tail_wrapper) -.popsection - -/* * A newly forked process directly context switches into this address. * * eax: prev task we switched from @@ -747,29 +727,22 @@ SYM_FUNC_END(schedule_tail_wrapper) * edi: kernel thread arg */ .pushsection .text, "ax" -SYM_CODE_START(ret_from_fork) - call schedule_tail_wrapper +SYM_CODE_START(ret_from_fork_asm) + movl %esp, %edx /* regs */ - testl %ebx, %ebx - jnz 1f /* kernel threads are uncommon */ + /* return address for the stack unwinder */ + pushl $.Lsyscall_32_done -2: - /* When we fork, we trace the syscall return in the child, too. */ - movl %esp, %eax - call syscall_exit_to_user_mode - jmp .Lsyscall_32_done + FRAME_BEGIN + /* prev already in EAX */ + movl %ebx, %ecx /* fn */ + pushl %edi /* fn_arg */ + call ret_from_fork + addl $4, %esp + FRAME_END - /* kernel thread */ -1: movl %edi, %eax - CALL_NOSPEC ebx - /* - * A kernel thread is allowed to return here after successfully - * calling kernel_execve(). Exit to userspace to complete the execve() - * syscall. - */ - movl $0, PT_EAX(%esp) - jmp 2b -SYM_CODE_END(ret_from_fork) + RET +SYM_CODE_END(ret_from_fork_asm) .popsection SYM_ENTRY(__begin_SYSENTER_singlestep_region, SYM_L_GLOBAL, SYM_A_NONE) diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index f31e286c2977..91f6818884fa 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -284,36 +284,19 @@ SYM_FUNC_END(__switch_to_asm) * r12: kernel thread arg */ .pushsection .text, "ax" - __FUNC_ALIGN -SYM_CODE_START_NOALIGN(ret_from_fork) - UNWIND_HINT_END_OF_STACK +SYM_CODE_START(ret_from_fork_asm) + UNWIND_HINT_REGS ANNOTATE_NOENDBR // copy_thread CALL_DEPTH_ACCOUNT - movq %rax, %rdi - call schedule_tail /* rdi: 'prev' task parameter */ - testq %rbx, %rbx /* from kernel_thread? */ - jnz 1f /* kernel threads are uncommon */ + movq %rax, %rdi /* prev */ + movq %rsp, %rsi /* regs */ + movq %rbx, %rdx /* fn */ + movq %r12, %rcx /* fn_arg */ + call ret_from_fork -2: - UNWIND_HINT_REGS - movq %rsp, %rdi - call syscall_exit_to_user_mode /* returns with IRQs disabled */ jmp swapgs_restore_regs_and_return_to_usermode - -1: - /* kernel thread */ - UNWIND_HINT_END_OF_STACK - movq %r12, %rdi - CALL_NOSPEC rbx - /* - * A kernel thread is allowed to return here after successfully - * calling kernel_execve(). Exit to userspace to complete the execve() - * syscall. - */ - movq $0, RAX(%rsp) - jmp 2b -SYM_CODE_END(ret_from_fork) +SYM_CODE_END(ret_from_fork_asm) .popsection .macro DEBUG_ENTRY_ASSERT_IRQS_OFF diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index a149fafad813..2a284ba951b7 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -3993,6 +3993,13 @@ static int intel_pmu_hw_config(struct perf_event *event) struct perf_event *leader = event->group_leader; struct perf_event *sibling = NULL; + /* + * When this memload event is also the first event (no group + * exists yet), then there is no aux event before it. + */ + if (leader == event) + return -ENODATA; + if (!is_mem_loads_aux_event(leader)) { for_each_sibling_event(sibling, leader) { if (is_mem_loads_aux_event(sibling)) diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h index 6c15a622ad60..9c4da699e11a 100644 --- a/arch/x86/include/asm/alternative.h +++ b/arch/x86/include/asm/alternative.h @@ -96,7 +96,7 @@ extern void alternative_instructions(void); extern void apply_alternatives(struct alt_instr *start, struct alt_instr *end); extern void apply_retpolines(s32 *start, s32 *end); extern void apply_returns(s32 *start, s32 *end); -extern void apply_ibt_endbr(s32 *start, s32 *end); +extern void apply_seal_endbr(s32 *start, s32 *end); extern void apply_fineibt(s32 *start_retpoline, s32 *end_retpoine, s32 *start_cfi, s32 *end_cfi); diff --git a/arch/x86/include/asm/ibt.h b/arch/x86/include/asm/ibt.h index baae6b4fea23..1e59581d500c 100644 --- a/arch/x86/include/asm/ibt.h +++ b/arch/x86/include/asm/ibt.h @@ -34,7 +34,7 @@ /* * Create a dummy function pointer reference to prevent objtool from marking * the function as needing to be "sealed" (i.e. ENDBR converted to NOP by - * apply_ibt_endbr()). + * apply_seal_endbr()). */ #define IBT_NOSEAL(fname) \ ".pushsection .discard.ibt_endbr_noseal\n\t" \ diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index 55388c9f7601..1a65cf4acb2b 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -234,6 +234,10 @@ * JMP_NOSPEC and CALL_NOSPEC macros can be used instead of a simple * indirect jmp/call which may be susceptible to the Spectre variant 2 * attack. + * + * NOTE: these do not take kCFI into account and are thus not comparable to C + * indirect calls, take care when using. The target of these should be an ENDBR + * instruction irrespective of kCFI. */ .macro JMP_NOSPEC reg:req #ifdef CONFIG_RETPOLINE diff --git a/arch/x86/include/asm/switch_to.h b/arch/x86/include/asm/switch_to.h index 5c91305d09d2..f42dbf17f52b 100644 --- a/arch/x86/include/asm/switch_to.h +++ b/arch/x86/include/asm/switch_to.h @@ -12,7 +12,9 @@ struct task_struct *__switch_to_asm(struct task_struct *prev, __visible struct task_struct *__switch_to(struct task_struct *prev, struct task_struct *next); -asmlinkage void ret_from_fork(void); +asmlinkage void ret_from_fork_asm(void); +__visible void ret_from_fork(struct task_struct *prev, struct pt_regs *regs, + int (*fn)(void *), void *fn_arg); /* * This is the structure pointed to by thread.sp for an inactive task. The diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c index 72646d75b6ff..2dcf3a06af09 100644 --- a/arch/x86/kernel/alternative.c +++ b/arch/x86/kernel/alternative.c @@ -778,6 +778,8 @@ void __init_or_module noinline apply_returns(s32 *start, s32 *end) { } #ifdef CONFIG_X86_KERNEL_IBT +static void poison_cfi(void *addr); + static void __init_or_module poison_endbr(void *addr, bool warn) { u32 endbr, poison = gen_endbr_poison(); @@ -802,8 +804,11 @@ static void __init_or_module poison_endbr(void *addr, bool warn) /* * Generated by: objtool --ibt + * + * Seal the functions for indirect calls by clobbering the ENDBR instructions + * and the kCFI hash value. */ -void __init_or_module noinline apply_ibt_endbr(s32 *start, s32 *end) +void __init_or_module noinline apply_seal_endbr(s32 *start, s32 *end) { s32 *s; @@ -812,13 +817,13 @@ void __init_or_module noinline apply_ibt_endbr(s32 *start, s32 *end) poison_endbr(addr, true); if (IS_ENABLED(CONFIG_FINEIBT)) - poison_endbr(addr - 16, false); + poison_cfi(addr - 16); } } #else -void __init_or_module apply_ibt_endbr(s32 *start, s32 *end) { } +void __init_or_module apply_seal_endbr(s32 *start, s32 *end) { } #endif /* CONFIG_X86_KERNEL_IBT */ @@ -1063,6 +1068,17 @@ static int cfi_rewrite_preamble(s32 *start, s32 *end) return 0; } +static void cfi_rewrite_endbr(s32 *start, s32 *end) +{ + s32 *s; + + for (s = start; s < end; s++) { + void *addr = (void *)s + *s; + + poison_endbr(addr+16, false); + } +} + /* .retpoline_sites */ static int cfi_rand_callers(s32 *start, s32 *end) { @@ -1157,14 +1173,19 @@ static void __apply_fineibt(s32 *start_retpoline, s32 *end_retpoline, return; case CFI_FINEIBT: + /* place the FineIBT preamble at func()-16 */ ret = cfi_rewrite_preamble(start_cfi, end_cfi); if (ret) goto err; + /* rewrite the callers to target func()-16 */ ret = cfi_rewrite_callers(start_retpoline, end_retpoline); if (ret) goto err; + /* now that nobody targets func()+0, remove ENDBR there */ + cfi_rewrite_endbr(start_cfi, end_cfi); + if (builtin) pr_info("Using FineIBT CFI\n"); return; @@ -1177,6 +1198,41 @@ err: pr_err("Something went horribly wrong trying to rewrite the CFI implementation.\n"); } +static inline void poison_hash(void *addr) +{ + *(u32 *)addr = 0; +} + +static void poison_cfi(void *addr) +{ + switch (cfi_mode) { + case CFI_FINEIBT: + /* + * __cfi_\func: + * osp nopl (%rax) + * subl $0, %r10d + * jz 1f + * ud2 + * 1: nop + */ + poison_endbr(addr, false); + poison_hash(addr + fineibt_preamble_hash); + break; + + case CFI_KCFI: + /* + * __cfi_\func: + * movl $0, %eax + * .skip 11, 0x90 + */ + poison_hash(addr + 1); + break; + + default: + break; + } +} + #else static void __apply_fineibt(s32 *start_retpoline, s32 *end_retpoline, @@ -1184,6 +1240,10 @@ static void __apply_fineibt(s32 *start_retpoline, s32 *end_retpoline, { } +#ifdef CONFIG_X86_KERNEL_IBT +static void poison_cfi(void *addr) { } +#endif + #endif void apply_fineibt(s32 *start_retpoline, s32 *end_retpoline, @@ -1565,7 +1625,10 @@ void __init alternative_instructions(void) */ callthunks_patch_builtin_calls(); - apply_ibt_endbr(__ibt_endbr_seal, __ibt_endbr_seal_end); + /* + * Seal all functions that do not have their address taken. + */ + apply_seal_endbr(__ibt_endbr_seal, __ibt_endbr_seal_end); #ifdef CONFIG_SMP /* Patch to UP if other cpus not imminent. */ diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c index b05f62ee2344..5f71a0cf4399 100644 --- a/arch/x86/kernel/module.c +++ b/arch/x86/kernel/module.c @@ -358,7 +358,7 @@ int module_finalize(const Elf_Ehdr *hdr, } if (ibt_endbr) { void *iseg = (void *)ibt_endbr->sh_addr; - apply_ibt_endbr(iseg, iseg + ibt_endbr->sh_size); + apply_seal_endbr(iseg, iseg + ibt_endbr->sh_size); } if (locks) { void *lseg = (void *)locks->sh_addr; diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index ff9b80a0e3e3..72015dba72ab 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -28,6 +28,7 @@ #include <linux/static_call.h> #include <trace/events/power.h> #include <linux/hw_breakpoint.h> +#include <linux/entry-common.h> #include <asm/cpu.h> #include <asm/apic.h> #include <linux/uaccess.h> @@ -134,6 +135,25 @@ static int set_new_tls(struct task_struct *p, unsigned long tls) return do_set_thread_area_64(p, ARCH_SET_FS, tls); } +__visible void ret_from_fork(struct task_struct *prev, struct pt_regs *regs, + int (*fn)(void *), void *fn_arg) +{ + schedule_tail(prev); + + /* Is this a kernel thread? */ + if (unlikely(fn)) { + fn(fn_arg); + /* + * A kernel thread is allowed to return here after successfully + * calling kernel_execve(). Exit to userspace to complete the + * execve() syscall. + */ + regs->ax = 0; + } + + syscall_exit_to_user_mode(regs); +} + int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) { unsigned long clone_flags = args->flags; @@ -149,7 +169,7 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args) frame = &fork_frame->frame; frame->bp = encode_frame_pointer(childregs); - frame->ret_addr = (unsigned long) ret_from_fork; + frame->ret_addr = (unsigned long) ret_from_fork_asm; p->thread.sp = (unsigned long) fork_frame; p->thread.io_bitmap = NULL; p->thread.iopl_warn = 0; diff --git a/arch/xtensa/kernel/align.S b/arch/xtensa/kernel/align.S index 20d6b4961001..ee97edce2300 100644 --- a/arch/xtensa/kernel/align.S +++ b/arch/xtensa/kernel/align.S @@ -1,7 +1,7 @@ /* * arch/xtensa/kernel/align.S * - * Handle unalignment exceptions in kernel space. + * Handle unalignment and load/store exceptions. * * This file is subject to the terms and conditions of the GNU General * Public License. See the file "COPYING" in the main directory of @@ -26,20 +26,18 @@ #define LOAD_EXCEPTION_HANDLER #endif -#if XCHAL_UNALIGNED_STORE_EXCEPTION || defined LOAD_EXCEPTION_HANDLER +#if XCHAL_UNALIGNED_STORE_EXCEPTION || defined CONFIG_XTENSA_LOAD_STORE +#define STORE_EXCEPTION_HANDLER +#endif + +#if defined LOAD_EXCEPTION_HANDLER || defined STORE_EXCEPTION_HANDLER #define ANY_EXCEPTION_HANDLER #endif -#if XCHAL_HAVE_WINDOWED +#if XCHAL_HAVE_WINDOWED && defined CONFIG_MMU #define UNALIGNED_USER_EXCEPTION #endif -/* First-level exception handler for unaligned exceptions. - * - * Note: This handler works only for kernel exceptions. Unaligned user - * access should get a seg fault. - */ - /* Big and little endian 16-bit values are located in * different halves of a register. HWORD_START helps to * abstract the notion of extracting a 16-bit value from a @@ -228,8 +226,6 @@ ENDPROC(fast_load_store) #ifdef ANY_EXCEPTION_HANDLER ENTRY(fast_unaligned) -#if XCHAL_UNALIGNED_LOAD_EXCEPTION || XCHAL_UNALIGNED_STORE_EXCEPTION - call0 .Lsave_and_load_instruction /* Analyze the instruction (load or store?). */ @@ -244,8 +240,7 @@ ENTRY(fast_unaligned) /* 'store indicator bit' not set, jump */ _bbci.l a4, OP1_SI_BIT + INSN_OP1, .Lload -#endif -#if XCHAL_UNALIGNED_STORE_EXCEPTION +#ifdef STORE_EXCEPTION_HANDLER /* Store: Jump to table entry to get the value in the source register.*/ @@ -254,7 +249,7 @@ ENTRY(fast_unaligned) addx8 a5, a6, a5 jx a5 # jump into table #endif -#if XCHAL_UNALIGNED_LOAD_EXCEPTION +#ifdef LOAD_EXCEPTION_HANDLER /* Load: Load memory address. */ @@ -328,7 +323,7 @@ ENTRY(fast_unaligned) mov a14, a3 ; _j .Lexit; .align 8 mov a15, a3 ; _j .Lexit; .align 8 #endif -#if XCHAL_UNALIGNED_STORE_EXCEPTION +#ifdef STORE_EXCEPTION_HANDLER .Lstore_table: l32i a3, a2, PT_AREG0; _j .Lstore_w; .align 8 mov a3, a1; _j .Lstore_w; .align 8 # fishy?? @@ -348,7 +343,6 @@ ENTRY(fast_unaligned) mov a3, a15 ; _j .Lstore_w; .align 8 #endif -#ifdef ANY_EXCEPTION_HANDLER /* We cannot handle this exception. */ .extern _kernel_exception @@ -377,8 +371,8 @@ ENTRY(fast_unaligned) 2: movi a0, _user_exception jx a0 -#endif -#if XCHAL_UNALIGNED_STORE_EXCEPTION + +#ifdef STORE_EXCEPTION_HANDLER # a7: instruction pointer, a4: instruction, a3: value .Lstore_w: @@ -444,7 +438,7 @@ ENTRY(fast_unaligned) s32i a6, a4, 4 #endif #endif -#ifdef ANY_EXCEPTION_HANDLER + .Lexit: #if XCHAL_HAVE_LOOPS rsr a4, lend # check if we reached LEND @@ -539,7 +533,7 @@ ENTRY(fast_unaligned) __src_b a4, a4, a5 # a4 has the instruction ret -#endif + ENDPROC(fast_unaligned) ENTRY(fast_unaligned_fixup) diff --git a/arch/xtensa/kernel/traps.c b/arch/xtensa/kernel/traps.c index 17eb180eff7c..427c125a137a 100644 --- a/arch/xtensa/kernel/traps.c +++ b/arch/xtensa/kernel/traps.c @@ -102,7 +102,8 @@ static dispatch_init_table_t __initdata dispatch_init_table[] = { #endif { EXCCAUSE_INTEGER_DIVIDE_BY_ZERO, 0, do_div0 }, /* EXCCAUSE_PRIVILEGED unhandled */ -#if XCHAL_UNALIGNED_LOAD_EXCEPTION || XCHAL_UNALIGNED_STORE_EXCEPTION +#if XCHAL_UNALIGNED_LOAD_EXCEPTION || XCHAL_UNALIGNED_STORE_EXCEPTION || \ + IS_ENABLED(CONFIG_XTENSA_LOAD_STORE) #ifdef CONFIG_XTENSA_UNALIGNED_USER { EXCCAUSE_UNALIGNED, USER, fast_unaligned }, #endif diff --git a/arch/xtensa/platforms/iss/network.c b/arch/xtensa/platforms/iss/network.c index 9ac46ab3a296..85c82cd42188 100644 --- a/arch/xtensa/platforms/iss/network.c +++ b/arch/xtensa/platforms/iss/network.c @@ -237,7 +237,7 @@ static int tuntap_probe(struct iss_net_private *lp, int index, char *init) init += sizeof(TRANSPORT_TUNTAP_NAME) - 1; if (*init == ',') { - rem = split_if_spec(init + 1, &mac_str, &dev_name); + rem = split_if_spec(init + 1, &mac_str, &dev_name, NULL); if (rem != NULL) { pr_err("%s: extra garbage on specification : '%s'\n", dev->name, rem); @@ -540,6 +540,7 @@ static void iss_net_configure(int index, char *init) rtnl_unlock(); pr_err("%s: error registering net device!\n", dev->name); platform_device_unregister(&lp->pdev); + /* dev is freed by the iss_net_pdev_release callback */ return; } rtnl_unlock(); diff --git a/block/blk-crypto-profile.c b/block/blk-crypto-profile.c index 2a67d3fb63e5..7fabc883e39f 100644 --- a/block/blk-crypto-profile.c +++ b/block/blk-crypto-profile.c @@ -79,7 +79,14 @@ int blk_crypto_profile_init(struct blk_crypto_profile *profile, unsigned int slot_hashtable_size; memset(profile, 0, sizeof(*profile)); - init_rwsem(&profile->lock); + + /* + * profile->lock of an underlying device can nest inside profile->lock + * of a device-mapper device, so use a dynamic lock class to avoid + * false-positive lockdep reports. + */ + lockdep_register_key(&profile->lockdep_key); + __init_rwsem(&profile->lock, "&profile->lock", &profile->lockdep_key); if (num_slots == 0) return 0; @@ -89,7 +96,7 @@ int blk_crypto_profile_init(struct blk_crypto_profile *profile, profile->slots = kvcalloc(num_slots, sizeof(profile->slots[0]), GFP_KERNEL); if (!profile->slots) - return -ENOMEM; + goto err_destroy; profile->num_slots = num_slots; @@ -435,6 +442,7 @@ void blk_crypto_profile_destroy(struct blk_crypto_profile *profile) { if (!profile) return; + lockdep_unregister_key(&profile->lockdep_key); kvfree(profile->slot_hashtable); kvfree_sensitive(profile->slots, sizeof(profile->slots[0]) * profile->num_slots); diff --git a/block/blk-flush.c b/block/blk-flush.c index dba392cf22be..8220517c2d67 100644 --- a/block/blk-flush.c +++ b/block/blk-flush.c @@ -189,7 +189,7 @@ static void blk_flush_complete_seq(struct request *rq, case REQ_FSEQ_DATA: list_move_tail(&rq->flush.list, &fq->flush_data_in_flight); spin_lock(&q->requeue_lock); - list_add_tail(&rq->queuelist, &q->flush_list); + list_add(&rq->queuelist, &q->requeue_list); spin_unlock(&q->requeue_lock); blk_mq_kick_requeue_list(q); break; diff --git a/block/blk-mq.c b/block/blk-mq.c index 5504719b970d..d50b1d62a3d9 100644 --- a/block/blk-mq.c +++ b/block/blk-mq.c @@ -328,8 +328,24 @@ void blk_rq_init(struct request_queue *q, struct request *rq) } EXPORT_SYMBOL(blk_rq_init); +/* Set start and alloc time when the allocated request is actually used */ +static inline void blk_mq_rq_time_init(struct request *rq, u64 alloc_time_ns) +{ + if (blk_mq_need_time_stamp(rq)) + rq->start_time_ns = ktime_get_ns(); + else + rq->start_time_ns = 0; + +#ifdef CONFIG_BLK_RQ_ALLOC_TIME + if (blk_queue_rq_alloc_time(rq->q)) + rq->alloc_time_ns = alloc_time_ns ?: rq->start_time_ns; + else + rq->alloc_time_ns = 0; +#endif +} + static struct request *blk_mq_rq_ctx_init(struct blk_mq_alloc_data *data, - struct blk_mq_tags *tags, unsigned int tag, u64 alloc_time_ns) + struct blk_mq_tags *tags, unsigned int tag) { struct blk_mq_ctx *ctx = data->ctx; struct blk_mq_hw_ctx *hctx = data->hctx; @@ -356,14 +372,7 @@ static struct request *blk_mq_rq_ctx_init(struct blk_mq_alloc_data *data, } rq->timeout = 0; - if (blk_mq_need_time_stamp(rq)) - rq->start_time_ns = ktime_get_ns(); - else - rq->start_time_ns = 0; rq->part = NULL; -#ifdef CONFIG_BLK_RQ_ALLOC_TIME - rq->alloc_time_ns = alloc_time_ns; -#endif rq->io_start_time_ns = 0; rq->stats_sectors = 0; rq->nr_phys_segments = 0; @@ -393,8 +402,7 @@ static struct request *blk_mq_rq_ctx_init(struct blk_mq_alloc_data *data, } static inline struct request * -__blk_mq_alloc_requests_batch(struct blk_mq_alloc_data *data, - u64 alloc_time_ns) +__blk_mq_alloc_requests_batch(struct blk_mq_alloc_data *data) { unsigned int tag, tag_offset; struct blk_mq_tags *tags; @@ -413,7 +421,7 @@ __blk_mq_alloc_requests_batch(struct blk_mq_alloc_data *data, tag = tag_offset + i; prefetch(tags->static_rqs[tag]); tag_mask &= ~(1UL << i); - rq = blk_mq_rq_ctx_init(data, tags, tag, alloc_time_ns); + rq = blk_mq_rq_ctx_init(data, tags, tag); rq_list_add(data->cached_rq, rq); nr++; } @@ -474,9 +482,11 @@ retry: * Try batched alloc if we want more than 1 tag. */ if (data->nr_tags > 1) { - rq = __blk_mq_alloc_requests_batch(data, alloc_time_ns); - if (rq) + rq = __blk_mq_alloc_requests_batch(data); + if (rq) { + blk_mq_rq_time_init(rq, alloc_time_ns); return rq; + } data->nr_tags = 1; } @@ -499,8 +509,9 @@ retry: goto retry; } - return blk_mq_rq_ctx_init(data, blk_mq_tags_from_data(data), tag, - alloc_time_ns); + rq = blk_mq_rq_ctx_init(data, blk_mq_tags_from_data(data), tag); + blk_mq_rq_time_init(rq, alloc_time_ns); + return rq; } static struct request *blk_mq_rq_cache_fill(struct request_queue *q, @@ -555,6 +566,7 @@ static struct request *blk_mq_alloc_cached_request(struct request_queue *q, return NULL; plug->cached_rq = rq_list_next(rq); + blk_mq_rq_time_init(rq, 0); } rq->cmd_flags = opf; @@ -656,8 +668,8 @@ struct request *blk_mq_alloc_request_hctx(struct request_queue *q, tag = blk_mq_get_tag(&data); if (tag == BLK_MQ_NO_TAG) goto out_queue_exit; - rq = blk_mq_rq_ctx_init(&data, blk_mq_tags_from_data(&data), tag, - alloc_time_ns); + rq = blk_mq_rq_ctx_init(&data, blk_mq_tags_from_data(&data), tag); + blk_mq_rq_time_init(rq, alloc_time_ns); rq->__data_len = 0; rq->__sector = (sector_t) -1; rq->bio = rq->biotail = NULL; @@ -2896,6 +2908,7 @@ static inline struct request *blk_mq_get_cached_request(struct request_queue *q, plug->cached_rq = rq_list_next(rq); rq_qos_throttle(q, *bio); + blk_mq_rq_time_init(rq, 0); rq->cmd_flags = (*bio)->bi_opf; INIT_LIST_HEAD(&rq->queuelist); return rq; diff --git a/block/blk-zoned.c b/block/blk-zoned.c index 0f9f97cdddd9..619ee41a51cc 100644 --- a/block/blk-zoned.c +++ b/block/blk-zoned.c @@ -442,7 +442,6 @@ struct blk_revalidate_zone_args { unsigned long *conv_zones_bitmap; unsigned long *seq_zones_wlock; unsigned int nr_zones; - sector_t zone_sectors; sector_t sector; }; @@ -456,38 +455,34 @@ static int blk_revalidate_zone_cb(struct blk_zone *zone, unsigned int idx, struct gendisk *disk = args->disk; struct request_queue *q = disk->queue; sector_t capacity = get_capacity(disk); + sector_t zone_sectors = q->limits.chunk_sectors; + + /* Check for bad zones and holes in the zone report */ + if (zone->start != args->sector) { + pr_warn("%s: Zone gap at sectors %llu..%llu\n", + disk->disk_name, args->sector, zone->start); + return -ENODEV; + } + + if (zone->start >= capacity || !zone->len) { + pr_warn("%s: Invalid zone start %llu, length %llu\n", + disk->disk_name, zone->start, zone->len); + return -ENODEV; + } /* * All zones must have the same size, with the exception on an eventual * smaller last zone. */ - if (zone->start == 0) { - if (zone->len == 0 || !is_power_of_2(zone->len)) { - pr_warn("%s: Invalid zoned device with non power of two zone size (%llu)\n", - disk->disk_name, zone->len); - return -ENODEV; - } - - args->zone_sectors = zone->len; - args->nr_zones = (capacity + zone->len - 1) >> ilog2(zone->len); - } else if (zone->start + args->zone_sectors < capacity) { - if (zone->len != args->zone_sectors) { + if (zone->start + zone->len < capacity) { + if (zone->len != zone_sectors) { pr_warn("%s: Invalid zoned device with non constant zone size\n", disk->disk_name); return -ENODEV; } - } else { - if (zone->len > args->zone_sectors) { - pr_warn("%s: Invalid zoned device with larger last zone size\n", - disk->disk_name); - return -ENODEV; - } - } - - /* Check for holes in the zone report */ - if (zone->start != args->sector) { - pr_warn("%s: Zone gap at sectors %llu..%llu\n", - disk->disk_name, args->sector, zone->start); + } else if (zone->len > zone_sectors) { + pr_warn("%s: Invalid zoned device with larger last zone size\n", + disk->disk_name); return -ENODEV; } @@ -526,11 +521,13 @@ static int blk_revalidate_zone_cb(struct blk_zone *zone, unsigned int idx, * @disk: Target disk * @update_driver_data: Callback to update driver data on the frozen disk * - * Helper function for low-level device drivers to (re) allocate and initialize - * a disk request queue zone bitmaps. This functions should normally be called - * within the disk ->revalidate method for blk-mq based drivers. For BIO based - * drivers only q->nr_zones needs to be updated so that the sysfs exposed value - * is correct. + * Helper function for low-level device drivers to check and (re) allocate and + * initialize a disk request queue zone bitmaps. This functions should normally + * be called within the disk ->revalidate method for blk-mq based drivers. + * Before calling this function, the device driver must already have set the + * device zone size (chunk_sector limit) and the max zone append limit. + * For BIO based drivers, this function cannot be used. BIO based device drivers + * only need to set disk->nr_zones so that the sysfs exposed value is correct. * If the @update_driver_data callback function is not NULL, the callback is * executed with the device request queue frozen after all zones have been * checked. @@ -539,9 +536,9 @@ int blk_revalidate_disk_zones(struct gendisk *disk, void (*update_driver_data)(struct gendisk *disk)) { struct request_queue *q = disk->queue; - struct blk_revalidate_zone_args args = { - .disk = disk, - }; + sector_t zone_sectors = q->limits.chunk_sectors; + sector_t capacity = get_capacity(disk); + struct blk_revalidate_zone_args args = { }; unsigned int noio_flag; int ret; @@ -550,13 +547,31 @@ int blk_revalidate_disk_zones(struct gendisk *disk, if (WARN_ON_ONCE(!queue_is_mq(q))) return -EIO; - if (!get_capacity(disk)) - return -EIO; + if (!capacity) + return -ENODEV; + + /* + * Checks that the device driver indicated a valid zone size and that + * the max zone append limit is set. + */ + if (!zone_sectors || !is_power_of_2(zone_sectors)) { + pr_warn("%s: Invalid non power of two zone size (%llu)\n", + disk->disk_name, zone_sectors); + return -ENODEV; + } + + if (!q->limits.max_zone_append_sectors) { + pr_warn("%s: Invalid 0 maximum zone append limit\n", + disk->disk_name); + return -ENODEV; + } /* * Ensure that all memory allocations in this context are done as if * GFP_NOIO was specified. */ + args.disk = disk; + args.nr_zones = (capacity + zone_sectors - 1) >> ilog2(zone_sectors); noio_flag = memalloc_noio_save(); ret = disk->fops->report_zones(disk, 0, UINT_MAX, blk_revalidate_zone_cb, &args); @@ -570,7 +585,7 @@ int blk_revalidate_disk_zones(struct gendisk *disk, * If zones where reported, make sure that the entire disk capacity * has been checked. */ - if (ret > 0 && args.sector != get_capacity(disk)) { + if (ret > 0 && args.sector != capacity) { pr_warn("%s: Missing zones from sector %llu\n", disk->disk_name, args.sector); ret = -ENODEV; @@ -583,7 +598,6 @@ int blk_revalidate_disk_zones(struct gendisk *disk, */ blk_mq_freeze_queue(q); if (ret > 0) { - blk_queue_chunk_sectors(q, args.zone_sectors); disk->nr_zones = args.nr_zones; swap(disk->seq_zones_wlock, args.seq_zones_wlock); swap(disk->conv_zones_bitmap, args.conv_zones_bitmap); diff --git a/block/mq-deadline.c b/block/mq-deadline.c index 6aa5daf7ae32..02a916ba62ee 100644 --- a/block/mq-deadline.c +++ b/block/mq-deadline.c @@ -176,7 +176,7 @@ static inline struct request *deadline_from_pos(struct dd_per_prio *per_prio, * zoned writes, start searching from the start of a zone. */ if (blk_rq_is_seq_zoned_write(rq)) - pos -= round_down(pos, rq->q->limits.chunk_sectors); + pos = round_down(pos, rq->q->limits.chunk_sectors); while (node) { rq = rb_entry_rq(node); diff --git a/block/partitions/amiga.c b/block/partitions/amiga.c index ed222b9c901b..506921095412 100644 --- a/block/partitions/amiga.c +++ b/block/partitions/amiga.c @@ -90,7 +90,7 @@ int amiga_partition(struct parsed_partitions *state) } blk = be32_to_cpu(rdb->rdb_PartitionList); put_dev_sector(sect); - for (part = 1; blk>0 && part<=16; part++, put_dev_sector(sect)) { + for (part = 1; (s32) blk>0 && part<=16; part++, put_dev_sector(sect)) { /* Read in terms partition table understands */ if (check_mul_overflow(blk, (sector_t) blksize, &blk)) { pr_err("Dev %s: overflow calculating partition block %llu! Skipping partitions %u and beyond\n", diff --git a/drivers/accel/ivpu/ivpu_drv.h b/drivers/accel/ivpu/ivpu_drv.h index d3013fbd13b3..399dc5dcefd7 100644 --- a/drivers/accel/ivpu/ivpu_drv.h +++ b/drivers/accel/ivpu/ivpu_drv.h @@ -75,6 +75,7 @@ struct ivpu_wa_table { bool punit_disabled; bool clear_runtime_mem; bool d3hot_after_power_off; + bool interrupt_clear_with_0; }; struct ivpu_hw_info; diff --git a/drivers/accel/ivpu/ivpu_hw_mtl.c b/drivers/accel/ivpu/ivpu_hw_mtl.c index fef35422c6f0..2a5dd3a5dc46 100644 --- a/drivers/accel/ivpu/ivpu_hw_mtl.c +++ b/drivers/accel/ivpu/ivpu_hw_mtl.c @@ -101,6 +101,9 @@ static void ivpu_hw_wa_init(struct ivpu_device *vdev) vdev->wa.punit_disabled = ivpu_is_fpga(vdev); vdev->wa.clear_runtime_mem = false; vdev->wa.d3hot_after_power_off = true; + + if (ivpu_device_id(vdev) == PCI_DEVICE_ID_MTL && ivpu_revision(vdev) < 4) + vdev->wa.interrupt_clear_with_0 = true; } static void ivpu_hw_timeouts_init(struct ivpu_device *vdev) @@ -885,7 +888,7 @@ static void ivpu_hw_mtl_irq_disable(struct ivpu_device *vdev) REGB_WR32(MTL_BUTTRESS_GLOBAL_INT_MASK, 0x1); REGB_WR32(MTL_BUTTRESS_LOCAL_INT_MASK, BUTTRESS_IRQ_DISABLE_MASK); REGV_WR64(MTL_VPU_HOST_SS_ICB_ENABLE_0, 0x0ull); - REGB_WR32(MTL_VPU_HOST_SS_FW_SOC_IRQ_EN, 0x0); + REGV_WR32(MTL_VPU_HOST_SS_FW_SOC_IRQ_EN, 0x0); } static void ivpu_hw_mtl_irq_wdt_nce_handler(struct ivpu_device *vdev) @@ -973,12 +976,15 @@ static u32 ivpu_hw_mtl_irqb_handler(struct ivpu_device *vdev, int irq) schedule_recovery = true; } - /* - * Clear local interrupt status by writing 0 to all bits. - * This must be done after interrupts are cleared at the source. - * Writing 1 triggers an interrupt, so we can't perform read update write. - */ - REGB_WR32(MTL_BUTTRESS_INTERRUPT_STAT, 0x0); + /* This must be done after interrupts are cleared at the source. */ + if (IVPU_WA(interrupt_clear_with_0)) + /* + * Writing 1 triggers an interrupt, so we can't perform read update write. + * Clear local interrupt status by writing 0 to all bits. + */ + REGB_WR32(MTL_BUTTRESS_INTERRUPT_STAT, 0x0); + else + REGB_WR32(MTL_BUTTRESS_INTERRUPT_STAT, status); /* Re-enable global interrupt */ REGB_WR32(MTL_BUTTRESS_GLOBAL_INT_MASK, 0x0); diff --git a/drivers/base/regmap/regmap-irq.c b/drivers/base/regmap/regmap-irq.c index ced0dcf86e0b..45fd13ef13fc 100644 --- a/drivers/base/regmap/regmap-irq.c +++ b/drivers/base/regmap/regmap-irq.c @@ -717,7 +717,7 @@ int regmap_add_irq_chip_fwnode(struct fwnode_handle *fwnode, if (!d->config_buf) goto err_alloc; - for (i = 0; i < chip->num_config_regs; i++) { + for (i = 0; i < chip->num_config_bases; i++) { d->config_buf[i] = kcalloc(chip->num_config_regs, sizeof(**d->config_buf), GFP_KERNEL); diff --git a/drivers/block/null_blk/zoned.c b/drivers/block/null_blk/zoned.c index 635ce0648133..55c5b48bc276 100644 --- a/drivers/block/null_blk/zoned.c +++ b/drivers/block/null_blk/zoned.c @@ -162,21 +162,15 @@ int null_register_zoned_dev(struct nullb *nullb) disk_set_zoned(nullb->disk, BLK_ZONED_HM); blk_queue_flag_set(QUEUE_FLAG_ZONE_RESETALL, q); blk_queue_required_elevator_features(q, ELEVATOR_F_ZBD_SEQ_WRITE); - - if (queue_is_mq(q)) { - int ret = blk_revalidate_disk_zones(nullb->disk, NULL); - - if (ret) - return ret; - } else { - blk_queue_chunk_sectors(q, dev->zone_size_sects); - nullb->disk->nr_zones = bdev_nr_zones(nullb->disk->part0); - } - + blk_queue_chunk_sectors(q, dev->zone_size_sects); + nullb->disk->nr_zones = bdev_nr_zones(nullb->disk->part0); blk_queue_max_zone_append_sectors(q, dev->zone_size_sects); disk_set_max_open_zones(nullb->disk, dev->zone_max_open); disk_set_max_active_zones(nullb->disk, dev->zone_max_active); + if (queue_is_mq(q)) + return blk_revalidate_disk_zones(nullb->disk, NULL); + return 0; } diff --git a/drivers/block/virtio_blk.c b/drivers/block/virtio_blk.c index b47358da92a2..1fe011676d07 100644 --- a/drivers/block/virtio_blk.c +++ b/drivers/block/virtio_blk.c @@ -751,7 +751,6 @@ static int virtblk_probe_zoned_device(struct virtio_device *vdev, { u32 v, wg; u8 model; - int ret; virtio_cread(vdev, struct virtio_blk_config, zoned.model, &model); @@ -806,6 +805,7 @@ static int virtblk_probe_zoned_device(struct virtio_device *vdev, vblk->zone_sectors); return -ENODEV; } + blk_queue_chunk_sectors(q, vblk->zone_sectors); dev_dbg(&vdev->dev, "zone sectors = %u\n", vblk->zone_sectors); if (virtio_has_feature(vdev, VIRTIO_BLK_F_DISCARD)) { @@ -814,26 +814,22 @@ static int virtblk_probe_zoned_device(struct virtio_device *vdev, blk_queue_max_discard_sectors(q, 0); } - ret = blk_revalidate_disk_zones(vblk->disk, NULL); - if (!ret) { - virtio_cread(vdev, struct virtio_blk_config, - zoned.max_append_sectors, &v); - if (!v) { - dev_warn(&vdev->dev, "zero max_append_sectors reported\n"); - return -ENODEV; - } - if ((v << SECTOR_SHIFT) < wg) { - dev_err(&vdev->dev, - "write granularity %u exceeds max_append_sectors %u limit\n", - wg, v); - return -ENODEV; - } - - blk_queue_max_zone_append_sectors(q, v); - dev_dbg(&vdev->dev, "max append sectors = %u\n", v); + virtio_cread(vdev, struct virtio_blk_config, + zoned.max_append_sectors, &v); + if (!v) { + dev_warn(&vdev->dev, "zero max_append_sectors reported\n"); + return -ENODEV; + } + if ((v << SECTOR_SHIFT) < wg) { + dev_err(&vdev->dev, + "write granularity %u exceeds max_append_sectors %u limit\n", + wg, v); + return -ENODEV; } + blk_queue_max_zone_append_sectors(q, v); + dev_dbg(&vdev->dev, "max append sectors = %u\n", v); - return ret; + return blk_revalidate_disk_zones(vblk->disk, NULL); } #else diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c index 5ec4ad0a5c86..764d176e9735 100644 --- a/drivers/bluetooth/btusb.c +++ b/drivers/bluetooth/btusb.c @@ -4104,6 +4104,7 @@ static int btusb_probe(struct usb_interface *intf, BT_DBG("intf %p id %p", intf, id); if ((id->driver_info & BTUSB_IFNUM_2) && + (intf->cur_altsetting->desc.bInterfaceNumber != 0) && (intf->cur_altsetting->desc.bInterfaceNumber != 2)) return -ENODEV; diff --git a/drivers/char/tpm/tpm-chip.c b/drivers/char/tpm/tpm-chip.c index cd48033b804a..cf5499e51999 100644 --- a/drivers/char/tpm/tpm-chip.c +++ b/drivers/char/tpm/tpm-chip.c @@ -518,6 +518,7 @@ static int tpm_add_legacy_sysfs(struct tpm_chip *chip) * 6.x.y.z series: 6.0.18.6 + * 3.x.y.z series: 3.57.y.5 + */ +#ifdef CONFIG_X86 static bool tpm_amd_is_rng_defective(struct tpm_chip *chip) { u32 val1, val2; @@ -566,6 +567,12 @@ release: return true; } +#else +static inline bool tpm_amd_is_rng_defective(struct tpm_chip *chip) +{ + return false; +} +#endif /* CONFIG_X86 */ static int tpm_hwrng_read(struct hwrng *rng, void *data, size_t max, bool wait) { diff --git a/drivers/char/tpm/tpm_crb.c b/drivers/char/tpm/tpm_crb.c index d43a0d7b97a8..1a5d09b18513 100644 --- a/drivers/char/tpm/tpm_crb.c +++ b/drivers/char/tpm/tpm_crb.c @@ -563,15 +563,18 @@ static int crb_map_io(struct acpi_device *device, struct crb_priv *priv, u32 rsp_size; int ret; - INIT_LIST_HEAD(&acpi_resource_list); - ret = acpi_dev_get_resources(device, &acpi_resource_list, - crb_check_resource, iores_array); - if (ret < 0) - return ret; - acpi_dev_free_resource_list(&acpi_resource_list); - - /* Pluton doesn't appear to define ACPI memory regions */ + /* + * Pluton sometimes does not define ACPI memory regions. + * Mapping is then done in crb_map_pluton + */ if (priv->sm != ACPI_TPM2_COMMAND_BUFFER_WITH_PLUTON) { + INIT_LIST_HEAD(&acpi_resource_list); + ret = acpi_dev_get_resources(device, &acpi_resource_list, + crb_check_resource, iores_array); + if (ret < 0) + return ret; + acpi_dev_free_resource_list(&acpi_resource_list); + if (resource_type(iores_array) != IORESOURCE_MEM) { dev_err(dev, FW_BUG "TPM2 ACPI table does not define a memory resource\n"); return -EINVAL; diff --git a/drivers/char/tpm/tpm_tis.c b/drivers/char/tpm/tpm_tis.c index 7db3593941ea..cc42cf3de960 100644 --- a/drivers/char/tpm/tpm_tis.c +++ b/drivers/char/tpm/tpm_tis.c @@ -116,6 +116,22 @@ static int tpm_tis_disable_irq(const struct dmi_system_id *d) static const struct dmi_system_id tpm_tis_dmi_table[] = { { .callback = tpm_tis_disable_irq, + .ident = "Framework Laptop (12th Gen Intel Core)", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Framework"), + DMI_MATCH(DMI_PRODUCT_NAME, "Laptop (12th Gen Intel Core)"), + }, + }, + { + .callback = tpm_tis_disable_irq, + .ident = "Framework Laptop (13th Gen Intel Core)", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "Framework"), + DMI_MATCH(DMI_PRODUCT_NAME, "Laptop (13th Gen Intel Core)"), + }, + }, + { + .callback = tpm_tis_disable_irq, .ident = "ThinkPad T490s", .matches = { DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), @@ -140,9 +156,18 @@ static const struct dmi_system_id tpm_tis_dmi_table[] = { }, { .callback = tpm_tis_disable_irq, + .ident = "ThinkPad L590", + .matches = { + DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"), + DMI_MATCH(DMI_PRODUCT_VERSION, "ThinkPad L590"), + }, + }, + { + .callback = tpm_tis_disable_irq, .ident = "UPX-TGL", .matches = { DMI_MATCH(DMI_SYS_VENDOR, "AAEON"), + DMI_MATCH(DMI_PRODUCT_VERSION, "UPX-TGL"), }, }, {} diff --git a/drivers/char/tpm/tpm_tis_core.c b/drivers/char/tpm/tpm_tis_core.c index 558144fa707a..88a5384c09c0 100644 --- a/drivers/char/tpm/tpm_tis_core.c +++ b/drivers/char/tpm/tpm_tis_core.c @@ -24,9 +24,12 @@ #include <linux/wait.h> #include <linux/acpi.h> #include <linux/freezer.h> +#include <linux/dmi.h> #include "tpm.h" #include "tpm_tis_core.h" +#define TPM_TIS_MAX_UNHANDLED_IRQS 1000 + static void tpm_tis_clkrun_enable(struct tpm_chip *chip, bool value); static bool wait_for_tpm_stat_cond(struct tpm_chip *chip, u8 mask, @@ -468,25 +471,29 @@ out_err: return rc; } -static void disable_interrupts(struct tpm_chip *chip) +static void __tpm_tis_disable_interrupts(struct tpm_chip *chip) +{ + struct tpm_tis_data *priv = dev_get_drvdata(&chip->dev); + u32 int_mask = 0; + + tpm_tis_read32(priv, TPM_INT_ENABLE(priv->locality), &int_mask); + int_mask &= ~TPM_GLOBAL_INT_ENABLE; + tpm_tis_write32(priv, TPM_INT_ENABLE(priv->locality), int_mask); + + chip->flags &= ~TPM_CHIP_FLAG_IRQ; +} + +static void tpm_tis_disable_interrupts(struct tpm_chip *chip) { struct tpm_tis_data *priv = dev_get_drvdata(&chip->dev); - u32 intmask; - int rc; if (priv->irq == 0) return; - rc = tpm_tis_read32(priv, TPM_INT_ENABLE(priv->locality), &intmask); - if (rc < 0) - intmask = 0; - - intmask &= ~TPM_GLOBAL_INT_ENABLE; - rc = tpm_tis_write32(priv, TPM_INT_ENABLE(priv->locality), intmask); + __tpm_tis_disable_interrupts(chip); devm_free_irq(chip->dev.parent, priv->irq, chip); priv->irq = 0; - chip->flags &= ~TPM_CHIP_FLAG_IRQ; } /* @@ -552,7 +559,7 @@ static int tpm_tis_send(struct tpm_chip *chip, u8 *buf, size_t len) if (!test_bit(TPM_TIS_IRQ_TESTED, &priv->flags)) tpm_msleep(1); if (!test_bit(TPM_TIS_IRQ_TESTED, &priv->flags)) - disable_interrupts(chip); + tpm_tis_disable_interrupts(chip); set_bit(TPM_TIS_IRQ_TESTED, &priv->flags); return rc; } @@ -752,6 +759,57 @@ static bool tpm_tis_req_canceled(struct tpm_chip *chip, u8 status) return status == TPM_STS_COMMAND_READY; } +static irqreturn_t tpm_tis_revert_interrupts(struct tpm_chip *chip) +{ + struct tpm_tis_data *priv = dev_get_drvdata(&chip->dev); + const char *product; + const char *vendor; + + dev_warn(&chip->dev, FW_BUG + "TPM interrupt storm detected, polling instead\n"); + + vendor = dmi_get_system_info(DMI_SYS_VENDOR); + product = dmi_get_system_info(DMI_PRODUCT_VERSION); + + if (vendor && product) { + dev_info(&chip->dev, + "Consider adding the following entry to tpm_tis_dmi_table:\n"); + dev_info(&chip->dev, "\tDMI_SYS_VENDOR: %s\n", vendor); + dev_info(&chip->dev, "\tDMI_PRODUCT_VERSION: %s\n", product); + } + + if (tpm_tis_request_locality(chip, 0) != 0) + return IRQ_NONE; + + __tpm_tis_disable_interrupts(chip); + tpm_tis_relinquish_locality(chip, 0); + + schedule_work(&priv->free_irq_work); + + return IRQ_HANDLED; +} + +static irqreturn_t tpm_tis_update_unhandled_irqs(struct tpm_chip *chip) +{ + struct tpm_tis_data *priv = dev_get_drvdata(&chip->dev); + irqreturn_t irqret = IRQ_HANDLED; + + if (!(chip->flags & TPM_CHIP_FLAG_IRQ)) + return IRQ_HANDLED; + + if (time_after(jiffies, priv->last_unhandled_irq + HZ/10)) + priv->unhandled_irqs = 1; + else + priv->unhandled_irqs++; + + priv->last_unhandled_irq = jiffies; + + if (priv->unhandled_irqs > TPM_TIS_MAX_UNHANDLED_IRQS) + irqret = tpm_tis_revert_interrupts(chip); + + return irqret; +} + static irqreturn_t tis_int_handler(int dummy, void *dev_id) { struct tpm_chip *chip = dev_id; @@ -761,10 +819,10 @@ static irqreturn_t tis_int_handler(int dummy, void *dev_id) rc = tpm_tis_read32(priv, TPM_INT_STATUS(priv->locality), &interrupt); if (rc < 0) - return IRQ_NONE; + goto err; if (interrupt == 0) - return IRQ_NONE; + goto err; set_bit(TPM_TIS_IRQ_TESTED, &priv->flags); if (interrupt & TPM_INTF_DATA_AVAIL_INT) @@ -780,10 +838,13 @@ static irqreturn_t tis_int_handler(int dummy, void *dev_id) rc = tpm_tis_write32(priv, TPM_INT_STATUS(priv->locality), interrupt); tpm_tis_relinquish_locality(chip, 0); if (rc < 0) - return IRQ_NONE; + goto err; tpm_tis_read32(priv, TPM_INT_STATUS(priv->locality), &interrupt); return IRQ_HANDLED; + +err: + return tpm_tis_update_unhandled_irqs(chip); } static void tpm_tis_gen_interrupt(struct tpm_chip *chip) @@ -804,6 +865,15 @@ static void tpm_tis_gen_interrupt(struct tpm_chip *chip) chip->flags &= ~TPM_CHIP_FLAG_IRQ; } +static void tpm_tis_free_irq_func(struct work_struct *work) +{ + struct tpm_tis_data *priv = container_of(work, typeof(*priv), free_irq_work); + struct tpm_chip *chip = priv->chip; + + devm_free_irq(chip->dev.parent, priv->irq, chip); + priv->irq = 0; +} + /* Register the IRQ and issue a command that will cause an interrupt. If an * irq is seen then leave the chip setup for IRQ operation, otherwise reverse * everything and leave in polling mode. Returns 0 on success. @@ -816,6 +886,7 @@ static int tpm_tis_probe_irq_single(struct tpm_chip *chip, u32 intmask, int rc; u32 int_status; + INIT_WORK(&priv->free_irq_work, tpm_tis_free_irq_func); rc = devm_request_threaded_irq(chip->dev.parent, irq, NULL, tis_int_handler, IRQF_ONESHOT | flags, @@ -918,6 +989,7 @@ void tpm_tis_remove(struct tpm_chip *chip) interrupt = 0; tpm_tis_write32(priv, reg, ~TPM_GLOBAL_INT_ENABLE & interrupt); + flush_work(&priv->free_irq_work); tpm_tis_clkrun_enable(chip, false); @@ -1021,6 +1093,7 @@ int tpm_tis_core_init(struct device *dev, struct tpm_tis_data *priv, int irq, chip->timeout_b = msecs_to_jiffies(TIS_TIMEOUT_B_MAX); chip->timeout_c = msecs_to_jiffies(TIS_TIMEOUT_C_MAX); chip->timeout_d = msecs_to_jiffies(TIS_TIMEOUT_D_MAX); + priv->chip = chip; priv->timeout_min = TPM_TIMEOUT_USECS_MIN; priv->timeout_max = TPM_TIMEOUT_USECS_MAX; priv->phy_ops = phy_ops; @@ -1179,7 +1252,7 @@ int tpm_tis_core_init(struct device *dev, struct tpm_tis_data *priv, int irq, rc = tpm_tis_request_locality(chip, 0); if (rc < 0) goto out_err; - disable_interrupts(chip); + tpm_tis_disable_interrupts(chip); tpm_tis_relinquish_locality(chip, 0); } } diff --git a/drivers/char/tpm/tpm_tis_core.h b/drivers/char/tpm/tpm_tis_core.h index 610bfadb6acf..b1a169d7d1ca 100644 --- a/drivers/char/tpm/tpm_tis_core.h +++ b/drivers/char/tpm/tpm_tis_core.h @@ -91,11 +91,15 @@ enum tpm_tis_flags { }; struct tpm_tis_data { + struct tpm_chip *chip; u16 manufacturer_id; struct mutex locality_count_mutex; unsigned int locality_count; int locality; int irq; + struct work_struct free_irq_work; + unsigned long last_unhandled_irq; + unsigned int unhandled_irqs; unsigned int int_mask; unsigned long flags; void __iomem *ilb_base_addr; diff --git a/drivers/char/tpm/tpm_tis_i2c.c b/drivers/char/tpm/tpm_tis_i2c.c index c8c34adc14c0..82fda488e98b 100644 --- a/drivers/char/tpm/tpm_tis_i2c.c +++ b/drivers/char/tpm/tpm_tis_i2c.c @@ -189,21 +189,28 @@ static int tpm_tis_i2c_read_bytes(struct tpm_tis_data *data, u32 addr, u16 len, int ret; for (i = 0; i < TPM_RETRY; i++) { - /* write register */ - msg.len = sizeof(reg); - msg.buf = ® - msg.flags = 0; - ret = tpm_tis_i2c_retry_transfer_until_ack(data, &msg); - if (ret < 0) - return ret; - - /* read data */ - msg.buf = result; - msg.len = len; - msg.flags = I2C_M_RD; - ret = tpm_tis_i2c_retry_transfer_until_ack(data, &msg); - if (ret < 0) - return ret; + u16 read = 0; + + while (read < len) { + /* write register */ + msg.len = sizeof(reg); + msg.buf = ® + msg.flags = 0; + ret = tpm_tis_i2c_retry_transfer_until_ack(data, &msg); + if (ret < 0) + return ret; + + /* read data */ + msg.buf = result + read; + msg.len = len - read; + msg.flags = I2C_M_RD; + if (msg.len > I2C_SMBUS_BLOCK_MAX) + msg.len = I2C_SMBUS_BLOCK_MAX; + ret = tpm_tis_i2c_retry_transfer_until_ack(data, &msg); + if (ret < 0) + return ret; + read += msg.len; + } ret = tpm_tis_i2c_sanity_check_read(reg, len, result); if (ret == 0) @@ -223,19 +230,27 @@ static int tpm_tis_i2c_write_bytes(struct tpm_tis_data *data, u32 addr, u16 len, struct i2c_msg msg = { .addr = phy->i2c_client->addr }; u8 reg = tpm_tis_i2c_address_to_register(addr); int ret; + u16 wrote = 0; if (len > TPM_BUFSIZE - 1) return -EIO; - /* write register and data in one go */ phy->io_buf[0] = reg; - memcpy(phy->io_buf + sizeof(reg), value, len); - - msg.len = sizeof(reg) + len; msg.buf = phy->io_buf; - ret = tpm_tis_i2c_retry_transfer_until_ack(data, &msg); - if (ret < 0) - return ret; + while (wrote < len) { + /* write register and data in one go */ + msg.len = sizeof(reg) + len - wrote; + if (msg.len > I2C_SMBUS_BLOCK_MAX) + msg.len = I2C_SMBUS_BLOCK_MAX; + + memcpy(phy->io_buf + sizeof(reg), value + wrote, + msg.len - sizeof(reg)); + + ret = tpm_tis_i2c_retry_transfer_until_ack(data, &msg); + if (ret < 0) + return ret; + wrote += msg.len - sizeof(reg); + } return 0; } diff --git a/drivers/char/tpm/tpm_tis_spi_main.c b/drivers/char/tpm/tpm_tis_spi_main.c index 1f5207974a17..9bfaba092a06 100644 --- a/drivers/char/tpm/tpm_tis_spi_main.c +++ b/drivers/char/tpm/tpm_tis_spi_main.c @@ -136,6 +136,14 @@ int tpm_tis_spi_transfer(struct tpm_tis_data *data, u32 addr, u16 len, } exit: + if (ret < 0) { + /* Deactivate chip select */ + memset(&spi_xfer, 0, sizeof(spi_xfer)); + spi_message_init(&m); + spi_message_add_tail(&spi_xfer, &m); + spi_sync_locked(phy->spi_device, &m); + } + spi_bus_unlock(phy->spi_device->master); return ret; } diff --git a/drivers/char/tpm/tpm_vtpm_proxy.c b/drivers/char/tpm/tpm_vtpm_proxy.c index 5c865987ba5c..30e953988cab 100644 --- a/drivers/char/tpm/tpm_vtpm_proxy.c +++ b/drivers/char/tpm/tpm_vtpm_proxy.c @@ -683,37 +683,21 @@ static struct miscdevice vtpmx_miscdev = { .fops = &vtpmx_fops, }; -static int vtpmx_init(void) -{ - return misc_register(&vtpmx_miscdev); -} - -static void vtpmx_cleanup(void) -{ - misc_deregister(&vtpmx_miscdev); -} - static int __init vtpm_module_init(void) { int rc; - rc = vtpmx_init(); - if (rc) { - pr_err("couldn't create vtpmx device\n"); - return rc; - } - workqueue = create_workqueue("tpm-vtpm"); if (!workqueue) { pr_err("couldn't create workqueue\n"); - rc = -ENOMEM; - goto err_vtpmx_cleanup; + return -ENOMEM; } - return 0; - -err_vtpmx_cleanup: - vtpmx_cleanup(); + rc = misc_register(&vtpmx_miscdev); + if (rc) { + pr_err("couldn't create vtpmx device\n"); + destroy_workqueue(workqueue); + } return rc; } @@ -721,7 +705,7 @@ err_vtpmx_cleanup: static void __exit vtpm_module_exit(void) { destroy_workqueue(workqueue); - vtpmx_cleanup(); + misc_deregister(&vtpmx_miscdev); } module_init(vtpm_module_init); diff --git a/drivers/cpufreq/sparc-us2e-cpufreq.c b/drivers/cpufreq/sparc-us2e-cpufreq.c index d3510cfdb3eb..2783d3d55fce 100644 --- a/drivers/cpufreq/sparc-us2e-cpufreq.c +++ b/drivers/cpufreq/sparc-us2e-cpufreq.c @@ -269,7 +269,7 @@ static int us2e_freq_target(struct cpufreq_policy *policy, unsigned int index) return smp_call_function_single(cpu, __us2e_freq_target, &index, 1); } -static int __init us2e_freq_cpu_init(struct cpufreq_policy *policy) +static int us2e_freq_cpu_init(struct cpufreq_policy *policy) { unsigned int cpu = policy->cpu; unsigned long clock_tick = sparc64_get_clock_tick(cpu) / 1000; diff --git a/drivers/cpufreq/sparc-us3-cpufreq.c b/drivers/cpufreq/sparc-us3-cpufreq.c index 91d1ed558136..6c3657679a88 100644 --- a/drivers/cpufreq/sparc-us3-cpufreq.c +++ b/drivers/cpufreq/sparc-us3-cpufreq.c @@ -117,7 +117,7 @@ static int us3_freq_target(struct cpufreq_policy *policy, unsigned int index) return smp_call_function_single(cpu, update_safari_cfg, &new_bits, 1); } -static int __init us3_freq_cpu_init(struct cpufreq_policy *policy) +static int us3_freq_cpu_init(struct cpufreq_policy *policy) { unsigned int cpu = policy->cpu; unsigned long clock_tick = sparc64_get_clock_tick(cpu) / 1000; diff --git a/drivers/dma-buf/dma-fence-unwrap.c b/drivers/dma-buf/dma-fence-unwrap.c index 7002bca792ff..c625bb2b5d56 100644 --- a/drivers/dma-buf/dma-fence-unwrap.c +++ b/drivers/dma-buf/dma-fence-unwrap.c @@ -66,18 +66,36 @@ struct dma_fence *__dma_fence_unwrap_merge(unsigned int num_fences, { struct dma_fence_array *result; struct dma_fence *tmp, **array; + ktime_t timestamp; unsigned int i; size_t count; count = 0; + timestamp = ns_to_ktime(0); for (i = 0; i < num_fences; ++i) { - dma_fence_unwrap_for_each(tmp, &iter[i], fences[i]) - if (!dma_fence_is_signaled(tmp)) + dma_fence_unwrap_for_each(tmp, &iter[i], fences[i]) { + if (!dma_fence_is_signaled(tmp)) { ++count; + } else if (test_bit(DMA_FENCE_FLAG_TIMESTAMP_BIT, + &tmp->flags)) { + if (ktime_after(tmp->timestamp, timestamp)) + timestamp = tmp->timestamp; + } else { + /* + * Use the current time if the fence is + * currently signaling. + */ + timestamp = ktime_get(); + } + } } + /* + * If we couldn't find a pending fence just return a private signaled + * fence with the timestamp of the last signaled one. + */ if (count == 0) - return dma_fence_get_stub(); + return dma_fence_allocate_private_stub(timestamp); array = kmalloc_array(count, sizeof(*array), GFP_KERNEL); if (!array) @@ -138,7 +156,7 @@ restart: } while (tmp); if (count == 0) { - tmp = dma_fence_get_stub(); + tmp = dma_fence_allocate_private_stub(ktime_get()); goto return_tmp; } diff --git a/drivers/dma-buf/dma-fence.c b/drivers/dma-buf/dma-fence.c index f177c56269bb..8aa8f8cb7071 100644 --- a/drivers/dma-buf/dma-fence.c +++ b/drivers/dma-buf/dma-fence.c @@ -150,16 +150,17 @@ EXPORT_SYMBOL(dma_fence_get_stub); /** * dma_fence_allocate_private_stub - return a private, signaled fence + * @timestamp: timestamp when the fence was signaled * * Return a newly allocated and signaled stub fence. */ -struct dma_fence *dma_fence_allocate_private_stub(void) +struct dma_fence *dma_fence_allocate_private_stub(ktime_t timestamp) { struct dma_fence *fence; fence = kzalloc(sizeof(*fence), GFP_KERNEL); if (fence == NULL) - return ERR_PTR(-ENOMEM); + return NULL; dma_fence_init(fence, &dma_fence_stub_ops, @@ -169,7 +170,7 @@ struct dma_fence *dma_fence_allocate_private_stub(void) set_bit(DMA_FENCE_FLAG_ENABLE_SIGNAL_BIT, &fence->flags); - dma_fence_signal(fence); + dma_fence_signal_timestamp(fence, timestamp); return fence; } diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h index 2f9c14aca73c..a3b86b86dc47 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h @@ -1296,6 +1296,7 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev, void amdgpu_device_pci_config_reset(struct amdgpu_device *adev); int amdgpu_device_pci_reset(struct amdgpu_device *adev); bool amdgpu_device_need_post(struct amdgpu_device *adev); +bool amdgpu_device_pcie_dynamic_switching_supported(void); bool amdgpu_device_should_use_aspm(struct amdgpu_device *adev); bool amdgpu_device_aspm_support_quirk(void); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c index f61527b800e6..a7f314ddd173 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c @@ -2881,6 +2881,9 @@ int amdgpu_amdkfd_gpuvm_restore_process_bos(void *info, struct dma_fence **ef) if (!attachment->is_mapped) continue; + if (attachment->bo_va->base.bo->tbo.pin_count) + continue; + kfd_mem_dmaunmap_attachment(mem, attachment); ret = update_gpuvm_pte(mem, attachment, &sync_obj); if (ret) { diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c index a92c6189b4b6..a2cdde0ca0a7 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c @@ -1458,6 +1458,25 @@ bool amdgpu_device_need_post(struct amdgpu_device *adev) return true; } +/* + * Intel hosts such as Raptor Lake and Sapphire Rapids don't support dynamic + * speed switching. Until we have confirmation from Intel that a specific host + * supports it, it's safer that we keep it disabled for all. + * + * https://edc.intel.com/content/www/us/en/design/products/platforms/details/raptor-lake-s/13th-generation-core-processors-datasheet-volume-1-of-2/005/pci-express-support/ + * https://gitlab.freedesktop.org/drm/amd/-/issues/2663 + */ +bool amdgpu_device_pcie_dynamic_switching_supported(void) +{ +#if IS_ENABLED(CONFIG_X86) + struct cpuinfo_x86 *c = &cpu_data(0); + + if (c->x86_vendor == X86_VENDOR_INTEL) + return false; +#endif + return true; +} + /** * amdgpu_device_should_use_aspm - check if the device should program ASPM * diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h index 6a0ac0bbaace..355c156d871a 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h +++ b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h @@ -295,5 +295,9 @@ int smu_v13_0_get_pptable_from_firmware(struct smu_context *smu, uint32_t *size, uint32_t pptable_id); +int smu_v13_0_update_pcie_parameters(struct smu_context *smu, + uint32_t pcie_gen_cap, + uint32_t pcie_width_cap); + #endif #endif diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c index 9cd005131f56..3bb18396d2f9 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c @@ -2113,7 +2113,6 @@ static int arcturus_i2c_xfer(struct i2c_adapter *i2c_adap, } mutex_lock(&adev->pm.mutex); r = smu_cmn_update_table(smu, SMU_TABLE_I2C_COMMANDS, 0, req, true); - mutex_unlock(&adev->pm.mutex); if (r) goto fail; @@ -2130,6 +2129,7 @@ static int arcturus_i2c_xfer(struct i2c_adapter *i2c_adap, } r = num_msgs; fail: + mutex_unlock(&adev->pm.mutex); kfree(req); return r; } diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c index c94d825a871b..95f6d821bacb 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c @@ -3021,7 +3021,6 @@ static int navi10_i2c_xfer(struct i2c_adapter *i2c_adap, } mutex_lock(&adev->pm.mutex); r = smu_cmn_update_table(smu, SMU_TABLE_I2C_COMMANDS, 0, req, true); - mutex_unlock(&adev->pm.mutex); if (r) goto fail; @@ -3038,6 +3037,7 @@ static int navi10_i2c_xfer(struct i2c_adapter *i2c_adap, } r = num_msgs; fail: + mutex_unlock(&adev->pm.mutex); kfree(req); return r; } diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c index f7ed3e655e39..f6599c00a6fd 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c @@ -2077,89 +2077,36 @@ static int sienna_cichlid_display_disable_memory_clock_switch(struct smu_context return ret; } -static void sienna_cichlid_get_override_pcie_settings(struct smu_context *smu, - uint32_t *gen_speed_override, - uint32_t *lane_width_override) -{ - struct amdgpu_device *adev = smu->adev; - - *gen_speed_override = 0xff; - *lane_width_override = 0xff; - - switch (adev->pdev->device) { - case 0x73A0: - case 0x73A1: - case 0x73A2: - case 0x73A3: - case 0x73AB: - case 0x73AE: - /* Bit 7:0: PCIE lane width, 1 to 7 corresponds is x1 to x32 */ - *lane_width_override = 6; - break; - case 0x73E0: - case 0x73E1: - case 0x73E3: - *lane_width_override = 4; - break; - case 0x7420: - case 0x7421: - case 0x7422: - case 0x7423: - case 0x7424: - *lane_width_override = 3; - break; - default: - break; - } -} - -#define MAX(a, b) ((a) > (b) ? (a) : (b)) - static int sienna_cichlid_update_pcie_parameters(struct smu_context *smu, uint32_t pcie_gen_cap, uint32_t pcie_width_cap) { struct smu_11_0_dpm_context *dpm_context = smu->smu_dpm.dpm_context; struct smu_11_0_pcie_table *pcie_table = &dpm_context->dpm_tables.pcie_table; - uint32_t gen_speed_override, lane_width_override; - uint8_t *table_member1, *table_member2; - uint32_t min_gen_speed, max_gen_speed; - uint32_t min_lane_width, max_lane_width; - uint32_t smu_pcie_arg; + u32 smu_pcie_arg; int ret, i; - GET_PPTABLE_MEMBER(PcieGenSpeed, &table_member1); - GET_PPTABLE_MEMBER(PcieLaneCount, &table_member2); - - sienna_cichlid_get_override_pcie_settings(smu, - &gen_speed_override, - &lane_width_override); + /* PCIE gen speed and lane width override */ + if (!amdgpu_device_pcie_dynamic_switching_supported()) { + if (pcie_table->pcie_gen[NUM_LINK_LEVELS - 1] < pcie_gen_cap) + pcie_gen_cap = pcie_table->pcie_gen[NUM_LINK_LEVELS - 1]; - /* PCIE gen speed override */ - if (gen_speed_override != 0xff) { - min_gen_speed = MIN(pcie_gen_cap, gen_speed_override); - max_gen_speed = MIN(pcie_gen_cap, gen_speed_override); - } else { - min_gen_speed = MAX(0, table_member1[0]); - max_gen_speed = MIN(pcie_gen_cap, table_member1[1]); - min_gen_speed = min_gen_speed > max_gen_speed ? - max_gen_speed : min_gen_speed; - } - pcie_table->pcie_gen[0] = min_gen_speed; - pcie_table->pcie_gen[1] = max_gen_speed; + if (pcie_table->pcie_lane[NUM_LINK_LEVELS - 1] < pcie_width_cap) + pcie_width_cap = pcie_table->pcie_lane[NUM_LINK_LEVELS - 1]; - /* PCIE lane width override */ - if (lane_width_override != 0xff) { - min_lane_width = MIN(pcie_width_cap, lane_width_override); - max_lane_width = MIN(pcie_width_cap, lane_width_override); + /* Force all levels to use the same settings */ + for (i = 0; i < NUM_LINK_LEVELS; i++) { + pcie_table->pcie_gen[i] = pcie_gen_cap; + pcie_table->pcie_lane[i] = pcie_width_cap; + } } else { - min_lane_width = MAX(1, table_member2[0]); - max_lane_width = MIN(pcie_width_cap, table_member2[1]); - min_lane_width = min_lane_width > max_lane_width ? - max_lane_width : min_lane_width; + for (i = 0; i < NUM_LINK_LEVELS; i++) { + if (pcie_table->pcie_gen[i] > pcie_gen_cap) + pcie_table->pcie_gen[i] = pcie_gen_cap; + if (pcie_table->pcie_lane[i] > pcie_width_cap) + pcie_table->pcie_lane[i] = pcie_width_cap; + } } - pcie_table->pcie_lane[0] = min_lane_width; - pcie_table->pcie_lane[1] = max_lane_width; for (i = 0; i < NUM_LINK_LEVELS; i++) { smu_pcie_arg = (i << 16 | @@ -3842,7 +3789,6 @@ static int sienna_cichlid_i2c_xfer(struct i2c_adapter *i2c_adap, } mutex_lock(&adev->pm.mutex); r = smu_cmn_update_table(smu, SMU_TABLE_I2C_COMMANDS, 0, req, true); - mutex_unlock(&adev->pm.mutex); if (r) goto fail; @@ -3859,6 +3805,7 @@ static int sienna_cichlid_i2c_xfer(struct i2c_adapter *i2c_adap, } r = num_msgs; fail: + mutex_unlock(&adev->pm.mutex); kfree(req); return r; } diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c index e80f122d8aec..ce50ef46e73f 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c @@ -1525,7 +1525,6 @@ static int aldebaran_i2c_xfer(struct i2c_adapter *i2c_adap, } mutex_lock(&adev->pm.mutex); r = smu_cmn_update_table(smu, SMU_TABLE_I2C_COMMANDS, 0, req, true); - mutex_unlock(&adev->pm.mutex); if (r) goto fail; @@ -1542,6 +1541,7 @@ static int aldebaran_i2c_xfer(struct i2c_adapter *i2c_adap, } r = num_msgs; fail: + mutex_unlock(&adev->pm.mutex); kfree(req); return r; } diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c index 3856da6c3f3d..9b62b45ebb7f 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c @@ -2424,3 +2424,51 @@ int smu_v13_0_mode1_reset(struct smu_context *smu) return ret; } + +int smu_v13_0_update_pcie_parameters(struct smu_context *smu, + uint32_t pcie_gen_cap, + uint32_t pcie_width_cap) +{ + struct smu_13_0_dpm_context *dpm_context = smu->smu_dpm.dpm_context; + struct smu_13_0_pcie_table *pcie_table = + &dpm_context->dpm_tables.pcie_table; + int num_of_levels = pcie_table->num_of_link_levels; + uint32_t smu_pcie_arg; + int ret, i; + + if (!amdgpu_device_pcie_dynamic_switching_supported()) { + if (pcie_table->pcie_gen[num_of_levels - 1] < pcie_gen_cap) + pcie_gen_cap = pcie_table->pcie_gen[num_of_levels - 1]; + + if (pcie_table->pcie_lane[num_of_levels - 1] < pcie_width_cap) + pcie_width_cap = pcie_table->pcie_lane[num_of_levels - 1]; + + /* Force all levels to use the same settings */ + for (i = 0; i < num_of_levels; i++) { + pcie_table->pcie_gen[i] = pcie_gen_cap; + pcie_table->pcie_lane[i] = pcie_width_cap; + } + } else { + for (i = 0; i < num_of_levels; i++) { + if (pcie_table->pcie_gen[i] > pcie_gen_cap) + pcie_table->pcie_gen[i] = pcie_gen_cap; + if (pcie_table->pcie_lane[i] > pcie_width_cap) + pcie_table->pcie_lane[i] = pcie_width_cap; + } + } + + for (i = 0; i < num_of_levels; i++) { + smu_pcie_arg = i << 16; + smu_pcie_arg |= pcie_table->pcie_gen[i] << 8; + smu_pcie_arg |= pcie_table->pcie_lane[i]; + + ret = smu_cmn_send_smc_msg_with_param(smu, + SMU_MSG_OverridePcieParameters, + smu_pcie_arg, + NULL); + if (ret) + return ret; + } + + return 0; +} diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c index 124287cbbff8..b9bde5fa8f8f 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c @@ -1645,37 +1645,6 @@ static int smu_v13_0_0_force_clk_levels(struct smu_context *smu, return ret; } -static int smu_v13_0_0_update_pcie_parameters(struct smu_context *smu, - uint32_t pcie_gen_cap, - uint32_t pcie_width_cap) -{ - struct smu_13_0_dpm_context *dpm_context = smu->smu_dpm.dpm_context; - struct smu_13_0_pcie_table *pcie_table = - &dpm_context->dpm_tables.pcie_table; - uint32_t smu_pcie_arg; - int ret, i; - - for (i = 0; i < pcie_table->num_of_link_levels; i++) { - if (pcie_table->pcie_gen[i] > pcie_gen_cap) - pcie_table->pcie_gen[i] = pcie_gen_cap; - if (pcie_table->pcie_lane[i] > pcie_width_cap) - pcie_table->pcie_lane[i] = pcie_width_cap; - - smu_pcie_arg = i << 16; - smu_pcie_arg |= pcie_table->pcie_gen[i] << 8; - smu_pcie_arg |= pcie_table->pcie_lane[i]; - - ret = smu_cmn_send_smc_msg_with_param(smu, - SMU_MSG_OverridePcieParameters, - smu_pcie_arg, - NULL); - if (ret) - return ret; - } - - return 0; -} - static const struct smu_temperature_range smu13_thermal_policy[] = { {-273150, 99000, 99000, -273150, 99000, 99000, -273150, 99000, 99000}, { 120000, 120000, 120000, 120000, 120000, 120000, 120000, 120000, 120000}, @@ -2320,7 +2289,6 @@ static int smu_v13_0_0_i2c_xfer(struct i2c_adapter *i2c_adap, } mutex_lock(&adev->pm.mutex); r = smu_cmn_update_table(smu, SMU_TABLE_I2C_COMMANDS, 0, req, true); - mutex_unlock(&adev->pm.mutex); if (r) goto fail; @@ -2337,6 +2305,7 @@ static int smu_v13_0_0_i2c_xfer(struct i2c_adapter *i2c_adap, } r = num_msgs; fail: + mutex_unlock(&adev->pm.mutex); kfree(req); return r; } @@ -2654,7 +2623,7 @@ static const struct pptable_funcs smu_v13_0_0_ppt_funcs = { .feature_is_enabled = smu_cmn_feature_is_enabled, .print_clk_levels = smu_v13_0_0_print_clk_levels, .force_clk_levels = smu_v13_0_0_force_clk_levels, - .update_pcie_parameters = smu_v13_0_0_update_pcie_parameters, + .update_pcie_parameters = smu_v13_0_update_pcie_parameters, .get_thermal_temperature_range = smu_v13_0_0_get_thermal_temperature_range, .register_irq_handler = smu_v13_0_register_irq_handler, .enable_thermal_alert = smu_v13_0_enable_thermal_alert, diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c index 6ef12252beb5..1ac552142763 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c @@ -1763,7 +1763,6 @@ static int smu_v13_0_6_i2c_xfer(struct i2c_adapter *i2c_adap, } mutex_lock(&adev->pm.mutex); r = smu_v13_0_6_request_i2c_xfer(smu, req); - mutex_unlock(&adev->pm.mutex); if (r) goto fail; @@ -1780,6 +1779,7 @@ static int smu_v13_0_6_i2c_xfer(struct i2c_adapter *i2c_adap, } r = num_msgs; fail: + mutex_unlock(&adev->pm.mutex); kfree(req); return r; } diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c index cda4e818aab7..3ba02131e682 100644 --- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c +++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c @@ -1635,37 +1635,6 @@ static int smu_v13_0_7_force_clk_levels(struct smu_context *smu, return ret; } -static int smu_v13_0_7_update_pcie_parameters(struct smu_context *smu, - uint32_t pcie_gen_cap, - uint32_t pcie_width_cap) -{ - struct smu_13_0_dpm_context *dpm_context = smu->smu_dpm.dpm_context; - struct smu_13_0_pcie_table *pcie_table = - &dpm_context->dpm_tables.pcie_table; - uint32_t smu_pcie_arg; - int ret, i; - - for (i = 0; i < pcie_table->num_of_link_levels; i++) { - if (pcie_table->pcie_gen[i] > pcie_gen_cap) - pcie_table->pcie_gen[i] = pcie_gen_cap; - if (pcie_table->pcie_lane[i] > pcie_width_cap) - pcie_table->pcie_lane[i] = pcie_width_cap; - - smu_pcie_arg = i << 16; - smu_pcie_arg |= pcie_table->pcie_gen[i] << 8; - smu_pcie_arg |= pcie_table->pcie_lane[i]; - - ret = smu_cmn_send_smc_msg_with_param(smu, - SMU_MSG_OverridePcieParameters, - smu_pcie_arg, - NULL); - if (ret) - return ret; - } - - return 0; -} - static const struct smu_temperature_range smu13_thermal_policy[] = { {-273150, 99000, 99000, -273150, 99000, 99000, -273150, 99000, 99000}, @@ -2234,7 +2203,7 @@ static const struct pptable_funcs smu_v13_0_7_ppt_funcs = { .feature_is_enabled = smu_cmn_feature_is_enabled, .print_clk_levels = smu_v13_0_7_print_clk_levels, .force_clk_levels = smu_v13_0_7_force_clk_levels, - .update_pcie_parameters = smu_v13_0_7_update_pcie_parameters, + .update_pcie_parameters = smu_v13_0_update_pcie_parameters, .get_thermal_temperature_range = smu_v13_0_7_get_thermal_temperature_range, .register_irq_handler = smu_v13_0_register_irq_handler, .enable_thermal_alert = smu_v13_0_enable_thermal_alert, diff --git a/drivers/gpu/drm/armada/armada_fbdev.c b/drivers/gpu/drm/armada/armada_fbdev.c index 3943e89cc06c..e40a95e51785 100644 --- a/drivers/gpu/drm/armada/armada_fbdev.c +++ b/drivers/gpu/drm/armada/armada_fbdev.c @@ -209,10 +209,6 @@ void armada_fbdev_setup(struct drm_device *dev) goto err_drm_client_init; } - ret = armada_fbdev_client_hotplug(&fbh->client); - if (ret) - drm_dbg_kms(dev, "client hotplug ret=%d\n", ret); - drm_client_register(&fbh->client); return; diff --git a/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c b/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c index 9d6dcaf317a1..7b66f362afd8 100644 --- a/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c +++ b/drivers/gpu/drm/bridge/synopsys/dw-hdmi.c @@ -1426,9 +1426,9 @@ void dw_hdmi_set_high_tmds_clock_ratio(struct dw_hdmi *hdmi, /* Control for TMDS Bit Period/TMDS Clock-Period Ratio */ if (dw_hdmi_support_scdc(hdmi, display)) { if (mtmdsclock > HDMI14_MAX_TMDSCLK) - drm_scdc_set_high_tmds_clock_ratio(&hdmi->connector, 1); + drm_scdc_set_high_tmds_clock_ratio(hdmi->curr_conn, 1); else - drm_scdc_set_high_tmds_clock_ratio(&hdmi->connector, 0); + drm_scdc_set_high_tmds_clock_ratio(hdmi->curr_conn, 0); } } EXPORT_SYMBOL_GPL(dw_hdmi_set_high_tmds_clock_ratio); @@ -2116,7 +2116,7 @@ static void hdmi_av_composer(struct dw_hdmi *hdmi, min_t(u8, bytes, SCDC_MIN_SOURCE_VERSION)); /* Enabled Scrambling in the Sink */ - drm_scdc_set_scrambling(&hdmi->connector, 1); + drm_scdc_set_scrambling(hdmi->curr_conn, 1); /* * To activate the scrambler feature, you must ensure @@ -2132,7 +2132,7 @@ static void hdmi_av_composer(struct dw_hdmi *hdmi, hdmi_writeb(hdmi, 0, HDMI_FC_SCRAMBLER_CTRL); hdmi_writeb(hdmi, (u8)~HDMI_MC_SWRSTZ_TMDSSWRST_REQ, HDMI_MC_SWRSTZ); - drm_scdc_set_scrambling(&hdmi->connector, 0); + drm_scdc_set_scrambling(hdmi->curr_conn, 0); } } @@ -3553,6 +3553,7 @@ struct dw_hdmi *dw_hdmi_probe(struct platform_device *pdev, hdmi->bridge.ops = DRM_BRIDGE_OP_DETECT | DRM_BRIDGE_OP_EDID | DRM_BRIDGE_OP_HPD; hdmi->bridge.interlace_allowed = true; + hdmi->bridge.ddc = hdmi->ddc; #ifdef CONFIG_OF hdmi->bridge.of_node = pdev->dev.of_node; #endif diff --git a/drivers/gpu/drm/bridge/ti-sn65dsi86.c b/drivers/gpu/drm/bridge/ti-sn65dsi86.c index c499a14d0b98..f448b903e190 100644 --- a/drivers/gpu/drm/bridge/ti-sn65dsi86.c +++ b/drivers/gpu/drm/bridge/ti-sn65dsi86.c @@ -170,10 +170,10 @@ * @pwm_refclk_freq: Cache for the reference clock input to the PWM. */ struct ti_sn65dsi86 { - struct auxiliary_device bridge_aux; - struct auxiliary_device gpio_aux; - struct auxiliary_device aux_aux; - struct auxiliary_device pwm_aux; + struct auxiliary_device *bridge_aux; + struct auxiliary_device *gpio_aux; + struct auxiliary_device *aux_aux; + struct auxiliary_device *pwm_aux; struct device *dev; struct regmap *regmap; @@ -468,27 +468,34 @@ static void ti_sn65dsi86_delete_aux(void *data) auxiliary_device_delete(data); } -/* - * AUX bus docs say that a non-NULL release is mandatory, but it makes no - * sense for the model used here where all of the aux devices are allocated - * in the single shared structure. We'll use this noop as a workaround. - */ -static void ti_sn65dsi86_noop(struct device *dev) {} +static void ti_sn65dsi86_aux_device_release(struct device *dev) +{ + struct auxiliary_device *aux = container_of(dev, struct auxiliary_device, dev); + + kfree(aux); +} static int ti_sn65dsi86_add_aux_device(struct ti_sn65dsi86 *pdata, - struct auxiliary_device *aux, + struct auxiliary_device **aux_out, const char *name) { struct device *dev = pdata->dev; + struct auxiliary_device *aux; int ret; + aux = kzalloc(sizeof(*aux), GFP_KERNEL); + if (!aux) + return -ENOMEM; + aux->name = name; aux->dev.parent = dev; - aux->dev.release = ti_sn65dsi86_noop; + aux->dev.release = ti_sn65dsi86_aux_device_release; device_set_of_node_from_dev(&aux->dev, dev); ret = auxiliary_device_init(aux); - if (ret) + if (ret) { + kfree(aux); return ret; + } ret = devm_add_action_or_reset(dev, ti_sn65dsi86_uninit_aux, aux); if (ret) return ret; @@ -497,6 +504,8 @@ static int ti_sn65dsi86_add_aux_device(struct ti_sn65dsi86 *pdata, if (ret) return ret; ret = devm_add_action_or_reset(dev, ti_sn65dsi86_delete_aux, aux); + if (!ret) + *aux_out = aux; return ret; } diff --git a/drivers/gpu/drm/drm_client.c b/drivers/gpu/drm/drm_client.c index f6292ba0e6fc..037e36f2049c 100644 --- a/drivers/gpu/drm/drm_client.c +++ b/drivers/gpu/drm/drm_client.c @@ -122,13 +122,34 @@ EXPORT_SYMBOL(drm_client_init); * drm_client_register() it is no longer permissible to call drm_client_release() * directly (outside the unregister callback), instead cleanup will happen * automatically on driver unload. + * + * Registering a client generates a hotplug event that allows the client + * to set up its display from pre-existing outputs. The client must have + * initialized its state to able to handle the hotplug event successfully. */ void drm_client_register(struct drm_client_dev *client) { struct drm_device *dev = client->dev; + int ret; mutex_lock(&dev->clientlist_mutex); list_add(&client->list, &dev->clientlist); + + if (client->funcs && client->funcs->hotplug) { + /* + * Perform an initial hotplug event to pick up the + * display configuration for the client. This step + * has to be performed *after* registering the client + * in the list of clients, or a concurrent hotplug + * event might be lost; leaving the display off. + * + * Hold the clientlist_mutex as for a regular hotplug + * event. + */ + ret = client->funcs->hotplug(client); + if (ret) + drm_dbg_kms(dev, "client hotplug ret=%d\n", ret); + } mutex_unlock(&dev->clientlist_mutex); } EXPORT_SYMBOL(drm_client_register); diff --git a/drivers/gpu/drm/drm_fbdev_dma.c b/drivers/gpu/drm/drm_fbdev_dma.c index d86773fa8ab0..f353daff65e1 100644 --- a/drivers/gpu/drm/drm_fbdev_dma.c +++ b/drivers/gpu/drm/drm_fbdev_dma.c @@ -217,7 +217,7 @@ static const struct drm_client_funcs drm_fbdev_dma_client_funcs = { * drm_fbdev_dma_setup() - Setup fbdev emulation for GEM DMA helpers * @dev: DRM device * @preferred_bpp: Preferred bits per pixel for the device. - * @dev->mode_config.preferred_depth is used if this is zero. + * 32 is used if this is zero. * * This function sets up fbdev emulation for GEM DMA drivers that support * dumb buffers with a virtual address and that can be mmap'ed. @@ -252,10 +252,6 @@ void drm_fbdev_dma_setup(struct drm_device *dev, unsigned int preferred_bpp) goto err_drm_client_init; } - ret = drm_fbdev_dma_client_hotplug(&fb_helper->client); - if (ret) - drm_dbg_kms(dev, "client hotplug ret=%d\n", ret); - drm_client_register(&fb_helper->client); return; diff --git a/drivers/gpu/drm/drm_fbdev_generic.c b/drivers/gpu/drm/drm_fbdev_generic.c index 98ae703848a0..b9343fb6cf13 100644 --- a/drivers/gpu/drm/drm_fbdev_generic.c +++ b/drivers/gpu/drm/drm_fbdev_generic.c @@ -339,10 +339,6 @@ void drm_fbdev_generic_setup(struct drm_device *dev, unsigned int preferred_bpp) goto err_drm_client_init; } - ret = drm_fbdev_generic_client_hotplug(&fb_helper->client); - if (ret) - drm_dbg_kms(dev, "client hotplug ret=%d\n", ret); - drm_client_register(&fb_helper->client); return; diff --git a/drivers/gpu/drm/drm_syncobj.c b/drivers/gpu/drm/drm_syncobj.c index 0c2be8360525..e592c5da70ce 100644 --- a/drivers/gpu/drm/drm_syncobj.c +++ b/drivers/gpu/drm/drm_syncobj.c @@ -353,10 +353,10 @@ EXPORT_SYMBOL(drm_syncobj_replace_fence); */ static int drm_syncobj_assign_null_handle(struct drm_syncobj *syncobj) { - struct dma_fence *fence = dma_fence_allocate_private_stub(); + struct dma_fence *fence = dma_fence_allocate_private_stub(ktime_get()); - if (IS_ERR(fence)) - return PTR_ERR(fence); + if (!fence) + return -ENOMEM; drm_syncobj_replace_fence(syncobj, fence); dma_fence_put(fence); diff --git a/drivers/gpu/drm/exynos/exynos_drm_fbdev.c b/drivers/gpu/drm/exynos/exynos_drm_fbdev.c index fdf65587f1fe..226310c765d8 100644 --- a/drivers/gpu/drm/exynos/exynos_drm_fbdev.c +++ b/drivers/gpu/drm/exynos/exynos_drm_fbdev.c @@ -215,10 +215,6 @@ void exynos_drm_fbdev_setup(struct drm_device *dev) if (ret) goto err_drm_client_init; - ret = exynos_drm_fbdev_client_hotplug(&fb_helper->client); - if (ret) - drm_dbg_kms(dev, "client hotplug ret=%d\n", ret); - drm_client_register(&fb_helper->client); return; diff --git a/drivers/gpu/drm/gma500/fbdev.c b/drivers/gpu/drm/gma500/fbdev.c index 955cbe9f05a7..054426549fc6 100644 --- a/drivers/gpu/drm/gma500/fbdev.c +++ b/drivers/gpu/drm/gma500/fbdev.c @@ -328,10 +328,6 @@ void psb_fbdev_setup(struct drm_psb_private *dev_priv) goto err_drm_fb_helper_unprepare; } - ret = psb_fbdev_client_hotplug(&fb_helper->client); - if (ret) - drm_dbg_kms(dev, "client hotplug ret=%d\n", ret); - drm_client_register(&fb_helper->client); return; diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c index d8533603ad05..16603d591f56 100644 --- a/drivers/gpu/drm/i915/display/intel_display.c +++ b/drivers/gpu/drm/i915/display/intel_display.c @@ -4564,7 +4564,6 @@ copy_bigjoiner_crtc_state_modeset(struct intel_atomic_state *state, saved_state->uapi = slave_crtc_state->uapi; saved_state->scaler_state = slave_crtc_state->scaler_state; saved_state->shared_dpll = slave_crtc_state->shared_dpll; - saved_state->dpll_hw_state = slave_crtc_state->dpll_hw_state; saved_state->crc_enabled = slave_crtc_state->crc_enabled; intel_crtc_free_hw_state(slave_crtc_state); diff --git a/drivers/gpu/drm/i915/gt/gen8_ppgtt.c b/drivers/gpu/drm/i915/gt/gen8_ppgtt.c index f948d33e5ec5..c8568e5d1147 100644 --- a/drivers/gpu/drm/i915/gt/gen8_ppgtt.c +++ b/drivers/gpu/drm/i915/gt/gen8_ppgtt.c @@ -37,9 +37,6 @@ static u64 gen8_pte_encode(dma_addr_t addr, if (unlikely(flags & PTE_READ_ONLY)) pte &= ~GEN8_PAGE_RW; - if (flags & PTE_LM) - pte |= GEN12_PPGTT_PTE_LM; - /* * For pre-gen12 platforms pat_index is the same as enum * i915_cache_level, so the switch-case here is still valid. diff --git a/drivers/gpu/drm/i915/gt/intel_gtt.c b/drivers/gpu/drm/i915/gt/intel_gtt.c index 2f6a9be0ffe6..731d9f2bbc56 100644 --- a/drivers/gpu/drm/i915/gt/intel_gtt.c +++ b/drivers/gpu/drm/i915/gt/intel_gtt.c @@ -670,7 +670,7 @@ __vm_create_scratch_for_read(struct i915_address_space *vm, unsigned long size) if (IS_ERR(obj)) return ERR_CAST(obj); - i915_gem_object_set_cache_coherency(obj, I915_CACHING_CACHED); + i915_gem_object_set_cache_coherency(obj, I915_CACHE_LLC); vma = i915_vma_instance(obj, vm, NULL); if (IS_ERR(vma)) { diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c index 0a111b281578..7413c11fb562 100644 --- a/drivers/gpu/drm/i915/i915_perf.c +++ b/drivers/gpu/drm/i915/i915_perf.c @@ -868,8 +868,17 @@ static int gen8_append_oa_reports(struct i915_perf_stream *stream, oa_report_id_clear(stream, report32); oa_timestamp_clear(stream, report32); } else { + u8 *oa_buf_end = stream->oa_buffer.vaddr + + OA_BUFFER_SIZE; + u32 part = oa_buf_end - (u8 *)report32; + /* Zero out the entire report */ - memset(report32, 0, report_size); + if (report_size <= part) { + memset(report32, 0, report_size); + } else { + memset(report32, 0, part); + memset(oa_buf_base, 0, report_size - part); + } } } diff --git a/drivers/gpu/drm/msm/msm_fbdev.c b/drivers/gpu/drm/msm/msm_fbdev.c index b933a85420f6..bf1e17dc4550 100644 --- a/drivers/gpu/drm/msm/msm_fbdev.c +++ b/drivers/gpu/drm/msm/msm_fbdev.c @@ -246,10 +246,6 @@ void msm_fbdev_setup(struct drm_device *dev) goto err_drm_fb_helper_unprepare; } - ret = msm_fbdev_client_hotplug(&helper->client); - if (ret) - drm_dbg_kms(dev, "client hotplug ret=%d\n", ret); - drm_client_register(&helper->client); return; diff --git a/drivers/gpu/drm/nouveau/dispnv50/disp.c b/drivers/gpu/drm/nouveau/dispnv50/disp.c index 42e1665ba11a..38d3fad0d97a 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/disp.c +++ b/drivers/gpu/drm/nouveau/dispnv50/disp.c @@ -910,15 +910,19 @@ nv50_msto_prepare(struct drm_atomic_state *state, struct nouveau_drm *drm = nouveau_drm(msto->encoder.dev); struct nv50_mstc *mstc = msto->mstc; struct nv50_mstm *mstm = mstc->mstm; - struct drm_dp_mst_atomic_payload *payload; + struct drm_dp_mst_topology_state *old_mst_state; + struct drm_dp_mst_atomic_payload *payload, *old_payload; NV_ATOMIC(drm, "%s: msto prepare\n", msto->encoder.name); + old_mst_state = drm_atomic_get_old_mst_topology_state(state, mgr); + payload = drm_atomic_get_mst_payload_state(mst_state, mstc->port); + old_payload = drm_atomic_get_mst_payload_state(old_mst_state, mstc->port); // TODO: Figure out if we want to do a better job of handling VCPI allocation failures here? if (msto->disabled) { - drm_dp_remove_payload(mgr, mst_state, payload, payload); + drm_dp_remove_payload(mgr, mst_state, old_payload, payload); nvif_outp_dp_mst_vcpi(&mstm->outp->outp, msto->head->base.index, 0, 0, 0, 0); } else { diff --git a/drivers/gpu/drm/nouveau/nouveau_chan.c b/drivers/gpu/drm/nouveau/nouveau_chan.c index e648ecd0c1a0..3dfbc374478e 100644 --- a/drivers/gpu/drm/nouveau/nouveau_chan.c +++ b/drivers/gpu/drm/nouveau/nouveau_chan.c @@ -90,6 +90,7 @@ nouveau_channel_del(struct nouveau_channel **pchan) if (cli) nouveau_svmm_part(chan->vmm->svmm, chan->inst); + nvif_object_dtor(&chan->blit); nvif_object_dtor(&chan->nvsw); nvif_object_dtor(&chan->gart); nvif_object_dtor(&chan->vram); diff --git a/drivers/gpu/drm/nouveau/nouveau_chan.h b/drivers/gpu/drm/nouveau/nouveau_chan.h index e06a8ffed31a..bad7466bd0d5 100644 --- a/drivers/gpu/drm/nouveau/nouveau_chan.h +++ b/drivers/gpu/drm/nouveau/nouveau_chan.h @@ -53,6 +53,7 @@ struct nouveau_channel { u32 user_put; struct nvif_object user; + struct nvif_object blit; struct nvif_event kill; atomic_t killed; diff --git a/drivers/gpu/drm/nouveau/nouveau_drm.c b/drivers/gpu/drm/nouveau/nouveau_drm.c index 7aac9384600e..40fb9a834918 100644 --- a/drivers/gpu/drm/nouveau/nouveau_drm.c +++ b/drivers/gpu/drm/nouveau/nouveau_drm.c @@ -375,15 +375,29 @@ nouveau_accel_gr_init(struct nouveau_drm *drm) ret = nvif_object_ctor(&drm->channel->user, "drmNvsw", NVDRM_NVSW, nouveau_abi16_swclass(drm), NULL, 0, &drm->channel->nvsw); + + if (ret == 0 && device->info.chipset >= 0x11) { + ret = nvif_object_ctor(&drm->channel->user, "drmBlit", + 0x005f, 0x009f, + NULL, 0, &drm->channel->blit); + } + if (ret == 0) { struct nvif_push *push = drm->channel->chan.push; - ret = PUSH_WAIT(push, 2); - if (ret == 0) + ret = PUSH_WAIT(push, 8); + if (ret == 0) { + if (device->info.chipset >= 0x11) { + PUSH_NVSQ(push, NV05F, 0x0000, drm->channel->blit.handle); + PUSH_NVSQ(push, NV09F, 0x0120, 0, + 0x0124, 1, + 0x0128, 2); + } PUSH_NVSQ(push, NV_SW, 0x0000, drm->channel->nvsw.handle); + } } if (ret) { - NV_ERROR(drm, "failed to allocate sw class, %d\n", ret); + NV_ERROR(drm, "failed to allocate sw or blit class, %d\n", ret); nouveau_accel_gr_fini(drm); return; } diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/g94.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/g94.c index a4853c4e5ee3..67ef889a0c5f 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/g94.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/g94.c @@ -295,6 +295,7 @@ g94_sor = { .clock = nv50_sor_clock, .war_2 = g94_sor_war_2, .war_3 = g94_sor_war_3, + .hdmi = &g84_sor_hdmi, .dp = &g94_sor_dp, }; diff --git a/drivers/gpu/drm/nouveau/nvkm/engine/disp/gt215.c b/drivers/gpu/drm/nouveau/nvkm/engine/disp/gt215.c index a2c7c6f83dcd..506ffbe7b842 100644 --- a/drivers/gpu/drm/nouveau/nvkm/engine/disp/gt215.c +++ b/drivers/gpu/drm/nouveau/nvkm/engine/disp/gt215.c @@ -125,7 +125,7 @@ gt215_sor_hdmi_infoframe_avi(struct nvkm_ior *ior, int head, void *data, u32 siz pack_hdmi_infoframe(&avi, data, size); nvkm_mask(device, 0x61c520 + soff, 0x00000001, 0x00000000); - if (size) + if (!size) return; nvkm_wr32(device, 0x61c528 + soff, avi.header); diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/acr/base.c b/drivers/gpu/drm/nouveau/nvkm/subdev/acr/base.c index 795f3a649b12..9b8ca4e898f9 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/acr/base.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/acr/base.c @@ -224,7 +224,7 @@ nvkm_acr_oneinit(struct nvkm_subdev *subdev) u64 falcons; int ret, i; - if (list_empty(&acr->hsfw)) { + if (list_empty(&acr->hsfw) || !acr->func || !acr->func->wpr_layout) { nvkm_debug(subdev, "No HSFW(s)\n"); nvkm_acr_cleanup(acr); return 0; diff --git a/drivers/gpu/drm/omapdrm/omap_fbdev.c b/drivers/gpu/drm/omapdrm/omap_fbdev.c index b7ccce0704a3..fe6639c1cdf3 100644 --- a/drivers/gpu/drm/omapdrm/omap_fbdev.c +++ b/drivers/gpu/drm/omapdrm/omap_fbdev.c @@ -318,10 +318,6 @@ void omap_fbdev_setup(struct drm_device *dev) INIT_WORK(&fbdev->work, pan_worker); - ret = omap_fbdev_client_hotplug(&helper->client); - if (ret) - drm_dbg_kms(dev, "client hotplug ret=%d\n", ret); - drm_client_register(&helper->client); return; diff --git a/drivers/gpu/drm/panel/panel-simple.c b/drivers/gpu/drm/panel/panel-simple.c index a247a0e7c799..aaba36b3a674 100644 --- a/drivers/gpu/drm/panel/panel-simple.c +++ b/drivers/gpu/drm/panel/panel-simple.c @@ -2178,6 +2178,7 @@ static const struct panel_desc innolux_at043tn24 = { .height = 54, }, .bus_format = MEDIA_BUS_FMT_RGB888_1X24, + .connector_type = DRM_MODE_CONNECTOR_DPI, .bus_flags = DRM_BUS_FLAG_DE_HIGH | DRM_BUS_FLAG_PIXDATA_DRIVE_POSEDGE, }; @@ -3202,6 +3203,7 @@ static const struct drm_display_mode powertip_ph800480t013_idf02_mode = { .vsync_start = 480 + 49, .vsync_end = 480 + 49 + 2, .vtotal = 480 + 49 + 2 + 22, + .flags = DRM_MODE_FLAG_NVSYNC | DRM_MODE_FLAG_NHSYNC, }; static const struct panel_desc powertip_ph800480t013_idf02 = { diff --git a/drivers/gpu/drm/radeon/radeon_fbdev.c b/drivers/gpu/drm/radeon/radeon_fbdev.c index ab9c1abbac97..f941e2e7cae6 100644 --- a/drivers/gpu/drm/radeon/radeon_fbdev.c +++ b/drivers/gpu/drm/radeon/radeon_fbdev.c @@ -383,10 +383,6 @@ void radeon_fbdev_setup(struct radeon_device *rdev) goto err_drm_client_init; } - ret = radeon_fbdev_client_hotplug(&fb_helper->client); - if (ret) - drm_dbg_kms(rdev->ddev, "client hotplug ret=%d\n", ret); - drm_client_register(&fb_helper->client); return; diff --git a/drivers/gpu/drm/scheduler/sched_entity.c b/drivers/gpu/drm/scheduler/sched_entity.c index b2bbc8a68b30..a42763e1429d 100644 --- a/drivers/gpu/drm/scheduler/sched_entity.c +++ b/drivers/gpu/drm/scheduler/sched_entity.c @@ -176,16 +176,32 @@ static void drm_sched_entity_kill_jobs_cb(struct dma_fence *f, { struct drm_sched_job *job = container_of(cb, struct drm_sched_job, finish_cb); - int r; + unsigned long index; dma_fence_put(f); /* Wait for all dependencies to avoid data corruptions */ - while (!xa_empty(&job->dependencies)) { - f = xa_erase(&job->dependencies, job->last_dependency++); - r = dma_fence_add_callback(f, &job->finish_cb, - drm_sched_entity_kill_jobs_cb); - if (!r) + xa_for_each(&job->dependencies, index, f) { + struct drm_sched_fence *s_fence = to_drm_sched_fence(f); + + if (s_fence && f == &s_fence->scheduled) { + /* The dependencies array had a reference on the scheduled + * fence, and the finished fence refcount might have + * dropped to zero. Use dma_fence_get_rcu() so we get + * a NULL fence in that case. + */ + f = dma_fence_get_rcu(&s_fence->finished); + + /* Now that we have a reference on the finished fence, + * we can release the reference the dependencies array + * had on the scheduled fence. + */ + dma_fence_put(&s_fence->scheduled); + } + + xa_erase(&job->dependencies, index); + if (f && !dma_fence_add_callback(f, &job->finish_cb, + drm_sched_entity_kill_jobs_cb)) return; dma_fence_put(f); @@ -415,8 +431,17 @@ static struct dma_fence * drm_sched_job_dependency(struct drm_sched_job *job, struct drm_sched_entity *entity) { - if (!xa_empty(&job->dependencies)) - return xa_erase(&job->dependencies, job->last_dependency++); + struct dma_fence *f; + + /* We keep the fence around, so we can iterate over all dependencies + * in drm_sched_entity_kill_jobs_cb() to ensure all deps are signaled + * before killing the job. + */ + f = xa_load(&job->dependencies, job->last_dependency); + if (f) { + job->last_dependency++; + return dma_fence_get(f); + } if (job->sched->ops->prepare_job) return job->sched->ops->prepare_job(job, entity); diff --git a/drivers/gpu/drm/scheduler/sched_fence.c b/drivers/gpu/drm/scheduler/sched_fence.c index ef120475e7c6..06cedfe4b486 100644 --- a/drivers/gpu/drm/scheduler/sched_fence.c +++ b/drivers/gpu/drm/scheduler/sched_fence.c @@ -48,8 +48,32 @@ static void __exit drm_sched_fence_slab_fini(void) kmem_cache_destroy(sched_fence_slab); } -void drm_sched_fence_scheduled(struct drm_sched_fence *fence) +static void drm_sched_fence_set_parent(struct drm_sched_fence *s_fence, + struct dma_fence *fence) { + /* + * smp_store_release() to ensure another thread racing us + * in drm_sched_fence_set_deadline_finished() sees the + * fence's parent set before test_bit() + */ + smp_store_release(&s_fence->parent, dma_fence_get(fence)); + if (test_bit(DRM_SCHED_FENCE_FLAG_HAS_DEADLINE_BIT, + &s_fence->finished.flags)) + dma_fence_set_deadline(fence, s_fence->deadline); +} + +void drm_sched_fence_scheduled(struct drm_sched_fence *fence, + struct dma_fence *parent) +{ + /* Set the parent before signaling the scheduled fence, such that, + * any waiter expecting the parent to be filled after the job has + * been scheduled (which is the case for drivers delegating waits + * to some firmware) doesn't have to busy wait for parent to show + * up. + */ + if (!IS_ERR_OR_NULL(parent)) + drm_sched_fence_set_parent(fence, parent); + dma_fence_signal(&fence->scheduled); } @@ -181,20 +205,6 @@ struct drm_sched_fence *to_drm_sched_fence(struct dma_fence *f) } EXPORT_SYMBOL(to_drm_sched_fence); -void drm_sched_fence_set_parent(struct drm_sched_fence *s_fence, - struct dma_fence *fence) -{ - /* - * smp_store_release() to ensure another thread racing us - * in drm_sched_fence_set_deadline_finished() sees the - * fence's parent set before test_bit() - */ - smp_store_release(&s_fence->parent, dma_fence_get(fence)); - if (test_bit(DRM_SCHED_FENCE_FLAG_HAS_DEADLINE_BIT, - &s_fence->finished.flags)) - dma_fence_set_deadline(fence, s_fence->deadline); -} - struct drm_sched_fence *drm_sched_fence_alloc(struct drm_sched_entity *entity, void *owner) { diff --git a/drivers/gpu/drm/scheduler/sched_main.c b/drivers/gpu/drm/scheduler/sched_main.c index 7b2bfc10c1a5..506371c42745 100644 --- a/drivers/gpu/drm/scheduler/sched_main.c +++ b/drivers/gpu/drm/scheduler/sched_main.c @@ -1043,10 +1043,9 @@ static int drm_sched_main(void *param) trace_drm_run_job(sched_job, entity); fence = sched->ops->run_job(sched_job); complete_all(&entity->entity_idle); - drm_sched_fence_scheduled(s_fence); + drm_sched_fence_scheduled(s_fence, fence); if (!IS_ERR_OR_NULL(fence)) { - drm_sched_fence_set_parent(s_fence, fence); /* Drop for original kref_init of the fence */ dma_fence_put(fence); diff --git a/drivers/gpu/drm/tegra/fbdev.c b/drivers/gpu/drm/tegra/fbdev.c index e74d9be981c7..d042234e1807 100644 --- a/drivers/gpu/drm/tegra/fbdev.c +++ b/drivers/gpu/drm/tegra/fbdev.c @@ -225,10 +225,6 @@ void tegra_fbdev_setup(struct drm_device *dev) if (ret) goto err_drm_client_init; - ret = tegra_fbdev_client_hotplug(&helper->client); - if (ret) - drm_dbg_kms(dev, "client hotplug ret=%d\n", ret); - drm_client_register(&helper->client); return; diff --git a/drivers/gpu/drm/ttm/ttm_bo.c b/drivers/gpu/drm/ttm/ttm_bo.c index bd5dae4d1624..7139a522b2f3 100644 --- a/drivers/gpu/drm/ttm/ttm_bo.c +++ b/drivers/gpu/drm/ttm/ttm_bo.c @@ -458,18 +458,18 @@ static int ttm_bo_evict(struct ttm_buffer_object *bo, goto out; } -bounce: - ret = ttm_bo_handle_move_mem(bo, evict_mem, true, ctx, &hop); - if (ret == -EMULTIHOP) { + do { + ret = ttm_bo_handle_move_mem(bo, evict_mem, true, ctx, &hop); + if (ret != -EMULTIHOP) + break; + ret = ttm_bo_bounce_temp_buffer(bo, &evict_mem, ctx, &hop); - if (ret) { - if (ret != -ERESTARTSYS && ret != -EINTR) - pr_err("Buffer eviction failed\n"); - ttm_resource_free(bo, &evict_mem); - goto out; - } - /* try and move to final place now. */ - goto bounce; + } while (!ret); + + if (ret) { + ttm_resource_free(bo, &evict_mem); + if (ret != -ERESTARTSYS && ret != -EINTR) + pr_err("Buffer eviction failed\n"); } out: return ret; @@ -517,6 +517,12 @@ static bool ttm_bo_evict_swapout_allowable(struct ttm_buffer_object *bo, { bool ret = false; + if (bo->pin_count) { + *locked = false; + *busy = false; + return false; + } + if (bo->base.resv == ctx->resv) { dma_resv_assert_held(bo->base.resv); if (ctx->allow_res_evict) @@ -1167,6 +1173,7 @@ int ttm_bo_swapout(struct ttm_buffer_object *bo, struct ttm_operation_ctx *ctx, ret = ttm_bo_handle_move_mem(bo, evict_mem, true, &ctx, &hop); if (unlikely(ret != 0)) { WARN(ret == -EMULTIHOP, "Unexpected multihop in swaput - likely driver bug.\n"); + ttm_resource_free(bo, &evict_mem); goto out; } } diff --git a/drivers/gpu/drm/ttm/ttm_resource.c b/drivers/gpu/drm/ttm/ttm_resource.c index 7333f7a87a2f..46ff9c75bb12 100644 --- a/drivers/gpu/drm/ttm/ttm_resource.c +++ b/drivers/gpu/drm/ttm/ttm_resource.c @@ -86,6 +86,8 @@ static void ttm_lru_bulk_move_pos_tail(struct ttm_lru_bulk_move_pos *pos, struct ttm_resource *res) { if (pos->last != res) { + if (pos->first == res) + pos->first = list_next_entry(res, lru); list_move(&res->lru, &pos->last->lru); pos->last = res; } @@ -111,7 +113,8 @@ static void ttm_lru_bulk_move_del(struct ttm_lru_bulk_move *bulk, { struct ttm_lru_bulk_move_pos *pos = ttm_lru_bulk_move_pos(bulk, res); - if (unlikely(pos->first == res && pos->last == res)) { + if (unlikely(WARN_ON(!pos->first || !pos->last) || + (pos->first == res && pos->last == res))) { pos->first = NULL; pos->last = NULL; } else if (pos->first == res) { diff --git a/drivers/iommu/iommu-sva.c b/drivers/iommu/iommu-sva.c index 3ebd4b6586b3..05c0fb2acbc4 100644 --- a/drivers/iommu/iommu-sva.c +++ b/drivers/iommu/iommu-sva.c @@ -34,8 +34,9 @@ static int iommu_sva_alloc_pasid(struct mm_struct *mm, ioasid_t min, ioasid_t ma } ret = ida_alloc_range(&iommu_global_pasid_ida, min, max, GFP_KERNEL); - if (ret < min) + if (ret < 0) goto out; + mm->pasid = ret; ret = 0; out: diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index da340f11c5f5..caaf563d38ae 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -2891,14 +2891,11 @@ static int iommu_setup_default_domain(struct iommu_group *group, ret = __iommu_group_set_domain_internal( group, dom, IOMMU_SET_DOMAIN_MUST_SUCCEED); if (WARN_ON(ret)) - goto out_free; + goto out_free_old; } else { ret = __iommu_group_set_domain(group, dom); - if (ret) { - iommu_domain_free(dom); - group->default_domain = old_dom; - return ret; - } + if (ret) + goto err_restore_def_domain; } /* @@ -2911,20 +2908,24 @@ static int iommu_setup_default_domain(struct iommu_group *group, for_each_group_device(group, gdev) { ret = iommu_create_device_direct_mappings(dom, gdev->dev); if (ret) - goto err_restore; + goto err_restore_domain; } } -err_restore: - if (old_dom) { +out_free_old: + if (old_dom) + iommu_domain_free(old_dom); + return ret; + +err_restore_domain: + if (old_dom) __iommu_group_set_domain_internal( group, old_dom, IOMMU_SET_DOMAIN_MUST_SUCCEED); +err_restore_def_domain: + if (old_dom) { iommu_domain_free(dom); - old_dom = NULL; + group->default_domain = old_dom; } -out_free: - if (old_dom) - iommu_domain_free(old_dom); return ret; } diff --git a/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c b/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c index 68df6d4641b5..eebf967f4711 100644 --- a/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c +++ b/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c @@ -227,6 +227,8 @@ static int __mcp251xfd_chip_set_mode(const struct mcp251xfd_priv *priv, const u8 mode_req, bool nowait) { + const struct can_bittiming *bt = &priv->can.bittiming; + unsigned long timeout_us = MCP251XFD_POLL_TIMEOUT_US; u32 con = 0, con_reqop, osc = 0; u8 mode; int err; @@ -246,12 +248,16 @@ __mcp251xfd_chip_set_mode(const struct mcp251xfd_priv *priv, if (mode_req == MCP251XFD_REG_CON_MODE_SLEEP || nowait) return 0; + if (bt->bitrate) + timeout_us = max_t(unsigned long, timeout_us, + MCP251XFD_FRAME_LEN_MAX_BITS * USEC_PER_SEC / + bt->bitrate); + err = regmap_read_poll_timeout(priv->map_reg, MCP251XFD_REG_CON, con, !mcp251xfd_reg_invalid(con) && FIELD_GET(MCP251XFD_REG_CON_OPMOD_MASK, con) == mode_req, - MCP251XFD_POLL_SLEEP_US, - MCP251XFD_POLL_TIMEOUT_US); + MCP251XFD_POLL_SLEEP_US, timeout_us); if (err != -ETIMEDOUT && err != -EBADMSG) return err; diff --git a/drivers/net/can/spi/mcp251xfd/mcp251xfd.h b/drivers/net/can/spi/mcp251xfd/mcp251xfd.h index 7024ff0cc2c0..24510b3b8020 100644 --- a/drivers/net/can/spi/mcp251xfd/mcp251xfd.h +++ b/drivers/net/can/spi/mcp251xfd/mcp251xfd.h @@ -387,6 +387,7 @@ static_assert(MCP251XFD_TIMESTAMP_WORK_DELAY_SEC < #define MCP251XFD_OSC_STAB_TIMEOUT_US (10 * MCP251XFD_OSC_STAB_SLEEP_US) #define MCP251XFD_POLL_SLEEP_US (10) #define MCP251XFD_POLL_TIMEOUT_US (USEC_PER_MSEC) +#define MCP251XFD_FRAME_LEN_MAX_BITS (736) /* Misc */ #define MCP251XFD_NAPI_WEIGHT 32 diff --git a/drivers/net/can/usb/gs_usb.c b/drivers/net/can/usb/gs_usb.c index d476c2884008..f418066569fc 100644 --- a/drivers/net/can/usb/gs_usb.c +++ b/drivers/net/can/usb/gs_usb.c @@ -303,12 +303,6 @@ struct gs_can { struct can_bittiming_const bt_const, data_bt_const; unsigned int channel; /* channel number */ - /* time counter for hardware timestamps */ - struct cyclecounter cc; - struct timecounter tc; - spinlock_t tc_lock; /* spinlock to guard access tc->cycle_last */ - struct delayed_work timestamp; - u32 feature; unsigned int hf_size_tx; @@ -325,6 +319,13 @@ struct gs_usb { struct gs_can *canch[GS_MAX_INTF]; struct usb_anchor rx_submitted; struct usb_device *udev; + + /* time counter for hardware timestamps */ + struct cyclecounter cc; + struct timecounter tc; + spinlock_t tc_lock; /* spinlock to guard access tc->cycle_last */ + struct delayed_work timestamp; + unsigned int hf_size_rx; u8 active_channels; }; @@ -388,15 +389,15 @@ static int gs_cmd_reset(struct gs_can *dev) GFP_KERNEL); } -static inline int gs_usb_get_timestamp(const struct gs_can *dev, +static inline int gs_usb_get_timestamp(const struct gs_usb *parent, u32 *timestamp_p) { __le32 timestamp; int rc; - rc = usb_control_msg_recv(dev->udev, 0, GS_USB_BREQ_TIMESTAMP, + rc = usb_control_msg_recv(parent->udev, 0, GS_USB_BREQ_TIMESTAMP, USB_DIR_IN | USB_TYPE_VENDOR | USB_RECIP_INTERFACE, - dev->channel, 0, + 0, 0, ×tamp, sizeof(timestamp), USB_CTRL_GET_TIMEOUT, GFP_KERNEL); @@ -410,20 +411,20 @@ static inline int gs_usb_get_timestamp(const struct gs_can *dev, static u64 gs_usb_timestamp_read(const struct cyclecounter *cc) __must_hold(&dev->tc_lock) { - struct gs_can *dev = container_of(cc, struct gs_can, cc); + struct gs_usb *parent = container_of(cc, struct gs_usb, cc); u32 timestamp = 0; int err; - lockdep_assert_held(&dev->tc_lock); + lockdep_assert_held(&parent->tc_lock); /* drop lock for synchronous USB transfer */ - spin_unlock_bh(&dev->tc_lock); - err = gs_usb_get_timestamp(dev, ×tamp); - spin_lock_bh(&dev->tc_lock); + spin_unlock_bh(&parent->tc_lock); + err = gs_usb_get_timestamp(parent, ×tamp); + spin_lock_bh(&parent->tc_lock); if (err) - netdev_err(dev->netdev, - "Error %d while reading timestamp. HW timestamps may be inaccurate.", - err); + dev_err(&parent->udev->dev, + "Error %d while reading timestamp. HW timestamps may be inaccurate.", + err); return timestamp; } @@ -431,14 +432,14 @@ static u64 gs_usb_timestamp_read(const struct cyclecounter *cc) __must_hold(&dev static void gs_usb_timestamp_work(struct work_struct *work) { struct delayed_work *delayed_work = to_delayed_work(work); - struct gs_can *dev; + struct gs_usb *parent; - dev = container_of(delayed_work, struct gs_can, timestamp); - spin_lock_bh(&dev->tc_lock); - timecounter_read(&dev->tc); - spin_unlock_bh(&dev->tc_lock); + parent = container_of(delayed_work, struct gs_usb, timestamp); + spin_lock_bh(&parent->tc_lock); + timecounter_read(&parent->tc); + spin_unlock_bh(&parent->tc_lock); - schedule_delayed_work(&dev->timestamp, + schedule_delayed_work(&parent->timestamp, GS_USB_TIMESTAMP_WORK_DELAY_SEC * HZ); } @@ -446,37 +447,38 @@ static void gs_usb_skb_set_timestamp(struct gs_can *dev, struct sk_buff *skb, u32 timestamp) { struct skb_shared_hwtstamps *hwtstamps = skb_hwtstamps(skb); + struct gs_usb *parent = dev->parent; u64 ns; - spin_lock_bh(&dev->tc_lock); - ns = timecounter_cyc2time(&dev->tc, timestamp); - spin_unlock_bh(&dev->tc_lock); + spin_lock_bh(&parent->tc_lock); + ns = timecounter_cyc2time(&parent->tc, timestamp); + spin_unlock_bh(&parent->tc_lock); hwtstamps->hwtstamp = ns_to_ktime(ns); } -static void gs_usb_timestamp_init(struct gs_can *dev) +static void gs_usb_timestamp_init(struct gs_usb *parent) { - struct cyclecounter *cc = &dev->cc; + struct cyclecounter *cc = &parent->cc; cc->read = gs_usb_timestamp_read; cc->mask = CYCLECOUNTER_MASK(32); cc->shift = 32 - bits_per(NSEC_PER_SEC / GS_USB_TIMESTAMP_TIMER_HZ); cc->mult = clocksource_hz2mult(GS_USB_TIMESTAMP_TIMER_HZ, cc->shift); - spin_lock_init(&dev->tc_lock); - spin_lock_bh(&dev->tc_lock); - timecounter_init(&dev->tc, &dev->cc, ktime_get_real_ns()); - spin_unlock_bh(&dev->tc_lock); + spin_lock_init(&parent->tc_lock); + spin_lock_bh(&parent->tc_lock); + timecounter_init(&parent->tc, &parent->cc, ktime_get_real_ns()); + spin_unlock_bh(&parent->tc_lock); - INIT_DELAYED_WORK(&dev->timestamp, gs_usb_timestamp_work); - schedule_delayed_work(&dev->timestamp, + INIT_DELAYED_WORK(&parent->timestamp, gs_usb_timestamp_work); + schedule_delayed_work(&parent->timestamp, GS_USB_TIMESTAMP_WORK_DELAY_SEC * HZ); } -static void gs_usb_timestamp_stop(struct gs_can *dev) +static void gs_usb_timestamp_stop(struct gs_usb *parent) { - cancel_delayed_work_sync(&dev->timestamp); + cancel_delayed_work_sync(&parent->timestamp); } static void gs_update_state(struct gs_can *dev, struct can_frame *cf) @@ -560,6 +562,9 @@ static void gs_usb_receive_bulk_callback(struct urb *urb) if (!netif_device_present(netdev)) return; + if (!netif_running(netdev)) + goto resubmit_urb; + if (hf->echo_id == -1) { /* normal rx */ if (hf->flags & GS_CAN_FLAG_FD) { skb = alloc_canfd_skb(dev->netdev, &cfd); @@ -833,6 +838,7 @@ static int gs_can_open(struct net_device *netdev) .mode = cpu_to_le32(GS_CAN_MODE_START), }; struct gs_host_frame *hf; + struct urb *urb = NULL; u32 ctrlmode; u32 flags = 0; int rc, i; @@ -855,14 +861,18 @@ static int gs_can_open(struct net_device *netdev) } if (!parent->active_channels) { + if (dev->feature & GS_CAN_FEATURE_HW_TIMESTAMP) + gs_usb_timestamp_init(parent); + for (i = 0; i < GS_MAX_RX_URBS; i++) { - struct urb *urb; u8 *buf; /* alloc rx urb */ urb = usb_alloc_urb(0, GFP_KERNEL); - if (!urb) - return -ENOMEM; + if (!urb) { + rc = -ENOMEM; + goto out_usb_kill_anchored_urbs; + } /* alloc rx buffer */ buf = kmalloc(dev->parent->hf_size_rx, @@ -870,8 +880,8 @@ static int gs_can_open(struct net_device *netdev) if (!buf) { netdev_err(netdev, "No memory left for USB buffer\n"); - usb_free_urb(urb); - return -ENOMEM; + rc = -ENOMEM; + goto out_usb_free_urb; } /* fill, anchor, and submit rx urb */ @@ -894,9 +904,7 @@ static int gs_can_open(struct net_device *netdev) netdev_err(netdev, "usb_submit failed (err=%d)\n", rc); - usb_unanchor_urb(urb); - usb_free_urb(urb); - break; + goto out_usb_unanchor_urb; } /* Drop reference, @@ -926,13 +934,9 @@ static int gs_can_open(struct net_device *netdev) flags |= GS_CAN_MODE_FD; /* if hardware supports timestamps, enable it */ - if (dev->feature & GS_CAN_FEATURE_HW_TIMESTAMP) { + if (dev->feature & GS_CAN_FEATURE_HW_TIMESTAMP) flags |= GS_CAN_MODE_HW_TIMESTAMP; - /* start polling timestamp */ - gs_usb_timestamp_init(dev); - } - /* finally start device */ dev->can.state = CAN_STATE_ERROR_ACTIVE; dm.flags = cpu_to_le32(flags); @@ -942,10 +946,9 @@ static int gs_can_open(struct net_device *netdev) GFP_KERNEL); if (rc) { netdev_err(netdev, "Couldn't start device (err=%d)\n", rc); - if (dev->feature & GS_CAN_FEATURE_HW_TIMESTAMP) - gs_usb_timestamp_stop(dev); dev->can.state = CAN_STATE_STOPPED; - return rc; + + goto out_usb_kill_anchored_urbs; } parent->active_channels++; @@ -953,6 +956,22 @@ static int gs_can_open(struct net_device *netdev) netif_start_queue(netdev); return 0; + +out_usb_unanchor_urb: + usb_unanchor_urb(urb); +out_usb_free_urb: + usb_free_urb(urb); +out_usb_kill_anchored_urbs: + if (!parent->active_channels) { + usb_kill_anchored_urbs(&dev->tx_submitted); + + if (dev->feature & GS_CAN_FEATURE_HW_TIMESTAMP) + gs_usb_timestamp_stop(parent); + } + + close_candev(netdev); + + return rc; } static int gs_usb_get_state(const struct net_device *netdev, @@ -998,14 +1017,13 @@ static int gs_can_close(struct net_device *netdev) netif_stop_queue(netdev); - /* stop polling timestamp */ - if (dev->feature & GS_CAN_FEATURE_HW_TIMESTAMP) - gs_usb_timestamp_stop(dev); - /* Stop polling */ parent->active_channels--; if (!parent->active_channels) { usb_kill_anchored_urbs(&parent->rx_submitted); + + if (dev->feature & GS_CAN_FEATURE_HW_TIMESTAMP) + gs_usb_timestamp_stop(parent); } /* Stop sending URBs */ diff --git a/drivers/net/dsa/microchip/ksz8795.c b/drivers/net/dsa/microchip/ksz8795.c index 84d502589f8e..91aba470fb2f 100644 --- a/drivers/net/dsa/microchip/ksz8795.c +++ b/drivers/net/dsa/microchip/ksz8795.c @@ -506,7 +506,13 @@ static int ksz8_r_sta_mac_table(struct ksz_device *dev, u16 addr, (data_hi & masks[STATIC_MAC_TABLE_FWD_PORTS]) >> shifts[STATIC_MAC_FWD_PORTS]; alu->is_override = (data_hi & masks[STATIC_MAC_TABLE_OVERRIDE]) ? 1 : 0; - data_hi >>= 1; + + /* KSZ8795 family switches have STATIC_MAC_TABLE_USE_FID and + * STATIC_MAC_TABLE_FID definitions off by 1 when doing read on the + * static MAC table compared to doing write. + */ + if (ksz_is_ksz87xx(dev)) + data_hi >>= 1; alu->is_static = true; alu->is_use_fid = (data_hi & masks[STATIC_MAC_TABLE_USE_FID]) ? 1 : 0; alu->fid = (data_hi & masks[STATIC_MAC_TABLE_FID]) >> diff --git a/drivers/net/dsa/microchip/ksz_common.c b/drivers/net/dsa/microchip/ksz_common.c index 07ba2b54ab99..1de2251a42dc 100644 --- a/drivers/net/dsa/microchip/ksz_common.c +++ b/drivers/net/dsa/microchip/ksz_common.c @@ -331,13 +331,13 @@ static const u32 ksz8795_masks[] = { [STATIC_MAC_TABLE_VALID] = BIT(21), [STATIC_MAC_TABLE_USE_FID] = BIT(23), [STATIC_MAC_TABLE_FID] = GENMASK(30, 24), - [STATIC_MAC_TABLE_OVERRIDE] = BIT(26), - [STATIC_MAC_TABLE_FWD_PORTS] = GENMASK(24, 20), + [STATIC_MAC_TABLE_OVERRIDE] = BIT(22), + [STATIC_MAC_TABLE_FWD_PORTS] = GENMASK(20, 16), [DYNAMIC_MAC_TABLE_ENTRIES_H] = GENMASK(6, 0), - [DYNAMIC_MAC_TABLE_MAC_EMPTY] = BIT(8), + [DYNAMIC_MAC_TABLE_MAC_EMPTY] = BIT(7), [DYNAMIC_MAC_TABLE_NOT_READY] = BIT(7), [DYNAMIC_MAC_TABLE_ENTRIES] = GENMASK(31, 29), - [DYNAMIC_MAC_TABLE_FID] = GENMASK(26, 20), + [DYNAMIC_MAC_TABLE_FID] = GENMASK(22, 16), [DYNAMIC_MAC_TABLE_SRC_PORT] = GENMASK(26, 24), [DYNAMIC_MAC_TABLE_TIMESTAMP] = GENMASK(28, 27), [P_MII_TX_FLOW_CTRL] = BIT(5), diff --git a/drivers/net/dsa/microchip/ksz_common.h b/drivers/net/dsa/microchip/ksz_common.h index 28444e5924f9..a4de58847dea 100644 --- a/drivers/net/dsa/microchip/ksz_common.h +++ b/drivers/net/dsa/microchip/ksz_common.h @@ -601,6 +601,13 @@ static inline void ksz_regmap_unlock(void *__mtx) mutex_unlock(mtx); } +static inline bool ksz_is_ksz87xx(struct ksz_device *dev) +{ + return dev->chip_id == KSZ8795_CHIP_ID || + dev->chip_id == KSZ8794_CHIP_ID || + dev->chip_id == KSZ8765_CHIP_ID; +} + static inline bool ksz_is_ksz88x3(struct ksz_device *dev) { return dev->chip_id == KSZ8830_CHIP_ID; diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index 8dd82fd87fc6..11a2e3d38484 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -109,6 +109,13 @@ int mv88e6xxx_wait_mask(struct mv88e6xxx_chip *chip, int addr, int reg, usleep_range(1000, 2000); } + err = mv88e6xxx_read(chip, addr, reg, &data); + if (err) + return err; + + if ((data & mask) == val) + return 0; + dev_err(chip->dev, "Timeout while waiting for switch\n"); return -ETIMEDOUT; } diff --git a/drivers/net/dsa/qca/ar9331.c b/drivers/net/dsa/qca/ar9331.c index 72730dcc9ca9..8d9d271ac3af 100644 --- a/drivers/net/dsa/qca/ar9331.c +++ b/drivers/net/dsa/qca/ar9331.c @@ -1002,6 +1002,8 @@ static const struct regmap_config ar9331_mdio_regmap_config = { .val_bits = 32, .reg_stride = 4, .max_register = AR9331_SW_REG_PAGE, + .use_single_read = true, + .use_single_write = true, .ranges = ar9331_regmap_range, .num_ranges = ARRAY_SIZE(ar9331_regmap_range), @@ -1018,8 +1020,6 @@ static struct regmap_bus ar9331_sw_bus = { .val_format_endian_default = REGMAP_ENDIAN_NATIVE, .read = ar9331_mdio_read, .write = ar9331_sw_bus_write, - .max_raw_read = 4, - .max_raw_write = 4, }; static int ar9331_sw_probe(struct mdio_device *mdiodev) diff --git a/drivers/net/ethernet/brocade/bna/bnad_debugfs.c b/drivers/net/ethernet/brocade/bna/bnad_debugfs.c index 04ad0f2b9677..7246e13dd559 100644 --- a/drivers/net/ethernet/brocade/bna/bnad_debugfs.c +++ b/drivers/net/ethernet/brocade/bna/bnad_debugfs.c @@ -512,11 +512,6 @@ bnad_debugfs_init(struct bnad *bnad) if (!bnad->port_debugfs_root) { bnad->port_debugfs_root = debugfs_create_dir(name, bna_debugfs_root); - if (!bnad->port_debugfs_root) { - netdev_warn(bnad->netdev, - "debugfs root dir creation failed\n"); - return; - } atomic_inc(&bna_debugfs_port_count); diff --git a/drivers/net/ethernet/intel/iavf/iavf.h b/drivers/net/ethernet/intel/iavf/iavf.h index f80f2735e688..8cbdebc5b698 100644 --- a/drivers/net/ethernet/intel/iavf/iavf.h +++ b/drivers/net/ethernet/intel/iavf/iavf.h @@ -255,8 +255,10 @@ struct iavf_adapter { struct workqueue_struct *wq; struct work_struct reset_task; struct work_struct adminq_task; + struct work_struct finish_config; struct delayed_work client_task; wait_queue_head_t down_waitqueue; + wait_queue_head_t reset_waitqueue; wait_queue_head_t vc_waitqueue; struct iavf_q_vector *q_vectors; struct list_head vlan_filter_list; @@ -518,8 +520,9 @@ int iavf_up(struct iavf_adapter *adapter); void iavf_down(struct iavf_adapter *adapter); int iavf_process_config(struct iavf_adapter *adapter); int iavf_parse_vf_resource_msg(struct iavf_adapter *adapter); -void iavf_schedule_reset(struct iavf_adapter *adapter); +void iavf_schedule_reset(struct iavf_adapter *adapter, u64 flags); void iavf_schedule_request_stats(struct iavf_adapter *adapter); +void iavf_schedule_finish_config(struct iavf_adapter *adapter); void iavf_reset(struct iavf_adapter *adapter); void iavf_set_ethtool_ops(struct net_device *netdev); void iavf_update_stats(struct iavf_adapter *adapter); @@ -582,4 +585,5 @@ void iavf_add_adv_rss_cfg(struct iavf_adapter *adapter); void iavf_del_adv_rss_cfg(struct iavf_adapter *adapter); struct iavf_mac_filter *iavf_add_filter(struct iavf_adapter *adapter, const u8 *macaddr); +int iavf_wait_for_reset(struct iavf_adapter *adapter); #endif /* _IAVF_H_ */ diff --git a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c index 6f171d1d85b7..2f47cfa7f06e 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_ethtool.c +++ b/drivers/net/ethernet/intel/iavf/iavf_ethtool.c @@ -484,6 +484,7 @@ static int iavf_set_priv_flags(struct net_device *netdev, u32 flags) { struct iavf_adapter *adapter = netdev_priv(netdev); u32 orig_flags, new_flags, changed_flags; + int ret = 0; u32 i; orig_flags = READ_ONCE(adapter->flags); @@ -531,12 +532,14 @@ static int iavf_set_priv_flags(struct net_device *netdev, u32 flags) /* issue a reset to force legacy-rx change to take effect */ if (changed_flags & IAVF_FLAG_LEGACY_RX) { if (netif_running(netdev)) { - adapter->flags |= IAVF_FLAG_RESET_NEEDED; - queue_work(adapter->wq, &adapter->reset_task); + iavf_schedule_reset(adapter, IAVF_FLAG_RESET_NEEDED); + ret = iavf_wait_for_reset(adapter); + if (ret) + netdev_warn(netdev, "Changing private flags timeout or interrupted waiting for reset"); } } - return 0; + return ret; } /** @@ -627,6 +630,7 @@ static int iavf_set_ringparam(struct net_device *netdev, { struct iavf_adapter *adapter = netdev_priv(netdev); u32 new_rx_count, new_tx_count; + int ret = 0; if ((ring->rx_mini_pending) || (ring->rx_jumbo_pending)) return -EINVAL; @@ -671,11 +675,13 @@ static int iavf_set_ringparam(struct net_device *netdev, } if (netif_running(netdev)) { - adapter->flags |= IAVF_FLAG_RESET_NEEDED; - queue_work(adapter->wq, &adapter->reset_task); + iavf_schedule_reset(adapter, IAVF_FLAG_RESET_NEEDED); + ret = iavf_wait_for_reset(adapter); + if (ret) + netdev_warn(netdev, "Changing ring parameters timeout or interrupted waiting for reset"); } - return 0; + return ret; } /** @@ -1830,7 +1836,7 @@ static int iavf_set_channels(struct net_device *netdev, { struct iavf_adapter *adapter = netdev_priv(netdev); u32 num_req = ch->combined_count; - int i; + int ret = 0; if ((adapter->vf_res->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_ADQ) && adapter->num_tc) { @@ -1852,22 +1858,13 @@ static int iavf_set_channels(struct net_device *netdev, adapter->num_req_queues = num_req; adapter->flags |= IAVF_FLAG_REINIT_ITR_NEEDED; - iavf_schedule_reset(adapter); + iavf_schedule_reset(adapter, IAVF_FLAG_RESET_NEEDED); - /* wait for the reset is done */ - for (i = 0; i < IAVF_RESET_WAIT_COMPLETE_COUNT; i++) { - msleep(IAVF_RESET_WAIT_MS); - if (adapter->flags & IAVF_FLAG_RESET_PENDING) - continue; - break; - } - if (i == IAVF_RESET_WAIT_COMPLETE_COUNT) { - adapter->flags &= ~IAVF_FLAG_REINIT_ITR_NEEDED; - adapter->num_active_queues = num_req; - return -EOPNOTSUPP; - } + ret = iavf_wait_for_reset(adapter); + if (ret) + netdev_warn(netdev, "Changing channel count timeout or interrupted waiting for reset"); - return 0; + return ret; } /** diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c index a483eb185c99..3a88d413ddee 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_main.c +++ b/drivers/net/ethernet/intel/iavf/iavf_main.c @@ -167,6 +167,45 @@ static struct iavf_adapter *iavf_pdev_to_adapter(struct pci_dev *pdev) } /** + * iavf_is_reset_in_progress - Check if a reset is in progress + * @adapter: board private structure + */ +static bool iavf_is_reset_in_progress(struct iavf_adapter *adapter) +{ + if (adapter->state == __IAVF_RESETTING || + adapter->flags & (IAVF_FLAG_RESET_PENDING | + IAVF_FLAG_RESET_NEEDED)) + return true; + + return false; +} + +/** + * iavf_wait_for_reset - Wait for reset to finish. + * @adapter: board private structure + * + * Returns 0 if reset finished successfully, negative on timeout or interrupt. + */ +int iavf_wait_for_reset(struct iavf_adapter *adapter) +{ + int ret = wait_event_interruptible_timeout(adapter->reset_waitqueue, + !iavf_is_reset_in_progress(adapter), + msecs_to_jiffies(5000)); + + /* If ret < 0 then it means wait was interrupted. + * If ret == 0 then it means we got a timeout while waiting + * for reset to finish. + * If ret > 0 it means reset has finished. + */ + if (ret > 0) + return 0; + else if (ret < 0) + return -EINTR; + else + return -EBUSY; +} + +/** * iavf_allocate_dma_mem_d - OS specific memory alloc for shared code * @hw: pointer to the HW structure * @mem: ptr to mem struct to fill out @@ -262,12 +301,14 @@ static int iavf_lock_timeout(struct mutex *lock, unsigned int msecs) /** * iavf_schedule_reset - Set the flags and schedule a reset event * @adapter: board private structure + * @flags: IAVF_FLAG_RESET_PENDING or IAVF_FLAG_RESET_NEEDED **/ -void iavf_schedule_reset(struct iavf_adapter *adapter) +void iavf_schedule_reset(struct iavf_adapter *adapter, u64 flags) { - if (!(adapter->flags & - (IAVF_FLAG_RESET_PENDING | IAVF_FLAG_RESET_NEEDED))) { - adapter->flags |= IAVF_FLAG_RESET_NEEDED; + if (!test_bit(__IAVF_IN_REMOVE_TASK, &adapter->crit_section) && + !(adapter->flags & + (IAVF_FLAG_RESET_PENDING | IAVF_FLAG_RESET_NEEDED))) { + adapter->flags |= flags; queue_work(adapter->wq, &adapter->reset_task); } } @@ -295,7 +336,7 @@ static void iavf_tx_timeout(struct net_device *netdev, unsigned int txqueue) struct iavf_adapter *adapter = netdev_priv(netdev); adapter->tx_timeout_count++; - iavf_schedule_reset(adapter); + iavf_schedule_reset(adapter, IAVF_FLAG_RESET_NEEDED); } /** @@ -1651,10 +1692,10 @@ static int iavf_set_interrupt_capability(struct iavf_adapter *adapter) adapter->msix_entries[vector].entry = vector; err = iavf_acquire_msix_vectors(adapter, v_budget); + if (!err) + iavf_schedule_finish_config(adapter); out: - netif_set_real_num_rx_queues(adapter->netdev, pairs); - netif_set_real_num_tx_queues(adapter->netdev, pairs); return err; } @@ -1828,19 +1869,16 @@ static int iavf_alloc_q_vectors(struct iavf_adapter *adapter) static void iavf_free_q_vectors(struct iavf_adapter *adapter) { int q_idx, num_q_vectors; - int napi_vectors; if (!adapter->q_vectors) return; num_q_vectors = adapter->num_msix_vectors - NONQ_VECS; - napi_vectors = adapter->num_active_queues; for (q_idx = 0; q_idx < num_q_vectors; q_idx++) { struct iavf_q_vector *q_vector = &adapter->q_vectors[q_idx]; - if (q_idx < napi_vectors) - netif_napi_del(&q_vector->napi); + netif_napi_del(&q_vector->napi); } kfree(adapter->q_vectors); adapter->q_vectors = NULL; @@ -1877,9 +1915,7 @@ static int iavf_init_interrupt_scheme(struct iavf_adapter *adapter) goto err_alloc_queues; } - rtnl_lock(); err = iavf_set_interrupt_capability(adapter); - rtnl_unlock(); if (err) { dev_err(&adapter->pdev->dev, "Unable to setup interrupt capabilities\n"); @@ -1932,15 +1968,16 @@ static void iavf_free_rss(struct iavf_adapter *adapter) /** * iavf_reinit_interrupt_scheme - Reallocate queues and vectors * @adapter: board private structure + * @running: true if adapter->state == __IAVF_RUNNING * * Returns 0 on success, negative on failure **/ -static int iavf_reinit_interrupt_scheme(struct iavf_adapter *adapter) +static int iavf_reinit_interrupt_scheme(struct iavf_adapter *adapter, bool running) { struct net_device *netdev = adapter->netdev; int err; - if (netif_running(netdev)) + if (running) iavf_free_traffic_irqs(adapter); iavf_free_misc_irq(adapter); iavf_reset_interrupt_capability(adapter); @@ -1965,6 +2002,78 @@ err: } /** + * iavf_finish_config - do all netdev work that needs RTNL + * @work: our work_struct + * + * Do work that needs both RTNL and crit_lock. + **/ +static void iavf_finish_config(struct work_struct *work) +{ + struct iavf_adapter *adapter; + int pairs, err; + + adapter = container_of(work, struct iavf_adapter, finish_config); + + /* Always take RTNL first to prevent circular lock dependency */ + rtnl_lock(); + mutex_lock(&adapter->crit_lock); + + if ((adapter->flags & IAVF_FLAG_SETUP_NETDEV_FEATURES) && + adapter->netdev_registered && + !test_bit(__IAVF_IN_REMOVE_TASK, &adapter->crit_section)) { + netdev_update_features(adapter->netdev); + adapter->flags &= ~IAVF_FLAG_SETUP_NETDEV_FEATURES; + } + + switch (adapter->state) { + case __IAVF_DOWN: + if (!adapter->netdev_registered) { + err = register_netdevice(adapter->netdev); + if (err) { + dev_err(&adapter->pdev->dev, "Unable to register netdev (%d)\n", + err); + + /* go back and try again.*/ + iavf_free_rss(adapter); + iavf_free_misc_irq(adapter); + iavf_reset_interrupt_capability(adapter); + iavf_change_state(adapter, + __IAVF_INIT_CONFIG_ADAPTER); + goto out; + } + adapter->netdev_registered = true; + } + + /* Set the real number of queues when reset occurs while + * state == __IAVF_DOWN + */ + fallthrough; + case __IAVF_RUNNING: + pairs = adapter->num_active_queues; + netif_set_real_num_rx_queues(adapter->netdev, pairs); + netif_set_real_num_tx_queues(adapter->netdev, pairs); + break; + + default: + break; + } + +out: + mutex_unlock(&adapter->crit_lock); + rtnl_unlock(); +} + +/** + * iavf_schedule_finish_config - Set the flags and schedule a reset event + * @adapter: board private structure + **/ +void iavf_schedule_finish_config(struct iavf_adapter *adapter) +{ + if (!test_bit(__IAVF_IN_REMOVE_TASK, &adapter->crit_section)) + queue_work(adapter->wq, &adapter->finish_config); +} + +/** * iavf_process_aq_command - process aq_required flags * and sends aq command * @adapter: pointer to iavf adapter structure @@ -2371,7 +2480,7 @@ int iavf_parse_vf_resource_msg(struct iavf_adapter *adapter) adapter->vsi_res->num_queue_pairs); adapter->flags |= IAVF_FLAG_REINIT_MSIX_NEEDED; adapter->num_req_queues = adapter->vsi_res->num_queue_pairs; - iavf_schedule_reset(adapter); + iavf_schedule_reset(adapter, IAVF_FLAG_RESET_NEEDED); return -EAGAIN; } @@ -2601,22 +2710,8 @@ static void iavf_init_config_adapter(struct iavf_adapter *adapter) netif_carrier_off(netdev); adapter->link_up = false; - - /* set the semaphore to prevent any callbacks after device registration - * up to time when state of driver will be set to __IAVF_DOWN - */ - rtnl_lock(); - if (!adapter->netdev_registered) { - err = register_netdevice(netdev); - if (err) { - rtnl_unlock(); - goto err_register; - } - } - - adapter->netdev_registered = true; - netif_tx_stop_all_queues(netdev); + if (CLIENT_ALLOWED(adapter)) { err = iavf_lan_add_device(adapter); if (err) @@ -2629,7 +2724,6 @@ static void iavf_init_config_adapter(struct iavf_adapter *adapter) iavf_change_state(adapter, __IAVF_DOWN); set_bit(__IAVF_VSI_DOWN, adapter->vsi.state); - rtnl_unlock(); iavf_misc_irq_enable(adapter); wake_up(&adapter->down_waitqueue); @@ -2649,10 +2743,11 @@ static void iavf_init_config_adapter(struct iavf_adapter *adapter) /* request initial VLAN offload settings */ iavf_set_vlan_offload_features(adapter, 0, netdev->features); + iavf_schedule_finish_config(adapter); return; + err_mem: iavf_free_rss(adapter); -err_register: iavf_free_misc_irq(adapter); err_sw_init: iavf_reset_interrupt_capability(adapter); @@ -2679,26 +2774,9 @@ static void iavf_watchdog_task(struct work_struct *work) goto restart_watchdog; } - if ((adapter->flags & IAVF_FLAG_SETUP_NETDEV_FEATURES) && - adapter->netdev_registered && - !test_bit(__IAVF_IN_REMOVE_TASK, &adapter->crit_section) && - rtnl_trylock()) { - netdev_update_features(adapter->netdev); - rtnl_unlock(); - adapter->flags &= ~IAVF_FLAG_SETUP_NETDEV_FEATURES; - } - if (adapter->flags & IAVF_FLAG_PF_COMMS_FAILED) iavf_change_state(adapter, __IAVF_COMM_FAILED); - if (adapter->flags & IAVF_FLAG_RESET_NEEDED) { - adapter->aq_required = 0; - adapter->current_op = VIRTCHNL_OP_UNKNOWN; - mutex_unlock(&adapter->crit_lock); - queue_work(adapter->wq, &adapter->reset_task); - return; - } - switch (adapter->state) { case __IAVF_STARTUP: iavf_startup(adapter); @@ -2826,11 +2904,10 @@ static void iavf_watchdog_task(struct work_struct *work) /* check for hw reset */ reg_val = rd32(hw, IAVF_VF_ARQLEN1) & IAVF_VF_ARQLEN1_ARQENABLE_MASK; if (!reg_val) { - adapter->flags |= IAVF_FLAG_RESET_PENDING; adapter->aq_required = 0; adapter->current_op = VIRTCHNL_OP_UNKNOWN; dev_err(&adapter->pdev->dev, "Hardware reset detected\n"); - queue_work(adapter->wq, &adapter->reset_task); + iavf_schedule_reset(adapter, IAVF_FLAG_RESET_PENDING); mutex_unlock(&adapter->crit_lock); queue_delayed_work(adapter->wq, &adapter->watchdog_task, HZ * 2); @@ -2940,11 +3017,6 @@ static void iavf_reset_task(struct work_struct *work) int i = 0, err; bool running; - /* Detach interface to avoid subsequent NDO callbacks */ - rtnl_lock(); - netif_device_detach(netdev); - rtnl_unlock(); - /* When device is being removed it doesn't make sense to run the reset * task, just return in such a case. */ @@ -2952,7 +3024,7 @@ static void iavf_reset_task(struct work_struct *work) if (adapter->state != __IAVF_REMOVE) queue_work(adapter->wq, &adapter->reset_task); - goto reset_finish; + return; } while (!mutex_trylock(&adapter->client_lock)) @@ -3010,11 +3082,6 @@ static void iavf_reset_task(struct work_struct *work) iavf_disable_vf(adapter); mutex_unlock(&adapter->client_lock); mutex_unlock(&adapter->crit_lock); - if (netif_running(netdev)) { - rtnl_lock(); - dev_close(netdev); - rtnl_unlock(); - } return; /* Do not attempt to reinit. It's dead, Jim. */ } @@ -3056,7 +3123,7 @@ continue_reset: if ((adapter->flags & IAVF_FLAG_REINIT_MSIX_NEEDED) || (adapter->flags & IAVF_FLAG_REINIT_ITR_NEEDED)) { - err = iavf_reinit_interrupt_scheme(adapter); + err = iavf_reinit_interrupt_scheme(adapter, running); if (err) goto reset_err; } @@ -3151,10 +3218,11 @@ continue_reset: adapter->flags &= ~IAVF_FLAG_REINIT_ITR_NEEDED; + wake_up(&adapter->reset_waitqueue); mutex_unlock(&adapter->client_lock); mutex_unlock(&adapter->crit_lock); - goto reset_finish; + return; reset_err: if (running) { set_bit(__IAVF_VSI_DOWN, adapter->vsi.state); @@ -3164,21 +3232,7 @@ reset_err: mutex_unlock(&adapter->client_lock); mutex_unlock(&adapter->crit_lock); - - if (netif_running(netdev)) { - /* Close device to ensure that Tx queues will not be started - * during netif_device_attach() at the end of the reset task. - */ - rtnl_lock(); - dev_close(netdev); - rtnl_unlock(); - } - dev_err(&adapter->pdev->dev, "failed to allocate resources during reinit\n"); -reset_finish: - rtnl_lock(); - netif_device_attach(netdev); - rtnl_unlock(); } /** @@ -3227,9 +3281,7 @@ static void iavf_adminq_task(struct work_struct *work) } while (pending); mutex_unlock(&adapter->crit_lock); - if ((adapter->flags & - (IAVF_FLAG_RESET_PENDING | IAVF_FLAG_RESET_NEEDED)) || - adapter->state == __IAVF_RESETTING) + if (iavf_is_reset_in_progress(adapter)) goto freedom; /* check for error indications */ @@ -4315,6 +4367,7 @@ static int iavf_close(struct net_device *netdev) static int iavf_change_mtu(struct net_device *netdev, int new_mtu) { struct iavf_adapter *adapter = netdev_priv(netdev); + int ret = 0; netdev_dbg(netdev, "changing MTU from %d to %d\n", netdev->mtu, new_mtu); @@ -4325,11 +4378,15 @@ static int iavf_change_mtu(struct net_device *netdev, int new_mtu) } if (netif_running(netdev)) { - adapter->flags |= IAVF_FLAG_RESET_NEEDED; - queue_work(adapter->wq, &adapter->reset_task); + iavf_schedule_reset(adapter, IAVF_FLAG_RESET_NEEDED); + ret = iavf_wait_for_reset(adapter); + if (ret < 0) + netdev_warn(netdev, "MTU change interrupted waiting for reset"); + else if (ret) + netdev_warn(netdev, "MTU change timed out waiting for reset"); } - return 0; + return ret; } #define NETIF_VLAN_OFFLOAD_FEATURES (NETIF_F_HW_VLAN_CTAG_RX | \ @@ -4922,6 +4979,7 @@ static int iavf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) INIT_WORK(&adapter->reset_task, iavf_reset_task); INIT_WORK(&adapter->adminq_task, iavf_adminq_task); + INIT_WORK(&adapter->finish_config, iavf_finish_config); INIT_DELAYED_WORK(&adapter->watchdog_task, iavf_watchdog_task); INIT_DELAYED_WORK(&adapter->client_task, iavf_client_task); queue_delayed_work(adapter->wq, &adapter->watchdog_task, @@ -4930,6 +4988,9 @@ static int iavf_probe(struct pci_dev *pdev, const struct pci_device_id *ent) /* Setup the wait queue for indicating transition to down status */ init_waitqueue_head(&adapter->down_waitqueue); + /* Setup the wait queue for indicating transition to running state */ + init_waitqueue_head(&adapter->reset_waitqueue); + /* Setup the wait queue for indicating virtchannel events */ init_waitqueue_head(&adapter->vc_waitqueue); @@ -5061,13 +5122,15 @@ static void iavf_remove(struct pci_dev *pdev) usleep_range(500, 1000); } cancel_delayed_work_sync(&adapter->watchdog_task); + cancel_work_sync(&adapter->finish_config); + rtnl_lock(); if (adapter->netdev_registered) { - rtnl_lock(); unregister_netdevice(netdev); adapter->netdev_registered = false; - rtnl_unlock(); } + rtnl_unlock(); + if (CLIENT_ALLOWED(adapter)) { err = iavf_lan_del_device(adapter); if (err) diff --git a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c index 7c0578b5457b..be3c007ce90a 100644 --- a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c +++ b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c @@ -1961,9 +1961,8 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter, case VIRTCHNL_EVENT_RESET_IMPENDING: dev_info(&adapter->pdev->dev, "Reset indication received from the PF\n"); if (!(adapter->flags & IAVF_FLAG_RESET_PENDING)) { - adapter->flags |= IAVF_FLAG_RESET_PENDING; dev_info(&adapter->pdev->dev, "Scheduling reset task\n"); - queue_work(adapter->wq, &adapter->reset_task); + iavf_schedule_reset(adapter, IAVF_FLAG_RESET_PENDING); } break; default: @@ -2237,6 +2236,7 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter, iavf_process_config(adapter); adapter->flags |= IAVF_FLAG_SETUP_NETDEV_FEATURES; + iavf_schedule_finish_config(adapter); iavf_set_queue_vlan_tag_loc(adapter); @@ -2285,6 +2285,7 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter, case VIRTCHNL_OP_ENABLE_QUEUES: /* enable transmits */ iavf_irq_enable(adapter, true); + wake_up(&adapter->reset_waitqueue); adapter->flags &= ~IAVF_FLAG_QUEUES_DISABLED; break; case VIRTCHNL_OP_DISABLE_QUEUES: diff --git a/drivers/net/ethernet/intel/ice/ice_base.c b/drivers/net/ethernet/intel/ice/ice_base.c index 3367b8ba9851..9ab9fb558b5e 100644 --- a/drivers/net/ethernet/intel/ice/ice_base.c +++ b/drivers/net/ethernet/intel/ice/ice_base.c @@ -793,6 +793,8 @@ void ice_vsi_free_q_vectors(struct ice_vsi *vsi) ice_for_each_q_vector(vsi, v_idx) ice_free_q_vector(vsi, v_idx); + + vsi->num_q_vectors = 0; } /** diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool.c b/drivers/net/ethernet/intel/ice/ice_ethtool.c index 8d5cbbd0b3d5..ad4d4702129f 100644 --- a/drivers/net/ethernet/intel/ice/ice_ethtool.c +++ b/drivers/net/ethernet/intel/ice/ice_ethtool.c @@ -2681,8 +2681,13 @@ ice_get_ringparam(struct net_device *netdev, struct ethtool_ringparam *ring, ring->rx_max_pending = ICE_MAX_NUM_DESC; ring->tx_max_pending = ICE_MAX_NUM_DESC; - ring->rx_pending = vsi->rx_rings[0]->count; - ring->tx_pending = vsi->tx_rings[0]->count; + if (vsi->tx_rings && vsi->rx_rings) { + ring->rx_pending = vsi->rx_rings[0]->count; + ring->tx_pending = vsi->tx_rings[0]->count; + } else { + ring->rx_pending = 0; + ring->tx_pending = 0; + } /* Rx mini and jumbo rings are not supported */ ring->rx_mini_max_pending = 0; @@ -2716,6 +2721,10 @@ ice_set_ringparam(struct net_device *netdev, struct ethtool_ringparam *ring, return -EINVAL; } + /* Return if there is no rings (device is reloading) */ + if (!vsi->tx_rings || !vsi->rx_rings) + return -EBUSY; + new_tx_cnt = ALIGN(ring->tx_pending, ICE_REQ_DESC_MULTIPLE); if (new_tx_cnt != ring->tx_pending) netdev_info(netdev, "Requested Tx descriptor count rounded up to %d\n", diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c index 00e3afd507a4..0054d7e64ec3 100644 --- a/drivers/net/ethernet/intel/ice/ice_lib.c +++ b/drivers/net/ethernet/intel/ice/ice_lib.c @@ -2972,39 +2972,12 @@ int ice_vsi_release(struct ice_vsi *vsi) return -ENODEV; pf = vsi->back; - /* do not unregister while driver is in the reset recovery pending - * state. Since reset/rebuild happens through PF service task workqueue, - * it's not a good idea to unregister netdev that is associated to the - * PF that is running the work queue items currently. This is done to - * avoid check_flush_dependency() warning on this wq - */ - if (vsi->netdev && !ice_is_reset_in_progress(pf->state) && - (test_bit(ICE_VSI_NETDEV_REGISTERED, vsi->state))) { - unregister_netdev(vsi->netdev); - clear_bit(ICE_VSI_NETDEV_REGISTERED, vsi->state); - } - - if (vsi->type == ICE_VSI_PF) - ice_devlink_destroy_pf_port(pf); - if (test_bit(ICE_FLAG_RSS_ENA, pf->flags)) ice_rss_clean(vsi); ice_vsi_close(vsi); ice_vsi_decfg(vsi); - if (vsi->netdev) { - if (test_bit(ICE_VSI_NETDEV_REGISTERED, vsi->state)) { - unregister_netdev(vsi->netdev); - clear_bit(ICE_VSI_NETDEV_REGISTERED, vsi->state); - } - if (test_bit(ICE_VSI_NETDEV_ALLOCD, vsi->state)) { - free_netdev(vsi->netdev); - vsi->netdev = NULL; - clear_bit(ICE_VSI_NETDEV_ALLOCD, vsi->state); - } - } - /* retain SW VSI data structure since it is needed to unregister and * free VSI netdev when PF is not in reset recovery pending state,\ * for ex: during rmmod. diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c index b74a50bfa906..4f70f5553c80 100644 --- a/drivers/net/ethernet/intel/ice/ice_main.c +++ b/drivers/net/ethernet/intel/ice/ice_main.c @@ -4431,9 +4431,9 @@ static int ice_start_eth(struct ice_vsi *vsi) if (err) return err; - rtnl_lock(); err = ice_vsi_open(vsi); - rtnl_unlock(); + if (err) + ice_fltr_remove_all(vsi); return err; } @@ -4896,6 +4896,7 @@ int ice_load(struct ice_pf *pf) params = ice_vsi_to_params(vsi); params.flags = ICE_VSI_FLAG_INIT; + rtnl_lock(); err = ice_vsi_cfg(vsi, ¶ms); if (err) goto err_vsi_cfg; @@ -4903,6 +4904,7 @@ int ice_load(struct ice_pf *pf) err = ice_start_eth(ice_get_main_vsi(pf)); if (err) goto err_start_eth; + rtnl_unlock(); err = ice_init_rdma(pf); if (err) @@ -4917,9 +4919,11 @@ int ice_load(struct ice_pf *pf) err_init_rdma: ice_vsi_close(ice_get_main_vsi(pf)); + rtnl_lock(); err_start_eth: ice_vsi_decfg(ice_get_main_vsi(pf)); err_vsi_cfg: + rtnl_unlock(); ice_deinit_dev(pf); return err; } @@ -4932,8 +4936,10 @@ void ice_unload(struct ice_pf *pf) { ice_deinit_features(pf); ice_deinit_rdma(pf); + rtnl_lock(); ice_stop_eth(ice_get_main_vsi(pf)); ice_vsi_decfg(ice_get_main_vsi(pf)); + rtnl_unlock(); ice_deinit_dev(pf); } diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c index ddb4386c00cc..b9146d84fa16 100644 --- a/drivers/net/ethernet/intel/igc/igc_main.c +++ b/drivers/net/ethernet/intel/igc/igc_main.c @@ -2828,9 +2828,8 @@ static void igc_xdp_xmit_zc(struct igc_ring *ring) struct netdev_queue *nq = txring_txq(ring); union igc_adv_tx_desc *tx_desc = NULL; int cpu = smp_processor_id(); - u16 ntu = ring->next_to_use; struct xdp_desc xdp_desc; - u16 budget; + u16 budget, ntu; if (!netif_carrier_ok(ring->netdev)) return; @@ -2840,6 +2839,7 @@ static void igc_xdp_xmit_zc(struct igc_ring *ring) /* Avoid transmit queue timeout since we share it with the slow path */ txq_trans_cond_update(nq); + ntu = ring->next_to_use; budget = igc_desc_unused(ring); while (xsk_tx_peek_desc(pool, &xdp_desc) && budget--) { diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/cn10k_macsec.c b/drivers/net/ethernet/marvell/octeontx2/nic/cn10k_macsec.c index 6e2fb24be8c1..59b138214af2 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/cn10k_macsec.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/cn10k_macsec.c @@ -4,6 +4,7 @@ * Copyright (C) 2022 Marvell. */ +#include <crypto/skcipher.h> #include <linux/rtnetlink.h> #include <linux/bitfield.h> #include "otx2_common.h" @@ -42,6 +43,56 @@ #define MCS_TCI_E 0x08 /* encryption */ #define MCS_TCI_C 0x04 /* changed text */ +#define CN10K_MAX_HASH_LEN 16 +#define CN10K_MAX_SAK_LEN 32 + +static int cn10k_ecb_aes_encrypt(struct otx2_nic *pfvf, u8 *sak, + u16 sak_len, u8 *hash) +{ + u8 data[CN10K_MAX_HASH_LEN] = { 0 }; + struct skcipher_request *req = NULL; + struct scatterlist sg_src, sg_dst; + struct crypto_skcipher *tfm; + DECLARE_CRYPTO_WAIT(wait); + int err; + + tfm = crypto_alloc_skcipher("ecb(aes)", 0, 0); + if (IS_ERR(tfm)) { + dev_err(pfvf->dev, "failed to allocate transform for ecb-aes\n"); + return PTR_ERR(tfm); + } + + req = skcipher_request_alloc(tfm, GFP_KERNEL); + if (!req) { + dev_err(pfvf->dev, "failed to allocate request for skcipher\n"); + err = -ENOMEM; + goto free_tfm; + } + + err = crypto_skcipher_setkey(tfm, sak, sak_len); + if (err) { + dev_err(pfvf->dev, "failed to set key for skcipher\n"); + goto free_req; + } + + /* build sg list */ + sg_init_one(&sg_src, data, CN10K_MAX_HASH_LEN); + sg_init_one(&sg_dst, hash, CN10K_MAX_HASH_LEN); + + skcipher_request_set_callback(req, 0, crypto_req_done, &wait); + skcipher_request_set_crypt(req, &sg_src, &sg_dst, + CN10K_MAX_HASH_LEN, NULL); + + err = crypto_skcipher_encrypt(req); + err = crypto_wait_req(err, &wait); + +free_req: + skcipher_request_free(req); +free_tfm: + crypto_free_skcipher(tfm); + return err; +} + static struct cn10k_mcs_txsc *cn10k_mcs_get_txsc(struct cn10k_mcs_cfg *cfg, struct macsec_secy *secy) { @@ -330,19 +381,53 @@ fail: return ret; } +static int cn10k_mcs_write_keys(struct otx2_nic *pfvf, + struct macsec_secy *secy, + struct mcs_sa_plcy_write_req *req, + u8 *sak, u8 *salt, ssci_t ssci) +{ + u8 hash_rev[CN10K_MAX_HASH_LEN]; + u8 sak_rev[CN10K_MAX_SAK_LEN]; + u8 salt_rev[MACSEC_SALT_LEN]; + u8 hash[CN10K_MAX_HASH_LEN]; + u32 ssci_63_32; + int err, i; + + err = cn10k_ecb_aes_encrypt(pfvf, sak, secy->key_len, hash); + if (err) { + dev_err(pfvf->dev, "Generating hash using ECB(AES) failed\n"); + return err; + } + + for (i = 0; i < secy->key_len; i++) + sak_rev[i] = sak[secy->key_len - 1 - i]; + + for (i = 0; i < CN10K_MAX_HASH_LEN; i++) + hash_rev[i] = hash[CN10K_MAX_HASH_LEN - 1 - i]; + + for (i = 0; i < MACSEC_SALT_LEN; i++) + salt_rev[i] = salt[MACSEC_SALT_LEN - 1 - i]; + + ssci_63_32 = (__force u32)cpu_to_be32((__force u32)ssci); + + memcpy(&req->plcy[0][0], sak_rev, secy->key_len); + memcpy(&req->plcy[0][4], hash_rev, CN10K_MAX_HASH_LEN); + memcpy(&req->plcy[0][6], salt_rev, MACSEC_SALT_LEN); + req->plcy[0][7] |= (u64)ssci_63_32 << 32; + + return 0; +} + static int cn10k_mcs_write_rx_sa_plcy(struct otx2_nic *pfvf, struct macsec_secy *secy, struct cn10k_mcs_rxsc *rxsc, u8 assoc_num, bool sa_in_use) { - unsigned char *src = rxsc->sa_key[assoc_num]; struct mcs_sa_plcy_write_req *plcy_req; - u8 *salt_p = rxsc->salt[assoc_num]; + u8 *sak = rxsc->sa_key[assoc_num]; + u8 *salt = rxsc->salt[assoc_num]; struct mcs_rx_sc_sa_map *map_req; struct mbox *mbox = &pfvf->mbox; - u64 ssci_salt_95_64 = 0; - u8 reg, key_len; - u64 salt_63_0; int ret; mutex_lock(&mbox->lock); @@ -360,20 +445,10 @@ static int cn10k_mcs_write_rx_sa_plcy(struct otx2_nic *pfvf, goto fail; } - for (reg = 0, key_len = 0; key_len < secy->key_len; key_len += 8) { - memcpy((u8 *)&plcy_req->plcy[0][reg], - (src + reg * 8), 8); - reg++; - } - - if (secy->xpn) { - memcpy((u8 *)&salt_63_0, salt_p, 8); - memcpy((u8 *)&ssci_salt_95_64, salt_p + 8, 4); - ssci_salt_95_64 |= (__force u64)rxsc->ssci[assoc_num] << 32; - - plcy_req->plcy[0][6] = salt_63_0; - plcy_req->plcy[0][7] = ssci_salt_95_64; - } + ret = cn10k_mcs_write_keys(pfvf, secy, plcy_req, sak, + salt, rxsc->ssci[assoc_num]); + if (ret) + goto fail; plcy_req->sa_index[0] = rxsc->hw_sa_id[assoc_num]; plcy_req->sa_cnt = 1; @@ -586,13 +661,10 @@ static int cn10k_mcs_write_tx_sa_plcy(struct otx2_nic *pfvf, struct cn10k_mcs_txsc *txsc, u8 assoc_num) { - unsigned char *src = txsc->sa_key[assoc_num]; struct mcs_sa_plcy_write_req *plcy_req; - u8 *salt_p = txsc->salt[assoc_num]; + u8 *sak = txsc->sa_key[assoc_num]; + u8 *salt = txsc->salt[assoc_num]; struct mbox *mbox = &pfvf->mbox; - u64 ssci_salt_95_64 = 0; - u8 reg, key_len; - u64 salt_63_0; int ret; mutex_lock(&mbox->lock); @@ -603,19 +675,10 @@ static int cn10k_mcs_write_tx_sa_plcy(struct otx2_nic *pfvf, goto fail; } - for (reg = 0, key_len = 0; key_len < secy->key_len; key_len += 8) { - memcpy((u8 *)&plcy_req->plcy[0][reg], (src + reg * 8), 8); - reg++; - } - - if (secy->xpn) { - memcpy((u8 *)&salt_63_0, salt_p, 8); - memcpy((u8 *)&ssci_salt_95_64, salt_p + 8, 4); - ssci_salt_95_64 |= (__force u64)txsc->ssci[assoc_num] << 32; - - plcy_req->plcy[0][6] = salt_63_0; - plcy_req->plcy[0][7] = ssci_salt_95_64; - } + ret = cn10k_mcs_write_keys(pfvf, secy, plcy_req, sak, + salt, txsc->ssci[assoc_num]); + if (ret) + goto fail; plcy_req->plcy[0][8] = assoc_num; plcy_req->sa_index[0] = txsc->hw_sa_id[assoc_num]; diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c index fe8ea4e531b7..9551b422622a 100644 --- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c +++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c @@ -1454,8 +1454,9 @@ static int otx2_init_hw_resources(struct otx2_nic *pf) if (err) goto err_free_npa_lf; - /* Enable backpressure */ - otx2_nix_config_bp(pf, true); + /* Enable backpressure for CGX mapped PF/VFs */ + if (!is_otx2_lbkvf(pf->pdev)) + otx2_nix_config_bp(pf, true); /* Init Auras and pools used by NIX RQ, for free buffer ptrs */ err = otx2_rq_aura_pool_init(pf); diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c index 834c644b67db..2d15342c260a 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c @@ -3846,23 +3846,6 @@ static int mtk_hw_deinit(struct mtk_eth *eth) return 0; } -static int __init mtk_init(struct net_device *dev) -{ - struct mtk_mac *mac = netdev_priv(dev); - struct mtk_eth *eth = mac->hw; - int ret; - - ret = of_get_ethdev_address(mac->of_node, dev); - if (ret) { - /* If the mac address is invalid, use random mac address */ - eth_hw_addr_random(dev); - dev_err(eth->dev, "generated random MAC address %pM\n", - dev->dev_addr); - } - - return 0; -} - static void mtk_uninit(struct net_device *dev) { struct mtk_mac *mac = netdev_priv(dev); @@ -4278,7 +4261,6 @@ static const struct ethtool_ops mtk_ethtool_ops = { }; static const struct net_device_ops mtk_netdev_ops = { - .ndo_init = mtk_init, .ndo_uninit = mtk_uninit, .ndo_open = mtk_open, .ndo_stop = mtk_stop, @@ -4340,6 +4322,17 @@ static int mtk_add_mac(struct mtk_eth *eth, struct device_node *np) mac->hw = eth; mac->of_node = np; + err = of_get_ethdev_address(mac->of_node, eth->netdev[id]); + if (err == -EPROBE_DEFER) + return err; + + if (err) { + /* If the mac address is invalid, use random mac address */ + eth_hw_addr_random(eth->netdev[id]); + dev_err(eth->dev, "generated random MAC address %pM\n", + eth->netdev[id]->dev_addr); + } + memset(mac->hwlro_ip, 0, sizeof(mac->hwlro_ip)); mac->hwlro_ip_cnt = 0; diff --git a/drivers/net/ethernet/mediatek/mtk_ppe_debugfs.c b/drivers/net/ethernet/mediatek/mtk_ppe_debugfs.c index 316fe2e70fea..1a97feca77f2 100644 --- a/drivers/net/ethernet/mediatek/mtk_ppe_debugfs.c +++ b/drivers/net/ethernet/mediatek/mtk_ppe_debugfs.c @@ -98,7 +98,7 @@ mtk_ppe_debugfs_foe_show(struct seq_file *m, void *private, bool bind) acct = mtk_foe_entry_get_mib(ppe, i, NULL); - type = FIELD_GET(MTK_FOE_IB1_PACKET_TYPE, entry->ib1); + type = mtk_get_ib1_pkt_type(ppe->eth, entry->ib1); seq_printf(m, "%05x %s %7s", i, mtk_foe_entry_state_str(state), mtk_foe_pkt_type_str(type)); diff --git a/drivers/net/ethernet/mscc/ocelot_fdma.c b/drivers/net/ethernet/mscc/ocelot_fdma.c index 8e3894cf5f7c..83a3ce0c568e 100644 --- a/drivers/net/ethernet/mscc/ocelot_fdma.c +++ b/drivers/net/ethernet/mscc/ocelot_fdma.c @@ -368,7 +368,8 @@ static bool ocelot_fdma_receive_skb(struct ocelot *ocelot, struct sk_buff *skb) if (unlikely(!ndev)) return false; - pskb_trim(skb, skb->len - ETH_FCS_LEN); + if (pskb_trim(skb, skb->len - ETH_FCS_LEN)) + return false; skb->dev = ndev; skb->protocol = eth_type_trans(skb, skb->dev); diff --git a/drivers/net/ethernet/qualcomm/emac/emac-mac.c b/drivers/net/ethernet/qualcomm/emac/emac-mac.c index 0d80447d4d3b..d5c688a8d7be 100644 --- a/drivers/net/ethernet/qualcomm/emac/emac-mac.c +++ b/drivers/net/ethernet/qualcomm/emac/emac-mac.c @@ -1260,8 +1260,11 @@ static int emac_tso_csum(struct emac_adapter *adpt, if (skb->protocol == htons(ETH_P_IP)) { u32 pkt_len = ((unsigned char *)ip_hdr(skb) - skb->data) + ntohs(ip_hdr(skb)->tot_len); - if (skb->len > pkt_len) - pskb_trim(skb, pkt_len); + if (skb->len > pkt_len) { + ret = pskb_trim(skb, pkt_len); + if (unlikely(ret)) + return ret; + } } hdr_len = skb_tcp_all_headers(skb); diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c index 9445f04f8d48..5eb50b265c0b 100644 --- a/drivers/net/ethernet/realtek/r8169_main.c +++ b/drivers/net/ethernet/realtek/r8169_main.c @@ -623,6 +623,7 @@ struct rtl8169_private { int cfg9346_usage_count; unsigned supports_gmii:1; + unsigned aspm_manageable:1; dma_addr_t counters_phys_addr; struct rtl8169_counters *counters; struct rtl8169_tc_offsets tc_offset; @@ -2746,7 +2747,15 @@ static void rtl_hw_aspm_clkreq_enable(struct rtl8169_private *tp, bool enable) if (tp->mac_version < RTL_GIGA_MAC_VER_32) return; - if (enable) { + /* Don't enable ASPM in the chip if OS can't control ASPM */ + if (enable && tp->aspm_manageable) { + /* On these chip versions ASPM can even harm + * bus communication of other PCI devices. + */ + if (tp->mac_version == RTL_GIGA_MAC_VER_42 || + tp->mac_version == RTL_GIGA_MAC_VER_43) + return; + rtl_mod_config5(tp, 0, ASPM_en); rtl_mod_config2(tp, 0, ClkReqEn); @@ -4514,10 +4523,6 @@ static irqreturn_t rtl8169_interrupt(int irq, void *dev_instance) } if (napi_schedule_prep(&tp->napi)) { - rtl_unlock_config_regs(tp); - rtl_hw_aspm_clkreq_enable(tp, false); - rtl_lock_config_regs(tp); - rtl_irq_disable(tp); __napi_schedule(&tp->napi); } @@ -4577,14 +4582,9 @@ static int rtl8169_poll(struct napi_struct *napi, int budget) work_done = rtl_rx(dev, tp, budget); - if (work_done < budget && napi_complete_done(napi, work_done)) { + if (work_done < budget && napi_complete_done(napi, work_done)) rtl_irq_enable(tp); - rtl_unlock_config_regs(tp); - rtl_hw_aspm_clkreq_enable(tp, true); - rtl_lock_config_regs(tp); - } - return work_done; } @@ -5158,6 +5158,16 @@ done: rtl_rar_set(tp, mac_addr); } +/* register is set if system vendor successfully tested ASPM 1.2 */ +static bool rtl_aspm_is_safe(struct rtl8169_private *tp) +{ + if (tp->mac_version >= RTL_GIGA_MAC_VER_61 && + r8168_mac_ocp_read(tp, 0xc0b2) & 0xf) + return true; + + return false; +} + static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) { struct rtl8169_private *tp; @@ -5227,6 +5237,19 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) xid); tp->mac_version = chipset; + /* Disable ASPM L1 as that cause random device stop working + * problems as well as full system hangs for some PCIe devices users. + * Chips from RTL8168h partially have issues with L1.2, but seem + * to work fine with L1 and L1.1. + */ + if (rtl_aspm_is_safe(tp)) + rc = 0; + else if (tp->mac_version >= RTL_GIGA_MAC_VER_46) + rc = pci_disable_link_state(pdev, PCIE_LINK_STATE_L1_2); + else + rc = pci_disable_link_state(pdev, PCIE_LINK_STATE_L1); + tp->aspm_manageable = !rc; + tp->dash_type = rtl_check_dash(tp); tp->cp_cmd = RTL_R16(tp, CPlusCmd) & CPCMD_MASK; diff --git a/drivers/net/ethernet/ti/cpsw_ale.c b/drivers/net/ethernet/ti/cpsw_ale.c index 0c5e783e574c..64bf22cd860c 100644 --- a/drivers/net/ethernet/ti/cpsw_ale.c +++ b/drivers/net/ethernet/ti/cpsw_ale.c @@ -106,23 +106,37 @@ struct cpsw_ale_dev_id { static inline int cpsw_ale_get_field(u32 *ale_entry, u32 start, u32 bits) { - int idx; + int idx, idx2; + u32 hi_val = 0; idx = start / 32; + idx2 = (start + bits - 1) / 32; + /* Check if bits to be fetched exceed a word */ + if (idx != idx2) { + idx2 = 2 - idx2; /* flip */ + hi_val = ale_entry[idx2] << ((idx2 * 32) - start); + } start -= idx * 32; idx = 2 - idx; /* flip */ - return (ale_entry[idx] >> start) & BITMASK(bits); + return (hi_val + (ale_entry[idx] >> start)) & BITMASK(bits); } static inline void cpsw_ale_set_field(u32 *ale_entry, u32 start, u32 bits, u32 value) { - int idx; + int idx, idx2; value &= BITMASK(bits); - idx = start / 32; + idx = start / 32; + idx2 = (start + bits - 1) / 32; + /* Check if bits to be set exceed a word */ + if (idx != idx2) { + idx2 = 2 - idx2; /* flip */ + ale_entry[idx2] &= ~(BITMASK(bits + start - (idx2 * 32))); + ale_entry[idx2] |= (value >> ((idx2 * 32) - start)); + } start -= idx * 32; - idx = 2 - idx; /* flip */ + idx = 2 - idx; /* flip */ ale_entry[idx] &= ~(BITMASK(bits) << start); ale_entry[idx] |= (value << start); } diff --git a/drivers/net/ethernet/wangxun/libwx/wx_hw.c b/drivers/net/ethernet/wangxun/libwx/wx_hw.c index f833c84a7876..85dc16faca54 100644 --- a/drivers/net/ethernet/wangxun/libwx/wx_hw.c +++ b/drivers/net/ethernet/wangxun/libwx/wx_hw.c @@ -1446,7 +1446,6 @@ void wx_configure_rx(struct wx *wx) psrtype = WX_RDB_PL_CFG_L4HDR | WX_RDB_PL_CFG_L3HDR | WX_RDB_PL_CFG_L2HDR | - WX_RDB_PL_CFG_TUN_TUNHDR | WX_RDB_PL_CFG_TUN_TUNHDR; wr32(wx, WX_RDB_PL_CFG(0), psrtype); diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index 0c2014accba7..61921d4dbb13 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -3451,23 +3451,30 @@ static int __init phy_init(void) { int rc; + ethtool_set_ethtool_phy_ops(&phy_ethtool_phy_ops); + rc = mdio_bus_init(); if (rc) - return rc; + goto err_ethtool_phy_ops; - ethtool_set_ethtool_phy_ops(&phy_ethtool_phy_ops); features_init(); rc = phy_driver_register(&genphy_c45_driver, THIS_MODULE); if (rc) - goto err_c45; + goto err_mdio_bus; rc = phy_driver_register(&genphy_driver, THIS_MODULE); - if (rc) { - phy_driver_unregister(&genphy_c45_driver); + if (rc) + goto err_c45; + + return 0; + err_c45: - mdio_bus_exit(); - } + phy_driver_unregister(&genphy_c45_driver); +err_mdio_bus: + mdio_bus_exit(); +err_ethtool_phy_ops: + ethtool_set_ethtool_phy_ops(NULL); return rc; } diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c index 283ffddda821..2d14b0d78541 100644 --- a/drivers/net/usb/usbnet.c +++ b/drivers/net/usb/usbnet.c @@ -1775,6 +1775,10 @@ usbnet_probe (struct usb_interface *udev, const struct usb_device_id *prod) } else if (!info->in || !info->out) status = usbnet_get_endpoints (dev, udev); else { + u8 ep_addrs[3] = { + info->in + USB_DIR_IN, info->out + USB_DIR_OUT, 0 + }; + dev->in = usb_rcvbulkpipe (xdev, info->in); dev->out = usb_sndbulkpipe (xdev, info->out); if (!(info->flags & FLAG_NO_SETINT)) @@ -1784,6 +1788,8 @@ usbnet_probe (struct usb_interface *udev, const struct usb_device_id *prod) else status = 0; + if (status == 0 && !usb_check_bulk_endpoints(udev, ep_addrs)) + status = -EINVAL; } if (status >= 0 && dev->status) status = init_status (dev, udev); diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c index bdb3a76a352e..6043e63b42f9 100644 --- a/drivers/net/vrf.c +++ b/drivers/net/vrf.c @@ -664,7 +664,7 @@ static int vrf_finish_output6(struct net *net, struct sock *sk, skb->protocol = htons(ETH_P_IPV6); skb->dev = dev; - rcu_read_lock_bh(); + rcu_read_lock(); nexthop = rt6_nexthop((struct rt6_info *)dst, &ipv6_hdr(skb)->daddr); neigh = __ipv6_neigh_lookup_noref(dst->dev, nexthop); if (unlikely(!neigh)) @@ -672,10 +672,10 @@ static int vrf_finish_output6(struct net *net, struct sock *sk, if (!IS_ERR(neigh)) { sock_confirm_neigh(skb, neigh); ret = neigh_output(neigh, skb, false); - rcu_read_unlock_bh(); + rcu_read_unlock(); return ret; } - rcu_read_unlock_bh(); + rcu_read_unlock(); IP6_INC_STATS(dev_net(dst->dev), ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES); @@ -889,7 +889,7 @@ static int vrf_finish_output(struct net *net, struct sock *sk, struct sk_buff *s } } - rcu_read_lock_bh(); + rcu_read_lock(); neigh = ip_neigh_for_gw(rt, skb, &is_v6gw); if (!IS_ERR(neigh)) { @@ -898,11 +898,11 @@ static int vrf_finish_output(struct net *net, struct sock *sk, struct sk_buff *s sock_confirm_neigh(skb, neigh); /* if crossing protocols, can not use the cached header */ ret = neigh_output(neigh, skb, is_v6gw); - rcu_read_unlock_bh(); + rcu_read_unlock(); return ret; } - rcu_read_unlock_bh(); + rcu_read_unlock(); vrf_tx_error(skb->dev, skb); return -EINVAL; } diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index 47d7ba2827ff..37b6fa746662 100644 --- a/drivers/nvme/host/core.c +++ b/drivers/nvme/host/core.c @@ -3431,10 +3431,40 @@ static int nvme_init_ns_head(struct nvme_ns *ns, struct nvme_ns_info *info) ret = nvme_global_check_duplicate_ids(ctrl->subsys, &info->ids); if (ret) { - dev_err(ctrl->device, - "globally duplicate IDs for nsid %d\n", info->nsid); + /* + * We've found two different namespaces on two different + * subsystems that report the same ID. This is pretty nasty + * for anything that actually requires unique device + * identification. In the kernel we need this for multipathing, + * and in user space the /dev/disk/by-id/ links rely on it. + * + * If the device also claims to be multi-path capable back off + * here now and refuse the probe the second device as this is a + * recipe for data corruption. If not this is probably a + * cheap consumer device if on the PCIe bus, so let the user + * proceed and use the shiny toy, but warn that with changing + * probing order (which due to our async probing could just be + * device taking longer to startup) the other device could show + * up at any time. + */ nvme_print_device_info(ctrl); - return ret; + if ((ns->ctrl->ops->flags & NVME_F_FABRICS) || /* !PCIe */ + ((ns->ctrl->subsys->cmic & NVME_CTRL_CMIC_MULTI_CTRL) && + info->is_shared)) { + dev_err(ctrl->device, + "ignoring nsid %d because of duplicate IDs\n", + info->nsid); + return ret; + } + + dev_err(ctrl->device, + "clearing duplicate IDs for nsid %d\n", info->nsid); + dev_err(ctrl->device, + "use of /dev/disk/by-id/ may cause data corruption\n"); + memset(&info->ids.nguid, 0, sizeof(info->ids.nguid)); + memset(&info->ids.uuid, 0, sizeof(info->ids.uuid)); + memset(&info->ids.eui64, 0, sizeof(info->ids.eui64)); + ctrl->quirks |= NVME_QUIRK_BOGUS_NID; } mutex_lock(&ctrl->subsys->lock); diff --git a/drivers/nvme/host/fault_inject.c b/drivers/nvme/host/fault_inject.c index 83d2e6860d38..1ba10a5c656d 100644 --- a/drivers/nvme/host/fault_inject.c +++ b/drivers/nvme/host/fault_inject.c @@ -27,7 +27,7 @@ void nvme_fault_inject_init(struct nvme_fault_inject *fault_inj, /* create debugfs directory and attribute */ parent = debugfs_create_dir(dev_name, NULL); - if (!parent) { + if (IS_ERR(parent)) { pr_warn("%s: failed to create debugfs directory\n", dev_name); return; } diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c index 691f2df574ce..1cd2bf82319a 100644 --- a/drivers/nvme/host/fc.c +++ b/drivers/nvme/host/fc.c @@ -2548,14 +2548,24 @@ nvme_fc_error_recovery(struct nvme_fc_ctrl *ctrl, char *errmsg) * the controller. Abort any ios on the association and let the * create_association error path resolve things. */ - if (ctrl->ctrl.state == NVME_CTRL_CONNECTING) { - __nvme_fc_abort_outstanding_ios(ctrl, true); + enum nvme_ctrl_state state; + unsigned long flags; + + spin_lock_irqsave(&ctrl->lock, flags); + state = ctrl->ctrl.state; + if (state == NVME_CTRL_CONNECTING) { set_bit(ASSOC_FAILED, &ctrl->flags); + spin_unlock_irqrestore(&ctrl->lock, flags); + __nvme_fc_abort_outstanding_ios(ctrl, true); + dev_warn(ctrl->ctrl.device, + "NVME-FC{%d}: transport error during (re)connect\n", + ctrl->cnum); return; } + spin_unlock_irqrestore(&ctrl->lock, flags); /* Otherwise, only proceed if in LIVE state - e.g. on first error */ - if (ctrl->ctrl.state != NVME_CTRL_LIVE) + if (state != NVME_CTRL_LIVE) return; dev_warn(ctrl->ctrl.device, @@ -3110,7 +3120,9 @@ nvme_fc_create_association(struct nvme_fc_ctrl *ctrl) */ ret = nvme_enable_ctrl(&ctrl->ctrl); - if (ret || test_bit(ASSOC_FAILED, &ctrl->flags)) + if (!ret && test_bit(ASSOC_FAILED, &ctrl->flags)) + ret = -EIO; + if (ret) goto out_disconnect_admin_queue; ctrl->ctrl.max_segments = ctrl->lport->ops->max_sgl_segments; @@ -3120,7 +3132,9 @@ nvme_fc_create_association(struct nvme_fc_ctrl *ctrl) nvme_unquiesce_admin_queue(&ctrl->ctrl); ret = nvme_init_ctrl_finish(&ctrl->ctrl, false); - if (ret || test_bit(ASSOC_FAILED, &ctrl->flags)) + if (!ret && test_bit(ASSOC_FAILED, &ctrl->flags)) + ret = -EIO; + if (ret) goto out_disconnect_admin_queue; /* sanity checks */ @@ -3165,10 +3179,16 @@ nvme_fc_create_association(struct nvme_fc_ctrl *ctrl) else ret = nvme_fc_recreate_io_queues(ctrl); } - if (ret || test_bit(ASSOC_FAILED, &ctrl->flags)) - goto out_term_aen_ops; + spin_lock_irqsave(&ctrl->lock, flags); + if (!ret && test_bit(ASSOC_FAILED, &ctrl->flags)) + ret = -EIO; + if (ret) { + spin_unlock_irqrestore(&ctrl->lock, flags); + goto out_term_aen_ops; + } changed = nvme_change_ctrl_state(&ctrl->ctrl, NVME_CTRL_LIVE); + spin_unlock_irqrestore(&ctrl->lock, flags); ctrl->ctrl.nr_reconnects = 0; @@ -3180,6 +3200,9 @@ nvme_fc_create_association(struct nvme_fc_ctrl *ctrl) out_term_aen_ops: nvme_fc_term_aen_ops(ctrl); out_disconnect_admin_queue: + dev_warn(ctrl->ctrl.device, + "NVME-FC{%d}: create_assoc failed, assoc_id %llx ret %d\n", + ctrl->cnum, ctrl->association_id, ret); /* send a Disconnect(association) LS to fc-nvme target */ nvme_fc_xmt_disconnect_assoc(ctrl); spin_lock_irqsave(&ctrl->lock, flags); diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c index 72725729cb6c..baf69af7ea78 100644 --- a/drivers/nvme/host/pci.c +++ b/drivers/nvme/host/pci.c @@ -967,7 +967,7 @@ static __always_inline void nvme_pci_unmap_rq(struct request *req) struct nvme_iod *iod = blk_mq_rq_to_pdu(req); dma_unmap_page(dev->dev, iod->meta_dma, - rq_integrity_vec(req)->bv_len, rq_data_dir(req)); + rq_integrity_vec(req)->bv_len, rq_dma_dir(req)); } if (blk_rq_nr_phys_segments(req)) @@ -1298,9 +1298,7 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req) */ if (nvme_should_reset(dev, csts)) { nvme_warn_reset(dev, csts); - nvme_dev_disable(dev, false); - nvme_reset_ctrl(&dev->ctrl); - return BLK_EH_DONE; + goto disable; } /* @@ -1351,10 +1349,7 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req) "I/O %d QID %d timeout, reset controller\n", req->tag, nvmeq->qid); nvme_req(req)->flags |= NVME_REQ_CANCELLED; - nvme_dev_disable(dev, false); - nvme_reset_ctrl(&dev->ctrl); - - return BLK_EH_DONE; + goto disable; } if (atomic_dec_return(&dev->ctrl.abort_limit) < 0) { @@ -1391,6 +1386,15 @@ static enum blk_eh_timer_return nvme_timeout(struct request *req) * as the device then is in a faulty state. */ return BLK_EH_RESET_TIMER; + +disable: + if (!nvme_change_ctrl_state(&dev->ctrl, NVME_CTRL_RESETTING)) + return BLK_EH_DONE; + + nvme_dev_disable(dev, false); + if (nvme_try_sched_reset(&dev->ctrl)) + nvme_unquiesce_io_queues(&dev->ctrl); + return BLK_EH_DONE; } static void nvme_free_queue(struct nvme_queue *nvmeq) @@ -3278,6 +3282,10 @@ static pci_ers_result_t nvme_error_detected(struct pci_dev *pdev, case pci_channel_io_frozen: dev_warn(dev->ctrl.device, "frozen state error detected, reset controller\n"); + if (!nvme_change_ctrl_state(&dev->ctrl, NVME_CTRL_RESETTING)) { + nvme_dev_disable(dev, true); + return PCI_ERS_RESULT_DISCONNECT; + } nvme_dev_disable(dev, false); return PCI_ERS_RESULT_NEED_RESET; case pci_channel_io_perm_failure: @@ -3294,7 +3302,8 @@ static pci_ers_result_t nvme_slot_reset(struct pci_dev *pdev) dev_info(dev->ctrl.device, "restart after slot reset\n"); pci_restore_state(pdev); - nvme_reset_ctrl(&dev->ctrl); + if (!nvme_try_sched_reset(&dev->ctrl)) + nvme_unquiesce_io_queues(&dev->ctrl); return PCI_ERS_RESULT_RECOVERED; } @@ -3396,6 +3405,8 @@ static const struct pci_device_id nvme_id_table[] = { .driver_data = NVME_QUIRK_DISABLE_WRITE_ZEROES, }, { PCI_DEVICE(0x144d, 0xa809), /* Samsung MZALQ256HBJD 256G */ .driver_data = NVME_QUIRK_DISABLE_WRITE_ZEROES, }, + { PCI_DEVICE(0x144d, 0xa802), /* Samsung SM953 */ + .driver_data = NVME_QUIRK_BOGUS_NID, }, { PCI_DEVICE(0x1cc4, 0x6303), /* UMIS RPJTJ512MGE1QDY 512G */ .driver_data = NVME_QUIRK_DISABLE_WRITE_ZEROES, }, { PCI_DEVICE(0x1cc4, 0x6302), /* UMIS RPJTJ256MGE1QDY 256G */ diff --git a/drivers/nvme/host/sysfs.c b/drivers/nvme/host/sysfs.c index 45e91811f905..212e1b05d298 100644 --- a/drivers/nvme/host/sysfs.c +++ b/drivers/nvme/host/sysfs.c @@ -92,7 +92,7 @@ static ssize_t uuid_show(struct device *dev, struct device_attribute *attr, * we have no UUID set */ if (uuid_is_null(&ids->uuid)) { - dev_warn_ratelimited(dev, + dev_warn_once(dev, "No UUID available providing old NGUID\n"); return sysfs_emit(buf, "%pU\n", ids->nguid); } diff --git a/drivers/nvme/host/zns.c b/drivers/nvme/host/zns.c index 12316ab51bda..ec8557810c21 100644 --- a/drivers/nvme/host/zns.c +++ b/drivers/nvme/host/zns.c @@ -10,12 +10,11 @@ int nvme_revalidate_zones(struct nvme_ns *ns) { struct request_queue *q = ns->queue; - int ret; - ret = blk_revalidate_disk_zones(ns->disk, NULL); - if (!ret) - blk_queue_max_zone_append_sectors(q, ns->ctrl->max_zone_append); - return ret; + blk_queue_chunk_sectors(q, ns->zsze); + blk_queue_max_zone_append_sectors(q, ns->ctrl->max_zone_append); + + return blk_revalidate_disk_zones(ns->disk, NULL); } static int nvme_set_max_append(struct nvme_ctrl *ctrl) diff --git a/drivers/nvme/target/loop.c b/drivers/nvme/target/loop.c index f2d24b2d992f..48d5df054cd0 100644 --- a/drivers/nvme/target/loop.c +++ b/drivers/nvme/target/loop.c @@ -373,7 +373,7 @@ static int nvme_loop_configure_admin_queue(struct nvme_loop_ctrl *ctrl) goto out_cleanup_tagset; ctrl->ctrl.max_hw_sectors = - (NVME_LOOP_MAX_SEGMENTS - 1) << (PAGE_SHIFT - 9); + (NVME_LOOP_MAX_SEGMENTS - 1) << PAGE_SECTORS_SHIFT; nvme_unquiesce_admin_queue(&ctrl->ctrl); diff --git a/drivers/nvme/target/passthru.c b/drivers/nvme/target/passthru.c index 71a9c1cc57f5..9fe07d7efa96 100644 --- a/drivers/nvme/target/passthru.c +++ b/drivers/nvme/target/passthru.c @@ -102,14 +102,14 @@ static u16 nvmet_passthru_override_id_ctrl(struct nvmet_req *req) * which depends on the host's memory fragementation. To solve this, * ensure mdts is limited to the pages equal to the number of segments. */ - max_hw_sectors = min_not_zero(pctrl->max_segments << (PAGE_SHIFT - 9), + max_hw_sectors = min_not_zero(pctrl->max_segments << PAGE_SECTORS_SHIFT, pctrl->max_hw_sectors); /* * nvmet_passthru_map_sg is limitted to using a single bio so limit * the mdts based on BIO_MAX_VECS as well */ - max_hw_sectors = min_not_zero(BIO_MAX_VECS << (PAGE_SHIFT - 9), + max_hw_sectors = min_not_zero(BIO_MAX_VECS << PAGE_SECTORS_SHIFT, max_hw_sectors); page_shift = NVME_CAP_MPSMIN(ctrl->cap) + 12; diff --git a/drivers/perf/riscv_pmu.c b/drivers/perf/riscv_pmu.c index ebca5eab9c9b..56897d4d4fd3 100644 --- a/drivers/perf/riscv_pmu.c +++ b/drivers/perf/riscv_pmu.c @@ -181,9 +181,6 @@ void riscv_pmu_start(struct perf_event *event, int flags) uint64_t max_period = riscv_pmu_ctr_get_width_mask(event); u64 init_val; - if (WARN_ON_ONCE(!(event->hw.state & PERF_HES_STOPPED))) - return; - if (flags & PERF_EF_RELOAD) WARN_ON_ONCE(!(event->hw.state & PERF_HES_UPTODATE)); diff --git a/drivers/pinctrl/pinctrl-amd.c b/drivers/pinctrl/pinctrl-amd.c index 3c4220be30ec..4a8c1b57a90d 100644 --- a/drivers/pinctrl/pinctrl-amd.c +++ b/drivers/pinctrl/pinctrl-amd.c @@ -116,21 +116,19 @@ static void amd_gpio_set_value(struct gpio_chip *gc, unsigned offset, int value) raw_spin_unlock_irqrestore(&gpio_dev->lock, flags); } -static int amd_gpio_set_debounce(struct gpio_chip *gc, unsigned offset, - unsigned debounce) +static int amd_gpio_set_debounce(struct amd_gpio *gpio_dev, unsigned int offset, + unsigned int debounce) { u32 time; u32 pin_reg; int ret = 0; - unsigned long flags; - struct amd_gpio *gpio_dev = gpiochip_get_data(gc); - - raw_spin_lock_irqsave(&gpio_dev->lock, flags); /* Use special handling for Pin0 debounce */ - pin_reg = readl(gpio_dev->base + WAKE_INT_MASTER_REG); - if (pin_reg & INTERNAL_GPIO0_DEBOUNCE) - debounce = 0; + if (offset == 0) { + pin_reg = readl(gpio_dev->base + WAKE_INT_MASTER_REG); + if (pin_reg & INTERNAL_GPIO0_DEBOUNCE) + debounce = 0; + } pin_reg = readl(gpio_dev->base + offset * 4); @@ -182,23 +180,10 @@ static int amd_gpio_set_debounce(struct gpio_chip *gc, unsigned offset, pin_reg &= ~(DB_CNTRl_MASK << DB_CNTRL_OFF); } writel(pin_reg, gpio_dev->base + offset * 4); - raw_spin_unlock_irqrestore(&gpio_dev->lock, flags); return ret; } -static int amd_gpio_set_config(struct gpio_chip *gc, unsigned offset, - unsigned long config) -{ - u32 debounce; - - if (pinconf_to_config_param(config) != PIN_CONFIG_INPUT_DEBOUNCE) - return -ENOTSUPP; - - debounce = pinconf_to_config_argument(config); - return amd_gpio_set_debounce(gc, offset, debounce); -} - #ifdef CONFIG_DEBUG_FS static void amd_gpio_dbg_show(struct seq_file *s, struct gpio_chip *gc) { @@ -220,7 +205,6 @@ static void amd_gpio_dbg_show(struct seq_file *s, struct gpio_chip *gc) char *pin_sts; char *interrupt_sts; char *wake_sts; - char *pull_up_sel; char *orientation; char debounce_value[40]; char *debounce_enable; @@ -328,14 +312,9 @@ static void amd_gpio_dbg_show(struct seq_file *s, struct gpio_chip *gc) seq_printf(s, " %s|", wake_sts); if (pin_reg & BIT(PULL_UP_ENABLE_OFF)) { - if (pin_reg & BIT(PULL_UP_SEL_OFF)) - pull_up_sel = "8k"; - else - pull_up_sel = "4k"; - seq_printf(s, "%s ↑|", - pull_up_sel); + seq_puts(s, " ↑ |"); } else if (pin_reg & BIT(PULL_DOWN_ENABLE_OFF)) { - seq_puts(s, " ↓|"); + seq_puts(s, " ↓ |"); } else { seq_puts(s, " |"); } @@ -761,7 +740,7 @@ static int amd_pinconf_get(struct pinctrl_dev *pctldev, break; case PIN_CONFIG_BIAS_PULL_UP: - arg = (pin_reg >> PULL_UP_SEL_OFF) & (BIT(0) | BIT(1)); + arg = (pin_reg >> PULL_UP_ENABLE_OFF) & BIT(0); break; case PIN_CONFIG_DRIVE_STRENGTH: @@ -780,7 +759,7 @@ static int amd_pinconf_get(struct pinctrl_dev *pctldev, } static int amd_pinconf_set(struct pinctrl_dev *pctldev, unsigned int pin, - unsigned long *configs, unsigned num_configs) + unsigned long *configs, unsigned int num_configs) { int i; u32 arg; @@ -798,9 +777,8 @@ static int amd_pinconf_set(struct pinctrl_dev *pctldev, unsigned int pin, switch (param) { case PIN_CONFIG_INPUT_DEBOUNCE: - pin_reg &= ~DB_TMR_OUT_MASK; - pin_reg |= arg & DB_TMR_OUT_MASK; - break; + ret = amd_gpio_set_debounce(gpio_dev, pin, arg); + goto out_unlock; case PIN_CONFIG_BIAS_PULL_DOWN: pin_reg &= ~BIT(PULL_DOWN_ENABLE_OFF); @@ -808,10 +786,8 @@ static int amd_pinconf_set(struct pinctrl_dev *pctldev, unsigned int pin, break; case PIN_CONFIG_BIAS_PULL_UP: - pin_reg &= ~BIT(PULL_UP_SEL_OFF); - pin_reg |= (arg & BIT(0)) << PULL_UP_SEL_OFF; pin_reg &= ~BIT(PULL_UP_ENABLE_OFF); - pin_reg |= ((arg>>1) & BIT(0)) << PULL_UP_ENABLE_OFF; + pin_reg |= (arg & BIT(0)) << PULL_UP_ENABLE_OFF; break; case PIN_CONFIG_DRIVE_STRENGTH: @@ -829,6 +805,7 @@ static int amd_pinconf_set(struct pinctrl_dev *pctldev, unsigned int pin, writel(pin_reg, gpio_dev->base + pin*4); } +out_unlock: raw_spin_unlock_irqrestore(&gpio_dev->lock, flags); return ret; @@ -870,6 +847,14 @@ static int amd_pinconf_group_set(struct pinctrl_dev *pctldev, return 0; } +static int amd_gpio_set_config(struct gpio_chip *gc, unsigned int pin, + unsigned long config) +{ + struct amd_gpio *gpio_dev = gpiochip_get_data(gc); + + return amd_pinconf_set(gpio_dev->pctrl, pin, &config, 1); +} + static const struct pinconf_ops amd_pinconf_ops = { .pin_config_get = amd_pinconf_get, .pin_config_set = amd_pinconf_set, diff --git a/drivers/pinctrl/pinctrl-amd.h b/drivers/pinctrl/pinctrl-amd.h index 1cf2d06bbd8c..34c5c3e71fb2 100644 --- a/drivers/pinctrl/pinctrl-amd.h +++ b/drivers/pinctrl/pinctrl-amd.h @@ -36,7 +36,6 @@ #define WAKE_CNTRL_OFF_S4 15 #define PIN_STS_OFF 16 #define DRV_STRENGTH_SEL_OFF 17 -#define PULL_UP_SEL_OFF 19 #define PULL_UP_ENABLE_OFF 20 #define PULL_DOWN_ENABLE_OFF 21 #define OUTPUT_VALUE_OFF 22 diff --git a/drivers/pinctrl/renesas/pinctrl-rzg2l.c b/drivers/pinctrl/renesas/pinctrl-rzg2l.c index 9511d920565e..b53d26167da5 100644 --- a/drivers/pinctrl/renesas/pinctrl-rzg2l.c +++ b/drivers/pinctrl/renesas/pinctrl-rzg2l.c @@ -249,6 +249,7 @@ static int rzg2l_map_add_config(struct pinctrl_map *map, static int rzg2l_dt_subnode_to_map(struct pinctrl_dev *pctldev, struct device_node *np, + struct device_node *parent, struct pinctrl_map **map, unsigned int *num_maps, unsigned int *index) @@ -266,6 +267,7 @@ static int rzg2l_dt_subnode_to_map(struct pinctrl_dev *pctldev, struct property *prop; int ret, gsel, fsel; const char **pin_fn; + const char *name; const char *pin; pinmux = of_find_property(np, "pinmux", NULL); @@ -349,8 +351,19 @@ static int rzg2l_dt_subnode_to_map(struct pinctrl_dev *pctldev, psel_val[i] = MUX_FUNC(value); } + if (parent) { + name = devm_kasprintf(pctrl->dev, GFP_KERNEL, "%pOFn.%pOFn", + parent, np); + if (!name) { + ret = -ENOMEM; + goto done; + } + } else { + name = np->name; + } + /* Register a single pin group listing all the pins we read from DT */ - gsel = pinctrl_generic_add_group(pctldev, np->name, pins, num_pinmux, NULL); + gsel = pinctrl_generic_add_group(pctldev, name, pins, num_pinmux, NULL); if (gsel < 0) { ret = gsel; goto done; @@ -360,17 +373,16 @@ static int rzg2l_dt_subnode_to_map(struct pinctrl_dev *pctldev, * Register a single group function where the 'data' is an array PSEL * register values read from DT. */ - pin_fn[0] = np->name; - fsel = pinmux_generic_add_function(pctldev, np->name, pin_fn, 1, - psel_val); + pin_fn[0] = name; + fsel = pinmux_generic_add_function(pctldev, name, pin_fn, 1, psel_val); if (fsel < 0) { ret = fsel; goto remove_group; } maps[idx].type = PIN_MAP_TYPE_MUX_GROUP; - maps[idx].data.mux.group = np->name; - maps[idx].data.mux.function = np->name; + maps[idx].data.mux.group = name; + maps[idx].data.mux.function = name; idx++; dev_dbg(pctrl->dev, "Parsed %pOF with %d pins\n", np, num_pinmux); @@ -417,7 +429,7 @@ static int rzg2l_dt_node_to_map(struct pinctrl_dev *pctldev, index = 0; for_each_child_of_node(np, child) { - ret = rzg2l_dt_subnode_to_map(pctldev, child, map, + ret = rzg2l_dt_subnode_to_map(pctldev, child, np, map, num_maps, &index); if (ret < 0) { of_node_put(child); @@ -426,7 +438,7 @@ static int rzg2l_dt_node_to_map(struct pinctrl_dev *pctldev, } if (*num_maps == 0) { - ret = rzg2l_dt_subnode_to_map(pctldev, np, map, + ret = rzg2l_dt_subnode_to_map(pctldev, np, NULL, map, num_maps, &index); if (ret < 0) goto done; diff --git a/drivers/pinctrl/renesas/pinctrl-rzv2m.c b/drivers/pinctrl/renesas/pinctrl-rzv2m.c index e5472293bc7f..35b23c1a5684 100644 --- a/drivers/pinctrl/renesas/pinctrl-rzv2m.c +++ b/drivers/pinctrl/renesas/pinctrl-rzv2m.c @@ -209,6 +209,7 @@ static int rzv2m_map_add_config(struct pinctrl_map *map, static int rzv2m_dt_subnode_to_map(struct pinctrl_dev *pctldev, struct device_node *np, + struct device_node *parent, struct pinctrl_map **map, unsigned int *num_maps, unsigned int *index) @@ -226,6 +227,7 @@ static int rzv2m_dt_subnode_to_map(struct pinctrl_dev *pctldev, struct property *prop; int ret, gsel, fsel; const char **pin_fn; + const char *name; const char *pin; pinmux = of_find_property(np, "pinmux", NULL); @@ -309,8 +311,19 @@ static int rzv2m_dt_subnode_to_map(struct pinctrl_dev *pctldev, psel_val[i] = MUX_FUNC(value); } + if (parent) { + name = devm_kasprintf(pctrl->dev, GFP_KERNEL, "%pOFn.%pOFn", + parent, np); + if (!name) { + ret = -ENOMEM; + goto done; + } + } else { + name = np->name; + } + /* Register a single pin group listing all the pins we read from DT */ - gsel = pinctrl_generic_add_group(pctldev, np->name, pins, num_pinmux, NULL); + gsel = pinctrl_generic_add_group(pctldev, name, pins, num_pinmux, NULL); if (gsel < 0) { ret = gsel; goto done; @@ -320,17 +333,16 @@ static int rzv2m_dt_subnode_to_map(struct pinctrl_dev *pctldev, * Register a single group function where the 'data' is an array PSEL * register values read from DT. */ - pin_fn[0] = np->name; - fsel = pinmux_generic_add_function(pctldev, np->name, pin_fn, 1, - psel_val); + pin_fn[0] = name; + fsel = pinmux_generic_add_function(pctldev, name, pin_fn, 1, psel_val); if (fsel < 0) { ret = fsel; goto remove_group; } maps[idx].type = PIN_MAP_TYPE_MUX_GROUP; - maps[idx].data.mux.group = np->name; - maps[idx].data.mux.function = np->name; + maps[idx].data.mux.group = name; + maps[idx].data.mux.function = name; idx++; dev_dbg(pctrl->dev, "Parsed %pOF with %d pins\n", np, num_pinmux); @@ -377,7 +389,7 @@ static int rzv2m_dt_node_to_map(struct pinctrl_dev *pctldev, index = 0; for_each_child_of_node(np, child) { - ret = rzv2m_dt_subnode_to_map(pctldev, child, map, + ret = rzv2m_dt_subnode_to_map(pctldev, child, np, map, num_maps, &index); if (ret < 0) { of_node_put(child); @@ -386,7 +398,7 @@ static int rzv2m_dt_node_to_map(struct pinctrl_dev *pctldev, } if (*num_maps == 0) { - ret = rzv2m_dt_subnode_to_map(pctldev, np, map, + ret = rzv2m_dt_subnode_to_map(pctldev, np, NULL, map, num_maps, &index); if (ret < 0) goto done; diff --git a/drivers/regulator/da9063-regulator.c b/drivers/regulator/da9063-regulator.c index c5dd77be558b..dfd5ec9f75c9 100644 --- a/drivers/regulator/da9063-regulator.c +++ b/drivers/regulator/da9063-regulator.c @@ -778,6 +778,9 @@ static int da9063_check_xvp_constraints(struct regulator_config *config) const struct notification_limit *uv_l = &constr->under_voltage_limits; const struct notification_limit *ov_l = &constr->over_voltage_limits; + if (!config->init_data) /* No config in DT, pointers will be invalid */ + return 0; + /* make sure that only one severity is used to clarify if unchanged, enabled or disabled */ if ((!!uv_l->prot + !!uv_l->err + !!uv_l->warn) > 1) { dev_err(config->dev, "%s: at most one voltage monitoring severity allowed!\n", diff --git a/drivers/scsi/aacraid/aacraid.h b/drivers/scsi/aacraid/aacraid.h index 7c6efde75da6..73b6ac0c01f5 100644 --- a/drivers/scsi/aacraid/aacraid.h +++ b/drivers/scsi/aacraid/aacraid.h @@ -2618,7 +2618,7 @@ struct aac_hba_info { struct aac_aifcmd { __le32 command; /* Tell host what type of notify this is */ __le32 seqnum; /* To allow ordering of reports (if necessary) */ - u8 data[1]; /* Undefined length (from kernel viewpoint) */ + u8 data[]; /* Undefined length (from kernel viewpoint) */ }; /** diff --git a/drivers/scsi/fnic/fnic_trace.c b/drivers/scsi/fnic/fnic_trace.c index f3c3a26a1384..be0d7c57b242 100644 --- a/drivers/scsi/fnic/fnic_trace.c +++ b/drivers/scsi/fnic/fnic_trace.c @@ -465,7 +465,7 @@ int fnic_trace_buf_init(void) fnic_max_trace_entries = (trace_max_pages * PAGE_SIZE)/ FNIC_ENTRY_SIZE_BYTES; - fnic_trace_buf_p = (unsigned long)vzalloc(trace_max_pages * PAGE_SIZE); + fnic_trace_buf_p = (unsigned long)vcalloc(trace_max_pages, PAGE_SIZE); if (!fnic_trace_buf_p) { printk(KERN_ERR PFX "Failed to allocate memory " "for fnic_trace_buf_p\n"); diff --git a/drivers/scsi/lpfc/lpfc_hbadisc.c b/drivers/scsi/lpfc/lpfc_hbadisc.c index 499849b58ee4..fdd7f69d87ef 100644 --- a/drivers/scsi/lpfc/lpfc_hbadisc.c +++ b/drivers/scsi/lpfc/lpfc_hbadisc.c @@ -6944,7 +6944,9 @@ lpfc_unregister_fcf_rescan(struct lpfc_hba *phba) if (rc) return; /* Reset HBA FCF states after successful unregister FCF */ + spin_lock_irq(&phba->hbalock); phba->fcf.fcf_flag = 0; + spin_unlock_irq(&phba->hbalock); phba->fcf.current_rec.flag = 0; /* diff --git a/drivers/scsi/qla2xxx/qla_def.h b/drivers/scsi/qla2xxx/qla_def.h index d44c4d37b50b..4ae38305c15a 100644 --- a/drivers/scsi/qla2xxx/qla_def.h +++ b/drivers/scsi/qla2xxx/qla_def.h @@ -4462,7 +4462,6 @@ struct qla_hw_data { /* n2n */ struct fc_els_flogi plogi_els_payld; -#define LOGIN_TEMPLATE_SIZE (sizeof(struct fc_els_flogi) - 4) void *swl; diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c index c3dd8dd4f734..367fba27fe69 100644 --- a/drivers/scsi/qla2xxx/qla_init.c +++ b/drivers/scsi/qla2xxx/qla_init.c @@ -8434,7 +8434,7 @@ qla24xx_load_risc_flash(scsi_qla_host_t *vha, uint32_t *srisc_addr, ql_dbg(ql_dbg_init, vha, 0x0163, "-> fwdt%u template allocate template %#x words...\n", j, risc_size); - fwdt->template = vmalloc(risc_size * sizeof(*dcode)); + fwdt->template = vmalloc_array(risc_size, sizeof(*dcode)); if (!fwdt->template) { ql_log(ql_log_warn, vha, 0x0164, "-> fwdt%u failed allocate template.\n", j); @@ -8689,7 +8689,7 @@ qla24xx_load_risc_blob(scsi_qla_host_t *vha, uint32_t *srisc_addr) ql_dbg(ql_dbg_init, vha, 0x0173, "-> fwdt%u template allocate template %#x words...\n", j, risc_size); - fwdt->template = vmalloc(risc_size * sizeof(*dcode)); + fwdt->template = vmalloc_array(risc_size, sizeof(*dcode)); if (!fwdt->template) { ql_log(ql_log_warn, vha, 0x0174, "-> fwdt%u failed allocate template.\n", j); diff --git a/drivers/scsi/qla2xxx/qla_iocb.c b/drivers/scsi/qla2xxx/qla_iocb.c index a1675f056a5c..730d8609276c 100644 --- a/drivers/scsi/qla2xxx/qla_iocb.c +++ b/drivers/scsi/qla2xxx/qla_iocb.c @@ -3073,7 +3073,8 @@ qla24xx_els_dcmd2_iocb(scsi_qla_host_t *vha, int els_opcode, memset(ptr, 0, sizeof(struct els_plogi_payload)); memset(resp_ptr, 0, sizeof(struct els_plogi_payload)); memcpy(elsio->u.els_plogi.els_plogi_pyld->data, - &ha->plogi_els_payld.fl_csp, LOGIN_TEMPLATE_SIZE); + (void *)&ha->plogi_els_payld + offsetof(struct fc_els_flogi, fl_csp), + sizeof(ha->plogi_els_payld) - offsetof(struct fc_els_flogi, fl_csp)); elsio->u.els_plogi.els_cmd = els_opcode; elsio->u.els_plogi.els_plogi_pyld->opcode = els_opcode; @@ -3911,7 +3912,7 @@ qla2x00_start_sp(srb_t *sp) pkt = __qla2x00_alloc_iocbs(sp->qpair, sp); if (!pkt) { - rval = EAGAIN; + rval = -EAGAIN; ql_log(ql_log_warn, vha, 0x700c, "qla2x00_alloc_iocbs failed.\n"); goto done; diff --git a/drivers/scsi/scsi_debug.c b/drivers/scsi/scsi_debug.c index 8c58128ad32a..9c0af50501f9 100644 --- a/drivers/scsi/scsi_debug.c +++ b/drivers/scsi/scsi_debug.c @@ -841,11 +841,6 @@ static int sdeb_zbc_nr_conv = DEF_ZBC_NR_CONV_ZONES; static int submit_queues = DEF_SUBMIT_QUEUES; /* > 1 for multi-queue (mq) */ static int poll_queues; /* iouring iopoll interface.*/ -static DEFINE_RWLOCK(atomic_rw); -static DEFINE_RWLOCK(atomic_rw2); - -static rwlock_t *ramdisk_lck_a[2]; - static char sdebug_proc_name[] = MY_NAME; static const char *my_name = MY_NAME; @@ -6818,9 +6813,6 @@ static int __init scsi_debug_init(void) int k, ret, hosts_to_add; int idx = -1; - ramdisk_lck_a[0] = &atomic_rw; - ramdisk_lck_a[1] = &atomic_rw2; - if (sdebug_ndelay >= 1000 * 1000 * 1000) { pr_warn("ndelay must be less than 1 second, ignored\n"); sdebug_ndelay = 0; diff --git a/drivers/scsi/sd_zbc.c b/drivers/scsi/sd_zbc.c index abbd08933ac7..a25215507668 100644 --- a/drivers/scsi/sd_zbc.c +++ b/drivers/scsi/sd_zbc.c @@ -831,7 +831,6 @@ int sd_zbc_revalidate_zones(struct scsi_disk *sdkp) struct request_queue *q = disk->queue; u32 zone_blocks = sdkp->early_zone_info.zone_blocks; unsigned int nr_zones = sdkp->early_zone_info.nr_zones; - u32 max_append; int ret = 0; unsigned int flags; @@ -876,6 +875,11 @@ int sd_zbc_revalidate_zones(struct scsi_disk *sdkp) goto unlock; } + blk_queue_chunk_sectors(q, + logical_to_sectors(sdkp->device, zone_blocks)); + blk_queue_max_zone_append_sectors(q, + q->limits.max_segments << PAGE_SECTORS_SHIFT); + ret = blk_revalidate_disk_zones(disk, sd_zbc_revalidate_zones_cb); memalloc_noio_restore(flags); @@ -888,12 +892,6 @@ int sd_zbc_revalidate_zones(struct scsi_disk *sdkp) goto unlock; } - max_append = min_t(u32, logical_to_sectors(sdkp->device, zone_blocks), - q->limits.max_segments << PAGE_SECTORS_SHIFT); - max_append = min_t(u32, max_append, queue_max_hw_sectors(q)); - - blk_queue_max_zone_append_sectors(q, max_append); - sd_zbc_print_zones(sdkp); unlock: diff --git a/drivers/scsi/storvsc_drv.c b/drivers/scsi/storvsc_drv.c index 659196a2f63a..7f12d931fe7c 100644 --- a/drivers/scsi/storvsc_drv.c +++ b/drivers/scsi/storvsc_drv.c @@ -318,6 +318,7 @@ enum storvsc_request_type { #define SRB_STATUS_INVALID_REQUEST 0x06 #define SRB_STATUS_DATA_OVERRUN 0x12 #define SRB_STATUS_INVALID_LUN 0x20 +#define SRB_STATUS_INTERNAL_ERROR 0x30 #define SRB_STATUS(status) \ (status & ~(SRB_STATUS_AUTOSENSE_VALID | SRB_STATUS_QUEUE_FROZEN)) @@ -978,6 +979,7 @@ static void storvsc_handle_error(struct vmscsi_request *vm_srb, case SRB_STATUS_ERROR: case SRB_STATUS_ABORTED: case SRB_STATUS_INVALID_REQUEST: + case SRB_STATUS_INTERNAL_ERROR: if (vm_srb->srb_status & SRB_STATUS_AUTOSENSE_VALID) { /* Check for capacity change */ if ((asc == 0x2a) && (ascq == 0x9)) { diff --git a/drivers/spi/spi-bcm63xx.c b/drivers/spi/spi-bcm63xx.c index 9aecb77c3d89..07b5b71b2352 100644 --- a/drivers/spi/spi-bcm63xx.c +++ b/drivers/spi/spi-bcm63xx.c @@ -126,7 +126,7 @@ enum bcm63xx_regs_spi { SPI_MSG_DATA_SIZE, }; -#define BCM63XX_SPI_MAX_PREPEND 15 +#define BCM63XX_SPI_MAX_PREPEND 7 #define BCM63XX_SPI_MAX_CS 8 #define BCM63XX_SPI_BUS_NUM 0 diff --git a/drivers/spi/spi-s3c64xx.c b/drivers/spi/spi-s3c64xx.c index fd55697144cc..b6c2659a66ca 100644 --- a/drivers/spi/spi-s3c64xx.c +++ b/drivers/spi/spi-s3c64xx.c @@ -684,6 +684,8 @@ static int s3c64xx_spi_config(struct s3c64xx_spi_driver_data *sdd) if ((sdd->cur_mode & SPI_LOOP) && sdd->port_conf->has_loopback) val |= S3C64XX_SPI_MODE_SELF_LOOPBACK; + else + val &= ~S3C64XX_SPI_MODE_SELF_LOOPBACK; writel(val, regs + S3C64XX_SPI_MODE_CFG); diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c index 983fae84d9e8..129446775796 100644 --- a/drivers/ufs/core/ufshcd.c +++ b/drivers/ufs/core/ufshcd.c @@ -8520,6 +8520,41 @@ out: return ret; } +static void ufshcd_set_timestamp_attr(struct ufs_hba *hba) +{ + int err; + struct ufs_query_req *request = NULL; + struct ufs_query_res *response = NULL; + struct ufs_dev_info *dev_info = &hba->dev_info; + struct utp_upiu_query_v4_0 *upiu_data; + + if (dev_info->wspecversion < 0x400) + return; + + ufshcd_hold(hba); + + mutex_lock(&hba->dev_cmd.lock); + + ufshcd_init_query(hba, &request, &response, + UPIU_QUERY_OPCODE_WRITE_ATTR, + QUERY_ATTR_IDN_TIMESTAMP, 0, 0); + + request->query_func = UPIU_QUERY_FUNC_STANDARD_WRITE_REQUEST; + + upiu_data = (struct utp_upiu_query_v4_0 *)&request->upiu_req; + + put_unaligned_be64(ktime_get_real_ns(), &upiu_data->osf3); + + err = ufshcd_exec_dev_cmd(hba, DEV_CMD_TYPE_QUERY, QUERY_REQ_TIMEOUT); + + if (err) + dev_err(hba->dev, "%s: failed to set timestamp %d\n", + __func__, err); + + mutex_unlock(&hba->dev_cmd.lock); + ufshcd_release(hba); +} + /** * ufshcd_add_lus - probe and add UFS logical units * @hba: per-adapter instance @@ -8708,6 +8743,8 @@ static int ufshcd_device_init(struct ufs_hba *hba, bool init_dev_params) ufshcd_set_ufs_dev_active(hba); ufshcd_force_reset_auto_bkops(hba); + ufshcd_set_timestamp_attr(hba); + /* Gear up to HS gear if supported */ if (hba->max_pwr_info.is_valid) { /* @@ -9749,6 +9786,7 @@ static int __ufshcd_wl_resume(struct ufs_hba *hba, enum ufs_pm_op pm_op) ret = ufshcd_set_dev_pwr_mode(hba, UFS_ACTIVE_PWR_MODE); if (ret) goto set_old_link_state; + ufshcd_set_timestamp_attr(hba); } if (ufshcd_keep_autobkops_enabled_except_suspend(hba)) diff --git a/drivers/ufs/host/Kconfig b/drivers/ufs/host/Kconfig index 16624ba08050..580c8d0bd8bb 100644 --- a/drivers/ufs/host/Kconfig +++ b/drivers/ufs/host/Kconfig @@ -72,6 +72,7 @@ config SCSI_UFS_QCOM config SCSI_UFS_MEDIATEK tristate "Mediatek specific hooks to UFS controller platform driver" depends on SCSI_UFSHCD_PLATFORM && ARCH_MEDIATEK + depends on RESET_CONTROLLER select PHY_MTK_UFS select RESET_TI_SYSCON help diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c index 48ae509f2ac2..23726152d62d 100644 --- a/fs/btrfs/block-group.c +++ b/fs/btrfs/block-group.c @@ -1640,13 +1640,14 @@ void btrfs_mark_bg_unused(struct btrfs_block_group *bg) { struct btrfs_fs_info *fs_info = bg->fs_info; - trace_btrfs_add_unused_block_group(bg); spin_lock(&fs_info->unused_bgs_lock); if (list_empty(&bg->bg_list)) { btrfs_get_block_group(bg); + trace_btrfs_add_unused_block_group(bg); list_add_tail(&bg->bg_list, &fs_info->unused_bgs); - } else { + } else if (!test_bit(BLOCK_GROUP_FLAG_NEW, &bg->runtime_flags)) { /* Pull out the block group from the reclaim_bgs list. */ + trace_btrfs_add_unused_block_group(bg); list_move_tail(&bg->bg_list, &fs_info->unused_bgs); } spin_unlock(&fs_info->unused_bgs_lock); @@ -2087,6 +2088,7 @@ static int exclude_super_stripes(struct btrfs_block_group *cache) /* Shouldn't have super stripes in sequential zones */ if (zoned && nr) { + kfree(logical); btrfs_err(fs_info, "zoned: block group %llu must not contain super block", cache->start); @@ -2668,6 +2670,7 @@ void btrfs_create_pending_block_groups(struct btrfs_trans_handle *trans) next: btrfs_delayed_refs_rsv_release(fs_info, 1); list_del_init(&block_group->bg_list); + clear_bit(BLOCK_GROUP_FLAG_NEW, &block_group->runtime_flags); } btrfs_trans_release_chunk_metadata(trans); } @@ -2707,6 +2710,13 @@ struct btrfs_block_group *btrfs_make_block_group(struct btrfs_trans_handle *tran if (!cache) return ERR_PTR(-ENOMEM); + /* + * Mark it as new before adding it to the rbtree of block groups or any + * list, so that no other task finds it and calls btrfs_mark_bg_unused() + * before the new flag is set. + */ + set_bit(BLOCK_GROUP_FLAG_NEW, &cache->runtime_flags); + cache->length = size; set_free_space_tree_thresholds(cache); cache->flags = type; diff --git a/fs/btrfs/block-group.h b/fs/btrfs/block-group.h index f204addc3fe8..381c54a56417 100644 --- a/fs/btrfs/block-group.h +++ b/fs/btrfs/block-group.h @@ -70,6 +70,11 @@ enum btrfs_block_group_flags { BLOCK_GROUP_FLAG_NEEDS_FREE_SPACE, /* Indicate that the block group is placed on a sequential zone */ BLOCK_GROUP_FLAG_SEQUENTIAL_ZONE, + /* + * Indicate that block group is in the list of new block groups of a + * transaction. + */ + BLOCK_GROUP_FLAG_NEW, }; enum btrfs_caching_type { diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c index dbbb67293e34..49cef61f6a39 100644 --- a/fs/btrfs/inode.c +++ b/fs/btrfs/inode.c @@ -3482,15 +3482,21 @@ zeroit: void btrfs_add_delayed_iput(struct btrfs_inode *inode) { struct btrfs_fs_info *fs_info = inode->root->fs_info; + unsigned long flags; if (atomic_add_unless(&inode->vfs_inode.i_count, -1, 1)) return; atomic_inc(&fs_info->nr_delayed_iputs); - spin_lock(&fs_info->delayed_iput_lock); + /* + * Need to be irq safe here because we can be called from either an irq + * context (see bio.c and btrfs_put_ordered_extent()) or a non-irq + * context. + */ + spin_lock_irqsave(&fs_info->delayed_iput_lock, flags); ASSERT(list_empty(&inode->delayed_iput)); list_add_tail(&inode->delayed_iput, &fs_info->delayed_iputs); - spin_unlock(&fs_info->delayed_iput_lock); + spin_unlock_irqrestore(&fs_info->delayed_iput_lock, flags); if (!test_bit(BTRFS_FS_CLEANER_RUNNING, &fs_info->flags)) wake_up_process(fs_info->cleaner_kthread); } @@ -3499,37 +3505,46 @@ static void run_delayed_iput_locked(struct btrfs_fs_info *fs_info, struct btrfs_inode *inode) { list_del_init(&inode->delayed_iput); - spin_unlock(&fs_info->delayed_iput_lock); + spin_unlock_irq(&fs_info->delayed_iput_lock); iput(&inode->vfs_inode); if (atomic_dec_and_test(&fs_info->nr_delayed_iputs)) wake_up(&fs_info->delayed_iputs_wait); - spin_lock(&fs_info->delayed_iput_lock); + spin_lock_irq(&fs_info->delayed_iput_lock); } static void btrfs_run_delayed_iput(struct btrfs_fs_info *fs_info, struct btrfs_inode *inode) { if (!list_empty(&inode->delayed_iput)) { - spin_lock(&fs_info->delayed_iput_lock); + spin_lock_irq(&fs_info->delayed_iput_lock); if (!list_empty(&inode->delayed_iput)) run_delayed_iput_locked(fs_info, inode); - spin_unlock(&fs_info->delayed_iput_lock); + spin_unlock_irq(&fs_info->delayed_iput_lock); } } void btrfs_run_delayed_iputs(struct btrfs_fs_info *fs_info) { - - spin_lock(&fs_info->delayed_iput_lock); + /* + * btrfs_put_ordered_extent() can run in irq context (see bio.c), which + * calls btrfs_add_delayed_iput() and that needs to lock + * fs_info->delayed_iput_lock. So we need to disable irqs here to + * prevent a deadlock. + */ + spin_lock_irq(&fs_info->delayed_iput_lock); while (!list_empty(&fs_info->delayed_iputs)) { struct btrfs_inode *inode; inode = list_first_entry(&fs_info->delayed_iputs, struct btrfs_inode, delayed_iput); run_delayed_iput_locked(fs_info, inode); - cond_resched_lock(&fs_info->delayed_iput_lock); + if (need_resched()) { + spin_unlock_irq(&fs_info->delayed_iput_lock); + cond_resched(); + spin_lock_irq(&fs_info->delayed_iput_lock); + } } - spin_unlock(&fs_info->delayed_iput_lock); + spin_unlock_irq(&fs_info->delayed_iput_lock); } /* @@ -3659,11 +3674,14 @@ int btrfs_orphan_cleanup(struct btrfs_root *root) found_key.type = BTRFS_INODE_ITEM_KEY; found_key.offset = 0; inode = btrfs_iget(fs_info->sb, last_objectid, root); - ret = PTR_ERR_OR_ZERO(inode); - if (ret && ret != -ENOENT) - goto out; + if (IS_ERR(inode)) { + ret = PTR_ERR(inode); + inode = NULL; + if (ret != -ENOENT) + goto out; + } - if (ret == -ENOENT && root == fs_info->tree_root) { + if (!inode && root == fs_info->tree_root) { struct btrfs_root *dead_root; int is_dead_root = 0; @@ -3724,17 +3742,17 @@ int btrfs_orphan_cleanup(struct btrfs_root *root) * deleted but wasn't. The inode number may have been reused, * but either way, we can delete the orphan item. */ - if (ret == -ENOENT || inode->i_nlink) { - if (!ret) { + if (!inode || inode->i_nlink) { + if (inode) { ret = btrfs_drop_verity_items(BTRFS_I(inode)); iput(inode); + inode = NULL; if (ret) goto out; } trans = btrfs_start_transaction(root, 1); if (IS_ERR(trans)) { ret = PTR_ERR(trans); - iput(inode); goto out; } btrfs_debug(fs_info, "auto deleting %Lu", @@ -3742,10 +3760,8 @@ int btrfs_orphan_cleanup(struct btrfs_root *root) ret = btrfs_del_orphan_item(trans, root, found_key.objectid); btrfs_end_transaction(trans); - if (ret) { - iput(inode); + if (ret) goto out; - } continue; } @@ -4847,9 +4863,6 @@ again: ret = -ENOMEM; goto out; } - ret = set_page_extent_mapped(page); - if (ret < 0) - goto out_unlock; if (!PageUptodate(page)) { ret = btrfs_read_folio(NULL, page_folio(page)); @@ -4864,6 +4877,17 @@ again: goto out_unlock; } } + + /* + * We unlock the page after the io is completed and then re-lock it + * above. release_folio() could have come in between that and cleared + * PagePrivate(), but left the page in the mapping. Set the page mapped + * here to make sure it's properly set for the subpage stuff. + */ + ret = set_page_extent_mapped(page); + if (ret < 0) + goto out_unlock; + wait_on_page_writeback(page); lock_extent(io_tree, block_start, block_end, &cached_state); @@ -7849,8 +7873,11 @@ static void btrfs_dio_submit_io(const struct iomap_iter *iter, struct bio *bio, ret = btrfs_extract_ordered_extent(bbio, dio_data->ordered); if (ret) { - bbio->bio.bi_status = errno_to_blk_status(ret); - btrfs_dio_end_io(bbio); + btrfs_finish_ordered_extent(dio_data->ordered, NULL, + file_offset, dip->bytes, + !ret); + bio->bi_status = errno_to_blk_status(ret); + iomap_dio_bio_end_io(bio); return; } } diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c index da1f84a0eb29..2637d6b157ff 100644 --- a/fs/btrfs/qgroup.c +++ b/fs/btrfs/qgroup.c @@ -4445,4 +4445,5 @@ void btrfs_qgroup_destroy_extent_records(struct btrfs_transaction *trans) ulist_free(entry->old_roots); kfree(entry); } + *root = RB_ROOT; } diff --git a/fs/btrfs/raid56.c b/fs/btrfs/raid56.c index f37b925d587f..0249ea52bb80 100644 --- a/fs/btrfs/raid56.c +++ b/fs/btrfs/raid56.c @@ -71,7 +71,7 @@ static void rmw_rbio_work_locked(struct work_struct *work); static void index_rbio_pages(struct btrfs_raid_bio *rbio); static int alloc_rbio_pages(struct btrfs_raid_bio *rbio); -static int finish_parity_scrub(struct btrfs_raid_bio *rbio, int need_check); +static int finish_parity_scrub(struct btrfs_raid_bio *rbio); static void scrub_rbio_work_locked(struct work_struct *work); static void free_raid_bio_pointers(struct btrfs_raid_bio *rbio) @@ -2404,7 +2404,7 @@ static int alloc_rbio_essential_pages(struct btrfs_raid_bio *rbio) return 0; } -static int finish_parity_scrub(struct btrfs_raid_bio *rbio, int need_check) +static int finish_parity_scrub(struct btrfs_raid_bio *rbio) { struct btrfs_io_context *bioc = rbio->bioc; const u32 sectorsize = bioc->fs_info->sectorsize; @@ -2445,9 +2445,6 @@ static int finish_parity_scrub(struct btrfs_raid_bio *rbio, int need_check) */ clear_bit(RBIO_CACHE_READY_BIT, &rbio->flags); - if (!need_check) - goto writeback; - p_sector.page = alloc_page(GFP_NOFS); if (!p_sector.page) return -ENOMEM; @@ -2516,7 +2513,6 @@ static int finish_parity_scrub(struct btrfs_raid_bio *rbio, int need_check) q_sector.page = NULL; } -writeback: /* * time to start writing. Make bios for everything from the * higher layers (the bio_list in our rbio) and our p/q. Ignore @@ -2699,7 +2695,6 @@ static int scrub_assemble_read_bios(struct btrfs_raid_bio *rbio) static void scrub_rbio(struct btrfs_raid_bio *rbio) { - bool need_check = false; int sector_nr; int ret; @@ -2722,7 +2717,7 @@ static void scrub_rbio(struct btrfs_raid_bio *rbio) * We have every sector properly prepared. Can finish the scrub * and writeback the good content. */ - ret = finish_parity_scrub(rbio, need_check); + ret = finish_parity_scrub(rbio); wait_event(rbio->io_wait, atomic_read(&rbio->stripes_pending) == 0); for (sector_nr = 0; sector_nr < rbio->stripe_nsectors; sector_nr++) { int found_errors; diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c index 73f9ea7672db..2ecb76cf3d91 100644 --- a/fs/btrfs/volumes.c +++ b/fs/btrfs/volumes.c @@ -4078,14 +4078,6 @@ static int alloc_profile_is_valid(u64 flags, int extended) return has_single_bit_set(flags); } -static inline int balance_need_close(struct btrfs_fs_info *fs_info) -{ - /* cancel requested || normal exit path */ - return atomic_read(&fs_info->balance_cancel_req) || - (atomic_read(&fs_info->balance_pause_req) == 0 && - atomic_read(&fs_info->balance_cancel_req) == 0); -} - /* * Validate target profile against allowed profiles and return true if it's OK. * Otherwise print the error message and return false. @@ -4275,6 +4267,7 @@ int btrfs_balance(struct btrfs_fs_info *fs_info, u64 num_devices; unsigned seq; bool reducing_redundancy; + bool paused = false; int i; if (btrfs_fs_closing(fs_info) || @@ -4405,6 +4398,7 @@ int btrfs_balance(struct btrfs_fs_info *fs_info, if (ret == -ECANCELED && atomic_read(&fs_info->balance_pause_req)) { btrfs_info(fs_info, "balance: paused"); btrfs_exclop_balance(fs_info, BTRFS_EXCLOP_BALANCE_PAUSED); + paused = true; } /* * Balance can be canceled by: @@ -4433,8 +4427,8 @@ int btrfs_balance(struct btrfs_fs_info *fs_info, btrfs_update_ioctl_balance_args(fs_info, bargs); } - if ((ret && ret != -ECANCELED && ret != -ENOSPC) || - balance_need_close(fs_info)) { + /* We didn't pause, we can clean everything up. */ + if (!paused) { reset_balance_state(fs_info); btrfs_exclop_finish(fs_info); } @@ -6404,7 +6398,8 @@ int btrfs_map_block(struct btrfs_fs_info *fs_info, enum btrfs_map_op op, (op == BTRFS_MAP_READ || !dev_replace_is_ongoing || !dev_replace->tgtdev)) { set_io_stripe(smap, map, stripe_index, stripe_offset, stripe_nr); - *mirror_num_ret = mirror_num; + if (mirror_num_ret) + *mirror_num_ret = mirror_num; *bioc_ret = NULL; ret = 0; goto out; diff --git a/fs/erofs/decompressor.c b/fs/erofs/decompressor.c index 2a29943fa5cc..cfad1eac7fd9 100644 --- a/fs/erofs/decompressor.c +++ b/fs/erofs/decompressor.c @@ -148,7 +148,7 @@ static void *z_erofs_lz4_handle_overlap(struct z_erofs_lz4_decompress_ctx *ctx, *maptype = 0; return inpage; } - kunmap_atomic(inpage); + kunmap_local(inpage); might_sleep(); src = erofs_vm_map_ram(rq->in, ctx->inpages); if (!src) @@ -162,7 +162,7 @@ docopy: src = erofs_get_pcpubuf(ctx->inpages); if (!src) { DBG_BUGON(1); - kunmap_atomic(inpage); + kunmap_local(inpage); return ERR_PTR(-EFAULT); } @@ -173,9 +173,9 @@ docopy: min_t(unsigned int, total, PAGE_SIZE - *inputmargin); if (!inpage) - inpage = kmap_atomic(*in); + inpage = kmap_local_page(*in); memcpy(tmp, inpage + *inputmargin, page_copycnt); - kunmap_atomic(inpage); + kunmap_local(inpage); inpage = NULL; tmp += page_copycnt; total -= page_copycnt; @@ -214,7 +214,7 @@ static int z_erofs_lz4_decompress_mem(struct z_erofs_lz4_decompress_ctx *ctx, int ret, maptype; DBG_BUGON(*rq->in == NULL); - headpage = kmap_atomic(*rq->in); + headpage = kmap_local_page(*rq->in); /* LZ4 decompression inplace is only safe if zero_padding is enabled */ if (erofs_sb_has_zero_padding(EROFS_SB(rq->sb))) { @@ -223,7 +223,7 @@ static int z_erofs_lz4_decompress_mem(struct z_erofs_lz4_decompress_ctx *ctx, min_t(unsigned int, rq->inputsize, rq->sb->s_blocksize - rq->pageofs_in)); if (ret) { - kunmap_atomic(headpage); + kunmap_local(headpage); return ret; } may_inplace = !((rq->pageofs_in + rq->inputsize) & @@ -261,7 +261,7 @@ static int z_erofs_lz4_decompress_mem(struct z_erofs_lz4_decompress_ctx *ctx, } if (maptype == 0) { - kunmap_atomic(headpage); + kunmap_local(headpage); } else if (maptype == 1) { vm_unmap_ram(src, ctx->inpages); } else if (maptype == 2) { @@ -289,7 +289,7 @@ static int z_erofs_lz4_decompress(struct z_erofs_decompress_req *rq, /* one optimized fast path only for non bigpcluster cases yet */ if (ctx.inpages == 1 && ctx.outpages == 1 && !rq->inplace_io) { DBG_BUGON(!*rq->out); - dst = kmap_atomic(*rq->out); + dst = kmap_local_page(*rq->out); dst_maptype = 0; goto dstmap_out; } @@ -311,7 +311,7 @@ static int z_erofs_lz4_decompress(struct z_erofs_decompress_req *rq, dstmap_out: ret = z_erofs_lz4_decompress_mem(&ctx, dst + rq->pageofs_out); if (!dst_maptype) - kunmap_atomic(dst); + kunmap_local(dst); else if (dst_maptype == 2) vm_unmap_ram(dst, ctx.outpages); return ret; @@ -328,7 +328,7 @@ static int z_erofs_transform_plain(struct z_erofs_decompress_req *rq, const unsigned int lefthalf = rq->outputsize - righthalf; const unsigned int interlaced_offset = rq->alg == Z_EROFS_COMPRESSION_SHIFTED ? 0 : rq->pageofs_out; - unsigned char *src, *dst; + u8 *src; if (outpages > 2 && rq->alg == Z_EROFS_COMPRESSION_SHIFTED) { DBG_BUGON(1); @@ -341,22 +341,19 @@ static int z_erofs_transform_plain(struct z_erofs_decompress_req *rq, } src = kmap_local_page(rq->in[inpages - 1]) + rq->pageofs_in; - if (rq->out[0]) { - dst = kmap_local_page(rq->out[0]); - memcpy(dst + rq->pageofs_out, src + interlaced_offset, - righthalf); - kunmap_local(dst); - } + if (rq->out[0]) + memcpy_to_page(rq->out[0], rq->pageofs_out, + src + interlaced_offset, righthalf); if (outpages > inpages) { DBG_BUGON(!rq->out[outpages - 1]); if (rq->out[outpages - 1] != rq->in[inpages - 1]) { - dst = kmap_local_page(rq->out[outpages - 1]); - memcpy(dst, interlaced_offset ? src : - (src + righthalf), lefthalf); - kunmap_local(dst); + memcpy_to_page(rq->out[outpages - 1], 0, src + + (interlaced_offset ? 0 : righthalf), + lefthalf); } else if (!interlaced_offset) { memmove(src, src + righthalf, lefthalf); + flush_dcache_page(rq->in[inpages - 1]); } } kunmap_local(src); diff --git a/fs/erofs/inode.c b/fs/erofs/inode.c index d70b12b81507..e12592727a54 100644 --- a/fs/erofs/inode.c +++ b/fs/erofs/inode.c @@ -183,7 +183,8 @@ static void *erofs_read_inode(struct erofs_buf *buf, inode->i_flags &= ~S_DAX; if (test_opt(&sbi->opt, DAX_ALWAYS) && S_ISREG(inode->i_mode) && - vi->datalayout == EROFS_INODE_FLAT_PLAIN) + (vi->datalayout == EROFS_INODE_FLAT_PLAIN || + vi->datalayout == EROFS_INODE_CHUNK_BASED)) inode->i_flags |= S_DAX; if (!nblks) diff --git a/fs/erofs/zdata.c b/fs/erofs/zdata.c index 5f1890e309c6..b69d89a11dd0 100644 --- a/fs/erofs/zdata.c +++ b/fs/erofs/zdata.c @@ -1035,7 +1035,7 @@ hitted: */ tight &= (fe->mode > Z_EROFS_PCLUSTER_FOLLOWED_NOINPLACE); - cur = end - min_t(unsigned int, offset + end - map->m_la, end); + cur = end - min_t(erofs_off_t, offset + end - map->m_la, end); if (!(map->m_flags & EROFS_MAP_MAPPED)) { zero_user_segment(page, cur, end); goto next_part; @@ -1841,7 +1841,7 @@ static void z_erofs_pcluster_readmore(struct z_erofs_decompress_frontend *f, } cur = map->m_la + map->m_llen - 1; - while (cur >= end) { + while ((cur >= end) && (cur < i_size_read(inode))) { pgoff_t index = cur >> PAGE_SHIFT; struct page *page; diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index 35bc174f9ba2..f67bef9d83c4 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -258,7 +258,7 @@ static int fuse_dentry_revalidate(struct dentry *entry, unsigned int flags) spin_unlock(&fi->lock); } kfree(forget); - if (ret == -ENOMEM) + if (ret == -ENOMEM || ret == -EINTR) goto out; if (ret || fuse_invalid_attr(&outarg.attr) || fuse_stale_inode(inode, outarg.generation, &outarg.attr)) @@ -395,8 +395,6 @@ int fuse_lookup_name(struct super_block *sb, u64 nodeid, const struct qstr *name goto out_put_forget; err = -EIO; - if (!outarg->nodeid) - goto out_put_forget; if (fuse_invalid_attr(&outarg->attr)) goto out_put_forget; diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index d66070af145d..f19d748890f0 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -1134,7 +1134,10 @@ static void process_init_reply(struct fuse_mount *fm, struct fuse_args *args, process_init_limits(fc, arg); if (arg->minor >= 6) { - u64 flags = arg->flags | (u64) arg->flags2 << 32; + u64 flags = arg->flags; + + if (flags & FUSE_INIT_EXT) + flags |= (u64) arg->flags2 << 32; ra_pages = arg->max_readahead / PAGE_SIZE; if (flags & FUSE_ASYNC_READ) @@ -1254,7 +1257,8 @@ void fuse_send_init(struct fuse_mount *fm) FUSE_ABORT_ERROR | FUSE_MAX_PAGES | FUSE_CACHE_SYMLINKS | FUSE_NO_OPENDIR_SUPPORT | FUSE_EXPLICIT_INVAL_DATA | FUSE_HANDLE_KILLPRIV_V2 | FUSE_SETXATTR_EXT | FUSE_INIT_EXT | - FUSE_SECURITY_CTX | FUSE_CREATE_SUPP_GROUP; + FUSE_SECURITY_CTX | FUSE_CREATE_SUPP_GROUP | + FUSE_HAS_EXPIRE_ONLY; #ifdef CONFIG_FUSE_DAX if (fm->fc->dax) flags |= FUSE_MAP_ALIGNMENT; diff --git a/fs/fuse/ioctl.c b/fs/fuse/ioctl.c index 8e01bfdfc430..726640fa439e 100644 --- a/fs/fuse/ioctl.c +++ b/fs/fuse/ioctl.c @@ -9,14 +9,23 @@ #include <linux/compat.h> #include <linux/fileattr.h> -static ssize_t fuse_send_ioctl(struct fuse_mount *fm, struct fuse_args *args) +static ssize_t fuse_send_ioctl(struct fuse_mount *fm, struct fuse_args *args, + struct fuse_ioctl_out *outarg) { - ssize_t ret = fuse_simple_request(fm, args); + ssize_t ret; + + args->out_args[0].size = sizeof(*outarg); + args->out_args[0].value = outarg; + + ret = fuse_simple_request(fm, args); /* Translate ENOSYS, which shouldn't be returned from fs */ if (ret == -ENOSYS) ret = -ENOTTY; + if (ret >= 0 && outarg->result == -ENOSYS) + outarg->result = -ENOTTY; + return ret; } @@ -264,13 +273,11 @@ long fuse_do_ioctl(struct file *file, unsigned int cmd, unsigned long arg, } ap.args.out_numargs = 2; - ap.args.out_args[0].size = sizeof(outarg); - ap.args.out_args[0].value = &outarg; ap.args.out_args[1].size = out_size; ap.args.out_pages = true; ap.args.out_argvar = true; - transferred = fuse_send_ioctl(fm, &ap.args); + transferred = fuse_send_ioctl(fm, &ap.args, &outarg); err = transferred; if (transferred < 0) goto out; @@ -399,12 +406,10 @@ static int fuse_priv_ioctl(struct inode *inode, struct fuse_file *ff, args.in_args[1].size = inarg.in_size; args.in_args[1].value = ptr; args.out_numargs = 2; - args.out_args[0].size = sizeof(outarg); - args.out_args[0].value = &outarg; args.out_args[1].size = inarg.out_size; args.out_args[1].value = ptr; - err = fuse_send_ioctl(fm, &args); + err = fuse_send_ioctl(fm, &args, &outarg); if (!err) { if (outarg.result < 0) err = outarg.result; diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c index adb92cdb24b0..aa8967cca1a3 100644 --- a/fs/iomap/buffered-io.c +++ b/fs/iomap/buffered-io.c @@ -872,10 +872,10 @@ iomap_file_buffered_write(struct kiocb *iocb, struct iov_iter *i, while ((ret = iomap_iter(&iter, ops)) > 0) iter.processed = iomap_write_iter(&iter, i); - if (unlikely(ret < 0)) + if (unlikely(iter.pos == iocb->ki_pos)) return ret; ret = iter.pos - iocb->ki_pos; - iocb->ki_pos += ret; + iocb->ki_pos = iter.pos; return ret; } EXPORT_SYMBOL_GPL(iomap_file_buffered_write); diff --git a/fs/smb/client/cifsglob.h b/fs/smb/client/cifsglob.h index b5808fe3469a..e5eec6d38d02 100644 --- a/fs/smb/client/cifsglob.h +++ b/fs/smb/client/cifsglob.h @@ -532,7 +532,7 @@ struct smb_version_operations { /* Check for STATUS_IO_TIMEOUT */ bool (*is_status_io_timeout)(char *buf); /* Check for STATUS_NETWORK_NAME_DELETED */ - void (*is_network_name_deleted)(char *buf, struct TCP_Server_Info *srv); + bool (*is_network_name_deleted)(char *buf, struct TCP_Server_Info *srv); }; struct smb_version_values { diff --git a/fs/smb/client/cifssmb.c b/fs/smb/client/cifssmb.c index 19f7385abeec..9dee267f1893 100644 --- a/fs/smb/client/cifssmb.c +++ b/fs/smb/client/cifssmb.c @@ -3184,7 +3184,7 @@ setAclRetry: param_offset = offsetof(struct smb_com_transaction2_spi_req, InformationLevel) - 4; offset = param_offset + params; - parm_data = ((char *) &pSMB->hdr.Protocol) + offset; + parm_data = ((char *)pSMB) + sizeof(pSMB->hdr.smb_buf_length) + offset; pSMB->ParameterOffset = cpu_to_le16(param_offset); /* convert to on the wire format for POSIX ACL */ diff --git a/fs/smb/client/connect.c b/fs/smb/client/connect.c index 85dd1b373974..9280e253bf09 100644 --- a/fs/smb/client/connect.c +++ b/fs/smb/client/connect.c @@ -60,7 +60,7 @@ extern bool disable_legacy_dialects; #define TLINK_IDLE_EXPIRE (600 * HZ) /* Drop the connection to not overload the server */ -#define NUM_STATUS_IO_TIMEOUT 5 +#define MAX_STATUS_IO_TIMEOUT 5 static int ip_connect(struct TCP_Server_Info *server); static int generic_ip_connect(struct TCP_Server_Info *server); @@ -1117,6 +1117,7 @@ cifs_demultiplex_thread(void *p) struct mid_q_entry *mids[MAX_COMPOUND]; char *bufs[MAX_COMPOUND]; unsigned int noreclaim_flag, num_io_timeout = 0; + bool pending_reconnect = false; noreclaim_flag = memalloc_noreclaim_save(); cifs_dbg(FYI, "Demultiplex PID: %d\n", task_pid_nr(current)); @@ -1156,6 +1157,8 @@ cifs_demultiplex_thread(void *p) cifs_dbg(FYI, "RFC1002 header 0x%x\n", pdu_length); if (!is_smb_response(server, buf[0])) continue; + + pending_reconnect = false; next_pdu: server->pdu_size = pdu_length; @@ -1213,10 +1216,13 @@ next_pdu: if (server->ops->is_status_io_timeout && server->ops->is_status_io_timeout(buf)) { num_io_timeout++; - if (num_io_timeout > NUM_STATUS_IO_TIMEOUT) { - cifs_reconnect(server, false); + if (num_io_timeout > MAX_STATUS_IO_TIMEOUT) { + cifs_server_dbg(VFS, + "Number of request timeouts exceeded %d. Reconnecting", + MAX_STATUS_IO_TIMEOUT); + + pending_reconnect = true; num_io_timeout = 0; - continue; } } @@ -1226,9 +1232,14 @@ next_pdu: if (mids[i] != NULL) { mids[i]->resp_buf_size = server->pdu_size; - if (bufs[i] && server->ops->is_network_name_deleted) - server->ops->is_network_name_deleted(bufs[i], - server); + if (bufs[i] != NULL) { + if (server->ops->is_network_name_deleted && + server->ops->is_network_name_deleted(bufs[i], + server)) { + cifs_server_dbg(FYI, + "Share deleted. Reconnect needed"); + } + } if (!mids[i]->multiRsp || mids[i]->multiEnd) mids[i]->callback(mids[i]); @@ -1263,6 +1274,11 @@ next_pdu: buf = server->smallbuf; goto next_pdu; } + + /* do this reconnect at the very end after processing all MIDs */ + if (pending_reconnect) + cifs_reconnect(server, true); + } /* end while !EXITING */ /* buffer usually freed in free_mid - need to free it here on exit */ diff --git a/fs/smb/client/dfs.c b/fs/smb/client/dfs.c index 1403a2d1ab17..df3fd3b720da 100644 --- a/fs/smb/client/dfs.c +++ b/fs/smb/client/dfs.c @@ -66,6 +66,12 @@ static int get_session(struct cifs_mount_ctx *mnt_ctx, const char *full_path) return rc; } +/* + * Track individual DFS referral servers used by new DFS mount. + * + * On success, their lifetime will be shared by final tcon (dfs_ses_list). + * Otherwise, they will be put by dfs_put_root_smb_sessions() in cifs_mount(). + */ static int add_root_smb_session(struct cifs_mount_ctx *mnt_ctx) { struct smb3_fs_context *ctx = mnt_ctx->fs_ctx; @@ -80,11 +86,12 @@ static int add_root_smb_session(struct cifs_mount_ctx *mnt_ctx) INIT_LIST_HEAD(&root_ses->list); spin_lock(&cifs_tcp_ses_lock); - ses->ses_count++; + cifs_smb_ses_inc_refcount(ses); spin_unlock(&cifs_tcp_ses_lock); root_ses->ses = ses; list_add_tail(&root_ses->list, &mnt_ctx->dfs_ses_list); } + /* Select new DFS referral server so that new referrals go through it */ ctx->dfs_root_ses = ses; return 0; } @@ -242,7 +249,6 @@ out: int dfs_mount_share(struct cifs_mount_ctx *mnt_ctx, bool *isdfs) { struct smb3_fs_context *ctx = mnt_ctx->fs_ctx; - struct cifs_ses *ses; bool nodfs = ctx->nodfs; int rc; @@ -276,20 +282,8 @@ int dfs_mount_share(struct cifs_mount_ctx *mnt_ctx, bool *isdfs) } *isdfs = true; - /* - * Prevent DFS root session of being put in the first call to - * cifs_mount_put_conns(). If another DFS root server was not found - * while chasing the referrals (@ctx->dfs_root_ses == @ses), then we - * can safely put extra refcount of @ses. - */ - ses = mnt_ctx->ses; - mnt_ctx->ses = NULL; - mnt_ctx->server = NULL; - rc = __dfs_mount_share(mnt_ctx); - if (ses == ctx->dfs_root_ses) - cifs_put_smb_ses(ses); - - return rc; + add_root_smb_session(mnt_ctx); + return __dfs_mount_share(mnt_ctx); } /* Update dfs referral path of superblock */ diff --git a/fs/smb/client/file.c b/fs/smb/client/file.c index 879bc8e6555c..fc5acc95cd13 100644 --- a/fs/smb/client/file.c +++ b/fs/smb/client/file.c @@ -1080,8 +1080,8 @@ int cifs_close(struct inode *inode, struct file *file) cfile = file->private_data; file->private_data = NULL; dclose = kmalloc(sizeof(struct cifs_deferred_close), GFP_KERNEL); - if ((cinode->oplock == CIFS_CACHE_RHW_FLG) && - cinode->lease_granted && + if ((cifs_sb->ctx->closetimeo && cinode->oplock == CIFS_CACHE_RHW_FLG) + && cinode->lease_granted && !test_bit(CIFS_INO_CLOSE_ON_LOCK, &cinode->flags) && dclose) { if (test_and_clear_bit(CIFS_INO_MODIFIED_ATTR, &cinode->flags)) { diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c index 87abce010974..0f62bc373ad0 100644 --- a/fs/smb/client/smb2ops.c +++ b/fs/smb/client/smb2ops.c @@ -2395,7 +2395,7 @@ smb2_is_status_io_timeout(char *buf) return false; } -static void +static bool smb2_is_network_name_deleted(char *buf, struct TCP_Server_Info *server) { struct smb2_hdr *shdr = (struct smb2_hdr *)buf; @@ -2404,7 +2404,7 @@ smb2_is_network_name_deleted(char *buf, struct TCP_Server_Info *server) struct cifs_tcon *tcon; if (shdr->Status != STATUS_NETWORK_NAME_DELETED) - return; + return false; /* If server is a channel, select the primary channel */ pserver = CIFS_SERVER_IS_CHAN(server) ? server->primary_server : server; @@ -2419,11 +2419,13 @@ smb2_is_network_name_deleted(char *buf, struct TCP_Server_Info *server) spin_unlock(&cifs_tcp_ses_lock); pr_warn_once("Server share %s deleted.\n", tcon->tree_name); - return; + return true; } } } spin_unlock(&cifs_tcp_ses_lock); + + return false; } static int diff --git a/fs/smb/client/smb2transport.c b/fs/smb/client/smb2transport.c index c6db898dab7c..7676091b3e77 100644 --- a/fs/smb/client/smb2transport.c +++ b/fs/smb/client/smb2transport.c @@ -160,7 +160,7 @@ smb2_find_smb_ses_unlocked(struct TCP_Server_Info *server, __u64 ses_id) spin_unlock(&ses->ses_lock); continue; } - ++ses->ses_count; + cifs_smb_ses_inc_refcount(ses); spin_unlock(&ses->ses_lock); return ses; } diff --git a/fs/xfs/libxfs/xfs_da_format.h b/fs/xfs/libxfs/xfs_da_format.h index 25e2841084e1..f9015f88eca7 100644 --- a/fs/xfs/libxfs/xfs_da_format.h +++ b/fs/xfs/libxfs/xfs_da_format.h @@ -591,7 +591,7 @@ struct xfs_attr_shortform { uint8_t valuelen; /* actual length of value (no NULL) */ uint8_t flags; /* flags bits (see xfs_attr_leaf.h) */ uint8_t nameval[]; /* name & value bytes concatenated */ - } list[1]; /* variable sized array */ + } list[]; /* variable sized array */ }; typedef struct xfs_attr_leaf_map { /* RLE map of free bytes */ @@ -620,19 +620,29 @@ typedef struct xfs_attr_leaf_entry { /* sorted on key, not name */ typedef struct xfs_attr_leaf_name_local { __be16 valuelen; /* number of bytes in value */ __u8 namelen; /* length of name bytes */ - __u8 nameval[1]; /* name/value bytes */ + /* + * In Linux 6.5 this flex array was converted from nameval[1] to + * nameval[]. Be very careful here about extra padding at the end; + * see xfs_attr_leaf_entsize_local() for details. + */ + __u8 nameval[]; /* name/value bytes */ } xfs_attr_leaf_name_local_t; typedef struct xfs_attr_leaf_name_remote { __be32 valueblk; /* block number of value bytes */ __be32 valuelen; /* number of bytes in value */ __u8 namelen; /* length of name bytes */ - __u8 name[1]; /* name bytes */ + /* + * In Linux 6.5 this flex array was converted from name[1] to name[]. + * Be very careful here about extra padding at the end; see + * xfs_attr_leaf_entsize_remote() for details. + */ + __u8 name[]; /* name bytes */ } xfs_attr_leaf_name_remote_t; typedef struct xfs_attr_leafblock { xfs_attr_leaf_hdr_t hdr; /* constant-structure header block */ - xfs_attr_leaf_entry_t entries[1]; /* sorted on key, not name */ + xfs_attr_leaf_entry_t entries[]; /* sorted on key, not name */ /* * The rest of the block contains the following structures after the * leaf entries, growing from the bottom up. The variables are never @@ -664,7 +674,7 @@ struct xfs_attr3_leaf_hdr { struct xfs_attr3_leafblock { struct xfs_attr3_leaf_hdr hdr; - struct xfs_attr_leaf_entry entries[1]; + struct xfs_attr_leaf_entry entries[]; /* * The rest of the block contains the following structures after the @@ -747,14 +757,61 @@ xfs_attr3_leaf_name_local(xfs_attr_leafblock_t *leafp, int idx) */ static inline int xfs_attr_leaf_entsize_remote(int nlen) { - return round_up(sizeof(struct xfs_attr_leaf_name_remote) - 1 + - nlen, XFS_ATTR_LEAF_NAME_ALIGN); + /* + * Prior to Linux 6.5, struct xfs_attr_leaf_name_remote ended with + * name[1], which was used as a flexarray. The layout of this struct + * is 9 bytes of fixed-length fields followed by a __u8 flex array at + * offset 9. + * + * On most architectures, struct xfs_attr_leaf_name_remote had two + * bytes of implicit padding at the end of the struct to make the + * struct length 12. After converting name[1] to name[], there are + * three implicit padding bytes and the struct size remains 12. + * However, there are compiler configurations that do not add implicit + * padding at all (m68k) and have been broken for years. + * + * This entsize computation historically added (the xattr name length) + * to (the padded struct length - 1) and rounded that sum up to the + * nearest multiple of 4 (NAME_ALIGN). IOWs, round_up(11 + nlen, 4). + * This is encoded in the ondisk format, so we cannot change this. + * + * Compute the entsize from offsetof of the flexarray and manually + * adding bytes for the implicit padding. + */ + const size_t remotesize = + offsetof(struct xfs_attr_leaf_name_remote, name) + 2; + + return round_up(remotesize + nlen, XFS_ATTR_LEAF_NAME_ALIGN); } static inline int xfs_attr_leaf_entsize_local(int nlen, int vlen) { - return round_up(sizeof(struct xfs_attr_leaf_name_local) - 1 + - nlen + vlen, XFS_ATTR_LEAF_NAME_ALIGN); + /* + * Prior to Linux 6.5, struct xfs_attr_leaf_name_local ended with + * nameval[1], which was used as a flexarray. The layout of this + * struct is 3 bytes of fixed-length fields followed by a __u8 flex + * array at offset 3. + * + * struct xfs_attr_leaf_name_local had zero bytes of implicit padding + * at the end of the struct to make the struct length 4. On most + * architectures, after converting nameval[1] to nameval[], there is + * one implicit padding byte and the struct size remains 4. However, + * there are compiler configurations that do not add implicit padding + * at all (m68k) and would break. + * + * This entsize computation historically added (the xattr name and + * value length) to (the padded struct length - 1) and rounded that sum + * up to the nearest multiple of 4 (NAME_ALIGN). IOWs, the formula is + * round_up(3 + nlen + vlen, 4). This is encoded in the ondisk format, + * so we cannot change this. + * + * Compute the entsize from offsetof of the flexarray and manually + * adding bytes for the implicit padding. + */ + const size_t localsize = + offsetof(struct xfs_attr_leaf_name_local, nameval); + + return round_up(localsize + nlen + vlen, XFS_ATTR_LEAF_NAME_ALIGN); } static inline int xfs_attr_leaf_entsize_local_max(int bsize) diff --git a/fs/xfs/libxfs/xfs_fs.h b/fs/xfs/libxfs/xfs_fs.h index 9c60ebb328b4..2cbf9ea39b8c 100644 --- a/fs/xfs/libxfs/xfs_fs.h +++ b/fs/xfs/libxfs/xfs_fs.h @@ -592,12 +592,12 @@ typedef struct xfs_attrlist_cursor { struct xfs_attrlist { __s32 al_count; /* number of entries in attrlist */ __s32 al_more; /* T/F: more attrs (do call again) */ - __s32 al_offset[1]; /* byte offsets of attrs [var-sized] */ + __s32 al_offset[]; /* byte offsets of attrs [var-sized] */ }; struct xfs_attrlist_ent { /* data from attr_list() */ __u32 a_valuelen; /* number bytes in value of attr */ - char a_name[1]; /* attr name (NULL terminated) */ + char a_name[]; /* attr name (NULL terminated) */ }; typedef struct xfs_fsop_attrlist_handlereq { diff --git a/fs/xfs/xfs_ondisk.h b/fs/xfs/xfs_ondisk.h index 9737b5a9f405..c4cc99b70dd3 100644 --- a/fs/xfs/xfs_ondisk.h +++ b/fs/xfs/xfs_ondisk.h @@ -56,7 +56,7 @@ xfs_check_ondisk_structs(void) /* dir/attr trees */ XFS_CHECK_STRUCT_SIZE(struct xfs_attr3_leaf_hdr, 80); - XFS_CHECK_STRUCT_SIZE(struct xfs_attr3_leafblock, 88); + XFS_CHECK_STRUCT_SIZE(struct xfs_attr3_leafblock, 80); XFS_CHECK_STRUCT_SIZE(struct xfs_attr3_rmt_hdr, 56); XFS_CHECK_STRUCT_SIZE(struct xfs_da3_blkinfo, 56); XFS_CHECK_STRUCT_SIZE(struct xfs_da3_intnode, 64); @@ -88,7 +88,8 @@ xfs_check_ondisk_structs(void) XFS_CHECK_OFFSET(xfs_attr_leaf_name_remote_t, valuelen, 4); XFS_CHECK_OFFSET(xfs_attr_leaf_name_remote_t, namelen, 8); XFS_CHECK_OFFSET(xfs_attr_leaf_name_remote_t, name, 9); - XFS_CHECK_STRUCT_SIZE(xfs_attr_leafblock_t, 40); + XFS_CHECK_STRUCT_SIZE(xfs_attr_leafblock_t, 32); + XFS_CHECK_STRUCT_SIZE(struct xfs_attr_shortform, 4); XFS_CHECK_OFFSET(struct xfs_attr_shortform, hdr.totsize, 0); XFS_CHECK_OFFSET(struct xfs_attr_shortform, hdr.count, 2); XFS_CHECK_OFFSET(struct xfs_attr_shortform, list[0].namelen, 4); diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index 0587354ba678..9c59409104f6 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -578,7 +578,6 @@ *(.text.unlikely .text.unlikely.*) \ *(.text.unknown .text.unknown.*) \ NOINSTR_TEXT \ - *(.text..refcount) \ *(.ref.text) \ *(.text.asan.* .text.tsan.*) \ MEM_KEEP(init.text*) \ diff --git a/include/drm/gpu_scheduler.h b/include/drm/gpu_scheduler.h index e95b4837e5a3..f9544d9b670d 100644 --- a/include/drm/gpu_scheduler.h +++ b/include/drm/gpu_scheduler.h @@ -583,15 +583,14 @@ void drm_sched_entity_set_priority(struct drm_sched_entity *entity, bool drm_sched_entity_is_ready(struct drm_sched_entity *entity); int drm_sched_entity_error(struct drm_sched_entity *entity); -void drm_sched_fence_set_parent(struct drm_sched_fence *s_fence, - struct dma_fence *fence); struct drm_sched_fence *drm_sched_fence_alloc( struct drm_sched_entity *s_entity, void *owner); void drm_sched_fence_init(struct drm_sched_fence *fence, struct drm_sched_entity *entity); void drm_sched_fence_free(struct drm_sched_fence *fence); -void drm_sched_fence_scheduled(struct drm_sched_fence *fence); +void drm_sched_fence_scheduled(struct drm_sched_fence *fence, + struct dma_fence *parent); void drm_sched_fence_finished(struct drm_sched_fence *fence, int result); unsigned long drm_sched_suspend_timeout(struct drm_gpu_scheduler *sched); diff --git a/include/linux/blk-crypto-profile.h b/include/linux/blk-crypto-profile.h index e6802b69cdd6..90ab33cb5d0e 100644 --- a/include/linux/blk-crypto-profile.h +++ b/include/linux/blk-crypto-profile.h @@ -111,6 +111,7 @@ struct blk_crypto_profile { * keyslots while ensuring that they can't be changed concurrently. */ struct rw_semaphore lock; + struct lock_class_key lockdep_key; /* List of idle slots, with least recently used slot at front */ wait_queue_head_t idle_slots_wait_queue; diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h index 2b7fb8e87793..b96e00499f9e 100644 --- a/include/linux/blk-mq.h +++ b/include/linux/blk-mq.h @@ -158,13 +158,13 @@ struct request { /* * The rb_node is only used inside the io scheduler, requests - * are pruned when moved to the dispatch queue. So let the - * completion_data share space with the rb_node. + * are pruned when moved to the dispatch queue. special_vec must + * only be used if RQF_SPECIAL_PAYLOAD is set, and those cannot be + * insert into an IO scheduler. */ union { struct rb_node rb_node; /* sort/lookup */ struct bio_vec special_vec; - void *completion_data; }; /* diff --git a/include/linux/dma-fence.h b/include/linux/dma-fence.h index d54b595a0fe0..0d678e9a7b24 100644 --- a/include/linux/dma-fence.h +++ b/include/linux/dma-fence.h @@ -606,7 +606,7 @@ static inline signed long dma_fence_wait(struct dma_fence *fence, bool intr) void dma_fence_set_deadline(struct dma_fence *fence, ktime_t deadline); struct dma_fence *dma_fence_get_stub(void); -struct dma_fence *dma_fence_allocate_private_stub(void); +struct dma_fence *dma_fence_allocate_private_stub(ktime_t timestamp); u64 dma_fence_context_alloc(unsigned num); extern const struct dma_fence_ops dma_fence_array_ops; diff --git a/include/linux/nvme.h b/include/linux/nvme.h index 182b6d614eb1..26dd3f859d9d 100644 --- a/include/linux/nvme.h +++ b/include/linux/nvme.h @@ -473,7 +473,7 @@ struct nvme_id_ns_nvm { }; enum { - NVME_ID_NS_NVM_STS_MASK = 0x3f, + NVME_ID_NS_NVM_STS_MASK = 0x7f, NVME_ID_NS_NVM_GUARD_SHIFT = 7, NVME_ID_NS_NVM_GUARD_MASK = 0x3, }; diff --git a/include/linux/psi.h b/include/linux/psi.h index ab26200c2803..e0745873e3f2 100644 --- a/include/linux/psi.h +++ b/include/linux/psi.h @@ -23,8 +23,9 @@ void psi_memstall_enter(unsigned long *flags); void psi_memstall_leave(unsigned long *flags); int psi_show(struct seq_file *s, struct psi_group *group, enum psi_res res); -struct psi_trigger *psi_trigger_create(struct psi_group *group, - char *buf, enum psi_res res, struct file *file); +struct psi_trigger *psi_trigger_create(struct psi_group *group, char *buf, + enum psi_res res, struct file *file, + struct kernfs_open_file *of); void psi_trigger_destroy(struct psi_trigger *t); __poll_t psi_trigger_poll(void **trigger_ptr, struct file *file, diff --git a/include/linux/psi_types.h b/include/linux/psi_types.h index 040c089581c6..f1fd3a8044e0 100644 --- a/include/linux/psi_types.h +++ b/include/linux/psi_types.h @@ -137,6 +137,9 @@ struct psi_trigger { /* Wait queue for polling */ wait_queue_head_t event_wait; + /* Kernfs file for cgroup triggers */ + struct kernfs_open_file *of; + /* Pending event flag */ int event; diff --git a/include/linux/tcp.h b/include/linux/tcp.h index fbcb0ce13171..d16abdb3541a 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -515,7 +515,7 @@ static inline void fastopen_queue_tune(struct sock *sk, int backlog) struct request_sock_queue *queue = &inet_csk(sk)->icsk_accept_queue; int somaxconn = READ_ONCE(sock_net(sk)->core.sysctl_somaxconn); - queue->fastopenq.max_qlen = min_t(unsigned int, backlog, somaxconn); + WRITE_ONCE(queue->fastopenq.max_qlen, min_t(unsigned int, backlog, somaxconn)); } static inline void tcp_move_syn(struct tcp_sock *tp, diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 9654567cfae3..e01d52cb668c 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -593,9 +593,7 @@ struct hci_dev { const char *fw_info; struct dentry *debugfs; -#ifdef CONFIG_DEV_COREDUMP struct hci_devcoredump dump; -#endif struct device dev; @@ -822,6 +820,7 @@ struct hci_conn_params { struct hci_conn *conn; bool explicit_connect; + /* Accessed without hdev->lock: */ hci_conn_flags_t flags; u8 privacy_mode; }; @@ -1573,7 +1572,11 @@ struct hci_conn_params *hci_conn_params_add(struct hci_dev *hdev, bdaddr_t *addr, u8 addr_type); void hci_conn_params_del(struct hci_dev *hdev, bdaddr_t *addr, u8 addr_type); void hci_conn_params_clear_disabled(struct hci_dev *hdev); +void hci_conn_params_free(struct hci_conn_params *param); +void hci_pend_le_list_del_init(struct hci_conn_params *param); +void hci_pend_le_list_add(struct hci_conn_params *param, + struct list_head *list); struct hci_conn_params *hci_pend_le_action_lookup(struct list_head *list, bdaddr_t *addr, u8 addr_type); diff --git a/include/net/bonding.h b/include/net/bonding.h index b57bec6e737e..30ac427cf0c6 100644 --- a/include/net/bonding.h +++ b/include/net/bonding.h @@ -277,7 +277,7 @@ struct bond_vlan_tag { unsigned short vlan_id; }; -/** +/* * Returns NULL if the net_device does not belong to any of the bond's slaves * * Caller must hold bond lock for read diff --git a/include/net/cfg802154.h b/include/net/cfg802154.h index e00057984489..f79ce133e51a 100644 --- a/include/net/cfg802154.h +++ b/include/net/cfg802154.h @@ -170,7 +170,8 @@ wpan_phy_cca_cmp(const struct wpan_phy_cca *a, const struct wpan_phy_cca *b) } /** - * @WPAN_PHY_FLAG_TRANSMIT_POWER: Indicates that transceiver will support + * enum wpan_phy_flags - WPAN PHY state flags + * @WPAN_PHY_FLAG_TXPOWER: Indicates that transceiver will support * transmit power setting. * @WPAN_PHY_FLAG_CCA_ED_LEVEL: Indicates that transceiver will support cca ed * level setting. diff --git a/include/net/codel.h b/include/net/codel.h index 5fed2f16cb8d..aa80f744826c 100644 --- a/include/net/codel.h +++ b/include/net/codel.h @@ -145,8 +145,8 @@ struct codel_vars { * @maxpacket: largest packet we've seen so far * @drop_count: temp count of dropped packets in dequeue() * @drop_len: bytes of dropped packets in dequeue() - * ecn_mark: number of packets we ECN marked instead of dropping - * ce_mark: number of packets CE marked because sojourn time was above ce_threshold + * @ecn_mark: number of packets we ECN marked instead of dropping + * @ce_mark: number of packets CE marked because sojourn time was above ce_threshold */ struct codel_stats { u32 maxpacket; diff --git a/include/net/devlink.h b/include/net/devlink.h index 9a3c51aa6e81..0cdb4b16e5b5 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -221,7 +221,7 @@ struct devlink_dpipe_field { /** * struct devlink_dpipe_header - dpipe header object * @name: header name - * @id: index, global/local detrmined by global bit + * @id: index, global/local determined by global bit * @fields: fields * @fields_count: number of fields * @global: indicates if header is shared like most protocol header @@ -241,7 +241,7 @@ struct devlink_dpipe_header { * @header_index: header index (packets can have several headers of same * type like in case of tunnels) * @header: header - * @fieled_id: field index + * @field_id: field index */ struct devlink_dpipe_match { enum devlink_dpipe_match_type type; @@ -256,7 +256,7 @@ struct devlink_dpipe_match { * @header_index: header index (packets can have several headers of same * type like in case of tunnels) * @header: header - * @fieled_id: field index + * @field_id: field index */ struct devlink_dpipe_action { enum devlink_dpipe_action_type type; @@ -292,7 +292,7 @@ struct devlink_dpipe_value { * struct devlink_dpipe_entry - table entry object * @index: index of the entry in the table * @match_values: match values - * @matche_values_count: count of matches tuples + * @match_values_count: count of matches tuples * @action_values: actions values * @action_values_count: count of actions values * @counter: value of counter @@ -342,7 +342,9 @@ struct devlink_dpipe_table_ops; */ struct devlink_dpipe_table { void *priv; + /* private: */ struct list_head list; + /* public: */ const char *name; bool counters_enabled; bool counter_control_extern; @@ -355,13 +357,13 @@ struct devlink_dpipe_table { /** * struct devlink_dpipe_table_ops - dpipe_table ops - * @actions_dump - dumps all tables actions - * @matches_dump - dumps all tables matches - * @entries_dump - dumps all active entries in the table - * @counters_set_update - when changing the counter status hardware sync + * @actions_dump: dumps all tables actions + * @matches_dump: dumps all tables matches + * @entries_dump: dumps all active entries in the table + * @counters_set_update: when changing the counter status hardware sync * maybe needed to allocate/free counter related * resources - * @size_get - get size + * @size_get: get size */ struct devlink_dpipe_table_ops { int (*actions_dump)(void *priv, struct sk_buff *skb); @@ -374,8 +376,8 @@ struct devlink_dpipe_table_ops { /** * struct devlink_dpipe_headers - dpipe headers - * @headers - header array can be shared (global bit) or driver specific - * @headers_count - count of headers + * @headers: header array can be shared (global bit) or driver specific + * @headers_count: count of headers */ struct devlink_dpipe_headers { struct devlink_dpipe_header **headers; @@ -387,7 +389,7 @@ struct devlink_dpipe_headers { * @size_min: minimum size which can be set * @size_max: maximum size which can be set * @size_granularity: size granularity - * @size_unit: resource's basic unit + * @unit: resource's basic unit */ struct devlink_resource_size_params { u64 size_min; @@ -457,6 +459,7 @@ struct devlink_flash_notify { /** * struct devlink_param - devlink configuration parameter data + * @id: devlink parameter id number * @name: name of the parameter * @generic: indicates if the parameter is generic or driver specific * @type: parameter type @@ -632,6 +635,7 @@ enum devlink_param_generic_id { * struct devlink_flash_update_params - Flash Update parameters * @fw: pointer to the firmware data to update from * @component: the flash component to update + * @overwrite_mask: which types of flash update are supported (may be %0) * * With the exception of fw, drivers must opt-in to parameters by * setting the appropriate bit in the supported_flash_update_params field in diff --git a/include/net/inet_frag.h b/include/net/inet_frag.h index 325ad893f624..153960663ce4 100644 --- a/include/net/inet_frag.h +++ b/include/net/inet_frag.h @@ -29,7 +29,7 @@ struct fqdir { }; /** - * fragment queue flags + * enum: fragment queue flags * * @INET_FRAG_FIRST_IN: first fragment has arrived * @INET_FRAG_LAST_IN: final fragment has arrived diff --git a/include/net/llc_conn.h b/include/net/llc_conn.h index 2c1ea3414640..374411b3066c 100644 --- a/include/net/llc_conn.h +++ b/include/net/llc_conn.h @@ -111,7 +111,7 @@ void llc_conn_resend_i_pdu_as_cmd(struct sock *sk, u8 nr, u8 first_p_bit); void llc_conn_resend_i_pdu_as_rsp(struct sock *sk, u8 nr, u8 first_f_bit); int llc_conn_remove_acked_pdus(struct sock *conn, u8 nr, u16 *how_many_unacked); struct sock *llc_lookup_established(struct llc_sap *sap, struct llc_addr *daddr, - struct llc_addr *laddr); + struct llc_addr *laddr, const struct net *net); void llc_sap_add_socket(struct llc_sap *sap, struct sock *sk); void llc_sap_remove_socket(struct llc_sap *sap, struct sock *sk); diff --git a/include/net/llc_pdu.h b/include/net/llc_pdu.h index 49aa79c7b278..7e73f8e5e497 100644 --- a/include/net/llc_pdu.h +++ b/include/net/llc_pdu.h @@ -269,7 +269,7 @@ static inline void llc_pdu_decode_sa(struct sk_buff *skb, u8 *sa) /** * llc_pdu_decode_da - extracts dest address of input frame * @skb: input skb that destination address must be extracted from it - * @sa: pointer to destination address (6 byte array). + * @da: pointer to destination address (6 byte array). * * This function extracts destination address(MAC) of input frame. */ @@ -321,7 +321,7 @@ static inline void llc_pdu_init_as_ui_cmd(struct sk_buff *skb) /** * llc_pdu_init_as_test_cmd - sets PDU as TEST - * @skb - Address of the skb to build + * @skb: Address of the skb to build * * Sets a PDU as TEST */ @@ -369,6 +369,8 @@ struct llc_xid_info { /** * llc_pdu_init_as_xid_cmd - sets bytes 3, 4 & 5 of LLC header as XID * @skb: input skb that header must be set into it. + * @svcs_supported: The class of the LLC (I or II) + * @rx_window: The size of the receive window of the LLC * * This function sets third,fourth,fifth and sixth bytes of LLC header as * a XID PDU. diff --git a/include/net/nsh.h b/include/net/nsh.h index 350b1ad11c7f..16a751093896 100644 --- a/include/net/nsh.h +++ b/include/net/nsh.h @@ -192,7 +192,7 @@ /** * struct nsh_md1_ctx - Keeps track of NSH context data - * @nshc<1-4>: NSH Contexts. + * @context: NSH Contexts. */ struct nsh_md1_ctx { __be32 context[4]; diff --git a/include/net/pie.h b/include/net/pie.h index 3fe2361e03b4..01cbc66825a4 100644 --- a/include/net/pie.h +++ b/include/net/pie.h @@ -17,7 +17,7 @@ /** * struct pie_params - contains pie parameters * @target: target delay in pschedtime - * @tudpate: interval at which drop probability is calculated + * @tupdate: interval at which drop probability is calculated * @limit: total number of packets that can be in the queue * @alpha: parameter to control drop probability * @beta: parameter to control drop probability diff --git a/include/net/rsi_91x.h b/include/net/rsi_91x.h index 040f07b47f1f..b2283762e446 100644 --- a/include/net/rsi_91x.h +++ b/include/net/rsi_91x.h @@ -1,4 +1,4 @@ -/** +/* * Copyright (c) 2017 Redpine Signals Inc. * * Permission to use, copy, modify, and/or distribute this software for any diff --git a/include/net/tcp.h b/include/net/tcp.h index c5fb90079920..d17cb8ab4c48 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1523,25 +1523,38 @@ void tcp_leave_memory_pressure(struct sock *sk); static inline int keepalive_intvl_when(const struct tcp_sock *tp) { struct net *net = sock_net((struct sock *)tp); + int val; - return tp->keepalive_intvl ? : - READ_ONCE(net->ipv4.sysctl_tcp_keepalive_intvl); + /* Paired with WRITE_ONCE() in tcp_sock_set_keepintvl() + * and do_tcp_setsockopt(). + */ + val = READ_ONCE(tp->keepalive_intvl); + + return val ? : READ_ONCE(net->ipv4.sysctl_tcp_keepalive_intvl); } static inline int keepalive_time_when(const struct tcp_sock *tp) { struct net *net = sock_net((struct sock *)tp); + int val; - return tp->keepalive_time ? : - READ_ONCE(net->ipv4.sysctl_tcp_keepalive_time); + /* Paired with WRITE_ONCE() in tcp_sock_set_keepidle_locked() */ + val = READ_ONCE(tp->keepalive_time); + + return val ? : READ_ONCE(net->ipv4.sysctl_tcp_keepalive_time); } static inline int keepalive_probes(const struct tcp_sock *tp) { struct net *net = sock_net((struct sock *)tp); + int val; - return tp->keepalive_probes ? : - READ_ONCE(net->ipv4.sysctl_tcp_keepalive_probes); + /* Paired with WRITE_ONCE() in tcp_sock_set_keepcnt() + * and do_tcp_setsockopt(). + */ + val = READ_ONCE(tp->keepalive_probes); + + return val ? : READ_ONCE(net->ipv4.sysctl_tcp_keepalive_probes); } static inline u32 keepalive_time_elapsed(const struct tcp_sock *tp) @@ -2062,7 +2075,11 @@ void __tcp_v4_send_check(struct sk_buff *skb, __be32 saddr, __be32 daddr); static inline u32 tcp_notsent_lowat(const struct tcp_sock *tp) { struct net *net = sock_net((struct sock *)tp); - return tp->notsent_lowat ?: READ_ONCE(net->ipv4.sysctl_tcp_notsent_lowat); + u32 val; + + val = READ_ONCE(tp->notsent_lowat); + + return val ?: READ_ONCE(net->ipv4.sysctl_tcp_notsent_lowat); } bool tcp_stream_memory_free(const struct sock *sk, int wake); diff --git a/include/uapi/linux/fuse.h b/include/uapi/linux/fuse.h index 1b9d0dfae72d..b3fcab13fcd3 100644 --- a/include/uapi/linux/fuse.h +++ b/include/uapi/linux/fuse.h @@ -206,6 +206,7 @@ * - add extension header * - add FUSE_EXT_GROUPS * - add FUSE_CREATE_SUPP_GROUP + * - add FUSE_HAS_EXPIRE_ONLY */ #ifndef _LINUX_FUSE_H @@ -369,6 +370,7 @@ struct fuse_file_lock { * FUSE_HAS_INODE_DAX: use per inode DAX * FUSE_CREATE_SUPP_GROUP: add supplementary group info to create, mkdir, * symlink and mknod (single group that matches parent) + * FUSE_HAS_EXPIRE_ONLY: kernel supports expiry-only entry invalidation */ #define FUSE_ASYNC_READ (1 << 0) #define FUSE_POSIX_LOCKS (1 << 1) @@ -406,6 +408,7 @@ struct fuse_file_lock { #define FUSE_SECURITY_CTX (1ULL << 32) #define FUSE_HAS_INODE_DAX (1ULL << 33) #define FUSE_CREATE_SUPP_GROUP (1ULL << 34) +#define FUSE_HAS_EXPIRE_ONLY (1ULL << 35) /** * CUSE INIT request/reply flags diff --git a/include/uapi/scsi/scsi_bsg_ufs.h b/include/uapi/scsi/scsi_bsg_ufs.h index 2801b65299aa..fd3f9e5ee241 100644 --- a/include/uapi/scsi/scsi_bsg_ufs.h +++ b/include/uapi/scsi/scsi_bsg_ufs.h @@ -71,6 +71,31 @@ struct utp_upiu_query { }; /** + * struct utp_upiu_query_v4_0 - upiu request buffer structure for + * query request >= UFS 4.0 spec. + * @opcode: command to perform B-0 + * @idn: a value that indicates the particular type of data B-1 + * @index: Index to further identify data B-2 + * @selector: Index to further identify data B-3 + * @osf4: spec field B-5 + * @osf5: spec field B 6,7 + * @osf6: spec field DW 8,9 + * @osf7: spec field DW 10,11 + */ +struct utp_upiu_query_v4_0 { + __u8 opcode; + __u8 idn; + __u8 index; + __u8 selector; + __u8 osf3; + __u8 osf4; + __be16 osf5; + __be32 osf6; + __be32 osf7; + __be32 reserved; +}; + +/** * struct utp_upiu_cmd - Command UPIU structure * @data_transfer_len: Data Transfer Length DW-3 * @cdb: Command Descriptor Block CDB DW-4 to DW-7 diff --git a/include/ufs/ufs.h b/include/ufs/ufs.h index 4e8d6240e589..198cb391f9db 100644 --- a/include/ufs/ufs.h +++ b/include/ufs/ufs.h @@ -170,6 +170,7 @@ enum attr_idn { QUERY_ATTR_IDN_WB_BUFF_LIFE_TIME_EST = 0x1E, QUERY_ATTR_IDN_CURR_WB_BUFF_SIZE = 0x1F, QUERY_ATTR_IDN_EXT_IID_EN = 0x2A, + QUERY_ATTR_IDN_TIMESTAMP = 0x30 }; /* Descriptor idn for Query requests */ diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c index e8096d502a7c..7505de2428e0 100644 --- a/io_uring/io_uring.c +++ b/io_uring/io_uring.c @@ -2489,6 +2489,8 @@ int io_run_task_work_sig(struct io_ring_ctx *ctx) static inline int io_cqring_wait_schedule(struct io_ring_ctx *ctx, struct io_wait_queue *iowq) { + int token, ret; + if (unlikely(READ_ONCE(ctx->check_cq))) return 1; if (unlikely(!llist_empty(&ctx->work_llist))) @@ -2499,11 +2501,20 @@ static inline int io_cqring_wait_schedule(struct io_ring_ctx *ctx, return -EINTR; if (unlikely(io_should_wake(iowq))) return 0; + + /* + * Use io_schedule_prepare/finish, so cpufreq can take into account + * that the task is waiting for IO - turns out to be important for low + * QD IO. + */ + token = io_schedule_prepare(); + ret = 0; if (iowq->timeout == KTIME_MAX) schedule(); else if (!schedule_hrtimeout(&iowq->timeout, HRTIMER_MODE_ABS)) - return -ETIME; - return 0; + ret = -ETIME; + io_schedule_finish(token); + return ret; } /* diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 803b91135ca0..71473c19093d 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -5587,16 +5587,17 @@ static int update_stack_depth(struct bpf_verifier_env *env, * Since recursion is prevented by check_cfg() this algorithm * only needs a local stack of MAX_CALL_FRAMES to remember callsites */ -static int check_max_stack_depth(struct bpf_verifier_env *env) +static int check_max_stack_depth_subprog(struct bpf_verifier_env *env, int idx) { - int depth = 0, frame = 0, idx = 0, i = 0, subprog_end; struct bpf_subprog_info *subprog = env->subprog_info; struct bpf_insn *insn = env->prog->insnsi; + int depth = 0, frame = 0, i, subprog_end; bool tail_call_reachable = false; int ret_insn[MAX_CALL_FRAMES]; int ret_prog[MAX_CALL_FRAMES]; int j; + i = subprog[idx].start; process_func: /* protect against potential stack overflow that might happen when * bpf2bpf calls get combined with tailcalls. Limit the caller's stack @@ -5635,7 +5636,7 @@ process_func: continue_func: subprog_end = subprog[idx + 1].start; for (; i < subprog_end; i++) { - int next_insn; + int next_insn, sidx; if (!bpf_pseudo_call(insn + i) && !bpf_pseudo_func(insn + i)) continue; @@ -5645,14 +5646,14 @@ continue_func: /* find the callee */ next_insn = i + insn[i].imm + 1; - idx = find_subprog(env, next_insn); - if (idx < 0) { + sidx = find_subprog(env, next_insn); + if (sidx < 0) { WARN_ONCE(1, "verifier bug. No program starts at insn %d\n", next_insn); return -EFAULT; } - if (subprog[idx].is_async_cb) { - if (subprog[idx].has_tail_call) { + if (subprog[sidx].is_async_cb) { + if (subprog[sidx].has_tail_call) { verbose(env, "verifier bug. subprog has tail_call and async cb\n"); return -EFAULT; } @@ -5661,6 +5662,7 @@ continue_func: continue; } i = next_insn; + idx = sidx; if (subprog[idx].has_tail_call) tail_call_reachable = true; @@ -5696,6 +5698,22 @@ continue_func: goto continue_func; } +static int check_max_stack_depth(struct bpf_verifier_env *env) +{ + struct bpf_subprog_info *si = env->subprog_info; + int ret; + + for (int i = 0; i < env->subprog_cnt; i++) { + if (!i || si[i].is_async_cb) { + ret = check_max_stack_depth_subprog(env, i); + if (ret < 0) + return ret; + } + continue; + } + return 0; +} + #ifndef CONFIG_BPF_JIT_ALWAYS_ON static int get_callee_stack_depth(struct bpf_verifier_env *env, const struct bpf_insn *insn, int idx) diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c index bfe3cd8ccf36..f55a40db065f 100644 --- a/kernel/cgroup/cgroup.c +++ b/kernel/cgroup/cgroup.c @@ -3730,7 +3730,7 @@ static ssize_t pressure_write(struct kernfs_open_file *of, char *buf, } psi = cgroup_psi(cgrp); - new = psi_trigger_create(psi, buf, res, of->file); + new = psi_trigger_create(psi, buf, res, of->file, of); if (IS_ERR(new)) { cgroup_put(cgrp); return PTR_ERR(new); diff --git a/kernel/kallsyms.c b/kernel/kallsyms.c index 7982cc9d497c..016d997131d4 100644 --- a/kernel/kallsyms.c +++ b/kernel/kallsyms.c @@ -174,11 +174,10 @@ static bool cleanup_symbol_name(char *s) * LLVM appends various suffixes for local functions and variables that * must be promoted to global scope as part of LTO. This can break * hooking of static functions with kprobes. '.' is not a valid - * character in an identifier in C. Suffixes observed: + * character in an identifier in C. Suffixes only in LLVM LTO observed: * - foo.llvm.[0-9a-f]+ - * - foo.[0-9a-f]+ */ - res = strchr(s, '.'); + res = strstr(s, ".llvm."); if (res) { *res = '\0'; return true; diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c index f62e89d0d906..e1b4bfa938dd 100644 --- a/kernel/power/hibernate.c +++ b/kernel/power/hibernate.c @@ -1179,6 +1179,7 @@ static ssize_t resume_store(struct kobject *kobj, struct kobj_attribute *attr, unsigned maj, min, offset; char *p, dummy; + error = 0; if (sscanf(name, "%u:%u%c", &maj, &min, &dummy) == 2 || sscanf(name, "%u:%u:%u:%c", &maj, &min, &offset, &dummy) == 3) { diff --git a/kernel/power/qos.c b/kernel/power/qos.c index af51ed6d45ef..782d3b41c1f3 100644 --- a/kernel/power/qos.c +++ b/kernel/power/qos.c @@ -426,6 +426,11 @@ late_initcall(cpu_latency_qos_init); /* Definitions related to the frequency QoS below. */ +static inline bool freq_qos_value_invalid(s32 value) +{ + return value < 0 && value != PM_QOS_DEFAULT_VALUE; +} + /** * freq_constraints_init - Initialize frequency QoS constraints. * @qos: Frequency QoS constraints to initialize. @@ -531,7 +536,7 @@ int freq_qos_add_request(struct freq_constraints *qos, { int ret; - if (IS_ERR_OR_NULL(qos) || !req || value < 0) + if (IS_ERR_OR_NULL(qos) || !req || freq_qos_value_invalid(value)) return -EINVAL; if (WARN(freq_qos_request_active(req), @@ -563,7 +568,7 @@ EXPORT_SYMBOL_GPL(freq_qos_add_request); */ int freq_qos_update_request(struct freq_qos_request *req, s32 new_value) { - if (!req || new_value < 0) + if (!req || freq_qos_value_invalid(new_value)) return -EINVAL; if (WARN(!freq_qos_request_active(req), diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index a80a73909dc2..b3e25be58e2b 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -7174,7 +7174,7 @@ static int select_idle_sibling(struct task_struct *p, int prev, int target) recent_used_cpu != target && cpus_share_cache(recent_used_cpu, target) && (available_idle_cpu(recent_used_cpu) || sched_idle_cpu(recent_used_cpu)) && - cpumask_test_cpu(p->recent_used_cpu, p->cpus_ptr) && + cpumask_test_cpu(recent_used_cpu, p->cpus_ptr) && asym_fits_cpu(task_util, util_min, util_max, recent_used_cpu)) { return recent_used_cpu; } diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c index 81fca77397f6..9bb3f2b3ccfc 100644 --- a/kernel/sched/psi.c +++ b/kernel/sched/psi.c @@ -493,8 +493,12 @@ static u64 update_triggers(struct psi_group *group, u64 now, bool *update_total, continue; /* Generate an event */ - if (cmpxchg(&t->event, 0, 1) == 0) - wake_up_interruptible(&t->event_wait); + if (cmpxchg(&t->event, 0, 1) == 0) { + if (t->of) + kernfs_notify(t->of->kn); + else + wake_up_interruptible(&t->event_wait); + } t->last_event_time = now; /* Reset threshold breach flag once event got generated */ t->pending_event = false; @@ -1271,8 +1275,9 @@ int psi_show(struct seq_file *m, struct psi_group *group, enum psi_res res) return 0; } -struct psi_trigger *psi_trigger_create(struct psi_group *group, - char *buf, enum psi_res res, struct file *file) +struct psi_trigger *psi_trigger_create(struct psi_group *group, char *buf, + enum psi_res res, struct file *file, + struct kernfs_open_file *of) { struct psi_trigger *t; enum psi_states state; @@ -1331,7 +1336,9 @@ struct psi_trigger *psi_trigger_create(struct psi_group *group, t->event = 0; t->last_event_time = 0; - init_waitqueue_head(&t->event_wait); + t->of = of; + if (!of) + init_waitqueue_head(&t->event_wait); t->pending_event = false; t->aggregator = privileged ? PSI_POLL : PSI_AVGS; @@ -1388,7 +1395,10 @@ void psi_trigger_destroy(struct psi_trigger *t) * being accessed later. Can happen if cgroup is deleted from under a * polling process. */ - wake_up_pollfree(&t->event_wait); + if (t->of) + kernfs_notify(t->of->kn); + else + wake_up_interruptible(&t->event_wait); if (t->aggregator == PSI_AVGS) { mutex_lock(&group->avgs_lock); @@ -1465,7 +1475,10 @@ __poll_t psi_trigger_poll(void **trigger_ptr, if (!t) return DEFAULT_POLLMASK | EPOLLERR | EPOLLPRI; - poll_wait(file, &t->event_wait, wait); + if (t->of) + kernfs_generic_poll(t->of, wait); + else + poll_wait(file, &t->event_wait, wait); if (cmpxchg(&t->event, 1, 0) == 1) ret |= EPOLLPRI; @@ -1535,7 +1548,7 @@ static ssize_t psi_write(struct file *file, const char __user *user_buf, return -EBUSY; } - new = psi_trigger_create(&psi_system, buf, res, file); + new = psi_trigger_create(&psi_system, buf, res, file, NULL); if (IS_ERR(new)) { mutex_unlock(&seq->lock); return PTR_ERR(new); diff --git a/kernel/sys.c b/kernel/sys.c index 05f838929e72..2410e3999ebe 100644 --- a/kernel/sys.c +++ b/kernel/sys.c @@ -2535,11 +2535,6 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3, else return -EINVAL; break; - case PR_GET_AUXV: - if (arg4 || arg5) - return -EINVAL; - error = prctl_get_auxv((void __user *)arg2, arg3); - break; default: return -EINVAL; } @@ -2694,6 +2689,11 @@ SYSCALL_DEFINE5(prctl, int, option, unsigned long, arg2, unsigned long, arg3, case PR_SET_VMA: error = prctl_set_vma(arg2, arg3, arg4, arg5); break; + case PR_GET_AUXV: + if (arg4 || arg5) + return -EINVAL; + error = prctl_get_auxv((void __user *)arg2, arg3); + break; #ifdef CONFIG_KSM case PR_SET_MEMORY_MERGE: if (arg3 || arg4 || arg5) diff --git a/kernel/trace/fprobe.c b/kernel/trace/fprobe.c index b70de44e6d3d..3b21f4063258 100644 --- a/kernel/trace/fprobe.c +++ b/kernel/trace/fprobe.c @@ -100,6 +100,12 @@ static void fprobe_kprobe_handler(unsigned long ip, unsigned long parent_ip, return; } + /* + * This user handler is shared with other kprobes and is not expected to be + * called recursively. So if any other kprobe handler is running, this will + * exit as kprobe does. See the section 'Share the callbacks with kprobes' + * in Documentation/trace/fprobe.rst for more information. + */ if (unlikely(kprobe_running())) { fp->nmissed++; goto recursion_unlock; diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index ed7906b13f09..e1edc2197fc8 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -113,6 +113,8 @@ enum trace_type { #define MEM_FAIL(condition, fmt, ...) \ DO_ONCE_LITE_IF(condition, pr_err, "ERROR: " fmt, ##__VA_ARGS__) +#define FAULT_STRING "(fault)" + #define HIST_STACKTRACE_DEPTH 16 #define HIST_STACKTRACE_SIZE (HIST_STACKTRACE_DEPTH * sizeof(unsigned long)) #define HIST_STACKTRACE_SKIP 5 diff --git a/kernel/trace/trace_probe.c b/kernel/trace/trace_probe.c index 7ba371da0926..b2b726bea1f9 100644 --- a/kernel/trace/trace_probe.c +++ b/kernel/trace/trace_probe.c @@ -67,7 +67,7 @@ int PRINT_TYPE_FUNC_NAME(string)(struct trace_seq *s, void *data, void *ent) int len = *(u32 *)data >> 16; if (!len) - trace_seq_puts(s, "(fault)"); + trace_seq_puts(s, FAULT_STRING); else trace_seq_printf(s, "\"%s\"", (const char *)get_loc_data(data, ent)); diff --git a/kernel/trace/trace_probe_kernel.h b/kernel/trace/trace_probe_kernel.h index c4e1d4c03a85..bb723eefd7b7 100644 --- a/kernel/trace/trace_probe_kernel.h +++ b/kernel/trace/trace_probe_kernel.h @@ -2,8 +2,6 @@ #ifndef __TRACE_PROBE_KERNEL_H_ #define __TRACE_PROBE_KERNEL_H_ -#define FAULT_STRING "(fault)" - /* * This depends on trace_probe.h, but can not include it due to * the way trace_probe_tmpl.h is used by trace_kprobe.c and trace_eprobe.c. @@ -15,16 +13,8 @@ static nokprobe_inline int fetch_store_strlen_user(unsigned long addr) { const void __user *uaddr = (__force const void __user *)addr; - int ret; - ret = strnlen_user_nofault(uaddr, MAX_STRING_SIZE); - /* - * strnlen_user_nofault returns zero on fault, insert the - * FAULT_STRING when that occurs. - */ - if (ret <= 0) - return strlen(FAULT_STRING) + 1; - return ret; + return strnlen_user_nofault(uaddr, MAX_STRING_SIZE); } /* Return the length of string -- including null terminal byte */ @@ -44,18 +34,14 @@ fetch_store_strlen(unsigned long addr) len++; } while (c && ret == 0 && len < MAX_STRING_SIZE); - /* For faults, return enough to hold the FAULT_STRING */ - return (ret < 0) ? strlen(FAULT_STRING) + 1 : len; + return (ret < 0) ? ret : len; } -static nokprobe_inline void set_data_loc(int ret, void *dest, void *__dest, void *base, int len) +static nokprobe_inline void set_data_loc(int ret, void *dest, void *__dest, void *base) { - if (ret >= 0) { - *(u32 *)dest = make_data_loc(ret, __dest - base); - } else { - strscpy(__dest, FAULT_STRING, len); - ret = strlen(__dest) + 1; - } + if (ret < 0) + ret = 0; + *(u32 *)dest = make_data_loc(ret, __dest - base); } /* @@ -76,7 +62,7 @@ fetch_store_string_user(unsigned long addr, void *dest, void *base) __dest = get_loc_data(dest, base); ret = strncpy_from_user_nofault(__dest, uaddr, maxlen); - set_data_loc(ret, dest, __dest, base, maxlen); + set_data_loc(ret, dest, __dest, base); return ret; } @@ -107,7 +93,7 @@ fetch_store_string(unsigned long addr, void *dest, void *base) * probing. */ ret = strncpy_from_kernel_nofault(__dest, (void *)addr, maxlen); - set_data_loc(ret, dest, __dest, base, maxlen); + set_data_loc(ret, dest, __dest, base); return ret; } diff --git a/kernel/trace/trace_probe_tmpl.h b/kernel/trace/trace_probe_tmpl.h index 00707630788d..3935b347f874 100644 --- a/kernel/trace/trace_probe_tmpl.h +++ b/kernel/trace/trace_probe_tmpl.h @@ -156,11 +156,11 @@ stage3: code++; goto array; case FETCH_OP_ST_USTRING: - ret += fetch_store_strlen_user(val + code->offset); + ret = fetch_store_strlen_user(val + code->offset); code++; goto array; case FETCH_OP_ST_SYMSTR: - ret += fetch_store_symstrlen(val + code->offset); + ret = fetch_store_symstrlen(val + code->offset); code++; goto array; default: @@ -204,6 +204,8 @@ stage3: array: /* the last stage: Loop on array */ if (code->op == FETCH_OP_LP_ARRAY) { + if (ret < 0) + ret = 0; total += ret; if (++i < code->param) { code = s3; @@ -265,9 +267,7 @@ store_trace_args(void *data, struct trace_probe *tp, void *rec, if (unlikely(arg->dynamic)) *dl = make_data_loc(maxlen, dyndata - base); ret = process_fetch_insn(arg->code, rec, dl, base); - if (unlikely(ret < 0 && arg->dynamic)) { - *dl = make_data_loc(0, dyndata - base); - } else { + if (arg->dynamic && likely(ret > 0)) { dyndata += ret; maxlen -= ret; } diff --git a/kernel/trace/trace_uprobe.c b/kernel/trace/trace_uprobe.c index eaa800530e92..555c223c3232 100644 --- a/kernel/trace/trace_uprobe.c +++ b/kernel/trace/trace_uprobe.c @@ -170,7 +170,8 @@ fetch_store_string(unsigned long addr, void *dest, void *base) */ ret++; *(u32 *)dest = make_data_loc(ret, (void *)dst - base); - } + } else + *(u32 *)dest = make_data_loc(0, (void *)dst - base); return ret; } diff --git a/lib/iov_iter.c b/lib/iov_iter.c index b667b1e2f688..e4dc809d1075 100644 --- a/lib/iov_iter.c +++ b/lib/iov_iter.c @@ -1349,7 +1349,7 @@ uaccess_end: return ret; } -static int copy_iovec_from_user(struct iovec *iov, +static __noclone int copy_iovec_from_user(struct iovec *iov, const struct iovec __user *uiov, unsigned long nr_segs) { int ret = -EFAULT; diff --git a/lib/maple_tree.c b/lib/maple_tree.c index bfffbb7cab26..4dd73cf936a6 100644 --- a/lib/maple_tree.c +++ b/lib/maple_tree.c @@ -3692,7 +3692,8 @@ static inline int mas_root_expand(struct ma_state *mas, void *entry) mas->offset = slot; pivots[slot] = mas->last; if (mas->last != ULONG_MAX) - slot++; + pivots[++slot] = ULONG_MAX; + mas->depth = 1; mas_set_height(mas); ma_set_meta(node, maple_leaf_64, 0, slot); diff --git a/lib/test_maple_tree.c b/lib/test_maple_tree.c index 9939be34e516..8d4c92cbdd0c 100644 --- a/lib/test_maple_tree.c +++ b/lib/test_maple_tree.c @@ -1898,13 +1898,16 @@ static noinline void __init next_prev_test(struct maple_tree *mt) 725}; static const unsigned long level2_32[] = { 1747, 2000, 1750, 1755, 1760, 1765}; + unsigned long last_index; if (MAPLE_32BIT) { nr_entries = 500; level2 = level2_32; + last_index = 0x138e; } else { nr_entries = 200; level2 = level2_64; + last_index = 0x7d6; } for (i = 0; i <= nr_entries; i++) @@ -2011,7 +2014,7 @@ static noinline void __init next_prev_test(struct maple_tree *mt) val = mas_next(&mas, ULONG_MAX); MT_BUG_ON(mt, val != NULL); - MT_BUG_ON(mt, mas.index != 0x7d6); + MT_BUG_ON(mt, mas.index != last_index); MT_BUG_ON(mt, mas.last != ULONG_MAX); val = mas_prev(&mas, 0); diff --git a/mm/mlock.c b/mm/mlock.c index d7db94519884..0a0c996c5c21 100644 --- a/mm/mlock.c +++ b/mm/mlock.c @@ -477,7 +477,6 @@ static int apply_vma_lock_flags(unsigned long start, size_t len, { unsigned long nstart, end, tmp; struct vm_area_struct *vma, *prev; - int error; VMA_ITERATOR(vmi, current->mm, start); VM_BUG_ON(offset_in_page(start)); @@ -498,6 +497,7 @@ static int apply_vma_lock_flags(unsigned long start, size_t len, nstart = start; tmp = vma->vm_start; for_each_vma_range(vmi, vma, end) { + int error; vm_flags_t newflags; if (vma->vm_start != tmp) @@ -511,14 +511,15 @@ static int apply_vma_lock_flags(unsigned long start, size_t len, tmp = end; error = mlock_fixup(&vmi, vma, &prev, nstart, tmp, newflags); if (error) - break; + return error; + tmp = vma_iter_end(&vmi); nstart = tmp; } - if (vma_iter_end(&vmi) < end) + if (tmp < end) return -ENOMEM; - return error; + return 0; } /* diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index 056f9516e46d..76222565e2df 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -118,7 +118,7 @@ static void hci_connect_le_scan_cleanup(struct hci_conn *conn, u8 status) */ params->explicit_connect = false; - list_del_init(¶ms->action); + hci_pend_le_list_del_init(params); switch (params->auto_connect) { case HCI_AUTO_CONN_EXPLICIT: @@ -127,10 +127,10 @@ static void hci_connect_le_scan_cleanup(struct hci_conn *conn, u8 status) return; case HCI_AUTO_CONN_DIRECT: case HCI_AUTO_CONN_ALWAYS: - list_add(¶ms->action, &hdev->pend_le_conns); + hci_pend_le_list_add(params, &hdev->pend_le_conns); break; case HCI_AUTO_CONN_REPORT: - list_add(¶ms->action, &hdev->pend_le_reports); + hci_pend_le_list_add(params, &hdev->pend_le_reports); break; default: break; @@ -1426,8 +1426,8 @@ static int hci_explicit_conn_params_set(struct hci_dev *hdev, if (params->auto_connect == HCI_AUTO_CONN_DISABLED || params->auto_connect == HCI_AUTO_CONN_REPORT || params->auto_connect == HCI_AUTO_CONN_EXPLICIT) { - list_del_init(¶ms->action); - list_add(¶ms->action, &hdev->pend_le_conns); + hci_pend_le_list_del_init(params); + hci_pend_le_list_add(params, &hdev->pend_le_conns); } params->explicit_connect = true; @@ -1684,7 +1684,7 @@ struct hci_conn *hci_connect_sco(struct hci_dev *hdev, int type, bdaddr_t *dst, if (!link) { hci_conn_drop(acl); hci_conn_drop(sco); - return NULL; + return ERR_PTR(-ENOLINK); } sco->setting = setting; @@ -2254,7 +2254,7 @@ struct hci_conn *hci_connect_cis(struct hci_dev *hdev, bdaddr_t *dst, if (!link) { hci_conn_drop(le); hci_conn_drop(cis); - return NULL; + return ERR_PTR(-ENOLINK); } /* If LE is already connected and CIS handle is already set proceed to diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index 48917c68358d..1ec83985f1ab 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -1972,6 +1972,7 @@ static int hci_remove_adv_monitor(struct hci_dev *hdev, struct adv_monitor *monitor) { int status = 0; + int handle; switch (hci_get_adv_monitor_offload_ext(hdev)) { case HCI_ADV_MONITOR_EXT_NONE: /* also goes here when powered off */ @@ -1980,9 +1981,10 @@ static int hci_remove_adv_monitor(struct hci_dev *hdev, goto free_monitor; case HCI_ADV_MONITOR_EXT_MSFT: + handle = monitor->handle; status = msft_remove_monitor(hdev, monitor); bt_dev_dbg(hdev, "%s remove monitor %d msft status %d", - hdev->name, monitor->handle, status); + hdev->name, handle, status); break; } @@ -2249,22 +2251,46 @@ struct hci_conn_params *hci_conn_params_lookup(struct hci_dev *hdev, return NULL; } -/* This function requires the caller holds hdev->lock */ +/* This function requires the caller holds hdev->lock or rcu_read_lock */ struct hci_conn_params *hci_pend_le_action_lookup(struct list_head *list, bdaddr_t *addr, u8 addr_type) { struct hci_conn_params *param; - list_for_each_entry(param, list, action) { + rcu_read_lock(); + + list_for_each_entry_rcu(param, list, action) { if (bacmp(¶m->addr, addr) == 0 && - param->addr_type == addr_type) + param->addr_type == addr_type) { + rcu_read_unlock(); return param; + } } + rcu_read_unlock(); + return NULL; } /* This function requires the caller holds hdev->lock */ +void hci_pend_le_list_del_init(struct hci_conn_params *param) +{ + if (list_empty(¶m->action)) + return; + + list_del_rcu(¶m->action); + synchronize_rcu(); + INIT_LIST_HEAD(¶m->action); +} + +/* This function requires the caller holds hdev->lock */ +void hci_pend_le_list_add(struct hci_conn_params *param, + struct list_head *list) +{ + list_add_rcu(¶m->action, list); +} + +/* This function requires the caller holds hdev->lock */ struct hci_conn_params *hci_conn_params_add(struct hci_dev *hdev, bdaddr_t *addr, u8 addr_type) { @@ -2297,14 +2323,15 @@ struct hci_conn_params *hci_conn_params_add(struct hci_dev *hdev, return params; } -static void hci_conn_params_free(struct hci_conn_params *params) +void hci_conn_params_free(struct hci_conn_params *params) { + hci_pend_le_list_del_init(params); + if (params->conn) { hci_conn_drop(params->conn); hci_conn_put(params->conn); } - list_del(¶ms->action); list_del(¶ms->list); kfree(params); } @@ -2342,8 +2369,7 @@ void hci_conn_params_clear_disabled(struct hci_dev *hdev) continue; } - list_del(¶ms->list); - kfree(params); + hci_conn_params_free(params); } BT_DBG("All LE disabled connection parameters were removed"); diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index 95816a938cea..31ca320ce38d 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -1564,7 +1564,7 @@ static u8 hci_cc_le_set_privacy_mode(struct hci_dev *hdev, void *data, params = hci_conn_params_lookup(hdev, &cp->bdaddr, cp->bdaddr_type); if (params) - params->privacy_mode = cp->mode; + WRITE_ONCE(params->privacy_mode, cp->mode); hci_dev_unlock(hdev); @@ -2784,6 +2784,9 @@ static void hci_cs_disconnect(struct hci_dev *hdev, u8 status) hci_enable_advertising(hdev); } + /* Inform sockets conn is gone before we delete it */ + hci_disconn_cfm(conn, HCI_ERROR_UNSPECIFIED); + goto done; } @@ -2804,8 +2807,8 @@ static void hci_cs_disconnect(struct hci_dev *hdev, u8 status) case HCI_AUTO_CONN_DIRECT: case HCI_AUTO_CONN_ALWAYS: - list_del_init(¶ms->action); - list_add(¶ms->action, &hdev->pend_le_conns); + hci_pend_le_list_del_init(params); + hci_pend_le_list_add(params, &hdev->pend_le_conns); break; default: @@ -3423,8 +3426,8 @@ static void hci_disconn_complete_evt(struct hci_dev *hdev, void *data, case HCI_AUTO_CONN_DIRECT: case HCI_AUTO_CONN_ALWAYS: - list_del_init(¶ms->action); - list_add(¶ms->action, &hdev->pend_le_conns); + hci_pend_le_list_del_init(params); + hci_pend_le_list_add(params, &hdev->pend_le_conns); hci_update_passive_scan(hdev); break; @@ -5962,7 +5965,7 @@ static void le_conn_complete_evt(struct hci_dev *hdev, u8 status, params = hci_pend_le_action_lookup(&hdev->pend_le_conns, &conn->dst, conn->dst_type); if (params) { - list_del_init(¶ms->action); + hci_pend_le_list_del_init(params); if (params->conn) { hci_conn_drop(params->conn); hci_conn_put(params->conn); diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c index 8561616abbe5..4d1e32bb6a9c 100644 --- a/net/bluetooth/hci_sync.c +++ b/net/bluetooth/hci_sync.c @@ -2160,15 +2160,23 @@ static int hci_le_del_accept_list_sync(struct hci_dev *hdev, return 0; } +struct conn_params { + bdaddr_t addr; + u8 addr_type; + hci_conn_flags_t flags; + u8 privacy_mode; +}; + /* Adds connection to resolve list if needed. * Setting params to NULL programs local hdev->irk */ static int hci_le_add_resolve_list_sync(struct hci_dev *hdev, - struct hci_conn_params *params) + struct conn_params *params) { struct hci_cp_le_add_to_resolv_list cp; struct smp_irk *irk; struct bdaddr_list_with_irk *entry; + struct hci_conn_params *p; if (!use_ll_privacy(hdev)) return 0; @@ -2203,6 +2211,16 @@ static int hci_le_add_resolve_list_sync(struct hci_dev *hdev, /* Default privacy mode is always Network */ params->privacy_mode = HCI_NETWORK_PRIVACY; + rcu_read_lock(); + p = hci_pend_le_action_lookup(&hdev->pend_le_conns, + ¶ms->addr, params->addr_type); + if (!p) + p = hci_pend_le_action_lookup(&hdev->pend_le_reports, + ¶ms->addr, params->addr_type); + if (p) + WRITE_ONCE(p->privacy_mode, HCI_NETWORK_PRIVACY); + rcu_read_unlock(); + done: if (hci_dev_test_flag(hdev, HCI_PRIVACY)) memcpy(cp.local_irk, hdev->irk, 16); @@ -2215,7 +2233,7 @@ done: /* Set Device Privacy Mode. */ static int hci_le_set_privacy_mode_sync(struct hci_dev *hdev, - struct hci_conn_params *params) + struct conn_params *params) { struct hci_cp_le_set_privacy_mode cp; struct smp_irk *irk; @@ -2240,6 +2258,8 @@ static int hci_le_set_privacy_mode_sync(struct hci_dev *hdev, bacpy(&cp.bdaddr, &irk->bdaddr); cp.mode = HCI_DEVICE_PRIVACY; + /* Note: params->privacy_mode is not updated since it is a copy */ + return __hci_cmd_sync_status(hdev, HCI_OP_LE_SET_PRIVACY_MODE, sizeof(cp), &cp, HCI_CMD_TIMEOUT); } @@ -2249,7 +2269,7 @@ static int hci_le_set_privacy_mode_sync(struct hci_dev *hdev, * properly set the privacy mode. */ static int hci_le_add_accept_list_sync(struct hci_dev *hdev, - struct hci_conn_params *params, + struct conn_params *params, u8 *num_entries) { struct hci_cp_le_add_to_accept_list cp; @@ -2447,6 +2467,52 @@ struct sk_buff *hci_read_local_oob_data_sync(struct hci_dev *hdev, return __hci_cmd_sync_sk(hdev, opcode, 0, NULL, 0, HCI_CMD_TIMEOUT, sk); } +static struct conn_params *conn_params_copy(struct list_head *list, size_t *n) +{ + struct hci_conn_params *params; + struct conn_params *p; + size_t i; + + rcu_read_lock(); + + i = 0; + list_for_each_entry_rcu(params, list, action) + ++i; + *n = i; + + rcu_read_unlock(); + + p = kvcalloc(*n, sizeof(struct conn_params), GFP_KERNEL); + if (!p) + return NULL; + + rcu_read_lock(); + + i = 0; + list_for_each_entry_rcu(params, list, action) { + /* Racing adds are handled in next scan update */ + if (i >= *n) + break; + + /* No hdev->lock, but: addr, addr_type are immutable. + * privacy_mode is only written by us or in + * hci_cc_le_set_privacy_mode that we wait for. + * We should be idempotent so MGMT updating flags + * while we are processing is OK. + */ + bacpy(&p[i].addr, ¶ms->addr); + p[i].addr_type = params->addr_type; + p[i].flags = READ_ONCE(params->flags); + p[i].privacy_mode = READ_ONCE(params->privacy_mode); + ++i; + } + + rcu_read_unlock(); + + *n = i; + return p; +} + /* Device must not be scanning when updating the accept list. * * Update is done using the following sequence: @@ -2466,11 +2532,12 @@ struct sk_buff *hci_read_local_oob_data_sync(struct hci_dev *hdev, */ static u8 hci_update_accept_list_sync(struct hci_dev *hdev) { - struct hci_conn_params *params; + struct conn_params *params; struct bdaddr_list *b, *t; u8 num_entries = 0; bool pend_conn, pend_report; u8 filter_policy; + size_t i, n; int err; /* Pause advertising if resolving list can be used as controllers @@ -2504,6 +2571,7 @@ static u8 hci_update_accept_list_sync(struct hci_dev *hdev) if (hci_conn_hash_lookup_le(hdev, &b->bdaddr, b->bdaddr_type)) continue; + /* Pointers not dereferenced, no locks needed */ pend_conn = hci_pend_le_action_lookup(&hdev->pend_le_conns, &b->bdaddr, b->bdaddr_type); @@ -2532,23 +2600,50 @@ static u8 hci_update_accept_list_sync(struct hci_dev *hdev) * available accept list entries in the controller, then * just abort and return filer policy value to not use the * accept list. + * + * The list and params may be mutated while we wait for events, + * so make a copy and iterate it. */ - list_for_each_entry(params, &hdev->pend_le_conns, action) { - err = hci_le_add_accept_list_sync(hdev, params, &num_entries); - if (err) + + params = conn_params_copy(&hdev->pend_le_conns, &n); + if (!params) { + err = -ENOMEM; + goto done; + } + + for (i = 0; i < n; ++i) { + err = hci_le_add_accept_list_sync(hdev, ¶ms[i], + &num_entries); + if (err) { + kvfree(params); goto done; + } } + kvfree(params); + /* After adding all new pending connections, walk through * the list of pending reports and also add these to the * accept list if there is still space. Abort if space runs out. */ - list_for_each_entry(params, &hdev->pend_le_reports, action) { - err = hci_le_add_accept_list_sync(hdev, params, &num_entries); - if (err) + + params = conn_params_copy(&hdev->pend_le_reports, &n); + if (!params) { + err = -ENOMEM; + goto done; + } + + for (i = 0; i < n; ++i) { + err = hci_le_add_accept_list_sync(hdev, ¶ms[i], + &num_entries); + if (err) { + kvfree(params); goto done; + } } + kvfree(params); + /* Use the allowlist unless the following conditions are all true: * - We are not currently suspending * - There are 1 or more ADV monitors registered and it's not offloaded @@ -4837,12 +4932,12 @@ static void hci_pend_le_actions_clear(struct hci_dev *hdev) struct hci_conn_params *p; list_for_each_entry(p, &hdev->le_conn_params, list) { + hci_pend_le_list_del_init(p); if (p->conn) { hci_conn_drop(p->conn); hci_conn_put(p->conn); p->conn = NULL; } - list_del_init(&p->action); } BT_DBG("All LE pending actions cleared"); diff --git a/net/bluetooth/iso.c b/net/bluetooth/iso.c index 0e6cc57b3911..505d62247268 100644 --- a/net/bluetooth/iso.c +++ b/net/bluetooth/iso.c @@ -123,8 +123,11 @@ static struct iso_conn *iso_conn_add(struct hci_conn *hcon) { struct iso_conn *conn = hcon->iso_data; - if (conn) + if (conn) { + if (!conn->hcon) + conn->hcon = hcon; return conn; + } conn = kzalloc(sizeof(*conn), GFP_KERNEL); if (!conn) @@ -300,14 +303,13 @@ static int iso_connect_bis(struct sock *sk) goto unlock; } - hci_dev_unlock(hdev); - hci_dev_put(hdev); + lock_sock(sk); err = iso_chan_add(conn, sk, NULL); - if (err) - return err; - - lock_sock(sk); + if (err) { + release_sock(sk); + goto unlock; + } /* Update source addr of the socket */ bacpy(&iso_pi(sk)->src, &hcon->src); @@ -321,7 +323,6 @@ static int iso_connect_bis(struct sock *sk) } release_sock(sk); - return err; unlock: hci_dev_unlock(hdev); @@ -389,14 +390,13 @@ static int iso_connect_cis(struct sock *sk) goto unlock; } - hci_dev_unlock(hdev); - hci_dev_put(hdev); + lock_sock(sk); err = iso_chan_add(conn, sk, NULL); - if (err) - return err; - - lock_sock(sk); + if (err) { + release_sock(sk); + goto unlock; + } /* Update source addr of the socket */ bacpy(&iso_pi(sk)->src, &hcon->src); @@ -413,7 +413,6 @@ static int iso_connect_cis(struct sock *sk) } release_sock(sk); - return err; unlock: hci_dev_unlock(hdev); @@ -1072,8 +1071,8 @@ static int iso_sock_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) { struct sock *sk = sock->sk; - struct iso_conn *conn = iso_pi(sk)->conn; struct sk_buff *skb, **frag; + size_t mtu; int err; BT_DBG("sock %p, sk %p", sock, sk); @@ -1085,11 +1084,18 @@ static int iso_sock_sendmsg(struct socket *sock, struct msghdr *msg, if (msg->msg_flags & MSG_OOB) return -EOPNOTSUPP; - if (sk->sk_state != BT_CONNECTED) + lock_sock(sk); + + if (sk->sk_state != BT_CONNECTED) { + release_sock(sk); return -ENOTCONN; + } + + mtu = iso_pi(sk)->conn->hcon->hdev->iso_mtu; + + release_sock(sk); - skb = bt_skb_sendmsg(sk, msg, len, conn->hcon->hdev->iso_mtu, - HCI_ISO_DATA_HDR_SIZE, 0); + skb = bt_skb_sendmsg(sk, msg, len, mtu, HCI_ISO_DATA_HDR_SIZE, 0); if (IS_ERR(skb)) return PTR_ERR(skb); @@ -1102,8 +1108,7 @@ static int iso_sock_sendmsg(struct socket *sock, struct msghdr *msg, while (len) { struct sk_buff *tmp; - tmp = bt_skb_sendmsg(sk, msg, len, conn->hcon->hdev->iso_mtu, - 0, 0); + tmp = bt_skb_sendmsg(sk, msg, len, mtu, 0, 0); if (IS_ERR(tmp)) { kfree_skb(skb); return PTR_ERR(tmp); @@ -1158,15 +1163,19 @@ static int iso_sock_recvmsg(struct socket *sock, struct msghdr *msg, BT_DBG("sk %p", sk); if (test_and_clear_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags)) { + lock_sock(sk); switch (sk->sk_state) { case BT_CONNECT2: - lock_sock(sk); iso_conn_defer_accept(pi->conn->hcon); sk->sk_state = BT_CONFIG; release_sock(sk); return 0; case BT_CONNECT: + release_sock(sk); return iso_connect_cis(sk); + default: + release_sock(sk); + break; } } diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index f7b2d0971f24..d4498037fadc 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -1297,15 +1297,15 @@ static void restart_le_actions(struct hci_dev *hdev) /* Needed for AUTO_OFF case where might not "really" * have been powered off. */ - list_del_init(&p->action); + hci_pend_le_list_del_init(p); switch (p->auto_connect) { case HCI_AUTO_CONN_DIRECT: case HCI_AUTO_CONN_ALWAYS: - list_add(&p->action, &hdev->pend_le_conns); + hci_pend_le_list_add(p, &hdev->pend_le_conns); break; case HCI_AUTO_CONN_REPORT: - list_add(&p->action, &hdev->pend_le_reports); + hci_pend_le_list_add(p, &hdev->pend_le_reports); break; default: break; @@ -5169,7 +5169,7 @@ static int set_device_flags(struct sock *sk, struct hci_dev *hdev, void *data, goto unlock; } - params->flags = current_flags; + WRITE_ONCE(params->flags, current_flags); status = MGMT_STATUS_SUCCESS; /* Update passive scan if HCI_CONN_FLAG_DEVICE_PRIVACY @@ -7285,7 +7285,7 @@ static void get_conn_info_complete(struct hci_dev *hdev, void *data, int err) bt_dev_dbg(hdev, "err %d", err); - memcpy(&rp.addr, &cp->addr.bdaddr, sizeof(rp.addr)); + memcpy(&rp.addr, &cp->addr, sizeof(rp.addr)); status = mgmt_status(err); if (status == MGMT_STATUS_SUCCESS) { @@ -7580,7 +7580,7 @@ static int hci_conn_params_set(struct hci_dev *hdev, bdaddr_t *addr, if (params->auto_connect == auto_connect) return 0; - list_del_init(¶ms->action); + hci_pend_le_list_del_init(params); switch (auto_connect) { case HCI_AUTO_CONN_DISABLED: @@ -7589,18 +7589,18 @@ static int hci_conn_params_set(struct hci_dev *hdev, bdaddr_t *addr, * connect to device, keep connecting. */ if (params->explicit_connect) - list_add(¶ms->action, &hdev->pend_le_conns); + hci_pend_le_list_add(params, &hdev->pend_le_conns); break; case HCI_AUTO_CONN_REPORT: if (params->explicit_connect) - list_add(¶ms->action, &hdev->pend_le_conns); + hci_pend_le_list_add(params, &hdev->pend_le_conns); else - list_add(¶ms->action, &hdev->pend_le_reports); + hci_pend_le_list_add(params, &hdev->pend_le_reports); break; case HCI_AUTO_CONN_DIRECT: case HCI_AUTO_CONN_ALWAYS: if (!is_connected(hdev, addr, addr_type)) - list_add(¶ms->action, &hdev->pend_le_conns); + hci_pend_le_list_add(params, &hdev->pend_le_conns); break; } @@ -7823,9 +7823,7 @@ static int remove_device(struct sock *sk, struct hci_dev *hdev, goto unlock; } - list_del(¶ms->action); - list_del(¶ms->list); - kfree(params); + hci_conn_params_free(params); device_removed(sk, hdev, &cp->addr.bdaddr, cp->addr.type); } else { @@ -7856,9 +7854,7 @@ static int remove_device(struct sock *sk, struct hci_dev *hdev, p->auto_connect = HCI_AUTO_CONN_EXPLICIT; continue; } - list_del(&p->action); - list_del(&p->list); - kfree(p); + hci_conn_params_free(p); } bt_dev_dbg(hdev, "All LE connection parameters were removed"); diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c index cd1a27ac555d..7762604ddfc0 100644 --- a/net/bluetooth/sco.c +++ b/net/bluetooth/sco.c @@ -126,8 +126,11 @@ static struct sco_conn *sco_conn_add(struct hci_conn *hcon) struct hci_dev *hdev = hcon->hdev; struct sco_conn *conn = hcon->sco_data; - if (conn) + if (conn) { + if (!conn->hcon) + conn->hcon = hcon; return conn; + } conn = kzalloc(sizeof(struct sco_conn), GFP_KERNEL); if (!conn) @@ -268,21 +271,21 @@ static int sco_connect(struct sock *sk) goto unlock; } - hci_dev_unlock(hdev); - hci_dev_put(hdev); - conn = sco_conn_add(hcon); if (!conn) { hci_conn_drop(hcon); - return -ENOMEM; + err = -ENOMEM; + goto unlock; } - err = sco_chan_add(conn, sk, NULL); - if (err) - return err; - lock_sock(sk); + err = sco_chan_add(conn, sk, NULL); + if (err) { + release_sock(sk); + goto unlock; + } + /* Update source addr of the socket */ bacpy(&sco_pi(sk)->src, &hcon->src); @@ -296,8 +299,6 @@ static int sco_connect(struct sock *sk) release_sock(sk); - return err; - unlock: hci_dev_unlock(hdev); hci_dev_put(hdev); diff --git a/net/can/bcm.c b/net/can/bcm.c index 9ba35685b043..9168114fc87f 100644 --- a/net/can/bcm.c +++ b/net/can/bcm.c @@ -1526,6 +1526,12 @@ static int bcm_release(struct socket *sock) lock_sock(sk); +#if IS_ENABLED(CONFIG_PROC_FS) + /* remove procfs entry */ + if (net->can.bcmproc_dir && bo->bcm_proc_read) + remove_proc_entry(bo->procname, net->can.bcmproc_dir); +#endif /* CONFIG_PROC_FS */ + list_for_each_entry_safe(op, next, &bo->tx_ops, list) bcm_remove_op(op); @@ -1561,12 +1567,6 @@ static int bcm_release(struct socket *sock) list_for_each_entry_safe(op, next, &bo->rx_ops, list) bcm_remove_op(op); -#if IS_ENABLED(CONFIG_PROC_FS) - /* remove procfs entry */ - if (net->can.bcmproc_dir && bo->bcm_proc_read) - remove_proc_entry(bo->procname, net->can.bcmproc_dir); -#endif /* CONFIG_PROC_FS */ - /* remove device reference */ if (bo->bound) { bo->bound = 0; diff --git a/net/can/raw.c b/net/can/raw.c index 15c79b079184..2302e4882967 100644 --- a/net/can/raw.c +++ b/net/can/raw.c @@ -84,6 +84,7 @@ struct raw_sock { struct sock sk; int bound; int ifindex; + struct net_device *dev; struct list_head notifier; int loopback; int recv_own_msgs; @@ -277,7 +278,7 @@ static void raw_notify(struct raw_sock *ro, unsigned long msg, if (!net_eq(dev_net(dev), sock_net(sk))) return; - if (ro->ifindex != dev->ifindex) + if (ro->dev != dev) return; switch (msg) { @@ -292,6 +293,7 @@ static void raw_notify(struct raw_sock *ro, unsigned long msg, ro->ifindex = 0; ro->bound = 0; + ro->dev = NULL; ro->count = 0; release_sock(sk); @@ -337,6 +339,7 @@ static int raw_init(struct sock *sk) ro->bound = 0; ro->ifindex = 0; + ro->dev = NULL; /* set default filter to single entry dfilter */ ro->dfilter.can_id = 0; @@ -385,19 +388,13 @@ static int raw_release(struct socket *sock) lock_sock(sk); + rtnl_lock(); /* remove current filters & unregister */ if (ro->bound) { - if (ro->ifindex) { - struct net_device *dev; - - dev = dev_get_by_index(sock_net(sk), ro->ifindex); - if (dev) { - raw_disable_allfilters(dev_net(dev), dev, sk); - dev_put(dev); - } - } else { + if (ro->dev) + raw_disable_allfilters(dev_net(ro->dev), ro->dev, sk); + else raw_disable_allfilters(sock_net(sk), NULL, sk); - } } if (ro->count > 1) @@ -405,8 +402,10 @@ static int raw_release(struct socket *sock) ro->ifindex = 0; ro->bound = 0; + ro->dev = NULL; ro->count = 0; free_percpu(ro->uniq); + rtnl_unlock(); sock_orphan(sk); sock->sk = NULL; @@ -422,6 +421,7 @@ static int raw_bind(struct socket *sock, struct sockaddr *uaddr, int len) struct sockaddr_can *addr = (struct sockaddr_can *)uaddr; struct sock *sk = sock->sk; struct raw_sock *ro = raw_sk(sk); + struct net_device *dev = NULL; int ifindex; int err = 0; int notify_enetdown = 0; @@ -431,14 +431,13 @@ static int raw_bind(struct socket *sock, struct sockaddr *uaddr, int len) if (addr->can_family != AF_CAN) return -EINVAL; + rtnl_lock(); lock_sock(sk); if (ro->bound && addr->can_ifindex == ro->ifindex) goto out; if (addr->can_ifindex) { - struct net_device *dev; - dev = dev_get_by_index(sock_net(sk), addr->can_ifindex); if (!dev) { err = -ENODEV; @@ -467,26 +466,20 @@ static int raw_bind(struct socket *sock, struct sockaddr *uaddr, int len) if (!err) { if (ro->bound) { /* unregister old filters */ - if (ro->ifindex) { - struct net_device *dev; - - dev = dev_get_by_index(sock_net(sk), - ro->ifindex); - if (dev) { - raw_disable_allfilters(dev_net(dev), - dev, sk); - dev_put(dev); - } - } else { + if (ro->dev) + raw_disable_allfilters(dev_net(ro->dev), + ro->dev, sk); + else raw_disable_allfilters(sock_net(sk), NULL, sk); - } } ro->ifindex = ifindex; ro->bound = 1; + ro->dev = dev; } out: release_sock(sk); + rtnl_unlock(); if (notify_enetdown) { sk->sk_err = ENETDOWN; @@ -553,9 +546,9 @@ static int raw_setsockopt(struct socket *sock, int level, int optname, rtnl_lock(); lock_sock(sk); - if (ro->bound && ro->ifindex) { - dev = dev_get_by_index(sock_net(sk), ro->ifindex); - if (!dev) { + dev = ro->dev; + if (ro->bound && dev) { + if (dev->reg_state != NETREG_REGISTERED) { if (count > 1) kfree(filter); err = -ENODEV; @@ -596,7 +589,6 @@ static int raw_setsockopt(struct socket *sock, int level, int optname, ro->count = count; out_fil: - dev_put(dev); release_sock(sk); rtnl_unlock(); @@ -614,9 +606,9 @@ static int raw_setsockopt(struct socket *sock, int level, int optname, rtnl_lock(); lock_sock(sk); - if (ro->bound && ro->ifindex) { - dev = dev_get_by_index(sock_net(sk), ro->ifindex); - if (!dev) { + dev = ro->dev; + if (ro->bound && dev) { + if (dev->reg_state != NETREG_REGISTERED) { err = -ENODEV; goto out_err; } @@ -640,7 +632,6 @@ static int raw_setsockopt(struct socket *sock, int level, int optname, ro->err_mask = err_mask; out_err: - dev_put(dev); release_sock(sk); rtnl_unlock(); diff --git a/net/ceph/messenger_v2.c b/net/ceph/messenger_v2.c index 1a888b86a494..1df1d29dee92 100644 --- a/net/ceph/messenger_v2.c +++ b/net/ceph/messenger_v2.c @@ -390,6 +390,8 @@ static int head_onwire_len(int ctrl_len, bool secure) int head_len; int rem_len; + BUG_ON(ctrl_len < 0 || ctrl_len > CEPH_MSG_MAX_CONTROL_LEN); + if (secure) { head_len = CEPH_PREAMBLE_SECURE_LEN; if (ctrl_len > CEPH_PREAMBLE_INLINE_LEN) { @@ -408,6 +410,10 @@ static int head_onwire_len(int ctrl_len, bool secure) static int __tail_onwire_len(int front_len, int middle_len, int data_len, bool secure) { + BUG_ON(front_len < 0 || front_len > CEPH_MSG_MAX_FRONT_LEN || + middle_len < 0 || middle_len > CEPH_MSG_MAX_MIDDLE_LEN || + data_len < 0 || data_len > CEPH_MSG_MAX_DATA_LEN); + if (!front_len && !middle_len && !data_len) return 0; @@ -520,29 +526,34 @@ static int decode_preamble(void *p, struct ceph_frame_desc *desc) desc->fd_aligns[i] = ceph_decode_16(&p); } - /* - * This would fire for FRAME_TAG_WAIT (it has one empty - * segment), but we should never get it as client. - */ - if (!desc->fd_lens[desc->fd_seg_cnt - 1]) { - pr_err("last segment empty\n"); + if (desc->fd_lens[0] < 0 || + desc->fd_lens[0] > CEPH_MSG_MAX_CONTROL_LEN) { + pr_err("bad control segment length %d\n", desc->fd_lens[0]); return -EINVAL; } - - if (desc->fd_lens[0] > CEPH_MSG_MAX_CONTROL_LEN) { - pr_err("control segment too big %d\n", desc->fd_lens[0]); + if (desc->fd_lens[1] < 0 || + desc->fd_lens[1] > CEPH_MSG_MAX_FRONT_LEN) { + pr_err("bad front segment length %d\n", desc->fd_lens[1]); return -EINVAL; } - if (desc->fd_lens[1] > CEPH_MSG_MAX_FRONT_LEN) { - pr_err("front segment too big %d\n", desc->fd_lens[1]); + if (desc->fd_lens[2] < 0 || + desc->fd_lens[2] > CEPH_MSG_MAX_MIDDLE_LEN) { + pr_err("bad middle segment length %d\n", desc->fd_lens[2]); return -EINVAL; } - if (desc->fd_lens[2] > CEPH_MSG_MAX_MIDDLE_LEN) { - pr_err("middle segment too big %d\n", desc->fd_lens[2]); + if (desc->fd_lens[3] < 0 || + desc->fd_lens[3] > CEPH_MSG_MAX_DATA_LEN) { + pr_err("bad data segment length %d\n", desc->fd_lens[3]); return -EINVAL; } - if (desc->fd_lens[3] > CEPH_MSG_MAX_DATA_LEN) { - pr_err("data segment too big %d\n", desc->fd_lens[3]); + + /* + * This would fire for FRAME_TAG_WAIT (it has one empty + * segment), but we should never get it as client. + */ + if (!desc->fd_lens[desc->fd_seg_cnt - 1]) { + pr_err("last segment empty, segment count %d\n", + desc->fd_seg_cnt); return -EINVAL; } diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c index ba06ed42e428..2be2d4922557 100644 --- a/net/ipv4/esp4.c +++ b/net/ipv4/esp4.c @@ -1132,7 +1132,7 @@ static int esp_init_authenc(struct xfrm_state *x, err = crypto_aead_setkey(aead, key, keylen); free_key: - kfree(key); + kfree_sensitive(key); error: return err; diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 0cc19cfbb673..aeebe8816689 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -1019,7 +1019,7 @@ static void reqsk_timer_handler(struct timer_list *t) icsk = inet_csk(sk_listener); net = sock_net(sk_listener); - max_syn_ack_retries = icsk->icsk_syn_retries ? : + max_syn_ack_retries = READ_ONCE(icsk->icsk_syn_retries) ? : READ_ONCE(net->ipv4.sysctl_tcp_synack_retries); /* Normally all the openreqs are young and become mature * (i.e. converted to established socket) for first timeout. diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index e7391bf310a7..0819d6001b9a 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -650,20 +650,8 @@ bool inet_ehash_insert(struct sock *sk, struct sock *osk, bool *found_dup_sk) spin_lock(lock); if (osk) { WARN_ON_ONCE(sk->sk_hash != osk->sk_hash); - ret = sk_hashed(osk); - if (ret) { - /* Before deleting the node, we insert a new one to make - * sure that the look-up-sk process would not miss either - * of them and that at least one node would exist in ehash - * table all the time. Otherwise there's a tiny chance - * that lookup process could find nothing in ehash table. - */ - __sk_nulls_add_node_tail_rcu(sk, list); - sk_nulls_del_node_init_rcu(osk); - } - goto unlock; - } - if (found_dup_sk) { + ret = sk_nulls_del_node_init_rcu(osk); + } else if (found_dup_sk) { *found_dup_sk = inet_ehash_lookup_by_sk(sk, list); if (*found_dup_sk) ret = false; @@ -672,7 +660,6 @@ bool inet_ehash_insert(struct sock *sk, struct sock *osk, bool *found_dup_sk) if (ret) __sk_nulls_add_node_rcu(sk, list); -unlock: spin_unlock(lock); return ret; diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c index 40052414c7c7..2c1b245dba8e 100644 --- a/net/ipv4/inet_timewait_sock.c +++ b/net/ipv4/inet_timewait_sock.c @@ -88,10 +88,10 @@ void inet_twsk_put(struct inet_timewait_sock *tw) } EXPORT_SYMBOL_GPL(inet_twsk_put); -static void inet_twsk_add_node_tail_rcu(struct inet_timewait_sock *tw, - struct hlist_nulls_head *list) +static void inet_twsk_add_node_rcu(struct inet_timewait_sock *tw, + struct hlist_nulls_head *list) { - hlist_nulls_add_tail_rcu(&tw->tw_node, list); + hlist_nulls_add_head_rcu(&tw->tw_node, list); } static void inet_twsk_add_bind_node(struct inet_timewait_sock *tw, @@ -144,7 +144,7 @@ void inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk, spin_lock(lock); - inet_twsk_add_node_tail_rcu(tw, &ehead->chain); + inet_twsk_add_node_rcu(tw, &ehead->chain); /* Step 3: Remove SK from hash chain */ if (__sk_nulls_del_node_init_rcu(sk)) diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 81a1cce1a7d1..22a26d1d29a0 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -548,7 +548,8 @@ static void erspan_fb_xmit(struct sk_buff *skb, struct net_device *dev) goto err_free_skb; if (skb->len > dev->mtu + dev->hard_header_len) { - pskb_trim(skb, dev->mtu + dev->hard_header_len); + if (pskb_trim(skb, dev->mtu + dev->hard_header_len)) + goto err_free_skb; truncate = true; } @@ -689,7 +690,8 @@ static netdev_tx_t erspan_xmit(struct sk_buff *skb, goto free_skb; if (skb->len > dev->mtu + dev->hard_header_len) { - pskb_trim(skb, dev->mtu + dev->hard_header_len); + if (pskb_trim(skb, dev->mtu + dev->hard_header_len)) + goto free_skb; truncate = true; } diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 88f4ebab12ac..aca5620cf3ba 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -3292,7 +3292,7 @@ int tcp_sock_set_syncnt(struct sock *sk, int val) return -EINVAL; lock_sock(sk); - inet_csk(sk)->icsk_syn_retries = val; + WRITE_ONCE(inet_csk(sk)->icsk_syn_retries, val); release_sock(sk); return 0; } @@ -3301,7 +3301,7 @@ EXPORT_SYMBOL(tcp_sock_set_syncnt); void tcp_sock_set_user_timeout(struct sock *sk, u32 val) { lock_sock(sk); - inet_csk(sk)->icsk_user_timeout = val; + WRITE_ONCE(inet_csk(sk)->icsk_user_timeout, val); release_sock(sk); } EXPORT_SYMBOL(tcp_sock_set_user_timeout); @@ -3313,7 +3313,8 @@ int tcp_sock_set_keepidle_locked(struct sock *sk, int val) if (val < 1 || val > MAX_TCP_KEEPIDLE) return -EINVAL; - tp->keepalive_time = val * HZ; + /* Paired with WRITE_ONCE() in keepalive_time_when() */ + WRITE_ONCE(tp->keepalive_time, val * HZ); if (sock_flag(sk, SOCK_KEEPOPEN) && !((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN))) { u32 elapsed = keepalive_time_elapsed(tp); @@ -3345,7 +3346,7 @@ int tcp_sock_set_keepintvl(struct sock *sk, int val) return -EINVAL; lock_sock(sk); - tcp_sk(sk)->keepalive_intvl = val * HZ; + WRITE_ONCE(tcp_sk(sk)->keepalive_intvl, val * HZ); release_sock(sk); return 0; } @@ -3357,7 +3358,8 @@ int tcp_sock_set_keepcnt(struct sock *sk, int val) return -EINVAL; lock_sock(sk); - tcp_sk(sk)->keepalive_probes = val; + /* Paired with READ_ONCE() in keepalive_probes() */ + WRITE_ONCE(tcp_sk(sk)->keepalive_probes, val); release_sock(sk); return 0; } @@ -3559,19 +3561,19 @@ int do_tcp_setsockopt(struct sock *sk, int level, int optname, if (val < 1 || val > MAX_TCP_KEEPINTVL) err = -EINVAL; else - tp->keepalive_intvl = val * HZ; + WRITE_ONCE(tp->keepalive_intvl, val * HZ); break; case TCP_KEEPCNT: if (val < 1 || val > MAX_TCP_KEEPCNT) err = -EINVAL; else - tp->keepalive_probes = val; + WRITE_ONCE(tp->keepalive_probes, val); break; case TCP_SYNCNT: if (val < 1 || val > MAX_TCP_SYNCNT) err = -EINVAL; else - icsk->icsk_syn_retries = val; + WRITE_ONCE(icsk->icsk_syn_retries, val); break; case TCP_SAVE_SYN: @@ -3584,18 +3586,18 @@ int do_tcp_setsockopt(struct sock *sk, int level, int optname, case TCP_LINGER2: if (val < 0) - tp->linger2 = -1; + WRITE_ONCE(tp->linger2, -1); else if (val > TCP_FIN_TIMEOUT_MAX / HZ) - tp->linger2 = TCP_FIN_TIMEOUT_MAX; + WRITE_ONCE(tp->linger2, TCP_FIN_TIMEOUT_MAX); else - tp->linger2 = val * HZ; + WRITE_ONCE(tp->linger2, val * HZ); break; case TCP_DEFER_ACCEPT: /* Translate value in seconds to number of retransmits */ - icsk->icsk_accept_queue.rskq_defer_accept = - secs_to_retrans(val, TCP_TIMEOUT_INIT / HZ, - TCP_RTO_MAX / HZ); + WRITE_ONCE(icsk->icsk_accept_queue.rskq_defer_accept, + secs_to_retrans(val, TCP_TIMEOUT_INIT / HZ, + TCP_RTO_MAX / HZ)); break; case TCP_WINDOW_CLAMP: @@ -3619,7 +3621,7 @@ int do_tcp_setsockopt(struct sock *sk, int level, int optname, if (val < 0) err = -EINVAL; else - icsk->icsk_user_timeout = val; + WRITE_ONCE(icsk->icsk_user_timeout, val); break; case TCP_FASTOPEN: @@ -3657,13 +3659,13 @@ int do_tcp_setsockopt(struct sock *sk, int level, int optname, if (!tp->repair) err = -EPERM; else - tp->tsoffset = val - tcp_time_stamp_raw(); + WRITE_ONCE(tp->tsoffset, val - tcp_time_stamp_raw()); break; case TCP_REPAIR_WINDOW: err = tcp_repair_set_window(tp, optval, optlen); break; case TCP_NOTSENT_LOWAT: - tp->notsent_lowat = val; + WRITE_ONCE(tp->notsent_lowat, val); sk->sk_write_space(sk); break; case TCP_INQ: @@ -3675,7 +3677,7 @@ int do_tcp_setsockopt(struct sock *sk, int level, int optname, case TCP_TX_DELAY: if (val) tcp_enable_tx_delay(); - tp->tcp_tx_delay = val; + WRITE_ONCE(tp->tcp_tx_delay, val); break; default: err = -ENOPROTOOPT; @@ -3992,17 +3994,18 @@ int do_tcp_getsockopt(struct sock *sk, int level, val = keepalive_probes(tp); break; case TCP_SYNCNT: - val = icsk->icsk_syn_retries ? : + val = READ_ONCE(icsk->icsk_syn_retries) ? : READ_ONCE(net->ipv4.sysctl_tcp_syn_retries); break; case TCP_LINGER2: - val = tp->linger2; + val = READ_ONCE(tp->linger2); if (val >= 0) val = (val ? : READ_ONCE(net->ipv4.sysctl_tcp_fin_timeout)) / HZ; break; case TCP_DEFER_ACCEPT: - val = retrans_to_secs(icsk->icsk_accept_queue.rskq_defer_accept, - TCP_TIMEOUT_INIT / HZ, TCP_RTO_MAX / HZ); + val = READ_ONCE(icsk->icsk_accept_queue.rskq_defer_accept); + val = retrans_to_secs(val, TCP_TIMEOUT_INIT / HZ, + TCP_RTO_MAX / HZ); break; case TCP_WINDOW_CLAMP: val = tp->window_clamp; @@ -4139,11 +4142,11 @@ int do_tcp_getsockopt(struct sock *sk, int level, break; case TCP_USER_TIMEOUT: - val = icsk->icsk_user_timeout; + val = READ_ONCE(icsk->icsk_user_timeout); break; case TCP_FASTOPEN: - val = icsk->icsk_accept_queue.fastopenq.max_qlen; + val = READ_ONCE(icsk->icsk_accept_queue.fastopenq.max_qlen); break; case TCP_FASTOPEN_CONNECT: @@ -4155,14 +4158,14 @@ int do_tcp_getsockopt(struct sock *sk, int level, break; case TCP_TX_DELAY: - val = tp->tcp_tx_delay; + val = READ_ONCE(tp->tcp_tx_delay); break; case TCP_TIMESTAMP: - val = tcp_time_stamp_raw() + tp->tsoffset; + val = tcp_time_stamp_raw() + READ_ONCE(tp->tsoffset); break; case TCP_NOTSENT_LOWAT: - val = tp->notsent_lowat; + val = READ_ONCE(tp->notsent_lowat); break; case TCP_INQ: val = tp->recvmsg_inq; diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c index 45cc7f1ca296..85e4953f1182 100644 --- a/net/ipv4/tcp_fastopen.c +++ b/net/ipv4/tcp_fastopen.c @@ -296,6 +296,7 @@ static struct sock *tcp_fastopen_create_child(struct sock *sk, static bool tcp_fastopen_queue_check(struct sock *sk) { struct fastopen_queue *fastopenq; + int max_qlen; /* Make sure the listener has enabled fastopen, and we don't * exceed the max # of pending TFO requests allowed before trying @@ -308,10 +309,11 @@ static bool tcp_fastopen_queue_check(struct sock *sk) * temporarily vs a server not supporting Fast Open at all. */ fastopenq = &inet_csk(sk)->icsk_accept_queue.fastopenq; - if (fastopenq->max_qlen == 0) + max_qlen = READ_ONCE(fastopenq->max_qlen); + if (max_qlen == 0) return false; - if (fastopenq->qlen >= fastopenq->max_qlen) { + if (fastopenq->qlen >= max_qlen) { struct request_sock *req1; spin_lock(&fastopenq->lock); req1 = fastopenq->rskq_rst_head; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index cecd5a135e64..09cffbc82d32 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -308,8 +308,9 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) inet->inet_daddr, inet->inet_sport, usin->sin_port)); - tp->tsoffset = secure_tcp_ts_off(net, inet->inet_saddr, - inet->inet_daddr); + WRITE_ONCE(tp->tsoffset, + secure_tcp_ts_off(net, inet->inet_saddr, + inet->inet_daddr)); } inet->inet_id = get_random_u16(); @@ -989,11 +990,12 @@ static void tcp_v4_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb, tcp_rsk(req)->rcv_nxt, req->rsk_rcv_wnd >> inet_rsk(req)->rcv_wscale, tcp_time_stamp_raw() + tcp_rsk(req)->ts_off, - req->ts_recent, + READ_ONCE(req->ts_recent), 0, tcp_md5_do_lookup(sk, l3index, addr, AF_INET), inet_rsk(req)->no_srccheck ? IP_REPLY_ARG_NOSRCCHECK : 0, - ip_hdr(skb)->tos, tcp_rsk(req)->txhash); + ip_hdr(skb)->tos, + READ_ONCE(tcp_rsk(req)->txhash)); } /* diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 04fc328727e6..c8f2aa003387 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -528,7 +528,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk, newicsk->icsk_ack.lrcvtime = tcp_jiffies32; newtp->lsndtime = tcp_jiffies32; - newsk->sk_txhash = treq->txhash; + newsk->sk_txhash = READ_ONCE(treq->txhash); newtp->total_retrans = req->num_retrans; tcp_init_xmit_timers(newsk); @@ -555,7 +555,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk, newtp->max_window = newtp->snd_wnd; if (newtp->rx_opt.tstamp_ok) { - newtp->rx_opt.ts_recent = req->ts_recent; + newtp->rx_opt.ts_recent = READ_ONCE(req->ts_recent); newtp->rx_opt.ts_recent_stamp = ktime_get_seconds(); newtp->tcp_header_len = sizeof(struct tcphdr) + TCPOLEN_TSTAMP_ALIGNED; } else { @@ -619,7 +619,7 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, tcp_parse_options(sock_net(sk), skb, &tmp_opt, 0, NULL); if (tmp_opt.saw_tstamp) { - tmp_opt.ts_recent = req->ts_recent; + tmp_opt.ts_recent = READ_ONCE(req->ts_recent); if (tmp_opt.rcv_tsecr) tmp_opt.rcv_tsecr -= tcp_rsk(req)->ts_off; /* We do not store true stamp, but it is not required, @@ -758,8 +758,11 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, /* In sequence, PAWS is OK. */ + /* TODO: We probably should defer ts_recent change once + * we take ownership of @req. + */ if (tmp_opt.saw_tstamp && !after(TCP_SKB_CB(skb)->seq, tcp_rsk(req)->rcv_nxt)) - req->ts_recent = tmp_opt.rcv_tsval; + WRITE_ONCE(req->ts_recent, tmp_opt.rcv_tsval); if (TCP_SKB_CB(skb)->seq == tcp_rsk(req)->rcv_isn) { /* Truncate SYN, it is out of window starting diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 2cb39b6dad02..51d8638d4b4c 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -878,7 +878,7 @@ static unsigned int tcp_synack_options(const struct sock *sk, if (likely(ireq->tstamp_ok)) { opts->options |= OPTION_TS; opts->tsval = tcp_skb_timestamp(skb) + tcp_rsk(req)->ts_off; - opts->tsecr = req->ts_recent; + opts->tsecr = READ_ONCE(req->ts_recent); remaining -= TCPOLEN_TSTAMP_ALIGNED; } if (likely(ireq->sack_ok)) { @@ -3660,7 +3660,7 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst, rcu_read_lock(); md5 = tcp_rsk(req)->af_specific->req_md5_lookup(sk, req_to_sk(req)); #endif - skb_set_hash(skb, tcp_rsk(req)->txhash, PKT_HASH_TYPE_L4); + skb_set_hash(skb, READ_ONCE(tcp_rsk(req)->txhash), PKT_HASH_TYPE_L4); /* bpf program will be interested in the tcp_flags */ TCP_SKB_CB(skb)->tcp_flags = TCPHDR_SYN | TCPHDR_ACK; tcp_header_size = tcp_synack_options(sk, req, mss, skb, &opts, md5, @@ -4210,7 +4210,7 @@ int tcp_rtx_synack(const struct sock *sk, struct request_sock *req) /* Paired with WRITE_ONCE() in sock_setsockopt() */ if (READ_ONCE(sk->sk_txrehash) == SOCK_TXREHASH_ENABLED) - tcp_rsk(req)->txhash = net_tx_rndhash(); + WRITE_ONCE(tcp_rsk(req)->txhash, net_tx_rndhash()); res = af_ops->send_synack(sk, NULL, &fl, req, NULL, TCP_SYNACK_NORMAL, NULL); if (!res) { diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index 75aa4de5b731..f402946da344 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -274,13 +274,20 @@ struct sk_buff *__udp_gso_segment(struct sk_buff *gso_skb, __sum16 check; __be16 newlen; - if (skb_shinfo(gso_skb)->gso_type & SKB_GSO_FRAGLIST) - return __udp_gso_segment_list(gso_skb, features, is_ipv6); - mss = skb_shinfo(gso_skb)->gso_size; if (gso_skb->len <= sizeof(*uh) + mss) return ERR_PTR(-EINVAL); + if (skb_gso_ok(gso_skb, features | NETIF_F_GSO_ROBUST)) { + /* Packet is from an untrusted source, reset gso_segs. */ + skb_shinfo(gso_skb)->gso_segs = DIV_ROUND_UP(gso_skb->len - sizeof(*uh), + mss); + return NULL; + } + + if (skb_shinfo(gso_skb)->gso_type & SKB_GSO_FRAGLIST) + return __udp_gso_segment_list(gso_skb, features, is_ipv6); + skb_pull(gso_skb, sizeof(*uh)); /* clear destructor to avoid skb_segment assigning it to tail */ @@ -388,8 +395,7 @@ static struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb, if (!pskb_may_pull(skb, sizeof(struct udphdr))) goto out; - if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4 && - !skb_gso_ok(skb, features | NETIF_F_GSO_ROBUST)) + if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4) return __udp_gso_segment(skb, features, false); mss = skb_shinfo(skb)->gso_size; diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index da80974ad23a..070d87abf7c0 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -955,7 +955,8 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb, goto tx_err; if (skb->len > dev->mtu + dev->hard_header_len) { - pskb_trim(skb, dev->mtu + dev->hard_header_len); + if (pskb_trim(skb, dev->mtu + dev->hard_header_len)) + goto tx_err; truncate = true; } diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 40dd92a2f480..4714eb695913 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1126,10 +1126,10 @@ static void tcp_v6_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb, tcp_rsk(req)->rcv_nxt, req->rsk_rcv_wnd >> inet_rsk(req)->rcv_wscale, tcp_time_stamp_raw() + tcp_rsk(req)->ts_off, - req->ts_recent, sk->sk_bound_dev_if, + READ_ONCE(req->ts_recent), sk->sk_bound_dev_if, tcp_v6_md5_do_lookup(sk, &ipv6_hdr(skb)->saddr, l3index), ipv6_get_dsfield(ipv6_hdr(skb)), 0, sk->sk_priority, - tcp_rsk(req)->txhash); + READ_ONCE(tcp_rsk(req)->txhash)); } diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c index ad3b8726873e..09fa7a42cb93 100644 --- a/net/ipv6/udp_offload.c +++ b/net/ipv6/udp_offload.c @@ -43,8 +43,7 @@ static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb, if (!pskb_may_pull(skb, sizeof(struct udphdr))) goto out; - if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4 && - !skb_gso_ok(skb, features | NETIF_F_GSO_ROBUST)) + if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4) return __udp_gso_segment(skb, features, true); mss = skb_shinfo(skb)->gso_size; diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c index 57c35c960b2c..9b06c380866b 100644 --- a/net/llc/af_llc.c +++ b/net/llc/af_llc.c @@ -402,7 +402,7 @@ static int llc_ui_bind(struct socket *sock, struct sockaddr *uaddr, int addrlen) memcpy(laddr.mac, addr->sllc_mac, IFHWADDRLEN); laddr.lsap = addr->sllc_sap; rc = -EADDRINUSE; /* mac + sap clash. */ - ask = llc_lookup_established(sap, &daddr, &laddr); + ask = llc_lookup_established(sap, &daddr, &laddr, &init_net); if (ask) { sock_put(ask); goto out_put; diff --git a/net/llc/llc_conn.c b/net/llc/llc_conn.c index 912aa9bd5e29..d037009ee10f 100644 --- a/net/llc/llc_conn.c +++ b/net/llc/llc_conn.c @@ -453,11 +453,13 @@ static int llc_exec_conn_trans_actions(struct sock *sk, static inline bool llc_estab_match(const struct llc_sap *sap, const struct llc_addr *daddr, const struct llc_addr *laddr, - const struct sock *sk) + const struct sock *sk, + const struct net *net) { struct llc_sock *llc = llc_sk(sk); - return llc->laddr.lsap == laddr->lsap && + return net_eq(sock_net(sk), net) && + llc->laddr.lsap == laddr->lsap && llc->daddr.lsap == daddr->lsap && ether_addr_equal(llc->laddr.mac, laddr->mac) && ether_addr_equal(llc->daddr.mac, daddr->mac); @@ -468,6 +470,7 @@ static inline bool llc_estab_match(const struct llc_sap *sap, * @sap: SAP * @daddr: address of remote LLC (MAC + SAP) * @laddr: address of local LLC (MAC + SAP) + * @net: netns to look up a socket in * * Search connection list of the SAP and finds connection using the remote * mac, remote sap, local mac, and local sap. Returns pointer for @@ -476,7 +479,8 @@ static inline bool llc_estab_match(const struct llc_sap *sap, */ static struct sock *__llc_lookup_established(struct llc_sap *sap, struct llc_addr *daddr, - struct llc_addr *laddr) + struct llc_addr *laddr, + const struct net *net) { struct sock *rc; struct hlist_nulls_node *node; @@ -486,12 +490,12 @@ static struct sock *__llc_lookup_established(struct llc_sap *sap, rcu_read_lock(); again: sk_nulls_for_each_rcu(rc, node, laddr_hb) { - if (llc_estab_match(sap, daddr, laddr, rc)) { + if (llc_estab_match(sap, daddr, laddr, rc, net)) { /* Extra checks required by SLAB_TYPESAFE_BY_RCU */ if (unlikely(!refcount_inc_not_zero(&rc->sk_refcnt))) goto again; if (unlikely(llc_sk(rc)->sap != sap || - !llc_estab_match(sap, daddr, laddr, rc))) { + !llc_estab_match(sap, daddr, laddr, rc, net))) { sock_put(rc); continue; } @@ -513,29 +517,33 @@ found: struct sock *llc_lookup_established(struct llc_sap *sap, struct llc_addr *daddr, - struct llc_addr *laddr) + struct llc_addr *laddr, + const struct net *net) { struct sock *sk; local_bh_disable(); - sk = __llc_lookup_established(sap, daddr, laddr); + sk = __llc_lookup_established(sap, daddr, laddr, net); local_bh_enable(); return sk; } static inline bool llc_listener_match(const struct llc_sap *sap, const struct llc_addr *laddr, - const struct sock *sk) + const struct sock *sk, + const struct net *net) { struct llc_sock *llc = llc_sk(sk); - return sk->sk_type == SOCK_STREAM && sk->sk_state == TCP_LISTEN && + return net_eq(sock_net(sk), net) && + sk->sk_type == SOCK_STREAM && sk->sk_state == TCP_LISTEN && llc->laddr.lsap == laddr->lsap && ether_addr_equal(llc->laddr.mac, laddr->mac); } static struct sock *__llc_lookup_listener(struct llc_sap *sap, - struct llc_addr *laddr) + struct llc_addr *laddr, + const struct net *net) { struct sock *rc; struct hlist_nulls_node *node; @@ -545,12 +553,12 @@ static struct sock *__llc_lookup_listener(struct llc_sap *sap, rcu_read_lock(); again: sk_nulls_for_each_rcu(rc, node, laddr_hb) { - if (llc_listener_match(sap, laddr, rc)) { + if (llc_listener_match(sap, laddr, rc, net)) { /* Extra checks required by SLAB_TYPESAFE_BY_RCU */ if (unlikely(!refcount_inc_not_zero(&rc->sk_refcnt))) goto again; if (unlikely(llc_sk(rc)->sap != sap || - !llc_listener_match(sap, laddr, rc))) { + !llc_listener_match(sap, laddr, rc, net))) { sock_put(rc); continue; } @@ -574,6 +582,7 @@ found: * llc_lookup_listener - Finds listener for local MAC + SAP * @sap: SAP * @laddr: address of local LLC (MAC + SAP) + * @net: netns to look up a socket in * * Search connection list of the SAP and finds connection listening on * local mac, and local sap. Returns pointer for parent socket found, @@ -581,24 +590,26 @@ found: * Caller has to make sure local_bh is disabled. */ static struct sock *llc_lookup_listener(struct llc_sap *sap, - struct llc_addr *laddr) + struct llc_addr *laddr, + const struct net *net) { + struct sock *rc = __llc_lookup_listener(sap, laddr, net); static struct llc_addr null_addr; - struct sock *rc = __llc_lookup_listener(sap, laddr); if (!rc) - rc = __llc_lookup_listener(sap, &null_addr); + rc = __llc_lookup_listener(sap, &null_addr, net); return rc; } static struct sock *__llc_lookup(struct llc_sap *sap, struct llc_addr *daddr, - struct llc_addr *laddr) + struct llc_addr *laddr, + const struct net *net) { - struct sock *sk = __llc_lookup_established(sap, daddr, laddr); + struct sock *sk = __llc_lookup_established(sap, daddr, laddr, net); - return sk ? : llc_lookup_listener(sap, laddr); + return sk ? : llc_lookup_listener(sap, laddr, net); } /** @@ -776,7 +787,7 @@ void llc_conn_handler(struct llc_sap *sap, struct sk_buff *skb) llc_pdu_decode_da(skb, daddr.mac); llc_pdu_decode_dsap(skb, &daddr.lsap); - sk = __llc_lookup(sap, &saddr, &daddr); + sk = __llc_lookup(sap, &saddr, &daddr, dev_net(skb->dev)); if (!sk) goto drop; diff --git a/net/llc/llc_if.c b/net/llc/llc_if.c index dde9bf08a593..58a5f419adc6 100644 --- a/net/llc/llc_if.c +++ b/net/llc/llc_if.c @@ -92,7 +92,7 @@ int llc_establish_connection(struct sock *sk, const u8 *lmac, u8 *dmac, u8 dsap) daddr.lsap = dsap; memcpy(daddr.mac, dmac, sizeof(daddr.mac)); memcpy(laddr.mac, lmac, sizeof(laddr.mac)); - existing = llc_lookup_established(llc->sap, &daddr, &laddr); + existing = llc_lookup_established(llc->sap, &daddr, &laddr, sock_net(sk)); if (existing) { if (existing->sk_state == TCP_ESTABLISHED) { sk = existing; diff --git a/net/llc/llc_input.c b/net/llc/llc_input.c index c309b72a5877..7cac441862e2 100644 --- a/net/llc/llc_input.c +++ b/net/llc/llc_input.c @@ -163,9 +163,6 @@ int llc_rcv(struct sk_buff *skb, struct net_device *dev, void (*sta_handler)(struct sk_buff *skb); void (*sap_handler)(struct llc_sap *sap, struct sk_buff *skb); - if (!net_eq(dev_net(dev), &init_net)) - goto drop; - /* * When the interface is in promisc. mode, drop all the crap that it * receives, do not try to analyse it. diff --git a/net/llc/llc_sap.c b/net/llc/llc_sap.c index 6805ce43a055..116c0e479183 100644 --- a/net/llc/llc_sap.c +++ b/net/llc/llc_sap.c @@ -294,25 +294,29 @@ static void llc_sap_rcv(struct llc_sap *sap, struct sk_buff *skb, static inline bool llc_dgram_match(const struct llc_sap *sap, const struct llc_addr *laddr, - const struct sock *sk) + const struct sock *sk, + const struct net *net) { struct llc_sock *llc = llc_sk(sk); return sk->sk_type == SOCK_DGRAM && - llc->laddr.lsap == laddr->lsap && - ether_addr_equal(llc->laddr.mac, laddr->mac); + net_eq(sock_net(sk), net) && + llc->laddr.lsap == laddr->lsap && + ether_addr_equal(llc->laddr.mac, laddr->mac); } /** * llc_lookup_dgram - Finds dgram socket for the local sap/mac * @sap: SAP * @laddr: address of local LLC (MAC + SAP) + * @net: netns to look up a socket in * * Search socket list of the SAP and finds connection using the local * mac, and local sap. Returns pointer for socket found, %NULL otherwise. */ static struct sock *llc_lookup_dgram(struct llc_sap *sap, - const struct llc_addr *laddr) + const struct llc_addr *laddr, + const struct net *net) { struct sock *rc; struct hlist_nulls_node *node; @@ -322,12 +326,12 @@ static struct sock *llc_lookup_dgram(struct llc_sap *sap, rcu_read_lock_bh(); again: sk_nulls_for_each_rcu(rc, node, laddr_hb) { - if (llc_dgram_match(sap, laddr, rc)) { + if (llc_dgram_match(sap, laddr, rc, net)) { /* Extra checks required by SLAB_TYPESAFE_BY_RCU */ if (unlikely(!refcount_inc_not_zero(&rc->sk_refcnt))) goto again; if (unlikely(llc_sk(rc)->sap != sap || - !llc_dgram_match(sap, laddr, rc))) { + !llc_dgram_match(sap, laddr, rc, net))) { sock_put(rc); continue; } @@ -429,7 +433,7 @@ void llc_sap_handler(struct llc_sap *sap, struct sk_buff *skb) llc_sap_mcast(sap, &laddr, skb); kfree_skb(skb); } else { - struct sock *sk = llc_lookup_dgram(sap, &laddr); + struct sock *sk = llc_lookup_dgram(sap, &laddr, dev_net(skb->dev)); if (sk) { llc_sap_rcv(sap, skb, sk); sock_put(sk); diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 237f739da3ca..b9a4d3fd1d34 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -3685,8 +3685,6 @@ int nft_chain_validate(const struct nft_ctx *ctx, const struct nft_chain *chain) if (err < 0) return err; } - - cond_resched(); } return 0; @@ -3710,6 +3708,8 @@ static int nft_table_validate(struct net *net, const struct nft_table *table) err = nft_chain_validate(&ctx, chain); if (err < 0) return err; + + cond_resched(); } return 0; @@ -4087,6 +4087,8 @@ static int nf_tables_delrule(struct sk_buff *skb, const struct nfnl_info *info, list_for_each_entry(chain, &table->chains, list) { if (!nft_is_active_next(net, chain)) continue; + if (nft_chain_is_bound(chain)) + continue; ctx.chain = chain; err = nft_delrule_by_chain(&ctx); @@ -10517,6 +10519,9 @@ static int nft_verdict_init(const struct nft_ctx *ctx, struct nft_data *data, if (!tb[NFTA_VERDICT_CODE]) return -EINVAL; + + /* zero padding hole for memcmp */ + memset(data, 0, sizeof(*data)); data->verdict.code = ntohl(nla_get_be32(tb[NFTA_VERDICT_CODE])); switch (data->verdict.code) { @@ -10799,6 +10804,9 @@ static void __nft_release_table(struct net *net, struct nft_table *table) ctx.family = table->family; ctx.table = table; list_for_each_entry(chain, &table->chains, list) { + if (nft_chain_is_bound(chain)) + continue; + ctx.chain = chain; list_for_each_entry_safe(rule, nr, &chain->rules, list) { list_del(&rule->list); diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c index db526cb7a485..49915a2a58eb 100644 --- a/net/netfilter/nft_set_pipapo.c +++ b/net/netfilter/nft_set_pipapo.c @@ -1929,7 +1929,11 @@ static void nft_pipapo_remove(const struct net *net, const struct nft_set *set, int i, start, rules_fx; match_start = data; - match_end = (const u8 *)nft_set_ext_key_end(&e->ext)->data; + + if (nft_set_ext_exists(&e->ext, NFT_SET_EXT_KEY_END)) + match_end = (const u8 *)nft_set_ext_key_end(&e->ext)->data; + else + match_end = data; start = first_rule; rules_fx = rules_f0; diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c index 466c26df853a..382c7a71f81f 100644 --- a/net/sched/cls_bpf.c +++ b/net/sched/cls_bpf.c @@ -406,56 +406,6 @@ static int cls_bpf_prog_from_efd(struct nlattr **tb, struct cls_bpf_prog *prog, return 0; } -static int cls_bpf_set_parms(struct net *net, struct tcf_proto *tp, - struct cls_bpf_prog *prog, unsigned long base, - struct nlattr **tb, struct nlattr *est, u32 flags, - struct netlink_ext_ack *extack) -{ - bool is_bpf, is_ebpf, have_exts = false; - u32 gen_flags = 0; - int ret; - - is_bpf = tb[TCA_BPF_OPS_LEN] && tb[TCA_BPF_OPS]; - is_ebpf = tb[TCA_BPF_FD]; - if ((!is_bpf && !is_ebpf) || (is_bpf && is_ebpf)) - return -EINVAL; - - ret = tcf_exts_validate(net, tp, tb, est, &prog->exts, flags, - extack); - if (ret < 0) - return ret; - - if (tb[TCA_BPF_FLAGS]) { - u32 bpf_flags = nla_get_u32(tb[TCA_BPF_FLAGS]); - - if (bpf_flags & ~TCA_BPF_FLAG_ACT_DIRECT) - return -EINVAL; - - have_exts = bpf_flags & TCA_BPF_FLAG_ACT_DIRECT; - } - if (tb[TCA_BPF_FLAGS_GEN]) { - gen_flags = nla_get_u32(tb[TCA_BPF_FLAGS_GEN]); - if (gen_flags & ~CLS_BPF_SUPPORTED_GEN_FLAGS || - !tc_flags_valid(gen_flags)) - return -EINVAL; - } - - prog->exts_integrated = have_exts; - prog->gen_flags = gen_flags; - - ret = is_bpf ? cls_bpf_prog_from_ops(tb, prog) : - cls_bpf_prog_from_efd(tb, prog, gen_flags, tp); - if (ret < 0) - return ret; - - if (tb[TCA_BPF_CLASSID]) { - prog->res.classid = nla_get_u32(tb[TCA_BPF_CLASSID]); - tcf_bind_filter(tp, &prog->res, base); - } - - return 0; -} - static int cls_bpf_change(struct net *net, struct sk_buff *in_skb, struct tcf_proto *tp, unsigned long base, u32 handle, struct nlattr **tca, @@ -463,9 +413,12 @@ static int cls_bpf_change(struct net *net, struct sk_buff *in_skb, struct netlink_ext_ack *extack) { struct cls_bpf_head *head = rtnl_dereference(tp->root); + bool is_bpf, is_ebpf, have_exts = false; struct cls_bpf_prog *oldprog = *arg; struct nlattr *tb[TCA_BPF_MAX + 1]; + bool bound_to_filter = false; struct cls_bpf_prog *prog; + u32 gen_flags = 0; int ret; if (tca[TCA_OPTIONS] == NULL) @@ -504,11 +457,51 @@ static int cls_bpf_change(struct net *net, struct sk_buff *in_skb, goto errout; prog->handle = handle; - ret = cls_bpf_set_parms(net, tp, prog, base, tb, tca[TCA_RATE], flags, - extack); + is_bpf = tb[TCA_BPF_OPS_LEN] && tb[TCA_BPF_OPS]; + is_ebpf = tb[TCA_BPF_FD]; + if ((!is_bpf && !is_ebpf) || (is_bpf && is_ebpf)) { + ret = -EINVAL; + goto errout_idr; + } + + ret = tcf_exts_validate(net, tp, tb, tca[TCA_RATE], &prog->exts, + flags, extack); + if (ret < 0) + goto errout_idr; + + if (tb[TCA_BPF_FLAGS]) { + u32 bpf_flags = nla_get_u32(tb[TCA_BPF_FLAGS]); + + if (bpf_flags & ~TCA_BPF_FLAG_ACT_DIRECT) { + ret = -EINVAL; + goto errout_idr; + } + + have_exts = bpf_flags & TCA_BPF_FLAG_ACT_DIRECT; + } + if (tb[TCA_BPF_FLAGS_GEN]) { + gen_flags = nla_get_u32(tb[TCA_BPF_FLAGS_GEN]); + if (gen_flags & ~CLS_BPF_SUPPORTED_GEN_FLAGS || + !tc_flags_valid(gen_flags)) { + ret = -EINVAL; + goto errout_idr; + } + } + + prog->exts_integrated = have_exts; + prog->gen_flags = gen_flags; + + ret = is_bpf ? cls_bpf_prog_from_ops(tb, prog) : + cls_bpf_prog_from_efd(tb, prog, gen_flags, tp); if (ret < 0) goto errout_idr; + if (tb[TCA_BPF_CLASSID]) { + prog->res.classid = nla_get_u32(tb[TCA_BPF_CLASSID]); + tcf_bind_filter(tp, &prog->res, base); + bound_to_filter = true; + } + ret = cls_bpf_offload(tp, prog, oldprog, extack); if (ret) goto errout_parms; @@ -530,6 +523,8 @@ static int cls_bpf_change(struct net *net, struct sk_buff *in_skb, return 0; errout_parms: + if (bound_to_filter) + tcf_unbind_filter(tp, &prog->res); cls_bpf_free_parms(prog); errout_idr: if (!oldprog) diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index f2b0bc4142fe..8da9d039d964 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -2173,53 +2173,6 @@ static bool fl_needs_tc_skb_ext(const struct fl_flow_key *mask) return mask->meta.l2_miss; } -static int fl_set_parms(struct net *net, struct tcf_proto *tp, - struct cls_fl_filter *f, struct fl_flow_mask *mask, - unsigned long base, struct nlattr **tb, - struct nlattr *est, - struct fl_flow_tmplt *tmplt, - u32 flags, u32 fl_flags, - struct netlink_ext_ack *extack) -{ - int err; - - err = tcf_exts_validate_ex(net, tp, tb, est, &f->exts, flags, - fl_flags, extack); - if (err < 0) - return err; - - if (tb[TCA_FLOWER_CLASSID]) { - f->res.classid = nla_get_u32(tb[TCA_FLOWER_CLASSID]); - if (flags & TCA_ACT_FLAGS_NO_RTNL) - rtnl_lock(); - tcf_bind_filter(tp, &f->res, base); - if (flags & TCA_ACT_FLAGS_NO_RTNL) - rtnl_unlock(); - } - - err = fl_set_key(net, tb, &f->key, &mask->key, extack); - if (err) - return err; - - fl_mask_update_range(mask); - fl_set_masked_key(&f->mkey, &f->key, mask); - - if (!fl_mask_fits_tmplt(tmplt, mask)) { - NL_SET_ERR_MSG_MOD(extack, "Mask does not fit the template"); - return -EINVAL; - } - - /* Enable tc skb extension if filter matches on data extracted from - * this extension. - */ - if (fl_needs_tc_skb_ext(&mask->key)) { - f->needs_tc_skb_ext = 1; - tc_skb_ext_tc_enable(); - } - - return 0; -} - static int fl_ht_insert_unique(struct cls_fl_filter *fnew, struct cls_fl_filter *fold, bool *in_ht) @@ -2251,6 +2204,7 @@ static int fl_change(struct net *net, struct sk_buff *in_skb, struct cls_fl_head *head = fl_head_dereference(tp); bool rtnl_held = !(flags & TCA_ACT_FLAGS_NO_RTNL); struct cls_fl_filter *fold = *arg; + bool bound_to_filter = false; struct cls_fl_filter *fnew; struct fl_flow_mask *mask; struct nlattr **tb; @@ -2335,15 +2289,46 @@ static int fl_change(struct net *net, struct sk_buff *in_skb, if (err < 0) goto errout_idr; - err = fl_set_parms(net, tp, fnew, mask, base, tb, tca[TCA_RATE], - tp->chain->tmplt_priv, flags, fnew->flags, - extack); - if (err) + err = tcf_exts_validate_ex(net, tp, tb, tca[TCA_RATE], + &fnew->exts, flags, fnew->flags, + extack); + if (err < 0) goto errout_idr; + if (tb[TCA_FLOWER_CLASSID]) { + fnew->res.classid = nla_get_u32(tb[TCA_FLOWER_CLASSID]); + if (flags & TCA_ACT_FLAGS_NO_RTNL) + rtnl_lock(); + tcf_bind_filter(tp, &fnew->res, base); + if (flags & TCA_ACT_FLAGS_NO_RTNL) + rtnl_unlock(); + bound_to_filter = true; + } + + err = fl_set_key(net, tb, &fnew->key, &mask->key, extack); + if (err) + goto unbind_filter; + + fl_mask_update_range(mask); + fl_set_masked_key(&fnew->mkey, &fnew->key, mask); + + if (!fl_mask_fits_tmplt(tp->chain->tmplt_priv, mask)) { + NL_SET_ERR_MSG_MOD(extack, "Mask does not fit the template"); + err = -EINVAL; + goto unbind_filter; + } + + /* Enable tc skb extension if filter matches on data extracted from + * this extension. + */ + if (fl_needs_tc_skb_ext(&mask->key)) { + fnew->needs_tc_skb_ext = 1; + tc_skb_ext_tc_enable(); + } + err = fl_check_assign_mask(head, fnew, fold, mask); if (err) - goto errout_idr; + goto unbind_filter; err = fl_ht_insert_unique(fnew, fold, &in_ht); if (err) @@ -2434,6 +2419,16 @@ errout_hw: fnew->mask->filter_ht_params); errout_mask: fl_mask_put(head, fnew->mask); + +unbind_filter: + if (bound_to_filter) { + if (flags & TCA_ACT_FLAGS_NO_RTNL) + rtnl_lock(); + tcf_unbind_filter(tp, &fnew->res); + if (flags & TCA_ACT_FLAGS_NO_RTNL) + rtnl_unlock(); + } + errout_idr: if (!fold) idr_remove(&head->handle_idr, fnew->handle); diff --git a/net/sched/cls_matchall.c b/net/sched/cls_matchall.c index fa3bbd187eb9..c4ed11df6254 100644 --- a/net/sched/cls_matchall.c +++ b/net/sched/cls_matchall.c @@ -159,26 +159,6 @@ static const struct nla_policy mall_policy[TCA_MATCHALL_MAX + 1] = { [TCA_MATCHALL_FLAGS] = { .type = NLA_U32 }, }; -static int mall_set_parms(struct net *net, struct tcf_proto *tp, - struct cls_mall_head *head, - unsigned long base, struct nlattr **tb, - struct nlattr *est, u32 flags, u32 fl_flags, - struct netlink_ext_ack *extack) -{ - int err; - - err = tcf_exts_validate_ex(net, tp, tb, est, &head->exts, flags, - fl_flags, extack); - if (err < 0) - return err; - - if (tb[TCA_MATCHALL_CLASSID]) { - head->res.classid = nla_get_u32(tb[TCA_MATCHALL_CLASSID]); - tcf_bind_filter(tp, &head->res, base); - } - return 0; -} - static int mall_change(struct net *net, struct sk_buff *in_skb, struct tcf_proto *tp, unsigned long base, u32 handle, struct nlattr **tca, @@ -187,6 +167,7 @@ static int mall_change(struct net *net, struct sk_buff *in_skb, { struct cls_mall_head *head = rtnl_dereference(tp->root); struct nlattr *tb[TCA_MATCHALL_MAX + 1]; + bool bound_to_filter = false; struct cls_mall_head *new; u32 userflags = 0; int err; @@ -226,11 +207,17 @@ static int mall_change(struct net *net, struct sk_buff *in_skb, goto err_alloc_percpu; } - err = mall_set_parms(net, tp, new, base, tb, tca[TCA_RATE], - flags, new->flags, extack); - if (err) + err = tcf_exts_validate_ex(net, tp, tb, tca[TCA_RATE], + &new->exts, flags, new->flags, extack); + if (err < 0) goto err_set_parms; + if (tb[TCA_MATCHALL_CLASSID]) { + new->res.classid = nla_get_u32(tb[TCA_MATCHALL_CLASSID]); + tcf_bind_filter(tp, &new->res, base); + bound_to_filter = true; + } + if (!tc_skip_hw(new->flags)) { err = mall_replace_hw_filter(tp, new, (unsigned long)new, extack); @@ -246,6 +233,8 @@ static int mall_change(struct net *net, struct sk_buff *in_skb, return 0; err_replace_hw_filter: + if (bound_to_filter) + tcf_unbind_filter(tp, &new->res); err_set_parms: free_percpu(new->pf); err_alloc_percpu: diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c index d15d50de7980..5abf31e432ca 100644 --- a/net/sched/cls_u32.c +++ b/net/sched/cls_u32.c @@ -712,8 +712,23 @@ static const struct nla_policy u32_policy[TCA_U32_MAX + 1] = { [TCA_U32_FLAGS] = { .type = NLA_U32 }, }; +static void u32_unbind_filter(struct tcf_proto *tp, struct tc_u_knode *n, + struct nlattr **tb) +{ + if (tb[TCA_U32_CLASSID]) + tcf_unbind_filter(tp, &n->res); +} + +static void u32_bind_filter(struct tcf_proto *tp, struct tc_u_knode *n, + unsigned long base, struct nlattr **tb) +{ + if (tb[TCA_U32_CLASSID]) { + n->res.classid = nla_get_u32(tb[TCA_U32_CLASSID]); + tcf_bind_filter(tp, &n->res, base); + } +} + static int u32_set_parms(struct net *net, struct tcf_proto *tp, - unsigned long base, struct tc_u_knode *n, struct nlattr **tb, struct nlattr *est, u32 flags, u32 fl_flags, struct netlink_ext_ack *extack) @@ -760,10 +775,6 @@ static int u32_set_parms(struct net *net, struct tcf_proto *tp, if (ht_old) ht_old->refcnt--; } - if (tb[TCA_U32_CLASSID]) { - n->res.classid = nla_get_u32(tb[TCA_U32_CLASSID]); - tcf_bind_filter(tp, &n->res, base); - } if (ifindex >= 0) n->ifindex = ifindex; @@ -903,17 +914,27 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, if (!new) return -ENOMEM; - err = u32_set_parms(net, tp, base, new, tb, - tca[TCA_RATE], flags, new->flags, - extack); + err = u32_set_parms(net, tp, new, tb, tca[TCA_RATE], + flags, new->flags, extack); if (err) { __u32_destroy_key(new); return err; } + u32_bind_filter(tp, new, base, tb); + err = u32_replace_hw_knode(tp, new, flags, extack); if (err) { + u32_unbind_filter(tp, new, tb); + + if (tb[TCA_U32_LINK]) { + struct tc_u_hnode *ht_old; + + ht_old = rtnl_dereference(n->ht_down); + if (ht_old) + ht_old->refcnt++; + } __u32_destroy_key(new); return err; } @@ -1074,15 +1095,18 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, } #endif - err = u32_set_parms(net, tp, base, n, tb, tca[TCA_RATE], + err = u32_set_parms(net, tp, n, tb, tca[TCA_RATE], flags, n->flags, extack); + + u32_bind_filter(tp, n, base, tb); + if (err == 0) { struct tc_u_knode __rcu **ins; struct tc_u_knode *pins; err = u32_replace_hw_knode(tp, n, flags, extack); if (err) - goto errhw; + goto errunbind; if (!tc_in_hw(n->flags)) n->flags |= TCA_CLS_FLAGS_NOT_IN_HW; @@ -1100,7 +1124,9 @@ static int u32_change(struct net *net, struct sk_buff *in_skb, return 0; } -errhw: +errunbind: + u32_unbind_filter(tp, n, tb); + #ifdef CONFIG_CLS_U32_MARK free_percpu(n->pcpu_success); #endif diff --git a/scripts/kallsyms.c b/scripts/kallsyms.c index d387c9381650..16c87938b316 100644 --- a/scripts/kallsyms.c +++ b/scripts/kallsyms.c @@ -349,10 +349,10 @@ static void cleanup_symbol_name(char *s) * ASCII[_] = 5f * ASCII[a-z] = 61,7a * - * As above, replacing '.' with '\0' does not affect the main sorting, - * but it helps us with subsorting. + * As above, replacing the first '.' in ".llvm." with '\0' does not + * affect the main sorting, but it helps us with subsorting. */ - p = strchr(s, '.'); + p = strstr(s, ".llvm."); if (p) *p = '\0'; } diff --git a/security/keys/request_key.c b/security/keys/request_key.c index 07a0ef2baacd..a7673ad86d18 100644 --- a/security/keys/request_key.c +++ b/security/keys/request_key.c @@ -401,17 +401,21 @@ static int construct_alloc_key(struct keyring_search_context *ctx, set_bit(KEY_FLAG_USER_CONSTRUCT, &key->flags); if (dest_keyring) { - ret = __key_link_lock(dest_keyring, &ctx->index_key); + ret = __key_link_lock(dest_keyring, &key->index_key); if (ret < 0) goto link_lock_failed; - ret = __key_link_begin(dest_keyring, &ctx->index_key, &edit); - if (ret < 0) - goto link_prealloc_failed; } - /* attach the key to the destination keyring under lock, but we do need + /* + * Attach the key to the destination keyring under lock, but we do need * to do another check just in case someone beat us to it whilst we - * waited for locks */ + * waited for locks. + * + * The caller might specify a comparison function which looks for keys + * that do not exactly match but are still equivalent from the caller's + * perspective. The __key_link_begin() operation must be done only after + * an actual key is determined. + */ mutex_lock(&key_construction_mutex); rcu_read_lock(); @@ -420,12 +424,16 @@ static int construct_alloc_key(struct keyring_search_context *ctx, if (!IS_ERR(key_ref)) goto key_already_present; - if (dest_keyring) + if (dest_keyring) { + ret = __key_link_begin(dest_keyring, &key->index_key, &edit); + if (ret < 0) + goto link_alloc_failed; __key_link(dest_keyring, key, &edit); + } mutex_unlock(&key_construction_mutex); if (dest_keyring) - __key_link_end(dest_keyring, &ctx->index_key, edit); + __key_link_end(dest_keyring, &key->index_key, edit); mutex_unlock(&user->cons_lock); *_key = key; kleave(" = 0 [%d]", key_serial(key)); @@ -438,10 +446,13 @@ key_already_present: mutex_unlock(&key_construction_mutex); key = key_ref_to_ptr(key_ref); if (dest_keyring) { + ret = __key_link_begin(dest_keyring, &key->index_key, &edit); + if (ret < 0) + goto link_alloc_failed_unlocked; ret = __key_link_check_live_key(dest_keyring, key); if (ret == 0) __key_link(dest_keyring, key, &edit); - __key_link_end(dest_keyring, &ctx->index_key, edit); + __key_link_end(dest_keyring, &key->index_key, edit); if (ret < 0) goto link_check_failed; } @@ -456,8 +467,10 @@ link_check_failed: kleave(" = %d [linkcheck]", ret); return ret; -link_prealloc_failed: - __key_link_end(dest_keyring, &ctx->index_key, edit); +link_alloc_failed: + mutex_unlock(&key_construction_mutex); +link_alloc_failed_unlocked: + __key_link_end(dest_keyring, &key->index_key, edit); link_lock_failed: mutex_unlock(&user->cons_lock); key_put(key); diff --git a/security/keys/trusted-keys/trusted_tpm2.c b/security/keys/trusted-keys/trusted_tpm2.c index 2b2c8eb258d5..bc700f85f80b 100644 --- a/security/keys/trusted-keys/trusted_tpm2.c +++ b/security/keys/trusted-keys/trusted_tpm2.c @@ -186,7 +186,7 @@ int tpm2_key_priv(void *context, size_t hdrlen, } /** - * tpm_buf_append_auth() - append TPMS_AUTH_COMMAND to the buffer. + * tpm2_buf_append_auth() - append TPMS_AUTH_COMMAND to the buffer. * * @buf: an allocated tpm_buf instance * @session_handle: session handle diff --git a/tools/arch/arm64/include/asm/cputype.h b/tools/arch/arm64/include/asm/cputype.h index 683ca3af4084..5f6f84837a49 100644 --- a/tools/arch/arm64/include/asm/cputype.h +++ b/tools/arch/arm64/include/asm/cputype.h @@ -126,6 +126,10 @@ #define APPLE_CPU_PART_M1_FIRESTORM_MAX 0x029 #define APPLE_CPU_PART_M2_BLIZZARD 0x032 #define APPLE_CPU_PART_M2_AVALANCHE 0x033 +#define APPLE_CPU_PART_M2_BLIZZARD_PRO 0x034 +#define APPLE_CPU_PART_M2_AVALANCHE_PRO 0x035 +#define APPLE_CPU_PART_M2_BLIZZARD_MAX 0x038 +#define APPLE_CPU_PART_M2_AVALANCHE_MAX 0x039 #define AMPERE_CPU_PART_AMPERE1 0xAC3 @@ -181,6 +185,10 @@ #define MIDR_APPLE_M1_FIRESTORM_MAX MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M1_FIRESTORM_MAX) #define MIDR_APPLE_M2_BLIZZARD MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M2_BLIZZARD) #define MIDR_APPLE_M2_AVALANCHE MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M2_AVALANCHE) +#define MIDR_APPLE_M2_BLIZZARD_PRO MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M2_BLIZZARD_PRO) +#define MIDR_APPLE_M2_AVALANCHE_PRO MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M2_AVALANCHE_PRO) +#define MIDR_APPLE_M2_BLIZZARD_MAX MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M2_BLIZZARD_MAX) +#define MIDR_APPLE_M2_AVALANCHE_MAX MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M2_AVALANCHE_MAX) #define MIDR_AMPERE1 MIDR_CPU_MODEL(ARM_CPU_IMP_AMPERE, AMPERE_CPU_PART_AMPERE1) /* Fujitsu Erratum 010001 affects A64FX 1.0 and 1.1, (v0r0 and v1r0) */ diff --git a/tools/build/feature/Makefile b/tools/build/feature/Makefile index 6654b1a35ab3..f0c5de018a95 100644 --- a/tools/build/feature/Makefile +++ b/tools/build/feature/Makefile @@ -208,7 +208,7 @@ $(OUTPUT)test-libtraceevent.bin: $(BUILD) -ltraceevent $(OUTPUT)test-libtracefs.bin: - $(BUILD) -ltracefs + $(BUILD) $(shell $(PKG_CONFIG) --cflags libtraceevent 2>/dev/null) -ltracefs $(OUTPUT)test-libcrypto.bin: $(BUILD) -lcrypto diff --git a/tools/include/uapi/asm-generic/unistd.h b/tools/include/uapi/asm-generic/unistd.h index dd7d8e10f16d..fd6c1cb585db 100644 --- a/tools/include/uapi/asm-generic/unistd.h +++ b/tools/include/uapi/asm-generic/unistd.h @@ -817,8 +817,11 @@ __SYSCALL(__NR_futex_waitv, sys_futex_waitv) #define __NR_set_mempolicy_home_node 450 __SYSCALL(__NR_set_mempolicy_home_node, sys_set_mempolicy_home_node) +#define __NR_cachestat 451 +__SYSCALL(__NR_cachestat, sys_cachestat) + #undef __NR_syscalls -#define __NR_syscalls 451 +#define __NR_syscalls 452 /* * 32 bit systems traditionally used different diff --git a/tools/include/uapi/drm/i915_drm.h b/tools/include/uapi/drm/i915_drm.h index dba7c5a5b25e..7000e5910a1d 100644 --- a/tools/include/uapi/drm/i915_drm.h +++ b/tools/include/uapi/drm/i915_drm.h @@ -280,7 +280,16 @@ enum drm_i915_pmu_engine_sample { #define I915_PMU_ENGINE_SEMA(class, instance) \ __I915_PMU_ENGINE(class, instance, I915_SAMPLE_SEMA) -#define __I915_PMU_OTHER(x) (__I915_PMU_ENGINE(0xff, 0xff, 0xf) + 1 + (x)) +/* + * Top 4 bits of every non-engine counter are GT id. + */ +#define __I915_PMU_GT_SHIFT (60) + +#define ___I915_PMU_OTHER(gt, x) \ + (((__u64)__I915_PMU_ENGINE(0xff, 0xff, 0xf) + 1 + (x)) | \ + ((__u64)(gt) << __I915_PMU_GT_SHIFT)) + +#define __I915_PMU_OTHER(x) ___I915_PMU_OTHER(0, x) #define I915_PMU_ACTUAL_FREQUENCY __I915_PMU_OTHER(0) #define I915_PMU_REQUESTED_FREQUENCY __I915_PMU_OTHER(1) @@ -290,6 +299,12 @@ enum drm_i915_pmu_engine_sample { #define I915_PMU_LAST /* Deprecated - do not use */ I915_PMU_RC6_RESIDENCY +#define __I915_PMU_ACTUAL_FREQUENCY(gt) ___I915_PMU_OTHER(gt, 0) +#define __I915_PMU_REQUESTED_FREQUENCY(gt) ___I915_PMU_OTHER(gt, 1) +#define __I915_PMU_INTERRUPTS(gt) ___I915_PMU_OTHER(gt, 2) +#define __I915_PMU_RC6_RESIDENCY(gt) ___I915_PMU_OTHER(gt, 3) +#define __I915_PMU_SOFTWARE_GT_AWAKE_TIME(gt) ___I915_PMU_OTHER(gt, 4) + /* Each region is a minimum of 16k, and there are at most 255 of them. */ #define I915_NR_TEX_REGIONS 255 /* table size 2k - maximum due to use @@ -659,7 +674,8 @@ typedef struct drm_i915_irq_wait { * If the IOCTL is successful, the returned parameter will be set to one of the * following values: * * 0 if HuC firmware load is not complete, - * * 1 if HuC firmware is authenticated and running. + * * 1 if HuC firmware is loaded and fully authenticated, + * * 2 if HuC firmware is loaded and authenticated for clear media only */ #define I915_PARAM_HUC_STATUS 42 @@ -771,6 +787,25 @@ typedef struct drm_i915_irq_wait { */ #define I915_PARAM_OA_TIMESTAMP_FREQUENCY 57 +/* + * Query the status of PXP support in i915. + * + * The query can fail in the following scenarios with the listed error codes: + * -ENODEV = PXP support is not available on the GPU device or in the + * kernel due to missing component drivers or kernel configs. + * + * If the IOCTL is successful, the returned parameter will be set to one of + * the following values: + * 1 = PXP feature is supported and is ready for use. + * 2 = PXP feature is supported but should be ready soon (pending + * initialization of non-i915 system dependencies). + * + * NOTE: When param is supported (positive return values), user space should + * still refer to the GEM PXP context-creation UAPI header specs to be + * aware of possible failure due to system state machine at the time. + */ +#define I915_PARAM_PXP_STATUS 58 + /* Must be kept compact -- no holes and well documented */ /** @@ -2096,6 +2131,21 @@ struct drm_i915_gem_context_param { * * -ENODEV: feature not available * -EPERM: trying to mark a recoverable or not bannable context as protected + * -ENXIO: A dependency such as a component driver or firmware is not yet + * loaded so user space may need to attempt again. Depending on the + * device, this error may be reported if protected context creation is + * attempted very early after kernel start because the internal timeout + * waiting for such dependencies is not guaranteed to be larger than + * required (numbers differ depending on system and kernel config): + * - ADL/RPL: dependencies may take up to 3 seconds from kernel start + * while context creation internal timeout is 250 milisecs + * - MTL: dependencies may take up to 8 seconds from kernel start + * while context creation internal timeout is 250 milisecs + * NOTE: such dependencies happen once, so a subsequent call to create a + * protected context after a prior successful call will not experience + * such timeouts and will not return -ENXIO (unless the driver is reloaded, + * or, depending on the device, resumes from a suspended state). + * -EIO: The firmware did not succeed in creating the protected context. */ #define I915_CONTEXT_PARAM_PROTECTED_CONTENT 0xd /* Must be kept compact -- no holes and well documented */ @@ -3630,9 +3680,13 @@ struct drm_i915_gem_create_ext { * * For I915_GEM_CREATE_EXT_PROTECTED_CONTENT usage see * struct drm_i915_gem_create_ext_protected_content. + * + * For I915_GEM_CREATE_EXT_SET_PAT usage see + * struct drm_i915_gem_create_ext_set_pat. */ #define I915_GEM_CREATE_EXT_MEMORY_REGIONS 0 #define I915_GEM_CREATE_EXT_PROTECTED_CONTENT 1 +#define I915_GEM_CREATE_EXT_SET_PAT 2 __u64 extensions; }; @@ -3747,6 +3801,43 @@ struct drm_i915_gem_create_ext_protected_content { __u32 flags; }; +/** + * struct drm_i915_gem_create_ext_set_pat - The + * I915_GEM_CREATE_EXT_SET_PAT extension. + * + * If this extension is provided, the specified caching policy (PAT index) is + * applied to the buffer object. + * + * Below is an example on how to create an object with specific caching policy: + * + * .. code-block:: C + * + * struct drm_i915_gem_create_ext_set_pat set_pat_ext = { + * .base = { .name = I915_GEM_CREATE_EXT_SET_PAT }, + * .pat_index = 0, + * }; + * struct drm_i915_gem_create_ext create_ext = { + * .size = PAGE_SIZE, + * .extensions = (uintptr_t)&set_pat_ext, + * }; + * + * int err = ioctl(fd, DRM_IOCTL_I915_GEM_CREATE_EXT, &create_ext); + * if (err) ... + */ +struct drm_i915_gem_create_ext_set_pat { + /** @base: Extension link. See struct i915_user_extension. */ + struct i915_user_extension base; + /** + * @pat_index: PAT index to be set + * PAT index is a bit field in Page Table Entry to control caching + * behaviors for GPU accesses. The definition of PAT index is + * platform dependent and can be found in hardware specifications, + */ + __u32 pat_index; + /** @rsvd: reserved for future use */ + __u32 rsvd; +}; + /* ID of the protected content session managed by i915 when PXP is active */ #define I915_PROTECTED_CONTENT_DEFAULT_SESSION 0xf diff --git a/tools/include/uapi/linux/fcntl.h b/tools/include/uapi/linux/fcntl.h index e8c07da58c9f..6c80f96049bd 100644 --- a/tools/include/uapi/linux/fcntl.h +++ b/tools/include/uapi/linux/fcntl.h @@ -112,4 +112,9 @@ #define AT_RECURSIVE 0x8000 /* Apply to the entire subtree */ +/* Flags for name_to_handle_at(2). We reuse AT_ flag space to save bits... */ +#define AT_HANDLE_FID AT_REMOVEDIR /* file handle is needed to + compare object identity and may not + be usable to open_by_handle_at(2) */ + #endif /* _UAPI_LINUX_FCNTL_H */ diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h index 737318b1c1d9..f089ab290978 100644 --- a/tools/include/uapi/linux/kvm.h +++ b/tools/include/uapi/linux/kvm.h @@ -1190,6 +1190,8 @@ struct kvm_ppc_resize_hpt { #define KVM_CAP_DIRTY_LOG_RING_WITH_BITMAP 225 #define KVM_CAP_PMU_EVENT_MASKED_EVENTS 226 #define KVM_CAP_COUNTER_OFFSET 227 +#define KVM_CAP_ARM_EAGER_SPLIT_CHUNK_SIZE 228 +#define KVM_CAP_ARM_SUPPORTED_BLOCK_SIZES 229 #ifdef KVM_CAP_IRQ_ROUTING @@ -1442,6 +1444,8 @@ enum kvm_device_type { #define KVM_DEV_TYPE_XIVE KVM_DEV_TYPE_XIVE KVM_DEV_TYPE_ARM_PV_TIME, #define KVM_DEV_TYPE_ARM_PV_TIME KVM_DEV_TYPE_ARM_PV_TIME + KVM_DEV_TYPE_RISCV_AIA, +#define KVM_DEV_TYPE_RISCV_AIA KVM_DEV_TYPE_RISCV_AIA KVM_DEV_TYPE_MAX, }; @@ -1613,7 +1617,7 @@ struct kvm_s390_ucas_mapping { #define KVM_GET_DEBUGREGS _IOR(KVMIO, 0xa1, struct kvm_debugregs) #define KVM_SET_DEBUGREGS _IOW(KVMIO, 0xa2, struct kvm_debugregs) /* - * vcpu version available with KVM_ENABLE_CAP + * vcpu version available with KVM_CAP_ENABLE_CAP * vm version available with KVM_CAP_ENABLE_CAP_VM */ #define KVM_ENABLE_CAP _IOW(KVMIO, 0xa3, struct kvm_enable_cap) diff --git a/tools/include/uapi/linux/mman.h b/tools/include/uapi/linux/mman.h index f55bc680b5b0..a246e11988d5 100644 --- a/tools/include/uapi/linux/mman.h +++ b/tools/include/uapi/linux/mman.h @@ -4,6 +4,7 @@ #include <asm/mman.h> #include <asm-generic/hugetlb_encode.h> +#include <linux/types.h> #define MREMAP_MAYMOVE 1 #define MREMAP_FIXED 2 @@ -41,4 +42,17 @@ #define MAP_HUGE_2GB HUGETLB_FLAG_ENCODE_2GB #define MAP_HUGE_16GB HUGETLB_FLAG_ENCODE_16GB +struct cachestat_range { + __u64 off; + __u64 len; +}; + +struct cachestat { + __u64 nr_cache; + __u64 nr_dirty; + __u64 nr_writeback; + __u64 nr_evicted; + __u64 nr_recently_evicted; +}; + #endif /* _UAPI_LINUX_MMAN_H */ diff --git a/tools/include/uapi/linux/mount.h b/tools/include/uapi/linux/mount.h index 4d93967f8aea..8eb0d7b758d2 100644 --- a/tools/include/uapi/linux/mount.h +++ b/tools/include/uapi/linux/mount.h @@ -74,7 +74,8 @@ #define MOVE_MOUNT_T_AUTOMOUNTS 0x00000020 /* Follow automounts on to path */ #define MOVE_MOUNT_T_EMPTY_PATH 0x00000040 /* Empty to path permitted */ #define MOVE_MOUNT_SET_GROUP 0x00000100 /* Set sharing group instead */ -#define MOVE_MOUNT__MASK 0x00000177 +#define MOVE_MOUNT_BENEATH 0x00000200 /* Mount beneath top mount */ +#define MOVE_MOUNT__MASK 0x00000377 /* * fsopen() flags. diff --git a/tools/include/uapi/linux/prctl.h b/tools/include/uapi/linux/prctl.h index f23d9a16507f..3c36aeade991 100644 --- a/tools/include/uapi/linux/prctl.h +++ b/tools/include/uapi/linux/prctl.h @@ -294,4 +294,15 @@ struct prctl_mm_map { #define PR_SET_MEMORY_MERGE 67 #define PR_GET_MEMORY_MERGE 68 + +#define PR_RISCV_V_SET_CONTROL 69 +#define PR_RISCV_V_GET_CONTROL 70 +# define PR_RISCV_V_VSTATE_CTRL_DEFAULT 0 +# define PR_RISCV_V_VSTATE_CTRL_OFF 1 +# define PR_RISCV_V_VSTATE_CTRL_ON 2 +# define PR_RISCV_V_VSTATE_CTRL_INHERIT (1 << 4) +# define PR_RISCV_V_VSTATE_CTRL_CUR_MASK 0x3 +# define PR_RISCV_V_VSTATE_CTRL_NEXT_MASK 0xc +# define PR_RISCV_V_VSTATE_CTRL_MASK 0x1f + #endif /* _LINUX_PRCTL_H */ diff --git a/tools/include/uapi/linux/vhost.h b/tools/include/uapi/linux/vhost.h index 92e1b700b51c..f5c48b61ab62 100644 --- a/tools/include/uapi/linux/vhost.h +++ b/tools/include/uapi/linux/vhost.h @@ -45,6 +45,25 @@ #define VHOST_SET_LOG_BASE _IOW(VHOST_VIRTIO, 0x04, __u64) /* Specify an eventfd file descriptor to signal on log write. */ #define VHOST_SET_LOG_FD _IOW(VHOST_VIRTIO, 0x07, int) +/* By default, a device gets one vhost_worker that its virtqueues share. This + * command allows the owner of the device to create an additional vhost_worker + * for the device. It can later be bound to 1 or more of its virtqueues using + * the VHOST_ATTACH_VRING_WORKER command. + * + * This must be called after VHOST_SET_OWNER and the caller must be the owner + * of the device. The new thread will inherit caller's cgroups and namespaces, + * and will share the caller's memory space. The new thread will also be + * counted against the caller's RLIMIT_NPROC value. + * + * The worker's ID used in other commands will be returned in + * vhost_worker_state. + */ +#define VHOST_NEW_WORKER _IOR(VHOST_VIRTIO, 0x8, struct vhost_worker_state) +/* Free a worker created with VHOST_NEW_WORKER if it's not attached to any + * virtqueue. If userspace is not able to call this for workers its created, + * the kernel will free all the device's workers when the device is closed. + */ +#define VHOST_FREE_WORKER _IOW(VHOST_VIRTIO, 0x9, struct vhost_worker_state) /* Ring setup. */ /* Set number of descriptors in ring. This parameter can not @@ -70,6 +89,18 @@ #define VHOST_VRING_BIG_ENDIAN 1 #define VHOST_SET_VRING_ENDIAN _IOW(VHOST_VIRTIO, 0x13, struct vhost_vring_state) #define VHOST_GET_VRING_ENDIAN _IOW(VHOST_VIRTIO, 0x14, struct vhost_vring_state) +/* Attach a vhost_worker created with VHOST_NEW_WORKER to one of the device's + * virtqueues. + * + * This will replace the virtqueue's existing worker. If the replaced worker + * is no longer attached to any virtqueues, it can be freed with + * VHOST_FREE_WORKER. + */ +#define VHOST_ATTACH_VRING_WORKER _IOW(VHOST_VIRTIO, 0x15, \ + struct vhost_vring_worker) +/* Return the vring worker's ID */ +#define VHOST_GET_VRING_WORKER _IOWR(VHOST_VIRTIO, 0x16, \ + struct vhost_vring_worker) /* The following ioctls use eventfd file descriptors to signal and poll * for events. */ diff --git a/tools/include/uapi/sound/asound.h b/tools/include/uapi/sound/asound.h index 0aa955aa8246..f9939da41122 100644 --- a/tools/include/uapi/sound/asound.h +++ b/tools/include/uapi/sound/asound.h @@ -274,6 +274,7 @@ typedef int __bitwise snd_pcm_subformat_t; #define SNDRV_PCM_INFO_DOUBLE 0x00000004 /* Double buffering needed for PCM start/stop */ #define SNDRV_PCM_INFO_BATCH 0x00000010 /* double buffering */ #define SNDRV_PCM_INFO_SYNC_APPLPTR 0x00000020 /* need the explicit sync of appl_ptr update */ +#define SNDRV_PCM_INFO_PERFECT_DRAIN 0x00000040 /* silencing at the end of stream is not required */ #define SNDRV_PCM_INFO_INTERLEAVED 0x00000100 /* channels are interleaved */ #define SNDRV_PCM_INFO_NONINTERLEAVED 0x00000200 /* channels are not interleaved */ #define SNDRV_PCM_INFO_COMPLEX 0x00000400 /* complex frame organization (mmap only) */ @@ -383,6 +384,9 @@ typedef int snd_pcm_hw_param_t; #define SNDRV_PCM_HW_PARAMS_NORESAMPLE (1<<0) /* avoid rate resampling */ #define SNDRV_PCM_HW_PARAMS_EXPORT_BUFFER (1<<1) /* export buffer */ #define SNDRV_PCM_HW_PARAMS_NO_PERIOD_WAKEUP (1<<2) /* disable period wakeups */ +#define SNDRV_PCM_HW_PARAMS_NO_DRAIN_SILENCE (1<<3) /* suppress drain with the filling + * of the silence samples + */ struct snd_interval { unsigned int min, max; @@ -708,7 +712,7 @@ enum { * Raw MIDI section - /dev/snd/midi?? */ -#define SNDRV_RAWMIDI_VERSION SNDRV_PROTOCOL_VERSION(2, 0, 2) +#define SNDRV_RAWMIDI_VERSION SNDRV_PROTOCOL_VERSION(2, 0, 4) enum { SNDRV_RAWMIDI_STREAM_OUTPUT = 0, @@ -719,6 +723,7 @@ enum { #define SNDRV_RAWMIDI_INFO_OUTPUT 0x00000001 #define SNDRV_RAWMIDI_INFO_INPUT 0x00000002 #define SNDRV_RAWMIDI_INFO_DUPLEX 0x00000004 +#define SNDRV_RAWMIDI_INFO_UMP 0x00000008 struct snd_rawmidi_info { unsigned int device; /* RO/WR (control): device number */ @@ -779,6 +784,72 @@ struct snd_rawmidi_status { }; #endif +/* UMP EP info flags */ +#define SNDRV_UMP_EP_INFO_STATIC_BLOCKS 0x01 + +/* UMP EP Protocol / JRTS capability bits */ +#define SNDRV_UMP_EP_INFO_PROTO_MIDI_MASK 0x0300 +#define SNDRV_UMP_EP_INFO_PROTO_MIDI1 0x0100 /* MIDI 1.0 */ +#define SNDRV_UMP_EP_INFO_PROTO_MIDI2 0x0200 /* MIDI 2.0 */ +#define SNDRV_UMP_EP_INFO_PROTO_JRTS_MASK 0x0003 +#define SNDRV_UMP_EP_INFO_PROTO_JRTS_TX 0x0001 /* JRTS Transmit */ +#define SNDRV_UMP_EP_INFO_PROTO_JRTS_RX 0x0002 /* JRTS Receive */ + +/* UMP Endpoint information */ +struct snd_ump_endpoint_info { + int card; /* card number */ + int device; /* device number */ + unsigned int flags; /* additional info */ + unsigned int protocol_caps; /* protocol capabilities */ + unsigned int protocol; /* current protocol */ + unsigned int num_blocks; /* # of function blocks */ + unsigned short version; /* UMP major/minor version */ + unsigned short family_id; /* MIDI device family ID */ + unsigned short model_id; /* MIDI family model ID */ + unsigned int manufacturer_id; /* MIDI manufacturer ID */ + unsigned char sw_revision[4]; /* software revision */ + unsigned short padding; + unsigned char name[128]; /* endpoint name string */ + unsigned char product_id[128]; /* unique product id string */ + unsigned char reserved[32]; +} __packed; + +/* UMP direction */ +#define SNDRV_UMP_DIR_INPUT 0x01 +#define SNDRV_UMP_DIR_OUTPUT 0x02 +#define SNDRV_UMP_DIR_BIDIRECTION 0x03 + +/* UMP block info flags */ +#define SNDRV_UMP_BLOCK_IS_MIDI1 (1U << 0) /* MIDI 1.0 port w/o restrict */ +#define SNDRV_UMP_BLOCK_IS_LOWSPEED (1U << 1) /* 31.25Kbps B/W MIDI1 port */ + +/* UMP block user-interface hint */ +#define SNDRV_UMP_BLOCK_UI_HINT_UNKNOWN 0x00 +#define SNDRV_UMP_BLOCK_UI_HINT_RECEIVER 0x01 +#define SNDRV_UMP_BLOCK_UI_HINT_SENDER 0x02 +#define SNDRV_UMP_BLOCK_UI_HINT_BOTH 0x03 + +/* UMP groups and blocks */ +#define SNDRV_UMP_MAX_GROUPS 16 +#define SNDRV_UMP_MAX_BLOCKS 32 + +/* UMP Block information */ +struct snd_ump_block_info { + int card; /* card number */ + int device; /* device number */ + unsigned char block_id; /* block ID (R/W) */ + unsigned char direction; /* UMP direction */ + unsigned char active; /* Activeness */ + unsigned char first_group; /* first group ID */ + unsigned char num_groups; /* number of groups */ + unsigned char midi_ci_version; /* MIDI-CI support version */ + unsigned char sysex8_streams; /* max number of sysex8 streams */ + unsigned char ui_hint; /* user interface hint */ + unsigned int flags; /* various info flags */ + unsigned char name[128]; /* block name string */ + unsigned char reserved[32]; +} __packed; + #define SNDRV_RAWMIDI_IOCTL_PVERSION _IOR('W', 0x00, int) #define SNDRV_RAWMIDI_IOCTL_INFO _IOR('W', 0x01, struct snd_rawmidi_info) #define SNDRV_RAWMIDI_IOCTL_USER_PVERSION _IOW('W', 0x02, int) @@ -786,6 +857,9 @@ struct snd_rawmidi_status { #define SNDRV_RAWMIDI_IOCTL_STATUS _IOWR('W', 0x20, struct snd_rawmidi_status) #define SNDRV_RAWMIDI_IOCTL_DROP _IOW('W', 0x30, int) #define SNDRV_RAWMIDI_IOCTL_DRAIN _IOW('W', 0x31, int) +/* Additional ioctls for UMP rawmidi devices */ +#define SNDRV_UMP_IOCTL_ENDPOINT_INFO _IOR('W', 0x40, struct snd_ump_endpoint_info) +#define SNDRV_UMP_IOCTL_BLOCK_INFO _IOR('W', 0x41, struct snd_ump_block_info) /* * Timer section - /dev/snd/timer @@ -961,7 +1035,7 @@ struct snd_timer_tread { * * ****************************************************************************/ -#define SNDRV_CTL_VERSION SNDRV_PROTOCOL_VERSION(2, 0, 8) +#define SNDRV_CTL_VERSION SNDRV_PROTOCOL_VERSION(2, 0, 9) struct snd_ctl_card_info { int card; /* card number */ @@ -1122,6 +1196,9 @@ struct snd_ctl_tlv { #define SNDRV_CTL_IOCTL_RAWMIDI_NEXT_DEVICE _IOWR('U', 0x40, int) #define SNDRV_CTL_IOCTL_RAWMIDI_INFO _IOWR('U', 0x41, struct snd_rawmidi_info) #define SNDRV_CTL_IOCTL_RAWMIDI_PREFER_SUBDEVICE _IOW('U', 0x42, int) +#define SNDRV_CTL_IOCTL_UMP_NEXT_DEVICE _IOWR('U', 0x43, int) +#define SNDRV_CTL_IOCTL_UMP_ENDPOINT_INFO _IOWR('U', 0x44, struct snd_ump_endpoint_info) +#define SNDRV_CTL_IOCTL_UMP_BLOCK_INFO _IOWR('U', 0x45, struct snd_ump_block_info) #define SNDRV_CTL_IOCTL_POWER _IOWR('U', 0xd0, int) #define SNDRV_CTL_IOCTL_POWER_STATE _IOR('U', 0xd1, int) diff --git a/tools/lib/subcmd/help.c b/tools/lib/subcmd/help.c index 67a8d6b740ea..adfbae27dc36 100644 --- a/tools/lib/subcmd/help.c +++ b/tools/lib/subcmd/help.c @@ -68,8 +68,13 @@ void exclude_cmds(struct cmdnames *cmds, struct cmdnames *excludes) while (ci < cmds->cnt && ei < excludes->cnt) { cmp = strcmp(cmds->names[ci]->name, excludes->names[ei]->name); if (cmp < 0) { - zfree(&cmds->names[cj]); - cmds->names[cj++] = cmds->names[ci++]; + if (ci == cj) { + ci++; + cj++; + } else { + zfree(&cmds->names[cj]); + cmds->names[cj++] = cmds->names[ci++]; + } } else if (cmp == 0) { ci++; ei++; @@ -77,10 +82,11 @@ void exclude_cmds(struct cmdnames *cmds, struct cmdnames *excludes) ei++; } } - - while (ci < cmds->cnt) { - zfree(&cmds->names[cj]); - cmds->names[cj++] = cmds->names[ci++]; + if (ci != cj) { + while (ci < cmds->cnt) { + zfree(&cmds->names[cj]); + cmds->names[cj++] = cmds->names[ci++]; + } } for (ci = cj; ci < cmds->cnt; ci++) zfree(&cmds->names[ci]); diff --git a/tools/objtool/elf.c b/tools/objtool/elf.c index d420b5d2e2b6..081befa4674b 100644 --- a/tools/objtool/elf.c +++ b/tools/objtool/elf.c @@ -1005,7 +1005,7 @@ struct elf *elf_open_read(const char *name, int flags) perror("malloc"); return NULL; } - memset(elf, 0, offsetof(struct elf, sections)); + memset(elf, 0, sizeof(*elf)); INIT_LIST_HEAD(&elf->sections); diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config index 0609c19caabd..c5db0de49868 100644 --- a/tools/perf/Makefile.config +++ b/tools/perf/Makefile.config @@ -155,9 +155,9 @@ FEATURE_CHECK_LDFLAGS-libcrypto = -lcrypto ifdef CSINCLUDES LIBOPENCSD_CFLAGS := -I$(CSINCLUDES) endif -OPENCSDLIBS := -lopencsd_c_api +OPENCSDLIBS := -lopencsd_c_api -lopencsd ifeq ($(findstring -static,${LDFLAGS}),-static) - OPENCSDLIBS += -lopencsd -lstdc++ + OPENCSDLIBS += -lstdc++ endif ifdef CSLIBS LIBOPENCSD_LDFLAGS := -L$(CSLIBS) diff --git a/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl b/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl index 3f1886ad9d80..cfda2511badf 100644 --- a/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl +++ b/tools/perf/arch/mips/entry/syscalls/syscall_n64.tbl @@ -365,3 +365,4 @@ 448 n64 process_mrelease sys_process_mrelease 449 n64 futex_waitv sys_futex_waitv 450 common set_mempolicy_home_node sys_set_mempolicy_home_node +451 n64 cachestat sys_cachestat diff --git a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl index a0be127475b1..8c0b08b7a80e 100644 --- a/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl +++ b/tools/perf/arch/powerpc/entry/syscalls/syscall.tbl @@ -537,3 +537,4 @@ 448 common process_mrelease sys_process_mrelease 449 common futex_waitv sys_futex_waitv 450 nospu set_mempolicy_home_node sys_set_mempolicy_home_node +451 common cachestat sys_cachestat diff --git a/tools/perf/arch/s390/entry/syscalls/syscall.tbl b/tools/perf/arch/s390/entry/syscalls/syscall.tbl index b68f47541169..a6935af2235c 100644 --- a/tools/perf/arch/s390/entry/syscalls/syscall.tbl +++ b/tools/perf/arch/s390/entry/syscalls/syscall.tbl @@ -453,3 +453,4 @@ 448 common process_mrelease sys_process_mrelease sys_process_mrelease 449 common futex_waitv sys_futex_waitv sys_futex_waitv 450 common set_mempolicy_home_node sys_set_mempolicy_home_node sys_set_mempolicy_home_node +451 common cachestat sys_cachestat sys_cachestat diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl index c84d12608cd2..227538b0ce80 100644 --- a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl +++ b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl @@ -372,6 +372,7 @@ 448 common process_mrelease sys_process_mrelease 449 common futex_waitv sys_futex_waitv 450 common set_mempolicy_home_node sys_set_mempolicy_home_node +451 common cachestat sys_cachestat # # Due to a historical design error, certain syscalls are numbered differently diff --git a/tools/perf/pmu-events/arch/x86/amdzen1/recommended.json b/tools/perf/pmu-events/arch/x86/amdzen1/recommended.json index bf5083c1c260..4d28177325a0 100644 --- a/tools/perf/pmu-events/arch/x86/amdzen1/recommended.json +++ b/tools/perf/pmu-events/arch/x86/amdzen1/recommended.json @@ -169,8 +169,9 @@ }, { "MetricName": "nps1_die_to_dram", - "BriefDescription": "Approximate: Combined DRAM B/bytes of all channels on a NPS1 node (die) (may need --metric-no-group)", + "BriefDescription": "Approximate: Combined DRAM B/bytes of all channels on a NPS1 node (die)", "MetricExpr": "dram_channel_data_controller_0 + dram_channel_data_controller_1 + dram_channel_data_controller_2 + dram_channel_data_controller_3 + dram_channel_data_controller_4 + dram_channel_data_controller_5 + dram_channel_data_controller_6 + dram_channel_data_controller_7", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricGroup": "data_fabric", "PerPkg": "1", "ScaleUnit": "6.1e-5MiB" diff --git a/tools/perf/pmu-events/arch/x86/amdzen2/recommended.json b/tools/perf/pmu-events/arch/x86/amdzen2/recommended.json index a71694a043ba..60e19456d4c8 100644 --- a/tools/perf/pmu-events/arch/x86/amdzen2/recommended.json +++ b/tools/perf/pmu-events/arch/x86/amdzen2/recommended.json @@ -169,8 +169,9 @@ }, { "MetricName": "nps1_die_to_dram", - "BriefDescription": "Approximate: Combined DRAM B/bytes of all channels on a NPS1 node (die) (may need --metric-no-group)", + "BriefDescription": "Approximate: Combined DRAM B/bytes of all channels on a NPS1 node (die)", "MetricExpr": "dram_channel_data_controller_0 + dram_channel_data_controller_1 + dram_channel_data_controller_2 + dram_channel_data_controller_3 + dram_channel_data_controller_4 + dram_channel_data_controller_5 + dram_channel_data_controller_6 + dram_channel_data_controller_7", + "MetricConstraint": "NO_GROUP_EVENTS", "MetricGroup": "data_fabric", "PerPkg": "1", "ScaleUnit": "6.1e-5MiB" diff --git a/tools/perf/pmu-events/arch/x86/amdzen3/recommended.json b/tools/perf/pmu-events/arch/x86/amdzen3/recommended.json index 988cf68ae825..3e9e1781812e 100644 --- a/tools/perf/pmu-events/arch/x86/amdzen3/recommended.json +++ b/tools/perf/pmu-events/arch/x86/amdzen3/recommended.json @@ -205,10 +205,11 @@ }, { "MetricName": "nps1_die_to_dram", - "BriefDescription": "Approximate: Combined DRAM B/bytes of all channels on a NPS1 node (die) (may need --metric-no-group)", + "BriefDescription": "Approximate: Combined DRAM B/bytes of all channels on a NPS1 node (die)", "MetricExpr": "dram_channel_data_controller_0 + dram_channel_data_controller_1 + dram_channel_data_controller_2 + dram_channel_data_controller_3 + dram_channel_data_controller_4 + dram_channel_data_controller_5 + dram_channel_data_controller_6 + dram_channel_data_controller_7", "MetricGroup": "data_fabric", "PerPkg": "1", + "MetricConstraint": "NO_GROUP_EVENTS", "ScaleUnit": "6.1e-5MiB" } ] diff --git a/tools/perf/tests/shell/test_uprobe_from_different_cu.sh b/tools/perf/tests/shell/test_uprobe_from_different_cu.sh new file mode 100755 index 000000000000..00d2e0e2e0c2 --- /dev/null +++ b/tools/perf/tests/shell/test_uprobe_from_different_cu.sh @@ -0,0 +1,77 @@ +#!/bin/bash +# test perf probe of function from different CU +# SPDX-License-Identifier: GPL-2.0 + +set -e + +temp_dir=$(mktemp -d /tmp/perf-uprobe-different-cu-sh.XXXXXXXXXX) + +cleanup() +{ + trap - EXIT TERM INT + if [[ "${temp_dir}" =~ ^/tmp/perf-uprobe-different-cu-sh.*$ ]]; then + echo "--- Cleaning up ---" + perf probe -x ${temp_dir}/testfile -d foo + rm -f "${temp_dir}/"* + rmdir "${temp_dir}" + fi +} + +trap_cleanup() +{ + cleanup + exit 1 +} + +trap trap_cleanup EXIT TERM INT + +cat > ${temp_dir}/testfile-foo.h << EOF +struct t +{ + int *p; + int c; +}; + +extern int foo (int i, struct t *t); +EOF + +cat > ${temp_dir}/testfile-foo.c << EOF +#include "testfile-foo.h" + +int +foo (int i, struct t *t) +{ + int j, res = 0; + for (j = 0; j < i && j < t->c; j++) + res += t->p[j]; + + return res; +} +EOF + +cat > ${temp_dir}/testfile-main.c << EOF +#include "testfile-foo.h" + +static struct t g; + +int +main (int argc, char **argv) +{ + int i; + int j[argc]; + g.c = argc; + g.p = j; + for (i = 0; i < argc; i++) + j[i] = (int) argv[i][0]; + return foo (3, &g); +} +EOF + +gcc -g -Og -flto -c ${temp_dir}/testfile-foo.c -o ${temp_dir}/testfile-foo.o +gcc -g -Og -c ${temp_dir}/testfile-main.c -o ${temp_dir}/testfile-main.o +gcc -g -Og -o ${temp_dir}/testfile ${temp_dir}/testfile-foo.o ${temp_dir}/testfile-main.o + +perf probe -x ${temp_dir}/testfile --funcs foo +perf probe -x ${temp_dir}/testfile foo + +cleanup diff --git a/tools/perf/tests/task-exit.c b/tools/perf/tests/task-exit.c index 25f075fa9125..968dddde6dda 100644 --- a/tools/perf/tests/task-exit.c +++ b/tools/perf/tests/task-exit.c @@ -58,9 +58,9 @@ static int test__task_exit(struct test_suite *test __maybe_unused, int subtest _ signal(SIGCHLD, sig_handler); - evlist = evlist__new_default(); + evlist = evlist__new_dummy(); if (evlist == NULL) { - pr_debug("evlist__new_default\n"); + pr_debug("evlist__new_dummy\n"); return -1; } diff --git a/tools/perf/trace/beauty/include/linux/socket.h b/tools/perf/trace/beauty/include/linux/socket.h index 3bef212a24d7..39b74d83c7c4 100644 --- a/tools/perf/trace/beauty/include/linux/socket.h +++ b/tools/perf/trace/beauty/include/linux/socket.h @@ -177,6 +177,7 @@ static inline size_t msg_data_left(struct msghdr *msg) #define SCM_RIGHTS 0x01 /* rw: access rights (array of int) */ #define SCM_CREDENTIALS 0x02 /* rw: struct ucred */ #define SCM_SECURITY 0x03 /* rw: security label */ +#define SCM_PIDFD 0x04 /* ro: pidfd (int) */ struct ucred { __u32 pid; @@ -326,6 +327,7 @@ struct ucred { */ #define MSG_ZEROCOPY 0x4000000 /* Use user data in kernel path */ +#define MSG_SPLICE_PAGES 0x8000000 /* Splice the pages from the iterator in sendmsg() */ #define MSG_FASTOPEN 0x20000000 /* Send data in TCP SYN */ #define MSG_CMSG_CLOEXEC 0x40000000 /* Set close_on_exec for file descriptor received through @@ -336,6 +338,9 @@ struct ucred { #define MSG_CMSG_COMPAT 0 /* We never have 32 bit fixups */ #endif +/* Flags to be cleared on entry by sendmsg and sendmmsg syscalls */ +#define MSG_INTERNAL_SENDMSG_FLAGS \ + (MSG_SPLICE_PAGES | MSG_SENDPAGE_NOPOLICY | MSG_SENDPAGE_DECRYPTED) /* Setsockoptions(2) level. Thanks to BSD these must match IPPROTO_xxx */ #define SOL_IP 0 diff --git a/tools/perf/trace/beauty/move_mount_flags.sh b/tools/perf/trace/beauty/move_mount_flags.sh index 32e552faf37a..ce5e632d1448 100755 --- a/tools/perf/trace/beauty/move_mount_flags.sh +++ b/tools/perf/trace/beauty/move_mount_flags.sh @@ -10,7 +10,7 @@ fi linux_mount=${linux_header_dir}/mount.h printf "static const char *move_mount_flags[] = {\n" -regex='^[[:space:]]*#[[:space:]]*define[[:space:]]+MOVE_MOUNT_([^_]+_[[:alnum:]_]+)[[:space:]]+(0x[[:xdigit:]]+)[[:space:]]*.*' +regex='^[[:space:]]*#[[:space:]]*define[[:space:]]+MOVE_MOUNT_([^_]+[[:alnum:]_]+)[[:space:]]+(0x[[:xdigit:]]+)[[:space:]]*.*' grep -E $regex ${linux_mount} | \ sed -r "s/$regex/\2 \1/g" | \ xargs printf "\t[ilog2(%s) + 1] = \"%s\",\n" diff --git a/tools/perf/trace/beauty/msg_flags.c b/tools/perf/trace/beauty/msg_flags.c index aa9934020232..ed3ff969b546 100644 --- a/tools/perf/trace/beauty/msg_flags.c +++ b/tools/perf/trace/beauty/msg_flags.c @@ -8,6 +8,12 @@ #ifndef MSG_WAITFORONE #define MSG_WAITFORONE 0x10000 #endif +#ifndef MSG_BATCH +#define MSG_BATCH 0x40000 +#endif +#ifndef MSG_ZEROCOPY +#define MSG_ZEROCOPY 0x4000000 +#endif #ifndef MSG_SPLICE_PAGES #define MSG_SPLICE_PAGES 0x8000000 #endif @@ -50,6 +56,8 @@ static size_t syscall_arg__scnprintf_msg_flags(char *bf, size_t size, P_MSG_FLAG(NOSIGNAL); P_MSG_FLAG(MORE); P_MSG_FLAG(WAITFORONE); + P_MSG_FLAG(BATCH); + P_MSG_FLAG(ZEROCOPY); P_MSG_FLAG(SPLICE_PAGES); P_MSG_FLAG(FASTOPEN); P_MSG_FLAG(CMSG_CLOEXEC); diff --git a/tools/perf/util/dwarf-aux.c b/tools/perf/util/dwarf-aux.c index 45e018c0ebf5..2941d88f2199 100644 --- a/tools/perf/util/dwarf-aux.c +++ b/tools/perf/util/dwarf-aux.c @@ -478,8 +478,10 @@ static const char *die_get_file_name(Dwarf_Die *dw_die, int idx) { Dwarf_Die cu_die; Dwarf_Files *files; + Dwarf_Attribute attr_mem; - if (idx < 0 || !dwarf_diecu(dw_die, &cu_die, NULL, NULL) || + if (idx < 0 || !dwarf_attr_integrate(dw_die, DW_AT_decl_file, &attr_mem) || + !dwarf_cu_die(attr_mem.cu, &cu_die, NULL, NULL, NULL, NULL, NULL, NULL) || dwarf_getsrcfiles(&cu_die, &files, NULL) != 0) return NULL; diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c index 5dcfbf316bf6..acde097e327c 100644 --- a/tools/perf/util/parse-events.c +++ b/tools/perf/util/parse-events.c @@ -1216,6 +1216,14 @@ static int config_term_pmu(struct perf_event_attr *attr, if (term->type_term == PARSE_EVENTS__TERM_TYPE_LEGACY_CACHE) { const struct perf_pmu *pmu = perf_pmus__find_by_type(attr->type); + if (!pmu) { + char *err_str; + + if (asprintf(&err_str, "Failed to find PMU for type %d", attr->type) >= 0) + parse_events_error__handle(err, term->err_term, + err_str, /*help=*/NULL); + return -EINVAL; + } if (perf_pmu__supports_legacy_cache(pmu)) { attr->type = PERF_TYPE_HW_CACHE; return parse_events__decode_legacy_cache(term->config, pmu->type, diff --git a/tools/testing/radix-tree/maple.c b/tools/testing/radix-tree/maple.c index 03539d86cdf0..75ea2081a317 100644 --- a/tools/testing/radix-tree/maple.c +++ b/tools/testing/radix-tree/maple.c @@ -206,9 +206,9 @@ static noinline void __init check_new_node(struct maple_tree *mt) e = i - 1; } else { if (i >= 4) - e = i - 4; - else if (i == 3) - e = i - 2; + e = i - 3; + else if (i >= 1) + e = i - 1; else e = 0; } diff --git a/tools/testing/selftests/arm64/Makefile b/tools/testing/selftests/arm64/Makefile index 9460cbe81bcc..ace8b67fb22d 100644 --- a/tools/testing/selftests/arm64/Makefile +++ b/tools/testing/selftests/arm64/Makefile @@ -42,7 +42,7 @@ run_tests: all done # Avoid any output on non arm64 on emit_tests -emit_tests: all +emit_tests: @for DIR in $(ARM64_SUBTARGETS); do \ BUILD_TARGET=$(OUTPUT)/$$DIR; \ make OUTPUT=$$BUILD_TARGET -C $$DIR $@; \ diff --git a/tools/testing/selftests/bpf/progs/async_stack_depth.c b/tools/testing/selftests/bpf/progs/async_stack_depth.c index 477ba950bb43..3517c0e01206 100644 --- a/tools/testing/selftests/bpf/progs/async_stack_depth.c +++ b/tools/testing/selftests/bpf/progs/async_stack_depth.c @@ -22,9 +22,16 @@ static int timer_cb(void *map, int *key, struct bpf_timer *timer) return buf[69]; } +__attribute__((noinline)) +static int bad_timer_cb(void *map, int *key, struct bpf_timer *timer) +{ + volatile char buf[300] = {}; + return buf[255] + timer_cb(NULL, NULL, NULL); +} + SEC("tc") -__failure __msg("combined stack size of 2 calls") -int prog(struct __sk_buff *ctx) +__failure __msg("combined stack size of 2 calls is 576. Too large") +int pseudo_call_check(struct __sk_buff *ctx) { struct hmap_elem *elem; volatile char buf[256] = {}; @@ -37,4 +44,18 @@ int prog(struct __sk_buff *ctx) return bpf_timer_set_callback(&elem->timer, timer_cb) + buf[0]; } +SEC("tc") +__failure __msg("combined stack size of 2 calls is 608. Too large") +int async_call_root_check(struct __sk_buff *ctx) +{ + struct hmap_elem *elem; + volatile char buf[256] = {}; + + elem = bpf_map_lookup_elem(&hmap, &(int){0}); + if (!elem) + return 0; + + return bpf_timer_set_callback(&elem->timer, bad_timer_cb) + buf[0]; +} + char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/mincore/mincore_selftest.c b/tools/testing/selftests/mincore/mincore_selftest.c index 4c88238fc8f0..e949a43a6145 100644 --- a/tools/testing/selftests/mincore/mincore_selftest.c +++ b/tools/testing/selftests/mincore/mincore_selftest.c @@ -150,8 +150,8 @@ TEST(check_huge_pages) MAP_PRIVATE | MAP_ANONYMOUS | MAP_HUGETLB, -1, 0); if (addr == MAP_FAILED) { - if (errno == ENOMEM) - SKIP(return, "No huge pages available."); + if (errno == ENOMEM || errno == EINVAL) + SKIP(return, "No huge pages available or CONFIG_HUGETLB_PAGE disabled."); else TH_LOG("mmap error: %s", strerror(errno)); } diff --git a/tools/testing/selftests/mm/charge_reserved_hugetlb.sh b/tools/testing/selftests/mm/charge_reserved_hugetlb.sh index a5cb4b09a46c..a5cb4b09a46c 100644..100755 --- a/tools/testing/selftests/mm/charge_reserved_hugetlb.sh +++ b/tools/testing/selftests/mm/charge_reserved_hugetlb.sh diff --git a/tools/testing/selftests/mm/check_config.sh b/tools/testing/selftests/mm/check_config.sh index 3954f4746161..3954f4746161 100644..100755 --- a/tools/testing/selftests/mm/check_config.sh +++ b/tools/testing/selftests/mm/check_config.sh diff --git a/tools/testing/selftests/mm/hugetlb_reparenting_test.sh b/tools/testing/selftests/mm/hugetlb_reparenting_test.sh index bf2d2a684edf..bf2d2a684edf 100644..100755 --- a/tools/testing/selftests/mm/hugetlb_reparenting_test.sh +++ b/tools/testing/selftests/mm/hugetlb_reparenting_test.sh diff --git a/tools/testing/selftests/mm/mkdirty.c b/tools/testing/selftests/mm/mkdirty.c index 6d71d972997b..301abb99e027 100644 --- a/tools/testing/selftests/mm/mkdirty.c +++ b/tools/testing/selftests/mm/mkdirty.c @@ -321,8 +321,8 @@ close_uffd: munmap: munmap(dst, pagesize); free(src); -#endif /* __NR_userfaultfd */ } +#endif /* __NR_userfaultfd */ int main(void) { diff --git a/tools/testing/selftests/mm/run_vmtests.sh b/tools/testing/selftests/mm/run_vmtests.sh index 3f26f6e15b2a..3f26f6e15b2a 100644..100755 --- a/tools/testing/selftests/mm/run_vmtests.sh +++ b/tools/testing/selftests/mm/run_vmtests.sh diff --git a/tools/testing/selftests/mm/test_hmm.sh b/tools/testing/selftests/mm/test_hmm.sh index 46e19b5d648d..46e19b5d648d 100644..100755 --- a/tools/testing/selftests/mm/test_hmm.sh +++ b/tools/testing/selftests/mm/test_hmm.sh diff --git a/tools/testing/selftests/mm/test_vmalloc.sh b/tools/testing/selftests/mm/test_vmalloc.sh index d73b846736f1..d73b846736f1 100644..100755 --- a/tools/testing/selftests/mm/test_vmalloc.sh +++ b/tools/testing/selftests/mm/test_vmalloc.sh diff --git a/tools/testing/selftests/mm/va_high_addr_switch.sh b/tools/testing/selftests/mm/va_high_addr_switch.sh index 45cae7cab27e..45cae7cab27e 100644..100755 --- a/tools/testing/selftests/mm/va_high_addr_switch.sh +++ b/tools/testing/selftests/mm/va_high_addr_switch.sh diff --git a/tools/testing/selftests/mm/write_hugetlb_memory.sh b/tools/testing/selftests/mm/write_hugetlb_memory.sh index 70a02301f4c2..70a02301f4c2 100644..100755 --- a/tools/testing/selftests/mm/write_hugetlb_memory.sh +++ b/tools/testing/selftests/mm/write_hugetlb_memory.sh diff --git a/tools/testing/selftests/riscv/Makefile b/tools/testing/selftests/riscv/Makefile index 9dd629cc86aa..f4b3d5c9af5b 100644 --- a/tools/testing/selftests/riscv/Makefile +++ b/tools/testing/selftests/riscv/Makefile @@ -43,7 +43,7 @@ run_tests: all done # Avoid any output on non riscv on emit_tests -emit_tests: all +emit_tests: @for DIR in $(RISCV_SUBTARGETS); do \ BUILD_TARGET=$(OUTPUT)/$$DIR; \ $(MAKE) OUTPUT=$$BUILD_TARGET -C $$DIR $@; \ diff --git a/tools/testing/selftests/tc-testing/config b/tools/testing/selftests/tc-testing/config index 6e73b09c20c8..71706197ba0f 100644 --- a/tools/testing/selftests/tc-testing/config +++ b/tools/testing/selftests/tc-testing/config @@ -5,6 +5,8 @@ CONFIG_NF_CONNTRACK=m CONFIG_NF_CONNTRACK_MARK=y CONFIG_NF_CONNTRACK_ZONES=y CONFIG_NF_CONNTRACK_LABELS=y +CONFIG_NF_CONNTRACK_PROCFS=y +CONFIG_NF_FLOW_TABLE=m CONFIG_NF_NAT=m CONFIG_NETFILTER_XT_TARGET_LOG=m diff --git a/tools/testing/selftests/tc-testing/settings b/tools/testing/selftests/tc-testing/settings new file mode 100644 index 000000000000..e2206265f67c --- /dev/null +++ b/tools/testing/selftests/tc-testing/settings @@ -0,0 +1 @@ +timeout=900 diff --git a/tools/testing/selftests/timers/raw_skew.c b/tools/testing/selftests/timers/raw_skew.c index 5beceeed0d11..6eba203f9da7 100644 --- a/tools/testing/selftests/timers/raw_skew.c +++ b/tools/testing/selftests/timers/raw_skew.c @@ -129,8 +129,7 @@ int main(int argc, char **argv) printf("%lld.%i(est)", eppm/1000, abs((int)(eppm%1000))); /* Avg the two actual freq samples adjtimex gave us */ - ppm = (tx1.freq + tx2.freq) * 1000 / 2; - ppm = (long long)tx1.freq * 1000; + ppm = (long long)(tx1.freq + tx2.freq) * 1000 / 2; ppm = shift_right(ppm, 16); printf(" %lld.%i(act)", ppm/1000, abs((int)(ppm%1000))); |