summaryrefslogtreecommitdiff
AgeCommit message (Collapse)Author
2025-05-21wifi: mt76: mt7996: adjust HW capabilities for mt7990Peter Chiu
This is a preliminary patch to support mt7990 chipset. Co-developed-by: Howard Hsu <howard-yh.hsu@mediatek.com> Signed-off-by: Howard Hsu <howard-yh.hsu@mediatek.com> Co-developed-by: Shayne Chen <shayne.chen@mediatek.com> Signed-off-by: Shayne Chen <shayne.chen@mediatek.com> Signed-off-by: Peter Chiu <chui-hao.chiu@mediatek.com> Link: https://patch.msgid.link/20250409140750.724437-8-shayne.chen@mediatek.com Signed-off-by: Felix Fietkau <nbd@nbd.name>
2025-05-21wifi: mt76: mt7996: add eeprom support for mt7990StanleyYP Wang
Add eeprom definition and default bin file for mt7990. This is a preliminary patch to support mt7990 chipset. Signed-off-by: StanleyYP Wang <StanleyYP.Wang@mediatek.com> Signed-off-by: Shayne Chen <shayne.chen@mediatek.com> Link: https://patch.msgid.link/20250409140750.724437-7-shayne.chen@mediatek.com Signed-off-by: Felix Fietkau <nbd@nbd.name>
2025-05-21wifi: mt76: mt7996: rework register mapping for mt7990StanleyYP Wang
Rework register offset and l1/l2/cbtop mapping for mt7990. This is a preliminary patch to support mt7990 chipset. Co-developed-by: Peter Chiu <chui-hao.chiu@mediatek.com> Signed-off-by: Peter Chiu <chui-hao.chiu@mediatek.com> Co-developed-by: Shayne Chen <shayne.chen@mediatek.com> Signed-off-by: Shayne Chen <shayne.chen@mediatek.com> Signed-off-by: StanleyYP Wang <StanleyYP.Wang@mediatek.com> Link: https://patch.msgid.link/20250409140750.724437-6-shayne.chen@mediatek.com Signed-off-by: Felix Fietkau <nbd@nbd.name>
2025-05-21wifi: mt76: mt7996: rework DMA configuration for mt7990Peter Chiu
Modify DMA ring setting for mt7990. This is a preliminary patch to support mt7990 chipset. Co-developed-by: StanleyYP Wang <StanleyYP.Wang@mediatek.com> Signed-off-by: StanleyYP Wang <StanleyYP.Wang@mediatek.com> Signed-off-by: Peter Chiu <chui-hao.chiu@mediatek.com> Signed-off-by: Shayne Chen <shayne.chen@mediatek.com> Link: https://patch.msgid.link/20250409140750.724437-5-shayne.chen@mediatek.com Signed-off-by: Felix Fietkau <nbd@nbd.name>
2025-05-21wifi: mt76: mt7996: rework WA mcu command for mt7990Peter Chiu
Since mt7990 lacks WA firmware, some WA commands are not supported or need to be refactored to use the SDO command. This is a preliminary patch to support mt7990 chipset. Signed-off-by: Peter Chiu <chui-hao.chiu@mediatek.com> Signed-off-by: Shayne Chen <shayne.chen@mediatek.com> Link: https://patch.msgid.link/20250409140750.724437-4-shayne.chen@mediatek.com Signed-off-by: Felix Fietkau <nbd@nbd.name>
2025-05-21wifi: mt76: connac: add support to load firmware for mt7990StanleyYP Wang
Add firmware download support. Note that mt7990 does not have WA and DSP firmwares. This is a preliminary patch to support mt7990 chipset. Co-developed-by: Peter Chiu <chui-hao.chiu@mediatek.com> Signed-off-by: Peter Chiu <chui-hao.chiu@mediatek.com> Signed-off-by: StanleyYP Wang <StanleyYP.Wang@mediatek.com> Signed-off-by: Shayne Chen <shayne.chen@mediatek.com> Link: https://patch.msgid.link/20250409140750.724437-3-shayne.chen@mediatek.com Signed-off-by: Felix Fietkau <nbd@nbd.name>
2025-05-21wifi: mt76: mt7996: add macros for pci device idsShayne Chen
The chipset name (i.e., brand name) used by the driver may cause confusion with the PCI device ID when adding support for new chipsets. | Chipset name | PCI device id | |--------------|----------------| | 7996 | 0x7990, 0x7991 | | 7992 | 0x7992, 0x799a | | 7990 | 0x7993, 0x799b | To prevent confusion, replace the code that directly uses the device ID with macros. This is a preliminary patch to support mt7990 chipset. Co-developed-by: Peter Chiu <chui-hao.chiu@mediatek.com> Signed-off-by: Peter Chiu <chui-hao.chiu@mediatek.com> Signed-off-by: Shayne Chen <shayne.chen@mediatek.com> Link: https://patch.msgid.link/20250409140750.724437-2-shayne.chen@mediatek.com Signed-off-by: Felix Fietkau <nbd@nbd.name>
2025-05-21can: dev: add struct data_bittiming_params to group FD parametersVincent Mailhol
This is a preparation patch for the introduction of CAN XL. CAN FD and CAN XL uses similar bittiming parameters. Add one level of nesting for all the CAN FD parameters. Typically: priv->can.data_bittiming; becomes: priv->can.fd.data_bittiming; This way, the CAN XL equivalent (to be introduced later) would be: priv->can.xl.data_bittiming; Add the new struct data_bittiming_params which contains all the data bittiming parameters, including the TDC and the callback functions. This done, update all the CAN FD drivers to make use of the new layout. Acked-by: Oliver Hartkopp <socketcan@hartkopp.net> Signed-off-by: Vincent Mailhol <mailhol.vincent@wanadoo.fr> Link: https://patch.msgid.link/20250501171213.2161572-2-mailhol.vincent@wanadoo.fr [mkl: fix rcar_canfd] Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
2025-05-21Merge patch series "Add support for RZ/G3E CANFD"Marc Kleine-Budde
Biju Das <biju.das.jz@bp.renesas.com> says: The CAN-FD module on RZ/G3E is very similar to the one on both R-Car V4H and RZ/G2L, but differs in some hardware parameters: * No external clock, but instead has ram clock. * Support up to 6 channels. * 20 interrupts. v8->v9: * Collected tags. * Added missing header bitfield.h. * Fixed logical error ch->BIT(ch) in rcar_canfd_global_error(). * Removed unneeded double space in rcar_canfd_setrnc(). * Updated commit description in patch#15. v7->v8: * Collected tags. * Updated commit description for patch#{5,9,15,16,17}. * Replaced the macro RCANFD_GERFL_EEF0_7->RCANFD_GERFL_EEF. * Dropped the redundant macro RCANFD_GERFL_EEF(ch). * Added patch for dropping the mask operation in RCANFD_GAFLCFG_SETRNC macro. * Converted RCANFD_GAFLCFG_SETRNC->rcar_canfd_setrnc(). * Updated RCANFD_GAFLCFG macro by replacing the parameter ch->w, where w is the GAFLCFG index used in the hardware manual. * Renamed the parameter x->page_num in RCANFD_GAFLECTR_AFLPN macro to make it clear. * Renamed the parameter x->cftml in RCANFD_CFCC_CFTML macro to make it clear. * Updated {rzg2l,car_gen3_hw_info} with ch_interface_mode = 0. * Updated {rzg2l,rcar_gen3}_hw_info with shared_can_regs = 0. * Started using struct rcanfd_regs instead of LUT for reg offsets. * Started using struct rcar_canfd_shift_data instead of LUT for shift data. * Renamed only_internal_clks->external_clk to avoid negation. * Updated rcar_canfd_hw_info tables with external_clk entries. * Replaced 10->sizeof(name) in scnprintf(). v6->v7: * Collected tags * Replaced 'aswell'->'as well' in patch#11 commit description. v5->v6: * Replaced RCANFD_RNC_PER_REG macro with rnc_stride variable. * Updated commit description for patch#7 and #8 * Dropped mask_table: AFLPN_MASK is replaced by max_aflpn variable. CFTML_MASK is replaced by max_cftml variable. BITTIMING MASK's are replaced by {nom,data}_bittiming variables. * Collected tag from Geert. v4->v5: * Collected tag from Geert. * The rules for R-Car Gen3/4 could be kept together, reducing the number of lines. Similar change for rzg2l-canfd aswell. * Keeping interrupts and resets together allows to keep a clear separation between RZ/G2L and RZ/G3E, at the expense of only a single line. * Retained the tags for binding patches as it is trivial changes. * Dropped the unused macro RCANFD_GAFLCFG_GETRNC. * Updated macro RCANFD_GERFL_ERR by using gpriv->channels_mask and dropped unused macro RCANFD_GERFL_EEF0_7. * Replaced RNC mask in RCANFD_GAFLCFG_SETRNC macro by using info->num_supported_rules variable. * Updated the macro RCANFD_GAFLCFG by using info->rnc_field_width variable. * Updated shift value in RCANFD_GAFLCFG_SETRNC macro by using a formula (32 - (n % rnc_per_reg + 1) * field_width). * Replaced the variable name shared_can_reg->shared_can_regs. * Improved commit description for patch{#11,#12}by replacing has->have. * Dropped RCANFD_EEF_MASK and RCANFD_RNC_MASK as it is taken care by gpriv->channels_mask and info->num_supported_rules. * Dropped RCANFD_FIRST_RNC_SH and RCANFD_SECOND_RNC_SH by using a formula (32 - (n % rnc_per_reg + 1) * rnc_field_width. * Improved commit description by "All SoCs supports extenal clock"-> "All existing SoCs support an external clock". * Updated error description in probe as "cannot get enabled ram clock" * Updated r9a09g047_hw_info table. v3->v4: * Added Rb tag from Rob for patch#2. * Added prefix RCANFD_* to enum rcar_canfd_reg_offset_id. * Added prefix RCANFD_* to enum rcar_canfd_mask_id. * Added prefix RCANFD_* to enum rcar_canfd_shift_id. v2->v3: * Collected tags. * Dropped reg_gen4() and is_gen4() by adding mask_table, shift_table, regs, ch_interface_mode and shared_can_reg variables to struct rcar_canfd_hw_info. v1->v2: * Split the series with fixes patch separately. * Added patch for Simplify rcar_canfd_probe() using of_get_available_child_by_name() as dependency patch hit on can-next. * Added Rb tag from Vincent Mailhol. * Dropped redundant comment from commit description for patch#3. Link: https://patch.msgid.link/20250417054320.14100-1-biju.das.jz@bp.renesas.com Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
2025-05-21can: rcar_canfd: Add RZ/G3E supportBiju Das
The CAN-FD IP found on the RZ/G3E SoC is similar to R-Car Gen4, but it has no external clock instead it has clk_ram, it has 6 channels and supports 20 interrupts. Add support for RZ/G3E CAN-FD driver. Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be> Reviewed-by: Vincent Mailhol <mailhol.vincent@wanadoo.fr> Signed-off-by: Biju Das <biju.das.jz@bp.renesas.com> Link: https://patch.msgid.link/20250417054320.14100-20-biju.das.jz@bp.renesas.com Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
2025-05-21can: rcar_canfd: Enhance multi_channel_irqs handlingBiju Das
Currently multi_channel_irqs has only 2 channels. But RZ/G3E has six channels. Enhance multi_channel_irqs handling to support more than two channels. Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be> Reviewed-by: Vincent Mailhol <mailhol.vincent@wanadoo.fr> Signed-off-by: Biju Das <biju.das.jz@bp.renesas.com> Link: https://patch.msgid.link/20250417054320.14100-19-biju.das.jz@bp.renesas.com Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
2025-05-21can: rcar_canfd: Add external_clk variable to struct rcar_canfd_hw_infoBiju Das
All existing SoCs support an external clock, but RZ/G3E has only internal clocks. Add external_clk variable to struct rcar_canfd_hw_info to handle this difference. Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be> Reviewed-by: Vincent Mailhol <mailhol.vincent@wanadoo.fr> Signed-off-by: Biju Das <biju.das.jz@bp.renesas.com> Link: https://patch.msgid.link/20250417054320.14100-18-biju.das.jz@bp.renesas.com Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
2025-05-21can: rcar_canfd: Add sh variable to struct rcar_canfd_hw_infoBiju Das
R-Car Gen3 and Gen4 have some differences in the shift bits. Introduce a struct rcar_canfd_shift_data to hold these values and add the struct rcar_canfd_shift_data variable sh to struct rcar_canfd_hw_info to handle these differences. After this, drop the unused functions reg_gen4() and is_gen4(). Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be> Signed-off-by: Biju Das <biju.das.jz@bp.renesas.com> Link: https://patch.msgid.link/20250417054320.14100-17-biju.das.jz@bp.renesas.com Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
2025-05-21can: rcar_canfd: Add struct rcanfd_regs variable to struct rcar_canfd_hw_infoBiju Das
R-Car Gen3 and Gen4 have some differences in the register offsets. Add struct rcanfd_regs variable regs to the struct rcar_canfd_hw_info to handle these differences. Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be> Signed-off-by: Biju Das <biju.das.jz@bp.renesas.com> Link: https://patch.msgid.link/20250417054320.14100-16-biju.das.jz@bp.renesas.com Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
2025-05-21can: rcar_canfd: Add shared_can_regs variable to struct rcar_canfd_hw_infoBiju Das
R-Car Gen4 has shared regs for both CAN-FD and Classical CAN operations. Add shared_can_regs variable to struct rcar_canfd_hw_info to handle this difference. Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be> Reviewed-by: Vincent Mailhol <mailhol.vincent@wanadoo.fr> Signed-off-by: Biju Das <biju.das.jz@bp.renesas.com> Link: https://patch.msgid.link/20250417054320.14100-15-biju.das.jz@bp.renesas.com Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
2025-05-21can: rcar_canfd: Add ch_interface_mode variable to struct rcar_canfd_hw_infoBiju Das
R-Car Gen4 has channel specific interface mode bit for setting CAN-FD or Classical CAN mode whereas on R-Car Gen3 it is global. Add a ch_interface_mode variable to struct rcar_canfd_hw_info to handle this difference. Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be> Reviewed-by: Vincent Mailhol <mailhol.vincent@wanadoo.fr> Signed-off-by: Biju Das <biju.das.jz@bp.renesas.com> Link: https://patch.msgid.link/20250417054320.14100-14-biju.das.jz@bp.renesas.com Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
2025-05-21can: rcar_canfd: Add {nom,data}_bittiming variables to struct rcar_canfd_hw_infoBiju Das
Both R-Car Gen4 and R-Car Gen3 have different bit timing parameters Add {nom,data}_bittiming variables to struct rcar_canfd_hw_info to handle this difference. Since the mask used in the macros are max value - 1, replace that as well. Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be> Reviewed-by: Vincent Mailhol <mailhol.vincent@wanadoo.fr> Signed-off-by: Biju Das <biju.das.jz@bp.renesas.com> Link: https://patch.msgid.link/20250417054320.14100-13-biju.das.jz@bp.renesas.com Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
2025-05-21can: rcar_canfd: Add max_cftml variable to struct rcar_canfd_hw_infoBiju Das
R-Car Gen3 has CFTML max positional value is 15 whereas on R-Car Gen4 it is 31. Add a max_cftml variable to struct rcar_canfd_hw_info to handle this difference. While at it, rename the parameter x->cftml in RCANFD_CFCC_CFTML macro to make it clear. Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be> Reviewed-by: Vincent Mailhol <mailhol.vincent@wanadoo.fr> Signed-off-by: Biju Das <biju.das.jz@bp.renesas.com> Link: https://patch.msgid.link/20250417054320.14100-12-biju.das.jz@bp.renesas.com Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
2025-05-21can: rcar_canfd: Add max_aflpn variable to struct rcar_canfd_hw_infoBiju Das
R-Car Gen3 has maximum acceptance filter list page number of 31 whereas on R-Car Gen4 it is 127. Add max_aflpn variable to struct rcar_canfd_hw_info in order to support RZ/G3E that has max AFLPN of 63. While at it, rename the parameter x->page_num in RCANFD_GAFLECTR_AFLPN macro to make it clear. Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be> Reviewed-by: Vincent Mailhol <mailhol.vincent@wanadoo.fr> Signed-off-by: Biju Das <biju.das.jz@bp.renesas.com> Link: https://patch.msgid.link/20250417054320.14100-11-biju.das.jz@bp.renesas.com Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
2025-05-21can: rcar_canfd: Add rnc_field_width variable to struct rcar_canfd_hw_infoBiju Das
The shift and w value in rcar_canfd_setrnc() are dictated by the field width: - R-Car Gen4 packs 2 values in a 32-bit word, using a field width of 16 bits, - R-Car Gen3 packs up to 4 values in a 32-bit word, using a field width of 8 bits. Add rnc_field_width variable to struct rcar_canfd_hw_info to handle this difference. The rnc_stride is 32 / rnc_field_width and the index parameter w is calculated by ch / rnc_stride. The shift value in rcar_canfd_setrnc() is computed by using (32 - (ch % rnc_stride + 1) * rnc_field_width). Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be> Signed-off-by: Biju Das <biju.das.jz@bp.renesas.com> Link: https://patch.msgid.link/20250417054320.14100-10-biju.das.jz@bp.renesas.com Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
2025-05-21can: rcar_canfd: Update RCANFD_GAFLCFG macroBiju Das
Update RCANFD_GAFLCFG macro by replacing the parameter ch->w, where w is the GAFLCFG index used in the hardware manual. Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be> Signed-off-by: Biju Das <biju.das.jz@bp.renesas.com> Link: https://patch.msgid.link/20250417054320.14100-9-biju.das.jz@bp.renesas.com Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
2025-05-21can: rcar_canfd: Add rcar_canfd_setrnc()Biju Das
Add rcar_canfd_setrnc() to replace the macro RCANFD_GAFLCFG_SETRNC. While at it, replace int->unsigned int for local variables offset, page and num_rules in rcar_canfd_configure_afl_rules(). Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be> Signed-off-by: Biju Das <biju.das.jz@bp.renesas.com> Link: https://patch.msgid.link/20250417054320.14100-8-biju.das.jz@bp.renesas.com Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
2025-05-21can: rcar_canfd: Drop the mask operation in RCANFD_GAFLCFG_SETRNC macroBiju Das
Drop the mask operation in RCANFD_GAFLCFG_SETRNC macro as the num_rules can never be larger than number of supported rules. Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be> Signed-off-by: Biju Das <biju.das.jz@bp.renesas.com> Link: https://patch.msgid.link/20250417054320.14100-7-biju.das.jz@bp.renesas.com Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
2025-05-21can: rcar_canfd: Update RCANFD_GERFL_ERR macroBiju Das
Replace the macro RCANFD_GERFL_EEF0_7->RCANFD_GERFL_EEF. The macros RCANFD_GERFL_EEF* in RCANFD_GERFL_ERR can be replaced by FIELD_PREP() and drop the redundant macro RCANFD_GERFL_EEF(ch). Signed-off-by: Biju Das <biju.das.jz@bp.renesas.com> Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be> Link: https://patch.msgid.link/20250417054320.14100-6-biju.das.jz@bp.renesas.com Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
2025-05-21can: rcar_canfd: Drop RCANFD_GAFLCFG_GETRNC macroBiju Das
Drop the unused macro RCANFD_GAFLCFG_GETRNC. Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be> Reviewed-by: Vincent Mailhol <mailhol.vincent@wanadoo.fr> Signed-off-by: Biju Das <biju.das.jz@bp.renesas.com> Link: https://patch.msgid.link/20250417054320.14100-5-biju.das.jz@bp.renesas.com Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
2025-05-21can: rcar_canfd: Use of_get_available_child_by_name()Biju Das
Simplify rcar_canfd_probe() using of_get_available_child_by_name(). While at it, move of_node_put(child) inside the if block to avoid additional check if of_child is NULL. Reviewed-by: Vincent Mailhol <mailhol.vincent@wanadoo.fr> Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be> Signed-off-by: Biju Das <biju.das.jz@bp.renesas.com> Link: https://patch.msgid.link/20250417054320.14100-4-biju.das.jz@bp.renesas.com Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
2025-05-21dt-bindings: can: renesas,rcar-canfd: Document RZ/G3E supportBiju Das
Document support for the CAN-FD Interface on the RZ/G3E (R9A09G047) SoC, which supports up to six channels. The CAN-FD module on RZ/G3E is very similar to the one on both R-Car V4H and RZ/G2L, but differs in some hardware parameters: * No external clock, but instead has ram clock. * Support up to 6 channels. * 20 interrupts. Reviewed-by: "Rob Herring (Arm)" <robh@kernel.org> Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be> Signed-off-by: Biju Das <biju.das.jz@bp.renesas.com> Link: https://patch.msgid.link/20250417054320.14100-3-biju.das.jz@bp.renesas.com Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
2025-05-21dt-bindings: can: renesas,rcar-canfd: Simplify the conditional schemaBiju Das
RZ/G3E SoC has 20 interrupts, 2 resets and 6 channels that need more branching with conditional schema. Simplify the conditional schema with if statements rather than the complex if-else statements to prepare for supporting RZ/G3E SoC. Acked-by: Conor Dooley <conor.dooley@microchip.com> Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be> Signed-off-by: Biju Das <biju.das.jz@bp.renesas.com> Link: https://patch.msgid.link/20250417054320.14100-2-biju.das.jz@bp.renesas.com Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
2025-05-21kernfs: Relax constraint in draining guardMichal Koutný
The active reference lifecycle provides the break/unbreak mechanism but the active reference is not truly active after unbreak -- callers don't use it afterwards but it's important for proper pairing of kn->active counting. Assuming this mechanism is in place, the WARN check in kernfs_should_drain_open_files() is too sensitive -- it may transiently catch those (rightful) callers between kernfs_unbreak_active_protection() and kernfs_put_active() as found out by Chen Ridong: kernfs_remove_by_name_ns kernfs_get_active // active=1 __kernfs_remove // active=0x80000002 kernfs_drain ... wait_event //waiting (active == 0x80000001) kernfs_break_active_protection // active = 0x80000001 // continue kernfs_unbreak_active_protection // active = 0x80000002 ... kernfs_should_drain_open_files // warning occurs kernfs_put_active To avoid the false positives (mind panic_on_warn) remove the check altogether. (This is meant as quick fix, I think active reference break/unbreak may be simplified with larger rework.) Fixes: bdb2fd7fc56e1 ("kernfs: Skip kernfs_drain_open_files() more aggressively") Link: https://lore.kernel.org/r/kmmrseckjctb4gxcx2rdminrjnq2b4ipf7562nvfd432ld5v5m@2byj5eedkb2o/ Cc: Chen Ridong <chenridong@huawei.com> Signed-off-by: Michal Koutný <mkoutny@suse.com> Acked-by: Tejun Heo <tj@kernel.org> Link: https://lore.kernel.org/r/20250505121201.879823-1-mkoutny@suse.com Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2025-05-21Documentation: embargoed-hardware-issues.rst: Remove myselfMichael Ellerman
I'm no longer able to perform this role since I left IBM. Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/8734czh8yg.fsf@mpe.ellerman.id.au Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2025-05-21Merge patch series "coredump: add coredump socket"Christian Brauner
Christian Brauner <brauner@kernel.org> says: Coredumping currently supports two modes: (1) Dumping directly into a file somewhere on the filesystem. (2) Dumping into a pipe connected to a usermode helper process spawned as a child of the system_unbound_wq or kthreadd. For simplicity I'm mostly ignoring (1). There's probably still some users of (1) out there but processing coredumps in this way can be considered adventurous especially in the face of set*id binaries. The most common option should be (2) by now. It works by allowing userspace to put a string into /proc/sys/kernel/core_pattern like: |/usr/lib/systemd/systemd-coredump %P %u %g %s %t %c %h The "|" at the beginning indicates to the kernel that a pipe must be used. The path following the pipe indicator is a path to a binary that will be spawned as a usermode helper process. Any additional parameters pass information about the task that is generating the coredump to the binary that processes the coredump. In the example core_pattern shown above systemd-coredump is spawned as a usermode helper. There's various conceptual consequences of this (non-exhaustive list): - systemd-coredump is spawned with file descriptor number 0 (stdin) connected to the read-end of the pipe. All other file descriptors are closed. That specifically includes 1 (stdout) and 2 (stderr). This has already caused bugs because userspace assumed that this cannot happen (Whether or not this is a sane assumption is irrelevant.). - systemd-coredump will be spawned as a child of system_unbound_wq. So it is not a child of any userspace process and specifically not a child of PID 1. It cannot be waited upon and is in a weird hybrid upcall which are difficult for userspace to control correctly. - systemd-coredump is spawned with full kernel privileges. This necessitates all kinds of weird privilege dropping excercises in userspace to make this safe. - A new usermode helper has to be spawned for each crashing process. This series adds a new mode: (3) Dumping into an AF_UNIX socket. Userspace can set /proc/sys/kernel/core_pattern to: @/path/to/coredump.socket The "@" at the beginning indicates to the kernel that an AF_UNIX coredump socket will be used to process coredumps. The coredump socket must be located in the initial mount namespace. When a task coredumps it opens a client socket in the initial network namespace and connects to the coredump socket. - The coredump server should use SO_PEERPIDFD to get a stable handle on the connected crashing task. The retrieved pidfd will provide a stable reference even if the crashing task gets SIGKILLed while generating the coredump. - By setting core_pipe_limit non-zero userspace can guarantee that the crashing task cannot be reaped behind it's back and thus process all necessary information in /proc/<pid>. The SO_PEERPIDFD can be used to detect whether /proc/<pid> still refers to the same process. The core_pipe_limit isn't used to rate-limit connections to the socket. This can simply be done via AF_UNIX socket directly. - The pidfd for the crashing task will contain information how the task coredumps. The PIDFD_GET_INFO ioctl gained a new flag PIDFD_INFO_COREDUMP which can be used to retreive the coredump information. If the coredump gets a new coredump client connection the kernel guarantees that PIDFD_INFO_COREDUMP information is available. Currently the following information is provided in the new @coredump_mask extension to struct pidfd_info: * PIDFD_COREDUMPED is raised if the task did actually coredump. * PIDFD_COREDUMP_SKIP is raised if the task skipped coredumping (e.g., undumpable). * PIDFD_COREDUMP_USER is raised if this is a regular coredump and doesn't need special care by the coredump server. * PIDFD_COREDUMP_ROOT is raised if the generated coredump should be treated as sensitive and the coredump server should restrict access to the generated coredump to sufficiently privileged users. - The coredump server should mark itself as non-dumpable. - A container coredump server in a separate network namespace can simply bind to another well-know address and systemd-coredump fowards coredumps to the container. - Coredumps could in the future also be handled via per-user/session coredump servers that run only with that users privileges. The coredump server listens on the coredump socket and accepts a new coredump connection. It then retrieves SO_PEERPIDFD for the client, inspects uid/gid and hands the accepted client to the users own coredump handler which runs with the users privileges only (It must of coure pay close attention to not forward crashing suid binaries.). The new coredump socket will allow userspace to not have to rely on usermode helpers for processing coredumps and provides a safer way to handle them instead of relying on super privileged coredumping helpers. This will also be significantly more lightweight since no fork()+exec() for the usermodehelper is required for each crashing process. The coredump server in userspace can just keep a worker pool. * patches from https://lore.kernel.org/20250516-work-coredump-socket-v8-0-664f3caf2516@kernel.org: selftests/coredump: add tests for AF_UNIX coredumps selftests/pidfd: add PIDFD_INFO_COREDUMP infrastructure coredump: validate socket name as it is written coredump: show supported coredump modes pidfs, coredump: add PIDFD_INFO_COREDUMP coredump: add coredump socket coredump: reflow dump helpers a little coredump: massage do_coredump() coredump: massage format_corename() Link: https://lore.kernel.org/20250516-work-coredump-socket-v8-0-664f3caf2516@kernel.org Signed-off-by: Christian Brauner <brauner@kernel.org>
2025-05-21selftests/coredump: add tests for AF_UNIX coredumpsChristian Brauner
Add a simple test for generating coredumps via AF_UNIX sockets. Link: https://lore.kernel.org/20250516-work-coredump-socket-v8-9-664f3caf2516@kernel.org Acked-by: Luca Boccassi <luca.boccassi@gmail.com> Reviewed-by: Alexander Mikhalitsyn <aleksandr.mikhalitsyn@canonical.com> Signed-off-by: Christian Brauner <brauner@kernel.org>
2025-05-21selftests/pidfd: add PIDFD_INFO_COREDUMP infrastructureChristian Brauner
Add PIDFD_INFO_COREDUMP infrastructure so we can use it in tests. Link: https://lore.kernel.org/20250516-work-coredump-socket-v8-8-664f3caf2516@kernel.org Acked-by: Luca Boccassi <luca.boccassi@gmail.com> Reviewed-by: Alexander Mikhalitsyn <aleksandr.mikhalitsyn@canonical.com> Signed-off-by: Christian Brauner <brauner@kernel.org>
2025-05-21coredump: validate socket name as it is writtenChristian Brauner
In contrast to other parameters written into /proc/sys/kernel/core_pattern that never fail we can validate enabling the new AF_UNIX support. This is obviously racy as hell but it's always been that way. Link: https://lore.kernel.org/20250516-work-coredump-socket-v8-7-664f3caf2516@kernel.org Acked-by: Luca Boccassi <luca.boccassi@gmail.com> Reviewed-by: Jann Horn <jannh@google.com> Reviewed-by: Alexander Mikhalitsyn <aleksandr.mikhalitsyn@canonical.com> Signed-off-by: Christian Brauner <brauner@kernel.org>
2025-05-21coredump: show supported coredump modesChristian Brauner
Allow userspace to discover what coredump modes are supported. Link: https://lore.kernel.org/20250516-work-coredump-socket-v8-6-664f3caf2516@kernel.org Acked-by: Luca Boccassi <luca.boccassi@gmail.com> Reviewed-by: Jann Horn <jannh@google.com> Reviewed-by: Alexander Mikhalitsyn <aleksandr.mikhalitsyn@canonical.com> Signed-off-by: Christian Brauner <brauner@kernel.org>
2025-05-21pidfs, coredump: add PIDFD_INFO_COREDUMPChristian Brauner
Extend the PIDFD_INFO_COREDUMP ioctl() with the new PIDFD_INFO_COREDUMP mask flag. This adds the @coredump_mask field to struct pidfd_info. When a task coredumps the kernel will provide the following information to userspace in @coredump_mask: * PIDFD_COREDUMPED is raised if the task did actually coredump. * PIDFD_COREDUMP_SKIP is raised if the task skipped coredumping (e.g., undumpable). * PIDFD_COREDUMP_USER is raised if this is a regular coredump and doesn't need special care by the coredump server. * PIDFD_COREDUMP_ROOT is raised if the generated coredump should be treated as sensitive and the coredump server should restrict to the generated coredump to sufficiently privileged users. The kernel guarantees that by the time the connection is made the all PIDFD_INFO_COREDUMP info is available. Link: https://lore.kernel.org/20250516-work-coredump-socket-v8-5-664f3caf2516@kernel.org Acked-by: Luca Boccassi <luca.boccassi@gmail.com> Reviewed-by: Alexander Mikhalitsyn <aleksandr.mikhalitsyn@canonical.com> Reviewed-by: Jann Horn <jannh@google.com> Signed-off-by: Christian Brauner <brauner@kernel.org>
2025-05-21coredump: add coredump socketChristian Brauner
Coredumping currently supports two modes: (1) Dumping directly into a file somewhere on the filesystem. (2) Dumping into a pipe connected to a usermode helper process spawned as a child of the system_unbound_wq or kthreadd. For simplicity I'm mostly ignoring (1). There's probably still some users of (1) out there but processing coredumps in this way can be considered adventurous especially in the face of set*id binaries. The most common option should be (2) by now. It works by allowing userspace to put a string into /proc/sys/kernel/core_pattern like: |/usr/lib/systemd/systemd-coredump %P %u %g %s %t %c %h The "|" at the beginning indicates to the kernel that a pipe must be used. The path following the pipe indicator is a path to a binary that will be spawned as a usermode helper process. Any additional parameters pass information about the task that is generating the coredump to the binary that processes the coredump. In the example core_pattern shown above systemd-coredump is spawned as a usermode helper. There's various conceptual consequences of this (non-exhaustive list): - systemd-coredump is spawned with file descriptor number 0 (stdin) connected to the read-end of the pipe. All other file descriptors are closed. That specifically includes 1 (stdout) and 2 (stderr). This has already caused bugs because userspace assumed that this cannot happen (Whether or not this is a sane assumption is irrelevant.). - systemd-coredump will be spawned as a child of system_unbound_wq. So it is not a child of any userspace process and specifically not a child of PID 1. It cannot be waited upon and is in a weird hybrid upcall which are difficult for userspace to control correctly. - systemd-coredump is spawned with full kernel privileges. This necessitates all kinds of weird privilege dropping excercises in userspace to make this safe. - A new usermode helper has to be spawned for each crashing process. This series adds a new mode: (3) Dumping into an AF_UNIX socket. Userspace can set /proc/sys/kernel/core_pattern to: @/path/to/coredump.socket The "@" at the beginning indicates to the kernel that an AF_UNIX coredump socket will be used to process coredumps. The coredump socket must be located in the initial mount namespace. When a task coredumps it opens a client socket in the initial network namespace and connects to the coredump socket. - The coredump server uses SO_PEERPIDFD to get a stable handle on the connected crashing task. The retrieved pidfd will provide a stable reference even if the crashing task gets SIGKILLed while generating the coredump. - By setting core_pipe_limit non-zero userspace can guarantee that the crashing task cannot be reaped behind it's back and thus process all necessary information in /proc/<pid>. The SO_PEERPIDFD can be used to detect whether /proc/<pid> still refers to the same process. The core_pipe_limit isn't used to rate-limit connections to the socket. This can simply be done via AF_UNIX sockets directly. - The pidfd for the crashing task will grow new information how the task coredumps. - The coredump server should mark itself as non-dumpable. - A container coredump server in a separate network namespace can simply bind to another well-know address and systemd-coredump fowards coredumps to the container. - Coredumps could in the future also be handled via per-user/session coredump servers that run only with that users privileges. The coredump server listens on the coredump socket and accepts a new coredump connection. It then retrieves SO_PEERPIDFD for the client, inspects uid/gid and hands the accepted client to the users own coredump handler which runs with the users privileges only (It must of coure pay close attention to not forward crashing suid binaries.). The new coredump socket will allow userspace to not have to rely on usermode helpers for processing coredumps and provides a safer way to handle them instead of relying on super privileged coredumping helpers that have and continue to cause significant CVEs. This will also be significantly more lightweight since no fork()+exec() for the usermodehelper is required for each crashing process. The coredump server in userspace can e.g., just keep a worker pool. Link: https://lore.kernel.org/20250516-work-coredump-socket-v8-4-664f3caf2516@kernel.org Acked-by: Luca Boccassi <luca.boccassi@gmail.com> Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com> Reviewed-by: Alexander Mikhalitsyn <aleksandr.mikhalitsyn@canonical.com> Reviewed-by: Jann Horn <jannh@google.com> Signed-off-by: Christian Brauner <brauner@kernel.org>
2025-05-21mips/perf: Remove driver-specific throttle supportKan Liang
The throttle support has been added in the generic code. Remove the driver-specific throttle support. Besides the throttle, perf_event_overflow may return true because of event_limit. It already does an inatomic event disable. The pmu->stop is not required either. Signed-off-by: Kan Liang <kan.liang@linux.intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Link: https://lore.kernel.org/r/20250520181644.2673067-17-kan.liang@linux.intel.com
2025-05-21xtensa/perf: Remove driver-specific throttle supportKan Liang
The throttle support has been added in the generic code. Remove the driver-specific throttle support. Besides the throttle, perf_event_overflow may return true because of event_limit. It already does an inatomic event disable. The pmu->stop is not required either. Signed-off-by: Kan Liang <kan.liang@linux.intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Reviewed-by: Max Filippov <jcmvbkbc@gmail.com> Link: https://lore.kernel.org/r/20250520181644.2673067-16-kan.liang@linux.intel.com
2025-05-21sparc/perf: Remove driver-specific throttle supportKan Liang
The throttle support has been added in the generic code. Remove the driver-specific throttle support. Besides the throttle, perf_event_overflow may return true because of event_limit. It already does an inatomic event disable. The pmu->stop is not required either. Signed-off-by: Kan Liang <kan.liang@linux.intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Link: https://lore.kernel.org/r/20250520181644.2673067-15-kan.liang@linux.intel.com
2025-05-21loongarch/perf: Remove driver-specific throttle supportKan Liang
The throttle support has been added in the generic code. Remove the driver-specific throttle support. Besides the throttle, perf_event_overflow may return true because of event_limit. It already does an inatomic event disable. The pmu->stop is not required either. Signed-off-by: Kan Liang <kan.liang@linux.intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Link: https://lore.kernel.org/r/20250520181644.2673067-14-kan.liang@linux.intel.com
2025-05-21csky/perf: Remove driver-specific throttle supportKan Liang
The throttle support has been added in the generic code. Remove the driver-specific throttle support. Besides the throttle, perf_event_overflow may return true because of event_limit. It already does an inatomic event disable. The pmu->stop is not required either. Signed-off-by: Kan Liang <kan.liang@linux.intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Acked-by: Guo Ren <guoren@kernel.org> Link: https://lore.kernel.org/r/20250520181644.2673067-13-kan.liang@linux.intel.com
2025-05-21arc/perf: Remove driver-specific throttle supportKan Liang
The throttle support has been added in the generic code. Remove the driver-specific throttle support. Besides the throttle, perf_event_overflow may return true because of event_limit. It already does an inatomic event disable. The pmu->stop is not required either. Signed-off-by: Kan Liang <kan.liang@linux.intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Acked-by: Vineet Gupta <vgupta@kernel.org> Link: https://lore.kernel.org/r/20250520181644.2673067-12-kan.liang@linux.intel.com
2025-05-21alpha/perf: Remove driver-specific throttle supportKan Liang
The throttle support has been added in the generic code. Remove the driver-specific throttle support. Besides the throttle, perf_event_overflow may return true because of event_limit. It already does an inatomic event disable. The pmu->stop is not required either. Signed-off-by: Kan Liang <kan.liang@linux.intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Link: https://lore.kernel.org/r/20250520181644.2673067-11-kan.liang@linux.intel.com
2025-05-21perf/apple_m1: Remove driver-specific throttle supportKan Liang
The throttle support has been added in the generic code. Remove the driver-specific throttle support. Besides the throttle, perf_event_overflow may return true because of event_limit. It already does an inatomic event disable. The pmu->stop is not required either. Signed-off-by: Kan Liang <kan.liang@linux.intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Link: https://lore.kernel.org/r/20250520181644.2673067-10-kan.liang@linux.intel.com
2025-05-21perf/arm: Remove driver-specific throttle supportKan Liang
The throttle support has been added in the generic code. Remove the driver-specific throttle support. Besides the throttle, perf_event_overflow may return true because of event_limit. It already does an inatomic event disable. The pmu->stop is not required either. Signed-off-by: Kan Liang <kan.liang@linux.intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Tested-by: Leo Yan <leo.yan@arm.com> Link: https://lore.kernel.org/r/20250520181644.2673067-9-kan.liang@linux.intel.com
2025-05-21s390/perf: Remove driver-specific throttle supportKan Liang
The throttle support has been added in the generic code. Remove the driver-specific throttle support. Besides the throttle, perf_event_overflow may return true because of event_limit. It already does an inatomic event disable. The pmu->stop is not required either. Signed-off-by: Kan Liang <kan.liang@linux.intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Tested-by: Thomas Richter <tmricht@linux.ibm.com> Link: https://lore.kernel.org/r/20250520181644.2673067-8-kan.liang@linux.intel.com
2025-05-21powerpc/perf: Remove driver-specific throttle supportKan Liang
The throttle support has been added in the generic code. Remove the driver-specific throttle support. Besides the throttle, perf_event_overflow may return true because of event_limit. It already does an inatomic event disable. The pmu->stop is not required either. Signed-off-by: Kan Liang <kan.liang@linux.intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Link: https://lore.kernel.org/r/20250520181644.2673067-7-kan.liang@linux.intel.com
2025-05-21perf/x86/zhaoxin: Remove driver-specific throttle supportKan Liang
The throttle support has been added in the generic code. Remove the driver-specific throttle support. Besides the throttle, perf_event_overflow may return true because of event_limit. It already does an inatomic event disable. The pmu->stop is not required either. Signed-off-by: Kan Liang <kan.liang@linux.intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Link: https://lore.kernel.org/r/20250520181644.2673067-6-kan.liang@linux.intel.com
2025-05-21perf/x86/amd: Remove driver-specific throttle supportKan Liang
The throttle support has been added in the generic code. Remove the driver-specific throttle support. Besides the throttle, perf_event_overflow may return true because of event_limit. It already does an inatomic event disable. The pmu->stop is not required either. Signed-off-by: Kan Liang <kan.liang@linux.intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Reviewed-by: Ravi Bangoria <ravi.bangoria@amd.com> Link: https://lore.kernel.org/r/20250520181644.2673067-5-kan.liang@linux.intel.com
generated by cgit (git 2.34.1) at 2025-07-17 21:52:32 +0000