December 2023 - Linux-stable-mirror

[PATCH 16/25] drm/amd/display: Wake DMCUB before sending a command

by Wayne Lin

From: Nicholas Kazlauskas <nicholas.kazlauskas(a)amd.com> [Why] We can hang in place trying to send commands when the DMCUB isn't powered on. [How] For functions that execute within a DC context or DC lock we can wrap the direct calls to dm_execute_dmub_cmd/list with code that exits idle power optimizations and reallows once we're done with the command submission on success. For DM direct submissions the DM will need to manage the enter/exit sequencing manually. We cannot invoke a DMCUB command directly within the DM execution helper or we can deadlock. Cc: Mario Limonciello <mario.limonciello(a)amd.com> Cc: Alex Deucher <alexander.deucher(a)amd.com> Cc: stable(a)vger.kernel.org Reviewed-by: Hansen Dsouza <hansen.dsouza(a)amd.com> Acked-by: Wayne Lin <wayne.lin(a)amd.com> Signed-off-by: Nicholas Kazlauskas <nicholas.kazlauskas(a)amd.com> --- .../gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 2 +- .../drm/amd/display/dc/bios/command_table2.c | 12 ++--- .../display/dc/clk_mgr/dcn31/dcn31_clk_mgr.c | 2 +- .../dc/clk_mgr/dcn314/dcn314_clk_mgr.c | 2 +- .../dc/clk_mgr/dcn315/dcn315_clk_mgr.c | 2 +- .../dc/clk_mgr/dcn316/dcn316_clk_mgr.c | 2 +- .../display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c | 2 +- drivers/gpu/drm/amd/display/dc/core/dc.c | 12 ++--- .../drm/amd/display/dc/core/dc_hw_sequencer.c | 2 +- drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c | 53 ++++++++++++++++--- drivers/gpu/drm/amd/display/dc/dc_dmub_srv.h | 40 ++++++++++++++ drivers/gpu/drm/amd/display/dc/dc_helper.c | 6 +-- .../gpu/drm/amd/display/dc/dce/dmub_abm_lcd.c | 14 ++--- .../drm/amd/display/dc/dce/dmub_hw_lock_mgr.c | 2 +- .../gpu/drm/amd/display/dc/dce/dmub_outbox.c | 2 +- drivers/gpu/drm/amd/display/dc/dce/dmub_psr.c | 14 ++--- .../gpu/drm/amd/display/dc/dcn21/dcn21_hubp.c | 2 +- .../display/dc/dcn31/dcn31_dio_link_encoder.c | 4 +- .../amd/display/dc/dcn31/dcn31_panel_cntl.c | 4 +- .../amd/display/dc/hwss/dcn21/dcn21_hwseq.c | 4 +- .../amd/display/dc/hwss/dcn30/dcn30_hwseq.c | 8 +-- .../amd/display/dc/hwss/dcn31/dcn31_hwseq.c | 4 +- .../amd/display/dc/hwss/dcn32/dcn32_hwseq.c | 6 +-- .../dc/link/protocols/link_dp_capability.c | 2 +- .../display/dc/link/protocols/link_dp_dpia.c | 3 +- 25 files changed, 143 insertions(+), 63 deletions(-) diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index 0954d7057a9b..34780bcde59c 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -10860,7 +10860,7 @@ static bool dm_edid_parser_send_cea(struct amdgpu_display_manager *dm, input->cea_total_length = total_length; memcpy(input->payload, data, length); - res = dm_execute_dmub_cmd(dm->dc->ctx, &cmd, DM_DMUB_WAIT_TYPE_WAIT_WITH_REPLY); + res = dc_wake_and_execute_dmub_cmd(dm->dc->ctx, &cmd, DM_DMUB_WAIT_TYPE_WAIT_WITH_REPLY); if (!res) { DRM_ERROR("EDID CEA parser failed\n"); return false; diff --git a/drivers/gpu/drm/amd/display/dc/bios/command_table2.c b/drivers/gpu/drm/amd/display/dc/bios/command_table2.c index ab0adabf9dd4..293a919d605d 100644 --- a/drivers/gpu/drm/amd/display/dc/bios/command_table2.c +++ b/drivers/gpu/drm/amd/display/dc/bios/command_table2.c @@ -123,7 +123,7 @@ static void encoder_control_dmcub( sizeof(cmd.digx_encoder_control.header); cmd.digx_encoder_control.encoder_control.dig.stream_param = *dig; - dm_execute_dmub_cmd(dmcub->ctx, &cmd, DM_DMUB_WAIT_TYPE_WAIT); + dc_wake_and_execute_dmub_cmd(dmcub->ctx, &cmd, DM_DMUB_WAIT_TYPE_WAIT); } static enum bp_result encoder_control_digx_v1_5( @@ -259,7 +259,7 @@ static void transmitter_control_dmcub( sizeof(cmd.dig1_transmitter_control.header); cmd.dig1_transmitter_control.transmitter_control.dig = *dig; - dm_execute_dmub_cmd(dmcub->ctx, &cmd, DM_DMUB_WAIT_TYPE_WAIT); + dc_wake_and_execute_dmub_cmd(dmcub->ctx, &cmd, DM_DMUB_WAIT_TYPE_WAIT); } static enum bp_result transmitter_control_v1_6( @@ -321,7 +321,7 @@ static void transmitter_control_dmcub_v1_7( sizeof(cmd.dig1_transmitter_control.header); cmd.dig1_transmitter_control.transmitter_control.dig_v1_7 = *dig; - dm_execute_dmub_cmd(dmcub->ctx, &cmd, DM_DMUB_WAIT_TYPE_WAIT); + dc_wake_and_execute_dmub_cmd(dmcub->ctx, &cmd, DM_DMUB_WAIT_TYPE_WAIT); } static enum bp_result transmitter_control_v1_7( @@ -429,7 +429,7 @@ static void set_pixel_clock_dmcub( sizeof(cmd.set_pixel_clock.header); cmd.set_pixel_clock.pixel_clock.clk = *clk; - dm_execute_dmub_cmd(dmcub->ctx, &cmd, DM_DMUB_WAIT_TYPE_WAIT); + dc_wake_and_execute_dmub_cmd(dmcub->ctx, &cmd, DM_DMUB_WAIT_TYPE_WAIT); } static enum bp_result set_pixel_clock_v7( @@ -796,7 +796,7 @@ static void enable_disp_power_gating_dmcub( sizeof(cmd.enable_disp_power_gating.header); cmd.enable_disp_power_gating.power_gating.pwr = *pwr; - dm_execute_dmub_cmd(dmcub->ctx, &cmd, DM_DMUB_WAIT_TYPE_WAIT); + dc_wake_and_execute_dmub_cmd(dmcub->ctx, &cmd, DM_DMUB_WAIT_TYPE_WAIT); } static enum bp_result enable_disp_power_gating_v2_1( @@ -1006,7 +1006,7 @@ static void enable_lvtma_control_dmcub( pwrseq_instance; cmd.lvtma_control.data.bypass_panel_control_wait = bypass_panel_control_wait; - dm_execute_dmub_cmd(dmcub->ctx, &cmd, DM_DMUB_WAIT_TYPE_WAIT); + dc_wake_and_execute_dmub_cmd(dmcub->ctx, &cmd, DM_DMUB_WAIT_TYPE_WAIT); } static enum bp_result enable_lvtma_control( diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_clk_mgr.c index 3db4ef564b99..ce1386e22576 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn31/dcn31_clk_mgr.c @@ -253,7 +253,7 @@ void dcn31_update_clocks(struct clk_mgr *clk_mgr_base, cmd.notify_clocks.clocks.dispclk_khz = clk_mgr_base->clks.dispclk_khz; cmd.notify_clocks.clocks.dppclk_khz = clk_mgr_base->clks.dppclk_khz; - dm_execute_dmub_cmd(dc->ctx, &cmd, DM_DMUB_WAIT_TYPE_WAIT); + dc_wake_and_execute_dmub_cmd(dc->ctx, &cmd, DM_DMUB_WAIT_TYPE_WAIT); } static int get_vco_frequency_from_reg(struct clk_mgr_internal *clk_mgr) diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.c index 7326b7565846..757528256326 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn314/dcn314_clk_mgr.c @@ -284,7 +284,7 @@ void dcn314_update_clocks(struct clk_mgr *clk_mgr_base, cmd.notify_clocks.clocks.dispclk_khz = clk_mgr_base->clks.dispclk_khz; cmd.notify_clocks.clocks.dppclk_khz = clk_mgr_base->clks.dppclk_khz; - dm_execute_dmub_cmd(dc->ctx, &cmd, DM_DMUB_WAIT_TYPE_WAIT); + dc_wake_and_execute_dmub_cmd(dc->ctx, &cmd, DM_DMUB_WAIT_TYPE_WAIT); } static int get_vco_frequency_from_reg(struct clk_mgr_internal *clk_mgr) diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_clk_mgr.c index 8776055bbeaa..644da4637320 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn315/dcn315_clk_mgr.c @@ -232,7 +232,7 @@ static void dcn315_update_clocks(struct clk_mgr *clk_mgr_base, cmd.notify_clocks.clocks.dispclk_khz = clk_mgr_base->clks.dispclk_khz; cmd.notify_clocks.clocks.dppclk_khz = clk_mgr_base->clks.dppclk_khz; - dm_execute_dmub_cmd(dc->ctx, &cmd, DM_DMUB_WAIT_TYPE_WAIT); + dc_wake_and_execute_dmub_cmd(dc->ctx, &cmd, DM_DMUB_WAIT_TYPE_WAIT); } static void dcn315_dump_clk_registers(struct clk_state_registers_and_bypass *regs_and_bypass, diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn316/dcn316_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn316/dcn316_clk_mgr.c index 09151cc56ce4..12f3e8aa46d8 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn316/dcn316_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn316/dcn316_clk_mgr.c @@ -239,7 +239,7 @@ static void dcn316_update_clocks(struct clk_mgr *clk_mgr_base, cmd.notify_clocks.clocks.dispclk_khz = clk_mgr_base->clks.dispclk_khz; cmd.notify_clocks.clocks.dppclk_khz = clk_mgr_base->clks.dppclk_khz; - dm_execute_dmub_cmd(dc->ctx, &cmd, DM_DMUB_WAIT_TYPE_WAIT); + dc_wake_and_execute_dmub_cmd(dc->ctx, &cmd, DM_DMUB_WAIT_TYPE_WAIT); } static void dcn316_dump_clk_registers(struct clk_state_registers_and_bypass *regs_and_bypass, diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c index 789091f3bdc8..9c660d1facc7 100644 --- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c @@ -343,7 +343,7 @@ void dcn35_update_clocks(struct clk_mgr *clk_mgr_base, cmd.notify_clocks.clocks.dispclk_khz = clk_mgr_base->clks.dispclk_khz; cmd.notify_clocks.clocks.dppclk_khz = clk_mgr_base->clks.dppclk_khz; - dm_execute_dmub_cmd(dc->ctx, &cmd, DM_DMUB_WAIT_TYPE_WAIT); + dc_wake_and_execute_dmub_cmd(dc->ctx, &cmd, DM_DMUB_WAIT_TYPE_WAIT); } static int get_vco_frequency_from_reg(struct clk_mgr_internal *clk_mgr) diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c index 445f87fa0eac..f2fc7df68b58 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc.c @@ -522,7 +522,7 @@ dc_stream_forward_dmub_crc_window(struct dc_dmub_srv *dmub_srv, cmd.secure_display.roi_info.y_end = rect->y + rect->height; } - dm_execute_dmub_cmd(dmub_srv->ctx, &cmd, DM_DMUB_WAIT_TYPE_NO_WAIT); + dc_wake_and_execute_dmub_cmd(dmub_srv->ctx, &cmd, DM_DMUB_WAIT_TYPE_NO_WAIT); } static inline void @@ -3381,7 +3381,7 @@ void dc_dmub_update_dirty_rect(struct dc *dc, update_dirty_rect->panel_inst = panel_inst; update_dirty_rect->pipe_idx = j; - dm_execute_dmub_cmd(dc->ctx, &cmd, DM_DMUB_WAIT_TYPE_NO_WAIT); + dc_wake_and_execute_dmub_cmd(dc->ctx, &cmd, DM_DMUB_WAIT_TYPE_NO_WAIT); } } } @@ -5207,7 +5207,7 @@ bool dc_process_dmub_aux_transfer_async(struct dc *dc, ); } - dm_execute_dmub_cmd(dc->ctx, &cmd, DM_DMUB_WAIT_TYPE_WAIT); + dc_wake_and_execute_dmub_cmd(dc->ctx, &cmd, DM_DMUB_WAIT_TYPE_WAIT); return true; } @@ -5261,7 +5261,7 @@ bool dc_process_dmub_set_config_async(struct dc *dc, cmd.set_config_access.set_config_control.cmd_pkt.msg_type = payload->msg_type; cmd.set_config_access.set_config_control.cmd_pkt.msg_data = payload->msg_data; - if (!dm_execute_dmub_cmd(dc->ctx, &cmd, DM_DMUB_WAIT_TYPE_WAIT_WITH_REPLY)) { + if (!dc_wake_and_execute_dmub_cmd(dc->ctx, &cmd, DM_DMUB_WAIT_TYPE_WAIT_WITH_REPLY)) { /* command is not processed by dmub */ notify->sc_status = SET_CONFIG_UNKNOWN_ERROR; return is_cmd_complete; @@ -5304,7 +5304,7 @@ enum dc_status dc_process_dmub_set_mst_slots(const struct dc *dc, cmd.set_mst_alloc_slots.mst_slots_control.instance = dc->links[link_index]->ddc_hw_inst; cmd.set_mst_alloc_slots.mst_slots_control.mst_alloc_slots = mst_alloc_slots; - if (!dm_execute_dmub_cmd(dc->ctx, &cmd, DM_DMUB_WAIT_TYPE_WAIT_WITH_REPLY)) + if (!dc_wake_and_execute_dmub_cmd(dc->ctx, &cmd, DM_DMUB_WAIT_TYPE_WAIT_WITH_REPLY)) /* command is not processed by dmub */ return DC_ERROR_UNEXPECTED; @@ -5342,7 +5342,7 @@ void dc_process_dmub_dpia_hpd_int_enable(const struct dc *dc, cmd.dpia_hpd_int_enable.header.type = DMUB_CMD__DPIA_HPD_INT_ENABLE; cmd.dpia_hpd_int_enable.enable = hpd_int_enable; - dm_execute_dmub_cmd(dc->ctx, &cmd, DM_DMUB_WAIT_TYPE_WAIT); + dc_wake_and_execute_dmub_cmd(dc->ctx, &cmd, DM_DMUB_WAIT_TYPE_WAIT); DC_LOG_DEBUG("%s: hpd_int_enable(%d)\n", __func__, hpd_int_enable); } diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_hw_sequencer.c b/drivers/gpu/drm/amd/display/dc/core/dc_hw_sequencer.c index fe07160932d6..fc18b9dc946f 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc_hw_sequencer.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc_hw_sequencer.c @@ -724,7 +724,7 @@ void hwss_send_dmcub_cmd(union block_sequence_params *params) union dmub_rb_cmd *cmd = params->send_dmcub_cmd_params.cmd; enum dm_dmub_wait_type wait_type = params->send_dmcub_cmd_params.wait_type; - dm_execute_dmub_cmd(ctx, cmd, wait_type); + dc_wake_and_execute_dmub_cmd(ctx, cmd, wait_type); } void hwss_program_manual_trigger(union block_sequence_params *params) diff --git a/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c b/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c index ccfe2b6046fd..fea13bcd4dc7 100644 --- a/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c +++ b/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c @@ -360,7 +360,7 @@ void dc_dmub_srv_drr_update_cmd(struct dc *dc, uint32_t tg_inst, uint32_t vtotal cmd.drr_update.header.payload_bytes = sizeof(cmd.drr_update) - sizeof(cmd.drr_update.header); // Send the command to the DMCUB. - dm_execute_dmub_cmd(dc->ctx, &cmd, DM_DMUB_WAIT_TYPE_WAIT); + dc_wake_and_execute_dmub_cmd(dc->ctx, &cmd, DM_DMUB_WAIT_TYPE_WAIT); } void dc_dmub_srv_set_drr_manual_trigger_cmd(struct dc *dc, uint32_t tg_inst) @@ -374,7 +374,7 @@ void dc_dmub_srv_set_drr_manual_trigger_cmd(struct dc *dc, uint32_t tg_inst) cmd.drr_update.header.payload_bytes = sizeof(cmd.drr_update) - sizeof(cmd.drr_update.header); // Send the command to the DMCUB. - dm_execute_dmub_cmd(dc->ctx, &cmd, DM_DMUB_WAIT_TYPE_WAIT); + dc_wake_and_execute_dmub_cmd(dc->ctx, &cmd, DM_DMUB_WAIT_TYPE_WAIT); } static uint8_t dc_dmub_srv_get_pipes_for_stream(struct dc *dc, struct dc_stream_state *stream) @@ -467,7 +467,7 @@ bool dc_dmub_srv_p_state_delegate(struct dc *dc, bool should_manage_pstate, stru sizeof(cmd.fw_assisted_mclk_switch) - sizeof(cmd.fw_assisted_mclk_switch.header); // Send the command to the DMCUB. - dm_execute_dmub_cmd(dc->ctx, &cmd, DM_DMUB_WAIT_TYPE_WAIT); + dc_wake_and_execute_dmub_cmd(dc->ctx, &cmd, DM_DMUB_WAIT_TYPE_WAIT); return true; } @@ -488,7 +488,7 @@ void dc_dmub_srv_query_caps_cmd(struct dc_dmub_srv *dc_dmub_srv) cmd.query_feature_caps.header.payload_bytes = sizeof(struct dmub_cmd_query_feature_caps_data); /* If command was processed, copy feature caps to dmub srv */ - if (dm_execute_dmub_cmd(dc_dmub_srv->ctx, &cmd, DM_DMUB_WAIT_TYPE_WAIT_WITH_REPLY) && + if (dc_wake_and_execute_dmub_cmd(dc_dmub_srv->ctx, &cmd, DM_DMUB_WAIT_TYPE_WAIT_WITH_REPLY) && cmd.query_feature_caps.header.ret_status == 0) { memcpy(&dc_dmub_srv->dmub->feature_caps, &cmd.query_feature_caps.query_feature_caps_data, @@ -513,7 +513,7 @@ void dc_dmub_srv_get_visual_confirm_color_cmd(struct dc *dc, struct pipe_ctx *pi cmd.visual_confirm_color.visual_confirm_color_data.visual_confirm_color.panel_inst = panel_inst; // If command was processed, copy feature caps to dmub srv - if (dm_execute_dmub_cmd(dc->ctx, &cmd, DM_DMUB_WAIT_TYPE_WAIT_WITH_REPLY) && + if (dc_wake_and_execute_dmub_cmd(dc->ctx, &cmd, DM_DMUB_WAIT_TYPE_WAIT_WITH_REPLY) && cmd.visual_confirm_color.header.ret_status == 0) { memcpy(&dc->ctx->dmub_srv->dmub->visual_confirm_color, &cmd.visual_confirm_color.visual_confirm_color_data, @@ -875,7 +875,7 @@ void dc_dmub_setup_subvp_dmub_command(struct dc *dc, cmd.fw_assisted_mclk_switch_v2.config_data.watermark_a_cache = wm_val_refclk < 0xFFFF ? wm_val_refclk : 0xFFFF; } - dm_execute_dmub_cmd(dc->ctx, &cmd, DM_DMUB_WAIT_TYPE_WAIT); + dc_wake_and_execute_dmub_cmd(dc->ctx, &cmd, DM_DMUB_WAIT_TYPE_WAIT); } bool dc_dmub_srv_get_diagnostic_data(struct dc_dmub_srv *dc_dmub_srv, struct dmub_diagnostic_data *diag_data) @@ -1112,7 +1112,7 @@ void dc_send_update_cursor_info_to_dmu( pipe_idx, pCtx->plane_res.hubp, pCtx->plane_res.dpp); /* Combine 2nd cmds update_curosr_info to DMU */ - dm_execute_dmub_cmd_list(pCtx->stream->ctx, 2, cmd, DM_DMUB_WAIT_TYPE_WAIT); + dc_wake_and_execute_dmub_cmd_list(pCtx->stream->ctx, 2, cmd, DM_DMUB_WAIT_TYPE_WAIT); } } @@ -1207,6 +1207,7 @@ static void dc_dmub_srv_notify_idle(const struct dc *dc, bool allow_idle) dc->hwss.set_idle_state(dc, true); } + /* NOTE: This does not use the "wake" interface since this is part of the wake path. */ dm_execute_dmub_cmd(dc->ctx, &cmd, DM_DMUB_WAIT_TYPE_WAIT); } @@ -1329,3 +1330,41 @@ void dc_dmub_srv_apply_idle_power_optimizations(const struct dc *dc, bool allow_ else dc_dmub_srv_notify_idle(dc, allow_idle); } + +bool dc_wake_and_execute_dmub_cmd(const struct dc_context *ctx, union dmub_rb_cmd *cmd, + enum dm_dmub_wait_type wait_type) +{ + return dc_wake_and_execute_dmub_cmd_list(ctx, 1, cmd, wait_type); +} + +bool dc_wake_and_execute_dmub_cmd_list(const struct dc_context *ctx, unsigned int count, + union dmub_rb_cmd *cmd, enum dm_dmub_wait_type wait_type) +{ + struct dc_dmub_srv *dc_dmub_srv = ctx->dmub_srv; + bool result = false, reallow_idle = false; + + if (!dc_dmub_srv || !dc_dmub_srv->dmub) + return false; + + if (count == 0) + return true; + + if (dc_dmub_srv->idle_allowed) { + dc_dmub_srv_apply_idle_power_optimizations(ctx->dc, false); + reallow_idle = true; + } + + /* + * These may have different implementations in DM, so ensure + * that we guide it to the expected helper. + */ + if (count > 1) + result = dm_execute_dmub_cmd_list(ctx, count, cmd, wait_type); + else + result = dm_execute_dmub_cmd(ctx, cmd, wait_type); + + if (result && reallow_idle) + dc_dmub_srv_apply_idle_power_optimizations(ctx->dc, true); + + return result; +} diff --git a/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.h b/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.h index b63cba6235fc..784ca3e44414 100644 --- a/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.h +++ b/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.h @@ -106,4 +106,44 @@ bool dc_dmub_srv_is_hw_pwr_up(struct dc_dmub_srv *dc_dmub_srv, bool wait); void dc_dmub_srv_apply_idle_power_optimizations(const struct dc *dc, bool allow_idle); void dc_dmub_srv_set_power_state(struct dc_dmub_srv *dc_dmub_srv, enum dc_acpi_cm_power_state powerState); + +/** + * dc_wake_and_execute_dmub_cmd() - Wrapper for DMUB command execution. + * + * Refer to dc_wake_and_execute_dmub_cmd_list() for usage and limitations, + * This function is a convenience wrapper for a single command execution. + * + * @ctx: DC context + * @cmd: The command to send/receive + * @wait_type: The wait behavior for the execution + * + * Return: true on command submission success, false otherwise + */ +bool dc_wake_and_execute_dmub_cmd(const struct dc_context *ctx, union dmub_rb_cmd *cmd, + enum dm_dmub_wait_type wait_type); + +/** + * dc_wake_and_execute_dmub_cmd_list() - Wrapper for DMUB command list execution. + * + * If the DMCUB hardware was asleep then it wakes the DMUB before + * executing the command and attempts to re-enter if the command + * submission was successful. + * + * This should be the preferred command submission interface provided + * the DC lock is acquired. + * + * Entry/exit out of idle power optimizations would need to be + * manually performed otherwise through dc_allow_idle_optimizations(). + * + * @ctx: DC context + * @count: Number of commands to send/receive + * @cmd: Array of commands to send + * @wait_type: The wait behavior for the execution + * + * Return: true on command submission success, false otherwise + */ +bool dc_wake_and_execute_dmub_cmd_list(const struct dc_context *ctx, unsigned int count, + union dmub_rb_cmd *cmd, enum dm_dmub_wait_type wait_type); + + #endif /* _DMUB_DC_SRV_H_ */ diff --git a/drivers/gpu/drm/amd/display/dc/dc_helper.c b/drivers/gpu/drm/amd/display/dc/dc_helper.c index cb6eaddab720..8f9a67825615 100644 --- a/drivers/gpu/drm/amd/display/dc/dc_helper.c +++ b/drivers/gpu/drm/amd/display/dc/dc_helper.c @@ -50,7 +50,7 @@ static inline void submit_dmub_read_modify_write( cmd_buf->header.payload_bytes = sizeof(struct dmub_cmd_read_modify_write_sequence) * offload->reg_seq_count; - dm_execute_dmub_cmd(ctx, &offload->cmd_data, DM_DMUB_WAIT_TYPE_NO_WAIT); + dc_wake_and_execute_dmub_cmd(ctx, &offload->cmd_data, DM_DMUB_WAIT_TYPE_NO_WAIT); memset(cmd_buf, 0, sizeof(*cmd_buf)); @@ -67,7 +67,7 @@ static inline void submit_dmub_burst_write( cmd_buf->header.payload_bytes = sizeof(uint32_t) * offload->reg_seq_count; - dm_execute_dmub_cmd(ctx, &offload->cmd_data, DM_DMUB_WAIT_TYPE_NO_WAIT); + dc_wake_and_execute_dmub_cmd(ctx, &offload->cmd_data, DM_DMUB_WAIT_TYPE_NO_WAIT); memset(cmd_buf, 0, sizeof(*cmd_buf)); @@ -80,7 +80,7 @@ static inline void submit_dmub_reg_wait( { struct dmub_rb_cmd_reg_wait *cmd_buf = &offload->cmd_data.reg_wait; - dm_execute_dmub_cmd(ctx, &offload->cmd_data, DM_DMUB_WAIT_TYPE_NO_WAIT); + dc_wake_and_execute_dmub_cmd(ctx, &offload->cmd_data, DM_DMUB_WAIT_TYPE_NO_WAIT); memset(cmd_buf, 0, sizeof(*cmd_buf)); offload->reg_seq_count = 0; diff --git a/drivers/gpu/drm/amd/display/dc/dce/dmub_abm_lcd.c b/drivers/gpu/drm/amd/display/dc/dce/dmub_abm_lcd.c index 42c802afc468..4cff36351f40 100644 --- a/drivers/gpu/drm/amd/display/dc/dce/dmub_abm_lcd.c +++ b/drivers/gpu/drm/amd/display/dc/dce/dmub_abm_lcd.c @@ -76,7 +76,7 @@ static void dmub_abm_enable_fractional_pwm(struct dc_context *dc) cmd.abm_set_pwm_frac.abm_set_pwm_frac_data.panel_mask = panel_mask; cmd.abm_set_pwm_frac.header.payload_bytes = sizeof(struct dmub_cmd_abm_set_pwm_frac_data); - dm_execute_dmub_cmd(dc, &cmd, DM_DMUB_WAIT_TYPE_WAIT); + dc_wake_and_execute_dmub_cmd(dc, &cmd, DM_DMUB_WAIT_TYPE_WAIT); } void dmub_abm_init(struct abm *abm, uint32_t backlight) @@ -155,7 +155,7 @@ bool dmub_abm_set_level(struct abm *abm, uint32_t level, uint8_t panel_mask) cmd.abm_set_level.abm_set_level_data.panel_mask = panel_mask; cmd.abm_set_level.header.payload_bytes = sizeof(struct dmub_cmd_abm_set_level_data); - dm_execute_dmub_cmd(dc, &cmd, DM_DMUB_WAIT_TYPE_WAIT); + dc_wake_and_execute_dmub_cmd(dc, &cmd, DM_DMUB_WAIT_TYPE_WAIT); return true; } @@ -186,7 +186,7 @@ void dmub_abm_init_config(struct abm *abm, cmd.abm_init_config.header.payload_bytes = sizeof(struct dmub_cmd_abm_init_config_data); - dm_execute_dmub_cmd(dc, &cmd, DM_DMUB_WAIT_TYPE_WAIT); + dc_wake_and_execute_dmub_cmd(dc, &cmd, DM_DMUB_WAIT_TYPE_WAIT); } @@ -203,7 +203,7 @@ bool dmub_abm_set_pause(struct abm *abm, bool pause, unsigned int panel_inst, un cmd.abm_pause.abm_pause_data.panel_mask = panel_mask; cmd.abm_set_level.header.payload_bytes = sizeof(struct dmub_cmd_abm_pause_data); - dm_execute_dmub_cmd(dc, &cmd, DM_DMUB_WAIT_TYPE_WAIT); + dc_wake_and_execute_dmub_cmd(dc, &cmd, DM_DMUB_WAIT_TYPE_WAIT); return true; } @@ -246,7 +246,7 @@ bool dmub_abm_save_restore( cmd.abm_save_restore.header.payload_bytes = sizeof(struct dmub_rb_cmd_abm_save_restore); - dm_execute_dmub_cmd(dc, &cmd, DM_DMUB_WAIT_TYPE_WAIT); + dc_wake_and_execute_dmub_cmd(dc, &cmd, DM_DMUB_WAIT_TYPE_WAIT); // Copy iramtable data into local structure memcpy((void *)pData, dc->dmub_srv->dmub->scratch_mem_fb.cpu_addr, bytes); @@ -274,7 +274,7 @@ bool dmub_abm_set_pipe(struct abm *abm, cmd.abm_set_pipe.abm_set_pipe_data.ramping_boundary = ramping_boundary; cmd.abm_set_pipe.header.payload_bytes = sizeof(struct dmub_cmd_abm_set_pipe_data); - dm_execute_dmub_cmd(dc, &cmd, DM_DMUB_WAIT_TYPE_WAIT); + dc_wake_and_execute_dmub_cmd(dc, &cmd, DM_DMUB_WAIT_TYPE_WAIT); return true; } @@ -296,7 +296,7 @@ bool dmub_abm_set_backlight_level(struct abm *abm, cmd.abm_set_backlight.abm_set_backlight_data.panel_mask = (0x01 << panel_inst); cmd.abm_set_backlight.header.payload_bytes = sizeof(struct dmub_cmd_abm_set_backlight_data); - dm_execute_dmub_cmd(dc, &cmd, DM_DMUB_WAIT_TYPE_WAIT); + dc_wake_and_execute_dmub_cmd(dc, &cmd, DM_DMUB_WAIT_TYPE_WAIT); return true; } diff --git a/drivers/gpu/drm/amd/display/dc/dce/dmub_hw_lock_mgr.c b/drivers/gpu/drm/amd/display/dc/dce/dmub_hw_lock_mgr.c index 2aa0e01a6891..ba1fec3016d5 100644 --- a/drivers/gpu/drm/amd/display/dc/dce/dmub_hw_lock_mgr.c +++ b/drivers/gpu/drm/amd/display/dc/dce/dmub_hw_lock_mgr.c @@ -47,7 +47,7 @@ void dmub_hw_lock_mgr_cmd(struct dc_dmub_srv *dmub_srv, if (!lock) cmd.lock_hw.lock_hw_data.should_release = 1; - dm_execute_dmub_cmd(dmub_srv->ctx, &cmd, DM_DMUB_WAIT_TYPE_WAIT); + dc_wake_and_execute_dmub_cmd(dmub_srv->ctx, &cmd, DM_DMUB_WAIT_TYPE_WAIT); } void dmub_hw_lock_mgr_inbox0_cmd(struct dc_dmub_srv *dmub_srv, diff --git a/drivers/gpu/drm/amd/display/dc/dce/dmub_outbox.c b/drivers/gpu/drm/amd/display/dc/dce/dmub_outbox.c index d8009b2dc56a..98a778996e1a 100644 --- a/drivers/gpu/drm/amd/display/dc/dce/dmub_outbox.c +++ b/drivers/gpu/drm/amd/display/dc/dce/dmub_outbox.c @@ -48,5 +48,5 @@ void dmub_enable_outbox_notification(struct dc_dmub_srv *dmub_srv) sizeof(cmd.outbox1_enable.header); cmd.outbox1_enable.enable = true; - dm_execute_dmub_cmd(dmub_srv->ctx, &cmd, DM_DMUB_WAIT_TYPE_WAIT); + dc_wake_and_execute_dmub_cmd(dmub_srv->ctx, &cmd, DM_DMUB_WAIT_TYPE_WAIT); } diff --git a/drivers/gpu/drm/amd/display/dc/dce/dmub_psr.c b/drivers/gpu/drm/amd/display/dc/dce/dmub_psr.c index 9d4170a356a2..3d7cef17f881 100644 --- a/drivers/gpu/drm/amd/display/dc/dce/dmub_psr.c +++ b/drivers/gpu/drm/amd/display/dc/dce/dmub_psr.c @@ -171,7 +171,7 @@ static bool dmub_psr_set_version(struct dmub_psr *dmub, struct dc_stream_state * cmd.psr_set_version.psr_set_version_data.panel_inst = panel_inst; cmd.psr_set_version.header.payload_bytes = sizeof(struct dmub_cmd_psr_set_version_data); - dm_execute_dmub_cmd(dc, &cmd, DM_DMUB_WAIT_TYPE_WAIT); + dc_wake_and_execute_dmub_cmd(dc, &cmd, DM_DMUB_WAIT_TYPE_WAIT); return true; } @@ -199,7 +199,7 @@ static void dmub_psr_enable(struct dmub_psr *dmub, bool enable, bool wait, uint8 cmd.psr_enable.header.payload_bytes = 0; // Send header only - dm_execute_dmub_cmd(dc->dmub_srv->ctx, &cmd, DM_DMUB_WAIT_TYPE_WAIT); + dc_wake_and_execute_dmub_cmd(dc->dmub_srv->ctx, &cmd, DM_DMUB_WAIT_TYPE_WAIT); /* Below loops 1000 x 500us = 500 ms. * Exit PSR may need to wait 1-2 frames to power up. Timeout after at @@ -248,7 +248,7 @@ static void dmub_psr_set_level(struct dmub_psr *dmub, uint16_t psr_level, uint8_ cmd.psr_set_level.psr_set_level_data.psr_level = psr_level; cmd.psr_set_level.psr_set_level_data.cmd_version = DMUB_CMD_PSR_CONTROL_VERSION_1; cmd.psr_set_level.psr_set_level_data.panel_inst = panel_inst; - dm_execute_dmub_cmd(dc, &cmd, DM_DMUB_WAIT_TYPE_WAIT); + dc_wake_and_execute_dmub_cmd(dc, &cmd, DM_DMUB_WAIT_TYPE_WAIT); } /* @@ -267,7 +267,7 @@ static void dmub_psr_set_sink_vtotal_in_psr_active(struct dmub_psr *dmub, cmd.psr_set_vtotal.psr_set_vtotal_data.psr_vtotal_idle = psr_vtotal_idle; cmd.psr_set_vtotal.psr_set_vtotal_data.psr_vtotal_su = psr_vtotal_su; - dm_execute_dmub_cmd(dc, &cmd, DM_DMUB_WAIT_TYPE_WAIT); + dc_wake_and_execute_dmub_cmd(dc, &cmd, DM_DMUB_WAIT_TYPE_WAIT); } /* @@ -286,7 +286,7 @@ static void dmub_psr_set_power_opt(struct dmub_psr *dmub, unsigned int power_opt cmd.psr_set_power_opt.psr_set_power_opt_data.power_opt = power_opt; cmd.psr_set_power_opt.psr_set_power_opt_data.panel_inst = panel_inst; - dm_execute_dmub_cmd(dc, &cmd, DM_DMUB_WAIT_TYPE_WAIT); + dc_wake_and_execute_dmub_cmd(dc, &cmd, DM_DMUB_WAIT_TYPE_WAIT); } /* @@ -423,7 +423,7 @@ static bool dmub_psr_copy_settings(struct dmub_psr *dmub, copy_settings_data->relock_delay_frame_cnt = 2; copy_settings_data->dsc_slice_height = psr_context->dsc_slice_height; - dm_execute_dmub_cmd(dc, &cmd, DM_DMUB_WAIT_TYPE_WAIT); + dc_wake_and_execute_dmub_cmd(dc, &cmd, DM_DMUB_WAIT_TYPE_WAIT); return true; } @@ -444,7 +444,7 @@ static void dmub_psr_force_static(struct dmub_psr *dmub, uint8_t panel_inst) cmd.psr_force_static.header.sub_type = DMUB_CMD__PSR_FORCE_STATIC; cmd.psr_enable.header.payload_bytes = 0; - dm_execute_dmub_cmd(dc, &cmd, DM_DMUB_WAIT_TYPE_WAIT); + dc_wake_and_execute_dmub_cmd(dc, &cmd, DM_DMUB_WAIT_TYPE_WAIT); } /* diff --git a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hubp.c b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hubp.c index 68cad55c72ab..e13d69a22c1c 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hubp.c +++ b/drivers/gpu/drm/amd/display/dc/dcn21/dcn21_hubp.c @@ -691,7 +691,7 @@ static void dmcub_PLAT_54186_wa(struct hubp *hubp, cmd.PLAT_54186_wa.flip.flip_params.vmid = flip_regs->vmid; PERF_TRACE(); // TODO: remove after performance is stable. - dm_execute_dmub_cmd(hubp->ctx, &cmd, DM_DMUB_WAIT_TYPE_WAIT); + dc_wake_and_execute_dmub_cmd(hubp->ctx, &cmd, DM_DMUB_WAIT_TYPE_WAIT); PERF_TRACE(); // TODO: remove after performance is stable. } diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_dio_link_encoder.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_dio_link_encoder.c index 4596f3bac1b4..26be5fee7411 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_dio_link_encoder.c +++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_dio_link_encoder.c @@ -125,7 +125,7 @@ static bool query_dp_alt_from_dmub(struct link_encoder *enc, cmd->query_dp_alt.header.payload_bytes = sizeof(cmd->query_dp_alt.data); cmd->query_dp_alt.data.phy_id = phy_id_from_transmitter(enc10->base.transmitter); - if (!dm_execute_dmub_cmd(enc->ctx, cmd, DM_DMUB_WAIT_TYPE_WAIT_WITH_REPLY)) + if (!dc_wake_and_execute_dmub_cmd(enc->ctx, cmd, DM_DMUB_WAIT_TYPE_WAIT_WITH_REPLY)) return false; return true; @@ -436,7 +436,7 @@ static bool link_dpia_control(struct dc_context *dc_ctx, cmd.dig1_dpia_control.dpia_control = *dpia_control; - dm_execute_dmub_cmd(dc_ctx, &cmd, DM_DMUB_WAIT_TYPE_WAIT); + dc_wake_and_execute_dmub_cmd(dc_ctx, &cmd, DM_DMUB_WAIT_TYPE_WAIT); return true; } diff --git a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_panel_cntl.c b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_panel_cntl.c index d849b1eaa4a5..03248422d6ff 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_panel_cntl.c +++ b/drivers/gpu/drm/amd/display/dc/dcn31/dcn31_panel_cntl.c @@ -52,7 +52,7 @@ static bool dcn31_query_backlight_info(struct panel_cntl *panel_cntl, union dmub cmd->panel_cntl.header.payload_bytes = sizeof(cmd->panel_cntl.data); cmd->panel_cntl.data.pwrseq_inst = dcn31_panel_cntl->base.pwrseq_inst; - return dm_execute_dmub_cmd(dc_dmub_srv->ctx, cmd, DM_DMUB_WAIT_TYPE_WAIT_WITH_REPLY); + return dc_wake_and_execute_dmub_cmd(dc_dmub_srv->ctx, cmd, DM_DMUB_WAIT_TYPE_WAIT_WITH_REPLY); } static uint32_t dcn31_get_16_bit_backlight_from_pwm(struct panel_cntl *panel_cntl) @@ -85,7 +85,7 @@ static uint32_t dcn31_panel_cntl_hw_init(struct panel_cntl *panel_cntl) panel_cntl->stored_backlight_registers.LVTMA_PWRSEQ_REF_DIV_BL_PWM_REF_DIV; cmd.panel_cntl.data.bl_pwm_ref_div2 = panel_cntl->stored_backlight_registers.PANEL_PWRSEQ_REF_DIV2; - if (!dm_execute_dmub_cmd(dc_dmub_srv->ctx, &cmd, DM_DMUB_WAIT_TYPE_WAIT_WITH_REPLY)) + if (!dc_wake_and_execute_dmub_cmd(dc_dmub_srv->ctx, &cmd, DM_DMUB_WAIT_TYPE_WAIT_WITH_REPLY)) return 0; panel_cntl->stored_backlight_registers.BL_PWM_CNTL = cmd.panel_cntl.data.bl_pwm_cntl; diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn21/dcn21_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn21/dcn21_hwseq.c index 08783ad097d2..8e88dcaf88f5 100644 --- a/drivers/gpu/drm/amd/display/dc/hwss/dcn21/dcn21_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn21/dcn21_hwseq.c @@ -154,7 +154,7 @@ static bool dmub_abm_set_pipe(struct abm *abm, uint32_t otg_inst, cmd.abm_set_pipe.abm_set_pipe_data.ramping_boundary = ramping_boundary; cmd.abm_set_pipe.header.payload_bytes = sizeof(struct dmub_cmd_abm_set_pipe_data); - dm_execute_dmub_cmd(dc, &cmd, DM_DMUB_WAIT_TYPE_WAIT); + dc_wake_and_execute_dmub_cmd(dc, &cmd, DM_DMUB_WAIT_TYPE_WAIT); return true; } @@ -173,7 +173,7 @@ static void dmub_abm_set_backlight(struct dc_context *dc, uint32_t backlight_pwm cmd.abm_set_backlight.abm_set_backlight_data.panel_mask = (0x01 << panel_inst); cmd.abm_set_backlight.header.payload_bytes = sizeof(struct dmub_cmd_abm_set_backlight_data); - dm_execute_dmub_cmd(dc, &cmd, DM_DMUB_WAIT_TYPE_WAIT); + dc_wake_and_execute_dmub_cmd(dc, &cmd, DM_DMUB_WAIT_TYPE_WAIT); } void dcn21_set_abm_immediate_disable(struct pipe_ctx *pipe_ctx) diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn30/dcn30_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn30/dcn30_hwseq.c index fd8a8c10a201..d337578d7e73 100644 --- a/drivers/gpu/drm/amd/display/dc/hwss/dcn30/dcn30_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn30/dcn30_hwseq.c @@ -754,7 +754,7 @@ bool dcn30_apply_idle_power_optimizations(struct dc *dc, bool enable) cmd.mall.header.sub_type = DMUB_CMD__MALL_ACTION_NO_DF_REQ; cmd.mall.header.payload_bytes = sizeof(cmd.mall) - sizeof(cmd.mall.header); - dm_execute_dmub_cmd(dc->ctx, &cmd, DM_DMUB_WAIT_TYPE_NO_WAIT); + dc_wake_and_execute_dmub_cmd(dc->ctx, &cmd, DM_DMUB_WAIT_TYPE_NO_WAIT); return true; } @@ -876,7 +876,7 @@ bool dcn30_apply_idle_power_optimizations(struct dc *dc, bool enable) cmd.mall.cursor_height = cursor_attr.height; cmd.mall.cursor_pitch = cursor_attr.pitch; - dm_execute_dmub_cmd(dc->ctx, &cmd, DM_DMUB_WAIT_TYPE_WAIT); + dc_wake_and_execute_dmub_cmd(dc->ctx, &cmd, DM_DMUB_WAIT_TYPE_WAIT); /* Use copied cursor, and it's okay to not switch back */ cursor_attr.address.quad_part = cmd.mall.cursor_copy_dst.quad_part; @@ -892,7 +892,7 @@ bool dcn30_apply_idle_power_optimizations(struct dc *dc, bool enable) cmd.mall.tmr_scale = tmr_scale; cmd.mall.debug_bits = dc->debug.mall_error_as_fatal; - dm_execute_dmub_cmd(dc->ctx, &cmd, DM_DMUB_WAIT_TYPE_NO_WAIT); + dc_wake_and_execute_dmub_cmd(dc->ctx, &cmd, DM_DMUB_WAIT_TYPE_NO_WAIT); return true; } @@ -909,7 +909,7 @@ bool dcn30_apply_idle_power_optimizations(struct dc *dc, bool enable) cmd.mall.header.payload_bytes = sizeof(cmd.mall) - sizeof(cmd.mall.header); - dm_execute_dmub_cmd(dc->ctx, &cmd, DM_DMUB_WAIT_TYPE_WAIT); + dc_wake_and_execute_dmub_cmd(dc->ctx, &cmd, DM_DMUB_WAIT_TYPE_WAIT); return true; } diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn31/dcn31_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn31/dcn31_hwseq.c index 5d62805f3bdf..994250b6f2ef 100644 --- a/drivers/gpu/drm/amd/display/dc/hwss/dcn31/dcn31_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn31/dcn31_hwseq.c @@ -416,7 +416,7 @@ void dcn31_z10_save_init(struct dc *dc) cmd.dcn_restore.header.type = DMUB_CMD__IDLE_OPT; cmd.dcn_restore.header.sub_type = DMUB_CMD__IDLE_OPT_DCN_SAVE_INIT; - dm_execute_dmub_cmd(dc->ctx, &cmd, DM_DMUB_WAIT_TYPE_WAIT); + dc_wake_and_execute_dmub_cmd(dc->ctx, &cmd, DM_DMUB_WAIT_TYPE_WAIT); } void dcn31_z10_restore(const struct dc *dc) @@ -434,7 +434,7 @@ void dcn31_z10_restore(const struct dc *dc) cmd.dcn_restore.header.type = DMUB_CMD__IDLE_OPT; cmd.dcn_restore.header.sub_type = DMUB_CMD__IDLE_OPT_DCN_RESTORE; - dm_execute_dmub_cmd(dc->ctx, &cmd, DM_DMUB_WAIT_TYPE_WAIT); + dc_wake_and_execute_dmub_cmd(dc->ctx, &cmd, DM_DMUB_WAIT_TYPE_WAIT); } void dcn31_hubp_pg_control(struct dce_hwseq *hws, unsigned int hubp_inst, bool power_on) diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.c index 5c323718ec90..92fe06870e3a 100644 --- a/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.c @@ -277,7 +277,7 @@ bool dcn32_apply_idle_power_optimizations(struct dc *dc, bool enable) cmd.cab.header.sub_type = DMUB_CMD__CAB_NO_DCN_REQ; cmd.cab.header.payload_bytes = sizeof(cmd.cab) - sizeof(cmd.cab.header); - dm_execute_dmub_cmd(dc->ctx, &cmd, DM_DMUB_WAIT_TYPE_NO_WAIT); + dc_wake_and_execute_dmub_cmd(dc->ctx, &cmd, DM_DMUB_WAIT_TYPE_NO_WAIT); return true; } @@ -311,7 +311,7 @@ bool dcn32_apply_idle_power_optimizations(struct dc *dc, bool enable) cmd.cab.header.payload_bytes = sizeof(cmd.cab) - sizeof(cmd.cab.header); cmd.cab.cab_alloc_ways = (uint8_t)ways; - dm_execute_dmub_cmd(dc->ctx, &cmd, DM_DMUB_WAIT_TYPE_NO_WAIT); + dc_wake_and_execute_dmub_cmd(dc->ctx, &cmd, DM_DMUB_WAIT_TYPE_NO_WAIT); return true; } @@ -327,7 +327,7 @@ bool dcn32_apply_idle_power_optimizations(struct dc *dc, bool enable) cmd.cab.header.payload_bytes = sizeof(cmd.cab) - sizeof(cmd.cab.header); - dm_execute_dmub_cmd(dc->ctx, &cmd, DM_DMUB_WAIT_TYPE_WAIT); + dc_wake_and_execute_dmub_cmd(dc->ctx, &cmd, DM_DMUB_WAIT_TYPE_WAIT); return true; } diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_capability.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_capability.c index 3c5334cdb3fb..289f5d133342 100644 --- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_capability.c +++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_capability.c @@ -1398,7 +1398,7 @@ static bool get_usbc_cable_id(struct dc_link *link, union dp_cable_id *cable_id) cmd.cable_id.header.payload_bytes = sizeof(cmd.cable_id.data); cmd.cable_id.data.input.phy_inst = resource_transmitter_to_phy_idx( link->dc, link->link_enc->transmitter); - if (dm_execute_dmub_cmd(link->dc->ctx, &cmd, DM_DMUB_WAIT_TYPE_WAIT_WITH_REPLY) && + if (dc_wake_and_execute_dmub_cmd(link->dc->ctx, &cmd, DM_DMUB_WAIT_TYPE_WAIT_WITH_REPLY) && cmd.cable_id.header.ret_status == 1) { cable_id->raw = cmd.cable_id.data.output_raw; DC_LOG_DC("usbc_cable_id = %d.\n", cable_id->raw); diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia.c index 0bb749133909..982eda3c46f5 100644 --- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia.c +++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_dpia.c @@ -90,7 +90,8 @@ bool dpia_query_hpd_status(struct dc_link *link) cmd.query_hpd.data.ch_type = AUX_CHANNEL_DPIA; /* Return HPD status reported by DMUB if query successfully executed. */ - if (dm_execute_dmub_cmd(dmub_srv->ctx, &cmd, DM_DMUB_WAIT_TYPE_WAIT_WITH_REPLY) && cmd.query_hpd.data.status == AUX_RET_SUCCESS) + if (dc_wake_and_execute_dmub_cmd(dmub_srv->ctx, &cmd, DM_DMUB_WAIT_TYPE_WAIT_WITH_REPLY) && + cmd.query_hpd.data.status == AUX_RET_SUCCESS) is_hpd_high = cmd.query_hpd.data.result; DC_LOG_DEBUG("%s: link(%d) dpia(%d) cmd_status(%d) result(%d)\n", -- 2.37.3

10 months, 1 week

1
0
0 0

[PATCH 15/25] drm/amd/display: Refactor DMCUB enter/exit idle interface

by Wayne Lin

From: Nicholas Kazlauskas <nicholas.kazlauskas(a)amd.com> [Why] We can hang in place trying to send commands when the DMCUB isn't powered on. [How] We need to exit out of the idle state prior to sending a command, but the process that performs the exit also invokes a command itself. Fixing this issue involves the following: 1. Using a software state to track whether or not we need to start the process to exit idle or notify idle. It's possible for the hardware to have exited an idle state without driver knowledge, but entering one is always restricted to a driver allow - which makes the SW state vs HW state mismatch issue purely one of optimization, which should seldomly be hit, if at all. 2. Refactor any instances of exit/notify idle to use a single wrapper that maintains this SW state. This works simialr to dc_allow_idle_optimizations, but works at the DMCUB level and makes sure the state is marked prior to any notify/exit idle so we don't enter an infinite loop. 3. Make sure we exit out of idle prior to sending any commands or waiting for DMCUB idle. This patch takes care of 1/2. A future patch will take care of wrapping DMCUB command submission with calls to this new interface. Cc: Mario Limonciello <mario.limonciello(a)amd.com> Cc: Alex Deucher <alexander.deucher(a)amd.com> Cc: stable(a)vger.kernel.org Reviewed-by: Hansen Dsouza <hansen.dsouza(a)amd.com> Acked-by: Wayne Lin <wayne.lin(a)amd.com> Signed-off-by: Nicholas Kazlauskas <nicholas.kazlauskas(a)amd.com> --- .../gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 4 +- drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c | 37 ++++++++++++++++++- drivers/gpu/drm/amd/display/dc/dc_dmub_srv.h | 6 ++- .../amd/display/dc/hwss/dcn35/dcn35_hwseq.c | 8 +--- 4 files changed, 43 insertions(+), 12 deletions(-) diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c index 84efa9e7c951..0954d7057a9b 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -2854,7 +2854,7 @@ static int dm_resume(void *handle) bool need_hotplug = false; if (dm->dc->caps.ips_support) { - dc_dmub_srv_exit_low_power_state(dm->dc); + dc_dmub_srv_apply_idle_power_optimizations(dm->dc, false); } if (amdgpu_in_reset(adev)) { @@ -8968,7 +8968,7 @@ static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state) if (new_con_state->crtc && new_con_state->crtc->state->active && drm_atomic_crtc_needs_modeset(new_con_state->crtc->state)) { - dc_dmub_srv_exit_low_power_state(dm->dc); + dc_dmub_srv_apply_idle_power_optimizations(dm->dc, false); break; } } diff --git a/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c b/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c index eb6f5640f19a..ccfe2b6046fd 100644 --- a/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c +++ b/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c @@ -1162,6 +1162,9 @@ bool dc_dmub_srv_is_hw_pwr_up(struct dc_dmub_srv *dc_dmub_srv, bool wait) struct dc_context *dc_ctx = dc_dmub_srv->ctx; enum dmub_status status; + if (!dc_dmub_srv || !dc_dmub_srv->dmub) + return true; + if (dc_dmub_srv->ctx->dc->debug.dmcub_emulation) return true; @@ -1183,7 +1186,7 @@ bool dc_dmub_srv_is_hw_pwr_up(struct dc_dmub_srv *dc_dmub_srv, bool wait) return true; } -void dc_dmub_srv_notify_idle(const struct dc *dc, bool allow_idle) +static void dc_dmub_srv_notify_idle(const struct dc *dc, bool allow_idle) { union dmub_rb_cmd cmd = {0}; @@ -1207,7 +1210,7 @@ void dc_dmub_srv_notify_idle(const struct dc *dc, bool allow_idle) dm_execute_dmub_cmd(dc->ctx, &cmd, DM_DMUB_WAIT_TYPE_WAIT); } -void dc_dmub_srv_exit_low_power_state(const struct dc *dc) +static void dc_dmub_srv_exit_low_power_state(const struct dc *dc) { const uint32_t max_num_polls = 10000; uint32_t allow_state = 0; @@ -1220,6 +1223,9 @@ void dc_dmub_srv_exit_low_power_state(const struct dc *dc) if (!dc->idle_optimizations_allowed) return; + if (!dc->ctx->dmub_srv || !dc->ctx->dmub_srv->dmub) + return; + if (dc->hwss.get_idle_state && dc->hwss.set_idle_state && dc->clk_mgr->funcs->exit_low_power_state) { @@ -1296,3 +1302,30 @@ void dc_dmub_srv_set_power_state(struct dc_dmub_srv *dc_dmub_srv, enum dc_acpi_c else dmub_srv_set_power_state(dmub, DMUB_POWER_STATE_D3); } + +void dc_dmub_srv_apply_idle_power_optimizations(const struct dc *dc, bool allow_idle) +{ + struct dc_dmub_srv *dc_dmub_srv = dc->ctx->dmub_srv; + + if (!dc_dmub_srv || !dc_dmub_srv->dmub) + return; + + if (dc_dmub_srv->idle_allowed == allow_idle) + return; + + /* + * Entering a low power state requires a driver notification. + * Powering up the hardware requires notifying PMFW and DMCUB. + * Clearing the driver idle allow requires a DMCUB command. + * DMCUB commands requires the DMCUB to be powered up and restored. + * + * Exit out early to prevent an infinite loop of DMCUB commands + * triggering exit low power - use software state to track this. + */ + dc_dmub_srv->idle_allowed = allow_idle; + + if (!allow_idle) + dc_dmub_srv_exit_low_power_state(dc); + else + dc_dmub_srv_notify_idle(dc, allow_idle); +} diff --git a/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.h b/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.h index c25ce7546f71..b63cba6235fc 100644 --- a/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.h +++ b/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.h @@ -50,6 +50,8 @@ struct dc_dmub_srv { struct dc_context *ctx; void *dm; + + bool idle_allowed; }; void dc_dmub_srv_wait_idle(struct dc_dmub_srv *dc_dmub_srv); @@ -100,8 +102,8 @@ void dc_dmub_srv_enable_dpia_trace(const struct dc *dc); void dc_dmub_srv_subvp_save_surf_addr(const struct dc_dmub_srv *dc_dmub_srv, const struct dc_plane_address *addr, uint8_t subvp_index); bool dc_dmub_srv_is_hw_pwr_up(struct dc_dmub_srv *dc_dmub_srv, bool wait); -void dc_dmub_srv_notify_idle(const struct dc *dc, bool allow_idle); -void dc_dmub_srv_exit_low_power_state(const struct dc *dc); + +void dc_dmub_srv_apply_idle_power_optimizations(const struct dc *dc, bool allow_idle); void dc_dmub_srv_set_power_state(struct dc_dmub_srv *dc_dmub_srv, enum dc_acpi_cm_power_state powerState); #endif /* _DMUB_DC_SRV_H_ */ diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.c index 9262d3336182..f48001317fab 100644 --- a/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.c @@ -687,11 +687,7 @@ bool dcn35_apply_idle_power_optimizations(struct dc *dc, bool enable) } // TODO: review other cases when idle optimization is allowed - - if (!enable) - dc_dmub_srv_exit_low_power_state(dc); - else - dc_dmub_srv_notify_idle(dc, enable); + dc_dmub_srv_apply_idle_power_optimizations(dc, enable); return true; } @@ -701,7 +697,7 @@ void dcn35_z10_restore(const struct dc *dc) if (dc->debug.disable_z10) return; - dc_dmub_srv_exit_low_power_state(dc); + dc_dmub_srv_apply_idle_power_optimizations(dc, false); dcn31_z10_restore(dc); } -- 2.37.3

10 months, 1 week

1
0
0 0

Re: [PATCH] irq: Resolve that mask_irq/unmask_irq may not be called in pairs

by xiongxin

在 2023/12/13 00:57, Jiri Kosina 写道: > On Mon, 11 Dec 2023, xiongxin wrote: > >> In this scenario, unmask_irq() will not be called, and then gpio corresponding >> interrupt pin will be masked. Finally, in the suspend() process driven by gpio >> interrupt controller, the interrupt mask register will be saved, and then >> masked will continue to be read when resuming () process. After the kernel >> resumed, the i2c hid gpio interrupt was masked and the i2c hid device was >> unavailable. > > In addition to what Thomas already wrote -- what exactly is the problem > you are trying to solve here? > > Is it that your device drive by i2c-hid driver is no longer sending any > data reports after a suspend/resume cycle? What makes you think that it's > because of its IRQ being disabled? > > Don't you just perhaps need I2C_HID_QUIRK_RESET_ON_RESUME quirk for that > device? > I have confirmed I2C_HID_QUIRK_RESET_ON_RESUME quirk, the current BUG is related to GPIO interrupt masking, and has little to do with hid code. I explained the detailed process of the BUG in another email.

10 months, 1 week

1
0
0 0

[merged mm-hotfixes-stable] mm-mglru-reclaim-offlined-memcgs-harder.patch removed from -mm tree

by Andrew Morton

The quilt patch titled Subject: mm/mglru: reclaim offlined memcgs harder has been removed from the -mm tree. Its filename was mm-mglru-reclaim-offlined-memcgs-harder.patch This patch was dropped because it was merged into the mm-hotfixes-stable branch of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm ------------------------------------------------------ From: Yu Zhao <yuzhao(a)google.com> Subject: mm/mglru: reclaim offlined memcgs harder Date: Thu, 7 Dec 2023 23:14:07 -0700 In the effort to reduce zombie memcgs [1], it was discovered that the memcg LRU doesn't apply enough pressure on offlined memcgs. Specifically, instead of rotating them to the tail of the current generation (MEMCG_LRU_TAIL) for a second attempt, it moves them to the next generation (MEMCG_LRU_YOUNG) after the first attempt. Not applying enough pressure on offlined memcgs can cause them to build up, and this can be particularly harmful to memory-constrained systems. On Pixel 8 Pro, launching apps for 50 cycles: Before After Change Zombie memcgs 45 35 -22% [1] https://lore.kernel.org/CABdmKX2M6koq4Q0Cmp_-=wbP0Qa190HdEGGaHfxNS05gAkUtPA… Link: https://lkml.kernel.org/r/20231208061407.2125867-4-yuzhao@google.com Fixes: e4dde56cd208 ("mm: multi-gen LRU: per-node lru_gen_folio lists") Signed-off-by: Yu Zhao <yuzhao(a)google.com> Reported-by: T.J. Mercier <tjmercier(a)google.com> Tested-by: T.J. Mercier <tjmercier(a)google.com> Cc: Charan Teja Kalla <quic_charante(a)quicinc.com> Cc: Hillf Danton <hdanton(a)sina.com> Cc: Jaroslav Pulchart <jaroslav.pulchart(a)gooddata.com> Cc: Kairui Song <ryncsn(a)gmail.com> Cc: Kalesh Singh <kaleshsingh(a)google.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- include/linux/mmzone.h | 8 ++++---- mm/vmscan.c | 24 ++++++++++++++++-------- 2 files changed, 20 insertions(+), 12 deletions(-) --- a/include/linux/mmzone.h~mm-mglru-reclaim-offlined-memcgs-harder +++ a/include/linux/mmzone.h @@ -519,10 +519,10 @@ void lru_gen_look_around(struct page_vma * 1. Exceeding the soft limit, which triggers MEMCG_LRU_HEAD; * 2. The first attempt to reclaim a memcg below low, which triggers * MEMCG_LRU_TAIL; - * 3. The first attempt to reclaim a memcg below reclaimable size threshold, - * which triggers MEMCG_LRU_TAIL; - * 4. The second attempt to reclaim a memcg below reclaimable size threshold, - * which triggers MEMCG_LRU_YOUNG; + * 3. The first attempt to reclaim a memcg offlined or below reclaimable size + * threshold, which triggers MEMCG_LRU_TAIL; + * 4. The second attempt to reclaim a memcg offlined or below reclaimable size + * threshold, which triggers MEMCG_LRU_YOUNG; * 5. Attempting to reclaim a memcg below min, which triggers MEMCG_LRU_YOUNG; * 6. Finishing the aging on the eviction path, which triggers MEMCG_LRU_YOUNG; * 7. Offlining a memcg, which triggers MEMCG_LRU_OLD. --- a/mm/vmscan.c~mm-mglru-reclaim-offlined-memcgs-harder +++ a/mm/vmscan.c @@ -4598,7 +4598,12 @@ static bool should_run_aging(struct lruv } /* try to scrape all its memory if this memcg was deleted */ - *nr_to_scan = mem_cgroup_online(memcg) ? (total >> sc->priority) : total; + if (!mem_cgroup_online(memcg)) { + *nr_to_scan = total; + return false; + } + + *nr_to_scan = total >> sc->priority; /* * The aging tries to be lazy to reduce the overhead, while the eviction @@ -4719,14 +4724,9 @@ static int shrink_one(struct lruvec *lru bool success; unsigned long scanned = sc->nr_scanned; unsigned long reclaimed = sc->nr_reclaimed; - int seg = lru_gen_memcg_seg(lruvec); struct mem_cgroup *memcg = lruvec_memcg(lruvec); struct pglist_data *pgdat = lruvec_pgdat(lruvec); - /* see the comment on MEMCG_NR_GENS */ - if (!lruvec_is_sizable(lruvec, sc)) - return seg != MEMCG_LRU_TAIL ? MEMCG_LRU_TAIL : MEMCG_LRU_YOUNG; - mem_cgroup_calculate_protection(NULL, memcg); if (mem_cgroup_below_min(NULL, memcg)) @@ -4734,7 +4734,7 @@ static int shrink_one(struct lruvec *lru if (mem_cgroup_below_low(NULL, memcg)) { /* see the comment on MEMCG_NR_GENS */ - if (seg != MEMCG_LRU_TAIL) + if (lru_gen_memcg_seg(lruvec) != MEMCG_LRU_TAIL) return MEMCG_LRU_TAIL; memcg_memory_event(memcg, MEMCG_LOW); @@ -4750,7 +4750,15 @@ static int shrink_one(struct lruvec *lru flush_reclaim_state(sc); - return success ? MEMCG_LRU_YOUNG : 0; + if (success && mem_cgroup_online(memcg)) + return MEMCG_LRU_YOUNG; + + if (!success && lruvec_is_sizable(lruvec, sc)) + return 0; + + /* one retry if offlined or too small */ + return lru_gen_memcg_seg(lruvec) != MEMCG_LRU_TAIL ? + MEMCG_LRU_TAIL : MEMCG_LRU_YOUNG; } #ifdef CONFIG_MEMCG _ Patches currently in -mm which might be from yuzhao(a)google.com are

10 months, 1 week

1
0
0 0

[merged mm-hotfixes-stable] mm-mglru-respect-min_ttl_ms-with-memcgs.patch removed from -mm tree

by Andrew Morton

The quilt patch titled Subject: mm/mglru: respect min_ttl_ms with memcgs has been removed from the -mm tree. Its filename was mm-mglru-respect-min_ttl_ms-with-memcgs.patch This patch was dropped because it was merged into the mm-hotfixes-stable branch of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm ------------------------------------------------------ From: Yu Zhao <yuzhao(a)google.com> Subject: mm/mglru: respect min_ttl_ms with memcgs Date: Thu, 7 Dec 2023 23:14:06 -0700 While investigating kswapd "consuming 100% CPU" [1] (also see "mm/mglru: try to stop at high watermarks"), it was discovered that the memcg LRU can breach the thrashing protection imposed by min_ttl_ms. Before the memcg LRU: kswapd() shrink_node_memcgs() mem_cgroup_iter() inc_max_seq() // always hit a different memcg lru_gen_age_node() mem_cgroup_iter() check the timestamp of the oldest generation After the memcg LRU: kswapd() shrink_many() restart: iterate the memcg LRU: inc_max_seq() // occasionally hit the same memcg if raced with lru_gen_rotate_memcg(): goto restart lru_gen_age_node() mem_cgroup_iter() check the timestamp of the oldest generation Specifically, when the restart happens in shrink_many(), it needs to stick with the (memcg LRU) generation it began with. In other words, it should neither re-read memcg_lru->seq nor age an lruvec of a different generation. Otherwise it can hit the same memcg multiple times without giving lru_gen_age_node() a chance to check the timestamp of that memcg's oldest generation (against min_ttl_ms). [1] https://lore.kernel.org/CAK8fFZ4DY+GtBA40Pm7Nn5xCHy+51w3sfxPqkqpqakSXYyX+Wg… Link: https://lkml.kernel.org/r/20231208061407.2125867-3-yuzhao@google.com Fixes: e4dde56cd208 ("mm: multi-gen LRU: per-node lru_gen_folio lists") Signed-off-by: Yu Zhao <yuzhao(a)google.com> Tested-by: T.J. Mercier <tjmercier(a)google.com> Cc: Charan Teja Kalla <quic_charante(a)quicinc.com> Cc: Hillf Danton <hdanton(a)sina.com> Cc: Jaroslav Pulchart <jaroslav.pulchart(a)gooddata.com> Cc: Kairui Song <ryncsn(a)gmail.com> Cc: Kalesh Singh <kaleshsingh(a)google.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- include/linux/mmzone.h | 30 +++++++++++++++++------------- mm/vmscan.c | 30 ++++++++++++++++-------------- 2 files changed, 33 insertions(+), 27 deletions(-) --- a/include/linux/mmzone.h~mm-mglru-respect-min_ttl_ms-with-memcgs +++ a/include/linux/mmzone.h @@ -505,33 +505,37 @@ void lru_gen_look_around(struct page_vma * the old generation, is incremented when all its bins become empty. * * There are four operations: - * 1. MEMCG_LRU_HEAD, which moves an memcg to the head of a random bin in its + * 1. MEMCG_LRU_HEAD, which moves a memcg to the head of a random bin in its * current generation (old or young) and updates its "seg" to "head"; - * 2. MEMCG_LRU_TAIL, which moves an memcg to the tail of a random bin in its + * 2. MEMCG_LRU_TAIL, which moves a memcg to the tail of a random bin in its * current generation (old or young) and updates its "seg" to "tail"; - * 3. MEMCG_LRU_OLD, which moves an memcg to the head of a random bin in the old + * 3. MEMCG_LRU_OLD, which moves a memcg to the head of a random bin in the old * generation, updates its "gen" to "old" and resets its "seg" to "default"; - * 4. MEMCG_LRU_YOUNG, which moves an memcg to the tail of a random bin in the + * 4. MEMCG_LRU_YOUNG, which moves a memcg to the tail of a random bin in the * young generation, updates its "gen" to "young" and resets its "seg" to * "default". * * The events that trigger the above operations are: * 1. Exceeding the soft limit, which triggers MEMCG_LRU_HEAD; - * 2. The first attempt to reclaim an memcg below low, which triggers + * 2. The first attempt to reclaim a memcg below low, which triggers * MEMCG_LRU_TAIL; - * 3. The first attempt to reclaim an memcg below reclaimable size threshold, + * 3. The first attempt to reclaim a memcg below reclaimable size threshold, * which triggers MEMCG_LRU_TAIL; - * 4. The second attempt to reclaim an memcg below reclaimable size threshold, + * 4. The second attempt to reclaim a memcg below reclaimable size threshold, * which triggers MEMCG_LRU_YOUNG; - * 5. Attempting to reclaim an memcg below min, which triggers MEMCG_LRU_YOUNG; + * 5. Attempting to reclaim a memcg below min, which triggers MEMCG_LRU_YOUNG; * 6. Finishing the aging on the eviction path, which triggers MEMCG_LRU_YOUNG; - * 7. Offlining an memcg, which triggers MEMCG_LRU_OLD. + * 7. Offlining a memcg, which triggers MEMCG_LRU_OLD. * - * Note that memcg LRU only applies to global reclaim, and the round-robin - * incrementing of their max_seq counters ensures the eventual fairness to all - * eligible memcgs. For memcg reclaim, it still relies on mem_cgroup_iter(). + * Notes: + * 1. Memcg LRU only applies to global reclaim, and the round-robin incrementing + * of their max_seq counters ensures the eventual fairness to all eligible + * memcgs. For memcg reclaim, it still relies on mem_cgroup_iter(). + * 2. There are only two valid generations: old (seq) and young (seq+1). + * MEMCG_NR_GENS is set to three so that when reading the generation counter + * locklessly, a stale value (seq-1) does not wraparound to young. */ -#define MEMCG_NR_GENS 2 +#define MEMCG_NR_GENS 3 #define MEMCG_NR_BINS 8 struct lru_gen_memcg { --- a/mm/vmscan.c~mm-mglru-respect-min_ttl_ms-with-memcgs +++ a/mm/vmscan.c @@ -4089,6 +4089,9 @@ static void lru_gen_rotate_memcg(struct else VM_WARN_ON_ONCE(true); + WRITE_ONCE(lruvec->lrugen.seg, seg); + WRITE_ONCE(lruvec->lrugen.gen, new); + hlist_nulls_del_rcu(&lruvec->lrugen.list); if (op == MEMCG_LRU_HEAD || op == MEMCG_LRU_OLD) @@ -4099,9 +4102,6 @@ static void lru_gen_rotate_memcg(struct pgdat->memcg_lru.nr_memcgs[old]--; pgdat->memcg_lru.nr_memcgs[new]++; - lruvec->lrugen.gen = new; - WRITE_ONCE(lruvec->lrugen.seg, seg); - if (!pgdat->memcg_lru.nr_memcgs[old] && old == get_memcg_gen(pgdat->memcg_lru.seq)) WRITE_ONCE(pgdat->memcg_lru.seq, pgdat->memcg_lru.seq + 1); @@ -4124,11 +4124,11 @@ void lru_gen_online_memcg(struct mem_cgr gen = get_memcg_gen(pgdat->memcg_lru.seq); + lruvec->lrugen.gen = gen; + hlist_nulls_add_tail_rcu(&lruvec->lrugen.list, &pgdat->memcg_lru.fifo[gen][bin]); pgdat->memcg_lru.nr_memcgs[gen]++; - lruvec->lrugen.gen = gen; - spin_unlock_irq(&pgdat->memcg_lru.lock); } } @@ -4635,7 +4635,7 @@ static long get_nr_to_scan(struct lruvec DEFINE_MAX_SEQ(lruvec); if (mem_cgroup_below_min(sc->target_mem_cgroup, memcg)) - return 0; + return -1; if (!should_run_aging(lruvec, max_seq, sc, can_swap, &nr_to_scan)) return nr_to_scan; @@ -4710,7 +4710,7 @@ static bool try_to_shrink_lruvec(struct cond_resched(); } - /* whether try_to_inc_max_seq() was successful */ + /* whether this lruvec should be rotated */ return nr_to_scan < 0; } @@ -4764,13 +4764,13 @@ static void shrink_many(struct pglist_da struct lruvec *lruvec; struct lru_gen_folio *lrugen; struct mem_cgroup *memcg; - const struct hlist_nulls_node *pos; + struct hlist_nulls_node *pos; + gen = get_memcg_gen(READ_ONCE(pgdat->memcg_lru.seq)); bin = first_bin = get_random_u32_below(MEMCG_NR_BINS); restart: op = 0; memcg = NULL; - gen = get_memcg_gen(READ_ONCE(pgdat->memcg_lru.seq)); rcu_read_lock(); @@ -4781,6 +4781,10 @@ restart: } mem_cgroup_put(memcg); + memcg = NULL; + + if (gen != READ_ONCE(lrugen->gen)) + continue; lruvec = container_of(lrugen, struct lruvec, lrugen); memcg = lruvec_memcg(lruvec); @@ -4865,16 +4869,14 @@ static void set_initial_priority(struct if (sc->priority != DEF_PRIORITY || sc->nr_to_reclaim < MIN_LRU_BATCH) return; /* - * Determine the initial priority based on ((total / MEMCG_NR_GENS) >> - * priority) * reclaimed_to_scanned_ratio = nr_to_reclaim, where the - * estimated reclaimed_to_scanned_ratio = inactive / total. + * Determine the initial priority based on + * (total >> priority) * reclaimed_to_scanned_ratio = nr_to_reclaim, + * where reclaimed_to_scanned_ratio = inactive / total. */ reclaimable = node_page_state(pgdat, NR_INACTIVE_FILE); if (get_swappiness(lruvec, sc)) reclaimable += node_page_state(pgdat, NR_INACTIVE_ANON); - reclaimable /= MEMCG_NR_GENS; - /* round down reclaimable and round up sc->nr_to_reclaim */ priority = fls_long(reclaimable) - 1 - fls_long(sc->nr_to_reclaim - 1); _ Patches currently in -mm which might be from yuzhao(a)google.com are

10 months, 1 week

1
0
0 0

[merged mm-hotfixes-stable] mm-mglru-try-to-stop-at-high-watermarks.patch removed from -mm tree

by Andrew Morton

The quilt patch titled Subject: mm/mglru: try to stop at high watermarks has been removed from the -mm tree. Its filename was mm-mglru-try-to-stop-at-high-watermarks.patch This patch was dropped because it was merged into the mm-hotfixes-stable branch of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm ------------------------------------------------------ From: Yu Zhao <yuzhao(a)google.com> Subject: mm/mglru: try to stop at high watermarks Date: Thu, 7 Dec 2023 23:14:05 -0700 The initial MGLRU patchset didn't include the memcg LRU support, and it relied on should_abort_scan(), added by commit f76c83378851 ("mm: multi-gen LRU: optimize multiple memcgs"), to "backoff to avoid overshooting their aggregate reclaim target by too much". Later on when the memcg LRU was added, should_abort_scan() was deemed unnecessary, and the test results [1] showed no side effects after it was removed by commit a579086c99ed ("mm: multi-gen LRU: remove eviction fairness safeguard"). However, that test used memory.reclaim, which sets nr_to_reclaim to SWAP_CLUSTER_MAX. So it can overshoot only by SWAP_CLUSTER_MAX-1 pages, i.e., from nr_reclaimed=nr_to_reclaim-1 to nr_reclaimed=nr_to_reclaim+SWAP_CLUSTER_MAX-1. Compared with the batch size kswapd sets to nr_to_reclaim, SWAP_CLUSTER_MAX is tiny. Therefore that test isn't able to reproduce the worst case scenario, i.e., kswapd overshooting GBs on large systems and "consuming 100% CPU" (see the Closes tag). Bring back a simplified version of should_abort_scan() on top of the memcg LRU, so that kswapd stops when all eligible zones are above their respective high watermarks plus a small delta to lower the chance of KSWAPD_HIGH_WMARK_HIT_QUICKLY. Note that this only applies to order-0 reclaim, meaning compaction-induced reclaim can still run wild (which is a different problem). On Android, launching 55 apps sequentially: Before After Change pgpgin 838377172 802955040 -4% pgpgout 38037080 34336300 -10% [1] https://lore.kernel.org/20221222041905.2431096-1-yuzhao@google.com/ Link: https://lkml.kernel.org/r/20231208061407.2125867-2-yuzhao@google.com Fixes: a579086c99ed ("mm: multi-gen LRU: remove eviction fairness safeguard") Signed-off-by: Yu Zhao <yuzhao(a)google.com> Reported-by: Charan Teja Kalla <quic_charante(a)quicinc.com> Reported-by: Jaroslav Pulchart <jaroslav.pulchart(a)gooddata.com> Closes: https://lore.kernel.org/CAK8fFZ4DY+GtBA40Pm7Nn5xCHy+51w3sfxPqkqpqakSXYyX+Wg… Tested-by: Jaroslav Pulchart <jaroslav.pulchart(a)gooddata.com> Tested-by: Kalesh Singh <kaleshsingh(a)google.com> Cc: Hillf Danton <hdanton(a)sina.com> Cc: Kairui Song <ryncsn(a)gmail.com> Cc: T.J. Mercier <tjmercier(a)google.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- mm/vmscan.c | 36 ++++++++++++++++++++++++++++-------- 1 file changed, 28 insertions(+), 8 deletions(-) --- a/mm/vmscan.c~mm-mglru-try-to-stop-at-high-watermarks +++ a/mm/vmscan.c @@ -4648,20 +4648,41 @@ static long get_nr_to_scan(struct lruvec return try_to_inc_max_seq(lruvec, max_seq, sc, can_swap, false) ? -1 : 0; } -static unsigned long get_nr_to_reclaim(struct scan_control *sc) +static bool should_abort_scan(struct lruvec *lruvec, struct scan_control *sc) { + int i; + enum zone_watermarks mark; + /* don't abort memcg reclaim to ensure fairness */ if (!root_reclaim(sc)) - return -1; + return false; + + if (sc->nr_reclaimed >= max(sc->nr_to_reclaim, compact_gap(sc->order))) + return true; + + /* check the order to exclude compaction-induced reclaim */ + if (!current_is_kswapd() || sc->order) + return false; + + mark = sysctl_numa_balancing_mode & NUMA_BALANCING_MEMORY_TIERING ? + WMARK_PROMO : WMARK_HIGH; + + for (i = 0; i <= sc->reclaim_idx; i++) { + struct zone *zone = lruvec_pgdat(lruvec)->node_zones + i; + unsigned long size = wmark_pages(zone, mark) + MIN_LRU_BATCH; + + if (managed_zone(zone) && !zone_watermark_ok(zone, 0, size, sc->reclaim_idx, 0)) + return false; + } - return max(sc->nr_to_reclaim, compact_gap(sc->order)); + /* kswapd should abort if all eligible zones are safe */ + return true; } static bool try_to_shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc) { long nr_to_scan; unsigned long scanned = 0; - unsigned long nr_to_reclaim = get_nr_to_reclaim(sc); int swappiness = get_swappiness(lruvec, sc); /* clean file folios are more likely to exist */ @@ -4683,7 +4704,7 @@ static bool try_to_shrink_lruvec(struct if (scanned >= nr_to_scan) break; - if (sc->nr_reclaimed >= nr_to_reclaim) + if (should_abort_scan(lruvec, sc)) break; cond_resched(); @@ -4744,7 +4765,6 @@ static void shrink_many(struct pglist_da struct lru_gen_folio *lrugen; struct mem_cgroup *memcg; const struct hlist_nulls_node *pos; - unsigned long nr_to_reclaim = get_nr_to_reclaim(sc); bin = first_bin = get_random_u32_below(MEMCG_NR_BINS); restart: @@ -4777,7 +4797,7 @@ restart: rcu_read_lock(); - if (sc->nr_reclaimed >= nr_to_reclaim) + if (should_abort_scan(lruvec, sc)) break; } @@ -4788,7 +4808,7 @@ restart: mem_cgroup_put(memcg); - if (sc->nr_reclaimed >= nr_to_reclaim) + if (!is_a_nulls(pos)) return; /* restart if raced with lru_gen_rotate_memcg() */ _ Patches currently in -mm which might be from yuzhao(a)google.com are

10 months, 1 week

1
0
0 0

[merged mm-hotfixes-stable] mm-mglru-fix-underprotected-page-cache.patch removed from -mm tree

by Andrew Morton

The quilt patch titled Subject: mm/mglru: fix underprotected page cache has been removed from the -mm tree. Its filename was mm-mglru-fix-underprotected-page-cache.patch This patch was dropped because it was merged into the mm-hotfixes-stable branch of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm ------------------------------------------------------ From: Yu Zhao <yuzhao(a)google.com> Subject: mm/mglru: fix underprotected page cache Date: Thu, 7 Dec 2023 23:14:04 -0700 Unmapped folios accessed through file descriptors can be underprotected. Those folios are added to the oldest generation based on: 1. The fact that they are less costly to reclaim (no need to walk the rmap and flush the TLB) and have less impact on performance (don't cause major PFs and can be non-blocking if needed again). 2. The observation that they are likely to be single-use. E.g., for client use cases like Android, its apps parse configuration files and store the data in heap (anon); for server use cases like MySQL, it reads from InnoDB files and holds the cached data for tables in buffer pools (anon). However, the oldest generation can be very short lived, and if so, it doesn't provide the PID controller with enough time to respond to a surge of refaults. (Note that the PID controller uses weighted refaults and those from evicted generations only take a half of the whole weight.) In other words, for a short lived generation, the moving average smooths out the spike quickly. To fix the problem: 1. For folios that are already on LRU, if they can be beyond the tracking range of tiers, i.e., five accesses through file descriptors, move them to the second oldest generation to give them more time to age. (Note that tiers are used by the PID controller to statistically determine whether folios accessed multiple times through file descriptors are worth protecting.) 2. When adding unmapped folios to LRU, adjust the placement of them so that they are not too close to the tail. The effect of this is similar to the above. On Android, launching 55 apps sequentially: Before After Change workingset_refault_anon 25641024 25598972 0% workingset_refault_file 115016834 106178438 -8% Link: https://lkml.kernel.org/r/20231208061407.2125867-1-yuzhao@google.com Fixes: ac35a4902374 ("mm: multi-gen LRU: minimal implementation") Signed-off-by: Yu Zhao <yuzhao(a)google.com> Reported-by: Charan Teja Kalla <quic_charante(a)quicinc.com> Tested-by: Kalesh Singh <kaleshsingh(a)google.com> Cc: T.J. Mercier <tjmercier(a)google.com> Cc: Kairui Song <ryncsn(a)gmail.com> Cc: Hillf Danton <hdanton(a)sina.com> Cc: Jaroslav Pulchart <jaroslav.pulchart(a)gooddata.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- include/linux/mm_inline.h | 23 ++++++++++++++--------- mm/vmscan.c | 2 +- mm/workingset.c | 6 +++--- 3 files changed, 18 insertions(+), 13 deletions(-) --- a/include/linux/mm_inline.h~mm-mglru-fix-underprotected-page-cache +++ a/include/linux/mm_inline.h @@ -232,22 +232,27 @@ static inline bool lru_gen_add_folio(str if (folio_test_unevictable(folio) || !lrugen->enabled) return false; /* - * There are three common cases for this page: - * 1. If it's hot, e.g., freshly faulted in or previously hot and - * migrated, add it to the youngest generation. - * 2. If it's cold but can't be evicted immediately, i.e., an anon page - * not in swapcache or a dirty page pending writeback, add it to the - * second oldest generation. - * 3. Everything else (clean, cold) is added to the oldest generation. + * There are four common cases for this page: + * 1. If it's hot, i.e., freshly faulted in, add it to the youngest + * generation, and it's protected over the rest below. + * 2. If it can't be evicted immediately, i.e., a dirty page pending + * writeback, add it to the second youngest generation. + * 3. If it should be evicted first, e.g., cold and clean from + * folio_rotate_reclaimable(), add it to the oldest generation. + * 4. Everything else falls between 2 & 3 above and is added to the + * second oldest generation if it's considered inactive, or the + * oldest generation otherwise. See lru_gen_is_active(). */ if (folio_test_active(folio)) seq = lrugen->max_seq; else if ((type == LRU_GEN_ANON && !folio_test_swapcache(folio)) || (folio_test_reclaim(folio) && (folio_test_dirty(folio) || folio_test_writeback(folio)))) - seq = lrugen->min_seq[type] + 1; - else + seq = lrugen->max_seq - 1; + else if (reclaiming || lrugen->min_seq[type] + MIN_NR_GENS >= lrugen->max_seq) seq = lrugen->min_seq[type]; + else + seq = lrugen->min_seq[type] + 1; gen = lru_gen_from_seq(seq); flags = (gen + 1UL) << LRU_GEN_PGOFF; --- a/mm/vmscan.c~mm-mglru-fix-underprotected-page-cache +++ a/mm/vmscan.c @@ -4232,7 +4232,7 @@ static bool sort_folio(struct lruvec *lr } /* protected */ - if (tier > tier_idx) { + if (tier > tier_idx || refs == BIT(LRU_REFS_WIDTH)) { int hist = lru_hist_from_seq(lrugen->min_seq[type]); gen = folio_inc_gen(lruvec, folio, false); --- a/mm/workingset.c~mm-mglru-fix-underprotected-page-cache +++ a/mm/workingset.c @@ -313,10 +313,10 @@ static void lru_gen_refault(struct folio * 1. For pages accessed through page tables, hotter pages pushed out * hot pages which refaulted immediately. * 2. For pages accessed multiple times through file descriptors, - * numbers of accesses might have been out of the range. + * they would have been protected by sort_folio(). */ - if (lru_gen_in_fault() || refs == BIT(LRU_REFS_WIDTH)) { - folio_set_workingset(folio); + if (lru_gen_in_fault() || refs >= BIT(LRU_REFS_WIDTH) - 1) { + set_mask_bits(&folio->flags, 0, LRU_REFS_MASK | BIT(PG_workingset)); mod_lruvec_state(lruvec, WORKINGSET_RESTORE_BASE + type, delta); } unlock: _ Patches currently in -mm which might be from yuzhao(a)google.com are

10 months, 1 week

1
0
0 0

[merged mm-hotfixes-stable] mm-shmem-fix-race-in-shmem_undo_range-w-thp.patch removed from -mm tree

by Andrew Morton

The quilt patch titled Subject: mm/shmem: fix race in shmem_undo_range w/THP has been removed from the -mm tree. Its filename was mm-shmem-fix-race-in-shmem_undo_range-w-thp.patch This patch was dropped because it was merged into the mm-hotfixes-stable branch of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm ------------------------------------------------------ From: David Stevens <stevensd(a)chromium.org> Subject: mm/shmem: fix race in shmem_undo_range w/THP Date: Tue, 18 Apr 2023 17:40:31 +0900 Split folios during the second loop of shmem_undo_range. It's not sufficient to only split folios when dealing with partial pages, since it's possible for a THP to be faulted in after that point. Calling truncate_inode_folio in that situation can result in throwing away data outside of the range being targeted. [akpm(a)linux-foundation.org: tidy up comment layout] Link: https://lkml.kernel.org/r/20230418084031.3439795-1-stevensd@google.com Fixes: b9a8a4195c7d ("truncate,shmem: Handle truncates that split large folios") Signed-off-by: David Stevens <stevensd(a)chromium.org> Cc: Matthew Wilcox (Oracle) <willy(a)infradead.org> Cc: Suleiman Souhlal <suleiman(a)google.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- mm/shmem.c | 19 ++++++++++++++++++- 1 file changed, 18 insertions(+), 1 deletion(-) --- a/mm/shmem.c~mm-shmem-fix-race-in-shmem_undo_range-w-thp +++ a/mm/shmem.c @@ -1080,7 +1080,24 @@ whole_folios: } VM_BUG_ON_FOLIO(folio_test_writeback(folio), folio); - truncate_inode_folio(mapping, folio); + + if (!folio_test_large(folio)) { + truncate_inode_folio(mapping, folio); + } else if (truncate_inode_partial_folio(folio, lstart, lend)) { + /* + * If we split a page, reset the loop so + * that we pick up the new sub pages. + * Otherwise the THP was entirely + * dropped or the target range was + * zeroed, so just continue the loop as + * is. + */ + if (!folio_test_large(folio)) { + folio_unlock(folio); + index = start; + break; + } + } } folio_unlock(folio); } _ Patches currently in -mm which might be from stevensd(a)chromium.org are

10 months, 1 week

1
0
0 0

[merged mm-hotfixes-stable] revert-selftests-error-out-if-kernel-header-files-are-not-yet-built.patch removed from -mm tree

by Andrew Morton

The quilt patch titled Subject: Revert "selftests: error out if kernel header files are not yet built" has been removed from the -mm tree. Its filename was revert-selftests-error-out-if-kernel-header-files-are-not-yet-built.patch This patch was dropped because it was merged into the mm-hotfixes-stable branch of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm ------------------------------------------------------ From: John Hubbard <jhubbard(a)nvidia.com> Subject: Revert "selftests: error out if kernel header files are not yet built" Date: Fri, 8 Dec 2023 18:01:44 -0800 This reverts commit 9fc96c7c19df ("selftests: error out if kernel header files are not yet built"). It turns out that requiring the kernel headers to be built as a prerequisite to building selftests, does not work in many cases. For example, Peter Zijlstra writes: "My biggest beef with the whole thing is that I simply do not want to use 'make headers', it doesn't work for me. I have a ton of output directories and I don't care to build tools into the output dirs, in fact some of them flat out refuse to work that way (bpf comes to mind)." [1] Therefore, stop erroring out on the selftests build. Additional patches will be required in order to change over to not requiring the kernel headers. [1] https://lore.kernel.org/20231208221007.GO28727@noisy.programming.kicks-ass.… Link: https://lkml.kernel.org/r/20231209020144.244759-1-jhubbard@nvidia.com Fixes: 9fc96c7c19df ("selftests: error out if kernel header files are not yet built") Signed-off-by: John Hubbard <jhubbard(a)nvidia.com> Cc: Anders Roxell <anders.roxell(a)linaro.org> Cc: Muhammad Usama Anjum <usama.anjum(a)collabora.com> Cc: David Hildenbrand <david(a)redhat.com> Cc: Peter Xu <peterx(a)redhat.com> Cc: Jonathan Corbet <corbet(a)lwn.net> Cc: Nathan Chancellor <nathan(a)kernel.org> Cc: Shuah Khan <shuah(a)kernel.org> Cc: Peter Zijlstra <peterz(a)infradead.org> Cc: Marcos Paulo de Souza <mpdesouza(a)suse.com> Cc: <stable(a)vger.kernel.org> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- tools/testing/selftests/Makefile | 21 --------------- tools/testing/selftests/lib.mk | 40 ++--------------------------- 2 files changed, 4 insertions(+), 57 deletions(-) --- a/tools/testing/selftests/lib.mk~revert-selftests-error-out-if-kernel-header-files-are-not-yet-built +++ a/tools/testing/selftests/lib.mk @@ -44,26 +44,10 @@ endif selfdir = $(realpath $(dir $(filter %/lib.mk,$(MAKEFILE_LIST)))) top_srcdir = $(selfdir)/../../.. -ifeq ("$(origin O)", "command line") - KBUILD_OUTPUT := $(O) +ifeq ($(KHDR_INCLUDES),) +KHDR_INCLUDES := -isystem $(top_srcdir)/usr/include endif -ifneq ($(KBUILD_OUTPUT),) - # Make's built-in functions such as $(abspath ...), $(realpath ...) cannot - # expand a shell special character '~'. We use a somewhat tedious way here. - abs_objtree := $(shell cd $(top_srcdir) && mkdir -p $(KBUILD_OUTPUT) && cd $(KBUILD_OUTPUT) && pwd) - $(if $(abs_objtree),, \ - $(error failed to create output directory "$(KBUILD_OUTPUT)")) - # $(realpath ...) resolves symlinks - abs_objtree := $(realpath $(abs_objtree)) - KHDR_DIR := ${abs_objtree}/usr/include -else - abs_srctree := $(shell cd $(top_srcdir) && pwd) - KHDR_DIR := ${abs_srctree}/usr/include -endif - -KHDR_INCLUDES := -isystem $(KHDR_DIR) - # The following are built by lib.mk common compile rules. # TEST_CUSTOM_PROGS should be used by tests that require # custom build rule and prevent common build rule use. @@ -74,25 +58,7 @@ TEST_GEN_PROGS := $(patsubst %,$(OUTPUT) TEST_GEN_PROGS_EXTENDED := $(patsubst %,$(OUTPUT)/%,$(TEST_GEN_PROGS_EXTENDED)) TEST_GEN_FILES := $(patsubst %,$(OUTPUT)/%,$(TEST_GEN_FILES)) -all: kernel_header_files $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED) \ - $(TEST_GEN_FILES) - -kernel_header_files: - @ls $(KHDR_DIR)/linux/*.h >/dev/null 2>/dev/null; \ - if [ $$? -ne 0 ]; then \ - RED='\033[1;31m'; \ - NOCOLOR='\033[0m'; \ - echo; \ - echo -e "$${RED}error$${NOCOLOR}: missing kernel header files."; \ - echo "Please run this and try again:"; \ - echo; \ - echo " cd $(top_srcdir)"; \ - echo " make headers"; \ - echo; \ - exit 1; \ - fi - -.PHONY: kernel_header_files +all: $(TEST_GEN_PROGS) $(TEST_GEN_PROGS_EXTENDED) $(TEST_GEN_FILES) define RUN_TESTS BASE_DIR="$(selfdir)"; \ --- a/tools/testing/selftests/Makefile~revert-selftests-error-out-if-kernel-header-files-are-not-yet-built +++ a/tools/testing/selftests/Makefile @@ -155,12 +155,10 @@ ifneq ($(KBUILD_OUTPUT),) abs_objtree := $(realpath $(abs_objtree)) BUILD := $(abs_objtree)/kselftest KHDR_INCLUDES := -isystem ${abs_objtree}/usr/include - KHDR_DIR := ${abs_objtree}/usr/include else BUILD := $(CURDIR) abs_srctree := $(shell cd $(top_srcdir) && pwd) KHDR_INCLUDES := -isystem ${abs_srctree}/usr/include - KHDR_DIR := ${abs_srctree}/usr/include DEFAULT_INSTALL_HDR_PATH := 1 endif @@ -174,7 +172,7 @@ export KHDR_INCLUDES # all isn't the first target in the file. .DEFAULT_GOAL := all -all: kernel_header_files +all: @ret=1; \ for TARGET in $(TARGETS); do \ BUILD_TARGET=$$BUILD/$$TARGET; \ @@ -185,23 +183,6 @@ all: kernel_header_files ret=$$((ret * $$?)); \ done; exit $$ret; -kernel_header_files: - @ls $(KHDR_DIR)/linux/*.h >/dev/null 2>/dev/null; \ - if [ $$? -ne 0 ]; then \ - RED='\033[1;31m'; \ - NOCOLOR='\033[0m'; \ - echo; \ - echo -e "$${RED}error$${NOCOLOR}: missing kernel header files."; \ - echo "Please run this and try again:"; \ - echo; \ - echo " cd $(top_srcdir)"; \ - echo " make headers"; \ - echo; \ - exit 1; \ - fi - -.PHONY: kernel_header_files - run_tests: all @for TARGET in $(TARGETS); do \ BUILD_TARGET=$$BUILD/$$TARGET; \ _ Patches currently in -mm which might be from jhubbard(a)nvidia.com are

10 months, 1 week

1
0
0 0

[merged mm-hotfixes-stable] mm-damon-core-make-damon_start-waits-until-kdamond_fn-starts.patch removed from -mm tree

by Andrew Morton

The quilt patch titled Subject: mm/damon/core: make damon_start() waits until kdamond_fn() starts has been removed from the -mm tree. Its filename was mm-damon-core-make-damon_start-waits-until-kdamond_fn-starts.patch This patch was dropped because it was merged into the mm-hotfixes-stable branch of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm ------------------------------------------------------ From: SeongJae Park <sj(a)kernel.org> Subject: mm/damon/core: make damon_start() waits until kdamond_fn() starts Date: Fri, 8 Dec 2023 17:50:18 +0000 The cleanup tasks of kdamond threads including reset of corresponding DAMON context's ->kdamond field and decrease of global nr_running_ctxs counter is supposed to be executed by kdamond_fn(). However, commit 0f91d13366a4 ("mm/damon: simplify stop mechanism") made neither damon_start() nor damon_stop() ensure the corresponding kdamond has started the execution of kdamond_fn(). As a result, the cleanup can be skipped if damon_stop() is called fast enough after the previous damon_start(). Especially the skipped reset of ->kdamond could cause a use-after-free. Fix it by waiting for start of kdamond_fn() execution from damon_start(). Link: https://lkml.kernel.org/r/20231208175018.63880-1-sj@kernel.org Fixes: 0f91d13366a4 ("mm/damon: simplify stop mechanism") Signed-off-by: SeongJae Park <sj(a)kernel.org> Reported-by: Jakub Acs <acsjakub(a)amazon.de> Cc: Changbin Du <changbin.du(a)intel.com> Cc: Jakub Acs <acsjakub(a)amazon.de> Cc: <stable(a)vger.kernel.org> # 5.15.x Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> --- include/linux/damon.h | 2 ++ mm/damon/core.c | 6 ++++++ 2 files changed, 8 insertions(+) --- a/include/linux/damon.h~mm-damon-core-make-damon_start-waits-until-kdamond_fn-starts +++ a/include/linux/damon.h @@ -559,6 +559,8 @@ struct damon_ctx { * update */ unsigned long next_ops_update_sis; + /* for waiting until the execution of the kdamond_fn is started */ + struct completion kdamond_started; /* public: */ struct task_struct *kdamond; --- a/mm/damon/core.c~mm-damon-core-make-damon_start-waits-until-kdamond_fn-starts +++ a/mm/damon/core.c @@ -445,6 +445,8 @@ struct damon_ctx *damon_new_ctx(void) if (!ctx) return NULL; + init_completion(&ctx->kdamond_started); + ctx->attrs.sample_interval = 5 * 1000; ctx->attrs.aggr_interval = 100 * 1000; ctx->attrs.ops_update_interval = 60 * 1000 * 1000; @@ -668,11 +670,14 @@ static int __damon_start(struct damon_ct mutex_lock(&ctx->kdamond_lock); if (!ctx->kdamond) { err = 0; + reinit_completion(&ctx->kdamond_started); ctx->kdamond = kthread_run(kdamond_fn, ctx, "kdamond.%d", nr_running_ctxs); if (IS_ERR(ctx->kdamond)) { err = PTR_ERR(ctx->kdamond); ctx->kdamond = NULL; + } else { + wait_for_completion(&ctx->kdamond_started); } } mutex_unlock(&ctx->kdamond_lock); @@ -1433,6 +1438,7 @@ static int kdamond_fn(void *data) pr_debug("kdamond (%d) starts\n", current->pid); + complete(&ctx->kdamond_started); kdamond_init_intervals_sis(ctx); if (ctx->ops.init) _ Patches currently in -mm which might be from sj(a)kernel.org are selftests-damon-implement-a-python-module-for-test-purpose-damon-sysfs-controls.patch selftests-damon-_damon_sysfs-implement-kdamonds-start-function.patch selftests-damon-_damon_sysfs-implement-updat_schemes_tried_bytes-command.patch selftests-damon-add-a-test-for-update_schemes_tried_regions-sysfs-command.patch selftests-damon-add-a-test-for-update_schemes_tried_regions-hang-bug.patch

10 months, 1 week

1
0
0 0

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror December 2023