March 2024 - Linux-stable-mirror

FAILED: Patch "drm/amdgpu/gfx11: set UNORD_DISPATCH in compute MQDs" failed to apply to 6.1-stable tree

by Sasha Levin

The patch below does not apply to the 6.1-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. Thanks, Sasha ------------------ original commit in Linus's tree ------------------ From fc8f5a29d4cf0979ac4019282c3ca5cb246969f9 Mon Sep 17 00:00:00 2001 From: Alex Deucher <alexander.deucher(a)amd.com> Date: Fri, 19 Jan 2024 12:32:59 -0500 Subject: [PATCH] drm/amdgpu/gfx11: set UNORD_DISPATCH in compute MQDs This needs to be set to 1 to avoid a potential deadlock in the GC 10.x and newer. On GC 9.x and older, this needs to be set to 0. This can lead to hangs in some mixed graphics and compute workloads. Updated firmware is also required for AQL. Reviewed-by: Feifei Xu <Feifei.Xu(a)amd.com> Signed-off-by: Alex Deucher <alexander.deucher(a)amd.com> Cc: stable(a)vger.kernel.org --- drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c | 2 +- drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v11.c | 1 + 2 files changed, 2 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c index 043eff309100f..c1e0000107608 100644 --- a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c +++ b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c @@ -3846,7 +3846,7 @@ static int gfx_v11_0_compute_mqd_init(struct amdgpu_device *adev, void *m, (order_base_2(prop->queue_size / 4) - 1)); tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, RPTR_BLOCK_SIZE, (order_base_2(AMDGPU_GPU_PAGE_SIZE / 4) - 1)); - tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, UNORD_DISPATCH, 0); + tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, UNORD_DISPATCH, 1); tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, TUNNEL_DISPATCH, prop->allow_tunneling); tmp = REG_SET_FIELD(tmp, CP_HQD_PQ_CONTROL, PRIV_STATE, 1); diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v11.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v11.c index 15277f1d5cf0a..d722cbd317834 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v11.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v11.c @@ -224,6 +224,7 @@ static void update_mqd(struct mqd_manager *mm, void *mqd, m->cp_hqd_pq_control = 5 << CP_HQD_PQ_CONTROL__RPTR_BLOCK_SIZE__SHIFT; m->cp_hqd_pq_control |= ffs(q->queue_size / sizeof(unsigned int)) - 1 - 1; + m->cp_hqd_pq_control |= CP_HQD_PQ_CONTROL__UNORD_DISPATCH_MASK; pr_debug("cp_hqd_pq_control 0x%x\n", m->cp_hqd_pq_control); m->cp_hqd_pq_base_lo = lower_32_bits((uint64_t)q->queue_address >> 8); -- 2.43.0

1 year, 3 months

1
0
0 0

FAILED: Patch "drm/amdgpu: make damage clips support configurable" failed to apply to 6.1-stable tree

by Sasha Levin

The patch below does not apply to the 6.1-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. Thanks, Sasha ------------------ original commit in Linus's tree ------------------ From fc184dbe9fd99ad2dfb197b6fe18768bae1774b1 Mon Sep 17 00:00:00 2001 From: Hamza Mahfooz <hamza.mahfooz(a)amd.com> Date: Thu, 8 Feb 2024 16:23:29 -0500 Subject: [PATCH] drm/amdgpu: make damage clips support configurable We have observed that there are quite a number of PSR-SU panels on the market that are unable to keep up with what user space throws at them, resulting in hangs and random black screens. So, make damage clips support configurable and disable it by default for PSR-SU displays. Cc: stable(a)vger.kernel.org Reviewed-by: Mario Limonciello <mario.limonciello(a)amd.com> Signed-off-by: Hamza Mahfooz <hamza.mahfooz(a)amd.com> Signed-off-by: Alex Deucher <alexander.deucher(a)amd.com> --- drivers/gpu/drm/amd/amdgpu/amdgpu.h | 1 + drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c | 13 +++++++++++++ drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c | 7 +++++++ 3 files changed, 21 insertions(+) diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu.h b/drivers/gpu/drm/amd/amdgpu/amdgpu.h index 312dfaec7b4a7..1291b8eb9dffa 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu.h +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu.h @@ -198,6 +198,7 @@ extern uint amdgpu_dc_debug_mask; extern uint amdgpu_dc_visual_confirm; extern uint amdgpu_dm_abm_level; extern int amdgpu_backlight; +extern int amdgpu_damage_clips; extern struct amdgpu_mgpu_info mgpu_info; extern int amdgpu_ras_enable; extern uint amdgpu_ras_mask; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index 161ecf9b41747..6ef7f22c1152c 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -211,6 +211,7 @@ int amdgpu_seamless = -1; /* auto */ uint amdgpu_debug_mask; int amdgpu_agp = -1; /* auto */ int amdgpu_wbrf = -1; +int amdgpu_damage_clips = -1; /* auto */ static void amdgpu_drv_delayed_reset_work_handler(struct work_struct *work); @@ -859,6 +860,18 @@ int amdgpu_backlight = -1; MODULE_PARM_DESC(backlight, "Backlight control (0 = pwm, 1 = aux, -1 auto (default))"); module_param_named(backlight, amdgpu_backlight, bint, 0444); +/** + * DOC: damageclips (int) + * Enable or disable damage clips support. If damage clips support is disabled, + * we will force full frame updates, irrespective of what user space sends to + * us. + * + * Defaults to -1 (where it is enabled unless a PSR-SU display is detected). + */ +MODULE_PARM_DESC(damageclips, + "Damage clips support (0 = disable, 1 = enable, -1 auto (default))"); +module_param_named(damageclips, amdgpu_damage_clips, int, 0444); + /** * DOC: tmz (int) * Trusted Memory Zone (TMZ) is a method to protect data being written 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 b7a717c3682f9..f9a7a16f1ec21 100644 --- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c +++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c @@ -5254,6 +5254,7 @@ static void fill_dc_dirty_rects(struct drm_plane *plane, struct drm_plane_state *new_plane_state, struct drm_crtc_state *crtc_state, struct dc_flip_addrs *flip_addrs, + bool is_psr_su, bool *dirty_regions_changed) { struct dm_crtc_state *dm_crtc_state = to_dm_crtc_state(crtc_state); @@ -5278,6 +5279,10 @@ static void fill_dc_dirty_rects(struct drm_plane *plane, num_clips = drm_plane_get_damage_clips_count(new_plane_state); clips = drm_plane_get_damage_clips(new_plane_state); + if (num_clips && (!amdgpu_damage_clips || (amdgpu_damage_clips < 0 && + is_psr_su))) + goto ffu; + if (!dm_crtc_state->mpo_requested) { if (!num_clips || num_clips > DC_MAX_DIRTY_RECTS) goto ffu; @@ -8412,6 +8417,8 @@ static void amdgpu_dm_commit_planes(struct drm_atomic_state *state, fill_dc_dirty_rects(plane, old_plane_state, new_plane_state, new_crtc_state, &bundle->flip_addrs[planes_count], + acrtc_state->stream->link->psr_settings.psr_version == + DC_PSR_VERSION_SU_1, &dirty_rects_changed); /* -- 2.43.0

1 year, 3 months

1
0
0 0

FAILED: Patch "LoongArch/crypto: Clean up useless assignment operations" failed to apply to 6.1-stable tree

by Sasha Levin

The patch below does not apply to the 6.1-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. Thanks, Sasha ------------------ original commit in Linus's tree ------------------ From fea1c949f6ca5059e12de00d0483645debc5b206 Mon Sep 17 00:00:00 2001 From: Yuli Wang <wangyuli(a)uniontech.com> Date: Tue, 19 Mar 2024 15:50:34 +0800 Subject: [PATCH] LoongArch/crypto: Clean up useless assignment operations The LoongArch CRC32 hw acceleration is based on arch/mips/crypto/ crc32-mips.c. While the MIPS code supports both MIPS32 and MIPS64, but LoongArch32 lacks the CRC instruction. As a result, the line "len -= sizeof(u32)" is unnecessary. Removing it can make context code style more unified and improve code readability. Cc: stable(a)vger.kernel.org Reviewed-by: WANG Xuerui <git(a)xen0n.name> Suggested-by: Wentao Guan <guanwentao(a)uniontech.com> Signed-off-by: Yuli Wang <wangyuli(a)uniontech.com> Signed-off-by: Huacai Chen <chenhuacai(a)loongson.cn> --- arch/loongarch/crypto/crc32-loongarch.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/arch/loongarch/crypto/crc32-loongarch.c b/arch/loongarch/crypto/crc32-loongarch.c index a49e507af38c0..3eebea3a7b478 100644 --- a/arch/loongarch/crypto/crc32-loongarch.c +++ b/arch/loongarch/crypto/crc32-loongarch.c @@ -44,7 +44,6 @@ static u32 crc32_loongarch_hw(u32 crc_, const u8 *p, unsigned int len) CRC32(crc, value, w); p += sizeof(u32); - len -= sizeof(u32); } if (len & sizeof(u16)) { @@ -80,7 +79,6 @@ static u32 crc32c_loongarch_hw(u32 crc_, const u8 *p, unsigned int len) CRC32C(crc, value, w); p += sizeof(u32); - len -= sizeof(u32); } if (len & sizeof(u16)) { -- 2.43.0

1 year, 3 months

1
0
0 0

FAILED: Patch "drm/amd/display: set odm_combine_policy based on context in dcn32 resource" failed to apply to 6.6-stable tree

by Sasha Levin

The patch below does not apply to the 6.6-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. Thanks, Sasha ------------------ original commit in Linus's tree ------------------ From 0a5fd7811a17af708cefdaab93af86838353002d Mon Sep 17 00:00:00 2001 From: Wenjing Liu <wenjing.liu(a)amd.com> Date: Thu, 18 Jan 2024 18:12:15 -0500 Subject: [PATCH] drm/amd/display: set odm_combine_policy based on context in dcn32 resource [why] When populating dml pipes, odm combine policy should be assigned based on the pipe topology of the context passed in. DML pipes could be repopulated multiple times during single validate bandwidth attempt. We need to make sure that whenever we repopulate the dml pipes it is always aligned with the updated context. There is a case where DML pipes get repopulated during FPO optimization after ODM combine policy is changed. Since in the current code we reinitlaize ODM combine policy, even though the current context has ODM combine enabled, we overwrite it despite the pipes are already split. This causes DML to think that MPC combine is used so we mistakenly enable MPC combine because we apply pipe split with ODM combine policy reset. This issue doesn't impact non windowed MPO with ODM case because the legacy policy has restricted use cases. We don't encounter the case where both ODM and FPO optimizations are enabled together. So we decide to leave it as is because it is about to be replaced anyway. Cc: stable(a)vger.kernel.org # 6.6+ Reviewed-by: Chaitanya Dhere <chaitanya.dhere(a)amd.com> Reviewed-by: Alvin Lee <alvin.lee2(a)amd.com> Acked-by: Hamza Mahfooz <hamza.mahfooz(a)amd.com> Signed-off-by: Wenjing Liu <wenjing.liu(a)amd.com> Signed-off-by: Alex Deucher <alexander.deucher(a)amd.com> --- .../drm/amd/display/dc/dml/dcn32/dcn32_fpu.c | 15 ++++++++++---- drivers/gpu/drm/amd/display/dc/inc/resource.h | 20 ++++++++----------- .../dc/resource/dcn32/dcn32_resource.c | 16 ++++++++++++++- 3 files changed, 34 insertions(+), 17 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c index a7981a0c4158f..4edf7df4c6aad 100644 --- a/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c +++ b/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c @@ -1289,7 +1289,7 @@ static bool update_pipes_with_split_flags(struct dc *dc, struct dc_state *contex return updated; } -static bool should_allow_odm_power_optimization(struct dc *dc, +static bool should_apply_odm_power_optimization(struct dc *dc, struct dc_state *context, struct vba_vars_st *v, int *split, bool *merge) { @@ -1393,9 +1393,12 @@ static void try_odm_power_optimization_and_revalidate( { int i; unsigned int new_vlevel; + unsigned int cur_policy[MAX_PIPES]; - for (i = 0; i < pipe_cnt; i++) + for (i = 0; i < pipe_cnt; i++) { + cur_policy[i] = pipes[i].pipe.dest.odm_combine_policy; pipes[i].pipe.dest.odm_combine_policy = dm_odm_combine_policy_2to1; + } new_vlevel = dml_get_voltage_level(&context->bw_ctx.dml, pipes, pipe_cnt); @@ -1404,6 +1407,9 @@ static void try_odm_power_optimization_and_revalidate( memset(merge, 0, MAX_PIPES * sizeof(bool)); *vlevel = dcn20_validate_apply_pipe_split_flags(dc, context, new_vlevel, split, merge); context->bw_ctx.dml.vba.VoltageLevel = *vlevel; + } else { + for (i = 0; i < pipe_cnt; i++) + pipes[i].pipe.dest.odm_combine_policy = cur_policy[i]; } } @@ -1581,7 +1587,7 @@ static void dcn32_full_validate_bw_helper(struct dc *dc, } } - if (should_allow_odm_power_optimization(dc, context, vba, split, merge)) + if (should_apply_odm_power_optimization(dc, context, vba, split, merge)) try_odm_power_optimization_and_revalidate( dc, context, pipes, split, merge, vlevel, *pipe_cnt); @@ -2210,7 +2216,8 @@ bool dcn32_internal_validate_bw(struct dc *dc, int i; pipe_cnt = dc->res_pool->funcs->populate_dml_pipes(dc, context, pipes, fast_validate); - dcn32_update_dml_pipes_odm_policy_based_on_context(dc, context, pipes); + if (!dc->config.enable_windowed_mpo_odm) + dcn32_update_dml_pipes_odm_policy_based_on_context(dc, context, pipes); /* repopulate_pipes = 1 means the pipes were either split or merged. In this case * we have to re-calculate the DET allocation and run through DML once more to diff --git a/drivers/gpu/drm/amd/display/dc/inc/resource.h b/drivers/gpu/drm/amd/display/dc/inc/resource.h index 1d51fed12e200..2eae2f3e846d8 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/resource.h +++ b/drivers/gpu/drm/amd/display/dc/inc/resource.h @@ -427,22 +427,18 @@ struct pipe_ctx *resource_get_primary_dpp_pipe(const struct pipe_ctx *dpp_pipe); int resource_get_mpc_slice_index(const struct pipe_ctx *dpp_pipe); /* - * Get number of MPC "cuts" of the plane associated with the pipe. MPC slice - * count is equal to MPC splits + 1. For example if a plane is cut 3 times, it - * will have 4 pieces of slice. - * return - 0 if pipe is not used for a plane with MPCC combine. otherwise - * the number of MPC "cuts" for the plane. + * Get the number of MPC slices associated with the pipe. + * The function returns 0 if the pipe is not associated with an MPC combine + * pipe topology. */ -int resource_get_mpc_slice_count(const struct pipe_ctx *opp_head); +int resource_get_mpc_slice_count(const struct pipe_ctx *pipe); /* - * Get number of ODM "cuts" of the timing associated with the pipe. ODM slice - * count is equal to ODM splits + 1. For example if a timing is cut 3 times, it - * will have 4 pieces of slice. - * return - 0 if pipe is not used for ODM combine. otherwise - * the number of ODM "cuts" for the timing. + * Get the number of ODM slices associated with the pipe. + * The function returns 0 if the pipe is not associated with an ODM combine + * pipe topology. */ -int resource_get_odm_slice_count(const struct pipe_ctx *otg_master); +int resource_get_odm_slice_count(const struct pipe_ctx *pipe); /* Get the ODM slice index counting from 0 from left most slice */ int resource_get_odm_slice_index(const struct pipe_ctx *opp_head); diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.c index ac04a9c9a3d86..71cd20618bfe0 100644 --- a/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.c +++ b/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.c @@ -1829,7 +1829,21 @@ int dcn32_populate_dml_pipes_from_context( dcn32_zero_pipe_dcc_fraction(pipes, pipe_cnt); DC_FP_END(); pipes[pipe_cnt].pipe.dest.vfront_porch = timing->v_front_porch; - pipes[pipe_cnt].pipe.dest.odm_combine_policy = dm_odm_combine_policy_dal; + if (dc->config.enable_windowed_mpo_odm && + dc->debug.enable_single_display_2to1_odm_policy) { + switch (resource_get_odm_slice_count(pipe)) { + case 2: + pipes[pipe_cnt].pipe.dest.odm_combine_policy = dm_odm_combine_policy_2to1; + break; + case 4: + pipes[pipe_cnt].pipe.dest.odm_combine_policy = dm_odm_combine_policy_4to1; + break; + default: + pipes[pipe_cnt].pipe.dest.odm_combine_policy = dm_odm_combine_policy_dal; + } + } else { + pipes[pipe_cnt].pipe.dest.odm_combine_policy = dm_odm_combine_policy_dal; + } pipes[pipe_cnt].pipe.src.gpuvm_min_page_size_kbytes = 256; // according to spreadsheet pipes[pipe_cnt].pipe.src.unbounded_req_mode = false; pipes[pipe_cnt].pipe.scale_ratio_depth.lb_depth = dm_lb_19; -- 2.43.0

1 year, 3 months

1
0
0 0

FAILED: Patch "x86/sev: Fix position dependent variable references in startup code" failed to apply to 6.6-stable tree

by Sasha Levin

The patch below does not apply to the 6.6-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. Thanks, Sasha ------------------ original commit in Linus's tree ------------------ From 1c811d403afd73f04bde82b83b24c754011bd0e8 Mon Sep 17 00:00:00 2001 From: Ard Biesheuvel <ardb(a)kernel.org> Date: Sat, 3 Feb 2024 13:53:06 +0100 Subject: [PATCH] x86/sev: Fix position dependent variable references in startup code The early startup code executes from a 1:1 mapping of memory, which differs from the mapping that the code was linked and/or relocated to run at. The latter mapping is not active yet at this point, and so symbol references that rely on it will fault. Given that the core kernel is built without -fPIC, symbol references are typically emitted as absolute, and so any such references occuring in the early startup code will therefore crash the kernel. While an attempt was made to work around this for the early SEV/SME startup code, by forcing RIP-relative addressing for certain global SEV/SME variables via inline assembly (see snp_cpuid_get_table() for example), RIP-relative addressing must be pervasively enforced for SEV/SME global variables when accessed prior to page table fixups. __startup_64() already handles this issue for select non-SEV/SME global variables using fixup_pointer(), which adjusts the pointer relative to a `physaddr` argument. To avoid having to pass around this `physaddr` argument across all functions needing to apply pointer fixups, introduce a macro RIP_RELATIVE_REF() which generates a RIP-relative reference to a given global variable. It is used where necessary to force RIP-relative accesses to global variables. For backporting purposes, this patch makes no attempt at cleaning up other occurrences of this pattern, involving either inline asm or fixup_pointer(). Those will be addressed later. [ bp: Call it "rip_rel_ref" everywhere like other code shortens "rIP-relative reference" and make the asm wrapper __always_inline. ] Co-developed-by: Kevin Loughlin <kevinloughlin(a)google.com> Signed-off-by: Kevin Loughlin <kevinloughlin(a)google.com> Signed-off-by: Ard Biesheuvel <ardb(a)kernel.org> Signed-off-by: Borislav Petkov (AMD) <bp(a)alien8.de> Cc: <stable(a)kernel.org> Link: https://lore.kernel.org/all/20240130220845.1978329-1-kevinloughlin@google.c… --- arch/x86/coco/core.c | 7 +------ arch/x86/include/asm/asm.h | 14 ++++++++++++++ arch/x86/include/asm/coco.h | 8 +++++++- arch/x86/include/asm/mem_encrypt.h | 15 +++++++++------ arch/x86/kernel/sev-shared.c | 12 ++++++------ arch/x86/kernel/sev.c | 4 ++-- arch/x86/mm/mem_encrypt_identity.c | 27 ++++++++++++--------------- 7 files changed, 51 insertions(+), 36 deletions(-) diff --git a/arch/x86/coco/core.c b/arch/x86/coco/core.c index eeec9986570ed..d07be9d05cd03 100644 --- a/arch/x86/coco/core.c +++ b/arch/x86/coco/core.c @@ -14,7 +14,7 @@ #include <asm/processor.h> enum cc_vendor cc_vendor __ro_after_init = CC_VENDOR_NONE; -static u64 cc_mask __ro_after_init; +u64 cc_mask __ro_after_init; static bool noinstr intel_cc_platform_has(enum cc_attr attr) { @@ -148,8 +148,3 @@ u64 cc_mkdec(u64 val) } } EXPORT_SYMBOL_GPL(cc_mkdec); - -__init void cc_set_mask(u64 mask) -{ - cc_mask = mask; -} diff --git a/arch/x86/include/asm/asm.h b/arch/x86/include/asm/asm.h index fbcfec4dc4ccd..ca8eed1d496ab 100644 --- a/arch/x86/include/asm/asm.h +++ b/arch/x86/include/asm/asm.h @@ -113,6 +113,20 @@ #endif +#ifndef __ASSEMBLY__ +#ifndef __pic__ +static __always_inline __pure void *rip_rel_ptr(void *p) +{ + asm("leaq %c1(%%rip), %0" : "=r"(p) : "i"(p)); + + return p; +} +#define RIP_REL_REF(var) (*(typeof(&(var)))rip_rel_ptr(&(var))) +#else +#define RIP_REL_REF(var) (var) +#endif +#endif + /* * Macros to generate condition code outputs from inline assembly, * The output operand must be type "bool". diff --git a/arch/x86/include/asm/coco.h b/arch/x86/include/asm/coco.h index 6ae2d16a7613b..21940ef8d2904 100644 --- a/arch/x86/include/asm/coco.h +++ b/arch/x86/include/asm/coco.h @@ -2,6 +2,7 @@ #ifndef _ASM_X86_COCO_H #define _ASM_X86_COCO_H +#include <asm/asm.h> #include <asm/types.h> enum cc_vendor { @@ -11,9 +12,14 @@ enum cc_vendor { }; extern enum cc_vendor cc_vendor; +extern u64 cc_mask; #ifdef CONFIG_ARCH_HAS_CC_PLATFORM -void cc_set_mask(u64 mask); +static inline void cc_set_mask(u64 mask) +{ + RIP_REL_REF(cc_mask) = mask; +} + u64 cc_mkenc(u64 val); u64 cc_mkdec(u64 val); #else diff --git a/arch/x86/include/asm/mem_encrypt.h b/arch/x86/include/asm/mem_encrypt.h index 359ada486fa92..b31eb9fd59544 100644 --- a/arch/x86/include/asm/mem_encrypt.h +++ b/arch/x86/include/asm/mem_encrypt.h @@ -15,7 +15,8 @@ #include <linux/init.h> #include <linux/cc_platform.h> -#include <asm/bootparam.h> +#include <asm/asm.h> +struct boot_params; #ifdef CONFIG_X86_MEM_ENCRYPT void __init mem_encrypt_init(void); @@ -58,6 +59,11 @@ void __init mem_encrypt_free_decrypted_mem(void); void __init sev_es_init_vc_handling(void); +static inline u64 sme_get_me_mask(void) +{ + return RIP_REL_REF(sme_me_mask); +} + #define __bss_decrypted __section(".bss..decrypted") #else /* !CONFIG_AMD_MEM_ENCRYPT */ @@ -89,6 +95,8 @@ early_set_mem_enc_dec_hypercall(unsigned long vaddr, unsigned long size, bool en static inline void mem_encrypt_free_decrypted_mem(void) { } +static inline u64 sme_get_me_mask(void) { return 0; } + #define __bss_decrypted #endif /* CONFIG_AMD_MEM_ENCRYPT */ @@ -106,11 +114,6 @@ void add_encrypt_protection_map(void); extern char __start_bss_decrypted[], __end_bss_decrypted[], __start_bss_decrypted_unused[]; -static inline u64 sme_get_me_mask(void) -{ - return sme_me_mask; -} - #endif /* __ASSEMBLY__ */ #endif /* __X86_MEM_ENCRYPT_H__ */ diff --git a/arch/x86/kernel/sev-shared.c b/arch/x86/kernel/sev-shared.c index 5db24d0fc557c..ae79f9505298d 100644 --- a/arch/x86/kernel/sev-shared.c +++ b/arch/x86/kernel/sev-shared.c @@ -560,9 +560,9 @@ static int snp_cpuid(struct ghcb *ghcb, struct es_em_ctxt *ctxt, struct cpuid_le leaf->eax = leaf->ebx = leaf->ecx = leaf->edx = 0; /* Skip post-processing for out-of-range zero leafs. */ - if (!(leaf->fn <= cpuid_std_range_max || - (leaf->fn >= 0x40000000 && leaf->fn <= cpuid_hyp_range_max) || - (leaf->fn >= 0x80000000 && leaf->fn <= cpuid_ext_range_max))) + if (!(leaf->fn <= RIP_REL_REF(cpuid_std_range_max) || + (leaf->fn >= 0x40000000 && leaf->fn <= RIP_REL_REF(cpuid_hyp_range_max)) || + (leaf->fn >= 0x80000000 && leaf->fn <= RIP_REL_REF(cpuid_ext_range_max)))) return 0; } @@ -1072,11 +1072,11 @@ static void __init setup_cpuid_table(const struct cc_blob_sev_info *cc_info) const struct snp_cpuid_fn *fn = &cpuid_table->fn[i]; if (fn->eax_in == 0x0) - cpuid_std_range_max = fn->eax; + RIP_REL_REF(cpuid_std_range_max) = fn->eax; else if (fn->eax_in == 0x40000000) - cpuid_hyp_range_max = fn->eax; + RIP_REL_REF(cpuid_hyp_range_max) = fn->eax; else if (fn->eax_in == 0x80000000) - cpuid_ext_range_max = fn->eax; + RIP_REL_REF(cpuid_ext_range_max) = fn->eax; } } diff --git a/arch/x86/kernel/sev.c b/arch/x86/kernel/sev.c index 002af6c30601b..1ef7ae806a01b 100644 --- a/arch/x86/kernel/sev.c +++ b/arch/x86/kernel/sev.c @@ -748,7 +748,7 @@ void __init early_snp_set_memory_private(unsigned long vaddr, unsigned long padd * This eliminates worries about jump tables or checking boot_cpu_data * in the cc_platform_has() function. */ - if (!(sev_status & MSR_AMD64_SEV_SNP_ENABLED)) + if (!(RIP_REL_REF(sev_status) & MSR_AMD64_SEV_SNP_ENABLED)) return; /* @@ -767,7 +767,7 @@ void __init early_snp_set_memory_shared(unsigned long vaddr, unsigned long paddr * This eliminates worries about jump tables or checking boot_cpu_data * in the cc_platform_has() function. */ - if (!(sev_status & MSR_AMD64_SEV_SNP_ENABLED)) + if (!(RIP_REL_REF(sev_status) & MSR_AMD64_SEV_SNP_ENABLED)) return; /* Ask hypervisor to mark the memory pages shared in the RMP table. */ diff --git a/arch/x86/mm/mem_encrypt_identity.c b/arch/x86/mm/mem_encrypt_identity.c index efe9f217fcf99..0166ab1780ccb 100644 --- a/arch/x86/mm/mem_encrypt_identity.c +++ b/arch/x86/mm/mem_encrypt_identity.c @@ -304,7 +304,8 @@ void __init sme_encrypt_kernel(struct boot_params *bp) * instrumentation or checking boot_cpu_data in the cc_platform_has() * function. */ - if (!sme_get_me_mask() || sev_status & MSR_AMD64_SEV_ENABLED) + if (!sme_get_me_mask() || + RIP_REL_REF(sev_status) & MSR_AMD64_SEV_ENABLED) return; /* @@ -541,11 +542,11 @@ void __init sme_enable(struct boot_params *bp) me_mask = 1UL << (ebx & 0x3f); /* Check the SEV MSR whether SEV or SME is enabled */ - sev_status = __rdmsr(MSR_AMD64_SEV); - feature_mask = (sev_status & MSR_AMD64_SEV_ENABLED) ? AMD_SEV_BIT : AMD_SME_BIT; + RIP_REL_REF(sev_status) = msr = __rdmsr(MSR_AMD64_SEV); + feature_mask = (msr & MSR_AMD64_SEV_ENABLED) ? AMD_SEV_BIT : AMD_SME_BIT; /* The SEV-SNP CC blob should never be present unless SEV-SNP is enabled. */ - if (snp && !(sev_status & MSR_AMD64_SEV_SNP_ENABLED)) + if (snp && !(msr & MSR_AMD64_SEV_SNP_ENABLED)) snp_abort(); /* Check if memory encryption is enabled */ @@ -571,7 +572,6 @@ void __init sme_enable(struct boot_params *bp) return; } else { /* SEV state cannot be controlled by a command line option */ - sme_me_mask = me_mask; goto out; } @@ -590,16 +590,13 @@ void __init sme_enable(struct boot_params *bp) cmdline_ptr = (const char *)((u64)bp->hdr.cmd_line_ptr | ((u64)bp->ext_cmd_line_ptr << 32)); - if (cmdline_find_option(cmdline_ptr, cmdline_arg, buffer, sizeof(buffer)) < 0) - goto out; - - if (!strncmp(buffer, cmdline_on, sizeof(buffer))) - sme_me_mask = me_mask; + if (cmdline_find_option(cmdline_ptr, cmdline_arg, buffer, sizeof(buffer)) < 0 || + strncmp(buffer, cmdline_on, sizeof(buffer))) + return; out: - if (sme_me_mask) { - physical_mask &= ~sme_me_mask; - cc_vendor = CC_VENDOR_AMD; - cc_set_mask(sme_me_mask); - } + RIP_REL_REF(sme_me_mask) = me_mask; + physical_mask &= ~me_mask; + cc_vendor = CC_VENDOR_AMD; + cc_set_mask(me_mask); } -- 2.43.0

1 year, 3 months

1
0
0 0

FAILED: Patch "tracing/ring-buffer: Fix wait_on_pipe() race" failed to apply to 6.6-stable tree

by Sasha Levin

The patch below does not apply to the 6.6-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. Thanks, Sasha ------------------ original commit in Linus's tree ------------------ From 2aa043a55b9a764c9cbde5a8c654eeaaffe224cf Mon Sep 17 00:00:00 2001 From: "Steven Rostedt (Google)" <rostedt(a)goodmis.org> Date: Tue, 12 Mar 2024 08:15:08 -0400 Subject: [PATCH] tracing/ring-buffer: Fix wait_on_pipe() race When the trace_pipe_raw file is closed, there should be no new readers on the file descriptor. This is mostly handled with the waking and wait_index fields of the iterator. But there's still a slight race. CPU 0 CPU 1 ----- ----- wait_index++; index = wait_index; ring_buffer_wake_waiters(); wait_on_pipe() ring_buffer_wait(); The ring_buffer_wait() will miss the wakeup from CPU 1. The problem is that the ring_buffer_wait() needs the logic of: prepare_to_wait(); if (!condition) schedule(); Where the missing condition check is the iter->wait_index update. Have the ring_buffer_wait() take a conditional callback function and a data parameter that can be used within the wait_event_interruptible() of the ring_buffer_wait() function. In wait_on_pipe(), pass a condition function that will check if the wait_index has been updated, if it has, it will return true to break out of the wait_event_interruptible() loop. Create a new field "closed" in the trace_iterator and set it in the .flush() callback before calling ring_buffer_wake_waiters(). This will keep any new readers from waiting on a closed file descriptor. Have the wait_on_pipe() condition callback also check the closed field. Change the wait_index field of the trace_iterator to atomic_t. There's no reason it needs to be 'long' and making it atomic and using atomic_read_acquire() and atomic_fetch_inc_release() will provide the necessary memory barriers. Add a "woken" flag to tracing_buffers_splice_read() to exit the loop after one more try to fetch data. That is, if it waited for data and something woke it up, it should try to collect any new data and then exit back to user space. Link: https://lore.kernel.org/linux-trace-kernel/CAHk-=wgsNgewHFxZAJiAQznwPMqEtQm… Link: https://lore.kernel.org/linux-trace-kernel/20240312121703.557950713@goodmis… Cc: stable(a)vger.kernel.org Cc: Masami Hiramatsu <mhiramat(a)kernel.org> Cc: Mark Rutland <mark.rutland(a)arm.com> Cc: Mathieu Desnoyers <mathieu.desnoyers(a)efficios.com> Cc: Andrew Morton <akpm(a)linux-foundation.org> Cc: Linus Torvalds <torvalds(a)linux-foundation.org> Cc: linke li <lilinke99(a)qq.com> Cc: Rabin Vincent <rabin(a)rab.in> Fixes: f3ddb74ad0790 ("tracing: Wake up ring buffer waiters on closing of the file") Signed-off-by: Steven Rostedt (Google) <rostedt(a)goodmis.org> --- include/linux/ring_buffer.h | 3 ++- include/linux/trace_events.h | 5 ++++- kernel/trace/ring_buffer.c | 13 ++++++----- kernel/trace/trace.c | 43 ++++++++++++++++++++++++++---------- 4 files changed, 45 insertions(+), 19 deletions(-) diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h index 338a33db1577e..dc5ae4e96aee0 100644 --- a/include/linux/ring_buffer.h +++ b/include/linux/ring_buffer.h @@ -99,7 +99,8 @@ __ring_buffer_alloc(unsigned long size, unsigned flags, struct lock_class_key *k }) typedef bool (*ring_buffer_cond_fn)(void *data); -int ring_buffer_wait(struct trace_buffer *buffer, int cpu, int full); +int ring_buffer_wait(struct trace_buffer *buffer, int cpu, int full, + ring_buffer_cond_fn cond, void *data); __poll_t ring_buffer_poll_wait(struct trace_buffer *buffer, int cpu, struct file *filp, poll_table *poll_table, int full); void ring_buffer_wake_waiters(struct trace_buffer *buffer, int cpu); diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h index d68ff9b1247f9..fc6d0af56bb17 100644 --- a/include/linux/trace_events.h +++ b/include/linux/trace_events.h @@ -103,13 +103,16 @@ struct trace_iterator { unsigned int temp_size; char *fmt; /* modified format holder */ unsigned int fmt_size; - long wait_index; + atomic_t wait_index; /* trace_seq for __print_flags() and __print_symbolic() etc. */ struct trace_seq tmp_seq; cpumask_var_t started; + /* Set when the file is closed to prevent new waiters */ + bool closed; + /* it's true when current open file is snapshot */ bool snapshot; diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c index f4c34b7c7e1e7..350607cce8694 100644 --- a/kernel/trace/ring_buffer.c +++ b/kernel/trace/ring_buffer.c @@ -902,23 +902,26 @@ static bool rb_wait_once(void *data) * @buffer: buffer to wait on * @cpu: the cpu buffer to wait on * @full: wait until the percentage of pages are available, if @cpu != RING_BUFFER_ALL_CPUS + * @cond: condition function to break out of wait (NULL to run once) + * @data: the data to pass to @cond. * * If @cpu == RING_BUFFER_ALL_CPUS then the task will wake up as soon * as data is added to any of the @buffer's cpu buffers. Otherwise * it will wait for data to be added to a specific cpu buffer. */ -int ring_buffer_wait(struct trace_buffer *buffer, int cpu, int full) +int ring_buffer_wait(struct trace_buffer *buffer, int cpu, int full, + ring_buffer_cond_fn cond, void *data) { struct ring_buffer_per_cpu *cpu_buffer; struct wait_queue_head *waitq; - ring_buffer_cond_fn cond; struct rb_irq_work *rbwork; - void *data; long once = 0; int ret = 0; - cond = rb_wait_once; - data = &once; + if (!cond) { + cond = rb_wait_once; + data = &once; + } /* * Depending on what the caller is waiting for, either any diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index c9c8983073485..d390fea3a6a52 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -1955,15 +1955,36 @@ update_max_tr_single(struct trace_array *tr, struct task_struct *tsk, int cpu) #endif /* CONFIG_TRACER_MAX_TRACE */ +struct pipe_wait { + struct trace_iterator *iter; + int wait_index; +}; + +static bool wait_pipe_cond(void *data) +{ + struct pipe_wait *pwait = data; + struct trace_iterator *iter = pwait->iter; + + if (atomic_read_acquire(&iter->wait_index) != pwait->wait_index) + return true; + + return iter->closed; +} + static int wait_on_pipe(struct trace_iterator *iter, int full) { + struct pipe_wait pwait; int ret; /* Iterators are static, they should be filled or empty */ if (trace_buffer_iter(iter, iter->cpu_file)) return 0; - ret = ring_buffer_wait(iter->array_buffer->buffer, iter->cpu_file, full); + pwait.wait_index = atomic_read_acquire(&iter->wait_index); + pwait.iter = iter; + + ret = ring_buffer_wait(iter->array_buffer->buffer, iter->cpu_file, full, + wait_pipe_cond, &pwait); #ifdef CONFIG_TRACER_MAX_TRACE /* @@ -8398,9 +8419,9 @@ static int tracing_buffers_flush(struct file *file, fl_owner_t id) struct ftrace_buffer_info *info = file->private_data; struct trace_iterator *iter = &info->iter; - iter->wait_index++; + iter->closed = true; /* Make sure the waiters see the new wait_index */ - smp_wmb(); + (void)atomic_fetch_inc_release(&iter->wait_index); ring_buffer_wake_waiters(iter->array_buffer->buffer, iter->cpu_file); @@ -8500,6 +8521,7 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos, .spd_release = buffer_spd_release, }; struct buffer_ref *ref; + bool woken = false; int page_size; int entries, i; ssize_t ret = 0; @@ -8573,17 +8595,17 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos, /* did we read anything? */ if (!spd.nr_pages) { - long wait_index; if (ret) goto out; + if (woken) + goto out; + ret = -EAGAIN; if ((file->f_flags & O_NONBLOCK) || (flags & SPLICE_F_NONBLOCK)) goto out; - wait_index = READ_ONCE(iter->wait_index); - ret = wait_on_pipe(iter, iter->snapshot ? 0 : iter->tr->buffer_percent); if (ret) goto out; @@ -8592,10 +8614,8 @@ tracing_buffers_splice_read(struct file *file, loff_t *ppos, if (!tracer_tracing_is_on(iter->tr)) goto out; - /* Make sure we see the new wait_index */ - smp_rmb(); - if (wait_index != iter->wait_index) - goto out; + /* Iterate one more time to collect any new data then exit */ + woken = true; goto again; } @@ -8618,9 +8638,8 @@ static long tracing_buffers_ioctl(struct file *file, unsigned int cmd, unsigned mutex_lock(&trace_types_lock); - iter->wait_index++; /* Make sure the waiters see the new wait_index */ - smp_wmb(); + (void)atomic_fetch_inc_release(&iter->wait_index); ring_buffer_wake_waiters(iter->array_buffer->buffer, iter->cpu_file); -- 2.43.0

1 year, 3 months

1
0
0 0

FAILED: Patch "drm/amd/display: Implement wait_for_odm_update_pending_complete" failed to apply to 6.6-stable tree

by Sasha Levin

The patch below does not apply to the 6.6-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. Thanks, Sasha ------------------ original commit in Linus's tree ------------------ From 2d7f3d1a5866705be2393150e1ffdf67030ab88d Mon Sep 17 00:00:00 2001 From: Wenjing Liu <wenjing.liu(a)amd.com> Date: Fri, 23 Feb 2024 15:38:40 -0500 Subject: [PATCH] drm/amd/display: Implement wait_for_odm_update_pending_complete [WHY] Odm update is doubled buffered. We need to wait for ODM update to be completed before optimizing bandwidth or programming new udpates. [HOW] implement wait_for_odm_update_pending_complete function to wait for: 1. odm configuration update is no longer pending in timing generator. 2. no pending dpg pattern update for each active OPP. Cc: Mario Limonciello <mario.limonciello(a)amd.com> Cc: Alex Deucher <alexander.deucher(a)amd.com> Cc: stable(a)vger.kernel.org Reviewed-by: Alvin Lee <alvin.lee2(a)amd.com> Acked-by: Alex Hung <alex.hung(a)amd.com> Signed-off-by: Wenjing Liu <wenjing.liu(a)amd.com> Tested-by: Daniel Wheeler <daniel.wheeler(a)amd.com> Signed-off-by: Alex Deucher <alexander.deucher(a)amd.com> --- drivers/gpu/drm/amd/display/dc/core/dc.c | 56 ++++++++++++++++++- .../gpu/drm/amd/display/dc/dcn10/dcn10_opp.c | 1 + .../gpu/drm/amd/display/dc/dcn20/dcn20_opp.c | 14 +++++ .../gpu/drm/amd/display/dc/dcn20/dcn20_opp.h | 2 + .../drm/amd/display/dc/dcn201/dcn201_opp.c | 1 + .../amd/display/dc/hwss/dcn20/dcn20_hwseq.c | 4 +- drivers/gpu/drm/amd/display/dc/inc/hw/opp.h | 3 + .../amd/display/dc/inc/hw/timing_generator.h | 1 + .../amd/display/dc/optc/dcn10/dcn10_optc.h | 3 +- .../amd/display/dc/optc/dcn32/dcn32_optc.c | 8 +++ .../amd/display/dc/optc/dcn32/dcn32_optc.h | 1 + 11 files changed, 90 insertions(+), 4 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c index 958552a8605ff..e7dc128f6284b 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc.c @@ -1302,6 +1302,54 @@ static void disable_vbios_mode_if_required( } } +/** + * wait_for_blank_complete - wait for all active OPPs to finish pending blank + * pattern updates + * + * @dc: [in] dc reference + * @context: [in] hardware context in use + */ +static void wait_for_blank_complete(struct dc *dc, + struct dc_state *context) +{ + struct pipe_ctx *opp_head; + struct dce_hwseq *hws = dc->hwseq; + int i; + + if (!hws->funcs.wait_for_blank_complete) + return; + + for (i = 0; i < MAX_PIPES; i++) { + opp_head = &context->res_ctx.pipe_ctx[i]; + + if (!resource_is_pipe_type(opp_head, OPP_HEAD) || + dc_state_get_pipe_subvp_type(context, opp_head) == SUBVP_PHANTOM) + continue; + + hws->funcs.wait_for_blank_complete(opp_head->stream_res.opp); + } +} + +static void wait_for_odm_update_pending_complete(struct dc *dc, struct dc_state *context) +{ + struct pipe_ctx *otg_master; + struct timing_generator *tg; + int i; + + for (i = 0; i < MAX_PIPES; i++) { + otg_master = &context->res_ctx.pipe_ctx[i]; + if (!resource_is_pipe_type(otg_master, OTG_MASTER) || + dc_state_get_pipe_subvp_type(context, otg_master) == SUBVP_PHANTOM) + continue; + tg = otg_master->stream_res.tg; + if (tg->funcs->wait_odm_doublebuffer_pending_clear) + tg->funcs->wait_odm_doublebuffer_pending_clear(tg); + } + + /* ODM update may require to reprogram blank pattern for each OPP */ + wait_for_blank_complete(dc, context); +} + static void wait_for_no_pipes_pending(struct dc *dc, struct dc_state *context) { int i; @@ -1993,6 +2041,11 @@ static enum dc_status dc_commit_state_no_check(struct dc *dc, struct dc_state *c context->stream_count == 0) { /* Must wait for no flips to be pending before doing optimize bw */ wait_for_no_pipes_pending(dc, context); + /* + * optimized dispclk depends on ODM setup. Need to wait for ODM + * update pending complete before optimizing bandwidth. + */ + wait_for_odm_update_pending_complete(dc, context); /* pplib is notified if disp_num changed */ dc->hwss.optimize_bandwidth(dc, context); /* Need to do otg sync again as otg could be out of sync due to otg @@ -3496,7 +3549,7 @@ static void commit_planes_for_stream_fast(struct dc *dc, top_pipe_to_program->stream->update_flags.raw = 0; } -static void wait_for_outstanding_hw_updates(struct dc *dc, const struct dc_state *dc_context) +static void wait_for_outstanding_hw_updates(struct dc *dc, struct dc_state *dc_context) { /* * This function calls HWSS to wait for any potentially double buffered @@ -3534,6 +3587,7 @@ static void wait_for_outstanding_hw_updates(struct dc *dc, const struct dc_state } } } + wait_for_odm_update_pending_complete(dc, dc_context); } static void commit_planes_for_stream(struct dc *dc, diff --git a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_opp.c b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_opp.c index 48a40dcc7050b..5838a11efd00c 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_opp.c +++ b/drivers/gpu/drm/amd/display/dc/dcn10/dcn10_opp.c @@ -384,6 +384,7 @@ static const struct opp_funcs dcn10_opp_funcs = { .opp_set_disp_pattern_generator = NULL, .opp_program_dpg_dimensions = NULL, .dpg_is_blanked = NULL, + .dpg_is_pending = NULL, .opp_destroy = opp1_destroy }; diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_opp.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_opp.c index 0784d01986610..fbf1b6370eb23 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_opp.c +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_opp.c @@ -337,6 +337,19 @@ bool opp2_dpg_is_blanked(struct output_pixel_processor *opp) (double_buffer_pending == 0); } +bool opp2_dpg_is_pending(struct output_pixel_processor *opp) +{ + struct dcn20_opp *oppn20 = TO_DCN20_OPP(opp); + uint32_t double_buffer_pending; + uint32_t dpg_en; + + REG_GET(DPG_CONTROL, DPG_EN, &dpg_en); + + REG_GET(DPG_STATUS, DPG_DOUBLE_BUFFER_PENDING, &double_buffer_pending); + + return (dpg_en == 1 && double_buffer_pending == 1); +} + void opp2_program_left_edge_extra_pixel ( struct output_pixel_processor *opp, bool count) @@ -363,6 +376,7 @@ static struct opp_funcs dcn20_opp_funcs = { .opp_set_disp_pattern_generator = opp2_set_disp_pattern_generator, .opp_program_dpg_dimensions = opp2_program_dpg_dimensions, .dpg_is_blanked = opp2_dpg_is_blanked, + .dpg_is_pending = opp2_dpg_is_pending, .opp_dpg_set_blank_color = opp2_dpg_set_blank_color, .opp_destroy = opp1_destroy, .opp_program_left_edge_extra_pixel = opp2_program_left_edge_extra_pixel, diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_opp.h b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_opp.h index 3ab221bdd27dd..8f186abd558db 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_opp.h +++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_opp.h @@ -159,6 +159,8 @@ void opp2_program_dpg_dimensions( bool opp2_dpg_is_blanked(struct output_pixel_processor *opp); +bool opp2_dpg_is_pending(struct output_pixel_processor *opp); + void opp2_dpg_set_blank_color( struct output_pixel_processor *opp, const struct tg_color *color); diff --git a/drivers/gpu/drm/amd/display/dc/dcn201/dcn201_opp.c b/drivers/gpu/drm/amd/display/dc/dcn201/dcn201_opp.c index 8e77db46a4090..6a71ba3dfc632 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn201/dcn201_opp.c +++ b/drivers/gpu/drm/amd/display/dc/dcn201/dcn201_opp.c @@ -50,6 +50,7 @@ static struct opp_funcs dcn201_opp_funcs = { .opp_set_disp_pattern_generator = opp2_set_disp_pattern_generator, .opp_program_dpg_dimensions = opp2_program_dpg_dimensions, .dpg_is_blanked = opp2_dpg_is_blanked, + .dpg_is_pending = opp2_dpg_is_pending, .opp_dpg_set_blank_color = opp2_dpg_set_blank_color, .opp_destroy = opp1_destroy, .opp_program_left_edge_extra_pixel = opp2_program_left_edge_extra_pixel, diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.c index 40098d9f70cbc..8b3536c380b8d 100644 --- a/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.c +++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn20/dcn20_hwseq.c @@ -2452,7 +2452,7 @@ bool dcn20_wait_for_blank_complete( int counter; for (counter = 0; counter < 1000; counter++) { - if (opp->funcs->dpg_is_blanked(opp)) + if (!opp->funcs->dpg_is_pending(opp)) break; udelay(100); @@ -2463,7 +2463,7 @@ bool dcn20_wait_for_blank_complete( return false; } - return true; + return opp->funcs->dpg_is_blanked(opp); } bool dcn20_dmdata_status_done(struct pipe_ctx *pipe_ctx) diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/opp.h b/drivers/gpu/drm/amd/display/dc/inc/hw/opp.h index aee5372e292c5..d89c92370d5b3 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/hw/opp.h +++ b/drivers/gpu/drm/amd/display/dc/inc/hw/opp.h @@ -337,6 +337,9 @@ struct opp_funcs { bool (*dpg_is_blanked)( struct output_pixel_processor *opp); + bool (*dpg_is_pending)(struct output_pixel_processor *opp); + + void (*opp_dpg_set_blank_color)( struct output_pixel_processor *opp, const struct tg_color *color); diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/timing_generator.h b/drivers/gpu/drm/amd/display/dc/inc/hw/timing_generator.h index d98d72f35be5b..ffad8fe16c54d 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/hw/timing_generator.h +++ b/drivers/gpu/drm/amd/display/dc/inc/hw/timing_generator.h @@ -331,6 +331,7 @@ struct timing_generator_funcs { void (*init_odm)(struct timing_generator *tg); void (*wait_drr_doublebuffer_pending_clear)(struct timing_generator *tg); + void (*wait_odm_doublebuffer_pending_clear)(struct timing_generator *tg); }; #endif diff --git a/drivers/gpu/drm/amd/display/dc/optc/dcn10/dcn10_optc.h b/drivers/gpu/drm/amd/display/dc/optc/dcn10/dcn10_optc.h index ab81594a7fadc..6c2e84d3967fc 100644 --- a/drivers/gpu/drm/amd/display/dc/optc/dcn10/dcn10_optc.h +++ b/drivers/gpu/drm/amd/display/dc/optc/dcn10/dcn10_optc.h @@ -557,7 +557,8 @@ struct dcn_optc_registers { type OTG_CRC_DATA_STREAM_SPLIT_MODE;\ type OTG_CRC_DATA_FORMAT;\ type OTG_V_TOTAL_LAST_USED_BY_DRR;\ - type OTG_DRR_TIMING_DBUF_UPDATE_PENDING; + type OTG_DRR_TIMING_DBUF_UPDATE_PENDING;\ + type OTG_H_TIMING_DIV_MODE_DB_UPDATE_PENDING; #define TG_REG_FIELD_LIST_DCN3_2(type) \ type OTG_H_TIMING_DIV_MODE_MANUAL; diff --git a/drivers/gpu/drm/amd/display/dc/optc/dcn32/dcn32_optc.c b/drivers/gpu/drm/amd/display/dc/optc/dcn32/dcn32_optc.c index 8234935433254..f07a4c7e48bc2 100644 --- a/drivers/gpu/drm/amd/display/dc/optc/dcn32/dcn32_optc.c +++ b/drivers/gpu/drm/amd/display/dc/optc/dcn32/dcn32_optc.c @@ -122,6 +122,13 @@ void optc32_get_odm_combine_segments(struct timing_generator *tg, int *odm_combi } } +void optc32_wait_odm_doublebuffer_pending_clear(struct timing_generator *tg) +{ + struct optc *optc1 = DCN10TG_FROM_TG(tg); + + REG_WAIT(OTG_DOUBLE_BUFFER_CONTROL, OTG_H_TIMING_DIV_MODE_DB_UPDATE_PENDING, 0, 2, 50000); +} + void optc32_set_h_timing_div_manual_mode(struct timing_generator *optc, bool manual_mode) { struct optc *optc1 = DCN10TG_FROM_TG(optc); @@ -345,6 +352,7 @@ static struct timing_generator_funcs dcn32_tg_funcs = { .set_odm_bypass = optc32_set_odm_bypass, .set_odm_combine = optc32_set_odm_combine, .get_odm_combine_segments = optc32_get_odm_combine_segments, + .wait_odm_doublebuffer_pending_clear = optc32_wait_odm_doublebuffer_pending_clear, .set_h_timing_div_manual_mode = optc32_set_h_timing_div_manual_mode, .get_optc_source = optc2_get_optc_source, .set_out_mux = optc3_set_out_mux, diff --git a/drivers/gpu/drm/amd/display/dc/optc/dcn32/dcn32_optc.h b/drivers/gpu/drm/amd/display/dc/optc/dcn32/dcn32_optc.h index 8ce3b178cab06..0c2c146955619 100644 --- a/drivers/gpu/drm/amd/display/dc/optc/dcn32/dcn32_optc.h +++ b/drivers/gpu/drm/amd/display/dc/optc/dcn32/dcn32_optc.h @@ -183,5 +183,6 @@ void optc32_set_h_timing_div_manual_mode(struct timing_generator *optc, bool man void optc32_get_odm_combine_segments(struct timing_generator *tg, int *odm_combine_segments); void optc32_set_odm_bypass(struct timing_generator *optc, const struct dc_crtc_timing *dc_crtc_timing); +void optc32_wait_odm_doublebuffer_pending_clear(struct timing_generator *tg); #endif /* __DC_OPTC_DCN32_H__ */ -- 2.43.0

1 year, 3 months

1
0
0 0

FAILED: Patch "Revert "drm/amd/display: Send DTBCLK disable message on first commit"" failed to apply to 6.6-stable tree

by Sasha Levin

The patch below does not apply to the 6.6-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. Thanks, Sasha ------------------ original commit in Linus's tree ------------------ From 3a6a32b31a111f6e66526fb2d3cb13a876465076 Mon Sep 17 00:00:00 2001 From: Gabe Teeger <gabe.teeger(a)amd.com> Date: Mon, 29 Jan 2024 13:31:44 -0500 Subject: [PATCH] Revert "drm/amd/display: Send DTBCLK disable message on first commit" This reverts commit f341055b10bd8be55c3c995dff5f770b236b8ca9. System hang observed, this commit is thought to be the regression point. Cc: Mario Limonciello <mario.limonciello(a)amd.com> Cc: Alex Deucher <alexander.deucher(a)amd.com> Cc: stable(a)vger.kernel.org Reviewed-by: Ovidiu Bunea <ovidiu.bunea(a)amd.com> Acked-by: Aurabindo Pillai <aurabindo.pillai(a)amd.com> Signed-off-by: Gabe Teeger <gabe.teeger(a)amd.com> Tested-by: Daniel Wheeler <daniel.wheeler(a)amd.com> Signed-off-by: Alex Deucher <alexander.deucher(a)amd.com> --- drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c | 1 - 1 file changed, 1 deletion(-) 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 06edca50a8fa1..36e5bb611fb10 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 @@ -414,7 +414,6 @@ static void init_clk_states(struct clk_mgr *clk_mgr) uint32_t ref_dtbclk = clk_mgr->clks.ref_dtbclk_khz; memset(&(clk_mgr->clks), 0, sizeof(struct dc_clocks)); - clk_mgr->clks.dtbclk_en = true; clk_mgr->clks.ref_dtbclk_khz = ref_dtbclk; // restore ref_dtbclk clk_mgr->clks.p_state_change_support = true; clk_mgr->clks.prev_p_state_change_support = true; -- 2.43.0

1 year, 3 months

1
0
0 0

FAILED: Patch "drm/amd/display: Fix idle check for shared firmware state" failed to apply to 6.6-stable tree

by Sasha Levin

The patch below does not apply to the 6.6-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. Thanks, Sasha ------------------ original commit in Linus's tree ------------------ From 3d066f9547dd58329b526db44f42c487a7974703 Mon Sep 17 00:00:00 2001 From: Nicholas Kazlauskas <nicholas.kazlauskas(a)amd.com> Date: Wed, 21 Feb 2024 12:27:31 -0500 Subject: [PATCH] drm/amd/display: Fix idle check for shared firmware state [WHY] We still had an instance of get_idle_state checking the PMFW scratch register instead of the actual idle allow signal. [HOW] Replace it with the SW state check for whether we had allowed idle through notify_idle. Cc: Mario Limonciello <mario.limonciello(a)amd.com> Cc: Alex Deucher <alexander.deucher(a)amd.com> Cc: stable(a)vger.kernel.org Reviewed-by: Duncan Ma <duncan.ma(a)amd.com> Acked-by: Alex Hung <alex.hung(a)amd.com> Signed-off-by: Nicholas Kazlauskas <nicholas.kazlauskas(a)amd.com> Tested-by: Daniel Wheeler <daniel.wheeler(a)amd.com> Signed-off-by: Alex Deucher <alexander.deucher(a)amd.com> --- drivers/gpu/drm/amd/display/dc/core/dc.c | 12 +++--------- 1 file changed, 3 insertions(+), 9 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c index 613d09c42f3b9..958552a8605ff 100644 --- a/drivers/gpu/drm/amd/display/dc/core/dc.c +++ b/drivers/gpu/drm/amd/display/dc/core/dc.c @@ -4847,22 +4847,16 @@ void dc_exit_ips_for_hw_access(struct dc *dc) bool dc_dmub_is_ips_idle_state(struct dc *dc) { - uint32_t idle_state = 0; - if (dc->debug.disable_idle_power_optimizations) return false; if (!dc->caps.ips_support || (dc->config.disable_ips == DMUB_IPS_DISABLE_ALL)) return false; - if (dc->hwss.get_idle_state) - idle_state = dc->hwss.get_idle_state(dc); - - if (!(idle_state & DMUB_IPS1_ALLOW_MASK) || - !(idle_state & DMUB_IPS2_ALLOW_MASK)) - return true; + if (!dc->ctx->dmub_srv) + return false; - return false; + return dc->ctx->dmub_srv->idle_allowed; } /* set min and max memory clock to lowest and highest DPM level, respectively */ -- 2.43.0

1 year, 3 months

1
0
0 0

FAILED: Patch "drm/amd/display: Only allow dig mapping to pwrseq in new asic" failed to apply to 6.6-stable tree

by Sasha Levin

The patch below does not apply to the 6.6-stable tree. If someone wants it applied there, or to any other stable or longterm tree, then please email the backport, including the original git commit id to <stable(a)vger.kernel.org>. Thanks, Sasha ------------------ original commit in Linus's tree ------------------ From 4af4d2c275aeb667bc2bca0d2135b825e931a55a Mon Sep 17 00:00:00 2001 From: Lewis Huang <lewis.huang(a)amd.com> Date: Wed, 31 Jan 2024 17:20:17 +0800 Subject: [PATCH] drm/amd/display: Only allow dig mapping to pwrseq in new asic [Why] The old asic only have 1 pwrseq hw. We don't need to map the diginst to pwrseq inst in old asic. [How] 1. Only mapping dig to pwrseq for new asic. 2. Move mapping function into dcn specific panel control component Cc: Stable <stable(a)vger.kernel.org> # v6.6+ Cc: Mario Limonciello <mario.limonciello(a)amd.com> Link: https://gitlab.freedesktop.org/drm/amd/-/issues/3122 Reviewed-by: Anthony Koo <anthony.koo(a)amd.com> Acked-by: Rodrigo Siqueira <rodrigo.siqueira(a)amd.com> Tested-by: Daniel Wheeler <daniel.wheeler(a)amd.com> Signed-off-by: Lewis Huang <lewis.huang(a)amd.com> Signed-off-by: Alex Deucher <alexander.deucher(a)amd.com> --- .../drm/amd/display/dc/dce/dce_panel_cntl.c | 1 + .../amd/display/dc/dcn301/dcn301_panel_cntl.c | 1 + .../amd/display/dc/dcn31/dcn31_panel_cntl.c | 18 ++++++++++++- .../drm/amd/display/dc/inc/hw/panel_cntl.h | 2 +- .../drm/amd/display/dc/link/link_factory.c | 26 +------------------ 5 files changed, 21 insertions(+), 27 deletions(-) diff --git a/drivers/gpu/drm/amd/display/dc/dce/dce_panel_cntl.c b/drivers/gpu/drm/amd/display/dc/dce/dce_panel_cntl.c index e8570060d007b..5bca67407c5b1 100644 --- a/drivers/gpu/drm/amd/display/dc/dce/dce_panel_cntl.c +++ b/drivers/gpu/drm/amd/display/dc/dce/dce_panel_cntl.c @@ -290,4 +290,5 @@ void dce_panel_cntl_construct( dce_panel_cntl->base.funcs = &dce_link_panel_cntl_funcs; dce_panel_cntl->base.ctx = init_data->ctx; dce_panel_cntl->base.inst = init_data->inst; + dce_panel_cntl->base.pwrseq_inst = 0; } diff --git a/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_panel_cntl.c b/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_panel_cntl.c index ad0df1a72a90a..9e96a3ace2077 100644 --- a/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_panel_cntl.c +++ b/drivers/gpu/drm/amd/display/dc/dcn301/dcn301_panel_cntl.c @@ -215,4 +215,5 @@ void dcn301_panel_cntl_construct( dcn301_panel_cntl->base.funcs = &dcn301_link_panel_cntl_funcs; dcn301_panel_cntl->base.ctx = init_data->ctx; dcn301_panel_cntl->base.inst = init_data->inst; + dcn301_panel_cntl->base.pwrseq_inst = 0; } 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 03248422d6ffd..281be20b1a107 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 @@ -154,8 +154,24 @@ void dcn31_panel_cntl_construct( struct dcn31_panel_cntl *dcn31_panel_cntl, const struct panel_cntl_init_data *init_data) { + uint8_t pwrseq_inst = 0xF; + dcn31_panel_cntl->base.funcs = &dcn31_link_panel_cntl_funcs; dcn31_panel_cntl->base.ctx = init_data->ctx; dcn31_panel_cntl->base.inst = init_data->inst; - dcn31_panel_cntl->base.pwrseq_inst = init_data->pwrseq_inst; + + switch (init_data->eng_id) { + case ENGINE_ID_DIGA: + pwrseq_inst = 0; + break; + case ENGINE_ID_DIGB: + pwrseq_inst = 1; + break; + default: + DC_LOG_WARNING("Unsupported pwrseq engine id: %d!\n", init_data->eng_id); + ASSERT(false); + break; + } + + dcn31_panel_cntl->base.pwrseq_inst = pwrseq_inst; } diff --git a/drivers/gpu/drm/amd/display/dc/inc/hw/panel_cntl.h b/drivers/gpu/drm/amd/display/dc/inc/hw/panel_cntl.h index 5dcbaa2db964a..e97d964a1791c 100644 --- a/drivers/gpu/drm/amd/display/dc/inc/hw/panel_cntl.h +++ b/drivers/gpu/drm/amd/display/dc/inc/hw/panel_cntl.h @@ -57,7 +57,7 @@ struct panel_cntl_funcs { struct panel_cntl_init_data { struct dc_context *ctx; uint32_t inst; - uint32_t pwrseq_inst; + uint32_t eng_id; }; struct panel_cntl { diff --git a/drivers/gpu/drm/amd/display/dc/link/link_factory.c b/drivers/gpu/drm/amd/display/dc/link/link_factory.c index 37d3027c32dcb..cf22b8f28ba6c 100644 --- a/drivers/gpu/drm/amd/display/dc/link/link_factory.c +++ b/drivers/gpu/drm/amd/display/dc/link/link_factory.c @@ -370,30 +370,6 @@ static enum transmitter translate_encoder_to_transmitter( } } -static uint8_t translate_dig_inst_to_pwrseq_inst(struct dc_link *link) -{ - uint8_t pwrseq_inst = 0xF; - struct dc_context *dc_ctx = link->dc->ctx; - - DC_LOGGER_INIT(dc_ctx->logger); - - switch (link->eng_id) { - case ENGINE_ID_DIGA: - pwrseq_inst = 0; - break; - case ENGINE_ID_DIGB: - pwrseq_inst = 1; - break; - default: - DC_LOG_WARNING("Unsupported pwrseq engine id: %d!\n", link->eng_id); - ASSERT(false); - break; - } - - return pwrseq_inst; -} - - static void link_destruct(struct dc_link *link) { int i; @@ -657,7 +633,7 @@ static bool construct_phy(struct dc_link *link, link->link_id.id == CONNECTOR_ID_LVDS)) { panel_cntl_init_data.ctx = dc_ctx; panel_cntl_init_data.inst = panel_cntl_init_data.ctx->dc_edp_id_count; - panel_cntl_init_data.pwrseq_inst = translate_dig_inst_to_pwrseq_inst(link); + panel_cntl_init_data.eng_id = link->eng_id; link->panel_cntl = link->dc->res_pool->funcs->panel_cntl_create( &panel_cntl_init_data); -- 2.43.0

1 year, 3 months

1
0
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror March 2024