December 2023 - Linux-stable-mirror

FAILED: patch "[PATCH] drm/i915: Skip some timing checks on BXT/GLK DSI transcoders" failed to apply to 6.1-stable tree

by gregkh＠linuxfoundation.org

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>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.1.y git checkout FETCH_HEAD git cherry-pick -x 20c2dbff342aec13bf93c2f6c951da198916a455 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023120943-defeat-twerp-da3a@gregkh' --subject-prefix 'PATCH 6.1.y' HEAD^.. Possible dependencies: 20c2dbff342a ("drm/i915: Skip some timing checks on BXT/GLK DSI transcoders") f2f9c8cb6421 ("drm/i915/sdvo: stop caching has_hdmi_monitor in struct intel_sdvo") 19d7dc6638a9 ("drm/i915/lvds: s/intel_encoder/encoder/ etc.") 7f66476c930c ("drm/i915/lvds: s/dev_priv/i915/") 9dd56e979cb6 ("drm/i915/lvds: Use REG_BIT() & co.") 15d045fd85eb ("drm/i915/panel: move panel fixed EDID to struct intel_panel") c36225a1e046 ("drm/i915/bios: convert intel_bios_init_panel() to drm_edid") 25fa6b0f69ac ("drm/i915/edid: convert DP, HDMI and LVDS to drm_edid") 9d04eb20bc71 ("drm/i915/display: Drop check for doublescan mode in modevalid") 3f9ffce5765d ("drm/i915: Do panel VBT init early if the VBT declares an explicit panel type") f70f8153e364 ("drm/i915: Introduce intel_panel_init_alloc()") 09b350d7b05a ("drm/i915/dvo: s/intel_encoder/encoder/ etc.") d82b9a898d52 ("drm/i915/dvo: Flatten intel_dvo_init()") c584f86c6242 ("drm/i915/dvo: Eliminate useless 'port' variable") 201ec1bbca03 ("drm/i915/dvo: Introduce intel_dvo_connector_type()") 6ebf5caf1fae ("drm/i915/dvo: Actually initialize the DVO encoder type") 3b5130a68df1 ("drm/i915/dvo: Don't leak connector state on DVO init failure") 4b9cc6efeb06 ("drm/i915/dvo: Remove unused panel_wants_dither") 002c6ca75289 ("Merge drm/drm-next into drm-intel-next") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 20c2dbff342aec13bf93c2f6c951da198916a455 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ville=20Syrj=C3=A4l=C3=A4?= <ville.syrjala(a)linux.intel.com> Date: Mon, 27 Nov 2023 16:50:25 +0200 Subject: [PATCH] drm/i915: Skip some timing checks on BXT/GLK DSI transcoders MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Apparently some BXT/GLK systems have DSI panels whose timings don't agree with the normal cpu transcoder hblank>=32 limitation. This is perhaps fine as there are no specific hblank/etc. limits listed for the BXT/GLK DSI transcoders. Move those checks out from the global intel_mode_valid() into into connector specific .mode_valid() hooks, skipping BXT/GLK DSI connectors. We'll leave the basic [hv]display/[hv]total checks in intel_mode_valid() as those seem like sensible upper limits regardless of the transcoder used. Cc: stable(a)vger.kernel.org Closes: https://gitlab.freedesktop.org/drm/intel/-/issues/9720 Fixes: 8f4b1068e7fc ("drm/i915: Check some transcoder timing minimum limits") Signed-off-by: Ville Syrjälä <ville.syrjala(a)linux.intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20231127145028.4899-1-ville.s… Reviewed-by: Jani Nikula <jani.nikula(a)intel.com> (cherry picked from commit e0ef2daa8ca8ce4dbc2fd0959e383b753a87fd7d) Signed-off-by: Jani Nikula <jani.nikula(a)intel.com> diff --git a/drivers/gpu/drm/i915/display/icl_dsi.c b/drivers/gpu/drm/i915/display/icl_dsi.c index c4585e445198..67143a0f5189 100644 --- a/drivers/gpu/drm/i915/display/icl_dsi.c +++ b/drivers/gpu/drm/i915/display/icl_dsi.c @@ -1440,6 +1440,13 @@ static void gen11_dsi_post_disable(struct intel_atomic_state *state, static enum drm_mode_status gen11_dsi_mode_valid(struct drm_connector *connector, struct drm_display_mode *mode) { + struct drm_i915_private *i915 = to_i915(connector->dev); + enum drm_mode_status status; + + status = intel_cpu_transcoder_mode_valid(i915, mode); + if (status != MODE_OK) + return status; + /* FIXME: DSC? */ return intel_dsi_mode_valid(connector, mode); } diff --git a/drivers/gpu/drm/i915/display/intel_crt.c b/drivers/gpu/drm/i915/display/intel_crt.c index 913e5d230a4d..6f6b348b8a40 100644 --- a/drivers/gpu/drm/i915/display/intel_crt.c +++ b/drivers/gpu/drm/i915/display/intel_crt.c @@ -348,8 +348,13 @@ intel_crt_mode_valid(struct drm_connector *connector, struct drm_device *dev = connector->dev; struct drm_i915_private *dev_priv = to_i915(dev); int max_dotclk = dev_priv->max_dotclk_freq; + enum drm_mode_status status; int max_clock; + status = intel_cpu_transcoder_mode_valid(dev_priv, mode); + if (status != MODE_OK) + return status; + if (mode->flags & DRM_MODE_FLAG_DBLSCAN) return MODE_NO_DBLESCAN; diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c index 94330108145e..4ee7d569b379 100644 --- a/drivers/gpu/drm/i915/display/intel_display.c +++ b/drivers/gpu/drm/i915/display/intel_display.c @@ -7869,6 +7869,16 @@ enum drm_mode_status intel_mode_valid(struct drm_device *dev, mode->vtotal > vtotal_max) return MODE_V_ILLEGAL; + return MODE_OK; +} + +enum drm_mode_status intel_cpu_transcoder_mode_valid(struct drm_i915_private *dev_priv, + const struct drm_display_mode *mode) +{ + /* + * Additional transcoder timing limits, + * excluding BXT/GLK DSI transcoders. + */ if (DISPLAY_VER(dev_priv) >= 5) { if (mode->hdisplay < 64 || mode->htotal - mode->hdisplay < 32) diff --git a/drivers/gpu/drm/i915/display/intel_display.h b/drivers/gpu/drm/i915/display/intel_display.h index 0e5dffe8f018..a05c7e2b782e 100644 --- a/drivers/gpu/drm/i915/display/intel_display.h +++ b/drivers/gpu/drm/i915/display/intel_display.h @@ -403,6 +403,9 @@ enum drm_mode_status intel_mode_valid_max_plane_size(struct drm_i915_private *dev_priv, const struct drm_display_mode *mode, bool bigjoiner); +enum drm_mode_status +intel_cpu_transcoder_mode_valid(struct drm_i915_private *i915, + const struct drm_display_mode *mode); enum phy intel_port_to_phy(struct drm_i915_private *i915, enum port port); bool is_trans_port_sync_mode(const struct intel_crtc_state *state); bool is_trans_port_sync_master(const struct intel_crtc_state *state); diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c index 2852958dd4e7..b21bcd40f111 100644 --- a/drivers/gpu/drm/i915/display/intel_dp.c +++ b/drivers/gpu/drm/i915/display/intel_dp.c @@ -1172,6 +1172,10 @@ intel_dp_mode_valid(struct drm_connector *_connector, enum drm_mode_status status; bool dsc = false, bigjoiner = false; + status = intel_cpu_transcoder_mode_valid(dev_priv, mode); + if (status != MODE_OK) + return status; + if (mode->flags & DRM_MODE_FLAG_DBLCLK) return MODE_H_ILLEGAL; diff --git a/drivers/gpu/drm/i915/display/intel_dp_mst.c b/drivers/gpu/drm/i915/display/intel_dp_mst.c index 851b312bd844..4816e4e77f83 100644 --- a/drivers/gpu/drm/i915/display/intel_dp_mst.c +++ b/drivers/gpu/drm/i915/display/intel_dp_mst.c @@ -959,6 +959,10 @@ intel_dp_mst_mode_valid_ctx(struct drm_connector *connector, return 0; } + *status = intel_cpu_transcoder_mode_valid(dev_priv, mode); + if (*status != MODE_OK) + return 0; + if (mode->flags & DRM_MODE_FLAG_DBLSCAN) { *status = MODE_NO_DBLESCAN; return 0; diff --git a/drivers/gpu/drm/i915/display/intel_dvo.c b/drivers/gpu/drm/i915/display/intel_dvo.c index 55d6743374bd..9111e9d46486 100644 --- a/drivers/gpu/drm/i915/display/intel_dvo.c +++ b/drivers/gpu/drm/i915/display/intel_dvo.c @@ -217,11 +217,17 @@ intel_dvo_mode_valid(struct drm_connector *_connector, struct drm_display_mode *mode) { struct intel_connector *connector = to_intel_connector(_connector); + struct drm_i915_private *i915 = to_i915(connector->base.dev); struct intel_dvo *intel_dvo = intel_attached_dvo(connector); const struct drm_display_mode *fixed_mode = intel_panel_fixed_mode(connector, mode); int max_dotclk = to_i915(connector->base.dev)->max_dotclk_freq; int target_clock = mode->clock; + enum drm_mode_status status; + + status = intel_cpu_transcoder_mode_valid(i915, mode); + if (status != MODE_OK) + return status; if (mode->flags & DRM_MODE_FLAG_DBLSCAN) return MODE_NO_DBLESCAN; diff --git a/drivers/gpu/drm/i915/display/intel_hdmi.c b/drivers/gpu/drm/i915/display/intel_hdmi.c index ac315f8e7820..bfa456fa7d25 100644 --- a/drivers/gpu/drm/i915/display/intel_hdmi.c +++ b/drivers/gpu/drm/i915/display/intel_hdmi.c @@ -1983,6 +1983,10 @@ intel_hdmi_mode_valid(struct drm_connector *connector, bool ycbcr_420_only; enum intel_output_format sink_format; + status = intel_cpu_transcoder_mode_valid(dev_priv, mode); + if (status != MODE_OK) + return status; + if ((mode->flags & DRM_MODE_FLAG_3D_MASK) == DRM_MODE_FLAG_3D_FRAME_PACKING) clock *= 2; diff --git a/drivers/gpu/drm/i915/display/intel_lvds.c b/drivers/gpu/drm/i915/display/intel_lvds.c index 2a4ca7e65775..bcbdd1984fd9 100644 --- a/drivers/gpu/drm/i915/display/intel_lvds.c +++ b/drivers/gpu/drm/i915/display/intel_lvds.c @@ -389,11 +389,16 @@ intel_lvds_mode_valid(struct drm_connector *_connector, struct drm_display_mode *mode) { struct intel_connector *connector = to_intel_connector(_connector); + struct drm_i915_private *i915 = to_i915(connector->base.dev); const struct drm_display_mode *fixed_mode = intel_panel_fixed_mode(connector, mode); int max_pixclk = to_i915(connector->base.dev)->max_dotclk_freq; enum drm_mode_status status; + status = intel_cpu_transcoder_mode_valid(i915, mode); + if (status != MODE_OK) + return status; + if (mode->flags & DRM_MODE_FLAG_DBLSCAN) return MODE_NO_DBLESCAN; diff --git a/drivers/gpu/drm/i915/display/intel_sdvo.c b/drivers/gpu/drm/i915/display/intel_sdvo.c index a636f42ceae5..a9ac7d45d1f3 100644 --- a/drivers/gpu/drm/i915/display/intel_sdvo.c +++ b/drivers/gpu/drm/i915/display/intel_sdvo.c @@ -1921,13 +1921,19 @@ static enum drm_mode_status intel_sdvo_mode_valid(struct drm_connector *connector, struct drm_display_mode *mode) { + struct drm_i915_private *i915 = to_i915(connector->dev); struct intel_sdvo *intel_sdvo = intel_attached_sdvo(to_intel_connector(connector)); struct intel_sdvo_connector *intel_sdvo_connector = to_intel_sdvo_connector(connector); - int max_dotclk = to_i915(connector->dev)->max_dotclk_freq; bool has_hdmi_sink = intel_has_hdmi_sink(intel_sdvo_connector, connector->state); + int max_dotclk = i915->max_dotclk_freq; + enum drm_mode_status status; int clock = mode->clock; + status = intel_cpu_transcoder_mode_valid(i915, mode); + if (status != MODE_OK) + return status; + if (mode->flags & DRM_MODE_FLAG_DBLSCAN) return MODE_NO_DBLESCAN; diff --git a/drivers/gpu/drm/i915/display/intel_tv.c b/drivers/gpu/drm/i915/display/intel_tv.c index 31a79fdfc812..2ee4f0d95851 100644 --- a/drivers/gpu/drm/i915/display/intel_tv.c +++ b/drivers/gpu/drm/i915/display/intel_tv.c @@ -958,8 +958,14 @@ static enum drm_mode_status intel_tv_mode_valid(struct drm_connector *connector, struct drm_display_mode *mode) { + struct drm_i915_private *i915 = to_i915(connector->dev); const struct tv_mode *tv_mode = intel_tv_mode_find(connector->state); - int max_dotclk = to_i915(connector->dev)->max_dotclk_freq; + int max_dotclk = i915->max_dotclk_freq; + enum drm_mode_status status; + + status = intel_cpu_transcoder_mode_valid(i915, mode); + if (status != MODE_OK) + return status; if (mode->flags & DRM_MODE_FLAG_DBLSCAN) return MODE_NO_DBLESCAN; diff --git a/drivers/gpu/drm/i915/display/vlv_dsi.c b/drivers/gpu/drm/i915/display/vlv_dsi.c index 55da627a8b8d..f488394d3108 100644 --- a/drivers/gpu/drm/i915/display/vlv_dsi.c +++ b/drivers/gpu/drm/i915/display/vlv_dsi.c @@ -1541,9 +1541,25 @@ static const struct drm_encoder_funcs intel_dsi_funcs = { .destroy = intel_dsi_encoder_destroy, }; +static enum drm_mode_status vlv_dsi_mode_valid(struct drm_connector *connector, + struct drm_display_mode *mode) +{ + struct drm_i915_private *i915 = to_i915(connector->dev); + + if (IS_VALLEYVIEW(i915) || IS_CHERRYVIEW(i915)) { + enum drm_mode_status status; + + status = intel_cpu_transcoder_mode_valid(i915, mode); + if (status != MODE_OK) + return status; + } + + return intel_dsi_mode_valid(connector, mode); +} + static const struct drm_connector_helper_funcs intel_dsi_connector_helper_funcs = { .get_modes = intel_dsi_get_modes, - .mode_valid = intel_dsi_mode_valid, + .mode_valid = vlv_dsi_mode_valid, .atomic_check = intel_digital_connector_atomic_check, };

1 year, 6 months

1
0
0 0

FAILED: patch "[PATCH] drm/amdgpu: Restrict extended wait to PSP v13.0.6" failed to apply to 6.6-stable tree

by gregkh＠linuxfoundation.org

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>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.6.y git checkout FETCH_HEAD git cherry-pick -x 6fce23a4d8c5f93bf80b7f122449fbb97f1e40dd # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023120932-suffocate-neuter-c5d7@gregkh' --subject-prefix 'PATCH 6.6.y' HEAD^.. Possible dependencies: 6fce23a4d8c5 ("drm/amdgpu: Restrict extended wait to PSP v13.0.6") d8c1925ba8cd ("drm/amdgpu: update retry times for psp BL wait") fc5988907156 ("drm/amdgpu: update retry times for psp vmbx wait") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 6fce23a4d8c5f93bf80b7f122449fbb97f1e40dd Mon Sep 17 00:00:00 2001 From: Lijo Lazar <lijo.lazar(a)amd.com> Date: Wed, 29 Nov 2023 18:06:55 +0530 Subject: [PATCH] drm/amdgpu: Restrict extended wait to PSP v13.0.6 Only PSPv13.0.6 SOCs take a longer time to reach steady state. Other PSPv13 based SOCs don't need extended wait. Also, reduce PSPv13.0.6 wait time. Cc: stable(a)vger.kernel.org Fixes: fc5988907156 ("drm/amdgpu: update retry times for psp vmbx wait") Fixes: d8c1925ba8cd ("drm/amdgpu: update retry times for psp BL wait") Link: https://lore.kernel.org/amd-gfx/34dd4c66-f7bf-44aa-af8f-c82889dd652c@amd.co… Signed-off-by: Lijo Lazar <lijo.lazar(a)amd.com> Reviewed-by: Asad Kamal <asad.kamal(a)amd.com> Reviewed-by: Mario Limonciello <mario.limonciello(a)amd.com> Signed-off-by: Alex Deucher <alexander.deucher(a)amd.com> diff --git a/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c b/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c index 5f46877f78cf..df1844d0800f 100644 --- a/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c +++ b/drivers/gpu/drm/amd/amdgpu/psp_v13_0.c @@ -60,7 +60,7 @@ MODULE_FIRMWARE("amdgpu/psp_14_0_0_ta.bin"); #define GFX_CMD_USB_PD_USE_LFB 0x480 /* Retry times for vmbx ready wait */ -#define PSP_VMBX_POLLING_LIMIT 20000 +#define PSP_VMBX_POLLING_LIMIT 3000 /* VBIOS gfl defines */ #define MBOX_READY_MASK 0x80000000 @@ -161,14 +161,18 @@ static int psp_v13_0_wait_for_vmbx_ready(struct psp_context *psp) static int psp_v13_0_wait_for_bootloader(struct psp_context *psp) { struct amdgpu_device *adev = psp->adev; - int retry_loop, ret; + int retry_loop, retry_cnt, ret; + retry_cnt = + (amdgpu_ip_version(adev, MP0_HWIP, 0) == IP_VERSION(13, 0, 6)) ? + PSP_VMBX_POLLING_LIMIT : + 10; /* Wait for bootloader to signify that it is ready having bit 31 of * C2PMSG_35 set to 1. All other bits are expected to be cleared. * If there is an error in processing command, bits[7:0] will be set. * This is applicable for PSP v13.0.6 and newer. */ - for (retry_loop = 0; retry_loop < PSP_VMBX_POLLING_LIMIT; retry_loop++) { + for (retry_loop = 0; retry_loop < retry_cnt; retry_loop++) { ret = psp_wait_for( psp, SOC15_REG_OFFSET(MP0, 0, regMP0_SMN_C2PMSG_35), 0x80000000, 0xffffffff, false);

1 year, 6 months

1
0
0 0

FAILED: patch "[PATCH] mm/memory_hotplug: fix error handling in" failed to apply to 6.1-stable tree

by gregkh＠linuxfoundation.org

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>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.1.y git checkout FETCH_HEAD git cherry-pick -x f42ce5f087eb69e47294ababd2e7e6f88a82d308 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023120918-qualify-refutable-6c2a@gregkh' --subject-prefix 'PATCH 6.1.y' HEAD^.. Possible dependencies: f42ce5f087eb ("mm/memory_hotplug: fix error handling in add_memory_resource()") 1a8c64e11043 ("mm/memory_hotplug: embed vmem_altmap details in memory block") 2d1f649c7c08 ("mm/memory_hotplug: support memmap_on_memory when memmap is not aligned to pageblocks") 85a2b4b08f20 ("mm/memory_hotplug: allow architecture to override memmap on memory support check") e3c2bfdd33a3 ("mm/memory_hotplug: allow memmap on memory hotplug request to fallback") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From f42ce5f087eb69e47294ababd2e7e6f88a82d308 Mon Sep 17 00:00:00 2001 From: Sumanth Korikkar <sumanthk(a)linux.ibm.com> Date: Mon, 20 Nov 2023 15:53:53 +0100 Subject: [PATCH] mm/memory_hotplug: fix error handling in add_memory_resource() In add_memory_resource(), creation of memory block devices occurs after successful call to arch_add_memory(). However, creation of memory block devices could fail. In that case, arch_remove_memory() is called to perform necessary cleanup. Currently with or without altmap support, arch_remove_memory() is always passed with altmap set to NULL during error handling. This leads to freeing of struct pages using free_pages(), eventhough the allocation might have been performed with altmap support via altmap_alloc_block_buf(). Fix the error handling by passing altmap in arch_remove_memory(). This ensures the following: * When altmap is disabled, deallocation of the struct pages array occurs via free_pages(). * When altmap is enabled, deallocation occurs via vmem_altmap_free(). Link: https://lkml.kernel.org/r/20231120145354.308999-3-sumanthk@linux.ibm.com Fixes: a08a2ae34613 ("mm,memory_hotplug: allocate memmap from the added memory range") Signed-off-by: Sumanth Korikkar <sumanthk(a)linux.ibm.com> Reviewed-by: Gerald Schaefer <gerald.schaefer(a)linux.ibm.com> Acked-by: David Hildenbrand <david(a)redhat.com> Cc: Alexander Gordeev <agordeev(a)linux.ibm.com> Cc: Aneesh Kumar K.V <aneesh.kumar(a)linux.ibm.com> Cc: Anshuman Khandual <anshuman.khandual(a)arm.com> Cc: Heiko Carstens <hca(a)linux.ibm.com> Cc: kernel test robot <lkp(a)intel.com> Cc: Michal Hocko <mhocko(a)suse.com> Cc: Oscar Salvador <osalvador(a)suse.de> Cc: Vasily Gorbik <gor(a)linux.ibm.com> Cc: <stable(a)vger.kernel.org> [5.15+] Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index bb908289679e..7a5fc89a8652 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1458,7 +1458,7 @@ int __ref add_memory_resource(int nid, struct resource *res, mhp_t mhp_flags) /* create memory block devices after memory was added */ ret = create_memory_block_devices(start, size, params.altmap, group); if (ret) { - arch_remove_memory(start, size, NULL); + arch_remove_memory(start, size, params.altmap); goto error_free; }

1 year, 6 months

1
0
0 0

FAILED: patch "[PATCH] mm/memory_hotplug: fix error handling in" failed to apply to 5.10-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.10-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>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.10.y git checkout FETCH_HEAD git cherry-pick -x f42ce5f087eb69e47294ababd2e7e6f88a82d308 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023120907-trophy-subdivide-10be@gregkh' --subject-prefix 'PATCH 5.10.y' HEAD^.. Possible dependencies: f42ce5f087eb ("mm/memory_hotplug: fix error handling in add_memory_resource()") 1a8c64e11043 ("mm/memory_hotplug: embed vmem_altmap details in memory block") 2d1f649c7c08 ("mm/memory_hotplug: support memmap_on_memory when memmap is not aligned to pageblocks") 85a2b4b08f20 ("mm/memory_hotplug: allow architecture to override memmap on memory support check") e3c2bfdd33a3 ("mm/memory_hotplug: allow memmap on memory hotplug request to fallback") 66361095129b ("mm: memory_hotplug: make hugetlb_optimize_vmemmap compatible with memmap_on_memory") 78f39084b41d ("mm: hugetlb_vmemmap: add hugetlb_optimize_vmemmap sysctl") 9c54c522bb76 ("mm: hugetlb_vmemmap: use kstrtobool for hugetlb_vmemmap param parsing") 6e02c46b4d97 ("mm: memory_hotplug: override memmap_on_memory when hugetlb_free_vmemmap=on") 0effdf461c57 ("mm: hugetlb_vmemmap: disable hugetlb_optimize_vmemmap when struct page crosses page boundaries") 47010c040dec ("mm: hugetlb_vmemmap: cleanup CONFIG_HUGETLB_PAGE_FREE_VMEMMAP*") f10f1442c309 ("mm: hugetlb_vmemmap: cleanup hugetlb_free_vmemmap_enabled*") 5981611d0a00 ("mm: hugetlb_vmemmap: cleanup hugetlb_vmemmap related functions") 1e63ac088f20 ("arm64: mm: hugetlb: enable HUGETLB_PAGE_FREE_VMEMMAP for arm64") 2e4ec02bbcc0 ("mm: hugetlb_vmemmap: introduce ARCH_WANT_HUGETLB_PAGE_FREE_VMEMMAP") 2aa065f7afb2 ("drivers/base/memory: clarify adding and removing of memory blocks") 395f6081bad4 ("drivers/base/memory: determine and store zone for single-zone memory blocks") 7ea0d2d79da0 ("drivers/base/memory: add memory block to memory group after registration succeeded") e54084173487 ("mm: sparsemem: move vmemmap related to HugeTLB to CONFIG_HUGETLB_PAGE_FREE_VMEMMAP") a6b40850c442 ("mm: hugetlb: replace hugetlb_free_vmemmap_enabled with a static_key") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From f42ce5f087eb69e47294ababd2e7e6f88a82d308 Mon Sep 17 00:00:00 2001 From: Sumanth Korikkar <sumanthk(a)linux.ibm.com> Date: Mon, 20 Nov 2023 15:53:53 +0100 Subject: [PATCH] mm/memory_hotplug: fix error handling in add_memory_resource() In add_memory_resource(), creation of memory block devices occurs after successful call to arch_add_memory(). However, creation of memory block devices could fail. In that case, arch_remove_memory() is called to perform necessary cleanup. Currently with or without altmap support, arch_remove_memory() is always passed with altmap set to NULL during error handling. This leads to freeing of struct pages using free_pages(), eventhough the allocation might have been performed with altmap support via altmap_alloc_block_buf(). Fix the error handling by passing altmap in arch_remove_memory(). This ensures the following: * When altmap is disabled, deallocation of the struct pages array occurs via free_pages(). * When altmap is enabled, deallocation occurs via vmem_altmap_free(). Link: https://lkml.kernel.org/r/20231120145354.308999-3-sumanthk@linux.ibm.com Fixes: a08a2ae34613 ("mm,memory_hotplug: allocate memmap from the added memory range") Signed-off-by: Sumanth Korikkar <sumanthk(a)linux.ibm.com> Reviewed-by: Gerald Schaefer <gerald.schaefer(a)linux.ibm.com> Acked-by: David Hildenbrand <david(a)redhat.com> Cc: Alexander Gordeev <agordeev(a)linux.ibm.com> Cc: Aneesh Kumar K.V <aneesh.kumar(a)linux.ibm.com> Cc: Anshuman Khandual <anshuman.khandual(a)arm.com> Cc: Heiko Carstens <hca(a)linux.ibm.com> Cc: kernel test robot <lkp(a)intel.com> Cc: Michal Hocko <mhocko(a)suse.com> Cc: Oscar Salvador <osalvador(a)suse.de> Cc: Vasily Gorbik <gor(a)linux.ibm.com> Cc: <stable(a)vger.kernel.org> [5.15+] Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index bb908289679e..7a5fc89a8652 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1458,7 +1458,7 @@ int __ref add_memory_resource(int nid, struct resource *res, mhp_t mhp_flags) /* create memory block devices after memory was added */ ret = create_memory_block_devices(start, size, params.altmap, group); if (ret) { - arch_remove_memory(start, size, NULL); + arch_remove_memory(start, size, params.altmap); goto error_free; }

1 year, 6 months

1
0
0 0

FAILED: patch "[PATCH] mm/memory_hotplug: fix error handling in" failed to apply to 5.15-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.15-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>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.15.y git checkout FETCH_HEAD git cherry-pick -x f42ce5f087eb69e47294ababd2e7e6f88a82d308 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023120904-duffel-joining-636f@gregkh' --subject-prefix 'PATCH 5.15.y' HEAD^.. Possible dependencies: f42ce5f087eb ("mm/memory_hotplug: fix error handling in add_memory_resource()") 1a8c64e11043 ("mm/memory_hotplug: embed vmem_altmap details in memory block") 2d1f649c7c08 ("mm/memory_hotplug: support memmap_on_memory when memmap is not aligned to pageblocks") 85a2b4b08f20 ("mm/memory_hotplug: allow architecture to override memmap on memory support check") e3c2bfdd33a3 ("mm/memory_hotplug: allow memmap on memory hotplug request to fallback") 66361095129b ("mm: memory_hotplug: make hugetlb_optimize_vmemmap compatible with memmap_on_memory") 78f39084b41d ("mm: hugetlb_vmemmap: add hugetlb_optimize_vmemmap sysctl") 9c54c522bb76 ("mm: hugetlb_vmemmap: use kstrtobool for hugetlb_vmemmap param parsing") 6e02c46b4d97 ("mm: memory_hotplug: override memmap_on_memory when hugetlb_free_vmemmap=on") 0effdf461c57 ("mm: hugetlb_vmemmap: disable hugetlb_optimize_vmemmap when struct page crosses page boundaries") 47010c040dec ("mm: hugetlb_vmemmap: cleanup CONFIG_HUGETLB_PAGE_FREE_VMEMMAP*") f10f1442c309 ("mm: hugetlb_vmemmap: cleanup hugetlb_free_vmemmap_enabled*") 5981611d0a00 ("mm: hugetlb_vmemmap: cleanup hugetlb_vmemmap related functions") 1e63ac088f20 ("arm64: mm: hugetlb: enable HUGETLB_PAGE_FREE_VMEMMAP for arm64") 2e4ec02bbcc0 ("mm: hugetlb_vmemmap: introduce ARCH_WANT_HUGETLB_PAGE_FREE_VMEMMAP") 2aa065f7afb2 ("drivers/base/memory: clarify adding and removing of memory blocks") 395f6081bad4 ("drivers/base/memory: determine and store zone for single-zone memory blocks") 7ea0d2d79da0 ("drivers/base/memory: add memory block to memory group after registration succeeded") e54084173487 ("mm: sparsemem: move vmemmap related to HugeTLB to CONFIG_HUGETLB_PAGE_FREE_VMEMMAP") a6b40850c442 ("mm: hugetlb: replace hugetlb_free_vmemmap_enabled with a static_key") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From f42ce5f087eb69e47294ababd2e7e6f88a82d308 Mon Sep 17 00:00:00 2001 From: Sumanth Korikkar <sumanthk(a)linux.ibm.com> Date: Mon, 20 Nov 2023 15:53:53 +0100 Subject: [PATCH] mm/memory_hotplug: fix error handling in add_memory_resource() In add_memory_resource(), creation of memory block devices occurs after successful call to arch_add_memory(). However, creation of memory block devices could fail. In that case, arch_remove_memory() is called to perform necessary cleanup. Currently with or without altmap support, arch_remove_memory() is always passed with altmap set to NULL during error handling. This leads to freeing of struct pages using free_pages(), eventhough the allocation might have been performed with altmap support via altmap_alloc_block_buf(). Fix the error handling by passing altmap in arch_remove_memory(). This ensures the following: * When altmap is disabled, deallocation of the struct pages array occurs via free_pages(). * When altmap is enabled, deallocation occurs via vmem_altmap_free(). Link: https://lkml.kernel.org/r/20231120145354.308999-3-sumanthk@linux.ibm.com Fixes: a08a2ae34613 ("mm,memory_hotplug: allocate memmap from the added memory range") Signed-off-by: Sumanth Korikkar <sumanthk(a)linux.ibm.com> Reviewed-by: Gerald Schaefer <gerald.schaefer(a)linux.ibm.com> Acked-by: David Hildenbrand <david(a)redhat.com> Cc: Alexander Gordeev <agordeev(a)linux.ibm.com> Cc: Aneesh Kumar K.V <aneesh.kumar(a)linux.ibm.com> Cc: Anshuman Khandual <anshuman.khandual(a)arm.com> Cc: Heiko Carstens <hca(a)linux.ibm.com> Cc: kernel test robot <lkp(a)intel.com> Cc: Michal Hocko <mhocko(a)suse.com> Cc: Oscar Salvador <osalvador(a)suse.de> Cc: Vasily Gorbik <gor(a)linux.ibm.com> Cc: <stable(a)vger.kernel.org> [5.15+] Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index bb908289679e..7a5fc89a8652 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1458,7 +1458,7 @@ int __ref add_memory_resource(int nid, struct resource *res, mhp_t mhp_flags) /* create memory block devices after memory was added */ ret = create_memory_block_devices(start, size, params.altmap, group); if (ret) { - arch_remove_memory(start, size, NULL); + arch_remove_memory(start, size, params.altmap); goto error_free; }

1 year, 6 months

1
0
0 0

FAILED: patch "[PATCH] mm/memory_hotplug: add missing mem_hotplug_lock" failed to apply to 5.15-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.15-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>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.15.y git checkout FETCH_HEAD git cherry-pick -x 001002e73712cdf6b8d9a103648cda3040ad7647 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023120927-immobile-half-41d8@gregkh' --subject-prefix 'PATCH 5.15.y' HEAD^.. Possible dependencies: 001002e73712 ("mm/memory_hotplug: add missing mem_hotplug_lock") 1a8c64e11043 ("mm/memory_hotplug: embed vmem_altmap details in memory block") 2d1f649c7c08 ("mm/memory_hotplug: support memmap_on_memory when memmap is not aligned to pageblocks") 85a2b4b08f20 ("mm/memory_hotplug: allow architecture to override memmap on memory support check") e3c2bfdd33a3 ("mm/memory_hotplug: allow memmap on memory hotplug request to fallback") 5033091de814 ("mm/hwpoison: introduce per-memory_block hwpoison counter") a46c9304b4bb ("mm/hwpoison: pass pfn to num_poisoned_pages_*()") d027122d8363 ("mm/hwpoison: move definitions of num_poisoned_pages_* to memory-failure.c") e591ef7d96d6 ("mm,hwpoison,hugetlb,memory_hotplug: hotremove memory section with hwpoisoned hugepage") 0d206b5d2e0d ("mm/swap: add swp_offset_pfn() to fetch PFN from swap entry") eba4d770efc8 ("mm/swap: comment all the ifdef in swapops.h") 21c9e90ab9a4 ("mm, hwpoison: use num_poisoned_pages_sub() to decrease num_poisoned_pages") f36a5543a748 ("mm, hwpoison: fix page refcnt leaking in try_memory_failure_hugetlb()") 7453bf621cfa ("mm, hwpoison: make __page_handle_poison returns int") 38f6d29397cc ("mm, hwpoison: set PG_hwpoison for busy hugetlb pages") ac5fcde0a96a ("mm, hwpoison: make unpoison aware of raw error info in hwpoisoned hugepage") 161df60e9e89 ("mm, hwpoison, hugetlb: support saving mechanism of raw error pages") 6213834c10de ("mm: hugetlb_vmemmap: improve hugetlb_vmemmap code readability") 998a2997885f ("mm: hugetlb_vmemmap: move vmemmap code related to HugeTLB to hugetlb_vmemmap.c") dff033818a06 ("mm: hugetlb_vmemmap: introduce the name HVO") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 001002e73712cdf6b8d9a103648cda3040ad7647 Mon Sep 17 00:00:00 2001 From: Sumanth Korikkar <sumanthk(a)linux.ibm.com> Date: Mon, 20 Nov 2023 15:53:52 +0100 Subject: [PATCH] mm/memory_hotplug: add missing mem_hotplug_lock From Documentation/core-api/memory-hotplug.rst: When adding/removing/onlining/offlining memory or adding/removing heterogeneous/device memory, we should always hold the mem_hotplug_lock in write mode to serialise memory hotplug (e.g. access to global/zone variables). mhp_(de)init_memmap_on_memory() functions can change zone stats and struct page content, but they are currently called w/o the mem_hotplug_lock. When memory block is being offlined and when kmemleak goes through each populated zone, the following theoretical race conditions could occur: CPU 0: | CPU 1: memory_offline() | -> offline_pages() | -> mem_hotplug_begin() | ... | -> mem_hotplug_done() | | kmemleak_scan() | -> get_online_mems() | ... -> mhp_deinit_memmap_on_memory() | [not protected by mem_hotplug_begin/done()]| Marks memory section as offline, | Retrieves zone_start_pfn poisons vmemmap struct pages and updates | and struct page members. the zone related data | | ... | -> put_online_mems() Fix this by ensuring mem_hotplug_lock is taken before performing mhp_init_memmap_on_memory(). Also ensure that mhp_deinit_memmap_on_memory() holds the lock. online/offline_pages() are currently only called from memory_block_online/offline(), so it is safe to move the locking there. Link: https://lkml.kernel.org/r/20231120145354.308999-2-sumanthk@linux.ibm.com Fixes: a08a2ae34613 ("mm,memory_hotplug: allocate memmap from the added memory range") Signed-off-by: Sumanth Korikkar <sumanthk(a)linux.ibm.com> Reviewed-by: Gerald Schaefer <gerald.schaefer(a)linux.ibm.com> Acked-by: David Hildenbrand <david(a)redhat.com> Cc: Alexander Gordeev <agordeev(a)linux.ibm.com> Cc: Aneesh Kumar K.V <aneesh.kumar(a)linux.ibm.com> Cc: Anshuman Khandual <anshuman.khandual(a)arm.com> Cc: Heiko Carstens <hca(a)linux.ibm.com> Cc: Michal Hocko <mhocko(a)suse.com> Cc: Oscar Salvador <osalvador(a)suse.de> Cc: Vasily Gorbik <gor(a)linux.ibm.com> Cc: kernel test robot <lkp(a)intel.com> Cc: <stable(a)vger.kernel.org> [5.15+] Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> diff --git a/drivers/base/memory.c b/drivers/base/memory.c index f3b9a4d0fa3b..8a13babd826c 100644 --- a/drivers/base/memory.c +++ b/drivers/base/memory.c @@ -180,6 +180,9 @@ static inline unsigned long memblk_nr_poison(struct memory_block *mem) } #endif +/* + * Must acquire mem_hotplug_lock in write mode. + */ static int memory_block_online(struct memory_block *mem) { unsigned long start_pfn = section_nr_to_pfn(mem->start_section_nr); @@ -204,10 +207,11 @@ static int memory_block_online(struct memory_block *mem) if (mem->altmap) nr_vmemmap_pages = mem->altmap->free; + mem_hotplug_begin(); if (nr_vmemmap_pages) { ret = mhp_init_memmap_on_memory(start_pfn, nr_vmemmap_pages, zone); if (ret) - return ret; + goto out; } ret = online_pages(start_pfn + nr_vmemmap_pages, @@ -215,7 +219,7 @@ static int memory_block_online(struct memory_block *mem) if (ret) { if (nr_vmemmap_pages) mhp_deinit_memmap_on_memory(start_pfn, nr_vmemmap_pages); - return ret; + goto out; } /* @@ -227,9 +231,14 @@ static int memory_block_online(struct memory_block *mem) nr_vmemmap_pages); mem->zone = zone; +out: + mem_hotplug_done(); return ret; } +/* + * Must acquire mem_hotplug_lock in write mode. + */ static int memory_block_offline(struct memory_block *mem) { unsigned long start_pfn = section_nr_to_pfn(mem->start_section_nr); @@ -247,6 +256,7 @@ static int memory_block_offline(struct memory_block *mem) if (mem->altmap) nr_vmemmap_pages = mem->altmap->free; + mem_hotplug_begin(); if (nr_vmemmap_pages) adjust_present_page_count(pfn_to_page(start_pfn), mem->group, -nr_vmemmap_pages); @@ -258,13 +268,15 @@ static int memory_block_offline(struct memory_block *mem) if (nr_vmemmap_pages) adjust_present_page_count(pfn_to_page(start_pfn), mem->group, nr_vmemmap_pages); - return ret; + goto out; } if (nr_vmemmap_pages) mhp_deinit_memmap_on_memory(start_pfn, nr_vmemmap_pages); mem->zone = NULL; +out: + mem_hotplug_done(); return ret; } diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index ab41a511e20a..bb908289679e 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1129,6 +1129,9 @@ void mhp_deinit_memmap_on_memory(unsigned long pfn, unsigned long nr_pages) kasan_remove_zero_shadow(__va(PFN_PHYS(pfn)), PFN_PHYS(nr_pages)); } +/* + * Must be called with mem_hotplug_lock in write mode. + */ int __ref online_pages(unsigned long pfn, unsigned long nr_pages, struct zone *zone, struct memory_group *group) { @@ -1149,7 +1152,6 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages, !IS_ALIGNED(pfn + nr_pages, PAGES_PER_SECTION))) return -EINVAL; - mem_hotplug_begin(); /* associate pfn range with the zone */ move_pfn_range_to_zone(zone, pfn, nr_pages, NULL, MIGRATE_ISOLATE); @@ -1208,7 +1210,6 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages, writeback_set_ratelimit(); memory_notify(MEM_ONLINE, &arg); - mem_hotplug_done(); return 0; failed_addition: @@ -1217,7 +1218,6 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages, (((unsigned long long) pfn + nr_pages) << PAGE_SHIFT) - 1); memory_notify(MEM_CANCEL_ONLINE, &arg); remove_pfn_range_from_zone(zone, pfn, nr_pages); - mem_hotplug_done(); return ret; } @@ -1863,6 +1863,9 @@ static int count_system_ram_pages_cb(unsigned long start_pfn, return 0; } +/* + * Must be called with mem_hotplug_lock in write mode. + */ int __ref offline_pages(unsigned long start_pfn, unsigned long nr_pages, struct zone *zone, struct memory_group *group) { @@ -1885,8 +1888,6 @@ int __ref offline_pages(unsigned long start_pfn, unsigned long nr_pages, !IS_ALIGNED(start_pfn + nr_pages, PAGES_PER_SECTION))) return -EINVAL; - mem_hotplug_begin(); - /* * Don't allow to offline memory blocks that contain holes. * Consequently, memory blocks with holes can never get onlined @@ -2031,7 +2032,6 @@ int __ref offline_pages(unsigned long start_pfn, unsigned long nr_pages, memory_notify(MEM_OFFLINE, &arg); remove_pfn_range_from_zone(zone, start_pfn, nr_pages); - mem_hotplug_done(); return 0; failed_removal_isolated: @@ -2046,7 +2046,6 @@ int __ref offline_pages(unsigned long start_pfn, unsigned long nr_pages, (unsigned long long) start_pfn << PAGE_SHIFT, ((unsigned long long) end_pfn << PAGE_SHIFT) - 1, reason); - mem_hotplug_done(); return ret; }

1 year, 6 months

1
0
0 0

FAILED: patch "[PATCH] mm/memory_hotplug: add missing mem_hotplug_lock" failed to apply to 6.1-stable tree

by gregkh＠linuxfoundation.org

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>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.1.y git checkout FETCH_HEAD git cherry-pick -x 001002e73712cdf6b8d9a103648cda3040ad7647 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023120925-hazard-mustard-8df5@gregkh' --subject-prefix 'PATCH 6.1.y' HEAD^.. Possible dependencies: 001002e73712 ("mm/memory_hotplug: add missing mem_hotplug_lock") 1a8c64e11043 ("mm/memory_hotplug: embed vmem_altmap details in memory block") 2d1f649c7c08 ("mm/memory_hotplug: support memmap_on_memory when memmap is not aligned to pageblocks") 85a2b4b08f20 ("mm/memory_hotplug: allow architecture to override memmap on memory support check") e3c2bfdd33a3 ("mm/memory_hotplug: allow memmap on memory hotplug request to fallback") 5033091de814 ("mm/hwpoison: introduce per-memory_block hwpoison counter") a46c9304b4bb ("mm/hwpoison: pass pfn to num_poisoned_pages_*()") d027122d8363 ("mm/hwpoison: move definitions of num_poisoned_pages_* to memory-failure.c") e591ef7d96d6 ("mm,hwpoison,hugetlb,memory_hotplug: hotremove memory section with hwpoisoned hugepage") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 001002e73712cdf6b8d9a103648cda3040ad7647 Mon Sep 17 00:00:00 2001 From: Sumanth Korikkar <sumanthk(a)linux.ibm.com> Date: Mon, 20 Nov 2023 15:53:52 +0100 Subject: [PATCH] mm/memory_hotplug: add missing mem_hotplug_lock From Documentation/core-api/memory-hotplug.rst: When adding/removing/onlining/offlining memory or adding/removing heterogeneous/device memory, we should always hold the mem_hotplug_lock in write mode to serialise memory hotplug (e.g. access to global/zone variables). mhp_(de)init_memmap_on_memory() functions can change zone stats and struct page content, but they are currently called w/o the mem_hotplug_lock. When memory block is being offlined and when kmemleak goes through each populated zone, the following theoretical race conditions could occur: CPU 0: | CPU 1: memory_offline() | -> offline_pages() | -> mem_hotplug_begin() | ... | -> mem_hotplug_done() | | kmemleak_scan() | -> get_online_mems() | ... -> mhp_deinit_memmap_on_memory() | [not protected by mem_hotplug_begin/done()]| Marks memory section as offline, | Retrieves zone_start_pfn poisons vmemmap struct pages and updates | and struct page members. the zone related data | | ... | -> put_online_mems() Fix this by ensuring mem_hotplug_lock is taken before performing mhp_init_memmap_on_memory(). Also ensure that mhp_deinit_memmap_on_memory() holds the lock. online/offline_pages() are currently only called from memory_block_online/offline(), so it is safe to move the locking there. Link: https://lkml.kernel.org/r/20231120145354.308999-2-sumanthk@linux.ibm.com Fixes: a08a2ae34613 ("mm,memory_hotplug: allocate memmap from the added memory range") Signed-off-by: Sumanth Korikkar <sumanthk(a)linux.ibm.com> Reviewed-by: Gerald Schaefer <gerald.schaefer(a)linux.ibm.com> Acked-by: David Hildenbrand <david(a)redhat.com> Cc: Alexander Gordeev <agordeev(a)linux.ibm.com> Cc: Aneesh Kumar K.V <aneesh.kumar(a)linux.ibm.com> Cc: Anshuman Khandual <anshuman.khandual(a)arm.com> Cc: Heiko Carstens <hca(a)linux.ibm.com> Cc: Michal Hocko <mhocko(a)suse.com> Cc: Oscar Salvador <osalvador(a)suse.de> Cc: Vasily Gorbik <gor(a)linux.ibm.com> Cc: kernel test robot <lkp(a)intel.com> Cc: <stable(a)vger.kernel.org> [5.15+] Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org> diff --git a/drivers/base/memory.c b/drivers/base/memory.c index f3b9a4d0fa3b..8a13babd826c 100644 --- a/drivers/base/memory.c +++ b/drivers/base/memory.c @@ -180,6 +180,9 @@ static inline unsigned long memblk_nr_poison(struct memory_block *mem) } #endif +/* + * Must acquire mem_hotplug_lock in write mode. + */ static int memory_block_online(struct memory_block *mem) { unsigned long start_pfn = section_nr_to_pfn(mem->start_section_nr); @@ -204,10 +207,11 @@ static int memory_block_online(struct memory_block *mem) if (mem->altmap) nr_vmemmap_pages = mem->altmap->free; + mem_hotplug_begin(); if (nr_vmemmap_pages) { ret = mhp_init_memmap_on_memory(start_pfn, nr_vmemmap_pages, zone); if (ret) - return ret; + goto out; } ret = online_pages(start_pfn + nr_vmemmap_pages, @@ -215,7 +219,7 @@ static int memory_block_online(struct memory_block *mem) if (ret) { if (nr_vmemmap_pages) mhp_deinit_memmap_on_memory(start_pfn, nr_vmemmap_pages); - return ret; + goto out; } /* @@ -227,9 +231,14 @@ static int memory_block_online(struct memory_block *mem) nr_vmemmap_pages); mem->zone = zone; +out: + mem_hotplug_done(); return ret; } +/* + * Must acquire mem_hotplug_lock in write mode. + */ static int memory_block_offline(struct memory_block *mem) { unsigned long start_pfn = section_nr_to_pfn(mem->start_section_nr); @@ -247,6 +256,7 @@ static int memory_block_offline(struct memory_block *mem) if (mem->altmap) nr_vmemmap_pages = mem->altmap->free; + mem_hotplug_begin(); if (nr_vmemmap_pages) adjust_present_page_count(pfn_to_page(start_pfn), mem->group, -nr_vmemmap_pages); @@ -258,13 +268,15 @@ static int memory_block_offline(struct memory_block *mem) if (nr_vmemmap_pages) adjust_present_page_count(pfn_to_page(start_pfn), mem->group, nr_vmemmap_pages); - return ret; + goto out; } if (nr_vmemmap_pages) mhp_deinit_memmap_on_memory(start_pfn, nr_vmemmap_pages); mem->zone = NULL; +out: + mem_hotplug_done(); return ret; } diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index ab41a511e20a..bb908289679e 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -1129,6 +1129,9 @@ void mhp_deinit_memmap_on_memory(unsigned long pfn, unsigned long nr_pages) kasan_remove_zero_shadow(__va(PFN_PHYS(pfn)), PFN_PHYS(nr_pages)); } +/* + * Must be called with mem_hotplug_lock in write mode. + */ int __ref online_pages(unsigned long pfn, unsigned long nr_pages, struct zone *zone, struct memory_group *group) { @@ -1149,7 +1152,6 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages, !IS_ALIGNED(pfn + nr_pages, PAGES_PER_SECTION))) return -EINVAL; - mem_hotplug_begin(); /* associate pfn range with the zone */ move_pfn_range_to_zone(zone, pfn, nr_pages, NULL, MIGRATE_ISOLATE); @@ -1208,7 +1210,6 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages, writeback_set_ratelimit(); memory_notify(MEM_ONLINE, &arg); - mem_hotplug_done(); return 0; failed_addition: @@ -1217,7 +1218,6 @@ int __ref online_pages(unsigned long pfn, unsigned long nr_pages, (((unsigned long long) pfn + nr_pages) << PAGE_SHIFT) - 1); memory_notify(MEM_CANCEL_ONLINE, &arg); remove_pfn_range_from_zone(zone, pfn, nr_pages); - mem_hotplug_done(); return ret; } @@ -1863,6 +1863,9 @@ static int count_system_ram_pages_cb(unsigned long start_pfn, return 0; } +/* + * Must be called with mem_hotplug_lock in write mode. + */ int __ref offline_pages(unsigned long start_pfn, unsigned long nr_pages, struct zone *zone, struct memory_group *group) { @@ -1885,8 +1888,6 @@ int __ref offline_pages(unsigned long start_pfn, unsigned long nr_pages, !IS_ALIGNED(start_pfn + nr_pages, PAGES_PER_SECTION))) return -EINVAL; - mem_hotplug_begin(); - /* * Don't allow to offline memory blocks that contain holes. * Consequently, memory blocks with holes can never get onlined @@ -2031,7 +2032,6 @@ int __ref offline_pages(unsigned long start_pfn, unsigned long nr_pages, memory_notify(MEM_OFFLINE, &arg); remove_pfn_range_from_zone(zone, start_pfn, nr_pages); - mem_hotplug_done(); return 0; failed_removal_isolated: @@ -2046,7 +2046,6 @@ int __ref offline_pages(unsigned long start_pfn, unsigned long nr_pages, (unsigned long long) start_pfn << PAGE_SHIFT, ((unsigned long long) end_pfn << PAGE_SHIFT) - 1, reason); - mem_hotplug_done(); return ret; }

1 year, 6 months

1
0
0 0

FAILED: patch "[PATCH] parisc: Fix asm operand number out of range build error in" failed to apply to 6.6-stable tree

by gregkh＠linuxfoundation.org

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>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-6.6.y git checkout FETCH_HEAD git cherry-pick -x 487635756198cad563feb47539c6a37ea57f1dae # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023120949-antiquity-primer-60c1@gregkh' --subject-prefix 'PATCH 6.6.y' HEAD^.. Possible dependencies: 487635756198 ("parisc: Fix asm operand number out of range build error in bug table") 43266838515d ("parisc: Reduce size of the bug_table on 64-bit kernel by half") fe76a1349f23 ("parisc: Use natural CPU alignment for bug_table") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 487635756198cad563feb47539c6a37ea57f1dae Mon Sep 17 00:00:00 2001 From: Helge Deller <deller(a)gmx.de> Date: Mon, 27 Nov 2023 10:39:26 +0100 Subject: [PATCH] parisc: Fix asm operand number out of range build error in bug table Build is broken if CONFIG_DEBUG_BUGVERBOSE=n. Fix it be using the correct asm operand number. Signed-off-by: Helge Deller <deller(a)gmx.de> Reported-by: Linux Kernel Functional Testing <lkft(a)linaro.org> Fixes: fe76a1349f23 ("parisc: Use natural CPU alignment for bug_table") Cc: stable(a)vger.kernel.org # v6.0+ diff --git a/arch/parisc/include/asm/bug.h b/arch/parisc/include/asm/bug.h index 1641ff9a8b83..833555f74ffa 100644 --- a/arch/parisc/include/asm/bug.h +++ b/arch/parisc/include/asm/bug.h @@ -71,7 +71,7 @@ asm volatile("\n" \ "1:\t" PARISC_BUG_BREAK_ASM "\n" \ "\t.pushsection __bug_table,\"a\"\n" \ - "\t.align %2\n" \ + "\t.align 4\n" \ "2:\t" __BUG_REL(1b) "\n" \ "\t.short %0\n" \ "\t.blockz %1-4-2\n" \

1 year, 6 months

1
0
0 0

FAILED: patch "[PATCH] r8169: fix rtl8125b PAUSE frames blasting when suspended" failed to apply to 5.4-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.4-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>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.4.y git checkout FETCH_HEAD git cherry-pick -x 4b0768b6556af56ee9b7cf4e68452a2b6289ae45 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023120919-consensus-dimmer-f852@gregkh' --subject-prefix 'PATCH 5.4.y' HEAD^.. Possible dependencies: 4b0768b6556a ("r8169: fix rtl8125b PAUSE frames blasting when suspended") efc37109c780 ("r8169: remove support for chip version 60") ebe598985711 ("r8169: remove support for chip versions 45 and 47") 68650b4e6c13 ("r8169: support L1.2 control on RTL8168h") c217ab7a3961 ("r8169: enable ASPM L1.2 if system vendor flags it as safe") 4b5f82f6aaef ("r8169: enable ASPM L1/L1.1 from RTL8168h") 18a9eae240cb ("r8169: enable ASPM L0s state") e6d6ca6e1204 ("r8169: Add support for another RTL8168FP") e0d38b588075 ("r8169: improve DASH support") c6cff9dfebb3 ("r8169: move ERI access functions to avoid forward declaration") ae0d0bb29b31 ("Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 4b0768b6556af56ee9b7cf4e68452a2b6289ae45 Mon Sep 17 00:00:00 2001 From: ChunHao Lin <hau(a)realtek.com> Date: Wed, 29 Nov 2023 23:53:50 +0800 Subject: [PATCH] r8169: fix rtl8125b PAUSE frames blasting when suspended When FIFO reaches near full state, device will issue pause frame. If pause slot is enabled(set to 1), in this time, device will issue pause frame only once. But if pause slot is disabled(set to 0), device will keep sending pause frames until FIFO reaches near empty state. When pause slot is disabled, if there is no one to handle receive packets, device FIFO will reach near full state and keep sending pause frames. That will impact entire local area network. This issue can be reproduced in Chromebox (not Chromebook) in developer mode running a test image (and v5.10 kernel): 1) ping -f $CHROMEBOX (from workstation on same local network) 2) run "powerd_dbus_suspend" from command line on the $CHROMEBOX 3) ping $ROUTER (wait until ping fails from workstation) Takes about ~20-30 seconds after step 2 for the local network to stop working. Fix this issue by enabling pause slot to only send pause frame once when FIFO reaches near full state. Fixes: f1bce4ad2f1c ("r8169: add support for RTL8125") Reported-by: Grant Grundler <grundler(a)chromium.org> Tested-by: Grant Grundler <grundler(a)chromium.org> Cc: stable(a)vger.kernel.org Signed-off-by: ChunHao Lin <hau(a)realtek.com> Reviewed-by: Jacob Keller <jacob.e.keller(a)intel.com> Reviewed-by: Heiner Kallweit <hkallweit1(a)gmail.com> Link: https://lore.kernel.org/r/20231129155350.5843-1-hau@realtek.com Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c index 62cabeeb842a..bb787a52bc75 100644 --- a/drivers/net/ethernet/realtek/r8169_main.c +++ b/drivers/net/ethernet/realtek/r8169_main.c @@ -196,6 +196,7 @@ enum rtl_registers { /* No threshold before first PCI xfer */ #define RX_FIFO_THRESH (7 << RXCFG_FIFO_SHIFT) #define RX_EARLY_OFF (1 << 11) +#define RX_PAUSE_SLOT_ON (1 << 11) /* 8125b and later */ #define RXCFG_DMA_SHIFT 8 /* Unlimited maximum PCI burst. */ #define RX_DMA_BURST (7 << RXCFG_DMA_SHIFT) @@ -2306,9 +2307,13 @@ static void rtl_init_rxcfg(struct rtl8169_private *tp) case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_53: RTL_W32(tp, RxConfig, RX128_INT_EN | RX_MULTI_EN | RX_DMA_BURST | RX_EARLY_OFF); break; - case RTL_GIGA_MAC_VER_61 ... RTL_GIGA_MAC_VER_63: + case RTL_GIGA_MAC_VER_61: RTL_W32(tp, RxConfig, RX_FETCH_DFLT_8125 | RX_DMA_BURST); break; + case RTL_GIGA_MAC_VER_63: + RTL_W32(tp, RxConfig, RX_FETCH_DFLT_8125 | RX_DMA_BURST | + RX_PAUSE_SLOT_ON); + break; default: RTL_W32(tp, RxConfig, RX128_INT_EN | RX_DMA_BURST); break;

1 year, 6 months

1
0
0 0

FAILED: patch "[PATCH] r8169: fix rtl8125b PAUSE frames blasting when suspended" failed to apply to 5.10-stable tree

by gregkh＠linuxfoundation.org

The patch below does not apply to the 5.10-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>. To reproduce the conflict and resubmit, you may use the following commands: git fetch https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/ linux-5.10.y git checkout FETCH_HEAD git cherry-pick -x 4b0768b6556af56ee9b7cf4e68452a2b6289ae45 # <resolve conflicts, build, test, etc.> git commit -s git send-email --to '<stable(a)vger.kernel.org>' --in-reply-to '2023120918-coma-plentiful-2159@gregkh' --subject-prefix 'PATCH 5.10.y' HEAD^.. Possible dependencies: 4b0768b6556a ("r8169: fix rtl8125b PAUSE frames blasting when suspended") efc37109c780 ("r8169: remove support for chip version 60") ebe598985711 ("r8169: remove support for chip versions 45 and 47") 68650b4e6c13 ("r8169: support L1.2 control on RTL8168h") c217ab7a3961 ("r8169: enable ASPM L1.2 if system vendor flags it as safe") 4b5f82f6aaef ("r8169: enable ASPM L1/L1.1 from RTL8168h") 18a9eae240cb ("r8169: enable ASPM L0s state") e6d6ca6e1204 ("r8169: Add support for another RTL8168FP") e0d38b588075 ("r8169: improve DASH support") c6cff9dfebb3 ("r8169: move ERI access functions to avoid forward declaration") ae0d0bb29b31 ("Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net") thanks, greg k-h ------------------ original commit in Linus's tree ------------------ From 4b0768b6556af56ee9b7cf4e68452a2b6289ae45 Mon Sep 17 00:00:00 2001 From: ChunHao Lin <hau(a)realtek.com> Date: Wed, 29 Nov 2023 23:53:50 +0800 Subject: [PATCH] r8169: fix rtl8125b PAUSE frames blasting when suspended When FIFO reaches near full state, device will issue pause frame. If pause slot is enabled(set to 1), in this time, device will issue pause frame only once. But if pause slot is disabled(set to 0), device will keep sending pause frames until FIFO reaches near empty state. When pause slot is disabled, if there is no one to handle receive packets, device FIFO will reach near full state and keep sending pause frames. That will impact entire local area network. This issue can be reproduced in Chromebox (not Chromebook) in developer mode running a test image (and v5.10 kernel): 1) ping -f $CHROMEBOX (from workstation on same local network) 2) run "powerd_dbus_suspend" from command line on the $CHROMEBOX 3) ping $ROUTER (wait until ping fails from workstation) Takes about ~20-30 seconds after step 2 for the local network to stop working. Fix this issue by enabling pause slot to only send pause frame once when FIFO reaches near full state. Fixes: f1bce4ad2f1c ("r8169: add support for RTL8125") Reported-by: Grant Grundler <grundler(a)chromium.org> Tested-by: Grant Grundler <grundler(a)chromium.org> Cc: stable(a)vger.kernel.org Signed-off-by: ChunHao Lin <hau(a)realtek.com> Reviewed-by: Jacob Keller <jacob.e.keller(a)intel.com> Reviewed-by: Heiner Kallweit <hkallweit1(a)gmail.com> Link: https://lore.kernel.org/r/20231129155350.5843-1-hau@realtek.com Signed-off-by: Jakub Kicinski <kuba(a)kernel.org> diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c index 62cabeeb842a..bb787a52bc75 100644 --- a/drivers/net/ethernet/realtek/r8169_main.c +++ b/drivers/net/ethernet/realtek/r8169_main.c @@ -196,6 +196,7 @@ enum rtl_registers { /* No threshold before first PCI xfer */ #define RX_FIFO_THRESH (7 << RXCFG_FIFO_SHIFT) #define RX_EARLY_OFF (1 << 11) +#define RX_PAUSE_SLOT_ON (1 << 11) /* 8125b and later */ #define RXCFG_DMA_SHIFT 8 /* Unlimited maximum PCI burst. */ #define RX_DMA_BURST (7 << RXCFG_DMA_SHIFT) @@ -2306,9 +2307,13 @@ static void rtl_init_rxcfg(struct rtl8169_private *tp) case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_53: RTL_W32(tp, RxConfig, RX128_INT_EN | RX_MULTI_EN | RX_DMA_BURST | RX_EARLY_OFF); break; - case RTL_GIGA_MAC_VER_61 ... RTL_GIGA_MAC_VER_63: + case RTL_GIGA_MAC_VER_61: RTL_W32(tp, RxConfig, RX_FETCH_DFLT_8125 | RX_DMA_BURST); break; + case RTL_GIGA_MAC_VER_63: + RTL_W32(tp, RxConfig, RX_FETCH_DFLT_8125 | RX_DMA_BURST | + RX_PAUSE_SLOT_ON); + break; default: RTL_W32(tp, RxConfig, RX128_INT_EN | RX_DMA_BURST); break;

1 year, 6 months

1
0
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror December 2023