--- /dev/null
+From 91dcc66b34beb72dde8412421bdc1b4cd40e4fb8 Mon Sep 17 00:00:00 2001
+From: "chr[]" <chris@rudorff.com>
+Date: Wed, 12 Feb 2025 16:51:38 +0100
+Subject: amdgpu/pm/legacy: fix suspend/resume issues
+
+From: chr[] <chris@rudorff.com>
+
+commit 91dcc66b34beb72dde8412421bdc1b4cd40e4fb8 upstream.
+
+resume and irq handler happily races in set_power_state()
+
+* amdgpu_legacy_dpm_compute_clocks() needs lock
+* protect irq work handler
+* fix dpm_enabled usage
+
+v2: fix clang build, integrate Lijo's comments (Alex)
+
+Closes: https://gitlab.freedesktop.org/drm/amd/-/issues/2524
+Fixes: 3712e7a49459 ("drm/amd/pm: unified lock protections in amdgpu_dpm.c")
+Reviewed-by: Lijo Lazar <lijo.lazar@amd.com>
+Tested-by: Maciej S. Szmigiero <mail@maciej.szmigiero.name> # on Oland PRO
+Signed-off-by: chr[] <chris@rudorff.com>
+Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
+(cherry picked from commit ee3dc9e204d271c9c7a8d4d38a0bce4745d33e71)
+Cc: stable@vger.kernel.org
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+---
+ drivers/gpu/drm/amd/pm/legacy-dpm/kv_dpm.c | 25 ++++++++++++++++++------
+ drivers/gpu/drm/amd/pm/legacy-dpm/legacy_dpm.c | 8 +++++--
+ drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c | 26 +++++++++++++++++++------
+ 3 files changed, 45 insertions(+), 14 deletions(-)
+
+--- a/drivers/gpu/drm/amd/pm/legacy-dpm/kv_dpm.c
++++ b/drivers/gpu/drm/amd/pm/legacy-dpm/kv_dpm.c
+@@ -3043,6 +3043,7 @@ static int kv_dpm_hw_init(void *handle)
+ if (!amdgpu_dpm)
+ return 0;
+
++ mutex_lock(&adev->pm.mutex);
+ kv_dpm_setup_asic(adev);
+ ret = kv_dpm_enable(adev);
+ if (ret)
+@@ -3050,6 +3051,8 @@ static int kv_dpm_hw_init(void *handle)
+ else
+ adev->pm.dpm_enabled = true;
+ amdgpu_legacy_dpm_compute_clocks(adev);
++ mutex_unlock(&adev->pm.mutex);
++
+ return ret;
+ }
+
+@@ -3067,32 +3070,42 @@ static int kv_dpm_suspend(void *handle)
+ {
+ struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+
++ cancel_work_sync(&adev->pm.dpm.thermal.work);
++
+ if (adev->pm.dpm_enabled) {
++ mutex_lock(&adev->pm.mutex);
++ adev->pm.dpm_enabled = false;
+ /* disable dpm */
+ kv_dpm_disable(adev);
+ /* reset the power state */
+ adev->pm.dpm.current_ps = adev->pm.dpm.requested_ps = adev->pm.dpm.boot_ps;
++ mutex_unlock(&adev->pm.mutex);
+ }
+ return 0;
+ }
+
+ static int kv_dpm_resume(void *handle)
+ {
+- int ret;
++ int ret = 0;
+ struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+
+- if (adev->pm.dpm_enabled) {
++ if (!amdgpu_dpm)
++ return 0;
++
++ if (!adev->pm.dpm_enabled) {
++ mutex_lock(&adev->pm.mutex);
+ /* asic init will reset to the boot state */
+ kv_dpm_setup_asic(adev);
+ ret = kv_dpm_enable(adev);
+- if (ret)
++ if (ret) {
+ adev->pm.dpm_enabled = false;
+- else
++ } else {
+ adev->pm.dpm_enabled = true;
+- if (adev->pm.dpm_enabled)
+ amdgpu_legacy_dpm_compute_clocks(adev);
++ }
++ mutex_unlock(&adev->pm.mutex);
+ }
+- return 0;
++ return ret;
+ }
+
+ static bool kv_dpm_is_idle(void *handle)
+--- a/drivers/gpu/drm/amd/pm/legacy-dpm/legacy_dpm.c
++++ b/drivers/gpu/drm/amd/pm/legacy-dpm/legacy_dpm.c
+@@ -1009,9 +1009,12 @@ void amdgpu_dpm_thermal_work_handler(str
+ enum amd_pm_state_type dpm_state = POWER_STATE_TYPE_INTERNAL_THERMAL;
+ int temp, size = sizeof(temp);
+
+- if (!adev->pm.dpm_enabled)
+- return;
++ mutex_lock(&adev->pm.mutex);
+
++ if (!adev->pm.dpm_enabled) {
++ mutex_unlock(&adev->pm.mutex);
++ return;
++ }
+ if (!pp_funcs->read_sensor(adev->powerplay.pp_handle,
+ AMDGPU_PP_SENSOR_GPU_TEMP,
+ (void *)&temp,
+@@ -1033,4 +1036,5 @@ void amdgpu_dpm_thermal_work_handler(str
+ adev->pm.dpm.state = dpm_state;
+
+ amdgpu_legacy_dpm_compute_clocks(adev->powerplay.pp_handle);
++ mutex_unlock(&adev->pm.mutex);
+ }
+--- a/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c
++++ b/drivers/gpu/drm/amd/pm/legacy-dpm/si_dpm.c
+@@ -7783,6 +7783,7 @@ static int si_dpm_hw_init(void *handle)
+ if (!amdgpu_dpm)
+ return 0;
+
++ mutex_lock(&adev->pm.mutex);
+ si_dpm_setup_asic(adev);
+ ret = si_dpm_enable(adev);
+ if (ret)
+@@ -7790,6 +7791,7 @@ static int si_dpm_hw_init(void *handle)
+ else
+ adev->pm.dpm_enabled = true;
+ amdgpu_legacy_dpm_compute_clocks(adev);
++ mutex_unlock(&adev->pm.mutex);
+ return ret;
+ }
+
+@@ -7807,32 +7809,44 @@ static int si_dpm_suspend(void *handle)
+ {
+ struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+
++ cancel_work_sync(&adev->pm.dpm.thermal.work);
++
+ if (adev->pm.dpm_enabled) {
++ mutex_lock(&adev->pm.mutex);
++ adev->pm.dpm_enabled = false;
+ /* disable dpm */
+ si_dpm_disable(adev);
+ /* reset the power state */
+ adev->pm.dpm.current_ps = adev->pm.dpm.requested_ps = adev->pm.dpm.boot_ps;
++ mutex_unlock(&adev->pm.mutex);
+ }
++
+ return 0;
+ }
+
+ static int si_dpm_resume(void *handle)
+ {
+- int ret;
++ int ret = 0;
+ struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+
+- if (adev->pm.dpm_enabled) {
++ if (!amdgpu_dpm)
++ return 0;
++
++ if (!adev->pm.dpm_enabled) {
+ /* asic init will reset to the boot state */
++ mutex_lock(&adev->pm.mutex);
+ si_dpm_setup_asic(adev);
+ ret = si_dpm_enable(adev);
+- if (ret)
++ if (ret) {
+ adev->pm.dpm_enabled = false;
+- else
++ } else {
+ adev->pm.dpm_enabled = true;
+- if (adev->pm.dpm_enabled)
+ amdgpu_legacy_dpm_compute_clocks(adev);
++ }
++ mutex_unlock(&adev->pm.mutex);
+ }
+- return 0;
++
++ return ret;
+ }
+
+ static bool si_dpm_is_idle(void *handle)
--- /dev/null
+From 2b90e7ace79774a3540ce569e000388f8d22c9e0 Mon Sep 17 00:00:00 2001
+From: Peter Jones <pjones@redhat.com>
+Date: Wed, 26 Feb 2025 15:18:39 -0500
+Subject: efi: Don't map the entire mokvar table to determine its size
+
+From: Peter Jones <pjones@redhat.com>
+
+commit 2b90e7ace79774a3540ce569e000388f8d22c9e0 upstream.
+
+Currently, when validating the mokvar table, we (re)map the entire table
+on each iteration of the loop, adding space as we discover new entries.
+If the table grows over a certain size, this fails due to limitations of
+early_memmap(), and we get a failure and traceback:
+
+ ------------[ cut here ]------------
+ WARNING: CPU: 0 PID: 0 at mm/early_ioremap.c:139 __early_ioremap+0xef/0x220
+ ...
+ Call Trace:
+ <TASK>
+ ? __early_ioremap+0xef/0x220
+ ? __warn.cold+0x93/0xfa
+ ? __early_ioremap+0xef/0x220
+ ? report_bug+0xff/0x140
+ ? early_fixup_exception+0x5d/0xb0
+ ? early_idt_handler_common+0x2f/0x3a
+ ? __early_ioremap+0xef/0x220
+ ? efi_mokvar_table_init+0xce/0x1d0
+ ? setup_arch+0x864/0xc10
+ ? start_kernel+0x6b/0xa10
+ ? x86_64_start_reservations+0x24/0x30
+ ? x86_64_start_kernel+0xed/0xf0
+ ? common_startup_64+0x13e/0x141
+ </TASK>
+ ---[ end trace 0000000000000000 ]---
+ mokvar: Failed to map EFI MOKvar config table pa=0x7c4c3000, size=265187.
+
+Mapping the entire structure isn't actually necessary, as we don't ever
+need more than one entry header mapped at once.
+
+Changes efi_mokvar_table_init() to only map each entry header, not the
+entire table, when determining the table size. Since we're not mapping
+any data past the variable name, it also changes the code to enforce
+that each variable name is NUL terminated, rather than attempting to
+verify it in place.
+
+Cc: <stable@vger.kernel.org>
+Signed-off-by: Peter Jones <pjones@redhat.com>
+Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
+Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
+---
+ drivers/firmware/efi/mokvar-table.c | 42 +++++++++++-------------------------
+ 1 file changed, 13 insertions(+), 29 deletions(-)
+
+--- a/drivers/firmware/efi/mokvar-table.c
++++ b/drivers/firmware/efi/mokvar-table.c
+@@ -103,9 +103,7 @@ void __init efi_mokvar_table_init(void)
+ void *va = NULL;
+ unsigned long cur_offset = 0;
+ unsigned long offset_limit;
+- unsigned long map_size = 0;
+ unsigned long map_size_needed = 0;
+- unsigned long size;
+ struct efi_mokvar_table_entry *mokvar_entry;
+ int err;
+
+@@ -134,48 +132,34 @@ void __init efi_mokvar_table_init(void)
+ */
+ err = -EINVAL;
+ while (cur_offset + sizeof(*mokvar_entry) <= offset_limit) {
+- mokvar_entry = va + cur_offset;
+- map_size_needed = cur_offset + sizeof(*mokvar_entry);
+- if (map_size_needed > map_size) {
+- if (va)
+- early_memunmap(va, map_size);
+- /*
+- * Map a little more than the fixed size entry
+- * header, anticipating some data. It's safe to
+- * do so as long as we stay within current memory
+- * descriptor.
+- */
+- map_size = min(map_size_needed + 2*EFI_PAGE_SIZE,
+- offset_limit);
+- va = early_memremap(efi.mokvar_table, map_size);
+- if (!va) {
+- pr_err("Failed to map EFI MOKvar config table pa=0x%lx, size=%lu.\n",
+- efi.mokvar_table, map_size);
+- return;
+- }
+- mokvar_entry = va + cur_offset;
++ if (va)
++ early_memunmap(va, sizeof(*mokvar_entry));
++ va = early_memremap(efi.mokvar_table + cur_offset, sizeof(*mokvar_entry));
++ if (!va) {
++ pr_err("Failed to map EFI MOKvar config table pa=0x%lx, size=%zu.\n",
++ efi.mokvar_table + cur_offset, sizeof(*mokvar_entry));
++ return;
+ }
++ mokvar_entry = va;
+
+ /* Check for last sentinel entry */
+ if (mokvar_entry->name[0] == '\0') {
+ if (mokvar_entry->data_size != 0)
+ break;
+ err = 0;
++ map_size_needed = cur_offset + sizeof(*mokvar_entry);
+ break;
+ }
+
+- /* Sanity check that the name is null terminated */
+- size = strnlen(mokvar_entry->name,
+- sizeof(mokvar_entry->name));
+- if (size >= sizeof(mokvar_entry->name))
+- break;
++ /* Enforce that the name is NUL terminated */
++ mokvar_entry->name[sizeof(mokvar_entry->name) - 1] = '\0';
+
+ /* Advance to the next entry */
+- cur_offset = map_size_needed + mokvar_entry->data_size;
++ cur_offset += sizeof(*mokvar_entry) + mokvar_entry->data_size;
+ }
+
+ if (va)
+- early_memunmap(va, map_size);
++ early_memunmap(va, sizeof(*mokvar_entry));
+ if (err) {
+ pr_err("EFI MOKvar config table is not valid\n");
+ return;
projects / thirdparty / kernel / stable-queue.git / commitdiff
