515.57

NVIDIA · Jul 2, 2022 · 5375d56 · 5375d56
1 parent a301003
commit 5375d56
Show file tree

Hide file tree

Showing 37 changed files with 546 additions and 339 deletions.
diff --git a/CHANGELOG.md b/CHANGELOG.md
@@ -2,6 +2,12 @@
 
 ## Release 515 Entries
 
+### [515.57] 2022-06-28
+
+#### Fixed
+
+- Backtick is deprecated, [#273](https://github.com/NVIDIA/open-gpu-kernel-modules/pull/273) by @arch-user-france1
+
 ### [515.48.07] 2022-05-31
 
 #### Added

diff --git a/README.md b/README.md
@@ -1,23 +1,23 @@
 # NVIDIA Linux Open GPU Kernel Module Source
 
 This is the source release of the NVIDIA Linux open GPU kernel modules,
-version 515.49.05.
+version 515.57.
 
 
 ## How to Build
 
 To build:
 
-    make modules -j`nproc`
+    make modules -j$(nproc)
 
 To install, first uninstall any existing NVIDIA kernel modules.  Then,
 as root:
 
-    make modules_install -j`nproc`
+    make modules_install -j$(nproc)
 
 Note that the kernel modules built here must be used with gsp.bin
 firmware and user-space NVIDIA GPU driver components from a corresponding
-515.49.05 driver release.  This can be achieved by installing
+515.57 driver release.  This can be achieved by installing
 the NVIDIA GPU driver from the .run file using the `--no-kernel-modules`
 option.  E.g.,
 
@@ -39,7 +39,7 @@ If cross-compiling, set these variables on the make command line:
 E.g.,
 
     # compile on x86_64 for aarch64
-    make modules -j`nproc`          \
+    make modules -j$(nproc)         \
         TARGET_ARCH=aarch64         \
         CC=aarch64-linux-gnu-gcc    \
         LD=aarch64-linux-gnu-ld     \
@@ -59,7 +59,7 @@ DEBUG - Set this to "1" to build the kernel modules as debug.  By default, the
 
 These variables can be set on the make command line.  E.g.,
 
-    make modules -j`nproc` NV_VERBOSE=1
+    make modules -j$(nproc) NV_VERBOSE=1
 
 
 ## Supported Toolchains
@@ -167,14 +167,18 @@ for the target kernel.
 ## Compatible GPUs
 
 The open-gpu-kernel-modules can be used on any Turing or later GPU
-(see the table below). However, in the 515.49.05 release,
+(see the table below). However, in the 515.57 release,
 GeForce and Workstation support is still considered alpha-quality.
 
 To enable use of the open kernel modules on GeForce and Workstation GPUs,
 set the "NVreg_OpenRmEnableUnsupportedGpus" nvidia.ko kernel module
 parameter to 1. For more details see the NVIDIA GPU end user README here:
 
-https://us.download.nvidia.com/XFree86/Linux-x86_64/515.49.05/README/kernel_open.html
+https://us.download.nvidia.com/XFree86/Linux-x86_64/515.57/README/kernel_open.html
+
+In the below table, if three IDs are listed, the first is the PCI Device 
+ID, the second is the PCI Subsystem Vendor ID, and the third is the PCI
+Subsystem Device ID.
 
 | Product Name                                    | PCI ID         |
 | ----------------------------------------------- | -------------- |
@@ -496,6 +500,7 @@ https://us.download.nvidia.com/XFree86/Linux-x86_64/515.49.05/README/kernel_open
 | Matrox D-Series D2450                           | 1F76 102B 2800 |
 | Matrox D-Series D2480                           | 1F76 102B 2900 |
 | NVIDIA GeForce GTX 1650                         | 1F82           |
+| NVIDIA GeForce GTX 1630                         | 1F83           |
 | NVIDIA GeForce GTX 1650                         | 1F91           |
 | NVIDIA GeForce GTX 1650 with Max-Q Design       | 1F91 103C 863E |
 | NVIDIA GeForce GTX 1650 with Max-Q Design       | 1F91 103C 86E7 |
@@ -698,8 +703,6 @@ https://us.download.nvidia.com/XFree86/Linux-x86_64/515.49.05/README/kernel_open
 | NVIDIA RTX A5500                                | 2233 10DE 165A |
 | NVIDIA RTX A5500                                | 2233 17AA 165A |
 | NVIDIA A40                                      | 2235 10DE 145A |
-| NVIDIA A10                                      | 2236 10DE 1482 |
-| NVIDIA A10G                                     | 2237 10DE 152F |
 | NVIDIA A10M                                     | 2238 10DE 1677 |
 | NVIDIA GeForce RTX 3060 Ti                      | 2414           |
 | NVIDIA GeForce RTX 3080 Ti Laptop GPU           | 2420           |

diff --git a/kernel-open/Kbuild b/kernel-open/Kbuild
@@ -72,7 +72,7 @@ EXTRA_CFLAGS += -I$(src)/common/inc
 EXTRA_CFLAGS += -I$(src)
 EXTRA_CFLAGS += -Wall -MD $(DEFINES) $(INCLUDES) -Wno-cast-qual -Wno-error -Wno-format-extra-args
 EXTRA_CFLAGS += -D__KERNEL__ -DMODULE -DNVRM
-EXTRA_CFLAGS += -DNV_VERSION_STRING=\"515.49.05\"
+EXTRA_CFLAGS += -DNV_VERSION_STRING=\"515.57\"
 
 EXTRA_CFLAGS += -Wno-unused-function
 

diff --git a/kernel-open/nvidia-uvm/uvm_gpu_replayable_faults.c b/kernel-open/nvidia-uvm/uvm_gpu_replayable_faults.c
@@ -1942,45 +1942,32 @@ static NV_STATUS cancel_faults_precise_va(uvm_gpu_t *gpu,
 
 // Function called when the system has found a global error and needs to
 // trigger RC in RM.
-// We cancel one entry per uTLB
 static void cancel_fault_batch_tlb(uvm_gpu_t *gpu,
                                    uvm_fault_service_batch_context_t *batch_context,
                                    UvmEventFatalReason reason)
 {
     NvU32 i;
 
-    // Fault filtering is not allowed in the TLB-based fault cancel path
-    UVM_ASSERT(batch_context->num_cached_faults == batch_context->num_coalesced_faults);
-
-    for (i = 0; i < batch_context->num_cached_faults; ++i) {
-        NV_STATUS status;
+    for (i = 0; i < batch_context->num_coalesced_faults; ++i) {
+        NV_STATUS status = NV_OK;
         uvm_fault_buffer_entry_t *current_entry;
-        uvm_fault_utlb_info_t *utlb;
+        uvm_fault_buffer_entry_t *coalesced_entry;
 
-        current_entry = &batch_context->fault_cache[i];
-        utlb = &batch_context->utlbs[current_entry->fault_source.utlb_id];
+        current_entry = batch_context->ordered_fault_cache[i];
 
-        // If this uTLB has been already cancelled, skip it
-        if (utlb->cancelled)
-            continue;
+        // The list iteration below skips the entry used as 'head'.
+        // Report the 'head' entry explicitly.
+        uvm_va_space_down_read(current_entry->va_space);
+        uvm_tools_record_gpu_fatal_fault(gpu->parent->id, current_entry->va_space, current_entry, reason);
 
-        record_fatal_fault_helper(gpu, current_entry, reason);
-
-        // Although the global cancellation method can be used here instead of
-        // targeted, we still use the targeted method since this function is
-        // only invoked in GPUs without support for VA fault cancellation, for
-        // which the targeted version is already required in
-        // cancel_faults_precise_tlb(). To maintain consistency, we use the
-        // targeted variant in both cases.
-        status = push_cancel_on_gpu_targeted(gpu,
-                                             current_entry->instance_ptr,
-                                             current_entry->fault_source.gpc_id,
-                                             current_entry->fault_source.client_id,
-                                             &batch_context->tracker);
+        list_for_each_entry(coalesced_entry, &current_entry->merged_instances_list, merged_instances_list)
+            uvm_tools_record_gpu_fatal_fault(gpu->parent->id, current_entry->va_space, coalesced_entry, reason);
+        uvm_va_space_up_read(current_entry->va_space);
+
+        // We need to cancel each instance pointer to correctly handle faults from multiple contexts.
+        status = push_cancel_on_gpu_global(gpu, current_entry->instance_ptr, &batch_context->tracker);
         if (status != NV_OK)
             break;
-
-        utlb->cancelled = true;
     }
 }
 

diff --git a/kernel-open/nvidia-uvm/uvm_migrate_pageable.c b/kernel-open/nvidia-uvm/uvm_migrate_pageable.c
@@ -899,9 +899,14 @@ static NV_STATUS migrate_pageable(migrate_vma_state_t *state)
 
     // VMAs are validated and migrated one at a time, since migrate_vma works
     // on one vma at a time
-    for (; vma->vm_start <= prev_outer; vma = vma->vm_next) {
+    for (; vma->vm_start <= prev_outer; vma = find_vma_intersection(mm, prev_outer, outer)) {
         unsigned long next_addr = 0;
-        NV_STATUS status = migrate_pageable_vma(vma, start, outer, state, &next_addr);
+        NV_STATUS status;
+
+        // Callers have already validated the range so the vma should be valid.
+        UVM_ASSERT(vma);
+
+        status = migrate_pageable_vma(vma, start, outer, state, &next_addr);
         if (status == NV_WARN_NOTHING_TO_DO) {
             NV_STATUS populate_status = NV_OK;
             bool touch = uvm_migrate_args->touch;

diff --git a/kernel-open/nvidia-uvm/uvm_policy.c b/kernel-open/nvidia-uvm/uvm_policy.c
@@ -44,7 +44,7 @@ bool uvm_is_valid_vma_range(struct mm_struct *mm, NvU64 start, NvU64 length)
         if (vma->vm_end >= end)
             return true;
         start = vma->vm_end;
-        vma = vma->vm_next;
+        vma = find_vma_intersection(mm, start, end);
     }
 
     return false;

diff --git a/kernel-open/nvidia-uvm/uvm_populate_pageable.c b/kernel-open/nvidia-uvm/uvm_populate_pageable.c
@@ -158,7 +158,7 @@ NV_STATUS uvm_populate_pageable(struct mm_struct *mm,
     // VMAs are validated and populated one at a time, since they may have
     // different protection flags
     // Validation of VM_SPECIAL flags is delegated to get_user_pages
-    for (; vma->vm_start <= prev_end; vma = vma->vm_next) {
+    for (; vma && vma->vm_start <= prev_end; vma = find_vma_intersection(mm, prev_end, end)) {
         NV_STATUS status = uvm_populate_pageable_vma(vma, start, end - start, min_prot, touch, populate_permissions);
 
         if (status != NV_OK)

diff --git a/src/common/displayport/inc/dp_messages.h b/src/common/displayport/inc/dp_messages.h
@@ -116,7 +116,9 @@ namespace DisplayPort
         bool                isBeingDestroyed;
         bool                isPaused;
 
+        // Properties from regkey
         bool                bNoReplyTimerForBusyWaiting;
+        bool                bDpcdProbingForBusyWaiting;
 
         List                messageReceivers;
         List                notYetSentDownRequest;    // Down Messages yet to be processed
@@ -159,7 +161,8 @@ namespace DisplayPort
         {
             DP_ASSERT(dpRegkeyDatabase.bInitialized &&
                       "All regkeys are invalid because dpRegkeyDatabase is not initialized!");
-            bNoReplyTimerForBusyWaiting = dpRegkeyDatabase.bNoReplyTimerForBusyWaiting;
+            bNoReplyTimerForBusyWaiting  = dpRegkeyDatabase.bNoReplyTimerForBusyWaiting;
+            bDpcdProbingForBusyWaiting   = dpRegkeyDatabase.bDpcdProbingForBusyWaiting;
         }
 
         MessageManager(DPCDHAL * hal, Timer * timer)

diff --git a/src/common/displayport/inc/dp_regkeydatabase.h b/src/common/displayport/inc/dp_regkeydatabase.h
@@ -72,6 +72,9 @@
 #define NV_DP_DSC_OPTIMIZE_LT_BUG_3534707              "DP_DSC_OPTIMIZE_LT_BUG_3534707"
 
 #define NV_DP_REGKEY_NO_REPLY_TIMER_FOR_BUSY_WAITING   "NO_REPLY_TIMER_FOR_BUSY_WAITING"
+
+#define NV_DP_REGKEY_DPCD_PROBING_FOR_BUSY_WAITING     "DP_DPCD_PROBING_FOR_BUSY_WAITING"
+
 //
 // Data Base used to store all the regkey values.
 // The actual data base is declared statically in dp_evoadapter.cpp.
@@ -106,6 +109,7 @@ struct DP_REGKEY_DATABASE
     bool  bDscMstEnablePassThrough;
     bool  bDscOptimizeLTBug3534707;
     bool  bNoReplyTimerForBusyWaiting;
+    bool  bDpcdProbingForBusyWaiting;
 };
 
 #endif //INCLUDED_DP_REGKEYDATABASE_H

diff --git a/src/common/displayport/src/dp_evoadapter.cpp b/src/common/displayport/src/dp_evoadapter.cpp
@@ -96,7 +96,8 @@ const struct
     {NV_DP_DSC_MST_CAP_BUG_3143315,                 &dpRegkeyDatabase.bDscMstCapBug3143315,            DP_REG_VAL_BOOL},
     {NV_DP_DSC_MST_ENABLE_PASS_THROUGH,             &dpRegkeyDatabase.bDscMstEnablePassThrough,        DP_REG_VAL_BOOL},
     {NV_DP_DSC_OPTIMIZE_LT_BUG_3534707,             &dpRegkeyDatabase.bDscOptimizeLTBug3534707,        DP_REG_VAL_BOOL},
-    {NV_DP_REGKEY_NO_REPLY_TIMER_FOR_BUSY_WAITING,  &dpRegkeyDatabase.bNoReplyTimerForBusyWaiting,     DP_REG_VAL_BOOL}
+    {NV_DP_REGKEY_NO_REPLY_TIMER_FOR_BUSY_WAITING,  &dpRegkeyDatabase.bNoReplyTimerForBusyWaiting,     DP_REG_VAL_BOOL},
+    {NV_DP_REGKEY_DPCD_PROBING_FOR_BUSY_WAITING,    &dpRegkeyDatabase.bDpcdProbingForBusyWaiting,      DP_REG_VAL_BOOL}
 };
 
 EvoMainLink::EvoMainLink(EvoInterface * provider, Timer * timer) :

diff --git a/src/common/displayport/src/dp_messages.cpp b/src/common/displayport/src/dp_messages.cpp
@@ -72,6 +72,20 @@ bool MessageManager::send(MessageManager::Message * message, NakData & nakData)
     startTime = timer->getTimeUs();
     do
     {
+        if (bDpcdProbingForBusyWaiting)
+        {
+            hal->updateDPCDOffline();
+            if (hal->isDpcdOffline())
+            {
+                DP_LOG(("DP-MM> Device went offline while waiting for reply and so ignoring message %p (ID = %02X, target = %s)",
+                    (Message*)this, ((Message*)this)->requestIdentifier, (((Message*)this)->state.target).toString(sb)));
+
+                nakData = completion.nakData;
+                completion.failed = true;
+                break;
+            }
+        }
+
         hal->notifyIRQ();
         if (hal->interruptDownReplyReady())
             IRQDownReply();
@@ -81,6 +95,7 @@ bool MessageManager::send(MessageManager::Message * message, NakData & nakData)
             nakData = completion.nakData;
             break;
         }
+
         elapsedTime = timer->getTimeUs() - startTime;
 
         if (elapsedTime > (DPCD_MESSAGE_REPLY_TIMEOUT * 1000))

diff --git a/src/common/displayport/src/dp_wardatabase.cpp b/src/common/displayport/src/dp_wardatabase.cpp
@@ -568,18 +568,28 @@ void Edid::applyEdidWorkArounds(NvU32 warFlag, const DpMonitorDenylistData *pDen
             }
             break;
 
-            //
-            // This panel advertise DSC capabilities, but panel doesn't support DSC
-            // So ignoring DSC capability on this panel
-            //
-            case 0x6F0E:
-                if (ProductID == 0x1609)
-                {
-                    this->WARFlags.bIgnoreDscCap = true;
-                    DP_LOG(("DP-WAR> Ignoring DSC capability on Lenovo CSOT 1609 Panel."));
-                    DP_LOG(("DP-WAR> Bug 3444252"));
-                }
-                break;
+        //
+        // This panel advertise DSC capabilities, but panel doesn't support DSC
+        // So ignoring DSC capability on this panel
+        //
+        case 0x6F0E:
+            if (ProductID == 0x1609)
+            {
+                this->WARFlags.bIgnoreDscCap = true;
+                DP_LOG(("DP-WAR> Ignoring DSC capability on Lenovo CSOT 1609 Panel."));
+                DP_LOG(("DP-WAR> Bug 3444252"));
+            }
+            break;
+
+        // Asus
+        case 0x6D1E:
+            if(ProductID == 0x7707)
+            {
+                this->WARFlags.bIgnoreDscCap = true;
+                DP_LOG(("DP-WAR> Panel incorrectly exposing DSC capability. Ignoring it."));
+                DP_LOG(("DP-WAR> Bug 3543158"));
+            }
+            break;
 
         default:
             break;

diff --git a/src/common/inc/nvBldVer.h b/src/common/inc/nvBldVer.h
@@ -36,25 +36,25 @@
 // and then checked back in. You cannot make changes to these sections without
 // corresponding changes to the buildmeister script
 #ifndef NV_BUILD_BRANCH
-    #define NV_BUILD_BRANCH             VK516_10
+    #define NV_BUILD_BRANCH             r515_00
 #endif
 #ifndef NV_PUBLIC_BRANCH
-    #define NV_PUBLIC_BRANCH             VK516_10
+    #define NV_PUBLIC_BRANCH             r515_00
 #endif
 
 #if defined(NV_LINUX) || defined(NV_BSD) || defined(NV_SUNOS)
-#define NV_BUILD_BRANCH_VERSION         "rel/gpu_drv/r515/VK516_10-204"
-#define NV_BUILD_CHANGELIST_NUM         (31466683)
+#define NV_BUILD_BRANCH_VERSION         "rel/gpu_drv/r515/r515_00-269"
+#define NV_BUILD_CHANGELIST_NUM         (31485447)
 #define NV_BUILD_TYPE                   "Official"
-#define NV_BUILD_NAME                   "rel/gpu_drv/r515/VK516_10-204"
-#define NV_LAST_OFFICIAL_CHANGELIST_NUM (31466683)
+#define NV_BUILD_NAME                   "rel/gpu_drv/r515/r515_00-269"
+#define NV_LAST_OFFICIAL_CHANGELIST_NUM (31485447)
 
 #else     /* Windows builds */
-#define NV_BUILD_BRANCH_VERSION         "VK516_10-5"
-#define NV_BUILD_CHANGELIST_NUM         (31466683)
+#define NV_BUILD_BRANCH_VERSION         "r515_00-210"
+#define NV_BUILD_CHANGELIST_NUM         (31485447)
 #define NV_BUILD_TYPE                   "Official"
-#define NV_BUILD_NAME                   "516.48"
-#define NV_LAST_OFFICIAL_CHANGELIST_NUM (31466683)
+#define NV_BUILD_NAME                   "516.56"
+#define NV_LAST_OFFICIAL_CHANGELIST_NUM (31485447)
 #define NV_BUILD_BRANCH_BASE_VERSION    R515
 #endif
 // End buildmeister python edited section

diff --git a/src/common/inc/nvUnixVersion.h b/src/common/inc/nvUnixVersion.h
@@ -4,7 +4,7 @@
 #if defined(NV_LINUX) || defined(NV_BSD) || defined(NV_SUNOS) || defined(NV_VMWARE) || defined(NV_QNX) || defined(NV_INTEGRITY) || \
     (defined(RMCFG_FEATURE_PLATFORM_GSP) && RMCFG_FEATURE_PLATFORM_GSP == 1)
 
-#define NV_VERSION_STRING               "515.49.05"
+#define NV_VERSION_STRING               "515.57"
 
 #else
 

diff --git a/src/common/sdk/nvidia/inc/ctrl/ctrl2080/ctrl2080internal.h b/src/common/sdk/nvidia/inc/ctrl/ctrl2080/ctrl2080internal.h
@@ -2223,4 +2223,19 @@ typedef struct NV2080_CTRL_INTERNAL_BIF_SET_PCIE_RO_PARAMS {
     NvBool enableRo;
 } NV2080_CTRL_INTERNAL_BIF_SET_PCIE_RO_PARAMS;
 
+/*!
+ * NV2080_CTRL_CMD_INTERNAL_GET_COHERENT_FB_APERTURE_SIZE
+ *
+ * Query Coherent FB Aperture Size.
+ *
+ */
+#define NV2080_CTRL_CMD_INTERNAL_GET_COHERENT_FB_APERTURE_SIZE (0x20800aba) /* finn: Evaluated from "(FINN_NV20_SUBDEVICE_0_INTERNAL_INTERFACE_ID << 8) | NV2080_CTRL_INTERNAL_GET_COHERENT_FB_APERTURE_SIZE_PARAMS_MESSAGE_ID" */
+
+#define NV2080_CTRL_INTERNAL_GET_COHERENT_FB_APERTURE_SIZE_PARAMS_MESSAGE_ID (0xbaU)
+
+typedef struct NV2080_CTRL_INTERNAL_GET_COHERENT_FB_APERTURE_SIZE_PARAMS {
+    // Get Coherent Fb Aperture Size
+    NV_DECLARE_ALIGNED(NvU64 coherentFbApertureSize, 8);
+} NV2080_CTRL_INTERNAL_GET_COHERENT_FB_APERTURE_SIZE_PARAMS;
+
 /* ctrl2080internal_h */
diff --git a/src/nvidia/arch/nvalloc/common/inc/nvcst.h b/src/nvidia/arch/nvalloc/common/inc/nvcst.h
@@ -181,6 +181,7 @@ CSINFO chipsetInfo[] =
     {PCI_VENDOR_ID_INTEL,       0x4385, CS_INTEL_4381,      "Intel-RocketLake",     Intel_4381_setupFunc},
     {PCI_VENDOR_ID_INTEL,       0x7A82, CS_INTEL_7A82,      "Intel-AlderLake",      Intel_7A82_setupFunc},
     {PCI_VENDOR_ID_INTEL,       0x7A84, CS_INTEL_7A82,      "Intel-AlderLake",      Intel_7A82_setupFunc},
+    {PCI_VENDOR_ID_INTEL,       0x1B81, CS_INTEL_1B81,      "Intel-SapphireRapids", NULL},
 
     {PCI_VENDOR_ID_NVIDIA,      0x0FAE, CS_NVIDIA_T210,      "T210",      Nvidia_T210_setupFunc},
     {PCI_VENDOR_ID_NVIDIA,      0x0FAF, CS_NVIDIA_T210,      "T210",      Nvidia_T210_setupFunc},

diff --git a/src/nvidia/arch/nvalloc/common/inc/nvdevid.h b/src/nvidia/arch/nvalloc/common/inc/nvdevid.h
@@ -641,6 +641,7 @@ enum {
 ,     CS_HYGON_C86
 ,     CS_PHYTIUM_S2500
 ,     CS_MELLANOX_BLUEFIELD2
+,     CS_INTEL_1B81
 ,     CS_MAX_PCIE
 };