aboutsummaryrefslogtreecommitdiffstats
path: root/nvdebug_entry.c
diff options
context:
space:
mode:
authorJoshua Bakita <bakitajoshua@gmail.com>2023-10-29 14:43:40 -0400
committerJoshua Bakita <bakitajoshua@gmail.com>2023-10-29 15:43:16 -0400
commit8da37f4bbb30027a6efa289bd97d98b2acb5c160 (patch)
tree08ffee914a0ea9b37fc8da07bae2a3bc88ab5ed9 /nvdebug_entry.c
parent874aecaf06a96f5866f9bf31437a1ebd27c2f408 (diff)
Support printing device info on Ampere+ GPUs. By Benjamin Hadad IV
commit c3d6f2c852eb046e9d4f4f1e6527b52c746b2693 Author: Joshua Bakita <bakitajoshua@gmail.com> Date: Sun Oct 29 14:37:51 2023 -0400 Print Ampere+ device_info fields with correct offsets/widths Everything now has been checked against how nvgpu handles it commit b70849d1ce67a58f9f69b37dc62122f789f4cdf7 Author: Joshua Bakita <jbakita@cs.unc.edu> Date: Wed Sep 20 14:27:38 2023 -0400 Rearrange, fix an off-by-one error, and remove an unused define The code in nvdebug.h has been rearranged to enable an easier merge against the jbakita-wip branch. commit 51f808e092846a60ea6c88ea3a1d2e349c92977b Author: Joshua Bakita <jbakita@cs.unc.edu> Date: Wed Sep 20 13:09:17 2023 -0400 Bug fixes and cleanup for new device_info logic - Update comments to match new structure - Make show() function idempotent - Skip empty table entries without aborting - Include names for new engine types - Add warning log messages for skipped table entries - Remove non-functional runlist file creation logic for Ampere+ commit 1d7adc3be1aef5ac9c144bb24008fd8cc5d688a5 Author: Benjamin Hadad IV <bh4@unc.edu> Date: Sat Aug 19 12:47:18 2023 -0400 Debugging changes made to restore functionality following refactoring. - Debugged data display errors. - Debugged crash bugs. - Debugged memory issue. commit 9e6cc03cdf736fbd817ed53fa9a7f506bc91a244 Author: Benjamin Hadad IV <bh4@unc.edu> Date: Wed Aug 16 22:00:20 2023 -0400 A variety of changes have been made as part of the code review. - Functions have been consolidated. - Code was clarified and tidied up overall. - Unnecessary elements were removed. commit 845960fc1b15995fdbd6d61c384567652a150bc4 Author: Benjamin Hadad IV <bh4@unc.edu> Date: Fri Jul 28 11:39:28 2023 -0400 Refactored various systems and debugged minor issues - Added device_info_iter - Merged functions in device_info_procfs.c - Separated device_info data structs by version in nvdebug.h - Fixed issue with device_info runlist ID data commit 8a57aaeba41c43233c323d7e0fc8bf1a81ebc65e Author: Benjamin Hadad IV <bh4@unc.edu> Date: Fri Jul 21 11:32:51 2023 -0400 I have updated the ptop_device_info_t comment in nvdebug.h. commit 33c915f08f5dc63674b158ecc18897494256a6d0 Author: Benjamin Hadad IV <bh4@unc.edu> Date: Wed Jul 19 13:02:52 2023 -0400 Debugged device_info functionality - Fixed device_info crash bugs - Made further edits to display functionality - Refactored code to enhance readability commit bfb4dcf0e78954c0163f3a06a5a088c4d1b437a8 Author: Benjamin Hadad IV <bh4@unc.edu> Date: Thu Jul 13 12:13:17 2023 -0400 This commit is to update the repo for display during a meeting. - Added an Ampere version of the device info data. - Added Ampere versions of auxillary functions. - Modified display functions to accommodate Ampere data. - Made other various small modifications. commit 068e7f4e7208d6c9250ad72208e0b36fd9fdf2f6 Merge: 3725b15 073e897 Author: Benjamin Hadad IV <bh4@unc.edu> Date: Mon Jul 10 12:39:12 2023 -0400 Merge branch 'jbakita-wip' of ssh://rtsrv.cs.unc.edu/public/nvdebug into wip I am merging Mr. Bakita's changes (046d7d2) into this repository. commit 3725b15d5da3e06ef202045d710aa5f15eb72fcc Author: Benjamin Hadad IV <bh4@unc.edu> Date: Mon Jul 3 04:30:54 2023 -0400 I modified nvdebug.h for Ampere.
Diffstat (limited to 'nvdebug_entry.c')
-rw-r--r--nvdebug_entry.c9
1 files changed, 5 insertions, 4 deletions
diff --git a/nvdebug_entry.c b/nvdebug_entry.c
index c362209..0abe658 100644
--- a/nvdebug_entry.c
+++ b/nvdebug_entry.c
@@ -146,7 +146,7 @@ int probe_and_cache_device(void) {
146 146
147// Create files `/proc/gpu#/runlist#`, world readable 147// Create files `/proc/gpu#/runlist#`, world readable
148int create_runlist_files(int device_id, struct proc_dir_entry *dir) { 148int create_runlist_files(int device_id, struct proc_dir_entry *dir) {
149 ptop_device_info_t info; 149 ptop_device_info_gk104_t info;
150 struct proc_dir_entry *rl_entry; 150 struct proc_dir_entry *rl_entry;
151 int i, rl_id; 151 int i, rl_id;
152 char runlist_name[12]; 152 char runlist_name[12];
@@ -154,8 +154,8 @@ int create_runlist_files(int device_id, struct proc_dir_entry *dir) {
154 // Figure out how many runlists there are by checking the device info 154 // Figure out how many runlists there are by checking the device info
155 // registers. Runlists are always numbered sequentially, so we just have 155 // registers. Runlists are always numbered sequentially, so we just have
156 // to find the highest-valued one and add 1 to get the number of runlists. 156 // to find the highest-valued one and add 1 to get the number of runlists.
157 for (i = 0; i < NV_PTOP_DEVICE_INFO__SIZE_1; i++) { 157 for (i = 0; i < NV_PTOP_DEVICE_INFO__SIZE_1_GK104; i++) {
158 info.raw = nvdebug_readl(&g_nvdebug_state[device_id], NV_PTOP_DEVICE_INFO(i)); 158 info.raw = nvdebug_readl(&g_nvdebug_state[device_id], NV_PTOP_DEVICE_INFO_GK104(i));
159 if (info.info_type != INFO_TYPE_ENUM || !info.runlist_is_valid) 159 if (info.info_type != INFO_TYPE_ENUM || !info.runlist_is_valid)
160 continue; 160 continue;
161 if (info.runlist_enum > max_rl_id) 161 if (info.runlist_enum > max_rl_id)
@@ -219,7 +219,8 @@ int __init nvdebug_init(void) {
219 if (!(dir = proc_mkdir_data(device_id_str, 0555, NULL, (void*)device_id))) 219 if (!(dir = proc_mkdir_data(device_id_str, 0555, NULL, (void*)device_id)))
220 goto out_nomem; 220 goto out_nomem;
221 // Create files `/proc/gpu#/runlist#`, world readable 221 // Create files `/proc/gpu#/runlist#`, world readable
222 rl_create_err = create_runlist_files(device_id, dir); 222 if (g_nvdebug_state[device_id].chip_id < NV_CHIP_ID_AMPERE)
223 create_runlist_files(device_id, dir);
223 // Create files `/proc/gpu#/gpc#_tpc_mask`, world readable 224 // Create files `/proc/gpu#/gpc#_tpc_mask`, world readable
224 tpc_masks_create_err = create_tpc_mask_files(device_id, dir); 225 tpc_masks_create_err = create_tpc_mask_files(device_id, dir);
225 // Create file `/proc/gpu#/preempt_tsg`, world writable 226 // Create file `/proc/gpu#/preempt_tsg`, world writable