selftests/resctrl: Enable MBM and MBA tests on AMD
Subsystems (2)
Babu Moger
reviewerv3 cover selftests/resctrl: Enable MBM and MBA tests on AMD
The MBM (Memory Bandwidth Monitoring) and MBA (Memory Bandwidth Allocation) features are not enabled for AMD systems. The reason was lack of perf counters to compare the resctrl test results.
Starting with the commit25e56847821f ("perf/x86/amd/uncore: Add memory controller support"), AMD now supports the UMC (Unified Memory Controller) perf events. These events can be used to compare the test results.
This series adds the support to detect the UMC events and enable MBM/MBA tests for AMD systems.
v3:
Note: Based the series on top of latest kselftests/master 1613e604df0cd359cf2a7fbd9be7a0bcfacfabd0 (tag: v6.10-rc1).
Also applied the patches from the series
https://lore.kernel.org/lkml/[email protected]/
Separated the fix patch.
Renamed the imc to just mc to make it generic. Changed the search string "uncore_imc_" and "amd_umc_" Changes related rebase to latest kselftest tree.
v2: Changes.
a. Rebased on top of tip/master (Apr 25, 2024)
b. Addressed Ilpo comments except the one about close call.
It seems more clear to keep READ and WRITE separate.
https://lore.kernel.org/lkml/[email protected]/
c. Used ksft_perror call when applicable.
d. Added vendor check for non contiguous CBM check.
v1: https://lore.kernel.org/lkml/[email protected]/
Babu Moger (4):
selftests/resctrl: Rename variables and functions to generic names selftests/resctrl: Pass sysfs controller name of the vendor selftests/resctrl: Add support for MBM and MBA tests on AMD selftests/resctrl: Enable MBA/MBA tests on AMD
tools/testing/selftests/resctrl/mba_test.c | 25 +- tools/testing/selftests/resctrl/mbm_test.c | 23 +- tools/testing/selftests/resctrl/resctrl.h | 2 +- tools/testing/selftests/resctrl/resctrl_val.c | 305 ++++++++++-------- tools/testing/selftests/resctrl/resctrlfs.c | 2 +- 5 files changed, 191 insertions(+), 166 deletions(-)
Signature · 1 line
2.34.1
Babu Moger
reviewerPATCH v3 1/4 selftests/resctrl: Rename variables and functions to generic names
In an effort to support MBM and MBA tests for AMD, renaming for variable and functions to generic names. For Intel, the memory controller is called Integrated Memory Controllers (IMC). For AMD, it is called Unified Memory Controller (UMC).
Change the names of variables and functions from imc (Integrated memory controller) to mc(Memory Controller). No functional change.
---
v3: More name changes. Mostly replacing imc with mc.
v2: Few more name changes.
--- tools/testing/selftests/resctrl/mba_test.c | 24 +- tools/testing/selftests/resctrl/mbm_test.c | 22 +- tools/testing/selftests/resctrl/resctrl.h | 2 +- tools/testing/selftests/resctrl/resctrl_val.c | 225 +++++++++--------- tools/testing/selftests/resctrl/resctrlfs.c | 2 +- 5 files changed, 138 insertions(+), 137 deletions(-)
tools/testing/selftests/resctrl/mba_test.c +12 -12
@@ -21,7 +21,7 @@ static int mba_init(const struct resctrl_val_param *param, int domain_id) {int ret; - ret =initialize_mem_bw_imc (); + ret =initialize_mem_bw_mc ();if (ret)return ret;
@@ -70,7 +70,7 @@ static int mba_measure(const struct user_params *uparams,return measure_mem_bw (uparams, param, bm_pid,"reads" ); } -static bool show_mba_info (unsigned long *bw_imc,unsigned long *bw_resc) +static bool show_mba_info (unsigned long *bw_mc,unsigned long *bw_resc) {int allocation, runs;bool ret = false;
@@ -79,8 +79,8 @@ static bool show_mba_info(unsigned long *bw_imc, unsigned long *bw_resc)/* Memory bandwidth from 100% down to 10% */ for (allocation =0 ; allocation <ALLOCATION_MAX /ALLOCATION_STEP ; allocation++) { -unsigned long sum_bw_imc =0 , sum_bw_resc =0 ; -long avg_bw_imc, avg_bw_resc; +unsigned long sum_bw_mc =0 , sum_bw_resc =0 ; +long avg_bw_mc, avg_bw_resc;int avg_diff_per;float avg_diff;
@@ -90,13 +90,13 @@ static bool show_mba_info(unsigned long *bw_imc, unsigned long *bw_resc)*/ for (runs =NUM_OF_RUNS * allocation +1 ; runs <NUM_OF_RUNS * allocation +NUM_OF_RUNS ; runs++) { - sum_bw_imc += bw_imc[runs]; + sum_bw_mc += bw_mc[runs]; sum_bw_resc += bw_resc[runs]; } - avg_bw_imc = sum_bw_imc / (NUM_OF_RUNS -1 ); + avg_bw_mc = sum_bw_mc / (NUM_OF_RUNS -1 ); avg_bw_resc = sum_bw_resc / (NUM_OF_RUNS -1 ); - avg_diff = (float )labs (avg_bw_resc - avg_bw_imc) / avg_bw_imc; + avg_diff = (float )labs (avg_bw_resc - avg_bw_mc) / avg_bw_mc; avg_diff_per = (int )(avg_diff *100 ); ksft_print_msg("%s Check MBA diff within %d%% for schemata %u\n",
@@ -106,7 +106,7 @@ static bool show_mba_info(unsigned long *bw_imc, unsigned long *bw_resc) ALLOCATION_MAX - ALLOCATION_STEP * allocation);ksft_print_msg ("avg_diff_per: %d%%\n" , avg_diff_per); -ksft_print_msg ("avg_bw_imc: %lu\n" , avg_bw_imc); +ksft_print_msg ("avg_bw_mc: %lu\n" , avg_bw_mc);ksft_print_msg ("avg_bw_resc: %lu\n" , avg_bw_resc);if (avg_diff_per >MAX_DIFF_PERCENT ) ret = true;
@@ -123,7 +123,7 @@ static bool show_mba_info(unsigned long *bw_imc, unsigned long *bw_resc)static int check_results (void ) {char *token_array[8 ], output[] =RESULT_FILE_NAME , temp[512 ]; -unsigned long bw_imc[1024 ], bw_resc[1024 ]; +unsigned long bw_mc[1024 ], bw_resc[1024 ];int runs;FILE *fp;
@@ -144,8 +144,8 @@ static int check_results(void) token =strtok (NULL ,":\t" ); } -/* Field 3 is perf imc value */ - bw_imc[runs] =strtoul (token_array[3 ],NULL ,0 ); +/* Field 3 is perf mc value */ + bw_mc[runs] =strtoul (token_array[3 ],NULL ,0 );/* Field 5 is resctrl value */ bw_resc[runs] =strtoul (token_array[5 ],NULL ,0 ); runs++;
@@ -153,7 +153,7 @@ static int check_results(void)fclose (fp); -return show_mba_info (bw_imc, bw_resc); +return show_mba_info (bw_mc, bw_resc); }static void mba_test_cleanup (void )
tools/testing/selftests/resctrl/mbm_test.c +11 -11
@@ -15,10 +15,10 @@#define NUM_OF_RUNS 5static int -show_bw_info (unsigned long *bw_imc,unsigned long *bw_resc,size_t span) +show_bw_info (unsigned long *bw_mc,unsigned long *bw_resc,size_t span) { -unsigned long sum_bw_imc =0 , sum_bw_resc =0 ; -long avg_bw_imc =0 , avg_bw_resc =0 ; +unsigned long sum_bw_mc =0 , sum_bw_resc =0 ; +long avg_bw_mc =0 , avg_bw_resc =0 ;int runs, ret, avg_diff_per;float avg_diff =0 ;
@@ -27,13 +27,13 @@ show_bw_info(unsigned long *bw_imc, unsigned long *bw_resc, size_t span)* transition phase. */ for (runs =1 ; runs <NUM_OF_RUNS ; runs++) { - sum_bw_imc += bw_imc[runs]; + sum_bw_mc += bw_mc[runs]; sum_bw_resc += bw_resc[runs]; } - avg_bw_imc = sum_bw_imc /4 ; + avg_bw_mc = sum_bw_mc /4 ; avg_bw_resc = sum_bw_resc /4 ; - avg_diff = (float )labs (avg_bw_resc - avg_bw_imc) / avg_bw_imc; + avg_diff = (float )labs (avg_bw_resc - avg_bw_mc) / avg_bw_mc; avg_diff_per = (int )(avg_diff *100 ); ret = avg_diff_per >MAX_DIFF_PERCENT ;
@@ -41,7 +41,7 @@ show_bw_info(unsigned long *bw_imc, unsigned long *bw_resc, size_t span) ret ? "Fail:" : "Pass:", MAX_DIFF_PERCENT);ksft_print_msg ("avg_diff_per: %d%%\n" , avg_diff_per);ksft_print_msg ("Span (MB): %zu\n" , span /MB ); -ksft_print_msg ("avg_bw_imc: %lu\n" , avg_bw_imc); +ksft_print_msg ("avg_bw_mc: %lu\n" , avg_bw_mc);ksft_print_msg ("avg_bw_resc: %lu\n" , avg_bw_resc);return ret;
@@ -49,7 +49,7 @@ show_bw_info(unsigned long *bw_imc, unsigned long *bw_resc, size_t span)static int check_results (size_t span) { -unsigned long bw_imc[NUM_OF_RUNS ], bw_resc[NUM_OF_RUNS ]; +unsigned long bw_mc[NUM_OF_RUNS ], bw_resc[NUM_OF_RUNS ];char temp[1024 ], *token_array[8 ];char output[] =RESULT_FILE_NAME ;int runs, ret;
@@ -75,11 +75,11 @@ static int check_results(size_t span) } bw_resc[runs] =strtoul (token_array[5 ],NULL ,0 ); - bw_imc[runs] =strtoul (token_array[3 ],NULL ,0 ); + bw_mc[runs] =strtoul (token_array[3 ],NULL ,0 ); runs++; } - ret =show_bw_info (bw_imc, bw_resc, span); + ret =show_bw_info (bw_mc, bw_resc, span);fclose (fp);
@@ -90,7 +90,7 @@ static int mbm_init(const struct resctrl_val_param *param, int domain_id) {int ret; - ret =initialize_mem_bw_imc (); + ret =initialize_mem_bw_mc ();if (ret)return ret;
tools/testing/selftests/resctrl/resctrl.h +1 -1
@@ -143,7 +143,7 @@ unsigned char *alloc_buffer(size_t buf_size, int memflush);void mem_flush (unsigned char *buf,size_t buf_size);void fill_cache_read (unsigned char *buf,size_t buf_size,bool once);int run_fill_buf (size_t buf_size,int memflush,int op,bool once); -int initialize_mem_bw_imc (void ); +int initialize_mem_bw_mc (void );int measure_mem_bw (const struct user_params *uparams,struct resctrl_val_param *param,pid_t bm_pid,const char *bw_report);
tools/testing/selftests/resctrl/resctrl_val.c +113 -112
492 lines not on this page · raw message
tools/testing/selftests/resctrl/resctrlfs.c +1 -1
@@ -843,7 +843,7 @@ const char *get_bw_report_type(const char *bw_report)if (strcmp (bw_report,"total" ) ==0 )return bw_report; -fprintf (stderr,"Requested iMC bandwidth report type unavailable\n" ); +fprintf (stderr,"Requested MC bandwidth report type unavailable\n" );return NULL ; }
Signature · 1 line
2.34.1
Babu Moger
reviewerPATCH v3 2/4 selftests/resctrl: Pass sysfs controller name of the vendor
In reply to Babu MogerThe test detects number of memory controllers by looking at the sysfs file system. Detect the vendor to pass the controller name appropriately. So, that rest of the code will be generic and can be used to support other vendors.
Also change the search to look for the full string "uncore_imc_". Replace the sizeof with strlen.
---
v3: Change the search string to "uncore_imc_".
v2: No changes
--- tools/testing/selftests/resctrl/resctrl_val.c | 22 ++++++++++++------- 1 file changed, 14 insertions(+), 8 deletions(-)
tools/testing/selftests/resctrl/resctrl_val.c +14 -8
@@ -10,7 +10,7 @@*/ #include "resctrl.h" -#define UNCORE_IMC "uncore_imc" +#define UNCORE_IMC "uncore_imc_"#define READ_FILE_NAME "events/cas_count_read"#define WRITE_FILE_NAME "events/cas_count_write"#define DYN_PMU_PATH "/sys/bus/event_source/devices"
@@ -206,24 +206,30 @@ static int num_of_mem_controllers(void)char mc_dir[512 ], *temp;unsigned int count =0 ;struct dirent *ep; -int ret; +char *sysfs_name; +int ret, vendor;DIR *dp; + vendor =get_vendor (); +if (vendor ==ARCH_INTEL ) { + sysfs_name =UNCORE_IMC ; + }else { +ksft_perror ("Unsupported vendor!\n" ); +return -1 ; + } + dp =opendir (DYN_PMU_PATH );if (dp) {while ((ep =readdir (dp))) { - temp =strstr (ep->d_name,UNCORE_IMC ); + temp =strstr (ep->d_name, sysfs_name);if (!temp)continue ;/* * imc counters are named as "uncore_imc_<n>", hence -* increment the pointer to point to <n>. Note that -* sizeof(UNCORE_IMC) would count for null character as -* well and hence the last underscore character in -* uncore_imc'_' need not be counted. +* increment the pointer to point to <n>. */ - temp = temp +sizeof (UNCORE_IMC ); + temp = temp +strlen (sysfs_name);/* * Some directories under "DYN_PMU_PATH" could have
Signature · 1 line
2.34.1
Babu Moger
reviewerPATCH v3 3/4 selftests/resctrl: Add support for MBM and MBA tests on AMD
In reply to Babu MogerAdd support to read UMC (Unified Memory Controller) perf events to compare the numbers with QoS monitor for AMD.
---
v3: Made read_from_mc_dir function generic to both AMD and Intel.
Rest are mostly related to rebase.
v2: Replace perror with ksft_perror.
--- tools/testing/selftests/resctrl/resctrl_val.c | 80 ++++++++++++------- 1 file changed, 50 insertions(+), 30 deletions(-)
tools/testing/selftests/resctrl/resctrl_val.c +50 -30
@@ -11,6 +11,7 @@#include "resctrl.h" #define UNCORE_IMC "uncore_imc_" +#define AMD_UMC "amd_umc_"#define READ_FILE_NAME "events/cas_count_read"#define WRITE_FILE_NAME "events/cas_count_write"#define DYN_PMU_PATH "/sys/bus/event_source/devices"
@@ -128,7 +129,7 @@ static int open_perf_event(int i, int cpu_no, int j) }/* Get type and config (read and write) of an MC counter */ -static int read_from_mc_dir (char *mc_dir,int count) +static int read_from_mc_dir (char *mc_dir,int count,int vendor) {char cas_count_cfg[1024 ], mc_counter_cfg[1024 ], mc_counter_type[1024 ];FILE *fp;
@@ -152,41 +153,56 @@ static int read_from_mc_dir(char *mc_dir, int count) mc_counters_config[count][WRITE ].type = mc_counters_config[count][READ ].type; -/* Get read config */ -sprintf (mc_counter_cfg,"%s%s" , mc_dir,READ_FILE_NAME ); - fp =fopen (mc_counter_cfg,"r" ); -if (!fp) { -ksft_perror ("Failed to open MC config file" ); +if (vendor ==ARCH_AMD ) { +/* +* Setup the event and umasks for UMC events +* Number of CAS commands sent for reads: +* EventCode = 0x0a, umask = 0x1 +* Number of CAS commands sent for writes: +* EventCode = 0x0a, umask = 0x2 +*/ + mc_counters_config[count][READ ].event =0xa ; + mc_counters_config[count][READ ].umask =0x1 ; -return -1 ; - } -if (fscanf (fp,"%s" , cas_count_cfg) <=0 ) { -ksft_perror ("Could not get MC cas count read" ); + mc_counters_config[count][WRITE ].event =0xa ; + mc_counters_config[count][WRITE ].umask =0x2 ; + }else { +/* Get read config */ +sprintf (mc_counter_cfg,"%s%s" , mc_dir,READ_FILE_NAME ); + fp =fopen (mc_counter_cfg,"r" ); +if (!fp) { +ksft_perror ("Failed to open MC config file" ); + +return -1 ; + } +if (fscanf (fp,"%s" , cas_count_cfg) <=0 ) { +ksft_perror ("Could not get MC cas count read" ); +fclose (fp); + +return -1 ; + }fclose (fp); -return -1 ; - } -fclose (fp); +get_event_and_umask (cas_count_cfg, count,READ ); -get_event_and_umask (cas_count_cfg, count,READ ); +/* Get write config */ +sprintf (mc_counter_cfg,"%s%s" , mc_dir,WRITE_FILE_NAME ); + fp =fopen (mc_counter_cfg,"r" ); +if (!fp) { +ksft_perror ("Failed to open MC config file" ); -/* Get write config */ -sprintf (mc_counter_cfg,"%s%s" , mc_dir,WRITE_FILE_NAME ); - fp =fopen (mc_counter_cfg,"r" ); -if (!fp) { -ksft_perror ("Failed to open MC config file" ); +return -1 ; + } +if (fscanf (fp,"%s" , cas_count_cfg) <=0 ) { +ksft_perror ("Could not get MC cas count write" ); +fclose (fp); -return -1 ; - } -if (fscanf (fp,"%s" , cas_count_cfg) <=0 ) { -ksft_perror ("Could not get MC cas count write" ); +return -1 ; + }fclose (fp); -return -1 ; +get_event_and_umask (cas_count_cfg, count,WRITE ); } -fclose (fp); - -get_event_and_umask (cas_count_cfg, count,WRITE );return 0 ; }
@@ -213,6 +229,8 @@ static int num_of_mem_controllers(void) vendor =get_vendor ();if (vendor ==ARCH_INTEL ) { sysfs_name =UNCORE_IMC ; + }else if (vendor ==ARCH_AMD ) { + sysfs_name =AMD_UMC ; }else {ksft_perror ("Unsupported vendor!\n" );return -1 ;
@@ -228,6 +246,7 @@ static int num_of_mem_controllers(void)/* * imc counters are named as "uncore_imc_<n>", hence * increment the pointer to point to <n>. +* For AMD, it will be amd_umc_<n>. */ temp = temp +strlen (sysfs_name);
@@ -239,7 +258,7 @@ static int num_of_mem_controllers(void)if (temp[0 ] >='0' && temp[0 ] <='9' ) {sprintf (mc_dir,"%s/%s/" ,DYN_PMU_PATH , ep->d_name); - ret =read_from_mc_dir (mc_dir, count); + ret =read_from_mc_dir (mc_dir, count, vendor);if (ret) {closedir (dp);
@@ -250,8 +269,9 @@ static int num_of_mem_controllers(void) }closedir (dp);if (count ==0 ) { -ksft_print_msg ("Unable to find MC counters\n" ); - +ksft_print_msg ("Unable to find iMC/UMC counters\n" ); +if (vendor ==ARCH_AMD ) +ksft_print_msg ("Try loading amd_uncore module\n" );return -1 ; } }else {
Signature · 1 line
2.34.1
Babu Moger
reviewerPATCH v3 4/4 selftests/resctrl: Enable MBA/MBA tests on AMD
In reply to Babu MogerEnable MBA/MBM tests if UMC (Unified Memory Controller) support is available on the system. Tests will be skipped otherwise.
---
v3: Separated fix as another patch.
https://lore.kernel.org/lkml/3a6c9dd9dc6bda6e2582db049bfe853cd836139f.1717622080.git.babu.moger@amd.com/
v2: No changes.
--- tools/testing/selftests/resctrl/mba_test.c | 1 - tools/testing/selftests/resctrl/mbm_test.c | 1 - 2 files changed, 2 deletions(-)
tools/testing/selftests/resctrl/mba_test.c +0 -1
@@ -192,7 +192,6 @@ static bool mba_feature_check(const struct resctrl_test *test)struct resctrl_test mba_test = { .name ="MBA" , .resource ="MB" , - .vendor_specific =ARCH_INTEL , .feature_check = mba_feature_check, .run_test = mba_run_test, .cleanup = mba_test_cleanup,
tools/testing/selftests/resctrl/mbm_test.c +0 -1
@@ -162,7 +162,6 @@ static bool mbm_feature_check(const struct resctrl_test *test)struct resctrl_test mbm_test = { .name ="MBM" , .resource ="MB" , - .vendor_specific =ARCH_INTEL , .feature_check = mbm_feature_check, .run_test = mbm_run_test, .cleanup = mbm_test_cleanup,
Signature · 1 line
2.34.1
Reinette Chatre
maintainerRe: [PATCH v3 1/4] selftests/resctrl: Rename variables and functions to generic names
In reply to Babu MogerHi Babu,
Quoted 2 lines · Babu Moger
In an effort to support MBM and MBA tests for AMD, renaming for variable and functions to generic names. For Intel, the memory controller is called
Changelog usually starts with some context and then problem to be solved. What the patch does follows that. Maybe just something like:
For Intel, the memory controller is called Integrated Memory Controller (IMC). For AMD, it is called Unified Memory Controller (UMC).
Change the names of variables and functions from imc to mc in preparation for support of MBM and MBA tests for AMD.
No functional change.
Quoted 8 lines
Integrated Memory Controllers (IMC). For AMD, it is called Unified Memory Controller (UMC).
Change the names of variables and functions from imc (Integrated memory controller) to mc(Memory Controller). No functional change.
Signed-off-by Babu Moger <[email protected]>---
...
tools/testing/selftests/resctrl/resctrl_val.c static void do_imc_mem_bw_test(void) · line 353
Quoted 6 lines
tools/testing/selftests/resctrl/resctrl_val.c +1
-1@@ -349,10 +350,10 @@ static void do_imc_mem_bw_test(void)* * Return: = 0 on success. < 0 on failure. */ -static int get_mem_bw_imc (const char *bw_report,float *bw_imc) +static int get_mem_bw_mc (const char *bw_report,float *bw_mc)
The name of the function is expected to be changed in the function comments also.
tools/testing/selftests/resctrl/resctrl_val.c static void do_imc_mem_bw_test(void) · line 358
Quoted 6 lines
tools/testing/selftests/resctrl/resctrl_val.c +1
-1{float reads, writes, of_mul_read, of_mul_write; -int imc; +int mc;/* Start all iMC counters to log values (both read and write) */
Was this intended to be MC?
tools/testing/selftests/resctrl/resctrl_val.c static int get_mem_bw_imc(const char *bw_report, float *bw_imc) · line 364
Quoted 5 lines
tools/testing/selftests/resctrl/resctrl_val.c +0
-0reads =0 , writes =0 , of_mul_read =1 , of_mul_write =1 ;@@ -361,21 +362,21 @@ static int get_mem_bw_imc(const char *bw_report, float *bw_imc)* Get results which are stored in struct type imc_counter_config * Take overflow into consideration before calculating total bandwidth. */
In below snippet imc_counter_config is renamed to mc_counter_config yet the comment above was not changed to match.
tools/testing/selftests/resctrl/resctrl_val.c static int get_mem_bw_imc(const char *bw_report, float *bw_imc) · line 370
Quoted 11 lines
tools/testing/selftests/resctrl/resctrl_val.c +5
-5-for (imc =0 ; imc < imcs; imc++) { -struct imc_counter_config *r = - &imc_counters_config[imc][READ ]; -struct imc_counter_config *w = - &imc_counters_config[imc][WRITE ]; +for (mc =0 ; mc < mcs; mc++) { +struct mc_counter_config *r = + &mc_counters_config[mc][READ ]; +struct mc_counter_config *w = + &mc_counters_config[mc][WRITE ];
I noticed a couple of misses by just looking at this patch. You can use grep to ensure that this patch does what you intend.
Reinette
Reinette Chatre
maintainerRe: [PATCH v3 2/4] selftests/resctrl: Pass sysfs controller name of the vendor
In reply to Babu MogerHi Babu,
Subject and changelog mentions how controller name is "passed" but the patch does not seem to "pass" anything new.
Quoted 31 lines · Babu Moger
The test detects number of memory controllers by looking at the sysfs file system. Detect the vendor to pass the controller name appropriately. So, that rest of the code will be generic and can be used to support other vendors.
Also change the search to look for the full string "
uncore_imc_". Replace the sizeof with strlen.Signed-off-by Babu Moger <[email protected]>---
v3: Change the search string to "uncore_imc_".v2: No changes
--- tools/testing/selftests/resctrl/resctrl_val.c | 22 ++++++++++++------- 1 file changed, 14 insertions(+), 8 deletions(-)tools/testing/selftests/resctrl/resctrl_val.c +1
-1@@ -10,7 +10,7 @@*/ #include "resctrl.h" -#define UNCORE_IMC "uncore_imc" +#define UNCORE_IMC "uncore_imc_"#define READ_FILE_NAME "events/cas_count_read"#define WRITE_FILE_NAME "events/cas_count_write"#define DYN_PMU_PATH "/sys/bus/event_source/devices"
tools/testing/selftests/resctrl/resctrl_val.c static int num_of_mem_controllers(void) · line 213
Quoted 9 lines
tools/testing/selftests/resctrl/resctrl_val.c +3
-1@@ -206,24 +206,30 @@ static int num_of_mem_controllers(void)char mc_dir[512 ], *temp;unsigned int count =0 ;struct dirent *ep; -int ret; +char *sysfs_name; +int ret, vendor;DIR *dp; + vendor =get_vendor ();
get_vendor() is already optimized to only need to do actual detection once. I thus do not see a need for a local variable.
tools/testing/selftests/resctrl/resctrl_val.c static int num_of_mem_controllers(void) · line 217
Quoted 4 lines
tools/testing/selftests/resctrl/resctrl_val.c +4
-0+if (vendor ==ARCH_INTEL ) { + sysfs_name =UNCORE_IMC ; + }else { +ksft_perror ("Unsupported vendor!\n" );
ksft_perror() also adds a "\n" so adding it here is not necessary. Also please drop the exclamation.
Quoted 14 lines
tools/testing/selftests/resctrl/resctrl_val.c +4
-2+return -1 ; + } + dp =opendir (DYN_PMU_PATH );if (dp) {while ((ep =readdir (dp))) { - temp =strstr (ep->d_name,UNCORE_IMC ); + temp =strstr (ep->d_name, sysfs_name);if (!temp)continue ;/* * imc counters are named as "uncore_imc_<n>", hence -* increment the pointer to point to <n>. Note that
tools/testing/selftests/resctrl/resctrl_val.c static int num_of_mem_controllers(void) · line 235
Quoted 10 lines
tools/testing/selftests/resctrl/resctrl_val.c +2
-4-* sizeof(UNCORE_IMC) would count for null character as -* well and hence the last underscore character in -* uncore_imc'_' need not be counted. +* increment the pointer to point to <n>. */ - temp = temp +sizeof (UNCORE_IMC ); + temp = temp +strlen (sysfs_name);/* * Some directories under "DYN_PMU_PATH" could have
Reinette
Reinette Chatre
maintainerRe: [PATCH v3 3/4] selftests/resctrl: Add support for MBM and MBA tests on AMD
In reply to Babu MogerHi Babu,
Quoted 145 lines · Babu Moger
Add support to read UMC (Unified Memory Controller) perf events to compare the numbers with QoS monitor for AMD.
Signed-off-by Babu Moger <[email protected]>---
v3: Maderead_from_mc_dirfunction generic to both AMD and Intel.
Rest are mostly related to rebase.v2: Replace perror with
ksft_perror.--- tools/testing/selftests/resctrl/resctrl_val.c | 80 ++++++++++++------- 1 file changed, 50 insertions(+), 30 deletions(-)tools/testing/selftests/resctrl/resctrl_val.c +47
-28@@ -11,6 +11,7 @@#include "resctrl.h" #define UNCORE_IMC "uncore_imc_" +#define AMD_UMC "amd_umc_"#define READ_FILE_NAME "events/cas_count_read"#define WRITE_FILE_NAME "events/cas_count_write"#define DYN_PMU_PATH "/sys/bus/event_source/devices"@@ -128,7 +129,7 @@ static int open_perf_event(int i, int cpu_no, int j) }/* Get type and config (read and write) of an MC counter */ -static int read_from_mc_dir (char *mc_dir,int count) +static int read_from_mc_dir (char *mc_dir,int count,int vendor) {char cas_count_cfg[1024 ], mc_counter_cfg[1024 ], mc_counter_type[1024 ];FILE *fp;@@ -152,41 +153,56 @@ static int read_from_mc_dir(char *mc_dir, int count) mc_counters_config[count][WRITE ].type = mc_counters_config[count][READ ].type; -/* Get read config */ -sprintf (mc_counter_cfg,"%s%s" , mc_dir,READ_FILE_NAME ); - fp =fopen (mc_counter_cfg,"r" ); -if (!fp) { -ksft_perror ("Failed to open MC config file" ); +if (vendor ==ARCH_AMD ) { +/* +* Setup the event and umasks for UMC events +* Number of CAS commands sent for reads: +* EventCode = 0x0a, umask = 0x1 +* Number of CAS commands sent for writes: +* EventCode = 0x0a, umask = 0x2 +*/ + mc_counters_config[count][READ ].event =0xa ; + mc_counters_config[count][READ ].umask =0x1 ; -return -1 ; - } -if (fscanf (fp,"%s" , cas_count_cfg) <=0 ) { -ksft_perror ("Could not get MC cas count read" ); + mc_counters_config[count][WRITE ].event =0xa ; + mc_counters_config[count][WRITE ].umask =0x2 ; + }else { +/* Get read config */ +sprintf (mc_counter_cfg,"%s%s" , mc_dir,READ_FILE_NAME ); + fp =fopen (mc_counter_cfg,"r" ); +if (!fp) { +ksft_perror ("Failed to open MC config file" ); + +return -1 ; + } +if (fscanf (fp,"%s" , cas_count_cfg) <=0 ) { +ksft_perror ("Could not get MC cas count read" ); +fclose (fp); + +return -1 ; + }fclose (fp); -return -1 ; - } -fclose (fp); +get_event_and_umask (cas_count_cfg, count,READ ); -get_event_and_umask (cas_count_cfg, count,READ ); +/* Get write config */ +sprintf (mc_counter_cfg,"%s%s" , mc_dir,WRITE_FILE_NAME ); + fp =fopen (mc_counter_cfg,"r" ); +if (!fp) { +ksft_perror ("Failed to open MC config file" ); -/* Get write config */ -sprintf (mc_counter_cfg,"%s%s" , mc_dir,WRITE_FILE_NAME ); - fp =fopen (mc_counter_cfg,"r" ); -if (!fp) { -ksft_perror ("Failed to open MC config file" ); +return -1 ; + } +if (fscanf (fp,"%s" , cas_count_cfg) <=0 ) { +ksft_perror ("Could not get MC cas count write" ); +fclose (fp); -return -1 ; - } -if (fscanf (fp,"%s" , cas_count_cfg) <=0 ) { -ksft_perror ("Could not get MC cas count write" ); +return -1 ; + }fclose (fp); -return -1 ; +get_event_and_umask (cas_count_cfg, count,WRITE ); } -fclose (fp); - -get_event_and_umask (cas_count_cfg, count,WRITE );return 0 ; }@@ -213,6 +229,8 @@ static int num_of_mem_controllers(void) vendor =get_vendor ();if (vendor ==ARCH_INTEL ) { sysfs_name =UNCORE_IMC ; + }else if (vendor ==ARCH_AMD ) { + sysfs_name =AMD_UMC ; }else {ksft_perror ("Unsupported vendor!\n" );return -1 ;@@ -228,6 +246,7 @@ static int num_of_mem_controllers(void)/* * imc counters are named as "uncore_imc_<n>", hence * increment the pointer to point to <n>. +* For AMD, it will be amd_umc_<n>. */ temp = temp +strlen (sysfs_name);@@ -239,7 +258,7 @@ static int num_of_mem_controllers(void)if (temp[0 ] >='0' && temp[0 ] <='9' ) {sprintf (mc_dir,"%s/%s/" ,DYN_PMU_PATH , ep->d_name); - ret =read_from_mc_dir (mc_dir, count); + ret =read_from_mc_dir (mc_dir, count, vendor);if (ret) {closedir (dp);@@ -250,8 +269,9 @@ static int num_of_mem_controllers(void) }
tools/testing/selftests/resctrl/resctrl_val.c static int num_of_mem_controllers(void) · line 277
Quoted 10 lines
tools/testing/selftests/resctrl/resctrl_val.c +3
-2closedir (dp);if (count ==0 ) { -ksft_print_msg ("Unable to find MC counters\n" ); - +ksft_print_msg ("Unable to find iMC/UMC counters\n" ); +if (vendor ==ARCH_AMD ) +ksft_print_msg ("Try loading amd_uncore module\n" );return -1 ; } }else {
Can all the vendor checking be contained in num_of_mem_controllers() instead of scattered through multiple layers? There can be two vendor specific functions to initialize mc_counters_config[][]. Only the type setting code ends up being shared so that can be split into a function that is called by both vendor functions?
Reinette
Reinette Chatre
maintainerRe: [PATCH v3 4/4] selftests/resctrl: Enable MBA/MBA tests on AMD
In reply to Babu MogerHi Babu,
Quoted 2 lines · Babu Moger
Enable MBA/MBM tests if UMC (Unified Memory Controller) support is available on the system. Tests will be skipped otherwise.
Could you please point out where the test is skipped if UMC is not available?
Reinette
Moger, Babu
reviewerRe: [PATCH v3 1/4] selftests/resctrl: Rename variables and functions to generic names
In reply to Reinette ChatreHi Reinette,
Quoted 10 lines · Reinette Chatre
Hi Babu,
Quoted 2 lines · Babu Moger
In an effort to support MBM and MBA tests for AMD, renaming for variable and functions to generic names. For Intel, the memory controller is called
Changelog usually starts with some context and then problem to be solved. What
the patch does follows that. Maybe just something like:
Quoted 5 lines
For Intel, the memory controller is called Integrated Memory
Controller (IMC). For AMD, it is called Unified Memory Controller (UMC).
Change the names of variables and functions from imc to mc in preparation for support of MBM and MBA tests for AMD.
No functional change.
Sure.
Quoted 12 lines
Quoted 9 lines
Integrated Memory Controllers (IMC). For AMD, it is called Unified Memory Controller (UMC).
Change the names of variables and functions from imc (Integrated memory controller) to mc(Memory Controller). No functional change.
Signed-off-by Babu Moger <[email protected]>---
...
Quoted 9 lines
tools/testing/selftests/resctrl/resctrl_val.c static void do_imc_mem_bw_test(void) · line 353
Quoted 6 lines
tools/testing/selftests/resctrl/resctrl_val.c +1
-1@@ -349,10 +350,10 @@ static void do_imc_mem_bw_test(void)* * Return: = 0 on success. < 0 on failure. */ -static int get_mem_bw_imc (const char *bw_report,float *bw_imc) +static int get_mem_bw_mc (const char *bw_report,float *bw_mc)The name of the function is expected to be changed in the function comments also.
Ok.
Quoted 8 lines
tools/testing/selftests/resctrl/resctrl_val.c static void do_imc_mem_bw_test(void) · line 358
Quoted 6 lines
tools/testing/selftests/resctrl/resctrl_val.c +1
-1{ float reads, writes, of_mul_read, of_mul_write; - int imc; + int mc; /* Start all iMC counters to log values (both read and write) */Was this intended to be MC?
Yes.
Quoted 11 lines
Quoted 8 lines
tools/testing/selftests/resctrl/resctrl_val.c +0
-0reads = 0, writes = 0, of_mul_read = 1, of_mul_write = 1;@@ -361,21 +362,21 @@ static int get_mem_bw_imc(const char *bw_report, float *bw_imc) * Get results which are stored in struct type imc_counter_config * Take overflow into consideration before calculating totalbandwidth.
*/In below snippet
imc_counter_configis renamed tomc_counter_configyet the comment above was not changed to match.
Will correct it.
Quoted 13 lines
Quoted 12 lines
- for (imc = 0; imc < imcs; imc++) {
- structimc_counter_config*r =
- &imc_counters_config[imc][READ];
- structimc_counter_config*w =
- &imc_counters_config[imc][WRITE];
+ for (mc = 0; mc < mcs; mc++) {
+ structmc_counter_config*r =
+ &mc_counters_config[mc][READ];
+ structmc_counter_config*w =
+ &mc_counters_config[mc][WRITE];
Quoted 2 lines
I noticed a couple of misses by just looking at this patch. You can use grep to ensure that this patch does what you intend.
Sure.--
Thanks
Babu Moger
Moger, Babu
reviewerRe: [PATCH v3 2/4] selftests/resctrl: Pass sysfs controller name of the vendor
In reply to Reinette ChatreHi Reinette,
Quoted 4 lines · Reinette Chatre
Hi Babu,
Subject and changelog mentions how controller name is "passed" but the patch does not seem to "pass" anything new.
Sure. Will change the subject to this. Also will update the commit message.
selftests/resctrl: Dynamically detect sysfs controller name of the vendor
Quoted 36 lines · Babu Moger
Quoted 34 lines
The test detects number of memory controllers by looking at the sysfs file system. Detect the vendor to pass the controller name appropriately. So, that rest of the code will be generic and can be used to support other vendors.
Also change the search to look for the full string "
uncore_imc_". Replace the sizeof with strlen.Signed-off-by Babu Moger <[email protected]>---
v3: Change the search string to "uncore_imc_".v2: No changes
---
tools/testing/selftests/resctrl/resctrl_val.c| 22 ++++++++++++-------1 file changed, 14 insertions(+), 8 deletions(-)tools/testing/selftests/resctrl/resctrl_val.c +0
-0@@ -10,7 +10,7 @@*/ #include "resctrl.h"-#define UNCORE_IMC "
uncore_imc"
+#define UNCORE_IMC "uncore_imc_"
#define READ_FILE_NAME "events/cas_count_read" #define WRITE_FILE_NAME "events/cas_count_write" #define DYN_PMU_PATH "/sys/bus/event_source/devices"tools/testing/selftests/resctrl/resctrl_val.c +0
-0@@ -206,24 +206,30 @@ static int num_of_mem_controllers(void) char mc_dir[512], *temp; unsigned int count = 0; struct dirent *ep;
Quoted 8 lines
tools/testing/selftests/resctrl/resctrl_val.c static int num_of_mem_controllers(void)
Quoted 5 lines
tools/testing/selftests/resctrl/resctrl_val.c +2
-1- int ret; + char *sysfs_name; + int ret, vendor; DIR *dp; + vendor = get_vendor();
get_vendor()is already optimized to only need to do actual detection once. I thus do not see a need for a local variable.
Sure.
Quoted 8 lines
tools/testing/selftests/resctrl/resctrl_val.c static int num_of_mem_controllers(void) · line 217
Quoted 5 lines
tools/testing/selftests/resctrl/resctrl_val.c +4
-0+ if (vendor == ARCH_INTEL) { + sysfs_name = UNCORE_IMC; + } else { + ksft_perror("Unsupported vendor!\n");
ksft_perror()also adds a "\n" so adding it here is not necessary. Also please drop the exclamation.
Sure.
Quoted 26 lines
Quoted 13 lines
tools/testing/selftests/resctrl/resctrl_val.c +4
-1+ return -1; + } + dp = opendir(DYN_PMU_PATH); if (dp) { while ((ep = readdir(dp))) { - temp = strstr(ep->d_name, UNCORE_IMC); + temp = strstr(ep->d_name, sysfs_name); if (!temp) continue; /** imc counters are named as "uncore_imc_<n>", hence tools/testing/selftests/resctrl/resctrl_val.c static int num_of_mem_controllers(void) · line 235
Quoted 10 lines
tools/testing/selftests/resctrl/resctrl_val.c +2
-5-* increment the pointer to point to <n>. Note that -* sizeof(UNCORE_IMC) would count for null character as -* well and hence the last underscore character in -* uncore_imc'_' need not be counted. +* increment the pointer to point to <n>. */ - temp = temp + sizeof(UNCORE_IMC); + temp = temp + strlen(sysfs_name); /** Some directories under "DYN_PMU_PATH" could have Reinette
Signature · 2 lines
Thanks Babu Moger
Moger, Babu
reviewerRe: [PATCH v3 3/4] selftests/resctrl: Add support for MBM and MBA tests on AMD
In reply to Reinette ChatreHi Reinette,
Quoted 149 lines · Reinette Chatre
Hi Babu,
Quoted 137 lines · Babu Moger
Add support to read UMC (Unified Memory Controller) perf events to compare the numbers with QoS monitor for AMD.
Signed-off-by Babu Moger <[email protected]>---
v3: Maderead_from_mc_dirfunction generic to both AMD and Intel. Rest are mostly related to rebase.v2: Replace perror with
ksft_perror.
---
tools/testing/selftests/resctrl/resctrl_val.c| 80 ++++++++++++-------1 file changed, 50 insertions(+), 30 deletions(-)tools/testing/selftests/resctrl/resctrl_val.c +2
-1@@ -11,6 +11,7 @@ #include "resctrl.h" #define UNCORE_IMC "uncore_imc_" +#define AMD_UMC "amd_umc_" #define READ_FILE_NAME "events/cas_count_read" #define WRITE_FILE_NAME "events/cas_count_write" #define DYN_PMU_PATH "/sys/bus/event_source/devices"@@ -128,7 +129,7 @@ static int open_perf_event(int i, int cpu_no, int j) } /* Get type and config (read and write) of an MC counter */ -static int read_from_mc_dir (char *mc_dir,int count) +static int read_from_mc_dir (char *mc_dir,int count,int vendor) { char cas_count_cfg[1024], mc_counter_cfg[1024], mc_counter_type[1024 ]; FILE *fp;@@ -152,41 +153,56 @@ static int read_from_mc_dir(char *mc_dir, int count)mc_counters_config[count][WRITE].type = mc_counters_config[count][READ].type; - /* Get read config */
-sprintf(mc_counter_cfg, "%s%s", mc_dir, READ_FILE_NAME); - fp =fopen(mc_counter_cfg, "r");
- if (!fp) {
-ksft_perror("Failed to open MC config file"); + if (vendor ==ARCH_AMD) {
+ /*
+ * Setup the event and umasks for UMC events
+ * Number of CAS commands sent for reads:
+ * EventCode =0x0a, umask =0x1
+ * Number of CAS commands sent for writes:
+ * EventCode =0x0a, umask =0x2
+ */
+ mc_counters_config[count][READ].event =0xa;
+ mc_counters_config[count][READ].umask =0x1;
- return -1;
- }
- if (fscanf(fp, "%s", cas_count_cfg)<= 0) {
-ksft_perror("Could not get MC cas count read"); + mc_counters_config[count][WRITE].event =0xa; + mc_counters_config[count][WRITE].umask =0x2; + } else {
+ /* Get read config */
+sprintf(mc_counter_cfg, "%s%s", mc_dir, READ_FILE_NAME); + fp =fopen(mc_counter_cfg, "r");
+ if (!fp) {
+ksft_perror("Failed to open MC config file");tools/testing/selftests/resctrl/resctrl_val.c +9
-0+ + return -1; + } + if (fscanf(fp, "%s", cas_count_cfg) <= 0) { + ksft_perror("Could not get MC cas count read"); + fclose(fp); + + return -1; + }fclose(fp);
- return -1;
- }
- fclose(fp);
+get_event_and_umask(cas_count_cfg, count, READ); -get_event_and_umask(cas_count_cfg, count, READ); + /* Get write config */
+sprintf(mc_counter_cfg, "%s%s", mc_dir, WRITE_FILE_NAME); + fp =fopen(mc_counter_cfg, "r");
+ if (!fp) {
+ksft_perror("Failed to open MC config file"); - /* Get write config */
-sprintf(mc_counter_cfg, "%s%s", mc_dir, WRITE_FILE_NAME); - fp =fopen(mc_counter_cfg, "r");
- if (!fp) {
-ksft_perror("Failed to open MC config file"); + return -1;
+ }
+ if (fscanf(fp, "%s", cas_count_cfg)<= 0) {
+ksft_perror("Could not get MC cas count write"); + fclose(fp);
- return -1;
- }
- if (fscanf(fp, "%s", cas_count_cfg)<= 0) {
-ksft_perror("Could not get MC cas count write"); + return -1;
+ }
fclose(fp);
- return -1;
+get_event_and_umask(cas_count_cfg, count, WRITE); }
- fclose(fp);
-
-get_event_and_umask(cas_count_cfg, count, WRITE); return 0;
}tools/testing/selftests/resctrl/resctrl_val.c +3
-0@@ -213,6 +229,8 @@ static int num_of_mem_controllers(void) vendor = get_vendor(); if (vendor == ARCH_INTEL) { sysfs_name = UNCORE_IMC; + } else if (vendor == ARCH_AMD) { + sysfs_name = AMD_UMC; } else { ksft_perror("Unsupported vendor!\n"); return -1;@@ -228,6 +246,7 @@ static int num_of_mem_controllers(void) /* * imc counters are named as "uncore_imc_<n>", hence * increment the pointer to point to <n>. + * For AMD, it will be amd_umc_<n>. */ temp = temp + strlen(sysfs_name); @@ -239,7 +258,7 @@ static int num_of_mem_controllers(void)if (temp[0] >= '0' && temp[0] <= '9') {
sprintf(mc_dir, "%s/%s/", DYN_PMU_PATH, ep->d_name);
- ret =read_from_mc_dir(mc_dir, count); + ret =read_from_mc_dir(mc_dir, count, vendor); if (ret) {
closedir(dp);
@@ -250,8 +269,9 @@ static intnum_of_mem_controllers(void)}
closedir(dp);
if (count == 0) {Quoted 8 lines
-
ksft_print_msg("Unable to find MC counters\n"); -
+ksft_print_msg("Unable to find iMC/UMC counters\n"); + if (vendor ==ARCH_AMD)
+ksft_print_msg("Try loading amd_uncore module\n"); return -1;
}
} else {
Quoted 7 lines
Can all the vendor checking be contained in
num_of_mem_controllers()instead of
scattered through multiple layers? There can be two vendor specific functions to
initialize mc_counters_config[][]. Only the type setting code ends up being shared so that can be split into a function that is called by both vendor functions?
Yes, We can do that. Will add it in v4.
Signature · 2 lines
Thanks Babu Moger
Moger, Babu
reviewerRe: [PATCH v3 4/4] selftests/resctrl: Enable MBA/MBA tests on AMD
In reply to Reinette ChatreHi Reinette,
Quoted 8 lines · Reinette Chatre
Hi Babu,
Quoted 2 lines · Babu Moger
Enable MBA/MBM tests if UMC (Unified Memory Controller) support is available on the system. Tests will be skipped otherwise.
Could you please point out where the test is skipped if UMC is not available?
My bad. It is not skipped. It will report as failed in UMC is not detected. I will update the commit message.
Signature · 2 lines
Thanks Babu Moger
Hello Babu,
I think you are still planning to upstream this patch series.
Do you have a timeline for posting v4? And when do you anticipate it being merged?
I'd like to enable MBM/MBA tests for ARM arch (MPAM driver),
However, I foresee potential conflicts if this patch series is not merged. I apologize for the inconvenience, I kindly request your attention to this matter.
Hello James, Dave,
Have you already considered or made any plans to enable the MBM/MBA tests for the MPAM driver?
Best regards,
Shaopeng TAN
Quoted 55 lines
The MBM (Memory Bandwidth Monitoring) and MBA (Memory Bandwidth Allocation) features are not enabled for AMD systems. The reason was lack of perf counters to compare the resctrl test results.
Starting with the commit
25e56847821f("perf/x86/amd/uncore: Add memory controller support"), AMD now supports the UMC (Unified Memory Controller) perf events. These events can be used to compare the test results.This series adds the support to detect the UMC events and enable MBM/MBA tests for AMD systems.
v3:
Note: Based the series on top of latest kselftests/master1613e604df0cd359cf2a7fbd9be7a0bcfacfabd0(tag: v6.10-rc1).Also applied the patches from the series
https://lore.kernel.org/lkml/[email protected].
com/Separated the fix patch.
Renamed the imc to just mc to make it generic. Changed the search string "uncore_imc_" and "amd_umc_" Changes related rebase to latest kselftest tree.v2: Changes.
a. Rebased on top of tip/master (Apr 25, 2024)
b. Addressed Ilpo comments except the one about close call.
It seems more clear to keep READ and WRITE separate.https://lore.kernel.org/lkml/8e4badb7-6cc5-61f1-e041-d902209a90d5@linux.
intel.com/
c. Usedksft_perrorcall when applicable. d. Added vendor check for non contiguous CBM check.v1: https://lore.kernel.org/lkml/[email protected]/
Babu Moger (4):
selftests/resctrl: Rename variables and functions to generic names selftests/resctrl: Pass sysfs controller name of the vendor selftests/resctrl: Add support for MBM and MBA tests on AMD selftests/resctrl: Enable MBA/MBA tests on AMDtools/testing/selftests/resctrl/mba_test.c | 25 +- tools/testing/selftests/resctrl/mbm_test.c | 23 +- tools/testing/selftests/resctrl/resctrl.h | 2 +- tools/testing/selftests/resctrl/resctrl_val.c | 305 ++++++++++-------- tools/testing/selftests/resctrl/resctrlfs.c | 2 +- 5 files changed, 191 insertions(+), 166 deletions(-)--
2.34.1
Hi Shaopeng,
Quoted 8 lines · Shaopeng Tan (Fujitsu)
Hello Babu,
I think you are still planning to upstream this patch series.
Do you have a timeline for posting v4? And when do you anticipate it being merged?I'd like to enable MBM/MBA tests for ARM arch (MPAM driver),
However, I foresee potential conflicts if this patch series is not merged. I apologize for the inconvenience, I kindly request your attention to this matter.
Thanks for following up.
Swapnil (CC’d) is currently working on revising the patches. We’re aiming to post the updated series by the first week of November. Since these patches will go through multiple rounds of review anyway, I’d recommend posting yours if they’re ready.
Thanks
Babu
Hello Babu,
Thank you for your reply.
I will post my patches once they are ready.
Thank you again for your guidance.
Best regards,
Shaopeng TAN
Quoted 26 lines
Subject: Re: RE: [PATCH v3 0/4] selftests/resctrl: Enable MBM and MBA tests on AMD
Hi Shaopeng,
Quoted 4 lines · Shaopeng Tan (Fujitsu)
Hello Babu,
I think you are still planning to upstream this patch series. Do you have a timeline for posting v4? And when do you anticipate it being
merged?
Quoted 4 lines
I'd like to enable MBM/MBA tests for ARM arch (MPAM driver), However, I foresee potential conflicts if this patch series is not merged. I apologize for the inconvenience, I kindly request your attention to this
matter.
Thanks for following up.
Swapnil (CC’d) is currently working on revising the patches. We’re aiming to post the updated series by the first week of November.
Since these patches will go through multiple rounds of review anyway, I’d recommend posting yours if they’re ready.Thanks
Babu