Thanks for Hawking's and Tao's review.
I will post patch v2 to address your comment.
Regards,
Guchun
-----Original Message-----
From: Zhou1, Tao <Tao.Zhou1@xxxxxxx>
Sent: Tuesday, August 6, 2019 6:07 PM
To: Chen, Guchun <Guchun.Chen@xxxxxxx>; amd-gfx@xxxxxxxxxxxxxxxxxxxxx; Zhang, Hawking <Hawking.Zhang@xxxxxxx>; Li, Dennis <Dennis.Li@xxxxxxx>; Pan, Xinhui <Xinhui.Pan@xxxxxxx>
Cc: Li, Dennis <Dennis.Li@xxxxxxx>; Chen, Guchun <Guchun.Chen@xxxxxxx>
Subject: RE: [PATCH libdrm 2/3] tests/amdgpu/ras: refine ras eject test
-----Original Message-----
From: amd-gfx <amd-gfx-bounces@xxxxxxxxxxxxxxxxxxxxx> On Behalf Of Guchun Chen
Sent: 2019年8月6日 15:36
To: amd-gfx@xxxxxxxxxxxxxxxxxxxxx; Zhang, Hawking <Hawking.Zhang@xxxxxxx>; Li, Dennis <Dennis.Li@xxxxxxx>; Pan, Xinhui <Xinhui.Pan@xxxxxxx>; Zhou1, Tao <Tao.Zhou1@xxxxxxx>
Cc: Li, Dennis <Dennis.Li@xxxxxxx>; Chen, Guchun <Guchun.Chen@xxxxxxx>
Subject: [PATCH libdrm 2/3] tests/amdgpu/ras: refine ras eject test
Ras eject test framework is invalid with original codes, so refine it to make it work on top of kernel ras support.
Change-Id: I63ac27707a69133cd08fa0da308f255b1b169c1f
Signed-off-by: Dennis Li <dennis.li@xxxxxxx>
Signed-off-by: Guchun Chen <guchun.chen@xxxxxxx>
---
configure.ac | 18 ++
meson.build | 1 +
tests/amdgpu/Makefile.am | 5 +-
tests/amdgpu/meson.build | 16 +-
tests/amdgpu/ras_tests.c | 520 +++++++++++++++++++++++++++++++++++----
5 files changed, 509 insertions(+), 51 deletions(-)
diff --git a/configure.ac b/configure.ac index 1cf91347..983b4371 100644
--- a/configure.ac
+++ b/configure.ac
@@ -430,10 +430,24 @@ if test "x$AMDGPU" != xno; then
AC_SUBST([CUNIT_CFLAGS])
fi
fi
+
+ # Detect json-c library
+ PKG_CHECK_MODULES([JSONC], [json-c >= 0.10.1], [have_jsonc=yes], [have_jsonc=no])
+ if test "x${have_jsonc}" = "xno"; then
+ AC_CHECK_LIB([json-c], [json_object_object_get], [have_jsonc=yes], [have_jsonc=no])
+ if test "x${have_jsonc}" = "xyes"; then
+ JSONC_LIBS="-ljson-c"
+ JSONC_CFLAGS=""
+ AC_SUBST([JSONC_LIBS])
+ AC_SUBST([JSONC_CFLAGS])
+ fi
+ fi
else
have_cunit=no
+ have_jsonc=no
fi
AM_CONDITIONAL(HAVE_CUNIT, [test "x$have_cunit" != "xno"])
+AM_CONDITIONAL(HAVE_JSONC, [test "x$have_jsonc" != "xno"])
AM_CONDITIONAL(HAVE_AMDGPU, [test "x$AMDGPU" = xyes]) if test "x$AMDGPU" = xyes; then @@ -442,6 +456,10 @@ if test "x$AMDGPU" = xyes; then
if test "x$have_cunit" = "xno"; then
AC_MSG_WARN([Could not find cunit library. Disabling amdgpu tests])
fi
+
+ if test "x$have_jsonc" = "xno"; then
+ AC_MSG_WARN([Could not find json-c library. Disabling amdgpu tests])
+ fi
else
AC_DEFINE(HAVE_AMDGPU, 0)
fi
diff --git a/meson.build b/meson.build
index e292554a..bc5cfc58 100644
--- a/meson.build
+++ b/meson.build
@@ -217,6 +217,7 @@ libdrm_c_args = warn_c_args + ['-fvisibility=hidden']
dep_pciaccess = dependency('pciaccess', version : '>= 0.10', required : with_intel) dep_cunit = dependency('cunit', version : '>= 2.1', required : false)
+dep_json = dependency('json-c', version : '>= 0.10.1', required :
+false)
_cairo_tests = get_option('cairo-tests') if _cairo_tests != 'false'
dep_cairo = dependency('cairo', required : _cairo_tests == 'true') diff --git a/tests/amdgpu/Makefile.am b/tests/amdgpu/Makefile.am index 920882d0..339bb0a9 100644
--- a/tests/amdgpu/Makefile.am
+++ b/tests/amdgpu/Makefile.am
@@ -7,7 +7,8 @@ AM_CFLAGS = \
LDADD = $(top_builddir)/libdrm.la \
$(top_builddir)/amdgpu/libdrm_amdgpu.la \
- $(CUNIT_LIBS)
+ $(CUNIT_LIBS) \
+ $(JSONC_LIBS)
if HAVE_INSTALL_TESTS
bin_PROGRAMS = \
@@ -17,7 +18,7 @@ noinst_PROGRAMS = \
amdgpu_test
endif
-amdgpu_test_CPPFLAGS = $(CUNIT_CFLAGS)
+amdgpu_test_CPPFLAGS = $(CUNIT_CFLAGS) $(JSONC_CFLAGS)
amdgpu_test_SOURCES = \
amdgpu_test.c \
diff --git a/tests/amdgpu/meson.build b/tests/amdgpu/meson.build index 1726cb43..4307295e 100644
--- a/tests/amdgpu/meson.build
+++ b/tests/amdgpu/meson.build
@@ -18,7 +18,7 @@
# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE # SOFTWARE.
-if dep_cunit.found()
+if dep_cunit.found() and dep_json.found()
amdgpu_test = executable(
'amdgpu_test',
files(
@@ -26,9 +26,19 @@ if dep_cunit.found()
'vce_tests.c', 'uvd_enc_tests.c', 'vcn_tests.c', 'deadlock_tests.c',
'vm_tests.c', 'ras_tests.c', 'syncobj_tests.c',
),
- dependencies : [dep_cunit, dep_threads],
+ dependencies : [dep_cunit, dep_json, dep_threads],
include_directories : [inc_root, inc_drm, include_directories('../../amdgpu')],
link_with : [libdrm, libdrm_amdgpu],
install : with_install_tests,
)
-endif
+
+ configure_file(input : '../../data/amdgpu_ras.json',
+ output : 'amdgpu_ras.json',
+ configuration : configuration_data())
+
+ install_data(
+ '../../data/amdgpu_ras.json',
+ install_mode : 'rw-r--r--',
+ install_dir : datadir_amdgpu,
+ )
+endif
\ No newline at end of file
diff --git a/tests/amdgpu/ras_tests.c b/tests/amdgpu/ras_tests.c index 81c34ad6..c72d53e9 100644
--- a/tests/amdgpu/ras_tests.c
+++ b/tests/amdgpu/ras_tests.c
@@ -30,6 +30,7 @@
#include <fcntl.h>
#include <stdio.h>
#include "xf86drm.h"
+#include "json.h"
const char *ras_block_string[] = {
"umc",
@@ -72,11 +73,252 @@ enum amdgpu_ras_block { #define AMDGPU_RAS_BLOCK_COUNT AMDGPU_RAS_BLOCK__LAST
#define AMDGPU_RAS_BLOCK_MASK ((1ULL << AMDGPU_RAS_BLOCK_COUNT) - 1)
+enum amdgpu_ras_gfx_subblock {
+ /* CPC */
+ AMDGPU_RAS_BLOCK__GFX_CPC_INDEX_START = 0,
+ AMDGPU_RAS_BLOCK__GFX_CPC_SCRATCH =
+ AMDGPU_RAS_BLOCK__GFX_CPC_INDEX_START,
+ AMDGPU_RAS_BLOCK__GFX_CPC_UCODE,
+ AMDGPU_RAS_BLOCK__GFX_DC_STATE_ME1,
+ AMDGPU_RAS_BLOCK__GFX_DC_CSINVOC_ME1,
+ AMDGPU_RAS_BLOCK__GFX_DC_RESTORE_ME1,
+ AMDGPU_RAS_BLOCK__GFX_DC_STATE_ME2,
+ AMDGPU_RAS_BLOCK__GFX_DC_CSINVOC_ME2,
+ AMDGPU_RAS_BLOCK__GFX_DC_RESTORE_ME2,
+ AMDGPU_RAS_BLOCK__GFX_CPC_INDEX_END =
+ AMDGPU_RAS_BLOCK__GFX_DC_RESTORE_ME2,
+ /* CPF */
+ AMDGPU_RAS_BLOCK__GFX_CPF_INDEX_START,
+ AMDGPU_RAS_BLOCK__GFX_CPF_ROQ_ME2 =
+ AMDGPU_RAS_BLOCK__GFX_CPF_INDEX_START,
+ AMDGPU_RAS_BLOCK__GFX_CPF_ROQ_ME1,
+ AMDGPU_RAS_BLOCK__GFX_CPF_TAG,
+ AMDGPU_RAS_BLOCK__GFX_CPF_INDEX_END = AMDGPU_RAS_BLOCK__GFX_CPF_TAG,
+ /* CPG */
+ AMDGPU_RAS_BLOCK__GFX_CPG_INDEX_START,
+ AMDGPU_RAS_BLOCK__GFX_CPG_DMA_ROQ =
+ AMDGPU_RAS_BLOCK__GFX_CPG_INDEX_START,
+ AMDGPU_RAS_BLOCK__GFX_CPG_DMA_TAG,
+ AMDGPU_RAS_BLOCK__GFX_CPG_TAG,
+ AMDGPU_RAS_BLOCK__GFX_CPG_INDEX_END = AMDGPU_RAS_BLOCK__GFX_CPG_TAG,
+ /* GDS */
+ AMDGPU_RAS_BLOCK__GFX_GDS_INDEX_START,
+ AMDGPU_RAS_BLOCK__GFX_GDS_MEM = AMDGPU_RAS_BLOCK__GFX_GDS_INDEX_START,
+ AMDGPU_RAS_BLOCK__GFX_GDS_INPUT_QUEUE,
+ AMDGPU_RAS_BLOCK__GFX_GDS_OA_PHY_CMD_RAM_MEM,
+ AMDGPU_RAS_BLOCK__GFX_GDS_OA_PHY_DATA_RAM_MEM,
+ AMDGPU_RAS_BLOCK__GFX_GDS_OA_PIPE_MEM,
+ AMDGPU_RAS_BLOCK__GFX_GDS_INDEX_END =
+ AMDGPU_RAS_BLOCK__GFX_GDS_OA_PIPE_MEM,
+ /* SPI */
+ AMDGPU_RAS_BLOCK__GFX_SPI_SR_MEM,
+ /* SQ */
+ AMDGPU_RAS_BLOCK__GFX_SQ_INDEX_START,
+ AMDGPU_RAS_BLOCK__GFX_SQ_SGPR = AMDGPU_RAS_BLOCK__GFX_SQ_INDEX_START,
+ AMDGPU_RAS_BLOCK__GFX_SQ_LDS_D,
+ AMDGPU_RAS_BLOCK__GFX_SQ_LDS_I,
+ AMDGPU_RAS_BLOCK__GFX_SQ_VGPR,
+ AMDGPU_RAS_BLOCK__GFX_SQ_INDEX_END = AMDGPU_RAS_BLOCK__GFX_SQ_VGPR,
+ /* SQC (3 ranges) */
+ AMDGPU_RAS_BLOCK__GFX_SQC_INDEX_START,
+ /* SQC range 0 */
+ AMDGPU_RAS_BLOCK__GFX_SQC_INDEX0_START =
+ AMDGPU_RAS_BLOCK__GFX_SQC_INDEX_START,
+ AMDGPU_RAS_BLOCK__GFX_SQC_INST_UTCL1_LFIFO =
+ AMDGPU_RAS_BLOCK__GFX_SQC_INDEX0_START,
+ AMDGPU_RAS_BLOCK__GFX_SQC_DATA_CU0_WRITE_DATA_BUF,
+ AMDGPU_RAS_BLOCK__GFX_SQC_DATA_CU0_UTCL1_LFIFO,
+ AMDGPU_RAS_BLOCK__GFX_SQC_DATA_CU1_WRITE_DATA_BUF,
+ AMDGPU_RAS_BLOCK__GFX_SQC_DATA_CU1_UTCL1_LFIFO,
+ AMDGPU_RAS_BLOCK__GFX_SQC_DATA_CU2_WRITE_DATA_BUF,
+ AMDGPU_RAS_BLOCK__GFX_SQC_DATA_CU2_UTCL1_LFIFO,
+ AMDGPU_RAS_BLOCK__GFX_SQC_INDEX0_END =
+ AMDGPU_RAS_BLOCK__GFX_SQC_DATA_CU2_UTCL1_LFIFO,
+ /* SQC range 1 */
+ AMDGPU_RAS_BLOCK__GFX_SQC_INDEX1_START,
+ AMDGPU_RAS_BLOCK__GFX_SQC_INST_BANKA_TAG_RAM =
+ AMDGPU_RAS_BLOCK__GFX_SQC_INDEX1_START,
+ AMDGPU_RAS_BLOCK__GFX_SQC_INST_BANKA_UTCL1_MISS_FIFO,
+ AMDGPU_RAS_BLOCK__GFX_SQC_INST_BANKA_MISS_FIFO,
+ AMDGPU_RAS_BLOCK__GFX_SQC_INST_BANKA_BANK_RAM,
+ AMDGPU_RAS_BLOCK__GFX_SQC_DATA_BANKA_TAG_RAM,
+ AMDGPU_RAS_BLOCK__GFX_SQC_DATA_BANKA_HIT_FIFO,
+ AMDGPU_RAS_BLOCK__GFX_SQC_DATA_BANKA_MISS_FIFO,
+ AMDGPU_RAS_BLOCK__GFX_SQC_DATA_BANKA_DIRTY_BIT_RAM,
+ AMDGPU_RAS_BLOCK__GFX_SQC_DATA_BANKA_BANK_RAM,
+ AMDGPU_RAS_BLOCK__GFX_SQC_INDEX1_END =
+ AMDGPU_RAS_BLOCK__GFX_SQC_DATA_BANKA_BANK_RAM,
+ /* SQC range 2 */
+ AMDGPU_RAS_BLOCK__GFX_SQC_INDEX2_START,
+ AMDGPU_RAS_BLOCK__GFX_SQC_INST_BANKB_TAG_RAM =
+ AMDGPU_RAS_BLOCK__GFX_SQC_INDEX2_START,
+ AMDGPU_RAS_BLOCK__GFX_SQC_INST_BANKB_UTCL1_MISS_FIFO,
+ AMDGPU_RAS_BLOCK__GFX_SQC_INST_BANKB_MISS_FIFO,
+ AMDGPU_RAS_BLOCK__GFX_SQC_INST_BANKB_BANK_RAM,
+ AMDGPU_RAS_BLOCK__GFX_SQC_DATA_BANKB_TAG_RAM,
+ AMDGPU_RAS_BLOCK__GFX_SQC_DATA_BANKB_HIT_FIFO,
+ AMDGPU_RAS_BLOCK__GFX_SQC_DATA_BANKB_MISS_FIFO,
+ AMDGPU_RAS_BLOCK__GFX_SQC_DATA_BANKB_DIRTY_BIT_RAM,
+ AMDGPU_RAS_BLOCK__GFX_SQC_DATA_BANKB_BANK_RAM,
+ AMDGPU_RAS_BLOCK__GFX_SQC_INDEX2_END =
+ AMDGPU_RAS_BLOCK__GFX_SQC_DATA_BANKB_BANK_RAM,
+ AMDGPU_RAS_BLOCK__GFX_SQC_INDEX_END =
+ AMDGPU_RAS_BLOCK__GFX_SQC_INDEX2_END,
+ /* TA */
+ AMDGPU_RAS_BLOCK__GFX_TA_INDEX_START,
+ AMDGPU_RAS_BLOCK__GFX_TA_FS_DFIFO =
+ AMDGPU_RAS_BLOCK__GFX_TA_INDEX_START,
+ AMDGPU_RAS_BLOCK__GFX_TA_FS_AFIFO,
+ AMDGPU_RAS_BLOCK__GFX_TA_FL_LFIFO,
+ AMDGPU_RAS_BLOCK__GFX_TA_FX_LFIFO,
+ AMDGPU_RAS_BLOCK__GFX_TA_FS_CFIFO,
+ AMDGPU_RAS_BLOCK__GFX_TA_INDEX_END = AMDGPU_RAS_BLOCK__GFX_TA_FS_CFIFO,
+ /* TCA */
+ AMDGPU_RAS_BLOCK__GFX_TCA_INDEX_START,
+ AMDGPU_RAS_BLOCK__GFX_TCA_HOLE_FIFO =
+ AMDGPU_RAS_BLOCK__GFX_TCA_INDEX_START,
+ AMDGPU_RAS_BLOCK__GFX_TCA_REQ_FIFO,
+ AMDGPU_RAS_BLOCK__GFX_TCA_INDEX_END =
+ AMDGPU_RAS_BLOCK__GFX_TCA_REQ_FIFO,
+ /* TCC (5 sub-ranges) */
+ AMDGPU_RAS_BLOCK__GFX_TCC_INDEX_START,
+ /* TCC range 0 */
+ AMDGPU_RAS_BLOCK__GFX_TCC_INDEX0_START =
+ AMDGPU_RAS_BLOCK__GFX_TCC_INDEX_START,
+ AMDGPU_RAS_BLOCK__GFX_TCC_CACHE_DATA =
+ AMDGPU_RAS_BLOCK__GFX_TCC_INDEX0_START,
+ AMDGPU_RAS_BLOCK__GFX_TCC_CACHE_DATA_BANK_0_1,
+ AMDGPU_RAS_BLOCK__GFX_TCC_CACHE_DATA_BANK_1_0,
+ AMDGPU_RAS_BLOCK__GFX_TCC_CACHE_DATA_BANK_1_1,
+ AMDGPU_RAS_BLOCK__GFX_TCC_CACHE_DIRTY_BANK_0,
+ AMDGPU_RAS_BLOCK__GFX_TCC_CACHE_DIRTY_BANK_1,
+ AMDGPU_RAS_BLOCK__GFX_TCC_HIGH_RATE_TAG,
+ AMDGPU_RAS_BLOCK__GFX_TCC_LOW_RATE_TAG,
+ AMDGPU_RAS_BLOCK__GFX_TCC_INDEX0_END =
+ AMDGPU_RAS_BLOCK__GFX_TCC_LOW_RATE_TAG,
+ /* TCC range 1 */
+ AMDGPU_RAS_BLOCK__GFX_TCC_INDEX1_START,
+ AMDGPU_RAS_BLOCK__GFX_TCC_IN_USE_DEC =
+ AMDGPU_RAS_BLOCK__GFX_TCC_INDEX1_START,
+ AMDGPU_RAS_BLOCK__GFX_TCC_IN_USE_TRANSFER,
+ AMDGPU_RAS_BLOCK__GFX_TCC_INDEX1_END =
+ AMDGPU_RAS_BLOCK__GFX_TCC_IN_USE_TRANSFER,
+ /* TCC range 2 */
+ AMDGPU_RAS_BLOCK__GFX_TCC_INDEX2_START,
+ AMDGPU_RAS_BLOCK__GFX_TCC_RETURN_DATA =
+ AMDGPU_RAS_BLOCK__GFX_TCC_INDEX2_START,
+ AMDGPU_RAS_BLOCK__GFX_TCC_RETURN_CONTROL,
+ AMDGPU_RAS_BLOCK__GFX_TCC_UC_ATOMIC_FIFO,
+ AMDGPU_RAS_BLOCK__GFX_TCC_WRITE_RETURN,
+ AMDGPU_RAS_BLOCK__GFX_TCC_WRITE_CACHE_READ,
+ AMDGPU_RAS_BLOCK__GFX_TCC_SRC_FIFO,
+ AMDGPU_RAS_BLOCK__GFX_TCC_SRC_FIFO_NEXT_RAM,
+ AMDGPU_RAS_BLOCK__GFX_TCC_CACHE_TAG_PROBE_FIFO,
+ AMDGPU_RAS_BLOCK__GFX_TCC_INDEX2_END =
+ AMDGPU_RAS_BLOCK__GFX_TCC_CACHE_TAG_PROBE_FIFO,
+ /* TCC range 3 */
+ AMDGPU_RAS_BLOCK__GFX_TCC_INDEX3_START,
+ AMDGPU_RAS_BLOCK__GFX_TCC_LATENCY_FIFO =
+ AMDGPU_RAS_BLOCK__GFX_TCC_INDEX3_START,
+ AMDGPU_RAS_BLOCK__GFX_TCC_LATENCY_FIFO_NEXT_RAM,
+ AMDGPU_RAS_BLOCK__GFX_TCC_INDEX3_END =
+ AMDGPU_RAS_BLOCK__GFX_TCC_LATENCY_FIFO_NEXT_RAM,
+ /* TCC range 4 */
+ AMDGPU_RAS_BLOCK__GFX_TCC_INDEX4_START,
+ AMDGPU_RAS_BLOCK__GFX_TCC_WRRET_TAG_WRITE_RETURN =
+ AMDGPU_RAS_BLOCK__GFX_TCC_INDEX4_START,
+ AMDGPU_RAS_BLOCK__GFX_TCC_ATOMIC_RETURN_BUFFER,
+ AMDGPU_RAS_BLOCK__GFX_TCC_INDEX4_END =
+ AMDGPU_RAS_BLOCK__GFX_TCC_ATOMIC_RETURN_BUFFER,
+ AMDGPU_RAS_BLOCK__GFX_TCC_INDEX_END =
+ AMDGPU_RAS_BLOCK__GFX_TCC_INDEX4_END,
+ /* TCI */
+ AMDGPU_RAS_BLOCK__GFX_TCI_WRITE_RAM,
+ /* TCP */
+ AMDGPU_RAS_BLOCK__GFX_TCP_INDEX_START,
+ AMDGPU_RAS_BLOCK__GFX_TCP_CACHE_RAM =
+ AMDGPU_RAS_BLOCK__GFX_TCP_INDEX_START,
+ AMDGPU_RAS_BLOCK__GFX_TCP_LFIFO_RAM,
+ AMDGPU_RAS_BLOCK__GFX_TCP_CMD_FIFO,
+ AMDGPU_RAS_BLOCK__GFX_TCP_VM_FIFO,
+ AMDGPU_RAS_BLOCK__GFX_TCP_DB_RAM,
+ AMDGPU_RAS_BLOCK__GFX_TCP_UTCL1_LFIFO0,
+ AMDGPU_RAS_BLOCK__GFX_TCP_UTCL1_LFIFO1,
+ AMDGPU_RAS_BLOCK__GFX_TCP_INDEX_END =
+ AMDGPU_RAS_BLOCK__GFX_TCP_UTCL1_LFIFO1,
+ /* TD */
+ AMDGPU_RAS_BLOCK__GFX_TD_INDEX_START,
+ AMDGPU_RAS_BLOCK__GFX_TD_SS_FIFO_LO =
+ AMDGPU_RAS_BLOCK__GFX_TD_INDEX_START,
+ AMDGPU_RAS_BLOCK__GFX_TD_SS_FIFO_HI,
+ AMDGPU_RAS_BLOCK__GFX_TD_CS_FIFO,
+ AMDGPU_RAS_BLOCK__GFX_TD_INDEX_END = AMDGPU_RAS_BLOCK__GFX_TD_CS_FIFO,
+ /* EA (3 sub-ranges) */
+ AMDGPU_RAS_BLOCK__GFX_EA_INDEX_START,
+ /* EA range 0 */
+ AMDGPU_RAS_BLOCK__GFX_EA_INDEX0_START =
+ AMDGPU_RAS_BLOCK__GFX_EA_INDEX_START,
+ AMDGPU_RAS_BLOCK__GFX_EA_DRAMRD_CMDMEM =
+ AMDGPU_RAS_BLOCK__GFX_EA_INDEX0_START,
+ AMDGPU_RAS_BLOCK__GFX_EA_DRAMWR_CMDMEM,
+ AMDGPU_RAS_BLOCK__GFX_EA_DRAMWR_DATAMEM,
+ AMDGPU_RAS_BLOCK__GFX_EA_RRET_TAGMEM,
+ AMDGPU_RAS_BLOCK__GFX_EA_WRET_TAGMEM,
+ AMDGPU_RAS_BLOCK__GFX_EA_GMIRD_CMDMEM,
+ AMDGPU_RAS_BLOCK__GFX_EA_GMIWR_CMDMEM,
+ AMDGPU_RAS_BLOCK__GFX_EA_GMIWR_DATAMEM,
+ AMDGPU_RAS_BLOCK__GFX_EA_INDEX0_END =
+ AMDGPU_RAS_BLOCK__GFX_EA_GMIWR_DATAMEM,
+ /* EA range 1 */
+ AMDGPU_RAS_BLOCK__GFX_EA_INDEX1_START,
+ AMDGPU_RAS_BLOCK__GFX_EA_DRAMRD_PAGEMEM =
+ AMDGPU_RAS_BLOCK__GFX_EA_INDEX1_START,
+ AMDGPU_RAS_BLOCK__GFX_EA_DRAMWR_PAGEMEM,
+ AMDGPU_RAS_BLOCK__GFX_EA_IORD_CMDMEM,
+ AMDGPU_RAS_BLOCK__GFX_EA_IOWR_CMDMEM,
+ AMDGPU_RAS_BLOCK__GFX_EA_IOWR_DATAMEM,
+ AMDGPU_RAS_BLOCK__GFX_EA_GMIRD_PAGEMEM,
+ AMDGPU_RAS_BLOCK__GFX_EA_GMIWR_PAGEMEM,
+ AMDGPU_RAS_BLOCK__GFX_EA_INDEX1_END =
+ AMDGPU_RAS_BLOCK__GFX_EA_GMIWR_PAGEMEM,
+ /* EA range 2 */
+ AMDGPU_RAS_BLOCK__GFX_EA_INDEX2_START,
+ AMDGPU_RAS_BLOCK__GFX_EA_MAM_D0MEM =
+ AMDGPU_RAS_BLOCK__GFX_EA_INDEX2_START,
+ AMDGPU_RAS_BLOCK__GFX_EA_MAM_D1MEM,
+ AMDGPU_RAS_BLOCK__GFX_EA_MAM_D2MEM,
+ AMDGPU_RAS_BLOCK__GFX_EA_MAM_D3MEM,
+ AMDGPU_RAS_BLOCK__GFX_EA_INDEX2_END =
+ AMDGPU_RAS_BLOCK__GFX_EA_MAM_D3MEM,
+ AMDGPU_RAS_BLOCK__GFX_EA_INDEX_END =
+ AMDGPU_RAS_BLOCK__GFX_EA_INDEX2_END,
+ /* UTC VM L2 bank */
+ AMDGPU_RAS_BLOCK__UTC_VML2_BANK_CACHE,
+ /* UTC VM walker */
+ AMDGPU_RAS_BLOCK__UTC_VML2_WALKER,
+ /* UTC ATC L2 2MB cache */
+ AMDGPU_RAS_BLOCK__UTC_ATCL2_CACHE_2M_BANK,
+ /* UTC ATC L2 4KB cache */
+ AMDGPU_RAS_BLOCK__UTC_ATCL2_CACHE_4K_BANK,
+ AMDGPU_RAS_BLOCK__GFX_MAX
+};
+
enum amdgpu_ras_error_type {
- AMDGPU_RAS_ERROR__NONE = 0,
- AMDGPU_RAS_ERROR__SINGLE_CORRECTABLE = 2,
- AMDGPU_RAS_ERROR__MULTI_UNCORRECTABLE = 4,
- AMDGPU_RAS_ERROR__POISON = 8,
+ AMDGPU_RAS_ERROR__NONE = 0,
+ AMDGPU_RAS_ERROR__PARITY = 1,
+ AMDGPU_RAS_ERROR__SINGLE_CORRECTABLE = 2,
+ AMDGPU_RAS_ERROR__MULTI_UNCORRECTABLE = 4,
+ AMDGPU_RAS_ERROR__POISON = 8,
+};
+
+struct ras_test_item {
+ char name[64];
+ int block;
+ int sub_block;
+ char error_type_str[64];
+ enum amdgpu_ras_error_type type;
+ uint64_t address;
+ uint64_t value;
};
struct ras_common_if {
@@ -100,8 +342,10 @@ struct ras_debug_if {
int op;
};
/* for now, only umc, gfx, sdma has implemented. */ -#define DEFAULT_RAS_BLOCK_MASK_INJECT (1 << AMDGPU_RAS_BLOCK__UMC) -#define DEFAULT_RAS_BLOCK_MASK_QUERY (1 << AMDGPU_RAS_BLOCK__UMC)
+#define DEFAULT_RAS_BLOCK_MASK_INJECT ((1 << AMDGPU_RAS_BLOCK__UMC) |\
+ (1 << AMDGPU_RAS_BLOCK__GFX))
+#define DEFAULT_RAS_BLOCK_MASK_QUERY ((1 << AMDGPU_RAS_BLOCK__UMC) |\
+ (1 << AMDGPU_RAS_BLOCK__GFX))
#define DEFAULT_RAS_BLOCK_MASK_BASIC (1 << AMDGPU_RAS_BLOCK__UMC |\
(1 << AMDGPU_RAS_BLOCK__SDMA) |\
(1 << AMDGPU_RAS_BLOCK__GFX))
@@ -453,6 +697,32 @@ static int amdgpu_ras_query_err_count(enum amdgpu_ras_block block,
return 0;
}
+static int amdgpu_ras_inject(enum amdgpu_ras_block block,
+ uint32_t sub_block, enum amdgpu_ras_error_type type,
+ uint64_t address, uint64_t value)
+{
+ struct ras_debug_if data = { .op = 2, };
+ struct ras_inject_if *inject = &data.inject;
+ int ret;
+
+ if (amdgpu_ras_is_feature_enabled(block) <= 0)
+ return -1;
[Tao] Maybe a print can be added here to indicate the error reason.
+
+ inject->head.block = block;
+ inject->head.type = type;
+ inject->head.sub_block_index = sub_block;
+ strncpy(inject->head.name, ras_block_str(block), 32);
+ inject->address = address;
+ inject->value = value;
+
+ ret = amdgpu_ras_invoke(&data);
+ CU_ASSERT_EQUAL(ret, 0);
+ if (ret)
+ return -1;
+
+ return 0;
+}
+
//tests
static void amdgpu_ras_features_test(int enable) { @@ -503,66 +773,224 @@ static void amdgpu_ras_enable_test(void)
}
}
-static void __amdgpu_ras_inject_test(void)
+static int _json_get_block_id(json_object *block_obj, const char *name)
{
- struct ras_debug_if data;
- int ret;
- int i;
- unsigned long ue, ce, ue_old, ce_old;
+ json_object *item_obj, *index_obj;
- data.op = 2;
- for (i = 0; i < AMDGPU_RAS_BLOCK__LAST; i++) {
- int timeout = 3;
- struct ras_inject_if inject = {
- .head = {
- .block = i,
- .type = AMDGPU_RAS_ERROR__MULTI_UNCORRECTABLE,
- .sub_block_index = 0,
- .name = "",
- },
- .address = 0,
- .value = 0,
- };
+ if (!json_object_object_get_ex(block_obj, name, &item_obj))
+ return -1;
- if (amdgpu_ras_is_feature_enabled(i) <= 0)
- continue;
+ if (!json_object_object_get_ex(item_obj, "index", &index_obj))
+ return -1;
- if (!((1 << i) & ras_block_mask_inject))
- continue;
+ return json_object_get_int(index_obj); }
- data.inject = inject;
+static int _json_get_subblock_id(json_object *block_obj, const char *block_name,
+ const char *subblock_name)
+{
+ json_object *item_obj, *subblock_obj, *name_obj;
- ret = amdgpu_ras_query_err_count(i, &ue_old, &ce_old);
- CU_ASSERT_EQUAL(ret, 0);
+ if (!json_object_object_get_ex(block_obj, block_name, &item_obj))
+ return -1;
- if (ret)
- continue;
+ if (!json_object_object_get_ex(item_obj, "subblock", &subblock_obj))
+ return -1;
- ret = amdgpu_ras_invoke(&data);
+ if (!json_object_object_get_ex(subblock_obj, subblock_name, &name_obj))
+ return -1;
+
+ return json_object_get_int(name_obj);
+}
+
+static int amdgpu_ras_get_test_items(struct ras_test_item **pitems, int
+*size) {
+ json_object *root_obj = NULL;
+ json_object *block_obj = NULL;
+ json_object *type_obj = NULL;
+ json_object *tests_obj = NULL;
+ json_object *test_obj = NULL;
+ json_object *tmp_obj = NULL;
+ json_object *tmp_type_obj = NULL;
+ json_object *subblock_obj = NULL;
+ int i, length;
+ struct ras_test_item *items = NULL;
+ int ret = -1;
+
+ root_obj = json_object_from_file("./amdgpu_ras.json");
+ if (!root_obj)
+ root_obj = json_object_from_file(
+ "/usr/share/libdrm/amdgpu_ras.json");
+
+ if (!root_obj) {
+ CU_FAIL_FATAL("Couldn't find amdgpu_ras.json");
+ goto pro_end;
+ }
+
+ /* Check Version */
+ if (!json_object_object_get_ex(root_obj, "version", &tmp_obj)) {
+ CU_FAIL_FATAL("Wrong format of amdgpu_ras.json");
+ goto pro_end;
+ }
+
+ /* Block Definition */
+ if (!json_object_object_get_ex(root_obj, "block", &block_obj)) {
+ fprintf(stderr, "block isn't defined\n");
+ goto pro_end;
+ }
+
+ /* Type Definition */
+ if (!json_object_object_get_ex(root_obj, "type", &type_obj)) {
+ fprintf(stderr, "type isn't defined\n");
+ goto pro_end;
+ }
+
+ /* Enumulate test items */
+ if (!json_object_object_get_ex(root_obj, "tests", &tests_obj)) {
+ fprintf(stderr, "tests are empty\n");
+ goto pro_end;
+ }
+
+ length = json_object_array_length(tests_obj);
+
+ items = malloc(sizeof(struct ras_test_item) * length);
+ if (!items) {
+ fprintf(stderr, "malloc failed\n");
+ goto pro_end;
+ }
+
+ for (i = 0; i < length; i++) {
+ test_obj = json_object_array_get_idx(tests_obj, i);
+
+ /* Name */
+ if (!json_object_object_get_ex(test_obj, "name", &tmp_obj)) {
+ fprintf(stderr, "Test %d has no name\n", i);
+ goto pro_end;
+ }
+ strncpy(items[i].name, json_object_get_string(tmp_obj), 64);
+
+ /* block */
+ if (!json_object_object_get_ex(test_obj, "block", &tmp_obj)) {
+ fprintf(stderr, "Test:%s: block isn't defined\n",
+ items[i].name);
+ goto pro_end;
+ }
+ items[i].block = _json_get_block_id(
+ block_obj, json_object_get_string(tmp_obj));
+
+ /* check block id */
+ if (items[i].block < AMDGPU_RAS_BLOCK__UMC ||
[Tao] AMDGPU_RAS_BLOCK__START can be defined to replace AMDGPU_RAS_BLOCK__UMC
+ items[i].block >= AMDGPU_RAS_BLOCK__LAST) {
+ fprintf(stderr, "Test:%s: block id %d is invalid\n",
+ items[i].name, items[i].block);
+ goto pro_end;
+ }
+
+ /* subblock */
+ if (json_object_object_get_ex(test_obj, "subblock", &tmp_obj)) {
+ json_object_object_get_ex(test_obj, "block",
+ &subblock_obj);
+
+ items[i].sub_block = _json_get_subblock_id(
+ block_obj,
+ json_object_get_string(subblock_obj),
+ json_object_get_string(tmp_obj));
[Tao] It's better to check items[i].sub_block returned by _json_get_subblock_id and add a print.
+ } else
+ items[i].sub_block = 0;
+
+ /* type */
+ if (json_object_object_get_ex(test_obj, "type", &tmp_obj)) {
+ strncpy(items[i].error_type_str,
+ json_object_get_string(tmp_obj), 64);
+
+ if (json_object_object_get_ex(type_obj,
+ json_object_get_string(tmp_obj), &tmp_type_obj))
+ items[i].type = json_object_get_int(tmp_type_obj);
+ else
+ items[i].type = (enum amdgpu_ras_error_type)0;
+ }
+
+ /* address */
+ if (json_object_object_get_ex(test_obj, "address", &tmp_obj))
+ items[i].address = json_object_get_int(tmp_obj);
+ else
+ items[i].address = 0; /* default address 0 */
+
+ /* value */
+ if (json_object_object_get_ex(test_obj, "value", &tmp_obj))
+ items[i].value = json_object_get_int(tmp_obj);
+ else
+ items[i].value = 0; /* default value 0 */
+ }
+
+ *pitems = items;
+ *size = length;
+ ret = 0;
+pro_end:
+ if (root_obj)
+ json_object_put(root_obj);
+
+ return ret;
+}
+
+static void __amdgpu_ras_inject_test(void) {
+ struct ras_test_item *items = NULL;
+ int i, size;
+ int ret;
+ unsigned long old_ue, old_ce;
+ unsigned long ue, ce;
+ int timeout;
+ bool pass;
+
+ ret = amdgpu_ras_get_test_items(&items, &size);
+ CU_ASSERT_EQUAL(ret, 0);
+ if (ret)
+ goto mem_free;
+
+ printf("...\n");
+ for (i = 0; i < size; i++) {
+ timeout = 3;
+ pass = false;
+
+ ret = amdgpu_ras_query_err_count(items[i].block, &old_ue,
+ &old_ce);
CU_ASSERT_EQUAL(ret, 0);
+ if (ret)
+ break;
+ ret = amdgpu_ras_inject(items[i].block, items[i].sub_block,
+ items[i].type, items[i].address,
+ items[i].value);
+ CU_ASSERT_EQUAL(ret, 0);
if (ret)
- continue;
+ break;
-loop:
while (timeout > 0) {
- ret = amdgpu_ras_query_err_count(i, &ue, &ce);
- CU_ASSERT_EQUAL(ret, 0);
+ sleep(5);
+ ret = amdgpu_ras_query_err_count(items[i].block, &ue,
+ &ce);
+ CU_ASSERT_EQUAL(ret, 0);
if (ret)
- continue;
- if (ue_old != ue) {
- /*recovery takes ~10s*/
- sleep(10);
break;
- }
- sleep(1);
+ if (old_ue != ue || old_ce != ce) {
+ pass = true;
+ sleep(20);
+ break;
+ }
timeout -= 1;
}
+ printf("\t Test %s@%s, address %ld, value %ld: %s\n",
+ items[i].name, items[i].error_type_str, items[i].address,
+ items[i].value, pass ? "Pass" : "Fail");
+ }
- CU_ASSERT_EQUAL(ue_old + 1, ue);
- CU_ASSERT_EQUAL(ce_old, ce);
+mem_free:
+ if (items) {
+ free(items);
+ items = NULL;
}
}
--
2.17.1
_______________________________________________
amd-gfx mailing list
amd-gfx@xxxxxxxxxxxxxxxxxxxxx
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
_______________________________________________
amd-gfx mailing list
amd-gfx@xxxxxxxxxxxxxxxxxxxxx
https://lists.freedesktop.org/mailman/listinfo/amd-gfx
