From: Bommu Krishnaiah <krishnaiah.bommu@intel.com>
To: igt-dev@lists.freedesktop.org
Cc: Bommu Krishnaiah <krishnaiah.bommu@intel.com>,
Oak Zeng <oak.zeng@intel.com>,
Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com>
Subject: [PATCH i-g-t v2 07/10] tests/intel/xe_svm: svm-invalid-va
Date: Tue, 14 May 2024 12:40:23 +0530 [thread overview]
Message-ID: <20240514071026.748257-8-krishnaiah.bommu@intel.com> (raw)
In-Reply-To: <20240514071026.748257-1-krishnaiah.bommu@intel.com>
Verify SVM functionality while accessing invalid address
Signed-off-by: Bommu Krishnaiah <krishnaiah.bommu@intel.com>
Cc: Oak Zeng <oak.zeng@intel.com>
Cc: Himal Prasad Ghimiray <himal.prasad.ghimiray@intel.com>
---
tests/intel/xe_svm.c | 34 ++++++++++++++++++++++++++++++++++
1 file changed, 34 insertions(+)
diff --git a/tests/intel/xe_svm.c b/tests/intel/xe_svm.c
index 421d7fd1a..b846ca71a 100644
--- a/tests/intel/xe_svm.c
+++ b/tests/intel/xe_svm.c
@@ -32,6 +32,8 @@
* Description: verify SVM basic functionality by using huge page access
* SUBTEST: svm-atomic-access
* Description: verify SVM basic functionality by using GPU atomic access any location in malloc'ed memory
+ * SUBTEST: svm_invalid_va
+ * Description: verify SVM functionality while accessing invalid address
*/
#include <fcntl.h>
@@ -224,6 +226,34 @@ static void svm_atomic_access(int fd, uint32_t vm, struct drm_xe_engine_class_in
free(dst);
}
+/**
+ * Submit a GPU command to access an invalid address.
+ * Driver should detect a catstrophic error.
+ */
+static void svm_invalid_va(int fd, uint32_t vm, struct drm_xe_engine_class_instance *eci)
+{
+ uint64_t gpu_va = 0x1a0000;
+ size_t bo_size = xe_bb_size(fd, PAGE_ALIGN_UFENCE);
+ uint32_t *dst;
+
+ struct xe_buffer cmd_buf = {
+ .fd = fd,
+ .gpu_addr = (void *)(uintptr_t)gpu_va,
+ .vm = vm,
+ .size = bo_size,
+ .placement = vram_if_possible(fd, eci->gt_id),
+ .flag = DRM_XE_GEM_CREATE_FLAG_NEEDS_VISIBLE_VRAM
+ };
+
+ dst = (uint32_t *)0x1fffffffffff000;
+
+ xe_create_cmdbuf(&cmd_buf, insert_store, (uint64_t)dst, 0xc0ffee, eci);
+ igt_assert_eq(__xe_submit_cmd(&cmd_buf), -EIO); // for invalid address __xe_wait_ufence will return -EIO
+
+ xe_destroy_cmdbuf(&cmd_buf);
+ free(dst);
+}
+
igt_main
{
int fd;
@@ -262,6 +292,10 @@ igt_main
xe_for_each_engine(fd, hwe)
svm_atomic_access(fd, vm, hwe);
+ igt_subtest_f("svm-invalid-va")
+ xe_for_each_engine(fd, hwe)
+ svm_invalid_va(fd, vm, hwe);
+
igt_fixture {
xe_vm_destroy(fd, vm);
drm_close_driver(fd);
--
2.25.1
next prev parent reply other threads:[~2024-05-14 7:10 UTC|newest]
Thread overview: 16+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-05-14 7:10 [PATCH i-g-t v2 00/10] helper function Bommu Krishnaiah
2024-05-14 7:10 ` [PATCH i-g-t v2 01/10] lib/xe/xe_util: Introduce helper functions for buffer creation and command submission etc Bommu Krishnaiah
2024-05-14 7:10 ` [PATCH i-g-t v2 02/10] tests/intel/xe_svm: basic xe_svm test Bommu Krishnaiah
2024-05-14 7:10 ` [PATCH i-g-t v2 03/10] tests/xe_svm: basic svm test Bommu Krishnaiah
2024-05-15 17:38 ` Kamil Konieczny
2024-05-14 7:10 ` [PATCH i-g-t v2 04/10] tests/intel/xe_svm: svm_random_access Bommu Krishnaiah
2024-05-14 7:10 ` [PATCH i-g-t v2 05/10] tests/intel/xe_svm: svm-huge-page Bommu Krishnaiah
2024-05-14 7:10 ` [PATCH i-g-t v2 06/10] tests/intel/xe_svm: svm_atomic_access Bommu Krishnaiah
2024-05-14 8:14 ` Lisovskiy, Stanislav
2024-05-14 7:10 ` Bommu Krishnaiah [this message]
2024-05-14 7:10 ` [PATCH i-g-t v2 08/10] tests/intel/xe_svm: svm_benchmark Bommu Krishnaiah
2024-05-14 7:10 ` [PATCH i-g-t v2 09/10] tests/intel/xe_svm: svm_mprotect Bommu Krishnaiah
2024-05-14 7:10 ` [PATCH i-g-t v2 10/10] tests/intel/xe_svm: svm-sparse-access Bommu Krishnaiah
2024-05-14 7:52 ` ✗ Fi.CI.BUILD: failure for helper function (rev2) Patchwork
2024-05-14 7:58 ` ✗ GitLab.Pipeline: warning " Patchwork
2024-05-15 17:29 ` [PATCH i-g-t v2 00/10] helper function Kamil Konieczny
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20240514071026.748257-8-krishnaiah.bommu@intel.com \
--to=krishnaiah.bommu@intel.com \
--cc=himal.prasad.ghimiray@intel.com \
--cc=igt-dev@lists.freedesktop.org \
--cc=oak.zeng@intel.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox