From patchwork Thu Oct 27 15:35:38 2016 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 8bit X-Patchwork-Submitter: akash.goel@intel.com X-Patchwork-Id: 9399719 Return-Path: Received: from mail.wl.linuxfoundation.org (pdx-wl-mail.web.codeaurora.org [172.30.200.125]) by pdx-korg-patchwork.web.codeaurora.org (Postfix) with ESMTP id 79547600BA for ; Thu, 27 Oct 2016 15:17:37 +0000 (UTC) Received: from mail.wl.linuxfoundation.org (localhost [127.0.0.1]) by mail.wl.linuxfoundation.org (Postfix) with ESMTP id 61C362A2F5 for ; Thu, 27 Oct 2016 15:17:37 +0000 (UTC) Received: by mail.wl.linuxfoundation.org (Postfix, from userid 486) id 54BD62A2A7; Thu, 27 Oct 2016 15:17:37 +0000 (UTC) X-Spam-Checker-Version: SpamAssassin 3.3.1 (2010-03-16) on pdx-wl-mail.web.codeaurora.org X-Spam-Level: X-Spam-Status: No, score=-4.2 required=2.0 tests=BAYES_00, RCVD_IN_DNSWL_MED autolearn=ham version=3.3.1 Received: from gabe.freedesktop.org (gabe.freedesktop.org [131.252.210.177]) (using TLSv1.2 with cipher DHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by mail.wl.linuxfoundation.org (Postfix) with ESMTPS id 7277C2A2A7 for ; Thu, 27 Oct 2016 15:17:32 +0000 (UTC) Received: from gabe.freedesktop.org (localhost [127.0.0.1]) by gabe.freedesktop.org (Postfix) with ESMTP id 035EB6E265; Thu, 27 Oct 2016 15:17:32 +0000 (UTC) X-Original-To: intel-gfx@lists.freedesktop.org Delivered-To: intel-gfx@lists.freedesktop.org Received: from mga06.intel.com (mga06.intel.com [134.134.136.31]) by gabe.freedesktop.org (Postfix) with ESMTPS id 4B4D56E265 for ; Thu, 27 Oct 2016 15:17:31 +0000 (UTC) Received: from fmsmga001.fm.intel.com ([10.253.24.23]) by orsmga104.jf.intel.com with ESMTP; 27 Oct 2016 08:17:30 -0700 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos; i="5.31,553,1473145200"; d="scan'208"; a="1060103098" Received: from akashgoe-desktop.iind.intel.com ([10.223.82.36]) by fmsmga001.fm.intel.com with ESMTP; 27 Oct 2016 08:17:28 -0700 From: akash.goel@intel.com To: intel-gfx@lists.freedesktop.org Date: Thu, 27 Oct 2016 21:05:38 +0530 Message-Id: <1477582538-23502-1-git-send-email-akash.goel@intel.com> X-Mailer: git-send-email 1.9.2 In-Reply-To: <1458635856-4737-1-git-send-email-akash.goel@intel.com> References: <1458635856-4737-1-git-send-email-akash.goel@intel.com> MIME-Version: 1.0 Cc: Akash Goel Subject: [Intel-gfx] [PATCH v9] igt/gem_trtt: Exercise the TRTT hardware X-BeenThere: intel-gfx@lists.freedesktop.org X-Mailman-Version: 2.1.18 Precedence: list List-Id: Intel graphics driver community testing & development List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: intel-gfx-bounces@lists.freedesktop.org Sender: "Intel-gfx" X-Virus-Scanned: ClamAV using ClamSMTP From: Akash Goel This patch provides the testcase to exercise the TRTT hardware. Some platforms have an additional address translation hardware support in form of Tiled Resource Translation Table (TR-TT) which provides an extra level of abstraction over PPGTT. This is useful for mapping Sparse/Tiled texture resources. TR-TT is tightly coupled with PPGTT, a new instance of TR-TT will be required for a new PPGTT instance, but TR-TT may not enabled for every context. 1/16th of the 48bit PPGTT space is earmarked for the translation by TR-TT, which such chunk to use is conveyed to HW through a register. Any GFX address, which lies in that reserved 44 bit range will be translated through TR-TT first and then through PPGTT to get the actual physical address. TRTT is constructed as a 3 level tile Table. Each tile is 64KB is size which leaves behind 44-16=28 address bits. 28bits are partitioned as 9+9+10, and each level is contained within a 4KB page hence L3 and L2 is composed of 512 64b entries and L1 is composed of 1024 32b entries. There is a provision to keep TR-TT Tables in virtual space, where the pages of TRTT tables will be mapped to PPGTT. This is the adopted mode, as in this mode UMD will have a full control on TR-TT management, with bare minimum support from KMD. So the entries of L3 table will contain the PPGTT offset of L2 Table pages, similarly entries of L2 table will contain the PPGTT offset of L1 Table pages. The entries of L1 table will contain the PPGTT offset of BOs actually backing the Sparse resources. I915_GEM_CONTEXT_SETPARAM ioctl is used to request KMD to enable TRTT for a certain context, a new I915_CONTEXT_PARAM_ENABLE_TRTT param has been added to the CONTEXT_SETPARAM ioctl for that purpose. v2: - Add new wrapper function __gem_context_require_param and used that to detect the TR-TT support - Use igt_main macro, rename certain function, remove extra white space, cleanup the code (Chris) - Enhance the basic subtest to exercise all possible TR-TT segment start locations (i.e. 16 of them) & for every iteration create a new context. v3: - Get rid of some superfluous local variables (Chris) - Add asserts to validate whether the GFX address used in MI_STORE_DATA_IMM command is in canonical form & is correctly aligned or not (Chris) - Remove clearing of errno in has_trtt_support function (Chris) - Use the 48B_ADDRESS flag for batch buffer BO also (Chris) - Rebased. v4: - Add new subtest for invalid settings. - Add new local function query_trtt to check the Driver state (Chris) - Add new helper function gem_uses_64b_ppgtt to detect 64bit PPGTT support - Remove local functions uses_full_ppgtt & has_softpin_support, instead use existing wrappers gem_has_softpin & gem_uses_64b_ppgtt (Chris). - Remove redundant bit masking in emit_store_xxx functions (Chris). v5: - Add 2 new subtests checking the forceful eviction of active/hanging objects overlapping with the TR-TT segment (Chris). - Move gen8_canonical_addr to igt_aux as its needed by other tests also, which does soft pinning, and not just gem_softpin (Michel) v6: - Allow each subtest to have their own private drm file instance. - Update the basic subtest to check each segment location for both default and User created contexts (Chris). - Reorder igt_require(softpin/64b_ppgtt/trtt) to have trtt first (Chris). - Update the invalid subtest to check for the improper value of Null & Invalid tiles. v7: - Add interruptible version of the 2 eviction subtests (Chris) - Correct the alignment check for the MI Store qword command (Chris). v8: - Use new igt_interruptible macro for the interruptible subtests, as its more effective & precise. - Remove interruptible version of evict_hang subtest, as it doesn't provide any additional coverage (Chris) - Rebased. v9: - Rebased. Cc: Chris Wilson Signed-off-by: Michel Thierry Signed-off-by: Akash Goel Reviewed-by: Michel Thierry (v5) --- lib/igt_aux.c | 11 + lib/igt_aux.h | 1 + lib/igt_gt.h | 1 + lib/ioctl_wrappers.c | 39 ++- lib/ioctl_wrappers.h | 3 + tests/Makefile.sources | 1 + tests/gem_softpin.c | 18 +- tests/gem_trtt.c | 630 +++++++++++++++++++++++++++++++++++++++++++++++++ 8 files changed, 681 insertions(+), 23 deletions(-) create mode 100644 tests/gem_trtt.c diff --git a/lib/igt_aux.c b/lib/igt_aux.c index 421f6d4..9cb4666 100644 --- a/lib/igt_aux.c +++ b/lib/igt_aux.c @@ -487,6 +487,17 @@ void igt_exchange_int(void *array, unsigned i, unsigned j) int_arr[j] = tmp; } +/* igt_canonical_addr + * Used to convert any address into canonical form, i.e. [63:48] == [47]. + * Based on kernel's sign_extend64 implementation. + * @address - a virtual address +*/ +uint64_t igt_canonical_addr(uint64_t address) +{ + __u8 shift = 63 - GEN8_HIGH_ADDRESS_BIT; + return (__s64)(address << shift) >> shift; +} + /** * igt_permute_array: * @array: pointer to array diff --git a/lib/igt_aux.h b/lib/igt_aux.h index d30196b..3c55152 100644 --- a/lib/igt_aux.h +++ b/lib/igt_aux.h @@ -106,6 +106,7 @@ void igt_permute_array(void *array, unsigned size, void igt_progress(const char *header, uint64_t i, uint64_t total); void igt_print_activity(void); bool igt_check_boolean_env_var(const char *env_var, bool default_value); +uint64_t igt_canonical_addr(uint64_t address); bool igt_aub_dump_enabled(void); diff --git a/lib/igt_gt.h b/lib/igt_gt.h index 8d6c573..45f0f18 100644 --- a/lib/igt_gt.h +++ b/lib/igt_gt.h @@ -78,5 +78,6 @@ extern const struct intel_execution_engine { e__++) \ for_if (gem_has_ring(fd, flags__ = e__->exec_id | e__->flags)) +#define GEN8_HIGH_ADDRESS_BIT 47 #endif /* IGT_GT_H */ diff --git a/lib/ioctl_wrappers.c b/lib/ioctl_wrappers.c index 95bc5e2..763eb4d 100644 --- a/lib/ioctl_wrappers.c +++ b/lib/ioctl_wrappers.c @@ -938,6 +938,22 @@ void gem_context_set_param(int fd, struct local_i915_gem_context_param *p) igt_assert(__gem_context_set_param(fd, p) == 0); } +int __gem_context_require_param(int fd, uint64_t param) +{ + struct local_i915_gem_context_param p; + int ret; + + p.context = 0; + p.param = param; + p.value = 0; + p.size = 0; + + ret = igt_ioctl(fd, LOCAL_IOCTL_I915_GEM_CONTEXT_GETPARAM, &p); + if (ret) + return -errno; + return 0; +} + /** * gem_context_require_param: * @fd: open i915 drm file descriptor @@ -948,14 +964,7 @@ void gem_context_set_param(int fd, struct local_i915_gem_context_param *p) */ void gem_context_require_param(int fd, uint64_t param) { - struct local_i915_gem_context_param p; - - p.context = 0; - p.param = param; - p.value = 0; - p.size = 0; - - igt_require(igt_ioctl(fd, LOCAL_IOCTL_I915_GEM_CONTEXT_GETPARAM, &p) == 0); + igt_require(__gem_context_require_param(fd, param) == 0); } void gem_context_require_ban_period(int fd) @@ -1112,6 +1121,20 @@ bool gem_uses_full_ppgtt(int fd) } /** + * gem_uses_64b_ppgtt: + * @fd: open i915 drm file descriptor + * + * Feature test macro to check whether the kernel internally uses full + * 64b per-process gtt to execute batches. + * + * Returns: Whether batches are run through full 64b ppgtt. + */ +bool gem_uses_64b_ppgtt(int fd) +{ + return gem_gtt_type(fd) > 2; +} + +/** * gem_available_fences: * @fd: open i915 drm file descriptor * diff --git a/lib/ioctl_wrappers.h b/lib/ioctl_wrappers.h index 465f760..775c098 100644 --- a/lib/ioctl_wrappers.h +++ b/lib/ioctl_wrappers.h @@ -120,9 +120,11 @@ struct local_i915_gem_context_param { #define LOCAL_CONTEXT_PARAM_NO_ZEROMAP 0x2 #define LOCAL_CONTEXT_PARAM_GTT_SIZE 0x3 #define LOCAL_CONTEXT_PARAM_NO_ERROR_CAPTURE 0x4 +#define LOCAL_CONTEXT_PARAM_TRTT 0x5 uint64_t value; }; void gem_context_require_ban_period(int fd); +int __gem_context_require_param(int fd, uint64_t param); void gem_context_require_param(int fd, uint64_t param); void gem_context_get_param(int fd, struct local_i915_gem_context_param *p); void gem_context_set_param(int fd, struct local_i915_gem_context_param *p); @@ -155,6 +157,7 @@ bool gem_has_bsd2(int fd); int gem_gtt_type(int fd); bool gem_uses_ppgtt(int fd); bool gem_uses_full_ppgtt(int fd); +bool gem_uses_64b_ppgtt(int fd); int gem_available_fences(int fd); uint64_t gem_total_mappable_size(int fd); uint64_t gem_total_stolen_size(int fd); diff --git a/tests/Makefile.sources b/tests/Makefile.sources index 6d081c3..211fb2e 100644 --- a/tests/Makefile.sources +++ b/tests/Makefile.sources @@ -81,6 +81,7 @@ TESTS_progs_M = \ gem_streaming_writes \ gem_tiled_blits \ gem_tiled_partial_pwrite_pread \ + gem_trtt \ gem_userptr_blits \ gem_write_read_ring_switch \ gvt_basic \ diff --git a/tests/gem_softpin.c b/tests/gem_softpin.c index ea162c8..bd3631f 100644 --- a/tests/gem_softpin.c +++ b/tests/gem_softpin.c @@ -31,18 +31,6 @@ #define EXEC_OBJECT_PINNED (1<<4) #define EXEC_OBJECT_SUPPORTS_48B_ADDRESS (1<<3) -/* gen8_canonical_addr - * Used to convert any address into canonical form, i.e. [63:48] == [47]. - * Based on kernel's sign_extend64 implementation. - * @address - a virtual address -*/ -#define GEN8_HIGH_ADDRESS_BIT 47 -static uint64_t gen8_canonical_addr(uint64_t address) -{ - __u8 shift = 63 - GEN8_HIGH_ADDRESS_BIT; - return (__s64)(address << shift) >> shift; -} - static void test_invalid(int fd) { const uint32_t bbe = MI_BATCH_BUFFER_END; @@ -70,7 +58,7 @@ static void test_invalid(int fd) /* Check beyond bounds of aperture */ object.offset = gem_aperture_size(fd) - 4096; - object.offset = gen8_canonical_addr(object.offset); + object.offset = igt_canonical_addr(object.offset); igt_assert_eq(__gem_execbuf(fd, &execbuf), -EINVAL); /* Check gen8 canonical addressing */ @@ -78,7 +66,7 @@ static void test_invalid(int fd) object.offset = 1ull << GEN8_HIGH_ADDRESS_BIT; igt_assert_eq(__gem_execbuf(fd, &execbuf), -EINVAL); - object.offset = gen8_canonical_addr(object.offset); + object.offset = igt_canonical_addr(object.offset); igt_assert_eq(__gem_execbuf(fd, &execbuf), 0); } @@ -88,7 +76,7 @@ static void test_invalid(int fd) object.offset = 1ull<<32; igt_assert_eq(__gem_execbuf(fd, &execbuf), -EINVAL); - object.offset = gen8_canonical_addr(object.offset); + object.offset = igt_canonical_addr(object.offset); object.flags |= EXEC_OBJECT_SUPPORTS_48B_ADDRESS; igt_assert_eq(__gem_execbuf(fd, &execbuf), 0); } diff --git a/tests/gem_trtt.c b/tests/gem_trtt.c new file mode 100644 index 0000000..81816a1 --- /dev/null +++ b/tests/gem_trtt.c @@ -0,0 +1,630 @@ +/* + * Copyright © 2016 Intel Corporation + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the "Software"), + * to deal in the Software without restriction, including without limitation + * the rights to use, copy, modify, merge, publish, distribute, sublicense, + * and/or sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice (including the next + * paragraph) shall be included in all copies or substantial portions of the + * Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER + * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING + * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS + * IN THE SOFTWARE. + * + * Authors: + * Akash Goel + * + */ + +#include "igt.h" + +#define BO_SIZE 4096 +#define EXEC_OBJECT_PINNED (1<<4) +#define EXEC_OBJECT_SUPPORTS_48B_ADDRESS (1<<3) + +/* has_trtt_support + * Finds if trtt hw is present + * @fd DRM fd + */ +static bool has_trtt_support(int fd) +{ + int ret = __gem_context_require_param(fd, LOCAL_CONTEXT_PARAM_TRTT); + + return (ret == 0); +} + +/* mmap_bo + * helper for creating a CPU mmapping of the buffer + * @fd - drm fd + * @handle - handle of the buffer to mmap + * @size: size of the buffer + */ +static void* mmap_bo(int fd, uint32_t handle, uint64_t size) +{ + uint32_t *ptr = gem_mmap__cpu(fd, handle, 0, size, PROT_READ); + gem_set_domain(fd, handle, I915_GEM_DOMAIN_CPU, 0); + return ptr; +} + +/* emit_store_dword + * populate batch buffer with MI_STORE_DWORD_IMM command + * @fd: drm file descriptor + * @cmd_buf: batch buffer + * @dw_offset: write offset in batch buffer + * @vaddr: destination Virtual address + * @data: u32 data to be stored at destination + */ +static int emit_store_dword(int fd, uint32_t *cmd_buf, uint32_t dw_offset, + uint64_t vaddr, uint32_t data) +{ + /* Check that softpin addresses are in the correct form */ + igt_assert_eq_u64(vaddr, igt_canonical_addr(vaddr)); + + /* SDI cannot write to unaligned addresses */ + igt_assert((vaddr & 3) == 0); + + cmd_buf[dw_offset++] = MI_STORE_DWORD_IMM; + cmd_buf[dw_offset++] = (uint32_t)vaddr; + cmd_buf[dw_offset++] = (uint32_t)(vaddr >> 32); + cmd_buf[dw_offset++] = data; + + return dw_offset; +} + +/* emit_store_qword + * populate batch buffer with MI_STORE_DWORD_IMM command + * @fd: drm file descriptor + * @cmd_buf: batch buffer + * @dw_offset: write offset in batch buffer + * @vaddr: destination Virtual address + * @data: u64 data to be stored at destination + */ +static int emit_store_qword(int fd, uint32_t *cmd_buf, uint32_t dw_offset, + uint64_t vaddr, uint64_t data) +{ + /* Check that softpin addresses are in the correct form */ + igt_assert_eq_u64(vaddr, igt_canonical_addr(vaddr)); + + /* SDI cannot write to unaligned addresses */ + igt_assert((vaddr & 7) == 0); + + cmd_buf[dw_offset++] = MI_STORE_DWORD_IMM | 0x3; + cmd_buf[dw_offset++] = (uint32_t)vaddr; + cmd_buf[dw_offset++] = (uint32_t)(vaddr >> 32); + cmd_buf[dw_offset++] = data; + cmd_buf[dw_offset++] = data >> 32; + + return dw_offset; +} + +/* emit_bb_end + * populate batch buffer with MI_BATCH_BUFFER_END command + * @fd: drm file descriptor + * @cmd_buf: batch buffer + * @dw_offset: write offset in batch buffer + */ +static int emit_bb_end(int fd, uint32_t *cmd_buf, uint32_t dw_offset) +{ + dw_offset = ALIGN(dw_offset, 2); + cmd_buf[dw_offset++] = MI_BATCH_BUFFER_END; + dw_offset++; + + return dw_offset; +} + +/* setup_execbuffer + * helper for buffer execution + * @execbuf - pointer to execbuffer + * @exec_object - pointer to exec object2 struct + * @ring - ring to be used + * @buffer_count - how manu buffers to submit + * @batch_length - length of batch buffer + */ +static void setup_execbuffer(struct drm_i915_gem_execbuffer2 *execbuf, + struct drm_i915_gem_exec_object2 *exec_object, + uint32_t ctx_id, int ring, int buffer_count, int batch_length) +{ + memset(execbuf, 0, sizeof(*execbuf)); + + execbuf->buffers_ptr = (unsigned long)exec_object; + execbuf->buffer_count = buffer_count; + execbuf->batch_len = batch_length; + execbuf->flags = ring; + i915_execbuffer2_set_context_id(*execbuf, ctx_id); +} + +#define TABLE_SIZE 0x1000 +#define TILE_SIZE 0x10000 + +#define TRTT_SEGMENT_SIZE (1ULL << 44) +#define PPGTT_SIZE (1ULL << 48) + +#define NULL_TILE_PATTERN 0xFFFFFFFF +#define INVALID_TILE_PATTERN 0xFFFFFFFE + +struct local_i915_gem_context_trtt_param { + uint64_t segment_base_addr; + uint64_t l3_table_address; + uint32_t invd_tile_val; + uint32_t null_tile_val; +}; + +/* query_trtt + * Helper function to check if the TR-TT settings stored with the KMD, + * for a context, have the expected values (set previously). + * @fd - drm fd + * @ctx_id - id of the context for which TRTT is to be enabled + * @l3_table_address - GFX address of the L3 table + * @segment_base_addr - offset of the TRTT segment in PPGTT space + */ +static void +query_trtt(int fd, uint32_t ctx_id, uint64_t l3_table_address, + uint64_t segment_base_addr) +{ + struct local_i915_gem_context_param ctx_param; + struct local_i915_gem_context_trtt_param trtt_param; + + ctx_param.context = ctx_id; + ctx_param.size = sizeof(trtt_param); + ctx_param.param = LOCAL_CONTEXT_PARAM_TRTT; + ctx_param.value = (uint64_t)&trtt_param; + + gem_context_get_param(fd, &ctx_param); + + igt_assert_eq_u64(trtt_param.l3_table_address, l3_table_address); + igt_assert_eq_u64(trtt_param.segment_base_addr, segment_base_addr); + igt_assert_eq_u32(trtt_param.invd_tile_val, INVALID_TILE_PATTERN); + igt_assert_eq_u32(trtt_param.null_tile_val, NULL_TILE_PATTERN); +} + +static int +__setup_trtt(int fd, uint32_t ctx_id, uint64_t l3_table_address, + uint64_t segment_base_addr, uint32_t null_tile_val, + uint32_t invd_tile_val) +{ + struct local_i915_gem_context_param ctx_param; + struct local_i915_gem_context_trtt_param trtt_param; + + trtt_param.null_tile_val = null_tile_val; + trtt_param.invd_tile_val = invd_tile_val; + trtt_param.l3_table_address = l3_table_address; + trtt_param.segment_base_addr = segment_base_addr; + + ctx_param.context = ctx_id; + ctx_param.size = sizeof(trtt_param); + ctx_param.param = LOCAL_CONTEXT_PARAM_TRTT; + ctx_param.value = (uint64_t)&trtt_param; + + return __gem_context_set_param(fd, &ctx_param); +} + +/* setup_trtt + * Helper function to request KMD to enable TRTT + * @fd - drm fd + * @ctx_id - id of the context for which TRTT is to be enabled + * @l3_table_address - GFX address of the L3 table + * @segment_base_addr - offset of the TRTT segment in PPGTT space + */ +static int +setup_trtt(int fd, uint32_t ctx_id, uint64_t l3_table_address, + uint64_t segment_base_addr) +{ + return __setup_trtt(fd, ctx_id, l3_table_address, segment_base_addr, + NULL_TILE_PATTERN, INVALID_TILE_PATTERN); +} + +/* bo_alloc_setup + * allocate bo and populate exec object + * @exec_object2 - pointer to exec object + * @bo_sizee - buffer size + * @flags - exec flags + * @bo_offset - pointer to the current PPGTT offset + */ +static void bo_alloc_setup(int fd, struct drm_i915_gem_exec_object2 *exec_object2, + uint64_t bo_size, uint64_t flags, uint64_t *bo_offset) +{ + memset(exec_object2, 0, sizeof(*exec_object2)); + exec_object2->handle = gem_create(fd, bo_size); + exec_object2->flags = flags; + + if (bo_offset) + { + exec_object2->offset = *bo_offset; + *bo_offset += bo_size; + } +} + +/* busy_batch + * This helper function will prepare & submit a batch on the BCS ring, + * which will keep the ring busy for sometime, long enough to submit + * some other work which can trigger the eviction of that batch object + * while it is still getting executed on the ring. + */ +static uint64_t busy_batch(int fd, uint32_t ctx_id) +{ + const int gen = intel_gen(intel_get_drm_devid(fd)); + const int has_64bit_reloc = gen >= 8; + struct drm_i915_gem_execbuffer2 execbuf; + struct drm_i915_gem_exec_object2 object[2]; + uint32_t *map; + int factor = 10; + int i = 0; + + /* Until the kernel ABI is fixed, only default contexts can be used + * on !RCS rings */ + igt_require(ctx_id == 0); + + memset(object, 0, sizeof(object)); + object[0].handle = gem_create(fd, 1024*1024); + object[1].handle = gem_create(fd, 4096); + map = gem_mmap__cpu(fd, object[1].handle, 0, 4096, PROT_WRITE); + gem_set_domain(fd, object[1].handle, + I915_GEM_DOMAIN_CPU, I915_GEM_DOMAIN_CPU); + + setup_execbuffer(&execbuf, object, ctx_id, I915_EXEC_BLT, 2, + emit_bb_end(fd, map, 0)*4); + gem_execbuf(fd, &execbuf); + + igt_debug("Active offsets = [%08llx, %08llx]\n", + object[0].offset, object[1].offset); + +#define COPY_BLT_CMD (2<<29|0x53<<22|0x6) +#define BLT_WRITE_ALPHA (1<<21) +#define BLT_WRITE_RGB (1<<20) + gem_set_domain(fd, object[1].handle, + I915_GEM_DOMAIN_CPU, I915_GEM_DOMAIN_CPU); + while (factor--) { + /* XY_SRC_COPY */ + map[i++] = COPY_BLT_CMD | BLT_WRITE_ALPHA | BLT_WRITE_RGB; + if (has_64bit_reloc) + map[i-1] += 2; + map[i++] = 0xcc << 16 | 1 << 25 | 1 << 24 | (4*1024); + map[i++] = 0; + map[i++] = 256 << 16 | 1024; + map[i++] = object[0].offset; + if (has_64bit_reloc) + map[i++] = object[0].offset >> 32; + map[i++] = 0; + map[i++] = 4096; + map[i++] = object[0].offset; + if (has_64bit_reloc) + map[i++] = object[0].offset >> 32; + } + i = emit_bb_end(fd, map, i); + munmap(map, 4096); + + object[0].flags = EXEC_OBJECT_PINNED | EXEC_OBJECT_WRITE; + object[1].flags = EXEC_OBJECT_PINNED; + execbuf.batch_len = i*4; + gem_execbuf(fd, &execbuf); + gem_close(fd, object[0].handle); + gem_close(fd, object[1].handle); + + return object[1].offset; +} + +/* active object eviction test + * This test will force the eviction of an active object, by choosing the + * TR-TT segment location which will overlap with the object's location. + */ +static void test_evict_active(void) +{ + int fd; + uint64_t expected; + uint64_t segment_base_addr; + uint64_t l3_offset; + + fd = drm_open_driver(DRIVER_INTEL); + + expected = busy_batch(fd, 0); + + /* Determine the segment_base_addr according to the offset of active + * buffer, forcing its eviction + */ + segment_base_addr = expected & (~(TRTT_SEGMENT_SIZE - 1)); + + /* Keep the l3 table outside the segment to avoid the conflict */ + l3_offset = segment_base_addr ? 0 : TRTT_SEGMENT_SIZE; + + igt_assert(setup_trtt(fd, 0, l3_offset, segment_base_addr) == 0); + + query_trtt(fd, 0, l3_offset, segment_base_addr); + close(fd); +} + +/* hanging object eviction test + * This test will force the eviction of a hanging object, by choosing the + * TR-TT segment location which will overlap with the object's location. + */ +static void test_evict_hang(void) +{ + int fd; + uint32_t ctx_id; + uint64_t segment_base_addr; + uint64_t l3_offset; + uint64_t expected; + + fd = drm_open_driver(DRIVER_INTEL); + ctx_id = gem_context_create(fd); + + igt_hang_ctx(fd, ctx_id, I915_EXEC_RENDER, 0, (uint64_t *)&expected); + + /* Determine the segment_base_addr according to the offset of hanging + * buffer, forcing its eviction + */ + segment_base_addr = expected & (~(TRTT_SEGMENT_SIZE - 1)); + + /* Keep the l3 table outside the segment to avoid the conflict */ + l3_offset = segment_base_addr ? 0 : TRTT_SEGMENT_SIZE; + + igt_assert(setup_trtt(fd, ctx_id, l3_offset, segment_base_addr) == 0); + + query_trtt(fd, ctx_id, l3_offset, segment_base_addr); + gem_context_destroy(fd, ctx_id); + close (fd); +} + +/* submit_trtt_context + * This helper function will create a new context if the TR-TT segment + * base address is not zero, allocate a L3 table page, 2 pages apiece + * for L2/L1 tables and couple of data buffers of 64KB in size, matching the + * Tile size. The 2 data buffers will be mapped to the 2 ends of TRTT virtual + * space. Series of MI_STORE_DWORD_IMM commands will be added in the batch + * buffer to first update the TR-TT table entries and then to update the data + * buffers using their TR-TT VA, exercising the table programming done + * previously. + * Invoke CONTEXT_SETPARAM ioctl to request KMD to enable TRTT. + * Invoke execbuffer to submit the batch buffer. + * Verify value of first DWORD in the 2 data buffer matches the data asked + * to be written by the GPU. + */ +static void submit_trtt_context(int fd, uint64_t segment_base_addr, uint32_t ctx_id) +{ + enum { + L3_TBL, + L2_TBL1, + L2_TBL2, + L1_TBL1, + L1_TBL2, + DATA1, + DATA2, + BATCH, + NUM_BUFFERS, + }; + + int ring, len = 0; + uint32_t *ptr; + struct drm_i915_gem_execbuffer2 execbuf; + struct drm_i915_gem_exec_object2 exec_object2[NUM_BUFFERS]; + uint32_t batch_buffer[BO_SIZE]; + uint32_t data, last_entry_offset; + uint64_t cur_ppgtt_off, exec_flags; + uint64_t first_tile_addr, last_tile_addr; + + first_tile_addr = segment_base_addr; + last_tile_addr = first_tile_addr + TRTT_SEGMENT_SIZE - TILE_SIZE; + + /* To avoid conflict with the TR-TT segment */ + cur_ppgtt_off = segment_base_addr ? 0 : TRTT_SEGMENT_SIZE; + + exec_flags = EXEC_OBJECT_SUPPORTS_48B_ADDRESS; + + /* first allocate Batch buffer BO */ + bo_alloc_setup(fd, &exec_object2[BATCH], BO_SIZE, exec_flags, NULL); + + /* table BOs and data buffer BOs are written by GPU and are soft pinned */ + exec_flags |= (EXEC_OBJECT_WRITE | EXEC_OBJECT_PINNED); + + /* Allocate a L3 table BO */ + bo_alloc_setup(fd, &exec_object2[L3_TBL], TABLE_SIZE, exec_flags, &cur_ppgtt_off); + + /* Allocate two L2 table BOs */ + bo_alloc_setup(fd, &exec_object2[L2_TBL1], TABLE_SIZE, exec_flags, &cur_ppgtt_off); + bo_alloc_setup(fd, &exec_object2[L2_TBL2], TABLE_SIZE, exec_flags, &cur_ppgtt_off); + + /* Allocate two L1 table BOs */ + bo_alloc_setup(fd, &exec_object2[L1_TBL1], TABLE_SIZE, exec_flags, &cur_ppgtt_off); + bo_alloc_setup(fd, &exec_object2[L1_TBL2], TABLE_SIZE, exec_flags, &cur_ppgtt_off); + + /* Align the PPGTT offsets for the 2 data buffers to next 64 KB boundary */ + cur_ppgtt_off = ALIGN(cur_ppgtt_off, TILE_SIZE); + + /* Allocate two Data buffer BOs */ + bo_alloc_setup(fd, &exec_object2[DATA1], TILE_SIZE, exec_flags, &cur_ppgtt_off); + bo_alloc_setup(fd, &exec_object2[DATA2], TILE_SIZE, exec_flags, &cur_ppgtt_off); + + /* Add commands to update the two L3 table entries to point them to the L2 tables*/ + last_entry_offset = 511*sizeof(uint64_t); + + len = emit_store_qword(fd, batch_buffer, len, + exec_object2[L3_TBL].offset, + exec_object2[L2_TBL1].offset); + + len = emit_store_qword(fd, batch_buffer, len, + exec_object2[L3_TBL].offset + last_entry_offset, + exec_object2[L2_TBL2].offset); + + /* Add commands to update an entry of 2 L2 tables to point them to the L1 tables*/ + len = emit_store_qword(fd, batch_buffer, len, + exec_object2[L2_TBL1].offset, + exec_object2[L1_TBL1].offset); + + len = emit_store_qword(fd, batch_buffer, len, + exec_object2[L2_TBL2].offset + last_entry_offset, + exec_object2[L1_TBL2].offset); + + /* Add commands to update an entry of 2 L1 tables to point them to the data buffers*/ + last_entry_offset = 1023*sizeof(uint32_t); + + len = emit_store_dword(fd, batch_buffer, len, + exec_object2[L1_TBL1].offset, + exec_object2[DATA1].offset >> 16); + + len = emit_store_dword(fd, batch_buffer, len, + exec_object2[L1_TBL2].offset + last_entry_offset, + exec_object2[DATA2].offset >> 16); + + /* Add commands to update the 2 data buffers, using their TRTT VA */ + data = 0x12345678; + len = emit_store_dword(fd, batch_buffer, len, + igt_canonical_addr(first_tile_addr), + data); + len = emit_store_dword(fd, batch_buffer, len, + igt_canonical_addr(last_tile_addr), + data); + + len = emit_bb_end(fd, batch_buffer, len); + gem_write(fd, exec_object2[BATCH].handle, 0, batch_buffer, len*4); + + /* Request KMD to setup the TR-TT */ + igt_assert(setup_trtt(fd, ctx_id, exec_object2[L3_TBL].offset, first_tile_addr) == 0); + + ring = I915_EXEC_RENDER; + setup_execbuffer(&execbuf, exec_object2, ctx_id, ring, NUM_BUFFERS, len*4); + + /* submit command buffer */ + gem_execbuf(fd, &execbuf); + + /* read the 2 data buffers to check for the value written by the GPU */ + ptr = mmap_bo(fd, exec_object2[DATA1].handle, TILE_SIZE); + igt_assert_eq_u32(ptr[0], data); + + ptr = mmap_bo(fd, exec_object2[DATA2].handle, TILE_SIZE); + igt_assert_eq_u32(ptr[0], data); + + gem_close(fd, exec_object2[L3_TBL].handle); + gem_close(fd, exec_object2[L2_TBL1].handle); + gem_close(fd, exec_object2[L2_TBL2].handle); + gem_close(fd, exec_object2[L1_TBL1].handle); + gem_close(fd, exec_object2[L1_TBL2].handle); + gem_close(fd, exec_object2[DATA1].handle); + gem_close(fd, exec_object2[DATA2].handle); + gem_close(fd, exec_object2[BATCH].handle); + + /* Check if the TRTT params stored with the Driver are intact or not */ + query_trtt(fd, ctx_id, exec_object2[L3_TBL].offset, first_tile_addr); +} + +/* basic trtt test + * This will test the basic TR-TT functionality by doing couple of store + * operations through it. Also it will exercise all possible TR-TT segment + * start locations (i.e. 16 of them) for both default & User created contexts. + */ +static void test_basic_trtt_use(void) +{ + int fd; + uint32_t ctx_id; + uint64_t segment_base_addr; + + for (segment_base_addr = 0; + segment_base_addr < PPGTT_SIZE; + segment_base_addr += TRTT_SEGMENT_SIZE) + { + /* In order to test the default context for all segment start + * locations, need to open a new file instance on every iteration + * as TRTT settings are immutable once set for a context. + */ + fd = drm_open_driver(DRIVER_INTEL); + + submit_trtt_context(fd, segment_base_addr, 0); + + ctx_id = gem_context_create(fd); + submit_trtt_context(fd, segment_base_addr, ctx_id); + gem_context_destroy(fd, ctx_id); + + close(fd); + } +} + +static void test_invalid(void) +{ + int fd; + uint32_t ctx_id; + uint64_t segment_base_addr; + uint64_t l3_offset; + + fd = drm_open_driver(DRIVER_INTEL); + ctx_id = gem_context_create(fd); + + /* Check for an incorrectly aligned base location for TR-TT segment */ + segment_base_addr = TRTT_SEGMENT_SIZE + 0x1000; + l3_offset = TILE_SIZE; + igt_assert_eq(setup_trtt(fd, ctx_id, l3_offset, segment_base_addr), -EINVAL); + + /* Correct the segment_base_addr value */ + segment_base_addr = TRTT_SEGMENT_SIZE; + + /* Check for the same/conflicting value for L3 table and TR-TT segment location */ + l3_offset = segment_base_addr; + igt_assert_eq(setup_trtt(fd, ctx_id, l3_offset, segment_base_addr), -EINVAL); + + /* Check for an incorrectly aligned location for L3 table */ + l3_offset = TILE_SIZE + 0x1000; + igt_assert_eq(setup_trtt(fd, ctx_id, l3_offset, segment_base_addr), -EINVAL); + + /* Correct the l3_offset value */ + l3_offset = TILE_SIZE; + + /* Check for the same value for Null & Invalid tile patterns */ + igt_assert_eq(__setup_trtt(fd, ctx_id, l3_offset, segment_base_addr, + NULL_TILE_PATTERN, NULL_TILE_PATTERN), -EINVAL); + + /* Use the correct settings now */ + igt_assert(setup_trtt(fd, ctx_id, l3_offset, segment_base_addr) == 0); + /* Check the overriding of TR-TT settings for the same context */ + segment_base_addr += TRTT_SEGMENT_SIZE; + l3_offset += TILE_SIZE; + igt_assert_eq(setup_trtt(fd, ctx_id, l3_offset, segment_base_addr), -EEXIST); + + gem_context_destroy(fd, ctx_id); + close(fd); +} + +igt_main +{ + int fd = -1; + + igt_fixture { + fd = drm_open_driver(DRIVER_INTEL); + + igt_require(has_trtt_support(fd)); + /* test also needs 48 PPGTT & Soft Pin support */ + igt_require(gem_has_softpin(fd)); + igt_require(gem_uses_64b_ppgtt(fd)); + } + + /* Each subtest will open its own private file instance to avoid + * any interference. Otherwise once TRTT is enabled for the default + * context with segment_base_addr value of 0, all the other tests which + * are implicitly done, such as quiescent_gpu, will break as they only + * use the default context and do not use the 48B_ADDRESS flag for it. + */ + + igt_subtest("invalid") + test_invalid(); + + igt_subtest("basic") + test_basic_trtt_use(); + + igt_subtest("evict_active") + test_evict_active(); + + igt_subtest("evict_hang") + test_evict_hang(); + + igt_subtest("evict_active-interruptible") + igt_while_interruptible(true) test_evict_active(); + + igt_fixture + close(fd); +} +