linux/drivers/gpu/drm/i915/intel_guc_loader.c

694 lines
20 KiB
C
Raw Normal View History

/*
* Copyright © 2014 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:
* Vinit Azad <vinit.azad@intel.com>
* Ben Widawsky <ben@bwidawsk.net>
* Dave Gordon <david.s.gordon@intel.com>
* Alex Dai <yu.dai@intel.com>
*/
#include <linux/firmware.h>
#include "i915_drv.h"
#include "intel_guc.h"
/**
* DOC: GuC-specific firmware loader
*
* intel_guc:
* Top level structure of guc. It handles firmware loading and manages client
* pool and doorbells. intel_guc owns a i915_guc_client to replace the legacy
* ExecList submission.
*
* Firmware versioning:
* The firmware build process will generate a version header file with major and
* minor version defined. The versions are built into CSS header of firmware.
* i915 kernel driver set the minimal firmware version required per platform.
* The firmware installation package will install (symbolic link) proper version
* of firmware.
*
* GuC address space:
* GuC does not allow any gfx GGTT address that falls into range [0, WOPCM_TOP),
* which is reserved for Boot ROM, SRAM and WOPCM. Currently this top address is
* 512K. In order to exclude 0-512K address space from GGTT, all gfx objects
* used by GuC is pinned with PIN_OFFSET_BIAS along with size of WOPCM.
*
* Firmware log:
* Firmware log is enabled by setting i915.guc_log_level to non-negative level.
* Log data is printed out via reading debugfs i915_guc_log_dump. Reading from
* i915_guc_load_status will print out firmware loading status and scratch
* registers value.
*
*/
#define I915_SKL_GUC_UCODE "i915/skl_guc_ver6.bin"
MODULE_FIRMWARE(I915_SKL_GUC_UCODE);
/* User-friendly representation of an enum */
const char *intel_guc_fw_status_repr(enum intel_guc_fw_status status)
{
switch (status) {
case GUC_FIRMWARE_FAIL:
return "FAIL";
case GUC_FIRMWARE_NONE:
return "NONE";
case GUC_FIRMWARE_PENDING:
return "PENDING";
case GUC_FIRMWARE_SUCCESS:
return "SUCCESS";
default:
return "UNKNOWN!";
}
};
static void direct_interrupts_to_host(struct drm_i915_private *dev_priv)
{
struct intel_engine_cs *engine;
int irqs;
/* tell all command streamers NOT to forward interrupts and vblank to GuC */
irqs = _MASKED_FIELD(GFX_FORWARD_VBLANK_MASK, GFX_FORWARD_VBLANK_NEVER);
irqs |= _MASKED_BIT_DISABLE(GFX_INTERRUPT_STEERING);
for_each_engine(engine, dev_priv)
I915_WRITE(RING_MODE_GEN7(engine), irqs);
/* route all GT interrupts to the host */
I915_WRITE(GUC_BCS_RCS_IER, 0);
I915_WRITE(GUC_VCS2_VCS1_IER, 0);
I915_WRITE(GUC_WD_VECS_IER, 0);
}
static void direct_interrupts_to_guc(struct drm_i915_private *dev_priv)
{
struct intel_engine_cs *engine;
int irqs;
/* tell all command streamers to forward interrupts and vblank to GuC */
irqs = _MASKED_FIELD(GFX_FORWARD_VBLANK_MASK, GFX_FORWARD_VBLANK_ALWAYS);
irqs |= _MASKED_BIT_ENABLE(GFX_INTERRUPT_STEERING);
for_each_engine(engine, dev_priv)
I915_WRITE(RING_MODE_GEN7(engine), irqs);
/* route USER_INTERRUPT to Host, all others are sent to GuC. */
irqs = GT_RENDER_USER_INTERRUPT << GEN8_RCS_IRQ_SHIFT |
GT_RENDER_USER_INTERRUPT << GEN8_BCS_IRQ_SHIFT;
/* These three registers have the same bit definitions */
I915_WRITE(GUC_BCS_RCS_IER, ~irqs);
I915_WRITE(GUC_VCS2_VCS1_IER, ~irqs);
I915_WRITE(GUC_WD_VECS_IER, ~irqs);
}
static u32 get_gttype(struct drm_i915_private *dev_priv)
{
/* XXX: GT type based on PCI device ID? field seems unused by fw */
return 0;
}
static u32 get_core_family(struct drm_i915_private *dev_priv)
{
switch (INTEL_INFO(dev_priv)->gen) {
case 9:
return GFXCORE_FAMILY_GEN9;
default:
DRM_ERROR("GUC: unsupported core family\n");
return GFXCORE_FAMILY_UNKNOWN;
}
}
static void set_guc_init_params(struct drm_i915_private *dev_priv)
{
struct intel_guc *guc = &dev_priv->guc;
u32 params[GUC_CTL_MAX_DWORDS];
int i;
memset(&params, 0, sizeof(params));
params[GUC_CTL_DEVICE_INFO] |=
(get_gttype(dev_priv) << GUC_CTL_GTTYPE_SHIFT) |
(get_core_family(dev_priv) << GUC_CTL_COREFAMILY_SHIFT);
/*
* GuC ARAT increment is 10 ns. GuC default scheduler quantum is one
* second. This ARAR is calculated by:
* Scheduler-Quantum-in-ns / ARAT-increment-in-ns = 1000000000 / 10
*/
params[GUC_CTL_ARAT_HIGH] = 0;
params[GUC_CTL_ARAT_LOW] = 100000000;
params[GUC_CTL_WA] |= GUC_CTL_WA_UK_BY_DRIVER;
params[GUC_CTL_FEATURE] |= GUC_CTL_DISABLE_SCHEDULER |
GUC_CTL_VCS2_ENABLED;
if (i915.guc_log_level >= 0) {
params[GUC_CTL_LOG_PARAMS] = guc->log_flags;
params[GUC_CTL_DEBUG] =
i915.guc_log_level << GUC_LOG_VERBOSITY_SHIFT;
}
if (guc->ads_obj) {
u32 ads = (u32)i915_gem_obj_ggtt_offset(guc->ads_obj)
>> PAGE_SHIFT;
params[GUC_CTL_DEBUG] |= ads << GUC_ADS_ADDR_SHIFT;
params[GUC_CTL_DEBUG] |= GUC_ADS_ENABLED;
}
/* If GuC submission is enabled, set up additional parameters here */
if (i915.enable_guc_submission) {
u32 pgs = i915_gem_obj_ggtt_offset(dev_priv->guc.ctx_pool_obj);
u32 ctx_in_16 = GUC_MAX_GPU_CONTEXTS / 16;
pgs >>= PAGE_SHIFT;
params[GUC_CTL_CTXINFO] = (pgs << GUC_CTL_BASE_ADDR_SHIFT) |
(ctx_in_16 << GUC_CTL_CTXNUM_IN16_SHIFT);
params[GUC_CTL_FEATURE] |= GUC_CTL_KERNEL_SUBMISSIONS;
/* Unmask this bit to enable the GuC's internal scheduler */
params[GUC_CTL_FEATURE] &= ~GUC_CTL_DISABLE_SCHEDULER;
}
I915_WRITE(SOFT_SCRATCH(0), 0);
for (i = 0; i < GUC_CTL_MAX_DWORDS; i++)
I915_WRITE(SOFT_SCRATCH(1 + i), params[i]);
}
/*
* Read the GuC status register (GUC_STATUS) and store it in the
* specified location; then return a boolean indicating whether
* the value matches either of two values representing completion
* of the GuC boot process.
*
* This is used for polling the GuC status in a wait_for()
* loop below.
*/
static inline bool guc_ucode_response(struct drm_i915_private *dev_priv,
u32 *status)
{
u32 val = I915_READ(GUC_STATUS);
u32 uk_val = val & GS_UKERNEL_MASK;
*status = val;
return (uk_val == GS_UKERNEL_READY ||
((val & GS_MIA_CORE_STATE) && uk_val == GS_UKERNEL_LAPIC_DONE));
}
/*
* Transfer the firmware image to RAM for execution by the microcontroller.
*
* Architecturally, the DMA engine is bidirectional, and can potentially even
* transfer between GTT locations. This functionality is left out of the API
* for now as there is no need for it.
*
* Note that GuC needs the CSS header plus uKernel code to be copied by the
* DMA engine in one operation, whereas the RSA signature is loaded via MMIO.
*/
static int guc_ucode_xfer_dma(struct drm_i915_private *dev_priv)
{
struct intel_guc_fw *guc_fw = &dev_priv->guc.guc_fw;
struct drm_i915_gem_object *fw_obj = guc_fw->guc_fw_obj;
unsigned long offset;
struct sg_table *sg = fw_obj->pages;
u32 status, rsa[UOS_RSA_SCRATCH_MAX_COUNT];
int i, ret = 0;
/* where RSA signature starts */
offset = guc_fw->rsa_offset;
/* Copy RSA signature from the fw image to HW for verification */
sg_pcopy_to_buffer(sg->sgl, sg->nents, rsa, sizeof(rsa), offset);
for (i = 0; i < UOS_RSA_SCRATCH_MAX_COUNT; i++)
I915_WRITE(UOS_RSA_SCRATCH(i), rsa[i]);
/* The header plus uCode will be copied to WOPCM via DMA, excluding any
* other components */
I915_WRITE(DMA_COPY_SIZE, guc_fw->header_size + guc_fw->ucode_size);
/* Set the source address for the new blob */
offset = i915_gem_obj_ggtt_offset(fw_obj) + guc_fw->header_offset;
I915_WRITE(DMA_ADDR_0_LOW, lower_32_bits(offset));
I915_WRITE(DMA_ADDR_0_HIGH, upper_32_bits(offset) & 0xFFFF);
/*
* Set the DMA destination. Current uCode expects the code to be
* loaded at 8k; locations below this are used for the stack.
*/
I915_WRITE(DMA_ADDR_1_LOW, 0x2000);
I915_WRITE(DMA_ADDR_1_HIGH, DMA_ADDRESS_SPACE_WOPCM);
/* Finally start the DMA */
I915_WRITE(DMA_CTRL, _MASKED_BIT_ENABLE(UOS_MOVE | START_DMA));
/*
* Wait for the DMA to complete & the GuC to start up.
* NB: Docs recommend not using the interrupt for completion.
* Measurements indicate this should take no more than 20ms, so a
* timeout here indicates that the GuC has failed and is unusable.
* (Higher levels of the driver will attempt to fall back to
* execlist mode if this happens.)
*/
ret = wait_for(guc_ucode_response(dev_priv, &status), 100);
DRM_DEBUG_DRIVER("DMA status 0x%x, GuC status 0x%x\n",
I915_READ(DMA_CTRL), status);
if ((status & GS_BOOTROM_MASK) == GS_BOOTROM_RSA_FAILED) {
DRM_ERROR("GuC firmware signature verification failed\n");
ret = -ENOEXEC;
}
DRM_DEBUG_DRIVER("returning %d\n", ret);
return ret;
}
/*
* Load the GuC firmware blob into the MinuteIA.
*/
static int guc_ucode_xfer(struct drm_i915_private *dev_priv)
{
struct intel_guc_fw *guc_fw = &dev_priv->guc.guc_fw;
struct drm_device *dev = dev_priv->dev;
int ret;
ret = i915_gem_object_set_to_gtt_domain(guc_fw->guc_fw_obj, false);
if (ret) {
DRM_DEBUG_DRIVER("set-domain failed %d\n", ret);
return ret;
}
ret = i915_gem_obj_ggtt_pin(guc_fw->guc_fw_obj, 0, 0);
if (ret) {
DRM_DEBUG_DRIVER("pin failed %d\n", ret);
return ret;
}
/* Invalidate GuC TLB to let GuC take the latest updates to GTT. */
I915_WRITE(GEN8_GTCR, GEN8_GTCR_INVALIDATE);
intel_uncore_forcewake_get(dev_priv, FORCEWAKE_ALL);
/* init WOPCM */
I915_WRITE(GUC_WOPCM_SIZE, GUC_WOPCM_SIZE_VALUE);
I915_WRITE(DMA_GUC_WOPCM_OFFSET, GUC_WOPCM_OFFSET_VALUE);
/* Enable MIA caching. GuC clock gating is disabled. */
I915_WRITE(GUC_SHIM_CONTROL, GUC_SHIM_CONTROL_VALUE);
/* WaDisableMinuteIaClockGating:skl,bxt */
if (IS_SKL_REVID(dev, 0, SKL_REVID_B0) ||
IS_BXT_REVID(dev, 0, BXT_REVID_A1)) {
I915_WRITE(GUC_SHIM_CONTROL, (I915_READ(GUC_SHIM_CONTROL) &
~GUC_ENABLE_MIA_CLOCK_GATING));
}
/* WaC6DisallowByGfxPause*/
I915_WRITE(GEN6_GFXPAUSE, 0x30FFF);
if (IS_BROXTON(dev))
I915_WRITE(GEN9LP_GT_PM_CONFIG, GT_DOORBELL_ENABLE);
else
I915_WRITE(GEN9_GT_PM_CONFIG, GT_DOORBELL_ENABLE);
if (IS_GEN9(dev)) {
/* DOP Clock Gating Enable for GuC clocks */
I915_WRITE(GEN7_MISCCPCTL, (GEN8_DOP_CLOCK_GATE_GUC_ENABLE |
I915_READ(GEN7_MISCCPCTL)));
/* allows for 5us before GT can go to RC6 */
I915_WRITE(GUC_ARAT_C6DIS, 0x1FF);
}
set_guc_init_params(dev_priv);
ret = guc_ucode_xfer_dma(dev_priv);
intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL);
/*
* We keep the object pages for reuse during resume. But we can unpin it
* now that DMA has completed, so it doesn't continue to take up space.
*/
i915_gem_object_ggtt_unpin(guc_fw->guc_fw_obj);
return ret;
}
static int i915_reset_guc(struct drm_i915_private *dev_priv)
{
int ret;
u32 guc_status;
ret = intel_guc_reset(dev_priv);
if (ret) {
DRM_ERROR("GuC reset failed, ret = %d\n", ret);
return ret;
}
guc_status = I915_READ(GUC_STATUS);
WARN(!(guc_status & GS_MIA_IN_RESET),
"GuC status: 0x%x, MIA core expected to be in reset\n", guc_status);
return ret;
}
/**
* intel_guc_ucode_load() - load GuC uCode into the device
* @dev: drm device
*
* Called from gem_init_hw() during driver loading and also after a GPU reset.
*
* The firmware image should have already been fetched into memory by the
* earlier call to intel_guc_ucode_init(), so here we need only check that
* is succeeded, and then transfer the image to the h/w.
*
* Return: non-zero code on error
*/
int intel_guc_ucode_load(struct drm_device *dev)
{
struct drm_i915_private *dev_priv = dev->dev_private;
struct intel_guc_fw *guc_fw = &dev_priv->guc.guc_fw;
int err = 0;
if (!i915.enable_guc_submission)
return 0;
DRM_DEBUG_DRIVER("GuC fw status: fetch %s, load %s\n",
intel_guc_fw_status_repr(guc_fw->guc_fw_fetch_status),
intel_guc_fw_status_repr(guc_fw->guc_fw_load_status));
direct_interrupts_to_host(dev_priv);
if (guc_fw->guc_fw_fetch_status == GUC_FIRMWARE_NONE)
return 0;
if (guc_fw->guc_fw_fetch_status == GUC_FIRMWARE_SUCCESS &&
guc_fw->guc_fw_load_status == GUC_FIRMWARE_FAIL)
return -ENOEXEC;
guc_fw->guc_fw_load_status = GUC_FIRMWARE_PENDING;
DRM_DEBUG_DRIVER("GuC fw fetch status %s\n",
intel_guc_fw_status_repr(guc_fw->guc_fw_fetch_status));
switch (guc_fw->guc_fw_fetch_status) {
case GUC_FIRMWARE_FAIL:
/* something went wrong :( */
err = -EIO;
goto fail;
case GUC_FIRMWARE_NONE:
case GUC_FIRMWARE_PENDING:
default:
/* "can't happen" */
WARN_ONCE(1, "GuC fw %s invalid guc_fw_fetch_status %s [%d]\n",
guc_fw->guc_fw_path,
intel_guc_fw_status_repr(guc_fw->guc_fw_fetch_status),
guc_fw->guc_fw_fetch_status);
err = -ENXIO;
goto fail;
case GUC_FIRMWARE_SUCCESS:
break;
}
err = i915_guc_submission_init(dev);
if (err)
goto fail;
/*
* WaEnableuKernelHeaderValidFix:skl,bxt
* For BXT, this is only upto B0 but below WA is required for later
* steppings also so this is extended as well.
*/
/* WaEnableGuCBootHashCheckNotSet:skl,bxt */
err = guc_ucode_xfer(dev_priv);
if (err) {
int retries = 3;
DRM_ERROR("GuC fw load failed, err=%d, attempting reset and retry\n", err);
while (retries--) {
err = i915_reset_guc(dev_priv);
if (err)
break;
err = guc_ucode_xfer(dev_priv);
if (!err) {
DRM_DEBUG_DRIVER("GuC fw reload succeeded after reset\n");
break;
}
DRM_DEBUG_DRIVER("GuC fw reload retries left: %d\n", retries);
}
if (err) {
DRM_ERROR("GuC fw reload attempt failed, ret=%d\n", err);
goto fail;
}
}
guc_fw->guc_fw_load_status = GUC_FIRMWARE_SUCCESS;
DRM_DEBUG_DRIVER("GuC fw status: fetch %s, load %s\n",
intel_guc_fw_status_repr(guc_fw->guc_fw_fetch_status),
intel_guc_fw_status_repr(guc_fw->guc_fw_load_status));
if (i915.enable_guc_submission) {
/* The execbuf_client will be recreated. Release it first. */
i915_guc_submission_disable(dev);
err = i915_guc_submission_enable(dev);
if (err)
goto fail;
direct_interrupts_to_guc(dev_priv);
}
return 0;
fail:
if (guc_fw->guc_fw_load_status == GUC_FIRMWARE_PENDING)
guc_fw->guc_fw_load_status = GUC_FIRMWARE_FAIL;
direct_interrupts_to_host(dev_priv);
i915_guc_submission_disable(dev);
i915_guc_submission_fini(dev);
return err;
}
static void guc_fw_fetch(struct drm_device *dev, struct intel_guc_fw *guc_fw)
{
struct drm_i915_gem_object *obj;
const struct firmware *fw;
struct guc_css_header *css;
size_t size;
int err;
DRM_DEBUG_DRIVER("before requesting firmware: GuC fw fetch status %s\n",
intel_guc_fw_status_repr(guc_fw->guc_fw_fetch_status));
err = request_firmware(&fw, guc_fw->guc_fw_path, &dev->pdev->dev);
if (err)
goto fail;
if (!fw)
goto fail;
DRM_DEBUG_DRIVER("fetch GuC fw from %s succeeded, fw %p\n",
guc_fw->guc_fw_path, fw);
/* Check the size of the blob before examining buffer contents */
if (fw->size < sizeof(struct guc_css_header)) {
DRM_ERROR("Firmware header is missing\n");
goto fail;
}
css = (struct guc_css_header *)fw->data;
/* Firmware bits always start from header */
guc_fw->header_offset = 0;
guc_fw->header_size = (css->header_size_dw - css->modulus_size_dw -
css->key_size_dw - css->exponent_size_dw) * sizeof(u32);
if (guc_fw->header_size != sizeof(struct guc_css_header)) {
DRM_ERROR("CSS header definition mismatch\n");
goto fail;
}
/* then, uCode */
guc_fw->ucode_offset = guc_fw->header_offset + guc_fw->header_size;
guc_fw->ucode_size = (css->size_dw - css->header_size_dw) * sizeof(u32);
/* now RSA */
if (css->key_size_dw != UOS_RSA_SCRATCH_MAX_COUNT) {
DRM_ERROR("RSA key size is bad\n");
goto fail;
}
guc_fw->rsa_offset = guc_fw->ucode_offset + guc_fw->ucode_size;
guc_fw->rsa_size = css->key_size_dw * sizeof(u32);
/* At least, it should have header, uCode and RSA. Size of all three. */
size = guc_fw->header_size + guc_fw->ucode_size + guc_fw->rsa_size;
if (fw->size < size) {
DRM_ERROR("Missing firmware components\n");
goto fail;
}
/* Header and uCode will be loaded to WOPCM. Size of the two. */
size = guc_fw->header_size + guc_fw->ucode_size;
/* Top 32k of WOPCM is reserved (8K stack + 24k RC6 context). */
if (size > GUC_WOPCM_SIZE_VALUE - 0x8000) {
DRM_ERROR("Firmware is too large to fit in WOPCM\n");
goto fail;
}
/*
* The GuC firmware image has the version number embedded at a well-known
* offset within the firmware blob; note that major / minor version are
* TWO bytes each (i.e. u16), although all pointers and offsets are defined
* in terms of bytes (u8).
*/
guc_fw->guc_fw_major_found = css->guc_sw_version >> 16;
guc_fw->guc_fw_minor_found = css->guc_sw_version & 0xFFFF;
if (guc_fw->guc_fw_major_found != guc_fw->guc_fw_major_wanted ||
guc_fw->guc_fw_minor_found < guc_fw->guc_fw_minor_wanted) {
DRM_ERROR("GuC firmware version %d.%d, required %d.%d\n",
guc_fw->guc_fw_major_found, guc_fw->guc_fw_minor_found,
guc_fw->guc_fw_major_wanted, guc_fw->guc_fw_minor_wanted);
err = -ENOEXEC;
goto fail;
}
DRM_DEBUG_DRIVER("firmware version %d.%d OK (minimum %d.%d)\n",
guc_fw->guc_fw_major_found, guc_fw->guc_fw_minor_found,
guc_fw->guc_fw_major_wanted, guc_fw->guc_fw_minor_wanted);
drm/i915: Fix locking around GuC firmware load The GuC firmware load requires struct_mutex to create a GEM object, but this collides badly with request_firmware. Move struct_mutex locking down into the loader itself, so we don't hold it across the entire load process, including request_firmware. [ 20.451400] ====================================================== [ 20.451420] [ INFO: possible circular locking dependency detected ] [ 20.451441] 4.3.0-rc5+ #1 Tainted: G W [ 20.451457] ------------------------------------------------------- [ 20.451477] plymouthd/371 is trying to acquire lock: [ 20.451494] (&dev->struct_mutex){+.+.+.}, at: [<ffffffffa0093c62>] drm_gem_mmap+0x112/0x290 [drm] [ 20.451538] but task is already holding lock: [ 20.451557] (&mm->mmap_sem){++++++}, at: [<ffffffff811fd9ac>] vm_mmap_pgoff+0x8c/0xf0 [ 20.451591] which lock already depends on the new lock. [ 20.451617] the existing dependency chain (in reverse order) is: [ 20.451640] -> #3 (&mm->mmap_sem){++++++}: [ 20.451661] [<ffffffff8110644e>] lock_acquire+0xce/0x1c0 [ 20.451683] [<ffffffff8120ec9a>] __might_fault+0x7a/0xa0 [ 20.451705] [<ffffffff8127e34e>] filldir+0x9e/0x130 [ 20.451726] [<ffffffff81295b86>] dcache_readdir+0x186/0x230 [ 20.451748] [<ffffffff8127e117>] iterate_dir+0x97/0x130 [ 20.451769] [<ffffffff8127e66a>] SyS_getdents+0x9a/0x130 [ 20.451790] [<ffffffff8184f2f2>] entry_SYSCALL_64_fastpath+0x12/0x76 [ 20.451829] -> #2 (&sb->s_type->i_mutex_key#2){+.+.+.}: [ 20.451852] [<ffffffff8110644e>] lock_acquire+0xce/0x1c0 [ 20.451872] [<ffffffff8184b516>] mutex_lock_nested+0x86/0x400 [ 20.451893] [<ffffffff81277790>] walk_component+0x1d0/0x2a0 [ 20.451914] [<ffffffff812779f0>] link_path_walk+0x190/0x5a0 [ 20.451935] [<ffffffff8127803b>] path_openat+0xab/0x1260 [ 20.451955] [<ffffffff8127a651>] do_filp_open+0x91/0x100 [ 20.451975] [<ffffffff81267e67>] file_open_name+0xf7/0x150 [ 20.451995] [<ffffffff81267ef3>] filp_open+0x33/0x60 [ 20.452014] [<ffffffff8157e1e7>] _request_firmware+0x277/0x880 [ 20.452038] [<ffffffff8157e9e4>] request_firmware_work_func+0x34/0x80 [ 20.452060] [<ffffffff810c7020>] process_one_work+0x230/0x680 [ 20.452082] [<ffffffff810c74be>] worker_thread+0x4e/0x450 [ 20.452102] [<ffffffff810ce511>] kthread+0x101/0x120 [ 20.452121] [<ffffffff8184f66f>] ret_from_fork+0x3f/0x70 [ 20.452140] -> #1 (umhelper_sem){++++.+}: [ 20.452159] [<ffffffff8110644e>] lock_acquire+0xce/0x1c0 [ 20.452178] [<ffffffff8184c5c1>] down_read+0x51/0xa0 [ 20.452197] [<ffffffff810c203b>] usermodehelper_read_trylock+0x5b/0x130 [ 20.452221] [<ffffffff8157e147>] _request_firmware+0x1d7/0x880 [ 20.452242] [<ffffffff8157e821>] request_firmware+0x31/0x50 [ 20.452262] [<ffffffffa01b54a4>] intel_guc_ucode_init+0xf4/0x400 [i915] [ 20.452305] [<ffffffffa0213913>] i915_driver_load+0xd63/0x16e0 [i915] [ 20.452343] [<ffffffffa00987d9>] drm_dev_register+0xa9/0xc0 [drm] [ 20.452369] [<ffffffffa009ae3d>] drm_get_pci_dev+0x8d/0x1e0 [drm] [ 20.452396] [<ffffffffa01521e4>] i915_pci_probe+0x34/0x50 [i915] [ 20.452421] [<ffffffff81464675>] local_pci_probe+0x45/0xa0 [ 20.452443] [<ffffffff81465a6d>] pci_device_probe+0xfd/0x140 [ 20.452464] [<ffffffff8156a2e4>] driver_probe_device+0x224/0x480 [ 20.452486] [<ffffffff8156a5c8>] __driver_attach+0x88/0x90 [ 20.452505] [<ffffffff81567cf3>] bus_for_each_dev+0x73/0xc0 [ 20.452526] [<ffffffff81569a7e>] driver_attach+0x1e/0x20 [ 20.452546] [<ffffffff815695ae>] bus_add_driver+0x1ee/0x280 [ 20.452566] [<ffffffff8156b100>] driver_register+0x60/0xe0 [ 20.453197] [<ffffffff81464050>] __pci_register_driver+0x60/0x70 [ 20.453845] [<ffffffffa009b070>] drm_pci_init+0xe0/0x110 [drm] [ 20.454497] [<ffffffffa027f092>] 0xffffffffa027f092 [ 20.455156] [<ffffffff81002123>] do_one_initcall+0xb3/0x200 [ 20.455796] [<ffffffff811d8c01>] do_init_module+0x5f/0x1e7 [ 20.456434] [<ffffffff8114c4e6>] load_module+0x2126/0x27d0 [ 20.457071] [<ffffffff8114cdf9>] SyS_finit_module+0xb9/0xf0 [ 20.457738] [<ffffffff8184f2f2>] entry_SYSCALL_64_fastpath+0x12/0x76 [ 20.458370] -> #0 (&dev->struct_mutex){+.+.+.}: [ 20.459773] [<ffffffff8110584f>] __lock_acquire+0x191f/0x1ba0 [ 20.460451] [<ffffffff8110644e>] lock_acquire+0xce/0x1c0 [ 20.461074] [<ffffffffa0093c88>] drm_gem_mmap+0x138/0x290 [drm] [ 20.461693] [<ffffffff8121a5ec>] mmap_region+0x3ec/0x670 [ 20.462298] [<ffffffff8121abb2>] do_mmap+0x342/0x420 [ 20.462901] [<ffffffff811fd9d2>] vm_mmap_pgoff+0xb2/0xf0 [ 20.463532] [<ffffffff81218f62>] SyS_mmap_pgoff+0x1f2/0x290 [ 20.464118] [<ffffffff8102187b>] SyS_mmap+0x1b/0x30 [ 20.464702] [<ffffffff8184f2f2>] entry_SYSCALL_64_fastpath+0x12/0x76 [ 20.465289] other info that might help us debug this: [ 20.467179] Chain exists of: &dev->struct_mutex --> &sb->s_type->i_mutex_key#2 --> &mm->mmap_sem [ 20.468928] Possible unsafe locking scenario: [ 20.470161] CPU0 CPU1 [ 20.470745] ---- ---- [ 20.471325] lock(&mm->mmap_sem); [ 20.471902] lock(&sb->s_type->i_mutex_key#2); [ 20.472538] lock(&mm->mmap_sem); [ 20.473118] lock(&dev->struct_mutex); [ 20.473704] *** DEADLOCK *** Signed-off-by: Daniel Stone <daniels@collabora.com> Signed-off-by: Dave Airlie <airlied@redhat.com>
2015-11-03 21:42:31 +00:00
mutex_lock(&dev->struct_mutex);
obj = i915_gem_object_create_from_data(dev, fw->data, fw->size);
drm/i915: Fix locking around GuC firmware load The GuC firmware load requires struct_mutex to create a GEM object, but this collides badly with request_firmware. Move struct_mutex locking down into the loader itself, so we don't hold it across the entire load process, including request_firmware. [ 20.451400] ====================================================== [ 20.451420] [ INFO: possible circular locking dependency detected ] [ 20.451441] 4.3.0-rc5+ #1 Tainted: G W [ 20.451457] ------------------------------------------------------- [ 20.451477] plymouthd/371 is trying to acquire lock: [ 20.451494] (&dev->struct_mutex){+.+.+.}, at: [<ffffffffa0093c62>] drm_gem_mmap+0x112/0x290 [drm] [ 20.451538] but task is already holding lock: [ 20.451557] (&mm->mmap_sem){++++++}, at: [<ffffffff811fd9ac>] vm_mmap_pgoff+0x8c/0xf0 [ 20.451591] which lock already depends on the new lock. [ 20.451617] the existing dependency chain (in reverse order) is: [ 20.451640] -> #3 (&mm->mmap_sem){++++++}: [ 20.451661] [<ffffffff8110644e>] lock_acquire+0xce/0x1c0 [ 20.451683] [<ffffffff8120ec9a>] __might_fault+0x7a/0xa0 [ 20.451705] [<ffffffff8127e34e>] filldir+0x9e/0x130 [ 20.451726] [<ffffffff81295b86>] dcache_readdir+0x186/0x230 [ 20.451748] [<ffffffff8127e117>] iterate_dir+0x97/0x130 [ 20.451769] [<ffffffff8127e66a>] SyS_getdents+0x9a/0x130 [ 20.451790] [<ffffffff8184f2f2>] entry_SYSCALL_64_fastpath+0x12/0x76 [ 20.451829] -> #2 (&sb->s_type->i_mutex_key#2){+.+.+.}: [ 20.451852] [<ffffffff8110644e>] lock_acquire+0xce/0x1c0 [ 20.451872] [<ffffffff8184b516>] mutex_lock_nested+0x86/0x400 [ 20.451893] [<ffffffff81277790>] walk_component+0x1d0/0x2a0 [ 20.451914] [<ffffffff812779f0>] link_path_walk+0x190/0x5a0 [ 20.451935] [<ffffffff8127803b>] path_openat+0xab/0x1260 [ 20.451955] [<ffffffff8127a651>] do_filp_open+0x91/0x100 [ 20.451975] [<ffffffff81267e67>] file_open_name+0xf7/0x150 [ 20.451995] [<ffffffff81267ef3>] filp_open+0x33/0x60 [ 20.452014] [<ffffffff8157e1e7>] _request_firmware+0x277/0x880 [ 20.452038] [<ffffffff8157e9e4>] request_firmware_work_func+0x34/0x80 [ 20.452060] [<ffffffff810c7020>] process_one_work+0x230/0x680 [ 20.452082] [<ffffffff810c74be>] worker_thread+0x4e/0x450 [ 20.452102] [<ffffffff810ce511>] kthread+0x101/0x120 [ 20.452121] [<ffffffff8184f66f>] ret_from_fork+0x3f/0x70 [ 20.452140] -> #1 (umhelper_sem){++++.+}: [ 20.452159] [<ffffffff8110644e>] lock_acquire+0xce/0x1c0 [ 20.452178] [<ffffffff8184c5c1>] down_read+0x51/0xa0 [ 20.452197] [<ffffffff810c203b>] usermodehelper_read_trylock+0x5b/0x130 [ 20.452221] [<ffffffff8157e147>] _request_firmware+0x1d7/0x880 [ 20.452242] [<ffffffff8157e821>] request_firmware+0x31/0x50 [ 20.452262] [<ffffffffa01b54a4>] intel_guc_ucode_init+0xf4/0x400 [i915] [ 20.452305] [<ffffffffa0213913>] i915_driver_load+0xd63/0x16e0 [i915] [ 20.452343] [<ffffffffa00987d9>] drm_dev_register+0xa9/0xc0 [drm] [ 20.452369] [<ffffffffa009ae3d>] drm_get_pci_dev+0x8d/0x1e0 [drm] [ 20.452396] [<ffffffffa01521e4>] i915_pci_probe+0x34/0x50 [i915] [ 20.452421] [<ffffffff81464675>] local_pci_probe+0x45/0xa0 [ 20.452443] [<ffffffff81465a6d>] pci_device_probe+0xfd/0x140 [ 20.452464] [<ffffffff8156a2e4>] driver_probe_device+0x224/0x480 [ 20.452486] [<ffffffff8156a5c8>] __driver_attach+0x88/0x90 [ 20.452505] [<ffffffff81567cf3>] bus_for_each_dev+0x73/0xc0 [ 20.452526] [<ffffffff81569a7e>] driver_attach+0x1e/0x20 [ 20.452546] [<ffffffff815695ae>] bus_add_driver+0x1ee/0x280 [ 20.452566] [<ffffffff8156b100>] driver_register+0x60/0xe0 [ 20.453197] [<ffffffff81464050>] __pci_register_driver+0x60/0x70 [ 20.453845] [<ffffffffa009b070>] drm_pci_init+0xe0/0x110 [drm] [ 20.454497] [<ffffffffa027f092>] 0xffffffffa027f092 [ 20.455156] [<ffffffff81002123>] do_one_initcall+0xb3/0x200 [ 20.455796] [<ffffffff811d8c01>] do_init_module+0x5f/0x1e7 [ 20.456434] [<ffffffff8114c4e6>] load_module+0x2126/0x27d0 [ 20.457071] [<ffffffff8114cdf9>] SyS_finit_module+0xb9/0xf0 [ 20.457738] [<ffffffff8184f2f2>] entry_SYSCALL_64_fastpath+0x12/0x76 [ 20.458370] -> #0 (&dev->struct_mutex){+.+.+.}: [ 20.459773] [<ffffffff8110584f>] __lock_acquire+0x191f/0x1ba0 [ 20.460451] [<ffffffff8110644e>] lock_acquire+0xce/0x1c0 [ 20.461074] [<ffffffffa0093c88>] drm_gem_mmap+0x138/0x290 [drm] [ 20.461693] [<ffffffff8121a5ec>] mmap_region+0x3ec/0x670 [ 20.462298] [<ffffffff8121abb2>] do_mmap+0x342/0x420 [ 20.462901] [<ffffffff811fd9d2>] vm_mmap_pgoff+0xb2/0xf0 [ 20.463532] [<ffffffff81218f62>] SyS_mmap_pgoff+0x1f2/0x290 [ 20.464118] [<ffffffff8102187b>] SyS_mmap+0x1b/0x30 [ 20.464702] [<ffffffff8184f2f2>] entry_SYSCALL_64_fastpath+0x12/0x76 [ 20.465289] other info that might help us debug this: [ 20.467179] Chain exists of: &dev->struct_mutex --> &sb->s_type->i_mutex_key#2 --> &mm->mmap_sem [ 20.468928] Possible unsafe locking scenario: [ 20.470161] CPU0 CPU1 [ 20.470745] ---- ---- [ 20.471325] lock(&mm->mmap_sem); [ 20.471902] lock(&sb->s_type->i_mutex_key#2); [ 20.472538] lock(&mm->mmap_sem); [ 20.473118] lock(&dev->struct_mutex); [ 20.473704] *** DEADLOCK *** Signed-off-by: Daniel Stone <daniels@collabora.com> Signed-off-by: Dave Airlie <airlied@redhat.com>
2015-11-03 21:42:31 +00:00
mutex_unlock(&dev->struct_mutex);
if (IS_ERR_OR_NULL(obj)) {
err = obj ? PTR_ERR(obj) : -ENOMEM;
goto fail;
}
guc_fw->guc_fw_obj = obj;
guc_fw->guc_fw_size = fw->size;
DRM_DEBUG_DRIVER("GuC fw fetch status SUCCESS, obj %p\n",
guc_fw->guc_fw_obj);
release_firmware(fw);
guc_fw->guc_fw_fetch_status = GUC_FIRMWARE_SUCCESS;
return;
fail:
DRM_DEBUG_DRIVER("GuC fw fetch status FAIL; err %d, fw %p, obj %p\n",
err, fw, guc_fw->guc_fw_obj);
DRM_ERROR("Failed to fetch GuC firmware from %s (error %d)\n",
guc_fw->guc_fw_path, err);
mutex_lock(&dev->struct_mutex);
obj = guc_fw->guc_fw_obj;
if (obj)
drm_gem_object_unreference(&obj->base);
guc_fw->guc_fw_obj = NULL;
mutex_unlock(&dev->struct_mutex);
release_firmware(fw); /* OK even if fw is NULL */
guc_fw->guc_fw_fetch_status = GUC_FIRMWARE_FAIL;
}
/**
* intel_guc_ucode_init() - define parameters and fetch firmware
* @dev: drm device
*
* Called early during driver load, but after GEM is initialised.
*
* The firmware will be transferred to the GuC's memory later,
* when intel_guc_ucode_load() is called.
*/
void intel_guc_ucode_init(struct drm_device *dev)
{
struct drm_i915_private *dev_priv = dev->dev_private;
struct intel_guc_fw *guc_fw = &dev_priv->guc.guc_fw;
const char *fw_path;
if (!HAS_GUC_SCHED(dev))
i915.enable_guc_submission = false;
if (!HAS_GUC_UCODE(dev)) {
fw_path = NULL;
} else if (IS_SKYLAKE(dev)) {
fw_path = I915_SKL_GUC_UCODE;
guc_fw->guc_fw_major_wanted = 6;
guc_fw->guc_fw_minor_wanted = 1;
} else {
i915.enable_guc_submission = false;
fw_path = ""; /* unknown device */
}
if (!i915.enable_guc_submission)
return;
guc_fw->guc_dev = dev;
guc_fw->guc_fw_path = fw_path;
guc_fw->guc_fw_fetch_status = GUC_FIRMWARE_NONE;
guc_fw->guc_fw_load_status = GUC_FIRMWARE_NONE;
if (fw_path == NULL)
return;
if (*fw_path == '\0') {
DRM_ERROR("No GuC firmware known for this platform\n");
guc_fw->guc_fw_fetch_status = GUC_FIRMWARE_FAIL;
return;
}
guc_fw->guc_fw_fetch_status = GUC_FIRMWARE_PENDING;
DRM_DEBUG_DRIVER("GuC firmware pending, path %s\n", fw_path);
guc_fw_fetch(dev, guc_fw);
/* status must now be FAIL or SUCCESS */
}
/**
* intel_guc_ucode_fini() - clean up all allocated resources
* @dev: drm device
*/
void intel_guc_ucode_fini(struct drm_device *dev)
{
struct drm_i915_private *dev_priv = dev->dev_private;
struct intel_guc_fw *guc_fw = &dev_priv->guc.guc_fw;
mutex_lock(&dev->struct_mutex);
direct_interrupts_to_host(dev_priv);
i915_guc_submission_disable(dev);
i915_guc_submission_fini(dev);
if (guc_fw->guc_fw_obj)
drm_gem_object_unreference(&guc_fw->guc_fw_obj->base);
guc_fw->guc_fw_obj = NULL;
drm/i915: Fix locking around GuC firmware load The GuC firmware load requires struct_mutex to create a GEM object, but this collides badly with request_firmware. Move struct_mutex locking down into the loader itself, so we don't hold it across the entire load process, including request_firmware. [ 20.451400] ====================================================== [ 20.451420] [ INFO: possible circular locking dependency detected ] [ 20.451441] 4.3.0-rc5+ #1 Tainted: G W [ 20.451457] ------------------------------------------------------- [ 20.451477] plymouthd/371 is trying to acquire lock: [ 20.451494] (&dev->struct_mutex){+.+.+.}, at: [<ffffffffa0093c62>] drm_gem_mmap+0x112/0x290 [drm] [ 20.451538] but task is already holding lock: [ 20.451557] (&mm->mmap_sem){++++++}, at: [<ffffffff811fd9ac>] vm_mmap_pgoff+0x8c/0xf0 [ 20.451591] which lock already depends on the new lock. [ 20.451617] the existing dependency chain (in reverse order) is: [ 20.451640] -> #3 (&mm->mmap_sem){++++++}: [ 20.451661] [<ffffffff8110644e>] lock_acquire+0xce/0x1c0 [ 20.451683] [<ffffffff8120ec9a>] __might_fault+0x7a/0xa0 [ 20.451705] [<ffffffff8127e34e>] filldir+0x9e/0x130 [ 20.451726] [<ffffffff81295b86>] dcache_readdir+0x186/0x230 [ 20.451748] [<ffffffff8127e117>] iterate_dir+0x97/0x130 [ 20.451769] [<ffffffff8127e66a>] SyS_getdents+0x9a/0x130 [ 20.451790] [<ffffffff8184f2f2>] entry_SYSCALL_64_fastpath+0x12/0x76 [ 20.451829] -> #2 (&sb->s_type->i_mutex_key#2){+.+.+.}: [ 20.451852] [<ffffffff8110644e>] lock_acquire+0xce/0x1c0 [ 20.451872] [<ffffffff8184b516>] mutex_lock_nested+0x86/0x400 [ 20.451893] [<ffffffff81277790>] walk_component+0x1d0/0x2a0 [ 20.451914] [<ffffffff812779f0>] link_path_walk+0x190/0x5a0 [ 20.451935] [<ffffffff8127803b>] path_openat+0xab/0x1260 [ 20.451955] [<ffffffff8127a651>] do_filp_open+0x91/0x100 [ 20.451975] [<ffffffff81267e67>] file_open_name+0xf7/0x150 [ 20.451995] [<ffffffff81267ef3>] filp_open+0x33/0x60 [ 20.452014] [<ffffffff8157e1e7>] _request_firmware+0x277/0x880 [ 20.452038] [<ffffffff8157e9e4>] request_firmware_work_func+0x34/0x80 [ 20.452060] [<ffffffff810c7020>] process_one_work+0x230/0x680 [ 20.452082] [<ffffffff810c74be>] worker_thread+0x4e/0x450 [ 20.452102] [<ffffffff810ce511>] kthread+0x101/0x120 [ 20.452121] [<ffffffff8184f66f>] ret_from_fork+0x3f/0x70 [ 20.452140] -> #1 (umhelper_sem){++++.+}: [ 20.452159] [<ffffffff8110644e>] lock_acquire+0xce/0x1c0 [ 20.452178] [<ffffffff8184c5c1>] down_read+0x51/0xa0 [ 20.452197] [<ffffffff810c203b>] usermodehelper_read_trylock+0x5b/0x130 [ 20.452221] [<ffffffff8157e147>] _request_firmware+0x1d7/0x880 [ 20.452242] [<ffffffff8157e821>] request_firmware+0x31/0x50 [ 20.452262] [<ffffffffa01b54a4>] intel_guc_ucode_init+0xf4/0x400 [i915] [ 20.452305] [<ffffffffa0213913>] i915_driver_load+0xd63/0x16e0 [i915] [ 20.452343] [<ffffffffa00987d9>] drm_dev_register+0xa9/0xc0 [drm] [ 20.452369] [<ffffffffa009ae3d>] drm_get_pci_dev+0x8d/0x1e0 [drm] [ 20.452396] [<ffffffffa01521e4>] i915_pci_probe+0x34/0x50 [i915] [ 20.452421] [<ffffffff81464675>] local_pci_probe+0x45/0xa0 [ 20.452443] [<ffffffff81465a6d>] pci_device_probe+0xfd/0x140 [ 20.452464] [<ffffffff8156a2e4>] driver_probe_device+0x224/0x480 [ 20.452486] [<ffffffff8156a5c8>] __driver_attach+0x88/0x90 [ 20.452505] [<ffffffff81567cf3>] bus_for_each_dev+0x73/0xc0 [ 20.452526] [<ffffffff81569a7e>] driver_attach+0x1e/0x20 [ 20.452546] [<ffffffff815695ae>] bus_add_driver+0x1ee/0x280 [ 20.452566] [<ffffffff8156b100>] driver_register+0x60/0xe0 [ 20.453197] [<ffffffff81464050>] __pci_register_driver+0x60/0x70 [ 20.453845] [<ffffffffa009b070>] drm_pci_init+0xe0/0x110 [drm] [ 20.454497] [<ffffffffa027f092>] 0xffffffffa027f092 [ 20.455156] [<ffffffff81002123>] do_one_initcall+0xb3/0x200 [ 20.455796] [<ffffffff811d8c01>] do_init_module+0x5f/0x1e7 [ 20.456434] [<ffffffff8114c4e6>] load_module+0x2126/0x27d0 [ 20.457071] [<ffffffff8114cdf9>] SyS_finit_module+0xb9/0xf0 [ 20.457738] [<ffffffff8184f2f2>] entry_SYSCALL_64_fastpath+0x12/0x76 [ 20.458370] -> #0 (&dev->struct_mutex){+.+.+.}: [ 20.459773] [<ffffffff8110584f>] __lock_acquire+0x191f/0x1ba0 [ 20.460451] [<ffffffff8110644e>] lock_acquire+0xce/0x1c0 [ 20.461074] [<ffffffffa0093c88>] drm_gem_mmap+0x138/0x290 [drm] [ 20.461693] [<ffffffff8121a5ec>] mmap_region+0x3ec/0x670 [ 20.462298] [<ffffffff8121abb2>] do_mmap+0x342/0x420 [ 20.462901] [<ffffffff811fd9d2>] vm_mmap_pgoff+0xb2/0xf0 [ 20.463532] [<ffffffff81218f62>] SyS_mmap_pgoff+0x1f2/0x290 [ 20.464118] [<ffffffff8102187b>] SyS_mmap+0x1b/0x30 [ 20.464702] [<ffffffff8184f2f2>] entry_SYSCALL_64_fastpath+0x12/0x76 [ 20.465289] other info that might help us debug this: [ 20.467179] Chain exists of: &dev->struct_mutex --> &sb->s_type->i_mutex_key#2 --> &mm->mmap_sem [ 20.468928] Possible unsafe locking scenario: [ 20.470161] CPU0 CPU1 [ 20.470745] ---- ---- [ 20.471325] lock(&mm->mmap_sem); [ 20.471902] lock(&sb->s_type->i_mutex_key#2); [ 20.472538] lock(&mm->mmap_sem); [ 20.473118] lock(&dev->struct_mutex); [ 20.473704] *** DEADLOCK *** Signed-off-by: Daniel Stone <daniels@collabora.com> Signed-off-by: Dave Airlie <airlied@redhat.com>
2015-11-03 21:42:31 +00:00
mutex_unlock(&dev->struct_mutex);
guc_fw->guc_fw_fetch_status = GUC_FIRMWARE_NONE;
}