linux/drivers/gpu/drm/i915/intel_uncore.h
Dave Airlie 1176d15f0f Merge tag 'drm-intel-gt-next-2021-10-08' of git://anongit.freedesktop.org/drm/drm-intel into drm-next
UAPI Changes:

- Add uAPI for using PXP protected objects

  Mesa changes: https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/8064

- Add PCI IDs and LMEM discovery/placement uAPI for DG1

  Mesa changes: https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/11584

- Disable engine bonding on Gen12+ except TGL, RKL and ADL-S

Cross-subsystem Changes:

- Merges 'tip/locking/wwmutex' branch (core kernel tip)
- "mei: pxp: export pavp client to me client bus"

Core Changes:

- Update ttm_move_memcpy for async use (Thomas)

Driver Changes:

- Enable GuC submission by default on DG1 (Matt B)
- Add PXP (Protected Xe Path) support for Gen12 integrated (Daniele,
  Sean, Anshuman)
  See "drm/i915/pxp: add PXP documentation" for details!
- Remove force_probe protection for ADL-S (Raviteja)
- Add base support for XeHP/XeHP SDV (Matt R, Stuart, Lucas)
- Handle DRI_PRIME=1 on Intel igfx + Intel dgfx hybrid graphics setup (Tvrtko)
- Use Transparent Hugepages when IOMMU is enabled (Tvrtko, Chris)
- Implement LMEM backup and restore for suspend / resume (Thomas)
- Report INSTDONE_GEOM values in error state for DG2 (Matt R)
- Add DG2-specific shadow register table (Matt R)
- Update Gen11/Gen12/XeHP shadow register tables (Matt R)
- Maintain backward-compatible nested batch behavior on TGL+ (Matt R)
- Add new LRI reg offsets for DG2 (Akeem)
- Initialize unused MOCS entries to device specific values (Ayaz)
- Track and use the correct UC MOCS index on Gen12 (Ayaz)
- Add separate MOCS table for Gen12 devices other than TGL/RKL (Ayaz)
- Simplify the locking and eliminate some RCU usage (Daniel)
- Add some flushing for the 64K GTT path (Matt A)
- Mark GPU wedging on driver unregister unrecoverable (Janusz)

- Major rework in the GuC codebase, simplify locking and add docs (Matt B)
- Add DG1 GuC/HuC firmwares (Daniele, Matt B)
- Remember to call i915_sw_fence_fini on guc_state.blocked (Matt A)
- Use "gt" forcewake domain name for error messages instead of "blitter" (Matt R)
- Drop now duplicate LMEM uAPI RFC kerneldoc section (Daniel)
- Fix early tracepoints for requests (Matt A)
- Use locked access to ctx->engines in set_priority (Daniel)
- Convert gen6/gen7/gen8 read operations to fwtable (Matt R)
- Drop gen11/gen12 specific mmio write handlers (Matt R)
- Drop gen11 specific mmio read handlers (Matt R)
- Use designated initializers for init/exit table (Kees)
- Fix syncmap memory leak (Matt B)
- Add pretty printing for buddy allocator state debug (Matt A)
- Fix potential error pointer dereference in pinned_context() (Dan)
- Remove IS_ACTIVE macro (Lucas)
- Static code checker fixes (Nathan)
- Clean up disabled warnings (Nathan)
- Increase timeout in i915_gem_contexts selftests 5x for GuC submission (Matt B)
- Ensure wa_init_finish() is called for ctx workaround list (Matt R)
- Initialize L3CC table in mocs init (Sreedhar, Ayaz, Ram)
- Get PM ref before accessing HW register (Vinay)
- Move __i915_gem_free_object to ttm_bo_destroy (Maarten)
- Deduplicate frequency dump on debugfs (Lucas)
- Make wa list per-gt (Venkata)
- Do not define dummy vma in stack (Venkata)
- Take pinning into account in __i915_gem_object_is_lmem (Matt B, Thomas)
- Do not report currently active engine when describing objects (Tvrtko)
- Fix pdfdocs build error by removing nested grid from GuC docs (Akira)
- Remove false warning from the rps worker (Tejas)
- Flush buffer pools on driver remove (Janusz)
- Fix runtime pm handling in i915_gem_shrink (Maarten)
- Rework TTM object initialization slightly (Thomas)
- Use fixed offset for PTEs location (Michal Wa)
- Verify result from CTB (de)register action and improve error messages (Michal Wa)
- Fix bug in user proto-context creation that leaked contexts (Matt B)

- Re-use Gen11 forcewake read functions on Gen12 (Matt R)
- Make shadow tables range-based (Matt R)
- Ditch the i915_gem_ww_ctx loop member (Thomas, Maarten)
- Use NULL instead of 0 where appropriate (Ville)
- Rename pci/debugfs functions to respect file prefix (Jani, Lucas)
- Drop guc_communication_enabled (Daniele)
- Selftest fixes (Thomas, Daniel, Matt A, Maarten)
- Clean up inconsistent indenting (Colin)
- Use direction definition DMA_BIDIRECTIONAL instead of
  PCI_DMA_BIDIRECTIONAL (Cai)
- Add "intel_" as prefix in set_mocs_index() (Ayaz)

From: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/YWAO80MB2eyToYoy@jlahtine-mobl.ger.corp.intel.com
Signed-off-by: Dave Airlie <airlied@redhat.com>
2021-10-11 18:09:39 +10:00

456 lines
14 KiB
C

/*
* Copyright © 2017 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.
*
*/
#ifndef __INTEL_UNCORE_H__
#define __INTEL_UNCORE_H__
#include <linux/spinlock.h>
#include <linux/notifier.h>
#include <linux/hrtimer.h>
#include <linux/io-64-nonatomic-lo-hi.h>
#include "i915_reg.h"
struct drm_i915_private;
struct intel_runtime_pm;
struct intel_uncore;
struct intel_gt;
struct intel_uncore_mmio_debug {
spinlock_t lock; /** lock is also taken in irq contexts. */
int unclaimed_mmio_check;
int saved_mmio_check;
u32 suspend_count;
};
enum forcewake_domain_id {
FW_DOMAIN_ID_RENDER = 0,
FW_DOMAIN_ID_GT, /* also includes blitter engine */
FW_DOMAIN_ID_MEDIA,
FW_DOMAIN_ID_MEDIA_VDBOX0,
FW_DOMAIN_ID_MEDIA_VDBOX1,
FW_DOMAIN_ID_MEDIA_VDBOX2,
FW_DOMAIN_ID_MEDIA_VDBOX3,
FW_DOMAIN_ID_MEDIA_VDBOX4,
FW_DOMAIN_ID_MEDIA_VDBOX5,
FW_DOMAIN_ID_MEDIA_VDBOX6,
FW_DOMAIN_ID_MEDIA_VDBOX7,
FW_DOMAIN_ID_MEDIA_VEBOX0,
FW_DOMAIN_ID_MEDIA_VEBOX1,
FW_DOMAIN_ID_MEDIA_VEBOX2,
FW_DOMAIN_ID_MEDIA_VEBOX3,
FW_DOMAIN_ID_COUNT
};
enum forcewake_domains {
FORCEWAKE_RENDER = BIT(FW_DOMAIN_ID_RENDER),
FORCEWAKE_GT = BIT(FW_DOMAIN_ID_GT),
FORCEWAKE_MEDIA = BIT(FW_DOMAIN_ID_MEDIA),
FORCEWAKE_MEDIA_VDBOX0 = BIT(FW_DOMAIN_ID_MEDIA_VDBOX0),
FORCEWAKE_MEDIA_VDBOX1 = BIT(FW_DOMAIN_ID_MEDIA_VDBOX1),
FORCEWAKE_MEDIA_VDBOX2 = BIT(FW_DOMAIN_ID_MEDIA_VDBOX2),
FORCEWAKE_MEDIA_VDBOX3 = BIT(FW_DOMAIN_ID_MEDIA_VDBOX3),
FORCEWAKE_MEDIA_VDBOX4 = BIT(FW_DOMAIN_ID_MEDIA_VDBOX4),
FORCEWAKE_MEDIA_VDBOX5 = BIT(FW_DOMAIN_ID_MEDIA_VDBOX5),
FORCEWAKE_MEDIA_VDBOX6 = BIT(FW_DOMAIN_ID_MEDIA_VDBOX6),
FORCEWAKE_MEDIA_VDBOX7 = BIT(FW_DOMAIN_ID_MEDIA_VDBOX7),
FORCEWAKE_MEDIA_VEBOX0 = BIT(FW_DOMAIN_ID_MEDIA_VEBOX0),
FORCEWAKE_MEDIA_VEBOX1 = BIT(FW_DOMAIN_ID_MEDIA_VEBOX1),
FORCEWAKE_MEDIA_VEBOX2 = BIT(FW_DOMAIN_ID_MEDIA_VEBOX2),
FORCEWAKE_MEDIA_VEBOX3 = BIT(FW_DOMAIN_ID_MEDIA_VEBOX3),
FORCEWAKE_ALL = BIT(FW_DOMAIN_ID_COUNT) - 1,
};
struct intel_uncore_fw_get {
void (*force_wake_get)(struct intel_uncore *uncore,
enum forcewake_domains domains);
};
struct intel_uncore_funcs {
enum forcewake_domains (*read_fw_domains)(struct intel_uncore *uncore,
i915_reg_t r);
enum forcewake_domains (*write_fw_domains)(struct intel_uncore *uncore,
i915_reg_t r);
u8 (*mmio_readb)(struct intel_uncore *uncore,
i915_reg_t r, bool trace);
u16 (*mmio_readw)(struct intel_uncore *uncore,
i915_reg_t r, bool trace);
u32 (*mmio_readl)(struct intel_uncore *uncore,
i915_reg_t r, bool trace);
u64 (*mmio_readq)(struct intel_uncore *uncore,
i915_reg_t r, bool trace);
void (*mmio_writeb)(struct intel_uncore *uncore,
i915_reg_t r, u8 val, bool trace);
void (*mmio_writew)(struct intel_uncore *uncore,
i915_reg_t r, u16 val, bool trace);
void (*mmio_writel)(struct intel_uncore *uncore,
i915_reg_t r, u32 val, bool trace);
};
struct intel_forcewake_range {
u32 start;
u32 end;
enum forcewake_domains domains;
};
/* Other register ranges (e.g., shadow tables, MCR tables, etc.) */
struct i915_range {
u32 start;
u32 end;
};
struct intel_uncore {
void __iomem *regs;
struct drm_i915_private *i915;
struct intel_runtime_pm *rpm;
spinlock_t lock; /** lock is also taken in irq contexts. */
unsigned int flags;
#define UNCORE_HAS_FORCEWAKE BIT(0)
#define UNCORE_HAS_FPGA_DBG_UNCLAIMED BIT(1)
#define UNCORE_HAS_DBG_UNCLAIMED BIT(2)
#define UNCORE_HAS_FIFO BIT(3)
const struct intel_forcewake_range *fw_domains_table;
unsigned int fw_domains_table_entries;
/*
* Shadowed registers are special cases where we can safely write
* to the register *without* grabbing forcewake.
*/
const struct i915_range *shadowed_reg_table;
unsigned int shadowed_reg_table_entries;
struct notifier_block pmic_bus_access_nb;
const struct intel_uncore_fw_get *fw_get_funcs;
struct intel_uncore_funcs funcs;
unsigned int fifo_count;
enum forcewake_domains fw_domains;
enum forcewake_domains fw_domains_active;
enum forcewake_domains fw_domains_timer;
enum forcewake_domains fw_domains_saved; /* user domains saved for S3 */
struct intel_uncore_forcewake_domain {
struct intel_uncore *uncore;
enum forcewake_domain_id id;
enum forcewake_domains mask;
unsigned int wake_count;
bool active;
struct hrtimer timer;
u32 __iomem *reg_set;
u32 __iomem *reg_ack;
} *fw_domain[FW_DOMAIN_ID_COUNT];
unsigned int user_forcewake_count;
struct intel_uncore_mmio_debug *debug;
};
/* Iterate over initialised fw domains */
#define for_each_fw_domain_masked(domain__, mask__, uncore__, tmp__) \
for (tmp__ = (mask__); tmp__ ;) \
for_each_if(domain__ = (uncore__)->fw_domain[__mask_next_bit(tmp__)])
#define for_each_fw_domain(domain__, uncore__, tmp__) \
for_each_fw_domain_masked(domain__, (uncore__)->fw_domains, uncore__, tmp__)
static inline bool
intel_uncore_has_forcewake(const struct intel_uncore *uncore)
{
return uncore->flags & UNCORE_HAS_FORCEWAKE;
}
static inline bool
intel_uncore_has_fpga_dbg_unclaimed(const struct intel_uncore *uncore)
{
return uncore->flags & UNCORE_HAS_FPGA_DBG_UNCLAIMED;
}
static inline bool
intel_uncore_has_dbg_unclaimed(const struct intel_uncore *uncore)
{
return uncore->flags & UNCORE_HAS_DBG_UNCLAIMED;
}
static inline bool
intel_uncore_has_fifo(const struct intel_uncore *uncore)
{
return uncore->flags & UNCORE_HAS_FIFO;
}
u32 intel_uncore_read_with_mcr_steering_fw(struct intel_uncore *uncore,
i915_reg_t reg,
int slice, int subslice);
u32 intel_uncore_read_with_mcr_steering(struct intel_uncore *uncore,
i915_reg_t reg, int slice, int subslice);
void
intel_uncore_mmio_debug_init_early(struct intel_uncore_mmio_debug *mmio_debug);
void intel_uncore_init_early(struct intel_uncore *uncore,
struct drm_i915_private *i915);
int intel_uncore_init_mmio(struct intel_uncore *uncore);
void intel_uncore_prune_engine_fw_domains(struct intel_uncore *uncore,
struct intel_gt *gt);
bool intel_uncore_unclaimed_mmio(struct intel_uncore *uncore);
bool intel_uncore_arm_unclaimed_mmio_detection(struct intel_uncore *uncore);
void intel_uncore_fini_mmio(struct intel_uncore *uncore);
void intel_uncore_suspend(struct intel_uncore *uncore);
void intel_uncore_resume_early(struct intel_uncore *uncore);
void intel_uncore_runtime_resume(struct intel_uncore *uncore);
void assert_forcewakes_inactive(struct intel_uncore *uncore);
void assert_forcewakes_active(struct intel_uncore *uncore,
enum forcewake_domains fw_domains);
const char *intel_uncore_forcewake_domain_to_str(const enum forcewake_domain_id id);
enum forcewake_domains
intel_uncore_forcewake_for_reg(struct intel_uncore *uncore,
i915_reg_t reg, unsigned int op);
#define FW_REG_READ (1)
#define FW_REG_WRITE (2)
void intel_uncore_forcewake_get(struct intel_uncore *uncore,
enum forcewake_domains domains);
void intel_uncore_forcewake_put(struct intel_uncore *uncore,
enum forcewake_domains domains);
void intel_uncore_forcewake_flush(struct intel_uncore *uncore,
enum forcewake_domains fw_domains);
/*
* Like above but the caller must manage the uncore.lock itself.
* Must be used with intel_uncore_read_fw() and friends.
*/
void intel_uncore_forcewake_get__locked(struct intel_uncore *uncore,
enum forcewake_domains domains);
void intel_uncore_forcewake_put__locked(struct intel_uncore *uncore,
enum forcewake_domains domains);
void intel_uncore_forcewake_user_get(struct intel_uncore *uncore);
void intel_uncore_forcewake_user_put(struct intel_uncore *uncore);
int __intel_wait_for_register(struct intel_uncore *uncore,
i915_reg_t reg,
u32 mask,
u32 value,
unsigned int fast_timeout_us,
unsigned int slow_timeout_ms,
u32 *out_value);
static inline int
intel_wait_for_register(struct intel_uncore *uncore,
i915_reg_t reg,
u32 mask,
u32 value,
unsigned int timeout_ms)
{
return __intel_wait_for_register(uncore, reg, mask, value, 2,
timeout_ms, NULL);
}
int __intel_wait_for_register_fw(struct intel_uncore *uncore,
i915_reg_t reg,
u32 mask,
u32 value,
unsigned int fast_timeout_us,
unsigned int slow_timeout_ms,
u32 *out_value);
static inline int
intel_wait_for_register_fw(struct intel_uncore *uncore,
i915_reg_t reg,
u32 mask,
u32 value,
unsigned int timeout_ms)
{
return __intel_wait_for_register_fw(uncore, reg, mask, value,
2, timeout_ms, NULL);
}
/* register access functions */
#define __raw_read(x__, s__) \
static inline u##x__ __raw_uncore_read##x__(const struct intel_uncore *uncore, \
i915_reg_t reg) \
{ \
return read##s__(uncore->regs + i915_mmio_reg_offset(reg)); \
}
#define __raw_write(x__, s__) \
static inline void __raw_uncore_write##x__(const struct intel_uncore *uncore, \
i915_reg_t reg, u##x__ val) \
{ \
write##s__(val, uncore->regs + i915_mmio_reg_offset(reg)); \
}
__raw_read(8, b)
__raw_read(16, w)
__raw_read(32, l)
__raw_read(64, q)
__raw_write(8, b)
__raw_write(16, w)
__raw_write(32, l)
__raw_write(64, q)
#undef __raw_read
#undef __raw_write
#define __uncore_read(name__, x__, s__, trace__) \
static inline u##x__ intel_uncore_##name__(struct intel_uncore *uncore, \
i915_reg_t reg) \
{ \
return uncore->funcs.mmio_read##s__(uncore, reg, (trace__)); \
}
#define __uncore_write(name__, x__, s__, trace__) \
static inline void intel_uncore_##name__(struct intel_uncore *uncore, \
i915_reg_t reg, u##x__ val) \
{ \
uncore->funcs.mmio_write##s__(uncore, reg, val, (trace__)); \
}
__uncore_read(read8, 8, b, true)
__uncore_read(read16, 16, w, true)
__uncore_read(read, 32, l, true)
__uncore_read(read16_notrace, 16, w, false)
__uncore_read(read_notrace, 32, l, false)
__uncore_write(write8, 8, b, true)
__uncore_write(write16, 16, w, true)
__uncore_write(write, 32, l, true)
__uncore_write(write_notrace, 32, l, false)
/* Be very careful with read/write 64-bit values. On 32-bit machines, they
* will be implemented using 2 32-bit writes in an arbitrary order with
* an arbitrary delay between them. This can cause the hardware to
* act upon the intermediate value, possibly leading to corruption and
* machine death. For this reason we do not support intel_uncore_write64,
* or uncore->funcs.mmio_writeq.
*
* When reading a 64-bit value as two 32-bit values, the delay may cause
* the two reads to mismatch, e.g. a timestamp overflowing. Also note that
* occasionally a 64-bit register does not actually support a full readq
* and must be read using two 32-bit reads.
*
* You have been warned.
*/
__uncore_read(read64, 64, q, true)
static inline u64
intel_uncore_read64_2x32(struct intel_uncore *uncore,
i915_reg_t lower_reg, i915_reg_t upper_reg)
{
u32 upper, lower, old_upper, loop = 0;
upper = intel_uncore_read(uncore, upper_reg);
do {
old_upper = upper;
lower = intel_uncore_read(uncore, lower_reg);
upper = intel_uncore_read(uncore, upper_reg);
} while (upper != old_upper && loop++ < 2);
return (u64)upper << 32 | lower;
}
#define intel_uncore_posting_read(...) ((void)intel_uncore_read_notrace(__VA_ARGS__))
#define intel_uncore_posting_read16(...) ((void)intel_uncore_read16_notrace(__VA_ARGS__))
#undef __uncore_read
#undef __uncore_write
/* These are untraced mmio-accessors that are only valid to be used inside
* critical sections, such as inside IRQ handlers, where forcewake is explicitly
* controlled.
*
* Think twice, and think again, before using these.
*
* As an example, these accessors can possibly be used between:
*
* spin_lock_irq(&uncore->lock);
* intel_uncore_forcewake_get__locked();
*
* and
*
* intel_uncore_forcewake_put__locked();
* spin_unlock_irq(&uncore->lock);
*
*
* Note: some registers may not need forcewake held, so
* intel_uncore_forcewake_{get,put} can be omitted, see
* intel_uncore_forcewake_for_reg().
*
* Certain architectures will die if the same cacheline is concurrently accessed
* by different clients (e.g. on Ivybridge). Access to registers should
* therefore generally be serialised, by either the dev_priv->uncore.lock or
* a more localised lock guarding all access to that bank of registers.
*/
#define intel_uncore_read_fw(...) __raw_uncore_read32(__VA_ARGS__)
#define intel_uncore_write_fw(...) __raw_uncore_write32(__VA_ARGS__)
#define intel_uncore_write64_fw(...) __raw_uncore_write64(__VA_ARGS__)
#define intel_uncore_posting_read_fw(...) ((void)intel_uncore_read_fw(__VA_ARGS__))
static inline void intel_uncore_rmw(struct intel_uncore *uncore,
i915_reg_t reg, u32 clear, u32 set)
{
u32 old, val;
old = intel_uncore_read(uncore, reg);
val = (old & ~clear) | set;
if (val != old)
intel_uncore_write(uncore, reg, val);
}
static inline void intel_uncore_rmw_fw(struct intel_uncore *uncore,
i915_reg_t reg, u32 clear, u32 set)
{
u32 old, val;
old = intel_uncore_read_fw(uncore, reg);
val = (old & ~clear) | set;
if (val != old)
intel_uncore_write_fw(uncore, reg, val);
}
static inline int intel_uncore_write_and_verify(struct intel_uncore *uncore,
i915_reg_t reg, u32 val,
u32 mask, u32 expected_val)
{
u32 reg_val;
intel_uncore_write(uncore, reg, val);
reg_val = intel_uncore_read(uncore, reg);
return (reg_val & mask) != expected_val ? -EINVAL : 0;
}
#define raw_reg_read(base, reg) \
readl(base + i915_mmio_reg_offset(reg))
#define raw_reg_write(base, reg, value) \
writel(value, base + i915_mmio_reg_offset(reg))
#endif /* !__INTEL_UNCORE_H__ */