Replace packet2's with packet0 writes to UVD_NO_OP.  The
value written to UVD_NO_OP does not matter.
Reviewed-by: NChristian König <christian.koenig@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

In some cases, like when freezing for hibernation, we need to be
able to force hard reset even if no engine are stuck. This patch
add a bool option to current asic reset callback to allow to force
hard reset on asic that supports it.
Reviewed-by: NChristian König <christian.koenig@amd.com>
Signed-off-by: NJérôme Glisse <jglisse@redhat.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Cc: Christian König <christian.koenig@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

This match the exact same control flow as existing code. It just
use goto instead of multiple levels of if/else. It also clarify
early initialization failures by clearing rdev->has_vce doing so
does not change end result from hardware point of view, it only
avoids printing more error messages down the line and thus only
the original error is reported.
Acked-by: NChristian König <christian.koenig@amd.com>
Signed-off-by: NJérôme Glisse <jglisse@redhat.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Cc: Christian König <christian.koenig@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

This match the exact same control flow as existing code. It just
use goto instead of multiple levels of if/else. It also clarify
early initialization failures by clearing rdev->has_uvd doing so
does not change end result from hardware point of view, it only
avoids printing more error messages down the line and thus only
the original error is reported.
Acked-by: NChristian König <christian.koenig@amd.com>
Signed-off-by: NJérôme Glisse <jglisse@redhat.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Cc: Christian König <christian.koenig@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

I hate doing this but it hurts my eyes to go over code that does not
comply with indentation rules. Only thing that is not only space change
is in atom.c all other files are space indentation issues.
Acked-by: NChristian König <christian.koenig@amd.com>
Signed-off-by: NJérôme Glisse <jglisse@redhat.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

Cayman does not have vce.  There were a few places in the
shared cayman/TV code where we were trying to do vce stuff.

v2: remove -ENOENT check
Reviewed-by: NChristian König <christian.koenig@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

This patch deinlines indirect register accessor functions.

These functions perform two mmio accesses, framed by spin lock/unlock.
Spin lock/unlock by itself takes more than 50 cycles in ideal case
(if lock is exclusively cached on current CPU).

With this .config: http://busybox.net/~vda/kernel_config,
after uninlining these functions have sizes and callsite counts
as follows:

r600_uvd_ctx_rreg: 111 bytes, 4 callsites
r600_uvd_ctx_wreg: 113 bytes, 5 callsites
eg_pif_phy0_rreg: 106 bytes, 13 callsites
eg_pif_phy0_wreg: 108 bytes, 13 callsites
eg_pif_phy1_rreg: 107 bytes, 13 callsites
eg_pif_phy1_wreg: 108 bytes, 13 callsites
rv370_pcie_rreg: 111 bytes, 21 callsites
rv370_pcie_wreg: 113 bytes, 24 callsites
r600_rcu_rreg: 111 bytes, 16 callsites
r600_rcu_wreg: 113 bytes, 25 callsites
cik_didt_rreg: 106 bytes, 10 callsites
cik_didt_wreg: 107 bytes, 10 callsites
tn_smc_rreg: 106 bytes, 126 callsites
tn_smc_wreg: 107 bytes, 116 callsites
eg_cg_rreg: 107 bytes, 20 callsites
eg_cg_wreg: 108 bytes, 52 callsites

Functions r100_mm_rreg() and r100_mm_rreg() have a fast path and
a locked (slow) path. This patch deinlines only slow path.

r100_mm_rreg_slow: 78 bytes, 2083 callsites
r100_mm_wreg_slow: 81 bytes, 3570 callsites

Reduction in code size is more than 65,000 bytes:

    text     data      bss       dec     hex filename
85740176 22294680 20627456 128662312 7ab3b28 vmlinux.before
85674192 22294776 20627456 128598664 7aa4288 vmlinux
Signed-off-by: NDenys Vlasenko <dvlasenk@redhat.com>
Cc: Christian König <christian.koenig@amd.com>
Cc: Alex Deucher <alexander.deucher@amd.com>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

We have that bug for years and some users report side effects when fixing it on older hardware.

So revert it for VM_CONTEXT0_PAGE_TABLE_END_ADDR, but keep it for VM 1-15.
Signed-off-by: NChristian König <christian.koenig@amd.com>
CC: stable@vger.kernel.org
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

Initial support for VCE 1.0 using newest firmware.

v2: rebased
v3: fix for TN
v4: fix FW size calculation
Signed-off-by: NChristian König <christian.koenig@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

This implements the function to set the vce clocks
on TN hardware.
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

The mapping range is inclusive between starting and ending addresses.
Signed-off-by: NChristian König <christian.koenig@amd.com>
CC: stable@vger.kernel.org
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

Registers that can be fetched from the info ioctl.
Tested-by: NMarek Olšák <marek.olsak@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

The logic was reversed from what the hw actually exposed.
Fixes graphics corruption in certain harvest configurations.
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org

Signed-off-by: NChristian König <christian.koenig@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

Reviewed-by: NChristian König <christian.koenig@amd.com>
Signed-off-by: NSlava Grigorev <slava.grigorev@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

Reviewed-by: NChristian König <christian.koenig@amd.com>
Signed-off-by: NSlava Grigorev <slava.grigorev@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

We need to wait for the GPUVM flush to complete.  There
was some confusion as to how this mechanism was supposed
to work.  The operation is not atomic.  For GPU initiated
invalidations you need to read back a VM register to
introduce enough latency for the update to complete.

v2: drop gart changes
v3: just read back rather than polling
Reviewed-by: NChristian König <christian.koenig@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org

Use multiple VMIDs for each VM, one for each ring. That allows
us to execute flushes separately on each ring, still not ideal
cause in a lot of cases rings can share IDs.
Signed-off-by: NChristian König <christian.koenig@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

Use ring structure instead of index and provide vm_id and pd_addr separately.
Signed-off-by: NChristian König <christian.koenig@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

This fixes a problem with GPU resets and TLB flushes on SI/CIK.
Signed-off-by: NChristian König <christian.koenig@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

It isn't necessary for command streams generated by the kernel (at least
not while we aren't storing ring or indirect buffers in VRAM).
Signed-off-by: NMichel Dänzer <michel.daenzer@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

Doesn't seem necessary, the GART table memory should be persistent.
Signed-off-by: NMichel Dänzer <michel.daenzer@amd.com>
Reviewed-by: NChristian König <christian.koenig@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

Query to find out how many compute units on a GPU.
Useful for OpenCL usermode drivers.
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

Signed-off-by: NChristian König <christian.koenig@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

Replace occurrences of "v & 0xffffffff" with lower_32_bits(v)
when it's next to an upper_32_bits(v). Also remove unnecessary
"upper_32_bits(v) & 0xffffffff" code snippets.
Signed-off-by: NChristian König <christian.koenig@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

This patch makes it possible to decide how many address
bits are spend on the page directory vs the page tables.

v2: remove unintended change
Signed-off-by: NChristian König <christian.koenig@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

This patch implements support for VRAM page table entry compression.
PTE construction is enhanced to identify physically contiguous page
ranges and mark them in the PTE fragment field. L1/L2 TLB support is
enabled for 64KB (SI/CIK) and 256KB (NI) PTE fragments, significantly
improving TLB utilization for VRAM allocations.

Linear store bandwidth is improved from 60GB/s to 125GB/s on Pitcairn.
Unigine Heaven 3.0 sees an average improvement from 24.7 to 27.7 FPS
on default settings at 1920x1200 resolution with vsync disabled.

See main comment in radeon_vm.c for a technical description.

v2 (chk): rebased and simplified.
v3 (chk): add missing hw setup
v4 (chk): rebased on current drm-fixes-3.15
v5 (chk): fix comments and commit text
Signed-off-by: NJay Cornwall <jay@jcornwall.me>
Signed-off-by: NChristian König <christian.koenig@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

Moving the pm resume up in the init order to fix
dpm seems to have regressed somes cases with the old
pm code.  Move it back to late resume.
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

The reason for the false positives was fixed quite some time ago and since
most engines can still execute NOPs while being locked up it leads to false
negatives.
Signed-off-by: NChristian König <christian.koenig@amd.com>
Reviewed-by: NAlex Deucher <alexander.deucher@amd.com>

In all cases where it really matters we are using the read functions anyway.
Signed-off-by: NChristian König <christian.koenig@amd.com>
Reviewed-by: NAlex Deucher <alexander.deucher@amd.com>

If we are not able to properly initialize one of the gpu
engines for buffer paging, we limit vram to the size of
the cpu visible aperture.  We generally either use the gfx
or dma engine to do this.  Clean up the size limiting code
to only adjust the size based on what ring is selected
for buffer paging rather than making assumptions about which
engine is selected for paging.
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>
Reviewed-by: NChristian König <christian.koenig@amd.com>

We need to set the engine bit to select the ME and
also set the full cache bit.  Should help stability
on TN and cayman.

V2: fix up surface sync in ib execute as well
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org

pci config reset is a low level reset that resets
the entire chip from the bus interface.  It can
be more reliable if soft reset fails.

v2: put behind module parameter
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

Fill in asic family specific versions rather than
using the generic version.  This lets us handle asic
specific differences more easily.  In this case, we
disable sw swapping of the rtpr writeback value on
r6xx+ since the hw does it for us.  Fixes bogus
rptr readback on BE systems.

v2: remove missed cpu_to_le32(), add comments
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

We need more control over the ordering of dpm init with
respect to the rest of the asic.  Specifically, the SMC
has to be initialized before the rlc and cg/pg.  The pm
code currently initializes late in the driver, but we need
it to happen much earlier so move pm handling into the asic
specific callbacks.

This makes dpm more reliable and makes clockgating work
properly on CIK parts and should help on SI parts as well.
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

We need to reorder the driver init sequence to better accomodate
dpm which needs to be loaded earlier in the init sequence.  Move
fw init up so that it's available for dpm init.
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

Fixes gfx corruption on certain TN/RL parts.

bug:
https://bugs.freedesktop.org/show_bug.cgi?id=60389Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org

The DMA ring seems to be stable now.

v2: remove pt_ring_index as well
Signed-off-by: NChristian König <christian.koenig@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>

Prevent driver load problems if the smc is missing.

bug:
https://bugzilla.kernel.org/show_bug.cgi?id=63011Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>
Tested-by: NMikko Rapeli <mikko.rapeli@iki.fi>
Cc: stable@vger.kernel.org

The vram scratch buffer needs to be initialized
before the mc is programmed otherwise we program
0 as the GPU address of the default GPU fault
page.  In most cases we put vram at zero anyway and
reserve a page for the legacy vga buffer so in practice
this shouldn't cause any problems, but better to make
it correct.

Was changed in:
6fab3febReported-by: NFrankR Huang <FrankR.Huang@amd.com>
Signed-off-by: NAlex Deucher <alexander.deucher@amd.com>
Cc: stable@vger.kernel.org