linux-toradex.git/drivers/gpu/drm/radeon/cik.c, branch v4.2.2

drm/radeon: Handle irqs only based on irq ring, not irq status regs.

2015-07-08T16:41:36+00:00

Trying to resolve issues with missed vblanks and impossible
values inside delivered kms pageflip completion events showed
that radeon's irq handling sometimes doesn't handle valid irqs,
but silently skips them. This was observed for vblank interrupts.

Although those irqs have corresponding events queued in the gpu's
irq ring at time of interrupt, and therefore the corresponding
handling code gets triggered by these events, the handling code
sometimes silently skipped processing the irq. The reason for those
skips is that the handling code double-checks for each irq event if
the corresponding irq status bits in the irq status registers
are set. Sometimes those bits are not set at time of check
for valid irqs, maybe due to some hardware race on some setups?

The problem only seems to happen on some machine + card combos
sometimes, e.g., never happened during my testing of different PC
cards of the DCE-2/3/4 generation a year ago, but happens consistently
now on two different Apple Mac cards (RV730, DCE-3, Apple iMac and
Evergreen JUNIPER, DCE-4 in a Apple MacPro). It also doesn't happen
at each interrupt but only occassionally every couple of
hundred or thousand vblank interrupts.

This results in XOrg warning messages like

"[  7084.472] (WW) RADEON(0): radeon_dri2_flip_event_handler:
Pageflip completion event has impossible msc 420120 < target_msc 420121"

as well as skipped frames and problems for applications that
use kms pageflip events or vblank events, e.g., users of DRI2 and
DRI3/Present, Waylands Weston compositor, etc. See also

https://bugs.freedesktop.org/show_bug.cgi?id=85203

After some talking to Alex and Michel, we decided to fix this
by turning the double-check for asserted irq status bits into a
warning. Whenever a irq event is queued in the IH ring, always
execute the corresponding interrupt handler. Still check the irq
status bits, but only to log a DRM_DEBUG message on a mismatch.

This fixed the problems reliably on both previously failing
cards, RV-730 dual-head tested on both crtcs (pipes D1 and D2)
and a triple-output Juniper HD-5770 card tested on all three
available crtcs (D1/D2/D3). The r600 and evergreen irq handling
is therefore tested, but the cik an si handling is only compile
tested due to lack of hw.

Reviewed-by: Christian König 
Signed-off-by: Mario Kleiner 
CC: Michel Dänzer 
CC: Alex Deucher 
CC:  # v3.16+
Signed-off-by: Alex Deucher

drm/radeon: compute ring fix hibernation (CI GPU family) v2.

2015-06-29T15:21:41+00:00

In order for hibernation to reliably work we need to cleanup more
thoroughly the compute ring. Hibernation is different from suspend
resume as when we resume from hibernation the hardware is first
fully initialize by regular kernel then freeze callback happens
(which correspond to a suspend inside the radeon kernel driver)
and turn off each of the block. It turns out we were not cleanly
shutting down the compute ring. This patch fix that.

Hibernation and suspend to ram were tested (several times) on :
Bonaire
Hawaii
Mullins
Kaveri
Kabini

Changed since v1:
  - Factor the ring stop logic into a function taking ring as arg.

Cc: stable@vger.kernel.org
Signed-off-by: Jérôme Glisse 
Reviewed-by: Christian König 
Signed-off-by: Alex Deucher

Merge tag 'v4.1-rc6' into drm-next

2015-06-03T23:23:51+00:00

Linux 4.1-rc6

backmerge 4.1-rc6 as some of the later pull reqs are based on newer bases
and I'd prefer to do the fixup myself.

radeon: Deinline indirect register accessor functions

2015-05-28T18:52:40+00:00

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: Denys Vlasenko 
Cc: Christian König 
Cc: Alex Deucher 
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Alex Deucher

drm/radeon: partially revert "fix VM_CONTEXT*_PAGE_TABLE_END_ADDR handling"

2015-05-28T13:54:43+00:00

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: Christian König 
CC: stable@vger.kernel.org
Signed-off-by: Alex Deucher

drm/radeon: fix VM_CONTEXT*_PAGE_TABLE_END_ADDR handling

2015-05-12T13:12:42+00:00

The mapping range is inclusive between starting and ending addresses.

Signed-off-by: Christian König 
CC: stable@vger.kernel.org
Signed-off-by: Alex Deucher

radeon/cik: add support for short HPD irqs

2015-03-19T16:26:47+00:00

This adds support to process short HPD irqs on CIK gpus.

Signed-off-by: Alex Deucher

drm/radeon: add get_allowed_info_register for CIK

2015-03-19T16:26:41+00:00

Registers that can be fetched from the info ioctl.

Tested-by: Marek Olšák 
Signed-off-by: Alex Deucher

drm/radeon: do a posting read in cik_set_irq

2015-03-03T22:28:29+00:00

To make sure the writes go through the pci bridge.

bug:
https://bugzilla.kernel.org/show_bug.cgi?id=90741

Signed-off-by: Alex Deucher 
Cc: stable@vger.kernel.org

drm/radeon: enable SRBM timeout interrupt on CIK v2

2015-02-25T21:06:07+00:00

v2: disable it on suspend

Signed-off-by: Christian König 
Signed-off-by: Alex Deucher