search for: text_poke_bp

...back and forth between native and paravirt mode. > ([1] lists some representative numbers of the increased memory > footprint.) > > Mechanism: the patching itself is done using stop_machine(). That is > not ideal -- text_poke_stop_machine() was replaced with INT3+emulation > via text_poke_bp(), but I'm using this to address two issues: > 1) emulation in text_poke() can only easily handle a small set > of instructions and this is problematic for inlined pv-ops (and see > a possible alternatives use-case below.) > 2) paravirt patching might have inter-dependendent ops...

...back and forth between native and paravirt mode. > ([1] lists some representative numbers of the increased memory > footprint.) > > Mechanism: the patching itself is done using stop_machine(). That is > not ideal -- text_poke_stop_machine() was replaced with INT3+emulation > via text_poke_bp(), but I'm using this to address two issues: > 1) emulation in text_poke() can only easily handle a small set > of instructions and this is problematic for inlined pv-ops (and see > a possible alternatives use-case below.) > 2) paravirt patching might have inter-dependendent ops...

...[<c07b93a9>] check_sync+0x169/0x6e0 [ 37.496945] [<c049a949>] ? sched_clock_local+0x49/0x180 [ 37.496961] [<c07b9a2d>] debug_dma_sync_single_for_device+0x7d/0x90 [ 37.496989] [<f7e22298>] ? ttm_bo_del_sub_from_lru+0x18/0x50 [ttm] [ 37.497006] [<c040b650>] ? text_poke_bp+0xd0/0xd0 [ 37.497144] [<f85ba340>] nouveau_bo_sync_for_device+0x80/0xc0 [nouveau] [ 37.497228] [<f85ba474>] nouveau_bo_validate+0x34/0x40 [nouveau] [ 37.497310] [<f85ba608>] nouveau_bo_pin+0x188/0x290 [nouveau] [ 37.497391] [<f85b8b60>] ? nv10_bo_put_tile_region...

On 08.04.20 14:08, Peter Zijlstra wrote: > On Tue, Apr 07, 2020 at 10:02:57PM -0700, Ankur Arora wrote: >> Mechanism: the patching itself is done using stop_machine(). That is >> not ideal -- text_poke_stop_machine() was replaced with INT3+emulation >> via text_poke_bp(), but I'm using this to address two issues: >> 1) emulation in text_poke() can only easily handle a small set >> of instructions and this is problematic for inlined pv-ops (and see >> a possible alternatives use-case below.) >> 2) paravirt patching might have in...

...7b9029>] ? check_sync+0x169/0x6e0 > [<c046203e>] warn_slowpath_fmt+0x3e/0x60 > [<c07b9029>] check_sync+0x169/0x6e0 > [<c07b96ad>] debug_dma_sync_single_for_device+0x7d/0x90 > [<f7ece298>] ? ttm_bo_del_sub_from_lru+0x18/0x50 [ttm] > [<c040bef0>] ? text_poke_bp+0xd0/0xd0 > [<f85d96db>] nouveau_bo_sync_for_device+0x8b/0xa0 [nouveau] > [<f85d97c4>] nouveau_bo_validate+0x34/0x40 [nouveau] > [<f85d9958>] nouveau_bo_pin+0x188/0x290 [nouveau] > [<f85d7fe0>] ? nv10_bo_put_tile_region+0x80/0x80 [nouveau] > [<f85ec7fd...

On 11/10/2015 05:00 PM, Thierry Reding wrote: > On Tue, Nov 10, 2015 at 03:54:52PM +0100, Mario Kleiner wrote: >> From: Daniel Vetter <daniel.vetter at ffwll.ch> >> >> Apparently pre-nv50 pageflip events happen before the actual vblank >> period. Therefore that functionality got semi-disabled in >> >> commit af4870e406126b7ac0ae7c7ce5751f25ebe60f28

...sync+0x169/0x6e0 [<c07b9029>] ? check_sync+0x169/0x6e0 [<c046203e>] warn_slowpath_fmt+0x3e/0x60 [<c07b9029>] check_sync+0x169/0x6e0 [<c07b96ad>] debug_dma_sync_single_for_device+0x7d/0x90 [<f7ece298>] ? ttm_bo_del_sub_from_lru+0x18/0x50 [ttm] [<c040bef0>] ? text_poke_bp+0xd0/0xd0 [<f85d96db>] nouveau_bo_sync_for_device+0x8b/0xa0 [nouveau] [<f85d97c4>] nouveau_bo_validate+0x34/0x40 [nouveau] [<f85d9958>] nouveau_bo_pin+0x188/0x290 [nouveau] [<f85d7fe0>] ? nv10_bo_put_tile_region+0x80/0x80 [nouveau] [<f85ec7fd>] nouveau_channel_pre...