Use drm_clflush* instead of clflush
Subsystems (2)
v4 cover Use drm_clflush* instead of clflush
This patch series re-work a few i915 functions to use drm_clflush_virt_range instead of calling clflush or clflushopt directly. This will prevent errors when building for non-x86 architectures.
v2: s/PAGE_SIZE/sizeof(value) for Re-work intel_write_status_page and added more patches to convert additional clflush/clflushopt to use drm_clflush*. (Michael Cheng)
v3: Drop invalidate_csb_entries and directly invoke drm_clflush_virt_ran
v4: Remove extra memory barriers
Michael Cheng (4):
drm/i915/gt: Re-work intel_write_status_page
drm/i915/gt: Drop invalidate_csb_entries
drm/i915/gt: Re-work reset_csb
drm/i915/: Re-work clflush_write32
drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c | 8 +++----- drivers/gpu/drm/i915/gt/intel_engine.h | 13 ++++--------- .../drm/i915/gt/intel_execlists_submission.c | 17 +++++------------ 3 files changed, 12 insertions(+), 26 deletions(-)
Signature · 1 line
2.25.1
PATCH v4 1/4 drm/i915/gt: Re-work intel_write_status_page
Re-work intel_write_status_page to use drm_clflush_virt_range. This will prevent compiler errors when building for non-x86 architectures.
--- drivers/gpu/drm/i915/gt/intel_engine.h | 13 ++++--------- 1 file changed, 4 insertions(+), 9 deletions(-)
drivers/gpu/drm/i915/gt/intel_engine.h +4 -9
@@ -4,6 +4,7 @@#include <asm/cacheflush.h> #include <drm/drm_util.h> +#include <drm/drm_cache.h> #include <linux/hashtable.h> #include <linux/irq_work.h>
@@ -143,15 +144,9 @@ intel_write_status_page(struct intel_engine_cs *engine, int reg, u32 value)* of extra paranoia to try and ensure that the HWS takes the value * we give and that it doesn't end up trapped inside the CPU! */ -if (static_cpu_has (X86_FEATURE_CLFLUSH )) { -mb (); -clflush (&engine->status_page.addr[reg]); - engine->status_page.addr[reg] = value; -clflush (&engine->status_page.addr[reg]); -mb (); - }else { -WRITE_ONCE (engine->status_page.addr[reg], value); - } +drm_clflush_virt_range (&engine->status_page.addr[reg],sizeof (value)); +WRITE_ONCE (engine->status_page.addr[reg], value); +drm_clflush_virt_range (&engine->status_page.addr[reg],sizeof (value)); }/*
Signature · 1 line
2.25.1
PATCH v4 2/4 drm/i915/gt: Drop invalidate_csb_entries
In reply to Michael ChengDrop invalidate_csb_entries and directly call drm_clflush_virt_range. This allows for one less function call, and prevent complier errors when building for non-x86 architectures.
v2(Michael Cheng): Drop invalidate_csb_entries function and directly
invoke drm_clflush_virt_range. Thanks to Tvrtko for the sugguestion.
--- drivers/gpu/drm/i915/gt/intel_execlists_submission.c | 12 +++--------- 1 file changed, 3 insertions(+), 9 deletions(-)
drivers/gpu/drm/i915/gt/intel_execlists_submission.c +3 -9
@@ -1646,12 +1646,6 @@ cancel_port_requests(struct intel_engine_execlists * const execlists,return inactive; } -static void invalidate_csb_entries (const u64 *first,const u64 *last) -{ -clflush ((void *)first); -clflush ((void *)last); -} -/* * Starting with Gen12, the status has a new format: *
@@ -1999,7 +1993,7 @@ process_csb(struct intel_engine_cs *engine, struct i915_request **inactive)* the wash as hardware, working or not, will need to do the * invalidation before. */ -invalidate_csb_entries (&buf[0 ], &buf[num_entries -1 ]); +drm_clflush_virt_range (&buf[0 ], num_entries *sizeof (buf[0 ]));/* * We assume that any event reflects a change in context flow
@@ -2783,8 +2777,8 @@ static void reset_csb_pointers(struct intel_engine_cs *engine)/* Check that the GPU does indeed update the CSB entries! */ memset (execlists->csb_status,-1 , (reset_value +1 ) *sizeof (u64)); -invalidate_csb_entries (&execlists->csb_status[0 ], - &execlists->csb_status[reset_value]); +drm_clflush_virt_range (&execlists->csb_status[0 ], +sizeof (&execlists->csb_status[reset_value]));/* Once more for luck and our trusty paranoia */ ENGINE_WRITE(engine, RING_CONTEXT_STATUS_PTR,
Signature · 1 line
2.25.1
PATCH v4 3/4 drm/i915/gt: Re-work reset_csb
In reply to Michael ChengUse drm_clflush_virt_range instead of directly invoking clflush. This will prevent compiler errors when building for non-x86 architectures.
v2(Michael Cheng): Remove extra clflush
v3(Michael Cheng): Remove memory barrier since drm_clflush_virt_range
takes care of it.
--- drivers/gpu/drm/i915/gt/intel_execlists_submission.c | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-)
drivers/gpu/drm/i915/gt/intel_execlists_submission.c +2 -3
@@ -2944,9 +2944,8 @@ reset_csb(struct intel_engine_cs *engine, struct i915_request **inactive) {struct intel_engine_execlists *const execlists = &engine->execlists; -mb ();/* paranoia: read the CSB pointers from after the reset */ -clflush (execlists->csb_write); -mb (); +drm_clflush_virt_range (execlists->csb_write, +sizeof (execlists->csb_write)); inactive =process_csb (engine, inactive);/* drain preemption events */
Signature · 1 line
2.25.1
PATCH v4 4/4 drm/i915/: Re-work clflush_write32
In reply to Michael ChengUse drm_clflush_virt_range instead of clflushopt and remove the memory barrier, since drm_clflush_virt_range takes care of that.
--- drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-)
drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c +3 -5
@@ -1332,10 +1332,8 @@ static void *reloc_vaddr(struct i915_vma *vma,static void clflush_write32 (u32 *addr,u32 value,unsigned int flushes) {if (unlikely (flushes & (CLFLUSH_BEFORE |CLFLUSH_AFTER ))) { -if (flushes &CLFLUSH_BEFORE ) { -clflushopt (addr); -mb (); - } +if (flushes &CLFLUSH_BEFORE ) +drm_clflush_virt_range (addr,sizeof (addr)); *addr = value;
@@ -1347,7 +1345,7 @@ static void clflush_write32(u32 *addr, u32 value, unsigned int flushes)* to ensure ordering of clflush wrt to the system. */ if (flushes &CLFLUSH_AFTER ) -clflushopt (addr); +drm_clflush_virt_range (addr,sizeof (addr)); }else *addr = value; }
Signature · 1 line
2.25.1