Commit 71b6b255 authored by Umesh Nerlige Ramappa's avatar Umesh Nerlige Ramappa Committed by Rodrigo Vivi

i915/uncore: Acquire fw before loop in intel_uncore_read64_2x32

PMU reads the GT timestamp as a 2x32 mmio read and since upper and lower
32 bit registers are read in a loop, there is a latency involved between
getting the GT timestamp and the CPU timestamp. As part of the
resolution, refactor intel_uncore_read64_2x32 to acquire forcewake and
uncore lock prior to reading upper and lower regs.
Signed-off-by: default avatarUmesh Nerlige Ramappa <umesh.nerlige.ramappa@intel.com>
Reviewed-by: default avatarTvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: default avatarAshutosh Dixit <ashutosh.dixit@intel.com>
Signed-off-by: default avatarJohn Harrison <John.C.Harrison@Intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20221110171913.670286-2-umesh.nerlige.ramappa@intel.com
(cherry picked from commit e746f84b)
Signed-off-by: default avatarRodrigo Vivi <rodrigo.vivi@intel.com>
parent dfa5e6ef
......@@ -382,20 +382,6 @@ __uncore_write(write_notrace, 32, l, false)
*/
__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__))
......@@ -455,6 +441,36 @@ static inline void intel_uncore_rmw_fw(struct intel_uncore *uncore,
intel_uncore_write_fw(uncore, reg, val);
}
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;
enum forcewake_domains fw_domains;
unsigned long flags;
fw_domains = intel_uncore_forcewake_for_reg(uncore, lower_reg,
FW_REG_READ);
fw_domains |= intel_uncore_forcewake_for_reg(uncore, upper_reg,
FW_REG_READ);
spin_lock_irqsave(&uncore->lock, flags);
intel_uncore_forcewake_get__locked(uncore, fw_domains);
upper = intel_uncore_read_fw(uncore, upper_reg);
do {
old_upper = upper;
lower = intel_uncore_read_fw(uncore, lower_reg);
upper = intel_uncore_read_fw(uncore, upper_reg);
} while (upper != old_upper && loop++ < 2);
intel_uncore_forcewake_put__locked(uncore, fw_domains);
spin_unlock_irqrestore(&uncore->lock, flags);
return (u64)upper << 32 | lower;
}
static inline int intel_uncore_write_and_verify(struct intel_uncore *uncore,
i915_reg_t reg, u32 val,
u32 mask, u32 expected_val)
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment