| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Message-ID: <20241219170521.64879-2-karunika.choo@arm.com>
Date: Thu, 19 Dec 2024 17:05:18 +0000
From: Karunika Choo <karunika.choo@....com>
To: dri-devel@...ts.freedesktop.org
Cc: nd@....com,
Boris Brezillon <boris.brezillon@...labora.com>,
Steven Price <steven.price@....com>,
Liviu Dudau <liviu.dudau@....com>,
Maarten Lankhorst <maarten.lankhorst@...ux.intel.com>,
Maxime Ripard <mripard@...nel.org>,
Thomas Zimmermann <tzimmermann@...e.de>,
David Airlie <airlied@...il.com>,
Simona Vetter <simona@...ll.ch>,
linux-kernel@...r.kernel.org
Subject: [RFC PATCH 1/4] drm/panthor: Add 64-bit register accessors
This patch adds 64-bit register accessors to simplify register access in
Panthor. It also adds 64-bit variants for read_poll_timeout and replaces
all 64-bit and poll register accesses with these new functions.
Signed-off-by: Karunika Choo <karunika.choo@....com>
---
drivers/gpu/drm/panthor/panthor_fw.c | 11 +-
drivers/gpu/drm/panthor/panthor_gpu.c | 143 +++++++------------------
drivers/gpu/drm/panthor/panthor_mmu.c | 34 ++----
drivers/gpu/drm/panthor/panthor_regs.h | 49 +++++++++
4 files changed, 104 insertions(+), 133 deletions(-)
diff --git a/drivers/gpu/drm/panthor/panthor_fw.c b/drivers/gpu/drm/panthor/panthor_fw.c
index 68eb4fb4d3a8..8f1b9eff66ef 100644
--- a/drivers/gpu/drm/panthor/panthor_fw.c
+++ b/drivers/gpu/drm/panthor/panthor_fw.c
@@ -1061,8 +1061,8 @@ static void panthor_fw_stop(struct panthor_device *ptdev)
u32 status;
gpu_write(ptdev, MCU_CONTROL, MCU_CONTROL_DISABLE);
- if (readl_poll_timeout(ptdev->iomem + MCU_STATUS, status,
- status == MCU_STATUS_DISABLED, 10, 100000))
+ if (gpu_read_poll_timeout(ptdev, MCU_STATUS, status,
+ status == MCU_STATUS_DISABLED, 10, 100000))
drm_err(&ptdev->base, "Failed to stop MCU");
}
@@ -1087,9 +1087,10 @@ void panthor_fw_pre_reset(struct panthor_device *ptdev, bool on_hang)
panthor_fw_update_reqs(glb_iface, req, GLB_HALT, GLB_HALT);
gpu_write(ptdev, CSF_DOORBELL(CSF_GLB_DOORBELL_ID), 1);
- if (!readl_poll_timeout(ptdev->iomem + MCU_STATUS, status,
- status == MCU_STATUS_HALT, 10, 100000)) {
- ptdev->reset.fast = true;
+ if (!gpu_read_poll_timeout(ptdev, MCU_STATUS, status,
+ status == MCU_STATUS_HALT, 10,
+ 100000)) {
+ ptdev->fw->fast_reset = true;
} else {
drm_warn(&ptdev->base, "Failed to cleanly suspend MCU");
}
diff --git a/drivers/gpu/drm/panthor/panthor_gpu.c b/drivers/gpu/drm/panthor/panthor_gpu.c
index 671049020afa..a7d5022d34be 100644
--- a/drivers/gpu/drm/panthor/panthor_gpu.c
+++ b/drivers/gpu/drm/panthor/panthor_gpu.c
@@ -108,14 +108,9 @@ static void panthor_gpu_init_info(struct panthor_device *ptdev)
ptdev->gpu_info.as_present = gpu_read(ptdev, GPU_AS_PRESENT);
- ptdev->gpu_info.shader_present = gpu_read(ptdev, GPU_SHADER_PRESENT_LO);
- ptdev->gpu_info.shader_present |= (u64)gpu_read(ptdev, GPU_SHADER_PRESENT_HI) << 32;
-
- ptdev->gpu_info.tiler_present = gpu_read(ptdev, GPU_TILER_PRESENT_LO);
- ptdev->gpu_info.tiler_present |= (u64)gpu_read(ptdev, GPU_TILER_PRESENT_HI) << 32;
-
- ptdev->gpu_info.l2_present = gpu_read(ptdev, GPU_L2_PRESENT_LO);
- ptdev->gpu_info.l2_present |= (u64)gpu_read(ptdev, GPU_L2_PRESENT_HI) << 32;
+ ptdev->gpu_info.shader_present = gpu_read64(ptdev, GPU_SHADER_PRESENT_LO);
+ ptdev->gpu_info.tiler_present = gpu_read64(ptdev, GPU_TILER_PRESENT_LO);
+ ptdev->gpu_info.l2_present = gpu_read64(ptdev, GPU_L2_PRESENT_LO);
arch_major = GPU_ARCH_MAJOR(ptdev->gpu_info.gpu_id);
product_major = GPU_PROD_MAJOR(ptdev->gpu_info.gpu_id);
@@ -152,8 +147,7 @@ static void panthor_gpu_irq_handler(struct panthor_device *ptdev, u32 status)
{
if (status & GPU_IRQ_FAULT) {
u32 fault_status = gpu_read(ptdev, GPU_FAULT_STATUS);
- u64 address = ((u64)gpu_read(ptdev, GPU_FAULT_ADDR_HI) << 32) |
- gpu_read(ptdev, GPU_FAULT_ADDR_LO);
+ u64 address = gpu_read64(ptdev, GPU_FAULT_ADDR_LO);
drm_warn(&ptdev->base, "GPU Fault 0x%08x (%s) at 0x%016llx\n",
fault_status, panthor_exception_name(ptdev, fault_status & 0xFF),
@@ -244,45 +238,28 @@ int panthor_gpu_block_power_off(struct panthor_device *ptdev,
u32 pwroff_reg, u32 pwrtrans_reg,
u64 mask, u32 timeout_us)
{
- u32 val, i;
+ u64 val;
int ret;
- for (i = 0; i < 2; i++) {
- u32 mask32 = mask >> (i * 32);
-
- if (!mask32)
- continue;
-
- ret = readl_relaxed_poll_timeout(ptdev->iomem + pwrtrans_reg + (i * 4),
- val, !(mask32 & val),
- 100, timeout_us);
- if (ret) {
- drm_err(&ptdev->base, "timeout waiting on %s:%llx power transition",
- blk_name, mask);
- return ret;
- }
+ ret = gpu_read64_relaxed_poll_timeout(ptdev, pwrtrans_reg, val,
+ !(mask & val), 100, timeout_us);
+ if (ret) {
+ drm_err(&ptdev->base,
+ "timeout waiting on %s:%llx power transition", blk_name,
+ mask);
+ return ret;
}
- if (mask & GENMASK(31, 0))
- gpu_write(ptdev, pwroff_reg, mask);
-
- if (mask >> 32)
- gpu_write(ptdev, pwroff_reg + 4, mask >> 32);
-
- for (i = 0; i < 2; i++) {
- u32 mask32 = mask >> (i * 32);
+ if (mask)
+ gpu_write64(ptdev, pwroff_reg, mask);
- if (!mask32)
- continue;
-
- ret = readl_relaxed_poll_timeout(ptdev->iomem + pwrtrans_reg + (i * 4),
- val, !(mask32 & val),
- 100, timeout_us);
- if (ret) {
- drm_err(&ptdev->base, "timeout waiting on %s:%llx power transition",
- blk_name, mask);
- return ret;
- }
+ ret = gpu_read64_relaxed_poll_timeout(ptdev, pwrtrans_reg, val,
+ !(mask & val), 100, timeout_us);
+ if (ret) {
+ drm_err(&ptdev->base,
+ "timeout waiting on %s:%llx power transition", blk_name,
+ mask);
+ return ret;
}
return 0;
@@ -305,45 +282,26 @@ int panthor_gpu_block_power_on(struct panthor_device *ptdev,
u32 pwron_reg, u32 pwrtrans_reg,
u32 rdy_reg, u64 mask, u32 timeout_us)
{
- u32 val, i;
+ u64 val;
int ret;
- for (i = 0; i < 2; i++) {
- u32 mask32 = mask >> (i * 32);
-
- if (!mask32)
- continue;
-
- ret = readl_relaxed_poll_timeout(ptdev->iomem + pwrtrans_reg + (i * 4),
- val, !(mask32 & val),
- 100, timeout_us);
- if (ret) {
- drm_err(&ptdev->base, "timeout waiting on %s:%llx power transition",
- blk_name, mask);
- return ret;
- }
+ ret = gpu_read64_relaxed_poll_timeout(ptdev, pwrtrans_reg, val,
+ !(mask & val), 100, timeout_us);
+ if (ret) {
+ drm_err(&ptdev->base, "timeout waiting on %s:%llx power transition",
+ blk_name, mask);
+ return ret;
}
- if (mask & GENMASK(31, 0))
- gpu_write(ptdev, pwron_reg, mask);
-
- if (mask >> 32)
- gpu_write(ptdev, pwron_reg + 4, mask >> 32);
-
- for (i = 0; i < 2; i++) {
- u32 mask32 = mask >> (i * 32);
+ if (mask)
+ gpu_write64(ptdev, pwron_reg, mask);
- if (!mask32)
- continue;
-
- ret = readl_relaxed_poll_timeout(ptdev->iomem + rdy_reg + (i * 4),
- val, (mask32 & val) == mask32,
- 100, timeout_us);
- if (ret) {
- drm_err(&ptdev->base, "timeout waiting on %s:%llx readiness",
- blk_name, mask);
- return ret;
- }
+ ret = gpu_read64_relaxed_poll_timeout(
+ ptdev, rdy_reg, val, (mask & val) == mask, 100, timeout_us);
+ if (ret) {
+ drm_err(&ptdev->base, "timeout waiting on %s:%llx readiness",
+ blk_name, mask);
+ return ret;
}
return 0;
@@ -492,26 +450,6 @@ void panthor_gpu_resume(struct panthor_device *ptdev)
panthor_gpu_l2_power_on(ptdev);
}
-/**
- * panthor_gpu_read_64bit_counter() - Read a 64-bit counter at a given offset.
- * @ptdev: Device.
- * @reg: The offset of the register to read.
- *
- * Return: The counter value.
- */
-static u64
-panthor_gpu_read_64bit_counter(struct panthor_device *ptdev, u32 reg)
-{
- u32 hi, lo;
-
- do {
- hi = gpu_read(ptdev, reg + 0x4);
- lo = gpu_read(ptdev, reg);
- } while (hi != gpu_read(ptdev, reg + 0x4));
-
- return ((u64)hi << 32) | lo;
-}
-
/**
* panthor_gpu_read_timestamp() - Read the timestamp register.
* @ptdev: Device.
@@ -520,7 +458,7 @@ panthor_gpu_read_64bit_counter(struct panthor_device *ptdev, u32 reg)
*/
u64 panthor_gpu_read_timestamp(struct panthor_device *ptdev)
{
- return panthor_gpu_read_64bit_counter(ptdev, GPU_TIMESTAMP_LO);
+ return gpu_read64_sync(ptdev, GPU_TIMESTAMP_LO);
}
/**
@@ -531,10 +469,5 @@ u64 panthor_gpu_read_timestamp(struct panthor_device *ptdev)
*/
u64 panthor_gpu_read_timestamp_offset(struct panthor_device *ptdev)
{
- u32 hi, lo;
-
- hi = gpu_read(ptdev, GPU_TIMESTAMP_OFFSET_HI);
- lo = gpu_read(ptdev, GPU_TIMESTAMP_OFFSET_LO);
-
- return ((u64)hi << 32) | lo;
+ return gpu_read64(ptdev, GPU_TIMESTAMP_OFFSET_LO);
}
diff --git a/drivers/gpu/drm/panthor/panthor_mmu.c b/drivers/gpu/drm/panthor/panthor_mmu.c
index c39e3eb1c15d..bed13089bbd4 100644
--- a/drivers/gpu/drm/panthor/panthor_mmu.c
+++ b/drivers/gpu/drm/panthor/panthor_mmu.c
@@ -509,9 +509,9 @@ static int wait_ready(struct panthor_device *ptdev, u32 as_nr)
/* Wait for the MMU status to indicate there is no active command, in
* case one is pending.
*/
- ret = readl_relaxed_poll_timeout_atomic(ptdev->iomem + AS_STATUS(as_nr),
- val, !(val & AS_STATUS_AS_ACTIVE),
- 10, 100000);
+ ret = gpu_read_relaxed_poll_timeout_atomic(ptdev, AS_STATUS(as_nr), val,
+ !(val & AS_STATUS_AS_ACTIVE),
+ 10, 100000);
if (ret) {
panthor_device_schedule_reset(ptdev);
@@ -563,8 +563,7 @@ static void lock_region(struct panthor_device *ptdev, u32 as_nr,
region = region_width | region_start;
/* Lock the region that needs to be updated */
- gpu_write(ptdev, AS_LOCKADDR_LO(as_nr), lower_32_bits(region));
- gpu_write(ptdev, AS_LOCKADDR_HI(as_nr), upper_32_bits(region));
+ gpu_write64(ptdev, AS_LOCKADDR_LO(as_nr), region);
write_cmd(ptdev, as_nr, AS_COMMAND_LOCK);
}
@@ -614,14 +613,9 @@ static int panthor_mmu_as_enable(struct panthor_device *ptdev, u32 as_nr,
if (ret)
return ret;
- gpu_write(ptdev, AS_TRANSTAB_LO(as_nr), lower_32_bits(transtab));
- gpu_write(ptdev, AS_TRANSTAB_HI(as_nr), upper_32_bits(transtab));
-
- gpu_write(ptdev, AS_MEMATTR_LO(as_nr), lower_32_bits(memattr));
- gpu_write(ptdev, AS_MEMATTR_HI(as_nr), upper_32_bits(memattr));
-
- gpu_write(ptdev, AS_TRANSCFG_LO(as_nr), lower_32_bits(transcfg));
- gpu_write(ptdev, AS_TRANSCFG_HI(as_nr), upper_32_bits(transcfg));
+ gpu_write64(ptdev, AS_TRANSTAB_LO(as_nr), transtab);
+ gpu_write64(ptdev, AS_MEMATTR_LO(as_nr), memattr);
+ gpu_write64(ptdev, AS_TRANSCFG_LO(as_nr), transcfg);
return write_cmd(ptdev, as_nr, AS_COMMAND_UPDATE);
}
@@ -634,14 +628,9 @@ static int panthor_mmu_as_disable(struct panthor_device *ptdev, u32 as_nr)
if (ret)
return ret;
- gpu_write(ptdev, AS_TRANSTAB_LO(as_nr), 0);
- gpu_write(ptdev, AS_TRANSTAB_HI(as_nr), 0);
-
- gpu_write(ptdev, AS_MEMATTR_LO(as_nr), 0);
- gpu_write(ptdev, AS_MEMATTR_HI(as_nr), 0);
-
- gpu_write(ptdev, AS_TRANSCFG_LO(as_nr), AS_TRANSCFG_ADRMODE_UNMAPPED);
- gpu_write(ptdev, AS_TRANSCFG_HI(as_nr), 0);
+ gpu_write64(ptdev, AS_TRANSTAB_LO(as_nr), 0);
+ gpu_write64(ptdev, AS_MEMATTR_LO(as_nr), 0);
+ gpu_write64(ptdev, AS_TRANSCFG_LO(as_nr), AS_TRANSCFG_ADRMODE_UNMAPPED);
return write_cmd(ptdev, as_nr, AS_COMMAND_UPDATE);
}
@@ -1677,8 +1666,7 @@ static void panthor_mmu_irq_handler(struct panthor_device *ptdev, u32 status)
u32 source_id;
fault_status = gpu_read(ptdev, AS_FAULTSTATUS(as));
- addr = gpu_read(ptdev, AS_FAULTADDRESS_LO(as));
- addr |= (u64)gpu_read(ptdev, AS_FAULTADDRESS_HI(as)) << 32;
+ addr = gpu_read64(ptdev, AS_FAULTADDRESS_LO(as));
/* decode the fault status */
exception_type = fault_status & 0xFF;
diff --git a/drivers/gpu/drm/panthor/panthor_regs.h b/drivers/gpu/drm/panthor/panthor_regs.h
index b7b3b3add166..269c2c68dde2 100644
--- a/drivers/gpu/drm/panthor/panthor_regs.h
+++ b/drivers/gpu/drm/panthor/panthor_regs.h
@@ -10,6 +10,9 @@
#ifndef __PANTHOR_REGS_H__
#define __PANTHOR_REGS_H__
+#include <linux/iopoll.h>
+
+/* GX10 registers */
#define GPU_ID 0x0
#define GPU_ARCH_MAJOR(x) ((x) >> 28)
#define GPU_ARCH_MINOR(x) (((x) & GENMASK(27, 24)) >> 24)
@@ -236,4 +239,50 @@
#define gpu_read(dev, reg) \
readl((dev)->iomem + (reg))
+#define gpu_read_relaxed(dev, reg) \
+ readl_relaxed((dev)->iomem + (reg))
+
+#define gpu_write64(dev, reg, data) \
+ do { \
+ u64 __val = (u64)(data); \
+ gpu_write(dev, reg, lower_32_bits(__val)); \
+ gpu_write(dev, reg + 4, upper_32_bits(__val)); \
+ } while (0)
+
+#define gpu_read64(dev, reg) \
+ (gpu_read(dev, reg) | ((u64)gpu_read(dev, reg + 4) << 32))
+
+#define gpu_read64_relaxed(dev, reg) \
+ (gpu_read_relaxed(dev, reg) | ((u64)gpu_read_relaxed(dev, reg + 4) << 32))
+
+#define gpu_read64_sync(dev, reg_lo) \
+ ({ \
+ u32 lo, hi1, hi2; \
+ const u64 reg_hi = reg_lo + 4; \
+ do { \
+ hi1 = readl((dev)->iomem + (reg_hi)); \
+ lo = readl((dev)->iomem + (reg_lo)); \
+ hi2 = readl((dev)->iomem + (reg_hi)); \
+ } while (hi1 != hi2); \
+ lo | ((u64)hi2 << 32u); \
+ })
+
+#define gpu_read_poll_timeout(dev, reg, val, cond, delay_us, timeout_us) \
+ read_poll_timeout(gpu_read, val, cond, delay_us, timeout_us, false, dev, reg)
+
+#define gpu_read_poll_timeout_atomic(dev, reg, val, cond, delay_us, timeout_us) \
+ read_poll_timeout_atomic(gpu_read, val, cond, delay_us, timeout_us, false, dev, reg)
+
+#define gpu_read64_poll_timeout(dev, reg, val, cond, delay_us, timeout_us) \
+ read_poll_timeout(gpu_read64, val, cond, delay_us, timeout_us, false, dev, reg)
+
+#define gpu_read64_poll_timeout_atomic(dev, reg, val, cond, delay_us, timeout_us) \
+ read_poll_timeout_atomic(gpu_read64, val, cond, delay_us, timeout_us, false, dev, reg)
+
+#define gpu_read_relaxed_poll_timeout_atomic(dev, reg, val, cond, delay_us, timeout_us) \
+ read_poll_timeout_atomic(gpu_read_relaxed, val, cond, delay_us, timeout_us, false, dev, reg)
+
+#define gpu_read64_relaxed_poll_timeout(dev, reg, val, cond, delay_us, timeout_us) \
+ read_poll_timeout(gpu_read64_relaxed, val, cond, delay_us, timeout_us, false, dev, reg)
+
#endif
--
2.47.1
Powered by blists - more mailing lists