diff options
Diffstat (limited to 'drivers')
88 files changed, 1468 insertions, 613 deletions
diff --git a/drivers/acpi/ec.c b/drivers/acpi/ec.c index d4e5610e09c5..9d66a47d32fb 100644 --- a/drivers/acpi/ec.c +++ b/drivers/acpi/ec.c @@ -1034,6 +1034,18 @@ void acpi_ec_unblock_transactions(void) acpi_ec_start(first_ec, true); } +void acpi_ec_mark_gpe_for_wake(void) +{ + if (first_ec && !ec_no_wakeup) + acpi_mark_gpe_for_wake(NULL, first_ec->gpe); +} + +void acpi_ec_set_gpe_wake_mask(u8 action) +{ + if (first_ec && !ec_no_wakeup) + acpi_set_gpe_wake_mask(NULL, first_ec->gpe, action); +} + void acpi_ec_dispatch_gpe(void) { if (first_ec) diff --git a/drivers/acpi/internal.h b/drivers/acpi/internal.h index 530a3f675490..f59d0b9e2683 100644 --- a/drivers/acpi/internal.h +++ b/drivers/acpi/internal.h @@ -188,6 +188,8 @@ int acpi_ec_ecdt_probe(void); int acpi_ec_dsdt_probe(void); void acpi_ec_block_transactions(void); void acpi_ec_unblock_transactions(void); +void acpi_ec_mark_gpe_for_wake(void); +void acpi_ec_set_gpe_wake_mask(u8 action); void acpi_ec_dispatch_gpe(void); int acpi_ec_add_query_handler(struct acpi_ec *ec, u8 query_bit, acpi_handle handle, acpi_ec_query_func func, diff --git a/drivers/acpi/sleep.c b/drivers/acpi/sleep.c index 754d59f95500..403c4ff15349 100644 --- a/drivers/acpi/sleep.c +++ b/drivers/acpi/sleep.c @@ -940,6 +940,8 @@ static int lps0_device_attach(struct acpi_device *adev, acpi_handle_debug(adev->handle, "_DSM function mask: 0x%x\n", bitmask); + + acpi_ec_mark_gpe_for_wake(); } else { acpi_handle_debug(adev->handle, "_DSM function 0 evaluation failed\n"); @@ -968,16 +970,23 @@ static int acpi_s2idle_prepare(void) if (lps0_device_handle) { acpi_sleep_run_lps0_dsm(ACPI_LPS0_SCREEN_OFF); acpi_sleep_run_lps0_dsm(ACPI_LPS0_ENTRY); + + acpi_ec_set_gpe_wake_mask(ACPI_GPE_ENABLE); } if (acpi_sci_irq_valid()) enable_irq_wake(acpi_sci_irq); + /* Change the configuration of GPEs to avoid spurious wakeup. */ + acpi_enable_all_wakeup_gpes(); + acpi_os_wait_events_complete(); return 0; } static void acpi_s2idle_wake(void) { + if (!lps0_device_handle) + return; if (pm_debug_messages_on) lpi_check_constraints(); @@ -996,8 +1005,7 @@ static void acpi_s2idle_wake(void) * takes too much time for EC wakeup events to survive, so look * for them now. */ - if (lps0_device_handle) - acpi_ec_dispatch_gpe(); + acpi_ec_dispatch_gpe(); } } @@ -1017,10 +1025,14 @@ static void acpi_s2idle_sync(void) static void acpi_s2idle_restore(void) { + acpi_enable_all_runtime_gpes(); + if (acpi_sci_irq_valid()) disable_irq_wake(acpi_sci_irq); if (lps0_device_handle) { + acpi_ec_set_gpe_wake_mask(ACPI_GPE_DISABLE); + acpi_sleep_run_lps0_dsm(ACPI_LPS0_EXIT); acpi_sleep_run_lps0_dsm(ACPI_LPS0_SCREEN_ON); } diff --git a/drivers/clk/qcom/gcc-qcs404.c b/drivers/clk/qcom/gcc-qcs404.c index ef1b267cb058..64da032bb9ed 100644 --- a/drivers/clk/qcom/gcc-qcs404.c +++ b/drivers/clk/qcom/gcc-qcs404.c @@ -297,7 +297,7 @@ static struct clk_alpha_pll gpll0_out_main = { .hw.init = &(struct clk_init_data){ .name = "gpll0_out_main", .parent_names = (const char *[]) - { "gpll0_sleep_clk_src" }, + { "cxo" }, .num_parents = 1, .ops = &clk_alpha_pll_ops, }, diff --git a/drivers/cpufreq/Kconfig.arm b/drivers/cpufreq/Kconfig.arm index 4e1131ef85ae..688f10227793 100644 --- a/drivers/cpufreq/Kconfig.arm +++ b/drivers/cpufreq/Kconfig.arm @@ -114,6 +114,17 @@ config ARM_QCOM_CPUFREQ_KRYO If in doubt, say N. +config ARM_QCOM_CPUFREQ_HW + tristate "QCOM CPUFreq HW driver" + depends on ARCH_QCOM || COMPILE_TEST + help + Support for the CPUFreq HW driver. + Some QCOM chipsets have a HW engine to offload the steps + necessary for changing the frequency of the CPUs. Firmware loaded + in this engine exposes a programming interface to the OS. + The driver implements the cpufreq interface for this HW engine. + Say Y if you want to support CPUFreq HW. + config ARM_S3C_CPUFREQ bool help diff --git a/drivers/cpufreq/Makefile b/drivers/cpufreq/Makefile index d5ee4562ed06..08c071be2491 100644 --- a/drivers/cpufreq/Makefile +++ b/drivers/cpufreq/Makefile @@ -61,6 +61,7 @@ obj-$(CONFIG_MACH_MVEBU_V7) += mvebu-cpufreq.o obj-$(CONFIG_ARM_OMAP2PLUS_CPUFREQ) += omap-cpufreq.o obj-$(CONFIG_ARM_PXA2xx_CPUFREQ) += pxa2xx-cpufreq.o obj-$(CONFIG_PXA3xx) += pxa3xx-cpufreq.o +obj-$(CONFIG_ARM_QCOM_CPUFREQ_HW) += qcom-cpufreq-hw.o obj-$(CONFIG_ARM_QCOM_CPUFREQ_KRYO) += qcom-cpufreq-kryo.o obj-$(CONFIG_ARM_S3C2410_CPUFREQ) += s3c2410-cpufreq.o obj-$(CONFIG_ARM_S3C2412_CPUFREQ) += s3c2412-cpufreq.o diff --git a/drivers/cpufreq/cpufreq-nforce2.c b/drivers/cpufreq/cpufreq-nforce2.c index dbf82f36d270..33c309a08c64 100644 --- a/drivers/cpufreq/cpufreq-nforce2.c +++ b/drivers/cpufreq/cpufreq-nforce2.c @@ -123,8 +123,6 @@ static void nforce2_write_pll(int pll) /* Now write the value in all 64 registers */ for (temp = 0; temp <= 0x3f; temp++) pci_write_config_dword(nforce2_dev, NFORCE2_PLLREG, pll); - - return; } /** @@ -438,4 +436,3 @@ static void __exit nforce2_exit(void) module_init(nforce2_init); module_exit(nforce2_exit); - diff --git a/drivers/cpufreq/ia64-acpi-cpufreq.c b/drivers/cpufreq/ia64-acpi-cpufreq.c index dd5440d3372d..80c5bf590acb 100644 --- a/drivers/cpufreq/ia64-acpi-cpufreq.c +++ b/drivers/cpufreq/ia64-acpi-cpufreq.c @@ -16,7 +16,6 @@ #include <linux/init.h> #include <linux/cpufreq.h> #include <linux/proc_fs.h> -#include <linux/seq_file.h> #include <asm/io.h> #include <linux/uaccess.h> #include <asm/pal.h> @@ -28,7 +27,6 @@ MODULE_AUTHOR("Venkatesh Pallipadi"); MODULE_DESCRIPTION("ACPI Processor P-States Driver"); MODULE_LICENSE("GPL"); - struct cpufreq_acpi_io { struct acpi_processor_performance acpi_data; unsigned int resume; @@ -348,10 +346,7 @@ acpi_cpufreq_exit (void) pr_debug("acpi_cpufreq_exit\n"); cpufreq_unregister_driver(&acpi_cpufreq_driver); - return; } - late_initcall(acpi_cpufreq_init); module_exit(acpi_cpufreq_exit); - diff --git a/drivers/cpufreq/imx6q-cpufreq.c b/drivers/cpufreq/imx6q-cpufreq.c index d8c3595e9023..9fedf627e000 100644 --- a/drivers/cpufreq/imx6q-cpufreq.c +++ b/drivers/cpufreq/imx6q-cpufreq.c @@ -177,22 +177,16 @@ static int imx6q_set_target(struct cpufreq_policy *policy, unsigned int index) /* scaling down? scale voltage after frequency */ if (new_freq < old_freq) { ret = regulator_set_voltage_tol(arm_reg, volt, 0); - if (ret) { + if (ret) dev_warn(cpu_dev, "failed to scale vddarm down: %d\n", ret); - ret = 0; - } ret = regulator_set_voltage_tol(soc_reg, imx6_soc_volt[index], 0); - if (ret) { + if (ret) dev_warn(cpu_dev, "failed to scale vddsoc down: %d\n", ret); - ret = 0; - } if (!IS_ERR(pu_reg)) { ret = regulator_set_voltage_tol(pu_reg, imx6_soc_volt[index], 0); - if (ret) { + if (ret) dev_warn(cpu_dev, "failed to scale vddpu down: %d\n", ret); - ret = 0; - } } } @@ -411,9 +405,10 @@ static int imx6q_cpufreq_probe(struct platform_device *pdev) if (of_machine_is_compatible("fsl,imx6ul") || of_machine_is_compatible("fsl,imx6ull")) { ret = imx6ul_opp_check_speed_grading(cpu_dev); - if (ret == -EPROBE_DEFER) - return ret; if (ret) { + if (ret == -EPROBE_DEFER) + return ret; + dev_err(cpu_dev, "failed to read ocotp: %d\n", ret); return ret; diff --git a/drivers/cpufreq/intel_pstate.c b/drivers/cpufreq/intel_pstate.c index 9578312e43f2..106402b89961 100644 --- a/drivers/cpufreq/intel_pstate.c +++ b/drivers/cpufreq/intel_pstate.c @@ -830,6 +830,28 @@ skip_epp: wrmsrl_on_cpu(cpu, MSR_HWP_REQUEST, value); } +static void intel_pstate_hwp_force_min_perf(int cpu) +{ + u64 value; + int min_perf; + + value = all_cpu_data[cpu]->hwp_req_cached; + value &= ~GENMASK_ULL(31, 0); + min_perf = HWP_LOWEST_PERF(all_cpu_data[cpu]->hwp_cap_cached); + + /* Set hwp_max = hwp_min */ + value |= HWP_MAX_PERF(min_perf); + value |= HWP_MIN_PERF(min_perf); + + /* Set EPP/EPB to min */ + if (static_cpu_has(X86_FEATURE_HWP_EPP)) + value |= HWP_ENERGY_PERF_PREFERENCE(HWP_EPP_POWERSAVE); + else + intel_pstate_set_epb(cpu, HWP_EPP_BALANCE_POWERSAVE); + + wrmsrl_on_cpu(cpu, MSR_HWP_REQUEST, value); +} + static int intel_pstate_hwp_save_state(struct cpufreq_policy *policy) { struct cpudata *cpu_data = all_cpu_data[policy->cpu]; @@ -2084,10 +2106,12 @@ static void intel_pstate_stop_cpu(struct cpufreq_policy *policy) pr_debug("CPU %d exiting\n", policy->cpu); intel_pstate_clear_update_util_hook(policy->cpu); - if (hwp_active) + if (hwp_active) { intel_pstate_hwp_save_state(policy); - else + intel_pstate_hwp_force_min_perf(policy->cpu); + } else { intel_cpufreq_stop_cpu(policy); + } } static int intel_pstate_cpu_exit(struct cpufreq_policy *policy) diff --git a/drivers/cpufreq/pmac64-cpufreq.c b/drivers/cpufreq/pmac64-cpufreq.c index be623dd7b9f2..1d32a863332d 100644 --- a/drivers/cpufreq/pmac64-cpufreq.c +++ b/drivers/cpufreq/pmac64-cpufreq.c @@ -411,6 +411,7 @@ static int __init g5_neo2_cpufreq_init(struct device_node *cpunode) pfunc_set_vdnap0 = pmf_find_function(root, "set-vdnap0"); pfunc_vdnap0_complete = pmf_find_function(root, "slewing-done"); + of_node_put(root); if (pfunc_set_vdnap0 == NULL || pfunc_vdnap0_complete == NULL) { pr_err("Can't find required platform function\n"); diff --git a/drivers/cpufreq/powernv-cpufreq.c b/drivers/cpufreq/powernv-cpufreq.c index bf6519cf64bc..7e7ad3879c4e 100644 --- a/drivers/cpufreq/powernv-cpufreq.c +++ b/drivers/cpufreq/powernv-cpufreq.c @@ -253,18 +253,18 @@ static int init_powernv_pstates(void) if (of_property_read_u32(power_mgt, "ibm,pstate-min", &pstate_min)) { pr_warn("ibm,pstate-min node not found\n"); - return -ENODEV; + goto out; } if (of_property_read_u32(power_mgt, "ibm,pstate-max", &pstate_max)) { pr_warn("ibm,pstate-max node not found\n"); - return -ENODEV; + goto out; } if (of_property_read_u32(power_mgt, "ibm,pstate-nominal", &pstate_nominal)) { pr_warn("ibm,pstate-nominal not found\n"); - return -ENODEV; + goto out; } if (of_property_read_u32(power_mgt, "ibm,pstate-ultra-turbo", @@ -293,14 +293,14 @@ next: pstate_ids = of_get_property(power_mgt, "ibm,pstate-ids", &len_ids); if (!pstate_ids) { pr_warn("ibm,pstate-ids not found\n"); - return -ENODEV; + goto out; } pstate_freqs = of_get_property(power_mgt, "ibm,pstate-frequencies-mhz", &len_freqs); if (!pstate_freqs) { pr_warn("ibm,pstate-frequencies-mhz not found\n"); - return -ENODEV; + goto out; } if (len_ids != len_freqs) { @@ -311,7 +311,7 @@ next: nr_pstates = min(len_ids, len_freqs) / sizeof(u32); if (!nr_pstates) { pr_warn("No PStates found\n"); - return -ENODEV; + goto out; } powernv_pstate_info.nr_pstates = nr_pstates; @@ -352,7 +352,12 @@ next: /* End of list marker entry */ powernv_freqs[i].frequency = CPUFREQ_TABLE_END; + + of_node_put(power_mgt); return 0; +out: + of_node_put(power_mgt); + return -ENODEV; } /* Returns the CPU frequency corresponding to the pstate_id. */ diff --git a/drivers/cpufreq/qcom-cpufreq-hw.c b/drivers/cpufreq/qcom-cpufreq-hw.c new file mode 100644 index 000000000000..d83939a1b3d4 --- /dev/null +++ b/drivers/cpufreq/qcom-cpufreq-hw.c @@ -0,0 +1,308 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2018, The Linux Foundation. All rights reserved. + */ + +#include <linux/bitfield.h> +#include <linux/cpufreq.h> +#include <linux/init.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/of_address.h> +#include <linux/of_platform.h> +#include <linux/slab.h> + +#define LUT_MAX_ENTRIES 40U +#define LUT_SRC GENMASK(31, 30) +#define LUT_L_VAL GENMASK(7, 0) +#define LUT_CORE_COUNT GENMASK(18, 16) +#define LUT_ROW_SIZE 32 +#define CLK_HW_DIV 2 + +/* Register offsets */ +#define REG_ENABLE 0x0 +#define REG_LUT_TABLE 0x110 +#define REG_PERF_STATE 0x920 + +static unsigned long cpu_hw_rate, xo_rate; +static struct platform_device *global_pdev; + +static int qcom_cpufreq_hw_target_index(struct cpufreq_policy *policy, + unsigned int index) +{ + void __iomem *perf_state_reg = policy->driver_data; + + writel_relaxed(index, perf_state_reg); + + return 0; +} + +static unsigned int qcom_cpufreq_hw_get(unsigned int cpu) +{ + void __iomem *perf_state_reg; + struct cpufreq_policy *policy; + unsigned int index; + + policy = cpufreq_cpu_get_raw(cpu); + if (!policy) + return 0; + + perf_state_reg = policy->driver_data; + + index = readl_relaxed(perf_state_reg); + index = min(index, LUT_MAX_ENTRIES - 1); + + return policy->freq_table[index].frequency; +} + +static unsigned int qcom_cpufreq_hw_fast_switch(struct cpufreq_policy *policy, + unsigned int target_freq) +{ + void __iomem *perf_state_reg = policy->driver_data; + int index; + + index = policy->cached_resolved_idx; + if (index < 0) + return 0; + + writel_relaxed(index, perf_state_reg); + + return policy->freq_table[index].frequency; +} + +static int qcom_cpufreq_hw_read_lut(struct device *dev, + struct cpufreq_policy *policy, + void __iomem *base) +{ + u32 data, src, lval, i, core_count, prev_cc = 0, prev_freq = 0, freq; + unsigned int max_cores = cpumask_weight(policy->cpus); + struct cpufreq_frequency_table *table; + + table = kcalloc(LUT_MAX_ENTRIES + 1, sizeof(*table), GFP_KERNEL); + if (!table) + return -ENOMEM; + + for (i = 0; i < LUT_MAX_ENTRIES; i++) { + data = readl_relaxed(base + REG_LUT_TABLE + i * LUT_ROW_SIZE); + src = FIELD_GET(LUT_SRC, data); + lval = FIELD_GET(LUT_L_VAL, data); + core_count = FIELD_GET(LUT_CORE_COUNT, data); + + if (src) + freq = xo_rate * lval / 1000; + else + freq = cpu_hw_rate / 1000; + + /* Ignore boosts in the middle of the table */ + if (core_count != max_cores) { + table[i].frequency = CPUFREQ_ENTRY_INVALID; + } else { + table[i].frequency = freq; + dev_dbg(dev, "index=%d freq=%d, core_count %d\n", i, + freq, core_count); + } + + /* + * Two of the same frequencies with the same core counts means + * end of table + */ + if (i > 0 && prev_freq == freq && prev_cc == core_count) { + struct cpufreq_frequency_table *prev = &table[i - 1]; + + /* + * Only treat the last frequency that might be a boost + * as the boost frequency + */ + if (prev_cc != max_cores) { + prev->frequency = prev_freq; + prev->flags = CPUFREQ_BOOST_FREQ; + } + + break; + } + + prev_cc = core_count; + prev_freq = freq; + } + + table[i].frequency = CPUFREQ_TABLE_END; + policy->freq_table = table; + + return 0; +} + +static void qcom_get_related_cpus(int index, struct cpumask *m) +{ + struct device_node *cpu_np; + struct of_phandle_args args; + int cpu, ret; + + for_each_possible_cpu(cpu) { + cpu_np = of_cpu_device_node_get(cpu); + if (!cpu_np) + continue; + + ret = of_parse_phandle_with_args(cpu_np, "qcom,freq-domain", + "#freq-domain-cells", 0, + &args); + of_node_put(cpu_np); + if (ret < 0) + continue; + + if (index == args.args[0]) + cpumask_set_cpu(cpu, m); + } +} + +static int qcom_cpufreq_hw_cpu_init(struct cpufreq_policy *policy) +{ + struct device *dev = &global_pdev->dev; + struct of_phandle_args args; + struct device_node *cpu_np; + struct resource *res; + void __iomem *base; + int ret, index; + + cpu_np = of_cpu_device_node_get(policy->cpu); + if (!cpu_np) + return -EINVAL; + + ret = of_parse_phandle_with_args(cpu_np, "qcom,freq-domain", + "#freq-domain-cells", 0, &args); + of_node_put(cpu_np); + if (ret) + return ret; + + index = args.args[0]; + + res = platform_get_resource(global_pdev, IORESOURCE_MEM, index); + if (!res) + return -ENODEV; + + base = devm_ioremap(dev, res->start, resource_size(res)); + if (!base) + return -ENOMEM; + + /* HW should be in enabled state to proceed */ + if (!(readl_relaxed(base + REG_ENABLE) & 0x1)) { + dev_err(dev, "Domain-%d cpufreq hardware not enabled\n", index); + ret = -ENODEV; + goto error; + } + + qcom_get_related_cpus(index, policy->cpus); + if (!cpumask_weight(policy->cpus)) { + dev_err(dev, "Domain-%d failed to get related CPUs\n", index); + ret = -ENOENT; + goto error; + } + + policy->driver_data = base + REG_PERF_STATE; + + ret = qcom_cpufreq_hw_read_lut(dev, policy, base); + if (ret) { + dev_err(dev, "Domain-%d failed to read LUT\n", index); + goto error; + } + + policy->fast_switch_possible = true; + + return 0; +error: + devm_iounmap(dev, base); + return ret; +} + +static int qcom_cpufreq_hw_cpu_exit(struct cpufreq_policy *policy) +{ + void __iomem *base = policy->driver_data - REG_PERF_STATE; + + kfree(policy->freq_table); + devm_iounmap(&global_pdev->dev, base); + + return 0; +} + +static struct freq_attr *qcom_cpufreq_hw_attr[] = { + &cpufreq_freq_attr_scaling_available_freqs, + &cpufreq_freq_attr_scaling_boost_freqs, + NULL +}; + +static struct cpufreq_driver cpufreq_qcom_hw_driver = { + .flags = CPUFREQ_STICKY | CPUFREQ_NEED_INITIAL_FREQ_CHECK | + CPUFREQ_HAVE_GOVERNOR_PER_POLICY, + .verify = cpufreq_generic_frequency_table_verify, + .target_index = qcom_cpufreq_hw_target_index, + .get = qcom_cpufreq_hw_get, + .init = qcom_cpufreq_hw_cpu_init, + .exit = qcom_cpufreq_hw_cpu_exit, + .fast_switch = qcom_cpufreq_hw_fast_switch, + .name = "qcom-cpufreq-hw", + .attr = qcom_cpufreq_hw_attr, +}; + +static int qcom_cpufreq_hw_driver_probe(struct platform_device *pdev) +{ + struct clk *clk; + int ret; + + clk = clk_get(&pdev->dev, "xo"); + if (IS_ERR(clk)) + return PTR_ERR(clk); + + xo_rate = clk_get_rate(clk); + clk_put(clk); + + clk = clk_get(&pdev->dev, "alternate"); + if (IS_ERR(clk)) + return PTR_ERR(clk); + + cpu_hw_rate = clk_get_rate(clk) / CLK_HW_DIV; + clk_put(clk); + + global_pdev = pdev; + + ret = cpufreq_register_driver(&cpufreq_qcom_hw_driver); + if (ret) + dev_err(&pdev->dev, "CPUFreq HW driver failed to register\n"); + else + dev_dbg(&pdev->dev, "QCOM CPUFreq HW driver initialized\n"); + + return ret; +} + +static int qcom_cpufreq_hw_driver_remove(struct platform_device *pdev) +{ + return cpufreq_unregister_driver(&cpufreq_qcom_hw_driver); +} + +static const struct of_device_id qcom_cpufreq_hw_match[] = { + { .compatible = "qcom,cpufreq-hw" }, + {} +}; +MODULE_DEVICE_TABLE(of, qcom_cpufreq_hw_match); + +static struct platform_driver qcom_cpufreq_hw_driver = { + .probe = qcom_cpufreq_hw_driver_probe, + .remove = qcom_cpufreq_hw_driver_remove, + .driver = { + .name = "qcom-cpufreq-hw", + .of_match_table = qcom_cpufreq_hw_match, + }, +}; + +static int __init qcom_cpufreq_hw_init(void) +{ + return platform_driver_register(&qcom_cpufreq_hw_driver); +} +subsys_initcall(qcom_cpufreq_hw_init); + +static void __exit qcom_cpufreq_hw_exit(void) +{ + platform_driver_unregister(&qcom_cpufreq_hw_driver); +} +module_exit(qcom_cpufreq_hw_exit); + +MODULE_DESCRIPTION("QCOM CPUFREQ HW Driver"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/cpufreq/s3c24xx-cpufreq-debugfs.c b/drivers/cpufreq/s3c24xx-cpufreq-debugfs.c index 4d976e8dbb2f..0df87b6480fe 100644 --- a/drivers/cpufreq/s3c24xx-cpufreq-debugfs.c +++ b/drivers/cpufreq/s3c24xx-cpufreq-debugfs.c @@ -63,18 +63,7 @@ static int board_show(struct seq_file *seq, void *p) return 0; } -static int fops_board_open(struct inode *inode, struct file *file) -{ - return single_open(file, board_show, NULL); -} - -static const struct file_operations fops_board = { - .open = fops_board_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, - .owner = THIS_MODULE, -}; +DEFINE_SHOW_ATTRIBUTE(board); static int info_show(struct seq_file *seq, void *p) { @@ -105,18 +94,7 @@ static int info_show(struct seq_file *seq, void *p) return 0; } -static int fops_info_open(struct inode *inode, struct file *file) -{ - return single_open(file, info_show, NULL); -} - -static const struct file_operations fops_info = { - .open = fops_info_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, - .owner = THIS_MODULE, -}; +DEFINE_SHOW_ATTRIBUTE(info); static int io_show(struct seq_file *seq, void *p) { @@ -162,19 +140,7 @@ static int io_show(struct seq_file *seq, void *p) return 0; } -static int fops_io_open(struct inode *inode, struct file *file) -{ - return single_open(file, io_show, NULL); -} - -static const struct file_operations fops_io = { - .open = fops_io_open, - .read = seq_read, - .llseek = seq_lseek, - .release = single_release, - .owner = THIS_MODULE, -}; - +DEFINE_SHOW_ATTRIBUTE(io); static int __init s3c_freq_debugfs_init(void) { @@ -185,13 +151,13 @@ static int __init s3c_freq_debugfs_init(void) } dbgfs_file_io = debugfs_create_file("io-timing", S_IRUGO, dbgfs_root, - NULL, &fops_io); + NULL, &io_fops); dbgfs_file_info = debugfs_create_file("info", S_IRUGO, dbgfs_root, - NULL, &fops_info); + NULL, &info_fops); dbgfs_file_board = debugfs_create_file("board", S_IRUGO, dbgfs_root, - NULL, &fops_board); + NULL, &board_fops); return 0; } diff --git a/drivers/cpuidle/cpuidle-big_little.c b/drivers/cpuidle/cpuidle-big_little.c index db2ede565f1a..b44476a1b7ad 100644 --- a/drivers/cpuidle/cpuidle-big_little.c +++ b/drivers/cpuidle/cpuidle-big_little.c @@ -167,6 +167,7 @@ static int __init bl_idle_init(void) { int ret; struct device_node *root = of_find_node_by_path("/"); + const struct of_device_id *match_id; if (!root) return -ENODEV; @@ -174,7 +175,11 @@ static int __init bl_idle_init(void) /* * Initialize the driver just for a compliant set of machines */ - if (!of_match_node(compatible_machine_match, root)) + match_id = of_match_node(compatible_machine_match, root); + + of_node_put(root); + + if (!match_id) return -ENODEV; if (!mcpm_is_available()) diff --git a/drivers/cpuidle/cpuidle.c b/drivers/cpuidle/cpuidle.c index 4a97446f66d8..7f108309e871 100644 --- a/drivers/cpuidle/cpuidle.c +++ b/drivers/cpuidle/cpuidle.c @@ -202,7 +202,6 @@ int cpuidle_enter_state(struct cpuidle_device *dev, struct cpuidle_driver *drv, struct cpuidle_state *target_state = &drv->states[index]; bool broadcast = !!(target_state->flags & CPUIDLE_FLAG_TIMER_STOP); ktime_t time_start, time_end; - s64 diff; /* * Tell the time framework to switch to a broadcast timer because our @@ -248,6 +247,9 @@ int cpuidle_enter_state(struct cpuidle_device *dev, struct cpuidle_driver *drv, local_irq_enable(); if (entered_state >= 0) { + s64 diff, delay = drv->states[entered_state].exit_latency; + int i; + /* * Update cpuidle counters * This can be moved to within driver enter routine, @@ -260,6 +262,33 @@ int cpuidle_enter_state(struct cpuidle_device *dev, struct cpuidle_driver *drv, dev->last_residency = (int)diff; dev->states_usage[entered_state].time += dev->last_residency; dev->states_usage[entered_state].usage++; + + if (diff < drv->states[entered_state].target_residency) { + for (i = entered_state - 1; i >= 0; i--) { + if (drv->states[i].disabled || + dev->states_usage[i].disable) + continue; + + /* Shallower states are enabled, so update. */ + dev->states_usage[entered_state].above++; + break; + } + } else if (diff > delay) { + for (i = entered_state + 1; i < drv->state_count; i++) { + if (drv->states[i].disabled || + dev->states_usage[i].disable) + continue; + + /* + * Update if a deeper state would have been a + * better match for the observed idle duration. + */ + if (diff - delay >= drv->states[i].target_residency) + dev->states_usage[entered_state].below++; + + break; + } + } } else { dev->last_residency = 0; } @@ -702,4 +731,5 @@ static int __init cpuidle_init(void) } module_param(off, int, 0444); +module_param_string(governor, param_governor, CPUIDLE_NAME_LEN, 0444); core_initcall(cpuidle_init); diff --git a/drivers/cpuidle/cpuidle.h b/drivers/cpuidle/cpuidle.h index 2965ab32a583..d6613101af92 100644 --- a/drivers/cpuidle/cpuidle.h +++ b/drivers/cpuidle/cpuidle.h @@ -7,6 +7,7 @@ #define __DRIVER_CPUIDLE_H /* For internal use only */ +extern char param_governor[]; extern struct cpuidle_governor *cpuidle_curr_governor; extern struct list_head cpuidle_governors; extern struct list_head cpuidle_detected_devices; diff --git a/drivers/cpuidle/governor.c b/drivers/cpuidle/governor.c index 9fed1b829292..bb93e5cf6a4a 100644 --- a/drivers/cpuidle/governor.c +++ b/drivers/cpuidle/governor.c @@ -11,10 +11,13 @@ #include <linux/cpu.h> #include <linux/cpuidle.h> #include <linux/mutex.h> +#include <linux/module.h> #include <linux/pm_qos.h> #include "cpuidle.h" +char param_governor[CPUIDLE_NAME_LEN]; + LIST_HEAD(cpuidle_governors); struct cpuidle_governor *cpuidle_curr_governor; @@ -86,9 +89,11 @@ int cpuidle_register_governor(struct cpuidle_governor *gov) mutex_lock(&cpuidle_lock); if (__cpuidle_find_governor(gov->name) == NULL) { ret = 0; - list_add_tail(&gov->governor_list, &cpuidle_governors); if (!cpuidle_curr_governor || - cpuidle_curr_governor->rating < gov->rating) + !strncasecmp(param_governor, gov->name, CPUIDLE_NAME_LEN) || + (cpuidle_curr_governor->rating < gov->rating && + strncasecmp(param_governor, cpuidle_curr_governor->name, + CPUIDLE_NAME_LEN))) cpuidle_switch_governor(gov); } mutex_unlock(&cpuidle_lock); diff --git a/drivers/cpuidle/poll_state.c b/drivers/cpuidle/poll_state.c index 85792d371add..b17d153e724f 100644 --- a/drivers/cpuidle/poll_state.c +++ b/drivers/cpuidle/poll_state.c @@ -20,8 +20,17 @@ static int __cpuidle poll_idle(struct cpuidle_device *dev, local_irq_enable(); if (!current_set_polling_and_test()) { - u64 limit = (u64)drv->states[1].target_residency * NSEC_PER_USEC; unsigned int loop_count = 0; + u64 limit = TICK_USEC; + int i; + + for (i = 1; i < drv->state_count; i++) { + if (drv->states[i].disabled || dev->states_usage[i].disable) + continue; + + limit = (u64)drv->states[i].target_residency * NSEC_PER_USEC; + break; + } while (!need_resched()) { cpu_relax(); diff --git a/drivers/cpuidle/sysfs.c b/drivers/cpuidle/sysfs.c index e754c7aae7f7..eb20adb5de23 100644 --- a/drivers/cpuidle/sysfs.c +++ b/drivers/cpuidle/sysfs.c @@ -301,6 +301,8 @@ define_show_state_str_function(name) define_show_state_str_function(desc) define_show_state_ull_function(disable) define_store_state_ull_function(disable) +define_show_state_ull_function(above) +define_show_state_ull_function(below) define_one_state_ro(name, show_state_name); define_one_state_ro(desc, show_state_desc); @@ -310,6 +312,8 @@ define_one_state_ro(power, show_state_power_usage); define_one_state_ro(usage, show_state_usage); define_one_state_ro(time, show_state_time); define_one_state_rw(disable, show_state_disable, store_state_disable); +define_one_state_ro(above, show_state_above); +define_one_state_ro(below, show_state_below); static struct attribute *cpuidle_state_default_attrs[] = { &attr_name.attr, @@ -320,6 +324,8 @@ static struct attribute *cpuidle_state_default_attrs[] = { &attr_usage.attr, &attr_time.attr, &attr_disable.attr, + &attr_above.attr, + &attr_below.attr, NULL }; diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c index 8816c697b205..387f1cf1dc20 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c @@ -330,7 +330,9 @@ static int amdgpu_cgs_get_firmware_info(struct cgs_device *cgs_device, case CHIP_TOPAZ: if (((adev->pdev->device == 0x6900) && (adev->pdev->revision == 0x81)) || ((adev->pdev->device == 0x6900) && (adev->pdev->revision == 0x83)) || - ((adev->pdev->device == 0x6907) && (adev->pdev->revision == 0x87))) { + ((adev->pdev->device == 0x6907) && (adev->pdev->revision == 0x87)) || + ((adev->pdev->device == 0x6900) && (adev->pdev->revision == 0xD1)) || + ((adev->pdev->device == 0x6900) && (adev->pdev->revision == 0xD3))) { info->is_kicker = true; strcpy(fw_name, "amdgpu/topaz_k_smc.bin"); } else @@ -351,7 +353,6 @@ static int amdgpu_cgs_get_firmware_info(struct cgs_device *cgs_device, if (type == CGS_UCODE_ID_SMU) { if (((adev->pdev->device == 0x67ef) && ((adev->pdev->revision == 0xe0) || - (adev->pdev->revision == 0xe2) || (adev->pdev->revision == 0xe5))) || ((adev->pdev->device == 0x67ff) && ((adev->pdev->revision == 0xcf) || @@ -359,8 +360,13 @@ static int amdgpu_cgs_get_firmware_info(struct cgs_device *cgs_device, (adev->pdev->revision == 0xff)))) { info->is_kicker = true; strcpy(fw_name, "amdgpu/polaris11_k_smc.bin"); - } else + } else if ((adev->pdev->device == 0x67ef) && + (adev->pdev->revision == 0xe2)) { + info->is_kicker = true; + strcpy(fw_name, "amdgpu/polaris11_k2_smc.bin"); + } else { strcpy(fw_name, "amdgpu/polaris11_smc.bin"); + } } else if (type == CGS_UCODE_ID_SMU_SK) { strcpy(fw_name, "amdgpu/polaris11_smc_sk.bin"); } @@ -375,17 +381,35 @@ static int amdgpu_cgs_get_firmware_info(struct cgs_device *cgs_device, (adev->pdev->revision == 0xe7) || (adev->pdev->revision == 0xef))) || ((adev->pdev->device == 0x6fdf) && - (adev->pdev->revision == 0xef))) { + ((adev->pdev->revision == 0xef) || + (adev->pdev->revision == 0xff)))) { info->is_kicker = true; strcpy(fw_name, "amdgpu/polaris10_k_smc.bin"); - } else + } else if ((adev->pdev->device == 0x67df) && + ((adev->pdev->revision == 0xe1) || + (adev->pdev->revision == 0xf7))) { + info->is_kicker = true; + strcpy(fw_name, "amdgpu/polaris10_k2_smc.bin"); + } else { strcpy(fw_name, "amdgpu/polaris10_smc.bin"); + } } else if (type == CGS_UCODE_ID_SMU_SK) { strcpy(fw_name, "amdgpu/polaris10_smc_sk.bin"); } break; case CHIP_POLARIS12: - strcpy(fw_name, "amdgpu/polaris12_smc.bin"); + if (((adev->pdev->device == 0x6987) && + ((adev->pdev->revision == 0xc0) || + (adev->pdev->revision == 0xc3))) || + ((adev->pdev->device == 0x6981) && + ((adev->pdev->revision == 0x00) || + (adev->pdev->revision == 0x01) || + (adev->pdev->revision == 0x10)))) { + info->is_kicker = true; + strcpy(fw_name, "amdgpu/polaris12_k_smc.bin"); + } else { + strcpy(fw_name, "amdgpu/polaris12_smc.bin"); + } break; case CHIP_VEGAM: strcpy(fw_name, "amdgpu/vegam_smc.bin"); diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c index 663043c8f0f5..0acc8dee2cb8 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c @@ -124,14 +124,14 @@ static int amdgpu_cs_parser_init(struct amdgpu_cs_parser *p, union drm_amdgpu_cs goto free_chunk; } + mutex_lock(&p->ctx->lock); + /* skip guilty context job */ if (atomic_read(&p->ctx->guilty) == 1) { ret = -ECANCELED; goto free_chunk; } - mutex_lock(&p->ctx->lock); - /* get chunks */ chunk_array_user = u64_to_user_ptr(cs->in.chunks); if (copy_from_user(chunk_array, chunk_array_user, diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c index 8de55f7f1a3a..74b611e8a1b1 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_drv.c @@ -872,7 +872,13 @@ static const struct pci_device_id pciidlist[] = { {0x1002, 0x6864, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VEGA10}, {0x1002, 0x6867, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VEGA10}, {0x1002, 0x6868, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VEGA10}, + {0x1002, 0x6869, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VEGA10}, + {0x1002, 0x686a, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VEGA10}, + {0x1002, 0x686b, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VEGA10}, {0x1002, 0x686c, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VEGA10}, + {0x1002, 0x686d, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VEGA10}, + {0x1002, 0x686e, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VEGA10}, + {0x1002, 0x686f, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VEGA10}, {0x1002, 0x687f, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VEGA10}, /* Vega 12 */ {0x1002, 0x69A0, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VEGA12}, @@ -885,6 +891,7 @@ static const struct pci_device_id pciidlist[] = { {0x1002, 0x66A1, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VEGA20}, {0x1002, 0x66A2, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VEGA20}, {0x1002, 0x66A3, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VEGA20}, + {0x1002, 0x66A4, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VEGA20}, {0x1002, 0x66A7, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VEGA20}, {0x1002, 0x66AF, PCI_ANY_ID, PCI_ANY_ID, 0, 0, CHIP_VEGA20}, /* Raven */ diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_device.c b/drivers/gpu/drm/amd/amdkfd/kfd_device.c index a9f18ea7e354..e4ded890b1cb 100644 --- a/drivers/gpu/drm/amd/amdkfd/kfd_device.c +++ b/drivers/gpu/drm/amd/amdkfd/kfd_device.c @@ -337,12 +337,19 @@ static const struct kfd_deviceid supported_devices[] = { { 0x6864, &vega10_device_info }, /* Vega10 */ { 0x6867, &vega10_device_info }, /* Vega10 */ { 0x6868, &vega10_device_info }, /* Vega10 */ + { 0x6869, &vega10_device_info }, /* Vega10 */ + { 0x686A, &vega10_device_info }, /* Vega10 */ + { 0x686B, &vega10_device_info }, /* Vega10 */ { 0x686C, &vega10_vf_device_info }, /* Vega10 vf*/ + { 0x686D, &vega10_device_info }, /* Vega10 */ + { 0x686E, &vega10_device_info }, /* Vega10 */ + { 0x686F, &vega10_device_info }, /* Vega10 */ { 0x687F, &vega10_device_info }, /* Vega10 */ { 0x66a0, &vega20_device_info }, /* Vega20 */ { 0x66a1, &vega20_device_info }, /* Vega20 */ { 0x66a2, &vega20_device_info }, /* Vega20 */ { 0x66a3, &vega20_device_info }, /* Vega20 */ + { 0x66a4, &vega20_device_info }, /* Vega20 */ { 0x66a7, &vega20_device_info }, /* Vega20 */ { 0x66af, &vega20_device_info } /* Vega20 */ }; diff --git a/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_hwmgr.c b/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_hwmgr.c index 3367dd30cdd0..3b7fce5d7258 100644 --- a/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_hwmgr.c +++ b/drivers/gpu/drm/amd/powerplay/hwmgr/vega20_hwmgr.c @@ -130,7 +130,7 @@ static void vega20_set_default_registry_data(struct pp_hwmgr *hwmgr) data->registry_data.disable_auto_wattman = 1; data->registry_data.auto_wattman_debug = 0; data->registry_data.auto_wattman_sample_period = 100; - data->registry_data.fclk_gfxclk_ratio = 0x3F6CCCCD; + data->registry_data.fclk_gfxclk_ratio = 0; data->registry_data.auto_wattman_threshold = 50; data->registry_data.gfxoff_controlled_by_driver = 1; data->gfxoff_allowed = false; diff --git a/drivers/gpu/drm/amd/powerplay/inc/smu7_ppsmc.h b/drivers/gpu/drm/amd/powerplay/inc/smu7_ppsmc.h index 62f36ba2435b..c1a99dfe4913 100644 --- a/drivers/gpu/drm/amd/powerplay/inc/smu7_ppsmc.h +++ b/drivers/gpu/drm/amd/powerplay/inc/smu7_ppsmc.h @@ -386,6 +386,8 @@ typedef uint16_t PPSMC_Result; #define PPSMC_MSG_AgmResetPsm ((uint16_t) 0x403) #define PPSMC_MSG_ReadVftCell ((uint16_t) 0x404) +#define PPSMC_MSG_ApplyAvfsCksOffVoltage ((uint16_t) 0x415) + #define PPSMC_MSG_GFX_CU_PG_ENABLE ((uint16_t) 0x280) #define PPSMC_MSG_GFX_CU_PG_DISABLE ((uint16_t) 0x281) #define PPSMC_MSG_GetCurrPkgPwr ((uint16_t) 0x282) diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/polaris10_smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/polaris10_smumgr.c index 872d3824337b..a1e0ac9ae248 100644 --- a/drivers/gpu/drm/amd/powerplay/smumgr/polaris10_smumgr.c +++ b/drivers/gpu/drm/amd/powerplay/smumgr/polaris10_smumgr.c @@ -1985,6 +1985,12 @@ int polaris10_thermal_avfs_enable(struct pp_hwmgr *hwmgr) smum_send_msg_to_smc(hwmgr, PPSMC_MSG_EnableAvfs); + /* Apply avfs cks-off voltages to avoid the overshoot + * when switching to the highest sclk frequency + */ + if (data->apply_avfs_cks_off_voltage) + smum_send_msg_to_smc(hwmgr, PPSMC_MSG_ApplyAvfsCksOffVoltage); + return 0; } diff --git a/drivers/gpu/drm/amd/powerplay/smumgr/smumgr.c b/drivers/gpu/drm/amd/powerplay/smumgr/smumgr.c index 99d5e4f98f49..a6edd5df33b0 100644 --- a/drivers/gpu/drm/amd/powerplay/smumgr/smumgr.c +++ b/drivers/gpu/drm/amd/powerplay/smumgr/smumgr.c @@ -37,10 +37,13 @@ MODULE_FIRMWARE("amdgpu/fiji_smc.bin"); MODULE_FIRMWARE("amdgpu/polaris10_smc.bin"); MODULE_FIRMWARE("amdgpu/polaris10_smc_sk.bin"); MODULE_FIRMWARE("amdgpu/polaris10_k_smc.bin"); +MODULE_FIRMWARE("amdgpu/polaris10_k2_smc.bin"); MODULE_FIRMWARE("amdgpu/polaris11_smc.bin"); MODULE_FIRMWARE("amdgpu/polaris11_smc_sk.bin"); MODULE_FIRMWARE("amdgpu/polaris11_k_smc.bin"); +MODULE_FIRMWARE("amdgpu/polaris11_k2_smc.bin"); MODULE_FIRMWARE("amdgpu/polaris12_smc.bin"); +MODULE_FIRMWARE("amdgpu/polaris12_k_smc.bin"); MODULE_FIRMWARE("amdgpu/vegam_smc.bin"); MODULE_FIRMWARE("amdgpu/vega10_smc.bin"); MODULE_FIRMWARE("amdgpu/vega10_acg_smc.bin"); diff --git a/drivers/gpu/drm/i915/gvt/fb_decoder.c b/drivers/gpu/drm/i915/gvt/fb_decoder.c index 481896fb712a..85e6736f0a32 100644 --- a/drivers/gpu/drm/i915/gvt/fb_decoder.c +++ b/drivers/gpu/drm/i915/gvt/fb_decoder.c @@ -235,7 +235,7 @@ int intel_vgpu_decode_primary_plane(struct intel_vgpu *vgpu, plane->bpp = skl_pixel_formats[fmt].bpp; plane->drm_format = skl_pixel_formats[fmt].drm_format; } else { - plane->tiled = !!(val & DISPPLANE_TILED); + plane->tiled = val & DISPPLANE_TILED; fmt = bdw_format_to_drm(val & DISPPLANE_PIXFORMAT_MASK); plane->bpp = bdw_pixel_formats[fmt].bpp; plane->drm_format = bdw_pixel_formats[fmt].drm_format; diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c index ffdbbac4400e..47062ee979cf 100644 --- a/drivers/gpu/drm/i915/i915_drv.c +++ b/drivers/gpu/drm/i915/i915_drv.c @@ -1444,6 +1444,7 @@ static int i915_driver_init_hw(struct drm_i915_private *dev_priv) intel_uncore_sanitize(dev_priv); + intel_gt_init_workarounds(dev_priv); i915_gem_load_init_fences(dev_priv); /* On the 945G/GM, the chipset reports the MSI capability on the diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h index 9102571e9692..872a2e159a5f 100644 --- a/drivers/gpu/drm/i915/i915_drv.h +++ b/drivers/gpu/drm/i915/i915_drv.h @@ -67,6 +67,7 @@ #include "intel_ringbuffer.h" #include "intel_uncore.h" #include "intel_wopcm.h" +#include "intel_workarounds.h" #include "intel_uc.h" #include "i915_gem.h" @@ -1805,6 +1806,7 @@ struct drm_i915_private { int dpio_phy_iosf_port[I915_NUM_PHYS_VLV]; struct i915_workarounds workarounds; + struct i915_wa_list gt_wa_list; struct i915_frontbuffer_tracking fb_tracking; @@ -2148,6 +2150,8 @@ struct drm_i915_private { struct delayed_work idle_work; ktime_t last_init_time; + + struct i915_vma *scratch; } gt; /* perform PHY state sanity checks? */ @@ -3870,4 +3874,9 @@ static inline int intel_hws_csb_write_index(struct drm_i915_private *i915) return I915_HWS_CSB_WRITE_INDEX; } +static inline u32 i915_scratch_offset(const struct drm_i915_private *i915) +{ + return i915_ggtt_offset(i915->gt.scratch); +} + #endif diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c index 0c8aa57ce83b..6ae9a6080cc8 100644 --- a/drivers/gpu/drm/i915/i915_gem.c +++ b/drivers/gpu/drm/i915/i915_gem.c @@ -5305,7 +5305,7 @@ int i915_gem_init_hw(struct drm_i915_private *dev_priv) } } - intel_gt_workarounds_apply(dev_priv); + intel_gt_apply_workarounds(dev_priv); i915_gem_init_swizzling(dev_priv); @@ -5500,6 +5500,44 @@ err_active: goto out_ctx; } +static int +i915_gem_init_scratch(struct drm_i915_private *i915, unsigned int size) +{ + struct drm_i915_gem_object *obj; + struct i915_vma *vma; + int ret; + + obj = i915_gem_object_create_stolen(i915, size); + if (!obj) + obj = i915_gem_object_create_internal(i915, size); + if (IS_ERR(obj)) { + DRM_ERROR("Failed to allocate scratch page\n"); + return PTR_ERR(obj); + } + + vma = i915_vma_instance(obj, &i915->ggtt.vm, NULL); + if (IS_ERR(vma)) { + ret = PTR_ERR(vma); + goto err_unref; + } + + ret = i915_vma_pin(vma, 0, 0, PIN_GLOBAL | PIN_HIGH); + if (ret) + goto err_unref; + + i915->gt.scratch = vma; + return 0; + +err_unref: + i915_gem_object_put(obj); + return ret; +} + +static void i915_gem_fini_scratch(struct drm_i915_private *i915) +{ + i915_vma_unpin_and_release(&i915->gt.scratch, 0); +} + int i915_gem_init(struct drm_i915_private *dev_priv) { int ret; @@ -5546,12 +5584,19 @@ int i915_gem_init(struct drm_i915_private *dev_priv) goto err_unlock; } - ret = i915_gem_contexts_init(dev_priv); + ret = i915_gem_init_scratch(dev_priv, + IS_GEN2(dev_priv) ? SZ_256K : PAGE_SIZE); if (ret) { GEM_BUG_ON(ret == -EIO); goto err_ggtt; } + ret = i915_gem_contexts_init(dev_priv); + if (ret) { + GEM_BUG_ON(ret == -EIO); + goto err_scratch; + } + ret = intel_engines_init(dev_priv); if (ret) { GEM_BUG_ON(ret == -EIO); @@ -5624,6 +5669,8 @@ err_pm: err_context: if (ret != -EIO) i915_gem_contexts_fini(dev_priv); +err_scratch: + i915_gem_fini_scratch(dev_priv); err_ggtt: err_unlock: intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL); @@ -5675,8 +5722,11 @@ void i915_gem_fini(struct drm_i915_private *dev_priv) intel_uc_fini(dev_priv); i915_gem_cleanup_engines(dev_priv); i915_gem_contexts_fini(dev_priv); + i915_gem_fini_scratch(dev_priv); mutex_unlock(&dev_priv->drm.struct_mutex); + intel_wa_list_free(&dev_priv->gt_wa_list); + intel_cleanup_gt_powersave(dev_priv); intel_uc_fini_misc(dev_priv); diff --git a/drivers/gpu/drm/i915/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/i915_gem_execbuffer.c index d4fac09095f8..1aaccbe7e1de 100644 --- a/drivers/gpu/drm/i915/i915_gem_execbuffer.c +++ b/drivers/gpu/drm/i915/i915_gem_execbuffer.c @@ -1268,7 +1268,7 @@ relocate_entry(struct i915_vma *vma, else if (gen >= 4) len = 4; else - len = 6; + len = 3; batch = reloc_gpu(eb, vma, len); if (IS_ERR(batch)) @@ -1309,11 +1309,6 @@ relocate_entry(struct i915_vma *vma, *batch++ = MI_STORE_DWORD_IMM | MI_MEM_VIRTUAL; *batch++ = addr; *batch++ = target_offset; - - /* And again for good measure (blb/pnv) */ - *batch++ = MI_STORE_DWORD_IMM | MI_MEM_VIRTUAL; - *batch++ = addr; - *batch++ = target_offset; } goto out; diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c index 3eb33e000d6f..db4128d6c09b 100644 --- a/drivers/gpu/drm/i915/i915_gpu_error.c +++ b/drivers/gpu/drm/i915/i915_gpu_error.c @@ -1495,7 +1495,7 @@ static void gem_record_rings(struct i915_gpu_state *error) if (HAS_BROKEN_CS_TLB(i915)) ee->wa_batchbuffer = i915_error_object_create(i915, - engine->scratch); + i915->gt.scratch); request_record_user_bo(request, ee); ee->ctx = diff --git a/drivers/gpu/drm/i915/intel_engine_cs.c b/drivers/gpu/drm/i915/intel_engine_cs.c index 217ed3ee1cab..76b5f94ea6cb 100644 --- a/drivers/gpu/drm/i915/intel_engine_cs.c +++ b/drivers/gpu/drm/i915/intel_engine_cs.c @@ -490,46 +490,6 @@ void intel_engine_setup_common(struct intel_engine_cs *engine) intel_engine_init_cmd_parser(engine); } -int intel_engine_create_scratch(struct intel_engine_cs *engine, - unsigned int size) -{ - struct drm_i915_gem_object *obj; - struct i915_vma *vma; - int ret; - - WARN_ON(engine->scratch); - - obj = i915_gem_object_create_stolen(engine->i915, size); - if (!obj) - obj = i915_gem_object_create_internal(engine->i915, size); - if (IS_ERR(obj)) { - DRM_ERROR("Failed to allocate scratch page\n"); - return PTR_ERR(obj); - } - - vma = i915_vma_instance(obj, &engine->i915->ggtt.vm, NULL); - if (IS_ERR(vma)) { - ret = PTR_ERR(vma); - goto err_unref; - } - - ret = i915_vma_pin(vma, 0, 0, PIN_GLOBAL | PIN_HIGH); - if (ret) - goto err_unref; - - engine->scratch = vma; - return 0; - -err_unref: - i915_gem_object_put(obj); - return ret; -} - -void intel_engine_cleanup_scratch(struct intel_engine_cs *engine) -{ - i915_vma_unpin_and_release(&engine->scratch, 0); -} - static void cleanup_status_page(struct intel_engine_cs *engine) { if (HWS_NEEDS_PHYSICAL(engine->i915)) { @@ -704,8 +664,6 @@ void intel_engine_cleanup_common(struct intel_engine_cs *engine) { struct drm_i915_private *i915 = engine->i915; - intel_engine_cleanup_scratch(engine); - cleanup_status_page(engine); intel_engine_fini_breadcrumbs(engine); @@ -720,6 +678,8 @@ void intel_engine_cleanup_common(struct intel_engine_cs *engine) __intel_context_unpin(i915->kernel_context, engine); i915_timeline_fini(&engine->timeline); + + intel_wa_list_free(&engine->wa_list); } u64 intel_engine_get_active_head(const struct intel_engine_cs *engine) diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c index 37c94a54efcb..58d1d3d47dd3 100644 --- a/drivers/gpu/drm/i915/intel_lrc.c +++ b/drivers/gpu/drm/i915/intel_lrc.c @@ -442,8 +442,13 @@ static u64 execlists_update_context(struct i915_request *rq) * may not be visible to the HW prior to the completion of the UC * register write and that we may begin execution from the context * before its image is complete leading to invalid PD chasing. + * + * Furthermore, Braswell, at least, wants a full mb to be sure that + * the writes are coherent in memory (visible to the GPU) prior to + * execution, and not just visible to other CPUs (as is the result of + * wmb). */ - wmb(); + mb(); return ce->lrc_desc; } @@ -1443,9 +1448,10 @@ static int execlists_request_alloc(struct i915_request *request) static u32 * gen8_emit_flush_coherentl3_wa(struct intel_engine_cs *engine, u32 *batch) { + /* NB no one else is allowed to scribble over scratch + 256! */ *batch++ = MI_STORE_REGISTER_MEM_GEN8 | MI_SRM_LRM_GLOBAL_GTT; *batch++ = i915_mmio_reg_offset(GEN8_L3SQCREG4); - *batch++ = i915_ggtt_offset(engine->scratch) + 256; + *batch++ = i915_scratch_offset(engine->i915) + 256; *batch++ = 0; *batch++ = MI_LOAD_REGISTER_IMM(1); @@ -1459,7 +1465,7 @@ gen8_emit_flush_coherentl3_wa(struct intel_engine_cs *engine, u32 *batch) *batch++ = MI_LOAD_REGISTER_MEM_GEN8 | MI_SRM_LRM_GLOBAL_GTT; *batch++ = i915_mmio_reg_offset(GEN8_L3SQCREG4); - *batch++ = i915_ggtt_offset(engine->scratch) + 256; + *batch++ = i915_scratch_offset(engine->i915) + 256; *batch++ = 0; return batch; @@ -1496,7 +1502,7 @@ static u32 *gen8_init_indirectctx_bb(struct intel_engine_cs *engine, u32 *batch) PIPE_CONTROL_GLOBAL_GTT_IVB | PIPE_CONTROL_CS_STALL | PIPE_CONTROL_QW_WRITE, - i915_ggtt_offset(engine->scratch) + + i915_scratch_offset(engine->i915) + 2 * CACHELINE_BYTES); *batch++ = MI_ARB_ON_OFF | MI_ARB_ENABLE; @@ -1573,7 +1579,7 @@ static u32 *gen9_init_indirectctx_bb(struct intel_engine_cs *engine, u32 *batch) PIPE_CONTROL_GLOBAL_GTT_IVB | PIPE_CONTROL_CS_STALL | PIPE_CONTROL_QW_WRITE, - i915_ggtt_offset(engine->scratch) + i915_scratch_offset(engine->i915) + 2 * CACHELINE_BYTES); } @@ -1793,6 +1799,8 @@ static bool unexpected_starting_state(struct intel_engine_cs *engine) static int gen8_init_common_ring(struct intel_engine_cs *engine) { + intel_engine_apply_workarounds(engine); + intel_mocs_init_engine(engine); intel_engine_reset_breadcrumbs(engine); @@ -2139,7 +2147,7 @@ static int gen8_emit_flush_render(struct i915_request *request, { struct intel_engine_cs *engine = request->engine; u32 scratch_addr = - i915_ggtt_offset(engine->scratch) + 2 * CACHELINE_BYTES; + i915_scratch_offset(engine->i915) + 2 * CACHELINE_BYTES; bool vf_flush_wa = false, dc_flush_wa = false; u32 *cs, flags = 0; int len; @@ -2476,10 +2484,6 @@ int logical_render_ring_init(struct intel_engine_cs *engine) if (ret) return ret; - ret = intel_engine_create_scratch(engine, PAGE_SIZE); - if (ret) - goto err_cleanup_common; - ret = intel_init_workaround_bb(engine); if (ret) { /* @@ -2491,11 +2495,9 @@ int logical_render_ring_init(struct intel_engine_cs *engine) ret); } - return 0; + intel_engine_init_workarounds(engine); -err_cleanup_common: - intel_engine_cleanup_common(engine); - return ret; + return 0; } int logical_xcs_ring_init(struct intel_engine_cs *engine) diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c index 187bb0ceb4ac..1f8d2a66c791 100644 --- a/drivers/gpu/drm/i915/intel_ringbuffer.c +++ b/drivers/gpu/drm/i915/intel_ringbuffer.c @@ -69,19 +69,28 @@ unsigned int intel_ring_update_space(struct intel_ring *ring) static int gen2_render_ring_flush(struct i915_request *rq, u32 mode) { + unsigned int num_store_dw; u32 cmd, *cs; cmd = MI_FLUSH; - + num_store_dw = 0; if (mode & EMIT_INVALIDATE) cmd |= MI_READ_FLUSH; + if (mode & EMIT_FLUSH) + num_store_dw = 4; - cs = intel_ring_begin(rq, 2); + cs = intel_ring_begin(rq, 2 + 3 * num_store_dw); if (IS_ERR(cs)) return PTR_ERR(cs); *cs++ = cmd; - *cs++ = MI_NOOP; + while (num_store_dw--) { + *cs++ = MI_STORE_DWORD_IMM | MI_MEM_VIRTUAL; + *cs++ = i915_scratch_offset(rq->i915); + *cs++ = 0; + } + *cs++ = MI_FLUSH | MI_NO_WRITE_FLUSH; + intel_ring_advance(rq, cs); return 0; @@ -150,8 +159,7 @@ gen4_render_ring_flush(struct i915_request *rq, u32 mode) */ if (mode & EMIT_INVALIDATE) { *cs++ = GFX_OP_PIPE_CONTROL(4) | PIPE_CONTROL_QW_WRITE; - *cs++ = i915_ggtt_offset(rq->engine->scratch) | - PIPE_CONTROL_GLOBAL_GTT; + *cs++ = i915_scratch_offset(rq->i915) | PIPE_CONTROL_GLOBAL_GTT; *cs++ = 0; *cs++ = 0; @@ -159,8 +167,7 @@ gen4_render_ring_flush(struct i915_request *rq, u32 mode) *cs++ = MI_FLUSH; *cs++ = GFX_OP_PIPE_CONTROL(4) | PIPE_CONTROL_QW_WRITE; - *cs++ = i915_ggtt_offset(rq->engine->scratch) | - PIPE_CONTROL_GLOBAL_GTT; + *cs++ = i915_scratch_offset(rq->i915) | PIPE_CONTROL_GLOBAL_GTT; *cs++ = 0; *cs++ = 0; } @@ -212,8 +219,7 @@ gen4_render_ring_flush(struct i915_request *rq, u32 mode) static int intel_emit_post_sync_nonzero_flush(struct i915_request *rq) { - u32 scratch_addr = - i915_ggtt_offset(rq->engine->scratch) + 2 * CACHELINE_BYTES; + u32 scratch_addr = i915_scratch_offset(rq->i915) + 2 * CACHELINE_BYTES; u32 *cs; cs = intel_ring_begin(rq, 6); @@ -246,8 +252,7 @@ intel_emit_post_sync_nonzero_flush(struct i915_request *rq) static int gen6_render_ring_flush(struct i915_request *rq, u32 mode) { - u32 scratch_addr = - i915_ggtt_offset(rq->engine->scratch) + 2 * CACHELINE_BYTES; + u32 scratch_addr = i915_scratch_offset(rq->i915) + 2 * CACHELINE_BYTES; u32 *cs, flags = 0; int ret; @@ -316,8 +321,7 @@ gen7_render_ring_cs_stall_wa(struct i915_request *rq) static int gen7_render_ring_flush(struct i915_request *rq, u32 mode) { - u32 scratch_addr = - i915_ggtt_offset(rq->engine->scratch) + 2 * CACHELINE_BYTES; + u32 scratch_addr = i915_scratch_offset(rq->i915) + 2 * CACHELINE_BYTES; u32 *cs, flags = 0; /* @@ -971,7 +975,7 @@ i965_emit_bb_start(struct i915_request *rq, } /* Just userspace ABI convention to limit the wa batch bo to a resonable size */ -#define I830_BATCH_LIMIT (256*1024) +#define I830_BATCH_LIMIT SZ_256K #define I830_TLB_ENTRIES (2) #define I830_WA_SIZE max(I830_TLB_ENTRIES*4096, I830_BATCH_LIMIT) static int @@ -979,7 +983,9 @@ i830_emit_bb_start(struct i915_request *rq, u64 offset, u32 len, unsigned int dispatch_flags) { - u32 *cs, cs_offset = i915_ggtt_offset(rq->engine->scratch); + u32 *cs, cs_offset = i915_scratch_offset(rq->i915); + + GEM_BUG_ON(rq->i915->gt.scratch->size < I830_WA_SIZE); cs = intel_ring_begin(rq, 6); if (IS_ERR(cs)) @@ -1437,7 +1443,6 @@ static int intel_init_ring_buffer(struct intel_engine_cs *engine) { struct i915_timeline *timeline; struct intel_ring *ring; - unsigned int size; int err; intel_engine_setup_common(engine); @@ -1462,21 +1467,12 @@ static int intel_init_ring_buffer(struct intel_engine_cs *engine) GEM_BUG_ON(engine->buffer); engine->buffer = ring; - size = PAGE_SIZE; - if (HAS_BROKEN_CS_TLB(engine->i915)) - size = I830_WA_SIZE; - err = intel_engine_create_scratch(engine, size); - if (err) - goto err_unpin; - err = intel_engine_init_common(engine); if (err) - goto err_scratch; + goto err_unpin; return 0; -err_scratch: - intel_engine_cleanup_scratch(engine); err_unpin: intel_ring_unpin(ring); err_ring: @@ -1550,7 +1546,7 @@ static int flush_pd_dir(struct i915_request *rq) /* Stall until the page table load is complete */ *cs++ = MI_STORE_REGISTER_MEM | MI_SRM_LRM_GLOBAL_GTT; *cs++ = i915_mmio_reg_offset(RING_PP_DIR_BASE(engine)); - *cs++ = i915_ggtt_offset(engine->scratch); + *cs++ = i915_scratch_offset(rq->i915); *cs++ = MI_NOOP; intel_ring_advance(rq, cs); @@ -1659,7 +1655,7 @@ static inline int mi_set_context(struct i915_request *rq, u32 flags) /* Insert a delay before the next switch! */ *cs++ = MI_STORE_REGISTER_MEM | MI_SRM_LRM_GLOBAL_GTT; *cs++ = i915_mmio_reg_offset(last_reg); - *cs++ = i915_ggtt_offset(engine->scratch); + *cs++ = i915_scratch_offset(rq->i915); *cs++ = MI_NOOP; } *cs++ = MI_ARB_ON_OFF | MI_ARB_ENABLE; diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h index 2dfa585712c2..767a7192c969 100644 --- a/drivers/gpu/drm/i915/intel_ringbuffer.h +++ b/drivers/gpu/drm/i915/intel_ringbuffer.h @@ -15,6 +15,7 @@ #include "i915_selftest.h" #include "i915_timeline.h" #include "intel_gpu_commands.h" +#include "intel_workarounds.h" struct drm_printer; struct i915_sched_attr; @@ -440,7 +441,7 @@ struct intel_engine_cs { struct intel_hw_status_page status_page; struct i915_ctx_workarounds wa_ctx; - struct i915_vma *scratch; + struct i915_wa_list wa_list; u32 irq_keep_mask; /* always keep these interrupts */ u32 irq_enable_mask; /* bitmask to enable ring interrupt */ @@ -898,10 +899,6 @@ void intel_engine_setup_common(struct intel_engine_cs *engine); int intel_engine_init_common(struct intel_engine_cs *engine); void intel_engine_cleanup_common(struct intel_engine_cs *engine); -int intel_engine_create_scratch(struct intel_engine_cs *engine, - unsigned int size); -void intel_engine_cleanup_scratch(struct intel_engine_cs *engine); - int intel_init_render_ring_buffer(struct intel_engine_cs *engine); int intel_init_bsd_ring_buffer(struct intel_engine_cs *engine); int intel_init_blt_ring_buffer(struct intel_engine_cs *engine); diff --git a/drivers/gpu/drm/i915/intel_workarounds.c b/drivers/gpu/drm/i915/intel_workarounds.c index 4bcdeaf8d98f..6e580891db96 100644 --- a/drivers/gpu/drm/i915/intel_workarounds.c +++ b/drivers/gpu/drm/i915/intel_workarounds.c @@ -48,6 +48,20 @@ * - Public functions to init or apply the given workaround type. */ +static void wa_init_start(struct i915_wa_list *wal, const char *name) +{ + wal->name = name; +} + +static void wa_init_finish(struct i915_wa_list *wal) +{ + if (!wal->count) + return; + + DRM_DEBUG_DRIVER("Initialized %u %s workarounds\n", + wal->count, wal->name); +} + static void wa_add(struct drm_i915_private *i915, i915_reg_t reg, const u32 mask, const u32 val) { @@ -580,160 +594,175 @@ int intel_ctx_workarounds_emit(struct i915_request *rq) return 0; } -static void bdw_gt_workarounds_apply(struct drm_i915_private *dev_priv) +static void +wal_add(struct i915_wa_list *wal, const struct i915_wa *wa) +{ + const unsigned int grow = 1 << 4; + + GEM_BUG_ON(!is_power_of_2(grow)); + + if (IS_ALIGNED(wal->count, grow)) { /* Either uninitialized or full. */ + struct i915_wa *list; + + list = kmalloc_array(ALIGN(wal->count + 1, grow), sizeof(*wa), + GFP_KERNEL); + if (!list) { + DRM_ERROR("No space for workaround init!\n"); + return; + } + + if (wal->list) + memcpy(list, wal->list, sizeof(*wa) * wal->count); + + wal->list = list; + } + + wal->list[wal->count++] = *wa; +} + +static void +wa_masked_en(struct i915_wa_list *wal, i915_reg_t reg, u32 val) +{ + struct i915_wa wa = { + .reg = reg, + .mask = val, + .val = _MASKED_BIT_ENABLE(val) + }; + + wal_add(wal, &wa); +} + +static void +wa_write_masked_or(struct i915_wa_list *wal, i915_reg_t reg, u32 mask, + u32 val) { + struct i915_wa wa = { + .reg = reg, + .mask = mask, + .val = val + }; + + wal_add(wal, &wa); } -static void chv_gt_workarounds_apply(struct drm_i915_private *dev_priv) +static void +wa_write(struct i915_wa_list *wal, i915_reg_t reg, u32 val) { + wa_write_masked_or(wal, reg, ~0, val); } -static void gen9_gt_workarounds_apply(struct drm_i915_private *dev_priv) +static void +wa_write_or(struct i915_wa_list *wal, i915_reg_t reg, u32 val) { - /* WaContextSwitchWithConcurrentTLBInvalidate:skl,bxt,kbl,glk,cfl */ - I915_WRITE(GEN9_CSFE_CHICKEN1_RCS, - _MASKED_BIT_ENABLE(GEN9_PREEMPT_GPGPU_SYNC_SWITCH_DISABLE)); + wa_write_masked_or(wal, reg, val, val); +} - /* WaEnableLbsSlaRetryTimerDecrement:skl,bxt,kbl,glk,cfl */ - I915_WRITE(BDW_SCRATCH1, I915_READ(BDW_SCRATCH1) | - GEN9_LBS_SLA_RETRY_TIMER_DECREMENT_ENABLE); +static void gen9_gt_workarounds_init(struct drm_i915_private *i915) +{ + struct i915_wa_list *wal = &i915->gt_wa_list; /* WaDisableKillLogic:bxt,skl,kbl */ - if (!IS_COFFEELAKE(dev_priv)) - I915_WRITE(GAM_ECOCHK, I915_READ(GAM_ECOCHK) | - ECOCHK_DIS_TLB); + if (!IS_COFFEELAKE(i915)) + wa_write_or(wal, + GAM_ECOCHK, + ECOCHK_DIS_TLB); - if (HAS_LLC(dev_priv)) { + if (HAS_LLC(i915)) { /* WaCompressedResourceSamplerPbeMediaNewHashMode:skl,kbl * * Must match Display Engine. See * WaCompressedResourceDisplayNewHashMode. */ - I915_WRITE(MMCD_MISC_CTRL, - I915_READ(MMCD_MISC_CTRL) | - MMCD_PCLA | - MMCD_HOTSPOT_EN); + wa_write_or(wal, + MMCD_MISC_CTRL, + MMCD_PCLA | MMCD_HOTSPOT_EN); } /* WaDisableHDCInvalidation:skl,bxt,kbl,cfl */ - I915_WRITE(GAM_ECOCHK, I915_READ(GAM_ECOCHK) | - BDW_DISABLE_HDC_INVALIDATION); - - /* WaProgramL3SqcReg1DefaultForPerf:bxt,glk */ - if (IS_GEN9_LP(dev_priv)) { - u32 val = I915_READ(GEN8_L3SQCREG1); - - val &= ~L3_PRIO_CREDITS_MASK; - val |= L3_GENERAL_PRIO_CREDITS(62) | L3_HIGH_PRIO_CREDITS(2); - I915_WRITE(GEN8_L3SQCREG1, val); - } - - /* WaOCLCoherentLineFlush:skl,bxt,kbl,cfl */ - I915_WRITE(GEN8_L3SQCREG4, - I915_READ(GEN8_L3SQCREG4) | GEN8_LQSC_FLUSH_COHERENT_LINES); - - /* WaEnablePreemptionGranularityControlByUMD:skl,bxt,kbl,cfl,[cnl] */ - I915_WRITE(GEN7_FF_SLICE_CS_CHICKEN1, - _MASKED_BIT_ENABLE(GEN9_FFSC_PERCTX_PREEMPT_CTRL)); + wa_write_or(wal, + GAM_ECOCHK, + BDW_DISABLE_HDC_INVALIDATION); } -static void skl_gt_workarounds_apply(struct drm_i915_private *dev_priv) +static void skl_gt_workarounds_init(struct drm_i915_private *i915) { - gen9_gt_workarounds_apply(dev_priv); + struct i915_wa_list *wal = &i915->gt_wa_list; - /* WaEnableGapsTsvCreditFix:skl */ - I915_WRITE(GEN8_GARBCNTL, - I915_READ(GEN8_GARBCNTL) | GEN9_GAPS_TSV_CREDIT_DISABLE); + gen9_gt_workarounds_init(i915); /* WaDisableGafsUnitClkGating:skl */ - I915_WRITE(GEN7_UCGCTL4, - I915_READ(GEN7_UCGCTL4) | GEN8_EU_GAUNIT_CLOCK_GATE_DISABLE); + wa_write_or(wal, + GEN7_UCGCTL4, + GEN8_EU_GAUNIT_CLOCK_GATE_DISABLE); /* WaInPlaceDecompressionHang:skl */ - if (IS_SKL_REVID(dev_priv, SKL_REVID_H0, REVID_FOREVER)) - I915_WRITE(GEN9_GAMT_ECO_REG_RW_IA, - I915_READ(GEN9_GAMT_ECO_REG_RW_IA) | - GAMT_ECO_ENABLE_IN_PLACE_DECOMPRESS); + if (IS_SKL_REVID(i915, SKL_REVID_H0, REVID_FOREVER)) + wa_write_or(wal, + GEN9_GAMT_ECO_REG_RW_IA, + GAMT_ECO_ENABLE_IN_PLACE_DECOMPRESS); } -static void bxt_gt_workarounds_apply(struct drm_i915_private *dev_priv) +static void bxt_gt_workarounds_init(struct drm_i915_private *i915) { - gen9_gt_workarounds_apply(dev_priv); + struct i915_wa_list *wal = &i915->gt_wa_list; - /* WaDisablePooledEuLoadBalancingFix:bxt */ - I915_WRITE(FF_SLICE_CS_CHICKEN2, - _MASKED_BIT_ENABLE(GEN9_POOLED_EU_LOAD_BALANCING_FIX_DISABLE)); + gen9_gt_workarounds_init(i915); /* WaInPlaceDecompressionHang:bxt */ - I915_WRITE(GEN9_GAMT_ECO_REG_RW_IA, - I915_READ(GEN9_GAMT_ECO_REG_RW_IA) | - GAMT_ECO_ENABLE_IN_PLACE_DECOMPRESS); + wa_write_or(wal, + GEN9_GAMT_ECO_REG_RW_IA, + GAMT_ECO_ENABLE_IN_PLACE_DECOMPRESS); } -static void kbl_gt_workarounds_apply(struct drm_i915_private *dev_priv) +static void kbl_gt_workarounds_init(struct drm_i915_private *i915) { - gen9_gt_workarounds_apply(dev_priv); + struct i915_wa_list *wal = &i915->gt_wa_list; - /* WaEnableGapsTsvCreditFix:kbl */ - I915_WRITE(GEN8_GARBCNTL, - I915_READ(GEN8_GARBCNTL) | GEN9_GAPS_TSV_CREDIT_DISABLE); + gen9_gt_workarounds_init(i915); /* WaDisableDynamicCreditSharing:kbl */ - if (IS_KBL_REVID(dev_priv, 0, KBL_REVID_B0)) - I915_WRITE(GAMT_CHKN_BIT_REG, - I915_READ(GAMT_CHKN_BIT_REG) | - GAMT_CHKN_DISABLE_DYNAMIC_CREDIT_SHARING); + if (IS_KBL_REVID(i915, 0, KBL_REVID_B0)) + wa_write_or(wal, + GAMT_CHKN_BIT_REG, + GAMT_CHKN_DISABLE_DYNAMIC_CREDIT_SHARING); /* WaDisableGafsUnitClkGating:kbl */ - I915_WRITE(GEN7_UCGCTL4, - I915_READ(GEN7_UCGCTL4) | GEN8_EU_GAUNIT_CLOCK_GATE_DISABLE); + wa_write_or(wal, + GEN7_UCGCTL4, + GEN8_EU_GAUNIT_CLOCK_GATE_DISABLE); /* WaInPlaceDecompressionHang:kbl */ - I915_WRITE(GEN9_GAMT_ECO_REG_RW_IA, - I915_READ(GEN9_GAMT_ECO_REG_RW_IA) | - GAMT_ECO_ENABLE_IN_PLACE_DECOMPRESS); - - /* WaKBLVECSSemaphoreWaitPoll:kbl */ - if (IS_KBL_REVID(dev_priv, KBL_REVID_A0, KBL_REVID_E0)) { - struct intel_engine_cs *engine; - unsigned int tmp; - - for_each_engine(engine, dev_priv, tmp) { - if (engine->id == RCS) - continue; - - I915_WRITE(RING_SEMA_WAIT_POLL(engine->mmio_base), 1); - } - } + wa_write_or(wal, + GEN9_GAMT_ECO_REG_RW_IA, + GAMT_ECO_ENABLE_IN_PLACE_DECOMPRESS); } -static void glk_gt_workarounds_apply(struct drm_i915_private *dev_priv) +static void glk_gt_workarounds_init(struct drm_i915_private *i915) { - gen9_gt_workarounds_apply(dev_priv); + gen9_gt_workarounds_init(i915); } -static void cfl_gt_workarounds_apply(struct drm_i915_private *dev_priv) +static void cfl_gt_workarounds_init(struct drm_i915_private *i915) { - gen9_gt_workarounds_apply(dev_priv); + struct i915_wa_list *wal = &i915->gt_wa_list; - /* WaEnableGapsTsvCreditFix:cfl */ - I915_WRITE(GEN8_GARBCNTL, - I915_READ(GEN8_GARBCNTL) | GEN9_GAPS_TSV_CREDIT_DISABLE); + gen9_gt_workarounds_init(i915); /* WaDisableGafsUnitClkGating:cfl */ - I915_WRITE(GEN7_UCGCTL4, - I915_READ(GEN7_UCGCTL4) | GEN8_EU_GAUNIT_CLOCK_GATE_DISABLE); + wa_write_or(wal, + GEN7_UCGCTL4, + GEN8_EU_GAUNIT_CLOCK_GATE_DISABLE); /* WaInPlaceDecompressionHang:cfl */ - I915_WRITE(GEN9_GAMT_ECO_REG_RW_IA, - I915_READ(GEN9_GAMT_ECO_REG_RW_IA) | - GAMT_ECO_ENABLE_IN_PLACE_DECOMPRESS); + wa_write_or(wal, + GEN9_GAMT_ECO_REG_RW_IA, + GAMT_ECO_ENABLE_IN_PLACE_DECOMPRESS); } static void wa_init_mcr(struct drm_i915_private *dev_priv) { const struct sseu_dev_info *sseu = &(INTEL_INFO(dev_priv)->sseu); - u32 mcr; + struct i915_wa_list *wal = &dev_priv->gt_wa_list; u32 mcr_slice_subslice_mask; /* @@ -770,8 +799,6 @@ static void wa_init_mcr(struct drm_i915_private *dev_priv) WARN_ON((enabled_mask & disabled_mask) != enabled_mask); } - mcr = I915_READ(GEN8_MCR_SELECTOR); - if (INTEL_GEN(dev_priv) >= 11) mcr_slice_subslice_mask = GEN11_MCR_SLICE_MASK | GEN11_MCR_SUBSLICE_MASK; @@ -789,148 +816,170 @@ static void wa_init_mcr(struct drm_i915_private *dev_priv) * occasions, such as INSTDONE, where this value is dependent * on s/ss combo, the read should be done with read_subslice_reg. */ - mcr &= ~mcr_slice_subslice_mask; - mcr |= intel_calculate_mcr_s_ss_select(dev_priv); - I915_WRITE(GEN8_MCR_SELECTOR, mcr); + wa_write_masked_or(wal, + GEN8_MCR_SELECTOR, + mcr_slice_subslice_mask, + intel_calculate_mcr_s_ss_select(dev_priv)); } -static void cnl_gt_workarounds_apply(struct drm_i915_private *dev_priv) +static void cnl_gt_workarounds_init(struct drm_i915_private *i915) { - wa_init_mcr(dev_priv); + struct i915_wa_list *wal = &i915->gt_wa_list; + + wa_init_mcr(i915); /* WaDisableI2mCycleOnWRPort:cnl (pre-prod) */ - if (IS_CNL_REVID(dev_priv, CNL_REVID_B0, CNL_REVID_B0)) - I915_WRITE(GAMT_CHKN_BIT_REG, - I915_READ(GAMT_CHKN_BIT_REG) | - GAMT_CHKN_DISABLE_I2M_CYCLE_ON_WR_PORT); + if (IS_CNL_REVID(i915, CNL_REVID_B0, CNL_REVID_B0)) + wa_write_or(wal, + GAMT_CHKN_BIT_REG, + GAMT_CHKN_DISABLE_I2M_CYCLE_ON_WR_PORT); /* WaInPlaceDecompressionHang:cnl */ - I915_WRITE(GEN9_GAMT_ECO_REG_RW_IA, - I915_READ(GEN9_GAMT_ECO_REG_RW_IA) | - GAMT_ECO_ENABLE_IN_PLACE_DECOMPRESS); - - /* WaEnablePreemptionGranularityControlByUMD:cnl */ - I915_WRITE(GEN7_FF_SLICE_CS_CHICKEN1, - _MASKED_BIT_ENABLE(GEN9_FFSC_PERCTX_PREEMPT_CTRL)); + wa_write_or(wal, + GEN9_GAMT_ECO_REG_RW_IA, + GAMT_ECO_ENABLE_IN_PLACE_DECOMPRESS); } -static void icl_gt_workarounds_apply(struct drm_i915_private *dev_priv) +static void icl_gt_workarounds_init(struct drm_i915_private *i915) { - wa_init_mcr(dev_priv); + struct i915_wa_list *wal = &i915->gt_wa_list; - /* This is not an Wa. Enable for better image quality */ - I915_WRITE(_3D_CHICKEN3, - _MASKED_BIT_ENABLE(_3D_CHICKEN3_AA_LINE_QUALITY_FIX_ENABLE)); + wa_init_mcr(i915); /* WaInPlaceDecompressionHang:icl */ - I915_WRITE(GEN9_GAMT_ECO_REG_RW_IA, I915_READ(GEN9_GAMT_ECO_REG_RW_IA) | - GAMT_ECO_ENABLE_IN_PLACE_DECOMPRESS); - - /* WaPipelineFlushCoherentLines:icl */ - I915_WRITE(GEN8_L3SQCREG4, I915_READ(GEN8_L3SQCREG4) | - GEN8_LQSC_FLUSH_COHERENT_LINES); - - /* Wa_1405543622:icl - * Formerly known as WaGAPZPriorityScheme - */ - I915_WRITE(GEN8_GARBCNTL, I915_READ(GEN8_GARBCNTL) | - GEN11_ARBITRATION_PRIO_ORDER_MASK); - - /* Wa_1604223664:icl - * Formerly known as WaL3BankAddressHashing - */ - I915_WRITE(GEN8_GARBCNTL, - (I915_READ(GEN8_GARBCNTL) & ~GEN11_HASH_CTRL_EXCL_MASK) | - GEN11_HASH_CTRL_EXCL_BIT0); - I915_WRITE(GEN11_GLBLINVL, - (I915_READ(GEN11_GLBLINVL) & ~GEN11_BANK_HASH_ADDR_EXCL_MASK) | - GEN11_BANK_HASH_ADDR_EXCL_BIT0); + wa_write_or(wal, + GEN9_GAMT_ECO_REG_RW_IA, + GAMT_ECO_ENABLE_IN_PLACE_DECOMPRESS); /* WaModifyGamTlbPartitioning:icl */ - I915_WRITE(GEN11_GACB_PERF_CTRL, - (I915_READ(GEN11_GACB_PERF_CTRL) & ~GEN11_HASH_CTRL_MASK) | - GEN11_HASH_CTRL_BIT0 | GEN11_HASH_CTRL_BIT4); - - /* Wa_1405733216:icl - * Formerly known as WaDisableCleanEvicts - */ - I915_WRITE(GEN8_L3SQCREG4, I915_READ(GEN8_L3SQCREG4) | - GEN11_LQSC_CLEAN_EVICT_DISABLE); + wa_write_masked_or(wal, + GEN11_GACB_PERF_CTRL, + GEN11_HASH_CTRL_MASK, + GEN11_HASH_CTRL_BIT0 | GEN11_HASH_CTRL_BIT4); /* Wa_1405766107:icl * Formerly known as WaCL2SFHalfMaxAlloc */ - I915_WRITE(GEN11_LSN_UNSLCVC, I915_READ(GEN11_LSN_UNSLCVC) | - GEN11_LSN_UNSLCVC_GAFS_HALF_SF_MAXALLOC | - GEN11_LSN_UNSLCVC_GAFS_HALF_CL2_MAXALLOC); + wa_write_or(wal, + GEN11_LSN_UNSLCVC, + GEN11_LSN_UNSLCVC_GAFS_HALF_SF_MAXALLOC | + GEN11_LSN_UNSLCVC_GAFS_HALF_CL2_MAXALLOC); /* Wa_220166154:icl * Formerly known as WaDisCtxReload */ - I915_WRITE(GAMW_ECO_DEV_RW_IA_REG, I915_READ(GAMW_ECO_DEV_RW_IA_REG) | - GAMW_ECO_DEV_CTX_RELOAD_DISABLE); + wa_write_or(wal, + GEN8_GAMW_ECO_DEV_RW_IA, + GAMW_ECO_DEV_CTX_RELOAD_DISABLE); /* Wa_1405779004:icl (pre-prod) */ - if (IS_ICL_REVID(dev_priv, ICL_REVID_A0, ICL_REVID_A0)) - I915_WRITE(SLICE_UNIT_LEVEL_CLKGATE, - I915_READ(SLICE_UNIT_LEVEL_CLKGATE) | - MSCUNIT_CLKGATE_DIS); + if (IS_ICL_REVID(i915, ICL_REVID_A0, ICL_REVID_A0)) + wa_write_or(wal, + SLICE_UNIT_LEVEL_CLKGATE, + MSCUNIT_CLKGATE_DIS); /* Wa_1406680159:icl */ - I915_WRITE(SUBSLICE_UNIT_LEVEL_CLKGATE, - I915_READ(SUBSLICE_UNIT_LEVEL_CLKGATE) | - GWUNIT_CLKGATE_DIS); - - /* Wa_1604302699:icl */ - I915_WRITE(GEN10_L3_CHICKEN_MODE_REGISTER, - I915_READ(GEN10_L3_CHICKEN_MODE_REGISTER) | - GEN11_I2M_WRITE_DISABLE); + wa_write_or(wal, + SUBSLICE_UNIT_LEVEL_CLKGATE, + GWUNIT_CLKGATE_DIS); /* Wa_1406838659:icl (pre-prod) */ - if (IS_ICL_REVID(dev_priv, ICL_REVID_A0, ICL_REVID_B0)) - I915_WRITE(INF_UNIT_LEVEL_CLKGATE, - I915_READ(INF_UNIT_LEVEL_CLKGATE) | - CGPSF_CLKGATE_DIS); - - /* WaForwardProgressSoftReset:icl */ - I915_WRITE(GEN10_SCRATCH_LNCF2, - I915_READ(GEN10_SCRATCH_LNCF2) | - PMFLUSHDONE_LNICRSDROP | - PMFLUSH_GAPL3UNBLOCK | - PMFLUSHDONE_LNEBLK); + if (IS_ICL_REVID(i915, ICL_REVID_A0, ICL_REVID_B0)) + wa_write_or(wal, + INF_UNIT_LEVEL_CLKGATE, + CGPSF_CLKGATE_DIS); /* Wa_1406463099:icl * Formerly known as WaGamTlbPendError */ - I915_WRITE(GAMT_CHKN_BIT_REG, - I915_READ(GAMT_CHKN_BIT_REG) | - GAMT_CHKN_DISABLE_L3_COH_PIPE); + wa_write_or(wal, + GAMT_CHKN_BIT_REG, + GAMT_CHKN_DISABLE_L3_COH_PIPE); } -void intel_gt_workarounds_apply(struct drm_i915_private *dev_priv) +void intel_gt_init_workarounds(struct drm_i915_private *i915) { - if (INTEL_GEN(dev_priv) < 8) + struct i915_wa_list *wal = &i915->gt_wa_list; + + wa_init_start(wal, "GT"); + + if (INTEL_GEN(i915) < 8) return; - else if (IS_BROADWELL(dev_priv)) - bdw_gt_workarounds_apply(dev_priv); - else if (IS_CHERRYVIEW(dev_priv)) - chv_gt_workarounds_apply(dev_priv); - else if (IS_SKYLAKE(dev_priv)) - skl_gt_workarounds_apply(dev_priv); - else if (IS_BROXTON(dev_priv)) - bxt_gt_workarounds_apply(dev_priv); - else if (IS_KABYLAKE(dev_priv)) - kbl_gt_workarounds_apply(dev_priv); - else if (IS_GEMINILAKE(dev_priv)) - glk_gt_workarounds_apply(dev_priv); - else if (IS_COFFEELAKE(dev_priv)) - cfl_gt_workarounds_apply(dev_priv); - else if (IS_CANNONLAKE(dev_priv)) - cnl_gt_workarounds_apply(dev_priv); - else if (IS_ICELAKE(dev_priv)) - icl_gt_workarounds_apply(dev_priv); + else if (IS_BROADWELL(i915)) + return; + else if (IS_CHERRYVIEW(i915)) + return; + else if (IS_SKYLAKE(i915)) + skl_gt_workarounds_init(i915); + else if (IS_BROXTON(i915)) + bxt_gt_workarounds_init(i915); + else if (IS_KABYLAKE(i915)) + kbl_gt_workarounds_init(i915); + else if (IS_GEMINILAKE(i915)) + glk_gt_workarounds_init(i915); + else if (IS_COFFEELAKE(i915)) + cfl_gt_workarounds_init(i915); + else if (IS_CANNONLAKE(i915)) + cnl_gt_workarounds_init(i915); + else if (IS_ICELAKE(i915)) + icl_gt_workarounds_init(i915); else - MISSING_CASE(INTEL_GEN(dev_priv)); + MISSING_CASE(INTEL_GEN(i915)); + + wa_init_finish(wal); +} + +static enum forcewake_domains +wal_get_fw_for_rmw(struct drm_i915_private *dev_priv, + const struct i915_wa_list *wal) +{ + enum forcewake_domains fw = 0; + struct i915_wa *wa; + unsigned int i; + + for (i = 0, wa = wal->list; i < wal->count; i++, wa++) + fw |= intel_uncore_forcewake_for_reg(dev_priv, + wa->reg, + FW_REG_READ | + FW_REG_WRITE); + + return fw; +} + +static void +wa_list_apply(struct drm_i915_private *dev_priv, const struct i915_wa_list *wal) +{ + enum forcewake_domains fw; + unsigned long flags; + struct i915_wa *wa; + unsigned int i; + + if (!wal->count) + return; + + fw = wal_get_fw_for_rmw(dev_priv, wal); + + spin_lock_irqsave(&dev_priv->uncore.lock, flags); + intel_uncore_forcewake_get__locked(dev_priv, fw); + + for (i = 0, wa = wal->list; i < wal->count; i++, wa++) { + u32 val = I915_READ_FW(wa->reg); + + val &= ~wa->mask; + val |= wa->val; + + I915_WRITE_FW(wa->reg, val); + } + + intel_uncore_forcewake_put__locked(dev_priv, fw); + spin_unlock_irqrestore(&dev_priv->uncore.lock, flags); + + DRM_DEBUG_DRIVER("Applied %u %s workarounds\n", wal->count, wal->name); +} + +void intel_gt_apply_workarounds(struct drm_i915_private *dev_priv) +{ + wa_list_apply(dev_priv, &dev_priv->gt_wa_list); } struct whitelist { @@ -1077,6 +1126,146 @@ void intel_whitelist_workarounds_apply(struct intel_engine_cs *engine) whitelist_apply(engine, whitelist_build(engine, &w)); } +static void rcs_engine_wa_init(struct intel_engine_cs *engine) +{ + struct drm_i915_private *i915 = engine->i915; + struct i915_wa_list *wal = &engine->wa_list; + + if (IS_ICELAKE(i915)) { + /* This is not an Wa. Enable for better image quality */ + wa_masked_en(wal, + _3D_CHICKEN3, + _3D_CHICKEN3_AA_LINE_QUALITY_FIX_ENABLE); + + /* WaPipelineFlushCoherentLines:icl */ + wa_write_or(wal, + GEN8_L3SQCREG4, + GEN8_LQSC_FLUSH_COHERENT_LINES); + + /* + * Wa_1405543622:icl + * Formerly known as WaGAPZPriorityScheme + */ + wa_write_or(wal, + GEN8_GARBCNTL, + GEN11_ARBITRATION_PRIO_ORDER_MASK); + + /* + * Wa_1604223664:icl + * Formerly known as WaL3BankAddressHashing + */ + wa_write_masked_or(wal, + GEN8_GARBCNTL, + GEN11_HASH_CTRL_EXCL_MASK, + GEN11_HASH_CTRL_EXCL_BIT0); + wa_write_masked_or(wal, + GEN11_GLBLINVL, + GEN11_BANK_HASH_ADDR_EXCL_MASK, + GEN11_BANK_HASH_ADDR_EXCL_BIT0); + + /* + * Wa_1405733216:icl + * Formerly known as WaDisableCleanEvicts + */ + wa_write_or(wal, + GEN8_L3SQCREG4, + GEN11_LQSC_CLEAN_EVICT_DISABLE); + + /* Wa_1604302699:icl */ + wa_write_or(wal, + GEN10_L3_CHICKEN_MODE_REGISTER, + GEN11_I2M_WRITE_DISABLE); + + /* WaForwardProgressSoftReset:icl */ + wa_write_or(wal, + GEN10_SCRATCH_LNCF2, + PMFLUSHDONE_LNICRSDROP | + PMFLUSH_GAPL3UNBLOCK | + PMFLUSHDONE_LNEBLK); + } + + if (IS_GEN9(i915) || IS_CANNONLAKE(i915)) { + /* WaEnablePreemptionGranularityControlByUMD:skl,bxt,kbl,cfl,cnl */ + wa_masked_en(wal, + GEN7_FF_SLICE_CS_CHICKEN1, + GEN9_FFSC_PERCTX_PREEMPT_CTRL); + } + + if (IS_SKYLAKE(i915) || IS_KABYLAKE(i915) || IS_COFFEELAKE(i915)) { + /* WaEnableGapsTsvCreditFix:skl,kbl,cfl */ + wa_write_or(wal, + GEN8_GARBCNTL, + GEN9_GAPS_TSV_CREDIT_DISABLE); + } + + if (IS_BROXTON(i915)) { + /* WaDisablePooledEuLoadBalancingFix:bxt */ + wa_masked_en(wal, + FF_SLICE_CS_CHICKEN2, + GEN9_POOLED_EU_LOAD_BALANCING_FIX_DISABLE); + } + + if (IS_GEN9(i915)) { + /* WaContextSwitchWithConcurrentTLBInvalidate:skl,bxt,kbl,glk,cfl */ + wa_masked_en(wal, + GEN9_CSFE_CHICKEN1_RCS, + GEN9_PREEMPT_GPGPU_SYNC_SWITCH_DISABLE); + + /* WaEnableLbsSlaRetryTimerDecrement:skl,bxt,kbl,glk,cfl */ + wa_write_or(wal, + BDW_SCRATCH1, + GEN9_LBS_SLA_RETRY_TIMER_DECREMENT_ENABLE); + + /* WaProgramL3SqcReg1DefaultForPerf:bxt,glk */ + if (IS_GEN9_LP(i915)) + wa_write_masked_or(wal, + GEN8_L3SQCREG1, + L3_PRIO_CREDITS_MASK, + L3_GENERAL_PRIO_CREDITS(62) | + L3_HIGH_PRIO_CREDITS(2)); + + /* WaOCLCoherentLineFlush:skl,bxt,kbl,cfl */ + wa_write_or(wal, + GEN8_L3SQCREG4, + GEN8_LQSC_FLUSH_COHERENT_LINES); + } +} + +static void xcs_engine_wa_init(struct intel_engine_cs *engine) +{ + struct drm_i915_private *i915 = engine->i915; + struct i915_wa_list *wal = &engine->wa_list; + + /* WaKBLVECSSemaphoreWaitPoll:kbl */ + if (IS_KBL_REVID(i915, KBL_REVID_A0, KBL_REVID_E0)) { + wa_write(wal, + RING_SEMA_WAIT_POLL(engine->mmio_base), + 1); + } +} + +void intel_engine_init_workarounds(struct intel_engine_cs *engine) +{ + struct i915_wa_list *wal = &engine->wa_list; + + if (GEM_WARN_ON(INTEL_GEN(engine->i915) < 8)) + return; + + wa_init_start(wal, engine->name); + + if (engine->id == RCS) + rcs_engine_wa_init(engine); + else + xcs_engine_wa_init(engine); + + wa_init_finish(wal); +} + +void intel_engine_apply_workarounds(struct intel_engine_cs *engine) +{ + wa_list_apply(engine->i915, &engine->wa_list); +} + #if IS_ENABLED(CONFIG_DRM_I915_SELFTEST) #include "selftests/intel_workarounds.c" #endif diff --git a/drivers/gpu/drm/i915/intel_workarounds.h b/drivers/gpu/drm/i915/intel_workarounds.h index b11d0623e626..979695a53964 100644 --- a/drivers/gpu/drm/i915/intel_workarounds.h +++ b/drivers/gpu/drm/i915/intel_workarounds.h @@ -7,11 +7,35 @@ #ifndef _I915_WORKAROUNDS_H_ #define _I915_WORKAROUNDS_H_ +#include <linux/slab.h> + +struct i915_wa { + i915_reg_t reg; + u32 mask; + u32 val; +}; + +struct i915_wa_list { + const char *name; + struct i915_wa *list; + unsigned int count; +}; + +static inline void intel_wa_list_free(struct i915_wa_list *wal) +{ + kfree(wal->list); + memset(wal, 0, sizeof(*wal)); +} + int intel_ctx_workarounds_init(struct drm_i915_private *dev_priv); int intel_ctx_workarounds_emit(struct i915_request *rq); -void intel_gt_workarounds_apply(struct drm_i915_private *dev_priv); +void intel_gt_init_workarounds(struct drm_i915_private *dev_priv); +void intel_gt_apply_workarounds(struct drm_i915_private *dev_priv); void intel_whitelist_workarounds_apply(struct intel_engine_cs *engine); +void intel_engine_init_workarounds(struct intel_engine_cs *engine); +void intel_engine_apply_workarounds(struct intel_engine_cs *engine); + #endif diff --git a/drivers/gpu/drm/mediatek/mtk_dsi.c b/drivers/gpu/drm/mediatek/mtk_dsi.c index 66df1b177959..27b507eb4a99 100644 --- a/drivers/gpu/drm/mediatek/mtk_dsi.c +++ b/drivers/gpu/drm/mediatek/mtk_dsi.c @@ -818,10 +818,13 @@ static int mtk_dsi_create_conn_enc(struct drm_device *drm, struct mtk_dsi *dsi) dsi->encoder.possible_crtcs = 1; /* If there's a bridge, attach to it and let it create the connector */ - ret = drm_bridge_attach(&dsi->encoder, dsi->bridge, NULL); - if (ret) { - DRM_ERROR("Failed to attach bridge to drm\n"); - + if (dsi->bridge) { + ret = drm_bridge_attach(&dsi->encoder, dsi->bridge, NULL); + if (ret) { + DRM_ERROR("Failed to attach bridge to drm\n"); + goto err_encoder_cleanup; + } + } else { /* Otherwise create our own connector and attach to a panel */ ret = mtk_dsi_create_connector(drm, dsi); if (ret) diff --git a/drivers/gpu/drm/nouveau/dispnv50/disp.c b/drivers/gpu/drm/nouveau/dispnv50/disp.c index 6cbbae3f438b..db1bf7f88c1f 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/disp.c +++ b/drivers/gpu/drm/nouveau/dispnv50/disp.c @@ -198,6 +198,22 @@ nv50_dmac_create(struct nvif_device *device, struct nvif_object *disp, /****************************************************************************** * EVO channel helpers *****************************************************************************/ +static void +evo_flush(struct nv50_dmac *dmac) +{ + /* Push buffer fetches are not coherent with BAR1, we need to ensure + * writes have been flushed right through to VRAM before writing PUT. + */ + if (dmac->push.type & NVIF_MEM_VRAM) { + struct nvif_device *device = dmac->base.device; + nvif_wr32(&device->object, 0x070000, 0x00000001); + nvif_msec(device, 2000, + if (!(nvif_rd32(&device->object, 0x070000) & 0x00000002)) + break; + ); + } +} + u32 * evo_wait(struct nv50_dmac *evoc, int nr) { @@ -208,6 +224,7 @@ evo_wait(struct nv50_dmac *evoc, int nr) mutex_lock(&dmac->lock); if (put + nr >= (PAGE_SIZE / 4) - 8) { dmac->ptr[put] = 0x20000000; + evo_flush(dmac); nvif_wr32(&dmac->base.user, 0x0000, 0x00000000); if (nvif_msec(device, 2000, @@ -230,17 +247,7 @@ evo_kick(u32 *push, struct nv50_dmac *evoc) { struct nv50_dmac *dmac = evoc; - /* Push buffer fetches are not coherent with BAR1, we need to ensure - * writes have been flushed right through to VRAM before writing PUT. - */ - if (dmac->push.type & NVIF_MEM_VRAM) { - struct nvif_device *device = dmac->base.device; - nvif_wr32(&device->object, 0x070000, 0x00000001); - nvif_msec(device, 2000, - if (!(nvif_rd32(&device->object, 0x070000) & 0x00000002)) - break; - ); - } + evo_flush(dmac); nvif_wr32(&dmac->base.user, 0x0000, (push - dmac->ptr) << 2); mutex_unlock(&dmac->lock); @@ -1264,6 +1271,7 @@ nv50_mstm_del(struct nv50_mstm **pmstm) { struct nv50_mstm *mstm = *pmstm; if (mstm) { + drm_dp_mst_topology_mgr_destroy(&mstm->mgr); kfree(*pmstm); *pmstm = NULL; } diff --git a/drivers/gpu/drm/nouveau/nouveau_drm.c b/drivers/gpu/drm/nouveau/nouveau_drm.c index 2b2baf6e0e0d..d2928d43f29a 100644 --- a/drivers/gpu/drm/nouveau/nouveau_drm.c +++ b/drivers/gpu/drm/nouveau/nouveau_drm.c @@ -1171,10 +1171,16 @@ nouveau_platform_device_create(const struct nvkm_device_tegra_func *func, goto err_free; } + err = nouveau_drm_device_init(drm); + if (err) + goto err_put; + platform_set_drvdata(pdev, drm); return drm; +err_put: + drm_dev_put(drm); err_free: nvkm_device_del(pdevice); diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_drv.c b/drivers/gpu/drm/rockchip/rockchip_drm_drv.c index 941f35233b1f..5864cb452c5c 100644 --- a/drivers/gpu/drm/rockchip/rockchip_drm_drv.c +++ b/drivers/gpu/drm/rockchip/rockchip_drm_drv.c @@ -448,11 +448,6 @@ static int rockchip_drm_platform_remove(struct platform_device *pdev) return 0; } -static void rockchip_drm_platform_shutdown(struct platform_device *pdev) -{ - rockchip_drm_platform_remove(pdev); -} - static const struct of_device_id rockchip_drm_dt_ids[] = { { .compatible = "rockchip,display-subsystem", }, { /* sentinel */ }, @@ -462,7 +457,6 @@ MODULE_DEVICE_TABLE(of, rockchip_drm_dt_ids); static struct platform_driver rockchip_drm_platform_driver = { .probe = rockchip_drm_platform_probe, .remove = rockchip_drm_platform_remove, - .shutdown = rockchip_drm_platform_shutdown, .driver = { .name = "rockchip-drm", .of_match_table = rockchip_drm_dt_ids, diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c index 61a84b958d67..d7a2dfb8ee9b 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.c @@ -49,6 +49,8 @@ #define VMWGFX_REPO "In Tree" +#define VMWGFX_VALIDATION_MEM_GRAN (16*PAGE_SIZE) + /** * Fully encoded drm commands. Might move to vmw_drm.h @@ -918,7 +920,7 @@ static int vmw_driver_load(struct drm_device *dev, unsigned long chipset) spin_unlock(&dev_priv->cap_lock); } - + vmw_validation_mem_init_ttm(dev_priv, VMWGFX_VALIDATION_MEM_GRAN); ret = vmw_kms_init(dev_priv); if (unlikely(ret != 0)) goto out_no_kms; diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h index 59f614225bcd..aca974b14b55 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h @@ -606,6 +606,9 @@ struct vmw_private { struct vmw_cmdbuf_man *cman; DECLARE_BITMAP(irqthread_pending, VMW_IRQTHREAD_MAX); + + /* Validation memory reservation */ + struct vmw_validation_mem vvm; }; static inline struct vmw_surface *vmw_res_to_srf(struct vmw_resource *res) @@ -846,6 +849,8 @@ extern int vmw_ttm_global_init(struct vmw_private *dev_priv); extern void vmw_ttm_global_release(struct vmw_private *dev_priv); extern int vmw_mmap(struct file *filp, struct vm_area_struct *vma); +extern void vmw_validation_mem_init_ttm(struct vmw_private *dev_priv, + size_t gran); /** * TTM buffer object driver - vmwgfx_ttm_buffer.c */ diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c index 5a6b70ba137a..f2d13a72c05d 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_execbuf.c @@ -1738,7 +1738,6 @@ static int vmw_cmd_check_define_gmrfb(struct vmw_private *dev_priv, void *buf) { struct vmw_buffer_object *vmw_bo; - int ret; struct { uint32_t header; @@ -1748,7 +1747,6 @@ static int vmw_cmd_check_define_gmrfb(struct vmw_private *dev_priv, return vmw_translate_guest_ptr(dev_priv, sw_context, &cmd->body.ptr, &vmw_bo); - return ret; } @@ -3837,6 +3835,8 @@ int vmw_execbuf_process(struct drm_file *file_priv, struct sync_file *sync_file = NULL; DECLARE_VAL_CONTEXT(val_ctx, &sw_context->res_ht, 1); + vmw_validation_set_val_mem(&val_ctx, &dev_priv->vvm); + if (flags & DRM_VMW_EXECBUF_FLAG_EXPORT_FENCE_FD) { out_fence_fd = get_unused_fd_flags(O_CLOEXEC); if (out_fence_fd < 0) { diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_glue.c b/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_glue.c index 7b1e5a5cbd2c..f88247046721 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_glue.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_ttm_glue.c @@ -96,3 +96,39 @@ void vmw_ttm_global_release(struct vmw_private *dev_priv) drm_global_item_unref(&dev_priv->bo_global_ref.ref); drm_global_item_unref(&dev_priv->mem_global_ref); } + +/* struct vmw_validation_mem callback */ +static int vmw_vmt_reserve(struct vmw_validation_mem *m, size_t size) +{ + static struct ttm_operation_ctx ctx = {.interruptible = false, + .no_wait_gpu = false}; + struct vmw_private *dev_priv = container_of(m, struct vmw_private, vvm); + + return ttm_mem_global_alloc(vmw_mem_glob(dev_priv), size, &ctx); +} + +/* struct vmw_validation_mem callback */ +static void vmw_vmt_unreserve(struct vmw_validation_mem *m, size_t size) +{ + struct vmw_private *dev_priv = container_of(m, struct vmw_private, vvm); + + return ttm_mem_global_free(vmw_mem_glob(dev_priv), size); +} + +/** + * vmw_validation_mem_init_ttm - Interface the validation memory tracker + * to ttm. + * @dev_priv: Pointer to struct vmw_private. The reason we choose a vmw private + * rather than a struct vmw_validation_mem is to make sure assumption in the + * callbacks that struct vmw_private derives from struct vmw_validation_mem + * holds true. + * @gran: The recommended allocation granularity + */ +void vmw_validation_mem_init_ttm(struct vmw_private *dev_priv, size_t gran) +{ + struct vmw_validation_mem *vvm = &dev_priv->vvm; + + vvm->reserve_mem = vmw_vmt_reserve; + vvm->unreserve_mem = vmw_vmt_unreserve; + vvm->gran = gran; +} diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_validation.c b/drivers/gpu/drm/vmwgfx/vmwgfx_validation.c index 184025fa938e..f116f092e00b 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_validation.c +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_validation.c @@ -104,11 +104,25 @@ void *vmw_validation_mem_alloc(struct vmw_validation_context *ctx, return NULL; if (ctx->mem_size_left < size) { - struct page *page = alloc_page(GFP_KERNEL | __GFP_ZERO); + struct page *page; + if (ctx->vm && ctx->vm_size_left < PAGE_SIZE) { + int ret = ctx->vm->reserve_mem(ctx->vm, ctx->vm->gran); + + if (ret) + return NULL; + + ctx->vm_size_left += ctx->vm->gran; + ctx->total_mem += ctx->vm->gran; + } + + page = alloc_page(GFP_KERNEL | __GFP_ZERO); if (!page) return NULL; + if (ctx->vm) + ctx->vm_size_left -= PAGE_SIZE; + list_add_tail(&page->lru, &ctx->page_list); ctx->page_address = page_address(page); ctx->mem_size_left = PAGE_SIZE; @@ -138,6 +152,11 @@ static void vmw_validation_mem_free(struct vmw_validation_context *ctx) } ctx->mem_size_left = 0; + if (ctx->vm && ctx->total_mem) { + ctx->vm->unreserve_mem(ctx->vm, ctx->total_mem); + ctx->total_mem = 0; + ctx->vm_size_left = 0; + } } /** diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_validation.h b/drivers/gpu/drm/vmwgfx/vmwgfx_validation.h index b57e3292c386..3b396fea40d7 100644 --- a/drivers/gpu/drm/vmwgfx/vmwgfx_validation.h +++ b/drivers/gpu/drm/vmwgfx/vmwgfx_validation.h @@ -34,6 +34,21 @@ #include <drm/ttm/ttm_execbuf_util.h> /** + * struct vmw_validation_mem - Custom interface to provide memory reservations + * for the validation code. + * @reserve_mem: Callback to reserve memory + * @unreserve_mem: Callback to unreserve memory + * @gran: Reservation granularity. Contains a hint how much memory should + * be reserved in each call to @reserve_mem(). A slow implementation may want + * reservation to be done in large batches. + */ +struct vmw_validation_mem { + int (*reserve_mem)(struct vmw_validation_mem *m, size_t size); + void (*unreserve_mem)(struct vmw_validation_mem *m, size_t size); + size_t gran; +}; + +/** * struct vmw_validation_context - Per command submission validation context * @ht: Hash table used to find resource- or buffer object duplicates * @resource_list: List head for resource validation metadata @@ -47,6 +62,10 @@ * buffer objects * @mem_size_left: Free memory left in the last page in @page_list * @page_address: Kernel virtual address of the last page in @page_list + * @vm: A pointer to the memory reservation interface or NULL if no + * memory reservation is needed. + * @vm_size_left: Amount of reserved memory that so far has not been allocated. + * @total_mem: Amount of reserved memory. */ struct vmw_validation_context { struct drm_open_hash *ht; @@ -59,6 +78,9 @@ struct vmw_validation_context { unsigned int merge_dups; unsigned int mem_size_left; u8 *page_address; + struct vmw_validation_mem *vm; + size_t vm_size_left; + size_t total_mem; }; struct vmw_buffer_object; @@ -102,6 +124,21 @@ vmw_validation_has_bos(struct vmw_validation_context *ctx) } /** + * vmw_validation_set_val_mem - Register a validation mem object for + * validation memory reservation + * @ctx: The validation context + * @vm: Pointer to a struct vmw_validation_mem + * + * Must be set before the first attempt to allocate validation memory. + */ +static inline void +vmw_validation_set_val_mem(struct vmw_validation_context *ctx, + struct vmw_validation_mem *vm) +{ + ctx->vm = vm; +} + +/** * vmw_validation_set_ht - Register a hash table for duplicate finding * @ctx: The validation context * @ht: Pointer to a hash table to use for duplicate finding diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h index ed35c9a9a110..27519eb8ee63 100644 --- a/drivers/hid/hid-ids.h +++ b/drivers/hid/hid-ids.h @@ -17,6 +17,9 @@ #ifndef HID_IDS_H_FILE #define HID_IDS_H_FILE +#define USB_VENDOR_ID_258A 0x258a +#define USB_DEVICE_ID_258A_6A88 0x6a88 + #define USB_VENDOR_ID_3M 0x0596 #define USB_DEVICE_ID_3M1968 0x0500 #define USB_DEVICE_ID_3M2256 0x0502 @@ -941,6 +944,10 @@ #define USB_VENDOR_ID_REALTEK 0x0bda #define USB_DEVICE_ID_REALTEK_READER 0x0152 +#define USB_VENDOR_ID_RETROUSB 0xf000 +#define USB_DEVICE_ID_RETROUSB_SNES_RETROPAD 0x0003 +#define USB_DEVICE_ID_RETROUSB_SNES_RETROPORT 0x00f1 + #define USB_VENDOR_ID_ROCCAT 0x1e7d #define USB_DEVICE_ID_ROCCAT_ARVO 0x30d4 #define USB_DEVICE_ID_ROCCAT_ISKU 0x319c diff --git a/drivers/hid/hid-ite.c b/drivers/hid/hid-ite.c index 1882a4ab0f29..98b059d79bc8 100644 --- a/drivers/hid/hid-ite.c +++ b/drivers/hid/hid-ite.c @@ -42,6 +42,7 @@ static int ite_event(struct hid_device *hdev, struct hid_field *field, static const struct hid_device_id ite_devices[] = { { HID_USB_DEVICE(USB_VENDOR_ID_ITE, USB_DEVICE_ID_ITE8595) }, + { HID_USB_DEVICE(USB_VENDOR_ID_258A, USB_DEVICE_ID_258A_6A88) }, { } }; MODULE_DEVICE_TABLE(hid, ite_devices); diff --git a/drivers/hid/hid-quirks.c b/drivers/hid/hid-quirks.c index c85a79986b6a..94088c0ed68a 100644 --- a/drivers/hid/hid-quirks.c +++ b/drivers/hid/hid-quirks.c @@ -137,6 +137,8 @@ static const struct hid_device_id hid_quirks[] = { { HID_USB_DEVICE(USB_VENDOR_ID_QUANTA, USB_DEVICE_ID_QUANTA_OPTICAL_TOUCH_3003), HID_QUIRK_NOGET }, { HID_USB_DEVICE(USB_VENDOR_ID_QUANTA, USB_DEVICE_ID_QUANTA_OPTICAL_TOUCH_3008), HID_QUIRK_NOGET }, { HID_USB_DEVICE(USB_VENDOR_ID_REALTEK, USB_DEVICE_ID_REALTEK_READER), HID_QUIRK_NO_INIT_REPORTS }, + { HID_USB_DEVICE(USB_VENDOR_ID_RETROUSB, USB_DEVICE_ID_RETROUSB_SNES_RETROPAD), HID_QUIRK_INCREMENT_USAGE_ON_DUPLICATE }, + { HID_USB_DEVICE(USB_VENDOR_ID_RETROUSB, USB_DEVICE_ID_RETROUSB_SNES_RETROPORT), HID_QUIRK_INCREMENT_USAGE_ON_DUPLICATE }, { HID_USB_DEVICE(USB_VENDOR_ID_SAITEK, USB_DEVICE_ID_SAITEK_RUMBLEPAD), HID_QUIRK_BADPAD }, { HID_USB_DEVICE(USB_VENDOR_ID_SEMICO, USB_DEVICE_ID_SEMICO_USB_KEYKOARD2), HID_QUIRK_NO_INIT_REPORTS }, { HID_USB_DEVICE(USB_VENDOR_ID_SEMICO, USB_DEVICE_ID_SEMICO_USB_KEYKOARD), HID_QUIRK_NO_INIT_REPORTS }, diff --git a/drivers/infiniband/core/roce_gid_mgmt.c b/drivers/infiniband/core/roce_gid_mgmt.c index 25d43c8f1c2a..558de0b9895c 100644 --- a/drivers/infiniband/core/roce_gid_mgmt.c +++ b/drivers/infiniband/core/roce_gid_mgmt.c @@ -267,6 +267,9 @@ is_upper_ndev_bond_master_filter(struct ib_device *ib_dev, u8 port, struct net_device *cookie_ndev = cookie; bool match = false; + if (!rdma_ndev) + return false; + rcu_read_lock(); if (netif_is_bond_master(cookie_ndev) && rdma_is_upper_dev_rcu(rdma_ndev, cookie_ndev)) diff --git a/drivers/infiniband/hw/hfi1/chip.c b/drivers/infiniband/hw/hfi1/chip.c index 9b20479dc710..7e6d70936c63 100644 --- a/drivers/infiniband/hw/hfi1/chip.c +++ b/drivers/infiniband/hw/hfi1/chip.c @@ -12500,7 +12500,8 @@ static int init_cntrs(struct hfi1_devdata *dd) } /* allocate space for the counter values */ - dd->cntrs = kcalloc(dd->ndevcntrs, sizeof(u64), GFP_KERNEL); + dd->cntrs = kcalloc(dd->ndevcntrs + num_driver_cntrs, sizeof(u64), + GFP_KERNEL); if (!dd->cntrs) goto bail; diff --git a/drivers/infiniband/hw/hfi1/hfi.h b/drivers/infiniband/hw/hfi1/hfi.h index 1401b6ea4a28..2b882347d0c2 100644 --- a/drivers/infiniband/hw/hfi1/hfi.h +++ b/drivers/infiniband/hw/hfi1/hfi.h @@ -155,6 +155,8 @@ struct hfi1_ib_stats { extern struct hfi1_ib_stats hfi1_stats; extern const struct pci_error_handlers hfi1_pci_err_handler; +extern int num_driver_cntrs; + /* * First-cut criterion for "device is active" is * two thousand dwords combined Tx, Rx traffic per diff --git a/drivers/infiniband/hw/hfi1/qp.c b/drivers/infiniband/hw/hfi1/qp.c index 6f3bc4dab858..1a016248039f 100644 --- a/drivers/infiniband/hw/hfi1/qp.c +++ b/drivers/infiniband/hw/hfi1/qp.c @@ -340,6 +340,13 @@ int hfi1_setup_wqe(struct rvt_qp *qp, struct rvt_swqe *wqe, bool *call_send) default: break; } + + /* + * System latency between send and schedule is large enough that + * forcing call_send to true for piothreshold packets is necessary. + */ + if (wqe->length <= piothreshold) + *call_send = true; return 0; } diff --git a/drivers/infiniband/hw/hfi1/verbs.c b/drivers/infiniband/hw/hfi1/verbs.c index 48e11e510358..a365089a9305 100644 --- a/drivers/infiniband/hw/hfi1/verbs.c +++ b/drivers/infiniband/hw/hfi1/verbs.c @@ -1479,7 +1479,7 @@ static const char * const driver_cntr_names[] = { static DEFINE_MUTEX(cntr_names_lock); /* protects the *_cntr_names bufers */ static const char **dev_cntr_names; static const char **port_cntr_names; -static int num_driver_cntrs = ARRAY_SIZE(driver_cntr_names); +int num_driver_cntrs = ARRAY_SIZE(driver_cntr_names); static int num_dev_cntrs; static int num_port_cntrs; static int cntr_names_initialized; diff --git a/drivers/infiniband/hw/mlx5/devx.c b/drivers/infiniband/hw/mlx5/devx.c index 61aab7c0c513..45c421c87100 100644 --- a/drivers/infiniband/hw/mlx5/devx.c +++ b/drivers/infiniband/hw/mlx5/devx.c @@ -1066,7 +1066,9 @@ static int devx_umem_get(struct mlx5_ib_dev *dev, struct ib_ucontext *ucontext, err = uverbs_get_flags32(&access, attrs, MLX5_IB_ATTR_DEVX_UMEM_REG_ACCESS, - IB_ACCESS_SUPPORTED); + IB_ACCESS_LOCAL_WRITE | + IB_ACCESS_REMOTE_WRITE | + IB_ACCESS_REMOTE_READ); if (err) return err; diff --git a/drivers/infiniband/hw/mlx5/odp.c b/drivers/infiniband/hw/mlx5/odp.c index 2cc3d69ab6f6..4dc6cc640ce0 100644 --- a/drivers/infiniband/hw/mlx5/odp.c +++ b/drivers/infiniband/hw/mlx5/odp.c @@ -506,14 +506,13 @@ void mlx5_ib_free_implicit_mr(struct mlx5_ib_mr *imr) static int pagefault_mr(struct mlx5_ib_dev *dev, struct mlx5_ib_mr *mr, u64 io_virt, size_t bcnt, u32 *bytes_mapped) { + int npages = 0, current_seq, page_shift, ret, np; + bool implicit = false; struct ib_umem_odp *odp_mr = to_ib_umem_odp(mr->umem); u64 access_mask = ODP_READ_ALLOWED_BIT; - int npages = 0, page_shift, np; u64 start_idx, page_mask; struct ib_umem_odp *odp; - int current_seq; size_t size; - int ret; if (!odp_mr->page_list) { odp = implicit_mr_get_data(mr, io_virt, bcnt); @@ -521,7 +520,7 @@ static int pagefault_mr(struct mlx5_ib_dev *dev, struct mlx5_ib_mr *mr, if (IS_ERR(odp)) return PTR_ERR(odp); mr = odp->private; - + implicit = true; } else { odp = odp_mr; } @@ -600,7 +599,7 @@ next_mr: out: if (ret == -EAGAIN) { - if (mr->parent || !odp->dying) { + if (implicit || !odp->dying) { unsigned long timeout = msecs_to_jiffies(MMU_NOTIFIER_TIMEOUT); diff --git a/drivers/md/dm-cache-metadata.c b/drivers/md/dm-cache-metadata.c index 5936de71883f..6fc93834da44 100644 --- a/drivers/md/dm-cache-metadata.c +++ b/drivers/md/dm-cache-metadata.c @@ -930,6 +930,10 @@ static int blocks_are_clean_separate_dirty(struct dm_cache_metadata *cmd, bool dirty_flag; *result = true; + if (from_cblock(cmd->cache_blocks) == 0) + /* Nothing to do */ + return 0; + r = dm_bitset_cursor_begin(&cmd->dirty_info, cmd->dirty_root, from_cblock(cmd->cache_blocks), &cmd->dirty_cursor); if (r) { diff --git a/drivers/md/dm-thin.c b/drivers/md/dm-thin.c index 0bd8d498b3b9..dadd9696340c 100644 --- a/drivers/md/dm-thin.c +++ b/drivers/md/dm-thin.c @@ -195,7 +195,7 @@ static void throttle_unlock(struct throttle *t) struct dm_thin_new_mapping; /* - * The pool runs in 4 modes. Ordered in degraded order for comparisons. + * The pool runs in various modes. Ordered in degraded order for comparisons. */ enum pool_mode { PM_WRITE, /* metadata may be changed */ @@ -282,9 +282,38 @@ struct pool { mempool_t mapping_pool; }; -static enum pool_mode get_pool_mode(struct pool *pool); static void metadata_operation_failed(struct pool *pool, const char *op, int r); +static enum pool_mode get_pool_mode(struct pool *pool) +{ + return pool->pf.mode; +} + +static void notify_of_pool_mode_change(struct pool *pool) +{ + const char *descs[] = { + "write", + "out-of-data-space", + "read-only", + "read-only", + "fail" + }; + const char *extra_desc = NULL; + enum pool_mode mode = get_pool_mode(pool); + + if (mode == PM_OUT_OF_DATA_SPACE) { + if (!pool->pf.error_if_no_space) + extra_desc = " (queue IO)"; + else + extra_desc = " (error IO)"; + } + + dm_table_event(pool->ti->table); + DMINFO("%s: switching pool to %s%s mode", + dm_device_name(pool->pool_md), + descs[(int)mode], extra_desc ? : ""); +} + /* * Target context for a pool. */ @@ -2351,8 +2380,6 @@ static void do_waker(struct work_struct *ws) queue_delayed_work(pool->wq, &pool->waker, COMMIT_PERIOD); } -static void notify_of_pool_mode_change_to_oods(struct pool *pool); - /* * We're holding onto IO to allow userland time to react. After the * timeout either the pool will have been resized (and thus back in @@ -2365,7 +2392,7 @@ static void do_no_space_timeout(struct work_struct *ws) if (get_pool_mode(pool) == PM_OUT_OF_DATA_SPACE && !pool->pf.error_if_no_space) { pool->pf.error_if_no_space = true; - notify_of_pool_mode_change_to_oods(pool); + notify_of_pool_mode_change(pool); error_retry_list_with_code(pool, BLK_STS_NOSPC); } } @@ -2433,26 +2460,6 @@ static void noflush_work(struct thin_c *tc, void (*fn)(struct work_struct *)) /*----------------------------------------------------------------*/ -static enum pool_mode get_pool_mode(struct pool *pool) -{ - return pool->pf.mode; -} - -static void notify_of_pool_mode_change(struct pool *pool, const char *new_mode) -{ - dm_table_event(pool->ti->table); - DMINFO("%s: switching pool to %s mode", - dm_device_name(pool->pool_md), new_mode); -} - -static void notify_of_pool_mode_change_to_oods(struct pool *pool) -{ - if (!pool->pf.error_if_no_space) - notify_of_pool_mode_change(pool, "out-of-data-space (queue IO)"); - else - notify_of_pool_mode_change(pool, "out-of-data-space (error IO)"); -} - static bool passdown_enabled(struct pool_c *pt) { return pt->adjusted_pf.discard_passdown; @@ -2501,8 +2508,6 @@ static void set_pool_mode(struct pool *pool, enum pool_mode new_mode) switch (new_mode) { case PM_FAIL: - if (old_mode != new_mode) - notify_of_pool_mode_change(pool, "failure"); dm_pool_metadata_read_only(pool->pmd); pool->process_bio = process_bio_fail; pool->process_discard = process_bio_fail; @@ -2516,8 +2521,6 @@ static void set_pool_mode(struct pool *pool, enum pool_mode new_mode) case PM_OUT_OF_METADATA_SPACE: case PM_READ_ONLY: - if (!is_read_only_pool_mode(old_mode)) - notify_of_pool_mode_change(pool, "read-only"); dm_pool_metadata_read_only(pool->pmd); pool->process_bio = process_bio_read_only; pool->process_discard = process_bio_success; @@ -2538,8 +2541,6 @@ static void set_pool_mode(struct pool *pool, enum pool_mode new_mode) * alarming rate. Adjust your low water mark if you're * frequently seeing this mode. */ - if (old_mode != new_mode) - notify_of_pool_mode_change_to_oods(pool); pool->out_of_data_space = true; pool->process_bio = process_bio_read_only; pool->process_discard = process_discard_bio; @@ -2552,8 +2553,6 @@ static void set_pool_mode(struct pool *pool, enum pool_mode new_mode) break; case PM_WRITE: - if (old_mode != new_mode) - notify_of_pool_mode_change(pool, "write"); if (old_mode == PM_OUT_OF_DATA_SPACE) cancel_delayed_work_sync(&pool->no_space_timeout); pool->out_of_data_space = false; @@ -2573,6 +2572,9 @@ static void set_pool_mode(struct pool *pool, enum pool_mode new_mode) * doesn't cause an unexpected mode transition on resume. */ pt->adjusted_pf.mode = new_mode; + + if (old_mode != new_mode) + notify_of_pool_mode_change(pool); } static void abort_transaction(struct pool *pool) @@ -4023,7 +4025,7 @@ static struct target_type pool_target = { .name = "thin-pool", .features = DM_TARGET_SINGLETON | DM_TARGET_ALWAYS_WRITEABLE | DM_TARGET_IMMUTABLE, - .version = {1, 20, 0}, + .version = {1, 21, 0}, .module = THIS_MODULE, .ctr = pool_ctr, .dtr = pool_dtr, @@ -4397,7 +4399,7 @@ static void thin_io_hints(struct dm_target *ti, struct queue_limits *limits) static struct target_type thin_target = { .name = "thin", - .version = {1, 20, 0}, + .version = {1, 21, 0}, .module = THIS_MODULE, .ctr = thin_ctr, .dtr = thin_dtr, diff --git a/drivers/md/dm-zoned-target.c b/drivers/md/dm-zoned-target.c index 981154e59461..6af5babe6837 100644 --- a/drivers/md/dm-zoned-target.c +++ b/drivers/md/dm-zoned-target.c @@ -20,7 +20,6 @@ struct dmz_bioctx { struct dm_zone *zone; struct bio *bio; refcount_t ref; - blk_status_t status; }; /* @@ -78,65 +77,66 @@ static inline void dmz_bio_endio(struct bio *bio, blk_status_t status) { struct dmz_bioctx *bioctx = dm_per_bio_data(bio, sizeof(struct dmz_bioctx)); - if (bioctx->status == BLK_STS_OK && status != BLK_STS_OK) - bioctx->status = status; - bio_endio(bio); + if (status != BLK_STS_OK && bio->bi_status == BLK_STS_OK) + bio->bi_status = status; + + if (refcount_dec_and_test(&bioctx->ref)) { + struct dm_zone *zone = bioctx->zone; + + if (zone) { + if (bio->bi_status != BLK_STS_OK && + bio_op(bio) == REQ_OP_WRITE && + dmz_is_seq(zone)) + set_bit(DMZ_SEQ_WRITE_ERR, &zone->flags); + dmz_deactivate_zone(zone); + } + bio_endio(bio); + } } /* - * Partial clone read BIO completion callback. This terminates the + * Completion callback for an internally cloned target BIO. This terminates the * target BIO when there are no more references to its context. */ -static void dmz_read_bio_end_io(struct bio *bio) +static void dmz_clone_endio(struct bio *clone) { - struct dmz_bioctx *bioctx = bio->bi_private; - blk_status_t status = bio->bi_status; + struct dmz_bioctx *bioctx = clone->bi_private; + blk_status_t status = clone->bi_status; - bio_put(bio); + bio_put(clone); dmz_bio_endio(bioctx->bio, status); } /* - * Issue a BIO to a zone. The BIO may only partially process the + * Issue a clone of a target BIO. The clone may only partially process the * original target BIO. */ -static int dmz_submit_read_bio(struct dmz_target *dmz, struct dm_zone *zone, - struct bio *bio, sector_t chunk_block, - unsigned int nr_blocks) +static int dmz_submit_bio(struct dmz_target *dmz, struct dm_zone *zone, + struct bio *bio, sector_t chunk_block, + unsigned int nr_blocks) { struct dmz_bioctx *bioctx = dm_per_bio_data(bio, sizeof(struct dmz_bioctx)); - sector_t sector; struct bio *clone; - /* BIO remap sector */ - sector = dmz_start_sect(dmz->metadata, zone) + dmz_blk2sect(chunk_block); - - /* If the read is not partial, there is no need to clone the BIO */ - if (nr_blocks == dmz_bio_blocks(bio)) { - /* Setup and submit the BIO */ - bio->bi_iter.bi_sector = sector; - refcount_inc(&bioctx->ref); - generic_make_request(bio); - return 0; - } - - /* Partial BIO: we need to clone the BIO */ clone = bio_clone_fast(bio, GFP_NOIO, &dmz->bio_set); if (!clone) return -ENOMEM; - /* Setup the clone */ - clone->bi_iter.bi_sector = sector; + bio_set_dev(clone, dmz->dev->bdev); + clone->bi_iter.bi_sector = + dmz_start_sect(dmz->metadata, zone) + dmz_blk2sect(chunk_block); clone->bi_iter.bi_size = dmz_blk2sect(nr_blocks) << SECTOR_SHIFT; - clone->bi_end_io = dmz_read_bio_end_io; + clone->bi_end_io = dmz_clone_endio; clone->bi_private = bioctx; bio_advance(bio, clone->bi_iter.bi_size); - /* Submit the clone */ refcount_inc(&bioctx->ref); generic_make_request(clone); + if (bio_op(bio) == REQ_OP_WRITE && dmz_is_seq(zone)) + zone->wp_block += nr_blocks; + return 0; } @@ -214,7 +214,7 @@ static int dmz_handle_read(struct dmz_target *dmz, struct dm_zone *zone, if (nr_blocks) { /* Valid blocks found: read them */ nr_blocks = min_t(unsigned int, nr_blocks, end_block - chunk_block); - ret = dmz_submit_read_bio(dmz, rzone, bio, chunk_block, nr_blocks); + ret = dmz_submit_bio(dmz, rzone, bio, chunk_block, nr_blocks); if (ret) return ret; chunk_block += nr_blocks; @@ -229,25 +229,6 @@ static int dmz_handle_read(struct dmz_target *dmz, struct dm_zone *zone, } /* - * Issue a write BIO to a zone. - */ -static void dmz_submit_write_bio(struct dmz_target *dmz, struct dm_zone *zone, - struct bio *bio, sector_t chunk_block, - unsigned int nr_blocks) -{ - struct dmz_bioctx *bioctx = dm_per_bio_data(bio, sizeof(struct dmz_bioctx)); - - /* Setup and submit the BIO */ - bio_set_dev(bio, dmz->dev->bdev); - bio->bi_iter.bi_sector = dmz_start_sect(dmz->metadata, zone) + dmz_blk2sect(chunk_block); - refcount_inc(&bioctx->ref); - generic_make_request(bio); - - if (dmz_is_seq(zone)) - zone->wp_block += nr_blocks; -} - -/* * Write blocks directly in a data zone, at the write pointer. * If a buffer zone is assigned, invalidate the blocks written * in place. @@ -265,7 +246,9 @@ static int dmz_handle_direct_write(struct dmz_target *dmz, return -EROFS; /* Submit write */ - dmz_submit_write_bio(dmz, zone, bio, chunk_block, nr_blocks); + ret = dmz_submit_bio(dmz, zone, bio, chunk_block, nr_blocks); + if (ret) + return ret; /* * Validate the blocks in the data zone and invalidate @@ -301,7 +284,9 @@ static int dmz_handle_buffered_write(struct dmz_target *dmz, return -EROFS; /* Submit write */ - dmz_submit_write_bio(dmz, bzone, bio, chunk_block, nr_blocks); + ret = dmz_submit_bio(dmz, bzone, bio, chunk_block, nr_blocks); + if (ret) + return ret; /* * Validate the blocks in the buffer zone @@ -600,7 +585,6 @@ static int dmz_map(struct dm_target *ti, struct bio *bio) bioctx->zone = NULL; bioctx->bio = bio; refcount_set(&bioctx->ref, 1); - bioctx->status = BLK_STS_OK; /* Set the BIO pending in the flush list */ if (!nr_sectors && bio_op(bio) == REQ_OP_WRITE) { @@ -624,35 +608,6 @@ static int dmz_map(struct dm_target *ti, struct bio *bio) } /* - * Completed target BIO processing. - */ -static int dmz_end_io(struct dm_target *ti, struct bio *bio, blk_status_t *error) -{ - struct dmz_bioctx *bioctx = dm_per_bio_data(bio, sizeof(struct dmz_bioctx)); - - if (bioctx->status == BLK_STS_OK && *error) - bioctx->status = *error; - - if (!refcount_dec_and_test(&bioctx->ref)) - return DM_ENDIO_INCOMPLETE; - - /* Done */ - bio->bi_status = bioctx->status; - - if (bioctx->zone) { - struct dm_zone *zone = bioctx->zone; - - if (*error && bio_op(bio) == REQ_OP_WRITE) { - if (dmz_is_seq(zone)) - set_bit(DMZ_SEQ_WRITE_ERR, &zone->flags); - } - dmz_deactivate_zone(zone); - } - - return DM_ENDIO_DONE; -} - -/* * Get zoned device information. */ static int dmz_get_zoned_device(struct dm_target *ti, char *path) @@ -946,7 +901,6 @@ static struct target_type dmz_type = { .ctr = dmz_ctr, .dtr = dmz_dtr, .map = dmz_map, - .end_io = dmz_end_io, .io_hints = dmz_io_hints, .prepare_ioctl = dmz_prepare_ioctl, .postsuspend = dmz_suspend, diff --git a/drivers/md/dm.c b/drivers/md/dm.c index c510179a7f84..63a7c416b224 100644 --- a/drivers/md/dm.c +++ b/drivers/md/dm.c @@ -1593,6 +1593,8 @@ static blk_qc_t __split_and_process_bio(struct mapped_device *md, return ret; } + blk_queue_split(md->queue, &bio); + init_clone_info(&ci, md, map, bio); if (bio->bi_opf & REQ_PREFLUSH) { diff --git a/drivers/media/Kconfig b/drivers/media/Kconfig index 8add62a18293..102eb35fcf3f 100644 --- a/drivers/media/Kconfig +++ b/drivers/media/Kconfig @@ -110,6 +110,19 @@ config MEDIA_CONTROLLER_DVB This is currently experimental. +config MEDIA_CONTROLLER_REQUEST_API + bool "Enable Media controller Request API (EXPERIMENTAL)" + depends on MEDIA_CONTROLLER && STAGING_MEDIA + default n + ---help--- + DO NOT ENABLE THIS OPTION UNLESS YOU KNOW WHAT YOU'RE DOING. + + This option enables the Request API for the Media controller and V4L2 + interfaces. It is currently needed by a few stateless codec drivers. + + There is currently no intention to provide API or ABI stability for + this new API as of yet. + # # Video4Linux support # Only enables if one of the V4L2 types (ATV, webcam, radio) is selected diff --git a/drivers/media/common/videobuf2/videobuf2-core.c b/drivers/media/common/videobuf2/videobuf2-core.c index 975ff5669f72..8ff8722cb6b1 100644 --- a/drivers/media/common/videobuf2/videobuf2-core.c +++ b/drivers/media/common/videobuf2/videobuf2-core.c @@ -947,7 +947,7 @@ void vb2_buffer_done(struct vb2_buffer *vb, enum vb2_buffer_state state) } atomic_dec(&q->owned_by_drv_count); - if (vb->req_obj.req) { + if (state != VB2_BUF_STATE_QUEUED && vb->req_obj.req) { /* This is not supported at the moment */ WARN_ON(state == VB2_BUF_STATE_REQUEUEING); media_request_object_unbind(&vb->req_obj); @@ -1359,8 +1359,12 @@ static void vb2_req_release(struct media_request_object *obj) { struct vb2_buffer *vb = container_of(obj, struct vb2_buffer, req_obj); - if (vb->state == VB2_BUF_STATE_IN_REQUEST) + if (vb->state == VB2_BUF_STATE_IN_REQUEST) { vb->state = VB2_BUF_STATE_DEQUEUED; + if (vb->request) + media_request_put(vb->request); + vb->request = NULL; + } } static const struct media_request_object_ops vb2_core_req_ops = { @@ -1528,6 +1532,18 @@ int vb2_core_qbuf(struct vb2_queue *q, unsigned int index, void *pb, return ret; vb->state = VB2_BUF_STATE_IN_REQUEST; + + /* + * Increment the refcount and store the request. + * The request refcount is decremented again when the + * buffer is dequeued. This is to prevent vb2_buffer_done() + * from freeing the request from interrupt context, which can + * happen if the application closed the request fd after + * queueing the request. + */ + media_request_get(req); + vb->request = req; + /* Fill buffer information for the userspace */ if (pb) { call_void_bufop(q, copy_timestamp, vb, pb); @@ -1749,10 +1765,6 @@ static void __vb2_dqbuf(struct vb2_buffer *vb) call_void_memop(vb, unmap_dmabuf, vb->planes[i].mem_priv); vb->planes[i].dbuf_mapped = 0; } - if (vb->req_obj.req) { - media_request_object_unbind(&vb->req_obj); - media_request_object_put(&vb->req_obj); - } call_void_bufop(q, init_buffer, vb); } @@ -1797,6 +1809,14 @@ int vb2_core_dqbuf(struct vb2_queue *q, unsigned int *pindex, void *pb, /* go back to dequeued state */ __vb2_dqbuf(vb); + if (WARN_ON(vb->req_obj.req)) { + media_request_object_unbind(&vb->req_obj); + media_request_object_put(&vb->req_obj); + } + if (vb->request) + media_request_put(vb->request); + vb->request = NULL; + dprintk(2, "dqbuf of buffer %d, with state %d\n", vb->index, vb->state); @@ -1903,6 +1923,14 @@ static void __vb2_queue_cancel(struct vb2_queue *q) vb->prepared = false; } __vb2_dqbuf(vb); + + if (vb->req_obj.req) { + media_request_object_unbind(&vb->req_obj); + media_request_object_put(&vb->req_obj); + } + if (vb->request) + media_request_put(vb->request); + vb->request = NULL; } } @@ -1940,10 +1968,8 @@ int vb2_core_streamon(struct vb2_queue *q, unsigned int type) if (ret) return ret; ret = vb2_start_streaming(q); - if (ret) { - __vb2_queue_cancel(q); + if (ret) return ret; - } } q->streaming = 1; diff --git a/drivers/media/common/videobuf2/videobuf2-v4l2.c b/drivers/media/common/videobuf2/videobuf2-v4l2.c index a17033ab2c22..1d35aeabfd85 100644 --- a/drivers/media/common/videobuf2/videobuf2-v4l2.c +++ b/drivers/media/common/videobuf2/videobuf2-v4l2.c @@ -333,10 +333,10 @@ static int vb2_fill_vb2_v4l2_buffer(struct vb2_buffer *vb, struct v4l2_buffer *b } static int vb2_queue_or_prepare_buf(struct vb2_queue *q, struct media_device *mdev, - struct v4l2_buffer *b, - const char *opname, + struct v4l2_buffer *b, bool is_prepare, struct media_request **p_req) { + const char *opname = is_prepare ? "prepare_buf" : "qbuf"; struct media_request *req; struct vb2_v4l2_buffer *vbuf; struct vb2_buffer *vb; @@ -378,6 +378,9 @@ static int vb2_queue_or_prepare_buf(struct vb2_queue *q, struct media_device *md return ret; } + if (is_prepare) + return 0; + if (!(b->flags & V4L2_BUF_FLAG_REQUEST_FD)) { if (q->uses_requests) { dprintk(1, "%s: queue uses requests\n", opname); @@ -631,8 +634,10 @@ static void fill_buf_caps(struct vb2_queue *q, u32 *caps) *caps |= V4L2_BUF_CAP_SUPPORTS_USERPTR; if (q->io_modes & VB2_DMABUF) *caps |= V4L2_BUF_CAP_SUPPORTS_DMABUF; +#ifdef CONFIG_MEDIA_CONTROLLER_REQUEST_API if (q->supports_requests) *caps |= V4L2_BUF_CAP_SUPPORTS_REQUESTS; +#endif } int vb2_reqbufs(struct vb2_queue *q, struct v4l2_requestbuffers *req) @@ -657,7 +662,7 @@ int vb2_prepare_buf(struct vb2_queue *q, struct media_device *mdev, if (b->flags & V4L2_BUF_FLAG_REQUEST_FD) return -EINVAL; - ret = vb2_queue_or_prepare_buf(q, mdev, b, "prepare_buf", NULL); + ret = vb2_queue_or_prepare_buf(q, mdev, b, true, NULL); return ret ? ret : vb2_core_prepare_buf(q, b->index, b); } @@ -729,7 +734,7 @@ int vb2_qbuf(struct vb2_queue *q, struct media_device *mdev, return -EBUSY; } - ret = vb2_queue_or_prepare_buf(q, mdev, b, "qbuf", &req); + ret = vb2_queue_or_prepare_buf(q, mdev, b, false, &req); if (ret) return ret; ret = vb2_core_qbuf(q, b->index, b, req); diff --git a/drivers/media/media-device.c b/drivers/media/media-device.c index bed24372e61f..b8ec88612df7 100644 --- a/drivers/media/media-device.c +++ b/drivers/media/media-device.c @@ -381,10 +381,14 @@ static long media_device_get_topology(struct media_device *mdev, void *arg) static long media_device_request_alloc(struct media_device *mdev, int *alloc_fd) { +#ifdef CONFIG_MEDIA_CONTROLLER_REQUEST_API if (!mdev->ops || !mdev->ops->req_validate || !mdev->ops->req_queue) return -ENOTTY; return media_request_alloc(mdev, alloc_fd); +#else + return -ENOTTY; +#endif } static long copy_arg_from_user(void *karg, void __user *uarg, unsigned int cmd) diff --git a/drivers/media/platform/vicodec/vicodec-core.c b/drivers/media/platform/vicodec/vicodec-core.c index 013cdebecbc4..13fb69c58967 100644 --- a/drivers/media/platform/vicodec/vicodec-core.c +++ b/drivers/media/platform/vicodec/vicodec-core.c @@ -997,11 +997,18 @@ static int vicodec_start_streaming(struct vb2_queue *q, q_data->sequence = 0; - if (!V4L2_TYPE_IS_OUTPUT(q->type)) + if (!V4L2_TYPE_IS_OUTPUT(q->type)) { + if (!ctx->is_enc) { + state->width = q_data->width; + state->height = q_data->height; + } return 0; + } - state->width = q_data->width; - state->height = q_data->height; + if (ctx->is_enc) { + state->width = q_data->width; + state->height = q_data->height; + } state->ref_frame.width = state->ref_frame.height = 0; state->ref_frame.luma = kvmalloc(size + 2 * size / chroma_div, GFP_KERNEL); diff --git a/drivers/media/platform/vivid/vivid-sdr-cap.c b/drivers/media/platform/vivid/vivid-sdr-cap.c index dcdc80e272c2..9acc709b0740 100644 --- a/drivers/media/platform/vivid/vivid-sdr-cap.c +++ b/drivers/media/platform/vivid/vivid-sdr-cap.c @@ -276,8 +276,6 @@ static int sdr_cap_start_streaming(struct vb2_queue *vq, unsigned count) list_for_each_entry_safe(buf, tmp, &dev->sdr_cap_active, list) { list_del(&buf->list); - v4l2_ctrl_request_complete(buf->vb.vb2_buf.req_obj.req, - &dev->ctrl_hdl_sdr_cap); vb2_buffer_done(&buf->vb.vb2_buf, VB2_BUF_STATE_QUEUED); } diff --git a/drivers/media/platform/vivid/vivid-vbi-cap.c b/drivers/media/platform/vivid/vivid-vbi-cap.c index 903cebeb5ce5..d666271bdaed 100644 --- a/drivers/media/platform/vivid/vivid-vbi-cap.c +++ b/drivers/media/platform/vivid/vivid-vbi-cap.c @@ -204,8 +204,6 @@ static int vbi_cap_start_streaming(struct vb2_queue *vq, unsigned count) list_for_each_entry_safe(buf, tmp, &dev->vbi_cap_active, list) { list_del(&buf->list); - v4l2_ctrl_request_complete(buf->vb.vb2_buf.req_obj.req, - &dev->ctrl_hdl_vbi_cap); vb2_buffer_done(&buf->vb.vb2_buf, VB2_BUF_STATE_QUEUED); } diff --git a/drivers/media/platform/vivid/vivid-vbi-out.c b/drivers/media/platform/vivid/vivid-vbi-out.c index 9357c07e30d6..cd56476902a2 100644 --- a/drivers/media/platform/vivid/vivid-vbi-out.c +++ b/drivers/media/platform/vivid/vivid-vbi-out.c @@ -96,8 +96,6 @@ static int vbi_out_start_streaming(struct vb2_queue *vq, unsigned count) list_for_each_entry_safe(buf, tmp, &dev->vbi_out_active, list) { list_del(&buf->list); - v4l2_ctrl_request_complete(buf->vb.vb2_buf.req_obj.req, - &dev->ctrl_hdl_vbi_out); vb2_buffer_done(&buf->vb.vb2_buf, VB2_BUF_STATE_QUEUED); } diff --git a/drivers/media/platform/vivid/vivid-vid-cap.c b/drivers/media/platform/vivid/vivid-vid-cap.c index 9c8e8be81ce3..673772cd17d6 100644 --- a/drivers/media/platform/vivid/vivid-vid-cap.c +++ b/drivers/media/platform/vivid/vivid-vid-cap.c @@ -243,8 +243,6 @@ static int vid_cap_start_streaming(struct vb2_queue *vq, unsigned count) list_for_each_entry_safe(buf, tmp, &dev->vid_cap_active, list) { list_del(&buf->list); - v4l2_ctrl_request_complete(buf->vb.vb2_buf.req_obj.req, - &dev->ctrl_hdl_vid_cap); vb2_buffer_done(&buf->vb.vb2_buf, VB2_BUF_STATE_QUEUED); } diff --git a/drivers/media/platform/vivid/vivid-vid-out.c b/drivers/media/platform/vivid/vivid-vid-out.c index aaf13f03d5d4..628eae154ee7 100644 --- a/drivers/media/platform/vivid/vivid-vid-out.c +++ b/drivers/media/platform/vivid/vivid-vid-out.c @@ -162,8 +162,6 @@ static int vid_out_start_streaming(struct vb2_queue *vq, unsigned count) list_for_each_entry_safe(buf, tmp, &dev->vid_out_active, list) { list_del(&buf->list); - v4l2_ctrl_request_complete(buf->vb.vb2_buf.req_obj.req, - &dev->ctrl_hdl_vid_out); vb2_buffer_done(&buf->vb.vb2_buf, VB2_BUF_STATE_QUEUED); } diff --git a/drivers/media/platform/vsp1/vsp1_lif.c b/drivers/media/platform/vsp1/vsp1_lif.c index 0b18f0bd7419..8b0a26335d70 100644 --- a/drivers/media/platform/vsp1/vsp1_lif.c +++ b/drivers/media/platform/vsp1/vsp1_lif.c @@ -95,7 +95,7 @@ static void lif_configure_stream(struct vsp1_entity *entity, format = vsp1_entity_get_pad_format(&lif->entity, lif->entity.config, LIF_PAD_SOURCE); - switch (entity->vsp1->version & VI6_IP_VERSION_SOC_MASK) { + switch (entity->vsp1->version & VI6_IP_VERSION_MODEL_MASK) { case VI6_IP_VERSION_MODEL_VSPD_GEN2: case VI6_IP_VERSION_MODEL_VSPD_V2H: hbth = 1536; diff --git a/drivers/media/v4l2-core/v4l2-ctrls.c b/drivers/media/v4l2-core/v4l2-ctrls.c index 5f2b033a7a42..10b8d94edbef 100644 --- a/drivers/media/v4l2-core/v4l2-ctrls.c +++ b/drivers/media/v4l2-core/v4l2-ctrls.c @@ -1563,7 +1563,7 @@ static int std_validate(const struct v4l2_ctrl *ctrl, u32 idx, u64 offset; s64 val; - switch (ctrl->type) { + switch ((u32)ctrl->type) { case V4L2_CTRL_TYPE_INTEGER: return ROUND_TO_RANGE(ptr.p_s32[idx], u32, ctrl); case V4L2_CTRL_TYPE_INTEGER64: @@ -2232,7 +2232,7 @@ static struct v4l2_ctrl *v4l2_ctrl_new(struct v4l2_ctrl_handler *hdl, is_array = nr_of_dims > 0; /* Prefill elem_size for all types handled by std_type_ops */ - switch (type) { + switch ((u32)type) { case V4L2_CTRL_TYPE_INTEGER64: elem_size = sizeof(s64); break; diff --git a/drivers/mmc/core/block.c b/drivers/mmc/core/block.c index c35b5b08bb33..111934838da2 100644 --- a/drivers/mmc/core/block.c +++ b/drivers/mmc/core/block.c @@ -472,7 +472,7 @@ out: static int __mmc_blk_ioctl_cmd(struct mmc_card *card, struct mmc_blk_data *md, struct mmc_blk_ioc_data *idata) { - struct mmc_command cmd = {}; + struct mmc_command cmd = {}, sbc = {}; struct mmc_data data = {}; struct mmc_request mrq = {}; struct scatterlist sg; @@ -550,10 +550,15 @@ static int __mmc_blk_ioctl_cmd(struct mmc_card *card, struct mmc_blk_data *md, } if (idata->rpmb) { - err = mmc_set_blockcount(card, data.blocks, - idata->ic.write_flag & (1 << 31)); - if (err) - return err; + sbc.opcode = MMC_SET_BLOCK_COUNT; + /* + * We don't do any blockcount validation because the max size + * may be increased by a future standard. We just copy the + * 'Reliable Write' bit here. + */ + sbc.arg = data.blocks | (idata->ic.write_flag & BIT(31)); + sbc.flags = MMC_RSP_R1 | MMC_CMD_AC; + mrq.sbc = &sbc; } if ((MMC_EXTRACT_INDEX_FROM_ARG(cmd.arg) == EXT_CSD_SANITIZE_START) && diff --git a/drivers/mmc/host/omap.c b/drivers/mmc/host/omap.c index adf32682f27a..c60a7625b1fa 100644 --- a/drivers/mmc/host/omap.c +++ b/drivers/mmc/host/omap.c @@ -104,6 +104,7 @@ struct mmc_omap_slot { unsigned int vdd; u16 saved_con; u16 bus_mode; + u16 power_mode; unsigned int fclk_freq; struct tasklet_struct cover_tasklet; @@ -1157,7 +1158,7 @@ static void mmc_omap_set_ios(struct mmc_host *mmc, struct mmc_ios *ios) struct mmc_omap_slot *slot = mmc_priv(mmc); struct mmc_omap_host *host = slot->host; int i, dsor; - int clk_enabled; + int clk_enabled, init_stream; mmc_omap_select_slot(slot, 0); @@ -1167,6 +1168,7 @@ static void mmc_omap_set_ios(struct mmc_host *mmc, struct mmc_ios *ios) slot->vdd = ios->vdd; clk_enabled = 0; + init_stream = 0; switch (ios->power_mode) { case MMC_POWER_OFF: mmc_omap_set_power(slot, 0, ios->vdd); @@ -1174,13 +1176,17 @@ static void mmc_omap_set_ios(struct mmc_host *mmc, struct mmc_ios *ios) case MMC_POWER_UP: /* Cannot touch dsor yet, just power up MMC */ mmc_omap_set_power(slot, 1, ios->vdd); + slot->power_mode = ios->power_mode; goto exit; case MMC_POWER_ON: mmc_omap_fclk_enable(host, 1); clk_enabled = 1; dsor |= 1 << 11; + if (slot->power_mode != MMC_POWER_ON) + init_stream = 1; break; } + slot->power_mode = ios->power_mode; if (slot->bus_mode != ios->bus_mode) { if (slot->pdata->set_bus_mode != NULL) @@ -1196,7 +1202,7 @@ static void mmc_omap_set_ios(struct mmc_host *mmc, struct mmc_ios *ios) for (i = 0; i < 2; i++) OMAP_MMC_WRITE(host, CON, dsor); slot->saved_con = dsor; - if (ios->power_mode == MMC_POWER_ON) { + if (init_stream) { /* worst case at 400kHz, 80 cycles makes 200 microsecs */ int usecs = 250; @@ -1234,6 +1240,7 @@ static int mmc_omap_new_slot(struct mmc_omap_host *host, int id) slot->host = host; slot->mmc = mmc; slot->id = id; + slot->power_mode = MMC_POWER_UNDEFINED; slot->pdata = &host->pdata->slots[id]; host->slots[id] = slot; diff --git a/drivers/mmc/host/sdhci-omap.c b/drivers/mmc/host/sdhci-omap.c index 88347ce78f23..d264391616f9 100644 --- a/drivers/mmc/host/sdhci-omap.c +++ b/drivers/mmc/host/sdhci-omap.c @@ -288,9 +288,9 @@ static int sdhci_omap_execute_tuning(struct mmc_host *mmc, u32 opcode) struct device *dev = omap_host->dev; struct mmc_ios *ios = &mmc->ios; u32 start_window = 0, max_window = 0; + bool dcrc_was_enabled = false; u8 cur_match, prev_match = 0; u32 length = 0, max_len = 0; - u32 ier = host->ier; u32 phase_delay = 0; int ret = 0; u32 reg; @@ -317,9 +317,10 @@ static int sdhci_omap_execute_tuning(struct mmc_host *mmc, u32 opcode) * during the tuning procedure. So disable it during the * tuning procedure. */ - ier &= ~SDHCI_INT_DATA_CRC; - sdhci_writel(host, ier, SDHCI_INT_ENABLE); - sdhci_writel(host, ier, SDHCI_SIGNAL_ENABLE); + if (host->ier & SDHCI_INT_DATA_CRC) { + host->ier &= ~SDHCI_INT_DATA_CRC; + dcrc_was_enabled = true; + } while (phase_delay <= MAX_PHASE_DELAY) { sdhci_omap_set_dll(omap_host, phase_delay); @@ -366,6 +367,9 @@ tuning_error: ret: sdhci_reset(host, SDHCI_RESET_CMD | SDHCI_RESET_DATA); + /* Reenable forbidden interrupt */ + if (dcrc_was_enabled) + host->ier |= SDHCI_INT_DATA_CRC; sdhci_writel(host, host->ier, SDHCI_INT_ENABLE); sdhci_writel(host, host->ier, SDHCI_SIGNAL_ENABLE); return ret; diff --git a/drivers/mmc/host/sdhci.c b/drivers/mmc/host/sdhci.c index 99bdae53fa2e..451b08a818a9 100644 --- a/drivers/mmc/host/sdhci.c +++ b/drivers/mmc/host/sdhci.c @@ -216,8 +216,12 @@ void sdhci_reset(struct sdhci_host *host, u8 mask) timeout = ktime_add_ms(ktime_get(), 100); /* hw clears the bit when it's done */ - while (sdhci_readb(host, SDHCI_SOFTWARE_RESET) & mask) { - if (ktime_after(ktime_get(), timeout)) { + while (1) { + bool timedout = ktime_after(ktime_get(), timeout); + + if (!(sdhci_readb(host, SDHCI_SOFTWARE_RESET) & mask)) + break; + if (timedout) { pr_err("%s: Reset 0x%x never completed.\n", mmc_hostname(host->mmc), (int)mask); sdhci_dumpregs(host); @@ -1608,9 +1612,13 @@ void sdhci_enable_clk(struct sdhci_host *host, u16 clk) /* Wait max 20 ms */ timeout = ktime_add_ms(ktime_get(), 20); - while (!((clk = sdhci_readw(host, SDHCI_CLOCK_CONTROL)) - & SDHCI_CLOCK_INT_STABLE)) { - if (ktime_after(ktime_get(), timeout)) { + while (1) { + bool timedout = ktime_after(ktime_get(), timeout); + + clk = sdhci_readw(host, SDHCI_CLOCK_CONTROL); + if (clk & SDHCI_CLOCK_INT_STABLE) + break; + if (timedout) { pr_err("%s: Internal clock never stabilised.\n", mmc_hostname(host->mmc)); sdhci_dumpregs(host); diff --git a/drivers/pinctrl/meson/pinctrl-meson.c b/drivers/pinctrl/meson/pinctrl-meson.c index 53d449076dee..ea87d739f534 100644 --- a/drivers/pinctrl/meson/pinctrl-meson.c +++ b/drivers/pinctrl/meson/pinctrl-meson.c @@ -191,7 +191,8 @@ static int meson_pinconf_set(struct pinctrl_dev *pcdev, unsigned int pin, case PIN_CONFIG_BIAS_DISABLE: dev_dbg(pc->dev, "pin %u: disable bias\n", pin); - meson_calc_reg_and_bit(bank, pin, REG_PULL, ®, &bit); + meson_calc_reg_and_bit(bank, pin, REG_PULLEN, ®, + &bit); ret = regmap_update_bits(pc->reg_pullen, reg, BIT(bit), 0); if (ret) diff --git a/drivers/pinctrl/qcom/pinctrl-sdm660.c b/drivers/pinctrl/qcom/pinctrl-sdm660.c index 6838b38555a1..1bfb0ae6b387 100644 --- a/drivers/pinctrl/qcom/pinctrl-sdm660.c +++ b/drivers/pinctrl/qcom/pinctrl-sdm660.c @@ -33,7 +33,7 @@ enum { } -#define PINGROUP(id, base, f1, f2, f3, f4, f5, f6, f7, f8, f9) \ +#define PINGROUP(id, _tile, f1, f2, f3, f4, f5, f6, f7, f8, f9) \ { \ .name = "gpio" #id, \ .pins = gpio##id##_pins, \ @@ -51,11 +51,12 @@ enum { msm_mux_##f9 \ }, \ .nfuncs = 10, \ - .ctl_reg = base + REG_SIZE * id, \ - .io_reg = base + 0x4 + REG_SIZE * id, \ - .intr_cfg_reg = base + 0x8 + REG_SIZE * id, \ - .intr_status_reg = base + 0xc + REG_SIZE * id, \ - .intr_target_reg = base + 0x8 + REG_SIZE * id, \ + .ctl_reg = REG_SIZE * id, \ + .io_reg = 0x4 + REG_SIZE * id, \ + .intr_cfg_reg = 0x8 + REG_SIZE * id, \ + .intr_status_reg = 0xc + REG_SIZE * id, \ + .intr_target_reg = 0x8 + REG_SIZE * id, \ + .tile = _tile, \ .mux_bit = 2, \ .pull_bit = 0, \ .drv_bit = 6, \ @@ -82,6 +83,7 @@ enum { .intr_cfg_reg = 0, \ .intr_status_reg = 0, \ .intr_target_reg = 0, \ + .tile = NORTH, \ .mux_bit = -1, \ .pull_bit = pull, \ .drv_bit = drv, \ @@ -1397,13 +1399,13 @@ static const struct msm_pingroup sdm660_groups[] = { PINGROUP(111, SOUTH, _, _, _, _, _, _, _, _, _), PINGROUP(112, SOUTH, _, _, _, _, _, _, _, _, _), PINGROUP(113, SOUTH, _, _, _, _, _, _, _, _, _), - SDC_QDSD_PINGROUP(sdc1_clk, 0x99a000, 13, 6), - SDC_QDSD_PINGROUP(sdc1_cmd, 0x99a000, 11, 3), - SDC_QDSD_PINGROUP(sdc1_data, 0x99a000, 9, 0), - SDC_QDSD_PINGROUP(sdc2_clk, 0x99b000, 14, 6), - SDC_QDSD_PINGROUP(sdc2_cmd, 0x99b000, 11, 3), - SDC_QDSD_PINGROUP(sdc2_data, 0x99b000, 9, 0), - SDC_QDSD_PINGROUP(sdc1_rclk, 0x99a000, 15, 0), + SDC_QDSD_PINGROUP(sdc1_clk, 0x9a000, 13, 6), + SDC_QDSD_PINGROUP(sdc1_cmd, 0x9a000, 11, 3), + SDC_QDSD_PINGROUP(sdc1_data, 0x9a000, 9, 0), + SDC_QDSD_PINGROUP(sdc2_clk, 0x9b000, 14, 6), + SDC_QDSD_PINGROUP(sdc2_cmd, 0x9b000, 11, 3), + SDC_QDSD_PINGROUP(sdc2_data, 0x9b000, 9, 0), + SDC_QDSD_PINGROUP(sdc1_rclk, 0x9a000, 15, 0), }; static const struct msm_pinctrl_soc_data sdm660_pinctrl = { diff --git a/drivers/pinctrl/sunxi/pinctrl-sun8i-a83t.c b/drivers/pinctrl/sunxi/pinctrl-sun8i-a83t.c index 6624499eae72..4ada80317a3b 100644 --- a/drivers/pinctrl/sunxi/pinctrl-sun8i-a83t.c +++ b/drivers/pinctrl/sunxi/pinctrl-sun8i-a83t.c @@ -568,7 +568,7 @@ static const struct sunxi_desc_pin sun8i_a83t_pins[] = { SUNXI_PIN(SUNXI_PINCTRL_PIN(H, 11), SUNXI_FUNCTION(0x0, "gpio_in"), SUNXI_FUNCTION(0x1, "gpio_out"), - SUNXI_FUNCTION_IRQ_BANK(0x6, 2, 1)), /* PH_EINT11 */ + SUNXI_FUNCTION_IRQ_BANK(0x6, 2, 11)), /* PH_EINT11 */ }; static const struct sunxi_pinctrl_desc sun8i_a83t_pinctrl_data = { diff --git a/drivers/staging/media/sunxi/cedrus/Kconfig b/drivers/staging/media/sunxi/cedrus/Kconfig index a7a34e89c42d..3252efa422f9 100644 --- a/drivers/staging/media/sunxi/cedrus/Kconfig +++ b/drivers/staging/media/sunxi/cedrus/Kconfig @@ -3,6 +3,7 @@ config VIDEO_SUNXI_CEDRUS depends on VIDEO_DEV && VIDEO_V4L2 && MEDIA_CONTROLLER depends on HAS_DMA depends on OF + depends on MEDIA_CONTROLLER_REQUEST_API select SUNXI_SRAM select VIDEOBUF2_DMA_CONTIG select V4L2_MEM2MEM_DEV diff --git a/drivers/staging/media/sunxi/cedrus/cedrus_hw.c b/drivers/staging/media/sunxi/cedrus/cedrus_hw.c index 32adbcbe6175..07520a2ce179 100644 --- a/drivers/staging/media/sunxi/cedrus/cedrus_hw.c +++ b/drivers/staging/media/sunxi/cedrus/cedrus_hw.c @@ -255,10 +255,10 @@ int cedrus_hw_probe(struct cedrus_dev *dev) res = platform_get_resource(dev->pdev, IORESOURCE_MEM, 0); dev->base = devm_ioremap_resource(dev->dev, res); - if (!dev->base) { + if (IS_ERR(dev->base)) { v4l2_err(&dev->v4l2_dev, "Failed to map registers\n"); - ret = -ENOMEM; + ret = PTR_ERR(dev->base); goto err_sram; } diff --git a/drivers/thermal/hisi_thermal.c b/drivers/thermal/hisi_thermal.c index c4111a98f1a7..2d26ae80e202 100644 --- a/drivers/thermal/hisi_thermal.c +++ b/drivers/thermal/hisi_thermal.c @@ -424,7 +424,7 @@ static int hi3660_thermal_probe(struct hisi_thermal_data *data) struct platform_device *pdev = data->pdev; struct device *dev = &pdev->dev; - data->nr_sensors = 2; + data->nr_sensors = 1; data->sensor = devm_kzalloc(dev, sizeof(*data->sensor) * data->nr_sensors, GFP_KERNEL); @@ -589,7 +589,7 @@ static int hisi_thermal_probe(struct platform_device *pdev) return ret; } - ret = platform_get_irq_byname(pdev, sensor->irq_name); + ret = platform_get_irq(pdev, 0); if (ret < 0) return ret; diff --git a/drivers/thermal/st/stm_thermal.c b/drivers/thermal/st/stm_thermal.c index 47623da0f91b..bbd73c5a4a4e 100644 --- a/drivers/thermal/st/stm_thermal.c +++ b/drivers/thermal/st/stm_thermal.c @@ -241,8 +241,8 @@ static int stm_thermal_read_factory_settings(struct stm_thermal_sensor *sensor) sensor->t0 = TS1_T0_VAL1; /* Retrieve fmt0 and put it on Hz */ - sensor->fmt0 = ADJUST * readl_relaxed(sensor->base + DTS_T0VALR1_OFFSET) - & TS1_FMT0_MASK; + sensor->fmt0 = ADJUST * (readl_relaxed(sensor->base + + DTS_T0VALR1_OFFSET) & TS1_FMT0_MASK); /* Retrieve ramp coefficient */ sensor->ramp_coeff = readl_relaxed(sensor->base + DTS_RAMPVALR_OFFSET) & @@ -532,6 +532,10 @@ static int stm_thermal_prepare(struct stm_thermal_sensor *sensor) if (ret) return ret; + ret = stm_thermal_read_factory_settings(sensor); + if (ret) + goto thermal_unprepare; + ret = stm_thermal_calibration(sensor); if (ret) goto thermal_unprepare; @@ -636,10 +640,6 @@ static int stm_thermal_probe(struct platform_device *pdev) /* Populate sensor */ sensor->base = base; - ret = stm_thermal_read_factory_settings(sensor); - if (ret) - return ret; - sensor->clk = devm_clk_get(&pdev->dev, "pclk"); if (IS_ERR(sensor->clk)) { dev_err(&pdev->dev, "%s: failed to fetch PCLK clock\n", diff --git a/drivers/video/backlight/pwm_bl.c b/drivers/video/backlight/pwm_bl.c index 678b27063198..f9ef0673a083 100644 --- a/drivers/video/backlight/pwm_bl.c +++ b/drivers/video/backlight/pwm_bl.c @@ -562,7 +562,30 @@ static int pwm_backlight_probe(struct platform_device *pdev) goto err_alloc; } - if (!data->levels) { + if (data->levels) { + /* + * For the DT case, only when brightness levels is defined + * data->levels is filled. For the non-DT case, data->levels + * can come from platform data, however is not usual. + */ + for (i = 0; i <= data->max_brightness; i++) { + if (data->levels[i] > pb->scale) + pb->scale = data->levels[i]; + + pb->levels = data->levels; + } + } else if (!data->max_brightness) { + /* + * If no brightness levels are provided and max_brightness is + * not set, use the default brightness table. For the DT case, + * max_brightness is set to 0 when brightness levels is not + * specified. For the non-DT case, max_brightness is usually + * set to some value. + */ + + /* Get the PWM period (in nanoseconds) */ + pwm_get_state(pb->pwm, &state); + ret = pwm_backlight_brightness_default(&pdev->dev, data, state.period); if (ret < 0) { @@ -570,13 +593,19 @@ static int pwm_backlight_probe(struct platform_device *pdev) "failed to setup default brightness table\n"); goto err_alloc; } - } - for (i = 0; i <= data->max_brightness; i++) { - if (data->levels[i] > pb->scale) - pb->scale = data->levels[i]; + for (i = 0; i <= data->max_brightness; i++) { + if (data->levels[i] > pb->scale) + pb->scale = data->levels[i]; - pb->levels = data->levels; + pb->levels = data->levels; + } + } else { + /* + * That only happens for the non-DT case, where platform data + * sets the max_brightness value. + */ + pb->scale = data->max_brightness; } pb->lth_brightness = data->lth_brightness * (state.period / pb->scale); |