diff options
Diffstat (limited to 'arch/arm/mm')
| -rw-r--r-- | arch/arm/mm/Kconfig | 17 | ||||
| -rw-r--r-- | arch/arm/mm/Makefile | 3 | ||||
| -rw-r--r-- | arch/arm/mm/cache-l2x0-pmu.c | 584 | ||||
| -rw-r--r-- | arch/arm/mm/cache-l2x0.c | 11 | ||||
| -rw-r--r-- | arch/arm/mm/cache-uniphier.c | 63 | ||||
| -rw-r--r-- | arch/arm/mm/cache-v7m.S | 453 | ||||
| -rw-r--r-- | arch/arm/mm/dma-mapping.c | 67 | ||||
| -rw-r--r-- | arch/arm/mm/mmu.c | 2 | ||||
| -rw-r--r-- | arch/arm/mm/proc-macros.S | 16 | ||||
| -rw-r--r-- | arch/arm/mm/proc-v7m.S | 108 |
10 files changed, 1241 insertions, 83 deletions
diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig index d15a7fe51618..c1799dd1d0d9 100644 --- a/arch/arm/mm/Kconfig +++ b/arch/arm/mm/Kconfig @@ -403,6 +403,7 @@ config CPU_V7M bool select CPU_32v7M select CPU_ABRT_NOMMU + select CPU_CACHE_V7M select CPU_CACHE_NOP select CPU_PABRT_LEGACY select CPU_THUMBONLY @@ -518,6 +519,9 @@ config CPU_CACHE_VIPT config CPU_CACHE_FA bool +config CPU_CACHE_V7M + bool + if MMU # The copy-page model config CPU_COPY_V4WT @@ -750,14 +754,14 @@ config CPU_HIGH_VECTOR config CPU_ICACHE_DISABLE bool "Disable I-Cache (I-bit)" - depends on CPU_CP15 && !(CPU_ARM720T || CPU_ARM740T || CPU_XSCALE || CPU_XSC3) + depends on (CPU_CP15 && !(CPU_ARM720T || CPU_ARM740T || CPU_XSCALE || CPU_XSC3)) || CPU_V7M help Say Y here to disable the processor instruction cache. Unless you have a reason not to or are unsure, say N. config CPU_DCACHE_DISABLE bool "Disable D-Cache (C-bit)" - depends on CPU_CP15 && !SMP + depends on (CPU_CP15 && !SMP) || CPU_V7M help Say Y here to disable the processor data cache. Unless you have a reason not to or are unsure, say N. @@ -792,7 +796,7 @@ config CPU_CACHE_ROUND_ROBIN config CPU_BPREDICT_DISABLE bool "Disable branch prediction" - depends on CPU_ARM1020 || CPU_V6 || CPU_V6K || CPU_MOHAWK || CPU_XSC3 || CPU_V7 || CPU_FA526 + depends on CPU_ARM1020 || CPU_V6 || CPU_V6K || CPU_MOHAWK || CPU_XSC3 || CPU_V7 || CPU_FA526 || CPU_V7M help Say Y here to disable branch prediction. If unsure, say N. @@ -916,6 +920,13 @@ config CACHE_L2X0 help This option enables the L2x0 PrimeCell. +config CACHE_L2X0_PMU + bool "L2x0 performance monitor support" if CACHE_L2X0 + depends on PERF_EVENTS + help + This option enables support for the performance monitoring features + of the L220 and PL310 outer cache controllers. + if CACHE_L2X0 config PL310_ERRATA_588369 diff --git a/arch/arm/mm/Makefile b/arch/arm/mm/Makefile index 7f76d96ce546..e8698241ece9 100644 --- a/arch/arm/mm/Makefile +++ b/arch/arm/mm/Makefile @@ -43,9 +43,11 @@ obj-$(CONFIG_CPU_CACHE_V6) += cache-v6.o obj-$(CONFIG_CPU_CACHE_V7) += cache-v7.o obj-$(CONFIG_CPU_CACHE_FA) += cache-fa.o obj-$(CONFIG_CPU_CACHE_NOP) += cache-nop.o +obj-$(CONFIG_CPU_CACHE_V7M) += cache-v7m.o AFLAGS_cache-v6.o :=-Wa,-march=armv6 AFLAGS_cache-v7.o :=-Wa,-march=armv7-a +AFLAGS_cache-v7m.o :=-Wa,-march=armv7-m obj-$(CONFIG_CPU_COPY_V4WT) += copypage-v4wt.o obj-$(CONFIG_CPU_COPY_V4WB) += copypage-v4wb.o @@ -101,6 +103,7 @@ AFLAGS_proc-v7.o :=-Wa,-march=armv7-a obj-$(CONFIG_OUTER_CACHE) += l2c-common.o obj-$(CONFIG_CACHE_FEROCEON_L2) += cache-feroceon-l2.o obj-$(CONFIG_CACHE_L2X0) += cache-l2x0.o l2c-l2x0-resume.o +obj-$(CONFIG_CACHE_L2X0_PMU) += cache-l2x0-pmu.o obj-$(CONFIG_CACHE_XSC3L2) += cache-xsc3l2.o obj-$(CONFIG_CACHE_TAUROS2) += cache-tauros2.o obj-$(CONFIG_CACHE_UNIPHIER) += cache-uniphier.o diff --git a/arch/arm/mm/cache-l2x0-pmu.c b/arch/arm/mm/cache-l2x0-pmu.c new file mode 100644 index 000000000000..976d3057272e --- /dev/null +++ b/arch/arm/mm/cache-l2x0-pmu.c @@ -0,0 +1,584 @@ +/* + * L220/L310 cache controller support + * + * Copyright (C) 2016 ARM Limited + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + */ +#include <linux/errno.h> +#include <linux/hrtimer.h> +#include <linux/io.h> +#include <linux/list.h> +#include <linux/perf_event.h> +#include <linux/printk.h> +#include <linux/slab.h> +#include <linux/types.h> + +#include <asm/hardware/cache-l2x0.h> + +#define PMU_NR_COUNTERS 2 + +static void __iomem *l2x0_base; +static struct pmu *l2x0_pmu; +static cpumask_t pmu_cpu; + +static const char *l2x0_name; + +static ktime_t l2x0_pmu_poll_period; +static struct hrtimer l2x0_pmu_hrtimer; + +/* + * The L220/PL310 PMU has two equivalent counters, Counter1 and Counter0. + * Registers controlling these are laid out in pairs, in descending order, i.e. + * the register for Counter1 comes first, followed by the register for + * Counter0. + * We ensure that idx 0 -> Counter0, and idx1 -> Counter1. + */ +static struct perf_event *events[PMU_NR_COUNTERS]; + +/* Find an unused counter */ +static int l2x0_pmu_find_idx(void) +{ + int i; + + for (i = 0; i < PMU_NR_COUNTERS; i++) { + if (!events[i]) + return i; + } + + return -1; +} + +/* How many counters are allocated? */ +static int l2x0_pmu_num_active_counters(void) +{ + int i, cnt = 0; + + for (i = 0; i < PMU_NR_COUNTERS; i++) { + if (events[i]) + cnt++; + } + + return cnt; +} + +static void l2x0_pmu_counter_config_write(int idx, u32 val) +{ + writel_relaxed(val, l2x0_base + L2X0_EVENT_CNT0_CFG - 4 * idx); +} + +static u32 l2x0_pmu_counter_read(int idx) +{ + return readl_relaxed(l2x0_base + L2X0_EVENT_CNT0_VAL - 4 * idx); +} + +static void l2x0_pmu_counter_write(int idx, u32 val) +{ + writel_relaxed(val, l2x0_base + L2X0_EVENT_CNT0_VAL - 4 * idx); +} + +static void __l2x0_pmu_enable(void) +{ + u32 val = readl_relaxed(l2x0_base + L2X0_EVENT_CNT_CTRL); + val |= L2X0_EVENT_CNT_CTRL_ENABLE; + writel_relaxed(val, l2x0_base + L2X0_EVENT_CNT_CTRL); +} + +static void __l2x0_pmu_disable(void) +{ + u32 val = readl_relaxed(l2x0_base + L2X0_EVENT_CNT_CTRL); + val &= ~L2X0_EVENT_CNT_CTRL_ENABLE; + writel_relaxed(val, l2x0_base + L2X0_EVENT_CNT_CTRL); +} + +static void l2x0_pmu_enable(struct pmu *pmu) +{ + if (l2x0_pmu_num_active_counters() == 0) + return; + + __l2x0_pmu_enable(); +} + +static void l2x0_pmu_disable(struct pmu *pmu) +{ + if (l2x0_pmu_num_active_counters() == 0) + return; + + __l2x0_pmu_disable(); +} + +static void warn_if_saturated(u32 count) +{ + if (count != 0xffffffff) + return; + + pr_warn_ratelimited("L2X0 counter saturated. Poll period too long\n"); +} + +static void l2x0_pmu_event_read(struct perf_event *event) +{ + struct hw_perf_event *hw = &event->hw; + u64 prev_count, new_count, mask; + + do { + prev_count = local64_read(&hw->prev_count); + new_count = l2x0_pmu_counter_read(hw->idx); + } while (local64_xchg(&hw->prev_count, new_count) != prev_count); + + mask = GENMASK_ULL(31, 0); + local64_add((new_count - prev_count) & mask, &event->count); + + warn_if_saturated(new_count); +} + +static void l2x0_pmu_event_configure(struct perf_event *event) +{ + struct hw_perf_event *hw = &event->hw; + + /* + * The L2X0 counters saturate at 0xffffffff rather than wrapping, so we + * will *always* lose some number of events when a counter saturates, + * and have no way of detecting how many were lost. + * + * To minimize the impact of this, we try to maximize the period by + * always starting counters at zero. To ensure that group ratios are + * representative, we poll periodically to avoid counters saturating. + * See l2x0_pmu_poll(). + */ + local64_set(&hw->prev_count, 0); + l2x0_pmu_counter_write(hw->idx, 0); +} + +static enum hrtimer_restart l2x0_pmu_poll(struct hrtimer *hrtimer) +{ + unsigned long flags; + int i; + + local_irq_save(flags); + __l2x0_pmu_disable(); + + for (i = 0; i < PMU_NR_COUNTERS; i++) { + struct perf_event *event = events[i]; + + if (!event) + continue; + + l2x0_pmu_event_read(event); + l2x0_pmu_event_configure(event); + } + + __l2x0_pmu_enable(); + local_irq_restore(flags); + + hrtimer_forward_now(hrtimer, l2x0_pmu_poll_period); + return HRTIMER_RESTART; +} + + +static void __l2x0_pmu_event_enable(int idx, u32 event) +{ + u32 val; + + val = event << L2X0_EVENT_CNT_CFG_SRC_SHIFT; + val |= L2X0_EVENT_CNT_CFG_INT_DISABLED; + l2x0_pmu_counter_config_write(idx, val); +} + +static void l2x0_pmu_event_start(struct perf_event *event, int flags) +{ + struct hw_perf_event *hw = &event->hw; + + if (WARN_ON_ONCE(!(event->hw.state & PERF_HES_STOPPED))) + return; + + if (flags & PERF_EF_RELOAD) { + WARN_ON_ONCE(!(hw->state & PERF_HES_UPTODATE)); + l2x0_pmu_event_configure(event); + } + + hw->state = 0; + + __l2x0_pmu_event_enable(hw->idx, hw->config_base); +} + +static void __l2x0_pmu_event_disable(int idx) +{ + u32 val; + + val = L2X0_EVENT_CNT_CFG_SRC_DISABLED << L2X0_EVENT_CNT_CFG_SRC_SHIFT; + val |= L2X0_EVENT_CNT_CFG_INT_DISABLED; + l2x0_pmu_counter_config_write(idx, val); +} + +static void l2x0_pmu_event_stop(struct perf_event *event, int flags) +{ + struct hw_perf_event *hw = &event->hw; + + if (WARN_ON_ONCE(event->hw.state & PERF_HES_STOPPED)) + return; + + __l2x0_pmu_event_disable(hw->idx); + + hw->state |= PERF_HES_STOPPED; + + if (flags & PERF_EF_UPDATE) { + l2x0_pmu_event_read(event); + hw->state |= PERF_HES_UPTODATE; + } +} + +static int l2x0_pmu_event_add(struct perf_event *event, int flags) +{ + struct hw_perf_event *hw = &event->hw; + int idx = l2x0_pmu_find_idx(); + + if (idx == -1) + return -EAGAIN; + + /* + * Pin the timer, so that the overflows are handled by the chosen + * event->cpu (this is the same one as presented in "cpumask" + * attribute). + */ + if (l2x0_pmu_num_active_counters() == 0) + hrtimer_start(&l2x0_pmu_hrtimer, l2x0_pmu_poll_period, + HRTIMER_MODE_REL_PINNED); + + events[idx] = event; + hw->idx = idx; + + l2x0_pmu_event_configure(event); + + hw->state = PERF_HES_STOPPED | PERF_HES_UPTODATE; + + if (flags & PERF_EF_START) + l2x0_pmu_event_start(event, 0); + + return 0; +} + +static void l2x0_pmu_event_del(struct perf_event *event, int flags) +{ + struct hw_perf_event *hw = &event->hw; + + l2x0_pmu_event_stop(event, PERF_EF_UPDATE); + + events[hw->idx] = NULL; + hw->idx = -1; + + if (l2x0_pmu_num_active_counters() == 0) + hrtimer_cancel(&l2x0_pmu_hrtimer); +} + +static bool l2x0_pmu_group_is_valid(struct perf_event *event) +{ + struct pmu *pmu = event->pmu; + struct perf_event *leader = event->group_leader; + struct perf_event *sibling; + int num_hw = 0; + + if (leader->pmu == pmu) + num_hw++; + else if (!is_software_event(leader)) + return false; + + list_for_each_entry(sibling, &leader->sibling_list, group_entry) { + if (sibling->pmu == pmu) + num_hw++; + else if (!is_software_event(sibling)) + return false; + } + + return num_hw <= PMU_NR_COUNTERS; +} + +static int l2x0_pmu_event_init(struct perf_event *event) +{ + struct hw_perf_event *hw = &event->hw; + + if (event->attr.type != l2x0_pmu->type) + return -ENOENT; + + if (is_sampling_event(event) || + event->attach_state & PERF_ATTACH_TASK) + return -EINVAL; + + if (event->attr.exclude_user || + event->attr.exclude_kernel || + event->attr.exclude_hv || + event->attr.exclude_idle || + event->attr.exclude_host || + event->attr.exclude_guest) + return -EINVAL; + + if (event->cpu < 0) + return -EINVAL; + + if (event->attr.config & ~L2X0_EVENT_CNT_CFG_SRC_MASK) + return -EINVAL; + + hw->config_base = event->attr.config; + + if (!l2x0_pmu_group_is_valid(event)) + return -EINVAL; + + event->cpu = cpumask_first(&pmu_cpu); + + return 0; +} + +struct l2x0_event_attribute { + struct device_attribute attr; + unsigned int config; + bool pl310_only; +}; + +#define L2X0_EVENT_ATTR(_name, _config, _pl310_only) \ + (&((struct l2x0_event_attribute[]) {{ \ + .attr = __ATTR(_name, S_IRUGO, l2x0_pmu_event_show, NULL), \ + .config = _config, \ + .pl310_only = _pl310_only, \ + }})[0].attr.attr) + +#define L220_PLUS_EVENT_ATTR(_name, _config) \ + L2X0_EVENT_ATTR(_name, _config, false) + +#define PL310_EVENT_ATTR(_name, _config) \ + L2X0_EVENT_ATTR(_name, _config, true) + +static ssize_t l2x0_pmu_event_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct l2x0_event_attribute *lattr; + + lattr = container_of(attr, typeof(*lattr), attr); + return snprintf(buf, PAGE_SIZE, "config=0x%x\n", lattr->config); +} + +static umode_t l2x0_pmu_event_attr_is_visible(struct kobject *kobj, + struct attribute *attr, + int unused) +{ + struct device *dev = kobj_to_dev(kobj); + struct pmu *pmu = dev_get_drvdata(dev); + struct l2x0_event_attribute *lattr; + + lattr = container_of(attr, typeof(*lattr), attr.attr); + + if (!lattr->pl310_only || strcmp("l2c_310", pmu->name) == 0) + return attr->mode; + + return 0; +} + +static struct attribute *l2x0_pmu_event_attrs[] = { + L220_PLUS_EVENT_ATTR(co, 0x1), + L220_PLUS_EVENT_ATTR(drhit, 0x2), + L220_PLUS_EVENT_ATTR(drreq, 0x3), + L220_PLUS_EVENT_ATTR(dwhit, 0x4), + L220_PLUS_EVENT_ATTR(dwreq, 0x5), + L220_PLUS_EVENT_ATTR(dwtreq, 0x6), + L220_PLUS_EVENT_ATTR(irhit, 0x7), + L220_PLUS_EVENT_ATTR(irreq, 0x8), + L220_PLUS_EVENT_ATTR(wa, 0x9), + PL310_EVENT_ATTR(ipfalloc, 0xa), + PL310_EVENT_ATTR(epfhit, 0xb), + PL310_EVENT_ATTR(epfalloc, 0xc), + PL310_EVENT_ATTR(srrcvd, 0xd), + PL310_EVENT_ATTR(srconf, 0xe), + PL310_EVENT_ATTR(epfrcvd, 0xf), + NULL +}; + +static struct attribute_group l2x0_pmu_event_attrs_group = { + .name = "events", + .attrs = l2x0_pmu_event_attrs, + .is_visible = l2x0_pmu_event_attr_is_visible, +}; + +static ssize_t l2x0_pmu_cpumask_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + return cpumap_print_to_pagebuf(true, buf, &pmu_cpu); +} + +static struct device_attribute l2x0_pmu_cpumask_attr = + __ATTR(cpumask, S_IRUGO, l2x0_pmu_cpumask_show, NULL); + +static struct attribute *l2x0_pmu_cpumask_attrs[] = { + &l2x0_pmu_cpumask_attr.attr, + NULL, +}; + +static struct attribute_group l2x0_pmu_cpumask_attr_group = { + .attrs = l2x0_pmu_cpumask_attrs, +}; + +static const struct attribute_group *l2x0_pmu_attr_groups[] = { + &l2x0_pmu_event_attrs_group, + &l2x0_pmu_cpumask_attr_group, + NULL, +}; + +static void l2x0_pmu_reset(void) +{ + int i; + + __l2x0_pmu_disable(); + + for (i = 0; i < PMU_NR_COUNTERS; i++) + __l2x0_pmu_event_disable(i); +} + +static int l2x0_pmu_offline_cpu(unsigned int cpu) +{ + unsigned int target; + + if (!cpumask_test_and_clear_cpu(cpu, &pmu_cpu)) + return 0; + + target = cpumask_any_but(cpu_online_mask, cpu); + if (target >= nr_cpu_ids) + return 0; + + perf_pmu_migrate_context(l2x0_pmu, cpu, target); + cpumask_set_cpu(target, &pmu_cpu); + + return 0; +} + +void l2x0_pmu_suspend(void) +{ + int i; + + if (!l2x0_pmu) + return; + + l2x0_pmu_disable(l2x0_pmu); + + for (i = 0; i < PMU_NR_COUNTERS; i++) { + if (events[i]) + l2x0_pmu_event_stop(events[i], PERF_EF_UPDATE); + } + +} + +void l2x0_pmu_resume(void) +{ + int i; + + if (!l2x0_pmu) + return; + + l2x0_pmu_reset(); + + for (i = 0; i < PMU_NR_COUNTERS; i++) { + if (events[i]) + l2x0_pmu_event_start(events[i], PERF_EF_RELOAD); + } + + l2x0_pmu_enable(l2x0_pmu); +} + +void __init l2x0_pmu_register(void __iomem *base, u32 part) +{ + /* + * Determine whether we support the PMU, and choose the name for sysfs. + * This is also used by l2x0_pmu_event_attr_is_visible to determine + * which events to display, as the PL310 PMU supports a superset of + * L220 events. + * + * The L210 PMU has a different programmer's interface, and is not + * supported by this driver. + * + * We must defer registering the PMU until the perf subsystem is up and + * running, so just stash the name and base, and leave that to another + * initcall. + */ + switch (part & L2X0_CACHE_ID_PART_MASK) { + case L2X0_CACHE_ID_PART_L220: + l2x0_name = "l2c_220"; + break; + case L2X0_CACHE_ID_PART_L310: + l2x0_name = "l2c_310"; + break; + default: + return; + } + + l2x0_base = base; +} + +static __init int l2x0_pmu_init(void) +{ + int ret; + + if (!l2x0_base) + return 0; + + l2x0_pmu = kzalloc(sizeof(*l2x0_pmu), GFP_KERNEL); + if (!l2x0_pmu) { + pr_warn("Unable to allocate L2x0 PMU\n"); + return -ENOMEM; + } + + *l2x0_pmu = (struct pmu) { + .task_ctx_nr = perf_invalid_context, + .pmu_enable = l2x0_pmu_enable, + .pmu_disable = l2x0_pmu_disable, + .read = l2x0_pmu_event_read, + .start = l2x0_pmu_event_start, + .stop = l2x0_pmu_event_stop, + .add = l2x0_pmu_event_add, + .del = l2x0_pmu_event_del, + .event_init = l2x0_pmu_event_init, + .attr_groups = l2x0_pmu_attr_groups, + }; + + l2x0_pmu_reset(); + + /* + * We always use a hrtimer rather than an interrupt. + * See comments in l2x0_pmu_event_configure and l2x0_pmu_poll. + * + * Polling once a second allows the counters to fill up to 1/128th on a + * quad-core test chip with cores clocked at 400MHz. Hopefully this + * leaves sufficient headroom to avoid overflow on production silicon + * at higher frequencies. + */ + l2x0_pmu_poll_period = ms_to_ktime(1000); + hrtimer_init(&l2x0_pmu_hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); + l2x0_pmu_hrtimer.function = l2x0_pmu_poll; + + cpumask_set_cpu(0, &pmu_cpu); + ret = cpuhp_setup_state_nocalls(CPUHP_AP_PERF_ARM_L2X0_ONLINE, + "AP_PERF_ARM_L2X0_ONLINE", NULL, + l2x0_pmu_offline_cpu); + if (ret) + goto out_pmu; + + ret = perf_pmu_register(l2x0_pmu, l2x0_name, -1); + if (ret) + goto out_cpuhp; + + return 0; + +out_cpuhp: + cpuhp_remove_state_nocalls(CPUHP_AP_PERF_ARM_L2X0_ONLINE); +out_pmu: + kfree(l2x0_pmu); + l2x0_pmu = NULL; + return ret; +} +device_initcall(l2x0_pmu_init); diff --git a/arch/arm/mm/cache-l2x0.c b/arch/arm/mm/cache-l2x0.c index cc12905ae6f8..d1870c777c6e 100644 --- a/arch/arm/mm/cache-l2x0.c +++ b/arch/arm/mm/cache-l2x0.c @@ -142,6 +142,8 @@ static void l2c_disable(void) { void __iomem *base = l2x0_base; + l2x0_pmu_suspend(); + outer_cache.flush_all(); l2c_write_sec(0, base, L2X0_CTRL); dsb(st); @@ -159,6 +161,8 @@ static void l2c_resume(void) /* Do not touch the controller if already enabled. */ if (!(readl_relaxed(base + L2X0_CTRL) & L2X0_CTRL_EN)) l2c_enable(base, l2x0_data->num_lock); + + l2x0_pmu_resume(); } /* @@ -709,9 +713,8 @@ static void __init l2c310_fixup(void __iomem *base, u32 cache_id, if (revision >= L310_CACHE_ID_RTL_R3P0 && revision < L310_CACHE_ID_RTL_R3P2) { u32 val = l2x0_saved_regs.prefetch_ctrl; - /* I don't think bit23 is required here... but iMX6 does so */ - if (val & (BIT(30) | BIT(23))) { - val &= ~(BIT(30) | BIT(23)); + if (val & L310_PREFETCH_CTRL_DBL_LINEFILL) { + val &= ~L310_PREFETCH_CTRL_DBL_LINEFILL; l2x0_saved_regs.prefetch_ctrl = val; errata[n++] = "752271"; } @@ -892,6 +895,8 @@ static int __init __l2c_init(const struct l2c_init_data *data, pr_info("%s: CACHE_ID 0x%08x, AUX_CTRL 0x%08x\n", data->type, cache_id, aux); + l2x0_pmu_register(l2x0_base, cache_id); + return 0; } diff --git a/arch/arm/mm/cache-uniphier.c b/arch/arm/mm/cache-uniphier.c index c8e2f4947223..dfe97b409916 100644 --- a/arch/arm/mm/cache-uniphier.c +++ b/arch/arm/mm/cache-uniphier.c @@ -1,5 +1,6 @@ /* - * Copyright (C) 2015 Masahiro Yamada <yamada.masahiro@socionext.com> + * Copyright (C) 2015-2016 Socionext Inc. + * Author: Masahiro Yamada <yamada.masahiro@socionext.com> * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by @@ -43,27 +44,15 @@ #define UNIPHIER_SSCOPE_CM_SYNC 0x8 /* sync (drain bufs) */ #define UNIPHIER_SSCOPE_CM_FLUSH_PREFETCH 0x9 /* flush p-fetch buf */ #define UNIPHIER_SSCOQM 0x248 /* Cache Operation Queue Mode */ -#define UNIPHIER_SSCOQM_TID_MASK (0x3 << 21) -#define UNIPHIER_SSCOQM_TID_LRU_DATA (0x0 << 21) -#define UNIPHIER_SSCOQM_TID_LRU_INST (0x1 << 21) -#define UNIPHIER_SSCOQM_TID_WAY (0x2 << 21) #define UNIPHIER_SSCOQM_S_MASK (0x3 << 17) #define UNIPHIER_SSCOQM_S_RANGE (0x0 << 17) #define UNIPHIER_SSCOQM_S_ALL (0x1 << 17) -#define UNIPHIER_SSCOQM_S_WAY (0x2 << 17) #define UNIPHIER_SSCOQM_CE BIT(15) /* notify completion */ #define UNIPHIER_SSCOQM_CM_INV 0x0 /* invalidate */ #define UNIPHIER_SSCOQM_CM_CLEAN 0x1 /* clean */ #define UNIPHIER_SSCOQM_CM_FLUSH 0x2 /* flush */ -#define UNIPHIER_SSCOQM_CM_PREFETCH 0x3 /* prefetch to cache */ -#define UNIPHIER_SSCOQM_CM_PREFETCH_BUF 0x4 /* prefetch to pf-buf */ -#define UNIPHIER_SSCOQM_CM_TOUCH 0x5 /* touch */ -#define UNIPHIER_SSCOQM_CM_TOUCH_ZERO 0x6 /* touch to zero */ -#define UNIPHIER_SSCOQM_CM_TOUCH_DIRTY 0x7 /* touch with dirty */ #define UNIPHIER_SSCOQAD 0x24c /* Cache Operation Queue Address */ #define UNIPHIER_SSCOQSZ 0x250 /* Cache Operation Queue Size */ -#define UNIPHIER_SSCOQMASK 0x254 /* Cache Operation Queue Address Mask */ -#define UNIPHIER_SSCOQWN 0x258 /* Cache Operation Queue Way Number */ #define UNIPHIER_SSCOPPQSEF 0x25c /* Cache Operation Queue Set Complete*/ #define UNIPHIER_SSCOPPQSEF_FE BIT(1) #define UNIPHIER_SSCOPPQSEF_OE BIT(0) @@ -72,9 +61,6 @@ #define UNIPHIER_SSCOLPQS_EST BIT(1) #define UNIPHIER_SSCOLPQS_QST BIT(0) -/* Is the touch/pre-fetch destination specified by ways? */ -#define UNIPHIER_SSCOQM_TID_IS_WAY(op) \ - ((op & UNIPHIER_SSCOQM_TID_MASK) == UNIPHIER_SSCOQM_TID_WAY) /* Is the operation region specified by address range? */ #define UNIPHIER_SSCOQM_S_IS_RANGE(op) \ ((op & UNIPHIER_SSCOQM_S_MASK) == UNIPHIER_SSCOQM_S_RANGE) @@ -178,11 +164,6 @@ static void __uniphier_cache_maint_common(struct uniphier_cache_data *data, writel_relaxed(start, data->op_base + UNIPHIER_SSCOQAD); writel_relaxed(size, data->op_base + UNIPHIER_SSCOQSZ); } - - /* set target ways if needed */ - if (unlikely(UNIPHIER_SSCOQM_TID_IS_WAY(operation))) - writel_relaxed(data->way_locked_mask, - data->op_base + UNIPHIER_SSCOQWN); } while (unlikely(readl_relaxed(data->op_base + UNIPHIER_SSCOPPQSEF) & (UNIPHIER_SSCOPPQSEF_FE | UNIPHIER_SSCOPPQSEF_OE))); @@ -338,46 +319,8 @@ static void uniphier_cache_sync(void) __uniphier_cache_sync(data); } -int __init uniphier_cache_l2_is_enabled(void) -{ - struct uniphier_cache_data *data; - - data = list_first_entry_or_null(&uniphier_cache_list, - struct uniphier_cache_data, list); - if (!data) - return 0; - - return !!(readl_relaxed(data->ctrl_base + UNIPHIER_SSCC) & - UNIPHIER_SSCC_ON); -} - -void __init uniphier_cache_l2_touch_range(unsigned long start, - unsigned long end) -{ - struct uniphier_cache_data *data; - - data = list_first_entry_or_null(&uniphier_cache_list, - struct uniphier_cache_data, list); - if (data) - __uniphier_cache_maint_range(data, start, end, - UNIPHIER_SSCOQM_TID_WAY | - UNIPHIER_SSCOQM_CM_TOUCH); -} - -void __init uniphier_cache_l2_set_locked_ways(u32 way_mask) -{ - struct uniphier_cache_data *data; - - data = list_first_entry_or_null(&uniphier_cache_list, - struct uniphier_cache_data, list); - if (data) - __uniphier_cache_set_locked_ways(data, way_mask); -} - static const struct of_device_id uniphier_cache_match[] __initconst = { - { - .compatible = "socionext,uniphier-system-cache", - }, + { .compatible = "socionext,uniphier-system-cache" }, { /* sentinel */ } }; diff --git a/arch/arm/mm/cache-v7m.S b/arch/arm/mm/cache-v7m.S new file mode 100644 index 000000000000..816a7e44e6f1 --- /dev/null +++ b/arch/arm/mm/cache-v7m.S @@ -0,0 +1,453 @@ +/* + * linux/arch/arm/mm/cache-v7m.S + * + * Based on linux/arch/arm/mm/cache-v7.S + * + * Copyright (C) 2001 Deep Blue Solutions Ltd. + * Copyright (C) 2005 ARM Ltd. + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * This is the "shell" of the ARMv7M processor support. + */ +#include <linux/linkage.h> +#include <linux/init.h> +#include <asm/assembler.h> +#include <asm/errno.h> +#include <asm/unwind.h> +#include <asm/v7m.h> + +#include "proc-macros.S" + +/* Generic V7M read/write macros for memory mapped cache operations */ +.macro v7m_cache_read, rt, reg + movw \rt, #:lower16:BASEADDR_V7M_SCB + \reg + movt \rt, #:upper16:BASEADDR_V7M_SCB + \reg + ldr \rt, [\rt] +.endm + +.macro v7m_cacheop, rt, tmp, op, c = al + movw\c \tmp, #:lower16:BASEADDR_V7M_SCB + \op + movt\c \tmp, #:upper16:BASEADDR_V7M_SCB + \op + str\c \rt, [\tmp] +.endm + + +.macro read_ccsidr, rt + v7m_cache_read \rt, V7M_SCB_CCSIDR +.endm + +.macro read_clidr, rt + v7m_cache_read \rt, V7M_SCB_CLIDR +.endm + +.macro write_csselr, rt, tmp + v7m_cacheop \rt, \tmp, V7M_SCB_CSSELR +.endm + +/* + * dcisw: Invalidate data cache by set/way + */ +.macro dcisw, rt, tmp + v7m_cacheop \rt, \tmp, V7M_SCB_DCISW +.endm + +/* + * dccisw: Clean and invalidate data cache by set/way + */ +.macro dccisw, rt, tmp + v7m_cacheop \rt, \tmp, V7M_SCB_DCCISW +.endm + +/* + * dccimvac: Clean and invalidate data cache line by MVA to PoC. + */ +.irp c,,eq,ne,cs,cc,mi,pl,vs,vc,hi,ls,ge,lt,gt,le,hs,lo +.macro dccimvac\c, rt, tmp + v7m_cacheop \rt, \tmp, V7M_SCB_DCCIMVAC, \c +.endm +.endr + +/* + * dcimvac: Invalidate data cache line by MVA to PoC + */ +.macro dcimvac, rt, tmp + v7m_cacheop \rt, \tmp, V7M_SCB_DCIMVAC +.endm + +/* + * dccmvau: Clean data cache line by MVA to PoU + */ +.macro dccmvau, rt, tmp + v7m_cacheop \rt, \tmp, V7M_SCB_DCCMVAU +.endm + +/* + * dccmvac: Clean data cache line by MVA to PoC + */ +.macro dccmvac, rt, tmp + v7m_cacheop \rt, \tmp, V7M_SCB_DCCMVAC +.endm + +/* + * icimvau: Invalidate instruction caches by MVA to PoU + */ +.macro icimvau, rt, tmp + v7m_cacheop \rt, \tmp, V7M_SCB_ICIMVAU +.endm + +/* + * Invalidate the icache, inner shareable if SMP, invalidate BTB for UP. + * rt data ignored by ICIALLU(IS), so can be used for the address + */ +.macro invalidate_icache, rt + v7m_cacheop \rt, \rt, V7M_SCB_ICIALLU + mov \rt, #0 +.endm + +/* + * Invalidate the BTB, inner shareable if SMP. + * rt data ignored by BPIALL, so it can be used for the address + */ +.macro invalidate_bp, rt + v7m_cacheop \rt, \rt, V7M_SCB_BPIALL + mov \rt, #0 +.endm + +ENTRY(v7m_invalidate_l1) + mov r0, #0 + + write_csselr r0, r1 + read_ccsidr r0 + + movw r1, #0x7fff + and r2, r1, r0, lsr #13 + + movw r1, #0x3ff + + and r3, r1, r0, lsr #3 @ NumWays - 1 + add r2, r2, #1 @ NumSets + + and r0, r0, #0x7 + add r0, r0, #4 @ SetShift + + clz r1, r3 @ WayShift + add r4, r3, #1 @ NumWays +1: sub r2, r2, #1 @ NumSets-- + mov r3, r4 @ Temp = NumWays +2: subs r3, r3, #1 @ Temp-- + mov r5, r3, lsl r1 + mov r6, r2, lsl r0 + orr r5, r5, r6 @ Reg = (Temp<<WayShift)|(NumSets<<SetShift) + dcisw r5, r6 + bgt 2b + cmp r2, #0 + bgt 1b + dsb st + isb + ret lr +ENDPROC(v7m_invalidate_l1) + +/* + * v7m_flush_icache_all() + * + * Flush the whole I-cache. + * + * Registers: + * r0 - set to 0 + */ +ENTRY(v7m_flush_icache_all) + invalidate_icache r0 + ret lr +ENDPROC(v7m_flush_icache_all) + +/* + * v7m_flush_dcache_all() + * + * Flush the whole D-cache. + * + * Corrupted registers: r0-r7, r9-r11 + */ +ENTRY(v7m_flush_dcache_all) + dmb @ ensure ordering with previous memory accesses + read_clidr r0 + mov r3, r0, lsr #23 @ move LoC into position + ands r3, r3, #7 << 1 @ extract LoC*2 from clidr + beq finished @ if loc is 0, then no need to clean +start_flush_levels: + mov r10, #0 @ start clean at cache level 0 +flush_levels: + add r2, r10, r10, lsr #1 @ work out 3x current cache level + mov r1, r0, lsr r2 @ extract cache type bits from clidr + and r1, r1, #7 @ mask of the bits for current cache only + cmp r1, #2 @ see what cache we have at this level + blt skip @ skip if no cache, or just i-cache +#ifdef CONFIG_PREEMPT + save_and_disable_irqs_notrace r9 @ make cssr&csidr read atomic +#endif + write_csselr r10, r1 @ set current cache level + isb @ isb to sych the new cssr&csidr + read_ccsidr r1 @ read the new csidr +#ifdef CONFIG_PREEMPT + restore_irqs_notrace r9 +#endif + and r2, r1, #7 @ extract the length of the cache lines + add r2, r2, #4 @ add 4 (line length offset) + movw r4, #0x3ff + ands r4, r4, r1, lsr #3 @ find maximum number on the way size + clz r5, r4 @ find bit position of way size increment + movw r7, #0x7fff + ands r7, r7, r1, lsr #13 @ extract max number of the index size +loop1: + mov r9, r7 @ create working copy of max index +loop2: + lsl r6, r4, r5 + orr r11, r10, r6 @ factor way and cache number into r11 + lsl r6, r9, r2 + orr r11, r11, r6 @ factor index number into r11 + dccisw r11, r6 @ clean/invalidate by set/way + subs r9, r9, #1 @ decrement the index + bge loop2 + subs r4, r4, #1 @ decrement the way + bge loop1 +skip: + add r10, r10, #2 @ increment cache number + cmp r3, r10 + bgt flush_levels +finished: + mov r10, #0 @ swith back to cache level 0 + write_csselr r10, r3 @ select current cache level in cssr + dsb st + isb + ret lr +ENDPROC(v7m_flush_dcache_all) + +/* + * v7m_flush_cache_all() + * + * Flush the entire cache system. + * The data cache flush is now achieved using atomic clean / invalidates + * working outwards from L1 cache. This is done using Set/Way based cache + * maintenance instructions. + * The instruction cache can still be invalidated back to the point of + * unification in a single instruction. + * + */ +ENTRY(v7m_flush_kern_cache_all) + stmfd sp!, {r4-r7, r9-r11, lr} + bl v7m_flush_dcache_all + invalidate_icache r0 + ldmfd sp!, {r4-r7, r9-r11, lr} + ret lr +ENDPROC(v7m_flush_kern_cache_all) + +/* + * v7m_flush_cache_all() + * + * Flush all TLB entries in a particular address space + * + * - mm - mm_struct describing address space + */ +ENTRY(v7m_flush_user_cache_all) + /*FALLTHROUGH*/ + +/* + * v7m_flush_cache_range(start, end, flags) + * + * Flush a range of TLB entries in the specified address space. + * + * - start - start address (may not be aligned) + * - end - end address (exclusive, may not be aligned) + * - flags - vm_area_struct flags describing address space + * + * It is assumed that: + * - we have a VIPT cache. + */ +ENTRY(v7m_flush_user_cache_range) + ret lr +ENDPROC(v7m_flush_user_cache_all) +ENDPROC(v7m_flush_user_cache_range) + +/* + * v7m_coherent_kern_range(start,end) + * + * Ensure that the I and D caches are coherent within specified + * region. This is typically used when code has been written to + * a memory region, and will be executed. + * + * - start - virtual start address of region + * - end - virtual end address of region + * + * It is assumed that: + * - the Icache does not read data from the write buffer + */ +ENTRY(v7m_coherent_kern_range) + /* FALLTHROUGH */ + +/* + * v7m_coherent_user_range(start,end) + * + * Ensure that the I and D caches are coherent within specified + * region. This is typically used when code has been written to + * a memory region, and will be executed. + * + * - start - virtual start address of region + * - end - virtual end address of region + * + * It is assumed that: + * - the Icache does not read data from the write buffer + */ +ENTRY(v7m_coherent_user_range) + UNWIND(.fnstart ) + dcache_line_size r2, r3 + sub r3, r2, #1 + bic r12, r0, r3 +1: +/* + * We use open coded version of dccmvau otherwise USER() would + * point at movw instruction. + */ + dccmvau r12, r3 + add r12, r12, r2 + cmp r12, r1 + blo 1b + dsb ishst + icache_line_size r2, r3 + sub r3, r2, #1 + bic r12, r0, r3 +2: + icimvau r12, r3 + add r12, r12, r2 + cmp r12, r1 + blo 2b + invalidate_bp r0 + dsb ishst + isb + ret lr + UNWIND(.fnend ) +ENDPROC(v7m_coherent_kern_range) +ENDPROC(v7m_coherent_user_range) + +/* + * v7m_flush_kern_dcache_area(void *addr, size_t size) + * + * Ensure that the data held in the page kaddr is written back + * to the page in question. + * + * - addr - kernel address + * - size - region size + */ +ENTRY(v7m_flush_kern_dcache_area) + dcache_line_size r2, r3 + add r1, r0, r1 + sub r3, r2, #1 + bic r0, r0, r3 +1: + dccimvac r0, r3 @ clean & invalidate D line / unified line + add r0, r0, r2 + cmp r0, r1 + blo 1b + dsb st + ret lr +ENDPROC(v7m_flush_kern_dcache_area) + +/* + * v7m_dma_inv_range(start,end) + * + * Invalidate the data cache within the specified region; we will + * be performing a DMA operation in this region and we want to + * purge old data in the cache. + * + * - start - virtual start address of region + * - end - virtual end address of region + */ +v7m_dma_inv_range: + dcache_line_size r2, r3 + sub r3, r2, #1 + tst r0, r3 + bic r0, r0, r3 + dccimvacne r0, r3 + subne r3, r2, #1 @ restore r3, corrupted by v7m's dccimvac + tst r1, r3 + bic r1, r1, r3 + dccimvacne r1, r3 +1: + dcimvac r0, r3 + add r0, r0, r2 + cmp r0, r1 + blo 1b + dsb st + ret lr +ENDPROC(v7m_dma_inv_range) + +/* + * v7m_dma_clean_range(start,end) + * - start - virtual start address of region + * - end - virtual end address of region + */ +v7m_dma_clean_range: + dcache_line_size r2, r3 + sub r3, r2, #1 + bic r0, r0, r3 +1: + dccmvac r0, r3 @ clean D / U line + add r0, r0, r2 + cmp r0, r1 + blo 1b + dsb st + ret lr +ENDPROC(v7m_dma_clean_range) + +/* + * v7m_dma_flush_range(start,end) + * - start - virtual start address of region + * - end - virtual end address of region + */ +ENTRY(v7m_dma_flush_range) + dcache_line_size r2, r3 + sub r3, r2, #1 + bic r0, r0, r3 +1: + dccimvac r0, r3 @ clean & invalidate D / U line + add r0, r0, r2 + cmp r0, r1 + blo 1b + dsb st + ret lr +ENDPROC(v7m_dma_flush_range) + +/* + * dma_map_area(start, size, dir) + * - start - kernel virtual start address + * - size - size of region + * - dir - DMA direction + */ +ENTRY(v7m_dma_map_area) + add r1, r1, r0 + teq r2, #DMA_FROM_DEVICE + beq v7m_dma_inv_range + b v7m_dma_clean_range +ENDPROC(v7m_dma_map_area) + +/* + * dma_unmap_area(start, size, dir) + * - start - kernel virtual start address + * - size - size of region + * - dir - DMA direction + */ +ENTRY(v7m_dma_unmap_area) + add r1, r1, r0 + teq r2, #DMA_TO_DEVICE + bne v7m_dma_inv_range + ret lr +ENDPROC(v7m_dma_unmap_area) + + .globl v7m_flush_kern_cache_louis + .equ v7m_flush_kern_cache_louis, v7m_flush_kern_cache_all + + __INITDATA + + @ define struct cpu_cache_fns (see <asm/cacheflush.h> and proc-macros.S) + define_cache_functions v7m diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c index c6834c0cfd1c..ab4f74536057 100644 --- a/arch/arm/mm/dma-mapping.c +++ b/arch/arm/mm/dma-mapping.c @@ -436,7 +436,7 @@ static int __init atomic_pool_init(void) gen_pool_set_algo(atomic_pool, gen_pool_first_fit_order_align, (void *)PAGE_SHIFT); - pr_info("DMA: preallocated %zd KiB pool for atomic coherent allocations\n", + pr_info("DMA: preallocated %zu KiB pool for atomic coherent allocations\n", atomic_pool_size / 1024); return 0; } @@ -445,7 +445,7 @@ destroy_genpool: gen_pool_destroy(atomic_pool); atomic_pool = NULL; out: - pr_err("DMA: failed to allocate %zx KiB pool for atomic coherent allocation\n", + pr_err("DMA: failed to allocate %zu KiB pool for atomic coherent allocation\n", atomic_pool_size / 1024); return -ENOMEM; } @@ -2014,6 +2014,63 @@ static void arm_iommu_unmap_page(struct device *dev, dma_addr_t handle, __free_iova(mapping, iova, len); } +/** + * arm_iommu_map_resource - map a device resource for DMA + * @dev: valid struct device pointer + * @phys_addr: physical address of resource + * @size: size of resource to map + * @dir: DMA transfer direction + */ +static dma_addr_t arm_iommu_map_resource(struct device *dev, + phys_addr_t phys_addr, size_t size, + enum dma_data_direction dir, unsigned long attrs) +{ + struct dma_iommu_mapping *mapping = to_dma_iommu_mapping(dev); + dma_addr_t dma_addr; + int ret, prot; + phys_addr_t addr = phys_addr & PAGE_MASK; + unsigned int offset = phys_addr & ~PAGE_MASK; + size_t len = PAGE_ALIGN(size + offset); + + dma_addr = __alloc_iova(mapping, len); + if (dma_addr == DMA_ERROR_CODE) + return dma_addr; + + prot = __dma_direction_to_prot(dir) | IOMMU_MMIO; + + ret = iommu_map(mapping->domain, dma_addr, addr, len, prot); + if (ret < 0) + goto fail; + + return dma_addr + offset; +fail: + __free_iova(mapping, dma_addr, len); + return DMA_ERROR_CODE; +} + +/** + * arm_iommu_unmap_resource - unmap a device DMA resource + * @dev: valid struct device pointer + * @dma_handle: DMA address to resource + * @size: size of resource to map + * @dir: DMA transfer direction + */ +static void arm_iommu_unmap_resource(struct device *dev, dma_addr_t dma_handle, + size_t size, enum dma_data_direction dir, + unsigned long attrs) +{ + struct dma_iommu_mapping *mapping = to_dma_iommu_mapping(dev); + dma_addr_t iova = dma_handle & PAGE_MASK; + unsigned int offset = dma_handle & ~PAGE_MASK; + size_t len = PAGE_ALIGN(size + offset); + + if (!iova) + return; + + iommu_unmap(mapping->domain, iova, len); + __free_iova(mapping, iova, len); +} + static void arm_iommu_sync_single_for_cpu(struct device *dev, dma_addr_t handle, size_t size, enum dma_data_direction dir) { @@ -2057,6 +2114,9 @@ struct dma_map_ops iommu_ops = { .unmap_sg = arm_iommu_unmap_sg, .sync_sg_for_cpu = arm_iommu_sync_sg_for_cpu, .sync_sg_for_device = arm_iommu_sync_sg_for_device, + + .map_resource = arm_iommu_map_resource, + .unmap_resource = arm_iommu_unmap_resource, }; struct dma_map_ops iommu_coherent_ops = { @@ -2070,6 +2130,9 @@ struct dma_map_ops iommu_coherent_ops = { .map_sg = arm_coherent_iommu_map_sg, .unmap_sg = arm_coherent_iommu_unmap_sg, + + .map_resource = arm_iommu_map_resource, + .unmap_resource = arm_iommu_unmap_resource, }; /** diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c index 30fe03f95c85..4001dd15818d 100644 --- a/arch/arm/mm/mmu.c +++ b/arch/arm/mm/mmu.c @@ -243,7 +243,7 @@ __setup("noalign", noalign_setup); #define PROT_PTE_S2_DEVICE PROT_PTE_DEVICE #define PROT_SECT_DEVICE PMD_TYPE_SECT|PMD_SECT_AP_WRITE -static struct mem_type mem_types[] = { +static struct mem_type mem_types[] __ro_after_init = { [MT_DEVICE] = { /* Strongly ordered / ARMv6 shared device */ .prot_pte = PROT_PTE_DEVICE | L_PTE_MT_DEV_SHARED | L_PTE_SHARED, diff --git a/arch/arm/mm/proc-macros.S b/arch/arm/mm/proc-macros.S index c671f345266a..0d40c285bd86 100644 --- a/arch/arm/mm/proc-macros.S +++ b/arch/arm/mm/proc-macros.S @@ -7,6 +7,10 @@ #include <asm/asm-offsets.h> #include <asm/thread_info.h> +#ifdef CONFIG_CPU_V7M +#include <asm/v7m.h> +#endif + /* * vma_vm_mm - get mm pointer from vma pointer (vma->vm_mm) */ @@ -70,7 +74,13 @@ * on ARMv7. */ .macro dcache_line_size, reg, tmp +#ifdef CONFIG_CPU_V7M + movw \tmp, #:lower16:BASEADDR_V7M_SCB + V7M_SCB_CTR + movt \tmp, #:upper16:BASEADDR_V7M_SCB + V7M_SCB_CTR + ldr \tmp, [\tmp] +#else mrc p15, 0, \tmp, c0, c0, 1 @ read ctr +#endif lsr \tmp, \tmp, #16 and \tmp, \tmp, #0xf @ cache line size encoding mov \reg, #4 @ bytes per word @@ -82,7 +92,13 @@ * on ARMv7. */ .macro icache_line_size, reg, tmp +#ifdef CONFIG_CPU_V7M + movw \tmp, #:lower16:BASEADDR_V7M_SCB + V7M_SCB_CTR + movt \tmp, #:upper16:BASEADDR_V7M_SCB + V7M_SCB_CTR + ldr \tmp, [\tmp] +#else mrc p15, 0, \tmp, c0, c0, 1 @ read ctr +#endif and \tmp, \tmp, #0xf @ cache line size encoding mov \reg, #4 @ bytes per word mov \reg, \reg, lsl \tmp @ actual cache line size diff --git a/arch/arm/mm/proc-v7m.S b/arch/arm/mm/proc-v7m.S index 7229d8d0be1a..f6d333f09bfe 100644 --- a/arch/arm/mm/proc-v7m.S +++ b/arch/arm/mm/proc-v7m.S @@ -74,14 +74,42 @@ ENTRY(cpu_v7m_do_resume) ENDPROC(cpu_v7m_do_resume) #endif +ENTRY(cpu_cm7_dcache_clean_area) + dcache_line_size r2, r3 + movw r3, #:lower16:BASEADDR_V7M_SCB + V7M_SCB_DCCMVAC + movt r3, #:upper16:BASEADDR_V7M_SCB + V7M_SCB_DCCMVAC + +1: str r0, [r3] @ clean D entry + add r0, r0, r2 + subs r1, r1, r2 + bhi 1b + dsb + ret lr +ENDPROC(cpu_cm7_dcache_clean_area) + +ENTRY(cpu_cm7_proc_fin) + movw r2, #:lower16:(BASEADDR_V7M_SCB + V7M_SCB_CCR) + movt r2, #:upper16:(BASEADDR_V7M_SCB + V7M_SCB_CCR) + ldr r0, [r2] + bic r0, r0, #(V7M_SCB_CCR_DC | V7M_SCB_CCR_IC) + str r0, [r2] + ret lr +ENDPROC(cpu_cm7_proc_fin) + .section ".text.init", #alloc, #execinstr +__v7m_cm7_setup: + mov r8, #(V7M_SCB_CCR_DC | V7M_SCB_CCR_IC| V7M_SCB_CCR_BP) + b __v7m_setup_cont /* * __v7m_setup * * This should be able to cover all ARMv7-M cores. */ __v7m_setup: + mov r8, 0 + +__v7m_setup_cont: @ Configure the vector table base address ldr r0, =BASEADDR_V7M_SCB ldr r12, =vector_table @@ -104,6 +132,7 @@ __v7m_setup: badr r1, 1f ldr r5, [r12, #11 * 4] @ read the SVC vector entry str r1, [r12, #11 * 4] @ write the temporary SVC vector entry + dsb mov r6, lr @ save LR ldr sp, =init_thread_union + THREAD_START_SP cpsie i @@ -116,15 +145,32 @@ __v7m_setup: mov r1, #1 msr control, r1 @ Thread mode has unpriviledged access + @ Configure caches (if implemented) + teq r8, #0 + stmneia r12, {r0-r6, lr} @ v7m_invalidate_l1 touches r0-r6 + blne v7m_invalidate_l1 + teq r8, #0 @ re-evalutae condition + ldmneia r12, {r0-r6, lr} + @ Configure the System Control Register to ensure 8-byte stack alignment @ Note the STKALIGN bit is either RW or RAO. - ldr r12, [r0, V7M_SCB_CCR] @ system control register - orr r12, #V7M_SCB_CCR_STKALIGN - str r12, [r0, V7M_SCB_CCR] + ldr r0, [r0, V7M_SCB_CCR] @ system control register + orr r0, #V7M_SCB_CCR_STKALIGN + orr r0, r0, r8 + ret lr ENDPROC(__v7m_setup) +/* + * Cortex-M7 processor functions + */ + globl_equ cpu_cm7_proc_init, cpu_v7m_proc_init + globl_equ cpu_cm7_reset, cpu_v7m_reset + globl_equ cpu_cm7_do_idle, cpu_v7m_do_idle + globl_equ cpu_cm7_switch_mm, cpu_v7m_switch_mm + define_processor_functions v7m, dabort=nommu_early_abort, pabort=legacy_pabort, nommu=1 + define_processor_functions cm7, dabort=nommu_early_abort, pabort=legacy_pabort, nommu=1 .section ".rodata" string cpu_arch_name, "armv7m" @@ -133,6 +179,50 @@ ENDPROC(__v7m_setup) .section ".proc.info.init", #alloc +.macro __v7m_proc name, initfunc, cache_fns = nop_cache_fns, hwcaps = 0, proc_fns = v7m_processor_functions + .long 0 /* proc_info_list.__cpu_mm_mmu_flags */ + .long 0 /* proc_info_list.__cpu_io_mmu_flags */ + initfn \initfunc, \name + .long cpu_arch_name + .long cpu_elf_name + .long HWCAP_HALF | HWCAP_THUMB | HWCAP_FAST_MULT | \hwcaps + .long cpu_v7m_name + .long \proc_fns + .long 0 /* proc_info_list.tlb */ + .long 0 /* proc_info_list.user */ + .long \cache_fns +.endm + + /* + * Match ARM Cortex-M7 processor. + */ + .type __v7m_cm7_proc_info, #object +__v7m_cm7_proc_info: + .long 0x410fc270 /* ARM Cortex-M7 0xC27 */ + .long 0xff0ffff0 /* Mask off revision, patch release */ + __v7m_proc __v7m_cm7_proc_info, __v7m_cm7_setup, hwcaps = HWCAP_EDSP, cache_fns = v7m_cache_fns, proc_fns = cm7_processor_functions + .size __v7m_cm7_proc_info, . - __v7m_cm7_proc_info + + /* + * Match ARM Cortex-M4 processor. + */ + .type __v7m_cm4_proc_info, #object +__v7m_cm4_proc_info: + .long 0x410fc240 /* ARM Cortex-M4 0xC24 */ + .long 0xff0ffff0 /* Mask off revision, patch release */ + __v7m_proc __v7m_cm4_proc_info, __v7m_setup, hwcaps = HWCAP_EDSP + .size __v7m_cm4_proc_info, . - __v7m_cm4_proc_info + + /* + * Match ARM Cortex-M3 processor. + */ + .type __v7m_cm3_proc_info, #object +__v7m_cm3_proc_info: + .long 0x410fc230 /* ARM Cortex-M3 0xC23 */ + .long 0xff0ffff0 /* Mask off revision, patch release */ + __v7m_proc __v7m_cm3_proc_info, __v7m_setup + .size __v7m_cm3_proc_info, . - __v7m_cm3_proc_info + /* * Match any ARMv7-M processor core. */ @@ -140,16 +230,6 @@ ENDPROC(__v7m_setup) __v7m_proc_info: .long 0x000f0000 @ Required ID value .long 0x000f0000 @ Mask for ID - .long 0 @ proc_info_list.__cpu_mm_mmu_flags - .long 0 @ proc_info_list.__cpu_io_mmu_flags - initfn __v7m_setup, __v7m_proc_info @ proc_info_list.__cpu_flush - .long cpu_arch_name - .long cpu_elf_name - .long HWCAP_HALF|HWCAP_THUMB|HWCAP_FAST_MULT - .long cpu_v7m_name - .long v7m_processor_functions @ proc_info_list.proc - .long 0 @ proc_info_list.tlb - .long 0 @ proc_info_list.user - .long nop_cache_fns @ proc_info_list.cache + __v7m_proc __v7m_proc_info, __v7m_setup .size __v7m_proc_info, . - __v7m_proc_info |