/* * arch/arm/mm/cache-l2x0.c - L210/L220 cache controller support * * Copyright (C) 2007 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 #include #include #include #include #include #include #include #include "cache-aurora-l2.h" #define CACHE_LINE_SIZE 32 static void __iomem *l2x0_base; static DEFINE_RAW_SPINLOCK(l2x0_lock); static u32 l2x0_way_mask; /* Bitmask of active ways */ static u32 l2x0_size; static unsigned long sync_reg_offset = L2X0_CACHE_SYNC; /* Aurora don't have the cache ID register available, so we have to * pass it though the device tree */ static u32 cache_id_part_number_from_dt; struct l2x0_regs l2x0_saved_regs; struct l2x0_of_data { void (*setup)(const struct device_node *, u32 *, u32 *); void (*save)(void); struct outer_cache_fns outer_cache; }; static bool of_init = false; static inline void cache_wait_way(void __iomem *reg, unsigned long mask) { /* wait for cache operation by line or way to complete */ while (readl_relaxed(reg) & mask) cpu_relax(); } #ifdef CONFIG_CACHE_PL310 static inline void cache_wait(void __iomem *reg, unsigned long mask) { /* cache operations by line are atomic on PL310 */ } #else #define cache_wait cache_wait_way #endif static inline void cache_sync(void) { void __iomem *base = l2x0_base; writel_relaxed(0, base + sync_reg_offset); cache_wait(base + L2X0_CACHE_SYNC, 1); } static inline void l2x0_clean_line(unsigned long addr) { void __iomem *base = l2x0_base; cache_wait(base + L2X0_CLEAN_LINE_PA, 1); writel_relaxed(addr, base + L2X0_CLEAN_LINE_PA); } static inline void l2x0_inv_line(unsigned long addr) { void __iomem *base = l2x0_base; cache_wait(base + L2X0_INV_LINE_PA, 1); writel_relaxed(addr, base + L2X0_INV_LINE_PA); } #if defined(CONFIG_PL310_ERRATA_588369) || defined(CONFIG_PL310_ERRATA_727915) static inline void debug_writel(unsigned long val) { if (outer_cache.set_debug) outer_cache.set_debug(val); } static void pl310_set_debug(unsigned long val) { writel_relaxed(val, l2x0_base + L2X0_DEBUG_CTRL); } #else /* Optimised out for non-errata case */ static inline void debug_writel(unsigned long val) { } #define pl310_set_debug NULL #endif #ifdef CONFIG_PL310_ERRATA_588369 static inline void l2x0_flush_line(unsigned long addr) { void __iomem *base = l2x0_base; /* Clean by PA followed by Invalidate by PA */ cache_wait(base + L2X0_CLEAN_LINE_PA, 1); writel_relaxed(addr, base + L2X0_CLEAN_LINE_PA); cache_wait(base + L2X0_INV_LINE_PA, 1); writel_relaxed(addr, base + L2X0_INV_LINE_PA); } #else static inline void l2x0_flush_line(unsigned long addr) { void __iomem *base = l2x0_base; cache_wait(base + L2X0_CLEAN_INV_LINE_PA, 1); writel_relaxed(addr, base + L2X0_CLEAN_INV_LINE_PA); } #endif static void l2x0_cache_sync(void) { unsigned long flags; raw_spin_lock_irqsave(&l2x0_lock, flags); cache_sync(); raw_spin_unlock_irqrestore(&l2x0_lock, flags); } static void __l2x0_flush_all(void) { debug_writel(0x03); writel_relaxed(l2x0_way_mask, l2x0_base + L2X0_CLEAN_INV_WAY); cache_wait_way(l2x0_base + L2X0_CLEAN_INV_WAY, l2x0_way_mask); cache_sync(); debug_writel(0x00); } static void l2x0_flush_all(void) { unsigned long flags; /* clean all ways */ raw_spin_lock_irqsave(&l2x0_lock, flags); __l2x0_flush_all(); raw_spin_unlock_irqrestore(&l2x0_lock, flags); } static void l2x0_clean_all(void) { unsigned long flags; /* clean all ways */ raw_spin_lock_irqsave(&l2x0_lock, flags); writel_relaxed(l2x0_way_mask, l2x0_base + L2X0_CLEAN_WAY); cache_wait_way(l2x0_base + L2X0_CLEAN_WAY, l2x0_way_mask); cache_sync(); raw_spin_unlock_irqrestore(&l2x0_lock, flags); } static void l2x0_inv_all(void) { unsigned long flags; /* invalidate all ways */ raw_spin_lock_irqsave(&l2x0_lock, flags); /* Invalidating when L2 is enabled is a nono */ BUG_ON(readl(l2x0_base + L2X0_CTRL) & L2X0_CTRL_EN); writel_relaxed(l2x0_way_mask, l2x0_base + L2X0_INV_WAY); cache_wait_way(l2x0_base + L2X0_INV_WAY, l2x0_way_mask); cache_sync(); raw_spin_unlock_irqrestore(&l2x0_lock, flags); } static void l2x0_inv_range(unsigned long start, unsigned long end) { void __iomem *base = l2x0_base; unsigned long flags; raw_spin_lock_irqsave(&l2x0_lock, flags); if (start & (CACHE_LINE_SIZE - 1)) { start &= ~(CACHE_LINE_SIZE - 1); debug_writel(0x03); l2x0_flush_line(start); debug_writel(0x00); start += CACHE_LINE_SIZE; } if (end & (CACHE_LINE_SIZE - 1)) { end &= ~(CACHE_LINE_SIZE - 1); debug_writel(0x03); l2x0_flush_line(end); debug_writel(0x00); } while (start < end) { unsigned long blk_end = start + min(end - start, 4096UL); while (start < blk_end) { l2x0_inv_line(start); start += CACHE_LINE_SIZE; } if (blk_end < end) { raw_spin_unlock_irqrestore(&l2x0_lock, flags); raw_spin_lock_irqsave(&l2x0_lock, flags); } } cache_wait(base + L2X0_INV_LINE_PA, 1); cache_sync(); raw_spin_unlock_irqrestore(&l2x0_lock, flags); } static void l2x0_clean_range(unsigned long start, unsigned long end) { void __iomem *base = l2x0_base; unsigned long flags; if ((end - start) >= l2x0_size) { l2x0_clean_all(); return; } raw_spin_lock_irqsave(&l2x0_lock, flags); start &= ~(CACHE_LINE_SIZE - 1); while (start < end) { unsigned long blk_end = start + min(end - start, 4096UL); while (start < blk_end) { l2x0_clean_line(start); start += CACHE_LINE_SIZE; } if (blk_end < end) { raw_spin_unlock_irqrestore(&l2x0_lock, flags); raw_spin_lock_irqsave(&l2x0_lock, flags); } } cache_wait(base + L2X0_CLEAN_LINE_PA, 1); cache_sync(); raw_spin_unlock_irqrestore(&l2x0_lock, flags); } static void l2x0_flush_range(unsigned long start, unsigned long end) { void __iomem *base = l2x0_base; unsigned long flags; if ((end - start) >= l2x0_size) { l2x0_flush_all(); return; } raw_spin_lock_irqsave(&l2x0_lock, flags); start &= ~(CACHE_LINE_SIZE - 1); while (start < end) { unsigned long blk_end = start + min(end - start, 4096UL); debug_writel(0x03); while (start < blk_end) { l2x0_flush_line(start); start += CACHE_LINE_SIZE; } debug_writel(0x00); if (blk_end < end) { raw_spin_unlock_irqrestore(&l2x0_lock, flags); raw_spin_lock_irqsave(&l2x0_lock, flags); } } cache_wait(base + L2X0_CLEAN_INV_LINE_PA, 1); cache_sync(); raw_spin_unlock_irqrestore(&l2x0_lock, flags); } static void l2x0_disable(void) { unsigned long flags; raw_spin_lock_irqsave(&l2x0_lock, flags); __l2x0_flush_all(); writel_relaxed(0, l2x0_base + L2X0_CTRL); dsb(); raw_spin_unlock_irqrestore(&l2x0_lock, flags); } static void l2x0_unlock(u32 cache_id) { int lockregs; int i; switch (cache_id) { case L2X0_CACHE_ID_PART_L310: lockregs = 8; break; case AURORA_CACHE_ID: lockregs = 4; break; default: /* L210 and unknown types */ lockregs = 1; break; } for (i = 0; i < lockregs; i++) { writel_relaxed(0x0, l2x0_base + L2X0_LOCKDOWN_WAY_D_BASE + i * L2X0_LOCKDOWN_STRIDE); writel_relaxed(0x0, l2x0_base + L2X0_LOCKDOWN_WAY_I_BASE + i * L2X0_LOCKDOWN_STRIDE); } } void __init l2x0_init(void __iomem *base, u32 aux_val, u32 aux_mask) { u32 aux; u32 cache_id; u32 way_size = 0; int ways; int way_size_shift = L2X0_WAY_SIZE_SHIFT; const char *type; l2x0_base = base; if (cache_id_part_number_from_dt) cache_id = cache_id_part_number_from_dt; else cache_id = readl_relaxed(l2x0_base + L2X0_CACHE_ID) & L2X0_CACHE_ID_PART_MASK; aux = readl_relaxed(l2x0_base + L2X0_AUX_CTRL); aux &= aux_mask; aux |= aux_val; /* Determine the number of ways */ switch (cache_id) { case L2X0_CACHE_ID_PART_L310: if (aux & (1 << 16)) ways = 16; else ways = 8; type = "L310"; #ifdef CONFIG_PL310_ERRATA_753970 /* Unmapped register. */ sync_reg_offset = L2X0_DUMMY_REG; #endif if ((cache_id & L2X0_CACHE_ID_RTL_MASK) <= L2X0_CACHE_ID_RTL_R3P0) outer_cache.set_debug = pl310_set_debug; break; case L2X0_CACHE_ID_PART_L210: ways = (aux >> 13) & 0xf; type = "L210"; break; case AURORA_CACHE_ID: sync_reg_offset = AURORA_SYNC_REG; ways = (aux >> 13) & 0xf; ways = 2 << ((ways + 1) >> 2); way_size_shift = AURORA_WAY_SIZE_SHIFT; type = "Aurora"; break; default: /* Assume unknown chips have 8 ways */ ways = 8; type = "L2x0 series"; break; } l2x0_way_mask = (1 << ways) - 1; /* * L2 cache Size = Way size * Number of ways */ way_size = (aux & L2X0_AUX_CTRL_WAY_SIZE_MASK) >> 17; way_size = 1 << (way_size + way_size_shift); l2x0_size = ways * way_size * SZ_1K; /* * Check if l2x0 controller is already enabled. * If you are booting from non-secure mode * accessing the below registers will fault. */ if (!(readl_relaxed(l2x0_base + L2X0_CTRL) & L2X0_CTRL_EN)) { /* Make sure that I&D is not locked down when starting */ l2x0_unlock(cache_id); /* l2x0 controller is disabled */ writel_relaxed(aux, l2x0_base + L2X0_AUX_CTRL); l2x0_inv_all(); /* enable L2X0 */ writel_relaxed(L2X0_CTRL_EN, l2x0_base + L2X0_CTRL); } /* Re-read it in case some bits are reserved. */ aux = readl_relaxed(l2x0_base + L2X0_AUX_CTRL); /* Save the value for resuming. */ l2x0_saved_regs.aux_ctrl = aux; if (!of_init) { outer_cache.inv_range = l2x0_inv_range; outer_cache.clean_range = l2x0_clean_range; outer_cache.flush_range = l2x0_flush_range; outer_cache.sync = l2x0_cache_sync; outer_cache.flush_all = l2x0_flush_all; outer_cache.inv_all = l2x0_inv_all; outer_cache.disable = l2x0_disable; } printk(KERN_INFO "%s cache controller enabled\n", type); printk(KERN_INFO "l2x0: %d ways, CACHE_ID 0x%08x, AUX_CTRL 0x%08x, Cache size: %d B\n", ways, cache_id, aux, l2x0_size); } #ifdef CONFIG_OF static int l2_wt_override; /* * Note that the end addresses passed to Linux primitives are * noninclusive, while the hardware cache range operations use * inclusive start and end addresses. */ static unsigned long calc_range_end(unsigned long start, unsigned long end) { /* * Limit the number of cache lines processed at once, * since cache range operations stall the CPU pipeline * until completion. */ if (end > start + MAX_RANGE_SIZE) end = start + MAX_RANGE_SIZE; /* * Cache range operations can't straddle a page boundary. */ if (end > PAGE_ALIGN(start+1)) end = PAGE_ALIGN(start+1); return end; } /* * Make sure 'start' and 'end' reference the same page, as L2 is PIPT * and range operations only do a TLB lookup on the start address. */ static void aurora_pa_range(unsigned long start, unsigned long end, unsigned long offset) { unsigned long flags; raw_spin_lock_irqsave(&l2x0_lock, flags); writel_relaxed(start, l2x0_base + AURORA_RANGE_BASE_ADDR_REG);