@@ -862,6 +862,7 @@ config ARCH_DAVINCI
bool "TI DaVinci"
select GENERIC_CLOCKEVENTS
select ARCH_REQUIRE_GPIOLIB
+ select PV_POOL
select ZONE_DMA
select HAVE_IDE
select CLKDEV_LOOKUP
@@ -875,6 +876,7 @@ config ARCH_OMAP
select HAVE_CLK
select ARCH_REQUIRE_GPIOLIB
select ARCH_HAS_CPUFREQ
+ select PV_POOL
select GENERIC_CLOCKEVENTS
select HAVE_SCHED_CLOCK
select ARCH_HAS_HOLES_MEMORYMODEL
@@ -39,3 +39,7 @@ config SHARP_PARAM
config SHARP_SCOOP
bool
+
+config PV_POOL
+ bool
+ select GENERIC_ALLOCATOR
@@ -17,3 +17,4 @@ obj-$(CONFIG_ARCH_IXP2000) += uengine.o
obj-$(CONFIG_ARCH_IXP23XX) += uengine.o
obj-$(CONFIG_PCI_HOST_ITE8152) += it8152.o
obj-$(CONFIG_ARM_TIMER_SP804) += timer-sp.o
+obj-$(CONFIG_PV_POOL) += pv-pool.o
@@ -0,0 +1,69 @@
+/*
+ * Unified Phys/Virt allocator, based on mach-davinci/sram.c, which was
+ * Copyright (C) 2009 David Brownell.
+ *
+ * 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
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+#include <linux/dma-mapping.h>
+#include <linux/genalloc.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+
+#include <asm/pv-pool.h>
+
+struct pv_pool {
+ struct gen_pool *genpool;
+ void *cpu_base;
+ phys_addr_t phys_base;
+};
+
+void *pv_pool_alloc(struct pv_pool *pool, size_t len, phys_addr_t *phys)
+{
+ void *addr = (void *)gen_pool_alloc(pool->genpool, len);
+
+ if (phys)
+ *phys = addr ? (pool->phys_base + (addr - pool->cpu_base)) :
+ (phys_addr_t)-1ULL;
+
+ return addr;
+}
+EXPORT_SYMBOL_GPL(pv_pool_alloc);
+
+void pv_pool_free(struct pv_pool *pool, void *addr, size_t len)
+{
+ gen_pool_free(pool->genpool, (unsigned long)addr, len);
+}
+EXPORT_SYMBOL_GPL(pv_pool_free);
+
+struct pv_pool *pv_pool_create(void *addr, phys_addr_t phys, size_t len,
+ int min_alloc_order)
+{
+ struct pv_pool *pool = kzalloc(sizeof(struct pv_pool), GFP_KERNEL);
+
+ if (pool) {
+ pool->cpu_base = addr;
+ pool->phys_base = phys;
+ pool->genpool = gen_pool_create(min_alloc_order, -1);
+ if (!pool->genpool) {
+ kfree(pool);
+ pool = NULL;
+ } else {
+ WARN_ON(gen_pool_add(pool->genpool, (unsigned long)addr,
+ len, -1) < 0);
+ }
+ }
+
+ return pool;
+}
+EXPORT_SYMBOL_GPL(pv_pool_create);
+
+void pv_pool_destroy(struct pv_pool *pool)
+{
+ gen_pool_destroy(pool->genpool);
+ kfree(pool);
+}
+EXPORT_SYMBOL_GPL(pv_pool_destroy);
@@ -0,0 +1,20 @@
+#ifndef __ASMARM_PV_POOL_H
+#define __ASMARM_PV_POOL_H
+
+#include <asm/fncpy.h>
+
+struct pv_pool;
+
+void *pv_pool_alloc(struct pv_pool *, size_t, phys_addr_t *);
+void pv_pool_free(struct pv_pool *, void *, size_t);
+struct pv_pool *pv_pool_create(void *, phys_addr_t, size_t, int);
+void pv_pool_destroy(struct pv_pool *);
+
+/* Macro to copy a function into SRAM, using the fncpy API */
+#define pv_pool_fncpy(pool, funcp, size) ({ \
+ size_t _sz = size; \
+ void *_sram = pv_pool_alloc(pool, _sz, NULL); \
+ (_sram ? fncpy(_sram, &(funcp), _sz) : NULL); \
+})
+
+#endif
@@ -1099,7 +1099,7 @@ static struct davinci_soc_info davinci_soc_info_da850 = {
.gpio_irq = IRQ_DA8XX_GPIO0,
.serial_dev = &da8xx_serial_device,
.emac_pdata = &da8xx_emac_pdata,
- .sram_dma = DA8XX_ARM_RAM_BASE,
+ .sram_phys = DA8XX_ARM_RAM_BASE,
.sram_len = SZ_8K,
.reset_device = &da8xx_wdt_device,
};
@@ -850,7 +850,7 @@ static struct davinci_soc_info davinci_soc_info_dm355 = {
.gpio_num = 104,
.gpio_irq = IRQ_DM355_GPIOBNK0,
.serial_dev = &dm355_serial_device,
- .sram_dma = 0x00010000,
+ .sram_phys = 0x00010000,
.sram_len = SZ_32K,
.reset_device = &davinci_wdt_device,
};
@@ -1082,7 +1082,7 @@ static struct davinci_soc_info davinci_soc_info_dm365 = {
.gpio_unbanked = 8, /* really 16 ... skip muxed GPIOs */
.serial_dev = &dm365_serial_device,
.emac_pdata = &dm365_emac_pdata,
- .sram_dma = 0x00010000,
+ .sram_phys = 0x00010000,
.sram_len = SZ_32K,
.reset_device = &davinci_wdt_device,
};
@@ -764,7 +764,7 @@ static struct davinci_soc_info davinci_soc_info_dm644x = {
.gpio_irq = IRQ_GPIOBNK0,
.serial_dev = &dm644x_serial_device,
.emac_pdata = &dm644x_emac_pdata,
- .sram_dma = 0x00008000,
+ .sram_phys = 0x00008000,
.sram_len = SZ_16K,
.reset_device = &davinci_wdt_device,
};
@@ -848,7 +848,7 @@ static struct davinci_soc_info davinci_soc_info_dm646x = {
.gpio_irq = IRQ_DM646X_GPIOBNK0,
.serial_dev = &dm646x_serial_device,
.emac_pdata = &dm646x_emac_pdata,
- .sram_dma = 0x10010000,
+ .sram_phys = 0x10010000,
.sram_len = SZ_32K,
.reset_device = &davinci_wdt_device,
};
@@ -75,7 +75,7 @@ struct davinci_soc_info {
int gpio_ctlrs_num;
struct platform_device *serial_dev;
struct emac_platform_data *emac_pdata;
- dma_addr_t sram_dma;
+ phys_addr_t sram_phys;
unsigned sram_len;
struct platform_device *reset_device;
void (*reset)(struct platform_device *);
@@ -10,18 +10,11 @@
#ifndef __MACH_SRAM_H
#define __MACH_SRAM_H
+#include <asm/pv-pool.h>
+
/* ARBITRARY: SRAM allocations are multiples of this 2^N size */
#define SRAM_GRANULARITY 512
-/*
- * SRAM allocations return a CPU virtual address, or NULL on error.
- * If a DMA address is requested and the SRAM supports DMA, its
- * mapped address is also returned.
- *
- * Errors include SRAM memory not being available, and requesting
- * DMA mapped SRAM on systems which don't allow that.
- */
-extern void *sram_alloc(size_t len, dma_addr_t *dma);
-extern void sram_free(void *addr, size_t len);
+extern struct pv_pool *davinci_pv_pool;
#endif /* __MACH_SRAM_H */
@@ -27,14 +27,9 @@
#define DEEPSLEEP_SLEEPCOUNT_MASK 0xFFFF
static void (*davinci_sram_suspend) (struct davinci_pm_config *);
+static void *davinci_sram_suspend_mem;
static struct davinci_pm_config *pdata;
-static void davinci_sram_push(void *dest, void *src, unsigned int size)
-{
- memcpy(dest, src, size);
- flush_icache_range((unsigned long)dest, (unsigned long)(dest + size));
-}
-
static void davinci_pm_suspend(void)
{
unsigned val;
@@ -123,14 +118,14 @@ static int __init davinci_pm_probe(struct platform_device *pdev)
return -ENOENT;
}
- davinci_sram_suspend = sram_alloc(davinci_cpu_suspend_sz, NULL);
- if (!davinci_sram_suspend) {
+ davinci_sram_suspend_mem = pv_pool_alloc(davinci_pv_pool,
+ davinci_cpu_suspend_sz, NULL);
+ if (!davinci_sram_suspend_mem) {
dev_err(&pdev->dev, "cannot allocate SRAM memory\n");
return -ENOMEM;
}
-
- davinci_sram_push(davinci_sram_suspend, davinci_cpu_suspend,
- davinci_cpu_suspend_sz);
+ davinci_sram_suspend = fncpy(davinci_sram_suspend_mem,
+ davinci_cpu_suspend, davinci_cpu_suspend_sz);
suspend_set_ops(&davinci_pm_ops);
@@ -139,7 +134,8 @@ static int __init davinci_pm_probe(struct platform_device *pdev)
static int __exit davinci_pm_remove(struct platform_device *pdev)
{
- sram_free(davinci_sram_suspend, davinci_cpu_suspend_sz);
+ pv_pool_free(davinci_pv_pool, davinci_sram_suspend_mem,
+ davinci_cpu_suspend_sz);
return 0;
}
@@ -10,40 +10,13 @@
*/
#include <linux/module.h>
#include <linux/init.h>
-#include <linux/genalloc.h>
+#include <asm/pv-pool.h>
#include <mach/common.h>
#include <mach/sram.h>
-static struct gen_pool *sram_pool;
-
-void *sram_alloc(size_t len, dma_addr_t *dma)
-{
- unsigned long vaddr;
- dma_addr_t dma_base = davinci_soc_info.sram_dma;
-
- if (dma)
- *dma = 0;
- if (!sram_pool || (dma && !dma_base))
- return NULL;
-
- vaddr = gen_pool_alloc(sram_pool, len);
- if (!vaddr)
- return NULL;
-
- if (dma)
- *dma = dma_base + (vaddr - SRAM_VIRT);
- return (void *)vaddr;
-
-}
-EXPORT_SYMBOL(sram_alloc);
-
-void sram_free(void *addr, size_t len)
-{
- gen_pool_free(sram_pool, (unsigned long) addr, len);
-}
-EXPORT_SYMBOL(sram_free);
-
+struct pv_pool *davinci_pv_pool;
+EXPORT_SYMBOL_GPL(davinci_pv_pool);
/*
* REVISIT This supports CPU and DMA access to/from SRAM, but it
@@ -58,13 +31,12 @@ static int __init sram_init(void)
if (len) {
len = min_t(unsigned, len, SRAM_SIZE);
- sram_pool = gen_pool_create(ilog2(SRAM_GRANULARITY), -1);
- if (!sram_pool)
+ davinci_pv_pool = pv_pool_create((void *)SRAM_VIRT,
+ davinci_soc_info.sram_phys, len,
+ ilog2(SRAM_GRANULARITY));
+ if (!davinci_pv_pool)
status = -ENOMEM;
}
- if (sram_pool)
- status = gen_pool_add(sram_pool, SRAM_VIRT, len, -1);
- WARN_ON(status < 0);
return status;
}
core_initcall(sram_init);
@@ -118,6 +118,6 @@ config ARCH_MXC_AUDMUX_V2
config IRAM_ALLOC
bool
- select GENERIC_ALLOCATOR
+ select PV_POOL
endif
@@ -17,25 +17,37 @@
* MA 02110-1301, USA.
*/
#include <linux/errno.h>
+#include <asm/pv-pool.h>
#ifdef CONFIG_IRAM_ALLOC
-int __init iram_init(unsigned long base, unsigned long size);
-void __iomem *iram_alloc(unsigned int size, unsigned long *dma_addr);
-void iram_free(unsigned long dma_addr, unsigned int size);
+int __init iram_init(phys_addr_t base, size_t size);
+
+extern struct pv_pool *mxc_iram_pool;
+
+static inline void *iram_alloc(size_t size, phys_addr_t *phys)
+{
+ return pv_pool_alloc(iram_pool, size, phys);
+}
+
+static inline void iram_free(void *addr, size_t size)
+{
+ pv_pool_free(iram_pool, addr, size);
+}
#else
-static inline int __init iram_init(unsigned long base, unsigned long size)
+static inline int __init iram_init(phys_addr_t base, size_t size)
{
return -ENOMEM;
}
-static inline void __iomem *iram_alloc(unsigned int size, unsigned long *dma_addr)
+static inline void *iram_alloc(size_t size, phys_addr_t *phys)
{
+ *phys = (phys_addr_t)-1ULL;
return NULL;
}
-static inline void iram_free(unsigned long base, unsigned long size) {}
+static inline void iram_free(void *addr, size_t size) {}
#endif
@@ -24,50 +24,24 @@
#include <linux/genalloc.h>
#include <mach/iram.h>
-static unsigned long iram_phys_base;
-static void __iomem *iram_virt_base;
-static struct gen_pool *iram_pool;
+struct pv_pool *mxc_iram_pool;
+EXPORT_SYMBOL(mxc_iram_pool);
-static inline void __iomem *iram_phys_to_virt(unsigned long p)
+int __init iram_init(phys_addr_t base, size_t size)
{
- return iram_virt_base + (p - iram_phys_base);
-}
-
-void __iomem *iram_alloc(unsigned int size, unsigned long *dma_addr)
-{
- if (!iram_pool)
- return NULL;
-
- *dma_addr = gen_pool_alloc(iram_pool, size);
- pr_debug("iram alloc - %dB@0x%lX\n", size, *dma_addr);
- if (!*dma_addr)
- return NULL;
- return iram_phys_to_virt(*dma_addr);
-}
-EXPORT_SYMBOL(iram_alloc);
-
-void iram_free(unsigned long addr, unsigned int size)
-{
- if (!iram_pool)
- return;
-
- gen_pool_free(iram_pool, addr, size);
-}
-EXPORT_SYMBOL(iram_free);
+ void *addr = /*FIXME*/ ioremap(base, size);
-int __init iram_init(unsigned long base, unsigned long size)
-{
- iram_phys_base = base;
+ if (!addr)
+ return -EIO;
- iram_pool = gen_pool_create(PAGE_SHIFT, -1);
- if (!iram_pool)
+ mxc_iram_pool = pv_pool_create(addr, base, size, PAGE_SHIFT);
+ if (!mxc_iram_pool) {
+ iounmap(addr);
return -ENOMEM;
+ }
- gen_pool_add(iram_pool, base, size, -1);
- iram_virt_base = ioremap(iram_phys_base, size);
- if (!iram_virt_base)
- return -EIO;
+ pr_debug("i.MX IRAM pool: %lu KB@0x%08llx\n", size / 1024,
+ (unsigned long long)base);
- pr_debug("i.MX IRAM pool: %ld KB@0x%p\n", size / 1024, iram_virt_base);
return 0;
}
@@ -12,16 +12,19 @@
#define __ARCH_ARM_OMAP_SRAM_H
#ifndef __ASSEMBLY__
-#include <asm/fncpy.h>
+#include <asm/pv-pool.h>
-extern void *omap_sram_push_address(unsigned long size);
+extern struct pv_pool *omap_pv_pool;
-/* Macro to push a function to the internal SRAM, using the fncpy API */
+/*
+ * Note that fncpy requires the SRAM address to be aligned to an 8-byte
+ * boundary, so the min_alloc_order for the pool is set appropriately.
+ */
#define omap_sram_push(funcp, size) ({ \
- typeof(&(funcp)) _res = NULL; \
- void *_sram_address = omap_sram_push_address(size); \
- if (_sram_address) \
- _res = fncpy(_sram_address, &(funcp), size); \
+ typeof(&(funcp)) _res; \
+ _res = pv_pool_fncpy(omap_pv_pool, funcp, size); \
+ if (!_res) \
+ pr_err("Not enough space in SRAM\n"); \
_res; \
})
@@ -75,7 +75,6 @@
static unsigned long omap_sram_start;
static unsigned long omap_sram_base;
static unsigned long omap_sram_size;
-static unsigned long omap_sram_ceil;
/*
* Depending on the target RAMFS firewall setup, the public usable amount of
@@ -104,6 +103,8 @@ static int is_sram_locked(void)
return 1; /* assume locked with no PPA or security driver */
}
+struct pv_pool *omap_pv_pool;
+
/*
* The amount of SRAM depends on the core type.
* Note that we cannot try to test for SRAM here because writes
@@ -182,7 +183,16 @@ static void __init omap_detect_sram(void)
omap_sram_size - SRAM_BOOTLOADER_SZ);
omap_sram_size -= reserved;
- omap_sram_ceil = omap_sram_base + omap_sram_size;
+ {
+ /* The first SRAM_BOOTLOADER_SZ of SRAM are reserved */
+ void *base = (void *)omap_sram_base + SRAM_BOOTLOADER_SZ;
+ phys_addr_t phys = omap_sram_start + SRAM_BOOTLOADER_SZ;
+ size_t len = omap_sram_size - SRAM_BOOTLOADER_SZ;
+
+ omap_pv_pool = pv_pool_create(base, phys, len,
+ ilog2(FNCPY_ALIGN));
+ WARN_ON(!omap_pv_pool);
+ }
}
static struct map_desc omap_sram_io_desc[] __initdata = {
@@ -242,26 +252,6 @@ static void __init omap_map_sram(void)
omap_sram_size - SRAM_BOOTLOADER_SZ);
}
-/*
- * Memory allocator for SRAM: calculates the new ceiling address
- * for pushing a function using the fncpy API.
- *
- * Note that fncpy requires the returned address to be aligned
- * to an 8-byte boundary.
- */
-void *omap_sram_push_address(unsigned long size)
-{
- if (size > (omap_sram_ceil - (omap_sram_base + SRAM_BOOTLOADER_SZ))) {
- printk(KERN_ERR "Not enough space in SRAM\n");
- return NULL;
- }
-
- omap_sram_ceil -= size;
- omap_sram_ceil = ROUND_DOWN(omap_sram_ceil, FNCPY_ALIGN);
-
- return (void *)omap_sram_ceil;
-}
-
#ifdef CONFIG_ARCH_OMAP1
static void (*_omap_sram_reprogram_clock)(u32 dpllctl, u32 ckctl);
@@ -62,7 +62,7 @@ MODULE_PARM_DESC(extram_pool_sz, "external ram pool size to allocate");
struct uio_pruss_dev {
struct uio_info *info;
struct clk *pruss_clk;
- dma_addr_t sram_paddr;
+ phys_addr_t sram_paddr;
dma_addr_t ddr_paddr;
void __iomem *prussio_vaddr;
void *sram_vaddr;
@@ -106,7 +106,7 @@ static void pruss_cleanup(struct platform_device *dev,
gdev->ddr_paddr);
}
if (gdev->sram_vaddr)
- sram_free(gdev->sram_vaddr, sram_pool_sz);
+ pv_pool_free(davinci_pv_pool, gdev->sram_vaddr, sram_pool_sz);
kfree(gdev->info);
clk_put(gdev->pruss_clk);
kfree(gdev);
@@ -152,7 +152,8 @@ static int __devinit pruss_probe(struct platform_device *dev)
goto out_free;
}
- gdev->sram_vaddr = sram_alloc(sram_pool_sz, &(gdev->sram_paddr));
+ gdev->sram_vaddr = pv_pool_alloc(davinci_pv_pool, sram_pool_sz,
+ &(gdev->sram_paddr));
if (!gdev->sram_vaddr) {
dev_err(&dev->dev, "Could not allocate SRAM pool\n");
goto out_free;
@@ -232,14 +232,14 @@ static int allocate_sram(struct snd_pcm_substream *substream, unsigned size,
{
struct snd_dma_buffer *buf = &substream->dma_buffer;
struct snd_dma_buffer *iram_dma = NULL;
- dma_addr_t iram_phys = 0;
+ phys_addr_t iram_phys;
void *iram_virt = NULL;
if (buf->private_data || !size)
return 0;
ppcm->period_bytes_max = size;
- iram_virt = sram_alloc(size, &iram_phys);
+ iram_virt = pv_pool_alloc(davinci_pv_pool, size, &iram_phys);
if (!iram_virt)
goto exit1;
iram_dma = kzalloc(sizeof(*iram_dma), GFP_KERNEL);
@@ -253,7 +253,7 @@ static int allocate_sram(struct snd_pcm_substream *substream, unsigned size,
return 0;
exit2:
if (iram_virt)
- sram_free(iram_virt, size);
+ pv_pool_free(davinci_pv_pool, iram_virt, size);
exit1:
return -ENOMEM;
}
@@ -803,7 +803,8 @@ static void davinci_pcm_free(struct snd_pcm *pcm)
buf->area = NULL;
iram_dma = buf->private_data;
if (iram_dma) {
- sram_free(iram_dma->area, iram_dma->bytes);
+ pv_pool_free(davinci_pv_pool, iram_dma->area,
+ iram_dma->bytes);
kfree(iram_dma);
}
}
On Fri, Apr 15, 2011 at 02:06:07PM +0100, Russell King - ARM Linux wrote: This is work in progress. We have two SoCs using SRAM, both with their own allocation systems, and both with their own ways of copying functions into the SRAM. Let's unify this before we have additional SoCs re-implementing this obviously common functionality themselves. Unfortunately, we end up with code growth through doing this, but that will become a win when we have another SoC using this (which I know there's at least one in the pipeline). One of the considerations here is that we can easily convert sram-pool.c to hook into device tree stuff, which can tell the sram allocator: - physical address of sram - size of sram - allocation granularity and then we just need to ensure that it is appropriately mapped. This uses the physical address, and unlike Davinci's dma address usage, it always wants to have the physical address, and will always return the corresponding physical address when passed that pointer. OMAP could probably do with some more work to make the omapfb and other allocations use the sram allocator, rather than hooking in before the sram allocator is initialized - and then further cleanups so that we have an initialization function which just does sram_create(phys, size) virt = map sram(phys, size) create sram pool(virt, phys, size, min_alloc_order) Another question is whether we should allow multiple SRAM pools or not - this code does allow multiple pools, but so far we only have one pool per SoC. Overdesign? Maybe, but it prevents SoCs wanting to duplicate it if they want to partition the SRAM, or have peripheral-local SRAMs. Lastly, uio_pruss should probably take the SRAM pool pointer via platform data so that it doesn't have to include Davinci specific includes. Signed-off-by: Russell King <rmk+kernel@arm.linux.org.uk> --- This version fixes the davinci pm free, and adds updates for the davinci pcm driver. As I don't know what's happening with Jean's patch tweaking the genpool allocator, I've kept my version. This still suffers from the "only one region per pvpool" problem which I believe Jean's patch doesn't suffer. arch/arm/Kconfig | 2 + arch/arm/common/Kconfig | 4 ++ arch/arm/common/Makefile | 1 + arch/arm/common/pv-pool.c | 69 +++++++++++++++++++++++++++ arch/arm/include/asm/pv-pool.h | 20 ++++++++ arch/arm/mach-davinci/da850.c | 2 +- arch/arm/mach-davinci/dm355.c | 2 +- arch/arm/mach-davinci/dm365.c | 2 +- arch/arm/mach-davinci/dm644x.c | 2 +- arch/arm/mach-davinci/dm646x.c | 2 +- arch/arm/mach-davinci/include/mach/common.h | 2 +- arch/arm/mach-davinci/include/mach/sram.h | 13 +---- arch/arm/mach-davinci/pm.c | 20 +++----- arch/arm/mach-davinci/sram.c | 42 +++-------------- arch/arm/plat-mxc/Kconfig | 2 +- arch/arm/plat-mxc/include/mach/iram.h | 24 +++++++-- arch/arm/plat-mxc/iram_alloc.c | 50 +++++--------------- arch/arm/plat-omap/include/plat/sram.h | 17 ++++--- arch/arm/plat-omap/sram.c | 34 +++++--------- drivers/uio/uio_pruss.c | 7 ++- sound/soc/davinci/davinci-pcm.c | 9 ++-- 21 files changed, 182 insertions(+), 144 deletions(-)