[RFC 7/8] TILER-DMM: Main TILER driver implementation.
David Sin
davidsin at ti.com
Fri Jul 23 19:28:13 EDT 2010
From: Lajos Molnar <molnar at ti.com>
This patch contains the TILER driver and implementation of the TILER
block manipulation and mapping functions.
It also contains the makefile and config file for the TILER driver.
Signed-off-by: Lajos Molnar <molnar at ti.com>
Signed-off-by: David Sin <davidsin at ti.com>
---
drivers/media/video/tiler/Kconfig | 65 +++++
drivers/media/video/tiler/Makefile | 7 +
drivers/media/video/tiler/tiler-iface.c | 106 ++++++++
drivers/media/video/tiler/tiler-main.c | 426 +++++++++++++++++++++++++++++++
4 files changed, 604 insertions(+), 0 deletions(-)
create mode 100644 drivers/media/video/tiler/Kconfig
create mode 100644 drivers/media/video/tiler/Makefile
create mode 100644 drivers/media/video/tiler/tiler-iface.c
create mode 100644 drivers/media/video/tiler/tiler-main.c
diff --git a/drivers/media/video/tiler/Kconfig b/drivers/media/video/tiler/Kconfig
new file mode 100644
index 0000000..2c61471
--- /dev/null
+++ b/drivers/media/video/tiler/Kconfig
@@ -0,0 +1,65 @@
+config HAVE_TI_TILER
+ bool
+ default y
+ depends on ARCH_OMAP4
+
+menuconfig TI_TILER
+ tristate "TI TILER support"
+ default y
+ depends on HAVE_TI_TILER
+ help
+ TILER and TILER-DMM driver for TI chips. The TI TILER device
+ enables video rotation on certain TI chips such as OMAP4 or
+ Netra. Video rotation will be limited without TILER support.
+
+config TILER_GRANULARITY
+ int "Allocation granularity (2^n)"
+ range 1 4096
+ default 128
+ depends on TI_TILER
+ help
+ This option sets the default TILER allocation granularity. It can
+ be overriden by the tiler.grain boot argument.
+
+ The allocation granularity is the smallest TILER block size (in
+ bytes) managed distinctly by the TILER driver. TILER blocks of any
+ size are managed in chunks of at least this size.
+
+ Must be a 2^n in the range of 1 to 4096; however, the TILER driver
+ may use a larger supported granularity.
+
+ Supported values are: 1, 2, 4, 8, 16, 32, 64, 128, 256, 512, 1024,
+ 2048, 4096.
+
+config TILER_ALIGNMENT
+ int "Allocation alignment (2^n)"
+ range 1 4096
+ default 4096
+ depends on TI_TILER
+ help
+ This option sets the default TILER allocation alignment. It can
+ be overriden by the tiler.align boot argument.
+
+ Must be a 2^n in the range of 1 to 4096; however, it is naturally
+ aligned to the TILER granularity.
+
+ Supported values are: 1, 2, 4, 8, 16, 32, 64, 128, 256, 512, 1024,
+ 2048, 4096.
+
+config TILER_CACHE_LIMIT
+ int "Memory limit to cache free pages in MBytes"
+ range 0 128
+ default 40
+ depends on TI_TILER
+ help
+ This option sets the minimum memory that TILER retains even if
+ there is less TILER allocated memory is use. The unused memory is
+ instead stored in a cache to speed up allocation and freeing of
+ physical pages.
+
+ This option can be overriden by the tiler.cache boot argument.
+
+ While initially TILER will use less memory than this limit (0), it
+ will not release any memory used until it reaches this limit.
+ Thereafter, TILER will release any unused memory immediately as
+ long as there it is above this threshold.
diff --git a/drivers/media/video/tiler/Makefile b/drivers/media/video/tiler/Makefile
new file mode 100644
index 0000000..4a6495e
--- /dev/null
+++ b/drivers/media/video/tiler/Makefile
@@ -0,0 +1,7 @@
+obj-$(CONFIG_TI_TILER) += tcm/
+
+obj-$(CONFIG_TI_TILER) += tiler.o
+tiler-objs = tiler-geom.o tiler-main.o tiler-iface.o tmm-pat.o
+
+obj-$(CONFIG_TI_TILER) += tiler_dmm.o
+tiler_dmm-objs = dmm.o
diff --git a/drivers/media/video/tiler/tiler-iface.c b/drivers/media/video/tiler/tiler-iface.c
new file mode 100644
index 0000000..0b10fae
--- /dev/null
+++ b/drivers/media/video/tiler/tiler-iface.c
@@ -0,0 +1,106 @@
+/*
+ * tiler-iface.c
+ *
+ * TILER driver interace functions for TI TILER hardware block.
+ *
+ * Authors: Lajos Molnar <molnar at ti.com>
+ * David Sin <davidsin at ti.com>
+ *
+ * Copyright (C) 2009-2010 Texas Instruments, Inc.
+ *
+ * This package 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 PACKAGE IS PROVIDED ``AS IS'' AND WITHOUT ANY EXPRESS OR
+ * IMPLIED WARRANTIES, INCLUDING, WITHOUT LIMITATION, THE IMPLIED
+ * WARRANTIES OF MERCHANTIBILITY AND FITNESS FOR A PARTICULAR PURPOSE.
+ */
+
+#include <linux/module.h>
+#include <linux/slab.h> /* kmalloc */
+#include <linux/mm.h>
+#include <linux/mm_types.h>
+#include <asm/mach/map.h> /* for ioremap_page */
+
+#include "_tiler.h"
+
+/*
+ * Memory-Map Kernel APIs
+ * ==========================================================================
+ */
+
+s32 tiler_mmap_blk(struct tiler_block_t *blk, u32 offs, u32 size,
+ struct vm_area_struct *vma, u32 voffs)
+{
+ u32 v, p, len;
+
+ /* don't allow mremap */
+ vma->vm_flags |= VM_DONTEXPAND | VM_RESERVED;
+
+ /* mapping must fit into vma */
+ BUG_ON(vma->vm_start > vma->vm_start + voffs ||
+ vma->vm_start + voffs > vma->vm_start + voffs + size ||
+ vma->vm_start + voffs + size > vma->vm_end);
+
+ /* mapping must fit into block */
+ BUG_ON(offs > offs + size || offs + size > tiler_size(blk));
+
+ v = tiler_vstride(blk);
+ p = tiler_pstride(blk);
+
+ /* remap block portion */
+ len = v - (offs % v); /* initial area to map */
+ while (size) {
+ /* restrict to size still needs mapping */
+ if (len > size)
+ len = size;
+
+ vma->vm_pgoff = (blk->phys + offs) >> PAGE_SHIFT;
+ if (remap_pfn_range(vma, vma->vm_start + voffs, vma->vm_pgoff,
+ len, vma->vm_page_prot))
+ return -EAGAIN;
+ voffs += len;
+ offs += len + p - v;
+ size -= len;
+ len = v; /* subsequent area to map */
+ }
+ return 0;
+}
+EXPORT_SYMBOL(tiler_mmap_blk);
+
+s32 tiler_ioremap_blk(struct tiler_block_t *blk, u32 offs, u32 size,
+ u32 addr, u32 mtype)
+{
+ u32 v, p;
+ u32 len; /* area to map */
+ const struct mem_type *type = get_mem_type(mtype);
+
+ /* mapping must fit into address space */
+ BUG_ON(addr > addr + size);
+
+ /* mapping must fit into block */
+ BUG_ON(offs > offs + size || offs + size > tiler_size(blk));
+
+ v = tiler_vstride(blk);
+ p = tiler_pstride(blk);
+
+ /* move offset and address to end */
+ offs += blk->phys + size;
+ addr += size;
+
+ len = v - (offs % v); /* initial area to map */
+ while (size) {
+ while (len && size) {
+ if (ioremap_page(addr - size, offs - size, type))
+ return -EAGAIN;
+ len -= PAGE_SIZE;
+ size -= PAGE_SIZE;
+ }
+
+ offs += p - v;
+ len = v; /* subsequent area to map */
+ }
+ return 0;
+}
+EXPORT_SYMBOL(tiler_ioremap_blk);
diff --git a/drivers/media/video/tiler/tiler-main.c b/drivers/media/video/tiler/tiler-main.c
new file mode 100644
index 0000000..cbd84d1
--- /dev/null
+++ b/drivers/media/video/tiler/tiler-main.c
@@ -0,0 +1,426 @@
+/*
+ * tiler-main.c
+ *
+ * TILER driver main support functions for TI TILER hardware block.
+ *
+ * Authors: Lajos Molnar <molnar at ti.com>
+ * David Sin <davidsin at ti.com>
+ *
+ * Copyright (C) 2009-2010 Texas Instruments, Inc.
+ *
+ * This package 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 PACKAGE IS PROVIDED ``AS IS'' AND WITHOUT ANY EXPRESS OR
+ * IMPLIED WARRANTIES, INCLUDING, WITHOUT LIMITATION, THE IMPLIED
+ * WARRANTIES OF MERCHANTIBILITY AND FITNESS FOR A PARTICULAR PURPOSE.
+ */
+
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/platform_device.h> /* platform_device() */
+#include <linux/errno.h>
+#include <linux/mutex.h>
+#include <linux/dma-mapping.h> /* dma_alloc_coherent */
+#include <linux/pagemap.h> /* page_cache_release() */
+#include <linux/slab.h>
+
+#include <mach/dmm.h>
+#include "tmm.h"
+#include "_tiler.h"
+#include "tcm/tcm-sita.h" /* TCM algorithm */
+
+static uint default_align = CONFIG_TILER_ALIGNMENT;
+static uint granularity = CONFIG_TILER_GRANULARITY;
+
+module_param_named(align, default_align, uint, 0444);
+MODULE_PARM_DESC(align, "Default block ssptr alignment");
+module_param_named(grain, granularity, uint, 0444);
+MODULE_PARM_DESC(grain, "Granularity (bytes)");
+
+struct platform_driver tiler_driver_ldm = {
+ .driver = {
+ .owner = THIS_MODULE,
+ .name = "tiler",
+ },
+ .probe = NULL,
+ .shutdown = NULL,
+ .remove = NULL,
+};
+
+static struct tiler_ops tiler; /* shared methods and variables */
+
+static struct list_head blocks; /* all tiler blocks */
+
+static struct mutex mtx;
+static struct tcm *tcm[TILER_FORMATS];
+static struct tmm *tmm[TILER_FORMATS];
+static u32 *dmac_va;
+static dma_addr_t dmac_pa;
+
+/* info for a block */
+struct mem_info {
+ struct list_head global; /* global blocks */
+ struct tiler_block_t blk; /* block info */
+ struct tcm_area area;
+ u32 *mem; /* list of alloced phys addresses */
+};
+
+/*
+ * TMM connectors
+ * ==========================================================================
+ */
+/* wrapper around tmm_map */
+static s32 refill_pat(struct tmm *tmm, struct tcm_area *area, u32 *ptr)
+{
+ s32 res = 0;
+ struct pat_area p_area = {0};
+
+ p_area.x0 = area->p0.x;
+ p_area.y0 = area->p0.y;
+ p_area.x1 = area->p1.x;
+ p_area.y1 = area->p1.y;
+
+ memcpy(dmac_va, ptr, sizeof(*ptr) * tcm_sizeof(*area));
+
+ if (tmm_map(tmm, p_area, dmac_pa))
+ res = -EFAULT;
+
+ return res;
+}
+
+/* wrapper around tmm_clear */
+static void clear_pat(struct tmm *tmm, struct tcm_area *area)
+{
+ struct pat_area p_area = {0};
+
+ p_area.x0 = area->p0.x;
+ p_area.y0 = area->p0.y;
+ p_area.x1 = area->p1.x;
+ p_area.y1 = area->p1.y;
+
+ tmm_clear(tmm, p_area);
+}
+
+/*
+ * Area handling methods
+ * ==========================================================================
+ */
+
+/* verify input params and calculate tiler container params for a block */
+static s32 __analize_area(enum tiler_fmt fmt, u32 width, u32 height,
+ u16 *x_area, u16 *y_area, u16 *align, u16 *offs)
+{
+ /* input: width, height is in pixels, *align, *offs in bytes */
+ /* output: x_area, y_area, *align in slots */
+
+ /* slot width, height, and row size */
+ u32 slot_row, min_align;
+ const struct tiler_geom *g;
+
+ /* width and height must be positive, format must be 2D */
+ if (!width || !height || fmt == TILFMT_PAGE)
+ return -EINVAL;
+
+ /* align must be 2 power */
+ if (*align & (*align - 1))
+ return -EINVAL;
+
+ /* format must be valid */
+ g = tiler.geom(fmt);
+ if (!g)
+ return -EINVAL;
+
+ /* get the # of bytes per row in 1 slot */
+ slot_row = g->slot_w * g->bpp;
+
+ /* minimum alignment is at least 1 slot. Use default if needed */
+ min_align = max(slot_row, granularity);
+ *align = ALIGN(*align ? : default_align, min_align);
+
+ /* offset must be multiple of bpp */
+ if (*offs & (g->bpp - 1) || *offs >= *align)
+ return -EINVAL;
+
+ /* round down the offset to the nearest slot size, and increase width
+ to allow space for having the correct offset */
+ width += (*offs & (min_align - 1)) / g->bpp;
+
+ /* expand width to block size */
+ width = ALIGN(width, min_align / g->bpp);
+
+ /* adjust to slots */
+ *x_area = DIV_ROUND_UP(width, g->slot_w);
+ *y_area = DIV_ROUND_UP(height, g->slot_h);
+ *align /= slot_row;
+
+ if (*x_area > tiler.width || *y_area > tiler.height)
+ return -ENOMEM;
+ return 0;
+}
+
+/* allocate a mem_info structure and reserves a 2d container area */
+static struct mem_info *get_2d_area(u16 w, u16 h, u16 align, struct tcm *tcm)
+{
+ struct mem_info *mi = NULL;
+
+ /* reserve a block struct */
+ mi = kmalloc(sizeof(*mi), GFP_KERNEL);
+ if (!mi)
+ return mi;
+ memset(mi, 0, sizeof(*mi));
+
+ /* reserve an area */
+ if (tcm_reserve_2d(tcm, w, h, align, &mi->area)) {
+ kfree(mi);
+ return NULL;
+ }
+
+ return mi;
+}
+
+/*
+ * Block operations
+ * ==========================================================================
+ */
+
+/* free a block */
+static s32 free_block(struct mem_info *mi)
+{
+ /* release memory */
+ if (mi->mem)
+ tmm_free(tmm[tiler_fmt(mi->blk.phys)], mi->mem);
+ clear_pat(tmm[tiler_fmt(mi->blk.phys)], &mi->area);
+
+ /* unreserve area */
+ tcm_free(&mi->area);
+
+ /* have mutex */
+
+ /* safe deletion as list may not have been assigned */
+ if (mi->global.next)
+ list_del(&mi->global);
+
+ kfree(mi);
+ return 0;
+}
+
+/* create an empty block with just an area and add it to the global list */
+static struct mem_info *get_area(enum tiler_fmt fmt, u32 width, u32 height,
+ u16 align, u16 offs)
+{
+ u16 x, y;
+ struct mem_info *mi = NULL;
+ const struct tiler_geom *g = tiler.geom(fmt);
+
+ /* calculate dimensions and alignment in slots */
+ if (__analize_area(fmt, width, height, &x, &y, &align, &offs))
+ return NULL;
+
+ mi = get_2d_area(x, y, align, tcm[fmt]);
+ if (!mi)
+ return NULL;
+
+ /* have mutex */
+ list_add(&mi->global, &blocks);
+
+ mi->blk.phys = tiler.addr(fmt,
+ mi->area.p0.x * g->slot_w, mi->area.p0.y * g->slot_h)
+ + offs;
+ return mi;
+}
+
+/* allocate a new tiler block */
+static s32 alloc_block(enum tiler_fmt fmt, u32 width, u32 height,
+ u32 align, u32 offs, struct mem_info **info)
+{
+ struct mem_info *mi = NULL;
+
+ *info = NULL;
+
+ /* only support up to page alignment */
+ if (align > PAGE_SIZE || offs >= (align ? : default_align))
+ return -EINVAL;
+
+ mutex_lock(&mtx);
+
+ /* reserve area in tiler container */
+ mi = get_area(fmt, width, height, align, offs);
+ if (!mi)
+ goto nomem;
+
+ mi->blk.width = width;
+ mi->blk.height = height;
+
+ /* allocate and map if mapping is supported */
+ if (tmm_can_map(tmm[fmt])) {
+ mi->mem = tmm_get(tmm[fmt], tcm_sizeof(mi->area));
+ if (!mi->mem)
+ goto cleanup;
+
+ /* Ensure the data reaches to main memory before PAT refill */
+ wmb();
+
+ /* program PAT */
+ if (refill_pat(tmm[fmt], &mi->area, mi->mem))
+ goto cleanup;
+ }
+ *info = mi;
+ mutex_unlock(&mtx);
+ return 0;
+
+cleanup:
+ free_block(mi);
+nomem:
+ mutex_unlock(&mtx);
+ return -ENOMEM;
+}
+
+/*
+ * Driver code
+ * ==========================================================================
+ */
+
+/* driver initialization */
+static s32 __init tiler_init(void)
+{
+ s32 r = -1;
+ struct tcm *sita = NULL;
+ struct tmm *tmm_pat = NULL;
+
+ tiler_geom_init(&tiler);
+
+ /* check module parameters for correctness */
+ if (default_align > PAGE_SIZE ||
+ default_align & (default_align - 1) ||
+ granularity < 1 || granularity > PAGE_SIZE ||
+ granularity & (granularity - 1))
+ return -EINVAL;
+
+ /*
+ * Array of physical pages for PAT programming, which must be a 16-byte
+ * aligned physical address.
+ */
+ dmac_va = dma_alloc_coherent(NULL, tiler.width * tiler.height *
+ sizeof(*dmac_va), &dmac_pa, GFP_ATOMIC);
+ if (!dmac_va)
+ return -ENOMEM;
+
+ /* Allocate tiler container manager (we share 1 on OMAP4) */
+ sita = sita_init(tiler.width, tiler.height, NULL);
+
+ tcm[TILFMT_8BIT] = sita;
+ tcm[TILFMT_16BIT] = sita;
+ tcm[TILFMT_32BIT] = sita;
+
+ /* Allocate tiler memory manager (must have 1 unique TMM per TCM ) */
+ tmm_pat = tmm_pat_init(0);
+ tmm[TILFMT_8BIT] = tmm_pat;
+ tmm[TILFMT_16BIT] = tmm_pat;
+ tmm[TILFMT_32BIT] = tmm_pat;
+
+ if (!sita || !tmm_pat) {
+ r = -ENOMEM;
+ goto error;
+ }
+
+ r = platform_driver_register(&tiler_driver_ldm);
+
+ mutex_init(&mtx);
+ INIT_LIST_HEAD(&blocks);
+
+error:
+ if (r) {
+ tcm_deinit(sita);
+ tmm_deinit(tmm_pat);
+ dma_free_coherent(NULL, tiler.width * tiler.height *
+ sizeof(*dmac_va), dmac_va, dmac_pa);
+ }
+
+ return r;
+}
+
+/* driver cleanup */
+static void __exit tiler_exit(void)
+{
+ int i, j;
+ struct mem_info *mi, *mi_;
+
+ mutex_lock(&mtx);
+
+ /* free all blocks */
+ list_for_each_entry_safe(mi, mi_, &blocks, global)
+ free_block(mi);
+
+ /* all lists should have cleared */
+ BUG_ON(!list_empty(&blocks));
+
+ mutex_unlock(&mtx);
+
+ dma_free_coherent(NULL, tiler.width * tiler.height * sizeof(*dmac_va),
+ dmac_va, dmac_pa);
+
+ /* close containers only once */
+ for (i = TILFMT_MIN; i <= TILFMT_MAX; i++) {
+ /* remove identical containers (tmm is unique per tcm) */
+ for (j = i + 1; j <= TILFMT_MAX; j++)
+ if (tcm[i] == tcm[j]) {
+ tcm[j] = NULL;
+ tmm[j] = NULL;
+ }
+
+ tcm_deinit(tcm[i]);
+ tmm_deinit(tmm[i]);
+ }
+
+ mutex_destroy(&mtx);
+ platform_driver_unregister(&tiler_driver_ldm);
+}
+
+/*
+ * Block Kernel APIs
+ * ==========================================================================
+ */
+
+s32 tiler_alloc(struct tiler_block_t *blk, enum tiler_fmt fmt,
+ u32 align, u32 offs)
+{
+ struct mem_info *mi;
+ s32 res;
+
+ /* blk must be valid, and blk->phys must be 0 */
+ BUG_ON(!blk || blk->phys);
+
+ res = alloc_block(fmt, blk->width, blk->height, align, offs, &mi);
+ if (mi)
+ blk->phys = mi->blk.phys;
+ return res;
+}
+EXPORT_SYMBOL(tiler_alloc);
+
+void tiler_free(struct tiler_block_t *blk)
+{
+ struct mem_info *mi;
+
+ mutex_lock(&mtx);
+
+ /* find block */
+ list_for_each_entry(mi, &blocks, global) {
+ if (mi->blk.phys == blk->phys) {
+ free_block(mi);
+ break;
+ }
+ }
+
+ blk->phys = 0;
+
+ mutex_unlock(&mtx);
+}
+EXPORT_SYMBOL(tiler_free);
+
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Lajos Molnar <molnar at ti.com>");
+MODULE_AUTHOR("David Sin <davidsin at ti.com>");
+module_init(tiler_init);
+module_exit(tiler_exit);
--
1.6.3.3
More information about the linux-arm-kernel
mailing list