linux/arch/powerpc/platforms/iseries/iommu.c

261 lines
7.2 KiB
C
Raw Normal View History

/*
* Copyright (C) 2001 Mike Corrigan & Dave Engebretsen, IBM Corporation
*
* Rewrite, cleanup:
*
* Copyright (C) 2004 Olof Johansson <olof@lixom.net>, IBM Corporation
* Copyright (C) 2006 Olof Johansson <olof@lixom.net>
*
* Dynamic DMA mapping support, iSeries-specific parts.
*
*
* 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.
*
* 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/types.h>
#include <linux/dma-mapping.h>
#include <linux/list.h>
#include <linux/pci.h>
#include <linux/module.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 09:04:11 +01:00
#include <linux/slab.h>
#include <asm/iommu.h>
#include <asm/vio.h>
#include <asm/tce.h>
#include <asm/machdep.h>
#include <asm/abs_addr.h>
#include <asm/prom.h>
#include <asm/pci-bridge.h>
#include <asm/iseries/hv_call_xm.h>
#include <asm/iseries/hv_call_event.h>
#include <asm/iseries/iommu.h>
static int tce_build_iSeries(struct iommu_table *tbl, long index, long npages,
unsigned long uaddr, enum dma_data_direction direction,
struct dma_attrs *attrs)
{
u64 rc;
u64 tce, rpn;
while (npages--) {
rpn = virt_to_abs(uaddr) >> TCE_SHIFT;
tce = (rpn & TCE_RPN_MASK) << TCE_RPN_SHIFT;
if (tbl->it_type == TCE_VB) {
/* Virtual Bus */
tce |= TCE_VALID|TCE_ALLIO;
if (direction != DMA_TO_DEVICE)
tce |= TCE_VB_WRITE;
} else {
/* PCI Bus */
tce |= TCE_PCI_READ; /* Read allowed */
if (direction != DMA_TO_DEVICE)
tce |= TCE_PCI_WRITE;
}
rc = HvCallXm_setTce((u64)tbl->it_index, (u64)index, tce);
if (rc)
panic("PCI_DMA: HvCallXm_setTce failed, Rc: 0x%llx\n",
rc);
index++;
uaddr += TCE_PAGE_SIZE;
}
return 0;
}
static void tce_free_iSeries(struct iommu_table *tbl, long index, long npages)
{
u64 rc;
while (npages--) {
rc = HvCallXm_setTce((u64)tbl->it_index, (u64)index, 0);
if (rc)
panic("PCI_DMA: HvCallXm_setTce failed, Rc: 0x%llx\n",
rc);
index++;
}
}
/*
* Structure passed to HvCallXm_getTceTableParms
*/
struct iommu_table_cb {
unsigned long itc_busno; /* Bus number for this tce table */
unsigned long itc_start; /* Will be NULL for secondary */
unsigned long itc_totalsize; /* Size (in pages) of whole table */
unsigned long itc_offset; /* Index into real tce table of the
start of our section */
unsigned long itc_size; /* Size (in pages) of our section */
unsigned long itc_index; /* Index of this tce table */
unsigned short itc_maxtables; /* Max num of tables for partition */
unsigned char itc_virtbus; /* Flag to indicate virtual bus */
unsigned char itc_slotno; /* IOA Tce Slot Index */
unsigned char itc_rsvd[4];
};
/*
* Call Hv with the architected data structure to get TCE table info.
* info. Put the returned data into the Linux representation of the
* TCE table data.
* The Hardware Tce table comes in three flavors.
* 1. TCE table shared between Buses.
* 2. TCE table per Bus.
* 3. TCE Table per IOA.
*/
void iommu_table_getparms_iSeries(unsigned long busno,
unsigned char slotno,
unsigned char virtbus,
struct iommu_table* tbl)
{
struct iommu_table_cb *parms;
parms = kzalloc(sizeof(*parms), GFP_KERNEL);
if (parms == NULL)
panic("PCI_DMA: TCE Table Allocation failed.");
parms->itc_busno = busno;
parms->itc_slotno = slotno;
parms->itc_virtbus = virtbus;
HvCallXm_getTceTableParms(iseries_hv_addr(parms));
if (parms->itc_size == 0)
panic("PCI_DMA: parms->size is zero, parms is 0x%p", parms);
/* itc_size is in pages worth of table, it_size is in # of entries */
tbl->it_size = (parms->itc_size * TCE_PAGE_SIZE) / TCE_ENTRY_SIZE;
tbl->it_busno = parms->itc_busno;
tbl->it_offset = parms->itc_offset;
tbl->it_index = parms->itc_index;
tbl->it_blocksize = 1;
tbl->it_type = virtbus ? TCE_VB : TCE_PCI;
kfree(parms);
}
#ifdef CONFIG_PCI
/*
* This function compares the known tables to find an iommu_table
* that has already been built for hardware TCEs.
*/
static struct iommu_table *iommu_table_find(struct iommu_table * tbl)
{
struct device_node *node;
for (node = NULL; (node = of_find_all_nodes(node)); ) {
struct pci_dn *pdn = PCI_DN(node);
struct iommu_table *it;
if (pdn == NULL)
continue;
it = pdn->iommu_table;
if ((it != NULL) &&
(it->it_type == TCE_PCI) &&
(it->it_offset == tbl->it_offset) &&
(it->it_index == tbl->it_index) &&
(it->it_size == tbl->it_size)) {
of_node_put(node);
return it;
}
}
return NULL;
}
static void pci_dma_dev_setup_iseries(struct pci_dev *pdev)
{
struct iommu_table *tbl;
struct device_node *dn = pci_device_to_OF_node(pdev);
struct pci_dn *pdn = PCI_DN(dn);
const u32 *lsn = of_get_property(dn, "linux,logical-slot-number", NULL);
BUG_ON(lsn == NULL);
tbl = kzalloc(sizeof(struct iommu_table), GFP_KERNEL);
iommu_table_getparms_iSeries(pdn->busno, *lsn, 0, tbl);
/* Look for existing tce table */
pdn->iommu_table = iommu_table_find(tbl);
if (pdn->iommu_table == NULL)
pdn->iommu_table = iommu_init_table(tbl, -1);
else
kfree(tbl);
set_iommu_table_base(&pdev->dev, pdn->iommu_table);
}
#else
#define pci_dma_dev_setup_iseries NULL
#endif
static struct iommu_table veth_iommu_table;
static struct iommu_table vio_iommu_table;
void *iseries_hv_alloc(size_t size, dma_addr_t *dma_handle, gfp_t flag)
{
return iommu_alloc_coherent(NULL, &vio_iommu_table, size, dma_handle,
DMA_BIT_MASK(32), flag, -1);
}
EXPORT_SYMBOL_GPL(iseries_hv_alloc);
void iseries_hv_free(size_t size, void *vaddr, dma_addr_t dma_handle)
{
iommu_free_coherent(&vio_iommu_table, size, vaddr, dma_handle);
}
EXPORT_SYMBOL_GPL(iseries_hv_free);
dma_addr_t iseries_hv_map(void *vaddr, size_t size,
enum dma_data_direction direction)
{
return iommu_map_page(NULL, &vio_iommu_table, virt_to_page(vaddr),
(unsigned long)vaddr % PAGE_SIZE, size,
DMA_BIT_MASK(32), direction, NULL);
}
void iseries_hv_unmap(dma_addr_t dma_handle, size_t size,
enum dma_data_direction direction)
{
iommu_unmap_page(&vio_iommu_table, dma_handle, size, direction, NULL);
}
void __init iommu_vio_init(void)
{
iommu_table_getparms_iSeries(255, 0, 0xff, &veth_iommu_table);
veth_iommu_table.it_size /= 2;
vio_iommu_table = veth_iommu_table;
vio_iommu_table.it_offset += veth_iommu_table.it_size;
if (!iommu_init_table(&veth_iommu_table, -1))
printk("Virtual Bus VETH TCE table failed.\n");
if (!iommu_init_table(&vio_iommu_table, -1))
printk("Virtual Bus VIO TCE table failed.\n");
}
struct iommu_table *vio_build_iommu_table_iseries(struct vio_dev *dev)
{
if (strcmp(dev->type, "network") == 0)
return &veth_iommu_table;
return &vio_iommu_table;
}
void iommu_init_early_iSeries(void)
{
ppc_md.tce_build = tce_build_iSeries;
ppc_md.tce_free = tce_free_iSeries;
ppc_md.pci_dma_dev_setup = pci_dma_dev_setup_iseries;
set_pci_dma_ops(&dma_iommu_ops);
}