UbiquitousOS
/
OpenCloudOS-Kernel
mirror of https://gitee.com/OpenCloudOS/OpenCloudOS-Kernel.git
11
0
Fork 0
Code Issues Projects Releases Wiki Activity
OpenCloudOS-Kernel/arch/sparc/kernel/pci_schizo.c

1510 lines
48 KiB
C
Raw Normal View History

License cleanup: add SPDX GPL-2.0 license identifier to files with no license Many source files in the tree are missing licensing information, which makes it harder for compliance tools to determine the correct license. By default all files without license information are under the default license of the kernel, which is GPL version 2. Update the files which contain no license information with the 'GPL-2.0' SPDX license identifier. The SPDX identifier is a legally binding shorthand, which can be used instead of the full boiler plate text. This patch is based on work done by Thomas Gleixner and Kate Stewart and Philippe Ombredanne. How this work was done: Patches were generated and checked against linux-4.14-rc6 for a subset of the use cases: - file had no licensing information it it. - file was a */uapi/* one with no licensing information in it, - file was a */uapi/* one with existing licensing information, Further patches will be generated in subsequent months to fix up cases where non-standard license headers were used, and references to license had to be inferred by heuristics based on keywords. The analysis to determine which SPDX License Identifier to be applied to a file was done in a spreadsheet of side by side results from of the output of two independent scanners (ScanCode & Windriver) producing SPDX tag:value files created by Philippe Ombredanne. Philippe prepared the base worksheet, and did an initial spot review of a few 1000 files. The 4.13 kernel was the starting point of the analysis with 60,537 files assessed. Kate Stewart did a file by file comparison of the scanner results in the spreadsheet to determine which SPDX license identifier(s) to be applied to the file. She confirmed any determination that was not immediately clear with lawyers working with the Linux Foundation. Criteria used to select files for SPDX license identifier tagging was: - Files considered eligible had to be source code files. - Make and config files were included as candidates if they contained >5 lines of source - File already had some variant of a license header in it (even if <5 lines). All documentation files were explicitly excluded. The following heuristics were used to determine which SPDX license identifiers to apply. - when both scanners couldn't find any license traces, file was considered to have no license information in it, and the top level COPYING file license applied. For non */uapi/* files that summary was: SPDX license identifier # files ---------------------------------------------------|------- GPL-2.0 11139 and resulted in the first patch in this series. If that file was a */uapi/* path one, it was "GPL-2.0 WITH Linux-syscall-note" otherwise it was "GPL-2.0". Results of that was: SPDX license identifier # files ---------------------------------------------------|------- GPL-2.0 WITH Linux-syscall-note 930 and resulted in the second patch in this series. - if a file had some form of licensing information in it, and was one of the */uapi/* ones, it was denoted with the Linux-syscall-note if any GPL family license was found in the file or had no licensing in it (per prior point). Results summary: SPDX license identifier # files ---------------------------------------------------|------ GPL-2.0 WITH Linux-syscall-note 270 GPL-2.0+ WITH Linux-syscall-note 169 ((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) 21 ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) 17 LGPL-2.1+ WITH Linux-syscall-note 15 GPL-1.0+ WITH Linux-syscall-note 14 ((GPL-2.0+ WITH Linux-syscall-note) OR BSD-3-Clause) 5 LGPL-2.0+ WITH Linux-syscall-note 4 LGPL-2.1 WITH Linux-syscall-note 3 ((GPL-2.0 WITH Linux-syscall-note) OR MIT) 3 ((GPL-2.0 WITH Linux-syscall-note) AND MIT) 1 and that resulted in the third patch in this series. - when the two scanners agreed on the detected license(s), that became the concluded license(s). - when there was disagreement between the two scanners (one detected a license but the other didn't, or they both detected different licenses) a manual inspection of the file occurred. - In most cases a manual inspection of the information in the file resulted in a clear resolution of the license that should apply (and which scanner probably needed to revisit its heuristics). - When it was not immediately clear, the license identifier was confirmed with lawyers working with the Linux Foundation. - If there was any question as to the appropriate license identifier, the file was flagged for further research and to be revisited later in time. In total, over 70 hours of logged manual review was done on the spreadsheet to determine the SPDX license identifiers to apply to the source files by Kate, Philippe, Thomas and, in some cases, confirmation by lawyers working with the Linux Foundation. Kate also obtained a third independent scan of the 4.13 code base from FOSSology, and compared selected files where the other two scanners disagreed against that SPDX file, to see if there was new insights. The Windriver scanner is based on an older version of FOSSology in part, so they are related. Thomas did random spot checks in about 500 files from the spreadsheets for the uapi headers and agreed with SPDX license identifier in the files he inspected. For the non-uapi files Thomas did random spot checks in about 15000 files. In initial set of patches against 4.14-rc6, 3 files were found to have copy/paste license identifier errors, and have been fixed to reflect the correct identifier. Additionally Philippe spent 10 hours this week doing a detailed manual inspection and review of the 12,461 patched files from the initial patch version early this week with: - a full scancode scan run, collecting the matched texts, detected license ids and scores - reviewing anything where there was a license detected (about 500+ files) to ensure that the applied SPDX license was correct - reviewing anything where there was no detection but the patch license was not GPL-2.0 WITH Linux-syscall-note to ensure that the applied SPDX license was correct This produced a worksheet with 20 files needing minor correction. This worksheet was then exported into 3 different .csv files for the different types of files to be modified. These .csv files were then reviewed by Greg. Thomas wrote a script to parse the csv files and add the proper SPDX tag to the file, in the format that the file expected. This script was further refined by Greg based on the output to detect more types of files automatically and to distinguish between header and source .c files (which need different comment types.) Finally Greg ran the script using the .csv files to generate the patches. Reviewed-by: Kate Stewart <kstewart@linuxfoundation.org> Reviewed-by: Philippe Ombredanne <pombredanne@nexb.com> Reviewed-by: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2017-11-01 22:07:57 +08:00
// SPDX-License-Identifier: GPL-2.0
[SPARC64]: Consolidate PCI mem/io resource determination. It can be done for every PCI configuration using OF properties. Signed-off-by: David S. Miller <davem@davemloft.net>
2007-03-09 13:55:49 +08:00
/* pci_schizo.c: SCHIZO/TOMATILLO specific PCI controller support.
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
*
sparc64: Convert SCHIZO PCI controller driver into a real driver. The idea is to convert all of the PCI controller drivers into genuine OF drivers, then we can get rid of this terrible probing table and infrastructure in arch/sparc64/kernel/pci.c Signed-off-by: David S. Miller <davem@davemloft.net>
2008-08-30 17:30:24 +08:00
* Copyright (C) 2001, 2002, 2003, 2007, 2008 David S. Miller (davem@davemloft.net)
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
*/
#include <linux/kernel.h>
#include <linux/types.h>
#include <linux/pci.h>
#include <linux/init.h>
#include <linux/slab.h>
sparc: add export.h to arch/sparc files as required These files are only exporting symbols, so they don't need the full module.h header file. Previously they were getting access to EXPORT_SYMBOL implicitly via overuse of module.h from within other .h files, but that is being cleaned up. Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com>
2011-07-19 03:57:46 +08:00
#include <linux/export.h>
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
#include <linux/interrupt.h>
sparc: don't use asm/of_device.h Use linux/of_device.h instead. Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-08-08 06:33:36 +08:00
#include <linux/of_device.h>
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
#include <asm/iommu.h>
#include <asm/irq.h>
[SPARC64]: Do proper DMA IRQ syncing on Tomatillo This was the main impetus behind adding the PCI IRQ shim. In order to properly order DMA writes wrt. interrupts, you have to write to a PCI controller register, then poll for that bit clearing. There is one bit for each interrupt source, and setting this register bit tells Tomatillo to drain all pending DMA from that device. Furthermore, Tomatillo's with revision less than 4 require us to do a block store due to some memory transaction ordering issues it has on JBUS. Signed-off-by: David S. Miller <davem@davemloft.net>
2005-07-05 04:26:04 +08:00
#include <asm/pstate.h>
[SPARC64]: Use in-kernel OBP device tree for PCI controller probing. It can be pushed even further down, but this is a first step. Signed-off-by: David S. Miller <davem@davemloft.net>
2006-06-22 09:18:47 +08:00
#include <asm/prom.h>
sparc64: Kill hand-crafted I/O accessors in PCI controller drivers. Use existing upa_{read,write}q() interfaces instead. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-09-10 19:13:10 +08:00
#include <asm/upa.h>
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
#include "pci_impl.h"
#include "iommu_common.h"
sparc64: Convert SCHIZO PCI controller driver into a real driver. The idea is to convert all of the PCI controller drivers into genuine OF drivers, then we can get rid of this terrible probing table and infrastructure in arch/sparc64/kernel/pci.c Signed-off-by: David S. Miller <davem@davemloft.net>
2008-08-30 17:30:24 +08:00
#define DRIVER_NAME "schizo"
#define PFX DRIVER_NAME ": "
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
/* This is a convention that at least Excalibur and Merlin
* follow. I suppose the SCHIZO used in Starcat and friends
* will do similar.
*
* The only way I could see this changing is if the newlink
* block requires more space in Schizo's address space than
* they predicted, thus requiring an address space reorg when
* the newer Schizo is taped out.
*/
/* Streaming buffer control register. */
#define SCHIZO_STRBUF_CTRL_LPTR 0x00000000000000f0UL /* LRU Lock Pointer */
#define SCHIZO_STRBUF_CTRL_LENAB 0x0000000000000008UL /* LRU Lock Enable */
#define SCHIZO_STRBUF_CTRL_RRDIS 0x0000000000000004UL /* Rerun Disable */
#define SCHIZO_STRBUF_CTRL_DENAB 0x0000000000000002UL /* Diagnostic Mode Enable */
#define SCHIZO_STRBUF_CTRL_ENAB 0x0000000000000001UL /* Streaming Buffer Enable */
/* IOMMU control register. */
#define SCHIZO_IOMMU_CTRL_RESV 0xfffffffff9000000UL /* Reserved */
#define SCHIZO_IOMMU_CTRL_XLTESTAT 0x0000000006000000UL /* Translation Error Status */
#define SCHIZO_IOMMU_CTRL_XLTEERR 0x0000000001000000UL /* Translation Error encountered */
#define SCHIZO_IOMMU_CTRL_LCKEN 0x0000000000800000UL /* Enable translation locking */
#define SCHIZO_IOMMU_CTRL_LCKPTR 0x0000000000780000UL /* Translation lock pointer */
#define SCHIZO_IOMMU_CTRL_TSBSZ 0x0000000000070000UL /* TSB Size */
#define SCHIZO_IOMMU_TSBSZ_1K 0x0000000000000000UL /* TSB Table 1024 8-byte entries */
#define SCHIZO_IOMMU_TSBSZ_2K 0x0000000000010000UL /* TSB Table 2048 8-byte entries */
#define SCHIZO_IOMMU_TSBSZ_4K 0x0000000000020000UL /* TSB Table 4096 8-byte entries */
#define SCHIZO_IOMMU_TSBSZ_8K 0x0000000000030000UL /* TSB Table 8192 8-byte entries */
#define SCHIZO_IOMMU_TSBSZ_16K 0x0000000000040000UL /* TSB Table 16k 8-byte entries */
#define SCHIZO_IOMMU_TSBSZ_32K 0x0000000000050000UL /* TSB Table 32k 8-byte entries */
#define SCHIZO_IOMMU_TSBSZ_64K 0x0000000000060000UL /* TSB Table 64k 8-byte entries */
#define SCHIZO_IOMMU_TSBSZ_128K 0x0000000000070000UL /* TSB Table 128k 8-byte entries */
#define SCHIZO_IOMMU_CTRL_RESV2 0x000000000000fff8UL /* Reserved */
#define SCHIZO_IOMMU_CTRL_TBWSZ 0x0000000000000004UL /* Assumed page size, 0=8k 1=64k */
#define SCHIZO_IOMMU_CTRL_DENAB 0x0000000000000002UL /* Diagnostic mode enable */
#define SCHIZO_IOMMU_CTRL_ENAB 0x0000000000000001UL /* IOMMU Enable */
/* Schizo config space address format is nearly identical to
* that of PSYCHO:
*
* 32 24 23 16 15 11 10 8 7 2 1 0
* ---------------------------------------------------------
* |0 0 0 0 0 0 0 0 0| bus | device | function | reg | 0 0 |
* ---------------------------------------------------------
*/
#define SCHIZO_CONFIG_BASE(PBM) ((PBM)->config_space)
#define SCHIZO_CONFIG_ENCODE(BUS, DEVFN, REG) \
(((unsigned long)(BUS) << 16) | \
((unsigned long)(DEVFN) << 8) | \
((unsigned long)(REG)))
static void *schizo_pci_config_mkaddr(struct pci_pbm_info *pbm,
unsigned char bus,
unsigned int devfn,
int where)
{
if (!pbm)
return NULL;
bus -= pbm->pci_first_busno;
return (void *)
(SCHIZO_CONFIG_BASE(pbm) |
SCHIZO_CONFIG_ENCODE(bus, devfn, where));
}
/* SCHIZO error handling support. */
enum schizo_error_type {
UE_ERR, CE_ERR, PCI_ERR, SAFARI_ERR
};
static DEFINE_SPINLOCK(stc_buf_lock);
static unsigned long stc_error_buf[128];
static unsigned long stc_tag_buf[16];
static unsigned long stc_line_buf[16];
#define SCHIZO_UE_INO 0x30 /* Uncorrectable ECC error */
#define SCHIZO_CE_INO 0x31 /* Correctable ECC error */
#define SCHIZO_PCIERR_A_INO 0x32 /* PBM A PCI bus error */
#define SCHIZO_PCIERR_B_INO 0x33 /* PBM B PCI bus error */
#define SCHIZO_SERR_INO 0x34 /* Safari interface error */
#define SCHIZO_STC_ERR 0xb800UL /* --> 0xba00 */
#define SCHIZO_STC_TAG 0xba00UL /* --> 0xba80 */
#define SCHIZO_STC_LINE 0xbb00UL /* --> 0xbb80 */
#define SCHIZO_STCERR_WRITE 0x2UL
#define SCHIZO_STCERR_READ 0x1UL
#define SCHIZO_STCTAG_PPN 0x3fffffff00000000UL
#define SCHIZO_STCTAG_VPN 0x00000000ffffe000UL
#define SCHIZO_STCTAG_VALID 0x8000000000000000UL
#define SCHIZO_STCTAG_READ 0x4000000000000000UL
#define SCHIZO_STCLINE_LINDX 0x0000000007800000UL
#define SCHIZO_STCLINE_SPTR 0x000000000007e000UL
#define SCHIZO_STCLINE_LADDR 0x0000000000001fc0UL
#define SCHIZO_STCLINE_EPTR 0x000000000000003fUL
#define SCHIZO_STCLINE_VALID 0x0000000000600000UL
#define SCHIZO_STCLINE_FOFN 0x0000000000180000UL
static void __schizo_check_stc_error_pbm(struct pci_pbm_info *pbm,
enum schizo_error_type type)
{
[SPARC64]: Convert PCI over to generic struct iommu/strbuf. Signed-off-by: David S. Miller <davem@davemloft.net>
2007-04-27 12:08:21 +08:00
struct strbuf *strbuf = &pbm->stc;
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
unsigned long regbase = pbm->pbm_regs;
unsigned long err_base, tag_base, line_base;
u64 control;
int i;
err_base = regbase + SCHIZO_STC_ERR;
tag_base = regbase + SCHIZO_STC_TAG;
line_base = regbase + SCHIZO_STC_LINE;
spin_lock(&stc_buf_lock);
/* This is __REALLY__ dangerous. When we put the
* streaming buffer into diagnostic mode to probe
* it's tags and error status, we _must_ clear all
* of the line tag valid bits before re-enabling
* the streaming buffer. If any dirty data lives
* in the STC when we do this, we will end up
* invalidating it before it has a chance to reach
* main memory.
*/
sparc64: Kill hand-crafted I/O accessors in PCI controller drivers. Use existing upa_{read,write}q() interfaces instead. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-09-10 19:13:10 +08:00
control = upa_readq(strbuf->strbuf_control);
upa_writeq((control | SCHIZO_STRBUF_CTRL_DENAB),
strbuf->strbuf_control);
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
for (i = 0; i < 128; i++) {
unsigned long val;
sparc64: Kill hand-crafted I/O accessors in PCI controller drivers. Use existing upa_{read,write}q() interfaces instead. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-09-10 19:13:10 +08:00
val = upa_readq(err_base + (i * 8UL));
upa_writeq(0UL, err_base + (i * 8UL));
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
stc_error_buf[i] = val;
}
for (i = 0; i < 16; i++) {
sparc64: Kill hand-crafted I/O accessors in PCI controller drivers. Use existing upa_{read,write}q() interfaces instead. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-09-10 19:13:10 +08:00
stc_tag_buf[i] = upa_readq(tag_base + (i * 8UL));
stc_line_buf[i] = upa_readq(line_base + (i * 8UL));
upa_writeq(0UL, tag_base + (i * 8UL));
upa_writeq(0UL, line_base + (i * 8UL));
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
}
/* OK, state is logged, exit diagnostic mode. */
sparc64: Kill hand-crafted I/O accessors in PCI controller drivers. Use existing upa_{read,write}q() interfaces instead. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-09-10 19:13:10 +08:00
upa_writeq(control, strbuf->strbuf_control);
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
for (i = 0; i < 16; i++) {
int j, saw_error, first, last;
saw_error = 0;
first = i * 8;
last = first + 8;
for (j = first; j < last; j++) {
unsigned long errval = stc_error_buf[j];
if (errval != 0) {
saw_error++;
printk("%s: STC_ERR(%d)[wr(%d)rd(%d)]\n",
pbm->name,
j,
(errval & SCHIZO_STCERR_WRITE) ? 1 : 0,
(errval & SCHIZO_STCERR_READ) ? 1 : 0);
}
}
if (saw_error != 0) {
unsigned long tagval = stc_tag_buf[i];
unsigned long lineval = stc_line_buf[i];
printk("%s: STC_TAG(%d)[PA(%016lx)VA(%08lx)V(%d)R(%d)]\n",
pbm->name,
i,
((tagval & SCHIZO_STCTAG_PPN) >> 19UL),
(tagval & SCHIZO_STCTAG_VPN),
((tagval & SCHIZO_STCTAG_VALID) ? 1 : 0),
((tagval & SCHIZO_STCTAG_READ) ? 1 : 0));
/* XXX Should spit out per-bank error information... -DaveM */
printk("%s: STC_LINE(%d)[LIDX(%lx)SP(%lx)LADDR(%lx)EP(%lx)"
"V(%d)FOFN(%d)]\n",
pbm->name,
i,
((lineval & SCHIZO_STCLINE_LINDX) >> 23UL),
((lineval & SCHIZO_STCLINE_SPTR) >> 13UL),
((lineval & SCHIZO_STCLINE_LADDR) >> 6UL),
((lineval & SCHIZO_STCLINE_EPTR) >> 0UL),
((lineval & SCHIZO_STCLINE_VALID) ? 1 : 0),
((lineval & SCHIZO_STCLINE_FOFN) ? 1 : 0));
}
}
spin_unlock(&stc_buf_lock);
}
/* IOMMU is per-PBM in Schizo, so interrogate both for anonymous
* controller level errors.
*/
#define SCHIZO_IOMMU_TAG 0xa580UL
#define SCHIZO_IOMMU_DATA 0xa600UL
#define SCHIZO_IOMMU_TAG_CTXT 0x0000001ffe000000UL
#define SCHIZO_IOMMU_TAG_ERRSTS 0x0000000001800000UL
#define SCHIZO_IOMMU_TAG_ERR 0x0000000000400000UL
#define SCHIZO_IOMMU_TAG_WRITE 0x0000000000200000UL
#define SCHIZO_IOMMU_TAG_STREAM 0x0000000000100000UL
#define SCHIZO_IOMMU_TAG_SIZE 0x0000000000080000UL
#define SCHIZO_IOMMU_TAG_VPAGE 0x000000000007ffffUL
#define SCHIZO_IOMMU_DATA_VALID 0x0000000100000000UL
#define SCHIZO_IOMMU_DATA_CACHE 0x0000000040000000UL
#define SCHIZO_IOMMU_DATA_PPAGE 0x000000003fffffffUL
static void schizo_check_iommu_error_pbm(struct pci_pbm_info *pbm,
enum schizo_error_type type)
{
[SPARC64]: Convert PCI over to generic struct iommu/strbuf. Signed-off-by: David S. Miller <davem@davemloft.net>
2007-04-27 12:08:21 +08:00
struct iommu *iommu = pbm->iommu;
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
unsigned long iommu_tag[16];
unsigned long iommu_data[16];
unsigned long flags;
u64 control;
int i;
spin_lock_irqsave(&iommu->lock, flags);
sparc64: Kill hand-crafted I/O accessors in PCI controller drivers. Use existing upa_{read,write}q() interfaces instead. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-09-10 19:13:10 +08:00
control = upa_readq(iommu->iommu_control);
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
if (control & SCHIZO_IOMMU_CTRL_XLTEERR) {
unsigned long base;
char *type_string;
/* Clear the error encountered bit. */
control &= ~SCHIZO_IOMMU_CTRL_XLTEERR;
sparc64: Kill hand-crafted I/O accessors in PCI controller drivers. Use existing upa_{read,write}q() interfaces instead. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-09-10 19:13:10 +08:00
upa_writeq(control, iommu->iommu_control);
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
switch((control & SCHIZO_IOMMU_CTRL_XLTESTAT) >> 25UL) {
case 0:
type_string = "Protection Error";
break;
case 1:
type_string = "Invalid Error";
break;
case 2:
type_string = "TimeOut Error";
break;
case 3:
default:
type_string = "ECC Error";
break;
sparc: Remove unnecessary semicolons Semicolons are not necessary after switch/while/for/if braces so remove them. Signed-off-by: Joe Perches <joe@perches.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2011-06-03 22:45:23 +08:00
}
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
printk("%s: IOMMU Error, type[%s]\n",
pbm->name, type_string);
/* Put the IOMMU into diagnostic mode and probe
* it's TLB for entries with error status.
*
* It is very possible for another DVMA to occur
* while we do this probe, and corrupt the system
* further. But we are so screwed at this point
* that we are likely to crash hard anyways, so
* get as much diagnostic information to the
* console as we can.
*/
sparc64: Kill hand-crafted I/O accessors in PCI controller drivers. Use existing upa_{read,write}q() interfaces instead. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-09-10 19:13:10 +08:00
upa_writeq(control | SCHIZO_IOMMU_CTRL_DENAB,
iommu->iommu_control);
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
base = pbm->pbm_regs;
for (i = 0; i < 16; i++) {
iommu_tag[i] =
sparc64: Kill hand-crafted I/O accessors in PCI controller drivers. Use existing upa_{read,write}q() interfaces instead. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-09-10 19:13:10 +08:00
upa_readq(base + SCHIZO_IOMMU_TAG + (i * 8UL));
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
iommu_data[i] =
sparc64: Kill hand-crafted I/O accessors in PCI controller drivers. Use existing upa_{read,write}q() interfaces instead. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-09-10 19:13:10 +08:00
upa_readq(base + SCHIZO_IOMMU_DATA + (i * 8UL));
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
/* Now clear out the entry. */
sparc64: Kill hand-crafted I/O accessors in PCI controller drivers. Use existing upa_{read,write}q() interfaces instead. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-09-10 19:13:10 +08:00
upa_writeq(0, base + SCHIZO_IOMMU_TAG + (i * 8UL));
upa_writeq(0, base + SCHIZO_IOMMU_DATA + (i * 8UL));
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
}
/* Leave diagnostic mode. */
sparc64: Kill hand-crafted I/O accessors in PCI controller drivers. Use existing upa_{read,write}q() interfaces instead. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-09-10 19:13:10 +08:00
upa_writeq(control, iommu->iommu_control);
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
for (i = 0; i < 16; i++) {
unsigned long tag, data;
tag = iommu_tag[i];
if (!(tag & SCHIZO_IOMMU_TAG_ERR))
continue;
data = iommu_data[i];
switch((tag & SCHIZO_IOMMU_TAG_ERRSTS) >> 23UL) {
case 0:
type_string = "Protection Error";
break;
case 1:
type_string = "Invalid Error";
break;
case 2:
type_string = "TimeOut Error";
break;
case 3:
default:
type_string = "ECC Error";
break;
sparc: Remove unnecessary semicolons Semicolons are not necessary after switch/while/for/if braces so remove them. Signed-off-by: Joe Perches <joe@perches.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2011-06-03 22:45:23 +08:00
}
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
printk("%s: IOMMU TAG(%d)[error(%s) ctx(%x) wr(%d) str(%d) "
"sz(%dK) vpg(%08lx)]\n",
pbm->name, i, type_string,
(int)((tag & SCHIZO_IOMMU_TAG_CTXT) >> 25UL),
((tag & SCHIZO_IOMMU_TAG_WRITE) ? 1 : 0),
((tag & SCHIZO_IOMMU_TAG_STREAM) ? 1 : 0),
((tag & SCHIZO_IOMMU_TAG_SIZE) ? 64 : 8),
(tag & SCHIZO_IOMMU_TAG_VPAGE) << IOMMU_PAGE_SHIFT);
printk("%s: IOMMU DATA(%d)[valid(%d) cache(%d) ppg(%016lx)]\n",
pbm->name, i,
((data & SCHIZO_IOMMU_DATA_VALID) ? 1 : 0),
((data & SCHIZO_IOMMU_DATA_CACHE) ? 1 : 0),
(data & SCHIZO_IOMMU_DATA_PPAGE) << IOMMU_PAGE_SHIFT);
}
}
if (pbm->stc.strbuf_enabled)
__schizo_check_stc_error_pbm(pbm, type);
spin_unlock_irqrestore(&iommu->lock, flags);
}
sparc64: Get rid of pci_controller_info. It is just used as a parent to encapsulate two PBM objects. But that layout is only really relevant and necessary for psycho PCI controllers, which unlike all the others share a single IOMMU instance between sibling PCI busses. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-09-10 14:54:02 +08:00
static void schizo_check_iommu_error(struct pci_pbm_info *pbm,
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
enum schizo_error_type type)
{
sparc64: Get rid of pci_controller_info. It is just used as a parent to encapsulate two PBM objects. But that layout is only really relevant and necessary for psycho PCI controllers, which unlike all the others share a single IOMMU instance between sibling PCI busses. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-09-10 14:54:02 +08:00
schizo_check_iommu_error_pbm(pbm, type);
if (pbm->sibling)
schizo_check_iommu_error_pbm(pbm->sibling, type);
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
}
/* Uncorrectable ECC error status gathering. */
#define SCHIZO_UE_AFSR 0x10030UL
#define SCHIZO_UE_AFAR 0x10038UL
#define SCHIZO_UEAFSR_PPIO 0x8000000000000000UL /* Safari */
#define SCHIZO_UEAFSR_PDRD 0x4000000000000000UL /* Safari/Tomatillo */
#define SCHIZO_UEAFSR_PDWR 0x2000000000000000UL /* Safari */
#define SCHIZO_UEAFSR_SPIO 0x1000000000000000UL /* Safari */
#define SCHIZO_UEAFSR_SDMA 0x0800000000000000UL /* Safari/Tomatillo */
#define SCHIZO_UEAFSR_ERRPNDG 0x0300000000000000UL /* Safari */
#define SCHIZO_UEAFSR_BMSK 0x000003ff00000000UL /* Safari */
#define SCHIZO_UEAFSR_QOFF 0x00000000c0000000UL /* Safari/Tomatillo */
#define SCHIZO_UEAFSR_AID 0x000000001f000000UL /* Safari/Tomatillo */
#define SCHIZO_UEAFSR_PARTIAL 0x0000000000800000UL /* Safari */
#define SCHIZO_UEAFSR_OWNEDIN 0x0000000000400000UL /* Safari */
#define SCHIZO_UEAFSR_MTAGSYND 0x00000000000f0000UL /* Safari */
#define SCHIZO_UEAFSR_MTAG 0x000000000000e000UL /* Safari */
#define SCHIZO_UEAFSR_ECCSYND 0x00000000000001ffUL /* Safari */
[PATCH] sparc64 pt_regs fixes Signed-off-by: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-10-08 20:23:28 +08:00
static irqreturn_t schizo_ue_intr(int irq, void *dev_id)
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
{
[SPARC64] PCI: Use root list of pbm's instead of pci_controller_info's The idea is to move more and more things into the pbm, with the eventual goal of eliminating the pci_controller_info entirely as there really isn't any need for it. This stage of the transformations requires some reworking of the PCI error interrupt handling. It might be tricky to get rid of the pci_controller_info parenting for a few reasons: 1) When we get an uncorrectable or correctable error we want to interrogate the IOMMU and streaming cache of both PBMs for error status. These errors come from the UPA front-end which is shared between the two PBM PCI bus segments. Historically speaking this is why I choose the datastructure hierarchy of pci_controller_info-->pci_pbm_info 2) The probing does a portid/devhandle match to look for the 'other' pbm, but this is entirely an artifact and can be eliminated trivially. What we could do to solve #1 is to have a "buddy" pointer from one pbm to another. Signed-off-by: David S. Miller <davem@davemloft.net>
2007-05-08 14:06:27 +08:00
struct pci_pbm_info *pbm = dev_id;
unsigned long afsr_reg = pbm->controller_regs + SCHIZO_UE_AFSR;
unsigned long afar_reg = pbm->controller_regs + SCHIZO_UE_AFAR;
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
unsigned long afsr, afar, error_bits;
int reported, limit;
/* Latch uncorrectable error status. */
sparc64: Kill hand-crafted I/O accessors in PCI controller drivers. Use existing upa_{read,write}q() interfaces instead. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-09-10 19:13:10 +08:00
afar = upa_readq(afar_reg);
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
/* If either of the error pending bits are set in the
* AFSR, the error status is being actively updated by
* the hardware and we must re-read to get a clean value.
*/
limit = 1000;
do {
sparc64: Kill hand-crafted I/O accessors in PCI controller drivers. Use existing upa_{read,write}q() interfaces instead. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-09-10 19:13:10 +08:00
afsr = upa_readq(afsr_reg);
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
} while ((afsr & SCHIZO_UEAFSR_ERRPNDG) != 0 && --limit);
/* Clear the primary/secondary error status bits. */
error_bits = afsr &
(SCHIZO_UEAFSR_PPIO | SCHIZO_UEAFSR_PDRD | SCHIZO_UEAFSR_PDWR |
SCHIZO_UEAFSR_SPIO | SCHIZO_UEAFSR_SDMA);
if (!error_bits)
return IRQ_NONE;
sparc64: Kill hand-crafted I/O accessors in PCI controller drivers. Use existing upa_{read,write}q() interfaces instead. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-09-10 19:13:10 +08:00
upa_writeq(error_bits, afsr_reg);
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
/* Log the error. */
[SPARC64]: Move index info pci_pbm_info. Signed-off-by: David S. Miller <davem@davemloft.net>
2007-05-08 14:49:01 +08:00
printk("%s: Uncorrectable Error, primary error type[%s]\n",
pbm->name,
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
(((error_bits & SCHIZO_UEAFSR_PPIO) ?
"PIO" :
((error_bits & SCHIZO_UEAFSR_PDRD) ?
"DMA Read" :
((error_bits & SCHIZO_UEAFSR_PDWR) ?
"DMA Write" : "???")))));
[SPARC64]: Move index info pci_pbm_info. Signed-off-by: David S. Miller <davem@davemloft.net>
2007-05-08 14:49:01 +08:00
printk("%s: bytemask[%04lx] qword_offset[%lx] SAFARI_AID[%02lx]\n",
pbm->name,
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
(afsr & SCHIZO_UEAFSR_BMSK) >> 32UL,
(afsr & SCHIZO_UEAFSR_QOFF) >> 30UL,
(afsr & SCHIZO_UEAFSR_AID) >> 24UL);
[SPARC64]: Move index info pci_pbm_info. Signed-off-by: David S. Miller <davem@davemloft.net>
2007-05-08 14:49:01 +08:00
printk("%s: partial[%d] owned_in[%d] mtag[%lx] mtag_synd[%lx] ecc_sync[%lx]\n",
pbm->name,
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
(afsr & SCHIZO_UEAFSR_PARTIAL) ? 1 : 0,
(afsr & SCHIZO_UEAFSR_OWNEDIN) ? 1 : 0,
(afsr & SCHIZO_UEAFSR_MTAG) >> 13UL,
(afsr & SCHIZO_UEAFSR_MTAGSYND) >> 16UL,
(afsr & SCHIZO_UEAFSR_ECCSYND) >> 0UL);
[SPARC64]: Move index info pci_pbm_info. Signed-off-by: David S. Miller <davem@davemloft.net>
2007-05-08 14:49:01 +08:00
printk("%s: UE AFAR [%016lx]\n", pbm->name, afar);
printk("%s: UE Secondary errors [", pbm->name);
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
reported = 0;
if (afsr & SCHIZO_UEAFSR_SPIO) {
reported++;
printk("(PIO)");
}
if (afsr & SCHIZO_UEAFSR_SDMA) {
reported++;
printk("(DMA)");
}
if (!reported)
printk("(none)");
printk("]\n");
/* Interrogate IOMMU for error status. */
sparc64: Get rid of pci_controller_info. It is just used as a parent to encapsulate two PBM objects. But that layout is only really relevant and necessary for psycho PCI controllers, which unlike all the others share a single IOMMU instance between sibling PCI busses. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-09-10 14:54:02 +08:00
schizo_check_iommu_error(pbm, UE_ERR);
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
return IRQ_HANDLED;
}
#define SCHIZO_CE_AFSR 0x10040UL
#define SCHIZO_CE_AFAR 0x10048UL
#define SCHIZO_CEAFSR_PPIO 0x8000000000000000UL
#define SCHIZO_CEAFSR_PDRD 0x4000000000000000UL
#define SCHIZO_CEAFSR_PDWR 0x2000000000000000UL
#define SCHIZO_CEAFSR_SPIO 0x1000000000000000UL
#define SCHIZO_CEAFSR_SDMA 0x0800000000000000UL
#define SCHIZO_CEAFSR_ERRPNDG 0x0300000000000000UL
#define SCHIZO_CEAFSR_BMSK 0x000003ff00000000UL
#define SCHIZO_CEAFSR_QOFF 0x00000000c0000000UL
#define SCHIZO_CEAFSR_AID 0x000000001f000000UL
#define SCHIZO_CEAFSR_PARTIAL 0x0000000000800000UL
#define SCHIZO_CEAFSR_OWNEDIN 0x0000000000400000UL
#define SCHIZO_CEAFSR_MTAGSYND 0x00000000000f0000UL
#define SCHIZO_CEAFSR_MTAG 0x000000000000e000UL
#define SCHIZO_CEAFSR_ECCSYND 0x00000000000001ffUL
[PATCH] sparc64 pt_regs fixes Signed-off-by: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-10-08 20:23:28 +08:00
static irqreturn_t schizo_ce_intr(int irq, void *dev_id)
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
{
[SPARC64] PCI: Use root list of pbm's instead of pci_controller_info's The idea is to move more and more things into the pbm, with the eventual goal of eliminating the pci_controller_info entirely as there really isn't any need for it. This stage of the transformations requires some reworking of the PCI error interrupt handling. It might be tricky to get rid of the pci_controller_info parenting for a few reasons: 1) When we get an uncorrectable or correctable error we want to interrogate the IOMMU and streaming cache of both PBMs for error status. These errors come from the UPA front-end which is shared between the two PBM PCI bus segments. Historically speaking this is why I choose the datastructure hierarchy of pci_controller_info-->pci_pbm_info 2) The probing does a portid/devhandle match to look for the 'other' pbm, but this is entirely an artifact and can be eliminated trivially. What we could do to solve #1 is to have a "buddy" pointer from one pbm to another. Signed-off-by: David S. Miller <davem@davemloft.net>
2007-05-08 14:06:27 +08:00
struct pci_pbm_info *pbm = dev_id;
unsigned long afsr_reg = pbm->controller_regs + SCHIZO_CE_AFSR;
unsigned long afar_reg = pbm->controller_regs + SCHIZO_CE_AFAR;
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
unsigned long afsr, afar, error_bits;
int reported, limit;
/* Latch error status. */
sparc64: Kill hand-crafted I/O accessors in PCI controller drivers. Use existing upa_{read,write}q() interfaces instead. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-09-10 19:13:10 +08:00
afar = upa_readq(afar_reg);
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
/* If either of the error pending bits are set in the
* AFSR, the error status is being actively updated by
* the hardware and we must re-read to get a clean value.
*/
limit = 1000;
do {
sparc64: Kill hand-crafted I/O accessors in PCI controller drivers. Use existing upa_{read,write}q() interfaces instead. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-09-10 19:13:10 +08:00
afsr = upa_readq(afsr_reg);
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
} while ((afsr & SCHIZO_UEAFSR_ERRPNDG) != 0 && --limit);
/* Clear primary/secondary error status bits. */
error_bits = afsr &
(SCHIZO_CEAFSR_PPIO | SCHIZO_CEAFSR_PDRD | SCHIZO_CEAFSR_PDWR |
SCHIZO_CEAFSR_SPIO | SCHIZO_CEAFSR_SDMA);
if (!error_bits)
return IRQ_NONE;
sparc64: Kill hand-crafted I/O accessors in PCI controller drivers. Use existing upa_{read,write}q() interfaces instead. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-09-10 19:13:10 +08:00
upa_writeq(error_bits, afsr_reg);
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
/* Log the error. */
[SPARC64]: Move index info pci_pbm_info. Signed-off-by: David S. Miller <davem@davemloft.net>
2007-05-08 14:49:01 +08:00
printk("%s: Correctable Error, primary error type[%s]\n",
pbm->name,
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
(((error_bits & SCHIZO_CEAFSR_PPIO) ?
"PIO" :
((error_bits & SCHIZO_CEAFSR_PDRD) ?
"DMA Read" :
((error_bits & SCHIZO_CEAFSR_PDWR) ?
"DMA Write" : "???")))));
/* XXX Use syndrome and afar to print out module string just like
* XXX UDB CE trap handler does... -DaveM
*/
[SPARC64]: Move index info pci_pbm_info. Signed-off-by: David S. Miller <davem@davemloft.net>
2007-05-08 14:49:01 +08:00
printk("%s: bytemask[%04lx] qword_offset[%lx] SAFARI_AID[%02lx]\n",
pbm->name,
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
(afsr & SCHIZO_UEAFSR_BMSK) >> 32UL,
(afsr & SCHIZO_UEAFSR_QOFF) >> 30UL,
(afsr & SCHIZO_UEAFSR_AID) >> 24UL);
[SPARC64]: Move index info pci_pbm_info. Signed-off-by: David S. Miller <davem@davemloft.net>
2007-05-08 14:49:01 +08:00
printk("%s: partial[%d] owned_in[%d] mtag[%lx] mtag_synd[%lx] ecc_sync[%lx]\n",
pbm->name,
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
(afsr & SCHIZO_UEAFSR_PARTIAL) ? 1 : 0,
(afsr & SCHIZO_UEAFSR_OWNEDIN) ? 1 : 0,
(afsr & SCHIZO_UEAFSR_MTAG) >> 13UL,
(afsr & SCHIZO_UEAFSR_MTAGSYND) >> 16UL,
(afsr & SCHIZO_UEAFSR_ECCSYND) >> 0UL);
[SPARC64]: Move index info pci_pbm_info. Signed-off-by: David S. Miller <davem@davemloft.net>
2007-05-08 14:49:01 +08:00
printk("%s: CE AFAR [%016lx]\n", pbm->name, afar);
printk("%s: CE Secondary errors [", pbm->name);
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
reported = 0;
if (afsr & SCHIZO_CEAFSR_SPIO) {
reported++;
printk("(PIO)");
}
if (afsr & SCHIZO_CEAFSR_SDMA) {
reported++;
printk("(DMA)");
}
if (!reported)
printk("(none)");
printk("]\n");
return IRQ_HANDLED;
}
#define SCHIZO_PCI_AFSR 0x2010UL
#define SCHIZO_PCI_AFAR 0x2018UL
#define SCHIZO_PCIAFSR_PMA 0x8000000000000000UL /* Schizo/Tomatillo */
#define SCHIZO_PCIAFSR_PTA 0x4000000000000000UL /* Schizo/Tomatillo */
#define SCHIZO_PCIAFSR_PRTRY 0x2000000000000000UL /* Schizo/Tomatillo */
#define SCHIZO_PCIAFSR_PPERR 0x1000000000000000UL /* Schizo/Tomatillo */
#define SCHIZO_PCIAFSR_PTTO 0x0800000000000000UL /* Schizo/Tomatillo */
#define SCHIZO_PCIAFSR_PUNUS 0x0400000000000000UL /* Schizo */
#define SCHIZO_PCIAFSR_SMA 0x0200000000000000UL /* Schizo/Tomatillo */
#define SCHIZO_PCIAFSR_STA 0x0100000000000000UL /* Schizo/Tomatillo */
#define SCHIZO_PCIAFSR_SRTRY 0x0080000000000000UL /* Schizo/Tomatillo */
#define SCHIZO_PCIAFSR_SPERR 0x0040000000000000UL /* Schizo/Tomatillo */
#define SCHIZO_PCIAFSR_STTO 0x0020000000000000UL /* Schizo/Tomatillo */
#define SCHIZO_PCIAFSR_SUNUS 0x0010000000000000UL /* Schizo */
#define SCHIZO_PCIAFSR_BMSK 0x000003ff00000000UL /* Schizo/Tomatillo */
#define SCHIZO_PCIAFSR_BLK 0x0000000080000000UL /* Schizo/Tomatillo */
#define SCHIZO_PCIAFSR_CFG 0x0000000040000000UL /* Schizo/Tomatillo */
#define SCHIZO_PCIAFSR_MEM 0x0000000020000000UL /* Schizo/Tomatillo */
#define SCHIZO_PCIAFSR_IO 0x0000000010000000UL /* Schizo/Tomatillo */
#define SCHIZO_PCI_CTRL (0x2000UL)
#define SCHIZO_PCICTRL_BUS_UNUS (1UL << 63UL) /* Safari */
[SPARC64]: Small Schizo PCI controller programming tweaks. Use macro instead of magic value for Tomatillo discard- timeout interrupt enable register bit. Leave OBP programming PTO value unless Tomatillo and version >= 0x2. If no-bus-parking property is present, explicitly clear PCICTRL_PARK bit. Signed-off-by: David S. Miller <davem@davemloft.net>
2005-07-05 05:53:33 +08:00
#define SCHIZO_PCICTRL_DTO_INT (1UL << 61UL) /* Tomatillo */
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
#define SCHIZO_PCICTRL_ARB_PRIO (0x1ff << 52UL) /* Tomatillo */
#define SCHIZO_PCICTRL_ESLCK (1UL << 51UL) /* Safari */
#define SCHIZO_PCICTRL_ERRSLOT (7UL << 48UL) /* Safari */
#define SCHIZO_PCICTRL_TTO_ERR (1UL << 38UL) /* Safari/Tomatillo */
#define SCHIZO_PCICTRL_RTRY_ERR (1UL << 37UL) /* Safari/Tomatillo */
#define SCHIZO_PCICTRL_DTO_ERR (1UL << 36UL) /* Safari/Tomatillo */
#define SCHIZO_PCICTRL_SBH_ERR (1UL << 35UL) /* Safari */
#define SCHIZO_PCICTRL_SERR (1UL << 34UL) /* Safari/Tomatillo */
#define SCHIZO_PCICTRL_PCISPD (1UL << 33UL) /* Safari */
#define SCHIZO_PCICTRL_MRM_PREF (1UL << 30UL) /* Tomatillo */
#define SCHIZO_PCICTRL_RDO_PREF (1UL << 29UL) /* Tomatillo */
#define SCHIZO_PCICTRL_RDL_PREF (1UL << 28UL) /* Tomatillo */
#define SCHIZO_PCICTRL_PTO (3UL << 24UL) /* Safari/Tomatillo */
#define SCHIZO_PCICTRL_PTO_SHIFT 24UL
#define SCHIZO_PCICTRL_TRWSW (7UL << 21UL) /* Tomatillo */
#define SCHIZO_PCICTRL_F_TGT_A (1UL << 20UL) /* Tomatillo */
#define SCHIZO_PCICTRL_S_DTO_INT (1UL << 19UL) /* Safari */
#define SCHIZO_PCICTRL_F_TGT_RT (1UL << 19UL) /* Tomatillo */
#define SCHIZO_PCICTRL_SBH_INT (1UL << 18UL) /* Safari */
#define SCHIZO_PCICTRL_T_DTO_INT (1UL << 18UL) /* Tomatillo */
#define SCHIZO_PCICTRL_EEN (1UL << 17UL) /* Safari/Tomatillo */
#define SCHIZO_PCICTRL_PARK (1UL << 16UL) /* Safari/Tomatillo */
#define SCHIZO_PCICTRL_PCIRST (1UL << 8UL) /* Safari */
#define SCHIZO_PCICTRL_ARB_S (0x3fUL << 0UL) /* Safari */
#define SCHIZO_PCICTRL_ARB_T (0xffUL << 0UL) /* Tomatillo */
static irqreturn_t schizo_pcierr_intr_other(struct pci_pbm_info *pbm)
{
unsigned long csr_reg, csr, csr_error_bits;
irqreturn_t ret = IRQ_NONE;
sparc64: Fix crashes in schizo_pcierr_intr_other(). Meelis Roos reports crashes during bootup on a V480 that look like this: ==================== [ 61.300577] PCI: Scanning PBM /pci@9,600000 [ 61.304867] schizo f009b070: PCI host bridge to bus 0003:00 [ 61.310385] pci_bus 0003:00: root bus resource [io 0x7ffe9000000-0x7ffe9ffffff] (bus address [0x0000-0xffffff]) [ 61.320515] pci_bus 0003:00: root bus resource [mem 0x7fb00000000-0x7fbffffffff] (bus address [0x00000000-0xffffffff]) [ 61.331173] pci_bus 0003:00: root bus resource [bus 00] [ 61.385344] Unable to handle kernel NULL pointer dereference [ 61.390970] tsk->{mm,active_mm}->context = 0000000000000000 [ 61.396515] tsk->{mm,active_mm}->pgd = fff000b000002000 [ 61.401716] \|/ ____ \|/ [ 61.401716] "@'/ .. \`@" [ 61.401716] /_| \__/ |_\ [ 61.401716] \__U_/ [ 61.416362] swapper/0(0): Oops [#1] [ 61.419837] CPU: 0 PID: 0 Comm: swapper/0 Not tainted 3.18.0-rc1-00422-g2cc9188-dirty #24 [ 61.427975] task: fff000b0fd8e9c40 ti: fff000b0fd928000 task.ti: fff000b0fd928000 [ 61.435426] TSTATE: 0000004480e01602 TPC: 00000000004455e4 TNPC: 00000000004455e8 Y: 00000000 Not tainted [ 61.445230] TPC: <schizo_pcierr_intr+0x104/0x560> [ 61.449897] g0: 0000000000000000 g1: 0000000000000000 g2: 0000000000a10f78 g3: 000000000000000a [ 61.458563] g4: fff000b0fd8e9c40 g5: fff000b0fdd82000 g6: fff000b0fd928000 g7: 000000000000000a [ 61.467229] o0: 000000000000003d o1: 0000000000000000 o2: 0000000000000006 o3: fff000b0ffa5fc7e [ 61.475894] o4: 0000000000060000 o5: c000000000000000 sp: fff000b0ffa5f3c1 ret_pc: 00000000004455cc [ 61.484909] RPC: <schizo_pcierr_intr+0xec/0x560> [ 61.489500] l0: fff000b0fd8e9c40 l1: 0000000000a20800 l2: 0000000000000000 l3: 000000000119a430 [ 61.498164] l4: 0000000001742400 l5: 00000000011cfbe0 l6: 00000000011319c0 l7: fff000b0fd8ea348 [ 61.506830] i0: 0000000000000000 i1: fff000b0fdb34000 i2: 0000000320000000 i3: 0000000000000000 [ 61.515497] i4: 00060002010b003f i5: 0000040004e02000 i6: fff000b0ffa5f481 i7: 00000000004a9920 [ 61.524175] I7: <handle_irq_event_percpu+0x40/0x140> [ 61.529099] Call Trace: [ 61.531531] [00000000004a9920] handle_irq_event_percpu+0x40/0x140 [ 61.537681] [00000000004a9a58] handle_irq_event+0x38/0x80 [ 61.543145] [00000000004ac77c] handle_fasteoi_irq+0xbc/0x200 [ 61.548860] [00000000004a9084] generic_handle_irq+0x24/0x40 [ 61.554500] [000000000042be0c] handler_irq+0xac/0x100 ==================== The problem is that pbm->pci_bus->self is NULL. This code is trying to go through the standard PCI config space interfaces to read the PCI controller's PCI_STATUS register. This doesn't work, because we more often than not do not enumerate the PCI controller as a bonafide PCI device during the OF device node scan. Therefore bus->self remains NULL. Existing common code for PSYCHO and PSYCHO-like PCI controllers handles this properly, by doing the config space access directly. Do the same here, pbm->pci_ops->{read,write}(). Reported-by: Meelis Roos <mroos@linux.ee> Tested-by: Meelis Roos <mroos@linux.ee> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-11-01 12:33:58 +08:00
u32 stat;
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
csr_reg = pbm->pbm_regs + SCHIZO_PCI_CTRL;
sparc64: Kill hand-crafted I/O accessors in PCI controller drivers. Use existing upa_{read,write}q() interfaces instead. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-09-10 19:13:10 +08:00
csr = upa_readq(csr_reg);
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
csr_error_bits =
csr & (SCHIZO_PCICTRL_BUS_UNUS |
SCHIZO_PCICTRL_TTO_ERR |
SCHIZO_PCICTRL_RTRY_ERR |
SCHIZO_PCICTRL_DTO_ERR |
SCHIZO_PCICTRL_SBH_ERR |
SCHIZO_PCICTRL_SERR);
if (csr_error_bits) {
/* Clear the errors. */
sparc64: Kill hand-crafted I/O accessors in PCI controller drivers. Use existing upa_{read,write}q() interfaces instead. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-09-10 19:13:10 +08:00
upa_writeq(csr, csr_reg);
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
/* Log 'em. */
if (csr_error_bits & SCHIZO_PCICTRL_BUS_UNUS)
printk("%s: Bus unusable error asserted.\n",
pbm->name);
if (csr_error_bits & SCHIZO_PCICTRL_TTO_ERR)
printk("%s: PCI TRDY# timeout error asserted.\n",
pbm->name);
if (csr_error_bits & SCHIZO_PCICTRL_RTRY_ERR)
printk("%s: PCI excessive retry error asserted.\n",
pbm->name);
if (csr_error_bits & SCHIZO_PCICTRL_DTO_ERR)
printk("%s: PCI discard timeout error asserted.\n",
pbm->name);
if (csr_error_bits & SCHIZO_PCICTRL_SBH_ERR)
printk("%s: PCI streaming byte hole error asserted.\n",
pbm->name);
if (csr_error_bits & SCHIZO_PCICTRL_SERR)
printk("%s: PCI SERR signal asserted.\n",
pbm->name);
ret = IRQ_HANDLED;
}
sparc64: Fix crashes in schizo_pcierr_intr_other(). Meelis Roos reports crashes during bootup on a V480 that look like this: ==================== [ 61.300577] PCI: Scanning PBM /pci@9,600000 [ 61.304867] schizo f009b070: PCI host bridge to bus 0003:00 [ 61.310385] pci_bus 0003:00: root bus resource [io 0x7ffe9000000-0x7ffe9ffffff] (bus address [0x0000-0xffffff]) [ 61.320515] pci_bus 0003:00: root bus resource [mem 0x7fb00000000-0x7fbffffffff] (bus address [0x00000000-0xffffffff]) [ 61.331173] pci_bus 0003:00: root bus resource [bus 00] [ 61.385344] Unable to handle kernel NULL pointer dereference [ 61.390970] tsk->{mm,active_mm}->context = 0000000000000000 [ 61.396515] tsk->{mm,active_mm}->pgd = fff000b000002000 [ 61.401716] \|/ ____ \|/ [ 61.401716] "@'/ .. \`@" [ 61.401716] /_| \__/ |_\ [ 61.401716] \__U_/ [ 61.416362] swapper/0(0): Oops [#1] [ 61.419837] CPU: 0 PID: 0 Comm: swapper/0 Not tainted 3.18.0-rc1-00422-g2cc9188-dirty #24 [ 61.427975] task: fff000b0fd8e9c40 ti: fff000b0fd928000 task.ti: fff000b0fd928000 [ 61.435426] TSTATE: 0000004480e01602 TPC: 00000000004455e4 TNPC: 00000000004455e8 Y: 00000000 Not tainted [ 61.445230] TPC: <schizo_pcierr_intr+0x104/0x560> [ 61.449897] g0: 0000000000000000 g1: 0000000000000000 g2: 0000000000a10f78 g3: 000000000000000a [ 61.458563] g4: fff000b0fd8e9c40 g5: fff000b0fdd82000 g6: fff000b0fd928000 g7: 000000000000000a [ 61.467229] o0: 000000000000003d o1: 0000000000000000 o2: 0000000000000006 o3: fff000b0ffa5fc7e [ 61.475894] o4: 0000000000060000 o5: c000000000000000 sp: fff000b0ffa5f3c1 ret_pc: 00000000004455cc [ 61.484909] RPC: <schizo_pcierr_intr+0xec/0x560> [ 61.489500] l0: fff000b0fd8e9c40 l1: 0000000000a20800 l2: 0000000000000000 l3: 000000000119a430 [ 61.498164] l4: 0000000001742400 l5: 00000000011cfbe0 l6: 00000000011319c0 l7: fff000b0fd8ea348 [ 61.506830] i0: 0000000000000000 i1: fff000b0fdb34000 i2: 0000000320000000 i3: 0000000000000000 [ 61.515497] i4: 00060002010b003f i5: 0000040004e02000 i6: fff000b0ffa5f481 i7: 00000000004a9920 [ 61.524175] I7: <handle_irq_event_percpu+0x40/0x140> [ 61.529099] Call Trace: [ 61.531531] [00000000004a9920] handle_irq_event_percpu+0x40/0x140 [ 61.537681] [00000000004a9a58] handle_irq_event+0x38/0x80 [ 61.543145] [00000000004ac77c] handle_fasteoi_irq+0xbc/0x200 [ 61.548860] [00000000004a9084] generic_handle_irq+0x24/0x40 [ 61.554500] [000000000042be0c] handler_irq+0xac/0x100 ==================== The problem is that pbm->pci_bus->self is NULL. This code is trying to go through the standard PCI config space interfaces to read the PCI controller's PCI_STATUS register. This doesn't work, because we more often than not do not enumerate the PCI controller as a bonafide PCI device during the OF device node scan. Therefore bus->self remains NULL. Existing common code for PSYCHO and PSYCHO-like PCI controllers handles this properly, by doing the config space access directly. Do the same here, pbm->pci_ops->{read,write}(). Reported-by: Meelis Roos <mroos@linux.ee> Tested-by: Meelis Roos <mroos@linux.ee> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-11-01 12:33:58 +08:00
pbm->pci_ops->read(pbm->pci_bus, 0, PCI_STATUS, 2, &stat);
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
if (stat & (PCI_STATUS_PARITY |
PCI_STATUS_SIG_TARGET_ABORT |
PCI_STATUS_REC_TARGET_ABORT |
PCI_STATUS_REC_MASTER_ABORT |
PCI_STATUS_SIG_SYSTEM_ERROR)) {
printk("%s: PCI bus error, PCI_STATUS[%04x]\n",
pbm->name, stat);
sparc64: Fix crashes in schizo_pcierr_intr_other(). Meelis Roos reports crashes during bootup on a V480 that look like this: ==================== [ 61.300577] PCI: Scanning PBM /pci@9,600000 [ 61.304867] schizo f009b070: PCI host bridge to bus 0003:00 [ 61.310385] pci_bus 0003:00: root bus resource [io 0x7ffe9000000-0x7ffe9ffffff] (bus address [0x0000-0xffffff]) [ 61.320515] pci_bus 0003:00: root bus resource [mem 0x7fb00000000-0x7fbffffffff] (bus address [0x00000000-0xffffffff]) [ 61.331173] pci_bus 0003:00: root bus resource [bus 00] [ 61.385344] Unable to handle kernel NULL pointer dereference [ 61.390970] tsk->{mm,active_mm}->context = 0000000000000000 [ 61.396515] tsk->{mm,active_mm}->pgd = fff000b000002000 [ 61.401716] \|/ ____ \|/ [ 61.401716] "@'/ .. \`@" [ 61.401716] /_| \__/ |_\ [ 61.401716] \__U_/ [ 61.416362] swapper/0(0): Oops [#1] [ 61.419837] CPU: 0 PID: 0 Comm: swapper/0 Not tainted 3.18.0-rc1-00422-g2cc9188-dirty #24 [ 61.427975] task: fff000b0fd8e9c40 ti: fff000b0fd928000 task.ti: fff000b0fd928000 [ 61.435426] TSTATE: 0000004480e01602 TPC: 00000000004455e4 TNPC: 00000000004455e8 Y: 00000000 Not tainted [ 61.445230] TPC: <schizo_pcierr_intr+0x104/0x560> [ 61.449897] g0: 0000000000000000 g1: 0000000000000000 g2: 0000000000a10f78 g3: 000000000000000a [ 61.458563] g4: fff000b0fd8e9c40 g5: fff000b0fdd82000 g6: fff000b0fd928000 g7: 000000000000000a [ 61.467229] o0: 000000000000003d o1: 0000000000000000 o2: 0000000000000006 o3: fff000b0ffa5fc7e [ 61.475894] o4: 0000000000060000 o5: c000000000000000 sp: fff000b0ffa5f3c1 ret_pc: 00000000004455cc [ 61.484909] RPC: <schizo_pcierr_intr+0xec/0x560> [ 61.489500] l0: fff000b0fd8e9c40 l1: 0000000000a20800 l2: 0000000000000000 l3: 000000000119a430 [ 61.498164] l4: 0000000001742400 l5: 00000000011cfbe0 l6: 00000000011319c0 l7: fff000b0fd8ea348 [ 61.506830] i0: 0000000000000000 i1: fff000b0fdb34000 i2: 0000000320000000 i3: 0000000000000000 [ 61.515497] i4: 00060002010b003f i5: 0000040004e02000 i6: fff000b0ffa5f481 i7: 00000000004a9920 [ 61.524175] I7: <handle_irq_event_percpu+0x40/0x140> [ 61.529099] Call Trace: [ 61.531531] [00000000004a9920] handle_irq_event_percpu+0x40/0x140 [ 61.537681] [00000000004a9a58] handle_irq_event+0x38/0x80 [ 61.543145] [00000000004ac77c] handle_fasteoi_irq+0xbc/0x200 [ 61.548860] [00000000004a9084] generic_handle_irq+0x24/0x40 [ 61.554500] [000000000042be0c] handler_irq+0xac/0x100 ==================== The problem is that pbm->pci_bus->self is NULL. This code is trying to go through the standard PCI config space interfaces to read the PCI controller's PCI_STATUS register. This doesn't work, because we more often than not do not enumerate the PCI controller as a bonafide PCI device during the OF device node scan. Therefore bus->self remains NULL. Existing common code for PSYCHO and PSYCHO-like PCI controllers handles this properly, by doing the config space access directly. Do the same here, pbm->pci_ops->{read,write}(). Reported-by: Meelis Roos <mroos@linux.ee> Tested-by: Meelis Roos <mroos@linux.ee> Signed-off-by: David S. Miller <davem@davemloft.net>
2014-11-01 12:33:58 +08:00
pbm->pci_ops->write(pbm->pci_bus, 0, PCI_STATUS, 2, 0xffff);
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
ret = IRQ_HANDLED;
}
return ret;
}
[PATCH] sparc64 pt_regs fixes Signed-off-by: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-10-08 20:23:28 +08:00
static irqreturn_t schizo_pcierr_intr(int irq, void *dev_id)
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
{
struct pci_pbm_info *pbm = dev_id;
unsigned long afsr_reg, afar_reg, base;
unsigned long afsr, afar, error_bits;
int reported;
base = pbm->pbm_regs;
afsr_reg = base + SCHIZO_PCI_AFSR;
afar_reg = base + SCHIZO_PCI_AFAR;
/* Latch error status. */
sparc64: Kill hand-crafted I/O accessors in PCI controller drivers. Use existing upa_{read,write}q() interfaces instead. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-09-10 19:13:10 +08:00
afar = upa_readq(afar_reg);
afsr = upa_readq(afsr_reg);
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
/* Clear primary/secondary error status bits. */
error_bits = afsr &
(SCHIZO_PCIAFSR_PMA | SCHIZO_PCIAFSR_PTA |
SCHIZO_PCIAFSR_PRTRY | SCHIZO_PCIAFSR_PPERR |
SCHIZO_PCIAFSR_PTTO | SCHIZO_PCIAFSR_PUNUS |
SCHIZO_PCIAFSR_SMA | SCHIZO_PCIAFSR_STA |
SCHIZO_PCIAFSR_SRTRY | SCHIZO_PCIAFSR_SPERR |
SCHIZO_PCIAFSR_STTO | SCHIZO_PCIAFSR_SUNUS);
if (!error_bits)
return schizo_pcierr_intr_other(pbm);
sparc64: Kill hand-crafted I/O accessors in PCI controller drivers. Use existing upa_{read,write}q() interfaces instead. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-09-10 19:13:10 +08:00
upa_writeq(error_bits, afsr_reg);
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
/* Log the error. */
printk("%s: PCI Error, primary error type[%s]\n",
pbm->name,
(((error_bits & SCHIZO_PCIAFSR_PMA) ?
"Master Abort" :
((error_bits & SCHIZO_PCIAFSR_PTA) ?
"Target Abort" :
((error_bits & SCHIZO_PCIAFSR_PRTRY) ?
"Excessive Retries" :
((error_bits & SCHIZO_PCIAFSR_PPERR) ?
"Parity Error" :
((error_bits & SCHIZO_PCIAFSR_PTTO) ?
"Timeout" :
((error_bits & SCHIZO_PCIAFSR_PUNUS) ?
"Bus Unusable" : "???"))))))));
printk("%s: bytemask[%04lx] was_block(%d) space(%s)\n",
pbm->name,
(afsr & SCHIZO_PCIAFSR_BMSK) >> 32UL,
(afsr & SCHIZO_PCIAFSR_BLK) ? 1 : 0,
((afsr & SCHIZO_PCIAFSR_CFG) ?
"Config" :
((afsr & SCHIZO_PCIAFSR_MEM) ?
"Memory" :
((afsr & SCHIZO_PCIAFSR_IO) ?
"I/O" : "???"))));
printk("%s: PCI AFAR [%016lx]\n",
pbm->name, afar);
printk("%s: PCI Secondary errors [",
pbm->name);
reported = 0;
if (afsr & SCHIZO_PCIAFSR_SMA) {
reported++;
printk("(Master Abort)");
}
if (afsr & SCHIZO_PCIAFSR_STA) {
reported++;
printk("(Target Abort)");
}
if (afsr & SCHIZO_PCIAFSR_SRTRY) {
reported++;
printk("(Excessive Retries)");
}
if (afsr & SCHIZO_PCIAFSR_SPERR) {
reported++;
printk("(Parity Error)");
}
if (afsr & SCHIZO_PCIAFSR_STTO) {
reported++;
printk("(Timeout)");
}
if (afsr & SCHIZO_PCIAFSR_SUNUS) {
reported++;
printk("(Bus Unusable)");
}
if (!reported)
printk("(none)");
printk("]\n");
/* For the error types shown, scan PBM's PCI bus for devices
* which have logged that error type.
*/
/* If we see a Target Abort, this could be the result of an
* IOMMU translation error of some sort. It is extremely
* useful to log this information as usually it indicates
* a bug in the IOMMU support code or a PCI device driver.
*/
if (error_bits & (SCHIZO_PCIAFSR_PTA | SCHIZO_PCIAFSR_STA)) {
sparc64: Get rid of pci_controller_info. It is just used as a parent to encapsulate two PBM objects. But that layout is only really relevant and necessary for psycho PCI controllers, which unlike all the others share a single IOMMU instance between sibling PCI busses. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-09-10 14:54:02 +08:00
schizo_check_iommu_error(pbm, PCI_ERR);
[SPARC64]: Move index info pci_pbm_info. Signed-off-by: David S. Miller <davem@davemloft.net>
2007-05-08 14:49:01 +08:00
pci_scan_for_target_abort(pbm, pbm->pci_bus);
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
}
if (error_bits & (SCHIZO_PCIAFSR_PMA | SCHIZO_PCIAFSR_SMA))
[SPARC64]: Move index info pci_pbm_info. Signed-off-by: David S. Miller <davem@davemloft.net>
2007-05-08 14:49:01 +08:00
pci_scan_for_master_abort(pbm, pbm->pci_bus);
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
/* For excessive retries, PSYCHO/PBM will abort the device
* and there is no way to specifically check for excessive
* retries in the config space status registers. So what
* we hope is that we'll catch it via the master/target
* abort events.
*/
if (error_bits & (SCHIZO_PCIAFSR_PPERR | SCHIZO_PCIAFSR_SPERR))
[SPARC64]: Move index info pci_pbm_info. Signed-off-by: David S. Miller <davem@davemloft.net>
2007-05-08 14:49:01 +08:00
pci_scan_for_parity_error(pbm, pbm->pci_bus);
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
return IRQ_HANDLED;
}
#define SCHIZO_SAFARI_ERRLOG 0x10018UL
#define SAFARI_ERRLOG_ERROUT 0x8000000000000000UL
#define BUS_ERROR_BADCMD 0x4000000000000000UL /* Schizo/Tomatillo */
#define BUS_ERROR_SSMDIS 0x2000000000000000UL /* Safari */
#define BUS_ERROR_BADMA 0x1000000000000000UL /* Safari */
#define BUS_ERROR_BADMB 0x0800000000000000UL /* Safari */
#define BUS_ERROR_BADMC 0x0400000000000000UL /* Safari */
#define BUS_ERROR_SNOOP_GR 0x0000000000200000UL /* Tomatillo */
#define BUS_ERROR_SNOOP_PCI 0x0000000000100000UL /* Tomatillo */
#define BUS_ERROR_SNOOP_RD 0x0000000000080000UL /* Tomatillo */
#define BUS_ERROR_SNOOP_RDS 0x0000000000020000UL /* Tomatillo */
#define BUS_ERROR_SNOOP_RDSA 0x0000000000010000UL /* Tomatillo */
#define BUS_ERROR_SNOOP_OWN 0x0000000000008000UL /* Tomatillo */
#define BUS_ERROR_SNOOP_RDO 0x0000000000004000UL /* Tomatillo */
#define BUS_ERROR_CPU1PS 0x0000000000002000UL /* Safari */
#define BUS_ERROR_WDATA_PERR 0x0000000000002000UL /* Tomatillo */
#define BUS_ERROR_CPU1PB 0x0000000000001000UL /* Safari */
#define BUS_ERROR_CTRL_PERR 0x0000000000001000UL /* Tomatillo */
#define BUS_ERROR_CPU0PS 0x0000000000000800UL /* Safari */
#define BUS_ERROR_SNOOP_ERR 0x0000000000000800UL /* Tomatillo */
#define BUS_ERROR_CPU0PB 0x0000000000000400UL /* Safari */
#define BUS_ERROR_JBUS_ILL_B 0x0000000000000400UL /* Tomatillo */
#define BUS_ERROR_CIQTO 0x0000000000000200UL /* Safari */
#define BUS_ERROR_LPQTO 0x0000000000000100UL /* Safari */
#define BUS_ERROR_JBUS_ILL_C 0x0000000000000100UL /* Tomatillo */
#define BUS_ERROR_SFPQTO 0x0000000000000080UL /* Safari */
#define BUS_ERROR_UFPQTO 0x0000000000000040UL /* Safari */
#define BUS_ERROR_RD_PERR 0x0000000000000040UL /* Tomatillo */
#define BUS_ERROR_APERR 0x0000000000000020UL /* Safari/Tomatillo */
#define BUS_ERROR_UNMAP 0x0000000000000010UL /* Safari/Tomatillo */
#define BUS_ERROR_BUSERR 0x0000000000000004UL /* Safari/Tomatillo */
#define BUS_ERROR_TIMEOUT 0x0000000000000002UL /* Safari/Tomatillo */
#define BUS_ERROR_ILL 0x0000000000000001UL /* Safari */
/* We only expect UNMAP errors here. The rest of the Safari errors
* are marked fatal and thus cause a system reset.
*/
[PATCH] sparc64 pt_regs fixes Signed-off-by: Al Viro <viro@zeniv.linux.org.uk> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
2006-10-08 20:23:28 +08:00
static irqreturn_t schizo_safarierr_intr(int irq, void *dev_id)
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
{
[SPARC64] PCI: Use root list of pbm's instead of pci_controller_info's The idea is to move more and more things into the pbm, with the eventual goal of eliminating the pci_controller_info entirely as there really isn't any need for it. This stage of the transformations requires some reworking of the PCI error interrupt handling. It might be tricky to get rid of the pci_controller_info parenting for a few reasons: 1) When we get an uncorrectable or correctable error we want to interrogate the IOMMU and streaming cache of both PBMs for error status. These errors come from the UPA front-end which is shared between the two PBM PCI bus segments. Historically speaking this is why I choose the datastructure hierarchy of pci_controller_info-->pci_pbm_info 2) The probing does a portid/devhandle match to look for the 'other' pbm, but this is entirely an artifact and can be eliminated trivially. What we could do to solve #1 is to have a "buddy" pointer from one pbm to another. Signed-off-by: David S. Miller <davem@davemloft.net>
2007-05-08 14:06:27 +08:00
struct pci_pbm_info *pbm = dev_id;
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
u64 errlog;
sparc64: Kill hand-crafted I/O accessors in PCI controller drivers. Use existing upa_{read,write}q() interfaces instead. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-09-10 19:13:10 +08:00
errlog = upa_readq(pbm->controller_regs + SCHIZO_SAFARI_ERRLOG);
upa_writeq(errlog & ~(SAFARI_ERRLOG_ERROUT),
pbm->controller_regs + SCHIZO_SAFARI_ERRLOG);
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
if (!(errlog & BUS_ERROR_UNMAP)) {
sparc64: Use unsigned long long for u64. Andrew Morton wrote: People keep on doing printk("%llu", some_u64); testing it only on x86_64 and this generates a warning storm on powerpc, sparc64, etc. Because they use `long', not `long long'. Quite a few 64-bit architectures are using `long' for their s64/u64 types. We should convert them all to `long long'. Update types.h so we use unsigned long long for u64 and fix all warnings in sparc64 code. Tested with an allnoconfig, defconfig and allmodconfig builds. This patch introduces additional warnings in several drivers. These will be dealt with in separate patches. Signed-off-by: Sam Ravnborg <sam@ravnborg.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2009-01-07 05:19:28 +08:00
printk("%s: Unexpected Safari/JBUS error interrupt, errlog[%016llx]\n",
[SPARC64]: Move index info pci_pbm_info. Signed-off-by: David S. Miller <davem@davemloft.net>
2007-05-08 14:49:01 +08:00
pbm->name, errlog);
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
return IRQ_HANDLED;
}
[SPARC64]: Move index info pci_pbm_info. Signed-off-by: David S. Miller <davem@davemloft.net>
2007-05-08 14:49:01 +08:00
printk("%s: Safari/JBUS interrupt, UNMAPPED error, interrogating IOMMUs.\n",
pbm->name);
sparc64: Get rid of pci_controller_info. It is just used as a parent to encapsulate two PBM objects. But that layout is only really relevant and necessary for psycho PCI controllers, which unlike all the others share a single IOMMU instance between sibling PCI busses. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-09-10 14:54:02 +08:00
schizo_check_iommu_error(pbm, SAFARI_ERR);
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
return IRQ_HANDLED;
}
/* Nearly identical to PSYCHO equivalents... */
#define SCHIZO_ECC_CTRL 0x10020UL
#define SCHIZO_ECCCTRL_EE 0x8000000000000000UL /* Enable ECC Checking */
#define SCHIZO_ECCCTRL_UE 0x4000000000000000UL /* Enable UE Interrupts */
#define SCHIZO_ECCCTRL_CE 0x2000000000000000UL /* Enable CE INterrupts */
#define SCHIZO_SAFARI_ERRCTRL 0x10008UL
#define SCHIZO_SAFERRCTRL_EN 0x8000000000000000UL
#define SCHIZO_SAFARI_IRQCTRL 0x10010UL
#define SCHIZO_SAFIRQCTRL_EN 0x8000000000000000UL
[SPARC64] PCI: Use root list of pbm's instead of pci_controller_info's The idea is to move more and more things into the pbm, with the eventual goal of eliminating the pci_controller_info entirely as there really isn't any need for it. This stage of the transformations requires some reworking of the PCI error interrupt handling. It might be tricky to get rid of the pci_controller_info parenting for a few reasons: 1) When we get an uncorrectable or correctable error we want to interrogate the IOMMU and streaming cache of both PBMs for error status. These errors come from the UPA front-end which is shared between the two PBM PCI bus segments. Historically speaking this is why I choose the datastructure hierarchy of pci_controller_info-->pci_pbm_info 2) The probing does a portid/devhandle match to look for the 'other' pbm, but this is entirely an artifact and can be eliminated trivially. What we could do to solve #1 is to have a "buddy" pointer from one pbm to another. Signed-off-by: David S. Miller <davem@davemloft.net>
2007-05-08 14:06:27 +08:00
static int pbm_routes_this_ino(struct pci_pbm_info *pbm, u32 ino)
{
ino &= IMAP_INO;
if (pbm->ino_bitmap & (1UL << ino))
return 1;
return 0;
}
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
/* How the Tomatillo IRQs are routed around is pure guesswork here.
*
* All the Tomatillo devices I see in prtconf dumps seem to have only
[SPARC64]: Spelling fixes Signed-off-by: Joe Perches <joe@perches.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2007-12-21 05:55:10 +08:00
* a single PCI bus unit attached to it. It would seem they are separate
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
* devices because their PortID (ie. JBUS ID) values are all different
* and thus the registers are mapped to totally different locations.
*
* However, two Tomatillo's look "similar" in that the only difference
* in their PortID is the lowest bit.
*
* So if we were to ignore this lower bit, it certainly looks like two
* PCI bus units of the same Tomatillo. I still have not really
* figured this out...
*/
[SPARC64] PCI: Use root list of pbm's instead of pci_controller_info's The idea is to move more and more things into the pbm, with the eventual goal of eliminating the pci_controller_info entirely as there really isn't any need for it. This stage of the transformations requires some reworking of the PCI error interrupt handling. It might be tricky to get rid of the pci_controller_info parenting for a few reasons: 1) When we get an uncorrectable or correctable error we want to interrogate the IOMMU and streaming cache of both PBMs for error status. These errors come from the UPA front-end which is shared between the two PBM PCI bus segments. Historically speaking this is why I choose the datastructure hierarchy of pci_controller_info-->pci_pbm_info 2) The probing does a portid/devhandle match to look for the 'other' pbm, but this is entirely an artifact and can be eliminated trivially. What we could do to solve #1 is to have a "buddy" pointer from one pbm to another. Signed-off-by: David S. Miller <davem@davemloft.net>
2007-05-08 14:06:27 +08:00
static void tomatillo_register_error_handlers(struct pci_pbm_info *pbm)
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
{
sparc: remove references to of_device and to_of_device of_device is just a #define alias to platform_device. This patch replaces all references to it with platform_device. Signed-off-by: Grant Likely <grant.likely@secretlab.ca> Acked-by: David S. Miller <davem@davemloft.net>
2010-07-23 06:04:30 +08:00
struct platform_device *op = of_find_device_by_node(pbm->op->dev.of_node);
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
u64 tmp, err_mask, err_no_mask;
[SPARC64]: Fix request_irq() ignored result warnings in PCI controller code. Signed-off-by: David S. Miller <davem@davemloft.net>
2007-05-09 08:23:31 +08:00
int err;
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
[SPARC64]: of_device layer IRQ resolution Do IRQ determination generically by parsing the PROM properties, and using IRQ controller drivers for final resolution. One immediate positive effect is that all of the IRQ frobbing in the EBUS, ISA, and PCI controller layers has been eliminated. We just look up the of_device and use the properly computed value. The PCI controller irq_build() routines are gone and no longer used. Unfortunately sbus_build_irq() has to remain as there is a direct reference to this in the sunzilog driver. That can be killed off once the sparc32 side of this is written and the sunzilog driver is transformed into an "of" bus driver. Signed-off-by: David S. Miller <davem@davemloft.net>
2006-06-30 06:07:37 +08:00
/* Tomatillo IRQ property layout is:
* 0: PCIERR
* 1: UE ERR
* 2: CE ERR
* 3: SERR
* 4: POWER FAIL?
*/
[SPARC64]: Fix request_irq() ignored result warnings in PCI controller code. Signed-off-by: David S. Miller <davem@davemloft.net>
2007-05-09 08:23:31 +08:00
if (pbm_routes_this_ino(pbm, SCHIZO_UE_INO)) {
sparc/of: Move of_device fields into struct pdev_archdata This patch moves SPARC architecture specific data members out of struct of_device and into the pdev_archdata structure. The reason for this change is to unify the struct of_device definition amongst all the architectures. It also remvoes the .sysdata, .slot, .portid and .clock_freq properties because they aren't actually used by anything. A subsequent patch will replace struct of_device entirely with struct platform_device and the of_platform support code will share common routines with the platform bus (but the bus instances themselves can remain separate). This patch also adds 'struct resources *resource' and num_resources to match the fields defined in struct platform_device. After this change, 'struct platform_device' can be used as a drop-in replacement for 'struct of_platform'. This change is in preparation for merging the of_platform_bus_type with the platform_bus_type. Signed-off-by: Grant Likely <grant.likely@secretlab.ca> Acked-by: David S. Miller <davem@davemloft.net> Cc: Stephen Rothwell <sfr@canb.auug.org.au>
2010-06-19 01:09:58 +08:00
err = request_irq(op->archdata.irqs[1], schizo_ue_intr, 0,
[SPARC64]: Fix request_irq() ignored result warnings in PCI controller code. Signed-off-by: David S. Miller <davem@davemloft.net>
2007-05-09 08:23:31 +08:00
"TOMATILLO_UE", pbm);
if (err)
printk(KERN_WARNING "%s: Could not register UE, "
"err=%d\n", pbm->name, err);
}
if (pbm_routes_this_ino(pbm, SCHIZO_CE_INO)) {
sparc/of: Move of_device fields into struct pdev_archdata This patch moves SPARC architecture specific data members out of struct of_device and into the pdev_archdata structure. The reason for this change is to unify the struct of_device definition amongst all the architectures. It also remvoes the .sysdata, .slot, .portid and .clock_freq properties because they aren't actually used by anything. A subsequent patch will replace struct of_device entirely with struct platform_device and the of_platform support code will share common routines with the platform bus (but the bus instances themselves can remain separate). This patch also adds 'struct resources *resource' and num_resources to match the fields defined in struct platform_device. After this change, 'struct platform_device' can be used as a drop-in replacement for 'struct of_platform'. This change is in preparation for merging the of_platform_bus_type with the platform_bus_type. Signed-off-by: Grant Likely <grant.likely@secretlab.ca> Acked-by: David S. Miller <davem@davemloft.net> Cc: Stephen Rothwell <sfr@canb.auug.org.au>
2010-06-19 01:09:58 +08:00
err = request_irq(op->archdata.irqs[2], schizo_ce_intr, 0,
[SPARC64]: Fix request_irq() ignored result warnings in PCI controller code. Signed-off-by: David S. Miller <davem@davemloft.net>
2007-05-09 08:23:31 +08:00
"TOMATILLO_CE", pbm);
if (err)
printk(KERN_WARNING "%s: Could not register CE, "
"err=%d\n", pbm->name, err);
}
err = 0;
if (pbm_routes_this_ino(pbm, SCHIZO_PCIERR_A_INO)) {
sparc/of: Move of_device fields into struct pdev_archdata This patch moves SPARC architecture specific data members out of struct of_device and into the pdev_archdata structure. The reason for this change is to unify the struct of_device definition amongst all the architectures. It also remvoes the .sysdata, .slot, .portid and .clock_freq properties because they aren't actually used by anything. A subsequent patch will replace struct of_device entirely with struct platform_device and the of_platform support code will share common routines with the platform bus (but the bus instances themselves can remain separate). This patch also adds 'struct resources *resource' and num_resources to match the fields defined in struct platform_device. After this change, 'struct platform_device' can be used as a drop-in replacement for 'struct of_platform'. This change is in preparation for merging the of_platform_bus_type with the platform_bus_type. Signed-off-by: Grant Likely <grant.likely@secretlab.ca> Acked-by: David S. Miller <davem@davemloft.net> Cc: Stephen Rothwell <sfr@canb.auug.org.au>
2010-06-19 01:09:58 +08:00
err = request_irq(op->archdata.irqs[0], schizo_pcierr_intr, 0,
[SPARC64]: Fix request_irq() ignored result warnings in PCI controller code. Signed-off-by: David S. Miller <davem@davemloft.net>
2007-05-09 08:23:31 +08:00
"TOMATILLO_PCIERR", pbm);
} else if (pbm_routes_this_ino(pbm, SCHIZO_PCIERR_B_INO)) {
sparc/of: Move of_device fields into struct pdev_archdata This patch moves SPARC architecture specific data members out of struct of_device and into the pdev_archdata structure. The reason for this change is to unify the struct of_device definition amongst all the architectures. It also remvoes the .sysdata, .slot, .portid and .clock_freq properties because they aren't actually used by anything. A subsequent patch will replace struct of_device entirely with struct platform_device and the of_platform support code will share common routines with the platform bus (but the bus instances themselves can remain separate). This patch also adds 'struct resources *resource' and num_resources to match the fields defined in struct platform_device. After this change, 'struct platform_device' can be used as a drop-in replacement for 'struct of_platform'. This change is in preparation for merging the of_platform_bus_type with the platform_bus_type. Signed-off-by: Grant Likely <grant.likely@secretlab.ca> Acked-by: David S. Miller <davem@davemloft.net> Cc: Stephen Rothwell <sfr@canb.auug.org.au>
2010-06-19 01:09:58 +08:00
err = request_irq(op->archdata.irqs[0], schizo_pcierr_intr, 0,
[SPARC64]: Fix request_irq() ignored result warnings in PCI controller code. Signed-off-by: David S. Miller <davem@davemloft.net>
2007-05-09 08:23:31 +08:00
"TOMATILLO_PCIERR", pbm);
}
if (err)
printk(KERN_WARNING "%s: Could not register PCIERR, "
"err=%d\n", pbm->name, err);
if (pbm_routes_this_ino(pbm, SCHIZO_SERR_INO)) {
sparc/of: Move of_device fields into struct pdev_archdata This patch moves SPARC architecture specific data members out of struct of_device and into the pdev_archdata structure. The reason for this change is to unify the struct of_device definition amongst all the architectures. It also remvoes the .sysdata, .slot, .portid and .clock_freq properties because they aren't actually used by anything. A subsequent patch will replace struct of_device entirely with struct platform_device and the of_platform support code will share common routines with the platform bus (but the bus instances themselves can remain separate). This patch also adds 'struct resources *resource' and num_resources to match the fields defined in struct platform_device. After this change, 'struct platform_device' can be used as a drop-in replacement for 'struct of_platform'. This change is in preparation for merging the of_platform_bus_type with the platform_bus_type. Signed-off-by: Grant Likely <grant.likely@secretlab.ca> Acked-by: David S. Miller <davem@davemloft.net> Cc: Stephen Rothwell <sfr@canb.auug.org.au>
2010-06-19 01:09:58 +08:00
err = request_irq(op->archdata.irqs[3], schizo_safarierr_intr, 0,
[SPARC64]: Fix request_irq() ignored result warnings in PCI controller code. Signed-off-by: David S. Miller <davem@davemloft.net>
2007-05-09 08:23:31 +08:00
"TOMATILLO_SERR", pbm);
if (err)
printk(KERN_WARNING "%s: Could not register SERR, "
"err=%d\n", pbm->name, err);
}
[SPARC64] PCI: Use root list of pbm's instead of pci_controller_info's The idea is to move more and more things into the pbm, with the eventual goal of eliminating the pci_controller_info entirely as there really isn't any need for it. This stage of the transformations requires some reworking of the PCI error interrupt handling. It might be tricky to get rid of the pci_controller_info parenting for a few reasons: 1) When we get an uncorrectable or correctable error we want to interrogate the IOMMU and streaming cache of both PBMs for error status. These errors come from the UPA front-end which is shared between the two PBM PCI bus segments. Historically speaking this is why I choose the datastructure hierarchy of pci_controller_info-->pci_pbm_info 2) The probing does a portid/devhandle match to look for the 'other' pbm, but this is entirely an artifact and can be eliminated trivially. What we could do to solve #1 is to have a "buddy" pointer from one pbm to another. Signed-off-by: David S. Miller <davem@davemloft.net>
2007-05-08 14:06:27 +08:00
/* Enable UE and CE interrupts for controller. */
sparc64: Kill hand-crafted I/O accessors in PCI controller drivers. Use existing upa_{read,write}q() interfaces instead. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-09-10 19:13:10 +08:00
upa_writeq((SCHIZO_ECCCTRL_EE |
SCHIZO_ECCCTRL_UE |
SCHIZO_ECCCTRL_CE), pbm->controller_regs + SCHIZO_ECC_CTRL);
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
/* Enable PCI Error interrupts and clear error
* bits.
*/
err_mask = (SCHIZO_PCICTRL_BUS_UNUS |
SCHIZO_PCICTRL_TTO_ERR |
SCHIZO_PCICTRL_RTRY_ERR |
SCHIZO_PCICTRL_SERR |
SCHIZO_PCICTRL_EEN);
err_no_mask = SCHIZO_PCICTRL_DTO_ERR;
sparc64: Kill hand-crafted I/O accessors in PCI controller drivers. Use existing upa_{read,write}q() interfaces instead. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-09-10 19:13:10 +08:00
tmp = upa_readq(pbm->pbm_regs + SCHIZO_PCI_CTRL);
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
tmp |= err_mask;
tmp &= ~err_no_mask;
sparc64: Kill hand-crafted I/O accessors in PCI controller drivers. Use existing upa_{read,write}q() interfaces instead. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-09-10 19:13:10 +08:00
upa_writeq(tmp, pbm->pbm_regs + SCHIZO_PCI_CTRL);
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
err_mask = (SCHIZO_PCIAFSR_PMA | SCHIZO_PCIAFSR_PTA |
SCHIZO_PCIAFSR_PRTRY | SCHIZO_PCIAFSR_PPERR |
SCHIZO_PCIAFSR_PTTO |
SCHIZO_PCIAFSR_SMA | SCHIZO_PCIAFSR_STA |
SCHIZO_PCIAFSR_SRTRY | SCHIZO_PCIAFSR_SPERR |
SCHIZO_PCIAFSR_STTO);
sparc64: Kill hand-crafted I/O accessors in PCI controller drivers. Use existing upa_{read,write}q() interfaces instead. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-09-10 19:13:10 +08:00
upa_writeq(err_mask, pbm->pbm_regs + SCHIZO_PCI_AFSR);
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
err_mask = (BUS_ERROR_BADCMD | BUS_ERROR_SNOOP_GR |
BUS_ERROR_SNOOP_PCI | BUS_ERROR_SNOOP_RD |
BUS_ERROR_SNOOP_RDS | BUS_ERROR_SNOOP_RDSA |
BUS_ERROR_SNOOP_OWN | BUS_ERROR_SNOOP_RDO |
BUS_ERROR_WDATA_PERR | BUS_ERROR_CTRL_PERR |
BUS_ERROR_SNOOP_ERR | BUS_ERROR_JBUS_ILL_B |
BUS_ERROR_JBUS_ILL_C | BUS_ERROR_RD_PERR |
BUS_ERROR_APERR | BUS_ERROR_UNMAP |
BUS_ERROR_BUSERR | BUS_ERROR_TIMEOUT);
sparc64: Kill hand-crafted I/O accessors in PCI controller drivers. Use existing upa_{read,write}q() interfaces instead. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-09-10 19:13:10 +08:00
upa_writeq((SCHIZO_SAFERRCTRL_EN | err_mask),
pbm->controller_regs + SCHIZO_SAFARI_ERRCTRL);
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
sparc64: Kill hand-crafted I/O accessors in PCI controller drivers. Use existing upa_{read,write}q() interfaces instead. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-09-10 19:13:10 +08:00
upa_writeq((SCHIZO_SAFIRQCTRL_EN | (BUS_ERROR_UNMAP)),
pbm->controller_regs + SCHIZO_SAFARI_IRQCTRL);
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
}
[SPARC64] PCI: Use root list of pbm's instead of pci_controller_info's The idea is to move more and more things into the pbm, with the eventual goal of eliminating the pci_controller_info entirely as there really isn't any need for it. This stage of the transformations requires some reworking of the PCI error interrupt handling. It might be tricky to get rid of the pci_controller_info parenting for a few reasons: 1) When we get an uncorrectable or correctable error we want to interrogate the IOMMU and streaming cache of both PBMs for error status. These errors come from the UPA front-end which is shared between the two PBM PCI bus segments. Historically speaking this is why I choose the datastructure hierarchy of pci_controller_info-->pci_pbm_info 2) The probing does a portid/devhandle match to look for the 'other' pbm, but this is entirely an artifact and can be eliminated trivially. What we could do to solve #1 is to have a "buddy" pointer from one pbm to another. Signed-off-by: David S. Miller <davem@davemloft.net>
2007-05-08 14:06:27 +08:00
static void schizo_register_error_handlers(struct pci_pbm_info *pbm)
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
{
sparc: remove references to of_device and to_of_device of_device is just a #define alias to platform_device. This patch replaces all references to it with platform_device. Signed-off-by: Grant Likely <grant.likely@secretlab.ca> Acked-by: David S. Miller <davem@davemloft.net>
2010-07-23 06:04:30 +08:00
struct platform_device *op = of_find_device_by_node(pbm->op->dev.of_node);
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
u64 tmp, err_mask, err_no_mask;
[SPARC64]: Fix request_irq() ignored result warnings in PCI controller code. Signed-off-by: David S. Miller <davem@davemloft.net>
2007-05-09 08:23:31 +08:00
int err;
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
[SPARC64]: of_device layer IRQ resolution Do IRQ determination generically by parsing the PROM properties, and using IRQ controller drivers for final resolution. One immediate positive effect is that all of the IRQ frobbing in the EBUS, ISA, and PCI controller layers has been eliminated. We just look up the of_device and use the properly computed value. The PCI controller irq_build() routines are gone and no longer used. Unfortunately sbus_build_irq() has to remain as there is a direct reference to this in the sunzilog driver. That can be killed off once the sparc32 side of this is written and the sunzilog driver is transformed into an "of" bus driver. Signed-off-by: David S. Miller <davem@davemloft.net>
2006-06-30 06:07:37 +08:00
/* Schizo IRQ property layout is:
* 0: PCIERR
* 1: UE ERR
* 2: CE ERR
* 3: SERR
* 4: POWER FAIL?
*/
[SPARC64]: Fix request_irq() ignored result warnings in PCI controller code. Signed-off-by: David S. Miller <davem@davemloft.net>
2007-05-09 08:23:31 +08:00
if (pbm_routes_this_ino(pbm, SCHIZO_UE_INO)) {
sparc/of: Move of_device fields into struct pdev_archdata This patch moves SPARC architecture specific data members out of struct of_device and into the pdev_archdata structure. The reason for this change is to unify the struct of_device definition amongst all the architectures. It also remvoes the .sysdata, .slot, .portid and .clock_freq properties because they aren't actually used by anything. A subsequent patch will replace struct of_device entirely with struct platform_device and the of_platform support code will share common routines with the platform bus (but the bus instances themselves can remain separate). This patch also adds 'struct resources *resource' and num_resources to match the fields defined in struct platform_device. After this change, 'struct platform_device' can be used as a drop-in replacement for 'struct of_platform'. This change is in preparation for merging the of_platform_bus_type with the platform_bus_type. Signed-off-by: Grant Likely <grant.likely@secretlab.ca> Acked-by: David S. Miller <davem@davemloft.net> Cc: Stephen Rothwell <sfr@canb.auug.org.au>
2010-06-19 01:09:58 +08:00
err = request_irq(op->archdata.irqs[1], schizo_ue_intr, 0,
[SPARC64]: Fix request_irq() ignored result warnings in PCI controller code. Signed-off-by: David S. Miller <davem@davemloft.net>
2007-05-09 08:23:31 +08:00
"SCHIZO_UE", pbm);
if (err)
printk(KERN_WARNING "%s: Could not register UE, "
"err=%d\n", pbm->name, err);
}
if (pbm_routes_this_ino(pbm, SCHIZO_CE_INO)) {
sparc/of: Move of_device fields into struct pdev_archdata This patch moves SPARC architecture specific data members out of struct of_device and into the pdev_archdata structure. The reason for this change is to unify the struct of_device definition amongst all the architectures. It also remvoes the .sysdata, .slot, .portid and .clock_freq properties because they aren't actually used by anything. A subsequent patch will replace struct of_device entirely with struct platform_device and the of_platform support code will share common routines with the platform bus (but the bus instances themselves can remain separate). This patch also adds 'struct resources *resource' and num_resources to match the fields defined in struct platform_device. After this change, 'struct platform_device' can be used as a drop-in replacement for 'struct of_platform'. This change is in preparation for merging the of_platform_bus_type with the platform_bus_type. Signed-off-by: Grant Likely <grant.likely@secretlab.ca> Acked-by: David S. Miller <davem@davemloft.net> Cc: Stephen Rothwell <sfr@canb.auug.org.au>
2010-06-19 01:09:58 +08:00
err = request_irq(op->archdata.irqs[2], schizo_ce_intr, 0,
[SPARC64]: Fix request_irq() ignored result warnings in PCI controller code. Signed-off-by: David S. Miller <davem@davemloft.net>
2007-05-09 08:23:31 +08:00
"SCHIZO_CE", pbm);
if (err)
printk(KERN_WARNING "%s: Could not register CE, "
"err=%d\n", pbm->name, err);
}
err = 0;
if (pbm_routes_this_ino(pbm, SCHIZO_PCIERR_A_INO)) {
sparc/of: Move of_device fields into struct pdev_archdata This patch moves SPARC architecture specific data members out of struct of_device and into the pdev_archdata structure. The reason for this change is to unify the struct of_device definition amongst all the architectures. It also remvoes the .sysdata, .slot, .portid and .clock_freq properties because they aren't actually used by anything. A subsequent patch will replace struct of_device entirely with struct platform_device and the of_platform support code will share common routines with the platform bus (but the bus instances themselves can remain separate). This patch also adds 'struct resources *resource' and num_resources to match the fields defined in struct platform_device. After this change, 'struct platform_device' can be used as a drop-in replacement for 'struct of_platform'. This change is in preparation for merging the of_platform_bus_type with the platform_bus_type. Signed-off-by: Grant Likely <grant.likely@secretlab.ca> Acked-by: David S. Miller <davem@davemloft.net> Cc: Stephen Rothwell <sfr@canb.auug.org.au>
2010-06-19 01:09:58 +08:00
err = request_irq(op->archdata.irqs[0], schizo_pcierr_intr, 0,
[SPARC64]: Fix request_irq() ignored result warnings in PCI controller code. Signed-off-by: David S. Miller <davem@davemloft.net>
2007-05-09 08:23:31 +08:00
"SCHIZO_PCIERR", pbm);
} else if (pbm_routes_this_ino(pbm, SCHIZO_PCIERR_B_INO)) {
sparc/of: Move of_device fields into struct pdev_archdata This patch moves SPARC architecture specific data members out of struct of_device and into the pdev_archdata structure. The reason for this change is to unify the struct of_device definition amongst all the architectures. It also remvoes the .sysdata, .slot, .portid and .clock_freq properties because they aren't actually used by anything. A subsequent patch will replace struct of_device entirely with struct platform_device and the of_platform support code will share common routines with the platform bus (but the bus instances themselves can remain separate). This patch also adds 'struct resources *resource' and num_resources to match the fields defined in struct platform_device. After this change, 'struct platform_device' can be used as a drop-in replacement for 'struct of_platform'. This change is in preparation for merging the of_platform_bus_type with the platform_bus_type. Signed-off-by: Grant Likely <grant.likely@secretlab.ca> Acked-by: David S. Miller <davem@davemloft.net> Cc: Stephen Rothwell <sfr@canb.auug.org.au>
2010-06-19 01:09:58 +08:00
err = request_irq(op->archdata.irqs[0], schizo_pcierr_intr, 0,
[SPARC64]: Fix request_irq() ignored result warnings in PCI controller code. Signed-off-by: David S. Miller <davem@davemloft.net>
2007-05-09 08:23:31 +08:00
"SCHIZO_PCIERR", pbm);
}
if (err)
printk(KERN_WARNING "%s: Could not register PCIERR, "
"err=%d\n", pbm->name, err);
if (pbm_routes_this_ino(pbm, SCHIZO_SERR_INO)) {
sparc/of: Move of_device fields into struct pdev_archdata This patch moves SPARC architecture specific data members out of struct of_device and into the pdev_archdata structure. The reason for this change is to unify the struct of_device definition amongst all the architectures. It also remvoes the .sysdata, .slot, .portid and .clock_freq properties because they aren't actually used by anything. A subsequent patch will replace struct of_device entirely with struct platform_device and the of_platform support code will share common routines with the platform bus (but the bus instances themselves can remain separate). This patch also adds 'struct resources *resource' and num_resources to match the fields defined in struct platform_device. After this change, 'struct platform_device' can be used as a drop-in replacement for 'struct of_platform'. This change is in preparation for merging the of_platform_bus_type with the platform_bus_type. Signed-off-by: Grant Likely <grant.likely@secretlab.ca> Acked-by: David S. Miller <davem@davemloft.net> Cc: Stephen Rothwell <sfr@canb.auug.org.au>
2010-06-19 01:09:58 +08:00
err = request_irq(op->archdata.irqs[3], schizo_safarierr_intr, 0,
[SPARC64]: Fix request_irq() ignored result warnings in PCI controller code. Signed-off-by: David S. Miller <davem@davemloft.net>
2007-05-09 08:23:31 +08:00
"SCHIZO_SERR", pbm);
if (err)
printk(KERN_WARNING "%s: Could not register SERR, "
"err=%d\n", pbm->name, err);
}
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
/* Enable UE and CE interrupts for controller. */
sparc64: Kill hand-crafted I/O accessors in PCI controller drivers. Use existing upa_{read,write}q() interfaces instead. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-09-10 19:13:10 +08:00
upa_writeq((SCHIZO_ECCCTRL_EE |
SCHIZO_ECCCTRL_UE |
SCHIZO_ECCCTRL_CE), pbm->controller_regs + SCHIZO_ECC_CTRL);
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
err_mask = (SCHIZO_PCICTRL_BUS_UNUS |
SCHIZO_PCICTRL_ESLCK |
SCHIZO_PCICTRL_TTO_ERR |
SCHIZO_PCICTRL_RTRY_ERR |
SCHIZO_PCICTRL_SBH_ERR |
SCHIZO_PCICTRL_SERR |
SCHIZO_PCICTRL_EEN);
err_no_mask = (SCHIZO_PCICTRL_DTO_ERR |
SCHIZO_PCICTRL_SBH_INT);
/* Enable PCI Error interrupts and clear error
* bits for each PBM.
*/
sparc64: Kill hand-crafted I/O accessors in PCI controller drivers. Use existing upa_{read,write}q() interfaces instead. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-09-10 19:13:10 +08:00
tmp = upa_readq(pbm->pbm_regs + SCHIZO_PCI_CTRL);
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
tmp |= err_mask;
tmp &= ~err_no_mask;
sparc64: Kill hand-crafted I/O accessors in PCI controller drivers. Use existing upa_{read,write}q() interfaces instead. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-09-10 19:13:10 +08:00
upa_writeq(tmp, pbm->pbm_regs + SCHIZO_PCI_CTRL);
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
sparc64: Kill hand-crafted I/O accessors in PCI controller drivers. Use existing upa_{read,write}q() interfaces instead. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-09-10 19:13:10 +08:00
upa_writeq((SCHIZO_PCIAFSR_PMA | SCHIZO_PCIAFSR_PTA |
SCHIZO_PCIAFSR_PRTRY | SCHIZO_PCIAFSR_PPERR |
SCHIZO_PCIAFSR_PTTO | SCHIZO_PCIAFSR_PUNUS |
SCHIZO_PCIAFSR_SMA | SCHIZO_PCIAFSR_STA |
SCHIZO_PCIAFSR_SRTRY | SCHIZO_PCIAFSR_SPERR |
SCHIZO_PCIAFSR_STTO | SCHIZO_PCIAFSR_SUNUS),
pbm->pbm_regs + SCHIZO_PCI_AFSR);
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
/* Make all Safari error conditions fatal except unmapped
* errors which we make generate interrupts.
*/
err_mask = (BUS_ERROR_BADCMD | BUS_ERROR_SSMDIS |
BUS_ERROR_BADMA | BUS_ERROR_BADMB |
BUS_ERROR_BADMC |
BUS_ERROR_CPU1PS | BUS_ERROR_CPU1PB |
BUS_ERROR_CPU0PS | BUS_ERROR_CPU0PB |
BUS_ERROR_CIQTO |
BUS_ERROR_LPQTO | BUS_ERROR_SFPQTO |
BUS_ERROR_UFPQTO | BUS_ERROR_APERR |
BUS_ERROR_BUSERR | BUS_ERROR_TIMEOUT |
BUS_ERROR_ILL);
#if 1
/* XXX Something wrong with some Excalibur systems
* XXX Sun is shipping. The behavior on a 2-cpu
* XXX machine is that both CPU1 parity error bits
* XXX are set and are immediately set again when
* XXX their error status bits are cleared. Just
* XXX ignore them for now. -DaveM
*/
err_mask &= ~(BUS_ERROR_CPU1PS | BUS_ERROR_CPU1PB |
BUS_ERROR_CPU0PS | BUS_ERROR_CPU0PB);
#endif
sparc64: Kill hand-crafted I/O accessors in PCI controller drivers. Use existing upa_{read,write}q() interfaces instead. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-09-10 19:13:10 +08:00
upa_writeq((SCHIZO_SAFERRCTRL_EN | err_mask),
pbm->controller_regs + SCHIZO_SAFARI_ERRCTRL);
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
}
[PATCH] Make sparc64 use setup-res.c There were three changes necessary in order to allow sparc64 to use setup-res.c: 1) Sparc64 roots the PCI I/O and MEM address space using parent resources contained in the PCI controller structure. I'm actually surprised no other platforms do this, especially ones like Alpha and PPC{,64}. These resources get linked into the iomem/ioport tree when PCI controllers are probed. So the hierarchy looks like this: iomem --| PCI controller 1 MEM space --| device 1 device 2 etc. PCI controller 2 MEM space --| ... ioport --| PCI controller 1 IO space --| ... PCI controller 2 IO space --| ... You get the idea. The drivers/pci/setup-res.c code allocates using plain iomem_space and ioport_space as the root, so that wouldn't work with the above setup. So I added a pcibios_select_root() that is used to handle this. It uses the PCI controller struct's io_space and mem_space on sparc64, and io{port,mem}_resource on every other platform to keep current behavior. 2) quirk_io_region() is buggy. It takes in raw BUS view addresses and tries to use them as a PCI resource. pci_claim_resource() expects the resource to be fully formed when it gets called. The sparc64 implementation would do the translation but that's absolutely wrong, because if the same resource gets released then re-claimed we'll adjust things twice. So I fixed up quirk_io_region() to do the proper pcibios_bus_to_resource() conversion before passing it on to pci_claim_resource(). 3) I was mistakedly __init'ing the function methods the PCI controller drivers provide on sparc64 to implement some parts of these routines. This was, of course, easy to fix. So we end up with the following, and that nasty SPARC64 makefile ifdef in drivers/pci/Makefile is finally zapped. Signed-off-by: David S. Miller <davem@davemloft.net> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2005-08-09 04:19:08 +08:00
static void pbm_config_busmastering(struct pci_pbm_info *pbm)
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
{
u8 *addr;
/* Set cache-line size to 64 bytes, this is actually
* a nop but I do it for completeness.
*/
addr = schizo_pci_config_mkaddr(pbm, pbm->pci_first_busno,
0, PCI_CACHE_LINE_SIZE);
pci_config_write8(addr, 64 / sizeof(u32));
/* Set PBM latency timer to 64 PCI clocks. */
addr = schizo_pci_config_mkaddr(pbm, pbm->pci_first_busno,
0, PCI_LATENCY_TIMER);
pci_config_write8(addr, 64);
}
sparc: remove __devinit, __devexit annotations __devinit, __devexit annotations are nops - so drop them. Likewise for __devexit_p. Adjusted alignment of arguments when needed. Signed-off-by: Sam Ravnborg <sam@ravnborg.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-01-01 23:02:33 +08:00
static void schizo_scan_bus(struct pci_pbm_info *pbm, struct device *parent)
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
{
[SPARC64] PCI: Use root list of pbm's instead of pci_controller_info's The idea is to move more and more things into the pbm, with the eventual goal of eliminating the pci_controller_info entirely as there really isn't any need for it. This stage of the transformations requires some reworking of the PCI error interrupt handling. It might be tricky to get rid of the pci_controller_info parenting for a few reasons: 1) When we get an uncorrectable or correctable error we want to interrogate the IOMMU and streaming cache of both PBMs for error status. These errors come from the UPA front-end which is shared between the two PBM PCI bus segments. Historically speaking this is why I choose the datastructure hierarchy of pci_controller_info-->pci_pbm_info 2) The probing does a portid/devhandle match to look for the 'other' pbm, but this is entirely an artifact and can be eliminated trivially. What we could do to solve #1 is to have a "buddy" pointer from one pbm to another. Signed-off-by: David S. Miller <davem@davemloft.net>
2007-05-08 14:06:27 +08:00
pbm_config_busmastering(pbm);
pbm->is_66mhz_capable =
of: Always use 'struct device.of_node' to get device node pointer. The following structure elements duplicate the information in 'struct device.of_node' and so are being eliminated. This patch makes all readers of these elements use device.of_node instead. (struct of_device *)->node (struct dev_archdata *)->prom_node (sparc) (struct dev_archdata *)->of_node (powerpc & microblaze) Signed-off-by: Grant Likely <grant.likely@secretlab.ca>
2010-04-14 07:12:29 +08:00
(of_find_property(pbm->op->dev.of_node, "66mhz-capable", NULL)
[SPARC64]: Use in-kernel OBP device tree for PCI controller probing. It can be pushed even further down, but this is a first step. Signed-off-by: David S. Miller <davem@davemloft.net>
2006-06-22 09:18:47 +08:00
!= NULL);
[SPARC64]: Minor cleanups to schizo pci controller driver. Signed-off-by: David S. Miller <davem@davemloft.net>
2007-03-02 03:20:37 +08:00
sparc64: Pass proper parent device down into root pci_create_bus() call. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-09-02 09:32:22 +08:00
pbm->pci_bus = pci_scan_one_pbm(pbm, parent);
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
[SPARC64] PCI: Use root list of pbm's instead of pci_controller_info's The idea is to move more and more things into the pbm, with the eventual goal of eliminating the pci_controller_info entirely as there really isn't any need for it. This stage of the transformations requires some reworking of the PCI error interrupt handling. It might be tricky to get rid of the pci_controller_info parenting for a few reasons: 1) When we get an uncorrectable or correctable error we want to interrogate the IOMMU and streaming cache of both PBMs for error status. These errors come from the UPA front-end which is shared between the two PBM PCI bus segments. Historically speaking this is why I choose the datastructure hierarchy of pci_controller_info-->pci_pbm_info 2) The probing does a portid/devhandle match to look for the 'other' pbm, but this is entirely an artifact and can be eliminated trivially. What we could do to solve #1 is to have a "buddy" pointer from one pbm to another. Signed-off-by: David S. Miller <davem@davemloft.net>
2007-05-08 14:06:27 +08:00
if (pbm->chip_type == PBM_CHIP_TYPE_TOMATILLO)
tomatillo_register_error_handlers(pbm);
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
else
[SPARC64] PCI: Use root list of pbm's instead of pci_controller_info's The idea is to move more and more things into the pbm, with the eventual goal of eliminating the pci_controller_info entirely as there really isn't any need for it. This stage of the transformations requires some reworking of the PCI error interrupt handling. It might be tricky to get rid of the pci_controller_info parenting for a few reasons: 1) When we get an uncorrectable or correctable error we want to interrogate the IOMMU and streaming cache of both PBMs for error status. These errors come from the UPA front-end which is shared between the two PBM PCI bus segments. Historically speaking this is why I choose the datastructure hierarchy of pci_controller_info-->pci_pbm_info 2) The probing does a portid/devhandle match to look for the 'other' pbm, but this is entirely an artifact and can be eliminated trivially. What we could do to solve #1 is to have a "buddy" pointer from one pbm to another. Signed-off-by: David S. Miller <davem@davemloft.net>
2007-05-08 14:06:27 +08:00
schizo_register_error_handlers(pbm);
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
}
#define SCHIZO_STRBUF_CONTROL (0x02800UL)
#define SCHIZO_STRBUF_FLUSH (0x02808UL)
#define SCHIZO_STRBUF_FSYNC (0x02810UL)
#define SCHIZO_STRBUF_CTXFLUSH (0x02818UL)
#define SCHIZO_STRBUF_CTXMATCH (0x10000UL)
static void schizo_pbm_strbuf_init(struct pci_pbm_info *pbm)
{
unsigned long base = pbm->pbm_regs;
u64 control;
if (pbm->chip_type == PBM_CHIP_TYPE_TOMATILLO) {
/* TOMATILLO lacks streaming cache. */
return;
}
/* SCHIZO has context flushing. */
pbm->stc.strbuf_control = base + SCHIZO_STRBUF_CONTROL;
pbm->stc.strbuf_pflush = base + SCHIZO_STRBUF_FLUSH;
pbm->stc.strbuf_fsync = base + SCHIZO_STRBUF_FSYNC;
pbm->stc.strbuf_ctxflush = base + SCHIZO_STRBUF_CTXFLUSH;
pbm->stc.strbuf_ctxmatch_base = base + SCHIZO_STRBUF_CTXMATCH;
pbm->stc.strbuf_flushflag = (volatile unsigned long *)
((((unsigned long)&pbm->stc.__flushflag_buf[0])
+ 63UL)
& ~63UL);
pbm->stc.strbuf_flushflag_pa = (unsigned long)
__pa(pbm->stc.strbuf_flushflag);
/* Turn off LRU locking and diag mode, enable the
* streaming buffer and leave the rerun-disable
* setting however OBP set it.
*/
sparc64: Kill hand-crafted I/O accessors in PCI controller drivers. Use existing upa_{read,write}q() interfaces instead. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-09-10 19:13:10 +08:00
control = upa_readq(pbm->stc.strbuf_control);
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
control &= ~(SCHIZO_STRBUF_CTRL_LPTR |
SCHIZO_STRBUF_CTRL_LENAB |
SCHIZO_STRBUF_CTRL_DENAB);
control |= SCHIZO_STRBUF_CTRL_ENAB;
sparc64: Kill hand-crafted I/O accessors in PCI controller drivers. Use existing upa_{read,write}q() interfaces instead. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-09-10 19:13:10 +08:00
upa_writeq(control, pbm->stc.strbuf_control);
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
pbm->stc.strbuf_enabled = 1;
}
#define SCHIZO_IOMMU_CONTROL (0x00200UL)
#define SCHIZO_IOMMU_TSBBASE (0x00208UL)
#define SCHIZO_IOMMU_FLUSH (0x00210UL)
#define SCHIZO_IOMMU_CTXFLUSH (0x00218UL)
[SPARC64]: Fix conflicts in SBUS/PCI/EBUS/ISA DMA handling. Fully unify all of the DMA ops so that subordinate bus types to the DMA operation providers (such as ebus, isa, of_device) can work transparently. Basically, we just make sure that for every system device we create, the dev->archdata 'iommu' and 'stc' fields are filled in. Then we have two platform variants of the DMA ops, one for SUN4U which actually programs the real hardware, and one for SUN4V which makes hypervisor calls. This also fixes the crashes in parport_pc on sparc64, reported by Meelis Roos. Signed-off-by: David S. Miller <davem@davemloft.net>
2007-07-28 13:39:14 +08:00
static int schizo_pbm_iommu_init(struct pci_pbm_info *pbm)
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
{
pci_schizo: Use of_get_property() and delete spurious local vars. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-09-02 11:21:15 +08:00
static const u32 vdma_default[] = { 0xc0000000, 0x40000000 };
[SPARC64]: Consolidate common PCI IOMMU init code. All the PCI controller drivers were doing the same thing setting up the IOMMU software state, put it all in one spot. Signed-off-by: David S. Miller <davem@davemloft.net>
2005-10-14 12:10:08 +08:00
unsigned long i, tagbase, database;
pci_schizo: Use of_get_property() and delete spurious local vars. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-09-02 11:21:15 +08:00
struct iommu *iommu = pbm->iommu;
[SPARC64]: Fix conflicts in SBUS/PCI/EBUS/ISA DMA handling. Fully unify all of the DMA ops so that subordinate bus types to the DMA operation providers (such as ebus, isa, of_device) can work transparently. Basically, we just make sure that for every system device we create, the dev->archdata 'iommu' and 'stc' fields are filled in. Then we have two platform variants of the DMA ops, one for SUN4U which actually programs the real hardware, and one for SUN4V which makes hypervisor calls. This also fixes the crashes in parport_pc on sparc64, reported by Meelis Roos. Signed-off-by: David S. Miller <davem@davemloft.net>
2007-07-28 13:39:14 +08:00
int tsbsize, err;
pci_schizo: Use of_get_property() and delete spurious local vars. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-09-02 11:21:15 +08:00
const u32 *vdma;
u32 dma_mask;
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
u64 control;
of: Always use 'struct device.of_node' to get device node pointer. The following structure elements duplicate the information in 'struct device.of_node' and so are being eliminated. This patch makes all readers of these elements use device.of_node instead. (struct of_device *)->node (struct dev_archdata *)->prom_node (sparc) (struct dev_archdata *)->of_node (powerpc & microblaze) Signed-off-by: Grant Likely <grant.likely@secretlab.ca>
2010-04-14 07:12:29 +08:00
vdma = of_get_property(pbm->op->dev.of_node, "virtual-dma", NULL);
pci_schizo: Use of_get_property() and delete spurious local vars. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-09-02 11:21:15 +08:00
if (!vdma)
vdma = vdma_default;
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
dma_mask = vdma[0];
switch (vdma[1]) {
case 0x20000000:
dma_mask |= 0x1fffffff;
tsbsize = 64;
break;
case 0x40000000:
dma_mask |= 0x3fffffff;
tsbsize = 128;
break;
case 0x80000000:
dma_mask |= 0x7fffffff;
tsbsize = 128;
break;
default:
sparc64: Convert SCHIZO PCI controller driver into a real driver. The idea is to convert all of the PCI controller drivers into genuine OF drivers, then we can get rid of this terrible probing table and infrastructure in arch/sparc64/kernel/pci.c Signed-off-by: David S. Miller <davem@davemloft.net>
2008-08-30 17:30:24 +08:00
printk(KERN_ERR PFX "Strange virtual-dma size.\n");
return -EINVAL;
}
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
/* Register addresses, SCHIZO has iommu ctx flushing. */
iommu->iommu_control = pbm->pbm_regs + SCHIZO_IOMMU_CONTROL;
iommu->iommu_tsbbase = pbm->pbm_regs + SCHIZO_IOMMU_TSBBASE;
iommu->iommu_flush = pbm->pbm_regs + SCHIZO_IOMMU_FLUSH;
[SPARC64]: Fix conflicts in SBUS/PCI/EBUS/ISA DMA handling. Fully unify all of the DMA ops so that subordinate bus types to the DMA operation providers (such as ebus, isa, of_device) can work transparently. Basically, we just make sure that for every system device we create, the dev->archdata 'iommu' and 'stc' fields are filled in. Then we have two platform variants of the DMA ops, one for SUN4U which actually programs the real hardware, and one for SUN4V which makes hypervisor calls. This also fixes the crashes in parport_pc on sparc64, reported by Meelis Roos. Signed-off-by: David S. Miller <davem@davemloft.net>
2007-07-28 13:39:14 +08:00
iommu->iommu_tags = iommu->iommu_flush + (0xa580UL - 0x0210UL);
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
iommu->iommu_ctxflush = pbm->pbm_regs + SCHIZO_IOMMU_CTXFLUSH;
/* We use the main control/status register of SCHIZO as the write
* completion register.
*/
iommu->write_complete_reg = pbm->controller_regs + 0x10000UL;
/*
* Invalidate TLB Entries.
*/
sparc64: Kill hand-crafted I/O accessors in PCI controller drivers. Use existing upa_{read,write}q() interfaces instead. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-09-10 19:13:10 +08:00
control = upa_readq(iommu->iommu_control);
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
control |= SCHIZO_IOMMU_CTRL_DENAB;
sparc64: Kill hand-crafted I/O accessors in PCI controller drivers. Use existing upa_{read,write}q() interfaces instead. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-09-10 19:13:10 +08:00
upa_writeq(control, iommu->iommu_control);
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
tagbase = SCHIZO_IOMMU_TAG, database = SCHIZO_IOMMU_DATA;
sparc64: Convert SCHIZO PCI controller driver into a real driver. The idea is to convert all of the PCI controller drivers into genuine OF drivers, then we can get rid of this terrible probing table and infrastructure in arch/sparc64/kernel/pci.c Signed-off-by: David S. Miller <davem@davemloft.net>
2008-08-30 17:30:24 +08:00
for (i = 0; i < 16; i++) {
sparc64: Kill hand-crafted I/O accessors in PCI controller drivers. Use existing upa_{read,write}q() interfaces instead. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-09-10 19:13:10 +08:00
upa_writeq(0, pbm->pbm_regs + tagbase + (i * 8UL));
upa_writeq(0, pbm->pbm_regs + database + (i * 8UL));
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
}
/* Leave diag mode enabled for full-flushing done
* in pci_iommu.c
*/
[SPARC64]: NUMA device infrastructure. Record and propagate NUMA information for devices. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-03-19 19:52:48 +08:00
err = iommu_table_init(iommu, tsbsize * 8 * 1024, vdma[0], dma_mask,
pbm->numa_node);
sparc64: Convert SCHIZO PCI controller driver into a real driver. The idea is to convert all of the PCI controller drivers into genuine OF drivers, then we can get rid of this terrible probing table and infrastructure in arch/sparc64/kernel/pci.c Signed-off-by: David S. Miller <davem@davemloft.net>
2008-08-30 17:30:24 +08:00
if (err) {
printk(KERN_ERR PFX "iommu_table_init() fails with %d\n", err);
[SPARC64]: Fix conflicts in SBUS/PCI/EBUS/ISA DMA handling. Fully unify all of the DMA ops so that subordinate bus types to the DMA operation providers (such as ebus, isa, of_device) can work transparently. Basically, we just make sure that for every system device we create, the dev->archdata 'iommu' and 'stc' fields are filled in. Then we have two platform variants of the DMA ops, one for SUN4U which actually programs the real hardware, and one for SUN4V which makes hypervisor calls. This also fixes the crashes in parport_pc on sparc64, reported by Meelis Roos. Signed-off-by: David S. Miller <davem@davemloft.net>
2007-07-28 13:39:14 +08:00
return err;
sparc64: Convert SCHIZO PCI controller driver into a real driver. The idea is to convert all of the PCI controller drivers into genuine OF drivers, then we can get rid of this terrible probing table and infrastructure in arch/sparc64/kernel/pci.c Signed-off-by: David S. Miller <davem@davemloft.net>
2008-08-30 17:30:24 +08:00
}
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
sparc64: Kill hand-crafted I/O accessors in PCI controller drivers. Use existing upa_{read,write}q() interfaces instead. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-09-10 19:13:10 +08:00
upa_writeq(__pa(iommu->page_table), iommu->iommu_tsbbase);
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
sparc64: Kill hand-crafted I/O accessors in PCI controller drivers. Use existing upa_{read,write}q() interfaces instead. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-09-10 19:13:10 +08:00
control = upa_readq(iommu->iommu_control);
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
control &= ~(SCHIZO_IOMMU_CTRL_TSBSZ | SCHIZO_IOMMU_CTRL_TBWSZ);
switch (tsbsize) {
case 64:
control |= SCHIZO_IOMMU_TSBSZ_64K;
break;
case 128:
control |= SCHIZO_IOMMU_TSBSZ_128K;
break;
sparc64: Convert SCHIZO PCI controller driver into a real driver. The idea is to convert all of the PCI controller drivers into genuine OF drivers, then we can get rid of this terrible probing table and infrastructure in arch/sparc64/kernel/pci.c Signed-off-by: David S. Miller <davem@davemloft.net>
2008-08-30 17:30:24 +08:00
}
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
control |= SCHIZO_IOMMU_CTRL_ENAB;
sparc64: Kill hand-crafted I/O accessors in PCI controller drivers. Use existing upa_{read,write}q() interfaces instead. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-09-10 19:13:10 +08:00
upa_writeq(control, iommu->iommu_control);
[SPARC64]: Fix conflicts in SBUS/PCI/EBUS/ISA DMA handling. Fully unify all of the DMA ops so that subordinate bus types to the DMA operation providers (such as ebus, isa, of_device) can work transparently. Basically, we just make sure that for every system device we create, the dev->archdata 'iommu' and 'stc' fields are filled in. Then we have two platform variants of the DMA ops, one for SUN4U which actually programs the real hardware, and one for SUN4V which makes hypervisor calls. This also fixes the crashes in parport_pc on sparc64, reported by Meelis Roos. Signed-off-by: David S. Miller <davem@davemloft.net>
2007-07-28 13:39:14 +08:00
return 0;
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
}
#define SCHIZO_PCI_IRQ_RETRY (0x1a00UL)
#define SCHIZO_IRQ_RETRY_INF 0xffUL
#define SCHIZO_PCI_DIAG (0x2020UL)
#define SCHIZO_PCIDIAG_D_BADECC (1UL << 10UL) /* Disable BAD ECC errors (Schizo) */
#define SCHIZO_PCIDIAG_D_BYPASS (1UL << 9UL) /* Disable MMU bypass mode (Schizo/Tomatillo) */
#define SCHIZO_PCIDIAG_D_TTO (1UL << 8UL) /* Disable TTO errors (Schizo/Tomatillo) */
#define SCHIZO_PCIDIAG_D_RTRYARB (1UL << 7UL) /* Disable retry arbitration (Schizo) */
#define SCHIZO_PCIDIAG_D_RETRY (1UL << 6UL) /* Disable retry limit (Schizo/Tomatillo) */
#define SCHIZO_PCIDIAG_D_INTSYNC (1UL << 5UL) /* Disable interrupt/DMA synch (Schizo/Tomatillo) */
#define SCHIZO_PCIDIAG_I_DMA_PARITY (1UL << 3UL) /* Invert DMA parity (Schizo/Tomatillo) */
#define SCHIZO_PCIDIAG_I_PIOD_PARITY (1UL << 2UL) /* Invert PIO data parity (Schizo/Tomatillo) */
#define SCHIZO_PCIDIAG_I_PIOA_PARITY (1UL << 1UL) /* Invert PIO address parity (Schizo/Tomatillo) */
#define TOMATILLO_PCI_IOC_CSR (0x2248UL)
#define TOMATILLO_IOC_PART_WPENAB 0x0000000000080000UL
#define TOMATILLO_IOC_RDMULT_PENAB 0x0000000000040000UL
#define TOMATILLO_IOC_RDONE_PENAB 0x0000000000020000UL
#define TOMATILLO_IOC_RDLINE_PENAB 0x0000000000010000UL
#define TOMATILLO_IOC_RDMULT_PLEN 0x000000000000c000UL
#define TOMATILLO_IOC_RDMULT_PLEN_SHIFT 14UL
#define TOMATILLO_IOC_RDONE_PLEN 0x0000000000003000UL
#define TOMATILLO_IOC_RDONE_PLEN_SHIFT 12UL
#define TOMATILLO_IOC_RDLINE_PLEN 0x0000000000000c00UL
#define TOMATILLO_IOC_RDLINE_PLEN_SHIFT 10UL
#define TOMATILLO_IOC_PREF_OFF 0x00000000000003f8UL
#define TOMATILLO_IOC_PREF_OFF_SHIFT 3UL
#define TOMATILLO_IOC_RDMULT_CPENAB 0x0000000000000004UL
#define TOMATILLO_IOC_RDONE_CPENAB 0x0000000000000002UL
#define TOMATILLO_IOC_RDLINE_CPENAB 0x0000000000000001UL
#define TOMATILLO_PCI_IOC_TDIAG (0x2250UL)
#define TOMATILLO_PCI_IOC_DDIAG (0x2290UL)
[PATCH] Make sparc64 use setup-res.c There were three changes necessary in order to allow sparc64 to use setup-res.c: 1) Sparc64 roots the PCI I/O and MEM address space using parent resources contained in the PCI controller structure. I'm actually surprised no other platforms do this, especially ones like Alpha and PPC{,64}. These resources get linked into the iomem/ioport tree when PCI controllers are probed. So the hierarchy looks like this: iomem --| PCI controller 1 MEM space --| device 1 device 2 etc. PCI controller 2 MEM space --| ... ioport --| PCI controller 1 IO space --| ... PCI controller 2 IO space --| ... You get the idea. The drivers/pci/setup-res.c code allocates using plain iomem_space and ioport_space as the root, so that wouldn't work with the above setup. So I added a pcibios_select_root() that is used to handle this. It uses the PCI controller struct's io_space and mem_space on sparc64, and io{port,mem}_resource on every other platform to keep current behavior. 2) quirk_io_region() is buggy. It takes in raw BUS view addresses and tries to use them as a PCI resource. pci_claim_resource() expects the resource to be fully formed when it gets called. The sparc64 implementation would do the translation but that's absolutely wrong, because if the same resource gets released then re-claimed we'll adjust things twice. So I fixed up quirk_io_region() to do the proper pcibios_bus_to_resource() conversion before passing it on to pci_claim_resource(). 3) I was mistakedly __init'ing the function methods the PCI controller drivers provide on sparc64 to implement some parts of these routines. This was, of course, easy to fix. So we end up with the following, and that nasty SPARC64 makefile ifdef in drivers/pci/Makefile is finally zapped. Signed-off-by: David S. Miller <davem@davemloft.net> Signed-off-by: Greg Kroah-Hartman <gregkh@suse.de>
2005-08-09 04:19:08 +08:00
static void schizo_pbm_hw_init(struct pci_pbm_info *pbm)
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
{
u64 tmp;
sparc64: Kill hand-crafted I/O accessors in PCI controller drivers. Use existing upa_{read,write}q() interfaces instead. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-09-10 19:13:10 +08:00
upa_writeq(5, pbm->pbm_regs + SCHIZO_PCI_IRQ_RETRY);
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
sparc64: Kill hand-crafted I/O accessors in PCI controller drivers. Use existing upa_{read,write}q() interfaces instead. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-09-10 19:13:10 +08:00
tmp = upa_readq(pbm->pbm_regs + SCHIZO_PCI_CTRL);
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
[SPARC64]: Small Schizo PCI controller programming tweaks. Use macro instead of magic value for Tomatillo discard- timeout interrupt enable register bit. Leave OBP programming PTO value unless Tomatillo and version >= 0x2. If no-bus-parking property is present, explicitly clear PCICTRL_PARK bit. Signed-off-by: David S. Miller <davem@davemloft.net>
2005-07-05 05:53:33 +08:00
/* Enable arbiter for all PCI slots. */
tmp |= 0xff;
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
if (pbm->chip_type == PBM_CHIP_TYPE_TOMATILLO &&
pbm->chip_version >= 0x2)
tmp |= 0x3UL << SCHIZO_PCICTRL_PTO_SHIFT;
of: Always use 'struct device.of_node' to get device node pointer. The following structure elements duplicate the information in 'struct device.of_node' and so are being eliminated. This patch makes all readers of these elements use device.of_node instead. (struct of_device *)->node (struct dev_archdata *)->prom_node (sparc) (struct dev_archdata *)->of_node (powerpc & microblaze) Signed-off-by: Grant Likely <grant.likely@secretlab.ca>
2010-04-14 07:12:29 +08:00
if (!of_find_property(pbm->op->dev.of_node, "no-bus-parking", NULL))
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
tmp |= SCHIZO_PCICTRL_PARK;
[SPARC64]: Small Schizo PCI controller programming tweaks. Use macro instead of magic value for Tomatillo discard- timeout interrupt enable register bit. Leave OBP programming PTO value unless Tomatillo and version >= 0x2. If no-bus-parking property is present, explicitly clear PCICTRL_PARK bit. Signed-off-by: David S. Miller <davem@davemloft.net>
2005-07-05 05:53:33 +08:00
else
tmp &= ~SCHIZO_PCICTRL_PARK;
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
if (pbm->chip_type == PBM_CHIP_TYPE_TOMATILLO &&
pbm->chip_version <= 0x1)
[SPARC64]: Small Schizo PCI controller programming tweaks. Use macro instead of magic value for Tomatillo discard- timeout interrupt enable register bit. Leave OBP programming PTO value unless Tomatillo and version >= 0x2. If no-bus-parking property is present, explicitly clear PCICTRL_PARK bit. Signed-off-by: David S. Miller <davem@davemloft.net>
2005-07-05 05:53:33 +08:00
tmp |= SCHIZO_PCICTRL_DTO_INT;
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
else
[SPARC64]: Small Schizo PCI controller programming tweaks. Use macro instead of magic value for Tomatillo discard- timeout interrupt enable register bit. Leave OBP programming PTO value unless Tomatillo and version >= 0x2. If no-bus-parking property is present, explicitly clear PCICTRL_PARK bit. Signed-off-by: David S. Miller <davem@davemloft.net>
2005-07-05 05:53:33 +08:00
tmp &= ~SCHIZO_PCICTRL_DTO_INT;
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
if (pbm->chip_type == PBM_CHIP_TYPE_TOMATILLO)
tmp |= (SCHIZO_PCICTRL_MRM_PREF |
SCHIZO_PCICTRL_RDO_PREF |
SCHIZO_PCICTRL_RDL_PREF);
sparc64: Kill hand-crafted I/O accessors in PCI controller drivers. Use existing upa_{read,write}q() interfaces instead. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-09-10 19:13:10 +08:00
upa_writeq(tmp, pbm->pbm_regs + SCHIZO_PCI_CTRL);
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
sparc64: Kill hand-crafted I/O accessors in PCI controller drivers. Use existing upa_{read,write}q() interfaces instead. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-09-10 19:13:10 +08:00
tmp = upa_readq(pbm->pbm_regs + SCHIZO_PCI_DIAG);
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
tmp &= ~(SCHIZO_PCIDIAG_D_RTRYARB |
SCHIZO_PCIDIAG_D_RETRY |
SCHIZO_PCIDIAG_D_INTSYNC);
sparc64: Kill hand-crafted I/O accessors in PCI controller drivers. Use existing upa_{read,write}q() interfaces instead. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-09-10 19:13:10 +08:00
upa_writeq(tmp, pbm->pbm_regs + SCHIZO_PCI_DIAG);
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
if (pbm->chip_type == PBM_CHIP_TYPE_TOMATILLO) {
/* Clear prefetch lengths to workaround a bug in
* Jalapeno...
*/
tmp = (TOMATILLO_IOC_PART_WPENAB |
(1 << TOMATILLO_IOC_PREF_OFF_SHIFT) |
TOMATILLO_IOC_RDMULT_CPENAB |
TOMATILLO_IOC_RDONE_CPENAB |
TOMATILLO_IOC_RDLINE_CPENAB);
sparc64: Kill hand-crafted I/O accessors in PCI controller drivers. Use existing upa_{read,write}q() interfaces instead. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-09-10 19:13:10 +08:00
upa_writeq(tmp, pbm->pbm_regs + TOMATILLO_PCI_IOC_CSR);
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
}
}
sparc: remove __devinit, __devexit annotations __devinit, __devexit annotations are nops - so drop them. Likewise for __devexit_p. Adjusted alignment of arguments when needed. Signed-off-by: Sam Ravnborg <sam@ravnborg.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-01-01 23:02:33 +08:00
static int schizo_pbm_init(struct pci_pbm_info *pbm,
struct platform_device *op, u32 portid,
int chip_type)
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
{
[SPARC64]: Fix PCI rework to adhere to of_get_property() const return. Signed-off-by: David S. Miller <davem@davemloft.net>
2007-03-29 16:50:16 +08:00
const struct linux_prom64_registers *regs;
of: Always use 'struct device.of_node' to get device node pointer. The following structure elements duplicate the information in 'struct device.of_node' and so are being eliminated. This patch makes all readers of these elements use device.of_node instead. (struct of_device *)->node (struct dev_archdata *)->prom_node (sparc) (struct dev_archdata *)->of_node (powerpc & microblaze) Signed-off-by: Grant Likely <grant.likely@secretlab.ca>
2010-04-14 07:12:29 +08:00
struct device_node *dp = op->dev.of_node;
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
const char *chipset_name;
sparc64: Fix build errors with gcc-4.6.0 Most of the warnings emitted (we fail arch/sparc file builds with -Werror) were legitimate but harmless, however one case (n2_pcr_write) was a genuine bug. Based almost entirely upon a patch by Sam Ravnborg. Reported-by: Dennis Gilmore <dennis@ausil.us> Signed-off-by: David S. Miller <davem@davemloft.net>
2011-02-27 15:40:02 +08:00
int err;
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
switch (chip_type) {
case PBM_CHIP_TYPE_TOMATILLO:
chipset_name = "TOMATILLO";
break;
case PBM_CHIP_TYPE_SCHIZO_PLUS:
chipset_name = "SCHIZO+";
break;
case PBM_CHIP_TYPE_SCHIZO:
default:
chipset_name = "SCHIZO";
break;
sparc: Remove unnecessary semicolons Semicolons are not necessary after switch/while/for/if braces so remove them. Signed-off-by: Joe Perches <joe@perches.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2011-06-03 22:45:23 +08:00
}
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
/* For SCHIZO, three OBP regs:
* 1) PBM controller regs
* 2) Schizo front-end controller regs (same for both PBMs)
* 3) PBM PCI config space
*
* For TOMATILLO, four OBP regs:
* 1) PBM controller regs
* 2) Tomatillo front-end controller regs
* 3) PBM PCI config space
* 4) Ichip regs
*/
[SPARC64]: Minor cleanups to schizo pci controller driver. Signed-off-by: David S. Miller <davem@davemloft.net>
2007-03-02 03:20:37 +08:00
regs = of_get_property(dp, "reg", NULL);
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
[SPARC64] PCI: Use root list of pbm's instead of pci_controller_info's The idea is to move more and more things into the pbm, with the eventual goal of eliminating the pci_controller_info entirely as there really isn't any need for it. This stage of the transformations requires some reworking of the PCI error interrupt handling. It might be tricky to get rid of the pci_controller_info parenting for a few reasons: 1) When we get an uncorrectable or correctable error we want to interrogate the IOMMU and streaming cache of both PBMs for error status. These errors come from the UPA front-end which is shared between the two PBM PCI bus segments. Historically speaking this is why I choose the datastructure hierarchy of pci_controller_info-->pci_pbm_info 2) The probing does a portid/devhandle match to look for the 'other' pbm, but this is entirely an artifact and can be eliminated trivially. What we could do to solve #1 is to have a "buddy" pointer from one pbm to another. Signed-off-by: David S. Miller <davem@davemloft.net>
2007-05-08 14:06:27 +08:00
pbm->next = pci_pbm_root;
pci_pbm_root = pbm;
[SPARC64]: NUMA device infrastructure. Record and propagate NUMA information for devices. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-03-19 19:52:48 +08:00
pbm->numa_node = -1;
[SPARC64] PCI: Consolidate PCI access code into pci_common.c All the sun4u controllers do the same thing to compute the physical I/O address to poke, and we can move the sun4v code into this common location too. This one needs a bit of testing, in particular the Sabre code had some funny stuff that would break up u16 and/or u32 accesses into pieces and I didn't think that was needed any more. If it is we need to find out why and add back code to do it again. Signed-off-by: David S. Miller <davem@davemloft.net>
2007-05-09 17:35:27 +08:00
pbm->pci_ops = &sun4u_pci_ops;
pbm->config_space_reg_bits = 8;
[SPARC64] PCI: Use root list of pbm's instead of pci_controller_info's The idea is to move more and more things into the pbm, with the eventual goal of eliminating the pci_controller_info entirely as there really isn't any need for it. This stage of the transformations requires some reworking of the PCI error interrupt handling. It might be tricky to get rid of the pci_controller_info parenting for a few reasons: 1) When we get an uncorrectable or correctable error we want to interrogate the IOMMU and streaming cache of both PBMs for error status. These errors come from the UPA front-end which is shared between the two PBM PCI bus segments. Historically speaking this is why I choose the datastructure hierarchy of pci_controller_info-->pci_pbm_info 2) The probing does a portid/devhandle match to look for the 'other' pbm, but this is entirely an artifact and can be eliminated trivially. What we could do to solve #1 is to have a "buddy" pointer from one pbm to another. Signed-off-by: David S. Miller <davem@davemloft.net>
2007-05-08 14:06:27 +08:00
[SPARC64]: Move index info pci_pbm_info. Signed-off-by: David S. Miller <davem@davemloft.net>
2007-05-08 14:49:01 +08:00
pbm->index = pci_num_pbms++;
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
pbm->portid = portid;
sparc64: Record OF device instead of device node pointer in pci_pbm_info. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-09-10 15:19:28 +08:00
pbm->op = op;
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
pbm->chip_type = chip_type;
[SPARC64]: Minor cleanups to schizo pci controller driver. Signed-off-by: David S. Miller <davem@davemloft.net>
2007-03-02 03:20:37 +08:00
pbm->chip_version = of_getintprop_default(dp, "version#", 0);
pbm->chip_revision = of_getintprop_default(dp, "module-version#", 0);
[SPARC64]: Use in-kernel OBP device tree for PCI controller probing. It can be pushed even further down, but this is a first step. Signed-off-by: David S. Miller <davem@davemloft.net>
2006-06-22 09:18:47 +08:00
pbm->pbm_regs = regs[0].phys_addr;
pbm->controller_regs = regs[1].phys_addr - 0x10000UL;
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
[SPARC64]: Do proper DMA IRQ syncing on Tomatillo This was the main impetus behind adding the PCI IRQ shim. In order to properly order DMA writes wrt. interrupts, you have to write to a PCI controller register, then poll for that bit clearing. There is one bit for each interrupt source, and setting this register bit tells Tomatillo to drain all pending DMA from that device. Furthermore, Tomatillo's with revision less than 4 require us to do a block store due to some memory transaction ordering issues it has on JBUS. Signed-off-by: David S. Miller <davem@davemloft.net>
2005-07-05 04:26:04 +08:00
if (chip_type == PBM_CHIP_TYPE_TOMATILLO)
[SPARC64]: Use in-kernel OBP device tree for PCI controller probing. It can be pushed even further down, but this is a first step. Signed-off-by: David S. Miller <davem@davemloft.net>
2006-06-22 09:18:47 +08:00
pbm->sync_reg = regs[3].phys_addr + 0x1a18UL;
[SPARC64]: Do proper DMA IRQ syncing on Tomatillo This was the main impetus behind adding the PCI IRQ shim. In order to properly order DMA writes wrt. interrupts, you have to write to a PCI controller register, then poll for that bit clearing. There is one bit for each interrupt source, and setting this register bit tells Tomatillo to drain all pending DMA from that device. Furthermore, Tomatillo's with revision less than 4 require us to do a block store due to some memory transaction ordering issues it has on JBUS. Signed-off-by: David S. Miller <davem@davemloft.net>
2005-07-05 04:26:04 +08:00
[SPARC64]: Use in-kernel OBP device tree for PCI controller probing. It can be pushed even further down, but this is a first step. Signed-off-by: David S. Miller <davem@davemloft.net>
2006-06-22 09:18:47 +08:00
pbm->name = dp->full_name;
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
[SPARC64]: Use in-kernel OBP device tree for PCI controller probing. It can be pushed even further down, but this is a first step. Signed-off-by: David S. Miller <davem@davemloft.net>
2006-06-22 09:18:47 +08:00
printk("%s: %s PCI Bus Module ver[%x:%x]\n",
[SPARC64]: Minor cleanups to schizo pci controller driver. Signed-off-by: David S. Miller <davem@davemloft.net>
2007-03-02 03:20:37 +08:00
pbm->name, chipset_name,
[SPARC64]: Use in-kernel OBP device tree for PCI controller probing. It can be pushed even further down, but this is a first step. Signed-off-by: David S. Miller <davem@davemloft.net>
2006-06-22 09:18:47 +08:00
pbm->chip_version, pbm->chip_revision);
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
schizo_pbm_hw_init(pbm);
[SPARC64]: Consolidate PCI mem/io resource determination. It can be done for every PCI configuration using OF properties. Signed-off-by: David S. Miller <davem@davemloft.net>
2007-03-09 13:55:49 +08:00
pci_determine_mem_io_space(pbm);
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
[SPARC64] PCI: Use common routine to fetch PBM properties. Namely bus-range and ino-bitmap. This allows us also to eliminate pci_controller_info's pci_{first,last}_busno fields as only the pbm ones are used now. Signed-off-by: David S. Miller <davem@davemloft.net>
2007-05-08 12:51:41 +08:00
pci_get_pbm_props(pbm);
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
[SPARC64]: Fix conflicts in SBUS/PCI/EBUS/ISA DMA handling. Fully unify all of the DMA ops so that subordinate bus types to the DMA operation providers (such as ebus, isa, of_device) can work transparently. Basically, we just make sure that for every system device we create, the dev->archdata 'iommu' and 'stc' fields are filled in. Then we have two platform variants of the DMA ops, one for SUN4U which actually programs the real hardware, and one for SUN4V which makes hypervisor calls. This also fixes the crashes in parport_pc on sparc64, reported by Meelis Roos. Signed-off-by: David S. Miller <davem@davemloft.net>
2007-07-28 13:39:14 +08:00
err = schizo_pbm_iommu_init(pbm);
if (err)
return err;
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
schizo_pbm_strbuf_init(pbm);
[SPARC64]: Fix conflicts in SBUS/PCI/EBUS/ISA DMA handling. Fully unify all of the DMA ops so that subordinate bus types to the DMA operation providers (such as ebus, isa, of_device) can work transparently. Basically, we just make sure that for every system device we create, the dev->archdata 'iommu' and 'stc' fields are filled in. Then we have two platform variants of the DMA ops, one for SUN4U which actually programs the real hardware, and one for SUN4V which makes hypervisor calls. This also fixes the crashes in parport_pc on sparc64, reported by Meelis Roos. Signed-off-by: David S. Miller <davem@davemloft.net>
2007-07-28 13:39:14 +08:00
sparc64: Pass proper parent device down into root pci_create_bus() call. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-09-02 09:32:22 +08:00
schizo_scan_bus(pbm, &op->dev);
sparc64: Convert SCHIZO PCI controller driver into a real driver. The idea is to convert all of the PCI controller drivers into genuine OF drivers, then we can get rid of this terrible probing table and infrastructure in arch/sparc64/kernel/pci.c Signed-off-by: David S. Miller <davem@davemloft.net>
2008-08-30 17:30:24 +08:00
[SPARC64]: Fix conflicts in SBUS/PCI/EBUS/ISA DMA handling. Fully unify all of the DMA ops so that subordinate bus types to the DMA operation providers (such as ebus, isa, of_device) can work transparently. Basically, we just make sure that for every system device we create, the dev->archdata 'iommu' and 'stc' fields are filled in. Then we have two platform variants of the DMA ops, one for SUN4U which actually programs the real hardware, and one for SUN4V which makes hypervisor calls. This also fixes the crashes in parport_pc on sparc64, reported by Meelis Roos. Signed-off-by: David S. Miller <davem@davemloft.net>
2007-07-28 13:39:14 +08:00
return 0;
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
}
static inline int portid_compare(u32 x, u32 y, int chip_type)
{
if (chip_type == PBM_CHIP_TYPE_TOMATILLO) {
if (x == (y ^ 1))
return 1;
return 0;
}
return (x == y);
}
sparc: remove __devinit, __devexit annotations __devinit, __devexit annotations are nops - so drop them. Likewise for __devexit_p. Adjusted alignment of arguments when needed. Signed-off-by: Sam Ravnborg <sam@ravnborg.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-01-01 23:02:33 +08:00
static struct pci_pbm_info *schizo_find_sibling(u32 portid, int chip_type)
sparc64: Get rid of pci_controller_info. It is just used as a parent to encapsulate two PBM objects. But that layout is only really relevant and necessary for psycho PCI controllers, which unlike all the others share a single IOMMU instance between sibling PCI busses. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-09-10 14:54:02 +08:00
{
struct pci_pbm_info *pbm;
for (pbm = pci_pbm_root; pbm; pbm = pbm->next) {
if (portid_compare(pbm->portid, portid, chip_type))
return pbm;
}
return NULL;
}
sparc: remove __devinit, __devexit annotations __devinit, __devexit annotations are nops - so drop them. Likewise for __devexit_p. Adjusted alignment of arguments when needed. Signed-off-by: Sam Ravnborg <sam@ravnborg.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-01-01 23:02:33 +08:00
static int __schizo_init(struct platform_device *op, unsigned long chip_type)
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
{
of: Always use 'struct device.of_node' to get device node pointer. The following structure elements duplicate the information in 'struct device.of_node' and so are being eliminated. This patch makes all readers of these elements use device.of_node instead. (struct of_device *)->node (struct dev_archdata *)->prom_node (sparc) (struct dev_archdata *)->of_node (powerpc & microblaze) Signed-off-by: Grant Likely <grant.likely@secretlab.ca>
2010-04-14 07:12:29 +08:00
struct device_node *dp = op->dev.of_node;
[SPARC64] PCI: Use root list of pbm's instead of pci_controller_info's The idea is to move more and more things into the pbm, with the eventual goal of eliminating the pci_controller_info entirely as there really isn't any need for it. This stage of the transformations requires some reworking of the PCI error interrupt handling. It might be tricky to get rid of the pci_controller_info parenting for a few reasons: 1) When we get an uncorrectable or correctable error we want to interrogate the IOMMU and streaming cache of both PBMs for error status. These errors come from the UPA front-end which is shared between the two PBM PCI bus segments. Historically speaking this is why I choose the datastructure hierarchy of pci_controller_info-->pci_pbm_info 2) The probing does a portid/devhandle match to look for the 'other' pbm, but this is entirely an artifact and can be eliminated trivially. What we could do to solve #1 is to have a "buddy" pointer from one pbm to another. Signed-off-by: David S. Miller <davem@davemloft.net>
2007-05-08 14:06:27 +08:00
struct pci_pbm_info *pbm;
[SPARC64]: Convert PCI over to generic struct iommu/strbuf. Signed-off-by: David S. Miller <davem@davemloft.net>
2007-04-27 12:08:21 +08:00
struct iommu *iommu;
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
u32 portid;
sparc64: Simplify error handling in PCI controller probing. Based upon suggestions from Stephen Rothwell. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-08-31 16:33:52 +08:00
int err;
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
[SPARC64]: Minor cleanups to schizo pci controller driver. Signed-off-by: David S. Miller <davem@davemloft.net>
2007-03-02 03:20:37 +08:00
portid = of_getintprop_default(dp, "portid", 0xff);
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
sparc64: Simplify error handling in PCI controller probing. Based upon suggestions from Stephen Rothwell. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-08-31 16:33:52 +08:00
err = -ENOMEM;
sparc64: Get rid of pci_controller_info. It is just used as a parent to encapsulate two PBM objects. But that layout is only really relevant and necessary for psycho PCI controllers, which unlike all the others share a single IOMMU instance between sibling PCI busses. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-09-10 14:54:02 +08:00
pbm = kzalloc(sizeof(*pbm), GFP_KERNEL);
if (!pbm) {
printk(KERN_ERR PFX "Cannot allocate pci_pbm_info.\n");
sparc64: Simplify error handling in PCI controller probing. Based upon suggestions from Stephen Rothwell. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-08-31 16:33:52 +08:00
goto out_err;
sparc64: Convert SCHIZO PCI controller driver into a real driver. The idea is to convert all of the PCI controller drivers into genuine OF drivers, then we can get rid of this terrible probing table and infrastructure in arch/sparc64/kernel/pci.c Signed-off-by: David S. Miller <davem@davemloft.net>
2008-08-30 17:30:24 +08:00
}
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
sparc64: Get rid of pci_controller_info. It is just used as a parent to encapsulate two PBM objects. But that layout is only really relevant and necessary for psycho PCI controllers, which unlike all the others share a single IOMMU instance between sibling PCI busses. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-09-10 14:54:02 +08:00
pbm->sibling = schizo_find_sibling(portid, chip_type);
iommu = kzalloc(sizeof(struct iommu), GFP_KERNEL);
sparc64: Convert SCHIZO PCI controller driver into a real driver. The idea is to convert all of the PCI controller drivers into genuine OF drivers, then we can get rid of this terrible probing table and infrastructure in arch/sparc64/kernel/pci.c Signed-off-by: David S. Miller <davem@davemloft.net>
2008-08-30 17:30:24 +08:00
if (!iommu) {
printk(KERN_ERR PFX "Cannot allocate PBM A iommu.\n");
sparc64: Get rid of pci_controller_info. It is just used as a parent to encapsulate two PBM objects. But that layout is only really relevant and necessary for psycho PCI controllers, which unlike all the others share a single IOMMU instance between sibling PCI busses. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-09-10 14:54:02 +08:00
goto out_free_pbm;
sparc64: Convert SCHIZO PCI controller driver into a real driver. The idea is to convert all of the PCI controller drivers into genuine OF drivers, then we can get rid of this terrible probing table and infrastructure in arch/sparc64/kernel/pci.c Signed-off-by: David S. Miller <davem@davemloft.net>
2008-08-30 17:30:24 +08:00
}
[SPARC64]: Minor cleanups to schizo pci controller driver. Signed-off-by: David S. Miller <davem@davemloft.net>
2007-03-02 03:20:37 +08:00
sparc64: Get rid of pci_controller_info. It is just used as a parent to encapsulate two PBM objects. But that layout is only really relevant and necessary for psycho PCI controllers, which unlike all the others share a single IOMMU instance between sibling PCI busses. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-09-10 14:54:02 +08:00
pbm->iommu = iommu;
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
sparc64: Get rid of pci_controller_info. It is just used as a parent to encapsulate two PBM objects. But that layout is only really relevant and necessary for psycho PCI controllers, which unlike all the others share a single IOMMU instance between sibling PCI busses. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-09-10 14:54:02 +08:00
if (schizo_pbm_init(pbm, op, portid, chip_type))
goto out_free_iommu;
[SPARC64]: Minor cleanups to schizo pci controller driver. Signed-off-by: David S. Miller <davem@davemloft.net>
2007-03-02 03:20:37 +08:00
sparc64: Get rid of pci_controller_info. It is just used as a parent to encapsulate two PBM objects. But that layout is only really relevant and necessary for psycho PCI controllers, which unlike all the others share a single IOMMU instance between sibling PCI busses. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-09-10 14:54:02 +08:00
if (pbm->sibling)
pbm->sibling->sibling = pbm;
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
sparc64: Get rid of pci_controller_info. It is just used as a parent to encapsulate two PBM objects. But that layout is only really relevant and necessary for psycho PCI controllers, which unlike all the others share a single IOMMU instance between sibling PCI busses. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-09-10 14:54:02 +08:00
dev_set_drvdata(&op->dev, pbm);
[SPARC64]: Fix conflicts in SBUS/PCI/EBUS/ISA DMA handling. Fully unify all of the DMA ops so that subordinate bus types to the DMA operation providers (such as ebus, isa, of_device) can work transparently. Basically, we just make sure that for every system device we create, the dev->archdata 'iommu' and 'stc' fields are filled in. Then we have two platform variants of the DMA ops, one for SUN4U which actually programs the real hardware, and one for SUN4V which makes hypervisor calls. This also fixes the crashes in parport_pc on sparc64, reported by Meelis Roos. Signed-off-by: David S. Miller <davem@davemloft.net>
2007-07-28 13:39:14 +08:00
sparc64: Convert SCHIZO PCI controller driver into a real driver. The idea is to convert all of the PCI controller drivers into genuine OF drivers, then we can get rid of this terrible probing table and infrastructure in arch/sparc64/kernel/pci.c Signed-off-by: David S. Miller <davem@davemloft.net>
2008-08-30 17:30:24 +08:00
return 0;
[SPARC64]: Minor cleanups to schizo pci controller driver. Signed-off-by: David S. Miller <davem@davemloft.net>
2007-03-02 03:20:37 +08:00
sparc64: Get rid of pci_controller_info. It is just used as a parent to encapsulate two PBM objects. But that layout is only really relevant and necessary for psycho PCI controllers, which unlike all the others share a single IOMMU instance between sibling PCI busses. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-09-10 14:54:02 +08:00
out_free_iommu:
kfree(pbm->iommu);
sparc64: Simplify error handling in PCI controller probing. Based upon suggestions from Stephen Rothwell. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-08-31 16:33:52 +08:00
sparc64: Get rid of pci_controller_info. It is just used as a parent to encapsulate two PBM objects. But that layout is only really relevant and necessary for psycho PCI controllers, which unlike all the others share a single IOMMU instance between sibling PCI busses. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-09-10 14:54:02 +08:00
out_free_pbm:
kfree(pbm);
sparc64: Simplify error handling in PCI controller probing. Based upon suggestions from Stephen Rothwell. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-08-31 16:33:52 +08:00
out_err:
return err;
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
}
drivercore: revert addition of of_match to struct device Commit b826291c, "drivercore/dt: add a match table pointer to struct device" added an of_match pointer to struct device to cache the of_match_table entry discovered at driver match time. This was unsafe because matching is not an atomic operation with probing a driver. If two or more drivers are attempted to be matched to a driver at the same time, then the cached matching entry pointer could get overwritten. This patch reverts the of_match cache pointer and reworks all users to call of_match_device() directly instead. Signed-off-by: Grant Likely <grant.likely@secretlab.ca>
2011-05-19 01:19:24 +08:00
static const struct of_device_id schizo_match[];
sparc: remove __devinit, __devexit annotations __devinit, __devexit annotations are nops - so drop them. Likewise for __devexit_p. Adjusted alignment of arguments when needed. Signed-off-by: Sam Ravnborg <sam@ravnborg.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2013-01-01 23:02:33 +08:00
static int schizo_probe(struct platform_device *op)
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
{
drivercore: revert addition of of_match to struct device Commit b826291c, "drivercore/dt: add a match table pointer to struct device" added an of_match pointer to struct device to cache the of_match_table entry discovered at driver match time. This was unsafe because matching is not an atomic operation with probing a driver. If two or more drivers are attempted to be matched to a driver at the same time, then the cached matching entry pointer could get overwritten. This patch reverts the of_match cache pointer and reworks all users to call of_match_device() directly instead. Signed-off-by: Grant Likely <grant.likely@secretlab.ca>
2011-05-19 01:19:24 +08:00
const struct of_device_id *match;
match = of_match_device(schizo_match, &op->dev);
if (!match)
dt/sparc: Eliminate users of of_platform_{,un}register_driver Get rid of old users of of_platform_driver in arch/sparc. Most of_platform_driver users can be converted to use the platform_bus directly. Signed-off-by: Grant Likely <grant.likely@secretlab.ca>
2011-02-23 11:01:33 +08:00
return -EINVAL;
drivercore: revert addition of of_match to struct device Commit b826291c, "drivercore/dt: add a match table pointer to struct device" added an of_match pointer to struct device to cache the of_match_table entry discovered at driver match time. This was unsafe because matching is not an atomic operation with probing a driver. If two or more drivers are attempted to be matched to a driver at the same time, then the cached matching entry pointer could get overwritten. This patch reverts the of_match cache pointer and reworks all users to call of_match_device() directly instead. Signed-off-by: Grant Likely <grant.likely@secretlab.ca>
2011-05-19 01:19:24 +08:00
return __schizo_init(op, (unsigned long)match->data);
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
}
sparc64: Convert SCHIZO PCI controller driver into a real driver. The idea is to convert all of the PCI controller drivers into genuine OF drivers, then we can get rid of this terrible probing table and infrastructure in arch/sparc64/kernel/pci.c Signed-off-by: David S. Miller <davem@davemloft.net>
2008-08-30 17:30:24 +08:00
/* The ordering of this table is very important. Some Tomatillo
* nodes announce that they are compatible with both pci108e,a801
* and pci108e,8001. So list the chips in reverse chronological
* order.
*/
sparc64: Fix section mis-match errors. Fix all of the problems spotted by CONFIG_DEBUG_SECTION_MISMATCH under arch/sparc during a 64-bit defconfig build. They fall into two categorites: 1) of_device_id is marked as __initdata, and we can never do this since these objects sit in the device core data structures way past boot. So even if a driver will never be reloaded, we have to keep the device ID table around. Mark such cases const instead. 2) The bootmem alloc/free handling code in mdesc.c was not fully marked __init as it should be, thus generating a reference to free_bootmem_late() (which is __init) from non-__init code. Signed-off-by: David S. Miller <davem@davemloft.net>
2011-03-31 08:37:56 +08:00
static const struct of_device_id schizo_match[] = {
sparc64: Convert SCHIZO PCI controller driver into a real driver. The idea is to convert all of the PCI controller drivers into genuine OF drivers, then we can get rid of this terrible probing table and infrastructure in arch/sparc64/kernel/pci.c Signed-off-by: David S. Miller <davem@davemloft.net>
2008-08-30 17:30:24 +08:00
{
.name = "pci",
.compatible = "pci108e,a801",
.data = (void *) PBM_CHIP_TYPE_TOMATILLO,
},
{
.name = "pci",
.compatible = "pci108e,8002",
.data = (void *) PBM_CHIP_TYPE_SCHIZO_PLUS,
},
{
.name = "pci",
.compatible = "pci108e,8001",
.data = (void *) PBM_CHIP_TYPE_SCHIZO,
},
{},
};
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
dt/sparc: Eliminate users of of_platform_{,un}register_driver Get rid of old users of of_platform_driver in arch/sparc. Most of_platform_driver users can be converted to use the platform_bus directly. Signed-off-by: Grant Likely <grant.likely@secretlab.ca>
2011-02-23 11:01:33 +08:00
static struct platform_driver schizo_driver = {
of: Remove duplicate fields from of_platform_driver .name, .match_table and .owner are duplicated in both of_platform_driver and device_driver. This patch is a removes the extra copies from struct of_platform_driver and converts all users to the device_driver members. This patch is a pretty mechanical change. The usage model doesn't change and if any drivers have been missed, or if anything has been fixed up incorrectly, then it will fail with a compile time error, and the fixup will be trivial. This patch looks big and scary because it touches so many files, but it should be pretty safe. Signed-off-by: Grant Likely <grant.likely@secretlab.ca> Acked-by: Sean MacLennan <smaclennan@pikatech.com>
2010-04-14 07:13:02 +08:00
.driver = {
.name = DRIVER_NAME,
.of_match_table = schizo_match,
},
sparc64: Convert SCHIZO PCI controller driver into a real driver. The idea is to convert all of the PCI controller drivers into genuine OF drivers, then we can get rid of this terrible probing table and infrastructure in arch/sparc64/kernel/pci.c Signed-off-by: David S. Miller <davem@davemloft.net>
2008-08-30 17:30:24 +08:00
.probe = schizo_probe,
};
static int __init schizo_init(void)
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
{
dt/sparc: Eliminate users of of_platform_{,un}register_driver Get rid of old users of of_platform_driver in arch/sparc. Most of_platform_driver users can be converted to use the platform_bus directly. Signed-off-by: Grant Likely <grant.likely@secretlab.ca>
2011-02-23 11:01:33 +08:00
return platform_driver_register(&schizo_driver);
Linux-2.6.12-rc2 Initial git repository build. I'm not bothering with the full history, even though we have it. We can create a separate "historical" git archive of that later if we want to, and in the meantime it's about 3.2GB when imported into git - space that would just make the early git days unnecessarily complicated, when we don't have a lot of good infrastructure for it. Let it rip!
2005-04-17 06:20:36 +08:00
}
sparc64: Convert SCHIZO PCI controller driver into a real driver. The idea is to convert all of the PCI controller drivers into genuine OF drivers, then we can get rid of this terrible probing table and infrastructure in arch/sparc64/kernel/pci.c Signed-off-by: David S. Miller <davem@davemloft.net>
2008-08-30 17:30:24 +08:00
subsys_initcall(schizo_init);