OpenCloudOS-Kernel/arch/sparc/mm/srmmu.c

1829 lines
49 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
/*
* srmmu.c: SRMMU specific routines for memory management.
*
* Copyright (C) 1995 David S. Miller (davem@caip.rutgers.edu)
* Copyright (C) 1995,2002 Pete Zaitcev (zaitcev@yahoo.com)
* Copyright (C) 1996 Eddie C. Dost (ecd@skynet.be)
* Copyright (C) 1997,1998 Jakub Jelinek (jj@sunsite.mff.cuni.cz)
* Copyright (C) 1999,2000 Anton Blanchard (anton@samba.org)
*/
#include <linux/seq_file.h>
#include <linux/spinlock.h>
mm: remove include/linux/bootmem.h Move remaining definitions and declarations from include/linux/bootmem.h into include/linux/memblock.h and remove the redundant header. The includes were replaced with the semantic patch below and then semi-automated removal of duplicated '#include <linux/memblock.h> @@ @@ - #include <linux/bootmem.h> + #include <linux/memblock.h> [sfr@canb.auug.org.au: dma-direct: fix up for the removal of linux/bootmem.h] Link: http://lkml.kernel.org/r/20181002185342.133d1680@canb.auug.org.au [sfr@canb.auug.org.au: powerpc: fix up for removal of linux/bootmem.h] Link: http://lkml.kernel.org/r/20181005161406.73ef8727@canb.auug.org.au [sfr@canb.auug.org.au: x86/kaslr, ACPI/NUMA: fix for linux/bootmem.h removal] Link: http://lkml.kernel.org/r/20181008190341.5e396491@canb.auug.org.au Link: http://lkml.kernel.org/r/1536927045-23536-30-git-send-email-rppt@linux.vnet.ibm.com Signed-off-by: Mike Rapoport <rppt@linux.vnet.ibm.com> Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au> Acked-by: Michal Hocko <mhocko@suse.com> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Chris Zankel <chris@zankel.net> Cc: "David S. Miller" <davem@davemloft.net> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Greentime Hu <green.hu@gmail.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Guan Xuetao <gxt@pku.edu.cn> Cc: Ingo Molnar <mingo@redhat.com> Cc: "James E.J. Bottomley" <jejb@parisc-linux.org> Cc: Jonas Bonn <jonas@southpole.se> Cc: Jonathan Corbet <corbet@lwn.net> Cc: Ley Foon Tan <lftan@altera.com> Cc: Mark Salter <msalter@redhat.com> Cc: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: Matt Turner <mattst88@gmail.com> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Michal Simek <monstr@monstr.eu> Cc: Palmer Dabbelt <palmer@sifive.com> Cc: Paul Burton <paul.burton@mips.com> Cc: Richard Kuo <rkuo@codeaurora.org> Cc: Richard Weinberger <richard@nod.at> Cc: Rich Felker <dalias@libc.org> Cc: Russell King <linux@armlinux.org.uk> Cc: Serge Semin <fancer.lancer@gmail.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Tony Luck <tony.luck@intel.com> Cc: Vineet Gupta <vgupta@synopsys.com> Cc: Yoshinori Sato <ysato@users.sourceforge.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2018-10-31 06:09:49 +08:00
#include <linux/memblock.h>
#include <linux/pagemap.h>
#include <linux/vmalloc.h>
#include <linux/kdebug.h>
#include <linux/export.h>
#include <linux/kernel.h>
#include <linux/init.h>
#include <linux/log2.h>
include cleanup: Update gfp.h and slab.h includes to prepare for breaking implicit slab.h inclusion from percpu.h percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
2010-03-24 16:04:11 +08:00
#include <linux/gfp.h>
#include <linux/fs.h>
#include <linux/mm.h>
#include <asm/mmu_context.h>
#include <asm/cacheflush.h>
#include <asm/tlbflush.h>
#include <asm/io-unit.h>
#include <asm/pgalloc.h>
#include <asm/pgtable.h>
#include <asm/bitext.h>
#include <asm/vaddrs.h>
#include <asm/cache.h>
#include <asm/traps.h>
#include <asm/oplib.h>
#include <asm/mbus.h>
#include <asm/page.h>
#include <asm/asi.h>
#include <asm/smp.h>
#include <asm/io.h>
/* Now the cpu specific definitions. */
#include <asm/turbosparc.h>
#include <asm/tsunami.h>
#include <asm/viking.h>
#include <asm/swift.h>
#include <asm/leon.h>
#include <asm/mxcc.h>
#include <asm/ross.h>
#include "mm_32.h"
enum mbus_module srmmu_modtype;
static unsigned int hwbug_bitmask;
int vac_cache_size;
EXPORT_SYMBOL(vac_cache_size);
int vac_line_size;
extern struct resource sparc_iomap;
extern unsigned long last_valid_pfn;
static pgd_t *srmmu_swapper_pg_dir;
const struct sparc32_cachetlb_ops *sparc32_cachetlb_ops;
EXPORT_SYMBOL(sparc32_cachetlb_ops);
#ifdef CONFIG_SMP
const struct sparc32_cachetlb_ops *local_ops;
#define FLUSH_BEGIN(mm)
#define FLUSH_END
#else
#define FLUSH_BEGIN(mm) if ((mm)->context != NO_CONTEXT) {
#define FLUSH_END }
#endif
int flush_page_for_dma_global = 1;
char *srmmu_name;
ctxd_t *srmmu_ctx_table_phys;
static ctxd_t *srmmu_context_table;
int viking_mxcc_present;
static DEFINE_SPINLOCK(srmmu_context_spinlock);
static int is_hypersparc;
static int srmmu_cache_pagetables;
/* these will be initialized in srmmu_nocache_calcsize() */
static unsigned long srmmu_nocache_size;
static unsigned long srmmu_nocache_end;
/* 1 bit <=> 256 bytes of nocache <=> 64 PTEs */
#define SRMMU_NOCACHE_BITMAP_SHIFT (PAGE_SHIFT - 4)
/* The context table is a nocache user with the biggest alignment needs. */
#define SRMMU_NOCACHE_ALIGN_MAX (sizeof(ctxd_t)*SRMMU_MAX_CONTEXTS)
void *srmmu_nocache_pool;
static struct bit_map srmmu_nocache_map;
static inline int srmmu_pmd_none(pmd_t pmd)
{ return !(pmd_val(pmd) & 0xFFFFFFF); }
/* XXX should we hyper_flush_whole_icache here - Anton */
static inline void srmmu_ctxd_set(ctxd_t *ctxp, pgd_t *pgdp)
{
pte_t pte;
pte = __pte((SRMMU_ET_PTD | (__nocache_pa(pgdp) >> 4)));
set_pte((pte_t *)ctxp, pte);
}
/*
* Locations of MSI Registers.
*/
#define MSI_MBUS_ARBEN 0xe0001008 /* MBus Arbiter Enable register */
/*
* Useful bits in the MSI Registers.
*/
#define MSI_ASYNC_MODE 0x80000000 /* Operate the MSI asynchronously */
static void msi_set_sync(void)
{
__asm__ __volatile__ ("lda [%0] %1, %%g3\n\t"
"andn %%g3, %2, %%g3\n\t"
"sta %%g3, [%0] %1\n\t" : :
"r" (MSI_MBUS_ARBEN),
"i" (ASI_M_CTL), "r" (MSI_ASYNC_MODE) : "g3");
}
void pmd_set(pmd_t *pmdp, pte_t *ptep)
{
unsigned long ptp = __nocache_pa(ptep) >> 4;
set_pte((pte_t *)&pmd_val(*pmdp), __pte(SRMMU_ET_PTD | ptp));
}
/*
* size: bytes to allocate in the nocache area.
* align: bytes, number to align at.
* Returns the virtual address of the allocated area.
*/
static void *__srmmu_get_nocache(int size, int align)
{
int offset, minsz = 1 << SRMMU_NOCACHE_BITMAP_SHIFT;
unsigned long addr;
if (size < minsz) {
printk(KERN_ERR "Size 0x%x too small for nocache request\n",
size);
size = minsz;
}
if (size & (minsz - 1)) {
printk(KERN_ERR "Size 0x%x unaligned in nocache request\n",
size);
size += minsz - 1;
}
BUG_ON(align > SRMMU_NOCACHE_ALIGN_MAX);
offset = bit_map_string_get(&srmmu_nocache_map,
size >> SRMMU_NOCACHE_BITMAP_SHIFT,
align >> SRMMU_NOCACHE_BITMAP_SHIFT);
if (offset == -1) {
printk(KERN_ERR "srmmu: out of nocache %d: %d/%d\n",
size, (int) srmmu_nocache_size,
srmmu_nocache_map.used << SRMMU_NOCACHE_BITMAP_SHIFT);
return NULL;
}
addr = SRMMU_NOCACHE_VADDR + (offset << SRMMU_NOCACHE_BITMAP_SHIFT);
return (void *)addr;
}
void *srmmu_get_nocache(int size, int align)
{
void *tmp;
tmp = __srmmu_get_nocache(size, align);
if (tmp)
memset(tmp, 0, size);
return tmp;
}
void srmmu_free_nocache(void *addr, int size)
{
unsigned long vaddr;
int offset;
vaddr = (unsigned long)addr;
if (vaddr < SRMMU_NOCACHE_VADDR) {
printk("Vaddr %lx is smaller than nocache base 0x%lx\n",
vaddr, (unsigned long)SRMMU_NOCACHE_VADDR);
BUG();
}
if (vaddr + size > srmmu_nocache_end) {
printk("Vaddr %lx is bigger than nocache end 0x%lx\n",
vaddr, srmmu_nocache_end);
BUG();
}
if (!is_power_of_2(size)) {
printk("Size 0x%x is not a power of 2\n", size);
BUG();
}
if (size < SRMMU_NOCACHE_BITMAP_SHIFT) {
printk("Size 0x%x is too small\n", size);
BUG();
}
if (vaddr & (size - 1)) {
printk("Vaddr %lx is not aligned to size 0x%x\n", vaddr, size);
BUG();
}
offset = (vaddr - SRMMU_NOCACHE_VADDR) >> SRMMU_NOCACHE_BITMAP_SHIFT;
size = size >> SRMMU_NOCACHE_BITMAP_SHIFT;
bit_map_clear(&srmmu_nocache_map, offset, size);
}
static void srmmu_early_allocate_ptable_skeleton(unsigned long start,
unsigned long end);
/* Return how much physical memory we have. */
static unsigned long __init probe_memory(void)
{
unsigned long total = 0;
int i;
for (i = 0; sp_banks[i].num_bytes; i++)
total += sp_banks[i].num_bytes;
return total;
}
/*
* Reserve nocache dynamically proportionally to the amount of
* system RAM. -- Tomas Szepe <szepe@pinerecords.com>, June 2002
*/
static void __init srmmu_nocache_calcsize(void)
{
unsigned long sysmemavail = probe_memory() / 1024;
int srmmu_nocache_npages;
srmmu_nocache_npages =
sysmemavail / SRMMU_NOCACHE_ALCRATIO / 1024 * 256;
/* P3 XXX The 4x overuse: corroborated by /proc/meminfo. */
// if (srmmu_nocache_npages < 256) srmmu_nocache_npages = 256;
if (srmmu_nocache_npages < SRMMU_MIN_NOCACHE_PAGES)
srmmu_nocache_npages = SRMMU_MIN_NOCACHE_PAGES;
/* anything above 1280 blows up */
if (srmmu_nocache_npages > SRMMU_MAX_NOCACHE_PAGES)
srmmu_nocache_npages = SRMMU_MAX_NOCACHE_PAGES;
srmmu_nocache_size = srmmu_nocache_npages * PAGE_SIZE;
srmmu_nocache_end = SRMMU_NOCACHE_VADDR + srmmu_nocache_size;
}
static void __init srmmu_nocache_init(void)
{
void *srmmu_nocache_bitmap;
unsigned int bitmap_bits;
pgd_t *pgd;
2019-12-05 08:54:20 +08:00
p4d_t *p4d;
pud_t *pud;
pmd_t *pmd;
pte_t *pte;
unsigned long paddr, vaddr;
unsigned long pteval;
bitmap_bits = srmmu_nocache_size >> SRMMU_NOCACHE_BITMAP_SHIFT;
arch: use memblock_alloc() instead of memblock_alloc_from(size, align, 0) The last parameter of memblock_alloc_from() is the lower limit for the memory allocation. When it is 0, the call is equivalent to memblock_alloc(). Link: http://lkml.kernel.org/r/1548057848-15136-13-git-send-email-rppt@linux.ibm.com Signed-off-by: Mike Rapoport <rppt@linux.ibm.com> Acked-by: Paul Burton <paul.burton@mips.com> # MIPS part Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Christophe Leroy <christophe.leroy@c-s.fr> Cc: Christoph Hellwig <hch@lst.de> Cc: "David S. Miller" <davem@davemloft.net> Cc: Dennis Zhou <dennis@kernel.org> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Greentime Hu <green.hu@gmail.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Guan Xuetao <gxt@pku.edu.cn> Cc: Guo Ren <guoren@kernel.org> Cc: Guo Ren <ren_guo@c-sky.com> [c-sky] Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Juergen Gross <jgross@suse.com> [Xen] Cc: Mark Salter <msalter@redhat.com> Cc: Matt Turner <mattst88@gmail.com> Cc: Max Filippov <jcmvbkbc@gmail.com> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Michal Simek <monstr@monstr.eu> Cc: Petr Mladek <pmladek@suse.com> Cc: Richard Weinberger <richard@nod.at> Cc: Rich Felker <dalias@libc.org> Cc: Rob Herring <robh+dt@kernel.org> Cc: Rob Herring <robh@kernel.org> Cc: Russell King <linux@armlinux.org.uk> Cc: Stafford Horne <shorne@gmail.com> Cc: Tony Luck <tony.luck@intel.com> Cc: Vineet Gupta <vgupta@synopsys.com> Cc: Yoshinori Sato <ysato@users.sourceforge.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-03-12 14:29:50 +08:00
srmmu_nocache_pool = memblock_alloc(srmmu_nocache_size,
SRMMU_NOCACHE_ALIGN_MAX);
sparc: add checks for the return value of memblock_alloc*() Add panic() calls if memblock_alloc*() returns NULL. Most of the changes are simply addition of if(!ptr) panic(); statements after the calls to memblock_alloc*() variants. Exceptions are pcpu_populate_pte() and kernel_map_range() that were slightly refactored to accommodate the change. Link: http://lkml.kernel.org/r/1548057848-15136-16-git-send-email-rppt@linux.ibm.com Signed-off-by: Mike Rapoport <rppt@linux.ibm.com> Acked-by: David S. Miller <davem@davemloft.net> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Christophe Leroy <christophe.leroy@c-s.fr> Cc: Christoph Hellwig <hch@lst.de> Cc: Dennis Zhou <dennis@kernel.org> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Greentime Hu <green.hu@gmail.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Guan Xuetao <gxt@pku.edu.cn> Cc: Guo Ren <guoren@kernel.org> Cc: Guo Ren <ren_guo@c-sky.com> [c-sky] Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Juergen Gross <jgross@suse.com> [Xen] Cc: Mark Salter <msalter@redhat.com> Cc: Matt Turner <mattst88@gmail.com> Cc: Max Filippov <jcmvbkbc@gmail.com> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Michal Simek <monstr@monstr.eu> Cc: Paul Burton <paul.burton@mips.com> Cc: Petr Mladek <pmladek@suse.com> Cc: Richard Weinberger <richard@nod.at> Cc: Rich Felker <dalias@libc.org> Cc: Rob Herring <robh+dt@kernel.org> Cc: Rob Herring <robh@kernel.org> Cc: Russell King <linux@armlinux.org.uk> Cc: Stafford Horne <shorne@gmail.com> Cc: Tony Luck <tony.luck@intel.com> Cc: Vineet Gupta <vgupta@synopsys.com> Cc: Yoshinori Sato <ysato@users.sourceforge.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-03-12 14:30:10 +08:00
if (!srmmu_nocache_pool)
panic("%s: Failed to allocate %lu bytes align=0x%x\n",
__func__, srmmu_nocache_size, SRMMU_NOCACHE_ALIGN_MAX);
memset(srmmu_nocache_pool, 0, srmmu_nocache_size);
srmmu_nocache_bitmap =
arch: use memblock_alloc() instead of memblock_alloc_from(size, align, 0) The last parameter of memblock_alloc_from() is the lower limit for the memory allocation. When it is 0, the call is equivalent to memblock_alloc(). Link: http://lkml.kernel.org/r/1548057848-15136-13-git-send-email-rppt@linux.ibm.com Signed-off-by: Mike Rapoport <rppt@linux.ibm.com> Acked-by: Paul Burton <paul.burton@mips.com> # MIPS part Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Christophe Leroy <christophe.leroy@c-s.fr> Cc: Christoph Hellwig <hch@lst.de> Cc: "David S. Miller" <davem@davemloft.net> Cc: Dennis Zhou <dennis@kernel.org> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Greentime Hu <green.hu@gmail.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Guan Xuetao <gxt@pku.edu.cn> Cc: Guo Ren <guoren@kernel.org> Cc: Guo Ren <ren_guo@c-sky.com> [c-sky] Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Juergen Gross <jgross@suse.com> [Xen] Cc: Mark Salter <msalter@redhat.com> Cc: Matt Turner <mattst88@gmail.com> Cc: Max Filippov <jcmvbkbc@gmail.com> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Michal Simek <monstr@monstr.eu> Cc: Petr Mladek <pmladek@suse.com> Cc: Richard Weinberger <richard@nod.at> Cc: Rich Felker <dalias@libc.org> Cc: Rob Herring <robh+dt@kernel.org> Cc: Rob Herring <robh@kernel.org> Cc: Russell King <linux@armlinux.org.uk> Cc: Stafford Horne <shorne@gmail.com> Cc: Tony Luck <tony.luck@intel.com> Cc: Vineet Gupta <vgupta@synopsys.com> Cc: Yoshinori Sato <ysato@users.sourceforge.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-03-12 14:29:50 +08:00
memblock_alloc(BITS_TO_LONGS(bitmap_bits) * sizeof(long),
SMP_CACHE_BYTES);
sparc: add checks for the return value of memblock_alloc*() Add panic() calls if memblock_alloc*() returns NULL. Most of the changes are simply addition of if(!ptr) panic(); statements after the calls to memblock_alloc*() variants. Exceptions are pcpu_populate_pte() and kernel_map_range() that were slightly refactored to accommodate the change. Link: http://lkml.kernel.org/r/1548057848-15136-16-git-send-email-rppt@linux.ibm.com Signed-off-by: Mike Rapoport <rppt@linux.ibm.com> Acked-by: David S. Miller <davem@davemloft.net> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Christophe Leroy <christophe.leroy@c-s.fr> Cc: Christoph Hellwig <hch@lst.de> Cc: Dennis Zhou <dennis@kernel.org> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Greentime Hu <green.hu@gmail.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Guan Xuetao <gxt@pku.edu.cn> Cc: Guo Ren <guoren@kernel.org> Cc: Guo Ren <ren_guo@c-sky.com> [c-sky] Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Juergen Gross <jgross@suse.com> [Xen] Cc: Mark Salter <msalter@redhat.com> Cc: Matt Turner <mattst88@gmail.com> Cc: Max Filippov <jcmvbkbc@gmail.com> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Michal Simek <monstr@monstr.eu> Cc: Paul Burton <paul.burton@mips.com> Cc: Petr Mladek <pmladek@suse.com> Cc: Richard Weinberger <richard@nod.at> Cc: Rich Felker <dalias@libc.org> Cc: Rob Herring <robh+dt@kernel.org> Cc: Rob Herring <robh@kernel.org> Cc: Russell King <linux@armlinux.org.uk> Cc: Stafford Horne <shorne@gmail.com> Cc: Tony Luck <tony.luck@intel.com> Cc: Vineet Gupta <vgupta@synopsys.com> Cc: Yoshinori Sato <ysato@users.sourceforge.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-03-12 14:30:10 +08:00
if (!srmmu_nocache_bitmap)
panic("%s: Failed to allocate %zu bytes\n", __func__,
BITS_TO_LONGS(bitmap_bits) * sizeof(long));
bit_map_init(&srmmu_nocache_map, srmmu_nocache_bitmap, bitmap_bits);
srmmu_swapper_pg_dir = __srmmu_get_nocache(SRMMU_PGD_TABLE_SIZE, SRMMU_PGD_TABLE_SIZE);
memset(__nocache_fix(srmmu_swapper_pg_dir), 0, SRMMU_PGD_TABLE_SIZE);
init_mm.pgd = srmmu_swapper_pg_dir;
srmmu_early_allocate_ptable_skeleton(SRMMU_NOCACHE_VADDR, srmmu_nocache_end);
paddr = __pa((unsigned long)srmmu_nocache_pool);
vaddr = SRMMU_NOCACHE_VADDR;
while (vaddr < srmmu_nocache_end) {
pgd = pgd_offset_k(vaddr);
p4d = p4d_offset(pgd, vaddr);
pud = pud_offset(p4d, vaddr);
pmd = pmd_offset(__nocache_fix(pud), vaddr);
pte = pte_offset_kernel(__nocache_fix(pmd), vaddr);
pteval = ((paddr >> 4) | SRMMU_ET_PTE | SRMMU_PRIV);
if (srmmu_cache_pagetables)
pteval |= SRMMU_CACHE;
set_pte(__nocache_fix(pte), __pte(pteval));
vaddr += PAGE_SIZE;
paddr += PAGE_SIZE;
}
flush_cache_all();
flush_tlb_all();
}
pgd_t *get_pgd_fast(void)
{
pgd_t *pgd = NULL;
pgd = __srmmu_get_nocache(SRMMU_PGD_TABLE_SIZE, SRMMU_PGD_TABLE_SIZE);
if (pgd) {
pgd_t *init = pgd_offset_k(0);
memset(pgd, 0, USER_PTRS_PER_PGD * sizeof(pgd_t));
memcpy(pgd + USER_PTRS_PER_PGD, init + USER_PTRS_PER_PGD,
(PTRS_PER_PGD - USER_PTRS_PER_PGD) * sizeof(pgd_t));
}
return pgd;
}
/*
* Hardware needs alignment to 256 only, but we align to whole page size
* to reduce fragmentation problems due to the buddy principle.
* XXX Provide actual fragmentation statistics in /proc.
*
* Alignments up to the page size are the same for physical and virtual
* addresses of the nocache area.
*/
mm: treewide: remove unused address argument from pte_alloc functions Patch series "Add support for fast mremap". This series speeds up the mremap(2) syscall by copying page tables at the PMD level even for non-THP systems. There is concern that the extra 'address' argument that mremap passes to pte_alloc may do something subtle architecture related in the future that may make the scheme not work. Also we find that there is no point in passing the 'address' to pte_alloc since its unused. This patch therefore removes this argument tree-wide resulting in a nice negative diff as well. Also ensuring along the way that the enabled architectures do not do anything funky with the 'address' argument that goes unnoticed by the optimization. Build and boot tested on x86-64. Build tested on arm64. The config enablement patch for arm64 will be posted in the future after more testing. The changes were obtained by applying the following Coccinelle script. (thanks Julia for answering all Coccinelle questions!). Following fix ups were done manually: * Removal of address argument from pte_fragment_alloc * Removal of pte_alloc_one_fast definitions from m68k and microblaze. // Options: --include-headers --no-includes // Note: I split the 'identifier fn' line, so if you are manually // running it, please unsplit it so it runs for you. virtual patch @pte_alloc_func_def depends on patch exists@ identifier E2; identifier fn =~ "^(__pte_alloc|pte_alloc_one|pte_alloc|__pte_alloc_kernel|pte_alloc_one_kernel)$"; type T2; @@ fn(... - , T2 E2 ) { ... } @pte_alloc_func_proto_noarg depends on patch exists@ type T1, T2, T3, T4; identifier fn =~ "^(__pte_alloc|pte_alloc_one|pte_alloc|__pte_alloc_kernel|pte_alloc_one_kernel)$"; @@ ( - T3 fn(T1, T2); + T3 fn(T1); | - T3 fn(T1, T2, T4); + T3 fn(T1, T2); ) @pte_alloc_func_proto depends on patch exists@ identifier E1, E2, E4; type T1, T2, T3, T4; identifier fn =~ "^(__pte_alloc|pte_alloc_one|pte_alloc|__pte_alloc_kernel|pte_alloc_one_kernel)$"; @@ ( - T3 fn(T1 E1, T2 E2); + T3 fn(T1 E1); | - T3 fn(T1 E1, T2 E2, T4 E4); + T3 fn(T1 E1, T2 E2); ) @pte_alloc_func_call depends on patch exists@ expression E2; identifier fn =~ "^(__pte_alloc|pte_alloc_one|pte_alloc|__pte_alloc_kernel|pte_alloc_one_kernel)$"; @@ fn(... -, E2 ) @pte_alloc_macro depends on patch exists@ identifier fn =~ "^(__pte_alloc|pte_alloc_one|pte_alloc|__pte_alloc_kernel|pte_alloc_one_kernel)$"; identifier a, b, c; expression e; position p; @@ ( - #define fn(a, b, c) e + #define fn(a, b) e | - #define fn(a, b) e + #define fn(a) e ) Link: http://lkml.kernel.org/r/20181108181201.88826-2-joelaf@google.com Signed-off-by: Joel Fernandes (Google) <joel@joelfernandes.org> Suggested-by: Kirill A. Shutemov <kirill@shutemov.name> Acked-by: Kirill A. Shutemov <kirill@shutemov.name> Cc: Michal Hocko <mhocko@kernel.org> Cc: Julia Lawall <Julia.Lawall@lip6.fr> Cc: Kirill A. Shutemov <kirill@shutemov.name> Cc: William Kucharski <william.kucharski@oracle.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-01-04 07:28:34 +08:00
pgtable_t pte_alloc_one(struct mm_struct *mm)
{
pte_t *ptep;
CONFIG_HIGHPTE vs. sub-page page tables. Background: I've implemented 1K/2K page tables for s390. These sub-page page tables are required to properly support the s390 virtualization instruction with KVM. The SIE instruction requires that the page tables have 256 page table entries (pte) followed by 256 page status table entries (pgste). The pgstes are only required if the process is using the SIE instruction. The pgstes are updated by the hardware and by the hypervisor for a number of reasons, one of them is dirty and reference bit tracking. To avoid wasting memory the standard pte table allocation should return 1K/2K (31/64 bit) and 2K/4K if the process is using SIE. Problem: Page size on s390 is 4K, page table size is 1K or 2K. That means the s390 version for pte_alloc_one cannot return a pointer to a struct page. Trouble is that with the CONFIG_HIGHPTE feature on x86 pte_alloc_one cannot return a pointer to a pte either, since that would require more than 32 bit for the return value of pte_alloc_one (and the pte * would not be accessible since its not kmapped). Solution: The only solution I found to this dilemma is a new typedef: a pgtable_t. For s390 pgtable_t will be a (pte *) - to be introduced with a later patch. For everybody else it will be a (struct page *). The additional problem with the initialization of the ptl lock and the NR_PAGETABLE accounting is solved with a constructor pgtable_page_ctor and a destructor pgtable_page_dtor. The page table allocation and free functions need to call these two whenever a page table page is allocated or freed. pmd_populate will get a pgtable_t instead of a struct page pointer. To get the pgtable_t back from a pmd entry that has been installed with pmd_populate a new function pmd_pgtable is added. It replaces the pmd_page call in free_pte_range and apply_to_pte_range. Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com> Cc: <linux-arch@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2008-02-08 20:22:04 +08:00
struct page *page;
if (!(ptep = pte_alloc_one_kernel(mm)))
return NULL;
page = pfn_to_page(__nocache_pa((unsigned long)ptep) >> PAGE_SHIFT);
spin_lock(&mm->page_table_lock);
if (page_ref_inc_return(page) == 2 && !pgtable_pte_page_ctor(page)) {
page_ref_dec(page);
ptep = NULL;
}
spin_unlock(&mm->page_table_lock);
return ptep;
}
void pte_free(struct mm_struct *mm, pgtable_t ptep)
{
struct page *page;
page = pfn_to_page(__nocache_pa((unsigned long)ptep) >> PAGE_SHIFT);
spin_lock(&mm->page_table_lock);
if (page_ref_dec_return(page) == 1)
pgtable_pte_page_dtor(page);
spin_unlock(&mm->page_table_lock);
srmmu_free_nocache(ptep, SRMMU_PTE_TABLE_SIZE);
}
/* context handling - a dynamically sized pool is used */
#define NO_CONTEXT -1
struct ctx_list {
struct ctx_list *next;
struct ctx_list *prev;
unsigned int ctx_number;
struct mm_struct *ctx_mm;
};
static struct ctx_list *ctx_list_pool;
static struct ctx_list ctx_free;
static struct ctx_list ctx_used;
/* At boot time we determine the number of contexts */
static int num_contexts;
static inline void remove_from_ctx_list(struct ctx_list *entry)
{
entry->next->prev = entry->prev;
entry->prev->next = entry->next;
}
static inline void add_to_ctx_list(struct ctx_list *head, struct ctx_list *entry)
{
entry->next = head;
(entry->prev = head->prev)->next = entry;
head->prev = entry;
}
#define add_to_free_ctxlist(entry) add_to_ctx_list(&ctx_free, entry)
#define add_to_used_ctxlist(entry) add_to_ctx_list(&ctx_used, entry)
static inline void alloc_context(struct mm_struct *old_mm, struct mm_struct *mm)
{
struct ctx_list *ctxp;
ctxp = ctx_free.next;
if (ctxp != &ctx_free) {
remove_from_ctx_list(ctxp);
add_to_used_ctxlist(ctxp);
mm->context = ctxp->ctx_number;
ctxp->ctx_mm = mm;
return;
}
ctxp = ctx_used.next;
if (ctxp->ctx_mm == old_mm)
ctxp = ctxp->next;
if (ctxp == &ctx_used)
panic("out of mmu contexts");
flush_cache_mm(ctxp->ctx_mm);
flush_tlb_mm(ctxp->ctx_mm);
remove_from_ctx_list(ctxp);
add_to_used_ctxlist(ctxp);
ctxp->ctx_mm->context = NO_CONTEXT;
ctxp->ctx_mm = mm;
mm->context = ctxp->ctx_number;
}
static inline void free_context(int context)
{
struct ctx_list *ctx_old;
ctx_old = ctx_list_pool + context;
remove_from_ctx_list(ctx_old);
add_to_free_ctxlist(ctx_old);
}
static void __init sparc_context_init(int numctx)
{
int ctx;
unsigned long size;
size = numctx * sizeof(struct ctx_list);
arch: use memblock_alloc() instead of memblock_alloc_from(size, align, 0) The last parameter of memblock_alloc_from() is the lower limit for the memory allocation. When it is 0, the call is equivalent to memblock_alloc(). Link: http://lkml.kernel.org/r/1548057848-15136-13-git-send-email-rppt@linux.ibm.com Signed-off-by: Mike Rapoport <rppt@linux.ibm.com> Acked-by: Paul Burton <paul.burton@mips.com> # MIPS part Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Christophe Leroy <christophe.leroy@c-s.fr> Cc: Christoph Hellwig <hch@lst.de> Cc: "David S. Miller" <davem@davemloft.net> Cc: Dennis Zhou <dennis@kernel.org> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Greentime Hu <green.hu@gmail.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Guan Xuetao <gxt@pku.edu.cn> Cc: Guo Ren <guoren@kernel.org> Cc: Guo Ren <ren_guo@c-sky.com> [c-sky] Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Juergen Gross <jgross@suse.com> [Xen] Cc: Mark Salter <msalter@redhat.com> Cc: Matt Turner <mattst88@gmail.com> Cc: Max Filippov <jcmvbkbc@gmail.com> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Michal Simek <monstr@monstr.eu> Cc: Petr Mladek <pmladek@suse.com> Cc: Richard Weinberger <richard@nod.at> Cc: Rich Felker <dalias@libc.org> Cc: Rob Herring <robh+dt@kernel.org> Cc: Rob Herring <robh@kernel.org> Cc: Russell King <linux@armlinux.org.uk> Cc: Stafford Horne <shorne@gmail.com> Cc: Tony Luck <tony.luck@intel.com> Cc: Vineet Gupta <vgupta@synopsys.com> Cc: Yoshinori Sato <ysato@users.sourceforge.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-03-12 14:29:50 +08:00
ctx_list_pool = memblock_alloc(size, SMP_CACHE_BYTES);
sparc: add checks for the return value of memblock_alloc*() Add panic() calls if memblock_alloc*() returns NULL. Most of the changes are simply addition of if(!ptr) panic(); statements after the calls to memblock_alloc*() variants. Exceptions are pcpu_populate_pte() and kernel_map_range() that were slightly refactored to accommodate the change. Link: http://lkml.kernel.org/r/1548057848-15136-16-git-send-email-rppt@linux.ibm.com Signed-off-by: Mike Rapoport <rppt@linux.ibm.com> Acked-by: David S. Miller <davem@davemloft.net> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: Christophe Leroy <christophe.leroy@c-s.fr> Cc: Christoph Hellwig <hch@lst.de> Cc: Dennis Zhou <dennis@kernel.org> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Greentime Hu <green.hu@gmail.com> Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Cc: Guan Xuetao <gxt@pku.edu.cn> Cc: Guo Ren <guoren@kernel.org> Cc: Guo Ren <ren_guo@c-sky.com> [c-sky] Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Juergen Gross <jgross@suse.com> [Xen] Cc: Mark Salter <msalter@redhat.com> Cc: Matt Turner <mattst88@gmail.com> Cc: Max Filippov <jcmvbkbc@gmail.com> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Michal Simek <monstr@monstr.eu> Cc: Paul Burton <paul.burton@mips.com> Cc: Petr Mladek <pmladek@suse.com> Cc: Richard Weinberger <richard@nod.at> Cc: Rich Felker <dalias@libc.org> Cc: Rob Herring <robh+dt@kernel.org> Cc: Rob Herring <robh@kernel.org> Cc: Russell King <linux@armlinux.org.uk> Cc: Stafford Horne <shorne@gmail.com> Cc: Tony Luck <tony.luck@intel.com> Cc: Vineet Gupta <vgupta@synopsys.com> Cc: Yoshinori Sato <ysato@users.sourceforge.jp> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2019-03-12 14:30:10 +08:00
if (!ctx_list_pool)
panic("%s: Failed to allocate %lu bytes\n", __func__, size);
for (ctx = 0; ctx < numctx; ctx++) {
struct ctx_list *clist;
clist = (ctx_list_pool + ctx);
clist->ctx_number = ctx;
clist->ctx_mm = NULL;
}
ctx_free.next = ctx_free.prev = &ctx_free;
ctx_used.next = ctx_used.prev = &ctx_used;
for (ctx = 0; ctx < numctx; ctx++)
add_to_free_ctxlist(ctx_list_pool + ctx);
}
void switch_mm(struct mm_struct *old_mm, struct mm_struct *mm,
struct task_struct *tsk)
{
unsigned long flags;
if (mm->context == NO_CONTEXT) {
spin_lock_irqsave(&srmmu_context_spinlock, flags);
alloc_context(old_mm, mm);
spin_unlock_irqrestore(&srmmu_context_spinlock, flags);
srmmu_ctxd_set(&srmmu_context_table[mm->context], mm->pgd);
}
if (sparc_cpu_model == sparc_leon)
leon_switch_mm();
if (is_hypersparc)
hyper_flush_whole_icache();
srmmu_set_context(mm->context);
}
/* Low level IO area allocation on the SRMMU. */
static inline void srmmu_mapioaddr(unsigned long physaddr,
unsigned long virt_addr, int bus_type)
{
pgd_t *pgdp;
2019-12-05 08:54:20 +08:00
p4d_t *p4dp;
pud_t *pudp;
pmd_t *pmdp;
pte_t *ptep;
unsigned long tmp;
physaddr &= PAGE_MASK;
pgdp = pgd_offset_k(virt_addr);
2019-12-05 08:54:20 +08:00
p4dp = p4d_offset(pgdp, virt_addr);
pudp = pud_offset(p4dp, virt_addr);
pmdp = pmd_offset(pudp, virt_addr);
ptep = pte_offset_kernel(pmdp, virt_addr);
tmp = (physaddr >> 4) | SRMMU_ET_PTE;
/* I need to test whether this is consistent over all
* sun4m's. The bus_type represents the upper 4 bits of
* 36-bit physical address on the I/O space lines...
*/
tmp |= (bus_type << 28);
tmp |= SRMMU_PRIV;
__flush_page_to_ram(virt_addr);
set_pte(ptep, __pte(tmp));
}
void srmmu_mapiorange(unsigned int bus, unsigned long xpa,
unsigned long xva, unsigned int len)
{
while (len != 0) {
len -= PAGE_SIZE;
srmmu_mapioaddr(xpa, xva, bus);
xva += PAGE_SIZE;
xpa += PAGE_SIZE;
}
flush_tlb_all();
}
static inline void srmmu_unmapioaddr(unsigned long virt_addr)
{
pgd_t *pgdp;
2019-12-05 08:54:20 +08:00
p4d_t *p4dp;
pud_t *pudp;
pmd_t *pmdp;
pte_t *ptep;
2019-12-05 08:54:20 +08:00
pgdp = pgd_offset_k(virt_addr);
2019-12-05 08:54:20 +08:00
p4dp = p4d_offset(pgdp, virt_addr);
pudp = pud_offset(p4dp, virt_addr);
pmdp = pmd_offset(pudp, virt_addr);
ptep = pte_offset_kernel(pmdp, virt_addr);
/* No need to flush uncacheable page. */
__pte_clear(ptep);
}
void srmmu_unmapiorange(unsigned long virt_addr, unsigned int len)
{
while (len != 0) {
len -= PAGE_SIZE;
srmmu_unmapioaddr(virt_addr);
virt_addr += PAGE_SIZE;
}
flush_tlb_all();
}
/* tsunami.S */
extern void tsunami_flush_cache_all(void);
extern void tsunami_flush_cache_mm(struct mm_struct *mm);
extern void tsunami_flush_cache_range(struct vm_area_struct *vma, unsigned long start, unsigned long end);
extern void tsunami_flush_cache_page(struct vm_area_struct *vma, unsigned long page);
extern void tsunami_flush_page_to_ram(unsigned long page);
extern void tsunami_flush_page_for_dma(unsigned long page);
extern void tsunami_flush_sig_insns(struct mm_struct *mm, unsigned long insn_addr);
extern void tsunami_flush_tlb_all(void);
extern void tsunami_flush_tlb_mm(struct mm_struct *mm);
extern void tsunami_flush_tlb_range(struct vm_area_struct *vma, unsigned long start, unsigned long end);
extern void tsunami_flush_tlb_page(struct vm_area_struct *vma, unsigned long page);
extern void tsunami_setup_blockops(void);
/* swift.S */
extern void swift_flush_cache_all(void);
extern void swift_flush_cache_mm(struct mm_struct *mm);
extern void swift_flush_cache_range(struct vm_area_struct *vma,
unsigned long start, unsigned long end);
extern void swift_flush_cache_page(struct vm_area_struct *vma, unsigned long page);
extern void swift_flush_page_to_ram(unsigned long page);
extern void swift_flush_page_for_dma(unsigned long page);
extern void swift_flush_sig_insns(struct mm_struct *mm, unsigned long insn_addr);
extern void swift_flush_tlb_all(void);
extern void swift_flush_tlb_mm(struct mm_struct *mm);
extern void swift_flush_tlb_range(struct vm_area_struct *vma,
unsigned long start, unsigned long end);
extern void swift_flush_tlb_page(struct vm_area_struct *vma, unsigned long page);
#if 0 /* P3: deadwood to debug precise flushes on Swift. */
void swift_flush_tlb_page(struct vm_area_struct *vma, unsigned long page)
{
int cctx, ctx1;
page &= PAGE_MASK;
if ((ctx1 = vma->vm_mm->context) != -1) {
cctx = srmmu_get_context();
/* Is context # ever different from current context? P3 */
if (cctx != ctx1) {
printk("flush ctx %02x curr %02x\n", ctx1, cctx);
srmmu_set_context(ctx1);
swift_flush_page(page);
__asm__ __volatile__("sta %%g0, [%0] %1\n\t" : :
"r" (page), "i" (ASI_M_FLUSH_PROBE));
srmmu_set_context(cctx);
} else {
/* Rm. prot. bits from virt. c. */
/* swift_flush_cache_all(); */
/* swift_flush_cache_page(vma, page); */
swift_flush_page(page);
__asm__ __volatile__("sta %%g0, [%0] %1\n\t" : :
"r" (page), "i" (ASI_M_FLUSH_PROBE));
/* same as above: srmmu_flush_tlb_page() */
}
}
}
#endif
/*
* The following are all MBUS based SRMMU modules, and therefore could
* be found in a multiprocessor configuration. On the whole, these
* chips seems to be much more touchy about DVMA and page tables
* with respect to cache coherency.
*/
/* viking.S */
extern void viking_flush_cache_all(void);
extern void viking_flush_cache_mm(struct mm_struct *mm);
extern void viking_flush_cache_range(struct vm_area_struct *vma, unsigned long start,
unsigned long end);
extern void viking_flush_cache_page(struct vm_area_struct *vma, unsigned long page);
extern void viking_flush_page_to_ram(unsigned long page);
extern void viking_flush_page_for_dma(unsigned long page);
extern void viking_flush_sig_insns(struct mm_struct *mm, unsigned long addr);
extern void viking_flush_page(unsigned long page);
extern void viking_mxcc_flush_page(unsigned long page);
extern void viking_flush_tlb_all(void);
extern void viking_flush_tlb_mm(struct mm_struct *mm);
extern void viking_flush_tlb_range(struct vm_area_struct *vma, unsigned long start,
unsigned long end);
extern void viking_flush_tlb_page(struct vm_area_struct *vma,
unsigned long page);
extern void sun4dsmp_flush_tlb_all(void);
extern void sun4dsmp_flush_tlb_mm(struct mm_struct *mm);
extern void sun4dsmp_flush_tlb_range(struct vm_area_struct *vma, unsigned long start,
unsigned long end);
extern void sun4dsmp_flush_tlb_page(struct vm_area_struct *vma,
unsigned long page);
/* hypersparc.S */
extern void hypersparc_flush_cache_all(void);
extern void hypersparc_flush_cache_mm(struct mm_struct *mm);
extern void hypersparc_flush_cache_range(struct vm_area_struct *vma, unsigned long start, unsigned long end);
extern void hypersparc_flush_cache_page(struct vm_area_struct *vma, unsigned long page);
extern void hypersparc_flush_page_to_ram(unsigned long page);
extern void hypersparc_flush_page_for_dma(unsigned long page);
extern void hypersparc_flush_sig_insns(struct mm_struct *mm, unsigned long insn_addr);
extern void hypersparc_flush_tlb_all(void);
extern void hypersparc_flush_tlb_mm(struct mm_struct *mm);
extern void hypersparc_flush_tlb_range(struct vm_area_struct *vma, unsigned long start, unsigned long end);
extern void hypersparc_flush_tlb_page(struct vm_area_struct *vma, unsigned long page);
extern void hypersparc_setup_blockops(void);
/*
* NOTE: All of this startup code assumes the low 16mb (approx.) of
* kernel mappings are done with one single contiguous chunk of
* ram. On small ram machines (classics mainly) we only get
* around 8mb mapped for us.
*/
static void __init early_pgtable_allocfail(char *type)
{
prom_printf("inherit_prom_mappings: Cannot alloc kernel %s.\n", type);
prom_halt();
}
static void __init srmmu_early_allocate_ptable_skeleton(unsigned long start,
unsigned long end)
{
pgd_t *pgdp;
2019-12-05 08:54:20 +08:00
p4d_t *p4dp;
pud_t *pudp;
pmd_t *pmdp;
pte_t *ptep;
while (start < end) {
pgdp = pgd_offset_k(start);
2019-12-05 08:54:20 +08:00
p4dp = p4d_offset(pgdp, start);
pudp = pud_offset(p4dp, start);
if (pud_none(*__nocache_fix(pudp))) {
pmdp = __srmmu_get_nocache(
SRMMU_PMD_TABLE_SIZE, SRMMU_PMD_TABLE_SIZE);
if (pmdp == NULL)
early_pgtable_allocfail("pmd");
memset(__nocache_fix(pmdp), 0, SRMMU_PMD_TABLE_SIZE);
2019-12-05 08:54:20 +08:00
pud_set(__nocache_fix(pudp), pmdp);
}
2019-12-05 08:54:20 +08:00
pmdp = pmd_offset(__nocache_fix(pudp), start);
if (srmmu_pmd_none(*__nocache_fix(pmdp))) {
ptep = __srmmu_get_nocache(PTE_SIZE, PTE_SIZE);
if (ptep == NULL)
early_pgtable_allocfail("pte");
memset(__nocache_fix(ptep), 0, PTE_SIZE);
pmd_set(__nocache_fix(pmdp), ptep);
}
if (start > (0xffffffffUL - PMD_SIZE))
break;
start = (start + PMD_SIZE) & PMD_MASK;
}
}
static void __init srmmu_allocate_ptable_skeleton(unsigned long start,
unsigned long end)
{
pgd_t *pgdp;
2019-12-05 08:54:20 +08:00
p4d_t *p4dp;
pud_t *pudp;
pmd_t *pmdp;
pte_t *ptep;
while (start < end) {
pgdp = pgd_offset_k(start);
2019-12-05 08:54:20 +08:00
p4dp = p4d_offset(pgdp, start);
pudp = pud_offset(p4dp, start);
if (pud_none(*pudp)) {
pmdp = __srmmu_get_nocache(SRMMU_PMD_TABLE_SIZE, SRMMU_PMD_TABLE_SIZE);
if (pmdp == NULL)
early_pgtable_allocfail("pmd");
memset(pmdp, 0, SRMMU_PMD_TABLE_SIZE);
2019-12-05 08:54:20 +08:00
pud_set((pud_t *)pgdp, pmdp);
}
2019-12-05 08:54:20 +08:00
pmdp = pmd_offset(pudp, start);
if (srmmu_pmd_none(*pmdp)) {
ptep = __srmmu_get_nocache(PTE_SIZE,
PTE_SIZE);
if (ptep == NULL)
early_pgtable_allocfail("pte");
memset(ptep, 0, PTE_SIZE);
pmd_set(pmdp, ptep);
}
if (start > (0xffffffffUL - PMD_SIZE))
break;
start = (start + PMD_SIZE) & PMD_MASK;
}
}
/* These flush types are not available on all chips... */
static inline unsigned long srmmu_probe(unsigned long vaddr)
{
unsigned long retval;
if (sparc_cpu_model != sparc_leon) {
vaddr &= PAGE_MASK;
__asm__ __volatile__("lda [%1] %2, %0\n\t" :
"=r" (retval) :
"r" (vaddr | 0x400), "i" (ASI_M_FLUSH_PROBE));
} else {
retval = leon_swprobe(vaddr, NULL);
}
return retval;
}
/*
* This is much cleaner than poking around physical address space
* looking at the prom's page table directly which is what most
* other OS's do. Yuck... this is much better.
*/
static void __init srmmu_inherit_prom_mappings(unsigned long start,
unsigned long end)
{
unsigned long probed;
unsigned long addr;
pgd_t *pgdp;
2019-12-05 08:54:20 +08:00
p4d_t *p4dp;
pud_t *pudp;
pmd_t *pmdp;
pte_t *ptep;
int what; /* 0 = normal-pte, 1 = pmd-level pte, 2 = pgd-level pte */
while (start <= end) {
if (start == 0)
break; /* probably wrap around */
if (start == 0xfef00000)
start = KADB_DEBUGGER_BEGVM;
probed = srmmu_probe(start);
if (!probed) {
/* continue probing until we find an entry */
start += PAGE_SIZE;
continue;
}
/* A red snapper, see what it really is. */
what = 0;
addr = start - PAGE_SIZE;
if (!(start & ~(PMD_MASK))) {
if (srmmu_probe(addr + PMD_SIZE) == probed)
what = 1;
}
if (!(start & ~(PGDIR_MASK))) {
if (srmmu_probe(addr + PGDIR_SIZE) == probed)
what = 2;
}
pgdp = pgd_offset_k(start);
2019-12-05 08:54:20 +08:00
p4dp = p4d_offset(pgdp, start);
pudp = pud_offset(p4dp, start);
if (what == 2) {
*__nocache_fix(pgdp) = __pgd(probed);
start += PGDIR_SIZE;
continue;
}
if (pud_none(*__nocache_fix(pudp))) {
pmdp = __srmmu_get_nocache(SRMMU_PMD_TABLE_SIZE,
SRMMU_PMD_TABLE_SIZE);
if (pmdp == NULL)
early_pgtable_allocfail("pmd");
memset(__nocache_fix(pmdp), 0, SRMMU_PMD_TABLE_SIZE);
2019-12-05 08:54:20 +08:00
pud_set(__nocache_fix(pudp), pmdp);
}
pmdp = pmd_offset(__nocache_fix(pudp), start);
if (what == 1) {
*(pmd_t *)__nocache_fix(pmdp) = __pmd(probed);
start += PMD_SIZE;
continue;
}
if (srmmu_pmd_none(*__nocache_fix(pmdp))) {
ptep = __srmmu_get_nocache(PTE_SIZE, PTE_SIZE);
if (ptep == NULL)
early_pgtable_allocfail("pte");
memset(__nocache_fix(ptep), 0, PTE_SIZE);
pmd_set(__nocache_fix(pmdp), ptep);
}
ptep = pte_offset_kernel(__nocache_fix(pmdp), start);
*__nocache_fix(ptep) = __pte(probed);
start += PAGE_SIZE;
}
}
#define KERNEL_PTE(page_shifted) ((page_shifted)|SRMMU_CACHE|SRMMU_PRIV|SRMMU_VALID)
/* Create a third-level SRMMU 16MB page mapping. */
static void __init do_large_mapping(unsigned long vaddr, unsigned long phys_base)
{
pgd_t *pgdp = pgd_offset_k(vaddr);
unsigned long big_pte;
big_pte = KERNEL_PTE(phys_base >> 4);
*__nocache_fix(pgdp) = __pgd(big_pte);
}
/* Map sp_bank entry SP_ENTRY, starting at virtual address VBASE. */
static unsigned long __init map_spbank(unsigned long vbase, int sp_entry)
{
unsigned long pstart = (sp_banks[sp_entry].base_addr & PGDIR_MASK);
unsigned long vstart = (vbase & PGDIR_MASK);
unsigned long vend = PGDIR_ALIGN(vbase + sp_banks[sp_entry].num_bytes);
/* Map "low" memory only */
const unsigned long min_vaddr = PAGE_OFFSET;
const unsigned long max_vaddr = PAGE_OFFSET + SRMMU_MAXMEM;
if (vstart < min_vaddr || vstart >= max_vaddr)
return vstart;
if (vend > max_vaddr || vend < min_vaddr)
vend = max_vaddr;
while (vstart < vend) {
do_large_mapping(vstart, pstart);
vstart += PGDIR_SIZE; pstart += PGDIR_SIZE;
}
return vstart;
}
static void __init map_kernel(void)
{
int i;
if (phys_base > 0) {
do_large_mapping(PAGE_OFFSET, phys_base);
}
for (i = 0; sp_banks[i].num_bytes != 0; i++) {
map_spbank((unsigned long)__va(sp_banks[i].base_addr), i);
}
}
sparc: delete __cpuinit/__CPUINIT usage from all users The __cpuinit type of throwaway sections might have made sense some time ago when RAM was more constrained, but now the savings do not offset the cost and complications. For example, the fix in commit 5e427ec2d0 ("x86: Fix bit corruption at CPU resume time") is a good example of the nasty type of bugs that can be created with improper use of the various __init prefixes. After a discussion on LKML[1] it was decided that cpuinit should go the way of devinit and be phased out. Once all the users are gone, we can then finally remove the macros themselves from linux/init.h. Note that some harmless section mismatch warnings may result, since notify_cpu_starting() and cpu_up() are arch independent (kernel/cpu.c) are flagged as __cpuinit -- so if we remove the __cpuinit from arch specific callers, we will also get section mismatch warnings. As an intermediate step, we intend to turn the linux/init.h cpuinit content into no-ops as early as possible, since that will get rid of these warnings. In any case, they are temporary and harmless. This removes all the arch/sparc uses of the __cpuinit macros from C files and removes __CPUINIT from assembly files. Note that even though arch/sparc/kernel/trampoline_64.S has instances of ".previous" in it, they are all paired off against explicit ".section" directives, and not implicitly paired with __CPUINIT (unlike mips and arm were). [1] https://lkml.org/lkml/2013/5/20/589 Cc: "David S. Miller" <davem@davemloft.net> Cc: sparclinux@vger.kernel.org Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com>
2013-06-18 03:43:14 +08:00
void (*poke_srmmu)(void) = NULL;
void __init srmmu_paging_init(void)
{
int i;
phandle cpunode;
char node_str[128];
pgd_t *pgd;
2019-12-05 08:54:20 +08:00
p4d_t *p4d;
pud_t *pud;
pmd_t *pmd;
pte_t *pte;
unsigned long pages_avail;
init_mm.context = (unsigned long) NO_CONTEXT;
sparc_iomap.start = SUN4M_IOBASE_VADDR; /* 16MB of IOSPACE on all sun4m's. */
if (sparc_cpu_model == sun4d)
num_contexts = 65536; /* We know it is Viking */
else {
/* Find the number of contexts on the srmmu. */
cpunode = prom_getchild(prom_root_node);
num_contexts = 0;
while (cpunode != 0) {
prom_getstring(cpunode, "device_type", node_str, sizeof(node_str));
if (!strcmp(node_str, "cpu")) {
num_contexts = prom_getintdefault(cpunode, "mmu-nctx", 0x8);
break;
}
cpunode = prom_getsibling(cpunode);
}
}
if (!num_contexts) {
prom_printf("Something wrong, can't find cpu node in paging_init.\n");
prom_halt();
}
pages_avail = 0;
last_valid_pfn = bootmem_init(&pages_avail);
srmmu_nocache_calcsize();
srmmu_nocache_init();
srmmu_inherit_prom_mappings(0xfe400000, (LINUX_OPPROM_ENDVM - PAGE_SIZE));
map_kernel();
/* ctx table has to be physically aligned to its size */
srmmu_context_table = __srmmu_get_nocache(num_contexts * sizeof(ctxd_t), num_contexts * sizeof(ctxd_t));
srmmu_ctx_table_phys = (ctxd_t *)__nocache_pa(srmmu_context_table);
for (i = 0; i < num_contexts; i++)
srmmu_ctxd_set(__nocache_fix(&srmmu_context_table[i]), srmmu_swapper_pg_dir);
flush_cache_all();
srmmu_set_ctable_ptr((unsigned long)srmmu_ctx_table_phys);
#ifdef CONFIG_SMP
/* Stop from hanging here... */
local_ops->tlb_all();
#else
flush_tlb_all();
#endif
poke_srmmu();
srmmu_allocate_ptable_skeleton(sparc_iomap.start, IOBASE_END);
srmmu_allocate_ptable_skeleton(DVMA_VADDR, DVMA_END);
srmmu_allocate_ptable_skeleton(
__fix_to_virt(__end_of_fixed_addresses - 1), FIXADDR_TOP);
srmmu_allocate_ptable_skeleton(PKMAP_BASE, PKMAP_END);
pgd = pgd_offset_k(PKMAP_BASE);
2019-12-05 08:54:20 +08:00
p4d = p4d_offset(pgd, PKMAP_BASE);
pud = pud_offset(p4d, PKMAP_BASE);
pmd = pmd_offset(pud, PKMAP_BASE);
pte = pte_offset_kernel(pmd, PKMAP_BASE);
pkmap_page_table = pte;
flush_cache_all();
flush_tlb_all();
sparc_context_init(num_contexts);
{
sparc32: simplify detection of memory zone boundaries free_area_init() only requires the definition of maximal PFN for each of the supported zone rater than calculation of actual zone sizes and the sizes of the holes between the zones. After removal of CONFIG_HAVE_MEMBLOCK_NODE_MAP the free_area_init() is available to all architectures. Using this function instead of free_area_init_node() simplifies the zone detection. Signed-off-by: Mike Rapoport <rppt@linux.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Tested-by: Hoan Tran <hoan@os.amperecomputing.com> [arm64] Cc: Baoquan He <bhe@redhat.com> Cc: Brian Cain <bcain@codeaurora.org> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: "David S. Miller" <davem@davemloft.net> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Greentime Hu <green.hu@gmail.com> Cc: Greg Ungerer <gerg@linux-m68k.org> Cc: Guan Xuetao <gxt@pku.edu.cn> Cc: Guo Ren <guoren@kernel.org> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Helge Deller <deller@gmx.de> Cc: "James E.J. Bottomley" <James.Bottomley@HansenPartnership.com> Cc: Jonathan Corbet <corbet@lwn.net> Cc: Ley Foon Tan <ley.foon.tan@intel.com> Cc: Mark Salter <msalter@redhat.com> Cc: Matt Turner <mattst88@gmail.com> Cc: Max Filippov <jcmvbkbc@gmail.com> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Michal Hocko <mhocko@kernel.org> Cc: Michal Simek <monstr@monstr.eu> Cc: Nick Hu <nickhu@andestech.com> Cc: Paul Walmsley <paul.walmsley@sifive.com> Cc: Richard Weinberger <richard@nod.at> Cc: Rich Felker <dalias@libc.org> Cc: Russell King <linux@armlinux.org.uk> Cc: Stafford Horne <shorne@gmail.com> Cc: Thomas Bogendoerfer <tsbogend@alpha.franken.de> Cc: Tony Luck <tony.luck@intel.com> Cc: Vineet Gupta <vgupta@synopsys.com> Cc: Yoshinori Sato <ysato@users.sourceforge.jp> Link: http://lkml.kernel.org/r/20200412194859.12663-13-rppt@kernel.org Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-06-04 06:57:41 +08:00
unsigned long max_zone_pfn[MAX_NR_ZONES] = { 0 };
sparc32: simplify detection of memory zone boundaries free_area_init() only requires the definition of maximal PFN for each of the supported zone rater than calculation of actual zone sizes and the sizes of the holes between the zones. After removal of CONFIG_HAVE_MEMBLOCK_NODE_MAP the free_area_init() is available to all architectures. Using this function instead of free_area_init_node() simplifies the zone detection. Signed-off-by: Mike Rapoport <rppt@linux.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Tested-by: Hoan Tran <hoan@os.amperecomputing.com> [arm64] Cc: Baoquan He <bhe@redhat.com> Cc: Brian Cain <bcain@codeaurora.org> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: "David S. Miller" <davem@davemloft.net> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Greentime Hu <green.hu@gmail.com> Cc: Greg Ungerer <gerg@linux-m68k.org> Cc: Guan Xuetao <gxt@pku.edu.cn> Cc: Guo Ren <guoren@kernel.org> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Helge Deller <deller@gmx.de> Cc: "James E.J. Bottomley" <James.Bottomley@HansenPartnership.com> Cc: Jonathan Corbet <corbet@lwn.net> Cc: Ley Foon Tan <ley.foon.tan@intel.com> Cc: Mark Salter <msalter@redhat.com> Cc: Matt Turner <mattst88@gmail.com> Cc: Max Filippov <jcmvbkbc@gmail.com> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Michal Hocko <mhocko@kernel.org> Cc: Michal Simek <monstr@monstr.eu> Cc: Nick Hu <nickhu@andestech.com> Cc: Paul Walmsley <paul.walmsley@sifive.com> Cc: Richard Weinberger <richard@nod.at> Cc: Rich Felker <dalias@libc.org> Cc: Russell King <linux@armlinux.org.uk> Cc: Stafford Horne <shorne@gmail.com> Cc: Thomas Bogendoerfer <tsbogend@alpha.franken.de> Cc: Tony Luck <tony.luck@intel.com> Cc: Vineet Gupta <vgupta@synopsys.com> Cc: Yoshinori Sato <ysato@users.sourceforge.jp> Link: http://lkml.kernel.org/r/20200412194859.12663-13-rppt@kernel.org Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-06-04 06:57:41 +08:00
max_zone_pfn[ZONE_DMA] = max_low_pfn;
max_zone_pfn[ZONE_NORMAL] = max_low_pfn;
max_zone_pfn[ZONE_HIGHMEM] = highend_pfn;
sparc32: simplify detection of memory zone boundaries free_area_init() only requires the definition of maximal PFN for each of the supported zone rater than calculation of actual zone sizes and the sizes of the holes between the zones. After removal of CONFIG_HAVE_MEMBLOCK_NODE_MAP the free_area_init() is available to all architectures. Using this function instead of free_area_init_node() simplifies the zone detection. Signed-off-by: Mike Rapoport <rppt@linux.ibm.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Tested-by: Hoan Tran <hoan@os.amperecomputing.com> [arm64] Cc: Baoquan He <bhe@redhat.com> Cc: Brian Cain <bcain@codeaurora.org> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: "David S. Miller" <davem@davemloft.net> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Greentime Hu <green.hu@gmail.com> Cc: Greg Ungerer <gerg@linux-m68k.org> Cc: Guan Xuetao <gxt@pku.edu.cn> Cc: Guo Ren <guoren@kernel.org> Cc: Heiko Carstens <heiko.carstens@de.ibm.com> Cc: Helge Deller <deller@gmx.de> Cc: "James E.J. Bottomley" <James.Bottomley@HansenPartnership.com> Cc: Jonathan Corbet <corbet@lwn.net> Cc: Ley Foon Tan <ley.foon.tan@intel.com> Cc: Mark Salter <msalter@redhat.com> Cc: Matt Turner <mattst88@gmail.com> Cc: Max Filippov <jcmvbkbc@gmail.com> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Michal Hocko <mhocko@kernel.org> Cc: Michal Simek <monstr@monstr.eu> Cc: Nick Hu <nickhu@andestech.com> Cc: Paul Walmsley <paul.walmsley@sifive.com> Cc: Richard Weinberger <richard@nod.at> Cc: Rich Felker <dalias@libc.org> Cc: Russell King <linux@armlinux.org.uk> Cc: Stafford Horne <shorne@gmail.com> Cc: Thomas Bogendoerfer <tsbogend@alpha.franken.de> Cc: Tony Luck <tony.luck@intel.com> Cc: Vineet Gupta <vgupta@synopsys.com> Cc: Yoshinori Sato <ysato@users.sourceforge.jp> Link: http://lkml.kernel.org/r/20200412194859.12663-13-rppt@kernel.org Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2020-06-04 06:57:41 +08:00
free_area_init(max_zone_pfn);
}
}
void mmu_info(struct seq_file *m)
{
seq_printf(m,
"MMU type\t: %s\n"
"contexts\t: %d\n"
"nocache total\t: %ld\n"
"nocache used\t: %d\n",
srmmu_name,
num_contexts,
srmmu_nocache_size,
srmmu_nocache_map.used << SRMMU_NOCACHE_BITMAP_SHIFT);
}
int init_new_context(struct task_struct *tsk, struct mm_struct *mm)
{
mm->context = NO_CONTEXT;
return 0;
}
void destroy_context(struct mm_struct *mm)
{
unsigned long flags;
if (mm->context != NO_CONTEXT) {
flush_cache_mm(mm);
srmmu_ctxd_set(&srmmu_context_table[mm->context], srmmu_swapper_pg_dir);
flush_tlb_mm(mm);
spin_lock_irqsave(&srmmu_context_spinlock, flags);
free_context(mm->context);
spin_unlock_irqrestore(&srmmu_context_spinlock, flags);
mm->context = NO_CONTEXT;
}
}
/* Init various srmmu chip types. */
static void __init srmmu_is_bad(void)
{
prom_printf("Could not determine SRMMU chip type.\n");
prom_halt();
}
static void __init init_vac_layout(void)
{
phandle nd;
int cache_lines;
char node_str[128];
#ifdef CONFIG_SMP
int cpu = 0;
unsigned long max_size = 0;
unsigned long min_line_size = 0x10000000;
#endif
nd = prom_getchild(prom_root_node);
while ((nd = prom_getsibling(nd)) != 0) {
prom_getstring(nd, "device_type", node_str, sizeof(node_str));
if (!strcmp(node_str, "cpu")) {
vac_line_size = prom_getint(nd, "cache-line-size");
if (vac_line_size == -1) {
prom_printf("can't determine cache-line-size, halting.\n");
prom_halt();
}
cache_lines = prom_getint(nd, "cache-nlines");
if (cache_lines == -1) {
prom_printf("can't determine cache-nlines, halting.\n");
prom_halt();
}
vac_cache_size = cache_lines * vac_line_size;
#ifdef CONFIG_SMP
if (vac_cache_size > max_size)
max_size = vac_cache_size;
if (vac_line_size < min_line_size)
min_line_size = vac_line_size;
//FIXME: cpus not contiguous!!
cpu++;
if (cpu >= nr_cpu_ids || !cpu_online(cpu))
break;
#else
break;
#endif
}
}
if (nd == 0) {
prom_printf("No CPU nodes found, halting.\n");
prom_halt();
}
#ifdef CONFIG_SMP
vac_cache_size = max_size;
vac_line_size = min_line_size;
#endif
printk("SRMMU: Using VAC size of %d bytes, line size %d bytes.\n",
(int)vac_cache_size, (int)vac_line_size);
}
sparc: delete __cpuinit/__CPUINIT usage from all users The __cpuinit type of throwaway sections might have made sense some time ago when RAM was more constrained, but now the savings do not offset the cost and complications. For example, the fix in commit 5e427ec2d0 ("x86: Fix bit corruption at CPU resume time") is a good example of the nasty type of bugs that can be created with improper use of the various __init prefixes. After a discussion on LKML[1] it was decided that cpuinit should go the way of devinit and be phased out. Once all the users are gone, we can then finally remove the macros themselves from linux/init.h. Note that some harmless section mismatch warnings may result, since notify_cpu_starting() and cpu_up() are arch independent (kernel/cpu.c) are flagged as __cpuinit -- so if we remove the __cpuinit from arch specific callers, we will also get section mismatch warnings. As an intermediate step, we intend to turn the linux/init.h cpuinit content into no-ops as early as possible, since that will get rid of these warnings. In any case, they are temporary and harmless. This removes all the arch/sparc uses of the __cpuinit macros from C files and removes __CPUINIT from assembly files. Note that even though arch/sparc/kernel/trampoline_64.S has instances of ".previous" in it, they are all paired off against explicit ".section" directives, and not implicitly paired with __CPUINIT (unlike mips and arm were). [1] https://lkml.org/lkml/2013/5/20/589 Cc: "David S. Miller" <davem@davemloft.net> Cc: sparclinux@vger.kernel.org Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com>
2013-06-18 03:43:14 +08:00
static void poke_hypersparc(void)
{
volatile unsigned long clear;
unsigned long mreg = srmmu_get_mmureg();
hyper_flush_unconditional_combined();
mreg &= ~(HYPERSPARC_CWENABLE);
mreg |= (HYPERSPARC_CENABLE | HYPERSPARC_WBENABLE);
mreg |= (HYPERSPARC_CMODE);
srmmu_set_mmureg(mreg);
#if 0 /* XXX I think this is bad news... -DaveM */
hyper_clear_all_tags();
#endif
put_ross_icr(HYPERSPARC_ICCR_FTD | HYPERSPARC_ICCR_ICE);
hyper_flush_whole_icache();
clear = srmmu_get_faddr();
clear = srmmu_get_fstatus();
}
static const struct sparc32_cachetlb_ops hypersparc_ops = {
.cache_all = hypersparc_flush_cache_all,
.cache_mm = hypersparc_flush_cache_mm,
.cache_page = hypersparc_flush_cache_page,
.cache_range = hypersparc_flush_cache_range,
.tlb_all = hypersparc_flush_tlb_all,
.tlb_mm = hypersparc_flush_tlb_mm,
.tlb_page = hypersparc_flush_tlb_page,
.tlb_range = hypersparc_flush_tlb_range,
.page_to_ram = hypersparc_flush_page_to_ram,
.sig_insns = hypersparc_flush_sig_insns,
.page_for_dma = hypersparc_flush_page_for_dma,
};
static void __init init_hypersparc(void)
{
srmmu_name = "ROSS HyperSparc";
srmmu_modtype = HyperSparc;
init_vac_layout();
is_hypersparc = 1;
sparc32_cachetlb_ops = &hypersparc_ops;
poke_srmmu = poke_hypersparc;
hypersparc_setup_blockops();
}
sparc: delete __cpuinit/__CPUINIT usage from all users The __cpuinit type of throwaway sections might have made sense some time ago when RAM was more constrained, but now the savings do not offset the cost and complications. For example, the fix in commit 5e427ec2d0 ("x86: Fix bit corruption at CPU resume time") is a good example of the nasty type of bugs that can be created with improper use of the various __init prefixes. After a discussion on LKML[1] it was decided that cpuinit should go the way of devinit and be phased out. Once all the users are gone, we can then finally remove the macros themselves from linux/init.h. Note that some harmless section mismatch warnings may result, since notify_cpu_starting() and cpu_up() are arch independent (kernel/cpu.c) are flagged as __cpuinit -- so if we remove the __cpuinit from arch specific callers, we will also get section mismatch warnings. As an intermediate step, we intend to turn the linux/init.h cpuinit content into no-ops as early as possible, since that will get rid of these warnings. In any case, they are temporary and harmless. This removes all the arch/sparc uses of the __cpuinit macros from C files and removes __CPUINIT from assembly files. Note that even though arch/sparc/kernel/trampoline_64.S has instances of ".previous" in it, they are all paired off against explicit ".section" directives, and not implicitly paired with __CPUINIT (unlike mips and arm were). [1] https://lkml.org/lkml/2013/5/20/589 Cc: "David S. Miller" <davem@davemloft.net> Cc: sparclinux@vger.kernel.org Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com>
2013-06-18 03:43:14 +08:00
static void poke_swift(void)
{
unsigned long mreg;
/* Clear any crap from the cache or else... */
swift_flush_cache_all();
/* Enable I & D caches */
mreg = srmmu_get_mmureg();
mreg |= (SWIFT_IE | SWIFT_DE);
/*
* The Swift branch folding logic is completely broken. At
* trap time, if things are just right, if can mistakenly
* think that a trap is coming from kernel mode when in fact
* it is coming from user mode (it mis-executes the branch in
* the trap code). So you see things like crashme completely
* hosing your machine which is completely unacceptable. Turn
* this shit off... nice job Fujitsu.
*/
mreg &= ~(SWIFT_BF);
srmmu_set_mmureg(mreg);
}
static const struct sparc32_cachetlb_ops swift_ops = {
.cache_all = swift_flush_cache_all,
.cache_mm = swift_flush_cache_mm,
.cache_page = swift_flush_cache_page,
.cache_range = swift_flush_cache_range,
.tlb_all = swift_flush_tlb_all,
.tlb_mm = swift_flush_tlb_mm,
.tlb_page = swift_flush_tlb_page,
.tlb_range = swift_flush_tlb_range,
.page_to_ram = swift_flush_page_to_ram,
.sig_insns = swift_flush_sig_insns,
.page_for_dma = swift_flush_page_for_dma,
};
#define SWIFT_MASKID_ADDR 0x10003018
static void __init init_swift(void)
{
unsigned long swift_rev;
__asm__ __volatile__("lda [%1] %2, %0\n\t"
"srl %0, 0x18, %0\n\t" :
"=r" (swift_rev) :
"r" (SWIFT_MASKID_ADDR), "i" (ASI_M_BYPASS));
srmmu_name = "Fujitsu Swift";
switch (swift_rev) {
case 0x11:
case 0x20:
case 0x23:
case 0x30:
srmmu_modtype = Swift_lots_o_bugs;
hwbug_bitmask |= (HWBUG_KERN_ACCBROKEN | HWBUG_KERN_CBITBROKEN);
/*
* Gee george, I wonder why Sun is so hush hush about
* this hardware bug... really braindamage stuff going
* on here. However I think we can find a way to avoid
* all of the workaround overhead under Linux. Basically,
* any page fault can cause kernel pages to become user
* accessible (the mmu gets confused and clears some of
* the ACC bits in kernel ptes). Aha, sounds pretty
* horrible eh? But wait, after extensive testing it appears
* that if you use pgd_t level large kernel pte's (like the
* 4MB pages on the Pentium) the bug does not get tripped
* at all. This avoids almost all of the major overhead.
* Welcome to a world where your vendor tells you to,
* "apply this kernel patch" instead of "sorry for the
* broken hardware, send it back and we'll give you
* properly functioning parts"
*/
break;
case 0x25:
case 0x31:
srmmu_modtype = Swift_bad_c;
hwbug_bitmask |= HWBUG_KERN_CBITBROKEN;
/*
* You see Sun allude to this hardware bug but never
* admit things directly, they'll say things like,
* "the Swift chip cache problems" or similar.
*/
break;
default:
srmmu_modtype = Swift_ok;
break;
}
sparc32_cachetlb_ops = &swift_ops;
flush_page_for_dma_global = 0;
/*
* Are you now convinced that the Swift is one of the
* biggest VLSI abortions of all time? Bravo Fujitsu!
* Fujitsu, the !#?!%$'d up processor people. I bet if
* you examined the microcode of the Swift you'd find
* XXX's all over the place.
*/
poke_srmmu = poke_swift;
}
static void turbosparc_flush_cache_all(void)
{
flush_user_windows();
turbosparc_idflash_clear();
}
static void turbosparc_flush_cache_mm(struct mm_struct *mm)
{
FLUSH_BEGIN(mm)
flush_user_windows();
turbosparc_idflash_clear();
FLUSH_END
}
static void turbosparc_flush_cache_range(struct vm_area_struct *vma, unsigned long start, unsigned long end)
{
FLUSH_BEGIN(vma->vm_mm)
flush_user_windows();
turbosparc_idflash_clear();
FLUSH_END
}
static void turbosparc_flush_cache_page(struct vm_area_struct *vma, unsigned long page)
{
FLUSH_BEGIN(vma->vm_mm)
flush_user_windows();
if (vma->vm_flags & VM_EXEC)
turbosparc_flush_icache();
turbosparc_flush_dcache();
FLUSH_END
}
/* TurboSparc is copy-back, if we turn it on, but this does not work. */
static void turbosparc_flush_page_to_ram(unsigned long page)
{
#ifdef TURBOSPARC_WRITEBACK
volatile unsigned long clear;
if (srmmu_probe(page))
turbosparc_flush_page_cache(page);
clear = srmmu_get_fstatus();
#endif
}
static void turbosparc_flush_sig_insns(struct mm_struct *mm, unsigned long insn_addr)
{
}
static void turbosparc_flush_page_for_dma(unsigned long page)
{
turbosparc_flush_dcache();
}
static void turbosparc_flush_tlb_all(void)
{
srmmu_flush_whole_tlb();
}
static void turbosparc_flush_tlb_mm(struct mm_struct *mm)
{
FLUSH_BEGIN(mm)
srmmu_flush_whole_tlb();
FLUSH_END
}
static void turbosparc_flush_tlb_range(struct vm_area_struct *vma, unsigned long start, unsigned long end)
{
FLUSH_BEGIN(vma->vm_mm)
srmmu_flush_whole_tlb();
FLUSH_END
}
static void turbosparc_flush_tlb_page(struct vm_area_struct *vma, unsigned long page)
{
FLUSH_BEGIN(vma->vm_mm)
srmmu_flush_whole_tlb();
FLUSH_END
}
sparc: delete __cpuinit/__CPUINIT usage from all users The __cpuinit type of throwaway sections might have made sense some time ago when RAM was more constrained, but now the savings do not offset the cost and complications. For example, the fix in commit 5e427ec2d0 ("x86: Fix bit corruption at CPU resume time") is a good example of the nasty type of bugs that can be created with improper use of the various __init prefixes. After a discussion on LKML[1] it was decided that cpuinit should go the way of devinit and be phased out. Once all the users are gone, we can then finally remove the macros themselves from linux/init.h. Note that some harmless section mismatch warnings may result, since notify_cpu_starting() and cpu_up() are arch independent (kernel/cpu.c) are flagged as __cpuinit -- so if we remove the __cpuinit from arch specific callers, we will also get section mismatch warnings. As an intermediate step, we intend to turn the linux/init.h cpuinit content into no-ops as early as possible, since that will get rid of these warnings. In any case, they are temporary and harmless. This removes all the arch/sparc uses of the __cpuinit macros from C files and removes __CPUINIT from assembly files. Note that even though arch/sparc/kernel/trampoline_64.S has instances of ".previous" in it, they are all paired off against explicit ".section" directives, and not implicitly paired with __CPUINIT (unlike mips and arm were). [1] https://lkml.org/lkml/2013/5/20/589 Cc: "David S. Miller" <davem@davemloft.net> Cc: sparclinux@vger.kernel.org Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com>
2013-06-18 03:43:14 +08:00
static void poke_turbosparc(void)
{
unsigned long mreg = srmmu_get_mmureg();
unsigned long ccreg;
/* Clear any crap from the cache or else... */
turbosparc_flush_cache_all();
/* Temporarily disable I & D caches */
mreg &= ~(TURBOSPARC_ICENABLE | TURBOSPARC_DCENABLE);
mreg &= ~(TURBOSPARC_PCENABLE); /* Don't check parity */
srmmu_set_mmureg(mreg);
ccreg = turbosparc_get_ccreg();
#ifdef TURBOSPARC_WRITEBACK
ccreg |= (TURBOSPARC_SNENABLE); /* Do DVMA snooping in Dcache */
ccreg &= ~(TURBOSPARC_uS2 | TURBOSPARC_WTENABLE);
/* Write-back D-cache, emulate VLSI
* abortion number three, not number one */
#else
/* For now let's play safe, optimize later */
ccreg |= (TURBOSPARC_SNENABLE | TURBOSPARC_WTENABLE);
/* Do DVMA snooping in Dcache, Write-thru D-cache */
ccreg &= ~(TURBOSPARC_uS2);
/* Emulate VLSI abortion number three, not number one */
#endif
switch (ccreg & 7) {
case 0: /* No SE cache */
case 7: /* Test mode */
break;
default:
ccreg |= (TURBOSPARC_SCENABLE);
}
turbosparc_set_ccreg(ccreg);
mreg |= (TURBOSPARC_ICENABLE | TURBOSPARC_DCENABLE); /* I & D caches on */
mreg |= (TURBOSPARC_ICSNOOP); /* Icache snooping on */
srmmu_set_mmureg(mreg);
}
static const struct sparc32_cachetlb_ops turbosparc_ops = {
.cache_all = turbosparc_flush_cache_all,
.cache_mm = turbosparc_flush_cache_mm,
.cache_page = turbosparc_flush_cache_page,
.cache_range = turbosparc_flush_cache_range,
.tlb_all = turbosparc_flush_tlb_all,
.tlb_mm = turbosparc_flush_tlb_mm,
.tlb_page = turbosparc_flush_tlb_page,
.tlb_range = turbosparc_flush_tlb_range,
.page_to_ram = turbosparc_flush_page_to_ram,
.sig_insns = turbosparc_flush_sig_insns,
.page_for_dma = turbosparc_flush_page_for_dma,
};
static void __init init_turbosparc(void)
{
srmmu_name = "Fujitsu TurboSparc";
srmmu_modtype = TurboSparc;
sparc32_cachetlb_ops = &turbosparc_ops;
poke_srmmu = poke_turbosparc;
}
sparc: delete __cpuinit/__CPUINIT usage from all users The __cpuinit type of throwaway sections might have made sense some time ago when RAM was more constrained, but now the savings do not offset the cost and complications. For example, the fix in commit 5e427ec2d0 ("x86: Fix bit corruption at CPU resume time") is a good example of the nasty type of bugs that can be created with improper use of the various __init prefixes. After a discussion on LKML[1] it was decided that cpuinit should go the way of devinit and be phased out. Once all the users are gone, we can then finally remove the macros themselves from linux/init.h. Note that some harmless section mismatch warnings may result, since notify_cpu_starting() and cpu_up() are arch independent (kernel/cpu.c) are flagged as __cpuinit -- so if we remove the __cpuinit from arch specific callers, we will also get section mismatch warnings. As an intermediate step, we intend to turn the linux/init.h cpuinit content into no-ops as early as possible, since that will get rid of these warnings. In any case, they are temporary and harmless. This removes all the arch/sparc uses of the __cpuinit macros from C files and removes __CPUINIT from assembly files. Note that even though arch/sparc/kernel/trampoline_64.S has instances of ".previous" in it, they are all paired off against explicit ".section" directives, and not implicitly paired with __CPUINIT (unlike mips and arm were). [1] https://lkml.org/lkml/2013/5/20/589 Cc: "David S. Miller" <davem@davemloft.net> Cc: sparclinux@vger.kernel.org Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com>
2013-06-18 03:43:14 +08:00
static void poke_tsunami(void)
{
unsigned long mreg = srmmu_get_mmureg();
tsunami_flush_icache();
tsunami_flush_dcache();
mreg &= ~TSUNAMI_ITD;
mreg |= (TSUNAMI_IENAB | TSUNAMI_DENAB);
srmmu_set_mmureg(mreg);
}
static const struct sparc32_cachetlb_ops tsunami_ops = {
.cache_all = tsunami_flush_cache_all,
.cache_mm = tsunami_flush_cache_mm,
.cache_page = tsunami_flush_cache_page,
.cache_range = tsunami_flush_cache_range,
.tlb_all = tsunami_flush_tlb_all,
.tlb_mm = tsunami_flush_tlb_mm,
.tlb_page = tsunami_flush_tlb_page,
.tlb_range = tsunami_flush_tlb_range,
.page_to_ram = tsunami_flush_page_to_ram,
.sig_insns = tsunami_flush_sig_insns,
.page_for_dma = tsunami_flush_page_for_dma,
};
static void __init init_tsunami(void)
{
/*
* Tsunami's pretty sane, Sun and TI actually got it
* somewhat right this time. Fujitsu should have
* taken some lessons from them.
*/
srmmu_name = "TI Tsunami";
srmmu_modtype = Tsunami;
sparc32_cachetlb_ops = &tsunami_ops;
poke_srmmu = poke_tsunami;
tsunami_setup_blockops();
}
sparc: delete __cpuinit/__CPUINIT usage from all users The __cpuinit type of throwaway sections might have made sense some time ago when RAM was more constrained, but now the savings do not offset the cost and complications. For example, the fix in commit 5e427ec2d0 ("x86: Fix bit corruption at CPU resume time") is a good example of the nasty type of bugs that can be created with improper use of the various __init prefixes. After a discussion on LKML[1] it was decided that cpuinit should go the way of devinit and be phased out. Once all the users are gone, we can then finally remove the macros themselves from linux/init.h. Note that some harmless section mismatch warnings may result, since notify_cpu_starting() and cpu_up() are arch independent (kernel/cpu.c) are flagged as __cpuinit -- so if we remove the __cpuinit from arch specific callers, we will also get section mismatch warnings. As an intermediate step, we intend to turn the linux/init.h cpuinit content into no-ops as early as possible, since that will get rid of these warnings. In any case, they are temporary and harmless. This removes all the arch/sparc uses of the __cpuinit macros from C files and removes __CPUINIT from assembly files. Note that even though arch/sparc/kernel/trampoline_64.S has instances of ".previous" in it, they are all paired off against explicit ".section" directives, and not implicitly paired with __CPUINIT (unlike mips and arm were). [1] https://lkml.org/lkml/2013/5/20/589 Cc: "David S. Miller" <davem@davemloft.net> Cc: sparclinux@vger.kernel.org Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com>
2013-06-18 03:43:14 +08:00
static void poke_viking(void)
{
unsigned long mreg = srmmu_get_mmureg();
static int smp_catch;
if (viking_mxcc_present) {
unsigned long mxcc_control = mxcc_get_creg();
mxcc_control |= (MXCC_CTL_ECE | MXCC_CTL_PRE | MXCC_CTL_MCE);
mxcc_control &= ~(MXCC_CTL_RRC);
mxcc_set_creg(mxcc_control);
/*
* We don't need memory parity checks.
* XXX This is a mess, have to dig out later. ecd.
viking_mxcc_turn_off_parity(&mreg, &mxcc_control);
*/
/* We do cache ptables on MXCC. */
mreg |= VIKING_TCENABLE;
} else {
unsigned long bpreg;
mreg &= ~(VIKING_TCENABLE);
if (smp_catch++) {
/* Must disable mixed-cmd mode here for other cpu's. */
bpreg = viking_get_bpreg();
bpreg &= ~(VIKING_ACTION_MIX);
viking_set_bpreg(bpreg);
/* Just in case PROM does something funny. */
msi_set_sync();
}
}
mreg |= VIKING_SPENABLE;
mreg |= (VIKING_ICENABLE | VIKING_DCENABLE);
mreg |= VIKING_SBENABLE;
mreg &= ~(VIKING_ACENABLE);
srmmu_set_mmureg(mreg);
}
static struct sparc32_cachetlb_ops viking_ops __ro_after_init = {
.cache_all = viking_flush_cache_all,
.cache_mm = viking_flush_cache_mm,
.cache_page = viking_flush_cache_page,
.cache_range = viking_flush_cache_range,
.tlb_all = viking_flush_tlb_all,
.tlb_mm = viking_flush_tlb_mm,
.tlb_page = viking_flush_tlb_page,
.tlb_range = viking_flush_tlb_range,
.page_to_ram = viking_flush_page_to_ram,
.sig_insns = viking_flush_sig_insns,
.page_for_dma = viking_flush_page_for_dma,
};
#ifdef CONFIG_SMP
/* On sun4d the cpu broadcasts local TLB flushes, so we can just
* perform the local TLB flush and all the other cpus will see it.
* But, unfortunately, there is a bug in the sun4d XBUS backplane
* that requires that we add some synchronization to these flushes.
*
* The bug is that the fifo which keeps track of all the pending TLB
* broadcasts in the system is an entry or two too small, so if we
* have too many going at once we'll overflow that fifo and lose a TLB
* flush resulting in corruption.
*
* Our workaround is to take a global spinlock around the TLB flushes,
* which guarentees we won't ever have too many pending. It's a big
* hammer, but a semaphore like system to make sure we only have N TLB
* flushes going at once will require SMP locking anyways so there's
* no real value in trying any harder than this.
*/
static struct sparc32_cachetlb_ops viking_sun4d_smp_ops __ro_after_init = {
.cache_all = viking_flush_cache_all,
.cache_mm = viking_flush_cache_mm,
.cache_page = viking_flush_cache_page,
.cache_range = viking_flush_cache_range,
.tlb_all = sun4dsmp_flush_tlb_all,
.tlb_mm = sun4dsmp_flush_tlb_mm,
.tlb_page = sun4dsmp_flush_tlb_page,
.tlb_range = sun4dsmp_flush_tlb_range,
.page_to_ram = viking_flush_page_to_ram,
.sig_insns = viking_flush_sig_insns,
.page_for_dma = viking_flush_page_for_dma,
};
#endif
static void __init init_viking(void)
{
unsigned long mreg = srmmu_get_mmureg();
/* Ahhh, the viking. SRMMU VLSI abortion number two... */
if (mreg & VIKING_MMODE) {
srmmu_name = "TI Viking";
viking_mxcc_present = 0;
msi_set_sync();
/*
* We need this to make sure old viking takes no hits
* on it's cache for dma snoops to workaround the
* "load from non-cacheable memory" interrupt bug.
* This is only necessary because of the new way in
* which we use the IOMMU.
*/
viking_ops.page_for_dma = viking_flush_page;
#ifdef CONFIG_SMP
viking_sun4d_smp_ops.page_for_dma = viking_flush_page;
#endif
flush_page_for_dma_global = 0;
} else {
srmmu_name = "TI Viking/MXCC";
viking_mxcc_present = 1;
srmmu_cache_pagetables = 1;
}
sparc32_cachetlb_ops = (const struct sparc32_cachetlb_ops *)
&viking_ops;
#ifdef CONFIG_SMP
if (sparc_cpu_model == sun4d)
sparc32_cachetlb_ops = (const struct sparc32_cachetlb_ops *)
&viking_sun4d_smp_ops;
#endif
poke_srmmu = poke_viking;
}
/* Probe for the srmmu chip version. */
static void __init get_srmmu_type(void)
{
unsigned long mreg, psr;
unsigned long mod_typ, mod_rev, psr_typ, psr_vers;
srmmu_modtype = SRMMU_INVAL_MOD;
hwbug_bitmask = 0;
mreg = srmmu_get_mmureg(); psr = get_psr();
mod_typ = (mreg & 0xf0000000) >> 28;
mod_rev = (mreg & 0x0f000000) >> 24;
psr_typ = (psr >> 28) & 0xf;
psr_vers = (psr >> 24) & 0xf;
/* First, check for sparc-leon. */
if (sparc_cpu_model == sparc_leon) {
init_leon();
return;
}
/* Second, check for HyperSparc or Cypress. */
if (mod_typ == 1) {
switch (mod_rev) {
case 7:
/* UP or MP Hypersparc */
init_hypersparc();
break;
case 0:
case 2:
case 10:
case 11:
case 12:
case 13:
case 14:
case 15:
default:
prom_printf("Sparc-Linux Cypress support does not longer exit.\n");
prom_halt();
break;
}
return;
}
/* Now Fujitsu TurboSparc. It might happen that it is
* in Swift emulation mode, so we will check later...
*/
if (psr_typ == 0 && psr_vers == 5) {
init_turbosparc();
return;
}
/* Next check for Fujitsu Swift. */
if (psr_typ == 0 && psr_vers == 4) {
phandle cpunode;
char node_str[128];
/* Look if it is not a TurboSparc emulating Swift... */
cpunode = prom_getchild(prom_root_node);
while ((cpunode = prom_getsibling(cpunode)) != 0) {
prom_getstring(cpunode, "device_type", node_str, sizeof(node_str));
if (!strcmp(node_str, "cpu")) {
if (!prom_getintdefault(cpunode, "psr-implementation", 1) &&
prom_getintdefault(cpunode, "psr-version", 1) == 5) {
init_turbosparc();
return;
}
break;
}
}
init_swift();
return;
}
/* Now the Viking family of srmmu. */
if (psr_typ == 4 &&
((psr_vers == 0) ||
((psr_vers == 1) && (mod_typ == 0) && (mod_rev == 0)))) {
init_viking();
return;
}
/* Finally the Tsunami. */
if (psr_typ == 4 && psr_vers == 1 && (mod_typ || mod_rev)) {
init_tsunami();
return;
}
/* Oh well */
srmmu_is_bad();
}
#ifdef CONFIG_SMP
/* Local cross-calls. */
static void smp_flush_page_for_dma(unsigned long page)
{
xc1(local_ops->page_for_dma, page);
local_ops->page_for_dma(page);
}
static void smp_flush_cache_all(void)
{
xc0(local_ops->cache_all);
local_ops->cache_all();
}
static void smp_flush_tlb_all(void)
{
xc0(local_ops->tlb_all);
local_ops->tlb_all();
}
static void smp_flush_cache_mm(struct mm_struct *mm)
{
if (mm->context != NO_CONTEXT) {
cpumask_t cpu_mask;
cpumask_copy(&cpu_mask, mm_cpumask(mm));
cpumask_clear_cpu(smp_processor_id(), &cpu_mask);
if (!cpumask_empty(&cpu_mask))
xc1(local_ops->cache_mm, (unsigned long)mm);
local_ops->cache_mm(mm);
}
}
static void smp_flush_tlb_mm(struct mm_struct *mm)
{
if (mm->context != NO_CONTEXT) {
cpumask_t cpu_mask;
cpumask_copy(&cpu_mask, mm_cpumask(mm));
cpumask_clear_cpu(smp_processor_id(), &cpu_mask);
if (!cpumask_empty(&cpu_mask)) {
xc1(local_ops->tlb_mm, (unsigned long)mm);
if (atomic_read(&mm->mm_users) == 1 && current->active_mm == mm)
cpumask_copy(mm_cpumask(mm),
cpumask_of(smp_processor_id()));
}
local_ops->tlb_mm(mm);
}
}
static void smp_flush_cache_range(struct vm_area_struct *vma,
unsigned long start,
unsigned long end)
{
struct mm_struct *mm = vma->vm_mm;
if (mm->context != NO_CONTEXT) {
cpumask_t cpu_mask;
cpumask_copy(&cpu_mask, mm_cpumask(mm));
cpumask_clear_cpu(smp_processor_id(), &cpu_mask);
if (!cpumask_empty(&cpu_mask))
xc3(local_ops->cache_range, (unsigned long)vma, start,
end);
local_ops->cache_range(vma, start, end);
}
}
static void smp_flush_tlb_range(struct vm_area_struct *vma,
unsigned long start,
unsigned long end)
{
struct mm_struct *mm = vma->vm_mm;
if (mm->context != NO_CONTEXT) {
cpumask_t cpu_mask;
cpumask_copy(&cpu_mask, mm_cpumask(mm));
cpumask_clear_cpu(smp_processor_id(), &cpu_mask);
if (!cpumask_empty(&cpu_mask))
xc3(local_ops->tlb_range, (unsigned long)vma, start,
end);
local_ops->tlb_range(vma, start, end);
}
}
static void smp_flush_cache_page(struct vm_area_struct *vma, unsigned long page)
{
struct mm_struct *mm = vma->vm_mm;
if (mm->context != NO_CONTEXT) {
cpumask_t cpu_mask;
cpumask_copy(&cpu_mask, mm_cpumask(mm));
cpumask_clear_cpu(smp_processor_id(), &cpu_mask);
if (!cpumask_empty(&cpu_mask))
xc2(local_ops->cache_page, (unsigned long)vma, page);
local_ops->cache_page(vma, page);
}
}
static void smp_flush_tlb_page(struct vm_area_struct *vma, unsigned long page)
{
struct mm_struct *mm = vma->vm_mm;
if (mm->context != NO_CONTEXT) {
cpumask_t cpu_mask;
cpumask_copy(&cpu_mask, mm_cpumask(mm));
cpumask_clear_cpu(smp_processor_id(), &cpu_mask);
if (!cpumask_empty(&cpu_mask))
xc2(local_ops->tlb_page, (unsigned long)vma, page);
local_ops->tlb_page(vma, page);
}
}
static void smp_flush_page_to_ram(unsigned long page)
{
/* Current theory is that those who call this are the one's
* who have just dirtied their cache with the pages contents
* in kernel space, therefore we only run this on local cpu.
*
* XXX This experiment failed, research further... -DaveM
*/
#if 1
xc1(local_ops->page_to_ram, page);
#endif
local_ops->page_to_ram(page);
}
static void smp_flush_sig_insns(struct mm_struct *mm, unsigned long insn_addr)
{
cpumask_t cpu_mask;
cpumask_copy(&cpu_mask, mm_cpumask(mm));
cpumask_clear_cpu(smp_processor_id(), &cpu_mask);
if (!cpumask_empty(&cpu_mask))
xc2(local_ops->sig_insns, (unsigned long)mm, insn_addr);
local_ops->sig_insns(mm, insn_addr);
}
static struct sparc32_cachetlb_ops smp_cachetlb_ops __ro_after_init = {
.cache_all = smp_flush_cache_all,
.cache_mm = smp_flush_cache_mm,
.cache_page = smp_flush_cache_page,
.cache_range = smp_flush_cache_range,
.tlb_all = smp_flush_tlb_all,
.tlb_mm = smp_flush_tlb_mm,
.tlb_page = smp_flush_tlb_page,
.tlb_range = smp_flush_tlb_range,
.page_to_ram = smp_flush_page_to_ram,
.sig_insns = smp_flush_sig_insns,
.page_for_dma = smp_flush_page_for_dma,
};
#endif
/* Load up routines and constants for sun4m and sun4d mmu */
void __init load_mmu(void)
{
/* Functions */
get_srmmu_type();
#ifdef CONFIG_SMP
/* El switcheroo... */
local_ops = sparc32_cachetlb_ops;
if (sparc_cpu_model == sun4d || sparc_cpu_model == sparc_leon) {
smp_cachetlb_ops.tlb_all = local_ops->tlb_all;
smp_cachetlb_ops.tlb_mm = local_ops->tlb_mm;
smp_cachetlb_ops.tlb_range = local_ops->tlb_range;
smp_cachetlb_ops.tlb_page = local_ops->tlb_page;
}
if (poke_srmmu == poke_viking) {
/* Avoid unnecessary cross calls. */
smp_cachetlb_ops.cache_all = local_ops->cache_all;
smp_cachetlb_ops.cache_mm = local_ops->cache_mm;
smp_cachetlb_ops.cache_range = local_ops->cache_range;
smp_cachetlb_ops.cache_page = local_ops->cache_page;
smp_cachetlb_ops.page_to_ram = local_ops->page_to_ram;
smp_cachetlb_ops.sig_insns = local_ops->sig_insns;
smp_cachetlb_ops.page_for_dma = local_ops->page_for_dma;
}
/* It really is const after this point. */
sparc32_cachetlb_ops = (const struct sparc32_cachetlb_ops *)
&smp_cachetlb_ops;
#endif
if (sparc_cpu_model != sun4d)
ld_mmu_iommu();
#ifdef CONFIG_SMP
if (sparc_cpu_model == sun4d)
sun4d_init_smp();
else if (sparc_cpu_model == sparc_leon)
leon_init_smp();
else
sun4m_init_smp();
#endif
}