summaryrefslogtreecommitdiffstats
path: root/arch/mips/mm/tlbex.c
Commit message (Collapse)AuthorAgeFilesLines
* MIPS: Replace MIPS-specific 64BIT_PHYS_ADDR with generic PHYS_ADDR_T_64BITRalf Baechle2014-11-241-9/+9
| | | | Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
* MIPS: tlbex: Properly fix HUGE TLB Refill exception handlerDavid Daney2014-10-221-1/+5
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | In commit 8393c524a25609 (MIPS: tlbex: Fix a missing statement for HUGETLB), the TLB Refill handler was fixed so that non-OCTEON targets would work properly with huge pages. The change was incorrect in that it broke the OCTEON case. The problem is shown here: xxx0: df7a0000 ld k0,0(k1) . . . xxxc0: df610000 ld at,0(k1) xxxc4: 335a0ff0 andi k0,k0,0xff0 xxxc8: e825ffcd bbit1 at,0x5,0x0 xxxcc: 003ad82d daddu k1,at,k0 . . . In the non-octeon case there is a destructive test for the huge PTE bit, and then at 0, $k0 is reloaded (that is what the 8393c524a25609 patch added). In the octeon case, we modify k1 in the branch delay slot, but we never need k0 again, so the new load is not needed, but since k1 is modified, if we do the load, we load from a garbage location and then get a nested TLB Refill, which is seen in userspace as either SIGBUS or SIGSEGV (depending on the garbage). The real fix is to only do this reloading if it is needed, and never where it is harmful. Signed-off-by: David Daney <david.daney@cavium.com> Cc: Huacai Chen <chenhc@lemote.com> Cc: Fuxin Zhang <zhangfx@lemote.com> Cc: Zhangjin Wu <wuzhangjin@gmail.com> Cc: stable@vger.kernel.org Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/8151/ Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
* Merge branch '3.16-fixes' into mips-for-linux-nextRalf Baechle2014-08-021-0/+3
|\
| * MIPS: bugfix: missed cache flush of TLB refill handlerLeonid Yegoshin2014-08-011-0/+2
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Commit Commit 1d40cfcd3442a53e98468cdb3e6d4d9a568d76cf Author: Ralf Baechle <ralf@linux-mips.org> Date: Fri Jul 15 15:23:23 2005 +0000 Avoid SMP cacheflushes. This is a minor optimization of startup but will also avoid smp_call_function from doing stupid things when called from a CPU that is not yet marked online. missed an appropriate cache flush of TLB refill handler because that time it was at fixed location CAC_BASE. After years the refill handler in EBASE vector is not at that location and can be allocated in some another memory and needs I-cache sync as other TLB exception vectors. Besides that, the new function - local_flash_icache_range() was introduced to avoid SMP cacheflushes. Signed-off-by: Leonid Yegoshin <Leonid.Yegoshin@imgtec.com> Cc: linux-mips@linux-mips.org Cc: paul.gortmaker@windriver.com Cc: jchandra@broadcom.com Cc: linux-kernel@vger.kernel.org Cc: david.daney@cavium.com Patchwork: https://patchwork.linux-mips.org/patch/7312/ Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
| * MIPS: tlbex: Fix a missing statement for HUGETLBHuacai Chen2014-07-301-0/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | In commit 2c8c53e28f1 (MIPS: Optimize TLB handlers for Octeon CPUs) build_r4000_tlb_refill_handler() is modified. But it doesn't compatible with the original code in HUGETLB case. Because there is a copy & paste error and one line of code is missing. It is very easy to produce a bug with LTP's hugemmap05 test. Signed-off-by: Huacai Chen <chenhc@lemote.com> Signed-off-by: Binbin Zhou <zhoubb@lemote.com> Cc: <stable@vger.kernel.org> Cc: John Crispin <john@phrozen.org> Cc: Steven J. Hill <Steven.Hill@imgtec.com> Cc: linux-mips@linux-mips.org Cc: Fuxin Zhang <zhangfx@lemote.com> Cc: Zhangjin Wu <wuzhangjin@gmail.com> Patchwork: https://patchwork.linux-mips.org/patch/7496/ Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
* | MIPS: Use dedicated exception handler if CPU supports RI/XI exceptionsLeonid Yegoshin2014-08-021-2/+2
| | | | | | | | | | | | | | | | | | | | | | | | | | Use the regular tlb_do_page_fault_0 (no write) handler to handle the RI and XI exceptions. Also skip the RI/XI validation check on TLB load handler since it's redundant when the CPU has unique RI/XI exceptions. Singed-off-by: Leonid Yegoshin <Leonid.Yegoshin@imgtec.com> Signed-off-by: Markos Chandras <markos.chandras@imgtec.com> Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/7339/ Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
* | MIPS: mm: Use the Hardware Page Table Walker if the core supports itMarkos Chandras2014-08-021-0/+91
|/ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The Hardware Page Table Walker aims to speed up TLB refill exceptions by handling them in the hardware level instead of having a software TLB refill handler. However, a TLB refill exception can still be thrown in certain cases such as, synchronus exceptions, or address translation or memory errors during the HTW operation. As a result of which, HTW must not be considered a complete replacement for the TLB refill software handler, but rather a fast-path for it. For HTW to work, the PWBase register must contain the task's page global directory address so the HTW will kick in on TLB refill exceptions. Due to HTW being a separate engine embedded deep in the CPU pipeline, we need to restart the HTW everytime a PTE changes to avoid HTW fetching a old entry from the page tables. It's also necessary to restart the HTW on context switches to prevent it from fetching a page from the previous process. Finally, since HTW is using the entryhi register to write the translations to the TLB, it's necessary to stop the HTW whenever the entryhi changes (eg for tlb probe perations) and enable it back afterwards. == Performance == The following trivial test was used to measure the performance of the HTW. Using the same root filesystem, the following command was used to measure the number of tlb refill handler executions with and without (using 'nohtw' kernel parameter) HTW support. The kernel was modified to use a scratch register as a counter for the TLB refill exceptions. find /usr -type f -exec ls -lh {} \; HTW Enabled: TLB refill exceptions: 12306 HTW Disabled: TLB refill exceptions: 17805 Signed-off-by: Markos Chandras <markos.chandras@imgtec.com> Cc: linux-mips@linux-mips.org Cc: Markos Chandras <markos.chandras@imgtec.com> Patchwork: https://patchwork.linux-mips.org/patch/7336/ Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
* MIPS: Add code for new system 'paravirt'David Daney2014-06-021-6/+2
| | | | | | | | | | | | | For para-virtualized guests running under KVM or other equivalent hypervisor. Signed-off-by: David Daney <david.daney@cavium.com> Signed-off-by: Andreas Herrmann <andreas.herrmann@caviumnetworks.com> Cc: linux-mips@linux-mips.org Cc: James Hogan <james.hogan@imgtec.com> Cc: kvm@vger.kernel.org Patchwork: https://patchwork.linux-mips.org/patch/7004/ Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
* MIPS: Don't build fast TLB refill handler with 32-bit kernelsDavid Daney2014-05-301-2/+6
| | | | | | | | | | | | The fast handler only supports 64-bit kernels. Signed-off-by: David Daney <david.daney@cavium.com> Signed-off-by: Andreas Herrmann <andreas.herrmann@caviumnetworks.com> Cc: linux-mips@linux-mips.org Cc: James Hogan <james.hogan@imgtec.com> Cc: kvm@vger.kernel.org Patchwork: https://patchwork.linux-mips.org/patch/7010/ Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
* MIPS: mm: Fix broken microMIPS kernel regression.Steven J. Hill2014-05-141-3/+4
| | | | | | | | | | | | Commit f4ae17aa0f2122b52f642985b46210a1f2eceb0a [MIPS: mm: Use scratch for PGD when !CONFIG_MIPS_PGD_C0_CONTEXT] broke microMIPS kernel builds. This patch refactors that code similar to what was done for the 'clear_page' and 'copy_page' functions. Signed-off-by: Steven J. Hill <Steven.Hill@imgtec.com> Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/6744/ Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
* MIPS: Loongson: Add basic Loongson-3 CPU supportHuacai Chen2014-03-311-0/+1
| | | | | | | | | | | | | | | | | | | Basic Loongson-3 CPU support include CPU probing and TLB/cache initializing. Signed-off-by: Huacai Chen <chenhc@lemote.com> Signed-off-by: Hongliang Tao <taohl@lemote.com> Signed-off-by: Hua Yan <yanh@lemote.com> Tested-by: Alex Smith <alex.smith@imgtec.com> Reviewed-by: Alex Smith <alex.smith@imgtec.com> Cc: John Crispin <john@phrozen.org> Cc: Steven J. Hill <Steven.Hill@imgtec.com> Cc: Aurelien Jarno <aurelien@aurel32.net> Cc: linux-mips@linux-mips.org Cc: Fuxin Zhang <zhangfx@lemote.com> Cc: Zhangjin Wu <wuzhangjin@gmail.com> Patchwork: https://patchwork.linux-mips.org/patch/6630 Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
* MIPS: Use current_cpu_type() instead of c->cputypeWu Zhangjin2014-03-311-1/+1
| | | | | | | | | | If current_cpu_type() is pre-defined in cpu-feature-overrides.h, This may save about 10k for the compressed kernel image(vmlinuz). Signed-off-by: Wu Zhangjin <wuzhangjin@gmail.com> Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/1901/ Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
* MIPS: Add support for the M5150 processorLeonid Yegoshin2014-03-261-0/+1
| | | | | | | | | | | | | | The M5150 core is a 32-bit MIPS RISC which implements the MIPS Architecture Release-5 in a 5-stage pipeline. In addition, it includes the MIPS Architecture Virtualization Module that enables virtualization of operating systems, which provides a scalable, trusted, and secure execution environment. Signed-off-by: Leonid Yegoshin <Leonid.Yegoshin@imgtec.com> Signed-off-by: Markos Chandras <markos.chandras@imgtec.com> Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/6596/ Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
* MIPS: Add cases for CPU_P5600James Hogan2014-03-261-0/+1
| | | | | | | | | | | Add a CPU_P5600 case to various switch statements, doing the same thing as for CPU_PROAPTIV. Signed-off-by: James Hogan <james.hogan@imgtec.com> Reviewed-by: Markos Chandras <markos.chandras@imgtec.com> Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/6408/ Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
* MIPS: Add 1074K CPU support explicitly.Steven J. Hill2014-03-061-0/+1
| | | | | | | | | | | | The 1074K is a multiprocessing coherent processing system (CPS) based on modified 74K cores. This patch makes the 1074K an actual unique CPU type, instead of a 74K derivative, which it is not. Signed-off-by: Steven J. Hill <Steven.Hill@imgtec.com> Reviewed-by: Leonid Yegoshin <Leonid.Yegoshin@imgtec.com> Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/6389/ Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
* mips: delete non-required instances of include <linux/init.h>Paul Gortmaker2014-01-241-1/+0
| | | | | | | | | | | None of these files are actually using any __init type directives and hence don't need to include <linux/init.h>. Most are just a left over from __devinit and __cpuinit removal, or simply due to code getting copied from one driver to the next. Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com> Signed-off-by: John Crispin <blogic@openwrt.org> Patchwork: http://patchwork.linux-mips.org/patch/6320/
* MIPS: Add support for the proAptiv coresLeonid Yegoshin2014-01-221-0/+1
| | | | | | | | | | | | | | | | The proAptiv Multiprocessing System is a power efficient multi-core microprocessor for use in system-on-chip (SoC) applications. The proAptiv Multiprocessing System combines a deep pipeline with multi-issue out of order execution for improved computational throughput. The proAptiv Multiprocessing System can contain one to six MIPS32r3 proAptiv cores, system level coherence manager with L2 cache, optional coherent I/O port, and optional floating point unit. Signed-off-by: Leonid Yegoshin <Leonid.Yegoshin@imgtec.com> Signed-off-by: Markos Chandras <markos.chandras@imgtec.com> Signed-off-by: John Crispin <blogic@openwrt.org> Patchwork: http://patchwork.linux-mips.org/patch/6134/
* MIPS: Loongson: Get rid of Loongson 2 #ifdefery all over arch/mips.Ralf Baechle2013-10-291-82/+87
| | | | | | It was ugly. Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
* MIPS: mm: Use scratch for PGD when !CONFIG_MIPS_PGD_C0_CONTEXTJayachandran C2013-10-291-33/+57
| | | | | | | | | | | | | | | | | | | | | | | Allow usage of scratch register for current pgd even when MIPS_PGD_C0_CONTEXT is not configured. MIPS_PGD_C0_CONTEXT is set for 64r2 platforms to indicate availability of Xcontext for saving cpuid, thus freeing Context to be used for saving PGD. This option was also tied to using a scratch register for storing PGD. This commit will allow usage of scratch register to store the current pgd if one can be allocated for the platform, even when MIPS_PGD_C0_CONTEXT is not set. The cpuid will be kept in the CP0 Context register in this case. The code to store the current pgd for the TLB miss handler is now generated in all cases. When scratch register is available, the PGD is also stored in the scratch register. Signed-off-by: Jayachandran C <jchandra@broadcom.com> Cc: linux-mips@linux-mips.org Cc: Hauke Mehrtens <hauke@hauke-m.de> Patchwork: https://patchwork.linux-mips.org/patch/5906/ Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
* MIPS: Move definition of SMP processor id register to header fileJayachandran C2013-10-291-50/+6
| | | | | | | | | | The definition of the CP0 register used to save the smp processor id is repicated in many files, move them all to thread_info.h. Signed-off-by: Jayachandran C <jchandra@broadcom.com> Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/5708/ Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
* MIPS: Optimize current_cpu_type() for better code.Ralf Baechle2013-09-171-0/+1
| | | | | | | | | | | | | o Move current_cpu_type() to a separate header file o #ifdefing on supported CPU types lets modern GCC know that certain code in callers may be discarded ideally turning current_cpu_type() into a function returning a constant. o Use current_cpu_type() rather than direct access to struct cpuinfo_mips. Signed-off-by: Ralf Baechle <ralf@linux-mips.org> Cc: Steven J. Hill <Steven.Hill@imgtec.com> Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/5833/
* MIPS: Generate OCTEON3 TLB handlers with the same features as OCTEON2.David Daney2013-08-261-0/+2
| | | | | | | | | OCTEON2 need the same code. Signed-off-by: David Daney <david.daney@cavium.com> Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/5637/ Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
* Merge branch 'upstream' of git://git.linux-mips.org/pub/scm/ralf/upstream-linusLinus Torvalds2013-07-191-2/+2
|\ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Pull MIPS fixes from Ralf Baechle: "MIPS fixes for 3.11. Half of then is for Netlogic the remainder touches things across arch/mips. Nothing really dramatic and by rc1 standards MIPS will be in fairly good shape with this applied. Tested by building all MIPS defconfigs of which with this pull request four platforms won't build. And yes, it boots also on my favorite test systems" * 'upstream' of git://git.linux-mips.org/pub/scm/ralf/upstream-linus: MIPS: kvm: Kconfig: Drop HAVE_KVM dependency from VIRTUALIZATION MIPS: Octeon: Fix DT pruning bug with pip ports MIPS: KVM: Mark KVM_GUEST (T&E KVM) as BROKEN_ON_SMP MIPS: tlbex: fix broken build in v3.11-rc1 MIPS: Netlogic: Add XLP PIC irqdomain MIPS: Netlogic: Fix USB block's coherent DMA mask MIPS: tlbex: Fix typo in r3000 tlb store handler MIPS: BMIPS: Fix thinko to release slave TP from reset MIPS: Delete dead invocation of exception_exit().
| * MIPS: tlbex: fix broken build in v3.11-rc1Aaro Koskinen2013-07-191-1/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | Commit 6ba045f9fbdafb48da42aa8576ea7a3980443136 (MIPS: Move generated code to .text for microMIPS) deleted tlbmiss_handler_setup_pgd_array, but some references were not converted. Fix that to enable building a MIPS kernel. Signed-off-by: Aaro Koskinen <aaro.koskinen@iki.fi> Acked-by: Jayachandran C. <jchandra@broadcom.com> Acked-by: David Daney <david.daney@cavium.com> Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/5589/ Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
| * MIPS: tlbex: Fix typo in r3000 tlb store handlerTony Wu2013-07-191-1/+1
| | | | | | | | | | | | | | | | | | | | | | | | commit 6ba045f (MIPS: Move generated code to .text for microMIPS) causes a panic at boot. The handler builder should test against handle_tlbs_end, not handle_tlbs. Signed-off-by: Tony Wu <tung7970@gmail.com> Acked-by: Jayachandran C. <jchandra@broadcom.com> Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/5600/ Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
* | MIPS: Delete __cpuinit/__CPUINIT usage from MIPS codePaul Gortmaker2013-07-141-77/+67
|/ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | commit 3747069b25e419f6b51395f48127e9812abc3596 upstream. 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) and are flagged as __cpuinit -- so if we remove the __cpuinit from the arch specific callers, we will also get section mismatch warnings. As an intermediate step, we intend to turn the linux/init.h cpuinit related content into no-ops as early as possible, since that will get rid of these warnings. In any case, they are temporary and harmless. Here, we remove all the MIPS __cpuinit from C code and __CPUINIT from asm files. MIPS is interesting in this respect, because there are also uasm users hiding behind their own renamed versions of the __cpuinit macros. [1] https://lkml.org/lkml/2013/5/20/589 [ralf@linux-mips.org: Folded in Paul's followup fix.] Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com> Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/5494/ Patchwork: https://patchwork.linux-mips.org/patch/5495/ Patchwork: https://patchwork.linux-mips.org/patch/5509/ Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
* Merge branch '3.10-fixes' into mips-for-linux-nextRalf Baechle2013-07-121-14/+42
|\ | | | | | | | | This that should have been fixed but weren't, way to much, intrusive and late.
| * MIPS: tlbex: Fix size of area to be flushed.Ralf Baechle2013-06-271-1/+1
| | | | | | | | Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
| * MIPS: Flush TLB handlers directly after writing themJonas Gorski2013-06-251-14/+16
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | When having enabled MIPS_PGD_C0_CONTEXT, trap_init() might call the generated tlbmiss_handler_setup_pgd before it was committed to memory, causing boot failures: trap_init() |- per_cpu_trap_init() | |- TLBMISS_HANDLER_SETUP() | |- tlbmiss_handler_setup_pgd() |- flush_tlb_handlers() To avoid this, move flush_tlb_handlers() into build_tlb_refill_handler() right after they were generated. We can do this as the cache handling is initialized just before creating the tlb handlers. This issue was introduced in 3d8bfdd0307223de678962f1c1907a7cec549136 ("MIPS: Use C0_KScratch (if present) to hold PGD pointer."). Signed-off-by: Jonas Gorski <jogo@openwrt.org> Cc: linux-mips@linux-mips.org Cc: Steven J. Hill <Steven.Hill@imgtec.com> Cc: Jayachandran C <jchandra@broadcom.com> Cc: David Daney <david.daney@cavium.com> Patchwork: https://patchwork.linux-mips.org/patch/5539/ Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
| * MIPS: Fix TLBR-use hazards for R2 cores in the TLB reload handlersRalf Baechle2013-06-211-0/+26
| | | | | | | | | | | | | | | | | | | | MIPS R2 documents state that an execution hazard barrier is needed after a TLBR before reading EntryLo. Original patch by Leonid Yegoshin <Leonid.Yegoshin@imgtec.com>. Signed-off-by: Ralf Baechle <ralf@linux-mips.org> Patchwork: https://patchwork.linux-mips.org/patch/5526/
* | MIPS: Fix typos and cleanup commentTony Wu2013-07-011-1/+1
| | | | | | | | | | | | | | Signed-off-by: Tony Wu <tung7970@gmail.com> Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/5535/ Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
* | MIPS: Move generated code to .text for microMIPSJayachandran C2013-07-011-40/+44
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Prepare of a next patch which will call tlbmiss_handler_setup_pgd on microMIPS. MicroMIPS complains if the called code s not in the .text section. To fix this we generate code into space reserved in arch/mips/mm/tlb-funcs.S While there, move the rest of the generated functions (handle_tlbl, handle_tlbs, handle_tlbm) to the same file. Signed-off-by: Jayachandran C <jchandra@broadcom.com> Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/5542/ Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
* | MIPS: Fixup check for invalid scratch registerJayachandran C2013-06-131-5/+5
| | | | | | | | | | | | | | | | | | | | | | The invalid value for scratch register is -1, so update the checks of the form (scratch_reg > 0) to be (scratch_reg >= 0). This will fix the case in Netlogic XLP where the scratch_reg can be 0. Signed-off-by: Jayachandran C <jchandra@broadcom.com> Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/5444/ Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
* | MIPS: Allow platform specific scratch registersJayachandran C2013-06-131-15/+26
|/ | | | | | | | | | | | | | | XLR/XLP COP0 scratch is register 22, sel 0-7. Add a function c0_kscratch() which returns the scratch register for the platform, and use the return value while generating TLB handlers. Setup kscratch_mask to 0xf for XLR/XLP since the config4 register does not exist. This allows the kernel to allocate scratch registers 0-3 if needed. Signed-off-by: Jayachandran C <jchandra@broadcom.com> Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/5445/ Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
* MIPS: Remove duplicate definition of check_for_high_segbits.David Daney2013-05-231-4/+0
| | | | | | | | | In C, one definition is sufficient. Signed-off-by: David Daney <david.daney@cavium.com> Cc: linux-mips@linux-mips.org Patchwork: https://patchwork.linux-mips.org/patch/5304/ Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
* Revert "MIPS: Allow ASID size to be determined at boot time."David Daney2013-05-161-49/+0
| | | | | | | | | | | | | | | | | | | | | | | | This reverts commit d532f3d26716a39dfd4b88d687bd344fbe77e390. The original commit has several problems: 1) Doesn't work with 64-bit kernels. 2) Calls TLBMISS_HANDLER_SETUP() before the code is generated. 3) Calls TLBMISS_HANDLER_SETUP() twice in per_cpu_trap_init() when only one call is needed. [ralf@linux-mips.org: Also revert the bits of the ASID patch which were hidden in the KVM merge.] Signed-off-by: David Daney <david.daney@cavium.com> Cc: linux-mips@linux-mips.org Cc: linux-kernel@vger.kernel.org Cc: "Steven J. Hill" <Steven.Hill@imgtec.com> Cc: David Daney <david.daney@cavium.com> Patchwork: https://patchwork.linux-mips.org/patch/5242/ Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
* Revert "MIPS: microMIPS: Support dynamic ASID sizing."David Daney2013-05-161-32/+2
| | | | | | | | | | | | | | This reverts commit f6b06d9361a008afb93b97fb3683a6e92d69d0f4. The next revert depends on this one, so this has to go too. Signed-off-by: David Daney <david.daney@cavium.com> Cc: linux-mips@linux-mips.org Cc: linux-kernel@vger.kernel.org Cc: "Steven J. Hill" <Steven.Hill@imgtec.com> Cc: David Daney <david.daney@cavium.com> Patchwork: https://patchwork.linux-mips.org/patch/5241/ Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
* Merge branch 'mti-next' of ↵Ralf Baechle2013-05-091-0/+100
|\ | | | | | | git://git.linux-mips.org/pub/scm/sjhill/linux-sjhill into mips-for-linux-next
| * MIPS: microMIPS: Add support for exception handling.Steven J. Hill2013-05-091-0/+21
| | | | | | | | | | | | | | | | | | All exceptions must be taken in microMIPS mode, never in classic MIPS mode or the kernel falls apart. A few NOP instructions are used to maintain the correct alignment of microMIPS versions of the exception vectors. Signed-off-by: Steven J. Hill <Steven.Hill@imgtec.com>
| * MIPS: microMIPS: Support dynamic ASID sizing.Steven J. Hill2013-05-081-2/+32
| | | | | | | | | | | | | | | | | | | | Changes for pure microMIPS cores to dynamically determine the ASID size at boot time. Includes bug fix https://patchwork.linux-mips.org/patch/5230/ Signed-off-by: Steven J. Hill <Steven.Hill@imgtec.com> Signed-off-by: Jonas Gorski <jogo@openwrt.org>
| * MIPS: Allow ASID size to be determined at boot time.Steven J. Hill2013-05-081-0/+49
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Original patch by Ralf Baechle and removed by Harold Koerfgen with commit f67e4ffc79905482c3b9b8c8dd65197bac7eb508. This allows for more generic kernels since the size of the ASID and corresponding masks can be determined at run-time. This patch is also required for the new Aptiv cores and has been tested on Malta and Malta Aptiv platforms. [ralf@linux-mips.org: Added relevant part of fix https://patchwork.linux-mips.org/patch/5213/] Signed-off-by: Steven J. Hill <Steven.Hill@imgtec.com> Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
* | Merge branch 'mips-next-3.10' of ↵Ralf Baechle2013-05-081-2/+8
|\ \ | | | | | | | | | git://git.linux-mips.org/pub/scm/john/linux-john into mips-for-linux-next
| * | MIPS: Build uasm-generated code only once to avoid CPU Hotplug problemHuacai Chen2013-05-081-2/+8
| |/ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This and the next patch resolve memory corruption problems while CPU hotplug. Without these patches, memory corruption can triggered easily as below: On a quad-core MIPS platform, use "spawn" of UnixBench-5.1.3 (http:// code.google.com/p/byte-unixbench/) and a CPU hotplug script like this (hotplug.sh): while true; do echo 0 >/sys/devices/system/cpu/cpu1/online echo 0 >/sys/devices/system/cpu/cpu2/online echo 0 >/sys/devices/system/cpu/cpu3/online sleep 1 echo 1 >/sys/devices/system/cpu/cpu1/online echo 1 >/sys/devices/system/cpu/cpu2/online echo 1 >/sys/devices/system/cpu/cpu3/online sleep 1 done Run "hotplug.sh" and then run "spawn 10000", spawn will get segfault after a few minutes. This patch: Currently, clear_page()/copy_page() are generated by Micro-assembler dynamically. But they are unavailable until uasm_resolve_relocs() has finished because jump labels are illegal before that. Since these functions are shared by every CPU, we only call build_clear_page()/ build_copy_page() only once at boot time. Without this patch, programs will get random memory corruption (segmentation fault, bus error, etc.) while CPU Hotplug (e.g. one CPU is using clear_page() while another is generating it in cpu_cache_init()). For similar reasons we modify build_tlb_refill_handler()'s invocation. V2: 1, Rework the code to make CPU#0 can be online/offline. 2, Introduce cpu_has_local_ebase feature since some types of MIPS CPU need a per-CPU tlb_refill_handler(). Signed-off-by: Huacai Chen <chenhc@lemote.com> Signed-off-by: Hongbing Hu <huhb@lemote.com> Acked-by: David Daney <david.daney@cavium.com> Patchwork: http://patchwork.linux-mips.org/patch/4994/ Acked-by: John Crispin <blogic@openwrt.org>
* | MIPS: Make declarations and definitions of tlbmiss_handler_setup_pgd match.Ralf Baechle2013-04-111-11/+11
|/ | | | | | | | | tlbmiss_handler_setup_pgd is run-time generated code and it was convenient to pretend the symbol was an array in the generator but a function for the users. LTO gcc won't tolerate this kind of lie anymore so solve the problem through a cast and function pointer instead. Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
* Merge branch 'mips-next-3.9' of ↵Ralf Baechle2013-02-211-0/+1
|\ | | | | | | git://git.linux-mips.org/pub/scm/john/linux-john into mips-for-linux-next
| * MIPS: Add support for the M14KEc core.Steven J. Hill2013-02-171-0/+1
| | | | | | | | | | | | Signed-off-by: Steven J. Hill <sjhill@mips.com> Patchwork: http://patchwork.linux-mips.org/patch/4682/ Signed-off-by: John Crispin <blogic@openwrt.org>
* | MIPS: Whitespace cleanup.Ralf Baechle2013-02-011-16/+16
|/ | | | | | | | Having received another series of whitespace patches I decided to do this once and for all rather than dealing with this kind of patches trickling in forever. Signed-off-by: Ralf Baechle <ralf@linux-mips.org>
* Revert "MIPS: Optimise TLB handlers for MIPS32/64 R2 cores."Ralf Baechle2012-12-271-16/+0
| | | | | | This reverts commit ff401e52100dcdc85e572d1ad376d3307b3fe28e. This breaks on MIPS64 R2 cores such as Broadcom's.
* Merge branch 'mips-next' of http://dev.phrozen.org/githttp/mips-next into ↵Ralf Baechle2012-12-131-2/+6
|\ | | | | | | mips-for-linux-next
| * MIPS: tlbex: Fix section mismatchesKevin Cernekee2012-11-091-2/+6
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The new functions introduced in commit 02a5417751 (MIPS: tlbex: Deal with re-definition of label) should be marked __cpuinit, to eliminate a warning that can pop up when CONFIG_EXPORT_UASM is disabled: LD arch/mips/mm/built-in.o WARNING: arch/mips/mm/built-in.o(.text+0x2a4c): Section mismatch in reference from the function uasm_bgezl_hazard() to the function .cpuinit.text:uasm_il_bgezl() The function uasm_bgezl_hazard() references the function __cpuinit uasm_il_bgezl(). This is often because uasm_bgezl_hazard lacks a __cpuinit annotation or the annotation of uasm_il_bgezl is wrong. WARNING: arch/mips/mm/built-in.o(.text+0x2a68): Section mismatch in reference from the function uasm_bgezl_label() to the function .cpuinit.text:uasm_build_label() The function uasm_bgezl_label() references the function __cpuinit uasm_build_label(). This is often because uasm_bgezl_label lacks a __cpuinit annotation or the annotation of uasm_build_label is wrong. (This warning might not occur if the function was inlined.) Signed-off-by: Kevin Cernekee <cernekee@gmail.com> Patchwork: http://patchwork.linux-mips.org/patch/4517 Signed-off-by: John Crispin <blogic@openwrt.org>
OpenPOWER on IntegriCloud