summaryrefslogtreecommitdiffstats
path: root/arch/powerpc/platforms (follow)
Commit message (Collapse)AuthorAgeFilesLines
* [POWERPC] Convert pci and eeh code to of_device_is_availableNathan Lynch2008-04-071-3/+2
| | | | | | | | A couple of places are duplicating the function of of_device_is_available; convert them to use it. Signed-off-by: Nathan Lynch <ntl@pobox.com> Signed-off-by: Paul Mackerras <paulus@samba.org>
* [POWERPC] 4xx: Use machine_device_initcall() for warp_nandValentine Barshak2008-04-051-1/+2
| | | | | | | | | | | | With a multiplatform kernel, once built we always have warp_setup_nand_flash() called and NDFC probed, no matter what machine we actually run on. This potentially can cause problems (such as kernel crash), since NDFC is probed at a warp-predefined address. Using machine_device_initcall() NAND devices are registered if we run on a warp only. Signed-off-by: Valentine Barshak <vbarshak@ru.mvista.com> Signed-off-by: Josh Boyer <jwboyer@linux.vnet.ibm.com>
* [POWERPC] 4xx: Create common ppc4xx_reset_system() in ppc4xx_soc.cStefan Roese2008-04-0317-43/+35
| | | | | | | | | | | | | | This patch creates a common system reset routine for all 40x and 44x systems. Previously only a 44x routine existed. But since this system reset via the debug control register is common for 40x and 44x let's share this code for all those platforms in ppc4xx_soc.c. This patch also enables CONFIG_4xx_SOC for all 40x and 44x platforms. Tested on Kilauea (405EX) and Canyonlands (440EX). Signed-off-by: Stefan Roese <sr@denx.de> Signed-off-by: Josh Boyer <jwboyer@linux.vnet.ibm.com>
* [POWERPC] Replace remaining __FUNCTION__ occurrencesHarvey Harrison2008-04-0114-42/+42
| | | | | | | | | __FUNCTION__ is gcc-specific, use __func__ Signed-off-by: Harvey Harrison <harvey.harrison@gmail.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Paul Mackerras <paulus@samba.org>
* [POWERPC] PS3: Split device setup for static vs. dynamic devicesGeert Uytterhoeven2008-04-011-32/+46
| | | | | | | | | | | | | | | Split the device setup code in ps3_register_repository_device() in two routines: 1. ps3_setup_static_device(), to handle the setup of static devices in the PS3 repository, which can be __init, 2. ps3_setup_dynamic_device(), to handle the setup of storage devices that may appear later in the PS3 repository. This fixes a few section mismatch warnings. Signed-off-by: Geert Uytterhoeven <Geert.Uytterhoeven@sonycom.com> Signed-off-by: Geoff Levand <geoffrey.levand@am.sony.com> Signed-off-by: Paul Mackerras <paulus@samba.org>
* [POWERPC] PS3: Save power in busy loops on haltGeert Uytterhoeven2008-04-011-1/+11
| | | | | | | | | | | | PS3 save power on halt: - Replace infinite busy loops by smarter loops calling lv1_pause() to save power. - Add ps3_halt() and ps3_sys_manager_halt(). - Add __noreturn annotations. Signed-off-by: Geert Uytterhoeven <Geert.Uytterhoeven@sonycom.com> Signed-off-by: Geoff Levand <geoffrey.levand@am.sony.com> Signed-off-by: Paul Mackerras <paulus@samba.org>
* [POWERPC] PS3: Add ps3_get_speid routineTakashi Yamamoto2008-04-011-0/+7
| | | | | | | | | Add a new routine ps3_get_speid() which returns the logical SPE ID. This ID is needed for profiling support. Signed-off-by: Takashi Yamamoto <TakashiA.Yamamoto@jp.sony.com> Signed-off-by: Geoff Levand <geoffrey.levand@am.sony.com> Signed-off-by: Paul Mackerras <paulus@samba.org>
* [POWERPC] PS3: Fix unlikely typo in ps3_get_irqRoel Kluin2008-04-011-1/+1
| | | | | | | | | Fix a typo bug 'unlikely(x) == y' and add an unlikely() call to an unlikely code path in the PS3 interrupt routine ps3_get_irq(). Signed-off-by: Roel Kluin <12o3l@tiscali.nl> Signed-off-by: Geoff Levand <geoffrey.levand@am.sony.com> Signed-off-by: Paul Mackerras <paulus@samba.org>
* Merge branch 'powerpc-next' of ↵Paul Mackerras2008-04-013-0/+265
|\ | | | | | | master.kernel.org:/pub/scm/linux/kernel/git/galak/powerpc
| * [POWERPC] 85xx: Emerson KSI8560 base supportAlexandr Smirnov2008-03-263-0/+265
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The KSI8560 is a single compact, mid-, or full-size Advanced Mezzanine Card (AdvancedMC™) based on the Freescale™ Semiconductor MPC8560 PowerQUICC III™ microprocessor. This product will serve in data and signaling applications such as signaling gateways (SGW) and softswitch signaling interface cards. The board has altera maxii CPLD, that is used to obtain and manage board configuration. Also there are two SCC UART serial consoles and FCC ethernet, that is routed to the front panel, while other ethernet controlers (TSEC's) are routed to the backplane. Signed-off-by: Alexandr Smirnov <asmirnov@ru.mvista.com> Signed-off-by: Kumar Gala <galak@kernel.crashing.org>
* | [POWERPC] 4xx: Add PPC4xx L2-cache support (440GX)Stefan Roese2008-03-261-0/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This patch adds support for the 256k L2 cache found on some IBM/AMCC 4xx PPC's. It introduces a common 4xx SoC file (sysdev/ppc4xx_soc.c) which currently "only" adds the L2 cache init code. Other common 4xx stuff can be added later here. The L2 cache handling code is a copy of Eugene's code in arch/ppc with small modifications. Tested on AMCC Taishan 440GX. Signed-off-by: Stefan Roese <sr@denx.de> Signed-off-by: Josh Boyer <jwboyer@linux.vnet.ibm.com>
* | [POWERPC] 4xx: Add platform support for the AMCC Yosemite boardJosh Boyer2008-03-262-0/+10
| | | | | | | | | | | | | | | | The AMCC 440EP Yosemite board is very similar to the original AMCC Bamboo board. This adds a YOSEMITE option to Kconfig, and reuses the existing bamboo board support in the kernel. Signed-off-by: Josh Boyer <jwboyer@linux.vnet.ibm.com>
* | [POWERPC] 4xx: Add AMCC Canyonlands 460EX eval board support to platforms/44xStefan Roese2008-03-263-0/+83
|/ | | | | | | | | | | | | Canyonlands is the AMCC 460EX eval board, featuring nearly all of the 460EX interfaces: - 1 * PCI (max 66MHz), 2 * PCIe (one 4-lane, one 1-lane) - 2 * GBit Ethernet with TCP/IP acceleration - USB 2.0 Host/Device OTG and Host interface - SATA port Signed-off-by: Stefan Roese <sr@denx.de> Signed-off-by: Josh Boyer <jwboyer@linux.vnet.ibm.com>
* Merge branch 'linux-2.6'Paul Mackerras2008-03-252-16/+61
|\
| * [POWERPC] Hide resources on Axon PCIE root complex nodesMichael Ellerman2008-03-201-0/+36
| | | | | | | | | | | | | | | | | | | | | | The PCI bridge representing the PCIE root complex on Axon, contains device BARs for a memory range and ROM that define inbound accesses. This confuses the kernel resource management code -- the resources need to be hidden when Axon is a host bridge. Signed-off-by: Michael Ellerman <michael@ellerman.id.au> Acked-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Paul Mackerras <paulus@samba.org>
| * [POWERPC] Fix cell IOMMU code to cope with empty dma-ranges and non-PCI devicesMichael Ellerman2008-03-201-16/+25
| | | | | | | | | | | | | | | | | | | | | | | | | | | | The cell IOMMU code to parse the dma-ranges properties, used for the fixed mapping, was broken in two ways for some devices. Firstly it didn't cope with empty dma-ranges properties. An empty property implies no translation so can be safely skipped. The code also wrongly assumed it would be looking at PCI devices, and hard coded the number of address and size cells. Signed-off-by: Michael Ellerman <michael@ellerman.id.au> Signed-off-by: Paul Mackerras <paulus@samba.org>
* | [POWERPC] scanlog_init cleanup and minor fixesNathan Lynch2008-03-251-19/+18
| | | | | | | | | | | | | | | | | | | | | | | | | | | | scanlog_init() could use some love. * properly return -ENODEV if this system doesn't support scan-log-dump * don't printk if scan-log-dump not present; only older systems have it * convert from create_proc_entry() to preferred proc_create() * allocate zeroed data buffer * fix potential memory leak of ent->data on failed create_proc_entry() * simplify control flow Signed-off-by: Nathan Lynch <ntl@pobox.com> Signed-off-by: Paul Mackerras <paulus@samba.org>
* | [POWERPC] pseries: phyp dump: Inform kdump when phyp-dump is loadedManish Ahuja2008-03-251-0/+18
| | | | | | | | | | | | | | | | | | This adds /sys/kernel/phyp_dump_active so that kdump init scripts may look for it and take appropriate action if this file is found. This file is only created when phyp_dump has been registered. Signed-off-by: Manish Ahuja <mahuja@us.ibm.com> Signed-off-by: Paul Mackerras <paulus@samba.org>
* | [POWERPC] pseries: phyp dump: Disable phyp-dump through boot-varManish Ahuja2008-03-251-0/+18
| | | | | | | | | | | | | | | | | | | | | | This adds a kernel command line option "phyp_dump", which takes a 0/1 value for disabling/ enabling phyp_dump at boot time. Kdump can use this on cmdline (phyp_dump=0) to disable phyp-dump during boot when enabling itself. This will ensure only one dumping mechanism is active at any given time. Signed-off-by: Manish Ahuja <mahuja@us.ibm.com> Signed-off-by: Paul Mackerras <paulus@samba.org>
* | [POWERPC] pseries: phyp dump: Tracking memory range freedManish Ahuja2008-03-251-0/+35
| | | | | | | | | | | | | | | | | | This tracks the size freed. For now it does a simple rudimentary calculation of the ranges freed. The idea is to keep it simple at the external shell script level and send in large chunks for now. Signed-off-by: Manish Ahuja <mahuja@us.ibm.com> Signed-off-by: Paul Mackerras <paulus@samba.org>
* | [POWERPC] pseries: phyp dump: Invalidate and print dump areasManish Ahuja2008-03-251-6/+77
| | | | | | | | | | | | | | | | | | | | | | | | This adds routines to a. invalidate dump b. calculate region that is reserved and needs to be freed. This is exported through sysfs interface. Unregister has been removed for now as it wasn't being used. Signed-off-by: Manish Ahuja <mahuja@us.ibm.com> Signed-off-by: Paul Mackerras <paulus@samba.org>
* | [POWERPC] pseries: phyp dump: Debugging print routinesManish Ahuja2008-03-251-2/+59
| | | | | | | | | | | | | | | | Provide some basic debugging support. Signed-off-by: Manish Ahuja <mahuja@us.ibm.com> Signed-off-by: Linas Vepstas <linasvepstas@gmail.com> Signed-off-by: Paul Mackerras <paulus@samba.org>
* | [POWERPC] pseries: phyp dump: Register dump areaManish Ahuja2008-03-251-6/+131
| | | | | | | | | | | | | | | | Set up the actual dump header, register it with the hypervisor. Signed-off-by: Manish Ahuja <mahuja@us.ibm.com> Signed-off-by: Linas Vepstas <linasvepstas@gmail.com> Signed-off-by: Paul Mackerras <paulus@samba.org>
* | [POWERPC] pseries: phyp dump: Use sysfs to release reserved memManish Ahuja2008-03-251-5/+76
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Check to see if there actually is data from a previously crashed kernel waiting. If so, allow user-space tools to grab the data (by reading /proc/kcore). When user-space finishes dumping a section, it must release that memory by writing to sysfs. For example, echo "0x40000000 0x10000000" > /sys/kernel/release_region will release 256MB starting at the 1GB. The released memory becomes free for general use. Signed-off-by: Linas Vepstas <linasvepstas@gmail.com> Signed-off-by: Manish Ahuja <mahuja@us.ibm.com> Signed-off-by: Paul Mackerras <paulus@samba.org>
* | [POWERPC] pseries: phyp dump: Reserve and release memoryManish Ahuja2008-03-252-0/+104
| | | | | | | | | | | | | | | | | | | | Initial patch for reserving memory in early boot, and freeing it later. If the previous boot had ended with a crash, the reserved memory would contain a copy of the crashed kernel data. Signed-off-by: Manish Ahuja <mahuja@us.ibm.com> Signed-off-by: Linas Vepstas <linasvepstas@gmail.com> Signed-off-by: Paul Mackerras <paulus@samba.org>
* | [POWERPC] arch/powerpc/platforms/iseries/pci.c: Use time_* macrosS.Çağlar Onur2008-03-251-1/+2
| | | | | | | | | | | | | | | | | | | | | | | | | | The functions time_before, time_before_eq, time_after, and time_after_eq are more robust for comparing jiffies against other values. This implements usage of the time_after() macro, defined at linux/jiffies.h, which deals with wrapping correctly. Signed-off-by: S.Çağlar Onur <caglar@pardus.org.tr> Acked-by: Stephen Rothwell <sfr@canb.auug.org.au> Signed-off-by: Paul Mackerras <paulus@samba.org>
* | [POWERPC] Update wait_state_cycles in the VPATony Breeds2008-03-251-0/+4
| | | | | | | | | | | | | | | | | | | | | | | | The hypervisor can look at the value in the wait_state_cycles field of the VPA for an estimate of how busy dedicated processors are. Currently, as the kernel never touches this field, we appear to be 100% busy. This records the duration the kernel is in powersave and passes that to the HV to provide a reasonable indication of utilisation. Signed-off-by: Tony Breeds <tony@bakeyournoodle.com> Signed-off-by: Paul Mackerras <paulus@samba.org>
* | [POWERPC] maple: Kill fixup_maple_ideNathan Lynch2008-03-251-47/+0
| | | | | | | | | | | | | | | | This function has been a no-op for about 18 months; it's there in the history should anyone need to resurrect it. Signed-off-by: Nathan Lynch <ntl@pobox.com> Signed-off-by: Paul Mackerras <paulus@samba.org>
* | [POWERPC] maple: Use platform name in define_machine()Nathan Lynch2008-03-251-1/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Prevailing practice for define_machine() in powerpc is to use the platform name when the platform has only one define_machine() statement, but maple uses "maple_md". This caused me some head-scratching when writing some new code that uses machine_is(maple). Use "maple" instead of "maple_md". There should not be any behavioral change -- fixup_maple_ide() calls machine_is(maple) but the body of the function is ifdef'd out. Signed-off-by: Nathan Lynch <ntl@pobox.com> Signed-off-by: Paul Mackerras <paulus@samba.org>
* | Merge branch 'linux-2.6'Paul Mackerras2008-03-1316-90/+151
|\|
| * [POWERPC] Fix arch/powerpc/platforms/powermac/pic.c when !CONFIG_ADB_PMUTony Breeds2008-03-131-1/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | When building arch/powerpc/platforms/powermac/pic.c when !CONFIG_ADB_PMU we get the following warnings: arch/powerpc/platforms/powermac/pic.c: In function 'pmacpic_find_viaint': arch/powerpc/platforms/powermac/pic.c:623: warning: label 'not_found' defined but not used This fixes it. Signed-off-by: Tony Breeds <tony@bakeyournoodle.com> Signed-off-by: Paul Mackerras <paulus@samba.org>
| * Merge branch 'master' of ↵Paul Mackerras2008-03-124-4/+7
| |\ | | | | | | | | | git://git.kernel.org/pub/scm/linux/kernel/git/jk/spufs into merge
| | * [POWERPC] spufs: fix rescheduling of non-runnable contextsJeremy Kerr2008-03-111-1/+2
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | At present, we can hit the BUG_ON in __spu_update_sched_info by reading the regs file of a context between two calls to spu_run. The spu_release_saved called by spufs_regs_read() is resulting in the (now non-runnable) context being placed back on the run queue, so the next call to spu_run ends up in the bug condition. This change uses the SPU_SCHED_SPU_RUN flag to only reschedule a context if it's still in spu_run(). Signed-off-by: Jeremy Kerr <jk@ozlabs.org>
| | * [POWERPC] spufs: don't (ab)use SCHED_IDLEJeremy Kerr2008-03-113-3/+5
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | commit 4ef11014 introduced a usage of SCHED_IDLE to detect when a context is within spu_run. Instead of SCHED_IDLE (which has other meaning), add a flag to sched_flags to tell if a context should be running. Signed-off-by: Jeremy Kerr <jk@ozlabs.org>
| * | [POWERPC] 83xx: Make 83xx perfmon support selectableAndy Fleming2008-03-102-2/+6
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Not all e300 cores support the performance monitors, and the ones that don't will be confused by the mf/mtpmr instructions. This allows the support to be optional, so the 8349 can turn it off while the 8379 can turn it on. Sadly, those aren't config options, so it will be left to the defconfigs and the users to make that determination. Signed-off-by: Andy Fleming <afleming@freescale.com> Signed-off-by: Kumar Gala <galak@kernel.crashing.org>
| * | [POWERPC] 83xx: Add local bus device nodes to MPC837xMDS device trees.Li Yang2008-03-071-5/+3
| |/ | | | | | | | | Signed-off-by: Li Yang <leoli@freescale.com> Signed-off-by: Kumar Gala <galak@kernel.crashing.org>
| * Merge branch 'for-2.6.25' of ↵Paul Mackerras2008-03-033-66/+95
| |\ | | | | | | | | | master.kernel.org:/pub/scm/linux/kernel/git/arnd/cell-2.6 into merge
| | * [POWERPC] Convert the cell IOMMU fixed mapping to 16M IOMMU pagesMichael Ellerman2008-03-031-15/+22
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The only tricky part is we need to adjust the PTE insertion loop to cater for holes in the page table. The PTEs for each segment start on a 4K boundary, so with 16M pages we have 16 PTEs per segment and then a gap to the next 4K page boundary. It might be possible to allocate the PTEs for each segment separately, saving the memory currently filling the gaps. However we'd need to check that's OK with the hardware, and that it actually saves memory. Signed-off-by: Michael Ellerman <michael@ellerman.id.au> Signed-off-by: Arnd Bergmann <arnd@arndb.de>
| | * [POWERPC] Allow for different IOMMU page sizes in cell IOMMU codeMichael Ellerman2008-03-031-13/+18
| | | | | | | | | | | | | | | | | | | | | | | | Make some preliminary changes to cell_iommu_alloc_ptab() to allow it to take the page size as a parameter rather than assuming IOMMU_PAGE_SIZE. Signed-off-by: Michael Ellerman <michael@ellerman.id.au> Signed-off-by: Arnd Bergmann <arnd@arndb.de>
| | * [POWERPC] Cell IOMMU: n_pte_pages is in 4K page units, not IOMMU_PAGE_SIZEMichael Ellerman2008-03-031-5/+4
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | We use n_pte_pages to calculate the stride through the page tables, but we also use it to set the NPPT value in the segment table entry. That is defined as the number of 4K pages per segment, so we should calculate it as such regardless of the IOMMU page size. Signed-off-by: Michael Ellerman <michael@ellerman.id.au> Signed-off-by: Arnd Bergmann <arnd@arndb.de>
| | * [POWERPC] Split setup of IOMMU stab and ptab, allocate dynamic/fixed ptabs ↵Michael Ellerman2008-03-031-26/+43
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | separately Currently the cell IOMMU code allocates the entire IOMMU page table in a contiguous chunk. This is nice and tidy, but for machines with larger amounts of RAM the page table allocation can fail due to it simply being too large. So split the segment table and page table setup routine, and arrange to have the dynamic and fixed page tables allocated separately. Signed-off-by: Michael Ellerman <michael@ellerman.id.au> Signed-off-by: Arnd Bergmann <arnd@arndb.de>
| | * [POWERPC] Move allocation of cell IOMMU pad pageMichael Ellerman2008-03-031-6/+6
| | | | | | | | | | | | | | | | | | | | | | | | There's no need to allocate the pad page unless we're going to actually use it - so move the allocation to where we know we're going to use it. Signed-off-by: Michael Ellerman <michael@ellerman.id.au> Signed-off-by: Arnd Bergmann <arnd@arndb.de>
| | * [POWERPC] Remove unused pte_offset variableMichael Ellerman2008-03-031-4/+1
| | | | | | | | | | | | | | | | | | | | | | | | The cell IOMMU code no longer needs to save the pte_offset variable separately, it is incorporated into tbl->it_offset. Signed-off-by: Michael Ellerman <michael@ellerman.id.au> Signed-off-by: Arnd Bergmann <arnd@arndb.de>
| | * [POWERPC] Use it_offset not pte_offset in cell IOMMU codeMichael Ellerman2008-03-031-2/+2
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The cell IOMMU tce build and free routines use pte_offset to convert the index passed from the generic IOMMU code into a page table offset. This takes into account the SPIDER_DMA_OFFSET which sets the top bit of every DMA address. However it doesn't cater for the IOMMU window starting at a non-zero address, as the base of the window is not incorporated into pte_offset at all. As it turns out tbl->it_offset already contains the value we need, it takes into account the base of the window and also pte_offset. So use it instead! Signed-off-by: Michael Ellerman <michael@ellerman.id.au> Signed-off-by: Arnd Bergmann <arnd@arndb.de>
| | * [POWERPC] Clearup cell IOMMU fixed mapping terminologyMichael Ellerman2008-03-031-4/+4
| | | | | | | | | | | | | | | | | | | | | It's called the fixed mapping, not the static mapping. Signed-off-by: Michael Ellerman <michael@ellerman.id.au> Signed-off-by: Arnd Bergmann <arnd@arndb.de>
| | * [POWERPC] enable hardware watchpoints on cell bladesJens Osterkamp2008-03-031-0/+7
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Ulrich Weigand has found that the hardware watchpoints on cell were not working back in November : http://ozlabs.org/pipermail/linuxppc-dev/2007-November/046135.html This patch sets them during initialization. Signed-off-by: Jens Osterkamp <jens@de.ibm.com> Signed-off-by: Arnd Bergmann <arnd@arndb.de>
| | * [POWERPC] move celleb DABRX definitionsJens Osterkamp2008-03-031-3/+0
| | | | | | | | | | | | | | | | | | | | | | | | This moves the private DABRX definitions for celleb from beat.h to reg.h to make them usable for all. Signed-off-by: Jens Osterkamp <jens@de.ibm.com> Signed-off-by: Arnd Bergmann <arnd@arndb.de>
| * | Merge branch 'master' of ↵Paul Mackerras2008-03-036-12/+38
| |\ \ | | | | | | | | | | | | git://git.kernel.org/pub/scm/linux/kernel/git/jk/spufs into merge
| | * | [POWERPC] spufs: fix use time accounting on SPE-overcommitAndre Detsch2008-02-291-1/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The spu_runcntl_RW register is restored within spu_restore function. So, at the end of spu_bind_context, the SPU context is not just loaded, but running. This change corrects the state switch to account the time as USER. Signed-off-by: Andre Detsch <adetsch@br.ibm.com> Signed-off-by: Jeremy Kerr <jk@ozlabs.org>
| | * | [POWERPC] spufs: serialize SLB invalidation against SLB loadingArnd Bergmann2008-02-291-3/+9
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | There is a potential race between flushes of the entire SLB in the MFC and the point where new entries are being established. The problem is that we might put a ESID entry into the MFC SLB when the VSID entry has just been cleared by the global flush. This can be circumvented by holding the register_lock throughout both the flushing and the creation of SLB entries. Signed-off-by: Arnd Bergmann <arnd@arndb.de> Signed-off-by: Jeremy Kerr <jk@ozlabs.org>
generated by cgit v1.2.3 (git 2.39.1) at 2025-01-05 01:55:22 +0100