- 14 Apr, 2021 40 commits
-
-
Nicholas Piggin authored
64e non-maskable interrupts save the state of the irq soft-mask in asm. This can be done in C in interrupt wrappers as 64s does. I haven't been able to test this with qemu because it doesn't seem to cause FSL bookE WDT interrupts. This makes WatchdogException an NMI interrupt, which affects 32-bit as well (okay, or create a new handler?) Signed-off-by:
Nicholas Piggin <npiggin@gmail.com> Signed-off-by:
Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/20210316104206.407354-6-npiggin@gmail.com
-
Nicholas Piggin authored
Update the new C and asm interrupt return code to account for 64e specifics, switch over to use it. The now-unused old ret_from_except code, that was moved to 64e after the 64s conversion, is removed. Signed-off-by:
-
Nicholas Piggin authored
This makes adjustments to 64-bit asm and common C interrupt return code to be usable by the 64e subarchitecture. Signed-off-by:
-
Nicholas Piggin authored
In order to use the C interrupt return, nvgprs must always be saved. Signed-off-by:
-
Nicholas Piggin authored
user_exit_irqoff() -> __context_tracking_exit -> vtime_user_exit warns in __seqprop_assert due to lockdep thinking preemption is enabled because trace_hardirqs_off() has not yet been called. Switch the order of these two calls, which matches their ordering in interrupt_enter_prepare. Fixes: 5f0b6ac3 ("powerpc/64/syscall: Reconcile interrupts") Signed-off-by:
-
Madhavan Srinivasan authored
Introduce code to support the checking of attr.config* for values which are reserved for a given platform. Performance Monitoring Unit (PMU) configuration registers have fields that are reserved and some specific values for bit fields are reserved. For ex., MMCRA[61:62] is Random Sampling Mode (SM) and value of 0b11 for this field is reserved. Writing non-zero or invalid values in these fields will have unknown behaviours. Patch adds a generic call-back function "check_attr_config" in "struct power_pmu", to be called in event_init to check for attr.config* values for a given platform. Signed-off-by:
Madhavan Srinivasan <maddy@linux.ibm.com> Signed-off-by:
-
Pu Lehui authored
Fix sparse warnings: arch/powerpc/platforms/pseries/rtas-fadump.c:250:6: warning: symbol 'rtas_fadump_set_regval' was not declared. Should it be static? Signed-off-by:
Pu Lehui <pulehui@huawei.com> Signed-off-by:
-
Christophe Leroy authored
Flushing functions don't rely on preemption being disabled, so use kmap_local_page() instead of kmap_atomic(). Signed-off-by:
Christophe Leroy <christophe.leroy@csgroup.eu> Signed-off-by:
-
Christophe Leroy authored
flush_dcache_page() is only a few lines, it is worth inlining. ia64, csky, mips, openrisc and riscv have a similar flush_dcache_page() and inline it. On pmac32_defconfig, we get a small size reduction. On ppc64_defconfig, we get a very small size increase. In both case that's in the noise (less than 0.1%). text data bss dec hex filename 18991155 5934744 1497624f 26423523 19330e3 vmlinux64.before 18994829 5936732 1497624f 26429185 1934701 vmlinux64.after 9150963 2467502 184548 11803013 b41985 vmlinux32.before 9149689 2467302 184548 11801539 b413c3 vmlinux32.after Signed-off-by:
-
Christophe Leroy authored
'And' the given page address with PAGE_MASK to help GCC. With the patch: 00000024 <__flush_dcache_icache>: 24: 54 63 00 26 rlwinm r3,r3,0,0,19 28: 39 40 00 40 li r10,64 2c: 7c 69 1b 78 mr r9,r3 30: 7d 49 03 a6 mtctr r10 34: 7c 00 48 6c dcbst 0,r9 38: 39 29 00 20 addi r9,r9,32 3c: 7c 00 48 6c dcbst 0,r9 40: 39 29 00 20 addi r9,r9,32 44: 42 00 ff f0 bdnz 34 <__flush_dcache_icache+0x10> 48: 7c 00 04 ac hwsync 4c: 39 20 00 40 li r9,64 50: 7d 29 03 a6 mtctr r9 54: 7c 00 1f ac icbi 0,r3 58: 38 63 00 20 addi r3,r3,32 5c: 7c 00 1f ac icbi 0,r3 60: 38 63 00 20 addi r3,r3,32 64: 42 00 ff f0 bdnz 54 <__flush_dcache_icache+0x30> 68: 7c 00 04 ac hwsync 6c: 4c 00 01 2c isync 70: 4e 80 00 20 blr Without the patch: 00000024 <__flush_dcache_icache>: 24: 54 6a 00 34 rlwinm r10,r3,0,0,26 28: 39 23 10 1f addi r9,r3,4127 2c: 7d 2a 48 50 subf r9,r10,r9 30: 55 29 d9 7f rlwinm. r9,r9,27,5,31 34: 41 82 00 94 beq c8 <__flush_dcache_icache+0xa4> 38: 71 28 00 01 andi. r8,r9,1 3c: 38 c9 ff ff addi r6,r9,-1 40: 7d 48 53 78 mr r8,r10 44: 7d 27 4b 78 mr r7,r9 48: 40 82 00 6c bne b4 <__flush_dcache_icache+0x90> 4c: 54 e7 f8 7e rlwinm r7,r7,31,1,31 50: 7c e9 03 a6 mtctr r7 54: 7c 00 40 6c dcbst 0,r8 58: 39 08 00 20 addi r8,r8,32 5c: 7c 00 40 6c dcbst 0,r8 60: 39 08 00 20 addi r8,r8,32 64: 42 00 ff f0 bdnz 54 <__flush_dcache_icache+0x30> 68: 7c 00 04 ac hwsync 6c: 71 28 00 01 andi. r8,r9,1 70: 39 09 ff ff addi r8,r9,-1 74: 40 82 00 2c bne a0 <__flush_dcache_icache+0x7c> 78: 55 29 f8 7e rlwinm r9,r9,31,1,31 7c: 7d 29 03 a6 mtctr r9 80: 7c 00 57 ac icbi 0,r10 84: 39 4a 00 20 addi r10,r10,32 88: 7c 00 57 ac icbi 0,r10 8c: 39 4a 00 20 addi r10,r10,32 90: 42 00 ff f0 bdnz 80 <__flush_dcache_icache+0x5c> 94: 7c 00 04 ac hwsync 98: 4c 00 01 2c isync 9c: 4e 80 00 20 blr a0: 7c 00 57 ac icbi 0,r10 a4: 2c 08 00 00 cmpwi r8,0 a8: 39 4a 00 20 addi r10,r10,32 ac: 40 82 ff cc bne 78 <__flush_dcache_icache+0x54> b0: 4b ff ff e4 b 94 <__flush_dcache_icache+0x70> b4: 7c 00 50 6c dcbst 0,r10 b8: 2c 06 00 00 cmpwi r6,0 bc: 39 0a 00 20 addi r8,r10,32 c0: 40 82 ff 8c bne 4c <__flush_dcache_icache+0x28> c4: 4b ff ff a4 b 68 <__flush_dcache_icache+0x44> c8: 7c 00 04 ac hwsync cc: 7c 00 04 ac hwsync d0: 4c 00 01 2c isync d4: 4e 80 00 20 blr Signed-off-by:
-
Christophe Leroy authored
__flush_dcache_icache() is usable for non HIGHMEM pages on every platform. It is only for HIGHMEM pages that BOOKE needs kmap() and BOOK3S needs flush_dcache_icache_phys(). So make flush_dcache_icache_phys() dependent on CONFIG_HIGHMEM and call it only when it is a HIGHMEM page. We could make flush_dcache_icache_phys() available at all time, but as it is declared NOKPROBE_SYMBOL(), GCC doesn't optimise it out when it is not used. So define a stub for !CONFIG_HIGHMEM in order to remove the #ifdef in flush_dcache_icache_page() and use IS_ENABLED() instead. Signed-off-by:
-
Christophe Leroy authored
flush_dcache_icache_hugepage() is a static function, with only one caller. That caller calls it when PageCompound() is true, so bugging on !PageCompound() is useless if we can trust the compiler a little. Remove the BUG_ON(!PageCompound()). The number of elements of a page won't change over time, but GCC doesn't know about it, so it gets the value at every iteration. To avoid that, call compound_nr() outside the loop and save it in a local variable. Whether the page is a HIGHMEM page or not doesn't change over time. But GCC doesn't know it so it does the test on every iteration. Do the test outside the loop. When the page is not a HIGHMEM page, page_address() will fallback on lowmem_page_address(), so call lowmem_page_address() directly and don't suffer the call to page_address() on every iteration. Signed-off-by:
-
Christophe Leroy authored
flush_coherent_icache() doesn't need the address anymore, so it can be called immediately when entering the public functions and doesn't need to be disseminated among lower level functions. And use page_to_phys() instead of open coding the calculation of phys address to call flush_dcache_icache_phys(). Signed-off-by:
-
Christophe Leroy authored
flush_coherent_icache() can use any valid address as mentionned by the comment. Use PAGE_OFFSET as base address. This allows removing the user access stuff. Signed-off-by:
-
Christophe Leroy authored
__flush_dcache_icache() is only used in mem.c. Move it before the functions that use it and declare it static. And also fix the name of the parameter in the comment. Signed-off-by:
-
Christophe Leroy authored
Cache flushing functions are in the middle of completely unrelated stuff in mm/mem.c Create a dedicated mm/cacheflush.c for those functions. Also cleanup the list of included headers. Signed-off-by:
-
Bixuan Cui authored
The sparse tool complains as follows: arch/powerpc/platforms/powernv/opal-core.c:74:16: warning: symbol 'mpipl_kobj' was not declared. This symbol is not used outside of opal-core.c, so marks it static. Reported-by:
Hulk Robot <hulkci@huawei.com> Signed-off-by:
Bixuan Cui <cuibixuan@huawei.com> Signed-off-by:
-
Pu Lehui authored
Fix sparse warning: arch/powerpc/xmon/xmon.c:4216:1: warning: symbol 'spu_inst_dump' was not declared. Should it be static? This symbol is not used outside of xmon.c, so make it static. Signed-off-by:
-
Bixuan Cui authored
The sparse tool complains as follows: arch/powerpc/perf/hv-24x7.c:229:1: warning: symbol '__pcpu_scope_hv_24x7_txn_flags' was not declared. Should it be static? arch/powerpc/perf/hv-24x7.c:230:1: warning: symbol '__pcpu_scope_hv_24x7_txn_err' was not declared. Should it be static? arch/powerpc/perf/hv-24x7.c:236:1: warning: symbol '__pcpu_scope_hv_24x7_hw' was not declared. Should it be static? arch/powerpc/perf/hv-24x7.c:244:1: warning: symbol '__pcpu_scope_hv_24x7_reqb' was not declared. Should it be static? arch/powerpc/perf/hv-24x7.c:245:1: warning: symbol '__pcpu_scope_hv_24x7_resb' was not declared. Should it be static? This symbol is not used outside of hv-24x7.c, so this commit marks it static. Reported-by:
-
Bixuan Cui authored
The sparse tool complains as follows: arch/powerpc/perf/isa207-common.c:24:18: warning: symbol 'isa207_pmu_format_attr' was not declared. Should it be static? This symbol is not used outside of isa207-common.c, so this commit marks it static. Reported-by:
-
Bixuan Cui authored
The sparse tool complains as follows: arch/powerpc/platforms/pseries/pmem.c:142:27: warning: symbol 'drc_pmem_match' was not declared. Should it be static? This symbol is not used outside of pmem.c, so this commit marks it static. Reported-by:
-
Bixuan Cui authored
The sparse tool complains as follows: arch/powerpc/platforms/pseries/hvCall_inst.c:29:1: warning: symbol '__pcpu_scope_hcall_stats' was not declared. Should it be static? This symbol is not used outside of hvCall_inst.c, so this commit marks it static. Reported-by:
-
Leonardo Bras authored
According to LoPAR, ibm,query-pe-dma-window output named "IO Page Sizes" will let the OS know all possible pagesizes that can be used for creating a new DDW. Currently Linux will only try using 3 of the 8 available options: 4K, 64K and 16M. According to LoPAR, Hypervisor may also offer 32M, 64M, 128M, 256M and 16G. Enabling bigger pages would be interesting for direct mapping systems with a lot of RAM, while using less TCE entries. Signed-off-by:
Leonardo Bras <leobras.c@gmail.com> Signed-off-by:
-
Masahiro Yamada authored
Many architectures duplicate similar shell scripts. This commit converts powerpc to use scripts/syscallhdr.sh. Signed-off-by:
Masahiro Yamada <masahiroy@kernel.org> Signed-off-by:
-
Masahiro Yamada authored
Many architectures duplicate similar shell scripts. This commit converts powerpc to use scripts/syscalltbl.sh. This also unifies syscall_table_32.h and syscall_table_c32.h. Signed-off-by:
-
Nathan Lynch authored
RTAS_RMOBUF_MAX doesn't actually describe a "maximum" value in any sense. It represents the size of an area of memory set aside for user space to use as work areas for certain RTAS calls. Rename it to RTAS_USER_REGION_SIZE. Signed-off-by:
Nathan Lynch <nathanl@linux.ibm.com> Reviewed-by:
Andrew Donnellan <ajd@linux.ibm.com> Signed-off-by:
-
Nathan Lynch authored
Reduce conditionally compiled sections within rtas_initialize() by moving the filter table initialization into its own function already guarded by CONFIG_PPC_RTAS_FILTER. No behavior change intended. Signed-off-by:
Alexey Kardashevskiy <aik@ozlabs.ru> Acked-by:
-
Nathan Lynch authored
There's not a compelling reason to cache the value of the token for the ibm,suspend-me function. Just look it up when needed in the RTAS syscall's special case for it. Signed-off-by:
-
Nathan Lynch authored
This constant is unused. Signed-off-by:
-
Nathan Lynch authored
Add kerneldoc for ppc_rtas_rmo_buf_show(), the callback for /proc/powerpc/rtas/rmo_buffer, explaining its expected use. Signed-off-by:
-
Mahesh Salgaonkar authored
During the EEH MMIO error checking, the current implementation fails to map the (virtual) MMIO address back to the pci device on radix with hugepage mappings for I/O. This results into failure to dispatch EEH event with no recovery even when EEH capability has been enabled on the device. eeh_check_failure(token) # token = virtual MMIO address addr = eeh_token_to_phys(token); edev = eeh_addr_cache_get_dev(addr); if (!edev) return 0; eeh_dev_check_failure(edev); <= Dispatch the EEH event In case of hugepage mappings, eeh_token_to_phys() has a bug in virt -> phys translation that results in wrong physical address, which is then passed to eeh_addr_cache_get_dev() to match it against cached pci I/O address ranges to get to a PCI device. Hence, it fails to find a match and the EEH event never gets dispatched leaving the device in failed state. The commit 33439620 ("powerpc/eeh: Handle hugepages in ioremap space") introduced following logic to translate virt to phys for hugepage mappings: eeh_token_to_phys(): + pa = pte_pfn(*ptep); + + /* On radix we can do hugepage mappings for io, so handle that */ + if (hugepage_shift) { + pa <<= hugepage_shift; <= This is wrong + pa |= token & ((1ul << hugepage_shift) - 1); + } This patch fixes the virt -> phys translation in eeh_token_to_phys() function. $ cat /sys/kernel/debug/powerpc/eeh_address_cache mem addr range [0x0000040080000000-0x00000400807fffff]: 0030:01:00.1 mem addr range [0x0000040080800000-0x0000040080ffffff]: 0030:01:00.1 mem addr range [0x0000040081000000-0x00000400817fffff]: 0030:01:00.0 mem addr range [0x0000040081800000-0x0000040081ffffff]: 0030:01:00.0 mem addr range [0x0000040082000000-0x000004008207ffff]: 0030:01:00.1 mem addr range [0x0000040082080000-0x00000400820fffff]: 0030:01:00.0 mem addr range [0x0000040082100000-0x000004008210ffff]: 0030:01:00.1 mem addr range [0x0000040082110000-0x000004008211ffff]: 0030:01:00.0 Above is the list of cached io address ranges of pci 0030:01:00.<fn>. Before this patch: Tracing 'arg1' of function eeh_addr_cache_get_dev() during error injection clearly shows that 'addr=' contains wrong physical address: kworker/u16:0-7 [001] .... 108.883775: eeh_addr_cache_get_dev: (eeh_addr_cache_get_dev+0xc/0xf0) addr=0x80103000a510 dmesg shows no EEH recovery messages: [ 108.563768] bnx2x: [bnx2x_timer:5801(eth2)]MFW seems hanged: drv_pulse (0x9ae) != mcp_pulse (0x7fff) [ 108.563788] bnx2x: [bnx2x_hw_stats_update:870(eth2)]NIG timer max (4294967295) [ 108.883788] bnx2x: [bnx2x_acquire_hw_lock:2013(eth1)]lock_status 0xffffffff resource_bit 0x1 [ 108.884407] bnx2x 0030:01:00.0 eth1: MDC/MDIO access timeout [ 108.884976] bnx2x 0030:01:00.0 eth1: MDC/MDIO access timeout <..> After this patch: eeh_addr_cache_get_dev() trace shows correct physical address: <idle>-0 [001] ..s. 1043.123828: eeh_addr_cache_get_dev: (eeh_addr_cache_get_dev+0xc/0xf0) addr=0x40080bc7cd8 dmesg logs shows EEH recovery getting triggerred: [ 964.323980] bnx2x: [bnx2x_timer:5801(eth2)]MFW seems hanged: drv_pulse (0x746f) != mcp_pulse (0x7fff) [ 964.323991] EEH: Recovering PHB#30-PE#10000 [ 964.324002] EEH: PE location: N/A, PHB location: N/A [ 964.324006] EEH: Frozen PHB#30-PE#10000 detected <..> Fixes: 33439620 ("powerpc/eeh: Handle hugepages in ioremap space") Cc: stable@vger.kernel.org # v5.3+ Reported-by:
Dominic DeMarco <ddemarc@us.ibm.com> Signed-off-by:
Mahesh Salgaonkar <mahesh@linux.ibm.com> Signed-off-by:
Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com> Signed-off-by:
-
Cédric Le Goater authored
Instead of calling irq_create_mapping() to map the IPI for a node, introduce an 'alloc' handler. This is usually an extension to support hierarchy irq_domains which is not exactly the case for XIVE-IPI domain. However, we can now use the irq_domain_alloc_irqs() routine which allocates the IRQ descriptor on the specified node, even better for cache performance on multi node machines. Signed-off-by:
Cédric Le Goater <clg@kaod.org> Signed-off-by:
-
Cédric Le Goater authored
ipistorm [*] can be used to benchmark the raw interrupt rate of an interrupt controller by measuring the number of IPIs a system can sustain. When applied to the XIVE interrupt controller of POWER9 and POWER10 systems, a significant drop of the interrupt rate can be observed when crossing the second node boundary. This is due to the fact that a single IPI interrupt is used for all CPUs of the system. The structure is shared and the cache line updates impact greatly the traffic between nodes and the overall IPI performance. As a workaround, the impact can be reduced by deactivating the IRQ lockup detector ("noirqdebug") which does a lot of accounting in the Linux IRQ descriptor structure and is responsible for most of the performance penalty. As a fix, this proposal allocates an IPI interrupt per node, to be shared by all CPUs of that node. It solves the scaling issue, the IRQ lockup detector still has an impact but the XIVE interrupt rate scales linearly. It also improves the "noirqdebug" case as showed in the tables below. * P9 DD2.2 - 2s * 64 threads "noirqdebug" Mint/s Mint/s chips cpus IPI/sys IPI/chip IPI/chip IPI/sys -------------------------------------------------------------- 1 0-15 4.984023 4.875405 4.996536 5.048892 0-31 10.879164 10.544040 10.757632 11.037859 0-47 15.345301 14.688764 14.926520 15.310053 0-63 17.064907 17.066812 17.613416 17.874511 2 0-79 11.768764 21.650749 22.689120 22.566508 0-95 10.616812 26.878789 28.434703 28.320324 0-111 10.151693 31.397803 31.771773 32.388122 0-127 9.948502 33.139336 34.875716 35.224548 * P10 DD1 - 4s (not homogeneous) 352 threads "noirqdebug" Mint/s Mint/s chips cpus IPI/sys IPI/chip IPI/chip IPI/sys -------------------------------------------------------------- 1 0-15 2.409402 2.364108 2.383303 2.395091 0-31 6.028325 6.046075 6.089999 6.073750 0-47 8.655178 8.644531 8.712830 8.724702 0-63 11.629652 11.735953 12.088203 12.055979 0-79 14.392321 14.729959 14.986701 14.973073 0-95 12.604158 13.004034 17.528748 17.568095 2 0-111 9.767753 13.719831 19.968606 20.024218 0-127 6.744566 16.418854 22.898066 22.995110 0-143 6.005699 19.174421 25.425622 25.417541 0-159 5.649719 21.938836 27.952662 28.059603 0-175 5.441410 24.109484 31.133915 31.127996 3 0-191 5.318341 24.405322 33.999221 33.775354 0-207 5.191382 26.449769 36.050161 35.867307 0-223 5.102790 29.356943 39.544135 39.508169 0-239 5.035295 31.933051 42.135075 42.071975 0-255 4.969209 34.477367 44.655395 44.757074 4 0-271 4.907652 35.887016 47.080545 47.318537 0-287 4.839581 38.076137 50.464307 50.636219 0-303 4.786031 40.881319 53.478684 53.310759 0-319 4.743750 43.448424 56.388102 55.973969 0-335 4.709936 45.623532 59.400930 58.926857 0-351 4.681413 45.646151 62.035804 61.830057 [*] https://github.com/antonblanchard/ipistormSigned-off-by: -
Cédric Le Goater authored
When under xmon, the "dxi" command dumps the state of the XIVE interrupts. If an interrupt number is specified, only the state of the associated XIVE interrupt is dumped. This form of the command lacks an irq_data parameter which is nevertheless used by xmon_xive_get_irq_config(), leading to an xmon crash. Fix that by doing a lookup in the system IRQ mapping to query the IRQ descriptor data. Invalid interrupt numbers, or not belonging to the XIVE IRQ domain, OPAL event interrupt number for instance, should be caught by the previous query done at the firmware level. Fixes: 97ef2750 ("powerpc/xive: Fix xmon support on the PowerNV platform") Reported-by:
kernel test robot <lkp@intel.com> Reported-by:
Dan Carpenter <dan.carpenter@oracle.com> Signed-off-by:
Greg Kurz <groug@kaod.org> Reviewed-by:
-
Cédric Le Goater authored
Move the xmon routine under XIVE subsystem and rework the loop on the interrupts taking into account the xive_irq_domain to filter out IPIs. Signed-off-by:
-
Cédric Le Goater authored
When looping on IRQ descriptor, irq_data is always valid. Fixes: 930914b7 ("powerpc/xive: Add a debugfs file to dump internal XIVE state") Reported-by:
-
Cédric Le Goater authored
Now that the IPI interrupt has its own domain, the checks on the HW interrupt number XIVE_IPI_HW_IRQ and on the chip can be replaced by a check on the domain. Signed-off-by:
-
Cédric Le Goater authored
The IPI interrupt has its own domain now. Testing the HW interrupt number is not needed anymore. Signed-off-by:
-
Cédric Le Goater authored
The IPI interrupt is a special case of the XIVE IRQ domain. When mapping and unmapping the interrupts in the Linux interrupt number space, the HW interrupt number 0 (XIVE_IPI_HW_IRQ) is checked to distinguish the IPI interrupt from other interrupts of the system. Simplify the XIVE interrupt domain by introducing a specific domain for the IPI. Signed-off-by:
-
Yu Kuai authored
The sparse tool complains as follows: arch/powerpc/kernel/smp.c:86:1: warning: symbol '__pcpu_scope_cpu_coregroup_map' was not declared. Should it be static? arch/powerpc/kernel/smp.c:125:1: warning: symbol '__pcpu_scope_thread_group_l1_cache_map' was not declared. Should it be static? arch/powerpc/kernel/smp.c:132:1: warning: symbol '__pcpu_scope_thread_group_l2_cache_map' was not declared. Should it be static? These symbols are not used outside of smp.c, so this commit marks them static. Reported-by:
Yu Kuai <yukuai3@huawei.com> Signed-off-by:
-
