- 14 Mar, 2018 2 commits
-
-
Mark Hairgrove authored
pnv_npu2_init_context wasn't checking the return code from __mmu_notifier_register. If __mmu_notifier_register failed, the npu_context was still assigned to the mm and the caller wasn't given any indication that things went wrong. Later on pnv_npu2_destroy_context would be called, which in turn called mmu_notifier_unregister and dropped mm->mm_count without having incremented it in the first place. This led to various forms of corruption like mm use-after-free and mm double-free. __mmu_notifier_register can fail with EINTR if a signal is pending, so this case can be frequent. This patch calls opal_npu_destroy_context on the failure paths, and makes sure not to assign mm->context.npu_context until past the failure points. Signed-off-by:
Mark Hairgrove <mhairgrove@nvidia.com> Acked-By:
Alistair Popple <alistair@popple.id.au> Signed-off-by:
Michael Ellerman <mpe@ellerman.id.au>
-
Christophe Lombard authored
The PSL Timebase register is updated by the PSL to maintain the timebase. On P9, the Timebase value is only provided by the CAPP as received the last time a timebase request was performed. The timebase requests are initiated through the adapter configuration or application registers. The specific sysfs entry "/sys/class/cxl/cardxx/psl_timebase_synced" is now dynamically updated according the content of the PSL Timebase register. Fixes: f24be42a ("cxl: Add psl9 specific code") Signed-off-by:
Christophe Lombard <clombard@linux.vnet.ibm.com> Reviewed-by:
Vaibhav Jain <vaibhav@linux.vnet.ibm.com> Acked-by:
Andrew Donnellan <andrew.donnellan@au1.ibm.com> Acked-by:
Frederic Barrat <fbarrat@linux.vnet.ibm.com> Signed-off-by:
-
- 13 Mar, 2018 38 commits
-
-
Nicholas Piggin authored
This is a tidy up which removes radix MMU calls into the slice code. Signed-off-by:
Nicholas Piggin <npiggin@gmail.com> Signed-off-by:
-
Nicholas Piggin authored
The slice_mask cache was a basic conversion which copied the slice mask into caller's structures, because that's how the original code worked. In most cases the pointer can be used directly instead, saving a copy and an on-stack structure. On POWER8, this increases vfork+exec+exit performance by 0.3% and reduces time to mmap+munmap a 64kB page by 2%. Signed-off-by:
-
Nicholas Piggin authored
This code is never compiled in, and it gets broken by the next patch, so remove it. Signed-off-by:
-
Nicholas Piggin authored
This converts the slice_mask bit operation helpers to be the usual 3-operand kind, which allows 2 inputs to set a different output without an extra copy, which is used in the next patch. Adds slice_copy_mask, which will be used in the next patch. Signed-off-by:
-
Nicholas Piggin authored
Rather than build slice masks from a range then use that to check for fit in a candidate mask, implement slice_check_range_fits that checks if a range fits in a mask directly. This allows several structures to be removed from stacks, and also we don't expect a huge range in a lot of these cases, so building and comparing a full mask is going to be more expensive than testing just one or two bits of the range. On POWER8, this increases vfork+exec+exit performance by 0.3% and reduces time to mmap+munmap a 64kB page by 5%. Signed-off-by:
-
Nicholas Piggin authored
Calculating the slice mask can become a signifcant overhead for get_unmapped_area. This patch adds a struct slice_mask for each page size in the mm_context, and keeps these in synch with the slices psize arrays and slb_addr_limit. On Book3S/64 this adds 288 bytes to the mm_context_t for the slice mask caches. On POWER8, this increases vfork+exec+exit performance by 9.9% and reduces time to mmap+munmap a 64kB page by 28%. Reduces time to mmap+munmap by about 10% on 8xx. Signed-off-by:
-
Nicholas Piggin authored
Pass around const pointers to struct slice_mask where possible, rather than copies of slice_mask, to reduce stack and call overhead. checkstack.pl gives, before: 0x00000d1c slice_get_unmapped_area [slice.o]: 592 0x00001864 is_hugepage_only_range [slice.o]: 448 0x00000754 slice_find_area_topdown [slice.o]: 400 0x00000484 slice_find_area_bottomup.isra.1 [slice.o]: 272 0x000017b4 slice_set_range_psize [slice.o]: 224 0x00000a4c slice_find_area [slice.o]: 128 0x00000160 slice_check_fit [slice.o]: 112 after: 0x00000ad0 slice_get_unmapped_area [slice.o]: 448 0x00001464 is_hugepage_only_range [slice.o]: 288 0x000006c0 slice_find_area [slice.o]: 144 0x0000016c slice_check_fit [slice.o]: 128 0x00000528 slice_find_area_bottomup.isra.2 [slice.o]: 128 0x000013e4 slice_set_range_psize [slice.o]: 128 This increases vfork+exec+exit performance by 1.5%. Reduces time to mmap+munmap a 64kB page by 17%. Signed-off-by:
-
Nicholas Piggin authored
Make these loops look the same, and change their form so the important part is not wrapped over so many lines. Signed-off-by:
-
Nicholas Piggin authored
The slice state of an mm gets zeroed then initialised upon exec. This is the only caller of slice_set_user_psize now, so that can be removed and instead implement a faster and simplified approach that requires no locking or checking existing state. This speeds up vfork+exec+exit performance on POWER8 by 3%. Signed-off-by:
-
Michael Ellerman authored
Now that plpar_wrappers.h has an #ifdef PSERIES we can move the empty version of plpar_set_ciabr() which xmon wants into there. Signed-off-by: -
Michael Ellerman authored
Back in 2013 we added some hypercall wrappers which misspelled "plpar" (P-series Logical PARtition) as "plapr". Visually they're hard to distinguish and it almost doesn't matter, but it is confusing when grepping to miss some calls because of the typo. They've also started spreading, so before they take over let's fix them all to be "plpar". Signed-off-by: -
Michael Ellerman authored
Currently plpar_wrappers.h is not safe to include when CONFIG_PPC_PSERIES=n, or at least it can be depending on other config options and so on. Fix that by wrapping the entire content in an ifdef. Signed-off-by: -
Michael Ellerman authored
smp_query_cpu_stopped() and related #defines are currently in plpar_wrappers.h. The function actually does an RTAS call, not an hcall, and basically has nothing to do with plpar_wrappers.h Move it into pseries.h, where it can easily be used by the only two callers in pseries/smp.c and pseries/hotplug-cpu.c. Signed-off-by: -
Mathieu Malaterre authored
early_init() and machine_init() have no prototype, add one in asm-prototypes.h. Fixes the following warnings (treated as error in W=1): arch/powerpc/kernel/setup_32.c:68:30: error: no previous prototype for ‘early_init’ arch/powerpc/kernel/setup_32.c:99:21: error: no previous prototype for ‘machine_init’ Signed-off-by:
Mathieu Malaterre <malat@debian.org> [mpe: Move them to asm-prototypes.h, drop other functions] Signed-off-by:
-
Mathieu Malaterre authored
These functions can all be static, make it so. Signed-off-by:
-
Mathieu Malaterre authored
Rewrite function-like macro into regular static inline function to avoid a warning during macro expansion. Fix warning (treated as error in W=1): ./arch/powerpc/include/asm/uaccess.h:52:35: error: comparison of unsigned expression >= 0 is always true (((size) == 0) || (((size) - 1) <= ((segment).seg - (addr))))) ^ Suggested-by:Segher Boessenkool <segher@kernel.crashing.org> Signed-off-by:
Christophe Leroy <christophe.leroy@c-s.fr> Signed-off-by:
-
Mathieu Malaterre authored
Rewrite comparison since all values compared are of type `unsigned long`. Instead of using unsigned properties and rewriting the original code as: (originally suggested by Segher Boessenkool <segher@kernel.crashing.org>) #define pfn_valid(pfn) \ (((pfn) - ARCH_PFN_OFFSET) < (max_mapnr - ARCH_PFN_OFFSET)) Prefer a static inline function to make code as readable as possible. Fix a warning (treated as error in W=1): arch/powerpc/include/asm/page.h:129:32: error: comparison of unsigned expression >= 0 is always true [-Werror=type-limits] #define pfn_valid(pfn) ((pfn) >= ARCH_PFN_OFFSET && (pfn) < max_mapnr) ^ Suggested-by: -
Mathieu Malaterre authored
When neither CONFIG_ALTIVEC, nor CONFIG_VSX or CONFIG_PPC64 is defined, the array feature_properties is defined as an empty array, which in turn triggers the following warning (treated as error on W=1): arch/powerpc/kernel/prom.c: In function ‘check_cpu_feature_properties’: arch/powerpc/kernel/prom.c:298:16: error: comparison of unsigned expression < 0 is always false for (i = 0; i < ARRAY_SIZE(feature_properties); ++i, ++fp) { ^ Suggested-by: -
Mathieu Malaterre authored
Add missing prototypes for ppc_select() & ppc_fadvise64_64() to header asm-prototypes.h. Fix the following warnings (treated as errors in W=1) arch/powerpc/kernel/syscalls.c:87:1: error: no previous prototype for ‘ppc_select’ arch/powerpc/kernel/syscalls.c:119:6: error: no previous prototype for ‘ppc_fadvise64_64’ Signed-off-by:
-
Mathieu Malaterre authored
In commit 5aae8a53 ("powerpc, hw_breakpoints: Implement hw_breakpoints for 64-bit server processors") function hw_breakpoint_handler() and arch_unregister_hw_breakpoint() were added without function prototypes in hw_breakpoint.h header. Fix the following warning(s) (treated as error in W=1): arch/powerpc/kernel/hw_breakpoint.c:106:6: error: no previous prototype for ‘arch_unregister_hw_breakpoint’ arch/powerpc/kernel/hw_breakpoint.c:209:5: error: no previous prototype for ‘hw_breakpoint_handler’ Signed-off-by:
-
Mathieu Malaterre authored
Two functions did not have a prototype defined in signal.h header. Fix the following two warnings (treated as errors in W=1): arch/powerpc/kernel/signal_32.c:1135:6: error: no previous prototype for ‘sys_rt_sigreturn’ arch/powerpc/kernel/signal_32.c:1422:6: error: no previous prototype for ‘sys_sigreturn’ Signed-off-by:
-
Mathieu Malaterre authored
In commit 81e7009e ("powerpc: merge ppc signal.c and ppc64 signal32.c") the function sys_debug_setcontext was added without a prototype. Fix compilation warning (treated as error in W=1): arch/powerpc/kernel/signal_32.c:1227:5: error: no previous prototype for ‘sys_debug_setcontext’ Signed-off-by:
-
Mathieu Malaterre authored
A function init_IRQ() was added without a prototype declared in header irq.h. Fix the following warning (treated as error in W=1): arch/powerpc/kernel/irq.c:662:13: error: no previous prototype for ‘init_IRQ’ Signed-off-by:
-
Mathieu Malaterre authored
In commit 4f8b50bb ("irq_work, ppc: Fix up arch hooks") a new function arch_irq_work_raise() was added without a prototype in header irq_work.h. Fix the following warning (treated as error in W=1): arch/powerpc/kernel/time.c:523:6: error: no previous prototype for ‘arch_irq_work_raise’ Signed-off-by:
-
Mathieu Malaterre authored
In commit 55ccf3fe ("fork: move the real prepare_to_copy() users to arch_dup_task_struct()") a new arch_dup_task_struct() was added without a prototype declared in thread_info.h header. Fix the following warning (treated as error in W=1): arch/powerpc/kernel/process.c:1609:5: error: no previous prototype for ‘arch_dup_task_struct’ Signed-off-by:
-
Mathieu Malaterre authored
The function time_init did not have a prototype defined in the time.h header. Fix the following warning (treated as error in W=1): arch/powerpc/kernel/time.c:1068:13: error: no previous prototype for ‘time_init’ Signed-off-by:
-
Mathieu Malaterre authored
In commit dabe859e ("powerpc: Give hypervisor decrementer interrupts their own handler") an empty body function was added, but no prototype was declared. Fix warning (treated as error in W=1): arch/powerpc/kernel/time.c:629:6: error: no previous prototype for ‘hdec_interrupt’ Signed-off-by:
-
Mathieu Malaterre authored
In commit f0f558b1 ("powerpc/mm: Preserve CFAR value on SLB miss caused by access to bogus address"), the function slb_miss_bad_addr() was added without a prototype. This commit adds it. Fix a warning (treated as error in W=1): arch/powerpc/kernel/traps.c:1498:6: error: no previous prototype for ‘slb_miss_bad_addr’ Signed-off-by:
-
Mathieu Malaterre authored
__giveup_fpu() is never called outside process.c, so it can be static. That also means we don't need an empty definition in switch_to.h Signed-off-by:
-
Mathieu Malaterre authored
Change signature of two functions, adding static keyword to prevent the following two warnings (treated as errors on W=1): arch/powerpc/platforms/embedded6xx/flipper-pic.c:135:28: error: no previous prototype for ‘flipper_pic_init’ arch/powerpc/platforms/embedded6xx/usbgecko_udbg.c:172:6: error: no previous prototype for ‘ug_udbg_putc’ Signed-off-by:
-
Mathieu Malaterre authored
Since the value of `tmp` is never intended to be read, declare both `tmp` variables as unused. Fix warning (treated as error in W=1): arch/powerpc/kernel/signal_32.c: In function ‘sys_swapcontext’: arch/powerpc/kernel/signal_32.c:1048:16: error: variable ‘tmp’ set but not used arch/powerpc/kernel/signal_32.c: In function ‘sys_debug_setcontext’: arch/powerpc/kernel/signal_32.c:1234:16: error: variable ‘tmp’ set but not used Signed-off-by:
-
Mathieu Malaterre authored
The inline keyword was not at the beginning of the function declaration. Fix the following warning (treated as error in W=1): arch/powerpc/lib/sstep.c:283:1: error: ‘inline’ is not at beginning of declaration static int nokprobe_inline copy_mem_in(u8 *dest, unsigned long ea, int nb, arch/powerpc/lib/sstep.c:388:1: error: ‘inline’ is not at beginning of declaration static int nokprobe_inline copy_mem_out(u8 *dest, unsigned long ea, int nb, Signed-off-by:
-
Mathieu Malaterre authored
Fix warning for all register unsigned long (0,3-12) that appear during W=1 compilation: ./arch/powerpc/include/asm/epapr_hcalls.h:479:2: warning: ‘register’ is not at beginning of declaration [-Wold-style-declaration] unsigned long register r[\d] asm("r[\d]"); Signed-off-by: -
Simon Guo authored
In pnv_php_unregister_one(), pnv_php_put_slot() might kfree php_slot structure. But there is pci_hp_deregister() after that with php_slot reference. This patch moves pnv_php_put_slot() to the end of function. Signed-off-by:
Simon Guo <wei.guo.simon@gmail.com> Signed-off-by:
-
Balbir Singh authored
On MCE the current code will restart the machine with ppc_md.restart(). This case was extremely unlikely since prior to that a skiboot call is made and that resulted in a checkstop for analysis. With newer skiboots, on P9 we don't checkstop the box by default, instead we return back to the kernel to extract useful information at the time of the MCE. While we still get this information, this patch converts the restart to a panic(), so that if configured a dump can be taken and we can track and probably debug the potential issue causing the MCE. Signed-off-by:
Balbir Singh <bsingharora@gmail.com> Reviewed-by:
Stewart Smith <stewart@linux.vnet.ibm.com> Signed-off-by:
-
Philippe Bergheaud authored
Configure the P9 XSL_DSNCTL register with PHB indications found in the device tree, or else use legacy hard-coded values. Signed-off-by:
Philippe Bergheaud <felix@linux.vnet.ibm.com> Reviewed-by:
-
Philippe Bergheaud authored
P9 supports PCI tunneled operations (atomics and as_notify). This patch adds support for tunneled operations on powernv, with a new API, to be called by device drivers: pnv_pci_enable_tunnel() Enable tunnel operations, tell driver the 16-bit ASN indication used by kernel. pnv_pci_disable_tunnel() Disable tunnel operations. pnv_pci_set_tunnel_bar() Tell kernel the Tunnel BAR Response address used by driver. This function uses two new OPAL calls, as the PBCQ Tunnel BAR register is configured by skiboot. pnv_pci_get_as_notify_info() Return the ASN info of the thread to be woken up. Signed-off-by:
-
Alistair Popple authored
When sending TLB invalidates to the NPU we need to send extra flushes due to a hardware issue. The original implementation would lock the all the ATSD MMIO registers sequentially before unlocking and relocking each of them sequentially to do the extra flush. This introduced a deadlock as it is possible for one thread to hold one ATSD register whilst waiting for another register to be freed while the other thread is holding that register waiting for the one in the first thread to be freed. For example if there are two threads and two ATSD registers: Thread A Thread B ---------------------- Acquire 1 Acquire 2 Release 1 Acquire 1 Wait 1 Wait 2 Both threads will be stuck waiting to acquire a register resulting in an RCU stall warning or soft lockup. This patch solves the deadlock by refactoring the code to ensure registers are not released between flushes and to ensure all registers are either acquired or released together and in order. Fixes: bbd5ff50 ("powerpc/powernv/npu-dma: Add explicit flush when sending an ATSD") Signed-off-by:
-
