- 19 Apr, 2017 10 commits
-
-
Madhavan Srinivasan authored
Patch to export SIER bits to userspace via perf_mem_data_src and perf_sample_data struct. Signed-off-by:
Sukadev Bhattiprolu <sukadev@linux.vnet.ibm.com> Signed-off-by:
Madhavan Srinivasan <maddy@linux.vnet.ibm.com> Signed-off-by:
Michael Ellerman <mpe@ellerman.id.au>
-
Madhavan Srinivasan authored
Threshold feature when used with MMCRA [Threshold Event Counter Event], MMCRA[Threshold Start event] and MMCRA[Threshold End event] will update MMCRA[Threashold Event Counter Exponent] and MMCRA[Threshold Event Counter Multiplier] with the corresponding threshold event count values. Patch to export MMCRA[TECX/TECM] to userspace in 'weight' field of struct perf_sample_data. Signed-off-by:
-
Madhavan Srinivasan authored
The LDST field and DATA_SRC in SIER identifies the memory hierarchy level (eg: L1, L2 etc), from which a data-cache miss for a marked instruction was satisfied. Use the 'perf_mem_data_src' object to export this hierarchy level to user space. Signed-off-by:
-
Sukadev Bhattiprolu authored
perf_mem_data_src is a union that is initialized in the kernel via the ->val field and accessed by userspace via the mem_xxx bitfields. For this to work correctly on big endian platforms, we need a big-endian definition for the bitfields. Currently on a big endian system, if a user requests PERF_SAMPLE_DATA_SRC (perf report -d), they will get the default value from perf_sample_data_init(), which is PERF_MEM_NA. The value for PERF_MEM_NA is constructed using shifts: /* TLB access */ #define PERF_MEM_TLB_NA 0x01 /* not available */ ... #define PERF_MEM_TLB_SHIFT 26 #define PERF_MEM_S(a, s) \ (((__u64)PERF_MEM_##a##_##s) << PERF_MEM_##a##_SHIFT) #define PERF_MEM_NA (PERF_MEM_S(OP, NA) |\ PERF_MEM_S(LVL, NA) |\ PERF_MEM_S(SNOOP, NA) |\ PERF_MEM_S(LOCK, NA) |\ PERF_MEM_S(TLB, NA)) Which works out as: ((0x01 << 0) | (0x01 << 5) | (0x01 << 19) | (0x01 << 24) | (0x01 << 26)) Which means the PERF_MEM_NA value comes out of the kernel as 0x5080021 in CPU endian. But then in the perf tool, the code uses the bitfields to inspect the value, and currently the bitfields are defined using little endian ordering. So eg. in perf_mem__tlb_scnprintf() we see: data_src->val = 0x5080021 op = 0x0 lvl = 0x0 snoop = 0x0 lock = 0x0 dtlb = 0x0 rsvd = 0x5080021 Because of the way the perf tool code is written this is still displayed to the user as "N/A", so there is no bug visible at the UI level. Currently there are no big endian architectures which export a meaningful value (ie. other than PERF_MEM_NA), so the extent of the bug on big endian platforms is that the PERF_MEM_NA value is exported incorrectly as described above. Subsequent patches will add support on big endian powerpc for populating the data source value. This patch does a minimal fix of adding big endian definition of the bitfields to match the values that are already exported by the kernel on big endian. And it makes no change on little endian. Signed-off-by:Peter Zijlstra (Intel) <peterz@infradead.org> Signed-off-by:
-
Alexey Kardashevskiy authored
The CMA pages migration code does not support compound pages at the moment so it performs few tests before proceeding to actual page migration. One of the tests - PageTransHuge() - has VM_BUG_ON_PAGE(PageTail()) as it is designed to be called on head pages only. Since we also test for PageCompound(), and it contains PageTail() and PageHead(), we can simplify the check by leaving just PageCompound() and therefore avoid possible VM_BUG_ON_PAGE. Fixes: 2e5bbb54 ("KVM: PPC: Book3S HV: Migrate pinned pages out of CMA") Cc: stable@vger.kernel.org # v4.9+ Signed-off-by:
Alexey Kardashevskiy <aik@ozlabs.ru> Acked-by:
Balbir Singh <bsingharora@gmail.com> Signed-off-by:
-
Aneesh Kumar K.V authored
As part of the new large address space support, processes start out life with a 128TB virtual address space. However when calling mmap() a process can pass a hint address, and if that hint is > 128TB the kernel will use the full 512TB address space to try and satisfy the mmap() request. Currently we have a check that the hint is > 128TB and < 512TB (TASK_SIZE), which was added as an optimisation to avoid updating addr_limit unnecessarily and also to avoid calling slice_flush_segments() on all CPUs more than necessary. However this has the user-visible side effect that an mmap() hint above 512TB does not search the full address space unless a preceding mmap() used a hint value > 128TB && < 512TB. So fix it to treat any hint above 128TB as a hint to search the full address space, instead of checking the hint against TASK_SIZE, we instead check if the addr_limit is already == TASK_SIZE. This also brings the ABI in-line with what is proposed on x86. ie, that a hint address above 128TB up to and including (2^64)-1 is an indication to search the full address space. Fixes: f4ea6dcb (powerpc/mm: Enable mappings above 128TB) Signed-off-by:
Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com> Signed-off-by:
-
Matthew R. Ochs authored
Add support for future IBM Coherent Accelerator (CXL) devices with an IDs of 0x0623 and 0x0628. Signed-off-by:
Matthew R. Ochs <mrochs@linux.vnet.ibm.com> Signed-off-by:
Uma Krishnan <ukrishn@linux.vnet.ibm.com> Acked-by:
Frederic Barrat <fbarrat@linux.vnet.ibm.com> Signed-off-by:
-
Nicholas Piggin authored
The TLB flush for radix first flushes TLB for radix configuration, then flushes for hash configuration. The second flush is unnecessary but does not affect correctness. Fixes: 1a472c9d ("powerpc/mm/radix: Add tlbflush routines") Signed-off-by:
Nicholas Piggin <npiggin@gmail.com> Reviewed-by:
-
Aneesh Kumar K.V authored
We don't init addr_limit correctly for 32 bit applications. So default to using mm->task_size for boundary condition checking. We use addr_limit to only control free space search. This makes sure that we do the right thing with 32 bit applications. We should consolidate the usage of TASK_SIZE/mm->task_size and mm->context.addr_limit later. This partially reverts commit fbfef902 (powerpc/mm: Switch some TASK_SIZE checks to use mm_context addr_limit). Fixes: fbfef902 ("powerpc/mm: Switch some TASK_SIZE checks to use mm_context addr_limit") Signed-off-by:
-
Nicholas Piggin authored
The XIVE enablement patches included a change to set the LPES (Logical Partitioning Environment Selector) bit (bit # 3) in LPCR (Logical Partitioning Control Register) on POWER9 hosts. This bit sets external interrupts to guest delivery mode, which uses SRR0/1. The host's EE interrupt handler is written to expect HSRR0/1 (for earlier CPUs). This should be fine because XIVE is configured not to deliver EEs to the host (Hypervisor Virtulization Interrupt is used instead) so the EE handler should never be executed. However a bug in interrupt controller code, hardware, or odd configuration of a simulator could result in the host getting an EE incorrectly. Keeping the EE delivery mode matching the host EE handler prevents strange crashes due to using the wrong exception registers. KVM will configure the LPCR to set LPES prior to running a guest so that EEs are delivered to the guest using SRR0/1. Fixes: 08a1e650 ("powerpc: Fixup LPCR:PECE and HEIC setting on POWER9") Signed-off-by:
-
- 13 Apr, 2017 18 commits
-
-
Michael Ellerman authored
The pseries platform supports Power4 and later CPUs, all of which are multithreaded and/or multicore. In practice no one ever builds a SMP=n kernel for these machines. So as we did for powernv, have the pseries platform imply SMP=y. Signed-off-by: -
Michael Ellerman authored
The powernv platform supports Power7 and later CPUs, all of which are multithreaded and multicore. As such we never build a SMP=n kernel for those machines, other than possibly for debugging or running in a simulator. In the debugging case we can get a similar effect by booting with nr_cpus=1, or there's always the option of building a custom kernel with SMP hacked out. For running in simulators the code size reduction from building without SMP is not particularly important, what matters is the number of instructions executed. A quick test shows that a SMP=y kernel takes ~6% more instructions to boot to a shell. Booting with nr_cpus=1 recovers about half that deficit. On the flip side, keeping the SMP=n kernel building can be a pain at times. And although we've mostly kept it building in recent years, no one is regularly testing that the SMP=n kernel actually boots and works well on these machines. Signed-off-by: -
Michael Ellerman authored
Of the 64-bit Book3S platforms, only powermac supports booting on an actual non-SMP system. The other platforms can be built with SMP disabled, but it doesn't make a lot of sense given the CPUs they support are all multicore or multithreaded. So give platforms the option of forcing SMP=y. Signed-off-by: -
Michael Ellerman authored
Currently powerpc's asm/io.h includes linux/io.h, and linux/io.h includes asm/io.h. This can cause problems because depending on which is included first the order of definitions between the two files will change. The include of linux/io.h was added back in 2008 in commit b41e5fff ("[POWERPC] devres: Add devm_ioremap_prot()"). It's not entirely clear it was needed then, but devm_ioremap_prot() has since been removed entirely as unused, in dedd24a1 ("powerpc: Remove unused devm_ioremap_prot()"). So it seems to be unnecessary and can potentially cause problems, so remove the include of linux/io.h from asm/io.h Signed-off-by:
-
Nicholas Piggin authored
POWER9 requires msgsync for receiver-side synchronization, and a DD1 workaround restricts IPIs to core-local. Signed-off-by:
-
Nicholas Piggin authored
IPIs are a pretty hot path and we already have the ability to do asm feature patching, so use it. Signed-off-by:
-
Nicholas Piggin authored
POWER9 changes requirements and adds new instructions for synchronization. Signed-off-by:
-
Nicholas Piggin authored
Change the doorbell callers to know about their msgsnd addressing, rather than have them set a per-cpu target data tag at boot that gets sent to the cause_ipi functions. The data is only used for doorbell IPI functions, no other IPI types, so it makes sense to keep that detail local to doorbell. Have the platform code understand doorbell IPIs, rather than the interrupt controller code understand them. Platform code can look at capabilities it has available and decide which to use. Signed-off-by:
-
Nicholas Piggin authored
Add the bit definition and use it in facility_unavailable_exception() so we can intelligently report the cause if we take a fault for SCV. This doesn't actually enable SCV. Signed-off-by:
-
Nicholas Piggin authored
Signed-off-by:
-
Aneesh Kumar K.V authored
We have a #define for it, so use it. Signed-off-by:
-
Christophe Lombard authored
The new Coherent Accelerator Interface Architecture, level 2, for the IBM POWER9 brings new content and features: - POWER9 Service Layer - Registers - Radix mode - Process element entry - Dedicated-Shared Process Programming Model - Translation Fault Handling - CAPP - Memory Context ID If a valid mm_struct is found the memory context id is used for each transaction associated with the process handle. The PSL uses the context ID to find the corresponding process element. Signed-off-by:Christophe Lombard <clombard@linux.vnet.ibm.com> Acked-by:
-
Christophe Lombard authored
Point out the specific Coherent Accelerator Interface Architecture, level 1, registers. Code and functions specific to PSL8 (CAIA1) must be framed. Signed-off-by:
-
Christophe Lombard authored
Rename a few functions, changing the '_psl' suffix to '_psl8', to make clear that the implementation is psl8 specific. Those functions will have an equivalent implementation for the psl9 in a later patch. Signed-off-by:
Andrew Donnellan <andrew.donnellan@au1.ibm.com> Acked-by:
-
Christophe Lombard authored
The service layer API (in cxl.h) lists some low-level functions whose implementation is different on PSL8, PSL9 and XSL: - Init implementation for the adapter and the afu. - Invalidate TLB/SLB. - Attach process for dedicated/directed models. - Handle psl interrupts. - Debug registers for the adapter and the afu. - Traces. Each environment implements its own functions, and the common code uses them through function pointers, defined in cxl_service_layer_ops. Signed-off-by:
-
Christophe Lombard authored
The mm_struct corresponding to the current task is acquired each time an interrupt is raised. So to simplify the code, we only get the mm_struct when attaching an AFU context to the process. The mm_count reference is increased to ensure that the mm_struct can't be freed. The mm_struct will be released when the context is detached. A reference on mm_users is not kept to avoid a circular dependency if the process mmaps its cxl mmio and forget to unmap before exiting. The field glpid (pid of the group leader associated with the pid), of the structure cxl_context, is removed because it's no longer useful. Signed-off-by:
-
Christophe Lombard authored
The two previously fields pid and tid, located in the structure cxl_irq_info, are only used in the guest environment. To avoid confusion, it's not necessary to fill the fields in the bare-metal environment. Pid_tid is now renamed to 'reserved' to avoid undefined behavior on bare-metal. The PSL Process and Thread Identification Register (CXL_PSL_PID_TID_An) is only used when attaching a dedicated process for PSL8 only. This register goes away in CAIA2. Signed-off-by:
-
Christophe Lombard authored
This bit is used to cause a flash image load for programmable CAIA-compliant implementation. If this bit is set to ‘0’, a power cycle of the adapter is required to load a programmable CAIA-com- pliant implementation from flash. This field will be used by the following patches. Signed-off-by:
-
- 12 Apr, 2017 6 commits
-
-
Rashmica Gupta authored
The current behaviour of the hash table dump assumes that memory is contiguous and iterates from the start of memory to (start + size of memory). When memory isn't physically contiguous, this doesn't work. If memory exists at 0-5 GB and 6-10 GB then the current approach will check if entries exist in the hash table from 0GB to 9GB. This patch changes the behaviour to iterate over any holes up to the end of memory. Fixes: 1515ab93 ("powerpc/mm: Dump hash table") Signed-off-by:
Rashmica Gupta <rashmica.g@gmail.com> Signed-off-by:
-
Oliver O'Halloran authored
The current page table dumper scans the Linux page tables and coalesces mappings with adjacent virtual addresses and similar PTE flags. This behaviour is somewhat broken when you consider the IOREMAP space where entirely unrelated mappings will appear to be virtually contiguous. This patch modifies the range coalescing so that only ranges that are both physically and virtually contiguous are combined. This patch also adds to the dump output the physical address at the start of each range. Fixes: 8eb07b18 ("powerpc/mm: Dump linux pagetables") Signed-off-by:
Oliver O'Halloran <oohall@gmail.com> [mpe: Print the physicall address with 0x like the other addresses] Signed-off-by:
-
Oliver O'Halloran authored
On Book3s we have two PTE flags used to mark cache-inhibited mappings: _PAGE_TOLERANT and _PAGE_NON_IDEMPOTENT. Currently the kernel page table dumper only looks at the generic _PAGE_NO_CACHE which is defined to be _PAGE_TOLERANT. This patch modifies the dumper so both flags are shown in the dump. Fixes: 8eb07b18 ("powerpc/mm: Dump linux pagetables") Signed-off-by:
-
Balbir Singh authored
Currently sys_mmap() and sys_mmap2() (32-bit only), are not visible to the syscall tracing machinery. This means users are not able to see the execution of mmap() syscalls using the syscall tracer. Fix that by using SYSCALL_DEFINE6 for sys_mmap() and sys_mmap2() so that the meta-data associated with these syscalls is visible to the syscall tracer. A side-effect of this change is that the return type has changed from unsigned long to long. However this should have no effect, the only code in the kernel which uses the result of these syscalls is in the syscall return path, which is written in asm and treats the result as unsigned regardless. Example output: cat-3399 [001] .... 196.542410: sys_mmap(addr: 7fff922a0000, len: 20000, prot: 3, flags: 812, fd: 3, offset: 1b0000) cat-3399 [001] .... 196.542443: sys_mmap -> 0x7fff922a0000 cat-3399 [001] .... 196.542668: sys_munmap(addr: 7fff922c0000, len: 6d2c) cat-3399 [001] .... 196.542677: sys_munmap -> 0x0 Signed-off-by:
-
Michael Ellerman authored
Recently in commit f6eedbba ("powerpc/mm/hash: Increase VA range to 128TB"), we increased H_PGD_INDEX_SIZE to 15 when we're building with 64K pages. This makes it larger than RADIX_PGD_INDEX_SIZE (13), which means the logic to calculate MAX_PGD_INDEX_SIZE in book3s/64/pgtable.h is wrong. The end result is that the PGD (Page Global Directory, ie top level page table) of the kernel (aka. swapper_pg_dir), is too small. This generally doesn't lead to a crash, as we don't use the full range in normal operation. However if we try to dump the kernel pagetables we can trigger a crash because we walk off the end of the pgd into other memory and eventually try to dereference something bogus: $ cat /sys/kernel/debug/kernel_pagetables Unable to handle kernel paging request for data at address 0xe8fece0000000000 Faulting instruction address: 0xc000000000072314 cpu 0xc: Vector: 380 (Data SLB Access) at [c0000000daa13890] pc: c000000000072314: ptdump_show+0x164/0x430 lr: c000000000072550: ptdump_show+0x3a0/0x430 dar: e802cf0000000000 seq_read+0xf8/0x560 full_proxy_read+0x84/0xc0 __vfs_read+0x6c/0x1d0 vfs_read+0xbc/0x1b0 SyS_read+0x6c/0x110 system_call+0x38/0xfc The root cause is that MAX_PGD_INDEX_SIZE isn't actually computed to be the max of H_PGD_INDEX_SIZE or RADIX_PGD_INDEX_SIZE. To fix that move the calculation into asm-offsets.c where we can do it easily using max(). Fixes: f6eedbba ("powerpc/mm/hash: Increase VA range to 128TB") Signed-off-by:
-
Michael Ellerman authored
This merges the arch part of the XIVE support, leaving the final commit with the KVM specific pieces dangling on the branch for Paul to merge via the kvm-ppc tree.
-
- 10 Apr, 2017 6 commits
-
-
Gautham R. Shenoy authored
POWER9 DD1.0 hardware has a bug where the SPRs of a thread waking up from stop 0,1,2 with ESL=1 can endup being misplaced in the core. Thus the HSPRG0 of a thread waking up from can contain the paca pointer of its sibling. This patch implements a context recovery framework within threads of a core, by provisioning space in paca_struct for saving every sibling threads's paca pointers. Basically, we should be able to arrive at the right paca pointer from any of the thread's existing paca pointer. At bootup, during powernv idle-init, we save the paca address of every CPU in each one its siblings paca_struct in the slot corresponding to this CPU's index in the core. On wakeup from a stop, the thread will determine its index in the core from the TIR register and recover its PACA pointer by indexing into the correct slot in the provisioned space in the current PACA. Furthermore, ensure that the NVGPRs are restored from the stack on the way out by setting the NAPSTATELOST in paca. [Changelog written with inputs from svaidy@linux.vnet.ibm.com] Signed-off-by:
Gautham R. Shenoy <ego@linux.vnet.ibm.com> Reviewed-by:
-
Gautham R. Shenoy authored
Currently during idle-init on power9, if we don't find suitable stop states in the device tree that can be used as the default_stop/deepest_stop, we set stop0 (ESL=1,EC=1) as the default stop state psscr to be used by power9_idle and deepest stop state which is used by CPU-Hotplug. However, if the platform firmware has not configured or enabled a stop state, the kernel should not make any assumptions and fallback to a default choice. If the kernel uses a stop state that is not configured by the platform firmware, it may lead to further failures which should be avoided. In this patch, we modify the init code to ensure that the kernel uses only the stop states exposed by the firmware through the device tree. When a suitable default stop state isn't found, we disable ppc_md.power_save for power9. Similarly, when a suitable deepest_stop_state is not found in the device tree exported by the firmware, fall back to the default busy-wait loop in the CPU-Hotplug code. [Changelog written with inputs from svaidy@linux.vnet.ibm.com] Reviewed-by:
-
Gautham R. Shenoy authored
Currently, the powernv cpu-offline function assumes that platform idle states such as stop on POWER9, winkle/sleep/nap on POWER8 are always available. On POWER8, it picks nap as the default state if other deep idle states like sleep/winkle are not available and enabled in the platform. On POWER9, nap is not available and all idle states are managed by STOP instruction. The parameters to the idle state are passed through processor stop status control register (PSSCR). Hence as such executing STOP would take parameters from current PSSCR. We do not want to make any assumptions in kernel on what STOP states and PSSCR features are configured by the platform. Ideally platform will configure a good set of stop states that can be used in the kernel. We would like to start with a clean slate, if the platform choose to not configure any state or there is an error in platform firmware that lead to no stop states being configured or allowed to be requested. This patch adds a fallback method for CPU-Hotplug that is similar to snooze loop at idle where the threads are left to spin at low priority and hence reduce the cycles consumed. This is a safe fallback mechanism in the case when no stop state would be requested if the platform firmware did not configure them most likely due to an error condition. Requesting a stop state when the platform has not configured them or enabled them would lead to further error conditions which could be difficult to debug. [Changelog written with inputs from svaidy@linux.vnet.ibm.com] Reviewed-by:
-
Gautham R. Shenoy authored
Move the piece of code in powernv/smp.c::pnv_smp_cpu_kill_self() which transitions the CPU to the deepest available platform idle state to a new function named pnv_cpu_offline() in powernv/idle.c. The rationale behind this code movement is that the data required to determine the deepest available platform state resides in powernv/idle.c. Reviewed-by:
-
Anshuman Khandual authored
Add user space exported API definitions for 512KB, 1MB, 2MB, 8MB, 16MB, 1GB, 16GB non default huge page sizes to be used with mmap() system call. Signed-off-by:
Anshuman Khandual <khandual@linux.vnet.ibm.com> [mpe: Reword the comment to emphasise that these are only needed to use the non-default huge page size, and updated the change log.] Signed-off-by:
-
Anshuman Khandual authored
Generic core VM already prints these information in the log buffer, hence there is no need for a second print. This just removes the second print from arch powerpc NUMA init path. Before the patch: $ dmesg | grep "Initmem" numa: Initmem setup node 0 [mem 0x00000000-0xffffffff] numa: Initmem setup node 1 [mem 0x100000000-0x1ffffffff] numa: Initmem setup node 2 [mem 0x200000000-0x2ffffffff] numa: Initmem setup node 3 [mem 0x300000000-0x3ffffffff] numa: Initmem setup node 4 [mem 0x400000000-0x4ffffffff] numa: Initmem setup node 5 [mem 0x500000000-0x5ffffffff] numa: Initmem setup node 6 [mem 0x600000000-0x6ffffffff] numa: Initmem setup node 7 [mem 0x700000000-0x7ffffffff] Initmem setup node 0 [mem 0x0000000000000000-0x00000000ffffffff] Initmem setup node 1 [mem 0x0000000100000000-0x00000001ffffffff] Initmem setup node 2 [mem 0x0000000200000000-0x00000002ffffffff] Initmem setup node 3 [mem 0x0000000300000000-0x00000003ffffffff] Initmem setup node 4 [mem 0x0000000400000000-0x00000004ffffffff] Initmem setup node 5 [mem 0x0000000500000000-0x00000005ffffffff] Initmem setup node 6 [mem 0x0000000600000000-0x00000006ffffffff] Initmem setup node 7 [mem 0x0000000700000000-0x00000007ffffffff] After the patch just the latter set is printed. Signed-off-by:
-
