diff options
| author | Linus Torvalds <torvalds@linux-foundation.org> | 2014-10-11 20:34:00 -0400 |
|---|---|---|
| committer | Linus Torvalds <torvalds@linux-foundation.org> | 2014-10-11 20:34:00 -0400 |
| commit | fd9879b9bb3258ebc27a4cc6d2d29f528f71901f (patch) | |
| tree | 48b68994f5e8083aafe116533e8143cb2bf30c85 /drivers | |
| parent | 81ae31d78239318610d7c2acb3e2610d622a5aa4 (diff) | |
| parent | d53ba6b3bba33432cc37b7101a86f8f3392c46e7 (diff) | |
| download | linux-fd9879b9bb3258ebc27a4cc6d2d29f528f71901f.tar.gz linux-fd9879b9bb3258ebc27a4cc6d2d29f528f71901f.tar.bz2 linux-fd9879b9bb3258ebc27a4cc6d2d29f528f71901f.zip | |
Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mpe/linux
Pull powerpc updates from Michael Ellerman:
"Here's a first pull request for powerpc updates for 3.18.
The bulk of the additions are for the "cxl" driver, for IBM's Coherent
Accelerator Processor Interface (CAPI). Most of it's in drivers/misc,
which Greg & Arnd maintain, Greg said he was happy for us to take it
through our tree.
There's the usual minor cleanups and fixes, including a bit of noise
in drivers from some of those. A bunch of updates to our EEH code,
which has been getting more testing. Several nice speedups from
Anton, including 20% in clear_page().
And a bunch of updates for freescale from Scott"
* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mpe/linux: (130 commits)
cxl: Fix afu_read() not doing finish_wait() on signal or non-blocking
cxl: Add documentation for userspace APIs
cxl: Add driver to Kbuild and Makefiles
cxl: Add userspace header file
cxl: Driver code for powernv PCIe based cards for userspace access
cxl: Add base builtin support
powerpc/mm: Add hooks for cxl
powerpc/opal: Add PHB to cxl mode call
powerpc/mm: Add new hash_page_mm()
powerpc/powerpc: Add new PCIe functions for allocating cxl interrupts
cxl: Add new header for call backs and structs
powerpc/powernv: Split out set MSI IRQ chip code
powerpc/mm: Export mmu_kernel_ssize and mmu_linear_psize
powerpc/msi: Improve IRQ bitmap allocator
powerpc/cell: Make spu_flush_all_slbs() generic
powerpc/cell: Move data segment faulting code out of cell platform
powerpc/cell: Move spu_handle_mm_fault() out of cell platform
powerpc/pseries: Use new defines when calling H_SET_MODE
powerpc: Update contact info in Documentation files
powerpc/perf/hv-24x7: Simplify catalog_read()
...
Diffstat (limited to 'drivers')
| -rw-r--r-- | drivers/cpufreq/pmac32-cpufreq.c | 2 | ||||
| -rw-r--r-- | drivers/macintosh/adb.c | 5 | ||||
| -rw-r--r-- | drivers/macintosh/via-cuda.c | 2 | ||||
| -rw-r--r-- | drivers/misc/Kconfig | 1 | ||||
| -rw-r--r-- | drivers/misc/Makefile | 1 | ||||
| -rw-r--r-- | drivers/misc/cxl/Kconfig | 25 | ||||
| -rw-r--r-- | drivers/misc/cxl/Makefile | 3 | ||||
| -rw-r--r-- | drivers/misc/cxl/base.c | 86 | ||||
| -rw-r--r-- | drivers/misc/cxl/context.c | 193 | ||||
| -rw-r--r-- | drivers/misc/cxl/cxl.h | 629 | ||||
| -rw-r--r-- | drivers/misc/cxl/debugfs.c | 132 | ||||
| -rw-r--r-- | drivers/misc/cxl/fault.c | 291 | ||||
| -rw-r--r-- | drivers/misc/cxl/file.c | 518 | ||||
| -rw-r--r-- | drivers/misc/cxl/irq.c | 402 | ||||
| -rw-r--r-- | drivers/misc/cxl/main.c | 230 | ||||
| -rw-r--r-- | drivers/misc/cxl/native.c | 683 | ||||
| -rw-r--r-- | drivers/misc/cxl/pci.c | 1000 | ||||
| -rw-r--r-- | drivers/misc/cxl/sysfs.c | 385 | ||||
| -rw-r--r-- | drivers/tty/hvc/hvc_vio.c | 2 |
19 files changed, 4588 insertions, 2 deletions
diff --git a/drivers/cpufreq/pmac32-cpufreq.c b/drivers/cpufreq/pmac32-cpufreq.c index 7615180d7ee3..1f49d97a70ea 100644 --- a/drivers/cpufreq/pmac32-cpufreq.c +++ b/drivers/cpufreq/pmac32-cpufreq.c @@ -611,7 +611,7 @@ static int __init pmac_cpufreq_setup(void) struct device_node *cpunode; const u32 *value; - if (strstr(cmd_line, "nocpufreq")) + if (strstr(boot_command_line, "nocpufreq")) return 0; /* Get first CPU node */ diff --git a/drivers/macintosh/adb.c b/drivers/macintosh/adb.c index 9e9c56758a08..226179b975a0 100644 --- a/drivers/macintosh/adb.c +++ b/drivers/macintosh/adb.c @@ -411,6 +411,7 @@ adb_poll(void) return; adb_controller->poll(); } +EXPORT_SYMBOL(adb_poll); static void adb_sync_req_done(struct adb_request *req) { @@ -460,6 +461,7 @@ adb_request(struct adb_request *req, void (*done)(struct adb_request *), return rc; } +EXPORT_SYMBOL(adb_request); /* Ultimately this should return the number of devices with the given default id. @@ -495,6 +497,7 @@ adb_register(int default_id, int handler_id, struct adb_ids *ids, mutex_unlock(&adb_handler_mutex); return ids->nids; } +EXPORT_SYMBOL(adb_register); int adb_unregister(int index) @@ -516,6 +519,7 @@ adb_unregister(int index) mutex_unlock(&adb_handler_mutex); return ret; } +EXPORT_SYMBOL(adb_unregister); void adb_input(unsigned char *buf, int nb, int autopoll) @@ -582,6 +586,7 @@ adb_try_handler_change(int address, int new_id) mutex_unlock(&adb_handler_mutex); return ret; } +EXPORT_SYMBOL(adb_try_handler_change); int adb_get_infos(int address, int *original_address, int *handler_id) diff --git a/drivers/macintosh/via-cuda.c b/drivers/macintosh/via-cuda.c index d61f271d2207..bad18130f125 100644 --- a/drivers/macintosh/via-cuda.c +++ b/drivers/macintosh/via-cuda.c @@ -379,6 +379,7 @@ cuda_request(struct adb_request *req, void (*done)(struct adb_request *), req->reply_expected = 1; return cuda_write(req); } +EXPORT_SYMBOL(cuda_request); static int cuda_write(struct adb_request *req) @@ -441,6 +442,7 @@ cuda_poll(void) if (cuda_irq) enable_irq(cuda_irq); } +EXPORT_SYMBOL(cuda_poll); static irqreturn_t cuda_interrupt(int irq, void *arg) diff --git a/drivers/misc/Kconfig b/drivers/misc/Kconfig index b841180c7c74..bbeb4516facf 100644 --- a/drivers/misc/Kconfig +++ b/drivers/misc/Kconfig @@ -527,4 +527,5 @@ source "drivers/misc/vmw_vmci/Kconfig" source "drivers/misc/mic/Kconfig" source "drivers/misc/genwqe/Kconfig" source "drivers/misc/echo/Kconfig" +source "drivers/misc/cxl/Kconfig" endmenu diff --git a/drivers/misc/Makefile b/drivers/misc/Makefile index 5497d026e651..7d5c4cd118c4 100644 --- a/drivers/misc/Makefile +++ b/drivers/misc/Makefile @@ -55,3 +55,4 @@ obj-y += mic/ obj-$(CONFIG_GENWQE) += genwqe/ obj-$(CONFIG_ECHO) += echo/ obj-$(CONFIG_VEXPRESS_SYSCFG) += vexpress-syscfg.o +obj-$(CONFIG_CXL_BASE) += cxl/ diff --git a/drivers/misc/cxl/Kconfig b/drivers/misc/cxl/Kconfig new file mode 100644 index 000000000000..a990b39b4dfb --- /dev/null +++ b/drivers/misc/cxl/Kconfig @@ -0,0 +1,25 @@ +# +# IBM Coherent Accelerator (CXL) compatible devices +# + +config CXL_BASE + bool + default n + select PPC_COPRO_BASE + +config CXL + tristate "Support for IBM Coherent Accelerators (CXL)" + depends on PPC_POWERNV && PCI_MSI + select CXL_BASE + default m + help + Select this option to enable driver support for IBM Coherent + Accelerators (CXL). CXL is otherwise known as Coherent Accelerator + Processor Interface (CAPI). CAPI allows accelerators in FPGAs to be + coherently attached to a CPU via an MMU. This driver enables + userspace programs to access these accelerators via /dev/cxl/afuM.N + devices. + + CAPI adapters are found in POWER8 based systems. + + If unsure, say N. diff --git a/drivers/misc/cxl/Makefile b/drivers/misc/cxl/Makefile new file mode 100644 index 000000000000..165e98fef2c2 --- /dev/null +++ b/drivers/misc/cxl/Makefile @@ -0,0 +1,3 @@ +cxl-y += main.o file.o irq.o fault.o native.o context.o sysfs.o debugfs.o pci.o +obj-$(CONFIG_CXL) += cxl.o +obj-$(CONFIG_CXL_BASE) += base.o diff --git a/drivers/misc/cxl/base.c b/drivers/misc/cxl/base.c new file mode 100644 index 000000000000..0654ad83675e --- /dev/null +++ b/drivers/misc/cxl/base.c @@ -0,0 +1,86 @@ +/* + * Copyright 2014 IBM Corp. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#include <linux/module.h> +#include <linux/rcupdate.h> +#include <asm/errno.h> +#include <misc/cxl.h> +#include "cxl.h" + +/* protected by rcu */ +static struct cxl_calls *cxl_calls; + +atomic_t cxl_use_count = ATOMIC_INIT(0); +EXPORT_SYMBOL(cxl_use_count); + +#ifdef CONFIG_CXL_MODULE + +static inline struct cxl_calls *cxl_calls_get(void) +{ + struct cxl_calls *calls = NULL; + + rcu_read_lock(); + calls = rcu_dereference(cxl_calls); + if (calls && !try_module_get(calls->owner)) + calls = NULL; + rcu_read_unlock(); + + return calls; +} + +static inline void cxl_calls_put(struct cxl_calls *calls) +{ + BUG_ON(calls != cxl_calls); + + /* we don't need to rcu this, as we hold a reference to the module */ + module_put(cxl_calls->owner); +} + +#else /* !defined CONFIG_CXL_MODULE */ + +static inline struct cxl_calls *cxl_calls_get(void) +{ + return cxl_calls; +} + +static inline void cxl_calls_put(struct cxl_calls *calls) { } + +#endif /* CONFIG_CXL_MODULE */ + +void cxl_slbia(struct mm_struct *mm) +{ + struct cxl_calls *calls; + + calls = cxl_calls_get(); + if (!calls) + return; + + if (cxl_ctx_in_use()) + calls->cxl_slbia(mm); + + cxl_calls_put(calls); +} + +int register_cxl_calls(struct cxl_calls *calls) +{ + if (cxl_calls) + return -EBUSY; + + rcu_assign_pointer(cxl_calls, calls); + return 0; +} +EXPORT_SYMBOL_GPL(register_cxl_calls); + +void unregister_cxl_calls(struct cxl_calls *calls) +{ + BUG_ON(cxl_calls->owner != calls->owner); + RCU_INIT_POINTER(cxl_calls, NULL); + synchronize_rcu(); +} +EXPORT_SYMBOL_GPL(unregister_cxl_calls); diff --git a/drivers/misc/cxl/context.c b/drivers/misc/cxl/context.c new file mode 100644 index 000000000000..cca472109135 --- /dev/null +++ b/drivers/misc/cxl/context.c @@ -0,0 +1,193 @@ +/* + * Copyright 2014 IBM Corp. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#include <linux/module.h> +#include <linux/kernel.h> +#include <linux/bitmap.h> +#include <linux/sched.h> +#include <linux/pid.h> +#include <linux/fs.h> +#include <linux/mm.h> +#include <linux/debugfs.h> +#include <linux/slab.h> +#include <linux/idr.h> +#include <asm/cputable.h> +#include <asm/current.h> +#include <asm/copro.h> + +#include "cxl.h" + +/* + * Allocates space for a CXL context. + */ +struct cxl_context *cxl_context_alloc(void) +{ + return kzalloc(sizeof(struct cxl_context), GFP_KERNEL); +} + +/* + * Initialises a CXL context. + */ +int cxl_context_init(struct cxl_context *ctx, struct cxl_afu *afu, bool master) +{ + int i; + + spin_lock_init(&ctx->sste_lock); + ctx->afu = afu; + ctx->master = master; + ctx->pid = NULL; /* Set in start work ioctl */ + + /* + * Allocate the segment table before we put it in the IDR so that we + * can always access it when dereferenced from IDR. For the same + * reason, the segment table is only destroyed after the context is + * removed from the IDR. Access to this in the IOCTL is protected by + * Linux filesytem symantics (can't IOCTL until open is complete). + */ + i = cxl_alloc_sst(ctx); + if (i) + return i; + + INIT_WORK(&ctx->fault_work, cxl_handle_fault); + + init_waitqueue_head(&ctx->wq); + spin_lock_init(&ctx->lock); + + ctx->irq_bitmap = NULL; + ctx->pending_irq = false; + ctx->pending_fault = false; + ctx->pending_afu_err = false; + + /* + * When we have to destroy all contexts in cxl_context_detach_all() we + * end up with afu_release_irqs() called from inside a + * idr_for_each_entry(). Hence we need to make sure that anything + * dereferenced from this IDR is ok before we allocate the IDR here. + * This clears out the IRQ ranges to ensure this. + */ + for (i = 0; i < CXL_IRQ_RANGES; i++) + ctx->irqs.range[i] = 0; + + mutex_init(&ctx->status_mutex); + + ctx->status = OPENED; + + /* + * Allocating IDR! We better make sure everything's setup that + * dereferences from it. + */ + idr_preload(GFP_KERNEL); + spin_lock(&afu->contexts_lock); + i = idr_alloc(&ctx->afu->contexts_idr, ctx, 0, + ctx->afu->num_procs, GFP_NOWAIT); + spin_unlock(&afu->contexts_lock); + idr_preload_end(); + if (i < 0) + return i; + + ctx->pe = i; + ctx->elem = &ctx->afu->spa[i]; + ctx->pe_inserted = false; + return 0; +} + +/* + * Map a per-context mmio space into the given vma. + */ +int cxl_context_iomap(struct cxl_context *ctx, struct vm_area_struct *vma) +{ + u64 len = vma->vm_end - vma->vm_start; + len = min(len, ctx->psn_size); + + if (ctx->afu->current_mode == CXL_MODE_DEDICATED) { + vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot); + return vm_iomap_memory(vma, ctx->afu->psn_phys, ctx->afu->adapter->ps_size); + } + + /* make sure there is a valid per process space for this AFU */ + if ((ctx->master && !ctx->afu->psa) || (!ctx->afu->pp_psa)) { + pr_devel("AFU doesn't support mmio space\n"); + return -EINVAL; + } + + /* Can't mmap until the AFU is enabled */ + if (!ctx->afu->enabled) + return -EBUSY; + + pr_devel("%s: mmio physical: %llx pe: %i master:%i\n", __func__, + ctx->psn_phys, ctx->pe , ctx->master); + + vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot); + return vm_iomap_memory(vma, ctx->psn_phys, len); +} + +/* + * Detach a context from the hardware. This disables interrupts and doesn't + * return until all outstanding interrupts for this context have completed. The + * hardware should no longer access *ctx after this has returned. + */ +static void __detach_context(struct cxl_context *ctx) +{ + enum cxl_context_status status; + + mutex_lock(&ctx->status_mutex); + status = ctx->status; + ctx->status = CLOSED; + mutex_unlock(&ctx->status_mutex); + if (status != STARTED) + return; + + WARN_ON(cxl_detach_process(ctx)); + afu_release_irqs(ctx); + flush_work(&ctx->fault_work); /* Only needed for dedicated process */ + wake_up_all(&ctx->wq); +} + +/* + * Detach the given context from the AFU. This doesn't actually + * free the context but it should stop the context running in hardware + * (ie. prevent this context from generating any further interrupts + * so that it can be freed). + */ +void cxl_context_detach(struct cxl_context *ctx) +{ + __detach_context(ctx); +} + +/* + * Detach all contexts on the given AFU. + */ +void cxl_context_detach_all(struct cxl_afu *afu) +{ + struct cxl_context *ctx; + int tmp; + + rcu_read_lock(); + idr_for_each_entry(&afu->contexts_idr, ctx, tmp) + /* + * Anything done in here needs to be setup before the IDR is + * created and torn down after the IDR removed + */ + __detach_context(ctx); + rcu_read_unlock(); +} + +void cxl_context_free(struct cxl_context *ctx) +{ + spin_lock(&ctx->afu->contexts_lock); + idr_remove(&ctx->afu->contexts_idr, ctx->pe); + spin_unlock(&ctx->afu->contexts_lock); + synchronize_rcu(); + + free_page((u64)ctx->sstp); + ctx->sstp = NULL; + + put_pid(ctx->pid); + kfree(ctx); +} diff --git a/drivers/misc/cxl/cxl.h b/drivers/misc/cxl/cxl.h new file mode 100644 index 000000000000..3d2b8677ec8a --- /dev/null +++ b/drivers/misc/cxl/cxl.h @@ -0,0 +1,629 @@ +/* + * Copyright 2014 IBM Corp. + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + +#ifndef _CXL_H_ +#define _CXL_H_ + +#include <linux/interrupt.h> +#include <linux/semaphore.h> +#include <linux/device.h> +#include <linux/types.h> +#include <linux/cdev.h> +#include <linux/pid.h> +#include <linux/io.h> +#include <linux/pci.h> +#include <asm/cputable.h> +#include <asm/mmu.h> +#include <asm/reg.h> +#include <misc/cxl.h> + +#include <uapi/misc/cxl.h> + +extern uint cxl_verbose; + +#define CXL_TIMEOUT 5 + +/* + * Bump version each time a user API change is made, whether it is + * backwards compatible ot not. + */ +#define CXL_API_VERSION 1 +#define CXL_API_VERSION_COMPATIBLE 1 + +/* + * Opaque types to avoid accidentally passing registers for the wrong MMIO + * + * At the end of the day, I'm not married to using typedef here, but it might + * (and has!) help avoid bugs like mixing up CXL_PSL_CtxTime and + * CXL_PSL_CtxTime_An, or calling cxl_p1n_write instead of cxl_p1_write. + * + * I'm quite happy if these are changed back to #defines before upstreaming, it + * should be little more than a regexp search+replace operation in this file. + */ +typedef struct { + const int x; +} cxl_p1_reg_t; +typedef struct { + const int x; +} cxl_p1n_reg_t; +typedef struct { + const int x; +} cxl_p2n_reg_t; +#define cxl_reg_off(reg) \ + (reg.x) + +/* Memory maps. Ref CXL Appendix A */ + +/* PSL Privilege 1 Memory Map */ +/* Configuration and Control area */ +static const cxl_p1_reg_t CXL_PSL_CtxTime = {0x0000}; +static const cxl_p1_reg_t CXL_PSL_ErrIVTE = {0x0008}; +static const cxl_p1_reg_t CXL_PSL_KEY1 = {0x0010}; +static const cxl_p1_reg_t CXL_PSL_KEY2 = {0x0018}; +static const cxl_p1_reg_t CXL_PSL_Control = {0x0020}; +/* Downloading */ +static const cxl_p1_reg_t CXL_PSL_DLCNTL = {0x0060}; +static const cxl_p1_reg_t CXL_PSL_DLADDR = {0x0068}; + +/* PSL Lookaside Buffer Management Area */ +static const cxl_p1_reg_t CXL_PSL_LBISEL = {0x0080}; +static const cxl_p1_reg_t CXL_PSL_SLBIE = {0x0088}; +static const cxl_p1_reg_t CXL_PSL_SLBIA = {0x0090}; +static const cxl_p1_reg_t CXL_PSL_TLBIE = {0x00A0}; +static const cxl_p1_reg_t CXL_PSL_TLBIA = {0x00A8}; +static const cxl_p1_reg_t CXL_PSL_AFUSEL = {0x00B0}; + +/* 0x00C0:7EFF Implementation dependent area */ +static const cxl_p1_reg_t CXL_PSL_FIR1 = {0x0100}; +static const cxl_p1_reg_t CXL_PSL_FIR2 = {0x0108}; +static const cxl_p1_reg_t CXL_PSL_VERSION = {0x0118}; +static const cxl_p1_reg_t CXL_PSL_RESLCKTO = {0x0128}; +static const cxl_p1_reg_t CXL_PSL_FIR_CNTL = {0x0148}; +static const cxl_p1_reg_t CXL_PSL_DSNDCTL = {0x0150}; +static const cxl_p1_reg_t CXL_PSL_SNWRALLOC = {0x0158}; +static const cxl_p1_reg_t CXL_PSL_TRACE = {0x0170}; +/* 0x7F00:7FFF Reserved PCIe MSI-X Pending Bit Array area */ +/* 0x8000:FFFF Reserved PCIe MSI-X Table Area */ + +/* PSL Slice Privilege 1 Memory Map */ +/* Configuration Area */ +static const cxl_p1n_reg_t CXL_PSL_SR_An = {0x00}; +static const cxl_p1n_reg_t CXL_PSL_LPID_An = {0x08}; +static const cxl_p1n_reg_t CXL_PSL_AMBAR_An = {0x10}; +static const cxl_p1n_reg_t CXL_PSL_SPOffset_An = {0x18}; +static const cxl_p1n_reg_t CXL_PSL_ID_An = {0x20}; +static const cxl_p1n_reg_t CXL_PSL_SERR_An = {0x28}; +/* Memory Management and Lookaside Buffer Management */ +static const cxl_p1n_reg_t CXL_PSL_SDR_An = {0x30}; +static const cxl_p1n_reg_t CXL_PSL_AMOR_An = {0x38}; +/* Pointer Area */ +static const cxl_p1n_reg_t CXL_HAURP_An = {0x80}; +static const cxl_p1n_reg_t CXL_PSL_SPAP_An = {0x88}; +static const cxl_p1n_reg_t CXL_PSL_LLCMD_An = {0x90}; +/* Control Area */ +static const cxl_p1n_reg_t CXL_PSL_SCNTL_An = {0xA0}; +static const cxl_p1n_reg_t CXL_PSL_CtxTime_An = {0xA8}; +static const cxl_p1n_reg_t CXL_PSL_IVTE_Offset_An = {0xB0}; +static const cxl_p1n_reg_t CXL_PSL_IVTE_Limit_An = {0xB8}; +/* 0xC0:FF Implementation Dependent Area */ +static const cxl_p1n_reg_t CXL_PSL_FIR_SLICE_An = {0xC0}; +static const cxl_p1n_reg_t CXL_AFU_DEBUG_An = {0xC8}; +static const cxl_p1n_reg_t CXL_PSL_APCALLOC_A = {0xD0}; +static const cxl_p1n_reg_t CXL_PSL_COALLOC_A = {0xD8}; +static const cxl_p1n_reg_t CXL_PSL_RXCTL_A = {0xE0}; +static const cxl_p1n_reg_t CXL_PSL_SLICE_TRACE = {0xE8}; + +/* PSL Slice Privilege 2 Memory Map */ +/* Configuration and Control Area */ +static const cxl_p2n_reg_t CXL_PSL_PID_TID_An = {0x000}; +static const cxl_p2n_reg_t CXL_CSRP_An = {0x008}; +static const cxl_p2n_reg_t CXL_AURP0_An = {0x010}; +static const cxl_p2n_reg_t CXL_AURP1_An = {0x018}; +static const cxl_p2n_reg_t CXL_SSTP0_An = {0x020}; +static const cxl_p2n_reg_t CXL_SSTP1_An = {0x028}; +static const cxl_p2n_reg_t CXL_PSL_AMR_An = {0x030}; +/* Segment Lookaside Buffer Management */ +static const cxl_p2n_reg_t CXL_SLBIE_An = {0x040}; +static const cxl_p2n_reg_t CXL_SLBIA_An = {0x048}; +static const cxl_p2n_reg_t CXL_SLBI_Select_An = {0x050}; +/* Interrupt Registers */ +static const cxl_p2n_reg_t CXL_PSL_DSISR_An = {0x060}; +static const cxl_p2n_reg_t CXL_PSL_DAR_An = {0x068}; +static const cxl_p2n_reg_t CXL_PSL_DSR_An = {0x070}; +static const cxl_p2n_reg_t CXL_PSL_TFC_An = {0x078}; +static const cxl_p2n_reg_t CXL_PSL_PEHandle_An = {0x080}; +static const cxl_p2n_reg_t CXL_PSL_ErrStat_An = {0x088}; +/* AFU Registers */ +static const cxl_p2n_reg_t CXL_AFU_Cntl_An = {0x090}; +static const cxl_p2n_reg_t CXL_AFU_ERR_An = {0x098}; +/* Work Element Descriptor */ +static const cxl_p2n_reg_t CXL_PSL_WED_An = {0x0A0}; +/* 0x0C0:FFF Implementation Dependent Area */ + +#define CXL_PSL_SPAP_Addr 0x0ffffffffffff000ULL +#define CXL_PSL_SPAP_Size 0x0000000000000ff0ULL +#define CXL_PSL_SPAP_Size_Shift 4 +#define CXL_PSL_SPAP_V 0x0000000000000001ULL + +/****** CXL_PSL_DLCNTL *****************************************************/ +#define CXL_PSL_DLCNTL_D (0x1ull << (63-28)) +#define CXL_PSL_DLCNTL_C (0x1ull << (63-29)) +#define CXL_PSL_DLCNTL_E (0x1ull << (63-30)) +#define CXL_PSL_DLCNTL_S (0x1ull << (63-31)) +#define CXL_PSL_DLCNTL_CE (CXL_PSL_DLCNTL_C | CXL_PSL_DLCNTL_E) +#define CXL_PSL_DLCNTL_DCES (CXL_PSL_DLCNTL_D | CXL_PSL_DLCNTL_CE | CXL_PSL_DLCNTL_S) + +/****** CXL_PSL_SR_An ******************************************************/ +#define CXL_PSL_SR_An_SF MSR_SF /* 64bit */ +#define CXL_PSL_SR_An_TA (1ull << (63-1)) /* Tags active, GA1: 0 */ +#define CXL_PSL_SR_An_HV MSR_HV /* Hypervisor, GA1: 0 */ +#define CXL_PSL_SR_An_PR MSR_PR /* Problem state, GA1: 1 */ +#define CXL_PSL_SR_An_ISL (1ull << (63-53)) /* Ignore Segment Large Page */ +#define CXL_PSL_SR_An_TC (1ull << (63-54)) /* Page Table secondary hash */ +#define CXL_PSL_SR_An_US (1ull << (63-56)) /* User state, GA1: X */ +#define CXL_PSL_SR_An_SC (1ull << (63-58)) /* Segment Table secondary hash */ +#define CXL_PSL_SR_An_R MSR_DR /* Relocate, GA1: 1 */ +#define CXL_PSL_SR_An_MP (1ull << (63-62)) /* Master Process */ +#define CXL_PSL_SR_An_LE (1ull << (63-63)) /* Little Endian */ + +/****** CXL_PSL_LLCMD_An ****************************************************/ +#define CXL_LLCMD_TERMINATE 0x0001000000000000ULL +#define CXL_LLCMD_REMOVE 0x0002000000000000ULL +#define CXL_LLCMD_SUSPEND 0x0003000000000000ULL +#define CXL_LLCMD_RESUME 0x0004000000000000ULL +#define CXL_LLCMD_ADD 0x0005000000000000ULL +#define CXL_LLCMD_UPDATE 0x0006000000000000ULL +#define CXL_LLCMD_HANDLE_MASK 0x000000000000ffffULL + +/****** CXL_PSL_ID_An ****************************************************/ +#define CXL_PSL_ID_An_F (1ull << (63-31)) +#define CXL_PSL_ID_An_L (1ull << (63-30)) + +/****** CXL_PSL_SCNTL_An ****************************************************/ +#define CXL_PSL_SCNTL_An_CR (0x1ull << (63-15)) +/* Programming Modes: */ +#define CXL_PSL_SCNTL_An_PM_MASK (0xffffull << (63-31)) +#define CXL_PSL_SCNTL_An_PM_Shared (0x0000ull << (63-31)) +#define CXL_PSL_SCNTL_An_PM_OS (0x0001ull << (63-31)) +#define CXL_PSL_SCNTL_An_PM_Process (0x0002ull << (63-31)) +#define CXL_PSL_SCNTL_An_PM_AFU (0x0004ull << (63-31)) +#define CXL_PSL_SCNTL_An_PM_AFU_PBT (0x0104ull << (63-31)) +/* Purge Status (ro) */ +#define CXL_PSL_SCNTL_An_Ps_MASK (0x3ull << (63-39)) +#define CXL_PSL_SCNTL_An_Ps_Pending (0x1ull << (63-39)) +#define CXL_PSL_SCNTL_An_Ps_Complete (0x3ull << (63-39)) +/* Purge */ +#define CXL_PSL_SCNTL_An_Pc (0x1ull << (63-48)) +/* Suspend Status (ro) */ +#define CXL_PSL_SCNTL_An_Ss_MASK (0x3ull << (63-55)) +#define CXL_PSL_SCNTL_An_Ss_Pending (0x1ull << (63-55)) +#define CXL_PSL_SCNTL_An_Ss_Complete (0x3ull << (63-55)) +/* Suspend Control */ +#define CXL_PSL_SCNTL_An_Sc (0x1ull << (63-63)) + +/* AFU Slice Enable Status (ro) */ +#define CXL_AFU_Cntl_An_ES_MASK (0x7ull << (63-2)) +#define CXL_AFU_Cntl_An_ES_Disabled (0x0ull << (63-2)) +#define CXL_AFU_Cntl_An_ES_Enabled (0x4ull << (63-2)) +/* AFU Slice Enable */ +#define CXL_AFU_Cntl_An_E (0x1ull << (63-3)) +/* AFU Slice Reset status (ro) */ +#define CXL_AFU_Cntl_An_RS_MASK (0x3ull << (63-5)) +#define CXL_AFU_Cntl_An_RS_Pending (0x1ull << (63-5)) +#define CXL_AFU_Cntl_An_RS_Complete (0x2ull << (63-5)) +/* AFU Slice Reset */ +#define CXL_AFU_Cntl_An_RA (0x1ull << (63-7)) + +/****** CXL_SSTP0/1_An ******************************************************/ +/* These top bits are for the segment that CONTAINS the segment table */ +#define CXL_SSTP0_An_B_SHIFT SLB_VSID_SSIZE_SHIFT +#define CXL_SSTP0_An_KS (1ull << (63-2)) +#define CXL_SSTP0_An_KP (1ull << (63-3)) +#define CXL_SSTP0_An_N (1ull << (63-4)) +#define CXL_SSTP0_An_L (1ull << (63-5)) +#define CXL_SSTP0_An_C (1ull << (63-6)) +#define CXL_SSTP0_An_TA (1ull << (63-7)) +#define CXL_SSTP0_An_LP_SHIFT (63-9) /* 2 Bits */ +/* And finally, the virtual address & size of the segment table: */ +#define CXL_SSTP0_An_SegTableSize_SHIFT (63-31) /* 12 Bits */ +#define CXL_SSTP0_An_SegTableSize_MASK \ + (((1ull << 12) - 1) << CXL_SSTP0_An_SegTableSize_SHIFT) +#define CXL_SSTP0_An_STVA_U_MASK ((1ull << (63-49))-1) +#define CXL_SSTP1_An_STVA_L_MASK (~((1ull << (63-55))-1)) +#define CXL_SSTP1_An_V (1ull << (63-63)) + +/****** CXL_PSL_SLBIE_[An] **************************************************/ +/* write: */ +#define CXL_SLBIE_C PPC_BIT(36) /* Class */ +#define CXL_SLBIE_SS PPC_BITMASK(37, 38) /* Segment Size */ +#define CXL_SLBIE_SS_SHIFT PPC_BITLSHIFT(38) +#define CXL_SLBIE_TA PPC_BIT(38) /* Tags Active */ +/* read: */ +#define CXL_SLBIE_MAX PPC_BITMASK(24, 31) +#define CXL_SLBIE_PENDING PPC_BITMASK(56, 63) + +/****** Common to all CXL_TLBIA/SLBIA_[An] **********************************/ +#define CXL_TLB_SLB_P (1ull) /* Pending (read) */ + +/****** Common to all CXL_TLB/SLB_IA/IE_[An] registers **********************/ +#define CXL_TLB_SLB_IQ_ALL (0ull) /* Inv qualifier */ +#define CXL_TLB_SLB_IQ_LPID (1ull) /* Inv qualifier */ +#define CXL_TLB_SLB_IQ_LPIDPID (3ull) /* Inv qualifier */ + +/****** CXL_PSL_AFUSEL ******************************************************/ +#define CXL_PSL_AFUSEL_A (1ull << (63-55)) /* Adapter wide invalidates affect all AFUs */ + +/****** CXL_PSL_DSISR_An ****************************************************/ +#define CXL_PSL_DSISR_An_DS (1ull << (63-0)) /* Segment not found */ +#define CXL_PSL_DSISR_An_DM (1ull << (63-1)) /* PTE not found (See also: M) or protection fault */ +#define CXL_PSL_DSISR_An_ST (1ull << (63-2)) /* Segment Table PTE not found */ +#define CXL_PSL_DSISR_An_UR (1ull << (63-3)) /* AURP PTE not found */ +#define CXL_PSL_DSISR_TRANS (CXL_PSL_DSISR_An_DS | CXL_PSL_DSISR_An_DM | CXL_PSL_DSISR_An_ST | CXL_PSL_DSISR_An_UR) +#define CXL_PSL_DSISR_An_PE (1ull << (63-4)) /* PSL Error (implementation specific) */ +#define CXL_PSL_DSISR_An_AE (1ull << (63-5)) /* AFU Error */ +#define CXL_PSL_DSISR_An_OC (1ull << (63-6)) /* OS Context Warning */ +/* NOTE: Bits 32:63 are undefined if DSISR[DS] = 1 */ +#define CXL_PSL_DSISR_An_M DSISR_NOHPTE /* PTE not found */ +#define CXL_PSL_DSISR_An_P DSISR_PROTFAULT /* Storage protection violation */ +#define CXL_PSL_DSISR_An_A (1ull << (63-37)) /* AFU lock access to write through or cache inhibited storage */ +#define CXL_PSL_DSISR_An_S DSISR_ISSTORE /* Access was afu_wr or afu_zero */ +#define CXL_PSL_DSISR_An_K DSISR_KEYFAULT /* Access not permitted by virtual page class key protection */ + +/****** CXL_PSL_TFC_An ******************************************************/ +#define CXL_PSL_TFC_An_A (1ull << (63-28)) /* Acknowledge non-translation fault */ +#define CXL_PSL_TFC_An_C (1ull << (63-29)) /* Continue (abort transaction) */ +#define CXL_PSL_TFC_An_AE (1ull << (63-30)) /* Restart PSL with address error */ +#define CXL_PSL_TFC_An_R (1ull << (63-31)) /* Restart PSL transaction */ + +/* cxl_process_element->software_status */ +#define CXL_PE_SOFTWARE_STATE_V (1ul << (31 - 0)) /* Valid */ +#define CXL_PE_SOFTWARE_STATE_C (1ul << (31 - 29)) /* Complete */ +#define CXL_PE_SOFTWARE_STATE_S (1ul << (31 - 30)) /* Suspend */ +#define CXL_PE_SOFTWARE_STATE_T (1ul << (31 - 31)) /* Terminate */ + +/* SPA->sw_command_status */ +#define CXL_SPA_SW_CMD_MASK 0xffff000000000000ULL +#define CXL_SPA_SW_CMD_TERMINATE 0x0001000000000000ULL +#define CXL_SPA_SW_CMD_REMOVE 0x0002000000000000ULL +#define CXL_SPA_SW_CMD_SUSPEND 0x0003000000000000ULL +#define CXL_SPA_SW_CMD_RESUME 0x0004000000000000ULL +#define CXL_SPA_SW_CMD_ADD 0x0005000000000000ULL +#define CXL_SPA_SW_CMD_UPDATE 0x0006000000000000ULL +#define CXL_SPA_SW_STATE_MASK 0x0000ffff00000000ULL +#define CXL_SPA_SW_STATE_TERMINATED 0x0000000100000000ULL +#define CXL_SPA_SW_STATE_REMOVED 0x0000000200000000ULL +#define CXL_SPA_SW_STATE_SUSPENDED 0x0000000300000000ULL +#define CXL_SPA_SW_STATE_RESUMED 0x0000000400000000ULL +#define CXL_SPA_SW_STATE_ADDED 0x0000000500000000ULL +#define CXL_SPA_SW_STATE_UPDATED 0x0000000600000000ULL +#define CXL_SPA_SW_PSL_ID_MASK 0x00000000ffff0000ULL +#define CXL_SPA_SW_LINK_MASK 0x000000000000ffffULL + +#define CXL_MAX_SLICES 4 +#define MAX_AFU_MMIO_REGS 3 + +#define CXL_MODE_DEDICATED 0x1 +#define CXL_MODE_DIRECTED 0x2 +#define CXL_MODE_TIME_SLICED 0x4 +#define CXL_SUPPORTED_MODES (CXL_MODE_DEDICATED | CXL_MODE_DIRECTED) + +enum cxl_context_status { + CLOSED, + OPENED, + STARTED +}; + +enum prefault_modes { + CXL_PREFAULT_NONE, + CXL_PREFAULT_WED, + CXL_PREFAULT_ALL, +}; + +struct cxl_sste { + __be64 esid_data; + __be64 vsid_data; +}; + +#define to_cxl_adapter(d) container_of(d, struct cxl, dev) +#define to_cxl_afu(d) container_of(d, struct cxl_afu, dev) + +struct cxl_afu { + irq_hw_number_t psl_hwirq; + irq_hw_number_t serr_hwirq; + unsigned int serr_virq; + void __iomem *p1n_mmio; + void __iomem *p2n_mmio; + phys_addr_t psn_phys; + u64 pp_offset; + u64 pp_size; + void __iomem *afu_desc_mmio; + struct cxl *adapter; + struct device dev; + struct cdev afu_cdev_s, afu_cdev_m, afu_cdev_d; + struct device *chardev_s, *chardev_m, *chardev_d; + struct idr contexts_idr; + struct dentry *debugfs; + spinlock_t contexts_lock; + struct mutex spa_mutex; + spinlock_t afu_cntl_lock; + + /* + * Only the first part of the SPA is used for the process element + * linked list. The only other part that software needs to worry about + * is sw_command_status, which we store a separate pointer to. + * Everything else in the SPA is only used by hardware + */ + struct cxl_process_element *spa; + __be64 *sw_command_status; + unsigned int spa_size; + int spa_order; + int spa_max_procs; + unsigned int psl_virq; + + int pp_irqs; + int irqs_max; + int num_procs; + int max_procs_virtualised; + int slice; + int modes_supported; + int current_mode; + enum prefault |
