diff options
Diffstat (limited to 'drivers/misc/cxl')
| -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 | 508 | ||||
| -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 |
10 files changed, 4453 insertions, 0 deletions
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_modes prefault_mode; + bool psa; + bool pp_psa; + bool enabled; +}; + +/* + * This is a cxl context. If the PSL is in dedicated mode, there will be one + * of these per AFU. If in AFU directed there can be lots of these. + */ +struct cxl_context { + struct cxl_afu *afu; + + /* Problem state MMIO */ + phys_addr_t psn_phys; + u64 psn_size; + + spinlock_t sste_lock; /* Protects segment table entries */ + struct cxl_sste *sstp; + u64 sstp0, sstp1; + unsigned int sst_size, sst_lru; + + wait_queue_head_t wq; + struct pid *pid; + spinlock_t lock; /* Protects pending_irq_mask, pending_fault and fault_addr */ + /* Only used in PR mode */ + u64 process_token; + + unsigned long *irq_bitmap; /* Accessed from IRQ context */ + struct cxl_irq_ranges irqs; + u64 fault_addr; + u64 fault_dsisr; + u64 afu_err; + + /* + * This status and it's lock pretects start and detach context + * from racing. It also prevents detach from racing with + * itself + */ + enum cxl_context_status status; + struct mutex status_mutex; + + + /* XXX: Is it possible to need multiple work items at once? */ + struct work_struct fault_work; + u64 dsisr; + u64 dar; + + struct cxl_process_element *elem; + + int pe; /* process element handle */ + u32 irq_count; + bool pe_inserted; + bool master; + bool kernel; + bool pending_irq; + bool pending_fault; + bool pending_afu_err; +}; + +struct cxl { + void __iomem *p1_mmio; + void __iomem *p2_mmio; + irq_hw_number_t err_hwirq; + unsigned int err_virq; + spinlock_t afu_list_lock; + struct cxl_afu *afu[CXL_MAX_SLICES]; + struct device dev; + struct dentry *trace; + struct dentry *psl_err_chk; + struct dentry *debugfs; + struct bin_attribute cxl_attr; + int adapter_num; + int user_irqs; + u64 afu_desc_off; + u64 afu_desc_size; + u64 ps_off; + u64 ps_size; + u16 psl_rev; + u16 base_image; + u8 vsec_status; + u8 caia_major; + u8 caia_minor; + u8 slices; + bool user_image_loaded; + bool perst_loads_image; + bool perst_select_user; +}; + +int cxl_alloc_one_irq(struct cxl *adapter); +void cxl_release_one_irq(struct cxl *adapter, int hwirq); +int cxl_alloc_irq_ranges(struct cxl_irq_ranges *irqs, struct cxl *adapter, unsigned int num); +void cxl_release_irq_ranges(struct cxl_irq_ranges *irqs, struct cxl *adapter); +int cxl_setup_irq(struct cxl *adapter, unsigned int hwirq, unsigned int virq); + +/* common == phyp + powernv */ +struct cxl_process_element_common { + __be32 tid; + __be32 pid; + __be64 csrp; + __be64 aurp0; + __be64 aurp1; + __be64 sstp0; + __be64 sstp1; + __be64 amr; + u8 reserved3[4]; + __be64 wed; +} __packed; + +/* just powernv */ +struct cxl_process_element { + __be64 sr; + __be64 SPOffset; + __be64 sdr; + __be64 haurp; + __be32 ctxtime; + __be16 ivte_offsets[4]; + __be16 ivte_ranges[4]; + __be32 lpid; + struct cxl_process_element_common common; + __be32 software_state; +} __packed; + +static inline void __iomem *_cxl_p1_addr(struct cxl *cxl, cxl_p1_reg_t reg) +{ + WARN_ON(!cpu_has_feature(CPU_FTR_HVMODE)); + return cxl->p1_mmio + cxl_reg_off(reg); +} + +#define cxl_p1_write(cxl, reg, val) \ + out_be64(_cxl_p1_addr(cxl, reg), val) +#define cxl_p1_read(cxl, reg) \ + in_be64(_cxl_p1_addr(cxl, reg)) + +static inline void __iomem *_cxl_p1n_addr(struct cxl_afu *afu, cxl_p1n_reg_t reg) +{ + WARN_ON(!cpu_has_feature(CPU_FTR_HVMODE)); + return afu->p1n_mmio + cxl_reg_off(reg); +} + +#define cxl_p1n_write(afu, reg, val) \ + out_be64(_cxl_p1n_addr(afu, reg), val) +#define cxl_p1n_read(afu, reg) \ + in_be64(_cxl_p1n_addr(afu, reg)) + +static inline void __iomem *_cxl_p2n_addr(struct cxl_afu *afu, cxl_p2n_reg_t reg) +{ + return afu->p2n_mmio + cxl_reg_off(reg); +} + +#define cxl_p2n_write(afu, reg, val) \ + out_be64(_cxl_p2n_addr(afu, reg), val) +#define cxl_p2n_read(afu, reg) \ + in_be64(_cxl_p2n_addr(afu, reg)) + +struct cxl_calls { + void (*cxl_slbia)(struct mm_struct *mm); + struct module *owner; +}; +int register_cxl_calls(struct cxl_calls *calls); +void unregister_cxl_calls(struct cxl_calls *calls); + +int cxl_alloc_adapter_nr(struct cxl *adapter); +void cxl_remove_adapter_nr(struct cxl *adapter); + +int cxl_file_init(void); +void cxl_file_exit(void); +int cxl_register_adapter(struct cxl *adapter); +int cxl_register_afu(struct cxl_afu *afu); +int cxl_chardev_d_afu_add(struct cxl_afu *afu); +int cxl_chardev_m_afu_add(struct cxl_afu *afu); +int cxl_chardev_s_afu_add(struct cxl_afu *afu); +void cxl_chardev_afu_remove(struct cxl_afu *afu); + +void cxl_context_detach_all(struct cxl_afu *afu); +void cxl_context_free(struct cxl_context *ctx); +void cxl_context_detach(struct cxl_context *ctx); + +int cxl_sysfs_adapter_add(struct cxl *adapter); +void cxl_sysfs_adapter_remove(struct cxl *adapter); +int cxl_sysfs_afu_add(struct cxl_afu *afu); +void cxl_sysfs_afu_remove(struct cxl_afu *afu); +int cxl_sysfs_afu_m_add(struct cxl_afu *afu); +void cxl_sysfs_afu_m_remove(struct cxl_afu *afu); + +int cxl_afu_activate_mode(struct cxl_afu *afu, int mode); +int _cxl_afu_deactivate_mode(struct cxl_afu *afu, int mode); +int cxl_afu_deactivate_mode(struct cxl_afu *afu); +int cxl_afu_select_best_mode(struct cxl_afu *afu); + +unsigned int cxl_map_irq(struct cxl *adapter, irq_hw_number_t hwirq, + irq_handler_t handler, void *cookie); +void cxl_unmap_irq(unsigned int virq, void *cookie); +int cxl_register_psl_irq(struct cxl_afu *afu); +void cxl_release_psl_irq(struct cxl_afu *afu); +int cxl_register_psl_err_irq(struct cxl *adapter); +void cxl_release_psl_err_irq(struct cxl *adapter); +int cxl_register_serr_irq(struct cxl_afu *afu); +void cxl_release_serr_irq(struct cxl_afu *afu); +int afu_register_irqs(struct cxl_context *ctx, u32 count); +void afu_release_irqs(struct cxl_context *ctx); +irqreturn_t cxl_slice_irq_err(int irq, void *data); + +int cxl_debugfs_init(void); +void cxl_debugfs_exit(void); +int cxl_debugfs_adapter_add(struct cxl *adapter); +void cxl_debugfs_adapter_remove(struct cxl *adapter); +int cxl_debugfs_afu_add(struct cxl_afu *afu); +void cxl_debugfs_afu_remove(struct cxl_afu *afu); + +void cxl_handle_fault(struct work_struct *work); +void cxl_prefault(struct cxl_context *ctx, u64 wed); + +struct cxl *get_cxl_adapter(int num); +int cxl_alloc_sst(struct cxl_context *ctx); + +void init_cxl_native(void); + +struct cxl_context *cxl_context_alloc(void); +int cxl_context_init(struct cxl_context *ctx, struct cxl_afu *afu, bool master); +void cxl_context_free(struct cxl_context *ctx); +int cxl_context_iomap(struct cxl_context *ctx, struct vm_area_struct *vma); + +/* This matches the layout of the H_COLLECT_CA_INT_INFO retbuf */ +struct cxl_irq_info { + u64 dsisr; + u64 dar; + u64 dsr; + u32 pid; + u32 tid; + u64 afu_err; + u64 errstat; + u64 padding[3]; /* to match the expected retbuf size for plpar_hcall9 */ +}; + +int cxl_attach_process(struct cxl_context *ctx, bool kernel, u64 wed, + u64 amr); +int cxl_detach_process(struct cxl_context *ctx); + +int cxl_get_irq(struct cxl_context *ctx, struct cxl_irq_info *info); +int cxl_ack_irq(struct cxl_context *ctx, u64 tfc, u64 psl_reset_mask); + +int cxl_check_error(struct cxl_afu *afu); +int cxl_afu_slbia(struct cxl_afu *afu); +int cxl_tlb_slb_invalidate(struct cxl *adapter); +int cxl_afu_disable(struct cxl_afu *afu); +int cxl_afu_reset(struct cxl_afu *afu); +int cxl_psl_purge(struct cxl_afu *afu); + +void cxl_stop_trace(struct cxl *cxl); + +extern struct pci_driver cxl_pci_driver; + +#endif diff --git a/drivers/misc/cxl/debugfs.c b/drivers/misc/cxl/debugfs.c new file mode 100644 index 000000000000..825c412580bc --- /dev/null +++ b/drivers/misc/cxl/debugfs.c @@ -0,0 +1,132 @@ +/* + * 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/debugfs.h> +#include <linux/kernel.h> +#include <linux/slab.h> + +#include "cxl.h" + +static struct dentry *cxl_debugfs; + +void cxl_stop_trace(struct cxl *adapter) +{ + int slice; + + /* Stop the trace */ + cxl_p1_write(adapter, CXL_PSL_TRACE, 0x8000000000000017LL); + + /* Stop the slice traces */ + spin_lock(&adapter->afu_list_lock); + for (slice = 0; slice < adapter->slices; slice++) { + if (adapter->afu[slice]) + cxl_p1n_write(adapter->afu[slice], CXL_PSL_SLICE_TRACE, 0x8000000000000000LL); + } + spin_unlock(&adapter->afu_list_lock); +} + +/* Helpers to export CXL mmaped IO registers via debugfs */ +static int debugfs_io_u64_get(void *data, u64 *val) +{ + *val = in_be64((u64 __iomem *)data); + return 0; +} + +static int debugfs_io_u64_set(void *data, u64 val) +{ + out_be64((u64 __iomem *)data, val); + return 0; +} +DEFINE_SIMPLE_ATTRIBUTE(fops_io_x64, debugfs_io_u64_get, debugfs_io_u64_set, "0x%016llx\n"); + +static struct dentry *debugfs_create_io_x64(const char *name, umode_t mode, + struct dentry *parent, u64 __iomem *value) +{ + return debugfs_create_file(name, mode, parent, (void *)value, &fops_io_x64); +} + +int cxl_debugfs_adapter_add(struct cxl *adapter) +{ + struct dentry *dir; + char buf[32]; + + if (!cxl_debugfs) + return -ENODEV; + + snprintf(buf, 32, "card%i", adapter->adapter_num); + dir = debugfs_create_dir(buf, cxl_debugfs); + if (IS_ERR(dir)) + return PTR_ERR(dir); + adapter->debugfs = dir; + + debugfs_create_io_x64("fir1", S_IRUSR, dir, _cxl_p1_addr(adapter, CXL_PSL_FIR1)); + debugfs_create_io_x64("fir2", S_IRUSR, dir, _cxl_p1_addr(adapter, CXL_PSL_FIR2)); + debugfs_create_io_x64("fir_cntl", S_IRUSR, dir, _cxl_p1_addr(adapter, CXL_PSL_FIR_CNTL)); + debugfs_create_io_x64("err_ivte", S_IRUSR, dir, _cxl_p1_addr(adapter, CXL_PSL_ErrIVTE)); + + debugfs_create_io_x64("trace", S_IRUSR | S_IWUSR, dir, _cxl_p1_addr(adapter, CXL_PSL_TRACE)); + + return 0; +} + +void cxl_debugfs_adapter_remove(struct cxl *adapter) +{ + debugfs_remove_recursive(adapter->debugfs); +} + +int cxl_debugfs_afu_add(struct cxl_afu *afu) +{ + struct dentry *dir; + char buf[32]; + + if (!afu->adapter->debugfs) + return -ENODEV; + + snprintf(buf, 32, "psl%i.%i", afu->adapter->adapter_num, afu->slice); + dir = debugfs_create_dir(buf, afu->adapter->debugfs); + if (IS_ERR(dir)) + return PTR_ERR(dir); + afu->debugfs = dir; + + debugfs_create_io_x64("fir", S_IRUSR, dir, _cxl_p1n_addr(afu, CXL_PSL_FIR_SLICE_An)); + debugfs_create_io_x64("serr", S_IRUSR, dir, _cxl_p1n_addr(afu, CXL_PSL_SERR_An)); + debugfs_create_io_x64("afu_debug", S_IRUSR, dir, _cxl_p1n_addr(afu, CXL_AFU_DEBUG_An)); + debugfs_create_io_x64("sr", S_IRUSR, dir, _cxl_p1n_addr(afu, CXL_PSL_SR_An)); + + debugfs_create_io_x64("dsisr", S_IRUSR, dir, _cxl_p2n_addr(afu, CXL_PSL_DSISR_An)); + debugfs_create_io_x64("dar", S_IRUSR, dir, _cxl_p2n_addr(afu, CXL_PSL_DAR_An)); + debugfs_create_io_x64("sstp0", S_IRUSR, dir, _cxl_p2n_addr(afu, CXL_SSTP0_An)); + debugfs_create_io_x64("sstp1", S_IRUSR, dir, _cxl_p2n_addr(afu, CXL_SSTP1_An)); + debugfs_create_io_x64("err_status", S_IRUSR, dir, _cxl_p2n_addr(afu, CXL_PSL_ErrStat_An)); + + debugfs_create_io_x64("trace", S_IRUSR | S_IWUSR, dir, _cxl_p1n_addr(afu, CXL_PSL_SLICE_TRACE)); + + return 0; +} + +void cxl_debugfs_afu_remove(struct cxl_afu *afu) +{ + debugfs_remove_recursive(afu->debugfs); +} + +int __init cxl_debugfs_init(void) +{ + struct dentry *ent; + ent = debugfs_create_dir("cxl", NULL); + if (IS_ERR(ent)) + return PTR_ERR(ent); + cxl_debugfs = ent; + + return 0; +} + +void cxl_debugfs_exit(void) +{ + debugfs_remove_recursive(cxl_debugfs); +} diff --git a/drivers/misc/cxl/fault.c b/drivers/misc/cxl/fault.c new file mode 100644 index 000000000000..69506ebd4d07 --- /dev/null +++ b/drivers/misc/cxl/fault.c @@ -0,0 +1,291 @@ +/* + * 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/workqueue.h> +#include <linux/sched.h> +#include <linux/pid.h> +#include <linux/mm.h> +#include <linux/moduleparam.h> + +#undef MODULE_PARAM_PREFIX +#define MODULE_PARAM_PREFIX "cxl" "." +#include <asm/current.h> +#include <asm/copro.h> +#include <asm/mmu.h> + +#include "cxl.h" + +static struct cxl_sste* find_free_sste(struct cxl_sste *primary_group, + bool sec_hash, + struct cxl_sste *secondary_group, + unsigned int *lru) +{ + unsigned int i, entry; + struct cxl_sste *sste, *group = primary_group; + + for (i = 0; i < 2; i++) { + for (entry = 0; entry < 8; entry++) { + sste = group + entry; + if (!(be64_to_cpu(sste->esid_data) & SLB_ESID_V)) + return sste; + } + if (!sec_hash) + break; + group = secondary_group; + } + /* Nothing free, select an entry to cast out */ + if (sec_hash && (*lru & 0x8)) + sste = secondary_group + (*lru & 0x7); + else + sste = primary_group + (*lru & 0x7); + *lru = (*lru + 1) & 0xf; + + return sste; +} + +static void cxl_load_segment(struct cxl_context *ctx, struct copro_slb *slb) +{ + /* mask is the group index, we search primary and secondary here. */ + unsigned int mask = (ctx->sst_size >> 7)-1; /* SSTP0[SegTableSize] */ + bool sec_hash = 1; + struct cxl_sste *sste; + unsigned int hash; + unsigned long flags; + + + sec_hash = !!(cxl_p1n_read(ctx->afu, CXL_PSL_SR_An) & CXL_PSL_SR_An_SC); + + if (slb->vsid & SLB_VSID_B_1T) + hash = (slb->esid >> SID_SHIFT_1T) & mask; + else /* 256M */ + hash = (slb->esid >> SID_SHIFT) & mask; + + spin_lock_irqsave(&ctx->sste_lock, flags); + sste = find_free_sste(ctx->sstp + (hash << 3), sec_hash, + ctx->sstp + ((~hash & mask) << 3), &ctx->sst_lru); + + pr_devel("CXL Populating SST[%li]: %#llx %#llx\n", + sste - ctx->sstp, slb->vsid, slb->esid); + + sste->vsid_data = cpu_to_be64(slb->vsid); + sste->esid_data = cpu_to_be64(slb->esid); + spin_unlock_irqrestore(&ctx->sste_lock, flags); +} + +static int cxl_fault_segment(struct cxl_context *ctx, struct mm_struct *mm, + u64 ea) +{ + struct copro_slb slb = {0,0}; + int rc; + + if (!(rc = copro_calculate_slb(mm, ea, &slb))) { + cxl_load_segment(ctx, &slb); + } + + return rc; +} + +static void cxl_ack_ae(struct cxl_context *ctx) +{ + unsigned long flags; + + cxl_ack_irq(ctx, CXL_PSL_TFC_An_AE, 0); + + spin_lock_irqsave(&ctx->lock, flags); + ctx->pending_fault = true; + ctx->fault_addr = ctx->dar; + ctx->fault_dsisr = ctx->dsisr; + spin_unlock_irqrestore(&ctx->lock, flags); + + wake_up_all(&ctx->wq); +} + +static int cxl_handle_segment_miss(struct cxl_context *ctx, + struct mm_struct *mm, u64 ea) +{ + int rc; + + pr_devel("CXL interrupt: Segment fault pe: %i ea: %#llx\n", ctx->pe, ea); + + if ((rc = cxl_fault_segment(ctx, mm, ea))) + cxl_ack_ae(ctx); + else { + + mb(); /* Order seg table write to TFC MMIO write */ + cxl_ack_irq(ctx, CXL_PSL_TFC_An_R, 0); + } + + return IRQ_HANDLED; +} + +static void cxl_handle_page_fault(struct cxl_context *ctx, + struct mm_struct *mm, u64 dsisr, u64 dar) +{ + unsigned flt = 0; + int result; + unsigned long access, flags; + + if ((result = copro_handle_mm_fault(mm, dar, dsisr, &flt))) { + pr_devel("copro_handle_mm_fault failed: %#x\n", result); + return cxl_ack_ae(ctx); + } + + /* + * update_mmu_cache() will not have loaded the hash since current->trap + * is not a 0x400 or 0x300, so just call hash_page_mm() here. + */ + access = _PAGE_PRESENT; + if (dsisr & CXL_PSL_DSISR_An_S) + access |= _PAGE_RW; + if ((!ctx->kernel) || ~(dar & (1ULL << 63))) + access |= _PAGE_USER; + local_irq_save(flags); + hash_page_mm(mm, dar, access, 0x300); + local_irq_restore(flags); + + pr_devel("Page fault successfully handled for pe: %i!\n", ctx->pe); + cxl_ack_irq(ctx, CXL_PSL_TFC_An_R, 0); +} + +void cxl_handle_fault(struct work_struct *fault_work) +{ + struct cxl_context *ctx = + container_of(fault_work, struct cxl_context, fault_work); + u64 dsisr = ctx->dsisr; + u64 dar = ctx->dar; + struct task_struct *task; + struct mm_struct *mm; + + if (cxl_p2n_read(ctx->afu, CXL_PSL_DSISR_An) != dsisr || + cxl_p2n_read(ctx->afu, CXL_PSL_DAR_An) != dar || + cxl_p2n_read(ctx->afu, CXL_PSL_PEHandle_An) != ctx->pe) { + /* Most likely explanation is harmless - a dedicated process + * has detached and these were cleared by the PSL purge, but + * warn about it just in case */ + dev_notice(&ctx->afu->dev, "cxl_handle_fault: Translation fault regs changed\n"); + return; + } + + pr_devel("CXL BOTTOM HALF handling fault for afu pe: %i. " + "DSISR: %#llx DAR: %#llx\n", ctx->pe, dsisr, dar); + + if (!(task = get_pid_task(ctx->pid, PIDTYPE_PID))) { + pr_devel("cxl_handle_fault unable to get task %i\n", + pid_nr(ctx->pid)); + cxl_ack_ae(ctx); + return; + } + if (!(mm = get_task_mm(task))) { + pr_devel("cxl_handle_fault unable to get mm %i\n", + pid_nr(ctx->pid)); + cxl_ack_ae(ctx); + goto out; + } + + if (dsisr & CXL_PSL_DSISR_An_DS) + cxl_handle_segment_miss(ctx, mm, dar); + else if (dsisr & CXL_PSL_DSISR_An_DM) + cxl_handle_page_fault(ctx, mm, dsisr, dar); + else + WARN(1, "cxl_handle_fault has nothing to handle\n"); + + mmput(mm); +out: + put_task_struct(task); +} + +static void cxl_prefault_one(struct cxl_context *ctx, u64 ea) +{ + int rc; + struct task_struct *task; + struct mm_struct *mm; + + if (!(task = get_pid_task(ctx->pid, PIDTYPE_PID))) { + pr_devel("cxl_prefault_one unable to get task %i\n", + pid_nr(ctx->pid)); + return; + } + if (!(mm = get_task_mm(task))) { + pr_devel("cxl_prefault_one unable to get mm %i\n", + pid_nr(ctx->pid)); + put_task_struct(task); + return; + } + + rc = cxl_fault_segment(ctx, mm, ea); + + mmput(mm); + put_task_struct(task); +} + +static u64 next_segment(u64 ea, u64 vsid) +{ + if (vsid & SLB_VSID_B_1T) + ea |= (1ULL << 40) - 1; + else + ea |= (1ULL << 28) - 1; + + return ea + 1; +} + +static void cxl_prefault_vma(struct cxl_context *ctx) +{ + u64 ea, last_esid = 0; + struct copro_slb slb; + struct vm_area_struct *vma; + int rc; + struct task_struct *task; + struct mm_struct *mm; + + if (!(task = get_pid_task(ctx->pid, PIDTYPE_PID))) { + pr_devel("cxl_prefault_vma unable to get task %i\n", + pid_nr(ctx->pid)); + return; + } + if (!(mm = get_task_mm(task))) { + pr_devel("cxl_prefault_vm unable to get mm %i\n", + pid_nr(ctx->pid)); + goto out1; + } + + down_read(&mm->mmap_sem); + for (vma = mm->mmap; vma; vma = vma->vm_next) { + for (ea = vma->vm_start; ea < vma->vm_end; + ea = next_segment(ea, slb.vsid)) { + rc = copro_calculate_slb(mm, ea, &slb); + if (rc) + continue; + + if (last_esid == slb.esid) + continue; + + cxl_load_segment(ctx, &slb); + last_esid = slb.esid; + } + } + up_read(&mm->mmap_sem); + + mmput(mm); +out1: + put_task_struct(task); +} + +void cxl_prefault(struct cxl_context *ctx, u64 wed) +{ + switch (ctx->afu->prefault_mode) { + case CXL_PREFAULT_WED: + cxl_prefault_one(ctx, wed); + break; + case CXL_PREFAULT_ALL: + cxl_prefault_vma(ctx); + break; + default: + break; + } +} diff --git a/drivers/misc/cxl/file.c b/drivers/misc/cxl/file.c new file mode 100644 index 000000000000..847b7e646a7e --- /dev/null +++ b/drivers/misc/cxl/file.c @@ -0,0 +1,508 @@ +/* + * 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/spinlock.h> +#include <linux/module.h> +#include <linux/export.h> +#include <linux/kernel.h> +#include <linux/bitmap.h> +#include <linux/sched.h> +#include <linux/poll.h> +#include <linux/pid.h> +#include <linux/fs.h> +#include <linux/mm.h> +#include <linux/slab.h> +#include <asm/cputable.h> +#include <asm/current.h> +#include <asm/copro.h> + +#include "cxl.h" + +#define CXL_NUM_MINORS 256 /* Total to reserve */ +#define CXL_DEV_MINORS 13 /* 1 control + 4 AFUs * 3 (dedicated/master/shared) */ + +#define CXL_CARD_MINOR(adapter) (adapter->adapter_num * CXL_DEV_MINORS) +#define CXL_AFU_MINOR_D(afu) (CXL_CARD_MINOR(afu->adapter) + 1 + (3 * afu->slice)) +#define CXL_AFU_MINOR_M(afu) (CXL_AFU_MINOR_D(afu) + 1) +#define CXL_AFU_MINOR_S(afu) (CXL_AFU_MINOR_D(afu) + 2) +#define CXL_AFU_MKDEV_D(afu) MKDEV(MAJOR(cxl_dev), CXL_AFU_MINOR_D(afu)) +#define CXL_AFU_MKDEV_M(afu) MKDEV(MAJOR(cxl_dev), CXL_AFU_MINOR_M(afu)) +#define CXL_AFU_MKDEV_S(afu) MKDEV(MAJOR(cxl_dev), CXL_AFU_MINOR_S(afu)) + +#define CXL_DEVT_ADAPTER(dev) (MINOR(dev) / CXL_DEV_MINORS) +#define CXL_DEVT_AFU(dev) ((MINOR(dev) % CXL_DEV_MINORS - 1) / 3) + +#define CXL_DEVT_IS_CARD(dev) (MINOR(dev) % CXL_DEV_MINORS == 0) + +static dev_t cxl_dev; + +static struct class *cxl_class; + +static int __afu_open(struct inode *inode, struct file *file, bool master) +{ + struct cxl *adapter; + struct cxl_afu *afu; + struct cxl_context *ctx; + int adapter_num = CXL_DEVT_ADAPTER(inode->i_rdev); + int slice = CXL_DEVT_AFU(inode->i_rdev); + int rc = -ENODEV; + + pr_devel("afu_open afu%i.%i\n", slice, adapter_num); + + if (!(adapter = get_cxl_adapter(adapter_num))) + return -ENODEV; + + if (slice > adapter->slices) + goto err_put_adapter; + + spin_lock(&adapter->afu_list_lock); + if (!(afu = adapter->afu[slice])) { + spin_unlock(&adapter->afu_list_lock); + goto err_put_adapter; + } + get_device(&afu->dev); + spin_unlock(&adapter->afu_list_lock); + + if (!afu->current_mode) + goto err_put_afu; + + if (!(ctx = cxl_context_alloc())) { + rc = -ENOMEM; + goto err_put_afu; + } + + if ((rc = cxl_context_init(ctx, afu, master))) + goto err_put_afu; + + pr_devel("afu_open pe: %i\n", ctx->pe); + file->private_data = ctx; + cxl_ctx_get(); + + /* Our ref on the AFU will now hold the adapter */ + put_device(&adapter->dev); + + return 0; + +err_put_afu: + put_device(&afu->dev); +err_put_adapter: + put_device(&adapter->dev); + return rc; +} +static int afu_open(struct inode *inode, struct file *file) +{ + return __afu_open(inode, file, false); +} + +static int afu_master_open(struct inode *inode, struct file *file) +{ + return __afu_open(inode, file, true); +} + +static int afu_release(struct inode *inode, struct file *file) +{ + struct cxl_context *ctx = file->private_data; + + pr_devel("%s: closing cxl file descriptor. pe: %i\n", + __func__, ctx->pe); + cxl_context_detach(ctx); + + put_device(&ctx->afu->dev); + + /* + * At this this point all bottom halfs have finished and we should be + * getting no more IRQs from the hardware for this context. Once it's + * removed from the IDR (and RCU synchronised) it's safe to free the + * sstp and context. + */ + cxl_context_free(ctx); + + cxl_ctx_put(); + return 0; +} + +static long afu_ioctl_start_work(struct cxl_context *ctx, + struct cxl_ioctl_start_work __user *uwork) +{ + struct cxl_ioctl_start_work work; + u64 amr = 0; + int rc; + + pr_devel("%s: pe: %i\n", __func__, ctx->pe); + + mutex_lock(&ctx->status_mutex); + if (ctx->status != OPENED) { + rc = -EIO; + goto out; + } + + if (copy_from_user(&work, uwork, + sizeof(struct cxl_ioctl_start_work))) { + rc = -EFAULT; + goto out; + } + + /* + * if any of the reserved fields are set or any of the unused + * flags are set it's invalid + */ + if (work.reserved1 || work.reserved2 || work.reserved3 || + work.reserved4 || work.reserved5 || work.reserved6 || + (work.flags & ~CXL_START_WORK_ALL)) { + rc = -EINVAL; + goto out; + } + + if (!(work.flags & CXL_START_WORK_NUM_IRQS)) + work.num_interrupts = ctx->afu->pp_irqs; + else if ((work.num_interrupts < ctx->afu->pp_irqs) || + (work.num_interrupts > ctx->afu->irqs_max)) { + rc = -EINVAL; + goto out; + } + if ((rc = afu_register_irqs(ctx, work.num_interrupts))) + goto out; + + if (work.flags & CXL_START_WORK_AMR) + amr = work.amr & mfspr(SPRN_UAMOR); + + /* + * We grab the PID here and not in the file open to allow for the case + * where a process (master, some daemon, etc) has opened the chardev on + * behalf of another process, so the AFU's mm gets bound to the process + * that performs this ioctl and not the process that opened the file. + */ + ctx->pid = get_pid(get_task_pid(current, PIDTYPE_PID)); + + if ((rc = cxl_attach_process(ctx, false, work.work_element_descriptor, + amr))) + goto out; + + ctx->status = STARTED; + rc = 0; +out: + mutex_unlock(&ctx->status_mutex); + return rc; +} +static long afu_ioctl_process_element(struct cxl_context *ctx, + int __user *upe) +{ + pr_devel("%s: pe: %i\n", __func__, ctx->pe); + + if (copy_to_user(upe, &ctx->pe, sizeof(__u32))) + return -EFAULT; + + return 0; +} + +static long afu_ioctl(struct file *file, unsigned int cmd, unsigned long arg) +{ + struct cxl_context *ctx = file->private_data; + + if (ctx->status == CLOSED) + return -EIO; + + pr_devel("afu_ioctl\n"); + switch (cmd) { + case CXL_IOCTL_START_WORK: + return afu_ioctl_start_work(ctx, (struct cxl_ioctl_start_work __user *)arg); + case CXL_IOCTL_GET_PROCESS_ELEMENT: + return afu_ioctl_process_element(ctx, (__u32 __user *)arg); + } + return -EINVAL; +} + +static long afu_compat_ioctl(struct file *file, unsigned int cmd, + unsigned long arg) +{ + return afu_ioctl(file, cmd, arg); +} + +static int afu_mmap(struct file *file, struct vm_area_struct *vm) +{ + struct cxl_context *ctx = file->private_data; + + /* AFU must be started before we can MMIO */ + if (ctx->status != STARTED) + return -EIO; + + return cxl_context_iomap(ctx, vm); +} + +static unsigned int afu_poll(struct file *file, struct poll_table_struct *poll) +{ + struct cxl_context *ctx = file->private_data; + int mask = 0; + unsigned long flags; + + + poll_wait(file, &ctx->wq, poll); + + pr_devel("afu_poll wait done pe: %i\n", ctx->pe); + + spin_lock_irqsave(&ctx->lock, flags); + if (ctx->pending_irq || ctx->pending_fault || + ctx->pending_afu_err) + mask |= POLLIN | POLLRDNORM; + else if (ctx->status == CLOSED) + /* Only error on closed when there are no futher events pending + */ + mask |= POLLERR; + spin_unlock_irqrestore(&ctx->lock, flags); + + pr_devel("afu_poll pe: %i returning %#x\n", ctx->pe, mask); + + return mask; +} + +static inline int ctx_event_pending(struct cxl_context *ctx) +{ + return (ctx->pending_irq || ctx->pending_fault || + ctx->pending_afu_err || (ctx->status == CLOSED)); +} + +static ssize_t afu_read(struct file *file, char __user *buf, size_t count, + loff_t *off) +{ + struct cxl_context *ctx = file->private_data; + struct cxl_event event; + unsigned long flags; + DEFINE_WAIT(wait); + + if (count < CXL_READ_MIN_SIZE) + return -EINVAL; + + spin_lock_irqsave(&ctx->lock, flags); + + for (;;) { + prepare_to_wait(&ctx->wq, &wait, TASK_INTERRUPTIBLE); + if (ctx_event_pending(ctx)) + break; + + spin_unlock_irqrestore(&ctx->lock, flags); + if (file->f_flags & O_NONBLOCK) + return -EAGAIN; + + if (signal_pending(current)) + return -ERESTARTSYS; + + pr_devel("afu_read going to sleep...\n"); + schedule(); + pr_devel("afu_read woken up\n"); + spin_lock_irqsave(&ctx->lock, flags); + } + + finish_wait(&ctx->wq, &wait); + + memset(&event, 0, sizeof(event)); + event.header.process_element = ctx->pe; + event.header.size = sizeof(struct cxl_event_header); + if (ctx->pending_irq) { + pr_devel("afu_read delivering AFU interrupt\n"); + event.header.size += sizeof(struct cxl_event_afu_interrupt); + event.header.type = CXL_EVENT_AFU_INTERRUPT; + event.irq.irq = find_first_bit(ctx->irq_bitmap, ctx->irq_count) + 1; + clear_bit(event.irq.irq - 1, ctx->irq_bitmap); + if (bitmap_empty(ctx->irq_bitmap, ctx->irq_count)) + ctx->pending_irq = false; + } else if (ctx->pending_fault) { + pr_devel("afu_read delivering data storage fault\n"); + event.header.size += sizeof(struct cxl_event_data_storage); + event.header.type = CXL_EVENT_DATA_STORAGE; + event.fault.addr = ctx->fault_addr; + event.fault.dsisr = ctx->fault_dsisr; + ctx->pending_fault = false; + } else if (ctx->pending_afu_err) { + pr_devel("afu_read delivering afu error\n"); + event.header.size += sizeof(struct cxl_event_afu_error); + event.header.type = CXL_EVENT_AFU_ERROR; + event.afu_error.error = ctx->afu_err; + ctx->pending_afu_err = false; + } else if (ctx->status == CLOSED) { + pr_devel("afu_read fatal error\n"); + spin_unlock_irqrestore(&ctx->lock, flags); + return -EIO; + } else + WARN(1, "afu_read must be buggy\n"); + + spin_unlock_irqrestore(&ctx->lock, flags); + + if (copy_to_user(buf, &event, event.header.size)) + return -EFAULT; + return event.header.size; +} + +static const struct file_operations afu_fops = { + .owner = THIS_MODULE, + .open = afu_open, + .poll = afu_poll, + .read = afu_read, + .release = afu_release, + .unlocked_ioctl = afu_ioctl, + .compat_ioctl = afu_compat_ioctl, + .mmap = afu_mmap, +}; + +static const struct file_operations afu_master_fops = { + .owner = THIS_MODULE, + .open = afu_master_open, + .poll = afu_poll, + .read = afu_read, + .release = afu_release, + .unlocked_ioctl = afu_ioctl, + .compat_ioctl = afu_compat_ioctl, + .mmap = afu_mmap, +}; + + +static char *cxl_devnode(struct device *dev, umode_t *mode) +{ + if (CXL_DEVT_IS_CARD(dev->devt)) { + /* + * These minor numbers will eventually be used to program the + * PSL and AFUs once we have dynamic reprogramming support + */ + return NULL; + } + return kasprintf(GFP_KERNEL, "cxl/%s", dev_name(dev)); +} + +extern struct class *cxl_class; + +static int cxl_add_chardev(struct cxl_afu *afu, dev_t devt, struct cdev *cdev, + struct device **chardev, char *postfix, char *desc, + const struct file_operations *fops) +{ + struct device *dev; + int rc; + + cdev_init(cdev, fops); + if ((rc = cdev_add(cdev, devt, 1))) { + dev_err(&afu->dev, "Unable to add %s chardev: %i\n", desc, rc); + return rc; + } + + dev = device_create(cxl_class, &afu->dev, devt, afu, + "afu%i.%i%s", afu->adapter->adapter_num, afu->slice, postfix); + if (IS_ERR(dev)) { + dev_err(&afu->dev, "Unable to create %s chardev in sysfs: %i\n", desc, rc); + rc = PTR_ERR(dev); + goto err; + } + + *chardev = dev; + + return 0; +err: + cdev_del(cdev); + return rc; +} + +int cxl_chardev_d_afu_add(struct cxl_afu *afu) +{ + return cxl_add_chardev(afu, CXL_AFU_MKDEV_D(afu), &afu->afu_cdev_d, + &afu->chardev_d, "d", "dedicated", + &afu_master_fops); /* Uses master fops */ +} + +int cxl_chardev_m_afu_add(struct cxl_afu *afu) +{ + return cxl_add_chardev(afu, CXL_AFU_MKDEV_M(afu), &afu->afu_cdev_m, + &afu->chardev_m, "m", "master", + &afu_master_fops); +} + +int cxl_chardev_s_afu_add(struct cxl_afu *afu) +{ + return cxl_add_chardev(afu, CXL_AFU_MKDEV_S(afu), &afu->afu_cdev_s, + &afu->chardev_s, "s", "shared", + &afu_fops); +} + +void cxl_chardev_afu_remove(struct cxl_afu *afu) +{ + if (afu->chardev_d) { + cdev_del(&afu->afu_cdev_d); + device_unregister(afu->chardev_d); + afu->chardev_d = NULL; + } + if (afu->chardev_m) { + cdev_del(&afu->afu_cdev_m); + device_unregister(afu->chardev_m); + afu->chardev_m = NULL; + } + if (afu->chardev_s) { + cdev_del(&afu->afu_cdev_s); + device_unregister(afu->chardev_s); + afu->chardev_s = NULL; + } +} + +int cxl_register_afu(struct cxl_afu *afu) +{ + afu->dev.class = cxl_class; + + return device_register(&afu->dev); +} + +int cxl_register_adapter(struct cxl *adapter) +{ + adapter->dev.class = cxl_class; + + /* + * Future: When we support dynamically reprogramming the PSL & AFU we + * will expose the interface to do that via a chardev: + * adapter->dev.devt = CXL_CARD_MKDEV(adapter); + */ + + return device_register(&adapter->dev); +} + +int __init cxl_file_init(void) +{ + int rc; + + /* + * If these change we really need to update API. Either change some + * flags or update API version number CXL_API_VERSION. + */ + BUILD_BUG_ON(CXL_API_VERSION != 1); + BUILD_BUG_ON(sizeof(struct cxl_ioctl_start_work) != 64); + BUILD_BUG_ON(sizeof(struct cxl_event_header) != 8); + BUILD_BUG_ON(sizeof(struct cxl_event_afu_interrupt) != 8); + BUILD_BUG_ON(sizeof(struct cxl_event_data_storage) != 32); + BUILD_BUG_ON(sizeof(struct cxl_event_afu_error) != 16); + + if ((rc = alloc_chrdev_region(&cxl_dev, 0, CXL_NUM_MINORS, "cxl"))) { + pr_err("Unable to allocate CXL major number: %i\n", rc); + return rc; + } + + pr_devel("CXL device allocated, MAJOR %i\n", MAJOR(cxl_dev)); + + cxl_class = class_create(THIS_MODULE, "cxl"); + if (IS_ERR(cxl_class)) { + pr_err("Unable to create CXL class\n"); + rc = PTR_ERR(cxl_class); + goto err; + } + cxl_class->devnode = cxl_devnode; + + return 0; + +err: + unregister_chrdev_region(cxl_dev, CXL_NUM_MINORS); + return rc; +} + +void cxl_file_exit(void) +{ + unregister_chrdev_region(cxl_dev, CXL_NUM_MINORS); + class_destroy(cxl_class); +} diff --git a/drivers/misc/cxl/irq.c b/drivers/misc/cxl/irq.c new file mode 100644 index 000000000000..336020c8e1af --- /dev/null +++ b/drivers/misc/cxl/irq.c @@ -0,0 +1,402 @@ +/* + * 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/interrupt.h> +#include <linux/workqueue.h> +#include <linux/sched.h> +#include <linux/wait.h> +#include <linux/slab.h> +#include <linux/pid.h> +#include <asm/cputable.h> +#include <misc/cxl.h> + +#include "cxl.h" + +/* XXX: This is implementation specific */ +static irqreturn_t handle_psl_slice_error(struct cxl_context *ctx, u64 dsisr, u64 errstat) +{ + u64 fir1, fir2, fir_slice, serr, afu_debug; + + fir1 = cxl_p1_read(ctx->afu->adapter, CXL_PSL_FIR1); + fir2 = cxl_p1_read(ctx->afu->adapter, CXL_PSL_FIR2); + fir_slice = cxl_p1n_read(ctx->afu, CXL_PSL_FIR_SLICE_An); + serr = cxl_p1n_read(ctx->afu, CXL_PSL_SERR_An); + afu_debug = cxl_p1n_read(ctx->afu, CXL_AFU_DEBUG_An); + + dev_crit(&ctx->afu->dev, "PSL ERROR STATUS: 0x%.16llx\n", errstat); + dev_crit(&ctx->afu->dev, "PSL_FIR1: 0x%.16llx\n", fir1); + dev_crit(&ctx->afu->dev, "PSL_FIR2: 0x%.16llx\n", fir2); + dev_crit(&ctx->afu->dev, "PSL_SERR_An: 0x%.16llx\n", serr); + dev_crit(&ctx->afu->dev, "PSL_FIR_SLICE_An: 0x%.16llx\n", fir_slice); + dev_crit(&ctx->afu->dev, "CXL_PSL_AFU_DEBUG_An: 0x%.16llx\n", afu_debug); + + dev_crit(&ctx->afu->dev, "STOPPING CXL TRACE\n"); + cxl_stop_trace(ctx->afu->adapter); + + return cxl_ack_irq(ctx, 0, errstat); +} + +irqreturn_t cxl_slice_irq_err(int irq, void *data) +{ + struct cxl_afu *afu = data; + u64 fir_slice, errstat, serr, afu_debug; + + WARN(irq, "CXL SLICE ERROR interrupt %i\n", irq); + + serr = cxl_p1n_read(afu, CXL_PSL_SERR_An); + fir_slice = cxl_p1n_read(afu, CXL_PSL_FIR_SLICE_An); + errstat = cxl_p2n_read(afu, CXL_PSL_ErrStat_An); + afu_debug = cxl_p1n_read(afu, CXL_AFU_DEBUG_An); + dev_crit(&afu->dev, "PSL_SERR_An: 0x%.16llx\n", serr); + dev_crit(&afu->dev, "PSL_FIR_SLICE_An: 0x%.16llx\n", fir_slice); + dev_crit(&afu->dev, "CXL_PSL_ErrStat_An: 0x%.16llx\n", errstat); + dev_crit(&afu->dev, "CXL_PSL_AFU_DEBUG_An: 0x%.16llx\n", afu_debug); + + cxl_p1n_write(afu, CXL_PSL_SERR_An, serr); + + return IRQ_HANDLED; +} + +static irqreturn_t cxl_irq_err(int irq, void *data) +{ + struct cxl *adapter = data; + u64 fir1, fir2, err_ivte; + + WARN(1, "CXL ERROR interrupt %i\n", irq); + + err_ivte = cxl_p1_read(adapter, CXL_PSL_ErrIVTE); + dev_crit(&adapter->dev, "PSL_ErrIVTE: 0x%.16llx\n", err_ivte); + + dev_crit(&adapter->dev, "STOPPING CXL TRACE\n"); + cxl_stop_trace(adapter); + + fir1 = cxl_p1_read(adapter, CXL_PSL_FIR1); + fir2 = cxl_p1_read(adapter, CXL_PSL_FIR2); + + dev_crit(&adapter->dev, "PSL_FIR1: 0x%.16llx\nPSL_FIR2: 0x%.16llx\n", fir1, fir2); + + return IRQ_HANDLED; +} + +static irqreturn_t schedule_cxl_fault(struct cxl_context *ctx, u64 dsisr, u64 dar) +{ + ctx->dsisr = dsisr; + ctx->dar = dar; + schedule_work(&ctx->fault_work); + return IRQ_HANDLED; +} + +static irqreturn_t cxl_irq(int irq, void *data) +{ + struct cxl_context *ctx = data; + struct cxl_irq_info irq_info; + u64 dsisr, dar; + int result; + + if ((result = cxl_get_irq(ctx, &irq_info))) { + WARN(1, "Unable to get CXL IRQ Info: %i\n", result); + return IRQ_HANDLED; + } + + dsisr = irq_info.dsisr; + dar = irq_info.dar; + + pr_devel("CXL interrupt %i for afu pe: %i DSISR: %#llx DAR: %#llx\n", irq, ctx->pe, dsisr, dar); + + if (dsisr & CXL_PSL_DSISR_An_DS) { + /* + * We don't inherently need to sleep to handle this, but we do + * need to get a ref to the task's mm, which we can't do from + * irq context without the potential for a deadlock since it + * takes the task_lock. An alternate option would be to keep a + * reference to the task's mm the entire time it has cxl open, + * but to do that we need to solve the issue where we hold a + * ref to the mm, but the mm can hold a ref to the fd after an + * mmap preventing anything from being cleaned up. + */ + pr_devel("Scheduling segment miss handling for later pe: %i\n", ctx->pe); + return schedule_cxl_fault(ctx, dsisr, dar); + } + + if (dsisr & CXL_PSL_DSISR_An_M) + pr_devel("CXL interrupt: PTE not found\n"); + if (dsisr & CXL_PSL_DSISR_An_P) + pr_devel("CXL interrupt: Storage protection violation\n"); + if (dsisr & CXL_PSL_DSISR_An_A) + pr_devel("CXL interrupt: AFU lock access to write through or cache inhibited storage\n"); + if (dsisr & CXL_PSL_DSISR_An_S) + pr_devel("CXL interrupt: Access was afu_wr or afu_zero\n"); + if (dsisr & CXL_PSL_DSISR_An_K) + pr_devel("CXL interrupt: Access not permitted by virtual page class key protection\n"); + + if (dsisr & CXL_PSL_DSISR_An_DM) { + /* + * In some cases we might be able to handle the fault + * immediately if hash_page would succeed, but we still need + * the task's mm, which as above we can't get without a lock + */ + pr_devel("Scheduling page fault handling for later pe: %i\n", ctx->pe); + return schedule_cxl_fault(ctx, dsisr, dar); + } + if (dsisr & CXL_PSL_DSISR_An_ST) + WARN(1, "CXL interrupt: Segment Table PTE not found\n"); + if (dsisr & CXL_PSL_DSISR_An_UR) + pr_devel("CXL interrupt: AURP PTE not found\n"); + if (dsisr & CXL_PSL_DSISR_An_PE) + return handle_psl_slice_error(ctx, dsisr, irq_info.errstat); + if (dsisr & CXL_PSL_DSISR_An_AE) { + pr_devel("CXL interrupt: AFU Error %.llx\n", irq_info.afu_err); + + if (ctx->pending_afu_err) { + /* + * This shouldn't happen - the PSL treats these errors + * as fatal and will have reset the AFU, so there's not + * much point buffering multiple AFU errors. + * OTOH if we DO ever see a storm of these come in it's + * probably best that we log them somewhere: + */ + dev_err_ratelimited(&ctx->afu->dev, "CXL AFU Error " + "undelivered to pe %i: %.llx\n", + ctx->pe, irq_info.afu_err); + } else { + spin_lock(&ctx->lock); + ctx->afu_err = irq_info.afu_err; + ctx->pending_afu_err = 1; + spin_unlock(&ctx->lock); + + wake_up_all(&ctx->wq); + } + + cxl_ack_irq(ctx, CXL_PSL_TFC_An_A, 0); + } + if (dsisr & CXL_PSL_DSISR_An_OC) + pr_devel("CXL interrupt: OS Context Warning\n"); + + WARN(1, "Unhandled CXL PSL IRQ\n"); + return IRQ_HANDLED; +} + +static irqreturn_t cxl_irq_multiplexed(int irq, void *data) +{ + struct cxl_afu *afu = data; + struct cxl_context *ctx; + int ph = cxl_p2n_read(afu, CXL_PSL_PEHandle_An) & 0xffff; + int ret; + + rcu_read_lock(); + ctx = idr_find(&afu->contexts_idr, ph); + if (ctx) { + ret = cxl_irq(irq, ctx); + rcu_read_unlock(); + return ret; + } + rcu_read_unlock(); + + WARN(1, "Unable to demultiplex CXL PSL IRQ\n"); + return IRQ_HANDLED; +} + +static irqreturn_t cxl_irq_afu(int irq, void *data) +{ + struct cxl_context *ctx = data; + irq_hw_number_t hwirq = irqd_to_hwirq(irq_get_irq_data(irq)); + int irq_off, afu_irq = 1; + __u16 range; + int r; + + for (r = 1; r < CXL_IRQ_RANGES; r++) { + irq_off = hwirq - ctx->irqs.offset[r]; + range = ctx->irqs.range[r]; + if (irq_off >= 0 && irq_off < range) { + afu_irq += irq_off; + break; + } + afu_irq += range; + } + if (unlikely(r >= CXL_IRQ_RANGES)) { + WARN(1, "Recieved AFU IRQ out of range for pe %i (virq %i hwirq %lx)\n", + ctx->pe, irq, hwirq); + return IRQ_HANDLED; + } + + pr_devel("Received AFU interrupt %i for pe: %i (virq %i hwirq %lx)\n", + afu_irq, ctx->pe, irq, hwirq); + + if (unlikely(!ctx->irq_bitmap)) { + WARN(1, "Recieved AFU IRQ for context with no IRQ bitmap\n"); + return IRQ_HANDLED; + } + spin_lock(&ctx->lock); + set_bit(afu_irq - 1, ctx->irq_bitmap); + ctx->pending_irq = true; + spin_unlock(&ctx->lock); + + wake_up_all(&ctx->wq); + + return IRQ_HANDLED; +} + +unsigned int cxl_map_irq(struct cxl *adapter, irq_hw_number_t hwirq, + irq_handler_t handler, void *cookie) +{ + unsigned int virq; + int result; + + /* IRQ Domain? */ + virq = irq_create_mapping(NULL, hwirq); + if (!virq) { + dev_warn(&adapter->dev, "cxl_map_irq: irq_create_mapping failed\n"); + return 0; + } + + cxl_setup_irq(adapter, hwirq, virq); + + pr_devel("hwirq %#lx mapped to virq %u\n", hwirq, virq); + + result = request_irq(virq, handler, 0, "cxl", cookie); + if (result) { + dev_warn(&adapter->dev, "cxl_map_irq: request_irq failed: %i\n", result); + return 0; + } + + return virq; +} + +void cxl_unmap_irq(unsigned int virq, void *cookie) +{ + free_irq(virq, cookie); + irq_dispose_mapping(virq); +} + +static int cxl_register_one_irq(struct cxl *adapter, + irq_handler_t handler, + void *cookie, + irq_hw_number_t *dest_hwirq, + unsigned int *dest_virq) +{ + int hwirq, virq; + + if ((hwirq = cxl_alloc_one_irq(adapter)) < 0) + return hwirq; + + if (!(virq = cxl_map_irq(adapter, hwirq, handler, cookie))) + goto err; + + *dest_hwirq = hwirq; + *dest_virq = virq; + + return 0; + +err: + cxl_release_one_irq(adapter, hwirq); + return -ENOMEM; +} + +int cxl_register_psl_err_irq(struct cxl *adapter) +{ + int rc; + + if ((rc = cxl_register_one_irq(adapter, cxl_irq_err, adapter, + &adapter->err_hwirq, + &adapter->err_virq))) + return rc; + + cxl_p1_write(adapter, CXL_PSL_ErrIVTE, adapter->err_hwirq & 0xffff); + + return 0; +} + +void cxl_release_psl_err_irq(struct cxl *adapter) +{ + cxl_p1_write(adapter, CXL_PSL_ErrIVTE, 0x0000000000000000); + cxl_unmap_irq(adapter->err_virq, adapter); + cxl_release_one_irq(adapter, adapter->err_hwirq); +} + +int cxl_register_serr_irq(struct cxl_afu *afu) +{ + u64 serr; + int rc; + + if ((rc = cxl_register_one_irq(afu->adapter, cxl_slice_irq_err, afu, + &afu->serr_hwirq, + &afu->serr_virq))) + return rc; + + serr = cxl_p1n_read(afu, CXL_PSL_SERR_An); + serr = (serr & 0x00ffffffffff0000ULL) | (afu->serr_hwirq & 0xffff); + cxl_p1n_write(afu, CXL_PSL_SERR_An, serr); + + return 0; +} + +void cxl_release_serr_irq(struct cxl_afu *afu) +{ + cxl_p1n_write(afu, CXL_PSL_SERR_An, 0x0000000000000000); + cxl_unmap_irq(afu->serr_virq, afu); + cxl_release_one_irq(afu->adapter, afu->serr_hwirq); +} + +int cxl_register_psl_irq(struct cxl_afu *afu) +{ + return cxl_register_one_irq(afu->adapter, cxl_irq_multiplexed, afu, + &afu->psl_hwirq, &afu->psl_virq); +} + +void cxl_release_psl_irq(struct cxl_afu *afu) +{ + cxl_unmap_irq(afu->psl_virq, afu); + cxl_release_one_irq(afu->adapter, afu->psl_hwirq); +} + +int afu_register_irqs(struct cxl_context *ctx, u32 count) +{ + irq_hw_number_t hwirq; + int rc, r, i; + + if ((rc = cxl_alloc_irq_ranges(&ctx->irqs, ctx->afu->adapter, count))) + return rc; + + /* Multiplexed PSL Interrupt */ + ctx->irqs.offset[0] = ctx->afu->psl_hwirq; + ctx->irqs.range[0] = 1; + + ctx->irq_count = count; + ctx->irq_bitmap = kcalloc(BITS_TO_LONGS(count), + sizeof(*ctx->irq_bitmap), GFP_KERNEL); + if (!ctx->irq_bitmap) + return -ENOMEM; + for (r = 1; r < CXL_IRQ_RANGES; r++) { + hwirq = ctx->irqs.offset[r]; + for (i = 0; i < ctx->irqs.range[r]; hwirq++, i++) { + cxl_map_irq(ctx->afu->adapter, hwirq, + cxl_irq_afu, ctx); + } + } + + return 0; +} + +void afu_release_irqs(struct cxl_context *ctx) +{ + irq_hw_number_t hwirq; + unsigned int virq; + int r, i; + + for (r = 1; r < CXL_IRQ_RANGES; r++) { + hwirq = ctx->irqs.offset[r]; + for (i = 0; i < ctx->irqs.range[r]; hwirq++, i++) { + virq = irq_find_mapping(NULL, hwirq); + if (virq) + cxl_unmap_irq(virq, ctx); + } + } + + cxl_release_irq_ranges(&ctx->irqs, ctx->afu->adapter); +} diff --git a/drivers/misc/cxl/main.c b/drivers/misc/cxl/main.c new file mode 100644 index 000000000000..4cde9b661642 --- /dev/null +++ b/drivers/misc/cxl/main.c @@ -0,0 +1,230 @@ +/* + * 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/spinlock.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/device.h> +#include <linux/mutex.h> +#include <linux/init.h> +#include <linux/list.h> +#include <linux/mm.h> +#include <linux/of.h> +#include <linux/slab.h> +#include <linux/idr.h> +#include <linux/pci.h> +#include <asm/cputable.h> +#include <misc/cxl.h> + +#include "cxl.h" + +static DEFINE_SPINLOCK(adapter_idr_lock); +static DEFINE_IDR(cxl_adapter_idr); + +uint cxl_verbose; +module_param_named(verbose, cxl_verbose, uint, 0600); +MODULE_PARM_DESC(verbose, "Enable verbose dmesg output"); + +static inline void _cxl_slbia(struct cxl_context *ctx, struct mm_struct *mm) +{ + struct task_struct *task; + unsigned long flags; + if (!(task = get_pid_task(ctx->pid, PIDTYPE_PID))) { + pr_devel("%s unable to get task %i\n", + __func__, pid_nr(ctx->pid)); + return; + } + + if (task->mm != mm) + goto out_put; + + pr_devel("%s matched mm - card: %i afu: %i pe: %i\n", __func__, + ctx->afu->adapter->adapter_num, ctx->afu->slice, ctx->pe); + + spin_lock_irqsave(&ctx->sste_lock, flags); + memset(ctx->sstp, 0, ctx->sst_size); + spin_unlock_irqrestore(&ctx->sste_lock, flags); + mb(); + cxl_afu_slbia(ctx->afu); +out_put: + put_task_struct(task); +} + +static inline void cxl_slbia_core(struct mm_struct *mm) +{ + struct cxl *adapter; + struct cxl_afu *afu; + struct cxl_context *ctx; + int card, slice, id; + + pr_devel("%s called\n", __func__); + + spin_lock(&adapter_idr_lock); + idr_for_each_entry(&cxl_adapter_idr, adapter, card) { + /* XXX: Make this lookup faster with link from mm to ctx */ + spin_lock(&adapter->afu_list_lock); + for (slice = 0; slice < adapter->slices; slice++) { + afu = adapter->afu[slice]; + if (!afu->enabled) + continue; + rcu_read_lock(); + idr_for_each_entry(&afu->contexts_idr, ctx, id) + _cxl_slbia(ctx, mm); + rcu_read_unlock(); + } + spin_unlock(&adapter->afu_list_lock); + } + spin_unlock(&adapter_idr_lock); +} + +static struct cxl_calls cxl_calls = { + .cxl_slbia = cxl_slbia_core, + .owner = THIS_MODULE, +}; + +int cxl_alloc_sst(struct cxl_context *ctx) +{ + unsigned long vsid; + u64 ea_mask, size, sstp0, sstp1; + + sstp0 = 0; + sstp1 = 0; + + ctx->sst_size = PAGE_SIZE; + ctx->sst_lru = 0; + ctx->sstp = (struct cxl_sste *)get_zeroed_page(GFP_KERNEL); + if (!ctx->sstp) { + pr_err("cxl_alloc_sst: Unable to allocate segment table\n"); + return -ENOMEM; + } + pr_devel("SSTP allocated at 0x%p\n", ctx->sstp); + + vsid = get_kernel_vsid((u64)ctx->sstp, mmu_kernel_ssize) << 12; + + sstp0 |= (u64)mmu_kernel_ssize << CXL_SSTP0_An_B_SHIFT; + sstp0 |= (SLB_VSID_KERNEL | mmu_psize_defs[mmu_linear_psize].sllp) << 50; + + size = (((u64)ctx->sst_size >> 8) - 1) << CXL_SSTP0_An_SegTableSize_SHIFT; + if (unlikely(size & ~CXL_SSTP0_An_SegTableSize_MASK)) { + WARN(1, "Impossible segment table size\n"); + return -EINVAL; + } + sstp0 |= size; + + if (mmu_kernel_ssize == MMU_SEGSIZE_256M) + ea_mask = 0xfffff00ULL; + else + ea_mask = 0xffffffff00ULL; + + sstp0 |= vsid >> (50-14); /* Top 14 bits of VSID */ + sstp1 |= (vsid << (64-(50-14))) & ~ea_mask; + sstp1 |= (u64)ctx->sstp & ea_mask; + sstp1 |= CXL_SSTP1_An_V; + + pr_devel("Looked up %#llx: slbfee. %#llx (ssize: %x, vsid: %#lx), copied to SSTP0: %#llx, SSTP1: %#llx\n", + (u64)ctx->sstp, (u64)ctx->sstp & ESID_MASK, mmu_kernel_ssize, vsid, sstp0, sstp1); + + /* Store calculated sstp hardware points for use later */ + ctx->sstp0 = sstp0; + ctx->sstp1 = sstp1; + + return 0; +} + +/* Find a CXL adapter by it's number and increase it's refcount */ +struct cxl *get_cxl_adapter(int num) +{ + struct cxl *adapter; + + spin_lock(&adapter_idr_lock); + if ((adapter = idr_find(&cxl_adapter_idr, num))) + get_device(&adapter->dev); + spin_unlock(&adapter_idr_lock); + + return adapter; +} + +int cxl_alloc_adapter_nr(struct cxl *adapter) +{ + int i; + + idr_preload(GFP_KERNEL); + spin_lock(&adapter_idr_lock); + i = idr_alloc(&cxl_adapter_idr, adapter, 0, 0, GFP_NOWAIT); + spin_unlock(&adapter_idr_lock); + idr_preload_end(); + if (i < 0) + return i; + + adapter->adapter_num = i; + + return 0; +} + +void cxl_remove_adapter_nr(struct cxl *adapter) +{ + idr_remove(&cxl_adapter_idr, adapter->adapter_num); +} + +int cxl_afu_select_best_mode(struct cxl_afu *afu) +{ + if (afu->modes_supported & CXL_MODE_DIRECTED) + return cxl_afu_activate_mode(afu, CXL_MODE_DIRECTED); + + if (afu->modes_supported & CXL_MODE_DEDICATED) + return cxl_afu_activate_mode(afu, CXL_MODE_DEDICATED); + + dev_warn(&afu->dev, "No supported programming modes available\n"); + /* We don't fail this so the user can inspect sysfs */ + return 0; +} + +static int __init init_cxl(void) +{ + int rc = 0; + + if (!cpu_has_feature(CPU_FTR_HVMODE)) + return -EPERM; + + if ((rc = cxl_file_init())) + return rc; + + cxl_debugfs_init(); + + if ((rc = register_cxl_calls(&cxl_calls))) + goto err; + + if ((rc = pci_register_driver(&cxl_pci_driver))) + goto err1; + + return 0; +err1: + unregister_cxl_calls(&cxl_calls); +err: + cxl_debugfs_exit(); + cxl_file_exit(); + + return rc; +} + +static void exit_cxl(void) +{ + pci_unregister_driver(&cxl_pci_driver); + + cxl_debugfs_exit(); + cxl_file_exit(); + unregister_cxl_calls(&cxl_calls); +} + +module_init(init_cxl); +module_exit(exit_cxl); + +MODULE_DESCRIPTION("IBM Coherent Accelerator"); +MODULE_AUTHOR("Ian Munsie <imunsie@au1.ibm.com>"); +MODULE_LICENSE("GPL"); diff --git a/drivers/misc/cxl/native.c b/drivers/misc/cxl/native.c new file mode 100644 index 000000000000..623286a77114 --- /dev/null +++ b/drivers/misc/cxl/native.c @@ -0,0 +1,683 @@ +/* + * 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/spinlock.h> +#include <linux/sched.h> +#include <linux/slab.h> +#include <linux/sched.h> +#include <linux/mutex.h> +#include <linux/mm.h> +#include <linux/uaccess.h> +#include <asm/synch.h> +#include <misc/cxl.h> + +#include "cxl.h" + +static int afu_control(struct cxl_afu *afu, u64 command, + u64 result, u64 mask, bool enabled) +{ + u64 AFU_Cntl = cxl_p2n_read(afu, CXL_AFU_Cntl_An); + unsigned long timeout = jiffies + (HZ * CXL_TIMEOUT); + + spin_lock(&afu->afu_cntl_lock); + pr_devel("AFU command starting: %llx\n", command); + + cxl_p2n_write(afu, CXL_AFU_Cntl_An, AFU_Cntl | command); + + AFU_Cntl = cxl_p2n_read(afu, CXL_AFU_Cntl_An); + while ((AFU_Cntl & mask) != result) { + if (time_after_eq(jiffies, timeout)) { + dev_warn(&afu->dev, "WARNING: AFU control timed out!\n"); + spin_unlock(&afu->afu_cntl_lock); + return -EBUSY; + } + pr_devel_ratelimited("AFU control... (0x%.16llx)\n", + AFU_Cntl | command); + cpu_relax(); + AFU_Cntl = cxl_p2n_read(afu, CXL_AFU_Cntl_An); + }; + pr_devel("AFU command complete: %llx\n", command); + afu->enabled = enabled; + spin_unlock(&afu->afu_cntl_lock); + + return 0; +} + +static int afu_enable(struct cxl_afu *afu) +{ + pr_devel("AFU enable request\n"); + + return afu_control(afu, CXL_AFU_Cntl_An_E, + CXL_AFU_Cntl_An_ES_Enabled, + CXL_AFU_Cntl_An_ES_MASK, true); +} + +int cxl_afu_disable(struct cxl_afu *afu) +{ + pr_devel("AFU disable request\n"); + + return afu_control(afu, 0, CXL_AFU_Cntl_An_ES_Disabled, + CXL_AFU_Cntl_An_ES_MASK, false); +} + +/* This will disable as well as reset */ +int cxl_afu_reset(struct cxl_afu *afu) +{ + pr_devel("AFU reset request\n"); + + return afu_control(afu, CXL_AFU_Cntl_An_RA, + CXL_AFU_Cntl_An_RS_Complete | CXL_AFU_Cntl_An_ES_Disabled, + CXL_AFU_Cntl_An_RS_MASK | CXL_AFU_Cntl_An_ES_MASK, + false); +} + +static int afu_check_and_enable(struct cxl_afu *afu) +{ + if (afu->enabled) + return 0; + return afu_enable(afu); +} + +int cxl_psl_purge(struct cxl_afu *afu) +{ + u64 PSL_CNTL = cxl_p1n_read(afu, CXL_PSL_SCNTL_An); + u64 AFU_Cntl = cxl_p2n_read(afu, CXL_AFU_Cntl_An); + u64 dsisr, dar; + u64 start, end; + unsigned long timeout = jiffies + (HZ * CXL_TIMEOUT); + + pr_devel("PSL purge request\n"); + + if ((AFU_Cntl & CXL_AFU_Cntl_An_ES_MASK) != CXL_AFU_Cntl_An_ES_Disabled) { + WARN(1, "psl_purge request while AFU not disabled!\n"); + cxl_afu_disable(afu); + } + + cxl_p1n_write(afu, CXL_PSL_SCNTL_An, + PSL_CNTL | CXL_PSL_SCNTL_An_Pc); + start = local_clock(); + PSL_CNTL = cxl_p1n_read(afu, CXL_PSL_SCNTL_An); + while ((PSL_CNTL & CXL_PSL_SCNTL_An_Ps_MASK) + == CXL_PSL_SCNTL_An_Ps_Pending) { + if (time_after_eq(jiffies, timeout)) { + dev_warn(&afu->dev, "WARNING: PSL Purge timed out!\n"); + return -EBUSY; + } + dsisr = cxl_p2n_read(afu, CXL_PSL_DSISR_An); + pr_devel_ratelimited("PSL purging... PSL_CNTL: 0x%.16llx PSL_DSISR: 0x%.16llx\n", PSL_CNTL, dsisr); + if (dsisr & CXL_PSL_DSISR_TRANS) { + dar = cxl_p2n_read(afu, CXL_PSL_DAR_An); + dev_notice(&afu->dev, "PSL purge terminating pending translation, DSISR: 0x%.16llx, DAR: 0x%.16llx\n", dsisr, dar); + cxl_p2n_write(afu, CXL_PSL_TFC_An, CXL_PSL_TFC_An_AE); + } else if (dsisr) { + dev_notice(&afu->dev, "PSL purge acknowledging pending non-translation fault, DSISR: 0x%.16llx\n", dsisr); + cxl_p2n_write(afu, CXL_PSL_TFC_An, CXL_PSL_TFC_An_A); + } else { + cpu_relax(); + } + PSL_CNTL = cxl_p1n_read(afu, CXL_PSL_SCNTL_An); + }; + end = local_clock(); + pr_devel("PSL purged in %lld ns\n", end - start); + + cxl_p1n_write(afu, CXL_PSL_SCNTL_An, + PSL_CNTL & ~CXL_PSL_SCNTL_An_Pc); + return 0; +} + +static int spa_max_procs(int spa_size) +{ + /* + * From the CAIA: + * end_of_SPA_area = SPA_Base + ((n+4) * 128) + (( ((n*8) + 127) >> 7) * 128) + 255 + * Most of that junk is really just an overly-complicated way of saying + * the last 256 bytes are __aligned(128), so it's really: + * end_of_SPA_area = end_of_PSL_queue_area + __aligned(128) 255 + * and + * end_of_PSL_queue_area = SPA_Base + ((n+4) * 128) + (n*8) - 1 + * so + * sizeof(SPA) = ((n+4) * 128) + (n*8) + __aligned(128) 256 + * Ignore the alignment (which is safe in this case as long as we are + * careful with our rounding) and solve for n: + */ + return ((spa_size / 8) - 96) / 17; +} + +static int alloc_spa(struct cxl_afu *afu) +{ + u64 spap; + + /* Work out how many pages to allocate */ + afu->spa_order = 0; + do { + afu->spa_order++; + afu->spa_size = (1 << afu->spa_order) * PAGE_SIZE; + afu->spa_max_procs = spa_max_procs(afu->spa_size); + } while (afu->spa_max_procs < afu->num_procs); + + WARN_ON(afu->spa_size > 0x100000); /* Max size supported by the hardware */ + + if (!(afu->spa = (struct cxl_process_element *) + __get_free_pages(GFP_KERNEL | __GFP_ZERO, afu->spa_order))) { + pr_err("cxl_alloc_spa: Unable to allocate scheduled process area\n"); + return -ENOMEM; + } + pr_devel("spa pages: %i afu->spa_max_procs: %i afu->num_procs: %i\n", + 1<<afu->spa_order, afu->spa_max_procs, afu->num_procs); + + afu->sw_command_status = (__be64 *)((char *)afu->spa + + ((afu->spa_max_procs + 3) * 128)); + + spap = virt_to_phys(afu->spa) & CXL_PSL_SPAP_Addr; + spap |= ((afu->spa_size >> (12 - CXL_PSL_SPAP_Size_Shift)) - 1) & CXL_PSL_SPAP_Size; + spap |= CXL_PSL_SPAP_V; + pr_devel("cxl: SPA allocated at 0x%p. Max processes: %i, sw_command_status: 0x%p CXL_PSL_SPAP_An=0x%016llx\n", afu->spa, afu->spa_max_procs, afu->sw_command_status, spap); + cxl_p1n_write(afu, CXL_PSL_SPAP_An, spap); + + return 0; +} + +static void release_spa(struct cxl_afu *afu) +{ + free_pages((unsigned long) afu->spa, afu->spa_order); +} + +int cxl_tlb_slb_invalidate(struct cxl *adapter) +{ + unsigned long timeout = jiffies + (HZ * CXL_TIMEOUT); + + pr_devel("CXL adapter wide TLBIA & SLBIA\n"); + + cxl_p1_write(adapter, CXL_PSL_AFUSEL, CXL_PSL_AFUSEL_A); + + cxl_p1_write(adapter, CXL_PSL_TLBIA, CXL_TLB_SLB_IQ_ALL); + while (cxl_p1_read(adapter, CXL_PSL_TLBIA) & CXL_TLB_SLB_P) { + if (time_after_eq(jiffies, timeout)) { + dev_warn(&adapter->dev, "WARNING: CXL adapter wide TLBIA timed out!\n"); + return -EBUSY; + } + cpu_relax(); + } + + cxl_p1_write(adapter, CXL_PSL_SLBIA, CXL_TLB_SLB_IQ_ALL); + while (cxl_p1_read(adapter, CXL_PSL_SLBIA) & CXL_TLB_SLB_P) { + if (time_after_eq(jiffies, timeout)) { + dev_warn(&adapter->dev, "WARNING: CXL adapter wide SLBIA timed out!\n"); + return -EBUSY; + } + cpu_relax(); + } + return 0; +} + +int cxl_afu_slbia(struct cxl_afu *afu) +{ + unsigned long timeout = jiffies + (HZ * CXL_TIMEOUT); + + pr_devel("cxl_afu_slbia issuing SLBIA command\n"); + cxl_p2n_write(afu, CXL_SLBIA_An, CXL_TLB_SLB_IQ_ALL); + while (cxl_p2n_read(afu, CXL_SLBIA_An) & CXL_TLB_SLB_P) { + if (time_after_eq(jiffies, timeout)) { + dev_warn(&afu->dev, "WARNING: CXL AFU SLBIA timed out!\n"); + return -EBUSY; + } + cpu_relax(); + } + return 0; +} + +static int cxl_write_sstp(struct cxl_afu *afu, u64 sstp0, u64 sstp1) +{ + int rc; + + /* 1. Disable SSTP by writing 0 to SSTP1[V] */ + cxl_p2n_write(afu, CXL_SSTP1_An, 0); + + /* 2. Invalidate all SLB entries */ + if ((rc = cxl_afu_slbia(afu))) + return rc; + + /* 3. Set SSTP0_An */ + cxl_p2n_write(afu, CXL_SSTP0_An, sstp0); + + /* 4. Set SSTP1_An */ + cxl_p2n_write(afu, CXL_SSTP1_An, sstp1); + + return 0; +} + +/* Using per slice version may improve performance here. (ie. SLBIA_An) */ +static void slb_invalid(struct cxl_context *ctx) +{ + struct cxl *adapter = ctx->afu->adapter; + u64 slbia; + + WARN_ON(!mutex_is_locked(&ctx->afu->spa_mutex)); + + cxl_p1_write(adapter, CXL_PSL_LBISEL, + ((u64)be32_to_cpu(ctx->elem->common.pid) << 32) | + be32_to_cpu(ctx->elem->lpid)); + cxl_p1_write(adapter, CXL_PSL_SLBIA, CXL_TLB_SLB_IQ_LPIDPID); + + while (1) { + slbia = cxl_p1_read(adapter, CXL_PSL_SLBIA); + if (!(slbia & CXL_TLB_SLB_P)) + break; + cpu_relax(); + } +} + +static int do_process_element_cmd(struct cxl_context *ctx, + u64 cmd, u64 pe_state) +{ + u64 state; + + WARN_ON(!ctx->afu->enabled); + + ctx->elem->software_state = cpu_to_be32(pe_state); + smp_wmb(); + *(ctx->afu->sw_command_status) = cpu_to_be64(cmd | 0 | ctx->pe); + smp_mb(); + cxl_p1n_write(ctx->afu, CXL_PSL_LLCMD_An, cmd | ctx->pe); + while (1) { + state = be64_to_cpup(ctx->afu->sw_command_status); + if (state == ~0ULL) { + pr_err("cxl: Error adding process element to AFU\n"); + return -1; + } + if ((state & (CXL_SPA_SW_CMD_MASK | CXL_SPA_SW_STATE_MASK | CXL_SPA_SW_LINK_MASK)) == + (cmd | (cmd >> 16) | ctx->pe)) + break; + /* + * The command won't finish in the PSL if there are + * outstanding DSIs. Hence we need to yield here in + * case there are outstanding DSIs that we need to + * service. Tuning possiblity: we could wait for a + * while before sched + */ + schedule(); + + } + return 0; +} + +static int add_process_element(struct cxl_context *ctx) +{ + int rc = 0; + + mutex_lock(&ctx->afu->spa_mutex); + pr_devel("%s Adding pe: %i started\n", __func__, ctx->pe); + if (!(rc = do_process_element_cmd(ctx, CXL_SPA_SW_CMD_ADD, CXL_PE_SOFTWARE_STATE_V))) + ctx->pe_inserted = true; + pr_devel("%s Adding pe: %i finished\n", __func__, ctx->pe); + mutex_unlock(&ctx->afu->spa_mutex); + return rc; +} + +static int terminate_process_element(struct cxl_context *ctx) +{ + int rc = 0; + + /* fast path terminate if it's already invalid */ + if (!(ctx->elem->software_state & cpu_to_be32(CXL_PE_SOFTWARE_STATE_V))) + return rc; + + mutex_lock(&ctx->afu->spa_mutex); + pr_devel("%s Terminate pe: %i started\n", __func__, ctx->pe); + rc = do_process_element_cmd(ctx, CXL_SPA_SW_CMD_TERMINATE, + CXL_PE_SOFTWARE_STATE_V | CXL_PE_SOFTWARE_STATE_T); + ctx->elem->software_state = 0; /* Remove Valid bit */ + pr_devel("%s Terminate pe: %i finished\n", __func__, ctx->pe); + mutex_unlock(&ctx->afu->spa_mutex); + return rc; +} + +static int remove_process_element(struct cxl_context *ctx) +{ + int rc = 0; + + mutex_lock(&ctx->afu->spa_mutex); + pr_devel("%s Remove pe: %i started\n", __func__, ctx->pe); + if (!(rc = do_process_element_cmd(ctx, CXL_SPA_SW_CMD_REMOVE, 0))) + ctx->pe_inserted = false; + slb_invalid(ctx); + pr_devel("%s Remove pe: %i finished\n", __func__, ctx->pe); + mutex_unlock(&ctx->afu->spa_mutex); + + return rc; +} + + +static void assign_psn_space(struct cxl_context *ctx) +{ + if (!ctx->afu->pp_size || ctx->master) { + ctx->psn_phys = ctx->afu->psn_phys; + ctx->psn_size = ctx->afu->adapter->ps_size; + } else { + ctx->psn_phys = ctx->afu->psn_phys + + (ctx->afu->pp_offset + ctx->afu->pp_size * ctx->pe); + ctx->psn_size = ctx->afu->pp_size; + } +} + +static int activate_afu_directed(struct cxl_afu *afu) +{ + int rc; + + dev_info(&afu->dev, "Activating AFU directed mode\n"); + + if (alloc_spa(afu)) + return -ENOMEM; + + cxl_p1n_write(afu, CXL_PSL_SCNTL_An, CXL_PSL_SCNTL_An_PM_AFU); + cxl_p1n_write(afu, CXL_PSL_AMOR_An, 0xFFFFFFFFFFFFFFFFULL); + cxl_p1n_write(afu, CXL_PSL_ID_An, CXL_PSL_ID_An_F | CXL_PSL_ID_An_L); + + afu->current_mode = CXL_MODE_DIRECTED; + afu->num_procs = afu->max_procs_virtualised; + + if ((rc = cxl_chardev_m_afu_add(afu))) + return rc; + + if ((rc = cxl_sysfs_afu_m_add(afu))) + goto err; + + if ((rc = cxl_chardev_s_afu_add(afu))) + goto err1; + + return 0; +err1: + cxl_sysfs_afu_m_remove(afu); +err: + cxl_chardev_afu_remove(afu); + return rc; +} + +#ifdef CONFIG_CPU_LITTLE_ENDIAN +#define set_endian(sr) ((sr) |= CXL_PSL_SR_An_LE) +#else +#define set_endian(sr) ((sr) &= ~(CXL_PSL_SR_An_LE)) +#endif + +static int attach_afu_directed(struct cxl_context *ctx, u64 wed, u64 amr) +{ + u64 sr; + int r, result; + + assign_psn_space(ctx); + + ctx->elem->ctxtime = 0; /* disable */ + ctx->elem->lpid = cpu_to_be32(mfspr(SPRN_LPID)); + ctx->elem->haurp = 0; /* disable */ + ctx->elem->sdr = cpu_to_be64(mfspr(SPRN_SDR1)); + + sr = CXL_PSL_SR_An_SC; + if (ctx->master) + sr |= CXL_PSL_SR_An_MP; + if (mfspr(SPRN_LPCR) & LPCR_TC) + sr |= CXL_PSL_SR_An_TC; + /* HV=0, PR=1, R=1 for userspace + * For kernel contexts: this would need to change + */ + sr |= CXL_PSL_SR_An_PR | CXL_PSL_SR_An_R; + set_endian(sr); + sr &= ~(CXL_PSL_SR_An_HV); + if (!test_tsk_thread_flag(current, TIF_32BIT)) + sr |= CXL_PSL_SR_An_SF; + ctx->elem->common.pid = cpu_to_be32(current->pid); + ctx->elem->common.tid = 0; + ctx->elem->sr = cpu_to_be64(sr); + + ctx->elem->common.csrp = 0; /* disable */ + ctx->elem->common.aurp0 = 0; /* disable */ + ctx->elem->common.aurp1 = 0; /* disable */ + + cxl_prefault(ctx, wed); + + ctx->elem->common.sstp0 = cpu_to_be64(ctx->sstp0); + ctx->elem->common.sstp1 = cpu_to_be64(ctx->sstp1); + + for (r = 0; r < CXL_IRQ_RANGES; r++) { + ctx->elem->ivte_offsets[r] = cpu_to_be16(ctx->irqs.offset[r]); + ctx->elem->ivte_ranges[r] = cpu_to_be16(ctx->irqs.range[r]); + } + + ctx->elem->common.amr = cpu_to_be64(amr); + ctx->elem->common.wed = cpu_to_be64(wed); + + /* first guy needs to enable */ + if ((result = afu_check_and_enable(ctx->afu))) + return result; + + add_process_element(ctx); + + return 0; +} + +static int deactivate_afu_directed(struct cxl_afu *afu) +{ + dev_info(&afu->dev, "Deactivating AFU directed mode\n"); + + afu->current_mode = 0; + afu->num_procs = 0; + + cxl_sysfs_afu_m_remove(afu); + cxl_chardev_afu_remove(afu); + + cxl_afu_reset(afu); + cxl_afu_disable(afu); + cxl_psl_purge(afu); + + release_spa(afu); + + return 0; +} + +static int activate_dedicated_process(struct cxl_afu *afu) +{ + dev_info(&afu->dev, "Activating dedicated process mode\n"); + + cxl_p1n_write(afu, CXL_PSL_SCNTL_An, CXL_PSL_SCNTL_An_PM_Process); + + cxl_p1n_write(afu, CXL_PSL_CtxTime_An, 0); /* disable */ + cxl_p1n_write(afu, CXL_PSL_SPAP_An, 0); /* disable */ + cxl_p1n_write(afu, CXL_PSL_AMOR_An, 0xFFFFFFFFFFFFFFFFULL); + cxl_p1n_write(afu, CXL_PSL_LPID_An, mfspr(SPRN_LPID)); + cxl_p1n_write(afu, CXL_HAURP_An, 0); /* disable */ + cxl_p1n_write(afu, CXL_PSL_SDR_An, mfspr(SPRN_SDR1)); + + cxl_p2n_write(afu, CXL_CSRP_An, 0); /* disable */ + cxl_p2n_write(afu, CXL_AURP0_An, 0); /* disable */ + cxl_p2n_write(afu, CXL_AURP1_An, 0); /* disable */ + + afu->current_mode = CXL_MODE_DEDICATED; + afu->num_procs = 1; + + return cxl_chardev_d_afu_add(afu); +} + +static int attach_dedicated(struct cxl_context *ctx, u64 wed, u64 amr) +{ + struct cxl_afu *afu = ctx->afu; + u64 sr; + int rc; + + sr = CXL_PSL_SR_An_SC; + set_endian(sr); + if (ctx->master) + sr |= CXL_PSL_SR_An_MP; + if (mfspr(SPRN_LPCR) & LPCR_TC) + sr |= CXL_PSL_SR_An_TC; + sr |= CXL_PSL_SR_An_PR | CXL_PSL_SR_An_R; + if (!test_tsk_thread_flag(current, TIF_32BIT)) + sr |= CXL_PSL_SR_An_SF; + cxl_p2n_write(afu, CXL_PSL_PID_TID_An, (u64)current->pid << 32); + cxl_p1n_write(afu, CXL_PSL_SR_An, sr); + + if ((rc = cxl_write_sstp(afu, ctx->sstp0, ctx->sstp1))) + return rc; + + cxl_prefault(ctx, wed); + + cxl_p1n_write(afu, CXL_PSL_IVTE_Offset_An, + (((u64)ctx->irqs.offset[0] & 0xffff) << 48) | + (((u64)ctx->irqs.offset[1] & 0xffff) << 32) | + (((u64)ctx->irqs.offset[2] & 0xffff) << 16) | + ((u64)ctx->irqs.offset[3] & 0xffff)); + cxl_p1n_write(afu, CXL_PSL_IVTE_Limit_An, (u64) + (((u64)ctx->irqs.range[0] & 0xffff) << 48) | + (((u64)ctx->irqs.range[1] & 0xffff) << 32) | + (((u64)ctx->irqs.range[2] & 0xffff) << 16) | + ((u64)ctx->irqs.range[3] & 0xffff)); + + cxl_p2n_write(afu, CXL_PSL_AMR_An, amr); + + /* master only context for dedicated */ + assign_psn_space(ctx); + + if ((rc = cxl_afu_reset(afu))) + return rc; + + cxl_p2n_write(afu, CXL_PSL_WED_An, wed); + + return afu_enable(afu); +} + +static int deactivate_dedicated_process(struct cxl_afu *afu) +{ + dev_info(&afu->dev, "Deactivating dedicated process mode\n"); + + afu->current_mode = 0; + afu->num_procs = 0; + + cxl_chardev_afu_remove(afu); + + return 0; +} + +int _cxl_afu_deactivate_mode(struct cxl_afu *afu, int mode) +{ + if (mode == CXL_MODE_DIRECTED) + return deactivate_afu_directed(afu); + if (mode == CXL_MODE_DEDICATED) + return deactivate_dedicated_process(afu); + return 0; +} + +int cxl_afu_deactivate_mode(struct cxl_afu *afu) +{ + return _cxl_afu_deactivate_mode(afu, afu->current_mode); +} + +int cxl_afu_activate_mode(struct cxl_afu *afu, int mode) +{ + if (!mode) + return 0; + if (!(mode & afu->modes_supported)) + return -EINVAL; + + if (mode == CXL_MODE_DIRECTED) + return activate_afu_directed(afu); + if (mode == CXL_MODE_DEDICATED) + return activate_dedicated_process(afu); + + return -EINVAL; +} + +int cxl_attach_process(struct cxl_context *ctx, bool kernel, u64 wed, u64 amr) +{ + ctx->kernel = kernel; + if (ctx->afu->current_mode == CXL_MODE_DIRECTED) + return attach_afu_directed(ctx, wed, amr); + + if (ctx->afu->current_mode == CXL_MODE_DEDICATED) + return attach_dedicated(ctx, wed, amr); + + return -EINVAL; +} + +static inline int detach_process_native_dedicated(struct cxl_context *ctx) +{ + cxl_afu_reset(ctx->afu); + cxl_afu_disable(ctx->afu); + cxl_psl_purge(ctx->afu); + return 0; +} + +/* + * TODO: handle case when this is called inside a rcu_read_lock() which may + * happen when we unbind the driver (ie. cxl_context_detach_all()) . Terminate + * & remove use a mutex lock and schedule which will not good with lock held. + * May need to write do_process_element_cmd() that handles outstanding page + * faults synchronously. + */ +static inline int detach_process_native_afu_directed(struct cxl_context *ctx) +{ + if (!ctx->pe_inserted) + return 0; + if (terminate_process_element(ctx)) + return -1; + if (remove_process_element(ctx)) + return -1; + + return 0; +} + +int cxl_detach_process(struct cxl_context *ctx) +{ + if (ctx->afu->current_mode == CXL_MODE_DEDICATED) + return detach_process_native_dedicated(ctx); + + return detach_process_native_afu_directed(ctx); +} + +int cxl_get_irq(struct cxl_context *ctx, struct cxl_irq_info *info) +{ + u64 pidtid; + + info->dsisr = cxl_p2n_read(ctx->afu, CXL_PSL_DSISR_An); + info->dar = cxl_p2n_read(ctx->afu, CXL_PSL_DAR_An); + info->dsr = cxl_p2n_read(ctx->afu, CXL_PSL_DSR_An); + pidtid = cxl_p2n_read(ctx->afu, CXL_PSL_PID_TID_An); + info->pid = pidtid >> 32; + info->tid = pidtid & 0xffffffff; + info->afu_err = cxl_p2n_read(ctx->afu, CXL_AFU_ERR_An); + info->errstat = cxl_p2n_read(ctx->afu, CXL_PSL_ErrStat_An); + + return 0; +} + +static void recover_psl_err(struct cxl_afu *afu, u64 errstat) +{ + u64 dsisr; + + pr_devel("RECOVERING FROM PSL ERROR... (0x%.16llx)\n", errstat); + + /* Clear PSL_DSISR[PE] */ + dsisr = cxl_p2n_read(afu, CXL_PSL_DSISR_An); + cxl_p2n_write(afu, CXL_PSL_DSISR_An, dsisr & ~CXL_PSL_DSISR_An_PE); + + /* Write 1s to clear error status bits */ + cxl_p2n_write(afu, CXL_PSL_ErrStat_An, errstat); +} + +int cxl_ack_irq(struct cxl_context *ctx, u64 tfc, u64 psl_reset_mask) +{ + if (tfc) + cxl_p2n_write(ctx->afu, CXL_PSL_TFC_An, tfc); + if (psl_reset_mask) + recover_psl_err(ctx->afu, psl_reset_mask); + + return 0; +} + +int cxl_check_error(struct cxl_afu *afu) +{ + return (cxl_p1n_read(afu, CXL_PSL_SCNTL_An) == ~0ULL); +} diff --git a/drivers/misc/cxl/pci.c b/drivers/misc/cxl/pci.c new file mode 100644 index 000000000000..10c98ab7f46e --- /dev/null +++ b/drivers/misc/cxl/pci.c @@ -0,0 +1,1000 @@ +/* + * 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/pci_regs.h> +#include <linux/pci_ids.h> +#include <linux/device.h> +#include <linux/module.h> +#include <linux/kernel.h> +#include <linux/slab.h> +#include <linux/sort.h> +#include <linux/pci.h> +#include <linux/of.h> +#include <linux/delay.h> +#include <asm/opal.h> +#include <asm/msi_bitmap.h> +#include <asm/pci-bridge.h> /* for struct pci_controller */ +#include <asm/pnv-pci.h> + +#include "cxl.h" + + +#define CXL_PCI_VSEC_ID 0x1280 +#define CXL_VSEC_MIN_SIZE 0x80 + +#define CXL_READ_VSEC_LENGTH(dev, vsec, dest) \ + { \ + pci_read_config_word(dev, vsec + 0x6, dest); \ + *dest >>= 4; \ + } +#define CXL_READ_VSEC_NAFUS(dev, vsec, dest) \ + pci_read_config_byte(dev, vsec + 0x8, dest) + +#define CXL_READ_VSEC_STATUS(dev, vsec, dest) \ + pci_read_config_byte(dev, vsec + 0x9, dest) +#define CXL_STATUS_SECOND_PORT 0x80 +#define CXL_STATUS_MSI_X_FULL 0x40 +#define CXL_STATUS_MSI_X_SINGLE 0x20 +#define CXL_STATUS_FLASH_RW 0x08 +#define CXL_STATUS_FLASH_RO 0x04 +#define CXL_STATUS_LOADABLE_AFU 0x02 +#define CXL_STATUS_LOADABLE_PSL 0x01 +/* If we see these features we won't try to use the card */ +#define CXL_UNSUPPORTED_FEATURES \ + (CXL_STATUS_MSI_X_FULL | CXL_STATUS_MSI_X_SINGLE) + +#define CXL_READ_VSEC_MODE_CONTROL(dev, vsec, dest) \ + pci_read_config_byte(dev, vsec + 0xa, dest) +#define CXL_WRITE_VSEC_MODE_CONTROL(dev, vsec, val) \ + pci_write_config_byte(dev, vsec + 0xa, val) +#define CXL_VSEC_PROTOCOL_MASK 0xe0 +#define CXL_VSEC_PROTOCOL_1024TB 0x80 +#define CXL_VSEC_PROTOCOL_512TB 0x40 +#define CXL_VSEC_PROTOCOL_256TB 0x20 /* Power 8 uses this */ +#define CXL_VSEC_PROTOCOL_ENABLE 0x01 + +#define CXL_READ_VSEC_PSL_REVISION(dev, vsec, dest) \ + pci_read_config_word(dev, vsec + 0xc, dest) +#define CXL_READ_VSEC_CAIA_MINOR(dev, vsec, dest) \ + pci_read_config_byte(dev, vsec + 0xe, dest) +#define CXL_READ_VSEC_CAIA_MAJOR(dev, vsec, dest) \ + pci_read_config_byte(dev, vsec + 0xf, dest) +#define CXL_READ_VSEC_BASE_IMAGE(dev, vsec, dest) \ + pci_read_config_word(dev, vsec + 0x10, dest) + +#define CXL_READ_VSEC_IMAGE_STATE(dev, vsec, dest) \ + pci_read_config_byte(dev, vsec + 0x13, dest) +#define CXL_WRITE_VSEC_IMAGE_STATE(dev, vsec, val) \ + pci_write_config_byte(dev, vsec + 0x13, val) +#define CXL_VSEC_USER_IMAGE_LOADED 0x80 /* RO */ +#define CXL_VSEC_PERST_LOADS_IMAGE 0x20 /* RW */ +#define CXL_VSEC_PERST_SELECT_USER 0x10 /* RW */ + +#define CXL_READ_VSEC_AFU_DESC_OFF(dev, vsec, dest) \ + pci_read_config_dword(dev, vsec + 0x20, dest) +#define CXL_READ_VSEC_AFU_DESC_SIZE(dev, vsec, dest) \ + pci_read_config_dword(dev, vsec + 0x24, dest) +#define CXL_READ_VSEC_PS_OFF(dev, vsec, dest) \ + pci_read_config_dword(dev, vsec + 0x28, dest) +#define CXL_READ_VSEC_PS_SIZE(dev, vsec, dest) \ + pci_read_config_dword(dev, vsec + 0x2c, dest) + + +/* This works a little different than the p1/p2 register accesses to make it + * easier to pull out individual fields */ +#define AFUD_READ(afu, off) in_be64(afu->afu_desc_mmio + off) +#define EXTRACT_PPC_BIT(val, bit) (!!(val & PPC_BIT(bit))) +#define EXTRACT_PPC_BITS(val, bs, be) ((val & PPC_BITMASK(bs, be)) >> PPC_BITLSHIFT(be)) + +#define AFUD_READ_INFO(afu) AFUD_READ(afu, 0x0) +#define AFUD_NUM_INTS_PER_PROC(val) EXTRACT_PPC_BITS(val, 0, 15) +#define AFUD_NUM_PROCS(val) EXTRACT_PPC_BITS(val, 16, 31) +#define AFUD_NUM_CRS(val) EXTRACT_PPC_BITS(val, 32, 47) +#define AFUD_MULTIMODE(val) EXTRACT_PPC_BIT(val, 48) +#define AFUD_PUSH_BLOCK_TRANSFER(val) EXTRACT_PPC_BIT(val, 55) +#define AFUD_DEDICATED_PROCESS(val) EXTRACT_PPC_BIT(val, 59) +#define AFUD_AFU_DIRECTED(val) EXTRACT_PPC_BIT(val, 61) +#define AFUD_TIME_SLICED(val) EXTRACT_PPC_BIT(val, 63) +#define AFUD_READ_CR(afu) AFUD_READ(afu, 0x20) +#define AFUD_CR_LEN(val) EXTRACT_PPC_BITS(val, 8, 63) +#define AFUD_READ_CR_OFF(afu) AFUD_READ(afu, 0x28) +#define AFUD_READ_PPPSA(afu) AFUD_READ(afu, 0x30) +#define AFUD_PPPSA_PP(val) EXTRACT_PPC_BIT(val, 6) +#define AFUD_PPPSA_PSA(val) EXTRACT_PPC_BIT(val, 7) +#define AFUD_PPPSA_LEN(val) EXTRACT_PPC_BITS(val, 8, 63) +#define AFUD_READ_PPPSA_OFF(afu) AFUD_READ(afu, 0x38) +#define AFUD_READ_EB(afu) AFUD_READ(afu, 0x40) +#define AFUD_EB_LEN(val) EXTRACT_PPC_BITS(val, 8, 63) +#define AFUD_READ_EB_OFF(afu) AFUD_READ(afu, 0x48) + +static DEFINE_PCI_DEVICE_TABLE(cxl_pci_tbl) = { + { PCI_DEVICE(PCI_VENDOR_ID_IBM, 0x0477), }, + { PCI_DEVICE(PCI_VENDOR_ID_IBM, 0x044b), }, + { PCI_DEVICE(PCI_VENDOR_ID_IBM, 0x04cf), }, + { PCI_DEVICE_CLASS(0x120000, ~0), }, + + { } +}; +MODULE_DEVICE_TABLE(pci, cxl_pci_tbl); + + +/* + * Mostly using these wrappers to avoid confusion: + * priv 1 is BAR2, while priv 2 is BAR0 + */ +static inline resource_size_t p1_base(struct pci_dev *dev) +{ + return pci_resource_start(dev, 2); +} + +static inline resource_size_t p1_size(struct pci_dev *dev) +{ + return pci_resource_len(dev, 2); +} + +static inline resource_size_t p2_base(struct pci_dev *dev) +{ + return pci_resource_start(dev, 0); +} + +static inline resource_size_t p2_size(struct pci_dev *dev) +{ + return pci_resource_len(dev, 0); +} + +static int find_cxl_vsec(struct pci_dev *dev) +{ + int vsec = 0; + u16 val; + + while ((vsec = pci_find_next_ext_capability(dev, vsec, PCI_EXT_CAP_ID_VNDR))) { + pci_read_config_word(dev, vsec + 0x4, &val); + if (val == CXL_PCI_VSEC_ID) + return vsec; + } + return 0; + +} + +static void dump_cxl_config_space(struct pci_dev *dev) +{ + int vsec; + u32 val; + + dev_info(&dev->dev, "dump_cxl_config_space\n"); + + pci_read_config_dword(dev, PCI_BASE_ADDRESS_0, &val); + dev_info(&dev->dev, "BAR0: %#.8x\n", val); + pci_read_config_dword(dev, PCI_BASE_ADDRESS_1, &val); + dev_info(&dev->dev, "BAR1: %#.8x\n", val); + pci_read_config_dword(dev, PCI_BASE_ADDRESS_2, &val); + dev_info(&dev->dev, "BAR2: %#.8x\n", val); + pci_read_config_dword(dev, PCI_BASE_ADDRESS_3, &val); + dev_info(&dev->dev, "BAR3: %#.8x\n", val); + pci_read_config_dword(dev, PCI_BASE_ADDRESS_4, &val); + dev_info(&dev->dev, "BAR4: %#.8x\n", val); + pci_read_config_dword(dev, PCI_BASE_ADDRESS_5, &val); + dev_info(&dev->dev, "BAR5: %#.8x\n", val); + + dev_info(&dev->dev, "p1 regs: %#llx, len: %#llx\n", + p1_base(dev), p1_size(dev)); + dev_info(&dev->dev, "p2 regs: %#llx, len: %#llx\n", + p1_base(dev), p2_size(dev)); + dev_info(&dev->dev, "BAR 4/5: %#llx, len: %#llx\n", + pci_resource_start(dev, 4), pci_resource_len(dev, 4)); + + if (!(vsec = find_cxl_vsec(dev))) + return; + +#define show_reg(name, what) \ + dev_info(&dev->dev, "cxl vsec: %30s: %#x\n", name, what) + + pci_read_config_dword(dev, vsec + 0x0, &val); + show_reg("Cap ID", (val >> 0) & 0xffff); + show_reg("Cap Ver", (val >> 16) & 0xf); + show_reg("Next Cap Ptr", (val >> 20) & 0xfff); + pci_read_config_dword(dev, vsec + 0x4, &val); + show_reg("VSEC ID", (val >> 0) & 0xffff); + show_reg("VSEC Rev", (val >> 16) & 0xf); + show_reg("VSEC Length", (val >> 20) & 0xfff); + pci_read_config_dword(dev, vsec + 0x8, &val); + show_reg("Num AFUs", (val >> 0) & 0xff); + show_reg("Status", (val >> 8) & 0xff); + show_reg("Mode Control", (val >> 16) & 0xff); + show_reg("Reserved", (val >> 24) & 0xff); + pci_read_config_dword(dev, vsec + 0xc, &val); + show_reg("PSL Rev", (val >> 0) & 0xffff); + show_reg("CAIA Ver", (val >> 16) & 0xffff); + pci_read_config_dword(dev, vsec + 0x10, &val); + show_reg("Base Image Rev", (val >> 0) & 0xffff); + show_reg("Reserved", (val >> 16) & 0x0fff); + show_reg("Image Control", (val >> 28) & 0x3); + show_reg("Reserved", (val >> 30) & 0x1); + show_reg("Image Loaded", (val >> 31) & 0x1); + + pci_read_config_dword(dev, vsec + 0x14, &val); + show_reg("Reserved", val); + pci_read_config_dword(dev, vsec + 0x18, &val); + show_reg("Reserved", val); + pci_read_config_dword(dev, vsec + 0x1c, &val); + show_reg("Reserved", val); + + pci_read_config_dword(dev, vsec + 0x20, &val); + show_reg("AFU Descriptor Offset", val); + pci_read_config_dword(dev, vsec + 0x24, &val); + show_reg("AFU Descriptor Size", val); + pci_read_config_dword(dev, vsec + 0x28, &val); + show_reg("Problem State Offset", val); + pci_read_config_dword(dev, vsec + 0x2c, &val); + show_reg("Problem State Size", val); + + pci_read_config_dword(dev, vsec + 0x30, &val); + show_reg("Reserved", val); + pci_read_config_dword(dev, vsec + 0x34, &val); + show_reg("Reserved", val); + pci_read_config_dword(dev, vsec + 0x38, &val); + show_reg("Reserved", val); + pci_read_config_dword(dev, vsec + 0x3c, &val); + show_reg("Reserved", val); + + pci_read_config_dword(dev, vsec + 0x40, &val); + show_reg("PSL Programming Port", val); + pci_read_config_dword(dev, vsec + 0x44, &val); + show_reg("PSL Programming Control", val); + + pci_read_config_dword(dev, vsec + 0x48, &val); + show_reg("Reserved", val); + pci_read_config_dword(dev, vsec + 0x4c, &val); + show_reg("Reserved", val); + + pci_read_config_dword(dev, vsec + 0x50, &val); + show_reg("Flash Address Register", val); + pci_read_config_dword(dev, vsec + 0x54, &val); + show_reg("Flash Size Register", val); + pci_read_config_dword(dev, vsec + 0x58, &val); + show_reg("Flash Status/Control Register", val); + pci_read_config_dword(dev, vsec + 0x58, &val); + show_reg("Flash Data Port", val); + +#undef show_reg +} + +static void dump_afu_descriptor(struct cxl_afu *afu) +{ + u64 val; + +#define show_reg(name, what) \ + dev_info(&afu->dev, "afu desc: %30s: %#llx\n", name, what) + + val = AFUD_READ_INFO(afu); + show_reg("num_ints_per_process", AFUD_NUM_INTS_PER_PROC(val)); + show_reg("num_of_processes", AFUD_NUM_PROCS(val)); + show_reg("num_of_afu_CRs", AFUD_NUM_CRS(val)); + show_reg("req_prog_mode", val & 0xffffULL); + + val = AFUD_READ(afu, 0x8); + show_reg("Reserved", val); + val = AFUD_READ(afu, 0x10); + show_reg("Reserved", val); + val = AFUD_READ(afu, 0x18); + show_reg("Reserved", val); + + val = AFUD_READ_CR(afu); + show_reg("Reserved", (val >> (63-7)) & 0xff); + show_reg("AFU_CR_len", AFUD_CR_LEN(val)); + + val = AFUD_READ_CR_OFF(afu); + show_reg("AFU_CR_offset", val); + + val = AFUD_READ_PPPSA(afu); + show_reg("PerProcessPSA_control", (val >> (63-7)) & 0xff); + show_reg("PerProcessPSA Length", AFUD_PPPSA_LEN(val)); + + val = AFUD_READ_PPPSA_OFF(afu); + show_reg("PerProcessPSA_offset", val); + + val = AFUD_READ_EB(afu); + show_reg("Reserved", (val >> (63-7)) & 0xff); + show_reg("AFU_EB_len", AFUD_EB_LEN(val)); + + val = AFUD_READ_EB_OFF(afu); + show_reg("AFU_EB_offset", val); + +#undef show_reg +} + +static int init_implementation_adapter_regs(struct cxl *adapter, struct pci_dev *dev) +{ + struct device_node *np; + const __be32 *prop; + u64 psl_dsnctl; + u64 chipid; + + if (!(np = pnv_pci_to_phb_node(dev))) + return -ENODEV; + + while (np && !(prop = of_get_property(np, "ibm,chip-id", NULL))) + np = of_get_next_parent(np); + if (!np) + return -ENODEV; + chipid = be32_to_cpup(prop); + of_node_put(np); + + /* Tell PSL where to route data to */ + psl_dsnctl = 0x02E8900002000000ULL | (chipid << (63-5)); + cxl_p1_write(adapter, CXL_PSL_DSNDCTL, psl_dsnctl); + cxl_p1_write(adapter, CXL_PSL_RESLCKTO, 0x20000000200ULL); + /* snoop write mask */ + cxl_p1_write(adapter, CXL_PSL_SNWRALLOC, 0x00000000FFFFFFFFULL); + /* set fir_accum */ + cxl_p1_write(adapter, CXL_PSL_FIR_CNTL, 0x0800000000000000ULL); + /* for debugging with trace arrays */ + cxl_p1_write(adapter, CXL_PSL_TRACE, 0x0000FF7C00000000ULL); + + return 0; +} + +static int init_implementation_afu_regs(struct cxl_afu *afu) +{ + /* read/write masks for this slice */ + cxl_p1n_write(afu, CXL_PSL_APCALLOC_A, 0xFFFFFFFEFEFEFEFEULL); + /* APC read/write masks for this slice */ + cxl_p1n_write(afu, CXL_PSL_COALLOC_A, 0xFF000000FEFEFEFEULL); + /* for debugging with trace arrays */ + cxl_p1n_write(afu, CXL_PSL_SLICE_TRACE, 0x0000FFFF00000000ULL); + cxl_p1n_write(afu, CXL_PSL_RXCTL_A, 0xF000000000000000ULL); + + return 0; +} + +int cxl_setup_irq(struct cxl *adapter, unsigned int hwirq, + unsigned int virq) +{ + struct pci_dev *dev = to_pci_dev(adapter->dev.parent); + + return pnv_cxl_ioda_msi_setup(dev, hwirq, virq); +} + +int cxl_alloc_one_irq(struct cxl *adapter) +{ + struct pci_dev *dev = to_pci_dev(adapter->dev.parent); + + return pnv_cxl_alloc_hwirqs(dev, 1); +} + +void cxl_release_one_irq(struct cxl *adapter, int hwirq) +{ + struct pci_dev *dev = to_pci_dev(adapter->dev.parent); + + return pnv_cxl_release_hwirqs(dev, hwirq, 1); +} + +int cxl_alloc_irq_ranges(struct cxl_irq_ranges *irqs, struct cxl *adapter, unsigned int num) +{ + struct pci_dev *dev = to_pci_dev(adapter->dev.parent); + + return pnv_cxl_alloc_hwirq_ranges(irqs, dev, num); +} + +void cxl_release_irq_ranges(struct cxl_irq_ranges *irqs, struct cxl *adapter) +{ + struct pci_dev *dev = to_pci_dev(adapter->dev.parent); + + pnv_cxl_release_hwirq_ranges(irqs, dev); +} + +static int setup_cxl_bars(struct pci_dev *dev) +{ + /* Safety check in case we get backported to < 3.17 without M64 */ + if ((p1_base(dev) < 0x100000000ULL) || + (p2_base(dev) < 0x100000000ULL)) { + dev_err(&dev->dev, "ABORTING: M32 BAR assignment incompatible with CXL\n"); + return -ENODEV; + } + + /* + * BAR 4/5 has a special meaning for CXL and must be programmed with a + * special value corresponding to the CXL protocol address range. + * For POWER 8 that means bits 48:49 must be set to 10 + */ + pci_write_config_dword(dev, PCI_BASE_ADDRESS_4, 0x00000000); + pci_write_config_dword(dev, PCI_BASE_ADDRESS_5, 0x00020000); + + return 0; +} + +/* pciex node: ibm,opal-m64-window = <0x3d058 0x0 0x3d058 0x0 0x8 0x0>; */ +static int switch_card_to_cxl(struct pci_dev *dev) +{ + int vsec; + u8 val; + int rc; + + dev_info(&dev->dev, "switch card to CXL\n"); + + if (!(vsec = find_cxl_vsec(dev))) { + dev_err(&dev->dev, "ABORTING: CXL VSEC not found!\n"); + return -ENODEV; + } + + if ((rc = CXL_READ_VSEC_MODE_CONTROL(dev, vsec, &val))) { + dev_err(&dev->dev, "failed to read current mode control: %i", rc); + return rc; + } + val &= ~CXL_VSEC_PROTOCOL_MASK; + val |= CXL_VSEC_PROTOCOL_256TB | CXL_VSEC_PROTOCOL_ENABLE; + if ((rc = CXL_WRITE_VSEC_MODE_CONTROL(dev, vsec, val))) { + dev_err(&dev->dev, "failed to enable CXL protocol: %i", rc); + return rc; + } + /* + * The CAIA spec (v0.12 11.6 Bi-modal Device Support) states + * we must wait 100ms after this mode switch before touching + * PCIe config space. + */ + msleep(100); + + return 0; +} + +static int cxl_map_slice_regs(struct cxl_afu *afu, struct cxl *adapter, struct pci_dev *dev) +{ + u64 p1n_base, p2n_base, afu_desc; + const u64 p1n_size = 0x100; + const u64 p2n_size = 0x1000; + + p1n_base = p1_base(dev) + 0x10000 + (afu->slice * p1n_size); + p2n_base = p2_base(dev) + (afu->slice * p2n_size); + afu->psn_phys = p2_base(dev) + (adapter->ps_off + (afu->slice * adapter->ps_size)); + afu_desc = p2_base(dev) + adapter->afu_desc_off + (afu->slice * adapter->afu_desc_size); + + if (!(afu->p1n_mmio = ioremap(p1n_base, p1n_size))) + goto err; + if (!(afu->p2n_mmio = ioremap(p2n_base, p2n_size))) + goto err1; + if (afu_desc) { + if (!(afu->afu_desc_mmio = ioremap(afu_desc, adapter->afu_desc_size))) + goto err2; + } + + return 0; +err2: + iounmap(afu->p2n_mmio); +err1: + iounmap(afu->p1n_mmio); +err: + dev_err(&afu->dev, "Error mapping AFU MMIO regions\n"); + return -ENOMEM; +} + +static void cxl_unmap_slice_regs(struct cxl_afu *afu) +{ + if (afu->p1n_mmio) + iounmap(afu->p2n_mmio); + if (afu->p1n_mmio) + iounmap(afu->p1n_mmio); +} + +static void cxl_release_afu(struct device *dev) +{ + struct cxl_afu *afu = to_cxl_afu(dev); + + pr_devel("cxl_release_afu\n"); + + kfree(afu); +} + +static struct cxl_afu *cxl_alloc_afu(struct cxl *adapter, int slice) +{ + struct cxl_afu *afu; + + if (!(afu = kzalloc(sizeof(struct cxl_afu), GFP_KERNEL))) + return NULL; + + afu->adapter = adapter; + afu->dev.parent = &adapter->dev; + afu->dev.release = cxl_release_afu; + afu->slice = slice; + idr_init(&afu->contexts_idr); + spin_lock_init(&afu->contexts_lock); + spin_lock_init(&afu->afu_cntl_lock); + mutex_init(&afu->spa_mutex); + + afu->prefault_mode = CXL_PREFAULT_NONE; + afu->irqs_max = afu->adapter->user_irqs; + + return afu; +} + +/* Expects AFU struct to have recently been zeroed out */ +static int cxl_read_afu_descriptor(struct cxl_afu *afu) +{ + u64 val; + + val = AFUD_READ_INFO(afu); + afu->pp_irqs = AFUD_NUM_INTS_PER_PROC(val); + afu->max_procs_virtualised = AFUD_NUM_PROCS(val); + + if (AFUD_AFU_DIRECTED(val)) + afu->modes_supported |= CXL_MODE_DIRECTED; + if (AFUD_DEDICATED_PROCESS(val)) + afu->modes_supported |= CXL_MODE_DEDICATED; + if (AFUD_TIME_SLICED(val)) + afu->modes_supported |= CXL_MODE_TIME_SLICED; + + val = AFUD_READ_PPPSA(afu); + afu->pp_size = AFUD_PPPSA_LEN(val) * 4096; + afu->psa = AFUD_PPPSA_PSA(val); + if ((afu->pp_psa = AFUD_PPPSA_PP(val))) + afu->pp_offset = AFUD_READ_PPPSA_OFF(afu); + + return 0; +} + +static int cxl_afu_descriptor_looks_ok(struct cxl_afu *afu) +{ + if (afu->psa && afu->adapter->ps_size < + (afu->pp_offset + afu->pp_size*afu->max_procs_virtualised)) { + dev_err(&afu->dev, "per-process PSA can't fit inside the PSA!\n"); + return -ENODEV; + } + + if (afu->pp_psa && (afu->pp_size < PAGE_SIZE)) + dev_warn(&afu->dev, "AFU uses < PAGE_SIZE per-process PSA!"); + + return 0; +} + +static int sanitise_afu_regs(struct cxl_afu *afu) +{ + u64 reg; + + /* + * Clear out any regs that contain either an IVTE or address or may be + * waiting on an acknowledgement to try to be a bit safer as we bring + * it online + */ + reg = cxl_p2n_read(afu, CXL_AFU_Cntl_An); + if ((reg & CXL_AFU_Cntl_An_ES_MASK) != CXL_AFU_Cntl_An_ES_Disabled) { + dev_warn(&afu->dev, "WARNING: AFU was not disabled: %#.16llx\n", reg); + if (cxl_afu_reset(afu)) + return -EIO; + if (cxl_afu_disable(afu)) + return -EIO; + if (cxl_psl_purge(afu)) + return -EIO; + } + cxl_p1n_write(afu, CXL_PSL_SPAP_An, 0x0000000000000000); + cxl_p1n_write(afu, CXL_PSL_IVTE_Limit_An, 0x0000000000000000); + cxl_p1n_write(afu, CXL_PSL_IVTE_Offset_An, 0x0000000000000000); + cxl_p1n_write(afu, CXL_PSL_AMBAR_An, 0x0000000000000000); + cxl_p1n_write(afu, CXL_PSL_SPOffset_An, 0x0000000000000000); + cxl_p1n_write(afu, CXL_HAURP_An, 0x0000000000000000); + cxl_p2n_write(afu, CXL_CSRP_An, 0x0000000000000000); + cxl_p2n_write(afu, CXL_AURP1_An, 0x0000000000000000); + cxl_p2n_write(afu, CXL_AURP0_An, 0x0000000000000000); + cxl_p2n_write(afu, CXL_SSTP1_An, 0x0000000000000000); + cxl_p2n_write(afu, CXL_SSTP0_An, 0x0000000000000000); + reg = cxl_p2n_read(afu, CXL_PSL_DSISR_An); + if (reg) { + dev_warn(&afu->dev, "AFU had pending DSISR: %#.16llx\n", reg); + if (reg & CXL_PSL_DSISR_TRANS) + cxl_p2n_write(afu, CXL_PSL_TFC_An, CXL_PSL_TFC_An_AE); + else + cxl_p2n_write(afu, CXL_PSL_TFC_An, CXL_PSL_TFC_An_A); + } + reg = cxl_p1n_read(afu, CXL_PSL_SERR_An); + if (reg) { + if (reg & ~0xffff) + dev_warn(&afu->dev, "AFU had pending SERR: %#.16llx\n", reg); + cxl_p1n_write(afu, CXL_PSL_SERR_An, reg & ~0xffff); + } + reg = cxl_p2n_read(afu, CXL_PSL_ErrStat_An); + if (reg) { + dev_warn(&afu->dev, "AFU had pending error status: %#.16llx\n", reg); + cxl_p2n_write(afu, CXL_PSL_ErrStat_An, reg); + } + + return 0; +} + +static int cxl_init_afu(struct cxl *adapter, int slice, struct pci_dev *dev) +{ + struct cxl_afu *afu; + bool free = true; + int rc; + + if (!(afu = cxl_alloc_afu(adapter, slice))) + return -ENOMEM; + + if ((rc = dev_set_name(&afu->dev, "afu%i.%i", adapter->adapter_num, slice))) + goto err1; + + if ((rc = cxl_map_slice_regs(afu, adapter, dev))) + goto err1; + + if ((rc = sanitise_afu_regs(afu))) + goto err2; + + /* We need to reset the AFU before we can read the AFU descriptor */ + if ((rc = cxl_afu_reset(afu))) + goto err2; + + if (cxl_verbose) + dump_afu_descriptor(afu); + + if ((rc = cxl_read_afu_descriptor(afu))) + goto err2; + + if ((rc = cxl_afu_descriptor_looks_ok(afu))) + goto err2; + + if ((rc = init_implementation_afu_regs(afu))) + goto err2; + + if ((rc = cxl_register_serr_irq(afu))) + goto err2; + + if ((rc = cxl_register_psl_irq(afu))) + goto err3; + + /* Don't care if this fails */ + cxl_debugfs_afu_add(afu); + + /* + * After we call this function we must not free the afu directly, even + * if it returns an error! + */ + if ((rc = cxl_register_afu(afu))) + goto err_put1; + + if ((rc = cxl_sysfs_afu_add(afu))) + goto err_put1; + + + if ((rc = cxl_afu_select_best_mode(afu))) + goto err_put2; + + adapter->afu[afu->slice] = afu; + + return 0; + +err_put2: + cxl_sysfs_afu_remove(afu); +err_put1: + device_unregister(&afu->dev); + free = false; + cxl_debugfs_afu_remove(afu); + cxl_release_psl_irq(afu); +err3: + cxl_release_serr_irq(afu); +err2: + cxl_unmap_slice_regs(afu); +err1: + if (free) + kfree(afu); + return rc; +} + +static void cxl_remove_afu(struct cxl_afu *afu) +{ + pr_devel("cxl_remove_afu\n"); + + if (!afu) + return; + + cxl_sysfs_afu_remove(afu); + cxl_debugfs_afu_remove(afu); + + spin_lock(&afu->adapter->afu_list_lock); + afu->adapter->afu[afu->slice] = NULL; + spin_unlock(&afu->adapter->afu_list_lock); + + cxl_context_detach_all(afu); + cxl_afu_deactivate_mode(afu); + + cxl_release_psl_irq(afu); + cxl_release_serr_irq(afu); + cxl_unmap_slice_regs(afu); + + device_unregister(&afu->dev); +} + + +static int cxl_map_adapter_regs(struct cxl *adapter, struct pci_dev *dev) +{ + if (pci_request_region(dev, 2, "priv 2 regs")) + goto err1; + if (pci_request_region(dev, 0, "priv 1 regs")) + goto err2; + + pr_devel("cxl_map_adapter_regs: p1: %#.16llx %#llx, p2: %#.16llx %#llx", + p1_base(dev), p1_size(dev), p2_base(dev), p2_size(dev)); + + if (!(adapter->p1_mmio = ioremap(p1_base(dev), p1_size(dev)))) + goto err3; + + if (!(adapter->p2_mmio = ioremap(p2_base(dev), p2_size(dev)))) + goto err4; + + return 0; + +err4: + iounmap(adapter->p1_mmio); + adapter->p1_mmio = NULL; +err3: + pci_release_region(dev, 0); +err2: + pci_release_region(dev, 2); +err1: + return -ENOMEM; +} + +static void cxl_unmap_adapter_regs(struct cxl *adapter) +{ + if (adapter->p1_mmio) + iounmap(adapter->p1_mmio); + if (adapter->p2_mmio) + iounmap(adapter->p2_mmio); +} + +static int cxl_read_vsec(struct cxl *adapter, struct pci_dev *dev) +{ + int vsec; + u32 afu_desc_off, afu_desc_size; + u32 ps_off, ps_size; + u16 vseclen; + u8 image_state; + + if (!(vsec = find_cxl_vsec(dev))) { + dev_err(&adapter->dev, "ABORTING: CXL VSEC not found!\n"); + return -ENODEV; + } + + CXL_READ_VSEC_LENGTH(dev, vsec, &vseclen); + if (vseclen < CXL_VSEC_MIN_SIZE) { + pr_err("ABORTING: CXL VSEC too short\n"); + return -EINVAL; + } + + CXL_READ_VSEC_STATUS(dev, vsec, &adapter->vsec_status); + CXL_READ_VSEC_PSL_REVISION(dev, vsec, &adapter->psl_rev); + CXL_READ_VSEC_CAIA_MAJOR(dev, vsec, &adapter->caia_major); + CXL_READ_VSEC_CAIA_MINOR(dev, vsec, &adapter->caia_minor); + CXL_READ_VSEC_BASE_IMAGE(dev, vsec, &adapter->base_image); + CXL_READ_VSEC_IMAGE_STATE(dev, vsec, &image_state); + adapter->user_image_loaded = !!(image_state & CXL_VSEC_USER_IMAGE_LOADED); + adapter->perst_loads_image = !!(image_state & CXL_VSEC_PERST_LOADS_IMAGE); + adapter->perst_select_user = !!(image_state & CXL_VSEC_PERST_SELECT_USER); + + CXL_READ_VSEC_NAFUS(dev, vsec, &adapter->slices); + CXL_READ_VSEC_AFU_DESC_OFF(dev, vsec, &afu_desc_off); + CXL_READ_VSEC_AFU_DESC_SIZE(dev, vsec, &afu_desc_size); + CXL_READ_VSEC_PS_OFF(dev, vsec, &ps_off); + CXL_READ_VSEC_PS_SIZE(dev, vsec, &ps_size); + + /* Convert everything to bytes, because there is NO WAY I'd look at the + * code a month later and forget what units these are in ;-) */ + adapter->ps_off = ps_off * 64 * 1024; + adapter->ps_size = ps_size * 64 * 1024; + adapter->afu_desc_off = afu_desc_off * 64 * 1024; + adapter->afu_desc_size = afu_desc_size *64 * 1024; + + /* Total IRQs - 1 PSL ERROR - #AFU*(1 slice error + 1 DSI) */ + adapter->user_irqs = pnv_cxl_get_irq_count(dev) - 1 - 2*adapter->slices; + + return 0; +} + +static int cxl_vsec_looks_ok(struct cxl *adapter, struct pci_dev *dev) +{ + if (adapter->vsec_status & CXL_STATUS_SECOND_PORT) + return -EBUSY; + + if (adapter->vsec_status & CXL_UNSUPPORTED_FEATURES) { + dev_err(&adapter->dev, "ABORTING: CXL requires unsupported features\n"); + return -EINVAL; + } + + if (!adapter->slices) { + /* Once we support dynamic reprogramming we can use the card if + * it supports loadable AFUs */ + dev_err(&adapter->dev, "ABORTING: Device has no AFUs\n"); + return -EINVAL; + } + + if (!adapter->afu_desc_off || !adapter->afu_desc_size) { + dev_err(&adapter->dev, "ABORTING: VSEC shows no AFU descriptors\n"); + return -EINVAL; + } + + if (adapter->ps_size > p2_size(dev) - adapter->ps_off) { + dev_err(&adapter->dev, "ABORTING: Problem state size larger than " + "available in BAR2: 0x%llx > 0x%llx\n", + adapter->ps_size, p2_size(dev) - adapter->ps_off); + return -EINVAL; + } + + return 0; +} + +static void cxl_release_adapter(struct device *dev) +{ + struct cxl *adapter = to_cxl_adapter(dev); + + pr_devel("cxl_release_adapter\n"); + + kfree(adapter); +} + +static struct cxl *cxl_alloc_adapter(struct pci_dev *dev) +{ + struct cxl *adapter; + + if (!(adapter = kzalloc(sizeof(struct cxl), GFP_KERNEL))) + return NULL; + + adapter->dev.parent = &dev->dev; + adapter->dev.release = cxl_release_adapter; + pci_set_drvdata(dev, adapter); + spin_lock_init(&adapter->afu_list_lock); + + return adapter; +} + +static int sanitise_adapter_regs(struct cxl *adapter) +{ + cxl_p1_write(adapter, CXL_PSL_ErrIVTE, 0x0000000000000000); + return cxl_tlb_slb_invalidate(adapter); +} + +static struct cxl *cxl_init_adapter(struct pci_dev *dev) +{ + struct cxl *adapter; + bool free = true; + int rc; + + + if (!(adapter = cxl_alloc_adapter(dev))) + return ERR_PTR(-ENOMEM); + + if ((rc = switch_card_to_cxl(dev))) + goto err1; + + if ((rc = cxl_alloc_adapter_nr(adapter))) + goto err1; + + if ((rc = dev_set_name(&adapter->dev, "card%i", adapter->adapter_num))) + goto err2; + + if ((rc = cxl_read_vsec(adapter, dev))) + goto err2; + + if ((rc = cxl_vsec_looks_ok(adapter, dev))) + goto err2; + + if ((rc = cxl_map_adapter_regs(adapter, dev))) + goto err2; + + if ((rc = sanitise_adapter_regs(adapter))) + goto err2; + + if ((rc = init_implementation_adapter_regs(adapter, dev))) + goto err3; + + if ((rc = pnv_phb_to_cxl(dev))) + goto err3; + + if ((rc = cxl_register_psl_err_irq(adapter))) + goto err3; + + /* Don't care if this one fails: */ + cxl_debugfs_adapter_add(adapter); + + /* + * After we call this function we must not free the adapter directly, + * even if it returns an error! + */ + if ((rc = cxl_register_adapter(adapter))) + goto err_put1; + + if ((rc = cxl_sysfs_adapter_add(adapter))) + goto err_put1; + + return adapter; + +err_put1: + device_unregister(&adapter->dev); + free = false; + cxl_debugfs_adapter_remove(adapter); + cxl_release_psl_err_irq(adapter); +err3: + cxl_unmap_adapter_regs(adapter); +err2: + cxl_remove_adapter_nr(adapter); +err1: + if (free) + kfree(adapter); + return ERR_PTR(rc); +} + +static void cxl_remove_adapter(struct cxl *adapter) +{ + struct pci_dev *pdev = to_pci_dev(adapter->dev.parent); + + pr_devel("cxl_release_adapter\n"); + + cxl_sysfs_adapter_remove(adapter); + cxl_debugfs_adapter_remove(adapter); + cxl_release_psl_err_irq(adapter); + cxl_unmap_adapter_regs(adapter); + cxl_remove_adapter_nr(adapter); + + device_unregister(&adapter->dev); + + pci_release_region(pdev, 0); + pci_release_region(pdev, 2); + pci_disable_device(pdev); +} + +static int cxl_probe(struct pci_dev *dev, const struct pci_device_id *id) +{ + struct cxl *adapter; + int slice; + int rc; + + pci_dev_get(dev); + + if (cxl_verbose) + dump_cxl_config_space(dev); + + if ((rc = setup_cxl_bars(dev))) + return rc; + + if ((rc = pci_enable_device(dev))) { + dev_err(&dev->dev, "pci_enable_device failed: %i\n", rc); + return rc; + } + + adapter = cxl_init_adapter(dev); + if (IS_ERR(adapter)) { + dev_err(&dev->dev, "cxl_init_adapter failed: %li\n", PTR_ERR(adapter)); + return PTR_ERR(adapter); + } + + for (slice = 0; slice < adapter->slices; slice++) { + if ((rc = cxl_init_afu(adapter, slice, dev))) + dev_err(&dev->dev, "AFU %i failed to initialise: %i\n", slice, rc); + } + + return 0; +} + +static void cxl_remove(struct pci_dev *dev) +{ + struct cxl *adapter = pci_get_drvdata(dev); + int afu; + + dev_warn(&dev->dev, "pci remove\n"); + + /* + * Lock to prevent someone grabbing a ref through the adapter list as + * we are removing it + */ + for (afu = 0; afu < adapter->slices; afu++) + cxl_remove_afu(adapter->afu[afu]); + cxl_remove_adapter(adapter); +} + +struct pci_driver cxl_pci_driver = { + .name = "cxl-pci", + .id_table = cxl_pci_tbl, + .probe = cxl_probe, + .remove = cxl_remove, +}; diff --git a/drivers/misc/cxl/sysfs.c b/drivers/misc/cxl/sysfs.c new file mode 100644 index 000000000000..ce7ec06d87d1 --- /dev/null +++ b/drivers/misc/cxl/sysfs.c @@ -0,0 +1,385 @@ +/* + * 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/kernel.h> +#include <linux/device.h> +#include <linux/sysfs.h> + +#include "cxl.h" + +#define to_afu_chardev_m(d) dev_get_drvdata(d) + +/********* Adapter attributes **********************************************/ + +static ssize_t caia_version_show(struct device *device, + struct device_attribute *attr, + char *buf) +{ + struct cxl *adapter = to_cxl_adapter(device); + + return scnprintf(buf, PAGE_SIZE, "%i.%i\n", adapter->caia_major, + adapter->caia_minor); +} + +static ssize_t psl_revision_show(struct device *device, + struct device_attribute *attr, + char *buf) +{ + struct cxl *adapter = to_cxl_adapter(device); + + return scnprintf(buf, PAGE_SIZE, "%i\n", adapter->psl_rev); +} + +static ssize_t base_image_show(struct device *device, + struct device_attribute *attr, + char *buf) +{ + struct cxl *adapter = to_cxl_adapter(device); + + return scnprintf(buf, PAGE_SIZE, "%i\n", adapter->base_image); +} + +static ssize_t image_loaded_show(struct device *device, + struct device_attribute *attr, + char *buf) +{ + struct cxl *adapter = to_cxl_adapter(device); + + if (adapter->user_image_loaded) + return scnprintf(buf, PAGE_SIZE, "user\n"); + return scnprintf(buf, PAGE_SIZE, "factory\n"); +} + +static struct device_attribute adapter_attrs[] = { + __ATTR_RO(caia_version), + __ATTR_RO(psl_revision), + __ATTR_RO(base_image), + __ATTR_RO(image_loaded), +}; + + +/********* AFU master specific attributes **********************************/ + +static ssize_t mmio_size_show_master(struct device *device, + struct device_attribute *attr, + char *buf) +{ + struct cxl_afu *afu = to_afu_chardev_m(device); + + return scnprintf(buf, PAGE_SIZE, "%llu\n", afu->adapter->ps_size); +} + +static ssize_t pp_mmio_off_show(struct device *device, + struct device_attribute *attr, + char *buf) +{ + struct cxl_afu *afu = to_afu_chardev_m(device); + + return scnprintf(buf, PAGE_SIZE, "%llu\n", afu->pp_offset); +} + +static ssize_t pp_mmio_len_show(struct device *device, + struct device_attribute *attr, + char *buf) +{ + struct cxl_afu *afu = to_afu_chardev_m(device); + + return scnprintf(buf, PAGE_SIZE, "%llu\n", afu->pp_size); +} + +static struct device_attribute afu_master_attrs[] = { + __ATTR(mmio_size, S_IRUGO, mmio_size_show_master, NULL), + __ATTR_RO(pp_mmio_off), + __ATTR_RO(pp_mmio_len), +}; + + +/********* AFU attributes **************************************************/ + +static ssize_t mmio_size_show(struct device *device, + struct device_attribute *attr, + char *buf) +{ + struct cxl_afu *afu = to_cxl_afu(device); + + if (afu->pp_size) + return scnprintf(buf, PAGE_SIZE, "%llu\n", afu->pp_size); + return scnprintf(buf, PAGE_SIZE, "%llu\n", afu->adapter->ps_size); +} + +static ssize_t reset_store_afu(struct device *device, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct cxl_afu *afu = to_cxl_afu(device); + int rc; + + /* Not safe to reset if it is currently in use */ + spin_lock(&afu->contexts_lock); + if (!idr_is_empty(&afu->contexts_idr)) { + rc = -EBUSY; + goto err; + } + + if ((rc = cxl_afu_reset(afu))) + goto err; + + rc = count; +err: + spin_unlock(&afu->contexts_lock); + return rc; +} + +static ssize_t irqs_min_show(struct device *device, + struct device_attribute *attr, + char *buf) +{ + struct cxl_afu *afu = to_cxl_afu(device); + + return scnprintf(buf, PAGE_SIZE, "%i\n", afu->pp_irqs); +} + +static ssize_t irqs_max_show(struct device *device, + struct device_attribute *attr, + char *buf) +{ + struct cxl_afu *afu = to_cxl_afu(device); + + return scnprintf(buf, PAGE_SIZE, "%i\n", afu->irqs_max); +} + +static ssize_t irqs_max_store(struct device *device, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct cxl_afu *afu = to_cxl_afu(device); + ssize_t ret; + int irqs_max; + + ret = sscanf(buf, "%i", &irqs_max); + if (ret != 1) + return -EINVAL; + + if (irqs_max < afu->pp_irqs) + return -EINVAL; + + if (irqs_max > afu->adapter->user_irqs) + return -EINVAL; + + afu->irqs_max = irqs_max; + return count; +} + +static ssize_t modes_supported_show(struct device *device, + struct device_attribute *attr, char *buf) +{ + struct cxl_afu *afu = to_cxl_afu(device); + char *p = buf, *end = buf + PAGE_SIZE; + + if (afu->modes_supported & CXL_MODE_DEDICATED) + p += scnprintf(p, end - p, "dedicated_process\n"); + if (afu->modes_supported & CXL_MODE_DIRECTED) + p += scnprintf(p, end - p, "afu_directed\n"); + return (p - buf); +} + +static ssize_t prefault_mode_show(struct device *device, + struct device_attribute *attr, + char *buf) +{ + struct cxl_afu *afu = to_cxl_afu(device); + + switch (afu->prefault_mode) { + case CXL_PREFAULT_WED: + return scnprintf(buf, PAGE_SIZE, "work_element_descriptor\n"); + case CXL_PREFAULT_ALL: + return scnprintf(buf, PAGE_SIZE, "all\n"); + default: + return scnprintf(buf, PAGE_SIZE, "none\n"); + } +} + +static ssize_t prefault_mode_store(struct device *device, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct cxl_afu *afu = to_cxl_afu(device); + enum prefault_modes mode = -1; + + if (!strncmp(buf, "work_element_descriptor", 23)) + mode = CXL_PREFAULT_WED; + if (!strncmp(buf, "all", 3)) + mode = CXL_PREFAULT_ALL; + if (!strncmp(buf, "none", 4)) + mode = CXL_PREFAULT_NONE; + + if (mode == -1) + return -EINVAL; + + afu->prefault_mode = mode; + return count; +} + +static ssize_t mode_show(struct device *device, + struct device_attribute *attr, + char *buf) +{ + struct cxl_afu *afu = to_cxl_afu(device); + + if (afu->current_mode == CXL_MODE_DEDICATED) + return scnprintf(buf, PAGE_SIZE, "dedicated_process\n"); + if (afu->current_mode == CXL_MODE_DIRECTED) + return scnprintf(buf, PAGE_SIZE, "afu_directed\n"); + return scnprintf(buf, PAGE_SIZE, "none\n"); +} + +static ssize_t mode_store(struct device *device, struct device_attribute *attr, + const char *buf, size_t count) +{ + struct cxl_afu *afu = to_cxl_afu(device); + int old_mode, mode = -1; + int rc = -EBUSY; + + /* can't change this if we have a user */ + spin_lock(&afu->contexts_lock); + if (!idr_is_empty(&afu->contexts_idr)) + goto err; + + if (!strncmp(buf, "dedicated_process", 17)) + mode = CXL_MODE_DEDICATED; + if (!strncmp(buf, "afu_directed", 12)) + mode = CXL_MODE_DIRECTED; + if (!strncmp(buf, "none", 4)) + mode = 0; + + if (mode == -1) { + rc = -EINVAL; + goto err; + } + + /* + * cxl_afu_deactivate_mode needs to be done outside the lock, prevent + * other contexts coming in before we are ready: + */ + old_mode = afu->current_mode; + afu->current_mode = 0; + afu->num_procs = 0; + + spin_unlock(&afu->contexts_lock); + + if ((rc = _cxl_afu_deactivate_mode(afu, old_mode))) + return rc; + if ((rc = cxl_afu_activate_mode(afu, mode))) + return rc; + + return count; +err: + spin_unlock(&afu->contexts_lock); + return rc; +} + +static ssize_t api_version_show(struct device *device, + struct device_attribute *attr, + char *buf) +{ + return scnprintf(buf, PAGE_SIZE, "%i\n", CXL_API_VERSION); +} + +static ssize_t api_version_compatible_show(struct device *device, + struct device_attribute *attr, + char *buf) +{ + return scnprintf(buf, PAGE_SIZE, "%i\n", CXL_API_VERSION_COMPATIBLE); +} + +static struct device_attribute afu_attrs[] = { + __ATTR_RO(mmio_size), + __ATTR_RO(irqs_min), + __ATTR_RW(irqs_max), + __ATTR_RO(modes_supported), + __ATTR_RW(mode), + __ATTR_RW(prefault_mode), + __ATTR_RO(api_version), + __ATTR_RO(api_version_compatible), + __ATTR(reset, S_IWUSR, NULL, reset_store_afu), +}; + + + +int cxl_sysfs_adapter_add(struct cxl *adapter) +{ + int i, rc; + + for (i = 0; i < ARRAY_SIZE(adapter_attrs); i++) { + if ((rc = device_create_file(&adapter->dev, &adapter_attrs[i]))) + goto err; + } + return 0; +err: + for (i--; i >= 0; i--) + device_remove_file(&adapter->dev, &adapter_attrs[i]); + return rc; +} +void cxl_sysfs_adapter_remove(struct cxl *adapter) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(adapter_attrs); i++) + device_remove_file(&adapter->dev, &adapter_attrs[i]); +} + +int cxl_sysfs_afu_add(struct cxl_afu *afu) +{ + int i, rc; + + for (i = 0; i < ARRAY_SIZE(afu_attrs); i++) { + if ((rc = device_create_file(&afu->dev, &afu_attrs[i]))) + goto err; + } + + return 0; + +err: + for (i--; i >= 0; i--) + device_remove_file(&afu->dev, &afu_attrs[i]); + return rc; +} + +void cxl_sysfs_afu_remove(struct cxl_afu *afu) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(afu_attrs); i++) + device_remove_file(&afu->dev, &afu_attrs[i]); +} + +int cxl_sysfs_afu_m_add(struct cxl_afu *afu) +{ + int i, rc; + + for (i = 0; i < ARRAY_SIZE(afu_master_attrs); i++) { + if ((rc = device_create_file(afu->chardev_m, &afu_master_attrs[i]))) + goto err; + } + + return 0; + +err: + for (i--; i >= 0; i--) + device_remove_file(afu->chardev_m, &afu_master_attrs[i]); + return rc; +} + +void cxl_sysfs_afu_m_remove(struct cxl_afu *afu) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(afu_master_attrs); i++) + device_remove_file(afu->chardev_m, &afu_master_attrs[i]); +} |