iv/linux
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
a6b07d8257
linux/drivers/misc/cxl/cxl.h

677 lines
24 KiB
C
Raw Normal View History

cxl: Driver code for powernv PCIe based cards for userspace access This is the core of the cxl driver. It adds support for using cxl cards in the powernv environment only (ie POWER8 bare metal). It allows access to cxl accelerators by userspace using the /dev/cxl/afuM.N char devices. The kernel driver has no knowledge of the function implemented by the accelerator. It provides services to userspace via the /dev/cxl/afuM.N devices. When a program opens this device and runs the start work IOCTL, the accelerator will have coherent access to that processes memory using the same virtual addresses. That process may mmap the device to access any MMIO space the accelerator provides. Also, reads on the device will allow interrupts to be received. These services are further documented in a later patch in Documentation/powerpc/cxl.txt. Documentation of the cxl hardware architecture and userspace API is provided in subsequent patches. Signed-off-by: Ian Munsie <imunsie@au1.ibm.com> Signed-off-by: Michael Neuling <mikey@neuling.org> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2014-10-08 12:55:02 +04:00
/*
* 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 */
cxl: Disable AFU debug flag Upon inspection of the implementation specific registers, it was discovered that the high bit of the implementation specific RXCTL register was enabled, which enables the DEADB00F debug feature. The debug feature causes MMIO reads to a disabled AFU to respond with 0xDEADB00F instead of all Fs. In general this should not be visible as the kernel will only allow MMIO access to enabled AFUs, but there may be some circumstances where an AFU may become disabled while it is use. One such case would be an AFU designed to only be used in the dedicated process mode and to disable itself after it has completed it's work (however even in that case the effects of this debug flag would be limited as the userspace application must have completed any required MMIO accesses before the AFU disables itself with or without the flag). This patch removes the debug flag and replaces the magic value programmed into this register with a preprocessor define so it is clearer what the rest of this initialisation does. Signed-off-by: Ian Munsie <imunsie@au1.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2014-12-08 11:17:59 +03:00
/****** CXL_PSL_RXCTL_An (Implementation Specific) **************************
* Controls AFU Hang Pulse, which sets the timeout for the AFU to respond to
* the PSL for any response (except MMIO). Timeouts will occur between 1x to 2x
* of the hang pulse frequency.
*/
#define CXL_PSL_RXCTL_AFUHP_4S 0x7000000000000000ULL
cxl: Driver code for powernv PCIe based cards for userspace access This is the core of the cxl driver. It adds support for using cxl cards in the powernv environment only (ie POWER8 bare metal). It allows access to cxl accelerators by userspace using the /dev/cxl/afuM.N char devices. The kernel driver has no knowledge of the function implemented by the accelerator. It provides services to userspace via the /dev/cxl/afuM.N devices. When a program opens this device and runs the start work IOCTL, the accelerator will have coherent access to that processes memory using the same virtual addresses. That process may mmap the device to access any MMIO space the accelerator provides. Also, reads on the device will allow interrupts to be received. These services are further documented in a later patch in Documentation/powerpc/cxl.txt. Documentation of the cxl hardware architecture and userspace API is provided in subsequent patches. Signed-off-by: Ian Munsie <imunsie@au1.ibm.com> Signed-off-by: Michael Neuling <mikey@neuling.org> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2014-10-08 12:55:02 +04:00
/* 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_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;
cxl: Name interrupts in /proc/interrupt Currently all interrupts generated by cxl are named "cxl". This is not very informative as we can't distinguish between cards, AFUs, error interrupts, user contexts and user interrupts numbers. Being able to distinguish them is useful for setting affinity. This patch gives each of these names in /proc/interrupts. A two card CAPI system, with afu0.0 having 2 active contexts each with 4 user IRQs each, will now look like this: % grep cxl /proc/interrupts 444: 0 OPAL ICS 141312 Level cxl-card1-err 445: 0 OPAL ICS 141313 Level cxl-afu1.0-err 446: 0 OPAL ICS 141314 Level cxl-afu1.0 462: 0 OPAL ICS 2052 Level cxl-afu0.0-pe0-1 463: 75517 OPAL ICS 2053 Level cxl-afu0.0-pe0-2 468: 0 OPAL ICS 2054 Level cxl-afu0.0-pe0-3 469: 0 OPAL ICS 2055 Level cxl-afu0.0-pe0-4 470: 0 OPAL ICS 2056 Level cxl-afu0.0-pe1-1 471: 75506 OPAL ICS 2057 Level cxl-afu0.0-pe1-2 472: 0 OPAL ICS 2058 Level cxl-afu0.0-pe1-3 473: 0 OPAL ICS 2059 Level cxl-afu0.0-pe1-4 502: 1066 OPAL ICS 2050 Level cxl-afu0.0 514: 0 OPAL ICS 2048 Level cxl-card0-err 515: 0 OPAL ICS 2049 Level cxl-afu0.0-err Signed-off-by: Michael Neuling <mikey@neuling.org> Signed-off-by: Ian Munsie <imunsie@au1.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2014-11-14 10:09:28 +03:00
char *err_irq_name;
char *psl_irq_name;
cxl: Driver code for powernv PCIe based cards for userspace access This is the core of the cxl driver. It adds support for using cxl cards in the powernv environment only (ie POWER8 bare metal). It allows access to cxl accelerators by userspace using the /dev/cxl/afuM.N char devices. The kernel driver has no knowledge of the function implemented by the accelerator. It provides services to userspace via the /dev/cxl/afuM.N devices. When a program opens this device and runs the start work IOCTL, the accelerator will have coherent access to that processes memory using the same virtual addresses. That process may mmap the device to access any MMIO space the accelerator provides. Also, reads on the device will allow interrupts to be received. These services are further documented in a later patch in Documentation/powerpc/cxl.txt. Documentation of the cxl hardware architecture and userspace API is provided in subsequent patches. Signed-off-by: Ian Munsie <imunsie@au1.ibm.com> Signed-off-by: Michael Neuling <mikey@neuling.org> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2014-10-08 12:55:02 +04:00
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;
cxl: Change contexts_lock to a mutex to fix sleep while atomic bug We had a known sleep while atomic bug if a CXL device was forcefully unbound while it was in use. This could occur as a result of EEH, or manually induced with something like this while the device was in use: echo 0000:01:00.0 > /sys/bus/pci/drivers/cxl-pci/unbind The issue was that in this code path we iterated over each context and forcefully detached it with the contexts_lock spin lock held, however the detach also needed to take the spu_mutex, and call schedule. This patch changes the contexts_lock to a mutex so that we are not in atomic context while doing the detach, thereby avoiding the sleep while atomic. Also delete the related TODO comment, which suggested an alternate solution which turned out to not be workable. Cc: stable@vger.kernel.org Signed-off-by: Ian Munsie <imunsie@au1.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2014-12-08 11:17:55 +03:00
struct mutex contexts_lock;
cxl: Driver code for powernv PCIe based cards for userspace access This is the core of the cxl driver. It adds support for using cxl cards in the powernv environment only (ie POWER8 bare metal). It allows access to cxl accelerators by userspace using the /dev/cxl/afuM.N char devices. The kernel driver has no knowledge of the function implemented by the accelerator. It provides services to userspace via the /dev/cxl/afuM.N devices. When a program opens this device and runs the start work IOCTL, the accelerator will have coherent access to that processes memory using the same virtual addresses. That process may mmap the device to access any MMIO space the accelerator provides. Also, reads on the device will allow interrupts to be received. These services are further documented in a later patch in Documentation/powerpc/cxl.txt. Documentation of the cxl hardware architecture and userspace API is provided in subsequent patches. Signed-off-by: Ian Munsie <imunsie@au1.ibm.com> Signed-off-by: Michael Neuling <mikey@neuling.org> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2014-10-08 12:55:02 +04:00
struct mutex spa_mutex;
spinlock_t afu_cntl_lock;
cxl: Export AFU error buffer via sysfs Export the "AFU Error Buffer" via sysfs attribute (afu_err_buf). AFU error buffer is used by the AFU to report application specific errors. The contents of this buffer are AFU specific and are intended to be interpreted by the application interacting with the afu. Suggested-by: Michael Neuling <mikey@neuling.org> Signed-off-by: Vaibhav Jain <vaibhav@linux.vnet.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2015-05-22 08:26:05 +03:00
/* AFU error buffer fields and bin attribute for sysfs */
u64 eb_len, eb_offset;
struct bin_attribute attr_eb;
cxl: Driver code for powernv PCIe based cards for userspace access This is the core of the cxl driver. It adds support for using cxl cards in the powernv environment only (ie POWER8 bare metal). It allows access to cxl accelerators by userspace using the /dev/cxl/afuM.N char devices. The kernel driver has no knowledge of the function implemented by the accelerator. It provides services to userspace via the /dev/cxl/afuM.N devices. When a program opens this device and runs the start work IOCTL, the accelerator will have coherent access to that processes memory using the same virtual addresses. That process may mmap the device to access any MMIO space the accelerator provides. Also, reads on the device will allow interrupts to be received. These services are further documented in a later patch in Documentation/powerpc/cxl.txt. Documentation of the cxl hardware architecture and userspace API is provided in subsequent patches. Signed-off-by: Ian Munsie <imunsie@au1.ibm.com> Signed-off-by: Michael Neuling <mikey@neuling.org> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2014-10-08 12:55:02 +04:00
/*
* 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;
cxl: Export optional AFU configuration record in sysfs An AFU may optionally contain one or more PCIe like configuration records, which can be used to identify the AFU. This patch adds support for exposing the raw config space and the vendor, device and class code under sysfs. These will appear in a subdirectory of the AFU device corresponding with the configuration record number, e.g. cat /sys/class/cxl/afu0.0/cr0/vendor 0x1014 cat /sys/class/cxl/afu0.0/cr0/device 0x4350 cat /sys/class/cxl/afu0.0/cr0/class 0x120000 hexdump -C /sys/class/cxl/afu0.0/cr0/config 00000000 14 10 50 43 00 00 00 00 06 00 00 12 00 00 00 00 |..PC............| 00000010 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 |................| * 00000100 These files behave in much the same way as the equivalent files for PCI devices, with one exception being that the config file is currently read-only and restricted to the root user. It is not necessarily required to be this strict, but we currently do not have a compelling use-case to make it writable and/or world-readable, so I erred on the side of being restrictive. Signed-off-by: Ian Munsie <imunsie@au1.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2015-02-04 11:09:01 +03:00
int crs_num;
u64 crs_len;
u64 crs_offset;
struct list_head crs;
cxl: Driver code for powernv PCIe based cards for userspace access This is the core of the cxl driver. It adds support for using cxl cards in the powernv environment only (ie POWER8 bare metal). It allows access to cxl accelerators by userspace using the /dev/cxl/afuM.N char devices. The kernel driver has no knowledge of the function implemented by the accelerator. It provides services to userspace via the /dev/cxl/afuM.N devices. When a program opens this device and runs the start work IOCTL, the accelerator will have coherent access to that processes memory using the same virtual addresses. That process may mmap the device to access any MMIO space the accelerator provides. Also, reads on the device will allow interrupts to be received. These services are further documented in a later patch in Documentation/powerpc/cxl.txt. Documentation of the cxl hardware architecture and userspace API is provided in subsequent patches. Signed-off-by: Ian Munsie <imunsie@au1.ibm.com> Signed-off-by: Michael Neuling <mikey@neuling.org> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2014-10-08 12:55:02 +04:00
enum prefault_modes prefault_mode;
bool psa;
bool pp_psa;
bool enabled;
};
cxl: Name interrupts in /proc/interrupt Currently all interrupts generated by cxl are named "cxl". This is not very informative as we can't distinguish between cards, AFUs, error interrupts, user contexts and user interrupts numbers. Being able to distinguish them is useful for setting affinity. This patch gives each of these names in /proc/interrupts. A two card CAPI system, with afu0.0 having 2 active contexts each with 4 user IRQs each, will now look like this: % grep cxl /proc/interrupts 444: 0 OPAL ICS 141312 Level cxl-card1-err 445: 0 OPAL ICS 141313 Level cxl-afu1.0-err 446: 0 OPAL ICS 141314 Level cxl-afu1.0 462: 0 OPAL ICS 2052 Level cxl-afu0.0-pe0-1 463: 75517 OPAL ICS 2053 Level cxl-afu0.0-pe0-2 468: 0 OPAL ICS 2054 Level cxl-afu0.0-pe0-3 469: 0 OPAL ICS 2055 Level cxl-afu0.0-pe0-4 470: 0 OPAL ICS 2056 Level cxl-afu0.0-pe1-1 471: 75506 OPAL ICS 2057 Level cxl-afu0.0-pe1-2 472: 0 OPAL ICS 2058 Level cxl-afu0.0-pe1-3 473: 0 OPAL ICS 2059 Level cxl-afu0.0-pe1-4 502: 1066 OPAL ICS 2050 Level cxl-afu0.0 514: 0 OPAL ICS 2048 Level cxl-card0-err 515: 0 OPAL ICS 2049 Level cxl-afu0.0-err Signed-off-by: Michael Neuling <mikey@neuling.org> Signed-off-by: Ian Munsie <imunsie@au1.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2014-11-14 10:09:28 +03:00
struct cxl_irq_name {
struct list_head list;
char *name;
};
cxl: Driver code for powernv PCIe based cards for userspace access This is the core of the cxl driver. It adds support for using cxl cards in the powernv environment only (ie POWER8 bare metal). It allows access to cxl accelerators by userspace using the /dev/cxl/afuM.N char devices. The kernel driver has no knowledge of the function implemented by the accelerator. It provides services to userspace via the /dev/cxl/afuM.N devices. When a program opens this device and runs the start work IOCTL, the accelerator will have coherent access to that processes memory using the same virtual addresses. That process may mmap the device to access any MMIO space the accelerator provides. Also, reads on the device will allow interrupts to be received. These services are further documented in a later patch in Documentation/powerpc/cxl.txt. Documentation of the cxl hardware architecture and userspace API is provided in subsequent patches. Signed-off-by: Ian Munsie <imunsie@au1.ibm.com> Signed-off-by: Michael Neuling <mikey@neuling.org> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2014-10-08 12:55:02 +04:00
/*
* 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;
cxl: Unmap MMIO regions when detaching a context If we need to force detach a context (e.g. due to EEH or simply force unbinding the driver) we should prevent the userspace contexts from being able to access the Problem State Area MMIO region further, which they may have mapped with mmap(). This patch unmaps any mapped MMIO regions when detaching a userspace context. Cc: stable@vger.kernel.org Signed-off-by: Ian Munsie <imunsie@au1.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2014-12-08 11:18:01 +03:00
/* Used to unmap any mmaps when force detaching */
struct address_space *mapping;
struct mutex mapping_lock;
cxl: Driver code for powernv PCIe based cards for userspace access This is the core of the cxl driver. It adds support for using cxl cards in the powernv environment only (ie POWER8 bare metal). It allows access to cxl accelerators by userspace using the /dev/cxl/afuM.N char devices. The kernel driver has no knowledge of the function implemented by the accelerator. It provides services to userspace via the /dev/cxl/afuM.N devices. When a program opens this device and runs the start work IOCTL, the accelerator will have coherent access to that processes memory using the same virtual addresses. That process may mmap the device to access any MMIO space the accelerator provides. Also, reads on the device will allow interrupts to be received. These services are further documented in a later patch in Documentation/powerpc/cxl.txt. Documentation of the cxl hardware architecture and userspace API is provided in subsequent patches. Signed-off-by: Ian Munsie <imunsie@au1.ibm.com> Signed-off-by: Michael Neuling <mikey@neuling.org> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2014-10-08 12:55:02 +04:00
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;
cxl: Name interrupts in /proc/interrupt Currently all interrupts generated by cxl are named "cxl". This is not very informative as we can't distinguish between cards, AFUs, error interrupts, user contexts and user interrupts numbers. Being able to distinguish them is useful for setting affinity. This patch gives each of these names in /proc/interrupts. A two card CAPI system, with afu0.0 having 2 active contexts each with 4 user IRQs each, will now look like this: % grep cxl /proc/interrupts 444: 0 OPAL ICS 141312 Level cxl-card1-err 445: 0 OPAL ICS 141313 Level cxl-afu1.0-err 446: 0 OPAL ICS 141314 Level cxl-afu1.0 462: 0 OPAL ICS 2052 Level cxl-afu0.0-pe0-1 463: 75517 OPAL ICS 2053 Level cxl-afu0.0-pe0-2 468: 0 OPAL ICS 2054 Level cxl-afu0.0-pe0-3 469: 0 OPAL ICS 2055 Level cxl-afu0.0-pe0-4 470: 0 OPAL ICS 2056 Level cxl-afu0.0-pe1-1 471: 75506 OPAL ICS 2057 Level cxl-afu0.0-pe1-2 472: 0 OPAL ICS 2058 Level cxl-afu0.0-pe1-3 473: 0 OPAL ICS 2059 Level cxl-afu0.0-pe1-4 502: 1066 OPAL ICS 2050 Level cxl-afu0.0 514: 0 OPAL ICS 2048 Level cxl-card0-err 515: 0 OPAL ICS 2049 Level cxl-afu0.0-err Signed-off-by: Michael Neuling <mikey@neuling.org> Signed-off-by: Ian Munsie <imunsie@au1.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2014-11-14 10:09:28 +03:00
struct list_head irq_names;
cxl: Driver code for powernv PCIe based cards for userspace access This is the core of the cxl driver. It adds support for using cxl cards in the powernv environment only (ie POWER8 bare metal). It allows access to cxl accelerators by userspace using the /dev/cxl/afuM.N char devices. The kernel driver has no knowledge of the function implemented by the accelerator. It provides services to userspace via the /dev/cxl/afuM.N devices. When a program opens this device and runs the start work IOCTL, the accelerator will have coherent access to that processes memory using the same virtual addresses. That process may mmap the device to access any MMIO space the accelerator provides. Also, reads on the device will allow interrupts to be received. These services are further documented in a later patch in Documentation/powerpc/cxl.txt. Documentation of the cxl hardware architecture and userspace API is provided in subsequent patches. Signed-off-by: Ian Munsie <imunsie@au1.ibm.com> Signed-off-by: Michael Neuling <mikey@neuling.org> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2014-10-08 12:55:02 +04:00
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;
cxl: Use call_rcu to reduce latency when releasing the afu fd The afu fd release path was identified as a significant bottleneck in the overall performance of cxl. While an optimal AFU design would minimise the need to close & reopen the AFU fd, it is not always practical to avoid. The bottleneck seems to be down to the call to synchronize_rcu(), which will block until every other thread is guaranteed to be out of an RCU critical section. Replace it with call_rcu() to free the context structures later so we can return to the application sooner. This reduces the time spent in the fd release path from 13356 usec to 13.3 usec - about a 100x speed up. Reported-by: Fei K Chen <uchen@cn.ibm.com> Signed-off-by: Ian Munsie <imunsie@au1.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2015-05-08 15:55:18 +03:00
struct rcu_head rcu;
cxl: Driver code for powernv PCIe based cards for userspace access This is the core of the cxl driver. It adds support for using cxl cards in the powernv environment only (ie POWER8 bare metal). It allows access to cxl accelerators by userspace using the /dev/cxl/afuM.N char devices. The kernel driver has no knowledge of the function implemented by the accelerator. It provides services to userspace via the /dev/cxl/afuM.N devices. When a program opens this device and runs the start work IOCTL, the accelerator will have coherent access to that processes memory using the same virtual addresses. That process may mmap the device to access any MMIO space the accelerator provides. Also, reads on the device will allow interrupts to be received. These services are further documented in a later patch in Documentation/powerpc/cxl.txt. Documentation of the cxl hardware architecture and userspace API is provided in subsequent patches. Signed-off-by: Ian Munsie <imunsie@au1.ibm.com> Signed-off-by: Michael Neuling <mikey@neuling.org> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2014-10-08 12:55:02 +04:00
};
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;
cxl: Name interrupts in /proc/interrupt Currently all interrupts generated by cxl are named "cxl". This is not very informative as we can't distinguish between cards, AFUs, error interrupts, user contexts and user interrupts numbers. Being able to distinguish them is useful for setting affinity. This patch gives each of these names in /proc/interrupts. A two card CAPI system, with afu0.0 having 2 active contexts each with 4 user IRQs each, will now look like this: % grep cxl /proc/interrupts 444: 0 OPAL ICS 141312 Level cxl-card1-err 445: 0 OPAL ICS 141313 Level cxl-afu1.0-err 446: 0 OPAL ICS 141314 Level cxl-afu1.0 462: 0 OPAL ICS 2052 Level cxl-afu0.0-pe0-1 463: 75517 OPAL ICS 2053 Level cxl-afu0.0-pe0-2 468: 0 OPAL ICS 2054 Level cxl-afu0.0-pe0-3 469: 0 OPAL ICS 2055 Level cxl-afu0.0-pe0-4 470: 0 OPAL ICS 2056 Level cxl-afu0.0-pe1-1 471: 75506 OPAL ICS 2057 Level cxl-afu0.0-pe1-2 472: 0 OPAL ICS 2058 Level cxl-afu0.0-pe1-3 473: 0 OPAL ICS 2059 Level cxl-afu0.0-pe1-4 502: 1066 OPAL ICS 2050 Level cxl-afu0.0 514: 0 OPAL ICS 2048 Level cxl-card0-err 515: 0 OPAL ICS 2049 Level cxl-afu0.0-err Signed-off-by: Michael Neuling <mikey@neuling.org> Signed-off-by: Ian Munsie <imunsie@au1.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2014-11-14 10:09:28 +03:00
char *irq_name;
cxl: Driver code for powernv PCIe based cards for userspace access This is the core of the cxl driver. It adds support for using cxl cards in the powernv environment only (ie POWER8 bare metal). It allows access to cxl accelerators by userspace using the /dev/cxl/afuM.N char devices. The kernel driver has no knowledge of the function implemented by the accelerator. It provides services to userspace via the /dev/cxl/afuM.N devices. When a program opens this device and runs the start work IOCTL, the accelerator will have coherent access to that processes memory using the same virtual addresses. That process may mmap the device to access any MMIO space the accelerator provides. Also, reads on the device will allow interrupts to be received. These services are further documented in a later patch in Documentation/powerpc/cxl.txt. Documentation of the cxl hardware architecture and userspace API is provided in subsequent patches. Signed-off-by: Ian Munsie <imunsie@au1.ibm.com> Signed-off-by: Michael Neuling <mikey@neuling.org> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2014-10-08 12:55:02 +04:00
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);
cxl: Use image state defaults for reloading FPGA Select defaults such that a PERST causes flash image reload. Select which image based on what the card is set up to load. CXL_VSEC_PERST_LOADS_IMAGE selects whether PERST assertion causes flash image load. CXL_VSEC_PERST_SELECT_USER selects which image is loaded on the next PERST. cxl_update_image_control writes these bits into the VSEC. Signed-off-by: Ryan Grimm <grimm@linux.vnet.ibm.com> Acked-by: Ian Munsie <imunsie@au1.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2015-01-19 20:52:48 +03:00
int cxl_update_image_control(struct cxl *adapter);
cxl: Add ability to reset the card Adds reset to sysfs which will PERST the card. If load_image_on_perst is set to "user" or "factory", the PERST will cause that image to be loaded. load_image_on_perst is set to "user" for production. "none" could be used for debugging. The PSL trace arrays are preserved which then can be read through debugfs. PERST also triggers CAPP recovery. An HMI comes in, which is handled by EEH. EEH unbinds the driver, calls into Sapphire to reinitialize the PHB, then rebinds the driver. Signed-off-by: Ryan Grimm <grimm@linux.vnet.ibm.com> Acked-by: Ian Munsie <imunsie@au1.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2015-01-19 20:52:51 +03:00
int cxl_reset(struct cxl *adapter);
cxl: Driver code for powernv PCIe based cards for userspace access This is the core of the cxl driver. It adds support for using cxl cards in the powernv environment only (ie POWER8 bare metal). It allows access to cxl accelerators by userspace using the /dev/cxl/afuM.N char devices. The kernel driver has no knowledge of the function implemented by the accelerator. It provides services to userspace via the /dev/cxl/afuM.N devices. When a program opens this device and runs the start work IOCTL, the accelerator will have coherent access to that processes memory using the same virtual addresses. That process may mmap the device to access any MMIO space the accelerator provides. Also, reads on the device will allow interrupts to be received. These services are further documented in a later patch in Documentation/powerpc/cxl.txt. Documentation of the cxl hardware architecture and userspace API is provided in subsequent patches. Signed-off-by: Ian Munsie <imunsie@au1.ibm.com> Signed-off-by: Michael Neuling <mikey@neuling.org> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2014-10-08 12:55:02 +04:00
/* 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))
cxl: Export optional AFU configuration record in sysfs An AFU may optionally contain one or more PCIe like configuration records, which can be used to identify the AFU. This patch adds support for exposing the raw config space and the vendor, device and class code under sysfs. These will appear in a subdirectory of the AFU device corresponding with the configuration record number, e.g. cat /sys/class/cxl/afu0.0/cr0/vendor 0x1014 cat /sys/class/cxl/afu0.0/cr0/device 0x4350 cat /sys/class/cxl/afu0.0/cr0/class 0x120000 hexdump -C /sys/class/cxl/afu0.0/cr0/config 00000000 14 10 50 43 00 00 00 00 06 00 00 12 00 00 00 00 |..PC............| 00000010 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 |................| * 00000100 These files behave in much the same way as the equivalent files for PCI devices, with one exception being that the config file is currently read-only and restricted to the root user. It is not necessarily required to be this strict, but we currently do not have a compelling use-case to make it writable and/or world-readable, so I erred on the side of being restrictive. Signed-off-by: Ian Munsie <imunsie@au1.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2015-02-04 11:09:01 +03:00
#define cxl_afu_cr_read64(afu, cr, off) \
in_le64((afu)->afu_desc_mmio + (afu)->crs_offset + ((cr) * (afu)->crs_len) + (off))
#define cxl_afu_cr_read32(afu, cr, off) \
in_le32((afu)->afu_desc_mmio + (afu)->crs_offset + ((cr) * (afu)->crs_len) + (off))
u16 cxl_afu_cr_read16(struct cxl_afu *afu, int cr, u64 off);
u8 cxl_afu_cr_read8(struct cxl_afu *afu, int cr, u64 off);
cxl: Export AFU error buffer via sysfs Export the "AFU Error Buffer" via sysfs attribute (afu_err_buf). AFU error buffer is used by the AFU to report application specific errors. The contents of this buffer are AFU specific and are intended to be interpreted by the application interacting with the afu. Suggested-by: Michael Neuling <mikey@neuling.org> Signed-off-by: Vaibhav Jain <vaibhav@linux.vnet.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2015-05-22 08:26:05 +03:00
ssize_t cxl_afu_read_err_buffer(struct cxl_afu *afu, char *buf,
loff_t off, size_t count);
cxl: Export optional AFU configuration record in sysfs An AFU may optionally contain one or more PCIe like configuration records, which can be used to identify the AFU. This patch adds support for exposing the raw config space and the vendor, device and class code under sysfs. These will appear in a subdirectory of the AFU device corresponding with the configuration record number, e.g. cat /sys/class/cxl/afu0.0/cr0/vendor 0x1014 cat /sys/class/cxl/afu0.0/cr0/device 0x4350 cat /sys/class/cxl/afu0.0/cr0/class 0x120000 hexdump -C /sys/class/cxl/afu0.0/cr0/config 00000000 14 10 50 43 00 00 00 00 06 00 00 12 00 00 00 00 |..PC............| 00000010 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 |................| * 00000100 These files behave in much the same way as the equivalent files for PCI devices, with one exception being that the config file is currently read-only and restricted to the root user. It is not necessarily required to be this strict, but we currently do not have a compelling use-case to make it writable and/or world-readable, so I erred on the side of being restrictive. Signed-off-by: Ian Munsie <imunsie@au1.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2015-02-04 11:09:01 +03:00
cxl: Driver code for powernv PCIe based cards for userspace access This is the core of the cxl driver. It adds support for using cxl cards in the powernv environment only (ie POWER8 bare metal). It allows access to cxl accelerators by userspace using the /dev/cxl/afuM.N char devices. The kernel driver has no knowledge of the function implemented by the accelerator. It provides services to userspace via the /dev/cxl/afuM.N devices. When a program opens this device and runs the start work IOCTL, the accelerator will have coherent access to that processes memory using the same virtual addresses. That process may mmap the device to access any MMIO space the accelerator provides. Also, reads on the device will allow interrupts to be received. These services are further documented in a later patch in Documentation/powerpc/cxl.txt. Documentation of the cxl hardware architecture and userspace API is provided in subsequent patches. Signed-off-by: Ian Munsie <imunsie@au1.ibm.com> Signed-off-by: Michael Neuling <mikey@neuling.org> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2014-10-08 12:55:02 +04:00
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);
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);
cxl: Add cookie parameter to afu_release_irqs() Add cookie parameter to afu_release_irqs() so that we can pass in a different cookie than the context structure. This will be useful for other kernel drivers that want to call this but get their own cookie back in the interrupt handler. Update all existing call sites. Signed-off-by: Michael Neuling <mikey@neuling.org> Acked-by: Ian Munsie <imunsie@au1.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2015-05-27 09:07:07 +03:00
void afu_release_irqs(struct cxl_context *ctx, void *cookie);
cxl: Driver code for powernv PCIe based cards for userspace access This is the core of the cxl driver. It adds support for using cxl cards in the powernv environment only (ie POWER8 bare metal). It allows access to cxl accelerators by userspace using the /dev/cxl/afuM.N char devices. The kernel driver has no knowledge of the function implemented by the accelerator. It provides services to userspace via the /dev/cxl/afuM.N devices. When a program opens this device and runs the start work IOCTL, the accelerator will have coherent access to that processes memory using the same virtual addresses. That process may mmap the device to access any MMIO space the accelerator provides. Also, reads on the device will allow interrupts to be received. These services are further documented in a later patch in Documentation/powerpc/cxl.txt. Documentation of the cxl hardware architecture and userspace API is provided in subsequent patches. Signed-off-by: Ian Munsie <imunsie@au1.ibm.com> Signed-off-by: Michael Neuling <mikey@neuling.org> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2014-10-08 12:55:02 +04:00
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);
cxl: Unmap MMIO regions when detaching a context If we need to force detach a context (e.g. due to EEH or simply force unbinding the driver) we should prevent the userspace contexts from being able to access the Problem State Area MMIO region further, which they may have mapped with mmap(). This patch unmaps any mapped MMIO regions when detaching a userspace context. Cc: stable@vger.kernel.org Signed-off-by: Ian Munsie <imunsie@au1.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2014-12-08 11:18:01 +03:00
int cxl_context_init(struct cxl_context *ctx, struct cxl_afu *afu, bool master,
struct address_space *mapping);
cxl: Driver code for powernv PCIe based cards for userspace access This is the core of the cxl driver. It adds support for using cxl cards in the powernv environment only (ie POWER8 bare metal). It allows access to cxl accelerators by userspace using the /dev/cxl/afuM.N char devices. The kernel driver has no knowledge of the function implemented by the accelerator. It provides services to userspace via the /dev/cxl/afuM.N devices. When a program opens this device and runs the start work IOCTL, the accelerator will have coherent access to that processes memory using the same virtual addresses. That process may mmap the device to access any MMIO space the accelerator provides. Also, reads on the device will allow interrupts to be received. These services are further documented in a later patch in Documentation/powerpc/cxl.txt. Documentation of the cxl hardware architecture and userspace API is provided in subsequent patches. Signed-off-by: Ian Munsie <imunsie@au1.ibm.com> Signed-off-by: Michael Neuling <mikey@neuling.org> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2014-10-08 12:55:02 +04:00
void cxl_context_free(struct cxl_context *ctx);
int cxl_context_iomap(struct cxl_context *ctx, struct vm_area_struct *vma);
cxl: Export some symbols Export some symbols which will soon be used elsewhere in this driver. Now they are global we rename them so to avoid collisions. Signed-off-by: Michael Neuling <mikey@neuling.org> Acked-by: Ian Munsie <imunsie@au1.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2015-05-27 09:07:10 +03:00
unsigned int cxl_map_irq(struct cxl *adapter, irq_hw_number_t hwirq,
irq_handler_t handler, void *cookie, const char *name);
void cxl_unmap_irq(unsigned int virq, void *cookie);
cxl: Rework detach context functions Rework __detach_context() and cxl_context_detach() so we can reuse them in the kernel API. Signed-off-by: Michael Neuling <mikey@neuling.org> Acked-by: Ian Munsie <imunsie@au1.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2015-05-27 09:07:08 +03:00
int __detach_context(struct cxl_context *ctx);
cxl: Driver code for powernv PCIe based cards for userspace access This is the core of the cxl driver. It adds support for using cxl cards in the powernv environment only (ie POWER8 bare metal). It allows access to cxl accelerators by userspace using the /dev/cxl/afuM.N char devices. The kernel driver has no knowledge of the function implemented by the accelerator. It provides services to userspace via the /dev/cxl/afuM.N devices. When a program opens this device and runs the start work IOCTL, the accelerator will have coherent access to that processes memory using the same virtual addresses. That process may mmap the device to access any MMIO space the accelerator provides. Also, reads on the device will allow interrupts to be received. These services are further documented in a later patch in Documentation/powerpc/cxl.txt. Documentation of the cxl hardware architecture and userspace API is provided in subsequent patches. Signed-off-by: Ian Munsie <imunsie@au1.ibm.com> Signed-off-by: Michael Neuling <mikey@neuling.org> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2014-10-08 12:55:02 +04:00
/* 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 */
};
cxl: Export some symbols Export some symbols which will soon be used elsewhere in this driver. Now they are global we rename them so to avoid collisions. Signed-off-by: Michael Neuling <mikey@neuling.org> Acked-by: Ian Munsie <imunsie@au1.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2015-05-27 09:07:10 +03:00
void cxl_assign_psn_space(struct cxl_context *ctx);
cxl: Driver code for powernv PCIe based cards for userspace access This is the core of the cxl driver. It adds support for using cxl cards in the powernv environment only (ie POWER8 bare metal). It allows access to cxl accelerators by userspace using the /dev/cxl/afuM.N char devices. The kernel driver has no knowledge of the function implemented by the accelerator. It provides services to userspace via the /dev/cxl/afuM.N devices. When a program opens this device and runs the start work IOCTL, the accelerator will have coherent access to that processes memory using the same virtual addresses. That process may mmap the device to access any MMIO space the accelerator provides. Also, reads on the device will allow interrupts to be received. These services are further documented in a later patch in Documentation/powerpc/cxl.txt. Documentation of the cxl hardware architecture and userspace API is provided in subsequent patches. Signed-off-by: Ian Munsie <imunsie@au1.ibm.com> Signed-off-by: Michael Neuling <mikey@neuling.org> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2014-10-08 12:55:02 +04:00
int cxl_attach_process(struct cxl_context *ctx, bool kernel, u64 wed,
u64 amr);
int cxl_detach_process(struct cxl_context *ctx);
cxl: Return error to PSL if IRQ demultiplexing fails & print clearer warning If an AFU has a hardware bug that causes it to acknowledge a context terminate or remove while that context has outstanding transactions, it is possible for the kernel to receive an interrupt for that context after we have removed it from the context list. The kernel will not be able to demultiplex the interrupt (or worse - if we have already reallocated the process handle we could mis-attribute it to the new context), and printed a big scary warning. It did not acknowledge the interrupt, which would effectively halt further translation fault processing on the PSL. This patch makes the warning clearer about the likely cause of the issue (i.e. hardware bug) to make it obvious to future AFU designers of what needs to be fixed. It also prints out the process handle which can then be matched up with hardware and software traces for debugging. It also acknowledges the interrupt to the PSL with either an address error or acknowledge, so that the PSL can continue with other translations. Signed-off-by: Ian Munsie <imunsie@au1.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2014-11-14 09:37:50 +03:00
int cxl_get_irq(struct cxl_afu *afu, struct cxl_irq_info *info);
cxl: Driver code for powernv PCIe based cards for userspace access This is the core of the cxl driver. It adds support for using cxl cards in the powernv environment only (ie POWER8 bare metal). It allows access to cxl accelerators by userspace using the /dev/cxl/afuM.N char devices. The kernel driver has no knowledge of the function implemented by the accelerator. It provides services to userspace via the /dev/cxl/afuM.N devices. When a program opens this device and runs the start work IOCTL, the accelerator will have coherent access to that processes memory using the same virtual addresses. That process may mmap the device to access any MMIO space the accelerator provides. Also, reads on the device will allow interrupts to be received. These services are further documented in a later patch in Documentation/powerpc/cxl.txt. Documentation of the cxl hardware architecture and userspace API is provided in subsequent patches. Signed-off-by: Ian Munsie <imunsie@au1.ibm.com> Signed-off-by: Michael Neuling <mikey@neuling.org> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2014-10-08 12:55:02 +04:00
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);
cxl: cxl_afu_reset() -> __cxl_afu_reset() Rename cxl_afu_reset() to __cxl_afu_reset() to we can reuse this function name in the API. Signed-off-by: Michael Neuling <mikey@neuling.org> Acked-by: Ian Munsie <imunsie@au1.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2015-05-27 09:07:09 +03:00
int __cxl_afu_reset(struct cxl_afu *afu);
cxl: Export some symbols Export some symbols which will soon be used elsewhere in this driver. Now they are global we rename them so to avoid collisions. Signed-off-by: Michael Neuling <mikey@neuling.org> Acked-by: Ian Munsie <imunsie@au1.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2015-05-27 09:07:10 +03:00
int cxl_afu_check_and_enable(struct cxl_afu *afu);
cxl: Driver code for powernv PCIe based cards for userspace access This is the core of the cxl driver. It adds support for using cxl cards in the powernv environment only (ie POWER8 bare metal). It allows access to cxl accelerators by userspace using the /dev/cxl/afuM.N char devices. The kernel driver has no knowledge of the function implemented by the accelerator. It provides services to userspace via the /dev/cxl/afuM.N devices. When a program opens this device and runs the start work IOCTL, the accelerator will have coherent access to that processes memory using the same virtual addresses. That process may mmap the device to access any MMIO space the accelerator provides. Also, reads on the device will allow interrupts to be received. These services are further documented in a later patch in Documentation/powerpc/cxl.txt. Documentation of the cxl hardware architecture and userspace API is provided in subsequent patches. Signed-off-by: Ian Munsie <imunsie@au1.ibm.com> Signed-off-by: Michael Neuling <mikey@neuling.org> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2014-10-08 12:55:02 +04:00
int cxl_psl_purge(struct cxl_afu *afu);
void cxl_stop_trace(struct cxl *cxl);
extern struct pci_driver cxl_pci_driver;
#endif
Reference in New Issue Copy Permalink