OpenCloudOS-Kernel/drivers/misc/cxl/file.c

661 lines
16 KiB
C
Raw Normal View History

/*
* 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"
#include "trace.h"
#define CXL_NUM_MINORS 256 /* Total to reserve */
#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_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;
}
2015-11-16 12:03:45 +08:00
/*
* taking a ref to the afu so that it doesn't go away
* for rest of the function. This ref is released before
* we return.
*/
cxl_afu_get(afu);
spin_unlock(&adapter->afu_list_lock);
if (!afu->current_mode)
goto err_put_afu;
if (!cxl_ops->link_ok(adapter, afu)) {
rc = -EIO;
goto err_put_afu;
}
if (!(ctx = cxl_context_alloc())) {
rc = -ENOMEM;
goto err_put_afu;
}
cxl: Fix coredump generation when cxl_get_fd() is used If a process dumps core while owning a cxl file descriptor obtained from an AFU driver (e.g. cxlflash) through the cxl_get_fd() API, the following error occurs: [ 868.027591] Unable to handle kernel paging request for data at address ... [ 868.027778] Faulting instruction address: 0xc00000000035edb0 cpu 0x8c: Vector: 300 (Data Access) at [c000003c688275e0] pc: c00000000035edb0: elf_core_dump+0xd60/0x1300 lr: c00000000035ed80: elf_core_dump+0xd30/0x1300 sp: c000003c68827860 msr: 9000000100009033 dar: c dsisr: 40000000 current = 0xc000003c68780000 paca = 0xc000000001b73200 softe: 0 irq_happened: 0x01 pid = 46725, comm = hxesurelock enter ? for help [c000003c68827a60] c00000000036948c do_coredump+0xcec/0x11e0 [c000003c68827c20] c0000000000ce9e0 get_signal+0x540/0x7b0 [c000003c68827d10] c000000000017354 do_signal+0x54/0x2b0 [c000003c68827e00] c00000000001777c do_notify_resume+0xbc/0xd0 [c000003c68827e30] c000000000009838 ret_from_except_lite+0x64/0x68 --- Exception: 300 (Data Access) at 00003fff98ad2918 The root cause is that the address_space structure for the file doesn't define a 'host' member. When cxl allocates a file descriptor, it's using the anonymous inode to back the file, but allocates a private address_space for each context. The private address_space allows to track memory allocation for each context. cxl doesn't define the 'host' member of the address space, i.e. the inode. We don't want to define it as the anonymous inode, since there's no longer a 1-to-1 relation between address_space and inode. To fix it, instead of using the anonymous inode, we introduce a simple pseudo filesystem so that cxl can allocate its own inodes. So we now have one inode for each file and address_space. The pseudo filesystem is only mounted on the first allocation of a file descriptor by cxl_get_fd(). Tested with cxlflash. Signed-off-by: Frederic Barrat <fbarrat@linux.vnet.ibm.com> Reviewed-by: Matthew R. Ochs <mrochs@linux.vnet.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2016-11-18 20:00:31 +08:00
rc = cxl_context_init(ctx, afu, master);
if (rc)
goto err_put_afu;
cxl: Fix coredump generation when cxl_get_fd() is used If a process dumps core while owning a cxl file descriptor obtained from an AFU driver (e.g. cxlflash) through the cxl_get_fd() API, the following error occurs: [ 868.027591] Unable to handle kernel paging request for data at address ... [ 868.027778] Faulting instruction address: 0xc00000000035edb0 cpu 0x8c: Vector: 300 (Data Access) at [c000003c688275e0] pc: c00000000035edb0: elf_core_dump+0xd60/0x1300 lr: c00000000035ed80: elf_core_dump+0xd30/0x1300 sp: c000003c68827860 msr: 9000000100009033 dar: c dsisr: 40000000 current = 0xc000003c68780000 paca = 0xc000000001b73200 softe: 0 irq_happened: 0x01 pid = 46725, comm = hxesurelock enter ? for help [c000003c68827a60] c00000000036948c do_coredump+0xcec/0x11e0 [c000003c68827c20] c0000000000ce9e0 get_signal+0x540/0x7b0 [c000003c68827d10] c000000000017354 do_signal+0x54/0x2b0 [c000003c68827e00] c00000000001777c do_notify_resume+0xbc/0xd0 [c000003c68827e30] c000000000009838 ret_from_except_lite+0x64/0x68 --- Exception: 300 (Data Access) at 00003fff98ad2918 The root cause is that the address_space structure for the file doesn't define a 'host' member. When cxl allocates a file descriptor, it's using the anonymous inode to back the file, but allocates a private address_space for each context. The private address_space allows to track memory allocation for each context. cxl doesn't define the 'host' member of the address space, i.e. the inode. We don't want to define it as the anonymous inode, since there's no longer a 1-to-1 relation between address_space and inode. To fix it, instead of using the anonymous inode, we introduce a simple pseudo filesystem so that cxl can allocate its own inodes. So we now have one inode for each file and address_space. The pseudo filesystem is only mounted on the first allocation of a file descriptor by cxl_get_fd(). Tested with cxlflash. Signed-off-by: Frederic Barrat <fbarrat@linux.vnet.ibm.com> Reviewed-by: Matthew R. Ochs <mrochs@linux.vnet.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2016-11-18 20:00:31 +08:00
cxl_context_set_mapping(ctx, inode->i_mapping);
pr_devel("afu_open pe: %i\n", ctx->pe);
file->private_data = ctx;
cxl_ctx_get();
2015-11-16 12:03:45 +08:00
/* indicate success */
rc = 0;
err_put_afu:
2015-11-16 12:03:45 +08:00
/* release the ref taken earlier */
cxl_afu_put(afu);
err_put_adapter:
put_device(&adapter->dev);
return rc;
}
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);
}
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);
/*
* Delete the context's mapping pointer, unless it's created by the
* kernel API, in which case leave it so it can be freed by reclaim_ctx()
*/
if (!ctx->kernelapi) {
mutex_lock(&ctx->mapping_lock);
ctx->mapping = NULL;
mutex_unlock(&ctx->mapping_lock);
}
/*
* 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);
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);
/* Do this outside the status_mutex to avoid a circular dependency with
* the locking in cxl_mmap_fault() */
if (copy_from_user(&work, uwork,
sizeof(struct cxl_ioctl_start_work))) {
rc = -EFAULT;
goto out;
}
mutex_lock(&ctx->status_mutex);
if (ctx->status != OPENED) {
rc = -EIO;
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);
cxl: Add alternate MMIO error handling userspace programs using cxl currently have to use two strategies for dealing with MMIO errors simultaneously. They have to check every read for a return of all Fs in case the adapter has gone away and the kernel has not yet noticed, and they have to deal with SIGBUS in case the kernel has already noticed, invalidated the mapping and marked the context as failed. In order to simplify things, this patch adds an alternative approach where the kernel will return a page filled with Fs instead of delivering a SIGBUS. This allows userspace to only need to deal with one of these two error paths, and is intended for use in libraries that use cxl transparently and may not be able to safely install a signal handler. This approach will only work if certain constraints are met. Namely, if the application is both reading and writing to an address in the problem state area it cannot assume that a non-FF read is OK, as it may just be reading out a value it has previously written. Further - since only one page is used per context a write to a given offset would be visible when reading the same offset from a different page in the mapping (this only applies within a single context, not between contexts). An application could deal with this by e.g. making sure it also reads from a read-only offset after any reads to a read/write offset. Due to these constraints, this functionality must be explicitly requested by userspace when starting the context by passing in the CXL_START_WORK_ERR_FF flag. Signed-off-by: Ian Munsie <imunsie@au1.ibm.com> Acked-by: Michael Neuling <mikey@neuling.org> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2015-07-23 14:43:56 +08:00
ctx->mmio_err_ff = !!(work.flags & CXL_START_WORK_ERR_FF);
/*
* Increment the mapped context count for adapter. This also checks
* if adapter_context_lock is taken.
*/
rc = cxl_adapter_context_get(ctx->afu->adapter);
if (rc) {
afu_release_irqs(ctx, ctx);
goto out;
}
/*
* 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.
cxl: Fix DSI misses when the context owning task exits Presently when a user-space process issues CXL_IOCTL_START_WORK ioctl we store the pid of the current task_struct and use it to get pointer to the mm_struct of the process, while processing page or segment faults from the capi card. However this causes issues when the thread that had originally issued the start-work ioctl exits in which case the stored pid is no more valid and the cxl driver is unable to handle faults as the mm_struct corresponding to process is no more accessible. This patch fixes this issue by using the mm_struct of the next alive task in the thread group. This is done by iterating over all the tasks in the thread group starting from thread group leader and calling get_task_mm on each one of them. When a valid mm_struct is obtained the pid of the associated task is stored in the context replacing the exiting one for handling future faults. The patch introduces a new function named get_mem_context that checks if the current task pointed to by ctx->pid is dead? If yes it performs the steps described above. Also a new variable cxl_context.glpid is introduced which stores the pid of the thread group leader associated with the context owning task. Reported-by: Matthew R. Ochs <mrochs@linux.vnet.ibm.com> Reported-by: Frank Haverkamp <HAVERKAM@de.ibm.com> Suggested-by: Ian Munsie <imunsie@au1.ibm.com> Signed-off-by: Vaibhav Jain <vaibhav@linux.vnet.ibm.com> Acked-by: Ian Munsie <imunsie@au1.ibm.com> Reviewed-by: Frederic Barrat <fbarrat@linux.vnet.ibm.com> Reviewed-by: Matthew R. Ochs <mrochs@linux.vnet.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2015-11-24 18:56:18 +08:00
* Also we grab the PID of the group leader so that if the task that
* has performed the attach operation exits the mm context of the
* process is still accessible.
*/
cxl: Fix DSI misses when the context owning task exits Presently when a user-space process issues CXL_IOCTL_START_WORK ioctl we store the pid of the current task_struct and use it to get pointer to the mm_struct of the process, while processing page or segment faults from the capi card. However this causes issues when the thread that had originally issued the start-work ioctl exits in which case the stored pid is no more valid and the cxl driver is unable to handle faults as the mm_struct corresponding to process is no more accessible. This patch fixes this issue by using the mm_struct of the next alive task in the thread group. This is done by iterating over all the tasks in the thread group starting from thread group leader and calling get_task_mm on each one of them. When a valid mm_struct is obtained the pid of the associated task is stored in the context replacing the exiting one for handling future faults. The patch introduces a new function named get_mem_context that checks if the current task pointed to by ctx->pid is dead? If yes it performs the steps described above. Also a new variable cxl_context.glpid is introduced which stores the pid of the thread group leader associated with the context owning task. Reported-by: Matthew R. Ochs <mrochs@linux.vnet.ibm.com> Reported-by: Frank Haverkamp <HAVERKAM@de.ibm.com> Suggested-by: Ian Munsie <imunsie@au1.ibm.com> Signed-off-by: Vaibhav Jain <vaibhav@linux.vnet.ibm.com> Acked-by: Ian Munsie <imunsie@au1.ibm.com> Reviewed-by: Frederic Barrat <fbarrat@linux.vnet.ibm.com> Reviewed-by: Matthew R. Ochs <mrochs@linux.vnet.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2015-11-24 18:56:18 +08:00
ctx->pid = get_task_pid(current, PIDTYPE_PID);
ctx->glpid = get_task_pid(current->group_leader, PIDTYPE_PID);
cxl: Prevent adapter reset if an active context exists This patch prevents resetting the cxl adapter via sysfs in presence of one or more active cxl_context on it. This protects against an unrecoverable error caused by PSL owning a dirty cache line even after reset and host tries to touch the same cache line. In case a force reset of the card is required irrespective of any active contexts, the int value -1 can be stored in the 'reset' sysfs attribute of the card. The patch introduces a new atomic_t member named contexts_num inside struct cxl that holds the number of active context attached to the card , which is checked against '0' before proceeding with the reset. To prevent against a race condition where a context is activated just after reset check is performed, the contexts_num is atomically set to '-1' after reset-check to indicate that no more contexts can be activated on the card anymore. Before activating a context we atomically test if contexts_num is non-negative and if so, increment its value by one. In case the value of contexts_num is negative then it indicates that the card is about to be reset and context activation is error-ed out at that point. Fixes: 62fa19d4b4fd ("cxl: Add ability to reset the card") Cc: stable@vger.kernel.org # v4.0+ Acked-by: Frederic Barrat <fbarrat@linux.vnet.ibm.com> Reviewed-by: Andrew Donnellan <andrew.donnellan@au1.ibm.com> Signed-off-by: Vaibhav Jain <vaibhav@linux.vnet.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2016-10-14 17:38:36 +08:00
trace_cxl_attach(ctx, work.work_element_descriptor, work.num_interrupts, amr);
if ((rc = cxl_ops->attach_process(ctx, false, work.work_element_descriptor,
amr))) {
afu_release_irqs(ctx, ctx);
cxl: Prevent adapter reset if an active context exists This patch prevents resetting the cxl adapter via sysfs in presence of one or more active cxl_context on it. This protects against an unrecoverable error caused by PSL owning a dirty cache line even after reset and host tries to touch the same cache line. In case a force reset of the card is required irrespective of any active contexts, the int value -1 can be stored in the 'reset' sysfs attribute of the card. The patch introduces a new atomic_t member named contexts_num inside struct cxl that holds the number of active context attached to the card , which is checked against '0' before proceeding with the reset. To prevent against a race condition where a context is activated just after reset check is performed, the contexts_num is atomically set to '-1' after reset-check to indicate that no more contexts can be activated on the card anymore. Before activating a context we atomically test if contexts_num is non-negative and if so, increment its value by one. In case the value of contexts_num is negative then it indicates that the card is about to be reset and context activation is error-ed out at that point. Fixes: 62fa19d4b4fd ("cxl: Add ability to reset the card") Cc: stable@vger.kernel.org # v4.0+ Acked-by: Frederic Barrat <fbarrat@linux.vnet.ibm.com> Reviewed-by: Andrew Donnellan <andrew.donnellan@au1.ibm.com> Signed-off-by: Vaibhav Jain <vaibhav@linux.vnet.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2016-10-14 17:38:36 +08:00
cxl_adapter_context_put(ctx->afu->adapter);
put_pid(ctx->glpid);
put_pid(ctx->pid);
ctx->glpid = ctx->pid = NULL;
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->external_pe, sizeof(__u32)))
return -EFAULT;
return 0;
}
static long afu_ioctl_get_afu_id(struct cxl_context *ctx,
struct cxl_afu_id __user *upafuid)
{
struct cxl_afu_id afuid = { 0 };
afuid.card_id = ctx->afu->adapter->adapter_num;
afuid.afu_offset = ctx->afu->slice;
afuid.afu_mode = ctx->afu->current_mode;
/* set the flag bit in case the afu is a slave */
if (ctx->afu->current_mode == CXL_MODE_DIRECTED && !ctx->master)
afuid.flags |= CXL_AFUID_FLAG_SLAVE;
if (copy_to_user(upafuid, &afuid, sizeof(afuid)))
return -EFAULT;
return 0;
}
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;
if (!cxl_ops->link_ok(ctx->afu->adapter, ctx->afu))
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);
case CXL_IOCTL_GET_AFU_ID:
return afu_ioctl_get_afu_id(ctx, (struct cxl_afu_id __user *)
arg);
}
return -EINVAL;
}
static long afu_compat_ioctl(struct file *file, unsigned int cmd,
unsigned long arg)
{
return afu_ioctl(file, cmd, arg);
}
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;
if (!cxl_ops->link_ok(ctx->afu->adapter, ctx->afu))
return -EIO;
return cxl_context_iomap(ctx, vm);
}
cxl: Add mechanism for delivering AFU driver specific events This adds an afu_driver_ops structure with fetch_event() and event_delivered() callbacks. An AFU driver such as cxlflash can fill this out and associate it with a context to enable passing custom AFU specific events to userspace. This also adds a new kernel API function cxl_context_pending_events(), that the AFU driver can use to notify the cxl driver that new specific events are ready to be delivered, and wake up anyone waiting on the context wait queue. The current count of AFU driver specific events is stored in the field afu_driver_events of the context structure. The cxl driver checks the afu_driver_events count during poll, select, read, etc. calls to check if an AFU driver specific event is pending, and calls fetch_event() to obtain and deliver that event. This way, the cxl driver takes care of all the usual locking semantics around these calls and handles all the generic cxl events, so that the AFU driver only needs to worry about it's own events. fetch_event() return a struct cxl_event_afu_driver_reserved, allocated by the AFU driver, and filled in with the specific event information and size. Total event size (header + data) should not be greater than CXL_READ_MIN_SIZE (4K). Th cxl driver prepends an appropriate cxl event header, copies the event to userspace, and finally calls event_delivered() to return the status of the operation to the AFU driver. The event is identified by the context and cxl_event_afu_driver_reserved pointers. Since AFU drivers provide their own means for userspace to obtain the AFU file descriptor (i.e. cxlflash uses an ioctl on their scsi file descriptor to obtain the AFU file descriptor) and the generic cxl driver will never use this event, the ABI of the event is up to each individual AFU driver. Signed-off-by: Philippe Bergheaud <felix@linux.vnet.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2016-06-23 21:03:53 +08:00
static inline bool ctx_event_pending(struct cxl_context *ctx)
{
if (ctx->pending_irq || ctx->pending_fault || ctx->pending_afu_err)
return true;
if (ctx->afu_driver_ops && atomic_read(&ctx->afu_driver_events))
return true;
return false;
}
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);
cxl: Add mechanism for delivering AFU driver specific events This adds an afu_driver_ops structure with fetch_event() and event_delivered() callbacks. An AFU driver such as cxlflash can fill this out and associate it with a context to enable passing custom AFU specific events to userspace. This also adds a new kernel API function cxl_context_pending_events(), that the AFU driver can use to notify the cxl driver that new specific events are ready to be delivered, and wake up anyone waiting on the context wait queue. The current count of AFU driver specific events is stored in the field afu_driver_events of the context structure. The cxl driver checks the afu_driver_events count during poll, select, read, etc. calls to check if an AFU driver specific event is pending, and calls fetch_event() to obtain and deliver that event. This way, the cxl driver takes care of all the usual locking semantics around these calls and handles all the generic cxl events, so that the AFU driver only needs to worry about it's own events. fetch_event() return a struct cxl_event_afu_driver_reserved, allocated by the AFU driver, and filled in with the specific event information and size. Total event size (header + data) should not be greater than CXL_READ_MIN_SIZE (4K). Th cxl driver prepends an appropriate cxl event header, copies the event to userspace, and finally calls event_delivered() to return the status of the operation to the AFU driver. The event is identified by the context and cxl_event_afu_driver_reserved pointers. Since AFU drivers provide their own means for userspace to obtain the AFU file descriptor (i.e. cxlflash uses an ioctl on their scsi file descriptor to obtain the AFU file descriptor) and the generic cxl driver will never use this event, the ABI of the event is up to each individual AFU driver. Signed-off-by: Philippe Bergheaud <felix@linux.vnet.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2016-06-23 21:03:53 +08:00
if (ctx_event_pending(ctx))
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;
}
cxl: Add mechanism for delivering AFU driver specific events This adds an afu_driver_ops structure with fetch_event() and event_delivered() callbacks. An AFU driver such as cxlflash can fill this out and associate it with a context to enable passing custom AFU specific events to userspace. This also adds a new kernel API function cxl_context_pending_events(), that the AFU driver can use to notify the cxl driver that new specific events are ready to be delivered, and wake up anyone waiting on the context wait queue. The current count of AFU driver specific events is stored in the field afu_driver_events of the context structure. The cxl driver checks the afu_driver_events count during poll, select, read, etc. calls to check if an AFU driver specific event is pending, and calls fetch_event() to obtain and deliver that event. This way, the cxl driver takes care of all the usual locking semantics around these calls and handles all the generic cxl events, so that the AFU driver only needs to worry about it's own events. fetch_event() return a struct cxl_event_afu_driver_reserved, allocated by the AFU driver, and filled in with the specific event information and size. Total event size (header + data) should not be greater than CXL_READ_MIN_SIZE (4K). Th cxl driver prepends an appropriate cxl event header, copies the event to userspace, and finally calls event_delivered() to return the status of the operation to the AFU driver. The event is identified by the context and cxl_event_afu_driver_reserved pointers. Since AFU drivers provide their own means for userspace to obtain the AFU file descriptor (i.e. cxlflash uses an ioctl on their scsi file descriptor to obtain the AFU file descriptor) and the generic cxl driver will never use this event, the ABI of the event is up to each individual AFU driver. Signed-off-by: Philippe Bergheaud <felix@linux.vnet.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2016-06-23 21:03:53 +08:00
static ssize_t afu_driver_event_copy(struct cxl_context *ctx,
char __user *buf,
struct cxl_event *event,
struct cxl_event_afu_driver_reserved *pl)
{
cxl: Add mechanism for delivering AFU driver specific events This adds an afu_driver_ops structure with fetch_event() and event_delivered() callbacks. An AFU driver such as cxlflash can fill this out and associate it with a context to enable passing custom AFU specific events to userspace. This also adds a new kernel API function cxl_context_pending_events(), that the AFU driver can use to notify the cxl driver that new specific events are ready to be delivered, and wake up anyone waiting on the context wait queue. The current count of AFU driver specific events is stored in the field afu_driver_events of the context structure. The cxl driver checks the afu_driver_events count during poll, select, read, etc. calls to check if an AFU driver specific event is pending, and calls fetch_event() to obtain and deliver that event. This way, the cxl driver takes care of all the usual locking semantics around these calls and handles all the generic cxl events, so that the AFU driver only needs to worry about it's own events. fetch_event() return a struct cxl_event_afu_driver_reserved, allocated by the AFU driver, and filled in with the specific event information and size. Total event size (header + data) should not be greater than CXL_READ_MIN_SIZE (4K). Th cxl driver prepends an appropriate cxl event header, copies the event to userspace, and finally calls event_delivered() to return the status of the operation to the AFU driver. The event is identified by the context and cxl_event_afu_driver_reserved pointers. Since AFU drivers provide their own means for userspace to obtain the AFU file descriptor (i.e. cxlflash uses an ioctl on their scsi file descriptor to obtain the AFU file descriptor) and the generic cxl driver will never use this event, the ABI of the event is up to each individual AFU driver. Signed-off-by: Philippe Bergheaud <felix@linux.vnet.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2016-06-23 21:03:53 +08:00
/* Check event */
if (!pl) {
ctx->afu_driver_ops->event_delivered(ctx, pl, -EINVAL);
return -EFAULT;
}
/* Check event size */
event->header.size += pl->data_size;
if (event->header.size > CXL_READ_MIN_SIZE) {
ctx->afu_driver_ops->event_delivered(ctx, pl, -EINVAL);
return -EFAULT;
}
/* Copy event header */
if (copy_to_user(buf, event, sizeof(struct cxl_event_header))) {
ctx->afu_driver_ops->event_delivered(ctx, pl, -EFAULT);
return -EFAULT;
}
/* Copy event data */
buf += sizeof(struct cxl_event_header);
if (copy_to_user(buf, &pl->data, pl->data_size)) {
ctx->afu_driver_ops->event_delivered(ctx, pl, -EFAULT);
return -EFAULT;
}
ctx->afu_driver_ops->event_delivered(ctx, pl, 0); /* Success */
return event->header.size;
}
ssize_t afu_read(struct file *file, char __user *buf, size_t count,
loff_t *off)
{
struct cxl_context *ctx = file->private_data;
cxl: Add mechanism for delivering AFU driver specific events This adds an afu_driver_ops structure with fetch_event() and event_delivered() callbacks. An AFU driver such as cxlflash can fill this out and associate it with a context to enable passing custom AFU specific events to userspace. This also adds a new kernel API function cxl_context_pending_events(), that the AFU driver can use to notify the cxl driver that new specific events are ready to be delivered, and wake up anyone waiting on the context wait queue. The current count of AFU driver specific events is stored in the field afu_driver_events of the context structure. The cxl driver checks the afu_driver_events count during poll, select, read, etc. calls to check if an AFU driver specific event is pending, and calls fetch_event() to obtain and deliver that event. This way, the cxl driver takes care of all the usual locking semantics around these calls and handles all the generic cxl events, so that the AFU driver only needs to worry about it's own events. fetch_event() return a struct cxl_event_afu_driver_reserved, allocated by the AFU driver, and filled in with the specific event information and size. Total event size (header + data) should not be greater than CXL_READ_MIN_SIZE (4K). Th cxl driver prepends an appropriate cxl event header, copies the event to userspace, and finally calls event_delivered() to return the status of the operation to the AFU driver. The event is identified by the context and cxl_event_afu_driver_reserved pointers. Since AFU drivers provide their own means for userspace to obtain the AFU file descriptor (i.e. cxlflash uses an ioctl on their scsi file descriptor to obtain the AFU file descriptor) and the generic cxl driver will never use this event, the ABI of the event is up to each individual AFU driver. Signed-off-by: Philippe Bergheaud <felix@linux.vnet.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2016-06-23 21:03:53 +08:00
struct cxl_event_afu_driver_reserved *pl = NULL;
struct cxl_event event;
unsigned long flags;
int rc;
DEFINE_WAIT(wait);
if (!cxl_ops->link_ok(ctx->afu->adapter, ctx->afu))
return -EIO;
if (count < CXL_READ_MIN_SIZE)
return -EINVAL;
spin_lock_irqsave(&ctx->lock, flags);
for (;;) {
prepare_to_wait(&ctx->wq, &wait, TASK_INTERRUPTIBLE);
cxl: Add mechanism for delivering AFU driver specific events This adds an afu_driver_ops structure with fetch_event() and event_delivered() callbacks. An AFU driver such as cxlflash can fill this out and associate it with a context to enable passing custom AFU specific events to userspace. This also adds a new kernel API function cxl_context_pending_events(), that the AFU driver can use to notify the cxl driver that new specific events are ready to be delivered, and wake up anyone waiting on the context wait queue. The current count of AFU driver specific events is stored in the field afu_driver_events of the context structure. The cxl driver checks the afu_driver_events count during poll, select, read, etc. calls to check if an AFU driver specific event is pending, and calls fetch_event() to obtain and deliver that event. This way, the cxl driver takes care of all the usual locking semantics around these calls and handles all the generic cxl events, so that the AFU driver only needs to worry about it's own events. fetch_event() return a struct cxl_event_afu_driver_reserved, allocated by the AFU driver, and filled in with the specific event information and size. Total event size (header + data) should not be greater than CXL_READ_MIN_SIZE (4K). Th cxl driver prepends an appropriate cxl event header, copies the event to userspace, and finally calls event_delivered() to return the status of the operation to the AFU driver. The event is identified by the context and cxl_event_afu_driver_reserved pointers. Since AFU drivers provide their own means for userspace to obtain the AFU file descriptor (i.e. cxlflash uses an ioctl on their scsi file descriptor to obtain the AFU file descriptor) and the generic cxl driver will never use this event, the ABI of the event is up to each individual AFU driver. Signed-off-by: Philippe Bergheaud <felix@linux.vnet.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2016-06-23 21:03:53 +08:00
if (ctx_event_pending(ctx) || (ctx->status == CLOSED))
break;
if (!cxl_ops->link_ok(ctx->afu->adapter, ctx->afu)) {
rc = -EIO;
goto out;
}
if (file->f_flags & O_NONBLOCK) {
rc = -EAGAIN;
goto out;
}
if (signal_pending(current)) {
rc = -ERESTARTSYS;
goto out;
}
spin_unlock_irqrestore(&ctx->lock, flags);
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);
cxl: Add mechanism for delivering AFU driver specific events This adds an afu_driver_ops structure with fetch_event() and event_delivered() callbacks. An AFU driver such as cxlflash can fill this out and associate it with a context to enable passing custom AFU specific events to userspace. This also adds a new kernel API function cxl_context_pending_events(), that the AFU driver can use to notify the cxl driver that new specific events are ready to be delivered, and wake up anyone waiting on the context wait queue. The current count of AFU driver specific events is stored in the field afu_driver_events of the context structure. The cxl driver checks the afu_driver_events count during poll, select, read, etc. calls to check if an AFU driver specific event is pending, and calls fetch_event() to obtain and deliver that event. This way, the cxl driver takes care of all the usual locking semantics around these calls and handles all the generic cxl events, so that the AFU driver only needs to worry about it's own events. fetch_event() return a struct cxl_event_afu_driver_reserved, allocated by the AFU driver, and filled in with the specific event information and size. Total event size (header + data) should not be greater than CXL_READ_MIN_SIZE (4K). Th cxl driver prepends an appropriate cxl event header, copies the event to userspace, and finally calls event_delivered() to return the status of the operation to the AFU driver. The event is identified by the context and cxl_event_afu_driver_reserved pointers. Since AFU drivers provide their own means for userspace to obtain the AFU file descriptor (i.e. cxlflash uses an ioctl on their scsi file descriptor to obtain the AFU file descriptor) and the generic cxl driver will never use this event, the ABI of the event is up to each individual AFU driver. Signed-off-by: Philippe Bergheaud <felix@linux.vnet.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2016-06-23 21:03:53 +08:00
if (ctx->afu_driver_ops && atomic_read(&ctx->afu_driver_events)) {
pr_devel("afu_read delivering AFU driver specific event\n");
pl = ctx->afu_driver_ops->fetch_event(ctx);
atomic_dec(&ctx->afu_driver_events);
event.header.type = CXL_EVENT_AFU_DRIVER;
} else 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);
cxl: Add mechanism for delivering AFU driver specific events This adds an afu_driver_ops structure with fetch_event() and event_delivered() callbacks. An AFU driver such as cxlflash can fill this out and associate it with a context to enable passing custom AFU specific events to userspace. This also adds a new kernel API function cxl_context_pending_events(), that the AFU driver can use to notify the cxl driver that new specific events are ready to be delivered, and wake up anyone waiting on the context wait queue. The current count of AFU driver specific events is stored in the field afu_driver_events of the context structure. The cxl driver checks the afu_driver_events count during poll, select, read, etc. calls to check if an AFU driver specific event is pending, and calls fetch_event() to obtain and deliver that event. This way, the cxl driver takes care of all the usual locking semantics around these calls and handles all the generic cxl events, so that the AFU driver only needs to worry about it's own events. fetch_event() return a struct cxl_event_afu_driver_reserved, allocated by the AFU driver, and filled in with the specific event information and size. Total event size (header + data) should not be greater than CXL_READ_MIN_SIZE (4K). Th cxl driver prepends an appropriate cxl event header, copies the event to userspace, and finally calls event_delivered() to return the status of the operation to the AFU driver. The event is identified by the context and cxl_event_afu_driver_reserved pointers. Since AFU drivers provide their own means for userspace to obtain the AFU file descriptor (i.e. cxlflash uses an ioctl on their scsi file descriptor to obtain the AFU file descriptor) and the generic cxl driver will never use this event, the ABI of the event is up to each individual AFU driver. Signed-off-by: Philippe Bergheaud <felix@linux.vnet.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2016-06-23 21:03:53 +08:00
if (event.header.type == CXL_EVENT_AFU_DRIVER)
return afu_driver_event_copy(ctx, buf, &event, pl);
if (copy_to_user(buf, &event, event.header.size))
return -EFAULT;
return event.header.size;
out:
finish_wait(&ctx->wq, &wait);
spin_unlock_irqrestore(&ctx->lock, flags);
return rc;
}
/*
* Note: if this is updated, we need to update api.c to patch the new ones in
* too
*/
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 (cpu_has_feature(CPU_FTR_HVMODE) &&
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);
}
dev_t cxl_get_dev(void)
{
return cxl_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.
*/
cxl: Add mechanism for delivering AFU driver specific events This adds an afu_driver_ops structure with fetch_event() and event_delivered() callbacks. An AFU driver such as cxlflash can fill this out and associate it with a context to enable passing custom AFU specific events to userspace. This also adds a new kernel API function cxl_context_pending_events(), that the AFU driver can use to notify the cxl driver that new specific events are ready to be delivered, and wake up anyone waiting on the context wait queue. The current count of AFU driver specific events is stored in the field afu_driver_events of the context structure. The cxl driver checks the afu_driver_events count during poll, select, read, etc. calls to check if an AFU driver specific event is pending, and calls fetch_event() to obtain and deliver that event. This way, the cxl driver takes care of all the usual locking semantics around these calls and handles all the generic cxl events, so that the AFU driver only needs to worry about it's own events. fetch_event() return a struct cxl_event_afu_driver_reserved, allocated by the AFU driver, and filled in with the specific event information and size. Total event size (header + data) should not be greater than CXL_READ_MIN_SIZE (4K). Th cxl driver prepends an appropriate cxl event header, copies the event to userspace, and finally calls event_delivered() to return the status of the operation to the AFU driver. The event is identified by the context and cxl_event_afu_driver_reserved pointers. Since AFU drivers provide their own means for userspace to obtain the AFU file descriptor (i.e. cxlflash uses an ioctl on their scsi file descriptor to obtain the AFU file descriptor) and the generic cxl driver will never use this event, the ABI of the event is up to each individual AFU driver. Signed-off-by: Philippe Bergheaud <felix@linux.vnet.ibm.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2016-06-23 21:03:53 +08:00
BUILD_BUG_ON(CXL_API_VERSION != 3);
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);
}