Merge tag 'powerpc-4.3-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux

Pull powerpc updates from Michael Ellerman:

 - support "hybrid" iommu/direct DMA ops for coherent_mask < dma_mask
   from Benjamin Herrenschmidt

 - EEH fixes for SRIOV from Gavin

 - introduce rtas_get_sensor_fast() for IRQ handlers from Thomas Huth

 - use hardware RNG for arch_get_random_seed_* not arch_get_random_*
   from Paul Mackerras

 - seccomp filter support from Michael Ellerman

 - opal_cec_reboot2() handling for HMIs & machine checks from Mahesh
   Salgaonkar

 - add powerpc timebase as a trace clock source from Naveen N.  Rao

 - misc cleanups in the xmon, signal & SLB code from Anshuman Khandual

 - add an inline function to update POWER8 HID0 from Gautham R.  Shenoy

 - fix pte_pagesize_index() crash on 4K w/64K hash from Michael Ellerman

 - drop support for 64K local store on 4K kernels from Michael Ellerman

 - move dma_get_required_mask() from pnv_phb to pci_controller_ops from
   Andrew Donnellan

 - initialize distance lookup table from drconf path from Nikunj A
   Dadhania

 - enable RTC class support from Vaibhav Jain

 - disable automatically blocked PCI config from Gavin Shan

 - add LEDs driver for PowerNV platform from Vasant Hegde

 - fix endianness issues in the HVSI driver from Laurent Dufour

 - kexec endian fixes from Samuel Mendoza-Jonas

 - fix corrupted pdn list from Gavin Shan

 - fix fenced PHB caused by eeh_slot_error_detail() from Gavin Shan

 - Freescale updates from Scott: Highlights include 32-bit memcpy/memset
   optimizations, checksum optimizations, 85xx config fragments and
   updates, device tree updates, e6500 fixes for non-SMP, and misc
   cleanup and minor fixes.

 - a ton of cxl updates & fixes:
    - add explicit precision specifiers from Rasmus Villemoes
    - use more common format specifier from Rasmus Villemoes
    - destroy cxl_adapter_idr on module_exit from Johannes Thumshirn
    - destroy afu->contexts_idr on release of an afu from Johannes
      Thumshirn
    - compile with -Werror from Daniel Axtens
    - EEH support from Daniel Axtens
    - plug irq_bitmap getting leaked in cxl_context from Vaibhav Jain
    - add alternate MMIO error handling from Ian Munsie
    - allow release of contexts which have been OPENED but not STARTED
      from Andrew Donnellan
    - remove use of macro DEFINE_PCI_DEVICE_TABLE from Vaishali Thakkar
    - release irqs if memory allocation fails from Vaibhav Jain
    - remove racy attempt to force EEH invocation in reset from Daniel
      Axtens
    - fix + cleanup error paths in cxl_dev_context_init from Ian Munsie
    - fix force unmapping mmaps of contexts allocated through the kernel
      api from Ian Munsie
    - set up and enable PSL Timebase from Philippe Bergheaud

* tag 'powerpc-4.3-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (140 commits)
  cxl: Set up and enable PSL Timebase
  cxl: Fix force unmapping mmaps of contexts allocated through the kernel api
  cxl: Fix + cleanup error paths in cxl_dev_context_init
  powerpc/eeh: Fix fenced PHB caused by eeh_slot_error_detail()
  powerpc/pseries: Cleanup on pci_dn_reconfig_notifier()
  powerpc/pseries: Fix corrupted pdn list
  powerpc/powernv: Enable LEDS support
  powerpc/iommu: Set default DMA offset in dma_dev_setup
  cxl: Remove racy attempt to force EEH invocation in reset
  cxl: Release irqs if memory allocation fails
  cxl: Remove use of macro DEFINE_PCI_DEVICE_TABLE
  powerpc/powernv: Fix mis-merge of OPAL support for LEDS driver
  powerpc/powernv: Reset HILE before kexec_sequence()
  powerpc/kexec: Reset secondary cpu endianness before kexec
  powerpc/hvsi: Fix endianness issues in the HVSI driver
  leds/powernv: Add driver for PowerNV platform
  powerpc/powernv: Create LED platform device
  powerpc/powernv: Add OPAL interfaces for accessing and modifying system LED states
  powerpc/powernv: Fix the log message when disabling VF
  cxl: Allow release of contexts which have been OPENED but not STARTED
  ...

drivers/misc/cxl/Kconfig

@@ -11,11 +11,16 @@ config CXL_KERNEL_API
 	bool
 	default n
 
+config CXL_EEH
+	bool
+	default n
+
 config CXL
 	tristate "Support for IBM Coherent Accelerators (CXL)"
-	depends on PPC_POWERNV && PCI_MSI
+	depends on PPC_POWERNV && PCI_MSI && EEH
 	select CXL_BASE
 	select CXL_KERNEL_API
+	select CXL_EEH
 	default m
 	help
 	  Select this option to enable driver support for IBM Coherent

drivers/misc/cxl/Makefile

@@ -1,3 +1,5 @@
+ccflags-y := -Werror
+
 cxl-y				+= main.o file.o irq.o fault.o native.o
 cxl-y				+= context.o sysfs.o debugfs.o pci.o trace.o
 cxl-y				+= vphb.o api.o

drivers/misc/cxl/api.c

@@ -12,11 +12,13 @@
 #include <linux/anon_inodes.h>
 #include <linux/file.h>
 #include <misc/cxl.h>
+#include <linux/fs.h>
 
 #include "cxl.h"
 
 struct cxl_context *cxl_dev_context_init(struct pci_dev *dev)
 {
+	struct address_space *mapping;
 	struct cxl_afu *afu;
 	struct cxl_context  *ctx;
 	int rc;
@@ -25,19 +27,42 @@ struct cxl_context *cxl_dev_context_init(struct pci_dev *dev)
 
 	get_device(&afu->dev);
 	ctx = cxl_context_alloc();
-	if (IS_ERR(ctx))
-		return ctx;
+	if (IS_ERR(ctx)) {
+		rc = PTR_ERR(ctx);
+		goto err_dev;
+	}
+
+	ctx->kernelapi = true;
+
+	/*
+	 * Make our own address space since we won't have one from the
+	 * filesystem like the user api has, and even if we do associate a file
+	 * with this context we don't want to use the global anonymous inode's
+	 * address space as that can invalidate unrelated users:
+	 */
+	mapping = kmalloc(sizeof(struct address_space), GFP_KERNEL);
+	if (!mapping) {
+		rc = -ENOMEM;
+		goto err_ctx;
+	}
+	address_space_init_once(mapping);
 
 	/* Make it a slave context.  We can promote it later? */
-	rc = cxl_context_init(ctx, afu, false, NULL);
-	if (rc) {
-		kfree(ctx);
-		put_device(&afu->dev);
-		return ERR_PTR(-ENOMEM);
-	}
+	rc = cxl_context_init(ctx, afu, false, mapping);
+	if (rc)
+		goto err_mapping;
+
 	cxl_assign_psn_space(ctx);
 
 	return ctx;
+
+err_mapping:
+	kfree(mapping);
+err_ctx:
+	kfree(ctx);
+err_dev:
+	put_device(&afu->dev);
+	return ERR_PTR(rc);
 }
 EXPORT_SYMBOL_GPL(cxl_dev_context_init);
 
@@ -59,7 +84,7 @@ EXPORT_SYMBOL_GPL(cxl_get_phys_dev);
 
 int cxl_release_context(struct cxl_context *ctx)
 {
-	if (ctx->status != CLOSED)
+	if (ctx->status >= STARTED)
 		return -EBUSY;
 
 	put_device(&ctx->afu->dev);
@@ -255,9 +280,16 @@ struct file *cxl_get_fd(struct cxl_context *ctx, struct file_operations *fops,
 
 	file = anon_inode_getfile("cxl", fops, ctx, flags);
 	if (IS_ERR(file))
-		put_unused_fd(fdtmp);
+		goto err_fd;
+
+	file->f_mapping = ctx->mapping;
+
 	*fd = fdtmp;
 	return file;
+
+err_fd:
+	put_unused_fd(fdtmp);
+	return NULL;
 }
 EXPORT_SYMBOL_GPL(cxl_get_fd);
 
@@ -327,3 +359,10 @@ int cxl_afu_reset(struct cxl_context *ctx)
 	return cxl_afu_check_and_enable(afu);
 }
 EXPORT_SYMBOL_GPL(cxl_afu_reset);
+
+void cxl_perst_reloads_same_image(struct cxl_afu *afu,
+				  bool perst_reloads_same_image)
+{
+	afu->adapter->perst_same_image = perst_reloads_same_image;
+}
+EXPORT_SYMBOL_GPL(cxl_perst_reloads_same_image);

drivers/misc/cxl/context.c

@@ -126,6 +126,18 @@ static int cxl_mmap_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 	if (ctx->status != STARTED) {
 		mutex_unlock(&ctx->status_mutex);
 		pr_devel("%s: Context not started, failing problem state access\n", __func__);
+		if (ctx->mmio_err_ff) {
+			if (!ctx->ff_page) {
+				ctx->ff_page = alloc_page(GFP_USER);
+				if (!ctx->ff_page)
+					return VM_FAULT_OOM;
+				memset(page_address(ctx->ff_page), 0xff, PAGE_SIZE);
+			}
+			get_page(ctx->ff_page);
+			vmf->page = ctx->ff_page;
+			vma->vm_page_prot = pgprot_cached(vma->vm_page_prot);
+			return 0;
+		}
 		return VM_FAULT_SIGBUS;
 	}
 
@@ -193,7 +205,11 @@ int __detach_context(struct cxl_context *ctx)
 	if (status != STARTED)
 		return -EBUSY;
 
-	WARN_ON(cxl_detach_process(ctx));
+	/* Only warn if we detached while the link was OK.
+	 * If detach fails when hw is down, we don't care.
+	 */
+	WARN_ON(cxl_detach_process(ctx) &&
+		cxl_adapter_link_ok(ctx->afu->adapter));
 	flush_work(&ctx->fault_work); /* Only needed for dedicated process */
 	put_pid(ctx->pid);
 	cxl_ctx_put();
@@ -253,7 +269,11 @@ static void reclaim_ctx(struct rcu_head *rcu)
 	struct cxl_context *ctx = container_of(rcu, struct cxl_context, rcu);
 
 	free_page((u64)ctx->sstp);
+	if (ctx->ff_page)
+		__free_page(ctx->ff_page);
 	ctx->sstp = NULL;
+	if (ctx->kernelapi)
+		kfree(ctx->mapping);
 
 	kfree(ctx);
 }

drivers/misc/cxl/cxl.h

@@ -34,7 +34,7 @@ extern uint cxl_verbose;
  * 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 2
 #define CXL_API_VERSION_COMPATIBLE 1
 
 /*
@@ -83,8 +83,10 @@ 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_Timebase  = {0x0110};
 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_TB_CTLSTAT = {0x0140};
 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};
@@ -152,6 +154,9 @@ static const cxl_p2n_reg_t CXL_PSL_WED_An     = {0x0A0};
 #define CXL_PSL_SPAP_Size_Shift 4
 #define CXL_PSL_SPAP_V    0x0000000000000001ULL
 
+/****** CXL_PSL_Control ****************************************************/
+#define CXL_PSL_Control_tb 0x0000000000000001ULL
+
 /****** CXL_PSL_DLCNTL *****************************************************/
 #define CXL_PSL_DLCNTL_D (0x1ull << (63-28))
 #define CXL_PSL_DLCNTL_C (0x1ull << (63-29))
@@ -418,6 +423,9 @@ struct cxl_context {
 	/* Used to unmap any mmaps when force detaching */
 	struct address_space *mapping;
 	struct mutex mapping_lock;
+	struct page *ff_page;
+	bool mmio_err_ff;
+	bool kernelapi;
 
 	spinlock_t sste_lock; /* Protects segment table entries */
 	struct cxl_sste *sstp;
@@ -493,6 +501,7 @@ struct cxl {
 	bool user_image_loaded;
 	bool perst_loads_image;
 	bool perst_select_user;
+	bool perst_same_image;
 };
 
 int cxl_alloc_one_irq(struct cxl *adapter);
@@ -531,16 +540,33 @@ struct cxl_process_element {
 	__be32 software_state;
 } __packed;
 
+static inline bool cxl_adapter_link_ok(struct cxl *cxl)
+{
+	struct pci_dev *pdev;
+
+	pdev = to_pci_dev(cxl->dev.parent);
+	return !pci_channel_offline(pdev);
+}
+
 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 cxl_p1_write(struct cxl *cxl, cxl_p1_reg_t reg, u64 val)
+{
+	if (likely(cxl_adapter_link_ok(cxl)))
+		out_be64(_cxl_p1_addr(cxl, reg), val);
+}
+
+static inline u64 cxl_p1_read(struct cxl *cxl, cxl_p1_reg_t reg)
+{
+	if (likely(cxl_adapter_link_ok(cxl)))
+		return in_be64(_cxl_p1_addr(cxl, reg));
+	else
+		return ~0ULL;
+}
 
 static inline void __iomem *_cxl_p1n_addr(struct cxl_afu *afu, cxl_p1n_reg_t reg)
 {
@@ -548,26 +574,56 @@ static inline void __iomem *_cxl_p1n_addr(struct cxl_afu *afu, cxl_p1n_reg_t reg
 	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 cxl_p1n_write(struct cxl_afu *afu, cxl_p1n_reg_t reg, u64 val)
+{
+	if (likely(cxl_adapter_link_ok(afu->adapter)))
+		out_be64(_cxl_p1n_addr(afu, reg), val);
+}
+
+static inline u64 cxl_p1n_read(struct cxl_afu *afu, cxl_p1n_reg_t reg)
+{
+	if (likely(cxl_adapter_link_ok(afu->adapter)))
+		return in_be64(_cxl_p1n_addr(afu, reg));
+	else
+		return ~0ULL;
+}
 
 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))
+static inline void cxl_p2n_write(struct cxl_afu *afu, cxl_p2n_reg_t reg, u64 val)
+{
+	if (likely(cxl_adapter_link_ok(afu->adapter)))
+		out_be64(_cxl_p2n_addr(afu, reg), val);
+}
 
+static inline u64 cxl_p2n_read(struct cxl_afu *afu, cxl_p2n_reg_t reg)
+{
+	if (likely(cxl_adapter_link_ok(afu->adapter)))
+		return in_be64(_cxl_p2n_addr(afu, reg));
+	else
+		return ~0ULL;
+}
 
-#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))
+static inline u64 cxl_afu_cr_read64(struct cxl_afu *afu, int cr, u64 off)
+{
+	if (likely(cxl_adapter_link_ok(afu->adapter)))
+		return in_le64((afu)->afu_desc_mmio + (afu)->crs_offset +
+			       ((cr) * (afu)->crs_len) + (off));
+	else
+		return ~0ULL;
+}
+
+static inline u32 cxl_afu_cr_read32(struct cxl_afu *afu, int cr, u64 off)
+{
+	if (likely(cxl_adapter_link_ok(afu->adapter)))
+		return in_le32((afu)->afu_desc_mmio + (afu)->crs_offset +
+			       ((cr) * (afu)->crs_len) + (off));
+	else
+		return 0xffffffff;
+}
 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);
 
@@ -585,6 +641,9 @@ 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_alloc_spa(struct cxl_afu *afu);
+void cxl_release_spa(struct cxl_afu *afu);
+
 int cxl_file_init(void);
 void cxl_file_exit(void);
 int cxl_register_adapter(struct cxl *adapter);
@@ -675,6 +734,7 @@ int cxl_psl_purge(struct cxl_afu *afu);
 
 void cxl_stop_trace(struct cxl *cxl);
 int cxl_pci_vphb_add(struct cxl_afu *afu);
+void cxl_pci_vphb_reconfigure(struct cxl_afu *afu);
 void cxl_pci_vphb_remove(struct cxl_afu *afu);
 
 extern struct pci_driver cxl_pci_driver;

drivers/misc/cxl/debugfs.c

@@ -48,7 +48,7 @@ DEFINE_SIMPLE_ATTRIBUTE(fops_io_x64, debugfs_io_u64_get, debugfs_io_u64_set, "0x
 static struct dentry *debugfs_create_io_x64(const char *name, umode_t mode,
 					    struct dentry *parent, u64 __iomem *value)
 {
-	return debugfs_create_file(name, mode, parent, (void *)value, &fops_io_x64);
+	return debugfs_create_file(name, mode, parent, (void __force *)value, &fops_io_x64);
 }
 
 int cxl_debugfs_adapter_add(struct cxl *adapter)

drivers/misc/cxl/file.c

@@ -73,6 +73,11 @@ static int __afu_open(struct inode *inode, struct file *file, bool master)
 	if (!afu->current_mode)
 		goto err_put_afu;
 
+	if (!cxl_adapter_link_ok(adapter)) {
+		rc = -EIO;
+		goto err_put_afu;
+	}
+
 	if (!(ctx = cxl_context_alloc())) {
 		rc = -ENOMEM;
 		goto err_put_afu;
@@ -179,6 +184,8 @@ static long afu_ioctl_start_work(struct cxl_context *ctx,
 	if (work.flags & CXL_START_WORK_AMR)
 		amr = work.amr & mfspr(SPRN_UAMOR);
 
+	ctx->mmio_err_ff = !!(work.flags & CXL_START_WORK_ERR_FF);
+
 	/*
 	 * 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
@@ -238,6 +245,9 @@ long afu_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 	if (ctx->status == CLOSED)
 		return -EIO;
 
+	if (!cxl_adapter_link_ok(ctx->afu->adapter))
+		return -EIO;
+
 	pr_devel("afu_ioctl\n");
 	switch (cmd) {
 	case CXL_IOCTL_START_WORK:
@@ -251,7 +261,7 @@ long afu_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 	return -EINVAL;
 }
 
-long afu_compat_ioctl(struct file *file, unsigned int cmd,
+static long afu_compat_ioctl(struct file *file, unsigned int cmd,
 			     unsigned long arg)
 {
 	return afu_ioctl(file, cmd, arg);
@@ -265,6 +275,9 @@ int afu_mmap(struct file *file, struct vm_area_struct *vm)
 	if (ctx->status != STARTED)
 		return -EIO;
 
+	if (!cxl_adapter_link_ok(ctx->afu->adapter))
+		return -EIO;
+
 	return cxl_context_iomap(ctx, vm);
 }
 
@@ -309,6 +322,9 @@ ssize_t afu_read(struct file *file, char __user *buf, size_t count,
 	int rc;
 	DEFINE_WAIT(wait);
 
+	if (!cxl_adapter_link_ok(ctx->afu->adapter))
+		return -EIO;
+
 	if (count < CXL_READ_MIN_SIZE)
 		return -EINVAL;
 
@@ -319,6 +335,11 @@ ssize_t afu_read(struct file *file, char __user *buf, size_t count,
 		if (ctx_event_pending(ctx))
 			break;
 
+		if (!cxl_adapter_link_ok(ctx->afu->adapter)) {
+			rc = -EIO;
+			goto out;
+		}
+
 		if (file->f_flags & O_NONBLOCK) {
 			rc = -EAGAIN;
 			goto out;
@@ -396,7 +417,7 @@ const struct file_operations afu_fops = {
 	.mmap           = afu_mmap,
 };
 
-const struct file_operations afu_master_fops = {
+static const struct file_operations afu_master_fops = {
 	.owner		= THIS_MODULE,
 	.open           = afu_master_open,
 	.poll		= afu_poll,
@@ -519,7 +540,7 @@ int __init cxl_file_init(void)
 	 * If these change we really need to update API.  Either change some
 	 * flags or update API version number CXL_API_VERSION.
 	 */
-	BUILD_BUG_ON(CXL_API_VERSION != 1);
+	BUILD_BUG_ON(CXL_API_VERSION != 2);
 	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);

drivers/misc/cxl/irq.c

@@ -30,12 +30,12 @@ static irqreturn_t handle_psl_slice_error(struct cxl_context *ctx, u64 dsisr, u6
 	serr = cxl_p1n_read(ctx->afu, CXL_PSL_SERR_An);
 	afu_debug = cxl_p1n_read(ctx->afu, CXL_AFU_DEBUG_An);
 
-	dev_crit(&ctx->afu->dev, "PSL ERROR STATUS: 0x%.16llx\n", errstat);
-	dev_crit(&ctx->afu->dev, "PSL_FIR1: 0x%.16llx\n", fir1);
-	dev_crit(&ctx->afu->dev, "PSL_FIR2: 0x%.16llx\n", fir2);
-	dev_crit(&ctx->afu->dev, "PSL_SERR_An: 0x%.16llx\n", serr);
-	dev_crit(&ctx->afu->dev, "PSL_FIR_SLICE_An: 0x%.16llx\n", fir_slice);
-	dev_crit(&ctx->afu->dev, "CXL_PSL_AFU_DEBUG_An: 0x%.16llx\n", afu_debug);
+	dev_crit(&ctx->afu->dev, "PSL ERROR STATUS: 0x%016llx\n", errstat);
+	dev_crit(&ctx->afu->dev, "PSL_FIR1: 0x%016llx\n", fir1);
+	dev_crit(&ctx->afu->dev, "PSL_FIR2: 0x%016llx\n", fir2);
+	dev_crit(&ctx->afu->dev, "PSL_SERR_An: 0x%016llx\n", serr);
+	dev_crit(&ctx->afu->dev, "PSL_FIR_SLICE_An: 0x%016llx\n", fir_slice);
+	dev_crit(&ctx->afu->dev, "CXL_PSL_AFU_DEBUG_An: 0x%016llx\n", afu_debug);
 
 	dev_crit(&ctx->afu->dev, "STOPPING CXL TRACE\n");
 	cxl_stop_trace(ctx->afu->adapter);
@@ -54,10 +54,10 @@ irqreturn_t cxl_slice_irq_err(int irq, void *data)
 	fir_slice = cxl_p1n_read(afu, CXL_PSL_FIR_SLICE_An);
 	errstat = cxl_p2n_read(afu, CXL_PSL_ErrStat_An);
 	afu_debug = cxl_p1n_read(afu, CXL_AFU_DEBUG_An);
-	dev_crit(&afu->dev, "PSL_SERR_An: 0x%.16llx\n", serr);
-	dev_crit(&afu->dev, "PSL_FIR_SLICE_An: 0x%.16llx\n", fir_slice);
-	dev_crit(&afu->dev, "CXL_PSL_ErrStat_An: 0x%.16llx\n", errstat);
-	dev_crit(&afu->dev, "CXL_PSL_AFU_DEBUG_An: 0x%.16llx\n", afu_debug);
+	dev_crit(&afu->dev, "PSL_SERR_An: 0x%016llx\n", serr);
+	dev_crit(&afu->dev, "PSL_FIR_SLICE_An: 0x%016llx\n", fir_slice);
+	dev_crit(&afu->dev, "CXL_PSL_ErrStat_An: 0x%016llx\n", errstat);
+	dev_crit(&afu->dev, "CXL_PSL_AFU_DEBUG_An: 0x%016llx\n", afu_debug);
 
 	cxl_p1n_write(afu, CXL_PSL_SERR_An, serr);
 
@@ -72,7 +72,7 @@ static irqreturn_t cxl_irq_err(int irq, void *data)
 	WARN(1, "CXL ERROR interrupt %i\n", irq);
 
 	err_ivte = cxl_p1_read(adapter, CXL_PSL_ErrIVTE);
-	dev_crit(&adapter->dev, "PSL_ErrIVTE: 0x%.16llx\n", err_ivte);
+	dev_crit(&adapter->dev, "PSL_ErrIVTE: 0x%016llx\n", err_ivte);
 
 	dev_crit(&adapter->dev, "STOPPING CXL TRACE\n");
 	cxl_stop_trace(adapter);
@@ -80,7 +80,7 @@ static irqreturn_t cxl_irq_err(int irq, void *data)
 	fir1 = cxl_p1_read(adapter, CXL_PSL_FIR1);
 	fir2 = cxl_p1_read(adapter, CXL_PSL_FIR2);
 
-	dev_crit(&adapter->dev, "PSL_FIR1: 0x%.16llx\nPSL_FIR2: 0x%.16llx\n", fir1, fir2);
+	dev_crit(&adapter->dev, "PSL_FIR1: 0x%016llx\nPSL_FIR2: 0x%016llx\n", fir1, fir2);
 
 	return IRQ_HANDLED;
 }
@@ -147,7 +147,7 @@ static irqreturn_t cxl_irq(int irq, void *data, struct cxl_irq_info *irq_info)
 	if (dsisr & CXL_PSL_DSISR_An_PE)
 		return handle_psl_slice_error(ctx, dsisr, irq_info->errstat);
 	if (dsisr & CXL_PSL_DSISR_An_AE) {
-		pr_devel("CXL interrupt: AFU Error %.llx\n", irq_info->afu_err);
+		pr_devel("CXL interrupt: AFU Error 0x%016llx\n", irq_info->afu_err);
 
 		if (ctx->pending_afu_err) {
 			/*
@@ -158,7 +158,7 @@ static irqreturn_t cxl_irq(int irq, void *data, struct cxl_irq_info *irq_info)
 			 * probably best that we log them somewhere:
 			 */
 			dev_err_ratelimited(&ctx->afu->dev, "CXL AFU Error "
-					    "undelivered to pe %i: %.llx\n",
+					    "undelivered to pe %i: 0x%016llx\n",
 					    ctx->pe, irq_info->afu_err);
 		} else {
 			spin_lock(&ctx->lock);
@@ -211,8 +211,8 @@ static irqreturn_t cxl_irq_multiplexed(int irq, void *data)
 	}
 	rcu_read_unlock();
 
-	WARN(1, "Unable to demultiplex CXL PSL IRQ for PE %i DSISR %.16llx DAR"
-		" %.16llx\n(Possible AFU HW issue - was a term/remove acked"
+	WARN(1, "Unable to demultiplex CXL PSL IRQ for PE %i DSISR %016llx DAR"
+		" %016llx\n(Possible AFU HW issue - was a term/remove acked"
 		" with outstanding transactions?)\n", ph, irq_info.dsisr,
 		irq_info.dar);
 	return fail_psl_irq(afu, &irq_info);
@@ -341,6 +341,9 @@ int cxl_register_psl_err_irq(struct cxl *adapter)
 
 void cxl_release_psl_err_irq(struct cxl *adapter)
 {
+	if (adapter->err_virq != irq_find_mapping(NULL, adapter->err_hwirq))
+		return;
+
 	cxl_p1_write(adapter, CXL_PSL_ErrIVTE, 0x0000000000000000);
 	cxl_unmap_irq(adapter->err_virq, adapter);
 	cxl_release_one_irq(adapter, adapter->err_hwirq);
@@ -374,6 +377,9 @@ int cxl_register_serr_irq(struct cxl_afu *afu)
 
 void cxl_release_serr_irq(struct cxl_afu *afu)
 {
+	if (afu->serr_virq != irq_find_mapping(NULL, afu->serr_hwirq))
+		return;
+
 	cxl_p1n_write(afu, CXL_PSL_SERR_An, 0x0000000000000000);
 	cxl_unmap_irq(afu->serr_virq, afu);
 	cxl_release_one_irq(afu->adapter, afu->serr_hwirq);
@@ -400,12 +406,15 @@ int cxl_register_psl_irq(struct cxl_afu *afu)
 
 void cxl_release_psl_irq(struct cxl_afu *afu)
 {
+	if (afu->psl_virq != irq_find_mapping(NULL, afu->psl_hwirq))
+		return;
+
 	cxl_unmap_irq(afu->psl_virq, afu);
 	cxl_release_one_irq(afu->adapter, afu->psl_hwirq);
 	kfree(afu->psl_irq_name);
 }
 
-void afu_irq_name_free(struct cxl_context *ctx)
+static void afu_irq_name_free(struct cxl_context *ctx)
 {
 	struct cxl_irq_name *irq_name, *tmp;
 
@@ -421,6 +430,9 @@ int afu_allocate_irqs(struct cxl_context *ctx, u32 count)
 	int rc, r, i, j = 1;
 	struct cxl_irq_name *irq_name;
 
+	/* Initialize the list head to hold irq names */
+	INIT_LIST_HEAD(&ctx->irq_names);
+
 	if ((rc = cxl_alloc_irq_ranges(&ctx->irqs, ctx->afu->adapter, count)))
 		return rc;
 
@@ -432,13 +444,12 @@ int afu_allocate_irqs(struct cxl_context *ctx, u32 count)
 	ctx->irq_bitmap = kcalloc(BITS_TO_LONGS(count),
 				  sizeof(*ctx->irq_bitmap), GFP_KERNEL);
 	if (!ctx->irq_bitmap)
-		return -ENOMEM;
+		goto out;
 
 	/*
 	 * Allocate names first.  If any fail, bail out before allocating
 	 * actual hardware IRQs.
 	 */
-	INIT_LIST_HEAD(&ctx->irq_names);
 	for (r = 1; r < CXL_IRQ_RANGES; r++) {
 		for (i = 0; i < ctx->irqs.range[r]; i++) {
 			irq_name = kmalloc(sizeof(struct cxl_irq_name),
@@ -460,11 +471,12 @@ int afu_allocate_irqs(struct cxl_context *ctx, u32 count)
 	return 0;
 
 out:
+	cxl_release_irq_ranges(&ctx->irqs, ctx->afu->adapter);
 	afu_irq_name_free(ctx);
 	return -ENOMEM;
 }
 
-void afu_register_hwirqs(struct cxl_context *ctx)
+static void afu_register_hwirqs(struct cxl_context *ctx)
 {
 	irq_hw_number_t hwirq;
 	struct cxl_irq_name *irq_name;
@@ -511,4 +523,8 @@ void afu_release_irqs(struct cxl_context *ctx, void *cookie)
 
 	afu_irq_name_free(ctx);
 	cxl_release_irq_ranges(&ctx->irqs, ctx->afu->adapter);
+
+	kfree(ctx->irq_bitmap);
+	ctx->irq_bitmap = NULL;
+	ctx->irq_count = 0;
 }

drivers/misc/cxl/main.c

@@ -222,6 +222,7 @@ static void exit_cxl(void)
 	cxl_debugfs_exit();
 	cxl_file_exit();
 	unregister_cxl_calls(&cxl_calls);
+	idr_destroy(&cxl_adapter_idr);
 }
 
 module_init(init_cxl);

drivers/misc/cxl/native.c

@@ -41,7 +41,14 @@ static int afu_control(struct cxl_afu *afu, u64 command,
 			rc = -EBUSY;
 			goto out;
 		}
-		pr_devel_ratelimited("AFU control... (0x%.16llx)\n",
+
+		if (!cxl_adapter_link_ok(afu->adapter)) {
+			afu->enabled = enabled;
+			rc = -EIO;
+			goto out;
+		}
+
+		pr_devel_ratelimited("AFU control... (0x%016llx)\n",
 				     AFU_Cntl | command);
 		cpu_relax();
 		AFU_Cntl = cxl_p2n_read(afu, CXL_AFU_Cntl_An);
@@ -85,6 +92,10 @@ int __cxl_afu_reset(struct cxl_afu *afu)
 
 int cxl_afu_check_and_enable(struct cxl_afu *afu)
 {
+	if (!cxl_adapter_link_ok(afu->adapter)) {
+		WARN(1, "Refusing to enable afu while link down!\n");
+		return -EIO;
+	}
 	if (afu->enabled)
 		return 0;
 	return afu_enable(afu);
@@ -103,6 +114,12 @@ int cxl_psl_purge(struct cxl_afu *afu)
 
 	pr_devel("PSL purge request\n");
 
+	if (!cxl_adapter_link_ok(afu->adapter)) {
+		dev_warn(&afu->dev, "PSL Purge called with link down, ignoring\n");
+		rc = -EIO;
+		goto out;
+	}
+
 	if ((AFU_Cntl & CXL_AFU_Cntl_An_ES_MASK) != CXL_AFU_Cntl_An_ES_Disabled) {
 		WARN(1, "psl_purge request while AFU not disabled!\n");
 		cxl_afu_disable(afu);
@@ -119,14 +136,19 @@ int cxl_psl_purge(struct cxl_afu *afu)
 			rc = -EBUSY;
 			goto out;
 		}
+		if (!cxl_adapter_link_ok(afu->adapter)) {
+			rc = -EIO;
+			goto out;
+		}
+
 		dsisr = cxl_p2n_read(afu, CXL_PSL_DSISR_An);
-		pr_devel_ratelimited("PSL purging... PSL_CNTL: 0x%.16llx  PSL_DSISR: 0x%.16llx\n", PSL_CNTL, dsisr);
+		pr_devel_ratelimited("PSL purging... PSL_CNTL: 0x%016llx  PSL_DSISR: 0x%016llx\n", PSL_CNTL, dsisr);
 		if (dsisr & CXL_PSL_DSISR_TRANS) {
 			dar = cxl_p2n_read(afu, CXL_PSL_DAR_An);
-			dev_notice(&afu->dev, "PSL purge terminating pending translation, DSISR: 0x%.16llx, DAR: 0x%.16llx\n", dsisr, dar);
+			dev_notice(&afu->dev, "PSL purge terminating pending translation, DSISR: 0x%016llx, DAR: 0x%016llx\n", dsisr, dar);
 			cxl_p2n_write(afu, CXL_PSL_TFC_An, CXL_PSL_TFC_An_AE);
 		} else if (dsisr) {
-			dev_notice(&afu->dev, "PSL purge acknowledging pending non-translation fault, DSISR: 0x%.16llx\n", dsisr);
+			dev_notice(&afu->dev, "PSL purge acknowledging pending non-translation fault, DSISR: 0x%016llx\n", dsisr);
 			cxl_p2n_write(afu, CXL_PSL_TFC_An, CXL_PSL_TFC_An_A);
 		} else {
 			cpu_relax();
@@ -161,10 +183,8 @@ static int spa_max_procs(int spa_size)
 	return ((spa_size / 8) - 96) / 17;
 }
 
-static int alloc_spa(struct cxl_afu *afu)
+int cxl_alloc_spa(struct cxl_afu *afu)
 {
-	u64 spap;
-
 	/* Work out how many pages to allocate */
 	afu->spa_order = 0;
 	do {
@@ -183,6 +203,13 @@ static int alloc_spa(struct cxl_afu *afu)
 	pr_devel("spa pages: %i afu->spa_max_procs: %i   afu->num_procs: %i\n",
 		 1<<afu->spa_order, afu->spa_max_procs, afu->num_procs);
 
+	return 0;
+}
+
+static void attach_spa(struct cxl_afu *afu)
+{
+	u64 spap;
+
 	afu->sw_command_status = (__be64 *)((char *)afu->spa +
 					    ((afu->spa_max_procs + 3) * 128));
 
@@ -191,14 +218,19 @@ static int alloc_spa(struct cxl_afu *afu)
 	spap |= CXL_PSL_SPAP_V;
 	pr_devel("cxl: SPA allocated at 0x%p. Max processes: %i, sw_command_status: 0x%p CXL_PSL_SPAP_An=0x%016llx\n", afu->spa, afu->spa_max_procs, afu->sw_command_status, spap);
 	cxl_p1n_write(afu, CXL_PSL_SPAP_An, spap);
-
-	return 0;
 }
 
-static void release_spa(struct cxl_afu *afu)
+static inline void detach_spa(struct cxl_afu *afu)
 {
 	cxl_p1n_write(afu, CXL_PSL_SPAP_An, 0);
-	free_pages((unsigned long) afu->spa, afu->spa_order);
+}
+
+void cxl_release_spa(struct cxl_afu *afu)
+{
+	if (afu->spa) {
+		free_pages((unsigned long) afu->spa, afu->spa_order);
+		afu->spa = NULL;
+	}
 }
 
 int cxl_tlb_slb_invalidate(struct cxl *adapter)
@@ -215,6 +247,8 @@ int cxl_tlb_slb_invalidate(struct cxl *adapter)
 			dev_warn(&adapter->dev, "WARNING: CXL adapter wide TLBIA timed out!\n");
 			return -EBUSY;
 		}
+		if (!cxl_adapter_link_ok(adapter))
+			return -EIO;
 		cpu_relax();
 	}
 
@@ -224,6 +258,8 @@ int cxl_tlb_slb_invalidate(struct cxl *adapter)
 			dev_warn(&adapter->dev, "WARNING: CXL adapter wide SLBIA timed out!\n");
 			return -EBUSY;
 		}
+		if (!cxl_adapter_link_ok(adapter))
+			return -EIO;
 		cpu_relax();
 	}
 	return 0;
@@ -240,6 +276,11 @@ int cxl_afu_slbia(struct cxl_afu *afu)
 			dev_warn(&afu->dev, "WARNING: CXL AFU SLBIA timed out!\n");
 			return -EBUSY;
 		}
+		/* If the adapter has gone down, we can assume that we
+		 * will PERST it and that will invalidate everything.
+		 */
+		if (!cxl_adapter_link_ok(afu->adapter))
+			return -EIO;
 		cpu_relax();
 	}
 	return 0;
@@ -279,6 +320,8 @@ static void slb_invalid(struct cxl_context *ctx)
 	cxl_p1_write(adapter, CXL_PSL_SLBIA, CXL_TLB_SLB_IQ_LPIDPID);
 
 	while (1) {
+		if (!cxl_adapter_link_ok(adapter))
+			break;
 		slbia = cxl_p1_read(adapter, CXL_PSL_SLBIA);
 		if (!(slbia & CXL_TLB_SLB_P))
 			break;
@@ -308,6 +351,11 @@ static int do_process_element_cmd(struct cxl_context *ctx,
 			rc = -EBUSY;
 			goto out;
 		}
+		if (!cxl_adapter_link_ok(ctx->afu->adapter)) {
+			dev_warn(&ctx->afu->dev, "WARNING: Device link down, aborting Process Element Command!\n");
+			rc = -EIO;
+			goto out;
+		}
 		state = be64_to_cpup(ctx->afu->sw_command_status);
 		if (state == ~0ULL) {
 			pr_err("cxl: Error adding process element to AFU\n");
@@ -355,8 +403,13 @@ static int terminate_process_element(struct cxl_context *ctx)
 
 	mutex_lock(&ctx->afu->spa_mutex);
 	pr_devel("%s Terminate pe: %i started\n", __func__, ctx->pe);
-	rc = do_process_element_cmd(ctx, CXL_SPA_SW_CMD_TERMINATE,
-				    CXL_PE_SOFTWARE_STATE_V | CXL_PE_SOFTWARE_STATE_T);
+	/* We could be asked to terminate when the hw is down. That
+	 * should always succeed: it's not running if the hw has gone
+	 * away and is being reset.
+	 */
+	if (cxl_adapter_link_ok(ctx->afu->adapter))
+		rc = do_process_element_cmd(ctx, CXL_SPA_SW_CMD_TERMINATE,
+					    CXL_PE_SOFTWARE_STATE_V | CXL_PE_SOFTWARE_STATE_T);
 	ctx->elem->software_state = 0;	/* Remove Valid bit */
 	pr_devel("%s Terminate pe: %i finished\n", __func__, ctx->pe);
 	mutex_unlock(&ctx->afu->spa_mutex);
@@ -369,7 +422,14 @@ static int remove_process_element(struct cxl_context *ctx)
 
 	mutex_lock(&ctx->afu->spa_mutex);
 	pr_devel("%s Remove pe: %i started\n", __func__, ctx->pe);
-	if (!(rc = do_process_element_cmd(ctx, CXL_SPA_SW_CMD_REMOVE, 0)))
+
+	/* We could be asked to remove when the hw is down. Again, if
+	 * the hw is down, the PE is gone, so we succeed.
+	 */
+	if (cxl_adapter_link_ok(ctx->afu->adapter))
+		rc = do_process_element_cmd(ctx, CXL_SPA_SW_CMD_REMOVE, 0);
+
+	if (!rc)
 		ctx->pe_inserted = false;
 	slb_invalid(ctx);
 	pr_devel("%s Remove pe: %i finished\n", __func__, ctx->pe);
@@ -397,8 +457,11 @@ static int activate_afu_directed(struct cxl_afu *afu)
 
 	dev_info(&afu->dev, "Activating AFU directed mode\n");
 
-	if (alloc_spa(afu))
-		return -ENOMEM;
+	if (afu->spa == NULL) {
+		if (cxl_alloc_spa(afu))
+			return -ENOMEM;
+	}
+	attach_spa(afu);
 
 	cxl_p1n_write(afu, CXL_PSL_SCNTL_An, CXL_PSL_SCNTL_An_PM_AFU);
 	cxl_p1n_write(afu, CXL_PSL_AMOR_An, 0xFFFFFFFFFFFFFFFFULL);
@@ -492,9 +555,7 @@ static int attach_afu_directed(struct cxl_context *ctx, u64 wed, u64 amr)
 	if ((result = cxl_afu_check_and_enable(ctx->afu)))
 		return result;
 
-	add_process_element(ctx);
-
-	return 0;
+	return add_process_element(ctx);
 }
 
 static int deactivate_afu_directed(struct cxl_afu *afu)
@@ -511,8 +572,6 @@ static int deactivate_afu_directed(struct cxl_afu *afu)
 	cxl_afu_disable(afu);
 	cxl_psl_purge(afu);
 
-	release_spa(afu);
-
 	return 0;
 }
 
@@ -614,6 +673,11 @@ int cxl_afu_activate_mode(struct cxl_afu *afu, int mode)
 	if (!(mode & afu->modes_supported))
 		return -EINVAL;
 
+	if (!cxl_adapter_link_ok(afu->adapter)) {
+		WARN(1, "Device link is down, refusing to activate!\n");
+		return -EIO;
+	}
+
 	if (mode == CXL_MODE_DIRECTED)
 		return activate_afu_directed(afu);
 	if (mode == CXL_MODE_DEDICATED)
@@ -624,6 +688,11 @@ int cxl_afu_activate_mode(struct cxl_afu *afu, int mode)
 
 int cxl_attach_process(struct cxl_context *ctx, bool kernel, u64 wed, u64 amr)
 {
+	if (!cxl_adapter_link_ok(ctx->afu->adapter)) {
+		WARN(1, "Device link is down, refusing to attach process!\n");
+		return -EIO;
+	}
+
 	ctx->kernel = kernel;
 	if (ctx->afu->current_mode == CXL_MODE_DIRECTED)
 		return attach_afu_directed(ctx, wed, amr);
@@ -668,6 +737,12 @@ int cxl_get_irq(struct cxl_afu *afu, struct cxl_irq_info *info)
 {
 	u64 pidtid;
 
+	/* If the adapter has gone away, we can't get any meaningful
+	 * information.
+	 */
+	if (!cxl_adapter_link_ok(afu->adapter))
+		return -EIO;
+
 	info->dsisr = cxl_p2n_read(afu, CXL_PSL_DSISR_An);
 	info->dar = cxl_p2n_read(afu, CXL_PSL_DAR_An);
 	info->dsr = cxl_p2n_read(afu, CXL_PSL_DSR_An);
@@ -684,7 +759,7 @@ static void recover_psl_err(struct cxl_afu *afu, u64 errstat)
 {
 	u64 dsisr;
 
-	pr_devel("RECOVERING FROM PSL ERROR... (0x%.16llx)\n", errstat);
+	pr_devel("RECOVERING FROM PSL ERROR... (0x%016llx)\n", errstat);
 
 	/* Clear PSL_DSISR[PE] */
 	dsisr = cxl_p2n_read(afu, CXL_PSL_DSISR_An);

drivers/misc/cxl/pci.c

@@ -24,6 +24,7 @@
 #include <asm/io.h>
 
 #include "cxl.h"
+#include <misc/cxl.h>
 
 
 #define CXL_PCI_VSEC_ID	0x1280
@@ -133,7 +134,7 @@ u8 cxl_afu_cr_read8(struct cxl_afu *afu, int cr, u64 off)
 	return (val >> ((off & 0x3) * 8)) & 0xff;
 }
 
-static DEFINE_PCI_DEVICE_TABLE(cxl_pci_tbl) = {
+static const struct pci_device_id cxl_pci_tbl[] = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_IBM, 0x0477), },
 	{ PCI_DEVICE(PCI_VENDOR_ID_IBM, 0x044b), },
 	{ PCI_DEVICE(PCI_VENDOR_ID_IBM, 0x04cf), },
@@ -369,6 +370,55 @@ static int init_implementation_adapter_regs(struct cxl *adapter, struct pci_dev
 	return 0;
 }
 
+#define TBSYNC_CNT(n) (((u64)n & 0x7) << (63-6))
+#define _2048_250MHZ_CYCLES 1
+
+static int cxl_setup_psl_timebase(struct cxl *adapter, struct pci_dev *dev)
+{
+	u64 psl_tb;
+	int delta;
+	unsigned int retry = 0;
+	struct device_node *np;
+
+	if (!(np = pnv_pci_get_phb_node(dev)))
+		return -ENODEV;
+
+	/* Do not fail when CAPP timebase sync is not supported by OPAL */
+	of_node_get(np);
+	if (! of_get_property(np, "ibm,capp-timebase-sync", NULL)) {
+		of_node_put(np);
+		pr_err("PSL: Timebase sync: OPAL support missing\n");
+		return 0;
+	}
+	of_node_put(np);
+
+	/*
+	 * Setup PSL Timebase Control and Status register
+	 * with the recommended Timebase Sync Count value
+	 */
+	cxl_p1_write(adapter, CXL_PSL_TB_CTLSTAT,
+		     TBSYNC_CNT(2 * _2048_250MHZ_CYCLES));
+
+	/* Enable PSL Timebase */
+	cxl_p1_write(adapter, CXL_PSL_Control, 0x0000000000000000);
+	cxl_p1_write(adapter, CXL_PSL_Control, CXL_PSL_Control_tb);
+
+	/* Wait until CORE TB and PSL TB difference <= 16usecs */
+	do {
+		msleep(1);
+		if (retry++ > 5) {
+			pr_err("PSL: Timebase sync: giving up!\n");
+			return -EIO;
+		}
+		psl_tb = cxl_p1_read(adapter, CXL_PSL_Timebase);
+		delta = mftb() - psl_tb;
+		if (delta < 0)
+			delta = -delta;
+	} while (cputime_to_usecs(delta) > 16);
+
+	return 0;
+}
+
 static int init_implementation_afu_regs(struct cxl_afu *afu)
 {
 	/* read/write masks for this slice */
@@ -539,10 +589,18 @@ err:
 
 static void cxl_unmap_slice_regs(struct cxl_afu *afu)
 {
-	if (afu->p2n_mmio)
+	if (afu->p2n_mmio) {
 		iounmap(afu->p2n_mmio);
-	if (afu->p1n_mmio)
+		afu->p2n_mmio = NULL;
+	}
+	if (afu->p1n_mmio) {
 		iounmap(afu->p1n_mmio);
+		afu->p1n_mmio = NULL;
+	}
+	if (afu->afu_desc_mmio) {
+		iounmap(afu->afu_desc_mmio);
+		afu->afu_desc_mmio = NULL;
+	}
 }
 
 static void cxl_release_afu(struct device *dev)
@@ -551,6 +609,9 @@ static void cxl_release_afu(struct device *dev)
 
 	pr_devel("cxl_release_afu\n");
 
+	idr_destroy(&afu->contexts_idr);
+	cxl_release_spa(afu);
+
 	kfree(afu);
 }
 
@@ -656,7 +717,7 @@ static int sanitise_afu_regs(struct cxl_afu *afu)
 	 */
 	reg = cxl_p2n_read(afu, CXL_AFU_Cntl_An);
 	if ((reg & CXL_AFU_Cntl_An_ES_MASK) != CXL_AFU_Cntl_An_ES_Disabled) {
-		dev_warn(&afu->dev, "WARNING: AFU was not disabled: %#.16llx\n", reg);
+		dev_warn(&afu->dev, "WARNING: AFU was not disabled: %#016llx\n", reg);
 		if (__cxl_afu_reset(afu))
 			return -EIO;
 		if (cxl_afu_disable(afu))
@@ -677,7 +738,7 @@ static int sanitise_afu_regs(struct cxl_afu *afu)
 	cxl_p2n_write(afu, CXL_SSTP0_An, 0x0000000000000000);
 	reg = cxl_p2n_read(afu, CXL_PSL_DSISR_An);
 	if (reg) {
-		dev_warn(&afu->dev, "AFU had pending DSISR: %#.16llx\n", reg);
+		dev_warn(&afu->dev, "AFU had pending DSISR: %#016llx\n", reg);
 		if (reg & CXL_PSL_DSISR_TRANS)
 			cxl_p2n_write(afu, CXL_PSL_TFC_An, CXL_PSL_TFC_An_AE);
 		else
@@ -686,12 +747,12 @@ static int sanitise_afu_regs(struct cxl_afu *afu)
 	reg = cxl_p1n_read(afu, CXL_PSL_SERR_An);
 	if (reg) {
 		if (reg & ~0xffff)
-			dev_warn(&afu->dev, "AFU had pending SERR: %#.16llx\n", reg);
+			dev_warn(&afu->dev, "AFU had pending SERR: %#016llx\n", reg);
 		cxl_p1n_write(afu, CXL_PSL_SERR_An, reg & ~0xffff);
 	}
 	reg = cxl_p2n_read(afu, CXL_PSL_ErrStat_An);
 	if (reg) {
-		dev_warn(&afu->dev, "AFU had pending error status: %#.16llx\n", reg);
+		dev_warn(&afu->dev, "AFU had pending error status: %#016llx\n", reg);
 		cxl_p2n_write(afu, CXL_PSL_ErrStat_An, reg);
 	}
 
@@ -742,45 +803,70 @@ ssize_t cxl_afu_read_err_buffer(struct cxl_afu *afu, char *buf,
 	return count;
 }
 
-static int cxl_init_afu(struct cxl *adapter, int slice, struct pci_dev *dev)
+static int cxl_configure_afu(struct cxl_afu *afu, struct cxl *adapter, struct pci_dev *dev)
 {
-	struct cxl_afu *afu;
-	bool free = true;
 	int rc;
 
-	if (!(afu = cxl_alloc_afu(adapter, slice)))
-		return -ENOMEM;
-
-	if ((rc = dev_set_name(&afu->dev, "afu%i.%i", adapter->adapter_num, slice)))
-		goto err1;
-
 	if ((rc = cxl_map_slice_regs(afu, adapter, dev)))
-		goto err1;
+		return rc;
 
 	if ((rc = sanitise_afu_regs(afu)))
-		goto err2;
+		goto err1;
 
 	/* We need to reset the AFU before we can read the AFU descriptor */
 	if ((rc = __cxl_afu_reset(afu)))
-		goto err2;
+		goto err1;
 
 	if (cxl_verbose)
 		dump_afu_descriptor(afu);
 
 	if ((rc = cxl_read_afu_descriptor(afu)))
-		goto err2;
+		goto err1;
 
 	if ((rc = cxl_afu_descriptor_looks_ok(afu)))
-		goto err2;
+		goto err1;
 
 	if ((rc = init_implementation_afu_regs(afu)))
-		goto err2;
+		goto err1;
 
 	if ((rc = cxl_register_serr_irq(afu)))
-		goto err2;
+		goto err1;
 
 	if ((rc = cxl_register_psl_irq(afu)))
-		goto err3;
+		goto err2;
+
+	return 0;
+
+err2:
+	cxl_release_serr_irq(afu);
+err1:
+	cxl_unmap_slice_regs(afu);
+	return rc;
+}
+
+static void cxl_deconfigure_afu(struct cxl_afu *afu)
+{
+	cxl_release_psl_irq(afu);
+	cxl_release_serr_irq(afu);
+	cxl_unmap_slice_regs(afu);
+}
+
+static int cxl_init_afu(struct cxl *adapter, int slice, struct pci_dev *dev)
+{
+	struct cxl_afu *afu;
+	int rc;
+
+	afu = cxl_alloc_afu(adapter, slice);
+	if (!afu)
+		return -ENOMEM;
+
+	rc = dev_set_name(&afu->dev, "afu%i.%i", adapter->adapter_num, slice);
+	if (rc)
+		goto err_free;
+
+	rc = cxl_configure_afu(afu, adapter, dev);
+	if (rc)
+		goto err_free;
 
 	/* Don't care if this fails */
 	cxl_debugfs_afu_add(afu);
@@ -795,10 +881,6 @@ static int cxl_init_afu(struct cxl *adapter, int slice, struct pci_dev *dev)
 	if ((rc = cxl_sysfs_afu_add(afu)))
 		goto err_put1;
 
-
-	if ((rc = cxl_afu_select_best_mode(afu)))
-		goto err_put2;
-
 	adapter->afu[afu->slice] = afu;
 
 	if ((rc = cxl_pci_vphb_add(afu)))
@@ -806,21 +888,16 @@ static int cxl_init_afu(struct cxl *adapter, int slice, struct pci_dev *dev)
 
 	return 0;
 
-err_put2:
-	cxl_sysfs_afu_remove(afu);
 err_put1:
-	device_unregister(&afu->dev);
-	free = false;
+	cxl_deconfigure_afu(afu);
 	cxl_debugfs_afu_remove(afu);
-	cxl_release_psl_irq(afu);
-err3:
-	cxl_release_serr_irq(afu);
-err2:
-	cxl_unmap_slice_regs(afu);
-err1:
-	if (free)
-		kfree(afu);
+	device_unregister(&afu->dev);
 	return rc;
+
+err_free:
+	kfree(afu);
+	return rc;
+
 }
 
 static void cxl_remove_afu(struct cxl_afu *afu)
@@ -840,10 +917,7 @@ static void cxl_remove_afu(struct cxl_afu *afu)
 	cxl_context_detach_all(afu);
 	cxl_afu_deactivate_mode(afu);
 
-	cxl_release_psl_irq(afu);
-	cxl_release_serr_irq(afu);
-	cxl_unmap_slice_regs(afu);
-
+	cxl_deconfigure_afu(afu);
 	device_unregister(&afu->dev);
 }
 
@@ -851,16 +925,15 @@ int cxl_reset(struct cxl *adapter)
 {
 	struct pci_dev *dev = to_pci_dev(adapter->dev.parent);
 	int rc;
-	int i;
-	u32 val;
+
+	if (adapter->perst_same_image) {
+		dev_warn(&dev->dev,
+			 "cxl: refusing to reset/reflash when perst_reloads_same_image is set.\n");
+		return -EINVAL;
+	}
 
 	dev_info(&dev->dev, "CXL reset\n");
 
-	for (i = 0; i < adapter->slices; i++) {
-		cxl_pci_vphb_remove(adapter->afu[i]);
-		cxl_remove_afu(adapter->afu[i]);
-	}
-
 	/* pcie_warm_reset requests a fundamental pci reset which includes a
 	 * PERST assert/deassert.  PERST triggers a loading of the image
 	 * if "user" or "factory" is selected in sysfs */
@@ -869,20 +942,6 @@ int cxl_reset(struct cxl *adapter)
 		return rc;
 	}
 
-	/* the PERST done above fences the PHB.  So, reset depends on EEH
-	 * to unbind the driver, tell Sapphire to reinit the PHB, and rebind
-	 * the driver.  Do an mmio read explictly to ensure EEH notices the
-	 * fenced PHB.  Retry for a few seconds before giving up. */
-	i = 0;
-	while (((val = mmio_read32be(adapter->p1_mmio)) != 0xffffffff) &&
-		(i < 5)) {
-		msleep(500);
-		i++;
-	}
-
-	if (val != 0xffffffff)
-		dev_err(&dev->dev, "cxl: PERST failed to trigger EEH\n");
-
 	return rc;
 }
 
@@ -893,7 +952,7 @@ static int cxl_map_adapter_regs(struct cxl *adapter, struct pci_dev *dev)
 	if (pci_request_region(dev, 0, "priv 1 regs"))
 		goto err2;
 
-	pr_devel("cxl_map_adapter_regs: p1: %#.16llx %#llx, p2: %#.16llx %#llx",
+	pr_devel("cxl_map_adapter_regs: p1: %#016llx %#llx, p2: %#016llx %#llx",
 			p1_base(dev), p1_size(dev), p2_base(dev), p2_size(dev));
 
 	if (!(adapter->p1_mmio = ioremap(p1_base(dev), p1_size(dev))))
@@ -917,10 +976,16 @@ err1:
 
 static void cxl_unmap_adapter_regs(struct cxl *adapter)
 {
-	if (adapter->p1_mmio)
+	if (adapter->p1_mmio) {
 		iounmap(adapter->p1_mmio);
-	if (adapter->p2_mmio)
+		adapter->p1_mmio = NULL;
+		pci_release_region(to_pci_dev(adapter->dev.parent), 2);
+	}
+	if (adapter->p2_mmio) {
 		iounmap(adapter->p2_mmio);
+		adapter->p2_mmio = NULL;
+		pci_release_region(to_pci_dev(adapter->dev.parent), 0);
+	}
 }
 
 static int cxl_read_vsec(struct cxl *adapter, struct pci_dev *dev)
@@ -949,7 +1014,6 @@ static int cxl_read_vsec(struct cxl *adapter, struct pci_dev *dev)
 	CXL_READ_VSEC_BASE_IMAGE(dev, vsec, &adapter->base_image);
 	CXL_READ_VSEC_IMAGE_STATE(dev, vsec, &image_state);
 	adapter->user_image_loaded = !!(image_state & CXL_VSEC_USER_IMAGE_LOADED);
-	adapter->perst_loads_image = true;
 	adapter->perst_select_user = !!(image_state & CXL_VSEC_USER_IMAGE_LOADED);
 
 	CXL_READ_VSEC_NAFUS(dev, vsec, &adapter->slices);
@@ -1009,82 +1073,139 @@ static void cxl_release_adapter(struct device *dev)
 
 	pr_devel("cxl_release_adapter\n");
 
+	cxl_remove_adapter_nr(adapter);
+
 	kfree(adapter);
 }
 
-static struct cxl *cxl_alloc_adapter(struct pci_dev *dev)
+static struct cxl *cxl_alloc_adapter(void)
 {
 	struct cxl *adapter;
 
 	if (!(adapter = kzalloc(sizeof(struct cxl), GFP_KERNEL)))
 		return NULL;
 
-	adapter->dev.parent = &dev->dev;
-	adapter->dev.release = cxl_release_adapter;
-	pci_set_drvdata(dev, adapter);
 	spin_lock_init(&adapter->afu_list_lock);
 
+	if (cxl_alloc_adapter_nr(adapter))
+		goto err1;
+
+	if (dev_set_name(&adapter->dev, "card%i", adapter->adapter_num))
+		goto err2;
+
 	return adapter;
+
+err2:
+	cxl_remove_adapter_nr(adapter);
+err1:
+	kfree(adapter);
+	return NULL;
 }
 
+#define CXL_PSL_ErrIVTE_tberror (0x1ull << (63-31))
+
 static int sanitise_adapter_regs(struct cxl *adapter)
 {
-	cxl_p1_write(adapter, CXL_PSL_ErrIVTE, 0x0000000000000000);
+	/* Clear PSL tberror bit by writing 1 to it */
+	cxl_p1_write(adapter, CXL_PSL_ErrIVTE, CXL_PSL_ErrIVTE_tberror);
 	return cxl_tlb_slb_invalidate(adapter);
 }
 
+/* This should contain *only* operations that can safely be done in
+ * both creation and recovery.
+ */
+static int cxl_configure_adapter(struct cxl *adapter, struct pci_dev *dev)
+{
+	int rc;
+
+	adapter->dev.parent = &dev->dev;
+	adapter->dev.release = cxl_release_adapter;
+	pci_set_drvdata(dev, adapter);
+
+	rc = pci_enable_device(dev);
+	if (rc) {
+		dev_err(&dev->dev, "pci_enable_device failed: %i\n", rc);
+		return rc;
+	}
+
+	if ((rc = cxl_read_vsec(adapter, dev)))
+		return rc;
+
+	if ((rc = cxl_vsec_looks_ok(adapter, dev)))
+	        return rc;
+
+	if ((rc = setup_cxl_bars(dev)))
+		return rc;
+
+	if ((rc = switch_card_to_cxl(dev)))
+		return rc;
+
+	if ((rc = cxl_update_image_control(adapter)))
+		return rc;
+
+	if ((rc = cxl_map_adapter_regs(adapter, dev)))
+		return rc;
+
+	if ((rc = sanitise_adapter_regs(adapter)))
+		goto err;
+
+	if ((rc = init_implementation_adapter_regs(adapter, dev)))
+		goto err;
+
+	if ((rc = pnv_phb_to_cxl_mode(dev, OPAL_PHB_CAPI_MODE_CAPI)))
+		goto err;
+
+	/* If recovery happened, the last step is to turn on snooping.
+	 * In the non-recovery case this has no effect */
+	if ((rc = pnv_phb_to_cxl_mode(dev, OPAL_PHB_CAPI_MODE_SNOOP_ON)))
+		goto err;
+
+	if ((rc = cxl_setup_psl_timebase(adapter, dev)))
+		goto err;
+
+	if ((rc = cxl_register_psl_err_irq(adapter)))
+		goto err;
+
+	return 0;
+
+err:
+	cxl_unmap_adapter_regs(adapter);
+	return rc;
+
+}
+
+static void cxl_deconfigure_adapter(struct cxl *adapter)
+{
+	struct pci_dev *pdev = to_pci_dev(adapter->dev.parent);
+
+	cxl_release_psl_err_irq(adapter);
+	cxl_unmap_adapter_regs(adapter);
+
+	pci_disable_device(pdev);
+}
+
 static struct cxl *cxl_init_adapter(struct pci_dev *dev)
 {
 	struct cxl *adapter;
-	bool free = true;
 	int rc;
 
-
-	if (!(adapter = cxl_alloc_adapter(dev)))
+	adapter = cxl_alloc_adapter();
+	if (!adapter)
 		return ERR_PTR(-ENOMEM);
 
-	if ((rc = cxl_read_vsec(adapter, dev)))
-		goto err1;
+	/* Set defaults for parameters which need to persist over
+	 * configure/reconfigure
+	 */
+	adapter->perst_loads_image = true;
+	adapter->perst_same_image = false;
 
-	if ((rc = cxl_vsec_looks_ok(adapter, dev)))
-		goto err1;
-
-	if ((rc = setup_cxl_bars(dev)))
-		goto err1;
-
-	if ((rc = switch_card_to_cxl(dev)))
-		goto err1;
-
-	if ((rc = cxl_alloc_adapter_nr(adapter)))
-		goto err1;
-
-	if ((rc = dev_set_name(&adapter->dev, "card%i", adapter->adapter_num)))
-		goto err2;
-
-	if ((rc = cxl_update_image_control(adapter)))
-		goto err2;
-
-	if ((rc = cxl_map_adapter_regs(adapter, dev)))
-		goto err2;
-
-	if ((rc = sanitise_adapter_regs(adapter)))
-		goto err2;
-
-	if ((rc = init_implementation_adapter_regs(adapter, dev)))
-		goto err3;
-
-	if ((rc = pnv_phb_to_cxl_mode(dev, OPAL_PHB_CAPI_MODE_CAPI)))
-		goto err3;
-
-	/* If recovery happened, the last step is to turn on snooping.
-	 * In the non-recovery case this has no effect */
-	if ((rc = pnv_phb_to_cxl_mode(dev, OPAL_PHB_CAPI_MODE_SNOOP_ON))) {
-		goto err3;
+	rc = cxl_configure_adapter(adapter, dev);
+	if (rc) {
+		pci_disable_device(dev);
+		cxl_release_adapter(&adapter->dev);
+		return ERR_PTR(rc);
 	}
 
-	if ((rc = cxl_register_psl_err_irq(adapter)))
-		goto err3;
-
 	/* Don't care if this one fails: */
 	cxl_debugfs_adapter_add(adapter);
 
@@ -1101,37 +1222,25 @@ static struct cxl *cxl_init_adapter(struct pci_dev *dev)
 	return adapter;
 
 err_put1:
-	device_unregister(&adapter->dev);
-	free = false;
+	/* This should mirror cxl_remove_adapter, except without the
+	 * sysfs parts
+	 */
 	cxl_debugfs_adapter_remove(adapter);
-	cxl_release_psl_err_irq(adapter);
-err3:
-	cxl_unmap_adapter_regs(adapter);
-err2:
-	cxl_remove_adapter_nr(adapter);
-err1:
-	if (free)
-		kfree(adapter);
+	cxl_deconfigure_adapter(adapter);
+	device_unregister(&adapter->dev);
 	return ERR_PTR(rc);
 }
 
 static void cxl_remove_adapter(struct cxl *adapter)
 {
-	struct pci_dev *pdev = to_pci_dev(adapter->dev.parent);
-
-	pr_devel("cxl_release_adapter\n");
+	pr_devel("cxl_remove_adapter\n");
 
 	cxl_sysfs_adapter_remove(adapter);
 	cxl_debugfs_adapter_remove(adapter);
-	cxl_release_psl_err_irq(adapter);
-	cxl_unmap_adapter_regs(adapter);
-	cxl_remove_adapter_nr(adapter);
+
+	cxl_deconfigure_adapter(adapter);
 
 	device_unregister(&adapter->dev);
-
-	pci_release_region(pdev, 0);
-	pci_release_region(pdev, 2);
-	pci_disable_device(pdev);
 }
 
 static int cxl_probe(struct pci_dev *dev, const struct pci_device_id *id)
@@ -1145,21 +1254,21 @@ static int cxl_probe(struct pci_dev *dev, const struct pci_device_id *id)
 	if (cxl_verbose)
 		dump_cxl_config_space(dev);
 
-	if ((rc = pci_enable_device(dev))) {
-		dev_err(&dev->dev, "pci_enable_device failed: %i\n", rc);
-		return rc;
-	}
-
 	adapter = cxl_init_adapter(dev);
 	if (IS_ERR(adapter)) {
 		dev_err(&dev->dev, "cxl_init_adapter failed: %li\n", PTR_ERR(adapter));
-		pci_disable_device(dev);
 		return PTR_ERR(adapter);
 	}
 
 	for (slice = 0; slice < adapter->slices; slice++) {
-		if ((rc = cxl_init_afu(adapter, slice, dev)))
+		if ((rc = cxl_init_afu(adapter, slice, dev))) {
 			dev_err(&dev->dev, "AFU %i failed to initialise: %i\n", slice, rc);
+			continue;
+		}
+
+		rc = cxl_afu_select_best_mode(adapter->afu[slice]);
+		if (rc)
+			dev_err(&dev->dev, "AFU %i failed to start: %i\n", slice, rc);
 	}
 
 	return 0;
@@ -1183,10 +1292,262 @@ static void cxl_remove(struct pci_dev *dev)
 	cxl_remove_adapter(adapter);
 }
 
+static pci_ers_result_t cxl_vphb_error_detected(struct cxl_afu *afu,
+						pci_channel_state_t state)
+{
+	struct pci_dev *afu_dev;
+	pci_ers_result_t result = PCI_ERS_RESULT_NEED_RESET;
+	pci_ers_result_t afu_result = PCI_ERS_RESULT_NEED_RESET;
+
+	/* There should only be one entry, but go through the list
+	 * anyway
+	 */
+	list_for_each_entry(afu_dev, &afu->phb->bus->devices, bus_list) {
+		if (!afu_dev->driver)
+			continue;
+
+		afu_dev->error_state = state;
+
+		if (afu_dev->driver->err_handler)
+			afu_result = afu_dev->driver->err_handler->error_detected(afu_dev,
+										  state);
+		/* Disconnect trumps all, NONE trumps NEED_RESET */
+		if (afu_result == PCI_ERS_RESULT_DISCONNECT)
+			result = PCI_ERS_RESULT_DISCONNECT;
+		else if ((afu_result == PCI_ERS_RESULT_NONE) &&
+			 (result == PCI_ERS_RESULT_NEED_RESET))
+			result = PCI_ERS_RESULT_NONE;
+	}
+	return result;
+}
+
+static pci_ers_result_t cxl_pci_error_detected(struct pci_dev *pdev,
+					       pci_channel_state_t state)
+{
+	struct cxl *adapter = pci_get_drvdata(pdev);
+	struct cxl_afu *afu;
+	pci_ers_result_t result = PCI_ERS_RESULT_NEED_RESET;
+	int i;
+
+	/* At this point, we could still have an interrupt pending.
+	 * Let's try to get them out of the way before they do
+	 * anything we don't like.
+	 */
+	schedule();
+
+	/* If we're permanently dead, give up. */
+	if (state == pci_channel_io_perm_failure) {
+		/* Tell the AFU drivers; but we don't care what they
+		 * say, we're going away.
+		 */
+		for (i = 0; i < adapter->slices; i++) {
+			afu = adapter->afu[i];
+			cxl_vphb_error_detected(afu, state);
+		}
+		return PCI_ERS_RESULT_DISCONNECT;
+	}
+
+	/* Are we reflashing?
+	 *
+	 * If we reflash, we could come back as something entirely
+	 * different, including a non-CAPI card. As such, by default
+	 * we don't participate in the process. We'll be unbound and
+	 * the slot re-probed. (TODO: check EEH doesn't blindly rebind
+	 * us!)
+	 *
+	 * However, this isn't the entire story: for reliablity
+	 * reasons, we usually want to reflash the FPGA on PERST in
+	 * order to get back to a more reliable known-good state.
+	 *
+	 * This causes us a bit of a problem: if we reflash we can't
+	 * trust that we'll come back the same - we could have a new
+	 * image and been PERSTed in order to load that
+	 * image. However, most of the time we actually *will* come
+	 * back the same - for example a regular EEH event.
+	 *
+	 * Therefore, we allow the user to assert that the image is
+	 * indeed the same and that we should continue on into EEH
+	 * anyway.
+	 */
+	if (adapter->perst_loads_image && !adapter->perst_same_image) {
+		/* TODO take the PHB out of CXL mode */
+		dev_info(&pdev->dev, "reflashing, so opting out of EEH!\n");
+		return PCI_ERS_RESULT_NONE;
+	}
+
+	/*
+	 * At this point, we want to try to recover.  We'll always
+	 * need a complete slot reset: we don't trust any other reset.
+	 *
+	 * Now, we go through each AFU:
+	 *  - We send the driver, if bound, an error_detected callback.
+	 *    We expect it to clean up, but it can also tell us to give
+	 *    up and permanently detach the card. To simplify things, if
+	 *    any bound AFU driver doesn't support EEH, we give up on EEH.
+	 *
+	 *  - We detach all contexts associated with the AFU. This
+	 *    does not free them, but puts them into a CLOSED state
+	 *    which causes any the associated files to return useful
+	 *    errors to userland. It also unmaps, but does not free,
+	 *    any IRQs.
+	 *
+	 *  - We clean up our side: releasing and unmapping resources we hold
+	 *    so we can wire them up again when the hardware comes back up.
+	 *
+	 * Driver authors should note:
+	 *
+	 *  - Any contexts you create in your kernel driver (except
+	 *    those associated with anonymous file descriptors) are
+	 *    your responsibility to free and recreate. Likewise with
+	 *    any attached resources.
+	 *
+	 *  - We will take responsibility for re-initialising the
+	 *    device context (the one set up for you in
+	 *    cxl_pci_enable_device_hook and accessed through
+	 *    cxl_get_context). If you've attached IRQs or other
+	 *    resources to it, they remains yours to free.
+	 *
+	 * You can call the same functions to release resources as you
+	 * normally would: we make sure that these functions continue
+	 * to work when the hardware is down.
+	 *
+	 * Two examples:
+	 *
+	 * 1) If you normally free all your resources at the end of
+	 *    each request, or if you use anonymous FDs, your
+	 *    error_detected callback can simply set a flag to tell
+	 *    your driver not to start any new calls. You can then
+	 *    clear the flag in the resume callback.
+	 *
+	 * 2) If you normally allocate your resources on startup:
+	 *     * Set a flag in error_detected as above.
+	 *     * Let CXL detach your contexts.
+	 *     * In slot_reset, free the old resources and allocate new ones.
+	 *     * In resume, clear the flag to allow things to start.
+	 */
+	for (i = 0; i < adapter->slices; i++) {
+		afu = adapter->afu[i];
+
+		result = cxl_vphb_error_detected(afu, state);
+
+		/* Only continue if everyone agrees on NEED_RESET */
+		if (result != PCI_ERS_RESULT_NEED_RESET)
+			return result;
+
+		cxl_context_detach_all(afu);
+		cxl_afu_deactivate_mode(afu);
+		cxl_deconfigure_afu(afu);
+	}
+	cxl_deconfigure_adapter(adapter);
+
+	return result;
+}
+
+static pci_ers_result_t cxl_pci_slot_reset(struct pci_dev *pdev)
+{
+	struct cxl *adapter = pci_get_drvdata(pdev);
+	struct cxl_afu *afu;
+	struct cxl_context *ctx;
+	struct pci_dev *afu_dev;
+	pci_ers_result_t afu_result = PCI_ERS_RESULT_RECOVERED;
+	pci_ers_result_t result = PCI_ERS_RESULT_RECOVERED;
+	int i;
+
+	if (cxl_configure_adapter(adapter, pdev))
+		goto err;
+
+	for (i = 0; i < adapter->slices; i++) {
+		afu = adapter->afu[i];
+
+		if (cxl_configure_afu(afu, adapter, pdev))
+			goto err;
+
+		if (cxl_afu_select_best_mode(afu))
+			goto err;
+
+		cxl_pci_vphb_reconfigure(afu);
+
+		list_for_each_entry(afu_dev, &afu->phb->bus->devices, bus_list) {
+			/* Reset the device context.
+			 * TODO: make this less disruptive
+			 */
+			ctx = cxl_get_context(afu_dev);
+
+			if (ctx && cxl_release_context(ctx))
+				goto err;
+
+			ctx = cxl_dev_context_init(afu_dev);
+			if (!ctx)
+				goto err;
+
+			afu_dev->dev.archdata.cxl_ctx = ctx;
+
+			if (cxl_afu_check_and_enable(afu))
+				goto err;
+
+			afu_dev->error_state = pci_channel_io_normal;
+
+			/* If there's a driver attached, allow it to
+			 * chime in on recovery. Drivers should check
+			 * if everything has come back OK, but
+			 * shouldn't start new work until we call
+			 * their resume function.
+			 */
+			if (!afu_dev->driver)
+				continue;
+
+			if (afu_dev->driver->err_handler &&
+			    afu_dev->driver->err_handler->slot_reset)
+				afu_result = afu_dev->driver->err_handler->slot_reset(afu_dev);
+
+			if (afu_result == PCI_ERS_RESULT_DISCONNECT)
+				result = PCI_ERS_RESULT_DISCONNECT;
+		}
+	}
+	return result;
+
+err:
+	/* All the bits that happen in both error_detected and cxl_remove
+	 * should be idempotent, so we don't need to worry about leaving a mix
+	 * of unconfigured and reconfigured resources.
+	 */
+	dev_err(&pdev->dev, "EEH recovery failed. Asking to be disconnected.\n");
+	return PCI_ERS_RESULT_DISCONNECT;
+}
+
+static void cxl_pci_resume(struct pci_dev *pdev)
+{
+	struct cxl *adapter = pci_get_drvdata(pdev);
+	struct cxl_afu *afu;
+	struct pci_dev *afu_dev;
+	int i;
+
+	/* Everything is back now. Drivers should restart work now.
+	 * This is not the place to be checking if everything came back up
+	 * properly, because there's no return value: do that in slot_reset.
+	 */
+	for (i = 0; i < adapter->slices; i++) {
+		afu = adapter->afu[i];
+
+		list_for_each_entry(afu_dev, &afu->phb->bus->devices, bus_list) {
+			if (afu_dev->driver && afu_dev->driver->err_handler &&
+			    afu_dev->driver->err_handler->resume)
+				afu_dev->driver->err_handler->resume(afu_dev);
+		}
+	}
+}
+
+static const struct pci_error_handlers cxl_err_handler = {
+	.error_detected = cxl_pci_error_detected,
+	.slot_reset = cxl_pci_slot_reset,
+	.resume = cxl_pci_resume,
+};
+
 struct pci_driver cxl_pci_driver = {
 	.name = "cxl-pci",
 	.id_table = cxl_pci_tbl,
 	.probe = cxl_probe,
 	.remove = cxl_remove,
 	.shutdown = cxl_remove,
+	.err_handler = &cxl_err_handler,
 };

drivers/misc/cxl/sysfs.c

@@ -112,12 +112,38 @@ static ssize_t load_image_on_perst_store(struct device *device,
 	return count;
 }
 
+static ssize_t perst_reloads_same_image_show(struct device *device,
+				 struct device_attribute *attr,
+				 char *buf)
+{
+	struct cxl *adapter = to_cxl_adapter(device);
+
+	return scnprintf(buf, PAGE_SIZE, "%i\n", adapter->perst_same_image);
+}
+
+static ssize_t perst_reloads_same_image_store(struct device *device,
+				 struct device_attribute *attr,
+				 const char *buf, size_t count)
+{
+	struct cxl *adapter = to_cxl_adapter(device);
+	int rc;
+	int val;
+
+	rc = sscanf(buf, "%i", &val);
+	if ((rc != 1) || !(val == 1 || val == 0))
+		return -EINVAL;
+
+	adapter->perst_same_image = (val == 1 ? true : false);
+	return count;
+}
+
 static struct device_attribute adapter_attrs[] = {
 	__ATTR_RO(caia_version),
 	__ATTR_RO(psl_revision),
 	__ATTR_RO(base_image),
 	__ATTR_RO(image_loaded),
 	__ATTR_RW(load_image_on_perst),
+	__ATTR_RW(perst_reloads_same_image),
 	__ATTR(reset, S_IWUSR, NULL, reset_adapter_store),
 };
 

drivers/misc/cxl/trace.h

@@ -105,7 +105,7 @@ TRACE_EVENT(cxl_attach,
 		__entry->num_interrupts = num_interrupts;
 	),
 
-	TP_printk("afu%i.%i pid=%i pe=%i wed=0x%.16llx irqs=%i amr=0x%llx",
+	TP_printk("afu%i.%i pid=%i pe=%i wed=0x%016llx irqs=%i amr=0x%llx",
 		__entry->card,
 		__entry->afu,
 		__entry->pid,
@@ -177,7 +177,7 @@ TRACE_EVENT(cxl_psl_irq,
 		__entry->dar = dar;
 	),
 
-	TP_printk("afu%i.%i pe=%i irq=%i dsisr=%s dar=0x%.16llx",
+	TP_printk("afu%i.%i pe=%i irq=%i dsisr=%s dar=0x%016llx",
 		__entry->card,
 		__entry->afu,
 		__entry->pe,
@@ -233,7 +233,7 @@ TRACE_EVENT(cxl_ste_miss,
 		__entry->dar = dar;
 	),
 
-	TP_printk("afu%i.%i pe=%i dar=0x%.16llx",
+	TP_printk("afu%i.%i pe=%i dar=0x%016llx",
 		__entry->card,
 		__entry->afu,
 		__entry->pe,
@@ -264,7 +264,7 @@ TRACE_EVENT(cxl_ste_write,
 		__entry->v = v;
 	),
 
-	TP_printk("afu%i.%i pe=%i SSTE[%i] E=0x%.16llx V=0x%.16llx",
+	TP_printk("afu%i.%i pe=%i SSTE[%i] E=0x%016llx V=0x%016llx",
 		__entry->card,
 		__entry->afu,
 		__entry->pe,
@@ -295,7 +295,7 @@ TRACE_EVENT(cxl_pte_miss,
 		__entry->dar = dar;
 	),
 
-	TP_printk("afu%i.%i pe=%i dsisr=%s dar=0x%.16llx",
+	TP_printk("afu%i.%i pe=%i dsisr=%s dar=0x%016llx",
 		__entry->card,
 		__entry->afu,
 		__entry->pe,

drivers/misc/cxl/vphb.c

@@ -138,6 +138,26 @@ static int cxl_pcie_config_info(struct pci_bus *bus, unsigned int devfn,
 	return 0;
 }
 
+
+static inline bool cxl_config_link_ok(struct pci_bus *bus)
+{
+	struct pci_controller *phb;
+	struct cxl_afu *afu;
+
+	/* Config space IO is based on phb->cfg_addr, which is based on
+	 * afu_desc_mmio. This isn't safe to read/write when the link
+	 * goes down, as EEH tears down MMIO space.
+	 *
+	 * Check if the link is OK before proceeding.
+	 */
+
+	phb = pci_bus_to_host(bus);
+	if (phb == NULL)
+		return false;
+	afu = (struct cxl_afu *)phb->private_data;
+	return cxl_adapter_link_ok(afu->adapter);
+}
+
 static int cxl_pcie_read_config(struct pci_bus *bus, unsigned int devfn,
 				int offset, int len, u32 *val)
 {
@@ -150,6 +170,9 @@ static int cxl_pcie_read_config(struct pci_bus *bus, unsigned int devfn,
 	if (rc)
 		return rc;
 
+	if (!cxl_config_link_ok(bus))
+		return PCIBIOS_DEVICE_NOT_FOUND;
+
 	/* Can only read 32 bits */
 	*val = (in_le32(ioaddr) >> shift) & mask;
 	return PCIBIOS_SUCCESSFUL;
@@ -167,6 +190,9 @@ static int cxl_pcie_write_config(struct pci_bus *bus, unsigned int devfn,
 	if (rc)
 		return rc;
 
+	if (!cxl_config_link_ok(bus))
+		return PCIBIOS_DEVICE_NOT_FOUND;
+
 	/* Can only write 32 bits so do read-modify-write */
 	mask <<= shift;
 	val <<= shift;
@@ -240,6 +266,14 @@ int cxl_pci_vphb_add(struct cxl_afu *afu)
 	return 0;
 }
 
+void cxl_pci_vphb_reconfigure(struct cxl_afu *afu)
+{
+	/* When we are reconfigured, the AFU's MMIO space is unmapped
+	 * and remapped. We need to reflect this in the PHB's view of
+	 * the world.
+	 */
+	afu->phb->cfg_addr = afu->afu_desc_mmio + afu->crs_offset;
+}
 
 void cxl_pci_vphb_remove(struct cxl_afu *afu)
 {