Merge tag 'powerpc-4.15-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux

Pull powerpc updates from Michael Ellerman:
 "A bit of a small release, I suspect in part due to me travelling for
  KS. But my backlog of patches to review is smaller than usual, so I
  think in part folks just didn't send as much this cycle.

  Non-highlights:

   - Five fixes for the >128T address space handling, both to fix bugs
     in our implementation and to bring the semantics exactly into line
     with x86.

  Highlights:

   - Support for a new OPAL call on bare metal machines which gives us a
     true NMI (ie. is not masked by MSR[EE]=0) for debugging etc.

   - Support for Power9 DD2 in the CXL driver.

   - Improvements to machine check handling so that uncorrectable errors
     can be reported into the generic memory_failure() machinery.

   - Some fixes and improvements for VPHN, which is used under PowerVM
     to notify the Linux partition of topology changes.

   - Plumbing to enable TM (transactional memory) without suspend on
     some Power9 processors (PPC_FEATURE2_HTM_NO_SUSPEND).

   - Support for emulating vector loads form cache-inhibited memory, on
     some Power9 revisions.

   - Disable the fast-endian switch "syscall" by default (behind a
     CONFIG), we believe it has never had any users.

   - A major rework of the API drivers use when initiating and waiting
     for long running operations performed by OPAL firmware, and changes
     to the powernv_flash driver to use the new API.

   - Several fixes for the handling of FP/VMX/VSX while processes are
     using transactional memory.

   - Optimisations of TLB range flushes when using the radix MMU on
     Power9.

   - Improvements to the VAS facility used to access coprocessors on
     Power9, and related improvements to the way the NX crypto driver
     handles requests.

   - Implementation of PMEM_API and UACCESS_FLUSHCACHE for 64-bit.

  Thanks to: Alexey Kardashevskiy, Alistair Popple, Allen Pais, Andrew
  Donnellan, Aneesh Kumar K.V, Arnd Bergmann, Balbir Singh, Benjamin
  Herrenschmidt, Breno Leitao, Christophe Leroy, Christophe Lombard,
  Cyril Bur, Frederic Barrat, Gautham R. Shenoy, Geert Uytterhoeven,
  Guilherme G. Piccoli, Gustavo Romero, Haren Myneni, Joel Stanley,
  Kamalesh Babulal, Kautuk Consul, Markus Elfring, Masami Hiramatsu,
  Michael Bringmann, Michael Neuling, Michal Suchanek, Naveen N. Rao,
  Nicholas Piggin, Oliver O'Halloran, Paul Mackerras, Pedro Miraglia
  Franco de Carvalho, Philippe Bergheaud, Sandipan Das, Seth Forshee,
  Shriya, Stephen Rothwell, Stewart Smith, Sukadev Bhattiprolu, Tyrel
  Datwyler, Vaibhav Jain, Vaidyanathan Srinivasan, and William A.
  Kennington III"

* tag 'powerpc-4.15-1' of git://git.kernel.org/pub/scm/linux/kernel/git/powerpc/linux: (151 commits)
  powerpc/64s: Fix Power9 DD2.0 workarounds by adding DD2.1 feature
  powerpc/64s: Fix masking of SRR1 bits on instruction fault
  powerpc/64s: mm_context.addr_limit is only used on hash
  powerpc/64s/radix: Fix 128TB-512TB virtual address boundary case allocation
  powerpc/64s/hash: Allow MAP_FIXED allocations to cross 128TB boundary
  powerpc/64s/hash: Fix fork() with 512TB process address space
  powerpc/64s/hash: Fix 128TB-512TB virtual address boundary case allocation
  powerpc/64s/hash: Fix 512T hint detection to use >= 128T
  powerpc: Fix DABR match on hash based systems
  powerpc/signal: Properly handle return value from uprobe_deny_signal()
  powerpc/fadump: use kstrtoint to handle sysfs store
  powerpc/lib: Implement UACCESS_FLUSHCACHE API
  powerpc/lib: Implement PMEM API
  powerpc/powernv/npu: Don't explicitly flush nmmu tlb
  powerpc/powernv/npu: Use flush_all_mm() instead of flush_tlb_mm()
  powerpc/powernv/idle: Round up latency and residency values
  powerpc/kprobes: refactor kprobe_lookup_name for safer string operations
  powerpc/kprobes: Blacklist emulate_update_regs() from kprobes
  powerpc/kprobes: Do not disable interrupts for optprobes and kprobes_on_ftrace
  powerpc/kprobes: Disable preemption before invoking probe handler for optprobes
  ...

8 files changed, 141 insertions, 83 deletions

diff --git a/drivers/misc/cxl/api.c b/drivers/misc/cxl/api.c
index a0c44d16bf30..7c11bad5cded 100644
--- a/drivers/misc/cxl/api.c
+++ b/drivers/misc/cxl/api.c
@@ -15,6 +15,7 @@
 #include <linux/module.h>
 #include <linux/mount.h>
 #include <linux/sched/mm.h>
+#include <linux/mmu_context.h>
 
 #include "cxl.h"
 
@@ -331,9 +332,12 @@ int cxl_start_context(struct cxl_context *ctx, u64 wed,
 		/* ensure this mm_struct can't be freed */
 		cxl_context_mm_count_get(ctx);
 
-		/* decrement the use count */
-		if (ctx->mm)
+		if (ctx->mm) {
+			/* decrement the use count from above */
 			mmput(ctx->mm);
+			/* make TLBIs for this context global */
+			mm_context_add_copro(ctx->mm);
+		}
 	}
 
 	/*
@@ -342,13 +346,19 @@ int cxl_start_context(struct cxl_context *ctx, u64 wed,
 	 */
 	cxl_ctx_get();
 
+	/* See the comment in afu_ioctl_start_work() */
+	smp_mb();
+
 	if ((rc = cxl_ops->attach_process(ctx, kernel, wed, 0))) {
 		put_pid(ctx->pid);
 		ctx->pid = NULL;
 		cxl_adapter_context_put(ctx->afu->adapter);
 		cxl_ctx_put();
-		if (task)
+		if (task) {
 			cxl_context_mm_count_put(ctx);
+			if (ctx->mm)
+				mm_context_remove_copro(ctx->mm);
+		}
 		goto out;
 	}
 
diff --git a/drivers/misc/cxl/context.c b/drivers/misc/cxl/context.c
index 8c32040b9c09..12a41b2753f0 100644
--- a/drivers/misc/cxl/context.c
+++ b/drivers/misc/cxl/context.c
@@ -18,6 +18,7 @@
 #include <linux/slab.h>
 #include <linux/idr.h>
 #include <linux/sched/mm.h>
+#include <linux/mmu_context.h>
 #include <asm/cputable.h>
 #include <asm/current.h>
 #include <asm/copro.h>
@@ -267,6 +268,8 @@ int __detach_context(struct cxl_context *ctx)
 
 	/* Decrease the mm count on the context */
 	cxl_context_mm_count_put(ctx);
+	if (ctx->mm)
+		mm_context_remove_copro(ctx->mm);
 	ctx->mm = NULL;
 
 	return 0;
diff --git a/drivers/misc/cxl/cxl.h b/drivers/misc/cxl/cxl.h
index b1afeccbb97f..e46a4062904a 100644
--- a/drivers/misc/cxl/cxl.h
+++ b/drivers/misc/cxl/cxl.h
@@ -100,9 +100,12 @@ static const cxl_p1_reg_t CXL_XSL_FEC       = {0x0158};
 static const cxl_p1_reg_t CXL_XSL_DSNCTL    = {0x0168};
 /* PSL registers - CAIA 2 */
 static const cxl_p1_reg_t CXL_PSL9_CONTROL  = {0x0020};
+static const cxl_p1_reg_t CXL_XSL9_INV      = {0x0110};
+static const cxl_p1_reg_t CXL_XSL9_DBG      = {0x0130};
+static const cxl_p1_reg_t CXL_XSL9_DEF      = {0x0140};
 static const cxl_p1_reg_t CXL_XSL9_DSNCTL   = {0x0168};
 static const cxl_p1_reg_t CXL_PSL9_FIR1     = {0x0300};
-static const cxl_p1_reg_t CXL_PSL9_FIR2     = {0x0308};
+static const cxl_p1_reg_t CXL_PSL9_FIR_MASK = {0x0308};
 static const cxl_p1_reg_t CXL_PSL9_Timebase = {0x0310};
 static const cxl_p1_reg_t CXL_PSL9_DEBUG    = {0x0320};
 static const cxl_p1_reg_t CXL_PSL9_FIR_CNTL = {0x0348};
@@ -112,6 +115,7 @@ static const cxl_p1_reg_t CXL_PSL9_TRACECFG = {0x0368};
 static const cxl_p1_reg_t CXL_PSL9_APCDEDALLOC = {0x0378};
 static const cxl_p1_reg_t CXL_PSL9_APCDEDTYPE = {0x0380};
 static const cxl_p1_reg_t CXL_PSL9_TNR_ADDR = {0x0388};
+static const cxl_p1_reg_t CXL_PSL9_CTCCFG = {0x0390};
 static const cxl_p1_reg_t CXL_PSL9_GP_CT = {0x0398};
 static const cxl_p1_reg_t CXL_XSL9_IERAT = {0x0588};
 static const cxl_p1_reg_t CXL_XSL9_ILPP  = {0x0590};
@@ -414,6 +418,9 @@ static const cxl_p2n_reg_t CXL_PSL_WED_An     = {0x0A0};
 #define CXL_CARD_MINOR(adapter) (adapter->adapter_num * CXL_DEV_MINORS)
 #define CXL_DEVT_ADAPTER(dev) (MINOR(dev) / CXL_DEV_MINORS)
 
+#define CXL_PSL9_TRACEID_MAX 0xAU
+#define CXL_PSL9_TRACESTATE_FIN 0x3U
+
 enum cxl_context_status {
 	CLOSED,
 	OPENED,
@@ -938,8 +945,6 @@ int cxl_debugfs_adapter_add(struct cxl *adapter);
 void cxl_debugfs_adapter_remove(struct cxl *adapter);
 int cxl_debugfs_afu_add(struct cxl_afu *afu);
 void cxl_debugfs_afu_remove(struct cxl_afu *afu);
-void cxl_stop_trace_psl9(struct cxl *cxl);
-void cxl_stop_trace_psl8(struct cxl *cxl);
 void cxl_debugfs_add_adapter_regs_psl9(struct cxl *adapter, struct dentry *dir);
 void cxl_debugfs_add_adapter_regs_psl8(struct cxl *adapter, struct dentry *dir);
 void cxl_debugfs_add_adapter_regs_xsl(struct cxl *adapter, struct dentry *dir);
@@ -975,14 +980,6 @@ static inline void cxl_debugfs_afu_remove(struct cxl_afu *afu)
 {
 }
 
-static inline void cxl_stop_trace_psl9(struct cxl *cxl)
-{
-}
-
-static inline void cxl_stop_trace_psl8(struct cxl *cxl)
-{
-}
-
 static inline void cxl_debugfs_add_adapter_regs_psl9(struct cxl *adapter,
 						    struct dentry *dir)
 {
@@ -1070,7 +1067,8 @@ u64 cxl_calculate_sr(bool master, bool kernel, bool real_mode, bool p9);
 
 void cxl_native_irq_dump_regs_psl9(struct cxl_context *ctx);
 void cxl_native_irq_dump_regs_psl8(struct cxl_context *ctx);
-void cxl_native_err_irq_dump_regs(struct cxl *adapter);
+void cxl_native_err_irq_dump_regs_psl8(struct cxl *adapter);
+void cxl_native_err_irq_dump_regs_psl9(struct cxl *adapter);
 int cxl_pci_vphb_add(struct cxl_afu *afu);
 void cxl_pci_vphb_remove(struct cxl_afu *afu);
 void cxl_release_mapping(struct cxl_context *ctx);
diff --git a/drivers/misc/cxl/debugfs.c b/drivers/misc/cxl/debugfs.c
index eae9d749f967..1643850d2302 100644
--- a/drivers/misc/cxl/debugfs.c
+++ b/drivers/misc/cxl/debugfs.c
@@ -15,28 +15,6 @@
 
 static struct dentry *cxl_debugfs;
 
-void cxl_stop_trace_psl9(struct cxl *adapter)
-{
-	/* Stop the trace */
-	cxl_p1_write(adapter, CXL_PSL9_TRACECFG, 0x4480000000000000ULL);
-}
-
-void cxl_stop_trace_psl8(struct cxl *adapter)
-{
-	int slice;
-
-	/* Stop the trace */
-	cxl_p1_write(adapter, CXL_PSL_TRACE, 0x8000000000000017LL);
-
-	/* Stop the slice traces */
-	spin_lock(&adapter->afu_list_lock);
-	for (slice = 0; slice < adapter->slices; slice++) {
-		if (adapter->afu[slice])
-			cxl_p1n_write(adapter->afu[slice], CXL_PSL_SLICE_TRACE, 0x8000000000000000LL);
-	}
-	spin_unlock(&adapter->afu_list_lock);
-}
-
 /* Helpers to export CXL mmaped IO registers via debugfs */
 static int debugfs_io_u64_get(void *data, u64 *val)
 {
@@ -62,9 +40,14 @@ static struct dentry *debugfs_create_io_x64(const char *name, umode_t mode,
 void cxl_debugfs_add_adapter_regs_psl9(struct cxl *adapter, struct dentry *dir)
 {
 	debugfs_create_io_x64("fir1", S_IRUSR, dir, _cxl_p1_addr(adapter, CXL_PSL9_FIR1));
-	debugfs_create_io_x64("fir2", S_IRUSR, dir, _cxl_p1_addr(adapter, CXL_PSL9_FIR2));
+	debugfs_create_io_x64("fir_mask", 0400, dir,
+			      _cxl_p1_addr(adapter, CXL_PSL9_FIR_MASK));
 	debugfs_create_io_x64("fir_cntl", S_IRUSR, dir, _cxl_p1_addr(adapter, CXL_PSL9_FIR_CNTL));
 	debugfs_create_io_x64("trace", S_IRUSR | S_IWUSR, dir, _cxl_p1_addr(adapter, CXL_PSL9_TRACECFG));
+	debugfs_create_io_x64("debug", 0600, dir,
+			      _cxl_p1_addr(adapter, CXL_PSL9_DEBUG));
+	debugfs_create_io_x64("xsl-debug", 0600, dir,
+			      _cxl_p1_addr(adapter, CXL_XSL9_DBG));
 }
 
 void cxl_debugfs_add_adapter_regs_psl8(struct cxl *adapter, struct dentry *dir)
diff --git a/drivers/misc/cxl/fault.c b/drivers/misc/cxl/fault.c
index f17f72ea0545..70dbb6de102c 100644
--- a/drivers/misc/cxl/fault.c
+++ b/drivers/misc/cxl/fault.c
@@ -220,22 +220,11 @@ static bool cxl_is_segment_miss(struct cxl_context *ctx, u64 dsisr)
 
 static bool cxl_is_page_fault(struct cxl_context *ctx, u64 dsisr)
 {
-	u64 crs; /* Translation Checkout Response Status */
-
 	if ((cxl_is_power8()) && (dsisr & CXL_PSL_DSISR_An_DM))
 		return true;
 
-	if (cxl_is_power9()) {
-		crs = (dsisr & CXL_PSL9_DSISR_An_CO_MASK);
-		if ((crs == CXL_PSL9_DSISR_An_PF_SLR) ||
-		    (crs == CXL_PSL9_DSISR_An_PF_RGC) ||
-		    (crs == CXL_PSL9_DSISR_An_PF_RGP) ||
-		    (crs == CXL_PSL9_DSISR_An_PF_HRH) ||
-		    (crs == CXL_PSL9_DSISR_An_PF_STEG) ||
-		    (crs == CXL_PSL9_DSISR_An_URTCH)) {
-			return true;
-		}
-	}
+	if (cxl_is_power9())
+		return true;
 
 	return false;
 }
diff --git a/drivers/misc/cxl/file.c b/drivers/misc/cxl/file.c
index 4bfad9f6dc9f..76c0b0ca9388 100644
--- a/drivers/misc/cxl/file.c
+++ b/drivers/misc/cxl/file.c
@@ -19,6 +19,7 @@
 #include <linux/mm.h>
 #include <linux/slab.h>
 #include <linux/sched/mm.h>
+#include <linux/mmu_context.h>
 #include <asm/cputable.h>
 #include <asm/current.h>
 #include <asm/copro.h>
@@ -220,9 +221,12 @@ static long afu_ioctl_start_work(struct cxl_context *ctx,
 	/* ensure this mm_struct can't be freed */
 	cxl_context_mm_count_get(ctx);
 
-	/* decrement the use count */
-	if (ctx->mm)
+	if (ctx->mm) {
+		/* decrement the use count from above */
 		mmput(ctx->mm);
+		/* make TLBIs for this context global */
+		mm_context_add_copro(ctx->mm);
+	}
 
 	/*
 	 * Increment driver use count. Enables global TLBIs for hash
@@ -230,6 +234,20 @@ static long afu_ioctl_start_work(struct cxl_context *ctx,
 	 */
 	cxl_ctx_get();
 
+	/*
+	 * A barrier is needed to make sure all TLBIs are global
+	 * before we attach and the context starts being used by the
+	 * adapter.
+	 *
+	 * Needed after mm_context_add_copro() for radix and
+	 * cxl_ctx_get() for hash/p8.
+	 *
+	 * The barrier should really be mb(), since it involves a
+	 * device. However, it's only useful when we have local
+	 * vs. global TLBIs, i.e SMP=y. So keep smp_mb().
+	 */
+	smp_mb();
+
 	trace_cxl_attach(ctx, work.work_element_descriptor, work.num_interrupts, amr);
 
 	if ((rc = cxl_ops->attach_process(ctx, false, work.work_element_descriptor,
@@ -240,6 +258,8 @@ static long afu_ioctl_start_work(struct cxl_context *ctx,
 		ctx->pid = NULL;
 		cxl_ctx_put();
 		cxl_context_mm_count_put(ctx);
+		if (ctx->mm)
+			mm_context_remove_copro(ctx->mm);
 		goto out;
 	}
 
diff --git a/drivers/misc/cxl/native.c b/drivers/misc/cxl/native.c
index 4a82c313cf71..02b6b45b4c20 100644
--- a/drivers/misc/cxl/native.c
+++ b/drivers/misc/cxl/native.c
@@ -897,6 +897,14 @@ int cxl_attach_dedicated_process_psl9(struct cxl_context *ctx, u64 wed, u64 amr)
 	if (ctx->afu->adapter->native->sl_ops->update_dedicated_ivtes)
 		afu->adapter->native->sl_ops->update_dedicated_ivtes(ctx);
 
+	ctx->elem->software_state = cpu_to_be32(CXL_PE_SOFTWARE_STATE_V);
+	/*
+	 * Ideally we should do a wmb() here to make sure the changes to the
+	 * PE are visible to the card before we call afu_enable.
+	 * On ppc64 though all mmios are preceded by a 'sync' instruction hence
+	 * we dont dont need one here.
+	 */
+
 	result = cxl_ops->afu_reset(afu);
 	if (result)
 		return result;
@@ -1077,13 +1085,11 @@ static int native_get_irq_info(struct cxl_afu *afu, struct cxl_irq_info *info)
 
 void cxl_native_irq_dump_regs_psl9(struct cxl_context *ctx)
 {
-	u64 fir1, fir2, serr;
+	u64 fir1, serr;
 
 	fir1 = cxl_p1_read(ctx->afu->adapter, CXL_PSL9_FIR1);
-	fir2 = cxl_p1_read(ctx->afu->adapter, CXL_PSL9_FIR2);
 
 	dev_crit(&ctx->afu->dev, "PSL_FIR1: 0x%016llx\n", fir1);
-	dev_crit(&ctx->afu->dev, "PSL_FIR2: 0x%016llx\n", fir2);
 	if (ctx->afu->adapter->native->sl_ops->register_serr_irq) {
 		serr = cxl_p1n_read(ctx->afu, CXL_PSL_SERR_An);
 		cxl_afu_decode_psl_serr(ctx->afu, serr);
@@ -1257,14 +1263,23 @@ static irqreturn_t native_slice_irq_err(int irq, void *data)
 	return IRQ_HANDLED;
 }
 
-void cxl_native_err_irq_dump_regs(struct cxl *adapter)
+void cxl_native_err_irq_dump_regs_psl9(struct cxl *adapter)
+{
+	u64 fir1;
+
+	fir1 = cxl_p1_read(adapter, CXL_PSL9_FIR1);
+	dev_crit(&adapter->dev, "PSL_FIR: 0x%016llx\n", fir1);
+}
+
+void cxl_native_err_irq_dump_regs_psl8(struct cxl *adapter)
 {
 	u64 fir1, fir2;
 
 	fir1 = cxl_p1_read(adapter, CXL_PSL_FIR1);
 	fir2 = cxl_p1_read(adapter, CXL_PSL_FIR2);
-
-	dev_crit(&adapter->dev, "PSL_FIR1: 0x%016llx\nPSL_FIR2: 0x%016llx\n", fir1, fir2);
+	dev_crit(&adapter->dev,
+		 "PSL_FIR1: 0x%016llx\nPSL_FIR2: 0x%016llx\n",
+		 fir1, fir2);
 }
 
 static irqreturn_t native_irq_err(int irq, void *data)
diff --git a/drivers/misc/cxl/pci.c b/drivers/misc/cxl/pci.c
index 3ba04f371380..bb7fd3f4edab 100644
--- a/drivers/misc/cxl/pci.c
+++ b/drivers/misc/cxl/pci.c
@@ -401,7 +401,8 @@ int cxl_calc_capp_routing(struct pci_dev *dev, u64 *chipid,
 	*capp_unit_id = get_capp_unit_id(np, *phb_index);
 	of_node_put(np);
 	if (!*capp_unit_id) {
-		pr_err("cxl: invalid capp unit id\n");
+		pr_err("cxl: invalid capp unit id (phb_index: %d)\n",
+		       *phb_index);
 		return -ENODEV;
 	}
 
@@ -475,37 +476,37 @@ static int init_implementation_adapter_regs_psl9(struct cxl *adapter,
 	psl_fircntl |= 0x1ULL; /* ce_thresh */
 	cxl_p1_write(adapter, CXL_PSL9_FIR_CNTL, psl_fircntl);
 
-	/* vccredits=0x1  pcklat=0x4 */
-	cxl_p1_write(adapter, CXL_PSL9_DSNDCTL, 0x0000000000001810ULL);
-
-	/*
-	 * For debugging with trace arrays.
-	 * Configure RX trace 0 segmented mode.
-	 * Configure CT trace 0 segmented mode.
-	 * Configure LA0 trace 0 segmented mode.
-	 * Configure LA1 trace 0 segmented mode.
+	/* Setup the PSL to transmit packets on the PCIe before the
+	 * CAPP is enabled
 	 */
-	cxl_p1_write(adapter, CXL_PSL9_TRACECFG, 0x8040800080000000ULL);
-	cxl_p1_write(adapter, CXL_PSL9_TRACECFG, 0x8040800080000003ULL);
-	cxl_p1_write(adapter, CXL_PSL9_TRACECFG, 0x8040800080000005ULL);
-	cxl_p1_write(adapter, CXL_PSL9_TRACECFG, 0x8040800080000006ULL);
+	cxl_p1_write(adapter, CXL_PSL9_DSNDCTL, 0x0001001000002A10ULL);
 
 	/*
 	 * A response to an ASB_Notify request is returned by the
 	 * system as an MMIO write to the address defined in
-	 * the PSL_TNR_ADDR register
+	 * the PSL_TNR_ADDR register.
+	 * keep the Reset Value: 0x00020000E0000000
 	 */
-	/* PSL_TNR_ADDR */
 
-	/* NORST */
-	cxl_p1_write(adapter, CXL_PSL9_DEBUG, 0x8000000000000000ULL);
+	/* Enable XSL rty limit */
+	cxl_p1_write(adapter, CXL_XSL9_DEF, 0x51F8000000000005ULL);
+
+	/* Change XSL_INV dummy read threshold */
+	cxl_p1_write(adapter, CXL_XSL9_INV, 0x0000040007FFC200ULL);
+
+	if (phb_index == 3) {
+		/* disable machines 31-47 and 20-27 for DMA */
+		cxl_p1_write(adapter, CXL_PSL9_APCDEDTYPE, 0x40000FF3FFFF0000ULL);
+	}
 
-	/* allocate the apc machines */
-	cxl_p1_write(adapter, CXL_PSL9_APCDEDTYPE, 0x40000003FFFF0000ULL);
+	/* Snoop machines */
+	cxl_p1_write(adapter, CXL_PSL9_APCDEDALLOC, 0x800F000200000000ULL);
 
-	/* Disable vc dd1 fix */
-	if (cxl_is_power9_dd1())
-		cxl_p1_write(adapter, CXL_PSL9_GP_CT, 0x0400000000000001ULL);
+	if (cxl_is_power9_dd1()) {
+		/* Disabling deadlock counter CAR */
+		cxl_p1_write(adapter, CXL_PSL9_GP_CT, 0x0020000000000001ULL);
+	} else
+		cxl_p1_write(adapter, CXL_PSL9_DEBUG, 0x4000000000000000ULL);
 
 	return 0;
 }
@@ -1746,6 +1747,44 @@ static void cxl_deconfigure_adapter(struct cxl *adapter)
 	pci_disable_device(pdev);
 }
 
+static void cxl_stop_trace_psl9(struct cxl *adapter)
+{
+	int traceid;
+	u64 trace_state, trace_mask;
+	struct pci_dev *dev = to_pci_dev(adapter->dev.parent);
+
+	/* read each tracearray state and issue mmio to stop them is needed */
+	for (traceid = 0; traceid <= CXL_PSL9_TRACEID_MAX; ++traceid) {
+		trace_state = cxl_p1_read(adapter, CXL_PSL9_CTCCFG);
+		trace_mask = (0x3ULL << (62 - traceid * 2));
+		trace_state = (trace_state & trace_mask) >> (62 - traceid * 2);
+		dev_dbg(&dev->dev, "cxl: Traceid-%d trace_state=0x%0llX\n",
+			traceid, trace_state);
+
+		/* issue mmio if the trace array isn't in FIN state */
+		if (trace_state != CXL_PSL9_TRACESTATE_FIN)
+			cxl_p1_write(adapter, CXL_PSL9_TRACECFG,
+				     0x8400000000000000ULL | traceid);
+	}
+}
+
+static void cxl_stop_trace_psl8(struct cxl *adapter)
+{
+	int slice;
+
+	/* Stop the trace */
+	cxl_p1_write(adapter, CXL_PSL_TRACE, 0x8000000000000017LL);
+
+	/* Stop the slice traces */
+	spin_lock(&adapter->afu_list_lock);
+	for (slice = 0; slice < adapter->slices; slice++) {
+		if (adapter->afu[slice])
+			cxl_p1n_write(adapter->afu[slice], CXL_PSL_SLICE_TRACE,
+				      0x8000000000000000LL);
+	}
+	spin_unlock(&adapter->afu_list_lock);
+}
+
 static const struct cxl_service_layer_ops psl9_ops = {
 	.adapter_regs_init = init_implementation_adapter_regs_psl9,
 	.invalidate_all = cxl_invalidate_all_psl9,
@@ -1762,6 +1801,7 @@ static const struct cxl_service_layer_ops psl9_ops = {
 	.debugfs_add_adapter_regs = cxl_debugfs_add_adapter_regs_psl9,
 	.debugfs_add_afu_regs = cxl_debugfs_add_afu_regs_psl9,
 	.psl_irq_dump_registers = cxl_native_irq_dump_regs_psl9,
+	.err_irq_dump_registers = cxl_native_err_irq_dump_regs_psl9,
 	.debugfs_stop_trace = cxl_stop_trace_psl9,
 	.write_timebase_ctrl = write_timebase_ctrl_psl9,
 	.timebase_read = timebase_read_psl9,
@@ -1785,7 +1825,7 @@ static const struct cxl_service_layer_ops psl8_ops = {
 	.debugfs_add_adapter_regs = cxl_debugfs_add_adapter_regs_psl8,
 	.debugfs_add_afu_regs = cxl_debugfs_add_afu_regs_psl8,
 	.psl_irq_dump_registers = cxl_native_irq_dump_regs_psl8,
-	.err_irq_dump_registers = cxl_native_err_irq_dump_regs,
+	.err_irq_dump_registers = cxl_native_err_irq_dump_regs_psl8,
 	.debugfs_stop_trace = cxl_stop_trace_psl8,
 	.write_timebase_ctrl = write_timebase_ctrl_psl8,
 	.timebase_read = timebase_read_psl8,