From de369538436ae0caf784c69187ad0e53152b7ddf Mon Sep 17 00:00:00 2001
From: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Date: Thu, 11 Jun 2015 13:27:52 +0200
Subject: cxl: use more common format specifier

A precision of 16 (%.16llx) has the same effect as a field width of 16
along with passing the 0 flag (%016llx), but the latter is much more
common in the kernel tree. Update cxl to use that.

Signed-off-by: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Acked-by: Ian Munsie <imunsie@au1.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 drivers/misc/cxl/pci.c | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

(limited to 'drivers/misc/cxl/pci.c')

diff --git a/drivers/misc/cxl/pci.c b/drivers/misc/cxl/pci.c
index 32ad09705949..eb05efb74eed 100644
--- a/drivers/misc/cxl/pci.c
+++ b/drivers/misc/cxl/pci.c
@@ -656,7 +656,7 @@ 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 +677,7 @@ 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 +686,12 @@ 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);
 	}
 
@@ -893,7 +893,7 @@ 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))))
-- 
cgit v1.2.3-70-g09d2


From bd664f892e3e2b01c79197cad3111d54b7aedf39 Mon Sep 17 00:00:00 2001
From: Johannes Thumshirn <jthumshirn@suse.de>
Date: Thu, 9 Jul 2015 09:39:42 +0200
Subject: cxl: Destroy afu->contexts_idr on release of an afu

Destroy afu->contexts_idr on release of an afu, reclaiming the allocated
memory.

Signed-off-by: Johannes Thumshirn <jthumshirn@suse.de>
Acked-by: Ian Munsie <imunsie@au1.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 drivers/misc/cxl/pci.c | 1 +
 1 file changed, 1 insertion(+)

(limited to 'drivers/misc/cxl/pci.c')

diff --git a/drivers/misc/cxl/pci.c b/drivers/misc/cxl/pci.c
index eb05efb74eed..1d314f1f95fe 100644
--- a/drivers/misc/cxl/pci.c
+++ b/drivers/misc/cxl/pci.c
@@ -551,6 +551,7 @@ static void cxl_release_afu(struct device *dev)
 
 	pr_devel("cxl_release_afu\n");
 
+	idr_destroy(&afu->contexts_idr);
 	kfree(afu);
 }
 
-- 
cgit v1.2.3-70-g09d2


From 05155772f642a5b0e421adf2017f993759bf7f95 Mon Sep 17 00:00:00 2001
From: Daniel Axtens <dja@axtens.net>
Date: Fri, 14 Aug 2015 17:41:19 +1000
Subject: cxl: Allocate and release the SPA with the AFU

Previously the SPA was allocated and freed upon entering and leaving
AFU-directed mode. This causes some issues for error recovery - contexts
hold a pointer inside the SPA, and they may persist after the AFU has
been detached.

We would ideally like to allocate the SPA when the AFU is allocated, and
release it until the AFU is released. However, we don't know how big the
SPA needs to be until we read the AFU descriptor.

Therefore, restructure the code:

 - Allocate the SPA only once, on the first attach.

 - Release the SPA only when the entire AFU is being released (not
   detached). Guard the release with a NULL check, so we don't free
   if it was never allocated (e.g. dedicated mode)

Acked-by: Cyril Bur <cyrilbur@gmail.com>
Signed-off-by: Daniel Axtens <dja@axtens.net>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 drivers/misc/cxl/cxl.h    |  3 +++
 drivers/misc/cxl/native.c | 33 ++++++++++++++++++++++-----------
 drivers/misc/cxl/pci.c    |  2 ++
 3 files changed, 27 insertions(+), 11 deletions(-)

(limited to 'drivers/misc/cxl/pci.c')

diff --git a/drivers/misc/cxl/cxl.h b/drivers/misc/cxl/cxl.h
index 9b9e89fd02cc..d540542f9931 100644
--- a/drivers/misc/cxl/cxl.h
+++ b/drivers/misc/cxl/cxl.h
@@ -632,6 +632,9 @@ 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);
diff --git a/drivers/misc/cxl/native.c b/drivers/misc/cxl/native.c
index 44568dd68bb9..b37f2e8004f5 100644
--- a/drivers/misc/cxl/native.c
+++ b/drivers/misc/cxl/native.c
@@ -183,10 +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 {
@@ -205,6 +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));
 
@@ -213,14 +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)
@@ -447,8 +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);
@@ -559,8 +572,6 @@ static int deactivate_afu_directed(struct cxl_afu *afu)
 	cxl_afu_disable(afu);
 	cxl_psl_purge(afu);
 
-	release_spa(afu);
-
 	return 0;
 }
 
diff --git a/drivers/misc/cxl/pci.c b/drivers/misc/cxl/pci.c
index 1d314f1f95fe..dc26cdd653ad 100644
--- a/drivers/misc/cxl/pci.c
+++ b/drivers/misc/cxl/pci.c
@@ -552,6 +552,8 @@ 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);
 }
 
-- 
cgit v1.2.3-70-g09d2


From 575e6986f028711287fbbf250e5289a089bac8cb Mon Sep 17 00:00:00 2001
From: Daniel Axtens <dja@axtens.net>
Date: Fri, 14 Aug 2015 17:41:21 +1000
Subject: cxl: Clean up adapter MMIO unmap path.

- MMIO pointer unmapping is guarded by a null pointer check.
   However, iounmap doesn't null the pointer, just invalidate it.
   Therefore, explicitly null the pointer after unmapping.

 - afu_desc_mmio also needs to be unmapped.

 - PCI regions are allocated in cxl_map_adapter_regs.
   Therefore they should be released in unmap, not elsewhere.

Acked-by: Cyril Bur <cyrilbur@gmail.com>
Signed-off-by: Daniel Axtens <dja@axtens.net>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 drivers/misc/cxl/pci.c | 24 ++++++++++++++++++------
 1 file changed, 18 insertions(+), 6 deletions(-)

(limited to 'drivers/misc/cxl/pci.c')

diff --git a/drivers/misc/cxl/pci.c b/drivers/misc/cxl/pci.c
index dc26cdd653ad..1dae1db3166d 100644
--- a/drivers/misc/cxl/pci.c
+++ b/drivers/misc/cxl/pci.c
@@ -539,10 +539,18 @@ 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)
@@ -920,10 +928,16 @@ 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)
@@ -1132,8 +1146,6 @@ static void cxl_remove_adapter(struct cxl *adapter)
 
 	device_unregister(&adapter->dev);
 
-	pci_release_region(pdev, 0);
-	pci_release_region(pdev, 2);
 	pci_disable_device(pdev);
 }
 
-- 
cgit v1.2.3-70-g09d2


From c044c4154247372c86b468644de88a4e48f903e9 Mon Sep 17 00:00:00 2001
From: Daniel Axtens <dja@axtens.net>
Date: Fri, 14 Aug 2015 17:41:22 +1000
Subject: cxl: Refactor adaptor init/teardown

Some aspects of initialisation are done only once in the lifetime of
an adapter: for example, allocating memory for the adapter,
allocating the adapter number, or setting up sysfs/debugfs files.

However, we may want to be able to do some parts of the
initialisation multiple times: for example, in error recovery we
want to be able to tear down and then re-map IO memory and IRQs.

Therefore, refactor CXL init/teardown as follows.

 - Keep the overarching functions 'cxl_init_adapter' and its pair,
   'cxl_remove_adapter'.

 - Move all 'once only' allocation/freeing steps to the existing
   'cxl_alloc_adapter' function, and its pair 'cxl_release_adapter'
   (This involves moving allocation of the adapter number out of
   cxl_init_adapter.)

 - Create two new functions: 'cxl_configure_adapter', and its pair
   'cxl_deconfigure_adapter'. These two functions 'wire up' the
   hardware --- they (de)configure resources that do not need to
   last the entire lifetime of the adapter

Signed-off-by: Daniel Axtens <dja@axtens.net>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 drivers/misc/cxl/pci.c | 139 ++++++++++++++++++++++++++++++-------------------
 1 file changed, 86 insertions(+), 53 deletions(-)

(limited to 'drivers/misc/cxl/pci.c')

diff --git a/drivers/misc/cxl/pci.c b/drivers/misc/cxl/pci.c
index 1dae1db3166d..feec4800e922 100644
--- a/drivers/misc/cxl/pci.c
+++ b/drivers/misc/cxl/pci.c
@@ -966,7 +966,6 @@ 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);
@@ -1026,22 +1025,33 @@ 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;
 }
 
 static int sanitise_adapter_regs(struct cxl *adapter)
@@ -1050,57 +1060,96 @@ static int sanitise_adapter_regs(struct cxl *adapter)
 	return cxl_tlb_slb_invalidate(adapter);
 }
 
-static struct cxl *cxl_init_adapter(struct pci_dev *dev)
+/* 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)
 {
-	struct cxl *adapter;
-	bool free = true;
 	int rc;
 
+	adapter->dev.parent = &dev->dev;
+	adapter->dev.release = cxl_release_adapter;
+	pci_set_drvdata(dev, adapter);
 
-	if (!(adapter = cxl_alloc_adapter(dev)))
-		return ERR_PTR(-ENOMEM);
+	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)))
-		goto err1;
+		return rc;
 
 	if ((rc = cxl_vsec_looks_ok(adapter, dev)))
-		goto err1;
+	        return rc;
 
 	if ((rc = setup_cxl_bars(dev)))
-		goto err1;
+		return rc;
 
 	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;
+		return rc;
 
 	if ((rc = cxl_update_image_control(adapter)))
-		goto err2;
+		return rc;
 
 	if ((rc = cxl_map_adapter_regs(adapter, dev)))
-		goto err2;
+		return rc;
 
 	if ((rc = sanitise_adapter_regs(adapter)))
-		goto err2;
+		goto err;
 
 	if ((rc = init_implementation_adapter_regs(adapter, dev)))
-		goto err3;
+		goto err;
 
 	if ((rc = pnv_phb_to_cxl_mode(dev, OPAL_PHB_CAPI_MODE_CAPI)))
-		goto err3;
+		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 err3;
-	}
+	if ((rc = pnv_phb_to_cxl_mode(dev, OPAL_PHB_CAPI_MODE_SNOOP_ON)))
+		goto err;
 
 	if ((rc = cxl_register_psl_err_irq(adapter)))
-		goto err3;
+		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;
+	int rc;
+
+	adapter = cxl_alloc_adapter();
+	if (!adapter)
+		return ERR_PTR(-ENOMEM);
+
+	/* Set defaults for parameters which need to persist over
+	 * configure/reconfigure
+	 */
+	adapter->perst_loads_image = true;
+
+	rc = cxl_configure_adapter(adapter, dev);
+	if (rc) {
+		pci_disable_device(dev);
+		cxl_release_adapter(&adapter->dev);
+		return ERR_PTR(rc);
+	}
 
 	/* Don't care if this one fails: */
 	cxl_debugfs_adapter_add(adapter);
@@ -1118,35 +1167,25 @@ 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);
 
-	device_unregister(&adapter->dev);
+	cxl_deconfigure_adapter(adapter);
 
-	pci_disable_device(pdev);
+	device_unregister(&adapter->dev);
 }
 
 static int cxl_probe(struct pci_dev *dev, const struct pci_device_id *id)
@@ -1160,15 +1199,9 @@ 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);
 	}
 
-- 
cgit v1.2.3-70-g09d2


From d76427b0d89524fdb623774a22a005ba5c400134 Mon Sep 17 00:00:00 2001
From: Daniel Axtens <dja@axtens.net>
Date: Fri, 14 Aug 2015 17:41:23 +1000
Subject: cxl: Refactor AFU init/teardown

As with an adapter, some aspects of initialisation are done only once
in the lifetime of an AFU: for example, allocating memory, or setting
up sysfs/debugfs files.

However, we may want to be able to do some parts of the initialisation
multiple times: for example, in error recovery we want to be able to
tear down and then re-map IO memory and IRQs.

Therefore, refactor AFU init/teardown as follows.

 - Create two new functions: 'cxl_configure_afu', and its pair
   'cxl_deconfigure_afu'. As with the adapter functions,
   these (de)configure resources that do not need to last the entire
   lifetime of the AFU.

 - Allocating and releasing memory remain the task of 'cxl_alloc_afu'
   and 'cxl_release_afu'.

 - Once-only functions that do not involve allocating/releasing memory
   stay in the overarching 'cxl_init_afu'/'cxl_remove_afu' pair.
   However, the task of picking an AFU mode and activating it has been
   broken out.

Signed-off-by: Daniel Axtens <dja@axtens.net>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 drivers/misc/cxl/pci.c | 95 ++++++++++++++++++++++++++++++--------------------
 1 file changed, 57 insertions(+), 38 deletions(-)

(limited to 'drivers/misc/cxl/pci.c')

diff --git a/drivers/misc/cxl/pci.c b/drivers/misc/cxl/pci.c
index feec4800e922..b63d96023c50 100644
--- a/drivers/misc/cxl/pci.c
+++ b/drivers/misc/cxl/pci.c
@@ -753,45 +753,70 @@ 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);
@@ -806,10 +831,6 @@ 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)))
@@ -817,21 +838,16 @@ 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)
@@ -851,10 +867,7 @@ 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);
 }
 
@@ -1206,8 +1219,14 @@ static int cxl_probe(struct pci_dev *dev, const struct pci_device_id *id)
 	}
 
 	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;
-- 
cgit v1.2.3-70-g09d2


From 4e1efb403c1c016ae831bd9988a7d2e5e0af41a0 Mon Sep 17 00:00:00 2001
From: Daniel Axtens <dja@axtens.net>
Date: Fri, 14 Aug 2015 17:41:24 +1000
Subject: cxl: Don't remove AFUs/vPHBs in cxl_reset

If the driver doesn't participate in EEH, the AFUs will be removed
by cxl_remove, which will be invoked by EEH.

If the driver does particpate in EEH, the vPHB needs to stick around
so that the it can particpate.

In both cases, we shouldn't remove the AFU/vPHB.

Reviewed-by: Cyril Bur <cyrilbur@gmail.com>
Signed-off-by: Daniel Axtens <dja@axtens.net>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 drivers/misc/cxl/pci.c | 5 -----
 1 file changed, 5 deletions(-)

(limited to 'drivers/misc/cxl/pci.c')

diff --git a/drivers/misc/cxl/pci.c b/drivers/misc/cxl/pci.c
index b63d96023c50..2b61cb1ee62c 100644
--- a/drivers/misc/cxl/pci.c
+++ b/drivers/misc/cxl/pci.c
@@ -880,11 +880,6 @@ int cxl_reset(struct cxl *adapter)
 
 	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 */
-- 
cgit v1.2.3-70-g09d2


From 13e68d8bd05c998cae452a4f3400af1e8edd852e Mon Sep 17 00:00:00 2001
From: Daniel Axtens <dja@axtens.net>
Date: Fri, 14 Aug 2015 17:41:25 +1000
Subject: cxl: Allow the kernel to trust that an image won't change on PERST.

Provide a kernel API and a sysfs entry which allow a user to specify
that when a card is PERSTed, it's image will stay the same, allowing
it to participate in EEH.

cxl_reset is used to reflash the card. In that case, we cannot safely
assert that the image will not change. Therefore, disallow cxl_reset
if the flag is set.

Signed-off-by: Daniel Axtens <dja@axtens.net>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 Documentation/ABI/testing/sysfs-class-cxl | 10 ++++++++++
 drivers/misc/cxl/api.c                    |  7 +++++++
 drivers/misc/cxl/cxl.h                    |  1 +
 drivers/misc/cxl/pci.c                    |  7 +++++++
 drivers/misc/cxl/sysfs.c                  | 26 ++++++++++++++++++++++++++
 include/misc/cxl.h                        | 10 ++++++++++
 6 files changed, 61 insertions(+)

(limited to 'drivers/misc/cxl/pci.c')

diff --git a/Documentation/ABI/testing/sysfs-class-cxl b/Documentation/ABI/testing/sysfs-class-cxl
index acfe9df83139..b07e86d4597f 100644
--- a/Documentation/ABI/testing/sysfs-class-cxl
+++ b/Documentation/ABI/testing/sysfs-class-cxl
@@ -223,3 +223,13 @@ Description:    write only
                 Writing 1 will issue a PERST to card which may cause the card
                 to reload the FPGA depending on load_image_on_perst.
 Users:		https://github.com/ibm-capi/libcxl
+
+What:		/sys/class/cxl/<card>/perst_reloads_same_image
+Date:		July 2015
+Contact:	linuxppc-dev@lists.ozlabs.org
+Description:	read/write
+		Trust that when an image is reloaded via PERST, it will not
+		have changed.
+		0 = don't trust, the image may be different (default)
+		1 = trust that the image will not change.
+Users:		https://github.com/ibm-capi/libcxl
diff --git a/drivers/misc/cxl/api.c b/drivers/misc/cxl/api.c
index 729e0851167d..6a768a9ad22f 100644
--- a/drivers/misc/cxl/api.c
+++ b/drivers/misc/cxl/api.c
@@ -327,3 +327,10 @@ 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);
diff --git a/drivers/misc/cxl/cxl.h b/drivers/misc/cxl/cxl.h
index d540542f9931..cda02412b01e 100644
--- a/drivers/misc/cxl/cxl.h
+++ b/drivers/misc/cxl/cxl.h
@@ -493,6 +493,7 @@ 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);
diff --git a/drivers/misc/cxl/pci.c b/drivers/misc/cxl/pci.c
index 2b61cb1ee62c..bfbd6478c0c5 100644
--- a/drivers/misc/cxl/pci.c
+++ b/drivers/misc/cxl/pci.c
@@ -878,6 +878,12 @@ int cxl_reset(struct cxl *adapter)
 	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");
 
 	/* pcie_warm_reset requests a fundamental pci reset which includes a
@@ -1151,6 +1157,7 @@ static struct cxl *cxl_init_adapter(struct pci_dev *dev)
 	 * configure/reconfigure
 	 */
 	adapter->perst_loads_image = true;
+	adapter->perst_same_image = false;
 
 	rc = cxl_configure_adapter(adapter, dev);
 	if (rc) {
diff --git a/drivers/misc/cxl/sysfs.c b/drivers/misc/cxl/sysfs.c
index 31f38bc71a3d..6619cf1f6e1f 100644
--- a/drivers/misc/cxl/sysfs.c
+++ b/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),
 };
 
diff --git a/include/misc/cxl.h b/include/misc/cxl.h
index 7a6c1d6cc173..f2ffe5bd720d 100644
--- a/include/misc/cxl.h
+++ b/include/misc/cxl.h
@@ -200,4 +200,14 @@ unsigned int cxl_fd_poll(struct file *file, struct poll_table_struct *poll);
 ssize_t cxl_fd_read(struct file *file, char __user *buf, size_t count,
 			   loff_t *off);
 
+/*
+ * For EEH, a driver may want to assert a PERST will reload the same image
+ * from flash into the FPGA.
+ *
+ * This is a property of the entire adapter, not a single AFU, so drivers
+ * should set this property with care!
+ */
+void cxl_perst_reloads_same_image(struct cxl_afu *afu,
+				  bool perst_reloads_same_image);
+
 #endif /* _MISC_CXL_H */
-- 
cgit v1.2.3-70-g09d2


From 9e8df8a219635c5af36a49d78c1f69009b780339 Mon Sep 17 00:00:00 2001
From: Daniel Axtens <dja@axtens.net>
Date: Fri, 14 Aug 2015 17:41:26 +1000
Subject: cxl: EEH support

EEH (Enhanced Error Handling) allows a driver to recover from the
temporary failure of an attached PCI card. Enable basic CXL support
for EEH.

Signed-off-by: Daniel Axtens <dja@axtens.net>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 drivers/misc/cxl/cxl.h  |   1 +
 drivers/misc/cxl/pci.c  | 253 ++++++++++++++++++++++++++++++++++++++++++++++++
 drivers/misc/cxl/vphb.c |   8 ++
 3 files changed, 262 insertions(+)

(limited to 'drivers/misc/cxl/pci.c')

diff --git a/drivers/misc/cxl/cxl.h b/drivers/misc/cxl/cxl.h
index cda02412b01e..6f5386653dae 100644
--- a/drivers/misc/cxl/cxl.h
+++ b/drivers/misc/cxl/cxl.h
@@ -726,6 +726,7 @@ 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;
diff --git a/drivers/misc/cxl/pci.c b/drivers/misc/cxl/pci.c
index bfbd6478c0c5..03ddb2d8f974 100644
--- a/drivers/misc/cxl/pci.c
+++ b/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
@@ -1252,10 +1253,262 @@ 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,
 };
diff --git a/drivers/misc/cxl/vphb.c b/drivers/misc/cxl/vphb.c
index 2930911c1e42..6dd16a6d153f 100644
--- a/drivers/misc/cxl/vphb.c
+++ b/drivers/misc/cxl/vphb.c
@@ -266,6 +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)
 {
-- 
cgit v1.2.3-70-g09d2


From f47f966fbe0aaff4ebbdb83d95acdfa5d3c20477 Mon Sep 17 00:00:00 2001
From: Vaishali Thakkar <vthakkar1994@gmail.com>
Date: Sun, 19 Jul 2015 22:53:52 +0530
Subject: cxl: Remove use of macro DEFINE_PCI_DEVICE_TABLE

Macro DEFINE_PCI_DEVICE_TABLE is deprecated. So, here use
struct pci_device_id instead of DEFINE_PCI_DEVICE_TABLE with
the goal of getting rid of this macro completely.

The Coccinelle semantic patch that performs this transformation
is as follows:

@@
identifier a;
declarer name DEFINE_PCI_DEVICE_TABLE;
initializer i;
@@
- DEFINE_PCI_DEVICE_TABLE(a)
+ const struct pci_device_id a[]
= i;

Signed-off-by: Vaishali Thakkar <vthakkar1994@gmail.com>
Acked-by: Michael Neuling <mikey@neuling.org>
Acked-by: Ian Munsie <imunsie@au1.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 drivers/misc/cxl/pci.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'drivers/misc/cxl/pci.c')

diff --git a/drivers/misc/cxl/pci.c b/drivers/misc/cxl/pci.c
index 03ddb2d8f974..273374c507f7 100644
--- a/drivers/misc/cxl/pci.c
+++ b/drivers/misc/cxl/pci.c
@@ -134,7 +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), },
-- 
cgit v1.2.3-70-g09d2


From 9d8e27673c45927fee9e7d8992ffb325a6b0b0e4 Mon Sep 17 00:00:00 2001
From: Daniel Axtens <dja@axtens.net>
Date: Fri, 21 Aug 2015 17:25:15 +1000
Subject: cxl: Remove racy attempt to force EEH invocation in reset

cxl_reset currently PERSTs the slot, and then repeatedly tries to
read MMIO space in order to kick off EEH.

There are 2 problems with this: it's unnecessary, and it's racy.

It's unnecessary because the PERST will bring down the PHB link.
That will be picked up by the CAPP, which will send out an HMI.
Skiboot, noticing an HMI from the CAPP, will send an OPAL
notification to the kernel, which will trigger EEH recovery.

It's also racy: the EEH recovery triggered by the CAPP will
eventually cause the MMIO space to have its mapping invalidated
and the pointer NULLed out. This races with our attempt to read
the MMIO space. This is causing OOPSes in testing.

Simply drop all the attempts to force EEH detection, and trust
that Skiboot will send the notification and that we'll act on it.
The Skiboot code to send the EEH notification has been in Skiboot
for as long as CAPP recovery has been supported, so we don't need
to worry about breaking obscure setups with ancient firmware.

Cc: Ryan Grimm <grimm@linux.vnet.ibm.com>
Cc: stable@vger.kernel.org
Fixes: 62fa19d4b4fd ("cxl: Add ability to reset the card")
Signed-off-by: Daniel Axtens <dja@axtens.net>
Acked-by: Ian Munsie <imunsie@au1.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 drivers/misc/cxl/pci.c | 16 ----------------
 1 file changed, 16 deletions(-)

(limited to 'drivers/misc/cxl/pci.c')

diff --git a/drivers/misc/cxl/pci.c b/drivers/misc/cxl/pci.c
index 273374c507f7..6ca7c3d0ef9b 100644
--- a/drivers/misc/cxl/pci.c
+++ b/drivers/misc/cxl/pci.c
@@ -876,8 +876,6 @@ 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,
@@ -895,20 +893,6 @@ 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;
 }
 
-- 
cgit v1.2.3-70-g09d2


From 390fd5929f52bdfb9dfcc03820041ba556780f4a Mon Sep 17 00:00:00 2001
From: Philippe Bergheaud <felix@linux.vnet.ibm.com>
Date: Fri, 28 Aug 2015 09:37:36 +0200
Subject: cxl: Set up and enable PSL Timebase

This patch configures the PSL Timebase function and enables it,
after the CAPP has been initialized by OPAL.

Acked-by: Ian Munsie <imunsie@au1.ibm.com>
Signed-off-by: Philippe Bergheaud <felix@linux.vnet.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
---
 drivers/misc/cxl/cxl.h |  5 +++++
 drivers/misc/cxl/pci.c | 57 +++++++++++++++++++++++++++++++++++++++++++++++++-
 2 files changed, 61 insertions(+), 1 deletion(-)

(limited to 'drivers/misc/cxl/pci.c')

diff --git a/drivers/misc/cxl/cxl.h b/drivers/misc/cxl/cxl.h
index d6566c60bcb0..1c30ef77073d 100644
--- a/drivers/misc/cxl/cxl.h
+++ b/drivers/misc/cxl/cxl.h
@@ -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))
diff --git a/drivers/misc/cxl/pci.c b/drivers/misc/cxl/pci.c
index 6ca7c3d0ef9b..02c85160bfe9 100644
--- a/drivers/misc/cxl/pci.c
+++ b/drivers/misc/cxl/pci.c
@@ -370,6 +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 */
@@ -1053,9 +1102,12 @@ err1:
 	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);
 }
 
@@ -1108,6 +1160,9 @@ static int cxl_configure_adapter(struct cxl *adapter, struct pci_dev *dev)
 	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;
 
-- 
cgit v1.2.3-70-g09d2