summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorVishal Verma <vishal.l.verma@intel.com>2022-04-13 10:36:18 +0300
committerDan Williams <dan.j.williams@intel.com>2022-04-29 00:01:54 +0300
commit56368029d93bbb3246ee2e03268fa6dd9754be05 (patch)
tree41b2516ec4344c90978359d90a935a06efc33786
parent241d26bc26add2e2867c546f7474902406d37c60 (diff)
downloadlinux-56368029d93bbb3246ee2e03268fa6dd9754be05.tar.xz
PCI/ACPI: negotiate CXL _OSC
Add full support for negotiating _OSC as defined in the CXL 2.0 spec, as applicable to CXL-enabled platforms. Advertise support for the CXL features we support - 'CXL 2.0 port/device register access', 'Protocol Error Reporting', and 'CXL Native Hot Plug'. Request control for 'CXL Memory Error Reporting'. The requests are dependent on CONFIG_* based prerequisites, and prior PCI enabling, similar to how the standard PCI _OSC bits are determined. The CXL specification does not define any additional constraints on the hotplug flow beyond PCIe native hotplug, so a kernel that supports native PCIe hotplug, supports CXL hotplug. For error handling protocol and link errors just use PCIe AER. There is nascent support for amending AER events with CXL specific status [1], but there's otherwise no additional OS responsibility for CXL errors beyond PCIe AER. CXL Memory Errors behave the same as typical memory errors so CONFIG_MEMORY_FAILURE is sufficient to indicate support to platform firmware. [1]: https://lore.kernel.org/linux-cxl/164740402242.3912056.8303625392871313860.stgit@dwillia2-desk3.amr.corp.intel.com/ Cc: Bjorn Helgaas <bhelgaas@google.com> Cc: "Rafael J. Wysocki" <rafael@kernel.org> Cc: Robert Moore <robert.moore@intel.com> Cc: Dan Williams <dan.j.williams@intel.com> Reviewed-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Reviewed-by: Davidlohr Bueso <dave@stgolabs.net> Signed-off-by: Vishal Verma <vishal.l.verma@intel.com> Link: https://lore.kernel.org/r/20220413073618.291335-4-vishal.l.verma@intel.com Signed-off-by: Dan Williams <dan.j.williams@intel.com>
-rw-r--r--drivers/acpi/pci_root.c179
-rw-r--r--include/acpi/acpi_bus.h6
-rw-r--r--include/linux/acpi.h25
3 files changed, 188 insertions, 22 deletions
diff --git a/drivers/acpi/pci_root.c b/drivers/acpi/pci_root.c
index 1e683c115ee0..c82ad63fffed 100644
--- a/drivers/acpi/pci_root.c
+++ b/drivers/acpi/pci_root.c
@@ -140,6 +140,17 @@ static struct pci_osc_bit_struct pci_osc_control_bit[] = {
{ OSC_PCI_EXPRESS_DPC_CONTROL, "DPC" },
};
+static struct pci_osc_bit_struct cxl_osc_support_bit[] = {
+ { OSC_CXL_1_1_PORT_REG_ACCESS_SUPPORT, "CXL11PortRegAccess" },
+ { OSC_CXL_2_0_PORT_DEV_REG_ACCESS_SUPPORT, "CXL20PortDevRegAccess" },
+ { OSC_CXL_PROTOCOL_ERR_REPORTING_SUPPORT, "CXLProtocolErrorReporting" },
+ { OSC_CXL_NATIVE_HP_SUPPORT, "CXLNativeHotPlug" },
+};
+
+static struct pci_osc_bit_struct cxl_osc_control_bit[] = {
+ { OSC_CXL_ERROR_REPORTING_CONTROL, "CXLMemErrorReporting" },
+};
+
static void decode_osc_bits(struct acpi_pci_root *root, char *msg, u32 word,
struct pci_osc_bit_struct *table, int size)
{
@@ -168,6 +179,18 @@ static void decode_osc_control(struct acpi_pci_root *root, char *msg, u32 word)
ARRAY_SIZE(pci_osc_control_bit));
}
+static void decode_cxl_osc_support(struct acpi_pci_root *root, char *msg, u32 word)
+{
+ decode_osc_bits(root, msg, word, cxl_osc_support_bit,
+ ARRAY_SIZE(cxl_osc_support_bit));
+}
+
+static void decode_cxl_osc_control(struct acpi_pci_root *root, char *msg, u32 word)
+{
+ decode_osc_bits(root, msg, word, cxl_osc_control_bit,
+ ARRAY_SIZE(cxl_osc_control_bit));
+}
+
static inline bool is_pcie(struct acpi_pci_root *root)
{
return root->bridge_type == ACPI_BRIDGE_TYPE_PCIE;
@@ -196,7 +219,8 @@ static int cap_length(struct acpi_pci_root *root)
}
static acpi_status acpi_pci_run_osc(struct acpi_pci_root *root,
- const u32 *capbuf, u32 *retval)
+ const u32 *capbuf, u32 *pci_control,
+ u32 *cxl_control)
{
struct acpi_osc_context context = {
.uuid_str = to_uuid(root),
@@ -208,18 +232,20 @@ static acpi_status acpi_pci_run_osc(struct acpi_pci_root *root,
status = acpi_run_osc(root->device->handle, &context);
if (ACPI_SUCCESS(status)) {
- *retval = acpi_osc_ctx_get_pci_control(&context);
+ *pci_control = acpi_osc_ctx_get_pci_control(&context);
+ if (is_cxl(root))
+ *cxl_control = acpi_osc_ctx_get_cxl_control(&context);
kfree(context.ret.pointer);
}
return status;
}
-static acpi_status acpi_pci_query_osc(struct acpi_pci_root *root,
- u32 support,
- u32 *control)
+static acpi_status acpi_pci_query_osc(struct acpi_pci_root *root, u32 support,
+ u32 *control, u32 cxl_support,
+ u32 *cxl_control)
{
acpi_status status;
- u32 result, capbuf[OSC_CXL_CAPABILITY_DWORDS];
+ u32 pci_result, cxl_result, capbuf[OSC_CXL_CAPABILITY_DWORDS];
support |= root->osc_support_set;
@@ -227,11 +253,21 @@ static acpi_status acpi_pci_query_osc(struct acpi_pci_root *root,
capbuf[OSC_SUPPORT_DWORD] = support;
capbuf[OSC_CONTROL_DWORD] = *control | root->osc_control_set;
+ if (is_cxl(root)) {
+ cxl_support |= root->osc_ext_support_set;
+ capbuf[OSC_EXT_SUPPORT_DWORD] = cxl_support;
+ capbuf[OSC_EXT_CONTROL_DWORD] = *cxl_control | root->osc_ext_control_set;
+ }
+
retry:
- status = acpi_pci_run_osc(root, capbuf, &result);
+ status = acpi_pci_run_osc(root, capbuf, &pci_result, &cxl_result);
if (ACPI_SUCCESS(status)) {
root->osc_support_set = support;
- *control = result;
+ *control = pci_result;
+ if (is_cxl(root)) {
+ root->osc_ext_support_set = cxl_support;
+ *cxl_control = cxl_result;
+ }
} else if (is_cxl(root)) {
/*
* CXL _OSC is optional on CXL 1.1 hosts. Fall back to PCIe _OSC
@@ -354,6 +390,8 @@ EXPORT_SYMBOL_GPL(acpi_get_pci_dev);
* @handle: ACPI handle of a PCI root bridge (or PCIe Root Complex).
* @mask: Mask of _OSC bits to request control of, place to store control mask.
* @support: _OSC supported capability.
+ * @cxl_mask: Mask of CXL _OSC control bits, place to store control mask.
+ * @cxl_support: CXL _OSC supported capability.
*
* Run _OSC query for @mask and if that is successful, compare the returned
* mask of control bits with @req. If all of the @req bits are set in the
@@ -364,12 +402,14 @@ EXPORT_SYMBOL_GPL(acpi_get_pci_dev);
* _OSC bits the BIOS has granted control of, but its contents are meaningless
* on failure.
**/
-static acpi_status acpi_pci_osc_control_set(acpi_handle handle, u32 *mask, u32 support)
+static acpi_status acpi_pci_osc_control_set(acpi_handle handle, u32 *mask,
+ u32 support, u32 *cxl_mask,
+ u32 cxl_support)
{
u32 req = OSC_PCI_EXPRESS_CAPABILITY_CONTROL;
struct acpi_pci_root *root;
acpi_status status;
- u32 ctrl, capbuf[OSC_CXL_CAPABILITY_DWORDS];
+ u32 ctrl, cxl_ctrl = 0, capbuf[OSC_CXL_CAPABILITY_DWORDS];
if (!mask)
return AE_BAD_PARAMETER;
@@ -381,20 +421,42 @@ static acpi_status acpi_pci_osc_control_set(acpi_handle handle, u32 *mask, u32 s
ctrl = *mask;
*mask |= root->osc_control_set;
+ if (is_cxl(root)) {
+ cxl_ctrl = *cxl_mask;
+ *cxl_mask |= root->osc_ext_control_set;
+ }
+
/* Need to check the available controls bits before requesting them. */
do {
- status = acpi_pci_query_osc(root, support, mask);
+ u32 pci_missing = 0, cxl_missing = 0;
+
+ status = acpi_pci_query_osc(root, support, mask, cxl_support,
+ cxl_mask);
if (ACPI_FAILURE(status))
return status;
- if (ctrl == *mask)
- break;
- decode_osc_control(root, "platform does not support",
- ctrl & ~(*mask));
+ if (is_cxl(root)) {
+ if (ctrl == *mask && cxl_ctrl == *cxl_mask)
+ break;
+ pci_missing = ctrl & ~(*mask);
+ cxl_missing = cxl_ctrl & ~(*cxl_mask);
+ } else {
+ if (ctrl == *mask)
+ break;
+ pci_missing = ctrl & ~(*mask);
+ }
+ if (pci_missing)
+ decode_osc_control(root, "platform does not support",
+ pci_missing);
+ if (cxl_missing)
+ decode_cxl_osc_control(root, "CXL platform does not support",
+ cxl_missing);
ctrl = *mask;
- } while (*mask);
+ cxl_ctrl = *cxl_mask;
+ } while (*mask || *cxl_mask);
/* No need to request _OSC if the control was already granted. */
- if ((root->osc_control_set & ctrl) == ctrl)
+ if ((root->osc_control_set & ctrl) == ctrl &&
+ (root->osc_ext_control_set & cxl_ctrl) == cxl_ctrl)
return AE_OK;
if ((ctrl & req) != req) {
@@ -406,11 +468,17 @@ static acpi_status acpi_pci_osc_control_set(acpi_handle handle, u32 *mask, u32 s
capbuf[OSC_QUERY_DWORD] = 0;
capbuf[OSC_SUPPORT_DWORD] = root->osc_support_set;
capbuf[OSC_CONTROL_DWORD] = ctrl;
- status = acpi_pci_run_osc(root, capbuf, mask);
+ if (is_cxl(root)) {
+ capbuf[OSC_EXT_SUPPORT_DWORD] = root->osc_ext_support_set;
+ capbuf[OSC_EXT_CONTROL_DWORD] = cxl_ctrl;
+ }
+
+ status = acpi_pci_run_osc(root, capbuf, mask, cxl_mask);
if (ACPI_FAILURE(status))
return status;
root->osc_control_set = *mask;
+ root->osc_ext_control_set = *cxl_mask;
return AE_OK;
}
@@ -436,6 +504,53 @@ static u32 calculate_support(void)
return support;
}
+/*
+ * Background on hotplug support, and making it depend on only
+ * CONFIG_HOTPLUG_PCI_PCIE vs. also considering CONFIG_MEMORY_HOTPLUG:
+ *
+ * CONFIG_ACPI_HOTPLUG_MEMORY does depend on CONFIG_MEMORY_HOTPLUG, but
+ * there is no existing _OSC for memory hotplug support. The reason is that
+ * ACPI memory hotplug requires the OS to acknowledge / coordinate with
+ * memory plug events via a scan handler. On the CXL side the equivalent
+ * would be if Linux supported the Mechanical Retention Lock [1], or
+ * otherwise had some coordination for the driver of a PCI device
+ * undergoing hotplug to be consulted on whether the hotplug should
+ * proceed or not.
+ *
+ * The concern is that if Linux says no to supporting CXL hotplug then
+ * the BIOS may say no to giving the OS hotplug control of any other PCIe
+ * device. So the question here is not whether hotplug is enabled, it's
+ * whether it is handled natively by the at all OS, and if
+ * CONFIG_HOTPLUG_PCI_PCIE is enabled then the answer is "yes".
+ *
+ * Otherwise, the plan for CXL coordinated remove, since the kernel does
+ * not support blocking hotplug, is to require the memory device to be
+ * disabled before hotplug is attempted. When CONFIG_MEMORY_HOTPLUG is
+ * disabled that step will fail and the remove attempt cancelled by the
+ * user. If that is not honored and the card is removed anyway then it
+ * does not matter if CONFIG_MEMORY_HOTPLUG is enabled or not, it will
+ * cause a crash and other badness.
+ *
+ * Therefore, just say yes to CXL hotplug and require removal to
+ * be coordinated by userspace unless and until the kernel grows better
+ * mechanisms for doing "managed" removal of devices in consultation with
+ * the driver.
+ *
+ * [1]: https://lore.kernel.org/all/20201122014203.4706-1-ashok.raj@intel.com/
+ */
+static u32 calculate_cxl_support(void)
+{
+ u32 support;
+
+ support = OSC_CXL_2_0_PORT_DEV_REG_ACCESS_SUPPORT;
+ if (pci_aer_available())
+ support |= OSC_CXL_PROTOCOL_ERR_REPORTING_SUPPORT;
+ if (IS_ENABLED(CONFIG_HOTPLUG_PCI_PCIE))
+ support |= OSC_CXL_NATIVE_HP_SUPPORT;
+
+ return support;
+}
+
static u32 calculate_control(void)
{
u32 control;
@@ -467,6 +582,16 @@ static u32 calculate_control(void)
return control;
}
+static u32 calculate_cxl_control(void)
+{
+ u32 control = 0;
+
+ if (IS_ENABLED(CONFIG_MEMORY_FAILURE))
+ control |= OSC_CXL_ERROR_REPORTING_CONTROL;
+
+ return control;
+}
+
static bool os_control_query_checks(struct acpi_pci_root *root, u32 support)
{
struct acpi_device *device = root->device;
@@ -488,6 +613,7 @@ static bool os_control_query_checks(struct acpi_pci_root *root, u32 support)
static void negotiate_os_control(struct acpi_pci_root *root, int *no_aspm)
{
u32 support, control = 0, requested = 0;
+ u32 cxl_support = 0, cxl_control = 0, cxl_requested = 0;
acpi_status status;
struct acpi_device *device = root->device;
acpi_handle handle = device->handle;
@@ -511,10 +637,20 @@ static void negotiate_os_control(struct acpi_pci_root *root, int *no_aspm)
if (os_control_query_checks(root, support))
requested = control = calculate_control();
- status = acpi_pci_osc_control_set(handle, &control, support);
+ if (is_cxl(root)) {
+ cxl_support = calculate_cxl_support();
+ decode_cxl_osc_support(root, "OS supports", cxl_support);
+ cxl_requested = cxl_control = calculate_cxl_control();
+ }
+
+ status = acpi_pci_osc_control_set(handle, &control, support,
+ &cxl_control, cxl_support);
if (ACPI_SUCCESS(status)) {
if (control)
decode_osc_control(root, "OS now controls", control);
+ if (cxl_control)
+ decode_cxl_osc_control(root, "OS now controls",
+ cxl_control);
if (acpi_gbl_FADT.boot_flags & ACPI_FADT_NO_ASPM) {
/*
@@ -543,6 +679,11 @@ static void negotiate_os_control(struct acpi_pci_root *root, int *no_aspm)
decode_osc_control(root, "OS requested", requested);
decode_osc_control(root, "platform willing to grant", control);
}
+ if (cxl_control) {
+ decode_cxl_osc_control(root, "OS requested", cxl_requested);
+ decode_cxl_osc_control(root, "platform willing to grant",
+ cxl_control);
+ }
dev_info(&device->dev, "_OSC: platform retains control of PCIe features (%s)\n",
acpi_format_exception(status));
diff --git a/include/acpi/acpi_bus.h b/include/acpi/acpi_bus.h
index 305ebf2a3fa7..4c463ae2777b 100644
--- a/include/acpi/acpi_bus.h
+++ b/include/acpi/acpi_bus.h
@@ -594,8 +594,10 @@ struct acpi_pci_root {
int bridge_type;
struct resource secondary; /* downstream bus range */
- u32 osc_support_set; /* _OSC state of support bits */
- u32 osc_control_set; /* _OSC state of control bits */
+ u32 osc_support_set; /* _OSC state of support bits */
+ u32 osc_control_set; /* _OSC state of control bits */
+ u32 osc_ext_support_set; /* _OSC state of extended support bits */
+ u32 osc_ext_control_set; /* _OSC state of extended control bits */
phys_addr_t mcfg_addr;
};
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index 82d91d9ccce5..378a431666b3 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -554,10 +554,12 @@ acpi_status acpi_run_osc(acpi_handle handle, struct acpi_osc_context *context);
#define OSC_PCI_CAPABILITY_DWORDS 3
#define OSC_CXL_CAPABILITY_DWORDS 5
-/* Indexes into _OSC Capabilities Buffer (DWORDs 2 & 3 are device-specific) */
+/* Indexes into _OSC Capabilities Buffer (DWORDs 2 to 5 are device-specific) */
#define OSC_QUERY_DWORD 0 /* DWORD 1 */
#define OSC_SUPPORT_DWORD 1 /* DWORD 2 */
#define OSC_CONTROL_DWORD 2 /* DWORD 3 */
+#define OSC_EXT_SUPPORT_DWORD 3 /* DWORD 4 */
+#define OSC_EXT_CONTROL_DWORD 4 /* DWORD 5 */
/* _OSC Capabilities DWORD 1: Query/Control and Error Returns (generic) */
#define OSC_QUERY_ENABLE 0x00000001 /* input */
@@ -612,6 +614,15 @@ extern u32 osc_sb_native_usb4_control;
#define OSC_PCI_EXPRESS_LTR_CONTROL 0x00000020
#define OSC_PCI_EXPRESS_DPC_CONTROL 0x00000080
+/* CXL _OSC: Capabilities DWORD 4: Support Field */
+#define OSC_CXL_1_1_PORT_REG_ACCESS_SUPPORT 0x00000001
+#define OSC_CXL_2_0_PORT_DEV_REG_ACCESS_SUPPORT 0x00000002
+#define OSC_CXL_PROTOCOL_ERR_REPORTING_SUPPORT 0x00000004
+#define OSC_CXL_NATIVE_HP_SUPPORT 0x00000008
+
+/* CXL _OSC: Capabilities DWORD 5: Control Field */
+#define OSC_CXL_ERROR_REPORTING_CONTROL 0x00000001
+
static inline u32 acpi_osc_ctx_get_pci_control(struct acpi_osc_context *context)
{
u32 *ret = context->ret.pointer;
@@ -619,6 +630,13 @@ static inline u32 acpi_osc_ctx_get_pci_control(struct acpi_osc_context *context)
return ret[OSC_CONTROL_DWORD];
}
+static inline u32 acpi_osc_ctx_get_cxl_control(struct acpi_osc_context *context)
+{
+ u32 *ret = context->ret.pointer;
+
+ return ret[OSC_EXT_CONTROL_DWORD];
+}
+
#define ACPI_GSB_ACCESS_ATTRIB_QUICK 0x00000002
#define ACPI_GSB_ACCESS_ATTRIB_SEND_RCV 0x00000004
#define ACPI_GSB_ACCESS_ATTRIB_BYTE 0x00000006
@@ -1021,6 +1039,11 @@ static inline u32 acpi_osc_ctx_get_pci_control(struct acpi_osc_context *context)
return 0;
}
+static inline u32 acpi_osc_ctx_get_cxl_control(struct acpi_osc_context *context)
+{
+ return 0;
+}
+
#endif /* !CONFIG_ACPI */
#ifdef CONFIG_ACPI_HOTPLUG_IOAPIC