Merge tag 'trace-v7.3-2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-tracegrafted

Pull tracing fixes from Steven Rostedt:

 - Fix error output of boot instance creation failure

   Currently if a boot instance creation fails, instead of printing out
   the name of the instance that failed, it prints "(null)". That is
   because it prints "cur_str" that had already been processed by
   strsep(). Print the saved name instead.

   While at it, print the error code of the failure.

 - Fix use-after-free for same named historgrams

   Histograms can be named so that they can be used in multiple events.
   But if the named histogram has a variable attached, the second event
   that uses the named histogram which duplicates it and needs to free
   the original after duplication leaves the old variable in place and
   still visible. If another histogram uses than variable, it will use
   the stale one which will try to reference the freed duplicate
   histogram and crash the kernel.

   Free the duplicate variables along with the duplicated histogram
   data.

 - Check return value of kthread_run() in event self test

   The events self tests uses a kthread for testing but does not check
   if it succeeded in creating a kthread. If the kthread creation were
   to fail, the code will still try to call kthread_stop() on the error
   returned.

 - Fix race between reading trace_pipe and updating subbuffer size

   If a user is reading the trace_pipe file at the same time they update
   the ring buffer sub-buffer size, can cause the trace_pipe read to
   read stale data. Add trace_access_lock() around updating the ring
   buffer sub-buffer size.

 - Fix eventfs_inode on failure path in creation of the events directory

   In the creation of the "events" directory, if after allocating the
   eventfs_inode a failure is detected, it calls cleanup_ei() which
   calls free_ei(). The free_ei() will test if eventfs_inode being freed
   has no children. It is a bug if it does. But on the failure case of
   the creation of the "events" directory, the children lists have not
   yet been initialized and the free will trigger a warning because
   list_empty() on an uninitialized list returns false.

   Move the initialization into init_ei() where it makes more sense and
   makes sure that a created eventfs_inode has its lists initialized
   upon creation.

 - Check return value of kthread_run() in ftrace direct sample code

   The sample code that shows how to use the ftrace direct calls does
   not test the return of kthread_run() to see if it succeeds. Return a
   failure if the kthread_run() doesn't succeed.

 - Clear user events state on fork in case of alloc failure

   On fork, the child gets a pointer to the parent's user events state.
   It makes a copy of it then updates the child's pointer to it. But if
   the allocation fails, the duplication function leaves the child with
   a pointer to its parent's descriptor. When the child cleans up its
   data, it will free the parent's descriptor while the parent is still
   using it.

   In the duplication function, set the child's user_event_mm to NULL
   before testing if the allocation succeeded, and when it exits it will
   not free the parent's descriptor.

 - Fix retry exhaustion in simple ring buffer reader swap

   simple_ring_buffer_swap_reader_page() starts with retry set to 8 and
   post-decrements it only after a failed link replacement. On the final
   attempt, a successful replacement leaves retry at zero, while a
   failed replacement leaves it at -1.

   But the check for success expects the retry value to be non-zero and
   exits with an error on zero. This is the opposite result. Fix it.

 - Fail nicely when the remote swap_reader_page() returns an error

   Currently, if the swap_reader_page() of a remote buffer fails, it
   triggers a WARN_ON_ONCE() and continues normally. Instead, have it
   exit with an error and a pr_warn() print instead of a full WARNING.

* tag 'trace-v7.3-2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace:
  ring-buffer: Stop remote reader update when page swap fails
  tracing: Fix retry exhaustion in simple ring buffer reader swap
  tracing/user_events: Clear copied tracing state before fork duplication
  samples/ftrace: Fix kthread_stop() on ERR_PTR in ftrace-direct-multi-modify
  samples/ftrace: Fix kthread_stop() on ERR_PTR in ftrace-direct-modify
  eventfs: Initialize ei->children and ei->list in init_ei()
  tracing: Fix use-after-free in trace_pipe read on sub-buffer order change
  tracing: Fix crash passing ERR_PTR to kthread_stop()
  tracing: Fix use-after-free with same-name named triggers
  tracing: Fix logged instance name on creation failure

1 files changed, 406 insertions, 0 deletions

diff --git a/drivers/acpi/acpi_extlog.c b/drivers/acpi/acpi_extlog.c
new file mode 100644
index 000000000..7ad3b3601
--- /dev/null
+++ b/drivers/acpi/acpi_extlog.c
@@ -0,0 +1,406 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Extended Error Log driver
+ *
+ * Copyright (C) 2013 Intel Corp.
+ * Author: Chen, Gong <gong.chen@intel.com>
+ */
+
+#include <linux/module.h>
+#include <linux/acpi.h>
+#include <linux/cper.h>
+#include <linux/ratelimit.h>
+#include <linux/edac.h>
+#include <linux/ras.h>
+#include <cxl/event.h>
+#include <acpi/ghes.h>
+#include <asm/cpu.h>
+#include <asm/mce.h>
+#include <asm/msr.h>
+
+#include "apei/apei-internal.h"
+#include <ras/ras_event.h>
+
+#define EXT_ELOG_ENTRY_MASK	GENMASK_ULL(51, 0) /* elog entry address mask */
+
+#define EXTLOG_DSM_REV		0x0
+#define	EXTLOG_FN_ADDR		0x1
+
+#define FLAG_OS_OPTIN		BIT(0)
+#define ELOG_ENTRY_VALID	(1ULL<<63)
+#define ELOG_ENTRY_LEN		0x1000
+
+#define EMCA_BUG \
+	"Can not request iomem region <0x%016llx-0x%016llx> - eMCA disabled\n"
+
+struct extlog_l1_head {
+	u32 ver;	/* Header Version */
+	u32 hdr_len;	/* Header Length */
+	u64 total_len;	/* entire L1 Directory length including this header */
+	u64 elog_base;	/* MCA Error Log Directory base address */
+	u64 elog_len;	/* MCA Error Log Directory length */
+	u32 flags;	/* bit 0 - OS/VMM Opt-in */
+	u8  rev0[12];
+	u32 entries;	/* Valid L1 Directory entries per logical processor */
+	u8  rev1[12];
+};
+
+static u8 extlog_dsm_uuid[] __initdata = "663E35AF-CC10-41A4-88EA-5470AF055295";
+
+/* L1 table related physical address */
+static u64 elog_base;
+static size_t elog_size;
+static u64 l1_dirbase;
+static size_t l1_size;
+
+/* L1 table related virtual address */
+static void __iomem *extlog_l1_addr;
+static void __iomem *elog_addr;
+
+static void *elog_buf;
+
+static u64 *l1_entry_base;
+static u32 l1_percpu_entry;
+
+#define ELOG_IDX(cpu, bank) \
+	(cpu_physical_id(cpu) * l1_percpu_entry + (bank))
+
+#define ELOG_ENTRY_DATA(idx) \
+	(*(l1_entry_base + (idx)))
+
+#define ELOG_ENTRY_ADDR(phyaddr) \
+	(phyaddr - elog_base + (u8 *)elog_addr)
+
+static struct acpi_hest_generic_status *extlog_elog_entry_check(int cpu, int bank)
+{
+	int idx;
+	u64 data;
+	struct acpi_hest_generic_status *estatus;
+
+	WARN_ON(cpu < 0);
+	idx = ELOG_IDX(cpu, bank);
+	data = ELOG_ENTRY_DATA(idx);
+	if ((data & ELOG_ENTRY_VALID) == 0)
+		return NULL;
+
+	data &= EXT_ELOG_ENTRY_MASK;
+	estatus = (struct acpi_hest_generic_status *)ELOG_ENTRY_ADDR(data);
+
+	/* if no valid data in elog entry, just return */
+	if (estatus->block_status == 0)
+		return NULL;
+
+	return estatus;
+}
+
+static void __print_extlog_rcd(const char *pfx,
+			       struct acpi_hest_generic_status *estatus, int cpu)
+{
+	static atomic_t seqno;
+	unsigned int curr_seqno;
+	char pfx_seq[64];
+
+	if (!pfx) {
+		if (estatus->error_severity <= CPER_SEV_CORRECTED)
+			pfx = KERN_INFO;
+		else
+			pfx = KERN_ERR;
+	}
+	curr_seqno = atomic_inc_return(&seqno);
+	snprintf(pfx_seq, sizeof(pfx_seq), "%s{%u}", pfx, curr_seqno);
+	printk("%s""Hardware error detected on CPU%d\n", pfx_seq, cpu);
+	cper_estatus_print(pfx_seq, estatus);
+}
+
+static int print_extlog_rcd(const char *pfx,
+			    struct acpi_hest_generic_status *estatus, int cpu)
+{
+	/* Not more than 2 messages every 5 seconds */
+	static DEFINE_RATELIMIT_STATE(ratelimit_corrected, 5*HZ, 2);
+	static DEFINE_RATELIMIT_STATE(ratelimit_uncorrected, 5*HZ, 2);
+	struct ratelimit_state *ratelimit;
+
+	if (estatus->error_severity == CPER_SEV_CORRECTED ||
+	    (estatus->error_severity == CPER_SEV_INFORMATIONAL))
+		ratelimit = &ratelimit_corrected;
+	else
+		ratelimit = &ratelimit_uncorrected;
+	if (__ratelimit(ratelimit)) {
+		__print_extlog_rcd(pfx, estatus, cpu);
+		return 0;
+	}
+
+	return 1;
+}
+
+static void extlog_print_pcie(struct cper_sec_pcie *pcie_err,
+			      int severity)
+{
+#ifdef ACPI_APEI_PCIEAER
+	struct aer_capability_regs *aer;
+	struct pci_dev *pdev;
+	unsigned int devfn;
+	unsigned int bus;
+	int aer_severity;
+	int domain;
+
+	if (!(pcie_err->validation_bits & CPER_PCIE_VALID_DEVICE_ID &&
+	      pcie_err->validation_bits & CPER_PCIE_VALID_AER_INFO))
+		return;
+
+	aer_severity = cper_severity_to_aer(severity);
+	aer = (struct aer_capability_regs *)pcie_err->aer_info;
+	domain = pcie_err->device_id.segment;
+	bus = pcie_err->device_id.bus;
+	devfn = PCI_DEVFN(pcie_err->device_id.device,
+			  pcie_err->device_id.function);
+	pdev = pci_get_domain_bus_and_slot(domain, bus, devfn);
+	if (!pdev)
+		return;
+
+	pci_print_aer(pdev, aer_severity, aer);
+	pci_dev_put(pdev);
+#endif
+}
+
+static void
+extlog_cxl_cper_handle_prot_err(struct cxl_cper_sec_prot_err *prot_err,
+				int severity)
+{
+#ifdef ACPI_APEI_PCIEAER
+	struct cxl_cper_prot_err_work_data wd;
+
+	if (cxl_cper_sec_prot_err_valid(prot_err))
+		return;
+
+	if (cxl_cper_setup_prot_err_work_data(&wd, prot_err, severity))
+		return;
+
+	cxl_cper_handle_prot_err(&wd);
+#endif
+}
+
+static int extlog_print(struct notifier_block *nb, unsigned long val,
+			void *data)
+{
+	struct mce *mce = (struct mce *)data;
+	int	bank = mce->bank;
+	int	cpu = mce->extcpu;
+	struct acpi_hest_generic_status *estatus, *tmp;
+	struct acpi_hest_generic_data *gdata;
+	const guid_t *fru_id;
+	char *fru_text;
+	guid_t *sec_type;
+	static u32 err_seq;
+
+	estatus = extlog_elog_entry_check(cpu, bank);
+	if (!estatus)
+		return NOTIFY_DONE;
+
+	if (mce->kflags & MCE_HANDLED_CEC) {
+		estatus->block_status = 0;
+		return NOTIFY_DONE;
+	}
+
+	memcpy(elog_buf, (void *)estatus, ELOG_ENTRY_LEN);
+	/* clear record status to enable BIOS to update it again */
+	estatus->block_status = 0;
+
+	tmp = (struct acpi_hest_generic_status *)elog_buf;
+
+	if (!ras_userspace_consumers()) {
+		print_extlog_rcd(NULL, tmp, cpu);
+		goto out;
+	}
+
+	/* log event via trace */
+	err_seq++;
+	apei_estatus_for_each_section(tmp, gdata) {
+		if (gdata->validation_bits & CPER_SEC_VALID_FRU_ID)
+			fru_id = (guid_t *)gdata->fru_id;
+		else
+			fru_id = &guid_null;
+		if (gdata->validation_bits & CPER_SEC_VALID_FRU_TEXT)
+			fru_text = gdata->fru_text;
+		else
+			fru_text = "";
+		sec_type = (guid_t *)gdata->section_type;
+		if (guid_equal(sec_type, &CPER_SEC_PLATFORM_MEM)) {
+			struct cper_sec_mem_err *mem = acpi_hest_get_payload(gdata);
+
+			if (gdata->error_data_length >= sizeof(*mem))
+				trace_extlog_mem_event(mem, err_seq, fru_id, fru_text,
+						       (u8)gdata->error_severity);
+		} else if (guid_equal(sec_type, &CPER_SEC_CXL_PROT_ERR)) {
+			struct cxl_cper_sec_prot_err *prot_err =
+				acpi_hest_get_payload(gdata);
+
+			extlog_cxl_cper_handle_prot_err(prot_err,
+							gdata->error_severity);
+		} else if (guid_equal(sec_type, &CPER_SEC_PCIE)) {
+			struct cper_sec_pcie *pcie_err = acpi_hest_get_payload(gdata);
+
+			extlog_print_pcie(pcie_err, gdata->error_severity);
+		} else {
+			void *err = acpi_hest_get_payload(gdata);
+
+			log_non_standard_event(sec_type, fru_id, fru_text,
+					       gdata->error_severity, err,
+					       gdata->error_data_length);
+		}
+	}
+
+out:
+	mce->kflags |= MCE_HANDLED_EXTLOG;
+	return NOTIFY_OK;
+}
+
+static bool __init extlog_get_l1addr(void)
+{
+	guid_t guid;
+	acpi_handle handle;
+	union acpi_object *obj;
+
+	if (guid_parse(extlog_dsm_uuid, &guid))
+		return false;
+	if (ACPI_FAILURE(acpi_get_handle(NULL, "\\_SB", &handle)))
+		return false;
+	if (!acpi_check_dsm(handle, &guid, EXTLOG_DSM_REV, 1 << EXTLOG_FN_ADDR))
+		return false;
+	obj = acpi_evaluate_dsm_typed(handle, &guid, EXTLOG_DSM_REV,
+				      EXTLOG_FN_ADDR, NULL, ACPI_TYPE_INTEGER);
+	if (!obj) {
+		return false;
+	} else {
+		l1_dirbase = obj->integer.value;
+		ACPI_FREE(obj);
+	}
+
+	/* Spec says L1 directory must be 4K aligned, bail out if it isn't */
+	if (l1_dirbase & ((1 << 12) - 1)) {
+		pr_warn(FW_BUG "L1 Directory is invalid at physical %llx\n",
+			l1_dirbase);
+		return false;
+	}
+
+	return true;
+}
+static struct notifier_block extlog_mce_dec = {
+	.notifier_call	= extlog_print,
+	.priority	= MCE_PRIO_EXTLOG,
+};
+
+static int __init extlog_init(void)
+{
+	struct extlog_l1_head *l1_head;
+	void __iomem *extlog_l1_hdr;
+	size_t l1_hdr_size;
+	struct resource *r;
+	u64 cap;
+	int rc;
+
+	if (rdmsrq_safe(MSR_IA32_MCG_CAP, &cap) ||
+	    !(cap & MCG_ELOG_P) ||
+	    !extlog_get_l1addr())
+		return -ENODEV;
+
+	rc = -EINVAL;
+	/* get L1 header to fetch necessary information */
+	l1_hdr_size = sizeof(struct extlog_l1_head);
+	r = request_mem_region(l1_dirbase, l1_hdr_size, "L1 DIR HDR");
+	if (!r) {
+		pr_warn(FW_BUG EMCA_BUG,
+			(unsigned long long)l1_dirbase,
+			(unsigned long long)l1_dirbase + l1_hdr_size);
+		goto err;
+	}
+
+	extlog_l1_hdr = acpi_os_map_iomem(l1_dirbase, l1_hdr_size);
+	if (!extlog_l1_hdr) {
+		rc = -ENOMEM;
+		goto err_release_l1_hdr;
+	}
+	l1_head = (struct extlog_l1_head *)extlog_l1_hdr;
+	l1_size = l1_head->total_len;
+	l1_percpu_entry = l1_head->entries;
+	elog_base = l1_head->elog_base;
+	elog_size = l1_head->elog_len;
+	acpi_os_unmap_iomem(extlog_l1_hdr, l1_hdr_size);
+	release_mem_region(l1_dirbase, l1_hdr_size);
+
+	/* remap L1 header again based on completed information */
+	r = request_mem_region(l1_dirbase, l1_size, "L1 Table");
+	if (!r) {
+		pr_warn(FW_BUG EMCA_BUG,
+			(unsigned long long)l1_dirbase,
+			(unsigned long long)l1_dirbase + l1_size);
+		goto err;
+	}
+	extlog_l1_addr = acpi_os_map_iomem(l1_dirbase, l1_size);
+	if (!extlog_l1_addr) {
+		rc = -ENOMEM;
+		goto err_release_l1_dir;
+	}
+	l1_entry_base = (u64 *)((u8 *)extlog_l1_addr + l1_hdr_size);
+
+	/* remap elog table */
+	r = request_mem_region(elog_base, elog_size, "Elog Table");
+	if (!r) {
+		pr_warn(FW_BUG EMCA_BUG,
+			(unsigned long long)elog_base,
+			(unsigned long long)elog_base + elog_size);
+		goto err_release_l1_dir;
+	}
+	elog_addr = acpi_os_map_iomem(elog_base, elog_size);
+	if (!elog_addr) {
+		rc = -ENOMEM;
+		goto err_release_elog;
+	}
+
+	rc = -ENOMEM;
+	/* allocate buffer to save elog record */
+	elog_buf = kmalloc(ELOG_ENTRY_LEN, GFP_KERNEL);
+	if (elog_buf == NULL)
+		goto err_release_elog;
+
+	mce_register_decode_chain(&extlog_mce_dec);
+	/* enable OS to be involved to take over management from BIOS */
+	((struct extlog_l1_head *)extlog_l1_addr)->flags |= FLAG_OS_OPTIN;
+
+	return 0;
+
+err_release_elog:
+	if (elog_addr)
+		acpi_os_unmap_iomem(elog_addr, elog_size);
+	release_mem_region(elog_base, elog_size);
+err_release_l1_dir:
+	if (extlog_l1_addr)
+		acpi_os_unmap_iomem(extlog_l1_addr, l1_size);
+	release_mem_region(l1_dirbase, l1_size);
+err_release_l1_hdr:
+	release_mem_region(l1_dirbase, l1_hdr_size);
+err:
+	pr_warn(FW_BUG "Extended error log disabled because of problems parsing f/w tables\n");
+	return rc;
+}
+
+static void __exit extlog_exit(void)
+{
+	mce_unregister_decode_chain(&extlog_mce_dec);
+	if (extlog_l1_addr) {
+		((struct extlog_l1_head *)extlog_l1_addr)->flags &= ~FLAG_OS_OPTIN;
+		acpi_os_unmap_iomem(extlog_l1_addr, l1_size);
+	}
+	if (elog_addr)
+		acpi_os_unmap_iomem(elog_addr, elog_size);
+	release_mem_region(elog_base, elog_size);
+	release_mem_region(l1_dirbase, l1_size);
+	kfree(elog_buf);
+}
+
+module_init(extlog_init);
+module_exit(extlog_exit);
+
+MODULE_AUTHOR("Chen, Gong <gong.chen@intel.com>");
+MODULE_DESCRIPTION("Extended MCA Error Log Driver");
+MODULE_LICENSE("GPL");