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, 303 insertions, 0 deletions

diff --git a/drivers/edac/pasemi_edac.c b/drivers/edac/pasemi_edac.c
new file mode 100644
index 000000000..1a1c3296c
--- /dev/null
+++ b/drivers/edac/pasemi_edac.c
@@ -0,0 +1,303 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2006-2007 PA Semi, Inc
+ *
+ * Author: Egor Martovetsky <egor@pasemi.com>
+ * Maintained by: Olof Johansson <olof@lixom.net>
+ *
+ * Driver for the PWRficient onchip memory controllers
+ */
+
+
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/pci.h>
+#include <linux/pci_ids.h>
+#include <linux/edac.h>
+#include "edac_module.h"
+
+#define MODULE_NAME "pasemi_edac"
+
+#define MCCFG_MCEN				0x300
+#define   MCCFG_MCEN_MMC_EN			0x00000001
+#define MCCFG_ERRCOR				0x388
+#define   MCCFG_ERRCOR_RNK_FAIL_DET_EN		0x00000100
+#define   MCCFG_ERRCOR_ECC_GEN_EN		0x00000010
+#define   MCCFG_ERRCOR_ECC_CRR_EN		0x00000001
+#define MCCFG_SCRUB				0x384
+#define   MCCFG_SCRUB_RGLR_SCRB_EN		0x00000001
+#define MCDEBUG_ERRCTL1				0x728
+#define   MCDEBUG_ERRCTL1_RFL_LOG_EN		0x00080000
+#define   MCDEBUG_ERRCTL1_MBE_LOG_EN		0x00040000
+#define   MCDEBUG_ERRCTL1_SBE_LOG_EN		0x00020000
+#define MCDEBUG_ERRSTA				0x730
+#define   MCDEBUG_ERRSTA_RFL_STATUS		0x00000004
+#define   MCDEBUG_ERRSTA_MBE_STATUS		0x00000002
+#define   MCDEBUG_ERRSTA_SBE_STATUS		0x00000001
+#define MCDEBUG_ERRCNT1				0x734
+#define   MCDEBUG_ERRCNT1_SBE_CNT_OVRFLO	0x00000080
+#define MCDEBUG_ERRLOG1A			0x738
+#define   MCDEBUG_ERRLOG1A_MERR_TYPE_M		0x30000000
+#define   MCDEBUG_ERRLOG1A_MERR_TYPE_NONE	0x00000000
+#define   MCDEBUG_ERRLOG1A_MERR_TYPE_SBE	0x10000000
+#define   MCDEBUG_ERRLOG1A_MERR_TYPE_MBE	0x20000000
+#define   MCDEBUG_ERRLOG1A_MERR_TYPE_RFL	0x30000000
+#define   MCDEBUG_ERRLOG1A_MERR_BA_M		0x00700000
+#define   MCDEBUG_ERRLOG1A_MERR_BA_S		20
+#define   MCDEBUG_ERRLOG1A_MERR_CS_M		0x00070000
+#define   MCDEBUG_ERRLOG1A_MERR_CS_S		16
+#define   MCDEBUG_ERRLOG1A_SYNDROME_M		0x0000ffff
+#define MCDRAM_RANKCFG				0x114
+#define   MCDRAM_RANKCFG_EN			0x00000001
+#define   MCDRAM_RANKCFG_TYPE_SIZE_M		0x000001c0
+#define   MCDRAM_RANKCFG_TYPE_SIZE_S		6
+
+#define PASEMI_EDAC_NR_CSROWS			8
+#define PASEMI_EDAC_NR_CHANS			1
+#define PASEMI_EDAC_ERROR_GRAIN			64
+
+static int last_page_in_mmc;
+static int system_mmc_id;
+
+
+static u32 pasemi_edac_get_error_info(struct mem_ctl_info *mci)
+{
+	struct pci_dev *pdev = to_pci_dev(mci->pdev);
+	u32 tmp;
+
+	pci_read_config_dword(pdev, MCDEBUG_ERRSTA,
+			      &tmp);
+
+	tmp &= (MCDEBUG_ERRSTA_RFL_STATUS | MCDEBUG_ERRSTA_MBE_STATUS
+		| MCDEBUG_ERRSTA_SBE_STATUS);
+
+	if (tmp) {
+		if (tmp & MCDEBUG_ERRSTA_SBE_STATUS)
+			pci_write_config_dword(pdev, MCDEBUG_ERRCNT1,
+					       MCDEBUG_ERRCNT1_SBE_CNT_OVRFLO);
+		pci_write_config_dword(pdev, MCDEBUG_ERRSTA, tmp);
+	}
+
+	return tmp;
+}
+
+static void pasemi_edac_process_error_info(struct mem_ctl_info *mci, u32 errsta)
+{
+	struct pci_dev *pdev = to_pci_dev(mci->pdev);
+	u32 errlog1a;
+	u32 cs;
+
+	if (!errsta)
+		return;
+
+	pci_read_config_dword(pdev, MCDEBUG_ERRLOG1A, &errlog1a);
+
+	cs = (errlog1a & MCDEBUG_ERRLOG1A_MERR_CS_M) >>
+		MCDEBUG_ERRLOG1A_MERR_CS_S;
+
+	/* uncorrectable/multi-bit errors */
+	if (errsta & (MCDEBUG_ERRSTA_MBE_STATUS |
+		      MCDEBUG_ERRSTA_RFL_STATUS)) {
+		edac_mc_handle_error(HW_EVENT_ERR_UNCORRECTED, mci, 1,
+				     mci->csrows[cs]->first_page, 0, 0,
+				     cs, 0, -1, mci->ctl_name, "");
+	}
+
+	/* correctable/single-bit errors */
+	if (errsta & MCDEBUG_ERRSTA_SBE_STATUS)
+		edac_mc_handle_error(HW_EVENT_ERR_CORRECTED, mci, 1,
+				     mci->csrows[cs]->first_page, 0, 0,
+				     cs, 0, -1, mci->ctl_name, "");
+}
+
+static void pasemi_edac_check(struct mem_ctl_info *mci)
+{
+	u32 errsta;
+
+	errsta = pasemi_edac_get_error_info(mci);
+	if (errsta)
+		pasemi_edac_process_error_info(mci, errsta);
+}
+
+static int pasemi_edac_init_csrows(struct mem_ctl_info *mci,
+				   struct pci_dev *pdev,
+				   enum edac_type edac_mode)
+{
+	struct csrow_info *csrow;
+	struct dimm_info *dimm;
+	u32 rankcfg;
+	int index;
+
+	for (index = 0; index < mci->nr_csrows; index++) {
+		csrow = mci->csrows[index];
+		dimm = csrow->channels[0]->dimm;
+
+		pci_read_config_dword(pdev,
+				      MCDRAM_RANKCFG + (index * 12),
+				      &rankcfg);
+
+		if (!(rankcfg & MCDRAM_RANKCFG_EN))
+			continue;
+
+		switch ((rankcfg & MCDRAM_RANKCFG_TYPE_SIZE_M) >>
+			MCDRAM_RANKCFG_TYPE_SIZE_S) {
+		case 0:
+			dimm->nr_pages = 128 << (20 - PAGE_SHIFT);
+			break;
+		case 1:
+			dimm->nr_pages = 256 << (20 - PAGE_SHIFT);
+			break;
+		case 2:
+		case 3:
+			dimm->nr_pages = 512 << (20 - PAGE_SHIFT);
+			break;
+		case 4:
+			dimm->nr_pages = 1024 << (20 - PAGE_SHIFT);
+			break;
+		case 5:
+			dimm->nr_pages = 2048 << (20 - PAGE_SHIFT);
+			break;
+		default:
+			edac_mc_printk(mci, KERN_ERR,
+				"Unrecognized Rank Config. rankcfg=%u\n",
+				rankcfg);
+			return -EINVAL;
+		}
+
+		csrow->first_page = last_page_in_mmc;
+		csrow->last_page = csrow->first_page + dimm->nr_pages - 1;
+		last_page_in_mmc += dimm->nr_pages;
+		csrow->page_mask = 0;
+		dimm->grain = PASEMI_EDAC_ERROR_GRAIN;
+		dimm->mtype = MEM_DDR;
+		dimm->dtype = DEV_UNKNOWN;
+		dimm->edac_mode = edac_mode;
+	}
+	return 0;
+}
+
+static int pasemi_edac_probe(struct pci_dev *pdev,
+			     const struct pci_device_id *ent)
+{
+	struct mem_ctl_info *mci = NULL;
+	struct edac_mc_layer layers[2];
+	u32 errctl1, errcor, scrub, mcen;
+
+	pci_read_config_dword(pdev, MCCFG_MCEN, &mcen);
+	if (!(mcen & MCCFG_MCEN_MMC_EN))
+		return -ENODEV;
+
+	/*
+	 * We should think about enabling other error detection later on
+	 */
+
+	pci_read_config_dword(pdev, MCDEBUG_ERRCTL1, &errctl1);
+	errctl1 |= MCDEBUG_ERRCTL1_SBE_LOG_EN |
+		MCDEBUG_ERRCTL1_MBE_LOG_EN |
+		MCDEBUG_ERRCTL1_RFL_LOG_EN;
+	pci_write_config_dword(pdev, MCDEBUG_ERRCTL1, errctl1);
+
+	layers[0].type = EDAC_MC_LAYER_CHIP_SELECT;
+	layers[0].size = PASEMI_EDAC_NR_CSROWS;
+	layers[0].is_virt_csrow = true;
+	layers[1].type = EDAC_MC_LAYER_CHANNEL;
+	layers[1].size = PASEMI_EDAC_NR_CHANS;
+	layers[1].is_virt_csrow = false;
+	mci = edac_mc_alloc(system_mmc_id++, ARRAY_SIZE(layers), layers,
+			    0);
+	if (mci == NULL)
+		return -ENOMEM;
+
+	pci_read_config_dword(pdev, MCCFG_ERRCOR, &errcor);
+	errcor |= MCCFG_ERRCOR_RNK_FAIL_DET_EN |
+		MCCFG_ERRCOR_ECC_GEN_EN |
+		MCCFG_ERRCOR_ECC_CRR_EN;
+
+	mci->pdev = &pdev->dev;
+	mci->mtype_cap = MEM_FLAG_DDR | MEM_FLAG_RDDR;
+	mci->edac_ctl_cap = EDAC_FLAG_NONE | EDAC_FLAG_EC | EDAC_FLAG_SECDED;
+	mci->edac_cap = (errcor & MCCFG_ERRCOR_ECC_GEN_EN) ?
+		((errcor & MCCFG_ERRCOR_ECC_CRR_EN) ?
+		 (EDAC_FLAG_EC | EDAC_FLAG_SECDED) : EDAC_FLAG_EC) :
+		EDAC_FLAG_NONE;
+	mci->mod_name = MODULE_NAME;
+	mci->dev_name = pci_name(pdev);
+	mci->ctl_name = "pasemi,pwrficient-mc";
+	mci->edac_check = pasemi_edac_check;
+	mci->ctl_page_to_phys = NULL;
+	pci_read_config_dword(pdev, MCCFG_SCRUB, &scrub);
+	mci->scrub_cap = SCRUB_FLAG_HW_PROG | SCRUB_FLAG_HW_SRC;
+	mci->scrub_mode =
+		((errcor & MCCFG_ERRCOR_ECC_CRR_EN) ? SCRUB_FLAG_HW_SRC : 0) |
+		((scrub & MCCFG_SCRUB_RGLR_SCRB_EN) ? SCRUB_FLAG_HW_PROG : 0);
+
+	if (pasemi_edac_init_csrows(mci, pdev,
+				    (mci->edac_cap & EDAC_FLAG_SECDED) ?
+				    EDAC_SECDED :
+				    ((mci->edac_cap & EDAC_FLAG_EC) ?
+				     EDAC_EC : EDAC_NONE)))
+		goto fail;
+
+	/*
+	 * Clear status
+	 */
+	pasemi_edac_get_error_info(mci);
+
+	if (edac_mc_add_mc(mci))
+		goto fail;
+
+	/* get this far and it's successful */
+	return 0;
+
+fail:
+	edac_mc_free(mci);
+	return -ENODEV;
+}
+
+static void pasemi_edac_remove(struct pci_dev *pdev)
+{
+	struct mem_ctl_info *mci = edac_mc_del_mc(&pdev->dev);
+
+	if (!mci)
+		return;
+
+	edac_mc_free(mci);
+}
+
+
+static const struct pci_device_id pasemi_edac_pci_tbl[] = {
+	{ PCI_DEVICE(PCI_VENDOR_ID_PASEMI, 0xa00a) },
+	{ }
+};
+
+MODULE_DEVICE_TABLE(pci, pasemi_edac_pci_tbl);
+
+static struct pci_driver pasemi_edac_driver = {
+	.name = MODULE_NAME,
+	.probe = pasemi_edac_probe,
+	.remove = pasemi_edac_remove,
+	.id_table = pasemi_edac_pci_tbl,
+};
+
+static int __init pasemi_edac_init(void)
+{
+       /* Ensure that the OPSTATE is set correctly for POLL or NMI */
+       opstate_init();
+
+	return pci_register_driver(&pasemi_edac_driver);
+}
+
+static void __exit pasemi_edac_exit(void)
+{
+	pci_unregister_driver(&pasemi_edac_driver);
+}
+
+module_init(pasemi_edac_init);
+module_exit(pasemi_edac_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Egor Martovetsky <egor@pasemi.com>");
+MODULE_DESCRIPTION("MC support for PA Semi PWRficient memory controller");
+module_param(edac_op_state, int, 0444);
+MODULE_PARM_DESC(edac_op_state, "EDAC Error Reporting state: 0=Poll,1=NMI");
+