powerpc/pseries: Read/Write oops nvram partition via pstore

IBM's p series machines provide persistent storage for LPARs through NVRAM.
NVRAM's lnx,oops-log partition is used to log oops messages.
Currently the kernel provides the contents of p-series NVRAM only as a
simple stream of bytes via /dev/nvram, which must be interpreted in user
space by the nvram command in the powerpc-utils package.

This patch set exploits the pstore subsystem to expose oops partition in
NVRAM as a separate file in /dev/pstore. For instance, Oops messages will be
stored in a file named [dmesg-nvram-2]. In case pstore registration fails it
will fall back to kmsg_dump mechanism.

This patch will read/write the oops messages from/to this partition via pstore.

Signed-off-by: Jim Keniston <jkenisto@us.ibm.com>
Signed-off-by: Aruna Balakrishnaiah <aruna@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>

diff --git a/arch/powerpc/platforms/pseries/nvram.c b/arch/powerpc/platforms/pseries/nvram.c
index 088f023..9edec8e 100644 (file)
--- a/arch/powerpc/platforms/pseries/nvram.c
+++ b/arch/powerpc/platforms/pseries/nvram.c
@@ -18,6 +18,7 @@
 #include <linux/spinlock.h>
 #include <linux/slab.h>
 #include <linux/kmsg_dump.h>
+#include <linux/pstore.h>
 #include <linux/ctype.h>
 #include <linux/zlib.h>
 #include <asm/uaccess.h>
@@ -127,6 +128,14 @@ static size_t oops_data_sz;
 #define MEM_LEVEL 4
 static struct z_stream_s stream;
 
+#ifdef CONFIG_PSTORE
+static enum pstore_type_id nvram_type_ids[] = {
+       PSTORE_TYPE_DMESG,
+       -1
+};
+static int read_type;
+#endif
+
 static ssize_t pSeries_nvram_read(char *buf, size_t count, loff_t *index)
 {
        unsigned int i;
@@ -430,6 +439,149 @@ static int __init pseries_nvram_init_os_partition(struct nvram_os_partition
        return 0;
 }
 
+/*
+ * Are we using the ibm,rtas-log for oops/panic reports?  And if so,
+ * would logging this oops/panic overwrite an RTAS event that rtas_errd
+ * hasn't had a chance to read and process?  Return 1 if so, else 0.
+ *
+ * We assume that if rtas_errd hasn't read the RTAS event in
+ * NVRAM_RTAS_READ_TIMEOUT seconds, it's probably not going to.
+ */
+static int clobbering_unread_rtas_event(void)
+{
+       return (oops_log_partition.index == rtas_log_partition.index
+               && last_unread_rtas_event
+               && get_seconds() - last_unread_rtas_event <=
+                                               NVRAM_RTAS_READ_TIMEOUT);
+}
+
+#ifdef CONFIG_PSTORE
+static int nvram_pstore_open(struct pstore_info *psi)
+{
+       /* Reset the iterator to start reading partitions again */
+       read_type = -1;
+       return 0;
+}
+
+/**
+ * nvram_pstore_write - pstore write callback for nvram
+ * @type:               Type of message logged
+ * @reason:             reason behind dump (oops/panic)
+ * @id:                 identifier to indicate the write performed
+ * @part:               pstore writes data to registered buffer in parts,
+ *                      part number will indicate the same.
+ * @count:              Indicates oops count
+ * @size:               number of bytes written to the registered buffer
+ * @psi:                registered pstore_info structure
+ *
+ * Called by pstore_dump() when an oops or panic report is logged in the
+ * printk buffer.
+ * Returns 0 on successful write.
+ */
+static int nvram_pstore_write(enum pstore_type_id type,
+                               enum kmsg_dump_reason reason,
+                               u64 *id, unsigned int part, int count,
+                               size_t size, struct pstore_info *psi)
+{
+       int rc;
+       struct oops_log_info *oops_hdr = (struct oops_log_info *) oops_buf;
+
+       /* part 1 has the recent messages from printk buffer */
+       if (part > 1 || type != PSTORE_TYPE_DMESG ||
+                               clobbering_unread_rtas_event())
+               return -1;
+
+       oops_hdr->version = OOPS_HDR_VERSION;
+       oops_hdr->report_length = (u16) size;
+       oops_hdr->timestamp = get_seconds();
+       rc = nvram_write_os_partition(&oops_log_partition, oops_buf,
+               (int) (sizeof(*oops_hdr) + size), ERR_TYPE_KERNEL_PANIC,
+               count);
+
+       if (rc != 0)
+               return rc;
+
+       *id = part;
+       return 0;
+}
+
+/*
+ * Reads the oops/panic report.
+ * Returns the length of the data we read from each partition.
+ * Returns 0 if we've been called before.
+ */
+static ssize_t nvram_pstore_read(u64 *id, enum pstore_type_id *type,
+                               int *count, struct timespec *time, char **buf,
+                               struct pstore_info *psi)
+{
+       struct oops_log_info *oops_hdr;
+       unsigned int err_type, id_no;
+       struct nvram_os_partition *part = NULL;
+       char *buff = NULL;
+
+       read_type++;
+
+       switch (nvram_type_ids[read_type]) {
+       case PSTORE_TYPE_DMESG:
+               part = &oops_log_partition;
+               *type = PSTORE_TYPE_DMESG;
+               break;
+       default:
+               return 0;
+       }
+
+       buff = kmalloc(part->size, GFP_KERNEL);
+
+       if (!buff)
+               return -ENOMEM;
+
+       if (nvram_read_partition(part, buff, part->size, &err_type, &id_no)) {
+               kfree(buff);
+               return 0;
+       }
+
+       *count = 0;
+       *id = id_no;
+       oops_hdr = (struct oops_log_info *)buff;
+       *buf = buff + sizeof(*oops_hdr);
+       time->tv_sec = oops_hdr->timestamp;
+       time->tv_nsec = 0;
+       return oops_hdr->report_length;
+}
+
+static struct pstore_info nvram_pstore_info = {
+       .owner = THIS_MODULE,
+       .name = "nvram",
+       .open = nvram_pstore_open,
+       .read = nvram_pstore_read,
+       .write = nvram_pstore_write,
+};
+
+static int nvram_pstore_init(void)
+{
+       int rc = 0;
+
+       nvram_pstore_info.buf = oops_data;
+       nvram_pstore_info.bufsize = oops_data_sz;
+
+       rc = pstore_register(&nvram_pstore_info);
+       if (rc != 0)
+               pr_err("nvram: pstore_register() failed, defaults to "
+                               "kmsg_dump; returned %d\n", rc);
+       else
+               /*TODO: Support compression when pstore is configured */
+               pr_info("nvram: Compression of oops text supported only when "
+                               "pstore is not configured");
+
+       return rc;
+}
+#else
+static int nvram_pstore_init(void)
+{
+       return -1;
+}
+#endif
+
 static void __init nvram_init_oops_partition(int rtas_partition_exists)
 {
        int rc;
@@ -453,6 +605,11 @@ static void __init nvram_init_oops_partition(int rtas_partition_exists)
        oops_data = oops_buf + sizeof(struct oops_log_info);
        oops_data_sz = oops_log_partition.size - sizeof(struct oops_log_info);
 
+       rc = nvram_pstore_init();
+
+       if (!rc)
+               return;
+
        /*
         * Figure compression (preceded by elimination of each line's <n>
         * severity prefix) will reduce the oops/panic report to at most
@@ -525,21 +682,6 @@ int __init pSeries_nvram_init(void)
        return 0;
 }
 
-/*
- * Are we using the ibm,rtas-log for oops/panic reports?  And if so,
- * would logging this oops/panic overwrite an RTAS event that rtas_errd
- * hasn't had a chance to read and process?  Return 1 if so, else 0.
- *
- * We assume that if rtas_errd hasn't read the RTAS event in
- * NVRAM_RTAS_READ_TIMEOUT seconds, it's probably not going to.
- */
-static int clobbering_unread_rtas_event(void)
-{
-       return (oops_log_partition.index == rtas_log_partition.index
-               && last_unread_rtas_event
-               && get_seconds() - last_unread_rtas_event <=
-                                               NVRAM_RTAS_READ_TIMEOUT);
-}
 
 /* Derived from logfs_compress() */
 static int nvram_compress(const void *in, void *out, size_t inlen,