x86/microcode: Scan the initramfs payload for microcode blob

The Linux kernel is able to update the microcode during early bootup
via inspection of the initramfs blob to see if there is an cpio image
with certain microcode files. Linux is able to function with two (or
more) cpio archives in the initrd b/c it unpacks all of the cpio
archives.

The format of the early initramfs is nicely documented in Linux's
Documentation/x86/early-microcode.txt:

Early load microcode
====================
By Fenghua Yu <fenghua.yu@intel.com>

Kernel can update microcode in early phase of boot time. Loading microcode early
can fix CPU issues before they are observed during kernel boot time.

Microcode is stored in an initrd file. The microcode is read from the initrd
file and loaded to CPUs during boot time.

The format of the combined initrd image is microcode in cpio format followed by
the initrd image (maybe compressed). Kernel parses the combined initrd image
during boot time. The microcode file in cpio name space is:
kernel/x86/microcode/GenuineIntel.bin

During BSP boot (before SMP starts), if the kernel finds the microcode file in
the initrd file, it parses the microcode and saves matching microcode in memory.
If matching microcode is found, it will be uploaded in BSP and later on in all
APs.

The cached microcode patch is applied when CPUs resume from a sleep state.

There are two legacy user space interfaces to load microcode, either through
/dev/cpu/microcode or through /sys/devices/system/cpu/microcode/reload file
in sysfs.

In addition to these two legacy methods, the early loading method described
here is the third method with which microcode can be uploaded to a system's
CPUs.

The following example script shows how to generate a new combined initrd file in
/boot/initrd-3.5.0.ucode.img with original microcode microcode.bin and
original initrd image /boot/initrd-3.5.0.img.

mkdir initrd
cd initrd
mkdir kernel
mkdir kernel/x86
mkdir kernel/x86/microcode
cp ../microcode.bin kernel/x86/microcode/GenuineIntel.bin
find .|cpio -oc >../ucode.cpio
cd ..
cat ucode.cpio /boot/initrd-3.5.0.img >/boot/initrd-3.5.0.ucode.img

As such this code inspects the initrd to see if the microcode
signatures are present and if so updates the hypervisor.

The option to turn this scan on/off is gated by the 'ucode'
parameter. The options are now:
 'scan'      Scan for the microcode in any multiboot payload.
 <index>     Attempt to load microcode blob (not the cpio archive
             format) from the multiboot payload number.

This option alters slightly the 'ucode' parameter by only allowing
either parameter:
  ucode=[<index>|scan]

Implementation wise the ucode_blob is defined as __initdata.
That is OK from the viewpoint of suspend/resume as the the underlaying
architecture microcode (microcode_intel or microcode_amd) end up saving
the blob in 'struct ucode_cpu_info' which is a per-cpu data
structure (see ucode_cpu_info). They end up saving it when doing the
pre-SMP (for CPU0) and SMP (for the rest) microcode loading.

Naturally if one does a hypercall to update the microcode and it is
newer, then the old per-cpu data is replaced.

Signed-off-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Acked-by: Keir Fraser <keir@xen.org>

2 files changed, 152 insertions, 1 deletions

diff --git a/xen/common/Makefile b/xen/common/Makefile
index 5486140888..6da46513e2 100644
--- a/xen/common/Makefile
+++ b/xen/common/Makefile
@@ -49,7 +49,7 @@ obj-y += radix-tree.o
 obj-y += rbtree.o
 obj-y += lzo.o
 
-obj-bin-$(CONFIG_X86) += $(foreach n,decompress bunzip2 unxz unlzma unlzo,$(n).init.o)
+obj-bin-$(CONFIG_X86) += $(foreach n,decompress bunzip2 unxz unlzma unlzo earlycpio,$(n).init.o)
 
 obj-$(perfc)       += perfc.o
 obj-$(crash_debug) += gdbstub.o
diff --git a/xen/common/earlycpio.c b/xen/common/earlycpio.c
new file mode 100644
index 0000000000..5e5414242a
--- /dev/null
+++ b/xen/common/earlycpio.c
@@ -0,0 +1,151 @@
+/* ----------------------------------------------------------------------- *
+ *
+ *   Copyright 2012 Intel Corporation; author H. Peter Anvin
+ *
+ *   This file is part of the Linux kernel, and is made available
+ *   under the terms of the GNU General Public License version 2, as
+ *   published by the Free Software Foundation.
+ *
+ *   This program is distributed in the hope it will be useful, but
+ *   WITHOUT ANY WARRANTY; without even the implied warranty of
+ *   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ *   General Public License for more details.
+ *
+ * ----------------------------------------------------------------------- */
+
+/*
+ * earlycpio.c
+ *
+ * Find a specific cpio member; must precede any compressed content.
+ * This is used to locate data items in the initramfs used by the
+ * kernel itself during early boot (before the main initramfs is
+ * decompressed.)  It is the responsibility of the initramfs creator
+ * to ensure that these items are uncompressed at the head of the
+ * blob.  Depending on the boot loader or package tool that may be a
+ * separate file or part of the same file.
+ */
+
+#include <xen/config.h>
+#include <xen/init.h>
+#include <xen/lib.h>
+#include <xen/string.h>
+#include <xen/earlycpio.h>
+
+#define ALIGN(x, a) ((x + (a) - 1) & ~((a) - 1))
+#define PTR_ALIGN(p, a)         ((typeof(p))ALIGN((unsigned long)(p), (a)))
+
+enum cpio_fields {
+	C_MAGIC,
+	C_INO,
+	C_MODE,
+	C_UID,
+	C_GID,
+	C_NLINK,
+	C_MTIME,
+	C_FILESIZE,
+	C_MAJ,
+	C_MIN,
+	C_RMAJ,
+	C_RMIN,
+	C_NAMESIZE,
+	C_CHKSUM,
+	C_NFIELDS
+};
+
+/**
+ * cpio_data find_cpio_data - Search for files in an uncompressed cpio
+ * @path:   The directory to search for, including a slash at the end
+ * @data:   Pointer to the the cpio archive or a header inside
+ * @len:    Remaining length of the cpio based on data pointer
+ * @offset: When a matching file is found, this is the offset to the
+ *          beginning of the cpio. It can be used to iterate through
+ *          the cpio to find all files inside of a directory path
+ *
+ * @return: struct cpio_data containing the address, length and
+ *          filename (with the directory path cut off) of the found file.
+ *          If you search for a filename and not for files in a directory,
+ *          pass the absolute path of the filename in the cpio and make sure
+ *          the match returned an empty filename string.
+ */
+
+struct cpio_data __init find_cpio_data(const char *path, void *data,
+					  size_t len,  long *offset)
+{
+	const size_t cpio_header_len = 8*C_NFIELDS - 2;
+	struct cpio_data cd = { NULL, 0 };
+	const char *p, *dptr, *nptr;
+	unsigned int ch[C_NFIELDS], *chp, v;
+	unsigned char c, x;
+	size_t mypathsize = strlen(path);
+	int i, j;
+
+	p = data;
+
+	while (len > cpio_header_len) {
+		if (!*p) {
+			/* All cpio headers need to be 4-byte aligned */
+			p += 4;
+			len -= 4;
+			continue;
+		}
+
+		j = 6;		/* The magic field is only 6 characters */
+		chp = ch;
+		for (i = C_NFIELDS; i; i--) {
+			v = 0;
+			while (j--) {
+				v <<= 4;
+				c = *p++;
+
+				x = c - '0';
+				if (x < 10) {
+					v += x;
+					continue;
+				}
+
+				x = (c | 0x20) - 'a';
+				if (x < 6) {
+					v += x + 10;
+					continue;
+				}
+
+				goto quit; /* Invalid hexadecimal */
+			}
+			*chp++ = v;
+			j = 8;	/* All other fields are 8 characters */
+		}
+
+		if ((ch[C_MAGIC] - 0x070701) > 1)
+			goto quit; /* Invalid magic */
+
+		len -= cpio_header_len;
+
+		dptr = PTR_ALIGN(p + ch[C_NAMESIZE], 4);
+		nptr = PTR_ALIGN(dptr + ch[C_FILESIZE], 4);
+
+		if (nptr > p + len || dptr < p || nptr < dptr)
+			goto quit; /* Buffer overrun */
+
+		if ((ch[C_MODE] & 0170000) == 0100000 &&
+		    ch[C_NAMESIZE] >= mypathsize &&
+		    !memcmp(p, path, mypathsize)) {
+			*offset = (long)nptr - (long)data;
+			if (ch[C_NAMESIZE] - mypathsize >= MAX_CPIO_FILE_NAME) {
+				printk(
+				"File %s exceeding MAX_CPIO_FILE_NAME [%d]\n",
+				p, MAX_CPIO_FILE_NAME);
+			}
+			if (ch[C_NAMESIZE] - 1 /* includes \0 */ == mypathsize) {
+				cd.data = (void *)dptr;
+				cd.size = ch[C_FILESIZE];
+				return cd; /* Found it! */
+			}
+		}
+		len -= (nptr - p);
+		p = nptr;
+	}
+
+quit:
+	return cd;
+}
+