Hi,
This series adds DMA operations support to the qemu fw_cfg kernel
module and populates "etc/vmcoreinfo" with vmcoreinfo location
details.
Note: the support for this entry handling has been merged for next
qemu release (2.11)
v5:
- resent to CC kdump people on the paddr_vmcoreinfo_note() export patch
v4:
- export paddr_vmcoreinfo_note() to fix fw_cfg.ko build
- fix build with !CONFIG_CRASH_CORE
- replace the unbounded yield() loop with a usleep_range() loop and a
200ms timeout
- do not write vmcoreinfo entry when running the kdump kernel (D. Hatayama)
- drop the experimental sysfs write support patch from this series
v3: (thanks kbuild)
- add "fw_cfg: fix the command line module name" patch
- fix build of "fw_cfg: add DMA register" with CONFIG_FW_CFG_SYSFS_CMDLINE=y
- fix 'Wshift-count-overflow'
v2:
- use platform device for dma mapping
- add etc/vmcoreinfo patch
- some code cleanups
Marc-André Lureau (5):
fw_cfg: fix the command line module name
fw_cfg: add DMA register
fw_cfg: do DMA read operation
crash: export paddr_vmcoreinfo_note()
fw_cfg: write vmcoreinfo details
drivers/firmware/qemu_fw_cfg.c | 292 +++++++++++++++++++++++++++++++++++++----
kernel/crash_core.c | 1 +
2 files changed, 264 insertions(+), 29 deletions(-)
--
2.15.0.125.g8f49766d64
From 1583890267151428382@xxx Sun Nov 12 19:37:47 +0000 2017
X-GM-THRID: 1583890267151428382
X-Gmail-Labels: Inbox,Category Forums,HistoricalUnread
Modify fw_cfg_read_blob() to use DMA if the device supports it.
Return errors, because the operation may fail.
To avoid polling with unbound amount of time, the DMA operation is
expected to complete within 200ms, or will return ETIME error.
We may want to switch all the *buf addresses to use only kmalloc'ed
buffers (instead of using stack/image addresses with dma=false).
Signed-off-by: Marc-André Lureau <[email protected]>
---
drivers/firmware/qemu_fw_cfg.c | 154 ++++++++++++++++++++++++++++++++++++-----
1 file changed, 137 insertions(+), 17 deletions(-)
diff --git a/drivers/firmware/qemu_fw_cfg.c b/drivers/firmware/qemu_fw_cfg.c
index 1f3e8545dab7..8ce5e49b7c62 100644
--- a/drivers/firmware/qemu_fw_cfg.c
+++ b/drivers/firmware/qemu_fw_cfg.c
@@ -33,6 +33,8 @@
#include <linux/slab.h>
#include <linux/io.h>
#include <linux/ioport.h>
+#include <linux/delay.h>
+#include <linux/dma-mapping.h>
MODULE_AUTHOR("Gabriel L. Somlo <[email protected]>");
MODULE_DESCRIPTION("QEMU fw_cfg sysfs support");
@@ -43,12 +45,26 @@ MODULE_LICENSE("GPL");
#define FW_CFG_ID 0x01
#define FW_CFG_FILE_DIR 0x19
+#define FW_CFG_VERSION_DMA 0x02
+#define FW_CFG_DMA_CTL_ERROR 0x01
+#define FW_CFG_DMA_CTL_READ 0x02
+#define FW_CFG_DMA_CTL_SKIP 0x04
+#define FW_CFG_DMA_CTL_SELECT 0x08
+#define FW_CFG_DMA_CTL_WRITE 0x10
+#define FW_CFG_DMA_TIMEOUT 200 /* ms */
+
/* size in bytes of fw_cfg signature */
#define FW_CFG_SIG_SIZE 4
/* fw_cfg "file name" is up to 56 characters (including terminating nul) */
#define FW_CFG_MAX_FILE_PATH 56
+/* platform device for dma mapping */
+static struct device *dev;
+
+/* fw_cfg revision attribute, in /sys/firmware/qemu_fw_cfg top-level dir. */
+static u32 fw_cfg_rev;
+
/* fw_cfg file directory entry type */
struct fw_cfg_file {
u32 size;
@@ -57,6 +73,12 @@ struct fw_cfg_file {
char name[FW_CFG_MAX_FILE_PATH];
};
+struct fw_cfg_dma {
+ u32 control;
+ u32 length;
+ u64 address;
+} __packed;
+
/* fw_cfg device i/o register addresses */
static bool fw_cfg_is_mmio;
static phys_addr_t fw_cfg_p_base;
@@ -75,12 +97,93 @@ static inline u16 fw_cfg_sel_endianness(u16 key)
return fw_cfg_is_mmio ? cpu_to_be16(key) : cpu_to_le16(key);
}
+static inline bool fw_cfg_dma_enabled(void)
+{
+ return fw_cfg_rev & FW_CFG_VERSION_DMA && fw_cfg_reg_dma;
+}
+
+static bool fw_cfg_wait_for_control(struct fw_cfg_dma *d, unsigned long timeout)
+{
+ ktime_t start;
+ ktime_t stop;
+
+ start = ktime_get();
+ stop = ktime_add(start, ms_to_ktime(timeout));
+
+ do {
+ if ((be32_to_cpu(d->control) & ~FW_CFG_DMA_CTL_ERROR) == 0)
+ return true;
+
+ usleep_range(50, 100);
+ } while (ktime_before(ktime_get(), stop));
+
+ return false;
+}
+
+static ssize_t fw_cfg_dma_transfer(void *address, u32 length, u32 control)
+{
+ dma_addr_t dma_addr = 0;
+ struct fw_cfg_dma *d;
+ dma_addr_t dma;
+ ssize_t ret = length;
+ enum dma_data_direction dir =
+ (control & FW_CFG_DMA_CTL_READ ? DMA_FROM_DEVICE : 0);
+
+ if (address && length) {
+ dma_addr = dma_map_single(dev, address, length, dir);
+ if (dma_mapping_error(NULL, dma_addr)) {
+ WARN(1, "%s: failed to map address\n", __func__);
+ return -EFAULT;
+ }
+ }
+
+ d = kmalloc(sizeof(*d), GFP_KERNEL | GFP_DMA);
+ if (!d) {
+ ret = -ENOMEM;
+ goto end;
+ }
+
+ dma = dma_map_single(dev, d, sizeof(*d), DMA_BIDIRECTIONAL);
+ if (dma_mapping_error(NULL, dma)) {
+ WARN(1, "%s: failed to map fw_cfg_dma\n", __func__);
+ ret = -EFAULT;
+ goto end;
+ }
+
+ *d = (struct fw_cfg_dma) {
+ .address = cpu_to_be64(dma_addr),
+ .length = cpu_to_be32(length),
+ .control = cpu_to_be32(control)
+ };
+
+ iowrite32be((u64)dma >> 32, fw_cfg_reg_dma);
+ iowrite32be(dma, fw_cfg_reg_dma + 4);
+
+ if (!fw_cfg_wait_for_control(d, FW_CFG_DMA_TIMEOUT)) {
+ WARN(1, "%s: timeout", __func__);
+ ret = -ETIME;
+ } else if (be32_to_cpu(d->control) & FW_CFG_DMA_CTL_ERROR) {
+ ret = -EIO;
+ }
+
+ dma_unmap_single(dev, dma, sizeof(*d), DMA_BIDIRECTIONAL);
+
+end:
+ kfree(d);
+ if (dma_addr)
+ dma_unmap_single(dev, dma_addr, length, dir);
+
+ return ret;
+}
+
/* read chunk of given fw_cfg blob (caller responsible for sanity-check) */
-static inline void fw_cfg_read_blob(u16 key,
- void *buf, loff_t pos, size_t count)
+static ssize_t fw_cfg_read_blob(u16 key,
+ void *buf, loff_t pos, size_t count,
+ bool dma)
{
u32 glk = -1U;
acpi_status status;
+ ssize_t ret = count;
/* If we have ACPI, ensure mutual exclusion against any potential
* device access by the firmware, e.g. via AML methods:
@@ -90,17 +193,36 @@ static inline void fw_cfg_read_blob(u16 key,
/* Should never get here */
WARN(1, "fw_cfg_read_blob: Failed to lock ACPI!\n");
memset(buf, 0, count);
- return;
+ return -EBUSY;
}
mutex_lock(&fw_cfg_dev_lock);
- iowrite16(fw_cfg_sel_endianness(key), fw_cfg_reg_ctrl);
- while (pos-- > 0)
- ioread8(fw_cfg_reg_data);
- ioread8_rep(fw_cfg_reg_data, buf, count);
+ if (dma && fw_cfg_dma_enabled()) {
+ if (pos == 0) {
+ ret = fw_cfg_dma_transfer(buf, count, key << 16
+ | FW_CFG_DMA_CTL_SELECT
+ | FW_CFG_DMA_CTL_READ);
+ } else {
+ iowrite16(fw_cfg_sel_endianness(key), fw_cfg_reg_ctrl);
+ ret = fw_cfg_dma_transfer(0, pos, FW_CFG_DMA_CTL_SKIP);
+ if (ret < 0)
+ goto end;
+ ret = fw_cfg_dma_transfer(buf, count,
+ FW_CFG_DMA_CTL_READ);
+ }
+ } else {
+ iowrite16(fw_cfg_sel_endianness(key), fw_cfg_reg_ctrl);
+ while (pos-- > 0)
+ ioread8(fw_cfg_reg_data);
+ ioread8_rep(fw_cfg_reg_data, buf, count);
+ }
+
+end:
mutex_unlock(&fw_cfg_dev_lock);
acpi_release_global_lock(glk);
+
+ return ret;
}
/* clean up fw_cfg device i/o */
@@ -192,7 +314,7 @@ static int fw_cfg_do_platform_probe(struct platform_device *pdev)
#endif
/* verify fw_cfg device signature */
- fw_cfg_read_blob(FW_CFG_SIGNATURE, sig, 0, FW_CFG_SIG_SIZE);
+ fw_cfg_read_blob(FW_CFG_SIGNATURE, sig, 0, FW_CFG_SIG_SIZE, false);
if (memcmp(sig, "QEMU", FW_CFG_SIG_SIZE) != 0) {
fw_cfg_io_cleanup();
return -ENODEV;
@@ -201,9 +323,6 @@ static int fw_cfg_do_platform_probe(struct platform_device *pdev)
return 0;
}
-/* fw_cfg revision attribute, in /sys/firmware/qemu_fw_cfg top-level dir. */
-static u32 fw_cfg_rev;
-
static ssize_t fw_cfg_showrev(struct kobject *k, struct attribute *a, char *buf)
{
return sprintf(buf, "%u\n", fw_cfg_rev);
@@ -351,8 +470,7 @@ static ssize_t fw_cfg_sysfs_read_raw(struct file *filp, struct kobject *kobj,
if (count > entry->f.size - pos)
count = entry->f.size - pos;
- fw_cfg_read_blob(entry->f.select, buf, pos, count);
- return count;
+ return fw_cfg_read_blob(entry->f.select, buf, pos, count, true);
}
static struct bin_attribute fw_cfg_sysfs_attr_raw = {
@@ -505,7 +623,7 @@ static int fw_cfg_register_dir_entries(void)
struct fw_cfg_file *dir;
size_t dir_size;
- fw_cfg_read_blob(FW_CFG_FILE_DIR, &count, 0, sizeof(count));
+ fw_cfg_read_blob(FW_CFG_FILE_DIR, &count, 0, sizeof(count), false);
count = be32_to_cpu(count);
dir_size = count * sizeof(struct fw_cfg_file);
@@ -513,7 +631,7 @@ static int fw_cfg_register_dir_entries(void)
if (!dir)
return -ENOMEM;
- fw_cfg_read_blob(FW_CFG_FILE_DIR, dir, sizeof(count), dir_size);
+ fw_cfg_read_blob(FW_CFG_FILE_DIR, dir, sizeof(count), dir_size, true);
for (i = 0; i < count; i++) {
dir[i].size = be32_to_cpu(dir[i].size);
@@ -544,9 +662,10 @@ static int fw_cfg_sysfs_probe(struct platform_device *pdev)
* one fw_cfg device exist system-wide, so if one was already found
* earlier, we might as well stop here.
*/
- if (fw_cfg_sel_ko)
+ if (dev)
return -EBUSY;
+ dev = &pdev->dev;
/* create by_key and by_name subdirs of /sys/firmware/qemu_fw_cfg/ */
err = -ENOMEM;
fw_cfg_sel_ko = kobject_create_and_add("by_key", fw_cfg_top_ko);
@@ -562,7 +681,7 @@ static int fw_cfg_sysfs_probe(struct platform_device *pdev)
goto err_probe;
/* get revision number, add matching top-level attribute */
- fw_cfg_read_blob(FW_CFG_ID, &fw_cfg_rev, 0, sizeof(fw_cfg_rev));
+ fw_cfg_read_blob(FW_CFG_ID, &fw_cfg_rev, 0, sizeof(fw_cfg_rev), false);
fw_cfg_rev = le32_to_cpu(fw_cfg_rev);
err = sysfs_create_file(fw_cfg_top_ko, &fw_cfg_rev_attr.attr);
if (err)
@@ -587,6 +706,7 @@ static int fw_cfg_sysfs_probe(struct platform_device *pdev)
err_name:
fw_cfg_kobj_cleanup(fw_cfg_sel_ko);
err_sel:
+ dev = NULL;
return err;
}
--
2.15.0.125.g8f49766d64
From 1583468919684523330@xxx Wed Nov 08 04:00:39 +0000 2017
X-GM-THRID: 1583468919684523330
X-Gmail-Labels: Inbox,Category Forums,HistoricalUnread
Signed-off-by: Marc-André Lureau <[email protected]>
---
drivers/firmware/qemu_fw_cfg.c | 8 ++++----
1 file changed, 4 insertions(+), 4 deletions(-)
diff --git a/drivers/firmware/qemu_fw_cfg.c b/drivers/firmware/qemu_fw_cfg.c
index 0e2011636fbb..5cfe39f7a45f 100644
--- a/drivers/firmware/qemu_fw_cfg.c
+++ b/drivers/firmware/qemu_fw_cfg.c
@@ -10,9 +10,9 @@
* and select subsets of aarch64), a Device Tree node (on arm), or using
* a kernel module (or command line) parameter with the following syntax:
*
- * [fw_cfg.]ioport=<size>@<base>[:<ctrl_off>:<data_off>]
+ * [qemu_fw_cfg.]ioport=<size>@<base>[:<ctrl_off>:<data_off>]
* or
- * [fw_cfg.]mmio=<size>@<base>[:<ctrl_off>:<data_off>]
+ * [qemu_fw_cfg.]mmio=<size>@<base>[:<ctrl_off>:<data_off>]
*
* where:
* <size> := size of ioport or mmio range
@@ -21,9 +21,9 @@
* <data_off> := (optional) offset of data register
*
* e.g.:
- * fw_cfg.ioport=2@0x510:0:1 (the default on x86)
+ * qemu_fw_cfg.ioport=2@0x510:0:1 (the default on x86)
* or
- * fw_cfg.mmio=0xA@0x9020000:8:0 (the default on arm)
+ * qemu_fw_cfg.mmio=0xA@0x9020000:8:0 (the default on arm)
*/
#include <linux/module.h>
--
2.15.0.125.g8f49766d64
From 1583844584539859653@xxx Sun Nov 12 07:31:41 +0000 2017
X-GM-THRID: 1583844584539859653
X-Gmail-Labels: Inbox,Category Forums,HistoricalUnread
Add an optional <dma_off> kernel module (or command line) parameter
using the following syntax:
[qemu_fw_cfg.]ioport=<size>@<base>[:<ctrl_off>:<data_off>[:<dma_off>]]
or
[qemu_fw_cfg.]mmio=<size>@<base>[:<ctrl_off>:<data_off>[:<dma_off>]]
and initializes the register address using given or default offset.
Signed-off-by: Marc-André Lureau <[email protected]>
---
drivers/firmware/qemu_fw_cfg.c | 53 ++++++++++++++++++++++++++++++++----------
1 file changed, 41 insertions(+), 12 deletions(-)
diff --git a/drivers/firmware/qemu_fw_cfg.c b/drivers/firmware/qemu_fw_cfg.c
index 5cfe39f7a45f..1f3e8545dab7 100644
--- a/drivers/firmware/qemu_fw_cfg.c
+++ b/drivers/firmware/qemu_fw_cfg.c
@@ -10,20 +10,21 @@
* and select subsets of aarch64), a Device Tree node (on arm), or using
* a kernel module (or command line) parameter with the following syntax:
*
- * [qemu_fw_cfg.]ioport=<size>@<base>[:<ctrl_off>:<data_off>]
+ * [qemu_fw_cfg.]ioport=<size>@<base>[:<ctrl_off>:<data_off>[:<dma_off>]]
* or
- * [qemu_fw_cfg.]mmio=<size>@<base>[:<ctrl_off>:<data_off>]
+ * [qemu_fw_cfg.]mmio=<size>@<base>[:<ctrl_off>:<data_off>[:<dma_off>]]
*
* where:
* <size> := size of ioport or mmio range
* <base> := physical base address of ioport or mmio range
* <ctrl_off> := (optional) offset of control register
* <data_off> := (optional) offset of data register
+ * <dma_off> := (optional) offset of dma register
*
* e.g.:
- * qemu_fw_cfg.ioport=2@0x510:0:1 (the default on x86)
+ * qemu_fw_cfg.ioport=12@0x510:0:1:4 (the default on x86)
* or
- * qemu_fw_cfg.mmio=0xA@0x9020000:8:0 (the default on arm)
+ * qemu_fw_cfg.mmio=16@0x9020000:8:0:16 (the default on arm)
*/
#include <linux/module.h>
@@ -63,6 +64,7 @@ static resource_size_t fw_cfg_p_size;
static void __iomem *fw_cfg_dev_base;
static void __iomem *fw_cfg_reg_ctrl;
static void __iomem *fw_cfg_reg_data;
+static void __iomem *fw_cfg_reg_dma;
/* atomic access to fw_cfg device (potentially slow i/o, so using mutex) */
static DEFINE_MUTEX(fw_cfg_dev_lock);
@@ -118,12 +120,14 @@ static void fw_cfg_io_cleanup(void)
# if (defined(CONFIG_ARM) || defined(CONFIG_ARM64))
# define FW_CFG_CTRL_OFF 0x08
# define FW_CFG_DATA_OFF 0x00
+# define FW_CFG_DMA_OFF 0x10
# elif (defined(CONFIG_PPC_PMAC) || defined(CONFIG_SPARC32)) /* ppc/mac,sun4m */
# define FW_CFG_CTRL_OFF 0x00
# define FW_CFG_DATA_OFF 0x02
# elif (defined(CONFIG_X86) || defined(CONFIG_SPARC64)) /* x86, sun4u */
# define FW_CFG_CTRL_OFF 0x00
# define FW_CFG_DATA_OFF 0x01
+# define FW_CFG_DMA_OFF 0x04
# else
# error "QEMU FW_CFG not available on this architecture!"
# endif
@@ -133,7 +137,7 @@ static void fw_cfg_io_cleanup(void)
static int fw_cfg_do_platform_probe(struct platform_device *pdev)
{
char sig[FW_CFG_SIG_SIZE];
- struct resource *range, *ctrl, *data;
+ struct resource *range, *ctrl, *data, *dma;
/* acquire i/o range details */
fw_cfg_is_mmio = false;
@@ -170,6 +174,7 @@ static int fw_cfg_do_platform_probe(struct platform_device *pdev)
/* were custom register offsets provided (e.g. on the command line)? */
ctrl = platform_get_resource_byname(pdev, IORESOURCE_REG, "ctrl");
data = platform_get_resource_byname(pdev, IORESOURCE_REG, "data");
+ dma = platform_get_resource_byname(pdev, IORESOURCE_REG, "dma");
if (ctrl && data) {
fw_cfg_reg_ctrl = fw_cfg_dev_base + ctrl->start;
fw_cfg_reg_data = fw_cfg_dev_base + data->start;
@@ -179,6 +184,13 @@ static int fw_cfg_do_platform_probe(struct platform_device *pdev)
fw_cfg_reg_data = fw_cfg_dev_base + FW_CFG_DATA_OFF;
}
+ if (dma)
+ fw_cfg_reg_dma = fw_cfg_dev_base + dma->start;
+#ifdef FW_CFG_DMA_OFF
+ else
+ fw_cfg_reg_dma = fw_cfg_dev_base + FW_CFG_DMA_OFF;
+#endif
+
/* verify fw_cfg device signature */
fw_cfg_read_blob(FW_CFG_SIGNATURE, sig, 0, FW_CFG_SIG_SIZE);
if (memcmp(sig, "QEMU", FW_CFG_SIG_SIZE) != 0) {
@@ -628,6 +640,7 @@ static struct platform_device *fw_cfg_cmdline_dev;
/* use special scanf/printf modifier for phys_addr_t, resource_size_t */
#define PH_ADDR_SCAN_FMT "@%" __PHYS_ADDR_PREFIX "i%n" \
":%" __PHYS_ADDR_PREFIX "i" \
+ ":%" __PHYS_ADDR_PREFIX "i%n" \
":%" __PHYS_ADDR_PREFIX "i%n"
#define PH_ADDR_PR_1_FMT "0x%" __PHYS_ADDR_PREFIX "x@" \
@@ -637,12 +650,15 @@ static struct platform_device *fw_cfg_cmdline_dev;
":%" __PHYS_ADDR_PREFIX "u" \
":%" __PHYS_ADDR_PREFIX "u"
+#define PH_ADDR_PR_4_FMT PH_ADDR_PR_3_FMT \
+ ":%" __PHYS_ADDR_PREFIX "u"
+
static int fw_cfg_cmdline_set(const char *arg, const struct kernel_param *kp)
{
- struct resource res[3] = {};
+ struct resource res[4] = {};
char *str;
phys_addr_t base;
- resource_size_t size, ctrl_off, data_off;
+ resource_size_t size, ctrl_off, data_off, dma_off;
int processed, consumed = 0;
/* only one fw_cfg device can exist system-wide, so if one
@@ -658,19 +674,20 @@ static int fw_cfg_cmdline_set(const char *arg, const struct kernel_param *kp)
/* consume "<size>" portion of command line argument */
size = memparse(arg, &str);
- /* get "@<base>[:<ctrl_off>:<data_off>]" chunks */
+ /* get "@<base>[:<ctrl_off>:<data_off>[:<dma_off>]]" chunks */
processed = sscanf(str, PH_ADDR_SCAN_FMT,
&base, &consumed,
- &ctrl_off, &data_off, &consumed);
+ &ctrl_off, &data_off, &consumed,
+ &dma_off, &consumed);
- /* sscanf() must process precisely 1 or 3 chunks:
+ /* sscanf() must process precisely 1, 3 or 4 chunks:
* <base> is mandatory, optionally followed by <ctrl_off>
- * and <data_off>;
+ * and <data_off>, and <dma_off>;
* there must be no extra characters after the last chunk,
* so str[consumed] must be '\0'.
*/
if (str[consumed] ||
- (processed != 1 && processed != 3))
+ (processed != 1 && processed != 3 && processed != 4))
return -EINVAL;
res[0].start = base;
@@ -687,6 +704,11 @@ static int fw_cfg_cmdline_set(const char *arg, const struct kernel_param *kp)
res[2].start = data_off;
res[2].flags = IORESOURCE_REG;
}
+ if (processed > 3) {
+ res[3].name = "dma";
+ res[3].start = dma_off;
+ res[3].flags = IORESOURCE_REG;
+ }
/* "processed" happens to nicely match the number of resources
* we need to pass in to this platform device.
@@ -721,6 +743,13 @@ static int fw_cfg_cmdline_get(char *buf, const struct kernel_param *kp)
fw_cfg_cmdline_dev->resource[0].start,
fw_cfg_cmdline_dev->resource[1].start,
fw_cfg_cmdline_dev->resource[2].start);
+ case 4:
+ return snprintf(buf, PAGE_SIZE, PH_ADDR_PR_4_FMT,
+ resource_size(&fw_cfg_cmdline_dev->resource[0]),
+ fw_cfg_cmdline_dev->resource[0].start,
+ fw_cfg_cmdline_dev->resource[1].start,
+ fw_cfg_cmdline_dev->resource[2].start,
+ fw_cfg_cmdline_dev->resource[3].start);
}
/* Should never get here */
--
2.15.0.125.g8f49766d64
From 1583465457389001464@xxx Wed Nov 08 03:05:37 +0000 2017
X-GM-THRID: 1583245951783275789
X-Gmail-Labels: Inbox,Category Forums,HistoricalUnread