From 997c136f518c5debd63847e78e2a8694f56dcf90 Mon Sep 17 00:00:00 2001 From: Olaf Hering Date: Thu, 26 May 2011 16:25:54 -0700 Subject: [PATCH] fs/proc/vmcore.c: add hook to read_from_oldmem() to check for non-ram pages The balloon driver in a Xen guest frees guest pages and marks them as mmio. When the kernel crashes and the crash kernel attempts to read the oldmem via /proc/vmcore a read from ballooned pages will generate 100% load in dom0 because Xen asks qemu-dm for the page content. Since the reads come in as 8byte requests each ballooned page is tried 512 times. With this change a hook can be registered which checks wether the given pfn is really ram. The hook has to return a value > 0 for ram pages, a value < 0 on error (because the hypercall is not known) and 0 for non-ram pages. This will reduce the time to read /proc/vmcore. Without this change a 512M guest with 128M crashkernel region needs 200 seconds to read it, with this change it takes just 2 seconds. Signed-off-by: Olaf Hering Cc: Alexey Dobriyan Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- fs/proc/vmcore.c | 52 +++++++++++++++++++++++++++++++++++--- include/linux/crash_dump.h | 5 ++++ 2 files changed, 54 insertions(+), 3 deletions(-) diff --git a/fs/proc/vmcore.c b/fs/proc/vmcore.c index 74802bc5ded9..cd99bf557650 100644 --- a/fs/proc/vmcore.c +++ b/fs/proc/vmcore.c @@ -35,6 +35,46 @@ static u64 vmcore_size; static struct proc_dir_entry *proc_vmcore = NULL; +/* + * Returns > 0 for RAM pages, 0 for non-RAM pages, < 0 on error + * The called function has to take care of module refcounting. + */ +static int (*oldmem_pfn_is_ram)(unsigned long pfn); + +int register_oldmem_pfn_is_ram(int (*fn)(unsigned long pfn)) +{ + if (oldmem_pfn_is_ram) + return -EBUSY; + oldmem_pfn_is_ram = fn; + return 0; +} +EXPORT_SYMBOL_GPL(register_oldmem_pfn_is_ram); + +void unregister_oldmem_pfn_is_ram(void) +{ + oldmem_pfn_is_ram = NULL; + wmb(); +} +EXPORT_SYMBOL_GPL(unregister_oldmem_pfn_is_ram); + +static int pfn_is_ram(unsigned long pfn) +{ + int (*fn)(unsigned long pfn); + /* pfn is ram unless fn() checks pagetype */ + int ret = 1; + + /* + * Ask hypervisor if the pfn is really ram. + * A ballooned page contains no data and reading from such a page + * will cause high load in the hypervisor. + */ + fn = oldmem_pfn_is_ram; + if (fn) + ret = fn(pfn); + + return ret; +} + /* Reads a page from the oldmem device from given offset. */ static ssize_t read_from_oldmem(char *buf, size_t count, u64 *ppos, int userbuf) @@ -55,9 +95,15 @@ static ssize_t read_from_oldmem(char *buf, size_t count, else nr_bytes = count; - tmp = copy_oldmem_page(pfn, buf, nr_bytes, offset, userbuf); - if (tmp < 0) - return tmp; + /* If pfn is not ram, return zeros for sparse dump files */ + if (pfn_is_ram(pfn) == 0) + memset(buf, 0, nr_bytes); + else { + tmp = copy_oldmem_page(pfn, buf, nr_bytes, + offset, userbuf); + if (tmp < 0) + return tmp; + } *ppos += nr_bytes; count -= nr_bytes; buf += nr_bytes; diff --git a/include/linux/crash_dump.h b/include/linux/crash_dump.h index 088cd4ace4ef..74054074e876 100644 --- a/include/linux/crash_dump.h +++ b/include/linux/crash_dump.h @@ -66,6 +66,11 @@ static inline void vmcore_unusable(void) if (is_kdump_kernel()) elfcorehdr_addr = ELFCORE_ADDR_ERR; } + +#define HAVE_OLDMEM_PFN_IS_RAM 1 +extern int register_oldmem_pfn_is_ram(int (*fn)(unsigned long pfn)); +extern void unregister_oldmem_pfn_is_ram(void); + #else /* !CONFIG_CRASH_DUMP */ static inline int is_kdump_kernel(void) { return 0; } #endif /* CONFIG_CRASH_DUMP */ -- 2.39.5