From 3d214faea6e4f9b6018bf8589f4b245126349c0a Mon Sep 17 00:00:00 2001 From: Michael Holzheu Date: Sun, 30 Oct 2011 15:16:36 +0100 Subject: [S390] kdump: Add KEXEC_CRASH_CONTROL_MEMORY_LIMIT On s390 there is a different KEXEC_CONTROL_MEMORY_LIMIT for the normal and the kdump kexec case. Therefore this patch introduces a new macro KEXEC_CRASH_CONTROL_MEMORY_LIMIT. This is set to KEXEC_CONTROL_MEMORY_LIMIT for all architectures that do not define KEXEC_CRASH_CONTROL_MEMORY_LIMIT. Acked-by: Vivek Goyal Acked-by: Andrew Morton Signed-off-by: Michael Holzheu Signed-off-by: Martin Schwidefsky --- include/linux/kexec.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kexec.h b/include/linux/kexec.h index c2478a342cd7..07d9aba75562 100644 --- a/include/linux/kexec.h +++ b/include/linux/kexec.h @@ -33,6 +33,10 @@ #error KEXEC_ARCH not defined #endif +#ifndef KEXEC_CRASH_CONTROL_MEMORY_LIMIT +#define KEXEC_CRASH_CONTROL_MEMORY_LIMIT KEXEC_CONTROL_MEMORY_LIMIT +#endif + #define KEXEC_NOTE_HEAD_BYTES ALIGN(sizeof(struct elf_note), 4) #define KEXEC_CORE_NOTE_NAME "CORE" #define KEXEC_CORE_NOTE_NAME_BYTES ALIGN(sizeof(KEXEC_CORE_NOTE_NAME), 4) -- cgit v1.2.3 From d3bf37955d46718ee1a7f1fc69f953d2328ba7c2 Mon Sep 17 00:00:00 2001 From: Michael Holzheu Date: Sun, 30 Oct 2011 15:16:37 +0100 Subject: [S390] kdump: Add size to elfcorehdr kernel parameter Currently only the address of the pre-allocated ELF header is passed with the elfcorehdr= kernel parameter. In order to reserve memory for the header in the 2nd kernel also the size is required. Current kdump architecture backends use different methods to do that, e.g. x86 uses the memmap= kernel parameter. On s390 there is no easy way to transfer this information. Therefore the elfcorehdr kernel parameter is extended to also pass the size. This now can also be used as standard mechanism by all future kdump architecture backends. The syntax of the kernel parameter is extended as follows: elfcorehdr=[size[KMG]@]offset[KMG] This change is backward compatible because elfcorehdr=size is still allowed. Acked-by: Vivek Goyal Acked-by: Andrew Morton Signed-off-by: Michael Holzheu Signed-off-by: Martin Schwidefsky --- include/linux/crash_dump.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/crash_dump.h b/include/linux/crash_dump.h index 74054074e876..5c4abce94ad1 100644 --- a/include/linux/crash_dump.h +++ b/include/linux/crash_dump.h @@ -10,6 +10,7 @@ #define ELFCORE_ADDR_ERR (-2ULL) extern unsigned long long elfcorehdr_addr; +extern unsigned long long elfcorehdr_size; extern ssize_t copy_oldmem_page(unsigned long, char *, size_t, unsigned long, int); -- cgit v1.2.3 From 558df7209e7997275f6b8ad37737494cf2da1512 Mon Sep 17 00:00:00 2001 From: Michael Holzheu Date: Sun, 30 Oct 2011 15:16:43 +0100 Subject: [S390] kdump: Add infrastructure for unmapping crashkernel memory This patch introduces a mechanism that allows architecture backends to remove page tables for the crashkernel memory. This can protect the loaded kdump kernel from being overwritten by broken kernel code. Two new functions crash_map_reserved_pages() and crash_unmap_reserved_pages() are added that can be implemented by architecture code. The crash_map_reserved_pages() function is called before and crash_unmap_reserved_pages() after the crashkernel segments are loaded. The functions are also called in crash_shrink_memory() to create/remove page tables when the crashkernel memory size is reduced. To support architectures that have large pages this patch also introduces a new define KEXEC_CRASH_MEM_ALIGN. The crashkernel start and size must always be aligned with KEXEC_CRASH_MEM_ALIGN. Cc: Andrew Morton Acked-by: Vivek Goyal Signed-off-by: Michael Holzheu Signed-off-by: Martin Schwidefsky --- include/linux/kexec.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/kexec.h b/include/linux/kexec.h index 07d9aba75562..fe45136b32cc 100644 --- a/include/linux/kexec.h +++ b/include/linux/kexec.h @@ -37,6 +37,10 @@ #define KEXEC_CRASH_CONTROL_MEMORY_LIMIT KEXEC_CONTROL_MEMORY_LIMIT #endif +#ifndef KEXEC_CRASH_MEM_ALIGN +#define KEXEC_CRASH_MEM_ALIGN PAGE_SIZE +#endif + #define KEXEC_NOTE_HEAD_BYTES ALIGN(sizeof(struct elf_note), 4) #define KEXEC_CORE_NOTE_NAME "CORE" #define KEXEC_CORE_NOTE_NAME_BYTES ALIGN(sizeof(KEXEC_CORE_NOTE_NAME), 4) @@ -133,6 +137,8 @@ extern void crash_kexec(struct pt_regs *); int kexec_should_crash(struct task_struct *); void crash_save_cpu(struct pt_regs *regs, int cpu); void crash_save_vmcoreinfo(void); +void crash_map_reserved_pages(void); +void crash_unmap_reserved_pages(void); void arch_crash_save_vmcoreinfo(void); void vmcoreinfo_append_str(const char *fmt, ...) __attribute__ ((format (printf, 1, 2))); -- cgit v1.2.3 From 20b40a794baf3b4b0320c0a77ce944d5d1a01f25 Mon Sep 17 00:00:00 2001 From: Martin Schwidefsky Date: Sun, 30 Oct 2011 15:16:47 +0100 Subject: [S390] signal race with restarting system calls For a ERESTARTNOHAND/ERESTARTSYS/ERESTARTNOINTR restarting system call do_signal will prepare the restart of the system call with a rewind of the PSW before calling get_signal_to_deliver (where the debugger might take control). For A ERESTART_RESTARTBLOCK restarting system call do_signal will set -EINTR as return code. There are two issues with this approach: 1) strace never sees ERESTARTNOHAND, ERESTARTSYS, ERESTARTNOINTR or ERESTART_RESTARTBLOCK as the rewinding already took place or the return code has been changed to -EINTR 2) if get_signal_to_deliver does not return with a signal to deliver the restart via the repeat of the svc instruction is left in place. This opens a race if another signal is made pending before the system call instruction can be reexecuted. The original system call will be restarted even if the second signal would have ended the system call with -EINTR. These two issues can be solved by dropping the early rewind of the system call before get_signal_to_deliver has been called and by using the TIF_RESTART_SVC magic to do the restart if no signal has to be delivered. The only situation where the system call restart via the repeat of the svc instruction is appropriate is when a SA_RESTART signal is delivered to user space. Unfortunately this breaks inferior calls by the debugger again. The system call number and the length of the system call instruction is lost over the inferior call and user space will see ERESTARTNOHAND/ ERESTARTSYS/ERESTARTNOINTR/ERESTART_RESTARTBLOCK. To correct this a new ptrace interface is added to save/restore the system call number and system call instruction length. Signed-off-by: Martin Schwidefsky --- include/linux/elf.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/elf.h b/include/linux/elf.h index 110821cb6ea5..31f0508d7da7 100644 --- a/include/linux/elf.h +++ b/include/linux/elf.h @@ -395,6 +395,7 @@ typedef struct elf64_shdr { #define NT_S390_CTRS 0x304 /* s390 control registers */ #define NT_S390_PREFIX 0x305 /* s390 prefix register */ #define NT_S390_LAST_BREAK 0x306 /* s390 breaking event address */ +#define NT_S390_SYSTEM_CALL 0x307 /* s390 system call restart data */ #define NT_ARM_VFP 0x400 /* ARM VFP/NEON registers */ -- cgit v1.2.3