s390/kvm: avoid global config of vm.alloc_pgste=1

The system control vm.alloc_pgste is used to control the size of the
page tables, either 2K or 4K. The idea is that a KVM host sets the
vm.alloc_pgste control to 1 which causes *all* new processes to run
with 4K page tables. For a non-kvm system the control should stay off
to save on memory used for page tables.

Trouble is that distributions choose to set the control globally to
be able to run KVM guests. This wastes memory on non-KVM systems.

Introduce the PT_S390_PGSTE ELF segment type to "mark" the qemu
executable with it. All executables with this (empty) segment in
its ELF phdr array will be started with 4K page tables. Any executable
without PT_S390_PGSTE will run with the default 2K page tables.

This removes the need to set vm.alloc_pgste=1 for a KVM host and
minimizes the waste of memory for page tables.

Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>

1 files changed, 32 insertions, 0 deletions

diff --git a/arch/s390/include/asm/elf.h b/arch/s390/include/asm/elf.h
index e8f623041769..ec024c08dabe 100644
--- a/arch/s390/include/asm/elf.h
+++ b/arch/s390/include/asm/elf.h
@@ -117,6 +117,9 @@
 #define ELF_DATA	ELFDATA2MSB
 #define ELF_ARCH	EM_S390
 
+/* s390 specific phdr types */
+#define PT_S390_PGSTE	0x70000000
+
 /*
  * ELF register definitions..
  */
@@ -151,6 +154,35 @@ extern unsigned int vdso_enabled;
 	 && (x)->e_ident[EI_CLASS] == ELF_CLASS)
 #define compat_start_thread	start_thread31
 
+struct arch_elf_state {
+	int rc;
+};
+
+#define INIT_ARCH_ELF_STATE { .rc = 0 }
+
+#define arch_check_elf(ehdr, interp, interp_ehdr, state) (0)
+#ifdef CONFIG_PGSTE
+#define arch_elf_pt_proc(ehdr, phdr, elf, interp, state)	\
+({								\
+	struct arch_elf_state *_state = state;			\
+	if ((phdr)->p_type == PT_S390_PGSTE &&			\
+	    !page_table_allocate_pgste &&			\
+	    !test_thread_flag(TIF_PGSTE) &&			\
+	    !current->mm->context.alloc_pgste) {		\
+		set_thread_flag(TIF_PGSTE);			\
+		set_pt_regs_flag(task_pt_regs(current),		\
+				 PIF_SYSCALL_RESTART);		\
+		_state->rc = -EAGAIN;				\
+	}							\
+	_state->rc;						\
+})
+#else
+#define arch_elf_pt_proc(ehdr, phdr, elf, interp, state)	\
+({								\
+	(state)->rc;						\
+})
+#endif
+
 /* For SVR4/S390 the function pointer to be registered with `atexit` is
    passed in R14. */
 #define ELF_PLAT_INIT(_r, load_addr) \