Commit 16dd07bc authored by Jeff Dike's avatar Jeff Dike Committed by Linus Torvalds
Browse files

uml: more page fault path trimming 



More trimming of the page fault path.

Permissions are passed around in a single int rather than one bit per
int.  The permission values are copied from libc so that they can be
passed to mmap and mprotect without any further conversion.

The register sets used by do_syscall_stub and copy_context_skas0 are
initialized once, at boot time, rather than once per call.

wait_stub_done checks whether it is getting the signals it expects by
comparing the wait status to a mask containing bits for the signals of
interest rather than comparing individually to the signal numbers.  It
also has one check for a wait failure instead of two.  The caller is
expected to do the initial continue of the stub.  This gets rid of an
argument and some logic.  The fname argument is gone, as that can be
had from a stack trace.

user_signal() is collapsed into userspace() as it is basically one or
two lines of code afterwards.

The physical memory remapping stuff is gone, as it is unused.

flush_tlb_page is inlined.

Signed-off-by: default avatarJeff Dike <jdike@linux.intel.com>
Cc: Paolo 'Blaisorblade' Giarrusso <blaisorblade@yahoo.it>
Signed-off-by: default avatarAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: default avatarLinus Torvalds <torvalds@linux-foundation.org>
parent 3ec704e6

arch/um/include/os.h

+2 −4
Original line number Diff line number Diff line
@@ -300,13 +300,12 @@ extern long syscall_stub_data(struct mm_id * mm_idp, 
			      unsigned long *data, int data_count,

			      void **addr, void **stub_addr);

extern int map(struct mm_id * mm_idp, unsigned long virt,

	       unsigned long len, int r, int w, int x, int phys_fd,

	       unsigned long len, int prot, int phys_fd,

	       unsigned long long offset, int done, void **data);

extern int unmap(struct mm_id * mm_idp, unsigned long addr, unsigned long len,

		 int done, void **data);

extern int protect(struct mm_id * mm_idp, unsigned long addr,

		   unsigned long len, int r, int w, int x, int done,

		   void **data);

		   unsigned long len, unsigned int prot, int done, void **data);



/* skas/process.c */

extern int is_skas_winch(int pid, int fd, void *data);
@@ -342,7 +341,6 @@ extern void maybe_sigio_broken(int fd, int read); 


/* skas/trap */

extern void sig_handler_common_skas(int sig, void *sc_ptr);

extern void user_signal(int sig, union uml_pt_regs *regs, int pid);



/* sys-x86_64/prctl.c */

extern int os_arch_prctl(int pid, int code, unsigned long *addr);

arch/um/include/tlb.h

+2 −6
Original line number Diff line number Diff line
@@ -14,9 +14,7 @@ struct host_vm_op { 
		struct {

			unsigned long addr;

			unsigned long len;

			unsigned int r:1;

			unsigned int w:1;

			unsigned int x:1;

			unsigned int prot;

			int fd;

			__u64 offset;

		} mmap;
@@ -27,9 +25,7 @@ struct host_vm_op { 
		struct {

			unsigned long addr;

			unsigned long len;

			unsigned int r:1;

			unsigned int w:1;

			unsigned int x:1;

			unsigned int prot;

		} mprotect;

	} u;

};

arch/um/kernel/physmem.c

+1 −227
Original line number Diff line number Diff line
@@ -21,229 +21,8 @@ 
#include "kern.h"

#include "init.h"



struct phys_desc {

	struct rb_node rb;

	int fd;

	__u64 offset;

	void *virt;

	unsigned long phys;

	struct list_head list;

};



static struct rb_root phys_mappings = RB_ROOT;



static struct rb_node **find_rb(void *virt)

{

	struct rb_node **n = &phys_mappings.rb_node;

	struct phys_desc *d;



	while(*n != NULL){

		d = rb_entry(*n, struct phys_desc, rb);

		if(d->virt == virt)

			return n;



		if(d->virt > virt)

			n = &(*n)->rb_left;

		else

			n = &(*n)->rb_right;

	}



	return n;

}



static struct phys_desc *find_phys_mapping(void *virt)

{

	struct rb_node **n = find_rb(virt);



	if(*n == NULL)

		return NULL;



	return rb_entry(*n, struct phys_desc, rb);

}



static void insert_phys_mapping(struct phys_desc *desc)

{

	struct rb_node **n = find_rb(desc->virt);



	if(*n != NULL)

		panic("Physical remapping for %p already present",

		      desc->virt);



	rb_link_node(&desc->rb, rb_parent(*n), n);

	rb_insert_color(&desc->rb, &phys_mappings);

}



LIST_HEAD(descriptor_mappings);



struct desc_mapping {

	int fd;

	struct list_head list;

	struct list_head pages;

};



static struct desc_mapping *find_mapping(int fd)

{

	struct desc_mapping *desc;

	struct list_head *ele;



	list_for_each(ele, &descriptor_mappings){

		desc = list_entry(ele, struct desc_mapping, list);

		if(desc->fd == fd)

			return desc;

	}



	return NULL;

}



static struct desc_mapping *descriptor_mapping(int fd)

{

	struct desc_mapping *desc;



	desc = find_mapping(fd);

	if(desc != NULL)

		return desc;



	desc = kmalloc(sizeof(*desc), GFP_ATOMIC);

	if(desc == NULL)

		return NULL;



	*desc = ((struct desc_mapping)

		{ .fd =		fd,

		  .list =	LIST_HEAD_INIT(desc->list),

		  .pages =	LIST_HEAD_INIT(desc->pages) });

	list_add(&desc->list, &descriptor_mappings);



	return desc;

}



int physmem_subst_mapping(void *virt, int fd, __u64 offset, int w)

{

	struct desc_mapping *fd_maps;

	struct phys_desc *desc;

	unsigned long phys;

	int err;



	fd_maps = descriptor_mapping(fd);

	if(fd_maps == NULL)

		return -ENOMEM;



	phys = __pa(virt);

	desc = find_phys_mapping(virt);

	if(desc != NULL)

		panic("Address 0x%p is already substituted\n", virt);



	err = -ENOMEM;

	desc = kmalloc(sizeof(*desc), GFP_ATOMIC);

	if(desc == NULL)

		goto out;



	*desc = ((struct phys_desc)

		{ .fd =			fd,

		  .offset =		offset,

		  .virt =		virt,

		  .phys =		__pa(virt),

		  .list = 		LIST_HEAD_INIT(desc->list) });

	insert_phys_mapping(desc);



	list_add(&desc->list, &fd_maps->pages);



	virt = (void *) ((unsigned long) virt & PAGE_MASK);

	err = os_map_memory(virt, fd, offset, PAGE_SIZE, 1, w, 0);

	if(!err)

		goto out;



	rb_erase(&desc->rb, &phys_mappings);

	kfree(desc);

 out:

	return err;

}



static int physmem_fd = -1;



static void remove_mapping(struct phys_desc *desc)

{

	void *virt = desc->virt;

	int err;



	rb_erase(&desc->rb, &phys_mappings);

	list_del(&desc->list);

	kfree(desc);



	err = os_map_memory(virt, physmem_fd, __pa(virt), PAGE_SIZE, 1, 1, 0);

	if(err)

		panic("Failed to unmap block device page from physical memory, "

		      "errno = %d", -err);

}



int physmem_remove_mapping(void *virt)

{

	struct phys_desc *desc;



	virt = (void *) ((unsigned long) virt & PAGE_MASK);

	desc = find_phys_mapping(virt);

	if(desc == NULL)

		return 0;



	remove_mapping(desc);

	return 1;

}



void physmem_forget_descriptor(int fd)

{

	struct desc_mapping *desc;

	struct phys_desc *page;

	struct list_head *ele, *next;

	__u64 offset;

	void *addr;

	int err;



	desc = find_mapping(fd);

	if(desc == NULL)

		return;



	list_for_each_safe(ele, next, &desc->pages){

		page = list_entry(ele, struct phys_desc, list);

		offset = page->offset;

		addr = page->virt;

		remove_mapping(page);

		err = os_seek_file(fd, offset);

		if(err)

			panic("physmem_forget_descriptor - failed to seek "

			      "to %lld in fd %d, error = %d\n",

			      offset, fd, -err);

		err = os_read_file(fd, addr, PAGE_SIZE);

		if(err < 0)

			panic("physmem_forget_descriptor - failed to read "

			      "from fd %d to 0x%p, error = %d\n",

			      fd, addr, -err);

	}



	list_del(&desc->list);

	kfree(desc);

}



EXPORT_SYMBOL(physmem_forget_descriptor);

EXPORT_SYMBOL(physmem_remove_mapping);

EXPORT_SYMBOL(physmem_subst_mapping);



void arch_free_page(struct page *page, int order)

{

	void *virt;

	int i;



	for(i = 0; i < (1 << order); i++){

		virt = __va(page_to_phys(page + i));

		physmem_remove_mapping(virt);

	}

}



int is_remapped(void *virt)

{

 	struct phys_desc *desc = find_phys_mapping(virt);



	return desc != NULL;

}



/* Changed during early boot */

unsigned long high_physmem;
@@ -350,14 +129,9 @@ void setup_physmem(unsigned long start, unsigned long reserve_end, 


int phys_mapping(unsigned long phys, __u64 *offset_out)

{

	struct phys_desc *desc = find_phys_mapping(__va(phys & PAGE_MASK));

	int fd = -1;



	if(desc != NULL){

		fd = desc->fd;

		*offset_out = desc->offset;

	}

	else if(phys < physmem_size){

	if(phys < physmem_size){

		fd = physmem_fd;

		*offset_out = phys;

	}

arch/um/kernel/skas/tlb.c

+11 −10
Original line number Diff line number Diff line
@@ -27,9 +27,9 @@ static int do_ops(union mm_context *mmu, struct host_vm_op *ops, int last, 
		switch(op->type){

		case MMAP:

			ret = map(&mmu->skas.id, op->u.mmap.addr,

				  op->u.mmap.len, op->u.mmap.r, op->u.mmap.w,

				  op->u.mmap.x, op->u.mmap.fd,

				  op->u.mmap.offset, finished, flush);

				  op->u.mmap.len, op->u.mmap.prot,

				  op->u.mmap.fd, op->u.mmap.offset, finished,

				  flush);

			break;

		case MUNMAP:

			ret = unmap(&mmu->skas.id, op->u.munmap.addr,
@@ -37,8 +37,7 @@ static int do_ops(union mm_context *mmu, struct host_vm_op *ops, int last, 
			break;

		case MPROTECT:

			ret = protect(&mmu->skas.id, op->u.mprotect.addr,

				      op->u.mprotect.len, op->u.mprotect.r,

				      op->u.mprotect.w, op->u.mprotect.x,

				      op->u.mprotect.len, op->u.mprotect.prot,

				      finished, flush);

			break;

		default:
@@ -102,10 +101,10 @@ void flush_tlb_page_skas(struct vm_area_struct *vma, unsigned long address) 
	pte_t *pte;

	struct mm_struct *mm = vma->vm_mm;

	void *flush = NULL;

	int r, w, x, err = 0;

	int r, w, x, prot, err = 0;

	struct mm_id *mm_id;



	pgd = pgd_offset(vma->vm_mm, address);

	pgd = pgd_offset(mm, address);

	if(!pgd_present(*pgd))

		goto kill;
@@ -130,19 +129,21 @@ void flush_tlb_page_skas(struct vm_area_struct *vma, unsigned long address) 
	}



	mm_id = &mm->context.skas.id;

	prot = ((r ? UM_PROT_READ : 0) | (w ? UM_PROT_WRITE : 0) |

		(x ? UM_PROT_EXEC : 0));

	if(pte_newpage(*pte)){

		if(pte_present(*pte)){

			unsigned long long offset;

			int fd;



			fd = phys_mapping(pte_val(*pte) & PAGE_MASK, &offset);

			err = map(mm_id, address, PAGE_SIZE, r, w, x, fd,

				  offset, 1, &flush);

			err = map(mm_id, address, PAGE_SIZE, prot, fd, offset,

				  1, &flush);

		}

		else err = unmap(mm_id, address, PAGE_SIZE, 1, &flush);

	}

	else if(pte_newprot(*pte))

		err = protect(mm_id, address, PAGE_SIZE, r, w, x, 1, &flush);

		err = protect(mm_id, address, PAGE_SIZE, prot, 1, &flush);



	if(err)

		goto kill;

arch/um/kernel/tlb.c

+14 −28
Original line number Diff line number Diff line
@@ -17,7 +17,7 @@ 
#include "os.h"



static int add_mmap(unsigned long virt, unsigned long phys, unsigned long len,

		    int r, int w, int x, struct host_vm_op *ops, int *index,

		    unsigned int prot, struct host_vm_op *ops, int *index,

		    int last_filled, union mm_context *mmu, void **flush,

		    int (*do_ops)(union mm_context *, struct host_vm_op *,

				  int, int, void **))
@@ -31,8 +31,7 @@ static int add_mmap(unsigned long virt, unsigned long phys, unsigned long len, 
		last = &ops[*index];

		if((last->type == MMAP) &&

		   (last->u.mmap.addr + last->u.mmap.len == virt) &&

		   (last->u.mmap.r == r) && (last->u.mmap.w == w) &&

		   (last->u.mmap.x == x) && (last->u.mmap.fd == fd) &&

		   (last->u.mmap.prot == prot) && (last->u.mmap.fd == fd) &&

		   (last->u.mmap.offset + last->u.mmap.len == offset)){

			last->u.mmap.len += len;

			return 0;
@@ -48,9 +47,7 @@ static int add_mmap(unsigned long virt, unsigned long phys, unsigned long len, 
			     			.u = { .mmap = {

						       .addr	= virt,

						       .len	= len,

						       .r	= r,

						       .w	= w,

						       .x	= x,

						       .prot	= prot,

						       .fd	= fd,

						       .offset	= offset }

			   } });
@@ -87,8 +84,8 @@ static int add_munmap(unsigned long addr, unsigned long len, 
	return ret;

}



static int add_mprotect(unsigned long addr, unsigned long len, int r, int w,

			int x, struct host_vm_op *ops, int *index,

static int add_mprotect(unsigned long addr, unsigned long len,

			unsigned int prot, struct host_vm_op *ops, int *index,

			int last_filled, union mm_context *mmu, void **flush,

			int (*do_ops)(union mm_context *, struct host_vm_op *,

				      int, int, void **))
@@ -100,8 +97,7 @@ static int add_mprotect(unsigned long addr, unsigned long len, int r, int w, 
		last = &ops[*index];

		if((last->type == MPROTECT) &&

		   (last->u.mprotect.addr + last->u.mprotect.len == addr) &&

		   (last->u.mprotect.r == r) && (last->u.mprotect.w == w) &&

		   (last->u.mprotect.x == x)){

		   (last->u.mprotect.prot == prot)){

			last->u.mprotect.len += len;

			return 0;

		}
@@ -116,9 +112,7 @@ static int add_mprotect(unsigned long addr, unsigned long len, int r, int w, 
			     		       .u = { .mprotect = {

						       .addr	= addr,

						       .len	= len,

						       .r	= r,

						       .w	= w,

						       .x	= x } } });

						       .prot	= prot } } });

	return ret;

}
@@ -133,7 +127,7 @@ static inline int update_pte_range(pmd_t *pmd, unsigned long addr, 
						 void **))

{

	pte_t *pte;

	int r, w, x, ret = 0;

	int r, w, x, prot, ret = 0;



	pte = pte_offset_kernel(pmd, addr);

	do {
@@ -146,19 +140,19 @@ static inline int update_pte_range(pmd_t *pmd, unsigned long addr, 
		} else if (!pte_dirty(*pte)) {

			w = 0;

		}

		prot = ((r ? UM_PROT_READ : 0) | (w ? UM_PROT_WRITE : 0) |

			(x ? UM_PROT_EXEC : 0));

		if(force || pte_newpage(*pte)){

			if(pte_present(*pte))

				ret = add_mmap(addr, pte_val(*pte) & PAGE_MASK,

					       PAGE_SIZE, r, w, x, ops,

					       op_index, last_op, mmu, flush,

					       do_ops);

					       PAGE_SIZE, prot, ops, op_index,

					       last_op, mmu, flush, do_ops);

			else ret = add_munmap(addr, PAGE_SIZE, ops, op_index,

					      last_op, mmu, flush, do_ops);

		}

		else if(pte_newprot(*pte))

			ret = add_mprotect(addr, PAGE_SIZE, r, w, x, ops,

					   op_index, last_op, mmu, flush,

					   do_ops);

			ret = add_mprotect(addr, PAGE_SIZE, prot, ops, op_index,

					   last_op, mmu, flush, do_ops);

		*pte = pte_mkuptodate(*pte);

	} while (pte++, addr += PAGE_SIZE, ((addr != end) && !ret));

	return ret;
@@ -377,14 +371,6 @@ pte_t *addr_pte(struct task_struct *task, unsigned long addr) 
	return(pte_offset_map(pmd, addr));

}



void flush_tlb_page(struct vm_area_struct *vma, unsigned long address)

{

	address &= PAGE_MASK;



	CHOOSE_MODE(flush_tlb_range(vma, address, address + PAGE_SIZE),

		    flush_tlb_page_skas(vma, address));

}



void flush_tlb_all(void)

{

	flush_tlb_mm(current->mm);

CRA Git | Maintained and supported by SUSTech CRA and CCSE