minix/kernel/system/do_safecopy.c

410 lines
12 KiB
C
Raw Normal View History

/* The kernel call implemented in this file:
* m_type: SYS_SAFECOPYFROM or SYS_SAFECOPYTO or SYS_VSAFECOPY
*
* The parameters for this kernel call are:
* SCP_FROM_TO other endpoint
* SCP_SEG segment in own address space
* SCP_GID grant id
* SCP_OFFSET offset within granted space
* SCP_ADDRESS address in own address space
* SCP_BYTES bytes to be copied
*
* For the vectored variant (do_vsafecopy):
* VSCP_VEC_ADDR address of vector
* VSCP_VEC_SIZE number of significant elements in vector
*/
#include <minix/type.h>
#include <minix/safecopies.h>
2010-04-02 00:22:33 +02:00
#include "kernel/system.h"
#define MAX_INDIRECT_DEPTH 5 /* up to how many indirect grants to follow? */
#define MEM_TOP 0xFFFFFFFFUL
FORWARD _PROTOTYPE(int safecopy, (struct proc *, endpoint_t, endpoint_t,
cp_grant_id_t, int, int, size_t, vir_bytes, vir_bytes, int));
#define HASGRANTTABLE(gr) \
(!RTS_ISSET(gr, RTS_NO_PRIV) && priv(gr) && priv(gr)->s_grant_table > 0)
/*===========================================================================*
* verify_grant *
*===========================================================================*/
PUBLIC int verify_grant(granter, grantee, grant, bytes, access,
offset_in, offset_result, e_granter)
endpoint_t granter, grantee; /* copyee, copyer */
cp_grant_id_t grant; /* grant id */
vir_bytes bytes; /* copy size */
int access; /* direction (read/write) */
vir_bytes offset_in; /* copy offset within grant */
vir_bytes *offset_result; /* copy offset within virtual address space */
endpoint_t *e_granter; /* new granter (magic grants) */
{
static cp_grant_t g;
static int proc_nr;
static const struct proc *granter_proc;
int depth = 0;
do {
/* Get granter process slot (if valid), and check range of
* grant id.
*/
if(!isokendpt(granter, &proc_nr) ) {
printf(
"grant verify failed: invalid granter %d\n", (int) granter);
return(EINVAL);
}
if(!GRANT_VALID(grant)) {
printf(
"grant verify failed: invalid grant %d\n", (int) grant);
return(EINVAL);
}
granter_proc = proc_addr(proc_nr);
/* If there is no priv. structure, or no grant table in the
* priv. structure, or the grant table in the priv. structure
* is too small for the grant, return EPERM.
*/
if(!HASGRANTTABLE(granter_proc)) return EPERM;
if(priv(granter_proc)->s_grant_entries <= grant) {
printf(
"verify_grant: grant verify failed in ep %d "
"proc %d: grant %d out of range "
"for table size %d\n",
granter, proc_nr, grant,
priv(granter_proc)->s_grant_entries);
return(EPERM);
}
/* Copy the grant entry corresponding to this id to see what it
* looks like. If it fails, hide the fact that granter has
* (presumably) set an invalid grant table entry by returning
* EPERM, just like with an invalid grant id.
*/
if(data_copy(granter,
priv(granter_proc)->s_grant_table + sizeof(g)*grant,
KERNEL, (vir_bytes) &g, sizeof(g)) != OK) {
printf(
"verify_grant: grant verify: data_copy failed\n");
return EPERM;
}
/* Check validity. */
if((g.cp_flags & (CPF_USED | CPF_VALID)) !=
(CPF_USED | CPF_VALID)) {
printf(
"verify_grant: grant failed: invalid (%d flags 0x%lx)\n",
grant, g.cp_flags);
return EPERM;
}
/* The given grant may be an indirect grant, that is, a grant
* that provides permission to use a grant given to the
* granter (i.e., for which it is the grantee). This can lead
* to a chain of indirect grants which must be followed back.
*/
if((g.cp_flags & CPF_INDIRECT)) {
/* Stop after a few iterations. There may be a loop. */
if (depth == MAX_INDIRECT_DEPTH) {
printf(
"verify grant: indirect grant verify "
"failed: exceeded maximum depth\n");
return ELOOP;
}
depth++;
/* Verify actual grantee. */
if(g.cp_u.cp_indirect.cp_who_to != grantee &&
Initialization protocol for system services. SYSLIB CHANGES: - SEF framework now supports a new SEF Init request type from RS. 3 different callbacks are available (init_fresh, init_lu, init_restart) to specify initialization code when a service starts fresh, starts after a live update, or restarts. SYSTEM SERVICE CHANGES: - Initialization code for system services is now enclosed in a callback SEF will automatically call at init time. The return code of the callback will tell RS whether the initialization completed successfully. - Each init callback can access information passed by RS to initialize. As of now, each system service has access to the public entries of RS's system process table to gather all the information required to initialize. This design eliminates many existing or potential races at boot time and provides a uniform initialization interface to system services. The same interface will be reused for the upcoming publish/subscribe model to handle dynamic registration / deregistration of system services. VM CHANGES: - Uniform privilege management for all system services. Every service uses the same call mask format. For boot services, VM copies the call mask from init data. For dynamic services, VM still receives the call mask via rs_set_priv call that will be soon replaced by the upcoming publish/subscribe model. RS CHANGES: - The system process table has been reorganized and split into private entries and public entries. Only the latter ones are exposed to system services. - VM call masks are now entirely configured in rs/table.c - RS has now its own slot in the system process table. Only kernel tasks and user processes not included in the boot image are now left out from the system process table. - RS implements the initialization protocol for system services. - For services in the boot image, RS blocks till initialization is complete and panics when failure is reported back. Services are initialized in their order of appearance in the boot image priv table and RS blocks to implements synchronous initialization for every system service having the flag SF_SYNCH_BOOT set. - For services started dynamically, the initialization protocol is implemented as though it were the first ping for the service. In this case, if the system service fails to report back (or reports failure), RS brings the service down rather than trying to restart it.
2010-01-08 02:20:42 +01:00
grantee != ANY &&
g.cp_u.cp_indirect.cp_who_to != ANY) {
printf(
"verify_grant: indirect grant verify "
"failed: bad grantee\n");
return EPERM;
}
/* Start over with new granter, grant, and grantee. */
grantee = granter;
granter = g.cp_u.cp_indirect.cp_who_from;
grant = g.cp_u.cp_indirect.cp_grant;
}
} while(g.cp_flags & CPF_INDIRECT);
/* Check access of grant. */
if(((g.cp_flags & access) != access)) {
printf(
"verify_grant: grant verify failed: access invalid; want 0x%x, have 0x%x\n",
access, g.cp_flags);
return EPERM;
}
if((g.cp_flags & CPF_DIRECT)) {
/* Don't fiddle around with grants that wrap, arithmetic
* below may be confused.
*/
2010-06-04 20:05:38 +02:00
if(MEM_TOP - g.cp_u.cp_direct.cp_len + 1 <
g.cp_u.cp_direct.cp_start) {
printf(
"verify_grant: direct grant verify failed: len too long\n");
return EPERM;
}
/* Verify actual grantee. */
Initialization protocol for system services. SYSLIB CHANGES: - SEF framework now supports a new SEF Init request type from RS. 3 different callbacks are available (init_fresh, init_lu, init_restart) to specify initialization code when a service starts fresh, starts after a live update, or restarts. SYSTEM SERVICE CHANGES: - Initialization code for system services is now enclosed in a callback SEF will automatically call at init time. The return code of the callback will tell RS whether the initialization completed successfully. - Each init callback can access information passed by RS to initialize. As of now, each system service has access to the public entries of RS's system process table to gather all the information required to initialize. This design eliminates many existing or potential races at boot time and provides a uniform initialization interface to system services. The same interface will be reused for the upcoming publish/subscribe model to handle dynamic registration / deregistration of system services. VM CHANGES: - Uniform privilege management for all system services. Every service uses the same call mask format. For boot services, VM copies the call mask from init data. For dynamic services, VM still receives the call mask via rs_set_priv call that will be soon replaced by the upcoming publish/subscribe model. RS CHANGES: - The system process table has been reorganized and split into private entries and public entries. Only the latter ones are exposed to system services. - VM call masks are now entirely configured in rs/table.c - RS has now its own slot in the system process table. Only kernel tasks and user processes not included in the boot image are now left out from the system process table. - RS implements the initialization protocol for system services. - For services in the boot image, RS blocks till initialization is complete and panics when failure is reported back. Services are initialized in their order of appearance in the boot image priv table and RS blocks to implements synchronous initialization for every system service having the flag SF_SYNCH_BOOT set. - For services started dynamically, the initialization protocol is implemented as though it were the first ping for the service. In this case, if the system service fails to report back (or reports failure), RS brings the service down rather than trying to restart it.
2010-01-08 02:20:42 +01:00
if(g.cp_u.cp_direct.cp_who_to != grantee && grantee != ANY
&& g.cp_u.cp_direct.cp_who_to != ANY) {
printf(
"verify_grant: direct grant verify failed: bad grantee\n");
return EPERM;
}
/* Verify actual copy range. */
if((offset_in+bytes < offset_in) ||
offset_in+bytes > g.cp_u.cp_direct.cp_len) {
printf(
"verify_grant: direct grant verify failed: bad size or range. "
"granted %d bytes @ 0x%lx; wanted %d bytes @ 0x%lx\n",
g.cp_u.cp_direct.cp_len,
g.cp_u.cp_direct.cp_start,
bytes, offset_in);
return EPERM;
}
/* Verify successful - tell caller what address it is. */
*offset_result = g.cp_u.cp_direct.cp_start + offset_in;
*e_granter = granter;
} else if(g.cp_flags & CPF_MAGIC) {
/* Currently, it is hardcoded that only FS may do
* magic grants.
*/
if(granter != VFS_PROC_NR) {
printf(
"verify_grant: magic grant verify failed: granter (%d) "
"is not FS (%d)\n", granter, VFS_PROC_NR);
return EPERM;
}
/* Verify actual grantee. */
Initialization protocol for system services. SYSLIB CHANGES: - SEF framework now supports a new SEF Init request type from RS. 3 different callbacks are available (init_fresh, init_lu, init_restart) to specify initialization code when a service starts fresh, starts after a live update, or restarts. SYSTEM SERVICE CHANGES: - Initialization code for system services is now enclosed in a callback SEF will automatically call at init time. The return code of the callback will tell RS whether the initialization completed successfully. - Each init callback can access information passed by RS to initialize. As of now, each system service has access to the public entries of RS's system process table to gather all the information required to initialize. This design eliminates many existing or potential races at boot time and provides a uniform initialization interface to system services. The same interface will be reused for the upcoming publish/subscribe model to handle dynamic registration / deregistration of system services. VM CHANGES: - Uniform privilege management for all system services. Every service uses the same call mask format. For boot services, VM copies the call mask from init data. For dynamic services, VM still receives the call mask via rs_set_priv call that will be soon replaced by the upcoming publish/subscribe model. RS CHANGES: - The system process table has been reorganized and split into private entries and public entries. Only the latter ones are exposed to system services. - VM call masks are now entirely configured in rs/table.c - RS has now its own slot in the system process table. Only kernel tasks and user processes not included in the boot image are now left out from the system process table. - RS implements the initialization protocol for system services. - For services in the boot image, RS blocks till initialization is complete and panics when failure is reported back. Services are initialized in their order of appearance in the boot image priv table and RS blocks to implements synchronous initialization for every system service having the flag SF_SYNCH_BOOT set. - For services started dynamically, the initialization protocol is implemented as though it were the first ping for the service. In this case, if the system service fails to report back (or reports failure), RS brings the service down rather than trying to restart it.
2010-01-08 02:20:42 +01:00
if(g.cp_u.cp_magic.cp_who_to != grantee && grantee != ANY
&& g.cp_u.cp_direct.cp_who_to != ANY) {
printf(
"verify_grant: magic grant verify failed: bad grantee\n");
return EPERM;
}
/* Verify actual copy range. */
if((offset_in+bytes < offset_in) ||
offset_in+bytes > g.cp_u.cp_magic.cp_len) {
printf(
"verify_grant: magic grant verify failed: bad size or range. "
"granted %d bytes @ 0x%lx; wanted %d bytes @ 0x%lx\n",
g.cp_u.cp_magic.cp_len,
g.cp_u.cp_magic.cp_start,
bytes, offset_in);
return EPERM;
}
/* Verify successful - tell caller what address it is. */
*offset_result = g.cp_u.cp_magic.cp_start + offset_in;
*e_granter = g.cp_u.cp_magic.cp_who_from;
} else {
printf(
"verify_grant: grant verify failed: unknown grant type\n");
return EPERM;
}
return OK;
}
/*===========================================================================*
* safecopy *
*===========================================================================*/
PRIVATE int safecopy(caller, granter, grantee, grantid, src_seg, dst_seg, bytes,
g_offset, addr, access)
struct proc * caller;
endpoint_t granter, grantee;
cp_grant_id_t grantid;
int src_seg, dst_seg;
size_t bytes;
vir_bytes g_offset, addr;
int access; /* CPF_READ for a copy from granter to grantee, CPF_WRITE
* for a copy from grantee to granter.
*/
{
static struct vir_addr v_src, v_dst;
static vir_bytes v_offset;
endpoint_t new_granter, *src, *dst;
struct proc *granter_p;
int r;
2010-06-28 23:53:37 +02:00
#if PERF_USE_COW_SAFECOPY
vir_bytes size;
#endif
/* See if there is a reasonable grant table. */
if(!(granter_p = endpoint_lookup(granter))) return EINVAL;
if(!HASGRANTTABLE(granter_p)) return EPERM;
/* Decide who is src and who is dst. */
if(access & CPF_READ) {
src = &granter;
dst = &grantee;
} else {
src = &grantee;
dst = &granter;
}
/* Verify permission exists. */
if((r=verify_grant(granter, grantee, grantid, bytes, access,
g_offset, &v_offset, &new_granter)) != OK) {
printf(
"grant %d verify to copy %d->%d by %d failed: err %d\n",
grantid, *src, *dst, grantee, r);
return r;
}
/* verify_grant() can redirect the grantee to someone else,
* meaning the source or destination changes.
*/
granter = new_granter;
/* Now it's a regular copy. */
v_src.segment = src_seg;
v_dst.segment = dst_seg;
v_src.proc_nr_e = *src;
v_dst.proc_nr_e = *dst;
/* Now the offset in virtual addressing is known in 'offset'.
* Depending on the access, this is the source or destination
* address.
*/
if(access & CPF_READ) {
v_src.offset = v_offset;
v_dst.offset = (vir_bytes) addr;
} else {
v_src.offset = (vir_bytes) addr;
v_dst.offset = v_offset;
}
/* Do the regular copy. */
2010-06-28 23:53:37 +02:00
#if PERF_USE_COW_SAFECOPY
if(v_offset % CLICK_SIZE != addr % CLICK_SIZE || bytes < CLICK_SIZE) {
/* Give up on COW immediately when offsets are not aligned
* or we are copying less than a page.
*/
return virtual_copy_vmcheck(caller, &v_src, &v_dst, bytes);
}
if((size = v_offset % CLICK_SIZE) != 0) {
/* Normal copy for everything before the first page boundary. */
size = CLICK_SIZE - size;
r = virtual_copy_vmcheck(caller, &v_src, &v_dst, size);
if(r != OK)
return r;
v_src.offset += size;
v_dst.offset += size;
bytes -= size;
}
if((size = bytes / CLICK_SIZE) != 0) {
/* Use COW optimization when copying entire pages. */
size *= CLICK_SIZE;
r = map_invoke_vm(VMPTYPE_COWMAP,
v_dst.proc_nr_e, v_dst.segment, v_dst.offset,
v_src.proc_nr_e, v_src.segment, v_src.offset,
size, 0);
if(r != OK)
return r;
v_src.offset += size;
v_dst.offset += size;
bytes -= size;
}
if(bytes != 0) {
/* Normal copy for everything after the last page boundary. */
r = virtual_copy_vmcheck(caller, &v_src, &v_dst, bytes);
if(r != OK)
return r;
}
return OK;
#else
return virtual_copy_vmcheck(caller, &v_src, &v_dst, bytes);
#endif
}
/*===========================================================================*
* do_safecopy_to *
*===========================================================================*/
PUBLIC int do_safecopy_to(struct proc * caller, message * m_ptr)
{
return safecopy(caller, m_ptr->SCP_FROM_TO, caller->p_endpoint,
(cp_grant_id_t) m_ptr->SCP_GID, m_ptr->SCP_SEG, D,
m_ptr->SCP_BYTES, m_ptr->SCP_OFFSET,
(vir_bytes) m_ptr->SCP_ADDRESS, CPF_WRITE);
}
/*===========================================================================*
* do_safecopy_from *
*===========================================================================*/
PUBLIC int do_safecopy_from(struct proc * caller, message * m_ptr)
{
return safecopy(caller, m_ptr->SCP_FROM_TO, caller->p_endpoint,
(cp_grant_id_t) m_ptr->SCP_GID, D, m_ptr->SCP_SEG,
m_ptr->SCP_BYTES, m_ptr->SCP_OFFSET,
(vir_bytes) m_ptr->SCP_ADDRESS, CPF_READ);
}
/*===========================================================================*
* do_vsafecopy *
*===========================================================================*/
PUBLIC int do_vsafecopy(struct proc * caller, message * m_ptr)
{
static struct vscp_vec vec[SCPVEC_NR];
static struct vir_addr src, dst;
int r, i, els;
size_t bytes;
/* Set vector copy parameters. */
src.proc_nr_e = caller->p_endpoint;
src.offset = (vir_bytes) m_ptr->VSCP_VEC_ADDR;
src.segment = dst.segment = D;
dst.proc_nr_e = KERNEL;
dst.offset = (vir_bytes) vec;
/* No. of vector elements. */
els = m_ptr->VSCP_VEC_SIZE;
bytes = els * sizeof(struct vscp_vec);
/* Obtain vector of copies. */
if((r=virtual_copy_vmcheck(caller, &src, &dst, bytes)) != OK)
return r;
/* Perform safecopies. */
for(i = 0; i < els; i++) {
int access;
endpoint_t granter;
if(vec[i].v_from == SELF) {
access = CPF_WRITE;
granter = vec[i].v_to;
} else if(vec[i].v_to == SELF) {
access = CPF_READ;
granter = vec[i].v_from;
} else {
printf("vsafecopy: %d: element %d/%d: no SELF found\n",
caller->p_endpoint, i, els);
return EINVAL;
}
/* Do safecopy for this element. */
if((r=safecopy(caller, granter, caller->p_endpoint,
vec[i].v_gid, D, D,
vec[i].v_bytes, vec[i].v_offset,
vec[i].v_addr, access)) != OK) {
return r;
}
}
return OK;
}