minix/servers/is/dmp_kernel.c

384 lines
12 KiB
C
Raw Normal View History

/* Debugging dump procedures for the kernel. */
2005-10-20 22:28:54 +02:00
#include "inc.h"
#include <timers.h>
#include <assert.h>
#include <machine/interrupt.h>
endpoint-aware conversion of servers. 'who', indicating caller number in pm and fs and some other servers, has been removed in favour of 'who_e' (endpoint) and 'who_p' (proc nr.). In both PM and FS, isokendpt() convert endpoints to process slot numbers, returning OK if it was a valid and consistent endpoint number. okendpt() does the same but panic()s if it doesn't succeed. (In PM, this is pm_isok..) pm and fs keep their own records of process endpoints in their proc tables, which are needed to make kernel calls about those processes. message field names have changed. fs drivers are endpoints. fs now doesn't try to get out of driver deadlock, as the protocol isn't supposed to let that happen any more. (A warning is printed if ELOCKED is detected though.) fproc[].fp_task (indicating which driver the process is suspended on) became an int. PM and FS now get endpoint numbers of initial boot processes from the kernel. These happen to be the same as the old proc numbers, to let user processes reach them with the old numbers, but FS and PM don't know that. All new processes after INIT, even after the generation number wraps around, get endpoint numbers with generation 1 and higher, so the first instances of the boot processes are the only processes ever to have endpoint numbers in the old proc number range. More return code checks of sys_* functions have been added. IS has become endpoint-aware. Ditched the 'text' and 'data' fields in the kernel dump (which show locations, not sizes, so aren't terribly useful) in favour of the endpoint number. Proc number is still visible. Some other dumps (e.g. dmap, rs) show endpoint numbers now too which got the formatting changed. PM reading segments using rw_seg() has changed - it uses other fields in the message now instead of encoding the segment and process number and fd in the fd field. For that it uses _read_pm() and _write_pm() which to _taskcall()s directly in pm/misc.c. PM now sys_exit()s itself on panic(), instead of sys_abort(). RS also talks in endpoints instead of process numbers.
2006-03-03 11:20:58 +01:00
#include <minix/endpoint.h>
2009-01-12 23:14:43 +01:00
#include <minix/sysutil.h>
Split of architecture-dependent and -independent functions for i386, mainly in the kernel and headers. This split based on work by Ingmar Alting <iaalting@cs.vu.nl> done for his Minix PowerPC architecture port. . kernel does not program the interrupt controller directly, do any other architecture-dependent operations, or contain assembly any more, but uses architecture-dependent functions in arch/$(ARCH)/. . architecture-dependent constants and types defined in arch/$(ARCH)/include. . <ibm/portio.h> moved to <minix/portio.h>, as they have become, for now, architecture-independent functions. . int86, sdevio, readbios, and iopenable are now i386-specific kernel calls and live in arch/i386/do_* now. . i386 arch now supports even less 86 code; e.g. mpx86.s and klib86.s have gone, and 'machine.protected' is gone (and always taken to be 1 in i386). If 86 support is to return, it should be a new architecture. . prototypes for the architecture-dependent functions defined in kernel/arch/$(ARCH)/*.c but used in kernel/ are in kernel/proto.h . /etc/make.conf included in makefiles and shell scripts that need to know the building architecture; it defines ARCH=<arch>, currently only i386. . some basic per-architecture build support outside of the kernel (lib) . in clock.c, only dequeue a process if it was ready . fixes for new include files files deleted: . mpx/klib.s - only for choosing between mpx/klib86 and -386 . klib86.s - only for 86 i386-specific files files moved (or arch-dependent stuff moved) to arch/i386/: . mpx386.s (entry point) . klib386.s . sconst.h . exception.c . protect.c . protect.h . i8269.c
2006-12-22 16:22:27 +01:00
#include <minix/sys_config.h>
2010-04-02 00:22:33 +02:00
#include "kernel/const.h"
#include "kernel/config.h"
#include "kernel/debug.h"
#include "kernel/type.h"
#include "kernel/proc.h"
#include "kernel/ipc.h"
#define LINES 22
#define PRINTRTS(rp) { \
char *procname = ""; \
printf(" %s", p_rts_flags_str(rp->p_rts_flags)); \
if (rp->p_rts_flags & RTS_SENDING) \
procname = proc_name(_ENDPOINT_P(rp->p_sendto_e)); \
else if (rp->p_rts_flags & RTS_RECEIVING) \
procname = proc_name(_ENDPOINT_P(rp->p_getfrom_e)); \
printf(" %-7.7s", procname); \
}
static int pagelines;
#define PROCLOOP(rp, oldrp) \
pagelines = 0; \
for (rp = oldrp; rp < END_PROC_ADDR; rp++) { \
oldrp = BEG_PROC_ADDR; \
if (isemptyp(rp)) continue; \
if (++pagelines > LINES) { oldrp = rp; printf("--more--\n"); break; }\
if (proc_nr(rp) == IDLE) printf("(%2d) ", proc_nr(rp)); \
else if (proc_nr(rp) < 0) printf("[%2d] ", proc_nr(rp)); \
else printf(" %2d ", proc_nr(rp));
#define click_to_round_k(n) \
((unsigned) ((((unsigned long) (n) << CLICK_SHIFT) + 512) / 1024))
/* Declare some local dump procedures. */
2012-03-25 20:25:53 +02:00
static char *proc_name(int proc_nr);
static char *s_traps_str(int flags);
static char *s_flags_str(int flags);
static char *p_rts_flags_str(int flags);
/* Some global data that is shared among several dumping procedures.
* Note that the process table copy has the same name as in the kernel
* so that most macros and definitions from proc.h also apply here.
*/
2012-03-25 20:25:53 +02:00
struct proc proc[NR_TASKS + NR_PROCS];
struct priv priv[NR_SYS_PROCS];
struct boot_image image[NR_BOOT_PROCS];
extern struct minix_kerninfo *_minix_kerninfo;
/*===========================================================================*
* kmessages_dmp *
*===========================================================================*/
2012-03-25 20:25:53 +02:00
void kmessages_dmp()
{
struct kmessages *kmess; /* get copy of kernel messages */
char print_buf[_KMESS_BUF_SIZE+1]; /* this one is used to print */
int start; /* calculate start of messages */
int r;
int size;
assert(_minix_kerninfo);
kmess = _minix_kerninfo->kmessages;
/* Try to print the kernel messages. First determine start and copy the
* buffer into a print-buffer. This is done because the messages in the
* copy may wrap (the kernel buffer is circular).
*/
start = ((kmess->km_next + _KMESS_BUF_SIZE) - kmess->km_size) % _KMESS_BUF_SIZE;
r = 0;
size = kmess->km_size;
while (size > 0) {
print_buf[r] = kmess->km_buf[(start+r) % _KMESS_BUF_SIZE];
r ++;
size--;
}
print_buf[r] = 0; /* make sure it terminates */
printf("Dump of all messages generated by the kernel.\n\n");
printf("%s", print_buf); /* print the messages */
}
/*===========================================================================*
* monparams_dmp *
*===========================================================================*/
2012-03-25 20:25:53 +02:00
void monparams_dmp()
{
No more intel/minix segments. This commit removes all traces of Minix segments (the text/data/stack memory map abstraction in the kernel) and significance of Intel segments (hardware segments like CS, DS that add offsets to all addressing before page table translation). This ultimately simplifies the memory layout and addressing and makes the same layout possible on non-Intel architectures. There are only two types of addresses in the world now: virtual and physical; even the kernel and processes have the same virtual address space. Kernel and user processes can be distinguished at a glance as processes won't use 0xF0000000 and above. No static pre-allocated memory sizes exist any more. Changes to booting: . The pre_init.c leaves the kernel and modules exactly as they were left by the bootloader in physical memory . The kernel starts running using physical addressing, loaded at a fixed location given in its linker script by the bootloader. All code and data in this phase are linked to this fixed low location. . It makes a bootstrap pagetable to map itself to a fixed high location (also in linker script) and jumps to the high address. All code and data then use this high addressing. . All code/data symbols linked at the low addresses is prefixed by an objcopy step with __k_unpaged_*, so that that code cannot reference highly-linked symbols (which aren't valid yet) or vice versa (symbols that aren't valid any more). . The two addressing modes are separated in the linker script by collecting the unpaged_*.o objects and linking them with low addresses, and linking the rest high. Some objects are linked twice, once low and once high. . The bootstrap phase passes a lot of information (e.g. free memory list, physical location of the modules, etc.) using the kinfo struct. . After this bootstrap the low-linked part is freed. . The kernel maps in VM into the bootstrap page table so that VM can begin executing. Its first job is to make page tables for all other boot processes. So VM runs before RS, and RS gets a fully dynamic, VM-managed address space. VM gets its privilege info from RS as usual but that happens after RS starts running. . Both the kernel loading VM and VM organizing boot processes happen using the libexec logic. This removes the last reason for VM to still know much about exec() and vm/exec.c is gone. Further Implementation: . All segments are based at 0 and have a 4 GB limit. . The kernel is mapped in at the top of the virtual address space so as not to constrain the user processes. . Processes do not use segments from the LDT at all; there are no segments in the LDT any more, so no LLDT is needed. . The Minix segments T/D/S are gone and so none of the user-space or in-kernel copy functions use them. The copy functions use a process endpoint of NONE to realize it's a physical address, virtual otherwise. . The umap call only makes sense to translate a virtual address to a physical address now. . Segments-related calls like newmap and alloc_segments are gone. . All segments-related translation in VM is gone (vir2map etc). . Initialization in VM is simpler as no moving around is necessary. . VM and all other boot processes can be linked wherever they wish and will be mapped in at the right location by the kernel and VM respectively. Other changes: . The multiboot code is less special: it does not use mb_print for its diagnostics any more but uses printf() as normal, saving the output into the diagnostics buffer, only printing to the screen using the direct print functions if a panic() occurs. . The multiboot code uses the flexible 'free memory map list' style to receive the list of free memory if available. . The kernel determines the memory layout of the processes to a degree: it tells VM where the kernel starts and ends and where the kernel wants the top of the process to be. VM then uses this entire range, i.e. the stack is right at the top, and mmap()ped bits of memory are placed below that downwards, and the break grows upwards. Other Consequences: . Every process gets its own page table as address spaces can't be separated any more by segments. . As all segments are 0-based, there is no distinction between virtual and linear addresses, nor between userspace and kernel addresses. . Less work is done when context switching, leading to a net performance increase. (8% faster on my machine for 'make servers'.) . The layout and configuration of the GDT makes sysenter and syscall possible.
2012-05-07 16:03:35 +02:00
char val[MULTIBOOT_PARAM_BUF_SIZE];
char *e;
int r;
/* Try to get a copy of the boot monitor parameters. */
if ((r = sys_getmonparams(val, sizeof(val))) != OK) {
printf("IS: warning: couldn't get copy of monitor params: %d\n", r);
return;
}
/* Append new lines to the result. */
e = val;
do {
e += strlen(e);
*e++ = '\n';
} while (*e != 0);
/* Finally, print the result. */
printf("Dump of kernel environment strings set by boot monitor.\n");
printf("\n%s\n", val);
}
/*===========================================================================*
* irqtab_dmp *
*===========================================================================*/
2012-03-25 20:25:53 +02:00
void irqtab_dmp()
{
2005-08-25 14:04:36 +02:00
int i,r;
struct irq_hook irq_hooks[NR_IRQ_HOOKS];
2006-01-12 15:41:40 +01:00
int irq_actids[NR_IRQ_VECTORS];
struct irq_hook *e; /* irq tab entry */
if ((r = sys_getirqhooks(irq_hooks)) != OK) {
printf("IS: warning: couldn't get copy of irq hooks: %d\n", r);
return;
}
2006-01-12 15:41:40 +01:00
if ((r = sys_getirqactids(irq_actids)) != OK) {
printf("IS: warning: couldn't get copy of irq mask: %d\n", r);
2006-01-12 15:41:40 +01:00
return;
}
#if 0
2006-02-24 13:55:00 +01:00
printf("irq_actids:");
2006-01-12 15:41:40 +01:00
for (i= 0; i<NR_IRQ_VECTORS; i++)
2006-02-24 13:55:00 +01:00
printf(" [%d] = 0x%08x", i, irq_actids[i]);
printf("\n");
2006-01-12 15:41:40 +01:00
#endif
printf("IRQ policies dump shows use of kernel's IRQ hooks.\n");
2010-05-26 10:44:50 +02:00
printf("-h.id- -proc.nr- -irq nr- -policy- -notify id- -masked-\n");
for (i=0; i<NR_IRQ_HOOKS; i++) {
e = &irq_hooks[i];
printf("%3d", i);
endpoint-aware conversion of servers. 'who', indicating caller number in pm and fs and some other servers, has been removed in favour of 'who_e' (endpoint) and 'who_p' (proc nr.). In both PM and FS, isokendpt() convert endpoints to process slot numbers, returning OK if it was a valid and consistent endpoint number. okendpt() does the same but panic()s if it doesn't succeed. (In PM, this is pm_isok..) pm and fs keep their own records of process endpoints in their proc tables, which are needed to make kernel calls about those processes. message field names have changed. fs drivers are endpoints. fs now doesn't try to get out of driver deadlock, as the protocol isn't supposed to let that happen any more. (A warning is printed if ELOCKED is detected though.) fproc[].fp_task (indicating which driver the process is suspended on) became an int. PM and FS now get endpoint numbers of initial boot processes from the kernel. These happen to be the same as the old proc numbers, to let user processes reach them with the old numbers, but FS and PM don't know that. All new processes after INIT, even after the generation number wraps around, get endpoint numbers with generation 1 and higher, so the first instances of the boot processes are the only processes ever to have endpoint numbers in the old proc number range. More return code checks of sys_* functions have been added. IS has become endpoint-aware. Ditched the 'text' and 'data' fields in the kernel dump (which show locations, not sizes, so aren't terribly useful) in favour of the endpoint number. Proc number is still visible. Some other dumps (e.g. dmap, rs) show endpoint numbers now too which got the formatting changed. PM reading segments using rw_seg() has changed - it uses other fields in the message now instead of encoding the segment and process number and fd in the fd field. For that it uses _read_pm() and _write_pm() which to _taskcall()s directly in pm/misc.c. PM now sys_exit()s itself on panic(), instead of sys_abort(). RS also talks in endpoints instead of process numbers.
2006-03-03 11:20:58 +01:00
if (e->proc_nr_e==NONE) {
printf(" <unused>\n");
continue;
}
endpoint-aware conversion of servers. 'who', indicating caller number in pm and fs and some other servers, has been removed in favour of 'who_e' (endpoint) and 'who_p' (proc nr.). In both PM and FS, isokendpt() convert endpoints to process slot numbers, returning OK if it was a valid and consistent endpoint number. okendpt() does the same but panic()s if it doesn't succeed. (In PM, this is pm_isok..) pm and fs keep their own records of process endpoints in their proc tables, which are needed to make kernel calls about those processes. message field names have changed. fs drivers are endpoints. fs now doesn't try to get out of driver deadlock, as the protocol isn't supposed to let that happen any more. (A warning is printed if ELOCKED is detected though.) fproc[].fp_task (indicating which driver the process is suspended on) became an int. PM and FS now get endpoint numbers of initial boot processes from the kernel. These happen to be the same as the old proc numbers, to let user processes reach them with the old numbers, but FS and PM don't know that. All new processes after INIT, even after the generation number wraps around, get endpoint numbers with generation 1 and higher, so the first instances of the boot processes are the only processes ever to have endpoint numbers in the old proc number range. More return code checks of sys_* functions have been added. IS has become endpoint-aware. Ditched the 'text' and 'data' fields in the kernel dump (which show locations, not sizes, so aren't terribly useful) in favour of the endpoint number. Proc number is still visible. Some other dumps (e.g. dmap, rs) show endpoint numbers now too which got the formatting changed. PM reading segments using rw_seg() has changed - it uses other fields in the message now instead of encoding the segment and process number and fd in the fd field. For that it uses _read_pm() and _write_pm() which to _taskcall()s directly in pm/misc.c. PM now sys_exit()s itself on panic(), instead of sys_abort(). RS also talks in endpoints instead of process numbers.
2006-03-03 11:20:58 +01:00
printf("%10d ", e->proc_nr_e);
Mostly bugfixes of bugs triggered by the test set. bugfixes: SYSTEM: . removed rc->p_priv->s_flags = 0; for the priv struct shared by all user processes in get_priv(). this should only be done once. doing a SYS_PRIV_USER in sys_privctl() caused the flags of all user processes to be reset, so they were no longer PREEMPTIBLE. this happened when RS executed a policy script. (this broke test1 in the test set) VFS/MFS: . chown can change the mode of a file, and chmod arguments are only part of the full file mode so the full filemode is slightly magic. changed these calls so that the final modes are returned to VFS, so that the vnode can be kept up-to-date. (this broke test11 in the test set) MFS: . lookup() checked for sizeof(string) instead of sizeof(user_path), truncating long path names (caught by test 23) . truncate functions neglected to update ctime (this broke test16) VFS: . corner case of an empty filename lookup caused fields of a request not to be filled in in the lookup functions, not making it clear that the lookup had failed, causing messages to garbage processes, causing strange failures. (caught by test 30) . trust v_size in vnode when doing reads or writes on non-special files, truncating i/o where necessary; this is necessary for pipes, as MFS can't tell when a pipe has been truncated without it being told explicitly each time. when the last reader/writer on a pipe closes, tell FS about the new size using truncate_vn(). (this broke test 25, among others) . permission check for chdir() had disappeared; added a forbidden() call (caught by test 23) new code, shouldn't change anything: . introduced RTS_SET, RTS_UNSET, and RTS_ISSET macro's, and their LOCK variants. These macros set and clear the p_rts_flags field, causing a lot of duplicated logic like old_flags = rp->p_rts_flags; /* save value of the flags */ rp->p_rts_flags &= ~NO_PRIV; if (old_flags != 0 && rp->p_rts_flags == 0) lock_enqueue(rp); to change into the simpler RTS_LOCK_UNSET(rp, NO_PRIV); so the macros take care of calling dequeue() and enqueue() (or lock_*()), as the case may be). This makes the code a bit more readable and a bit less fragile. . removed return code from do_clocktick in CLOCK as it currently never replies . removed some debug code from VFS . fixed grant debug message in device.c preemptive checks, tests, changes: . added return code checks of receive() to SYSTEM and CLOCK . O_TRUNC should never arrive at MFS (added sanity check and removed O_TRUNC code) . user_path declared with PATH_MAX+1 to let it be null-terminated . checks in MFS to see if strings passed by VFS are null-terminated IS: . static irq name table thrown out
2007-02-01 18:50:02 +01:00
printf(" (%02d) ", e->irq);
printf(" %s", (e->policy & IRQ_REENABLE) ? "reenable" : " - ");
2010-07-02 14:41:19 +02:00
printf(" %4lu", e->notify_id);
2010-05-26 10:44:50 +02:00
if (irq_actids[e->irq] & e->id)
printf(" masked");
2006-01-12 15:41:40 +01:00
printf("\n");
}
printf("\n");
}
/*===========================================================================*
* image_dmp *
*===========================================================================*/
2012-03-25 20:25:53 +02:00
void image_dmp()
{
int m, r;
struct boot_image *ip;
if ((r = sys_getimage(image)) != OK) {
printf("IS: warning: couldn't get copy of image table: %d\n", r);
return;
}
printf("Image table dump showing all processes included in system image.\n");
printf("---name- -nr- flags -stack-\n");
for (m=0; m<NR_BOOT_PROCS; m++) {
ip = &image[m];
No more intel/minix segments. This commit removes all traces of Minix segments (the text/data/stack memory map abstraction in the kernel) and significance of Intel segments (hardware segments like CS, DS that add offsets to all addressing before page table translation). This ultimately simplifies the memory layout and addressing and makes the same layout possible on non-Intel architectures. There are only two types of addresses in the world now: virtual and physical; even the kernel and processes have the same virtual address space. Kernel and user processes can be distinguished at a glance as processes won't use 0xF0000000 and above. No static pre-allocated memory sizes exist any more. Changes to booting: . The pre_init.c leaves the kernel and modules exactly as they were left by the bootloader in physical memory . The kernel starts running using physical addressing, loaded at a fixed location given in its linker script by the bootloader. All code and data in this phase are linked to this fixed low location. . It makes a bootstrap pagetable to map itself to a fixed high location (also in linker script) and jumps to the high address. All code and data then use this high addressing. . All code/data symbols linked at the low addresses is prefixed by an objcopy step with __k_unpaged_*, so that that code cannot reference highly-linked symbols (which aren't valid yet) or vice versa (symbols that aren't valid any more). . The two addressing modes are separated in the linker script by collecting the unpaged_*.o objects and linking them with low addresses, and linking the rest high. Some objects are linked twice, once low and once high. . The bootstrap phase passes a lot of information (e.g. free memory list, physical location of the modules, etc.) using the kinfo struct. . After this bootstrap the low-linked part is freed. . The kernel maps in VM into the bootstrap page table so that VM can begin executing. Its first job is to make page tables for all other boot processes. So VM runs before RS, and RS gets a fully dynamic, VM-managed address space. VM gets its privilege info from RS as usual but that happens after RS starts running. . Both the kernel loading VM and VM organizing boot processes happen using the libexec logic. This removes the last reason for VM to still know much about exec() and vm/exec.c is gone. Further Implementation: . All segments are based at 0 and have a 4 GB limit. . The kernel is mapped in at the top of the virtual address space so as not to constrain the user processes. . Processes do not use segments from the LDT at all; there are no segments in the LDT any more, so no LLDT is needed. . The Minix segments T/D/S are gone and so none of the user-space or in-kernel copy functions use them. The copy functions use a process endpoint of NONE to realize it's a physical address, virtual otherwise. . The umap call only makes sense to translate a virtual address to a physical address now. . Segments-related calls like newmap and alloc_segments are gone. . All segments-related translation in VM is gone (vir2map etc). . Initialization in VM is simpler as no moving around is necessary. . VM and all other boot processes can be linked wherever they wish and will be mapped in at the right location by the kernel and VM respectively. Other changes: . The multiboot code is less special: it does not use mb_print for its diagnostics any more but uses printf() as normal, saving the output into the diagnostics buffer, only printing to the screen using the direct print functions if a panic() occurs. . The multiboot code uses the flexible 'free memory map list' style to receive the list of free memory if available. . The kernel determines the memory layout of the processes to a degree: it tells VM where the kernel starts and ends and where the kernel wants the top of the process to be. VM then uses this entire range, i.e. the stack is right at the top, and mmap()ped bits of memory are placed below that downwards, and the break grows upwards. Other Consequences: . Every process gets its own page table as address spaces can't be separated any more by segments. . As all segments are 0-based, there is no distinction between virtual and linear addresses, nor between userspace and kernel addresses. . Less work is done when context switching, leading to a net performance increase. (8% faster on my machine for 'make servers'.) . The layout and configuration of the GDT makes sysenter and syscall possible.
2012-05-07 16:03:35 +02:00
printf("%8s %4d\n", ip->proc_name, ip->proc_nr);
}
printf("\n");
}
/*===========================================================================*
* kenv_dmp *
*===========================================================================*/
2012-03-25 20:25:53 +02:00
void kenv_dmp()
{
struct kinfo kinfo;
struct machine machine;
int r;
if ((r = sys_getkinfo(&kinfo)) != OK) {
printf("IS: warning: couldn't get copy of kernel info struct: %d\n", r);
return;
}
if ((r = sys_getmachine(&machine)) != OK) {
printf("IS: warning: couldn't get copy of kernel machine struct: %d\n", r);
return;
}
2011-09-16 20:03:15 +02:00
printf("Dump of kinfo structure.\n\n");
printf("Kernel info structure:\n");
printf("- nr_procs: %3u\n", kinfo.nr_procs);
printf("- nr_tasks: %3u\n", kinfo.nr_tasks);
printf("- release: %.6s\n", kinfo.release);
printf("- version: %.6s\n", kinfo.version);
printf("\n");
}
Rewrite of boot process KERNEL CHANGES: - The kernel only knows about privileges of kernel tasks and the root system process (now RS). - Kernel tasks and the root system process are the only processes that are made schedulable by the kernel at startup. All the other processes in the boot image don't get their privileges set at startup and are inhibited from running by the RTS_NO_PRIV flag. - Removed the assumption on the ordering of processes in the boot image table. System processes can now appear in any order in the boot image table. - Privilege ids can now be assigned both statically or dynamically. The kernel assigns static privilege ids to kernel tasks and the root system process. Each id is directly derived from the process number. - User processes now all share the static privilege id of the root user process (now INIT). - sys_privctl split: we have more calls now to let RS set privileges for system processes. SYS_PRIV_ALLOW / SYS_PRIV_DISALLOW are only used to flip the RTS_NO_PRIV flag and allow / disallow a process from running. SYS_PRIV_SET_SYS / SYS_PRIV_SET_USER are used to set privileges for a system / user process. - boot image table flags split: PROC_FULLVM is the only flag that has been moved out of the privilege flags and is still maintained in the boot image table. All the other privilege flags are out of the kernel now. RS CHANGES: - RS is the only user-space process who gets to run right after in-kernel startup. - RS uses the boot image table from the kernel and three additional boot image info table (priv table, sys table, dev table) to complete the initialization of the system. - RS checks that the entries in the priv table match the entries in the boot image table to make sure that every process in the boot image gets schedulable. - RS only uses static privilege ids to set privileges for system services in the boot image. - RS includes basic memory management support to allocate the boot image buffer dynamically during initialization. The buffer shall contain the executable image of all the system services we would like to restart after a crash. - First step towards decoupling between resource provisioning and resource requirements in RS: RS must know what resources it needs to restart a process and what resources it has currently available. This is useful to tradeoff reliability and resource consumption. When required resources are missing, the process cannot be restarted. In that case, in the future, a system flag will tell RS what to do. For example, if CORE_PROC is set, RS should trigger a system-wide panic because the system can no longer function correctly without a core system process. PM CHANGES: - The process tree built at initialization time is changed to have INIT as root with pid 0, RS child of INIT and all the system services children of RS. This is required to make RS in control of all the system services. - PM no longer registers labels for system services in the boot image. This is now part of RS's initialization process.
2009-12-11 01:08:19 +01:00
/*===========================================================================*
* s_flags_str *
*===========================================================================*/
2012-03-25 20:25:53 +02:00
static char *s_flags_str(int flags)
2005-07-27 09:00:20 +02:00
{
static char str[10];
Rewrite of boot process KERNEL CHANGES: - The kernel only knows about privileges of kernel tasks and the root system process (now RS). - Kernel tasks and the root system process are the only processes that are made schedulable by the kernel at startup. All the other processes in the boot image don't get their privileges set at startup and are inhibited from running by the RTS_NO_PRIV flag. - Removed the assumption on the ordering of processes in the boot image table. System processes can now appear in any order in the boot image table. - Privilege ids can now be assigned both statically or dynamically. The kernel assigns static privilege ids to kernel tasks and the root system process. Each id is directly derived from the process number. - User processes now all share the static privilege id of the root user process (now INIT). - sys_privctl split: we have more calls now to let RS set privileges for system processes. SYS_PRIV_ALLOW / SYS_PRIV_DISALLOW are only used to flip the RTS_NO_PRIV flag and allow / disallow a process from running. SYS_PRIV_SET_SYS / SYS_PRIV_SET_USER are used to set privileges for a system / user process. - boot image table flags split: PROC_FULLVM is the only flag that has been moved out of the privilege flags and is still maintained in the boot image table. All the other privilege flags are out of the kernel now. RS CHANGES: - RS is the only user-space process who gets to run right after in-kernel startup. - RS uses the boot image table from the kernel and three additional boot image info table (priv table, sys table, dev table) to complete the initialization of the system. - RS checks that the entries in the priv table match the entries in the boot image table to make sure that every process in the boot image gets schedulable. - RS only uses static privilege ids to set privileges for system services in the boot image. - RS includes basic memory management support to allocate the boot image buffer dynamically during initialization. The buffer shall contain the executable image of all the system services we would like to restart after a crash. - First step towards decoupling between resource provisioning and resource requirements in RS: RS must know what resources it needs to restart a process and what resources it has currently available. This is useful to tradeoff reliability and resource consumption. When required resources are missing, the process cannot be restarted. In that case, in the future, a system flag will tell RS what to do. For example, if CORE_PROC is set, RS should trigger a system-wide panic because the system can no longer function correctly without a core system process. PM CHANGES: - The process tree built at initialization time is changed to have INIT as root with pid 0, RS child of INIT and all the system services children of RS. This is required to make RS in control of all the system services. - PM no longer registers labels for system services in the boot image. This is now part of RS's initialization process.
2009-12-11 01:08:19 +01:00
str[0] = (flags & PREEMPTIBLE) ? 'P' : '-';
str[1] = (flags & BILLABLE) ? 'B' : '-';
str[2] = (flags & DYN_PRIV_ID) ? 'D' : '-';
str[3] = (flags & SYS_PROC) ? 'S' : '-';
str[4] = (flags & CHECK_IO_PORT) ? 'I' : '-';
str[5] = (flags & CHECK_IRQ) ? 'Q' : '-';
str[6] = (flags & CHECK_MEM) ? 'M' : '-';
str[7] = '\0';
return str;
}
Rewrite of boot process KERNEL CHANGES: - The kernel only knows about privileges of kernel tasks and the root system process (now RS). - Kernel tasks and the root system process are the only processes that are made schedulable by the kernel at startup. All the other processes in the boot image don't get their privileges set at startup and are inhibited from running by the RTS_NO_PRIV flag. - Removed the assumption on the ordering of processes in the boot image table. System processes can now appear in any order in the boot image table. - Privilege ids can now be assigned both statically or dynamically. The kernel assigns static privilege ids to kernel tasks and the root system process. Each id is directly derived from the process number. - User processes now all share the static privilege id of the root user process (now INIT). - sys_privctl split: we have more calls now to let RS set privileges for system processes. SYS_PRIV_ALLOW / SYS_PRIV_DISALLOW are only used to flip the RTS_NO_PRIV flag and allow / disallow a process from running. SYS_PRIV_SET_SYS / SYS_PRIV_SET_USER are used to set privileges for a system / user process. - boot image table flags split: PROC_FULLVM is the only flag that has been moved out of the privilege flags and is still maintained in the boot image table. All the other privilege flags are out of the kernel now. RS CHANGES: - RS is the only user-space process who gets to run right after in-kernel startup. - RS uses the boot image table from the kernel and three additional boot image info table (priv table, sys table, dev table) to complete the initialization of the system. - RS checks that the entries in the priv table match the entries in the boot image table to make sure that every process in the boot image gets schedulable. - RS only uses static privilege ids to set privileges for system services in the boot image. - RS includes basic memory management support to allocate the boot image buffer dynamically during initialization. The buffer shall contain the executable image of all the system services we would like to restart after a crash. - First step towards decoupling between resource provisioning and resource requirements in RS: RS must know what resources it needs to restart a process and what resources it has currently available. This is useful to tradeoff reliability and resource consumption. When required resources are missing, the process cannot be restarted. In that case, in the future, a system flag will tell RS what to do. For example, if CORE_PROC is set, RS should trigger a system-wide panic because the system can no longer function correctly without a core system process. PM CHANGES: - The process tree built at initialization time is changed to have INIT as root with pid 0, RS child of INIT and all the system services children of RS. This is required to make RS in control of all the system services. - PM no longer registers labels for system services in the boot image. This is now part of RS's initialization process.
2009-12-11 01:08:19 +01:00
/*===========================================================================*
* s_traps_str *
*===========================================================================*/
2012-03-25 20:25:53 +02:00
static char *s_traps_str(int flags)
{
static char str[10];
str[0] = (flags & (1 << SEND)) ? 'S' : '-';
str[1] = (flags & (1 << SENDA)) ? 'A' : '-';
str[2] = (flags & (1 << RECEIVE)) ? 'R' : '-';
str[3] = (flags & (1 << SENDREC)) ? 'B' : '-';
str[4] = (flags & (1 << NOTIFY)) ? 'N' : '-';
str[5] = '\0';
2005-07-27 09:00:20 +02:00
return str;
}
/*===========================================================================*
* privileges_dmp *
*===========================================================================*/
2012-03-25 20:25:53 +02:00
void privileges_dmp()
{
register struct proc *rp;
static struct proc *oldrp = BEG_PROC_ADDR;
register struct priv *sp;
int r, i;
/* First obtain a fresh copy of the current process and system table. */
if ((r = sys_getprivtab(priv)) != OK) {
printf("IS: warning: couldn't get copy of system privileges table: %d\n", r);
return;
}
if ((r = sys_getproctab(proc)) != OK) {
printf("IS: warning: couldn't get copy of process table: %d\n", r);
return;
}
printf("-nr- -id- -name-- -flags- traps grants -ipc_to--"
" -kernel calls-\n");
PROCLOOP(rp, oldrp)
r = -1;
for (sp = &priv[0]; sp < &priv[NR_SYS_PROCS]; sp++)
if (sp->s_proc_nr == rp->p_nr) { r ++; break; }
if (r == -1 && !isemptyp(rp)) {
sp = &priv[USER_PRIV_ID];
}
printf("(%02u) %-7.7s %s %s %6d",
sp->s_id, rp->p_name,
s_flags_str(sp->s_flags), s_traps_str(sp->s_trap_mask),
sp->s_grant_entries);
for (i=0; i < NR_SYS_PROCS; i += BITCHUNK_BITS) {
printf(" %08x", get_sys_bits(sp->s_ipc_to, i));
}
printf(" ");
for (i=0; i < NR_SYS_CALLS; i += BITCHUNK_BITS) {
printf(" %08x", sp->s_k_call_mask[i/BITCHUNK_BITS]);
}
printf("\n");
}
}
Rewrite of boot process KERNEL CHANGES: - The kernel only knows about privileges of kernel tasks and the root system process (now RS). - Kernel tasks and the root system process are the only processes that are made schedulable by the kernel at startup. All the other processes in the boot image don't get their privileges set at startup and are inhibited from running by the RTS_NO_PRIV flag. - Removed the assumption on the ordering of processes in the boot image table. System processes can now appear in any order in the boot image table. - Privilege ids can now be assigned both statically or dynamically. The kernel assigns static privilege ids to kernel tasks and the root system process. Each id is directly derived from the process number. - User processes now all share the static privilege id of the root user process (now INIT). - sys_privctl split: we have more calls now to let RS set privileges for system processes. SYS_PRIV_ALLOW / SYS_PRIV_DISALLOW are only used to flip the RTS_NO_PRIV flag and allow / disallow a process from running. SYS_PRIV_SET_SYS / SYS_PRIV_SET_USER are used to set privileges for a system / user process. - boot image table flags split: PROC_FULLVM is the only flag that has been moved out of the privilege flags and is still maintained in the boot image table. All the other privilege flags are out of the kernel now. RS CHANGES: - RS is the only user-space process who gets to run right after in-kernel startup. - RS uses the boot image table from the kernel and three additional boot image info table (priv table, sys table, dev table) to complete the initialization of the system. - RS checks that the entries in the priv table match the entries in the boot image table to make sure that every process in the boot image gets schedulable. - RS only uses static privilege ids to set privileges for system services in the boot image. - RS includes basic memory management support to allocate the boot image buffer dynamically during initialization. The buffer shall contain the executable image of all the system services we would like to restart after a crash. - First step towards decoupling between resource provisioning and resource requirements in RS: RS must know what resources it needs to restart a process and what resources it has currently available. This is useful to tradeoff reliability and resource consumption. When required resources are missing, the process cannot be restarted. In that case, in the future, a system flag will tell RS what to do. For example, if CORE_PROC is set, RS should trigger a system-wide panic because the system can no longer function correctly without a core system process. PM CHANGES: - The process tree built at initialization time is changed to have INIT as root with pid 0, RS child of INIT and all the system services children of RS. This is required to make RS in control of all the system services. - PM no longer registers labels for system services in the boot image. This is now part of RS's initialization process.
2009-12-11 01:08:19 +01:00
/*===========================================================================*
* p_rts_flags_str *
*===========================================================================*/
2012-03-25 20:25:53 +02:00
static char *p_rts_flags_str(int flags)
{
static char str[10];
str[0] = (flags & RTS_PROC_STOP) ? 's' : '-';
str[1] = (flags & RTS_SENDING) ? 'S' : '-';
str[2] = (flags & RTS_RECEIVING) ? 'R' : '-';
str[3] = (flags & RTS_SIGNALED) ? 'I' : '-';
str[4] = (flags & RTS_SIG_PENDING) ? 'P' : '-';
str[5] = (flags & RTS_P_STOP) ? 'T' : '-';
str[6] = (flags & RTS_NO_PRIV) ? 'p' : '-';
str[7] = '\0';
return str;
}
/*===========================================================================*
* proctab_dmp *
*===========================================================================*/
#if (CHIP == INTEL)
2012-03-25 20:25:53 +02:00
void proctab_dmp()
{
/* Proc table dump */
register struct proc *rp;
static struct proc *oldrp = BEG_PROC_ADDR;
int r;
/* First obtain a fresh copy of the current process table. */
if ((r = sys_getproctab(proc)) != OK) {
printf("IS: warning: couldn't get copy of process table: %d\n", r);
return;
}
printf("\n-nr-----gen---endpoint-name--- -prior-quant- -user----sys-rtsflags-from/to-\n");
PROCLOOP(rp, oldrp)
2006-03-03 17:34:37 +01:00
printf(" %5d %10d ", _ENDPOINT_G(rp->p_endpoint), rp->p_endpoint);
2010-07-02 14:41:19 +02:00
printf("%-8.8s %5u %5u %6lu %6lu ",
rp->p_name,
Userspace scheduling - cotributed by Bjorn Swift - In this first phase, scheduling is moved from the kernel to the PM server. The next steps are to a) moving scheduling to its own server and b) include useful information in the "out of quantum" message, so that the scheduler can make use of this information. - The kernel process table now keeps record of who is responsible for scheduling each process (p_scheduler). When this pointer is NULL, the process will be scheduled by the kernel. If such a process runs out of quantum, the kernel will simply renew its quantum an requeue it. - When PM loads, it will take over scheduling of all running processes, except system processes, using sys_schedctl(). Essentially, this only results in taking over init. As children inherit a scheduler from their parent, user space programs forked by init will inherit PM (for now) as their scheduler. - Once a process has been assigned a scheduler, and runs out of quantum, its RTS_NO_QUANTUM flag will be set and the process dequeued. The kernel will send a message to the scheduler, on the process' behalf, informing the scheduler that it has run out of quantum. The scheduler can take what ever action it pleases, based on its policy, and then reschedule the process using the sys_schedule() system call. - Balance queues does not work as before. While the old in-kernel function used to renew the quantum of processes in the highest priority run queue, the user-space implementation only acts on processes that have been bumped down to a lower priority queue. This approach reacts slower to changes than the old one, but saves us sending a sys_schedule message for each process every time we balance the queues. Currently, when processes are moved up a priority queue, their quantum is also renewed, but this can be fiddled with. - do_nice has been removed from kernel. PM answers to get- and setpriority calls, updates it's own nice variable as well as the max_run_queue. This will be refactored once scheduling is moved to a separate server. We will probably have PM update it's local nice value and then send a message to whoever is scheduling the process. - changes to fix an issue in do_fork() where processes could run out of quantum but bypassing the code path that handles it correctly. The future plan is to remove the policy from do_fork() and implement it in userspace too.
2010-03-29 13:07:20 +02:00
rp->p_priority,
2010-05-26 09:16:39 +02:00
rp->p_quantum_size_ms,
rp->p_user_time, rp->p_sys_time);
PRINTRTS(rp);
printf("\n");
}
}
#endif /* (CHIP == INTEL) */
/*===========================================================================*
* procstack_dmp *
*===========================================================================*/
2012-03-25 20:25:53 +02:00
void procstack_dmp()
{
/* Proc table dump, with stack */
register struct proc *rp;
static struct proc *oldrp = BEG_PROC_ADDR;
int r;
/* First obtain a fresh copy of the current process table. */
if ((r = sys_getproctab(proc)) != OK) {
printf("IS: warning: couldn't get copy of process table: %d\n", r);
return;
}
printf("\n-nr-rts flags-- --stack--\n");
PROCLOOP(rp, oldrp)
PRINTRTS(rp);
sys_sysctl_stacktrace(rp->p_endpoint);
}
}
/*===========================================================================*
* proc_name *
*===========================================================================*/
2012-03-25 20:25:53 +02:00
static char *proc_name(proc_nr)
int proc_nr;
{
struct proc *p;
if (proc_nr == ANY) return "ANY";
if (proc_nr == NONE) return "NONE"; /* bogus */
if (proc_nr < -NR_TASKS || proc_nr >= NR_PROCS) return "BOGUS";
2010-06-08 15:38:44 +02:00
p = proc_addr(proc_nr);
if (isemptyp(p)) return "EMPTY"; /* bogus */
return p->p_name;
}