// // File-system system calls. // Mostly argument checking, since we don't trust // user code, and calls into file.c and fs.c. // #include "types.h" #include "riscv.h" #include "defs.h" #include "param.h" #include "stat.h" #include "spinlock.h" #include "proc.h" #include "fs.h" #include "sleeplock.h" #include "file.h" #include "fcntl.h" // Fetch the nth word-sized system call argument as a file descriptor // and return both the descriptor and the corresponding struct file. static int argfd(int n, int *pfd, struct file **pf) { int fd; struct file *f; argint(n, &fd); if(fd < 0 || fd >= NOFILE || (f=myproc()->ofile[fd]) == 0) return -1; if(pfd) *pfd = fd; if(pf) *pf = f; return 0; } // Allocate a file descriptor for the given file. // Takes over file reference from caller on success. static int fdalloc(struct file *f) { int fd; struct proc *p = myproc(); for(fd = 0; fd < NOFILE; fd++){ if(p->ofile[fd] == 0){ p->ofile[fd] = f; return fd; } } return -1; } uint64 sys_dup(void) { struct file *f; int fd; if(argfd(0, 0, &f) < 0) return -1; if((fd=fdalloc(f)) < 0) return -1; filedup(f); return fd; } uint64 sys_read(void) { struct file *f; int n; uint64 p; argaddr(1, &p); argint(2, &n); if(argfd(0, 0, &f) < 0) return -1; return fileread(f, p, n); } uint64 sys_write(void) { struct file *f; int n; uint64 p; argaddr(1, &p); argint(2, &n); if(argfd(0, 0, &f) < 0) return -1; return filewrite(f, p, n); } uint64 sys_close(void) { int fd; struct file *f; if(argfd(0, &fd, &f) < 0) return -1; myproc()->ofile[fd] = 0; fileclose(f); return 0; } uint64 sys_fstat(void) { struct file *f; uint64 st; // user pointer to struct stat argaddr(1, &st); if(argfd(0, 0, &f) < 0) return -1; return filestat(f, st); } // Create the path new as a link to the same inode as old. uint64 sys_link(void) { char name[DIRSIZ], new[MAXPATH], old[MAXPATH]; struct inode *dp, *ip; if(argstr(0, old, MAXPATH) < 0 || argstr(1, new, MAXPATH) < 0) return -1; begin_op(); if((ip = namei(old)) == 0){ end_op(); return -1; } ilock(ip); if(ip->type == T_DIR){ iunlockput(ip); end_op(); return -1; } ip->nlink++; iupdate(ip); iunlock(ip); if((dp = nameiparent(new, name)) == 0) goto bad; ilock(dp); if(dp->dev != ip->dev || dirlink(dp, name, ip->inum) < 0){ iunlockput(dp); goto bad; } iunlockput(dp); iput(ip); end_op(); return 0; bad: ilock(ip); ip->nlink--; iupdate(ip); iunlockput(ip); end_op(); return -1; } // Is the directory dp empty except for "." and ".." ? static int isdirempty(struct inode *dp) { int off; struct dirent de; for(off=2*sizeof(de); offsize; off+=sizeof(de)){ if(readi(dp, 0, (uint64)&de, off, sizeof(de)) != sizeof(de)) panic("isdirempty: readi"); if(de.inum != 0) return 0; } return 1; } uint64 sys_unlink(void) { struct inode *ip, *dp; struct dirent de; char name[DIRSIZ], path[MAXPATH]; uint off; if(argstr(0, path, MAXPATH) < 0) return -1; begin_op(); if((dp = nameiparent(path, name)) == 0){ end_op(); return -1; } ilock(dp); // Cannot unlink "." or "..". if(namecmp(name, ".") == 0 || namecmp(name, "..") == 0) goto bad; if((ip = dirlookup(dp, name, &off)) == 0) goto bad; ilock(ip); if(ip->nlink < 1) panic("unlink: nlink < 1"); if(ip->type == T_DIR && !isdirempty(ip)){ iunlockput(ip); goto bad; } memset(&de, 0, sizeof(de)); if(writei(dp, 0, (uint64)&de, off, sizeof(de)) != sizeof(de)) panic("unlink: writei"); if(ip->type == T_DIR){ dp->nlink--; iupdate(dp); } iunlockput(dp); ip->nlink--; iupdate(ip); iunlockput(ip); end_op(); return 0; bad: iunlockput(dp); end_op(); return -1; } static struct inode* create(char *path, short type, short major, short minor) { struct inode *ip, *dp; char name[DIRSIZ]; if((dp = nameiparent(path, name)) == 0) return 0; ilock(dp); if((ip = dirlookup(dp, name, 0)) != 0){ iunlockput(dp); ilock(ip); if(type == T_FILE && (ip->type == T_FILE || ip->type == T_DEVICE)) return ip; iunlockput(ip); return 0; } if((ip = ialloc(dp->dev, type)) == 0){ iunlockput(dp); return 0; } ilock(ip); ip->major = major; ip->minor = minor; ip->nlink = 1; iupdate(ip); if(type == T_DIR){ // Create . and .. entries. // No ip->nlink++ for ".": avoid cyclic ref count. if(dirlink(ip, ".", ip->inum) < 0 || dirlink(ip, "..", dp->inum) < 0) goto fail; } if(dirlink(dp, name, ip->inum) < 0) goto fail; if(type == T_DIR){ // now that success is guaranteed: dp->nlink++; // for ".." iupdate(dp); } iunlockput(dp); return ip; fail: // something went wrong. de-allocate ip. ip->nlink = 0; iupdate(ip); iunlockput(ip); iunlockput(dp); return 0; } uint64 sys_open(void) { char path[MAXPATH]; int fd, omode; struct file *f; struct inode *ip; int n; argint(1, &omode); if((n = argstr(0, path, MAXPATH)) < 0) return -1; begin_op(); if(omode & O_CREATE){ ip = create(path, T_FILE, 0, 0); if(ip == 0){ end_op(); return -1; } } else { if((ip = namei(path)) == 0){ end_op(); return -1; } ilock(ip); if(ip->type == T_DIR && omode != O_RDONLY){ iunlockput(ip); end_op(); return -1; } } if(ip->type == T_DEVICE && (ip->major < 0 || ip->major >= NDEV)){ iunlockput(ip); end_op(); return -1; } if((f = filealloc()) == 0 || (fd = fdalloc(f)) < 0){ if(f) fileclose(f); iunlockput(ip); end_op(); return -1; } if(ip->type == T_DEVICE){ f->type = FD_DEVICE; f->major = ip->major; } else { f->type = FD_INODE; f->off = 0; } f->ip = ip; f->readable = !(omode & O_WRONLY); f->writable = (omode & O_WRONLY) || (omode & O_RDWR); if((omode & O_TRUNC) && ip->type == T_FILE){ itrunc(ip); } iunlock(ip); end_op(); return fd; } uint64 sys_mkdir(void) { char path[MAXPATH]; struct inode *ip; begin_op(); if(argstr(0, path, MAXPATH) < 0 || (ip = create(path, T_DIR, 0, 0)) == 0){ end_op(); return -1; } iunlockput(ip); end_op(); return 0; } uint64 sys_mknod(void) { struct inode *ip; char path[MAXPATH]; int major, minor; begin_op(); argint(1, &major); argint(2, &minor); if((argstr(0, path, MAXPATH)) < 0 || (ip = create(path, T_DEVICE, major, minor)) == 0){ end_op(); return -1; } iunlockput(ip); end_op(); return 0; } uint64 sys_chdir(void) { char path[MAXPATH]; struct inode *ip; struct proc *p = myproc(); begin_op(); if(argstr(0, path, MAXPATH) < 0 || (ip = namei(path)) == 0){ end_op(); return -1; } ilock(ip); if(ip->type != T_DIR){ iunlockput(ip); end_op(); return -1; } iunlock(ip); iput(p->cwd); end_op(); p->cwd = ip; return 0; } uint64 sys_exec(void) { char path[MAXPATH], *argv[MAXARG]; int i; uint64 uargv, uarg; argaddr(1, &uargv); if(argstr(0, path, MAXPATH) < 0) { return -1; } memset(argv, 0, sizeof(argv)); for(i=0;; i++){ if(i >= NELEM(argv)){ goto bad; } if(fetchaddr(uargv+sizeof(uint64)*i, (uint64*)&uarg) < 0){ goto bad; } if(uarg == 0){ argv[i] = 0; break; } argv[i] = kalloc(); if(argv[i] == 0) goto bad; if(fetchstr(uarg, argv[i], PGSIZE) < 0) goto bad; } int ret = exec(path, argv); for(i = 0; i < NELEM(argv) && argv[i] != 0; i++) kfree(argv[i]); return ret; bad: for(i = 0; i < NELEM(argv) && argv[i] != 0; i++) kfree(argv[i]); return -1; } uint64 sys_pipe(void) { uint64 fdarray; // user pointer to array of two integers struct file *rf, *wf; int fd0, fd1; struct proc *p = myproc(); argaddr(0, &fdarray); if(pipealloc(&rf, &wf) < 0) return -1; fd0 = -1; if((fd0 = fdalloc(rf)) < 0 || (fd1 = fdalloc(wf)) < 0){ if(fd0 >= 0) p->ofile[fd0] = 0; fileclose(rf); fileclose(wf); return -1; } if(copyout(p->pagetable, fdarray, (char*)&fd0, sizeof(fd0)) < 0 || copyout(p->pagetable, fdarray+sizeof(fd0), (char *)&fd1, sizeof(fd1)) < 0){ p->ofile[fd0] = 0; p->ofile[fd1] = 0; fileclose(rf); fileclose(wf); return -1; } return 0; } const struct vma Null= {.addr=0,.len=0,.prot=0,.flags=0,.file=(struct file*)0,.offset=0,.vis=0}; uint64 sys_mmap(void) { uint64 addr,len; int prot, flags, fd, offset; argaddr(0, &addr); argaddr(1, &len), argint(2, &prot), argint(3, &flags), argint(4, &fd), argint(5, &offset); struct proc *p = myproc(); struct vma *vma = p->vma; if((!p->ofile[fd]->readable) && (prot & PROT_READ)) goto err1; if((!p->ofile[fd]->writable) && (prot &PROT_WRITE) && (flags & MAP_SHARED)) goto err1; uint64 ret = p->sz; for (int i = 0; i < NVMA; ++i) // don't process when it's full if (vma[i].len == Null.len) { // getting a mem size of 0 seems crazy vma[i].addr=ret;//addr is always 0, and ret is the position vma[i].len=len; vma[i].prot=prot; vma[i].flags=flags;// which is MAP flags vma[i].file=p->ofile[fd]; filedup(vma[i].file);//increased ref here vma[i].offset=offset; vma[i].vis=0; p->sz+=len; return ret; } err1: return -1; } void shrink_vma(){ struct proc *p=myproc(); //DEBUG(); while(1){ int found=0; int i; for(i=0;ivma[i].vis==-1 && p->vma[i].addr+p->vma[i].len==p->sz){ found=1; break; } if(!found) break; #ifdef CHECK_IF_EXISTS printf("current sz=%lu\n",p->sz); #endif p->sz-=p->vma[i].len; p->vma[i]=Null; } } int munmap(uint64 Argaddr,uint64 Arglen){ struct proc *p=myproc(); // well it's possible that the passed addr and len does not match a munmap // how do I know that all of the pages of an mmap zone has been removed --using vis // don't do crazy things like unmap two different mmap area at same time --it's fine, no such operation in test for(int i=0;ivma[i].addr; const int offset=p->vma[i].offset; struct file *file=p->vma[i].file; struct inode *ip=file->ip; const int len=p->vma[i].len; int *vis=&p->vma[i].vis; const int map_flag=p->vma[i].flags; if(*vis!=-1 && len >0 && PGROUNDDOWN(addr) + len >= Argaddr+Arglen && PGROUNDDOWN(addr) <= Argaddr){ // for(int i=0;ipagetable,cur,0); if(pte!=0 && (*pte & PTE_V)!=0){ // this page may not actually allocated // wait what happens for uvmunmap, if there's a mmap page between normal pages... --I bet this won't happen if(map_flag & (MAP_SHARED)){// write back begin_op(); // don't forget begin_op ilock(ip); const uint sz=ip->size; const int pos=offset+(cur-addr); const uint remain=sz-pos; if(writei(ip,1,cur,pos,PGSIZEpagetable,cur,1,1); } *vis |= 1<>i; if(all_clear){ // clear this vma // wait, what happens if this vma is the highest address? // and, it's responsible for exit, to call munmap in a dereasing order //if(p->sz == addr+len) //p->sz-=len; // release the file fileclose(file); // clean this vma //p->vma[i]=Null;// well, I don't need those pointers at all... p->vma[i].vis=-1; shrink_vma(); } return 0; err2: iunlock(ip); goto err1; } } err1: // hey! why did a uint64 func return -1?? return -1; //default not found } uint64 sys_munmap(void) { uint64 Argaddr,Arglen; argaddr(0,&Argaddr),argaddr(1,&Arglen); return munmap(Argaddr,Arglen); } int lazymap(uint64 va){ struct proc *p=myproc(); if(va>=p->sz) goto err1; uint64 scause=r_scause(); for(int i=0;ivma[i].addr; const int vma_flag=p->vma[i].prot; const int offset=p->vma[i].offset; struct file *file=p->vma[i].file; struct inode *ip=file->ip; const int len=p->vma[i].len; const int vis=p->vma[i].vis; // each addr and len won't intersect with each other, it's defined by sys_mmap process // it's > not >=, however // we must make sure that this va is within the range if(vis!=-1 && len > 0 && PGROUNDDOWN(addr) + len>va && PGROUNDDOWN(addr)<=va){// it's considered that addr is page-aligned const int x=(va-addr)/PGSIZE; if((1<pagetable,va,PGSIZE,(uint64)mem,pte_flag)<0){ kfree(mem); goto err1; } // why I need to call readi?? // oh, that's because I can't get file+offset directly... ilock(ip); // readi won't increase inode ref if(readi(ip,0,(uint64)mem,offset + (va-addr),PGSIZE)<=0) goto err2; // file pointer handles ref to inode, so don't increase inode ref there iunlock(ip); return 0; err2: uvmunmap(p->pagetable,va,1,1); iunlock(ip); goto err1; } } err1: return -1; }