summaryrefslogtreecommitdiffstats
path: root/fs
diff options
context:
space:
mode:
Diffstat (limited to 'fs')
-rw-r--r--fs/Kconfig.binfmt4
-rw-r--r--fs/Makefile1
-rw-r--r--fs/aio.c2
-rw-r--r--fs/binfmt_elf.c677
-rw-r--r--fs/compat_binfmt_elf.c131
-rw-r--r--fs/dlm/dir.c76
-rw-r--r--fs/dlm/dlm_internal.h16
-rw-r--r--fs/dlm/lock.c249
-rw-r--r--fs/dlm/lock.h2
-rw-r--r--fs/dlm/lockspace.c16
-rw-r--r--fs/dlm/lowcomms.c15
-rw-r--r--fs/dlm/main.c10
-rw-r--r--fs/dlm/member.c4
-rw-r--r--fs/dlm/member.h3
-rw-r--r--fs/dlm/memory.c32
-rw-r--r--fs/dlm/memory.h16
-rw-r--r--fs/dlm/midcomms.c15
-rw-r--r--fs/dlm/rcom.c25
-rw-r--r--fs/dlm/recover.c27
-rw-r--r--fs/dlm/recoverd.c11
-rw-r--r--fs/dlm/user.c29
-rw-r--r--fs/dlm/util.c82
-rw-r--r--fs/jbd/checkpoint.c3
-rw-r--r--fs/jbd/commit.c2
-rw-r--r--fs/jbd2/checkpoint.c3
-rw-r--r--fs/jbd2/commit.c2
26 files changed, 1051 insertions, 402 deletions
diff --git a/fs/Kconfig.binfmt b/fs/Kconfig.binfmt
index d4fc6095466..7c3d5f923da 100644
--- a/fs/Kconfig.binfmt
+++ b/fs/Kconfig.binfmt
@@ -23,6 +23,10 @@ config BINFMT_ELF
ld.so (check the file <file:Documentation/Changes> for location and
latest version).
+config COMPAT_BINFMT_ELF
+ bool
+ depends on COMPAT && MMU
+
config BINFMT_ELF_FDPIC
bool "Kernel support for FDPIC ELF binaries"
default y
diff --git a/fs/Makefile b/fs/Makefile
index 500cf15cdb4..1e7a11bd4da 100644
--- a/fs/Makefile
+++ b/fs/Makefile
@@ -39,6 +39,7 @@ obj-$(CONFIG_BINFMT_MISC) += binfmt_misc.o
obj-y += binfmt_script.o
obj-$(CONFIG_BINFMT_ELF) += binfmt_elf.o
+obj-$(CONFIG_COMPAT_BINFMT_ELF) += compat_binfmt_elf.o
obj-$(CONFIG_BINFMT_ELF_FDPIC) += binfmt_elf_fdpic.o
obj-$(CONFIG_BINFMT_SOM) += binfmt_som.o
obj-$(CONFIG_BINFMT_FLAT) += binfmt_flat.o
diff --git a/fs/aio.c b/fs/aio.c
index 9dec7d2d546..8a37dbbf343 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -397,7 +397,7 @@ void fastcall __put_ioctx(struct kioctx *ctx)
* This prevents races between the aio code path referencing the
* req (after submitting it) and aio_complete() freeing the req.
*/
-static struct kiocb *FASTCALL(__aio_get_req(struct kioctx *ctx));
+static struct kiocb *__aio_get_req(struct kioctx *ctx);
static struct kiocb fastcall *__aio_get_req(struct kioctx *ctx)
{
struct kiocb *req = NULL;
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index f0b3171842f..18ed6dd906c 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -45,7 +45,8 @@
static int load_elf_binary(struct linux_binprm *bprm, struct pt_regs *regs);
static int load_elf_library(struct file *);
-static unsigned long elf_map (struct file *, unsigned long, struct elf_phdr *, int, int);
+static unsigned long elf_map(struct file *, unsigned long, struct elf_phdr *,
+ int, int, unsigned long);
/*
* If we don't support core dumping, then supply a NULL so we
@@ -298,33 +299,70 @@ create_elf_tables(struct linux_binprm *bprm, struct elfhdr *exec,
#ifndef elf_map
static unsigned long elf_map(struct file *filep, unsigned long addr,
- struct elf_phdr *eppnt, int prot, int type)
+ struct elf_phdr *eppnt, int prot, int type,
+ unsigned long total_size)
{
unsigned long map_addr;
- unsigned long pageoffset = ELF_PAGEOFFSET(eppnt->p_vaddr);
+ unsigned long size = eppnt->p_filesz + ELF_PAGEOFFSET(eppnt->p_vaddr);
+ unsigned long off = eppnt->p_offset - ELF_PAGEOFFSET(eppnt->p_vaddr);
+ addr = ELF_PAGESTART(addr);
+ size = ELF_PAGEALIGN(size);
- down_write(&current->mm->mmap_sem);
/* mmap() will return -EINVAL if given a zero size, but a
* segment with zero filesize is perfectly valid */
- if (eppnt->p_filesz + pageoffset)
- map_addr = do_mmap(filep, ELF_PAGESTART(addr),
- eppnt->p_filesz + pageoffset, prot, type,
- eppnt->p_offset - pageoffset);
- else
- map_addr = ELF_PAGESTART(addr);
+ if (!size)
+ return addr;
+
+ down_write(&current->mm->mmap_sem);
+ /*
+ * total_size is the size of the ELF (interpreter) image.
+ * The _first_ mmap needs to know the full size, otherwise
+ * randomization might put this image into an overlapping
+ * position with the ELF binary image. (since size < total_size)
+ * So we first map the 'big' image - and unmap the remainder at
+ * the end. (which unmap is needed for ELF images with holes.)
+ */
+ if (total_size) {
+ total_size = ELF_PAGEALIGN(total_size);
+ map_addr = do_mmap(filep, addr, total_size, prot, type, off);
+ if (!BAD_ADDR(map_addr))
+ do_munmap(current->mm, map_addr+size, total_size-size);
+ } else
+ map_addr = do_mmap(filep, addr, size, prot, type, off);
+
up_write(&current->mm->mmap_sem);
return(map_addr);
}
#endif /* !elf_map */
+static unsigned long total_mapping_size(struct elf_phdr *cmds, int nr)
+{
+ int i, first_idx = -1, last_idx = -1;
+
+ for (i = 0; i < nr; i++) {
+ if (cmds[i].p_type == PT_LOAD) {
+ last_idx = i;
+ if (first_idx == -1)
+ first_idx = i;
+ }
+ }
+ if (first_idx == -1)
+ return 0;
+
+ return cmds[last_idx].p_vaddr + cmds[last_idx].p_memsz -
+ ELF_PAGESTART(cmds[first_idx].p_vaddr);
+}
+
+
/* This is much more generalized than the library routine read function,
so we keep this separate. Technically the library read function
is only provided so that we can read a.out libraries that have
an ELF header */
static unsigned long load_elf_interp(struct elfhdr *interp_elf_ex,
- struct file *interpreter, unsigned long *interp_load_addr)
+ struct file *interpreter, unsigned long *interp_map_addr,
+ unsigned long no_base)
{
struct elf_phdr *elf_phdata;
struct elf_phdr *eppnt;
@@ -332,6 +370,7 @@ static unsigned long load_elf_interp(struct elfhdr *interp_elf_ex,
int load_addr_set = 0;
unsigned long last_bss = 0, elf_bss = 0;
unsigned long error = ~0UL;
+ unsigned long total_size;
int retval, i, size;
/* First of all, some simple consistency checks */
@@ -370,6 +409,12 @@ static unsigned long load_elf_interp(struct elfhdr *interp_elf_ex,
goto out_close;
}
+ total_size = total_mapping_size(elf_phdata, interp_elf_ex->e_phnum);
+ if (!total_size) {
+ error = -EINVAL;
+ goto out_close;
+ }
+
eppnt = elf_phdata;
for (i = 0; i < interp_elf_ex->e_phnum; i++, eppnt++) {
if (eppnt->p_type == PT_LOAD) {
@@ -387,9 +432,14 @@ static unsigned long load_elf_interp(struct elfhdr *interp_elf_ex,
vaddr = eppnt->p_vaddr;
if (interp_elf_ex->e_type == ET_EXEC || load_addr_set)
elf_type |= MAP_FIXED;
+ else if (no_base && interp_elf_ex->e_type == ET_DYN)
+ load_addr = -vaddr;
map_addr = elf_map(interpreter, load_addr + vaddr,
- eppnt, elf_prot, elf_type);
+ eppnt, elf_prot, elf_type, total_size);
+ total_size = 0;
+ if (!*interp_map_addr)
+ *interp_map_addr = map_addr;
error = map_addr;
if (BAD_ADDR(map_addr))
goto out_close;
@@ -455,8 +505,7 @@ static unsigned long load_elf_interp(struct elfhdr *interp_elf_ex,
goto out_close;
}
- *interp_load_addr = load_addr;
- error = ((unsigned long)interp_elf_ex->e_entry) + load_addr;
+ error = load_addr;
out_close:
kfree(elf_phdata);
@@ -546,14 +595,14 @@ static int load_elf_binary(struct linux_binprm *bprm, struct pt_regs *regs)
int load_addr_set = 0;
char * elf_interpreter = NULL;
unsigned int interpreter_type = INTERPRETER_NONE;
- unsigned char ibcs2_interpreter = 0;
unsigned long error;
struct elf_phdr *elf_ppnt, *elf_phdata;
unsigned long elf_bss, elf_brk;
int elf_exec_fileno;
int retval, i;
unsigned int size;
- unsigned long elf_entry, interp_load_addr = 0;
+ unsigned long elf_entry;
+ unsigned long interp_load_addr = 0;
unsigned long start_code, end_code, start_data, end_data;
unsigned long reloc_func_desc = 0;
char passed_fileno[6];
@@ -663,14 +712,6 @@ static int load_elf_binary(struct linux_binprm *bprm, struct pt_regs *regs)
if (elf_interpreter[elf_ppnt->p_filesz - 1] != '\0')
goto out_free_interp;
- /* If the program interpreter is one of these two,
- * then assume an iBCS2 image. Otherwise assume
- * a native linux image.
- */
- if (strcmp(elf_interpreter,"/usr/lib/libc.so.1") == 0 ||
- strcmp(elf_interpreter,"/usr/lib/ld.so.1") == 0)
- ibcs2_interpreter = 1;
-
/*
* The early SET_PERSONALITY here is so that the lookup
* for the interpreter happens in the namespace of the
@@ -690,7 +731,7 @@ static int load_elf_binary(struct linux_binprm *bprm, struct pt_regs *regs)
* switch really is going to happen - do this in
* flush_thread(). - akpm
*/
- SET_PERSONALITY(loc->elf_ex, ibcs2_interpreter);
+ SET_PERSONALITY(loc->elf_ex, 0);
interpreter = open_exec(elf_interpreter);
retval = PTR_ERR(interpreter);
@@ -769,7 +810,7 @@ static int load_elf_binary(struct linux_binprm *bprm, struct pt_regs *regs)
goto out_free_dentry;
} else {
/* Executables without an interpreter also need a personality */
- SET_PERSONALITY(loc->elf_ex, ibcs2_interpreter);
+ SET_PERSONALITY(loc->elf_ex, 0);
}
/* OK, we are done with that, now set up the arg stuff,
@@ -803,7 +844,7 @@ static int load_elf_binary(struct linux_binprm *bprm, struct pt_regs *regs)
/* Do this immediately, since STACK_TOP as used in setup_arg_pages
may depend on the personality. */
- SET_PERSONALITY(loc->elf_ex, ibcs2_interpreter);
+ SET_PERSONALITY(loc->elf_ex, 0);
if (elf_read_implies_exec(loc->elf_ex, executable_stack))
current->personality |= READ_IMPLIES_EXEC;
@@ -825,9 +866,7 @@ static int load_elf_binary(struct linux_binprm *bprm, struct pt_regs *regs)
current->mm->start_stack = bprm->p;
/* Now we do a little grungy work by mmaping the ELF image into
- the correct location in memory. At this point, we assume that
- the image should be loaded at fixed address, not at a variable
- address. */
+ the correct location in memory. */
for(i = 0, elf_ppnt = elf_phdata;
i < loc->elf_ex.e_phnum; i++, elf_ppnt++) {
int elf_prot = 0, elf_flags;
@@ -881,11 +920,15 @@ static int load_elf_binary(struct linux_binprm *bprm, struct pt_regs *regs)
* default mmap base, as well as whatever program they
* might try to exec. This is because the brk will
* follow the loader, and is not movable. */
+#ifdef CONFIG_X86
+ load_bias = 0;
+#else
load_bias = ELF_PAGESTART(ELF_ET_DYN_BASE - vaddr);
+#endif
}
error = elf_map(bprm->file, load_bias + vaddr, elf_ppnt,
- elf_prot, elf_flags);
+ elf_prot, elf_flags, 0);
if (BAD_ADDR(error)) {
send_sig(SIGKILL, current, 0);
retval = IS_ERR((void *)error) ?
@@ -961,13 +1004,25 @@ static int load_elf_binary(struct linux_binprm *bprm, struct pt_regs *regs)
}
if (elf_interpreter) {
- if (interpreter_type == INTERPRETER_AOUT)
+ if (interpreter_type == INTERPRETER_AOUT) {
elf_entry = load_aout_interp(&loc->interp_ex,
interpreter);
- else
+ } else {
+ unsigned long uninitialized_var(interp_map_addr);
+
elf_entry = load_elf_interp(&loc->interp_elf_ex,
interpreter,
- &interp_load_addr);
+ &interp_map_addr,
+ load_bias);
+ if (!IS_ERR((void *)elf_entry)) {
+ /*
+ * load_elf_interp() returns relocation
+ * adjustment
+ */
+ interp_load_addr = elf_entry;
+ elf_entry += loc->interp_elf_ex.e_entry;
+ }
+ }
if (BAD_ADDR(elf_entry)) {
force_sig(SIGSEGV, current);
retval = IS_ERR((void *)elf_entry) ?
@@ -1021,6 +1076,12 @@ static int load_elf_binary(struct linux_binprm *bprm, struct pt_regs *regs)
current->mm->end_data = end_data;
current->mm->start_stack = bprm->p;
+#ifdef arch_randomize_brk
+ if (current->flags & PF_RANDOMIZE)
+ current->mm->brk = current->mm->start_brk =
+ arch_randomize_brk(current->mm);
+#endif
+
if (current->personality & MMAP_PAGE_ZERO) {
/* Why this, you ask??? Well SVr4 maps page 0 as read-only,
and some applications "depend" upon this behavior.
@@ -1325,7 +1386,8 @@ static int writenote(struct memelfnote *men, struct file *file,
if (!dump_seek(file, (off))) \
goto end_coredump;
-static void fill_elf_header(struct elfhdr *elf, int segs)
+static void fill_elf_header(struct elfhdr *elf, int segs,
+ u16 machine, u32 flags, u8 osabi)
{
memcpy(elf->e_ident, ELFMAG, SELFMAG);
elf->e_ident[EI_CLASS] = ELF_CLASS;
@@ -1335,12 +1397,12 @@ static void fill_elf_header(struct elfhdr *elf, int segs)
memset(elf->e_ident+EI_PAD, 0, EI_NIDENT-EI_PAD);
elf->e_type = ET_CORE;
- elf->e_machine = ELF_ARCH;
+ elf->e_machine = machine;
elf->e_version = EV_CURRENT;
elf->e_entry = 0;
elf->e_phoff = sizeof(struct elfhdr);
elf->e_shoff = 0;
- elf->e_flags = ELF_CORE_EFLAGS;
+ elf->e_flags = flags;
elf->e_ehsize = sizeof(struct elfhdr);
elf->e_phentsize = sizeof(struct elf_phdr);
elf->e_phnum = segs;
@@ -1447,6 +1509,238 @@ static int fill_psinfo(struct elf_prpsinfo *psinfo, struct task_struct *p,
return 0;
}
+static void fill_auxv_note(struct memelfnote *note, struct mm_struct *mm)
+{
+ elf_addr_t *auxv = (elf_addr_t *) mm->saved_auxv;
+ int i = 0;
+ do
+ i += 2;
+ while (auxv[i - 2] != AT_NULL);
+ fill_note(note, "CORE", NT_AUXV, i * sizeof(elf_addr_t), auxv);
+}
+
+#ifdef CORE_DUMP_USE_REGSET
+#include <linux/regset.h>
+
+struct elf_thread_core_info {
+ struct elf_thread_core_info *next;
+ struct task_struct *task;
+ struct elf_prstatus prstatus;
+ struct memelfnote notes[0];
+};
+
+struct elf_note_info {
+ struct elf_thread_core_info *thread;
+ struct memelfnote psinfo;
+ struct memelfnote auxv;
+ size_t size;
+ int thread_notes;
+};
+
+static int fill_thread_core_info(struct elf_thread_core_info *t,
+ const struct user_regset_view *view,
+ long signr, size_t *total)
+{
+ unsigned int i;
+
+ /*
+ * NT_PRSTATUS is the one special case, because the regset data
+ * goes into the pr_reg field inside the note contents, rather
+ * than being the whole note contents. We fill the reset in here.
+ * We assume that regset 0 is NT_PRSTATUS.
+ */
+ fill_prstatus(&t->prstatus, t->task, signr);
+ (void) view->regsets[0].get(t->task, &view->regsets[0],
+ 0, sizeof(t->prstatus.pr_reg),
+ &t->prstatus.pr_reg, NULL);
+
+ fill_note(&t->notes[0], "CORE", NT_PRSTATUS,
+ sizeof(t->prstatus), &t->prstatus);
+ *total += notesize(&t->notes[0]);
+
+ /*
+ * Each other regset might generate a note too. For each regset
+ * that has no core_note_type or is inactive, we leave t->notes[i]
+ * all zero and we'll know to skip writing it later.
+ */
+ for (i = 1; i < view->n; ++i) {
+ const struct user_regset *regset = &view->regsets[i];
+ if (regset->core_note_type &&
+ (!regset->active || regset->active(t->task, regset))) {
+ int ret;
+ size_t size = regset->n * regset->size;
+ void *data = kmalloc(size, GFP_KERNEL);
+ if (unlikely(!data))
+ return 0;
+ ret = regset->get(t->task, regset,
+ 0, size, data, NULL);
+ if (unlikely(ret))
+ kfree(data);
+ else {
+ if (regset->core_note_type != NT_PRFPREG)
+ fill_note(&t->notes[i], "LINUX",
+ regset->core_note_type,
+ size, data);
+ else {
+ t->prstatus.pr_fpvalid = 1;
+ fill_note(&t->notes[i], "CORE",
+ NT_PRFPREG, size, data);
+ }
+ *total += notesize(&t->notes[i]);
+ }
+ }
+ }
+
+ return 1;
+}
+
+static int fill_note_info(struct elfhdr *elf, int phdrs,
+ struct elf_note_info *info,
+ long signr, struct pt_regs *regs)
+{
+ struct task_struct *dump_task = current;
+ const struct user_regset_view *view = task_user_regset_view(dump_task);
+ struct elf_thread_core_info *t;
+ struct elf_prpsinfo *psinfo;
+ struct task_struct *g, *p;
+ unsigned int i;
+
+ info->size = 0;
+ info->thread = NULL;
+
+ psinfo = kmalloc(sizeof(*psinfo), GFP_KERNEL);
+ fill_note(&info->psinfo, "CORE", NT_PRPSINFO, sizeof(*psinfo), psinfo);
+
+ if (psinfo == NULL)
+ return 0;
+
+ /*
+ * Figure out how many notes we're going to need for each thread.
+ */
+ info->thread_notes = 0;
+ for (i = 0; i < view->n; ++i)
+ if (view->regsets[i].core_note_type != 0)
+ ++info->thread_notes;
+
+ /*
+ * Sanity check. We rely on regset 0 being in NT_PRSTATUS,
+ * since it is our one special case.
+ */
+ if (unlikely(info->thread_notes == 0) ||
+ unlikely(view->regsets[0].core_note_type != NT_PRSTATUS)) {
+ WARN_ON(1);
+ return 0;
+ }
+
+ /*
+ * Initialize the ELF file header.
+ */
+ fill_elf_header(elf, phdrs,
+ view->e_machine, view->e_flags, view->ei_osabi);
+
+ /*
+ * Allocate a structure for each thread.
+ */
+ rcu_read_lock();
+ do_each_thread(g, p)
+ if (p->mm == dump_task->mm) {
+ t = kzalloc(offsetof(struct elf_thread_core_info,
+ notes[info->thread_notes]),
+ GFP_ATOMIC);
+ if (unlikely(!t)) {
+ rcu_read_unlock();
+ return 0;
+ }
+ t->task = p;
+ if (p == dump_task || !info->thread) {
+ t->next = info->thread;
+ info->thread = t;
+ } else {
+ /*
+ * Make sure to keep the original task at
+ * the head of the list.
+ */
+ t->next = info->thread->next;
+ info->thread->next = t;
+ }
+ }
+ while_each_thread(g, p);
+ rcu_read_unlock();
+
+ /*
+ * Now fill in each thread's information.
+ */
+ for (t = info->thread; t != NULL; t = t->next)
+ if (!fill_thread_core_info(t, view, signr, &info->size))
+ return 0;
+
+ /*
+ * Fill in the two process-wide notes.
+ */
+ fill_psinfo(psinfo, dump_task->group_leader, dump_task->mm);
+ info->size += notesize(&info->psinfo);
+
+ fill_auxv_note(&info->auxv, current->mm);
+ info->size += notesize(&info->auxv);
+
+ return 1;
+}
+
+static size_t get_note_info_size(struct elf_note_info *info)
+{
+ return info->size;
+}
+
+/*
+ * Write all the notes for each thread. When writing the first thread, the
+ * process-wide notes are interleaved after the first thread-specific note.
+ */
+static int write_note_info(struct elf_note_info *info,
+ struct file *file, loff_t *foffset)
+{
+ bool first = 1;
+ struct elf_thread_core_info *t = info->thread;
+
+ do {
+ int i;
+
+ if (!writenote(&t->notes[0], file, foffset))
+ return 0;
+
+ if (first && !writenote(&info->psinfo, file, foffset))
+ return 0;
+ if (first && !writenote(&info->auxv, file, foffset))
+ return 0;
+
+ for (i = 1; i < info->thread_notes; ++i)
+ if (t->notes[i].data &&
+ !writenote(&t->notes[i], file, foffset))
+ return 0;
+
+ first = 0;
+ t = t->next;
+ } while (t);
+
+ return 1;
+}
+
+static void free_note_info(struct elf_note_info *info)
+{
+ struct elf_thread_core_info *threads = info->thread;
+ while (threads) {
+ unsigned int i;
+ struct elf_thread_core_info *t = threads;
+ threads = t->next;
+ WARN_ON(t->notes[0].data && t->notes[0].data != &t->prstatus);
+ for (i = 1; i < info->thread_notes; ++i)
+ kfree(t->notes[i].data);
+ kfree(t);
+ }
+ kfree(info->psinfo.data);
+}
+
+#else
+
/* Here is the structure in which status of each thread is captured. */
struct elf_thread_status
{
@@ -1499,6 +1793,176 @@ static int elf_dump_thread_status(long signr, struct elf_thread_status *t)
return sz;
}
+struct elf_note_info {
+ struct memelfnote *notes;
+ struct elf_prstatus *prstatus; /* NT_PRSTATUS */
+ struct elf_prpsinfo *psinfo; /* NT_PRPSINFO */
+ struct list_head thread_list;
+ elf_fpregset_t *fpu;
+#ifdef ELF_CORE_COPY_XFPREGS
+ elf_fpxregset_t *xfpu;
+#endif
+ int thread_status_size;
+ int numnote;
+};
+
+static int fill_note_info(struct elfhdr *elf, int phdrs,
+ struct elf_note_info *info,
+ long signr, struct pt_regs *regs)
+{
+#define NUM_NOTES 6
+ struct list_head *t;
+ struct task_struct *g, *p;
+
+ info->notes = NULL;
+ info->prstatus = NULL;
+ info->psinfo = NULL;
+ info->fpu = NULL;
+#ifdef ELF_CORE_COPY_XFPREGS
+ info->xfpu = NULL;
+#endif
+ INIT_LIST_HEAD(&info->thread_list);
+
+ info->notes = kmalloc(NUM_NOTES * sizeof(struct memelfnote),
+ GFP_KERNEL);
+ if (!info->notes)
+ return 0;
+ info->psinfo = kmalloc(sizeof(*info->psinfo), GFP_KERNEL);
+ if (!info->psinfo)
+ return 0;
+ info->prstatus = kmalloc(sizeof(*info->prstatus), GFP_KERNEL);
+ if (!info->prstatus)
+ return 0;
+ info->fpu = kmalloc(sizeof(*info->fpu), GFP_KERNEL);
+ if (!info->fpu)
+ return 0;
+#ifdef ELF_CORE_COPY_XFPREGS
+ info->xfpu = kmalloc(sizeof(*info->xfpu), GFP_KERNEL);
+ if (!info->xfpu)
+ return 0;
+#endif
+
+ info->thread_status_size = 0;
+ if (signr) {
+ struct elf_thread_status *tmp;
+ rcu_read_lock();
+ do_each_thread(g, p)
+ if (current->mm == p->mm && current != p) {
+ tmp = kzalloc(sizeof(*tmp), GFP_ATOMIC);
+ if (!tmp) {
+ rcu_read_unlock();
+ return 0;
+ }
+ tmp->thread = p;
+ list_add(&tmp->list, &info->thread_list);
+ }
+ while_each_thread(g, p);
+ rcu_read_unlock();
+ list_for_each(t, &info->thread_list) {
+ struct elf_thread_status *tmp;
+ int sz;
+
+ tmp = list_entry(t, struct elf_thread_status, list);
+ sz = elf_dump_thread_status(signr, tmp);
+ info->thread_status_size += sz;
+ }
+ }
+ /* now collect the dump for the current */
+ memset(info->prstatus, 0, sizeof(*info->prstatus));
+ fill_prstatus(info->prstatus, current, signr);
+ elf_core_copy_regs(&info->prstatus->pr_reg, regs);
+
+ /* Set up header */
+ fill_elf_header(elf, phdrs, ELF_ARCH, ELF_CORE_EFLAGS, ELF_OSABI);
+
+ /*
+ * Set up the notes in similar form to SVR4 core dumps made
+ * with info from their /proc.
+ */
+
+ fill_note(info->notes + 0, "CORE", NT_PRSTATUS,
+ sizeof(*info->prstatus), info->prstatus);
+ fill_psinfo(info->psinfo, current->group_leader, current->mm);
+ fill_note(info->notes + 1, "CORE", NT_PRPSINFO,
+ sizeof(*info->psinfo), info->psinfo);
+
+ info->numnote = 2;
+
+ fill_auxv_note(&info->notes[info->numnote++], current->mm);
+
+ /* Try to dump the FPU. */
+ info->prstatus->pr_fpvalid = elf_core_copy_task_fpregs(current, regs,
+ info->fpu);
+ if (info->prstatus->pr_fpvalid)
+ fill_note(info->notes + info->numnote++,
+ "CORE", NT_PRFPREG, sizeof(*info->fpu), info->fpu);
+#ifdef ELF_CORE_COPY_XFPREGS
+ if (elf_core_copy_task_xfpregs(current, info->xfpu))
+ fill_note(info->notes + info->numnote++,
+ "LINUX", ELF_CORE_XFPREG_TYPE,
+ sizeof(*info->xfpu), info->xfpu);
+#endif
+
+ return 1;
+
+#undef NUM_NOTES
+}
+
+static size_t get_note_info_size(struct elf_note_info *info)
+{
+ int sz = 0;
+ int i;
+
+ for (i = 0; i < info->numnote; i++)
+ sz += notesize(info->notes + i);
+
+ sz += info->thread_status_size;
+
+ return sz;
+}
+
+static int write_note_info(struct elf_note_info *info,
+ struct file *file, loff_t *foffset)
+{
+ int i;
+ struct list_head *t;
+
+ for (i = 0; i < info->numnote; i++)
+ if (!writenote(info->notes + i, file, foffset))
+ return 0;
+
+ /* write out the thread status notes section */
+ list_for_each(t, &info->thread_list) {
+ struct elf_thread_status *tmp =
+ list_entry(t, struct elf_thread_status, list);
+
+ for (i = 0; i < tmp->num_notes; i++)
+ if (!writenote(&tmp->notes[i], file, foffset))
+ return 0;
+ }
+
+ return 1;
+}
+
+static void free_note_info(struct elf_note_info *info)
+{
+ while (!list_empty(&info->thread_list)) {
+ struct list_head *tmp = info->thread_list.next;
+ list_del(tmp);
+ kfree(list_entry(tmp, struct elf_thread_status, list));
+ }
+
+ kfree(info->prstatus);
+ kfree(info->psinfo);
+ kfree(info->notes);
+ kfree(info->fpu);
+#ifdef ELF_CORE_COPY_XFPREGS
+ kfree(info->xfpu);
+#endif
+}
+
+#endif
+
static struct vm_area_struct *first_vma(struct task_struct *tsk,
struct vm_area_struct *gate_vma)
{
@@ -1534,29 +1998,15 @@ static struct vm_area_struct *next_vma(struct vm_area_struct *this_vma,
*/
static int elf_core_dump(long signr, struct pt_regs *regs, struct file *file, unsigned long limit)
{
-#define NUM_NOTES 6
int has_dumped = 0;
mm_segment_t fs;
int segs;
size_t size = 0;
- int i;
struct vm_area_struct *vma, *gate_vma;
struct elfhdr *elf = NULL;
loff_t offset = 0, dataoff, foffset;
- int numnote;
- struct memelfnote *notes = NULL;
- struct elf_prstatus *prstatus = NULL; /* NT_PRSTATUS */
- struct elf_prpsinfo *psinfo = NULL; /* NT_PRPSINFO */
- struct task_struct *g, *p;
- LIST_HEAD(thread_list);
- struct list_head *t;
- elf_fpregset_t *fpu = NULL;
-#ifdef ELF_CORE_COPY_XFPREGS
- elf_fpxregset_t *xfpu = NULL;
-#endif
- int thread_status_size = 0;
- elf_addr_t *auxv;
unsigned long mm_flags;
+ struct elf_note_info info;
/*
* We no longer stop all VM operations.
@@ -1574,52 +2024,6 @@ static int elf_core_dump(long signr, struct pt_regs *regs, struct file *file, un
elf = kmalloc(sizeof(*elf), GFP_KERNEL);
if (!elf)
goto cleanup;
- prstatus = kmalloc(sizeof(*prstatus), GFP_KERNEL);
- if (!prstatus)
- goto cleanup;
- psinfo = kmalloc(sizeof(*psinfo), GFP_KERNEL);
- if (!psinfo)
- goto cleanup;
- notes = kmalloc(NUM_NOTES * sizeof(struct memelfnote), GFP_KERNEL);
- if (!notes)
- goto cleanup;
- fpu = kmalloc(sizeof(*fpu), GFP_KERNEL);
- if (!fpu)
- goto cleanup;
-#ifdef ELF_CORE_COPY_XFPREGS
- xfpu = kmalloc(sizeof(*xfpu), GFP_KERNEL);
- if (!xfpu)
- goto cleanup;
-#endif
-
- if (signr) {
- struct elf_thread_status *tmp;
- rcu_read_lock();
- do_each_thread(g,p)
- if (current->mm == p->mm && current != p) {
- tmp = kzalloc(sizeof(*tmp), GFP_ATOMIC);
- if (!tmp) {
- rcu_read_unlock();
- goto cleanup;
- }
- tmp->thread = p;
- list_add(&tmp->list, &thread_list);
- }
- while_each_thread(g,p);
- rcu_read_unlock();
- list_for_each(t, &thread_list) {
- struct elf_thread_status *tmp;
- int sz;
-
- tmp = list_entry(t, struct elf_thread_status, list);
- sz = elf_dump_thread_status(signr, tmp);
- thread_status_size += sz;
- }
- }
- /* now collect the dump for the current */
- memset(prstatus, 0, sizeof(*prstatus));
- fill_prstatus(prstatus, current, signr);
- elf_core_copy_regs(&prstatus->pr_reg, regs);
segs = current->mm->map_count;
#ifdef ELF_CORE_EXTRA_PHDRS
@@ -1630,42 +2034,16 @@ static int elf_core_dump(long signr, struct pt_regs *regs, struct file *file, un
if (gate_vma != NULL)
segs++;
- /* Set up header */
- fill_elf_header(elf, segs + 1); /* including notes section */
-
- has_dumped = 1;
- current->flags |= PF_DUMPCORE;
-
/*
- * Set up the notes in similar form to SVR4 core dumps made
- * with info from their /proc.
+ * Collect all the non-memory information about the process for the
+ * notes. This also sets up the file header.
*/
+ if (!fill_note_info(elf, segs + 1, /* including notes section */
+ &info, signr, regs))
+ goto cleanup;
- fill_note(notes + 0, "CORE", NT_PRSTATUS, sizeof(*prstatus), prstatus);
- fill_psinfo(psinfo, current->group_leader, current->mm);
- fill_note(notes + 1, "CORE", NT_PRPSINFO, sizeof(*psinfo), psinfo);
-
- numnote = 2;
-
- auxv = (elf_addr_t *)current->mm->saved_auxv;
-
- i = 0;
- do
- i += 2;
- while (auxv[i - 2] != AT_NULL);
- fill_note(&notes[numnote++], "CORE", NT_AUXV,
- i * sizeof(elf_addr_t), auxv);
-
- /* Try to dump the FPU. */
- if ((prstatus->pr_fpvalid =
- elf_core_copy_task_fpregs(current, regs, fpu)))
- fill_note(notes + numnote++,
- "CORE", NT_PRFPREG, sizeof(*fpu), fpu);
-#ifdef ELF_CORE_COPY_XFPREGS
- if (elf_core_copy_task_xfpregs(current, xfpu))
- fill_note(notes + numnote++,
- "LINUX", ELF_CORE_XFPREG_TYPE, sizeof(*xfpu), xfpu);
-#endif
+ has_dumped = 1;
+ current->flags |= PF_DUMPCORE;
fs = get_fs();
set_fs(KERNEL_DS);
@@ -1678,12 +2056,7 @@ static int elf_core_dump(long signr, struct pt_regs *regs, struct file *file, un
/* Write notes phdr entry */
{
struct elf_phdr phdr;
- int sz = 0;
-
- for (i = 0; i < numnote; i++)
- sz += notesize(notes + i);
-
- sz += thread_status_size;
+ size_t sz = get_note_info_size(&info);
sz += elf_coredump_extra_notes_size();
@@ -1728,23 +2101,12 @@ static int elf_core_dump(long signr, struct pt_regs *regs, struct file *file, un
#endif
/* write out the notes section */
- for (i = 0; i < numnote; i++)
- if (!writenote(notes + i, file, &foffset))
- goto end_coredump;
+ if (!write_note_info(&info, file, &foffset))
+ goto end_coredump;
if (elf_coredump_extra_notes_write(file, &foffset))
goto end_coredump;
- /* write out the thread status notes section */
- list_for_each(t, &thread_list) {
- struct elf_thread_status *tmp =
- list_entry(t, struct elf_thread_status, list);
-
- for (i = 0; i < tmp->num_notes; i++)
- if (!writenote(&tmp->notes[i], file, &foffset))
- goto end_coredump;
- }
-
/* Align to page */
DUMP_SEEK(dataoff - foffset);
@@ -1795,22 +2157,9 @@ end_coredump:
set_fs(fs);
cleanup:
- while (!list_empty(&thread_list)) {
- struct list_head *tmp = thread_list.next;
- list_del(tmp);
- kfree(list_entry(tmp, struct elf_thread_status, list));
- }
-
kfree(elf);
- kfree(prstatus);
- kfree(psinfo);
- kfree(notes);
- kfree(fpu);
-#ifdef ELF_CORE_COPY_XFPREGS
- kfree(xfpu);
-#endif
+ free_note_info(&info);
return has_dumped;
-#undef NUM_NOTES
}
#endif /* USE_ELF_CORE_DUMP */
diff --git a/fs/compat_binfmt_elf.c b/fs/compat_binfmt_elf.c
new file mode 100644
index 00000000000..0adced2f296
--- /dev/null
+++ b/fs/compat_binfmt_elf.c
@@ -0,0 +1,131 @@
+/*
+ * 32-bit compatibility support for ELF format executables and core dumps.
+ *
+ * Copyright (C) 2007 Red Hat, Inc. All rights reserved.
+ *
+ * This copyrighted material is made available to anyone wishing to use,
+ * modify, copy, or redistribute it subject to the terms and conditions
+ * of the GNU General Public License v.2.
+ *
+ * Red Hat Author: Roland McGrath.
+ *
+ * This file is used in a 64-bit kernel that wants to support 32-bit ELF.
+ * asm/elf.h is responsible for defining the compat_* and COMPAT_* macros
+ * used below, with definitions appropriate for 32-bit ABI compatibility.
+ *
+ * We use macros to rename the ABI types and machine-dependent
+ * functions used in binfmt_elf.c to compat versions.
+ */
+
+#include <linux/elfcore-compat.h>
+#include <linux/time.h>
+
+/*
+ * Rename the basic ELF layout types to refer to the 32-bit class of files.
+ */
+#undef ELF_CLASS
+#define ELF_CLASS ELFCLASS32
+
+#undef elfhdr
+#undef elf_phdr
+#undef elf_note
+#undef elf_addr_t
+#define elfhdr elf32_hdr
+#define elf_phdr elf32_phdr
+#define elf_note elf32_note
+#define elf_addr_t Elf32_Addr
+
+/*
+ * The machine-dependent core note format types are defined in elfcore-compat.h,
+ * which requires asm/elf.h to define compat_elf_gregset_t et al.
+ */
+#define elf_prstatus compat_elf_prstatus
+#define elf_prpsinfo compat_elf_prpsinfo
+
+/*
+ * Compat version of cputime_to_compat_timeval, perhaps this
+ * should be an inline in <linux/compat.h>.
+ */
+static void cputime_to_compat_timeval(const cputime_t cputime,
+ struct compat_timeval *value)
+{
+ struct timeval tv;
+ cputime_to_timeval(cputime, &tv);
+ value->tv_sec = tv.tv_sec;
+ value->tv_usec = tv.tv_usec;
+}
+
+#undef cputime_to_timeval
+#define cputime_to_timeval cputime_to_compat_timeval
+
+
+/*
+ * To use this file, asm/elf.h must define compat_elf_check_arch.
+ * The other following macros can be defined if the compat versions
+ * differ from the native ones, or omitted when they match.
+ */
+
+#undef ELF_ARCH
+#undef elf_check_arch
+#define elf_check_arch compat_elf_check_arch
+
+#ifdef COMPAT_ELF_PLATFORM
+#undef ELF_PLATFORM
+#define ELF_PLATFORM COMPAT_ELF_PLATFORM
+#endif
+
+#ifdef COMPAT_ELF_HWCAP
+#undef ELF_HWCAP
+#define ELF_HWCAP COMPAT_ELF_HWCAP
+#endif
+
+#ifdef COMPAT_ARCH_DLINFO
+#undef ARCH_DLINFO
+#define ARCH_DLINFO COMPAT_ARCH_DLINFO
+#endif
+
+#ifdef COMPAT_ELF_ET_DYN_BASE
+#undef ELF_ET_DYN_BASE
+#define ELF_ET_DYN_BASE COMPAT_ELF_ET_DYN_BASE
+#endif
+
+#ifdef COMPAT_ELF_EXEC_PAGESIZE
+#undef ELF_EXEC_PAGESIZE
+#define ELF_EXEC_PAGESIZE COMPAT_ELF_EXEC_PAGESIZE
+#endif
+
+#ifdef COMPAT_ELF_PLAT_INIT
+#undef ELF_PLAT_INIT
+#define ELF_PLAT_INIT COMPAT_ELF_PLAT_INIT
+#endif
+
+#ifdef COMPAT_SET_PERSONALITY
+#undef SET_PERSONALITY
+#define SET_PERSONALITY COMPAT_SET_PERSONALITY
+#endif
+
+#ifdef compat_start_thread
+#undef start_thread
+#define start_thread compat_start_thread
+#endif
+
+#ifdef compat_arch_setup_additional_pages
+#undef ARCH_HAS_SETUP_ADDITIONAL_PAGES
+#define ARCH_HAS_SETUP_ADDITIONAL_PAGES 1
+#undef arch_setup_additional_pages
+#define arch_setup_additional_pages compat_arch_setup_additional_pages
+#endif
+
+/*
+ * Rename a few of the symbols that binfmt_elf.c will define.
+ * These are all local so the names don't really matter, but it
+ * might make some debugging less confusing not to duplicate them.
+ */
+#define elf_format compat_elf_format
+#define init_elf_binfmt init_compat_elf_binfmt
+#define exit_elf_binfmt exit_compat_elf_binfmt
+
+/*
+ * We share all the actual code with the native (64-bit) version.
+ */
+#include "binfmt_elf.c"
diff --git a/fs/dlm/dir.c b/fs/dlm/dir.c
index 46754553fdc..ff97ba92433 100644
--- a/fs/dlm/dir.c
+++ b/fs/dlm/dir.c
@@ -49,7 +49,7 @@ static struct dlm_direntry *get_free_de(struct dlm_ls *ls, int len)
spin_unlock(&ls->ls_recover_list_lock);
if (!found)
- de = allocate_direntry(ls, len);
+ de = kzalloc(sizeof(struct dlm_direntry) + len, GFP_KERNEL);
return de;
}
@@ -62,7 +62,7 @@ void dlm_clear_free_entries(struct dlm_ls *ls)
de = list_entry(ls->ls_recover_list.next, struct dlm_direntry,
list);
list_del(&de->list);
- free_direntry(de);
+ kfree(de);
}
spin_unlock(&ls->ls_recover_list_lock);
}
@@ -171,7 +171,7 @@ void dlm_dir_remove_entry(struct dlm_ls *ls, int nodeid, char *name, int namelen
}
list_del(&de->list);
- free_direntry(de);
+ kfree(de);
out:
write_unlock(&ls->ls_dirtbl[bucket].lock);
}
@@ -302,7 +302,7 @@ static int get_entry(struct dlm_ls *ls, int nodeid, char *name,
write_unlock(&ls->ls_dirtbl[bucket].lock);
- de = allocate_direntry(ls, namelen);
+ de = kzalloc(sizeof(struct dlm_direntry) + namelen, GFP_KERNEL);
if (!de)
return -ENOMEM;
@@ -313,7 +313,7 @@ static int get_entry(struct dlm_ls *ls, int nodeid, char *name,
write_lock(&ls->ls_dirtbl[bucket].lock);
tmp = search_bucket(ls, name, namelen, bucket);
if (tmp) {
- free_direntry(de);
+ kfree(de);
de = tmp;
} else {
list_add_tail(&de->list, &ls->ls_dirtbl[bucket].list);
@@ -329,49 +329,47 @@ int dlm_dir_lookup(struct dlm_ls *ls, int nodeid, char *name, int namelen,
return get_entry(ls, nodeid, name, namelen, r_nodeid);
}
-/* Copy the names of master rsb's into the buffer provided.
- Only select names whose dir node is the given nodeid. */
+static struct dlm_rsb *find_rsb_root(struct dlm_ls *ls, char *name, int len)
+{
+ struct dlm_rsb *r;
+
+ down_read(&ls->ls_root_sem);
+ list_for_each_entry(r, &ls->ls_root_list, res_root_list) {
+ if (len == r->res_length && !memcmp(name, r->res_name, len)) {
+ up_read(&ls->ls_root_sem);
+ return r;
+ }
+ }
+ up_read(&ls->ls_root_sem);
+ return NULL;
+}
+
+/* Find the rsb where we left off (or start again), then send rsb names
+ for rsb's we're master of and whose directory node matches the requesting
+ node. inbuf is the rsb name last sent, inlen is the name's length */
void dlm_copy_master_names(struct dlm_ls *ls, char *inbuf, int inlen,
char *outbuf, int outlen, int nodeid)
{
struct list_head *list;
- struct dlm_rsb *start_r = NULL, *r = NULL;
- int offset = 0, start_namelen, error, dir_nodeid;
- char *start_name;
+ struct dlm_rsb *r;
+ int offset = 0, dir_nodeid;
uint16_t be_namelen;
- /*
- * Find the rsb where we left off (or start again)
- */
-
- start_namelen = inlen;
- start_name = inbuf;
-
- if (start_namelen > 1) {
- /*
- * We could also use a find_rsb_root() function here that
- * searched the ls_root_list.
- */
- error = dlm_find_rsb(ls, start_name, start_namelen, R_MASTER,
- &start_r);
- DLM_ASSERT(!error && start_r,
- printk("error %d\n", error););
- DLM_ASSERT(!list_empty(&start_r->res_root_list),
- dlm_print_rsb(start_r););
- dlm_put_rsb(start_r);
- }
-
- /*
- * Send rsb names for rsb's we're master of and whose directory node
- * matches the requesting node.
- */
-
down_read(&ls->ls_root_sem);
- if (start_r)
- list = start_r->res_root_list.next;
- else
+
+ if (inlen > 1) {
+ r = find_rsb_root(ls, inbuf, inlen);
+ if (!r) {
+ inbuf[inlen - 1] = '\0';
+ log_error(ls, "copy_master_names from %d start %d %s",
+ nodeid, inlen, inbuf);
+ goto out;
+ }
+ list = r->res_root_list.next;
+ } else {
list = ls->ls_root_list.next;
+ }
for (offset = 0; list != &ls->ls_root_list; list = list->next) {
r = list_entry(list, struct dlm_rsb, res_root_list);
diff --git a/fs/dlm/dlm_internal.h b/fs/dlm/dlm_internal.h
index d2fc2384c3b..ec61bbaf25d 100644
--- a/fs/dlm/dlm_internal.h
+++ b/fs/dlm/dlm_internal.h
@@ -570,5 +570,21 @@ static inline int dlm_no_directory(struct dlm_ls *ls)
return (ls->ls_exflags & DLM_LSFL_NODIR) ? 1 : 0;
}
+int dlm_netlink_init(void);
+void dlm_netlink_exit(void);
+void dlm_timeout_warn(struct dlm_lkb *lkb);
+
+#ifdef CONFIG_DLM_DEBUG
+int dlm_register_debugfs(void);
+void dlm_unregister_debugfs(void);
+int dlm_create_debug_file(struct dlm_ls *ls);
+void dlm_delete_debug_file(struct dlm_ls *ls);
+#else
+static inline int dlm_register_debugfs(void) { return 0; }
+static inline void dlm_unregister_debugfs(void) { }
+static inline int dlm_create_debug_file(struct dlm_ls *ls) { return 0; }
+static inline void dlm_delete_debug_file(struct dlm_ls *ls) { }
+#endif
+
#endif /* __DLM_INTERNAL_DOT_H__ */
diff --git a/fs/dlm/lock.c b/fs/dlm/lock.c
index 3915b8e1414..ff4a198fa67 100644
--- a/fs/dlm/lock.c
+++ b/fs/dlm/lock.c
@@ -1,7 +1,7 @@
/******************************************************************************
*******************************************************************************
**
-** Copyright (C) 2005-2007 Red Hat, Inc. All rights reserved.
+** Copyright (C) 2005-2008 Red Hat, Inc. All rights reserved.
**
** This copyrighted material is made available to anyone wishing to use,
** modify, copy, or redistribute it subject to the terms and conditions
@@ -88,7 +88,6 @@ static void __receive_convert_reply(struct dlm_rsb *r, struct dlm_lkb *lkb,
static int receive_extralen(struct dlm_message *ms);
static void do_purge(struct dlm_ls *ls, int nodeid, int pid);
static void del_timeout(struct dlm_lkb *lkb);
-void dlm_timeout_warn(struct dlm_lkb *lkb);
/*
* Lock compatibilty matrix - thanks Steve
@@ -335,7 +334,7 @@ static struct dlm_rsb *create_rsb(struct dlm_ls *ls, char *name, int len)
{
struct dlm_rsb *r;
- r = allocate_rsb(ls, len);
+ r = dlm_allocate_rsb(ls, len);
if (!r)
return NULL;
@@ -478,7 +477,7 @@ static int find_rsb(struct dlm_ls *ls, char *name, int namelen,
error = _search_rsb(ls, name, namelen, bucket, 0, &tmp);
if (!error) {
write_unlock(&ls->ls_rsbtbl[bucket].lock);
- free_rsb(r);
+ dlm_free_rsb(r);
r = tmp;
goto out;
}
@@ -490,12 +489,6 @@ static int find_rsb(struct dlm_ls *ls, char *name, int namelen,
return error;
}
-int dlm_find_rsb(struct dlm_ls *ls, char *name, int namelen,
- unsigned int flags, struct dlm_rsb **r_ret)
-{
- return find_rsb(ls, name, namelen, flags, r_ret);
-}
-
/* This is only called to add a reference when the code already holds
a valid reference to the rsb, so there's no need for locking. */
@@ -519,7 +512,7 @@ static void toss_rsb(struct kref *kref)
list_move(&r->res_hashchain, &ls->ls_rsbtbl[r->res_bucket].toss);
r->res_toss_time = jiffies;
if (r->res_lvbptr) {
- free_lvb(r->res_lvbptr);
+ dlm_free_lvb(r->res_lvbptr);
r->res_lvbptr = NULL;
}
}
@@ -589,7 +582,7 @@ static int create_lkb(struct dlm_ls *ls, struct dlm_lkb **lkb_ret)
uint32_t lkid = 0;
uint16_t bucket;
- lkb = allocate_lkb(ls);
+ lkb = dlm_allocate_lkb(ls);
if (!lkb)
return -ENOMEM;
@@ -683,8 +676,8 @@ static int __put_lkb(struct dlm_ls *ls, struct dlm_lkb *lkb)
/* for local/process lkbs, lvbptr points to caller's lksb */
if (lkb->lkb_lvbptr && is_master_copy(lkb))
- free_lvb(lkb->lkb_lvbptr);
- free_lkb(lkb);
+ dlm_free_lvb(lkb->lkb_lvbptr);
+ dlm_free_lkb(lkb);
return 1;
} else {
write_unlock(&ls->ls_lkbtbl[bucket].lock);
@@ -988,7 +981,7 @@ static int shrink_bucket(struct dlm_ls *ls, int b)
if (is_master(r))
dir_remove(r);
- free_rsb(r);
+ dlm_free_rsb(r);
count++;
} else {
write_unlock(&ls->ls_rsbtbl[b].lock);
@@ -1171,7 +1164,7 @@ static void set_lvb_lock(struct dlm_rsb *r, struct dlm_lkb *lkb)
return;
if (!r->res_lvbptr)
- r->res_lvbptr = allocate_lvb(r->res_ls);
+ r->res_lvbptr = dlm_allocate_lvb(r->res_ls);
if (!r->res_lvbptr)
return;
@@ -1203,7 +1196,7 @@ static void set_lvb_unlock(struct dlm_rsb *r, struct dlm_lkb *lkb)
return;
if (!r->res_lvbptr)
- r->res_lvbptr = allocate_lvb(r->res_ls);
+ r->res_lvbptr = dlm_allocate_lvb(r->res_ls);
if (!r->res_lvbptr)
return;
@@ -1852,7 +1845,7 @@ static void send_blocking_asts_all(struct dlm_rsb *r, struct dlm_lkb *lkb)
static int set_master(struct dlm_rsb *r, struct dlm_lkb *lkb)
{
struct dlm_ls *ls = r->res_ls;
- int error, dir_nodeid, ret_nodeid, our_nodeid = dlm_our_nodeid();
+ int i, error, dir_nodeid, ret_nodeid, our_nodeid = dlm_our_nodeid();
if (rsb_flag(r, RSB_MASTER_UNCERTAIN)) {
rsb_clear_flag(r, RSB_MASTER_UNCERTAIN);
@@ -1886,7 +1879,7 @@ static int set_master(struct dlm_rsb *r, struct dlm_lkb *lkb)
return 1;
}
- for (;;) {
+ for (i = 0; i < 2; i++) {
/* It's possible for dlm_scand to remove an old rsb for
this same resource from the toss list, us to create
a new one, look up the master locally, and find it
@@ -1900,6 +1893,8 @@ static int set_master(struct dlm_rsb *r, struct dlm_lkb *lkb)
log_debug(ls, "dir_lookup error %d %s", error, r->res_name);
schedule();
}
+ if (error && error != -EEXIST)
+ return error;
if (ret_nodeid == our_nodeid) {
r->res_first_lkid = 0;
@@ -1941,8 +1936,11 @@ static void confirm_master(struct dlm_rsb *r, int error)
break;
case -EAGAIN:
- /* the remote master didn't queue our NOQUEUE request;
- make a waiting lkb the first_lkid */
+ case -EBADR:
+ case -ENOTBLK:
+ /* the remote request failed and won't be retried (it was
+ a NOQUEUE, or has been canceled/unlocked); make a waiting
+ lkb the first_lkid */
r->res_first_lkid = 0;
@@ -2108,17 +2106,18 @@ static int validate_unlock_args(struct dlm_lkb *lkb, struct dlm_args *args)
/* an lkb may be waiting for an rsb lookup to complete where the
lookup was initiated by another lock */
- if (args->flags & (DLM_LKF_CANCEL | DLM_LKF_FORCEUNLOCK)) {
- if (!list_empty(&lkb->lkb_rsb_lookup)) {
+ if (!list_empty(&lkb->lkb_rsb_lookup)) {
+ if (args->flags & (DLM_LKF_CANCEL | DLM_LKF_FORCEUNLOCK)) {
log_debug(ls, "unlock on rsb_lookup %x", lkb->lkb_id);
list_del_init(&lkb->lkb_rsb_lookup);
queue_cast(lkb->lkb_resource, lkb,
args->flags & DLM_LKF_CANCEL ?
-DLM_ECANCEL : -DLM_EUNLOCK);
unhold_lkb(lkb); /* undoes create_lkb() */
- rv = -EBUSY;
- goto out;
}
+ /* caller changes -EBUSY to 0 for CANCEL and FORCEUNLOCK */
+ rv = -EBUSY;
+ goto out;
}
/* cancel not allowed with another cancel/unlock in progress */
@@ -2986,7 +2985,7 @@ static int receive_lvb(struct dlm_ls *ls, struct dlm_lkb *lkb,
if (lkb->lkb_exflags & DLM_LKF_VALBLK) {
if (!lkb->lkb_lvbptr)
- lkb->lkb_lvbptr = allocate_lvb(ls);
+ lkb->lkb_lvbptr = dlm_allocate_lvb(ls);
if (!lkb->lkb_lvbptr)
return -ENOMEM;
len = receive_extralen(ms);
@@ -3006,11 +3005,9 @@ static int receive_request_args(struct dlm_ls *ls, struct dlm_lkb *lkb,
lkb->lkb_bastaddr = (void *) (long) (ms->m_asts & AST_BAST);
lkb->lkb_astaddr = (void *) (long) (ms->m_asts & AST_COMP);
- DLM_ASSERT(is_master_copy(lkb), dlm_print_lkb(lkb););
-
if (lkb->lkb_exflags & DLM_LKF_VALBLK) {
/* lkb was just created so there won't be an lvb yet */
- lkb->lkb_lvbptr = allocate_lvb(ls);
+ lkb->lkb_lvbptr = dlm_allocate_lvb(ls);
if (!lkb->lkb_lvbptr)
return -ENOMEM;
}
@@ -3021,16 +3018,6 @@ static int receive_request_args(struct dlm_ls *ls, struct dlm_lkb *lkb,
static int receive_convert_args(struct dlm_ls *ls, struct dlm_lkb *lkb,
struct dlm_message *ms)
{
- if (lkb->lkb_nodeid != ms->m_header.h_nodeid) {
- log_error(ls, "convert_args nodeid %d %d lkid %x %x",
- lkb->lkb_nodeid, ms->m_header.h_nodeid,
- lkb->lkb_id, lkb->lkb_remid);
- return -EINVAL;
- }
-
- if (!is_master_copy(lkb))
- return -EINVAL;
-
if (lkb->lkb_status != DLM_LKSTS_GRANTED)
return -EBUSY;
@@ -3046,8 +3033,6 @@ static int receive_convert_args(struct dlm_ls *ls, struct dlm_lkb *lkb,
static int receive_unlock_args(struct dlm_ls *ls, struct dlm_lkb *lkb,
struct dlm_message *ms)
{
- if (!is_master_copy(lkb))
- return -EINVAL;
if (receive_lvb(ls, lkb, ms))
return -ENOMEM;
return 0;
@@ -3063,6 +3048,50 @@ static void setup_stub_lkb(struct dlm_ls *ls, struct dlm_message *ms)
lkb->lkb_remid = ms->m_lkid;
}
+/* This is called after the rsb is locked so that we can safely inspect
+ fields in the lkb. */
+
+static int validate_message(struct dlm_lkb *lkb, struct dlm_message *ms)
+{
+ int from = ms->m_header.h_nodeid;
+ int error = 0;
+
+ switch (ms->m_type) {
+ case DLM_MSG_CONVERT:
+ case DLM_MSG_UNLOCK:
+ case DLM_MSG_CANCEL:
+ if (!is_master_copy(lkb) || lkb->lkb_nodeid != from)
+ error = -EINVAL;
+ break;
+
+ case DLM_MSG_CONVERT_REPLY:
+ case DLM_MSG_UNLOCK_REPLY:
+ case DLM_MSG_CANCEL_REPLY:
+ case DLM_MSG_GRANT:
+ case DLM_MSG_BAST:
+ if (!is_process_copy(lkb) || lkb->lkb_nodeid != from)
+ error = -EINVAL;
+ break;
+
+ case DLM_MSG_REQUEST_REPLY:
+ if (!is_process_copy(lkb))
+ error = -EINVAL;
+ else if (lkb->lkb_nodeid != -1 && lkb->lkb_nodeid != from)
+ error = -EINVAL;
+ break;
+
+ default:
+ error = -EINVAL;
+ }
+
+ if (error)
+ log_error(lkb->lkb_resource->res_ls,
+ "ignore invalid message %d from %d %x %x %x %d",
+ ms->m_type, from, lkb->lkb_id, lkb->lkb_remid,
+ lkb->lkb_flags, lkb->lkb_nodeid);
+ return error;
+}
+
static void receive_request(struct dlm_ls *ls, struct dlm_message *ms)
{
struct dlm_lkb *lkb;
@@ -3124,17 +3153,21 @@ static void receive_convert(struct dlm_ls *ls, struct dlm_message *ms)
hold_rsb(r);
lock_rsb(r);
+ error = validate_message(lkb, ms);
+ if (error)
+ goto out;
+
receive_flags(lkb, ms);
error = receive_convert_args(ls, lkb, ms);
if (error)
- goto out;
+ goto out_reply;
reply = !down_conversion(lkb);
error = do_convert(r, lkb);
- out:
+ out_reply:
if (reply)
send_convert_reply(r, lkb, error);
-
+ out:
unlock_rsb(r);
put_rsb(r);
dlm_put_lkb(lkb);
@@ -3160,15 +3193,19 @@ static void receive_unlock(struct dlm_ls *ls, struct dlm_message *ms)
hold_rsb(r);
lock_rsb(r);
+ error = validate_message(lkb, ms);
+ if (error)
+ goto out;
+
receive_flags(lkb, ms);
error = receive_unlock_args(ls, lkb, ms);
if (error)
- goto out;
+ goto out_reply;
error = do_unlock(r, lkb);
- out:
+ out_reply:
send_unlock_reply(r, lkb, error);
-
+ out:
unlock_rsb(r);
put_rsb(r);
dlm_put_lkb(lkb);
@@ -3196,9 +3233,13 @@ static void receive_cancel(struct dlm_ls *ls, struct dlm_message *ms)
hold_rsb(r);
lock_rsb(r);
+ error = validate_message(lkb, ms);
+ if (error)
+ goto out;
+
error = do_cancel(r, lkb);
send_cancel_reply(r, lkb, error);
-
+ out:
unlock_rsb(r);
put_rsb(r);
dlm_put_lkb(lkb);
@@ -3217,22 +3258,26 @@ static void receive_grant(struct dlm_ls *ls, struct dlm_message *ms)
error = find_lkb(ls, ms->m_remid, &lkb);
if (error) {
- log_error(ls, "receive_grant no lkb");
+ log_debug(ls, "receive_grant from %d no lkb %x",
+ ms->m_header.h_nodeid, ms->m_remid);
return;
}
- DLM_ASSERT(is_process_copy(lkb), dlm_print_lkb(lkb););
r = lkb->lkb_resource;
hold_rsb(r);
lock_rsb(r);
+ error = validate_message(lkb, ms);
+ if (error)
+ goto out;
+
receive_flags_reply(lkb, ms);
if (is_altmode(lkb))
munge_altmode(lkb, ms);
grant_lock_pc(r, lkb, ms);
queue_cast(r, lkb, 0);
-
+ out:
unlock_rsb(r);
put_rsb(r);
dlm_put_lkb(lkb);
@@ -3246,18 +3291,22 @@ static void receive_bast(struct dlm_ls *ls, struct dlm_message *ms)
error = find_lkb(ls, ms->m_remid, &lkb);
if (error) {
- log_error(ls, "receive_bast no lkb");
+ log_debug(ls, "receive_bast from %d no lkb %x",
+ ms->m_header.h_nodeid, ms->m_remid);
return;
}
- DLM_ASSERT(is_process_copy(lkb), dlm_print_lkb(lkb););
r = lkb->lkb_resource;
hold_rsb(r);
lock_rsb(r);
- queue_bast(r, lkb, ms->m_bastmode);
+ error = validate_message(lkb, ms);
+ if (error)
+ goto out;
+ queue_bast(r, lkb, ms->m_bastmode);
+ out:
unlock_rsb(r);
put_rsb(r);
dlm_put_lkb(lkb);
@@ -3323,15 +3372,19 @@ static void receive_request_reply(struct dlm_ls *ls, struct dlm_message *ms)
error = find_lkb(ls, ms->m_remid, &lkb);
if (error) {
- log_error(ls, "receive_request_reply no lkb");
+ log_debug(ls, "receive_request_reply from %d no lkb %x",
+ ms->m_header.h_nodeid, ms->m_remid);
return;
}
- DLM_ASSERT(is_process_copy(lkb), dlm_print_lkb(lkb););
r = lkb->lkb_resource;
hold_rsb(r);
lock_rsb(r);
+ error = validate_message(lkb, ms);
+ if (error)
+ goto out;
+
mstype = lkb->lkb_wait_type;
error = remove_from_waiters(lkb, DLM_MSG_REQUEST_REPLY);
if (error)
@@ -3383,6 +3436,7 @@ static void receive_request_reply(struct dlm_ls *ls, struct dlm_message *ms)
if (is_overlap(lkb)) {
/* we'll ignore error in cancel/unlock reply */
queue_cast_overlap(r, lkb);
+ confirm_master(r, result);
unhold_lkb(lkb); /* undoes create_lkb() */
} else
_request_lock(r, lkb);
@@ -3463,6 +3517,10 @@ static void _receive_convert_reply(struct dlm_lkb *lkb, struct dlm_message *ms)
hold_rsb(r);
lock_rsb(r);
+ error = validate_message(lkb, ms);
+ if (error)
+ goto out;
+
/* stub reply can happen with waiters_mutex held */
error = remove_from_waiters_ms(lkb, ms);
if (error)
@@ -3481,10 +3539,10 @@ static void receive_convert_reply(struct dlm_ls *ls, struct dlm_message *ms)
error = find_lkb(ls, ms->m_remid, &lkb);
if (error) {
- log_error(ls, "receive_convert_reply no lkb");
+ log_debug(ls, "receive_convert_reply from %d no lkb %x",
+ ms->m_header.h_nodeid, ms->m_remid);
return;
}
- DLM_ASSERT(is_process_copy(lkb), dlm_print_lkb(lkb););
_receive_convert_reply(lkb, ms);
dlm_put_lkb(lkb);
@@ -3498,6 +3556,10 @@ static void _receive_unlock_reply(struct dlm_lkb *lkb, struct dlm_message *ms)
hold_rsb(r);
lock_rsb(r);
+ error = validate_message(lkb, ms);
+ if (error)
+ goto out;
+
/* stub reply can happen with waiters_mutex held */
error = remove_from_waiters_ms(lkb, ms);
if (error)
@@ -3529,10 +3591,10 @@ static void receive_unlock_reply(struct dlm_ls *ls, struct dlm_message *ms)
error = find_lkb(ls, ms->m_remid, &lkb);
if (error) {
- log_error(ls, "receive_unlock_reply no lkb");
+ log_debug(ls, "receive_unlock_reply from %d no lkb %x",
+ ms->m_header.h_nodeid, ms->m_remid);
return;
}
- DLM_ASSERT(is_process_copy(lkb), dlm_print_lkb(lkb););
_receive_unlock_reply(lkb, ms);
dlm_put_lkb(lkb);
@@ -3546,6 +3608,10 @@ static void _receive_cancel_reply(struct dlm_lkb *lkb, struct dlm_message *ms)
hold_rsb(r);
lock_rsb(r);
+ error = validate_message(lkb, ms);
+ if (error)
+ goto out;
+
/* stub reply can happen with waiters_mutex held */
error = remove_from_waiters_ms(lkb, ms);
if (error)
@@ -3577,10 +3643,10 @@ static void receive_cancel_reply(struct dlm_ls *ls, struct dlm_message *ms)
error = find_lkb(ls, ms->m_remid, &lkb);
if (error) {
- log_error(ls, "receive_cancel_reply no lkb");
+ log_debug(ls, "receive_cancel_reply from %d no lkb %x",
+ ms->m_header.h_nodeid, ms->m_remid);
return;
}
- DLM_ASSERT(is_process_copy(lkb), dlm_print_lkb(lkb););
_receive_cancel_reply(lkb, ms);
dlm_put_lkb(lkb);
@@ -3640,6 +3706,13 @@ static void receive_lookup_reply(struct dlm_ls *ls, struct dlm_message *ms)
static void _receive_message(struct dlm_ls *ls, struct dlm_message *ms)
{
+ if (!dlm_is_member(ls, ms->m_header.h_nodeid)) {
+ log_debug(ls, "ignore non-member message %d from %d %x %x %d",
+ ms->m_type, ms->m_header.h_nodeid, ms->m_lkid,
+ ms->m_remid, ms->m_result);
+ return;
+ }
+
switch (ms->m_type) {
/* messages sent to a master node */
@@ -3778,8 +3851,9 @@ void dlm_receive_buffer(struct dlm_header *hd, int nodeid)
ls = dlm_find_lockspace_global(hd->h_lockspace);
if (!ls) {
- log_print("invalid h_lockspace %x from %d cmd %d type %d",
- hd->h_lockspace, nodeid, hd->h_cmd, type);
+ if (dlm_config.ci_log_debug)
+ log_print("invalid lockspace %x from %d cmd %d type %d",
+ hd->h_lockspace, nodeid, hd->h_cmd, type);
if (hd->h_cmd == DLM_RCOM && type == DLM_RCOM_STATUS)
dlm_send_ls_not_ready(nodeid, rc);
@@ -3806,6 +3880,7 @@ static void recover_convert_waiter(struct dlm_ls *ls, struct dlm_lkb *lkb)
ls->ls_stub_ms.m_type = DLM_MSG_CONVERT_REPLY;
ls->ls_stub_ms.m_result = -EINPROGRESS;
ls->ls_stub_ms.m_flags = lkb->lkb_flags;
+ ls->ls_stub_ms.m_header.h_nodeid = lkb->lkb_nodeid;
_receive_convert_reply(lkb, &ls->ls_stub_ms);
/* Same special case as in receive_rcom_lock_args() */
@@ -3847,6 +3922,7 @@ static int waiter_needs_recovery(struct dlm_ls *ls, struct dlm_lkb *lkb)
void dlm_recover_waiters_pre(struct dlm_ls *ls)
{
struct dlm_lkb *lkb, *safe;
+ int wait_type, stub_unlock_result, stub_cancel_result;
mutex_lock(&ls->ls_waiters_mutex);
@@ -3865,7 +3941,33 @@ void dlm_recover_waiters_pre(struct dlm_ls *ls)
if (!waiter_needs_recovery(ls, lkb))
continue;
- switch (lkb->lkb_wait_type) {
+ wait_type = lkb->lkb_wait_type;
+ stub_unlock_result = -DLM_EUNLOCK;
+ stub_cancel_result = -DLM_ECANCEL;
+
+ /* Main reply may have been received leaving a zero wait_type,
+ but a reply for the overlapping op may not have been
+ received. In that case we need to fake the appropriate
+ reply for the overlap op. */
+
+ if (!wait_type) {
+ if (is_overlap_cancel(lkb)) {
+ wait_type = DLM_MSG_CANCEL;
+ if (lkb->lkb_grmode == DLM_LOCK_IV)
+ stub_cancel_result = 0;
+ }
+ if (is_overlap_unlock(lkb)) {
+ wait_type = DLM_MSG_UNLOCK;
+ if (lkb->lkb_grmode == DLM_LOCK_IV)
+ stub_unlock_result = -ENOENT;
+ }
+
+ log_debug(ls, "rwpre overlap %x %x %d %d %d",
+ lkb->lkb_id, lkb->lkb_flags, wait_type,
+ stub_cancel_result, stub_unlock_result);
+ }
+
+ switch (wait_type) {
case DLM_MSG_REQUEST:
lkb->lkb_flags |= DLM_IFL_RESEND;
@@ -3878,8 +3980,9 @@ void dlm_recover_waiters_pre(struct dlm_ls *ls)
case DLM_MSG_UNLOCK:
hold_lkb(lkb);
ls->ls_stub_ms.m_type = DLM_MSG_UNLOCK_REPLY;
- ls->ls_stub_ms.m_result = -DLM_EUNLOCK;
+ ls->ls_stub_ms.m_result = stub_unlock_result;
ls->ls_stub_ms.m_flags = lkb->lkb_flags;
+ ls->ls_stub_ms.m_header.h_nodeid = lkb->lkb_nodeid;
_receive_unlock_reply(lkb, &ls->ls_stub_ms);
dlm_put_lkb(lkb);
break;
@@ -3887,15 +3990,16 @@ void dlm_recover_waiters_pre(struct dlm_ls *ls)
case DLM_MSG_CANCEL:
hold_lkb(lkb);
ls->ls_stub_ms.m_type = DLM_MSG_CANCEL_REPLY;
- ls->ls_stub_ms.m_result = -DLM_ECANCEL;
+ ls->ls_stub_ms.m_result = stub_cancel_result;
ls->ls_stub_ms.m_flags = lkb->lkb_flags;
+ ls->ls_stub_ms.m_header.h_nodeid = lkb->lkb_nodeid;
_receive_cancel_reply(lkb, &ls->ls_stub_ms);
dlm_put_lkb(lkb);
break;
default:
- log_error(ls, "invalid lkb wait_type %d",
- lkb->lkb_wait_type);
+ log_error(ls, "invalid lkb wait_type %d %d",
+ lkb->lkb_wait_type, wait_type);
}
schedule();
}
@@ -4184,7 +4288,7 @@ static int receive_rcom_lock_args(struct dlm_ls *ls, struct dlm_lkb *lkb,
lkb->lkb_astaddr = (void *) (long) (rl->rl_asts & AST_COMP);
if (lkb->lkb_exflags & DLM_LKF_VALBLK) {
- lkb->lkb_lvbptr = allocate_lvb(ls);
+ lkb->lkb_lvbptr = dlm_allocate_lvb(ls);
if (!lkb->lkb_lvbptr)
return -ENOMEM;
lvblen = rc->rc_header.h_length - sizeof(struct dlm_rcom) -
@@ -4259,7 +4363,7 @@ int dlm_recover_master_copy(struct dlm_ls *ls, struct dlm_rcom *rc)
put_rsb(r);
out:
if (error)
- log_print("recover_master_copy %d %x", error, rl->rl_lkid);
+ log_debug(ls, "recover_master_copy %d %x", error, rl->rl_lkid);
rl->rl_result = error;
return error;
}
@@ -4342,7 +4446,7 @@ int dlm_user_request(struct dlm_ls *ls, struct dlm_user_args *ua,
}
}
- /* After ua is attached to lkb it will be freed by free_lkb().
+ /* After ua is attached to lkb it will be freed by dlm_free_lkb().
When DLM_IFL_USER is set, the dlm knows that this is a userspace
lock and that lkb_astparam is the dlm_user_args structure. */
@@ -4679,6 +4783,7 @@ void dlm_clear_proc_locks(struct dlm_ls *ls, struct dlm_user_proc *proc)
}
list_for_each_entry_safe(lkb, safe, &proc->asts, lkb_astqueue) {
+ lkb->lkb_ast_type = 0;
list_del(&lkb->lkb_astqueue);
dlm_put_lkb(lkb);
}
diff --git a/fs/dlm/lock.h b/fs/dlm/lock.h
index ada04680a1e..27b6ed30291 100644
--- a/fs/dlm/lock.h
+++ b/fs/dlm/lock.h
@@ -19,8 +19,6 @@ void dlm_print_lkb(struct dlm_lkb *lkb);
void dlm_receive_message_saved(struct dlm_ls *ls, struct dlm_message *ms);
void dlm_receive_buffer(struct dlm_header *hd, int nodeid);
int dlm_modes_compat(int mode1, int mode2);
-int dlm_find_rsb(struct dlm_ls *ls, char *name, int namelen,
- unsigned int flags, struct dlm_rsb **r_ret);
void dlm_put_rsb(struct dlm_rsb *r);
void dlm_hold_rsb(struct dlm_rsb *r);
int dlm_put_lkb(struct dlm_lkb *lkb);
diff --git a/fs/dlm/lockspace.c b/fs/dlm/lockspace.c
index 5c108c49cb8..b180fdc5108 100644
--- a/fs/dlm/lockspace.c
+++ b/fs/dlm/lockspace.c
@@ -24,14 +24,6 @@
#include "recover.h"
#include "requestqueue.h"
-#ifdef CONFIG_DLM_DEBUG
-int dlm_create_debug_file(struct dlm_ls *ls);
-void dlm_delete_debug_file(struct dlm_ls *ls);
-#else
-static inline int dlm_create_debug_file(struct dlm_ls *ls) { return 0; }
-static inline void dlm_delete_debug_file(struct dlm_ls *ls) { }
-#endif
-
static int ls_count;
static struct mutex ls_lock;
static struct list_head lslist;
@@ -684,9 +676,9 @@ static int release_lockspace(struct dlm_ls *ls, int force)
dlm_del_ast(lkb);
if (lkb->lkb_lvbptr && lkb->lkb_flags & DLM_IFL_MSTCPY)
- free_lvb(lkb->lkb_lvbptr);
+ dlm_free_lvb(lkb->lkb_lvbptr);
- free_lkb(lkb);
+ dlm_free_lkb(lkb);
}
}
dlm_astd_resume();
@@ -704,7 +696,7 @@ static int release_lockspace(struct dlm_ls *ls, int force)
res_hashchain);
list_del(&rsb->res_hashchain);
- free_rsb(rsb);
+ dlm_free_rsb(rsb);
}
head = &ls->ls_rsbtbl[i].toss;
@@ -712,7 +704,7 @@ static int release_lockspace(struct dlm_ls *ls, int force)
rsb = list_entry(head->next, struct dlm_rsb,
res_hashchain);
list_del(&rsb->res_hashchain);
- free_rsb(rsb);
+ dlm_free_rsb(rsb);
}
}
diff --git a/fs/dlm/lowcomms.c b/fs/dlm/lowcomms.c
index e9923ca9c2d..7c1e5e5cccd 100644
--- a/fs/dlm/lowcomms.c
+++ b/fs/dlm/lowcomms.c
@@ -864,7 +864,7 @@ static void sctp_init_assoc(struct connection *con)
static void tcp_connect_to_sock(struct connection *con)
{
int result = -EHOSTUNREACH;
- struct sockaddr_storage saddr;
+ struct sockaddr_storage saddr, src_addr;
int addr_len;
struct socket *sock;
@@ -898,6 +898,17 @@ static void tcp_connect_to_sock(struct connection *con)
con->connect_action = tcp_connect_to_sock;
add_sock(sock, con);
+ /* Bind to our cluster-known address connecting to avoid
+ routing problems */
+ memcpy(&src_addr, dlm_local_addr[0], sizeof(src_addr));
+ make_sockaddr(&src_addr, 0, &addr_len);
+ result = sock->ops->bind(sock, (struct sockaddr *) &src_addr,
+ addr_len);
+ if (result < 0) {
+ log_print("could not bind for connect: %d", result);
+ /* This *may* not indicate a critical error */
+ }
+
make_sockaddr(&saddr, dlm_config.ci_tcp_port, &addr_len);
log_print("connecting to %d", con->nodeid);
@@ -1426,6 +1437,8 @@ void dlm_lowcomms_stop(void)
con = __nodeid2con(i, 0);
if (con) {
close_connection(con, true);
+ if (con->othercon)
+ kmem_cache_free(con_cache, con->othercon);
kmem_cache_free(con_cache, con);
}
}
diff --git a/fs/dlm/main.c b/fs/dlm/main.c
index eca2907f238..58487fb95a4 100644
--- a/fs/dlm/main.c
+++ b/fs/dlm/main.c
@@ -18,16 +18,6 @@
#include "memory.h"
#include "config.h"
-#ifdef CONFIG_DLM_DEBUG
-int dlm_register_debugfs(void);
-void dlm_unregister_debugfs(void);
-#else
-static inline int dlm_register_debugfs(void) { return 0; }
-static inline void dlm_unregister_debugfs(void) { }
-#endif
-int dlm_netlink_init(void);
-void dlm_netlink_exit(void);
-
static int __init init_dlm(void)
{
int error;
diff --git a/fs/dlm/member.c b/fs/dlm/member.c
index e9cdcab306e..fa17f5a2788 100644
--- a/fs/dlm/member.c
+++ b/fs/dlm/member.c
@@ -1,7 +1,7 @@
/******************************************************************************
*******************************************************************************
**
-** Copyright (C) 2005-2007 Red Hat, Inc. All rights reserved.
+** Copyright (C) 2005-2008 Red Hat, Inc. All rights reserved.
**
** This copyrighted material is made available to anyone wishing to use,
** modify, copy, or redistribute it subject to the terms and conditions
@@ -70,7 +70,7 @@ static void dlm_remove_member(struct dlm_ls *ls, struct dlm_member *memb)
ls->ls_num_nodes--;
}
-static int dlm_is_member(struct dlm_ls *ls, int nodeid)
+int dlm_is_member(struct dlm_ls *ls, int nodeid)
{
struct dlm_member *memb;
diff --git a/fs/dlm/member.h b/fs/dlm/member.h
index 927c08c1921..7a26fca1e0b 100644
--- a/fs/dlm/member.h
+++ b/fs/dlm/member.h
@@ -1,7 +1,7 @@
/******************************************************************************
*******************************************************************************
**
-** Copyright (C) 2005 Red Hat, Inc. All rights reserved.
+** Copyright (C) 2005-2008 Red Hat, Inc. All rights reserved.
**
** This copyrighted material is made available to anyone wishing to use,
** modify, copy, or redistribute it subject to the terms and conditions
@@ -19,6 +19,7 @@ void dlm_clear_members(struct dlm_ls *ls);
void dlm_clear_members_gone(struct dlm_ls *ls);
int dlm_recover_members(struct dlm_ls *ls, struct dlm_recover *rv,int *neg_out);
int dlm_is_removed(struct dlm_ls *ls, int nodeid);
+int dlm_is_member(struct dlm_ls *ls, int nodeid);
#endif /* __MEMBER_DOT_H__ */
diff --git a/fs/dlm/memory.c b/fs/dlm/memory.c
index ecf0e5cb203..f7783867491 100644
--- a/fs/dlm/memory.c
+++ b/fs/dlm/memory.c
@@ -2,7 +2,7 @@
*******************************************************************************
**
** Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved.
-** Copyright (C) 2004-2005 Red Hat, Inc. All rights reserved.
+** Copyright (C) 2004-2007 Red Hat, Inc. All rights reserved.
**
** This copyrighted material is made available to anyone wishing to use,
** modify, copy, or redistribute it subject to the terms and conditions
@@ -35,7 +35,7 @@ void dlm_memory_exit(void)
kmem_cache_destroy(lkb_cache);
}
-char *allocate_lvb(struct dlm_ls *ls)
+char *dlm_allocate_lvb(struct dlm_ls *ls)
{
char *p;
@@ -43,7 +43,7 @@ char *allocate_lvb(struct dlm_ls *ls)
return p;
}
-void free_lvb(char *p)
+void dlm_free_lvb(char *p)
{
kfree(p);
}
@@ -51,7 +51,7 @@ void free_lvb(char *p)
/* FIXME: have some minimal space built-in to rsb for the name and
kmalloc a separate name if needed, like dentries are done */
-struct dlm_rsb *allocate_rsb(struct dlm_ls *ls, int namelen)
+struct dlm_rsb *dlm_allocate_rsb(struct dlm_ls *ls, int namelen)
{
struct dlm_rsb *r;
@@ -61,14 +61,14 @@ struct dlm_rsb *allocate_rsb(struct dlm_ls *ls, int namelen)
return r;
}
-void free_rsb(struct dlm_rsb *r)
+void dlm_free_rsb(struct dlm_rsb *r)
{
if (r->res_lvbptr)
- free_lvb(r->res_lvbptr);
+ dlm_free_lvb(r->res_lvbptr);
kfree(r);
}
-struct dlm_lkb *allocate_lkb(struct dlm_ls *ls)
+struct dlm_lkb *dlm_allocate_lkb(struct dlm_ls *ls)
{
struct dlm_lkb *lkb;
@@ -76,7 +76,7 @@ struct dlm_lkb *allocate_lkb(struct dlm_ls *ls)
return lkb;
}
-void free_lkb(struct dlm_lkb *lkb)
+void dlm_free_lkb(struct dlm_lkb *lkb)
{
if (lkb->lkb_flags & DLM_IFL_USER) {
struct dlm_user_args *ua;
@@ -90,19 +90,3 @@ void free_lkb(struct dlm_lkb *lkb)
kmem_cache_free(lkb_cache, lkb);
}
-struct dlm_direntry *allocate_direntry(struct dlm_ls *ls, int namelen)
-{
- struct dlm_direntry *de;
-
- DLM_ASSERT(namelen <= DLM_RESNAME_MAXLEN,
- printk("namelen = %d\n", namelen););
-
- de = kzalloc(sizeof(*de) + namelen, GFP_KERNEL);
- return de;
-}
-
-void free_direntry(struct dlm_direntry *de)
-{
- kfree(de);
-}
-
diff --git a/fs/dlm/memory.h b/fs/dlm/memory.h
index 6ead158ccc5..485fb29143b 100644
--- a/fs/dlm/memory.h
+++ b/fs/dlm/memory.h
@@ -2,7 +2,7 @@
*******************************************************************************
**
** Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved.
-** Copyright (C) 2004-2005 Red Hat, Inc. All rights reserved.
+** Copyright (C) 2004-2007 Red Hat, Inc. All rights reserved.
**
** This copyrighted material is made available to anyone wishing to use,
** modify, copy, or redistribute it subject to the terms and conditions
@@ -16,14 +16,12 @@
int dlm_memory_init(void);
void dlm_memory_exit(void);
-struct dlm_rsb *allocate_rsb(struct dlm_ls *ls, int namelen);
-void free_rsb(struct dlm_rsb *r);
-struct dlm_lkb *allocate_lkb(struct dlm_ls *ls);
-void free_lkb(struct dlm_lkb *l);
-struct dlm_direntry *allocate_direntry(struct dlm_ls *ls, int namelen);
-void free_direntry(struct dlm_direntry *de);
-char *allocate_lvb(struct dlm_ls *ls);
-void free_lvb(char *l);
+struct dlm_rsb *dlm_allocate_rsb(struct dlm_ls *ls, int namelen);
+void dlm_free_rsb(struct dlm_rsb *r);
+struct dlm_lkb *dlm_allocate_lkb(struct dlm_ls *ls);
+void dlm_free_lkb(struct dlm_lkb *l);
+char *dlm_allocate_lvb(struct dlm_ls *ls);
+void dlm_free_lvb(char *l);
#endif /* __MEMORY_DOT_H__ */
diff --git a/fs/dlm/midcomms.c b/fs/dlm/midcomms.c
index f8c69dda16a..e69926e984d 100644
--- a/fs/dlm/midcomms.c
+++ b/fs/dlm/midcomms.c
@@ -2,7 +2,7 @@
*******************************************************************************
**
** Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved.
-** Copyright (C) 2004-2007 Red Hat, Inc. All rights reserved.
+** Copyright (C) 2004-2008 Red Hat, Inc. All rights reserved.
**
** This copyrighted material is made available to anyone wishing to use,
** modify, copy, or redistribute it subject to the terms and conditions
@@ -58,8 +58,12 @@ static void copy_from_cb(void *dst, const void *base, unsigned offset,
int dlm_process_incoming_buffer(int nodeid, const void *base,
unsigned offset, unsigned len, unsigned limit)
{
- unsigned char __tmp[DLM_INBUF_LEN];
- struct dlm_header *msg = (struct dlm_header *) __tmp;
+ union {
+ unsigned char __buf[DLM_INBUF_LEN];
+ /* this is to force proper alignment on some arches */
+ struct dlm_header dlm;
+ } __tmp;
+ struct dlm_header *msg = &__tmp.dlm;
int ret = 0;
int err = 0;
uint16_t msglen;
@@ -100,8 +104,7 @@ int dlm_process_incoming_buffer(int nodeid, const void *base,
in the buffer on the stack (which should work for most
ordinary messages). */
- if (msglen > sizeof(__tmp) &&
- msg == (struct dlm_header *) __tmp) {
+ if (msglen > DLM_INBUF_LEN && msg == &__tmp.dlm) {
msg = kmalloc(dlm_config.ci_buffer_size, GFP_KERNEL);
if (msg == NULL)
return ret;
@@ -119,7 +122,7 @@ int dlm_process_incoming_buffer(int nodeid, const void *base,
dlm_receive_buffer(msg, nodeid);
}
- if (msg != (struct dlm_header *) __tmp)
+ if (msg != &__tmp.dlm)
kfree(msg);
return err ? err : ret;
diff --git a/fs/dlm/rcom.c b/fs/dlm/rcom.c
index ae2fd97fa4a..026824cd3ac 100644
--- a/fs/dlm/rcom.c
+++ b/fs/dlm/rcom.c
@@ -2,7 +2,7 @@
*******************************************************************************
**
** Copyright (C) Sistina Software, Inc. 1997-2003 All rights reserved.
-** Copyright (C) 2005-2007 Red Hat, Inc. All rights reserved.
+** Copyright (C) 2005-2008 Red Hat, Inc. All rights reserved.
**
** This copyrighted material is made available to anyone wishing to use,
** modify, copy, or redistribute it subject to the terms and conditions
@@ -197,11 +197,6 @@ static void receive_sync_reply(struct dlm_ls *ls, struct dlm_rcom *rc_in)
spin_unlock(&ls->ls_rcom_spin);
}
-static void receive_rcom_status_reply(struct dlm_ls *ls, struct dlm_rcom *rc_in)
-{
- receive_sync_reply(ls, rc_in);
-}
-
int dlm_rcom_names(struct dlm_ls *ls, int nodeid, char *last_name, int last_len)
{
struct dlm_rcom *rc;
@@ -254,11 +249,6 @@ static void receive_rcom_names(struct dlm_ls *ls, struct dlm_rcom *rc_in)
send_rcom(ls, mh, rc);
}
-static void receive_rcom_names_reply(struct dlm_ls *ls, struct dlm_rcom *rc_in)
-{
- receive_sync_reply(ls, rc_in);
-}
-
int dlm_send_rcom_lookup(struct dlm_rsb *r, int dir_nodeid)
{
struct dlm_rcom *rc;
@@ -381,11 +371,6 @@ static void receive_rcom_lock(struct dlm_ls *ls, struct dlm_rcom *rc_in)
send_rcom(ls, mh, rc);
}
-static void receive_rcom_lock_reply(struct dlm_ls *ls, struct dlm_rcom *rc_in)
-{
- dlm_recover_process_copy(ls, rc_in);
-}
-
/* If the lockspace doesn't exist then still send a status message
back; it's possible that it just doesn't have its global_id yet. */
@@ -481,11 +466,11 @@ void dlm_receive_rcom(struct dlm_ls *ls, struct dlm_rcom *rc, int nodeid)
break;
case DLM_RCOM_STATUS_REPLY:
- receive_rcom_status_reply(ls, rc);
+ receive_sync_reply(ls, rc);
break;
case DLM_RCOM_NAMES_REPLY:
- receive_rcom_names_reply(ls, rc);
+ receive_sync_reply(ls, rc);
break;
case DLM_RCOM_LOOKUP_REPLY:
@@ -493,11 +478,11 @@ void dlm_receive_rcom(struct dlm_ls *ls, struct dlm_rcom *rc, int nodeid)
break;
case DLM_RCOM_LOCK_REPLY:
- receive_rcom_lock_reply(ls, rc);
+ dlm_recover_process_copy(ls, rc);
break;
default:
- DLM_ASSERT(0, printk("rc_type=%x\n", rc->rc_type););
+ log_error(ls, "receive_rcom bad type %d", rc->rc_type);
}
out:
return;
diff --git a/fs/dlm/recover.c b/fs/dlm/recover.c
index c2cc7694cd1..df075dc300f 100644
--- a/fs/dlm/recover.c
+++ b/fs/dlm/recover.c
@@ -629,7 +629,7 @@ static void recover_lvb(struct dlm_rsb *r)
goto out;
if (!r->res_lvbptr) {
- r->res_lvbptr = allocate_lvb(r->res_ls);
+ r->res_lvbptr = dlm_allocate_lvb(r->res_ls);
if (!r->res_lvbptr)
goto out;
}
@@ -731,6 +731,20 @@ int dlm_create_root_list(struct dlm_ls *ls)
list_add(&r->res_root_list, &ls->ls_root_list);
dlm_hold_rsb(r);
}
+
+ /* If we're using a directory, add tossed rsbs to the root
+ list; they'll have entries created in the new directory,
+ but no other recovery steps should do anything with them. */
+
+ if (dlm_no_directory(ls)) {
+ read_unlock(&ls->ls_rsbtbl[i].lock);
+ continue;
+ }
+
+ list_for_each_entry(r, &ls->ls_rsbtbl[i].toss, res_hashchain) {
+ list_add(&r->res_root_list, &ls->ls_root_list);
+ dlm_hold_rsb(r);
+ }
read_unlock(&ls->ls_rsbtbl[i].lock);
}
out:
@@ -750,6 +764,11 @@ void dlm_release_root_list(struct dlm_ls *ls)
up_write(&ls->ls_root_sem);
}
+/* If not using a directory, clear the entire toss list, there's no benefit to
+ caching the master value since it's fixed. If we are using a dir, keep the
+ rsb's we're the master of. Recovery will add them to the root list and from
+ there they'll be entered in the rebuilt directory. */
+
void dlm_clear_toss_list(struct dlm_ls *ls)
{
struct dlm_rsb *r, *safe;
@@ -759,8 +778,10 @@ void dlm_clear_toss_list(struct dlm_ls *ls)
write_lock(&ls->ls_rsbtbl[i].lock);
list_for_each_entry_safe(r, safe, &ls->ls_rsbtbl[i].toss,
res_hashchain) {
- list_del(&r->res_hashchain);
- free_rsb(r);
+ if (dlm_no_directory(ls) || !is_master(r)) {
+ list_del(&r->res_hashchain);
+ dlm_free_rsb(r);
+ }
}
write_unlock(&ls->ls_rsbtbl[i].lock);
}
diff --git a/fs/dlm/recoverd.c b/fs/dlm/recoverd.c
index 4b89e20eebe..997f9531d59 100644
--- a/fs/dlm/recoverd.c
+++ b/fs/dlm/recoverd.c
@@ -67,17 +67,18 @@ static int ls_recover(struct dlm_ls *ls, struct dlm_recover *rv)
dlm_astd_resume();
/*
- * This list of root rsb's will be the basis of most of the recovery
- * routines.
+ * Free non-master tossed rsb's. Master rsb's are kept on toss
+ * list and put on root list to be included in resdir recovery.
*/
- dlm_create_root_list(ls);
+ dlm_clear_toss_list(ls);
/*
- * Free all the tossed rsb's so we don't have to recover them.
+ * This list of root rsb's will be the basis of most of the recovery
+ * routines.
*/
- dlm_clear_toss_list(ls);
+ dlm_create_root_list(ls);
/*
* Add or remove nodes from the lockspace's ls_nodes list.
diff --git a/fs/dlm/user.c b/fs/dlm/user.c
index 4f741546f4b..7cbc6826239 100644
--- a/fs/dlm/user.c
+++ b/fs/dlm/user.c
@@ -24,8 +24,7 @@
#include "lvb_table.h"
#include "user.h"
-static const char *name_prefix="dlm";
-static struct miscdevice ctl_device;
+static const char name_prefix[] = "dlm";
static const struct file_operations device_fops;
#ifdef CONFIG_COMPAT
@@ -82,7 +81,8 @@ struct dlm_lock_result32 {
};
static void compat_input(struct dlm_write_request *kb,
- struct dlm_write_request32 *kb32)
+ struct dlm_write_request32 *kb32,
+ int max_namelen)
{
kb->version[0] = kb32->version[0];
kb->version[1] = kb32->version[1];
@@ -112,7 +112,11 @@ static void compat_input(struct dlm_write_request *kb,
kb->i.lock.bastaddr = (void *)(long)kb32->i.lock.bastaddr;
kb->i.lock.lksb = (void *)(long)kb32->i.lock.lksb;
memcpy(kb->i.lock.lvb, kb32->i.lock.lvb, DLM_USER_LVB_LEN);
- memcpy(kb->i.lock.name, kb32->i.lock.name, kb->i.lock.namelen);
+ if (kb->i.lock.namelen <= max_namelen)
+ memcpy(kb->i.lock.name, kb32->i.lock.name,
+ kb->i.lock.namelen);
+ else
+ kb->i.lock.namelen = max_namelen;
}
}
@@ -236,12 +240,12 @@ void dlm_user_add_ast(struct dlm_lkb *lkb, int type)
spin_unlock(&proc->asts_spin);
if (eol) {
- spin_lock(&ua->proc->locks_spin);
+ spin_lock(&proc->locks_spin);
if (!list_empty(&lkb->lkb_ownqueue)) {
list_del_init(&lkb->lkb_ownqueue);
dlm_put_lkb(lkb);
}
- spin_unlock(&ua->proc->locks_spin);
+ spin_unlock(&proc->locks_spin);
}
out:
mutex_unlock(&ls->ls_clear_proc_locks);
@@ -529,7 +533,8 @@ static ssize_t device_write(struct file *file, const char __user *buf,
if (proc)
set_bit(DLM_PROC_FLAGS_COMPAT, &proc->flags);
- compat_input(kbuf, k32buf);
+ compat_input(kbuf, k32buf,
+ count - sizeof(struct dlm_write_request32));
kfree(k32buf);
}
#endif
@@ -896,14 +901,16 @@ static const struct file_operations ctl_device_fops = {
.owner = THIS_MODULE,
};
+static struct miscdevice ctl_device = {
+ .name = "dlm-control",
+ .fops = &ctl_device_fops,
+ .minor = MISC_DYNAMIC_MINOR,
+};
+
int dlm_user_init(void)
{
int error;
- ctl_device.name = "dlm-control";
- ctl_device.fops = &ctl_device_fops;
- ctl_device.minor = MISC_DYNAMIC_MINOR;
-
error = misc_register(&ctl_device);
if (error)
log_print("misc_register failed for control device");
diff --git a/fs/dlm/util.c b/fs/dlm/util.c
index 963889cf674..4d9c1f4e1bd 100644
--- a/fs/dlm/util.c
+++ b/fs/dlm/util.c
@@ -1,7 +1,7 @@
/******************************************************************************
*******************************************************************************
**
-** Copyright (C) 2005 Red Hat, Inc. All rights reserved.
+** Copyright (C) 2005-2008 Red Hat, Inc. All rights reserved.
**
** This copyrighted material is made available to anyone wishing to use,
** modify, copy, or redistribute it subject to the terms and conditions
@@ -14,6 +14,14 @@
#include "rcom.h"
#include "util.h"
+#define DLM_ERRNO_EDEADLK 35
+#define DLM_ERRNO_EBADR 53
+#define DLM_ERRNO_EBADSLT 57
+#define DLM_ERRNO_EPROTO 71
+#define DLM_ERRNO_EOPNOTSUPP 95
+#define DLM_ERRNO_ETIMEDOUT 110
+#define DLM_ERRNO_EINPROGRESS 115
+
static void header_out(struct dlm_header *hd)
{
hd->h_version = cpu_to_le32(hd->h_version);
@@ -30,11 +38,54 @@ static void header_in(struct dlm_header *hd)
hd->h_length = le16_to_cpu(hd->h_length);
}
-void dlm_message_out(struct dlm_message *ms)
+/* higher errno values are inconsistent across architectures, so select
+ one set of values for on the wire */
+
+static int to_dlm_errno(int err)
+{
+ switch (err) {
+ case -EDEADLK:
+ return -DLM_ERRNO_EDEADLK;
+ case -EBADR:
+ return -DLM_ERRNO_EBADR;
+ case -EBADSLT:
+ return -DLM_ERRNO_EBADSLT;
+ case -EPROTO:
+ return -DLM_ERRNO_EPROTO;
+ case -EOPNOTSUPP:
+ return -DLM_ERRNO_EOPNOTSUPP;
+ case -ETIMEDOUT:
+ return -DLM_ERRNO_ETIMEDOUT;
+ case -EINPROGRESS:
+ return -DLM_ERRNO_EINPROGRESS;
+ }
+ return err;
+}
+
+static int from_dlm_errno(int err)
{
- struct dlm_header *hd = (struct dlm_header *) ms;
+ switch (err) {
+ case -DLM_ERRNO_EDEADLK:
+ return -EDEADLK;
+ case -DLM_ERRNO_EBADR:
+ return -EBADR;
+ case -DLM_ERRNO_EBADSLT:
+ return -EBADSLT;
+ case -DLM_ERRNO_EPROTO:
+ return -EPROTO;
+ case -DLM_ERRNO_EOPNOTSUPP:
+ return -EOPNOTSUPP;
+ case -DLM_ERRNO_ETIMEDOUT:
+ return -ETIMEDOUT;
+ case -DLM_ERRNO_EINPROGRESS:
+ return -EINPROGRESS;
+ }
+ return err;
+}
- header_out(hd);
+void dlm_message_out(struct dlm_message *ms)
+{
+ header_out(&ms->m_header);
ms->m_type = cpu_to_le32(ms->m_type);
ms->m_nodeid = cpu_to_le32(ms->m_nodeid);
@@ -53,14 +104,12 @@ void dlm_message_out(struct dlm_message *ms)
ms->m_rqmode = cpu_to_le32(ms->m_rqmode);
ms->m_bastmode = cpu_to_le32(ms->m_bastmode);
ms->m_asts = cpu_to_le32(ms->m_asts);
- ms->m_result = cpu_to_le32(ms->m_result);
+ ms->m_result = cpu_to_le32(to_dlm_errno(ms->m_result));
}
void dlm_message_in(struct dlm_message *ms)
{
- struct dlm_header *hd = (struct dlm_header *) ms;
-
- header_in(hd);
+ header_in(&ms->m_header);
ms->m_type = le32_to_cpu(ms->m_type);
ms->m_nodeid = le32_to_cpu(ms->m_nodeid);
@@ -79,7 +128,7 @@ void dlm_message_in(struct dlm_message *ms)
ms->m_rqmode = le32_to_cpu(ms->m_rqmode);
ms->m_bastmode = le32_to_cpu(ms->m_bastmode);
ms->m_asts = le32_to_cpu(ms->m_asts);
- ms->m_result = le32_to_cpu(ms->m_result);
+ ms->m_result = from_dlm_errno(le32_to_cpu(ms->m_result));
}
static void rcom_lock_out(struct rcom_lock *rl)
@@ -126,10 +175,9 @@ static void rcom_config_in(struct rcom_config *rf)
void dlm_rcom_out(struct dlm_rcom *rc)
{
- struct dlm_header *hd = (struct dlm_header *) rc;
int type = rc->rc_type;
- header_out(hd);
+ header_out(&rc->rc_header);
rc->rc_type = cpu_to_le32(rc->rc_type);
rc->rc_result = cpu_to_le32(rc->rc_result);
@@ -137,7 +185,7 @@ void dlm_rcom_out(struct dlm_rcom *rc)
rc->rc_seq = cpu_to_le64(rc->rc_seq);
rc->rc_seq_reply = cpu_to_le64(rc->rc_seq_reply);
- if (type == DLM_RCOM_LOCK)
+ if ((type == DLM_RCOM_LOCK) || (type == DLM_RCOM_LOCK_REPLY))
rcom_lock_out((struct rcom_lock *) rc->rc_buf);
else if (type == DLM_RCOM_STATUS_REPLY)
@@ -146,9 +194,9 @@ void dlm_rcom_out(struct dlm_rcom *rc)
void dlm_rcom_in(struct dlm_rcom *rc)
{
- struct dlm_header *hd = (struct dlm_header *) rc;
+ int type;
- header_in(hd);
+ header_in(&rc->rc_header);
rc->rc_type = le32_to_cpu(rc->rc_type);
rc->rc_result = le32_to_cpu(rc->rc_result);
@@ -156,10 +204,12 @@ void dlm_rcom_in(struct dlm_rcom *rc)
rc->rc_seq = le64_to_cpu(rc->rc_seq);
rc->rc_seq_reply = le64_to_cpu(rc->rc_seq_reply);
- if (rc->rc_type == DLM_RCOM_LOCK)
+ type = rc->rc_type;
+
+ if ((type == DLM_RCOM_LOCK) || (type == DLM_RCOM_LOCK_REPLY))
rcom_lock_in((struct rcom_lock *) rc->rc_buf);
- else if (rc->rc_type == DLM_RCOM_STATUS_REPLY)
+ else if (type == DLM_RCOM_STATUS_REPLY)
rcom_config_in((struct rcom_config *) rc->rc_buf);
}
diff --git a/fs/jbd/checkpoint.c b/fs/jbd/checkpoint.c
index 0f69c416eeb..a5432bbbfb8 100644
--- a/fs/jbd/checkpoint.c
+++ b/fs/jbd/checkpoint.c
@@ -347,7 +347,8 @@ restart:
break;
}
retry = __process_buffer(journal, jh, bhs,&batch_count);
- if (!retry && lock_need_resched(&journal->j_list_lock)){
+ if (!retry && (need_resched() ||
+ spin_needbreak(&journal->j_list_lock))) {
spin_unlock(&journal->j_list_lock);
retry = 1;
break;
diff --git a/fs/jbd/commit.c b/fs/jbd/commit.c
index 610264b99a8..31853eb65b4 100644
--- a/fs/jbd/commit.c
+++ b/fs/jbd/commit.c
@@ -265,7 +265,7 @@ write_out_data:
put_bh(bh);
}
- if (lock_need_resched(&journal->j_list_lock)) {
+ if (need_resched() || spin_needbreak(&journal->j_list_lock)) {
spin_unlock(&journal->j_list_lock);
goto write_out_data;
}
diff --git a/fs/jbd2/checkpoint.c b/fs/jbd2/checkpoint.c
index 1b7f282c1ae..6914598022c 100644
--- a/fs/jbd2/checkpoint.c
+++ b/fs/jbd2/checkpoint.c
@@ -353,7 +353,8 @@ restart:
}
retry = __process_buffer(journal, jh, bhs, &batch_count,
transaction);
- if (!retry && lock_need_resched(&journal->j_list_lock)){
+ if (!retry && (need_resched() ||
+ spin_needbreak(&journal->j_list_lock))) {
spin_unlock(&journal->j_list_lock);
retry = 1;
break;
diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c
index da8d0eb3b7b..4f302d27927 100644
--- a/fs/jbd2/commit.c
+++ b/fs/jbd2/commit.c
@@ -341,7 +341,7 @@ write_out_data:
put_bh(bh);
}
- if (lock_need_resched(&journal->j_list_lock)) {
+ if (need_resched() || spin_needbreak(&journal->j_list_lock)) {
spin_unlock(&journal->j_list_lock);
goto write_out_data;
}
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2025-03-27 09:47:26 +0000