Currently 3 filesystems support DAX: ext2, ext4 and xfs. Enabling DAX on them
is different.
-Enabling DAX on ext4 and ext2
+Enabling DAX on ext2
-----------------------------
When mounting the filesystem, use the "-o dax" option on the command line or
within the filesystem. It is equivalent to the '-o dax=always' behavior below.
-Enabling DAX on xfs
--------------------
+Enabling DAX on xfs and ext4
+----------------------------
Summary
-------
Verity files cannot have blocks allocated past the end of the verity
metadata.
+
+Verity and DAX are not compatible and attempts to set both of these flags
+on a file will fail.
.. kernel-doc:: arch/sh/kernel/cpu/sh4/sq.c
:export:
-SH-5
-----
-
-TLB Interfaces
-~~~~~~~~~~~~~~
-
-.. kernel-doc:: arch/sh/mm/tlb-sh5.c
- :internal:
-
-.. kernel-doc:: arch/sh/include/asm/tlb_64.h
- :internal:
-
Machine Specific Interfaces
===========================
S: Supported
F: drivers/dma/at_xdmac.c
-MICROSEMI ETHERNET SWITCH DRIVER
-M: Alexandre Belloni <alexandre.belloni@bootlin.com>
-M: Microchip Linux Driver Support <UNGLinuxDriver@microchip.com>
-L: netdev@vger.kernel.org
-S: Supported
-F: drivers/net/ethernet/mscc/
-F: include/soc/mscc/ocelot*
-
MICROSEMI MIPS SOCS
M: Alexandre Belloni <alexandre.belloni@bootlin.com>
M: Microchip Linux Driver Support <UNGLinuxDriver@microchip.com>
S: Supported
F: tools/objtool/
+OCELOT ETHERNET SWITCH DRIVER
+M: Microchip Linux Driver Support <UNGLinuxDriver@microchip.com>
+M: Vladimir Oltean <vladimir.oltean@nxp.com>
+M: Claudiu Manoil <claudiu.manoil@nxp.com>
+M: Alexandre Belloni <alexandre.belloni@bootlin.com>
+L: netdev@vger.kernel.org
+S: Supported
+F: drivers/net/dsa/ocelot/*
+F: drivers/net/ethernet/mscc/
+F: include/soc/mscc/ocelot*
+F: net/dsa/tag_ocelot.c
+
OCXL (Open Coherent Accelerator Processor Interface OpenCAPI) DRIVER
M: Frederic Barrat <fbarrat@linux.ibm.com>
M: Andrew Donnellan <ajd@linux.ibm.com>
F: drivers/i2c/busses/i2c-emev2.c
RENESAS ETHERNET DRIVERS
-R: Sergei Shtylyov <sergei.shtylyov@cogentembedded.com>
+R: Sergei Shtylyov <sergei.shtylyov@gmail.com>
L: netdev@vger.kernel.org
L: linux-renesas-soc@vger.kernel.org
F: Documentation/devicetree/bindings/net/renesas,*.txt
F: drivers/input/serio/userio.c
F: include/uapi/linux/userio.h
-VITESSE FELIX ETHERNET SWITCH DRIVER
-M: Vladimir Oltean <vladimir.oltean@nxp.com>
-M: Claudiu Manoil <claudiu.manoil@nxp.com>
-L: netdev@vger.kernel.org
-S: Maintained
-F: drivers/net/dsa/ocelot/*
-F: net/dsa/tag_ocelot.c
-
VIVID VIRTUAL VIDEO DRIVER
M: Hans Verkuil <hverkuil@xs4all.nl>
L: linux-media@vger.kernel.org
old = __opcode_to_mem_arm(old);
if (validate) {
- if (probe_kernel_read(&replaced, (void *)pc, MCOUNT_INSN_SIZE))
+ if (copy_from_kernel_nofault(&replaced, (void *)pc,
+ MCOUNT_INSN_SIZE))
return -EFAULT;
if (replaced != old)
/* patch_text() only supports int-sized breakpoints */
BUILD_BUG_ON(sizeof(int) != BREAK_INSTR_SIZE);
- err = probe_kernel_read(bpt->saved_instr, (char *)bpt->bpt_addr,
+ err = copy_from_kernel_nofault(bpt->saved_instr, (char *)bpt->bpt_addr,
BREAK_INSTR_SIZE);
if (err)
return err;
u32 insn = __opcode_to_mem_arm(BUG_INSTR_VALUE);
#endif
- if (probe_kernel_address((unsigned *)pc, bkpt))
+ if (get_kernel_nofault(bkpt, (void *)pc))
return 0;
return bkpt == insn;
if (user_mode(regs))
fault = get_user(instr, ip);
else
- fault = probe_kernel_address(ip, instr);
+ fault = get_kernel_nofault(instr, ip);
*inst = __mem_to_opcode_arm(instr);
if (user_mode(regs))
fault = get_user(instr, ip);
else
- fault = probe_kernel_address(ip, instr);
+ fault = get_kernel_nofault(instr, ip);
*inst = __mem_to_opcode_thumb16(instr);
int ret;
__le32 val;
- ret = probe_kernel_read(&val, addr, AARCH64_INSN_SIZE);
+ ret = copy_from_kernel_nofault(&val, addr, AARCH64_INSN_SIZE);
if (!ret)
*insnp = le32_to_cpu(val);
raw_spin_lock_irqsave(&patch_lock, flags);
waddr = patch_map(addr, FIX_TEXT_POKE0);
- ret = probe_kernel_write(waddr, &insn, AARCH64_INSN_SIZE);
+ ret = copy_to_kernel_nofault(waddr, &insn, AARCH64_INSN_SIZE);
patch_unmap(FIX_TEXT_POKE0);
raw_spin_unlock_irqrestore(&patch_lock, flags);
if (!user_mode(regs)) {
__le32 instr_le;
- if (probe_kernel_address((__force __le32 *)pc, instr_le))
+ if (get_kernel_nofault(instr_le, (__force __le32 *)pc))
goto exit;
instr = le32_to_cpu(instr_le);
} else if (compat_thumb_mode(regs)) {
uint16_t olds[7];
unsigned long hook_pos = hook - 2;
- if (probe_kernel_read((void *)olds, (void *)hook_pos, sizeof(nops)))
+ if (copy_from_kernel_nofault((void *)olds, (void *)hook_pos,
+ sizeof(nops)))
return -EFAULT;
if (memcmp((void *)nops, (void *)olds, sizeof(nops))) {
make_jbsr(target, hook, call, nolr);
- ret = probe_kernel_write((void *)hook_pos, enable ? call : nops,
+ ret = copy_to_kernel_nofault((void *)hook_pos, enable ? call : nops,
sizeof(nops));
if (ret)
return -EPERM;
struct fdesc *desc = ptr;
void *p;
- if (!probe_kernel_address(&desc->ip, p))
+ if (!get_kernel_nofault(p, (void *)&desc->ip))
ptr = p;
return ptr;
}
goto skip_check;
/* read the text we want to modify */
- if (probe_kernel_read(replaced, (void *)ip, MCOUNT_INSN_SIZE))
+ if (copy_from_kernel_nofault(replaced, (void *)ip, MCOUNT_INSN_SIZE))
return -EFAULT;
/* Make sure it is what we expect it to be */
skip_check:
/* replace the text with the new text */
- if (probe_kernel_write(((void *)ip), new_code, MCOUNT_INSN_SIZE))
+ if (copy_to_kernel_nofault(((void *)ip), new_code, MCOUNT_INSN_SIZE))
return -EPERM;
flush_icache_range(ip, ip + MCOUNT_INSN_SIZE);
unsigned char __attribute__((aligned(8))) replaced[MCOUNT_INSN_SIZE];
unsigned long ip = rec->ip;
- if (probe_kernel_read(replaced, (void *)ip, MCOUNT_INSN_SIZE))
+ if (copy_from_kernel_nofault(replaced, (void *)ip, MCOUNT_INSN_SIZE))
return -EFAULT;
if (rec->flags & FTRACE_FL_CONVERTED) {
struct ftrace_call_insn *call_insn, *tmp_call;
struct unw_info_block {
u64 header;
- u64 desc[0]; /* unwind descriptors */
+ u64 desc[]; /* unwind descriptors */
/* personality routine and language-specific data follow behind descriptors */
};
goto out;
}
- if ((probe_kernel_read(&prev_insn, p->addr - 1,
- sizeof(mips_instruction)) == 0) &&
- insn_has_delayslot(prev_insn)) {
+ if (copy_from_kernel_nofault(&prev_insn, p->addr - 1,
+ sizeof(mips_instruction)) == 0 &&
+ insn_has_delayslot(prev_insn)) {
pr_notice("Kprobes for branch delayslot are not supported\n");
ret = -EINVAL;
goto out;
unsigned long orig_insn[3];
if (validate) {
- if (probe_kernel_read(orig_insn, (void *)pc, MCOUNT_INSN_SIZE))
+ if (copy_from_kernel_nofault(orig_insn, (void *)pc,
+ MCOUNT_INSN_SIZE))
return -EFAULT;
if (memcmp(orig_insn, old_insn, MCOUNT_INSN_SIZE))
return -EINVAL;
}
- if (probe_kernel_write((void *)pc, new_insn, MCOUNT_INSN_SIZE))
+ if (copy_to_kernel_nofault((void *)pc, new_insn, MCOUNT_INSN_SIZE))
return -EPERM;
return 0;
ip = (void *)(rec->ip + 4 - size);
- ret = probe_kernel_read(insn, ip, size);
+ ret = copy_from_kernel_nofault(insn, ip, size);
if (ret)
return ret;
int kgdb_arch_set_breakpoint(struct kgdb_bkpt *bpt)
{
- int ret = probe_kernel_read(bpt->saved_instr, (char *)bpt->bpt_addr,
- BREAK_INSTR_SIZE);
+ int ret = copy_from_kernel_nofault(bpt->saved_instr,
+ (char *)bpt->bpt_addr, BREAK_INSTR_SIZE);
if (ret)
return ret;
Elf64_Fdesc *desc = ptr;
void *p;
- if (!probe_kernel_address(&desc->addr, p))
+ if (!get_kernel_nofault(p, (void *)&desc->addr))
ptr = p;
return ptr;
}
EXPORT_SYMBOL(raw_copy_in_user);
EXPORT_SYMBOL(memcpy);
-bool probe_kernel_read_allowed(const void *unsafe_src, size_t size)
+bool copy_from_kernel_nofault_allowed(const void *unsafe_src, size_t size)
{
if ((unsigned long)unsafe_src < PAGE_SIZE)
return false;
struct ppc64_opd_entry *desc = ptr;
void *p;
- if (!probe_kernel_address(&desc->funcaddr, p))
+ if (!get_kernel_nofault(p, (void *)&desc->funcaddr))
ptr = p;
return ptr;
}
unsigned int instr;
struct ppc_inst *addr = (struct ppc_inst *)bpt->bpt_addr;
- err = probe_kernel_address(addr, instr);
+ err = get_kernel_nofault(instr, (unsigned *) addr);
if (err)
return err;
if (!p) {
unsigned int instr;
- if (probe_kernel_address(addr, instr))
+ if (get_kernel_nofault(instr, addr))
goto no_kprobe;
if (instr != BREAKPOINT_INSTRUCTION) {
stub = (struct ppc64_stub_entry *)addr;
- if (probe_kernel_read(&magic, &stub->magic, sizeof(magic))) {
+ if (copy_from_kernel_nofault(&magic, &stub->magic,
+ sizeof(magic))) {
pr_err("%s: fault reading magic for stub %lx for %s\n", __func__, addr, mod->name);
return -EFAULT;
}
return -EFAULT;
}
- if (probe_kernel_read(&funcdata, &stub->funcdata, sizeof(funcdata))) {
+ if (copy_from_kernel_nofault(&funcdata, &stub->funcdata,
+ sizeof(funcdata))) {
pr_err("%s: fault reading funcdata for stub %lx for %s\n", __func__, addr, mod->name);
return -EFAULT;
}
#endif
if (!__kernel_text_address(pc) ||
- probe_kernel_address((const void *)pc, instr)) {
+ get_kernel_nofault(instr, (const void *)pc)) {
pr_cont("XXXXXXXX ");
} else {
if (regs->nip == pc)
for (i = 0; i < 8 && n; i++, n--, pc += sizeof(int)) {
int instr;
- if (probe_user_read(&instr, (void __user *)pc, sizeof(instr))) {
+ if (copy_from_user_nofault(&instr, (void __user *)pc,
+ sizeof(instr))) {
seq_buf_printf(&s, "XXXXXXXX ");
continue;
}
unsigned long ip = rec->ip;
unsigned long tramp;
- if (probe_kernel_read(&op, (void *)ip, MCOUNT_INSN_SIZE))
+ if (copy_from_kernel_nofault(&op, (void *)ip, MCOUNT_INSN_SIZE))
return -EFAULT;
/* Make sure that that this is still a 24bit jump */
pr_devel("ip:%lx jumps to %lx", ip, tramp);
/* Find where the trampoline jumps to */
- if (probe_kernel_read(jmp, (void *)tramp, sizeof(jmp))) {
+ if (copy_from_kernel_nofault(jmp, (void *)tramp, sizeof(jmp))) {
pr_err("Failed to read %lx\n", tramp);
return -EFAULT;
}
isync();
if (is_load)
- ret = probe_user_read(to, (const void __user *)from, n);
+ ret = copy_from_user_nofault(to, (const void __user *)from, n);
else
- ret = probe_user_write((void __user *)to, from, n);
+ ret = copy_to_user_nofault((void __user *)to, from, n);
/* switch the pid first to avoid running host with unallocated pid */
if (quadrant == 1 && pid != old_pid)
unsigned int val, suffix;
int err;
- err = probe_user_read(&val, nip, sizeof(val));
+ err = copy_from_user_nofault(&val, nip, sizeof(val));
if (err)
return err;
if (get_op(val) == OP_PREFIX) {
- err = probe_user_read(&suffix, (void __user *)nip + 4, 4);
+ err = copy_from_user_nofault(&suffix, (void __user *)nip + 4, 4);
*inst = ppc_inst_prefix(val, suffix);
} else {
*inst = ppc_inst(val);
unsigned int val, suffix;
int err;
- err = probe_kernel_read(&val, src, sizeof(val));
+ err = copy_from_kernel_nofault(&val, src, sizeof(val));
if (err)
return err;
if (get_op(val) == OP_PREFIX) {
- err = probe_kernel_read(&suffix, (void *)src + 4, 4);
+ err = copy_from_kernel_nofault(&suffix, (void *)src + 4, 4);
*inst = ppc_inst_prefix(val, suffix);
} else {
*inst = ppc_inst(val);
unsigned int val;
int err;
- err = probe_user_read(&val, nip, sizeof(val));
+ err = copy_from_user_nofault(&val, nip, sizeof(val));
if (!err)
*inst = ppc_inst(val);
unsigned int val;
int err;
- err = probe_kernel_read(&val, src, sizeof(val));
+ err = copy_from_kernel_nofault(&val, src, sizeof(val));
if (!err)
*inst = ppc_inst(val);
* which means that we've done all that we can do from
* interrupt context.
*/
- if (probe_user_read(stack_frame, (void __user *)p, sizeof(stack_frame)))
+ if (copy_from_user_nofault(stack_frame, (void __user *)p,
+ sizeof(stack_frame)))
return 0;
if (!is_first)
{
unsigned long stack_frame[3];
- if (probe_user_read(stack_frame, (void __user *)sp, sizeof(stack_frame)))
+ if (copy_from_user_nofault(stack_frame, (void __user *)sp,
+ sizeof(stack_frame)))
return 0;
if (!is_first)
((unsigned long)ptr & 3))
return -EFAULT;
- rc = probe_user_read(ret, ptr, sizeof(*ret));
+ rc = copy_from_user_nofault(ret, ptr, sizeof(*ret));
if (IS_ENABLED(CONFIG_PPC64) && rc)
return read_user_stack_slow(ptr, ret, 4);
((unsigned long)ptr & 7))
return -EFAULT;
- if (!probe_user_read(ret, ptr, sizeof(*ret)))
+ if (!copy_from_user_nofault(ret, ptr, sizeof(*ret)))
return 0;
return read_user_stack_slow(ptr, ret, 8);
__u64 target;
if (is_kernel_addr(addr)) {
- if (probe_kernel_read(&instr, (void *)addr, sizeof(instr)))
+ if (copy_from_kernel_nofault(&instr, (void *)addr,
+ sizeof(instr)))
return 0;
return branch_target((struct ppc_inst *)&instr);
}
/* Userspace: need copy instruction here then translate it */
- if (probe_user_read(&instr, (unsigned int __user *)addr, sizeof(instr)))
+ if (copy_from_user_nofault(&instr, (unsigned int __user *)addr,
+ sizeof(instr)))
return 0;
target = branch_target((struct ppc_inst *)&instr);
if (is_in_pci_mem_space(addr)) {
if (user_mode(regs))
- ret = probe_user_read(&inst, (void __user *)regs->nip,
- sizeof(inst));
+ ret = copy_from_user_nofault(&inst,
+ (void __user *)regs->nip, sizeof(inst));
else
- ret = probe_kernel_address((void *)regs->nip, inst);
+ ret = get_kernel_nofault(inst, (void *)regs->nip);
if (!ret && mcheck_handle_load(regs, inst)) {
regs->nip += 4;
* Read the text we want to modify;
* return must be -EFAULT on read error
*/
- if (probe_kernel_read(replaced, (void *)hook_pos, MCOUNT_INSN_SIZE))
+ if (copy_from_kernel_nofault(replaced, (void *)hook_pos,
+ MCOUNT_INSN_SIZE))
return -EFAULT;
/*
unsigned int rs1_num, rs2_num;
int op_code;
- if (probe_kernel_address((void *)pc, op_code))
+ if (get_kernel_nofault(op_code, (void *)pc))
return -EINVAL;
if ((op_code & __INSN_LENGTH_MASK) != __INSN_LENGTH_GE_32) {
if (is_c_jalr_insn(op_code) || is_c_jr_insn(op_code)) {
return error;
/* Store the op code in the stepped address */
- error = probe_kernel_address((void *)addr, stepped_opcode);
+ error = get_kernel_nofault(stepped_opcode, (void *)addr);
if (error)
return error;
stepped_address = addr;
/* Replace the op code with the break instruction */
- error = probe_kernel_write((void *)stepped_address,
+ error = copy_to_kernel_nofault((void *)stepped_address,
arch_kgdb_ops.gdb_bpt_instr,
BREAK_INSTR_SIZE);
/* Flush and return */
static void undo_single_step(struct pt_regs *regs)
{
if (stepped_opcode != 0) {
- probe_kernel_write((void *)stepped_address,
+ copy_to_kernel_nofault((void *)stepped_address,
(void *)&stepped_opcode, BREAK_INSTR_SIZE);
flush_icache_range(stepped_address,
stepped_address + BREAK_INSTR_SIZE);
waddr = patch_map(addr, FIX_TEXT_POKE0);
- ret = probe_kernel_write(waddr, insn, len);
+ ret = copy_to_kernel_nofault(waddr, insn, len);
patch_unmap(FIX_TEXT_POKE0);
#else
static int patch_insn_write(void *addr, const void *insn, size_t len)
{
- return probe_kernel_write(addr, insn, len);
+ return copy_to_kernel_nofault(addr, insn, len);
}
NOKPROBE_SYMBOL(patch_insn_write);
#endif /* CONFIG_MMU */
{
bug_insn_t insn;
- if (probe_kernel_address((bug_insn_t *)pc, insn))
+ if (get_kernel_nofault(insn, (bug_insn_t *)pc))
return 0;
return GET_INSN_LENGTH(insn);
if (pc < VMALLOC_START)
return 0;
- if (probe_kernel_address((bug_insn_t *)pc, insn))
+ if (get_kernel_nofault(insn, (bug_insn_t *)pc))
return 0;
if ((insn & __INSN_LENGTH_MASK) == __INSN_LENGTH_32)
return (insn == __BUG_INSN_32);
{
struct ftrace_insn orig, new, old;
- if (probe_kernel_read(&old, (void *) rec->ip, sizeof(old)))
+ if (copy_from_kernel_nofault(&old, (void *) rec->ip, sizeof(old)))
return -EFAULT;
if (addr == MCOUNT_ADDR) {
/* Initial code replacement */
{
struct ftrace_insn orig, new, old;
- if (probe_kernel_read(&old, (void *) rec->ip, sizeof(old)))
+ if (copy_from_kernel_nofault(&old, (void *) rec->ip, sizeof(old)))
return -EFAULT;
/* Replace nop with an ftrace call. */
ftrace_generate_nop_insn(&orig);
{
unsigned long dummy;
- return probe_kernel_address((unsigned long *)p, dummy);
+ return get_kernel_nofault(dummy, (unsigned long *)p);
}
static void dump_pagetable(unsigned long asce, unsigned long address)
* But if one were to fail, then they all should, and if one were
* to succeed, then they all should.
*/
- mod_code_status = probe_kernel_write(mod_code_ip, mod_code_newcode,
+ mod_code_status = copy_to_kernel_nofault(mod_code_ip, mod_code_newcode,
MCOUNT_INSN_SIZE);
/* if we fail, then kill any new writers */
*/
/* read the text we want to modify */
- if (probe_kernel_read(replaced, (void *)ip, MCOUNT_INSN_SIZE))
+ if (copy_from_kernel_nofault(replaced, (void *)ip, MCOUNT_INSN_SIZE))
return -EFAULT;
/* Make sure it is what we expect it to be */
{
unsigned char code[MCOUNT_INSN_SIZE];
- if (probe_kernel_read(code, (void *)ip, MCOUNT_INSN_SIZE))
+ if (copy_from_kernel_nofault(code, (void *)ip, MCOUNT_INSN_SIZE))
return -EFAULT;
if (old_addr != __raw_readl((unsigned long *)code))
if (addr < PAGE_OFFSET)
return 0;
- if (probe_kernel_address((insn_size_t *)addr, opcode))
+ if (get_kernel_nofault(opcode, (insn_size_t *)addr))
return 0;
if (opcode == TRAPA_BUG_OPCODE)
return 1;
#include <linux/kernel.h>
#include <os.h>
-bool probe_kernel_read_allowed(const void *src, size_t size)
+bool copy_from_kernel_nofault_allowed(const void *src, size_t size)
{
void *psrc = (void *)rounddown((unsigned long)src, PAGE_SIZE);
}
/* To avoid include hell, we can't include uaccess.h */
-extern long probe_kernel_read(void *dst, const void *src, size_t size);
+extern long copy_from_kernel_nofault(void *dst, const void *src, size_t size);
/**
* regs_get_kernel_stack_nth() - get Nth entry of the stack
addr = regs_get_kernel_stack_nth_addr(regs, n);
if (addr) {
- ret = probe_kernel_read(&val, addr, sizeof(val));
+ ret = copy_from_kernel_nofault(&val, addr, sizeof(val));
if (!ret)
return val;
}
bad_ip = user_mode(regs) &&
__chk_range_not_ok(prologue, OPCODE_BUFSIZE, TASK_SIZE_MAX);
- if (bad_ip || probe_kernel_read(opcodes, (u8 *)prologue,
+ if (bad_ip || copy_from_kernel_nofault(opcodes, (u8 *)prologue,
OPCODE_BUFSIZE)) {
printk("%sCode: Bad RIP value.\n", loglvl);
} else {
* sure what we read is what we expected it to be before modifying it.
*/
/* read the text we want to modify */
- if (probe_kernel_read(cur_code, (void *)ip, MCOUNT_INSN_SIZE)) {
+ if (copy_from_kernel_nofault(cur_code, (void *)ip, MCOUNT_INSN_SIZE)) {
WARN_ON(1);
return -EFAULT;
}
npages = DIV_ROUND_UP(*tramp_size, PAGE_SIZE);
/* Copy ftrace_caller onto the trampoline memory */
- ret = probe_kernel_read(trampoline, (void *)start_offset, size);
+ ret = copy_from_kernel_nofault(trampoline, (void *)start_offset, size);
if (WARN_ON(ret < 0))
goto fail;
/* The trampoline ends with ret(q) */
retq = (unsigned long)ftrace_stub;
- ret = probe_kernel_read(ip, (void *)retq, RET_SIZE);
+ ret = copy_from_kernel_nofault(ip, (void *)retq, RET_SIZE);
if (WARN_ON(ret < 0))
goto fail;
if (ops->flags & FTRACE_OPS_FL_SAVE_REGS) {
ip = trampoline + (ftrace_regs_caller_ret - ftrace_regs_caller);
- ret = probe_kernel_read(ip, (void *)retq, RET_SIZE);
+ ret = copy_from_kernel_nofault(ip, (void *)retq, RET_SIZE);
if (WARN_ON(ret < 0))
goto fail;
}
union text_poke_insn call;
int ret;
- ret = probe_kernel_read(&call, ptr, CALL_INSN_SIZE);
+ ret = copy_from_kernel_nofault(&call, ptr, CALL_INSN_SIZE);
if (WARN_ON_ONCE(ret < 0))
return NULL;
int err;
bpt->type = BP_BREAKPOINT;
- err = probe_kernel_read(bpt->saved_instr, (char *)bpt->bpt_addr,
+ err = copy_from_kernel_nofault(bpt->saved_instr, (char *)bpt->bpt_addr,
BREAK_INSTR_SIZE);
if (err)
return err;
- err = probe_kernel_write((char *)bpt->bpt_addr,
+ err = copy_to_kernel_nofault((char *)bpt->bpt_addr,
arch_kgdb_ops.gdb_bpt_instr, BREAK_INSTR_SIZE);
if (!err)
return err;
return 0;
knl_write:
- return probe_kernel_write((char *)bpt->bpt_addr,
+ return copy_to_kernel_nofault((char *)bpt->bpt_addr,
(char *)bpt->saved_instr, BREAK_INSTR_SIZE);
}
* Fortunately, we know that the original code is the ideal 5-byte
* long NOP.
*/
- if (probe_kernel_read(buf, (void *)addr,
+ if (copy_from_kernel_nofault(buf, (void *)addr,
MAX_INSN_SIZE * sizeof(kprobe_opcode_t)))
return 0UL;
return 0;
/* This can access kernel text if given address is not recovered */
- if (probe_kernel_read(dest, (void *)recovered_insn, MAX_INSN_SIZE))
+ if (copy_from_kernel_nofault(dest, (void *)recovered_insn,
+ MAX_INSN_SIZE))
return 0;
kernel_insn_init(insn, dest, MAX_INSN_SIZE);
* overwritten by jump destination address. In this case, original
* bytes must be recovered from op->optinsn.copied_insn buffer.
*/
- if (probe_kernel_read(buf, (void *)addr,
+ if (copy_from_kernel_nofault(buf, (void *)addr,
MAX_INSN_SIZE * sizeof(kprobe_opcode_t)))
return 0UL;
}
static bool probe_list(struct pci_dev *pdev, unsigned short vendor,
- const unsigned char *rom_list)
+ const void *rom_list)
{
unsigned short device;
do {
- if (probe_kernel_address(rom_list, device) != 0)
+ if (get_kernel_nofault(device, rom_list) != 0)
device = 0;
if (device && match_id(pdev, vendor, device))
for (i = 0; i < ARRAY_SIZE(adapter_rom_resources); i++) {
struct resource *res = &adapter_rom_resources[i];
unsigned short offset, vendor, device, list, rev;
- const unsigned char *rom;
+ const void *rom;
if (res->end == 0)
break;
rom = isa_bus_to_virt(res->start);
- if (probe_kernel_address(rom + 0x18, offset) != 0)
+ if (get_kernel_nofault(offset, rom + 0x18) != 0)
continue;
- if (probe_kernel_address(rom + offset + 0x4, vendor) != 0)
+ if (get_kernel_nofault(vendor, rom + offset + 0x4) != 0)
continue;
- if (probe_kernel_address(rom + offset + 0x6, device) != 0)
+ if (get_kernel_nofault(device, rom + offset + 0x6) != 0)
continue;
if (match_id(pdev, vendor, device)) {
break;
}
- if (probe_kernel_address(rom + offset + 0x8, list) == 0 &&
- probe_kernel_address(rom + offset + 0xc, rev) == 0 &&
+ if (get_kernel_nofault(list, rom + offset + 0x8) == 0 &&
+ get_kernel_nofault(rev, rom + offset + 0xc) == 0 &&
rev >= 3 && list &&
probe_list(pdev, vendor, rom + offset + list)) {
oprom = res;
const unsigned short * const ptr = (const unsigned short *)rom;
unsigned short sig;
- return probe_kernel_address(ptr, sig) == 0 && sig == ROMSIGNATURE;
+ return get_kernel_nofault(sig, ptr) == 0 && sig == ROMSIGNATURE;
}
static int __init romchecksum(const unsigned char *rom, unsigned long length)
{
unsigned char sum, c;
- for (sum = 0; length && probe_kernel_address(rom++, c) == 0; length--)
+ for (sum = 0; length && get_kernel_nofault(c, rom++) == 0; length--)
sum += c;
return !length && !sum;
}
video_rom_resource.start = start;
- if (probe_kernel_address(rom + 2, c) != 0)
+ if (get_kernel_nofault(c, rom + 2) != 0)
continue;
/* 0 < length <= 0x7f * 512, historically */
if (!romsignature(rom))
continue;
- if (probe_kernel_address(rom + 2, c) != 0)
+ if (get_kernel_nofault(c, rom + 2) != 0)
continue;
/* 0 < length <= 0x7f * 512, historically */
if (addr < TASK_SIZE_MAX)
return 0;
- if (probe_kernel_address((unsigned short *)addr, ud))
+ if (get_kernel_nofault(ud, (unsigned short *)addr))
return 0;
return ud == INSN_UD0 || ud == INSN_UD2;
u8 insn_buf[MAX_INSN_SIZE];
struct insn insn;
- if (probe_kernel_read(insn_buf, (void *)regs->ip, MAX_INSN_SIZE))
+ if (copy_from_kernel_nofault(insn_buf, (void *)regs->ip,
+ MAX_INSN_SIZE))
return GP_NO_HINT;
kernel_insn_init(&insn, insn_buf, MAX_INSN_SIZE);
return !instr_lo || (instr_lo>>1) == 1;
case 0x00:
/* Prefetch instruction is 0x0F0D or 0x0F18 */
- if (probe_kernel_address(instr, opcode))
+ if (get_kernel_nofault(opcode, instr))
return 0;
*prefetch = (instr_lo == 0xF) &&
while (instr < max_instr) {
unsigned char opcode;
- if (probe_kernel_address(instr, opcode))
+ if (get_kernel_nofault(opcode, instr))
break;
instr++;
{
unsigned long dummy;
- return probe_kernel_address((unsigned long *)p, dummy);
+ return get_kernel_nofault(dummy, (unsigned long *)p);
}
static void dump_pagetable(unsigned long address)
return;
}
- if (probe_kernel_read(&desc, (void *)(gdt->address + offset),
+ if (copy_from_kernel_nofault(&desc, (void *)(gdt->address + offset),
sizeof(struct ldttss_desc))) {
pr_alert("%s: 0x%hx -- GDT entry is not readable\n",
name, index);
__set_fixmap(FIX_WP_TEST, __pa_symbol(empty_zero_page), PAGE_KERNEL_RO);
- if (probe_kernel_write((char *)fix_to_virt(FIX_WP_TEST), &z, 1)) {
+ if (copy_to_kernel_nofault((char *)fix_to_virt(FIX_WP_TEST), &z, 1)) {
clear_fixmap(FIX_WP_TEST);
printk(KERN_CONT "Ok.\n");
return;
return ((s64)vaddr << (64 - vaddr_bits)) >> (64 - vaddr_bits);
}
-bool probe_kernel_read_allowed(const void *unsafe_src, size_t size)
+bool copy_from_kernel_nofault_allowed(const void *unsafe_src, size_t size)
{
unsigned long vaddr = (unsigned long)unsafe_src;
canonical_address(vaddr, boot_cpu_data.x86_virt_bits) == vaddr;
}
#else
-bool probe_kernel_read_allowed(const void *unsafe_src, size_t size)
+bool copy_from_kernel_nofault_allowed(const void *unsafe_src, size_t size)
{
return (unsigned long)unsafe_src >= TASK_SIZE_MAX;
}
check <= (union bios32 *) __va(0xffff0);
++check) {
long sig;
- if (probe_kernel_address(&check->fields.signature, sig))
+ if (get_kernel_nofault(sig, &check->fields.signature))
continue;
if (check->fields.signature != BIOS32_SIGNATURE)
PURGATORY_CFLAGS_REMOVE := -mcmodel=kernel
PURGATORY_CFLAGS := -mcmodel=large -ffreestanding -fno-zero-initialized-in-bss
PURGATORY_CFLAGS += $(DISABLE_STACKLEAK_PLUGIN) -DDISABLE_BRANCH_PROFILING
+PURGATORY_CFLAGS += $(call cc-option,-fno-stack-protector)
# Default KBUILD_CFLAGS can have -pg option set when FTRACE is enabled. That
# in turn leaves some undefined symbols like __fentry__ in purgatory and not
preempt_disable();
- probe_kernel_read(&dummy, v, 1);
+ copy_from_kernel_nofault(&dummy, v, 1);
if (HYPERVISOR_update_va_mapping((unsigned long)v, pte, 0))
BUG();
u8 num; /* Total number of records */
u8 rec; /* This is record number n */
u8 map; /* Which portions are in use */
- u8 data[0];
+ u8 data[];
};
/* In memory LDM database structures. */
struct tegra_ahb {
void __iomem *regs;
struct device *dev;
- u32 ctx[0];
+ u32 ctx[];
};
static inline u32 gizmo_readl(struct tegra_ahb *ahb, u32 offset)
unsigned int head_index;
unsigned int size;
int total; /* sum of all values */
- int values[0];
+ int values[];
};
extern struct fifo_buffer *fifo_alloc(unsigned int fifo_size);
u32 resync_rate;
/* Since protocol version 88 and higher. */
- char verify_alg[0];
+ char verify_alg[];
} __packed;
struct p_rs_param_89 {
u32 two_primaries;
/* Since protocol version 87 and higher. */
- char integrity_alg[0];
+ char integrity_alg[];
} __packed;
u16 dds_flags; /* use enum dds_flags here. */
/* optional queue_limits if (agreed_features & DRBD_FF_WSAME) */
- struct o_qlim qlim[0];
+ struct o_qlim qlim[];
} __packed;
struct p_state {
*/
u8 encoding;
- u8 code[0];
+ u8 code[];
} __packed;
struct p_delay_probe93 {
if (!ptr)
goto failed;
- probe = probe_kernel_read(bounce, ptr, sz);
+ probe = copy_from_kernel_nofault(bounce, ptr, sz);
unxlate_dev_mem_ptr(p, ptr);
if (probe)
goto failed;
struct __aead_ctx {
struct chcr_gcm_ctx gcm[0];
- struct chcr_authenc_ctx authenc[0];
+ struct chcr_authenc_ctx authenc[];
};
struct chcr_aead_ctx {
u8 nonce[4];
u16 hmac_ctrl;
u16 mayverify;
- struct __aead_ctx ctx[0];
+ struct __aead_ctx ctx[];
};
struct hmac_ctx {
struct __crypto_ctx {
struct hmac_ctx hmacctx[0];
struct ablk_ctx ablkctx[0];
- struct chcr_aead_ctx aeadctx[0];
+ struct chcr_aead_ctx aeadctx[];
};
struct chcr_context {
unsigned int ntxq;
unsigned int nrxq;
struct completion cbc_aes_aio_done;
- struct __crypto_ctx crypto_ctx[0];
+ struct __crypto_ctx crypto_ctx[];
};
struct chcr_hctx_per_wr {
else
va = ioremap(pa, PAGE_SIZE);
- if (probe_kernel_read(&i, (unsigned char *)va + DIO_IDOFF, 1)) {
+ if (copy_from_kernel_nofault(&i,
+ (unsigned char *)va + DIO_IDOFF, 1)) {
if (scode >= DIOII_SCBASE)
iounmap(va);
continue; /* no board present at that select code */
else
va = ioremap(pa, PAGE_SIZE);
- if (probe_kernel_read(&i, (unsigned char *)va + DIO_IDOFF, 1)) {
+ if (copy_from_kernel_nofault(&i,
+ (unsigned char *)va + DIO_IDOFF, 1)) {
if (scode >= DIOII_SCBASE)
iounmap(va);
continue; /* no board present at that select code */
struct dma_device ddev;
struct clk *clk;
void __iomem *reg_base;
- struct milbeaut_hdmac_chan channels[0];
+ struct milbeaut_hdmac_chan channels[];
};
static struct milbeaut_hdmac_chan *
struct milbeaut_xdmac_device {
struct dma_device ddev;
void __iomem *reg_base;
- struct milbeaut_xdmac_chan channels[0];
+ struct milbeaut_xdmac_chan channels[];
};
static struct milbeaut_xdmac_chan *
unsigned int dma_cycles;
struct virt_dma_desc vd;
uint8_t es;
- struct moxart_sg sg[0];
+ struct moxart_sg sg[];
};
struct moxart_chan {
u32 global_pause_count;
/* Last member of the structure */
- struct tegra_dma_channel channels[0];
+ struct tegra_dma_channel channels[];
};
static inline void tdma_write(struct tegra_dma *tdma, u32 reg, u32 val)
u32 residue;
u32 residue_stat;
- struct edma_pset pset[0];
+ struct edma_pset pset[];
};
struct edma_cc;
void *metadata; /* pointer to provided metadata buffer (EPIP, PSdata) */
unsigned int hwdesc_count;
- struct udma_hwdesc hwdesc[0];
+ struct udma_hwdesc hwdesc[];
};
enum udma_chan_state {
struct dma_device dma;
void __iomem *membase;
struct tasklet_struct tasklet;
- struct timb_dma_chan channels[0];
+ struct timb_dma_chan channels[];
};
static struct device *chan2dev(struct dma_chan *chan)
struct descriptor_resource {
struct client_resource resource;
struct fw_descriptor descriptor;
- u32 data[0];
+ u32 data[];
};
struct iso_resource {
u32 request_header[4];
int ack;
u32 length;
- u32 data[0];
+ u32 data[];
};
static void free_response_callback(struct fw_packet *packet,
/* Upper layer specific data. */
void *data;
- struct fw_node *ports[0];
+ struct fw_node *ports[];
};
static inline struct fw_node *fw_node_get(struct fw_node *node)
struct packet {
unsigned int length;
- char data[0];
+ char data[];
};
struct packet_buffer {
dma_addr_t buffer_bus;
size_t buffer_size;
size_t used;
- struct descriptor buffer[0];
+ struct descriptor buffer[];
};
struct context {
u8 header_format;
u8 type_descriptors_supported_count;
u8 per_log_type_descriptor_length;
- u8 supported_log_type_descriptos[0];
+ u8 supported_log_type_descriptos[];
} __packed;
#define DMI_SYSFS_SEL_FIELD(_field) \
struct cbmem_cons {
u32 size_dont_access_after_boot;
u32 cursor;
- u8 body[0];
+ u8 body[];
} __packed;
#define CURSOR_MASK ((1 << 28) - 1)
u32 version;
u32 ro_size;
u32 rw_size;
- u8 blob[0];
+ u8 blob[];
};
struct vpd_section {
u16 tgt0_off;
u16 nic1_off;
u16 tgt1_off;
- u16 expansion[0];
+ u16 expansion[];
} __attribute__((__packed__));
struct ibft_initiator {
u8 creator_id[4];
u32 creator_rev;
u32 num_uarts;
- struct pcdp_uart uart[0]; /* actual size is num_uarts */
+ struct pcdp_uart uart[]; /* actual size is num_uarts */
/* remainder of table is pcdp_device structures */
} __attribute__((packed));
unsigned int first_channel;
unsigned int last_channel;
/* this is the one that's exposed to the attributes */
- unsigned char priv[0];
+ unsigned char priv[];
};
void *stp_policy_node_priv(struct stp_policy_node *pn)
struct stp_master {
unsigned int nr_free;
- unsigned long chan_map[0];
+ unsigned long chan_map[];
};
struct stm_device {
const struct config_item_type *pdrv_node_type;
/* master allocation */
spinlock_t mc_lock;
- struct stp_master *masters[0];
+ struct stp_master *masters[];
};
#define to_stm_device(_d) \
hp_sdc.base_io = (unsigned long) 0xf0428000;
hp_sdc.data_io = (unsigned long) hp_sdc.base_io + 1;
hp_sdc.status_io = (unsigned long) hp_sdc.base_io + 3;
- if (!probe_kernel_read(&i, (unsigned char *)hp_sdc.data_io, 1))
+ if (!copy_from_kernel_nofault(&i, (unsigned char *)hp_sdc.data_io, 1))
hp_sdc.dev = (void *)1;
hp_sdc.dev_err = hp_sdc_init();
#endif
decompressor) */
__u8 cmd[4]; /* the four byte of the command (in case of
nala, only the first 3 bytes is filled) */
- __u8 rawframe[0]; /* frame_size = H / 4 * vbandlength */
+ __u8 rawframe[]; /* frame_size = H / 4 * vbandlength */
} __packed;
/* intermediate buffers with raw data from the USB cam */
static struct i2c_driver mt6360_pmu_driver = {
.driver = {
+ .name = "mt6360_pmu",
.pm = &mt6360_pmu_pm_ops,
.of_match_table = of_match_ptr(mt6360_pmu_of_id),
},
char before[BREAK_INSTR_SIZE];
char after[BREAK_INSTR_SIZE];
- probe_kernel_read(before, (char *)kgdbts_break_test,
+ copy_from_kernel_nofault(before, (char *)kgdbts_break_test,
BREAK_INSTR_SIZE);
init_simple_test();
ts.tst = plant_and_detach_test;
/* Activate test with initial breakpoint */
if (!is_early)
kgdb_breakpoint();
- probe_kernel_read(after, (char *)kgdbts_break_test,
- BREAK_INSTR_SIZE);
+ copy_from_kernel_nofault(after, (char *)kgdbts_break_test,
+ BREAK_INSTR_SIZE);
if (memcmp(before, after, BREAK_INSTR_SIZE)) {
printk(KERN_CRIT "kgdbts: ERROR kgdb corrupted memory\n");
panic("kgdb memory corruption");
static int bareudp2info(struct nlattr *data[], struct bareudp_conf *conf,
struct netlink_ext_ack *extack)
{
+ memset(conf, 0, sizeof(*conf));
+
if (!data[IFLA_BAREUDP_PORT]) {
NL_SET_ERR_MSG(extack, "port not specified");
return -EINVAL;
__le32 irq_status;
__le32 sys_time_low;
__le32 sys_time_high;
- struct pucan_rx_msg msg[0];
+ struct pucan_rx_msg msg[];
} __packed __aligned(4);
/* Tx Link record */
struct pci_dev *pci_dev;
int can_count;
spinlock_t cmd_lock; /* 64-bits cmds must be atomic */
- struct pciefd_can *can[0]; /* array of network devices */
+ struct pciefd_can *can[]; /* array of network devices */
};
/* supported device ids. */
mutex_lock(&ptp_data->lock);
- rc = sja1105_ptpclkval_read(priv, &ticks, NULL);
+ rc = sja1105_ptpegr_ts_poll(ds, port, &ts);
if (rc < 0) {
- dev_err(ds->dev, "Failed to read PTP clock: %d\n", rc);
+ dev_err(ds->dev, "timed out polling for tstamp\n");
kfree_skb(skb);
goto out;
}
- rc = sja1105_ptpegr_ts_poll(ds, port, &ts);
+ rc = sja1105_ptpclkval_read(priv, &ticks, NULL);
if (rc < 0) {
- dev_err(ds->dev, "timed out polling for tstamp\n");
+ dev_err(ds->dev, "Failed to read PTP clock: %d\n", rc);
kfree_skb(skb);
goto out;
}
static void __alx_stop(struct alx_priv *alx)
{
- alx_halt(alx);
alx_free_irq(alx);
+
+ cancel_work_sync(&alx->link_check_wk);
+ cancel_work_sync(&alx->reset_wk);
+
+ alx_halt(alx);
alx_free_rings(alx);
alx_free_napis(alx);
}
struct alx_priv *alx = pci_get_drvdata(pdev);
struct alx_hw *hw = &alx->hw;
- cancel_work_sync(&alx->link_check_wk);
- cancel_work_sync(&alx->reset_wk);
-
/* restore permanent mac address */
alx_set_macaddr(hw, hw->perm_addr);
struct bnxt *bp = from_timer(bp, t, timer);
struct net_device *dev = bp->dev;
- if (!netif_running(dev))
+ if (!netif_running(dev) || !test_bit(BNXT_STATE_OPEN, &bp->state))
return;
if (atomic_read(&bp->intr_sem) != 0)
goto resume_exit;
}
- if (bnxt_hwrm_queue_qportcfg(bp)) {
- rc = -ENODEV;
+ rc = bnxt_hwrm_func_qcaps(bp);
+ if (rc)
goto resume_exit;
- }
-
- if (bp->hwrm_spec_code >= 0x10803) {
- if (bnxt_alloc_ctx_mem(bp)) {
- rc = -ENODEV;
- goto resume_exit;
- }
- }
- if (BNXT_NEW_RM(bp))
- bnxt_hwrm_func_resc_qcaps(bp, false);
if (bnxt_hwrm_func_drv_rgtr(bp, NULL, 0, false)) {
rc = -ENODEV;
resume_exit:
bnxt_ulp_start(bp, rc);
+ if (!rc)
+ bnxt_reenable_sriov(bp);
rtnl_unlock();
return rc;
}
bnxt_close(netdev);
pci_disable_device(pdev);
+ bnxt_free_ctx_mem(bp);
+ kfree(bp->ctx);
+ bp->ctx = NULL;
rtnl_unlock();
/* Request a slot slot reset. */
pci_set_master(pdev);
err = bnxt_hwrm_func_reset(bp);
- if (!err && netif_running(netdev))
- err = bnxt_open(netdev);
-
- if (!err)
- result = PCI_ERS_RESULT_RECOVERED;
+ if (!err) {
+ err = bnxt_hwrm_func_qcaps(bp);
+ if (!err && netif_running(netdev))
+ err = bnxt_open(netdev);
+ }
bnxt_ulp_start(bp, err);
+ if (!err) {
+ bnxt_reenable_sriov(bp);
+ result = PCI_ERS_RESULT_RECOVERED;
+ }
}
if (result != PCI_ERS_RESULT_RECOVERED) {
if (bp->ptp_info)
bp->ptp_info->ptp_init(dev);
+ return 0;
+
napi_exit:
for (q = 0, queue = bp->queues; q < bp->num_queues; ++q, ++queue)
napi_disable(&queue->napi);
pm_exit:
- if (err) {
- pm_runtime_put_sync(&bp->pdev->dev);
- return err;
- }
- return 0;
+ pm_runtime_put_sync(&bp->pdev->dev);
+ return err;
}
static int macb_close(struct net_device *dev)
struct ibmvnic_adapter *adapter = netdev_priv(netdev);
unsigned long timeout = msecs_to_jiffies(30000);
int retry_count = 0;
+ int retries = 10;
bool retry;
int rc;
do {
retry = false;
- if (retry_count > IBMVNIC_MAX_QUEUES) {
+ if (retry_count > retries) {
netdev_warn(netdev, "Login attempts exceeded\n");
return -1;
}
if (!wait_for_completion_timeout(&adapter->init_done,
timeout)) {
- netdev_warn(netdev, "Login timed out\n");
- return -1;
+ netdev_warn(netdev, "Login timed out, retrying...\n");
+ retry = true;
+ adapter->init_done_rc = 0;
+ retry_count++;
+ continue;
}
- if (adapter->init_done_rc == PARTIALSUCCESS) {
+ if (adapter->init_done_rc == ABORTED) {
+ netdev_warn(netdev, "Login aborted, retrying...\n");
+ retry = true;
+ adapter->init_done_rc = 0;
+ retry_count++;
+ /* FW or device may be busy, so
+ * wait a bit before retrying login
+ */
+ msleep(500);
+ } else if (adapter->init_done_rc == PARTIALSUCCESS) {
retry_count++;
release_sub_crqs(adapter, 1);
__be16 proto, u16 vid);
static void e1000_restore_vlan(struct e1000_adapter *adapter);
-#ifdef CONFIG_PM
-static int e1000_suspend(struct pci_dev *pdev, pm_message_t state);
-static int e1000_resume(struct pci_dev *pdev);
-#endif
+static int __maybe_unused e1000_suspend(struct device *dev);
+static int __maybe_unused e1000_resume(struct device *dev);
static void e1000_shutdown(struct pci_dev *pdev);
#ifdef CONFIG_NET_POLL_CONTROLLER
.resume = e1000_io_resume,
};
+static SIMPLE_DEV_PM_OPS(e1000_pm_ops, e1000_suspend, e1000_resume);
+
static struct pci_driver e1000_driver = {
.name = e1000_driver_name,
.id_table = e1000_pci_tbl,
.probe = e1000_probe,
.remove = e1000_remove,
-#ifdef CONFIG_PM
- /* Power Management Hooks */
- .suspend = e1000_suspend,
- .resume = e1000_resume,
-#endif
+ .driver = {
+ .pm = &e1000_pm_ops,
+ },
.shutdown = e1000_shutdown,
.err_handler = &e1000_err_handler
};
struct e1000_hw *hw = &adapter->hw;
u32 ctrl, ctrl_ext, rctl, status;
u32 wufc = adapter->wol;
-#ifdef CONFIG_PM
- int retval = 0;
-#endif
netif_device_detach(netdev);
e1000_down(adapter);
}
-#ifdef CONFIG_PM
- retval = pci_save_state(pdev);
- if (retval)
- return retval;
-#endif
-
status = er32(STATUS);
if (status & E1000_STATUS_LU)
wufc &= ~E1000_WUFC_LNKC;
return 0;
}
-#ifdef CONFIG_PM
-static int e1000_suspend(struct pci_dev *pdev, pm_message_t state)
+static int __maybe_unused e1000_suspend(struct device *dev)
{
int retval;
+ struct pci_dev *pdev = to_pci_dev(dev);
bool wake;
retval = __e1000_shutdown(pdev, &wake);
- if (retval)
- return retval;
-
- if (wake) {
- pci_prepare_to_sleep(pdev);
- } else {
- pci_wake_from_d3(pdev, false);
- pci_set_power_state(pdev, PCI_D3hot);
- }
+ device_set_wakeup_enable(dev, wake);
- return 0;
+ return retval;
}
-static int e1000_resume(struct pci_dev *pdev)
+static int __maybe_unused e1000_resume(struct device *dev)
{
+ struct pci_dev *pdev = to_pci_dev(dev);
struct net_device *netdev = pci_get_drvdata(pdev);
struct e1000_adapter *adapter = netdev_priv(netdev);
struct e1000_hw *hw = &adapter->hw;
u32 err;
- pci_set_power_state(pdev, PCI_D0);
- pci_restore_state(pdev);
- pci_save_state(pdev);
-
if (adapter->need_ioport)
err = pci_enable_device(pdev);
else
return 0;
}
-#endif
static void e1000_shutdown(struct pci_dev *pdev)
{
pm_runtime_put_sync(netdev->dev.parent);
}
-#ifdef CONFIG_PM_SLEEP
/* S0ix implementation */
static void e1000e_s0ix_entry_flow(struct e1000_adapter *adapter)
{
mac_data &= ~E1000_CTRL_EXT_FORCE_SMBUS;
ew32(CTRL_EXT, mac_data);
}
-#endif /* CONFIG_PM_SLEEP */
static int e1000e_pm_freeze(struct device *dev)
{
struct net_device *netdev = pci_get_drvdata(pdev);
struct e1000_adapter *adapter = netdev_priv(netdev);
struct e1000_hw *hw = &adapter->hw;
- u32 ctrl, ctrl_ext, rctl, status;
- /* Runtime suspend should only enable wakeup for link changes */
- u32 wufc = runtime ? E1000_WUFC_LNKC : adapter->wol;
+ u32 ctrl, ctrl_ext, rctl, status, wufc;
int retval = 0;
+ /* Runtime suspend should only enable wakeup for link changes */
+ if (runtime)
+ wufc = E1000_WUFC_LNKC;
+ else if (device_may_wakeup(&pdev->dev))
+ wufc = adapter->wol;
+ else
+ wufc = 0;
+
status = er32(STATUS);
if (status & E1000_STATUS_LU)
wufc &= ~E1000_WUFC_LNKC;
if (adapter->hw.phy.type == e1000_phy_igp_3) {
e1000e_igp3_phy_powerdown_workaround_ich8lan(&adapter->hw);
} else if (hw->mac.type >= e1000_pch_lpt) {
- if (!(wufc & (E1000_WUFC_EX | E1000_WUFC_MC | E1000_WUFC_BC)))
+ if (wufc && !(wufc & (E1000_WUFC_EX | E1000_WUFC_MC | E1000_WUFC_BC)))
/* ULP does not support wake from unicast, multicast
* or broadcast.
*/
return rc;
}
-#ifdef CONFIG_PM
static int __e1000_resume(struct pci_dev *pdev)
{
struct net_device *netdev = pci_get_drvdata(pdev);
return 0;
}
-#ifdef CONFIG_PM_SLEEP
-static int e1000e_pm_suspend(struct device *dev)
+static __maybe_unused int e1000e_pm_suspend(struct device *dev)
{
struct net_device *netdev = pci_get_drvdata(to_pci_dev(dev));
struct e1000_adapter *adapter = netdev_priv(netdev);
return rc;
}
-static int e1000e_pm_resume(struct device *dev)
+static __maybe_unused int e1000e_pm_resume(struct device *dev)
{
struct net_device *netdev = pci_get_drvdata(to_pci_dev(dev));
struct e1000_adapter *adapter = netdev_priv(netdev);
return e1000e_pm_thaw(dev);
}
-#endif /* CONFIG_PM_SLEEP */
-static int e1000e_pm_runtime_idle(struct device *dev)
+static __maybe_unused int e1000e_pm_runtime_idle(struct device *dev)
{
struct net_device *netdev = dev_get_drvdata(dev);
struct e1000_adapter *adapter = netdev_priv(netdev);
return -EBUSY;
}
-static int e1000e_pm_runtime_resume(struct device *dev)
+static __maybe_unused int e1000e_pm_runtime_resume(struct device *dev)
{
struct pci_dev *pdev = to_pci_dev(dev);
struct net_device *netdev = pci_get_drvdata(pdev);
return rc;
}
-static int e1000e_pm_runtime_suspend(struct device *dev)
+static __maybe_unused int e1000e_pm_runtime_suspend(struct device *dev)
{
struct pci_dev *pdev = to_pci_dev(dev);
struct net_device *netdev = pci_get_drvdata(pdev);
return 0;
}
-#endif /* CONFIG_PM */
static void e1000_shutdown(struct pci_dev *pdev)
{
for (q = 0; q < port->ntxqs; q++)
for (i = 0; i < ARRAY_SIZE(mvpp2_ethtool_txq_regs); i++)
*pstats++ += mvpp2_read_index(port->priv,
- MVPP22_CTRS_TX_CTR(port->id, i),
+ MVPP22_CTRS_TX_CTR(port->id, q),
mvpp2_ethtool_txq_regs[i].offset);
/* Rxqs are numbered from 0 from the user standpoint, but not from the
for (q = 0; q < port->nrxqs; q++)
for (i = 0; i < ARRAY_SIZE(mvpp2_ethtool_rxq_regs); i++)
*pstats++ += mvpp2_read_index(port->priv,
- port->first_rxq + i,
+ port->first_rxq + q,
mvpp2_ethtool_rxq_regs[i].offset);
}
{
struct mvpp2 *priv = platform_get_drvdata(pdev);
struct fwnode_handle *fwnode = pdev->dev.fwnode;
+ int i = 0, poolnum = MVPP2_BM_POOLS_NUM;
struct fwnode_handle *port_fwnode;
- int i = 0;
mvpp2_dbgfs_cleanup(priv);
destroy_workqueue(priv->stats_queue);
- for (i = 0; i < MVPP2_BM_POOLS_NUM; i++) {
+ if (priv->percpu_pools)
+ poolnum = mvpp2_get_nrxqs(priv) * 2;
+
+ for (i = 0; i < poolnum; i++) {
struct mvpp2_bm_pool *bm_pool = &priv->bm_pools[i];
mvpp2_bm_pool_destroy(&pdev->dev, priv, bm_pool);
#include <linux/regmap.h>
#include <linux/skbuff.h>
#include <linux/spinlock.h>
-#include <linux/workqueue.h>
#define MTK_STAR_DRVNAME "mtk_star_emac"
spinlock_t lock;
struct rtnl_link_stats64 stats;
- struct work_struct stats_work;
};
static struct device *mtk_star_get_dev(struct mtk_star_priv *priv)
regmap_write(priv->regs, MTK_STAR_REG_INT_MASK, ~0);
}
-static void mtk_star_intr_enable_tx(struct mtk_star_priv *priv)
-{
- regmap_clear_bits(priv->regs, MTK_STAR_REG_INT_MASK,
- MTK_STAR_BIT_INT_STS_TNTC);
-}
-
-static void mtk_star_intr_enable_rx(struct mtk_star_priv *priv)
-{
- regmap_clear_bits(priv->regs, MTK_STAR_REG_INT_MASK,
- MTK_STAR_BIT_INT_STS_FNRC);
-}
-
-static void mtk_star_intr_enable_stats(struct mtk_star_priv *priv)
-{
- regmap_clear_bits(priv->regs, MTK_STAR_REG_INT_MASK,
- MTK_STAR_REG_INT_STS_MIB_CNT_TH);
-}
-
-static void mtk_star_intr_disable_tx(struct mtk_star_priv *priv)
-{
- regmap_set_bits(priv->regs, MTK_STAR_REG_INT_MASK,
- MTK_STAR_BIT_INT_STS_TNTC);
-}
-
-static void mtk_star_intr_disable_rx(struct mtk_star_priv *priv)
-{
- regmap_set_bits(priv->regs, MTK_STAR_REG_INT_MASK,
- MTK_STAR_BIT_INT_STS_FNRC);
-}
-
-static void mtk_star_intr_disable_stats(struct mtk_star_priv *priv)
-{
- regmap_set_bits(priv->regs, MTK_STAR_REG_INT_MASK,
- MTK_STAR_REG_INT_STS_MIB_CNT_TH);
-}
-
static unsigned int mtk_star_intr_read(struct mtk_star_priv *priv)
{
unsigned int val;
stats->rx_errors += stats->rx_fifo_errors;
}
-/* This runs in process context and parallel TX and RX paths executing in
- * napi context may result in losing some stats data but this should happen
- * seldom enough to be acceptable.
- */
-static void mtk_star_update_stats_work(struct work_struct *work)
-{
- struct mtk_star_priv *priv = container_of(work, struct mtk_star_priv,
- stats_work);
-
- mtk_star_update_stats(priv);
- mtk_star_reset_counters(priv);
- mtk_star_intr_enable_stats(priv);
-}
-
static struct sk_buff *mtk_star_alloc_skb(struct net_device *ndev)
{
uintptr_t tail, offset;
mtk_star_ring_free_skbs(priv, ring, mtk_star_dma_unmap_tx);
}
-/* All processing for TX and RX happens in the napi poll callback. */
+/* All processing for TX and RX happens in the napi poll callback.
+ *
+ * FIXME: The interrupt handling should be more fine-grained with each
+ * interrupt enabled/disabled independently when needed. Unfortunatly this
+ * turned out to impact the driver's stability and until we have something
+ * working properly, we're disabling all interrupts during TX & RX processing
+ * or when resetting the counter registers.
+ */
static irqreturn_t mtk_star_handle_irq(int irq, void *data)
{
struct mtk_star_priv *priv;
struct net_device *ndev;
- bool need_napi = false;
- unsigned int status;
ndev = data;
priv = netdev_priv(ndev);
if (netif_running(ndev)) {
- status = mtk_star_intr_read(priv);
-
- if (status & MTK_STAR_BIT_INT_STS_TNTC) {
- mtk_star_intr_disable_tx(priv);
- need_napi = true;
- }
-
- if (status & MTK_STAR_BIT_INT_STS_FNRC) {
- mtk_star_intr_disable_rx(priv);
- need_napi = true;
- }
-
- if (need_napi)
- napi_schedule(&priv->napi);
-
- /* One of the counters reached 0x8000000 - update stats and
- * reset all counters.
- */
- if (unlikely(status & MTK_STAR_REG_INT_STS_MIB_CNT_TH)) {
- mtk_star_intr_disable_stats(priv);
- schedule_work(&priv->stats_work);
- }
-
- mtk_star_intr_ack_all(priv);
+ mtk_star_intr_disable(priv);
+ napi_schedule(&priv->napi);
}
return IRQ_HANDLED;
if (wake && netif_queue_stopped(ndev))
netif_wake_queue(ndev);
- mtk_star_intr_enable_tx(priv);
-
spin_unlock(&priv->lock);
}
static int mtk_star_poll(struct napi_struct *napi, int budget)
{
struct mtk_star_priv *priv;
+ unsigned int status;
int received = 0;
priv = container_of(napi, struct mtk_star_priv, napi);
- /* Clean-up all TX descriptors. */
- mtk_star_tx_complete_all(priv);
- /* Receive up to $budget packets. */
- received = mtk_star_process_rx(priv, budget);
+ status = mtk_star_intr_read(priv);
+ mtk_star_intr_ack_all(priv);
- if (received < budget) {
- napi_complete_done(napi, received);
- mtk_star_intr_enable_rx(priv);
+ if (status & MTK_STAR_BIT_INT_STS_TNTC)
+ /* Clean-up all TX descriptors. */
+ mtk_star_tx_complete_all(priv);
+
+ if (status & MTK_STAR_BIT_INT_STS_FNRC)
+ /* Receive up to $budget packets. */
+ received = mtk_star_process_rx(priv, budget);
+
+ if (unlikely(status & MTK_STAR_REG_INT_STS_MIB_CNT_TH)) {
+ mtk_star_update_stats(priv);
+ mtk_star_reset_counters(priv);
}
+ if (received < budget)
+ napi_complete_done(napi, received);
+
+ mtk_star_intr_enable(priv);
+
return received;
}
ndev->max_mtu = MTK_STAR_MAX_FRAME_SIZE;
spin_lock_init(&priv->lock);
- INIT_WORK(&priv->stats_work, mtk_star_update_stats_work);
base = devm_platform_ioremap_resource(pdev, 0);
if (IS_ERR(base))
lossy = !(pfc || pause_en);
thres_cells = mlxsw_sp_pg_buf_threshold_get(mlxsw_sp, mtu);
+ mlxsw_sp_port_headroom_8x_adjust(mlxsw_sp_port, &thres_cells);
delay_cells = mlxsw_sp_pg_buf_delay_get(mlxsw_sp, mtu, delay,
pfc, pause_en);
+ mlxsw_sp_port_headroom_8x_adjust(mlxsw_sp_port, &delay_cells);
total_cells = thres_cells + delay_cells;
taken_headroom_cells += total_cells;
return NULL;
}
+static inline void
+mlxsw_sp_port_headroom_8x_adjust(const struct mlxsw_sp_port *mlxsw_sp_port,
+ u16 *p_size)
+{
+ /* Ports with eight lanes use two headroom buffers between which the
+ * configured headroom size is split. Therefore, multiply the calculated
+ * headroom size by two.
+ */
+ if (mlxsw_sp_port->mapping.width != 8)
+ return;
+ *p_size *= 2;
+}
+
enum mlxsw_sp_flood_type {
MLXSW_SP_FLOOD_TYPE_UC,
MLXSW_SP_FLOOD_TYPE_BC,
if (i == MLXSW_SP_PB_UNUSED)
continue;
+ mlxsw_sp_port_headroom_8x_adjust(mlxsw_sp_port, &size);
mlxsw_reg_pbmc_lossy_buffer_pack(pbmc_pl, i, size);
}
mlxsw_reg_pbmc_lossy_buffer_pack(pbmc_pl,
speed = 0;
buffsize = mlxsw_sp_span_buffsize_get(mlxsw_sp, speed, mtu);
+ mlxsw_sp_port_headroom_8x_adjust(mlxsw_sp_port, (u16 *) &buffsize);
mlxsw_reg_sbib_pack(sbib_pl, mlxsw_sp_port->local_port, buffsize);
return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(sbib), sbib_pl);
}
{ 0, }
};
+MODULE_DEVICE_TABLE(pci, lan743x_pcidev_tbl);
+
static struct pci_driver lan743x_pcidev_driver = {
.name = DRIVER_NAME,
.id_table = lan743x_pcidev_tbl,
struct bin_attribute *attr, char *buf,
loff_t offset, size_t size)
{
- struct device *dev = container_of(kobj, struct device, kobj);
+ struct device *dev = kobj_to_dev(kobj);
struct qlcnic_adapter *adapter = dev_get_drvdata(dev);
int ret;
struct bin_attribute *attr, char *buf,
loff_t offset, size_t size)
{
- struct device *dev = container_of(kobj, struct device, kobj);
+ struct device *dev = kobj_to_dev(kobj);
struct qlcnic_adapter *adapter = dev_get_drvdata(dev);
int ret;
struct bin_attribute *attr, char *buf,
loff_t offset, size_t size)
{
- struct device *dev = container_of(kobj, struct device, kobj);
+ struct device *dev = kobj_to_dev(kobj);
struct qlcnic_adapter *adapter = dev_get_drvdata(dev);
u64 data;
int ret;
struct bin_attribute *attr, char *buf,
loff_t offset, size_t size)
{
- struct device *dev = container_of(kobj, struct device, kobj);
+ struct device *dev = kobj_to_dev(kobj);
struct qlcnic_adapter *adapter = dev_get_drvdata(dev);
u64 data;
int ret;
char *buf, loff_t offset,
size_t size)
{
- struct device *dev = container_of(kobj, struct device, kobj);
+ struct device *dev = kobj_to_dev(kobj);
struct qlcnic_adapter *adapter = dev_get_drvdata(dev);
struct qlcnic_pm_func_cfg *pm_cfg;
u32 id, action, pci_func;
char *buf, loff_t offset,
size_t size)
{
- struct device *dev = container_of(kobj, struct device, kobj);
+ struct device *dev = kobj_to_dev(kobj);
struct qlcnic_adapter *adapter = dev_get_drvdata(dev);
struct qlcnic_pm_func_cfg *pm_cfg;
u8 pci_func;
char *buf, loff_t offset,
size_t size)
{
- struct device *dev = container_of(kobj, struct device, kobj);
+ struct device *dev = kobj_to_dev(kobj);
struct qlcnic_adapter *adapter = dev_get_drvdata(dev);
struct qlcnic_esw_func_cfg *esw_cfg;
struct qlcnic_npar_info *npar;
char *buf, loff_t offset,
size_t size)
{
- struct device *dev = container_of(kobj, struct device, kobj);
+ struct device *dev = kobj_to_dev(kobj);
struct qlcnic_adapter *adapter = dev_get_drvdata(dev);
struct qlcnic_esw_func_cfg *esw_cfg;
u8 pci_func;
char *buf, loff_t offset,
size_t size)
{
- struct device *dev = container_of(kobj, struct device, kobj);
+ struct device *dev = kobj_to_dev(kobj);
struct qlcnic_adapter *adapter = dev_get_drvdata(dev);
struct qlcnic_info nic_info;
struct qlcnic_npar_func_cfg *np_cfg;
char *buf, loff_t offset,
size_t size)
{
- struct device *dev = container_of(kobj, struct device, kobj);
+ struct device *dev = kobj_to_dev(kobj);
struct qlcnic_adapter *adapter = dev_get_drvdata(dev);
struct qlcnic_npar_func_cfg *np_cfg;
struct qlcnic_info nic_info;
char *buf, loff_t offset,
size_t size)
{
- struct device *dev = container_of(kobj, struct device, kobj);
+ struct device *dev = kobj_to_dev(kobj);
struct qlcnic_adapter *adapter = dev_get_drvdata(dev);
struct qlcnic_esw_statistics port_stats;
int ret;
char *buf, loff_t offset,
size_t size)
{
- struct device *dev = container_of(kobj, struct device, kobj);
+ struct device *dev = kobj_to_dev(kobj);
struct qlcnic_adapter *adapter = dev_get_drvdata(dev);
struct qlcnic_esw_statistics esw_stats;
int ret;
char *buf, loff_t offset,
size_t size)
{
- struct device *dev = container_of(kobj, struct device, kobj);
+ struct device *dev = kobj_to_dev(kobj);
struct qlcnic_adapter *adapter = dev_get_drvdata(dev);
int ret;
size_t size)
{
- struct device *dev = container_of(kobj, struct device, kobj);
+ struct device *dev = kobj_to_dev(kobj);
struct qlcnic_adapter *adapter = dev_get_drvdata(dev);
int ret;
char *buf, loff_t offset,
size_t size)
{
- struct device *dev = container_of(kobj, struct device, kobj);
+ struct device *dev = kobj_to_dev(kobj);
struct qlcnic_adapter *adapter = dev_get_drvdata(dev);
struct qlcnic_pci_func_cfg *pci_cfg;
struct qlcnic_pci_info *pci_info;
{
unsigned char *p_read_buf;
int ret, count;
- struct device *dev = container_of(kobj, struct device, kobj);
+ struct device *dev = kobj_to_dev(kobj);
struct qlcnic_adapter *adapter = dev_get_drvdata(dev);
if (!size)
int ret;
static int flash_mode;
unsigned long data;
- struct device *dev = container_of(kobj, struct device, kobj);
+ struct device *dev = kobj_to_dev(kobj);
struct qlcnic_adapter *adapter = dev_get_drvdata(dev);
ret = kstrtoul(buf, 16, &data);
err_dma_event_ring_bufs_alloc:
rocker_dma_ring_destroy(rocker, &rocker->event_ring);
err_dma_event_ring_create:
+ rocker_dma_cmd_ring_waits_free(rocker);
+err_dma_cmd_ring_waits_alloc:
rocker_dma_ring_bufs_free(rocker, &rocker->cmd_ring,
PCI_DMA_BIDIRECTIONAL);
-err_dma_cmd_ring_waits_alloc:
- rocker_dma_cmd_ring_waits_free(rocker);
err_dma_cmd_ring_bufs_alloc:
rocker_dma_ring_destroy(rocker, &rocker->cmd_ring);
return err;
#define XAE_RAF_TXVSTRPMODE_MASK 0x00000180 /* Tx VLAN STRIP mode */
#define XAE_RAF_RXVSTRPMODE_MASK 0x00000600 /* Rx VLAN STRIP mode */
#define XAE_RAF_NEWFNCENBL_MASK 0x00000800 /* New function mode */
-/* Exteneded Multicast Filtering mode */
+/* Extended Multicast Filtering mode */
#define XAE_RAF_EMULTIFLTRENBL_MASK 0x00001000
#define XAE_RAF_STATSRST_MASK 0x00002000 /* Stats. Counter Reset */
#define XAE_RAF_RXBADFRMEN_MASK 0x00004000 /* Recv Bad Frame Enable */
struct op_sample {
unsigned long eip;
unsigned long event;
- unsigned long data[0];
+ unsigned long data[];
};
struct op_entry;
struct regmap *reg_pmu;
struct regmap *reg_sys;
spinlock_t lock;
- struct samsung_usb2_phy_instance instances[0];
+ struct samsung_usb2_phy_instance instances[];
};
struct samsung_usb2_common_phy {
u16 start; /* logical minimal id */
u32 max; /* max number of IDs in table */
spinlock_t lock;
- unsigned long table[0];
+ unsigned long table[];
};
static int next_destid = 0;
u32 link_ram_size0;
u32 link_ram_base1;
u32 __pad2[2];
- u32 starvation[0];
+ u32 starvation[];
};
struct knav_reg_region {
if (err)
return err;
- err = probe_kernel_read(&i, (unsigned char *)INTFBVADDR + DIO_IDOFF, 1);
+ err = copy_from_kernel_nofault(&i, (unsigned char *)INTFBVADDR + DIO_IDOFF, 1);
if (!err && (i == DIO_ID_FBUFFER) && topcat_sid_ok(sid = DIO_SECID(INTFBVADDR))) {
if (!request_mem_region(INTFBPADDR, DIO_DEVSIZE, "Internal Topcat"))
__u32 res;
} mst;
} id;
- __u8 data[0];
+ __u8 data[];
};
/**
__u8 cmd;
__u8 res;
__u16 len;
- __u8 data[0];
+ __u8 data[];
};
#ifdef __KERNEL__
vp = &op->file[0];
abort_code = vp->scb.status.abort_code;
if (abort_code != 0) {
- op->abort_code = abort_code;
+ op->ac.abort_code = abort_code;
op->error = afs_abort_to_error(abort_code);
}
break;
.success = afs_do_lookup_success,
};
-static const struct afs_operation_ops afs_fetch_status_operation = {
+static const struct afs_operation_ops afs_lookup_fetch_status_operation = {
.issue_afs_rpc = afs_fs_fetch_status,
.issue_yfs_rpc = yfs_fs_fetch_status,
.success = afs_do_lookup_success,
+ .aborted = afs_check_for_remote_deletion,
};
/*
_enter("%pd", dentry);
}
+void afs_check_for_remote_deletion(struct afs_operation *op)
+{
+ struct afs_vnode *vnode = op->file[0].vnode;
+
+ switch (op->ac.abort_code) {
+ case VNOVNODE:
+ set_bit(AFS_VNODE_DELETED, &vnode->flags);
+ afs_break_callback(vnode, afs_cb_break_for_deleted);
+ }
+}
+
/*
* Create a new inode for create/mkdir/symlink
*/
static void afs_create_success(struct afs_operation *op)
{
_enter("op=%08x", op->debug_id);
- afs_check_for_remote_deletion(op, op->file[0].vnode);
+ op->ctime = op->file[0].scb.status.mtime_client;
afs_vnode_commit_status(op, &op->file[0]);
afs_update_dentry_version(op, &op->file[0], op->dentry);
afs_vnode_new_inode(op);
.issue_afs_rpc = afs_fs_make_dir,
.issue_yfs_rpc = yfs_fs_make_dir,
.success = afs_create_success,
+ .aborted = afs_check_for_remote_deletion,
.edit_dir = afs_create_edit_dir,
.put = afs_create_put,
};
afs_op_set_vnode(op, 0, dvnode);
op->file[0].dv_delta = 1;
+ op->file[0].update_ctime = true;
op->dentry = dentry;
op->create.mode = S_IFDIR | mode;
op->create.reason = afs_edit_dir_for_mkdir;
static void afs_rmdir_success(struct afs_operation *op)
{
_enter("op=%08x", op->debug_id);
- afs_check_for_remote_deletion(op, op->file[0].vnode);
+ op->ctime = op->file[0].scb.status.mtime_client;
afs_vnode_commit_status(op, &op->file[0]);
afs_update_dentry_version(op, &op->file[0], op->dentry);
}
.issue_afs_rpc = afs_fs_remove_dir,
.issue_yfs_rpc = yfs_fs_remove_dir,
.success = afs_rmdir_success,
+ .aborted = afs_check_for_remote_deletion,
.edit_dir = afs_rmdir_edit_dir,
.put = afs_rmdir_put,
};
afs_op_set_vnode(op, 0, dvnode);
op->file[0].dv_delta = 1;
+ op->file[0].update_ctime = true;
op->dentry = dentry;
op->ops = &afs_rmdir_operation;
static void afs_unlink_success(struct afs_operation *op)
{
_enter("op=%08x", op->debug_id);
- afs_check_for_remote_deletion(op, op->file[0].vnode);
+ op->ctime = op->file[0].scb.status.mtime_client;
+ afs_check_dir_conflict(op, &op->file[0]);
afs_vnode_commit_status(op, &op->file[0]);
afs_vnode_commit_status(op, &op->file[1]);
afs_update_dentry_version(op, &op->file[0], op->dentry);
.issue_afs_rpc = afs_fs_remove_file,
.issue_yfs_rpc = yfs_fs_remove_file,
.success = afs_unlink_success,
+ .aborted = afs_check_for_remote_deletion,
.edit_dir = afs_unlink_edit_dir,
.put = afs_unlink_put,
};
afs_op_set_vnode(op, 0, dvnode);
op->file[0].dv_delta = 1;
+ op->file[0].update_ctime = true;
/* Try to make sure we have a callback promise on the victim. */
ret = afs_validate(vnode, op->key);
spin_unlock(&dentry->d_lock);
op->file[1].vnode = vnode;
+ op->file[1].update_ctime = true;
+ op->file[1].op_unlinked = true;
op->dentry = dentry;
op->ops = &afs_unlink_operation;
- return afs_do_sync_operation(op);
+ afs_begin_vnode_operation(op);
+ afs_wait_for_operation(op);
+
+ /* If there was a conflict with a third party, check the status of the
+ * unlinked vnode.
+ */
+ if (op->error == 0 && (op->flags & AFS_OPERATION_DIR_CONFLICT)) {
+ op->file[1].update_ctime = false;
+ op->fetch_status.which = 1;
+ op->ops = &afs_fetch_status_operation;
+ afs_begin_vnode_operation(op);
+ afs_wait_for_operation(op);
+ }
+
+ return afs_put_operation(op);
error:
return afs_put_operation(op);
.issue_afs_rpc = afs_fs_create_file,
.issue_yfs_rpc = yfs_fs_create_file,
.success = afs_create_success,
+ .aborted = afs_check_for_remote_deletion,
.edit_dir = afs_create_edit_dir,
.put = afs_create_put,
};
afs_op_set_vnode(op, 0, dvnode);
op->file[0].dv_delta = 1;
+ op->file[0].update_ctime = true;
op->dentry = dentry;
op->create.mode = S_IFREG | mode;
struct afs_vnode_param *vp = &op->file[1];
_enter("op=%08x", op->debug_id);
+ op->ctime = dvp->scb.status.mtime_client;
afs_vnode_commit_status(op, dvp);
afs_vnode_commit_status(op, vp);
afs_update_dentry_version(op, dvp, op->dentry);
.issue_afs_rpc = afs_fs_link,
.issue_yfs_rpc = yfs_fs_link,
.success = afs_link_success,
+ .aborted = afs_check_for_remote_deletion,
.edit_dir = afs_create_edit_dir,
.put = afs_link_put,
};
afs_op_set_vnode(op, 0, dvnode);
afs_op_set_vnode(op, 1, vnode);
op->file[0].dv_delta = 1;
+ op->file[0].update_ctime = true;
+ op->file[1].update_ctime = true;
op->dentry = dentry;
op->dentry_2 = from;
.issue_afs_rpc = afs_fs_symlink,
.issue_yfs_rpc = yfs_fs_symlink,
.success = afs_create_success,
+ .aborted = afs_check_for_remote_deletion,
.edit_dir = afs_create_edit_dir,
.put = afs_create_put,
};
{
_enter("op=%08x", op->debug_id);
+ op->ctime = op->file[0].scb.status.mtime_client;
+ afs_check_dir_conflict(op, &op->file[1]);
afs_vnode_commit_status(op, &op->file[0]);
- if (op->file[1].vnode != op->file[0].vnode)
+ if (op->file[1].vnode != op->file[0].vnode) {
+ op->ctime = op->file[1].scb.status.mtime_client;
afs_vnode_commit_status(op, &op->file[1]);
+ }
}
static void afs_rename_edit_dir(struct afs_operation *op)
afs_op_set_vnode(op, 1, new_dvnode); /* May be same as orig_dvnode */
op->file[0].dv_delta = 1;
op->file[1].dv_delta = 1;
+ op->file[0].update_ctime = true;
+ op->file[1].update_ctime = true;
op->dentry = old_dentry;
op->dentry_2 = new_dentry;
{
_enter("op=%08x", op->debug_id);
+ afs_check_dir_conflict(op, &op->file[0]);
afs_vnode_commit_status(op, &op->file[0]);
}
return PTR_ERR(op);
afs_op_set_vnode(op, 0, dvnode);
+ afs_op_set_vnode(op, 1, dvnode);
+ op->file[0].dv_delta = 1;
+ op->file[1].dv_delta = 1;
+ op->file[0].update_ctime = true;
+ op->file[1].update_ctime = true;
op->dentry = old;
op->dentry_2 = new;
switch (ret) {
case 0:
/* The rename succeeded. */
+ set_bit(AFS_VNODE_SILLY_DELETED, &vnode->flags);
d_move(dentry, sdentry);
break;
case -ERESTARTSYS:
static void afs_silly_unlink_success(struct afs_operation *op)
{
- struct afs_vnode *vnode = op->file[1].vnode;
-
_enter("op=%08x", op->debug_id);
- afs_check_for_remote_deletion(op, op->file[0].vnode);
+ afs_check_dir_conflict(op, &op->file[0]);
afs_vnode_commit_status(op, &op->file[0]);
afs_vnode_commit_status(op, &op->file[1]);
afs_update_dentry_version(op, &op->file[0], op->dentry);
-
- drop_nlink(&vnode->vfs_inode);
- if (vnode->vfs_inode.i_nlink == 0) {
- set_bit(AFS_VNODE_DELETED, &vnode->flags);
- clear_bit(AFS_VNODE_CB_PROMISED, &vnode->flags);
- }
}
static void afs_silly_unlink_edit_dir(struct afs_operation *op)
.issue_afs_rpc = afs_fs_remove_file,
.issue_yfs_rpc = yfs_fs_remove_file,
.success = afs_silly_unlink_success,
+ .aborted = afs_check_for_remote_deletion,
.edit_dir = afs_silly_unlink_edit_dir,
};
afs_op_set_vnode(op, 0, dvnode);
afs_op_set_vnode(op, 1, vnode);
+ op->file[0].dv_delta = 1;
+ op->file[0].update_ctime = true;
+ op->file[1].op_unlinked = true;
+ op->file[1].update_ctime = true;
op->dentry = dentry;
op->ops = &afs_silly_unlink_operation;
trace_afs_silly_rename(vnode, true);
- return afs_do_sync_operation(op);
+ afs_begin_vnode_operation(op);
+ afs_wait_for_operation(op);
+
+ /* If there was a conflict with a third party, check the status of the
+ * unlinked vnode.
+ */
+ if (op->error == 0 && (op->flags & AFS_OPERATION_DIR_CONFLICT)) {
+ op->file[1].update_ctime = false;
+ op->fetch_status.which = 1;
+ op->ops = &afs_fetch_status_operation;
+ afs_begin_vnode_operation(op);
+ afs_wait_for_operation(op);
+ }
+
+ return afs_put_operation(op);
}
/*
struct afs_vnode *vnode = op->file[0].vnode;
_enter("op=%08x", op->debug_id);
- afs_check_for_remote_deletion(op, vnode);
afs_vnode_commit_status(op, &op->file[0]);
afs_stat_v(vnode, n_fetches);
atomic_long_add(op->fetch.req->actual_len, &op->net->n_fetch_bytes);
.issue_afs_rpc = afs_fs_fetch_data,
.issue_yfs_rpc = yfs_fs_fetch_data,
.success = afs_fetch_data_success,
+ .aborted = afs_check_for_remote_deletion,
.put = afs_fetch_data_put,
};
static void afs_lock_success(struct afs_operation *op)
{
- struct afs_vnode *vnode = op->file[0].vnode;
-
_enter("op=%08x", op->debug_id);
- afs_check_for_remote_deletion(op, vnode);
afs_vnode_commit_status(op, &op->file[0]);
}
.issue_afs_rpc = afs_fs_set_lock,
.issue_yfs_rpc = yfs_fs_set_lock,
.success = afs_lock_success,
+ .aborted = afs_check_for_remote_deletion,
};
/*
op->error = afs_wait_for_call_to_complete(op->call, &op->ac);
}
- if (op->error == 0) {
+ switch (op->error) {
+ case 0:
_debug("success");
op->ops->success(op);
+ break;
+ case -ECONNABORTED:
+ if (op->ops->aborted)
+ op->ops->aborted(op);
+ break;
+ default:
+ break;
}
afs_end_vnode_operation(op);
{
struct afs_file_status *status = &vp->scb.status;
struct afs_vnode *vnode = vp->vnode;
+ struct inode *inode = &vnode->vfs_inode;
struct timespec64 t;
umode_t mode;
bool data_changed = false;
+ bool change_size = vp->set_size;
_enter("{%llx:%llu.%u} %s",
vp->fid.vid, vp->fid.vnode, vp->fid.unique,
}
if (status->nlink != vnode->status.nlink)
- set_nlink(&vnode->vfs_inode, status->nlink);
+ set_nlink(inode, status->nlink);
if (status->owner != vnode->status.owner)
- vnode->vfs_inode.i_uid = make_kuid(&init_user_ns, status->owner);
+ inode->i_uid = make_kuid(&init_user_ns, status->owner);
if (status->group != vnode->status.group)
- vnode->vfs_inode.i_gid = make_kgid(&init_user_ns, status->group);
+ inode->i_gid = make_kgid(&init_user_ns, status->group);
if (status->mode != vnode->status.mode) {
- mode = vnode->vfs_inode.i_mode;
+ mode = inode->i_mode;
mode &= ~S_IALLUGO;
mode |= status->mode;
- WRITE_ONCE(vnode->vfs_inode.i_mode, mode);
+ WRITE_ONCE(inode->i_mode, mode);
}
t = status->mtime_client;
- vnode->vfs_inode.i_ctime = t;
- vnode->vfs_inode.i_mtime = t;
- vnode->vfs_inode.i_atime = t;
+ inode->i_mtime = t;
+ if (vp->update_ctime)
+ inode->i_ctime = op->ctime;
if (vnode->status.data_version != status->data_version)
data_changed = true;
} else {
set_bit(AFS_VNODE_ZAP_DATA, &vnode->flags);
}
+ change_size = true;
} else if (vnode->status.type == AFS_FTYPE_DIR) {
/* Expected directory change is handled elsewhere so
* that we can locally edit the directory and save on a
*/
if (test_bit(AFS_VNODE_DIR_VALID, &vnode->flags))
data_changed = false;
+ change_size = true;
}
if (data_changed) {
- inode_set_iversion_raw(&vnode->vfs_inode, status->data_version);
- afs_set_i_size(vnode, status->size);
+ inode_set_iversion_raw(inode, status->data_version);
+
+ /* Only update the size if the data version jumped. If the
+ * file is being modified locally, then we might have our own
+ * idea of what the size should be that's not the same as
+ * what's on the server.
+ */
+ if (change_size) {
+ afs_set_i_size(vnode, status->size);
+ inode->i_ctime = t;
+ inode->i_atime = t;
+ }
}
}
_enter("");
- ASSERTCMP(op->error, ==, 0);
-
write_seqlock(&vnode->cb_lock);
if (vp->scb.have_error) {
+ /* A YFS server will return this from RemoveFile2 and AFS and
+ * YFS will return this from InlineBulkStatus.
+ */
if (vp->scb.status.abort_code == VNOVNODE) {
set_bit(AFS_VNODE_DELETED, &vnode->flags);
clear_nlink(&vnode->vfs_inode);
__afs_break_callback(vnode, afs_cb_break_for_deleted);
+ op->flags &= ~AFS_OPERATION_DIR_CONFLICT;
}
- } else {
- if (vp->scb.have_status)
- afs_apply_status(op, vp);
+ } else if (vp->scb.have_status) {
+ afs_apply_status(op, vp);
if (vp->scb.have_cb)
afs_apply_callback(op, vp);
+ } else if (vp->op_unlinked && !(op->flags & AFS_OPERATION_DIR_CONFLICT)) {
+ drop_nlink(&vnode->vfs_inode);
+ if (vnode->vfs_inode.i_nlink == 0) {
+ set_bit(AFS_VNODE_DELETED, &vnode->flags);
+ __afs_break_callback(vnode, afs_cb_break_for_deleted);
+ }
}
write_sequnlock(&vnode->cb_lock);
- if (op->error == 0 && vp->scb.have_status)
+ if (vp->scb.have_status)
afs_cache_permit(vnode, op->key, vp->cb_break_before, &vp->scb);
}
static void afs_fetch_status_success(struct afs_operation *op)
{
- struct afs_vnode_param *vp = &op->file[0];
+ struct afs_vnode_param *vp = &op->file[op->fetch_status.which];
struct afs_vnode *vnode = vp->vnode;
int ret;
}
}
-static const struct afs_operation_ops afs_fetch_status_operation = {
+const struct afs_operation_ops afs_fetch_status_operation = {
.issue_afs_rpc = afs_fs_fetch_status,
.issue_yfs_rpc = yfs_fs_fetch_status,
.success = afs_fetch_status_success,
+ .aborted = afs_check_for_remote_deletion,
};
/*
do {
read_seqbegin_or_lock(&vnode->cb_lock, &seq);
generic_fillattr(inode, stat);
+ if (test_bit(AFS_VNODE_SILLY_DELETED, &vnode->flags) &&
+ stat->nlink > 0)
+ stat->nlink -= 1;
} while (need_seqretry(&vnode->cb_lock, seq));
done_seqretry(&vnode->cb_lock, seq);
static void afs_setattr_success(struct afs_operation *op)
{
+ struct inode *inode = &op->file[0].vnode->vfs_inode;
+
afs_vnode_commit_status(op, &op->file[0]);
+ if (op->setattr.attr->ia_valid & ATTR_SIZE) {
+ loff_t i_size = inode->i_size, size = op->setattr.attr->ia_size;
+ if (size > i_size)
+ pagecache_isize_extended(inode, i_size, size);
+ truncate_pagecache(inode, size);
+ }
}
static const struct afs_operation_ops afs_setattr_operation = {
{
struct afs_operation *op;
struct afs_vnode *vnode = AFS_FS_I(d_inode(dentry));
+ int ret;
_enter("{%llx:%llu},{n=%pd},%x",
vnode->fid.vid, vnode->fid.vnode, dentry,
attr->ia_valid);
if (!(attr->ia_valid & (ATTR_SIZE | ATTR_MODE | ATTR_UID | ATTR_GID |
- ATTR_MTIME))) {
+ ATTR_MTIME | ATTR_MTIME_SET | ATTR_TIMES_SET |
+ ATTR_TOUCH))) {
_leave(" = 0 [unsupported]");
return 0;
}
+ if (attr->ia_valid & ATTR_SIZE) {
+ if (!S_ISREG(vnode->vfs_inode.i_mode))
+ return -EISDIR;
+
+ ret = inode_newsize_ok(&vnode->vfs_inode, attr->ia_size);
+ if (ret)
+ return ret;
+
+ if (attr->ia_size == i_size_read(&vnode->vfs_inode))
+ attr->ia_valid &= ~ATTR_SIZE;
+ }
+
/* flush any dirty data outstanding on a regular file */
if (S_ISREG(vnode->vfs_inode.i_mode))
filemap_write_and_wait(vnode->vfs_inode.i_mapping);
afs_op_set_vnode(op, 0, vnode);
op->setattr.attr = attr;
- if (attr->ia_valid & ATTR_SIZE)
+ if (attr->ia_valid & ATTR_SIZE) {
op->file[0].dv_delta = 1;
+ op->file[0].set_size = true;
+ }
+ op->ctime = attr->ia_ctime;
+ op->file[0].update_ctime = 1;
op->ops = &afs_setattr_operation;
return afs_do_sync_operation(op);
#define AFS_VNODE_AUTOCELL 6 /* set if Vnode is an auto mount point */
#define AFS_VNODE_PSEUDODIR 7 /* set if Vnode is a pseudo directory */
#define AFS_VNODE_NEW_CONTENT 8 /* Set if file has new content (create/trunc-0) */
+#define AFS_VNODE_SILLY_DELETED 9 /* Set if file has been silly-deleted */
struct list_head wb_keys; /* List of keys available for writeback */
struct list_head pending_locks; /* locks waiting to be granted */
afs_dataversion_t dv_before; /* Data version before the call */
unsigned int cb_break_before; /* cb_break + cb_s_break before the call */
u8 dv_delta; /* Expected change in data version */
- bool put_vnode; /* T if we have a ref on the vnode */
- bool need_io_lock; /* T if we need the I/O lock on this */
+ bool put_vnode:1; /* T if we have a ref on the vnode */
+ bool need_io_lock:1; /* T if we need the I/O lock on this */
+ bool update_ctime:1; /* Need to update the ctime */
+ bool set_size:1; /* Must update i_size */
+ bool op_unlinked:1; /* True if file was unlinked by op */
};
/*
struct dentry *dentry; /* Dentry to be altered */
struct dentry *dentry_2; /* Second dentry to be altered */
struct timespec64 mtime; /* Modification time to record */
+ struct timespec64 ctime; /* Change time to set */
short nr_files; /* Number of entries in file[], more_files */
short error;
- unsigned int abort_code;
unsigned int debug_id;
unsigned int cb_v_break; /* Volume break counter before op */
#define AFS_OPERATION_LOCK_1 0x0200 /* Set if have io_lock on file[1] */
#define AFS_OPERATION_TRIED_ALL 0x0400 /* Set if we've tried all the fileservers */
#define AFS_OPERATION_RETRY_SERVER 0x0800 /* Set if we should retry the current server */
+#define AFS_OPERATION_DIR_CONFLICT 0x1000 /* Set if we detected a 3rd-party dir change */
};
/*
extern const struct dentry_operations afs_fs_dentry_operations;
extern void afs_d_release(struct dentry *);
+extern void afs_check_for_remote_deletion(struct afs_operation *);
/*
* dir_edit.c
/*
* inode.c
*/
+extern const struct afs_operation_ops afs_fetch_status_operation;
+
extern void afs_vnode_commit_status(struct afs_operation *, struct afs_vnode_param *);
extern int afs_fetch_status(struct afs_vnode *, struct key *, bool, afs_access_t *);
extern int afs_ilookup5_test_by_fid(struct inode *, void *);
/*
* yfsclient.c
*/
-extern void yfs_fs_fetch_file_status(struct afs_operation *);
extern void yfs_fs_fetch_data(struct afs_operation *);
extern void yfs_fs_create_file(struct afs_operation *);
extern void yfs_fs_make_dir(struct afs_operation *);
return &vnode->vfs_inode;
}
-static inline void afs_check_for_remote_deletion(struct afs_operation *op,
- struct afs_vnode *vnode)
-{
- if (op->error == -ENOENT) {
- set_bit(AFS_VNODE_DELETED, &vnode->flags);
- afs_break_callback(vnode, afs_cb_break_for_deleted);
- }
-}
-
/*
* Note that a dentry got changed. We need to set d_fsdata to the data version
* number derived from the result of the operation. It doesn't matter if
(void *)(unsigned long)dir_vp->scb.status.data_version;
}
+/*
+ * Check for a conflicting operation on a directory that we just unlinked from.
+ * If someone managed to sneak a link or an unlink in on the file we just
+ * unlinked, we won't be able to trust nlink on an AFS file (but not YFS).
+ */
+static inline void afs_check_dir_conflict(struct afs_operation *op,
+ struct afs_vnode_param *dvp)
+{
+ if (dvp->dv_before + dvp->dv_delta != dvp->scb.status.data_version)
+ op->flags |= AFS_OPERATION_DIR_CONFLICT;
+}
+
static inline int afs_io_error(struct afs_call *call, enum afs_io_error where)
{
trace_afs_io_error(call->debug_id, -EIO, where);
case UAENOLCK: return -ENOLCK;
case UAENOTEMPTY: return -ENOTEMPTY;
case UAELOOP: return -ELOOP;
+ case UAEOVERFLOW: return -EOVERFLOW;
case UAENOMEDIUM: return -ENOMEDIUM;
case UAEDQUOT: return -EDQUOT;
i_size = i_size_read(&vnode->vfs_inode);
if (maybe_i_size > i_size) {
- spin_lock(&vnode->wb_lock);
+ write_seqlock(&vnode->cb_lock);
i_size = i_size_read(&vnode->vfs_inode);
if (maybe_i_size > i_size)
i_size_write(&vnode->vfs_inode, maybe_i_size);
- spin_unlock(&vnode->wb_lock);
+ write_sequnlock(&vnode->cb_lock);
}
if (!PageUptodate(page)) {
{
struct afs_vnode *vnode = op->file[0].vnode;
+ op->ctime = op->file[0].scb.status.mtime_client;
afs_vnode_commit_status(op, &op->file[0]);
if (op->error == 0) {
afs_pages_written_back(vnode, op->store.first, op->store.last);
unsigned long count, priv;
unsigned n, offset, to, f, t;
pgoff_t start, first, last;
+ loff_t i_size, end;
int loop, ret;
_enter(",%lx", primary_page->index);
first = primary_page->index;
last = first + count - 1;
+ end = (loff_t)last * PAGE_SIZE + to;
+ i_size = i_size_read(&vnode->vfs_inode);
+
_debug("write back %lx[%u..] to %lx[..%u]", first, offset, last, to);
+ if (end > i_size)
+ to = i_size & ~PAGE_MASK;
ret = afs_store_data(mapping, first, last, offset, to);
switch (ret) {
vmf->page->index, priv);
SetPagePrivate(vmf->page);
set_page_private(vmf->page, priv);
+ file_update_time(file);
sb_end_pagefault(inode->i_sb);
return VM_FAULT_LOCKED;
*_bp += sizeof(*x) / sizeof(__be32);
}
-/*
- * Deliver a reply that's a status, callback and volsync.
- */
-static int yfs_deliver_fs_status_cb_and_volsync(struct afs_call *call)
-{
- struct afs_operation *op = call->op;
- const __be32 *bp;
- int ret;
-
- ret = afs_transfer_reply(call);
- if (ret < 0)
- return ret;
-
- /* unmarshall the reply once we've received all of it */
- bp = call->buffer;
- xdr_decode_YFSFetchStatus(&bp, call, &op->file[0].scb);
- xdr_decode_YFSCallBack(&bp, call, &op->file[0].scb);
- xdr_decode_YFSVolSync(&bp, &op->volsync);
-
- _leave(" = 0 [done]");
- return 0;
-}
-
/*
* Deliver reply data to operations that just return a file status and a volume
* sync record.
return 0;
}
-/*
- * YFS.FetchStatus operation type
- */
-static const struct afs_call_type yfs_RXYFSFetchStatus_vnode = {
- .name = "YFS.FetchStatus(vnode)",
- .op = yfs_FS_FetchStatus,
- .deliver = yfs_deliver_fs_status_cb_and_volsync,
- .destructor = afs_flat_call_destructor,
-};
-
-/*
- * Fetch the status information for a file.
- */
-void yfs_fs_fetch_file_status(struct afs_operation *op)
-{
- struct afs_vnode_param *vp = &op->file[0];
- struct afs_call *call;
- __be32 *bp;
-
- _enter(",%x,{%llx:%llu},,",
- key_serial(op->key), vp->fid.vid, vp->fid.vnode);
-
- call = afs_alloc_flat_call(op->net, &yfs_RXYFSFetchStatus_vnode,
- sizeof(__be32) * 2 +
- sizeof(struct yfs_xdr_YFSFid),
- sizeof(struct yfs_xdr_YFSFetchStatus) +
- sizeof(struct yfs_xdr_YFSCallBack) +
- sizeof(struct yfs_xdr_YFSVolSync));
- if (!call)
- return afs_op_nomem(op);
-
- /* marshall the parameters */
- bp = call->request;
- bp = xdr_encode_u32(bp, YFSFETCHSTATUS);
- bp = xdr_encode_u32(bp, 0); /* RPC flags */
- bp = xdr_encode_YFSFid(bp, &vp->fid);
- yfs_check_req(call, bp);
-
- trace_afs_make_fs_call(call, &vp->fid);
- afs_make_op_call(op, call, GFP_NOFS);
-}
-
/*
* Deliver reply data to an YFS.FetchData64.
*/
afs_make_op_call(op, call, GFP_NOFS);
}
+/*
+ * Deliver a reply to YFS.FetchStatus
+ */
+static int yfs_deliver_fs_fetch_status(struct afs_call *call)
+{
+ struct afs_operation *op = call->op;
+ struct afs_vnode_param *vp = &op->file[op->fetch_status.which];
+ const __be32 *bp;
+ int ret;
+
+ ret = afs_transfer_reply(call);
+ if (ret < 0)
+ return ret;
+
+ /* unmarshall the reply once we've received all of it */
+ bp = call->buffer;
+ xdr_decode_YFSFetchStatus(&bp, call, &vp->scb);
+ xdr_decode_YFSCallBack(&bp, call, &vp->scb);
+ xdr_decode_YFSVolSync(&bp, &op->volsync);
+
+ _leave(" = 0 [done]");
+ return 0;
+}
+
/*
* YFS.FetchStatus operation type
*/
static const struct afs_call_type yfs_RXYFSFetchStatus = {
.name = "YFS.FetchStatus",
.op = yfs_FS_FetchStatus,
- .deliver = yfs_deliver_fs_status_cb_and_volsync,
+ .deliver = yfs_deliver_fs_fetch_status,
.destructor = afs_flat_call_destructor,
};
*/
void yfs_fs_fetch_status(struct afs_operation *op)
{
- struct afs_vnode_param *vp = &op->file[0];
+ struct afs_vnode_param *vp = &op->file[op->fetch_status.which];
struct afs_call *call;
__be32 *bp;
unsigned header_length; /* size of aio_ring */
- struct io_event io_events[0];
+ struct io_event io_events[];
}; /* 128 bytes + ring size */
/*
extents_status.o file.o fsmap.o fsync.o hash.o ialloc.o \
indirect.o inline.o inode.o ioctl.o mballoc.o migrate.o \
mmp.o move_extent.o namei.o page-io.o readpage.o resize.o \
- super.o symlink.o sysfs.o xattr.o xattr_trusted.o xattr_user.o
+ super.o symlink.o sysfs.o xattr.o xattr_hurd.o xattr_trusted.o \
+ xattr_user.o
ext4-$(CONFIG_EXT4_FS_POSIX_ACL) += acl.o
ext4-$(CONFIG_EXT4_FS_SECURITY) += xattr_security.o
struct qstr qstr = {.name = str, .len = len };
const struct dentry *parent = READ_ONCE(dentry->d_parent);
const struct inode *inode = READ_ONCE(parent->d_inode);
+ char strbuf[DNAME_INLINE_LEN];
if (!inode || !IS_CASEFOLDED(inode) ||
!EXT4_SB(inode->i_sb)->s_encoding) {
return memcmp(str, name->name, len);
}
+ /*
+ * If the dentry name is stored in-line, then it may be concurrently
+ * modified by a rename. If this happens, the VFS will eventually retry
+ * the lookup, so it doesn't matter what ->d_compare() returns.
+ * However, it's unsafe to call utf8_strncasecmp() with an unstable
+ * string. Therefore, we have to copy the name into a temporary buffer.
+ */
+ if (len <= DNAME_INLINE_LEN - 1) {
+ memcpy(strbuf, str, len);
+ strbuf[len] = 0;
+ qstr.name = strbuf;
+ /* prevent compiler from optimizing out the temporary buffer */
+ barrier();
+ }
+
return ext4_ci_compare(inode, name, &qstr, false);
}
#define EXT4_VERITY_FL 0x00100000 /* Verity protected inode */
#define EXT4_EA_INODE_FL 0x00200000 /* Inode used for large EA */
/* 0x00400000 was formerly EXT4_EOFBLOCKS_FL */
+
+#define EXT4_DAX_FL 0x02000000 /* Inode is DAX */
+
#define EXT4_INLINE_DATA_FL 0x10000000 /* Inode has inline data. */
#define EXT4_PROJINHERIT_FL 0x20000000 /* Create with parents projid */
#define EXT4_CASEFOLD_FL 0x40000000 /* Casefolded directory */
#define EXT4_RESERVED_FL 0x80000000 /* reserved for ext4 lib */
-#define EXT4_FL_USER_VISIBLE 0x705BDFFF /* User visible flags */
-#define EXT4_FL_USER_MODIFIABLE 0x604BC0FF /* User modifiable flags */
+#define EXT4_FL_USER_VISIBLE 0x725BDFFF /* User visible flags */
+#define EXT4_FL_USER_MODIFIABLE 0x624BC0FF /* User modifiable flags */
/* Flags we can manipulate with through EXT4_IOC_FSSETXATTR */
#define EXT4_FL_XFLAG_VISIBLE (EXT4_SYNC_FL | \
EXT4_APPEND_FL | \
EXT4_NODUMP_FL | \
EXT4_NOATIME_FL | \
- EXT4_PROJINHERIT_FL)
+ EXT4_PROJINHERIT_FL | \
+ EXT4_DAX_FL)
/* Flags that should be inherited by new inodes from their parent. */
#define EXT4_FL_INHERITED (EXT4_SECRM_FL | EXT4_UNRM_FL | EXT4_COMPR_FL |\
EXT4_SYNC_FL | EXT4_NODUMP_FL | EXT4_NOATIME_FL |\
EXT4_NOCOMPR_FL | EXT4_JOURNAL_DATA_FL |\
EXT4_NOTAIL_FL | EXT4_DIRSYNC_FL |\
- EXT4_PROJINHERIT_FL | EXT4_CASEFOLD_FL)
+ EXT4_PROJINHERIT_FL | EXT4_CASEFOLD_FL |\
+ EXT4_DAX_FL)
/* Flags that are appropriate for regular files (all but dir-specific ones). */
#define EXT4_REG_FLMASK (~(EXT4_DIRSYNC_FL | EXT4_TOPDIR_FL | EXT4_CASEFOLD_FL |\
/* The only flags that should be swapped */
#define EXT4_FL_SHOULD_SWAP (EXT4_HUGE_FILE_FL | EXT4_EXTENTS_FL)
+/* Flags which are mutually exclusive to DAX */
+#define EXT4_DAX_MUT_EXCL (EXT4_VERITY_FL | EXT4_ENCRYPT_FL |\
+ EXT4_JOURNAL_DATA_FL)
+
/* Mask out flags that are inappropriate for the given type of inode. */
static inline __u32 ext4_mask_flags(umode_t mode, __u32 flags)
{
EXT4_INODE_VERITY = 20, /* Verity protected inode */
EXT4_INODE_EA_INODE = 21, /* Inode used for large EA */
/* 22 was formerly EXT4_INODE_EOFBLOCKS */
+ EXT4_INODE_DAX = 25, /* Inode is DAX */
EXT4_INODE_INLINE_DATA = 28, /* Data in inode. */
EXT4_INODE_PROJINHERIT = 29, /* Create with parents projid */
EXT4_INODE_CASEFOLD = 30, /* Casefolded directory */
#define EXT4_MOUNT_MINIX_DF 0x00080 /* Mimics the Minix statfs */
#define EXT4_MOUNT_NOLOAD 0x00100 /* Don't use existing journal*/
#ifdef CONFIG_FS_DAX
-#define EXT4_MOUNT_DAX 0x00200 /* Direct Access */
+#define EXT4_MOUNT_DAX_ALWAYS 0x00200 /* Direct Access */
#else
-#define EXT4_MOUNT_DAX 0
+#define EXT4_MOUNT_DAX_ALWAYS 0
#endif
#define EXT4_MOUNT_DATA_FLAGS 0x00C00 /* Mode for data writes: */
#define EXT4_MOUNT_JOURNAL_DATA 0x00400 /* Write data to journal */
blocks */
#define EXT4_MOUNT2_HURD_COMPAT 0x00000004 /* Support HURD-castrated
file systems */
+#define EXT4_MOUNT2_DAX_NEVER 0x00000008 /* Do not allow Direct Access */
+#define EXT4_MOUNT2_DAX_INODE 0x00000010 /* For printing options only */
#define EXT4_MOUNT2_EXPLICIT_JOURNAL_CHECKSUM 0x00000008 /* User explicitly
specified journal checksum */
*/
#define EXT4_FLAGS_RESIZING 0
#define EXT4_FLAGS_SHUTDOWN 1
+#define EXT4_FLAGS_BDEV_IS_DAX 2
static inline int ext4_forced_shutdown(struct ext4_sb_info *sbi)
{
extern int ext4_truncate(struct inode *);
extern int ext4_break_layouts(struct inode *);
extern int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length);
-extern void ext4_set_inode_flags(struct inode *);
+extern void ext4_set_inode_flags(struct inode *, bool init);
extern int ext4_alloc_da_blocks(struct inode *inode);
extern void ext4_set_aops(struct inode *inode);
extern int ext4_writepage_trans_blocks(struct inode *);
* in use to avoid freeing it when removing blocks.
*/
if (sbi->s_cluster_ratio > 1) {
- pblk = ext4_ext_pblock(ex) + end - ee_block + 2;
+ pblk = ext4_ext_pblock(ex) + end - ee_block + 1;
partial.pclu = EXT4_B2C(sbi, pblk);
partial.state = nofree;
}
ei->i_block_group = group;
ei->i_last_alloc_group = ~0;
- ext4_set_inode_flags(inode);
+ ext4_set_inode_flags(inode, true);
if (IS_DIRSYNC(inode))
ext4_handle_sync(handle);
if (insert_inode_locked(inode) < 0) {
!ext4_test_inode_state(inode, EXT4_STATE_XATTR));
}
-static bool ext4_should_use_dax(struct inode *inode)
+static bool ext4_should_enable_dax(struct inode *inode)
{
- if (!test_opt(inode->i_sb, DAX))
+ struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
+
+ if (test_opt2(inode->i_sb, DAX_NEVER))
return false;
if (!S_ISREG(inode->i_mode))
return false;
return false;
if (ext4_test_inode_flag(inode, EXT4_INODE_VERITY))
return false;
- return true;
+ if (!test_bit(EXT4_FLAGS_BDEV_IS_DAX, &sbi->s_ext4_flags))
+ return false;
+ if (test_opt(inode->i_sb, DAX_ALWAYS))
+ return true;
+
+ return ext4_test_inode_flag(inode, EXT4_INODE_DAX);
}
-void ext4_set_inode_flags(struct inode *inode)
+void ext4_set_inode_flags(struct inode *inode, bool init)
{
unsigned int flags = EXT4_I(inode)->i_flags;
unsigned int new_fl = 0;
+ WARN_ON_ONCE(IS_DAX(inode) && init);
+
if (flags & EXT4_SYNC_FL)
new_fl |= S_SYNC;
if (flags & EXT4_APPEND_FL)
new_fl |= S_NOATIME;
if (flags & EXT4_DIRSYNC_FL)
new_fl |= S_DIRSYNC;
- if (ext4_should_use_dax(inode))
+
+ /* Because of the way inode_set_flags() works we must preserve S_DAX
+ * here if already set. */
+ new_fl |= (inode->i_flags & S_DAX);
+ if (init && ext4_should_enable_dax(inode))
new_fl |= S_DAX;
+
if (flags & EXT4_ENCRYPT_FL)
new_fl |= S_ENCRYPTED;
if (flags & EXT4_CASEFOLD_FL)
* not initialized on a new filesystem. */
}
ei->i_flags = le32_to_cpu(raw_inode->i_flags);
- ext4_set_inode_flags(inode);
+ ext4_set_inode_flags(inode, true);
inode->i_blocks = ext4_inode_blocks(raw_inode, ei);
ei->i_file_acl = le32_to_cpu(raw_inode->i_file_acl_lo);
if (ext4_has_feature_64bit(sb))
return 0;
}
+static void ext4_dax_dontcache(struct inode *inode, unsigned int flags)
+{
+ struct ext4_inode_info *ei = EXT4_I(inode);
+
+ if (S_ISDIR(inode->i_mode))
+ return;
+
+ if (test_opt2(inode->i_sb, DAX_NEVER) ||
+ test_opt(inode->i_sb, DAX_ALWAYS))
+ return;
+
+ if ((ei->i_flags ^ flags) & EXT4_DAX_FL)
+ d_mark_dontcache(inode);
+}
+
+static bool dax_compatible(struct inode *inode, unsigned int oldflags,
+ unsigned int flags)
+{
+ if (flags & EXT4_DAX_FL) {
+ if ((oldflags & EXT4_DAX_MUT_EXCL) ||
+ ext4_test_inode_state(inode,
+ EXT4_STATE_VERITY_IN_PROGRESS)) {
+ return false;
+ }
+ }
+
+ if ((flags & EXT4_DAX_MUT_EXCL) && (oldflags & EXT4_DAX_FL))
+ return false;
+
+ return true;
+}
+
static int ext4_ioctl_setflags(struct inode *inode,
unsigned int flags)
{
int err = -EPERM, migrate = 0;
struct ext4_iloc iloc;
unsigned int oldflags, mask, i;
- unsigned int jflag;
struct super_block *sb = inode->i_sb;
/* Is it quota file? Do not allow user to mess with it */
oldflags = ei->i_flags;
- /* The JOURNAL_DATA flag is modifiable only by root */
- jflag = flags & EXT4_JOURNAL_DATA_FL;
-
err = vfs_ioc_setflags_prepare(inode, oldflags, flags);
if (err)
goto flags_out;
* The JOURNAL_DATA flag can only be changed by
* the relevant capability.
*/
- if ((jflag ^ oldflags) & (EXT4_JOURNAL_DATA_FL)) {
+ if ((flags ^ oldflags) & (EXT4_JOURNAL_DATA_FL)) {
if (!capable(CAP_SYS_RESOURCE))
goto flags_out;
}
+
+ if (!dax_compatible(inode, oldflags, flags)) {
+ err = -EOPNOTSUPP;
+ goto flags_out;
+ }
+
if ((flags ^ oldflags) & EXT4_EXTENTS_FL)
migrate = 1;
if (err)
goto flags_err;
+ ext4_dax_dontcache(inode, flags);
+
for (i = 0, mask = 1; i < 32; i++, mask <<= 1) {
if (!(mask & EXT4_FL_USER_MODIFIABLE))
continue;
ext4_clear_inode_flag(inode, i);
}
- ext4_set_inode_flags(inode);
+ ext4_set_inode_flags(inode, false);
+
inode->i_ctime = current_time(inode);
err = ext4_mark_iloc_dirty(handle, inode, &iloc);
if (err)
goto flags_out;
- if ((jflag ^ oldflags) & (EXT4_JOURNAL_DATA_FL)) {
+ if ((flags ^ oldflags) & (EXT4_JOURNAL_DATA_FL)) {
/*
* Changes to the journaling mode can cause unsafe changes to
- * S_DAX if we are using the DAX mount option.
+ * S_DAX if the inode is DAX
*/
- if (test_opt(inode->i_sb, DAX)) {
+ if (IS_DAX(inode)) {
err = -EBUSY;
goto flags_out;
}
- err = ext4_change_inode_journal_flag(inode, jflag);
+ err = ext4_change_inode_journal_flag(inode,
+ flags & EXT4_JOURNAL_DATA_FL);
if (err)
goto flags_out;
}
xflags |= FS_XFLAG_NOATIME;
if (iflags & EXT4_PROJINHERIT_FL)
xflags |= FS_XFLAG_PROJINHERIT;
+ if (iflags & EXT4_DAX_FL)
+ xflags |= FS_XFLAG_DAX;
return xflags;
}
#define EXT4_SUPPORTED_FS_XFLAGS (FS_XFLAG_SYNC | FS_XFLAG_IMMUTABLE | \
FS_XFLAG_APPEND | FS_XFLAG_NODUMP | \
- FS_XFLAG_NOATIME | FS_XFLAG_PROJINHERIT)
+ FS_XFLAG_NOATIME | FS_XFLAG_PROJINHERIT | \
+ FS_XFLAG_DAX)
/* Transfer xflags flags to internal */
static inline unsigned long ext4_xflags_to_iflags(__u32 xflags)
iflags |= EXT4_NOATIME_FL;
if (xflags & FS_XFLAG_PROJINHERIT)
iflags |= EXT4_PROJINHERIT_FL;
+ if (xflags & FS_XFLAG_DAX)
+ iflags |= EXT4_DAX_FL;
return iflags;
}
}
ac->ac_op = EXT4_MB_HISTORY_PREALLOC;
- seq = *this_cpu_ptr(&discard_pa_seq);
+ seq = this_cpu_read(discard_pa_seq);
if (!ext4_mb_use_preallocated(ac)) {
ac->ac_op = EXT4_MB_HISTORY_ALLOC;
ext4_mb_normalize_request(ac, ar);
smp_wmb();
sb->s_flags |= SB_RDONLY;
} else if (test_opt(sb, ERRORS_PANIC)) {
- if (EXT4_SB(sb)->s_journal &&
- !(EXT4_SB(sb)->s_journal->j_flags & JBD2_REC_ERR))
- return;
panic("EXT4-fs (device %s): panic forced after error\n",
sb->s_id);
}
va_end(args);
if (sb_rdonly(sb) == 0) {
- ext4_msg(sb, KERN_CRIT, "Remounting filesystem read-only");
EXT4_SB(sb)->s_mount_flags |= EXT4_MF_FS_ABORTED;
+ if (EXT4_SB(sb)->s_journal)
+ jbd2_journal_abort(EXT4_SB(sb)->s_journal, -EIO);
+
+ ext4_msg(sb, KERN_CRIT, "Remounting filesystem read-only");
/*
* Make sure updated value of ->s_mount_flags will be visible
* before ->s_flags update
*/
smp_wmb();
sb->s_flags |= SB_RDONLY;
- if (EXT4_SB(sb)->s_journal)
- jbd2_journal_abort(EXT4_SB(sb)->s_journal, -EIO);
}
- if (test_opt(sb, ERRORS_PANIC) && !system_going_down()) {
- if (EXT4_SB(sb)->s_journal &&
- !(EXT4_SB(sb)->s_journal->j_flags & JBD2_REC_ERR))
- return;
+ if (test_opt(sb, ERRORS_PANIC) && !system_going_down())
panic("EXT4-fs panic from previous error\n");
- }
}
void __ext4_msg(struct super_block *sb,
if (WARN_ON_ONCE(IS_DAX(inode) && i_size_read(inode)))
return -EINVAL;
+ if (ext4_test_inode_flag(inode, EXT4_INODE_DAX))
+ return -EOPNOTSUPP;
+
res = ext4_convert_inline_data(inode);
if (res)
return res;
* Update inode->i_flags - S_ENCRYPTED will be enabled,
* S_DAX may be disabled
*/
- ext4_set_inode_flags(inode);
+ ext4_set_inode_flags(inode, false);
}
return res;
}
* Update inode->i_flags - S_ENCRYPTED will be enabled,
* S_DAX may be disabled
*/
- ext4_set_inode_flags(inode);
+ ext4_set_inode_flags(inode, false);
res = ext4_mark_inode_dirty(handle, inode);
if (res)
EXT4_ERROR_INODE(inode, "Failed to mark inode dirty");
Opt_usrjquota, Opt_grpjquota, Opt_offusrjquota, Opt_offgrpjquota,
Opt_jqfmt_vfsold, Opt_jqfmt_vfsv0, Opt_jqfmt_vfsv1, Opt_quota,
Opt_noquota, Opt_barrier, Opt_nobarrier, Opt_err,
- Opt_usrquota, Opt_grpquota, Opt_prjquota, Opt_i_version, Opt_dax,
+ Opt_usrquota, Opt_grpquota, Opt_prjquota, Opt_i_version,
+ Opt_dax, Opt_dax_always, Opt_dax_inode, Opt_dax_never,
Opt_stripe, Opt_delalloc, Opt_nodelalloc, Opt_warn_on_error,
Opt_nowarn_on_error, Opt_mblk_io_submit,
Opt_lazytime, Opt_nolazytime, Opt_debug_want_extra_isize,
{Opt_nobarrier, "nobarrier"},
{Opt_i_version, "i_version"},
{Opt_dax, "dax"},
+ {Opt_dax_always, "dax=always"},
+ {Opt_dax_inode, "dax=inode"},
+ {Opt_dax_never, "dax=never"},
{Opt_stripe, "stripe=%u"},
{Opt_delalloc, "delalloc"},
{Opt_warn_on_error, "warn_on_error"},
#define MOPT_NO_EXT3 0x0200
#define MOPT_EXT4_ONLY (MOPT_NO_EXT2 | MOPT_NO_EXT3)
#define MOPT_STRING 0x0400
+#define MOPT_SKIP 0x0800
static const struct mount_opts {
int token;
{Opt_min_batch_time, 0, MOPT_GTE0},
{Opt_inode_readahead_blks, 0, MOPT_GTE0},
{Opt_init_itable, 0, MOPT_GTE0},
- {Opt_dax, EXT4_MOUNT_DAX, MOPT_SET},
+ {Opt_dax, EXT4_MOUNT_DAX_ALWAYS, MOPT_SET | MOPT_SKIP},
+ {Opt_dax_always, EXT4_MOUNT_DAX_ALWAYS,
+ MOPT_EXT4_ONLY | MOPT_SET | MOPT_SKIP},
+ {Opt_dax_inode, EXT4_MOUNT2_DAX_INODE,
+ MOPT_EXT4_ONLY | MOPT_SET | MOPT_SKIP},
+ {Opt_dax_never, EXT4_MOUNT2_DAX_NEVER,
+ MOPT_EXT4_ONLY | MOPT_SET | MOPT_SKIP},
{Opt_stripe, 0, MOPT_GTE0},
{Opt_resuid, 0, MOPT_GTE0},
{Opt_resgid, 0, MOPT_GTE0},
}
sbi->s_jquota_fmt = m->mount_opt;
#endif
- } else if (token == Opt_dax) {
+ } else if (token == Opt_dax || token == Opt_dax_always ||
+ token == Opt_dax_inode || token == Opt_dax_never) {
#ifdef CONFIG_FS_DAX
- ext4_msg(sb, KERN_WARNING,
- "DAX enabled. Warning: EXPERIMENTAL, use at your own risk");
- sbi->s_mount_opt |= m->mount_opt;
+ switch (token) {
+ case Opt_dax:
+ case Opt_dax_always:
+ if (is_remount &&
+ (!(sbi->s_mount_opt & EXT4_MOUNT_DAX_ALWAYS) ||
+ (sbi->s_mount_opt2 & EXT4_MOUNT2_DAX_NEVER))) {
+ fail_dax_change_remount:
+ ext4_msg(sb, KERN_ERR, "can't change "
+ "dax mount option while remounting");
+ return -1;
+ }
+ if (is_remount &&
+ (test_opt(sb, DATA_FLAGS) ==
+ EXT4_MOUNT_JOURNAL_DATA)) {
+ ext4_msg(sb, KERN_ERR, "can't mount with "
+ "both data=journal and dax");
+ return -1;
+ }
+ ext4_msg(sb, KERN_WARNING,
+ "DAX enabled. Warning: EXPERIMENTAL, use at your own risk");
+ sbi->s_mount_opt |= EXT4_MOUNT_DAX_ALWAYS;
+ sbi->s_mount_opt2 &= ~EXT4_MOUNT2_DAX_NEVER;
+ break;
+ case Opt_dax_never:
+ if (is_remount &&
+ (!(sbi->s_mount_opt2 & EXT4_MOUNT2_DAX_NEVER) ||
+ (sbi->s_mount_opt & EXT4_MOUNT_DAX_ALWAYS)))
+ goto fail_dax_change_remount;
+ sbi->s_mount_opt2 |= EXT4_MOUNT2_DAX_NEVER;
+ sbi->s_mount_opt &= ~EXT4_MOUNT_DAX_ALWAYS;
+ break;
+ case Opt_dax_inode:
+ if (is_remount &&
+ ((sbi->s_mount_opt & EXT4_MOUNT_DAX_ALWAYS) ||
+ (sbi->s_mount_opt2 & EXT4_MOUNT2_DAX_NEVER) ||
+ !(sbi->s_mount_opt2 & EXT4_MOUNT2_DAX_INODE)))
+ goto fail_dax_change_remount;
+ sbi->s_mount_opt &= ~EXT4_MOUNT_DAX_ALWAYS;
+ sbi->s_mount_opt2 &= ~EXT4_MOUNT2_DAX_NEVER;
+ /* Strictly for printing options */
+ sbi->s_mount_opt2 |= EXT4_MOUNT2_DAX_INODE;
+ break;
+ }
#else
ext4_msg(sb, KERN_INFO, "dax option not supported");
+ sbi->s_mount_opt2 |= EXT4_MOUNT2_DAX_NEVER;
+ sbi->s_mount_opt &= ~EXT4_MOUNT_DAX_ALWAYS;
return -1;
#endif
} else if (token == Opt_data_err_abort) {
for (m = ext4_mount_opts; m->token != Opt_err; m++) {
int want_set = m->flags & MOPT_SET;
if (((m->flags & (MOPT_SET|MOPT_CLEAR)) == 0) ||
- (m->flags & MOPT_CLEAR_ERR))
+ (m->flags & MOPT_CLEAR_ERR) || m->flags & MOPT_SKIP)
continue;
if (!nodefs && !(m->mount_opt & (sbi->s_mount_opt ^ def_mount_opt)))
continue; /* skip if same as the default */
fscrypt_show_test_dummy_encryption(seq, sep, sb);
+ if (test_opt(sb, DAX_ALWAYS)) {
+ if (IS_EXT2_SB(sb))
+ SEQ_OPTS_PUTS("dax");
+ else
+ SEQ_OPTS_PUTS("dax=always");
+ } else if (test_opt2(sb, DAX_NEVER)) {
+ SEQ_OPTS_PUTS("dax=never");
+ } else if (test_opt2(sb, DAX_INODE)) {
+ SEQ_OPTS_PUTS("dax=inode");
+ }
+
ext4_show_quota_options(seq, sb);
return 0;
}
ext4_msg(sb, KERN_ERR, "revision level too high, "
"forcing read-only mode");
err = -EROFS;
+ goto done;
}
if (read_only)
goto done;
"both data=journal and delalloc");
goto failed_mount;
}
- if (test_opt(sb, DAX)) {
+ if (test_opt(sb, DAX_ALWAYS)) {
ext4_msg(sb, KERN_ERR, "can't mount with "
"both data=journal and dax");
goto failed_mount;
goto failed_mount;
}
- if (sbi->s_mount_opt & EXT4_MOUNT_DAX) {
+ if (bdev_dax_supported(sb->s_bdev, blocksize))
+ set_bit(EXT4_FLAGS_BDEV_IS_DAX, &sbi->s_ext4_flags);
+
+ if (sbi->s_mount_opt & EXT4_MOUNT_DAX_ALWAYS) {
if (ext4_has_feature_inline_data(sb)) {
ext4_msg(sb, KERN_ERR, "Cannot use DAX on a filesystem"
" that may contain inline data");
goto failed_mount;
}
- if (!bdev_dax_supported(sb->s_bdev, blocksize)) {
+ if (!test_bit(EXT4_FLAGS_BDEV_IS_DAX, &sbi->s_ext4_flags)) {
ext4_msg(sb, KERN_ERR,
"DAX unsupported by block device.");
goto failed_mount;
err = -EINVAL;
goto restore_opts;
}
- if (test_opt(sb, DAX)) {
- ext4_msg(sb, KERN_ERR, "can't mount with "
- "both data=journal and dax");
- err = -EINVAL;
- goto restore_opts;
- }
} else if (test_opt(sb, DATA_FLAGS) == EXT4_MOUNT_ORDERED_DATA) {
if (test_opt(sb, JOURNAL_ASYNC_COMMIT)) {
ext4_msg(sb, KERN_ERR, "can't mount with "
goto restore_opts;
}
- if ((sbi->s_mount_opt ^ old_opts.s_mount_opt) & EXT4_MOUNT_DAX) {
- ext4_msg(sb, KERN_WARNING, "warning: refusing change of "
- "dax flag with busy inodes while remounting");
- sbi->s_mount_opt ^= EXT4_MOUNT_DAX;
- }
-
if (sbi->s_mount_flags & EXT4_MF_FS_ABORTED)
ext4_abort(sb, EXT4_ERR_ESHUTDOWN, "Abort forced by user");
handle_t *handle;
int err;
+ if (IS_DAX(inode) || ext4_test_inode_flag(inode, EXT4_INODE_DAX))
+ return -EINVAL;
+
if (ext4_verity_in_progress(inode))
return -EBUSY;
if (err)
goto out_stop;
ext4_set_inode_flag(inode, EXT4_INODE_VERITY);
- ext4_set_inode_flags(inode);
+ ext4_set_inode_flags(inode, false);
err = ext4_mark_iloc_dirty(handle, inode, &iloc);
}
out_stop:
#ifdef CONFIG_EXT4_FS_SECURITY
[EXT4_XATTR_INDEX_SECURITY] = &ext4_xattr_security_handler,
#endif
+ [EXT4_XATTR_INDEX_HURD] = &ext4_xattr_hurd_handler,
};
const struct xattr_handler *ext4_xattr_handlers[] = {
#ifdef CONFIG_EXT4_FS_SECURITY
&ext4_xattr_security_handler,
#endif
+ &ext4_xattr_hurd_handler,
NULL
};
extern const struct xattr_handler ext4_xattr_user_handler;
extern const struct xattr_handler ext4_xattr_trusted_handler;
extern const struct xattr_handler ext4_xattr_security_handler;
+extern const struct xattr_handler ext4_xattr_hurd_handler;
#define EXT4_XATTR_NAME_ENCRYPTION_CONTEXT "c"
--- /dev/null
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * linux/fs/ext4/xattr_hurd.c
+ * Handler for extended gnu attributes for the Hurd.
+ *
+ * Copyright (C) 2001 by Andreas Gruenbacher, <a.gruenbacher@computer.org>
+ * Copyright (C) 2020 by Jan (janneke) Nieuwenhuizen, <janneke@gnu.org>
+ */
+
+#include <linux/init.h>
+#include <linux/string.h>
+#include "ext4.h"
+#include "xattr.h"
+
+static bool
+ext4_xattr_hurd_list(struct dentry *dentry)
+{
+ return test_opt(dentry->d_sb, XATTR_USER);
+}
+
+static int
+ext4_xattr_hurd_get(const struct xattr_handler *handler,
+ struct dentry *unused, struct inode *inode,
+ const char *name, void *buffer, size_t size)
+{
+ if (!test_opt(inode->i_sb, XATTR_USER))
+ return -EOPNOTSUPP;
+
+ return ext4_xattr_get(inode, EXT4_XATTR_INDEX_HURD,
+ name, buffer, size);
+}
+
+static int
+ext4_xattr_hurd_set(const struct xattr_handler *handler,
+ struct dentry *unused, struct inode *inode,
+ const char *name, const void *value,
+ size_t size, int flags)
+{
+ if (!test_opt(inode->i_sb, XATTR_USER))
+ return -EOPNOTSUPP;
+
+ return ext4_xattr_set(inode, EXT4_XATTR_INDEX_HURD,
+ name, value, size, flags);
+}
+
+const struct xattr_handler ext4_xattr_hurd_handler = {
+ .prefix = XATTR_HURD_PREFIX,
+ .list = ext4_xattr_hurd_list,
+ .get = ext4_xattr_hurd_get,
+ .set = ext4_xattr_hurd_set,
+};
init_waitqueue_head(&journal->j_wait_commit);
init_waitqueue_head(&journal->j_wait_updates);
init_waitqueue_head(&journal->j_wait_reserved);
+ mutex_init(&journal->j_abort_mutex);
mutex_init(&journal->j_barrier);
mutex_init(&journal->j_checkpoint_mutex);
spin_lock_init(&journal->j_revoke_lock);
printk(KERN_ERR "JBD2: Error %d detected when updating "
"journal superblock for %s.\n", ret,
journal->j_devname);
- jbd2_journal_abort(journal, ret);
+ if (!is_journal_aborted(journal))
+ jbd2_journal_abort(journal, ret);
}
return ret;
{
transaction_t *transaction;
+ /*
+ * Lock the aborting procedure until everything is done, this avoid
+ * races between filesystem's error handling flow (e.g. ext4_abort()),
+ * ensure panic after the error info is written into journal's
+ * superblock.
+ */
+ mutex_lock(&journal->j_abort_mutex);
/*
* ESHUTDOWN always takes precedence because a file system check
* caused by any other journal abort error is not required after
journal->j_errno = errno;
jbd2_journal_update_sb_errno(journal);
}
+ mutex_unlock(&journal->j_abort_mutex);
return;
}
* layer could realise that a filesystem check is needed.
*/
jbd2_journal_update_sb_errno(journal);
-
- write_lock(&journal->j_state_lock);
- journal->j_flags |= JBD2_REC_ERR;
- write_unlock(&journal->j_state_lock);
+ mutex_unlock(&journal->j_abort_mutex);
}
/**
uint32_t ino; /* == zero for unlink */
unsigned int nhash;
unsigned char type;
- unsigned char name[0];
+ unsigned char name[];
};
/*
jint32_t ino; /* == zero for unlink */
uint8_t nsize; /* dirent name size */
uint8_t type; /* dirent type */
- uint8_t name[0]; /* dirent name */
+ uint8_t name[]; /* dirent name */
} __attribute__((packed));
struct jffs2_sum_xattr_flash
jint32_t ino; /* == zero for unlink */
uint8_t nsize; /* dirent name size */
uint8_t type; /* dirent type */
- uint8_t name[0]; /* dirent name */
+ uint8_t name[]; /* dirent name */
} __attribute__((packed));
struct jffs2_sum_xattr_mem
* Using bounce buffer to bypass the
* hardened user copy kernel text checks.
*/
- if (probe_kernel_read(buf, (void *) start, tsz)) {
+ if (copy_from_kernel_nofault(buf, (void *)start,
+ tsz)) {
if (clear_user(buffer, tsz)) {
ret = -EFAULT;
goto out;
__le32 index;
__le32 start_block;
__le32 size;
- unsigned char name[0];
+ unsigned char name[];
};
struct squashfs_base_inode {
__le32 inode_number;
__le32 nlink;
__le32 symlink_size;
- char symlink[0];
+ char symlink[];
};
struct squashfs_reg_inode {
__le32 fragment;
__le32 offset;
__le32 file_size;
- __le16 block_list[0];
+ __le16 block_list[];
};
struct squashfs_lreg_inode {
__le32 fragment;
__le32 offset;
__le32 xattr;
- __le16 block_list[0];
+ __le16 block_list[];
};
struct squashfs_dir_inode {
__le16 i_count;
__le16 offset;
__le32 xattr;
- struct squashfs_dir_index index[0];
+ struct squashfs_dir_index index[];
};
union squashfs_inode {
__le16 inode_number;
__le16 type;
__le16 size;
- char name[0];
+ char name[];
};
struct squashfs_dir_header {
struct squashfs_xattr_entry {
__le16 type;
__le16 size;
- char data[0];
+ char data[];
};
struct squashfs_xattr_val {
__le32 vsize;
- char value[0];
+ char value[];
};
struct squashfs_xattr_id {
struct displayid_detailed_timing_block {
struct displayid_block base;
- struct displayid_detailed_timings_1 timings[0];
+ struct displayid_detailed_timings_1 timings[];
};
#define for_each_displayid_db(displayid, block, idx, length) \
unsigned short payload_datalen; /* payload data length */
unsigned short encrypted_key_format; /* encrypted key format */
u8 *decrypted_data; /* decrypted data */
- u8 payload_data[0]; /* payload data + datablob + hmac */
+ u8 payload_data[]; /* payload data + datablob + hmac */
};
extern struct key_type key_type_encrypted;
u8 primary_flag; /* T if key for primary cell for this user */
u16 ticket_len; /* length of ticket[] */
u8 session_key[8]; /* DES session key */
- u8 ticket[0]; /* the encrypted ticket */
+ u8 ticket[]; /* the encrypted ticket */
};
/*
u32 expiry; /* time_t */
u32 kvno;
u8 session_key[8];
- u8 ticket[0];
+ u8 ticket[];
};
/*
struct can_skb_priv {
int ifindex;
int skbcnt;
- struct can_frame cf[0];
+ struct can_frame cf[];
};
static inline struct can_skb_priv *can_skb_prv(struct sk_buff *skb)
unsigned slot_mask;
unsigned slots;
spinlock_t irq_lock;
- struct cb710_slot slot[0];
+ struct cb710_slot slot[];
};
/* NOTE: cb710_chip.slots is modified only during device init/exit and
#ifndef __ASSEMBLY__
#ifdef __CHECKER__
-# define __user __attribute__((noderef, address_space(1)))
# define __kernel __attribute__((address_space(0)))
+# define __user __attribute__((noderef, address_space(__user)))
# define __safe __attribute__((safe))
# define __force __attribute__((force))
# define __nocast __attribute__((nocast))
-# define __iomem __attribute__((noderef, address_space(2)))
+# define __iomem __attribute__((noderef, address_space(__iomem)))
# define __must_hold(x) __attribute__((context(x,1,1)))
# define __acquires(x) __attribute__((context(x,0,1)))
# define __releases(x) __attribute__((context(x,1,0)))
# define __acquire(x) __context__(x,1)
# define __release(x) __context__(x,-1)
# define __cond_lock(x,c) ((c) ? ({ __acquire(x); 1; }) : 0)
-# define __percpu __attribute__((noderef, address_space(3)))
-# define __rcu __attribute__((noderef, address_space(4)))
+# define __percpu __attribute__((noderef, address_space(__percpu)))
+# define __rcu __attribute__((noderef, address_space(__rcu)))
# define __private __attribute__((noderef))
extern void __chk_user_ptr(const volatile void __user *);
extern void __chk_io_ptr(const volatile void __iomem *);
bool dst_sgl;
size_t numf;
size_t frame_size;
- struct data_chunk sgl[0];
+ struct data_chunk sgl[];
};
/**
struct device *dev;
struct kref kref;
size_t len;
- dma_addr_t addr[0];
+ dma_addr_t addr[];
};
struct dma_async_tx_descriptor;
unsigned long flags;
#define FSCACHE_TAG_RESERVED 0 /* T if tag is reserved for a cache */
atomic_t usage;
- char name[0]; /* tag name */
+ char name[]; /* tag name */
};
/*
*/
int j_errno;
+ /**
+ * @j_abort_mutex: Lock the whole aborting procedure.
+ */
+ struct mutex j_abort_mutex;
+
/**
* @j_sb_buffer: The first part of the superblock buffer.
*/
#define JBD2_ABORT_ON_SYNCDATA_ERR 0x040 /* Abort the journal on file
* data write error in ordered
* mode */
-#define JBD2_REC_ERR 0x080 /* The errno in the sb has been recorded */
/*
* Function declarations for the journaling transaction and buffer
struct crash_mem {
unsigned int max_nr_ranges;
unsigned int nr_ranges;
- struct crash_mem_range ranges[0];
+ struct crash_mem_range ranges[];
};
extern int crash_exclude_mem_range(struct crash_mem *mem,
kprobe_opcode_t *ret_addr;
struct task_struct *task;
void *fp;
- char data[0];
+ char data[];
};
struct kretprobe_blackpoint {
* Array indexed by gsi. Each entry contains list of irq chips
* the gsi is connected to.
*/
- struct hlist_head map[0];
+ struct hlist_head map[];
};
#endif
struct task_struct *eh_owner;
struct ata_port *simplex_claimed; /* channel owning the DMA */
- struct ata_port *ports[0];
+ struct ata_port *ports[];
};
struct ata_queued_cmd {
* struct_size() - Calculate size of structure with trailing array.
* @p: Pointer to the structure.
* @member: Name of the array member.
- * @n: Number of elements in the array.
+ * @count: Number of elements in the array.
*
* Calculates size of memory needed for structure @p followed by an
- * array of @n @member elements.
+ * array of @count number of @member elements.
*
* Return: number of bytes needed or SIZE_MAX on overflow.
*/
-#define struct_size(p, member, n) \
- __ab_c_size(n, \
+#define struct_size(p, member, count) \
+ __ab_c_size(count, \
sizeof(*(p)->member) + __must_be_array((p)->member),\
sizeof(*(p)))
+/**
+ * flex_array_size() - Calculate size of a flexible array member
+ * within an enclosing structure.
+ *
+ * @p: Pointer to the structure.
+ * @member: Name of the flexible array member.
+ * @count: Number of elements in the array.
+ *
+ * Calculates size of a flexible array of @count number of @member
+ * elements, at the end of structure @p.
+ *
+ * Return: number of bytes needed or SIZE_MAX on overflow.
+ */
+#define flex_array_size(p, member, count) \
+ array_size(count, \
+ sizeof(*(p)->member) + __must_be_array((p)->member))
+
#endif /* __LINUX_OVERFLOW_H */
__be16 stream;
__be16 ssn;
__u32 ppid;
- __u8 payload[0];
+ __u8 payload[];
};
struct sctp_data_chunk {
__be16 num_outbound_streams;
__be16 num_inbound_streams;
__be32 initial_tsn;
- __u8 params[0];
+ __u8 params[];
};
struct sctp_init_chunk {
/* Section 3.3.2.1 Host Name Address (11) */
struct sctp_hostname_param {
struct sctp_paramhdr param_hdr;
- uint8_t hostname[0];
+ uint8_t hostname[];
};
/* Section 3.3.2.1 Supported Address Types (12) */
struct sctp_supported_addrs_param {
struct sctp_paramhdr param_hdr;
- __be16 types[0];
+ __be16 types[];
};
/* ADDIP Section 3.2.6 Adaptation Layer Indication */
/* ADDIP Section 4.2.7 Supported Extensions Parameter */
struct sctp_supported_ext_param {
struct sctp_paramhdr param_hdr;
- __u8 chunks[0];
+ __u8 chunks[];
};
/* AUTH Section 3.1 Random */
struct sctp_random_param {
struct sctp_paramhdr param_hdr;
- __u8 random_val[0];
+ __u8 random_val[];
};
/* AUTH Section 3.2 Chunk List */
struct sctp_chunks_param {
struct sctp_paramhdr param_hdr;
- __u8 chunks[0];
+ __u8 chunks[];
};
/* AUTH Section 3.3 HMAC Algorithm */
struct sctp_hmac_algo_param {
struct sctp_paramhdr param_hdr;
- __be16 hmac_ids[0];
+ __be16 hmac_ids[];
};
/* RFC 2960. Section 3.3.3 Initiation Acknowledgement (INIT ACK) (2):
/* Section 3.3.3.1 State Cookie (7) */
struct sctp_cookie_param {
struct sctp_paramhdr p;
- __u8 body[0];
+ __u8 body[];
};
/* Section 3.3.3.1 Unrecognized Parameters (8) */
__be32 a_rwnd;
__be16 num_gap_ack_blocks;
__be16 num_dup_tsns;
- union sctp_sack_variable variable[0];
+ union sctp_sack_variable variable[];
};
struct sctp_sack_chunk {
struct sctp_errhdr {
__be16 cause;
__be16 length;
- __u8 variable[0];
+ __u8 variable[];
};
struct sctp_operr_chunk {
struct sctp_fwdtsn_hdr {
__be32 new_cum_tsn;
- struct sctp_fwdtsn_skip skip[0];
+ struct sctp_fwdtsn_skip skip[];
};
struct sctp_fwdtsn_chunk {
struct sctp_ifwdtsn_hdr {
__be32 new_cum_tsn;
- struct sctp_ifwdtsn_skip skip[0];
+ struct sctp_ifwdtsn_skip skip[];
};
struct sctp_ifwdtsn_chunk {
struct sctp_addiphdr {
__be32 serial;
- __u8 params[0];
+ __u8 params[];
};
struct sctp_addip_chunk {
struct sctp_authhdr {
__be16 shkey_id;
__be16 hmac_id;
- __u8 hmac[0];
+ __u8 hmac[];
};
struct sctp_auth_chunk {
struct sctp_reconf_chunk {
struct sctp_chunkhdr chunk_hdr;
- __u8 params[0];
+ __u8 params[];
};
struct sctp_strreset_outreq {
__be32 request_seq;
__be32 response_seq;
__be32 send_reset_at_tsn;
- __be16 list_of_streams[0];
+ __be16 list_of_streams[];
};
struct sctp_strreset_inreq {
struct sctp_paramhdr param_hdr;
__be32 request_seq;
- __be16 list_of_streams[0];
+ __be16 list_of_streams[];
};
struct sctp_strreset_tsnreq {
int (*has_ms_pif)(struct tifm_adapter *fm,
struct tifm_dev *sock);
- struct tifm_dev *sockets[0];
+ struct tifm_dev *sockets[];
};
struct tifm_adapter *tifm_alloc_adapter(unsigned int num_sockets,
return 0;
}
-bool probe_kernel_read_allowed(const void *unsafe_src, size_t size);
+bool copy_from_kernel_nofault_allowed(const void *unsafe_src, size_t size);
-extern long probe_kernel_read(void *dst, const void *src, size_t size);
-extern long probe_user_read(void *dst, const void __user *src, size_t size);
+long copy_from_kernel_nofault(void *dst, const void *src, size_t size);
+long notrace copy_to_kernel_nofault(void *dst, const void *src, size_t size);
-extern long notrace probe_kernel_write(void *dst, const void *src, size_t size);
-extern long notrace probe_user_write(void __user *dst, const void *src, size_t size);
+long copy_from_user_nofault(void *dst, const void __user *src, size_t size);
+long notrace copy_to_user_nofault(void __user *dst, const void *src,
+ size_t size);
long strncpy_from_kernel_nofault(char *dst, const void *unsafe_addr,
long count);
long strnlen_user_nofault(const void __user *unsafe_addr, long count);
/**
- * probe_kernel_address(): safely attempt to read from a location
- * @addr: address to read from
- * @retval: read into this variable
+ * get_kernel_nofault(): safely attempt to read from a location
+ * @val: read into this variable
+ * @ptr: address to read from
*
* Returns 0 on success, or -EFAULT.
*/
-#define probe_kernel_address(addr, retval) \
- probe_kernel_read(&retval, addr, sizeof(retval))
+#define get_kernel_nofault(val, ptr) ({ \
+ const typeof(val) *__gk_ptr = (ptr); \
+ copy_from_kernel_nofault(&(val), __gk_ptr, sizeof(val));\
+})
#ifndef user_access_begin
#define user_access_begin(ptr,len) access_ok(ptr, len)
struct flow_offload *flow_offload_alloc(struct nf_conn *ct);
void flow_offload_free(struct flow_offload *flow);
-int nf_flow_table_offload_add_cb(struct nf_flowtable *flow_table,
- flow_setup_cb_t *cb, void *cb_priv);
-void nf_flow_table_offload_del_cb(struct nf_flowtable *flow_table,
- flow_setup_cb_t *cb, void *cb_priv);
+static inline int
+nf_flow_table_offload_add_cb(struct nf_flowtable *flow_table,
+ flow_setup_cb_t *cb, void *cb_priv)
+{
+ struct flow_block *block = &flow_table->flow_block;
+ struct flow_block_cb *block_cb;
+ int err = 0;
+
+ down_write(&flow_table->flow_block_lock);
+ block_cb = flow_block_cb_lookup(block, cb, cb_priv);
+ if (block_cb) {
+ err = -EEXIST;
+ goto unlock;
+ }
+
+ block_cb = flow_block_cb_alloc(cb, cb_priv, cb_priv, NULL);
+ if (IS_ERR(block_cb)) {
+ err = PTR_ERR(block_cb);
+ goto unlock;
+ }
+
+ list_add_tail(&block_cb->list, &block->cb_list);
+
+unlock:
+ up_write(&flow_table->flow_block_lock);
+ return err;
+}
+
+static inline void
+nf_flow_table_offload_del_cb(struct nf_flowtable *flow_table,
+ flow_setup_cb_t *cb, void *cb_priv)
+{
+ struct flow_block *block = &flow_table->flow_block;
+ struct flow_block_cb *block_cb;
+
+ down_write(&flow_table->flow_block_lock);
+ block_cb = flow_block_cb_lookup(block, cb, cb_priv);
+ if (block_cb) {
+ list_del(&block_cb->list);
+ flow_block_cb_free(block_cb);
+ } else {
+ WARN_ON(true);
+ }
+ up_write(&flow_table->flow_block_lock);
+}
int flow_offload_route_init(struct flow_offload *flow,
const struct nf_flow_route *route);
#endif /* CONFIG_NF_CONNTRACK */
#if IS_ENABLED(CONFIG_NET_ACT_CT)
-void tcf_ct_flow_table_restore_skb(struct sk_buff *skb, unsigned long cookie);
+static inline void
+tcf_ct_flow_table_restore_skb(struct sk_buff *skb, unsigned long cookie)
+{
+ enum ip_conntrack_info ctinfo = cookie & NFCT_INFOMASK;
+ struct nf_conn *ct;
+
+ ct = (struct nf_conn *)(cookie & NFCT_PTRMASK);
+ nf_conntrack_get(&ct->ct_general);
+ nf_ct_set(skb, ct, ctinfo);
+}
#else
static inline void
tcf_ct_flow_table_restore_skb(struct sk_buff *skb, unsigned long cookie) { }
#define FS_EA_INODE_FL 0x00200000 /* Inode used for large EA */
#define FS_EOFBLOCKS_FL 0x00400000 /* Reserved for ext4 */
#define FS_NOCOW_FL 0x00800000 /* Do not cow file */
+#define FS_DAX_FL 0x02000000 /* Inode is DAX */
#define FS_INLINE_DATA_FL 0x10000000 /* Reserved for ext4 */
#define FS_PROJINHERIT_FL 0x20000000 /* Create with parents projid */
#define FS_CASEFOLD_FL 0x40000000 /* Folder is case insensitive */
Copyright (C) 2001 by Andreas Gruenbacher <a.gruenbacher@computer.org>
Copyright (c) 2001-2002 Silicon Graphics, Inc. All Rights Reserved.
Copyright (c) 2004 Red Hat, Inc., James Morris <jmorris@redhat.com>
+ Copyright (c) 2020 Jan (janneke) Nieuwenhuizen <janneke@gnu.org>
*/
#include <linux/libc-compat.h>
#define XATTR_BTRFS_PREFIX "btrfs."
#define XATTR_BTRFS_PREFIX_LEN (sizeof(XATTR_BTRFS_PREFIX) - 1)
+#define XATTR_HURD_PREFIX "gnu."
+#define XATTR_HURD_PREFIX_LEN (sizeof(XATTR_HURD_PREFIX) - 1)
+
#define XATTR_SECURITY_PREFIX "security."
#define XATTR_SECURITY_PREFIX_LEN (sizeof(XATTR_SECURITY_PREFIX) - 1)
{
int err;
- err = probe_kernel_read(bpt->saved_instr, (char *)bpt->bpt_addr,
+ err = copy_from_kernel_nofault(bpt->saved_instr, (char *)bpt->bpt_addr,
BREAK_INSTR_SIZE);
if (err)
return err;
- err = probe_kernel_write((char *)bpt->bpt_addr,
+ err = copy_to_kernel_nofault((char *)bpt->bpt_addr,
arch_kgdb_ops.gdb_bpt_instr, BREAK_INSTR_SIZE);
return err;
}
int __weak kgdb_arch_remove_breakpoint(struct kgdb_bkpt *bpt)
{
- return probe_kernel_write((char *)bpt->bpt_addr,
+ return copy_to_kernel_nofault((char *)bpt->bpt_addr,
(char *)bpt->saved_instr, BREAK_INSTR_SIZE);
}
*/
tmp = buf + count;
- err = probe_kernel_read(tmp, mem, count);
+ err = copy_from_kernel_nofault(tmp, mem, count);
if (err)
return NULL;
while (count > 0) {
*tmp_raw |= hex_to_bin(*tmp_hex--) << 4;
}
- return probe_kernel_write(mem, tmp_raw, count);
+ return copy_to_kernel_nofault(mem, tmp_raw, count);
}
/*
size++;
}
- return probe_kernel_write(mem, c, size);
+ return copy_to_kernel_nofault(mem, c, size);
}
#if DBG_MAX_REG_NUM > 0
int cpu;
unsigned long tmp;
- if (!p || probe_kernel_read(&tmp, (char *)p, sizeof(unsigned long)))
+ if (!p ||
+ copy_from_kernel_nofault(&tmp, (char *)p, sizeof(unsigned long)))
return;
cpu = kdb_process_cpu(p);
*/
int kdb_getarea_size(void *res, unsigned long addr, size_t size)
{
- int ret = probe_kernel_read((char *)res, (char *)addr, size);
+ int ret = copy_from_kernel_nofault((char *)res, (char *)addr, size);
if (ret) {
if (!KDB_STATE(SUPPRESS)) {
kdb_printf("kdb_getarea: Bad address 0x%lx\n", addr);
*/
int kdb_putarea_size(unsigned long addr, void *res, size_t size)
{
- int ret = probe_kernel_read((char *)addr, (char *)res, size);
+ int ret = copy_from_kernel_nofault((char *)addr, (char *)res, size);
if (ret) {
if (!KDB_STATE(SUPPRESS)) {
kdb_printf("kdb_putarea: Bad address 0x%lx\n", addr);
char state;
unsigned long tmp;
- if (!p || probe_kernel_read(&tmp, (char *)p, sizeof(unsigned long)))
+ if (!p ||
+ copy_from_kernel_nofault(&tmp, (char *)p, sizeof(unsigned long)))
return 'E';
cpu = kdb_process_cpu(p);
config DMA_NONCOHERENT_MMAP
bool
+config DMA_COHERENT_POOL
+ bool
+
config DMA_REMAP
+ bool
depends on MMU
select GENERIC_ALLOCATOR
select DMA_NONCOHERENT_MMAP
- bool
-
-config DMA_COHERENT_POOL
- bool
- select DMA_REMAP
config DMA_DIRECT_REMAP
bool
+ select DMA_REMAP
select DMA_COHERENT_POOL
config DMA_CMA
* sizes to 128KB per 1GB of memory, min 128KB, max MAX_ORDER-1.
*/
if (!atomic_pool_size) {
- atomic_pool_size = max(totalram_pages() >> PAGE_SHIFT, 1UL) *
- SZ_128K;
- atomic_pool_size = min_t(size_t, atomic_pool_size,
- 1 << (PAGE_SHIFT + MAX_ORDER-1));
+ unsigned long pages = totalram_pages() / (SZ_1G / SZ_128K);
+ pages = min_t(unsigned long, pages, MAX_ORDER_NR_PAGES);
+ atomic_pool_size = max_t(size_t, pages << PAGE_SHIFT, SZ_128K);
}
INIT_WORK(&atomic_pool_work, atomic_pool_work_fn);
struct kthread *kthread = to_kthread(task);
void *data = NULL;
- probe_kernel_read(&data, &kthread->data, sizeof(data));
+ copy_from_kernel_nofault(&data, &kthread->data, sizeof(data));
return data;
}
{
int ret;
- ret = probe_user_read(dst, unsafe_ptr, size);
+ ret = copy_from_user_nofault(dst, unsafe_ptr, size);
if (unlikely(ret < 0))
memset(dst, 0, size);
return ret;
if (unlikely(ret < 0))
goto fail;
- ret = probe_kernel_read(dst, unsafe_ptr, size);
+ ret = copy_from_kernel_nofault(dst, unsafe_ptr, size);
if (unlikely(ret < 0))
goto fail;
return ret;
if (unlikely(!nmi_uaccess_okay()))
return -EPERM;
- return probe_user_write(unsafe_ptr, src, size);
+ return copy_to_user_nofault(unsafe_ptr, src, size);
}
static const struct bpf_func_proto bpf_probe_write_user_proto = {
copy_size = (fmt[i + 2] == '4') ? 4 : 16;
- err = probe_kernel_read(bufs->buf[memcpy_cnt],
+ err = copy_from_kernel_nofault(bufs->buf[memcpy_cnt],
(void *) (long) args[fmt_cnt],
copy_size);
if (err < 0)
#endif
do {
- ret = probe_kernel_read(&c, (u8 *)addr + len, 1);
+ ret = copy_from_kernel_nofault(&c, (u8 *)addr + len, 1);
len++;
} while (c && ret == 0 && len < MAX_STRING_SIZE);
{
const void __user *uaddr = (__force const void __user *)src;
- return probe_user_read(dest, uaddr, size);
+ return copy_from_user_nofault(dest, uaddr, size);
}
static nokprobe_inline int
if ((unsigned long)src < TASK_SIZE)
return probe_mem_read_user(dest, src, size);
#endif
- return probe_kernel_read(dest, src, size);
+ return copy_from_kernel_nofault(dest, src, size);
}
/* Note that we don't verify it, since the code does not come from user space */
struct trace_event_call call;
struct list_head files;
struct list_head probes;
- struct trace_uprobe_filter filter[0];
+ struct trace_uprobe_filter filter[];
};
struct trace_probe {
* Carefully copy the associated workqueue's workfn, name and desc.
* Keep the original last '\0' in case the original is garbage.
*/
- probe_kernel_read(&fn, &worker->current_func, sizeof(fn));
- probe_kernel_read(&pwq, &worker->current_pwq, sizeof(pwq));
- probe_kernel_read(&wq, &pwq->wq, sizeof(wq));
- probe_kernel_read(name, wq->name, sizeof(name) - 1);
- probe_kernel_read(desc, worker->desc, sizeof(desc) - 1);
+ copy_from_kernel_nofault(&fn, &worker->current_func, sizeof(fn));
+ copy_from_kernel_nofault(&pwq, &worker->current_pwq, sizeof(pwq));
+ copy_from_kernel_nofault(&wq, &pwq->wq, sizeof(wq));
+ copy_from_kernel_nofault(name, wq->name, sizeof(name) - 1);
+ copy_from_kernel_nofault(desc, worker->desc, sizeof(desc) - 1);
if (fn || name[0] || desc[0]) {
printk("%sWorkqueue: %s %ps", log_lvl, name, fn);
/* should be at least readable kernel address */
if (access_ok(ptr, 1) ||
access_ok(ptr + size - 1, 1) ||
- probe_kernel_address(ptr, buf) ||
- probe_kernel_address(ptr + size - 1, buf)) {
+ get_kernel_nofault(buf, ptr) ||
+ get_kernel_nofault(buf, ptr + size - 1)) {
pr_err("invalid kernel ptr: %#lx\n", addr);
return true;
}
if (!addr)
return false;
- if (probe_kernel_address(ptr, magic) || magic != expected) {
+ if (get_kernel_nofault(magic, ptr) || magic != expected) {
pr_err("invalid magic at %#lx + %#x = %#x, expected %#x\n",
addr, offset, magic, expected);
return true;
err_world2_obj_get:
for (i--; i >= 0; i--)
world_obj_put(&world2, objagg, hints_case->key_ids[i]);
- objagg_hints_put(hints);
- objagg_destroy(objagg2);
i = hints_case->key_ids_count;
+ objagg_destroy(objagg2);
err_check_expect_hints_stats:
+ objagg_hints_put(hints);
err_hints_get:
err_check_expect_stats:
err_world_obj_get:
* mapping can be invalid pointer and we don't want to crash
* accessing it, so probe everything depending on it carefully
*/
- if (probe_kernel_read(&host, &mapping->host,
+ if (copy_from_kernel_nofault(&host, &mapping->host,
sizeof(struct inode *)) ||
- probe_kernel_read(&a_ops, &mapping->a_ops,
+ copy_from_kernel_nofault(&a_ops, &mapping->a_ops,
sizeof(struct address_space_operations *))) {
pr_warn("failed to read mapping->host or a_ops, mapping not a valid kernel address?\n");
goto out_mapping;
goto out_mapping;
}
- if (probe_kernel_read(&dentry_first,
+ if (copy_from_kernel_nofault(&dentry_first,
&host->i_dentry.first, sizeof(struct hlist_node *))) {
pr_warn("mapping->a_ops:%ps with invalid mapping->host inode address %px\n",
a_ops, host);
}
dentry_ptr = container_of(dentry_first, struct dentry, d_u.d_alias);
- if (probe_kernel_read(&dentry, dentry_ptr,
+ if (copy_from_kernel_nofault(&dentry, dentry_ptr,
sizeof(struct dentry))) {
pr_warn("mapping->aops:%ps with invalid mapping->host->i_dentry.first %px\n",
a_ops, dentry_ptr);
#include <linux/mm.h>
#include <linux/uaccess.h>
-bool __weak probe_kernel_read_allowed(const void *unsafe_src, size_t size)
+bool __weak copy_from_kernel_nofault_allowed(const void *unsafe_src,
+ size_t size)
{
return true;
}
#ifdef HAVE_GET_KERNEL_NOFAULT
-#define probe_kernel_read_loop(dst, src, len, type, err_label) \
+#define copy_from_kernel_nofault_loop(dst, src, len, type, err_label) \
while (len >= sizeof(type)) { \
__get_kernel_nofault(dst, src, type, err_label); \
dst += sizeof(type); \
len -= sizeof(type); \
}
-long probe_kernel_read(void *dst, const void *src, size_t size)
+long copy_from_kernel_nofault(void *dst, const void *src, size_t size)
{
- if (!probe_kernel_read_allowed(src, size))
+ if (!copy_from_kernel_nofault_allowed(src, size))
return -ERANGE;
pagefault_disable();
- probe_kernel_read_loop(dst, src, size, u64, Efault);
- probe_kernel_read_loop(dst, src, size, u32, Efault);
- probe_kernel_read_loop(dst, src, size, u16, Efault);
- probe_kernel_read_loop(dst, src, size, u8, Efault);
+ copy_from_kernel_nofault_loop(dst, src, size, u64, Efault);
+ copy_from_kernel_nofault_loop(dst, src, size, u32, Efault);
+ copy_from_kernel_nofault_loop(dst, src, size, u16, Efault);
+ copy_from_kernel_nofault_loop(dst, src, size, u8, Efault);
pagefault_enable();
return 0;
Efault:
pagefault_enable();
return -EFAULT;
}
-EXPORT_SYMBOL_GPL(probe_kernel_read);
+EXPORT_SYMBOL_GPL(copy_from_kernel_nofault);
-#define probe_kernel_write_loop(dst, src, len, type, err_label) \
+#define copy_to_kernel_nofault_loop(dst, src, len, type, err_label) \
while (len >= sizeof(type)) { \
__put_kernel_nofault(dst, src, type, err_label); \
dst += sizeof(type); \
len -= sizeof(type); \
}
-long probe_kernel_write(void *dst, const void *src, size_t size)
+long copy_to_kernel_nofault(void *dst, const void *src, size_t size)
{
pagefault_disable();
- probe_kernel_write_loop(dst, src, size, u64, Efault);
- probe_kernel_write_loop(dst, src, size, u32, Efault);
- probe_kernel_write_loop(dst, src, size, u16, Efault);
- probe_kernel_write_loop(dst, src, size, u8, Efault);
+ copy_to_kernel_nofault_loop(dst, src, size, u64, Efault);
+ copy_to_kernel_nofault_loop(dst, src, size, u32, Efault);
+ copy_to_kernel_nofault_loop(dst, src, size, u16, Efault);
+ copy_to_kernel_nofault_loop(dst, src, size, u8, Efault);
pagefault_enable();
return 0;
Efault:
if (unlikely(count <= 0))
return 0;
- if (!probe_kernel_read_allowed(unsafe_addr, count))
+ if (!copy_from_kernel_nofault_allowed(unsafe_addr, count))
return -ERANGE;
pagefault_disable();
}
#else /* HAVE_GET_KERNEL_NOFAULT */
/**
- * probe_kernel_read(): safely attempt to read from kernel-space
+ * copy_from_kernel_nofault(): safely attempt to read from kernel-space
* @dst: pointer to the buffer that shall take the data
* @src: address to read from
* @size: size of the data chunk
*
* We ensure that the copy_from_user is executed in atomic context so that
* do_page_fault() doesn't attempt to take mmap_lock. This makes
- * probe_kernel_read() suitable for use within regions where the caller
+ * copy_from_kernel_nofault() suitable for use within regions where the caller
* already holds mmap_lock, or other locks which nest inside mmap_lock.
*/
-long probe_kernel_read(void *dst, const void *src, size_t size)
+long copy_from_kernel_nofault(void *dst, const void *src, size_t size)
{
long ret;
mm_segment_t old_fs = get_fs();
- if (!probe_kernel_read_allowed(src, size))
+ if (!copy_from_kernel_nofault_allowed(src, size))
return -ERANGE;
set_fs(KERNEL_DS);
return -EFAULT;
return 0;
}
-EXPORT_SYMBOL_GPL(probe_kernel_read);
+EXPORT_SYMBOL_GPL(copy_from_kernel_nofault);
/**
- * probe_kernel_write(): safely attempt to write to a location
+ * copy_to_kernel_nofault(): safely attempt to write to a location
* @dst: address to write to
* @src: pointer to the data that shall be written
* @size: size of the data chunk
* Safely write to address @dst from the buffer at @src. If a kernel fault
* happens, handle that and return -EFAULT.
*/
-long probe_kernel_write(void *dst, const void *src, size_t size)
+long copy_to_kernel_nofault(void *dst, const void *src, size_t size)
{
long ret;
mm_segment_t old_fs = get_fs();
if (unlikely(count <= 0))
return 0;
- if (!probe_kernel_read_allowed(unsafe_addr, count))
+ if (!copy_from_kernel_nofault_allowed(unsafe_addr, count))
return -ERANGE;
set_fs(KERNEL_DS);
#endif /* HAVE_GET_KERNEL_NOFAULT */
/**
- * probe_user_read(): safely attempt to read from a user-space location
+ * copy_from_user_nofault(): safely attempt to read from a user-space location
* @dst: pointer to the buffer that shall take the data
* @src: address to read from. This must be a user address.
* @size: size of the data chunk
* Safely read from user address @src to the buffer at @dst. If a kernel fault
* happens, handle that and return -EFAULT.
*/
-long probe_user_read(void *dst, const void __user *src, size_t size)
+long copy_from_user_nofault(void *dst, const void __user *src, size_t size)
{
long ret = -EFAULT;
mm_segment_t old_fs = get_fs();
return -EFAULT;
return 0;
}
-EXPORT_SYMBOL_GPL(probe_user_read);
+EXPORT_SYMBOL_GPL(copy_from_user_nofault);
/**
- * probe_user_write(): safely attempt to write to a user-space location
+ * copy_to_user_nofault(): safely attempt to write to a user-space location
* @dst: address to write to
* @src: pointer to the data that shall be written
* @size: size of the data chunk
* Safely write to address @dst from the buffer at @src. If a kernel fault
* happens, handle that and return -EFAULT.
*/
-long probe_user_write(void __user *dst, const void *src, size_t size)
+long copy_to_user_nofault(void __user *dst, const void *src, size_t size)
{
long ret = -EFAULT;
mm_segment_t old_fs = get_fs();
return -EFAULT;
return 0;
}
-EXPORT_SYMBOL_GPL(probe_user_write);
+EXPORT_SYMBOL_GPL(copy_to_user_nofault);
/**
* strncpy_from_user_nofault: - Copy a NUL terminated string from unsafe user
}
/* test 2: write to the variable; this should fault */
- if (!probe_kernel_write((void *)&rodata_test_data,
+ if (!copy_to_kernel_nofault((void *)&rodata_test_data,
(void *)&zero, sizeof(zero))) {
pr_err("test data was not read only\n");
return;
return get_freepointer(s, object);
freepointer_addr = (unsigned long)object + s->offset;
- probe_kernel_read(&p, (void **)freepointer_addr, sizeof(p));
+ copy_from_kernel_nofault(&p, (void **)freepointer_addr, sizeof(p));
return freelist_ptr(s, p, freepointer_addr);
}
if (tcp_ooo_try_coalesce(sk, tp->ooo_last_skb,
skb, &fragstolen)) {
coalesce_done:
- tcp_grow_window(sk, skb);
+ /* For non sack flows, do not grow window to force DUPACK
+ * and trigger fast retransmit.
+ */
+ if (tcp_is_sack(tp))
+ tcp_grow_window(sk, skb);
kfree_skb_partial(skb, fragstolen);
skb = NULL;
goto add_sack;
tcp_sack_new_ofo_skb(sk, seq, end_seq);
end:
if (skb) {
- tcp_grow_window(sk, skb);
+ /* For non sack flows, do not grow window to force DUPACK
+ * and trigger fast retransmit.
+ */
+ if (tcp_is_sack(tp))
+ tcp_grow_window(sk, skb);
skb_condense(skb);
skb_set_owner_r(skb, sk);
}
idev->mc_list = i->next;
write_unlock_bh(&idev->lock);
+ ip6_mc_clear_src(i);
ma_put(i);
write_lock_bh(&idev->lock);
}
((nib & 0xF) << 8) | field);
}
-#define MPTCP_PM_MAX_ADDR 4
-
struct mptcp_addr_info {
sa_family_t family;
__be16 port;
{
struct mptcp_sock *msk = mptcp_sk(sk);
- if (list_empty(&msk->rtx_queue))
- return NULL;
-
- return list_first_entry(&msk->rtx_queue, struct mptcp_data_frag, list);
+ return list_first_entry_or_null(&msk->rtx_queue, struct mptcp_data_frag, list);
}
struct mptcp_subflow_request_sock {
err = tcp_set_ulp(sf->sk, "mptcp");
release_sock(sf->sk);
- if (err)
+ if (err) {
+ sock_release(sf);
return err;
+ }
/* the newly created socket really belongs to the owning MPTCP master
* socket, even if for additional subflows the allocation is performed
filter->mark.mask = 0xffffffff;
}
} else if (cda[CTA_MARK_MASK]) {
- return ERR_PTR(-EINVAL);
+ err = -EINVAL;
+ goto err_filter;
}
#endif
if (!cda[CTA_FILTER])
err = ctnetlink_parse_zone(cda[CTA_ZONE], &filter->zone);
if (err < 0)
- return ERR_PTR(err);
+ goto err_filter;
err = ctnetlink_parse_filter(cda[CTA_FILTER], filter);
if (err < 0)
- return ERR_PTR(err);
+ goto err_filter;
if (filter->orig_flags) {
- if (!cda[CTA_TUPLE_ORIG])
- return ERR_PTR(-EINVAL);
+ if (!cda[CTA_TUPLE_ORIG]) {
+ err = -EINVAL;
+ goto err_filter;
+ }
err = ctnetlink_parse_tuple_filter(cda, &filter->orig,
CTA_TUPLE_ORIG,
&filter->zone,
filter->orig_flags);
if (err < 0)
- return ERR_PTR(err);
+ goto err_filter;
}
if (filter->reply_flags) {
- if (!cda[CTA_TUPLE_REPLY])
- return ERR_PTR(-EINVAL);
+ if (!cda[CTA_TUPLE_REPLY]) {
+ err = -EINVAL;
+ goto err_filter;
+ }
err = ctnetlink_parse_tuple_filter(cda, &filter->reply,
CTA_TUPLE_REPLY,
filter->family,
&filter->zone,
filter->orig_flags);
- if (err < 0)
- return ERR_PTR(err);
+ if (err < 0) {
+ err = -EINVAL;
+ goto err_filter;
+ }
}
return filter;
+
+err_filter:
+ kfree(filter);
+
+ return ERR_PTR(err);
}
static bool ctnetlink_needs_filter(u8 family, const struct nlattr * const *cda)
queue_delayed_work(system_power_efficient_wq, &flow_table->gc_work, HZ);
}
-int nf_flow_table_offload_add_cb(struct nf_flowtable *flow_table,
- flow_setup_cb_t *cb, void *cb_priv)
-{
- struct flow_block *block = &flow_table->flow_block;
- struct flow_block_cb *block_cb;
- int err = 0;
-
- down_write(&flow_table->flow_block_lock);
- block_cb = flow_block_cb_lookup(block, cb, cb_priv);
- if (block_cb) {
- err = -EEXIST;
- goto unlock;
- }
-
- block_cb = flow_block_cb_alloc(cb, cb_priv, cb_priv, NULL);
- if (IS_ERR(block_cb)) {
- err = PTR_ERR(block_cb);
- goto unlock;
- }
-
- list_add_tail(&block_cb->list, &block->cb_list);
-
-unlock:
- up_write(&flow_table->flow_block_lock);
- return err;
-}
-EXPORT_SYMBOL_GPL(nf_flow_table_offload_add_cb);
-
-void nf_flow_table_offload_del_cb(struct nf_flowtable *flow_table,
- flow_setup_cb_t *cb, void *cb_priv)
-{
- struct flow_block *block = &flow_table->flow_block;
- struct flow_block_cb *block_cb;
-
- down_write(&flow_table->flow_block_lock);
- block_cb = flow_block_cb_lookup(block, cb, cb_priv);
- if (block_cb) {
- list_del(&block_cb->list);
- flow_block_cb_free(block_cb);
- } else {
- WARN_ON(true);
- }
- up_write(&flow_table->flow_block_lock);
-}
-EXPORT_SYMBOL_GPL(nf_flow_table_offload_del_cb);
static int nf_flow_nat_port_tcp(struct sk_buff *skb, unsigned int thoff,
__be16 port, __be16 new_port)
return err;
}
+static void nft_flowtable_hook_release(struct nft_flowtable_hook *flowtable_hook)
+{
+ struct nft_hook *this, *next;
+
+ list_for_each_entry_safe(this, next, &flowtable_hook->list, list) {
+ list_del(&this->list);
+ kfree(this);
+ }
+}
+
static int nft_delflowtable_hook(struct nft_ctx *ctx,
struct nft_flowtable *flowtable)
{
const struct nlattr * const *nla = ctx->nla;
struct nft_flowtable_hook flowtable_hook;
- struct nft_hook *this, *next, *hook;
+ struct nft_hook *this, *hook;
struct nft_trans *trans;
int err;
if (err < 0)
return err;
- list_for_each_entry_safe(this, next, &flowtable_hook.list, list) {
+ list_for_each_entry(this, &flowtable_hook.list, list) {
hook = nft_hook_list_find(&flowtable->hook_list, this);
if (!hook) {
err = -ENOENT;
goto err_flowtable_del_hook;
}
hook->inactive = true;
- list_del(&this->list);
- kfree(this);
}
trans = nft_trans_alloc(ctx, NFT_MSG_DELFLOWTABLE,
sizeof(struct nft_trans_flowtable));
- if (!trans)
- return -ENOMEM;
+ if (!trans) {
+ err = -ENOMEM;
+ goto err_flowtable_del_hook;
+ }
nft_trans_flowtable(trans) = flowtable;
nft_trans_flowtable_update(trans) = true;
INIT_LIST_HEAD(&nft_trans_flowtable_hooks(trans));
+ nft_flowtable_hook_release(&flowtable_hook);
list_add_tail(&trans->list, &ctx->net->nft.commit_list);
return 0;
err_flowtable_del_hook:
- list_for_each_entry(hook, &flowtable_hook.list, list)
+ list_for_each_entry(this, &flowtable_hook.list, list) {
+ hook = nft_hook_list_find(&flowtable->hook_list, this);
+ if (!hook)
+ break;
+
hook->inactive = false;
+ }
+ nft_flowtable_hook_release(&flowtable_hook);
return err;
}
end += NFT_PIPAPO_GROUPS_PADDED_SIZE(f);
}
- if (!*this_cpu_ptr(m->scratch) || bsize_max > m->bsize_max) {
+ if (!*get_cpu_ptr(m->scratch) || bsize_max > m->bsize_max) {
+ put_cpu_ptr(m->scratch);
+
err = pipapo_realloc_scratch(m, bsize_max);
if (err)
return err;
this_cpu_write(nft_pipapo_scratch_index, false);
m->bsize_max = bsize_max;
+ } else {
+ put_cpu_ptr(m->scratch);
}
*ext2 = &e->ext;
if (nft_rbtree_interval_start(new)) {
if (nft_rbtree_interval_end(rbe) &&
- nft_set_elem_active(&rbe->ext, genmask))
+ nft_set_elem_active(&rbe->ext, genmask) &&
+ !nft_set_elem_expired(&rbe->ext))
overlap = false;
} else {
overlap = nft_rbtree_interval_end(rbe) &&
nft_set_elem_active(&rbe->ext,
- genmask);
+ genmask) &&
+ !nft_set_elem_expired(&rbe->ext);
}
} else if (d > 0) {
p = &parent->rb_right;
if (nft_rbtree_interval_end(new)) {
overlap = nft_rbtree_interval_end(rbe) &&
nft_set_elem_active(&rbe->ext,
- genmask);
+ genmask) &&
+ !nft_set_elem_expired(&rbe->ext);
} else if (nft_rbtree_interval_end(rbe) &&
- nft_set_elem_active(&rbe->ext, genmask)) {
+ nft_set_elem_active(&rbe->ext, genmask) &&
+ !nft_set_elem_expired(&rbe->ext)) {
overlap = true;
}
} else {
nft_rbtree_interval_start(new)) {
p = &parent->rb_left;
- if (nft_set_elem_active(&rbe->ext, genmask))
+ if (nft_set_elem_active(&rbe->ext, genmask) &&
+ !nft_set_elem_expired(&rbe->ext))
overlap = false;
} else if (nft_rbtree_interval_start(rbe) &&
nft_rbtree_interval_end(new)) {
p = &parent->rb_right;
- if (nft_set_elem_active(&rbe->ext, genmask))
+ if (nft_set_elem_active(&rbe->ext, genmask) &&
+ !nft_set_elem_expired(&rbe->ext))
overlap = false;
- } else if (nft_set_elem_active(&rbe->ext, genmask)) {
+ } else if (nft_set_elem_active(&rbe->ext, genmask) &&
+ !nft_set_elem_expired(&rbe->ext)) {
*ext = &rbe->ext;
return -EEXIST;
} else {
int *vector_load;
};
-#define ibdev_to_node(ibdev) dev_to_node((ibdev)->dev.parent)
+static inline int ibdev_to_node(struct ib_device *ibdev)
+{
+ struct device *parent;
+
+ parent = ibdev->dev.parent;
+ return parent ? dev_to_node(parent) : NUMA_NO_NODE;
+}
#define rdsibdev_to_node(rdsibdev) ibdev_to_node(rdsibdev->dev)
/* bits for i_ack_flags */
destroy_workqueue(act_ct_wq);
}
-void tcf_ct_flow_table_restore_skb(struct sk_buff *skb, unsigned long cookie)
-{
- enum ip_conntrack_info ctinfo = cookie & NFCT_INFOMASK;
- struct nf_conn *ct;
-
- ct = (struct nf_conn *)(cookie & NFCT_PTRMASK);
- nf_conntrack_get(&ct->ct_general);
- nf_ct_set(skb, ct, ctinfo);
-}
-EXPORT_SYMBOL_GPL(tcf_ct_flow_table_restore_skb);
-
module_init(ct_init_module);
module_exit(ct_cleanup_module);
MODULE_AUTHOR("Paul Blakey <paulb@mellanox.com>");
struct amt_host_if_resp_header {
struct amt_host_if_msg_header header;
uint32_t status;
- unsigned char data[0];
+ unsigned char data[];
} __attribute__((packed));
const uuid_le MEI_IAMTHIF = UUID_LE(0x12f80028, 0xb4b7, 0x4b2d, \
elif [[ "${modcache[$module]+isset}" == "isset" ]]; then
local objfile=${modcache[$module]}
else
- [[ $modpath == "" ]] && return
+ if [[ $modpath == "" ]]; then
+ echo "WARNING! Modules path isn't set, but is needed to parse this symbol" >&2
+ return
+ fi
local objfile=$(find "$modpath" -name "${module//_/[-_]}.ko*" -print -quit)
[[ $objfile == "" ]] && return
modcache[$module]=$objfile
} ng;
u8 data[2];
} xattr;
- u8 digest[0];
+ u8 digest[];
} __packed;
/*
uint8_t hash_algo; /* Digest algorithm [enum hash_algo] */
__be32 keyid; /* IMA key identifier - not X509/PGP specific */
__be16 sig_size; /* signature size */
- uint8_t sig[0]; /* signature payload */
+ uint8_t sig[]; /* signature payload */
} __packed;
/* integrity data associated with an inode */
struct sof_ipc_probe_dma_add_params {
struct sof_ipc_cmd_hdr hdr;
unsigned int num_elems;
- struct sof_probe_dma dma[0];
+ struct sof_probe_dma dma[];
} __packed;
struct sof_ipc_probe_info_params {
struct sof_ipc_probe_dma_remove_params {
struct sof_ipc_cmd_hdr hdr;
unsigned int num_elems;
- unsigned int stream_tag[0];
+ unsigned int stream_tag[];
} __packed;
struct sof_ipc_probe_point_add_params {
struct sof_ipc_cmd_hdr hdr;
unsigned int num_elems;
- struct sof_probe_point_desc desc[0];
+ struct sof_probe_point_desc desc[];
} __packed;
struct sof_ipc_probe_point_remove_params {
struct sof_ipc_cmd_hdr hdr;
unsigned int num_elems;
- unsigned int buffer_id[0];
+ unsigned int buffer_id[];
} __packed;
int sof_ipc_probe_init(struct snd_sof_dev *sdev,
#define X86_FEATURE_AVX512_4FMAPS (18*32+ 3) /* AVX-512 Multiply Accumulation Single precision */
#define X86_FEATURE_FSRM (18*32+ 4) /* Fast Short Rep Mov */
#define X86_FEATURE_AVX512_VP2INTERSECT (18*32+ 8) /* AVX-512 Intersect for D/Q */
+#define X86_FEATURE_SRBDS_CTRL (18*32+ 9) /* "" SRBDS mitigation MSR available */
#define X86_FEATURE_MD_CLEAR (18*32+10) /* VERW clears CPU buffers */
#define X86_FEATURE_TSX_FORCE_ABORT (18*32+13) /* "" TSX_FORCE_ABORT */
#define X86_FEATURE_PCONFIG (18*32+18) /* Intel PCONFIG */
#define X86_BUG_SWAPGS X86_BUG(21) /* CPU is affected by speculation through SWAPGS */
#define X86_BUG_TAA X86_BUG(22) /* CPU is affected by TSX Async Abort(TAA) */
#define X86_BUG_ITLB_MULTIHIT X86_BUG(23) /* CPU may incur MCE during certain page attribute changes */
+#define X86_BUG_SRBDS X86_BUG(24) /* CPU may leak RNG bits if not mitigated */
#endif /* _ASM_X86_CPUFEATURES_H */
#define TSX_CTRL_RTM_DISABLE BIT(0) /* Disable RTM feature */
#define TSX_CTRL_CPUID_CLEAR BIT(1) /* Disable TSX enumeration */
+/* SRBDS support */
+#define MSR_IA32_MCU_OPT_CTRL 0x00000123
+#define RNGDS_MITG_DIS BIT(0)
+
#define MSR_IA32_SYSENTER_CS 0x00000174
#define MSR_IA32_SYSENTER_ESP 0x00000175
#define MSR_IA32_SYSENTER_EIP 0x00000176
#define KVM_X86_QUIRK_MISC_ENABLE_NO_MWAIT (1 << 4)
#define KVM_STATE_NESTED_FORMAT_VMX 0
-#define KVM_STATE_NESTED_FORMAT_SVM 1 /* unused */
+#define KVM_STATE_NESTED_FORMAT_SVM 1
#define KVM_STATE_NESTED_GUEST_MODE 0x00000001
#define KVM_STATE_NESTED_RUN_PENDING 0x00000002
#define KVM_STATE_NESTED_EVMCS 0x00000004
#define KVM_STATE_NESTED_MTF_PENDING 0x00000008
+#define KVM_STATE_NESTED_GIF_SET 0x00000100
#define KVM_STATE_NESTED_SMM_GUEST_MODE 0x00000001
#define KVM_STATE_NESTED_SMM_VMXON 0x00000002
#define KVM_STATE_NESTED_VMX_VMCS_SIZE 0x1000
+#define KVM_STATE_NESTED_SVM_VMCB_SIZE 0x1000
+
+#define KVM_STATE_VMX_PREEMPTION_TIMER_DEADLINE 0x00000001
+
struct kvm_vmx_nested_state_data {
__u8 vmcs12[KVM_STATE_NESTED_VMX_VMCS_SIZE];
__u8 shadow_vmcs12[KVM_STATE_NESTED_VMX_VMCS_SIZE];
- __u64 preemption_timer_deadline;
};
struct kvm_vmx_nested_state_hdr {
+ __u32 flags;
__u64 vmxon_pa;
__u64 vmcs12_pa;
+ __u64 preemption_timer_deadline;
struct {
__u16 flags;
} smm;
};
+struct kvm_svm_nested_state_data {
+ /* Save area only used if KVM_STATE_NESTED_RUN_PENDING. */
+ __u8 vmcb12[KVM_STATE_NESTED_SVM_VMCB_SIZE];
+};
+
+struct kvm_svm_nested_state_hdr {
+ __u64 vmcb_pa;
+};
+
/* for KVM_CAP_NESTED_STATE */
struct kvm_nested_state {
__u16 flags;
union {
struct kvm_vmx_nested_state_hdr vmx;
+ struct kvm_svm_nested_state_hdr svm;
/* Pad the header to 128 bytes. */
__u8 pad[120];
*/
union {
struct kvm_vmx_nested_state_data vmx[0];
+ struct kvm_svm_nested_state_data svm[0];
} data;
};
#ifndef _UAPI_ASM_X86_UNISTD_H
#define _UAPI_ASM_X86_UNISTD_H
-/* x32 syscall flag bit */
+/*
+ * x32 syscall flag bit. Some user programs expect syscall NR macros
+ * and __X32_SYSCALL_BIT to have type int, even though syscall numbers
+ * are, for practical purposes, unsigned long.
+ *
+ * Fortunately, expressions like (nr & ~__X32_SYSCALL_BIT) do the right
+ * thing regardless.
+ */
#define __X32_SYSCALL_BIT 0x40000000
#ifndef __KERNEL__
{ EXIT_REASON_UMWAIT, "UMWAIT" }, \
{ EXIT_REASON_TPAUSE, "TPAUSE" }
+#define VMX_EXIT_REASON_FLAGS \
+ { VMX_EXIT_REASONS_FAILED_VMENTRY, "FAILED_VMENTRY" }
+
#define VMX_ABORT_SAVE_GUEST_MSR_FAIL 1
#define VMX_ABORT_LOAD_HOST_PDPTE_FAIL 2
#define VMX_ABORT_LOAD_HOST_MSR_FAIL 4
__SYSCALL(__NR_openat2, sys_openat2)
#define __NR_pidfd_getfd 438
__SYSCALL(__NR_pidfd_getfd, sys_pidfd_getfd)
+#define __NR_faccessat2 439
+__SYSCALL(__NR_faccessat2, sys_faccessat2)
#undef __NR_syscalls
-#define __NR_syscalls 439
+#define __NR_syscalls 440
/*
* 32 bit systems traditionally used different
*/
DRM_I915_PERF_PROP_HOLD_PREEMPTION,
+ /**
+ * Specifying this pins all contexts to the specified SSEU power
+ * configuration for the duration of the recording.
+ *
+ * This parameter's value is a pointer to a struct
+ * drm_i915_gem_context_param_sseu.
+ *
+ * This property is available in perf revision 4.
+ */
+ DRM_I915_PERF_PROP_GLOBAL_SSEU,
+
+ /**
+ * This optional parameter specifies the timer interval in nanoseconds
+ * at which the i915 driver will check the OA buffer for available data.
+ * Minimum allowed value is 100 microseconds. A default value is used by
+ * the driver if this parameter is not specified. Note that larger timer
+ * values will reduce cpu consumption during OA perf captures. However,
+ * excessively large values would potentially result in OA buffer
+ * overwrites as captures reach end of the OA buffer.
+ *
+ * This property is available in perf revision 5.
+ */
+ DRM_I915_PERF_PROP_POLL_OA_PERIOD,
+
DRM_I915_PERF_PROP_MAX /* non-ABI */
};
#define DN_ATTRIB 0x00000020 /* File changed attibutes */
#define DN_MULTISHOT 0x80000000 /* Don't remove notifier */
+/*
+ * The constants AT_REMOVEDIR and AT_EACCESS have the same value. AT_EACCESS is
+ * meaningful only to faccessat, while AT_REMOVEDIR is meaningful only to
+ * unlinkat. The two functions do completely different things and therefore,
+ * the flags can be allowed to overlap. For example, passing AT_REMOVEDIR to
+ * faccessat would be undefined behavior and thus treating it equivalent to
+ * AT_EACCESS is valid undefined behavior.
+ */
#define AT_FDCWD -100 /* Special value used to indicate
openat should use the current
working directory. */
#define AT_SYMLINK_NOFOLLOW 0x100 /* Do not follow symbolic links. */
+#define AT_EACCESS 0x200 /* Test access permitted for
+ effective IDs, not real IDs. */
#define AT_REMOVEDIR 0x200 /* Remove directory instead of
unlinking file. */
#define AT_SYMLINK_FOLLOW 0x400 /* Follow symbolic links. */
#define FS_EA_INODE_FL 0x00200000 /* Inode used for large EA */
#define FS_EOFBLOCKS_FL 0x00400000 /* Reserved for ext4 */
#define FS_NOCOW_FL 0x00800000 /* Do not cow file */
+#define FS_DAX_FL 0x02000000 /* Inode is DAX */
#define FS_INLINE_DATA_FL 0x10000000 /* Reserved for ext4 */
#define FS_PROJINHERIT_FL 0x20000000 /* Create with parents projid */
#define FS_CASEFOLD_FL 0x40000000 /* Folder is case insensitive */
#define FSCRYPT_POLICY_FLAGS_PAD_MASK 0x03
#define FSCRYPT_POLICY_FLAG_DIRECT_KEY 0x04
#define FSCRYPT_POLICY_FLAG_IV_INO_LBLK_64 0x08
-#define FSCRYPT_POLICY_FLAGS_VALID 0x0F
+#define FSCRYPT_POLICY_FLAG_IV_INO_LBLK_32 0x10
+#define FSCRYPT_POLICY_FLAGS_VALID 0x1F
/* Encryption algorithms */
#define FSCRYPT_MODE_AES_256_XTS 1
struct kvm_hyperv_exit {
#define KVM_EXIT_HYPERV_SYNIC 1
#define KVM_EXIT_HYPERV_HCALL 2
+#define KVM_EXIT_HYPERV_SYNDBG 3
__u32 type;
+ __u32 pad1;
union {
struct {
__u32 msr;
+ __u32 pad2;
__u64 control;
__u64 evt_page;
__u64 msg_page;
__u64 result;
__u64 params[2];
} hcall;
+ struct {
+ __u32 msr;
+ __u32 pad2;
+ __u64 control;
+ __u64 status;
+ __u64 send_page;
+ __u64 recv_page;
+ __u64 pending_page;
+ } syndbg;
} u;
};
#define KVM_CAP_S390_VCPU_RESETS 179
#define KVM_CAP_S390_PROTECTED 180
#define KVM_CAP_PPC_SECURE_GUEST 181
+#define KVM_CAP_HALT_POLL 182
+#define KVM_CAP_ASYNC_PF_INT 183
#ifdef KVM_CAP_IRQ_ROUTING
__u32 stx_dev_major; /* ID of device containing file [uncond] */
__u32 stx_dev_minor;
/* 0x90 */
- __u64 __spare2[14]; /* Spare space for future expansion */
+ __u64 stx_mnt_id;
+ __u64 __spare2;
+ /* 0xa0 */
+ __u64 __spare3[12]; /* Spare space for future expansion */
/* 0x100 */
};
#define STATX_BLOCKS 0x00000400U /* Want/got stx_blocks */
#define STATX_BASIC_STATS 0x000007ffU /* The stuff in the normal stat struct */
#define STATX_BTIME 0x00000800U /* Want/got stx_btime */
+#define STATX_MNT_ID 0x00001000U /* Got stx_mnt_id */
#define STATX__RESERVED 0x80000000U /* Reserved for future struct statx expansion */
#define STATX_ATTR_NODUMP 0x00000040 /* [I] File is not to be dumped */
#define STATX_ATTR_ENCRYPTED 0x00000800 /* [I] File requires key to decrypt in fs */
#define STATX_ATTR_AUTOMOUNT 0x00001000 /* Dir: Automount trigger */
+#define STATX_ATTR_MOUNT_ROOT 0x00002000 /* Root of a mount */
#define STATX_ATTR_VERITY 0x00100000 /* [I] Verity protected file */
+#define STATX_ATTR_DAX 0x00002000 /* [I] File is DAX */
#endif /* _UAPI_LINUX_STAT_H */
#include <linux/types.h>
#include <linux/ioctl.h>
+#define VHOST_FILE_UNBIND -1
+
/* ioctls */
#define VHOST_VIRTIO 0xAF
/* Get the max ring size. */
#define VHOST_VDPA_GET_VRING_NUM _IOR(VHOST_VIRTIO, 0x76, __u16)
+/* Set event fd for config interrupt*/
+#define VHOST_VDPA_SET_CONFIG_CALL _IOW(VHOST_VIRTIO, 0x77, int)
#endif
return 0;
}
+static int append(char **buf, const char *delim, const char *str)
+{
+ char *new_buf;
+
+ new_buf = realloc(*buf, strlen(*buf) + strlen(delim) + strlen(str) + 1);
+ if (!new_buf)
+ return -1;
+ strcat(new_buf, delim);
+ strcat(new_buf, str);
+ *buf = new_buf;
+ return 0;
+}
+
static int event_read_fields(struct tep_event *event, struct tep_format_field **fields)
{
struct tep_format_field *field = NULL;
enum tep_event_type type;
char *token;
char *last_token;
+ char *delim = " ";
int count = 0;
+ int ret;
do {
unsigned int size_dynamic = 0;
field->flags |= TEP_FIELD_IS_POINTER;
if (field->type) {
- char *new_type;
- new_type = realloc(field->type,
- strlen(field->type) +
- strlen(last_token) + 2);
- if (!new_type) {
- free(last_token);
- goto fail;
- }
- field->type = new_type;
- strcat(field->type, " ");
- strcat(field->type, last_token);
+ ret = append(&field->type, delim, last_token);
free(last_token);
+ if (ret < 0)
+ goto fail;
} else
field->type = last_token;
last_token = token;
+ delim = " ";
continue;
}
+ /* Handle __attribute__((user)) */
+ if ((type == TEP_EVENT_DELIM) &&
+ strcmp("__attribute__", last_token) == 0 &&
+ token[0] == '(') {
+ int depth = 1;
+ int ret;
+
+ ret = append(&field->type, " ", last_token);
+ ret |= append(&field->type, "", "(");
+ if (ret < 0)
+ goto fail;
+
+ delim = " ";
+ while ((type = read_token(&token)) != TEP_EVENT_NONE) {
+ if (type == TEP_EVENT_DELIM) {
+ if (token[0] == '(')
+ depth++;
+ else if (token[0] == ')')
+ depth--;
+ if (!depth)
+ break;
+ ret = append(&field->type, "", token);
+ delim = "";
+ } else {
+ ret = append(&field->type, delim, token);
+ delim = " ";
+ }
+ if (ret < 0)
+ goto fail;
+ free(last_token);
+ last_token = token;
+ }
+ continue;
+ }
break;
}
if (strcmp(token, "[") == 0) {
enum tep_event_type last_type = type;
char *brackets = token;
- char *new_brackets;
- int len;
field->flags |= TEP_FIELD_IS_ARRAY;
field->arraylen = 0;
while (strcmp(token, "]") != 0) {
+ const char *delim;
+
if (last_type == TEP_EVENT_ITEM &&
type == TEP_EVENT_ITEM)
- len = 2;
+ delim = " ";
else
- len = 1;
+ delim = "";
+
last_type = type;
- new_brackets = realloc(brackets,
- strlen(brackets) +
- strlen(token) + len);
- if (!new_brackets) {
+ ret = append(&brackets, delim, token);
+ if (ret < 0) {
free(brackets);
goto fail;
}
- brackets = new_brackets;
- if (len == 2)
- strcat(brackets, " ");
- strcat(brackets, token);
/* We only care about the last token */
field->arraylen = strtoul(token, NULL, 0);
free_token(token);
type = read_token(&token);
if (type == TEP_EVENT_NONE) {
+ free(brackets);
do_warning_event(event, "failed to find token");
goto fail;
}
free_token(token);
- new_brackets = realloc(brackets, strlen(brackets) + 2);
- if (!new_brackets) {
+ ret = append(&brackets, "", "]");
+ if (ret < 0) {
free(brackets);
goto fail;
}
- brackets = new_brackets;
- strcat(brackets, "]");
/* add brackets to type */
* the format: type [] item;
*/
if (type == TEP_EVENT_ITEM) {
- char *new_type;
- new_type = realloc(field->type,
- strlen(field->type) +
- strlen(field->name) +
- strlen(brackets) + 2);
- if (!new_type) {
+ ret = append(&field->type, " ", field->name);
+ if (ret < 0) {
free(brackets);
goto fail;
}
- field->type = new_type;
- strcat(field->type, " ");
- strcat(field->type, field->name);
+ ret = append(&field->type, "", brackets);
+
size_dynamic = type_size(field->name);
free_token(field->name);
- strcat(field->type, brackets);
field->name = field->alias = token;
type = read_token(&token);
} else {
- char *new_type;
- new_type = realloc(field->type,
- strlen(field->type) +
- strlen(brackets) + 1);
- if (!new_type) {
+ ret = append(&field->type, "", brackets);
+ if (ret < 0) {
free(brackets);
goto fail;
}
- field->type = new_type;
- strcat(field->type, brackets);
}
free(brackets);
}
/* could just be a type pointer */
if ((strcmp(arg->op.op, "*") == 0) &&
type == TEP_EVENT_DELIM && (strcmp(token, ")") == 0)) {
- char *new_atom;
+ int ret;
if (left->type != TEP_PRINT_ATOM) {
do_warning_event(event, "bad pointer type");
goto out_free;
}
- new_atom = realloc(left->atom.atom,
- strlen(left->atom.atom) + 3);
- if (!new_atom)
+ ret = append(&left->atom.atom, " ", "*");
+ if (ret < 0)
goto out_warn_free;
- left->atom.atom = new_atom;
- strcat(left->atom.atom, " *");
free(arg->op.op);
*arg = *left;
free(left);
return TEP_EVENT_ERROR;
}
+static enum tep_event_type
+process_builtin_expect(struct tep_event *event, struct tep_print_arg *arg, char **tok)
+{
+ enum tep_event_type type;
+ char *token = NULL;
+
+ /* Handle __builtin_expect( cond, #) */
+ type = process_arg(event, arg, &token);
+
+ if (type != TEP_EVENT_DELIM || token[0] != ',')
+ goto out_free;
+
+ free_token(token);
+
+ /* We don't care what the second parameter is of the __builtin_expect() */
+ if (read_expect_type(TEP_EVENT_ITEM, &token) < 0)
+ goto out_free;
+
+ if (read_expected(TEP_EVENT_DELIM, ")") < 0)
+ goto out_free;
+
+ free_token(token);
+ type = read_token_item(tok);
+ return type;
+
+out_free:
+ free_token(token);
+ *tok = NULL;
+ return TEP_EVENT_ERROR;
+}
+
static enum tep_event_type
process_function(struct tep_event *event, struct tep_print_arg *arg,
char *token, char **tok)
free_token(token);
return process_dynamic_array_len(event, arg, tok);
}
+ if (strcmp(token, "__builtin_expect") == 0) {
+ free_token(token);
+ return process_builtin_expect(event, arg, tok);
+ }
func = find_func_handler(event->tep, token);
if (func) {
}
/* atoms can be more than one token long */
while (type == TEP_EVENT_ITEM) {
- char *new_atom;
- new_atom = realloc(atom,
- strlen(atom) + strlen(token) + 2);
- if (!new_atom) {
+ int ret;
+
+ ret = append(&atom, " ", token);
+ if (ret < 0) {
free(atom);
*tok = NULL;
free_token(token);
return TEP_EVENT_ERROR;
}
- atom = new_atom;
- strcat(atom, " ");
- strcat(atom, token);
free_token(token);
type = read_token_item(&token);
}
NO_LIBBPF := 1
NO_JVMTI := 1
else
+ ifneq ($(filter s% -fsanitize=address%,$(EXTRA_CFLAGS),),)
+ ifneq ($(shell ldconfig -p | grep libasan >/dev/null 2>&1; echo $$?), 0)
+ msg := $(error No libasan found, please install libasan);
+ endif
+ endif
+
+ ifneq ($(filter s% -fsanitize=undefined%,$(EXTRA_CFLAGS),),)
+ ifneq ($(shell ldconfig -p | grep libubsan >/dev/null 2>&1; echo $$?), 0)
+ msg := $(error No libubsan found, please install libubsan);
+ endif
+ endif
+
ifneq ($(filter s% -static%,$(LDFLAGS),),)
msg := $(error No static glibc found, please install glibc-static);
else
435 common clone3 sys_clone3
437 common openat2 sys_openat2
438 common pidfd_getfd sys_pidfd_getfd
+439 common faccessat2 sys_faccessat2
#
# x32-specific system call numbers start at 512 to avoid cache impact
if (rep->time_str)
ret += fprintf(fp, " (time slices: %s)", rep->time_str);
- if (symbol_conf.show_ref_callgraph &&
- strstr(evname, "call-graph=no")) {
+ if (symbol_conf.show_ref_callgraph && evname && strstr(evname, "call-graph=no")) {
ret += fprintf(fp, ", show reference callgraph");
}
if (err)
goto out_delete;
+ if (zstd_init(&(session->zstd_data), 0) < 0)
+ pr_warning("Decompression initialization failed. Reported data may be incomplete.\n");
+
err = __cmd_script(&script);
flush_scripting();
P_FLAG(SIZE);
P_FLAG(BLOCKS);
P_FLAG(BTIME);
+ P_FLAG(MNT_ID);
#undef P_FLAG
gen_read_mem(struct bpf_insn_pos *pos,
int src_base_addr_reg,
int dst_addr_reg,
- long offset)
+ long offset,
+ int probeid)
{
/* mov arg3, src_base_addr_reg */
if (src_base_addr_reg != BPF_REG_ARG3)
ins(BPF_MOV64_REG(BPF_REG_ARG1, dst_addr_reg), pos);
/* Call probe_read */
- ins(BPF_EMIT_CALL(BPF_FUNC_probe_read), pos);
+ ins(BPF_EMIT_CALL(probeid), pos);
/*
* Error processing: if read fail, goto error code,
* will be relocated. Target should be the start of
gen_prologue_slowpath(struct bpf_insn_pos *pos,
struct probe_trace_arg *args, int nargs)
{
- int err, i;
+ int err, i, probeid;
for (i = 0; i < nargs; i++) {
struct probe_trace_arg *arg = &args[i];
stack_offset), pos);
ref = arg->ref;
+ probeid = BPF_FUNC_probe_read_kernel;
while (ref) {
pr_debug("prologue: arg %d: offset %ld\n",
i, ref->offset);
+
+ if (ref->user_access)
+ probeid = BPF_FUNC_probe_read_user;
+
err = gen_read_mem(pos, BPF_REG_3, BPF_REG_7,
- ref->offset);
+ ref->offset, probeid);
if (err) {
pr_err("prologue: failed to generate probe_read function call\n");
goto errout;
YYABORT; \
} while (0)
-static struct list_head* alloc_list()
+static struct list_head* alloc_list(void)
{
struct list_head *list;
struct list_head *list;
char pmu_name[128];
- snprintf(&pmu_name, 128, "%s-%s", $1, $3);
+ snprintf(pmu_name, sizeof(pmu_name), "%s-%s", $1, $3);
free($1);
free($3);
if (parse_events_multi_pmu_add(_parse_state, pmu_name, &list) < 0)
struct perf_pmu_info *info);
struct list_head *perf_pmu__alias(struct perf_pmu *pmu,
struct list_head *head_terms);
-int perf_pmu_wrap(void);
void perf_pmu_error(struct list_head *list, char *name, char const *msg);
int perf_pmu__new_format(struct list_head *list, char *name,
}
tmp = strchr(str, '@');
- if (tmp && tmp != str && strcmp(tmp + 1, "user")) { /* user attr */
+ if (tmp && tmp != str && !strcmp(tmp + 1, "user")) { /* user attr */
if (!user_access_is_supported()) {
semantic_error("ftrace does not support user access\n");
return -EINVAL;
if (depth < 0)
return depth;
}
- err = strbuf_addf(buf, "%+ld(", ref->offset);
+ if (ref->user_access)
+ err = strbuf_addf(buf, "%s%ld(", "+u", ref->offset);
+ else
+ err = strbuf_addf(buf, "%+ld(", ref->offset);
return (err < 0) ? err : depth;
}
DEFINE_TYPE(FTRACE_README_PROBE_TYPE_X, "*type: * x8/16/32/64,*"),
DEFINE_TYPE(FTRACE_README_KRETPROBE_OFFSET, "*place (kretprobe): *"),
DEFINE_TYPE(FTRACE_README_UPROBE_REF_CTR, "*ref_ctr_offset*"),
- DEFINE_TYPE(FTRACE_README_USER_ACCESS, "*[u]<offset>*"),
+ DEFINE_TYPE(FTRACE_README_USER_ACCESS, "*u]<offset>*"),
DEFINE_TYPE(FTRACE_README_MULTIPROBE_EVENT, "*Create/append/*"),
DEFINE_TYPE(FTRACE_README_IMMEDIATE_VALUE, "*\\imm-value,*"),
};
int s;
bool first;
- if (!(config->aggr_map || config->aggr_get_id))
+ if (!config->aggr_map || !config->aggr_get_id)
return;
aggr_update_shadow(config, evlist);
int s;
bool first = true;
- if (!(config->aggr_map || config->aggr_get_id))
+ if (!config->aggr_map || !config->aggr_get_id)
return;
if (config->percore_show_thread)
__u32 nfit_device_handle;
__u32 _reserved;
__u64 dpa;
- } __packed devices[0];
+ } __packed devices[];
} __packed;
struct nd_error_stat_query_record {
__u64 err_inj_stat_spa_range_base;
__u64 err_inj_stat_spa_range_length;
- } __packed record[0];
+ } __packed record[];
} __packed;
#define ND_INTEL_SMART 1
__u32 context;
__u32 offset;
__u32 length;
- __u8 data[0];
+ __u8 data[];
/* this field is not declared due ot variable data from input */
/* __u32 status; */
} __packed;